[Qemu-devel] [RFC PATCH v2 2/2] utils: Add prefetch for Thunderx platform

[vijay.kilari@gmail.com]

From: Vijaya Kumar K <Vijaya.Kumar@cavium.com>

Thunderx pass2 chip requires explicit prefetch
instruction to give prefetch hint.

To speed up live migration on Thunderx platform,
prefetch instruction is added in zero buffer check
function.

The below results show live migration time improvement
with prefetch instruction with 1K and 4K page size.
VM with 4 VCPUs, 8GB RAM is migrated.

1K page size, no prefetch
=========================
Migration status: completed
total time: 13012 milliseconds
downtime: 10 milliseconds
setup: 15 milliseconds
transferred ram: 268131 kbytes
throughput: 168.84 mbps
remaining ram: 0 kbytes
total ram: 8519872 kbytes
duplicate: 8338072 pages
skipped: 0 pages
normal: 193335 pages
normal bytes: 193335 kbytes
dirty sync count: 4

1K page size with prefetch
=========================
Migration status: completed
total time: 7493 milliseconds
downtime: 71 milliseconds
setup: 16 milliseconds
transferred ram: 269666 kbytes
throughput: 294.88 mbps
remaining ram: 0 kbytes
total ram: 8519872 kbytes
duplicate: 8340596 pages
skipped: 0 pages
normal: 194837 pages
normal bytes: 194837 kbytes
dirty sync count: 3

4K page size with no prefetch
=============================
Migration status: completed
total time: 10456 milliseconds
downtime: 49 milliseconds
setup: 5 milliseconds
transferred ram: 231726 kbytes
throughput: 181.59 mbps
remaining ram: 0 kbytes
total ram: 8519872 kbytes
duplicate: 2079914 pages
skipped: 0 pages
normal: 53257 pages
normal bytes: 213028 kbytes
dirty sync count: 3

4K page size with prefetch
==========================
Migration status: completed
total time: 3937 milliseconds
downtime: 23 milliseconds
setup: 5 milliseconds
transferred ram: 229283 kbytes
throughput: 477.19 mbps
remaining ram: 0 kbytes
total ram: 8519872 kbytes
duplicate: 2079775 pages
skipped: 0 pages
normal: 52648 pages
normal bytes: 210592 kbytes
dirty sync count: 3

Signed-off-by: Vijaya Kumar K <Vijaya.Kumar@cavium.com>
---
 util/cutils.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/util/cutils.c b/util/cutils.c
index 7505fda..342d1e3 100644
--- a/util/cutils.c
+++ b/util/cutils.c
@@ -186,11 +186,14 @@ int qemu_fdatasync(int fd)
 #define VEC_OR(v1, v2) (_mm_or_si128(v1, v2))
 #elif defined(__aarch64__)
 #include "arm_neon.h"
+#include "qemu/aarch64-cpuid.h"
 #define VECTYPE        uint64x2_t
 #define ALL_EQ(v1, v2) \
         ((vgetq_lane_u64(v1, 0) == vgetq_lane_u64(v2, 0)) && \
          (vgetq_lane_u64(v1, 1) == vgetq_lane_u64(v2, 1)))
 #define VEC_OR(v1, v2) ((v1) | (v2))
+#define VEC_PREFETCH(base, index) \
+        __builtin_prefetch(&base[index], 0, 0);
 #else
 #define VECTYPE        unsigned long
 #define SPLAT(p)       (*(p) * (~0UL / 255))
@@ -200,6 +203,29 @@ int qemu_fdatasync(int fd)
 
 #define BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR 8
 
+static inline void prefetch_vector(const VECTYPE *p, int index)
+{
+#if defined(__aarch64__)
+    get_aarch64_cpu_id();
+    if (is_thunderx_pass2_cpu()) {
+        /* Prefetch first 3 cache lines */
+        VEC_PREFETCH(p, index + BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR);
+        VEC_PREFETCH(p, index + (BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR * 2));
+        VEC_PREFETCH(p, index + (BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR * 3));
+    }
+#endif
+}
+
+static inline void prefetch_vector_loop(const VECTYPE *p, int index)
+{
+#if defined(__aarch64__)
+    if (is_thunderx_pass2_cpu()) {
+        /* Prefetch 4 cache lines ahead from index */
+        VEC_PREFETCH(p, index + (BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR * 4));
+    }
+#endif
+}
+
 static bool
 can_use_buffer_find_nonzero_offset_inner(const void *buf, size_t len)
 {
@@ -246,9 +272,14 @@ static size_t buffer_find_nonzero_offset_inner(const void *buf, size_t len)
         }
     }
 
+    prefetch_vector(p, 0);
+
     for (i = BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR;
          i < len / sizeof(VECTYPE);
          i += BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR) {
+
+        prefetch_vector_loop(p, i);
+
         VECTYPE tmp0 = VEC_OR(p[i + 0], p[i + 1]);
         VECTYPE tmp1 = VEC_OR(p[i + 2], p[i + 3]);
         VECTYPE tmp2 = VEC_OR(p[i + 4], p[i + 5]);
-- 
1.9.1