linux-kernel - Re: [PATCH 3/5] dma-direct: refine dma_direct

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 27 Sep 2018 11:45:15 +1000
From:   Benjamin Herrenschmidt <benh@...nel.crashing.org>
To:     Christoph Hellwig <hch@....de>, iommu@...ts.linux-foundation.org
Cc:     Marek Szyprowski <m.szyprowski@...sung.com>,
        Robin Murphy <robin.murphy@....com>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        linux-kernel@...r.kernel.org, linuxppc-dev@...ts.ozlabs.org
Subject: Re: [PATCH 3/5] dma-direct: refine dma_direct_alloc zone selection

On Thu, 2018-09-20 at 20:52 +0200, Christoph Hellwig wrote:
> +static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
> +               u64 *phys_mask)
> +{
> +       if (force_dma_unencrypted())
> +               *phys_mask = __dma_to_phys(dev, dma_mask);
> +       else
> +               *phys_mask = dma_to_phys(dev, dma_mask);
> +
> +       /* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */
> +       if (*phys_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
> +               return GFP_DMA;
> +       if (*phys_mask <= DMA_BIT_MASK(32))
> +               return GFP_DMA32;
> +       return 0;
> +}

I'm not sure this is entirely right.

Let's say the mask is 30 bits. You will return GFP_DMA32, which will
fail if you allocate something above 1G (which is legit for
ZONE_DMA32).

I think the logic should be:

	if (mask < ZONE_DMA)
		fail;
	else if (mask < ZONE_DMA32)
		use ZONE_DMA or fail if doesn't exist
	else if (mask < top_of_ram)
		use ZONE_DMA32 or fail if doesn't exist
	else
		use ZONE_NORMAL

Additionally, we want to fold-in the top-of-ram test such that we don't
fail the second case if the mask is 31-bits (smaller than ZONE_DMA32)
but top of ram is also small enough.

So the top of ram test should take precendence.

Cheers,
Ben.