github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-06-02 03:24:19 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

drm/amdgpu/vcn3.0: split code along instances

Browse Source 
Split the code on a per instance basis.  This will allow
us to use the per instance functions in the future to
handle more things per instance.

v2: squash in fix for stop() from Boyuan

Reviewed-by: Boyuan Zhang <Boyuan.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Alex Deucher 2024-11-13 11:47:49 -05:00
parent dae8700198
commit d39f1bb577
1 changed files with 212 additions and 219 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

431
drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
View File

@ -1134,192 +1134,186 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
return 0;
}
static int vcn_v3_0_start(struct amdgpu_device *adev)
static int vcn_v3_0_start(struct amdgpu_device *adev, int i)
{
volatile struct amdgpu_fw_shared *fw_shared;
struct amdgpu_ring *ring;
uint32_t rb_bufsz, tmp;
int i, j, k, r;
int j, k, r;
for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
if (adev->pm.dpm_enabled)
amdgpu_dpm_enable_vcn(adev, true, i);
}
if (adev->vcn.harvest_config & (1 << i))
return 0;
for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
if (adev->vcn.harvest_config & (1 << i))
continue;
if (adev->pm.dpm_enabled)
amdgpu_dpm_enable_vcn(adev, true, i);
if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
r = vcn_v3_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
continue;
}
if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
return vcn_v3_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
/* disable VCN power gating */
vcn_v3_0_disable_static_power_gating(adev, i);
/* disable VCN power gating */
vcn_v3_0_disable_static_power_gating(adev, i);
/* set VCN status busy */
tmp = RREG32_SOC15(VCN, i, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY;
WREG32_SOC15(VCN, i, mmUVD_STATUS, tmp);
/* set VCN status busy */
tmp = RREG32_SOC15(VCN, i, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY;
WREG32_SOC15(VCN, i, mmUVD_STATUS, tmp);
/*SW clock gating */
vcn_v3_0_disable_clock_gating(adev, i);
/* SW clock gating */
vcn_v3_0_disable_clock_gating(adev, i);
/* enable VCPU clock */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
/* enable VCPU clock */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
/* disable master interrupt */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), 0,
~UVD_MASTINT_EN__VCPU_EN_MASK);
/* disable master interrupt */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), 0,
~UVD_MASTINT_EN__VCPU_EN_MASK);
/* enable LMI MC and UMC channels */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_CTRL2), 0,
~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
/* enable LMI MC and UMC channels */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_CTRL2), 0,
~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
/* setup mmUVD_LMI_CTRL */
tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL);
WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL, tmp |
UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
/* setup mmUVD_LMI_CTRL */
tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL);
WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL, tmp |
UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
/* setup mmUVD_MPC_CNTL */
tmp = RREG32_SOC15(VCN, i, mmUVD_MPC_CNTL);
tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
WREG32_SOC15(VCN, i, mmUVD_MPC_CNTL, tmp);
/* setup mmUVD_MPC_CNTL */
tmp = RREG32_SOC15(VCN, i, mmUVD_MPC_CNTL);
tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
WREG32_SOC15(VCN, i, mmUVD_MPC_CNTL, tmp);
/* setup UVD_MPC_SET_MUXA0 */
WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXA0,
((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
(0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
(0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
(0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
/* setup UVD_MPC_SET_MUXA0 */
WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXA0,
((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
(0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
(0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
(0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
/* setup UVD_MPC_SET_MUXB0 */
WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXB0,
((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
(0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
(0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
(0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
/* setup UVD_MPC_SET_MUXB0 */
WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXB0,
((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
(0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
(0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
(0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
/* setup mmUVD_MPC_SET_MUX */
WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUX,
((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
(0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
(0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
/* setup mmUVD_MPC_SET_MUX */
WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUX,
((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
(0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
(0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
vcn_v3_0_mc_resume(adev, i);
vcn_v3_0_mc_resume(adev, i);
/* VCN global tiling registers */
WREG32_SOC15(VCN, i, mmUVD_GFX10_ADDR_CONFIG,
adev->gfx.config.gb_addr_config);
/* VCN global tiling registers */
WREG32_SOC15(VCN, i, mmUVD_GFX10_ADDR_CONFIG,
adev->gfx.config.gb_addr_config);
/* unblock VCPU register access */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), 0,
~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
/* unblock VCPU register access */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), 0,
~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
/* release VCPU reset to boot */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
~UVD_VCPU_CNTL__BLK_RST_MASK);
/* release VCPU reset to boot */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
~UVD_VCPU_CNTL__BLK_RST_MASK);
for (j = 0; j < 10; ++j) {
uint32_t status;
for (j = 0; j < 10; ++j) {
uint32_t status;
for (k = 0; k < 100; ++k) {
status = RREG32_SOC15(VCN, i, mmUVD_STATUS);
if (status & 2)
break;
mdelay(10);
}
r = 0;
for (k = 0; k < 100; ++k) {
status = RREG32_SOC15(VCN, i, mmUVD_STATUS);
if (status & 2)
break;
DRM_ERROR("VCN[%d] decode not responding, trying to reset the VCPU!!!\n", i);
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
UVD_VCPU_CNTL__BLK_RST_MASK,
~UVD_VCPU_CNTL__BLK_RST_MASK);
mdelay(10);
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
~UVD_VCPU_CNTL__BLK_RST_MASK);
mdelay(10);
r = -1;
}
r = 0;
if (status & 2)
break;
if (r) {
DRM_ERROR("VCN[%d] decode not responding, giving up!!!\n", i);
return r;
}
DRM_ERROR("VCN[%d] decode not responding, trying to reset the VCPU!!!\n", i);
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
UVD_VCPU_CNTL__BLK_RST_MASK,
~UVD_VCPU_CNTL__BLK_RST_MASK);
mdelay(10);
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
~UVD_VCPU_CNTL__BLK_RST_MASK);
/* enable master interrupt */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN),
UVD_MASTINT_EN__VCPU_EN_MASK,
~UVD_MASTINT_EN__VCPU_EN_MASK);
mdelay(10);
r = -1;
}
/* clear the busy bit of VCN_STATUS */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_STATUS), 0,
~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
if (r) {
DRM_ERROR("VCN[%d] decode not responding, giving up!!!\n", i);
return r;
}
WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_VMID, 0);
/* enable master interrupt */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN),
UVD_MASTINT_EN__VCPU_EN_MASK,
~UVD_MASTINT_EN__VCPU_EN_MASK);
ring = &adev->vcn.inst[i].ring_dec;
/* force RBC into idle state */
rb_bufsz = order_base_2(ring->ring_size);
tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp);
/* clear the busy bit of VCN_STATUS */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_STATUS), 0,
~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
fw_shared->multi_queue.decode_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_VMID, 0);
/* programm the RB_BASE for ring buffer */
WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
lower_32_bits(ring->gpu_addr));
WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
upper_32_bits(ring->gpu_addr));
ring = &adev->vcn.inst[i].ring_dec;
/* force RBC into idle state */
rb_bufsz = order_base_2(ring->ring_size);
tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp);
/* Initialize the ring buffer's read and write pointers */
WREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR, 0);
fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
fw_shared->multi_queue.decode_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
WREG32_SOC15(VCN, i, mmUVD_SCRATCH2, 0);
ring->wptr = RREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR);
WREG32_SOC15(VCN, i, mmUVD_RBC_RB_WPTR,
lower_32_bits(ring->wptr));
fw_shared->rb.wptr = lower_32_bits(ring->wptr);
fw_shared->multi_queue.decode_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
/* programm the RB_BASE for ring buffer */
WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
lower_32_bits(ring->gpu_addr));
WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
upper_32_bits(ring->gpu_addr));
if (amdgpu_ip_version(adev, UVD_HWIP, 0) !=
IP_VERSION(3, 0, 33)) {
fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
ring = &adev->vcn.inst[i].ring_enc[0];
WREG32_SOC15(VCN, i, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
WREG32_SOC15(VCN, i, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO, ring->gpu_addr);
WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
WREG32_SOC15(VCN, i, mmUVD_RB_SIZE, ring->ring_size / 4);
fw_shared->multi_queue.encode_generalpurpose_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
/* Initialize the ring buffer's read and write pointers */
WREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR, 0);
fw_shared->multi_queue.encode_lowlatency_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
ring = &adev->vcn.inst[i].ring_enc[1];
WREG32_SOC15(VCN, i, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
WREG32_SOC15(VCN, i, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO2, ring->gpu_addr);
WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
WREG32_SOC15(VCN, i, mmUVD_RB_SIZE2, ring->ring_size / 4);
fw_shared->multi_queue.encode_lowlatency_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
}
WREG32_SOC15(VCN, i, mmUVD_SCRATCH2, 0);
ring->wptr = RREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR);
WREG32_SOC15(VCN, i, mmUVD_RBC_RB_WPTR,
lower_32_bits(ring->wptr));
fw_shared->rb.wptr = lower_32_bits(ring->wptr);
fw_shared->multi_queue.decode_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
if (amdgpu_ip_version(adev, UVD_HWIP, 0) !=
IP_VERSION(3, 0, 33)) {
fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
ring = &adev->vcn.inst[i].ring_enc[0];
WREG32_SOC15(VCN, i, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
WREG32_SOC15(VCN, i, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO, ring->gpu_addr);
WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
WREG32_SOC15(VCN, i, mmUVD_RB_SIZE, ring->ring_size / 4);
fw_shared->multi_queue.encode_generalpurpose_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
fw_shared->multi_queue.encode_lowlatency_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
ring = &adev->vcn.inst[i].ring_enc[1];
WREG32_SOC15(VCN, i, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
WREG32_SOC15(VCN, i, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO2, ring->gpu_addr);
WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
WREG32_SOC15(VCN, i, mmUVD_RB_SIZE2, ring->ring_size / 4);
fw_shared->multi_queue.encode_lowlatency_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
}
return 0;
@ -1565,81 +1559,78 @@ static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
return 0;
}
static int vcn_v3_0_stop(struct amdgpu_device *adev)
static int vcn_v3_0_stop(struct amdgpu_device *adev, int i)
{
uint32_t tmp;
int i, r = 0;
int r = 0;
for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
if (adev->vcn.harvest_config & (1 << i))
continue;
if (adev->vcn.harvest_config & (1 << i))
return 0;
if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
r = vcn_v3_0_stop_dpg_mode(adev, i);
continue;
}
/* wait for vcn idle */
r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7);
if (r)
return r;
tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
UVD_LMI_STATUS__READ_CLEAN_MASK |
UVD_LMI_STATUS__WRITE_CLEAN_MASK |
UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
if (r)
return r;
/* disable LMI UMC channel */
tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2);
tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2, tmp);
tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK|
UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
if (r)
return r;
/* block VCPU register access */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL),
UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
/* reset VCPU */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
UVD_VCPU_CNTL__BLK_RST_MASK,
~UVD_VCPU_CNTL__BLK_RST_MASK);
/* disable VCPU clock */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
~(UVD_VCPU_CNTL__CLK_EN_MASK));
/* apply soft reset */
tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
/* clear status */
WREG32_SOC15(VCN, i, mmUVD_STATUS, 0);
/* apply HW clock gating */
vcn_v3_0_enable_clock_gating(adev, i);
/* enable VCN power gating */
vcn_v3_0_enable_static_power_gating(adev, i);
if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
r = vcn_v3_0_stop_dpg_mode(adev, i);
goto done;
}
for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
if (adev->pm.dpm_enabled)
amdgpu_dpm_enable_vcn(adev, false, i);
}
/* wait for vcn idle */
r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7);
if (r)
goto done;
return 0;
tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
UVD_LMI_STATUS__READ_CLEAN_MASK |
UVD_LMI_STATUS__WRITE_CLEAN_MASK |
UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
if (r)
goto done;
/* disable LMI UMC channel */
tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2);
tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2, tmp);
tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK|
UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
if (r)
goto done;
/* block VCPU register access */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL),
UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
/* reset VCPU */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
UVD_VCPU_CNTL__BLK_RST_MASK,
~UVD_VCPU_CNTL__BLK_RST_MASK);
/* disable VCPU clock */
WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
~(UVD_VCPU_CNTL__CLK_EN_MASK));
/* apply soft reset */
tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
/* clear status */
WREG32_SOC15(VCN, i, mmUVD_STATUS, 0);
/* apply HW clock gating */
vcn_v3_0_enable_clock_gating(adev, i);
/* enable VCN power gating */
vcn_v3_0_enable_static_power_gating(adev, i);
done:
if (adev->pm.dpm_enabled)
amdgpu_dpm_enable_vcn(adev, false, i);
return r;
}
static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev,
@ -2163,7 +2154,7 @@ static int vcn_v3_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
enum amd_powergating_state state)
{
struct amdgpu_device *adev = ip_block->adev;
int ret;
int ret = 0, i;
/* for SRIOV, guest should not control VCN Power-gating
* MMSCH FW should control Power-gating and clock-gating
@ -2177,10 +2168,12 @@ static int vcn_v3_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
if (state == adev->vcn.cur_state)
return 0;
if (state == AMD_PG_STATE_GATE)
ret = vcn_v3_0_stop(adev);
else
ret = vcn_v3_0_start(adev);
for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
if (state == AMD_PG_STATE_GATE)
ret |= vcn_v3_0_stop(adev, i);
else
ret |= vcn_v3_0_start(adev, i);
}
if (!ret)
adev->vcn.cur_state = state;