From: Sean Christopherson <seanjc@google.com>
To: Sean Christopherson <seanjc@google.com>,
Paolo Bonzini <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
Maxim Levitsky <mlevitsk@redhat.com>
Subject: [PATCH 2/2] KVM: selftests: Increase robustness of LLC cache misses in PMU counters test
Date: Thu, 27 Jun 2024 17:55:57 -0700 [thread overview]
Message-ID: <20240628005558.3835480-3-seanjc@google.com> (raw)
In-Reply-To: <20240628005558.3835480-1-seanjc@google.com>
From: Maxim Levitsky <mlevitsk@redhat.com>
Currently the PMU counters test does a single CLFLUSH{,OPT} on the loop's
code, but due to speculative execution this might not cause LLC misses
within the measured section.
Instead of doing a single flush before the loop, do a cache flush on each
iteration of the loop to confuse the prediction and ensure that at least
one cache miss occurs within the measured section.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
[sean: keep MFENCE, massage changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
.../selftests/kvm/x86_64/pmu_counters_test.c | 24 +++++++++++--------
1 file changed, 14 insertions(+), 10 deletions(-)
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
index bb40d7c0f83e..698cb36989db 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
@@ -13,15 +13,18 @@
/* Each iteration of the loop retires one branch instruction. */
#define NUM_BRANCH_INSNS_RETIRED (NUM_LOOPS)
-/* Number of instructions in each loop. */
-#define NUM_INSNS_PER_LOOP 1
+/*
+ * Number of instructions in each loop. 1 CLFLUSH/CLFLUSHOPT/NOP, 1 MFENCE,
+ * 1 LOOP.
+ */
+#define NUM_INSNS_PER_LOOP 3
/*
* Number of "extra" instructions that will be counted, i.e. the number of
* instructions that are needed to set up the loop and then disable the
- * counter. 1 CLFLUSH/CLFLUSHOPT/NOP, 1 MFENCE, 2 MOV, 2 XOR, 1 WRMSR.
+ * counter. 2 MOV, 2 XOR, 1 WRMSR.
*/
-#define NUM_EXTRA_INSNS 7
+#define NUM_EXTRA_INSNS 5
/* Total number of instructions retired within the measured section. */
#define NUM_INSNS_RETIRED (NUM_LOOPS * NUM_INSNS_PER_LOOP + NUM_EXTRA_INSNS)
@@ -144,8 +147,8 @@ static void guest_assert_event_count(uint8_t idx,
* before the end of the sequence.
*
* If CLFUSH{,OPT} is supported, flush the cacheline containing (at least) the
- * start of the loop to force LLC references and misses, i.e. to allow testing
- * that those events actually count.
+ * CLFUSH{,OPT} instruction on each loop iteration to force LLC references and
+ * misses, i.e. to allow testing that those events actually count.
*
* If forced emulation is enabled (and specified), force emulation on a subset
* of the measured code to verify that KVM correctly emulates instructions and
@@ -155,10 +158,11 @@ static void guest_assert_event_count(uint8_t idx,
#define GUEST_MEASURE_EVENT(_msr, _value, clflush, FEP) \
do { \
__asm__ __volatile__("wrmsr\n\t" \
+ " mov $" __stringify(NUM_LOOPS) ", %%ecx\n\t" \
+ "1:\n\t" \
clflush "\n\t" \
"mfence\n\t" \
- "1: mov $" __stringify(NUM_LOOPS) ", %%ecx\n\t" \
- FEP "loop .\n\t" \
+ FEP "loop 1b\n\t" \
FEP "mov %%edi, %%ecx\n\t" \
FEP "xor %%eax, %%eax\n\t" \
FEP "xor %%edx, %%edx\n\t" \
@@ -173,9 +177,9 @@ do { \
wrmsr(pmc_msr, 0); \
\
if (this_cpu_has(X86_FEATURE_CLFLUSHOPT)) \
- GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflushopt 1f", FEP); \
+ GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflushopt .", FEP); \
else if (this_cpu_has(X86_FEATURE_CLFLUSH)) \
- GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflush 1f", FEP); \
+ GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflush .", FEP); \
else \
GUEST_MEASURE_EVENT(_ctrl_msr, _value, "nop", FEP); \
\
--
2.45.2.803.g4e1b14247a-goog
next prev parent reply other threads:[~2024-06-28 0:56 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-28 0:55 [PATCH 0/2] KVM: selftests: Fix PMU counters test flakiness Sean Christopherson
2024-06-28 0:55 ` [PATCH 1/2] KVM: selftests: Rework macros in PMU counters test to prep for multi-insn loop Sean Christopherson
2024-06-28 0:55 ` Sean Christopherson [this message]
2024-06-28 22:55 ` [PATCH 0/2] KVM: selftests: Fix PMU counters test flakiness Sean Christopherson
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=20240628005558.3835480-3-seanjc@google.com \
--to=seanjc@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mlevitsk@redhat.com \
--cc=pbonzini@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®