Make TLS's sendmsg() support MSG_SPLICE_PAGES. This causes pages to be
spliced from the source iterator if possible and copied the data if not.
This allows ->sendpage() to be replaced by something that can handle
multiple multipage folios in a single transaction.
Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
cc: Chuck Lever <chuck.lever@xxxxxxxxxx>
cc: Boris Pismenny <borisp@xxxxxxxxxx>
cc: John Fastabend <john.fastabend@xxxxxxxxx>
cc: Jakub Kicinski <kuba@xxxxxxxxxx>
cc: Eric Dumazet <edumazet@xxxxxxxxxx>
cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
cc: Paolo Abeni <pabeni@xxxxxxxxxx>
cc: Jens Axboe <axboe@xxxxxxxxx>
cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
cc: netdev@xxxxxxxxxxxxxxx
---
net/tls/tls_sw.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 56 insertions(+), 1 deletion(-)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 782d3701b86f..ce0c289e68ca 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -929,6 +929,49 @@ static int tls_sw_push_pending_record(struct sock *sk, int flags)
&copied, flags);
}
+static int rls_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, **pages = &page;
+
+ do {
+ ssize_t part;
+ size_t off;
+ bool put = false;
+
+ part = iov_iter_extract_pages(&msg->msg_iter, &pages,
+ try_to_copy, 1, 0, &off);
+ if (part <= 0)
+ return part ?: -EIO;
+
+ if (!sendpage_ok(page)) {
+ const void *p = kmap_local_page(page);
+ void *q;
+
+ q = page_frag_memdup(NULL, p + off, part,
+ sk->sk_allocation, ULONG_MAX);
+ kunmap_local(p);
+ if (!q) {
+ iov_iter_revert(&msg->msg_iter, part);
+ return -ENOMEM;
+ }
+ page = virt_to_page(q);
+ off = offset_in_page(q);
+ put = true;
+ }
+
+ sk_msg_page_add(msg_pl, page, part, off);
+ sk_mem_charge(sk, part);
+ if (put)
+ put_page(page);
+ *copied += part;
+ try_to_copy -= part;
+ } while (try_to_copy && !sk_msg_full(msg_pl));
+
+ return 0;
+}
+
int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
@@ -1016,6 +1059,17 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
full_record = true;
}
+ if (try_to_copy && (msg->msg_flags & MSG_SPLICE_PAGES)) {
+ ret = rls_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;
@@ -1078,8 +1132,9 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
/* Open records defined only if successfully copied, otherwise
* we would trim the sg but not reset the open record frags.
*/
- tls_ctx->pending_open_record_frags = true;
copied += try_to_copy;
+copied:
+ tls_ctx->pending_open_record_frags = true;
if (full_record || eor) {
ret = bpf_exec_tx_verdict(msg_pl, sk, full_record,
record_type, &copied,
