[RFC PATCH net-next v5 11/14] tcp: RX path for devmem TCP

[Mina Almasry <almasrymina@google.com>]

In tcp_recvmsg_locked(), detect if the skb being received by the user
is a devmem skb. In this case - if the user provided the MSG_SOCK_DEVMEM
flag - pass it to tcp_recvmsg_devmem() for custom handling.

tcp_recvmsg_devmem() copies any data in the skb header to the linear
buffer, and returns a cmsg to the user indicating the number of bytes
returned in the linear buffer.

tcp_recvmsg_devmem() then loops over the unaccessible devmem skb frags,
and returns to the user a cmsg_devmem indicating the location of the
data in the dmabuf device memory. cmsg_devmem contains this information:

1. the offset into the dmabuf where the payload starts. 'frag_offset'.
2. the size of the frag. 'frag_size'.
3. an opaque token 'frag_token' to return to the kernel when the buffer
is to be released.

The pages awaiting freeing are stored in the newly added
sk->sk_user_frags, and each page passed to userspace is get_page()'d.
This reference is dropped once the userspace indicates that it is
done reading this page.  All pages are released when the socket is
destroyed.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>

---

Changes in v1:
- Added dmabuf_id to dmabuf_cmsg (David/Stan).
- Devmem -> dmabuf (David).
- Change tcp_recvmsg_dmabuf() check to skb->dmabuf (Paolo).
- Use __skb_frag_ref() & napi_pp_put_page() for refcounting (Yunsheng).

RFC v3:
- Fixed issue with put_cmsg() failing silently.

---
 include/linux/socket.h            |   1 +
 include/net/netmem.h              |  13 ++
 include/net/sock.h                |   2 +
 include/uapi/asm-generic/socket.h |   5 +
 include/uapi/linux/uio.h          |  10 ++
 net/ipv4/tcp.c                    | 190 +++++++++++++++++++++++++++++-
 net/ipv4/tcp_ipv4.c               |   9 ++
 7 files changed, 225 insertions(+), 5 deletions(-)

diff --git a/include/linux/socket.h b/include/linux/socket.h
index cfcb7e2c3813..fe2b9e2081bb 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -326,6 +326,7 @@ struct ucred {
 					  * plain text and require encryption
 					  */
 
+#define MSG_SOCK_DEVMEM 0x2000000	/* Receive devmem skbs as cmsg */
 #define MSG_ZEROCOPY	0x4000000	/* Use user data in kernel path */
 #define MSG_SPLICE_PAGES 0x8000000	/* Splice the pages from the iterator in sendmsg() */
 #define MSG_FASTOPEN	0x20000000	/* Send data in TCP SYN */
diff --git a/include/net/netmem.h b/include/net/netmem.h
index ab3824b7b789..fa6d7b7ddef9 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -64,6 +64,19 @@ static inline unsigned int net_iov_idx(const struct net_iov *niov)
 	return niov - net_iov_owner(niov)->niovs;
 }
 
+static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov)
+{
+	struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov);
+
+	return owner->base_virtual +
+	       ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT);
+}
+
+static inline u32 net_iov_binding_id(const struct net_iov *niov)
+{
+	return net_iov_owner(niov)->binding->id;
+}
+
 static inline dma_addr_t net_iov_dma_addr(const struct net_iov *niov)
 {
 	struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov);
diff --git a/include/net/sock.h b/include/net/sock.h
index 8b6fe164b218..8eccf6ed8eb1 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -353,6 +353,7 @@ struct sk_filter;
   *	@sk_txtime_unused: unused txtime flags
   *	@ns_tracker: tracker for netns reference
   *	@sk_bind2_node: bind node in the bhash2 table
+  *	@sk_user_frags: xarray of pages the user is holding a reference on.
   */
 struct sock {
 	/*
@@ -545,6 +546,7 @@ struct sock {
 	struct rcu_head		sk_rcu;
 	netns_tracker		ns_tracker;
 	struct hlist_node	sk_bind2_node;
+	struct xarray		sk_user_frags;
 };
 
 enum sk_pacing {
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 8ce8a39a1e5f..25a2f5255f52 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -135,6 +135,11 @@
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
+#define SO_DEVMEM_LINEAR	98
+#define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
+#define SO_DEVMEM_DMABUF	99
+#define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h
index 059b1a9147f4..ad92e37699da 100644
--- a/include/uapi/linux/uio.h
+++ b/include/uapi/linux/uio.h
@@ -20,6 +20,16 @@ struct iovec
 	__kernel_size_t iov_len; /* Must be size_t (1003.1g) */
 };
 
+struct dmabuf_cmsg {
+	__u64 frag_offset;	/* offset into the dmabuf where the frag starts.
+				 */
+	__u32 frag_size;	/* size of the frag. */
+	__u32 frag_token;	/* token representing this frag for
+				 * DEVMEM_DONTNEED.
+				 */
+	__u32  dmabuf_id;	/* dmabuf id this frag belongs to. */
+};
+
 /*
  *	UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1)
  */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6f4c59143156..9df4f512d841 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -461,6 +461,7 @@ void tcp_init_sock(struct sock *sk)
 
 	set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
 	sk_sockets_allocated_inc(sk);
+	xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1);
 }
 EXPORT_SYMBOL(tcp_init_sock);
 
@@ -2303,6 +2304,155 @@ static int tcp_inq_hint(struct sock *sk)
 	return inq;
 }
 
+/* On error, returns the -errno. On success, returns number of bytes sent to the
+ * user. May not consume all of @remaining_len.
+ */
+static int tcp_recvmsg_dmabuf(const struct sock *sk, const struct sk_buff *skb,
+			      unsigned int offset, struct msghdr *msg,
+			      int remaining_len)
+{
+	struct dmabuf_cmsg dmabuf_cmsg = { 0 };
+	unsigned int start;
+	int i, copy, n;
+	int sent = 0;
+	int err = 0;
+
+	do {
+		start = skb_headlen(skb);
+
+		if (!skb->dmabuf) {
+			err = -ENODEV;
+			goto out;
+		}
+
+		/* Copy header. */
+		copy = start - offset;
+		if (copy > 0) {
+			copy = min(copy, remaining_len);
+
+			n = copy_to_iter(skb->data + offset, copy,
+					 &msg->msg_iter);
+			if (n != copy) {
+				err = -EFAULT;
+				goto out;
+			}
+
+			offset += copy;
+			remaining_len -= copy;
+
+			/* First a dmabuf_cmsg for # bytes copied to user
+			 * buffer.
+			 */
+			memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg));
+			dmabuf_cmsg.frag_size = copy;
+			err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR,
+				       sizeof(dmabuf_cmsg), &dmabuf_cmsg);
+			if (err || msg->msg_flags & MSG_CTRUNC) {
+				msg->msg_flags &= ~MSG_CTRUNC;
+				if (!err)
+					err = -ETOOSMALL;
+				goto out;
+			}
+
+			sent += copy;
+
+			if (remaining_len == 0)
+				goto out;
+		}
+
+		/* after that, send information of dmabuf pages through a
+		 * sequence of cmsg
+		 */
+		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+			struct net_iov *niov;
+			u64 frag_offset;
+			u32 user_token;
+			int end;
+
+			/* skb->dmabuf should indicate that ALL the frags in
+			 * this skb are dmabuf net_iovs. We're checking
+			 * for that flag above, but also check individual frags
+			 * here. If the tcp stack is not setting skb->dmabuf
+			 * correctly, we still don't want to crash here when
+			 * accessing pgmap or priv below.
+			 */
+			if (!skb_frag_net_iov(frag)) {
+				net_err_ratelimited("Found non-dmabuf skb with net_iov");
+				err = -ENODEV;
+				goto out;
+			}
+
+			niov = skb_frag_net_iov(frag);
+			end = start + skb_frag_size(frag);
+			copy = end - offset;
+
+			if (copy > 0) {
+				copy = min(copy, remaining_len);
+
+				frag_offset = net_iov_virtual_addr(niov) +
+					      skb_frag_off(frag) + offset -
+					      start;
+				dmabuf_cmsg.frag_offset = frag_offset;
+				dmabuf_cmsg.frag_size = copy;
+				err = xa_alloc((struct xarray *)&sk->sk_user_frags,
+					       &user_token, frag->bv_page,
+					       xa_limit_31b, GFP_KERNEL);
+				if (err)
+					goto out;
+
+				dmabuf_cmsg.frag_token = user_token;
+				dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov);
+
+				offset += copy;
+				remaining_len -= copy;
+
+				err = put_cmsg(msg, SOL_SOCKET,
+					       SO_DEVMEM_DMABUF,
+					       sizeof(dmabuf_cmsg),
+					       &dmabuf_cmsg);
+				if (err || msg->msg_flags & MSG_CTRUNC) {
+					msg->msg_flags &= ~MSG_CTRUNC;
+					xa_erase((struct xarray *)&sk->sk_user_frags,
+						 user_token);
+					if (!err)
+						err = -ETOOSMALL;
+					goto out;
+				}
+
+				atomic_long_inc(&niov->pp_ref_count);
+
+				sent += copy;
+
+				if (remaining_len == 0)
+					goto out;
+			}
+			start = end;
+		}
+
+		if (!remaining_len)
+			goto out;
+
+		/* if remaining_len is not satisfied yet, we need to go to the
+		 * next frag in the frag_list to satisfy remaining_len.
+		 */
+		skb = skb_shinfo(skb)->frag_list ?: skb->next;
+
+		offset = offset - start;
+	} while (skb);
+
+	if (remaining_len) {
+		err = -EFAULT;
+		goto out;
+	}
+
+out:
+	if (!sent)
+		sent = err;
+
+	return sent;
+}
+
 /*
  *	This routine copies from a sock struct into the user buffer.
  *
@@ -2316,6 +2466,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 			      int *cmsg_flags)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	int last_copied_dmabuf = -1; /* uninitialized */
 	int copied = 0;
 	u32 peek_seq;
 	u32 *seq;
@@ -2493,15 +2644,44 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 
 		if (!(flags & MSG_TRUNC)) {
-			err = skb_copy_datagram_msg(skb, offset, msg, used);
-			if (err) {
-				/* Exception. Bailout! */
-				if (!copied)
-					copied = -EFAULT;
+			if (last_copied_dmabuf != -1 &&
+			    last_copied_dmabuf != skb->dmabuf)
 				break;
+
+			if (!skb->dmabuf) {
+				err = skb_copy_datagram_msg(skb, offset, msg,
+							    used);
+				if (err) {
+					/* Exception. Bailout! */
+					if (!copied)
+						copied = -EFAULT;
+					break;
+				}
+			} else {
+				if (!(flags & MSG_SOCK_DEVMEM)) {
+					/* skb->dmabuf skbs can only be received
+					 * with the MSG_SOCK_DEVMEM flag.
+					 */
+					if (!copied)
+						copied = -EFAULT;
+
+					break;
+				}
+
+				err = tcp_recvmsg_dmabuf(sk, skb, offset, msg,
+							 used);
+				if (err <= 0) {
+					if (!copied)
+						copied = -EFAULT;
+
+					break;
+				}
+				used = err;
 			}
 		}
 
+		last_copied_dmabuf = skb->dmabuf;
+
 		WRITE_ONCE(*seq, *seq + used);
 		copied += used;
 		len -= used;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4bac6e319aca..bff35d9be076 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2501,6 +2501,15 @@ static void tcp_md5sig_info_free_rcu(struct rcu_head *head)
 void tcp_v4_destroy_sock(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	__maybe_unused unsigned long index;
+	__maybe_unused struct netmem *netmem;
+
+#ifdef CONFIG_PAGE_POOL
+	xa_for_each(&sk->sk_user_frags, index, netmem)
+		WARN_ON_ONCE(!napi_pp_put_page(netmem, false));
+#endif
+
+	xa_destroy(&sk->sk_user_frags);
 
 	trace_tcp_destroy_sock(sk);
 
-- 
2.43.0.472.g3155946c3a-goog