[PATCH v5 net-next 05/36] nvme-tcp: Add DDP offload control path

[Boris Pismenny <borisp@nvidia.com>]

From: Boris Pismenny <borisp@mellanox.com>

This commit introduces direct data placement offload to NVME
TCP. There is a context per queue, which is established after the
handshake using the ulp_ddp_sk_add/del NDOs.

Additionally, a resynchronization routine is used to assist
hardware recovery from TCP OOO, and continue the offload.
Resynchronization operates as follows:

1. TCP OOO causes the NIC HW to stop the offload

2. NIC HW identifies a PDU header at some TCP sequence number,
and asks NVMe-TCP to confirm it.
This request is delivered from the NIC driver to NVMe-TCP by first
finding the socket for the packet that triggered the request, and
then finding the nvme_tcp_queue that is used by this routine.
Finally, the request is recorded in the nvme_tcp_queue.

3. When NVMe-TCP observes the requested TCP sequence, it will compare
it with the PDU header TCP sequence, and report the result to the
NIC driver (ulp_ddp_resync), which will update the HW,
and resume offload when all is successful.

Furthermore, we let the offloading driver advertise what is the max hw
sectors/segments via ulp_ddp_limits.

A follow-up patch introduces the data-path changes required for this
offload.

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 | 180 +++++++++++++++++++++++++++++++++++++++-
 include/linux/skbuff.h  |   4 +-
 net/core/datagram.c     |   4 +-
 3 files changed, 182 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index c7bd37103cf4..f1a5520cabec 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -14,6 +14,7 @@
 #include <linux/blk-mq.h>
 #include <crypto/hash.h>
 #include <net/busy_poll.h>
+#include <net/ulp_ddp.h>
 
 #include "nvme.h"
 #include "fabrics.h"
@@ -62,6 +63,7 @@ enum nvme_tcp_queue_flags {
 	NVME_TCP_Q_ALLOCATED	= 0,
 	NVME_TCP_Q_LIVE		= 1,
 	NVME_TCP_Q_POLLING	= 2,
+	NVME_TCP_Q_OFF_DDP	= 3,
 };
 
 enum nvme_tcp_recv_state {
@@ -111,6 +113,8 @@ struct nvme_tcp_queue {
 	void (*state_change)(struct sock *);
 	void (*data_ready)(struct sock *);
 	void (*write_space)(struct sock *);
+
+	atomic64_t  resync_req;
 };
 
 struct nvme_tcp_ctrl {
@@ -130,6 +134,8 @@ struct nvme_tcp_ctrl {
 	struct delayed_work	connect_work;
 	struct nvme_tcp_request async_req;
 	u32			io_queues[HCTX_MAX_TYPES];
+
+	struct net_device       *offloading_netdev;
 };
 
 static LIST_HEAD(nvme_tcp_ctrl_list);
@@ -219,6 +225,167 @@ static inline size_t nvme_tcp_pdu_last_send(struct nvme_tcp_request *req,
 	return nvme_tcp_pdu_data_left(req) <= len;
 }
 
+#ifdef CONFIG_ULP_DDP
+
+static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags);
+static const struct ulp_ddp_ulp_ops nvme_tcp_ddp_ulp_ops = {
+	.resync_request		= nvme_tcp_resync_request,
+};
+
+static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
+{
+	struct net_device *netdev = queue->ctrl->offloading_netdev;
+	struct nvme_tcp_ddp_config config = {};
+	int ret;
+
+	if (!netdev || !(netdev->features & NETIF_F_HW_ULP_DDP))
+		return -EOPNOTSUPP;
+
+	config.cfg.type		= ULP_DDP_NVME;
+	config.pfv		= NVME_TCP_PFV_1_0;
+	config.cpda		= 0;
+	config.dgst		= queue->hdr_digest ?
+		NVME_TCP_HDR_DIGEST_ENABLE : 0;
+	config.dgst		|= queue->data_digest ?
+		NVME_TCP_DATA_DIGEST_ENABLE : 0;
+	config.queue_size	= queue->queue_size;
+	config.queue_id		= nvme_tcp_queue_id(queue);
+	config.io_cpu		= queue->io_cpu;
+
+	dev_hold(netdev); /* put by unoffload_socket */
+	ret = netdev->ulp_ddp_ops->ulp_ddp_sk_add(netdev,
+						  queue->sock->sk,
+						  &config.cfg);
+	if (ret) {
+		dev_put(netdev);
+		return ret;
+	}
+
+	inet_csk(queue->sock->sk)->icsk_ulp_ddp_ops = &nvme_tcp_ddp_ulp_ops;
+	if (netdev->features & NETIF_F_HW_ULP_DDP)
+		set_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
+
+	return ret;
+}
+
+static void nvme_tcp_unoffload_socket(struct nvme_tcp_queue *queue)
+{
+	struct net_device *netdev = queue->ctrl->offloading_netdev;
+
+	if (!netdev) {
+		dev_info_ratelimited(queue->ctrl->ctrl.device, "netdev not found\n");
+		return;
+	}
+
+	clear_bit(NVME_TCP_Q_OFF_DDP, &queue->flags);
+
+	netdev->ulp_ddp_ops->ulp_ddp_sk_del(netdev, queue->sock->sk);
+
+	inet_csk(queue->sock->sk)->icsk_ulp_ddp_ops = NULL;
+	dev_put(netdev); /* held by offload_socket */
+}
+
+static int nvme_tcp_offload_limits(struct nvme_tcp_queue *queue)
+{
+	struct net_device *netdev = get_netdev_for_sock(queue->sock->sk, true);
+	struct ulp_ddp_limits limits;
+	int ret = 0;
+
+	if (!netdev) {
+		dev_info_ratelimited(queue->ctrl->ctrl.device, "netdev not found\n");
+		queue->ctrl->offloading_netdev = NULL;
+		return -ENODEV;
+	}
+
+	if ((netdev->features & NETIF_F_HW_ULP_DDP) &&
+	    netdev->ulp_ddp_ops &&
+	    netdev->ulp_ddp_ops->ulp_ddp_limits)
+		ret = netdev->ulp_ddp_ops->ulp_ddp_limits(netdev, &limits);
+	else
+		ret = -EOPNOTSUPP;
+
+	if (!ret) {
+		queue->ctrl->offloading_netdev = netdev;
+		dev_dbg_ratelimited(queue->ctrl->ctrl.device,
+				    "netdev %s offload limits: max_ddp_sgl_len %d\n",
+				    netdev->name, limits.max_ddp_sgl_len);
+		queue->ctrl->ctrl.max_segments = limits.max_ddp_sgl_len;
+		queue->ctrl->ctrl.max_hw_sectors =
+			limits.max_ddp_sgl_len << (ilog2(SZ_4K) - 9);
+	} else {
+		queue->ctrl->offloading_netdev = NULL;
+	}
+
+	/* release the device as no offload context is established yet. */
+	dev_put(netdev);
+
+	return ret;
+}
+
+static void nvme_tcp_resync_response(struct nvme_tcp_queue *queue,
+				     struct sk_buff *skb, unsigned int offset)
+{
+	u64 pdu_seq = TCP_SKB_CB(skb)->seq + offset - queue->pdu_offset;
+	struct net_device *netdev = queue->ctrl->offloading_netdev;
+	u64 pdu_val = (pdu_seq << 32) | ULP_DDP_RESYNC_REQ;
+	u64 resync_val;
+	u32 resync_seq;
+
+	resync_val = atomic64_read(&queue->resync_req);
+	/* Lower 32 bit flags. Check validity of the request */
+	if ((resync_val & ULP_DDP_RESYNC_REQ) == 0)
+		return;
+
+	/* Obtain and check requested sequence number: is this PDU header before the request? */
+	resync_seq = resync_val >> 32;
+	if (before(pdu_seq, resync_seq))
+		return;
+
+	if (unlikely(!netdev)) {
+		pr_info_ratelimited("%s: netdev not found\n", __func__);
+		return;
+	}
+
+	/**
+	 * The atomic operation gurarantees that we don't miss any NIC driver
+	 * resync requests submitted after the above checks.
+	 */
+	if (atomic64_cmpxchg(&queue->resync_req, pdu_val,
+			     pdu_val & ~ULP_DDP_RESYNC_REQ) != atomic64_read(&queue->resync_req))
+		netdev->ulp_ddp_ops->ulp_ddp_resync(netdev, queue->sock->sk, pdu_seq);
+}
+
+static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags)
+{
+	struct nvme_tcp_queue *queue = sk->sk_user_data;
+
+	atomic64_set(&queue->resync_req,
+		     (((uint64_t)seq << 32) | flags));
+
+	return true;
+}
+
+#else
+
+static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
+{
+	return -EINVAL;
+}
+
+static void nvme_tcp_unoffload_socket(struct nvme_tcp_queue *queue)
+{}
+
+static int nvme_tcp_offload_limits(struct nvme_tcp_queue *queue)
+{
+	return -EINVAL;
+}
+
+static void nvme_tcp_resync_response(struct nvme_tcp_queue *queue,
+				     struct sk_buff *skb, unsigned int offset)
+{}
+
+#endif
+
 static void nvme_tcp_init_iter(struct nvme_tcp_request *req,
 		unsigned int dir)
 {
@@ -649,6 +816,9 @@ 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))
+		nvme_tcp_resync_response(queue, skb, *offset);
+
 	ret = skb_copy_bits(skb, *offset,
 		&pdu[queue->pdu_offset], rcv_len);
 	if (unlikely(ret))
@@ -1555,6 +1725,9 @@ 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))
+		nvme_tcp_unoffload_socket(queue);
 }
 
 static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
@@ -1573,10 +1746,13 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx)
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	int ret;
 
-	if (idx)
+	if (idx) {
 		ret = nvmf_connect_io_queue(nctrl, idx, false);
-	else
+		nvme_tcp_offload_socket(&ctrl->queues[idx]);
+	} else {
 		ret = nvmf_connect_admin_queue(nctrl);
+		nvme_tcp_offload_limits(&ctrl->queues[idx]);
+	}
 
 	if (!ret) {
 		set_bit(NVME_TCP_Q_LIVE, &ctrl->queues[idx].flags);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 8c1bfd7081d1..55dc858ff349 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3613,7 +3613,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
 			   struct poll_table_struct *wait);
 int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
 			   struct iov_iter *to, int size);
-#ifdef CONFIG_TCP_DDP
+#ifdef CONFIG_ULP_DDP
 int skb_ddp_copy_datagram_iter(const struct sk_buff *from, int offset,
 			       struct iov_iter *to, int size);
 #endif
@@ -3627,7 +3627,7 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen,
 int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset,
 			   struct iov_iter *to, int len,
 			   struct ahash_request *hash);
-#ifdef CONFIG_TCP_DDP
+#ifdef CONFIG_ULP_DDP
 int skb_ddp_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset,
 					struct iov_iter *to, int len,
 					struct ahash_request *hash);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index d346fd5da22c..5ad5fb22d3f8 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -495,7 +495,7 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset,
 	return 0;
 }
 
-#ifdef CONFIG_TCP_DDP
+#ifdef CONFIG_ULP_DDP
 /**
  *	skb_ddp_copy_and_hash_datagram_iter - Copies datagrams from skb frags to
  *	an iterator and update a hash. If the iterator and skb frag point to the
@@ -534,7 +534,7 @@ int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset,
 }
 EXPORT_SYMBOL(skb_copy_and_hash_datagram_iter);
 
-#ifdef CONFIG_TCP_DDP
+#ifdef CONFIG_ULP_DDP
 static size_t simple_ddp_copy_to_iter(const void *addr, size_t bytes,
 				      void *data __always_unused,
 				      struct iov_iter *i)
-- 
2.24.1