From:   Pavel Begunkov <asml.silence@gmail.com>
To:     io-uring@vger.kernel.org, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org
Cc:     Jakub Kicinski <kuba@kernel.org>,
        Jonathan Lemon <jonathan.lemon@gmail.com>,
        "David S . Miller" <davem@davemloft.net>,
        Willem de Bruijn <willemb@google.com>,
        Eric Dumazet <edumazet@google.com>,
        Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>,
        David Ahern <dsahern@kernel.org>, Jens Axboe <axboe@kernel.dk>,
        Pavel Begunkov <asml.silence@gmail.com>
Subject: [RFC 04/12] net: add zerocopy_sg_from_iter for bvec
Date:   Tue, 30 Nov 2021 15:18:52 +0000
Message-Id: <0ee5fc538d3badecb15d7e33fd8e204328d54776.1638282789.git.asml.silence@gmail.com>
In-Reply-To: <cover.1638282789.git.asml.silence@gmail.com>
References: <cover.1638282789.git.asml.silence@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Add a separate path for bvec iterators in __zerocopy_sg_from_iter, first
it's quite faster but also will be needed to optimise out
get/put_page()

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 net/core/datagram.c | 54 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index ee290776c661..e00f7e0a7a0a 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -616,11 +616,65 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 }
 EXPORT_SYMBOL(skb_copy_datagram_from_iter);
 
+static int __zerocopy_sg_from_bvec(struct sock *sk, struct sk_buff *skb,
+				   struct iov_iter *from, size_t length)
+{
+	int ret, frag = skb_shinfo(skb)->nr_frags;
+	struct bvec_iter bi;
+	struct bio_vec v;
+	ssize_t copied = 0;
+	unsigned long truesize = 0;
+
+	bi.bi_size = min(from->count, length);
+	bi.bi_bvec_done = from->iov_offset;
+	bi.bi_idx = 0;
+
+	while (bi.bi_size) {
+		if (frag == MAX_SKB_FRAGS) {
+			ret = -EMSGSIZE;
+			goto out;
+		}
+
+		/*
+		 * TODO: ignore compound pages for now, all bvec from io_uring
+		 * are within boundaries of a single page.
+		 */
+		v = mp_bvec_iter_bvec(from->bvec, bi);
+		copied += v.bv_len;
+		truesize += PAGE_ALIGN(v.bv_len + v.bv_offset);
+		get_page(v.bv_page);
+		skb_fill_page_desc(skb, frag++, v.bv_page, v.bv_offset, v.bv_len);
+		bvec_iter_advance_single(from->bvec, &bi, v.bv_len);
+	}
+	ret = 0;
+out:
+	skb->data_len += copied;
+	skb->len += copied;
+	skb->truesize += truesize;
+
+	if (sk && sk->sk_type == SOCK_STREAM) {
+		sk_wmem_queued_add(sk, truesize);
+		if (!skb_zcopy_pure(skb))
+			sk_mem_charge(sk, truesize);
+	} else {
+		refcount_add(truesize, &skb->sk->sk_wmem_alloc);
+	}
+
+	from->bvec += bi.bi_idx;
+	from->nr_segs -= bi.bi_idx;
+	from->count = bi.bi_size;
+	from->iov_offset = bi.bi_bvec_done;
+	return ret;
+}
+
 int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
 			    struct iov_iter *from, size_t length)
 {
 	int frag = skb_shinfo(skb)->nr_frags;
 
+	if (iov_iter_is_bvec(from))
+		return __zerocopy_sg_from_bvec(sk, skb, from, length);
+
 	while (length && iov_iter_count(from)) {
 		struct page *pages[MAX_SKB_FRAGS];
 		struct page *last_head = NULL;
-- 
2.34.0