Merge branch 'next' into for-linus

Prepare input updates for 5.20 (or 6.0) merge window.

1 files changed, 90 insertions, 218 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 9189fb85a4dd..5349ca4d19e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -63,13 +63,6 @@
 #define mmGCEA_PROBE_MAP                        0x070c
 #define mmGCEA_PROBE_MAP_BASE_IDX               0
 
-#define GFX9_RLCG_GC_WRITE_OLD			(0x8 << 28)
-#define GFX9_RLCG_GC_WRITE			(0x0 << 28)
-#define GFX9_RLCG_GC_READ			(0x1 << 28)
-#define GFX9_RLCG_VFGATE_DISABLED		0x4000000
-#define GFX9_RLCG_WRONG_OPERATION_TYPE		0x2000000
-#define GFX9_RLCG_NOT_IN_RANGE			0x1000000
-
 MODULE_FIRMWARE("amdgpu/vega10_ce.bin");
 MODULE_FIRMWARE("amdgpu/vega10_pfp.bin");
 MODULE_FIRMWARE("amdgpu/vega10_me.bin");
@@ -746,128 +739,6 @@ static const u32 GFX_RLC_SRM_INDEX_CNTL_DATA_OFFSETS[] =
 	mmRLC_SRM_INDEX_CNTL_DATA_7 - mmRLC_SRM_INDEX_CNTL_DATA_0,
 };
 
-static u32 gfx_v9_0_rlcg_rw(struct amdgpu_device *adev, u32 offset, u32 v, uint32_t flag)
-{
-	static void *scratch_reg0;
-	static void *scratch_reg1;
-	static void *scratch_reg2;
-	static void *scratch_reg3;
-	static void *spare_int;
-	static uint32_t grbm_cntl;
-	static uint32_t grbm_idx;
-	uint32_t i = 0;
-	uint32_t retries = 50000;
-	u32 ret = 0;
-	u32 tmp;
-
-	scratch_reg0 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG0_BASE_IDX] + mmSCRATCH_REG0)*4;
-	scratch_reg1 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG1)*4;
-	scratch_reg2 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG2_BASE_IDX] + mmSCRATCH_REG2)*4;
-	scratch_reg3 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG3_BASE_IDX] + mmSCRATCH_REG3)*4;
-	spare_int = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmRLC_SPARE_INT_BASE_IDX] + mmRLC_SPARE_INT)*4;
-
-	grbm_cntl = adev->reg_offset[GC_HWIP][0][mmGRBM_GFX_CNTL_BASE_IDX] + mmGRBM_GFX_CNTL;
-	grbm_idx = adev->reg_offset[GC_HWIP][0][mmGRBM_GFX_INDEX_BASE_IDX] + mmGRBM_GFX_INDEX;
-
-	if (offset == grbm_cntl || offset == grbm_idx) {
-		if (offset  == grbm_cntl)
-			writel(v, scratch_reg2);
-		else if (offset == grbm_idx)
-			writel(v, scratch_reg3);
-
-		writel(v, ((void __iomem *)adev->rmmio) + (offset * 4));
-	} else {
-		/*
-		 * SCRATCH_REG0 	= read/write value
-		 * SCRATCH_REG1[30:28]	= command
-		 * SCRATCH_REG1[19:0]	= address in dword
-		 * SCRATCH_REG1[26:24]	= Error reporting
-		 */
-		writel(v, scratch_reg0);
-		writel(offset | flag, scratch_reg1);
-		writel(1, spare_int);
-
-		for (i = 0; i < retries; i++) {
-			tmp = readl(scratch_reg1);
-			if (!(tmp & flag))
-				break;
-
-			udelay(10);
-		}
-
-		if (i >= retries) {
-			if (amdgpu_sriov_reg_indirect_gc(adev)) {
-				if (tmp & GFX9_RLCG_VFGATE_DISABLED)
-					pr_err("The vfgate is disabled, program reg:0x%05x failed!\n", offset);
-				else if (tmp & GFX9_RLCG_WRONG_OPERATION_TYPE)
-					pr_err("Wrong operation type, program reg:0x%05x failed!\n", offset);
-				else if (tmp & GFX9_RLCG_NOT_IN_RANGE)
-					pr_err("The register is not in range, program reg:0x%05x failed!\n", offset);
-				else
-					pr_err("Unknown error type, program reg:0x%05x failed!\n", offset);
-			} else
-				pr_err("timeout: rlcg program reg:0x%05x failed!\n", offset);
-		}
-	}
-
-	ret = readl(scratch_reg0);
-
-	return ret;
-}
-
-static bool gfx_v9_0_get_rlcg_flag(struct amdgpu_device *adev, u32 acc_flags, u32 hwip,
-				int write, u32 *rlcg_flag)
-{
-
-	switch (hwip) {
-	case GC_HWIP:
-		if (amdgpu_sriov_reg_indirect_gc(adev)) {
-			*rlcg_flag = write ? GFX9_RLCG_GC_WRITE : GFX9_RLCG_GC_READ;
-
-			return true;
-		/* only in new version, AMDGPU_REGS_NO_KIQ and AMDGPU_REGS_RLC enabled simultaneously */
-		} else if ((acc_flags & AMDGPU_REGS_RLC) && !(acc_flags & AMDGPU_REGS_NO_KIQ) && write) {
-			*rlcg_flag = GFX9_RLCG_GC_WRITE_OLD;
-			return true;
-		}
-
-		break;
-	default:
-		return false;
-	}
-
-	return false;
-}
-
-static u32 gfx_v9_0_sriov_rreg(struct amdgpu_device *adev, u32 offset, u32 acc_flags, u32 hwip)
-{
-	u32 rlcg_flag;
-
-	if (!amdgpu_sriov_runtime(adev) && gfx_v9_0_get_rlcg_flag(adev, acc_flags, hwip, 0, &rlcg_flag))
-		return gfx_v9_0_rlcg_rw(adev, offset, 0, rlcg_flag);
-
-	if (acc_flags & AMDGPU_REGS_NO_KIQ)
-		return RREG32_NO_KIQ(offset);
-	else
-		return RREG32(offset);
-}
-
-static void gfx_v9_0_sriov_wreg(struct amdgpu_device *adev, u32 offset,
-			       u32 value, u32 acc_flags, u32 hwip)
-{
-	u32 rlcg_flag;
-
-	if (!amdgpu_sriov_runtime(adev) && gfx_v9_0_get_rlcg_flag(adev, acc_flags, hwip, 1, &rlcg_flag)) {
-		gfx_v9_0_rlcg_rw(adev, offset, value, rlcg_flag);
-		return;
-	}
-
-	if (acc_flags & AMDGPU_REGS_NO_KIQ)
-		WREG32_NO_KIQ(offset, value);
-	else
-		WREG32(offset, value);
-}
-
 #define VEGA10_GB_ADDR_CONFIG_GOLDEN 0x2a114042
 #define VEGA12_GB_ADDR_CONFIG_GOLDEN 0x24104041
 #define RAVEN_GB_ADDR_CONFIG_GOLDEN 0x24000042
@@ -882,7 +753,7 @@ static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev,
 static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev);
 static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring);
 static u64 gfx_v9_0_ring_get_rptr_compute(struct amdgpu_ring *ring);
-static int gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
+static void gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
 					  void *ras_error_status);
 static int gfx_v9_0_ras_error_inject(struct amdgpu_device *adev,
 				     void *inject_if);
@@ -909,9 +780,8 @@ static void gfx_v9_0_kiq_set_resources(struct amdgpu_ring *kiq_ring,
 static void gfx_v9_0_kiq_map_queues(struct amdgpu_ring *kiq_ring,
 				 struct amdgpu_ring *ring)
 {
-	struct amdgpu_device *adev = kiq_ring->adev;
 	uint64_t mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
-	uint64_t wptr_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	uint64_t wptr_addr = ring->wptr_gpu_addr;
 	uint32_t eng_sel = ring->funcs->type == AMDGPU_RING_TYPE_GFX ? 4 : 0;
 
 	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
@@ -1080,13 +950,6 @@ static void gfx_v9_0_init_golden_registers(struct amdgpu_device *adev)
 						(const u32)ARRAY_SIZE(golden_settings_gc_9_x_common));
 }
 
-static void gfx_v9_0_scratch_init(struct amdgpu_device *adev)
-{
-	adev->gfx.scratch.num_reg = 8;
-	adev->gfx.scratch.reg_base = SOC15_REG_OFFSET(GC, 0, mmSCRATCH_REG0);
-	adev->gfx.scratch.free_mask = (1u << adev->gfx.scratch.num_reg) - 1;
-}
-
 static void gfx_v9_0_write_data_to_reg(struct amdgpu_ring *ring, int eng_sel,
 				       bool wc, uint32_t reg, uint32_t val)
 {
@@ -1124,27 +987,23 @@ static void gfx_v9_0_wait_reg_mem(struct amdgpu_ring *ring, int eng_sel,
 static int gfx_v9_0_ring_test_ring(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	uint32_t scratch;
 	uint32_t tmp = 0;
 	unsigned i;
 	int r;
 
-	r = amdgpu_gfx_scratch_get(adev, &scratch);
-	if (r)
-		return r;
-
-	WREG32(scratch, 0xCAFEDEAD);
+	WREG32_SOC15(GC, 0, mmSCRATCH_REG0, 0xCAFEDEAD);
 	r = amdgpu_ring_alloc(ring, 3);
 	if (r)
-		goto error_free_scratch;
+		return r;
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_SET_UCONFIG_REG, 1));
-	amdgpu_ring_write(ring, (scratch - PACKET3_SET_UCONFIG_REG_START));
+	amdgpu_ring_write(ring, SOC15_REG_OFFSET(GC, 0, mmSCRATCH_REG0) -
+			  PACKET3_SET_UCONFIG_REG_START);
 	amdgpu_ring_write(ring, 0xDEADBEEF);
 	amdgpu_ring_commit(ring);
 
 	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = RREG32(scratch);
+		tmp = RREG32_SOC15(GC, 0, mmSCRATCH_REG0);
 		if (tmp == 0xDEADBEEF)
 			break;
 		udelay(1);
@@ -1152,9 +1011,6 @@ static int gfx_v9_0_ring_test_ring(struct amdgpu_ring *ring)
 
 	if (i >= adev->usec_timeout)
 		r = -ETIMEDOUT;
-
-error_free_scratch:
-	amdgpu_gfx_scratch_free(adev, scratch);
 	return r;
 }
 
@@ -1334,6 +1190,8 @@ static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = {
 	{ 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 },
 	/* GFXOFF is unstable on C6 parts with a VBIOS 113-RAVEN-114 */
 	{ 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 },
+	/* Apple MacBook Pro (15-inch, 2019) Radeon Pro Vega 20 4 GB */
+	{ 0x1002, 0x69af, 0x106b, 0x019a, 0xc0 },
 	{ 0, 0, 0, 0, 0 },
 };
 
@@ -2008,6 +1866,21 @@ static int gfx_v9_0_cp_jump_table_num(struct amdgpu_device *adev)
 		return 4;
 }
 
+static void gfx_v9_0_init_rlcg_reg_access_ctrl(struct amdgpu_device *adev)
+{
+	struct amdgpu_rlcg_reg_access_ctrl *reg_access_ctrl;
+
+	reg_access_ctrl = &adev->gfx.rlc.reg_access_ctrl;
+	reg_access_ctrl->scratch_reg0 = SOC15_REG_OFFSET(GC, 0, mmSCRATCH_REG0);
+	reg_access_ctrl->scratch_reg1 = SOC15_REG_OFFSET(GC, 0, mmSCRATCH_REG1);
+	reg_access_ctrl->scratch_reg2 = SOC15_REG_OFFSET(GC, 0, mmSCRATCH_REG2);
+	reg_access_ctrl->scratch_reg3 = SOC15_REG_OFFSET(GC, 0, mmSCRATCH_REG3);
+	reg_access_ctrl->grbm_cntl = SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_CNTL);
+	reg_access_ctrl->grbm_idx = SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_INDEX);
+	reg_access_ctrl->spare_int = SOC15_REG_OFFSET(GC, 0, mmRLC_SPARE_INT);
+	adev->gfx.rlc.rlcg_reg_access_supported = true;
+}
+
 static int gfx_v9_0_rlc_init(struct amdgpu_device *adev)
 {
 	const struct cs_section_def *cs_data;
@@ -2197,12 +2070,16 @@ static const struct amdgpu_gfx_funcs gfx_v9_0_gfx_funcs = {
         .select_me_pipe_q = &gfx_v9_0_select_me_pipe_q,
 };
 
-static const struct amdgpu_gfx_ras_funcs gfx_v9_0_ras_funcs = {
-	.ras_late_init = amdgpu_gfx_ras_late_init,
-	.ras_fini = amdgpu_gfx_ras_fini,
-	.ras_error_inject = &gfx_v9_0_ras_error_inject,
-	.query_ras_error_count = &gfx_v9_0_query_ras_error_count,
-	.reset_ras_error_count = &gfx_v9_0_reset_ras_error_count,
+const struct amdgpu_ras_block_hw_ops  gfx_v9_0_ras_ops = {
+		.ras_error_inject = &gfx_v9_0_ras_error_inject,
+		.query_ras_error_count = &gfx_v9_0_query_ras_error_count,
+		.reset_ras_error_count = &gfx_v9_0_reset_ras_error_count,
+};
+
+static struct amdgpu_gfx_ras gfx_v9_0_ras = {
+	.ras_block = {
+		.hw_ops = &gfx_v9_0_ras_ops,
+	},
 };
 
 static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
@@ -2231,7 +2108,7 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
 		DRM_INFO("fix gfx.config for vega12\n");
 		break;
 	case IP_VERSION(9, 4, 0):
-		adev->gfx.ras_funcs = &gfx_v9_0_ras_funcs;
+		adev->gfx.ras = &gfx_v9_0_ras;
 		adev->gfx.config.max_hw_contexts = 8;
 		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
 		adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
@@ -2258,7 +2135,7 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
 			gb_addr_config = RAVEN_GB_ADDR_CONFIG_GOLDEN;
 		break;
 	case IP_VERSION(9, 4, 1):
-		adev->gfx.ras_funcs = &gfx_v9_4_ras_funcs;
+		adev->gfx.ras = &gfx_v9_4_ras;
 		adev->gfx.config.max_hw_contexts = 8;
 		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
 		adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
@@ -2279,7 +2156,7 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
 		gb_addr_config |= 0x22010042;
 		break;
 	case IP_VERSION(9, 4, 2):
-		adev->gfx.ras_funcs = &gfx_v9_4_2_ras_funcs;
+		adev->gfx.ras = &gfx_v9_4_2_ras;
 		adev->gfx.config.max_hw_contexts = 8;
 		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
 		adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
@@ -2298,6 +2175,27 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
 		break;
 	}
 
+	if (adev->gfx.ras) {
+		err = amdgpu_ras_register_ras_block(adev, &adev->gfx.ras->ras_block);
+		if (err) {
+			DRM_ERROR("Failed to register gfx ras block!\n");
+			return err;
+		}
+
+		strcpy(adev->gfx.ras->ras_block.ras_comm.name, "gfx");
+		adev->gfx.ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__GFX;
+		adev->gfx.ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+		adev->gfx.ras_if = &adev->gfx.ras->ras_block.ras_comm;
+
+		/* If not define special ras_late_init function, use gfx default ras_late_init */
+		if (!adev->gfx.ras->ras_block.ras_late_init)
+			adev->gfx.ras->ras_block.ras_late_init = amdgpu_gfx_ras_late_init;
+
+		/* If not defined special ras_cb function, use default ras_cb */
+		if (!adev->gfx.ras->ras_block.ras_cb)
+			adev->gfx.ras->ras_block.ras_cb = amdgpu_gfx_process_ras_data_cb;
+	}
+
 	adev->gfx.config.gb_addr_config = gb_addr_config;
 
 	adev->gfx.config.gb_addr_config_fields.num_pipes = 1 <<
@@ -2363,7 +2261,7 @@ static int gfx_v9_0_compute_ring_init(struct amdgpu_device *adev, int ring_id,
 		+ ((ring->me - 1) * adev->gfx.mec.num_pipe_per_mec)
 		+ ring->pipe;
 	hw_prio = amdgpu_gfx_is_high_priority_compute_queue(adev, ring) ?
-			AMDGPU_GFX_PIPE_PRIO_HIGH : AMDGPU_GFX_PIPE_PRIO_NORMAL;
+			AMDGPU_RING_PRIO_2 : AMDGPU_RING_PRIO_DEFAULT;
 	/* type-2 packets are deprecated on MEC, use type-3 instead */
 	return amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, irq_type,
 				hw_prio, NULL);
@@ -2426,18 +2324,20 @@ static int gfx_v9_0_sw_init(void *handle)
 
 	adev->gfx.gfx_current_status = AMDGPU_GFX_NORMAL_MODE;
 
-	gfx_v9_0_scratch_init(adev);
-
 	r = gfx_v9_0_init_microcode(adev);
 	if (r) {
 		DRM_ERROR("Failed to load gfx firmware!\n");
 		return r;
 	}
 
-	r = adev->gfx.rlc.funcs->init(adev);
-	if (r) {
-		DRM_ERROR("Failed to init rlc BOs!\n");
-		return r;
+	if (adev->gfx.rlc.funcs) {
+		if (adev->gfx.rlc.funcs->init) {
+			r = adev->gfx.rlc.funcs->init(adev);
+			if (r) {
+				dev_err(adev->dev, "Failed to init rlc BOs!\n");
+				return r;
+			}
+		}
 	}
 
 	r = gfx_v9_0_mec_init(adev);
@@ -2513,10 +2413,6 @@ static int gfx_v9_0_sw_fini(void *handle)
 	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (adev->gfx.ras_funcs &&
-	    adev->gfx.ras_funcs->ras_fini)
-		adev->gfx.ras_funcs->ras_fini(adev);
-
 	for (i = 0; i < adev->gfx.num_gfx_rings; i++)
 		amdgpu_ring_fini(&adev->gfx.gfx_ring[i]);
 	for (i = 0; i < adev->gfx.num_compute_rings; i++)
@@ -2639,7 +2535,7 @@ static void gfx_v9_0_init_compute_vmid(struct amdgpu_device *adev)
 	mutex_unlock(&adev->srbm_mutex);
 
 	/* Initialize all compute VMIDs to have no GDS, GWS, or OA
-	   acccess. These should be enabled by FW for target VMIDs. */
+	   access. These should be enabled by FW for target VMIDs. */
 	for (i = adev->vm_manager.first_kfd_vmid; i < AMDGPU_NUM_VMID; i++) {
 		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * i, 0);
 		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * i, 0);
@@ -3413,11 +3309,11 @@ static int gfx_v9_0_cp_gfx_resume(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmCP_RB0_WPTR_HI, upper_32_bits(ring->wptr));
 
 	/* set the wb address wether it's enabled or not */
-	rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	rptr_addr = ring->rptr_gpu_addr;
 	WREG32_SOC15(GC, 0, mmCP_RB0_RPTR_ADDR, lower_32_bits(rptr_addr));
 	WREG32_SOC15(GC, 0, mmCP_RB0_RPTR_ADDR_HI, upper_32_bits(rptr_addr) & CP_RB_RPTR_ADDR_HI__RB_RPTR_ADDR_HI_MASK);
 
-	wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wptr_gpu_addr = ring->wptr_gpu_addr;
 	WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_LO, lower_32_bits(wptr_gpu_addr));
 	WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_HI, upper_32_bits(wptr_gpu_addr));
 
@@ -3618,7 +3514,7 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, QUEUE_SIZE,
 			    (order_base_2(ring->ring_size / 4) - 1));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE,
-			((order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1) << 8));
+			(order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1));
 #ifdef __BIG_ENDIAN
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, ENDIAN_SWAP, 1);
 #endif
@@ -3629,33 +3525,16 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
 	mqd->cp_hqd_pq_control = tmp;
 
 	/* set the wb address whether it's enabled or not */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+	wb_gpu_addr = ring->rptr_gpu_addr;
 	mqd->cp_hqd_pq_rptr_report_addr_lo = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_hqd_pq_rptr_report_addr_hi =
 		upper_32_bits(wb_gpu_addr) & 0xffff;
 
 	/* only used if CP_PQ_WPTR_POLL_CNTL.CP_PQ_WPTR_POLL_CNTL__EN_MASK=1 */
-	wb_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	wb_gpu_addr = ring->wptr_gpu_addr;
 	mqd->cp_hqd_pq_wptr_poll_addr_lo = wb_gpu_addr & 0xfffffffc;
 	mqd->cp_hqd_pq_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr) & 0xffff;
 
-	tmp = 0;
-	/* enable the doorbell if requested */
-	if (ring->use_doorbell) {
-		tmp = RREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL);
-		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
-				DOORBELL_OFFSET, ring->doorbell_index);
-
-		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
-					 DOORBELL_EN, 1);
-		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
-					 DOORBELL_SOURCE, 0);
-		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
-					 DOORBELL_HIT, 0);
-	}
-
-	mqd->cp_hqd_pq_doorbell_control = tmp;
-
 	/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
 	ring->wptr = 0;
 	mqd->cp_hqd_pq_rptr = RREG32_SOC15(GC, 0, mmCP_HQD_PQ_RPTR);
@@ -3917,7 +3796,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)
 
 		/* reset ring buffer */
 		ring->wptr = 0;
-		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0);
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0);
 		amdgpu_ring_clear_ring(ring);
 	} else {
 		amdgpu_ring_clear_ring(ring);
@@ -4840,6 +4719,9 @@ static int gfx_v9_0_early_init(void *handle)
 	gfx_v9_0_set_gds_init(adev);
 	gfx_v9_0_set_rlc_funcs(adev);
 
+	/* init rlcg reg access ctrl */
+	gfx_v9_0_init_rlcg_reg_access_ctrl(adev);
+
 	return 0;
 }
 
@@ -4870,16 +4752,9 @@ static int gfx_v9_0_ecc_late_init(void *handle)
 	if (r)
 		return r;
 
-	if (adev->gfx.ras_funcs &&
-	    adev->gfx.ras_funcs->ras_late_init) {
-		r = adev->gfx.ras_funcs->ras_late_init(adev);
-		if (r)
-			return r;
-	}
-
-	if (adev->gfx.ras_funcs &&
-	    adev->gfx.ras_funcs->enable_watchdog_timer)
-		adev->gfx.ras_funcs->enable_watchdog_timer(adev);
+	if (adev->gfx.ras &&
+	    adev->gfx.ras->enable_watchdog_timer)
+		adev->gfx.ras->enable_watchdog_timer(adev);
 
 	return 0;
 }
@@ -5250,8 +5125,6 @@ static const struct amdgpu_rlc_funcs gfx_v9_0_rlc_funcs = {
 	.reset = gfx_v9_0_rlc_reset,
 	.start = gfx_v9_0_rlc_start,
 	.update_spm_vmid = gfx_v9_0_update_spm_vmid,
-	.sriov_wreg = gfx_v9_0_sriov_wreg,
-	.sriov_rreg = gfx_v9_0_sriov_rreg,
 	.is_rlcg_access_range = gfx_v9_0_is_rlcg_access_range,
 };
 
@@ -5326,7 +5199,7 @@ static int gfx_v9_0_set_clockgating_state(void *handle,
 	return 0;
 }
 
-static void gfx_v9_0_get_clockgating_state(void *handle, u32 *flags)
+static void gfx_v9_0_get_clockgating_state(void *handle, u64 *flags)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int data;
@@ -5372,7 +5245,7 @@ static void gfx_v9_0_get_clockgating_state(void *handle, u32 *flags)
 
 static u64 gfx_v9_0_ring_get_rptr_gfx(struct amdgpu_ring *ring)
 {
-	return ring->adev->wb.wb[ring->rptr_offs]; /* gfx9 is 32bit rptr*/
+	return *ring->rptr_cpu_addr; /* gfx9 is 32bit rptr*/
 }
 
 static u64 gfx_v9_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
@@ -5382,7 +5255,7 @@ static u64 gfx_v9_0_ring_get_wptr_gfx(struct amdgpu_ring *ring)
 
 	/* XXX check if swapping is necessary on BE */
 	if (ring->use_doorbell) {
-		wptr = atomic64_read((atomic64_t *)&adev->wb.wb[ring->wptr_offs]);
+		wptr = atomic64_read((atomic64_t *)ring->wptr_cpu_addr);
 	} else {
 		wptr = RREG32_SOC15(GC, 0, mmCP_RB0_WPTR);
 		wptr += (u64)RREG32_SOC15(GC, 0, mmCP_RB0_WPTR_HI) << 32;
@@ -5397,7 +5270,7 @@ static void gfx_v9_0_ring_set_wptr_gfx(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], ring->wptr);
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, ring->wptr);
 		WDOORBELL64(ring->doorbell_index, ring->wptr);
 	} else {
 		WREG32_SOC15(GC, 0, mmCP_RB0_WPTR, lower_32_bits(ring->wptr));
@@ -5562,7 +5435,7 @@ static void gfx_v9_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 
 static u64 gfx_v9_0_ring_get_rptr_compute(struct amdgpu_ring *ring)
 {
-	return ring->adev->wb.wb[ring->rptr_offs]; /* gfx9 hardware is 32bit rptr */
+	return *ring->rptr_cpu_addr; /* gfx9 hardware is 32bit rptr */
 }
 
 static u64 gfx_v9_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
@@ -5571,7 +5444,7 @@ static u64 gfx_v9_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
 
 	/* XXX check if swapping is necessary on BE */
 	if (ring->use_doorbell)
-		wptr = atomic64_read((atomic64_t *)&ring->adev->wb.wb[ring->wptr_offs]);
+		wptr = atomic64_read((atomic64_t *)ring->wptr_cpu_addr);
 	else
 		BUG();
 	return wptr;
@@ -5583,7 +5456,7 @@ static void gfx_v9_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
 
 	/* XXX check if swapping is necessary on BE */
 	if (ring->use_doorbell) {
-		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], ring->wptr);
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, ring->wptr);
 		WDOORBELL64(ring->doorbell_index, ring->wptr);
 	} else{
 		BUG(); /* only DOORBELL method supported on gfx9 now */
@@ -6819,7 +6692,7 @@ static void gfx_v9_0_reset_ras_error_count(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmATC_L2_CACHE_4K_EDC_INDEX, 255);
 }
 
-static int gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
+static void gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
 					  void *ras_error_status)
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
@@ -6828,7 +6701,7 @@ static int gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
 	uint32_t reg_value;
 
 	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX))
-		return -EINVAL;
+		return;
 
 	err_data->ue_count = 0;
 	err_data->ce_count = 0;
@@ -6857,8 +6730,6 @@ static int gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	gfx_v9_0_query_utc_edc_status(adev, err_data);
-
-	return 0;
 }
 
 static void gfx_v9_0_emit_mem_sync(struct amdgpu_ring *ring)
@@ -6962,6 +6833,7 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_gfx = {
 	.align_mask = 0xff,
 	.nop = PACKET3(PACKET3_NOP, 0x3FFF),
 	.support_64bit_ptrs = true,
+	.secure_submission_supported = true,
 	.vmhub = AMDGPU_GFXHUB_0,
 	.get_rptr = gfx_v9_0_ring_get_rptr_gfx,
 	.get_wptr = gfx_v9_0_ring_get_wptr_gfx,