Merge branch 'net-tls-fixes-for-nvme-over-tls'

Hannes Reinecke says:

====================
net/tls: fixes for NVMe-over-TLS

here are some small fixes to get NVMe-over-TLS up and running.
The first set are just minor modifications to have MSG_EOR handled
for TLS, but the second set implements the ->read_sock() callback
for tls_sw.
The ->read_sock() callbacks return -EIO when encountering any TLS
Alert message, but as that's the default behaviour anyway I guess
we can get away with it.
====================

Applied on top of the tag in case Sagi gets convinced to pull it.

Link: https://lore.kernel.org/r/20230726191556.41714-1-hare@suse.deSigned-off-by: Jakub Kicinski <kuba@kernel.org>

net/tls/tls.h

@@ -110,6 +110,8 @@ bool tls_sw_sock_is_readable(struct sock *sk);
 ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
 			   struct pipe_inode_info *pipe,
 			   size_t len, unsigned int flags);
+int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc,
+		     sk_read_actor_t read_actor);
 
 int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 void tls_device_splice_eof(struct socket *sock);

net/tls/tls_device.c

@@ -441,9 +441,13 @@ static int tls_push_data(struct sock *sk,
 	long timeo;
 
 	if (flags &
-	    ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SPLICE_PAGES))
+	    ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
+	      MSG_SPLICE_PAGES | MSG_EOR))
 		return -EOPNOTSUPP;
 
+	if ((flags & (MSG_MORE | MSG_EOR)) == (MSG_MORE | MSG_EOR))
+		return -EINVAL;
+
 	if (unlikely(sk->sk_err))
 		return -sk->sk_err;
 

net/tls/tls_main.c

@@ -962,10 +962,12 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG]
 	ops[TLS_BASE][TLS_SW  ] = ops[TLS_BASE][TLS_BASE];
 	ops[TLS_BASE][TLS_SW  ].splice_read	= tls_sw_splice_read;
 	ops[TLS_BASE][TLS_SW  ].poll		= tls_sk_poll;
+	ops[TLS_BASE][TLS_SW  ].read_sock	= tls_sw_read_sock;
 
 	ops[TLS_SW  ][TLS_SW  ] = ops[TLS_SW  ][TLS_BASE];
 	ops[TLS_SW  ][TLS_SW  ].splice_read	= tls_sw_splice_read;
 	ops[TLS_SW  ][TLS_SW  ].poll		= tls_sk_poll;
+	ops[TLS_SW  ][TLS_SW  ].read_sock	= tls_sw_read_sock;
 
 #ifdef CONFIG_TLS_DEVICE
 	ops[TLS_HW  ][TLS_BASE] = ops[TLS_BASE][TLS_BASE];

net/tls/tls_strp.c

@@ -369,7 +369,6 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb,
 
 static int tls_strp_read_copyin(struct tls_strparser *strp)
 {
-	struct socket *sock = strp->sk->sk_socket;
 	read_descriptor_t desc;
 
 	desc.arg.data = strp;
@@ -377,7 +376,7 @@ static int tls_strp_read_copyin(struct tls_strparser *strp)
 	desc.count = 1; /* give more than one skb per call */
 
 	/* sk should be locked here, so okay to do read_sock */
-	sock->ops->read_sock(strp->sk, &desc, tls_strp_copyin);
+	tcp_read_sock(strp->sk, &desc, tls_strp_copyin);
 
 	return desc.error;
 }

net/tls/tls_sw.c

@@ -984,6 +984,9 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 	int ret = 0;
 	int pending;
 
+	if (!eor && (msg->msg_flags & MSG_EOR))
+		return -EINVAL;
+
 	if (unlikely(msg->msg_controllen)) {
 		ret = tls_process_cmsg(sk, msg, &record_type);
 		if (ret) {
@@ -1193,7 +1196,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	int ret;
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
-			       MSG_CMSG_COMPAT | MSG_SPLICE_PAGES |
+			       MSG_CMSG_COMPAT | MSG_SPLICE_PAGES | MSG_EOR |
 			       MSG_SENDPAGE_NOPOLICY))
 		return -EOPNOTSUPP;
 
@@ -1845,13 +1848,10 @@ tls_read_flush_backlog(struct sock *sk, struct tls_prot_info *prot,
 	return sk_flush_backlog(sk);
 }
 
-static int tls_rx_reader_lock(struct sock *sk, struct tls_sw_context_rx *ctx,
-			      bool nonblock)
+static int tls_rx_reader_acquire(struct sock *sk, struct tls_sw_context_rx *ctx,
+				 bool nonblock)
 {
 	long timeo;
-	int err;
-
-	lock_sock(sk);
 
 	timeo = sock_rcvtimeo(sk, nonblock);
 
@@ -1865,26 +1865,30 @@ static int tls_rx_reader_lock(struct sock *sk, struct tls_sw_context_rx *ctx,
 			      !READ_ONCE(ctx->reader_present), &wait);
 		remove_wait_queue(&ctx->wq, &wait);
 
-		if (timeo <= 0) {
-			err = -EAGAIN;
-			goto err_unlock;
-		}
-		if (signal_pending(current)) {
-			err = sock_intr_errno(timeo);
-			goto err_unlock;
-		}
+		if (timeo <= 0)
+			return -EAGAIN;
+		if (signal_pending(current))
+			return sock_intr_errno(timeo);
 	}
 
 	WRITE_ONCE(ctx->reader_present, 1);
 
 	return 0;
+}
 
-err_unlock:
-	release_sock(sk);
+static int tls_rx_reader_lock(struct sock *sk, struct tls_sw_context_rx *ctx,
+			      bool nonblock)
+{
+	int err;
+
+	lock_sock(sk);
+	err = tls_rx_reader_acquire(sk, ctx, nonblock);
+	if (err)
+		release_sock(sk);
 	return err;
 }
 
-static void tls_rx_reader_unlock(struct sock *sk, struct tls_sw_context_rx *ctx)
+static void tls_rx_reader_release(struct sock *sk, struct tls_sw_context_rx *ctx)
 {
 	if (unlikely(ctx->reader_contended)) {
 		if (wq_has_sleeper(&ctx->wq))
@@ -1896,6 +1900,11 @@ static void tls_rx_reader_unlock(struct sock *sk, struct tls_sw_context_rx *ctx)
 	}
 
 	WRITE_ONCE(ctx->reader_present, 0);
+}
+
+static void tls_rx_reader_unlock(struct sock *sk, struct tls_sw_context_rx *ctx)
+{
+	tls_rx_reader_release(sk, ctx);
 	release_sock(sk);
 }
 
@@ -2193,6 +2202,105 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 	goto splice_read_end;
 }
 
+int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc,
+		     sk_read_actor_t read_actor)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+	struct tls_prot_info *prot = &tls_ctx->prot_info;
+	struct strp_msg *rxm = NULL;
+	struct sk_buff *skb = NULL;
+	struct sk_psock *psock;
+	size_t flushed_at = 0;
+	bool released = true;
+	struct tls_msg *tlm;
+	ssize_t copied = 0;
+	ssize_t decrypted;
+	int err, used;
+
+	psock = sk_psock_get(sk);
+	if (psock) {
+		sk_psock_put(sk, psock);
+		return -EINVAL;
+	}
+	err = tls_rx_reader_acquire(sk, ctx, true);
+	if (err < 0)
+		return err;
+
+	/* If crypto failed the connection is broken */
+	err = ctx->async_wait.err;
+	if (err)
+		goto read_sock_end;
+
+	decrypted = 0;
+	do {
+		if (!skb_queue_empty(&ctx->rx_list)) {
+			skb = __skb_dequeue(&ctx->rx_list);
+			rxm = strp_msg(skb);
+			tlm = tls_msg(skb);
+		} else {
+			struct tls_decrypt_arg darg;
+			int to_decrypt;
+
+			err = tls_rx_rec_wait(sk, NULL, true, released);
+			if (err <= 0)
+				goto read_sock_end;
+
+			memset(&darg.inargs, 0, sizeof(darg.inargs));
+
+			rxm = strp_msg(tls_strp_msg(ctx));
+			tlm = tls_msg(tls_strp_msg(ctx));
+
+			to_decrypt = rxm->full_len - prot->overhead_size;
+
+			err = tls_rx_one_record(sk, NULL, &darg);
+			if (err < 0) {
+				tls_err_abort(sk, -EBADMSG);
+				goto read_sock_end;
+			}
+
+			released = tls_read_flush_backlog(sk, prot, rxm->full_len, to_decrypt,
+							  decrypted, &flushed_at);
+			skb = darg.skb;
+			decrypted += rxm->full_len;
+
+			tls_rx_rec_done(ctx);
+		}
+
+		/* read_sock does not support reading control messages */
+		if (tlm->control != TLS_RECORD_TYPE_DATA) {
+			err = -EINVAL;
+			goto read_sock_requeue;
+		}
+
+		used = read_actor(desc, skb, rxm->offset, rxm->full_len);
+		if (used <= 0) {
+			if (!copied)
+				err = used;
+			goto read_sock_requeue;
+		}
+		copied += used;
+		if (used < rxm->full_len) {
+			rxm->offset += used;
+			rxm->full_len -= used;
+			if (!desc->count)
+				goto read_sock_requeue;
+		} else {
+			consume_skb(skb);
+			if (!desc->count)
+				skb = NULL;
+		}
+	} while (skb);
+
+read_sock_end:
+	tls_rx_reader_release(sk, ctx);
+	return copied ? : err;
+
+read_sock_requeue:
+	__skb_queue_head(&ctx->rx_list, skb);
+	goto read_sock_end;
+}
+
 bool tls_sw_sock_is_readable(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);

tools/testing/selftests/net/tls.c

@@ -486,6 +486,17 @@ TEST_F(tls, msg_more_unsent)
 	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1);
 }
 
+TEST_F(tls, msg_eor)
+{
+	char const *test_str = "test_read";
+	int send_len = 10;
+	char buf[10];
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, MSG_EOR), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
 TEST_F(tls, sendmsg_single)
 {
 	struct msghdr msg;