linux-kernel - [PATCH v3 31/55] chelsio: Support MSG_SPLICE

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20230331160914.1608208-32-dhowells@redhat.com>
Date:   Fri, 31 Mar 2023 17:08:50 +0100
From:   David Howells <dhowells@...hat.com>
To:     Matthew Wilcox <willy@...radead.org>,
        "David S. Miller" <davem@...emloft.net>,
        Eric Dumazet <edumazet@...gle.com>,
        Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>
Cc:     David Howells <dhowells@...hat.com>,
        Al Viro <viro@...iv.linux.org.uk>,
        Christoph Hellwig <hch@...radead.org>,
        Jens Axboe <axboe@...nel.dk>, Jeff Layton <jlayton@...nel.org>,
        Christian Brauner <brauner@...nel.org>,
        Chuck Lever III <chuck.lever@...cle.com>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        netdev@...r.kernel.org, linux-fsdevel@...r.kernel.org,
        linux-kernel@...r.kernel.org, linux-mm@...ck.org,
        Ayush Sawal <ayush.sawal@...lsio.com>
Subject: [PATCH v3 31/55] chelsio: Support MSG_SPLICE_PAGES

Make Chelsio's TLS offload sendmsg() support MSG_SPLICE_PAGES, splicing in
pages from the source iterator if possible and copying the data in
otherwise.

This allows ->sendpage() to be replaced by something that can handle
multiple multipage folios in a single transaction.

Signed-off-by: David Howells <dhowells@...hat.com>
cc: Ayush Sawal <ayush.sawal@...lsio.com>
cc: "David S. Miller" <davem@...emloft.net>
cc: Eric Dumazet <edumazet@...gle.com>
cc: Jakub Kicinski <kuba@...nel.org>
cc: Paolo Abeni <pabeni@...hat.com>
cc: Jens Axboe <axboe@...nel.dk>
cc: Matthew Wilcox <willy@...radead.org>
cc: netdev@...r.kernel.org
---
 .../chelsio/inline_crypto/chtls/chtls_io.c    | 60 ++++++++++++++++++-
 1 file changed, 59 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
index ae6b17b96bf1..ca3daf5df95c 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
@@ -1092,7 +1092,65 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		if (copy > size)
 			copy = size;
 
-		if (skb_tailroom(skb) > 0) {
+		if (msg->msg_flags & MSG_SPLICE_PAGES) {
+			struct page *page, **pages = &page;
+			ssize_t part;
+			size_t off, spliced = 0;
+			bool put = false;
+			int i;
+
+			do {
+				i = skb_shinfo(skb)->nr_frags;
+				part = iov_iter_extract_pages(&msg->msg_iter, &pages,
+							      copy - spliced, 1, 0, &off);
+				if (part <= 0) {
+					err = part ?: -EIO;
+					goto do_fault;
+				}
+
+				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;
+				}
+
+				if (skb_can_coalesce(skb, i, page, off)) {
+					skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], part);
+					spliced += part;
+					if (put)
+						put_page(page);
+				} else if (i < MAX_SKB_FRAGS) {
+					if (!put)
+						get_page(page);
+					skb_fill_page_desc(skb, i, page, off, spliced);
+					spliced += part;
+					put = false;
+				} else {
+					if (put)
+						put_page(page);
+					if (!spliced)
+						goto new_buf;
+					break;
+				}
+			} while (spliced < copy);
+
+			copy = spliced;
+			skb->len += copy;
+			skb->data_len += copy;
+			skb->truesize += copy;
+			sk->sk_wmem_queued += copy;
+			
+		} else if (skb_tailroom(skb) > 0) {
 			copy = min(copy, skb_tailroom(skb));
 			if (is_tls_tx(csk))
 				copy = min_t(int, copy, csk->tlshws.txleft);