Return-Path: Received: from mail-io0-f194.google.com ([209.85.223.194]:34742 "EHLO mail-io0-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752606AbdDIRGI (ORCPT ); Sun, 9 Apr 2017 13:06:08 -0400 Subject: [PATCH v3 04/14] svcrdma: Add helper to save pages under I/O From: Chuck Lever To: bfields@fieldses.org Cc: linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org Date: Sun, 09 Apr 2017 13:06:00 -0400 Message-ID: <20170409170600.15073.62156.stgit@klimt.1015granger.net> In-Reply-To: <20170409163820.15073.43257.stgit@klimt.1015granger.net> References: <20170409163820.15073.43257.stgit@klimt.1015granger.net> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Sender: linux-nfs-owner@vger.kernel.org List-ID: Clean up: extract the logic to save pages under I/O into a helper to add a big documenting comment without adding clutter in the send path. This is a refactoring change only. Signed-off-by: Chuck Lever Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig --- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index a7dc71d..2798f3e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -478,6 +478,23 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, return -EIO; } +/* The svc_rqst and all resources it owns are released as soon as + * svc_rdma_sendto returns. Transfer pages under I/O to the ctxt + * so they are released by the Send completion handler. + */ +static void svc_rdma_save_io_pages(struct svc_rqst *rqstp, + struct svc_rdma_op_ctxt *ctxt) +{ + int i, pages = rqstp->rq_next_page - rqstp->rq_respages; + + ctxt->count += pages; + for (i = 0; i < pages; i++) { + ctxt->pages[i + 1] = rqstp->rq_respages[i]; + rqstp->rq_respages[i] = NULL; + } + rqstp->rq_next_page = rqstp->rq_respages + 1; +} + /** * svc_rdma_post_send_wr - Set up and post one Send Work Request * @rdma: controlling transport @@ -543,8 +560,6 @@ static int send_reply(struct svcxprt_rdma *rdma, u32 xdr_off; int sge_no; int sge_bytes; - int page_no; - int pages; int ret = -EIO; /* Prepare the context */ @@ -587,17 +602,7 @@ static int send_reply(struct svcxprt_rdma *rdma, goto err; } - /* Save all respages in the ctxt and remove them from the - * respages array. They are our pages until the I/O - * completes. - */ - pages = rqstp->rq_next_page - rqstp->rq_respages; - for (page_no = 0; page_no < pages; page_no++) { - ctxt->pages[page_no+1] = rqstp->rq_respages[page_no]; - ctxt->count++; - rqstp->rq_respages[page_no] = NULL; - } - rqstp->rq_next_page = rqstp->rq_respages + 1; + svc_rdma_save_io_pages(rqstp, ctxt); if (sge_no > rdma->sc_max_sge) { pr_err("svcrdma: Too many sges (%d)\n", sge_no);