[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20211102064356.GB27749@lst.de>
Date: Tue, 2 Nov 2021 07:43:56 +0100
From: Christoph Hellwig <hch@....de>
To: Walter Wu <walter-zh.wu@...iatek.com>
Cc: Ard Biesheuvel <ardb@...nel.org>, Christoph Hellwig <hch@....de>,
Marek Szyprowski <m.szyprowski@...sung.com>,
Robin Murphy <robin.murphy@....com>,
Matthias Brugger <matthias.bgg@...il.com>,
Linux IOMMU <iommu@...ts.linux-foundation.org>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
Linux ARM <linux-arm-kernel@...ts.infradead.org>,
wsd_upstream <wsd_upstream@...iatek.com>,
linux-mediatek@...ts.infradead.org,
Andrew Morton <akpm@...ux-foundation.org>,
Will Deacon <will@...nel.org>
Subject: Re: [PATCH] dma-direct: fix DMA_ATTR_NO_KERNEL_MAPPING
On Tue, Nov 02, 2021 at 11:21:16AM +0800, Walter Wu wrote:
> Our platform is arch64. We need a dynamic allocated buffer from CMA is
> not to read by CPU peculative execution, so we need to remove its
> kernel mapping.
If your CPU speculates into unused kernel direct mappings your have
a worse problem than this, because all the dma coherent allocations for
non-coherent devices still have a cachable direct mapping. Will
mentioned he wanted to look into getting rid of that mapping now that
the core dma code has the infrastucture for that, so adding him here.
Powered by blists - more mailing lists