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 5/5] dma-iommu: account for min_align_mask
Date: Wed, 11 Aug 2021 20:12:02 +0100 [thread overview]
Message-ID: <b5fff839-3242-7080-13f7-61c0e40af304@arm.com> (raw)
In-Reply-To: <20210811024247.1144246-6-stevensd@google.com>
On 2021-08-11 03:42, David Stevens wrote:
> From: David Stevens <stevensd@chromium.org>
>
> For devices which set min_align_mask, swiotlb preserves the offset of
> the original physical address within that mask. Since __iommu_dma_map
> accounts for non-aligned addresses, passing a non-aligned swiotlb
> address with the swiotlb aligned size results in the offset being
> accounted for twice in the size passed to iommu_map_atomic. The extra
> page exposed to DMA is also not cleaned up by __iommu_dma_unmap, since
> tht at function unmaps with the correct size. This causes mapping failures
> if the iova gets reused, due to collisions in the iommu page tables.
>
> To fix this, pass the original size to __iommu_dma_map, since that
> function already handles alignment.
>
> Additionally, when swiotlb returns non-aligned addresses, there is
> padding at the start of the bounce buffer that needs to be cleared.
>
> Fixes: 1f221a0d0dbf ("swiotlb: respect min_align_mask")
> Signed-off-by: David Stevens <stevensd@chromium.org>
> ---
> drivers/iommu/dma-iommu.c | 23 ++++++++++++-----------
> 1 file changed, 12 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> index 89b689bf801f..ffa7e8ef5db4 100644
> --- a/drivers/iommu/dma-iommu.c
> +++ b/drivers/iommu/dma-iommu.c
> @@ -549,9 +549,8 @@ static dma_addr_t __iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys,
> struct iommu_domain *domain = iommu_get_dma_domain(dev);
> struct iommu_dma_cookie *cookie = domain->iova_cookie;
> struct iova_domain *iovad = &cookie->iovad;
> - size_t aligned_size = org_size;
> - void *padding_start;
> - size_t padding_size;
> + void *tlb_start;
> + size_t aligned_size, iova_off, mapping_end_off;
> dma_addr_t iova;
>
> /*
> @@ -566,24 +565,26 @@ static dma_addr_t __iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys,
> if (phys == DMA_MAPPING_ERROR)
> return DMA_MAPPING_ERROR;
>
> - /* Cleanup the padding area. */
> - padding_start = phys_to_virt(phys);
> - padding_size = aligned_size;
> + iova_off = iova_offset(iovad, phys);
> + tlb_start = phys_to_virt(phys - iova_off);
>
> + /* Cleanup the padding area. */
> if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
> (dir == DMA_TO_DEVICE ||
> dir == DMA_BIDIRECTIONAL)) {
> - padding_start += org_size;
> - padding_size -= org_size;
> + mapping_end_off = iova_off + org_size;
> + memset(tlb_start, 0, iova_off);
> + memset(tlb_start + mapping_end_off, 0,
> + aligned_size - mapping_end_off);
> + } else {
> + memset(tlb_start, 0, aligned_size);
> }
> -
> - memset(padding_start, 0, padding_size);
> }
>
> if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
> arch_sync_dma_for_device(phys, org_size, dir);
>
> - iova = __iommu_dma_map(dev, phys, aligned_size, prot, dma_mask);
> + iova = __iommu_dma_map(dev, phys, org_size, prot, dma_mask);
This doesn't feel right - what if the IOVA granule was equal to or
smaller than min_align_mask, wouldn't you potentially end up mapping the
padding rather than the data?
Robin.
> if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(phys))
> swiotlb_tbl_unmap_single(dev, phys, org_size, dir, attrs);
> return iova;
>
next prev parent reply other threads:[~2021-08-11 19:12 UTC|newest]
Thread overview: 19+ 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 ` [PATCH v3 1/5] dma-iommu: fix sync_sg with swiotlb David Stevens
2021-08-11 5:57 ` Christoph Hellwig
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 6:01 ` Christoph Hellwig
2021-08-11 18:47 ` Robin Murphy
2021-08-12 9:21 ` David Stevens
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 6:07 ` Christoph Hellwig
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 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 9:26 ` Mi, Dapeng1
2021-08-11 19:12 ` Robin Murphy [this message]
2021-08-12 1:45 ` David Stevens
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=b5fff839-3242-7080-13f7-61c0e40af304@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 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).