All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: mingo@elte.hu, linux-kernel@vger.kernel.org
Cc: paulus@samba.org, eranian@google.com, robert.richter@amd.com,
	fweisbec@gmail.com, Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [RFC][PATCH 11/11] perf, x86: Clean up IA32_PERF_CAPABILITIES usage
Date: Wed, 03 Mar 2010 17:39:47 +0100	[thread overview]
Message-ID: <20100303164306.678437077@chello.nl> (raw)
In-Reply-To: 20100303163936.906011640@chello.nl

[-- Attachment #1: perf-capabilities.patch --]
[-- Type: text/plain, Size: 6302 bytes --]

Saner PERF_CAPABILITIES support

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 arch/x86/kernel/cpu/perf_event.c           |   15 +++++++++++++--
 arch/x86/kernel/cpu/perf_event_intel.c     |   10 ++++++++++
 arch/x86/kernel/cpu/perf_event_intel_ds.c  |   26 +++++++++++++-------------
 arch/x86/kernel/cpu/perf_event_intel_lbr.c |   18 ++++--------------
 4 files changed, 40 insertions(+), 29 deletions(-)

Index: linux-2.6/arch/x86/kernel/cpu/perf_event.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/cpu/perf_event.c
+++ linux-2.6/arch/x86/kernel/cpu/perf_event.c
@@ -154,6 +154,17 @@ struct cpu_hw_events {
 #define for_each_event_constraint(e, c)	\
 	for ((e) = (c); (e)->cmask; (e)++)
 
+union perf_capabilities {
+	struct {
+		u64	lbr_format    : 6;
+		u64	pebs_trap     : 1;
+		u64	pebs_arch_reg : 1;
+		u64	pebs_format   : 4;
+		u64	smm_freeze    : 1;
+	};
+	u64	capabilities;
+};
+
 /*
  * struct x86_pmu - generic x86 pmu
  */
@@ -190,7 +201,8 @@ struct x86_pmu {
 	/*
 	 * Intel Arch Perfmon v2+
 	 */
-	u64		intel_ctrl;
+	u64			intel_ctrl;
+	union perf_capabilities intel_perf_capabilities;
 
 	/*
 	 * Intel DebugStore bits
@@ -205,7 +217,6 @@ struct x86_pmu {
 	 */
 	unsigned long	lbr_tos, lbr_from, lbr_to; /* MSR base regs       */
 	int		lbr_nr;			   /* hardware stack size */
-	int		lbr_format;		   /* hardware format     */
 };
 
 static struct x86_pmu x86_pmu __read_mostly;
Index: linux-2.6/arch/x86/kernel/cpu/perf_event_intel.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/cpu/perf_event_intel.c
+++ linux-2.6/arch/x86/kernel/cpu/perf_event_intel.c
@@ -840,6 +840,16 @@ static __init int intel_pmu_init(void)
 	if (version > 1)
 		x86_pmu.num_events_fixed = max((int)edx.split.num_events_fixed, 3);
 
+	/*
+	 * v2 and above have a perf capabilities MSR
+	 */
+	if (version > 1) {
+		u64 capabilities;
+
+		rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities);
+		x86_pmu.intel_perf_capabilities.capabilities = capabilities;
+	}
+
 	intel_ds_init();
 
 	/*
Index: linux-2.6/arch/x86/kernel/cpu/perf_event_intel_ds.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ linux-2.6/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -444,6 +444,12 @@ static void intel_pmu_pebs_fixup_ip(stru
 	u8 *kaddr;
 	int i;
 
+	/*
+	 * We don't need to fixup if the PEBS assist is fault like
+	 */
+	if (!x86_pmu.intel_perf_capabilities.pebs_trap)
+		return;
+
 	if (from && to) {
 		/*
 		 * We sampled a branch insn, rewind using the LBR stack
@@ -619,34 +625,28 @@ static void intel_ds_init(void)
 	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
 	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
 	if (x86_pmu.pebs) {
-		int format = 0;
-
-		if (x86_pmu.version > 1) {
-			u64 capabilities;
-			/*
-			 * v2+ has a PEBS format field
-			 */
-			rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities);
-			format = (capabilities >> 8) & 0xf;
-		}
+		int format = x86_pmu.intel_perf_capabilities.pebs_format;
+		char pebs_type =
+			x86_pmu.intel_perf_capabilities.pebs_trap ?  '+' : '-';
 
 		switch (format) {
 		case 0:
-			printk(KERN_CONT "PEBS v0, ");
+			printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
 			x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
 			x86_pmu.pebs_constraints = intel_core_pebs_events;
 			break;
 
 		case 1:
-			printk(KERN_CONT "PEBS v1, ");
+			printk(KERN_CONT "PEBS fmt1%c, ", pebs_type);
 			x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm);
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
 			x86_pmu.pebs_constraints = intel_nehalem_pebs_events;
 			break;
 
 		default:
-			printk(KERN_CONT "PEBS unknown format: %d, ", format);
+			printk(KERN_CONT "no PEBS fmt%d%c, ",
+					format, pebs_type);
 			x86_pmu.pebs = 0;
 			break;
 		}
Index: linux-2.6/arch/x86/kernel/cpu/perf_event_intel_lbr.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ linux-2.6/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -53,7 +53,7 @@ static void intel_pmu_lbr_reset_64(void)
 
 static void intel_pmu_lbr_reset(void)
 {
-	if (x86_pmu.lbr_format == LBR_FORMAT_32)
+	if (x86_pmu.intel_perf_capabilities.lbr_format == LBR_FORMAT_32)
 		intel_pmu_lbr_reset_32();
 	else
 		intel_pmu_lbr_reset_64();
@@ -155,6 +155,7 @@ static void intel_pmu_lbr_read_32(struct
 static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 {
 	unsigned long mask = x86_pmu.lbr_nr - 1;
+	int lbr_format = x86_pmu.intel_perf_capabilities.lbr_format;
 	u64 tos = intel_pmu_lbr_tos();
 	int i;
 
@@ -165,7 +166,7 @@ static void intel_pmu_lbr_read_64(struct
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
 		rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
 
-		if (x86_pmu.lbr_format == LBR_FORMAT_EIP_FLAGS) {
+		if (lbr_format == LBR_FORMAT_EIP_FLAGS) {
 			flags = !!(from & LBR_FROM_FLAG_MISPRED);
 			from = (u64)((((s64)from) << 1) >> 1);
 		}
@@ -184,7 +185,7 @@ static void intel_pmu_lbr_read(struct pe
 	if (!cpuc->lbr_users)
 		return;
 
-	if (x86_pmu.lbr_format == LBR_FORMAT_32)
+	if (x86_pmu.intel_perf_capabilities.lbr_format == LBR_FORMAT_32)
 		intel_pmu_lbr_read_32(cpuc);
 	else
 		intel_pmu_lbr_read_64(cpuc);
@@ -192,17 +193,8 @@ static void intel_pmu_lbr_read(struct pe
 	data->branches = &cpuc->lbr_stack;
 }
 
-static int intel_pmu_lbr_format(void)
-{
-	u64 capabilities;
-
-	rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities);
-	return capabilities & 0x1f;
-}
-
 static void intel_pmu_lbr_init_core(void)
 {
-	x86_pmu.lbr_format = intel_pmu_lbr_format();
 	x86_pmu.lbr_nr     = 4;
 	x86_pmu.lbr_tos    = 0x01c9;
 	x86_pmu.lbr_from   = 0x40;
@@ -211,7 +203,6 @@ static void intel_pmu_lbr_init_core(void
 
 static void intel_pmu_lbr_init_nhm(void)
 {
-	x86_pmu.lbr_format = intel_pmu_lbr_format();
 	x86_pmu.lbr_nr     = 16;
 	x86_pmu.lbr_tos    = 0x01c9;
 	x86_pmu.lbr_from   = 0x680;
@@ -220,7 +211,6 @@ static void intel_pmu_lbr_init_nhm(void)
 
 static void intel_pmu_lbr_init_atom(void)
 {
-	x86_pmu.lbr_format = intel_pmu_lbr_format();
 	x86_pmu.lbr_nr	   = 8;
 	x86_pmu.lbr_tos    = 0x01c9;
 	x86_pmu.lbr_from   = 0x40;

-- 


      parent reply	other threads:[~2010-03-03 16:47 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-03-03 16:39 [RFC][PATCH 00/11] Another stab at PEBS and LBR support Peter Zijlstra
2010-03-03 16:39 ` [RFC][PATCH 01/11] perf, x86: Remove superfluous arguments to x86_perf_event_set_period() Peter Zijlstra
2010-03-03 16:39 ` [RFC][PATCH 02/11] perf, x86: Remove superfluous arguments to x86_perf_event_update() Peter Zijlstra
2010-03-03 16:39 ` [RFC][PATCH 03/11] perf, x86: Change x86_pmu.{enable,disable} calling convention Peter Zijlstra
2010-03-03 16:39 ` [RFC][PATCH 04/11] perf, x86: Use unlocked bitops Peter Zijlstra
2010-03-03 16:39 ` [RFC][PATCH 05/11] perf: Generic perf_sample_data initialization Peter Zijlstra
2010-03-03 16:49   ` David Miller
2010-03-03 21:14   ` Frederic Weisbecker
2010-03-05  8:44   ` Jean Pihet
2010-03-03 16:39 ` [RFC][PATCH 06/11] perf, x86: PEBS infrastructure Peter Zijlstra
2010-03-03 17:38   ` Robert Richter
2010-03-03 17:42     ` Peter Zijlstra
2010-03-04  8:50       ` Robert Richter
2010-03-03 16:39 ` [RFC][PATCH 07/11] perf: Provide PERF_SAMPLE_REGS Peter Zijlstra
2010-03-03 17:30   ` Stephane Eranian
2010-03-03 17:39     ` Peter Zijlstra
2010-03-03 17:49       ` Stephane Eranian
2010-03-03 17:55         ` David Miller
2010-03-03 18:18           ` Stephane Eranian
2010-03-03 19:18           ` Peter Zijlstra
2010-03-04  2:59           ` Ingo Molnar
2010-03-04 12:58             ` Arnaldo Carvalho de Melo
2010-03-03 22:02   ` Frederic Weisbecker
2010-03-04  8:58     ` Peter Zijlstra
2010-03-04 11:04       ` Ingo Molnar
2010-03-03 16:39 ` [RFC][PATCH 08/11] perf, x86: Implement simple LBR support Peter Zijlstra
2010-03-03 21:52   ` Stephane Eranian
2010-03-04  8:58     ` Peter Zijlstra
2010-03-03 21:57   ` Stephane Eranian
2010-03-04  8:58     ` Peter Zijlstra
2010-03-04 17:54       ` Stephane Eranian
2010-03-04 18:18         ` Peter Zijlstra
2010-03-04 20:23           ` Peter Zijlstra
2010-03-04 20:57             ` Stephane Eranian
2010-03-03 16:39 ` [RFC][PATCH 09/11] perf, x86: Implement PERF_SAMPLE_BRANCH_STACK Peter Zijlstra
2010-03-03 21:08   ` Frederic Weisbecker
2010-03-03 16:39 ` [RFC][PATCH 10/11] perf, x86: use LBR for PEBS IP+1 fixup Peter Zijlstra
2010-03-03 18:05   ` Masami Hiramatsu
2010-03-03 19:37     ` Peter Zijlstra
2010-03-03 21:11       ` Masami Hiramatsu
2010-03-03 21:50         ` Stephane Eranian
2010-03-04  8:57           ` Peter Zijlstra
2010-03-09  1:41             ` Stephane Eranian
2010-03-03 16:39 ` Peter Zijlstra [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=20100303164306.678437077@chello.nl \
    --to=a.p.zijlstra@chello.nl \
    --cc=eranian@google.com \
    --cc=fweisbec@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=paulus@samba.org \
    --cc=robert.richter@amd.com \
    /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.