perf tests x86: Add dwarf unwind test

Adding dwarf unwind test, that setups live machine data over the perf
test thread and does the remote unwind.

At this moment this test fails due to bug in the max_stack processing in
unwind__get_entries function.  This is fixed in following patch.

Need to use -fno-optimize-sibling-calls for test compilation, otherwise
'krava_*' function calls are optimized into jumps and ommited from the
stack unwind.

So far it's enabled only for x86.

Signed-off-by: Jiri Olsa <[email protected]>
Acked-by: Jean Pihet <[email protected]>
Cc: Corey Ashford <[email protected]>
Cc: David Ahern <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jean Pihet <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

tools/perf/Makefile.perf

@@ -408,6 +408,11 @@ endif
 LIB_OBJS += $(OUTPUT)tests/code-reading.o
 LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
 LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
+ifndef NO_LIBUNWIND
+ifeq ($(ARCH),x86)
+LIB_OBJS += $(OUTPUT)tests/dwarf-unwind.o
+endif
+endif
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -655,6 +660,9 @@ $(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS
 		-DPYTHON='"$(PYTHON_WORD)"' \
 		$<
 
+$(OUTPUT)tests/dwarf-unwind.o: tests/dwarf-unwind.c
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -fno-optimize-sibling-calls $<
+
 $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 

tools/perf/arch/x86/Makefile

@@ -5,6 +5,7 @@ endif
 ifndef NO_LIBUNWIND
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o

tools/perf/arch/x86/include/perf_regs.h

@@ -9,12 +9,16 @@ void perf_regs_load(u64 *regs);
 
 #ifndef HAVE_ARCH_X86_64_SUPPORT
 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
+#define PERF_REGS_MAX PERF_REG_X86_32_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32
 #else
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
 		       (1ULL << PERF_REG_X86_ES) | \
 		       (1ULL << PERF_REG_X86_FS) | \
 		       (1ULL << PERF_REG_X86_GS))
 #define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
+#define PERF_REGS_MAX PERF_REG_X86_64_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
 #endif
 #define PERF_REG_IP PERF_REG_X86_IP
 #define PERF_REG_SP PERF_REG_X86_SP

tools/perf/arch/x86/tests/dwarf-unwind.c

@@ -0,0 +1,58 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.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_X86_SP];
+
+	map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		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 = malloc(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;
+
+	return sample_ustack(sample, thread, buf);
+}

tools/perf/tests/builtin-test.c

@@ -115,6 +115,14 @@ static struct test {
 		.desc = "Test parsing with no sample_id_all bit set",
 		.func = test__parse_no_sample_id_all,
 	},
+#if defined(__x86_64__) || defined(__i386__)
+#ifdef HAVE_LIBUNWIND_SUPPORT
+	{
+		.desc = "Test dwarf unwind",
+		.func = test__dwarf_unwind,
+	},
+#endif
+#endif
 	{
 		.func = NULL,
 	},

tools/perf/tests/dwarf-unwind.c

@@ -0,0 +1,144 @@
+#include <linux/compiler.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include "tests.h"
+#include "debug.h"
+#include "machine.h"
+#include "event.h"
+#include "unwind.h"
+#include "perf_regs.h"
+#include "map.h"
+#include "thread.h"
+
+static int mmap_handler(struct perf_tool *tool __maybe_unused,
+			union perf_event *event,
+			struct perf_sample *sample __maybe_unused,
+			struct machine *machine)
+{
+	return machine__process_mmap_event(machine, event, NULL);
+}
+
+static int init_live_machine(struct machine *machine)
+{
+	union perf_event event;
+	pid_t pid = getpid();
+
+	return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
+						  mmap_handler, machine, true);
+}
+
+#define MAX_STACK 6
+
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+	unsigned long *cnt = (unsigned long *) arg;
+	char *symbol = entry->sym ? entry->sym->name : NULL;
+	static const char *funcs[MAX_STACK] = {
+		"test__arch_unwind_sample",
+		"unwind_thread",
+		"krava_3",
+		"krava_2",
+		"krava_1",
+		"test__dwarf_unwind"
+	};
+
+	if (*cnt >= MAX_STACK) {
+		pr_debug("failed: crossed the max stack value %d\n", MAX_STACK);
+		return -1;
+	}
+
+	if (!symbol) {
+		pr_debug("failed: got unresolved address 0x%" PRIx64 "\n",
+			 entry->ip);
+		return -1;
+	}
+
+	pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip);
+	return strcmp((const char *) symbol, funcs[(*cnt)++]);
+}
+
+__attribute__ ((noinline))
+static int unwind_thread(struct thread *thread, struct machine *machine)
+{
+	struct perf_sample sample;
+	unsigned long cnt = 0;
+	int err = -1;
+
+	memset(&sample, 0, sizeof(sample));
+
+	if (test__arch_unwind_sample(&sample, thread)) {
+		pr_debug("failed to get unwind sample\n");
+		goto out;
+	}
+
+	err = unwind__get_entries(unwind_entry, &cnt, machine, thread,
+				  PERF_REGS_MASK, &sample, MAX_STACK);
+	if (err)
+		pr_debug("unwind failed\n");
+	else if (cnt != MAX_STACK) {
+		pr_debug("got wrong number of stack entries %lu != %d\n",
+			 cnt, MAX_STACK);
+		err = -1;
+	}
+
+ out:
+	free(sample.user_stack.data);
+	free(sample.user_regs.regs);
+	return err;
+}
+
+__attribute__ ((noinline))
+static int krava_3(struct thread *thread, struct machine *machine)
+{
+	return unwind_thread(thread, machine);
+}
+
+__attribute__ ((noinline))
+static int krava_2(struct thread *thread, struct machine *machine)
+{
+	return krava_3(thread, machine);
+}
+
+__attribute__ ((noinline))
+static int krava_1(struct thread *thread, struct machine *machine)
+{
+	return krava_2(thread, machine);
+}
+
+int test__dwarf_unwind(void)
+{
+	struct machines machines;
+	struct machine *machine;
+	struct thread *thread;
+	int err = -1;
+
+	machines__init(&machines);
+
+	machine = machines__find(&machines, HOST_KERNEL_ID);
+	if (!machine) {
+		pr_err("Could not get machine\n");
+		return -1;
+	}
+
+	if (init_live_machine(machine)) {
+		pr_err("Could not init machine\n");
+		goto out;
+	}
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	thread = machine__find_thread(machine, getpid());
+	if (!thread) {
+		pr_err("Could not get thread\n");
+		goto out;
+	}
+
+	err = krava_1(thread, machine);
+
+ out:
+	machine__delete_threads(machine);
+	machine__exit(machine);
+	machines__exit(&machines);
+	return err;
+}

tools/perf/tests/tests.h

@@ -40,5 +40,14 @@ int test__code_reading(void);
 int test__sample_parsing(void);
 int test__keep_tracking(void);
 int test__parse_no_sample_id_all(void);
+int test__dwarf_unwind(void);
 
+#if defined(__x86_64__) || defined(__i386__)
+#ifdef HAVE_LIBUNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread);
+#endif
+#endif
 #endif /* TESTS_H */