Merge branch 'tcp-zero-copy-receive'

Eric Dumazet says:

====================
tcp: add zero copy receive

This patch series add mmap() support to TCP sockets for RX zero copy.

While tcp_mmap() patch itself is quite small (~100 LOC), optimal support
for asynchronous mmap() required better SO_RCVLOWAT behavior, and a
test program to demonstrate how mmap() on TCP sockets can be used.

Note that mmap() (and associated munmap()) calls are adding more
pressure on per-process VM semaphore, so might not show benefit
for processus with high number of threads.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/net.h

@@ -197,6 +197,7 @@ struct proto_ops {
 					   int offset, size_t size, int flags);
 	int		(*sendmsg_locked)(struct sock *sk, struct msghdr *msg,
 					  size_t size);
+	int		(*set_rcvlowat)(struct sock *sk, int val);
 };
 
 #define DECLARE_SOCKADDR(type, dst, src)	\

include/net/tcp.h

@@ -402,6 +402,10 @@ void tcp_set_keepalive(struct sock *sk, int val);
 void tcp_syn_ack_timeout(const struct request_sock *req);
 int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		int flags, int *addr_len);
+int tcp_set_rcvlowat(struct sock *sk, int val);
+void tcp_data_ready(struct sock *sk);
+int tcp_mmap(struct file *file, struct socket *sock,
+	     struct vm_area_struct *vma);
 void tcp_parse_options(const struct net *net, const struct sk_buff *skb,
 		       struct tcp_options_received *opt_rx,
 		       int estab, struct tcp_fastopen_cookie *foc);

net/core/sock.c

@@ -905,7 +905,10 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 	case SO_RCVLOWAT:
 		if (val < 0)
 			val = INT_MAX;
-		sk->sk_rcvlowat = val ? : 1;
+		if (sock->ops->set_rcvlowat)
+			ret = sock->ops->set_rcvlowat(sk, val);
+		else
+			sk->sk_rcvlowat = val ? : 1;
 		break;
 
 	case SO_RCVTIMEO:

net/ipv4/af_inet.c

@@ -994,7 +994,7 @@ const struct proto_ops inet_stream_ops = {
 	.getsockopt	   = sock_common_getsockopt,
 	.sendmsg	   = inet_sendmsg,
 	.recvmsg	   = inet_recvmsg,
-	.mmap		   = sock_no_mmap,
+	.mmap		   = tcp_mmap,
 	.sendpage	   = inet_sendpage,
 	.splice_read	   = tcp_splice_read,
 	.read_sock	   = tcp_read_sock,
@@ -1006,6 +1006,7 @@ const struct proto_ops inet_stream_ops = {
 	.compat_getsockopt = compat_sock_common_getsockopt,
 	.compat_ioctl	   = inet_compat_ioctl,
 #endif
+	.set_rcvlowat	   = tcp_set_rcvlowat,
 };
 EXPORT_SYMBOL(inet_stream_ops);
 

net/ipv4/tcp.c

@@ -1701,6 +1701,144 @@ int tcp_peek_len(struct socket *sock)
 }
 EXPORT_SYMBOL(tcp_peek_len);
 
+/* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */
+int tcp_set_rcvlowat(struct sock *sk, int val)
+{
+	sk->sk_rcvlowat = val ? : 1;
+
+	/* Check if we need to signal EPOLLIN right now */
+	tcp_data_ready(sk);
+
+	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
+		return 0;
+
+	/* val comes from user space and might be close to INT_MAX */
+	val <<= 1;
+	if (val < 0)
+		val = INT_MAX;
+
+	val = min(val, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+	if (val > sk->sk_rcvbuf) {
+		sk->sk_rcvbuf = val;
+		tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(tcp_set_rcvlowat);
+
+/* When user wants to mmap X pages, we first need to perform the mapping
+ * before freeing any skbs in receive queue, otherwise user would be unable
+ * to fallback to standard recvmsg(). This happens if some data in the
+ * requested block is not exactly fitting in a page.
+ *
+ * We only support order-0 pages for the moment.
+ * mmap() on TCP is very strict, there is no point
+ * trying to accommodate with pathological layouts.
+ */
+int tcp_mmap(struct file *file, struct socket *sock,
+	     struct vm_area_struct *vma)
+{
+	unsigned long size = vma->vm_end - vma->vm_start;
+	unsigned int nr_pages = size >> PAGE_SHIFT;
+	struct page **pages_array = NULL;
+	u32 seq, len, offset, nr = 0;
+	struct sock *sk = sock->sk;
+	const skb_frag_t *frags;
+	struct tcp_sock *tp;
+	struct sk_buff *skb;
+	int ret;
+
+	if (vma->vm_pgoff || !nr_pages)
+		return -EINVAL;
+
+	if (vma->vm_flags & VM_WRITE)
+		return -EPERM;
+	/* TODO: Maybe the following is not needed if pages are COW */
+	vma->vm_flags &= ~VM_MAYWRITE;
+
+	lock_sock(sk);
+
+	ret = -ENOTCONN;
+	if (sk->sk_state == TCP_LISTEN)
+		goto out;
+
+	sock_rps_record_flow(sk);
+
+	if (tcp_inq(sk) < size) {
+		ret = sock_flag(sk, SOCK_DONE) ? -EIO : -EAGAIN;
+		goto out;
+	}
+	tp = tcp_sk(sk);
+	seq = tp->copied_seq;
+	/* Abort if urgent data is in the area */
+	if (unlikely(tp->urg_data)) {
+		u32 urg_offset = tp->urg_seq - seq;
+
+		ret = -EINVAL;
+		if (urg_offset < size)
+			goto out;
+	}
+	ret = -ENOMEM;
+	pages_array = kvmalloc_array(nr_pages, sizeof(struct page *),
+				     GFP_KERNEL);
+	if (!pages_array)
+		goto out;
+	skb = tcp_recv_skb(sk, seq, &offset);
+	ret = -EINVAL;
+skb_start:
+	/* We do not support anything not in page frags */
+	offset -= skb_headlen(skb);
+	if ((int)offset < 0)
+		goto out;
+	if (skb_has_frag_list(skb))
+		goto out;
+	len = skb->data_len - offset;
+	frags = skb_shinfo(skb)->frags;
+	while (offset) {
+		if (frags->size > offset)
+			goto out;
+		offset -= frags->size;
+		frags++;
+	}
+	while (nr < nr_pages) {
+		if (len) {
+			if (len < PAGE_SIZE)
+				goto out;
+			if (frags->size != PAGE_SIZE || frags->page_offset)
+				goto out;
+			pages_array[nr++] = skb_frag_page(frags);
+			frags++;
+			len -= PAGE_SIZE;
+			seq += PAGE_SIZE;
+			continue;
+		}
+		skb = skb->next;
+		offset = seq - TCP_SKB_CB(skb)->seq;
+		goto skb_start;
+	}
+	/* OK, we have a full set of pages ready to be inserted into vma */
+	for (nr = 0; nr < nr_pages; nr++) {
+		ret = vm_insert_page(vma, vma->vm_start + (nr << PAGE_SHIFT),
+				     pages_array[nr]);
+		if (ret)
+			goto out;
+	}
+	/* operation is complete, we can 'consume' all skbs */
+	tp->copied_seq = seq;
+	tcp_rcv_space_adjust(sk);
+
+	/* Clean up data we have read: This will do ACK frames. */
+	tcp_recv_skb(sk, seq, &offset);
+	tcp_cleanup_rbuf(sk, size);
+
+	ret = 0;
+out:
+	release_sock(sk);
+	kvfree(pages_array);
+	return ret;
+}
+EXPORT_SYMBOL(tcp_mmap);
+
 static void tcp_update_recv_tstamps(struct sk_buff *skb,
 				    struct scm_timestamping *tss)
 {

net/ipv4/tcp_input.c

@@ -4576,6 +4576,17 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 
 }
 
+void tcp_data_ready(struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	int avail = tp->rcv_nxt - tp->copied_seq;
+
+	if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+		return;
+
+	sk->sk_data_ready(sk);
+}
+
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -4633,7 +4644,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 		if (eaten > 0)
 			kfree_skb_partial(skb, fragstolen);
 		if (!sock_flag(sk, SOCK_DEAD))
-			sk->sk_data_ready(sk);
+			tcp_data_ready(sk);
 		return;
 	}
 
@@ -5026,9 +5037,12 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 	    /* More than one full frame received... */
 	if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss &&
 	     /* ... and right edge of window advances far enough.
-	      * (tcp_recvmsg() will send ACK otherwise). Or...
+	      * (tcp_recvmsg() will send ACK otherwise).
+	      * If application uses SO_RCVLOWAT, we want send ack now if
+	      * we have not received enough bytes to satisfy the condition.
 	      */
-	     __tcp_select_window(sk) >= tp->rcv_wnd) ||
+	    (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat ||
+	     __tcp_select_window(sk) >= tp->rcv_wnd)) ||
 	    /* We ACK each frame or... */
 	    tcp_in_quickack_mode(sk) ||
 	    /* We have out of order data. */
@@ -5431,7 +5445,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 no_ack:
 			if (eaten)
 				kfree_skb_partial(skb, fragstolen);
-			sk->sk_data_ready(sk);
+			tcp_data_ready(sk);
 			return;
 		}
 	}

net/ipv6/af_inet6.c

@@ -579,7 +579,7 @@ const struct proto_ops inet6_stream_ops = {
 	.getsockopt	   = sock_common_getsockopt,	/* ok		*/
 	.sendmsg	   = inet_sendmsg,		/* ok		*/
 	.recvmsg	   = inet_recvmsg,		/* ok		*/
-	.mmap		   = sock_no_mmap,
+	.mmap		   = tcp_mmap,
 	.sendpage	   = inet_sendpage,
 	.sendmsg_locked    = tcp_sendmsg_locked,
 	.sendpage_locked   = tcp_sendpage_locked,
@@ -590,6 +590,7 @@ const struct proto_ops inet6_stream_ops = {
 	.compat_setsockopt = compat_sock_common_setsockopt,
 	.compat_getsockopt = compat_sock_common_getsockopt,
 #endif
+	.set_rcvlowat	   = tcp_set_rcvlowat,
 };
 
 const struct proto_ops inet6_dgram_ops = {

tools/testing/selftests/net/Makefile

@@ -8,9 +8,11 @@ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetl
 TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
+TEST_GEN_FILES += tcp_mmap
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
 
 include ../lib.mk
 
 $(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma
+$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread