sched_ext: Maintain an online cid mask in the scheduler arenagrafted

Schedulers on the default cid mapping treat [0, nr_online_cids) as the
online set and restart on hotplug. Schedulers that install their own mapping
with scx_bpf_cid_override() have no way to learn which cids are online: the
count no longer identifies members and the CPU-form cpumask is unusable from
cid programs. This is an obvious hole in the cid API.

Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's
arena, allocated alongside the per-CPU scratch masks and populated after the
cid mapping is finalized and before ops.init(), for child schedulers too.
The pointer stays valid through ops.exit() with no reference to take. It is
the arena offset as a void pointer, the same form struct_ops arena arguments
arrive in. The verifier types the void return as a scalar for the program's
arena cast.

The mask follows the SCX hotplug notifications: seeded from cpu_active_mask
and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask
only inside a hotplug transition. Updates walk the scheduler list under the
lock that also serializes unlinking. Reads are live, not atomic snapshots.
Root initialization excludes hotplug.

v2: Reworded the getter kerneldoc (Andrea Righi).

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

7 files changed, 618 insertions, 0 deletions

diff --git a/tools/testing/selftests/mount/.gitignore b/tools/testing/selftests/mount/.gitignore
new file mode 100644
index 000000000..17f2d8415
--- /dev/null
+++ b/tools/testing/selftests/mount/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+unprivileged-remount-test
+nosymfollow-test
diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile
new file mode 100644
index 000000000..2d9454841
--- /dev/null
+++ b/tools/testing/selftests/mount/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for mount selftests.
+CFLAGS = -Wall \
+         -O2
+
+TEST_PROGS := run_unprivileged_remount.sh run_nosymfollow.sh
+TEST_GEN_FILES := unprivileged-remount-test nosymfollow-test
+
+include ../lib.mk
diff --git a/tools/testing/selftests/mount/config b/tools/testing/selftests/mount/config
new file mode 100644
index 000000000..416bd53ce
--- /dev/null
+++ b/tools/testing/selftests/mount/config
@@ -0,0 +1 @@
+CONFIG_USER_NS=y
diff --git a/tools/testing/selftests/mount/nosymfollow-test.c b/tools/testing/selftests/mount/nosymfollow-test.c
new file mode 100644
index 000000000..650d6d80a
--- /dev/null
+++ b/tools/testing/selftests/mount/nosymfollow-test.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <sched.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/vfs.h>
+#include <unistd.h>
+
+#ifndef MS_NOSYMFOLLOW
+# define MS_NOSYMFOLLOW 256     /* Do not follow symlinks */
+#endif
+
+#ifndef ST_NOSYMFOLLOW
+# define ST_NOSYMFOLLOW 0x2000  /* Do not follow symlinks */
+#endif
+
+#define DATA "/tmp/data"
+#define LINK "/tmp/symlink"
+#define TMP  "/tmp"
+
+static void die(char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	exit(EXIT_FAILURE);
+}
+
+static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt,
+		va_list ap)
+{
+	ssize_t written;
+	char buf[4096];
+	int buf_len;
+	int fd;
+
+	buf_len = vsnprintf(buf, sizeof(buf), fmt, ap);
+	if (buf_len < 0)
+		die("vsnprintf failed: %s\n", strerror(errno));
+
+	if (buf_len >= sizeof(buf))
+		die("vsnprintf output truncated\n");
+
+	fd = open(filename, O_WRONLY);
+	if (fd < 0) {
+		if ((errno == ENOENT) && enoent_ok)
+			return;
+		die("open of %s failed: %s\n", filename, strerror(errno));
+	}
+
+	written = write(fd, buf, buf_len);
+	if (written != buf_len) {
+		if (written >= 0) {
+			die("short write to %s\n", filename);
+		} else {
+			die("write to %s failed: %s\n",
+				filename, strerror(errno));
+		}
+	}
+
+	if (close(fd) != 0)
+		die("close of %s failed: %s\n", filename, strerror(errno));
+}
+
+static void maybe_write_file(char *filename, char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vmaybe_write_file(true, filename, fmt, ap);
+	va_end(ap);
+}
+
+static void write_file(char *filename, char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vmaybe_write_file(false, filename, fmt, ap);
+	va_end(ap);
+}
+
+static void create_and_enter_ns(void)
+{
+	uid_t uid = getuid();
+	gid_t gid = getgid();
+
+	if (unshare(CLONE_NEWUSER) != 0)
+		die("unshare(CLONE_NEWUSER) failed: %s\n", strerror(errno));
+
+	maybe_write_file("/proc/self/setgroups", "deny");
+	write_file("/proc/self/uid_map", "0 %d 1", uid);
+	write_file("/proc/self/gid_map", "0 %d 1", gid);
+
+	if (setgid(0) != 0)
+		die("setgid(0) failed %s\n", strerror(errno));
+	if (setuid(0) != 0)
+		die("setuid(0) failed %s\n", strerror(errno));
+
+	if (unshare(CLONE_NEWNS) != 0)
+		die("unshare(CLONE_NEWNS) failed: %s\n", strerror(errno));
+}
+
+static void setup_symlink(void)
+{
+	int data, err;
+
+	data = creat(DATA, O_RDWR);
+	if (data < 0)
+		die("creat failed: %s\n", strerror(errno));
+
+	err = symlink(DATA, LINK);
+	if (err < 0)
+		die("symlink failed: %s\n", strerror(errno));
+
+	if (close(data) != 0)
+		die("close of %s failed: %s\n", DATA, strerror(errno));
+}
+
+static void test_link_traversal(bool nosymfollow)
+{
+	int link;
+
+	link = open(LINK, 0, O_RDWR);
+	if (nosymfollow) {
+		if ((link != -1 || errno != ELOOP)) {
+			die("link traversal unexpected result: %d, %s\n",
+					link, strerror(errno));
+		}
+	} else {
+		if (link < 0)
+			die("link traversal failed: %s\n", strerror(errno));
+
+		if (close(link) != 0)
+			die("close of link failed: %s\n", strerror(errno));
+	}
+}
+
+static void test_readlink(void)
+{
+	char buf[4096];
+	ssize_t ret;
+
+	bzero(buf, sizeof(buf));
+
+	ret = readlink(LINK, buf, sizeof(buf));
+	if (ret < 0)
+		die("readlink failed: %s\n", strerror(errno));
+	if (strcmp(buf, DATA) != 0)
+		die("readlink strcmp failed: '%s' '%s'\n", buf, DATA);
+}
+
+static void test_realpath(void)
+{
+	char *path = realpath(LINK, NULL);
+
+	if (!path)
+		die("realpath failed: %s\n", strerror(errno));
+	if (strcmp(path, DATA) != 0)
+		die("realpath strcmp failed\n");
+
+	free(path);
+}
+
+static void test_statfs(bool nosymfollow)
+{
+	struct statfs buf;
+	int ret;
+
+	ret = statfs(TMP, &buf);
+	if (ret)
+		die("statfs failed: %s\n", strerror(errno));
+
+	if (nosymfollow) {
+		if ((buf.f_flags & ST_NOSYMFOLLOW) == 0)
+			die("ST_NOSYMFOLLOW not set on %s\n", TMP);
+	} else {
+		if ((buf.f_flags & ST_NOSYMFOLLOW) != 0)
+			die("ST_NOSYMFOLLOW set on %s\n", TMP);
+	}
+}
+
+static void run_tests(bool nosymfollow)
+{
+	test_link_traversal(nosymfollow);
+	test_readlink();
+	test_realpath();
+	test_statfs(nosymfollow);
+}
+
+int main(int argc, char **argv)
+{
+	create_and_enter_ns();
+
+	if (mount("testing", TMP, "ramfs", 0, NULL) != 0)
+		die("mount failed: %s\n", strerror(errno));
+
+	setup_symlink();
+	run_tests(false);
+
+	if (mount("testing", TMP, "ramfs", MS_REMOUNT|MS_NOSYMFOLLOW, NULL) != 0)
+		die("remount failed: %s\n", strerror(errno));
+
+	run_tests(true);
+
+	return EXIT_SUCCESS;
+}
diff --git a/tools/testing/selftests/mount/run_nosymfollow.sh b/tools/testing/selftests/mount/run_nosymfollow.sh
new file mode 100755
index 000000000..5fbbf0304
--- /dev/null
+++ b/tools/testing/selftests/mount/run_nosymfollow.sh
@@ -0,0 +1,4 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+./nosymfollow-test
diff --git a/tools/testing/selftests/mount/run_unprivileged_remount.sh b/tools/testing/selftests/mount/run_unprivileged_remount.sh
new file mode 100755
index 000000000..4ab8f507d
--- /dev/null
+++ b/tools/testing/selftests/mount/run_unprivileged_remount.sh
@@ -0,0 +1,12 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+# Run mount selftests
+if [ -f /proc/self/uid_map ] ; then
+	./unprivileged-remount-test ;
+else
+	echo "WARN: No /proc/self/uid_map exist, test skipped." ;
+	exit $ksft_skip
+fi
diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c
new file mode 100644
index 000000000..d2917054f
--- /dev/null
+++ b/tools/testing/selftests/mount/unprivileged-remount-test.c
@@ -0,0 +1,371 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <sys/wait.h>
+#include <sys/vfs.h>
+#include <sys/statvfs.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <grp.h>
+#include <stdbool.h>
+#include <stdarg.h>
+
+#ifndef CLONE_NEWNS
+# define CLONE_NEWNS 0x00020000
+#endif
+#ifndef CLONE_NEWUTS
+# define CLONE_NEWUTS 0x04000000
+#endif
+#ifndef CLONE_NEWIPC
+# define CLONE_NEWIPC 0x08000000
+#endif
+#ifndef CLONE_NEWNET
+# define CLONE_NEWNET 0x40000000
+#endif
+#ifndef CLONE_NEWUSER
+# define CLONE_NEWUSER 0x10000000
+#endif
+#ifndef CLONE_NEWPID
+# define CLONE_NEWPID 0x20000000
+#endif
+
+#ifndef MS_REC
+# define MS_REC 16384
+#endif
+#ifndef MS_RELATIME
+# define MS_RELATIME (1 << 21)
+#endif
+#ifndef MS_STRICTATIME
+# define MS_STRICTATIME (1 << 24)
+#endif
+
+static void die(char *fmt, ...)
+{
+	va_list ap;
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	exit(EXIT_FAILURE);
+}
+
+static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap)
+{
+	char buf[4096];
+	int fd;
+	ssize_t written;
+	int buf_len;
+
+	buf_len = vsnprintf(buf, sizeof(buf), fmt, ap);
+	if (buf_len < 0) {
+		die("vsnprintf failed: %s\n",
+		    strerror(errno));
+	}
+	if (buf_len >= sizeof(buf)) {
+		die("vsnprintf output truncated\n");
+	}
+
+	fd = open(filename, O_WRONLY);
+	if (fd < 0) {
+		if ((errno == ENOENT) && enoent_ok)
+			return;
+		die("open of %s failed: %s\n",
+		    filename, strerror(errno));
+	}
+	written = write(fd, buf, buf_len);
+	if (written != buf_len) {
+		if (written >= 0) {
+			die("short write to %s\n", filename);
+		} else {
+			die("write to %s failed: %s\n",
+				filename, strerror(errno));
+		}
+	}
+	if (close(fd) != 0) {
+		die("close of %s failed: %s\n",
+			filename, strerror(errno));
+	}
+}
+
+static void maybe_write_file(char *filename, char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vmaybe_write_file(true, filename, fmt, ap);
+	va_end(ap);
+
+}
+
+static void write_file(char *filename, char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vmaybe_write_file(false, filename, fmt, ap);
+	va_end(ap);
+
+}
+
+static int read_mnt_flags(const char *path)
+{
+	int ret;
+	struct statvfs stat;
+	int mnt_flags;
+
+	ret = statvfs(path, &stat);
+	if (ret != 0) {
+		die("statvfs of %s failed: %s\n",
+			path, strerror(errno));
+	}
+	if (stat.f_flag & ~(ST_RDONLY | ST_NOSUID | ST_NODEV | \
+			ST_NOEXEC | ST_NOATIME | ST_NODIRATIME | ST_RELATIME | \
+			ST_SYNCHRONOUS | ST_MANDLOCK)) {
+		die("Unrecognized mount flags\n");
+	}
+	mnt_flags = 0;
+	if (stat.f_flag & ST_RDONLY)
+		mnt_flags |= MS_RDONLY;
+	if (stat.f_flag & ST_NOSUID)
+		mnt_flags |= MS_NOSUID;
+	if (stat.f_flag & ST_NODEV)
+		mnt_flags |= MS_NODEV;
+	if (stat.f_flag & ST_NOEXEC)
+		mnt_flags |= MS_NOEXEC;
+	if (stat.f_flag & ST_NOATIME)
+		mnt_flags |= MS_NOATIME;
+	if (stat.f_flag & ST_NODIRATIME)
+		mnt_flags |= MS_NODIRATIME;
+	if (stat.f_flag & ST_RELATIME)
+		mnt_flags |= MS_RELATIME;
+	if (stat.f_flag & ST_SYNCHRONOUS)
+		mnt_flags |= MS_SYNCHRONOUS;
+	if (stat.f_flag & ST_MANDLOCK)
+		mnt_flags |= ST_MANDLOCK;
+
+	return mnt_flags;
+}
+
+static void create_and_enter_userns(void)
+{
+	uid_t uid;
+	gid_t gid;
+
+	uid = getuid();
+	gid = getgid();
+
+	if (unshare(CLONE_NEWUSER) !=0) {
+		die("unshare(CLONE_NEWUSER) failed: %s\n",
+			strerror(errno));
+	}
+
+	maybe_write_file("/proc/self/setgroups", "deny");
+	write_file("/proc/self/uid_map", "0 %d 1", uid);
+	write_file("/proc/self/gid_map", "0 %d 1", gid);
+
+	if (setgid(0) != 0) {
+		die ("setgid(0) failed %s\n",
+			strerror(errno));
+	}
+	if (setuid(0) != 0) {
+		die("setuid(0) failed %s\n",
+			strerror(errno));
+	}
+}
+
+static
+bool test_unpriv_remount(const char *fstype, const char *mount_options,
+			 int mount_flags, int remount_flags, int invalid_flags)
+{
+	pid_t child;
+
+	child = fork();
+	if (child == -1) {
+		die("fork failed: %s\n",
+			strerror(errno));
+	}
+	if (child != 0) { /* parent */
+		pid_t pid;
+		int status;
+		pid = waitpid(child, &status, 0);
+		if (pid == -1) {
+			die("waitpid failed: %s\n",
+				strerror(errno));
+		}
+		if (pid != child) {
+			die("waited for %d got %d\n",
+				child, pid);
+		}
+		if (!WIFEXITED(status)) {
+			die("child did not terminate cleanly\n");
+		}
+		return WEXITSTATUS(status) == EXIT_SUCCESS;
+	}
+
+	create_and_enter_userns();
+	if (unshare(CLONE_NEWNS) != 0) {
+		die("unshare(CLONE_NEWNS) failed: %s\n",
+			strerror(errno));
+	}
+
+	if (mount("testing", "/tmp", fstype, mount_flags, mount_options) != 0) {
+		die("mount of %s with options '%s' on /tmp failed: %s\n",
+		    fstype,
+		    mount_options? mount_options : "",
+		    strerror(errno));
+	}
+
+	create_and_enter_userns();
+
+	if (unshare(CLONE_NEWNS) != 0) {
+		die("unshare(CLONE_NEWNS) failed: %s\n",
+			strerror(errno));
+	}
+
+	if (mount("/tmp", "/tmp", "none",
+		  MS_REMOUNT | MS_BIND | remount_flags, NULL) != 0) {
+		/* system("cat /proc/self/mounts"); */
+		die("remount of /tmp failed: %s\n",
+		    strerror(errno));
+	}
+
+	if (mount("/tmp", "/tmp", "none",
+		  MS_REMOUNT | MS_BIND | invalid_flags, NULL) == 0) {
+		/* system("cat /proc/self/mounts"); */
+		die("remount of /tmp with invalid flags "
+		    "succeeded unexpectedly\n");
+	}
+	exit(EXIT_SUCCESS);
+}
+
+static bool test_unpriv_remount_simple(int mount_flags)
+{
+	return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags, 0);
+}
+
+static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags)
+{
+	return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags,
+				   invalid_flags);
+}
+
+static bool test_priv_mount_unpriv_remount(void)
+{
+	pid_t child;
+	int ret;
+	const char *orig_path = "/dev";
+	const char *dest_path = "/tmp";
+	int orig_mnt_flags, remount_mnt_flags;
+
+	child = fork();
+	if (child == -1) {
+		die("fork failed: %s\n",
+			strerror(errno));
+	}
+	if (child != 0) { /* parent */
+		pid_t pid;
+		int status;
+		pid = waitpid(child, &status, 0);
+		if (pid == -1) {
+			die("waitpid failed: %s\n",
+				strerror(errno));
+		}
+		if (pid != child) {
+			die("waited for %d got %d\n",
+				child, pid);
+		}
+		if (!WIFEXITED(status)) {
+			die("child did not terminate cleanly\n");
+		}
+		return WEXITSTATUS(status) == EXIT_SUCCESS;
+	}
+
+	orig_mnt_flags = read_mnt_flags(orig_path);
+
+	create_and_enter_userns();
+	ret = unshare(CLONE_NEWNS);
+	if (ret != 0) {
+		die("unshare(CLONE_NEWNS) failed: %s\n",
+			strerror(errno));
+	}
+
+	ret = mount(orig_path, dest_path, "bind", MS_BIND | MS_REC, NULL);
+	if (ret != 0) {
+		die("recursive bind mount of %s onto %s failed: %s\n",
+			orig_path, dest_path, strerror(errno));
+	}
+
+	ret = mount(dest_path, dest_path, "none",
+		    MS_REMOUNT | MS_BIND | orig_mnt_flags , NULL);
+	if (ret != 0) {
+		/* system("cat /proc/self/mounts"); */
+		die("remount of /tmp failed: %s\n",
+		    strerror(errno));
+	}
+
+	remount_mnt_flags = read_mnt_flags(dest_path);
+	if (orig_mnt_flags != remount_mnt_flags) {
+		die("Mount flags unexpectedly changed during remount of %s originally mounted on %s\n",
+			dest_path, orig_path);
+	}
+	exit(EXIT_SUCCESS);
+}
+
+int main(int argc, char **argv)
+{
+	if (!test_unpriv_remount_simple(MS_RDONLY)) {
+		die("MS_RDONLY malfunctions\n");
+	}
+	if (!test_unpriv_remount("devpts", "newinstance", MS_NODEV, MS_NODEV, 0)) {
+		die("MS_NODEV malfunctions\n");
+	}
+	if (!test_unpriv_remount_simple(MS_NOSUID)) {
+		die("MS_NOSUID malfunctions\n");
+	}
+	if (!test_unpriv_remount_simple(MS_NOEXEC)) {
+		die("MS_NOEXEC malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_RELATIME,
+				       MS_NOATIME))
+	{
+		die("MS_RELATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_STRICTATIME,
+				       MS_NOATIME))
+	{
+		die("MS_STRICTATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_NOATIME,
+				       MS_STRICTATIME))
+	{
+		die("MS_NOATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME,
+				       MS_NOATIME))
+	{
+		die("MS_RELATIME|MS_NODIRATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME,
+				       MS_NOATIME))
+	{
+		die("MS_STRICTATIME|MS_NODIRATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME,
+				       MS_STRICTATIME))
+	{
+		die("MS_NOATIME|MS_DIRATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount("ramfs", NULL, MS_STRICTATIME, 0, MS_NOATIME))
+	{
+		die("Default atime malfunctions\n");
+	}
+	if (!test_priv_mount_unpriv_remount()) {
+		die("Mount flags unexpectedly changed after remount\n");
+	}
+	return EXIT_SUCCESS;
+}