From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: dev@dpdk.org, tiwei.bie@intel.com, jfreimann@redhat.com,
zhihong.wang@intel.com, bruce.richardson@intel.com,
konstantin.ananyev@intel.com
Cc: Maxime Coquelin <maxime.coquelin@redhat.com>
Subject: [dpdk-dev] [PATCH 4/5] vhost: simplify descriptor's buffer prefetching
Date: Fri, 17 May 2019 14:22:19 +0200 [thread overview]
Message-ID: <20190517122220.31283-5-maxime.coquelin@redhat.com> (raw)
In-Reply-To: <20190517122220.31283-1-maxime.coquelin@redhat.com>
Now that we have a single function to map the descriptors
buffers, let's prefetch them there as it is the earliest
place we can do it.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
lib/librte_vhost/virtio_net.c | 32 ++------------------------------
1 file changed, 2 insertions(+), 30 deletions(-)
diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index 494dd9957e..d9031fe55c 100644
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -286,6 +286,8 @@ map_one_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
if (unlikely(!desc_addr))
return -1;
+ rte_prefetch0((void *)(uintptr_t)desc_addr);
+
buf_vec[vec_id].buf_iova = desc_iova;
buf_vec[vec_id].buf_addr = desc_addr;
buf_vec[vec_id].buf_len = desc_chunck_len;
@@ -664,9 +666,6 @@ copy_mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
buf_iova = buf_vec[vec_idx].buf_iova;
buf_len = buf_vec[vec_idx].buf_len;
- if (nr_vec > 1)
- rte_prefetch0((void *)(uintptr_t)buf_vec[1].buf_addr);
-
if (unlikely(buf_len < dev->vhost_hlen && nr_vec <= 1)) {
error = -1;
goto out;
@@ -709,10 +708,6 @@ copy_mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
buf_iova = buf_vec[vec_idx].buf_iova;
buf_len = buf_vec[vec_idx].buf_len;
- /* Prefetch next buffer address. */
- if (vec_idx + 1 < nr_vec)
- rte_prefetch0((void *)(uintptr_t)
- buf_vec[vec_idx + 1].buf_addr);
buf_offset = 0;
buf_avail = buf_len;
}
@@ -810,8 +805,6 @@ virtio_dev_rx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
break;
}
- rte_prefetch0((void *)(uintptr_t)buf_vec[0].buf_addr);
-
VHOST_LOG_DEBUG(VHOST_DATA, "(%d) current index %d | end index %d\n",
dev->vid, vq->last_avail_idx,
vq->last_avail_idx + num_buffers);
@@ -859,8 +852,6 @@ virtio_dev_rx_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
break;
}
- rte_prefetch0((void *)(uintptr_t)buf_vec[0].buf_addr);
-
VHOST_LOG_DEBUG(VHOST_DATA, "(%d) current index %d | end index %d\n",
dev->vid, vq->last_avail_idx,
vq->last_avail_idx + num_buffers);
@@ -1120,16 +1111,12 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
goto out;
}
- if (likely(nr_vec > 1))
- rte_prefetch0((void *)(uintptr_t)buf_vec[1].buf_addr);
-
if (virtio_net_with_host_offload(dev)) {
if (unlikely(buf_len < sizeof(struct virtio_net_hdr))) {
copy_vnet_hdr_from_desc(&tmp_hdr, buf_vec);
hdr = &tmp_hdr;
} else {
hdr = (struct virtio_net_hdr *)((uintptr_t)buf_addr);
- rte_prefetch0(hdr);
}
}
@@ -1159,9 +1146,6 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
buf_avail = buf_vec[vec_idx].buf_len - dev->vhost_hlen;
}
- rte_prefetch0((void *)(uintptr_t)
- (buf_addr + buf_offset));
-
PRINT_PACKET(dev,
(uintptr_t)(buf_addr + buf_offset),
(uint32_t)buf_avail, 0);
@@ -1227,14 +1211,6 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
buf_iova = buf_vec[vec_idx].buf_iova;
buf_len = buf_vec[vec_idx].buf_len;
- /*
- * Prefecth desc n + 1 buffer while
- * desc n buffer is processed.
- */
- if (vec_idx + 1 < nr_vec)
- rte_prefetch0((void *)(uintptr_t)
- buf_vec[vec_idx + 1].buf_addr);
-
buf_offset = 0;
buf_avail = buf_len;
@@ -1378,8 +1354,6 @@ virtio_dev_tx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
if (likely(dev->dequeue_zero_copy == 0))
update_shadow_used_ring_split(vq, head_idx, 0);
- rte_prefetch0((void *)(uintptr_t)buf_vec[0].buf_addr);
-
pkts[i] = rte_pktmbuf_alloc(mbuf_pool);
if (unlikely(pkts[i] == NULL)) {
RTE_LOG(ERR, VHOST_DATA,
@@ -1489,8 +1463,6 @@ virtio_dev_tx_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
update_shadow_used_ring_packed(vq, buf_id, 0,
desc_count);
- rte_prefetch0((void *)(uintptr_t)buf_vec[0].buf_addr);
-
pkts[i] = rte_pktmbuf_alloc(mbuf_pool);
if (unlikely(pkts[i] == NULL)) {
RTE_LOG(ERR, VHOST_DATA,
--
2.21.0
next prev parent reply other threads:[~2019-05-17 12:23 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-17 12:22 [dpdk-dev] [PATCH 0/5] vhost: I-cache pressure optimizations Maxime Coquelin
2019-05-17 12:22 ` [dpdk-dev] [PATCH 1/5] vhost: un-inline dirty pages logging functions Maxime Coquelin
2019-05-17 12:22 ` [dpdk-dev] [PATCH 2/5] vhost: do not inline packed and split functions Maxime Coquelin
2019-05-17 13:00 ` David Marchand
2019-05-17 14:42 ` Maxime Coquelin
2019-05-17 12:22 ` [dpdk-dev] [PATCH 3/5] vhost: do not inline unlikely fragmented buffers code Maxime Coquelin
2019-05-17 12:57 ` Maxime Coquelin
2019-05-21 19:43 ` Mattias Rönnblom
2019-05-23 14:30 ` Maxime Coquelin
2019-05-23 15:17 ` Mattias Rönnblom
2019-05-23 17:40 ` Maxime Coquelin
2019-05-17 12:22 ` Maxime Coquelin [this message]
2019-05-17 12:22 ` [dpdk-dev] [PATCH 5/5] eal/x86: force inlining of all memcpy and mov helpers Maxime Coquelin
2019-05-17 13:04 ` [dpdk-dev] [PATCH 0/5] vhost: I-cache pressure optimizations David Marchand
2019-05-17 14:42 ` 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=20190517122220.31283-5-maxime.coquelin@redhat.com \
--to=maxime.coquelin@redhat.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=jfreimann@redhat.com \
--cc=konstantin.ananyev@intel.com \
--cc=tiwei.bie@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).