perf tools: Add ARM64 perf_regs_load to support libunwind and enable testing

Newest libunwind does support ARM64, and perf is able to utilize it
also.

This patch enables the perf test dwarf unwind for arm64.

 Test result:
  # ./perf test unwind
  25: Test dwarf unwind                                      : Ok

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/r/1427461681-72971-1-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/arch/arm64/tests/Build

@@ -0,0 +1,2 @@
+libperf-y += regs_load.o
+libperf-y += dwarf-unwind.o

tools/perf/arch/arm64/tests/dwarf-unwind.c

@@ -0,0 +1,61 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "debug.h"
+#include "tests/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_ARM64_SP];
+
+	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/arm64/tests/regs_load.S

@@ -0,0 +1,46 @@
+#include <linux/linkage.h>
+
+.text
+.type perf_regs_load,%function
+#define STR_REG(r)	str x##r, [x0, 8 * r]
+#define LDR_REG(r)	ldr x##r, [x0, 8 * r]
+#define SP	(8 * 31)
+#define PC	(8 * 32)
+ENTRY(perf_regs_load)
+	STR_REG(0)
+	STR_REG(1)
+	STR_REG(2)
+	STR_REG(3)
+	STR_REG(4)
+	STR_REG(5)
+	STR_REG(6)
+	STR_REG(7)
+	STR_REG(8)
+	STR_REG(9)
+	STR_REG(10)
+	STR_REG(11)
+	STR_REG(12)
+	STR_REG(13)
+	STR_REG(14)
+	STR_REG(15)
+	STR_REG(16)
+	STR_REG(17)
+	STR_REG(18)
+	STR_REG(19)
+	STR_REG(20)
+	STR_REG(21)
+	STR_REG(22)
+	STR_REG(23)
+	STR_REG(24)
+	STR_REG(25)
+	STR_REG(26)
+	STR_REG(27)
+	STR_REG(28)
+	STR_REG(29)
+	STR_REG(30)
+	mov x1, sp
+	str x1, [x0, #SP]
+	str x30, [x0, #PC]
+	LDR_REG(1)
+	ret
+ENDPROC(perf_regs_load)