public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: tip-bot for Reinette Chatre <tipbot@zytor.com>
To: linux-tip-commits@vger.kernel.org
Cc: tglx@linutronix.de, linux-kernel@vger.kernel.org,
	reinette.chatre@intel.com, hpa@zytor.com, mingo@kernel.org
Subject: [tip:x86/cache] x86/intel_rdt: Support L3 cache performance event of Broadwell
Date: Tue, 19 Jun 2018 17:32:54 -0700	[thread overview]
Message-ID: <tip-1333d418c44559936c5079b7785af7bf2582487b@git.kernel.org> (raw)
In-Reply-To: <5b91247c6ea44df78ddb18a2d488b86bbd20898c.1527593971.git.reinette.chatre@intel.com>

Commit-ID:  1333d418c44559936c5079b7785af7bf2582487b
Gitweb:     https://git.kernel.org/tip/1333d418c44559936c5079b7785af7bf2582487b
Author:     Reinette Chatre <reinette.chatre@intel.com>
AuthorDate: Tue, 29 May 2018 05:58:02 -0700
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Wed, 20 Jun 2018 00:56:40 +0200

x86/intel_rdt: Support L3 cache performance event of Broadwell

Broadwell microarchitecture supports pseudo-locking. Add support for
the L3 cache related performance events of these systems so that
the success of pseudo-locking can be measured more accurately on these
platforms.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/5b91247c6ea44df78ddb18a2d488b86bbd20898c.1527593971.git.reinette.chatre@intel.com

---
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c       | 56 +++++++++++++++++++++++
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h | 10 ++++
 2 files changed, 66 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index acaec07134c7..17ed2e9d4551 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -847,6 +847,8 @@ static int measure_cycles_lat_fn(void *_plr)
 
 static int measure_cycles_perf_fn(void *_plr)
 {
+	unsigned long long l3_hits = 0, l3_miss = 0;
+	u64 l3_hit_bits = 0, l3_miss_bits = 0;
 	struct pseudo_lock_region *plr = _plr;
 	unsigned long long l2_hits, l2_miss;
 	u64 l2_hit_bits, l2_miss_bits;
@@ -880,6 +882,16 @@ static int measure_cycles_perf_fn(void *_plr)
 	 *     L2_HIT   02H
 	 *     L1_MISS  08H
 	 *     L2_MISS  10H
+	 *
+	 * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event
+	 * has two "no fix" errata associated with it: BDM35 and BDM100. On
+	 * this platform we use the following events instead:
+	 *  L2_RQSTS 24H (Documented in https://download.01.org/perfmon/BDW/)
+	 *       REFERENCES FFH
+	 *       MISS       3FH
+	 *  LONGEST_LAT_CACHE 2EH (Documented in SDM)
+	 *       REFERENCE 4FH
+	 *       MISS      41H
 	 */
 
 	/*
@@ -898,6 +910,14 @@ static int measure_cycles_perf_fn(void *_plr)
 		l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1;
 		l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1;
 		break;
+	case INTEL_FAM6_BROADWELL_X:
+		/* On BDW the l2_hit_bits count references, not hits */
+		l2_hit_bits = (0x52ULL << 16) | (0xff << 8) | 0x24;
+		l2_miss_bits = (0x52ULL << 16) | (0x3f << 8) | 0x24;
+		/* On BDW the l3_hit_bits count references, not hits */
+		l3_hit_bits = (0x52ULL << 16) | (0x4f << 8) | 0x2e;
+		l3_miss_bits = (0x52ULL << 16) | (0x41 << 8) | 0x2e;
+		break;
 	default:
 		goto out;
 	}
@@ -914,9 +934,21 @@ static int measure_cycles_perf_fn(void *_plr)
 	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0);
 	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0);
 	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0);
+	if (l3_hit_bits > 0) {
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x0);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, 0x0);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 2, 0x0);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 3, 0x0);
+	}
 	/* Set and enable the L2 counters */
 	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits);
 	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits);
+	if (l3_hit_bits > 0) {
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
+				      l3_hit_bits);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
+				      l3_miss_bits);
+	}
 	mem_r = plr->kmem;
 	size = plr->size;
 	line_size = plr->line_size;
@@ -934,11 +966,35 @@ static int measure_cycles_perf_fn(void *_plr)
 			      l2_hit_bits & ~(0x40ULL << 16));
 	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1,
 			      l2_miss_bits & ~(0x40ULL << 16));
+	if (l3_hit_bits > 0) {
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
+				      l3_hit_bits & ~(0x40ULL << 16));
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
+				      l3_miss_bits & ~(0x40ULL << 16));
+	}
 	l2_hits = native_read_pmc(0);
 	l2_miss = native_read_pmc(1);
+	if (l3_hit_bits > 0) {
+		l3_hits = native_read_pmc(2);
+		l3_miss = native_read_pmc(3);
+	}
 	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
 	local_irq_enable();
+	/*
+	 * On BDW we count references and misses, need to adjust. Sometimes
+	 * the "hits" counter is a bit more than the references, for
+	 * example, x references but x + 1 hits. To not report invalid
+	 * hit values in this case we treat that as misses eaqual to
+	 * references.
+	 */
+	if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
+		l2_hits -= (l2_miss > l2_hits ? l2_hits : l2_miss);
 	trace_pseudo_lock_l2(l2_hits, l2_miss);
+	if (l3_hit_bits > 0) {
+		if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
+			l3_hits -= (l3_miss > l3_hits ? l3_hits : l3_miss);
+		trace_pseudo_lock_l3(l3_hits, l3_miss);
+	}
 
 out:
 	plr->thread_done = 1;
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
index efad50d2ee2f..2c041e6d9f05 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
@@ -25,6 +25,16 @@ TRACE_EVENT(pseudo_lock_l2,
 	    TP_printk("hits=%llu miss=%llu",
 		      __entry->l2_hits, __entry->l2_miss));
 
+TRACE_EVENT(pseudo_lock_l3,
+	    TP_PROTO(u64 l3_hits, u64 l3_miss),
+	    TP_ARGS(l3_hits, l3_miss),
+	    TP_STRUCT__entry(__field(u64, l3_hits)
+			     __field(u64, l3_miss)),
+	    TP_fast_assign(__entry->l3_hits = l3_hits;
+			   __entry->l3_miss = l3_miss;),
+	    TP_printk("hits=%llu miss=%llu",
+		      __entry->l3_hits, __entry->l3_miss));
+
 #endif /* _TRACE_PSEUDO_LOCK_H */
 
 #undef TRACE_INCLUDE_PATH

  reply	other threads:[~2018-06-20  0:33 UTC|newest]

Thread overview: 91+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-29 12:57 [PATCH V5 00/38] Intel(R) Resource Director Technology Cache Pseudo-Locking enabling Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 01/38] x86/intel_rdt: Document new mode, size, and bit_usage Reinette Chatre
2018-06-20  0:12   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 02/38] x86/intel_rdt: Introduce RDT resource group mode Reinette Chatre
2018-06-20  0:13   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 03/38] x86/intel_rdt: Associate mode with each RDT resource group Reinette Chatre
2018-06-20  0:14   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 04/38] x86/intel_rdt: Introduce resource group's mode resctrl file Reinette Chatre
2018-06-20  0:14   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 05/38] x86/intel_rdt: Introduce test to determine if closid is in use Reinette Chatre
2018-06-20  0:15   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 06/38] x86/intel_rdt: Make useful functions available internally Reinette Chatre
2018-06-20  0:15   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 07/38] x86/intel_rdt: Initialize new resource group with sane defaults Reinette Chatre
2018-06-07 21:24   ` [PATCH V6 " Reinette Chatre
2018-06-19 12:31     ` Thomas Gleixner
2018-06-19 16:33       ` Reinette Chatre
2018-06-19 16:53         ` Thomas Gleixner
2018-06-19 17:06           ` Reinette Chatre
2018-06-20  0:16     ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 08/38] x86/intel_rdt: Introduce new "exclusive" mode Reinette Chatre
2018-06-20  0:16   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 09/38] x86/intel_rdt: Enable setting of exclusive mode Reinette Chatre
2018-06-20  0:17   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 10/38] x86/intel_rdt: Making CBM name and type more explicit Reinette Chatre
2018-06-20  0:17   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 11/38] x86/intel_rdt: Support flexible data to parsing callbacks Reinette Chatre
2018-06-20  0:18   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 12/38] x86/intel_rdt: Ensure requested schemata respects mode Reinette Chatre
2018-06-20  0:18   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 13/38] x86/intel_rdt: Introduce "bit_usage" to display cache allocations details Reinette Chatre
2018-06-20  0:19   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 14/38] x86/intel_rdt: Display resource groups' allocations' size in bytes Reinette Chatre
2018-06-20  0:20   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 15/38] x86/intel_rdt: Documentation for Cache Pseudo-Locking Reinette Chatre
2018-06-20  0:20   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 16/38] x86/intel_rdt: Introduce the Cache Pseudo-Locking modes Reinette Chatre
2018-06-20  0:21   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 17/38] x86/intel_rdt: Respect read and write access Reinette Chatre
2018-06-20  0:21   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 18/38] x86/intel_rdt: Add utility to test if tasks assigned to resource group Reinette Chatre
2018-06-20  0:22   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 19/38] x86/intel_rdt: Add utility to restrict/restore access to resctrl files Reinette Chatre
2018-06-20  0:22   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 20/38] x86/intel_rdt: Protect against resource group changes during locking Reinette Chatre
2018-06-20  0:23   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 21/38] x86/intel_rdt: Utilities to restrict/restore access to specific files Reinette Chatre
2018-06-20  0:23   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 22/38] x86/intel_rdt: Add check to determine if monitoring in progress Reinette Chatre
2018-06-20  0:24   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 23/38] x86/intel_rdt: Introduce pseudo-locked region Reinette Chatre
2018-06-20  0:25   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 24/38] x86/intel_rdt: Support enter/exit of locksetup mode Reinette Chatre
2018-06-20  0:25   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 25/38] x86/intel_rdt: Enable entering of pseudo-locksetup mode Reinette Chatre
2018-06-07 21:26   ` [PATCH V6 " Reinette Chatre
2018-06-20  0:26     ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 26/38] x86/intel_rdt: Split resource group removal in two Reinette Chatre
2018-06-20  0:26   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 27/38] x86/intel_rdt: Add utilities to test pseudo-locked region possibility Reinette Chatre
2018-06-01 13:09   ` [PATCH V6 " Reinette Chatre
2018-06-20  0:27     ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 28/38] x86/intel_rdt: Discover supported platforms via prefetch disable bits Reinette Chatre
2018-06-20  0:27   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 29/38] x86/intel_rdt: Pseudo-lock region creation/removal core Reinette Chatre
2018-05-31 21:06   ` [PATCH V6 " Reinette Chatre
2018-06-20  0:28     ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 30/38] x86/intel_rdt: Support creation/removal of pseudo-locked region Reinette Chatre
2018-06-20  0:29   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 31/38] x86/intel_rdt: resctrl files reflect pseudo-locked information Reinette Chatre
2018-06-20  0:29   ` [tip:x86/cache] x86/intel_rdt: Resctrl " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 32/38] x86/intel_rdt: Ensure RDT cleanup on exit Reinette Chatre
2018-06-20  0:30   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 33/38] x86/intel_rdt: Create resctrl debug area Reinette Chatre
2018-06-20  0:30   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:57 ` [PATCH V5 34/38] x86/intel_rdt: Create debugfs files for pseudo-locking testing Reinette Chatre
2018-06-20  0:31   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:58 ` [PATCH V5 35/38] x86/intel_rdt: Create character device exposing pseudo-locked region Reinette Chatre
2018-06-20  0:31   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:58 ` [PATCH V5 36/38] x86/intel_rdt: More precise L2 hit/miss measurements Reinette Chatre
2018-06-20  0:32   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-05-29 12:58 ` [PATCH V5 37/38] x86/intel_rdt: Support L3 cache performance event of Broadwell Reinette Chatre
2018-06-20  0:32   ` tip-bot for Reinette Chatre [this message]
2018-05-29 12:58 ` [PATCH V5 38/38] x86/intel_rdt: Limit C-states dynamically when pseudo-locking active Reinette Chatre
2018-06-20  0:33   ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-06-19 16:57 ` [PATCH V5 00/38] Intel(R) Resource Director Technology Cache Pseudo-Locking enabling Thomas Gleixner
2018-06-19 17:06   ` Reinette Chatre
2018-06-20  6:21     ` Thomas Gleixner
2018-06-20  6:38       ` Reinette Chatre
  -- strict thread matches above, loose matches on Subject: below --
2018-06-22 22:42 [PATCH V7 38/41] x86/intel_rdt: Support L3 cache performance event of Broadwell Reinette Chatre
2018-06-23 12:27 ` [tip:x86/cache] " tip-bot for Reinette Chatre
2018-06-24 13:40 ` tip-bot for Reinette Chatre

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=tip-1333d418c44559936c5079b7785af7bf2582487b@git.kernel.org \
    --to=tipbot@zytor.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tip-commits@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=reinette.chatre@intel.com \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox