perf unwind: Do not look just at the global callchain_param.record_mode

When setting up DWARF callchains on specific events, without using
'record' or 'trace' --call-graph, but instead doing it like:

	perf trace -e cycles/call-graph=dwarf/

The unwind__prepare_access() call in thread__insert_map() when we
process PERF_RECORD_MMAP(2) metadata events were not being performed,
precluding us from using per-event DWARF callchains, handling them just
when we asked for all events to be DWARF, using "--call-graph dwarf".

We do it in the PERF_RECORD_MMAP because we have to look at one of the
executable maps to figure out the executable type (64-bit, 32-bit) of
the DSO laid out in that mmap. Also to look at the architecture where
the perf.data file was recorded.

All this probably should be deferred to when we process a sample for
some thread that has callchains, so that we do this processing only for
the threads with samples, not for all of them.

For now, fix using DWARF on specific events.

Before:

  # perf trace --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1
  PING ::1(::1) 56 data bytes
  64 bytes from ::1: icmp_seq=1 ttl=64 time=0.048 ms

  --- ::1 ping statistics ---
  1 packets transmitted, 1 received, 0% packet loss, time 0ms
  rtt min/avg/max/mdev = 0.048/0.048/0.048/0.000 ms
     0.000 probe_libc:inet_pton:(7fe9597bb350))
  Problem processing probe_libc:inet_pton callchain, skipping...
  #

After:

  # perf trace --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1
  PING ::1(::1) 56 data bytes
  64 bytes from ::1: icmp_seq=1 ttl=64 time=0.060 ms

  --- ::1 ping statistics ---
  1 packets transmitted, 1 received, 0% packet loss, time 0ms
  rtt min/avg/max/mdev = 0.060/0.060/0.060/0.000 ms
       0.000 probe_libc:inet_pton:(7fd4aa930350))
                                         __inet_pton (inlined)
                                         gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
                                         __GI_getaddrinfo (inlined)
                                         [0xffffaa804e51af3f] (/usr/bin/ping)
                                         __libc_start_main (/usr/lib64/libc-2.26.so)
                                         [0xffffaa804e51b379] (/usr/bin/ping)
  #
  # perf trace --call-graph=dwarf --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1
  PING ::1(::1) 56 data bytes
  64 bytes from ::1: icmp_seq=1 ttl=64 time=0.057 ms

  --- ::1 ping statistics ---
  1 packets transmitted, 1 received, 0% packet loss, time 0ms
  rtt min/avg/max/mdev = 0.057/0.057/0.057/0.000 ms
       0.000 probe_libc:inet_pton:(7f9363b9e350))
                                         __inet_pton (inlined)
                                         gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
                                         __GI_getaddrinfo (inlined)
                                         [0xffffa9e8a14e0f3f] (/usr/bin/ping)
                                         __libc_start_main (/usr/lib64/libc-2.26.so)
                                         [0xffffa9e8a14e1379] (/usr/bin/ping)
  #
  # perf trace --call-graph=fp --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1
  PING ::1(::1) 56 data bytes
  64 bytes from ::1: icmp_seq=1 ttl=64 time=0.077 ms

  --- ::1 ping statistics ---
  1 packets transmitted, 1 received, 0% packet loss, time 0ms
  rtt min/avg/max/mdev = 0.077/0.077/0.077/0.000 ms
       0.000 probe_libc:inet_pton:(7f4947e1c350))
                                         __inet_pton (inlined)
                                         gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
                                         __GI_getaddrinfo (inlined)
                                         [0xffffaa716d88ef3f] (/usr/bin/ping)
                                         __libc_start_main (/usr/lib64/libc-2.26.so)
                                         [0xffffaa716d88f379] (/usr/bin/ping)
  #
  # perf trace --no-syscalls -e probe_libc:inet_pton/call-graph=fp/ ping -6 -c 1 ::1
  PING ::1(::1) 56 data bytes
  64 bytes from ::1: icmp_seq=1 ttl=64 time=0.078 ms

  --- ::1 ping statistics ---
  1 packets transmitted, 1 received, 0% packet loss, time 0ms
  rtt min/avg/max/mdev = 0.078/0.078/0.078/0.000 ms
       0.000 probe_libc:inet_pton:(7fa157696350))
                                         __GI___inet_pton (/usr/lib64/libc-2.26.so)
                                         getaddrinfo (/usr/lib64/libc-2.26.so)
                                         [0xffffa9ba39c74f40] (/usr/bin/ping)
  #
Acked-by: NNamhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrick Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/r/20180116182650.GE16107@kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-c2c.c

@@ -2390,9 +2390,10 @@ static int setup_callchain(struct perf_evlist *evlist)
 	enum perf_call_graph_mode mode = CALLCHAIN_NONE;
 
 	if ((sample_type & PERF_SAMPLE_REGS_USER) &&
-	    (sample_type & PERF_SAMPLE_STACK_USER))
+	    (sample_type & PERF_SAMPLE_STACK_USER)) {
 		mode = CALLCHAIN_DWARF;
-	else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+		dwarf_callchain_users = true;
+	} else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
 		mode = CALLCHAIN_LBR;
 	else if (sample_type & PERF_SAMPLE_CALLCHAIN)
 		mode = CALLCHAIN_FP;

tools/perf/builtin-report.c

@@ -338,9 +338,10 @@ static int report__setup_sample_type(struct report *rep)
 
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
 		if ((sample_type & PERF_SAMPLE_REGS_USER) &&
-		    (sample_type & PERF_SAMPLE_STACK_USER))
+		    (sample_type & PERF_SAMPLE_STACK_USER)) {
 			callchain_param.record_mode = CALLCHAIN_DWARF;
-		else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+			dwarf_callchain_users = true;
+		} else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
 			callchain_param.record_mode = CALLCHAIN_LBR;
 		else
 			callchain_param.record_mode = CALLCHAIN_FP;

tools/perf/builtin-script.c

@@ -2919,9 +2919,10 @@ static void script__setup_sample_type(struct perf_script *script)
 
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
 		if ((sample_type & PERF_SAMPLE_REGS_USER) &&
-		    (sample_type & PERF_SAMPLE_STACK_USER))
+		    (sample_type & PERF_SAMPLE_STACK_USER)) {
 			callchain_param.record_mode = CALLCHAIN_DWARF;
-		else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+			dwarf_callchain_users = true;
+		} else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
 			callchain_param.record_mode = CALLCHAIN_LBR;
 		else
 			callchain_param.record_mode = CALLCHAIN_FP;

tools/perf/tests/dwarf-unwind.c

@@ -173,6 +173,7 @@ int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unu
 	}
 
 	callchain_param.record_mode = CALLCHAIN_DWARF;
+	dwarf_callchain_users = true;
 
 	if (init_live_machine(machine)) {
 		pr_err("Could not init machine\n");

tools/perf/util/callchain.c

@@ -37,6 +37,15 @@ struct callchain_param callchain_param = {
 	CALLCHAIN_PARAM_DEFAULT
 };
 
+/*
+ * Are there any events usind DWARF callchains?
+ *
+ * I.e.
+ *
+ * -e cycles/call-graph=dwarf/
+ */
+bool dwarf_callchain_users;
+
 struct callchain_param callchain_param_default = {
 	CALLCHAIN_PARAM_DEFAULT
 };
@@ -265,6 +274,7 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
 			ret = 0;
 			param->record_mode = CALLCHAIN_DWARF;
 			param->dump_size = default_stack_dump_size;
+			dwarf_callchain_users = true;
 
 			tok = strtok_r(NULL, ",", &saveptr);
 			if (tok) {

tools/perf/util/callchain.h

@@ -89,6 +89,8 @@ enum chain_value {
 	CCVAL_COUNT,
 };
 
+extern bool dwarf_callchain_users;
+
 struct callchain_param {
 	bool			enabled;
 	enum perf_call_graph_mode record_mode;

tools/perf/util/unwind-libunwind-local.c

@@ -631,9 +631,8 @@ static unw_accessors_t accessors = {
 
 static int _unwind__prepare_access(struct thread *thread)
 {
-	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+	if (!dwarf_callchain_users)
 		return 0;
-
 	thread->addr_space = unw_create_addr_space(&accessors, 0);
 	if (!thread->addr_space) {
 		pr_err("unwind: Can't create unwind address space.\n");
@@ -646,17 +645,15 @@ static int _unwind__prepare_access(struct thread *thread)
 
 static void _unwind__flush_access(struct thread *thread)
 {
-	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+	if (!dwarf_callchain_users)
 		return;
-
 	unw_flush_cache(thread->addr_space, 0, 0);
 }
 
 static void _unwind__finish_access(struct thread *thread)
 {
-	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+	if (!dwarf_callchain_users)
 		return;
-
 	unw_destroy_addr_space(thread->addr_space);
 }