drm/amdgpu: Improve error handling for HMM

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>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index b25922e3d1ed4f5cc6e92de0c1000fef37aa2502..7138dc1dd1f44b9e871984c5a724481e99df7422 100644 (file)
--- 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 @@ out:
        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;