From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752498AbeDLI1y (ORCPT ); Thu, 12 Apr 2018 04:27:54 -0400 Received: from mx2.suse.de ([195.135.220.15]:59393 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750743AbeDLI1x (ORCPT ); Thu, 12 Apr 2018 04:27:53 -0400 Date: Thu, 12 Apr 2018 10:27:50 +0200 Message-ID: From: Takashi Iwai To: Christoph Hellwig Cc: Robin Murphy , linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org, Christian =?UTF-8?B?S8O2bmln?= , Konrad Rzeszutek Wilk Subject: Re: [PATCH] swiotlb: Fix unexpected swiotlb_alloc_coherent() failures In-Reply-To: References: <20180410170513.22834-1-tiwai@suse.de> <20180410170615.GA27589@lst.de> <40618b9c-786d-7f5f-3f5b-fc1dd8375846@arm.com> <20180410181020.GA28565@lst.de> <20180412060227.GA30248@lst.de> User-Agent: Wanderlust/2.15.9 (Almost Unreal) SEMI/1.14.6 (Maruoka) FLIM/1.14.9 (=?UTF-8?B?R29qxY0=?=) APEL/10.8 Emacs/25.3 (x86_64-suse-linux-gnu) MULE/6.0 (HANACHIRUSATO) MIME-Version: 1.0 (generated by SEMI 1.14.6 - "Maruoka") Content-Type: multipart/mixed; boundary="Multipart_Thu_Apr_12_10:27:50_2018-1" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --Multipart_Thu_Apr_12_10:27:50_2018-1 Content-Type: text/plain; charset=US-ASCII On Thu, 12 Apr 2018 10:19:05 +0200, Takashi Iwai wrote: > > On Thu, 12 Apr 2018 10:03:56 +0200, > Takashi Iwai wrote: > > > > On Thu, 12 Apr 2018 08:02:27 +0200, > > Christoph Hellwig wrote: > > > > > > On Wed, Apr 11, 2018 at 09:28:54AM +0200, Takashi Iwai wrote: > > > > > But we should try a GFP_DMA32 allocation first, so this is a bit > > > > > surprising. > > > > > > > > Hm, do we really try that? > > > > Through a quick glance, dma_alloc_coherent_gfp_flags() gives GFP_DMA32 > > > > only when coherent mask <= DMA_BIT_MASK(32); in the case of iwlwifi, > > > > it's 36bit, so GFP_DMA isn't set. > > > > > > Oh, yes - it is using an odd dma mask, and amdgpu seems to use an > > > just as odd 40-bit dma mask. > > > > > > > We had a fallback allocation with GFP_DMA32 in the past, but this > > > > seems gone long time ago along with cleanups (commit c647c3bb2d16). > > > > > > > > But I haven't followed about this topic for long time, so I might have > > > > missed obviously... > > > > > > I think a fallback would be much better here rather than relying on the > > > limited swiotlb buffer bool. dma_direct_alloc (which in 4.17 is also > > > used for x86) already has a GFP_DMA fallback, so extending this for > > > GFP_DMA32 as well would seem reasonable. > > > > > > Any volunteers? > > > > Below is a quick attempt, totally untested. Actually the retry with > > GFP_DMA is superfluous for archs without it, so the first patch > > corrects it. > > Gah, scratch this, it doesn't work. A different check is needed... The v2 patches are below, replaced with IS_ENABLED(CONFIG_ZONE_DMA). Takashi --Multipart_Thu_Apr_12_10:27:50_2018-1 Content-Type: application/octet-stream; type=patch Content-Disposition: attachment; filename="0001-dma-direct-Don-t-repeat-allocation-for-no-op-GFP_DMA.patch" Content-Transfer-Encoding: 7bit >>From 8d320bed20265ea98087a2b9c4abf2b4bf9cb9ec Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 12 Apr 2018 09:46:12 +0200 Subject: [PATCH v2 1/2] dma-direct: Don't repeat allocation for no-op GFP_DMA When an allocation with lower dma_coherent mask fails, dma_direct_alloc() retries the allocation with GFP_DMA. But, it's useless for architectures that has no ZONE_DMA, obviously. This patch fixes it by adding the check of CONFIG_ZONE_DMA before retrying the allocation. Fixes: 95f183916d4b ("dma-direct: retry allocations using GFP_DMA for small masks") Signed-off-by: Takashi Iwai --- lib/dma-direct.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/dma-direct.c b/lib/dma-direct.c index c0bba30fef0a..bbfb229aa067 100644 --- a/lib/dma-direct.c +++ b/lib/dma-direct.c @@ -84,7 +84,8 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, __free_pages(page, page_order); page = NULL; - if (dev->coherent_dma_mask < DMA_BIT_MASK(32) && + if (IS_ENABLED(CONFIG_ZONE_DMA) && + dev->coherent_dma_mask < DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) { gfp = (gfp & ~GFP_DMA32) | GFP_DMA; goto again; -- 2.16.3 --Multipart_Thu_Apr_12_10:27:50_2018-1 Content-Type: application/octet-stream; type=patch Content-Disposition: attachment; filename="0002-dma-direct-Try-reallocation-with-GFP_DMA32-if-possib.patch" Content-Transfer-Encoding: 7bit >>From 0d3781b8c0c397768c29c0351390f0fa04c9eaa8 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 12 Apr 2018 09:53:48 +0200 Subject: [PATCH v2 2/2] dma-direct: Try reallocation with GFP_DMA32 if possible This patch adds a similar fallback reallocation with GFP_DMA32 as we've done with GFP_DMA. The condition is that the coherent mask is smaller than 64bit (i.e. some address limitation), and neither GFP_DMA nor GFP_DMA32 is set beforehand. Signed-off-by: Takashi Iwai --- lib/dma-direct.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/lib/dma-direct.c b/lib/dma-direct.c index bbfb229aa067..970d39155618 100644 --- a/lib/dma-direct.c +++ b/lib/dma-direct.c @@ -84,6 +84,13 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, __free_pages(page, page_order); page = NULL; + if (IS_ENABLED(CONFIG_ZONE_DMA32) && + dev->coherent_dma_mask < DMA_BIT_MASK(64) && + !(gfp & (GFP_DMA32 | GFP_DMA))) { + gfp |= GFP_DMA32; + goto again; + } + if (IS_ENABLED(CONFIG_ZONE_DMA) && dev->coherent_dma_mask < DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) { -- 2.16.3 --Multipart_Thu_Apr_12_10:27:50_2018-1--