From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: Zhihong Wang <zhihong.wang@intel.com>, dev@dpdk.org
Cc: yuanhan.liu@linux.intel.com, thomas.monjalon@6wind.com
Subject: Re: [dpdk-dev] [PATCH v5 2/6] vhost: rewrite enqueue
Date: Mon, 12 Sep 2016 17:42:40 +0200 [thread overview]
Message-ID: <2cc970ca-ea2c-8e3b-069a-9f1ec1182b03@redhat.com> (raw)
In-Reply-To: <1473392368-84903-3-git-send-email-zhihong.wang@intel.com>
Hi,
On 09/09/2016 05:39 AM, Zhihong Wang wrote:
> This patch implements the vhost logic from scratch into a single function
> designed for high performance and better maintainability.
>
> This is the baseline version of the new code, more optimization will be
> added in the following patches in this patch set.
>
> Signed-off-by: Zhihong Wang <zhihong.wang@intel.com>
> ---
> Changes in v5:
>
> 1. Rebase to the latest branch.
>
> 2. Rename variables to keep consistent in naming style.
>
> 3. Small changes like return value adjustment and vertical alignment.
>
> ---
> Changes in v4:
>
> 1. Refactor the code for clearer logic.
>
> 2. Add PRINT_PACKET for debugging.
>
> ---
> Changes in v3:
>
> 1. Rewrite enqueue and delete the obsolete in the same patch.
>
> lib/librte_vhost/virtio_net.c | 514 ++++++++++++------------------------------
> 1 file changed, 138 insertions(+), 376 deletions(-)
>
> diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
> index 0d6e7d9..6f63968 100644
> --- a/lib/librte_vhost/virtio_net.c
> +++ b/lib/librte_vhost/virtio_net.c
> @@ -91,7 +91,7 @@ is_valid_virt_queue_idx(uint32_t idx, int is_tx, uint32_t qp_nb)
> return (is_tx ^ (idx & 1)) == 0 && idx < qp_nb * VIRTIO_QNUM;
> }
>
> -static void
> +static inline void __attribute__((always_inline))
> virtio_enqueue_offload(struct rte_mbuf *m_buf, struct virtio_net_hdr *net_hdr)
> {
> if (m_buf->ol_flags & PKT_TX_L4_MASK) {
> @@ -112,6 +112,10 @@ virtio_enqueue_offload(struct rte_mbuf *m_buf, struct virtio_net_hdr *net_hdr)
> cksum));
> break;
> }
> + } else {
> + net_hdr->flags = 0;
> + net_hdr->csum_start = 0;
> + net_hdr->csum_offset = 0;
> }
>
> if (m_buf->ol_flags & PKT_TX_TCP_SEG) {
> @@ -122,439 +126,197 @@ virtio_enqueue_offload(struct rte_mbuf *m_buf, struct virtio_net_hdr *net_hdr)
> net_hdr->gso_size = m_buf->tso_segsz;
> net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len
> + m_buf->l4_len;
> + } else {
> + net_hdr->gso_type = 0;
> + net_hdr->hdr_len = 0;
> + net_hdr->gso_size = 0;
> }
> }
>
> -static inline void
> -copy_virtio_net_hdr(struct virtio_net *dev, uint64_t desc_addr,
> - struct virtio_net_hdr_mrg_rxbuf hdr)
> +static inline void __attribute__((always_inline))
> +update_used_ring(struct virtio_net *dev, struct vhost_virtqueue *vq,
> + uint32_t desc_chain_head, uint32_t desc_chain_len)
> {
> - if (dev->vhost_hlen == sizeof(struct virtio_net_hdr_mrg_rxbuf))
> - *(struct virtio_net_hdr_mrg_rxbuf *)(uintptr_t)desc_addr = hdr;
> - else
> - *(struct virtio_net_hdr *)(uintptr_t)desc_addr = hdr.hdr;
> + uint32_t used_idx = vq->last_used_idx & (vq->size - 1);
> +
> + vq->used->ring[used_idx].id = desc_chain_head;
> + vq->used->ring[used_idx].len = desc_chain_len;
> + vq->last_used_idx++;
> + vhost_log_used_vring(dev, vq, offsetof(struct vring_used,
> + ring[used_idx]),
> + sizeof(vq->used->ring[used_idx]));
> }
>
> static inline int __attribute__((always_inline))
> -copy_mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
> - struct rte_mbuf *m, uint16_t desc_idx)
> +enqueue_packet(struct virtio_net *dev, struct vhost_virtqueue *vq,
> + uint16_t avail_idx, struct rte_mbuf *mbuf,
> + uint32_t is_mrg_rxbuf)
> {
> - uint32_t desc_avail, desc_offset;
> - uint32_t mbuf_avail, mbuf_offset;
> - uint32_t cpy_len;
> + struct virtio_net_hdr_mrg_rxbuf *virtio_hdr;
> struct vring_desc *desc;
> uint64_t desc_addr;
> - struct virtio_net_hdr_mrg_rxbuf virtio_hdr = {{0, 0, 0, 0, 0, 0}, 0};
> + uint32_t desc_chain_head;
> + uint32_t desc_chain_len;
> + uint32_t desc_current;
> + uint32_t desc_offset;
> + uint32_t mbuf_len;
> + uint32_t mbuf_avail;
> + uint32_t cpy_len;
> + uint32_t num_buffers = 0;
>
> - desc = &vq->desc[desc_idx];
> + /* start with the first mbuf of the packet */
> + mbuf_len = rte_pktmbuf_data_len(mbuf);
> + mbuf_avail = mbuf_len;
> +
> + /* get the current desc */
> + desc_current = vq->avail->ring[(vq->last_used_idx) & (vq->size - 1)];
> + desc_chain_head = desc_current;
> + desc = &vq->desc[desc_current];
> desc_addr = gpa_to_vva(dev, desc->addr);
> - /*
> - * Checking of 'desc_addr' placed outside of 'unlikely' macro to avoid
> - * performance issue with some versions of gcc (4.8.4 and 5.3.0) which
> - * otherwise stores offset on the stack instead of in a register.
> - */
> - if (unlikely(desc->len < dev->vhost_hlen) || !desc_addr)
> - return -1;
> + if (unlikely(!desc_addr))
> + goto error;
>
> - rte_prefetch0((void *)(uintptr_t)desc_addr);
> + /* handle virtio header */
> + virtio_hdr = (struct virtio_net_hdr_mrg_rxbuf *)(uintptr_t)desc_addr;
> + virtio_enqueue_offload(mbuf, &(virtio_hdr->hdr));
> + if (is_mrg_rxbuf)
> + virtio_hdr->num_buffers = 1;
>
> - virtio_enqueue_offload(m, &virtio_hdr.hdr);
> - copy_virtio_net_hdr(dev, desc_addr, virtio_hdr);
> vhost_log_write(dev, desc->addr, dev->vhost_hlen);
> PRINT_PACKET(dev, (uintptr_t)desc_addr, dev->vhost_hlen, 0);
> -
> desc_offset = dev->vhost_hlen;
> - desc_avail = desc->len - dev->vhost_hlen;
> -
> - mbuf_avail = rte_pktmbuf_data_len(m);
> - mbuf_offset = 0;
> - while (mbuf_avail != 0 || m->next != NULL) {
> - /* done with current mbuf, fetch next */
> - if (mbuf_avail == 0) {
> - m = m->next;
> -
> - mbuf_offset = 0;
> - mbuf_avail = rte_pktmbuf_data_len(m);
> + desc_chain_len = desc_offset;
> + desc_addr += desc_offset;
> +
> + /* start copy from mbuf to desc */
> + while (mbuf_avail || mbuf->next) {
> + /* get the next mbuf if the current done */
> + if (!mbuf_avail) {
> + mbuf = mbuf->next;
> + mbuf_len = rte_pktmbuf_data_len(mbuf);
> + mbuf_avail = mbuf_len;
> }
>
> - /* done with current desc buf, fetch next */
> - if (desc_avail == 0) {
> - if ((desc->flags & VRING_DESC_F_NEXT) == 0) {
> - /* Room in vring buffer is not enough */
> - return -1;
> - }
> - if (unlikely(desc->next >= vq->size))
> - return -1;
> + /* get the next desc if the current done */
> + if (desc->len <= desc_offset) {
> + if (desc->flags & VRING_DESC_F_NEXT) {
> + /* go on with the current desc chain */
> + desc_offset = 0;
> + desc_current = desc->next;
> + desc = &vq->desc[desc_current];
> + desc_addr = gpa_to_vva(dev, desc->addr);
> + if (unlikely(!desc_addr))
> + goto error;
> + } else if (is_mrg_rxbuf) {
> + /* start with the next desc chain */
> + update_used_ring(dev, vq, desc_chain_head,
> + desc_chain_len);
> + num_buffers++;
> + virtio_hdr->num_buffers++;
> + if (avail_idx == vq->last_used_idx)
> + goto error;
> +
> + desc_current =
> + vq->avail->ring[(vq->last_used_idx) &
> + (vq->size - 1)];
> + desc_chain_head = desc_current;
> + desc = &vq->desc[desc_current];
> + desc_addr = gpa_to_vva(dev, desc->addr);
> + if (unlikely(!desc_addr))
> + goto error;
>
> - desc = &vq->desc[desc->next];
> - desc_addr = gpa_to_vva(dev, desc->addr);
> - if (unlikely(!desc_addr))
> - return -1;
> -
> - desc_offset = 0;
> - desc_avail = desc->len;
> + desc_chain_len = 0;
> + desc_offset = 0;
As I commented on v3, there is code duplication between next flag, and
mrg buf cases:
desc_offset = 0;
and:
desc = &vq->desc[desc_current];
desc_addr = gpa_to_vva(dev, desc->addr);
if (unlikely(!desc_addr))
goto error;
Regards,
Maxime
next prev parent reply other threads:[~2016-09-12 15:42 UTC|newest]
Thread overview: 140+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-08-16 3:50 [dpdk-dev] [PATCH] optimize vhost enqueue Zhihong Wang
2016-08-16 13:59 ` Maxime Coquelin
2016-08-17 1:45 ` Wang, Zhihong
2016-08-17 2:38 ` Yuanhan Liu
2016-08-17 6:41 ` Wang, Zhihong
2016-08-17 9:17 ` Maxime Coquelin
2016-08-17 9:51 ` Yuanhan Liu
2016-08-18 13:44 ` Wang, Zhihong
2016-08-17 10:07 ` Wang, Zhihong
2016-08-18 6:33 ` [dpdk-dev] [PATCH v2 0/6] vhost: optimize enqueue Zhihong Wang
2016-08-18 6:33 ` [dpdk-dev] [PATCH v2 1/6] vhost: rewrite enqueue Zhihong Wang
2016-08-19 2:39 ` Yuanhan Liu
2016-08-19 7:07 ` Wang, Zhihong
2016-08-18 6:33 ` [dpdk-dev] [PATCH v2 2/6] vhost: remove obsolete Zhihong Wang
2016-08-19 2:32 ` Yuanhan Liu
2016-08-19 7:08 ` Wang, Zhihong
2016-08-18 6:33 ` [dpdk-dev] [PATCH v2 3/6] vhost: remove useless volatile Zhihong Wang
2016-08-18 6:33 ` [dpdk-dev] [PATCH v2 4/6] vhost: add desc prefetch Zhihong Wang
2016-08-18 6:33 ` [dpdk-dev] [PATCH v2 5/6] vhost: batch update used ring Zhihong Wang
2016-08-18 6:33 ` [dpdk-dev] [PATCH v2 6/6] vhost: optimize cache access Zhihong Wang
2016-08-19 5:43 ` [dpdk-dev] [PATCH v3 0/5] vhost: optimize enqueue Zhihong Wang
2016-08-19 5:43 ` [dpdk-dev] [PATCH v3 1/5] vhost: rewrite enqueue Zhihong Wang
2016-08-22 9:35 ` Maxime Coquelin
2016-08-23 2:27 ` Wang, Zhihong
2016-08-25 4:00 ` Yuanhan Liu
2016-08-19 5:43 ` [dpdk-dev] [PATCH v3 2/5] vhost: remove useless volatile Zhihong Wang
2016-08-19 5:43 ` [dpdk-dev] [PATCH v3 3/5] vhost: add desc prefetch Zhihong Wang
2016-08-19 5:43 ` [dpdk-dev] [PATCH v3 4/5] vhost: batch update used ring Zhihong Wang
2016-08-25 3:48 ` Yuanhan Liu
2016-08-25 5:19 ` Wang, Zhihong
2016-08-19 5:43 ` [dpdk-dev] [PATCH v3 5/5] vhost: optimize cache access Zhihong Wang
2016-08-22 8:11 ` [dpdk-dev] [PATCH v3 0/5] vhost: optimize enqueue Maxime Coquelin
2016-08-22 10:01 ` Maxime Coquelin
2016-08-22 10:35 ` Thomas Monjalon
2016-08-24 3:37 ` Wang, Zhihong
2016-08-23 2:31 ` Wang, Zhihong
2016-08-23 10:43 ` Wang, Zhihong
2016-08-23 12:16 ` Maxime Coquelin
2016-08-23 12:22 ` Yuanhan Liu
2016-08-23 2:15 ` Wang, Zhihong
2016-09-21 8:50 ` Jianbo Liu
2016-09-21 9:27 ` Wang, Zhihong
2016-09-21 12:54 ` Jianbo Liu
2016-09-22 2:11 ` Wang, Zhihong
2016-09-22 2:29 ` Yuanhan Liu
2016-09-22 5:47 ` Jianbo Liu
2016-09-22 6:58 ` Wang, Zhihong
2016-09-22 9:01 ` Jianbo Liu
2016-09-22 10:04 ` Wang, Zhihong
2016-09-22 14:41 ` Jianbo Liu
2016-09-23 2:56 ` Wang, Zhihong
2016-09-23 10:41 ` Jianbo Liu
2016-09-23 13:41 ` Thomas Monjalon
2016-09-25 5:41 ` Wang, Zhihong
2016-09-26 5:12 ` Jianbo Liu
2016-09-26 5:25 ` Wang, Zhihong
2016-09-26 5:38 ` Jianbo Liu
2016-09-26 6:00 ` Wang, Zhihong
2016-09-26 4:24 ` Jianbo Liu
2016-09-26 5:37 ` Luke Gorrie
2016-09-26 5:40 ` Jianbo Liu
2016-09-27 10:21 ` Yuanhan Liu
2016-09-27 16:45 ` Wang, Zhihong
2016-10-09 12:09 ` Wang, Zhihong
2016-10-10 2:44 ` Yuanhan Liu
2016-10-10 5:31 ` Jianbo Liu
2016-10-10 6:22 ` Wang, Zhihong
2016-10-10 6:57 ` Jianbo Liu
2016-10-10 7:25 ` Wang, Zhihong
2016-10-12 2:53 ` Yuanhan Liu
2016-10-12 12:22 ` Wang, Zhihong
2016-10-12 15:31 ` Thomas Monjalon
2016-10-13 1:21 ` Wang, Zhihong
2016-10-13 3:51 ` Jianbo Liu
2016-10-13 5:33 ` Yuanhan Liu
2016-10-13 5:35 ` Yuanhan Liu
2016-10-13 6:02 ` Wang, Zhihong
2016-10-13 7:54 ` Maxime Coquelin
2016-10-13 9:23 ` Maxime Coquelin
2016-10-14 10:11 ` Yuanhan Liu
2016-08-30 3:35 ` [dpdk-dev] [PATCH v4 0/6] " Zhihong Wang
2016-08-30 3:35 ` [dpdk-dev] [PATCH v4 1/6] vhost: fix windows vm hang Zhihong Wang
2016-09-05 5:24 ` [dpdk-dev] [dpdk-stable] " Yuanhan Liu
2016-09-05 5:25 ` Wang, Zhihong
2016-09-05 5:40 ` Yuanhan Liu
2016-08-30 3:36 ` [dpdk-dev] [PATCH v4 2/6] vhost: rewrite enqueue Zhihong Wang
2016-09-05 6:39 ` Yuanhan Liu
2016-09-07 5:33 ` Yuanhan Liu
2016-09-07 5:39 ` Wang, Zhihong
2016-08-30 3:36 ` [dpdk-dev] [PATCH v4 3/6] vhost: remove useless volatile Zhihong Wang
2016-08-30 3:36 ` [dpdk-dev] [PATCH v4 4/6] vhost: add desc prefetch Zhihong Wang
2016-08-30 3:36 ` [dpdk-dev] [PATCH v4 5/6] vhost: batch update used ring Zhihong Wang
2016-08-30 3:36 ` [dpdk-dev] [PATCH v4 6/6] vhost: optimize cache access Zhihong Wang
2016-09-09 3:39 ` [dpdk-dev] [PATCH v5 0/6] vhost: optimize enqueue Zhihong Wang
2016-09-09 3:39 ` [dpdk-dev] [PATCH v5 1/6] vhost: fix windows vm hang Zhihong Wang
2016-09-09 3:39 ` [dpdk-dev] [PATCH v5 2/6] vhost: rewrite enqueue Zhihong Wang
2016-09-12 15:42 ` Maxime Coquelin [this message]
2016-09-14 8:20 ` Wang, Zhihong
2016-09-15 16:35 ` Maxime Coquelin
2016-09-12 16:26 ` Maxime Coquelin
2016-09-14 8:22 ` Wang, Zhihong
2016-09-18 14:19 ` Yuanhan Liu
2016-09-19 3:29 ` Wang, Zhihong
2016-09-09 3:39 ` [dpdk-dev] [PATCH v5 3/6] vhost: remove useless volatile Zhihong Wang
2016-09-09 3:39 ` [dpdk-dev] [PATCH v5 4/6] vhost: add desc prefetch Zhihong Wang
2016-09-09 3:39 ` [dpdk-dev] [PATCH v5 5/6] vhost: batch update used ring Zhihong Wang
2016-09-12 15:45 ` Maxime Coquelin
2016-09-14 8:43 ` Wang, Zhihong
2016-09-15 16:38 ` Maxime Coquelin
2016-09-18 2:55 ` Yuanhan Liu
2016-09-18 2:57 ` Wang, Zhihong
2016-09-09 3:39 ` [dpdk-dev] [PATCH v5 6/6] vhost: optimize cache access Zhihong Wang
2016-09-12 13:52 ` [dpdk-dev] [PATCH v5 0/6] vhost: optimize enqueue Maxime Coquelin
2016-09-12 13:56 ` Maxime Coquelin
2016-09-12 14:01 ` Yuanhan Liu
2016-09-20 2:00 ` [dpdk-dev] [PATCH v6 " Zhihong Wang
2016-09-20 2:00 ` [dpdk-dev] [PATCH v6 1/6] vhost: fix windows vm hang Zhihong Wang
2016-10-13 6:18 ` [dpdk-dev] [dpdk-stable] " Yuanhan Liu
2016-09-20 2:00 ` [dpdk-dev] [PATCH v6 2/6] vhost: rewrite enqueue Zhihong Wang
2016-09-22 9:58 ` Jianbo Liu
2016-09-22 10:13 ` Wang, Zhihong
2016-09-20 2:00 ` [dpdk-dev] [PATCH v6 3/6] vhost: remove useless volatile Zhihong Wang
2016-09-20 2:00 ` [dpdk-dev] [PATCH v6 4/6] vhost: add desc prefetch Zhihong Wang
2016-09-20 2:00 ` [dpdk-dev] [PATCH v6 5/6] vhost: batch update used ring Zhihong Wang
2016-09-20 2:00 ` [dpdk-dev] [PATCH v6 6/6] vhost: optimize cache access Zhihong Wang
2016-09-21 2:26 ` [dpdk-dev] [PATCH v6 0/6] vhost: optimize enqueue Yuanhan Liu
2016-09-21 4:39 ` Maxime Coquelin
2016-10-14 9:34 ` [dpdk-dev] [PATCH v7 0/7] vhost: optimize mergeable Rx path Yuanhan Liu
2016-10-14 9:34 ` [dpdk-dev] [PATCH v7 1/7] vhost: remove useless volatile Yuanhan Liu
2016-10-14 9:34 ` [dpdk-dev] [PATCH v7 2/7] vhost: optimize cache access Yuanhan Liu
2016-10-14 9:34 ` [dpdk-dev] [PATCH v7 3/7] vhost: simplify mergeable Rx vring reservation Yuanhan Liu
2016-10-25 22:08 ` Thomas Monjalon
2016-10-26 2:56 ` Yuanhan Liu
2016-10-14 9:34 ` [dpdk-dev] [PATCH v7 4/7] vhost: use last avail idx for avail ring reservation Yuanhan Liu
2016-10-14 9:34 ` [dpdk-dev] [PATCH v7 5/7] vhost: shadow used ring update Yuanhan Liu
2016-10-14 9:34 ` [dpdk-dev] [PATCH v7 6/7] vhost: prefetch avail ring Yuanhan Liu
2016-10-14 9:34 ` [dpdk-dev] [PATCH v7 7/7] vhost: retrieve avail head once Yuanhan Liu
2016-10-18 2:25 ` [dpdk-dev] [PATCH v7 0/7] vhost: optimize mergeable Rx path Jianbo Liu
2016-10-18 14:53 ` Maxime Coquelin
2016-10-21 7:51 ` Yuanhan Liu
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=2cc970ca-ea2c-8e3b-069a-9f1ec1182b03@redhat.com \
--to=maxime.coquelin@redhat.com \
--cc=dev@dpdk.org \
--cc=thomas.monjalon@6wind.com \
--cc=yuanhan.liu@linux.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).