Merge "Merge 8ad78685ff ("Merge tag 'pstore-v6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux") into android-mainline" into android-mainline

MAINTAINERS

@@ -14734,7 +14734,7 @@ NETWORKING [LABELED] (NetLabel, Labeled IPsec, SECMARK)
 M:	Paul Moore <paul@paul-moore.com>
 L:	netdev@vger.kernel.org
 L:	linux-security-module@vger.kernel.org
-S:	Maintained
+S:	Supported
 W:	https://github.com/netlabel
 F:	Documentation/netlabel/
 F:	include/net/calipso.h

arch/Kconfig

@@ -1214,13 +1214,6 @@ config COMPAT_32BIT_TIME
 config ARCH_NO_PREEMPT
 	bool
 
-config ARCH_EPHEMERAL_INODES
-	def_bool n
-	help
-	  An arch should select this symbol if it doesn't keep track of inode
-	  instances on its own, but instead relies on something else (e.g. the
-	  host kernel for an UML kernel).
-
 config ARCH_SUPPORTS_RT
 	bool
 

arch/um/Kconfig

@@ -5,7 +5,6 @@ menu "UML-specific options"
 config UML
 	bool
 	default y
-	select ARCH_EPHEMERAL_INODES
 	select ARCH_HAS_CPU_FINALIZE_INIT
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL

fs/binfmt_elf.c

@@ -1517,7 +1517,7 @@ static void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offset)
 	phdr->p_filesz = sz;
 	phdr->p_memsz = 0;
 	phdr->p_flags = 0;
-	phdr->p_align = 0;
+	phdr->p_align = 4;
 }
 
 static void fill_note(struct memelfnote *note, const char *name, int type,
@@ -1773,7 +1773,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 	/*
 	 * NT_PRSTATUS is the one special case, because the regset data
 	 * goes into the pr_reg field inside the note contents, rather
-	 * than being the whole note contents.  We fill the reset in here.
+	 * than being the whole note contents.  We fill the regset in here.
 	 * We assume that regset 0 is NT_PRSTATUS.
 	 */
 	fill_prstatus(&t->prstatus.common, t->task, signr);

fs/binfmt_elf_fdpic.c

@@ -743,12 +743,12 @@ static int elf_fdpic_map_file(struct elf_fdpic_params *params,
 	struct elf32_fdpic_loadmap *loadmap;
 #ifdef CONFIG_MMU
 	struct elf32_fdpic_loadseg *mseg;
+	unsigned long load_addr;
 #endif
 	struct elf32_fdpic_loadseg *seg;
 	struct elf32_phdr *phdr;
-	unsigned long load_addr, stop;
 	unsigned nloads, tmp;
-	size_t size;
+	unsigned long stop;
 	int loop, ret;
 
 	/* allocate a load map table */
@@ -760,8 +760,7 @@ static int elf_fdpic_map_file(struct elf_fdpic_params *params,
 	if (nloads == 0)
 		return -ELIBBAD;
 
-	size = sizeof(*loadmap) + nloads * sizeof(*seg);
-	loadmap = kzalloc(size, GFP_KERNEL);
+	loadmap = kzalloc(struct_size(loadmap, segs, nloads), GFP_KERNEL);
 	if (!loadmap)
 		return -ENOMEM;
 
@@ -770,9 +769,6 @@ static int elf_fdpic_map_file(struct elf_fdpic_params *params,
 	loadmap->version = ELF32_FDPIC_LOADMAP_VERSION;
 	loadmap->nsegs = nloads;
 
-	load_addr = params->load_addr;
-	seg = loadmap->segs;
-
 	/* map the requested LOADs into the memory space */
 	switch (params->flags & ELF_FDPIC_FLAG_ARRANGEMENT) {
 	case ELF_FDPIC_FLAG_CONSTDISP:
@@ -1269,7 +1265,7 @@ static inline void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offs
 	phdr->p_filesz = sz;
 	phdr->p_memsz = 0;
 	phdr->p_flags = 0;
-	phdr->p_align = 0;
+	phdr->p_align = 4;
 	return;
 }
 

fs/hostfs/hostfs.h

@@ -65,6 +65,7 @@ struct hostfs_stat {
 	unsigned long long blocks;
 	unsigned int maj;
 	unsigned int min;
+	dev_t dev;
 };
 
 extern int stat_file(const char *path, struct hostfs_stat *p, int fd);

fs/hostfs/hostfs_kern.c

@@ -26,6 +26,7 @@ struct hostfs_inode_info {
 	fmode_t mode;
 	struct inode vfs_inode;
 	struct mutex open_mutex;
+	dev_t dev;
 };
 
 static inline struct hostfs_inode_info *HOSTFS_I(struct inode *inode)
@@ -182,14 +183,6 @@ static char *follow_link(char *link)
 	return ERR_PTR(n);
 }
 
-static struct inode *hostfs_iget(struct super_block *sb)
-{
-	struct inode *inode = new_inode(sb);
-	if (!inode)
-		return ERR_PTR(-ENOMEM);
-	return inode;
-}
-
 static int hostfs_statfs(struct dentry *dentry, struct kstatfs *sf)
 {
 	/*
@@ -228,6 +221,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb)
 		return NULL;
 	hi->fd = -1;
 	hi->mode = 0;
+	hi->dev = 0;
 	inode_init_once(&hi->vfs_inode);
 	mutex_init(&hi->open_mutex);
 	return &hi->vfs_inode;
@@ -240,6 +234,7 @@ static void hostfs_evict_inode(struct inode *inode)
 	if (HOSTFS_I(inode)->fd != -1) {
 		close_file(&HOSTFS_I(inode)->fd);
 		HOSTFS_I(inode)->fd = -1;
+		HOSTFS_I(inode)->dev = 0;
 	}
 }
 
@@ -265,6 +260,7 @@ static int hostfs_show_options(struct seq_file *seq, struct dentry *root)
 static const struct super_operations hostfs_sbops = {
 	.alloc_inode	= hostfs_alloc_inode,
 	.free_inode	= hostfs_free_inode,
+	.drop_inode	= generic_delete_inode,
 	.evict_inode	= hostfs_evict_inode,
 	.statfs		= hostfs_statfs,
 	.show_options	= hostfs_show_options,
@@ -512,18 +508,31 @@ static const struct address_space_operations hostfs_aops = {
 	.write_end	= hostfs_write_end,
 };
 
-static int read_name(struct inode *ino, char *name)
+static int hostfs_inode_update(struct inode *ino, const struct hostfs_stat *st)
 {
+	set_nlink(ino, st->nlink);
+	i_uid_write(ino, st->uid);
+	i_gid_write(ino, st->gid);
+	ino->i_atime =
+		(struct timespec64){ st->atime.tv_sec, st->atime.tv_nsec };
+	ino->i_mtime =
+		(struct timespec64){ st->mtime.tv_sec, st->mtime.tv_nsec };
+	ino->i_ctime =
+		(struct timespec64){ st->ctime.tv_sec, st->ctime.tv_nsec };
+	ino->i_size = st->size;
+	ino->i_blocks = st->blocks;
+	return 0;
+}
+
+static int hostfs_inode_set(struct inode *ino, void *data)
+{
+	struct hostfs_stat *st = data;
 	dev_t rdev;
-	struct hostfs_stat st;
-	int err = stat_file(name, &st, -1);
-	if (err)
-		return err;
 
 	/* Reencode maj and min with the kernel encoding.*/
-	rdev = MKDEV(st.maj, st.min);
+	rdev = MKDEV(st->maj, st->min);
 
-	switch (st.mode & S_IFMT) {
+	switch (st->mode & S_IFMT) {
 	case S_IFLNK:
 		ino->i_op = &hostfs_link_iops;
 		break;
@@ -535,7 +544,7 @@ static int read_name(struct inode *ino, char *name)
 	case S_IFBLK:
 	case S_IFIFO:
 	case S_IFSOCK:
-		init_special_inode(ino, st.mode & S_IFMT, rdev);
+		init_special_inode(ino, st->mode & S_IFMT, rdev);
 		ino->i_op = &hostfs_iops;
 		break;
 	case S_IFREG:
@@ -547,17 +556,42 @@ static int read_name(struct inode *ino, char *name)
 		return -EIO;
 	}
 
-	ino->i_ino = st.ino;
-	ino->i_mode = st.mode;
-	set_nlink(ino, st.nlink);
-	i_uid_write(ino, st.uid);
-	i_gid_write(ino, st.gid);
-	ino->i_atime = (struct timespec64){ st.atime.tv_sec, st.atime.tv_nsec };
-	ino->i_mtime = (struct timespec64){ st.mtime.tv_sec, st.mtime.tv_nsec };
-	ino->i_ctime = (struct timespec64){ st.ctime.tv_sec, st.ctime.tv_nsec };
-	ino->i_size = st.size;
-	ino->i_blocks = st.blocks;
-	return 0;
+	HOSTFS_I(ino)->dev = st->dev;
+	ino->i_ino = st->ino;
+	ino->i_mode = st->mode;
+	return hostfs_inode_update(ino, st);
+}
+
+static int hostfs_inode_test(struct inode *inode, void *data)
+{
+	const struct hostfs_stat *st = data;
+
+	return inode->i_ino == st->ino && HOSTFS_I(inode)->dev == st->dev;
+}
+
+static struct inode *hostfs_iget(struct super_block *sb, char *name)
+{
+	struct inode *inode;
+	struct hostfs_stat st;
+	int err = stat_file(name, &st, -1);
+
+	if (err)
+		return ERR_PTR(err);
+
+	inode = iget5_locked(sb, st.ino, hostfs_inode_test, hostfs_inode_set,
+			     &st);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	if (inode->i_state & I_NEW) {
+		unlock_new_inode(inode);
+	} else {
+		spin_lock(&inode->i_lock);
+		hostfs_inode_update(inode, &st);
+		spin_unlock(&inode->i_lock);
+	}
+
+	return inode;
 }
 
 static int hostfs_create(struct mnt_idmap *idmap, struct inode *dir,
@@ -565,62 +599,48 @@ static int hostfs_create(struct mnt_idmap *idmap, struct inode *dir,
 {
 	struct inode *inode;
 	char *name;
-	int error, fd;
+	int fd;
 
-	inode = hostfs_iget(dir->i_sb);
-	if (IS_ERR(inode)) {
-		error = PTR_ERR(inode);
-		goto out;
-	}
-
-	error = -ENOMEM;
 	name = dentry_name(dentry);
 	if (name == NULL)
-		goto out_put;
+		return -ENOMEM;
 
 	fd = file_create(name, mode & 0777);
-	if (fd < 0)
-		error = fd;
-	else
-		error = read_name(inode, name);
+	if (fd < 0) {
+		__putname(name);
+		return fd;
+	}
 
+	inode = hostfs_iget(dir->i_sb, name);
 	__putname(name);
-	if (error)
-		goto out_put;
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
 
 	HOSTFS_I(inode)->fd = fd;
 	HOSTFS_I(inode)->mode = FMODE_READ | FMODE_WRITE;
 	d_instantiate(dentry, inode);
 	return 0;
-
- out_put:
-	iput(inode);
- out:
-	return error;
 }
 
 static struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry,
 				    unsigned int flags)
 {
-	struct inode *inode;
+	struct inode *inode = NULL;
 	char *name;
-	int err;
 
-	inode = hostfs_iget(ino->i_sb);
-	if (IS_ERR(inode))
-		goto out;
-
-	err = -ENOMEM;
 	name = dentry_name(dentry);
-	if (name) {
-		err = read_name(inode, name);
-		__putname(name);
+	if (name == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	inode = hostfs_iget(ino->i_sb, name);
+	__putname(name);
+	if (IS_ERR(inode)) {
+		if (PTR_ERR(inode) == -ENOENT)
+			inode = NULL;
+		else
+			return ERR_CAST(inode);
 	}
-	if (err) {
-		iput(inode);
-		inode = (err == -ENOENT) ? NULL : ERR_PTR(err);
-	}
- out:
+
 	return d_splice_alias(inode, dentry);
 }
 
@@ -704,35 +724,23 @@ static int hostfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	char *name;
 	int err;
 
-	inode = hostfs_iget(dir->i_sb);
-	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
-		goto out;
-	}
-
-	err = -ENOMEM;
 	name = dentry_name(dentry);
 	if (name == NULL)
-		goto out_put;
+		return -ENOMEM;
 
 	err = do_mknod(name, mode, MAJOR(dev), MINOR(dev));
-	if (err)
-		goto out_free;
+	if (err) {
+		__putname(name);
+		return err;
+	}
 
-	err = read_name(inode, name);
+	inode = hostfs_iget(dir->i_sb, name);
 	__putname(name);
-	if (err)
-		goto out_put;
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
 
 	d_instantiate(dentry, inode);
 	return 0;
-
- out_free:
-	__putname(name);
- out_put:
-	iput(inode);
- out:
-	return err;
 }
 
 static int hostfs_rename2(struct mnt_idmap *idmap,
@@ -929,49 +937,40 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent)
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	err = super_setup_bdi(sb);
 	if (err)
-		goto out;
+		return err;
 
 	/* NULL is printed as '(null)' by printf(): avoid that. */
 	if (req_root == NULL)
 		req_root = "";
 
-	err = -ENOMEM;
 	sb->s_fs_info = host_root_path =
 		kasprintf(GFP_KERNEL, "%s/%s", root_ino, req_root);
 	if (host_root_path == NULL)
-		goto out;
+		return -ENOMEM;
 
-	root_inode = new_inode(sb);
-	if (!root_inode)
-		goto out;
-
-	err = read_name(root_inode, host_root_path);
-	if (err)
-		goto out_put;
+	root_inode = hostfs_iget(sb, host_root_path);
+	if (IS_ERR(root_inode))
+		return PTR_ERR(root_inode);
 
 	if (S_ISLNK(root_inode->i_mode)) {
-		char *name = follow_link(host_root_path);
-		if (IS_ERR(name)) {
-			err = PTR_ERR(name);
-			goto out_put;
-		}
-		err = read_name(root_inode, name);
+		char *name;
+
+		iput(root_inode);
+		name = follow_link(host_root_path);
+		if (IS_ERR(name))
+			return PTR_ERR(name);
+
+		root_inode = hostfs_iget(sb, name);
 		kfree(name);
-		if (err)
-			goto out_put;
+		if (IS_ERR(root_inode))
+			return PTR_ERR(root_inode);
 	}
 
-	err = -ENOMEM;
 	sb->s_root = d_make_root(root_inode);
 	if (sb->s_root == NULL)
-		goto out;
+		return -ENOMEM;
 
 	return 0;
-
-out_put:
-	iput(root_inode);
-out:
-	return err;
 }
 
 static struct dentry *hostfs_read_sb(struct file_system_type *type,

fs/hostfs/hostfs_user.c

@@ -36,6 +36,7 @@ static void stat64_to_hostfs(const struct stat64 *buf, struct hostfs_stat *p)
 	p->blocks = buf->st_blocks;
 	p->maj = os_major(buf->st_rdev);
 	p->min = os_minor(buf->st_rdev);
+	p->dev = buf->st_dev;
 }
 
 int stat_file(const char *path, struct hostfs_stat *p, int fd)

fs/proc/vmcore.c

@@ -877,7 +877,7 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
 	phdr.p_offset  = roundup(note_off, PAGE_SIZE);
 	phdr.p_vaddr   = phdr.p_paddr = 0;
 	phdr.p_filesz  = phdr.p_memsz = phdr_sz;
-	phdr.p_align   = 0;
+	phdr.p_align   = 4;
 
 	/* Add merged PT_NOTE program header*/
 	tmp = elfptr + sizeof(Elf64_Ehdr);
@@ -1068,7 +1068,7 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
 	phdr.p_offset  = roundup(note_off, PAGE_SIZE);
 	phdr.p_vaddr   = phdr.p_paddr = 0;
 	phdr.p_filesz  = phdr.p_memsz = phdr_sz;
-	phdr.p_align   = 0;
+	phdr.p_align   = 4;
 
 	/* Add merged PT_NOTE program header*/
 	tmp = elfptr + sizeof(Elf32_Ehdr);

fs/pstore/ram.c

@@ -875,7 +875,7 @@ fail_out:
 	return err;
 }
 
-static int ramoops_remove(struct platform_device *pdev)
+static void ramoops_remove(struct platform_device *pdev)
 {
 	struct ramoops_context *cxt = &oops_cxt;
 
@@ -885,8 +885,6 @@ static int ramoops_remove(struct platform_device *pdev)
 	cxt->pstore.bufsize = 0;
 
 	ramoops_free_przs(cxt);
-
-	return 0;
 }
 
 static const struct of_device_id dt_match[] = {
@@ -896,7 +894,7 @@ static const struct of_device_id dt_match[] = {
 
 static struct platform_driver ramoops_driver = {
 	.probe		= ramoops_probe,
-	.remove		= ramoops_remove,
+	.remove_new	= ramoops_remove,
 	.driver		= {
 		.name		= "ramoops",
 		.of_match_table	= dt_match,

fs/pstore/ram_core.c

@@ -599,6 +599,8 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
 	raw_spin_lock_init(&prz->buffer_lock);
 	prz->flags = flags;
 	prz->label = kstrdup(label, GFP_KERNEL);
+	if (!prz->label)
+		goto err;
 
 	ret = persistent_ram_buffer_map(start, size, prz, memtype);
 	if (ret)

fs/reiserfs/xattr_security.c

@@ -67,6 +67,7 @@ int reiserfs_security_init(struct inode *dir, struct inode *inode,
 
 	sec->name = NULL;
 	sec->value = NULL;
+	sec->length = 0;
 
 	/* Don't add selinux attributes on xattrs - they'll never get used */
 	if (IS_PRIVATE(dir))

include/linux/audit.h

@@ -130,8 +130,6 @@ extern unsigned compat_dir_class[];
 extern unsigned compat_chattr_class[];
 extern unsigned compat_signal_class[];
 
-extern int audit_classify_compat_syscall(int abi, unsigned syscall);
-
 /* audit_names->type values */
 #define	AUDIT_TYPE_UNKNOWN	0	/* we don't know yet */
 #define	AUDIT_TYPE_NORMAL	1	/* a "normal" audit record */

include/linux/audit_arch.h

@@ -21,4 +21,6 @@ enum auditsc_class_t {
 	AUDITSC_NVALS /* count */
 };
 
+extern int audit_classify_compat_syscall(int abi, unsigned syscall);
+
 #endif

include/linux/lsm_hook_defs.h

@@ -343,6 +343,7 @@ LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc,
 	 struct sock *sk, struct sock *newsk)
 LSM_HOOK(int, 0, sctp_assoc_established, struct sctp_association *asoc,
 	 struct sk_buff *skb)
+LSM_HOOK(int, 0, mptcp_add_subflow, struct sock *sk, struct sock *ssk)
 #endif /* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_INFINIBAND

include/linux/security.h

@@ -1465,6 +1465,7 @@ void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk,
 			    struct sock *newsk);
 int security_sctp_assoc_established(struct sctp_association *asoc,
 				    struct sk_buff *skb);
+int security_mptcp_add_subflow(struct sock *sk, struct sock *ssk);
 
 #else	/* CONFIG_SECURITY_NETWORK */
 static inline int security_unix_stream_connect(struct sock *sock,
@@ -1692,6 +1693,11 @@ static inline int security_sctp_assoc_established(struct sctp_association *asoc,
 {
 	return 0;
 }
+
+static inline int security_mptcp_add_subflow(struct sock *sk, struct sock *ssk)
+{
+	return 0;
+}
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_INFINIBAND

include/uapi/linux/capability.h

@@ -41,11 +41,12 @@ typedef struct __user_cap_header_struct {
 	int pid;
 } __user *cap_user_header_t;
 
-typedef struct __user_cap_data_struct {
+struct __user_cap_data_struct {
         __u32 effective;
         __u32 permitted;
         __u32 inheritable;
-} __user *cap_user_data_t;
+};
+typedef struct __user_cap_data_struct __user *cap_user_data_t;
 
 
 #define VFS_CAP_REVISION_MASK	0xFF000000

include/uapi/linux/elf.h

@@ -372,7 +372,8 @@ typedef struct elf64_shdr {
  * Notes used in ET_CORE. Architectures export some of the arch register sets
  * using the corresponding note types via the PTRACE_GETREGSET and
  * PTRACE_SETREGSET requests.
- * The note name for all these is "LINUX".
+ * The note name for these types is "LINUX", except NT_PRFPREG that is named
+ * "CORE".
  */
 #define NT_PRSTATUS	1
 #define NT_PRFPREG	2

kernel/audit.h

@@ -259,8 +259,8 @@ extern struct tty_struct *audit_get_tty(void);
 extern void audit_put_tty(struct tty_struct *tty);
 
 /* audit watch/mark/tree functions */
-#ifdef CONFIG_AUDITSYSCALL
 extern unsigned int audit_serial(void);
+#ifdef CONFIG_AUDITSYSCALL
 extern int auditsc_get_stamp(struct audit_context *ctx,
 			      struct timespec64 *t, unsigned int *serial);
 

kernel/capability.c

@@ -467,6 +467,7 @@ EXPORT_SYMBOL(file_ns_capable);
 /**
  * privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode?
  * @ns: The user namespace in question
+ * @idmap: idmap of the mount @inode was found from
  * @inode: The inode in question
  *
  * Return true if the inode uid and gid are within the namespace.
@@ -481,6 +482,7 @@ bool privileged_wrt_inode_uidgid(struct user_namespace *ns,
 
 /**
  * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped
+ * @idmap: idmap of the mount @inode was found from
  * @inode: The inode in question
  * @cap: The capability in question
  *

net/mptcp/subflow.c

@@ -1668,6 +1668,10 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 
 	lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING);
 
+	err = security_mptcp_add_subflow(sk, sf->sk);
+	if (err)
+		goto release_ssk;
+
 	/* the newly created socket has to be in the same cgroup as its parent */
 	mptcp_attach_cgroup(sk, sf->sk);
 
@@ -1680,6 +1684,8 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 	get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL);
 	sock_inuse_add(net, 1);
 	err = tcp_set_ulp(sf->sk, "mptcp");
+
+release_ssk:
 	release_sock(sf->sk);
 
 	if (err) {

security/commoncap.c

@@ -314,7 +314,7 @@ int cap_inode_need_killpriv(struct dentry *dentry)
  * the vfsmount must be passed through @idmap. This function will then
  * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs @nop_mnt_idmap.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  *
  * Return: 0 if successful, -ve on error.
  */
@@ -522,7 +522,7 @@ static bool validheader(size_t size, const struct vfs_cap_data *cap)
  * the vfsmount must be passed through @idmap. This function will then
  * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs @nop_mnt_idmap.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  *
  * Return: On success, return the new size; on error, return < 0.
  */
@@ -630,7 +630,7 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps,
  * the vfsmount must be passed through @idmap. This function will then
  * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs @nop_mnt_idmap.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  */
 int get_vfs_caps_from_disk(struct mnt_idmap *idmap,
 			   const struct dentry *dentry,
@@ -1133,7 +1133,7 @@ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags)
 		break;
 
 	case LSM_SETID_FS:
-		/* juggle the capabilties to follow FSUID changes, unless
+		/* juggle the capabilities to follow FSUID changes, unless
 		 * otherwise suppressed
 		 *
 		 * FIXME - is fsuser used for all CAP_FS_MASK capabilities?
@@ -1184,10 +1184,10 @@ static int cap_safe_nice(struct task_struct *p)
 }
 
 /**
- * cap_task_setscheduler - Detemine if scheduler policy change is permitted
+ * cap_task_setscheduler - Determine if scheduler policy change is permitted
  * @p: The task to affect
  *
- * Detemine if the requested scheduler policy change is permitted for the
+ * Determine if the requested scheduler policy change is permitted for the
  * specified task.
  *
  * Return: 0 if permission is granted, -ve if denied.
@@ -1198,11 +1198,11 @@ int cap_task_setscheduler(struct task_struct *p)
 }
 
 /**
- * cap_task_setioprio - Detemine if I/O priority change is permitted
+ * cap_task_setioprio - Determine if I/O priority change is permitted
  * @p: The task to affect
  * @ioprio: The I/O priority to set
  *
- * Detemine if the requested I/O priority change is permitted for the specified
+ * Determine if the requested I/O priority change is permitted for the specified
  * task.
  *
  * Return: 0 if permission is granted, -ve if denied.
@@ -1213,11 +1213,11 @@ int cap_task_setioprio(struct task_struct *p, int ioprio)
 }
 
 /**
- * cap_task_setnice - Detemine if task priority change is permitted
+ * cap_task_setnice - Determine if task priority change is permitted
  * @p: The task to affect
  * @nice: The nice value to set
  *
- * Detemine if the requested task priority change is permitted for the
+ * Determine if the requested task priority change is permitted for the
  * specified task.
  *
  * Return: 0 if permission is granted, -ve if denied.

security/device_cgroup.c

@@ -421,7 +421,7 @@ static bool verify_new_ex(struct dev_cgroup *dev_cgroup,
 		} else {
 			/*
 			 * new exception in the child will add more devices
-			 * that can be acessed, so it can't match any of
+			 * that can be accessed, so it can't match any of
 			 * parent's exceptions, even slightly
 			 */ 
 			match = match_exception_partial(&dev_cgroup->exceptions,
@@ -822,7 +822,6 @@ struct cgroup_subsys devices_cgrp_subsys = {
 
 /**
  * devcgroup_legacy_check_permission - checks if an inode operation is permitted
- * @dev_cgroup: the dev cgroup to be tested against
  * @type: device type
  * @major: device major number
  * @minor: device minor number

security/integrity/evm/evm_crypto.c

@@ -40,7 +40,7 @@ static const char evm_hmac[] = "hmac(sha1)";
 /**
  * evm_set_key() - set EVM HMAC key from the kernel
  * @key: pointer to a buffer with the key data
- * @size: length of the key data
+ * @keylen: length of the key data
  *
  * This function allows setting the EVM HMAC key from the kernel
  * without using the "encrypted" key subsystem keys. It can be used

security/integrity/evm/evm_main.c

@@ -318,7 +318,6 @@ int evm_protected_xattr_if_enabled(const char *req_xattr_name)
 /**
  * evm_read_protected_xattrs - read EVM protected xattr names, lengths, values
  * @dentry: dentry of the read xattrs
- * @inode: inode of the read xattrs
  * @buffer: buffer xattr names, lengths or values are copied to
  * @buffer_size: size of buffer
  * @type: n: names, l: lengths, v: values
@@ -390,6 +389,7 @@ int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer,
  * @xattr_name: requested xattr
  * @xattr_value: requested xattr value
  * @xattr_value_len: requested xattr value length
+ * @iint: inode integrity metadata
  *
  * Calculate the HMAC for the given dentry and verify it against the stored
  * security.evm xattr. For performance, use the xattr value and length
@@ -795,7 +795,9 @@ static int evm_attr_change(struct mnt_idmap *idmap,
 
 /**
  * evm_inode_setattr - prevent updating an invalid EVM extended attribute
+ * @idmap: idmap of the mount
  * @dentry: pointer to the affected dentry
+ * @attr: iattr structure containing the new file attributes
  *
  * Permit update of file attributes when files have a valid EVM signature,
  * except in the case of them having an immutable portable signature.

security/integrity/iint.c

@@ -43,12 +43,10 @@ static struct integrity_iint_cache *__integrity_iint_find(struct inode *inode)
 		else if (inode > iint->inode)
 			n = n->rb_right;
 		else
-			break;
+			return iint;
 	}
-	if (!n)
-		return NULL;
 
-	return iint;
+	return NULL;
 }
 
 /*
@@ -113,10 +111,15 @@ struct integrity_iint_cache *integrity_inode_get(struct inode *inode)
 		parent = *p;
 		test_iint = rb_entry(parent, struct integrity_iint_cache,
 				     rb_node);
-		if (inode < test_iint->inode)
+		if (inode < test_iint->inode) {
 			p = &(*p)->rb_left;
-		else
+		} else if (inode > test_iint->inode) {
 			p = &(*p)->rb_right;
+		} else {
+			write_unlock(&integrity_iint_lock);
+			kmem_cache_free(iint_cache, iint);
+			return test_iint;
+		}
 	}
 
 	iint->inode = inode;

security/integrity/ima/ima_api.c

@@ -13,7 +13,6 @@
 #include <linux/fs.h>
 #include <linux/xattr.h>
 #include <linux/evm.h>
-#include <linux/iversion.h>
 #include <linux/fsverity.h>
 
 #include "ima.h"
@@ -246,10 +245,11 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 	struct inode *inode = file_inode(file);
 	const char *filename = file->f_path.dentry->d_name.name;
 	struct ima_max_digest_data hash;
+	struct kstat stat;
 	int result = 0;
 	int length;
 	void *tmpbuf;
-	u64 i_version;
+	u64 i_version = 0;
 
 	/*
 	 * Always collect the modsig, because IMA might have already collected
@@ -268,7 +268,10 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 	 * to an initial measurement/appraisal/audit, but was modified to
 	 * assume the file changed.
 	 */
-	i_version = inode_query_iversion(inode);
+	result = vfs_getattr_nosec(&file->f_path, &stat, STATX_CHANGE_COOKIE,
+				   AT_STATX_SYNC_AS_STAT);
+	if (!result && (stat.result_mask & STATX_CHANGE_COOKIE))
+		i_version = stat.change_cookie;
 	hash.hdr.algo = algo;
 	hash.hdr.length = hash_digest_size[algo];
 

security/integrity/ima/ima_main.c

@@ -24,7 +24,6 @@
 #include <linux/slab.h>
 #include <linux/xattr.h>
 #include <linux/ima.h>
-#include <linux/iversion.h>
 #include <linux/fs.h>
 
 #include "ima.h"
@@ -164,11 +163,16 @@ static void ima_check_last_writer(struct integrity_iint_cache *iint,
 
 	mutex_lock(&iint->mutex);
 	if (atomic_read(&inode->i_writecount) == 1) {
+		struct kstat stat;
+
 		update = test_and_clear_bit(IMA_UPDATE_XATTR,
 					    &iint->atomic_flags);
-		if (!IS_I_VERSION(inode) ||
-		    !inode_eq_iversion(inode, iint->version) ||
-		    (iint->flags & IMA_NEW_FILE)) {
+		if ((iint->flags & IMA_NEW_FILE) ||
+		    vfs_getattr_nosec(&file->f_path, &stat,
+				      STATX_CHANGE_COOKIE,
+				      AT_STATX_SYNC_AS_STAT) ||
+		    !(stat.result_mask & STATX_CHANGE_COOKIE) ||
+		    stat.change_cookie != iint->version) {
 			iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE);
 			iint->measured_pcrs = 0;
 			if (update)

security/integrity/ima/ima_modsig.c

@@ -89,6 +89,9 @@ int ima_read_modsig(enum ima_hooks func, const void *buf, loff_t buf_len,
 
 /**
  * ima_collect_modsig - Calculate the file hash without the appended signature.
+ * @modsig: parsed module signature
+ * @buf: data to verify the signature on
+ * @size: data size
  *
  * Since the modsig is part of the file contents, the hash used in its signature
  * isn't the same one ordinarily calculated by IMA. Therefore PKCS7 code

security/integrity/ima/ima_policy.c

@@ -721,6 +721,7 @@ static int get_subaction(struct ima_rule_entry *rule, enum ima_hooks func)
  * @secid: LSM secid of the task to be validated
  * @func: IMA hook identifier
  * @mask: requested action (MAY_READ | MAY_WRITE | MAY_APPEND | MAY_EXEC)
+ * @flags: IMA actions to consider (e.g. IMA_MEASURE | IMA_APPRAISE)
  * @pcr: set the pcr to extend
  * @template_desc: the template that should be used for this rule
  * @func_data: func specific data, may be NULL
@@ -1915,7 +1916,7 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
 
 /**
  * ima_parse_add_rule - add a rule to ima_policy_rules
- * @rule - ima measurement policy rule
+ * @rule: ima measurement policy rule
  *
  * Avoid locking by allowing just one writer at a time in ima_write_policy()
  * Returns the length of the rule parsed, an error code on failure

security/landlock/Kconfig

@@ -2,7 +2,7 @@
 
 config SECURITY_LANDLOCK
 	bool "Landlock support"
-	depends on SECURITY && !ARCH_EPHEMERAL_INODES
+	depends on SECURITY
 	select SECURITY_PATH
 	help
 	  Landlock is a sandboxing mechanism that enables processes to restrict

security/lsm_audit.c

@@ -200,7 +200,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 	char comm[sizeof(current->comm)];
 
 	/*
-	 * To keep stack sizes in check force programers to notice if they
+	 * To keep stack sizes in check force programmers to notice if they
 	 * start making this union too large!  See struct lsm_network_audit
 	 * as an example of how to deal with large data.
 	 */

security/safesetid/lsm.c

@@ -131,7 +131,7 @@ static int safesetid_security_capable(const struct cred *cred,
 		 * set*gid() (e.g. setting up userns gid mappings).
 		 */
 		pr_warn("Operation requires CAP_SETGID, which is not available to GID %u for operations besides approved set*gid transitions\n",
-			__kuid_val(cred->uid));
+			__kgid_val(cred->gid));
 		return -EPERM;
 	default:
 		/* Error, the only capabilities were checking for is CAP_SETUID/GID */

security/security.c

@@ -2491,7 +2491,7 @@ int security_inode_copy_up_xattr(const char *name)
 	/*
 	 * The implementation can return 0 (accept the xattr), 1 (discard the
 	 * xattr), -EOPNOTSUPP if it does not know anything about the xattr or
-	 * any other error code incase of an error.
+	 * any other error code in case of an error.
 	 */
 	hlist_for_each_entry(hp,
 			     &security_hook_heads.inode_copy_up_xattr, list) {
@@ -4667,6 +4667,23 @@ int security_sctp_assoc_established(struct sctp_association *asoc,
 }
 EXPORT_SYMBOL(security_sctp_assoc_established);
 
+/**
+ * security_mptcp_add_subflow() - Inherit the LSM label from the MPTCP socket
+ * @sk: the owning MPTCP socket
+ * @ssk: the new subflow
+ *
+ * Update the labeling for the given MPTCP subflow, to match the one of the
+ * owning MPTCP socket. This hook has to be called after the socket creation and
+ * initialization via the security_socket_create() and
+ * security_socket_post_create() LSM hooks.
+ *
+ * Return: Returns 0 on success or a negative error code on failure.
+ */
+int security_mptcp_add_subflow(struct sock *sk, struct sock *ssk)
+{
+	return call_int_hook(mptcp_add_subflow, 0, sk, ssk);
+}
+
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_INFINIBAND
@@ -4676,7 +4693,7 @@ EXPORT_SYMBOL(security_sctp_assoc_established);
  * @subnet_prefix: subnet prefix of the port
  * @pkey: IB pkey
  *
- * Check permission to access a pkey when modifing a QP.
+ * Check permission to access a pkey when modifying a QP.
  *
  * Return: Returns 0 if permission is granted.
  */

security/selinux/Makefile

@@ -3,32 +3,38 @@
 # Makefile for building the SELinux module as part of the kernel tree.
 #
 
+# NOTE: There are a number of improvements that can be made to this Makefile
+# once the kernel requires make v4.3 or greater; the most important feature
+# lacking in older versions of make is support for grouped targets.  These
+# improvements are noted inline in the Makefile below ...
+
 obj-$(CONFIG_SECURITY_SELINUX) := selinux.o
 
+ccflags-y := -I$(srctree)/security/selinux -I$(srctree)/security/selinux/include
+
 selinux-y := avc.o hooks.o selinuxfs.o netlink.o nlmsgtab.o netif.o \
 	     netnode.o netport.o status.o \
 	     ss/ebitmap.o ss/hashtab.o ss/symtab.o ss/sidtab.o ss/avtab.o \
 	     ss/policydb.o ss/services.o ss/conditional.o ss/mls.o ss/context.o
 
 selinux-$(CONFIG_SECURITY_NETWORK_XFRM) += xfrm.o
-
 selinux-$(CONFIG_NETLABEL) += netlabel.o
-
 selinux-$(CONFIG_SECURITY_INFINIBAND) += ibpkey.o
-
 selinux-$(CONFIG_IMA) += ima.o
 
-ccflags-y := -I$(srctree)/security/selinux -I$(srctree)/security/selinux/include
+genhdrs := flask.h av_permissions.h
 
+# see the note above, replace the dependency rule with the one below:
+#  $(addprefix $(obj)/,$(selinux-y)): $(addprefix $(obj)/,$(genhdrs))
 $(addprefix $(obj)/,$(selinux-y)): $(obj)/flask.h
 
-quiet_cmd_flask = GEN     $(obj)/flask.h $(obj)/av_permissions.h
-      cmd_flask = $< $(obj)/flask.h $(obj)/av_permissions.h
+quiet_cmd_genhdrs = GEN     $(addprefix $(obj)/,$(genhdrs))
+      cmd_genhdrs = $< $(addprefix $(obj)/,$(genhdrs))
 
-targets += flask.h av_permissions.h
-# once make >= 4.3 is required, we can use grouped targets in the rule below,
-# which basically involves adding both headers and a '&' before the colon, see
-# the example below:
-#   $(obj)/flask.h $(obj)/av_permissions.h &: scripts/selinux/...
+# see the note above, replace the $targets and 'flask.h' rule with the lines
+# below:
+#  targets += $(genhdrs)
+#  $(addprefix $(obj)/,$(genhdrs)) &: scripts/selinux/...
+targets += flask.h
 $(obj)/flask.h: scripts/selinux/genheaders/genheaders FORCE
-	$(call if_changed,flask)
+	$(call if_changed,genhdrs)

security/selinux/avc.c

@@ -650,7 +650,6 @@ static void avc_insert(u32 ssid, u32 tsid, u16 tclass,
 	trace_android_rvh_selinux_avc_insert(node);
 found:
 	spin_unlock_irqrestore(lock, flag);
-	return;
 }
 
 /**
@@ -1211,22 +1210,3 @@ u32 avc_policy_seqno(void)
 {
 	return selinux_avc.avc_cache.latest_notif;
 }
-
-void avc_disable(void)
-{
-	/*
-	 * If you are looking at this because you have realized that we are
-	 * not destroying the avc_node_cachep it might be easy to fix, but
-	 * I don't know the memory barrier semantics well enough to know.  It's
-	 * possible that some other task dereferenced security_ops when
-	 * it still pointed to selinux operations.  If that is the case it's
-	 * possible that it is about to use the avc and is about to need the
-	 * avc_node_cachep.  I know I could wrap the security.c security_ops call
-	 * in an rcu_lock, but seriously, it's not worth it.  Instead I just flush
-	 * the cache and get that memory back.
-	 */
-	if (avc_node_cachep) {
-		avc_flush();
-		/* kmem_cache_destroy(avc_node_cachep); */
-	}
-}

security/selinux/hooks.c

@@ -357,7 +357,7 @@ enum {
 };
 
 #define A(s, has_arg) {#s, sizeof(#s) - 1, Opt_##s, has_arg}
-static struct {
+static const struct {
 	const char *name;
 	int len;
 	int opt;
@@ -605,6 +605,13 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 	u32 defcontext_sid = 0;
 	int rc = 0;
 
+	/*
+	 * Specifying internal flags without providing a place to
+	 * place the results is not allowed
+	 */
+	if (kern_flags && !set_kern_flags)
+		return -EINVAL;
+
 	mutex_lock(&sbsec->lock);
 
 	if (!selinux_initialized()) {
@@ -612,6 +619,10 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 			/* Defer initialization until selinux_complete_init,
 			   after the initial policy is loaded and the security
 			   server is ready to handle calls. */
+			if (kern_flags & SECURITY_LSM_NATIVE_LABELS) {
+				sbsec->flags |= SE_SBNATIVE;
+				*set_kern_flags |= SECURITY_LSM_NATIVE_LABELS;
+			}
 			goto out;
 		}
 		rc = -EINVAL;
@@ -619,12 +630,6 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 			"before the security server is initialized\n");
 		goto out;
 	}
-	if (kern_flags && !set_kern_flags) {
-		/* Specifying internal flags without providing a place to
-		 * place the results is not allowed */
-		rc = -EINVAL;
-		goto out;
-	}
 
 	/*
 	 * Binary mount data FS will come through this function twice.  Once
@@ -757,7 +762,17 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 	 * sets the label used on all file below the mountpoint, and will set
 	 * the superblock context if not already set.
 	 */
-	if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !context_sid) {
+	if (sbsec->flags & SE_SBNATIVE) {
+		/*
+		 * This means we are initializing a superblock that has been
+		 * mounted before the SELinux was initialized and the
+		 * filesystem requested native labeling. We had already
+		 * returned SECURITY_LSM_NATIVE_LABELS in *set_kern_flags
+		 * in the original mount attempt, so now we just need to set
+		 * the SECURITY_FS_USE_NATIVE behavior.
+		 */
+		sbsec->behavior = SECURITY_FS_USE_NATIVE;
+	} else if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !context_sid) {
 		sbsec->behavior = SECURITY_FS_USE_NATIVE;
 		*set_kern_flags |= SECURITY_LSM_NATIVE_LABELS;
 	}
@@ -868,13 +883,6 @@ static int selinux_sb_clone_mnt_opts(const struct super_block *oldsb,
 	int set_context =	(oldsbsec->flags & CONTEXT_MNT);
 	int set_rootcontext =	(oldsbsec->flags & ROOTCONTEXT_MNT);
 
-	/*
-	 * if the parent was able to be mounted it clearly had no special lsm
-	 * mount options.  thus we can safely deal with this superblock later
-	 */
-	if (!selinux_initialized())
-		return 0;
-
 	/*
 	 * Specifying internal flags without providing a place to
 	 * place the results is not allowed.
@@ -882,18 +890,31 @@ static int selinux_sb_clone_mnt_opts(const struct super_block *oldsb,
 	if (kern_flags && !set_kern_flags)
 		return -EINVAL;
 
+	mutex_lock(&newsbsec->lock);
+
+	/*
+	 * if the parent was able to be mounted it clearly had no special lsm
+	 * mount options.  thus we can safely deal with this superblock later
+	 */
+	if (!selinux_initialized()) {
+		if (kern_flags & SECURITY_LSM_NATIVE_LABELS) {
+			newsbsec->flags |= SE_SBNATIVE;
+			*set_kern_flags |= SECURITY_LSM_NATIVE_LABELS;
+		}
+		goto out;
+	}
+
 	/* how can we clone if the old one wasn't set up?? */
 	BUG_ON(!(oldsbsec->flags & SE_SBINITIALIZED));
 
 	/* if fs is reusing a sb, make sure that the contexts match */
 	if (newsbsec->flags & SE_SBINITIALIZED) {
+		mutex_unlock(&newsbsec->lock);
 		if ((kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context)
 			*set_kern_flags |= SECURITY_LSM_NATIVE_LABELS;
 		return selinux_cmp_sb_context(oldsb, newsb);
 	}
 
-	mutex_lock(&newsbsec->lock);
-
 	newsbsec->flags = oldsbsec->flags;
 
 	newsbsec->sid = oldsbsec->sid;
@@ -937,7 +958,7 @@ out:
 }
 
 /*
- * NOTE: the caller is resposible for freeing the memory even if on error.
+ * NOTE: the caller is responsible for freeing the memory even if on error.
  */
 static int selinux_add_opt(int token, const char *s, void **mnt_opts)
 {
@@ -1394,8 +1415,11 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
 	spin_unlock(&isec->lock);
 
 	switch (sbsec->behavior) {
+	/*
+	 * In case of SECURITY_FS_USE_NATIVE we need to re-fetch the labels
+	 * via xattr when called from delayed_superblock_init().
+	 */
 	case SECURITY_FS_USE_NATIVE:
-		break;
 	case SECURITY_FS_USE_XATTR:
 		if (!(inode->i_opflags & IOP_XATTR)) {
 			sid = sbsec->def_sid;
@@ -5379,6 +5403,21 @@ static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk
 	selinux_netlbl_sctp_sk_clone(sk, newsk);
 }
 
+static int selinux_mptcp_add_subflow(struct sock *sk, struct sock *ssk)
+{
+	struct sk_security_struct *ssksec = ssk->sk_security;
+	struct sk_security_struct *sksec = sk->sk_security;
+
+	ssksec->sclass = sksec->sclass;
+	ssksec->sid = sksec->sid;
+
+	/* replace the existing subflow label deleting the existing one
+	 * and re-recreating a new label using the updated context
+	 */
+	selinux_netlbl_sk_security_free(ssksec);
+	return selinux_netlbl_socket_post_create(ssk, ssk->sk_family);
+}
+
 static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
 				     struct request_sock *req)
 {
@@ -7074,6 +7113,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(sctp_sk_clone, selinux_sctp_sk_clone),
 	LSM_HOOK_INIT(sctp_bind_connect, selinux_sctp_bind_connect),
 	LSM_HOOK_INIT(sctp_assoc_established, selinux_sctp_assoc_established),
+	LSM_HOOK_INIT(mptcp_add_subflow, selinux_mptcp_add_subflow),
 	LSM_HOOK_INIT(inet_conn_request, selinux_inet_conn_request),
 	LSM_HOOK_INIT(inet_csk_clone, selinux_inet_csk_clone),
 	LSM_HOOK_INIT(inet_conn_established, selinux_inet_conn_established),

security/selinux/ima.c

@@ -4,7 +4,7 @@
  *
  * Author: Lakshmi Ramasubramanian (nramas@linux.microsoft.com)
  *
- * Measure critical data structures maintainted by SELinux
+ * Measure critical data structures maintained by SELinux
  * using IMA subsystem.
  */
 #include <linux/vmalloc.h>

security/selinux/include/audit.h

@@ -41,7 +41,7 @@ void selinux_audit_rule_free(void *rule);
  *	selinux_audit_rule_match - determine if a context ID matches a rule.
  *	@sid: the context ID to check
  *	@field: the field this rule refers to
- *	@op: the operater the rule uses
+ *	@op: the operator the rule uses
  *	@rule: pointer to the audit rule to check against
  *
  *	Returns 1 if the context id matches the rule, 0 if it does not, and

security/selinux/include/avc.h

@@ -168,9 +168,6 @@ int avc_get_hash_stats(char *page);
 unsigned int avc_get_cache_threshold(void);
 void avc_set_cache_threshold(unsigned int cache_threshold);
 
-/* Attempt to free avc node cache */
-void avc_disable(void);
-
 #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS
 DECLARE_PER_CPU(struct avc_cache_stats, avc_cache_stats);
 #endif

security/selinux/include/ibpkey.h

@@ -15,6 +15,7 @@
 #define _SELINUX_IB_PKEY_H
 
 #include <linux/types.h>
+#include "flask.h"
 
 #ifdef CONFIG_SECURITY_INFINIBAND
 void sel_ib_pkey_flush(void);

security/selinux/include/ima.h

@@ -4,7 +4,7 @@
  *
  * Author: Lakshmi Ramasubramanian (nramas@linux.microsoft.com)
  *
- * Measure critical data structures maintainted by SELinux
+ * Measure critical data structures maintained by SELinux
  * using IMA subsystem.
  */
 

security/selinux/include/initial_sid_to_string.h

@@ -1,4 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/stddef.h>
+
 static const char *const initial_sid_to_string[] = {
 	NULL,
 	"kernel",

security/selinux/include/security.h

@@ -65,6 +65,7 @@
 #define SE_SBPROC		0x0200
 #define SE_SBGENFS		0x0400
 #define SE_SBGENFS_XATTR	0x0800
+#define SE_SBNATIVE		0x1000
 
 #define CONTEXT_STR	"context"
 #define FSCONTEXT_STR	"fscontext"
@@ -400,7 +401,6 @@ struct selinux_kernel_status {
 extern void selinux_status_update_setenforce(int enforcing);
 extern void selinux_status_update_policyload(int seqno);
 extern void selinux_complete_init(void);
-extern void exit_sel_fs(void);
 extern struct path selinux_null;
 extern void selnl_notify_setenforce(int val);
 extern void selnl_notify_policyload(u32 seqno);

security/selinux/netlabel.c

@@ -154,8 +154,12 @@ void selinux_netlbl_err(struct sk_buff *skb, u16 family, int error, int gateway)
  */
 void selinux_netlbl_sk_security_free(struct sk_security_struct *sksec)
 {
-	if (sksec->nlbl_secattr != NULL)
-		netlbl_secattr_free(sksec->nlbl_secattr);
+	if (!sksec->nlbl_secattr)
+		return;
+
+	netlbl_secattr_free(sksec->nlbl_secattr);
+	sksec->nlbl_secattr = NULL;
+	sksec->nlbl_state = NLBL_UNSET;
 }
 
 /**

security/selinux/selinuxfs.c

@@ -951,7 +951,7 @@ static ssize_t sel_write_create(struct file *file, char *buf, size_t size)
 		 * either whitespace or multibyte characters, they shall be
 		 * encoded based on the percentage-encoding rule.
 		 * If not encoded, the sscanf logic picks up only left-half
-		 * of the supplied name; splitted by a whitespace unexpectedly.
+		 * of the supplied name; split by a whitespace unexpectedly.
 		 */
 		char   *r, *w;
 		int     c1, c2;
@@ -1649,7 +1649,7 @@ static int sel_make_ss_files(struct dentry *dir)
 	struct super_block *sb = dir->d_sb;
 	struct selinux_fs_info *fsi = sb->s_fs_info;
 	int i;
-	static struct tree_descr files[] = {
+	static const struct tree_descr files[] = {
 		{ "sidtab_hash_stats", &sel_sidtab_hash_stats_ops, S_IRUGO },
 	};
 

security/selinux/ss/avtab.c

@@ -354,7 +354,7 @@ int avtab_alloc_dup(struct avtab *new, const struct avtab *orig)
 	return avtab_alloc_common(new, orig->nslot);
 }
 
-void avtab_hash_eval(struct avtab *h, char *tag)
+void avtab_hash_eval(struct avtab *h, const char *tag)
 {
 	int i, chain_len, slots_used, max_chain_len;
 	unsigned long long chain2_len_sum;

security/selinux/ss/avtab.h

@@ -92,7 +92,7 @@ int avtab_alloc(struct avtab *, u32);
 int avtab_alloc_dup(struct avtab *new, const struct avtab *orig);
 struct avtab_datum *avtab_search(struct avtab *h, const struct avtab_key *k);
 void avtab_destroy(struct avtab *h);
-void avtab_hash_eval(struct avtab *h, char *tag);
+void avtab_hash_eval(struct avtab *h, const char *tag);
 
 struct policydb;
 int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,

security/selinux/ss/conditional.c

@@ -38,7 +38,7 @@ static int cond_evaluate_expr(struct policydb *p, struct cond_expr *expr)
 			if (sp == (COND_EXPR_MAXDEPTH - 1))
 				return -1;
 			sp++;
-			s[sp] = p->bool_val_to_struct[node->bool - 1]->state;
+			s[sp] = p->bool_val_to_struct[node->boolean - 1]->state;
 			break;
 		case COND_NOT:
 			if (sp < 0)
@@ -366,7 +366,7 @@ static int expr_node_isvalid(struct policydb *p, struct cond_expr_node *expr)
 		return 0;
 	}
 
-	if (expr->bool > p->p_bools.nprim) {
+	if (expr->boolean > p->p_bools.nprim) {
 		pr_err("SELinux: conditional expressions uses unknown bool.\n");
 		return 0;
 	}
@@ -401,7 +401,7 @@ static int cond_read_node(struct policydb *p, struct cond_node *node, void *fp)
 			return rc;
 
 		expr->expr_type = le32_to_cpu(buf[0]);
-		expr->bool = le32_to_cpu(buf[1]);
+		expr->boolean = le32_to_cpu(buf[1]);
 
 		if (!expr_node_isvalid(p, expr))
 			return -EINVAL;
@@ -518,7 +518,7 @@ static int cond_write_node(struct policydb *p, struct cond_node *node,
 
 	for (i = 0; i < node->expr.len; i++) {
 		buf[0] = cpu_to_le32(node->expr.nodes[i].expr_type);
-		buf[1] = cpu_to_le32(node->expr.nodes[i].bool);
+		buf[1] = cpu_to_le32(node->expr.nodes[i].boolean);
 		rc = put_entry(buf, sizeof(u32), 2, fp);
 		if (rc)
 			return rc;

security/selinux/ss/conditional.h

@@ -29,7 +29,7 @@ struct cond_expr_node {
 #define COND_NEQ	7 /* bool != bool */
 #define COND_LAST	COND_NEQ
 	u32 expr_type;
-	u32 bool;
+	u32 boolean;
 };
 
 struct cond_expr {

security/selinux/ss/context.h

@@ -167,6 +167,8 @@ static inline int context_cpy(struct context *dst, const struct context *src)
 	rc = mls_context_cpy(dst, src);
 	if (rc) {
 		kfree(dst->str);
+		dst->str = NULL;
+		dst->len = 0;
 		return rc;
 	}
 	return 0;

security/selinux/ss/policydb.c

@@ -42,7 +42,7 @@
 #include "services.h"
 
 #ifdef DEBUG_HASHES
-static const char *symtab_name[SYM_NUM] = {
+static const char *const symtab_name[SYM_NUM] = {
 	"common prefixes",
 	"classes",
 	"roles",
@@ -2257,6 +2257,10 @@ static int ocontext_read(struct policydb *p, const struct policydb_compat_info *
 				if (rc)
 					goto out;
 
+				if (i == OCON_FS)
+					pr_warn("SELinux:  void and deprecated fs ocon %s\n",
+						c->u.name);
+
 				rc = context_read_and_validate(&c->context[0], p, fp);
 				if (rc)
 					goto out;

security/selinux/ss/policydb.h

@@ -225,7 +225,7 @@ struct genfs {
 
 /* object context array indices */
 #define OCON_ISID	0 /* initial SIDs */
-#define OCON_FS		1 /* unlabeled file systems */
+#define OCON_FS		1 /* unlabeled file systems (deprecated) */
 #define OCON_PORT	2 /* TCP and UDP port numbers */
 #define OCON_NETIF	3 /* network interfaces */
 #define OCON_NODE	4 /* nodes */

security/selinux/ss/services.c

@@ -585,7 +585,7 @@ static void type_attribute_bounds_av(struct policydb *policydb,
 
 /*
  * flag which drivers have permissions
- * only looking for ioctl based extended permssions
+ * only looking for ioctl based extended permissions
  */
 void services_compute_xperms_drivers(
 		struct extended_perms *xperms,
@@ -3548,38 +3548,38 @@ int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule)
 	tmprule = kzalloc(sizeof(struct selinux_audit_rule), GFP_KERNEL);
 	if (!tmprule)
 		return -ENOMEM;
-
 	context_init(&tmprule->au_ctxt);
 
 	rcu_read_lock();
 	policy = rcu_dereference(state->policy);
 	policydb = &policy->policydb;
-
 	tmprule->au_seqno = policy->latest_granting;
-
 	switch (field) {
 	case AUDIT_SUBJ_USER:
 	case AUDIT_OBJ_USER:
-		rc = -EINVAL;
 		userdatum = symtab_search(&policydb->p_users, rulestr);
-		if (!userdatum)
-			goto out;
+		if (!userdatum) {
+			rc = -EINVAL;
+			goto err;
+		}
 		tmprule->au_ctxt.user = userdatum->value;
 		break;
 	case AUDIT_SUBJ_ROLE:
 	case AUDIT_OBJ_ROLE:
-		rc = -EINVAL;
 		roledatum = symtab_search(&policydb->p_roles, rulestr);
-		if (!roledatum)
-			goto out;
+		if (!roledatum) {
+			rc = -EINVAL;
+			goto err;
+		}
 		tmprule->au_ctxt.role = roledatum->value;
 		break;
 	case AUDIT_SUBJ_TYPE:
 	case AUDIT_OBJ_TYPE:
-		rc = -EINVAL;
 		typedatum = symtab_search(&policydb->p_types, rulestr);
-		if (!typedatum)
-			goto out;
+		if (!typedatum) {
+			rc = -EINVAL;
+			goto err;
+		}
 		tmprule->au_ctxt.type = typedatum->value;
 		break;
 	case AUDIT_SUBJ_SEN:
@@ -3589,20 +3589,18 @@ int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule)
 		rc = mls_from_string(policydb, rulestr, &tmprule->au_ctxt,
 				     GFP_ATOMIC);
 		if (rc)
-			goto out;
+			goto err;
 		break;
 	}
-	rc = 0;
-out:
 	rcu_read_unlock();
 
-	if (rc) {
-		selinux_audit_rule_free(tmprule);
-		tmprule = NULL;
-	}
-
 	*rule = tmprule;
+	return 0;
 
+err:
+	rcu_read_unlock();
+	selinux_audit_rule_free(tmprule);
+	*rule = NULL;
 	return rc;
 }
 

security/smack/smack.h

@@ -120,6 +120,7 @@ struct inode_smack {
 struct task_smack {
 	struct smack_known	*smk_task;	/* label for access control */
 	struct smack_known	*smk_forked;	/* label when forked */
+	struct smack_known	*smk_transmuted;/* label when transmuted */
 	struct list_head	smk_rules;	/* per task access rules */
 	struct mutex		smk_rules_lock;	/* lock for the rules */
 	struct list_head	smk_relabel;	/* transit allowed labels */

security/smack/smack_lsm.c

@@ -933,8 +933,9 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir,
 				     const struct qstr *qstr, const char **name,
 				     void **value, size_t *len)
 {
+	struct task_smack *tsp = smack_cred(current_cred());
 	struct inode_smack *issp = smack_inode(inode);
-	struct smack_known *skp = smk_of_current();
+	struct smack_known *skp = smk_of_task(tsp);
 	struct smack_known *isp = smk_of_inode(inode);
 	struct smack_known *dsp = smk_of_inode(dir);
 	int may;
@@ -943,20 +944,34 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir,
 		*name = XATTR_SMACK_SUFFIX;
 
 	if (value && len) {
-		rcu_read_lock();
-		may = smk_access_entry(skp->smk_known, dsp->smk_known,
-				       &skp->smk_rules);
-		rcu_read_unlock();
+		/*
+		 * If equal, transmuting already occurred in
+		 * smack_dentry_create_files_as(). No need to check again.
+		 */
+		if (tsp->smk_task != tsp->smk_transmuted) {
+			rcu_read_lock();
+			may = smk_access_entry(skp->smk_known, dsp->smk_known,
+					       &skp->smk_rules);
+			rcu_read_unlock();
+		}
 
 		/*
-		 * If the access rule allows transmutation and
-		 * the directory requests transmutation then
-		 * by all means transmute.
+		 * In addition to having smk_task equal to smk_transmuted,
+		 * if the access rule allows transmutation and the directory
+		 * requests transmutation then by all means transmute.
 		 * Mark the inode as changed.
 		 */
-		if (may > 0 && ((may & MAY_TRANSMUTE) != 0) &&
-		    smk_inode_transmutable(dir)) {
-			isp = dsp;
+		if ((tsp->smk_task == tsp->smk_transmuted) ||
+		    (may > 0 && ((may & MAY_TRANSMUTE) != 0) &&
+		     smk_inode_transmutable(dir))) {
+			/*
+			 * The caller of smack_dentry_create_files_as()
+			 * should have overridden the current cred, so the
+			 * inode label was already set correctly in
+			 * smack_inode_alloc_security().
+			 */
+			if (tsp->smk_task != tsp->smk_transmuted)
+				isp = dsp;
 			issp->smk_flags |= SMK_INODE_CHANGED;
 		}
 
@@ -1463,10 +1478,19 @@ static int smack_inode_getsecurity(struct mnt_idmap *idmap,
 	struct super_block *sbp;
 	struct inode *ip = inode;
 	struct smack_known *isp;
+	struct inode_smack *ispp;
+	size_t label_len;
+	char *label = NULL;
 
-	if (strcmp(name, XATTR_SMACK_SUFFIX) == 0)
+	if (strcmp(name, XATTR_SMACK_SUFFIX) == 0) {
 		isp = smk_of_inode(inode);
-	else {
+	} else if (strcmp(name, XATTR_SMACK_TRANSMUTE) == 0) {
+		ispp = smack_inode(inode);
+		if (ispp->smk_flags & SMK_INODE_TRANSMUTE)
+			label = TRANS_TRUE;
+		else
+			label = "";
+	} else {
 		/*
 		 * The rest of the Smack xattrs are only on sockets.
 		 */
@@ -1488,13 +1512,18 @@ static int smack_inode_getsecurity(struct mnt_idmap *idmap,
 			return -EOPNOTSUPP;
 	}
 
+	if (!label)
+		label = isp->smk_known;
+
+	label_len = strlen(label);
+
 	if (alloc) {
-		*buffer = kstrdup(isp->smk_known, GFP_KERNEL);
+		*buffer = kstrdup(label, GFP_KERNEL);
 		if (*buffer == NULL)
 			return -ENOMEM;
 	}
 
-	return strlen(isp->smk_known);
+	return label_len;
 }
 
 
@@ -4753,8 +4782,10 @@ static int smack_dentry_create_files_as(struct dentry *dentry, int mode,
 		 * providing access is transmuting use the containing
 		 * directory label instead of the process label.
 		 */
-		if (may > 0 && (may & MAY_TRANSMUTE))
+		if (may > 0 && (may & MAY_TRANSMUTE)) {
 			ntsp->smk_task = isp->smk_inode;
+			ntsp->smk_transmuted = ntsp->smk_task;
+		}
 	}
 	return 0;
 }

tools/testing/selftests/landlock/config

@@ -1,7 +1,10 @@
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
 CONFIG_OVERLAY_FS=y
-CONFIG_SECURITY_LANDLOCK=y
-CONFIG_SECURITY_PATH=y
+CONFIG_PROC_FS=y
 CONFIG_SECURITY=y
+CONFIG_SECURITY_LANDLOCK=y
 CONFIG_SHMEM=y
-CONFIG_TMPFS_XATTR=y
+CONFIG_SYSFS=y
 CONFIG_TMPFS=y
+CONFIG_TMPFS_XATTR=y

tools/testing/selftests/landlock/config.um

@@ -0,0 +1 @@
+CONFIG_HOSTFS=y

tools/testing/selftests/landlock/fs_test.c

@@ -10,6 +10,7 @@
 #define _GNU_SOURCE
 #include <fcntl.h>
 #include <linux/landlock.h>
+#include <linux/magic.h>
 #include <sched.h>
 #include <stdio.h>
 #include <string.h>
@@ -19,6 +20,7 @@
 #include <sys/sendfile.h>
 #include <sys/stat.h>
 #include <sys/sysmacros.h>
+#include <sys/vfs.h>
 #include <unistd.h>
 
 #include "common.h"
@@ -107,8 +109,10 @@ static bool fgrep(FILE *const inf, const char *const str)
 	return false;
 }
 
-static bool supports_overlayfs(void)
+static bool supports_filesystem(const char *const filesystem)
 {
+	char str[32];
+	int len;
 	bool res;
 	FILE *const inf = fopen("/proc/filesystems", "r");
 
@@ -119,11 +123,33 @@ static bool supports_overlayfs(void)
 	if (!inf)
 		return true;
 
-	res = fgrep(inf, "nodev\toverlay\n");
+	/* filesystem can be null for bind mounts. */
+	if (!filesystem)
+		return true;
+
+	len = snprintf(str, sizeof(str), "nodev\t%s\n", filesystem);
+	if (len >= sizeof(str))
+		/* Ignores too-long filesystem names. */
+		return true;
+
+	res = fgrep(inf, str);
 	fclose(inf);
 	return res;
 }
 
+static bool cwd_matches_fs(unsigned int fs_magic)
+{
+	struct statfs statfs_buf;
+
+	if (!fs_magic)
+		return true;
+
+	if (statfs(".", &statfs_buf))
+		return true;
+
+	return statfs_buf.f_type == fs_magic;
+}
+
 static void mkdir_parents(struct __test_metadata *const _metadata,
 			  const char *const path)
 {
@@ -206,7 +232,26 @@ out:
 	return err;
 }
 
-static void prepare_layout(struct __test_metadata *const _metadata)
+struct mnt_opt {
+	const char *const source;
+	const char *const type;
+	const unsigned long flags;
+	const char *const data;
+};
+
+const struct mnt_opt mnt_tmp = {
+	.type = "tmpfs",
+	.data = "size=4m,mode=700",
+};
+
+static int mount_opt(const struct mnt_opt *const mnt, const char *const target)
+{
+	return mount(mnt->source ?: mnt->type, target, mnt->type, mnt->flags,
+		     mnt->data);
+}
+
+static void prepare_layout_opt(struct __test_metadata *const _metadata,
+			       const struct mnt_opt *const mnt)
 {
 	disable_caps(_metadata);
 	umask(0077);
@@ -217,12 +262,28 @@ static void prepare_layout(struct __test_metadata *const _metadata)
 	 * for tests relying on pivot_root(2) and move_mount(2).
 	 */
 	set_cap(_metadata, CAP_SYS_ADMIN);
-	ASSERT_EQ(0, unshare(CLONE_NEWNS));
-	ASSERT_EQ(0, mount("tmp", TMP_DIR, "tmpfs", 0, "size=4m,mode=700"));
+	ASSERT_EQ(0, unshare(CLONE_NEWNS | CLONE_NEWCGROUP));
+	ASSERT_EQ(0, mount_opt(mnt, TMP_DIR))
+	{
+		TH_LOG("Failed to mount the %s filesystem: %s", mnt->type,
+		       strerror(errno));
+		/*
+		 * FIXTURE_TEARDOWN() is not called when FIXTURE_SETUP()
+		 * failed, so we need to explicitly do a minimal cleanup to
+		 * avoid cascading errors with other tests that don't depend on
+		 * the same filesystem.
+		 */
+		remove_path(TMP_DIR);
+	}
 	ASSERT_EQ(0, mount(NULL, TMP_DIR, NULL, MS_PRIVATE | MS_REC, NULL));
 	clear_cap(_metadata, CAP_SYS_ADMIN);
 }
 
+static void prepare_layout(struct __test_metadata *const _metadata)
+{
+	prepare_layout_opt(_metadata, &mnt_tmp);
+}
+
 static void cleanup_layout(struct __test_metadata *const _metadata)
 {
 	set_cap(_metadata, CAP_SYS_ADMIN);
@@ -231,6 +292,20 @@ static void cleanup_layout(struct __test_metadata *const _metadata)
 	EXPECT_EQ(0, remove_path(TMP_DIR));
 }
 
+/* clang-format off */
+FIXTURE(layout0) {};
+/* clang-format on */
+
+FIXTURE_SETUP(layout0)
+{
+	prepare_layout(_metadata);
+}
+
+FIXTURE_TEARDOWN(layout0)
+{
+	cleanup_layout(_metadata);
+}
+
 static void create_layout1(struct __test_metadata *const _metadata)
 {
 	create_file(_metadata, file1_s1d1);
@@ -248,7 +323,7 @@ static void create_layout1(struct __test_metadata *const _metadata)
 	create_file(_metadata, file1_s3d1);
 	create_directory(_metadata, dir_s3d2);
 	set_cap(_metadata, CAP_SYS_ADMIN);
-	ASSERT_EQ(0, mount("tmp", dir_s3d2, "tmpfs", 0, "size=4m,mode=700"));
+	ASSERT_EQ(0, mount_opt(&mnt_tmp, dir_s3d2));
 	clear_cap(_metadata, CAP_SYS_ADMIN);
 
 	ASSERT_EQ(0, mkdir(dir_s3d3, 0700));
@@ -262,11 +337,13 @@ static void remove_layout1(struct __test_metadata *const _metadata)
 	EXPECT_EQ(0, remove_path(file1_s1d3));
 	EXPECT_EQ(0, remove_path(file1_s1d2));
 	EXPECT_EQ(0, remove_path(file1_s1d1));
+	EXPECT_EQ(0, remove_path(dir_s1d3));
 
 	EXPECT_EQ(0, remove_path(file2_s2d3));
 	EXPECT_EQ(0, remove_path(file1_s2d3));
 	EXPECT_EQ(0, remove_path(file1_s2d2));
 	EXPECT_EQ(0, remove_path(file1_s2d1));
+	EXPECT_EQ(0, remove_path(dir_s2d2));
 
 	EXPECT_EQ(0, remove_path(file1_s3d1));
 	EXPECT_EQ(0, remove_path(dir_s3d3));
@@ -510,7 +587,7 @@ TEST_F_FORK(layout1, file_and_dir_access_rights)
 	ASSERT_EQ(0, close(ruleset_fd));
 }
 
-TEST_F_FORK(layout1, unknown_access_rights)
+TEST_F_FORK(layout0, unknown_access_rights)
 {
 	__u64 access_mask;
 
@@ -608,7 +685,7 @@ static void enforce_ruleset(struct __test_metadata *const _metadata,
 	}
 }
 
-TEST_F_FORK(layout1, proc_nsfs)
+TEST_F_FORK(layout0, proc_nsfs)
 {
 	const struct rule rules[] = {
 		{
@@ -657,11 +734,11 @@ TEST_F_FORK(layout1, proc_nsfs)
 	ASSERT_EQ(0, close(path_beneath.parent_fd));
 }
 
-TEST_F_FORK(layout1, unpriv)
+TEST_F_FORK(layout0, unpriv)
 {
 	const struct rule rules[] = {
 		{
-			.path = dir_s1d2,
+			.path = TMP_DIR,
 			.access = ACCESS_RO,
 		},
 		{},
@@ -1301,12 +1378,12 @@ TEST_F_FORK(layout1, inherit_superset)
 	ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
 }
 
-TEST_F_FORK(layout1, max_layers)
+TEST_F_FORK(layout0, max_layers)
 {
 	int i, err;
 	const struct rule rules[] = {
 		{
-			.path = dir_s1d2,
+			.path = TMP_DIR,
 			.access = ACCESS_RO,
 		},
 		{},
@@ -4030,21 +4107,24 @@ static const char (*merge_sub_files[])[] = {
  *         └── work
  */
 
-/* clang-format off */
-FIXTURE(layout2_overlay) {};
-/* clang-format on */
+FIXTURE(layout2_overlay)
+{
+	bool skip_test;
+};
 
 FIXTURE_SETUP(layout2_overlay)
 {
-	if (!supports_overlayfs())
-		SKIP(return, "overlayfs is not supported");
+	if (!supports_filesystem("overlay")) {
+		self->skip_test = true;
+		SKIP(return, "overlayfs is not supported (setup)");
+	}
 
 	prepare_layout(_metadata);
 
 	create_directory(_metadata, LOWER_BASE);
 	set_cap(_metadata, CAP_SYS_ADMIN);
 	/* Creates tmpfs mount points to get deterministic overlayfs. */
-	ASSERT_EQ(0, mount("tmp", LOWER_BASE, "tmpfs", 0, "size=4m,mode=700"));
+	ASSERT_EQ(0, mount_opt(&mnt_tmp, LOWER_BASE));
 	clear_cap(_metadata, CAP_SYS_ADMIN);
 	create_file(_metadata, lower_fl1);
 	create_file(_metadata, lower_dl1_fl2);
@@ -4054,7 +4134,7 @@ FIXTURE_SETUP(layout2_overlay)
 
 	create_directory(_metadata, UPPER_BASE);
 	set_cap(_metadata, CAP_SYS_ADMIN);
-	ASSERT_EQ(0, mount("tmp", UPPER_BASE, "tmpfs", 0, "size=4m,mode=700"));
+	ASSERT_EQ(0, mount_opt(&mnt_tmp, UPPER_BASE));
 	clear_cap(_metadata, CAP_SYS_ADMIN);
 	create_file(_metadata, upper_fu1);
 	create_file(_metadata, upper_du1_fu2);
@@ -4075,8 +4155,8 @@ FIXTURE_SETUP(layout2_overlay)
 
 FIXTURE_TEARDOWN(layout2_overlay)
 {
-	if (!supports_overlayfs())
-		SKIP(return, "overlayfs is not supported");
+	if (self->skip_test)
+		SKIP(return, "overlayfs is not supported (teardown)");
 
 	EXPECT_EQ(0, remove_path(lower_do1_fl3));
 	EXPECT_EQ(0, remove_path(lower_dl1_fl2));
@@ -4109,8 +4189,8 @@ FIXTURE_TEARDOWN(layout2_overlay)
 
 TEST_F_FORK(layout2_overlay, no_restriction)
 {
-	if (!supports_overlayfs())
-		SKIP(return, "overlayfs is not supported");
+	if (self->skip_test)
+		SKIP(return, "overlayfs is not supported (test)");
 
 	ASSERT_EQ(0, test_open(lower_fl1, O_RDONLY));
 	ASSERT_EQ(0, test_open(lower_dl1, O_RDONLY));
@@ -4275,8 +4355,8 @@ TEST_F_FORK(layout2_overlay, same_content_different_file)
 	size_t i;
 	const char *path_entry;
 
-	if (!supports_overlayfs())
-		SKIP(return, "overlayfs is not supported");
+	if (self->skip_test)
+		SKIP(return, "overlayfs is not supported (test)");
 
 	/* Sets rules on base directories (i.e. outside overlay scope). */
 	ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer1_base);
@@ -4423,4 +4503,261 @@ TEST_F_FORK(layout2_overlay, same_content_different_file)
 	}
 }
 
+FIXTURE(layout3_fs)
+{
+	bool has_created_dir;
+	bool has_created_file;
+	char *dir_path;
+	bool skip_test;
+};
+
+FIXTURE_VARIANT(layout3_fs)
+{
+	const struct mnt_opt mnt;
+	const char *const file_path;
+	unsigned int cwd_fs_magic;
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(layout3_fs, tmpfs) {
+	/* clang-format on */
+	.mnt = mnt_tmp,
+	.file_path = file1_s1d1,
+};
+
+FIXTURE_VARIANT_ADD(layout3_fs, ramfs) {
+	.mnt = {
+		.type = "ramfs",
+		.data = "mode=700",
+	},
+	.file_path = TMP_DIR "/dir/file",
+};
+
+FIXTURE_VARIANT_ADD(layout3_fs, cgroup2) {
+	.mnt = {
+		.type = "cgroup2",
+	},
+	.file_path = TMP_DIR "/test/cgroup.procs",
+};
+
+FIXTURE_VARIANT_ADD(layout3_fs, proc) {
+	.mnt = {
+		.type = "proc",
+	},
+	.file_path = TMP_DIR "/self/status",
+};
+
+FIXTURE_VARIANT_ADD(layout3_fs, sysfs) {
+	.mnt = {
+		.type = "sysfs",
+	},
+	.file_path = TMP_DIR "/kernel/notes",
+};
+
+FIXTURE_VARIANT_ADD(layout3_fs, hostfs) {
+	.mnt = {
+		.source = TMP_DIR,
+		.flags = MS_BIND,
+	},
+	.file_path = TMP_DIR "/dir/file",
+	.cwd_fs_magic = HOSTFS_SUPER_MAGIC,
+};
+
+FIXTURE_SETUP(layout3_fs)
+{
+	struct stat statbuf;
+	const char *slash;
+	size_t dir_len;
+
+	if (!supports_filesystem(variant->mnt.type) ||
+	    !cwd_matches_fs(variant->cwd_fs_magic)) {
+		self->skip_test = true;
+		SKIP(return, "this filesystem is not supported (setup)");
+	}
+
+	slash = strrchr(variant->file_path, '/');
+	ASSERT_NE(slash, NULL);
+	dir_len = (size_t)slash - (size_t)variant->file_path;
+	ASSERT_LT(0, dir_len);
+	self->dir_path = malloc(dir_len + 1);
+	self->dir_path[dir_len] = '\0';
+	strncpy(self->dir_path, variant->file_path, dir_len);
+
+	prepare_layout_opt(_metadata, &variant->mnt);
+
+	/* Creates directory when required. */
+	if (stat(self->dir_path, &statbuf)) {
+		set_cap(_metadata, CAP_DAC_OVERRIDE);
+		EXPECT_EQ(0, mkdir(self->dir_path, 0700))
+		{
+			TH_LOG("Failed to create directory \"%s\": %s",
+			       self->dir_path, strerror(errno));
+			free(self->dir_path);
+			self->dir_path = NULL;
+		}
+		self->has_created_dir = true;
+		clear_cap(_metadata, CAP_DAC_OVERRIDE);
+	}
+
+	/* Creates file when required. */
+	if (stat(variant->file_path, &statbuf)) {
+		int fd;
+
+		set_cap(_metadata, CAP_DAC_OVERRIDE);
+		fd = creat(variant->file_path, 0600);
+		EXPECT_LE(0, fd)
+		{
+			TH_LOG("Failed to create file \"%s\": %s",
+			       variant->file_path, strerror(errno));
+		}
+		EXPECT_EQ(0, close(fd));
+		self->has_created_file = true;
+		clear_cap(_metadata, CAP_DAC_OVERRIDE);
+	}
+}
+
+FIXTURE_TEARDOWN(layout3_fs)
+{
+	if (self->skip_test)
+		SKIP(return, "this filesystem is not supported (teardown)");
+
+	if (self->has_created_file) {
+		set_cap(_metadata, CAP_DAC_OVERRIDE);
+		/*
+		 * Don't check for error because the file might already
+		 * have been removed (cf. release_inode test).
+		 */
+		unlink(variant->file_path);
+		clear_cap(_metadata, CAP_DAC_OVERRIDE);
+	}
+
+	if (self->has_created_dir) {
+		set_cap(_metadata, CAP_DAC_OVERRIDE);
+		/*
+		 * Don't check for error because the directory might already
+		 * have been removed (cf. release_inode test).
+		 */
+		rmdir(self->dir_path);
+		clear_cap(_metadata, CAP_DAC_OVERRIDE);
+	}
+	free(self->dir_path);
+	self->dir_path = NULL;
+
+	cleanup_layout(_metadata);
+}
+
+static void layer3_fs_tag_inode(struct __test_metadata *const _metadata,
+				FIXTURE_DATA(layout3_fs) * self,
+				const FIXTURE_VARIANT(layout3_fs) * variant,
+				const char *const rule_path)
+{
+	const struct rule layer1_allow_read_file[] = {
+		{
+			.path = rule_path,
+			.access = LANDLOCK_ACCESS_FS_READ_FILE,
+		},
+		{},
+	};
+	const struct landlock_ruleset_attr layer2_deny_everything_attr = {
+		.handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE,
+	};
+	const char *const dev_null_path = "/dev/null";
+	int ruleset_fd;
+
+	if (self->skip_test)
+		SKIP(return, "this filesystem is not supported (test)");
+
+	/* Checks without Landlock. */
+	EXPECT_EQ(0, test_open(dev_null_path, O_RDONLY | O_CLOEXEC));
+	EXPECT_EQ(0, test_open(variant->file_path, O_RDONLY | O_CLOEXEC));
+
+	ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE,
+				    layer1_allow_read_file);
+	EXPECT_LE(0, ruleset_fd);
+	enforce_ruleset(_metadata, ruleset_fd);
+	EXPECT_EQ(0, close(ruleset_fd));
+
+	EXPECT_EQ(EACCES, test_open(dev_null_path, O_RDONLY | O_CLOEXEC));
+	EXPECT_EQ(0, test_open(variant->file_path, O_RDONLY | O_CLOEXEC));
+
+	/* Forbids directory reading. */
+	ruleset_fd =
+		landlock_create_ruleset(&layer2_deny_everything_attr,
+					sizeof(layer2_deny_everything_attr), 0);
+	EXPECT_LE(0, ruleset_fd);
+	enforce_ruleset(_metadata, ruleset_fd);
+	EXPECT_EQ(0, close(ruleset_fd));
+
+	/* Checks with Landlock and forbidden access. */
+	EXPECT_EQ(EACCES, test_open(dev_null_path, O_RDONLY | O_CLOEXEC));
+	EXPECT_EQ(EACCES, test_open(variant->file_path, O_RDONLY | O_CLOEXEC));
+}
+
+/* Matrix of tests to check file hierarchy evaluation. */
+
+TEST_F_FORK(layout3_fs, tag_inode_dir_parent)
+{
+	/* The current directory must not be the root for this test. */
+	layer3_fs_tag_inode(_metadata, self, variant, ".");
+}
+
+TEST_F_FORK(layout3_fs, tag_inode_dir_mnt)
+{
+	layer3_fs_tag_inode(_metadata, self, variant, TMP_DIR);
+}
+
+TEST_F_FORK(layout3_fs, tag_inode_dir_child)
+{
+	layer3_fs_tag_inode(_metadata, self, variant, self->dir_path);
+}
+
+TEST_F_FORK(layout3_fs, tag_inode_file)
+{
+	layer3_fs_tag_inode(_metadata, self, variant, variant->file_path);
+}
+
+/* Light version of layout1.release_inodes */
+TEST_F_FORK(layout3_fs, release_inodes)
+{
+	const struct rule layer1[] = {
+		{
+			.path = TMP_DIR,
+			.access = LANDLOCK_ACCESS_FS_READ_DIR,
+		},
+		{},
+	};
+	int ruleset_fd;
+
+	if (self->skip_test)
+		SKIP(return, "this filesystem is not supported (test)");
+
+	/* Clean up for the teardown to not fail. */
+	if (self->has_created_file)
+		EXPECT_EQ(0, remove_path(variant->file_path));
+
+	if (self->has_created_dir)
+		/* Don't check for error because of cgroup specificities. */
+		remove_path(self->dir_path);
+
+	ruleset_fd =
+		create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_DIR, layer1);
+	ASSERT_LE(0, ruleset_fd);
+
+	/* Unmount the filesystem while it is being used by a ruleset. */
+	set_cap(_metadata, CAP_SYS_ADMIN);
+	ASSERT_EQ(0, umount(TMP_DIR));
+	clear_cap(_metadata, CAP_SYS_ADMIN);
+
+	/* Replaces with a new mount point to simplify FIXTURE_TEARDOWN. */
+	set_cap(_metadata, CAP_SYS_ADMIN);
+	ASSERT_EQ(0, mount_opt(&mnt_tmp, TMP_DIR));
+	clear_cap(_metadata, CAP_SYS_ADMIN);
+
+	enforce_ruleset(_metadata, ruleset_fd);
+	ASSERT_EQ(0, close(ruleset_fd));
+
+	/* Checks that access to the new mount point is denied. */
+	ASSERT_EQ(EACCES, test_open(TMP_DIR, O_RDONLY));
+}
+
 TEST_HARNESS_MAIN