drm/amdgpu: compare MES firmware version ucode for gfx11

MES firmware should report the same version whether read from
the register or from the firmware ucode binary. This is not
always the case, so add a log when they mismatch.

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index c9467b26e42ce0e86c4ccf0e2f3c5db8022a32ff..e3972673fd641611242c3b5ce6917b45675a5611 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -781,6 +781,18 @@ out:
        return r;
 }
 
+void amdgpu_mes_validate_fw_version(struct amdgpu_device *adev)
+{
+       u32 fw_from_ucode = adev->mes.fw_version[AMDGPU_MES_SCHED_PIPE];
+       u32 fw_from_reg = adev->mes.sched_version & AMDGPU_MES_VERSION_MASK;
+
+       if (fw_from_ucode != fw_from_reg)
+               dev_info(adev->dev,
+                        "MES firmware reports incorrect version in ucode binary (0x%x vs 0x%x)\n",
+                        fw_from_ucode, fw_from_reg);
+}
+
+
 bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev)
 {
        uint32_t mes_rev = adev->mes.sched_version & AMDGPU_MES_VERSION_MASK;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 93990d4990f2e4eccd1b33694e6972bd5e68b53e..fdd06a17520a29513983fb5cbef3b1deae11fc58 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -441,6 +441,7 @@ struct amdgpu_mes_funcs {
        (adev)->mes.kiq_hw_fini((adev), (xcc_id))
 
 int amdgpu_mes_init_microcode(struct amdgpu_device *adev, int pipe);
+void amdgpu_mes_validate_fw_version(struct amdgpu_device *adev);
 int amdgpu_mes_init(struct amdgpu_device *adev);
 void amdgpu_mes_fini(struct amdgpu_device *adev);
 

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 147ba2942690fd391fbc2d42edb8c039b1642523..ac6d4f2773363c2320985110b7fddf6cc52b11c8 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -1688,6 +1688,7 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block)
        if (r)
                goto failure;
 
+       amdgpu_mes_validate_fw_version(adev);
 out:
        /*
         * Disable KIQ ring usage from the driver once MES is enabled.