[PATCH v2 0/4] kselftest/arm64: Floating point stress test harness

[PATCH v2 0/4] kselftest/arm64: Floating point stress test harness

[Mark Brown]

This series has a few small enhancements for the existing standalone
floating point stress tests and then builds on those with a kselftest
integrated program which gives those a very quick spin from within
kselftest, as well as having an option to set a custom timeout to allow
for use with longer soak testing. This makes it much easier to get
thorough testing of the floating point state management logic, rather
than requiring custom setup for coverage of the various vector lengths
in the system as is needed at present.

It might be nice in future to extend this to attach to some or all of
the test programs with ptrace and read/write their registers as another
means of potentially triggering race conditions or corruption but that's
definitely another step.

v2:
 - Rebase onto v6.0-rc3.
 - Announce the results of enumeration before we start everything.

Mark Brown (4):
  kselftest/arm64: Always encourage preemption for za-test
  kselftest/arm64: Count SIGUSR2 deliveries in FP stress tests
  kselftest/arm64: Install signal handlers before output in FP stress
    tests
  kselftest/arm64: kselftest harness for FP stress tests

 tools/testing/selftests/arm64/fp/.gitignore   |   1 +
 tools/testing/selftests/arm64/fp/Makefile     |   5 +-
 .../testing/selftests/arm64/fp/asm-offsets.h  |   1 +
 tools/testing/selftests/arm64/fp/fp-stress.c  | 535 ++++++++++++++++++
 .../testing/selftests/arm64/fp/fpsimd-test.S  |  51 +-
 tools/testing/selftests/arm64/fp/sve-test.S   |  51 +-
 tools/testing/selftests/arm64/fp/za-test.S    |  58 +-
 7 files changed, 641 insertions(+), 61 deletions(-)
 create mode 100644 tools/testing/selftests/arm64/fp/fp-stress.c


base-commit: b90cb1053190353cc30f0fef0ef1f378ccc063c5
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v2 1/4] kselftest/arm64: Always encourage preemption for za-test

[Mark Brown]

Since we now have an explicit test for the syscall ABI there is no need for
za-test to cover getpid() so just unconditionally do sched_yield() like we
do in fpsimd-test.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 tools/testing/selftests/arm64/fp/za-test.S | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S
index 9ab6f9cd9623..2dd358f9edf2 100644
--- a/tools/testing/selftests/arm64/fp/za-test.S
+++ b/tools/testing/selftests/arm64/fp/za-test.S
@@ -287,12 +287,7 @@ _start:
 	subs	x21, x21, #1
 	b.ne	0b
 
-	and	x8, x22, #127		// Every 128 interations...
-	cbz	x8, 0f
-	mov	x8, #__NR_getpid	// (otherwise minimal syscall)
-	b	1f
-0:
-	mov	x8, #__NR_sched_yield	// ...encourage preemption
+	mov	x8, #__NR_sched_yield	// encourage preemption
 1:
 	svc	#0
 
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v2 2/4] kselftest/arm64: Count SIGUSR2 deliveries in FP stress tests

[Mark Brown]

Currently the floating point stress tests mostly support testing that the
data they are checking can be disrupted from a signal handler triggered by
SIGUSR1. This is not properly implemented for all the tests and in testing
is frequently modified to just handle the signal without corrupting data in
order to ensure that signal handling does not corrupt data. Directly support
this usage by installing a SIGUSR2 handler which simply counts the signal
delivery.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 tools/testing/selftests/arm64/fp/asm-offsets.h |  1 +
 tools/testing/selftests/arm64/fp/fpsimd-test.S | 15 +++++++++++++++
 tools/testing/selftests/arm64/fp/sve-test.S    | 15 +++++++++++++++
 tools/testing/selftests/arm64/fp/za-test.S     | 15 +++++++++++++++
 4 files changed, 46 insertions(+)

diff --git a/tools/testing/selftests/arm64/fp/asm-offsets.h b/tools/testing/selftests/arm64/fp/asm-offsets.h
index a180851496ec..757b2fd75dd7 100644
--- a/tools/testing/selftests/arm64/fp/asm-offsets.h
+++ b/tools/testing/selftests/arm64/fp/asm-offsets.h
@@ -3,6 +3,7 @@
 #define sa_handler 0
 #define sa_mask_sz 8
 #define SIGUSR1 10
+#define SIGUSR2 12
 #define SIGTERM 15
 #define SIGINT 2
 #define SIGABRT 6
diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S
index e21e8ea52c7e..f0f92192351a 100644
--- a/tools/testing/selftests/arm64/fp/fpsimd-test.S
+++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S
@@ -151,6 +151,15 @@ function irritator_handler
 	ret
 endfunction
 
+function tickle_handler
+	// Increment the signal count (x23):
+	ldr	x0, [x2, #ucontext_regs + 8 * 23]
+	add	x0, x0, #1
+	str	x0, [x2, #ucontext_regs + 8 * 23]
+
+	ret
+endfunction
+
 function terminate_handler
 	mov	w21, w0
 	mov	x20, x2
@@ -255,6 +264,12 @@ _start:
 	orr	w2, w2, #SA_NODEFER
 	bl	setsignal
 
+	mov	w0, #SIGUSR2
+	adr	x1, tickle_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
 	mov	x22, #0		// generation number, increments per iteration
 .Ltest_loop:
 
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index 589264231a2d..79c56e6c5b23 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -314,6 +314,15 @@ function irritator_handler
 	ret
 endfunction
 
+function tickle_handler
+	// Increment the signal count (x23):
+	ldr	x0, [x2, #ucontext_regs + 8 * 23]
+	add	x0, x0, #1
+	str	x0, [x2, #ucontext_regs + 8 * 23]
+
+	ret
+endfunction
+
 function terminate_handler
 	mov	w21, w0
 	mov	x20, x2
@@ -423,6 +432,12 @@ _start:
 	orr	w2, w2, #SA_NODEFER
 	bl	setsignal
 
+	mov	w0, #SIGUSR2
+	adr	x1, tickle_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
 #ifdef SSVE
 	smstart_sm		// syscalls will have exited streaming mode
 #endif
diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S
index 2dd358f9edf2..901839107205 100644
--- a/tools/testing/selftests/arm64/fp/za-test.S
+++ b/tools/testing/selftests/arm64/fp/za-test.S
@@ -167,6 +167,15 @@ function irritator_handler
 	ret
 endfunction
 
+function tickle_handler
+	// Increment the signal count (x23):
+	ldr	x0, [x2, #ucontext_regs + 8 * 23]
+	add	x0, x0, #1
+	str	x0, [x2, #ucontext_regs + 8 * 23]
+
+	ret
+endfunction
+
 function terminate_handler
 	mov	w21, w0
 	mov	x20, x2
@@ -273,6 +282,12 @@ _start:
 	orr	w2, w2, #SA_NODEFER
 	bl	setsignal
 
+	mov	w0, #SIGUSR2
+	adr	x1, tickle_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
 	mov	x22, #0		// generation number, increments per iteration
 .Ltest_loop:
 	rdsvl	0, 8
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v2 3/4] kselftest/arm64: Install signal handlers before output in FP stress tests

[Mark Brown]

To interface more robustly with other processes install the signal handers
in the floating point stress tests before we produce any output, this
means that a parent process can know that if it has seen any output from
the test then the test is ready to handle incoming signals.
---
 .../testing/selftests/arm64/fp/fpsimd-test.S  | 48 +++++++++----------
 tools/testing/selftests/arm64/fp/sve-test.S   | 48 +++++++++----------
 tools/testing/selftests/arm64/fp/za-test.S    | 48 +++++++++----------
 3 files changed, 72 insertions(+), 72 deletions(-)

diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S
index f0f92192351a..918d04885a33 100644
--- a/tools/testing/selftests/arm64/fp/fpsimd-test.S
+++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S
@@ -216,6 +216,30 @@ endfunction
 .globl _start
 function _start
 _start:
+	mov	x23, #0		// signal count
+
+	mov	w0, #SIGINT
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGTERM
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGUSR1
+	adr	x1, irritator_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	mov	w0, #SIGUSR2
+	adr	x1, tickle_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
 	// Sanity-check and report the vector length
 
 	mov	x19, #128
@@ -246,30 +270,6 @@ _start:
 	mov	x0, x20
 	bl	putdecn
 
-	mov	x23, #0		// Irritation signal count
-
-	mov	w0, #SIGINT
-	adr	x1, terminate_handler
-	mov	w2, #SA_SIGINFO
-	bl	setsignal
-
-	mov	w0, #SIGTERM
-	adr	x1, terminate_handler
-	mov	w2, #SA_SIGINFO
-	bl	setsignal
-
-	mov	w0, #SIGUSR1
-	adr	x1, irritator_handler
-	mov	w2, #SA_SIGINFO
-	orr	w2, w2, #SA_NODEFER
-	bl	setsignal
-
-	mov	w0, #SIGUSR2
-	adr	x1, tickle_handler
-	mov	w2, #SA_SIGINFO
-	orr	w2, w2, #SA_NODEFER
-	bl	setsignal
-
 	mov	x22, #0		// generation number, increments per iteration
 .Ltest_loop:
 
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index 79c56e6c5b23..2a18cb4c528c 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -379,6 +379,30 @@ endfunction
 .globl _start
 function _start
 _start:
+	mov	x23, #0		// Irritation signal count
+
+	mov	w0, #SIGINT
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGTERM
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGUSR1
+	adr	x1, irritator_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	mov	w0, #SIGUSR2
+	adr	x1, tickle_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
 #ifdef SSVE
 	puts	"Streaming mode "
 	smstart_sm
@@ -414,30 +438,6 @@ _start:
 	mov	x0, x20
 	bl	putdecn
 
-	mov	x23, #0		// Irritation signal count
-
-	mov	w0, #SIGINT
-	adr	x1, terminate_handler
-	mov	w2, #SA_SIGINFO
-	bl	setsignal
-
-	mov	w0, #SIGTERM
-	adr	x1, terminate_handler
-	mov	w2, #SA_SIGINFO
-	bl	setsignal
-
-	mov	w0, #SIGUSR1
-	adr	x1, irritator_handler
-	mov	w2, #SA_SIGINFO
-	orr	w2, w2, #SA_NODEFER
-	bl	setsignal
-
-	mov	w0, #SIGUSR2
-	adr	x1, tickle_handler
-	mov	w2, #SA_SIGINFO
-	orr	w2, w2, #SA_NODEFER
-	bl	setsignal
-
 #ifdef SSVE
 	smstart_sm		// syscalls will have exited streaming mode
 #endif
diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S
index 901839107205..53c54af65704 100644
--- a/tools/testing/selftests/arm64/fp/za-test.S
+++ b/tools/testing/selftests/arm64/fp/za-test.S
@@ -232,6 +232,30 @@ endfunction
 .globl _start
 function _start
 _start:
+	mov	x23, #0		// signal count
+
+	mov	w0, #SIGINT
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGTERM
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGUSR1
+	adr	x1, irritator_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	mov	w0, #SIGUSR2
+	adr	x1, tickle_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
 	puts	"Streaming mode "
 	smstart_za
 
@@ -264,30 +288,6 @@ _start:
 	mov	x0, x20
 	bl	putdecn
 
-	mov	x23, #0		// Irritation signal count
-
-	mov	w0, #SIGINT
-	adr	x1, terminate_handler
-	mov	w2, #SA_SIGINFO
-	bl	setsignal
-
-	mov	w0, #SIGTERM
-	adr	x1, terminate_handler
-	mov	w2, #SA_SIGINFO
-	bl	setsignal
-
-	mov	w0, #SIGUSR1
-	adr	x1, irritator_handler
-	mov	w2, #SA_SIGINFO
-	orr	w2, w2, #SA_NODEFER
-	bl	setsignal
-
-	mov	w0, #SIGUSR2
-	adr	x1, tickle_handler
-	mov	w2, #SA_SIGINFO
-	orr	w2, w2, #SA_NODEFER
-	bl	setsignal
-
 	mov	x22, #0		// generation number, increments per iteration
 .Ltest_loop:
 	rdsvl	0, 8
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v2 4/4] kselftest/arm64: kselftest harness for FP stress tests

[Mark Brown]

Currently the stress test programs for floating point context switching are
run by hand, there are extremely simplistic harnesses which run some copies
of each test individually but they are not integrated into kselftest and
with SVE and SME they only run with whatever vector length the process has
by default. This is hassle when running the tests and means that they're
not being run at all by CI systems picking up kselftest.

In order to improve our coverage and provide a more convenient interface
provide a harness program which starts enough stress test programs up to
cause context switching and runs them for a set period. If only FPSIMD is
available in the system we start two copies of the FPSIMD stress test per
CPU, otherwise we start one copy of the FPSIMD and then start the SVE,
streaming SVE and ZA tests once per CPU for each available VL they have
to run on.  We then run for a set period monitoring for any errors
reported by the test programs before cleanly terminating them.

In order to provide additional coverage of signal handling and some extra
noise in the scheduling we send a SIGUSR2 to the stress tests once a
second, the tests will count the number of signals they get.

Since kselftest is generally expected to run quickly we by default only run
for ten seconds. This is enough to show if there is anything cripplingly
wrong but not exactly a thorough soak test, for interactive and more
focused use a command line option -t N is provided which overrides the
length of time to run for (specified in seconds) and if 0 is specified then
there is no timeout and the test must be manually terminated. The timeout
is counted in seconds with no output, this is done to account for the
potentially slow startup time for the test programs on virtual platforms
which tend to struggle during startup as they are both slow and tend to
support a wide range of vector lengths.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 tools/testing/selftests/arm64/fp/.gitignore  |   1 +
 tools/testing/selftests/arm64/fp/Makefile    |   5 +-
 tools/testing/selftests/arm64/fp/fp-stress.c | 535 +++++++++++++++++++
 3 files changed, 540 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/arm64/fp/fp-stress.c

diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore
index ea947af63882..df79d29664a1 100644
--- a/tools/testing/selftests/arm64/fp/.gitignore
+++ b/tools/testing/selftests/arm64/fp/.gitignore
@@ -1,4 +1,5 @@
 fp-pidbench
+fp-stress
 fpsimd-test
 rdvl-sme
 rdvl-sve
diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile
index a7c2286bf65b..36db61358ed5 100644
--- a/tools/testing/selftests/arm64/fp/Makefile
+++ b/tools/testing/selftests/arm64/fp/Makefile
@@ -5,7 +5,10 @@ top_srcdir = $(realpath ../../../../../)
 
 CFLAGS += -I$(top_srcdir)/usr/include/
 
-TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg za-fork za-ptrace
+TEST_GEN_PROGS := fp-stress \
+	sve-ptrace sve-probe-vls \
+	vec-syscfg \
+	za-fork za-ptrace
 TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \
 	rdvl-sme rdvl-sve \
 	sve-test \
diff --git a/tools/testing/selftests/arm64/fp/fp-stress.c b/tools/testing/selftests/arm64/fp/fp-stress.c
new file mode 100644
index 000000000000..01cef1962ab5
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/fp-stress.c
@@ -0,0 +1,535 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 ARM Limited.
+ */
+
+#define _GNU_SOURCE
+#define _POSIX_C_SOURCE 199309L
+
+#include <errno.h>
+#include <getopt.h>
+#include <poll.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/auxv.h>
+#include <sys/epoll.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <sys/wait.h>
+#include <asm/hwcap.h>
+
+#include "../../kselftest.h"
+
+#define MAX_VLS 16
+
+struct child_data {
+	char *name, *output;
+	pid_t pid;
+	int stdout;
+	bool output_seen;
+	bool exited;
+	int exit_status;
+};
+
+static int epoll_fd;
+static struct child_data *children;
+static int num_children;
+static bool terminate;
+
+static void drain_output(bool flush);
+
+static int num_processors(void)
+{
+	long nproc = sysconf(_SC_NPROCESSORS_CONF);
+	if (nproc < 0) {
+		perror("Unable to read number of processors\n");
+		exit(EXIT_FAILURE);
+	}
+
+	return nproc;
+}
+
+static void child_start(struct child_data *child, const char *program)
+{
+	int ret, pipefd[2], i;
+	struct epoll_event ev;
+
+	ret = pipe(pipefd);
+	if (ret != 0)
+		ksft_exit_fail_msg("Failed to create stdout pipe: %s (%d)\n",
+				   strerror(errno), errno);
+
+	child->pid = fork();
+	if (child->pid == -1)
+		ksft_exit_fail_msg("fork() failed: %s (%d)\n",
+				   strerror(errno), errno);
+
+	if (!child->pid) {
+		/*
+		 * In child, replace stdout with the pipe, errors to
+		 * stderr from here as kselftest prints to stdout.
+		 */
+		ret = dup2(pipefd[1], 1);
+		if (ret == -1) {
+			fprintf(stderr, "dup2() %d\n", errno);
+			exit(EXIT_FAILURE);
+		}
+
+		/*
+		 * Very dumb mechanism to clean open FDs other than
+		 * stdio. We don't want O_CLOEXEC for the pipes...
+		 */
+		for (i = 3; i < 8192; i++)
+			close(i);
+
+		ret = execl(program, program, NULL);
+		fprintf(stderr, "execl(%s) failed: %d (%s)\n",
+			program, errno, strerror(errno));
+
+		exit(EXIT_FAILURE);
+	} else {
+		/*
+		 * In parent, remember the child and close our copy of the
+		 * write side of stdout.
+		 */
+		close(pipefd[1]);
+		child->stdout = pipefd[0];
+		child->output = NULL;
+		child->exited = false;
+		child->output_seen = false;
+
+		ev.events = EPOLLIN | EPOLLHUP;
+		ev.data.ptr = child;
+
+		ret = epoll_ctl(epoll_fd, EPOLL_CTL_ADD, child->stdout, &ev);
+		if (ret < 0) {
+			ksft_exit_fail_msg("%s EPOLL_CTL_ADD failed: %s (%d)\n",
+					   child->name, strerror(errno), errno);
+		}
+
+		/*
+		 * Keep output flowing during child startup so logs
+		 * are more timely, can help debugging.
+		 */
+		drain_output(false);
+	}
+}
+
+static void child_output(struct child_data *child, uint32_t events,
+			 bool flush)
+{
+	char read_data[1024];
+	char work[1024];
+	int ret, len, cur_work, cur_read;
+
+	if (events & EPOLLIN) {
+		ret = read(child->stdout, read_data, sizeof(read_data));
+		if (ret < 0) {
+			ksft_print_msg("%s: read() failed: %s (%d)\n",
+				       child->name, strerror(errno), errno);
+			return;
+		}
+		len = ret;
+
+		child->output_seen = true;
+
+		/* Pick up any partial read */
+		if (child->output) {
+			strncpy(work, child->output, sizeof(work) - 1);
+			cur_work = strnlen(work, sizeof(work));
+			free(child->output);
+			child->output = NULL;
+		} else {
+			cur_work = 0;
+		}
+
+		cur_read = 0;
+		while (cur_read < len) {
+			work[cur_work] = read_data[cur_read++];
+
+			if (work[cur_work] == '\n') {
+				work[cur_work] = '\0';
+				ksft_print_msg("%s: %s\n", child->name, work);
+				cur_work = 0;
+			} else {
+				cur_work++;
+			}
+		}
+
+		if (cur_work) {
+			work[cur_work] = '\0';
+			ret = asprintf(&child->output, "%s", work);
+			if (ret == -1)
+				ksft_exit_fail_msg("Out of memory\n");
+		}
+	}
+
+	if (events & EPOLLHUP) {
+		close(child->stdout);
+		child->stdout = -1;
+		flush = true;
+	}
+
+	if (flush && child->output) {
+		ksft_print_msg("%s: %s<EOF>\n", child->name, child->output);
+		free(child->output);
+		child->output = NULL;
+	}
+}
+
+static void child_tickle(struct child_data *child)
+{
+	if (child->output_seen && !child->exited)
+		kill(child->pid, SIGUSR2);
+}
+
+static void child_stop(struct child_data *child)
+{
+	if (!child->exited)
+		kill(child->pid, SIGTERM);
+}
+
+static void child_cleanup(struct child_data *child)
+{
+	pid_t ret;
+	int status;
+	bool fail = false;
+
+	if (!child->exited) {
+		do {
+			ret = waitpid(child->pid, &status, 0);
+			if (ret == -1 && errno == EINTR)
+				continue;
+
+			if (ret == -1) {
+				ksft_print_msg("waitpid(%d) failed: %s (%d)\n",
+					       child->pid, strerror(errno),
+					       errno);
+				fail = true;
+				break;
+			}
+		} while (!WIFEXITED(status));
+		child->exit_status = WEXITSTATUS(status);
+	}
+
+	if (!child->output_seen) {
+		ksft_print_msg("%s no output seen\n", child->name);
+		fail = true;
+	}
+
+	if (child->exit_status != 0) {
+		ksft_print_msg("%s exited with error code %d\n",
+			       child->name, child->exit_status);
+		fail = true;
+	}
+
+	ksft_test_result(!fail, "%s\n", child->name);
+}
+
+static void handle_child_signal(int sig, siginfo_t *info, void *context)
+{
+	int i;
+	bool found = false;
+
+	for (i = 0; i < num_children; i++) {
+		if (children[i].pid == info->si_pid) {
+			children[i].exited = true;
+			children[i].exit_status = info->si_status;
+			found = true;
+			break;
+		}
+	}
+
+	if (!found)
+		ksft_print_msg("SIGCHILD for unknown PID %d with status %d\n",
+			       info->si_pid, info->si_status);
+}
+
+static void handle_exit_signal(int sig, siginfo_t *info, void *context)
+{
+	int i;
+
+	ksft_print_msg("Got signal, exiting...\n");
+
+	terminate = true;
+
+	/*
+	 * This should be redundant, the main loop should clean up
+	 * after us, but for safety stop everything we can here.
+	 */
+	for (i = 0; i < num_children; i++)
+		child_stop(&children[i]);
+}
+
+static void start_fpsimd(struct child_data *child, int cpu, int copy)
+{
+	int ret;
+
+	child_start(child, "./fpsimd-test");
+
+	ret = asprintf(&child->name, "FPSIMD-%d-%d", cpu, copy);
+	if (ret == -1)
+		ksft_exit_fail_msg("asprintf() failed\n");
+
+	ksft_print_msg("Started %s\n", child->name);
+}
+
+static void start_sve(struct child_data *child, int vl, int cpu)
+{
+	int ret;
+
+	ret = prctl(PR_SVE_SET_VL, vl | PR_SVE_VL_INHERIT);
+	if (ret < 0)
+		ksft_exit_fail_msg("Failed to set SVE VL %d\n", vl);
+
+	child_start(child, "./sve-test");
+
+	ret = asprintf(&child->name, "SVE-VL-%d-%d", vl, cpu);
+	if (ret == -1)
+		ksft_exit_fail_msg("asprintf() failed\n");
+
+	ksft_print_msg("Started %s\n", child->name);
+}
+
+static void start_ssve(struct child_data *child, int vl, int cpu)
+{
+	int ret;
+
+	ret = prctl(PR_SME_SET_VL, vl | PR_SME_VL_INHERIT);
+	if (ret < 0)
+		ksft_exit_fail_msg("Failed to set SME VL %d\n", ret);
+
+	child_start(child, "./ssve-test");
+
+	ret = asprintf(&child->name, "SSVE-VL-%d-%d", vl, cpu);
+	if (ret == -1)
+		ksft_exit_fail_msg("asprintf() failed\n");
+
+	ksft_print_msg("Started %s\n", child->name);
+}
+
+static void start_za(struct child_data *child, int vl, int cpu)
+{
+	int ret;
+
+	ret = prctl(PR_SME_SET_VL, vl | PR_SVE_VL_INHERIT);
+	if (ret < 0)
+		ksft_exit_fail_msg("Failed to set SME VL %d\n", ret);
+
+	child_start(child, "./za-test");
+
+	ret = asprintf(&child->name, "ZA-VL-%d-%d", vl, cpu);
+	if (ret == -1)
+		ksft_exit_fail_msg("asprintf() failed\n");
+
+	ksft_print_msg("Started %s\n", child->name);
+}
+
+static void probe_vls(int vls[], int *vl_count, int set_vl)
+{
+	unsigned int vq;
+	int vl;
+
+	*vl_count = 0;
+
+	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+		vl = prctl(set_vl, vq * 16);
+		if (vl == -1)
+			ksft_exit_fail_msg("SET_VL failed: %s (%d)\n",
+					   strerror(errno), errno);
+
+		vl &= PR_SVE_VL_LEN_MASK;
+
+		vq = sve_vq_from_vl(vl);
+
+		vls[*vl_count] = vl;
+		*vl_count += 1;
+	}
+}
+
+/* Handle any pending output without blocking */
+static void drain_output(bool flush)
+{
+	struct epoll_event ev;
+	int ret = 1;
+
+	while (ret > 0) {
+		ret = epoll_wait(epoll_fd, &ev, 1, 0);
+		if (ret < 0) {
+			if (errno == EINTR)
+				continue;
+			ksft_print_msg("epoll_wait() failed: %s (%d)\n",
+				       strerror(errno), errno);
+		}
+
+		if (ret == 1)
+			child_output(ev.data.ptr, ev.events, flush);
+	}
+}
+
+static const struct option options[] = {
+	{ "timeout",	required_argument, NULL, 't' },
+	{ }
+};
+
+int main(int argc, char **argv)
+{
+	int ret;
+	int timeout = 10;
+	int cpus, tests, i, j, c;
+	int sve_vl_count, sme_vl_count, fpsimd_per_cpu;
+	int sve_vls[MAX_VLS], sme_vls[MAX_VLS];
+	struct epoll_event ev;
+	struct sigaction sa;
+
+	while ((c = getopt_long(argc, argv, "t:", options, NULL)) != -1) {
+		switch (c) {
+		case 't':
+			ret = sscanf(optarg, "%d", &timeout);
+			if (ret != 1)
+				ksft_exit_fail_msg("Failed to parse timeout %s\n",
+						   optarg);
+			break;
+		default:
+			ksft_exit_fail_msg("Unknown argument\n");
+		}
+	}
+
+	cpus = num_processors();
+	tests = 0;
+
+	if (getauxval(AT_HWCAP) & HWCAP_SVE) {
+		probe_vls(sve_vls, &sve_vl_count, PR_SVE_SET_VL);
+		tests += sve_vl_count * cpus;
+	} else {
+		sve_vl_count = 0;
+	}
+
+	if (getauxval(AT_HWCAP2) & HWCAP2_SME) {
+		probe_vls(sme_vls, &sme_vl_count, PR_SME_SET_VL);
+		tests += sme_vl_count * cpus * 2;
+	} else {
+		sme_vl_count = 0;
+	}
+
+	/* Force context switching if we only have FPSIMD */
+	if (!sve_vl_count && !sme_vl_count)
+		fpsimd_per_cpu = 2;
+	else
+		fpsimd_per_cpu = 1;
+	tests += cpus * fpsimd_per_cpu;
+
+	ksft_print_header();
+	ksft_set_plan(tests);
+
+	ksft_print_msg("%d CPUs, %d SVE VLs, %d SME VLs\n",
+		       cpus, sve_vl_count, sme_vl_count);
+
+	if (timeout > 0)
+		ksft_print_msg("Will run for %ds\n", timeout);
+	else
+		ksft_print_msg("Will run until terminated\n");
+
+	children = calloc(sizeof(*children), tests);
+	if (!children)
+		ksft_exit_fail_msg("Unable to allocate child data\n");
+
+	ret = epoll_create1(EPOLL_CLOEXEC);
+	if (ret < 0)
+		ksft_exit_fail_msg("epoll_create1() failed: %s (%d)\n",
+				   strerror(errno), ret);
+	epoll_fd = ret;
+
+	/* Get signal handers ready before we start any children */
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handle_exit_signal;
+	sa.sa_flags = SA_RESTART | SA_SIGINFO;
+	sigemptyset(&sa.sa_mask);
+	ret = sigaction(SIGINT, &sa, NULL);
+	if (ret < 0)
+		ksft_print_msg("Failed to install SIGINT handler: %s (%d)\n",
+			       strerror(errno), errno);
+	ret = sigaction(SIGTERM, &sa, NULL);
+	if (ret < 0)
+		ksft_print_msg("Failed to install SIGTEM handler: %s (%d)\n",
+			       strerror(errno), errno);
+	sa.sa_sigaction = handle_child_signal;
+	ret = sigaction(SIGCHLD, &sa, NULL);
+	if (ret < 0)
+		ksft_print_msg("Failed to install SIGCHLD handler: %s (%d)\n",
+			       strerror(errno), errno);
+
+	for (i = 0; i < cpus; i++) {
+		for (j = 0; j < fpsimd_per_cpu; j++)
+			start_fpsimd(&children[num_children++], i, j);
+
+		for (j = 0; j < sve_vl_count; j++)
+			start_sve(&children[num_children++], sve_vls[j], i);
+
+		for (j = 0; j < sme_vl_count; j++) {
+			start_ssve(&children[num_children++], sme_vls[j], i);
+			start_za(&children[num_children++], sme_vls[j], i);
+		}
+	}
+
+	for (;;) {
+		/* Did we get a signal asking us to exit? */
+		if (terminate)
+			break;
+
+		/*
+		 * Timeout is counted in seconds with no output, the
+		 * tests print during startup then are silent when
+		 * running so this should ensure they all ran enough
+		 * to install the signal handler, this is especially
+		 * useful in emulation where we will both be slow and
+		 * likely to have a large set of VLs.
+		 */
+		ret = epoll_wait(epoll_fd, &ev, 1, 1000);
+		if (ret < 0) {
+			if (errno == EINTR)
+				continue;
+			ksft_exit_fail_msg("epoll_wait() failed: %s (%d)\n",
+					   strerror(errno), errno);
+		}
+
+		/* Output? */
+		if (ret == 1) {
+			child_output(ev.data.ptr, ev.events, false);
+			continue;
+		}
+
+		/* Otherwise epoll_wait() timed out */
+
+		for (i = 0; i < num_children; i++)
+			child_tickle(&children[i]);
+
+		/* Negative timeout means run indefinitely */
+		if (timeout < 0)
+			continue;
+		if (--timeout == 0)
+			break;
+	}
+
+	ksft_print_msg("Finishing up...\n");
+
+	for (i = 0; i < tests; i++)
+		child_stop(&children[i]);
+
+	drain_output(false);
+
+	for (i = 0; i < tests; i++)
+		child_cleanup(&children[i]);
+
+	drain_output(true);
+
+	ksft_print_cnts();
+
+	return 0;
+}
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v2 0/4] kselftest/arm64: Floating point stress test harness

[Catalin Marinas]

On Mon, 29 Aug 2022 16:44:48 +0100, Mark Brown wrote:
> This series has a few small enhancements for the existing standalone
> floating point stress tests and then builds on those with a kselftest
> integrated program which gives those a very quick spin from within
> kselftest, as well as having an option to set a custom timeout to allow
> for use with longer soak testing. This makes it much easier to get
> thorough testing of the floating point state management logic, rather
> than requiring custom setup for coverage of the various vector lengths
> in the system as is needed at present.
> 
> [...]

Applied to arm64 (for-next/kselftest), thanks!

[1/4] kselftest/arm64: Always encourage preemption for za-test
      https://git.kernel.org/arm64/c/9e40e6272353
[2/4] kselftest/arm64: Count SIGUSR2 deliveries in FP stress tests
      https://git.kernel.org/arm64/c/05a5980f7ff5
[3/4] kselftest/arm64: Install signal handlers before output in FP stress tests
      https://git.kernel.org/arm64/c/000aef672bf2
[4/4] kselftest/arm64: kselftest harness for FP stress tests
      https://git.kernel.org/arm64/c/bce4950aa05c

-- 
Catalin


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel