mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Andi Kleen <andi@firstfloor.org>
To: a.p.zijlstra@chello.nl
Cc: x86@kernel.org, linux-kernel@vger.kernel.org, acme@redhat.com,
	eranian@google.com, Andi Kleen <ak@linux.intel.com>
Subject: [PATCH 20/34] perf, core: Add generic transaction flags
Date: Thu, 18 Oct 2012 16:19:28 -0700	[thread overview]
Message-ID: <1350602382-12771-21-git-send-email-andi@firstfloor.org> (raw)
In-Reply-To: <1350602382-12771-1-git-send-email-andi@firstfloor.org>

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

Add a generic qualifier for transaction events, as a new sample
type that returns a flag word. This is particularly useful
for qualifying aborts: to distinguish aborts which happen
due to asynchronous events (like conflicts caused by another
CPU) versus instructions that lead to an abort.

The tuning strategies are very different for those cases,
so it's important to distinguish them easily and early.

Since it's inconvenient and inflexible to filter for this
in the kernel we report all the events out and allow
some post processing in user space.

The flags are based on the Intel TSX events, but should be fairly
generic and mostly applicable to other architectures too. In addition
to various flag words there's also reserved space to report an
program supplied abort code. For TSX this is used to distinguish specific
classes of aborts, like a lock busy abort when doing lock elision.

This adds the perf core glue needed for reporting the new flag word out.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 include/linux/perf_event.h      |    2 ++
 include/uapi/linux/perf_event.h |   24 ++++++++++++++++++++++--
 kernel/events/core.c            |    6 ++++++
 3 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f4ded17..7e6a4b6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -589,6 +589,7 @@ struct perf_sample_data {
 	struct perf_regs_user		regs_user;
 	u64				stack_user_size;
 	u64				weight;
+	u64				transaction;
 };
 
 static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -603,6 +604,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->regs_user.regs = NULL;
 	data->stack_user_size = 0;
 	data->weight = 0;
+	data->transaction = 0;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index c067c9c..d1ffdb6 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -133,9 +133,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_REGS_USER			= 1U << 12,
 	PERF_SAMPLE_STACK_USER			= 1U << 13,
 	PERF_SAMPLE_WEIGHT			= 1U << 14,
+	PERF_SAMPLE_TRANSACTION			= 1U << 15,
 
-	PERF_SAMPLE_MAX = 1U << 15,		/* non-ABI */
-
+	PERF_SAMPLE_MAX = 1U << 16,		/* non-ABI */
 };
 
 /*
@@ -179,6 +179,26 @@ enum perf_sample_regs_abi {
 };
 
 /*
+ * Values for the transaction event qualifier, mostly for abort events.
+ */
+enum {
+	PERF_SAMPLE_TXN_ELISION     = (1 << 0), /* From elision */
+	PERF_SAMPLE_TXN_TRANSACTION = (1 << 1), /* From transaction */
+	PERF_SAMPLE_TXN_SYNC        = (1 << 2), /* Instruction is related */
+	PERF_SAMPLE_TXN_ASYNC       = (1 << 3), /* Instruction not related */
+	PERF_SAMPLE_TXN_RETRY       = (1 << 4), /* Retry possible */
+	PERF_SAMPLE_TXN_CONFLICT    = (1 << 5), /* Conflict abort */
+	PERF_SAMPLE_TXN_CAPACITY    = (1 << 6), /* Capacity abort */
+
+	PERF_SAMPLE_TXN_MAX	    = (1 << 7),  /* non-ABI */
+
+	/* bits 24..31 are reserved for the abort code */
+
+	PERF_SAMPLE_TXN_ABORT_MASK  = 0xff000000,
+	PERF_SAMPLE_TXN_ABORT_SHIFT = 24,
+};
+
+/*
  * The format of the data returned by read() on a perf event fd,
  * as specified by attr.read_format:
  *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d633581..534810d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -955,6 +955,9 @@ static void perf_event__header_size(struct perf_event *event)
 	if (sample_type & PERF_SAMPLE_WEIGHT)
 		size += sizeof(data->weight);
 
+	if (sample_type & PERF_SAMPLE_TRANSACTION)
+		size += sizeof(data->transaction);
+
 	if (sample_type & PERF_SAMPLE_READ)
 		size += event->read_size;
 
@@ -4086,6 +4089,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_WEIGHT)
 		perf_output_put(handle, data->weight);
 
+	if (sample_type & PERF_SAMPLE_TRANSACTION)
+		perf_output_put(handle, data->transaction);
+
 	if (sample_type & PERF_SAMPLE_READ)
 		perf_output_read(handle, event);
 
-- 
1.7.7.6


  parent reply	other threads:[~2012-10-18 23:25 UTC|newest]

Thread overview: 65+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-10-18 23:19 perf PMU support for Haswell v3 Andi Kleen
2012-10-18 23:19 ` [PATCH 01/34] perf, x86: Add PEBSv2 record support Andi Kleen
2012-10-18 23:19 ` [PATCH 02/34] perf, x86: Basic Haswell PMU support v2 Andi Kleen
2012-10-18 23:19 ` [PATCH 03/34] perf, x86: Basic Haswell PEBS " Andi Kleen
2012-10-23 12:01   ` Peter Zijlstra
2012-10-23 13:31     ` Andi Kleen
2012-10-18 23:19 ` [PATCH 04/34] perf, x86: Support the TSX intx/intx_cp qualifiers Andi Kleen
2012-10-23 12:09   ` Peter Zijlstra
2012-10-23 13:33     ` Andi Kleen
2012-10-18 23:19 ` [PATCH 05/34] perf, x86: Report PEBS event in a raw format Andi Kleen
2012-10-23 12:31   ` Peter Zijlstra
2012-10-23 12:39     ` Stephane Eranian
2012-10-23 13:45       ` Andi Kleen
2012-10-23 13:58         ` Stephane Eranian
2012-10-23 14:11           ` Andi Kleen
2012-10-23 13:30     ` Andi Kleen
2012-10-23 13:50       ` Peter Zijlstra
2012-10-23 13:57         ` Andi Kleen
2012-10-24  7:50         ` Ingo Molnar
2012-10-18 23:19 ` [PATCH 06/34] perf, kvm: Support the intx/intx_cp modifiers in KVM arch perfmon emulation v2 Andi Kleen
2012-10-23 12:36   ` Peter Zijlstra
2012-10-23 12:53     ` Gleb Natapov
2012-10-23 13:35     ` Andi Kleen
2012-10-23 13:36       ` Andi Kleen
2012-10-23 13:05   ` [06/34] " Gleb Natapov
2012-10-23 13:20     ` Andi Kleen
2012-10-24 13:37       ` Gleb Natapov
2012-10-18 23:19 ` [PATCH 07/34] perf, x86: Support PERF_SAMPLE_ADDR on Haswell Andi Kleen
2012-10-18 23:19 ` [PATCH 08/34] perf, x86: Support Haswell v4 LBR format Andi Kleen
2012-10-23 12:37   ` Peter Zijlstra
2012-10-18 23:19 ` [PATCH 09/34] perf, x86: Disable LBR recording for unknown LBR_FMT Andi Kleen
2012-10-18 23:19 ` [PATCH 10/34] perf, x86: Support LBR filtering by INTX/NOTX/ABORT Andi Kleen
2012-10-18 23:19 ` [PATCH 11/34] perf, tools: Add abort,notx,intx branch filter options to perf report -j Andi Kleen
2012-10-23 12:44   ` Peter Zijlstra
2012-10-18 23:19 ` [PATCH 12/34] perf, tools: Support sorting by intx, abort branch flags Andi Kleen
2012-10-18 23:19 ` [PATCH 13/34] perf, x86: Support full width counting on Haswell Andi Kleen
2012-10-18 23:19 ` [PATCH 14/34] perf, x86: Avoid checkpointed counters causing excessive TSX aborts Andi Kleen
2012-10-23 13:03   ` Peter Zijlstra
2012-10-23 13:22     ` Andi Kleen
2012-10-23 13:05   ` Peter Zijlstra
2012-10-18 23:19 ` [PATCH 15/34] perf, core: Add a concept of a weightened sample Andi Kleen
2012-10-23 13:13   ` Peter Zijlstra
2012-10-23 13:19     ` Andi Kleen
2012-10-18 23:19 ` [PATCH 16/34] perf, x86: Support weight samples for PEBS Andi Kleen
2012-10-23 13:15   ` Peter Zijlstra
2012-10-23 14:05     ` Andi Kleen
2012-10-18 23:19 ` [PATCH 17/34] perf, tools: Add support for weight v2 Andi Kleen
2012-10-18 23:19 ` [PATCH 18/34] perf, tools: Handle XBEGIN like a jump Andi Kleen
2012-10-18 23:19 ` [PATCH 19/34] perf, x86: Support for printing PMU state on spurious PMIs v2 Andi Kleen
2012-10-18 23:19 ` Andi Kleen [this message]
2012-10-18 23:19 ` [PATCH 21/34] perf, x86: Add Haswell specific transaction flag reporting Andi Kleen
2012-10-18 23:19 ` [PATCH 22/34] perf, tools: Add support for record transaction flags Andi Kleen
2012-10-18 23:19 ` [PATCH 23/34] perf, tools: Point --sort documentation to --help Andi Kleen
2012-10-18 23:19 ` [PATCH 24/34] perf, tools: Add browser support for transaction flags Andi Kleen
2012-10-18 23:19 ` [PATCH 25/34] perf, tools: Move parse_events error printing to parse_events_options Andi Kleen
2012-10-18 23:19 ` [PATCH 26/34] perf, tools: Support events with - in the name Andi Kleen
2012-10-18 23:19 ` [PATCH 27/34] perf, x86: Report the arch perfmon events in sysfs Andi Kleen
2012-10-18 23:19 ` [PATCH 28/34] tools, perf: Add a precise event qualifier Andi Kleen
2012-10-18 23:19 ` [PATCH 29/34] perf, x86: Add Haswell TSX event aliases Andi Kleen
2012-10-18 23:19 ` [PATCH 30/34] perf, tools: Add perf stat --transaction v2 Andi Kleen
2012-10-18 23:19 ` [PATCH 31/34] perf, x86: Add a Haswell precise instructions event Andi Kleen
2012-10-18 23:19 ` [PATCH 32/34] perf, tools: Support generic events as pmu event names v2 Andi Kleen
2012-10-18 23:19 ` [PATCH 33/34] perf, tools: Default to cpu// for events v2 Andi Kleen
2012-10-18 23:19 ` [PATCH 34/34] perf, tools: List kernel supplied event aliases in perf list v2 Andi Kleen
2012-10-19  9:13 ` perf PMU support for Haswell v3 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=1350602382-12771-21-git-send-email-andi@firstfloor.org \
    --to=andi@firstfloor.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@redhat.com \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome