linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andi Kleen <andi@firstfloor.org>
To: linux-kernel@vger.kernel.org
Cc: acme@redhat.com, peterz@infradead.org, jolsa@redhat.com,
	eranian@google.com, mingo@kernel.org, namhyung@kernel.org,
	Andi Kleen <ak@linux.intel.com>
Subject: [PATCH 12/32] perf, x86: Support full width counting
Date: Fri,  9 Nov 2012 17:27:28 -0800	[thread overview]
Message-ID: <1352510868-7911-13-git-send-email-andi@firstfloor.org> (raw)
In-Reply-To: <1352510868-7911-1-git-send-email-andi@firstfloor.org>

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

Recent Intel CPUs have a new alternative MSR range for perfctrs that allows
writing the full counter width. Enable this range if the hardware reports it
using a new capability bit. This lowers overhead of perf stat slightly because
it has to do less interrupts to accumulate the counter value. On Haswell it
also avoids some problems with TSX aborting when the end of the counter
range is reached.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/include/asm/msr-index.h       |    3 +++
 arch/x86/kernel/cpu/perf_event.h       |    1 +
 arch/x86/kernel/cpu/perf_event_intel.c |    6 ++++++
 3 files changed, 10 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 7f0edce..2070f46 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -126,6 +126,9 @@
 #define MSR_KNC_EVNTSEL0               0x00000028
 #define MSR_KNC_EVNTSEL1               0x00000029
 
+/* Alternative perfctr range with full access. */
+#define MSR_IA32_PMC0			0x000004c1
+
 /* AMD64 MSRs. Not complete. See the architecture manual for a more
    complete list. */
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 1567b0d..ce2a863 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -278,6 +278,7 @@ union perf_capabilities {
 		u64	pebs_arch_reg:1;
 		u64	pebs_format:4;
 		u64	smm_freeze:1;
+		u64	fw_write:1;
 	};
 	u64	capabilities;
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 44e18c02..bc21bce 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2247,5 +2247,11 @@ __init int intel_pmu_init(void)
 		}
 	}
 
+	/* Support full width counters using alternative MSR range */
+	if (x86_pmu.intel_cap.fw_write) {
+		x86_pmu.max_period = x86_pmu.cntval_mask;
+		x86_pmu.perfctr = MSR_IA32_PMC0;
+	}
+
 	return 0;
 }
-- 
1.7.7.6


  parent reply	other threads:[~2012-11-10  1:28 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-11-10  1:27 perf PMU support for Haswell v6 Andi Kleen
2012-11-10  1:27 ` [PATCH 01/32] perf, x86: Add PEBSv2 record support Andi Kleen
2012-11-10  1:27 ` [PATCH 02/32] perf, x86: Basic Haswell PMU support v2 Andi Kleen
2012-11-10  1:27 ` [PATCH 03/32] perf, x86: Basic Haswell PEBS support v3 Andi Kleen
2012-11-10  1:27 ` [PATCH 04/32] perf, x86: Support the TSX intx/intx_cp qualifiers v2 Andi Kleen
2012-11-10  1:27 ` [PATCH 05/32] perf, kvm: Support the intx/intx_cp modifiers in KVM arch perfmon emulation v4 Andi Kleen
2012-11-12 12:43   ` Gleb Natapov
2012-11-10  1:27 ` [PATCH 06/32] perf, x86: Support PERF_SAMPLE_ADDR on Haswell Andi Kleen
2012-11-10  1:27 ` [PATCH 07/32] perf, x86: Support Haswell v4 LBR format Andi Kleen
2012-11-10  1:27 ` [PATCH 08/32] perf, x86: Disable LBR recording for unknown LBR_FMT Andi Kleen
2012-11-10  1:27 ` [PATCH 09/32] perf, x86: Support LBR filtering by INTX/NOTX/ABORT v2 Andi Kleen
2012-11-10  1:27 ` [PATCH 10/32] perf, tools: Add abort_tx,no_tx,in_tx branch filter options to perf record -j v3 Andi Kleen
2012-11-10  1:27 ` [PATCH 11/32] perf, tools: Support sorting by intx, abort branch flags Andi Kleen
2012-11-10  1:27 ` Andi Kleen [this message]
2012-11-10  1:27 ` [PATCH 13/32] perf, x86: Avoid checkpointed counters causing excessive TSX aborts v3 Andi Kleen
2012-11-10  1:27 ` [PATCH 14/32] perf, core: Add a concept of a weightened sample Andi Kleen
2012-11-10  1:27 ` [PATCH 15/32] perf, x86: Support weight samples for PEBS Andi Kleen
2012-11-10  1:27 ` [PATCH 16/32] perf, tools: Add support for weight v3 Andi Kleen
2012-11-10  1:27 ` [PATCH 17/32] perf, tools: Handle XBEGIN like a jump Andi Kleen
2012-11-10  1:27 ` [PATCH 18/32] perf, x86: Support for printing PMU state on spurious PMIs v3 Andi Kleen
2012-11-10  1:27 ` [PATCH 19/32] perf, core: Add generic transaction flags v2 Andi Kleen
2012-11-10  1:27 ` [PATCH 20/32] perf, x86: Add Haswell specific transaction flag reporting Andi Kleen
2012-11-10  1:27 ` [PATCH 21/32] perf, tools: Add support for record transaction flags v2 Andi Kleen
2012-11-10  1:27 ` [PATCH 22/32] perf, tools: Point --sort documentation to --help Andi Kleen
2012-11-10  1:27 ` [PATCH 23/32] perf, tools: Add browser support for transaction flags v3 Andi Kleen
2012-11-10  1:27 ` [PATCH 24/32] perf, tools: Add arbitary aliases and support names with - Andi Kleen
2012-11-10  1:27 ` [PATCH 25/32] tools, perf: Add a precise event qualifier Andi Kleen
2012-11-28 15:40   ` Jiri Olsa
2012-11-28 20:37     ` Andi Kleen
2012-11-10  1:27 ` [PATCH 26/32] perf, x86: improve sysfs event mapping with event string Andi Kleen
2012-11-10  1:27 ` [PATCH 27/32] perf, x86: Support CPU specific sysfs events Andi Kleen
2012-11-10  1:27 ` [PATCH 28/32] perf, x86: Add Haswell TSX event aliases v2 Andi Kleen
2012-11-10  1:27 ` [PATCH 29/32] perf, tools: Add perf stat --transaction v2 Andi Kleen
2012-11-10  1:27 ` [PATCH 30/32] perf, x86: Add a Haswell precise instructions event v2 Andi Kleen
2012-11-10  1:27 ` [PATCH 31/32] perf, tools: Default to cpu// for events v3 Andi Kleen
2012-11-28 15:53   ` Jiri Olsa
2012-11-28 19:04     ` Andi Kleen
2012-11-28 19:42       ` Arnaldo Carvalho de Melo
2012-11-10  1:27 ` [PATCH 32/32] perf, tools: List kernel supplied event aliases in perf list v2 Andi Kleen
  -- strict thread matches above, loose matches on Subject: below --
2012-10-31  0:33 perf PMU support for Haswell v5 Andi Kleen
2012-10-31  0:34 ` [PATCH 12/32] perf, x86: Support full width counting Andi Kleen

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=1352510868-7911-13-git-send-email-andi@firstfloor.org \
    --to=andi@firstfloor.org \
    --cc=acme@redhat.com \
    --cc=ak@linux.intel.com \
    --cc=eranian@google.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).