From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ozlabs.org (ozlabs.org [IPv6:2401:3900:2:1::2]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 273041A0023 for ; Fri, 7 Aug 2015 11:55:56 +1000 (AEST) Received: from e23smtp05.au.ibm.com (e23smtp05.au.ibm.com [202.81.31.147]) (using TLSv1 with cipher CAMELLIA256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id F1930140129 for ; Fri, 7 Aug 2015 11:55:55 +1000 (AEST) Received: from /spool/local by e23smtp05.au.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Fri, 7 Aug 2015 11:55:55 +1000 Received: from d23relay08.au.ibm.com (d23relay08.au.ibm.com [9.185.71.33]) by d23dlp03.au.ibm.com (Postfix) with ESMTP id A6C9E3578056 for ; Fri, 7 Aug 2015 11:55:52 +1000 (EST) Received: from d23av01.au.ibm.com (d23av01.au.ibm.com [9.190.234.96]) by d23relay08.au.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id t771td8Y59244764 for ; Fri, 7 Aug 2015 11:55:47 +1000 Received: from d23av01.au.ibm.com (localhost [127.0.0.1]) by d23av01.au.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id t771tJ2M020886 for ; Fri, 7 Aug 2015 11:55:20 +1000 Date: Fri, 7 Aug 2015 11:23:54 +1000 From: Gavin Shan To: Wei Yang Cc: Gavin Shan , aik@ozlabs.ru, benh@kernel.crashing.org, linuxppc-dev@ozlabs.org Subject: Re: [PATCH V2 5/6] powerpc/powernv: boundary the total vf bar size instead of the individual one Message-ID: <20150807012354.GA20794@gwshan> Reply-To: Gavin Shan References: <20150731020148.GA6151@richard> <1438737903-10399-1-git-send-email-weiyang@linux.vnet.ibm.com> <1438737903-10399-6-git-send-email-weiyang@linux.vnet.ibm.com> <20150806052851.GA5636@gwshan> <20150806140304.GC6235@richard> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <20150806140304.GC6235@richard> List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Thu, Aug 06, 2015 at 10:03:04PM +0800, Wei Yang wrote: >On Thu, Aug 06, 2015 at 03:28:51PM +1000, Gavin Shan wrote: >>On Wed, Aug 05, 2015 at 09:25:02AM +0800, Wei Yang wrote: >>>Each VF could have 6 BARs at most. When the total BAR size exceeds the >>>gate, after expanding it will also exhaust the M64 Window. >>> >>>This patch limits the boundary by checking the total VF BAR size instead of >>>the individual BAR. >>> >>>Signed-off-by: Wei Yang >> >>Ok. I didn't look at this when giving comments to last patch. It turns >>you have the change in this patch. Please merge it with the previous >>patch. >> > >Hmm... I prefer to have them in two patches. One focus on the calculation of >gate and the other focus on checking the total VF BAR size. This would help >record the change. > It's fine to me as well. I'll take close look on your next revision since you have to refresh the whole series. Is that fine to you? >>>--- >>> arch/powerpc/platforms/powernv/pci-ioda.c | 13 +++++++------ >>> 1 file changed, 7 insertions(+), 6 deletions(-) >>> >>>diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c >>>index 31dcedc..4042303 100644 >>>--- a/arch/powerpc/platforms/powernv/pci-ioda.c >>>+++ b/arch/powerpc/platforms/powernv/pci-ioda.c >>>@@ -2702,7 +2702,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) >>> struct pnv_phb *phb; >>> struct resource *res; >>> int i; >>>- resource_size_t size, gate; >>>+ resource_size_t size, gate, total_vf_bar_sz; >>> struct pci_dn *pdn; >>> int mul, total_vfs; >>> >>>@@ -2729,6 +2729,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) >>> * Window and limit the system flexibility. >>> */ >>> gate = phb->ioda.m64_segsize >> 1; >>>+ total_vf_bar_sz = 0; >>> >>> for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { >>> res = &pdev->resource[i + PCI_IOV_RESOURCES]; >>>@@ -2741,13 +2742,13 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) >>> return; >>> } >>> >>>- size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES); >>>+ total_vf_bar_sz += pci_iov_resource_size(pdev, >>>+ i + PCI_IOV_RESOURCES); >>> >>> /* bigger than or equal to gate */ >>>- if (size >= gate) { >>>- dev_info(&pdev->dev, "PowerNV: VF BAR%d: %pR IOV size " >>>- "is bigger than %lld, roundup power2\n", >>>- i, res, gate); >>>+ if (total_vf_bar_sz >= gate) { >>>+ dev_info(&pdev->dev, "PowerNV: VF BAR Total IOV size " >>>+ "is bigger than %lld, roundup power2\n", gate); >>> mul = roundup_pow_of_two(total_vfs); >>> pdn->m64_single_mode = true; >>> break; >>>-- >>>1.7.9.5 >>> > >-- >Richard Yang >Help you, Help me