From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id ED15FC761AF for ; Fri, 31 Mar 2023 16:18:27 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233501AbjCaQSZ (ORCPT ); Fri, 31 Mar 2023 12:18:25 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43410 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233214AbjCaQRw (ORCPT ); Fri, 31 Mar 2023 12:17:52 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 633C922937 for ; Fri, 31 Mar 2023 09:11:57 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1680279089; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=14pAi6JHwU3C53h/ZQrPmmNB396J3kzB8Cmz3sg/vjY=; b=jPjcc3i1evQtTAfzlejbvELJyXK2x1P/+PmqqsAPppTlzdbex5aGg3RgdBvgEy73fqfNXE glt1gDYzcUPgvkYTnF2g60vEQ8LGL5woeNDlp0gW/HOCbCdMtYBf1PWA+AA5IKcYKodUZT rsWtxjSxHCey4Pgk+AkE2s0Z73mcn0U= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-186-Zs9E43zDOwakJiLhI1Mt6A-1; Fri, 31 Mar 2023 12:11:26 -0400 X-MC-Unique: Zs9E43zDOwakJiLhI1Mt6A-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.rdu2.redhat.com [10.11.54.6]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id A289F3C0F383; Fri, 31 Mar 2023 16:11:25 +0000 (UTC) Received: from warthog.procyon.org.uk (unknown [10.33.36.18]) by smtp.corp.redhat.com (Postfix) with ESMTP id 2D14E2166B33; Fri, 31 Mar 2023 16:11:23 +0000 (UTC) From: David Howells To: Matthew Wilcox , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni Cc: David Howells , Al Viro , Christoph Hellwig , Jens Axboe , Jeff Layton , Christian Brauner , Chuck Lever III , Linus Torvalds , netdev@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, Ilya Dryomov , Xiubo Li , ceph-devel@vger.kernel.org Subject: [PATCH v3 45/55] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage() Date: Fri, 31 Mar 2023 17:09:04 +0100 Message-Id: <20230331160914.1608208-46-dhowells@redhat.com> In-Reply-To: <20230331160914.1608208-1-dhowells@redhat.com> References: <20230331160914.1608208-1-dhowells@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Scanned-By: MIMEDefang 3.1 on 10.11.54.6 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Use sendmsg() and MSG_SPLICE_PAGES rather than sendpage in ceph when transmitting data. For the moment, this can only transmit one page at a time because of the architecture of net/ceph/, but if write_partial_message_data() can be given a bvec[] at a time by the iteration code, this would allow pages to be sent in a batch. Signed-off-by: David Howells cc: Ilya Dryomov cc: Xiubo Li cc: Jeff Layton cc: "David S. Miller" cc: Eric Dumazet cc: Jakub Kicinski cc: Paolo Abeni cc: Jens Axboe cc: Matthew Wilcox cc: ceph-devel@vger.kernel.org cc: netdev@vger.kernel.org --- net/ceph/messenger_v2.c | 89 +++++++++-------------------------------- 1 file changed, 18 insertions(+), 71 deletions(-) diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 301a991dc6a6..1637a0c21126 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -117,91 +117,38 @@ static int ceph_tcp_recv(struct ceph_connection *con) return ret; } -static int do_sendmsg(struct socket *sock, struct iov_iter *it) -{ - struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS }; - int ret; - - msg.msg_iter = *it; - while (iov_iter_count(it)) { - ret = sock_sendmsg(sock, &msg); - if (ret <= 0) { - if (ret == -EAGAIN) - ret = 0; - return ret; - } - - iov_iter_advance(it, ret); - } - - WARN_ON(msg_data_left(&msg)); - return 1; -} - -static int do_try_sendpage(struct socket *sock, struct iov_iter *it) -{ - struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS }; - struct bio_vec bv; - int ret; - - if (WARN_ON(!iov_iter_is_bvec(it))) - return -EINVAL; - - while (iov_iter_count(it)) { - /* iov_iter_iovec() for ITER_BVEC */ - bvec_set_page(&bv, it->bvec->bv_page, - min(iov_iter_count(it), - it->bvec->bv_len - it->iov_offset), - it->bvec->bv_offset + it->iov_offset); - - /* - * sendpage cannot properly handle pages with - * page_count == 0, we need to fall back to sendmsg if - * that's the case. - * - * Same goes for slab pages: skb_can_coalesce() allows - * coalescing neighboring slab objects into a single frag - * which triggers one of hardened usercopy checks. - */ - if (sendpage_ok(bv.bv_page)) { - ret = sock->ops->sendpage(sock, bv.bv_page, - bv.bv_offset, bv.bv_len, - CEPH_MSG_FLAGS); - } else { - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, bv.bv_len); - ret = sock_sendmsg(sock, &msg); - } - if (ret <= 0) { - if (ret == -EAGAIN) - ret = 0; - return ret; - } - - iov_iter_advance(it, ret); - } - - return 1; -} - /* * Write as much as possible. The socket is expected to be corked, * so we don't bother with MSG_MORE/MSG_SENDPAGE_NOTLAST here. * * Return: - * 1 - done, nothing (else) to write + * >0 - done, nothing (else) to write * 0 - socket is full, need to wait * <0 - error */ static int ceph_tcp_send(struct ceph_connection *con) { + struct msghdr msg = { + .msg_iter = con->v2.out_iter, + .msg_flags = CEPH_MSG_FLAGS, + }; int ret; + if (WARN_ON(!iov_iter_is_bvec(&con->v2.out_iter))) + return -EINVAL; + + if (con->v2.out_iter_sendpage) + msg.msg_flags |= MSG_SPLICE_PAGES; + dout("%s con %p have %zu try_sendpage %d\n", __func__, con, iov_iter_count(&con->v2.out_iter), con->v2.out_iter_sendpage); - if (con->v2.out_iter_sendpage) - ret = do_try_sendpage(con->sock, &con->v2.out_iter); - else - ret = do_sendmsg(con->sock, &con->v2.out_iter); + + ret = sock_sendmsg(con->sock, &msg); + if (ret > 0) + iov_iter_advance(&con->v2.out_iter, ret); + else if (ret == -EAGAIN) + ret = 0; + dout("%s con %p ret %d left %zu\n", __func__, con, ret, iov_iter_count(&con->v2.out_iter)); return ret;