[PATCH 1/2] drm/amdgpu/vcn4.0.5: split code along instances

[PATCH 1/2] drm/amdgpu/vcn4.0.5: split code along instances

[Eric Naim]

From: Alex Deucher <alexander.deucher@amd.com>

commit ecc9ab4e924b7eb9e2c4a668162aaa1d9d60d08c upstream

Split the code on a per instance basis.  This will allow
us to use the per instance functions in the future to
handle more things per instance.

v2: squash in fix for stop() from Boyuan

Reviewed-by: Boyuan Zhang <Boyuan.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Eric Naim <dnaim@cachyos.org>
Signed-off-by: Eric Naim <dnaim@cachyos.org>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c | 444 ++++++++++++------------
 1 file changed, 220 insertions(+), 224 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index d2dfdb141b24..9f9a9bf8dab9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -991,183 +991,178 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
  * vcn_v4_0_5_start - VCN start
  *
  * @adev: amdgpu_device pointer
+ * @i: instance to start
  *
  * Start VCN block
  */
-static int vcn_v4_0_5_start(struct amdgpu_device *adev)
+static int vcn_v4_0_5_start(struct amdgpu_device *adev, int i)
 {
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
-	int i, j, k, r;
+	int j, k, r;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, true, i);
-	}
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, true, i);
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v4_0_5_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
-			continue;
-		}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v4_0_5_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
 
-		/* disable VCN power gating */
-		vcn_v4_0_5_disable_static_power_gating(adev, i);
-
-		/* set VCN status busy */
-		tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
-		WREG32_SOC15(VCN, i, regUVD_STATUS, tmp);
-
-		/*SW clock gating */
-		vcn_v4_0_5_disable_clock_gating(adev, i);
-
-		/* enable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-				UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
-
-		/* disable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0,
-				~UVD_MASTINT_EN__VCPU_EN_MASK);
-
-		/* enable LMI MC and UMC channels */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0,
-				~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
-
-		/* setup regUVD_LMI_CTRL */
-		tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL);
-		WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp |
-				UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
-				UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
-				UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
-				UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
-
-		/* setup regUVD_MPC_CNTL */
-		tmp = RREG32_SOC15(VCN, i, regUVD_MPC_CNTL);
-		tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
-		tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
-		WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp);
-
-		/* setup UVD_MPC_SET_MUXA0 */
-		WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXA0,
-				((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
-				 (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
-				 (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
-				 (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
-
-		/* setup UVD_MPC_SET_MUXB0 */
-		WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXB0,
-				((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
-				 (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
-				 (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
-				 (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
-
-		/* setup UVD_MPC_SET_MUX */
-		WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUX,
-				((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
-				 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
-				 (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
-
-		vcn_v4_0_5_mc_resume(adev, i);
-
-		/* VCN global tiling registers */
-		WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG,
-				adev->gfx.config.gb_addr_config);
-
-		/* unblock VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0,
-				~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
-
-		/* release VCPU reset to boot */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-				~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-		for (j = 0; j < 10; ++j) {
-			uint32_t status;
-
-			for (k = 0; k < 100; ++k) {
-				status = RREG32_SOC15(VCN, i, regUVD_STATUS);
-				if (status & 2)
-					break;
-				mdelay(10);
-				if (amdgpu_emu_mode == 1)
-					msleep(1);
-			}
+	/* disable VCN power gating */
+	vcn_v4_0_5_disable_static_power_gating(adev, i);
+
+	/* set VCN status busy */
+	tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
+	WREG32_SOC15(VCN, i, regUVD_STATUS, tmp);
 
-			if (amdgpu_emu_mode == 1) {
-				r = -1;
-				if (status & 2) {
-					r = 0;
-					break;
-				}
-			} else {
+	/* SW clock gating */
+	vcn_v4_0_5_disable_clock_gating(adev, i);
+
+	/* enable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
+
+	/* disable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
+
+	/* enable LMI MC and UMC channels */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0,
+		 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+
+	tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
+	tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
+
+	/* setup regUVD_LMI_CTRL */
+	tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL);
+	WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp |
+		     UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+		     UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		     UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		     UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
+
+	/* setup regUVD_MPC_CNTL */
+	tmp = RREG32_SOC15(VCN, i, regUVD_MPC_CNTL);
+	tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
+	tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
+	WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp);
+
+	/* setup UVD_MPC_SET_MUXA0 */
+	WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXA0,
+		     ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
+
+	/* setup UVD_MPC_SET_MUXB0 */
+	WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXB0,
+		     ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
+
+	/* setup UVD_MPC_SET_MUX */
+	WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUX,
+		     ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
+		      (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
+
+	vcn_v4_0_5_mc_resume(adev, i);
+
+	/* VCN global tiling registers */
+	WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+
+	/* unblock VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	/* release VCPU reset to boot */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	for (j = 0; j < 10; ++j) {
+		uint32_t status;
+
+		for (k = 0; k < 100; ++k) {
+			status = RREG32_SOC15(VCN, i, regUVD_STATUS);
+			if (status & 2)
+				break;
+			mdelay(10);
+			if (amdgpu_emu_mode == 1)
+				msleep(1);
+		}
+
+		if (amdgpu_emu_mode == 1) {
+			r = -1;
+			if (status & 2) {
 				r = 0;
-				if (status & 2)
-					break;
-
-				dev_err(adev->dev,
-					"VCN[%d] is not responding, trying to reset VCPU!!!\n", i);
-				WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-							UVD_VCPU_CNTL__BLK_RST_MASK,
-							~UVD_VCPU_CNTL__BLK_RST_MASK);
-				mdelay(10);
-				WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-						~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-				mdelay(10);
-				r = -1;
+				break;
 			}
+		} else {
+			r = 0;
+			if (status & 2)
+				break;
+
+			dev_err(adev->dev,
+				"VCN[%d] is not responding, trying to reset VCPU!!!\n", i);
+			WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
+				 UVD_VCPU_CNTL__BLK_RST_MASK,
+				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+			mdelay(10);
+			WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
+				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+			mdelay(10);
+			r = -1;
 		}
+	}
 
-		if (r) {
-			dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i);
-			return r;
-		}
+	if (r) {
+		dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i);
+		return r;
+	}
 
-		/* enable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN),
-				UVD_MASTINT_EN__VCPU_EN_MASK,
-				~UVD_MASTINT_EN__VCPU_EN_MASK);
+	/* enable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN),
+		 UVD_MASTINT_EN__VCPU_EN_MASK,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-		/* clear the busy bit of VCN_STATUS */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0,
-				~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+	/* clear the busy bit of VCN_STATUS */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0,
+		 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
 
-		ring = &adev->vcn.inst[i].ring_enc[0];
-		WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL,
-				ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
-				VCN_RB1_DB_CTRL__EN_MASK);
-
-		WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr);
-		WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4);
-
-		tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
-		tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
-		WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
-		fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
-		WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0);
-		WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0);
-
-		tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR);
-		WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp);
-		ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR);
-
-		tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
-		tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
-		WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
-		fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
-	}
+	ring = &adev->vcn.inst[i].ring_enc[0];
+	WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL,
+		     ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
+		     VCN_RB1_DB_CTRL__EN_MASK);
+
+	WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr);
+	WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4);
+
+	tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
+	tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
+	WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
+	WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0);
+	WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0);
+
+	tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR);
+	WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp);
+	ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR);
+
+	tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
+	tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
+	WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
 
 	return 0;
 }
@@ -1204,88 +1199,87 @@ static void vcn_v4_0_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
  * vcn_v4_0_5_stop - VCN stop
  *
  * @adev: amdgpu_device pointer
+ * @i: instance to stop
  *
  * Stop VCN block
  */
-static int vcn_v4_0_5_stop(struct amdgpu_device *adev)
+static int vcn_v4_0_5_stop(struct amdgpu_device *adev, int i)
 {
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared;
 	uint32_t tmp;
-	int i, r = 0;
+	int r = 0;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			vcn_v4_0_5_stop_dpg_mode(adev, i);
-			continue;
-		}
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
-		/* wait for vcn idle */
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
-		if (r)
-			return r;
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		vcn_v4_0_5_stop_dpg_mode(adev, i);
+		r = 0;
+		goto done;
+	}
 
-		tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__READ_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	/* wait for vcn idle */
+	r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
+	if (r)
+		goto done;
 
-		/* disable LMI UMC channel */
-		tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2);
-		tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
-		WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp);
-		tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
-			UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__READ_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		goto done;
+
+	/* disable LMI UMC channel */
+	tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2);
+	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+	WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp);
+	tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
+		UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		goto done;
 
-		/* block VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL),
-				UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
-				~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+	/* block VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL),
+		 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
 
-		/* reset VCPU */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-				UVD_VCPU_CNTL__BLK_RST_MASK,
-				~UVD_VCPU_CNTL__BLK_RST_MASK);
+	/* reset VCPU */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__BLK_RST_MASK,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
 
-		/* disable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-				~(UVD_VCPU_CNTL__CLK_EN_MASK));
+	/* disable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
+		 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
 
-		/* apply soft reset */
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
+	/* apply soft reset */
+	tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
+	tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
 
-		/* clear status */
-		WREG32_SOC15(VCN, i, regUVD_STATUS, 0);
+	/* clear status */
+	WREG32_SOC15(VCN, i, regUVD_STATUS, 0);
 
-		/* apply HW clock gating */
-		vcn_v4_0_5_enable_clock_gating(adev, i);
+	/* apply HW clock gating */
+	vcn_v4_0_5_enable_clock_gating(adev, i);
 
-		/* enable VCN power gating */
-		vcn_v4_0_5_enable_static_power_gating(adev, i);
-	}
+	/* enable VCN power gating */
+	vcn_v4_0_5_enable_static_power_gating(adev, i);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, false, i);
-	}
+done:
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, false, i);
 
-	return 0;
+	return r;
 }
 
 /**
@@ -1537,15 +1531,17 @@ static int vcn_v4_0_5_set_powergating_state(struct amdgpu_ip_block *ip_block,
 		enum amd_powergating_state state)
 {
 	struct amdgpu_device *adev = ip_block->adev;
-	int ret;
+	int ret = 0, i;
 
 	if (state == adev->vcn.cur_state)
 		return 0;
 
-	if (state == AMD_PG_STATE_GATE)
-		ret = vcn_v4_0_5_stop(adev);
-	else
-		ret = vcn_v4_0_5_start(adev);
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		if (state == AMD_PG_STATE_GATE)
+			ret |= vcn_v4_0_5_stop(adev, i);
+		else
+			ret |= vcn_v4_0_5_start(adev, i);
+	}
 
 	if (!ret)
 		adev->vcn.cur_state = state;
-- 
2.49.0

[PATCH 2/2] drm/amdgpu: read back register after written for VCN v4.0.5

[Eric Naim]

From: "David (Ming Qiang) Wu" <David.Wu3@amd.com>

commit ee7360fc27d6045510f8fe459b5649b2af27811a upstream

On VCN v4.0.5 there is a race condition where the WPTR is not
updated after starting from idle when doorbell is used. Adding
register read-back after written at function end is to ensure
all register writes are done before they can be used.

Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/12528
Signed-off-by: David (Ming Qiang) Wu <David.Wu3@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 07c9db090b86e5211188e1b351303fbc673378cf)
Cc: stable@vger.kernel.org
Tested-by: Eric Naim <dnaim@cachyos.org>
Signed-off-by: Eric Naim <dnaim@cachyos.org>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 9f9a9bf8dab9..c9761d27fd61 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -983,6 +983,10 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
 			ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
 			VCN_RB1_DB_CTRL__EN_MASK);
 
+	/* Keeping one read-back to ensure all register writes are done, otherwise
+	 * it may introduce race conditions */
+	RREG32_SOC15(VCN, inst_idx, regVCN_RB1_DB_CTRL);
+
 	return 0;
 }
 
@@ -1164,6 +1168,10 @@ static int vcn_v4_0_5_start(struct amdgpu_device *adev, int i)
 	WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
 	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
 
+	/* Keeping one read-back to ensure all register writes are done, otherwise
+	 * it may introduce race conditions */
+	RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
+
 	return 0;
 }
 
-- 
2.49.0

Re: [PATCH 2/2] drm/amdgpu: read back register after written for VCN v4.0.5

[Sasha Levin]

[ Sasha's backport helper bot ]

Hi,

✅ All tests passed successfully. No issues detected.
No action required from the submitter.

The upstream commit SHA1 provided is correct: ee7360fc27d6045510f8fe459b5649b2af27811a

WARNING: Author mismatch between patch and upstream commit:
Backport author: Eric Naim<dnaim@cachyos.org>
Commit author: David (Ming Qiang) Wu<David.Wu3@amd.com>

Note: The patch differs from the upstream commit:
---
1:  ee7360fc27d60 ! 1:  d66acea470dc1 drm/amdgpu: read back register after written for VCN v4.0.5
    @@ Metadata
      ## Commit message ##
         drm/amdgpu: read back register after written for VCN v4.0.5
     
    +    commit ee7360fc27d6045510f8fe459b5649b2af27811a upstream
    +
         On VCN v4.0.5 there is a race condition where the WPTR is not
         updated after starting from idle when doorbell is used. Adding
         register read-back after written at function end is to ensure
    @@ Commit message
         Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
         (cherry picked from commit 07c9db090b86e5211188e1b351303fbc673378cf)
         Cc: stable@vger.kernel.org
    +    Tested-by: Eric Naim <dnaim@cachyos.org>
    +    Signed-off-by: Eric Naim <dnaim@cachyos.org>
     
      ## drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c ##
    -@@ drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c: static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
    +@@ drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c: static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
      			ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
      			VCN_RB1_DB_CTRL__EN_MASK);
      
    @@ drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c: static int vcn_v4_0_5_start_dpg_mode(st
      	return 0;
      }
      
    -@@ drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c: static int vcn_v4_0_5_start(struct amdgpu_vcn_inst *vinst)
    +@@ drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c: static int vcn_v4_0_5_start(struct amdgpu_device *adev, int i)
      	WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
      	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
      
---

Results of testing on various branches:

| Branch                    | Patch Apply | Build Test |
|---------------------------|-------------|------------|
| stable/linux-5.4.y        |  Success    |  Success   |

Re: [PATCH 1/2] drm/amdgpu/vcn4.0.5: split code along instances

[Sasha Levin]

[ Sasha's backport helper bot ]

Hi,

✅ All tests passed successfully. No issues detected.
No action required from the submitter.

The upstream commit SHA1 provided is correct: ecc9ab4e924b7eb9e2c4a668162aaa1d9d60d08c

WARNING: Author mismatch between patch and upstream commit:
Backport author: Eric Naim<dnaim@cachyos.org>
Commit author: Alex Deucher<alexander.deucher@amd.com>

Note: The patch differs from the upstream commit:
---
1:  ecc9ab4e924b7 ! 1:  b72c0acf055f5 drm/amdgpu/vcn4.0.5: split code along instances
    @@ Metadata
      ## Commit message ##
         drm/amdgpu/vcn4.0.5: split code along instances
     
    +    commit ecc9ab4e924b7eb9e2c4a668162aaa1d9d60d08c upstream
    +
         Split the code on a per instance basis.  This will allow
         us to use the per instance functions in the future to
         handle more things per instance.
    @@ Commit message
     
         Reviewed-by: Boyuan Zhang <Boyuan.Zhang@amd.com>
         Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
    +    Tested-by: Eric Naim <dnaim@cachyos.org>
    +    Signed-off-by: Eric Naim <dnaim@cachyos.org>
     
      ## drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c ##
     @@ drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c: static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
---

Results of testing on various branches:

| Branch                    | Patch Apply | Build Test |
|---------------------------|-------------|------------|
| stable/linux-5.4.y        |  Success    |  Success   |