[PATCH V8 10/10] selftests, powerpc: Add test for BHRB branch filters (HW & SW)

[Anshuman Khandual <khandual@linux.vnet.ibm.com>]

From: "khandual@linux.vnet.ibm.com" <khandual@linux.vnet.ibm.com>

This patch adds a test for verifying that all the branch stack
sampling filters supported on powerpc works correctly. It also
adds some assembly helper functions in this regard. This patch
extends the generic event description to handle kernel mapped
ring buffers.

Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
---
 tools/testing/selftests/powerpc/pmu/Makefile       |  11 +-
 tools/testing/selftests/powerpc/pmu/bhrb/Makefile  |  13 +
 .../selftests/powerpc/pmu/bhrb/bhrb_filters.c      | 513 +++++++++++++++++++++
 .../selftests/powerpc/pmu/bhrb/bhrb_filters.h      |  16 +
 .../selftests/powerpc/pmu/bhrb/bhrb_filters_asm.S  | 260 +++++++++++
 tools/testing/selftests/powerpc/pmu/event.h        |   5 +
 6 files changed, 816 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/powerpc/pmu/bhrb/Makefile
 create mode 100644 tools/testing/selftests/powerpc/pmu/bhrb/bhrb_filters.c
 create mode 100644 tools/testing/selftests/powerpc/pmu/bhrb/bhrb_filters.h
 create mode 100644 tools/testing/selftests/powerpc/pmu/bhrb/bhrb_filters_asm.S

diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile
index a9099d9..2e103fd 100644
--- a/tools/testing/selftests/powerpc/pmu/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/Makefile
@@ -4,7 +4,7 @@ noarg:
 TEST_PROGS := count_instructions l3_bank_test per_event_excludes
 EXTRA_SOURCES := ../harness.c event.c lib.c
 
-all: $(TEST_PROGS) ebb
+all: $(TEST_PROGS) ebb bhrb
 
 $(TEST_PROGS): $(EXTRA_SOURCES)
 
@@ -18,25 +18,32 @@ DEFAULT_RUN_TESTS := $(RUN_TESTS)
 override define RUN_TESTS
 	$(DEFAULT_RUN_TESTS)
 	$(MAKE) -C ebb run_tests
+	$(MAKE) -C bhrb run_tests
 endef
 
 DEFAULT_EMIT_TESTS := $(EMIT_TESTS)
 override define EMIT_TESTS
 	$(DEFAULT_EMIT_TESTS)
 	$(MAKE) -s -C ebb emit_tests
+	$(MAKE) -s -C bhrb emit_tests
 endef
 
 DEFAULT_INSTALL_RULE := $(INSTALL_RULE)
 override define INSTALL_RULE
 	$(DEFAULT_INSTALL_RULE)
 	$(MAKE) -C ebb install
+	$(MAKE) -C bhrb install
 endef
 
 clean:
 	rm -f $(TEST_PROGS) loop.o
 	$(MAKE) -C ebb clean
+	$(MAKE) -C bhrb clean
 
 ebb:
 	$(MAKE) -k -C $@ all
 
-.PHONY: all run_tests clean ebb
+bhrb:
+	$(MAKE) -k -C $@ all
+
+.PHONY: all run_tests clean ebb bhrb
diff --git a/tools/testing/selftests/powerpc/pmu/bhrb/Makefile b/tools/testing/selftests/powerpc/pmu/bhrb/Makefile
new file mode 100644
index 0000000..61c032a
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/bhrb/Makefile
@@ -0,0 +1,13 @@
+noarg:
+	$(MAKE) -C ../../
+
+TEST_PROGS := bhrb_filters
+
+all: $(TEST_PROGS)
+
+$(TEST_PROGS): ../../harness.c ../event.c ../lib.c bhrb_filters_asm.S
+
+include ../../../lib.mk
+
+clean:
+	rm -f $(TEST_PROGS)
diff --git a/tools/testing/selftests/powerpc/pmu/bhrb/bhrb_filters.c b/tools/testing/selftests/powerpc/pmu/bhrb/bhrb_filters.c
new file mode 100644
index 0000000..13e6b72
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/bhrb/bhrb_filters.c
@@ -0,0 +1,513 @@
+/*
+ * BHRB filter test (HW & SW)
+ *
+ * Copyright 2015 Anshuman Khandual, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <poll.h>
+#include <sys/shm.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/mman.h>
+
+#include "bhrb_filters.h"
+#include "utils.h"
+#include "../event.h"
+#include "../lib.h"
+
+/* Fetched address counts */
+#define ALL_MAX		32
+#define CALL_MAX	12
+#define RET_MAX		10
+#define COND_MAX	8
+#define IND_MAX		4
+
+/* Test tunables */
+#define LOOP_COUNT	10
+#define SAMPLE_PERIOD	10000
+
+static int branch_sample_type;
+static int branch_test_set[27] = {
+		PERF_SAMPLE_BRANCH_ANY_CALL,		/* Single filters */
+		PERF_SAMPLE_BRANCH_ANY_RETURN,
+		PERF_SAMPLE_BRANCH_COND,
+		PERF_SAMPLE_BRANCH_IND_CALL,
+		PERF_SAMPLE_BRANCH_ANY,
+
+		PERF_SAMPLE_BRANCH_ANY_CALL |		/* Double filters */
+		PERF_SAMPLE_BRANCH_ANY_RETURN,
+		PERF_SAMPLE_BRANCH_ANY_CALL |
+		PERF_SAMPLE_BRANCH_COND,
+		PERF_SAMPLE_BRANCH_ANY_CALL |
+		PERF_SAMPLE_BRANCH_IND_CALL,
+		PERF_SAMPLE_BRANCH_ANY_CALL |
+		PERF_SAMPLE_BRANCH_ANY,
+
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_COND,
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_IND_CALL,
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_ANY,
+
+		PERF_SAMPLE_BRANCH_COND |
+		PERF_SAMPLE_BRANCH_IND_CALL,
+		PERF_SAMPLE_BRANCH_COND |
+		PERF_SAMPLE_BRANCH_ANY,
+
+		PERF_SAMPLE_BRANCH_IND_CALL |
+		PERF_SAMPLE_BRANCH_ANY,
+
+		PERF_SAMPLE_BRANCH_ANY_CALL |		/* Tripple filters */
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_COND,
+
+		PERF_SAMPLE_BRANCH_ANY_CALL |
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_IND_CALL,
+
+		PERF_SAMPLE_BRANCH_ANY_CALL |
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_ANY,
+
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_COND |
+		PERF_SAMPLE_BRANCH_IND_CALL,
+
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_COND |
+		PERF_SAMPLE_BRANCH_ANY,
+
+		PERF_SAMPLE_BRANCH_COND |
+		PERF_SAMPLE_BRANCH_IND_CALL |
+		PERF_SAMPLE_BRANCH_ANY,
+
+		PERF_SAMPLE_BRANCH_ANY_CALL |		/* Quadruple filters */
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_COND |
+		PERF_SAMPLE_BRANCH_IND_CALL,
+
+		PERF_SAMPLE_BRANCH_ANY_CALL |
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_COND |
+		PERF_SAMPLE_BRANCH_ANY,
+
+		PERF_SAMPLE_BRANCH_ANY_CALL |
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_IND_CALL |
+		PERF_SAMPLE_BRANCH_ANY,
+
+		PERF_SAMPLE_BRANCH_ANY_CALL |
+		PERF_SAMPLE_BRANCH_COND |
+		PERF_SAMPLE_BRANCH_IND_CALL |
+		PERF_SAMPLE_BRANCH_ANY,
+
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_COND |
+		PERF_SAMPLE_BRANCH_IND_CALL |
+		PERF_SAMPLE_BRANCH_ANY,
+
+		PERF_SAMPLE_BRANCH_ANY_CALL |		/* All filters */
+		PERF_SAMPLE_BRANCH_ANY_RETURN |
+		PERF_SAMPLE_BRANCH_COND |
+		PERF_SAMPLE_BRANCH_IND_CALL |
+		PERF_SAMPLE_BRANCH_ANY };
+
+static unsigned int all_set[ALL_MAX], call_set[CALL_MAX];
+static unsigned int ret_set[RET_MAX], cond_set[COND_MAX], ind_set[IND_MAX];
+
+static bool has_failed;
+static unsigned long branch_any_call;
+static unsigned long branch_any_return;
+static unsigned long branch_cond;
+static unsigned long branch_ind_call;
+static unsigned long branch_any;
+static unsigned long branch_total;
+
+static void init_branch_stats(void)
+{
+	branch_any_call = 0;
+	branch_any_return = 0;
+	branch_cond = 0;
+	branch_ind_call = 0;
+	branch_any = 0;
+	branch_total = 0;
+}
+
+static void show_branch_stats(void)
+{
+	printf("BRANCH STATS\n");
+	printf("ANY_CALL:	%ld\n", branch_any_call);
+	printf("ANY_RETURN:	%ld\n", branch_any_return);
+	printf("COND:		%ld\n", branch_cond);
+	printf("IND_CALL:	%ld\n", branch_ind_call);
+	printf("ANY:		%ld\n", branch_any);
+	printf("TOTAL:		%ld\n", branch_total);
+
+}
+
+static void fetch_branches(void)
+{
+	int i;
+
+	/* Clear */
+	memset(all_set, 0, sizeof(all_set));
+	memset(call_set, 0, sizeof(call_set));
+	memset(ret_set, 0, sizeof(ret_set));
+	memset(cond_set, 0, sizeof(cond_set));
+	memset(ind_set, 0, sizeof(ind_set));
+
+	/* Fetch */
+	fetch_all_branches(all_set);
+	fetch_all_calls(call_set);
+	fetch_all_rets(ret_set);
+	fetch_all_conds(cond_set);
+	fetch_all_inds(ind_set);
+
+	/* Display */
+	printf("ANY branches\n");
+	for (i = 0; i < ALL_MAX; i += 2)
+		printf("%x ---> %x\n", all_set[i], all_set[i + 1]);
+
+	printf("ANY_CALL branches\n");
+	for (i = 0; i < CALL_MAX; i += 2)
+		printf("%x ---> %x\n", call_set[i], call_set[i + 1]);
+
+	printf("ANY_RETURN branches\n");
+	for (i = 0; i < RET_MAX; i += 2)
+		printf("%x ---> %x\n", ret_set[i], ret_set[i + 1]);
+
+	printf("COND branches\n");
+	for (i = 0; i < COND_MAX; i += 2)
+		printf("%x ---> %x\n", cond_set[i], cond_set[i + 1]);
+
+	printf("IND_CALL branches\n");
+	for (i = 0; i < IND_MAX; i += 2)
+		printf("%x ---> %x\n", ind_set[i], ind_set[i + 1]);
+
+}
+
+/* Perf mmap stats */
+static unsigned long record_sample;
+static unsigned long record_mmap;
+static unsigned long record_lost;
+static unsigned long record_throttle;
+static unsigned long record_unthrottle;
+static unsigned long record_overlap;
+
+static void init_perf_mmap_stats(void)
+{
+	record_sample = 0;
+	record_mmap = 0;
+	record_lost = 0;
+	record_throttle = 0;
+	record_unthrottle = 0;
+	record_overlap = 0;
+}
+
+static void show_perf_mmap_stats(void)
+{
+	printf("PERF STATS\n");
+	printf("OVERLAP:		%ld\n", record_overlap);
+	printf("RECORD_SAMPLE:		%ld\n", record_sample);
+	printf("RECORD_MAP:		%ld\n", record_mmap);
+	printf("RECORD_LOST:		%ld\n", record_lost);
+	printf("RECORD_THROTTLE:	%ld\n", record_throttle);
+	printf("RECORD_UNTHROTTLE:	%ld\n", record_unthrottle);
+}
+
+static bool search_all_set(unsigned long from, unsigned long to)
+{
+	int i;
+
+	for (i = 0; i < ALL_MAX; i += 2) {
+		if ((all_set[i] == from) && (all_set[i+1] == to))
+			return true;
+	}
+	return false;
+}
+
+static bool search_call_set(unsigned long from, unsigned long to)
+{
+	int i;
+
+	for (i = 0; i < CALL_MAX; i += 2) {
+		if ((call_set[i] == from) && (call_set[i+1] == to))
+			return true;
+	}
+	return false;
+}
+
+static bool search_ret_set(unsigned long from, unsigned long to)
+{
+	int i;
+
+	for (i = 0; i < RET_MAX; i += 2) {
+		if ((ret_set[i] == from) && (ret_set[i+1] == to))
+			return true;
+	}
+	return false;
+}
+
+static bool search_cond_set(unsigned long from, unsigned long to)
+{
+	int i;
+
+	for (i = 0; i < COND_MAX; i += 2) {
+		if ((cond_set[i] == from) && (cond_set[i+1] == to))
+			return true;
+	}
+	return false;
+}
+
+static bool search_ind_set(unsigned long from, unsigned long to)
+{
+	int i;
+
+	for (i = 0; i < IND_MAX; i += 2) {
+		if ((ind_set[i] == from) && (ind_set[i+1] == to))
+			return true;
+	}
+	return false;
+}
+
+static int check_branch(unsigned long from, unsigned long to)
+{
+	bool result = false;
+
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_CALL) {
+		if (search_call_set(from, to)) {
+			branch_any_call++;
+			result = true;
+		}
+	}
+
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_RETURN) {
+		if (search_ret_set(from, to)) {
+			branch_any_return++;
+			result = true;
+		}
+	}
+
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_COND) {
+		if (search_cond_set(from, to)) {
+			branch_cond++;
+			result = true;
+		}
+	}
+
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_IND_CALL) {
+		if (search_ind_set(from, to)) {
+			branch_ind_call++;
+			result = true;
+		}
+	}
+
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY) {
+		if (search_all_set(from, to)) {
+			branch_any++;
+			result = true;
+		}
+	}
+
+	branch_total++;
+	return result;
+}
+
+static void *ring_buffer_mask(struct ring_buffer *r, void *p)
+{
+	unsigned long l = (unsigned long)p;
+
+	return (void *)(r->ring_base + ((l - r->ring_base) & r->mask));
+}
+
+static void dump_sample(struct perf_event_header *hdr, struct ring_buffer *r)
+{
+	unsigned long from, to, flag;
+	int i, nr;
+	int64_t *v;
+
+	/* NR Branches */
+	v = ring_buffer_mask(r, hdr + 1);
+
+	nr = *v;
+
+	/* Branches */
+	for (i = 0; i < nr; i++) {
+		v = ring_buffer_mask(r, v + 1);
+		from = *v;
+
+		v = ring_buffer_mask(r, v + 1);
+		to = *v;
+
+		v = ring_buffer_mask(r, v + 1);
+		flag = *v;
+
+		if (!check_branch(from, to)) {
+			has_failed = true;
+			printf("[Filter: %d] From: %lx To: %lx Flags: %lx\n",
+					branch_sample_type, from, to, flag);
+		}
+	}
+}
+
+static void read_ring_buffer(struct event *e)
+{
+	struct ring_buffer *r = &e->ring_buffer;
+	struct perf_event_header *hdr;
+	int old, head;
+
+	head = r->page->data_head & r->mask;
+
+	asm volatile ("sync": : :"memory");
+
+	old = r->page->data_tail & r->mask;
+
+	while (old != head) {
+		hdr = (struct perf_event_header *)(r->ring_base + old);
+
+		if ((old & r->mask) + hdr->size !=
+					((old + hdr->size) & r->mask))
+			++record_overlap;
+
+		if (hdr->type == PERF_RECORD_SAMPLE) {
+			++record_sample;
+			dump_sample(hdr, r);
+		}
+
+		if (hdr->type == PERF_RECORD_MMAP)
+			++record_mmap;
+
+		if (hdr->type == PERF_RECORD_LOST)
+			++record_lost;
+
+		if (hdr->type == PERF_RECORD_THROTTLE)
+			++record_throttle;
+
+		if (hdr->type == PERF_RECORD_UNTHROTTLE)
+			++record_unthrottle;
+
+		old = (old + hdr->size) & r->mask;
+	}
+	r->page->data_tail = old;
+}
+
+static void event_mmap(struct event *e)
+{
+	struct ring_buffer *r = &e->ring_buffer;
+
+	r->page = mmap(NULL, 9 * getpagesize(), PROT_READ |
+					PROT_WRITE, MAP_SHARED, e->fd, 0);
+
+	if (r->page == MAP_FAILED) {
+		r->page = NULL;
+		perror("mmap() failed");
+	}
+
+	r->mask = (8 * getpagesize()) - 1;
+	r->ring_base = (unsigned long)r->page + getpagesize();
+
+}
+
+static int filter_test(void)
+{
+	struct pollfd pollfd;
+	struct event ebhrb;
+	pid_t pid;
+	int ret, loop = 0;
+
+	has_failed = false;
+	pid = fork();
+	if (pid == -1) {
+		perror("fork() failed");
+		return 1;
+	}
+
+	/* Run child */
+	if (pid == 0) {
+		start_loop();
+		exit(0);
+	}
+
+	/* Prepare event */
+	event_init_opts(&ebhrb, PERF_COUNT_HW_INSTRUCTIONS,
+				PERF_TYPE_HARDWARE, "insturctions");
+	ebhrb.attr.sample_type = PERF_SAMPLE_BRANCH_STACK;
+	ebhrb.attr.disabled = 1;
+	ebhrb.attr.mmap = 1;
+	ebhrb.attr.mmap_data = 1;
+	ebhrb.attr.sample_period = SAMPLE_PERIOD;
+	ebhrb.attr.exclude_user = 0;
+	ebhrb.attr.exclude_kernel = 1;
+	ebhrb.attr.exclude_hv = 1;
+	ebhrb.attr.branch_sample_type = branch_sample_type;
+
+	/* Open event */
+	event_open_with_pid(&ebhrb, pid);
+
+	/* Mmap ring buffer and enable event */
+	event_mmap(&ebhrb);
+	FAIL_IF(event_enable(&ebhrb));
+
+	/* Prepare polling */
+	pollfd.fd = ebhrb.fd;
+	pollfd.events = POLLIN;
+
+	for (loop = 0; loop < LOOP_COUNT; loop++) {
+		ret = poll(&pollfd, 1, -1);
+		if (ret == -1) {
+			perror("poll() failed");
+			return 1;
+		}
+		if (ret == 0) {
+			perror("poll() timeout");
+			return 1;
+		}
+		read_ring_buffer(&ebhrb);
+		if (has_failed)
+			return 1;
+	}
+
+	/* Disable and close event */
+	FAIL_IF(event_disable(&ebhrb));
+	event_close(&ebhrb);
+
+	/* Terminate child */
+	kill(pid, SIGKILL);
+	return 0;
+}
+
+static int  bhrb_filters_test(void)
+{
+	int i;
+
+	/* Fetch branches */
+	fetch_branches();
+	init_branch_stats();
+	init_perf_mmap_stats();
+
+	for (i = 0; i < sizeof(branch_test_set)/sizeof(int); i++) {
+		branch_sample_type = branch_test_set[i];
+		if (filter_test())
+			return 1;
+	}
+
+	/* Show stats */
+	show_branch_stats();
+	show_perf_mmap_stats();
+
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(bhrb_filters_test, "bhrb_filters");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/bhrb/bhrb_filters.h b/tools/testing/selftests/powerpc/pmu/bhrb/bhrb_filters.h
new file mode 100644
index 0000000..072375a
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/bhrb/bhrb_filters.h
@@ -0,0 +1,16 @@
+/*
+ * Copyright 2015 Anshuman Khandual, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/* Assembly routines */
+extern void fetch_all_branches(unsigned int *);
+extern void fetch_all_calls(unsigned int *);
+extern void fetch_all_rets(unsigned int *);
+extern void fetch_all_conds(unsigned int *);
+extern void fetch_all_inds(unsigned int *);
+extern void start_loop(void);
diff --git a/tools/testing/selftests/powerpc/pmu/bhrb/bhrb_filters_asm.S b/tools/testing/selftests/powerpc/pmu/bhrb/bhrb_filters_asm.S
new file mode 100644
index 0000000..e72a585
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/bhrb/bhrb_filters_asm.S
@@ -0,0 +1,260 @@
+/*
+ * Assembly functions for BHRB test
+ *
+ * Copyright 2015 Anshuman Khandual, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#define GLUE(a,b) a##b
+#define _GLOBAL(name) \
+       .section ".text"; \
+       .align 2 ; \
+       .globl name; \
+       .globl GLUE(.,name); \
+       .section ".opd","aw"; \
+name: \
+       .quad GLUE(.,name); \
+       .quad .TOC.@tocbase; \
+       .quad 0; \
+       .previous; \
+       .type GLUE(.,name),@function; \
+GLUE(.,name):
+
+#define LR_SAVE 19
+
+#define LOAD_ADDR(reg, label)			\
+	lis     reg,(label)@highest;		\
+	ori     reg,reg,(label)@higher;		\
+	rldicr  reg,reg,32,31;			\
+	oris    reg,reg,(label)@h;		\
+	ori     reg,reg,(label)@l;		\
+
+#define LOAD_LABEL(reg1, label1, reg2, label2)	\
+	lis     reg1,(label1)@highest;		\
+	ori     reg1,reg1,(label1)@higher;	\
+	rldicr  reg1,reg1,32,31;		\
+	oris    reg1,reg1,(label1)@h;		\
+	ori     reg1,reg1,(label1)@l;		\
+	lis     reg2,(label2)@highest;		\
+	ori     reg2,reg2,(label2)@higher;	\
+	rldicr  reg2,reg2,32,31;		\
+	oris    reg2,reg2,(label2)@h;		\
+	ori     reg2,reg2,(label2)@l;		\
+
+_GLOBAL(start_loop)
+label:
+	b label0			/* ANY */
+	blr				/* ANY_RETURN */
+label0:
+	b label1			/* ANY */
+
+label1:
+	b label2			/* ANY */
+
+label2:
+	b label3			/* ANY */
+
+label3:
+	mflr LR_SAVE
+	bl label4			/* ANY | ANY_CALL */
+	mtlr LR_SAVE
+	b start_loop			/* ANY */
+label4:
+	mflr LR_SAVE
+	li 20, 12
+	cmpi 3, 20, 12
+	bcl 12, 4 * cr3+2, label5	/* ANY | ANY_CALL | COND */
+	li 20, 12
+	cmpi 4, 20, 20
+	bcl 12, 4 * cr4+0, label5	/* ANY | ANY_CALL | COND */
+	LOAD_ADDR(20, label5)
+	mtctr 20
+	li 22, 10
+	cmpi 0, 22, 10
+	bcctrl 12, 4*cr0+2		/* ANY | NY_CALL | IND_CALL | COND */
+	LOAD_ADDR(20, label5)
+	mtlr 20
+	li      20, 10
+	cmpi    0, 20, 10
+	bclrl   12, 4*cr0+2		/* ANY | ANY_CALL | IND_CALL | COND */
+	mtlr LR_SAVE
+	blr				/* ANY | ANY_RETURN */
+
+label5:
+	blr				/* ANY | ANY_RETURN */
+
+_GLOBAL(fetch_all_branches)
+	LOAD_LABEL(20, label, 21, label0)
+	st 20, 0(3)
+	st 21, 4(3)
+
+	LOAD_LABEL(20, label0, 21, label1)
+	st 20, 8(3)
+	st 21, 12(3)
+
+	LOAD_LABEL(20, label1, 21, label2)
+	st 20, 16(3)
+	st 21, 20(3)
+
+	LOAD_LABEL(20, label2, 21, label3)
+	st 20, 24(3)
+	st 21, 28(3)
+
+	LOAD_LABEL(20, label3, 21, label4)
+	addi 20, 20, 4
+	st 20, 32(3)
+	st 21, 36(3)
+
+	LOAD_LABEL(20, label3, 21, label)
+	addi 20, 20, 12
+	st 20, 40(3)
+	st 21, 44(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 12
+	st 20, 48(3)
+	st 21, 52(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 24
+	st 20, 56(3)
+	st 21, 60(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 60
+	st 20, 64(3)
+	st 21, 68(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 96
+	st 20, 72(3)
+	st 21, 76(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 104
+	st 20, 80(3)
+	st 21, 84(3)
+
+	LOAD_LABEL(20, label5, 21, label4)
+	st 20, 88(3)
+	addi 21, 21, 16
+	st 21, 92(3)
+
+	LOAD_LABEL(20, label5, 21, label4)
+	st 20, 96(3)
+	addi 21, 21, 28
+	st 21, 100(3)
+
+	LOAD_LABEL(20, label5, 21, label4)
+	st 20, 104(3)
+	addi 21, 21, 64
+	st 21, 108(3)
+
+	LOAD_LABEL(20, label5, 21, label4)
+	st 20, 112(3)
+	addi 21, 21, 100
+	st 21, 116(3)
+
+	LOAD_LABEL(20, label4, 21, label3)
+	addi 20, 20, 104
+	st 20, 120(3)
+	addi 21, 21, 8
+	st 21, 124(3)
+	blr
+
+_GLOBAL(fetch_all_calls)
+	LOAD_LABEL(20, label3, 21, label4)
+	addi 20, 20, 4
+	st 20, 0(3)
+	st 21, 4(3)
+
+	LOAD_LABEL(20, label3, 21, label4)
+	addi 20, 20, 4
+	st 20, 8(3)
+	st 21, 12(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 12
+	st 20, 16(3)
+	st 21, 20(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 24
+	st 20, 24(3)
+	st 21, 28(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 60
+	st 20, 32(3)
+	st 21, 36(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 96
+	st 20, 40(3)
+	st 21, 44(3)
+	blr
+
+_GLOBAL(fetch_all_rets)
+	LOAD_LABEL(20, label5, 21, label4)
+	st 20, 0(3)
+	addi 21, 21, 16
+	st 21, 4(3)
+
+	LOAD_LABEL(20, label5, 21, label4)
+	st 20, 8(3)
+	addi 21, 21, 28
+	st 21, 12(3)
+
+	LOAD_LABEL(20, label5, 21, label4)
+	st 20, 16(3)
+	addi 21, 21, 64
+	st 21, 20(3)
+
+	LOAD_LABEL(20, label5, 21, label4)
+	st 20, 24(3)
+	addi 21, 21, 100
+	st 21, 28(3)
+
+	LOAD_LABEL(20, label4, 21, label3)
+	addi 20, 20, 104
+	st 20, 32(3)
+	addi 21, 21, 8
+	st 21, 36(3)
+	blr
+
+_GLOBAL(fetch_all_conds)
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 12
+	st 20, 0(3)
+	st 21, 4(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 24
+	st 20, 8(3)
+	st 21, 12(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 60
+	st 20, 16(3)
+	st 21, 20(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 96
+	st 20, 24(3)
+	st 21, 28(3)
+	blr
+
+_GLOBAL(fetch_all_inds)
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 60
+	st 20, 0(3)
+	st 21, 4(3)
+
+	LOAD_LABEL(20, label4, 21, label5)
+	addi 20, 20, 96
+	st 20, 8(3)
+	st 21, 12(3)
+	blr
diff --git a/tools/testing/selftests/powerpc/pmu/event.h b/tools/testing/selftests/powerpc/pmu/event.h
index a0ea6b1..385b1c4 100644
--- a/tools/testing/selftests/powerpc/pmu/event.h
+++ b/tools/testing/selftests/powerpc/pmu/event.h
@@ -11,6 +11,10 @@
 
 #include "utils.h"
 
+struct ring_buffer {
+	struct perf_event_mmap_page *page;
+	unsigned long ring_base, old, mask;
+};
 
 struct event {
 	struct perf_event_attr attr;
@@ -22,6 +26,7 @@ struct event {
 		u64 running;
 		u64 enabled;
 	} result;
+	struct ring_buffer ring_buffer;
 };
 
 void event_init(struct event *e, u64 config);
-- 
2.1.0