Netdev Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Boris Pismenny <borisp@nvidia.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: <boris.pismenny@gmail.com>, <linux-nvme@lists.infradead.org>,
	<netdev@vger.kernel.org>, <benishay@nvidia.com>,
	<ogerlitz@nvidia.com>, <yorayz@nvidia.com>,
	Yoray Zack <yorayz@mellanox.com>,
	Boris Pismenny <borisp@mellanox.com>,
	Ben Ben-Ishay <benishay@mellanox.com>,
	Or Gerlitz <ogerlitz@mellanox.com>
Subject: [PATCH v5 net-next 07/36] nvme-tcp: RX DDGST offload
Date: Thu, 22 Jul 2021 14:02:56 +0300	[thread overview]
Message-ID: <20210722110325.371-8-borisp@nvidia.com> (raw)
In-Reply-To: <20210722110325.371-1-borisp@nvidia.com>

From: Yoray Zack <yorayz@mellanox.com>

Enable rx side of DDGST offload when supported.

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

We reworked the receive-side DDGST 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 DDGST 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 34982fb0c655..b23fdbb4fd8b 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;
@@ -230,6 +232,22 @@ 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_ULP_DDP
+		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;
@@ -243,6 +261,26 @@ static int nvme_tcp_req_map_sg(struct nvme_tcp_request *req, struct request *rq)
 	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_ULP_DDP
 
 static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags);
@@ -330,8 +368,10 @@ static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
 	}
 
 	inet_csk(queue->sock->sk)->icsk_ulp_ddp_ops = &nvme_tcp_ddp_ulp_ops;
-	if (netdev->features & NETIF_F_HW_ULP_DDP)
+	if (netdev->features & NETIF_F_HW_ULP_DDP) {
 		set_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
+		set_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags);
+	}
 
 	return ret;
 }
@@ -346,6 +386,7 @@ static void nvme_tcp_unoffload_socket(struct nvme_tcp_queue *queue)
 	}
 
 	clear_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
+	clear_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags);
 
 	netdev->ulp_ddp_ops->ulp_ddp_sk_del(netdev, queue->sock->sk);
 
@@ -721,6 +762,7 @@ 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)
@@ -914,7 +956,8 @@ 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,
@@ -977,14 +1020,14 @@ static int nvme_tcp_consume_skb(struct nvme_tcp_queue *queue, struct sk_buff *sk
 
 #ifdef CONFIG_ULP_DDP
 	if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags)) {
-		if (queue->data_digest)
+		if (queue->data_digest && !test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
 			ret = skb_ddp_copy_and_hash_datagram_iter(skb, *offset, iter, recv_len,
 					queue->rcv_hash);
 		else
 			ret = skb_ddp_copy_datagram_iter(skb, *offset, iter, recv_len);
 	} else {
 #endif
-		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, iter, recv_len,
 					queue->rcv_hash);
 		else
@@ -1003,6 +1046,8 @@ 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,
@@ -1055,7 +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) {
@@ -1076,8 +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;
@@ -1088,18 +1136,25 @@ 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++;
 	}
@@ -1851,7 +1906,8 @@ 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


  parent reply	other threads:[~2021-07-22 11:05 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-22 11:02 [PATCH v5 net-next 00/36] nvme-tcp receive and tarnsmit offloads Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 01/36] net: Introduce direct data placement tcp offload Boris Pismenny
2021-07-22 11:26   ` Eric Dumazet
2021-07-22 12:18     ` Boris Pismenny
2021-07-22 13:10       ` Eric Dumazet
2021-07-22 13:33         ` Boris Pismenny
2021-07-22 13:39           ` Eric Dumazet
2021-07-22 14:02             ` Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 02/36] iov_iter: DDP copy to iter/pages Boris Pismenny
2021-07-22 13:31   ` Christoph Hellwig
2021-07-22 20:23     ` Boris Pismenny
2021-07-23  5:03       ` Christoph Hellwig
2021-07-23  5:21         ` Al Viro
2021-08-04 14:13           ` Or Gerlitz
2021-08-10 13:29             ` Or Gerlitz
2021-07-22 20:55   ` Al Viro
2021-07-22 11:02 ` [PATCH v5 net-next 03/36] net: skb copy(+hash) iterators for DDP offloads Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 04/36] net/tls: expose get_netdev_for_sock Boris Pismenny
2021-07-23  6:06   ` Christoph Hellwig
2021-08-04 13:26     ` Or Gerlitz
     [not found]       ` <20210804072918.17ba9cff@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com>
2021-08-04 15:07         ` Or Gerlitz
2021-08-10 13:25           ` Or Gerlitz
2021-07-22 11:02 ` [PATCH v5 net-next 05/36] nvme-tcp: Add DDP offload control path Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 06/36] nvme-tcp: Add DDP data-path Boris Pismenny
2021-07-22 11:02 ` Boris Pismenny [this message]
2021-07-22 11:02 ` [PATCH v5 net-next 08/36] nvme-tcp: Deal with netdevice DOWN events Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 09/36] net/mlx5: Header file changes for nvme-tcp offload Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 10/36] net/mlx5: Add 128B CQE for NVMEoTCP offload Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 11/36] net/mlx5e: TCP flow steering for nvme-tcp Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 12/36] net/mlx5e: NVMEoTCP offload initialization Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 13/36] net/mlx5e: KLM UMR helper macros Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 14/36] net/mlx5e: NVMEoTCP use KLM UMRs Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 15/36] net/mlx5e: NVMEoTCP queue init/teardown Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 16/36] net/mlx5e: NVMEoTCP async ddp invalidation Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 17/36] net/mlx5e: NVMEoTCP ddp setup and resync Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 18/36] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 19/36] net/mlx5e: NVMEoTCP statistics Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 20/36] Documentation: add ULP DDP offload documentation Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 21/36] net: drop ULP DDP HW offload feature if no CSUM offload feature Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 22/36] net: Add ulp_ddp_pdu_info struct Boris Pismenny
2021-07-23 19:42   ` Sagi Grimberg
2021-07-22 11:03 ` [PATCH v5 net-next 23/36] net: Add to ulp_ddp support for fallback flow Boris Pismenny
2021-07-23  6:09   ` Christoph Hellwig
2021-07-22 11:03 ` [PATCH v5 net-next 24/36] net: Add MSG_DDP_CRC flag Boris Pismenny
2021-07-22 14:23   ` Eric Dumazet
2021-07-22 11:03 ` [PATCH v5 net-next 25/36] nvme-tcp: TX DDGST offload Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 26/36] nvme-tcp: Mapping between Tx NVMEoTCP pdu and TCP sequence Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 27/36] mlx5e: make preparation in TLS code for NVMEoTCP CRC Tx offload Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 28/36] mlx5: Add sq state test bit for nvmeotcp Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 29/36] mlx5: Add support to NETIF_F_HW_TCP_DDP_CRC_TX feature Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 30/36] net/mlx5e: NVMEoTCP DDGST TX offload TIS Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 31/36] net/mlx5e: NVMEoTCP DDGST Tx offload queue init/teardown Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 32/36] net/mlx5e: NVMEoTCP DDGST TX BSF and PSV Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 33/36] net/mlx5e: NVMEoTCP DDGST TX Data path Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 34/36] net/mlx5e: NVMEoTCP DDGST TX handle OOO packets Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 35/36] net/mlx5e: NVMEoTCP DDGST TX offload optimization Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 36/36] net/mlx5e: NVMEoTCP DDGST TX statistics Boris Pismenny
2021-07-23  5:56 ` [PATCH v5 net-next 00/36] nvme-tcp receive and tarnsmit offloads Christoph Hellwig
2021-07-23 19:58   ` Sagi Grimberg
2021-08-04 13:51     ` Or Gerlitz
2021-08-06 19:46       ` Sagi Grimberg
2021-08-10 13:37         ` 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=20210722110325.371-8-borisp@nvidia.com \
    --to=borisp@nvidia.com \
    --cc=axboe@fb.com \
    --cc=benishay@mellanox.com \
    --cc=benishay@nvidia.com \
    --cc=boris.pismenny@gmail.com \
    --cc=borisp@mellanox.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 \
    --subject='Re: [PATCH v5 net-next 07/36] nvme-tcp: RX DDGST offload' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).