From patchwork Thu Aug 3 18:19:44 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Logan Gunthorpe X-Patchwork-Id: 9879669 X-Patchwork-Delegate: bhelgaas@google.com Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id A87C560360 for ; Thu, 3 Aug 2017 18:24:32 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id A5A35288FC for ; Thu, 3 Aug 2017 18:24:32 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 9909E2891E; Thu, 3 Aug 2017 18:24:32 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 24084288FC for ; Thu, 3 Aug 2017 18:24:32 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752031AbdHCSYa (ORCPT ); Thu, 3 Aug 2017 14:24:30 -0400 Received: from ale.deltatee.com ([207.54.116.67]:41529 "EHLO ale.deltatee.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751600AbdHCSUC (ORCPT ); Thu, 3 Aug 2017 14:20:02 -0400 Received: from cgy1-donard.priv.deltatee.com ([172.16.1.31]) by ale.deltatee.com with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.84_2) (envelope-from ) id 1ddKis-0001H1-Qo; Thu, 03 Aug 2017 12:19:52 -0600 Received: from gunthorp by cgy1-donard.priv.deltatee.com with local (Exim 4.89) (envelope-from ) id 1ddKiz-00016A-Sd; Thu, 03 Aug 2017 12:19:57 -0600 From: Logan Gunthorpe To: linux-ntb@googlegroups.com, linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org Cc: Jon Mason , Dave Jiang , Allen Hubbe , Bjorn Helgaas , Greg Kroah-Hartman , Kurt Schwemmer , Stephen Bates , Serge Semin , Logan Gunthorpe Date: Thu, 3 Aug 2017 12:19:44 -0600 Message-Id: <20170803181954.4154-6-logang@deltatee.com> X-Mailer: git-send-email 2.11.0 In-Reply-To: <20170803181954.4154-1-logang@deltatee.com> References: <20170803181954.4154-1-logang@deltatee.com> X-SA-Exim-Connect-IP: 172.16.1.31 X-SA-Exim-Rcpt-To: linux-ntb@googlegroups.com, linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org, jdmason@kudzu.us, dave.jiang@intel.com, Allen.Hubbe@emc.com, bhelgaas@google.com, gregkh@linuxfoundation.org, kurt.schwemmer@microsemi.com, sbates@raithlin.com, fancer.lancer@gmail.com, logang@deltatee.com X-SA-Exim-Mail-From: gunthorp@deltatee.com Subject: [PATCH v4 05/15] NTB: Ensure ntb_mw_get_align() is only called when the link is up X-SA-Exim-Version: 4.2.1 (built Mon, 26 Dec 2011 16:24:06 +0000) X-SA-Exim-Scanned: Yes (on ale.deltatee.com) Sender: linux-pci-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-pci@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP With Switchtec hardware it's impossible to get the alignment parameters for a peer's memory window until the peer's driver has configured its windows. Strictly speaking, the link doesn't have to be up for this, but the link being up is the only way the client can tell that the other side has been configured. This patch converts ntb_transport and ntb_perf to use this function after the link goes up. This simplifies these clients slightly because they no longer have to store the alignment parameters. It also tweaks ntb_tool so that peer_mw_trans will print zero if it is run before the link goes up. Signed-off-by: Logan Gunthorpe Acked-by: Allen Hubbe --- drivers/ntb/ntb_transport.c | 20 ++++++++++---------- drivers/ntb/test/ntb_perf.c | 18 +++++++++--------- drivers/ntb/test/ntb_tool.c | 6 +++--- 3 files changed, 22 insertions(+), 22 deletions(-) diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index f58d8e305323..045e3dd4750e 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -191,8 +191,6 @@ struct ntb_transport_qp { struct ntb_transport_mw { phys_addr_t phys_addr; resource_size_t phys_size; - resource_size_t xlat_align; - resource_size_t xlat_align_size; void __iomem *vbase; size_t xlat_size; size_t buff_size; @@ -687,13 +685,20 @@ static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw, struct ntb_transport_mw *mw = &nt->mw_vec[num_mw]; struct pci_dev *pdev = nt->ndev->pdev; size_t xlat_size, buff_size; + resource_size_t xlat_align; + resource_size_t xlat_align_size; int rc; if (!size) return -EINVAL; - xlat_size = round_up(size, mw->xlat_align_size); - buff_size = round_up(size, mw->xlat_align); + rc = ntb_mw_get_align(nt->ndev, PIDX, num_mw, &xlat_align, + &xlat_align_size, NULL); + if (rc) + return rc; + + xlat_size = round_up(size, xlat_align_size); + buff_size = round_up(size, xlat_align); /* No need to re-setup */ if (mw->xlat_size == xlat_size) @@ -722,7 +727,7 @@ static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw, * is a requirement of the hardware. It is recommended to setup CMA * for BAR sizes equal or greater than 4MB. */ - if (!IS_ALIGNED(mw->dma_addr, mw->xlat_align)) { + if (!IS_ALIGNED(mw->dma_addr, xlat_align)) { dev_err(&pdev->dev, "DMA memory %pad is not aligned\n", &mw->dma_addr); ntb_free_mw(nt, num_mw); @@ -1104,11 +1109,6 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) for (i = 0; i < mw_count; i++) { mw = &nt->mw_vec[i]; - rc = ntb_mw_get_align(ndev, PIDX, i, &mw->xlat_align, - &mw->xlat_align_size, NULL); - if (rc) - goto err1; - rc = ntb_peer_mw_get_addr(ndev, i, &mw->phys_addr, &mw->phys_size); if (rc) diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 759f772fa00c..427112cf101a 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -108,8 +108,6 @@ MODULE_PARM_DESC(on_node, "Run threads only on NTB device node (default: true)") struct perf_mw { phys_addr_t phys_addr; resource_size_t phys_size; - resource_size_t xlat_align; - resource_size_t xlat_align_size; void __iomem *vbase; size_t xlat_size; size_t buf_size; @@ -472,13 +470,20 @@ static int perf_set_mw(struct perf_ctx *perf, resource_size_t size) { struct perf_mw *mw = &perf->mw; size_t xlat_size, buf_size; + resource_size_t xlat_align; + resource_size_t xlat_align_size; int rc; if (!size) return -EINVAL; - xlat_size = round_up(size, mw->xlat_align_size); - buf_size = round_up(size, mw->xlat_align); + rc = ntb_mw_get_align(perf->ntb, PIDX, 0, &xlat_align, + &xlat_align_size, NULL); + if (rc) + return rc; + + xlat_size = round_up(size, xlat_align_size); + buf_size = round_up(size, xlat_align); if (mw->xlat_size == xlat_size) return 0; @@ -567,11 +572,6 @@ static int perf_setup_mw(struct ntb_dev *ntb, struct perf_ctx *perf) mw = &perf->mw; - rc = ntb_mw_get_align(ntb, PIDX, 0, &mw->xlat_align, - &mw->xlat_align_size, NULL); - if (rc) - return rc; - rc = ntb_peer_mw_get_addr(ntb, 0, &mw->phys_addr, &mw->phys_size); if (rc) return rc; diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c index a69815c45ce6..91526a986caa 100644 --- a/drivers/ntb/test/ntb_tool.c +++ b/drivers/ntb/test/ntb_tool.c @@ -753,9 +753,9 @@ static ssize_t tool_peer_mw_trans_read(struct file *filep, phys_addr_t base; resource_size_t mw_size; - resource_size_t align_addr; - resource_size_t align_size; - resource_size_t max_size; + resource_size_t align_addr = 0; + resource_size_t align_size = 0; + resource_size_t max_size = 0; buf_size = min_t(size_t, size, 512);