From mboxrd@z Thu Jan 1 00:00:00 1970
Return-Path: <dev-bounces@dpdk.org>
Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124])
by inbox.dpdk.org (Postfix) with ESMTP id D5F01A0C44;
Mon, 12 Apr 2021 13:47:50 +0200 (CEST)
Received: from [217.70.189.124] (localhost [127.0.0.1])
by mails.dpdk.org (Postfix) with ESMTP id 99A3F141116;
Mon, 12 Apr 2021 13:47:50 +0200 (CEST)
Received: from mga12.intel.com (mga12.intel.com [192.55.52.136])
by mails.dpdk.org (Postfix) with ESMTP id 6E8AF14110A
for <dev@dpdk.org>; Mon, 12 Apr 2021 13:47:48 +0200 (CEST)
IronPort-SDR: PDyEWZSnxtin0C93bZn23cf/ITXXxjV4Oa6kKMBhJ9hK+a/jHo20h5uFSxK4Ba7KlW5t1fJa10
KaAipSa/X9Cw==
X-IronPort-AV: E=McAfee;i="6000,8403,9951"; a="173662376"
X-IronPort-AV: E=Sophos;i="5.82,216,1613462400"; d="scan'208";a="173662376"
Received: from fmsmga002.fm.intel.com ([10.253.24.26])
by fmsmga106.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384;
12 Apr 2021 04:47:47 -0700
IronPort-SDR: /UxGcCylbFRPhaNKyBU6EGdPvDSUD8Hkv4ccGtmLU9BDREaqaKk9f9ewJttMC7KeIKwoLD7UTD
nnPAF/AU/m6g==
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.82,216,1613462400"; d="scan'208";a="451421501"
Received: from dpdk_jiangcheng.sh.intel.com ([10.67.119.112])
by fmsmga002.fm.intel.com with ESMTP; 12 Apr 2021 04:47:45 -0700
From: Cheng Jiang <Cheng1.jiang@intel.com>
To: maxime.coquelin@redhat.com,
chenbo.xia@intel.com
Cc: dev@dpdk.org, jiayu.hu@intel.com, yvonnex.yang@intel.com,
yinan.wang@intel.com, yong.liu@intel.com,
Cheng Jiang <Cheng1.jiang@intel.com>
Date: Mon, 12 Apr 2021 11:34:27 +0000
Message-Id: <20210412113430.17587-2-Cheng1.jiang@intel.com>
X-Mailer: git-send-email 2.29.2
In-Reply-To: <20210412113430.17587-1-Cheng1.jiang@intel.com>
References: <20210317085426.10119-1-Cheng1.jiang@intel.com>
<20210412113430.17587-1-Cheng1.jiang@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Subject: [dpdk-dev] [PATCH v5 1/4] vhost: abstract and reorganize async
split ring code
X-BeenThere: dev@dpdk.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: DPDK patches and discussions <dev.dpdk.org>
List-Unsubscribe: <https://mails.dpdk.org/options/dev>,
<mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://mails.dpdk.org/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <https://mails.dpdk.org/listinfo/dev>,
<mailto:dev-request@dpdk.org?subject=subscribe>
Errors-To: dev-bounces@dpdk.org
Sender: "dev" <dev-bounces@dpdk.org>
In order to improve code efficiency and readability when async packed
ring support is enabled. This patch abstract some functions like
shadow_ring_store and write_back_completed_descs_split. And improve
the efficiency of some pointer offset calculation.
Signed-off-by: Cheng Jiang <Cheng1.jiang@intel.com>
---
lib/librte_vhost/virtio_net.c | 146 +++++++++++++++++++---------------
1 file changed, 84 insertions(+), 62 deletions(-)
diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index ff3987860..c43ab0093 100644
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -1458,6 +1458,29 @@ virtio_dev_rx_async_get_info_idx(uint16_t pkts_idx,
(vq_size - n_inflight + pkts_idx) & (vq_size - 1);
}
+static __rte_always_inline void
+shadow_ring_store(struct vhost_virtqueue *vq, void *shadow_ring, void *d_ring,
+ uint16_t s_idx, uint16_t d_idx,
+ uint16_t count, uint16_t elem_size)
+{
+ if (d_idx + count <= vq->size) {
+ rte_memcpy((void *)((uintptr_t)d_ring + d_idx * elem_size),
+ (void *)((uintptr_t)shadow_ring + s_idx * elem_size),
+ count * elem_size);
+ } else {
+ uint16_t size = vq->size - d_idx;
+
+ rte_memcpy((void *)((uintptr_t)d_ring + d_idx * elem_size),
+ (void *)((uintptr_t)shadow_ring + s_idx * elem_size),
+ size * elem_size);
+
+ rte_memcpy((void *)((uintptr_t)d_ring),
+ (void *)((uintptr_t)shadow_ring +
+ (s_idx + size) * elem_size),
+ (count - size) * elem_size);
+ }
+}
+
static __rte_noinline uint32_t
virtio_dev_rx_async_submit_split(struct virtio_net *dev,
struct vhost_virtqueue *vq, uint16_t queue_id,
@@ -1478,6 +1501,7 @@ virtio_dev_rx_async_submit_split(struct virtio_net *dev,
struct rte_vhost_iov_iter *dst_it = it_pool + 1;
uint16_t slot_idx = 0;
uint16_t segs_await = 0;
+ uint16_t iovec_idx = 0, it_idx = 0;
struct async_inflight_info *pkts_info = vq->async_pkts_info;
uint32_t n_pkts = 0, pkt_err = 0;
uint32_t num_async_pkts = 0, num_done_pkts = 0;
@@ -1513,27 +1537,32 @@ virtio_dev_rx_async_submit_split(struct virtio_net *dev,
if (async_mbuf_to_desc(dev, vq, pkts[pkt_idx],
buf_vec, nr_vec, num_buffers,
- src_iovec, dst_iovec, src_it, dst_it) < 0) {
+ &src_iovec[iovec_idx],
+ &dst_iovec[iovec_idx],
+ &src_it[it_idx],
+ &dst_it[it_idx]) < 0) {
vq->shadow_used_idx -= num_buffers;
break;
}
slot_idx = (vq->async_pkts_idx + num_async_pkts) &
(vq->size - 1);
- if (src_it->count) {
+ if (src_it[it_idx].count) {
uint16_t from, to;
- async_fill_desc(&tdes[pkt_burst_idx++], src_it, dst_it);
+ async_fill_desc(&tdes[pkt_burst_idx++],
+ &src_it[it_idx],
+ &dst_it[it_idx]);
pkts_info[slot_idx].descs = num_buffers;
pkts_info[slot_idx].mbuf = pkts[pkt_idx];
async_pkts_log[num_async_pkts].pkt_idx = pkt_idx;
async_pkts_log[num_async_pkts++].last_avail_idx =
vq->last_avail_idx;
- src_iovec += src_it->nr_segs;
- dst_iovec += dst_it->nr_segs;
- src_it += 2;
- dst_it += 2;
- segs_await += src_it->nr_segs;
+
+ iovec_idx += src_it[it_idx].nr_segs;
+ it_idx += 2;
+
+ segs_await += src_it[it_idx].nr_segs;
/**
* recover shadow used ring and keep DMA-occupied
@@ -1541,23 +1570,12 @@ virtio_dev_rx_async_submit_split(struct virtio_net *dev,
*/
from = vq->shadow_used_idx - num_buffers;
to = vq->async_desc_idx & (vq->size - 1);
- if (num_buffers + to <= vq->size) {
- rte_memcpy(&vq->async_descs_split[to],
- &vq->shadow_used_split[from],
- num_buffers *
- sizeof(struct vring_used_elem));
- } else {
- int size = vq->size - to;
-
- rte_memcpy(&vq->async_descs_split[to],
- &vq->shadow_used_split[from],
- size *
- sizeof(struct vring_used_elem));
- rte_memcpy(vq->async_descs_split,
- &vq->shadow_used_split[from +
- size], (num_buffers - size) *
- sizeof(struct vring_used_elem));
- }
+
+ shadow_ring_store(vq, vq->shadow_used_split,
+ vq->async_descs_split,
+ from, to, num_buffers,
+ sizeof(struct vring_used_elem));
+
vq->async_desc_idx += num_buffers;
vq->shadow_used_idx -= num_buffers;
} else
@@ -1575,10 +1593,9 @@ virtio_dev_rx_async_submit_split(struct virtio_net *dev,
BUF_VECTOR_MAX))) {
n_pkts = vq->async_ops.transfer_data(dev->vid,
queue_id, tdes, 0, pkt_burst_idx);
- src_iovec = vec_pool;
- dst_iovec = vec_pool + (VHOST_MAX_ASYNC_VEC >> 1);
- src_it = it_pool;
- dst_it = it_pool + 1;
+ iovec_idx = 0;
+ it_idx = 0;
+
segs_await = 0;
vq->async_pkts_inflight_n += n_pkts;
@@ -1639,6 +1656,43 @@ virtio_dev_rx_async_submit_split(struct virtio_net *dev,
return pkt_idx;
}
+static __rte_always_inline void
+write_back_completed_descs_split(struct vhost_virtqueue *vq, uint16_t n_descs)
+{
+ uint16_t nr_left = n_descs;
+ uint16_t nr_copy;
+ uint16_t to, from;
+
+ do {
+ from = vq->last_async_desc_idx & (vq->size - 1);
+ nr_copy = nr_left + from <= vq->size ? nr_left :
+ vq->size - from;
+ to = vq->last_used_idx & (vq->size - 1);
+
+ if (to + nr_copy <= vq->size) {
+ rte_memcpy(&vq->used->ring[to],
+ &vq->async_descs_split[from],
+ nr_copy *
+ sizeof(struct vring_used_elem));
+ } else {
+ uint16_t size = vq->size - to;
+
+ rte_memcpy(&vq->used->ring[to],
+ &vq->async_descs_split[from],
+ size *
+ sizeof(struct vring_used_elem));
+ rte_memcpy(vq->used->ring,
+ &vq->async_descs_split[from +
+ size], (nr_copy - size) *
+ sizeof(struct vring_used_elem));
+ }
+
+ vq->last_async_desc_idx += nr_copy;
+ vq->last_used_idx += nr_copy;
+ nr_left -= nr_copy;
+ } while (nr_left > 0);
+}
+
uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
struct rte_mbuf **pkts, uint16_t count)
{
@@ -1695,39 +1749,7 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
vq->async_pkts_inflight_n -= n_pkts_put;
if (likely(vq->enabled && vq->access_ok)) {
- uint16_t nr_left = n_descs;
- uint16_t nr_copy;
- uint16_t to;
-
- /* write back completed descriptors to used ring */
- do {
- from = vq->last_async_desc_idx & (vq->size - 1);
- nr_copy = nr_left + from <= vq->size ? nr_left :
- vq->size - from;
- to = vq->last_used_idx & (vq->size - 1);
-
- if (to + nr_copy <= vq->size) {
- rte_memcpy(&vq->used->ring[to],
- &vq->async_descs_split[from],
- nr_copy *
- sizeof(struct vring_used_elem));
- } else {
- uint16_t size = vq->size - to;
-
- rte_memcpy(&vq->used->ring[to],
- &vq->async_descs_split[from],
- size *
- sizeof(struct vring_used_elem));
- rte_memcpy(vq->used->ring,
- &vq->async_descs_split[from +
- size], (nr_copy - size) *
- sizeof(struct vring_used_elem));
- }
-
- vq->last_async_desc_idx += nr_copy;
- vq->last_used_idx += nr_copy;
- nr_left -= nr_copy;
- } while (nr_left > 0);
+ write_back_completed_descs_split(vq, n_descs);
__atomic_add_fetch(&vq->used->idx, n_descs, __ATOMIC_RELEASE);
vhost_vring_call_split(dev, vq);
--
2.29.2