From: <boyuan.zhang@amd.com>
To: <amd-gfx@lists.freedesktop.org>, <leo.liu@amd.com>,
<christian.koenig@amd.com>, <alexander.deucher@amd.com>,
<sunil.khatri@amd.com>
Cc: Boyuan Zhang <boyuan.zhang@amd.com>
Subject: [PATCH 15/18] drm/amdgpu: power vcn 4_0_3 by instance
Date: Wed, 2 Oct 2024 00:36:24 -0400 [thread overview]
Message-ID: <20241002043627.102414-16-boyuan.zhang@amd.com> (raw)
In-Reply-To: <20241002043627.102414-1-boyuan.zhang@amd.com>
From: Boyuan Zhang <boyuan.zhang@amd.com>
For vcn 4_0_3, add ip_block for each vcn instance during discovery stage.
And only powering on/off one of the vcn instance using the
instance value stored in ip_block, instead of powering on/off all
vcn instances. Modify the existing functions to use the instance value
in ip_block, and remove the original for loop for all vcn instances.
Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 3 +-
drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 487 +++++++++---------
2 files changed, 242 insertions(+), 248 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 8d8107241a5a..909a97b502d5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -2351,7 +2351,8 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &jpeg_v4_0_ip_block);
break;
case IP_VERSION(4, 0, 3):
- amdgpu_device_ip_block_add(adev, &vcn_v4_0_3_ip_block);
+ for (i = 0; i < adev->vcn.num_vcn_inst; ++i)
+ amdgpu_device_ip_block_add_instance(adev, &vcn_v4_0_3_ip_block, i);
amdgpu_device_ip_block_add(adev, &jpeg_v4_0_3_ip_block);
break;
case IP_VERSION(4, 0, 5):
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index 84939e92cd3a..aee8e1ee37ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -127,7 +127,7 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
{
struct amdgpu_device *adev = ip_block->adev;
struct amdgpu_ring *ring;
- int i, r, vcn_inst;
+ int inst = ip_block->instance, r, vcn_inst;
uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_3);
uint32_t *ptr;
@@ -147,38 +147,36 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
if (r)
return r;
- for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
- volatile struct amdgpu_vcn4_fw_shared *fw_shared;
+ volatile struct amdgpu_vcn4_fw_shared *fw_shared;
- vcn_inst = GET_INST(VCN, i);
+ vcn_inst = GET_INST(VCN, inst);
- ring = &adev->vcn.inst[i].ring_enc[0];
- ring->use_doorbell = true;
-
- if (!amdgpu_sriov_vf(adev))
- ring->doorbell_index =
- (adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
- 9 * vcn_inst;
- else
- ring->doorbell_index =
- (adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
- 32 * vcn_inst;
-
- ring->vm_hub = AMDGPU_MMHUB0(adev->vcn.inst[i].aid_id);
- sprintf(ring->name, "vcn_unified_%d", adev->vcn.inst[i].aid_id);
- r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0,
- AMDGPU_RING_PRIO_DEFAULT,
- &adev->vcn.inst[i].sched_score);
- if (r)
- return r;
+ ring = &adev->vcn.inst[inst].ring_enc[0];
+ ring->use_doorbell = true;
- fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
- fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
- fw_shared->sq.is_enabled = true;
+ if (!amdgpu_sriov_vf(adev))
+ ring->doorbell_index =
+ (adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
+ 9 * vcn_inst;
+ else
+ ring->doorbell_index =
+ (adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
+ 32 * vcn_inst;
+
+ ring->vm_hub = AMDGPU_MMHUB0(adev->vcn.inst[inst].aid_id);
+ sprintf(ring->name, "vcn_unified_%d", adev->vcn.inst[inst].aid_id);
+ r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0,
+ AMDGPU_RING_PRIO_DEFAULT,
+ &adev->vcn.inst[inst].sched_score);
+ if (r)
+ return r;
- if (amdgpu_vcnfw_log)
- amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
- }
+ fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
+ fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
+ fw_shared->sq.is_enabled = true;
+
+ if (amdgpu_vcnfw_log)
+ amdgpu_vcn_fwlog_init(&adev->vcn.inst[inst]);
if (amdgpu_sriov_vf(adev)) {
r = amdgpu_virt_alloc_mm_table(adev);
@@ -1091,172 +1089,170 @@ static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev)
*
* Start VCN block
*/
-static int vcn_v4_0_3_start(struct amdgpu_device *adev)
+static int vcn_v4_0_3_start(struct amdgpu_device *adev, unsigned int inst)
{
volatile struct amdgpu_vcn4_fw_shared *fw_shared;
struct amdgpu_ring *ring;
- int i, j, k, r, vcn_inst;
+ int j, k, r, vcn_inst;
uint32_t tmp;
if (adev->pm.dpm_enabled)
- amdgpu_dpm_enable_uvd(adev, true);
+ amdgpu_dpm_enable_vcn(adev, true, inst);
- for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
- if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
- r = vcn_v4_0_3_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
- continue;
- }
+ if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+ r = vcn_v4_0_3_start_dpg_mode(adev, inst, adev->vcn.indirect_sram);
+ return r;
+ }
- vcn_inst = GET_INST(VCN, i);
- /* set VCN status busy */
- tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) |
- UVD_STATUS__UVD_BUSY;
- WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp);
-
- /*SW clock gating */
- vcn_v4_0_3_disable_clock_gating(adev, i);
-
- /* enable VCPU clock */
- WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
- UVD_VCPU_CNTL__CLK_EN_MASK,
- ~UVD_VCPU_CNTL__CLK_EN_MASK);
-
- /* disable master interrupt */
- WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0,
- ~UVD_MASTINT_EN__VCPU_EN_MASK);
-
- /* enable LMI MC and UMC channels */
- WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0,
- ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-
- tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
- tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
- tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
- WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
-
- /* setup regUVD_LMI_CTRL */
- tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL);
- WREG32_SOC15(VCN, vcn_inst, regUVD_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 regUVD_MPC_CNTL */
- tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL);
- tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
- tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
- WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL, tmp);
-
- /* setup UVD_MPC_SET_MUXA0 */
- WREG32_SOC15(VCN, vcn_inst, regUVD_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, vcn_inst, regUVD_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_MUX */
- WREG32_SOC15(VCN, vcn_inst, regUVD_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_v4_0_3_mc_resume(adev, i);
-
- /* VCN global tiling registers */
- WREG32_SOC15(VCN, vcn_inst, regUVD_GFX8_ADDR_CONFIG,
- adev->gfx.config.gb_addr_config);
- WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG,
- adev->gfx.config.gb_addr_config);
-
- /* unblock VCPU register access */
- WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), 0,
- ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
-
- /* release VCPU reset to boot */
- WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
- ~UVD_VCPU_CNTL__BLK_RST_MASK);
+ vcn_inst = GET_INST(VCN, inst);
+ /* set VCN status busy */
+ tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) |
+ UVD_STATUS__UVD_BUSY;
+ WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp);
- for (j = 0; j < 10; ++j) {
- uint32_t status;
+ /*SW clock gating */
+ vcn_v4_0_3_disable_clock_gating(adev, inst);
- for (k = 0; k < 100; ++k) {
- status = RREG32_SOC15(VCN, vcn_inst,
- regUVD_STATUS);
- if (status & 2)
- break;
- mdelay(10);
- }
- r = 0;
- if (status & 2)
- break;
+ /* enable VCPU clock */
+ WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
+ UVD_VCPU_CNTL__CLK_EN_MASK,
+ ~UVD_VCPU_CNTL__CLK_EN_MASK);
- DRM_DEV_ERROR(adev->dev,
- "VCN decode not responding, trying to reset the VCPU!!!\n");
- WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst,
- regUVD_VCPU_CNTL),
- UVD_VCPU_CNTL__BLK_RST_MASK,
- ~UVD_VCPU_CNTL__BLK_RST_MASK);
- mdelay(10);
- WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst,
- regUVD_VCPU_CNTL),
- 0, ~UVD_VCPU_CNTL__BLK_RST_MASK);
+ /* disable master interrupt */
+ WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0,
+ ~UVD_MASTINT_EN__VCPU_EN_MASK);
+
+ /* enable LMI MC and UMC channels */
+ WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0,
+ ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+
+ tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
+ tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+ tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+ WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
+
+ /* setup regUVD_LMI_CTRL */
+ tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL);
+ WREG32_SOC15(VCN, vcn_inst, regUVD_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 regUVD_MPC_CNTL */
+ tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL);
+ tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
+ tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
+ WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL, tmp);
+
+ /* setup UVD_MPC_SET_MUXA0 */
+ WREG32_SOC15(VCN, vcn_inst, regUVD_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, vcn_inst, regUVD_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_MUX */
+ WREG32_SOC15(VCN, vcn_inst, regUVD_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_v4_0_3_mc_resume(adev, inst);
+
+ /* VCN global tiling registers */
+ WREG32_SOC15(VCN, vcn_inst, regUVD_GFX8_ADDR_CONFIG,
+ adev->gfx.config.gb_addr_config);
+ WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG,
+ adev->gfx.config.gb_addr_config);
+
+ /* unblock VCPU register access */
+ WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), 0,
+ ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+ /* release VCPU reset to boot */
+ WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
+ ~UVD_VCPU_CNTL__BLK_RST_MASK);
+ for (j = 0; j < 10; ++j) {
+ uint32_t status;
+
+ for (k = 0; k < 100; ++k) {
+ status = RREG32_SOC15(VCN, vcn_inst,
+ regUVD_STATUS);
+ if (status & 2)
+ break;
mdelay(10);
- r = -1;
}
+ r = 0;
+ if (status & 2)
+ break;
- if (r) {
- DRM_DEV_ERROR(adev->dev, "VCN decode not responding, giving up!!!\n");
- return r;
- }
+ DRM_DEV_ERROR(adev->dev,
+ "VCN decode not responding, trying to reset the VCPU!!!\n");
+ WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst,
+ regUVD_VCPU_CNTL),
+ UVD_VCPU_CNTL__BLK_RST_MASK,
+ ~UVD_VCPU_CNTL__BLK_RST_MASK);
+ mdelay(10);
+ WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst,
+ regUVD_VCPU_CNTL),
+ 0, ~UVD_VCPU_CNTL__BLK_RST_MASK);
- /* enable master interrupt */
- WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_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, vcn_inst, regUVD_STATUS), 0,
- ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+ if (r) {
+ DRM_DEV_ERROR(adev->dev, "VCN decode not responding, giving up!!!\n");
+ return r;
+ }
- ring = &adev->vcn.inst[i].ring_enc[0];
- fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+ /* enable master interrupt */
+ WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN),
+ UVD_MASTINT_EN__VCPU_EN_MASK,
+ ~UVD_MASTINT_EN__VCPU_EN_MASK);
- /* program the RB_BASE for ring buffer */
- WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO,
- lower_32_bits(ring->gpu_addr));
- WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI,
- upper_32_bits(ring->gpu_addr));
+ /* clear the busy bit of VCN_STATUS */
+ WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0,
+ ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
- WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE,
- ring->ring_size / sizeof(uint32_t));
+ ring = &adev->vcn.inst[inst].ring_enc[0];
+ fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
- /* resetting ring, fw should not check RB ring */
- tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
- tmp &= ~(VCN_RB_ENABLE__RB_EN_MASK);
- WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+ /* program the RB_BASE for ring buffer */
+ WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO,
+ lower_32_bits(ring->gpu_addr));
+ WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI,
+ upper_32_bits(ring->gpu_addr));
- /* Initialize the ring buffer's read and write pointers */
- WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0);
- WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0);
+ WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE,
+ ring->ring_size / sizeof(uint32_t));
- tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
- tmp |= VCN_RB_ENABLE__RB_EN_MASK;
- WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+ /* resetting ring, fw should not check RB ring */
+ tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
+ tmp &= ~(VCN_RB_ENABLE__RB_EN_MASK);
+ WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
- ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR);
- fw_shared->sq.queue_mode &=
- cpu_to_le32(~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF));
+ /* Initialize the ring buffer's read and write pointers */
+ WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0);
+ WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0);
+
+ tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
+ tmp |= VCN_RB_ENABLE__RB_EN_MASK;
+ WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+
+ ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR);
+ fw_shared->sq.queue_mode &=
+ cpu_to_le32(~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF));
- }
return 0;
}
@@ -1299,81 +1295,79 @@ static int vcn_v4_0_3_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
*
* Stop VCN block
*/
-static int vcn_v4_0_3_stop(struct amdgpu_device *adev)
+static int vcn_v4_0_3_stop(struct amdgpu_device *adev, unsigned int inst)
{
volatile struct amdgpu_vcn4_fw_shared *fw_shared;
- int i, r = 0, vcn_inst;
+ int r = 0, vcn_inst;
uint32_t tmp;
- for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
- vcn_inst = GET_INST(VCN, i);
+ vcn_inst = GET_INST(VCN, inst);
- fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
- fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
+ fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
+ fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
- if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
- vcn_v4_0_3_stop_dpg_mode(adev, i);
- continue;
- }
+ if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+ vcn_v4_0_3_stop_dpg_mode(adev, inst);
+ goto Done;
+ }
- /* wait for vcn idle */
- r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS,
- UVD_STATUS__IDLE, 0x7);
- if (r)
- goto Done;
-
- 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, vcn_inst, regUVD_LMI_STATUS, tmp,
- tmp);
- if (r)
- goto Done;
-
- /* stall UMC channel */
- tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2);
- tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
- WREG32_SOC15(VCN, vcn_inst, regUVD_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, vcn_inst, regUVD_LMI_STATUS, tmp,
- tmp);
- if (r)
- goto Done;
+ /* wait for vcn idle */
+ r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS,
+ UVD_STATUS__IDLE, 0x7);
+ if (r)
+ goto Done;
+
+ 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, vcn_inst, regUVD_LMI_STATUS, tmp,
+ tmp);
+ if (r)
+ goto Done;
+
+ /* stall UMC channel */
+ tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2);
+ tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+ WREG32_SOC15(VCN, vcn_inst, regUVD_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, vcn_inst, regUVD_LMI_STATUS, tmp,
+ tmp);
+ if (r)
+ goto Done;
- /* Unblock VCPU Register access */
- WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL),
- UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
- ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+ /* Unblock VCPU Register access */
+ WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL),
+ UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
+ ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
- /* release VCPU reset to boot */
- WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
- UVD_VCPU_CNTL__BLK_RST_MASK,
- ~UVD_VCPU_CNTL__BLK_RST_MASK);
+ /* release VCPU reset to boot */
+ WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
+ UVD_VCPU_CNTL__BLK_RST_MASK,
+ ~UVD_VCPU_CNTL__BLK_RST_MASK);
- /* disable VCPU clock */
- WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
- ~(UVD_VCPU_CNTL__CLK_EN_MASK));
+ /* disable VCPU clock */
+ WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
+ ~(UVD_VCPU_CNTL__CLK_EN_MASK));
- /* reset LMI UMC/LMI/VCPU */
- tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
- tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
- WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
+ /* reset LMI UMC/LMI/VCPU */
+ tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
+ tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+ WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
- tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
- tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
- WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
+ tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
+ tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+ WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
- /* clear VCN status */
- WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0);
+ /* clear VCN status */
+ WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0);
- /* apply HW clock gating */
- vcn_v4_0_3_enable_clock_gating(adev, i);
- }
+ /* apply HW clock gating */
+ vcn_v4_0_3_enable_clock_gating(adev, inst);
Done:
if (adev->pm.dpm_enabled)
- amdgpu_dpm_enable_uvd(adev, false);
+ amdgpu_dpm_enable_vcn(adev, false, inst);
return 0;
}
@@ -1630,29 +1624,28 @@ static int vcn_v4_0_3_set_powergating_state(struct amdgpu_ip_block *ip_block,
enum amd_powergating_state state)
{
struct amdgpu_device *adev = ip_block->adev;
+ int i = ip_block->instance;
int ret;
- for (int i = 0; i < adev->vcn.num_vcn_inst; ++i) {
- /* for SRIOV, guest should not control VCN Power-gating
- * MMSCH FW should control Power-gating and clock-gating
- * guest should avoid touching CGC and PG
- */
- if (amdgpu_sriov_vf(adev)) {
- adev->vcn.cur_state[i] = AMD_PG_STATE_UNGATE;
- return 0;
- }
+ /* for SRIOV, guest should not control VCN Power-gating
+ * MMSCH FW should control Power-gating and clock-gating
+ * guest should avoid touching CGC and PG
+ */
+ if (amdgpu_sriov_vf(adev)) {
+ adev->vcn.cur_state[i] = AMD_PG_STATE_UNGATE;
+ return 0;
+ }
- if (state == adev->vcn.cur_state[i])
- return 0;
+ if (state == adev->vcn.cur_state[i])
+ return 0;
- if (state == AMD_PG_STATE_GATE)
- ret = vcn_v4_0_3_stop(adev);
- else
- ret = vcn_v4_0_3_start(adev);
+ if (state == AMD_PG_STATE_GATE)
+ ret = vcn_v4_0_3_stop(adev, i);
+ else
+ ret = vcn_v4_0_3_start(adev, i);
- if (!ret)
- adev->vcn.cur_state[i] = state;
- }
+ if (!ret)
+ adev->vcn.cur_state[i] = state;
return ret;
}
--
2.34.1
next prev parent reply other threads:[~2024-10-02 4:40 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-02 4:36 [PATCH 00/18] Separating vcn power management by instance boyuan.zhang
2024-10-02 4:36 ` [PATCH 01/18] drm/amd/pm: add new vcn enable function pointer boyuan.zhang
2024-10-02 17:10 ` Alex Deucher
2024-10-04 18:38 ` Boyuan Zhang
2024-10-02 4:36 ` [PATCH 02/18] drm/amd/pm: enable vcn by instance for smu v13 boyuan.zhang
2024-10-02 4:36 ` [PATCH 03/18] drm/amd/pm: enable vcn by instance for smu v14 boyuan.zhang
2024-10-02 4:36 ` [PATCH 04/18] drm/amd/pm: enable vcn by instance for smu 11 boyuan.zhang
2024-10-02 4:36 ` [PATCH 05/18] drm/amd/pm: set vcn enable by instance boyuan.zhang
2024-10-02 11:19 ` Christian König
2024-10-04 18:40 ` Boyuan Zhang
2024-10-02 4:36 ` [PATCH 06/18] drm/amd/pm: set powergating by smu " boyuan.zhang
2024-10-02 4:36 ` [PATCH 07/18] drm/amdgpu/vcn: separate gating state " boyuan.zhang
2024-10-02 11:28 ` Christian König
2024-10-04 18:42 ` Boyuan Zhang
2024-10-02 4:36 ` [PATCH 08/18] drm/amdgpu/vcn: separate idle work " boyuan.zhang
2024-10-02 4:36 ` [PATCH 09/18] drm/amdgpu: pass ip_block in set_powergating_state boyuan.zhang
2024-10-02 11:41 ` Christian König
2024-10-04 19:34 ` Boyuan Zhang
2024-10-02 4:36 ` [PATCH 10/18] drm/amdgpu: add ip block with instance boyuan.zhang
2024-10-02 17:32 ` Alex Deucher
2024-10-04 18:44 ` Boyuan Zhang
2024-10-02 4:36 ` [PATCH 11/18] drm/amdgpu: add set_powergating_state_instance boyuan.zhang
2024-10-02 4:36 ` [PATCH 12/18] drm/amdgpu: power vcn 2_5 by instance boyuan.zhang
2024-10-02 4:36 ` [PATCH 13/18] drm/amdgpu: power vcn 3_0 " boyuan.zhang
2024-10-02 4:36 ` [PATCH 14/18] drm/amdgpu: power vcn 4_0 " boyuan.zhang
2024-10-02 4:36 ` boyuan.zhang [this message]
2024-10-02 4:36 ` [PATCH 16/18] drm/amdgpu: power vcn 4_0_5 " boyuan.zhang
2024-10-02 4:36 ` [PATCH 17/18] drm/amdgpu: power vcn 5_0_0 " boyuan.zhang
2024-10-02 4:36 ` [PATCH 18/18] drm/amdgpu: set powergating state by vcn instance boyuan.zhang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20241002043627.102414-16-boyuan.zhang@amd.com \
--to=boyuan.zhang@amd.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=christian.koenig@amd.com \
--cc=leo.liu@amd.com \
--cc=sunil.khatri@amd.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.