diff mbox series

[v5,5/6] iommu/dma: Force swiotlb_max_mapping_size on an untrusted device

Message ID 20240228133930.15400-6-will@kernel.org
State New
Headers
Series Fix double allocation in swiotlb_alloc() |

Commit Message

Will Deacon Feb. 28, 2024, 1:39 p.m. UTC 
  From: Nicolin Chen <nicolinc@nvidia.com>

The swiotlb does not support a mapping size > swiotlb_max_mapping_size().
On the other hand, with a 64KB PAGE_SIZE configuration, it's observed that
an NVME device can map a size between 300KB~512KB, which certainly failed
the swiotlb mappings, though the default pool of swiotlb has many slots:
    systemd[1]: Started Journal Service.
 => nvme 0000:00:01.0: swiotlb buffer is full (sz: 327680 bytes), total 32768 (slots), used 32 (slots)
    note: journal-offline[392] exited with irqs disabled
    note: journal-offline[392] exited with preempt_count 1

Call trace:
[    3.099918]  swiotlb_tbl_map_single+0x214/0x240
[    3.099921]  iommu_dma_map_page+0x218/0x328
[    3.099928]  dma_map_page_attrs+0x2e8/0x3a0
[    3.101985]  nvme_prep_rq.part.0+0x408/0x878 [nvme]
[    3.102308]  nvme_queue_rqs+0xc0/0x300 [nvme]
[    3.102313]  blk_mq_flush_plug_list.part.0+0x57c/0x600
[    3.102321]  blk_add_rq_to_plug+0x180/0x2a0
[    3.102323]  blk_mq_submit_bio+0x4c8/0x6b8
[    3.103463]  __submit_bio+0x44/0x220
[    3.103468]  submit_bio_noacct_nocheck+0x2b8/0x360
[    3.103470]  submit_bio_noacct+0x180/0x6c8
[    3.103471]  submit_bio+0x34/0x130
[    3.103473]  ext4_bio_write_folio+0x5a4/0x8c8
[    3.104766]  mpage_submit_folio+0xa0/0x100
[    3.104769]  mpage_map_and_submit_buffers+0x1a4/0x400
[    3.104771]  ext4_do_writepages+0x6a0/0xd78
[    3.105615]  ext4_writepages+0x80/0x118
[    3.105616]  do_writepages+0x90/0x1e8
[    3.105619]  filemap_fdatawrite_wbc+0x94/0xe0
[    3.105622]  __filemap_fdatawrite_range+0x68/0xb8
[    3.106656]  file_write_and_wait_range+0x84/0x120
[    3.106658]  ext4_sync_file+0x7c/0x4c0
[    3.106660]  vfs_fsync_range+0x3c/0xa8
[    3.106663]  do_fsync+0x44/0xc0

Since untrusted devices might go down the swiotlb pathway with dma-iommu,
these devices should not map a size larger than swiotlb_max_mapping_size.

To fix this bug, add iommu_dma_max_mapping_size() for untrusted devices to
take into account swiotlb_max_mapping_size() v.s. iova_rcache_range() from
the iommu_dma_opt_mapping_size().

Fixes: 82612d66d51d ("iommu: Allow the dma-iommu api to use bounce buffers")
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Link: https://lore.kernel.org/r/ee51a3a5c32cf885b18f6416171802669f4a718a.1707851466.git.nicolinc@nvidia.com
Acked-by: Robin Murphy <robin.murphy@arm.com>
[will: Drop redundant is_swiotlb_active(dev) check]
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/dma-iommu.c | 9 +++++++++
 1 file changed, 9 insertions(+)

Comments

Michael Kelley Feb. 29, 2024, 5:57 a.m. UTC | #1 
From: Will Deacon <will@kernel.org> Sent: Wednesday, February 28, 2024 5:39 AM
> 
> From: Nicolin Chen <nicolinc@nvidia.com>
> 
> The swiotlb does not support a mapping size > swiotlb_max_mapping_size().
> On the other hand, with a 64KB PAGE_SIZE configuration, it's observed that
> an NVME device can map a size between 300KB~512KB, which certainly failed
> the swiotlb mappings, though the default pool of swiotlb has many slots:
>     systemd[1]: Started Journal Service.
>  => nvme 0000:00:01.0: swiotlb buffer is full (sz: 327680 bytes), total 32768 (slots), used 32 (slots)
>     note: journal-offline[392] exited with irqs disabled
>     note: journal-offline[392] exited with preempt_count 1
> 
> Call trace:
> [    3.099918]  swiotlb_tbl_map_single+0x214/0x240
> [    3.099921]  iommu_dma_map_page+0x218/0x328
> [    3.099928]  dma_map_page_attrs+0x2e8/0x3a0
> [    3.101985]  nvme_prep_rq.part.0+0x408/0x878 [nvme]
> [    3.102308]  nvme_queue_rqs+0xc0/0x300 [nvme]
> [    3.102313]  blk_mq_flush_plug_list.part.0+0x57c/0x600
> [    3.102321]  blk_add_rq_to_plug+0x180/0x2a0
> [    3.102323]  blk_mq_submit_bio+0x4c8/0x6b8
> [    3.103463]  __submit_bio+0x44/0x220
> [    3.103468]  submit_bio_noacct_nocheck+0x2b8/0x360
> [    3.103470]  submit_bio_noacct+0x180/0x6c8
> [    3.103471]  submit_bio+0x34/0x130
> [    3.103473]  ext4_bio_write_folio+0x5a4/0x8c8
> [    3.104766]  mpage_submit_folio+0xa0/0x100
> [    3.104769]  mpage_map_and_submit_buffers+0x1a4/0x400
> [    3.104771]  ext4_do_writepages+0x6a0/0xd78
> [    3.105615]  ext4_writepages+0x80/0x118
> [    3.105616]  do_writepages+0x90/0x1e8
> [    3.105619]  filemap_fdatawrite_wbc+0x94/0xe0
> [    3.105622]  __filemap_fdatawrite_range+0x68/0xb8
> [    3.106656]  file_write_and_wait_range+0x84/0x120
> [    3.106658]  ext4_sync_file+0x7c/0x4c0
> [    3.106660]  vfs_fsync_range+0x3c/0xa8
> [    3.106663]  do_fsync+0x44/0xc0
> 
> Since untrusted devices might go down the swiotlb pathway with dma-iommu,
> these devices should not map a size larger than swiotlb_max_mapping_size.
> 
> To fix this bug, add iommu_dma_max_mapping_size() for untrusted devices to
> take into account swiotlb_max_mapping_size() v.s. iova_rcache_range() from
> the iommu_dma_opt_mapping_size().
> 
> Fixes: 82612d66d51d ("iommu: Allow the dma-iommu api to use bounce buffers")
> Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
> Link: https://lore.kernel.org/all/ee51a3a5c32cf885b18f6416171802669f4a718a.1707851466.git.nicolinc@nvidia.com/
> Acked-by: Robin Murphy <robin.murphy@arm.com>
> [will: Drop redundant is_swiotlb_active(dev) check]
> Signed-off-by: Will Deacon <will@kernel.org>
> ---
>  drivers/iommu/dma-iommu.c | 9 +++++++++
>  1 file changed, 9 insertions(+)
> 
> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> index 50ccc4f1ef81..639efa0c4072 100644
> --- a/drivers/iommu/dma-iommu.c
> +++ b/drivers/iommu/dma-iommu.c
> @@ -1706,6 +1706,14 @@ static size_t
> iommu_dma_opt_mapping_size(void)
>  	return iova_rcache_range();
>  }
> 
> +static size_t iommu_dma_max_mapping_size(struct device *dev)
> +{
> +	if (dev_is_untrusted(dev))
> +		return swiotlb_max_mapping_size(dev);
> +
> +	return SIZE_MAX;
> +}
> +
>  static const struct dma_map_ops iommu_dma_ops = {
>  	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED,
>  	.alloc			= iommu_dma_alloc,
> @@ -1728,6 +1736,7 @@ static const struct dma_map_ops iommu_dma_ops = {
>  	.unmap_resource		= iommu_dma_unmap_resource,
>  	.get_merge_boundary	= iommu_dma_get_merge_boundary,
>  	.opt_mapping_size	= iommu_dma_opt_mapping_size,
> +	.max_mapping_size       = iommu_dma_max_mapping_size,
>  };
> 
>  /*
> --
> 2.44.0.rc1.240.g4c46232300-goog

Reviewed-by: Michael Kelley <mhklinux@outlook.com>
diff mbox series

Patch

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 50ccc4f1ef81..639efa0c4072 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1706,6 +1706,14 @@  static size_t iommu_dma_opt_mapping_size(void)
 	return iova_rcache_range();
 }
 
+static size_t iommu_dma_max_mapping_size(struct device *dev)
+{
+	if (dev_is_untrusted(dev))
+		return swiotlb_max_mapping_size(dev);
+
+	return SIZE_MAX;
+}
+
 static const struct dma_map_ops iommu_dma_ops = {
 	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED,
 	.alloc			= iommu_dma_alloc,
@@ -1728,6 +1736,7 @@  static const struct dma_map_ops iommu_dma_ops = {
 	.unmap_resource		= iommu_dma_unmap_resource,
 	.get_merge_boundary	= iommu_dma_get_merge_boundary,
 	.opt_mapping_size	= iommu_dma_opt_mapping_size,
+	.max_mapping_size       = iommu_dma_max_mapping_size,
 };
 
 /*