All of lore.kernel.org
 help / color / mirror / Atom feed
From: Robin Murphy <robin.murphy@arm.com>
To: David Stevens <stevensd@chromium.org>, Will Deacon <will@kernel.org>
Cc: Joerg Roedel <joro@8bytes.org>,
	Lu Baolu <baolu.lu@linux.intel.com>, Tom Murphy <murphyt7@tcd.ie>,
	iommu@lists.linux-foundation.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3 3/5] dma-iommu: add SKIP_CPU_SYNC after syncing
Date: Wed, 11 Aug 2021 20:00:35 +0100	[thread overview]
Message-ID: <d8f07858-e8e7-9989-b95f-c512ba3904cf@arm.com> (raw)
In-Reply-To: <20210811024247.1144246-4-stevensd@google.com>

On 2021-08-11 03:42, David Stevens wrote:
> From: David Stevens <stevensd@chromium.org>
> 
> After syncing in map/unmap, add the DMA_ATTR_SKIP_CPU_SYNC flag so
> anything that uses attrs later on will skip any sync work that has
> already been completed. In particular, this skips copying from the
> swiotlb twice during unmap.
> 
> Signed-off-by: David Stevens <stevensd@chromium.org>
> ---
>   drivers/iommu/dma-iommu.c | 13 ++++++++++---
>   1 file changed, 10 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> index 4f0cc4a0a61f..be0214b1455c 100644
> --- a/drivers/iommu/dma-iommu.c
> +++ b/drivers/iommu/dma-iommu.c
> @@ -859,8 +859,11 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
>   static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
>   		size_t size, enum dma_data_direction dir, unsigned long attrs)
>   {
> -	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
> +	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
>   		iommu_dma_sync_single_for_cpu(dev, dma_handle, size, dir);
> +		attrs |= DMA_ATTR_SKIP_CPU_SYNC;
> +	}
> +
>   	__iommu_dma_unmap_swiotlb(dev, dma_handle, size, dir, attrs);

Again, fold that into here and put the arch sync in an else case to the 
is_swiotlb_buffer() check.

>   }
>   
> @@ -999,8 +1002,10 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
>   	if (dev_is_untrusted(dev))
>   		return iommu_dma_map_sg_swiotlb(dev, sg, nents, dir, attrs);
>   
> -	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
> +	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
>   		iommu_dma_sync_sg_for_device(dev, sg, nents, dir);
> +		attrs |= DMA_ATTR_SKIP_CPU_SYNC;
> +	}

Why? attrs is never referenced again after this.

>   	/*
>   	 * Work out how much IOVA space we need, and align the segments to
> @@ -1068,8 +1073,10 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
>   	struct scatterlist *tmp;
>   	int i;
>   
> -	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
> +	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
>   		iommu_dma_sync_sg_for_cpu(dev, sg, nents, dir);
> +		attrs |= DMA_ATTR_SKIP_CPU_SYNC;
> +	}

Just move it down so it's out of the SWIOTLB path entirely. Exactly like 
you did in patch #2 for map_sg, conspicuous in the hunk above.

Robin.

>   
>   	if (dev_is_untrusted(dev)) {
>   		iommu_dma_unmap_sg_swiotlb(dev, sg, nents, dir, attrs);
> 

WARNING: multiple messages have this Message-ID (diff)
From: Robin Murphy <robin.murphy@arm.com>
To: David Stevens <stevensd@chromium.org>, Will Deacon <will@kernel.org>
Cc: linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org,
	Tom Murphy <murphyt7@tcd.ie>
Subject: Re: [PATCH v3 3/5] dma-iommu: add SKIP_CPU_SYNC after syncing
Date: Wed, 11 Aug 2021 20:00:35 +0100	[thread overview]
Message-ID: <d8f07858-e8e7-9989-b95f-c512ba3904cf@arm.com> (raw)
In-Reply-To: <20210811024247.1144246-4-stevensd@google.com>

On 2021-08-11 03:42, David Stevens wrote:
> From: David Stevens <stevensd@chromium.org>
> 
> After syncing in map/unmap, add the DMA_ATTR_SKIP_CPU_SYNC flag so
> anything that uses attrs later on will skip any sync work that has
> already been completed. In particular, this skips copying from the
> swiotlb twice during unmap.
> 
> Signed-off-by: David Stevens <stevensd@chromium.org>
> ---
>   drivers/iommu/dma-iommu.c | 13 ++++++++++---
>   1 file changed, 10 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> index 4f0cc4a0a61f..be0214b1455c 100644
> --- a/drivers/iommu/dma-iommu.c
> +++ b/drivers/iommu/dma-iommu.c
> @@ -859,8 +859,11 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
>   static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
>   		size_t size, enum dma_data_direction dir, unsigned long attrs)
>   {
> -	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
> +	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
>   		iommu_dma_sync_single_for_cpu(dev, dma_handle, size, dir);
> +		attrs |= DMA_ATTR_SKIP_CPU_SYNC;
> +	}
> +
>   	__iommu_dma_unmap_swiotlb(dev, dma_handle, size, dir, attrs);

Again, fold that into here and put the arch sync in an else case to the 
is_swiotlb_buffer() check.

>   }
>   
> @@ -999,8 +1002,10 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
>   	if (dev_is_untrusted(dev))
>   		return iommu_dma_map_sg_swiotlb(dev, sg, nents, dir, attrs);
>   
> -	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
> +	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
>   		iommu_dma_sync_sg_for_device(dev, sg, nents, dir);
> +		attrs |= DMA_ATTR_SKIP_CPU_SYNC;
> +	}

Why? attrs is never referenced again after this.

>   	/*
>   	 * Work out how much IOVA space we need, and align the segments to
> @@ -1068,8 +1073,10 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
>   	struct scatterlist *tmp;
>   	int i;
>   
> -	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
> +	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
>   		iommu_dma_sync_sg_for_cpu(dev, sg, nents, dir);
> +		attrs |= DMA_ATTR_SKIP_CPU_SYNC;
> +	}

Just move it down so it's out of the SWIOTLB path entirely. Exactly like 
you did in patch #2 for map_sg, conspicuous in the hunk above.

Robin.

>   
>   	if (dev_is_untrusted(dev)) {
>   		iommu_dma_unmap_sg_swiotlb(dev, sg, nents, dir, attrs);
> 
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

  parent reply	other threads:[~2021-08-11 19:00 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-11  2:42 [PATCH v3 0/5] Fixes for dma-iommu swiotlb bounce buffers David Stevens
2021-08-11  2:42 ` David Stevens
2021-08-11  2:42 ` [PATCH v3 1/5] dma-iommu: fix sync_sg with swiotlb David Stevens
2021-08-11  2:42   ` David Stevens
2021-08-11  5:57   ` Christoph Hellwig
2021-08-11  5:57     ` Christoph Hellwig
2021-08-11 18:22     ` Robin Murphy
2021-08-11 18:22       ` Robin Murphy
2021-08-11  2:42 ` [PATCH v3 2/5] dma-iommu: fix arch_sync_dma for map David Stevens
2021-08-11  2:42   ` David Stevens
2021-08-11  6:01   ` Christoph Hellwig
2021-08-11  6:01     ` Christoph Hellwig
2021-08-11 18:47   ` Robin Murphy
2021-08-11 18:47     ` Robin Murphy
2021-08-12  9:21     ` David Stevens
2021-08-12  9:21       ` David Stevens
2021-08-12 10:38       ` Robin Murphy
2021-08-12 10:38         ` Robin Murphy
2021-08-11  2:42 ` [PATCH v3 3/5] dma-iommu: add SKIP_CPU_SYNC after syncing David Stevens
2021-08-11  2:42   ` David Stevens
2021-08-11  6:07   ` Christoph Hellwig
2021-08-11  6:07     ` Christoph Hellwig
2021-08-11 19:00   ` Robin Murphy [this message]
2021-08-11 19:00     ` Robin Murphy
2021-08-11  2:42 ` [PATCH v3 4/5] dma-iommu: Check CONFIG_SWIOTLB more broadly David Stevens
2021-08-11  2:42   ` David Stevens
2021-08-11 19:02   ` Robin Murphy
2021-08-11 19:02     ` Robin Murphy
2021-08-11  2:42 ` [PATCH v3 5/5] dma-iommu: account for min_align_mask David Stevens
2021-08-11  2:42   ` David Stevens
2021-08-11  9:26   ` Mi, Dapeng1
2021-08-11  9:26     ` Mi, Dapeng1
2021-08-11 19:12   ` Robin Murphy
2021-08-11 19:12     ` Robin Murphy
2021-08-12  1:45     ` David Stevens
2021-08-12  1:45       ` David Stevens
2021-08-12  9:57       ` Robin Murphy
2021-08-12  9:57         ` Robin Murphy

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=d8f07858-e8e7-9989-b95f-c512ba3904cf@arm.com \
    --to=robin.murphy@arm.com \
    --cc=baolu.lu@linux.intel.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=joro@8bytes.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=murphyt7@tcd.ie \
    --cc=stevensd@chromium.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.