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;
/* 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;
}
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);
}
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
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);
* 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);
#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, \
#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, \