perf test coresight: Add unroll thread test tool

Add test tool to be driven by further test scripts. This is a simple C
based test that is for arm64 with some inline ASM to manually unroll a
lot of code to have a very long sequence of commands.

Reviewed-by: James Clark <[e-mail]>
Signed-off-by: Carsten Haitzler <[e-mail]>
Cc: Leo Yan <[e-mail]>
Cc: Mathieu Poirier <[e-mail]>
Cc: Mike Leach <[e-mail]>
Cc: Suzuki Poulouse <[e-mail]>
Cc: [e-mail]
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/tests/shell/coresight/Makefile

···
 SUBDIRS = \
 	asm_pure_loop \
 	memcpy_thread \
-	thread_loop
+	thread_loop \
+	unroll_loop_thread
 
 all: $(SUBDIRS)
 $(SUBDIRS):

tools/perf/tests/shell/coresight/unroll_loop_thread/.gitignore

···
+unroll_loop_thread

tools/perf/tests/shell/coresight/unroll_loop_thread/Makefile

···
+# SPDX-License-Identifier: GPL-2.0
+# Carsten Haitzler <[e-mail]>, 2021
+include ../Makefile.miniconfig
+
+# Binary to produce
+BIN=unroll_loop_thread
+# Any linking/libraries needed for the binary - empty if none needed
+LIB=-pthread
+
+all: $(BIN)
+
+$(BIN): $(BIN).c
+ifdef CORESIGHT
+ifeq ($(ARCH),arm64)
+# Build line
+	$(Q)$(CC) $(BIN).c -o $(BIN) $(LIB)
+endif
+endif
+
+install-tests: all
+ifdef CORESIGHT
+ifeq ($(ARCH),arm64)
+# Install the test tool in the right place
+	$(call QUIET_INSTALL, tests) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$(INSTDIR_SUB)/$(BIN)'; \
+		$(INSTALL) $(BIN) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$(INSTDIR_SUB)/$(BIN)/$(BIN)'
+endif
+endif
+
+clean:
+	$(Q)$(RM) -f $(BIN)
+
+.PHONY: all clean install-tests

tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c

···
+// SPDX-License-Identifier: GPL-2.0
+// Carsten Haitzler <[e-mail]>, 2021
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <pthread.h>
+
+struct args {
+	pthread_t th;
+	unsigned int in;
+	void *ret;
+};
+
+static void *thrfn(void *arg)
+{
+	struct args *a = arg;
+	unsigned int i, in = a->in;
+
+	for (i = 0; i < 10000; i++) {
+		asm volatile (
+// force an unroll of thia add instruction so we can test long runs of code
+#define SNIP1 "add %[in], %[in], #1\n"
+// 10
+#define SNIP2 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1
+// 100
+#define SNIP3 SNIP2 SNIP2 SNIP2 SNIP2 SNIP2 SNIP2 SNIP2 SNIP2 SNIP2 SNIP2
+// 1000
+#define SNIP4 SNIP3 SNIP3 SNIP3 SNIP3 SNIP3 SNIP3 SNIP3 SNIP3 SNIP3 SNIP3
+// 10000
+#define SNIP5 SNIP4 SNIP4 SNIP4 SNIP4 SNIP4 SNIP4 SNIP4 SNIP4 SNIP4 SNIP4
+// 100000
+			SNIP5 SNIP5 SNIP5 SNIP5 SNIP5 SNIP5 SNIP5 SNIP5 SNIP5 SNIP5
+			: /* out */
+			: /* in */ [in] "r" (in)
+			: /* clobber */
+		);
+	}
+}
+
+static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
+{
+	pthread_t t;
+	pthread_attr_t attr;
+
+	pthread_attr_init(&attr);
+	pthread_create(&t, &attr, fn, arg);
+	return t;
+}
+
+int main(int argc, char **argv)
+{
+	unsigned int i, thr;
+	pthread_t threads[256];
+	struct args args[256];
+
+	if (argc < 2) {
+		printf("ERR: %s [numthreads]\n", argv[0]);
+		exit(1);
+	}
+
+	thr = atoi(argv[1]);
+	if ((thr > 256) || (thr < 1)) {
+		printf("ERR: threads 1-256\n");
+		exit(1);
+	}
+	for (i = 0; i < thr; i++) {
+		args[i].in = rand();
+		args[i].th = new_thr(thrfn, &(args[i]));
+	}
+	for (i = 0; i < thr; i++)
+		pthread_join(args[i].th, &(args[i].ret));
+	return 0;
+}