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 9BDF0A04FD;
	Mon, 23 May 2022 12:23:07 +0200 (CEST)
Received: from [217.70.189.124] (localhost [127.0.0.1])
	by mails.dpdk.org (Postfix) with ESMTP id 2282942824;
	Mon, 23 May 2022 12:22:47 +0200 (CEST)
Received: from mga18.intel.com (mga18.intel.com [134.134.136.126])
 by mails.dpdk.org (Postfix) with ESMTP id 0941340041
 for <dev@dpdk.org>; Mon, 23 May 2022 12:22:45 +0200 (CEST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple;
 d=intel.com; i=@intel.com; q=dns/txt; s=Intel;
 t=1653301366; x=1684837366;
 h=from:to:cc:subject:date:message-id:in-reply-to: references;
 bh=9gtdDkzEKSRAJs8DgVKi2p/HiEojZu7hZPdWl2eRWlI=;
 b=DAISFspNIYbTGwtnF3xsBRzpU9bwX1mWWA6nVVwRUqnTUMkrmkVozWoz
 nqnnTtl1NVJLNhEIxRJ9nySfSs9XDKfM/hM2/qVQSbyt0wsCY7fO/5azB
 2xiqtutTQvptZFA3ZZJjJBDSZK03ZFqk7gx5EGYLFYtwIt/6C/GXFeLhL
 VVvIJiCzyqvL9cwg6AEjqrInnVlUxLyPkEgLLzy2XXgewwwMcLWRmJYE0
 zJ487SOfWvl5pXkyrolT+66hiXYH+IV0cKIt9f9llOFwIS0hgLsniJREc
 vbRQu+PEvmRelDj+GOdDvsKgMk5VcsfQuBLGSsonJPOLqTrykf8GSrhLz A==;
X-IronPort-AV: E=McAfee;i="6400,9594,10355"; a="255239331"
X-IronPort-AV: E=Sophos;i="5.91,246,1647327600"; d="scan'208";a="255239331"
Received: from orsmga006.jf.intel.com ([10.7.209.51])
 by orsmga106.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384;
 23 May 2022 03:22:45 -0700
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.91,246,1647327600"; d="scan'208";a="547889444"
Received: from dpdk-dipei.sh.intel.com ([10.67.110.238])
 by orsmga006.jf.intel.com with ESMTP; 23 May 2022 03:22:43 -0700
From: Andy Pei <andy.pei@intel.com>
To: dev@dpdk.org
Cc: chenbo.xia@intel.com, maxime.coquelin@redhat.com, gang.cao@intel.com,
 changpeng.liu@intel.com, rosen.xu@intel.com, qimaix.xiao@intel.com
Subject: [PATCH v9 06/13] vdpa/ifc: add block device SW live-migration
Date: Mon, 23 May 2022 17:35:17 +0800
Message-Id: <1653298524-232138-7-git-send-email-andy.pei@intel.com>
X-Mailer: git-send-email 1.8.3.1
In-Reply-To: <1653298524-232138-1-git-send-email-andy.pei@intel.com>
References: <1643093258-47258-2-git-send-email-andy.pei@intel.com>
 <1653298524-232138-1-git-send-email-andy.pei@intel.com>
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

Add SW live-migration support to block device.
For block device, it is critical that no packet
should be dropped. So when virtio blk device is
paused, make sure hardware last_avail_idx and
last_used_idx are the same. This indicates all
requests have received acks, and no inflight IO.

Signed-off-by: Andy Pei <andy.pei@intel.com>
---
 drivers/vdpa/ifc/base/ifcvf.h |  1 +
 drivers/vdpa/ifc/ifcvf_vdpa.c | 42 ++++++++++++++++++++++++++++++++++++++----
 2 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/drivers/vdpa/ifc/base/ifcvf.h b/drivers/vdpa/ifc/base/ifcvf.h
index b6fdfdb..9d95aac 100644
--- a/drivers/vdpa/ifc/base/ifcvf.h
+++ b/drivers/vdpa/ifc/base/ifcvf.h
@@ -63,6 +63,7 @@
 #define IFCVF_MEDIATED_VRING		0x200000000000
 
 #define IFCVF_32_BIT_MASK		0xffffffff
+#define IFCVF_16_BIT_MASK		0xffff
 
 
 #ifndef VHOST_USER_PROTOCOL_F_CONFIG
diff --git a/drivers/vdpa/ifc/ifcvf_vdpa.c b/drivers/vdpa/ifc/ifcvf_vdpa.c
index 1d05529..7a0bdb4 100644
--- a/drivers/vdpa/ifc/ifcvf_vdpa.c
+++ b/drivers/vdpa/ifc/ifcvf_vdpa.c
@@ -316,8 +316,34 @@ struct rte_vdpa_dev_info {
 	uint64_t features = 0;
 	uint64_t log_base = 0, log_size = 0;
 	uint64_t len;
+	u32 ring_state = 0;
 
 	vid = internal->vid;
+
+	/* to make sure no packet is lost for blk device
+	 * do not stop until last_avail_idx == last_used_idx
+	 */
+	if (internal->hw.device_type == IFCVF_BLK) {
+		for (i = 0; i < hw->nr_vring; i++) {
+			do {
+				if (hw->lm_cfg != NULL)
+					ring_state = *(u32 *)(hw->lm_cfg +
+						IFCVF_LM_RING_STATE_OFFSET +
+						i * IFCVF_LM_CFG_SIZE);
+				hw->vring[i].last_avail_idx =
+					(u16)(ring_state & IFCVF_16_BIT_MASK);
+				hw->vring[i].last_used_idx =
+					(u16)(ring_state >> 16);
+				if (hw->vring[i].last_avail_idx !=
+					hw->vring[i].last_used_idx) {
+					ifcvf_notify_queue(hw, i);
+					usleep(10);
+				}
+			} while (hw->vring[i].last_avail_idx !=
+				hw->vring[i].last_used_idx);
+		}
+	}
+
 	ifcvf_stop_hw(hw);
 
 	for (i = 0; i < hw->nr_vring; i++)
@@ -641,8 +667,10 @@ struct rte_vdpa_dev_info {
 		}
 		hw->vring[i].avail = gpa;
 
-		/* Direct I/O for Tx queue, relay for Rx queue */
-		if (i & 1) {
+		/* NET: Direct I/O for Tx queue, relay for Rx queue
+		 * BLK: relay every queue
+		 */
+		if ((internal->hw.device_type == IFCVF_NET) && (i & 1)) {
 			gpa = hva_to_gpa(vid, (uint64_t)(uintptr_t)vq.used);
 			if (gpa == 0) {
 				DRV_LOG(ERR, "Fail to get GPA for used ring.");
@@ -692,8 +720,12 @@ struct rte_vdpa_dev_info {
 
 	for (i = 0; i < hw->nr_vring; i++) {
 		/* synchronize remaining new used entries if any */
-		if ((i & 1) == 0)
+		if (internal->hw.device_type == IFCVF_NET) {
+			if ((i & 1) == 0)
+				update_used_ring(internal, i);
+		} else if (internal->hw.device_type == IFCVF_BLK) {
 			update_used_ring(internal, i);
+		}
 
 		rte_vhost_get_vhost_vring(vid, i, &vq);
 		len = IFCVF_USED_RING_LEN(vq.size);
@@ -755,7 +787,9 @@ struct rte_vdpa_dev_info {
 		}
 	}
 
-	for (qid = 0; qid < q_num; qid += 2) {
+	for (qid = 0; qid < q_num; qid += 1) {
+		if ((internal->hw.device_type == IFCVF_NET) && (qid & 1))
+			continue;
 		ev.events = EPOLLIN | EPOLLPRI;
 		/* leave a flag to mark it's for interrupt */
 		ev.data.u64 = 1 | qid << 1 |
-- 
1.8.3.1