From patchwork Fri Dec 16 07:38:42 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Jiang, Cheng1" X-Patchwork-Id: 120968 X-Patchwork-Delegate: maxime.coquelin@redhat.com Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 631CBA0542; Fri, 16 Dec 2022 09:24:52 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id B543342D0D; Fri, 16 Dec 2022 09:24:51 +0100 (CET) Received: from mga06.intel.com (mga06b.intel.com [134.134.136.31]) by mails.dpdk.org (Postfix) with ESMTP id 5D3FE42D0D for ; Fri, 16 Dec 2022 09:24:49 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1671179089; x=1702715089; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=IojxJ6l0wm1MgYo5/4MsPy7IfxRRRYQk87Te/emTHlo=; b=PDwdV0Ckxl/FyCFzpMYaoeoT/9bS4LRRP9dqBRLM/YTj8aXTL+kr22Oe WhAG93yb5Ok6a7B9DUj51P1v6urxlBOn0cCNHlXK6BLQcn1PQc40AkCeu VGcdMgcodemk6L4maG7tgrIoJZMSm3UBYbvfDACM/UoU0YA6sXGFBYWcq QOM30Cn/QhBRqe8pcbVBrCqpTsA0cJSm+a9CO4CUb4+r7+L45+cGQQher VXnLaSwmPeSr9sWF2xxNxyG7YTStrG39sWvmA/8lCfbyrxhRzPPhpYgy/ XiLfXl2sV3SWDHAueqU5dImE4Sv+oJtQyyRi4FR+i+xlk/r5++iXTOevE A==; X-IronPort-AV: E=McAfee;i="6500,9779,10562"; a="381137585" X-IronPort-AV: E=Sophos;i="5.96,249,1665471600"; d="scan'208";a="381137585" Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga104.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 16 Dec 2022 00:24:49 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6500,9779,10562"; a="682221140" X-IronPort-AV: E=Sophos;i="5.96,249,1665471600"; d="scan'208";a="682221140" Received: from dpdk_jiangcheng.sh.intel.com ([10.67.118.237]) by orsmga001.jf.intel.com with ESMTP; 16 Dec 2022 00:24:46 -0800 From: Cheng Jiang To: maxime.coquelin@redhat.com, chenbo.xia@intel.com Cc: dev@dpdk.org, jiayu.hu@intel.com, xuan.ding@intel.com, wenwux.ma@intel.com, yuanx.wang@intel.com, yvonnex.yang@intel.com, xingguang.he@intel.com, Cheng Jiang Subject: [RFC 1/3] vhost: remove redundant copy for packed shadow used ring Date: Fri, 16 Dec 2022 07:38:42 +0000 Message-Id: <20221216073844.24448-2-cheng1.jiang@intel.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: <20221216073844.24448-1-cheng1.jiang@intel.com> References: <20221216073844.24448-1-cheng1.jiang@intel.com> MIME-Version: 1.0 X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org In the packed ring enqueue data path of the current asynchronous Vhost design, the shadow used ring is first copied to the sync shadow used ring, and then it will be moved to the async shadow used ring for some historical reasons. This is completely unnecessary. This patch removes redundant copy for the shadow used ring. The async shadow used ring will be updated directly. Signed-off-by: Cheng Jiang --- lib/vhost/virtio_net.c | 66 ++++++++++++++++++++---------------------- 1 file changed, 31 insertions(+), 35 deletions(-) diff --git a/lib/vhost/virtio_net.c b/lib/vhost/virtio_net.c index 4358899718..22f97d4f77 100644 --- a/lib/vhost/virtio_net.c +++ b/lib/vhost/virtio_net.c @@ -572,6 +572,26 @@ vhost_shadow_enqueue_packed(struct vhost_virtqueue *vq, } } +static __rte_always_inline void +vhost_async_shadow_enqueue_packed(struct vhost_virtqueue *vq, + uint32_t *len, + uint16_t *id, + uint16_t *count, + uint16_t num_buffers) +{ + uint16_t i; + struct vhost_async *async = vq->async; + + for (i = 0; i < num_buffers; i++) { + async->buffers_packed[async->buffer_idx_packed].id = id[i]; + async->buffers_packed[async->buffer_idx_packed].len = len[i]; + async->buffers_packed[async->buffer_idx_packed].count = count[i]; + async->buffer_idx_packed++; + if (async->buffer_idx_packed >= vq->size) + async->buffer_idx_packed -= vq->size; + } +} + static __rte_always_inline void vhost_shadow_enqueue_single_packed(struct virtio_net *dev, struct vhost_virtqueue *vq, @@ -1647,23 +1667,6 @@ store_dma_desc_info_split(struct vring_used_elem *s_ring, struct vring_used_elem } } -static __rte_always_inline void -store_dma_desc_info_packed(struct vring_used_elem_packed *s_ring, - struct vring_used_elem_packed *d_ring, - uint16_t ring_size, uint16_t s_idx, uint16_t d_idx, uint16_t count) -{ - size_t elem_size = sizeof(struct vring_used_elem_packed); - - if (d_idx + count <= ring_size) { - rte_memcpy(d_ring + d_idx, s_ring + s_idx, count * elem_size); - } else { - uint16_t size = ring_size - d_idx; - - rte_memcpy(d_ring + d_idx, s_ring + s_idx, size * elem_size); - rte_memcpy(d_ring, s_ring + s_idx + size, (count - size) * elem_size); - } -} - static __rte_noinline uint32_t virtio_dev_rx_async_submit_split(struct virtio_net *dev, struct vhost_virtqueue *vq, struct rte_mbuf **pkts, uint32_t count, int16_t dma_id, uint16_t vchan_id) @@ -1822,7 +1825,8 @@ vhost_enqueue_async_packed(struct virtio_net *dev, if (unlikely(mbuf_to_desc(dev, vq, pkt, buf_vec, nr_vec, *nr_buffers, true) < 0)) return -1; - vhost_shadow_enqueue_packed(vq, buffer_len, buffer_buf_id, buffer_desc_count, *nr_buffers); + vhost_async_shadow_enqueue_packed(vq, buffer_len, buffer_buf_id, + buffer_desc_count, *nr_buffers); return 0; } @@ -1852,6 +1856,7 @@ dma_error_handler_packed(struct vhost_virtqueue *vq, uint16_t slot_idx, { uint16_t descs_err = 0; uint16_t buffers_err = 0; + struct vhost_async *async = vq->async; struct async_inflight_info *pkts_info = vq->async->pkts_info; *pkt_idx -= nr_err; @@ -1869,7 +1874,10 @@ dma_error_handler_packed(struct vhost_virtqueue *vq, uint16_t slot_idx, vq->avail_wrap_counter ^= 1; } - vq->shadow_used_idx -= buffers_err; + if (async->buffer_idx_packed >= buffers_err) + async->buffer_idx_packed -= buffers_err; + else + async->buffer_idx_packed = async->buffer_idx_packed + vq->size - buffers_err; } static __rte_noinline uint32_t @@ -1923,23 +1931,11 @@ virtio_dev_rx_async_submit_packed(struct virtio_net *dev, struct vhost_virtqueue dma_error_handler_packed(vq, slot_idx, pkt_err, &pkt_idx); } - if (likely(vq->shadow_used_idx)) { - /* keep used descriptors. */ - store_dma_desc_info_packed(vq->shadow_used_packed, async->buffers_packed, - vq->size, 0, async->buffer_idx_packed, - vq->shadow_used_idx); - - async->buffer_idx_packed += vq->shadow_used_idx; - if (async->buffer_idx_packed >= vq->size) - async->buffer_idx_packed -= vq->size; - - async->pkts_idx += pkt_idx; - if (async->pkts_idx >= vq->size) - async->pkts_idx -= vq->size; + async->pkts_idx += pkt_idx; + if (async->pkts_idx >= vq->size) + async->pkts_idx -= vq->size; - vq->shadow_used_idx = 0; - async->pkts_inflight_n += pkt_idx; - } + async->pkts_inflight_n += pkt_idx; return pkt_idx; }