[PATCH] drm/amd/pm: fix the high voltage issue after unload

[Zhang, Hawking]

[AMD Official Use Only - General]

Reviewed-by: Hawking Zhang <Hawking.Zhang at amd.com>

Regards,
Hawking
-----Original Message-----
From: Kenneth Feng <kenneth.feng at amd.com>
Sent: Thursday, March 28, 2024 14:02
To: amd-gfx at lists.freedesktop.org
Cc: Zhang, Hawking <Hawking.Zhang at amd.com>; Feng, Kenneth <Kenneth.Feng at amd.com>
Subject: [PATCH] drm/amd/pm: fix the high voltage issue after unload

fix the high voltage issue after unload on smu 13.0.10

Signed-off-by: Kenneth Feng <kenneth.feng at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c    | 26 ++++++++++--------
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c     | 27 +++++++++++++++++--
 drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h |  1 +  .../drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c  |  8 +++++-
 4 files changed, 48 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 12dc71a6b5db..1b9136bb7f62 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4138,18 +4138,22 @@ int amdgpu_device_init(struct amdgpu_device *adev,
                                        adev->ip_blocks[i].status.hw = true;
                                }
                        }
+               } else if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) &&
+                                  !amdgpu_device_has_display_hardware(adev)) {
+                                       r = psp_gpu_reset(adev);
                } else {
-                       tmp = amdgpu_reset_method;
-                       /* It should do a default reset when loading or reloading the driver,
-                        * regardless of the module parameter reset_method.
-                        */
-                       amdgpu_reset_method = AMD_RESET_METHOD_NONE;
-                       r = amdgpu_asic_reset(adev);
-                       amdgpu_reset_method = tmp;
-                       if (r) {
-                               dev_err(adev->dev, "asic reset on init failed\n");
-                               goto failed;
-                       }
+                               tmp = amdgpu_reset_method;
+                               /* It should do a default reset when loading or reloading the driver,
+                                * regardless of the module parameter reset_method.
+                                */
+                               amdgpu_reset_method = AMD_RESET_METHOD_NONE;
+                               r = amdgpu_asic_reset(adev);
+                               amdgpu_reset_method = tmp;
+               }
+
+               if (r) {
+                 dev_err(adev->dev, "asic reset on init failed\n");
+                 goto failed;
                }
        }

diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 246b211b1e85..65333141b1c1 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -735,7 +735,7 @@ static int smu_early_init(void *handle)
        smu->adev = adev;
        smu->pm_enabled = !!amdgpu_dpm;
        smu->is_apu = false;
-       smu->smu_baco.state = SMU_BACO_STATE_EXIT;
+       smu->smu_baco.state = SMU_BACO_STATE_NONE;
        smu->smu_baco.platform_support = false;
        smu->user_dpm_profile.fan_mode = -1;

@@ -1966,10 +1966,25 @@ static int smu_smc_hw_cleanup(struct smu_context *smu)
        return 0;
 }

+static int smu_reset_mp1_state(struct smu_context *smu) {
+       struct amdgpu_device *adev = smu->adev;
+       int ret = 0;
+
+       if ((!adev->in_runpm) && (!adev->in_suspend) &&
+               (!amdgpu_in_reset(adev)) && amdgpu_ip_version(adev, MP1_HWIP, 0) ==
+                                                                       IP_VERSION(13, 0, 10) &&
+               !amdgpu_device_has_display_hardware(adev))
+               ret = smu_set_mp1_state(smu, PP_MP1_STATE_UNLOAD);
+
+       return ret;
+}
+
 static int smu_hw_fini(void *handle)
 {
        struct amdgpu_device *adev = (struct amdgpu_device *)handle;
        struct smu_context *smu = adev->powerplay.pp_handle;
+       int ret;

        if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
                return 0;
@@ -1987,7 +2002,15 @@ static int smu_hw_fini(void *handle)

        adev->pm.dpm_enabled = false;

-       return smu_smc_hw_cleanup(smu);
+       ret = smu_smc_hw_cleanup(smu);
+       if (ret)
+               return ret;
+
+       ret = smu_reset_mp1_state(smu);
+       if (ret)
+               return ret;
+
+       return 0;
 }

 static void smu_late_fini(void *handle) diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index a870bdd49a4e..1fa81575788c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -424,6 +424,7 @@ enum smu_reset_mode {  enum smu_baco_state {
        SMU_BACO_STATE_ENTER = 0,
        SMU_BACO_STATE_EXIT,
+       SMU_BACO_STATE_NONE,
 };

 struct smu_baco_context {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 5a857cb999f5..f4df4cceb06f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2752,7 +2752,13 @@ static int smu_v13_0_0_set_mp1_state(struct smu_context *smu,

        switch (mp1_state) {
        case PP_MP1_STATE_UNLOAD:
-               ret = smu_cmn_set_mp1_state(smu, mp1_state);
+               ret = smu_cmn_send_smc_msg_with_param(smu,
+                                                                                         SMU_MSG_PrepareMp1ForUnload,
+                                                                                         0x55, NULL);
+
+               if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT)
+                       ret = smu_v13_0_disable_pmfw_state(smu);
+
                break;
        default:
                /* Ignore others */
--
2.34.1