[PATCH v2] perf trace: Speed up startup time by bypassing the creation of kernel maps

[Howard Chu <howardchu95@gmail.com>]

If perf trace isn't run with '--call-graph' and '--kernel-syscall-graph'
options, e.g.

sudo ./perf trace --call-graph fp --kernel-syscall-graph -a

there is no need for creating kernel maps.

before:

perf $ time sudo ./perf trace -- sleep 1
         ? (         ): sleep/3462908  ... [continued]: execve())                                           = 0
	 ...
  1001.459 (         ): sleep/3463166 exit_group()                                                          = ?

real    0m2.834s
user    0m0.011s
sys     0m0.012s

after:

perf $ time sudo ./perf trace -- sleep 1
         ? (         ): sleep/3459948  ... [continued]: execve())                                           = 0
	 ...
  1001.471 (         ): 3459948 exit_group()                                                          = ?

real    0m1.810s
user    0m0.008s
sys     0m0.015s

I also want to express my gratitude to Krzysztof Łopatowski—his
profiling of the perf trace [1] inspired this patch. I'm not sure why
the discussion stalled, and I apologize for not being able to answer his
questions.

[1]: https://lore.kernel.org/linux-perf-users/CAOQCU67EsHyw_FsqGbRuityahZTSAtWzffU=hLUJ7K=aZ=1hhA@mail.gmail.com/

Cc: "Krzysztof Łopatowski" <krzysztof.m.lopatowski@gmail.com>
Suggested-by: "Krzysztof Łopatowski" <krzysztof.m.lopatowski@gmail.com>
Signed-off-by: Howard Chu <howardchu95@gmail.com>
---
Change in v2:
* Add a Suggested-by tag for Krzysztof

 tools/perf/builtin-buildid-list.c     | 2 +-
 tools/perf/builtin-trace.c            | 2 +-
 tools/perf/tests/code-reading.c       | 2 +-
 tools/perf/tests/dlfilter-test.c      | 2 +-
 tools/perf/tests/dwarf-unwind.c       | 2 +-
 tools/perf/tests/mmap-thread-lookup.c | 2 +-
 tools/perf/tests/symbols.c            | 2 +-
 tools/perf/util/machine.c             | 6 +++---
 tools/perf/util/machine.h             | 2 +-
 tools/perf/util/probe-event.c         | 2 +-
 10 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 52dfacaff8e3..357201d8ef0c 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -47,7 +47,7 @@ static void buildid__show_kernel_maps(void)
 {
 	struct machine *machine;
 
-	machine = machine__new_host();
+	machine = machine__new_host(true);
 	machine__for_each_kernel_map(machine, buildid__map_cb, NULL);
 	machine__delete(machine);
 }
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f55a8a6481f2..39f23ce39842 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1963,7 +1963,7 @@ static int trace__symbols_init(struct trace *trace, struct evlist *evlist)
 	if (err)
 		return err;
 
-	trace->host = machine__new_host();
+	trace->host = machine__new_host(callchain_param.enabled && trace->kernel_syscallchains);
 	if (trace->host == NULL)
 		return -ENOMEM;
 
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index cf6edbe697b2..17c7b9f95532 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -654,7 +654,7 @@ static int do_test_code_reading(bool try_kcore)
 
 	pid = getpid();
 
-	machine = machine__new_host();
+	machine = machine__new_host(true);
 	machine->env = &perf_env;
 
 	ret = machine__create_kernel_maps(machine);
diff --git a/tools/perf/tests/dlfilter-test.c b/tools/perf/tests/dlfilter-test.c
index 54f59d1246bc..11f70ebabacf 100644
--- a/tools/perf/tests/dlfilter-test.c
+++ b/tools/perf/tests/dlfilter-test.c
@@ -352,7 +352,7 @@ static int test__dlfilter_test(struct test_data *td)
 		return test_result("Failed to find program symbols", TEST_FAIL);
 
 	pr_debug("Creating new host machine structure\n");
-	td->machine = machine__new_host();
+	td->machine = machine__new_host(true);
 	td->machine->env = &perf_env;
 
 	td->fd = creat(td->perf_data_file_name, 0644);
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 4803ab2d97ba..b76712f68403 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -203,7 +203,7 @@ noinline int test__dwarf_unwind(struct test_suite *test __maybe_unused,
 	struct thread *thread;
 	int err = -1;
 
-	machine = machine__new_host();
+	machine = machine__new_host(true);
 	if (!machine) {
 		pr_err("Could not get machine\n");
 		return -1;
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index ddd1da9a4ba9..194b5affaa41 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -167,7 +167,7 @@ static int mmap_events(synth_cb synth)
 	 */
 	TEST_ASSERT_VAL("failed to create threads", !threads_create());
 
-	machine = machine__new_host();
+	machine = machine__new_host(true);
 
 	dump_trace = verbose > 1 ? 1 : 0;
 
diff --git a/tools/perf/tests/symbols.c b/tools/perf/tests/symbols.c
index ee20a366f32f..6b22a451211a 100644
--- a/tools/perf/tests/symbols.c
+++ b/tools/perf/tests/symbols.c
@@ -19,7 +19,7 @@ struct test_info {
 
 static int init_test_info(struct test_info *ti)
 {
-	ti->machine = machine__new_host();
+	ti->machine = machine__new_host(true);
 	if (!ti->machine) {
 		pr_debug("machine__new_host() failed!\n");
 		return TEST_FAIL;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 55d4977b9913..b1828e3922f2 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -125,14 +125,14 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	return 0;
 }
 
-struct machine *machine__new_host(void)
+struct machine *machine__new_host(bool create_kmaps)
 {
 	struct machine *machine = malloc(sizeof(*machine));
 
 	if (machine != NULL) {
 		machine__init(machine, "", HOST_KERNEL_ID);
 
-		if (machine__create_kernel_maps(machine) < 0)
+		if (create_kmaps && machine__create_kernel_maps(machine) < 0)
 			goto out_delete;
 
 		machine->env = &perf_env;
@@ -146,7 +146,7 @@ struct machine *machine__new_host(void)
 
 struct machine *machine__new_kallsyms(void)
 {
-	struct machine *machine = machine__new_host();
+	struct machine *machine = machine__new_host(true);
 	/*
 	 * FIXME:
 	 * 1) We should switch to machine__load_kallsyms(), i.e. not explicitly
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index ae3e5542d57d..e6faf8cd06e7 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -163,7 +163,7 @@ struct thread *machine__findnew_guest_code(struct machine *machine, pid_t pid);
 void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size);
 void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
-struct machine *machine__new_host(void);
+struct machine *machine__new_host(bool create_kmaps);
 struct machine *machine__new_kallsyms(void);
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *machine);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 307ad6242a4e..6b5b5542f454 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -94,7 +94,7 @@ int init_probe_symbol_maps(bool user_only)
 	if (symbol_conf.vmlinux_name)
 		pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
 
-	host_machine = machine__new_host();
+	host_machine = machine__new_host(true);
 	if (!host_machine) {
 		pr_debug("machine__new_host() failed.\n");
 		symbol__exit();
-- 
2.45.2