drm/amdgpu: add gart recovery by gtt list V2

V2:
a. gart recovery should be ahead of ring test.
b. rename to amdgpu_ttm_recover_gart

Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 829b0b4eb838b5f6b434d7c3d722f60b17962210..2cfaa6429c64a544ed7d34822ef480b30642c117 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -620,6 +620,7 @@ void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset,
 int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset,
                     int pages, struct page **pagelist,
                     dma_addr_t *dma_addr, uint32_t flags);
+int amdgpu_ttm_recover_gart(struct amdgpu_device *adev);
 
 /*
  * GPU MC structures, functions & helpers

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index bfdd445a8bb643e6fc78aa711e54bc320d0be5b7..c2459abb408dfa790e0ff4724371b6e9e20adab9 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2206,6 +2206,11 @@ retry:
        }
        if (!r) {
                amdgpu_irq_gpu_reset_resume_helper(adev);
+               if (need_full_reset && amdgpu_need_backup(adev)) {
+                       r = amdgpu_ttm_recover_gart(adev);
+                       if (r)
+                               DRM_ERROR("gart recovery failed!!!\n");
+               }
                r = amdgpu_ib_ring_tests(adev);
                if (r) {
                        dev_err(adev->dev, "ib ring test failed (%d).\n", r);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 26ca3dd183ebd855f2e714fec60a315e7a9a77e6..3beb10b75746de5f20d3820711eaa921c00cc0f1 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -673,6 +673,31 @@ static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm,
        return 0;
 }
 
+int amdgpu_ttm_recover_gart(struct amdgpu_device *adev)
+{
+       struct amdgpu_ttm_tt *gtt, *tmp;
+       struct ttm_mem_reg bo_mem;
+       uint32_t flags;
+       int r;
+
+       bo_mem.mem_type = TTM_PL_TT;
+       spin_lock(&adev->gtt_list_lock);
+       list_for_each_entry_safe(gtt, tmp, &adev->gtt_list, list) {
+               flags = amdgpu_ttm_tt_pte_flags(gtt->adev, &gtt->ttm.ttm, &bo_mem);
+               r = amdgpu_gart_bind(adev, gtt->offset, gtt->ttm.ttm.num_pages,
+                                    gtt->ttm.ttm.pages, gtt->ttm.dma_address,
+                                    flags);
+               if (r) {
+                       spin_unlock(&adev->gtt_list_lock);
+                       DRM_ERROR("failed to bind %lu pages at 0x%08X\n",
+                                 gtt->ttm.ttm.num_pages, (unsigned)gtt->offset);
+                       return r;
+               }
+       }
+       spin_unlock(&adev->gtt_list_lock);
+       return 0;
+}
+
 static int amdgpu_ttm_backend_unbind(struct ttm_tt *ttm)
 {
        struct amdgpu_ttm_tt *gtt = (void *)ttm;