Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   David Howells <dhowells@redhat.com>
To:     Matthew Wilcox <willy@infradead.org>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>
Cc:     David Howells <dhowells@redhat.com>,
        Al Viro <viro@zeniv.linux.org.uk>,
        Christoph Hellwig <hch@infradead.org>,
        Jens Axboe <axboe@kernel.dk>, Jeff Layton <jlayton@kernel.org>,
        Christian Brauner <brauner@kernel.org>,
        Chuck Lever III <chuck.lever@oracle.com>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        netdev@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [RFC PATCH v2 20/48] af_unix: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data
Date:   Wed, 29 Mar 2023 15:13:26 +0100
Message-Id: <20230329141354.516864-21-dhowells@redhat.com>
In-Reply-To: <20230329141354.516864-1-dhowells@redhat.com>
References: <20230329141354.516864-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

If sendmsg() with MSG_SPLICE_PAGES encounters a page that shouldn't be
spliced - a slab page, for instance, or one with a zero count - make
unix_extract_bvec_to_skb() copy it.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: netdev@vger.kernel.org
---
 net/unix/af_unix.c | 44 +++++++++++++++++++++++++++++++++-----------
 1 file changed, 33 insertions(+), 11 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 84a0d97f1aa4..b4b27a652ef0 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2154,12 +2154,12 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 /*
  * Extract pages from an iterator and add them to the socket buffer.
  */
-static ssize_t unix_extract_bvec_to_skb(struct sk_buff *skb,
-					struct iov_iter *iter, ssize_t maxsize)
+static ssize_t unix_extract_bvec_to_skb(struct sk_buff *skb, struct iov_iter *iter,
+					ssize_t maxsize, gfp_t gfp)
 {
 	struct page *pages[8], **ppages = pages;
 	unsigned int i, nr;
-	ssize_t ret = 0;
+	ssize_t spliced = 0, ret = 0;
 
 	while (iter->count > 0) {
 		size_t off, len;
@@ -2171,31 +2171,52 @@ static ssize_t unix_extract_bvec_to_skb(struct sk_buff *skb,
 
 		len = iov_iter_extract_pages(iter, &ppages, maxsize, nr, 0, &off);
 		if (len <= 0) {
-			if (!ret)
-				ret = len ?: -EIO;
+			ret = len ?: -EIO;
 			break;
 		}
 
 		i = 0;
 		do {
+			struct page *page = pages[i++];
 			size_t part = min(PAGE_SIZE - off, len);
+			bool put = false;
+
+			if (!sendpage_ok(page)) {
+				const void *p = kmap_local_page(page);
+				void *q;
+
+				q = page_frag_memdup(NULL, p + off, part, gfp,
+						     ULONG_MAX);
+				kunmap_local(p);
+				if (!q) {
+					iov_iter_revert(iter, len);
+					ret = -ENOMEM;
+					goto out;
+				}
+				page = virt_to_page(q);
+				off = offset_in_page(q);
+				put = true;
+			}
 
-			if (skb_append_pagefrags(skb, pages[i++], off, part) < 0) {
-				if (!ret)
-					ret = -EMSGSIZE;
+			ret = skb_append_pagefrags(skb, page, off, part);
+			if (put)
+				put_page(page);
+			if (ret < 0) {
+				iov_iter_revert(iter, len);
 				goto out;
 			}
 			off = 0;
-			ret += part;
+			spliced += part;
 			maxsize -= part;
 			len -= part;
 		} while (len > 0);
+
 		if (maxsize <= 0)
 			break;
 	}
 
 out:
-	return ret;
+	return spliced ?: ret;
 }
 
 static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
@@ -2272,7 +2293,8 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		fds_sent = true;
 
 		if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {
-			size = unix_extract_bvec_to_skb(skb, &msg->msg_iter, size);
+			size = unix_extract_bvec_to_skb(skb, &msg->msg_iter, size,
+							sk->sk_allocation);
 			skb->data_len += size;
 			skb->len += size;
 			skb->truesize += size;