[PATCH 1/1] drm/amdgpu: Improve error handling for HMM

[PATCH 1/1] drm/amdgpu: Improve error handling for HMM

[Kuehling, Felix]

Use unsigned long for number of pages.

Check that pfns are valid after hmm_vma_fault. If they are not,
return an error instead of continuing with invalid page pointers and
PTEs.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index c14198737dcd..38ce11e338e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -734,10 +734,11 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
 	struct mm_struct *mm = gtt->usertask->mm;
 	unsigned long start = gtt->userptr;
 	unsigned long end = start + ttm->num_pages * PAGE_SIZE;
-	struct hmm_range *ranges;
 	struct vm_area_struct *vma = NULL, *vmas[MAX_NR_VMAS];
+	struct hmm_range *ranges;
+	unsigned long nr_pages, i;
 	uint64_t *pfns, f;
-	int r = 0, i, nr_pages;
+	int r = 0;
 
 	if (!mm) /* Happens during process shutdown */
 		return -ESRCH;
@@ -813,8 +814,14 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
 
 	up_read(&mm->mmap_sem);
 
-	for (i = 0; i < ttm->num_pages; i++)
+	for (i = 0; i < ttm->num_pages; i++) {
 		pages[i] = hmm_pfn_to_page(&ranges[0], pfns[i]);
+		if (!pages[i]) {
+			pr_err("Page fault failed for pfn[%lu] = 0x%llx\n",
+			       i, pfns[i]);
+			goto out_invalid_pfn;
+		}
+	}
 	gtt->ranges = ranges;
 
 	return 0;
@@ -827,6 +834,13 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
 	up_read(&mm->mmap_sem);
 
 	return r;
+
+out_invalid_pfn:
+	for (i = 0; i < gtt->nr_ranges; i++)
+		hmm_vma_range_done(&ranges[i]);
+	kvfree(pfns);
+	kvfree(ranges);
+	return -ENOMEM;
 }
 
 /**
@@ -871,7 +885,7 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
  */
 void amdgpu_ttm_tt_set_user_pages(struct ttm_tt *ttm, struct page **pages)
 {
-	unsigned i;
+	unsigned long i;
 
 	for (i = 0; i < ttm->num_pages; ++i)
 		ttm->pages[i] = pages ? pages[i] : NULL;
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH 1/1] drm/amdgpu: Improve error handling for HMM

[Yang, Philip]

On 2019-05-07 5:52 p.m., Kuehling, Felix wrote:
> Use unsigned long for number of pages.
> 
> Check that pfns are valid after hmm_vma_fault. If they are not,
> return an error instead of continuing with invalid page pointers and
> PTEs.
> 
> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>

Reviewed-by: Philip Yang <Philip.Yang@amd.com>

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 22 ++++++++++++++++++----
>   1 file changed, 18 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index c14198737dcd..38ce11e338e0 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -734,10 +734,11 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
>   	struct mm_struct *mm = gtt->usertask->mm;
>   	unsigned long start = gtt->userptr;
>   	unsigned long end = start + ttm->num_pages * PAGE_SIZE;
> -	struct hmm_range *ranges;
>   	struct vm_area_struct *vma = NULL, *vmas[MAX_NR_VMAS];
> +	struct hmm_range *ranges;
> +	unsigned long nr_pages, i;
>   	uint64_t *pfns, f;
> -	int r = 0, i, nr_pages;
> +	int r = 0;
>   
>   	if (!mm) /* Happens during process shutdown */
>   		return -ESRCH;
> @@ -813,8 +814,14 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
>   
>   	up_read(&mm->mmap_sem);
>   
> -	for (i = 0; i < ttm->num_pages; i++)
> +	for (i = 0; i < ttm->num_pages; i++) {
>   		pages[i] = hmm_pfn_to_page(&ranges[0], pfns[i]);
> +		if (!pages[i]) {
> +			pr_err("Page fault failed for pfn[%lu] = 0x%llx\n",
> +			       i, pfns[i]);
> +			goto out_invalid_pfn;
> +		}
> +	}
>   	gtt->ranges = ranges;
>   
>   	return 0;
> @@ -827,6 +834,13 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
>   	up_read(&mm->mmap_sem);
>   
>   	return r;
> +
> +out_invalid_pfn:
> +	for (i = 0; i < gtt->nr_ranges; i++)
> +		hmm_vma_range_done(&ranges[i]);
> +	kvfree(pfns);
> +	kvfree(ranges);
> +	return -ENOMEM;
>   }
>   
>   /**
> @@ -871,7 +885,7 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
>    */
>   void amdgpu_ttm_tt_set_user_pages(struct ttm_tt *ttm, struct page **pages)
>   {
> -	unsigned i;
> +	unsigned long i;
>   
>   	for (i = 0; i < ttm->num_pages; ++i)
>   		ttm->pages[i] = pages ? pages[i] : NULL;
> 
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx