DPDK patches and discussions
 help / color / mirror / Atom feed
From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: Marvin Liu <yong.liu@intel.com>,
	xiaolong.ye@intel.com, zhihong.wang@intel.com
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH v10 6/9] net/virtio: add vectorized packed ring Rx path
Date: Mon, 27 Apr 2020 13:20:53 +0200	[thread overview]
Message-ID: <672a584a-46d1-c78b-7b21-9ed7bc060814@redhat.com> (raw)
In-Reply-To: <20200426021943.43158-7-yong.liu@intel.com>



On 4/26/20 4:19 AM, Marvin Liu wrote:
> Optimize packed ring Rx path with SIMD instructions. Solution of
> optimization is pretty like vhost, is that split path into batch and
> single functions. Batch function is further optimized by AVX512
> instructions. Also pad desc extra structure to 16 bytes aligned, thus
> four elements will be saved in one batch.
> 
> Signed-off-by: Marvin Liu <yong.liu@intel.com>
> 
> diff --git a/drivers/net/virtio/Makefile b/drivers/net/virtio/Makefile
> index c9edb84ee..102b1deab 100644
> --- a/drivers/net/virtio/Makefile
> +++ b/drivers/net/virtio/Makefile
> @@ -36,6 +36,41 @@ else ifneq ($(filter y,$(CONFIG_RTE_ARCH_ARM) $(CONFIG_RTE_ARCH_ARM64)),)
>  SRCS-$(CONFIG_RTE_LIBRTE_VIRTIO_PMD) += virtio_rxtx_simple_neon.c
>  endif
>  
> +ifneq ($(FORCE_DISABLE_AVX512), y)
> +	CC_AVX512_SUPPORT=\
> +	$(shell $(CC) -march=native -dM -E - </dev/null 2>&1 | \
> +	sed '/./{H;$$!d} ; x ; /AVX512F/!d; /AVX512BW/!d; /AVX512VL/!d' | \
> +	grep -q AVX512 && echo 1)
> +endif
> +
> +ifeq ($(CC_AVX512_SUPPORT), 1)
> +CFLAGS += -DCC_AVX512_SUPPORT
> +SRCS-$(CONFIG_RTE_LIBRTE_VIRTIO_PMD) += virtio_rxtx_packed_avx.c
> +
> +ifeq ($(RTE_TOOLCHAIN), gcc)
> +ifeq ($(shell test $(GCC_VERSION) -ge 83 && echo 1), 1)
> +CFLAGS += -DVIRTIO_GCC_UNROLL_PRAGMA
> +endif
> +endif
> +
> +ifeq ($(RTE_TOOLCHAIN), clang)
> +ifeq ($(shell test $(CLANG_MAJOR_VERSION)$(CLANG_MINOR_VERSION) -ge 37 && echo 1), 1)
> +CFLAGS += -DVIRTIO_CLANG_UNROLL_PRAGMA
> +endif
> +endif
> +
> +ifeq ($(RTE_TOOLCHAIN), icc)
> +ifeq ($(shell test $(ICC_MAJOR_VERSION) -ge 16 && echo 1), 1)
> +CFLAGS += -DVIRTIO_ICC_UNROLL_PRAGMA
> +endif
> +endif
> +
> +CFLAGS_virtio_rxtx_packed_avx.o += -mavx512f -mavx512bw -mavx512vl
> +ifeq ($(shell test $(GCC_VERSION) -ge 100 && echo 1), 1)
> +CFLAGS_virtio_rxtx_packed_avx.o += -Wno-zero-length-bounds
> +endif
> +endif
> +
>  ifeq ($(CONFIG_RTE_VIRTIO_USER),y)
>  SRCS-$(CONFIG_RTE_LIBRTE_VIRTIO_PMD) += virtio_user/vhost_user.c
>  SRCS-$(CONFIG_RTE_LIBRTE_VIRTIO_PMD) += virtio_user/vhost_kernel.c
> diff --git a/drivers/net/virtio/meson.build b/drivers/net/virtio/meson.build
> index 15150eea1..8e68c3039 100644
> --- a/drivers/net/virtio/meson.build
> +++ b/drivers/net/virtio/meson.build
> @@ -9,6 +9,20 @@ sources += files('virtio_ethdev.c',
>  deps += ['kvargs', 'bus_pci']
>  
>  if arch_subdir == 'x86'
> +	if '-mno-avx512f' not in machine_args
> +		if cc.has_argument('-mavx512f') and cc.has_argument('-mavx512vl') and cc.has_argument('-mavx512bw')
> +			cflags += ['-mavx512f', '-mavx512bw', '-mavx512vl']
> +			cflags += ['-DCC_AVX512_SUPPORT']
> +			if (toolchain == 'gcc' and cc.version().version_compare('>=8.3.0'))
> +				cflags += '-DVHOST_GCC_UNROLL_PRAGMA'
> +			elif (toolchain == 'clang' and cc.version().version_compare('>=3.7.0'))
> +				cflags += '-DVHOST_CLANG_UNROLL_PRAGMA'
> +			elif (toolchain == 'icc' and cc.version().version_compare('>=16.0.0'))
> +				cflags += '-DVHOST_ICC_UNROLL_PRAGMA'
> +			endif
> +			sources += files('virtio_rxtx_packed_avx.c')
> +		endif
> +	endif
>  	sources += files('virtio_rxtx_simple_sse.c')
>  elif arch_subdir == 'ppc'
>  	sources += files('virtio_rxtx_simple_altivec.c')
> diff --git a/drivers/net/virtio/virtio_ethdev.h b/drivers/net/virtio/virtio_ethdev.h
> index febaf17a8..5c112cac7 100644
> --- a/drivers/net/virtio/virtio_ethdev.h
> +++ b/drivers/net/virtio/virtio_ethdev.h
> @@ -105,6 +105,9 @@ uint16_t virtio_xmit_pkts_inorder(void *tx_queue, struct rte_mbuf **tx_pkts,
>  uint16_t virtio_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
>  		uint16_t nb_pkts);
>  
> +uint16_t virtio_recv_pkts_packed_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
> +		uint16_t nb_pkts);
> +
>  int eth_virtio_dev_init(struct rte_eth_dev *eth_dev);
>  
>  void virtio_interrupt_handler(void *param);
> diff --git a/drivers/net/virtio/virtio_rxtx.c b/drivers/net/virtio/virtio_rxtx.c
> index a549991aa..534562cca 100644
> --- a/drivers/net/virtio/virtio_rxtx.c
> +++ b/drivers/net/virtio/virtio_rxtx.c
> @@ -2030,3 +2030,11 @@ virtio_xmit_pkts_inorder(void *tx_queue,
>  
>  	return nb_tx;
>  }
> +
> +__rte_weak uint16_t
> +virtio_recv_pkts_packed_vec(void *rx_queue __rte_unused,
> +			    struct rte_mbuf **rx_pkts __rte_unused,
> +			    uint16_t nb_pkts __rte_unused)
> +{
> +	return 0;
> +}
> diff --git a/drivers/net/virtio/virtio_rxtx_packed_avx.c b/drivers/net/virtio/virtio_rxtx_packed_avx.c
> new file mode 100644
> index 000000000..8a7b459eb
> --- /dev/null
> +++ b/drivers/net/virtio/virtio_rxtx_packed_avx.c
> @@ -0,0 +1,374 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2010-2020 Intel Corporation
> + */
> +
> +#include <stdint.h>
> +#include <stdio.h>
> +#include <stdlib.h>
> +#include <string.h>
> +#include <errno.h>
> +
> +#include <rte_net.h>
> +
> +#include "virtio_logs.h"
> +#include "virtio_ethdev.h"
> +#include "virtio_pci.h"
> +#include "virtqueue.h"
> +
> +#define BYTE_SIZE 8
> +/* flag bits offset in packed ring desc higher 64bits */
> +#define FLAGS_BITS_OFFSET ((offsetof(struct vring_packed_desc, flags) - \
> +	offsetof(struct vring_packed_desc, len)) * BYTE_SIZE)
> +
> +#define PACKED_FLAGS_MASK ((0ULL | VRING_PACKED_DESC_F_AVAIL_USED) << \
> +	FLAGS_BITS_OFFSET)
> +
> +#define PACKED_BATCH_SIZE (RTE_CACHE_LINE_SIZE / \
> +	sizeof(struct vring_packed_desc))
> +#define PACKED_BATCH_MASK (PACKED_BATCH_SIZE - 1)
> +
> +#ifdef VIRTIO_GCC_UNROLL_PRAGMA
> +#define virtio_for_each_try_unroll(iter, val, size) _Pragma("GCC unroll 4") \
> +	for (iter = val; iter < size; iter++)
> +#endif
> +
> +#ifdef VIRTIO_CLANG_UNROLL_PRAGMA
> +#define virtio_for_each_try_unroll(iter, val, size) _Pragma("unroll 4") \
> +	for (iter = val; iter < size; iter++)
> +#endif
> +
> +#ifdef VIRTIO_ICC_UNROLL_PRAGMA
> +#define virtio_for_each_try_unroll(iter, val, size) _Pragma("unroll (4)") \
> +	for (iter = val; iter < size; iter++)
> +#endif
> +
> +#ifndef virtio_for_each_try_unroll
> +#define virtio_for_each_try_unroll(iter, val, num) \
> +	for (iter = val; iter < num; iter++)
> +#endif
> +
> +static inline void
> +virtio_update_batch_stats(struct virtnet_stats *stats,
> +			  uint16_t pkt_len1,
> +			  uint16_t pkt_len2,
> +			  uint16_t pkt_len3,
> +			  uint16_t pkt_len4)
> +{
> +	stats->bytes += pkt_len1;
> +	stats->bytes += pkt_len2;
> +	stats->bytes += pkt_len3;
> +	stats->bytes += pkt_len4;
> +}
> +
> +/* Optionally fill offload information in structure */
> +static inline int
> +virtio_vec_rx_offload(struct rte_mbuf *m, struct virtio_net_hdr *hdr)
> +{
> +	struct rte_net_hdr_lens hdr_lens;
> +	uint32_t hdrlen, ptype;
> +	int l4_supported = 0;
> +
> +	/* nothing to do */
> +	if (hdr->flags == 0)
> +		return 0;
> +
> +	/* GSO not support in vec path, skip check */
> +	m->ol_flags |= PKT_RX_IP_CKSUM_UNKNOWN;
> +
> +	ptype = rte_net_get_ptype(m, &hdr_lens, RTE_PTYPE_ALL_MASK);
> +	m->packet_type = ptype;
> +	if ((ptype & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_TCP ||
> +	    (ptype & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_UDP ||
> +	    (ptype & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_SCTP)
> +		l4_supported = 1;
> +
> +	if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
> +		hdrlen = hdr_lens.l2_len + hdr_lens.l3_len + hdr_lens.l4_len;
> +		if (hdr->csum_start <= hdrlen && l4_supported) {
> +			m->ol_flags |= PKT_RX_L4_CKSUM_NONE;
> +		} else {
> +			/* Unknown proto or tunnel, do sw cksum. We can assume
> +			 * the cksum field is in the first segment since the
> +			 * buffers we provided to the host are large enough.
> +			 * In case of SCTP, this will be wrong since it's a CRC
> +			 * but there's nothing we can do.
> +			 */
> +			uint16_t csum = 0, off;
> +
> +			rte_raw_cksum_mbuf(m, hdr->csum_start,
> +				rte_pktmbuf_pkt_len(m) - hdr->csum_start,
> +				&csum);
> +			if (likely(csum != 0xffff))
> +				csum = ~csum;
> +			off = hdr->csum_offset + hdr->csum_start;
> +			if (rte_pktmbuf_data_len(m) >= off + 1)
> +				*rte_pktmbuf_mtod_offset(m, uint16_t *,
> +					off) = csum;
> +		}
> +	} else if (hdr->flags & VIRTIO_NET_HDR_F_DATA_VALID && l4_supported) {
> +		m->ol_flags |= PKT_RX_L4_CKSUM_GOOD;
> +	}
> +
> +	return 0;
> +}
> +
> +static inline uint16_t
> +virtqueue_dequeue_batch_packed_vec(struct virtnet_rx *rxvq,
> +				   struct rte_mbuf **rx_pkts)
> +{
> +	struct virtqueue *vq = rxvq->vq;
> +	struct virtio_hw *hw = vq->hw;
> +	uint16_t hdr_size = hw->vtnet_hdr_size;
> +	uint64_t addrs[PACKED_BATCH_SIZE];
> +	uint16_t id = vq->vq_used_cons_idx;
> +	uint8_t desc_stats;
> +	uint16_t i;
> +	void *desc_addr;
> +
> +	if (id & PACKED_BATCH_MASK)
> +		return -1;
> +
> +	if (unlikely((id + PACKED_BATCH_SIZE) > vq->vq_nentries))
> +		return -1;
> +
> +	/* only care avail/used bits */
> +	__m512i v_mask = _mm512_maskz_set1_epi64(0xaa, PACKED_FLAGS_MASK);
> +	desc_addr = &vq->vq_packed.ring.desc[id];
> +
> +	__m512i v_desc = _mm512_loadu_si512(desc_addr);
> +	__m512i v_flag = _mm512_and_epi64(v_desc, v_mask);
> +
> +	__m512i v_used_flag = _mm512_setzero_si512();
> +	if (vq->vq_packed.used_wrap_counter)
> +		v_used_flag = _mm512_maskz_set1_epi64(0xaa, PACKED_FLAGS_MASK);
> +
> +	/* Check all descs are used */
> +	desc_stats = _mm512_cmpneq_epu64_mask(v_flag, v_used_flag);
> +	if (desc_stats)
> +		return -1;
> +
> +	virtio_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
> +		rx_pkts[i] = (struct rte_mbuf *)vq->vq_descx[id + i].cookie;
> +		rte_packet_prefetch(rte_pktmbuf_mtod(rx_pkts[i], void *));
> +
> +		addrs[i] = (uint64_t)rx_pkts[i]->rx_descriptor_fields1;
> +	}
> +
> +	/*
> +	 * load len from desc, store into mbuf pkt_len and data_len
> +	 * len limiated by l6bit buf_len, pkt_len[16:31] can be ignored
> +	 */
> +	const __mmask16 mask = 0x6 | 0x6 << 4 | 0x6 << 8 | 0x6 << 12;
> +	__m512i values = _mm512_maskz_shuffle_epi32(mask, v_desc, 0xAA);
> +
> +	/* reduce hdr_len from pkt_len and data_len */
> +	__m512i mbuf_len_offset = _mm512_maskz_set1_epi32(mask,
> +			(uint32_t)-hdr_size);
> +
> +	__m512i v_value = _mm512_add_epi32(values, mbuf_len_offset);
> +
> +	/* assert offset of data_len */
> +	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, data_len) !=
> +		offsetof(struct rte_mbuf, rx_descriptor_fields1) + 8);
> +
> +	__m512i v_index = _mm512_set_epi64(addrs[3] + 8, addrs[3],
> +					   addrs[2] + 8, addrs[2],
> +					   addrs[1] + 8, addrs[1],
> +					   addrs[0] + 8, addrs[0]);
> +	/* batch store into mbufs */
> +	_mm512_i64scatter_epi64(0, v_index, v_value, 1);
> +
> +	if (hw->has_rx_offload) {
> +		virtio_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
> +			char *addr = (char *)rx_pkts[i]->buf_addr +
> +				RTE_PKTMBUF_HEADROOM - hdr_size;
> +			virtio_vec_rx_offload(rx_pkts[i],
> +					(struct virtio_net_hdr *)addr);
> +		}
> +	}
> +
> +	virtio_update_batch_stats(&rxvq->stats, rx_pkts[0]->pkt_len,
> +			rx_pkts[1]->pkt_len, rx_pkts[2]->pkt_len,
> +			rx_pkts[3]->pkt_len);
> +
> +	vq->vq_free_cnt += PACKED_BATCH_SIZE;
> +
> +	vq->vq_used_cons_idx += PACKED_BATCH_SIZE;
> +	if (vq->vq_used_cons_idx >= vq->vq_nentries) {
> +		vq->vq_used_cons_idx -= vq->vq_nentries;
> +		vq->vq_packed.used_wrap_counter ^= 1;
> +	}
> +
> +	return 0;
> +}
> +
> +static uint16_t
> +virtqueue_dequeue_single_packed_vec(struct virtnet_rx *rxvq,
> +				    struct rte_mbuf **rx_pkts)
> +{
> +	uint16_t used_idx, id;
> +	uint32_t len;
> +	struct virtqueue *vq = rxvq->vq;
> +	struct virtio_hw *hw = vq->hw;
> +	uint32_t hdr_size = hw->vtnet_hdr_size;
> +	struct virtio_net_hdr *hdr;
> +	struct vring_packed_desc *desc;
> +	struct rte_mbuf *cookie;
> +
> +	desc = vq->vq_packed.ring.desc;
> +	used_idx = vq->vq_used_cons_idx;
> +	if (!desc_is_used(&desc[used_idx], vq))
> +		return -1;
> +
> +	len = desc[used_idx].len;
> +	id = desc[used_idx].id;
> +	cookie = (struct rte_mbuf *)vq->vq_descx[id].cookie;
> +	if (unlikely(cookie == NULL)) {
> +		PMD_DRV_LOG(ERR, "vring descriptor with no mbuf cookie at %u",
> +				vq->vq_used_cons_idx);
> +		return -1;
> +	}
> +	rte_prefetch0(cookie);
> +	rte_packet_prefetch(rte_pktmbuf_mtod(cookie, void *));
> +
> +	cookie->data_off = RTE_PKTMBUF_HEADROOM;
> +	cookie->ol_flags = 0;
> +	cookie->pkt_len = (uint32_t)(len - hdr_size);
> +	cookie->data_len = (uint32_t)(len - hdr_size);
> +
> +	hdr = (struct virtio_net_hdr *)((char *)cookie->buf_addr +
> +					RTE_PKTMBUF_HEADROOM - hdr_size);
> +	if (hw->has_rx_offload)
> +		virtio_vec_rx_offload(cookie, hdr);
> +
> +	*rx_pkts = cookie;
> +
> +	rxvq->stats.bytes += cookie->pkt_len;
> +
> +	vq->vq_free_cnt++;
> +	vq->vq_used_cons_idx++;
> +	if (vq->vq_used_cons_idx >= vq->vq_nentries) {
> +		vq->vq_used_cons_idx -= vq->vq_nentries;
> +		vq->vq_packed.used_wrap_counter ^= 1;
> +	}
> +
> +	return 0;
> +}
> +
> +static inline void
> +virtio_recv_refill_packed_vec(struct virtnet_rx *rxvq,
> +			      struct rte_mbuf **cookie,
> +			      uint16_t num)
> +{
> +	struct virtqueue *vq = rxvq->vq;
> +	struct vring_packed_desc *start_dp = vq->vq_packed.ring.desc;
> +	uint16_t flags = vq->vq_packed.cached_flags;
> +	struct virtio_hw *hw = vq->hw;
> +	struct vq_desc_extra *dxp;
> +	uint16_t idx, i;
> +	uint16_t batch_num, total_num = 0;
> +	uint16_t head_idx = vq->vq_avail_idx;
> +	uint16_t head_flag = vq->vq_packed.cached_flags;
> +	uint64_t addr;
> +
> +	do {
> +		idx = vq->vq_avail_idx;
> +
> +		batch_num = PACKED_BATCH_SIZE;
> +		if (unlikely((idx + PACKED_BATCH_SIZE) > vq->vq_nentries))
> +			batch_num = vq->vq_nentries - idx;
> +		if (unlikely((total_num + batch_num) > num))
> +			batch_num = num - total_num;
> +
> +		virtio_for_each_try_unroll(i, 0, batch_num) {
> +			dxp = &vq->vq_descx[idx + i];
> +			dxp->cookie = (void *)cookie[total_num + i];
> +
> +			addr = VIRTIO_MBUF_ADDR(cookie[total_num + i], vq) +
> +				RTE_PKTMBUF_HEADROOM - hw->vtnet_hdr_size;
> +			start_dp[idx + i].addr = addr;
> +			start_dp[idx + i].len = cookie[total_num + i]->buf_len
> +				- RTE_PKTMBUF_HEADROOM + hw->vtnet_hdr_size;
> +			if (total_num || i) {
> +				virtqueue_store_flags_packed(&start_dp[idx + i],
> +						flags, hw->weak_barriers);
> +			}
> +		}
> +
> +		vq->vq_avail_idx += batch_num;
> +		if (vq->vq_avail_idx >= vq->vq_nentries) {
> +			vq->vq_avail_idx -= vq->vq_nentries;
> +			vq->vq_packed.cached_flags ^=
> +				VRING_PACKED_DESC_F_AVAIL_USED;
> +			flags = vq->vq_packed.cached_flags;
> +		}
> +		total_num += batch_num;
> +	} while (total_num < num);
> +
> +	virtqueue_store_flags_packed(&start_dp[head_idx], head_flag,
> +				hw->weak_barriers);
> +	vq->vq_free_cnt = (uint16_t)(vq->vq_free_cnt - num);
> +}
> +
> +uint16_t
> +virtio_recv_pkts_packed_vec(void *rx_queue,
> +			    struct rte_mbuf **rx_pkts,
> +			    uint16_t nb_pkts)
> +{
> +	struct virtnet_rx *rxvq = rx_queue;
> +	struct virtqueue *vq = rxvq->vq;
> +	struct virtio_hw *hw = vq->hw;
> +	uint16_t num, nb_rx = 0;
> +	uint32_t nb_enqueued = 0;
> +	uint16_t free_cnt = vq->vq_free_thresh;
> +
> +	if (unlikely(hw->started == 0))
> +		return nb_rx;
> +
> +	num = RTE_MIN(VIRTIO_MBUF_BURST_SZ, nb_pkts);
> +	if (likely(num > PACKED_BATCH_SIZE))
> +		num = num - ((vq->vq_used_cons_idx + num) % PACKED_BATCH_SIZE);
> +
> +	while (num) {
> +		if (!virtqueue_dequeue_batch_packed_vec(rxvq,
> +					&rx_pkts[nb_rx])) {
> +			nb_rx += PACKED_BATCH_SIZE;
> +			num -= PACKED_BATCH_SIZE;
> +			continue;
> +		}
> +		if (!virtqueue_dequeue_single_packed_vec(rxvq,
> +					&rx_pkts[nb_rx])) {
> +			nb_rx++;
> +			num--;
> +			continue;
> +		}
> +		break;
> +	};
> +
> +	PMD_RX_LOG(DEBUG, "dequeue:%d", num);
> +
> +	rxvq->stats.packets += nb_rx;
> +
> +	if (likely(vq->vq_free_cnt >= free_cnt)) {
> +		struct rte_mbuf *new_pkts[free_cnt];
> +		if (likely(rte_pktmbuf_alloc_bulk(rxvq->mpool, new_pkts,
> +						free_cnt) == 0)) {
> +			virtio_recv_refill_packed_vec(rxvq, new_pkts,
> +					free_cnt);
> +			nb_enqueued += free_cnt;
> +		} else {
> +			struct rte_eth_dev *dev =
> +				&rte_eth_devices[rxvq->port_id];
> +			dev->data->rx_mbuf_alloc_failed += free_cnt;
> +		}
> +	}
> +
> +	if (likely(nb_enqueued)) {
> +		if (unlikely(virtqueue_kick_prepare_packed(vq))) {
> +			virtqueue_notify(vq);
> +			PMD_RX_LOG(DEBUG, "Notified");
> +		}
> +	}
> +
> +	return nb_rx;
> +}
> diff --git a/drivers/net/virtio/virtio_user_ethdev.c b/drivers/net/virtio/virtio_user_ethdev.c
> index 40ad786cc..c54698ad1 100644
> --- a/drivers/net/virtio/virtio_user_ethdev.c
> +++ b/drivers/net/virtio/virtio_user_ethdev.c
> @@ -528,6 +528,7 @@ virtio_user_eth_dev_alloc(struct rte_vdev_device *vdev)
>  	hw->use_msix = 1;
>  	hw->modern   = 0;
>  	hw->use_vec_rx = 0;
> +	hw->use_vec_tx = 0;
>  	hw->use_inorder_rx = 0;
>  	hw->use_inorder_tx = 0;
>  	hw->virtio_user_dev = dev;
> @@ -739,8 +740,19 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
>  		goto end;
>  	}
>  
> -	if (vectorized)
> -		hw->use_vec_rx = 1;
> +	if (vectorized) {
> +		if (packed_vq) {
> +#if defined(CC_AVX512_SUPPORT)
> +			hw->use_vec_rx = 1;
> +			hw->use_vec_tx = 1;
> +#else
> +			PMD_INIT_LOG(INFO,
> +				"building environment do not support packed ring vectorized");
> +#endif
> +		} else {
> +			hw->use_vec_rx = 1;
> +		}
> +	}
>  
>  	rte_eth_dev_probing_finish(eth_dev);
>  	ret = 0;
> diff --git a/drivers/net/virtio/virtqueue.h b/drivers/net/virtio/virtqueue.h
> index ca1c10499..ce0340743 100644
> --- a/drivers/net/virtio/virtqueue.h
> +++ b/drivers/net/virtio/virtqueue.h
> @@ -239,7 +239,8 @@ struct vq_desc_extra {
>  	void *cookie;
>  	uint16_t ndescs;
>  	uint16_t next;
> -};
> +	uint8_t padding[4];
> +} __rte_packed __rte_aligned(16);

Can't this introduce a performance impact for the non-vectorized
case? I think of worse cache liens utilization.

For example with a burst of 32 descriptors with 32B cachelines, before
it would take 14 cachelines, after 16. So for each burst, one could face
2 extra cache misses.

If you could run non-vectorized benchamrks with and without that patch,
I would be grateful.

Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>

Thanks,
Maxime


  reply	other threads:[~2020-04-27 11:21 UTC|newest]

Thread overview: 162+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-13 17:42 [dpdk-dev] [PATCH v1 0/7] vectorize virtio packed ring datapath Marvin Liu
2020-03-13 17:42 ` [dpdk-dev] [PATCH v1 1/7] net/virtio: add Rx free threshold setting Marvin Liu
2020-03-13 17:42 ` [dpdk-dev] [PATCH v1 2/7] net/virtio-user: add LRO parameter Marvin Liu
2020-03-13 17:42 ` [dpdk-dev] [PATCH v1 3/7] net/virtio: add vectorized packed ring Rx function Marvin Liu
2020-03-13 17:42 ` [dpdk-dev] [PATCH v1 4/7] net/virtio: reuse packed ring xmit functions Marvin Liu
2020-03-13 17:42 ` [dpdk-dev] [PATCH v1 5/7] net/virtio: add vectorized packed ring Tx function Marvin Liu
2020-03-13 17:42 ` [dpdk-dev] [PATCH v1 6/7] net/virtio: add election for vectorized datapath Marvin Liu
2020-03-13 17:42 ` [dpdk-dev] [PATCH v1 7/7] net/virtio: support meson build Marvin Liu
2020-03-27 16:54 ` [dpdk-dev] [PATCH v2 0/7] add packed ring vectorized datapath Marvin Liu
2020-03-27 16:54   ` [dpdk-dev] [PATCH v2 1/7] net/virtio: add Rx free threshold setting Marvin Liu
2020-03-27 16:54   ` [dpdk-dev] [PATCH v2 2/7] net/virtio-user: add vectorized packed ring parameter Marvin Liu
2020-03-27 16:54   ` [dpdk-dev] [PATCH v2 3/7] net/virtio: add vectorized packed ring Rx function Marvin Liu
2020-03-27 16:54   ` [dpdk-dev] [PATCH v2 4/7] net/virtio: reuse packed ring xmit functions Marvin Liu
2020-03-27 16:54   ` [dpdk-dev] [PATCH v2 5/7] net/virtio: add vectorized packed ring Tx datapath Marvin Liu
2020-03-27 16:54   ` [dpdk-dev] [PATCH v2 6/7] net/virtio: add election for vectorized datapath Marvin Liu
2020-03-27 16:54   ` [dpdk-dev] [PATCH v2 7/7] doc: add packed " Marvin Liu
2020-04-08  8:53 ` [dpdk-dev] [PATCH v3 0/7] add packed ring " Marvin Liu
2020-04-08  8:53   ` [dpdk-dev] [PATCH v3 1/7] net/virtio: add Rx free threshold setting Marvin Liu
2020-04-08  6:08     ` Ye Xiaolong
2020-04-08  8:53   ` [dpdk-dev] [PATCH v3 2/7] net/virtio-user: add vectorized packed ring parameter Marvin Liu
2020-04-08  6:22     ` Ye Xiaolong
2020-04-08  7:31       ` Liu, Yong
2020-04-08  8:53   ` [dpdk-dev] [PATCH v3 3/7] net/virtio: add vectorized packed ring Rx function Marvin Liu
2020-04-08  8:53   ` [dpdk-dev] [PATCH v3 4/7] net/virtio: reuse packed ring xmit functions Marvin Liu
2020-04-08  8:53   ` [dpdk-dev] [PATCH v3 5/7] net/virtio: add vectorized packed ring Tx datapath Marvin Liu
2020-04-08  8:53   ` [dpdk-dev] [PATCH v3 6/7] net/virtio: add election for vectorized datapath Marvin Liu
2020-04-08  8:53   ` [dpdk-dev] [PATCH v3 7/7] doc: add packed " Marvin Liu
2020-04-15 16:47 ` [dpdk-dev] [PATCH v4 0/8] add packed ring " Marvin Liu
2020-04-15 16:47   ` [dpdk-dev] [PATCH v4 1/8] net/virtio: enable " Marvin Liu
2020-04-15 16:47   ` [dpdk-dev] [PATCH v4 2/8] net/virtio-user: add vectorized datapath parameter Marvin Liu
2020-04-15 16:47   ` [dpdk-dev] [PATCH v4 3/8] net/virtio: add vectorized packed ring Rx function Marvin Liu
2020-04-15 16:47   ` [dpdk-dev] [PATCH v4 4/8] net/virtio: reuse packed ring xmit functions Marvin Liu
2020-04-15 16:47   ` [dpdk-dev] [PATCH v4 5/8] net/virtio: add vectorized packed ring Tx datapath Marvin Liu
2020-04-15 16:47   ` [dpdk-dev] [PATCH v4 6/8] eal/x86: identify AVX512 extensions flag Marvin Liu
2020-04-15 13:31     ` David Marchand
2020-04-15 14:57       ` Liu, Yong
2020-04-15 16:47   ` [dpdk-dev] [PATCH v4 7/8] net/virtio: add election for vectorized datapath Marvin Liu
2020-04-15 16:47   ` [dpdk-dev] [PATCH v4 8/8] doc: add packed " Marvin Liu
2020-04-16 15:31 ` [dpdk-dev] [PATCH v5 0/9] add packed ring vectorized path Marvin Liu
2020-04-16 15:31   ` [dpdk-dev] [PATCH v5 1/9] net/virtio: add Rx free threshold setting Marvin Liu
2020-04-16 15:31   ` [dpdk-dev] [PATCH v5 2/9] net/virtio: enable vectorized path Marvin Liu
2020-04-16 15:31   ` [dpdk-dev] [PATCH v5 3/9] net/virtio: inorder should depend on feature bit Marvin Liu
2020-04-16 15:31   ` [dpdk-dev] [PATCH v5 4/9] net/virtio-user: add vectorized path parameter Marvin Liu
2020-04-16 15:31   ` [dpdk-dev] [PATCH v5 5/9] net/virtio: add vectorized packed ring Rx path Marvin Liu
2020-04-16 15:31   ` [dpdk-dev] [PATCH v5 6/9] net/virtio: reuse packed ring xmit functions Marvin Liu
2020-04-16 15:31   ` [dpdk-dev] [PATCH v5 7/9] net/virtio: add vectorized packed ring Tx path Marvin Liu
2020-04-16 15:31   ` [dpdk-dev] [PATCH v5 8/9] net/virtio: add election for vectorized path Marvin Liu
2020-04-16 15:31   ` [dpdk-dev] [PATCH v5 9/9] doc: add packed " Marvin Liu
2020-04-16 22:24 ` [dpdk-dev] [PATCH v6 0/9] add packed ring " Marvin Liu
2020-04-16 22:24   ` [dpdk-dev] [PATCH v6 1/9] net/virtio: add Rx free threshold setting Marvin Liu
2020-04-16 22:24   ` [dpdk-dev] [PATCH v6 2/9] net/virtio: enable vectorized path Marvin Liu
2020-04-20 14:08     ` Maxime Coquelin
2020-04-21  6:43       ` Liu, Yong
2020-04-22  8:07         ` Liu, Yong
2020-04-16 22:24   ` [dpdk-dev] [PATCH v6 3/9] net/virtio: inorder should depend on feature bit Marvin Liu
2020-04-16 22:24   ` [dpdk-dev] [PATCH v6 4/9] net/virtio-user: add vectorized path parameter Marvin Liu
2020-04-16 22:24   ` [dpdk-dev] [PATCH v6 5/9] net/virtio: add vectorized packed ring Rx path Marvin Liu
2020-04-16 22:24   ` [dpdk-dev] [PATCH v6 6/9] net/virtio: reuse packed ring xmit functions Marvin Liu
2020-04-16 22:24   ` [dpdk-dev] [PATCH v6 7/9] net/virtio: add vectorized packed ring Tx path Marvin Liu
2020-04-16 22:24   ` [dpdk-dev] [PATCH v6 8/9] net/virtio: add election for vectorized path Marvin Liu
2020-04-16 22:24   ` [dpdk-dev] [PATCH v6 9/9] doc: add packed " Marvin Liu
2020-04-22  6:16 ` [dpdk-dev] [PATCH v7 0/9] add packed ring " Marvin Liu
2020-04-22  6:16   ` [dpdk-dev] [PATCH v7 1/9] net/virtio: add Rx free threshold setting Marvin Liu
2020-04-22  6:16   ` [dpdk-dev] [PATCH v7 2/9] net/virtio: enable vectorized path Marvin Liu
2020-04-22  6:16   ` [dpdk-dev] [PATCH v7 3/9] net/virtio: inorder should depend on feature bit Marvin Liu
2020-04-22  6:16   ` [dpdk-dev] [PATCH v7 4/9] net/virtio-user: add vectorized path parameter Marvin Liu
2020-04-22  6:16   ` [dpdk-dev] [PATCH v7 5/9] net/virtio: add vectorized packed ring Rx path Marvin Liu
2020-04-22  6:16   ` [dpdk-dev] [PATCH v7 6/9] net/virtio: reuse packed ring xmit functions Marvin Liu
2020-04-22  6:16   ` [dpdk-dev] [PATCH v7 7/9] net/virtio: add vectorized packed ring Tx path Marvin Liu
2020-04-22  6:16   ` [dpdk-dev] [PATCH v7 8/9] net/virtio: add election for vectorized path Marvin Liu
2020-04-22  6:16   ` [dpdk-dev] [PATCH v7 9/9] doc: add packed " Marvin Liu
2020-04-23 12:30 ` [dpdk-dev] [PATCH v8 0/9] add packed ring " Marvin Liu
2020-04-23 12:30   ` [dpdk-dev] [PATCH v8 1/9] net/virtio: add Rx free threshold setting Marvin Liu
2020-04-23  8:09     ` Maxime Coquelin
2020-04-23 12:30   ` [dpdk-dev] [PATCH v8 2/9] net/virtio: enable vectorized path Marvin Liu
2020-04-23  8:33     ` Maxime Coquelin
2020-04-23  8:46       ` Liu, Yong
2020-04-23  8:49         ` Maxime Coquelin
2020-04-23  9:59           ` Liu, Yong
2020-04-23 12:31   ` [dpdk-dev] [PATCH v8 3/9] net/virtio: inorder should depend on feature bit Marvin Liu
2020-04-23  8:46     ` Maxime Coquelin
2020-04-23 12:31   ` [dpdk-dev] [PATCH v8 4/9] net/virtio-user: add vectorized path parameter Marvin Liu
2020-04-23 12:31   ` [dpdk-dev] [PATCH v8 5/9] net/virtio: add vectorized packed ring Rx path Marvin Liu
2020-04-23 12:31   ` [dpdk-dev] [PATCH v8 6/9] net/virtio: reuse packed ring xmit functions Marvin Liu
2020-04-23 12:31   ` [dpdk-dev] [PATCH v8 7/9] net/virtio: add vectorized packed ring Tx path Marvin Liu
2020-04-23 12:31   ` [dpdk-dev] [PATCH v8 8/9] net/virtio: add election for vectorized path Marvin Liu
2020-04-23 12:31   ` [dpdk-dev] [PATCH v8 9/9] doc: add packed " Marvin Liu
2020-04-23 15:17   ` [dpdk-dev] [PATCH v8 0/9] add packed ring " Wang, Yinan
2020-04-24  9:24 ` [dpdk-dev] [PATCH v9 " Marvin Liu
2020-04-24  9:24   ` [dpdk-dev] [PATCH v9 1/9] net/virtio: add Rx free threshold setting Marvin Liu
2020-04-24  9:24   ` [dpdk-dev] [PATCH v9 2/9] net/virtio: inorder should depend on feature bit Marvin Liu
2020-04-24  9:24   ` [dpdk-dev] [PATCH v9 3/9] net/virtio: add vectorized devarg Marvin Liu
2020-04-24 11:27     ` Maxime Coquelin
2020-04-24  9:24   ` [dpdk-dev] [PATCH v9 4/9] net/virtio-user: " Marvin Liu
2020-04-24 11:29     ` Maxime Coquelin
2020-04-24  9:24   ` [dpdk-dev] [PATCH v9 5/9] net/virtio: add vectorized packed ring Rx path Marvin Liu
2020-04-24 11:51     ` Maxime Coquelin
2020-04-24 13:12       ` Liu, Yong
2020-04-24 13:33         ` Maxime Coquelin
2020-04-24 13:40           ` Liu, Yong
2020-04-24 15:58             ` Liu, Yong
2020-04-24  9:24   ` [dpdk-dev] [PATCH v9 6/9] net/virtio: reuse packed ring xmit functions Marvin Liu
2020-04-24 12:01     ` Maxime Coquelin
2020-04-24  9:24   ` [dpdk-dev] [PATCH v9 7/9] net/virtio: add vectorized packed ring Tx path Marvin Liu
2020-04-24 12:29     ` Maxime Coquelin
2020-04-24 13:33       ` Liu, Yong
2020-04-24 13:35         ` Maxime Coquelin
2020-04-24 13:47           ` Liu, Yong
2020-04-24  9:24   ` [dpdk-dev] [PATCH v9 8/9] net/virtio: add election for vectorized path Marvin Liu
2020-04-24 13:26     ` Maxime Coquelin
2020-04-24  9:24   ` [dpdk-dev] [PATCH v9 9/9] doc: add packed " Marvin Liu
2020-04-24 13:31     ` Maxime Coquelin
2020-04-26  2:19 ` [dpdk-dev] [PATCH v9 0/9] add packed ring " Marvin Liu
2020-04-26  2:19   ` [dpdk-dev] [PATCH v10 1/9] net/virtio: add Rx free threshold setting Marvin Liu
2020-04-26  2:19   ` [dpdk-dev] [PATCH v10 2/9] net/virtio: inorder should depend on feature bit Marvin Liu
2020-04-26  2:19   ` [dpdk-dev] [PATCH v10 3/9] net/virtio: add vectorized devarg Marvin Liu
2020-04-27 11:12     ` Maxime Coquelin
2020-04-26  2:19   ` [dpdk-dev] [PATCH v10 4/9] net/virtio-user: " Marvin Liu
2020-04-27 11:07     ` Maxime Coquelin
2020-04-28  1:29       ` Liu, Yong
2020-04-26  2:19   ` [dpdk-dev] [PATCH v10 5/9] net/virtio: reuse packed ring functions Marvin Liu
2020-04-27 11:08     ` Maxime Coquelin
2020-04-26  2:19   ` [dpdk-dev] [PATCH v10 6/9] net/virtio: add vectorized packed ring Rx path Marvin Liu
2020-04-27 11:20     ` Maxime Coquelin [this message]
2020-04-28  1:14       ` Liu, Yong
2020-04-28  8:44         ` Maxime Coquelin
2020-04-28 13:01           ` Liu, Yong
2020-04-28 13:46             ` Maxime Coquelin
2020-04-28 14:43               ` Liu, Yong
2020-04-28 14:50                 ` Maxime Coquelin
2020-04-28 15:35                   ` Liu, Yong
2020-04-28 15:40                     ` Maxime Coquelin
2020-04-28 15:55                       ` Liu, Yong
2020-04-28 17:01             ` Liu, Yong
2020-04-26  2:19   ` [dpdk-dev] [PATCH v10 7/9] net/virtio: add vectorized packed ring Tx path Marvin Liu
2020-04-27 11:55     ` Maxime Coquelin
2020-04-26  2:19   ` [dpdk-dev] [PATCH v10 8/9] net/virtio: add election for vectorized path Marvin Liu
2020-04-26  2:19   ` [dpdk-dev] [PATCH v10 9/9] doc: add packed " Marvin Liu
2020-04-28  8:32 ` [dpdk-dev] [PATCH v11 0/9] add packed ring " Marvin Liu
2020-04-28  8:32   ` [dpdk-dev] [PATCH v11 1/9] net/virtio: add Rx free threshold setting Marvin Liu
2020-04-28  8:32   ` [dpdk-dev] [PATCH v11 2/9] net/virtio: inorder should depend on feature bit Marvin Liu
2020-04-28  8:32   ` [dpdk-dev] [PATCH v11 3/9] net/virtio: add vectorized devarg Marvin Liu
2020-04-28  8:32   ` [dpdk-dev] [PATCH v11 4/9] net/virtio-user: " Marvin Liu
2020-04-28  8:32   ` [dpdk-dev] [PATCH v11 5/9] net/virtio: reuse packed ring functions Marvin Liu
2020-04-28  8:32   ` [dpdk-dev] [PATCH v11 6/9] net/virtio: add vectorized packed ring Rx path Marvin Liu
2020-04-30  9:48     ` Ferruh Yigit
2020-04-30 10:23       ` Bruce Richardson
2020-04-30 13:04         ` Ferruh Yigit
2020-04-28  8:32   ` [dpdk-dev] [PATCH v11 7/9] net/virtio: add vectorized packed ring Tx path Marvin Liu
2020-04-28  8:32   ` [dpdk-dev] [PATCH v11 8/9] net/virtio: add election for vectorized path Marvin Liu
2020-04-28  8:32   ` [dpdk-dev] [PATCH v11 9/9] doc: add packed " Marvin Liu
2020-04-29  7:28 ` [dpdk-dev] [PATCH v12 0/9] add packed ring " Marvin Liu
2020-04-29  7:28   ` [dpdk-dev] [PATCH v12 1/9] net/virtio: add Rx free threshold setting Marvin Liu
2020-04-29  7:28   ` [dpdk-dev] [PATCH v12 2/9] net/virtio: inorder should depend on feature bit Marvin Liu
2020-04-29  7:28   ` [dpdk-dev] [PATCH v12 3/9] net/virtio: add vectorized devarg Marvin Liu
2020-04-29  7:28   ` [dpdk-dev] [PATCH v12 4/9] net/virtio-user: " Marvin Liu
2020-04-29  7:28   ` [dpdk-dev] [PATCH v12 5/9] net/virtio: reuse packed ring functions Marvin Liu
2020-04-29  7:28   ` [dpdk-dev] [PATCH v12 6/9] net/virtio: add vectorized packed ring Rx path Marvin Liu
2020-04-29  7:28   ` [dpdk-dev] [PATCH v12 7/9] net/virtio: add vectorized packed ring Tx path Marvin Liu
2020-04-29  7:28   ` [dpdk-dev] [PATCH v12 8/9] net/virtio: add election for vectorized path Marvin Liu
2020-04-29  7:28   ` [dpdk-dev] [PATCH v12 9/9] doc: add packed " Marvin Liu
2020-04-29  8:17   ` [dpdk-dev] [PATCH v12 0/9] add packed ring " Maxime Coquelin

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=672a584a-46d1-c78b-7b21-9ed7bc060814@redhat.com \
    --to=maxime.coquelin@redhat.com \
    --cc=dev@dpdk.org \
    --cc=xiaolong.ye@intel.com \
    --cc=yong.liu@intel.com \
    --cc=zhihong.wang@intel.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;
as well as URLs for NNTP newsgroup(s).