Merge tag 'perf-core-for-mingo-5.1-20190311' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core improvements and fixes from Arnaldo:

kernel:

  Stephane Eranian :

  - Restore mmap record type correctly when handling PERF_RECORD_MMAP2
    events, as the same template is used for all the threads interested
    in mmap events, some may want just PERF_RECORD_MMAP, while some
    may want the extra info in MMAP2 records.

perf probe:

  Adrian Hunter:

  - Fix getting the kernel map, because since changes related to x86 PTI
    entry trampolines handling, there are more than one kernel map.

perf script:

  Andi Kleen:

  - Support insn output for normal samples, i.e.:

    perf script -F ip,sym,insn --xed

    Will fetch the sample IP from the thread address space and feed it
    to Intel's XED disassembler, producing lines such as:

      ffffffffa4068804 native_write_msr            wrmsr
      ffffffffa415b95e __hrtimer_next_event_base   movq  0x18(%rax), %rdx

    That match 'perf annotate's output.

  - Make the --cpu filter apply to  PERF_RECORD_COMM/FORK/... events, in
    addition to PERF_RECORD_SAMPLE.

perf report:

  - Add a new --samples option to save a small random number of samples
    per hist entry, using a reservoir technique to select a representative
    number of samples.

    Then allow browsing the samples using 'perf script' as part of the hist
    entry context menu. This automatically adds the right filters, so only
    the thread or CPU of the sample is displayed. Then we use less' search
    functionality to directly jump to the time stamp of the selected sample.

    It uses different menus for assembler and source display.  Assembler
    needs xed installed and source needs debuginfo.

  - Fix the UI browser scripts pop up menu when there are many scripts
    available.

perf report:

  Andi Kleen:

  - Add 'time' sort option. E.g.:

    % perf report --sort time,overhead,symbol --time-quantum 1ms --stdio
    ...
         0.67%  277061.87300  [.] _dl_start
         0.50%  277061.87300  [.] f1
         0.50%  277061.87300  [.] f2
         0.33%  277061.87300  [.] main
         0.29%  277061.87300  [.] _dl_lookup_symbol_x
         0.29%  277061.87300  [.] dl_main
         0.29%  277061.87300  [.] do_lookup_x
         0.17%  277061.87300  [.] _dl_debug_initialize
         0.17%  277061.87300  [.] _dl_init_paths
         0.08%  277061.87300  [.] check_match
         0.04%  277061.87300  [.] _dl_count_modids
         1.33%  277061.87400  [.] f1
         1.33%  277061.87400  [.] f2
         1.33%  277061.87400  [.] main
         1.17%  277061.87500  [.] main
         1.08%  277061.87500  [.] f1
         1.08%  277061.87500  [.] f2
         1.00%  277061.87600  [.] main
         0.83%  277061.87600  [.] f1
         0.83%  277061.87600  [.] f2
         1.00%  277061.87700  [.] main

tools headers:

  Arnaldo Carvalho de Melo:

  - Update x86's syscall_64.tbl, no change in tools/perf behaviour.

  -  Sync copies asm-generic/unistd.h and linux/in with the kernel sources.

perf data:

  Jiri Olsa:

  - Prep work to support having perf.data stored as a directory, with one
    file per CPU, that ultimately will allow having one ring buffer reading
    thread per CPU.

Vendor events:

  Martin Liška:

  - perf PMU events for AMD Family 17h.

perf script python:

  Tony Jones:

  - Add python3 support for the remaining Intel PT related scripts, with
    these we should have a clean build of perf with python3 while still
    supporting the build with python2.

libbpf:

  Arnaldo Carvalho de Melo:

  - Fix the build on uCLibc, adding the missing stdarg.h since we use
    va_list in one typedef.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 78 insertions, 33 deletions

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 53f78cf3113f..2f93d60c5a17 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -29,10 +29,12 @@
 #include "util/time-utils.h"
 #include "util/path.h"
 #include "print_binary.h"
+#include "archinsn.h"
 #include <linux/bitmap.h>
 #include <linux/kernel.h>
 #include <linux/stringify.h>
 #include <linux/time64.h>
+#include <sys/utsname.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
 #include "util/dump-insn.h"
@@ -58,11 +60,11 @@ static bool			no_callchain;
 static bool			latency_format;
 static bool			system_wide;
 static bool			print_flags;
-static bool			nanosecs;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 static struct perf_stat_config	stat_config;
 static int			max_blocks;
+static bool			native_arch;
 
 unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
 
@@ -688,7 +690,7 @@ static int perf_sample__fprintf_start(struct perf_sample *sample,
 		secs = nsecs / NSEC_PER_SEC;
 		nsecs -= secs * NSEC_PER_SEC;
 
-		if (nanosecs)
+		if (symbol_conf.nanosecs)
 			printed += fprintf(fp, "%5lu.%09llu: ", secs, nsecs);
 		else {
 			char sample_time[32];
@@ -1227,6 +1229,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 	return len + dlen;
 }
 
+__weak void arch_fetch_insn(struct perf_sample *sample __maybe_unused,
+			    struct thread *thread __maybe_unused,
+			    struct machine *machine __maybe_unused)
+{
+}
+
 static int perf_sample__fprintf_insn(struct perf_sample *sample,
 				     struct perf_event_attr *attr,
 				     struct thread *thread,
@@ -1234,9 +1242,12 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
 {
 	int printed = 0;
 
+	if (sample->insn_len == 0 && native_arch)
+		arch_fetch_insn(sample, thread, machine);
+
 	if (PRINT_FIELD(INSNLEN))
 		printed += fprintf(fp, " ilen: %d", sample->insn_len);
-	if (PRINT_FIELD(INSN)) {
+	if (PRINT_FIELD(INSN) && sample->insn_len) {
 		int i;
 
 		printed += fprintf(fp, " insn:");
@@ -1922,6 +1933,13 @@ static int cleanup_scripting(void)
 	return scripting_ops ? scripting_ops->stop_script() : 0;
 }
 
+static bool filter_cpu(struct perf_sample *sample)
+{
+	if (cpu_list)
+		return !test_bit(sample->cpu, cpu_bitmap);
+	return false;
+}
+
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
@@ -1956,7 +1974,7 @@ static int process_sample_event(struct perf_tool *tool,
 	if (al.filtered)
 		goto out_put;
 
-	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+	if (filter_cpu(sample))
 		goto out_put;
 
 	if (scripting_ops)
@@ -2041,9 +2059,11 @@ static int process_comm_event(struct perf_tool *tool,
 		sample->tid = event->comm.tid;
 		sample->pid = event->comm.pid;
 	}
-	perf_sample__fprintf_start(sample, thread, evsel,
+	if (!filter_cpu(sample)) {
+		perf_sample__fprintf_start(sample, thread, evsel,
 				   PERF_RECORD_COMM, stdout);
-	perf_event__fprintf(event, stdout);
+		perf_event__fprintf(event, stdout);
+	}
 	ret = 0;
 out:
 	thread__put(thread);
@@ -2077,9 +2097,11 @@ static int process_namespaces_event(struct perf_tool *tool,
 		sample->tid = event->namespaces.tid;
 		sample->pid = event->namespaces.pid;
 	}
-	perf_sample__fprintf_start(sample, thread, evsel,
-				   PERF_RECORD_NAMESPACES, stdout);
-	perf_event__fprintf(event, stdout);
+	if (!filter_cpu(sample)) {
+		perf_sample__fprintf_start(sample, thread, evsel,
+					   PERF_RECORD_NAMESPACES, stdout);
+		perf_event__fprintf(event, stdout);
+	}
 	ret = 0;
 out:
 	thread__put(thread);
@@ -2111,9 +2133,11 @@ static int process_fork_event(struct perf_tool *tool,
 		sample->tid = event->fork.tid;
 		sample->pid = event->fork.pid;
 	}
-	perf_sample__fprintf_start(sample, thread, evsel,
-				   PERF_RECORD_FORK, stdout);
-	perf_event__fprintf(event, stdout);
+	if (!filter_cpu(sample)) {
+		perf_sample__fprintf_start(sample, thread, evsel,
+					   PERF_RECORD_FORK, stdout);
+		perf_event__fprintf(event, stdout);
+	}
 	thread__put(thread);
 
 	return 0;
@@ -2141,9 +2165,11 @@ static int process_exit_event(struct perf_tool *tool,
 		sample->tid = event->fork.tid;
 		sample->pid = event->fork.pid;
 	}
-	perf_sample__fprintf_start(sample, thread, evsel,
-				   PERF_RECORD_EXIT, stdout);
-	perf_event__fprintf(event, stdout);
+	if (!filter_cpu(sample)) {
+		perf_sample__fprintf_start(sample, thread, evsel,
+					   PERF_RECORD_EXIT, stdout);
+		perf_event__fprintf(event, stdout);
+	}
 
 	if (perf_event__process_exit(tool, event, sample, machine) < 0)
 		err = -1;
@@ -2177,9 +2203,11 @@ static int process_mmap_event(struct perf_tool *tool,
 		sample->tid = event->mmap.tid;
 		sample->pid = event->mmap.pid;
 	}
-	perf_sample__fprintf_start(sample, thread, evsel,
-				   PERF_RECORD_MMAP, stdout);
-	perf_event__fprintf(event, stdout);
+	if (!filter_cpu(sample)) {
+		perf_sample__fprintf_start(sample, thread, evsel,
+					   PERF_RECORD_MMAP, stdout);
+		perf_event__fprintf(event, stdout);
+	}
 	thread__put(thread);
 	return 0;
 }
@@ -2209,9 +2237,11 @@ static int process_mmap2_event(struct perf_tool *tool,
 		sample->tid = event->mmap2.tid;
 		sample->pid = event->mmap2.pid;
 	}
-	perf_sample__fprintf_start(sample, thread, evsel,
-				   PERF_RECORD_MMAP2, stdout);
-	perf_event__fprintf(event, stdout);
+	if (!filter_cpu(sample)) {
+		perf_sample__fprintf_start(sample, thread, evsel,
+					   PERF_RECORD_MMAP2, stdout);
+		perf_event__fprintf(event, stdout);
+	}
 	thread__put(thread);
 	return 0;
 }
@@ -2236,9 +2266,11 @@ static int process_switch_event(struct perf_tool *tool,
 		return -1;
 	}
 
-	perf_sample__fprintf_start(sample, thread, evsel,
-				   PERF_RECORD_SWITCH, stdout);
-	perf_event__fprintf(event, stdout);
+	if (!filter_cpu(sample)) {
+		perf_sample__fprintf_start(sample, thread, evsel,
+					   PERF_RECORD_SWITCH, stdout);
+		perf_event__fprintf(event, stdout);
+	}
 	thread__put(thread);
 	return 0;
 }
@@ -2259,9 +2291,11 @@ process_lost_event(struct perf_tool *tool,
 	if (thread == NULL)
 		return -1;
 
-	perf_sample__fprintf_start(sample, thread, evsel,
-				   PERF_RECORD_LOST, stdout);
-	perf_event__fprintf(event, stdout);
+	if (!filter_cpu(sample)) {
+		perf_sample__fprintf_start(sample, thread, evsel,
+					   PERF_RECORD_LOST, stdout);
+		perf_event__fprintf(event, stdout);
+	}
 	thread__put(thread);
 	return 0;
 }
@@ -2948,7 +2982,8 @@ static int check_ev_match(char *dir_name, char *scriptname,
  * will list all statically runnable scripts, select one, execute it and
  * show the output in a perf browser.
  */
-int find_scripts(char **scripts_array, char **scripts_path_array)
+int find_scripts(char **scripts_array, char **scripts_path_array, int num,
+		 int pathlen)
 {
 	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
@@ -2993,7 +3028,10 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 			/* Skip those real time scripts: xxxtop.p[yl] */
 			if (strstr(script_dirent->d_name, "top."))
 				continue;
-			sprintf(scripts_path_array[i], "%s/%s", lang_path,
+			if (i >= num)
+				break;
+			snprintf(scripts_path_array[i], pathlen, "%s/%s",
+				lang_path,
 				script_dirent->d_name);
 			temp = strchr(script_dirent->d_name, '.');
 			snprintf(scripts_array[i],
@@ -3232,7 +3270,7 @@ static int parse_insn_trace(const struct option *opt __maybe_unused,
 {
 	parse_output_fields(NULL, "+insn,-event,-period", 0);
 	itrace_parse_synth_opts(opt, "i0ns", 0);
-	nanosecs = true;
+	symbol_conf.nanosecs = true;
 	return 0;
 }
 
@@ -3250,7 +3288,7 @@ static int parse_call_trace(const struct option *opt __maybe_unused,
 {
 	parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0);
 	itrace_parse_synth_opts(opt, "cewp", 0);
-	nanosecs = true;
+	symbol_conf.nanosecs = true;
 	return 0;
 }
 
@@ -3260,7 +3298,7 @@ static int parse_callret_trace(const struct option *opt __maybe_unused,
 {
 	parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0);
 	itrace_parse_synth_opts(opt, "crewp", 0);
-	nanosecs = true;
+	symbol_conf.nanosecs = true;
 	return 0;
 }
 
@@ -3277,6 +3315,7 @@ int cmd_script(int argc, const char **argv)
 		.set = false,
 		.default_no_sample = true,
 	};
+	struct utsname uts;
 	char *script_path = NULL;
 	const char **__argv;
 	int i, j, err = 0;
@@ -3395,7 +3434,7 @@ int cmd_script(int argc, const char **argv)
 	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_INTEGER(0, "max-blocks", &max_blocks,
 		    "Maximum number of code blocks to dump with brstackinsn"),
-	OPT_BOOLEAN(0, "ns", &nanosecs,
+	OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs,
 		    "Use 9 decimal places when displaying time"),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
 			    "Instruction Tracing options\n" ITRACE_HELP,
@@ -3615,6 +3654,12 @@ int cmd_script(int argc, const char **argv)
 	if (symbol__init(&session->header.env) < 0)
 		goto out_delete;
 
+	uname(&uts);
+	if (!strcmp(uts.machine, session->header.env.arch) ||
+	    (!strcmp(uts.machine, "x86_64") &&
+	     !strcmp(session->header.env.arch, "i386")))
+		native_arch = true;
+
 	script.session = session;
 	script__setup_sample_type(&script);