All of lore.kernel.org
 help / color / mirror / Atom feed
From: Stephane Eranian <eranian@google.com>
To: linux-kernel@vger.kernel.org
Cc: peterz@infradead.org, mingo@elte.hu, ak@linux.intel.com,
	acme@redhat.com, jolsa@redhat.com, ming.m.lin@intel.com
Subject: [Patch v1 08/10] perf report: add support for mem access profiling
Date: Mon, 29 Oct 2012 16:15:50 +0100	[thread overview]
Message-ID: <1351523752-4215-9-git-send-email-eranian@google.com> (raw)
In-Reply-To: <1351523752-4215-1-git-send-email-eranian@google.com>

This patch adds the --mem-mode option to perf report.

This mode requires a perf.data file created with memory
access samples.

Signed-off-by: Stephane Eranian <eranian@google.com>
---
 tools/perf/builtin-report.c |  131 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 127 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 90d1162..4d2e4f5 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -47,6 +47,7 @@ struct perf_report {
 	bool			show_full_info;
 	bool			show_threads;
 	bool			inverted_callchain;
+	bool			mem_mode;
 	struct perf_read_values	show_threads_values;
 	const char		*pretty_printing_style;
 	symbol_filter_t		annotate_init;
@@ -55,6 +56,96 @@ struct perf_report {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
+					   struct addr_location *al,
+					   struct perf_sample *sample,
+					   struct perf_evsel *evsel,
+					   struct machine *machine,
+					   union perf_event *event)
+{
+	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct symbol *parent = NULL;
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	int err = 0;
+	struct hist_entry *he;
+	struct mem_info *mi, *mx;
+	uint64_t cost;
+
+	if ((sort__has_parent || symbol_conf.use_callchain)
+	    && sample->callchain) {
+		err = machine__resolve_callchain(machine, evsel, al->thread,
+						 sample, &parent);
+		if (err)
+			return err;
+	}
+
+	mi = machine__resolve_mem(machine, al->thread, sample, cpumode);
+	if (!mi)
+		return -ENOMEM;
+
+	if (rep->hide_unresolved && !al->sym)
+		return 0;
+
+	cost = mi->cost;
+	if (!cost)
+		cost = 1;
+
+	/*
+	 * The report shows the percentage of total branches captured
+	 * and not events sampled. Thus we use a pseudo period of 1.
+	 * Only in the newt browser we are doing integrated annotation,
+	 * so we don't allocated the extra space needed because the stdio
+	 * code will not use it.
+	 */
+	he = __hists__add_mem_entry(&evsel->hists, al, parent, mi,
+				    cost);
+	if (!he)
+		return -ENOMEM;
+
+	if (sort__has_sym && he->ms.sym && use_browser > 0) {
+		struct annotation *notes = symbol__annotation(he->ms.sym);
+
+		assert(evsel != NULL);
+
+		if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
+			goto out;
+
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+		if (err)
+			goto out;
+	}
+
+	if (sort__has_sym && he->mem_info->daddr.sym && use_browser > 0) {
+		struct annotation *notes;
+
+		mx = he->mem_info;
+
+		notes = symbol__annotation(mx->daddr.sym);
+		if (!notes->src
+		    && symbol__alloc_hist(mx->daddr.sym) < 0)
+			goto out;
+
+		err = symbol__inc_addr_samples(mx->daddr.sym,
+					       mx->daddr.map,
+					       evsel->idx,
+					       mx->daddr.al_addr);
+		if (err)
+			goto out;
+	}
+
+	evsel->hists.stats.total_period += sample->period;
+	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	err = 0;
+
+	if (symbol_conf.use_callchain) {
+		err = callchain_append(he->callchain,
+				       &callchain_cursor,
+				       sample->period);
+	}
+out:
+	return err;
+}
+
 static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 					struct addr_location *al,
 					struct perf_sample *sample,
@@ -210,6 +301,12 @@ static int process_sample_event(struct perf_tool *tool,
 			pr_debug("problem adding lbr entry, skipping event\n");
 			return -1;
 		}
+	} else if (rep->mem_mode == 1) {
+		if (perf_report__add_mem_hist_entry(tool, &al, sample,
+						    evsel, machine, event)) {
+			pr_debug("problem adding mem entry, skipping event\n");
+			return -1;
+		}
 	} else {
 		if (al.map != NULL)
 			al.map->dso->hit = 1;
@@ -293,7 +390,8 @@ static void sig_handler(int sig __maybe_unused)
 	session_done = 1;
 }
 
-static size_t hists__fprintf_nr_sample_events(struct hists *self,
+static size_t hists__fprintf_nr_sample_events(struct perf_report *rep,
+					      struct hists *self,
 					      const char *evname, FILE *fp)
 {
 	size_t ret;
@@ -306,7 +404,11 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self,
 	if (evname != NULL)
 		ret += fprintf(fp, " of event '%s'", evname);
 
-	ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
+	if (rep->mem_mode) {
+		ret += fprintf(fp, "\n# Total cost : %" PRIu64, nr_events);
+		ret += fprintf(fp, "\n# Sort order : %s", sort_order);
+	} else
+		ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
 	return ret + fprintf(fp, "\n#\n");
 }
 
@@ -320,7 +422,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 		struct hists *hists = &pos->hists;
 		const char *evname = perf_evsel__name(pos);
 
-		hists__fprintf_nr_sample_events(hists, evname, stdout);
+		hists__fprintf_nr_sample_events(rep, hists, evname, stdout);
 		hists__fprintf(hists, true, 0, 0, stdout);
 		fprintf(stdout, "\n\n");
 	}
@@ -596,7 +698,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Use the stdio interface"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): pid, comm, dso, symbol, parent, dso_to,"
-		   " dso_from, symbol_to, symbol_from, mispredict"),
+		   " dso_from, symbol_to, symbol_from, mispredict, mem, cost, symbol_daddr, dso_daddr, tlb, snoop, locked"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
@@ -642,6 +744,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "use branch records for histogram filling", parse_branch_mode),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
 		   "objdump binary to use for disassembly and annotations"),
+	OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
 	OPT_END()
 	};
 
@@ -693,6 +796,18 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 				     "dso_to,symbol_to";
 
 	}
+	if (report.mem_mode) {
+		if (sort__branch_mode == 1) {
+			fprintf(stderr, "branch and mem mode incompatible\n");
+			goto error;
+		}
+		/*
+		 * if no sort_order is provided, then specify
+		 * branch-mode specific order
+		 */
+		if (sort_order == default_sort_order)
+			sort_order = "cost,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
+	}
 
 	if (strcmp(report.input_name, "-") != 0)
 		setup_browser(true);
@@ -764,6 +879,14 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout);
 		sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout);
 	} else {
+		if (report.mem_mode) {
+			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "symbol_daddr", stdout);
+			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso_daddr", stdout);
+			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "mem", stdout);
+			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "cost", stdout);
+			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "tlb", stdout);
+			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "snoop", stdout);
+		}
 		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
 		sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
 	}
-- 
1.7.9.5


  parent reply	other threads:[~2012-10-29 15:16 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-10-29 15:15 [Patch v1 00/10] perf: add memory access sampling support Stephane Eranian
2012-10-29 15:15 ` [Patch v1 01/10] perf/x86: improve sysfs event mapping with event string Stephane Eranian
2012-10-29 19:25   ` Andi Kleen
2012-10-29 15:15 ` [Patch v1 02/10] perf/x86: add flags to event constraints Stephane Eranian
2012-10-29 15:15 ` [Patch v1 03/10] perf: add generic memory sampling interface Stephane Eranian
2012-10-29 15:15 ` [Patch v1 04/10] perf/x86: add memory profiling via PEBS Load Latency Stephane Eranian
2012-10-29 15:23   ` Peter Zijlstra
2012-10-29 15:24     ` Stephane Eranian
2012-10-29 15:35   ` Peter Zijlstra
2012-10-29 15:39     ` Stephane Eranian
2012-10-29 15:38   ` Peter Zijlstra
2012-10-29 15:43     ` Stephane Eranian
2012-10-29 15:44       ` Peter Zijlstra
2012-10-29 19:42   ` Andi Kleen
2012-10-29 20:39     ` Stephane Eranian
2012-10-29 20:44       ` Peter Zijlstra
2012-10-29 21:16       ` Andi Kleen
2012-10-29 21:32         ` Stephane Eranian
2012-10-29 21:56           ` Andi Kleen
2012-10-30  8:43   ` Namhyung Kim
2012-10-29 15:15 ` [Patch v1 05/10] perf/x86: export PEBS load latency threshold register to sysfs Stephane Eranian
2012-10-29 15:15 ` [Patch v1 06/10] perf/x86: add support for PEBS Precise Store Stephane Eranian
2012-10-29 15:40   ` Peter Zijlstra
2012-10-29 15:44     ` Stephane Eranian
2012-10-31  5:21   ` Namhyung Kim
2012-10-31 13:28     ` Stephane Eranian
2012-10-29 15:15 ` [Patch v1 07/10] perf tools: add mem access sampling core support Stephane Eranian
2012-10-29 16:55   ` Andi Kleen
2012-10-29 17:00     ` Stephane Eranian
2012-10-31  5:51   ` Namhyung Kim
2012-10-31 13:30     ` Stephane Eranian
2012-10-29 15:15 ` Stephane Eranian [this message]
2012-10-31  6:01   ` [Patch v1 08/10] perf report: add support for mem access profiling Namhyung Kim
2012-10-29 15:15 ` [Patch v1 09/10] perf record: " Stephane Eranian
2012-10-29 15:15 ` [Patch v1 10/10] perf tools: add new mem command for memory " Stephane Eranian
2012-10-31  6:57   ` Namhyung Kim
2012-10-31 14:23     ` Stephane Eranian

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1351523752-4215-9-git-send-email-eranian@google.com \
    --to=eranian@google.com \
    --cc=acme@redhat.com \
    --cc=ak@linux.intel.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ming.m.lin@intel.com \
    --cc=mingo@elte.hu \
    --cc=peterz@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.