Merge tag 'perf-core-for-mingo-20160224' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements from Arnaldo Carvalho de Melo:

User visible changes:

  - Hierarchy histogram mode for 'perf top' and 'perf report', showing multiple
    levels, one per --sort entry: (Namhyung Kim)

    On a mostly idle system:

    # perf top --hierarchy -s comm,dso

    Then expand some levels and use 'P' to take a snapshot:

    # cat perf.hist.0
    -  92.32%         perf
          58.20%         perf
          22.29%         libc-2.22.so
           5.97%         [kernel]
           4.18%         libelf-0.165.so
           1.69%         [unknown]
    -   4.71%         qemu-system-x86
           3.10%         [kernel]
           1.60%         qemu-system-x86_64 (deleted)
    +   2.97%         swapper
    #

  - Check availability of memory events in 'perf mem': (Jiri Olsa)

    On a Intel Broadwell machine:

    # perf mem record -e list
    ldlat-loads : available
    ldlat-stores: available
    #

  - Decode data_src values (e.g. perf.data files generated by 'perf mem record')
    in 'perf script': (Jiri Olsa)

    # perf script
      perf 693 [1] 4.088652: 1 cpu/mem-loads,ldlat=30/P: ffff88007d0b0f40 68100142 L1 hit|SNP None|TLB L1 or L2 hit|LCK No <SNIP>
                                                                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  - Print bpf-output events in 'perf script': (Wang Nan).

    # perf record -e bpf-output/no-inherit,name=evt/ -e ./test_bpf_output_3.c/map:channel.event=evt/ usleep 1000
    # perf script
       usleep  4882 21384.532523:   evt:  ffffffff810e97d1 sys_nanosleep ([kernel.kallsyms])
        BPF output: 0000: 52 61 69 73 65 20 61 20  Raise a
                    0008: 42 50 46 20 65 76 65 6e  BPF even
                    0010: 74 21 00 00              t!..
        BPF string: "Raise a BPF event!"
    #

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 107 insertions, 6 deletions

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index f4caf48982457..ec4fbd410a4b0 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -23,6 +23,7 @@
 #include "util/stat.h"
 #include <linux/bitmap.h>
 #include "asm/bug.h"
+#include "util/mem-events.h"
 
 static char const		*script_name;
 static char const		*generate_script_lang;
@@ -60,6 +61,7 @@ enum perf_output_field {
 	PERF_OUTPUT_BRSTACKSYM	    = 1U << 16,
 	PERF_OUTPUT_DATA_SRC	    = 1U << 17,
 	PERF_OUTPUT_WEIGHT	    = 1U << 18,
+	PERF_OUTPUT_BPF_OUTPUT	    = 1U << 19,
 };
 
 struct output_option {
@@ -85,6 +87,7 @@ struct output_option {
 	{.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
 	{.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
 	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
+	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
 };
 
 /* default set to maintain compatibility with current format */
@@ -105,7 +108,7 @@ static struct {
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
 			      PERF_OUTPUT_PERIOD,
 
-		.invalid_fields = PERF_OUTPUT_TRACE,
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
 
 	[PERF_TYPE_SOFTWARE] = {
@@ -115,7 +118,7 @@ static struct {
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_PERIOD | PERF_OUTPUT_BPF_OUTPUT,
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},
@@ -125,7 +128,7 @@ static struct {
 
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 				  PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
-				  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE,
+				  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE
 	},
 
 	[PERF_TYPE_RAW] = {
@@ -138,7 +141,7 @@ static struct {
 			      PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
 			      PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
 
-		.invalid_fields = PERF_OUTPUT_TRACE,
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
 
 	[PERF_TYPE_BREAKPOINT] = {
@@ -150,7 +153,7 @@ static struct {
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
 			      PERF_OUTPUT_PERIOD,
 
-		.invalid_fields = PERF_OUTPUT_TRACE,
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
 };
 
@@ -623,6 +626,84 @@ static void print_sample_flags(u32 flags)
 	printf("  %-4s ", str);
 }
 
+struct printer_data {
+	int line_no;
+	bool hit_nul;
+	bool is_printable;
+};
+
+static void
+print_sample_bpf_output_printer(enum binary_printer_ops op,
+				unsigned int val,
+				void *extra)
+{
+	unsigned char ch = (unsigned char)val;
+	struct printer_data *printer_data = extra;
+
+	switch (op) {
+	case BINARY_PRINT_DATA_BEGIN:
+		printf("\n");
+		break;
+	case BINARY_PRINT_LINE_BEGIN:
+		printf("%17s", !printer_data->line_no ? "BPF output:" :
+						        "           ");
+		break;
+	case BINARY_PRINT_ADDR:
+		printf(" %04x:", val);
+		break;
+	case BINARY_PRINT_NUM_DATA:
+		printf(" %02x", val);
+		break;
+	case BINARY_PRINT_NUM_PAD:
+		printf("   ");
+		break;
+	case BINARY_PRINT_SEP:
+		printf("  ");
+		break;
+	case BINARY_PRINT_CHAR_DATA:
+		if (printer_data->hit_nul && ch)
+			printer_data->is_printable = false;
+
+		if (!isprint(ch)) {
+			printf("%c", '.');
+
+			if (!printer_data->is_printable)
+				break;
+
+			if (ch == '\0')
+				printer_data->hit_nul = true;
+			else
+				printer_data->is_printable = false;
+		} else {
+			printf("%c", ch);
+		}
+		break;
+	case BINARY_PRINT_CHAR_PAD:
+		printf(" ");
+		break;
+	case BINARY_PRINT_LINE_END:
+		printf("\n");
+		printer_data->line_no++;
+		break;
+	case BINARY_PRINT_DATA_END:
+	default:
+		break;
+	}
+}
+
+static void print_sample_bpf_output(struct perf_sample *sample)
+{
+	unsigned int nr_bytes = sample->raw_size;
+	struct printer_data printer_data = {0, false, true};
+
+	print_binary(sample->raw_data, nr_bytes, 8,
+		     print_sample_bpf_output_printer, &printer_data);
+
+	if (printer_data.is_printable && printer_data.hit_nul)
+		printf("%17s \"%s\"\n", "BPF string:",
+		       (char *)(sample->raw_data));
+}
+
 struct perf_script {
 	struct perf_tool	tool;
 	struct perf_session	*session;
@@ -649,6 +730,23 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist)
 	return max;
 }
 
+static size_t data_src__printf(u64 data_src)
+{
+	struct mem_info mi = { .data_src.val = data_src };
+	char decode[100];
+	char out[100];
+	static int maxlen;
+	int len;
+
+	perf_script__meminfo_scnprintf(decode, 100, &mi);
+
+	len = scnprintf(out, 100, "%16" PRIx64 " %s", data_src, decode);
+	if (maxlen < len)
+		maxlen = len;
+
+	return printf("%-*s", maxlen, out);
+}
+
 static void process_event(struct perf_script *script, union perf_event *event,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
 			  struct addr_location *al)
@@ -689,7 +787,7 @@ static void process_event(struct perf_script *script, union perf_event *event,
 		print_sample_addr(event, sample, thread, attr);
 
 	if (PRINT_FIELD(DATA_SRC))
-		printf("%16" PRIx64, sample->data_src);
+		data_src__printf(sample->data_src);
 
 	if (PRINT_FIELD(WEIGHT))
 		printf("%16" PRIu64, sample->weight);
@@ -713,6 +811,9 @@ static void process_event(struct perf_script *script, union perf_event *event,
 	else if (PRINT_FIELD(BRSTACKSYM))
 		print_sample_brstacksym(event, sample, thread, attr);
 
+	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
+		print_sample_bpf_output(sample);
+
 	printf("\n");
 }