Merge tag 'vfs-7.3-rc1.super' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs superblock updates from Christian Brauner:

 - Make it possible to share a block device between multiple
   filesystems.

   erofs can mount read-only blob devices shared between many
   superblocks, but because we only tracked a single superblock a
   freeze, thaw, removal or sync on such a device was never propagated
   to all the superblocks using it, and there was no way to find them.

   Add an efficient table to lookup all superblocks using a given block
   device.

 - A bunch of pre-existing fixes fell out of this work:

   A block-device freeze racing a btrfs device change could leave the
   whole filesystem stuck frozen. A bdev_freeze() issued by "dmsetup
   suspend" or an LVM snapshot resolves that holder to freeze the
   filesystem. and bdev_thaw() resolves it again to thaw. A freeze
   landing while btrfs is adding, removing or replacing a device freezes
   the filesystem. The membership change then drops that link. So the
   matching thaw could no longer find the superblock.

   Forbid freezing a device for the duration of a membership change,
   modelled on deny_write_access()/allow_write_access().

* tag 'vfs-7.3-rc1.super' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (24 commits)
  super: fix dying superblock warning messages
  block: reject block device inodes with i_rdev == 0 in lookup_bdev()
  selftests/filesystems: add ustat() coverage
  fs: look up the superblock via the device table in user_get_super()
  super: make fs_holder_ops private
  f2fs: open via dedicated fs bdev helpers
  erofs: open via dedicated fs bdev helpers
  fs: tolerate per-superblock freeze errors on shared devices
  fs: look up superblocks via the device table in fs_holder_ops
  ext4: open via dedicated fs bdev helpers
  btrfs: open via dedicated fs bdev helpers
  xfs: port to fs_bdev_file_open_by_path()
  fs: add dedicated block device open helpers for filesystems
  fs: maintain a global device-to-superblock table
  ocfs2: don't reset s_dev on dismount
  ext4: use anonymous devices for KUnit test superblocks
  fs, block: move blk_mode_t and fop_flags_t into <linux/types.h>
  super: take lock after last reference count
  super: convert s_count to refcount_t s_passive
  btrfs: deny freezing devices undergoing a replace
  ...

3 files changed, 137 insertions, 1 deletions

diff --git a/tools/testing/selftests/filesystems/.gitignore b/tools/testing/selftests/filesystems/.gitignore
index a78f894157de..9eb185fb2f9d 100644
--- a/tools/testing/selftests/filesystems/.gitignore
+++ b/tools/testing/selftests/filesystems/.gitignore
@@ -6,3 +6,4 @@ file_stressor
 anon_inode_test
 kernfs_test
 idmapped_tmpfile
+ustat_test
diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile
index a7ec2ba2dd83..03be337c1f35 100644
--- a/tools/testing/selftests/filesystems/Makefile
+++ b/tools/testing/selftests/filesystems/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 CFLAGS += $(KHDR_INCLUDES)
-TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test kernfs_test fclog
+TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test kernfs_test fclog ustat_test
 TEST_GEN_PROGS += idmapped_tmpfile
 TEST_GEN_PROGS_EXTENDED := dnotify_test
 
diff --git a/tools/testing/selftests/filesystems/ustat_test.c b/tools/testing/selftests/filesystems/ustat_test.c
new file mode 100644
index 000000000000..d429fd18d779
--- /dev/null
+++ b/tools/testing/selftests/filesystems/ustat_test.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test ustat(2): looking up superblocks by device number.
+ *
+ * ustat() resolves a device number to a mounted superblock via
+ * user_get_super(). Check that the device number of a mounted tmpfs (an
+ * anonymous device) resolves, that it stops resolving once the filesystem
+ * is unmounted and that bogus device numbers report EINVAL.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+/* struct ustat is not exported through UAPI, mirror include/linux/types.h. */
+struct ustat_buf {
+	int		f_tfree;
+	unsigned long	f_tinode;
+	char		f_fname[6];
+	char		f_fpack[6];
+	/* slack in case an architecture lays the struct out differently */
+	char		pad[64];
+};
+
+#ifdef __NR_ustat
+
+/*
+ * The kernel decodes @dev with new_decode_dev(), which matches the low 32
+ * bits of the st_dev encoding stat(2) returns for any major below 4096.
+ */
+static int sys_ustat(unsigned int dev, struct ustat_buf *buf)
+{
+	return syscall(__NR_ustat, dev, buf);
+}
+
+static int write_string(const char *path, const char *string)
+{
+	ssize_t len = strlen(string);
+	int fd;
+
+	fd = open(path, O_WRONLY);
+	if (fd < 0)
+		return -1;
+	if (write(fd, string, len) != len) {
+		close(fd);
+		return -1;
+	}
+	return close(fd);
+}
+
+/* Enter namespaces in which mounting a tmpfs instance is allowed. */
+static int setup_namespaces(void)
+{
+	uid_t uid = getuid();
+	gid_t gid = getgid();
+	char map[64];
+
+	if (unshare(CLONE_NEWNS | (uid ? CLONE_NEWUSER : 0)))
+		return -1;
+
+	if (uid) {
+		if (write_string("/proc/self/setgroups", "deny"))
+			return -1;
+		snprintf(map, sizeof(map), "0 %d 1", uid);
+		if (write_string("/proc/self/uid_map", map))
+			return -1;
+		snprintf(map, sizeof(map), "0 %d 1", gid);
+		if (write_string("/proc/self/gid_map", map))
+			return -1;
+	}
+
+	return mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL);
+}
+
+TEST(resolves_mounted_superblock)
+{
+	char dir[] = "/tmp/ustat_test.XXXXXX";
+	struct ustat_buf ub;
+	struct stat st;
+
+	ASSERT_NE(NULL, mkdtemp(dir));
+
+	if (setup_namespaces()) {
+		rmdir(dir);
+		SKIP(return, "cannot set up namespaces: %s", strerror(errno));
+	}
+
+	ASSERT_EQ(0, mount("ustat_test", dir, "tmpfs", 0, NULL));
+	ASSERT_EQ(0, stat(dir, &st));
+
+	memset(&ub, 0xff, sizeof(ub));
+	ASSERT_EQ(0, sys_ustat(st.st_dev, &ub))
+		TH_LOG("ustat(%u): %s", (unsigned int)st.st_dev,
+		       strerror(errno));
+
+	ASSERT_EQ(0, umount(dir));
+
+	/* The unmount removed the superblock, the device is gone. */
+	ASSERT_EQ(-1, sys_ustat(st.st_dev, &ub));
+	ASSERT_EQ(EINVAL, errno);
+
+	rmdir(dir);
+}
+
+TEST(bogus_device_numbers)
+{
+	struct ustat_buf ub;
+
+	ASSERT_EQ(-1, sys_ustat(0, &ub));
+	ASSERT_EQ(EINVAL, errno);
+
+	/* major 4095, minor 1048575: nothing plausible lives there */
+	ASSERT_EQ(-1, sys_ustat((0xfffu << 8) | 0xffu | (0xfff00u << 12), &ub));
+	ASSERT_EQ(EINVAL, errno);
+}
+
+#else /* !__NR_ustat */
+
+TEST(unsupported)
+{
+	SKIP(return, "ustat(2) is not available on this architecture");
+}
+
+#endif /* __NR_ustat */
+
+TEST_HARNESS_MAIN