linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Reinette Chatre <reinette.chatre@intel.com>
To: tglx@linutronix.de, fenghua.yu@intel.com, tony.luck@intel.com
Cc: gavin.hindman@intel.com, vikas.shivappa@linux.intel.com,
	dave.hansen@intel.com, mingo@redhat.com, hpa@zytor.com,
	x86@kernel.org, linux-kernel@vger.kernel.org,
	Reinette Chatre <reinette.chatre@intel.com>
Subject: [RFC PATCH V2 19/22] x86/intel_rdt: Support L3 cache performance event of Broadwell
Date: Tue, 13 Feb 2018 07:47:03 -0800	[thread overview]
Message-ID: <2a892970befa24ec1bb24db7a4d814ac13a8646e.1518443616.git.reinette.chatre@intel.com> (raw)
In-Reply-To: <cover.1518443616.git.reinette.chatre@intel.com>
In-Reply-To: <cover.1518443616.git.reinette.chatre@intel.com>

Broadwell microarchitecture supports pseudo-locking. Add support for
the L3 cache related performance events of these systems so that we can
measure the success of pseudo-locking.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
---
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c       | 56 +++++++++++++++++++++++
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h | 15 ++++++
 2 files changed, 71 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 34b2de387c3a..7511c2089d07 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -390,6 +390,8 @@ static int measure_cycles_hist_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;
@@ -424,6 +426,16 @@ 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
 	 */
 
 	/*
@@ -442,6 +454,14 @@ 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;
 	}
@@ -459,9 +479,21 @@ 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;
@@ -479,12 +511,36 @@ 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_restore(flags);
 	preempt_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:
 	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 45f6d1e35378..710535ae8235 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
@@ -29,6 +29,21 @@ TRACE_EVENT(pseudo_lock_l2,
 		      __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
-- 
2.13.6

  parent reply	other threads:[~2018-02-13 23:49 UTC|newest]

Thread overview: 65+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-02-13 15:46 [RFC PATCH V2 00/22] Intel(R) Resource Director Technology Cache Pseudo-Locking enabling Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 01/22] x86/intel_rdt: Documentation for Cache Pseudo-Locking Reinette Chatre
2018-02-19 20:35   ` Thomas Gleixner
2018-02-19 22:15     ` Reinette Chatre
2018-02-19 22:19       ` Thomas Gleixner
2018-02-19 22:24         ` Reinette Chatre
2018-02-19 21:27   ` Randy Dunlap
2018-02-19 22:21     ` Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 02/22] x86/intel_rdt: Make useful functions available internally Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 03/22] x86/intel_rdt: Introduce hooks to create pseudo-locking files Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 04/22] x86/intel_rdt: Introduce test to determine if closid is in use Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 05/22] x86/intel_rdt: Print more accurate pseudo-locking availability Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 06/22] x86/intel_rdt: Create pseudo-locked regions Reinette Chatre
2018-02-19 20:57   ` Thomas Gleixner
2018-02-19 23:02     ` Reinette Chatre
2018-02-19 23:16       ` Thomas Gleixner
2018-02-20  3:21         ` Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 07/22] x86/intel_rdt: Connect pseudo-locking directory to operations Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 08/22] x86/intel_rdt: Introduce pseudo-locking resctrl files Reinette Chatre
2018-02-19 21:01   ` Thomas Gleixner
2018-02-13 15:46 ` [RFC PATCH V2 09/22] x86/intel_rdt: Discover supported platforms via prefetch disable bits Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 10/22] x86/intel_rdt: Disable pseudo-locking if CDP enabled Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 11/22] x86/intel_rdt: Associate pseudo-locked regions with its domain Reinette Chatre
2018-02-19 21:19   ` Thomas Gleixner
2018-02-19 23:00     ` Reinette Chatre
2018-02-19 23:19       ` Thomas Gleixner
2018-02-20  3:17         ` Reinette Chatre
2018-02-20 10:00           ` Thomas Gleixner
2018-02-20 16:02             ` Reinette Chatre
2018-02-20 17:18               ` Thomas Gleixner
2018-02-13 15:46 ` [RFC PATCH V2 12/22] x86/intel_rdt: Support CBM checking from value and character buffer Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 13/22] x86/intel_rdt: Support schemata write - pseudo-locking core Reinette Chatre
2018-02-20 17:15   ` Thomas Gleixner
2018-02-20 18:47     ` Reinette Chatre
2018-02-20 23:21       ` Thomas Gleixner
2018-02-21  1:58         ` Mike Kravetz
2018-02-21  6:10           ` Reinette Chatre
2018-02-21  8:34           ` Thomas Gleixner
2018-02-21  5:58         ` Reinette Chatre
2018-02-27  0:34     ` Reinette Chatre
2018-02-27 10:36       ` Thomas Gleixner
2018-02-27 15:38         ` Thomas Gleixner
2018-02-27 19:52         ` Reinette Chatre
2018-02-27 21:33           ` Reinette Chatre
2018-02-28 18:39           ` Thomas Gleixner
2018-02-28 19:17             ` Reinette Chatre
2018-02-28 19:40               ` Thomas Gleixner
2018-02-27 21:01     ` Reinette Chatre
2018-02-28 17:57       ` Thomas Gleixner
2018-02-28 17:59         ` Thomas Gleixner
2018-02-28 18:34           ` Reinette Chatre
2018-02-28 18:42             ` Thomas Gleixner
2018-02-13 15:46 ` [RFC PATCH V2 14/22] x86/intel_rdt: Enable testing for pseudo-locked region Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 15/22] x86/intel_rdt: Prevent new allocations from pseudo-locked regions Reinette Chatre
2018-02-13 15:47 ` [RFC PATCH V2 16/22] x86/intel_rdt: Create debugfs files for pseudo-locking testing Reinette Chatre
2018-02-13 15:47 ` [RFC PATCH V2 17/22] x86/intel_rdt: Create character device exposing pseudo-locked region Reinette Chatre
2018-02-13 15:47 ` [RFC PATCH V2 18/22] x86/intel_rdt: More precise L2 hit/miss measurements Reinette Chatre
2018-02-13 15:47 ` Reinette Chatre [this message]
2018-02-13 15:47 ` [RFC PATCH V2 20/22] x86/intel_rdt: Limit C-states dynamically when pseudo-locking active Reinette Chatre
2018-02-13 15:47 ` [RFC PATCH V2 21/22] mm/hugetlb: Enable large allocations through gigantic page API Reinette Chatre
2018-02-13 15:47 ` [RFC PATCH V2 22/22] x86/intel_rdt: Support contiguous memory of all sizes Reinette Chatre
2018-02-14 18:12 ` [RFC PATCH V2 00/22] Intel(R) Resource Director Technology Cache Pseudo-Locking enabling Mike Kravetz
2018-02-14 18:31   ` Reinette Chatre
2018-02-15 20:39     ` Reinette Chatre
2018-02-15 21:10       ` Mike Kravetz

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=2a892970befa24ec1bb24db7a4d814ac13a8646e.1518443616.git.reinette.chatre@intel.com \
    --to=reinette.chatre@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=fenghua.yu@intel.com \
    --cc=gavin.hindman@intel.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=tony.luck@intel.com \
    --cc=vikas.shivappa@linux.intel.com \
    --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;
as well as URLs for NNTP newsgroup(s).