drm/amdgpu: adjust the kfd reset sequence in reset sriov function

This change revert previous commits:
9f4f2c1a3524 ("drm/amd/amdgpu: fix the kfd pre_reset sequence in sriov")
271fd38ce56d ("drm/amdgpu: move kfd post_reset out of reset_sriov function")

This change moves the amdgpu_amdkfd_pre_reset to an earlier place
in amdgpu_device_reset_sriov, presumably to address the sequence issue
that the first patch was originally meant to fix.

Some register access(GRBM_GFX_CNTL) only be allowed on full access
mode. Move kfd_pre_reset and  kfd_post_reset back inside reset_sriov
function.

Fixes: 9f4f2c1a3524 ("drm/amd/amdgpu: fix the kfd pre_reset sequence in sriov")
Fixes: 271fd38ce56d ("drm/amdgpu: move kfd post_reset out of reset_sriov function")
Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index efa9ff5..a1c1446 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4286,6 +4286,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 {
        int r;
 
+       amdgpu_amdkfd_pre_reset(adev);
+
        if (from_hypervisor)
                r = amdgpu_virt_request_full_gpu(adev, true);
        else
@@ -4313,6 +4315,7 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 
        amdgpu_irq_gpu_reset_resume_helper(adev);
        r = amdgpu_ib_ring_tests(adev);
+       amdgpu_amdkfd_post_reset(adev);
 
 error:
        if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
@@ -5027,7 +5030,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
                cancel_delayed_work_sync(&tmp_adev->delayed_init_work);
 
-               amdgpu_amdkfd_pre_reset(tmp_adev);
+               if (!amdgpu_sriov_vf(tmp_adev))
+                       amdgpu_amdkfd_pre_reset(tmp_adev);
 
                /*
                 * Mark these ASICs to be reseted as untracked first
@@ -5145,9 +5149,9 @@ skip_hw_reset:
 
 skip_sched_resume:
        list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
-               /* unlock kfd */
-               if (!need_emergency_restart)
-                       amdgpu_amdkfd_post_reset(tmp_adev);
+               /* unlock kfd: SRIOV would do it separately */
+               if (!need_emergency_restart && !amdgpu_sriov_vf(tmp_adev))
+                       amdgpu_amdkfd_post_reset(tmp_adev);
 
                /* kfd_post_reset will do nothing if kfd device is not initialized,
                 * need to bring up kfd here if it's not be initialized before