drm/amdgpu: Add xcc param to SRIOV kiq write and WREG32_SOC15_IP_NO_KIQ (v4)

WREG32/RREG32_SOC15_IP_NO_KIQ and amdgpu_virt_kiq_reg_write_reg_wait
are not using the correct rlcg interface or mec engine, respectively.

Add xcc instance parameter to them.

v4: Use GET_INST and squash commit with:
"drm/amdgpu: Add xcc_inst param to amdgpu_virt_kiq_reg_write_reg_wait"

v3: xcc not needed for MMMHUB

v2: rebase
Signed-off-by: Victor Lu <victorchengchi.lu@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c

@@ -73,9 +73,10 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev)
 
 void amdgpu_virt_kiq_reg_write_reg_wait(struct amdgpu_device *adev,
 					uint32_t reg0, uint32_t reg1,
-					uint32_t ref, uint32_t mask)
+					uint32_t ref, uint32_t mask,
+					uint32_t xcc_inst)
 {
-	struct amdgpu_kiq *kiq = &adev->gfx.kiq[0];
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq[xcc_inst];
 	struct amdgpu_ring *ring = &kiq->ring;
 	signed long r, cnt = 0;
 	unsigned long flags;

drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h

@@ -334,7 +334,8 @@ bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev);
 void amdgpu_virt_init_setting(struct amdgpu_device *adev);
 void amdgpu_virt_kiq_reg_write_reg_wait(struct amdgpu_device *adev,
 					uint32_t reg0, uint32_t rreg1,
-					uint32_t ref, uint32_t mask);
+					uint32_t ref, uint32_t mask,
+					uint32_t xcc_inst);
 int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init);
 int amdgpu_virt_release_full_gpu(struct amdgpu_device *adev, bool init);
 int amdgpu_virt_reset_gpu(struct amdgpu_device *adev);

drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c

@@ -268,7 +268,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	if (adev->gfx.kiq[0].ring.sched.ready && !adev->enable_mes &&
 	    (amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev))) {
 		amdgpu_virt_kiq_reg_write_reg_wait(adev, req, ack, inv_req,
-				1 << vmid);
+				1 << vmid, GET_INST(GC, 0));
 		return;
 	}
 

drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c

@@ -229,7 +229,7 @@ static void gmc_v11_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	if ((adev->gfx.kiq[0].ring.sched.ready || adev->mes.ring.sched.ready) &&
 	    (amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev))) {
 		amdgpu_virt_kiq_reg_write_reg_wait(adev, req, ack, inv_req,
-				1 << vmid);
+				1 << vmid, GET_INST(GC, 0));
 		return;
 	}
 

drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c

@@ -817,7 +817,7 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 					uint32_t vmhub, uint32_t flush_type)
 {
 	bool use_semaphore = gmc_v9_0_use_invalidate_semaphore(adev, vmhub);
-	u32 j, inv_req, tmp, sem, req, ack;
+	u32 j, inv_req, tmp, sem, req, ack, inst;
 	const unsigned int eng = 17;
 	struct amdgpu_vmhub *hub;
 
@@ -832,13 +832,17 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	/* This is necessary for a HW workaround under SRIOV as well
 	 * as GFXOFF under bare metal
 	 */
-	if (adev->gfx.kiq[0].ring.sched.ready &&
+	if (vmhub >= AMDGPU_MMHUB0(0))
+		inst = GET_INST(GC, 0);
+	else
+		inst = vmhub;
+	if (adev->gfx.kiq[inst].ring.sched.ready &&
 	    (amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev))) {
 		uint32_t req = hub->vm_inv_eng0_req + hub->eng_distance * eng;
 		uint32_t ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
 
 		amdgpu_virt_kiq_reg_write_reg_wait(adev, req, ack, inv_req,
-						   1 << vmid);
+						   1 << vmid, inst);
 		return;
 	}
 
@@ -856,9 +860,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 		for (j = 0; j < adev->usec_timeout; j++) {
 			/* a read return value of 1 means semaphore acquire */
 			if (vmhub >= AMDGPU_MMHUB0(0))
-				tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, sem);
+				tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, sem, inst);
 			else
-				tmp = RREG32_SOC15_IP_NO_KIQ(GC, sem);
+				tmp = RREG32_SOC15_IP_NO_KIQ(GC, sem, inst);
 			if (tmp & 0x1)
 				break;
 			udelay(1);
@@ -869,9 +873,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	}
 
 	if (vmhub >= AMDGPU_MMHUB0(0))
-		WREG32_SOC15_IP_NO_KIQ(MMHUB, req, inv_req);
+		WREG32_SOC15_IP_NO_KIQ(MMHUB, req, inv_req, inst);
 	else
-		WREG32_SOC15_IP_NO_KIQ(GC, req, inv_req);
+		WREG32_SOC15_IP_NO_KIQ(GC, req, inv_req, inst);
 
 	/*
 	 * Issue a dummy read to wait for the ACK register to
@@ -884,9 +888,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 
 	for (j = 0; j < adev->usec_timeout; j++) {
 		if (vmhub >= AMDGPU_MMHUB0(0))
-			tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, ack);
+			tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, ack, inst);
 		else
-			tmp = RREG32_SOC15_IP_NO_KIQ(GC, ack);
+			tmp = RREG32_SOC15_IP_NO_KIQ(GC, ack, inst);
 		if (tmp & (1 << vmid))
 			break;
 		udelay(1);
@@ -899,9 +903,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 		 * write with 0 means semaphore release
 		 */
 		if (vmhub >= AMDGPU_MMHUB0(0))
-			WREG32_SOC15_IP_NO_KIQ(MMHUB, sem, 0);
+			WREG32_SOC15_IP_NO_KIQ(MMHUB, sem, 0, inst);
 		else
-			WREG32_SOC15_IP_NO_KIQ(GC, sem, 0);
+			WREG32_SOC15_IP_NO_KIQ(GC, sem, 0, inst);
 	}
 
 	spin_unlock(&adev->gmc.invalidate_lock);

drivers/gpu/drm/amd/amdgpu/soc15_common.h

@@ -69,7 +69,7 @@
 
 #define RREG32_SOC15_IP(ip, reg) __RREG32_SOC15_RLC__(reg, 0, ip##_HWIP, 0)
 
-#define RREG32_SOC15_IP_NO_KIQ(ip, reg) __RREG32_SOC15_RLC__(reg, AMDGPU_REGS_NO_KIQ, ip##_HWIP, 0)
+#define RREG32_SOC15_IP_NO_KIQ(ip, reg, inst) __RREG32_SOC15_RLC__(reg, AMDGPU_REGS_NO_KIQ, ip##_HWIP, inst)
 
 #define RREG32_SOC15_NO_KIQ(ip, inst, reg) \
 	__RREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, \
@@ -86,8 +86,8 @@
 #define WREG32_SOC15_IP(ip, reg, value) \
 	 __WREG32_SOC15_RLC__(reg, value, 0, ip##_HWIP, 0)
 
-#define WREG32_SOC15_IP_NO_KIQ(ip, reg, value) \
-	 __WREG32_SOC15_RLC__(reg, value, AMDGPU_REGS_NO_KIQ, ip##_HWIP, 0)
+#define WREG32_SOC15_IP_NO_KIQ(ip, reg, value, inst) \
+	 __WREG32_SOC15_RLC__(reg, value, AMDGPU_REGS_NO_KIQ, ip##_HWIP, inst)
 
 #define WREG32_SOC15_NO_KIQ(ip, inst, reg, value) \
 	__WREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, \