Merge branch 'work.mount-syscalls' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull mount ABI updates from Al Viro:
 "The syscalls themselves, finally.

  That's not all there is to that stuff, but switching individual
  filesystems to new methods is fortunately independent from everything
  else, so e.g. NFS series can go through NFS tree, etc.

  As those conversions get done, we'll be finally able to get rid of a
  bunch of duplication in fs/super.c introduced in the beginning of the
  entire thing. I expect that to be finished in the next window..."

* 'work.mount-syscalls' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  vfs: Add a sample program for the new mount API
  vfs: syscall: Add fspick() to select a superblock for reconfiguration
  vfs: syscall: Add fsmount() to create a mount for a superblock
  vfs: syscall: Add fsconfig() for configuring and managing a context
  vfs: Implement logging through fs_context
  vfs: syscall: Add fsopen() to prepare for superblock creation
  Make anon_inodes unconditional
  teach move_mount(2) to work with OPEN_TREE_CLONE
  vfs: syscall: Add move_mount(2) to move mounts around
  vfs: syscall: Add open_tree(2) to reference or clone a mount

3 files changed, 410 insertions, 0 deletions

diff --git a/samples/vfs/Makefile b/samples/vfs/Makefile
new file mode 100644
index 000000000000..4ac9690fb3c4
--- /dev/null
+++ b/samples/vfs/Makefile
@@ -0,0 +1,10 @@
+# List of programs to build
+hostprogs-$(CONFIG_SAMPLE_VFS) := \
+	test-fsmount \
+	test-statx
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+
+HOSTCFLAGS_test-fsmount.o += -I$(objtree)/usr/include
+HOSTCFLAGS_test-statx.o += -I$(objtree)/usr/include
diff --git a/samples/vfs/test-fsmount.c b/samples/vfs/test-fsmount.c
new file mode 100644
index 000000000000..266d72b3dce4
--- /dev/null
+++ b/samples/vfs/test-fsmount.c
@@ -0,0 +1,133 @@
+/* fd-based mount test.
+ *
+ * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <linux/mount.h>
+#include <linux/unistd.h>
+
+#define E(x) do { if ((x) == -1) { perror(#x); exit(1); } } while(0)
+
+static void check_messages(int fd)
+{
+	char buf[4096];
+	int err, n;
+
+	err = errno;
+
+	for (;;) {
+		n = read(fd, buf, sizeof(buf));
+		if (n < 0)
+			break;
+		n -= 2;
+
+		switch (buf[0]) {
+		case 'e':
+			fprintf(stderr, "Error: %*.*s\n", n, n, buf + 2);
+			break;
+		case 'w':
+			fprintf(stderr, "Warning: %*.*s\n", n, n, buf + 2);
+			break;
+		case 'i':
+			fprintf(stderr, "Info: %*.*s\n", n, n, buf + 2);
+			break;
+		}
+	}
+
+	errno = err;
+}
+
+static __attribute__((noreturn))
+void mount_error(int fd, const char *s)
+{
+	check_messages(fd);
+	fprintf(stderr, "%s: %m\n", s);
+	exit(1);
+}
+
+/* Hope -1 isn't a syscall */
+#ifndef __NR_fsopen
+#define __NR_fsopen -1
+#endif
+#ifndef __NR_fsmount
+#define __NR_fsmount -1
+#endif
+#ifndef __NR_fsconfig
+#define __NR_fsconfig -1
+#endif
+#ifndef __NR_move_mount
+#define __NR_move_mount -1
+#endif
+
+
+static inline int fsopen(const char *fs_name, unsigned int flags)
+{
+	return syscall(__NR_fsopen, fs_name, flags);
+}
+
+static inline int fsmount(int fsfd, unsigned int flags, unsigned int ms_flags)
+{
+	return syscall(__NR_fsmount, fsfd, flags, ms_flags);
+}
+
+static inline int fsconfig(int fsfd, unsigned int cmd,
+			   const char *key, const void *val, int aux)
+{
+	return syscall(__NR_fsconfig, fsfd, cmd, key, val, aux);
+}
+
+static inline int move_mount(int from_dfd, const char *from_pathname,
+			     int to_dfd, const char *to_pathname,
+			     unsigned int flags)
+{
+	return syscall(__NR_move_mount,
+		       from_dfd, from_pathname,
+		       to_dfd, to_pathname, flags);
+}
+
+#define E_fsconfig(fd, cmd, key, val, aux)				\
+	do {								\
+		if (fsconfig(fd, cmd, key, val, aux) == -1)		\
+			mount_error(fd, key ?: "create");		\
+	} while (0)
+
+int main(int argc, char *argv[])
+{
+	int fsfd, mfd;
+
+	/* Mount a publically available AFS filesystem */
+	fsfd = fsopen("afs", 0);
+	if (fsfd == -1) {
+		perror("fsopen");
+		exit(1);
+	}
+
+	E_fsconfig(fsfd, FSCONFIG_SET_STRING, "source", "#grand.central.org:root.cell.", 0);
+	E_fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
+
+	mfd = fsmount(fsfd, 0, MOUNT_ATTR_RDONLY);
+	if (mfd < 0)
+		mount_error(fsfd, "fsmount");
+	E(close(fsfd));
+
+	if (move_mount(mfd, "", AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH) < 0) {
+		perror("move_mount");
+		exit(1);
+	}
+
+	E(close(mfd));
+	exit(0);
+}
diff --git a/samples/vfs/test-statx.c b/samples/vfs/test-statx.c
new file mode 100644
index 000000000000..e91f918e84c4
--- /dev/null
+++ b/samples/vfs/test-statx.c
@@ -0,0 +1,267 @@
+/* Test the statx() system call.
+ *
+ * Note that the output of this program is intended to look like the output of
+ * /bin/stat where possible.
+ *
+ * Copyright (C) 2015 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define _GNU_SOURCE
+#define _ATFILE_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <ctype.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <linux/stat.h>
+#include <linux/fcntl.h>
+#define statx foo
+#define statx_timestamp foo_timestamp
+#include <sys/stat.h>
+#undef statx
+#undef statx_timestamp
+
+#define AT_STATX_SYNC_TYPE	0x6000
+#define AT_STATX_SYNC_AS_STAT	0x0000
+#define AT_STATX_FORCE_SYNC	0x2000
+#define AT_STATX_DONT_SYNC	0x4000
+
+#ifndef __NR_statx
+#define __NR_statx -1
+#endif
+
+static __attribute__((unused))
+ssize_t statx(int dfd, const char *filename, unsigned flags,
+	      unsigned int mask, struct statx *buffer)
+{
+	return syscall(__NR_statx, dfd, filename, flags, mask, buffer);
+}
+
+static void print_time(const char *field, struct statx_timestamp *ts)
+{
+	struct tm tm;
+	time_t tim;
+	char buffer[100];
+	int len;
+
+	tim = ts->tv_sec;
+	if (!localtime_r(&tim, &tm)) {
+		perror("localtime_r");
+		exit(1);
+	}
+	len = strftime(buffer, 100, "%F %T", &tm);
+	if (len == 0) {
+		perror("strftime");
+		exit(1);
+	}
+	printf("%s", field);
+	fwrite(buffer, 1, len, stdout);
+	printf(".%09u", ts->tv_nsec);
+	len = strftime(buffer, 100, "%z", &tm);
+	if (len == 0) {
+		perror("strftime2");
+		exit(1);
+	}
+	fwrite(buffer, 1, len, stdout);
+	printf("\n");
+}
+
+static void dump_statx(struct statx *stx)
+{
+	char buffer[256], ft = '?';
+
+	printf("results=%x\n", stx->stx_mask);
+
+	printf(" ");
+	if (stx->stx_mask & STATX_SIZE)
+		printf(" Size: %-15llu", (unsigned long long)stx->stx_size);
+	if (stx->stx_mask & STATX_BLOCKS)
+		printf(" Blocks: %-10llu", (unsigned long long)stx->stx_blocks);
+	printf(" IO Block: %-6llu", (unsigned long long)stx->stx_blksize);
+	if (stx->stx_mask & STATX_TYPE) {
+		switch (stx->stx_mode & S_IFMT) {
+		case S_IFIFO:	printf("  FIFO\n");			ft = 'p'; break;
+		case S_IFCHR:	printf("  character special file\n");	ft = 'c'; break;
+		case S_IFDIR:	printf("  directory\n");		ft = 'd'; break;
+		case S_IFBLK:	printf("  block special file\n");	ft = 'b'; break;
+		case S_IFREG:	printf("  regular file\n");		ft = '-'; break;
+		case S_IFLNK:	printf("  symbolic link\n");		ft = 'l'; break;
+		case S_IFSOCK:	printf("  socket\n");			ft = 's'; break;
+		default:
+			printf(" unknown type (%o)\n", stx->stx_mode & S_IFMT);
+			break;
+		}
+	} else {
+		printf(" no type\n");
+	}
+
+	sprintf(buffer, "%02x:%02x", stx->stx_dev_major, stx->stx_dev_minor);
+	printf("Device: %-15s", buffer);
+	if (stx->stx_mask & STATX_INO)
+		printf(" Inode: %-11llu", (unsigned long long) stx->stx_ino);
+	if (stx->stx_mask & STATX_NLINK)
+		printf(" Links: %-5u", stx->stx_nlink);
+	if (stx->stx_mask & STATX_TYPE) {
+		switch (stx->stx_mode & S_IFMT) {
+		case S_IFBLK:
+		case S_IFCHR:
+			printf(" Device type: %u,%u",
+			       stx->stx_rdev_major, stx->stx_rdev_minor);
+			break;
+		}
+	}
+	printf("\n");
+
+	if (stx->stx_mask & STATX_MODE)
+		printf("Access: (%04o/%c%c%c%c%c%c%c%c%c%c)  ",
+		       stx->stx_mode & 07777,
+		       ft,
+		       stx->stx_mode & S_IRUSR ? 'r' : '-',
+		       stx->stx_mode & S_IWUSR ? 'w' : '-',
+		       stx->stx_mode & S_IXUSR ? 'x' : '-',
+		       stx->stx_mode & S_IRGRP ? 'r' : '-',
+		       stx->stx_mode & S_IWGRP ? 'w' : '-',
+		       stx->stx_mode & S_IXGRP ? 'x' : '-',
+		       stx->stx_mode & S_IROTH ? 'r' : '-',
+		       stx->stx_mode & S_IWOTH ? 'w' : '-',
+		       stx->stx_mode & S_IXOTH ? 'x' : '-');
+	if (stx->stx_mask & STATX_UID)
+		printf("Uid: %5d   ", stx->stx_uid);
+	if (stx->stx_mask & STATX_GID)
+		printf("Gid: %5d\n", stx->stx_gid);
+
+	if (stx->stx_mask & STATX_ATIME)
+		print_time("Access: ", &stx->stx_atime);
+	if (stx->stx_mask & STATX_MTIME)
+		print_time("Modify: ", &stx->stx_mtime);
+	if (stx->stx_mask & STATX_CTIME)
+		print_time("Change: ", &stx->stx_ctime);
+	if (stx->stx_mask & STATX_BTIME)
+		print_time(" Birth: ", &stx->stx_btime);
+
+	if (stx->stx_attributes_mask) {
+		unsigned char bits, mbits;
+		int loop, byte;
+
+		static char attr_representation[64 + 1] =
+			/* STATX_ATTR_ flags: */
+			"????????"	/* 63-56 */
+			"????????"	/* 55-48 */
+			"????????"	/* 47-40 */
+			"????????"	/* 39-32 */
+			"????????"	/* 31-24	0x00000000-ff000000 */
+			"????????"	/* 23-16	0x00000000-00ff0000 */
+			"???me???"	/* 15- 8	0x00000000-0000ff00 */
+			"?dai?c??"	/*  7- 0	0x00000000-000000ff */
+			;
+
+		printf("Attributes: %016llx (",
+		       (unsigned long long)stx->stx_attributes);
+		for (byte = 64 - 8; byte >= 0; byte -= 8) {
+			bits = stx->stx_attributes >> byte;
+			mbits = stx->stx_attributes_mask >> byte;
+			for (loop = 7; loop >= 0; loop--) {
+				int bit = byte + loop;
+
+				if (!(mbits & 0x80))
+					putchar('.');	/* Not supported */
+				else if (bits & 0x80)
+					putchar(attr_representation[63 - bit]);
+				else
+					putchar('-');	/* Not set */
+				bits <<= 1;
+				mbits <<= 1;
+			}
+			if (byte)
+				putchar(' ');
+		}
+		printf(")\n");
+	}
+}
+
+static void dump_hex(unsigned long long *data, int from, int to)
+{
+	unsigned offset, print_offset = 1, col = 0;
+
+	from /= 8;
+	to = (to + 7) / 8;
+
+	for (offset = from; offset < to; offset++) {
+		if (print_offset) {
+			printf("%04x: ", offset * 8);
+			print_offset = 0;
+		}
+		printf("%016llx", data[offset]);
+		col++;
+		if ((col & 3) == 0) {
+			printf("\n");
+			print_offset = 1;
+		} else {
+			printf(" ");
+		}
+	}
+
+	if (!print_offset)
+		printf("\n");
+}
+
+int main(int argc, char **argv)
+{
+	struct statx stx;
+	int ret, raw = 0, atflag = AT_SYMLINK_NOFOLLOW;
+
+	unsigned int mask = STATX_ALL;
+
+	for (argv++; *argv; argv++) {
+		if (strcmp(*argv, "-F") == 0) {
+			atflag &= ~AT_STATX_SYNC_TYPE;
+			atflag |= AT_STATX_FORCE_SYNC;
+			continue;
+		}
+		if (strcmp(*argv, "-D") == 0) {
+			atflag &= ~AT_STATX_SYNC_TYPE;
+			atflag |= AT_STATX_DONT_SYNC;
+			continue;
+		}
+		if (strcmp(*argv, "-L") == 0) {
+			atflag &= ~AT_SYMLINK_NOFOLLOW;
+			continue;
+		}
+		if (strcmp(*argv, "-O") == 0) {
+			mask &= ~STATX_BASIC_STATS;
+			continue;
+		}
+		if (strcmp(*argv, "-A") == 0) {
+			atflag |= AT_NO_AUTOMOUNT;
+			continue;
+		}
+		if (strcmp(*argv, "-R") == 0) {
+			raw = 1;
+			continue;
+		}
+
+		memset(&stx, 0xbf, sizeof(stx));
+		ret = statx(AT_FDCWD, *argv, atflag, mask, &stx);
+		printf("statx(%s) = %d\n", *argv, ret);
+		if (ret < 0) {
+			perror(*argv);
+			exit(1);
+		}
+
+		if (raw)
+			dump_hex((unsigned long long *)&stx, 0, sizeof(stx));
+
+		dump_statx(&stx);
+	}
+	return 0;
+}