drm/amdgpu: Support passing amdgpu critical error to host via GPU Mailbox.

This feature works for SRIOV enviroment. For non-SRIOV enviroment, the
trans_error function does nothing.

The error information includes error_code (16bit), error_flags(16bit)
and error_data(64bit). Since there are not many errors, we keep the
errors in an array and transfer all errors to Host before amdgpu
initialization function (amdgpu_device_init) exit.

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

1 files changed, 18 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ae4387fd2b65..88e45c6d36ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -53,6 +53,7 @@
 #include "bif/bif_4_1_d.h"
 #include <linux/pci.h>
 #include <linux/firmware.h>
+#include "amdgpu_vf_error.h"
 
 MODULE_FIRMWARE("amdgpu/vega10_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/raven_gpu_info.bin");
@@ -2134,6 +2135,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
         r = amdgpu_atombios_init(adev);
         if (r) {
                 dev_err(adev->dev, "amdgpu_atombios_init failed\n");
+                amdgpu_vf_error_put(AMDGIM_ERROR_VF_ATOMBIOS_INIT_FAIL, 0, 0);
                 goto failed;
         }
 
@@ -2144,6 +2146,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
         if (amdgpu_vpost_needed(adev)) {
                 if (!adev->bios) {
                         dev_err(adev->dev, "no vBIOS found\n");
+                        amdgpu_vf_error_put(AMDGIM_ERROR_VF_NO_VBIOS, 0, 0);
                         r = -EINVAL;
                         goto failed;
                 }
@@ -2151,6 +2154,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
                 r = amdgpu_atom_asic_init(adev->mode_info.atom_context);
                 if (r) {
                         dev_err(adev->dev, "gpu post error!\n");
+                        amdgpu_vf_error_put(AMDGIM_ERROR_VF_GPU_POST_ERROR, 0, 0);
                         goto failed;
                 }
         } else {
@@ -2162,7 +2166,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
                 r = amdgpu_atombios_get_clock_info(adev);
                 if (r) {
                         dev_err(adev->dev, "amdgpu_atombios_get_clock_info failed\n");
-                        return r;
+                        amdgpu_vf_error_put(AMDGIM_ERROR_VF_ATOMBIOS_GET_CLOCK_FAIL, 0, 0);
+                        goto failed;
                 }
                 /* init i2c buses */
                 amdgpu_atombios_i2c_init(adev);
@@ -2172,6 +2177,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
         r = amdgpu_fence_driver_init(adev);
         if (r) {
                 dev_err(adev->dev, "amdgpu_fence_driver_init failed\n");
+                amdgpu_vf_error_put(AMDGIM_ERROR_VF_FENCE_INIT_FAIL, 0, 0);
                 goto failed;
         }
 
@@ -2181,6 +2187,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
         r = amdgpu_init(adev);
         if (r) {
                 dev_err(adev->dev, "amdgpu_init failed\n");
+                amdgpu_vf_error_put(AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL, 0, 0);
                 amdgpu_fini(adev);
                 goto failed;
         }
@@ -2200,6 +2207,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
         r = amdgpu_ib_pool_init(adev);
         if (r) {
                 dev_err(adev->dev, "IB initialization failed (%d).\n", r);
+                amdgpu_vf_error_put(AMDGIM_ERROR_VF_IB_INIT_FAIL, 0, r);
                 goto failed;
         }
 
@@ -2244,12 +2252,14 @@ int amdgpu_device_init(struct amdgpu_device *adev,
         r = amdgpu_late_init(adev);
         if (r) {
                 dev_err(adev->dev, "amdgpu_late_init failed\n");
+                amdgpu_vf_error_put(AMDGIM_ERROR_VF_AMDGPU_LATE_INIT_FAIL, 0, r);
                 goto failed;
         }
 
         return 0;
 
 failed:
+        amdgpu_vf_error_trans_all(adev);
         if (runtime)
                 vga_switcheroo_fini_domain_pm_ops(adev->dev);
         return r;
@@ -2937,6 +2947,7 @@ out:
                 }
         } else {
                 dev_err(adev->dev, "asic resume failed (%d).\n", r);
+                amdgpu_vf_error_put(AMDGIM_ERROR_VF_ASIC_RESUME_FAIL, 0, r);
                 for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
                         if (adev->rings[i] && adev->rings[i]->sched.thread) {
                                 kthread_unpark(adev->rings[i]->sched.thread);
@@ -2947,12 +2958,16 @@ out:
         drm_helper_resume_force_mode(adev->ddev);
 
         ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, resched);
-        if (r)
+        if (r) {
                 /* bad news, how to tell it to userspace ? */
                 dev_info(adev->dev, "GPU reset failed\n");
-        else
+                amdgpu_vf_error_put(AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
+        }
+        else {
                 dev_info(adev->dev, "GPU reset successed!\n");
+        }
 
+        amdgpu_vf_error_trans_all(adev);
         return r;
 }