[PATCH v2 0/5] *** GFX9 RLCG Interface modifications ***

[PATCH v2 0/5] *** GFX9 RLCG Interface modifications ***

[Victor Skvortsov]

This patchset introduces an expanded sriov RLCG interface.
This interface will be used by Aldebaran in sriov mode
for indirect GC register access during full access.

v2: Added descriptions to scratch registers, and 
improved code readability.

Victor Skvortsov (5):
  drm/amdgpu: Add *_SOC15_IP_NO_KIQ() macro definitions
  drm/amdgpu: Modify indirect register access for gmc_v9_0 sriov
  drm/amdgpu: Modify indirect register access for amdkfd_gfx_v9 sriov
  drm/amdgpu: Initialize Aldebaran RLC function pointers
  drm/amdgpu: Modify indirect register access for gfx9 sriov

 .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c |  27 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c |   4 +
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c         | 120 +++++++++++++-----
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h         |   2 +
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c         |  57 +++++++--
 drivers/gpu/drm/amd/amdgpu/soc15_common.h     |   5 +
 6 files changed, 157 insertions(+), 58 deletions(-)

-- 
2.25.1

[PATCH v2 1/5] drm/amdgpu: Add *_SOC15_IP_NO_KIQ() macro definitions

[Victor Skvortsov]

Add helper macros to change register access
from direct to indirect.

Signed-off-by: Victor Skvortsov <victor.skvortsov@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/soc15_common.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
index 8a9ca87d8663..473767e03676 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
@@ -51,6 +51,8 @@
 
 #define RREG32_SOC15_IP(ip, reg) __RREG32_SOC15_RLC__(reg, 0, ip##_HWIP)
 
+#define RREG32_SOC15_IP_NO_KIQ(ip, reg) __RREG32_SOC15_RLC__(reg, AMDGPU_REGS_NO_KIQ, ip##_HWIP)
+
 #define RREG32_SOC15_NO_KIQ(ip, inst, reg) \
 	__RREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, \
 			 AMDGPU_REGS_NO_KIQ, ip##_HWIP)
@@ -65,6 +67,9 @@
 #define WREG32_SOC15_IP(ip, reg, value) \
 	 __WREG32_SOC15_RLC__(reg, value, 0, ip##_HWIP)
 
+#define WREG32_SOC15_IP_NO_KIQ(ip, reg, value) \
+	 __WREG32_SOC15_RLC__(reg, value, AMDGPU_REGS_NO_KIQ, ip##_HWIP)
+
 #define WREG32_SOC15_NO_KIQ(ip, inst, reg, value) \
 	__WREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, \
 			     value, AMDGPU_REGS_NO_KIQ, ip##_HWIP)
-- 
2.25.1

[PATCH v2 2/5] drm/amdgpu: Modify indirect register access for gmc_v9_0 sriov

[Victor Skvortsov]

Modify GC register access from MMIO to RLCG if the
indirect flag is set

v2: Replaced ternary operator with if-else for better
readability

Signed-off-by: Victor Skvortsov <victor.skvortsov@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 57 ++++++++++++++++++++-------
 1 file changed, 43 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index db2ec84f7237..e85a264c971a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -478,9 +478,18 @@ static int gmc_v9_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
 			hub = &adev->vmhub[j];
 			for (i = 0; i < 16; i++) {
 				reg = hub->vm_context0_cntl + i;
-				tmp = RREG32(reg);
+
+				if (j == AMDGPU_GFXHUB_0)
+					tmp = RREG32_SOC15_IP(GC, reg);
+				else
+					tmp = RREG32_SOC15_IP(MMHUB, reg);
+
 				tmp &= ~bits;
-				WREG32(reg, tmp);
+
+				if (j == AMDGPU_GFXHUB_0)
+					WREG32_SOC15_IP(GC, reg, tmp);
+				else
+					WREG32_SOC15_IP(MMHUB, reg, tmp);
 			}
 		}
 		break;
@@ -489,9 +498,18 @@ static int gmc_v9_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
 			hub = &adev->vmhub[j];
 			for (i = 0; i < 16; i++) {
 				reg = hub->vm_context0_cntl + i;
-				tmp = RREG32(reg);
+
+				if (j == AMDGPU_GFXHUB_0)
+					tmp = RREG32_SOC15_IP(GC, reg);
+				else
+					tmp = RREG32_SOC15_IP(MMHUB, reg);
+
 				tmp |= bits;
-				WREG32(reg, tmp);
+
+				if (j == AMDGPU_GFXHUB_0)
+					WREG32_SOC15_IP(GC, reg, tmp);
+				else
+					WREG32_SOC15_IP(MMHUB, reg, tmp);
 			}
 		}
 		break;
@@ -788,9 +806,12 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
 	if (use_semaphore) {
 		for (j = 0; j < adev->usec_timeout; j++) {
-			/* a read return value of 1 means semaphore acuqire */
-			tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem +
-					    hub->eng_distance * eng);
+			/* a read return value of 1 means semaphore acquire */
+			if (vmhub == AMDGPU_GFXHUB_0)
+				tmp = RREG32_SOC15_IP_NO_KIQ(GC, hub->vm_inv_eng0_sem + hub->eng_distance * eng);
+			else
+				tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, hub->vm_inv_eng0_sem + hub->eng_distance * eng);
+
 			if (tmp & 0x1)
 				break;
 			udelay(1);
@@ -801,8 +822,10 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	}
 
 	do {
-		WREG32_NO_KIQ(hub->vm_inv_eng0_req +
-			      hub->eng_distance * eng, inv_req);
+		if (vmhub == AMDGPU_GFXHUB_0)
+			WREG32_SOC15_IP_NO_KIQ(GC, hub->vm_inv_eng0_req + hub->eng_distance * eng, inv_req);
+		else
+			WREG32_SOC15_IP_NO_KIQ(MMHUB, hub->vm_inv_eng0_req + hub->eng_distance * eng, inv_req);
 
 		/*
 		 * Issue a dummy read to wait for the ACK register to
@@ -815,8 +838,11 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 				      hub->eng_distance * eng);
 
 		for (j = 0; j < adev->usec_timeout; j++) {
-			tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_ack +
-					    hub->eng_distance * eng);
+			if (vmhub == AMDGPU_GFXHUB_0)
+				tmp = RREG32_SOC15_IP_NO_KIQ(GC, hub->vm_inv_eng0_ack + hub->eng_distance * eng);
+			else
+				tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, hub->vm_inv_eng0_ack + hub->eng_distance * eng);
+
 			if (tmp & (1 << vmid))
 				break;
 			udelay(1);
@@ -827,13 +853,16 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	} while (inv_req);
 
 	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
-	if (use_semaphore)
+	if (use_semaphore) {
 		/*
 		 * add semaphore release after invalidation,
 		 * write with 0 means semaphore release
 		 */
-		WREG32_NO_KIQ(hub->vm_inv_eng0_sem +
-			      hub->eng_distance * eng, 0);
+		if (vmhub == AMDGPU_GFXHUB_0)
+			WREG32_SOC15_IP_NO_KIQ(GC, hub->vm_inv_eng0_sem + hub->eng_distance * eng, 0);
+		else
+			WREG32_SOC15_IP_NO_KIQ(MMHUB, hub->vm_inv_eng0_sem + hub->eng_distance * eng, 0);
+	}
 
 	spin_unlock(&adev->gmc.invalidate_lock);
 
-- 
2.25.1

[PATCH v2 3/5] drm/amdgpu: Modify indirect register access for amdkfd_gfx_v9 sriov

[Victor Skvortsov]

Modify GC register access from MMIO to RLCG if the indirect
flag is set

Signed-off-by: Victor Skvortsov <victor.skvortsov@amd.com>
---
 .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 27 +++++++++----------
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index ddfe7aff919d..1abf662a0e91 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -166,7 +166,7 @@ int kgd_gfx_v9_init_interrupts(struct amdgpu_device *adev, uint32_t pipe_id)
 
 	lock_srbm(adev, mec, pipe, 0, 0);
 
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmCPC_INT_CNTL),
+	WREG32_SOC15(GC, 0, mmCPC_INT_CNTL,
 		CP_INT_CNTL_RING0__TIME_STAMP_INT_ENABLE_MASK |
 		CP_INT_CNTL_RING0__OPCODE_ERROR_INT_ENABLE_MASK);
 
@@ -279,7 +279,7 @@ int kgd_gfx_v9_hqd_load(struct amdgpu_device *adev, void *mqd,
 		       lower_32_bits((uintptr_t)wptr));
 		WREG32_RLC(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI),
 		       upper_32_bits((uintptr_t)wptr));
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1),
+		WREG32_SOC15(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1,
 		       (uint32_t)get_queue_mask(adev, pipe_id, queue_id));
 	}
 
@@ -488,13 +488,13 @@ bool kgd_gfx_v9_hqd_is_occupied(struct amdgpu_device *adev,
 	uint32_t low, high;
 
 	acquire_queue(adev, pipe_id, queue_id);
-	act = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE));
+	act = RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE);
 	if (act) {
 		low = lower_32_bits(queue_address >> 8);
 		high = upper_32_bits(queue_address >> 8);
 
-		if (low == RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_BASE)) &&
-		   high == RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_BASE_HI)))
+		if (low == RREG32_SOC15(GC, 0, mmCP_HQD_PQ_BASE) &&
+		   high == RREG32_SOC15(GC, 0, mmCP_HQD_PQ_BASE_HI))
 			retval = true;
 	}
 	release_queue(adev);
@@ -556,7 +556,7 @@ int kgd_gfx_v9_hqd_destroy(struct amdgpu_device *adev, void *mqd,
 
 	end_jiffies = (utimeout * HZ / 1000) + jiffies;
 	while (true) {
-		temp = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE));
+		temp = RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE);
 		if (!(temp & CP_HQD_ACTIVE__ACTIVE_MASK))
 			break;
 		if (time_after(jiffies, end_jiffies)) {
@@ -645,7 +645,7 @@ int kgd_gfx_v9_wave_control_execute(struct amdgpu_device *adev,
 	mutex_lock(&adev->grbm_idx_mutex);
 
 	WREG32_SOC15_RLC_SHADOW(GC, 0, mmGRBM_GFX_INDEX, gfx_index_val);
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_CMD), sq_cmd);
+	WREG32_SOC15(GC, 0, mmSQ_CMD, sq_cmd);
 
 	data = REG_SET_FIELD(data, GRBM_GFX_INDEX,
 		INSTANCE_BROADCAST_WRITES, 1);
@@ -722,7 +722,7 @@ static void get_wave_count(struct amdgpu_device *adev, int queue_idx,
 	pipe_idx = queue_idx / adev->gfx.mec.num_queue_per_pipe;
 	queue_slot = queue_idx % adev->gfx.mec.num_queue_per_pipe;
 	soc15_grbm_select(adev, 1, pipe_idx, queue_slot, 0);
-	reg_val = RREG32(SOC15_REG_OFFSET(GC, 0, mmSPI_CSQ_WF_ACTIVE_COUNT_0) +
+	reg_val = RREG32_SOC15_IP(GC, SOC15_REG_OFFSET(GC, 0, mmSPI_CSQ_WF_ACTIVE_COUNT_0) +
 			 queue_slot);
 	*wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK;
 	if (*wave_cnt != 0)
@@ -809,8 +809,7 @@ void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, int pasid,
 		for (sh_idx = 0; sh_idx < sh_cnt; sh_idx++) {
 
 			gfx_v9_0_select_se_sh(adev, se_idx, sh_idx, 0xffffffff);
-			queue_map = RREG32(SOC15_REG_OFFSET(GC, 0,
-					   mmSPI_CSQ_WF_ACTIVE_STATUS));
+			queue_map = RREG32_SOC15(GC, 0, mmSPI_CSQ_WF_ACTIVE_STATUS);
 
 			/*
 			 * Assumption: queue map encodes following schema: four
@@ -860,17 +859,17 @@ void kgd_gfx_v9_program_trap_handler_settings(struct amdgpu_device *adev,
 	/*
 	 * Program TBA registers
 	 */
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_LO),
+	WREG32_SOC15(GC, 0, mmSQ_SHADER_TBA_LO,
                         lower_32_bits(tba_addr >> 8));
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_HI),
+	WREG32_SOC15(GC, 0, mmSQ_SHADER_TBA_HI,
                         upper_32_bits(tba_addr >> 8));
 
 	/*
 	 * Program TMA registers
 	 */
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_LO),
+	WREG32_SOC15(GC, 0, mmSQ_SHADER_TMA_LO,
 			lower_32_bits(tma_addr >> 8));
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_HI),
+	WREG32_SOC15(GC, 0, mmSQ_SHADER_TMA_HI,
 			upper_32_bits(tma_addr >> 8));
 
 	unlock_srbm(adev);
-- 
2.25.1

[PATCH v2 4/5] drm/amdgpu: Initialize Aldebaran RLC function pointers

[Victor Skvortsov]

In SRIOV, RLC function pointers must be initialized early as
we rely on the RLCG interface for all GC register access.

v2: Make aldebaran a seperate case

Signed-off-by: Victor Skvortsov <victor.skvortsov@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 4 ++++
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c         | 3 +--
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h         | 2 ++
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 65e1f6cc59dd..d7e1b503cd3b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -842,8 +842,12 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(9, 3, 0):
 	case IP_VERSION(9, 4, 0):
 	case IP_VERSION(9, 4, 1):
+		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
+		break;
 	case IP_VERSION(9, 4, 2):
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
+		if (amdgpu_sriov_vf(adev))
+			gfx_v9_0_set_rlc_funcs(adev);
 		break;
 	case IP_VERSION(10, 1, 10):
 	case IP_VERSION(10, 1, 2):
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index edb3e3b08eed..d252b06efa43 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -816,7 +816,6 @@ static void gfx_v9_0_sriov_wreg(struct amdgpu_device *adev, u32 offset,
 static void gfx_v9_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v9_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v9_0_set_gds_init(struct amdgpu_device *adev);
-static void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev);
 static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev,
 				struct amdgpu_cu_info *cu_info);
 static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev);
@@ -7066,7 +7065,7 @@ static void gfx_v9_0_set_irq_funcs(struct amdgpu_device *adev)
 	adev->gfx.cp_ecc_error_irq.funcs = &gfx_v9_0_cp_ecc_error_irq_funcs;
 }
 
-static void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev)
+void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev)
 {
 	switch (adev->ip_versions[GC_HWIP][0]) {
 	case IP_VERSION(9, 0, 1):
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h
index dfe8d4841f58..1817e252354f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h
@@ -29,4 +29,6 @@ extern const struct amdgpu_ip_block_version gfx_v9_0_ip_block;
 void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num,
 			   u32 instance);
 
+void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev);
+
 #endif
-- 
2.25.1

[PATCH v2 5/5] drm/amdgpu: Modify indirect register access for gfx9 sriov

[Victor Skvortsov]

Expand RLCG interface for new GC read & write commands.
New interface will only be used if the PF enables the flag in pf2vf msg.

v2: Added a description for the scratch registers

Signed-off-by: Victor Skvortsov <victor.skvortsov@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 117 ++++++++++++++++++++------
 1 file changed, 89 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index d252b06efa43..7a754cb8236e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -63,6 +63,13 @@
 #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");
@@ -739,7 +746,7 @@ static const u32 GFX_RLC_SRM_INDEX_CNTL_DATA_OFFSETS[] =
 	mmRLC_SRM_INDEX_CNTL_DATA_7 - mmRLC_SRM_INDEX_CNTL_DATA_0,
 };
 
-static void gfx_v9_0_rlcg_w(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag)
+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;
@@ -748,21 +755,20 @@ static void gfx_v9_0_rlcg_w(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 	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_REG1_BASE_IDX] + mmSCRATCH_REG2)*4;
-	scratch_reg3 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG3)*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 (amdgpu_sriov_runtime(adev)) {
-		pr_err("shouldn't call rlcg write register during runtime\n");
-		return;
-	}
-
 	if (offset == grbm_cntl || offset == grbm_idx) {
 		if (offset  == grbm_cntl)
 			writel(v, scratch_reg2);
@@ -771,41 +777,95 @@ static void gfx_v9_0_rlcg_w(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 
 		writel(v, ((void __iomem *)adev->rmmio) + (offset * 4));
 	} else {
-		uint32_t i = 0;
-		uint32_t retries = 50000;
-
+		/*
+		 * 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 | 0x80000000, scratch_reg1);
+		writel(offset | flag, scratch_reg1);
 		writel(1, spare_int);
-		for (i = 0; i < retries; i++) {
-			u32 tmp;
 
+		for (i = 0; i < retries; i++) {
 			tmp = readl(scratch_reg1);
-			if (!(tmp & 0x80000000))
+			if (!(tmp & flag))
 				break;
 
 			udelay(10);
 		}
-		if (i >= retries)
-			pr_err("timeout: rlcg program reg:0x%05x failed !\n", offset);
+
+		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 v, u32 acc_flags, u32 hwip)
+			       u32 value, u32 acc_flags, u32 hwip)
 {
-	if ((acc_flags & AMDGPU_REGS_RLC) &&
-	    amdgpu_sriov_fullaccess(adev)) {
-		gfx_v9_0_rlcg_w(adev, offset, v, acc_flags);
+	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, v);
+		WREG32_NO_KIQ(offset, value);
 	else
-		WREG32(offset, v);
+		WREG32(offset, value);
 }
 
 #define VEGA10_GB_ADDR_CONFIG_GOLDEN 0x2a114042
@@ -5134,7 +5194,7 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 	if (amdgpu_sriov_is_pp_one_vf(adev))
 		data = RREG32_NO_KIQ(reg);
 	else
-		data = RREG32(reg);
+		data = RREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL);
 
 	data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK;
 	data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT;
@@ -5190,6 +5250,7 @@ static const struct amdgpu_rlc_funcs gfx_v9_0_rlc_funcs = {
 	.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,
 };
 
@@ -5795,16 +5856,16 @@ static void gfx_v9_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
 
 	switch (state) {
 	case AMDGPU_IRQ_STATE_DISABLE:
-		mec_int_cntl = RREG32(mec_int_cntl_reg);
+		mec_int_cntl = RREG32_SOC15_IP(GC,mec_int_cntl_reg);
 		mec_int_cntl = REG_SET_FIELD(mec_int_cntl, CP_ME1_PIPE0_INT_CNTL,
 					     TIME_STAMP_INT_ENABLE, 0);
-		WREG32(mec_int_cntl_reg, mec_int_cntl);
+		WREG32_SOC15_IP(GC, mec_int_cntl_reg, mec_int_cntl);
 		break;
 	case AMDGPU_IRQ_STATE_ENABLE:
-		mec_int_cntl = RREG32(mec_int_cntl_reg);
+		mec_int_cntl = RREG32_SOC15_IP(GC, mec_int_cntl_reg);
 		mec_int_cntl = REG_SET_FIELD(mec_int_cntl, CP_ME1_PIPE0_INT_CNTL,
 					     TIME_STAMP_INT_ENABLE, 1);
-		WREG32(mec_int_cntl_reg, mec_int_cntl);
+		WREG32_SOC15_IP(GC, mec_int_cntl_reg, mec_int_cntl);
 		break;
 	default:
 		break;
-- 
2.25.1