From: Evan Quan <evan.quan@xxxxxxx>
[ Upstream commit 9c26ddb1c5b6e30c6bca48b8ad9205d96efe93d0 ]
Fix TCP hang when a lightweight invalidation happens on Navi1x.
Signed-off-by: Evan Quan <evan.quan@xxxxxxx>
Reviewed-by: Lijo Lazar <lijo.lazar@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 95 ++++++++++++++++++++++++++
1 file changed, 95 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 2342c5d216f9..5c40912b51d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -7744,6 +7744,97 @@ static void gfx_v10_0_update_fine_grain_clock_gating(struct amdgpu_device *adev,
}
}
+static void gfx_v10_0_apply_medium_grain_clock_gating_workaround(struct amdgpu_device *adev)
+{
+ uint32_t reg_data = 0;
+ uint32_t reg_idx = 0;
+ uint32_t i;
+
+ const uint32_t tcp_ctrl_regs[] = {
+ mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP00_CU1_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP01_CU0_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP01_CU1_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP02_CU0_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP02_CU1_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP10_CU0_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP10_CU1_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP11_CU0_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP11_CU1_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP12_CU0_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP12_CU1_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP00_CU0_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP00_CU1_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP01_CU0_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP01_CU1_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP02_CU0_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP02_CU1_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP10_CU0_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP10_CU1_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP11_CU0_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP11_CU1_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP12_CU0_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP12_CU1_TCP_CTRL_REG
+ };
+
+ const uint32_t tcp_ctrl_regs_nv12[] = {
+ mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP00_CU1_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP01_CU0_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP01_CU1_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP02_CU0_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP02_CU1_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP10_CU0_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP10_CU1_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP11_CU0_TCP_CTRL_REG,
+ mmCGTS_SA0_WGP11_CU1_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP00_CU0_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP00_CU1_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP01_CU0_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP01_CU1_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP02_CU0_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP02_CU1_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP10_CU0_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP10_CU1_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP11_CU0_TCP_CTRL_REG,
+ mmCGTS_SA1_WGP11_CU1_TCP_CTRL_REG,
+ };
+
+ const uint32_t sm_ctlr_regs[] = {
+ mmCGTS_SA0_QUAD0_SM_CTRL_REG,
+ mmCGTS_SA0_QUAD1_SM_CTRL_REG,
+ mmCGTS_SA1_QUAD0_SM_CTRL_REG,
+ mmCGTS_SA1_QUAD1_SM_CTRL_REG
+ };
+
+ if (adev->asic_type == CHIP_NAVI12) {
+ for (i = 0; i < ARRAY_SIZE(tcp_ctrl_regs_nv12); i++) {
+ reg_idx = adev->reg_offset[GC_HWIP][0][mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG_BASE_IDX] +
+ tcp_ctrl_regs_nv12[i];
+ reg_data = RREG32(reg_idx);
+ reg_data |= CGTS_SA0_WGP00_CU0_TCP_CTRL_REG__TCPI_LS_OVERRIDE_MASK;
+ WREG32(reg_idx, reg_data);
+ }
+ } else {
+ for (i = 0; i < ARRAY_SIZE(tcp_ctrl_regs); i++) {
+ reg_idx = adev->reg_offset[GC_HWIP][0][mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG_BASE_IDX] +
+ tcp_ctrl_regs[i];
+ reg_data = RREG32(reg_idx);
+ reg_data |= CGTS_SA0_WGP00_CU0_TCP_CTRL_REG__TCPI_LS_OVERRIDE_MASK;
+ WREG32(reg_idx, reg_data);
+ }
+ }
+
+ for (i = 0; i < ARRAY_SIZE(sm_ctlr_regs); i++) {
+ reg_idx = adev->reg_offset[GC_HWIP][0][mmCGTS_SA0_QUAD0_SM_CTRL_REG_BASE_IDX] +
+ sm_ctlr_regs[i];
+ reg_data = RREG32(reg_idx);
+ reg_data &= ~CGTS_SA0_QUAD0_SM_CTRL_REG__SM_MODE_MASK;
+ reg_data |= 2 << CGTS_SA0_QUAD0_SM_CTRL_REG__SM_MODE__SHIFT;
+ WREG32(reg_idx, reg_data);
+ }
+}
+
static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
bool enable)
{
@@ -7760,6 +7851,10 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
gfx_v10_0_update_3d_clock_gating(adev, enable);
/* === CGCG + CGLS === */
gfx_v10_0_update_coarse_grain_clock_gating(adev, enable);
+
+ if ((adev->asic_type >= CHIP_NAVI10) &&
+ (adev->asic_type <= CHIP_NAVI12))
+ gfx_v10_0_apply_medium_grain_clock_gating_workaround(adev);
} else {
/* CGCG/CGLS should be disabled before MGCG/MGLS
* === CGCG + CGLS ===
--
2.30.2
