public inbox for linux-nvme@lists.infradead.org
 help / color / mirror / Atom feed
From: Boris Pismenny <borisp@mellanox.com>
To: <dsahern@gmail.com>, <kuba@kernel.org>, <davem@davemloft.net>,
	<saeedm@nvidia.com>, <hch@lst.de>, <sagi@grimberg.me>,
	<axboe@fb.com>, <kbusch@kernel.org>, <viro@zeniv.linux.org.uk>,
	<edumazet@google.com>, <smalin@marvell.com>
Cc: Yoray Zack <yorayz@mellanox.com>,
	Boris Pismenny <borisp@mellanox.com>,
	yorayz@nvidia.com, boris.pismenny@gmail.com,
	Ben Ben-Ishay <benishay@mellanox.com>,
	benishay@nvidia.com, linux-nvme@lists.infradead.org,
	netdev@vger.kernel.org, Or Gerlitz <ogerlitz@mellanox.com>,
	ogerlitz@nvidia.com
Subject: [PATCH v4 net-next  08/21] nvme-tcp: RX CRC offload
Date: Thu, 11 Feb 2021 23:10:31 +0200	[thread overview]
Message-ID: <20210211211044.32701-9-borisp@mellanox.com> (raw)
In-Reply-To: <20210211211044.32701-1-borisp@mellanox.com>

From: Yoray Zack <yorayz@mellanox.com>

Enable rx side of crc offload when supported.

At the end of the capsule, check if all the skb bits are
on, and if not recalculate the crc in SW and check it.

We reworked the receive-side crc calculation to always run
at the end, so as to keep a single flow for both offload and
non-offload. This change simplifies the code, but it may
degrade performance for non-offload crc calculation.

Signed-off-by: Yoray Zack <yorayz@mellanox.com>
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ben Ben-Ishay <benishay@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
 drivers/nvme/host/tcp.c | 86 ++++++++++++++++++++++++++++++++++-------
 1 file changed, 71 insertions(+), 15 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 188e26ab7116..09cb9b2e2c2d 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -69,6 +69,7 @@ enum nvme_tcp_queue_flags {
 	NVME_TCP_Q_LIVE		= 1,
 	NVME_TCP_Q_POLLING	= 2,
 	NVME_TCP_Q_OFF_DDP	= 3,
+	NVME_TCP_Q_OFF_DDGST_RX = 4,
 };
 
 enum nvme_tcp_recv_state {
@@ -96,6 +97,7 @@ struct nvme_tcp_queue {
 	size_t			data_remaining;
 	size_t			ddgst_remaining;
 	unsigned int		nr_cqe;
+	bool			ddgst_valid;
 
 	/* send state */
 	struct nvme_tcp_request *request;
@@ -234,6 +236,22 @@ static inline size_t nvme_tcp_pdu_last_send(struct nvme_tcp_request *req,
 	return nvme_tcp_pdu_data_left(req) <= len;
 }
 
+static inline bool nvme_tcp_ddp_ddgst_ok(struct nvme_tcp_queue *queue)
+{
+	return queue->ddgst_valid;
+}
+
+static inline void nvme_tcp_ddp_ddgst_update(struct nvme_tcp_queue *queue,
+					     struct sk_buff *skb)
+{
+	if (queue->ddgst_valid)
+#ifdef CONFIG_TCP_DDP_CRC
+		queue->ddgst_valid = skb->ddp_crc;
+#else
+		queue->ddgst_valid = false;
+#endif
+}
+
 static int nvme_tcp_req_map_sg(struct nvme_tcp_request *req, struct request *rq)
 {
 	int ret;
@@ -247,7 +265,27 @@ static int nvme_tcp_req_map_sg(struct nvme_tcp_request *req, struct request *rq)
 	return 0;
 }
 
-#ifdef CONFIG_TCP_DDP
+static void nvme_tcp_ddp_ddgst_recalc(struct ahash_request *hash,
+				      struct request *rq)
+{
+	struct nvme_tcp_request *req;
+
+	if (!rq)
+		return;
+
+	req = blk_mq_rq_to_pdu(rq);
+
+	if (!req->offloaded && nvme_tcp_req_map_sg(req, rq))
+		return;
+
+	crypto_ahash_init(hash);
+	req->ddp.sg_table.sgl = req->ddp.first_sgl;
+	ahash_request_set_crypt(hash, req->ddp.sg_table.sgl, NULL,
+				le32_to_cpu(req->data_len));
+	crypto_ahash_update(hash);
+}
+
+#if defined(CONFIG_TCP_DDP) || defined(CONFIG_TCP_DDP_CRC)
 
 static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags);
 static void nvme_tcp_ddp_teardown_done(void *ddp_ctx);
@@ -316,7 +354,7 @@ static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
 	struct nvme_tcp_ddp_config config = {};
 	int ret;
 
-	if (!(netdev->features & NETIF_F_HW_TCP_DDP))
+	if (!(netdev->features & (NETIF_F_HW_TCP_DDP | NETIF_F_HW_TCP_DDP_CRC_RX)))
 		return -EOPNOTSUPP;
 
 	config.cfg.type		= TCP_DDP_NVME;
@@ -343,6 +381,9 @@ static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
 	if (netdev->features & NETIF_F_HW_TCP_DDP)
 		set_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
 
+	if (netdev->features & NETIF_F_HW_TCP_DDP_CRC_RX)
+		set_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags);
+
 	return ret;
 }
 
@@ -373,7 +414,7 @@ static int nvme_tcp_offload_limits(struct nvme_tcp_queue *queue)
 		return -ENODEV;
 	}
 
-	if (netdev->features & NETIF_F_HW_TCP_DDP &&
+	if ((netdev->features & (NETIF_F_HW_TCP_DDP | NETIF_F_HW_TCP_DDP_CRC_RX)) &&
 	    netdev->tcp_ddp_ops &&
 	    netdev->tcp_ddp_ops->tcp_ddp_limits)
 		ret = netdev->tcp_ddp_ops->tcp_ddp_limits(netdev, &limits);
@@ -720,6 +761,7 @@ static void nvme_tcp_init_recv_ctx(struct nvme_tcp_queue *queue)
 	queue->pdu_offset = 0;
 	queue->data_remaining = -1;
 	queue->ddgst_remaining = 0;
+	queue->ddgst_valid = true;
 }
 
 static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
@@ -906,7 +948,8 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 	size_t rcv_len = min_t(size_t, *len, queue->pdu_remaining);
 	int ret;
 
-	if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags))
+	if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags) ||
+	    test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
 		nvme_tcp_resync_response(queue, skb, *offset);
 
 	ret = skb_copy_bits(skb, *offset,
@@ -995,6 +1038,8 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 	struct nvme_tcp_request *req;
 	struct request *rq;
 
+	if (queue->data_digest && test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
+		nvme_tcp_ddp_ddgst_update(queue, skb);
 	rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
 	if (!rq) {
 		dev_err(queue->ctrl->ctrl.device,
@@ -1047,7 +1092,6 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 
 	if (!queue->data_remaining) {
 		if (queue->data_digest) {
-			nvme_tcp_ddgst_final(queue->rcv_hash, &queue->exp_ddgst);
 			queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH;
 		} else {
 			if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
@@ -1068,8 +1112,12 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
 	char *ddgst = (char *)&queue->recv_ddgst;
 	size_t recv_len = min_t(size_t, *len, queue->ddgst_remaining);
 	off_t off = NVME_TCP_DIGEST_LENGTH - queue->ddgst_remaining;
+	bool offload_fail, offload_en;
+	struct request *rq = NULL;
 	int ret;
 
+	if (test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
+		nvme_tcp_ddp_ddgst_update(queue, skb);
 	ret = skb_copy_bits(skb, *offset, &ddgst[off], recv_len);
 	if (unlikely(ret))
 		return ret;
@@ -1080,18 +1128,25 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
 	if (queue->ddgst_remaining)
 		return 0;
 
-	if (queue->recv_ddgst != queue->exp_ddgst) {
-		dev_err(queue->ctrl->ctrl.device,
-			"data digest error: recv %#x expected %#x\n",
-			le32_to_cpu(queue->recv_ddgst),
-			le32_to_cpu(queue->exp_ddgst));
-		return -EIO;
+	rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
+
+	offload_fail = !nvme_tcp_ddp_ddgst_ok(queue);
+	offload_en = test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags);
+	if (!offload_en || offload_fail) {
+		if (offload_en && offload_fail)  // software-fallback
+			nvme_tcp_ddp_ddgst_recalc(queue->rcv_hash, rq);
+
+		nvme_tcp_ddgst_final(queue->rcv_hash, &queue->exp_ddgst);
+		if (queue->recv_ddgst != queue->exp_ddgst) {
+			dev_err(queue->ctrl->ctrl.device,
+				"data digest error: recv %#x expected %#x\n",
+				le32_to_cpu(queue->recv_ddgst),
+				le32_to_cpu(queue->exp_ddgst));
+			return -EIO;
+		}
 	}
 
 	if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
-		struct request *rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue),
-						pdu->command_id);
-
 		nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
 		queue->nr_cqe++;
 	}
@@ -1833,7 +1888,8 @@ static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue)
 	nvme_tcp_restore_sock_calls(queue);
 	cancel_work_sync(&queue->io_work);
 
-	if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags))
+	if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags) ||
+	    test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
 		nvme_tcp_unoffload_socket(queue);
 }
 
-- 
2.24.1


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

  parent reply	other threads:[~2021-02-11 21:12 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-11 21:10 [PATCH v4 net-next 00/21] nvme-tcp receive offloads Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 01/21] net: Introduce direct data placement tcp offload Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 02/21] net: Introduce crc offload for tcp ddp ulp Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 03/21] iov_iter: DDP copy to iter/pages Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 04/21] net: skb copy(+hash) iterators for DDP offloads Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 05/21] net/tls: expose get_netdev_for_sock Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 06/21] nvme-tcp: Add DDP offload control path Boris Pismenny
2021-02-14 18:16   ` David Ahern
2021-02-15  7:57     ` Or Gerlitz
2021-02-17 13:55     ` Or Gerlitz
2021-02-21 11:29       ` Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 07/21] nvme-tcp: Add DDP data-path Boris Pismenny
2021-02-14 18:27   ` David Ahern
2021-02-17 14:01     ` Or Gerlitz
2021-02-17 17:00       ` David Ahern
2021-02-21 11:44         ` Boris Pismenny
2021-02-11 21:10 ` Boris Pismenny [this message]
2021-02-11 21:10 ` [PATCH v4 net-next 09/21] nvme-tcp: Deal with netdevice DOWN events Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 10/21] net/mlx5: Header file changes for nvme-tcp offload Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 11/21] net/mlx5: Add 128B CQE for NVMEoTCP offload Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 12/21] net/mlx5e: TCP flow steering for nvme-tcp Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 13/21] net/mlx5e: NVMEoTCP offload initialization Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 14/21] net/mlx5e: KLM UMR helper macros Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 15/21] net/mlx5e: NVMEoTCP use KLM UMRs Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 16/21] net/mlx5e: NVMEoTCP queue init/teardown Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 17/21] net/mlx5e: NVMEoTCP async ddp invalidation Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 18/21] net/mlx5e: NVMEoTCP ddp setup and resync Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 19/21] net/mlx5e: NVMEoTCP, data-path for DDP+CRC offload Boris Pismenny
2021-02-11 21:10 ` [PATCH v4 net-next 20/21] net/mlx5e: NVMEoTCP statistics Boris Pismenny
2021-02-11 21:32 ` [PATCH v4 net-next 00/21] nvme-tcp receive offloads Randy Dunlap
2021-02-12  5:22   ` Boris Pismenny
2021-02-21  8:52 ` Or Gerlitz

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=20210211211044.32701-9-borisp@mellanox.com \
    --to=borisp@mellanox.com \
    --cc=axboe@fb.com \
    --cc=benishay@mellanox.com \
    --cc=benishay@nvidia.com \
    --cc=boris.pismenny@gmail.com \
    --cc=davem@davemloft.net \
    --cc=dsahern@gmail.com \
    --cc=edumazet@google.com \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=kuba@kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=netdev@vger.kernel.org \
    --cc=ogerlitz@mellanox.com \
    --cc=ogerlitz@nvidia.com \
    --cc=saeedm@nvidia.com \
    --cc=sagi@grimberg.me \
    --cc=smalin@marvell.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=yorayz@mellanox.com \
    --cc=yorayz@nvidia.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