[PATCH v2 10/11] perf tools report: Implement browsing of individual samples

[Andi Kleen <andi@firstfloor.org>]

From: Andi Kleen <ak@linux.intel.com>

Now report can show whole time periods with perf script,
but the user still has to find individual samples of interest
manually.

It would be expensive and complicated to search for the
right samples in the whole perf file. Typically users
only need to look at a small number of samples for useful
analysis.

Also the full scripts tend to show samples of all CPUs and all
threads mixed up, which can be very confusing on larger systems.

Add a new --samples option to save a small random number of samples
per hist entry

Use a reservoir sample technique to select a representatve
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 the 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.

Currently it only supports as many samples as fit on
the screen due to some limitations in the slang ui code.

Signed-off-by: Andi Kleen <ak@linux.intel.com>

---
v2:
Free names on error path
Pass --inline and --show-*-event to child perf as needed.
---
 tools/perf/Documentation/perf-report.txt |  4 ++
 tools/perf/builtin-report.c              |  2 +
 tools/perf/ui/browsers/Build             |  1 +
 tools/perf/ui/browsers/hists.c           | 47 ++++++++++++++
 tools/perf/ui/browsers/res_sample.c      | 80 ++++++++++++++++++++++++
 tools/perf/ui/browsers/scripts.c         |  2 +-
 tools/perf/util/hist.c                   | 36 +++++++++++
 tools/perf/util/hist.h                   | 19 ++++++
 tools/perf/util/sort.h                   |  8 +++
 tools/perf/util/symbol.c                 |  1 +
 tools/perf/util/symbol_conf.h            |  1 +
 11 files changed, 200 insertions(+), 1 deletion(-)
 create mode 100644 tools/perf/ui/browsers/res_sample.c

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 546d87221ad8..f441baa794ce 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -461,6 +461,10 @@ include::itrace.txt[]
 --socket-filter::
 	Only report the samples on the processor socket that match with this filter
 
+--samples=N::
+	Save N individual samples for each histogram entry to show context in perf
+	report tui browser.
+
 --raw-trace::
 	When displaying traceevent output, do not use print fmt or plugins.
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f290c19304c8..f16a9a6f436a 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1158,6 +1158,8 @@ int cmd_report(int argc, const char **argv)
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
 	OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
+	OPT_INTEGER(0, "samples", &symbol_conf.res_sample,
+		    "Number of samples to save per histogram entry for individual browsing"),
 	OPT_CALLBACK(0, "percent-limit", &report, "percent",
 		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
diff --git a/tools/perf/ui/browsers/Build b/tools/perf/ui/browsers/Build
index 8fee56b46502..fdf86f7981ca 100644
--- a/tools/perf/ui/browsers/Build
+++ b/tools/perf/ui/browsers/Build
@@ -3,6 +3,7 @@ perf-y += hists.o
 perf-y += map.o
 perf-y += scripts.o
 perf-y += header.o
+perf-y += res_sample.o
 
 CFLAGS_annotate.o += -DENABLE_SLFUTURE_CONST
 CFLAGS_hists.o    += -DENABLE_SLFUTURE_CONST
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 10c5aa13ca0e..e35b274ee863 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2344,6 +2344,7 @@ struct popup_action {
 	struct map_symbol 	ms;
 	int			socket;
 	struct perf_evsel	*evsel;
+	enum rstype		rstype;
 
 	int (*fn)(struct hist_browser *browser, struct popup_action *act);
 };
@@ -2571,6 +2572,19 @@ do_run_script(struct hist_browser *browser __maybe_unused,
 	return 0;
 }
 
+static int
+do_res_sample_script(struct hist_browser *browser __maybe_unused,
+		     struct popup_action *act)
+{
+	struct hist_entry *he;
+	int num_res;
+
+	he = hist_browser__selected_entry(browser);
+	num_res = min(he->num_res, symbol_conf.res_sample);
+	res_sample_browse(he->res_samples, num_res, act->evsel, act->rstype);
+	return 0;
+}
+
 static int
 add_script_opt_2(struct hist_browser *browser __maybe_unused,
 	       struct popup_action *act, char **optstr,
@@ -2629,6 +2643,27 @@ add_script_opt(struct hist_browser *browser,
 	return n;
 }
 
+static int
+add_res_sample_opt(struct hist_browser *browser __maybe_unused,
+		   struct popup_action *act, char **optstr,
+		   struct res_sample *res_sample,
+		   struct perf_evsel *evsel,
+		   enum rstype type)
+{
+	if (!res_sample)
+		return 0;
+
+	if (asprintf(optstr, "Show context for individual samples %s",
+		type == A_ASM ? "with assembler" :
+		type == A_SOURCE ? "with source" : "") < 0)
+		return 0;
+
+	act->fn = do_res_sample_script;
+	act->evsel = evsel;
+	act->rstype = type;
+	return 1;
+}
+
 static int
 do_switch_data(struct hist_browser *browser __maybe_unused,
 	       struct popup_action *act __maybe_unused)
@@ -3115,6 +3150,18 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		}
 		nr_options += add_script_opt(browser, &actions[nr_options],
 					     &options[nr_options], NULL, NULL, evsel);
+		nr_options += add_res_sample_opt(browser, &actions[nr_options],
+						 &options[nr_options],
+				 hist_browser__selected_entry(browser)->res_samples,
+				 evsel, A_NORMAL);
+		nr_options += add_res_sample_opt(browser, &actions[nr_options],
+						 &options[nr_options],
+				 hist_browser__selected_entry(browser)->res_samples,
+				 evsel, A_ASM);
+		nr_options += add_res_sample_opt(browser, &actions[nr_options],
+						 &options[nr_options],
+				 hist_browser__selected_entry(browser)->res_samples,
+				 evsel, A_SOURCE);
 		nr_options += add_switch_opt(browser, &actions[nr_options],
 					     &options[nr_options]);
 skip_scripting:
diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c
new file mode 100644
index 000000000000..2f10c40cc7ab
--- /dev/null
+++ b/tools/perf/ui/browsers/res_sample.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Display a menu with individual samples to browse with perf script */
+#include "util.h"
+#include "hist.h"
+#include "evsel.h"
+#include "hists.h"
+#include "sort.h"
+#include "time-utils.h"
+
+/* In ns. Could make configurable. */
+#define CONTEXT_LEN 100000000
+
+int res_sample_browse(struct res_sample *res_samples, int num_res,
+		      struct perf_evsel *evsel, enum rstype rstype)
+{
+	char **names;
+	int i, n;
+	int choice;
+	char *cmd;
+	char pbuf[256], tidbuf[32], cpubuf[32];
+	const char *perf = perf_exe(pbuf, sizeof pbuf);
+	char trange[128], tsample[64];
+	struct res_sample *r;
+	char extra_format[256];
+
+	/* For now since ui__popup_menu doesn't like lists that don't fit */
+	num_res = max(min(SLtt_Screen_Rows - 4, num_res), 0);
+
+	names = calloc(num_res, sizeof(char *));
+	if (!names)
+		return -1;
+	for (i = 0; i < num_res; i++) {
+		char tbuf[64];
+
+		timestamp__scnprintf_nsec(res_samples[i].time, tbuf, sizeof tbuf);
+		if (asprintf(&names[i], "%s: CPU %d tid %d", tbuf,
+			     res_samples[i].cpu, res_samples[i].tid) < 0) {
+			while (--i >= 0)
+				free(names[i]);
+			free(names);
+			return -1;
+		}
+	}
+	choice = ui__popup_menu(num_res, names);
+	for (i = 0; i < num_res; i++)
+		free(names[i]);
+	free(names);
+
+	if (choice < 0 || choice >= num_res)
+		return -1;
+	r = &res_samples[choice];
+
+	n = timestamp__scnprintf_nsec(r->time - CONTEXT_LEN, trange, sizeof trange);
+	trange[n++] = ',';
+	timestamp__scnprintf_nsec(r->time + CONTEXT_LEN, trange + n, sizeof trange - n);
+
+	timestamp__scnprintf_nsec(r->time, tsample, sizeof tsample);
+
+	attr_to_script(extra_format, &evsel->attr);
+
+	if (asprintf(&cmd, "%s script %s%s --time %s %s%s %s%s --ns %s %s %s %s | less +/%s",
+		     perf,
+		     input_name ? "-i " : "",
+		     input_name ? input_name : "",
+		     trange,
+		     r->cpu ? "--cpu " : "",
+		     r->cpu ? (sprintf(cpubuf, "%d", r->cpu), cpubuf) : "",
+		     r->tid ? "--tid " : "",
+		     r->tid ? (sprintf(tidbuf, "%d", r->tid), tidbuf) : "",
+		     extra_format,
+		     rstype == A_ASM ? "-F +insn --xed" :
+		     rstype == A_SOURCE ? "-F +srcline,+srccode" : "",
+		     symbol_conf.inline_name ? "--inline" : "",
+		     "--show-lost-events --show-switch-events --show-task-events",
+		     tsample) < 0)
+		return -1;
+	run_script(cmd);
+	free(cmd);
+	return 0;
+}
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index 9e5f87558af6..cdba58447b85 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -125,7 +125,7 @@ static int list_scripts(char *script_name, bool *custom,
 	return ret;
 }
 
-static void run_script(char *cmd)
+void run_script(char *cmd)
 {
 	pr_debug("Running %s\n", cmd);
 	SLang_reset_tty();
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6040eb49ea23..ba8a58f2cdd0 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -593,6 +593,40 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	return he;
 }
 
+static unsigned random_max(unsigned high)
+{
+	unsigned thresh = -high % high;
+	for (;;) {
+		unsigned r = random();
+		if (r >= thresh)
+			return r % high;
+	}
+}
+
+static void hists__res_sample(struct hist_entry *he, struct perf_sample *sample)
+{
+	struct res_sample *r;
+	int j;
+
+	if (!he->res_samples) {
+		he->res_samples = calloc(sizeof(struct res_sample),
+					symbol_conf.res_sample);
+		if (!he->res_samples)
+			return;
+	}
+	if (he->num_res < symbol_conf.res_sample) {
+		j = he->num_res++;
+	} else {
+		j = random_max(++he->num_res + 1);
+		if (he->num_res > symbol_conf.res_sample)
+			return;
+	}
+	r = &he->res_samples[j];
+	r->time = sample->time;
+	r->cpu = sample->cpu;
+	r->tid = sample->tid;
+}
+
 static struct hist_entry*
 __hists__add_entry(struct hists *hists,
 		   struct addr_location *al,
@@ -640,6 +674,8 @@ __hists__add_entry(struct hists *hists,
 
 	if (!hists->has_callchains && he && he->callchain_size != 0)
 		hists->has_callchains = true;
+	if (he && symbol_conf.res_sample)
+		hists__res_sample(he, sample);
 	return he;
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 2113a6639cea..67b9b91e92df 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -433,6 +433,13 @@ struct hist_browser_timer {
 };
 
 struct annotation_options;
+struct res_sample;
+
+enum rstype {
+	A_NORMAL,
+	A_ASM,
+	A_SOURCE
+};
 
 #ifdef HAVE_SLANG_SUPPORT
 #include "../ui/keysyms.h"
@@ -454,6 +461,10 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 				  struct annotation_options *annotation_options);
 
 int script_browse(const char *script_opt, struct perf_evsel *evsel);
+
+void run_script(char *cmd);
+int res_sample_browse(struct res_sample *res_samples, int num_res,
+		      struct perf_evsel *evsel, enum rstype rstype);
 #else
 static inline
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
@@ -488,6 +499,14 @@ static inline int script_browse(const char *script_opt __maybe_unused,
 	return 0;
 }
 
+static inline int res_sample_browse(struct res_sample *res_samples __maybe_unused,
+				    int num_res __maybe_unused,
+				    struct perf_evsel *evsel __maybe_unused,
+				    enum rstype rstype __maybe_unused)
+{
+	return 0;
+}
+
 #define K_LEFT  -1000
 #define K_RIGHT -2000
 #define K_SWITCH_INPUT_DATA -3000
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 19dceb7f6145..bb9442ab7a0c 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -47,6 +47,12 @@ extern struct sort_entry sort_srcline;
 extern enum sort_type sort__first_dimension;
 extern const char default_mem_sort_order[];
 
+struct res_sample {
+	u64 time;
+	int cpu;
+	int tid;
+};
+
 struct he_stat {
 	u64			period;
 	u64			period_sys;
@@ -140,6 +146,8 @@ struct hist_entry {
 	struct mem_info		*mem_info;
 	void			*raw_data;
 	u32			raw_size;
+	int			num_res;
+	struct res_sample	*res_samples;
 	void			*trace_output;
 	struct perf_hpp_list	*hpp_list;
 	struct hist_entry	*parent_he;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 0f80743a1c25..754f7f2c1650 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -50,6 +50,7 @@ struct symbol_conf symbol_conf = {
 	.symfs			= "",
 	.event_group		= true,
 	.inline_name		= true,
+	.res_sample		= 0,
 };
 
 static enum dso_binary_type binary_type_symtab[] = {
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
index a5684a71b78e..6c55fa6fccec 100644
--- a/tools/perf/util/symbol_conf.h
+++ b/tools/perf/util/symbol_conf.h
@@ -68,6 +68,7 @@ struct symbol_conf {
 	struct intlist	*pid_list,
 			*tid_list;
 	const char	*symfs;
+	int		res_sample;
 };
 
 extern struct symbol_conf symbol_conf;
-- 
2.17.2