perf tools: Support for DWARF CFI unwinding on post processing

This brings the support for DWARF cfi unwinding on perf post
processing. Call frame informations are retrieved and then passed
to libunwind that requests memory and register content from the
applications.

Adding unwind object to handle the user stack backtrace based
on the user register values and user stack dump.

The unwind object access the libunwind via remote interface
and provides to it all the necessary data to unwind the stack.

The unwind interface provides following function:
	unwind__get_entries

And callback (specified in above function) to retrieve
the backtrace entries:
	typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry,
					 void *arg);

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-12-git-send-email-jolsa@redhat.com
[ Replaced use of perf_session by usage of perf_evsel ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Makefile

@@ -334,6 +334,7 @@ LIB_H += util/target.h
 LIB_H += util/rblist.h
 LIB_H += util/intlist.h
 LIB_H += util/perf_regs.h
+LIB_H += util/unwind.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -547,6 +548,7 @@ else
 	EXTLIBS += $(LIBUNWIND_LIBS)
 	BASIC_CFLAGS := $(LIBUNWIND_CFLAGS) $(BASIC_CFLAGS)
 	BASIC_LDFLAGS := $(LIBUNWIND_LDFLAGS) $(BASIC_LDFLAGS)
+	LIB_OBJS += $(OUTPUT)util/unwind.o
 endif
 
 ifdef NO_NEWT

tools/perf/arch/x86/Makefile

@@ -2,4 +2,7 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
+ifndef NO_LIBUNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
+endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o

tools/perf/arch/x86/util/unwind.c

@@ -0,0 +1,111 @@
+
+#include <errno.h>
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+
+#ifdef ARCH_X86_64
+int unwind__arch_reg_id(int regnum)
+{
+	int id;
+
+	switch (regnum) {
+	case UNW_X86_64_RAX:
+		id = PERF_REG_X86_AX;
+		break;
+	case UNW_X86_64_RDX:
+		id = PERF_REG_X86_DX;
+		break;
+	case UNW_X86_64_RCX:
+		id = PERF_REG_X86_CX;
+		break;
+	case UNW_X86_64_RBX:
+		id = PERF_REG_X86_BX;
+		break;
+	case UNW_X86_64_RSI:
+		id = PERF_REG_X86_SI;
+		break;
+	case UNW_X86_64_RDI:
+		id = PERF_REG_X86_DI;
+		break;
+	case UNW_X86_64_RBP:
+		id = PERF_REG_X86_BP;
+		break;
+	case UNW_X86_64_RSP:
+		id = PERF_REG_X86_SP;
+		break;
+	case UNW_X86_64_R8:
+		id = PERF_REG_X86_R8;
+		break;
+	case UNW_X86_64_R9:
+		id = PERF_REG_X86_R9;
+		break;
+	case UNW_X86_64_R10:
+		id = PERF_REG_X86_R10;
+		break;
+	case UNW_X86_64_R11:
+		id = PERF_REG_X86_R11;
+		break;
+	case UNW_X86_64_R12:
+		id = PERF_REG_X86_R12;
+		break;
+	case UNW_X86_64_R13:
+		id = PERF_REG_X86_R13;
+		break;
+	case UNW_X86_64_R14:
+		id = PERF_REG_X86_R14;
+		break;
+	case UNW_X86_64_R15:
+		id = PERF_REG_X86_R15;
+		break;
+	case UNW_X86_64_RIP:
+		id = PERF_REG_X86_IP;
+		break;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return id;
+}
+#else
+int unwind__arch_reg_id(int regnum)
+{
+	int id;
+
+	switch (regnum) {
+	case UNW_X86_EAX:
+		id = PERF_REG_X86_AX;
+		break;
+	case UNW_X86_EDX:
+		id = PERF_REG_X86_DX;
+		break;
+	case UNW_X86_ECX:
+		id = PERF_REG_X86_CX;
+		break;
+	case UNW_X86_EBX:
+		id = PERF_REG_X86_BX;
+		break;
+	case UNW_X86_ESI:
+		id = PERF_REG_X86_SI;
+		break;
+	case UNW_X86_EDI:
+		id = PERF_REG_X86_DI;
+		break;
+	case UNW_X86_EBP:
+		id = PERF_REG_X86_BP;
+		break;
+	case UNW_X86_ESP:
+		id = PERF_REG_X86_SP;
+		break;
+	case UNW_X86_EIP:
+		id = PERF_REG_X86_IP;
+		break;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return id;
+}
+#endif /* ARCH_X86_64 */

tools/perf/builtin-report.c

@@ -69,8 +69,8 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 
 	if ((sort__has_parent || symbol_conf.use_callchain)
 	    && sample->callchain) {
-		err = machine__resolve_callchain(machine, al->thread,
-						 sample->callchain, &parent);
+		err = machine__resolve_callchain(machine, evsel, al->thread,
+						 sample, &parent);
 		if (err)
 			return err;
 	}
@@ -140,8 +140,8 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 	struct hist_entry *he;
 
 	if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
-		err = machine__resolve_callchain(machine, al->thread,
-						 sample->callchain, &parent);
+		err = machine__resolve_callchain(machine, evsel, al->thread,
+						 sample, &parent);
 		if (err)
 			return err;
 	}
@@ -397,17 +397,17 @@ static int __cmd_report(struct perf_report *rep)
 		desc);
 	}
 
-	if (dump_trace) {
-		perf_session__fprintf_nr_events(session, stdout);
-		goto out_delete;
-	}
-
 	if (verbose > 3)
 		perf_session__fprintf(session, stdout);
 
 	if (verbose > 2)
 		perf_session__fprintf_dsos(session, stdout);
 
+	if (dump_trace) {
+		perf_session__fprintf_nr_events(session, stdout);
+		goto out_delete;
+	}
+
 	nr_samples = 0;
 	list_for_each_entry(pos, &session->evlist->entries, node) {
 		struct hists *hists = &pos->hists;

tools/perf/builtin-script.c

@@ -380,7 +380,7 @@ static void print_sample_bts(union perf_event *event,
 			printf(" ");
 		else
 			printf("\n");
-		perf_event__print_ip(event, sample, machine,
+		perf_evsel__print_ip(evsel, event, sample, machine,
 				     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
 				     PRINT_FIELD(SYMOFFSET));
 	}
@@ -422,7 +422,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 			printf(" ");
 		else
 			printf("\n");
-		perf_event__print_ip(event, sample, machine,
+		perf_evsel__print_ip(evsel, event, sample, machine,
 				     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
 				     PRINT_FIELD(SYMOFFSET));
 	}

tools/perf/builtin-top.c

@@ -783,8 +783,10 @@ static void perf_event__process_sample(struct perf_tool *tool,
 
 		if ((sort__has_parent || symbol_conf.use_callchain) &&
 		    sample->callchain) {
-			err = machine__resolve_callchain(machine, al.thread,
-							 sample->callchain, &parent);
+			err = machine__resolve_callchain(machine, evsel,
+							 al.thread, sample,
+							 &parent);
+
 			if (err)
 				return;
 		}

tools/perf/util/include/linux/compiler.h

@@ -10,5 +10,6 @@
 #endif
 
 #define __used		__attribute__((__unused__))
+#define __packed	__attribute__((__packed__))
 
 #endif

tools/perf/util/map.h

@@ -158,9 +158,12 @@ int machine__init(struct machine *self, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *self);
 void machine__delete(struct machine *self);
 
+struct perf_evsel;
+struct perf_sample;
 int machine__resolve_callchain(struct machine *machine,
+			       struct perf_evsel *evsel,
 			       struct thread *thread,
-			       struct ip_callchain *chain,
+			       struct perf_sample *sample,
 			       struct symbol **parent);
 int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
 				     u64 addr);

tools/perf/util/session.c

@@ -16,6 +16,7 @@
 #include "cpumap.h"
 #include "event-parse.h"
 #include "perf_regs.h"
+#include "unwind.h"
 
 static int perf_session__open(struct perf_session *self, bool force)
 {
@@ -289,10 +290,11 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
 	return bi;
 }
 
-int machine__resolve_callchain(struct machine *self,
-			       struct thread *thread,
-			       struct ip_callchain *chain,
-			       struct symbol **parent)
+static int machine__resolve_callchain_sample(struct machine *machine,
+					     struct thread *thread,
+					     struct ip_callchain *chain,
+					     struct symbol **parent)
+
 {
 	u8 cpumode = PERF_RECORD_MISC_USER;
 	unsigned int i;
@@ -317,11 +319,14 @@ int machine__resolve_callchain(struct machine *self,
 		if (ip >= PERF_CONTEXT_MAX) {
 			switch (ip) {
 			case PERF_CONTEXT_HV:
-				cpumode = PERF_RECORD_MISC_HYPERVISOR;	break;
+				cpumode = PERF_RECORD_MISC_HYPERVISOR;
+				break;
 			case PERF_CONTEXT_KERNEL:
-				cpumode = PERF_RECORD_MISC_KERNEL;	break;
+				cpumode = PERF_RECORD_MISC_KERNEL;
+				break;
 			case PERF_CONTEXT_USER:
-				cpumode = PERF_RECORD_MISC_USER;	break;
+				cpumode = PERF_RECORD_MISC_USER;
+				break;
 			default:
 				pr_debug("invalid callchain context: "
 					 "%"PRId64"\n", (s64) ip);
@@ -336,7 +341,7 @@ int machine__resolve_callchain(struct machine *self,
 		}
 
 		al.filtered = false;
-		thread__find_addr_location(thread, self, cpumode,
+		thread__find_addr_location(thread, machine, cpumode,
 					   MAP__FUNCTION, ip, &al, NULL);
 		if (al.sym != NULL) {
 			if (sort__has_parent && !*parent &&
@@ -355,6 +360,40 @@ int machine__resolve_callchain(struct machine *self,
 	return 0;
 }
 
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+	struct callchain_cursor *cursor = arg;
+	return callchain_cursor_append(cursor, entry->ip,
+				       entry->map, entry->sym);
+}
+
+int machine__resolve_callchain(struct machine *machine,
+			       struct perf_evsel *evsel,
+			       struct thread *thread,
+			       struct perf_sample *sample,
+			       struct symbol **parent)
+
+{
+	int ret;
+
+	callchain_cursor_reset(&callchain_cursor);
+
+	ret = machine__resolve_callchain_sample(machine, thread,
+						sample->callchain, parent);
+	if (ret)
+		return ret;
+
+	/* Can we do dwarf post unwind? */
+	if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
+	      (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
+		return 0;
+
+	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+				   thread, evsel->attr.sample_regs_user,
+				   sample);
+
+}
+
 static int process_event_synth_tracing_data_stub(union perf_event *event __used,
 						 struct perf_session *session __used)
 {
@@ -1533,9 +1572,9 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 	return NULL;
 }
 
-void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
-			  struct machine *machine, int print_sym,
-			  int print_dso, int print_symoffset)
+void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
+			  struct perf_sample *sample, struct machine *machine,
+			  int print_sym, int print_dso, int print_symoffset)
 {
 	struct addr_location al;
 	struct callchain_cursor_node *node;
@@ -1549,8 +1588,9 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
 
 	if (symbol_conf.use_callchain && sample->callchain) {
 
-		if (machine__resolve_callchain(machine, al.thread,
-						sample->callchain, NULL) != 0) {
+
+		if (machine__resolve_callchain(machine, evsel, al.thread,
+					       sample, NULL) != 0) {
 			if (verbose)
 				error("Failed to resolve callchain. Skipping\n");
 			return;

tools/perf/util/session.h

@@ -129,9 +129,9 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 					    unsigned int type);
 
-void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
-			  struct machine *machine, int print_sym,
-			  int print_dso, int print_symoffset);
+void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
+			  struct perf_sample *sample, struct machine *machine,
+			  int print_sym, int print_dso, int print_symoffset);
 
 int perf_session__cpu_bitmap(struct perf_session *session,
 			     const char *cpu_list, unsigned long *cpu_bitmap);

tools/perf/util/trace-event.h

@@ -77,6 +77,8 @@ void tracing_data_put(struct tracing_data *tdata);
 
 struct addr_location;
 
+struct perf_session;
+
 struct scripting_ops {
 	const char *name;
 	int (*start_script) (const char *script, int argc, const char **argv);

tools/perf/util/unwind.h

@@ -0,0 +1,34 @@
+#ifndef __UNWIND_H
+#define __UNWIND_H
+
+#include "types.h"
+#include "event.h"
+#include "symbol.h"
+
+struct unwind_entry {
+	struct map	*map;
+	struct symbol	*sym;
+	u64		ip;
+};
+
+typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
+
+#ifndef NO_LIBUNWIND_SUPPORT
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+			struct machine *machine,
+			struct thread *thread,
+			u64 sample_uregs,
+			struct perf_sample *data);
+int unwind__arch_reg_id(int regnum);
+#else
+static inline int
+unwind__get_entries(unwind_entry_cb_t cb __used, void *arg __used,
+		    struct machine *machine __used,
+		    struct thread *thread __used,
+		    u64 sample_uregs __used,
+		    struct perf_sample *data __used)
+{
+	return 0;
+}
+#endif /* NO_LIBUNWIND_SUPPORT */
+#endif /* __UNWIND_H */