Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965534AbeAJICL (ORCPT + 1 other); Wed, 10 Jan 2018 03:02:11 -0500 Received: from bombadil.infradead.org ([65.50.211.133]:36050 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S965502AbeAJICD (ORCPT ); Wed, 10 Jan 2018 03:02:03 -0500 From: Christoph Hellwig To: iommu@lists.linux-foundation.org Cc: Konrad Rzeszutek Wilk , linux-alpha@vger.kernel.org, linux-snps-arc@lists.infradead.org, linux-arm-kernel@lists.infradead.org, linux-c6x-dev@linux-c6x.org, linux-cris-kernel@axis.com, linux-hexagon@vger.kernel.org, linux-ia64@vger.kernel.org, linux-m68k@lists.linux-m68k.org, linux-metag@vger.kernel.org, Michal Simek , linux-mips@linux-mips.org, linux-parisc@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, patches@groups.riscv.org, linux-s390@vger.kernel.org, linux-sh@vger.kernel.org, sparclinux@vger.kernel.org, Guan Xuetao , x86@kernel.org, linux-arch@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH 29/33] dma-direct: retry allocations using GFP_DMA for small masks Date: Wed, 10 Jan 2018 09:00:23 +0100 Message-Id: <20180110080027.13879-30-hch@lst.de> X-Mailer: git-send-email 2.14.2 In-Reply-To: <20180110080027.13879-1-hch@lst.de> References: <20180110080027.13879-1-hch@lst.de> X-SRS-Rewrite: SMTP reverse-path rewritten from by bombadil.infradead.org. See http://www.infradead.org/rpr.html Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Return-Path: If an attempt to allocate memory succeeded, but isn't inside the supported DMA mask, retry the allocation with GFP_DMA set as a last resort. Based on the x86 code, but an off by one error in what is now dma_coherent_ok has been fixed vs the x86 code. Signed-off-by: Christoph Hellwig --- lib/dma-direct.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/lib/dma-direct.c b/lib/dma-direct.c index 8f76032ebc3c..4e43c2bb7f5f 100644 --- a/lib/dma-direct.c +++ b/lib/dma-direct.c @@ -35,6 +35,11 @@ check_addr(struct device *dev, dma_addr_t dma_addr, size_t size, return true; } +static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) +{ + return phys_to_dma(dev, phys) + size - 1 <= dev->coherent_dma_mask; +} + static void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { @@ -48,11 +53,29 @@ static void *dma_direct_alloc(struct device *dev, size_t size, if (dev->coherent_dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) gfp |= GFP_DMA32; +again: /* CMA can be used only in the context which permits sleeping */ - if (gfpflags_allow_blocking(gfp)) + if (gfpflags_allow_blocking(gfp)) { page = dma_alloc_from_contiguous(dev, count, page_order, gfp); + if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { + dma_release_from_contiguous(dev, page, count); + page = NULL; + } + } if (!page) page = alloc_pages_node(dev_to_node(dev), gfp, page_order); + + if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { + __free_pages(page, page_order); + page = NULL; + + if (dev->coherent_dma_mask < DMA_BIT_MASK(32) && + !(gfp & GFP_DMA)) { + gfp = (gfp & ~GFP_DMA32) | GFP_DMA; + goto again; + } + } + if (!page) return NULL; -- 2.14.2