All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andi Kleen <andi@firstfloor.org>
To: a.p.zijlstra@chello.nl
Cc: eranian@google.com, linux-kernel@vger.kernel.org, x86@kernel.org,
	Andi Kleen <ak@linux.intel.com>
Subject: [PATCH 4/4] perf-events: Fix LLC-* events on Intel Nehalem/Westmere v2
Date: Thu, 18 Nov 2010 11:47:34 +0100	[thread overview]
Message-ID: <1290077254-12165-5-git-send-email-andi@firstfloor.org> (raw)
In-Reply-To: <1290077254-12165-1-git-send-email-andi@firstfloor.org>

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

The generic perf LLC-* events do count the L2 caches, not the real
L3 LLC on Intel Nehalem and Westmere. This lead to quite some confusion.

Fixing this properly requires use of the special OFFCORE_RESPONSE
events which need a separate mask register. This has been implemented
in a earlier patch.

Now use this infrastructure to set correct events for the LLC-*
on Nehalem and Westmere

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event.c       |   12 ++++----
 arch/x86/kernel/cpu/perf_event_intel.c |   46 +++++++++++++++++++++++---------
 2 files changed, 39 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 346006a..b1abe89 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -467,8 +467,9 @@ static inline int x86_pmu_initialized(void)
 }
 
 static inline int
-set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
+set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
 {
+	struct perf_event_attr *attr = &event->attr;
 	unsigned int cache_type, cache_op, cache_result;
 	u64 config, val;
 
@@ -494,9 +495,8 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
 	if (val == -1)
 		return -EINVAL;
 
-	hwc->config |= val;
-
-	return 0;
+	hwc->config |= val & X86_RAW_EVENT_MASK;
+	return x86_pmu_extra_regs(val, event);
 }
 
 static int x86_setup_perfctr(struct perf_event *event)
@@ -521,10 +521,10 @@ static int x86_setup_perfctr(struct perf_event *event)
 	}
 
 	if (attr->type == PERF_TYPE_RAW)
-		return 0;
+		return x86_pmu_extra_regs(event->attr.config, event);
 
 	if (attr->type == PERF_TYPE_HW_CACHE)
-		return set_ext_hw_attr(hwc, attr);
+		return set_ext_hw_attr(hwc, event);
 
 	if (attr->config >= x86_pmu.max_events)
 		return -EINVAL;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 675a666..7017ef7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -86,7 +86,7 @@ static struct event_constraint intel_nehalem_event_constraints[] =
 
 static struct extra_reg intel_nehalem_extra_regs[] =
 {
-	INTEL_EVENT_EXTRA_REG(0xb7, 0x1a6, 0xffff, 32), /* OFFCORE_RESPONSE_0 */
+	INTEL_EVENT_EXTRA_REG(0xb7, 0x1a6, 0xffff, 32), /* OFFCORE_RESPONSE */
 	EVENT_EXTRA_END
 };
 
@@ -170,16 +170,26 @@ static __initconst const u64 westmere_hw_cache_event_ids
  },
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS               */
-		[ C(RESULT_MISS)   ] = 0x0224, /* L2_RQSTS.LD_MISS             */
+		/* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x00000711004301b7,
+		/* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x0000f811004301bb, 
 	},
+	/* 
+	 * Use RFO, not WRITEBACK, because a write miss would typically occur 
+	 * on RFO. 
+	 */
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS                */
-		[ C(RESULT_MISS)   ] = 0x0824, /* L2_RQSTS.RFO_MISS            */
+		/* OFFCORE_RESPONSE_1.ANY_RFO.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x00000722004301bb,
+		/* OFFCORE_RESPONSE_0.ANY_RFO.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x0000f822004301b7,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference                */
-		[ C(RESULT_MISS)   ] = 0x412e, /* LLC Misses                   */
+		/* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x00000770004301b7,
+		/* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x0000f870004301bb,
 	},
  },
  [ C(DTLB) ] = {
@@ -261,16 +271,26 @@ static __initconst const u64 nehalem_hw_cache_event_ids
  },
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS               */
-		[ C(RESULT_MISS)   ] = 0x0224, /* L2_RQSTS.LD_MISS             */
+		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x00000711004301b7,
+		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x0000f811004301b7, 
 	},
+	/* 
+	 * Use RFO, not WRITEBACK, because a write miss would typically occur 
+	 * on RFO. 
+	 */
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS                */
-		[ C(RESULT_MISS)   ] = 0x0824, /* L2_RQSTS.RFO_MISS            */
+		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x00000722004301b7,
+		/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x0000f822004301b7,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference                */
-		[ C(RESULT_MISS)   ] = 0x412e, /* LLC Misses                   */
+		/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x00000770004301b7,
+		/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x0000f870004301b7,
 	},
  },
  [ C(DTLB) ] = {
-- 
1.7.1


      parent reply	other threads:[~2010-11-18 10:48 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-11-18 10:47 perf offcore patchkit for merge Andi Kleen
2010-11-18 10:47 ` [PATCH 1/4] x86: set cpu masks before calling CPU_STARTING notifiers Andi Kleen
2010-11-18 11:52   ` Thomas Gleixner
2010-11-18 13:39     ` Andi Kleen
2010-11-26 15:05   ` [tip:perf/core] x86: Set " tip-bot for Andi Kleen
2010-11-18 10:47 ` [PATCH 2/4] perf: Document enhanced event encoding for OFFCORE_MSR Andi Kleen
2010-11-18 10:47 ` [PATCH 3/4] perf-events: Add support for supplementary event registers v3 Andi Kleen
2010-11-18 11:12   ` Peter Zijlstra
2010-11-18 11:16     ` Andi Kleen
2010-11-18 11:46       ` Peter Zijlstra
2010-11-26 15:28         ` Peter Zijlstra
2010-11-26 15:30           ` Peter Zijlstra
2010-11-18 12:07   ` Peter Zijlstra
2010-11-22 12:23   ` Lin Ming
2010-11-22 12:47     ` Stephane Eranian
2010-11-22 13:01       ` Lin Ming
2010-12-01 14:27   ` Peter Zijlstra
2010-12-01 16:19     ` Peter Zijlstra
2010-11-18 10:47 ` Andi Kleen [this message]

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=1290077254-12165-5-git-send-email-andi@firstfloor.org \
    --to=andi@firstfloor.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=ak@linux.intel.com \
    --cc=eranian@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=x86@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 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.