rds: zerocopy Tx support.

If the MSG_ZEROCOPY flag is specified with rds_sendmsg(), and,
if the SO_ZEROCOPY socket option has been set on the PF_RDS socket,
application pages sent down with rds_sendmsg() are pinned.

The pinning uses the accounting infrastructure added by
Commit a91dbff551a6 ("sock: ulimit on MSG_ZEROCOPY pages")

The payload bytes in the message may not be modified for the
duration that the message has been pinned. A multi-threaded
application using this infrastructure may thus need to be notified
about send-completion so that it can free/reuse the buffers
passed to rds_sendmsg(). Notification of send-completion will
identify each message-buffer by a cookie that the application
must specify as ancillary data to rds_sendmsg().
The ancillary data in this case has cmsg_level == SOL_RDS
and cmsg_type == RDS_CMSG_ZCOPY_COOKIE.

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 50 insertions, 1 deletions

diff --git a/net/rds/message.c b/net/rds/message.c
index bf1a656b198a..651834513481 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -341,12 +341,14 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in
 	return rm;
 }
 
-int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from)
+int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from,
+			       bool zcopy)
 {
 	unsigned long to_copy, nbytes;
 	unsigned long sg_off;
 	struct scatterlist *sg;
 	int ret = 0;
+	int length = iov_iter_count(from);
 
 	rm->m_inc.i_hdr.h_len = cpu_to_be32(iov_iter_count(from));
 
@@ -356,6 +358,53 @@ int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from)
 	sg = rm->data.op_sg;
 	sg_off = 0; /* Dear gcc, sg->page will be null from kzalloc. */
 
+	if (zcopy) {
+		int total_copied = 0;
+		struct sk_buff *skb;
+
+		skb = alloc_skb(SO_EE_ORIGIN_MAX_ZCOOKIES * sizeof(u32),
+				GFP_KERNEL);
+		if (!skb)
+			return -ENOMEM;
+		rm->data.op_mmp_znotifier = RDS_ZCOPY_SKB(skb);
+		if (mm_account_pinned_pages(&rm->data.op_mmp_znotifier->z_mmp,
+					    length)) {
+			ret = -ENOMEM;
+			goto err;
+		}
+		while (iov_iter_count(from)) {
+			struct page *pages;
+			size_t start;
+			ssize_t copied;
+
+			copied = iov_iter_get_pages(from, &pages, PAGE_SIZE,
+						    1, &start);
+			if (copied < 0) {
+				struct mmpin *mmp;
+				int i;
+
+				for (i = 0; i < rm->data.op_nents; i++)
+					put_page(sg_page(&rm->data.op_sg[i]));
+				mmp = &rm->data.op_mmp_znotifier->z_mmp;
+				mm_unaccount_pinned_pages(mmp);
+				ret = -EFAULT;
+				goto err;
+			}
+			total_copied += copied;
+			iov_iter_advance(from, copied);
+			length -= copied;
+			sg_set_page(sg, pages, copied, start);
+			rm->data.op_nents++;
+			sg++;
+		}
+		WARN_ON_ONCE(length != 0);
+		return ret;
+err:
+		consume_skb(skb);
+		rm->data.op_mmp_znotifier = NULL;
+		return ret;
+	} /* zcopy */
+
 	while (iov_iter_count(from)) {
 		if (!sg_page(sg)) {
 			ret = rds_page_remainder_alloc(sg, iov_iter_count(from),