diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 108 |
1 files changed, 28 insertions, 80 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index c87263ed20ec..3cabceee5f57 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -30,6 +30,7 @@ #include "soc15d.h" #include "vcn_v2_0.h" #include "mmsch_v3_0.h" +#include "vcn_sw_ring.h" #include "vcn/vcn_3_0_0_offset.h" #include "vcn/vcn_3_0_0_sh_mask.h" @@ -37,6 +38,9 @@ #include <drm/drm_drv.h> +#define VCN_VID_SOC_ADDRESS_2_0 0x1fa00 +#define VCN1_VID_SOC_ADDRESS_3_0 0x48200 + #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET 0x27 #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET 0x0f #define mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET 0x10 @@ -219,6 +223,11 @@ static int vcn_v3_0_sw_init(void *handle) cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) | cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB); fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED); + fw_shared->present_flag_0 |= AMDGPU_VCN_SMU_VERSION_INFO_FLAG; + if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 2)) + fw_shared->smu_interface_info.smu_interface_type = 2; + else if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 1)) + fw_shared->smu_interface_info.smu_interface_type = 1; if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); @@ -575,8 +584,8 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)), 0, indirect); /* VCN global tiling registers */ - WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( - UVD, 0, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); + WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( + UVD, inst_idx, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); } static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) @@ -1480,8 +1489,11 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) { + struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; + vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state); + /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); @@ -1687,7 +1699,7 @@ static uint64_t vcn_v3_0_dec_ring_get_wptr(struct amdgpu_ring *ring) struct amdgpu_device *adev = ring->adev; if (ring->use_doorbell) - return adev->wb.wb[ring->wptr_offs]; + return *ring->wptr_cpu_addr; else return RREG32_SOC15(VCN, ring->me, mmUVD_RBC_RB_WPTR); } @@ -1713,75 +1725,13 @@ static void vcn_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring) } if (ring->use_doorbell) { - adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr); + *ring->wptr_cpu_addr = lower_32_bits(ring->wptr); WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr)); } else { WREG32_SOC15(VCN, ring->me, mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr)); } } -static void vcn_v3_0_dec_sw_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, - u64 seq, uint32_t flags) -{ - WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT); - - amdgpu_ring_write(ring, VCN_DEC_SW_CMD_FENCE); - amdgpu_ring_write(ring, addr); - amdgpu_ring_write(ring, upper_32_bits(addr)); - amdgpu_ring_write(ring, seq); - amdgpu_ring_write(ring, VCN_DEC_SW_CMD_TRAP); -} - -static void vcn_v3_0_dec_sw_ring_insert_end(struct amdgpu_ring *ring) -{ - amdgpu_ring_write(ring, VCN_DEC_SW_CMD_END); -} - -static void vcn_v3_0_dec_sw_ring_emit_ib(struct amdgpu_ring *ring, - struct amdgpu_job *job, - struct amdgpu_ib *ib, - uint32_t flags) -{ - uint32_t vmid = AMDGPU_JOB_GET_VMID(job); - - amdgpu_ring_write(ring, VCN_DEC_SW_CMD_IB); - amdgpu_ring_write(ring, vmid); - amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr)); - amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr)); - amdgpu_ring_write(ring, ib->length_dw); -} - -static void vcn_v3_0_dec_sw_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, - uint32_t val, uint32_t mask) -{ - amdgpu_ring_write(ring, VCN_DEC_SW_CMD_REG_WAIT); - amdgpu_ring_write(ring, reg << 2); - amdgpu_ring_write(ring, mask); - amdgpu_ring_write(ring, val); -} - -static void vcn_v3_0_dec_sw_ring_emit_vm_flush(struct amdgpu_ring *ring, - uint32_t vmid, uint64_t pd_addr) -{ - struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub]; - uint32_t data0, data1, mask; - - pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr); - - /* wait for register write */ - data0 = hub->ctx0_ptb_addr_lo32 + vmid * hub->ctx_addr_distance; - data1 = lower_32_bits(pd_addr); - mask = 0xffffffff; - vcn_v3_0_dec_sw_ring_emit_reg_wait(ring, data0, data1, mask); -} - -static void vcn_v3_0_dec_sw_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val) -{ - amdgpu_ring_write(ring, VCN_DEC_SW_CMD_REG_WRITE); - amdgpu_ring_write(ring, reg << 2); - amdgpu_ring_write(ring, val); -} - static const struct amdgpu_ring_funcs vcn_v3_0_dec_sw_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0x3f, @@ -1794,22 +1744,20 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_sw_ring_vm_funcs = { .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 4 + - 4 + /* vcn_v3_0_dec_sw_ring_emit_vm_flush */ - 5 + 5 + /* vcn_v3_0_dec_sw_ring_emit_fdec_swe x2 vm fdec_swe */ - 1, /* vcn_v3_0_dec_sw_ring_insert_end */ - .emit_ib_size = 5, /* vcn_v3_0_dec_sw_ring_emit_ib */ - .emit_ib = vcn_v3_0_dec_sw_ring_emit_ib, - .emit_fence = vcn_v3_0_dec_sw_ring_emit_fence, - .emit_vm_flush = vcn_v3_0_dec_sw_ring_emit_vm_flush, + VCN_SW_RING_EMIT_FRAME_SIZE, + .emit_ib_size = 5, /* vcn_dec_sw_ring_emit_ib */ + .emit_ib = vcn_dec_sw_ring_emit_ib, + .emit_fence = vcn_dec_sw_ring_emit_fence, + .emit_vm_flush = vcn_dec_sw_ring_emit_vm_flush, .test_ring = amdgpu_vcn_dec_sw_ring_test_ring, .test_ib = NULL,//amdgpu_vcn_dec_sw_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, - .insert_end = vcn_v3_0_dec_sw_ring_insert_end, + .insert_end = vcn_dec_sw_ring_insert_end, .pad_ib = amdgpu_ring_generic_pad_ib, .begin_use = amdgpu_vcn_ring_begin_use, .end_use = amdgpu_vcn_ring_end_use, - .emit_wreg = vcn_v3_0_dec_sw_ring_emit_wreg, - .emit_reg_wait = vcn_v3_0_dec_sw_ring_emit_reg_wait, + .emit_wreg = vcn_dec_sw_ring_emit_wreg, + .emit_reg_wait = vcn_dec_sw_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, }; @@ -2004,12 +1952,12 @@ static uint64_t vcn_v3_0_enc_ring_get_wptr(struct amdgpu_ring *ring) if (ring == &adev->vcn.inst[ring->me].ring_enc[0]) { if (ring->use_doorbell) - return adev->wb.wb[ring->wptr_offs]; + return *ring->wptr_cpu_addr; else return RREG32_SOC15(VCN, ring->me, mmUVD_RB_WPTR); } else { if (ring->use_doorbell) - return adev->wb.wb[ring->wptr_offs]; + return *ring->wptr_cpu_addr; else return RREG32_SOC15(VCN, ring->me, mmUVD_RB_WPTR2); } @@ -2028,14 +1976,14 @@ static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring) if (ring == &adev->vcn.inst[ring->me].ring_enc[0]) { if (ring->use_doorbell) { - adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr); + *ring->wptr_cpu_addr = lower_32_bits(ring->wptr); WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr)); } else { WREG32_SOC15(VCN, ring->me, mmUVD_RB_WPTR, lower_32_bits(ring->wptr)); } } else { if (ring->use_doorbell) { - adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr); + *ring->wptr_cpu_addr = lower_32_bits(ring->wptr); WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr)); } else { WREG32_SOC15(VCN, ring->me, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr)); |