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:     netdev@vger.kernel.org
Cc:     David Howells <dhowells@redhat.com>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        Willem de Bruijn <willemdebruijn.kernel@gmail.com>,
        David Ahern <dsahern@kernel.org>,
        Matthew Wilcox <willy@infradead.org>,
        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>,
        linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-mm@kvack.org
Subject: [PATCH net-next v10 03/16] net: Add a function to splice pages into an skbuff for MSG_SPLICE_PAGES
Date:   Mon, 22 May 2023 13:11:12 +0100
Message-Id: <20230522121125.2595254-4-dhowells@redhat.com>
In-Reply-To: <20230522121125.2595254-1-dhowells@redhat.com>
References: <20230522121125.2595254-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Add a function to handle MSG_SPLICE_PAGES being passed internally to
sendmsg().  Pages are spliced into the given socket buffer if possible and
copied in if not (e.g. they're slab pages or have a zero refcount).

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Eric Dumazet <edumazet@google.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: David Ahern <dsahern@kernel.org>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Al Viro <viro@zeniv.linux.org.uk>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: netdev@vger.kernel.org
---

Notes:
    ver #8)
     - Order local variables in reverse xmas tree order.
     - Remove duplicate coalescence check.
     - Warn if sendpage_ok() fails.
    
    ver #7)
     - Export function.
     - Never copy data, return -EIO if sendpage_ok() returns false.

 include/linux/skbuff.h |  3 ++
 net/core/skbuff.c      | 88 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 91 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 15011408c47c..1b2ebf6113e0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -5097,5 +5097,8 @@ static inline void skb_mark_for_recycle(struct sk_buff *skb)
 #endif
 }
 
+ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
+			     ssize_t maxsize, gfp_t gfp);
+
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7f53dcb26ad3..f4a5b51aed22 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6892,3 +6892,91 @@ nodefer:	__kfree_skb(skb);
 	if (unlikely(kick) && !cmpxchg(&sd->defer_ipi_scheduled, 0, 1))
 		smp_call_function_single_async(cpu, &sd->defer_csd);
 }
+
+static void skb_splice_csum_page(struct sk_buff *skb, struct page *page,
+				 size_t offset, size_t len)
+{
+	const char *kaddr;
+	__wsum csum;
+
+	kaddr = kmap_local_page(page);
+	csum = csum_partial(kaddr + offset, len, 0);
+	kunmap_local(kaddr);
+	skb->csum = csum_block_add(skb->csum, csum, skb->len);
+}
+
+/**
+ * skb_splice_from_iter - Splice (or copy) pages to skbuff
+ * @skb: The buffer to add pages to
+ * @iter: Iterator representing the pages to be added
+ * @maxsize: Maximum amount of pages to be added
+ * @gfp: Allocation flags
+ *
+ * This is a common helper function for supporting MSG_SPLICE_PAGES.  It
+ * extracts pages from an iterator and adds them to the socket buffer if
+ * possible, copying them to fragments if not possible (such as if they're slab
+ * pages).
+ *
+ * Returns the amount of data spliced/copied or -EMSGSIZE if there's
+ * insufficient space in the buffer to transfer anything.
+ */
+ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
+			     ssize_t maxsize, gfp_t gfp)
+{
+	size_t frag_limit = READ_ONCE(sysctl_max_skb_frags);
+	struct page *pages[8], **ppages = pages;
+	ssize_t spliced = 0, ret = 0;
+	unsigned int i;
+
+	while (iter->count > 0) {
+		ssize_t space, nr;
+		size_t off, len;
+
+		ret = -EMSGSIZE;
+		space = frag_limit - skb_shinfo(skb)->nr_frags;
+		if (space < 0)
+			break;
+
+		/* We might be able to coalesce without increasing nr_frags */
+		nr = clamp_t(size_t, space, 1, ARRAY_SIZE(pages));
+
+		len = iov_iter_extract_pages(iter, &ppages, maxsize, nr, 0, &off);
+		if (len <= 0) {
+			ret = len ?: -EIO;
+			break;
+		}
+
+		i = 0;
+		do {
+			struct page *page = pages[i++];
+			size_t part = min_t(size_t, PAGE_SIZE - off, len);
+
+			ret = -EIO;
+			if (WARN_ON_ONCE(!sendpage_ok(page)))
+				goto out;
+
+			ret = skb_append_pagefrags(skb, page, off, part,
+						   frag_limit);
+			if (ret < 0) {
+				iov_iter_revert(iter, len);
+				goto out;
+			}
+
+			if (skb->ip_summed == CHECKSUM_NONE)
+				skb_splice_csum_page(skb, page, off, part);
+
+			off = 0;
+			spliced += part;
+			maxsize -= part;
+			len -= part;
+		} while (len > 0);
+
+		if (maxsize <= 0)
+			break;
+	}
+
+out:
+	skb_len_add(skb, spliced);
+	return spliced ?: ret;
+}
+EXPORT_SYMBOL(skb_splice_from_iter);