1 files changed, 120 insertions, 137 deletions

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 635b8bf6b937..53f944e6d8ef 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -70,7 +70,9 @@ noinline void tls_err_abort(struct sock *sk, int err)
 {
 	WARN_ON_ONCE(err >= 0);
 	/* sk->sk_err should contain a positive error code. */
-	sk->sk_err = -err;
+	WRITE_ONCE(sk->sk_err, -err);
+	/* Paired with smp_rmb() in tcp_poll() */
+	smp_wmb();
 	sk_error_report(sk);
 }
 
@@ -929,7 +931,37 @@ static int tls_sw_push_pending_record(struct sock *sk, int flags)
 				   &copied, flags);
 }
 
-int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+static int tls_sw_sendmsg_splice(struct sock *sk, struct msghdr *msg,
+				 struct sk_msg *msg_pl, size_t try_to_copy,
+				 ssize_t *copied)
+{
+	struct page *page = NULL, **pages = &page;
+
+	do {
+		ssize_t part;
+		size_t off;
+
+		part = iov_iter_extract_pages(&msg->msg_iter, &pages,
+					      try_to_copy, 1, 0, &off);
+		if (part <= 0)
+			return part ?: -EIO;
+
+		if (WARN_ON_ONCE(!sendpage_ok(page))) {
+			iov_iter_revert(&msg->msg_iter, part);
+			return -EIO;
+		}
+
+		sk_msg_page_add(msg_pl, page, part, off);
+		sk_mem_charge(sk, part);
+		*copied += part;
+		try_to_copy -= part;
+	} while (try_to_copy && !sk_msg_full(msg_pl));
+
+	return 0;
+}
+
+static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
+				 size_t size)
 {
 	long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
@@ -952,15 +984,6 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	int ret = 0;
 	int pending;
 
-	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
-			       MSG_CMSG_COMPAT))
-		return -EOPNOTSUPP;
-
-	ret = mutex_lock_interruptible(&tls_ctx->tx_lock);
-	if (ret)
-		return ret;
-	lock_sock(sk);
-
 	if (unlikely(msg->msg_controllen)) {
 		ret = tls_process_cmsg(sk, msg, &record_type);
 		if (ret) {
@@ -1018,6 +1041,17 @@ alloc_encrypted:
 			full_record = true;
 		}
 
+		if (try_to_copy && (msg->msg_flags & MSG_SPLICE_PAGES)) {
+			ret = tls_sw_sendmsg_splice(sk, msg, msg_pl,
+						    try_to_copy, &copied);
+			if (ret < 0)
+				goto send_end;
+			tls_ctx->pending_open_record_frags = true;
+			if (full_record || eor || sk_msg_full(msg_pl))
+				goto copied;
+			continue;
+		}
+
 		if (!is_kvec && (full_record || eor) && !async_capable) {
 			u32 first = msg_pl->sg.end;
 
@@ -1082,6 +1116,7 @@ fallback_to_reg_send:
 		 */
 		tls_ctx->pending_open_record_frags = true;
 		copied += try_to_copy;
+copied:
 		if (full_record || eor) {
 			ret = bpf_exec_tx_verdict(msg_pl, sk, full_record,
 						  record_type, &copied,
@@ -1149,157 +1184,101 @@ trim_sgl:
 
 send_end:
 	ret = sk_stream_error(sk, msg->msg_flags, ret);
+	return copied > 0 ? copied : ret;
+}
+
+int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	int ret;
 
+	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
+			       MSG_CMSG_COMPAT | MSG_SPLICE_PAGES |
+			       MSG_SENDPAGE_NOPOLICY))
+		return -EOPNOTSUPP;
+
+	ret = mutex_lock_interruptible(&tls_ctx->tx_lock);
+	if (ret)
+		return ret;
+	lock_sock(sk);
+	ret = tls_sw_sendmsg_locked(sk, msg, size);
 	release_sock(sk);
 	mutex_unlock(&tls_ctx->tx_lock);
-	return copied > 0 ? copied : ret;
+	return ret;
 }
 
-static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
-			      int offset, size_t size, int flags)
+/*
+ * Handle unexpected EOF during splice without SPLICE_F_MORE set.
+ */
+void tls_sw_splice_eof(struct socket *sock)
 {
-	long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
+	struct sock *sk = sock->sk;
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
-	struct tls_prot_info *prot = &tls_ctx->prot_info;
-	unsigned char record_type = TLS_RECORD_TYPE_DATA;
-	struct sk_msg *msg_pl;
 	struct tls_rec *rec;
-	int num_async = 0;
+	struct sk_msg *msg_pl;
 	ssize_t copied = 0;
-	bool full_record;
-	int record_room;
+	bool retrying = false;
 	int ret = 0;
-	bool eor;
-
-	eor = !(flags & MSG_SENDPAGE_NOTLAST);
-	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
-
-	/* Call the sk_stream functions to manage the sndbuf mem. */
-	while (size > 0) {
-		size_t copy, required_size;
-
-		if (sk->sk_err) {
-			ret = -sk->sk_err;
-			goto sendpage_end;
-		}
-
-		if (ctx->open_rec)
-			rec = ctx->open_rec;
-		else
-			rec = ctx->open_rec = tls_get_rec(sk);
-		if (!rec) {
-			ret = -ENOMEM;
-			goto sendpage_end;
-		}
-
-		msg_pl = &rec->msg_plaintext;
-
-		full_record = false;
-		record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size;
-		copy = size;
-		if (copy >= record_room) {
-			copy = record_room;
-			full_record = true;
-		}
-
-		required_size = msg_pl->sg.size + copy + prot->overhead_size;
-
-		if (!sk_stream_memory_free(sk))
-			goto wait_for_sndbuf;
-alloc_payload:
-		ret = tls_alloc_encrypted_msg(sk, required_size);
-		if (ret) {
-			if (ret != -ENOSPC)
-				goto wait_for_memory;
+	int pending;
 
-			/* Adjust copy according to the amount that was
-			 * actually allocated. The difference is due
-			 * to max sg elements limit
-			 */
-			copy -= required_size - msg_pl->sg.size;
-			full_record = true;
-		}
+	if (!ctx->open_rec)
+		return;
 
-		sk_msg_page_add(msg_pl, page, copy, offset);
-		sk_mem_charge(sk, copy);
+	mutex_lock(&tls_ctx->tx_lock);
+	lock_sock(sk);
 
-		offset += copy;
-		size -= copy;
-		copied += copy;
+retry:
+	rec = ctx->open_rec;
+	if (!rec)
+		goto unlock;
 
-		tls_ctx->pending_open_record_frags = true;
-		if (full_record || eor || sk_msg_full(msg_pl)) {
-			ret = bpf_exec_tx_verdict(msg_pl, sk, full_record,
-						  record_type, &copied, flags);
-			if (ret) {
-				if (ret == -EINPROGRESS)
-					num_async++;
-				else if (ret == -ENOMEM)
-					goto wait_for_memory;
-				else if (ret != -EAGAIN) {
-					if (ret == -ENOSPC)
-						ret = 0;
-					goto sendpage_end;
-				}
-			}
-		}
-		continue;
-wait_for_sndbuf:
-		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-wait_for_memory:
-		ret = sk_stream_wait_memory(sk, &timeo);
-		if (ret) {
-			if (ctx->open_rec)
-				tls_trim_both_msgs(sk, msg_pl->sg.size);
-			goto sendpage_end;
-		}
+	msg_pl = &rec->msg_plaintext;
 
-		if (ctx->open_rec)
-			goto alloc_payload;
+	/* Check the BPF advisor and perform transmission. */
+	ret = bpf_exec_tx_verdict(msg_pl, sk, false, TLS_RECORD_TYPE_DATA,
+				  &copied, 0);
+	switch (ret) {
+	case 0:
+	case -EAGAIN:
+		if (retrying)
+			goto unlock;
+		retrying = true;
+		goto retry;
+	case -EINPROGRESS:
+		break;
+	default:
+		goto unlock;
 	}
 
-	if (num_async) {
-		/* Transmit if any encryptions have completed */
-		if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
-			cancel_delayed_work(&ctx->tx_work.work);
-			tls_tx_records(sk, flags);
-		}
-	}
-sendpage_end:
-	ret = sk_stream_error(sk, flags, ret);
-	return copied > 0 ? copied : ret;
-}
+	/* Wait for pending encryptions to get completed */
+	spin_lock_bh(&ctx->encrypt_compl_lock);
+	ctx->async_notify = true;
 
-int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
-			   int offset, size_t size, int flags)
-{
-	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
-		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY |
-		      MSG_NO_SHARED_FRAGS))
-		return -EOPNOTSUPP;
+	pending = atomic_read(&ctx->encrypt_pending);
+	spin_unlock_bh(&ctx->encrypt_compl_lock);
+	if (pending)
+		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+	else
+		reinit_completion(&ctx->async_wait.completion);
 
-	return tls_sw_do_sendpage(sk, page, offset, size, flags);
-}
+	/* There can be no concurrent accesses, since we have no pending
+	 * encrypt operations
+	 */
+	WRITE_ONCE(ctx->async_notify, false);
 
-int tls_sw_sendpage(struct sock *sk, struct page *page,
-		    int offset, size_t size, int flags)
-{
-	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	int ret;
+	if (ctx->async_wait.err)
+		goto unlock;
 
-	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
-		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
-		return -EOPNOTSUPP;
+	/* Transmit if any encryptions have completed */
+	if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
+		cancel_delayed_work(&ctx->tx_work.work);
+		tls_tx_records(sk, 0);
+	}
 
-	ret = mutex_lock_interruptible(&tls_ctx->tx_lock);
-	if (ret)
-		return ret;
-	lock_sock(sk);
-	ret = tls_sw_do_sendpage(sk, page, offset, size, flags);
+unlock:
 	release_sock(sk);
 	mutex_unlock(&tls_ctx->tx_lock);
-	return ret;
 }
 
 static int
@@ -2304,10 +2283,14 @@ static void tls_data_ready(struct sock *sk)
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
 	struct sk_psock *psock;
+	gfp_t alloc_save;
 
 	trace_sk_data_ready(sk);
 
+	alloc_save = sk->sk_allocation;
+	sk->sk_allocation = GFP_ATOMIC;
 	tls_strp_data_ready(&ctx->strp);
+	sk->sk_allocation = alloc_save;
 
 	psock = sk_psock_get(sk);
 	if (psock) {