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

…el/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
chewitt · Jun 1, 2020 · f359287 · f359287
2 parents 8b39a57 + c8ffd8b
commit f359287
Show file tree

Hide file tree

Showing 39 changed files with 234 additions and 96 deletions.
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/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
diff --git a/arch/arm/tools/syscall.tbl b/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
diff --git a/arch/arm64/include/asm/unistd.h b/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

diff --git a/arch/arm64/include/asm/unistd32.h b/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

diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/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
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/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
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/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
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/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
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/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
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/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
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/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
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/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
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/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
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/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
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/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
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/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
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/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

diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/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
diff --git a/fs/aio.c b/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);

diff --git a/fs/char_dev.c b/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)

diff --git a/fs/fs_context.c b/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) {

diff --git a/fs/internal.h b/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);

diff --git a/fs/mount.h b/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);
diff --git a/fs/namei.c b/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);