> On Mar 30, 2023, at 9:16 AM, David Howells <dhowells@xxxxxxxxxx> wrote:
>
> David Howells <dhowells@xxxxxxxxxx> wrote:
>
>> Chuck Lever III <chuck.lever@xxxxxxxxxx> wrote:
>>
>>> Simply replacing the kernel_sendpage() loop would be a
>>> straightforward change and easy to evaluate and test, and
>>> I'd welcome that without hesitation.
>>
>> How about the attached for a first phase?
>>
>> It does three sendmsgs, one for the marker + header, one for the body and one
>> for the tail.
>
> ... And this as a second phase.
>
> David
> ---
> sunrpc: Allow xdr->bvec[] to be extended to do a single sendmsg
>
> Allow xdr->bvec[] to be extended and insert the marker, the header and the
> tail into it so that a single sendmsg() can be used to transmit the message.
Don't. Just change svc_tcp_send_kvec() to use sock_sendmsg, and
leave the marker alone for now, please.
Let's focus on replacing kernel_sendpage() in this series and
leave the deeper clean-ups for another time.
> I wonder if it would be possible to insert the marker at the beginning of the
> head buffer.
That's the way it used to work. The reason we don't do that is
because each transport has its own record marking mechanism.
UDP has nothing, since each RPC message is encapsulated in a
single datagram. RDMA has a full XDR-encoded header which
contains the location of data chunks to be moved via RDMA.
> Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
> cc: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
> cc: Anna Schumaker <anna@xxxxxxxxxx>
> cc: Chuck Lever <chuck.lever@xxxxxxxxxx>
> cc: Jeff Layton <jlayton@xxxxxxxxxx>
> cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
> cc: Eric Dumazet <edumazet@xxxxxxxxxx>
> cc: Jakub Kicinski <kuba@xxxxxxxxxx>
> cc: Paolo Abeni <pabeni@xxxxxxxxxx>
> cc: Jens Axboe <axboe@xxxxxxxxx>
> cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
> cc: linux-nfs@xxxxxxxxxxxxxxx
> cc: netdev@xxxxxxxxxxxxxxx
> ---
> include/linux/sunrpc/xdr.h | 2 -
> net/sunrpc/svcsock.c | 46 ++++++++++++++-------------------------------
> net/sunrpc/xdr.c | 19 ++++++++++--------
> net/sunrpc/xprtsock.c | 6 ++---
> 4 files changed, 30 insertions(+), 43 deletions(-)
>
> diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
> index 72014c9216fc..c74ea483228b 100644
> --- a/include/linux/sunrpc/xdr.h
> +++ b/include/linux/sunrpc/xdr.h
> @@ -137,7 +137,7 @@ void xdr_inline_pages(struct xdr_buf *, unsigned int,
> struct page **, unsigned int, unsigned int);
> void xdr_terminate_string(const struct xdr_buf *, const u32);
> size_t xdr_buf_pagecount(const struct xdr_buf *buf);
> -int xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp);
> +int xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp, unsigned int head, unsigned int tail);
> void xdr_free_bvec(struct xdr_buf *buf);
>
> static inline __be32 *xdr_encode_array(__be32 *p, const void *s, unsigned int len)
> diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
> index 14efcc08c6f8..e55761fe1ccf 100644
> --- a/net/sunrpc/svcsock.c
> +++ b/net/sunrpc/svcsock.c
> @@ -569,7 +569,7 @@ static int svc_udp_sendto(struct svc_rqst *rqstp)
> if (svc_xprt_is_dead(xprt))
> goto out_notconn;
>
> - err = xdr_alloc_bvec(xdr, GFP_KERNEL);
> + err = xdr_alloc_bvec(xdr, GFP_KERNEL, 0, 0);
> if (err < 0)
> goto out_unlock;
>
> @@ -1073,45 +1073,29 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr,
> {
> const struct kvec *head = xdr->head;
> const struct kvec *tail = xdr->tail;
> - struct kvec kv[2];
> - struct msghdr msg = { .msg_flags = MSG_SPLICE_PAGES | MSG_MORE, };
> - size_t sent;
> + struct msghdr msg = { .msg_flags = MSG_SPLICE_PAGES, };
> + size_t n;
> int ret;
>
> *sentp = 0;
> - ret = xdr_alloc_bvec(xdr, GFP_KERNEL);
> + ret = xdr_alloc_bvec(xdr, GFP_KERNEL, 2, 1);
> if (ret < 0)
> return ret;
>
> - kv[0].iov_base = ▮
> - kv[0].iov_len = sizeof(marker);
> - kv[1] = *head;
> - iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, kv, 2, sizeof(marker) + head->iov_len);
> + n = 2 + xdr_buf_pagecount(xdr);
> + bvec_set_virt(&xdr->bvec[0], &marker, sizeof(marker));
> + bvec_set_virt(&xdr->bvec[1], head->iov_base, head->iov_len);
> + bvec_set_virt(&xdr->bvec[n], tail->iov_base, tail->iov_len);
> + if (tail->iov_len)
> + n++;
> + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, xdr->bvec, n,
> + sizeof(marker) + xdr->len);
> ret = sock_sendmsg(sock, &msg);
> if (ret < 0)
> return ret;
> - sent = ret;
> -
> - if (!tail->iov_len)
> - msg.msg_flags &= ~MSG_MORE;
> - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, xdr->bvec,
> - xdr_buf_pagecount(xdr), xdr->page_len);
> - ret = sock_sendmsg(sock, &msg);
> - if (ret < 0)
> - return ret;
> - sent += ret;
> -
> - if (tail->iov_len) {
> - msg.msg_flags &= ~MSG_MORE;
> - iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, tail, 1, tail->iov_len);
> - ret = sock_sendmsg(sock, &msg);
> - if (ret < 0)
> - return ret;
> - sent += ret;
> - }
> - if (sent > 0)
> - *sentp = sent;
> - if (sent != sizeof(marker) + xdr->len)
> + if (ret > 0)
> + *sentp = ret;
> + if (ret != sizeof(marker) + xdr->len)
> return -EAGAIN;
> return 0;
> }
> diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
> index 36835b2f5446..695821963849 100644
> --- a/net/sunrpc/xdr.c
> +++ b/net/sunrpc/xdr.c
> @@ -141,18 +141,21 @@ size_t xdr_buf_pagecount(const struct xdr_buf *buf)
> }
>
> int
> -xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp)
> +xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp, unsigned int head, unsigned int tail)
> {
> - size_t i, n = xdr_buf_pagecount(buf);
> + size_t i, j = 0, n = xdr_buf_pagecount(buf);
>
> - if (n != 0 && buf->bvec == NULL) {
> - buf->bvec = kmalloc_array(n, sizeof(buf->bvec[0]), gfp);
> + if (head + n + tail != 0 && buf->bvec == NULL) {
> + buf->bvec = kmalloc_array(head + n + tail,
> + sizeof(buf->bvec[0]), gfp);
> if (!buf->bvec)
> return -ENOMEM;
> - for (i = 0; i < n; i++) {
> - bvec_set_page(&buf->bvec[i], buf->pages[i], PAGE_SIZE,
> - 0);
> - }
> + for (i = 0; i < head; i++)
> + bvec_set_page(&buf->bvec[j++], NULL, 0, 0);
> + for (i = 0; i < n; i++)
> + bvec_set_page(&buf->bvec[j++], buf->pages[i], PAGE_SIZE, 0);
> + for (i = 0; i < tail; i++)
> + bvec_set_page(&buf->bvec[j++], NULL, 0, 0);
> }
> return 0;
> }
> diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
> index adcbedc244d6..fdf67e84b1c7 100644
> --- a/net/sunrpc/xprtsock.c
> +++ b/net/sunrpc/xprtsock.c
> @@ -825,7 +825,7 @@ static int xs_stream_nospace(struct rpc_rqst *req, bool vm_wait)
>
> static int xs_stream_prepare_request(struct rpc_rqst *req, struct xdr_buf *buf)
> {
> - return xdr_alloc_bvec(buf, rpc_task_gfp_mask());
> + return xdr_alloc_bvec(buf, rpc_task_gfp_mask(), 0, 0);
> }
>
> /*
> @@ -954,7 +954,7 @@ static int xs_udp_send_request(struct rpc_rqst *req)
> if (!xprt_request_get_cong(xprt, req))
> return -EBADSLT;
>
> - status = xdr_alloc_bvec(xdr, rpc_task_gfp_mask());
> + status = xdr_alloc_bvec(xdr, rpc_task_gfp_mask(), 0, 0);
> if (status < 0)
> return status;
> req->rq_xtime = ktime_get();
> @@ -2591,7 +2591,7 @@ static int bc_sendto(struct rpc_rqst *req)
> int err;
>
> req->rq_xtime = ktime_get();
> - err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask());
> + err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask(), 0, 0);
> if (err < 0)
> return err;
> err = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, marker, &sent);
>
--
Chuck Lever
