diff options
Diffstat (limited to 'fs')
46 files changed, 404 insertions, 312 deletions
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index b177fd3b1eb3..be5768949cb1 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -655,6 +655,8 @@ const struct file_operations v9fs_cached_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = v9fs_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -667,6 +669,8 @@ const struct file_operations v9fs_cached_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = v9fs_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; @@ -678,6 +682,8 @@ const struct file_operations v9fs_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = generic_file_readonly_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -690,6 +696,8 @@ const struct file_operations v9fs_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = generic_file_readonly_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; @@ -701,6 +709,8 @@ const struct file_operations v9fs_mmap_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = v9fs_mmap_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -713,5 +723,7 @@ const struct file_operations v9fs_mmap_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = v9fs_mmap_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; diff --git a/fs/afs/super.c b/fs/afs/super.c index 6c5900df6aa5..e38bb1e7a4d2 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -230,6 +230,9 @@ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param) _enter(",%s", name); + if (fc->source) + return invalf(fc, "kAFS: Multiple sources not supported"); + if (!name) { printk(KERN_ERR "kAFS: no volume name specified\n"); return -EINVAL; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index fa50e8936f5f..ac0b5fc30ea6 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1246,7 +1246,7 @@ out_free_interp: set_binfmt(&elf_format); #ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES - retval = arch_setup_additional_pages(bprm, !!interpreter); + retval = ARCH_SETUP_ADDITIONAL_PAGES(bprm, elf_ex, !!interpreter); if (retval < 0) goto out; #endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */ @@ -1307,7 +1307,7 @@ out_free_interp: #endif finalize_exec(bprm); - start_thread(regs, elf_entry, bprm->p); + START_THREAD(elf_ex, regs, elf_entry, bprm->p); retval = 0; out: return retval; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 28c1459fb0fc..44f9cce57099 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -4546,7 +4546,8 @@ static void set_root_ses(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, if (ses) { spin_lock(&cifs_tcp_ses_lock); ses->ses_count++; - ses->tcon_ipc->remap = cifs_remap(cifs_sb); + if (ses->tcon_ipc) + ses->tcon_ipc->remap = cifs_remap(cifs_sb); spin_unlock(&cifs_tcp_ses_lock); } *root_ses = ses; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index dab94f67c988..3d914d7d0d11 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3114,8 +3114,8 @@ smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon, rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE; rc = SMB2_ioctl_init(tcon, server, - &rqst[1], fid.persistent_fid, - fid.volatile_fid, FSCTL_GET_REPARSE_POINT, + &rqst[1], COMPOUND_FID, + COMPOUND_FID, FSCTL_GET_REPARSE_POINT, true /* is_fctl */, NULL, 0, CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 445e80862865..acb72705062d 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2272,17 +2272,15 @@ static struct crt_sd_ctxt * create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) { struct crt_sd_ctxt *buf; - struct cifs_ace *pace; - unsigned int sdlen, acelen; + __u8 *ptr, *aclptr; + unsigned int acelen, acl_size, ace_count; unsigned int owner_offset = 0; unsigned int group_offset = 0; + struct smb3_acl acl; - *len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 2), 8); + *len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8); if (set_owner) { - /* offset fields are from beginning of security descriptor not of create context */ - owner_offset = sizeof(struct smb3_acl) + (sizeof(struct cifs_ace) * 2); - /* sizeof(struct owner_group_sids) is already multiple of 8 so no need to round */ *len += sizeof(struct owner_group_sids); } @@ -2291,26 +2289,22 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) if (buf == NULL) return buf; + ptr = (__u8 *)&buf[1]; if (set_owner) { + /* offset fields are from beginning of security descriptor not of create context */ + owner_offset = ptr - (__u8 *)&buf->sd; buf->sd.OffsetOwner = cpu_to_le32(owner_offset); - group_offset = owner_offset + sizeof(struct owner_sid); + group_offset = owner_offset + offsetof(struct owner_group_sids, group); buf->sd.OffsetGroup = cpu_to_le32(group_offset); + + setup_owner_group_sids(ptr); + ptr += sizeof(struct owner_group_sids); } else { buf->sd.OffsetOwner = 0; buf->sd.OffsetGroup = 0; } - sdlen = sizeof(struct smb3_sd) + sizeof(struct smb3_acl) + - 2 * sizeof(struct cifs_ace); - if (set_owner) { - sdlen += sizeof(struct owner_group_sids); - setup_owner_group_sids(owner_offset + sizeof(struct create_context) + 8 /* name */ - + (char *)buf); - } - - buf->ccontext.DataOffset = cpu_to_le16(offsetof - (struct crt_sd_ctxt, sd)); - buf->ccontext.DataLength = cpu_to_le32(sdlen); + buf->ccontext.DataOffset = cpu_to_le16(offsetof(struct crt_sd_ctxt, sd)); buf->ccontext.NameOffset = cpu_to_le16(offsetof(struct crt_sd_ctxt, Name)); buf->ccontext.NameLength = cpu_to_le16(4); /* SMB2_CREATE_SD_BUFFER_TOKEN is "SecD" */ @@ -2319,6 +2313,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) buf->Name[2] = 'c'; buf->Name[3] = 'D'; buf->sd.Revision = 1; /* Must be one see MS-DTYP 2.4.6 */ + /* * ACL is "self relative" ie ACL is stored in contiguous block of memory * and "DP" ie the DACL is present @@ -2326,28 +2321,38 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) buf->sd.Control = cpu_to_le16(ACL_CONTROL_SR | ACL_CONTROL_DP); /* offset owner, group and Sbz1 and SACL are all zero */ - buf->sd.OffsetDacl = cpu_to_le32(sizeof(struct smb3_sd)); - buf->acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */ + buf->sd.OffsetDacl = cpu_to_le32(ptr - (__u8 *)&buf->sd); + /* Ship the ACL for now. we will copy it into buf later. */ + aclptr = ptr; + ptr += sizeof(struct cifs_acl); /* create one ACE to hold the mode embedded in reserved special SID */ - pace = (struct cifs_ace *)(sizeof(struct crt_sd_ctxt) + (char *)buf); - acelen = setup_special_mode_ACE(pace, (__u64)mode); + acelen = setup_special_mode_ACE((struct cifs_ace *)ptr, (__u64)mode); + ptr += acelen; + acl_size = acelen + sizeof(struct smb3_acl); + ace_count = 1; if (set_owner) { /* we do not need to reallocate buffer to add the two more ACEs. plenty of space */ - pace = (struct cifs_ace *)(acelen + (sizeof(struct crt_sd_ctxt) + (char *)buf)); - acelen += setup_special_user_owner_ACE(pace); - /* it does not appear necessary to add an ACE for the NFS group SID */ - buf->acl.AceCount = cpu_to_le16(3); - } else - buf->acl.AceCount = cpu_to_le16(2); + acelen = setup_special_user_owner_ACE((struct cifs_ace *)ptr); + ptr += acelen; + acl_size += acelen; + ace_count += 1; + } /* and one more ACE to allow access for authenticated users */ - pace = (struct cifs_ace *)(acelen + (sizeof(struct crt_sd_ctxt) + - (char *)buf)); - acelen += setup_authusers_ACE(pace); - - buf->acl.AclSize = cpu_to_le16(sizeof(struct cifs_acl) + acelen); + acelen = setup_authusers_ACE((struct cifs_ace *)ptr); + ptr += acelen; + acl_size += acelen; + ace_count += 1; + + acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */ + acl.AclSize = cpu_to_le16(acl_size); + acl.AceCount = cpu_to_le16(ace_count); + memcpy(aclptr, &acl, sizeof(struct cifs_acl)); + + buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd); + *len = ptr - (__u8 *)buf; return buf; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index f05f9b12f689..fa57b03ca98c 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -963,8 +963,6 @@ struct crt_sd_ctxt { struct create_context ccontext; __u8 Name[8]; struct smb3_sd sd; - struct smb3_acl acl; - /* Followed by at least 4 ACEs */ } __packed; diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index 2d24c765cbd7..2c557229696a 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -106,15 +106,25 @@ #endif #ifdef compat_start_thread -#undef start_thread -#define start_thread compat_start_thread +#define COMPAT_START_THREAD(ex, regs, new_ip, new_sp) \ + compat_start_thread(regs, new_ip, new_sp) #endif -#ifdef compat_arch_setup_additional_pages +#ifdef COMPAT_START_THREAD +#undef START_THREAD +#define START_THREAD COMPAT_START_THREAD +#endif + +#ifdef compat_arch_setup_additional_pages +#define COMPAT_ARCH_SETUP_ADDITIONAL_PAGES(bprm, ex, interpreter) \ + compat_arch_setup_additional_pages(bprm, interpreter) +#endif + +#ifdef COMPAT_ARCH_SETUP_ADDITIONAL_PAGES #undef ARCH_HAS_SETUP_ADDITIONAL_PAGES #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 -#undef arch_setup_additional_pages -#define arch_setup_additional_pages compat_arch_setup_additional_pages +#undef ARCH_SETUP_ADDITIONAL_PAGES +#define ARCH_SETUP_ADDITIONAL_PAGES COMPAT_ARCH_SETUP_ADDITIONAL_PAGES #endif #ifdef compat_elf_read_implies_exec diff --git a/fs/coredump.c b/fs/coredump.c index 0cd9056d79cc..c6acfc694f65 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -229,7 +229,8 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm, */ if (ispipe) { if (isspace(*pat_ptr)) { - was_space = true; + if (cn->used != 0) + was_space = true; pat_ptr++; continue; } else if (was_space) { diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 1fbe6c24d705..3414d35ccbb6 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -14,7 +14,7 @@ #include <linux/namei.h> #include <linux/scatterlist.h> #include <crypto/hash.h> -#include <crypto/sha.h> +#include <crypto/sha2.h> #include <crypto/skcipher.h> #include "fscrypt_private.h" @@ -404,7 +404,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, fname->disk_name.len = iname->len; return 0; } - ret = fscrypt_get_encryption_info(dir); + ret = fscrypt_get_encryption_info(dir, lookup); if (ret) return ret; @@ -560,7 +560,11 @@ int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) return -ECHILD; dir = dget_parent(dentry); - err = fscrypt_get_encryption_info(d_inode(dir)); + /* + * Pass allow_unsupported=true, so that files with an unsupported + * encryption policy can be deleted. + */ + err = fscrypt_get_encryption_info(d_inode(dir), true); valid = !fscrypt_has_encryption_key(d_inode(dir)); dput(dir); diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 4f5806a3b73d..f0bed6b06fa6 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -25,6 +25,9 @@ #define FSCRYPT_CONTEXT_V1 1 #define FSCRYPT_CONTEXT_V2 2 +/* Keep this in sync with include/uapi/linux/fscrypt.h */ +#define FSCRYPT_MODE_MAX FSCRYPT_MODE_ADIANTUM + struct fscrypt_context_v1 { u8 version; /* FSCRYPT_CONTEXT_V1 */ u8 contents_encryption_mode; @@ -436,16 +439,9 @@ struct fscrypt_master_key { * FS_IOC_REMOVE_ENCRYPTION_KEY can be retried, or * FS_IOC_ADD_ENCRYPTION_KEY can add the secret again. * - * Locking: protected by key->sem (outer) and mk_secret_sem (inner). - * The reason for two locks is that key->sem also protects modifying - * mk_users, which ranks it above the semaphore for the keyring key - * type, which is in turn above page faults (via keyring_read). But - * sometimes filesystems call fscrypt_get_encryption_info() from within - * a transaction, which ranks it below page faults. So we need a - * separate lock which protects mk_secret but not also mk_users. + * Locking: protected by this master key's key->sem. */ struct fscrypt_master_key_secret mk_secret; - struct rw_semaphore mk_secret_sem; /* * For v1 policy keys: an arbitrary key descriptor which was assigned by @@ -464,8 +460,8 @@ struct fscrypt_master_key { * * This is NULL for v1 policy keys; those can only be added by root. * - * Locking: in addition to this keyrings own semaphore, this is - * protected by the master key's key->sem, so we can do atomic + * Locking: in addition to this keyring's own semaphore, this is + * protected by this master key's key->sem, so we can do atomic * search+insert. It can also be searched without taking any locks, but * in that case the returned key may have already been removed. */ @@ -491,9 +487,9 @@ struct fscrypt_master_key { * Per-mode encryption keys for the various types of encryption policies * that use them. Allocated and derived on-demand. */ - 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 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]; /* Hash key for inode numbers. Initialized only when needed. */ siphash_key_t mk_ino_hash_key; @@ -507,9 +503,9 @@ is_master_key_secret_present(const struct fscrypt_master_key_secret *secret) /* * The READ_ONCE() is only necessary for fscrypt_drop_inode() and * fscrypt_key_describe(). These run in atomic context, so they can't - * take ->mk_secret_sem and thus 'secret' can change concurrently which - * would be a data race. But they only need to know whether the secret - * *was* present at the time of check, so READ_ONCE() suffices. + * take the key semaphore and thus 'secret' can change concurrently + * which would be a data race. But they only need to know whether the + * secret *was* present at the time of check, so READ_ONCE() suffices. */ return READ_ONCE(secret->size) != 0; } @@ -575,6 +571,34 @@ int fscrypt_derive_dirhash_key(struct fscrypt_info *ci, void fscrypt_hash_inode_number(struct fscrypt_info *ci, const struct fscrypt_master_key *mk); +int fscrypt_get_encryption_info(struct inode *inode, bool allow_unsupported); + +/** + * fscrypt_require_key() - require an inode's encryption key + * @inode: the inode we need the key for + * + * If the inode is encrypted, set up its encryption key if not already done. + * Then require that the key be present and return -ENOKEY otherwise. + * + * No locks are needed, and the key will live as long as the struct inode --- so + * it won't go away from under you. + * + * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code + * if a problem occurred while setting up the encryption key. + */ +static inline int fscrypt_require_key(struct inode *inode) +{ + if (IS_ENCRYPTED(inode)) { + int err = fscrypt_get_encryption_info(inode, false); + + if (err) + return err; + if (!fscrypt_has_encryption_key(inode)) + return -ENOKEY; + } + return 0; +} + /* keysetup_v1.c */ void fscrypt_put_direct_key(struct fscrypt_direct_key *dk); diff --git a/fs/crypto/hkdf.c b/fs/crypto/hkdf.c index 0cba7928446d..e0ec21055505 100644 --- a/fs/crypto/hkdf.c +++ b/fs/crypto/hkdf.c @@ -10,7 +10,7 @@ */ #include <crypto/hash.h> -#include <crypto/sha.h> +#include <crypto/sha2.h> #include "fscrypt_private.h" diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index 20b0df47fe6a..79570e0e8e61 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -54,15 +54,12 @@ EXPORT_SYMBOL_GPL(fscrypt_file_open); int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, struct dentry *dentry) { - int err; - - err = fscrypt_require_key(dir); - if (err) - return err; - - /* ... in case we looked up no-key name before key was added */ - if (dentry->d_flags & DCACHE_NOKEY_NAME) + if (fscrypt_is_nokey_name(dentry)) return -ENOKEY; + /* + * We don't need to separately check that the directory inode's key is + * available, as it's implied by the dentry not being a no-key name. + */ if (!fscrypt_has_permitted_context(dir, inode)) return -EXDEV; @@ -75,19 +72,13 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { - int err; - - err = fscrypt_require_key(old_dir); - if (err) - return err; - - err = fscrypt_require_key(new_dir); - if (err) - return err; - - /* ... in case we looked up no-key name(s) before key was added */ - if ((old_dentry->d_flags | new_dentry->d_flags) & DCACHE_NOKEY_NAME) + if (fscrypt_is_nokey_name(old_dentry) || + fscrypt_is_nokey_name(new_dentry)) return -ENOKEY; + /* + * We don't need to separately check that the directory inodes' keys are + * available, as it's implied by the dentries not being no-key names. + */ if (old_dir != new_dir) { if (IS_ENCRYPTED(new_dir) && @@ -123,6 +114,20 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, } EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup); +int __fscrypt_prepare_readdir(struct inode *dir) +{ + return fscrypt_get_encryption_info(dir, true); +} +EXPORT_SYMBOL_GPL(__fscrypt_prepare_readdir); + +int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr) +{ + if (attr->ia_valid & ATTR_SIZE) + return fscrypt_require_key(d_inode(dentry)); + return 0; +} +EXPORT_SYMBOL_GPL(__fscrypt_prepare_setattr); + /** * fscrypt_prepare_setflags() - prepare to change flags with FS_IOC_SETFLAGS * @inode: the inode on which flags are being changed @@ -138,6 +143,7 @@ int fscrypt_prepare_setflags(struct inode *inode, unsigned int oldflags, unsigned int flags) { struct fscrypt_info *ci; + struct key *key; struct fscrypt_master_key *mk; int err; @@ -153,13 +159,14 @@ int fscrypt_prepare_setflags(struct inode *inode, ci = inode->i_crypt_info; if (ci->ci_policy.version != FSCRYPT_POLICY_V2) return -EINVAL; - mk = ci->ci_master_key->payload.data[0]; - down_read(&mk->mk_secret_sem); + key = ci->ci_master_key; + mk = key->payload.data[0]; + down_read(&key->sem); if (is_master_key_secret_present(&mk->mk_secret)) err = fscrypt_derive_dirhash_key(ci, mk); else err = -ENOKEY; - up_read(&mk->mk_secret_sem); + up_read(&key->sem); return err; } return 0; @@ -325,7 +332,7 @@ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, * Try to set up the symlink's encryption key, but we can continue * regardless of whether the key is available or not. */ - err = fscrypt_get_encryption_info(inode); + err = fscrypt_get_encryption_info(inode, false); if (err) return ERR_PTR(err); has_key = fscrypt_has_encryption_key(inode); diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 53cc552a7b8f..0b3ffbb4faf4 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -44,7 +44,7 @@ static void free_master_key(struct fscrypt_master_key *mk) wipe_master_key_secret(&mk->mk_secret); - for (i = 0; i <= __FSCRYPT_MODE_MAX; i++) { + for (i = 0; i <= FSCRYPT_MODE_MAX; i++) { fscrypt_destroy_prepared_key(&mk->mk_direct_keys[i]); fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_64_keys[i]); fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_32_keys[i]); @@ -347,7 +347,6 @@ static int add_new_master_key(struct fscrypt_master_key_secret *secret, mk->mk_spec = *mk_spec; move_master_key_secret(&mk->mk_secret, secret); - init_rwsem(&mk->mk_secret_sem); refcount_set(&mk->mk_refcount, 1); /* secret is present */ INIT_LIST_HEAD(&mk->mk_decrypted_inodes); @@ -427,11 +426,8 @@ static int add_existing_master_key(struct fscrypt_master_key *mk, } /* Re-add the secret if needed. */ - if (rekey) { - down_write(&mk->mk_secret_sem); + if (rekey) move_master_key_secret(&mk->mk_secret, secret); - up_write(&mk->mk_secret_sem); - } return 0; } @@ -975,10 +971,8 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) /* No user claims remaining. Go ahead and wipe the secret. */ dead = false; if (is_master_key_secret_present(&mk->mk_secret)) { - down_write(&mk->mk_secret_sem); wipe_master_key_secret(&mk->mk_secret); dead = refcount_dec_and_test(&mk->mk_refcount); - up_write(&mk->mk_secret_sem); } up_write(&key->sem); if (dead) { diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index d595abb8ef90..261293fb7097 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -56,6 +56,8 @@ static struct fscrypt_mode * select_encryption_mode(const union fscrypt_policy *policy, const struct inode *inode) { + BUILD_BUG_ON(ARRAY_SIZE(fscrypt_modes) != FSCRYPT_MODE_MAX + 1); + if (S_ISREG(inode->i_mode)) return &fscrypt_modes[fscrypt_policy_contents_mode(policy)]; @@ -168,7 +170,7 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci, unsigned int hkdf_infolen = 0; int err; - if (WARN_ON(mode_num > __FSCRYPT_MODE_MAX)) + if (WARN_ON(mode_num > FSCRYPT_MODE_MAX)) return -EINVAL; prep_key = &keys[mode_num]; @@ -335,11 +337,11 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci, * Find the master key, then set up the inode's actual encryption key. * * If the master key is found in the filesystem-level keyring, then the - * corresponding 'struct key' is returned in *master_key_ret with - * ->mk_secret_sem read-locked. This is needed to ensure that only one task - * links the fscrypt_info into ->mk_decrypted_inodes (as multiple tasks may race - * to create an fscrypt_info for the same inode), and to synchronize the master - * key being removed with a new inode starting to use it. + * corresponding 'struct key' is returned in *master_key_ret with its semaphore + * read-locked. This is needed to ensure that only one task links the + * fscrypt_info into ->mk_decrypted_inodes (as multiple tasks may race to create + * an fscrypt_info for the same inode), and to synchronize the master key being + * removed with a new inode starting to use it. */ static int setup_file_encryption_key(struct fscrypt_info *ci, bool need_dirhash_key, @@ -388,7 +390,7 @@ static int setup_file_encryption_key(struct fscrypt_info *ci, } mk = key->payload.data[0]; - down_read(&mk->mk_secret_sem); + down_read(&key->sem); /* Has the secret been removed (via FS_IOC_REMOVE_ENCRYPTION_KEY)? */ if (!is_master_key_secret_present(&mk->mk_secret)) { @@ -431,7 +433,7 @@ static int setup_file_encryption_key(struct fscrypt_info *ci, return 0; out_release_key: - up_read(&mk->mk_secret_sem); + up_read(&key->sem); key_put(key); return err; } @@ -534,9 +536,7 @@ fscrypt_setup_encryption_info(struct inode *inode, res = 0; out: if (master_key) { - struct fscrypt_master_key *mk = master_key->payload.data[0]; - - up_read(&mk->mk_secret_sem); + up_read(&master_key->sem); key_put(master_key); } put_crypt_info(crypt_info); @@ -546,6 +546,11 @@ out: /** * fscrypt_get_encryption_info() - set up an inode's encryption key * @inode: the inode to set up the key for. Must be encrypted. + * @allow_unsupported: if %true, treat an unsupported encryption policy (or + * unrecognized encryption context) the same way as the key + * being unavailable, instead of returning an error. Use + * %false unless the operation being performed is needed in + * order for files (or directories) to be deleted. * * Set up ->i_crypt_info, if it hasn't already been done. * @@ -556,7 +561,7 @@ out: * encryption key is unavailable. (Use fscrypt_has_encryption_key() to * distinguish these cases.) Also can return another -errno code. */ -int fscrypt_get_encryption_info(struct inode *inode) +int fscrypt_get_encryption_info(struct inode *inode, bool allow_unsupported) { int res; union fscrypt_context ctx; @@ -567,29 +572,38 @@ int fscrypt_get_encryption_info(struct inode *inode) res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx)); if (res < 0) { + if (res == -ERANGE && allow_unsupported) + return 0; fscrypt_warn(inode, "Error %d getting encryption context", res); return res; } res = fscrypt_policy_from_context(&policy, &ctx, res); if (res) { + if (allow_unsupported) + return 0; fscrypt_warn(inode, "Unrecognized or corrupt encryption context"); return res; } - if (!fscrypt_supported_policy(&policy, inode)) + if (!fscrypt_supported_policy(&policy, inode)) { + if (allow_unsupported) + return 0; return -EINVAL; + } res = fscrypt_setup_encryption_info(inode, &policy, fscrypt_context_nonce(&ctx), IS_CASEFOLDED(inode) && S_ISDIR(inode->i_mode)); + + if (res == -ENOPKG && allow_unsupported) /* Algorithm unavailable? */ + res = 0; if (res == -ENOKEY) res = 0; return res; } -EXPORT_SYMBOL(fscrypt_get_encryption_info); /** * fscrypt_prepare_new_inode() - prepare to create a new inode in a directory @@ -710,7 +724,7 @@ int fscrypt_drop_inode(struct inode *inode) return 0; /* - * Note: since we aren't holding ->mk_secret_sem, the result here can + * Note: since we aren't holding the key semaphore, the result here can * immediately become outdated. But there's no correctness problem with * unnecessarily evicting. Nor is there a correctness problem with not * evicting while iput() is racing with the key being removed, since diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 4441d9944b9e..a51cef6bd27f 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -175,7 +175,10 @@ static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy, return false; } - if (policy->flags & ~FSCRYPT_POLICY_FLAGS_VALID) { + if (policy->flags & ~(FSCRYPT_POLICY_FLAGS_PAD_MASK | + FSCRYPT_POLICY_FLAG_DIRECT_KEY | + FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 | + FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) { fscrypt_warn(inode, "Unsupported encryption flags (0x%02x)", policy->flags); return false; @@ -587,7 +590,7 @@ EXPORT_SYMBOL_GPL(fscrypt_ioctl_get_nonce); int fscrypt_has_permitted_context(struct inode *parent, struct inode *child) { union fscrypt_policy parent_policy, child_policy; - int err; + int err, err1, err2; /* No restrictions on file types which are never encrypted */ if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) && @@ -617,19 +620,25 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child) * In any case, if an unexpected error occurs, fall back to "forbidden". */ - err = fscrypt_get_encryption_info(parent); + err = fscrypt_get_encryption_info(parent, true); if (err) return 0; - err = fscrypt_get_encryption_info(child); + err = fscrypt_get_encryption_info(child, true); if (err) return 0; - err = fscrypt_get_policy(parent, &parent_policy); - if (err) - return 0; + err1 = fscrypt_get_policy(parent, &parent_policy); + err2 = fscrypt_get_policy(child, &child_policy); - err = fscrypt_get_policy(child, &child_policy); - if (err) + /* + * Allow the case where the parent and child both have an unrecognized + * encryption policy, so that files with an unrecognized encryption + * policy can be deleted. + */ + if (err1 == -EINVAL && err2 == -EINVAL) + return 1; + + if (err1 || err2) return 0; return fscrypt_policies_equal(&parent_policy, &child_policy); diff --git a/fs/exec.c b/fs/exec.c index 547a2390baf5..aee36e5733ce 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -64,6 +64,7 @@ #include <linux/compat.h> #include <linux/vmalloc.h> #include <linux/io_uring.h> +#include <linux/syscall_user_dispatch.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> @@ -1302,6 +1303,8 @@ int begin_new_exec(struct linux_binprm * bprm) flush_thread(); me->personality &= ~bprm->per_clear; + clear_syscall_work_syscall_user_dispatch(me); + /* * We have to apply CLOEXEC before we change whether the process is * dumpable (in setup_new_exec) to avoid a race with a process in userspace diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index ca50c90adc4c..c6d16353326a 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -118,11 +118,9 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) struct buffer_head *bh = NULL; struct fscrypt_str fstr = FSTR_INIT(NULL, 0); - if (IS_ENCRYPTED(inode)) { - err = fscrypt_get_encryption_info(inode); - if (err) - return err; - } + err = fscrypt_prepare_readdir(inode); + if (err) + return err; if (is_dx_dir(inode)) { err = ext4_dx_readdir(file, ctx); @@ -616,13 +614,6 @@ finished: return 0; } -static int ext4_dir_open(struct inode * inode, struct file * filp) -{ - if (IS_ENCRYPTED(inode)) - return fscrypt_get_encryption_info(inode) ? -EACCES : 0; - return 0; -} - static int ext4_release_dir(struct inode *inode, struct file *filp) { if (filp->private_data) @@ -664,7 +655,6 @@ const struct file_operations ext4_dir_operations = { .compat_ioctl = ext4_compat_ioctl, #endif .fsync = ext4_sync_file, - .open = ext4_dir_open, .release = ext4_release_dir, }; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 33509266f5a0..5fa8436cd5fa 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -643,13 +643,7 @@ static struct stats dx_show_leaf(struct inode *dir, name = de->name; len = de->name_len; - if (IS_ENCRYPTED(dir)) - res = fscrypt_get_encryption_info(dir); - if (res) { - printk(KERN_WARNING "Error setting up" - " fname crypto: %d\n", res); - } - if (!fscrypt_has_encryption_key(dir)) { + if (!IS_ENCRYPTED(dir)) { /* Directory is not encrypted */ ext4fs_dirhash(dir, de->name, de->name_len, &h); @@ -1010,7 +1004,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, EXT4_DIR_REC_LEN(0)); /* Check if the directory is encrypted */ if (IS_ENCRYPTED(dir)) { - err = fscrypt_get_encryption_info(dir); + err = fscrypt_prepare_readdir(dir); if (err < 0) { brelse(bh); return err; @@ -2195,6 +2189,9 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, if (!dentry->d_name.len) return -EINVAL; + if (fscrypt_is_nokey_name(dentry)) + return -ENOKEY; + #ifdef CONFIG_UNICODE if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) && sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name)) diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 4b9ef8bbfa4a..049500f1e764 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -1022,7 +1022,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) int err = 0; if (IS_ENCRYPTED(inode)) { - err = fscrypt_get_encryption_info(inode); + err = fscrypt_prepare_readdir(inode); if (err) goto out; @@ -1081,19 +1081,11 @@ out: return err < 0 ? err : 0; } -static int f2fs_dir_open(struct inode *inode, struct file *filp) -{ - if (IS_ENCRYPTED(inode)) - return fscrypt_get_encryption_info(inode) ? -EACCES : 0; - return 0; -} - const struct file_operations f2fs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = f2fs_readdir, .fsync = f2fs_sync_file, - .open = f2fs_dir_open, .unlocked_ioctl = f2fs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = f2fs_compat_ioctl, diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index cb700d797296..9a321c52face 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3251,6 +3251,8 @@ bool f2fs_empty_dir(struct inode *dir); static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) { + if (fscrypt_is_nokey_name(dentry)) + return -ENOKEY; return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name, inode, inode->i_ino, inode->i_mode); } diff --git a/fs/io_uring.c b/fs/io_uring.c index 1023f7b44cea..86dac2b2e276 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1284,7 +1284,7 @@ static bool io_identity_cow(struct io_kiocb *req) */ io_init_identity(id); if (creds) - req->work.identity->creds = creds; + id->creds = creds; /* add one for this request */ refcount_inc(&id->count); @@ -4499,7 +4499,8 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, return -EFAULT; if (clen < 0) return -EINVAL; - sr->len = iomsg->iov[0].iov_len; + sr->len = clen; + iomsg->iov[0].iov_len = clen; iomsg->iov = NULL; } else { ret = __import_iovec(READ, (struct iovec __user *)uiov, len, @@ -9182,6 +9183,7 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx) { struct file *file; int ret; + int fd; #if defined(CONFIG_UNIX) ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP, @@ -9193,12 +9195,12 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx) ret = get_unused_fd_flags(O_RDWR | O_CLOEXEC); if (ret < 0) goto err; + fd = ret; file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx, O_RDWR | O_CLOEXEC); if (IS_ERR(file)) { -err_fd: - put_unused_fd(ret); + put_unused_fd(fd); ret = PTR_ERR(file); goto err; } @@ -9206,12 +9208,14 @@ err_fd: #if defined(CONFIG_UNIX) ctx->ring_sock->file = file; #endif - if (unlikely(io_uring_add_task_file(ctx, file))) { - file = ERR_PTR(-ENOMEM); - goto err_fd; + ret = io_uring_add_task_file(ctx, file); + if (ret) { + fput(file); + put_unused_fd(fd); + goto err; } - fd_install(ret, file); - return ret; + fd_install(fd, file); + return fd; err: #if defined(CONFIG_UNIX) sock_release(ctx->ring_sock); diff --git a/fs/mount.h b/fs/mount.h index c7abb7b394d8..ce6c376e0bc2 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -6,7 +6,6 @@ #include <linux/fs_pin.h> struct mnt_namespace { - atomic_t count; struct ns_common ns; struct mount * root; /* @@ -120,7 +119,7 @@ static inline void detach_mounts(struct dentry *dentry) static inline void get_mnt_ns(struct mnt_namespace *ns) { - atomic_inc(&ns->count); + refcount_inc(&ns->ns.count); } extern seqlock_t mount_lock; diff --git a/fs/namespace.c b/fs/namespace.c index cebaa3e81794..2b681f65ca04 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -3274,7 +3274,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a new_ns->ns.ops = &mntns_operations; if (!anon) new_ns->seq = atomic64_add_return(1, &mnt_ns_seq); - atomic_set(&new_ns->count, 1); + refcount_set(&new_ns->ns.count, 1); INIT_LIST_HEAD(&new_ns->list); init_waitqueue_head(&new_ns->poll); spin_lock_init(&new_ns->ns_lock); @@ -3848,7 +3848,7 @@ void __init mnt_init(void) void put_mnt_ns(struct mnt_namespace *ns) { - if (!atomic_dec_and_test(&ns->count)) + if (!refcount_dec_and_test(&ns->ns.count)) return; drop_collected_mounts(&ns->root->mnt); free_mnt_ns(ns); diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 88e1763e02f3..e2a488d403a6 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -205,3 +205,12 @@ config NFS_DISABLE_UDP_SUPPORT Choose Y here to disable the use of NFS over UDP. NFS over UDP on modern networks (1Gb+) can lead to data corruption caused by fragmentation during high loads. + +config NFS_V4_2_READ_PLUS + bool "NFS: Enable support for the NFSv4.2 READ_PLUS operation" + depends on NFS_V4_2 + default n + help + This is intended for developers only. The READ_PLUS operation has + been shown to have issues under specific conditions and should not + be used in production. diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index a163533446fa..24bf5797f88a 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -838,7 +838,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_pgio_mirror *pgm; struct nfs4_ff_layout_mirror *mirror; struct nfs4_pnfs_ds *ds; - u32 ds_idx, i; + u32 ds_idx; retry: ff_layout_pg_check_layout(pgio, req); @@ -864,11 +864,9 @@ retry: goto retry; } - for (i = 0; i < pgio->pg_mirror_count; i++) { - mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); - pgm = &pgio->pg_mirrors[i]; - pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; - } + mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx); + pgm = &pgio->pg_mirrors[0]; + pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; pgio->pg_mirror_idx = ds_idx; @@ -985,6 +983,21 @@ out: return 1; } +static u32 +ff_layout_pg_set_mirror_write(struct nfs_pageio_descriptor *desc, u32 idx) +{ + u32 old = desc->pg_mirror_idx; + + desc->pg_mirror_idx = idx; + return old; +} + +static struct nfs_pgio_mirror * +ff_layout_pg_get_mirror_write(struct nfs_pageio_descriptor *desc, u32 idx) +{ + return &desc->pg_mirrors[idx]; +} + static const struct nfs_pageio_ops ff_layout_pg_read_ops = { .pg_init = ff_layout_pg_init_read, .pg_test = pnfs_generic_pg_test, @@ -998,6 +1011,8 @@ static const struct nfs_pageio_ops ff_layout_pg_write_ops = { .pg_doio = pnfs_generic_pg_writepages, .pg_get_mirror_count = ff_layout_pg_get_mirror_count_write, .pg_cleanup = pnfs_generic_pg_cleanup, + .pg_get_mirror = ff_layout_pg_get_mirror_write, + .pg_set_mirror = ff_layout_pg_set_mirror_write, }; static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 2b2211d1234e..4fc61e3d098d 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -1241,12 +1241,13 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf, .rpc_resp = &res, }; u32 xdrlen; - int ret, np; + int ret, np, i; + ret = -ENOMEM; res.scratch = alloc_page(GFP_KERNEL); if (!res.scratch) - return -ENOMEM; + goto out; xdrlen = nfs42_listxattr_xdrsize(buflen); if (xdrlen > server->lxasize) @@ -1254,9 +1255,12 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf, np = xdrlen / PAGE_SIZE + 1; pages = kcalloc(np, sizeof(struct page *), GFP_KERNEL); - if (pages == NULL) { - __free_page(res.scratch); - return -ENOMEM; + if (!pages) + goto out_free_scratch; + for (i = 0; i < np; i++) { + pages[i] = alloc_page(GFP_KERNEL); + if (!pages[i]) + goto out_free_pages; } arg.xattr_pages = pages; @@ -1271,14 +1275,15 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf, *eofp = res.eof; } +out_free_pages: while (--np >= 0) { if (pages[np]) __free_page(pages[np]); } - - __free_page(res.scratch); kfree(pages); - +out_free_scratch: + __free_page(res.scratch); +out: return ret; } diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 6e060a88f98c..8432bd6b95f0 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -1528,7 +1528,6 @@ static void nfs4_xdr_enc_listxattrs(struct rpc_rqst *req, rpc_prepare_reply_pages(req, args->xattr_pages, 0, args->count, hdr.replen); - req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES; encode_nops(&hdr); } diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 9d354de613da..57b3821d975a 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -377,10 +377,10 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, goto out_stateowner; set_bit(NFS_SRV_SSC_COPY_STATE, &ctx->state->flags); - set_bit(NFS_OPEN_STATE, &ctx->state->flags); memcpy(&ctx->state->open_stateid.other, &stateid->other, NFS4_STATEID_OTHER_SIZE); update_open_stateid(ctx->state, stateid, NULL, filep->f_mode); + set_bit(NFS_OPEN_STATE, &ctx->state->flags); nfs_file_set_open_context(filep, ctx); put_nfs_open_context(ctx); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9e0ca9b2b210..e89468678ae1 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5309,7 +5309,7 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) nfs4_read_done_cb(task, hdr); } -#ifdef CONFIG_NFS_V4_2 +#if defined CONFIG_NFS_V4_2 && defined CONFIG_NFS_V4_2_READ_PLUS static void nfs42_read_plus_support(struct nfs_server *server, struct rpc_message *msg) { if (server->caps & NFS_CAP_READ_PLUS) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 6985cacf4700..78c9c4bdef2b 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -31,13 +31,29 @@ static struct kmem_cache *nfs_page_cachep; static const struct rpc_call_ops nfs_pgio_common_ops; +static struct nfs_pgio_mirror * +nfs_pgio_get_mirror(struct nfs_pageio_descriptor *desc, u32 idx) +{ + if (desc->pg_ops->pg_get_mirror) + return desc->pg_ops->pg_get_mirror(desc, idx); + return &desc->pg_mirrors[0]; +} + struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc) { - return &desc->pg_mirrors[desc->pg_mirror_idx]; + return nfs_pgio_get_mirror(desc, desc->pg_mirror_idx); } EXPORT_SYMBOL_GPL(nfs_pgio_current_mirror); +static u32 +nfs_pgio_set_current_mirror(struct nfs_pageio_descriptor *desc, u32 idx) +{ + if (desc->pg_ops->pg_set_mirror) + return desc->pg_ops->pg_set_mirror(desc, idx); + return desc->pg_mirror_idx; +} + void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)) @@ -1259,7 +1275,7 @@ static void nfs_pageio_error_cleanup(struct nfs_pageio_descriptor *desc) return; for (midx = 0; midx < desc->pg_mirror_count; midx++) { - mirror = &desc->pg_mirrors[midx]; + mirror = nfs_pgio_get_mirror(desc, midx); desc->pg_completion_ops->error_cleanup(&mirror->pg_list, desc->pg_error); } @@ -1293,12 +1309,12 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, goto out_failed; } - desc->pg_mirror_idx = midx; + nfs_pgio_set_current_mirror(desc, midx); if (!nfs_pageio_add_request_mirror(desc, dupreq)) goto out_cleanup_subreq; } - desc->pg_mirror_idx = 0; + nfs_pgio_set_current_mirror(desc, 0); if (!nfs_pageio_add_request_mirror(desc, req)) goto out_failed; @@ -1320,10 +1336,12 @@ out_failed: static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, u32 mirror_idx) { - struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[mirror_idx]; - u32 restore_idx = desc->pg_mirror_idx; + struct nfs_pgio_mirror *mirror; + u32 restore_idx; + + restore_idx = nfs_pgio_set_current_mirror(desc, mirror_idx); + mirror = nfs_pgio_current_mirror(desc); - desc->pg_mirror_idx = mirror_idx; for (;;) { nfs_pageio_doio(desc); if (desc->pg_error < 0 || !mirror->pg_recoalesce) @@ -1331,7 +1349,7 @@ static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, if (!nfs_do_recoalesce(desc)) break; } - desc->pg_mirror_idx = restore_idx; + nfs_pgio_set_current_mirror(desc, restore_idx); } /* @@ -1405,7 +1423,7 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index) u32 midx; for (midx = 0; midx < desc->pg_mirror_count; midx++) { - mirror = &desc->pg_mirrors[midx]; + mirror = nfs_pgio_get_mirror(desc, midx); if (!list_empty(&mirror->pg_list)) { prev = nfs_list_entry(mirror->pg_list.prev); if (index != prev->wb_index + 1) { diff --git a/fs/proc/array.c b/fs/proc/array.c index 65ec2029fa80..277f654f289e 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -56,6 +56,7 @@ #include <linux/types.h> #include <linux/errno.h> #include <linux/time.h> +#include <linux/time_namespace.h> #include <linux/kernel.h> #include <linux/kernel_stat.h> #include <linux/tty.h> @@ -533,8 +534,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, priority = task_prio(task); nice = task_nice(task); - /* convert nsec -> ticks */ - start_time = nsec_to_clock_t(task->start_boottime); + /* apply timens offset for boottime and convert nsec -> ticks */ + start_time = + nsec_to_clock_t(timens_add_boottime_ns(task->start_boottime)); seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns)); seq_puts(m, " ("); diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 4695b6de3151..f25e8531fd27 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -10,6 +10,7 @@ #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/time.h> +#include <linux/time_namespace.h> #include <linux/irqnr.h> #include <linux/sched/cputime.h> #include <linux/tick.h> @@ -118,6 +119,8 @@ static int show_stat(struct seq_file *p, void *v) irq = softirq = steal = 0; guest = guest_nice = 0; getboottime64(&boottime); + /* shift boot timestamp according to the timens offset */ + timens_sub_boottime(&boottime); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 217aa2705d5d..ee5a235b3056 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1599,11 +1599,15 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, src = *ppos; svpfn = src / PM_ENTRY_BYTES; - start_vaddr = svpfn << PAGE_SHIFT; end_vaddr = mm->task_size; /* watch out for wraparound */ - if (svpfn > mm->task_size >> PAGE_SHIFT) + start_vaddr = end_vaddr; + if (svpfn <= (ULONG_MAX >> PAGE_SHIFT)) + start_vaddr = untagged_addr(svpfn << PAGE_SHIFT); + + /* Ensure the address is inside the task */ + if (start_vaddr > mm->task_size) start_vaddr = end_vaddr; /* diff --git a/fs/seq_file.c b/fs/seq_file.c index 3b20e21604e7..03a369ccd28c 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -168,12 +168,14 @@ EXPORT_SYMBOL(seq_read); ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct seq_file *m = iocb->ki_filp->private_data; - size_t size = iov_iter_count(iter); size_t copied = 0; size_t n; void *p; int err = 0; + if (!iov_iter_count(iter)) + return 0; + mutex_lock(&m->lock); /* @@ -206,36 +208,34 @@ ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter) if (!m->buf) goto Enomem; } - /* if not empty - flush it first */ + // something left in the buffer - copy it out first if (m->count) { - n = min(m->count, size); - if (copy_to_iter(m->buf + m->from, n, iter) != n) - goto Efault; + n = copy_to_iter(m->buf + m->from, m->count, iter); m->count -= n; m->from += n; - size -= n; copied += n; - if (!size) + if (m->count) // hadn't managed to copy everything goto Done; } - /* we need at least one record in buffer */ + // get a non-empty record in the buffer m->from = 0; p = m->op->start(m, &m->index); while (1) { err = PTR_ERR(p); - if (!p || IS_ERR(p)) + if (!p || IS_ERR(p)) // EOF or an error break; err = m->op->show(m, p); - if (err < 0) + if (err < 0) // hard error break; - if (unlikely(err)) + if (unlikely(err)) // ->show() says "skip it" m->count = 0; - if (unlikely(!m->count)) { + if (unlikely(!m->count)) { // empty record p = m->op->next(m, p, &m->index); continue; } - if (m->count < m->size) + if (!seq_has_overflowed(m)) // got it goto Fill; + // need a bigger buffer m->op->stop(m, p); kvfree(m->buf); m->count = 0; @@ -244,11 +244,14 @@ ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter) goto Enomem; p = m->op->start(m, &m->index); } + // EOF or an error m->op->stop(m, p); m->count = 0; goto Done; Fill: - /* they want more? let's try to get some more */ + // one non-empty record is in the buffer; if they want more, + // try to fit more in, but in any case we need to advance + // the iterator once for every record shown. while (1) { size_t offs = m->count; loff_t pos = m->index; @@ -259,30 +262,27 @@ Fill: m->op->next); m->index++; } - if (!p || IS_ERR(p)) { - err = PTR_ERR(p); + if (!p || IS_ERR(p)) // no next record for us break; - } - if (m->count >= size) + if (m->count >= iov_iter_count(iter)) break; err = m->op->show(m, p); - if (seq_has_overflowed(m) || err) { + if (err > 0) { // ->show() says "skip it" m->count = offs; - if (likely(err <= 0)) - break; + } else if (err || seq_has_overflowed(m)) { + m->count = offs; + break; } } m->op->stop(m, p); - n = min(m->count, size); - if (copy_to_iter(m->buf, n, iter) != n) - goto Efault; + n = copy_to_iter(m->buf, m->count, iter); copied += n; m->count -= n; m->from = n; Done: - if (!copied) - copied = err; - else { + if (unlikely(!copied)) { + copied = m->count ? -EFAULT : err; + } else { iocb->ki_pos += copied; m->read_pos += copied; } @@ -291,9 +291,6 @@ Done: Enomem: err = -ENOMEM; goto Done; -Efault: - err = -EFAULT; - goto Done; } EXPORT_SYMBOL(seq_read_iter); diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c index b93b3cd10bfd..0886d835f597 100644 --- a/fs/ubifs/auth.c +++ b/fs/ubifs/auth.c @@ -12,7 +12,6 @@ #include <linux/crypto.h> #include <linux/verification.h> #include <crypto/hash.h> -#include <crypto/sha.h> #include <crypto/algapi.h> #include <keys/user-type.h> #include <keys/asymmetric-type.h> diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 155521e51ac5..1f33a5598b93 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -270,6 +270,15 @@ done: return d_splice_alias(inode, dentry); } +static int ubifs_prepare_create(struct inode *dir, struct dentry *dentry, + struct fscrypt_name *nm) +{ + if (fscrypt_is_nokey_name(dentry)) + return -ENOKEY; + + return fscrypt_setup_filename(dir, &dentry->d_name, 0, nm); +} + static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { @@ -293,7 +302,7 @@ static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode, if (err) return err; - err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + err = ubifs_prepare_create(dir, dentry, &nm); if (err) goto out_budg; @@ -505,7 +514,7 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) return 0; if (encrypted) { - err = fscrypt_get_encryption_info(dir); + err = fscrypt_prepare_readdir(dir); if (err) return err; @@ -953,7 +962,7 @@ static int ubifs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (err) return err; - err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + err = ubifs_prepare_create(dir, dentry, &nm); if (err) goto out_budg; @@ -1038,7 +1047,7 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, return err; } - err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + err = ubifs_prepare_create(dir, dentry, &nm); if (err) { kfree(dev); goto out_budg; @@ -1122,7 +1131,7 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry, if (err) return err; - err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + err = ubifs_prepare_create(dir, dentry, &nm); if (err) goto out_budg; @@ -1610,14 +1619,6 @@ int ubifs_getattr(const struct path *path, struct kstat *stat, return 0; } -static int ubifs_dir_open(struct inode *dir, struct file *file) -{ - if (IS_ENCRYPTED(dir)) - return fscrypt_get_encryption_info(dir) ? -EACCES : 0; - - return 0; -} - const struct inode_operations ubifs_dir_inode_operations = { .lookup = ubifs_lookup, .create = ubifs_create, @@ -1644,7 +1645,6 @@ const struct file_operations ubifs_dir_operations = { .iterate_shared = ubifs_readdir, .fsync = ubifs_fsync, .unlocked_ioctl = ubifs_ioctl, - .open = ubifs_dir_open, #ifdef CONFIG_COMPAT .compat_ioctl = ubifs_compat_ioctl, #endif diff --git a/fs/verity/enable.c b/fs/verity/enable.c index 5ab3bbec8108..f7e997a01ad0 100644 --- a/fs/verity/enable.c +++ b/fs/verity/enable.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * fs/verity/enable.c: ioctl to enable verity on a file + * Ioctl to enable verity on a file * * Copyright 2019 Google LLC */ @@ -398,9 +398,9 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *uarg) * Some pages of the file may have been evicted from pagecache after * being used in the Merkle tree construction, then read into pagecache * again by another process reading from the file concurrently. Since - * these pages didn't undergo verification against the file measurement - * which fs-verity now claims to be enforcing, we have to wipe the - * pagecache to ensure that all future reads are verified. + * these pages didn't undergo verification against the file digest which + * fs-verity now claims to be enforcing, we have to wipe the pagecache + * to ensure that all future reads are verified. */ filemap_write_and_wait(inode->i_mapping); invalidate_inode_pages2(inode->i_mapping); diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h index e96d99d5145e..6413d28664d6 100644 --- a/fs/verity/fsverity_private.h +++ b/fs/verity/fsverity_private.h @@ -14,7 +14,7 @@ #define pr_fmt(fmt) "fs-verity: " fmt -#include <crypto/sha.h> +#include <crypto/sha2.h> #include <linux/fsverity.h> #include <linux/mempool.h> @@ -67,52 +67,22 @@ struct merkle_tree_params { * When a verity file is first opened, an instance of this struct is allocated * and stored in ->i_verity_info; it remains until the inode is evicted. It * caches information about the Merkle tree that's needed to efficiently verify - * data read from the file. It also caches the file measurement. The Merkle - * tree pages themselves are not cached here, but the filesystem may cache them. + * data read from the file. It also caches the file digest. The Merkle tree + * pages themselves are not cached here, but the filesystem may cache them. */ struct fsverity_info { struct merkle_tree_params tree_params; u8 root_hash[FS_VERITY_MAX_DIGEST_SIZE]; - u8 measurement[FS_VERITY_MAX_DIGEST_SIZE]; + u8 file_digest[FS_VERITY_MAX_DIGEST_SIZE]; const struct inode *inode; }; -/* - * Merkle tree properties. The file measurement is the hash of this structure - * excluding the signature and with the sig_size field set to 0. - */ -struct fsverity_descriptor { - __u8 version; /* must be 1 */ - __u8 hash_algorithm; /* Merkle tree hash algorithm */ - __u8 log_blocksize; /* log2 of size of data and tree blocks */ - __u8 salt_size; /* size of salt in bytes; 0 if none */ - __le32 sig_size; /* size of signature in bytes; 0 if none */ - __le64 data_size; /* size of file the Merkle tree is built over */ - __u8 root_hash[64]; /* Merkle tree root hash */ - __u8 salt[32]; /* salt prepended to each hashed block */ - __u8 __reserved[144]; /* must be 0's */ - __u8 signature[]; /* optional PKCS#7 signature */ -}; - /* Arbitrary limit to bound the kmalloc() size. Can be changed. */ #define FS_VERITY_MAX_DESCRIPTOR_SIZE 16384 #define FS_VERITY_MAX_SIGNATURE_SIZE (FS_VERITY_MAX_DESCRIPTOR_SIZE - \ sizeof(struct fsverity_descriptor)) -/* - * Format in which verity file measurements are signed. This is the same as - * 'struct fsverity_digest', except here some magic bytes are prepended to - * provide some context about what is being signed in case the same key is used - * for non-fsverity purposes, and here the fields have fixed endianness. - */ -struct fsverity_signed_digest { - char magic[8]; /* must be "FSVerity" */ - __le16 digest_algorithm; - __le16 digest_size; - __u8 digest[]; -}; - /* hash_algs.c */ extern struct fsverity_hash_alg fsverity_hash_algs[]; diff --git a/fs/verity/hash_algs.c b/fs/verity/hash_algs.c index c37e186ebeb6..71d0fccb6d4c 100644 --- a/fs/verity/hash_algs.c +++ b/fs/verity/hash_algs.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * fs/verity/hash_algs.c: fs-verity hash algorithms + * fs-verity hash algorithms * * Copyright 2019 Google LLC */ diff --git a/fs/verity/init.c b/fs/verity/init.c index 94c104e00861..c98b7016f446 100644 --- a/fs/verity/init.c +++ b/fs/verity/init.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * fs/verity/init.c: fs-verity module initialization and logging + * fs-verity module initialization and logging * * Copyright 2019 Google LLC */ diff --git a/fs/verity/measure.c b/fs/verity/measure.c index df409a5682ed..f0d7b30c62db 100644 --- a/fs/verity/measure.c +++ b/fs/verity/measure.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * fs/verity/measure.c: ioctl to get a verity file's measurement + * Ioctl to get a verity file's digest * * Copyright 2019 Google LLC */ @@ -10,12 +10,12 @@ #include <linux/uaccess.h> /** - * fsverity_ioctl_measure() - get a verity file's measurement - * @filp: file to get measurement of + * fsverity_ioctl_measure() - get a verity file's digest + * @filp: file to get digest of * @_uarg: user pointer to fsverity_digest * - * Retrieve the file measurement that the kernel is enforcing for reads from a - * verity file. See the "FS_IOC_MEASURE_VERITY" section of + * Retrieve the file digest that the kernel is enforcing for reads from a verity + * file. See the "FS_IOC_MEASURE_VERITY" section of * Documentation/filesystems/fsverity.rst for the documentation. * * Return: 0 on success, -errno on failure @@ -51,7 +51,7 @@ int fsverity_ioctl_measure(struct file *filp, void __user *_uarg) if (copy_to_user(uarg, &arg, sizeof(arg))) return -EFAULT; - if (copy_to_user(uarg->digest, vi->measurement, hash_alg->digest_size)) + if (copy_to_user(uarg->digest, vi->file_digest, hash_alg->digest_size)) return -EFAULT; return 0; diff --git a/fs/verity/open.c b/fs/verity/open.c index bfe0280c14e4..228d0eca3e2e 100644 --- a/fs/verity/open.c +++ b/fs/verity/open.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * fs/verity/open.c: opening fs-verity files + * Opening fs-verity files * * Copyright 2019 Google LLC */ @@ -124,18 +124,18 @@ out_err: } /* - * Compute the file measurement by hashing the fsverity_descriptor excluding the + * Compute the file digest by hashing the fsverity_descriptor excluding the * signature and with the sig_size field set to 0. */ -static int compute_file_measurement(struct fsverity_hash_alg *hash_alg, - struct fsverity_descriptor *desc, - u8 *measurement) +static int compute_file_digest(struct fsverity_hash_alg *hash_alg, + struct fsverity_descriptor *desc, + u8 *file_digest) { __le32 sig_size = desc->sig_size; int err; desc->sig_size = 0; - err = fsverity_hash_buffer(hash_alg, desc, sizeof(*desc), measurement); + err = fsverity_hash_buffer(hash_alg, desc, sizeof(*desc), file_digest); desc->sig_size = sig_size; return err; @@ -199,15 +199,15 @@ struct fsverity_info *fsverity_create_info(const struct inode *inode, memcpy(vi->root_hash, desc->root_hash, vi->tree_params.digest_size); - err = compute_file_measurement(vi->tree_params.hash_alg, desc, - vi->measurement); + err = compute_file_digest(vi->tree_params.hash_alg, desc, + vi->file_digest); if (err) { - fsverity_err(inode, "Error %d computing file measurement", err); + fsverity_err(inode, "Error %d computing file digest", err); goto out; } - pr_debug("Computed file measurement: %s:%*phN\n", + pr_debug("Computed file digest: %s:%*phN\n", vi->tree_params.hash_alg->name, - vi->tree_params.digest_size, vi->measurement); + vi->tree_params.digest_size, vi->file_digest); err = fsverity_verify_signature(vi, desc, desc_size); out: @@ -354,7 +354,7 @@ int __init fsverity_init_info_cache(void) { fsverity_info_cachep = KMEM_CACHE_USERCOPY(fsverity_info, SLAB_RECLAIM_ACCOUNT, - measurement); + file_digest); if (!fsverity_info_cachep) return -ENOMEM; return 0; diff --git a/fs/verity/signature.c b/fs/verity/signature.c index b14ed96387ec..012468eda2a7 100644 --- a/fs/verity/signature.c +++ b/fs/verity/signature.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * fs/verity/signature.c: verification of builtin signatures + * Verification of builtin signatures * * Copyright 2019 Google LLC */ @@ -32,8 +32,8 @@ static struct key *fsverity_keyring; * @desc: the file's fsverity_descriptor * @desc_size: size of @desc * - * If the file's fs-verity descriptor includes a signature of the file - * measurement, verify it against the certificates in the fs-verity keyring. + * If the file's fs-verity descriptor includes a signature of the file digest, + * verify it against the certificates in the fs-verity keyring. * * Return: 0 on success (signature valid or not required); -errno on failure */ @@ -44,7 +44,7 @@ int fsverity_verify_signature(const struct fsverity_info *vi, const struct inode *inode = vi->inode; const struct fsverity_hash_alg *hash_alg = vi->tree_params.hash_alg; const u32 sig_size = le32_to_cpu(desc->sig_size); - struct fsverity_signed_digest *d; + struct fsverity_formatted_digest *d; int err; if (sig_size == 0) { @@ -67,7 +67,7 @@ int fsverity_verify_signature(const struct fsverity_info *vi, memcpy(d->magic, "FSVerity", 8); d->digest_algorithm = cpu_to_le16(hash_alg - fsverity_hash_algs); d->digest_size = cpu_to_le16(hash_alg->digest_size); - memcpy(d->digest, vi->measurement, hash_alg->digest_size); + memcpy(d->digest, vi->file_digest, hash_alg->digest_size); err = verify_pkcs7_signature(d, sizeof(*d) + hash_alg->digest_size, desc->signature, sig_size, @@ -90,8 +90,8 @@ int fsverity_verify_signature(const struct fsverity_info *vi, return err; } - pr_debug("Valid signature for file measurement %s:%*phN\n", - hash_alg->name, hash_alg->digest_size, vi->measurement); + pr_debug("Valid signature for file digest %s:%*phN\n", + hash_alg->name, hash_alg->digest_size, vi->file_digest); return 0; } diff --git a/fs/verity/verify.c b/fs/verity/verify.c index a8b68c6f663d..0adb970f4e73 100644 --- a/fs/verity/verify.c +++ b/fs/verity/verify.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * fs/verity/verify.c: data verification functions, i.e. hooks for ->readpages() + * Data verification functions, i.e. hooks for ->readpages() * * Copyright 2019 Google LLC */ diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index ff5930be096c..bec47f2d074b 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -691,21 +691,23 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) bio->bi_opf |= REQ_FUA; ret = bio_iov_iter_get_pages(bio, from); - if (unlikely(ret)) { - bio_io_error(bio); - return ret; - } + if (unlikely(ret)) + goto out_release; + size = bio->bi_iter.bi_size; - task_io_account_write(ret); + task_io_account_write(size); if (iocb->ki_flags & IOCB_HIPRI) bio_set_polled(bio, iocb); ret = submit_bio_wait(bio); + zonefs_file_write_dio_end_io(iocb, size, ret, 0); + +out_release: + bio_release_pages(bio, false); bio_put(bio); - zonefs_file_write_dio_end_io(iocb, size, ret, 0); if (ret >= 0) { iocb->ki_pos += size; return size; |