diff options
97 files changed, 1760 insertions, 812 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 8b4ca2576a3d..afec09930efa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1159,11 +1159,18 @@ uint32_t amdgpu_device_rreg(struct amdgpu_device *adev, uint32_t reg, uint32_t acc_flags); u32 amdgpu_device_indirect_rreg_ext(struct amdgpu_device *adev, u64 reg_addr); +uint32_t amdgpu_device_xcc_rreg(struct amdgpu_device *adev, + uint32_t reg, uint32_t acc_flags, + uint32_t xcc_id); void amdgpu_device_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint32_t acc_flags); void amdgpu_device_indirect_wreg_ext(struct amdgpu_device *adev, u64 reg_addr, u32 reg_data); +void amdgpu_device_xcc_wreg(struct amdgpu_device *adev, + uint32_t reg, uint32_t v, + uint32_t acc_flags, + uint32_t xcc_id); void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint32_t xcc_id); void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value); @@ -1204,8 +1211,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev); #define RREG32_NO_KIQ(reg) amdgpu_device_rreg(adev, (reg), AMDGPU_REGS_NO_KIQ) #define WREG32_NO_KIQ(reg, v) amdgpu_device_wreg(adev, (reg), (v), AMDGPU_REGS_NO_KIQ) -#define RREG32_KIQ(reg) amdgpu_kiq_rreg(adev, (reg)) -#define WREG32_KIQ(reg, v) amdgpu_kiq_wreg(adev, (reg), (v)) +#define RREG32_KIQ(reg) amdgpu_kiq_rreg(adev, (reg), 0) +#define WREG32_KIQ(reg, v) amdgpu_kiq_wreg(adev, (reg), (v), 0) #define RREG8(reg) amdgpu_mm_rreg8(adev, (reg)) #define WREG8(reg, v) amdgpu_mm_wreg8(adev, (reg), (v)) @@ -1215,6 +1222,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev); #define WREG32(reg, v) amdgpu_device_wreg(adev, (reg), (v), 0) #define REG_SET(FIELD, v) (((v) << FIELD##_SHIFT) & FIELD##_MASK) #define REG_GET(FIELD, v) (((v) << FIELD##_SHIFT) & FIELD##_MASK) +#define RREG32_XCC(reg, inst) amdgpu_device_xcc_rreg(adev, (reg), 0, inst) +#define WREG32_XCC(reg, v, inst) amdgpu_device_xcc_wreg(adev, (reg), (v), 0, inst) #define RREG32_PCIE(reg) adev->pcie_rreg(adev, (reg)) #define WREG32_PCIE(reg, v) adev->pcie_wreg(adev, (reg), (v)) #define RREG32_PCIE_PORT(reg) adev->pciep_rreg(adev, (reg)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 4da82fc64fef..2deebece810e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -1494,6 +1494,9 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) if (adev->asic_type < CHIP_RAVEN) return false; + if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) + return false; + /* * If ACPI_FADT_LOW_POWER_S0 is not set in the FADT, it is generally * risky to do any special firmware-related preparations for entering diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c index 490c8f5ddb60..f6598b9e4faa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c @@ -300,14 +300,13 @@ static int kgd_gfx_v9_4_3_hqd_load(struct amdgpu_device *adev, void *mqd, hqd_end = SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_AQL_DISPATCH_ID_HI); for (reg = hqd_base; reg <= hqd_end; reg++) - WREG32_RLC(reg, mqd_hqd[reg - hqd_base]); + WREG32_XCC(reg, mqd_hqd[reg - hqd_base], inst); /* Activate doorbell logic before triggering WPTR poll. */ data = REG_SET_FIELD(m->cp_hqd_pq_doorbell_control, CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1); - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_PQ_DOORBELL_CONTROL), - data); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_PQ_DOORBELL_CONTROL, data); if (wptr) { /* Don't read wptr with get_user because the user @@ -336,27 +335,24 @@ static int kgd_gfx_v9_4_3_hqd_load(struct amdgpu_device *adev, void *mqd, guessed_wptr += m->cp_hqd_pq_wptr_lo & ~(queue_size - 1); guessed_wptr += (uint64_t)m->cp_hqd_pq_wptr_hi << 32; - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_LO), - lower_32_bits(guessed_wptr)); - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_HI), - upper_32_bits(guessed_wptr)); - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_POLL_ADDR), - lower_32_bits((uintptr_t)wptr)); - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), - regCP_HQD_PQ_WPTR_POLL_ADDR_HI), + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_LO, + lower_32_bits(guessed_wptr)); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_HI, + upper_32_bits(guessed_wptr)); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_POLL_ADDR, + lower_32_bits((uintptr_t)wptr)); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_POLL_ADDR_HI, upper_32_bits((uintptr_t)wptr)); - WREG32(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_PQ_WPTR_POLL_CNTL1), - (uint32_t)kgd_gfx_v9_get_queue_mask(adev, pipe_id, - queue_id)); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_PQ_WPTR_POLL_CNTL1, + (uint32_t)kgd_gfx_v9_get_queue_mask(adev, pipe_id, queue_id)); } /* Start the EOP fetcher */ - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_EOP_RPTR), - REG_SET_FIELD(m->cp_hqd_eop_rptr, - CP_HQD_EOP_RPTR, INIT_FETCHER, 1)); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_EOP_RPTR, + REG_SET_FIELD(m->cp_hqd_eop_rptr, CP_HQD_EOP_RPTR, INIT_FETCHER, 1)); data = REG_SET_FIELD(m->cp_hqd_active, CP_HQD_ACTIVE, ACTIVE, 1); - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_ACTIVE), data); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_ACTIVE, data); kgd_gfx_v9_release_queue(adev, inst); @@ -494,15 +490,15 @@ static uint32_t kgd_gfx_v9_4_3_set_address_watch( VALID, 1); - WREG32_RLC((SOC15_REG_OFFSET(GC, GET_INST(GC, inst), + WREG32_XCC((SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regTCP_WATCH0_ADDR_H) + (watch_id * TCP_WATCH_STRIDE)), - watch_address_high); + watch_address_high, inst); - WREG32_RLC((SOC15_REG_OFFSET(GC, GET_INST(GC, inst), + WREG32_XCC((SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regTCP_WATCH0_ADDR_L) + (watch_id * TCP_WATCH_STRIDE)), - watch_address_low); + watch_address_low, inst); return watch_address_cntl; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index 51011e8ee90d..00fbc0f44c92 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -91,8 +91,8 @@ void kgd_gfx_v9_program_sh_mem_settings(struct amdgpu_device *adev, uint32_t vmi { kgd_gfx_v9_lock_srbm(adev, 0, 0, 0, vmid, inst); - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmSH_MEM_CONFIG), sh_mem_config); - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmSH_MEM_BASES), sh_mem_bases); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmSH_MEM_CONFIG, sh_mem_config); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmSH_MEM_BASES, sh_mem_bases); /* APE1 no longer exists on GFX9 */ kgd_gfx_v9_unlock_srbm(adev, inst); @@ -239,14 +239,13 @@ int kgd_gfx_v9_hqd_load(struct amdgpu_device *adev, void *mqd, for (reg = hqd_base; reg <= SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_HI); reg++) - WREG32_RLC(reg, mqd_hqd[reg - hqd_base]); + WREG32_XCC(reg, mqd_hqd[reg - hqd_base], inst); /* Activate doorbell logic before triggering WPTR poll. */ data = REG_SET_FIELD(m->cp_hqd_pq_doorbell_control, CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1); - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_DOORBELL_CONTROL), - data); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_PQ_DOORBELL_CONTROL, data); if (wptr) { /* Don't read wptr with get_user because the user @@ -275,25 +274,24 @@ int kgd_gfx_v9_hqd_load(struct amdgpu_device *adev, void *mqd, guessed_wptr += m->cp_hqd_pq_wptr_lo & ~(queue_size - 1); guessed_wptr += (uint64_t)m->cp_hqd_pq_wptr_hi << 32; - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_LO), - lower_32_bits(guessed_wptr)); - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_HI), - upper_32_bits(guessed_wptr)); - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_POLL_ADDR), - lower_32_bits((uintptr_t)wptr)); - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_POLL_ADDR_HI), - upper_32_bits((uintptr_t)wptr)); - WREG32_SOC15(GC, GET_INST(GC, inst), mmCP_PQ_WPTR_POLL_CNTL1, - (uint32_t)kgd_gfx_v9_get_queue_mask(adev, pipe_id, queue_id)); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_LO, + lower_32_bits(guessed_wptr)); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_HI, + upper_32_bits(guessed_wptr)); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_POLL_ADDR, + lower_32_bits((uintptr_t)wptr)); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_POLL_ADDR_HI, + upper_32_bits((uintptr_t)wptr)); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_PQ_WPTR_POLL_CNTL1, + (uint32_t)kgd_gfx_v9_get_queue_mask(adev, pipe_id, queue_id)); } /* Start the EOP fetcher */ - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_EOP_RPTR), - REG_SET_FIELD(m->cp_hqd_eop_rptr, - CP_HQD_EOP_RPTR, INIT_FETCHER, 1)); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_EOP_RPTR, + REG_SET_FIELD(m->cp_hqd_eop_rptr, CP_HQD_EOP_RPTR, INIT_FETCHER, 1)); data = REG_SET_FIELD(m->cp_hqd_active, CP_HQD_ACTIVE, ACTIVE, 1); - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_ACTIVE), data); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_ACTIVE, data); kgd_gfx_v9_release_queue(adev, inst); @@ -556,7 +554,7 @@ int kgd_gfx_v9_hqd_destroy(struct amdgpu_device *adev, void *mqd, break; } - WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_DEQUEUE_REQUEST), type); + WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_DEQUEUE_REQUEST, type); end_jiffies = (utimeout * HZ / 1000) + jiffies; while (true) { @@ -908,8 +906,8 @@ void kgd_gfx_v9_get_iq_wait_times(struct amdgpu_device *adev, uint32_t inst) { - *wait_times = RREG32(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), - mmCP_IQ_WAIT_TIME2)); + *wait_times = RREG32_SOC15_RLC(GC, GET_INST(GC, inst), + mmCP_IQ_WAIT_TIME2); } void kgd_gfx_v9_set_vm_context_page_table_base(struct amdgpu_device *adev, diff --git |