5 files changed, 251 insertions, 257 deletions

diff --git a/net/tls/tls.h b/net/tls/tls.h
index 0672acab2773..86cef1c68e03 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -97,10 +97,7 @@ void tls_update_rx_zc_capable(struct tls_context *tls_ctx);
 void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx);
 void tls_sw_strparser_done(struct tls_context *tls_ctx);
 int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
-int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
-			   int offset, size_t size, int flags);
-int tls_sw_sendpage(struct sock *sk, struct page *page,
-		    int offset, size_t size, int flags);
+void tls_sw_splice_eof(struct socket *sock);
 void tls_sw_cancel_work_tx(struct tls_context *tls_ctx);
 void tls_sw_release_resources_tx(struct sock *sk);
 void tls_sw_free_ctx_tx(struct tls_context *tls_ctx);
@@ -115,8 +112,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
 			   size_t len, unsigned int flags);
 
 int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
-int tls_device_sendpage(struct sock *sk, struct page *page,
-			int offset, size_t size, int flags);
+void tls_device_splice_eof(struct socket *sock);
 int tls_tx_records(struct sock *sk, int flags);
 
 void tls_sw_write_space(struct sock *sk, struct tls_context *ctx);
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index bf69c9d6d06c..529101eb20bd 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -52,6 +52,8 @@ static LIST_HEAD(tls_device_list);
 static LIST_HEAD(tls_device_down_list);
 static DEFINE_SPINLOCK(tls_device_lock);
 
+static struct page *dummy_page;
+
 static void tls_device_free_ctx(struct tls_context *ctx)
 {
 	if (ctx->tx_conf == TLS_HW) {
@@ -268,9 +270,8 @@ static void tls_append_frag(struct tls_record_info *record,
 		skb_frag_size_add(frag, size);
 	} else {
 		++frag;
-		__skb_frag_set_page(frag, pfrag->page);
-		skb_frag_off_set(frag, pfrag->offset);
-		skb_frag_size_set(frag, size);
+		skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset,
+					size);
 		++record->num_frags;
 		get_page(pfrag->page);
 	}
@@ -313,36 +314,33 @@ static int tls_push_record(struct sock *sk,
 	return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags);
 }
 
-static int tls_device_record_close(struct sock *sk,
-				   struct tls_context *ctx,
-				   struct tls_record_info *record,
-				   struct page_frag *pfrag,
-				   unsigned char record_type)
+static void tls_device_record_close(struct sock *sk,
+				    struct tls_context *ctx,
+				    struct tls_record_info *record,
+				    struct page_frag *pfrag,
+				    unsigned char record_type)
 {
 	struct tls_prot_info *prot = &ctx->prot_info;
-	int ret;
+	struct page_frag dummy_tag_frag;
 
 	/* append tag
 	 * device will fill in the tag, we just need to append a placeholder
 	 * use socket memory to improve coalescing (re-using a single buffer
 	 * increases frag count)
-	 * if we can't allocate memory now, steal some back from data
+	 * if we can't allocate memory now use the dummy page
 	 */
-	if (likely(skb_page_frag_refill(prot->tag_size, pfrag,
-					sk->sk_allocation))) {
-		ret = 0;
-		tls_append_frag(record, pfrag, prot->tag_size);
-	} else {
-		ret = prot->tag_size;
-		if (record->len <= prot->overhead_size)
-			return -ENOMEM;
+	if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) &&
+	    !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) {
+		dummy_tag_frag.page = dummy_page;
+		dummy_tag_frag.offset = 0;
+		pfrag = &dummy_tag_frag;
 	}
+	tls_append_frag(record, pfrag, prot->tag_size);
 
 	/* fill prepend */
 	tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]),
 			 record->len - prot->overhead_size,
 			 record_type);
-	return ret;
 }
 
 static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx,
@@ -357,9 +355,8 @@ static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx,
 		return -ENOMEM;
 
 	frag = &record->frags[0];
-	__skb_frag_set_page(frag, pfrag->page);
-	skb_frag_off_set(frag, pfrag->offset);
-	skb_frag_size_set(frag, prepend_size);
+	skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset,
+				prepend_size);
 
 	get_page(pfrag->page);
 	pfrag->offset += prepend_size;
@@ -424,16 +421,10 @@ static int tls_device_copy_data(void *addr, size_t bytes, struct iov_iter *i)
 	return 0;
 }
 
-union tls_iter_offset {
-	struct iov_iter *msg_iter;
-	int offset;
-};
-
 static int tls_push_data(struct sock *sk,
-			 union tls_iter_offset iter_offset,
+			 struct iov_iter *iter,
 			 size_t size, int flags,
-			 unsigned char record_type,
-			 struct page *zc_page)
+			 unsigned char record_type)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_prot_info *prot = &tls_ctx->prot_info;
@@ -449,14 +440,14 @@ static int tls_push_data(struct sock *sk,
 	long timeo;
 
 	if (flags &
-	    ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST))
+	    ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SPLICE_PAGES))
 		return -EOPNOTSUPP;
 
 	if (unlikely(sk->sk_err))
 		return -sk->sk_err;
 
 	flags |= MSG_SENDPAGE_DECRYPTED;
-	tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
+	tls_push_record_flags = flags | MSG_MORE;
 
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 	if (tls_is_partially_sent_record(tls_ctx)) {
@@ -501,21 +492,35 @@ handle_error:
 		record = ctx->open_record;
 
 		copy = min_t(size_t, size, max_open_record_len - record->len);
-		if (copy && zc_page) {
+		if (copy && (flags & MSG_SPLICE_PAGES)) {
 			struct page_frag zc_pfrag;
+			struct page **pages = &zc_pfrag.page;
+			size_t off;
+
+			rc = iov_iter_extract_pages(iter, &pages,
+						    copy, 1, 0, &off);
+			if (rc <= 0) {
+				if (rc == 0)
+					rc = -EIO;
+				goto handle_error;
+			}
+			copy = rc;
 
-			zc_pfrag.page = zc_page;
-			zc_pfrag.offset = iter_offset.offset;
+			if (WARN_ON_ONCE(!sendpage_ok(zc_pfrag.page))) {
+				iov_iter_revert(iter, copy);
+				rc = -EIO;
+				goto handle_error;
+			}
+
+			zc_pfrag.offset = off;
 			zc_pfrag.size = copy;
 			tls_append_frag(record, &zc_pfrag, copy);
-
-			iter_offset.offset += copy;
 		} else if (copy) {
 			copy = min_t(size_t, copy, pfrag->size - pfrag->offset);
 
 			rc = tls_device_copy_data(page_address(pfrag->page) +
 						  pfrag->offset, copy,
-						  iter_offset.msg_iter);
+						  iter);
 			if (rc)
 				goto handle_error;
 			tls_append_frag(record, pfrag, copy);
@@ -525,7 +530,7 @@ handle_error:
 		if (!size) {
 last_record:
 			tls_push_record_flags = flags;
-			if (flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE)) {
+			if (flags & MSG_MORE) {
 				more = true;
 				break;
 			}
@@ -535,18 +540,8 @@ last_record:
 
 		if (done || record->len >= max_open_record_len ||
 		    (record->num_frags >= MAX_SKB_FRAGS - 1)) {
-			rc = tls_device_record_close(sk, tls_ctx, record,
-						     pfrag, record_type);
-			if (rc) {
-				if (rc > 0) {
-					size += rc;
-				} else {
-					size = orig_size;
-					destroy_record(record);
-					ctx->open_record = NULL;
-					break;
-				}
-			}
+			tls_device_record_close(sk, tls_ctx, record,
+						pfrag, record_type);
 
 			rc = tls_push_record(sk,
 					     tls_ctx,
@@ -570,9 +565,11 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	unsigned char record_type = TLS_RECORD_TYPE_DATA;
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	union tls_iter_offset iter;
 	int rc;
 
+	if (!tls_ctx->zerocopy_sendfile)
+		msg->msg_flags &= ~MSG_SPLICE_PAGES;
+
 	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 
@@ -582,8 +579,8 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 			goto out;
 	}
 
-	iter.msg_iter = &msg->msg_iter;
-	rc = tls_push_data(sk, iter, size, msg->msg_flags, record_type, NULL);
+	rc = tls_push_data(sk, &msg->msg_iter, size, msg->msg_flags,
+			   record_type);
 
 out:
 	release_sock(sk);
@@ -591,47 +588,25 @@ out:
 	return rc;
 }
 
-int tls_device_sendpage(struct sock *sk, struct page *page,
-			int offset, size_t size, int flags)
+void tls_device_splice_eof(struct socket *sock)
 {
+	struct sock *sk = sock->sk;
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	union tls_iter_offset iter_offset;
-	struct iov_iter msg_iter;
-	char *kaddr;
-	struct kvec iov;
-	int rc;
+	struct iov_iter iter = {};
 
-	if (flags & MSG_SENDPAGE_NOTLAST)
-		flags |= MSG_MORE;
+	if (!tls_is_partially_sent_record(tls_ctx))
+		return;
 
 	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 
-	if (flags & MSG_OOB) {
-		rc = -EOPNOTSUPP;
-		goto out;
-	}
-
-	if (tls_ctx->zerocopy_sendfile) {
-		iter_offset.offset = offset;
-		rc = tls_push_data(sk, iter_offset, size,
-				   flags, TLS_RECORD_TYPE_DATA, page);
-		goto out;
+	if (tls_is_partially_sent_record(tls_ctx)) {
+		iov_iter_bvec(&iter, ITER_SOURCE, NULL, 0, 0);
+		tls_push_data(sk, &iter, 0, 0, TLS_RECORD_TYPE_DATA);
 	}
 
-	kaddr = kmap(page);
-	iov.iov_base = kaddr + offset;
-	iov.iov_len = size;
-	iov_iter_kvec(&msg_iter, ITER_SOURCE, &iov, 1, size);
-	iter_offset.msg_iter = &msg_iter;
-	rc = tls_push_data(sk, iter_offset, size, flags, TLS_RECORD_TYPE_DATA,
-			   NULL);
-	kunmap(page);
-
-out:
 	release_sock(sk);
 	mutex_unlock(&tls_ctx->tx_lock);
-	return rc;
 }
 
 struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
@@ -696,12 +671,10 @@ EXPORT_SYMBOL(tls_get_record);
 
 static int tls_device_push_pending_record(struct sock *sk, int flags)
 {
-	union tls_iter_offset iter;
-	struct iov_iter msg_iter;
+	struct iov_iter iter;
 
-	iov_iter_kvec(&msg_iter, ITER_SOURCE, NULL, 0, 0);
-	iter.msg_iter = &msg_iter;
-	return tls_push_data(sk, iter, 0, flags, TLS_RECORD_TYPE_DATA, NULL);
+	iov_iter_kvec(&iter, ITER_SOURCE, NULL, 0, 0);
+	return tls_push_data(sk, &iter, 0, flags, TLS_RECORD_TYPE_DATA);
 }
 
 void tls_device_write_space(struct sock *sk, struct tls_context *ctx)
@@ -1217,7 +1190,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 	tls_device_attach(ctx, sk, netdev);
 	up_read(&device_offload_lock);
 
-	/* following this assignment tls_is_sk_tx_device_offloaded
+	/* following this assignment tls_is_skb_tx_device_offloaded
 	 * will return true and the context might be accessed
 	 * by the netdev's xmit function.
 	 */
@@ -1370,7 +1343,7 @@ static int tls_device_down(struct net_device *netdev)
 
 	list_for_each_entry_safe(ctx, tmp, &list, list)	{
 		/* Stop offloaded TX and switch to the fallback.
-		 * tls_is_sk_tx_device_offloaded will return false.
+		 * tls_is_skb_tx_device_offloaded will return false.
 		 */
 		WRITE_ONCE(ctx->sk->sk_validate_xmit_skb, tls_validate_xmit_skb_sw);
 
@@ -1466,14 +1439,26 @@ int __init tls_device_init(void)
 {
 	int err;
 
-	destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0);
-	if (!destruct_wq)
+	dummy_page = alloc_page(GFP_KERNEL);
+	if (!dummy_page)
 		return -ENOMEM;
 
+	destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0);
+	if (!destruct_wq) {
+		err = -ENOMEM;
+		goto err_free_dummy;
+	}
+
 	err = register_netdevice_notifier(&tls_dev_notifier);
 	if (err)
-		destroy_workqueue(destruct_wq);
+		goto err_destroy_wq;
+
+	return 0;
 
+err_destroy_wq:
+	destroy_workqueue(destruct_wq);
+err_free_dummy:
+	put_page(dummy_page);
 	return err;
 }
 
@@ -1482,4 +1467,5 @@ void __exit tls_device_cleanup(void)
 	unregister_netdevice_notifier(&tls_dev_notifier);
 	destroy_workqueue(destruct_wq);
 	clean_acked_data_flush();
+	put_page(dummy_page);
 }
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 7fbb1d0b69b3..b28c5e296dfd 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -271,7 +271,7 @@ static int fill_sg_in(struct scatterlist *sg_in,
 		 * There is a corner case where the packet contains
 		 * both an acked and a non-acked record.
 		 * We currently don't handle that case and rely
-		 * on TCP to retranmit a packet that doesn't contain
+		 * on TCP to retransmit a packet that doesn't contain
 		 * already acked payload.
 		 */
 		if (!is_start_marker)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index f2e7302a4d96..4a8ee2f6badb 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -125,7 +125,10 @@ int tls_push_sg(struct sock *sk,
 		u16 first_offset,
 		int flags)
 {
-	int sendpage_flags = flags | MSG_SENDPAGE_NOTLAST;
+	struct bio_vec bvec;
+	struct msghdr msg = {
+		.msg_flags = MSG_SPLICE_PAGES | flags,
+	};
 	int ret = 0;
 	struct page *p;
 	size_t size;
@@ -134,16 +137,16 @@ int tls_push_sg(struct sock *sk,
 	size = sg->length - offset;
 	offset += sg->offset;
 
-	ctx->in_tcp_sendpages = true;
+	ctx->splicing_pages = true;
 	while (1) {
-		if (sg_is_last(sg))
-			sendpage_flags = flags;
-
 		/* is sending application-limited? */
 		tcp_rate_check_app_limited(sk);
 		p = sg_page(sg);
 retry:
-		ret = do_tcp_sendpages(sk, p, offset, size, sendpage_flags);
+		bvec_set_page(&bvec, p, size, offset);
+		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
+
+		ret = tcp_sendmsg_locked(sk, &msg, size);
 
 		if (ret != size) {
 			if (ret > 0) {
@@ -155,7 +158,7 @@ retry:
 			offset -= sg->offset;
 			ctx->partially_sent_offset = offset;
 			ctx->partially_sent_record = (void *)sg;
-			ctx->in_tcp_sendpages = false;
+			ctx->splicing_pages = false;
 			return ret;
 		}
 
@@ -169,7 +172,7 @@ retry:
 		size = sg->length;
 	}
 
-	ctx->in_tcp_sendpages = false;
+	ctx->splicing_pages = false;
 
 	return 0;
 }
@@ -247,11 +250,11 @@ static void tls_write_space(struct sock *sk)
 {
 	struct tls_context *ctx = tls_get_ctx(sk);
 
-	/* If in_tcp_sendpages call lower protocol write space handler
+	/* If splicing_pages call lower protocol write space handler
 	 * to ensure we wake up any waiting operations there. For example
-	 * if do_tcp_sendpages where to call sk_wait_event.
+	 * if splicing pages where to call sk_wait_event.
 	 */
-	if (ctx->in_tcp_sendpages) {
+	if (ctx->splicing_pages) {
 		ctx->sk_write_space(sk);
 		return;
 	}
@@ -352,6 +355,39 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 		tls_ctx_free(sk, ctx);
 }
 
+static __poll_t tls_sk_poll(struct file *file, struct socket *sock,
+			    struct poll_table_struct *wait)
+{
+	struct tls_sw_context_rx *ctx;
+	struct tls_context *tls_ctx;
+	struct sock *sk = sock->sk;
+	struct sk_psock *psock;
+	__poll_t mask = 0;
+	u8 shutdown;
+	int state;
+
+	mask = tcp_poll(file, sock, wait);
+
+	state = inet_sk_state_load(sk);
+	shutdown = READ_ONCE(sk->sk_shutdown);
+	if (unlikely(state != TCP_ESTABLISHED || shutdown & RCV_SHUTDOWN))
+		return mask;
+
+	tls_ctx = tls_get_ctx(sk);
+	ctx = tls_sw_ctx_rx(tls_ctx);
+	psock = sk_psock_get(sk);
+
+	if (skb_queue_empty_lockless(&ctx->rx_list) &&
+	    !tls_strp_msg_ready(ctx) &&
+	    sk_psock_queue_empty(psock))
+		mask &= ~(EPOLLIN | EPOLLRDNORM);
+
+	if (psock)
+		sk_psock_put(sk, psock);
+
+	return mask;
+}
+
 static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval,
 				  int __user *optlen, int tx)
 {
@@ -918,27 +954,26 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG]
 	ops[TLS_BASE][TLS_BASE] = *base;
 
 	ops[TLS_SW  ][TLS_BASE] = ops[TLS_BASE][TLS_BASE];
-	ops[TLS_SW  ][TLS_BASE].sendpage_locked	= tls_sw_sendpage_locked;
+	ops[TLS_SW  ][TLS_BASE].splice_eof	= tls_sw_splice_eof;
 
 	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_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;
 
 #ifdef CONFIG_TLS_DEVICE
 	ops[TLS_HW  ][TLS_BASE] = ops[TLS_BASE][TLS_BASE];
-	ops[TLS_HW  ][TLS_BASE].sendpage_locked	= NULL;
 
 	ops[TLS_HW  ][TLS_SW  ] = ops[TLS_BASE][TLS_SW  ];
-	ops[TLS_HW  ][TLS_SW  ].sendpage_locked	= NULL;
 
 	ops[TLS_BASE][TLS_HW  ] = ops[TLS_BASE][TLS_SW  ];
 
 	ops[TLS_SW  ][TLS_HW  ] = ops[TLS_SW  ][TLS_SW  ];
 
 	ops[TLS_HW  ][TLS_HW  ] = ops[TLS_HW  ][TLS_SW  ];
-	ops[TLS_HW  ][TLS_HW  ].sendpage_locked	= NULL;
 #endif
 #ifdef CONFIG_TLS_TOE
 	ops[TLS_HW_RECORD][TLS_HW_RECORD] = *base;
@@ -986,7 +1021,7 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
 
 	prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE];
 	prot[TLS_SW][TLS_BASE].sendmsg		= tls_sw_sendmsg;
-	prot[TLS_SW][TLS_BASE].sendpage		= tls_sw_sendpage;
+	prot[TLS_SW][TLS_BASE].splice_eof	= tls_sw_splice_eof;
 
 	prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE];
 	prot[TLS_BASE][TLS_SW].recvmsg		  = tls_sw_recvmsg;
@@ -1001,11 +1036,11 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
 #ifdef CONFIG_TLS_DEVICE
 	prot[TLS_HW][TLS_BASE] = prot[TLS_BASE][TLS_BASE];
 	prot[TLS_HW][TLS_BASE].sendmsg		= tls_device_sendmsg;
-	prot[TLS_HW][TLS_BASE].sendpage		= tls_device_sendpage;
+	prot[TLS_HW][TLS_BASE].splice_eof	= tls_device_splice_eof;
 
 	prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW];
 	prot[TLS_HW][TLS_SW].sendmsg		= tls_device_sendmsg;
-	prot[TLS_HW][TLS_SW].sendpage		= tls_device_sendpage;
+	prot[TLS_HW][TLS_SW].splice_eof		= tls_device_splice_eof;
 
 	prot[TLS_BASE][TLS_HW] = prot[TLS_BASE][TLS_SW];
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 1a53c8f481e9..e047abc60089 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -817,7 +817,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 	psock = sk_psock_get(sk);
 	if (!psock || !policy) {
 		err = tls_push_record(sk, flags, record_type);
-		if (err && sk->sk_err == EBADMSG) {
+		if (err && err != -EINPROGRESS && sk->sk_err == EBADMSG) {
 			*copied -= sk_msg_free(sk, msg);
 			tls_free_open_rec(sk);
 			err = -sk->sk_err;
@@ -846,7 +846,7 @@ more_data:
 	switch (psock->eval) {
 	case __SK_PASS:
 		err = tls_push_record(sk, flags, record_type);
-		if (err && sk->sk_err == EBADMSG) {
+		if (err && err != -EINPROGRESS && sk->sk_err == EBADMSG) {
 			*copied -= sk_msg_free(sk, msg);
 			tls_free_open_rec(sk);
 			err = -sk->sk_err;
@@ -931,7 +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);
@@ -954,15 +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) {
@@ -1020,6 +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;
 
@@ -1084,6 +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,
@@ -1151,157 +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