[PATCH 2/3] KVM: selftests: Collect memory access latency samples

[Colton Lewis <coltonlewis@google.com>]

Collect memory access latency measured in clock cycles.

This introduces a dependency on the timers for ARM and x86. No other
architectures are implemented and their samples will all be 0.

Because keeping all samples is impractical due to the space required
in some cases (pooled memory w/ 64 vcpus would be 64 GB/vcpu * 64
vcpus * 250,000 samples/GB * 8 bytes/sample ~ 8 Gb extra memory just
for samples), resevior sampling is used to only keep a small number of
samples per vcpu (1000 samples in this patch).

Resevoir sampling means despite keeping only a small number of
samples, each sample has an equal chance of making it to the
resevoir. Simple proofs of this can be found online. This makes the
resevoir a good representation of the distribution of samples and
enables calculation of reasonably accurate percentiles.

All samples are stored in a statically allocated flat array for ease
of combining them later. Samples are stored at an offset in this array
calculated by the vcpu index (so vcpu 5 sample 10 would be stored at
address sample_times + 5 * vcpu_idx + 10).

Signed-off-by: Colton Lewis <coltonlewis@google.com>
---
 .../selftests/kvm/lib/perf_test_util.c        | 34 +++++++++++++++++--
 1 file changed, 32 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index a48904b64e19..0311da76bae0 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -4,6 +4,9 @@
  */
 #include <inttypes.h>
 
+#if defined(__aarch64__)
+#include "aarch64/arch_timer.h"
+#endif
 #include "kvm_util.h"
 #include "perf_test_util.h"
 #include "processor.h"
@@ -44,6 +47,18 @@ static struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
 /* Store all samples in a flat array so they can be easily sorted later. */
 uint64_t latency_samples[SAMPLE_CAPACITY];
 
+static uint64_t perf_test_timer_read(void)
+{
+#if defined(__aarch64__)
+	return timer_get_cntct(VIRTUAL);
+#elif defined(__x86_64__)
+	return rdtsc();
+#else
+#warn __func__ " is not implemented for this architecture, will return 0"
+	return 0;
+#endif
+}
+
 /*
  * Continuously write to the first 8 bytes of each page in the
  * specified region.
@@ -59,6 +74,10 @@ void perf_test_guest_code(uint32_t vcpu_idx)
 	int i;
 	struct guest_random_state rand_state =
 		new_guest_random_state(pta->random_seed + vcpu_idx);
+	uint64_t *latency_samples_offset = latency_samples + SAMPLES_PER_VCPU * vcpu_idx;
+	uint64_t count_before;
+	uint64_t count_after;
+	uint32_t maybe_sample;
 
 	gva = vcpu_args->gva;
 	pages = vcpu_args->pages;
@@ -75,10 +94,21 @@ void perf_test_guest_code(uint32_t vcpu_idx)
 
 			addr = gva + (page * pta->guest_page_size);
 
-			if (guest_random_u32(&rand_state) % 100 < pta->write_percent)
+			if (guest_random_u32(&rand_state) % 100 < pta->write_percent) {
+				count_before = perf_test_timer_read();
 				*(uint64_t *)addr = 0x0123456789ABCDEF;
-			else
+				count_after = perf_test_timer_read();
+			} else {
+				count_before = perf_test_timer_read();
 				READ_ONCE(*(uint64_t *)addr);
+				count_after = perf_test_timer_read();
+			}
+
+			maybe_sample = guest_random_u32(&rand_state) % (i + 1);
+			if (i < SAMPLES_PER_VCPU)
+				latency_samples_offset[i] = count_after - count_before;
+			else if (maybe_sample < SAMPLES_PER_VCPU)
+				latency_samples_offset[maybe_sample] = count_after - count_before;
 		}
 
 		GUEST_SYNC(1);
-- 
2.38.1.431.g37b22c650d-goog