drm/amdgpu: correctly toggle gfx on/off around RLC_SPM_* register access

As part of the ib padding process, accessing the RLC_SPM_* register may
trigger gfx hang. Since gfxoff may be already kicked during the whole period.
To address that, we manually toggle gfx on/off around the RLC_SPM_*
register access.

This can resolve the gfx hang issue observed on running Talos with RDP launched
in parallel.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Guchun Chen <guchun.chen@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/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index b53b36f..e7dfeb4 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -8249,6 +8249,9 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
        u32 reg, data;
+
+       amdgpu_gfx_off_ctrl(adev, false);
+
        /* not for *_SOC15 */
        reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL);
        if (amdgpu_sriov_is_pp_one_vf(adev))
@@ -8263,6 +8266,8 @@ static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
                WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data);
        else
                WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+
+       amdgpu_gfx_off_ctrl(adev, true);
 }
 
 static bool gfx_v10_0_check_rlcg_range(struct amdgpu_device *adev,

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 37b4a3d..d17a6f3 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -3575,12 +3575,16 @@ static void gfx_v7_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
        u32 data;
 
+       amdgpu_gfx_off_ctrl(adev, false);
+
        data = RREG32(mmRLC_SPM_VMID);
 
        data &= ~RLC_SPM_VMID__RLC_SPM_VMID_MASK;
        data |= (vmid & RLC_SPM_VMID__RLC_SPM_VMID_MASK) << RLC_SPM_VMID__RLC_SPM_VMID__SHIFT;
 
        WREG32(mmRLC_SPM_VMID, data);
+
+       amdgpu_gfx_off_ctrl(adev, true);
 }
 
 static void gfx_v7_0_enable_cgcg(struct amdgpu_device *adev, bool enable)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index e0302c2..5f112ef 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -5624,6 +5624,8 @@ static void gfx_v8_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
        u32 data;
 
+       amdgpu_gfx_off_ctrl(adev, false);
+
        if (amdgpu_sriov_is_pp_one_vf(adev))
                data = RREG32_NO_KIQ(mmRLC_SPM_VMID);
        else
@@ -5636,6 +5638,8 @@ static void gfx_v8_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
                WREG32_NO_KIQ(mmRLC_SPM_VMID, data);
        else
                WREG32(mmRLC_SPM_VMID, data);
+
+       amdgpu_gfx_off_ctrl(adev, true);
 }
 
 static const struct amdgpu_rlc_funcs iceland_rlc_funcs = {

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index be803eb..b4b80f2 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -5104,6 +5104,8 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
        u32 reg, data;
 
+       amdgpu_gfx_off_ctrl(adev, false);
+
        reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL);
        if (amdgpu_sriov_is_pp_one_vf(adev))
                data = RREG32_NO_KIQ(reg);
@@ -5117,6 +5119,8 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
                WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data);
        else
                WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+
+       amdgpu_gfx_off_ctrl(adev, true);
 }
 
 static bool gfx_v9_0_check_rlcg_range(struct amdgpu_device *adev,