From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 33CBBA0545; Wed, 15 Jul 2020 13:16:58 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 7E8161BEDC; Wed, 15 Jul 2020 13:16:57 +0200 (CEST) Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) by dpdk.org (Postfix) with ESMTP id 32ABD1BED7 for ; Wed, 15 Jul 2020 13:16:55 +0200 (CEST) IronPort-SDR: MauaJx+1xHEWrCqPqTN8mhQ4cIkeV5vrZ/SVMt/0BzkAYy9C/avx/nuy9kUEDVZg3dmF8MKEWK CCZUpE3/mJFQ== X-IronPort-AV: E=McAfee;i="6000,8403,9682"; a="137252120" X-IronPort-AV: E=Sophos;i="5.75,355,1589266800"; d="scan'208";a="137252120" X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga002.jf.intel.com ([10.7.209.21]) by orsmga101.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 15 Jul 2020 04:16:54 -0700 IronPort-SDR: J3+ezVcX3DMVzhvmYqWDYNua4sBG58j3R4Sdwkq7Uo76IxEwrWTUDLdPpeTi2vLAQtb1P4xuQS s1VQaZlY0wAQ== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.75,355,1589266800"; d="scan'208";a="299859563" Received: from npg-dpdk-patrickfu-casc2.sh.intel.com ([10.67.119.92]) by orsmga002.jf.intel.com with ESMTP; 15 Jul 2020 04:16:53 -0700 From: patrick.fu@intel.com To: dev@dpdk.org, maxime.coquelin@redhat.com, chenbo.xia@intel.com Cc: patrick.fu@intel.com, yinan.wang@intel.com Date: Wed, 15 Jul 2020 19:15:20 +0800 Message-Id: <20200715111520.2755307-1-patrick.fu@intel.com> X-Mailer: git-send-email 2.18.4 In-Reply-To: <20200715074650.2375332-1-patrick.fu@intel.com> References: <20200715074650.2375332-1-patrick.fu@intel.com> Subject: [dpdk-dev] [PATCH v2] vhost: support async copy free segmentations X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" From: Patrick Fu Vhost async enqueue assumes that all async copies should break at packet boundary. i.e. if a packet is splited into multiple copy segments, the async engine should always report copy completion when entire packet is finished. This patch removes the assumption. Fixes: cd6760da1076 ("vhost: introduce async enqueue for split ring") Signed-off-by: Patrick Fu --- v2: - fix an issue that can stuck async poll when packets buffer is full - rename a local variable to better reflect its usage lib/librte_vhost/vhost.h | 3 +++ lib/librte_vhost/virtio_net.c | 17 ++++++++++++----- 2 files changed, 15 insertions(+), 5 deletions(-) diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h index 8c01cee42..0f7212f88 100644 --- a/lib/librte_vhost/vhost.h +++ b/lib/librte_vhost/vhost.h @@ -46,6 +46,8 @@ #define MAX_PKT_BURST 32 +#define ASYNC_MAX_POLL_SEG 255 + #define VHOST_MAX_ASYNC_IT (MAX_PKT_BURST * 2) #define VHOST_MAX_ASYNC_VEC (BUF_VECTOR_MAX * 2) @@ -225,6 +227,7 @@ struct vhost_virtqueue { uint64_t *async_pending_info; uint16_t async_pkts_idx; uint16_t async_pkts_inflight_n; + uint16_t async_last_seg_n; /* vq async features */ bool async_inorder; diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c index 1d0be3dd4..17808ab29 100644 --- a/lib/librte_vhost/virtio_net.c +++ b/lib/librte_vhost/virtio_net.c @@ -1633,6 +1633,7 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id, struct vhost_virtqueue *vq; uint16_t n_pkts_cpl, n_pkts_put = 0, n_descs = 0; uint16_t start_idx, pkts_idx, vq_size; + uint16_t n_inflight; uint64_t *async_pending_info; VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__); @@ -1646,28 +1647,32 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id, rte_spinlock_lock(&vq->access_lock); + n_inflight = vq->async_pkts_inflight_n; pkts_idx = vq->async_pkts_idx; async_pending_info = vq->async_pending_info; vq_size = vq->size; start_idx = virtio_dev_rx_async_get_info_idx(pkts_idx, vq_size, vq->async_pkts_inflight_n); - n_pkts_cpl = - vq->async_ops.check_completed_copies(vid, queue_id, 0, count); + n_pkts_cpl = vq->async_ops.check_completed_copies(vid, queue_id, + 0, ASYNC_MAX_POLL_SEG - vq->async_last_seg_n) + + vq->async_last_seg_n; rte_smp_wmb(); - while (likely(((start_idx + n_pkts_put) & (vq_size - 1)) != pkts_idx)) { + while (likely((n_pkts_put < count) && n_inflight)) { uint64_t info = async_pending_info[ (start_idx + n_pkts_put) & (vq_size - 1)]; uint64_t n_segs; n_pkts_put++; + n_inflight--; n_descs += info & ASYNC_PENDING_INFO_N_MSK; n_segs = info >> ASYNC_PENDING_INFO_N_SFT; if (n_segs) { - if (!n_pkts_cpl || n_pkts_cpl < n_segs) { + if (unlikely(n_pkts_cpl < n_segs)) { n_pkts_put--; + n_inflight++; n_descs -= info & ASYNC_PENDING_INFO_N_MSK; if (n_pkts_cpl) { async_pending_info[ @@ -1684,8 +1689,10 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id, } } + vq->async_last_seg_n = n_pkts_cpl; + if (n_pkts_put) { - vq->async_pkts_inflight_n -= n_pkts_put; + vq->async_pkts_inflight_n = n_inflight; __atomic_add_fetch(&vq->used->idx, n_descs, __ATOMIC_RELEASE); vhost_vring_call_split(dev, vq); -- 2.18.4