perf tools: Allow specifying proc-map-timeout in config file

The default timeout of 500ms for parsing /proc/<pid>/maps files is too
short for profiling many of our services.

This can be overridden by passing --proc-map-timeout to the relevant
command but it'd be nice to globally increase our default value.

This patch permits setting a different default with the
core.proc-map-timeout config file parameter.

Signed-off-by: Mark Drayton <mbd@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20181204203420.1683114-1-mbd@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-config.txt

@@ -199,6 +199,12 @@ colors.*::
 		Colors for headers in the output of a sub-commands (top, report).
 		Default values are 'white', 'blue'.
 
+core.*::
+	core.proc-map-timeout::
+		Sets a timeout (in milliseconds) for parsing /proc/<pid>/maps files.
+		Can be overridden by the --proc-map-timeout option on supported
+		subcommands. The default timeout is 500ms.
+
 tui.*, gtk.*::
 	Subcommands that can be configured here are 'top', 'report' and 'annotate'.
 	These values are booleans, for example:

tools/perf/builtin-kvm.c

@@ -1364,7 +1364,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 			"show events other than"
 			" HLT (x86 only) or Wait state (s390 only)"
 			" that take longer than duration usecs"),
-		OPT_UINTEGER(0, "proc-map-timeout", &kvm->opts.proc_map_timeout,
+		OPT_UINTEGER(0, "proc-map-timeout", &proc_map_timeout,
 				"per thread proc mmap processing timeout in ms"),
 		OPT_END()
 	};
@@ -1394,7 +1394,6 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	kvm->opts.target.uses_mmap = false;
 	kvm->opts.target.uid_str = NULL;
 	kvm->opts.target.uid = UINT_MAX;
-	kvm->opts.proc_map_timeout = 500;
 
 	symbol__init(NULL);
 	disable_buildid_cache();
@@ -1453,8 +1452,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	perf_session__set_id_hdr_size(kvm->session);
 	ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true);
 	machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
-				    kvm->evlist->threads, false,
-				    kvm->opts.proc_map_timeout, 1);
+				    kvm->evlist->threads, false, 1);
 	err = kvm_live_open_events(kvm);
 	if (err)
 		goto out;

tools/perf/builtin-record.c

@@ -867,8 +867,7 @@ static int record__synthesize_workload(struct record *rec, bool tail)
 	err = perf_event__synthesize_thread_map(&rec->tool, thread_map,
 						 process_synthesized_event,
 						 &rec->session->machines.host,
-						 rec->opts.sample_address,
-						 rec->opts.proc_map_timeout);
+						 rec->opts.sample_address);
 	thread_map__put(thread_map);
 	return err;
 }
@@ -1085,7 +1084,7 @@ static int record__synthesize(struct record *rec, bool tail)
 
 	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
 					    process_synthesized_event, opts->sample_address,
-					    opts->proc_map_timeout, 1);
+					    1);
 out:
 	return err;
 }
@@ -1783,7 +1782,6 @@ static struct record record = {
 			.uses_mmap   = true,
 			.default_per_cpu = true,
 		},
-		.proc_map_timeout     = 500,
 	},
 	.tool = {
 		.sample		= process_sample_event,
@@ -1913,7 +1911,7 @@ static struct option __record_options[] = {
 	parse_clockid),
 	OPT_STRING_OPTARG('S', "snapshot", &record.opts.auxtrace_snapshot_opts,
 			  "opts", "AUX area tracing Snapshot Mode", ""),
-	OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
+	OPT_UINTEGER(0, "proc-map-timeout", &proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
 	OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces,
 		    "Record namespaces events"),

tools/perf/builtin-top.c

@@ -1096,7 +1096,6 @@ static int __cmd_top(struct perf_top *top)
 
 	machine__synthesize_threads(&top->session->machines.host, &opts->target,
 				    top->evlist->threads, false,
-				    opts->proc_map_timeout,
 				    top->nr_threads_synthesize);
 
 	if (top->nr_threads_synthesize > 1)
@@ -1256,7 +1255,6 @@ int cmd_top(int argc, const char **argv)
 			.target		= {
 				.uses_mmap   = true,
 			},
-			.proc_map_timeout    = 500,
 			/*
 			 * FIXME: This will lose PERF_RECORD_MMAP and other metadata
 			 * when we pause, fix that and reenable. Probably using a
@@ -1369,7 +1367,7 @@ int cmd_top(int argc, const char **argv)
 	OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
 		   "width[,width...]",
 		   "don't try to adjust column width, use these fixed values"),
-	OPT_UINTEGER(0, "proc-map-timeout", &opts->proc_map_timeout,
+	OPT_UINTEGER(0, "proc-map-timeout", &proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
 	OPT_CALLBACK_NOOPT('b', "branch-any", &opts->branch_stack,
 		     "branch any", "sample any taken branches",

tools/perf/builtin-trace.c

@@ -1264,7 +1264,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 
 	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
 					    evlist->threads, trace__tool_process, false,
-					    trace->opts.proc_map_timeout, 1);
+					    1);
 out:
 	if (err)
 		symbol__exit();
@@ -3393,7 +3393,6 @@ int cmd_trace(int argc, const char **argv)
 			.user_interval = ULLONG_MAX,
 			.no_buffering  = true,
 			.mmap_pages    = UINT_MAX,
-			.proc_map_timeout  = 500,
 		},
 		.output = stderr,
 		.show_comm = true,
@@ -3464,7 +3463,7 @@ int cmd_trace(int argc, const char **argv)
 		     "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
 	OPT_BOOLEAN(0, "print-sample", &trace.print_sample,
 			"print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info, for debugging"),
-	OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
+	OPT_UINTEGER(0, "proc-map-timeout", &proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
 	OPT_CALLBACK('G', "cgroup", &trace, "name", "monitor event in cgroup name only",
 		     trace__parse_cgroups),

tools/perf/perf.h

@@ -82,7 +82,6 @@ struct record_opts {
 	bool         use_clockid;
 	clockid_t    clockid;
 	u64          clockid_res_ns;
-	unsigned int proc_map_timeout;
 	int	     nr_cblocks;
 };
 

tools/perf/tests/code-reading.c

@@ -599,7 +599,7 @@ static int do_test_code_reading(bool try_kcore)
 	}
 
 	ret = perf_event__synthesize_thread_map(NULL, threads,
-						perf_event__process, machine, false, 500);
+						perf_event__process, machine, false);
 	if (ret < 0) {
 		pr_debug("perf_event__synthesize_thread_map failed\n");
 		goto out_err;

tools/perf/tests/dwarf-unwind.c

@@ -34,7 +34,7 @@ static int init_live_machine(struct machine *machine)
 	pid_t pid = getpid();
 
 	return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
-						  mmap_handler, machine, true, 500);
+						  mmap_handler, machine, true);
 }
 
 /*

tools/perf/tests/mmap-thread-lookup.c

@@ -132,7 +132,7 @@ static int synth_all(struct machine *machine)
 {
 	return perf_event__synthesize_threads(NULL,
 					      perf_event__process,
-					      machine, 0, 500, 1);
+					      machine, 0, 1);
 }
 
 static int synth_process(struct machine *machine)
@@ -144,7 +144,7 @@ static int synth_process(struct machine *machine)
 
 	err = perf_event__synthesize_thread_map(NULL, map,
 						perf_event__process,
-						machine, 0, 500);
+						machine, 0);
 
 	thread_map__put(map);
 	return err;

tools/perf/util/config.c

@@ -14,6 +14,7 @@
 #include "util.h"
 #include "cache.h"
 #include <subcmd/exec-cmd.h>
+#include "util/event.h"  /* proc_map_timeout */
 #include "util/hist.h"  /* perf_hist_config */
 #include "util/llvm-utils.h"   /* perf_llvm_config */
 #include "config.h"
@@ -419,6 +420,9 @@ static int perf_buildid_config(const char *var, const char *value)
 static int perf_default_core_config(const char *var __maybe_unused,
 				    const char *value __maybe_unused)
 {
+	if (!strcmp(var, "core.proc-map-timeout"))
+		proc_map_timeout = strtoul(value, NULL, 10);
+
 	/* Add other config variables here. */
 	return 0;
 }

tools/perf/util/event.c

@@ -25,6 +25,8 @@
 #include "asm/bug.h"
 #include "stat.h"
 
+#define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500
+
 static const char *perf_event__names[] = {
 	[0]					= "TOTAL",
 	[PERF_RECORD_MMAP]			= "MMAP",
@@ -72,6 +74,8 @@ static const char *perf_ns__names[] = {
 	[CGROUP_NS_INDEX]	= "cgroup",
 };
 
+unsigned int proc_map_timeout = DEFAULT_PROC_MAP_PARSE_TIMEOUT;
+
 const char *perf_event__name(unsigned int id)
 {
 	if (id >= ARRAY_SIZE(perf_event__names))
@@ -323,8 +327,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       pid_t pid, pid_t tgid,
 				       perf_event__handler_t process,
 				       struct machine *machine,
-				       bool mmap_data,
-				       unsigned int proc_map_timeout)
+				       bool mmap_data)
 {
 	char filename[PATH_MAX];
 	FILE *fp;
@@ -521,8 +524,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 				      perf_event__handler_t process,
 				      struct perf_tool *tool,
 				      struct machine *machine,
-				      bool mmap_data,
-				      unsigned int proc_map_timeout)
+				      bool mmap_data)
 {
 	char filename[PATH_MAX];
 	DIR *tasks;
@@ -548,8 +550,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		 */
 		if (pid == tgid &&
 		    perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-						       process, machine, mmap_data,
-						       proc_map_timeout))
+						       process, machine, mmap_data))
 			return -1;
 
 		return 0;
@@ -598,7 +599,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		if (_pid == pid) {
 			/* process the parent's maps too */
 			rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-						process, machine, mmap_data, proc_map_timeout);
+						process, machine, mmap_data);
 			if (rc)
 				break;
 		}
@@ -612,8 +613,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
 				      struct machine *machine,
-				      bool mmap_data,
-				      unsigned int proc_map_timeout)
+				      bool mmap_data)
 {
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	union perf_event *namespaces_event;
@@ -643,7 +643,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 					       fork_event, namespaces_event,
 					       thread_map__pid(threads, thread), 0,
 					       process, tool, machine,
-					       mmap_data, proc_map_timeout)) {
+					       mmap_data)) {
 			err = -1;
 			break;
 		}
@@ -669,7 +669,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 						       fork_event, namespaces_event,
 						       comm_event->comm.pid, 0,
 						       process, tool, machine,
-						       mmap_data, proc_map_timeout)) {
+						       mmap_data)) {
 				err = -1;
 				break;
 			}
@@ -690,7 +690,6 @@ static int __perf_event__synthesize_threads(struct perf_tool *tool,
 					    perf_event__handler_t process,
 					    struct machine *machine,
 					    bool mmap_data,
-					    unsigned int proc_map_timeout,
 					    struct dirent **dirent,
 					    int start,
 					    int num)
@@ -734,8 +733,7 @@ static int __perf_event__synthesize_threads(struct perf_tool *tool,
 		 */
 		__event__synthesize_thread(comm_event, mmap_event, fork_event,
 					   namespaces_event, pid, 1, process,
-					   tool, machine, mmap_data,
-					   proc_map_timeout);
+					   tool, machine, mmap_data);
 	}
 	err = 0;
 
@@ -755,7 +753,6 @@ struct synthesize_threads_arg {
 	perf_event__handler_t process;
 	struct machine *machine;
 	bool mmap_data;
-	unsigned int proc_map_timeout;
 	struct dirent **dirent;
 	int num;
 	int start;
@@ -767,7 +764,7 @@ static void *synthesize_threads_worker(void *arg)
 
 	__perf_event__synthesize_threads(args->tool, args->process,
 					 args->machine, args->mmap_data,
-					 args->proc_map_timeout, args->dirent,
+					 args->dirent,
 					 args->start, args->num);
 	return NULL;
 }
@@ -776,7 +773,6 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
 				   struct machine *machine,
 				   bool mmap_data,
-				   unsigned int proc_map_timeout,
 				   unsigned int nr_threads_synthesize)
 {
 	struct synthesize_threads_arg *args = NULL;
@@ -806,7 +802,6 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (thread_nr <= 1) {
 		err = __perf_event__synthesize_threads(tool, process,
 						       machine, mmap_data,
-						       proc_map_timeout,
 						       dirent, base, n);
 		goto free_dirent;
 	}
@@ -828,7 +823,6 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 		args[i].process = process;
 		args[i].machine = machine;
 		args[i].mmap_data = mmap_data;
-		args[i].proc_map_timeout = proc_map_timeout;
 		args[i].dirent = dirent;
 	}
 	for (i = 0; i < m; i++) {

tools/perf/util/event.h

@@ -669,8 +669,7 @@ typedef int (*perf_event__handler_t)(struct perf_tool *tool,
 int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
-				      struct machine *machine, bool mmap_data,
-				      unsigned int proc_map_timeout);
+				      struct machine *machine, bool mmap_data);
 int perf_event__synthesize_thread_map2(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
@@ -682,7 +681,6 @@ int perf_event__synthesize_cpu_map(struct perf_tool *tool,
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
 				   struct machine *machine, bool mmap_data,
-				   unsigned int proc_map_timeout,
 				   unsigned int nr_threads_synthesize);
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
@@ -797,8 +795,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       pid_t pid, pid_t tgid,
 				       perf_event__handler_t process,
 				       struct machine *machine,
-				       bool mmap_data,
-				       unsigned int proc_map_timeout);
+				       bool mmap_data);
 
 int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
 				       perf_event__handler_t process,
@@ -829,5 +826,6 @@ int perf_event_paranoid(void);
 
 extern int sysctl_perf_event_max_stack;
 extern int sysctl_perf_event_max_contexts_per_stack;
+extern unsigned int proc_map_timeout;
 
 #endif /* __PERF_RECORD_H */

tools/perf/util/machine.c

@@ -2493,15 +2493,13 @@ int machines__for_each_thread(struct machines *machines,
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,
 				  perf_event__handler_t process, bool data_mmap,
-				  unsigned int proc_map_timeout,
 				  unsigned int nr_threads_synthesize)
 {
 	if (target__has_task(target))
-		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap, proc_map_timeout);
+		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
 	else if (target__has_cpu(target))
 		return perf_event__synthesize_threads(tool, process,
 						      machine, data_mmap,
-						      proc_map_timeout,
 						      nr_threads_synthesize);
 	/* command specified */
 	return 0;

tools/perf/util/machine.h

@@ -250,17 +250,14 @@ int machines__for_each_thread(struct machines *machines,
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,
 				  perf_event__handler_t process, bool data_mmap,
-				  unsigned int proc_map_timeout,
 				  unsigned int nr_threads_synthesize);
 static inline
 int machine__synthesize_threads(struct machine *machine, struct target *target,
 				struct thread_map *threads, bool data_mmap,
-				unsigned int proc_map_timeout,
 				unsigned int nr_threads_synthesize)
 {
 	return __machine__synthesize_threads(machine, NULL, target, threads,
 					     perf_event__process, data_mmap,
-					     proc_map_timeout,
 					     nr_threads_synthesize);
 }