| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Tue, 19 Jun 2018 17:32:54 -0700
From: tip-bot for Reinette Chatre <tipbot@...or.com>
To: linux-tip-commits@...r.kernel.org
Cc: tglx@...utronix.de, linux-kernel@...r.kernel.org,
reinette.chatre@...el.com, hpa@...or.com, mingo@...nel.org
Subject: [tip:x86/cache] x86/intel_rdt: Support L3 cache performance event
of Broadwell
Commit-ID: 1333d418c44559936c5079b7785af7bf2582487b
Gitweb: https://git.kernel.org/tip/1333d418c44559936c5079b7785af7bf2582487b
Author: Reinette Chatre <reinette.chatre@...el.com>
AuthorDate: Tue, 29 May 2018 05:58:02 -0700
Committer: Thomas Gleixner <tglx@...utronix.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@...el.com>
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
Cc: fenghua.yu@...el.com
Cc: tony.luck@...el.com
Cc: vikas.shivappa@...ux.intel.com
Cc: gavin.hindman@...el.com
Cc: jithu.joseph@...el.com
Cc: dave.hansen@...el.com
Cc: hpa@...or.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
Powered by blists - more mailing lists