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>

5 files changed, 927 insertions, 0 deletions

diff --git a/tools/testing/selftests/breakpoints/.gitignore b/tools/testing/selftests/breakpoints/.gitignore
new file mode 100644
index 000000000..def2e97da
--- /dev/null
+++ b/tools/testing/selftests/breakpoints/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+breakpoint_test
+step_after_suspend_test
diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile
new file mode 100644
index 000000000..0b8f5acf7
--- /dev/null
+++ b/tools/testing/selftests/breakpoints/Makefile
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0
+# Taken from perf makefile
+ARCH ?= $(shell uname -m 2>/dev/null || echo not)
+override ARCH := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
+
+TEST_GEN_PROGS := step_after_suspend_test
+
+ifeq ($(ARCH),x86)
+TEST_GEN_PROGS += breakpoint_test
+endif
+ifneq (,$(filter $(ARCH),aarch64 arm64))
+TEST_GEN_PROGS += breakpoint_test_arm64
+endif
+
+include ../lib.mk
+
diff --git a/tools/testing/selftests/breakpoints/breakpoint_test.c b/tools/testing/selftests/breakpoints/breakpoint_test.c
new file mode 100644
index 000000000..1159d8189
--- /dev/null
+++ b/tools/testing/selftests/breakpoints/breakpoint_test.c
@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2011 Red Hat, Inc., Frederic Weisbecker <fweisbec@redhat.com>
+ *
+ * Selftests for breakpoints (and more generally the do_debug() path) in x86.
+ */
+
+
+#include <sys/ptrace.h>
+#include <unistd.h>
+#include <stddef.h>
+#include <sys/user.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <errno.h>
+#include <string.h>
+
+#include "kselftest.h"
+
+#define COUNT_ISN_BPS	4
+#define COUNT_WPS	4
+
+/* Breakpoint access modes */
+enum {
+	BP_X = 1,
+	BP_RW = 2,
+	BP_W = 4,
+};
+
+static pid_t child_pid;
+
+/*
+ * Ensures the child and parent are always "talking" about
+ * the same test sequence. (ie: that we haven't forgotten
+ * to call check_trapped() somewhere).
+ */
+static int nr_tests;
+
+static void set_breakpoint_addr(void *addr, int n)
+{
+	int ret;
+
+	ret = ptrace(PTRACE_POKEUSER, child_pid,
+		     offsetof(struct user, u_debugreg[n]), addr);
+	if (ret)
+		ksft_exit_fail_msg("Can't set breakpoint addr: %s\n",
+			strerror(errno));
+}
+
+static void toggle_breakpoint(int n, int type, int len,
+			      int local, int global, int set)
+{
+	int ret;
+
+	int xtype, xlen;
+	unsigned long vdr7, dr7;
+
+	switch (type) {
+	case BP_X:
+		xtype = 0;
+		break;
+	case BP_W:
+		xtype = 1;
+		break;
+	case BP_RW:
+		xtype = 3;
+		break;
+	}
+
+	switch (len) {
+	case 1:
+		xlen = 0;
+		break;
+	case 2:
+		xlen = 4;
+		break;
+	case 4:
+		xlen = 0xc;
+		break;
+	case 8:
+		xlen = 8;
+		break;
+	}
+
+	dr7 = ptrace(PTRACE_PEEKUSER, child_pid,
+		     offsetof(struct user, u_debugreg[7]), 0);
+
+	vdr7 = (xlen | xtype) << 16;
+	vdr7 <<= 4 * n;
+
+	if (local) {
+		vdr7 |= 1 << (2 * n);
+		vdr7 |= 1 << 8;
+	}
+	if (global) {
+		vdr7 |= 2 << (2 * n);
+		vdr7 |= 1 << 9;
+	}
+
+	if (set)
+		dr7 |= vdr7;
+	else
+		dr7 &= ~vdr7;
+
+	ret = ptrace(PTRACE_POKEUSER, child_pid,
+		     offsetof(struct user, u_debugreg[7]), dr7);
+	if (ret) {
+		ksft_print_msg("Can't set dr7: %s\n", strerror(errno));
+		exit(-1);
+	}
+}
+
+/* Dummy variables to test read/write accesses */
+static unsigned long long dummy_var[4];
+
+/* Dummy functions to test execution accesses */
+static void dummy_func(void) { }
+static void dummy_func1(void) { }
+static void dummy_func2(void) { }
+static void dummy_func3(void) { }
+
+static void (*dummy_funcs[])(void) = {
+	dummy_func,
+	dummy_func1,
+	dummy_func2,
+	dummy_func3,
+};
+
+static int trapped;
+
+static void check_trapped(void)
+{
+	/*
+	 * If we haven't trapped, wake up the parent
+	 * so that it notices the failure.
+	 */
+	if (!trapped)
+		kill(getpid(), SIGUSR1);
+	trapped = 0;
+
+	nr_tests++;
+}
+
+static void write_var(int len)
+{
+	char *pcval; short *psval; int *pival; long long *plval;
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		switch (len) {
+		case 1:
+			pcval = (char *)&dummy_var[i];
+			*pcval = 0xff;
+			break;
+		case 2:
+			psval = (short *)&dummy_var[i];
+			*psval = 0xffff;
+			break;
+		case 4:
+			pival = (int *)&dummy_var[i];
+			*pival = 0xffffffff;
+			break;
+		case 8:
+			plval = (long long *)&dummy_var[i];
+			*plval = 0xffffffffffffffffLL;
+			break;
+		}
+		check_trapped();
+	}
+}
+
+static void read_var(int len)
+{
+	char cval; short sval; int ival; long long lval;
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		switch (len) {
+		case 1:
+			cval = *(char *)&dummy_var[i];
+			break;
+		case 2:
+			sval = *(short *)&dummy_var[i];
+			break;
+		case 4:
+			ival = *(int *)&dummy_var[i];
+			break;
+		case 8:
+			lval = *(long long *)&dummy_var[i];
+			break;
+		}
+		check_trapped();
+	}
+}
+
+/*
+ * Do the r/w/x accesses to trigger the breakpoints. And run
+ * the usual traps.
+ */
+static void trigger_tests(void)
+{
+	int len, local, global, i;
+	char val;
+	int ret;
+
+	ret = ptrace(PTRACE_TRACEME, 0, NULL, 0);
+	if (ret) {
+		ksft_print_msg("Can't be traced? %s\n", strerror(errno));
+		return;
+	}
+
+	/* Wake up father so that it sets up the first test */
+	kill(getpid(), SIGUSR1);
+
+	/* Test instruction breakpoints */
+	for (local = 0; local < 2; local++) {
+		for (global = 0; global < 2; global++) {
+			if (!local && !global)
+				continue;
+
+			for (i = 0; i < COUNT_ISN_BPS; i++) {
+				dummy_funcs[i]();
+				check_trapped();
+			}
+		}
+	}
+
+	/* Test write watchpoints */
+	for (len = 1; len <= sizeof(long); len <<= 1) {
+		for (local = 0; local < 2; local++) {
+			for (global = 0; global < 2; global++) {
+				if (!local && !global)
+					continue;
+				write_var(len);
+			}
+		}
+	}
+
+	/* Test read/write watchpoints (on read accesses) */
+	for (len = 1; len <= sizeof(long); len <<= 1) {
+		for (local = 0; local < 2; local++) {
+			for (global = 0; global < 2; global++) {
+				if (!local && !global)
+					continue;
+				read_var(len);
+			}
+		}
+	}
+
+	/* Icebp trap */
+	asm(".byte 0xf1\n");
+	check_trapped();
+
+	/* Int 3 trap */
+	asm("int $3\n");
+	check_trapped();
+
+	kill(getpid(), SIGUSR1);
+}
+
+static void check_success(const char *msg)
+{
+	int child_nr_tests;
+	int status;
+	int ret;
+
+	/* Wait for the child to SIGTRAP */
+	wait(&status);
+
+	ret = 0;
+
+	if (WSTOPSIG(status) == SIGTRAP) {
+		child_nr_tests = ptrace(PTRACE_PEEKDATA, child_pid,
+					&nr_tests, 0);
+		if (child_nr_tests == nr_tests)
+			ret = 1;
+		if (ptrace(PTRACE_POKEDATA, child_pid, &trapped, 1))
+			ksft_exit_fail_msg("Can't poke: %s\n", strerror(errno));
+	}
+
+	nr_tests++;
+
+	if (ret)
+		ksft_test_result_pass("%s", msg);
+	else
+		ksft_test_result_fail("%s", msg);
+}
+
+static void launch_instruction_breakpoints(char *buf, int local, int global)
+{
+	int i;
+
+	for (i = 0; i < COUNT_ISN_BPS; i++) {
+		set_breakpoint_addr(dummy_funcs[i], i);
+		toggle_breakpoint(i, BP_X, 1, local, global, 1);
+		ptrace(PTRACE_CONT, child_pid, NULL, 0);
+		sprintf(buf, "Test breakpoint %d with local: %d global: %d\n",
+			i, local, global);
+		check_success(buf);
+		toggle_breakpoint(i, BP_X, 1, local, global, 0);
+	}
+}
+
+static void launch_watchpoints(char *buf, int mode, int len,
+			       int local, int global)
+{
+	const char *mode_str;
+	int i;
+
+	if (mode == BP_W)
+		mode_str = "write";
+	else
+		mode_str = "read";
+
+	for (i = 0; i < COUNT_WPS; i++) {
+		set_breakpoint_addr(&dummy_var[i], i);
+		toggle_breakpoint(i, mode, len, local, global, 1);
+		ptrace(PTRACE_CONT, child_pid, NULL, 0);
+		sprintf(buf,
+			"Test %s watchpoint %d with len: %d local: %d global: %d\n",
+			mode_str, i, len, local, global);
+		check_success(buf);
+		toggle_breakpoint(i, mode, len, local, global, 0);
+	}
+}
+
+/* Set the breakpoints and check the child successfully trigger them */
+static void launch_tests(void)
+{
+	char buf[1024];
+	unsigned int tests = 0;
+	int len, local, global, i;
+
+	tests += 3 * COUNT_ISN_BPS;
+	tests += sizeof(long) / 2 * 3 * COUNT_WPS;
+	tests += sizeof(long) / 2 * 3 * COUNT_WPS;
+	tests += 2;
+	ksft_set_plan(tests);
+
+	/* Instruction breakpoints */
+	for (local = 0; local < 2; local++) {
+		for (global = 0; global < 2; global++) {
+			if (!local && !global)
+				continue;
+			launch_instruction_breakpoints(buf, local, global);
+		}
+	}
+
+	/* Write watchpoint */
+	for (len = 1; len <= sizeof(long); len <<= 1) {
+		for (local = 0; local < 2; local++) {
+			for (global = 0; global < 2; global++) {
+				if (!local && !global)
+					continue;
+				launch_watchpoints(buf, BP_W, len,
+						   local, global);
+			}
+		}
+	}
+
+	/* Read-Write watchpoint */
+	for (len = 1; len <= sizeof(long); len <<= 1) {
+		for (local = 0; local < 2; local++) {
+			for (global = 0; global < 2; global++) {
+				if (!local && !global)
+					continue;
+				launch_watchpoints(buf, BP_RW, len,
+						   local, global);
+			}
+		}
+	}
+
+	/* Icebp traps */
+	ptrace(PTRACE_CONT, child_pid, NULL, 0);
+	check_success("Test icebp\n");
+
+	/* Int 3 traps */
+	ptrace(PTRACE_CONT, child_pid, NULL, 0);
+	check_success("Test int 3 trap\n");
+
+	ptrace(PTRACE_CONT, child_pid, NULL, 0);
+}
+
+int main(int argc, char **argv)
+{
+	pid_t pid;
+	int ret;
+
+	ksft_print_header();
+
+	pid = fork();
+	if (!pid) {
+		trigger_tests();
+		exit(0);
+	}
+
+	child_pid = pid;
+
+	wait(NULL);
+
+	launch_tests();
+
+	wait(NULL);
+
+	ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
new file mode 100644
index 000000000..5fc0f37f3
--- /dev/null
+++ b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2016 Google, Inc.
+ *
+ * Original Code by Pavel Labath <labath@google.com>
+ *
+ * Code modified by Pratyush Anand <panand@redhat.com>
+ * for testing different byte select for each access size.
+ */
+
+#define _GNU_SOURCE
+
+#include <asm/ptrace.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/ptrace.h>
+#include <sys/param.h>
+#include <sys/uio.h>
+#include <stdint.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <string.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <elf.h>
+#include <errno.h>
+#include <signal.h>
+
+#include "kselftest.h"
+
+static volatile uint8_t var[96] __attribute__((__aligned__(32)));
+
+static void child(int size, int wr)
+{
+	volatile uint8_t *addr = &var[32 + wr];
+
+	if (ptrace(PTRACE_TRACEME, 0, NULL, NULL) != 0) {
+		ksft_print_msg(
+			"ptrace(PTRACE_TRACEME) failed: %s\n",
+			strerror(errno));
+		_exit(1);
+	}
+
+	if (raise(SIGSTOP) != 0) {
+		ksft_print_msg(
+			"raise(SIGSTOP) failed: %s\n", strerror(errno));
+		_exit(1);
+	}
+
+	if ((uintptr_t) addr % size) {
+		ksft_print_msg(
+			 "Wrong address write for the given size: %s\n",
+			 strerror(errno));
+		_exit(1);
+	}
+
+	switch (size) {
+	case 1:
+		*addr = 47;
+		break;
+	case 2:
+		*(uint16_t *)addr = 47;
+		break;
+	case 4:
+		*(uint32_t *)addr = 47;
+		break;
+	case 8:
+		*(uint64_t *)addr = 47;
+		break;
+	case 16:
+		__asm__ volatile ("stp x29, x30, %0" : "=m" (addr[0]));
+		break;
+	case 32:
+		__asm__ volatile ("stp q29, q30, %0" : "=m" (addr[0]));
+		break;
+	}
+
+	_exit(0);
+}
+
+static bool set_watchpoint(pid_t pid, int size, int wp)
+{
+	const volatile uint8_t *addr = &var[32 + wp];
+	const int offset = (uintptr_t)addr % 8;
+	const unsigned int byte_mask = ((1 << size) - 1) << offset;
+	const unsigned int type = 2; /* Write */
+	const unsigned int enable = 1;
+	const unsigned int control = byte_mask << 5 | type << 3 | enable;
+	struct user_hwdebug_state dreg_state;
+	struct iovec iov;
+
+	memset(&dreg_state, 0, sizeof(dreg_state));
+	dreg_state.dbg_regs[0].addr = (uintptr_t)(addr - offset);
+	dreg_state.dbg_regs[0].ctrl = control;
+	iov.iov_base = &dreg_state;
+	iov.iov_len = offsetof(struct user_hwdebug_state, dbg_regs) +
+				sizeof(dreg_state.dbg_regs[0]);
+	if (ptrace(PTRACE_SETREGSET, pid, NT_ARM_HW_WATCH, &iov) == 0)
+		return true;
+
+	if (errno == EIO)
+		ksft_print_msg(
+			"ptrace(PTRACE_SETREGSET, NT_ARM_HW_WATCH) not supported on this hardware: %s\n",
+			strerror(errno));
+
+	ksft_print_msg(
+		"ptrace(PTRACE_SETREGSET, NT_ARM_HW_WATCH) failed: %s\n",
+		strerror(errno));
+	return false;
+}
+
+static bool run_test(int wr_size, int wp_size, int wr, int wp)
+{
+	int status;
+	siginfo_t siginfo;
+	pid_t pid = fork();
+	pid_t wpid;
+
+	if (pid < 0) {
+		ksft_test_result_fail(
+			"fork() failed: %s\n", strerror(errno));
+		return false;
+	}
+	if (pid == 0)
+		child(wr_size, wr);
+
+	wpid = waitpid(pid, &status, __WALL);
+	if (wpid != pid) {
+		ksft_print_msg(
+			"waitpid() failed: %s\n", strerror(errno));
+		return false;
+	}
+	if (!WIFSTOPPED(status)) {
+		ksft_print_msg(
+			"child did not stop: %s\n", strerror(errno));
+		return false;
+	}
+	if (WSTOPSIG(status) != SIGSTOP) {
+		ksft_print_msg("child did not stop with SIGSTOP\n");
+		return false;
+	}
+
+	if (!set_watchpoint(pid, wp_size, wp))
+		return false;
+
+	if (ptrace(PTRACE_CONT, pid, NULL, NULL) < 0) {
+		ksft_print_msg(
+			"ptrace(PTRACE_CONT) failed: %s\n",
+			strerror(errno));
+		return false;
+	}
+
+	alarm(3);
+	wpid = waitpid(pid, &status, __WALL);
+	if (wpid != pid) {
+		ksft_print_msg(
+			"waitpid() failed: %s\n", strerror(errno));
+		return false;
+	}
+	alarm(0);
+	if (WIFEXITED(status)) {
+		ksft_print_msg("child exited prematurely\n");
+		return false;
+	}
+	if (!WIFSTOPPED(status)) {
+		ksft_print_msg("child did not stop\n");
+		return false;
+	}
+	if (WSTOPSIG(status) != SIGTRAP) {
+		ksft_print_msg("child did not stop with SIGTRAP\n");
+		return false;
+	}
+	if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &siginfo) != 0) {
+		ksft_print_msg(
+			"ptrace(PTRACE_GETSIGINFO): %s\n",
+			strerror(errno));
+		return false;
+	}
+	if (siginfo.si_code != TRAP_HWBKPT) {
+		ksft_print_msg(
+			"Unexpected si_code %d\n", siginfo.si_code);
+		return false;
+	}
+
+	kill(pid, SIGKILL);
+	wpid = waitpid(pid, &status, 0);
+	if (wpid != pid) {
+		ksft_print_msg(
+			"waitpid() failed: %s\n", strerror(errno));
+		return false;
+	}
+	return true;
+}
+
+static void sigalrm(int sig)
+{
+}
+
+int main(int argc, char **argv)
+{
+	int opt;
+	bool succeeded = true;
+	struct sigaction act;
+	int wr, wp, size;
+	bool result;
+
+	ksft_print_header();
+	ksft_set_plan(213);
+
+	act.sa_handler = sigalrm;
+	sigemptyset(&act.sa_mask);
+	act.sa_flags = 0;
+	sigaction(SIGALRM, &act, NULL);
+	for (size = 1; size <= 32; size = size*2) {
+		for (wr = 0; wr <= 32; wr = wr + size) {
+			for (wp = wr - size; wp <= wr + size; wp = wp + size) {
+				result = run_test(size, MIN(size, 8), wr, wp);
+				if ((result && wr == wp) ||
+				    (!result && wr != wp))
+					ksft_test_result_pass(
+						"Test size = %d write offset = %d watchpoint offset = %d\n",
+						size, wr, wp);
+				else {
+					ksft_test_result_fail(
+						"Test size = %d write offset = %d watchpoint offset = %d\n",
+						size, wr, wp);
+					succeeded = false;
+				}
+			}
+		}
+	}
+
+	for (size = 1; size <= 32; size = size*2) {
+		if (run_test(size, 8, -size, -8))
+			ksft_test_result_pass(
+				"Test size = %d write offset = %d watchpoint offset = -8\n",
+				size, -size);
+		else {
+			ksft_test_result_fail(
+				"Test size = %d write offset = %d watchpoint offset = -8\n",
+				size, -size);
+			succeeded = false;
+		}
+	}
+
+	if (succeeded)
+		ksft_exit_pass();
+	else
+		ksft_exit_fail();
+}
diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
new file mode 100644
index 000000000..ca2aaab9e
--- /dev/null
+++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2016 Google, Inc.
+ */
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/ptrace.h>
+#include <sys/stat.h>
+#include <sys/timerfd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+#include "kselftest.h"
+
+void child(int cpu)
+{
+	cpu_set_t set;
+
+	CPU_ZERO(&set);
+	CPU_SET(cpu, &set);
+	if (sched_setaffinity(0, sizeof(set), &set) != 0) {
+		ksft_print_msg("sched_setaffinity() failed: %s\n",
+			strerror(errno));
+		_exit(1);
+	}
+
+	if (ptrace(PTRACE_TRACEME, 0, NULL, NULL) != 0) {
+		ksft_print_msg("ptrace(PTRACE_TRACEME) failed: %s\n",
+			strerror(errno));
+		_exit(1);
+	}
+
+	if (raise(SIGSTOP) != 0) {
+		ksft_print_msg("raise(SIGSTOP) failed: %s\n", strerror(errno));
+		_exit(1);
+	}
+
+	_exit(0);
+}
+
+int run_test(int cpu)
+{
+	int status;
+	pid_t pid = fork();
+	pid_t wpid;
+
+	if (pid < 0) {
+		ksft_print_msg("fork() failed: %s\n", strerror(errno));
+		return KSFT_FAIL;
+	}
+	if (pid == 0)
+		child(cpu);
+
+	wpid = waitpid(pid, &status, __WALL);
+	if (wpid != pid) {
+		ksft_print_msg("waitpid() failed: %s\n", strerror(errno));
+		return KSFT_FAIL;
+	}
+	if (!WIFSTOPPED(status)) {
+		ksft_print_msg("child did not stop: %s\n", strerror(errno));
+		return KSFT_FAIL;
+	}
+	if (WSTOPSIG(status) != SIGSTOP) {
+		ksft_print_msg("child did not stop with SIGSTOP: %s\n",
+			strerror(errno));
+		return KSFT_FAIL;
+	}
+
+	if (ptrace(PTRACE_SINGLESTEP, pid, NULL, NULL) < 0) {
+		if (errno == EIO) {
+			ksft_print_msg(
+				"ptrace(PTRACE_SINGLESTEP) not supported on this architecture: %s\n",
+				strerror(errno));
+			return KSFT_SKIP;
+		}
+		ksft_print_msg("ptrace(PTRACE_SINGLESTEP) failed: %s\n",
+			strerror(errno));
+		return KSFT_FAIL;
+	}
+
+	wpid = waitpid(pid, &status, __WALL);
+	if (wpid != pid) {
+		ksft_print_msg("waitpid() failed: %s\n", strerror(errno));
+		return KSFT_FAIL;
+	}
+	if (WIFEXITED(status)) {
+		ksft_print_msg("child did not single-step: %s\n",
+			strerror(errno));
+		return KSFT_FAIL;
+	}
+	if (!WIFSTOPPED(status)) {
+		ksft_print_msg("child did not stop: %s\n", strerror(errno));
+		return KSFT_FAIL;
+	}
+	if (WSTOPSIG(status) != SIGTRAP) {
+		ksft_print_msg("child did not stop with SIGTRAP: %s\n",
+			strerror(errno));
+		return KSFT_FAIL;
+	}
+
+	if (ptrace(PTRACE_CONT, pid, NULL, NULL) < 0) {
+		ksft_print_msg("ptrace(PTRACE_CONT) failed: %s\n",
+			strerror(errno));
+		return KSFT_FAIL;
+	}
+
+	wpid = waitpid(pid, &status, __WALL);
+	if (wpid != pid) {
+		ksft_print_msg("waitpid() failed: %s\n", strerror(errno));
+		return KSFT_FAIL;
+	}
+	if (!WIFEXITED(status)) {
+		ksft_print_msg("child did not exit after PTRACE_CONT: %s\n",
+			strerror(errno));
+		return KSFT_FAIL;
+	}
+
+	return KSFT_PASS;
+}
+
+/*
+ * Reads the suspend success count from sysfs.
+ * Returns the count on success or exits on failure.
+ */
+static int get_suspend_success_count_or_fail(void)
+{
+	FILE *fp;
+	int val;
+
+	fp = fopen("/sys/power/suspend_stats/success", "r");
+	if (!fp)
+		ksft_exit_fail_msg(
+			"Failed to open suspend_stats/success: %s\n",
+			strerror(errno));
+
+	if (fscanf(fp, "%d", &val) != 1) {
+		fclose(fp);
+		ksft_exit_fail_msg(
+			"Failed to read suspend success count\n");
+	}
+
+	fclose(fp);
+	return val;
+}
+
+void suspend(void)
+{
+	int timerfd;
+	int err;
+	int count_before;
+	int count_after;
+	struct itimerspec spec = {};
+
+	if (getuid() != 0)
+		ksft_exit_skip("Please run the test as root - Exiting.\n");
+
+	timerfd = timerfd_create(CLOCK_BOOTTIME_ALARM, 0);
+	if (timerfd < 0)
+		ksft_exit_fail_msg("timerfd_create() failed\n");
+
+	spec.it_value.tv_sec = 5;
+	err = timerfd_settime(timerfd, 0, &spec, NULL);
+	if (err < 0)
+		ksft_exit_fail_msg("timerfd_settime() failed\n");
+
+	count_before = get_suspend_success_count_or_fail();
+
+	system("(echo mem > /sys/power/state) 2> /dev/null");
+
+	count_after = get_suspend_success_count_or_fail();
+	if (count_after <= count_before)
+		ksft_exit_fail_msg("Failed to enter Suspend state\n");
+
+	close(timerfd);
+}
+
+int main(int argc, char **argv)
+{
+	int opt;
+	bool do_suspend = true;
+	bool succeeded = true;
+	unsigned int tests = 0;
+	cpu_set_t available_cpus;
+	int err;
+	int cpu;
+
+	ksft_print_header();
+
+	while ((opt = getopt(argc, argv, "n")) != -1) {
+		switch (opt) {
+		case 'n':
+			do_suspend = false;
+			break;
+		default:
+			printf("Usage: %s [-n]\n", argv[0]);
+			printf("        -n: do not trigger a suspend/resume cycle before the test\n");
+			return -1;
+		}
+	}
+
+	err = sched_getaffinity(0, sizeof(available_cpus), &available_cpus);
+	if (err < 0)
+		ksft_exit_fail_msg("sched_getaffinity() failed\n");
+
+	for (cpu = 0; cpu < CPU_SETSIZE; cpu++) {
+		if (!CPU_ISSET(cpu, &available_cpus))
+			continue;
+		tests++;
+	}
+
+	if (do_suspend)
+		suspend();
+
+	ksft_set_plan(tests);
+	for (cpu = 0; cpu < CPU_SETSIZE; cpu++) {
+		int test_success;
+
+		if (!CPU_ISSET(cpu, &available_cpus))
+			continue;
+
+		test_success = run_test(cpu);
+		switch (test_success) {
+		case KSFT_PASS:
+			ksft_test_result_pass("CPU %d\n", cpu);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("CPU %d\n", cpu);
+			break;
+		case KSFT_FAIL:
+			ksft_test_result_fail("CPU %d\n", cpu);
+			succeeded = false;
+			break;
+		}
+	}
+
+	if (succeeded)
+		ksft_exit_pass();
+	else
+		ksft_exit_fail();
+}