Re: [PATCH v15 06/12] swiotlb: Use is_swiotlb_force_bounce for swiotlb data bouncing

From: Claire Chang <tientzu@chromium.org>
To: Nathan Chancellor <nathan@kernel.org>
Cc: Rob Herring <robh+dt@kernel.org>,
	mpe@ellerman.id.au, Joerg Roedel <joro@8bytes.org>,
	Will Deacon <will@kernel.org>,
	Frank Rowand <frowand.list@gmail.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	boris.ostrovsky@oracle.com, jgross@suse.com,
	Christoph Hellwig <hch@lst.de>,
	Marek Szyprowski <m.szyprowski@samsung.com>,
	benh@kernel.crashing.org, paulus@samba.org,
	"list@263.net:IOMMU DRIVERS" <iommu@lists.linux-foundation.org>,
	Stefano Stabellini <sstabellini@kernel.org>,
	Robin Murphy <robin.murphy@arm.com>,
	grant.likely@arm.com, xypron.glpk@gmx.de,
	Thierry Reding <treding@nvidia.com>,
	mingo@kernel.org, bauerman@linux.ibm.com, peterz@infradead.org,
	Greg KH <gregkh@linuxfoundation.org>,
	Saravana Kannan <saravanak@google.com>,
	"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
	heikki.krogerus@linux.intel.com,
	Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
	Randy Dunlap <rdunlap@infradead.org>,
	Dan Williams <dan.j.williams@intel.com>,
	Bartosz Golaszewski <bgolaszewski@baylibre.com>,
	linux-devicetree <devicetree@vger.kernel.org>,
	lkml <linux-kernel@vger.kernel.org>,
	linuxppc-dev@lists.ozlabs.org, xen-devel@lists.xenproject.org,
	Nicolas Boichat <drinkcat@chromium.org>,
	Jim Quinlan <james.quinlan@broadcom.com>,
	Tomasz Figa <tfiga@chromium.org>,
	bskeggs@redhat.com, Bjorn Helgaas <bhelgaas@google.com>,
	chris@chris-wilson.co.uk, Daniel Vetter <daniel@ffwll.ch>,
	airlied@linux.ie, dri-devel@lists.freedesktop.org,
	intel-gfx@lists.freedesktop.org, jani.nikula@linux.intel.com,
	Jianxiong Gao <jxgao@google.com>,
	joonas.lahtinen@linux.intel.com, linux-pci@vger.kernel.org,
	maarten.lankhorst@linux.intel.com, matthew.auld@intel.com,
	rodrigo.vivi@intel.com, thomas.hellstrom@linux.intel.com,
	Tom Lendacky <thomas.lendacky@amd.com>,
	Qian Cai <quic_qiancai@quicinc.com>
Subject: Re: [PATCH v15 06/12] swiotlb: Use is_swiotlb_force_bounce for swiotlb data bouncing
Date: Wed, 30 Jun 2021 17:17:27 +0800	[thread overview]
Message-ID: <CALiNf2-a-haQN0-4+gX8+wa++52-0CnO2O4BEkxrQCxoTa_47w@mail.gmail.com> (raw)
In-Reply-To: <YNvMDFWKXSm4LRfZ@Ryzen-9-3900X.localdomain>

On Wed, Jun 30, 2021 at 9:43 AM Nathan Chancellor <nathan@kernel.org> wrote:
>
> On Thu, Jun 24, 2021 at 11:55:20PM +0800, Claire Chang wrote:
> > Propagate the swiotlb_force into io_tlb_default_mem->force_bounce and
> > use it to determine whether to bounce the data or not. This will be
> > useful later to allow for different pools.
> >
> > Signed-off-by: Claire Chang <tientzu@chromium.org>
> > Reviewed-by: Christoph Hellwig <hch@lst.de>
> > Tested-by: Stefano Stabellini <sstabellini@kernel.org>
> > Tested-by: Will Deacon <will@kernel.org>
> > Acked-by: Stefano Stabellini <sstabellini@kernel.org>
>
> This patch as commit af452ec1b1a3 ("swiotlb: Use is_swiotlb_force_bounce
> for swiotlb data bouncing") causes my Ryzen 3 4300G system to fail to
> get to an X session consistently (although not every single time),
> presumably due to a crash in the AMDGPU driver that I see in dmesg.
>
> I have attached logs at af452ec1b1a3 and f127c9556a8e and I am happy
> to provide any further information, debug, or test patches as necessary.

Are you using swiotlb=force? or the swiotlb_map is called because of
!dma_capable? (https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/tree/kernel/dma/direct.h#n93)

`BUG: unable to handle page fault for address: 00000000003a8290` and
the fact it crashed at `_raw_spin_lock_irqsave` look like the memory
(maybe dev->dma_io_tlb_mem) was corrupted?
The dev->dma_io_tlb_mem should be set here
(https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/tree/drivers/pci/probe.c#n2528)
through device_initialize.

I can't tell what happened from the logs, but maybe we could try KASAN
to see if it provides more clue.

Thanks,
Claire

>
> Cheers,
> Nathan