All of lore.kernel.org
 help / color / mirror / Atom feed
From: Aurelien Aptel <aaptel@nvidia.com>
To: linux-nvme@lists.infradead.org, netdev@vger.kernel.org,
	sagi@grimberg.me, hch@lst.de, kbusch@kernel.org, axboe@fb.com,
	chaitanyak@nvidia.com, davem@davemloft.net, kuba@kernel.org
Cc: Aurelien Aptel <aaptel@nvidia.com>,
	aurelien.aptel@gmail.com, smalin@nvidia.com, malin1024@gmail.com,
	ogerlitz@nvidia.com, yorayz@nvidia.com, borisp@nvidia.com
Subject: [PATCH v10 09/25] nvme-tcp: RX DDGST offload
Date: Thu, 26 Jan 2023 18:21:20 +0200	[thread overview]
Message-ID: <20230126162136.13003-10-aaptel@nvidia.com> (raw)
In-Reply-To: <20230126162136.13003-1-aaptel@nvidia.com>

From: Yoray Zack <yorayz@nvidia.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.

Signed-off-by: Yoray Zack <yorayz@nvidia.com>
Signed-off-by: Boris Pismenny <borisp@nvidia.com>
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Signed-off-by: Or Gerlitz <ogerlitz@nvidia.com>
Signed-off-by: Shai Malin <smalin@nvidia.com>
Signed-off-by: Aurelien Aptel <aaptel@nvidia.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
---
 drivers/nvme/host/tcp.c | 142 ++++++++++++++++++++++++++++++++++++----
 1 file changed, 128 insertions(+), 14 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 533177971777..7e3feb694e46 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -116,6 +116,7 @@ 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 {
@@ -143,6 +144,9 @@ struct nvme_tcp_queue {
 	size_t			ddgst_remaining;
 	unsigned int		nr_cqe;
 
+#ifdef CONFIG_ULP_DDP
+	bool			ddp_ddgst_valid;
+
 	/*
 	 * resync_req is a speculative PDU header tcp seq number (with
 	 * an additional flag at 32 lower bits) that the HW send to
@@ -152,6 +156,7 @@ struct nvme_tcp_queue {
 	 *   is pending (ULP_DDP_RESYNC_PENDING).
 	 */
 	atomic64_t		resync_req;
+#endif
 
 	/* send state */
 	struct nvme_tcp_request *request;
@@ -288,9 +293,22 @@ static inline size_t nvme_tcp_pdu_last_send(struct nvme_tcp_request *req,
 
 #ifdef CONFIG_ULP_DDP
 
-static inline bool is_netdev_ulp_offload_active(struct net_device *netdev)
+static inline bool is_netdev_ulp_offload_active(struct net_device *netdev,
+						struct nvme_tcp_queue *queue)
 {
-	return test_bit(ULP_DDP_C_NVME_TCP_BIT, netdev->ulp_ddp_caps.active);
+	bool ddgst_offload;
+
+	if (test_bit(ULP_DDP_C_NVME_TCP_BIT, netdev->ulp_ddp_caps.active))
+		return true;
+
+	ddgst_offload = test_bit(ULP_DDP_C_NVME_TCP_DDGST_RX_BIT,
+				 netdev->ulp_ddp_caps.active);
+	if (!queue && ddgst_offload)
+		return true;
+	if (queue && queue->data_digest && ddgst_offload)
+		return true;
+
+	return false;
 }
 
 static bool nvme_tcp_ddp_query_limits(struct net_device *netdev,
@@ -298,7 +316,7 @@ static bool nvme_tcp_ddp_query_limits(struct net_device *netdev,
 {
 	int ret;
 
-	if (!netdev || !is_netdev_ulp_offload_active(netdev) ||
+	if (!netdev || !is_netdev_ulp_offload_active(netdev, NULL) ||
 	    !netdev->netdev_ops->ulp_ddp_ops->limits)
 		return false;
 
@@ -314,6 +332,18 @@ static bool nvme_tcp_ddp_query_limits(struct net_device *netdev,
 	return true;
 }
 
+static inline bool nvme_tcp_ddp_ddgst_ok(struct nvme_tcp_queue *queue)
+{
+	return queue->ddp_ddgst_valid;
+}
+
+static inline void nvme_tcp_ddp_ddgst_update(struct nvme_tcp_queue *queue,
+					     struct sk_buff *skb)
+{
+	if (queue->ddp_ddgst_valid)
+		queue->ddp_ddgst_valid = skb_is_ulp_crc(skb);
+}
+
 static int nvme_tcp_req_map_sg(struct nvme_tcp_request *req, struct request *rq)
 {
 	int ret;
@@ -328,6 +358,38 @@ 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,
+				      __le32 *ddgst)
+{
+	struct nvme_tcp_request *req;
+
+	if (!rq)
+		return;
+
+	req = blk_mq_rq_to_pdu(rq);
+
+	if (!req->offloaded) {
+		/* if we have DDGST_RX offload without DDP the request
+		 * wasn't mapped, so we need to map it here
+		 */
+		if (nvme_tcp_req_map_sg(req, rq))
+			return;
+	}
+
+	req->ddp.sg_table.sgl = req->ddp.first_sgl;
+	ahash_request_set_crypt(hash, req->ddp.sg_table.sgl, (u8 *)ddgst,
+				req->data_len);
+	crypto_ahash_digest(hash);
+
+	if (!req->offloaded) {
+		/* without DDP, ddp_teardown() won't be called, so
+		 * free the table here
+		 */
+		sg_free_table_chained(&req->ddp.sg_table, SG_CHUNK_SIZE);
+	}
+}
+
 static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags);
 static void nvme_tcp_ddp_teardown_done(void *ddp_ctx);
 static const struct ulp_ddp_ulp_ops nvme_tcp_ddp_ulp_ops = {
@@ -387,6 +449,10 @@ static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
 {
 	struct net_device *netdev = queue->ctrl->offloading_netdev;
 	struct ulp_ddp_config config = {.type = ULP_DDP_NVME};
+	bool offload_ddp = test_bit(ULP_DDP_C_NVME_TCP_BIT,
+				    netdev->ulp_ddp_caps.active);
+	bool offload_ddgst_rx = test_bit(ULP_DDP_C_NVME_TCP_DDGST_RX_BIT,
+					 netdev->ulp_ddp_caps.active);
 	int ret;
 
 	config.nvmeotcp.pfv = NVME_TCP_PFV_1_0;
@@ -413,7 +479,10 @@ 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;
-	set_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
+	if (offload_ddp)
+		set_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
+	if (queue->data_digest && offload_ddgst_rx)
+		set_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags);
 	return 0;
 }
 
@@ -427,6 +496,7 @@ 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->netdev_ops->ulp_ddp_ops->sk_del(netdev, queue->sock->sk);
 
@@ -519,11 +589,26 @@ static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags)
 
 #else
 
-static inline bool is_netdev_ulp_offload_active(struct net_device *netdev)
+static inline bool is_netdev_ulp_offload_active(struct net_device *netdev,
+						struct nvme_tcp_queue *queue)
 {
 	return false;
 }
 
+static inline bool nvme_tcp_ddp_ddgst_ok(struct nvme_tcp_queue *queue)
+{
+	return true;
+}
+
+static inline void nvme_tcp_ddp_ddgst_update(struct nvme_tcp_queue *queue,
+					     struct sk_buff *skb)
+{}
+
+static void nvme_tcp_ddp_ddgst_recalc(struct ahash_request *hash,
+				      struct request *rq,
+				      __le32 *ddgst)
+{}
+
 static int nvme_tcp_setup_ddp(struct nvme_tcp_queue *queue, u16 command_id,
 			      struct request *rq)
 {
@@ -806,6 +891,9 @@ static void nvme_tcp_init_recv_ctx(struct nvme_tcp_queue *queue)
 	queue->pdu_offset = 0;
 	queue->data_remaining = -1;
 	queue->ddgst_remaining = 0;
+#ifdef CONFIG_ULP_DDP
+	queue->ddp_ddgst_valid = true;
+#endif
 }
 
 static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
@@ -1009,7 +1097,8 @@ 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,
@@ -1073,6 +1162,10 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		nvme_cid_to_rq(nvme_tcp_tagset(queue), pdu->command_id);
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 
+	if (queue->data_digest &&
+	    test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags))
+		nvme_tcp_ddp_ddgst_update(queue, skb);
+
 	while (true) {
 		int recv_len, ret;
 
@@ -1101,7 +1194,8 @@ 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 (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
@@ -1143,8 +1237,11 @@ 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;
+	struct request *rq;
 	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;
@@ -1155,9 +1252,25 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
 	if (queue->ddgst_remaining)
 		return 0;
 
+	rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
+			    pdu->command_id);
+
+	if (test_bit(NVME_TCP_Q_OFF_DDGST_RX, &queue->flags)) {
+		/*
+		 * If HW successfully offloaded the digest
+		 * verification, we can skip it
+		 */
+		if (nvme_tcp_ddp_ddgst_ok(queue))
+			goto out;
+		/*
+		 * Otherwise we have to recalculate and verify the
+		 * digest with the software-fallback
+		 */
+		nvme_tcp_ddp_ddgst_recalc(queue->rcv_hash, rq,
+					  &queue->exp_ddgst);
+	}
+
 	if (queue->recv_ddgst != queue->exp_ddgst) {
-		struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
-					pdu->command_id);
 		struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 
 		req->status = cpu_to_le16(NVME_SC_DATA_XFER_ERROR);
@@ -1168,9 +1281,8 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
 			le32_to_cpu(queue->exp_ddgst));
 	}
 
+out:
 	if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
-		struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
-					pdu->command_id);
 		struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 
 		nvme_tcp_end_request(rq, le16_to_cpu(req->status));
@@ -1981,7 +2093,8 @@ static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue)
 	kernel_sock_shutdown(queue->sock, SHUT_RDWR);
 	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);
 }
 
@@ -2011,7 +2124,8 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx)
 			goto err;
 
 		netdev = ctrl->queues[idx].ctrl->offloading_netdev;
-		if (netdev && is_netdev_ulp_offload_active(netdev)) {
+		if (netdev &&
+		    is_netdev_ulp_offload_active(netdev, &ctrl->queues[idx])) {
 			ret = nvme_tcp_offload_socket(&ctrl->queues[idx]);
 			if (ret) {
 				dev_err(nctrl->device,
@@ -2030,7 +2144,7 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx)
 			ctrl->offloading_netdev = NULL;
 			goto done;
 		}
-		if (is_netdev_ulp_offload_active(netdev))
+		if (is_netdev_ulp_offload_active(netdev, &ctrl->queues[idx]))
 			nvme_tcp_offload_limits(&ctrl->queues[idx], netdev);
 		/*
 		 * release the device as no offload context is
-- 
2.31.1


  parent reply	other threads:[~2023-01-26 16:23 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-01-26 16:21 [PATCH v10 00/25] nvme-tcp receive offloads Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 01/25] net: Introduce direct data placement tcp offload Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 02/25] net/ethtool: add new stringset ETH_SS_ULP_DDP_{CAPS,STATS} Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 03/25] net/ethtool: add ULP_DDP_{GET,SET} operations for caps and stats Aurelien Aptel
2023-02-01  4:53   ` Jakub Kicinski
2023-02-01 19:18     ` Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 04/25] Documentation: document netlink ULP_DDP_GET/SET messages Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 05/25] iov_iter: skip copy if src == dst for direct data placement Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 06/25] net/tls,core: export get_netdev_for_sock Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 07/25] nvme-tcp: Add DDP offload control path Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 08/25] nvme-tcp: Add DDP data-path Aurelien Aptel
2023-01-26 16:21 ` Aurelien Aptel [this message]
2023-01-26 16:21 ` [PATCH v10 10/25] nvme-tcp: Deal with netdevice DOWN events Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 11/25] nvme-tcp: Add modparam to control the ULP offload enablement Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 12/25] Documentation: add ULP DDP offload documentation Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 13/25] net/mlx5e: Rename from tls to transport static params Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 14/25] net/mlx5e: Refactor ico sq polling to get budget Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 15/25] net/mlx5e: Have mdev pointer directly on the icosq structure Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 16/25] net/mlx5e: Refactor doorbell function to allow avoiding a completion Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 17/25] net/mlx5: Add NVMEoTCP caps, HW bits, 128B CQE and enumerations Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 18/25] net/mlx5e: NVMEoTCP, offload initialization Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 19/25] net/mlx5e: TCP flow steering for nvme-tcp acceleration Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 20/25] net/mlx5e: NVMEoTCP, use KLM UMRs for buffer registration Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 21/25] net/mlx5e: NVMEoTCP, queue init/teardown Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 22/25] net/mlx5e: NVMEoTCP, ddp setup and resync Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 23/25] net/mlx5e: NVMEoTCP, async ddp invalidation Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 24/25] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload Aurelien Aptel
2023-01-26 16:21 ` [PATCH v10 25/25] net/mlx5e: NVMEoTCP, statistics Aurelien Aptel
2023-01-30  6:45 ` [PATCH v10 00/25] nvme-tcp receive offloads Christoph Hellwig
2023-02-06  5:12   ` Chaitanya Kulkarni

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=20230126162136.13003-10-aaptel@nvidia.com \
    --to=aaptel@nvidia.com \
    --cc=aurelien.aptel@gmail.com \
    --cc=axboe@fb.com \
    --cc=borisp@nvidia.com \
    --cc=chaitanyak@nvidia.com \
    --cc=davem@davemloft.net \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=kuba@kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=malin1024@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=ogerlitz@nvidia.com \
    --cc=sagi@grimberg.me \
    --cc=smalin@nvidia.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.