[PATCH v5 net-next 00/36] nvme-tcp receive and tarnsmit offloads

@@ -14,7 +14,7 @@ typedef u64 netdev_features_t;
 enum {
 	NETIF_F_SG_BIT,			/* Scatter/gather IO. */
 	NETIF_F_IP_CSUM_BIT,		/* Can checksum TCP/UDP over IPv4. */
-	__UNUSED_NETIF_F_1,
+	NETIF_F_HW_ULP_DDP_BIT,         /* ULP direct data placement offload */
 	NETIF_F_HW_CSUM_BIT,		/* Can checksum all the packets. */
 	NETIF_F_IPV6_CSUM_BIT,		/* Can checksum TCP/UDP over IPV6 */
 	NETIF_F_HIGHDMA_BIT,		/* Can DMA to high memory. */

@@ -168,6 +168,7 @@ enum {
 #define NETIF_F_HW_HSR_TAG_RM	__NETIF_F(HW_HSR_TAG_RM)
 #define NETIF_F_HW_HSR_FWD	__NETIF_F(HW_HSR_FWD)
 #define NETIF_F_HW_HSR_DUP	__NETIF_F(HW_HSR_DUP)
+#define NETIF_F_HW_ULP_DDP	__NETIF_F(HW_ULP_DDP)
 
 /* Finds the next feature with the highest number of the range of start till 0.
  */

@@ -1005,6 +1005,7 @@ struct dev_ifalias {
 
 struct devlink;
 struct tlsdev_ops;
+struct ulp_ddp_dev_ops;
 
 struct netdev_name_node {
 	struct hlist_node hlist;

@@ -2024,6 +2025,10 @@ struct net_device {
 	const struct tlsdev_ops *tlsdev_ops;
 #endif
 
+#if IS_ENABLED(CONFIG_ULP_DDP)
+	const struct ulp_ddp_dev_ops *ulp_ddp_ops;
+#endif
+
 	const struct header_ops *header_ops;
 
 	unsigned char		operstate;

@@ -689,6 +689,7 @@ typedef unsigned char *sk_buff_data_t;
  *		CHECKSUM_UNNECESSARY (max 3)
  *	@dst_pending_confirm: need to confirm neighbour
  *	@decrypted: Decrypted SKB
+ *	@ddp_crc: DDP or CRC offloaded
  *	@napi_id: id of the NAPI struct this skb came from
  *	@sender_cpu: (aka @napi_id) source CPU in XPS
  *	@secmark: security marking

@@ -870,6 +871,9 @@ struct sk_buff {
 #ifdef CONFIG_TLS_DEVICE
 	__u8			decrypted:1;
 #endif
+#ifdef CONFIG_ULP_DDP
+	__u8                    ddp_crc:1;
+#endif
 
 #ifdef CONFIG_NET_SCHED
 	__u16			tc_index;	/* traffic control index */

@@ -66,6 +66,8 @@ struct inet_connection_sock_af_ops {
  * @icsk_ulp_ops	   Pluggable ULP control hook
  * @icsk_ulp_data	   ULP private data
  * @icsk_clean_acked	   Clean acked data hook
+ * @icsk_ulp_ddp_ops	   Pluggable ULP direct data placement control hook
+ * @icsk_ulp_ddp_data	   ULP direct data placement private data
  * @icsk_listen_portaddr_node	hash to the portaddr listener hashtable
  * @icsk_ca_state:	   Congestion control state
  * @icsk_retransmits:	   Number of unrecovered [RTO] timeouts

@@ -96,6 +98,8 @@ struct inet_connection_sock {
 	const struct tcp_ulp_ops  *icsk_ulp_ops;
 	void __rcu		  *icsk_ulp_data;
 	void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
+	const struct ulp_ddp_ulp_ops  *icsk_ulp_ddp_ops;
+	void __rcu		  *icsk_ulp_ddp_data;
 	struct hlist_node         icsk_listen_portaddr_node;
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
 	__u8			  icsk_ca_state:5,

@@ -0,0 +1,136 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * ulp_ddp.h
+ *	Author:	Boris Pismenny <borisp@mellanox.com>
+ *	Copyright (C) 2021 Mellanox Technologies.
+ */
+#ifndef _ULP_DDP_H
+#define _ULP_DDP_H
+
+#include <linux/netdevice.h>
+#include <net/inet_connection_sock.h>
+#include <net/sock.h>
+
+/* limits returned by the offload driver, zero means don't care */
+struct ulp_ddp_limits {
+	int	 max_ddp_sgl_len;
+};
+
+enum ulp_ddp_type {
+	ULP_DDP_NVME = 1,
+};
+
+/**
+ * struct ulp_ddp_config - Generic ulp ddp configuration: tcp ddp IO queue
+ * config implementations must use this as the first member.
+ * Add new instances of ulp_ddp_config below (nvme-tcp, etc.).
+ */
+struct ulp_ddp_config {
+	enum ulp_ddp_type    type;
+	unsigned char        buf[];
+};
+
+/**
+ * struct nvme_tcp_ddp_config - nvme tcp ddp configuration for an IO queue
+ *
+ * @pfv:        pdu version (e.g., NVME_TCP_PFV_1_0)
+ * @cpda:       controller pdu data alignmend (dwords, 0's based)
+ * @dgst:       digest types enabled.
+ *              The netdev will offload crc if ddp_crc is supported.
+ * @queue_size: number of nvme-tcp IO queue elements
+ * @queue_id:   queue identifier
+ * @cpu_io:     cpu core running the IO thread for this queue
+ */
+struct nvme_tcp_ddp_config {
+	struct ulp_ddp_config   cfg;
+
+	u16			pfv;
+	u8			cpda;
+	u8			dgst;
+	int			queue_size;
+	int			queue_id;
+	int			io_cpu;
+};
+
+/**
+ * struct ulp_ddp_io - ulp ddp configuration for an IO request.
+ *
+ * @command_id:  identifier on the wire associated with these buffers
+ * @nents:       number of entries in the sg_table
+ * @sg_table:    describing the buffers for this IO request
+ * @first_sgl:   first SGL in sg_table
+ */
+struct ulp_ddp_io {
+	u32			command_id;
+	int			nents;
+	struct sg_table		sg_table;
+	struct scatterlist	first_sgl[SG_CHUNK_SIZE];
+};
+
+/* struct ulp_ddp_dev_ops - operations used by an upper layer protocol to configure ddp offload
+ *
+ * @ulp_ddp_limits:    limit the number of scatter gather entries per IO.
+ *                     the device driver can use this to limit the resources allocated per queue.
+ * @ulp_ddp_sk_add:    add offload for the queue represennted by the socket+config pair.
+ *                     this function is used to configure either copy, crc or both offloads.
+ * @ulp_ddp_sk_del:    remove offload from the socket, and release any device related resources.
+ * @ulp_ddp_setup:     request copy offload for buffers associated with a command_id in ulp_ddp_io.
+ * @ulp_ddp_teardown:  release offload resources association between buffers and command_id in
+ *                     ulp_ddp_io.
+ * @ulp_ddp_resync:    respond to the driver's resync_request. Called only if resync is successful.
+ */
+struct ulp_ddp_dev_ops {
+	int (*ulp_ddp_limits)(struct net_device *netdev,
+			      struct ulp_ddp_limits *limits);
+	int (*ulp_ddp_sk_add)(struct net_device *netdev,
+			      struct sock *sk,
+			      struct ulp_ddp_config *config);
+	void (*ulp_ddp_sk_del)(struct net_device *netdev,
+			       struct sock *sk);
+	int (*ulp_ddp_setup)(struct net_device *netdev,
+			     struct sock *sk,
+			     struct ulp_ddp_io *io);
+	int (*ulp_ddp_teardown)(struct net_device *netdev,
+				struct sock *sk,
+				struct ulp_ddp_io *io,
+				void *ddp_ctx);
+	void (*ulp_ddp_resync)(struct net_device *netdev,
+			       struct sock *sk, u32 seq);
+};
+
+#define ULP_DDP_RESYNC_REQ BIT(0)
+
+/**
+ * struct ulp_ddp_ulp_ops - Interface to register uppper layer Direct Data Placement (DDP) TCP offload
+ */
+struct ulp_ddp_ulp_ops {
+	/* NIC requests ulp to indicate if @seq is the start of a message */
+	bool (*resync_request)(struct sock *sk, u32 seq, u32 flags);
+	/* NIC driver informs the ulp that ddp teardown is done - used for async completions*/
+	void (*ddp_teardown_done)(void *ddp_ctx);
+};
+
+/**
+ * struct ulp_ddp_ctx - Generic ulp ddp context: device driver per queue contexts must
+ * use this as the first member.
+ */
+struct ulp_ddp_ctx {
+	enum ulp_ddp_type    type;
+	unsigned char        buf[];
+};
+
+static inline struct ulp_ddp_ctx *ulp_ddp_get_ctx(const struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	return (__force struct ulp_ddp_ctx *)icsk->icsk_ulp_ddp_data;
+}
+
+static inline void ulp_ddp_set_ctx(struct sock *sk, void *ctx)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	rcu_assign_pointer(icsk->icsk_ulp_ddp_data, ctx);
+}
+
+#endif //_ULP_DDP_H

@@ -454,4 +454,14 @@ config ETHTOOL_NETLINK
 	  netlink. It provides better extensibility and some new features,
 	  e.g. notification messages.
 
+config ULP_DDP
+	bool "ULP direct data placement offload"
+	default n
+	help
+	  Direct Data Placement (DDP) offload enables ULP, such as
+	  NVMe-TCP/iSCSI, to request the NIC to place ULP payload data
+	  of a command response directly into kernel pages while
+	  calculate/verify the data digest on ULP PDU as they go through
+	  the NIC. Thus avoiding the costly per-byte overhead.
+
 endif   # if NET

@@ -71,6 +71,7 @@
 #include <net/mpls.h>
 #include <net/mptcp.h>
 #include <net/page_pool.h>
+#include <net/ulp_ddp.h>
 
 #include <linux/uaccess.h>
 #include <trace/events/skb.h>

@@ -6295,9 +6296,14 @@ EXPORT_SYMBOL(pskb_extract);
  */
 void skb_condense(struct sk_buff *skb)
 {
+	bool is_ddp = false;
+
+#ifdef CONFIG_ULP_DDP
+	is_ddp = skb->ddp_crc;
+#endif
 	if (skb->data_len) {
 		if (skb->data_len > skb->end - skb->tail ||
-		    skb_cloned(skb))
+		    skb_cloned(skb) || is_ddp)
 			return;
 
 		/* Nice, we can free page frag(s) right now */

@@ -73,6 +73,7 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
 	[NETIF_F_HW_HSR_TAG_RM_BIT] =	 "hsr-tag-rm-offload",
 	[NETIF_F_HW_HSR_FWD_BIT] =	 "hsr-fwd-offload",
 	[NETIF_F_HW_HSR_DUP_BIT] =	 "hsr-dup-offload",
+	[NETIF_F_HW_ULP_DDP_BIT] =	 "ulp-ddp-offload",
 };
 
 const char

@@ -5149,6 +5149,9 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
 		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
 #ifdef CONFIG_TLS_DEVICE
 		nskb->decrypted = skb->decrypted;
+#endif
+#ifdef CONFIG_ULP_DDP
+		nskb->ddp_crc = skb->ddp_crc;
 #endif
 		TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
 		if (list)

@@ -5182,6 +5185,11 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
 #ifdef CONFIG_TLS_DEVICE
 				if (skb->decrypted != nskb->decrypted)
 					goto end;
+#endif
+#ifdef CONFIG_ULP_DDP
+
+				if (skb->ddp_crc != nskb->ddp_crc)
+					goto end;
 #endif
 			}
 		}

@@ -1830,6 +1830,9 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	      TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) ||
 #ifdef CONFIG_TLS_DEVICE
 	    tail->decrypted != skb->decrypted ||
+#endif
+#ifdef CONFIG_ULP_DDP
+	    tail->ddp_crc != skb->ddp_crc ||
 #endif
 	    thtail->doff != th->doff ||
 	    memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th)))

@@ -262,6 +262,9 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
 #ifdef CONFIG_TLS_DEVICE
 	flush |= p->decrypted ^ skb->decrypted;
 #endif
+#ifdef CONFIG_ULP_DDP
+	flush |= p->ddp_crc ^ skb->ddp_crc;
+#endif
 
 	if (flush || skb_gro_receive(p, skb)) {
 		mss = 1;

@@ -131,6 +131,9 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
 
 size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
+#ifdef CONFIG_ULP_DDP
+size_t _ddp_copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
+#endif
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
 bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i);
 size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i);

@@ -145,6 +148,16 @@ size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 		return _copy_to_iter(addr, bytes, i);
 }
 
+#ifdef CONFIG_ULP_DDP
+static __always_inline __must_check
+size_t ddp_copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
+{
+	if (unlikely(!check_copy_size(addr, bytes, true)))
+		return 0;
+	return _ddp_copy_to_iter(addr, bytes, i);
+}
+#endif
+
 static __always_inline __must_check
 size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {

@@ -281,6 +294,10 @@ size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct io
 bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
 		struct iov_iter *i);
+#ifdef CONFIG_ULP_DDP
+size_t ddp_hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
+		struct iov_iter *i);
+#endif
 
 struct iovec *iovec_from_user(const struct iovec __user *uvector,
 		unsigned long nr_segs, unsigned long fast_segs,

@@ -508,6 +508,18 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction,
 }
 EXPORT_SYMBOL(iov_iter_init);
 
+#ifdef CONFIG_ULP_DDP
+static void ddp_memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len)
+{
+	char *to = kmap_atomic(page);
+
+	if (to + offset != from)
+		memcpy(to + offset, from, len);
+
+	kunmap_atomic(to);
+}
+#endif
+
 static inline bool allocated(struct pipe_buffer *buf)
 {
 	return buf->ops == &default_pipe_buf_ops;

@@ -648,6 +660,28 @@ static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes,
 	return bytes;
 }
 
+#ifdef CONFIG_ULP_DDP
+size_t _ddp_copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
+{
+	const char *from = addr;
+	if (unlikely(iov_iter_is_pipe(i)))
+		return copy_pipe_to_iter(addr, bytes, i);
+	if (iter_is_iovec(i))
+		might_fault();
+	iterate_and_advance(i, bytes, v,
+		copyout(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
+		ddp_memcpy_to_page(v.bv_page, v.bv_offset,
+				   (from += v.bv_len) - v.bv_len, v.bv_len),
+		memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
+		ddp_memcpy_to_page(v.bv_page, v.bv_offset,
+				   (from += v.bv_len) - v.bv_len, v.bv_len)
+		)
+
+	return bytes;
+}
+EXPORT_SYMBOL(_ddp_copy_to_iter);
+#endif
+
 size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	const char *from = addr;

@@ -1818,6 +1852,27 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate,
 }
 EXPORT_SYMBOL(csum_and_copy_to_iter);
 
+#ifdef CONFIG_ULP_DDP
+size_t ddp_hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
+		struct iov_iter *i)
+{
+#ifdef CONFIG_CRYPTO_HASH
+	struct ahash_request *hash = hashp;
+	struct scatterlist sg;
+	size_t copied;
+
+	copied = ddp_copy_to_iter(addr, bytes, i);
+	sg_init_one(&sg, addr, copied);
+	ahash_request_set_crypt(hash, &sg, NULL, copied);
+	crypto_ahash_update(hash);
+	return copied;
+#else
+	return 0;
+#endif
+}
+EXPORT_SYMBOL(ddp_hash_and_copy_to_iter);
+#endif
+
 size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
 		struct iov_iter *i)
 {

@@ -3613,6 +3613,10 @@ __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
+int skb_ddp_copy_datagram_iter(const struct sk_buff *from, int offset,
+			       struct iov_iter *to, int size);
+#endif
 static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
 					struct msghdr *msg, int size)
 {

@@ -3623,6 +3627,11 @@ 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
+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);
+#endif
 int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 				 struct iov_iter *from, int len);
 int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm);

@@ -495,6 +495,27 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset,
 	return 0;
 }
 
+#ifdef CONFIG_TCP_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
+ *	same page and offset, then the copy is skipped.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: iovec iterator to copy to
+ *	@len: amount of data to copy from buffer to iovec
+ *      @hash: hash request to update
+ */
+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)
+{
+	return __skb_datagram_iter(skb, offset, to, len, true,
+			ddp_hash_and_copy_to_iter, hash);
+}
+EXPORT_SYMBOL(skb_ddp_copy_and_hash_datagram_iter);
+#endif
+
 /**
  *	skb_copy_and_hash_datagram_iter - Copy datagram to an iovec iterator
  *          and update a hash.

@@ -513,6 +534,33 @@ 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
+static size_t simple_ddp_copy_to_iter(const void *addr, size_t bytes,
+				      void *data __always_unused,
+				      struct iov_iter *i)
+{
+	return ddp_copy_to_iter(addr, bytes, i);
+}
+
+/**
+ *	skb_ddp_copy_datagram_iter - Copies datagrams from skb frags to an
+ *	iterator. If the iterator and skb frag point to the same page and
+ *	offset, then the copy is skipped.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: iovec iterator to copy to
+ *	@len: amount of data to copy from buffer to iovec
+ */
+int skb_ddp_copy_datagram_iter(const struct sk_buff *skb, int offset,
+			       struct iov_iter *to, int len)
+{
+	trace_skb_copy_datagram_iovec(skb, len);
+	return __skb_datagram_iter(skb, offset, to, len, false,
+			simple_ddp_copy_to_iter, NULL);
+}
+EXPORT_SYMBOL(skb_ddp_copy_datagram_iter);
+#endif
+
 static size_t simple_copy_to_iter(const void *addr, size_t bytes,
 		void *data __always_unused, struct iov_iter *i)
 {

@@ -2769,4 +2769,21 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs);
 
 int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len);
 
+/* Assume that the socket is already connected */
+static inline struct net_device *get_netdev_for_sock(struct sock *sk, bool hold)
+{
+	struct dst_entry *dst = sk_dst_get(sk);
+	struct net_device *netdev = NULL;
+
+	if (likely(dst)) {
+		netdev = dst->dev;
+		if (hold)
+			dev_hold(netdev);
+	}
+
+	dst_release(dst);
+
+	return netdev;
+}
+
 #endif	/* _SOCK_H */

@@ -107,22 +107,6 @@ static void tls_device_queue_ctx_destruction(struct tls_context *ctx)
 	spin_unlock_irqrestore(&tls_device_lock, flags);
 }
 
-/* We assume that the socket is already connected */
-static struct net_device *get_netdev_for_sock(struct sock *sk)
-{
-	struct dst_entry *dst = sk_dst_get(sk);
-	struct net_device *netdev = NULL;
-
-	if (likely(dst)) {
-		netdev = netdev_sk_get_lowest_dev(dst->dev, sk);
-		dev_hold(netdev);
-	}
-
-	dst_release(dst);
-
-	return netdev;
-}
-
 static void destroy_record(struct tls_record_info *record)
 {
 	int i;

@@ -1118,7 +1102,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 	if (skb)
 		TCP_SKB_CB(skb)->eor = 1;
 
-	netdev = get_netdev_for_sock(sk);
+	netdev = get_netdev_for_sock(sk, true);
 	if (!netdev) {
 		pr_err_ratelimited("%s: netdev not found\n", __func__);
 		rc = -EINVAL;

@@ -1194,7 +1178,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
 	if (ctx->crypto_recv.info.version != TLS_1_2_VERSION)
 		return -EOPNOTSUPP;
 
-	netdev = get_netdev_for_sock(sk);
+	netdev = get_netdev_for_sock(sk, true);
 	if (!netdev) {
 		pr_err_ratelimited("%s: netdev not found\n", __func__);
 		return -EINVAL;

@@ -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);

@@ -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);

@@ -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)

@@ -57,6 +57,11 @@ struct nvme_tcp_request {
 	size_t			offset;
 	size_t			data_sent;
 	enum nvme_tcp_send_state state;
+
+	bool			offloaded;
+	struct ulp_ddp_io	ddp;
+	__le16			status;
+	union nvme_result	result;
 };
 
 enum nvme_tcp_queue_flags {

@@ -225,13 +230,76 @@ static inline size_t nvme_tcp_pdu_last_send(struct nvme_tcp_request *req,
 	return nvme_tcp_pdu_data_left(req) <= len;
 }
 
+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;
+}
+
 #ifdef CONFIG_ULP_DDP
 
 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 = {
 	.resync_request		= nvme_tcp_resync_request,
+	.ddp_teardown_done	= nvme_tcp_ddp_teardown_done,
 };
 
+static int nvme_tcp_teardown_ddp(struct nvme_tcp_queue *queue,
+				 u16 command_id,
+				 struct request *rq)
+{
+	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+	struct net_device *netdev = queue->ctrl->offloading_netdev;
+	int ret;
+
+	ret = netdev->ulp_ddp_ops->ulp_ddp_teardown(netdev, queue->sock->sk,
+						    &req->ddp, rq);
+	sg_free_table_chained(&req->ddp.sg_table, SG_CHUNK_SIZE);
+	return ret;
+}
+
+static void nvme_tcp_ddp_teardown_done(void *ddp_ctx)
+{
+	struct request *rq = ddp_ctx;
+	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+
+	if (!nvme_try_complete_req(rq, req->status, req->result))
+		nvme_complete_rq(rq);
+}
+
+static int nvme_tcp_setup_ddp(struct nvme_tcp_queue *queue,
+			      u16 command_id,
+			      struct request *rq)
+{
+	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+	struct net_device *netdev = queue->ctrl->offloading_netdev;
+	int ret;
+
+	if (!test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags) ||
+	    !blk_rq_nr_phys_segments(rq) || !(rq_data_dir(rq) == READ))
+		return -EINVAL;
+
+	req->ddp.command_id = command_id;
+	ret = nvme_tcp_req_map_sg(req, rq);
+	if (ret)
+		return -ENOMEM;
+
+	ret = netdev->ulp_ddp_ops->ulp_ddp_setup(netdev,
+						 queue->sock->sk,
+						 &req->ddp);
+	if (!ret)
+		req->offloaded = true;
+	return ret;
+}
+
 static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
 {
 	struct net_device *netdev = queue->ctrl->offloading_netdev;