perf tests: Add dwarf unwind test for powerpc

The user stack dump feature was recently added for powerpc. But there
was no test case available to test it.

This test works same as on other architectures by preparing a stack
frame on the perf test thread and comparing each frame by unwinding it.

  $ ./perf test 50
    50: Test dwarf unwind    : Ok

User stack dump for powerpc: https://lkml.org/lkml/2016/4/28/482

Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Anju T Sudhakar <anju@linux.vnet.ibm.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Matt Fleming <matt.fleming@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/1474267100-31079-1-git-send-email-ravi.bangoria@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/arch/powerpc/Build

@@ -1 +1,2 @@
 libperf-y += util/
+libperf-y += tests/

tools/perf/arch/powerpc/include/arch-tests.h

@@ -0,0 +1,13 @@
+#ifndef ARCH_TESTS_H
+#define ARCH_TESTS_H
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread);
+#endif
+
+extern struct test arch_tests[];
+
+#endif

tools/perf/arch/powerpc/include/perf_regs.h

@@ -5,6 +5,8 @@
 #include <linux/types.h>
 #include <asm/perf_regs.h>
 
+void perf_regs_load(u64 *regs);
+
 #define PERF_REGS_MASK  ((1ULL << PERF_REG_POWERPC_MAX) - 1)
 #define PERF_REGS_MAX   PERF_REG_POWERPC_MAX
 #ifdef __powerpc64__

tools/perf/arch/powerpc/tests/Build

@@ -0,0 +1,4 @@
+libperf-$(CONFIG_DWARF_UNWIND) += regs_load.o
+libperf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
+
+libperf-y += arch-tests.o

tools/perf/arch/powerpc/tests/arch-tests.c

@@ -0,0 +1,15 @@
+#include <string.h>
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+struct test arch_tests[] = {
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	{
+		.desc = "Test dwarf unwind",
+		.func = test__dwarf_unwind,
+	},
+#endif
+	{
+		.func = NULL,
+	},
+};

tools/perf/arch/powerpc/tests/dwarf-unwind.c

@@ -0,0 +1,62 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_POWERPC_R1];
+
+	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		free(buf);
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = calloc(1, sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}

tools/perf/arch/powerpc/tests/regs_load.S

@@ -0,0 +1,94 @@
+#include <linux/linkage.h>
+
+/* Offset is based on macros from arch/powerpc/include/uapi/asm/ptrace.h. */
+#define R0	 0
+#define R1	 1 * 8
+#define R2	 2 * 8
+#define R3	 3 * 8
+#define R4	 4 * 8
+#define R5	 5 * 8
+#define R6	 6 * 8
+#define R7	 7 * 8
+#define R8	 8 * 8
+#define R9	 9 * 8
+#define R10	10 * 8
+#define R11	11 * 8
+#define R12	12 * 8
+#define R13	13 * 8
+#define R14	14 * 8
+#define R15	15 * 8
+#define R16	16 * 8
+#define R17	17 * 8
+#define R18	18 * 8
+#define R19	19 * 8
+#define R20	20 * 8
+#define R21	21 * 8
+#define R22	22 * 8
+#define R23	23 * 8
+#define R24	24 * 8
+#define R25	25 * 8
+#define R26	26 * 8
+#define R27	27 * 8
+#define R28	28 * 8
+#define R29	29 * 8
+#define R30	30 * 8
+#define R31	31 * 8
+#define NIP	32 * 8
+#define CTR	35 * 8
+#define LINK	36 * 8
+#define XER	37 * 8
+
+.globl perf_regs_load
+perf_regs_load:
+	std 0, R0(3)
+	std 1, R1(3)
+	std 2, R2(3)
+	std 3, R3(3)
+	std 4, R4(3)
+	std 5, R5(3)
+	std 6, R6(3)
+	std 7, R7(3)
+	std 8, R8(3)
+	std 9, R9(3)
+	std 10, R10(3)
+	std 11, R11(3)
+	std 12, R12(3)
+	std 13, R13(3)
+	std 14, R14(3)
+	std 15, R15(3)
+	std 16, R16(3)
+	std 17, R17(3)
+	std 18, R18(3)
+	std 19, R19(3)
+	std 20, R20(3)
+	std 21, R21(3)
+	std 22, R22(3)
+	std 23, R23(3)
+	std 24, R24(3)
+	std 25, R25(3)
+	std 26, R26(3)
+	std 27, R27(3)
+	std 28, R28(3)
+	std 29, R29(3)
+	std 30, R30(3)
+	std 31, R31(3)
+
+	/* store NIP */
+	mflr 4
+	std 4, NIP(3)
+
+	/* Store LR */
+	std 4, LINK(3)
+
+	/* Store XER */
+	mfxer 4
+	std 4, XER(3)
+
+	/* Store CTR */
+	mfctr 4
+	std 4, CTR(3)
+
+	/* Restore original value of r4 */
+	ld 4, R4(3)
+
+	blr

tools/perf/tests/Build

@@ -71,7 +71,7 @@ $(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/B
 	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
 	$(Q)echo ';' >> $@
 
-ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
+ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64 powerpc))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
 

tools/perf/tests/dwarf-unwind.c

@@ -11,7 +11,7 @@
 #include "thread.h"
 #include "callchain.h"
 
-#if defined (__x86_64__) || defined (__i386__)
+#if defined (__x86_64__) || defined (__i386__) || defined (__powerpc__)
 #include "arch-tests.h"
 #endif