powerpc/perf: Adjust callchain based on DWARF debug info

powerpc/perf: Adjust callchain based on DWARF debug info

When saving the callchain on Power, the kernel conservatively saves excess entries in the callchain. A few of these entries are needed in some cases but not others. We should use the DWARF debug information to determine when the entries are needed.

Eg: the value in the link register (LR) is needed only when it holds the return address of a function. At other times it must be ignored.

If the unnecessary entries are not ignored, we end up with duplicate arcs in the call-graphs.

Use the DWARF debug information to determine if any callchain entries should be ignored when building call-graphs.

Callgraph before the patch:

    14.67%          2234  sprintft  libc-2.18.so       [.] __random
            |
            --- __random
               |
               |--61.12%-- __random
               |          |
               |          |--97.15%-- rand
               |          |          do_my_sprintf
               |          |          main
               |          |          generic_start_main.isra.0
               |          |          __libc_start_main
               |          |          0x0
               |          |
               |           --2.85%-- do_my_sprintf
               |                     main
               |                     generic_start_main.isra.0
               |                     __libc_start_main
               |                     0x0
               |
                --38.88%-- rand
                          |
                          |--94.01%-- rand
                          |          do_my_sprintf
                          |          main
                          |          generic_start_main.isra.0
                          |          __libc_start_main
                          |          0x0
                          |
                           --5.99%-- do_my_sprintf
                                     main
                                     generic_start_main.isra.0
                                     __libc_start_main
                                     0x0

Callgraph after the patch:

    14.67%          2234  sprintft  libc-2.18.so       [.] __random
            |
            --- __random
               |
               |--95.93%-- rand
               |          do_my_sprintf
               |          main
               |          generic_start_main.isra.0
               |          __libc_start_main
               |          0x0
               |
                --4.07%-- do_my_sprintf
                          main
                          generic_start_main.isra.0
                          __libc_start_main
                          0x0

TODO: For split-debug info objects like glibc, we can only determine
the call-frame-address only when both .eh_frame and .debug_info sections are available. We should be able to determin the CFA even without the .eh_frame section.

Fix suggested by Anton Blanchard.

Thanks to valuable input on DWARF debug information from Ulrich Weigand.

---
Changelog[v3]
[Jiri Olsa] Rename function to arch_skip_callchain_idx() to be
consistent with behavior.
[Jiri Olsa] Add '__maybe_unused' tags for unused parameters.

Changelog[v2]:
- Add missing dwfl_end()
- Fix merge conflicts due to some unwind code

 tools/perf/arch/powerpc/Makefile                  |    1 +
 tools/perf/arch/powerpc/util/skip-callchain-idx.c |  266 +++++++++++++++++++++
 tools/perf/config/Makefile                        |    4 +
 tools/perf/util/callchain.h                       |   13 +
 tools/perf/util/machine.c                         |   16 +-
 5 files changed, 298 insertions(+), 2 deletions(-)
 create mode 100644 tools/perf/arch/powerpc/util/skip-callchain-idx.c

index 744e629..b92219b 100644
@@ -3,3 +3,4 @@ PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o

index 729bbdf..8d1417d 100644
@@ -48,6 +48,10 @@ ifneq ($(ARCH),$(filter $(ARCH),x86 arm))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
+ifeq ($(ARCH),powerpc)
+  CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
+endif
+
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
 else

index bde2b0c..5176599 100644
@@ -165,4 +165,17 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp
 
 extern const char record_callchain_help[];
 int parse_callchain_report_opt(const char *arg);
+
+#ifdef HAVE_SKIP_CALLCHAIN_IDX
+extern int arch_skip_callchain_idx(struct machine *machine,
+			struct thread *thread, struct ip_callchain *chain);
+#else
+static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused,
+			struct thread *thread __maybe_unused,
+			struct ip_callchain *chain __maybe_unused)
+{
+	return -1;
+}
+#endif
+
 #endif	/* __PERF_CALLCHAIN_H */

index 7409ac8..bc93279 100644
@@ -1290,6 +1290,7 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 	int chain_nr = min(max_stack, (int)chain->nr);
 	int i;
 	int err;
+	int skip_slot;
 
 	callchain_cursor_reset(&callchain_cursor);
 

@@ -1298,14 +1299,25 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 		return 0;
 	}
 
+	/*
+	 * Based on DWARF debug information, some architectures skip
+	 * some of the callchain entries saved by the kernel.
+	 */
+	skip_slot = arch_skip_callchain_idx(machine, thread, chain);
+
 	for (i = 0; i < chain_nr; i++) {
 		u64 ip;
 		struct addr_location al;
 
-		if (callchain_param.order == ORDER_CALLEE)
+		if (callchain_param.order == ORDER_CALLEE) {
+			if (i == skip_slot)
+				continue;
 			ip = chain->ips[i];
-		else
+		} else {
+			if ((int)(chain->nr - i - 1) == skip_slot)
+				continue;
 			ip = chain->ips[chain->nr - i - 1];
+		}
 
 		if (ip >= PERF_CONTEXT_MAX) {
 			switch (ip) {

1.7.9.5