linux-kernel - [tip:perf/core] perf tools: Handle partial AUX records and print a warning

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <tip-05a1f47ed47a83736aca117aeee96e926cc0dfd0@git.kernel.org>
Date:   Mon, 20 Mar 2017 23:51:35 -0700
From:   tip-bot for Alexander Shishkin <tipbot@...or.com>
To:     linux-tip-commits@...r.kernel.org
Cc:     linux-kernel@...r.kernel.org, vince@...ter.net, hpa@...or.com,
        tglx@...utronix.de, adrian.hunter@...el.com,
        a.p.zijlstra@...llo.nl, acme@...hat.com,
        alexander.shishkin@...ux.intel.com, eranian@...gle.com,
        mingo@...nel.org
Subject: [tip:perf/core] perf tools: Handle partial AUX records and print a
 warning

Commit-ID:  05a1f47ed47a83736aca117aeee96e926cc0dfd0
Gitweb:     http://git.kernel.org/tip/05a1f47ed47a83736aca117aeee96e926cc0dfd0
Author:     Alexander Shishkin <alexander.shishkin@...ux.intel.com>
AuthorDate: Thu, 16 Mar 2017 18:41:59 +0200
Committer:  Arnaldo Carvalho de Melo <acme@...hat.com>
CommitDate: Fri, 17 Mar 2017 11:52:18 -0300

perf tools: Handle partial AUX records and print a warning

This patch decodes the 'partial' flag in AUX records and prints
a warning to the user, so that they don't have to guess why their
PT traces contain gaps (or missing altogether):

  Warning:
  AUX data had gaps in it 8 times out of 8!

  Are you running a KVM guest in the background?

Trying to be even more helpful, we will detect if the user's kvm driver sets up
exclusive VMX root mode for the entire lifespan of the kvm process:

  Reloading kvm_intel module with vmm_exclusive=0
  will reduce the gaps to only guest's timeslices.

Note however, that you'll still have gaps in cpu-wide traces even with
vmm_exclusive=0, but the number of gaps will be below 100% (as opposed to the
above example).

Currently this is the only reason for partial records.

Signed-off-by: Alexander Shishkin <alexander.shishkin@...ux.intel.com>
Cc: Adrian Hunter <adrian.hunter@...el.com>
Cc: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc: Stephane Eranian <eranian@...gle.com>
Cc: Vince Weaver <vince@...ter.net>
Link: http://lkml.kernel.org/r/8760j941ig.fsf@ashishki-desk.ger.corp.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@...hat.com>
---
 tools/perf/util/event.c   |  5 +++--
 tools/perf/util/event.h   |  1 +
 tools/perf/util/session.c | 27 ++++++++++++++++++++++++---
 3 files changed, 28 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 33fc2e9..76b9c6b 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1288,11 +1288,12 @@ int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
 
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
 {
-	return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n",
+	return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s%s]\n",
 		       event->aux.aux_offset, event->aux.aux_size,
 		       event->aux.flags,
 		       event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
-		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
+		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "",
+		       event->aux.flags & PERF_AUX_FLAG_PARTIAL   ? "P" : "");
 }
 
 size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index e1d8166..eb7a7b2 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -276,6 +276,7 @@ struct events_stats {
 	u64 total_lost;
 	u64 total_lost_samples;
 	u64 total_aux_lost;
+	u64 total_aux_partial;
 	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_non_filtered_samples;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ae42e74..24259bc2 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1,5 +1,6 @@
 #include <linux/kernel.h>
 #include <traceevent/event-parse.h>
+#include <api/fs/fs.h>
 
 #include <byteswap.h>
 #include <unistd.h>
@@ -1260,9 +1261,12 @@ static int machines__deliver_event(struct machines *machines,
 	case PERF_RECORD_UNTHROTTLE:
 		return tool->unthrottle(tool, event, sample, machine);
 	case PERF_RECORD_AUX:
-		if (tool->aux == perf_event__process_aux &&
-		    (event->aux.flags & PERF_AUX_FLAG_TRUNCATED))
-			evlist->stats.total_aux_lost += 1;
+		if (tool->aux == perf_event__process_aux) {
+			if (event->aux.flags & PERF_AUX_FLAG_TRUNCATED)
+				evlist->stats.total_aux_lost += 1;
+			if (event->aux.flags & PERF_AUX_FLAG_PARTIAL)
+				evlist->stats.total_aux_partial += 1;
+		}
 		return tool->aux(tool, event, sample, machine);
 	case PERF_RECORD_ITRACE_START:
 		return tool->itrace_start(tool, event, sample, machine);
@@ -1555,6 +1559,23 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 			    stats->nr_events[PERF_RECORD_AUX]);
 	}
 
+	if (session->tool->aux == perf_event__process_aux &&
+	    stats->total_aux_partial != 0) {
+		bool vmm_exclusive = false;
+
+		(void)sysfs__read_bool("module/kvm_intel/parameters/vmm_exclusive",
+		                       &vmm_exclusive);
+
+		ui__warning("AUX data had gaps in it %" PRIu64 " times out of %u!\n\n"
+		            "Are you running a KVM guest in the background?%s\n\n",
+			    stats->total_aux_partial,
+			    stats->nr_events[PERF_RECORD_AUX],
+			    vmm_exclusive ?
+			    "\nReloading kvm_intel module with vmm_exclusive=0\n"
+			    "will reduce the gaps to only guest's timeslices." :
+			    "");
+	}
+
 	if (stats->nr_unknown_events != 0) {
 		ui__warning("Found %u unknown events!\n\n"
 			    "Is this an older tool processing a perf.data "