From: Robin Murphy <robin.murphy@arm.com>
To: Catalin Marinas <catalin.marinas@arm.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Christoph Hellwig <hch@lst.de>
Cc: Arnd Bergmann <arnd@arndb.de>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Will Deacon <will@kernel.org>, Marc Zyngier <maz@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Herbert Xu <herbert@gondor.apana.org.au>,
Ard Biesheuvel <ardb@kernel.org>,
Isaac Manjarres <isaacmanjarres@google.com>,
Saravana Kannan <saravanak@google.com>,
Alasdair Kergon <agk@redhat.com>, Daniel Vetter <daniel@ffwll.ch>,
Joerg Roedel <joro@8bytes.org>, Mark Brown <broonie@kernel.org>,
Mike Snitzer <snitzer@kernel.org>,
"Rafael J. Wysocki" <rafael@kernel.org>,
linux-mm@kvack.org, iommu@lists.linux.dev,
linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH v5 13/15] iommu/dma: Force bouncing if the size is not cacheline-aligned
Date: Thu, 25 May 2023 16:57:53 +0100 [thread overview]
Message-ID: <df0dd2a4-34f5-3627-ce8c-7636974879ee@arm.com> (raw)
In-Reply-To: <20230524171904.3967031-14-catalin.marinas@arm.com>
On 24/05/2023 6:19 pm, Catalin Marinas wrote:
> Similarly to the direct DMA, bounce small allocations as they may have
> originated from a kmalloc() cache not safe for DMA. Unlike the direct
> DMA, iommu_dma_map_sg() cannot call iommu_dma_map_sg_swiotlb() for all
> non-coherent devices as this would break some cases where the iova is
> expected to be contiguous (dmabuf). Instead, scan the scatterlist for
> any small sizes and only go the swiotlb path if any element of the list
> needs bouncing (note that iommu_dma_map_page() would still only bounce
> those buffers which are not DMA-aligned).
>
> To avoid scanning the scatterlist on the 'sync' operations, introduce an
> SG_DMA_USE_SWIOTLB flag set by iommu_dma_map_sg_swiotlb(). The
> dev_use_swiotlb() function together with the newly added
> dev_use_sg_swiotlb() now check for both untrusted devices and unaligned
> kmalloc() buffers (suggested by Robin Murphy).
>
> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Joerg Roedel <joro@8bytes.org>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Robin Murphy <robin.murphy@arm.com>
> ---
[...]
> diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
> index 87aaf8b5cdb4..330a157c5501 100644
> --- a/include/linux/scatterlist.h
> +++ b/include/linux/scatterlist.h
> @@ -248,6 +248,29 @@ static inline void sg_unmark_end(struct scatterlist *sg)
> sg->page_link &= ~SG_END;
> }
>
> +#define SG_DMA_BUS_ADDRESS (1 << 0)
> +#define SG_DMA_USE_SWIOTLB (1 << 1)
> +
> +#ifdef CONFIG_SWIOTLB
> +static inline bool sg_is_dma_use_swiotlb(struct scatterlist *sg)
Nit: can we decide whether this API is named sg_<verb>_<flag name> or
sg_dma_<verb>_<flag suffix>? I'm leaning towards the latter, which would
be consistent with the existing kerneldoc if not all the code (which I
shall probably now send a patch to fix).
However, my internal grammar parser just cannot cope with the "is use"
double-verb construct, so I would be inclined to collapse this
particular one to "sg_dma_use_swiotlb" either way. Yes, it breaks the
pattern, but that's what the English language does best :)
Otherwise,
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
I don't seem to have got round to giving this a spin on my Juno today,
but will try to do so soon.
Cheers,
Robin.
> +{
> + return sg->dma_flags & SG_DMA_USE_SWIOTLB;
> +}
> +
> +static inline void sg_dma_mark_use_swiotlb(struct scatterlist *sg)
> +{
> + sg->dma_flags |= SG_DMA_USE_SWIOTLB;
> +}
> +#else
> +static inline bool sg_is_dma_use_swiotlb(struct scatterlist *sg)
> +{
> + return false;
> +}
> +static inline void sg_dma_mark_use_swiotlb(struct scatterlist *sg)
> +{
> +}
> +#endif
> +
> /*
> * CONFIG_PCI_P2PDMA depends on CONFIG_64BIT which means there is 4 bytes
> * in struct scatterlist (assuming also CONFIG_NEED_SG_DMA_LENGTH is set).
> @@ -256,8 +279,6 @@ static inline void sg_unmark_end(struct scatterlist *sg)
> */
> #ifdef CONFIG_PCI_P2PDMA
>
> -#define SG_DMA_BUS_ADDRESS (1 << 0)
> -
> /**
> * sg_dma_is_bus address - Return whether a given segment was marked
> * as a bus address
next prev parent reply other threads:[~2023-05-25 15:57 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-24 17:18 [PATCH v5 00/15] mm, dma, arm64: Reduce ARCH_KMALLOC_MINALIGN to 8 Catalin Marinas
2023-05-24 17:18 ` [PATCH v5 01/15] mm/slab: Decouple ARCH_KMALLOC_MINALIGN from ARCH_DMA_MINALIGN Catalin Marinas
2023-05-24 17:18 ` [PATCH v5 02/15] dma: Allow dma_get_cache_alignment() to be overridden by the arch code Catalin Marinas
2023-05-25 13:59 ` Christoph Hellwig
2023-05-24 17:18 ` [PATCH v5 03/15] mm/slab: Simplify create_kmalloc_cache() args and make it static Catalin Marinas
2023-05-24 17:18 ` [PATCH v5 04/15] mm/slab: Limit kmalloc() minimum alignment to dma_get_cache_alignment() Catalin Marinas
2023-05-24 17:18 ` [PATCH v5 05/15] drivers/base: Use ARCH_DMA_MINALIGN instead of ARCH_KMALLOC_MINALIGN Catalin Marinas
2023-05-24 17:18 ` [PATCH v5 06/15] drivers/gpu: " Catalin Marinas
2023-05-24 17:18 ` [PATCH v5 07/15] drivers/usb: " Catalin Marinas
2023-05-24 17:18 ` [PATCH v5 08/15] drivers/spi: " Catalin Marinas
2023-05-24 17:18 ` [PATCH v5 09/15] drivers/md: " Catalin Marinas
2023-05-25 14:00 ` Christoph Hellwig
2023-05-24 17:18 ` [PATCH v5 10/15] arm64: Allow kmalloc() caches aligned to the smaller cache_line_size() Catalin Marinas
2023-05-24 17:19 ` [PATCH v5 11/15] scatterlist: Add dedicated config for DMA flags Catalin Marinas
2023-05-24 17:19 ` [PATCH v5 12/15] dma-mapping: Force bouncing if the kmalloc() size is not cache-line-aligned Catalin Marinas
2023-05-25 15:53 ` Robin Murphy
2023-05-24 17:19 ` [PATCH v5 13/15] iommu/dma: Force bouncing if the size is not cacheline-aligned Catalin Marinas
2023-05-25 15:57 ` Robin Murphy [this message]
2023-05-26 16:36 ` Jisheng Zhang
2023-05-26 19:22 ` Catalin Marinas
2023-05-30 13:01 ` Robin Murphy
2023-05-24 17:19 ` [PATCH v5 14/15] mm: slab: Reduce the kmalloc() minimum alignment if DMA bouncing possible Catalin Marinas
2023-05-24 17:19 ` [PATCH v5 15/15] arm64: Enable ARCH_WANT_KMALLOC_DMA_BOUNCE for arm64 Catalin Marinas
2023-05-25 16:12 ` Robin Murphy
2023-05-25 17:08 ` Catalin Marinas
2023-05-25 12:31 ` [PATCH v5 00/15] mm, dma, arm64: Reduce ARCH_KMALLOC_MINALIGN to 8 Jonathan Cameron
2023-05-25 14:31 ` Catalin Marinas
2023-05-26 16:07 ` Jonathan Cameron
2023-05-26 16:29 ` Jonathan Cameron
2023-05-30 13:38 ` Catalin Marinas
2023-05-30 16:31 ` Jonathan Cameron
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=df0dd2a4-34f5-3627-ce8c-7636974879ee@arm.com \
--to=robin.murphy@arm.com \
--cc=agk@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=ardb@kernel.org \
--cc=arnd@arndb.de \
--cc=broonie@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=daniel@ffwll.ch \
--cc=gregkh@linuxfoundation.org \
--cc=hch@lst.de \
--cc=herbert@gondor.apana.org.au \
--cc=iommu@lists.linux.dev \
--cc=isaacmanjarres@google.com \
--cc=joro@8bytes.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-mm@kvack.org \
--cc=maz@kernel.org \
--cc=rafael@kernel.org \
--cc=saravanak@google.com \
--cc=snitzer@kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=will@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).