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 V3 06/23] perf/x86: Support constraint ranges
Date: Fri, 22 Mar 2019 09:37:01 -0700	[thread overview]
Message-ID: <20190322163718.2191-7-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20190322163718.2191-1-kan.liang@linux.intel.com>

From: Peter Zijlstra <peterz@infradead.org>

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.

A lot of scheduler constraints are required 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.

Originally-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---

Changes since V2
- Add comments for EVENT_CONSTRAINT_RANGE
- Correct the Author

 arch/x86/events/intel/core.c |  2 +-
 arch/x86/events/intel/ds.c   |  2 +-
 arch/x86/events/perf_event.h | 42 ++++++++++++++++++++++++++++++------
 3 files changed, 38 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 620beae035a0..d5d796e114a1 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2688,7 +2688,7 @@ 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 1a076beb5fb1..3ee1a0198c13 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 f2351e47de3d..a502e9bb02bb 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -49,11 +49,12 @@ struct event_constraint {
 		unsigned long	idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 		u64		idxmsk64;
 	};
-	u64	code;
-	u64	cmask;
-	int	weight;
-	int	overlap;
-	int	flags;
+	u64		code;
+	u64		cmask;
+	int		weight;
+	int		overlap;
+	int		flags;
+	unsigned int	size;
 };
 /*
  * struct hw_perf_event.flags flags
@@ -71,6 +72,10 @@ 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)
+{
+	return ((ecode & c->cmask) - c->code) <= (u64)c->size;
+}
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -263,18 +268,29 @@ struct cpu_hw_events {
 	void				*kfree_on_online[X86_PERF_KFREE_MAX];
 };
 
-#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
+#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) {	\
 	{ .idxmsk64 = (n) },		\
 	.code = (c),			\
+	.size = (e) - (c),		\
 	.cmask = (m),			\
 	.weight = (w),			\
 	.overlap = (o),			\
 	.flags = f,			\
 }
 
+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \
+	__EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f)
+
 #define EVENT_CONSTRAINT(c, n, m)	\
 	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
 
+/*
+ * Only works for Intel events, which has 'small' event codes.
+ * Need to fix the rang compare for 'big' event codes, e.g AMD64_EVENTSEL_EVENT
+ */
+#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)
@@ -309,6 +325,12 @@ 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
  *
@@ -356,6 +378,9 @@ 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)
@@ -372,6 +397,11 @@ 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:[~2019-03-22 16:39 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-22 16:36 [PATCH V3 00/23] perf: Add Icelake support kan.liang
2019-03-22 16:36 ` [PATCH V3 01/23] perf/x86: Support outputting XMM registers kan.liang
2019-03-22 17:08   ` Peter Zijlstra
2019-03-22 17:22     ` Andi Kleen
2019-03-23  9:56       ` Peter Zijlstra
2019-03-25 20:35         ` Liang, Kan
2019-03-26  0:02           ` Thomas Gleixner
2019-03-26  0:11   ` Thomas Gleixner
2019-03-26 13:14     ` Liang, Kan
2019-03-26 13:47       ` Thomas Gleixner
2019-03-26 13:55         ` Liang, Kan
2019-03-22 16:36 ` [PATCH V3 02/23] perf/x86/intel: Extract memory code PEBS parser for reuse kan.liang
2019-03-22 16:36 ` [PATCH V3 03/23] perf/x86/intel/ds: Extract code of event update in short period kan.liang
2019-03-22 16:36 ` [PATCH V3 04/23] perf/x86/intel: Support adaptive PEBSv4 kan.liang
2019-03-22 16:37 ` [PATCH V3 05/23] perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them kan.liang
2019-03-22 16:37 ` kan.liang [this message]
2019-03-22 16:37 ` [PATCH V3 07/23] perf/x86/intel: Add Icelake support kan.liang
2019-03-22 16:37 ` [PATCH V3 08/23] perf/x86/intel/cstate: " kan.liang
2019-03-22 16:37 ` [PATCH V3 09/23] perf/x86/intel/rapl: " kan.liang
2019-03-22 16:37 ` [PATCH V3 10/23] perf/x86/msr: " kan.liang
2019-03-22 16:37 ` [PATCH V3 11/23] perf/x86/intel/uncore: Add Intel Icelake uncore support kan.liang
2019-03-22 16:37 ` [PATCH V3 12/23] perf/core: Support a REMOVE transaction kan.liang
2019-03-22 16:37 ` [PATCH V3 13/23] perf/x86/intel: Basic support for metrics counters kan.liang
2019-03-22 16:37 ` [PATCH V3 14/23] perf/x86/intel: Support overflows on SLOTS kan.liang
2019-03-22 16:37 ` [PATCH V3 15/23] perf/x86/intel: Support hardware TopDown metrics kan.liang
2019-03-22 16:37 ` [PATCH V3 16/23] perf/x86/intel: Set correct weight for topdown subevent counters kan.liang
2019-03-22 16:37 ` [PATCH V3 17/23] perf/x86/intel: Export new top down events for Icelake kan.liang
2019-03-22 16:37 ` [PATCH V3 18/23] perf/x86/intel: Disable sampling read slots and topdown kan.liang
2019-03-22 16:37 ` [PATCH V3 19/23] perf/x86/intel: Support CPUID 10.ECX to disable fixed counters kan.liang
2019-03-22 16:37 ` [PATCH V3 20/23] perf, tools: Add support for recording and printing XMM registers kan.liang
2019-03-22 16:37 ` [PATCH 21/23] perf, tools, stat: Support new per thread TopDown metrics kan.liang
2019-03-22 16:37 ` [PATCH V3 22/23] perf, tools: Add documentation for topdown metrics kan.liang
2019-03-22 16:37 ` [PATCH V3 23/23] 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=20190322163718.2191-7-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.