drm/amdgpu: add dummy read for some GCVM status registers

The GRBM register interface is now capable of bursting 1 cycle per
register wr->wr, wr->rd much faster than previous muticycle per
transaction done interface.  This has caused a problem where status
registers requiring HW to update have a 1 cycle delay, due to the
register update having to go through GRBM.

SW may operate on an incorrect value if they write a register and
immediately check the corresponding status register.

Registers requiring HW to clear or set fields may be delayed by 1 cycle.
For example,

1. write VM_INVALIDATE_ENG0_REQ mask = 5a
2. read VM_INVALIDATE_ENG0_ACK till the ack is same as the request mask = 5a
    a. HW will reset VM_INVALIDATE_ENG0_ACK = 0 until invalidation is complete
3. write VM_INVALIDATE_ENG0_REQ mask = 5a
4. read VM_INVALIDATE_ENG0_ACK till the ack is same as the request mask = 5a
    a. First read of VM_INVALIDATE_ENG0_ACK = 5a instead of 0
    b. Second read of VM_INVALIDATE_ENG0_ACK = 0 because
       the remote GRBM h/w register takes one extra cycle to be cleared
    c. In this case, SW will see a false ACK if they exit on first read

Affected registers (only GC variant)  |  Recommended Dummy Read
--------------------------------------+----------------------------
VM_INVALIDATE_ENG*_ACK                |  VM_INVALIDATE_ENG*_REQ
VM_L2_STATUS                          |  VM_L2_STATUS
VM_L2_PROTECTION_FAULT_STATUS         |  VM_L2_PROTECTION_FAULT_STATUS
VM_L2_PROTECTION_FAULT_ADDR_HI/LO32   |  VM_L2_PROTECTION_FAULT_ADDR_HI/LO32
VM_L2_IH_LOG_BUSY                     |  VM_L2_IH_LOG_BUSY
MC_VM_L2_PERFCOUNTER_HI/LO            |  MC_VM_L2_PERFCOUNTER_HI/LO
ATC_L2_PERFCOUNTER_HI/LO              |  ATC_L2_PERFCOUNTER_HI/LO
ATC_L2_PERFCOUNTER2_HI/LO             |  ATC_L2_PERFCOUNTER2_HI/LO
Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -136,6 +136,14 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev,
 	addr |= ((u64)entry->src_data[1] & 0xf) << 44;
 
 	if (!amdgpu_sriov_vf(adev)) {
+		/*
+		 * Issue a dummy read to wait for the status register to
+		 * be updated to avoid reading an incorrect value due to
+		 * the new fast GRBM interface.
+		 */
+		if (entry->vmid_src == AMDGPU_GFXHUB_0)
+			RREG32(hub->vm_l2_pro_fault_status);
+
 		status = RREG32(hub->vm_l2_pro_fault_status);
 		WREG32_P(hub->vm_l2_pro_fault_cntl, 1, ~1);
 	}
@@ -229,6 +237,13 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 
 	WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, tmp);
 
+	/*
+	 * Issue a dummy read to wait for the ACK register to be cleared
+	 * to avoid a false ACK due to the new fast GRBM interface.
+	 */
+	if (vmhub == AMDGPU_GFXHUB_0)
+		RREG32_NO_KIQ(hub->vm_inv_eng0_req + eng);
+
 	/* Wait for ACK with a delay.*/
 	for (i = 0; i < adev->usec_timeout; i++) {
 		tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_ack + eng);

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

@@ -356,6 +356,14 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 
 	/* If it's the first fault for this address, process it normally */
 	if (!amdgpu_sriov_vf(adev)) {
+		/*
+		 * Issue a dummy read to wait for the status register to
+		 * be updated to avoid reading an incorrect value due to
+		 * the new fast GRBM interface.
+		 */
+		if (entry->vmid_src == AMDGPU_GFXHUB_0)
+			RREG32(hub->vm_l2_pro_fault_status);
+
 		status = RREG32(hub->vm_l2_pro_fault_status);
 		WREG32_P(hub->vm_l2_pro_fault_cntl, 1, ~1);
 	}
@@ -484,6 +492,14 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 
 	spin_lock(&adev->gmc.invalidate_lock);
 	WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, tmp);
+
+	/*
+	 * Issue a dummy read to wait for the ACK register to be cleared
+	 * to avoid a false ACK due to the new fast GRBM interface.
+	 */
+	if (vmhub == AMDGPU_GFXHUB_0)
+		RREG32_NO_KIQ(hub->vm_inv_eng0_req + eng);
+
 	for (j = 0; j < adev->usec_timeout; j++) {
 		tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_ack + eng);
 		if (tmp & (1 << vmid))