mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Kan Liang <kan.liang@intel.com>
Cc: mingo@kernel.org, acme@infradead.org, eranian@google.com,
	andi@firstfloor.org, linux-kernel@vger.kernel.org
Subject: [RFC][PATCH] perf, pebs: Add PEBS v3 record decoding
Date: Tue, 12 May 2015 15:25:57 +0200	[thread overview]
Message-ID: <20150512132557.GQ21418@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <1431285195-14269-4-git-send-email-kan.liang@intel.com>



So seeing how I have both this series and Andi's SKL patches, I did the
below on top of them both.

Could someone try that?

---
Subject: perf, pebs: Add PEBS v3 record decoding
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue May 12 15:18:18 CEST 2015

PEBS v3 as present on Skylake fixed the long standing issue of the
status bits. They now really reflect the events that generated the
record.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/kernel/cpu/perf_event_intel_ds.c |   30 +++++++++++++++++++-----------
 1 file changed, 19 insertions(+), 11 deletions(-)

--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -1034,6 +1034,9 @@ get_next_pebs_record_by_bit(void *base,
 		struct pebs_record_nhm *p = at;
 
 		if (test_bit(bit, (unsigned long *)&p->status)) {
+			/* PEBS v3 has accurate status bits */
+			if (x86_pmu.intel_cap.pebs_format >= 3)
+				return at;
 
 			if (p->status == (1 << bit))
 				return at;
@@ -1055,20 +1058,18 @@ static void __intel_pmu_pebs_event(struc
 {
 	struct perf_sample_data data;
 	struct pt_regs regs;
-	int i;
 	void *at = get_next_pebs_record_by_bit(base, top, bit);
 
 	if (!intel_pmu_save_and_restart(event) &&
 	    !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD))
 		return;
 
-	if (count > 1) {
-		for (i = 0; i < count - 1; i++) {
-			setup_pebs_sample_data(event, iregs, at, &data, &regs);
-			perf_event_output(event, &data, &regs);
-			at += x86_pmu.pebs_record_size;
-			at = get_next_pebs_record_by_bit(at, top, bit);
-		}
+	while (count > 1) {
+		setup_pebs_sample_data(event, iregs, at, &data, &regs);
+		perf_event_output(event, &data, &regs);
+		at += x86_pmu.pebs_record_size;
+		at = get_next_pebs_record_by_bit(at, top, bit);
+		count--;
 	}
 
 	setup_pebs_sample_data(event, iregs, at, &data, &regs);
@@ -1124,9 +1125,9 @@ static void intel_pmu_drain_pebs_nhm(str
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event;
 	void *base, *at, *top;
-	int bit;
 	short counts[MAX_PEBS_EVENTS] = {};
 	short error[MAX_PEBS_EVENTS] = {};
+	int bit, i;
 
 	if (!x86_pmu.pebs_active)
 		return;
@@ -1142,6 +1143,15 @@ static void intel_pmu_drain_pebs_nhm(str
 	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
 		struct pebs_record_nhm *p = at;
 
+		/* PEBS v3 has accurate status bits */
+		if (x86_pmu.intel_cap.pebs_format >= 3) {
+			for_each_set_bit(bit, (unsigned long *)&p->status,
+					 MAX_PEBS_EVENTS)
+				counts[bit]++;
+
+			continue;
+		}
+
 		bit = find_first_bit((unsigned long *)&p->status,
 					x86_pmu.max_pebs_events);
 		if (bit >= x86_pmu.max_pebs_events)
@@ -1171,8 +1181,6 @@ static void intel_pmu_drain_pebs_nhm(str
 			pebs_status = p->status & cpuc->pebs_enabled;
 			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
 			if (pebs_status != (1 << bit)) {
-				u8 i;
-
 				for_each_set_bit(i, (unsigned long *)&pebs_status,
 						 MAX_PEBS_EVENTS)
 					error[i]++;

  reply	other threads:[~2015-05-12 13:26 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-10 19:13 [PATCH V9 0/8] large PEBS interrupt threshold Kan Liang
2015-05-10 19:13 ` [PATCH V9 1/8] perf, x86: use the PEBS auto reload mechanism when possible Kan Liang
2015-05-10 19:13 ` [PATCH V9 2/8] perf, x86: introduce setup_pebs_sample_data() Kan Liang
2015-05-10 19:13 ` [PATCH V9 3/8] perf, x86: handle multiple records in PEBS buffer Kan Liang
2015-05-12 13:25   ` Peter Zijlstra [this message]
2015-05-12 18:08     ` [RFC][PATCH] perf, pebs: Add PEBS v3 record decoding Andi Kleen
2015-05-13  1:31       ` Liang, Kan
2015-05-10 19:13 ` [PATCH V9 4/8] perf, x86: large PEBS interrupt threshold Kan Liang
2015-05-10 19:13 ` [PATCH V9 5/8] perf, x86: drain PEBS buffer during context switch Kan Liang
2015-05-10 19:13 ` [PATCH V9 6/8] perf, x86: enlarge PEBS buffer Kan Liang
2015-05-10 19:13 ` [PATCH V9 7/8] perf, x86: introduce PERF_RECORD_LOST_SAMPLES Kan Liang
2015-05-11 19:06   ` Arnaldo Carvalho de Melo
2015-06-07 17:50   ` [tip:perf/core] perf/x86/intel: Introduce PERF_RECORD_LOST_SAMPLES tip-bot for Kan Liang
2015-05-10 19:13 ` [PATCH V9 8/8] perf tools: handle PERF_RECORD_LOST_SAMPLES Kan Liang
2015-05-11 19:22   ` Arnaldo Carvalho de Melo
2015-05-11 20:40     ` Liang, Kan
2015-05-11 21:27       ` Arnaldo Carvalho de Melo
2015-05-12 12:43         ` Peter Zijlstra
2015-05-12 13:04           ` Arnaldo Carvalho de Melo
2015-06-07 17:51   ` [tip:perf/core] " tip-bot for Kan Liang
2015-05-11 16:06 ` [PATCH V9 0/8] large PEBS interrupt threshold Peter Zijlstra
2015-05-11 16:08   ` Liang, Kan

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=20150512132557.GQ21418@twins.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=acme@infradead.org \
    --cc=andi@firstfloor.org \
    --cc=eranian@google.com \
    --cc=kan.liang@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®