[PATCH] dma-buf/udmabuf: skip redundant cpu sync to fix cacheline EEXIST warning

[PATCH] dma-buf/udmabuf: skip redundant cpu sync to fix cacheline EEXIST warning

[Mikhail Gavrilov]

When CONFIG_DMA_API_DEBUG_SG is enabled, importing a udmabuf into a DRM
driver (e.g. amdgpu for video playback in GNOME Videos / Showtime)
triggers a spurious warning:

  DMA-API: amdgpu 0000:03:00.0: cacheline tracking EEXIST, \
      overlapping mappings aren't supported
  WARNING: kernel/dma/debug.c:619 at add_dma_entry+0x473/0x5f0

The call chain is:

  amdgpu_cs_ioctl
   -> amdgpu_ttm_backend_bind
    -> dma_buf_map_attachment
     -> [udmabuf] map_udmabuf -> get_sg_table
      -> dma_map_sgtable(dev, sg, direction, 0)  // attrs=0
       -> debug_dma_map_sg -> add_dma_entry -> EEXIST

This happens because udmabuf builds a per-page scatter-gather list via
sg_set_folio().  When begin_cpu_udmabuf() has already created an sg
table mapped for the misc device, and an importer such as amdgpu maps
the same pages for its own device via map_udmabuf(), the DMA debug
infrastructure sees two active mappings whose physical addresses share
cacheline boundaries and warns about the overlap.

The DMA_ATTR_SKIP_CPU_SYNC flag suppresses this check in
add_dma_entry() because it signals that no CPU cache maintenance is
performed at map/unmap time, making the cacheline overlap harmless.

All other major dma-buf exporters already pass this flag:
  - drm_gem_map_dma_buf() passes DMA_ATTR_SKIP_CPU_SYNC
  - amdgpu_dma_buf_map() passes DMA_ATTR_SKIP_CPU_SYNC

The CPU sync at map/unmap time is also redundant for udmabuf:
begin_cpu_udmabuf() and end_cpu_udmabuf() already perform explicit
cache synchronization via dma_sync_sgtable_for_cpu/device() when CPU
access is requested through the dma-buf interface.

Pass DMA_ATTR_SKIP_CPU_SYNC to dma_map_sgtable() and
dma_unmap_sgtable() in udmabuf to suppress the spurious warning and
skip the redundant sync.

Fixes: 284562e1f348 ("udmabuf: implement begin_cpu_access/end_cpu_access hooks")
Cc: stable@vger.kernel.org
Signed-off-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
---
 drivers/dma-buf/udmabuf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 94b8ecb892bb..9c6f8785a28a 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -162,7 +162,7 @@ static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf,
 		sg_set_folio(sgl, ubuf->folios[i], PAGE_SIZE,
 			     ubuf->offsets[i]);
 
-	ret = dma_map_sgtable(dev, sg, direction, 0);
+	ret = dma_map_sgtable(dev, sg, direction, DMA_ATTR_SKIP_CPU_SYNC);
 	if (ret < 0)
 		goto err_map;
 	return sg;
@@ -177,7 +177,7 @@ static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf,
 static void put_sg_table(struct device *dev, struct sg_table *sg,
 			 enum dma_data_direction direction)
 {
-	dma_unmap_sgtable(dev, sg, direction, 0);
+	dma_unmap_sgtable(dev, sg, direction, DMA_ATTR_SKIP_CPU_SYNC);
 	sg_free_table(sg);
 	kfree(sg);
 }
-- 
2.53.0

RE: [PATCH] dma-buf/udmabuf: skip redundant cpu sync to fix cacheline EEXIST warning

[Kasireddy, Vivek]

Hi Mikhail,

> Subject: [PATCH] dma-buf/udmabuf: skip redundant cpu sync to fix
> cacheline EEXIST warning
> 
> When CONFIG_DMA_API_DEBUG_SG is enabled, importing a udmabuf
> into a DRM
> driver (e.g. amdgpu for video playback in GNOME Videos / Showtime)
> triggers a spurious warning:
> 
>   DMA-API: amdgpu 0000:03:00.0: cacheline tracking EEXIST, \
>       overlapping mappings aren't supported
>   WARNING: kernel/dma/debug.c:619 at add_dma_entry+0x473/0x5f0
> 
> The call chain is:
> 
>   amdgpu_cs_ioctl
>    -> amdgpu_ttm_backend_bind
>     -> dma_buf_map_attachment
>      -> [udmabuf] map_udmabuf -> get_sg_table
>       -> dma_map_sgtable(dev, sg, direction, 0)  // attrs=0
>        -> debug_dma_map_sg -> add_dma_entry -> EEXIST
> 
> This happens because udmabuf builds a per-page scatter-gather list via
> sg_set_folio().  When begin_cpu_udmabuf() has already created an sg
> table mapped for the misc device, and an importer such as amdgpu
> maps
> the same pages for its own device via map_udmabuf(), the DMA debug
> infrastructure sees two active mappings whose physical addresses share
> cacheline boundaries and warns about the overlap.
> 
> The DMA_ATTR_SKIP_CPU_SYNC flag suppresses this check in
> add_dma_entry() because it signals that no CPU cache maintenance is
> performed at map/unmap time, making the cacheline overlap harmless.
> 
> All other major dma-buf exporters already pass this flag:
>   - drm_gem_map_dma_buf() passes DMA_ATTR_SKIP_CPU_SYNC
>   - amdgpu_dma_buf_map() passes DMA_ATTR_SKIP_CPU_SYNC
> 
> The CPU sync at map/unmap time is also redundant for udmabuf:
> begin_cpu_udmabuf() and end_cpu_udmabuf() already perform explicit
> cache synchronization via dma_sync_sgtable_for_cpu/device() when
> CPU
> access is requested through the dma-buf interface.
> 
> Pass DMA_ATTR_SKIP_CPU_SYNC to dma_map_sgtable() and
> dma_unmap_sgtable() in udmabuf to suppress the spurious warning
> and
> skip the redundant sync.
> 
> Fixes: 284562e1f348 ("udmabuf: implement
> begin_cpu_access/end_cpu_access hooks")
> Cc: stable@vger.kernel.org
> Signed-off-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
> ---
>  drivers/dma-buf/udmabuf.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
> index 94b8ecb892bb..9c6f8785a28a 100644
> --- a/drivers/dma-buf/udmabuf.c
> +++ b/drivers/dma-buf/udmabuf.c
> @@ -162,7 +162,7 @@ static struct sg_table *get_sg_table(struct device
> *dev, struct dma_buf *buf,
>  		sg_set_folio(sgl, ubuf->folios[i], PAGE_SIZE,
>  			     ubuf->offsets[i]);
> 
> -	ret = dma_map_sgtable(dev, sg, direction, 0);
> +	ret = dma_map_sgtable(dev, sg, direction,
> DMA_ATTR_SKIP_CPU_SYNC);
>  	if (ret < 0)
>  		goto err_map;
>  	return sg;
> @@ -177,7 +177,7 @@ static struct sg_table *get_sg_table(struct device
> *dev, struct dma_buf *buf,
>  static void put_sg_table(struct device *dev, struct sg_table *sg,
>  			 enum dma_data_direction direction)
>  {
> -	dma_unmap_sgtable(dev, sg, direction, 0);
> +	dma_unmap_sgtable(dev, sg, direction,
> DMA_ATTR_SKIP_CPU_SYNC);
Looks OK to me but it would be nice if Christian or someone else can
provide an Ack for this patch.

Thanks,
Vivek

>  	sg_free_table(sg);
>  	kfree(sg);
>  }
> --
> 2.53.0

Re: [PATCH] dma-buf/udmabuf: skip redundant cpu sync to fix cacheline EEXIST warning

[Christian König]

On 3/18/26 06:40, Kasireddy, Vivek wrote:
> Hi Mikhail,
> 
>> Subject: [PATCH] dma-buf/udmabuf: skip redundant cpu sync to fix
>> cacheline EEXIST warning
>>
>> When CONFIG_DMA_API_DEBUG_SG is enabled, importing a udmabuf
>> into a DRM
>> driver (e.g. amdgpu for video playback in GNOME Videos / Showtime)
>> triggers a spurious warning:
>>
>>   DMA-API: amdgpu 0000:03:00.0: cacheline tracking EEXIST, \
>>       overlapping mappings aren't supported
>>   WARNING: kernel/dma/debug.c:619 at add_dma_entry+0x473/0x5f0
>>
>> The call chain is:
>>
>>   amdgpu_cs_ioctl
>>    -> amdgpu_ttm_backend_bind
>>     -> dma_buf_map_attachment
>>      -> [udmabuf] map_udmabuf -> get_sg_table
>>       -> dma_map_sgtable(dev, sg, direction, 0)  // attrs=0
>>        -> debug_dma_map_sg -> add_dma_entry -> EEXIST
>>
>> This happens because udmabuf builds a per-page scatter-gather list via
>> sg_set_folio().  When begin_cpu_udmabuf() has already created an sg
>> table mapped for the misc device, and an importer such as amdgpu
>> maps
>> the same pages for its own device via map_udmabuf(), the DMA debug
>> infrastructure sees two active mappings whose physical addresses share
>> cacheline boundaries and warns about the overlap.
>>
>> The DMA_ATTR_SKIP_CPU_SYNC flag suppresses this check in
>> add_dma_entry() because it signals that no CPU cache maintenance is
>> performed at map/unmap time, making the cacheline overlap harmless.
>>
>> All other major dma-buf exporters already pass this flag:
>>   - drm_gem_map_dma_buf() passes DMA_ATTR_SKIP_CPU_SYNC
>>   - amdgpu_dma_buf_map() passes DMA_ATTR_SKIP_CPU_SYNC
>>
>> The CPU sync at map/unmap time is also redundant for udmabuf:
>> begin_cpu_udmabuf() and end_cpu_udmabuf() already perform explicit
>> cache synchronization via dma_sync_sgtable_for_cpu/device() when
>> CPU
>> access is requested through the dma-buf interface.
>>
>> Pass DMA_ATTR_SKIP_CPU_SYNC to dma_map_sgtable() and
>> dma_unmap_sgtable() in udmabuf to suppress the spurious warning
>> and
>> skip the redundant sync.
>>
>> Fixes: 284562e1f348 ("udmabuf: implement
>> begin_cpu_access/end_cpu_access hooks")
>> Cc: stable@vger.kernel.org
>> Signed-off-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
>> ---
>>  drivers/dma-buf/udmabuf.c | 4 ++--
>>  1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
>> index 94b8ecb892bb..9c6f8785a28a 100644
>> --- a/drivers/dma-buf/udmabuf.c
>> +++ b/drivers/dma-buf/udmabuf.c
>> @@ -162,7 +162,7 @@ static struct sg_table *get_sg_table(struct device
>> *dev, struct dma_buf *buf,
>>  		sg_set_folio(sgl, ubuf->folios[i], PAGE_SIZE,
>>  			     ubuf->offsets[i]);
>>
>> -	ret = dma_map_sgtable(dev, sg, direction, 0);
>> +	ret = dma_map_sgtable(dev, sg, direction,
>> DMA_ATTR_SKIP_CPU_SYNC);
>>  	if (ret < 0)
>>  		goto err_map;
>>  	return sg;
>> @@ -177,7 +177,7 @@ static struct sg_table *get_sg_table(struct device
>> *dev, struct dma_buf *buf,
>>  static void put_sg_table(struct device *dev, struct sg_table *sg,
>>  			 enum dma_data_direction direction)
>>  {
>> -	dma_unmap_sgtable(dev, sg, direction, 0);
>> +	dma_unmap_sgtable(dev, sg, direction,
>> DMA_ATTR_SKIP_CPU_SYNC);
> Looks OK to me but it would be nice if Christian or someone else can
> provide an Ack for this patch.

The details of the udmabuf handling is absolutely not my field of expertise.

Feel free to add my Acked-by since it obviously seems to fix a bug, but it would be nice if somebody could do an in deep review as well.

Regards,
Christian.

> 
> Thanks,
> Vivek
> 
>>  	sg_free_table(sg);
>>  	kfree(sg);
>>  }
>> --
>> 2.53.0
>