drm/amdgpu: fix ring0 failed on pro card

the root cause is vram content is lost completely after pci reset.

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

1 files changed, 50 insertions, 7 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e4d9aa470278..3c95e1858aa2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1872,13 +1872,40 @@ static int amdgpu_sriov_reinit_late(struct amdgpu_device *adev)
         return 0;
 }
 
-static int amdgpu_resume(struct amdgpu_device *adev)
+static int amdgpu_resume_phase1(struct amdgpu_device *adev)
 {
         int i, r;
 
         for (i = 0; i < adev->num_ip_blocks; i++) {
                 if (!adev->ip_blocks[i].status.valid)
                         continue;
+                if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON ||
+                                adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC ||
+                                adev->ip_blocks[i].version->type ==
+                                AMD_IP_BLOCK_TYPE_IH) {
+                        r = adev->ip_blocks[i].version->funcs->resume(adev);
+                        if (r) {
+                                DRM_ERROR("resume of IP block <%s> failed %d\n",
+                                          adev->ip_blocks[i].version->funcs->name, r);
+                                return r;
+                        }
+                }
+        }
+
+        return 0;
+}
+
+static int amdgpu_resume_phase2(struct amdgpu_device *adev)
+{
+        int i, r;
+
+        for (i = 0; i < adev->num_ip_blocks; i++) {
+                if (!adev->ip_blocks[i].status.valid)
+                        continue;
+                if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON ||
+                                adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC ||
+                                adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH )
+                        continue;
                 r = adev->ip_blocks[i].version->funcs->resume(adev);
                 if (r) {
                         DRM_ERROR("resume of IP block <%s> failed %d\n",
@@ -1890,6 +1917,18 @@ static int amdgpu_resume(struct amdgpu_device *adev)
         return 0;
 }
 
+static int amdgpu_resume(struct amdgpu_device *adev)
+{
+        int r;
+
+        r = amdgpu_resume_phase1(adev);
+        if (r)
+                return r;
+        r = amdgpu_resume_phase2(adev);
+
+        return r;
+}
+
 static void amdgpu_device_detect_sriov_bios(struct amdgpu_device *adev)
 {
         if (adev->is_atom_fw) {
@@ -2753,16 +2792,20 @@ retry:
 
                 if (!r) {
                         dev_info(adev->dev, "GPU reset succeeded, trying to resume\n");
-                        r = amdgpu_resume(adev);
+                        r = amdgpu_resume_phase1(adev);
+                        if (r)
+                                goto out;
+                        r = amdgpu_ttm_recover_gart(adev);
+                        if (r)
+                                goto out;
+                        r = amdgpu_resume_phase2(adev);
+                        if (r)
+                                goto out;
                 }
         }
+out:
         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);