[PATCH 2/2] drm/amdgpu: add gart recovery by gtt list V2

[David1.Zhou@xxxxxxx (Chunming Zhou)]

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

Change-Id: I8daf687d43b51d69f9be36cae8b265deb88e5754
Signed-off-by: Chunming Zhou <David1.Zhou at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  5 +++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 25 +++++++++++++++++++++++++
 3 files changed, 31 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 6f0af25..ddd03d0 100644
--- 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 a968fc6..3ba17e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2230,6 +2230,11 @@ 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 0c561c6..45f6c39 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -674,6 +674,31 @@ 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;
-- 
1.9.1