Merge branch 'from-miklos' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs updates from Al Viro:
 "Assorted patches from Miklos.

  An interesting part here is /proc/mounts stuff..."

The "/proc/mounts stuff" is using a cursor for keeeping the location
data while traversing the mount listing.

Also probably worth noting is the addition of faccessat2(), which takes
an additional set of flags to specify how the lookup is done
(AT_EACCESS, AT_SYMLINK_NOFOLLOW, AT_EMPTY_PATH).

* 'from-miklos' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  vfs: add faccessat2 syscall
  vfs: don't parse "silent" option
  vfs: don't parse "posixacl" option
  vfs: don't parse forbidden flags
  statx: add mount_root
  statx: add mount ID
  statx: don't clear STATX_ATIME on SB_RDONLY
  uapi: deprecate STATX_ALL
  utimensat: AT_EMPTY_PATH support
  vfs: split out access_override_creds()
  proc/mounts: add cursor
  aio: fix async fsync creds
  vfs: allow unprivileged whiteout creation

arch/alpha/kernel/syscalls/syscall.tbl

@@ -477,3 +477,4 @@
 # 545 reserved for clone3
 547	common	openat2				sys_openat2
 548	common	pidfd_getfd			sys_pidfd_getfd
+549	common	faccessat2			sys_faccessat2

arch/arm/tools/syscall.tbl

@@ -451,3 +451,4 @@
 435	common	clone3				sys_clone3
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/arm64/include/asm/unistd.h

@@ -38,7 +38,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		439
+#define __NR_compat_syscalls		440
 #endif
 
 #define __ARCH_WANT_SYS_CLONE

arch/arm64/include/asm/unistd32.h

@@ -883,6 +883,8 @@ __SYSCALL(__NR_clone3, sys_clone3)
 __SYSCALL(__NR_openat2, sys_openat2)
 #define __NR_pidfd_getfd 438
 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
+#define __NR_faccessat2 439
+__SYSCALL(__NR_faccessat2, sys_faccessat2)
 
 /*
  * Please add new compat syscalls above this comment and update

arch/ia64/kernel/syscalls/syscall.tbl

@@ -358,3 +358,4 @@
 # 435 reserved for clone3
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/m68k/kernel/syscalls/syscall.tbl

@@ -437,3 +437,4 @@
 435	common	clone3				__sys_clone3
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/microblaze/kernel/syscalls/syscall.tbl

@@ -443,3 +443,4 @@
 435	common	clone3				sys_clone3
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/mips/kernel/syscalls/syscall_n32.tbl

@@ -376,3 +376,4 @@
 435	n32	clone3				__sys_clone3
 437	n32	openat2				sys_openat2
 438	n32	pidfd_getfd			sys_pidfd_getfd
+439	n32	faccessat2			sys_faccessat2

arch/mips/kernel/syscalls/syscall_n64.tbl

@@ -352,3 +352,4 @@
 435	n64	clone3				__sys_clone3
 437	n64	openat2				sys_openat2
 438	n64	pidfd_getfd			sys_pidfd_getfd
+439	n64	faccessat2			sys_faccessat2

arch/mips/kernel/syscalls/syscall_o32.tbl

@@ -425,3 +425,4 @@
 435	o32	clone3				__sys_clone3
 437	o32	openat2				sys_openat2
 438	o32	pidfd_getfd			sys_pidfd_getfd
+439	o32	faccessat2			sys_faccessat2

arch/parisc/kernel/syscalls/syscall.tbl

@@ -435,3 +435,4 @@
 435	common	clone3				sys_clone3_wrapper
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/powerpc/kernel/syscalls/syscall.tbl

@@ -527,3 +527,4 @@
 435	spu	clone3				sys_ni_syscall
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/s390/kernel/syscalls/syscall.tbl

@@ -440,3 +440,4 @@
 435  common	clone3			sys_clone3			sys_clone3
 437  common	openat2			sys_openat2			sys_openat2
 438  common	pidfd_getfd		sys_pidfd_getfd			sys_pidfd_getfd
+439  common	faccessat2		sys_faccessat2			sys_faccessat2

arch/sh/kernel/syscalls/syscall.tbl

@@ -440,3 +440,4 @@
 # 435 reserved for clone3
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/sparc/kernel/syscalls/syscall.tbl

@@ -483,3 +483,4 @@
 # 435 reserved for clone3
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/x86/entry/syscalls/syscall_32.tbl

@@ -442,3 +442,4 @@
 435	i386	clone3			sys_clone3
 437	i386	openat2			sys_openat2
 438	i386	pidfd_getfd		sys_pidfd_getfd
+439	i386	faccessat2		sys_faccessat2

arch/x86/entry/syscalls/syscall_64.tbl

@@ -359,6 +359,7 @@
 435	common	clone3			sys_clone3
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd		sys_pidfd_getfd
+439	common	faccessat2		sys_faccessat2
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

arch/xtensa/kernel/syscalls/syscall.tbl

@@ -408,3 +408,4 @@
 435	common	clone3				sys_clone3
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

fs/aio.c

@@ -176,6 +176,7 @@ struct fsync_iocb {
 	struct file		*file;
 	struct work_struct	work;
 	bool			datasync;
+	struct cred		*creds;
 };
 
 struct poll_iocb {
@@ -1589,8 +1590,11 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb,
 static void aio_fsync_work(struct work_struct *work)
 {
 	struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work);
+	const struct cred *old_cred = override_creds(iocb->fsync.creds);
 
 	iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync);
+	revert_creds(old_cred);
+	put_cred(iocb->fsync.creds);
 	iocb_put(iocb);
 }
 
@@ -1604,6 +1608,10 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb,
 	if (unlikely(!req->file->f_op->fsync))
 		return -EINVAL;
 
+	req->creds = prepare_creds();
+	if (!req->creds)
+		return -ENOMEM;
+
 	req->datasync = datasync;
 	INIT_WORK(&req->work, aio_fsync_work);
 	schedule_work(&req->work);

fs/char_dev.c

@@ -483,6 +483,9 @@ int cdev_add(struct cdev *p, dev_t dev, unsigned count)
 	p->dev = dev;
 	p->count = count;
 
+	if (WARN_ON(dev == WHITEOUT_DEV))
+		return -EBUSY;
+
 	error = kobj_map(cdev_map, dev, count, NULL,
 			 exact_match, exact_lock, p);
 	if (error)

fs/fs_context.c

@@ -42,7 +42,6 @@ static const struct constant_table common_set_sb_flag[] = {
 	{ "dirsync",	SB_DIRSYNC },
 	{ "lazytime",	SB_LAZYTIME },
 	{ "mand",	SB_MANDLOCK },
-	{ "posixacl",	SB_POSIXACL },
 	{ "ro",		SB_RDONLY },
 	{ "sync",	SB_SYNCHRONOUS },
 	{ },
@@ -53,44 +52,15 @@ static const struct constant_table common_clear_sb_flag[] = {
 	{ "nolazytime",	SB_LAZYTIME },
 	{ "nomand",	SB_MANDLOCK },
 	{ "rw",		SB_RDONLY },
-	{ "silent",	SB_SILENT },
 	{ },
 };
 
-static const char *const forbidden_sb_flag[] = {
-	"bind",
-	"dev",
-	"exec",
-	"move",
-	"noatime",
-	"nodev",
-	"nodiratime",
-	"noexec",
-	"norelatime",
-	"nostrictatime",
-	"nosuid",
-	"private",
-	"rec",
-	"relatime",
-	"remount",
-	"shared",
-	"slave",
-	"strictatime",
-	"suid",
-	"unbindable",
-};
-
 /*
  * Check for a common mount option that manipulates s_flags.
  */
 static int vfs_parse_sb_flag(struct fs_context *fc, const char *key)
 {
 	unsigned int token;
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(forbidden_sb_flag); i++)
-		if (strcmp(key, forbidden_sb_flag[i]) == 0)
-			return -EINVAL;
 
 	token = lookup_constant(common_set_sb_flag, key, 0);
 	if (token) {

fs/internal.h

@@ -126,7 +126,6 @@ extern struct open_how build_open_how(int flags, umode_t mode);
 extern int build_open_flags(const struct open_how *how, struct open_flags *op);
 
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
-long do_faccessat(int dfd, const char __user *filename, int mode);
 int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);

fs/mount.h

@@ -9,7 +9,13 @@ struct mnt_namespace {
 	atomic_t		count;
 	struct ns_common	ns;
 	struct mount *	root;
+	/*
+	 * Traversal and modification of .list is protected by either
+	 * - taking namespace_sem for write, OR
+	 * - taking namespace_sem for read AND taking .ns_lock.
+	 */
 	struct list_head	list;
+	spinlock_t		ns_lock;
 	struct user_namespace	*user_ns;
 	struct ucounts		*ucounts;
 	u64			seq;	/* Sequence number to prevent loops */
@@ -133,9 +139,7 @@ struct proc_mounts {
 	struct mnt_namespace *ns;
 	struct path root;
 	int (*show)(struct seq_file *, struct vfsmount *);
-	void *cached_mount;
-	u64 cached_event;
-	loff_t cached_index;
+	struct mount cursor;
 };
 
 extern const struct seq_operations mounts_op;
@@ -153,3 +157,5 @@ static inline bool is_anon_ns(struct mnt_namespace *ns)
 {
 	return ns->seq == 0;
 }
+
+extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor);

fs/namei.c

@@ -3505,12 +3505,14 @@ EXPORT_SYMBOL(user_path_create);
 
 int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
 {
+	bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV;
 	int error = may_create(dir, dentry);
 
 	if (error)
 		return error;
 
-	if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
+	if ((S_ISCHR(mode) || S_ISBLK(mode)) && !is_whiteout &&
+	    !capable(CAP_MKNOD))
 		return -EPERM;
 
 	if (!dir->i_op->mknod)
@@ -4345,9 +4347,6 @@ static int do_renameat2(int olddfd, const char __user *oldname, int newdfd,
 	    (flags & RENAME_EXCHANGE))
 		return -EINVAL;
 
-	if ((flags & RENAME_WHITEOUT) && !capable(CAP_MKNOD))
-		return -EPERM;
-
 	if (flags & RENAME_EXCHANGE)
 		target_flags = 0;
 
@@ -4483,20 +4482,6 @@ SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newna
 	return do_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
-int vfs_whiteout(struct inode *dir, struct dentry *dentry)
-{
-	int error = may_create(dir, dentry);
-	if (error)
-		return error;
-
-	if (!dir->i_op->mknod)
-		return -EPERM;
-
-	return dir->i_op->mknod(dir, dentry,
-				S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
-}
-EXPORT_SYMBOL(vfs_whiteout);
-
 int readlink_copy(char __user *buffer, int buflen, const char *link)
 {
 	int len = PTR_ERR(link);

fs/namespace.c

@@ -648,6 +648,21 @@ struct vfsmount *lookup_mnt(const struct path *path)
 	return m;
 }
 
+static inline void lock_ns_list(struct mnt_namespace *ns)
+{
+	spin_lock(&ns->ns_lock);
+}
+
+static inline void unlock_ns_list(struct mnt_namespace *ns)
+{
+	spin_unlock(&ns->ns_lock);
+}
+
+static inline bool mnt_is_cursor(struct mount *mnt)
+{
+	return mnt->mnt.mnt_flags & MNT_CURSOR;
+}
+
 /*
  * __is_local_mountpoint - Test to see if dentry is a mountpoint in the
  *                         current mount namespace.
@@ -673,11 +688,15 @@ bool __is_local_mountpoint(struct dentry *dentry)
 		goto out;
 
 	down_read(&namespace_sem);
+	lock_ns_list(ns);
 	list_for_each_entry(mnt, &ns->list, mnt_list) {
+		if (mnt_is_cursor(mnt))
+			continue;
 		is_covered = (mnt->mnt_mountpoint == dentry);
 		if (is_covered)
 			break;
 	}
+	unlock_ns_list(ns);
 	up_read(&namespace_sem);
 out:
 	return is_covered;
@@ -1245,46 +1264,71 @@ struct vfsmount *mnt_clone_internal(const struct path *path)
 }
 
 #ifdef CONFIG_PROC_FS
+static struct mount *mnt_list_next(struct mnt_namespace *ns,
+				   struct list_head *p)
+{
+	struct mount *mnt, *ret = NULL;
+
+	lock_ns_list(ns);
+	list_for_each_continue(p, &ns->list) {
+		mnt = list_entry(p, typeof(*mnt), mnt_list);
+		if (!mnt_is_cursor(mnt)) {
+			ret = mnt;
+			break;
+		}
+	}
+	unlock_ns_list(ns);
+
+	return ret;
+}
+
 /* iterator; we want it to have access to namespace_sem, thus here... */
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
 	struct proc_mounts *p = m->private;
+	struct list_head *prev;
 
 	down_read(&namespace_sem);
-	if (p->cached_event == p->ns->event) {
-		void *v = p->cached_mount;
-		if (*pos == p->cached_index)
-			return v;
-		if (*pos == p->cached_index + 1) {
-			v = seq_list_next(v, &p->ns->list, &p->cached_index);
-			return p->cached_mount = v;
-		}
+	if (!*pos) {
+		prev = &p->ns->list;
+	} else {
+		prev = &p->cursor.mnt_list;
+
+		/* Read after we'd reached the end? */
+		if (list_empty(prev))
+			return NULL;
 	}
 
-	p->cached_event = p->ns->event;
-	p->cached_mount = seq_list_start(&p->ns->list, *pos);
-	p->cached_index = *pos;
-	return p->cached_mount;
+	return mnt_list_next(p->ns, prev);
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct proc_mounts *p = m->private;
+	struct mount *mnt = v;
 
-	p->cached_mount = seq_list_next(v, &p->ns->list, pos);
-	p->cached_index = *pos;
-	return p->cached_mount;
+	++*pos;
+	return mnt_list_next(p->ns, &mnt->mnt_list);
 }
 
 static void m_stop(struct seq_file *m, void *v)
 {
+	struct proc_mounts *p = m->private;
+	struct mount *mnt = v;
+
+	lock_ns_list(p->ns);
+	if (mnt)
+		list_move_tail(&p->cursor.mnt_list, &mnt->mnt_list);
+	else
+		list_del_init(&p->cursor.mnt_list);
+	unlock_ns_list(p->ns);
 	up_read(&namespace_sem);
 }
 
 static int m_show(struct seq_file *m, void *v)
 {
 	struct proc_mounts *p = m->private;
-	struct mount *r = list_entry(v, struct mount, mnt_list);
+	struct mount *r = v;
 	return p->show(m, &r->mnt);
 }
 
@@ -1294,6 +1338,15 @@ const struct seq_operations mounts_op = {
 	.stop	= m_stop,
 	.show	= m_show,
 };
+
+void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor)
+{
+	down_read(&namespace_sem);
+	lock_ns_list(ns);
+	list_del(&cursor->mnt_list);
+	unlock_ns_list(ns);
+	up_read(&namespace_sem);
+}
 #endif  /* CONFIG_PROC_FS */
 
 /**
@@ -3202,6 +3255,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a
 	atomic_set(&new_ns->count, 1);
 	INIT_LIST_HEAD(&new_ns->list);
 	init_waitqueue_head(&new_ns->poll);
+	spin_lock_init(&new_ns->ns_lock);
 	new_ns->user_ns = get_user_ns(user_ns);
 	new_ns->ucounts = ucounts;
 	return new_ns;
@@ -3842,10 +3896,14 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
 	bool visible = false;
 
 	down_read(&namespace_sem);
+	lock_ns_list(ns);
 	list_for_each_entry(mnt, &ns->list, mnt_list) {
 		struct mount *child;
 		int mnt_flags;
 
+		if (mnt_is_cursor(mnt))
+			continue;
+
 		if (mnt->mnt.mnt_sb->s_type != sb->s_type)
 			continue;
 
@@ -3893,6 +3951,7 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
 	next:	;
 	}
 found:
+	unlock_ns_list(ns);
 	up_read(&namespace_sem);
 	return visible;
 }

fs/open.c

@@ -345,21 +345,14 @@ SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len)
  * We do this by temporarily clearing all FS-related capabilities and
  * switching the fsuid/fsgid around to the real ones.
  */
-long do_faccessat(int dfd, const char __user *filename, int mode)
+static const struct cred *access_override_creds(void)
 {
 	const struct cred *old_cred;
 	struct cred *override_cred;
-	struct path path;
-	struct inode *inode;
-	int res;
-	unsigned int lookup_flags = LOOKUP_FOLLOW;
-
-	if (mode & ~S_IRWXO)	/* where's F_OK, X_OK, W_OK, R_OK? */
-		return -EINVAL;
 
 	override_cred = prepare_creds();
 	if (!override_cred)
-		return -ENOMEM;
+		return NULL;
 
 	override_cred->fsuid = override_cred->uid;
 	override_cred->fsgid = override_cred->gid;
@@ -394,6 +387,38 @@ long do_faccessat(int dfd, const char __user *filename, int mode)
 	override_cred->non_rcu = 1;
 
 	old_cred = override_creds(override_cred);
+
+	/* override_cred() gets its own ref */
+	put_cred(override_cred);
+
+	return old_cred;
+}
+
+long do_faccessat(int dfd, const char __user *filename, int mode, int flags)
+{
+	struct path path;
+	struct inode *inode;
+	int res;
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
+	const struct cred *old_cred = NULL;
+
+	if (mode & ~S_IRWXO)	/* where's F_OK, X_OK, W_OK, R_OK? */
+		return -EINVAL;
+
+	if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH))
+		return -EINVAL;
+
+	if (flags & AT_SYMLINK_NOFOLLOW)
+		lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+
+	if (!(flags & AT_EACCESS)) {
+		old_cred = access_override_creds();
+		if (!old_cred)
+			return -ENOMEM;
+	}
+
 retry:
 	res = user_path_at(dfd, filename, lookup_flags, &path);
 	if (res)
@@ -435,19 +460,26 @@ long do_faccessat(int dfd, const char __user *filename, int mode)
 		goto retry;
 	}
 out:
+	if (old_cred)
 		revert_creds(old_cred);
-	put_cred(override_cred);
+
 	return res;
 }
 
 SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
 {
-	return do_faccessat(dfd, filename, mode);
+	return do_faccessat(dfd, filename, mode, 0);
+}
+
+SYSCALL_DEFINE4(faccessat2, int, dfd, const char __user *, filename, int, mode,
+		int, flags)
+{
+	return do_faccessat(dfd, filename, mode, flags);
 }
 
 SYSCALL_DEFINE2(access, const char __user *, filename, int, mode)
 {
-	return do_faccessat(AT_FDCWD, filename, mode);
+	return do_faccessat(AT_FDCWD, filename, mode, 0);
 }
 
 int ksys_chdir(const char __user *filename)

fs/proc_namespace.c

@@ -279,7 +279,8 @@ static int mounts_open_common(struct inode *inode, struct file *file,
 	p->ns = ns;
 	p->root = root;
 	p->show = show;
-	p->cached_event = ~0ULL;
+	INIT_LIST_HEAD(&p->cursor.mnt_list);
+	p->cursor.mnt.mnt_flags = MNT_CURSOR;
 
 	return 0;
 
@@ -296,6 +297,7 @@ static int mounts_release(struct inode *inode, struct file *file)
 	struct seq_file *m = file->private_data;
 	struct proc_mounts *p = m->private;
 	path_put(&p->root);
+	mnt_cursor_del(p->ns, &p->cursor);
 	put_mnt_ns(p->ns);
 	return seq_release_private(inode, file);
 }

fs/stat.c

@@ -22,6 +22,7 @@
 #include <asm/unistd.h>
 
 #include "internal.h"
+#include "mount.h"
 
 /**
  * generic_fillattr - Fill in the basic attributes from the inode struct
@@ -70,11 +71,11 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
 
 	memset(stat, 0, sizeof(*stat));
 	stat->result_mask |= STATX_BASIC_STATS;
-	request_mask &= STATX_ALL;
 	query_flags &= KSTAT_QUERY_FLAGS;
 
 	/* allow the fs to override these if it really wants to */
-	if (IS_NOATIME(inode))
+	/* SB_NOATIME means filesystem supplies dummy atime value */
+	if (inode->i_sb->s_flags & SB_NOATIME)
 		stat->result_mask &= ~STATX_ATIME;
 	if (IS_AUTOMOUNT(inode))
 		stat->attributes |= STATX_ATTR_AUTOMOUNT;
@@ -199,6 +200,11 @@ int vfs_statx(int dfd, const char __user *filename, int flags,
 		goto out;
 
 	error = vfs_getattr(&path, stat, request_mask, flags);
+	stat->mnt_id = real_mount(path.mnt)->mnt_id;
+	stat->result_mask |= STATX_MNT_ID;
+	if (path.mnt->mnt_root == path.dentry)
+		stat->attributes |= STATX_ATTR_MOUNT_ROOT;
+	stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT;
 	path_put(&path);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
@@ -563,6 +569,7 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer)
 	tmp.stx_rdev_minor = MINOR(stat->rdev);
 	tmp.stx_dev_major = MAJOR(stat->dev);
 	tmp.stx_dev_minor = MINOR(stat->dev);
+	tmp.stx_mnt_id = stat->mnt_id;
 
 	return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
 }

fs/utimes.c

@@ -95,13 +95,13 @@ long do_utimes(int dfd, const char __user *filename, struct timespec64 *times,
 		goto out;
 	}
 
-	if (flags & ~AT_SYMLINK_NOFOLLOW)
+	if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH))
 		goto out;
 
 	if (filename == NULL && dfd != AT_FDCWD) {
 		struct fd f;
 
-		if (flags & AT_SYMLINK_NOFOLLOW)
+		if (flags)
 			goto out;
 
 		f = fdget(dfd);
@@ -117,6 +117,8 @@ long do_utimes(int dfd, const char __user *filename, struct timespec64 *times,
 
 		if (!(flags & AT_SYMLINK_NOFOLLOW))
 			lookup_flags |= LOOKUP_FOLLOW;
+		if (flags & AT_EMPTY_PATH)
+			lookup_flags |= LOOKUP_EMPTY;
 retry:
 		error = user_path_at(dfd, filename, lookup_flags, &path);
 		if (error)

include/linux/device_cgroup.h

@@ -44,6 +44,9 @@ static inline int devcgroup_inode_mknod(int mode, dev_t dev)
 	if (!S_ISBLK(mode) && !S_ISCHR(mode))
 		return 0;
 
+	if (S_ISCHR(mode) && dev == WHITEOUT_DEV)
+		return 0;
+
 	if (S_ISBLK(mode))
 		type = DEVCG_DEV_BLOCK;
 	else

include/linux/fs.h

@@ -1721,7 +1721,11 @@ extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct ino
 extern int vfs_rmdir(struct inode *, struct dentry *);
 extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
 extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
-extern int vfs_whiteout(struct inode *, struct dentry *);
+
+static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry)
+{
+	return vfs_mknod(dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
+}
 
 extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode,
 				  int open_flag);

include/linux/mount.h

@@ -50,7 +50,8 @@ struct fs_context;
 #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME )
 
 #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
-			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED)
+			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | \
+			    MNT_CURSOR)
 
 #define MNT_INTERNAL	0x4000
 
@@ -64,6 +65,7 @@ struct fs_context;
 #define MNT_SYNC_UMOUNT		0x2000000
 #define MNT_MARKED		0x4000000
 #define MNT_UMOUNT		0x8000000
+#define MNT_CURSOR		0x10000000
 
 struct vfsmount {
 	struct dentry *mnt_root;	/* root of the mounted tree */

include/linux/stat.h

@@ -47,6 +47,7 @@ struct kstat {
 	struct timespec64 ctime;
 	struct timespec64 btime;			/* File creation time */
 	u64		blocks;
+	u64		mnt_id;
 };
 
 #endif

include/linux/syscalls.h

@@ -428,6 +428,8 @@ asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length);
 #endif
 asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len);
 asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode);
+asmlinkage long sys_faccessat2(int dfd, const char __user *filename, int mode,
+			       int flags);
 asmlinkage long sys_chdir(const char __user *filename);
 asmlinkage long sys_fchdir(unsigned int fd);
 asmlinkage long sys_chroot(const char __user *filename);
@@ -1333,11 +1335,11 @@ static inline int ksys_chmod(const char __user *filename, umode_t mode)
 	return do_fchmodat(AT_FDCWD, filename, mode);
 }
 
-extern long do_faccessat(int dfd, const char __user *filename, int mode);
+long do_faccessat(int dfd, const char __user *filename, int mode, int flags);
 
 static inline long ksys_access(const char __user *filename, int mode)
 {
-	return do_faccessat(AT_FDCWD, filename, mode);
+	return do_faccessat(AT_FDCWD, filename, mode, 0);
 }
 
 extern int do_fchownat(int dfd, const char __user *filename, uid_t user,

include/uapi/asm-generic/unistd.h

@@ -855,9 +855,11 @@ __SYSCALL(__NR_clone3, sys_clone3)
 __SYSCALL(__NR_openat2, sys_openat2)
 #define __NR_pidfd_getfd 438
 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
+#define __NR_faccessat2 439
+__SYSCALL(__NR_faccessat2, sys_faccessat2)
 
 #undef __NR_syscalls
-#define __NR_syscalls 439
+#define __NR_syscalls 440
 
 /*
  * 32 bit systems traditionally used different

include/uapi/linux/fcntl.h

@@ -84,10 +84,20 @@
 #define DN_ATTRIB	0x00000020	/* File changed attibutes */
 #define DN_MULTISHOT	0x80000000	/* Don't remove notifier */
 
+/*
+ * The constants AT_REMOVEDIR and AT_EACCESS have the same value.  AT_EACCESS is
+ * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to
+ * unlinkat.  The two functions do completely different things and therefore,
+ * the flags can be allowed to overlap.  For example, passing AT_REMOVEDIR to
+ * faccessat would be undefined behavior and thus treating it equivalent to
+ * AT_EACCESS is valid undefined behavior.
+ */
 #define AT_FDCWD		-100    /* Special value used to indicate
                                            openat should use the current
                                            working directory. */
 #define AT_SYMLINK_NOFOLLOW	0x100   /* Do not follow symbolic links.  */
+#define AT_EACCESS		0x200	/* Test access permitted for
+                                           effective IDs, not real IDs.  */
 #define AT_REMOVEDIR		0x200   /* Remove directory instead of
                                            unlinking file.  */
 #define AT_SYMLINK_FOLLOW	0x400   /* Follow symbolic links.  */

include/uapi/linux/stat.h

@@ -123,7 +123,10 @@ struct statx {
 	__u32	stx_dev_major;	/* ID of device containing file [uncond] */
 	__u32	stx_dev_minor;
 	/* 0x90 */
-	__u64	__spare2[14];	/* Spare space for future expansion */
+	__u64	stx_mnt_id;
+	__u64	__spare2;
+	/* 0xa0 */
+	__u64	__spare3[12];	/* Spare space for future expansion */
 	/* 0x100 */
 };
 
@@ -148,9 +151,19 @@ struct statx {
 #define STATX_BLOCKS		0x00000400U	/* Want/got stx_blocks */
 #define STATX_BASIC_STATS	0x000007ffU	/* The stuff in the normal stat struct */
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
-#define STATX_ALL		0x00000fffU	/* All currently supported flags */
+#define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
+
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
+#ifndef __KERNEL__
+/*
+ * This is deprecated, and shall remain the same value in the future.  To avoid
+ * confusion please use the equivalent (STATX_BASIC_STATS | STATX_BTIME)
+ * instead.
+ */
+#define STATX_ALL		0x00000fffU
+#endif
+
 /*
  * Attributes to be found in stx_attributes and masked in stx_attributes_mask.
  *
@@ -168,6 +181,7 @@ struct statx {
 #define STATX_ATTR_NODUMP		0x00000040 /* [I] File is not to be dumped */
 #define STATX_ATTR_ENCRYPTED		0x00000800 /* [I] File requires key to decrypt in fs */
 #define STATX_ATTR_AUTOMOUNT		0x00001000 /* Dir: Automount trigger */
+#define STATX_ATTR_MOUNT_ROOT		0x00002000 /* Root of a mount */
 #define STATX_ATTR_VERITY		0x00100000 /* [I] Verity protected file */
 
 

samples/vfs/test-statx.c

@@ -216,7 +216,7 @@ int main(int argc, char **argv)
 	struct statx stx;
 	int ret, raw = 0, atflag = AT_SYMLINK_NOFOLLOW;
 
-	unsigned int mask = STATX_ALL;
+	unsigned int mask = STATX_BASIC_STATS | STATX_BTIME;
 
 	for (argv++; *argv; argv++) {
 		if (strcmp(*argv, "-F") == 0) {

tools/include/uapi/linux/stat.h

@@ -148,9 +148,18 @@ struct statx {
 #define STATX_BLOCKS		0x00000400U	/* Want/got stx_blocks */
 #define STATX_BASIC_STATS	0x000007ffU	/* The stuff in the normal stat struct */
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
-#define STATX_ALL		0x00000fffU	/* All currently supported flags */
+
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
+#ifndef __KERNEL__
+/*
+ * This is deprecated, and shall remain the same value in the future.  To avoid
+ * confusion please use the equivalent (STATX_BASIC_STATS | STATX_BTIME)
+ * instead.
+ */
+#define STATX_ALL		0x00000fffU
+#endif
+
 /*
  * Attributes to be found in stx_attributes and masked in stx_attributes_mask.
  *