Re: [PATCH v6 2/8] drm/ttm: Add ttm_bo_access

[Rodrigo Vivi <rodrigo.vivi@intel.com>]

On Mon, Nov 04, 2024 at 01:30:41PM -0800, Matthew Brost wrote:
> On Mon, Nov 04, 2024 at 08:47:01PM +0100, Christian König wrote:
> > Am 01.11.24 um 00:43 schrieb Matthew Brost:
> > > On Thu, Oct 31, 2024 at 11:10:42AM -0700, Matthew Brost wrote:
> > > > Non-contiguous VRAM cannot easily be mapped in TTM nor can non-visible
> > > > VRAM easily be accessed. Add ttm_bo_access, which is similar to
> > > > ttm_bo_vm_access, to access such memory.
> > > > 
> > > > v4:
> > > >   - Fix checkpatch warnings (CI)
> > > > v5:
> > > >   - Fix checkpatch warnings (CI)
> > > > v6:
> > > >   - Fix kernel doc (Auld)
> > > > 
> > > Christian - Do you mind if I merge patch along with the rest of the
> > > series to drm-xe-next?
> > 
> > I don't see the original patch anywhere in my inbox, please make sure to CC
> > me while sending things out.
> > 
> 
> I think I had you on an earlier revision but used the wrong alias to send out
> this latest one. I will be sure to include you on future patches.
> 
> Would you like to continue the discussion here, or should I send out a fresh
> revision with you included and an updated commit message?

please send over a refreshed version with updated commit message and also
cc'ing dri-devel

> 
> > Apart from that I absolutely don't see any justification for this patch. You
> > move stuff into ttm_bo_util.c which not even remotely belongs in there.
> > 
> 
> The justification is that EuDebugger requires essentially the same functionality
> as ptrace -> vm_access. This patch simply adds a helper to achieve this. There
> is no functional change to the existing code.
> 
> Regarding the statement about ttm_bo_util.c, that seems quite aggressive. It is
> a TTM BO helper function, so it could logically belong in either ttm_bo.c or
> ttm_bo_util.c. A BO helper definitely shouldn't call into ttm_bo_vm.c, nor
> should it reside there. Perhaps I chose the wrong ttm_bo* file? I apologize for
> that. It would be helpful to know why you think this is the wrong place so I can
> better understand your expectations for TTM.

I also believe that the ttm_bo_util seems a good place for that, but
perhaps someone else has some other better ideas or suggestions there

> 
> Matt
> 
> > Regards,
> > Christian.
> > 
> > > 
> > > Matt
> > > 
> > > > Reported-by: Christoph Manszewski <christoph.manszewski@intel.com>
> > > > Suggested-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> > > > Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> > > > Tested-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> > > > Reviewed-by: Matthew Auld <matthew.auld@intel.com>
> > > > ---
> > > >   drivers/gpu/drm/ttm/ttm_bo_util.c | 86 +++++++++++++++++++++++++++++++
> > > >   drivers/gpu/drm/ttm/ttm_bo_vm.c   | 65 +----------------------
> > > >   include/drm/ttm/ttm_bo.h          |  2 +
> > > >   3 files changed, 89 insertions(+), 64 deletions(-)
> > > > 
> > > > diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
> > > > index d939925efa81..77e760ea7193 100644
> > > > --- a/drivers/gpu/drm/ttm/ttm_bo_util.c
> > > > +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
> > > > @@ -919,3 +919,89 @@ s64 ttm_lru_walk_for_evict(struct ttm_lru_walk *walk, struct ttm_device *bdev,
> > > >   	return progress;
> > > >   }
> > > > +
> > > > +static int ttm_bo_access_kmap(struct ttm_buffer_object *bo,
> > > > +			      unsigned long offset,
> > > > +			      void *buf, int len, int write)
> > > > +{
> > > > +	unsigned long page = offset >> PAGE_SHIFT;
> > > > +	unsigned long bytes_left = len;
> > > > +	int ret;
> > > > +
> > > > +	/* Copy a page at a time, that way no extra virtual address
> > > > +	 * mapping is needed
> > > > +	 */
> > > > +	offset -= page << PAGE_SHIFT;
> > > > +	do {
> > > > +		unsigned long bytes = min(bytes_left, PAGE_SIZE - offset);
> > > > +		struct ttm_bo_kmap_obj map;
> > > > +		void *ptr;
> > > > +		bool is_iomem;
> > > > +
> > > > +		ret = ttm_bo_kmap(bo, page, 1, &map);
> > > > +		if (ret)
> > > > +			return ret;
> > > > +
> > > > +		ptr = (void *)ttm_kmap_obj_virtual(&map, &is_iomem) + offset;
> > > > +		WARN_ON_ONCE(is_iomem);
> > > > +		if (write)
> > > > +			memcpy(ptr, buf, bytes);
> > > > +		else
> > > > +			memcpy(buf, ptr, bytes);
> > > > +		ttm_bo_kunmap(&map);
> > > > +
> > > > +		page++;
> > > > +		buf += bytes;
> > > > +		bytes_left -= bytes;
> > > > +		offset = 0;
> > > > +	} while (bytes_left);
> > > > +
> > > > +	return len;
> > > > +}
> > > > +
> > > > +/**
> > > > + * ttm_bo_access - Helper to access a buffer object
> > > > + *
> > > > + * @bo: ttm buffer object
> > > > + * @offset: access offset into buffer object
> > > > + * @buf: pointer to caller memory to read into or write from
> > > > + * @len: length of access
> > > > + * @write: write access
> > > > + *
> > > > + * Utility function to access a buffer object. Useful when buffer object cannot
> > > > + * be easily mapped (non-contiguous, non-visible, etc...).
> > > > + *
> > > > + * Returns:
> > > > + * @len if successful, negative error code on failure.
> > > > + */
> > > > +int ttm_bo_access(struct ttm_buffer_object *bo, unsigned long offset,
> > > > +		  void *buf, int len, int write)
> > > > +{
> > > > +	int ret;
> > > > +
> > > > +	if (len < 1 || (offset + len) > bo->base.size)
> > > > +		return -EIO;
> > > > +
> > > > +	ret = ttm_bo_reserve(bo, true, false, NULL);
> > > > +	if (ret)
> > > > +		return ret;
> > > > +
> > > > +	switch (bo->resource->mem_type) {
> > > > +	case TTM_PL_SYSTEM:
> > > > +		fallthrough;
> > > > +	case TTM_PL_TT:
> > > > +		ret = ttm_bo_access_kmap(bo, offset, buf, len, write);
> > > > +		break;
> > > > +	default:
> > > > +		if (bo->bdev->funcs->access_memory)
> > > > +			ret = bo->bdev->funcs->access_memory
> > > > +				(bo, offset, buf, len, write);
> > > > +		else
> > > > +			ret = -EIO;
> > > > +	}
> > > > +
> > > > +	ttm_bo_unreserve(bo);
> > > > +
> > > > +	return ret;
> > > > +}
> > > > +EXPORT_SYMBOL(ttm_bo_access);
> > > > diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
> > > > index 2c699ed1963a..20b1e5f78684 100644
> > > > --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
> > > > +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
> > > > @@ -366,45 +366,6 @@ void ttm_bo_vm_close(struct vm_area_struct *vma)
> > > >   }
> > > >   EXPORT_SYMBOL(ttm_bo_vm_close);
> > > > -static int ttm_bo_vm_access_kmap(struct ttm_buffer_object *bo,
> > > > -				 unsigned long offset,
> > > > -				 uint8_t *buf, int len, int write)
> > > > -{
> > > > -	unsigned long page = offset >> PAGE_SHIFT;
> > > > -	unsigned long bytes_left = len;
> > > > -	int ret;
> > > > -
> > > > -	/* Copy a page at a time, that way no extra virtual address
> > > > -	 * mapping is needed
> > > > -	 */
> > > > -	offset -= page << PAGE_SHIFT;
> > > > -	do {
> > > > -		unsigned long bytes = min(bytes_left, PAGE_SIZE - offset);
> > > > -		struct ttm_bo_kmap_obj map;
> > > > -		void *ptr;
> > > > -		bool is_iomem;
> > > > -
> > > > -		ret = ttm_bo_kmap(bo, page, 1, &map);
> > > > -		if (ret)
> > > > -			return ret;
> > > > -
> > > > -		ptr = (uint8_t *)ttm_kmap_obj_virtual(&map, &is_iomem) + offset;
> > > > -		WARN_ON_ONCE(is_iomem);
> > > > -		if (write)
> > > > -			memcpy(ptr, buf, bytes);
> > > > -		else
> > > > -			memcpy(buf, ptr, bytes);
> > > > -		ttm_bo_kunmap(&map);
> > > > -
> > > > -		page++;
> > > > -		buf += bytes;
> > > > -		bytes_left -= bytes;
> > > > -		offset = 0;
> > > > -	} while (bytes_left);
> > > > -
> > > > -	return len;
> > > > -}
> > > > -
> > > >   int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
> > > >   		     void *buf, int len, int write)
> > > >   {
> > > > @@ -412,32 +373,8 @@ int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
> > > >   	unsigned long offset = (addr) - vma->vm_start +
> > > >   		((vma->vm_pgoff - drm_vma_node_start(&bo->base.vma_node))
> > > >   		 << PAGE_SHIFT);
> > > > -	int ret;
> > > > -
> > > > -	if (len < 1 || (offset + len) > bo->base.size)
> > > > -		return -EIO;
> > > > -	ret = ttm_bo_reserve(bo, true, false, NULL);
> > > > -	if (ret)
> > > > -		return ret;
> > > > -
> > > > -	switch (bo->resource->mem_type) {
> > > > -	case TTM_PL_SYSTEM:
> > > > -		fallthrough;
> > > > -	case TTM_PL_TT:
> > > > -		ret = ttm_bo_vm_access_kmap(bo, offset, buf, len, write);
> > > > -		break;
> > > > -	default:
> > > > -		if (bo->bdev->funcs->access_memory)
> > > > -			ret = bo->bdev->funcs->access_memory(
> > > > -				bo, offset, buf, len, write);
> > > > -		else
> > > > -			ret = -EIO;
> > > > -	}
> > > > -
> > > > -	ttm_bo_unreserve(bo);
> > > > -
> > > > -	return ret;
> > > > +	return ttm_bo_access(bo, offset, buf, len, write);
> > > >   }
> > > >   EXPORT_SYMBOL(ttm_bo_vm_access);
> > > > diff --git a/include/drm/ttm/ttm_bo.h b/include/drm/ttm/ttm_bo.h
> > > > index 5804408815be..8ea11cd8df39 100644
> > > > --- a/include/drm/ttm/ttm_bo.h
> > > > +++ b/include/drm/ttm/ttm_bo.h
> > > > @@ -421,6 +421,8 @@ void ttm_bo_unpin(struct ttm_buffer_object *bo);
> > > >   int ttm_bo_evict_first(struct ttm_device *bdev,
> > > >   		       struct ttm_resource_manager *man,
> > > >   		       struct ttm_operation_ctx *ctx);
> > > > +int ttm_bo_access(struct ttm_buffer_object *bo, unsigned long offset,
> > > > +		  void *buf, int len, int write);
> > > >   vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
> > > >   			     struct vm_fault *vmf);
> > > >   vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
> > > > -- 
> > > > 2.34.1
> > > > 
> >