Linux IOMMU Development
 help / color / mirror / Atom feed
From: Robin Murphy <robin.murphy@arm.com>
To: Christoph Hellwig <hch@lst.de>, iommu@lists.linux-foundation.org
Cc: David Rientjes <rientjes@google.com>
Subject: Re: [PATCH 06/11] dma-direct: refactor the !coherent checks in dma_direct_alloc
Date: Mon, 6 Dec 2021 16:33:17 +0000	[thread overview]
Message-ID: <b2a337e3-6c23-d2c0-a0db-aa3ec0d0df9f@arm.com> (raw)
In-Reply-To: <20211111065028.32761-7-hch@lst.de>

On 2021-11-11 06:50, Christoph Hellwig wrote:
> Add a big central !dev_is_dma_coherent(dev) block to deal with as much
> as of the uncached allocation schemes and document the schemes a bit
> better.

With a clear mind and a side-by-side diff viewer, indeed the end result 
is much more readable than the patch itself :)

Reviewed-by: Robin Murphy <robin.murphy@arm.com>

> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>   kernel/dma/direct.c | 66 ++++++++++++++++++++++++++++-----------------
>   1 file changed, 41 insertions(+), 25 deletions(-)
> 
> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
> index 01104660ec439..f9658fe18498c 100644
> --- a/kernel/dma/direct.c
> +++ b/kernel/dma/direct.c
> @@ -201,29 +201,49 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>   	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev))
>   		return dma_direct_alloc_no_mapping(dev, size, dma_handle, gfp);
>   
> -	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
> -	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> -	    !IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
> -	    !dev_is_dma_coherent(dev) &&
> -	    !is_swiotlb_for_alloc(dev))
> -		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
> +	if (!dev_is_dma_coherent(dev)) {
> +		/*
> +		 * Fallback to the arch handler if it exists.  This should
> +		 * eventually go away.
> +		 */
> +		if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
> +		    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> +		    !IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
> +		    !is_swiotlb_for_alloc(dev))
> +			return arch_dma_alloc(dev, size, dma_handle, gfp,
> +					      attrs);
>   
> -	if (IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
> -	    !dev_is_dma_coherent(dev))
> -		return dma_alloc_from_global_coherent(dev, size, dma_handle);
> +		/*
> +		 * If there is a global pool, always allocate from it for
> +		 * non-coherent devices.
> +		 */
> +		if (IS_ENABLED(CONFIG_DMA_GLOBAL_POOL))
> +			return dma_alloc_from_global_coherent(dev, size,
> +					dma_handle);
> +
> +		/*
> +		 * Otherwise remap if the architecture is asking for it.  But
> +		 * given that remapping memory is a blocking operation we'll
> +		 * instead have to dip into the atomic pools.
> +		 */
> +		remap = IS_ENABLED(CONFIG_DMA_DIRECT_REMAP);
> +		if (remap) {
> +			if (!gfpflags_allow_blocking(gfp) &&
> +			    !is_swiotlb_for_alloc(dev))
> +				return dma_direct_alloc_from_pool(dev, size,
> +						dma_handle, gfp);
> +		} else {
> +			if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED))
> +				set_uncached = true;
> +		}
> +	}
>   
>   	/*
> -	 * Remapping or decrypting memory may block. If either is required and
> -	 * we can't block, allocate the memory from the atomic pools.
> -	 * If restricted DMA (i.e., is_swiotlb_for_alloc) is required, one must
> -	 * set up another device coherent pool by shared-dma-pool and use
> -	 * dma_alloc_from_dev_coherent instead.
> +	 * Decrypting memory may block, so allocate the memory from the atomic
> +	 * pools if we can't block.
>   	 */
>   	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
> -	    !gfpflags_allow_blocking(gfp) &&
> -	    (force_dma_unencrypted(dev) ||
> -	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> -	      !dev_is_dma_coherent(dev))) &&
> +	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp) &&
>   	    !is_swiotlb_for_alloc(dev))
>   		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
>   
> @@ -231,10 +251,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>   	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
>   	if (!page)
>   		return NULL;
> -
> -	if (!dev_is_dma_coherent(dev) && IS_ENABLED(CONFIG_DMA_DIRECT_REMAP)) {
> -		remap = true;
> -	} else if (PageHighMem(page)) {
> +	if (PageHighMem(page)) {
>   		/*
>   		 * Depending on the cma= arguments and per-arch setup,
>   		 * dma_alloc_contiguous could return highmem pages.
> @@ -246,9 +263,8 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>   			goto out_free_pages;
>   		}
>   		remap = true;
> -	} else if (!dev_is_dma_coherent(dev) &&
> -		   IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED))
> -		set_uncached = true;
> +		set_uncached = false;
> +	}
>   
>   	if (remap) {
>   		/* remove any dirty cache lines on the kernel alias */
> 
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

  reply	other threads:[~2021-12-06 16:33 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-11  6:50 dma-direct fixes and cleanups v3 Christoph Hellwig
2021-11-11  6:50 ` [PATCH 01/11] dma-direct: factor out dma_set_{de,en}crypted helpers Christoph Hellwig
2021-11-11  6:50 ` [PATCH 02/11] dma-direct: don't call dma_set_decrypted for remapped allocations Christoph Hellwig
2021-11-11  6:50 ` [PATCH 03/11] dma-direct: always leak memory that can't be re-encrypted Christoph Hellwig
2021-12-06 16:32   ` Robin Murphy
2021-12-07 11:48     ` Christoph Hellwig
2021-11-11  6:50 ` [PATCH 04/11] dma-direct: clean up the remapping checks in dma_direct_alloc Christoph Hellwig
2021-12-06 16:33   ` Robin Murphy
2021-12-07 11:49     ` Christoph Hellwig
2021-12-07 12:43       ` Robin Murphy
2021-11-11  6:50 ` [PATCH 05/11] dma-direct: factor out a helper for DMA_ATTR_NO_KERNEL_MAPPING allocations Christoph Hellwig
2021-11-11  6:50 ` [PATCH 06/11] dma-direct: refactor the !coherent checks in dma_direct_alloc Christoph Hellwig
2021-12-06 16:33   ` Robin Murphy [this message]
2021-11-11  6:50 ` [PATCH 07/11] dma-direct: fail allocations that can't be made coherent Christoph Hellwig
2021-12-06 16:33   ` Robin Murphy
2021-11-11  6:50 ` [PATCH 08/11] dma-direct: warn if there is no pool for force unencrypted allocations Christoph Hellwig
2021-11-11  6:50 ` [PATCH 09/11] dma-direct: drop two CONFIG_DMA_RESTRICTED_POOL conditionals Christoph Hellwig
2021-11-11  6:50 ` [PATCH 10/11] dma-direct: factor the swiotlb code out of __dma_direct_alloc_pages Christoph Hellwig
2021-11-11  6:50 ` [PATCH 11/11] dma-direct: add a dma_direct_use_pool helper Christoph Hellwig
2021-12-08 15:44   ` Marek Szyprowski
2021-12-08 15:48     ` Christoph Hellwig
2021-11-16 11:31 ` dma-direct fixes and cleanups v3 Robin Murphy
2021-11-17  5:51   ` Christoph Hellwig

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=b2a337e3-6c23-d2c0-a0db-aa3ec0d0df9f@arm.com \
    --to=robin.murphy@arm.com \
    --cc=hch@lst.de \
    --cc=iommu@lists.linux-foundation.org \
    --cc=rientjes@google.com \
    /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