public inbox for linux-nvme@lists.infradead.org
 help / color / mirror / Atom feed
From: Boris Pismenny <borisp@mellanox.com>
To: 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, dsahern@gmail.com,
	smalin@marvell.com
Cc: Yoray Zack <yorayz@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 v2 net-next 08/21] nvme-tcp : Recalculate crc in the end of the capsule
Date: Thu, 14 Jan 2021 17:10:20 +0200	[thread overview]
Message-ID: <20210114151033.13020-9-borisp@mellanox.com> (raw)
In-Reply-To: <20210114151033.13020-1-borisp@mellanox.com>

From: Ben Ben-ishay <benishay@nvidia.com>

crc offload of the nvme capsule. Check if all the skb bits
are on, and if not recalculate the crc in SW and check it.

This patch reworks 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: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ben Ben-Ishay <benishay@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Yoray Zack <yorayz@mellanox.com>
---
 drivers/nvme/host/tcp.c | 116 ++++++++++++++++++++++++++++++++--------
 1 file changed, 94 insertions(+), 22 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 9a43bd31ec15..09d2e2e529cd 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 {
@@ -95,6 +96,7 @@ 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;
@@ -233,6 +235,55 @@ 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;
+
+	req->ddp.sg_table.sgl = req->ddp.first_sgl;
+	ret = sg_alloc_table_chained(&req->ddp.sg_table, blk_rq_nr_phys_segments(rq),
+				     req->ddp.sg_table.sgl, SG_CHUNK_SIZE);
+	if (ret)
+		return -ENOMEM;
+	req->ddp.nents = blk_rq_map_sg(rq->q, rq, req->ddp.sg_table.sgl);
+	return 0;
+}
+
+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);
+}
+
 #ifdef CONFIG_TCP_DDP
 
 static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags);
@@ -289,12 +340,9 @@ int nvme_tcp_setup_ddp(struct nvme_tcp_queue *queue,
 	}
 
 	req->ddp.command_id = command_id;
-	req->ddp.sg_table.sgl = req->ddp.first_sgl;
-	ret = sg_alloc_table_chained(&req->ddp.sg_table, blk_rq_nr_phys_segments(rq),
-				     req->ddp.sg_table.sgl, SG_CHUNK_SIZE);
+	ret = nvme_tcp_req_map_sg(req, rq);
 	if (ret)
 		return -ENOMEM;
-	req->ddp.nents = blk_rq_map_sg(rq->q, rq, req->ddp.sg_table.sgl);
 
 	ret = netdev->tcp_ddp_ops->tcp_ddp_setup(netdev,
 						 queue->sock->sk,
@@ -316,7 +364,7 @@ int nvme_tcp_offload_socket(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))) {
 		dev_put(netdev);
 		return -EOPNOTSUPP;
 	}
@@ -344,6 +392,9 @@ 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;
 }
 
@@ -375,7 +426,7 @@ 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);
@@ -727,6 +778,7 @@ 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)
@@ -907,7 +959,8 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 
 	u64 pdu_seq = TCP_SKB_CB(skb)->seq + *offset - queue->pdu_offset;
 
-	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, pdu_seq);
 
 	ret = skb_copy_bits(skb, *offset,
@@ -976,6 +1029,8 @@ 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,
@@ -1013,15 +1068,17 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		recv_len = min_t(size_t, recv_len,
 				iov_iter_count(&req->iter));
 
-		if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags)) {
-			if (queue->data_digest)
+		if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags)) { 
+			if (queue->data_digest &&
+			    !test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
 				ret = skb_ddp_copy_and_hash_datagram_iter(skb, *offset,
 						&req->iter, recv_len, queue->rcv_hash);
 			else
 				ret = skb_ddp_copy_datagram_iter(skb, *offset,
 						&req->iter, recv_len);
 		} else {
-			if (queue->data_digest)
+			if (queue->data_digest &&
+			    !test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
 				ret = skb_copy_and_hash_datagram_iter(skb, *offset,
 						&req->iter, recv_len, queue->rcv_hash);
 			else
@@ -1043,7 +1100,6 @@ 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) {
@@ -1064,8 +1120,12 @@ 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;
@@ -1076,17 +1136,29 @@ 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;
+	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
+			rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue),
+					      pdu->command_id);
+			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);
+		if (!rq)
+			rq = blk_mq_tag_to_rq(nvme_tcp_tagset(queue),
+					      pdu->command_id);
 
 		nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
 		queue->nr_cqe++;
@@ -1825,8 +1897,10 @@ 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);
+
 }
 
 static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
@@ -1953,8 +2027,6 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
 {
 	int ret;
 
-	to_tcp_ctrl(ctrl)->offloading_netdev = NULL;
-
 	ret = nvme_tcp_alloc_queue(ctrl, 0, NVME_AQ_DEPTH);
 	if (ret)
 		return ret;
-- 
2.24.1


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

  parent reply	other threads:[~2021-01-14 15:11 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-14 15:10 [PATCH v2 net-next 00/21] nvme-tcp receive offloads Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 01/21] iov_iter: Introduce new procedures for copy to iter/pages Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 02/21] net: Introduce direct data placement tcp offload Boris Pismenny
2021-01-14 15:57   ` Eric Dumazet
2021-01-14 20:19     ` Boris Pismenny
2021-01-14 20:43       ` Eric Dumazet
2021-01-31 10:40         ` Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 03/21] net: Introduce crc offload for tcp ddp ulp Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 04/21] net: SKB copy(+hash) iterators for DDP offloads Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 05/21] net/tls: expose get_netdev_for_sock Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 06/21] nvme-tcp: Add DDP offload control path Boris Pismenny
2021-01-19  3:47   ` David Ahern
2021-01-31  7:51     ` Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 07/21] nvme-tcp: Add DDP data-path Boris Pismenny
2021-01-19  4:18   ` David Ahern
2021-01-31  8:44     ` Boris Pismenny
2021-01-14 15:10 ` Boris Pismenny [this message]
2021-01-14 15:10 ` [PATCH v2 net-next 09/21] nvme-tcp: Deal with netdevice DOWN events Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 10/21] net/mlx5: Header file changes for nvme-tcp offload Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 11/21] net/mlx5: Add 128B CQE for NVMEoTCP offload Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 12/21] net/mlx5e: TCP flow steering for nvme-tcp Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 13/21] net/mlx5e: NVMEoTCP offload initialization Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 14/21] net/mlx5e: KLM UMR helper macros Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 15/21] net/mlx5e: NVMEoTCP use KLM UMRs Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 16/21] net/mlx5e: NVMEoTCP queue init/teardown Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 17/21] net/mlx5e: NVMEoTCP async ddp invalidation Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 18/21] net/mlx5e: NVMEoTCP ddp setup and resync Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 19/21] net/mlx5e: NVMEoTCP, data-path for DDP offload Boris Pismenny
2021-01-16  4:57   ` David Ahern
2021-01-17  8:42     ` Boris Pismenny
2021-01-19  4:36       ` David Ahern
2021-01-31  9:27         ` Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 20/21] net/mlx5e: NVMEoTCP statistics Boris Pismenny
2021-01-14 15:10 ` [PATCH v2 net-next 21/21] Documentation: add TCP DDP offload documentation Boris Pismenny

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=20210114151033.13020-9-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