All of lore.kernel.org
 help / color / mirror / Atom feed
From: kan.liang@linux.intel.com
To: peterz@infradead.org, acme@kernel.org, mingo@redhat.com,
	linux-kernel@vger.kernel.org
Cc: tglx@linutronix.de, jolsa@kernel.org, eranian@google.com,
	alexander.shishkin@linux.intel.com, ak@linux.intel.com,
	Kan Liang <kan.liang@linux.intel.com>
Subject: [PATCH 05/22] perf/x86: Support constraint ranges
Date: Mon, 18 Mar 2019 14:41:27 -0700	[thread overview]
Message-ID: <20190318214144.4639-6-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20190318214144.4639-1-kan.liang@linux.intel.com>

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

Icelake extended the general counters to 8, even when SMT is enabled.
However only a (large) subset of the events can be used on all 8
counters.

The events that can or cannot be used on all counters are organized
in ranges.

We need a lot of scheduler constraints to handle all this.

To avoid blowing up the tables add event code ranges to the constraint
tables, and a new inline function to match them.

The changes costs ~2k text size according to 0day report.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
 arch/x86/events/intel/core.c |  2 +-
 arch/x86/events/intel/ds.c   |  2 +-
 arch/x86/events/perf_event.h | 34 ++++++++++++++++++++++++++++++++++
 3 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a964b9832b0c..8486ab87f8f8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2655,7 +2655,7 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 
 	if (x86_pmu.event_constraints) {
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if ((event->hw.config & c->cmask) == c->code) {
+			if (constraint_match(c, event->hw.config)) {
 				event->hw.flags |= c->flags;
 				return c;
 			}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 974284c5ed6c..30370fb93e21 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -858,7 +858,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 
 	if (x86_pmu.pebs_constraints) {
 		for_each_event_constraint(c, x86_pmu.pebs_constraints) {
-			if ((event->hw.config & c->cmask) == c->code) {
+			if (constraint_match(c, event->hw.config)) {
 				event->hw.flags |= c->flags;
 				return c;
 			}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 27c7945b5174..863d27f4c352 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -54,6 +54,7 @@ struct event_constraint {
 	int	weight;
 	int	overlap;
 	int	flags;
+	u64	range_end;
 };
 /*
  * struct hw_perf_event.flags flags
@@ -71,6 +72,12 @@ struct event_constraint {
 #define PERF_X86_EVENT_AUTO_RELOAD	0x0400 /* use PEBS auto-reload */
 #define PERF_X86_EVENT_LARGE_PEBS	0x0800 /* use large PEBS */
 
+static inline bool constraint_match(struct event_constraint *c, u64 ecode)
+{
+	ecode &= c->cmask;
+	return ecode == c->code ||
+		(c->range_end && ecode >= c->code && ecode <= c->range_end);
+}
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -267,9 +274,22 @@ struct cpu_hw_events {
 	.flags = f,			\
 }
 
+#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) {	\
+	{ .idxmsk64 = (n) },		\
+	.code = (c),			\
+	.range_end = (e),		\
+	.cmask = (m),			\
+	.weight = (w),			\
+	.overlap = (o),			\
+	.flags = f,			\
+}
+
 #define EVENT_CONSTRAINT(c, n, m)	\
 	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
 
+#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
+	__EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
+
 #define INTEL_EXCLEVT_CONSTRAINT(c, n)	\
 	__EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\
 			   0, PERF_X86_EVENT_EXCL)
@@ -304,6 +324,12 @@ struct cpu_hw_events {
 #define INTEL_EVENT_CONSTRAINT(c, n)	\
 	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
 
+/*
+ * Constraint on a range of Event codes
+ */
+#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n)			\
+	EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT)
+
 /*
  * Constraint on the Event code + UMask + fixed-mask
  *
@@ -351,6 +377,9 @@ struct cpu_hw_events {
 #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
 
+#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n)			\
+	EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
 /* Check only flags, but allow all event/umask */
 #define INTEL_ALL_EVENT_CONSTRAINT(code, n)	\
 	EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
@@ -367,6 +396,11 @@ struct cpu_hw_events {
 			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
 
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \
+	__EVENT_CONSTRAINT_RANGE(code, end, n,				\
+			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
 #define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \
 	__EVENT_CONSTRAINT(code, n,			\
 			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
-- 
2.17.1


  parent reply	other threads:[~2019-03-18 21:45 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-18 21:41 [PATCH 00/22] perf: Add Icelake support kan.liang
2019-03-18 21:41 ` [PATCH 01/22] perf/core: Support outputting registers from a separate array kan.liang
2019-03-19 13:00   ` Peter Zijlstra
2019-03-19 14:13     ` Peter Zijlstra
2019-03-18 21:41 ` [PATCH 02/22] perf/x86/intel: Extract memory code PEBS parser for reuse kan.liang
2019-03-19 13:14   ` Peter Zijlstra
2019-03-18 21:41 ` [PATCH 03/22] perf/x86/intel: Support adaptive PEBSv4 kan.liang
2019-03-19 14:47   ` Peter Zijlstra
2019-03-19 16:03     ` Andi Kleen
2019-03-19 16:11       ` Peter Zijlstra
2019-03-19 21:20     ` Liang, Kan
2019-03-19 21:38     ` Andi Kleen
2019-03-20 15:58       ` Peter Zijlstra
2019-03-18 21:41 ` [PATCH 04/22] perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them kan.liang
2019-03-18 21:41 ` kan.liang [this message]
2019-03-19 14:53   ` [PATCH 05/22] perf/x86: Support constraint ranges Peter Zijlstra
2019-03-19 15:27     ` Peter Zijlstra
2019-03-19 15:57     ` Andi Kleen
2019-03-19 16:09       ` Peter Zijlstra
2019-03-18 21:41 ` [PATCH 06/22] perf/x86/intel: Add Icelake support kan.liang
2019-03-20  0:08   ` Stephane Eranian
2019-03-20 14:20     ` Liang, Kan
2019-03-18 21:41 ` [PATCH 07/22] perf/x86/intel/cstate: " kan.liang
2019-03-18 21:41 ` [PATCH 08/22] perf/x86/intel/rapl: " kan.liang
2019-03-18 21:41 ` [PATCH 09/22] perf/x86/msr: " kan.liang
2019-03-18 21:41 ` [PATCH 10/22] perf/x86/intel/uncore: Add Intel Icelake uncore support kan.liang
2019-03-18 21:41 ` [PATCH 11/22] perf/core: Support a REMOVE transaction kan.liang
2019-03-19 15:29   ` Peter Zijlstra
2019-03-18 21:41 ` [PATCH 12/22] perf/x86/intel: Basic support for metrics counters kan.liang
2019-03-18 21:41 ` [PATCH 13/22] perf/x86/intel: Support overflows on SLOTS kan.liang
2019-03-18 21:41 ` [PATCH 14/22] perf/x86/intel: Support hardware TopDown metrics kan.liang
2019-03-18 21:41 ` [PATCH 15/22] perf/x86/intel: Set correct weight for topdown subevent counters kan.liang
2019-03-18 21:41 ` [PATCH 16/22] perf/x86/intel: Export new top down events for Icelake kan.liang
2019-03-18 21:41 ` [PATCH 17/22] perf/x86/intel: Disable sampling read slots and topdown kan.liang
2019-03-18 21:41 ` [PATCH 18/22] perf/x86/intel: Support CPUID 10.ECX to disable fixed counters kan.liang
2019-03-18 21:41 ` [PATCH 19/22] perf, tools: Add support for recording and printing XMM registers kan.liang
2019-03-18 21:41 ` [PATCH 20/22] perf, tools, stat: Support new per thread TopDown metrics kan.liang
2019-03-18 21:41 ` [PATCH 21/22] perf, tools: Add documentation for topdown metrics kan.liang
2019-03-18 21:41 ` [PATCH 22/22] perf vendor events intel: Add JSON files for Icelake kan.liang

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=20190318214144.4639-6-kan.liang@linux.intel.com \
    --to=kan.liang@linux.intel.com \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=eranian@google.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    /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.