[dpdk-dev] [PATCH v3 14/15] vhost: check whether disable software pre-fetch

[Marvin Liu]

Disable software pre-fetch actions on Skylake and later platforms.
Hardware can fetch needed data for vhost, additional software pre-fetch
will impact performance.

Signed-off-by: Marvin Liu <yong.liu at intel.com>

diff --git a/lib/librte_vhost/Makefile b/lib/librte_vhost/Makefile
index 30839a001..5f3b42e56 100644
--- a/lib/librte_vhost/Makefile
+++ b/lib/librte_vhost/Makefile
@@ -16,6 +16,12 @@ CFLAGS += -I vhost_user
 CFLAGS += -fno-strict-aliasing
 LDLIBS += -lpthread
 
+AVX512_SUPPORT=$(shell $(CC) -march=native -dM -E - </dev/null |grep AVX512F)
+
+ifneq ($(AVX512_SUPPORT),)
+CFLAGS += -DDISABLE_SWPREFETCH
+endif
+
 ifeq ($(RTE_TOOLCHAIN), gcc)
 ifeq ($(shell test $(GCC_VERSION) -ge 83 && echo 1), 1)
 CFLAGS += -DSUPPORT_GCC_UNROLL_PRAGMA
diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index 20624efdc..e3872e384 100644
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -1075,7 +1075,9 @@ virtio_dev_rx_batch_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
 
 	UNROLL_PRAGMA(UNROLL_PRAGMA_PARAM)
 	for (i = 0; i < PACKED_BATCH_SIZE; i++) {
+#ifndef DISABLE_SWPREFETCH
 		rte_prefetch0((void *)(uintptr_t)desc_addrs[i]);
+#endif
 		hdrs[i] = (struct virtio_net_hdr_mrg_rxbuf *)
 					(uintptr_t)desc_addrs[i];
 		lens[i] = pkts[i]->pkt_len + dev->vhost_hlen;
@@ -1144,8 +1146,10 @@ virtio_dev_rx_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	uint32_t remained = count;
 
 	do {
+#ifndef DISABLE_SWPREFETCH
 		rte_prefetch0(&vq->desc_packed[vq->last_avail_idx &
 			(vq->size - 1)]);
+#endif
 		if (remained >= PACKED_BATCH_SIZE) {
 			if (!virtio_dev_rx_batch_packed(dev, vq, pkts)) {
 				pkt_idx += PACKED_BATCH_SIZE;
@@ -1790,7 +1794,9 @@ virtio_dev_tx_batch_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
 
 	UNROLL_PRAGMA(UNROLL_PRAGMA_PARAM)
 	for (i = 0; i < PACKED_BATCH_SIZE; i++) {
+#ifndef DISABLE_SWPREFETCH
 		rte_prefetch0((void *)(uintptr_t)desc_addrs[i]);
+#endif
 		rte_memcpy(rte_pktmbuf_mtod_offset(pkts[i], void *, 0),
 			   (void *)(uintptr_t)(desc_addrs[i] + buf_offset),
 			   pkts[i]->pkt_len);
@@ -2046,8 +2052,10 @@ virtio_dev_tx_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	uint32_t remained = count;
 
 	do {
+#ifndef DISABLE_SWPREFETCH
 		rte_prefetch0(&vq->desc_packed[vq->last_avail_idx &
 		       (vq->size - 1)]);
+#endif
 
 		if (remained >= PACKED_BATCH_SIZE) {
 			if (!virtio_dev_tx_batch_packed(dev, vq, mbuf_pool,
-- 
2.17.1