diff options
Diffstat (limited to 'drivers/gpu')
641 files changed, 19944 insertions, 9587 deletions
diff --git a/drivers/gpu/Makefile b/drivers/gpu/Makefile index 8997f0096545..36a54d456630 100644 --- a/drivers/gpu/Makefile +++ b/drivers/gpu/Makefile @@ -5,3 +5,4 @@ obj-y += host1x/ drm/ vga/ obj-$(CONFIG_IMX_IPUV3_CORE) += ipu-v3/ obj-$(CONFIG_TRACE_GPU_MEM) += trace/ +obj-$(CONFIG_NOVA_CORE) += nova-core/ diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index e5b59de28216..1be14d8634f4 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -278,6 +278,15 @@ config DRM_GPUVM GPU-VM representation providing helpers to manage a GPUs virtual address space +config DRM_GPUSVM + tristate + depends on DRM && DEVICE_PRIVATE + select HMM_MIRROR + select MMU_NOTIFIER + help + GPU-SVM representation providing helpers to manage a GPUs shared + virtual memory + config DRM_BUDDY tristate depends on DRM diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 4cd054188faf..ed54a546bbe2 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -104,6 +104,7 @@ obj-$(CONFIG_DRM_PANEL_BACKLIGHT_QUIRKS) += drm_panel_backlight_quirks.o # obj-$(CONFIG_DRM_EXEC) += drm_exec.o obj-$(CONFIG_DRM_GPUVM) += drm_gpuvm.o +obj-$(CONFIG_DRM_GPUSVM) += drm_gpusvm.o obj-$(CONFIG_DRM_BUDDY) += drm_buddy.o diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 2b1990ea9639..2a9a41f4e748 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1192,6 +1192,7 @@ struct amdgpu_device { bool debug_use_vram_fw_buf; bool debug_enable_ras_aca; bool debug_exp_resets; + bool debug_disable_gpu_ring_reset; bool enforce_isolation[MAX_XCP]; /* Added this mutex for cleaner shader isolation between GFX and compute processes */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c index d11593cd1922..ffd4c64e123c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c @@ -392,6 +392,9 @@ static void aca_banks_generate_cper(struct amdgpu_device *adev, struct aca_bank_node *node; struct aca_bank *bank; + if (!adev->cper.enabled) + return; + if (!banks || !count) { dev_warn(adev->dev, "fail to generate cper records\n"); return; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h index b84a3489b116..6f62e5d80ed6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h @@ -76,6 +76,12 @@ struct ras_query_context; #define mmSMNAID_XCD1_MCA_SMU 0x38430400 /* SMN AID XCD1 */ #define mmSMNXCD_XCD0_MCA_SMU 0x40430400 /* SMN XCD XCD0 */ +#define ACA_BANK_ERR_CE_DE_DECODE(bank) \ + ((ACA_REG__STATUS__POISON((bank)->regs[ACA_REG_IDX_STATUS]) || \ + ACA_REG__STATUS__DEFERRED((bank)->regs[ACA_REG_IDX_STATUS])) ? \ + ACA_ERROR_TYPE_DEFERRED : \ + ACA_ERROR_TYPE_CE) + enum aca_reg_idx { ACA_REG_IDX_CTL = 0, ACA_REG_IDX_STATUS = 1, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c index deb0785350e8..4926996f94da 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c @@ -579,7 +579,7 @@ static int acp_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool acp_is_idle(void *handle) +static bool acp_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index b8d4e07d2043..b7f8f2ff143d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -394,6 +394,10 @@ static int amdgpu_atif_query_backlight_caps(struct amdgpu_atif *atif) characteristics.max_input_signal; atif->backlight_caps.ac_level = characteristics.ac_level; atif->backlight_caps.dc_level = characteristics.dc_level; + atif->backlight_caps.data_points = characteristics.number_of_points; + memcpy(atif->backlight_caps.luminance_data, + characteristics.data_points, + sizeof(atif->backlight_caps.luminance_data)); out: kfree(info); return err; @@ -1277,11 +1281,7 @@ void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_caps *caps) { struct amdgpu_atif *atif = &amdgpu_acpi_priv.atif; - caps->caps_valid = atif->backlight_caps.caps_valid; - caps->min_input_signal = atif->backlight_caps.min_input_signal; - caps->max_input_signal = atif->backlight_caps.max_input_signal; - caps->ac_level = atif->backlight_caps.ac_level; - caps->dc_level = atif->backlight_caps.dc_level; + memcpy(caps, &atif->backlight_caps, sizeof(*caps)); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 0312231b703e..4cec3a873995 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -555,48 +555,6 @@ out_put: return r; } -uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct amdgpu_device *dst, - struct amdgpu_device *src) -{ - struct amdgpu_device *peer_adev = src; - struct amdgpu_device *adev = dst; - int ret = amdgpu_xgmi_get_hops_count(adev, peer_adev); - - if (ret < 0) { - DRM_ERROR("amdgpu: failed to get xgmi hops count between node %d and %d. ret = %d\n", - adev->gmc.xgmi.physical_node_id, - peer_adev->gmc.xgmi.physical_node_id, ret); - ret = 0; - } - return (uint8_t)ret; -} - -int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst, - struct amdgpu_device *src, - bool is_min) -{ - struct amdgpu_device *adev = dst, *peer_adev; - int num_links; - - if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 4, 2)) - return 0; - - if (src) - peer_adev = src; - - /* num links returns 0 for indirect peers since indirect route is unknown. */ - num_links = is_min ? 1 : amdgpu_xgmi_get_num_links(adev, peer_adev); - if (num_links < 0) { - DRM_ERROR("amdgpu: failed to get xgmi num links between node %d and %d. ret = %d\n", - adev->gmc.xgmi.physical_node_id, - peer_adev->gmc.xgmi.physical_node_id, num_links); - num_links = 0; - } - - /* Aldebaran xGMI DPM is defeatured so assume x16 x 25Gbps for bandwidth. */ - return (num_links * 16 * 25000)/BITS_PER_BYTE; -} - int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct amdgpu_device *adev, bool is_min) { int num_lanes_shift = (is_min ? ffs(adev->pm.pcie_mlw_mask) : diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 236b73e283e8..b6ca41859b53 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -193,7 +193,7 @@ int kfd_debugfs_kfd_mem_limits(struct seq_file *m, void *data); #if IS_ENABLED(CONFIG_HSA_AMD) bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm); struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f); -int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo); +void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo); int amdgpu_amdkfd_evict_userptr(struct mmu_interval_notifier *mni, unsigned long cur_seq, struct kgd_mem *mem); int amdgpu_amdkfd_bo_validate_and_fence(struct amdgpu_bo *bo, @@ -213,9 +213,8 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f) } static inline -int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo) +void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo) { - return 0; } static inline @@ -255,11 +254,6 @@ int amdgpu_amdkfd_get_dmabuf_info(struct amdgpu_device *adev, int dma_buf_fd, uint64_t *bo_size, void *metadata_buffer, size_t buffer_size, uint32_t *metadata_size, uint32_t *flags, int8_t *xcp_id); -uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct amdgpu_device *dst, - struct amdgpu_device *src); -int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst, - struct amdgpu_device *src, - bool is_min); int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct amdgpu_device *adev, bool is_min); int amdgpu_amdkfd_send_close_event_drain_irq(struct amdgpu_device *adev, uint32_t *payload); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c index 8dfdb18197c4..6e861d08d044 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c @@ -193,4 +193,5 @@ const struct kfd2kgd_calls aldebaran_kfd2kgd = { .program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings, .hqd_get_pq_addr = kgd_gfx_v9_hqd_get_pq_addr, .hqd_reset = kgd_gfx_v9_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v9_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c index 9abf29b58ac7..c820418e8ccd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c @@ -419,5 +419,6 @@ const struct kfd2kgd_calls arcturus_kfd2kgd = { .get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy, .program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings, .hqd_get_pq_addr = kgd_gfx_v9_hqd_get_pq_addr, - .hqd_reset = kgd_gfx_v9_hqd_reset + .hqd_reset = kgd_gfx_v9_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v9_hqd_sdma_get_doorbell }; 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 e2ae714a700f..0c0998477598 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 @@ -509,6 +509,17 @@ static uint32_t kgd_gfx_v9_4_3_clear_address_watch(struct amdgpu_device *adev, return 0; } +static uint32_t kgd_gfx_v9_4_3_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue) +{ + uint32_t reg_offset = get_sdma_rlc_reg_offset(adev, engine, queue); + uint32_t status = RREG32(regSDMA_RLC0_CONTEXT_STATUS + reg_offset); + uint32_t doorbell_off = RREG32(regSDMA_RLC0_DOORBELL_OFFSET + reg_offset); + bool is_active = !!REG_GET_FIELD(status, SDMA_RLC0_CONTEXT_STATUS, SELECTED); + + return is_active ? doorbell_off >> 2 : 0; +} + const struct kfd2kgd_calls gc_9_4_3_kfd2kgd = { .program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings, .set_pasid_vmid_mapping = kgd_gfx_v9_4_3_set_pasid_vmid_mapping, @@ -543,5 +554,6 @@ const struct kfd2kgd_calls gc_9_4_3_kfd2kgd = { .set_address_watch = kgd_gfx_v9_4_3_set_address_watch, .clear_address_watch = kgd_gfx_v9_4_3_clear_address_watch, .hqd_get_pq_addr = kgd_gfx_v9_hqd_get_pq_addr, - .hqd_reset = kgd_gfx_v9_hqd_reset + .hqd_reset = kgd_gfx_v9_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v9_4_3_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c index 62176d607bef..2887b6f3eaa2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c @@ -1084,6 +1084,12 @@ uint64_t kgd_gfx_v10_hqd_reset(struct amdgpu_device *adev, return 0; } +uint32_t kgd_gfx_v10_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue) +{ + return 0; +} + const struct kfd2kgd_calls gfx_v10_kfd2kgd = { .program_sh_mem_settings = kgd_program_sh_mem_settings, .set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping, @@ -1112,5 +1118,6 @@ const struct kfd2kgd_calls gfx_v10_kfd2kgd = { .build_grace_period_packet_info = kgd_gfx_v10_build_grace_period_packet_info, .program_trap_handler_settings = program_trap_handler_settings, .hqd_get_pq_addr = kgd_gfx_v10_hqd_get_pq_addr, - .hqd_reset = kgd_gfx_v10_hqd_reset + .hqd_reset = kgd_gfx_v10_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v10_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h index 9efd2dd4fdd7..db577c2a847a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h @@ -65,3 +65,5 @@ uint64_t kgd_gfx_v10_hqd_reset(struct amdgpu_device *adev, uint32_t queue_id, uint32_t inst, unsigned int utimeout); +uint32_t kgd_gfx_v10_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c index c718bedda0ca..ac9ad505f9d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c @@ -682,5 +682,6 @@ const struct kfd2kgd_calls gfx_v10_3_kfd2kgd = { .set_address_watch = kgd_gfx_v10_set_address_watch, .clear_address_watch = kgd_gfx_v10_clear_address_watch, .hqd_get_pq_addr = kgd_gfx_v10_hqd_get_pq_addr, - .hqd_reset = kgd_gfx_v10_hqd_reset + .hqd_reset = kgd_gfx_v10_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v10_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c index a4ba49cb22db..e0e6a6a49d90 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c @@ -800,6 +800,12 @@ static uint64_t kgd_gfx_v11_hqd_reset(struct amdgpu_device *adev, return 0; } +static uint32_t kgd_gfx_v11_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue) +{ + return 0; +} + const struct kfd2kgd_calls gfx_v11_kfd2kgd = { .program_sh_mem_settings = program_sh_mem_settings_v11, .set_pasid_vmid_mapping = set_pasid_vmid_mapping_v11, @@ -824,5 +830,6 @@ const struct kfd2kgd_calls gfx_v11_kfd2kgd = { .set_address_watch = kgd_gfx_v11_set_address_watch, .clear_address_watch = kgd_gfx_v11_clear_address_watch, .hqd_get_pq_addr = kgd_gfx_v11_hqd_get_pq_addr, - .hqd_reset = kgd_gfx_v11_hqd_reset + .hqd_reset = kgd_gfx_v11_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v11_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c index 0dfe7093bd8a..6f0dc23c901b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c @@ -361,6 +361,12 @@ static uint32_t kgd_gfx_v12_clear_address_watch(struct amdgpu_device *adev, return 0; } +static uint32_t kgd_gfx_v12_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue) +{ + return 0; +} + const struct kfd2kgd_calls gfx_v12_kfd2kgd = { .init_interrupts = init_interrupts_v12, .hqd_dump = hqd_dump_v12, @@ -374,4 +380,5 @@ const struct kfd2kgd_calls gfx_v12_kfd2kgd = { .set_wave_launch_mode = kgd_gfx_v12_set_wave_launch_mode, .set_address_watch = kgd_gfx_v12_set_address_watch, .clear_address_watch = kgd_gfx_v12_clear_address_watch, + .hqd_sdma_get_doorbell = kgd_gfx_v12_hqd_sdma_get_doorbell }; 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 441568163e20..84135eb90660 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -1131,9 +1131,6 @@ uint64_t kgd_gfx_v9_hqd_get_pq_addr(struct amdgpu_device *adev, uint32_t low, high; uint64_t queue_addr = 0; - if (!amdgpu_gpu_recovery) - return 0; - kgd_gfx_v9_acquire_queue(adev, pipe_id, queue_id, inst); amdgpu_gfx_rlc_enter_safe_mode(adev, inst); @@ -1182,9 +1179,6 @@ uint64_t kgd_gfx_v9_hqd_reset(struct amdgpu_device *adev, uint32_t low, high, pipe_reset_data = 0; uint64_t queue_addr = 0; - if (!amdgpu_gpu_recovery) - return 0; - kgd_gfx_v9_acquire_queue(adev, pipe_id, queue_id, inst); amdgpu_gfx_rlc_enter_safe_mode(adev, inst); @@ -1229,6 +1223,13 @@ unlock_out: return queue_addr; } +uint32_t kgd_gfx_v9_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue) + +{ + return 0; +} + const struct kfd2kgd_calls gfx_v9_kfd2kgd = { .program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings, .set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping, @@ -1258,5 +1259,6 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = { .get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy, .program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings, .hqd_get_pq_addr = kgd_gfx_v9_hqd_get_pq_addr, - .hqd_reset = kgd_gfx_v9_hqd_reset + .hqd_reset = kgd_gfx_v9_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v9_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h index b6a91a552aa4..90c8fa13d519 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h @@ -111,3 +111,5 @@ uint64_t kgd_gfx_v9_hqd_reset(struct amdgpu_device *adev, uint32_t queue_id, uint32_t inst, unsigned int utimeout); +uint32_t kgd_gfx_v9_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index ea3f7ee18923..2ac6d4fa0601 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -370,40 +370,32 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo, return 0; } -int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo) +/** + * amdgpu_amdkfd_remove_all_eviction_fences - Remove all eviction fences + * @bo: the BO where to remove the evictions fences from. + * + * This functions should only be used on release when all references to the BO + * are already dropped. We remove the eviction fence from the private copy of + * the dma_resv object here since that is what is used during release to + * determine of the BO is idle or not. + */ +void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo) { - struct amdgpu_bo *root = bo; - struct amdgpu_vm_bo_base *vm_bo; - struct amdgpu_vm *vm; - struct amdkfd_process_info *info; - struct amdgpu_amdkfd_fence *ef; - int ret; - - /* we can always get vm_bo from root PD bo.*/ - while (root->parent) - root = root->parent; + struct dma_resv *resv = &bo->tbo.base._resv; + struct dma_fence *fence, *stub; + struct dma_resv_iter cursor; - vm_bo = root->vm_bo; - if (!vm_bo) - return 0; - - vm = vm_bo->vm; - if (!vm) - return 0; - - info = vm->process_info; - if (!info || !info->eviction_fence) - return 0; + dma_resv_assert_held(resv); - ef = container_of(dma_fence_get(&info->eviction_fence->base), - struct amdgpu_amdkfd_fence, base); - - BUG_ON(!dma_resv_trylock(bo->tbo.base.resv)); - ret = amdgpu_amdkfd_remove_eviction_fence(bo, ef); - dma_resv_unlock(bo->tbo.base.resv); + stub = dma_fence_get_stub(); + dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP, fence) { + if (!to_amdgpu_amdkfd_fence(fence)) + continue; - dma_fence_put(&ef->base); - return ret; + dma_resv_replace_fences(resv, fence->context, stub, + DMA_RESV_USAGE_BOOKKEEP); + } + dma_fence_put(stub); } static int amdgpu_amdkfd_bo_validate(struct amdgpu_bo *bo, uint32_t domain, @@ -603,12 +595,6 @@ kfd_mem_dmamap_dmabuf(struct kfd_mem_attachment *attachment) { struct ttm_operation_ctx ctx = {.interruptible = true}; struct amdgpu_bo *bo = attachment->bo_va->base.bo; - int ret; - - amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU); - ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); - if (ret) - return ret; amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT); return ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c index 20c474a32852..3f291b30b79f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c @@ -57,6 +57,8 @@ void amdgpu_cper_entry_fill_hdr(struct amdgpu_device *adev, enum amdgpu_cper_type type, enum cper_error_severity sev) { + char record_id[16]; + hdr->signature[0] = 'C'; hdr->signature[1] = 'P'; hdr->signature[2] = 'E'; @@ -71,7 +73,13 @@ void amdgpu_cper_entry_fill_hdr(struct amdgpu_device *adev, amdgpu_cper_get_timestamp(&hdr->timestamp); - snprintf(hdr->record_id, 8, "%d", atomic_inc_return(&adev->cper.unique_id)); + snprintf(record_id, 9, "%d:%X", + (adev->smuio.funcs && adev->smuio.funcs->get_socket_id) ? + adev->smuio.funcs->get_socket_id(adev) : + 0, + atomic_inc_return(&adev->cper.unique_id)); + memcpy(hdr->record_id, record_id, 8); + snprintf(hdr->platform_id, 16, "0x%04X:0x%04X", adev->pdev->vendor, adev->pdev->device); /* pmfw version should be part of creator_id according to CPER spec */ @@ -112,18 +120,15 @@ static int amdgpu_cper_entry_fill_section_desc(struct amdgpu_device *adev, section_desc->revision_major = CPER_SEC_MAJOR_REV_22; section_desc->sec_offset = section_offset; section_desc->sec_length = section_length; - section_desc->valid_bits.fru_id = 1; section_desc->valid_bits.fru_text = 1; section_desc->flag_bits.primary = 1; section_desc->severity = sev; section_desc->sec_type = sec_type; - if (adev->smuio.funcs && - adev->smuio.funcs->get_socket_id) - snprintf(section_desc->fru_text, 20, "OAM%d", - adev->smuio.funcs->get_socket_id(adev)); - /* TODO: fru_id is 16 bytes in CPER spec, but driver defines it as 20 bytes */ - snprintf(section_desc->fru_id, 16, "%llx", adev->unique_id); + snprintf(section_desc->fru_text, 20, "OAM%d", + (adev->smuio.funcs && adev->smuio.funcs->get_socket_id) ? + adev->smuio.funcs->get_socket_id(adev) : + 0); if (bp_threshold) section_desc->flag_bits.exceed_err_threshold = 1; @@ -304,6 +309,7 @@ int amdgpu_cper_generate_ue_record(struct amdgpu_device *adev, return ret; amdgpu_cper_ring_write(ring, fatal, fatal->record_length); + kfree(fatal); return 0; } @@ -326,6 +332,7 @@ int amdgpu_cper_generate_bp_threshold_record(struct amdgpu_device *adev) return ret; amdgpu_cper_ring_write(ring, bp_threshold, bp_threshold->record_length); + kfree(bp_threshold); return 0; } @@ -376,7 +383,7 @@ int amdgpu_cper_generate_ce_records(struct amdgpu_device *adev, amdgpu_cper_entry_fill_hdr(adev, corrected, AMDGPU_CPER_TYPE_RUNTIME, sev); - /* Combine CE and UE in cper record */ + /* Combine CE and DE in cper record */ list_for_each_entry(node, &banks->list, node) { bank = &node->bank; reg_data[CPER_ACA_REG_CTL_LO] = lower_32_bits(bank->regs[ACA_REG_IDX_CTL]); @@ -402,6 +409,7 @@ int amdgpu_cper_generate_ce_records(struct amdgpu_device *adev, } amdgpu_cper_ring_write(ring, corrected, corrected->record_length); + kfree(corrected); return 0; } @@ -538,15 +546,23 @@ static int amdgpu_cper_ring_init(struct amdgpu_device *adev) int amdgpu_cper_init(struct amdgpu_device *adev) { + int r; + if (!amdgpu_aca_is_enabled(adev)) return 0; + r = amdgpu_cper_ring_init(adev); + if (r) { + dev_err(adev->dev, "failed to initialize cper ring, r = %d\n", r); + return r; + } + mutex_init(&adev->cper.cper_lock); adev->cper.enabled = true; adev->cper.max_count = CPER_MAX_ALLOWED_COUNT; - return amdgpu_cper_ring_init(adev); + return 0; } int amdgpu_cper_fini(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c index 824f9da5b6ce..7b50741dc097 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c @@ -364,5 +364,9 @@ void amdgpu_coredump(struct amdgpu_device *adev, bool skip_vram_check, dev_coredumpm(dev->dev, THIS_MODULE, coredump, 0, GFP_NOWAIT, amdgpu_devcoredump_read, amdgpu_devcoredump_free); + + drm_info(dev, "AMDGPU device coredump file has been created\n"); + drm_info(dev, "Check your /sys/class/drm/card%d/device/devcoredump/data\n", + dev->primary->index); } #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 17e5967bfa60..9e9fec5b52de 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1662,6 +1662,13 @@ int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev) if (amdgpu_sriov_vf(adev)) return 0; + /* resizing on Dell G5 SE platforms causes problems with runtime pm */ + if ((amdgpu_runtime_pm != 0) && + adev->pdev->vendor == PCI_VENDOR_ID_ATI && + adev->pdev->device == 0x731f && + adev->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL) + return 0; + /* PCI_EXT_CAP_ID_VNDR extended capability is located at 0x100 */ if (!pci_find_ext_capability(adev->pdev, PCI_EXT_CAP_ID_VNDR)) DRM_WARN("System can't access extended configuration space, please check!!\n"); @@ -3098,7 +3105,8 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) amdgpu_fru_get_product_info(adev); - r = amdgpu_cper_init(adev); + if (!amdgpu_sriov_vf(adev) || amdgpu_sriov_ras_cper_en(adev)) + r = amdgpu_cper_init(adev); init_failed: @@ -4332,10 +4340,8 @@ int amdgpu_device_init(struct amdgpu_device *adev, * for throttling interrupt) = 60 seconds. */ ratelimit_state_init(&adev->throttling_logging_rs, (60 - 1) * HZ, 1); - ratelimit_state_init(&adev->virt.ras_telemetry_rs, 5 * HZ, 1); ratelimit_set_flags(&adev->throttling_logging_rs, RATELIMIT_MSG_ON_RELEASE); - ratelimit_set_flags(&adev->virt.ras_telemetry_rs, RATELIMIT_MSG_ON_RELEASE); /* Registers mapping */ /* TODO: block userspace mapping of io register */ @@ -4367,7 +4373,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, return -ENOMEM; /* detect hw virtualization here */ - amdgpu_detect_virtualization(adev); + amdgpu_virt_init(adev); amdgpu_device_get_pcie_info(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 1819166cb4cf..ce08c428ba4c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -137,6 +137,7 @@ enum AMDGPU_DEBUG_MASK { AMDGPU_DEBUG_USE_VRAM_FW_BUF = BIT(3), AMDGPU_DEBUG_ENABLE_RAS_ACA = BIT(4), AMDGPU_DEBUG_ENABLE_EXP_RESETS = BIT(5), + AMDGPU_DEBUG_DISABLE_GPU_RING_RESET = BIT(6), }; unsigned int amdgpu_vram_limit = UINT_MAX; @@ -2223,6 +2224,11 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev) pr_info("debug: enable experimental reset features\n"); adev->debug_exp_resets = true; } + + if (amdgpu_debug_mask & AMDGPU_DEBUG_DISABLE_GPU_RING_RESET) { + pr_info("debug: ring reset disabled\n"); + adev->debug_disable_gpu_ring_reset = true; + } } static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags) @@ -2557,7 +2563,6 @@ static int amdgpu_pmops_freeze(struct device *dev) int r; r = amdgpu_device_suspend(drm_dev, true); - adev->in_s4 = false; if (r) return r; @@ -2569,8 +2574,13 @@ static int amdgpu_pmops_freeze(struct device *dev) static int amdgpu_pmops_thaw(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + int r; - return amdgpu_device_resume(drm_dev, true); + r = amdgpu_device_resume(drm_dev, true); + adev->in_s4 = false; + + return r; } static int amdgpu_pmops_poweroff(struct device *dev) @@ -2583,6 +2593,9 @@ static int amdgpu_pmops_poweroff(struct device *dev) static int amdgpu_pmops_restore(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + + adev->in_s4 = false; return amdgpu_device_resume(drm_dev, true); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c index 89109eb2ce16..1ae88c459da5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c @@ -31,6 +31,7 @@ #define FRU_EEPROM_MADDR_6 0x60000 #define FRU_EEPROM_MADDR_8 0x80000 +#define FRU_EEPROM_MADDR_INV 0xFFFFF static bool is_fru_eeprom_supported(struct amdgpu_device *adev, u32 *fru_addr) { @@ -104,6 +105,10 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev, u32 *fru_addr) if (fru_addr) *fru_addr = FRU_EEPROM_MADDR_8; return true; + case IP_VERSION(13, 0, 12): + if (fru_addr) + *fru_addr = FRU_EEPROM_MADDR_INV; + return true; default: return false; } @@ -120,6 +125,10 @@ int amdgpu_fru_get_product_info(struct amdgpu_device *adev) if (!is_fru_eeprom_supported(adev, &fru_addr)) return 0; + /* FRU data avaialble, but no direct EEPROM access */ + if (fru_addr == FRU_EEPROM_MADDR_INV) + return 0; + if (!adev->fru_info) { adev->fru_info = kzalloc(sizeof(*adev->fru_info), GFP_KERNEL); if (!adev->fru_info) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index b9bd6654f317..a194bf3347cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -1665,24 +1665,19 @@ static ssize_t amdgpu_gfx_set_enforce_isolation(struct device *dev, } mutex_lock(&adev->enforce_isolation_mutex); - for (i = 0; i < num_partitions; i++) { - if (adev->enforce_isolation[i] && !partition_values[i]) { + if (adev->enforce_isolation[i] && !partition_values[i]) /* Going from enabled to disabled */ amdgpu_vmid_free_reserved(adev, AMDGPU_GFXHUB(i)); - if (adev->enable_mes && adev->gfx.enable_cleaner_shader) - amdgpu_mes_set_enforce_isolation(adev, i, false); - } else if (!adev->enforce_isolation[i] && partition_values[i]) { + else if (!adev->enforce_isolation[i] && partition_values[i]) /* Going from disabled to enabled */ amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(i)); - if (adev->enable_mes && adev->gfx.enable_cleaner_shader) - amdgpu_mes_set_enforce_isolation(adev, i, true); - } adev->enforce_isolation[i] = partition_values[i]; } - mutex_unlock(&adev->enforce_isolation_mutex); + amdgpu_mes_update_enforce_isolation(adev); + return count; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index c6e5c50a3322..4eefa17fa39b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -269,7 +269,7 @@ void amdgpu_gmc_sysvm_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc * @mc: memory controller structure holding memory information * @gart_placement: GART placement policy with respect to VRAM * - * Function will place try to place GART before or after VRAM. + * Function will try to place GART before or after VRAM. * If GART size is bigger than space left then we ajust GART size. * Thus function will never fails. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h index 459a30fe239f..bd7fc123b8f9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h @@ -29,6 +29,7 @@ #include <linux/types.h> #include "amdgpu_irq.h" +#include "amdgpu_xgmi.h" #include "amdgpu_ras.h" /* VA hole for 48bit addresses on Vega10 */ @@ -174,28 +175,6 @@ struct amdgpu_gmc_funcs { bool (*need_reset_on_init)(struct amdgpu_device *adev); }; -struct amdgpu_xgmi_ras { - struct amdgpu_ras_block_object ras_block; -}; - -struct amdgpu_xgmi { - /* from psp */ - u64 node_id; - u64 hive_id; - /* fixed per family */ - u64 node_segment_size; - /* physical node (0-3) */ - unsigned physical_node_id; - /* number of nodes (0-4) */ - unsigned num_physical_nodes; - /* gpu list in the same hive */ - struct list_head head; - bool supported; - struct ras_common_if *ras_if; - bool connected_to_cpu; - struct amdgpu_xgmi_ras *ras; -}; - struct amdgpu_mem_partition_info { union { struct { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h index 7d4395a5d8ac..b0a88f92cd82 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h @@ -78,6 +78,9 @@ struct amdgpu_ih_ring { #define amdgpu_ih_ts_after(t1, t2) \ (((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) > 0LL) +#define amdgpu_ih_ts_after_or_equal(t1, t2) \ + (((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) >= 0LL) + /* provided by the ih block */ struct amdgpu_ih_funcs { /* ring read/write ptr handling, called from interrupt context */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c index 732744488b03..43fc941dfa57 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c @@ -124,7 +124,7 @@ static int isp_early_init(struct amdgpu_ip_block *ip_block) return 0; } -static bool isp_is_idle(void *handle) +static bool isp_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h index b03664c66dd6..4f3b7b5d9c1f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h @@ -50,6 +50,7 @@ struct amdgpu_isp { struct mfd_cell *isp_cell; struct resource *isp_res; struct resource *isp_i2c_res; + struct resource *isp_gpio_res; struct isp_platform_data *isp_pdata; unsigned int harvest_config; const struct firmware *fw; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 1899c601c95c..1d26be3c6d9d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -130,29 +130,47 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) amdgpu_vm_put_task_info(ti); } - dma_fence_set_error(&s_job->s_fence->finished, -ETIME); - /* attempt a per ring reset */ - if (amdgpu_gpu_recovery && - ring->funcs->reset) { + if (unlikely(adev->debug_disable_gpu_ring_reset)) { + dev_err(adev->dev, "Ring reset disabled by debug mask\n"); + } else if (amdgpu_gpu_recovery && ring->funcs->reset) { + bool is_guilty; + dev_err(adev->dev, "Starting %s ring reset\n", s_job->sched->name); /* stop the scheduler, but don't mess with the * bad job yet because if ring reset fails * we'll fall back to full GPU reset. */ drm_sched_wqueue_stop(&ring->sched); + + /* for engine resets, we need to reset the engine, + * but individual queues may be unaffected. + * check here to make sure the accounting is correct. + */ + if (ring->funcs->is_guilty) + is_guilty = ring->funcs->is_guilty(ring); + else + is_guilty = true; + + if (is_guilty) + dma_fence_set_error(&s_job->s_fence->finished, -ETIME); + r = amdgpu_ring_reset(ring, job->vmid); if (!r) { if (amdgpu_ring_sched_ready(ring)) drm_sched_stop(&ring->sched, s_job); - atomic_inc(&ring->adev->gpu_reset_counter); - amdgpu_fence_driver_force_completion(ring); + if (is_guilty) { + atomic_inc(&ring->adev->gpu_reset_counter); + amdgpu_fence_driver_force_completion(ring); + } if (amdgpu_ring_sched_ready(ring)) drm_sched_start(&ring->sched, 0); + dev_err(adev->dev, "Ring %s reset succeeded\n", ring->sched.name); goto exit; } dev_err(adev->dev, "Ring %s reset failure\n", ring->sched.name); } + dma_fence_set_error(&s_job->s_fence->finished, -ETIME); if (amdgpu_device_should_recover_gpu(ring->adev)) { struct amdgpu_reset_context reset_context; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 05c73bf7541c..27bfe9c8af06 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -459,7 +459,7 @@ static int amdgpu_hw_ip_info(struct amdgpu_device *adev, if (adev->vcn.harvest_config & (1 << i)) continue; - for (j = 0; j < adev->vcn.num_enc_rings; j++) + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; j++) if (adev->vcn.inst[i].ring_enc[j].sched.ready) ++num_rings; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index 32b27a1658e7..709c11cbeabd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -1681,7 +1681,8 @@ bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev) } /* Fix me -- node_id is used to identify the correct MES instances in the future */ -int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable) +static int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, + uint32_t node_id, bool enable) { struct mes_misc_op_input op_input = {0}; int r; @@ -1703,6 +1704,23 @@ error: return r; } +int amdgpu_mes_update_enforce_isolation(struct amdgpu_device *adev) +{ + int i, r = 0; + + if (adev->enable_mes && adev->gfx.enable_cleaner_shader) { + mutex_lock(&adev->enforce_isolation_mutex); + for (i = 0; i < (adev->xcp_mgr ? adev->xcp_mgr->num_xcps : 1); i++) { + if (adev->enforce_isolation[i]) + r |= amdgpu_mes_set_enforce_isolation(adev, i, true); + else + r |= amdgpu_mes_set_enforce_isolation(adev, i, false); + } + mutex_unlock(&adev->enforce_isolation_mutex); + } + return r; +} + #if defined(CONFIG_DEBUG_FS) static int amdgpu_debugfs_mes_event_log_show(struct seq_file *m, void *unused) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index 2df2444ee892..68d640aaa2e1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -56,7 +56,7 @@ enum amdgpu_mes_priority_level { struct amdgpu_mes_funcs; -enum admgpu_mes_pipe { +enum amdgpu_mes_pipe { AMDGPU_MES_SCHED_PIPE = 0, AMDGPU_MES_KIQ_PIPE, AMDGPU_MAX_MES_PIPES = 2, @@ -534,6 +534,6 @@ static inline void amdgpu_mes_unlock(struct amdgpu_mes *mes) bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev); -int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable); +int amdgpu_mes_update_enforce_isolation(struct amdgpu_device *adev); #endif /* __AMDGPU_MES_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 96f4b8904e9a..80cd6f5273db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1295,28 +1295,36 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) if (abo->kfd_bo) amdgpu_amdkfd_release_notify(abo); - /* We only remove the fence if the resv has individualized. */ - WARN_ON_ONCE(bo->type == ttm_bo_type_kernel - && bo->base.resv != &bo->base._resv); - if (bo->base.resv == &bo->base._resv) - amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo); + /* + * We lock the private dma_resv object here and since the BO is about to + * be released nobody else should have a pointer to it. + * So when this locking here fails something is wrong with the reference + * counting. + */ + if (WARN_ON_ONCE(!dma_resv_trylock(&bo->base._resv))) + return; + + amdgpu_amdkfd_remove_all_eviction_fences(abo); if (!bo->resource || bo->resource->mem_type != TTM_PL_VRAM || !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) || adev->in_suspend || drm_dev_is_unplugged(adev_to_drm(adev))) - return; + goto out; - if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv))) - return; + r = dma_resv_reserve_fences(&bo->base._resv, 1); + if (r) + goto out; - r = amdgpu_fill_buffer(abo, 0, bo->base.resv, &fence, true); - if (!WARN_ON(r)) { - amdgpu_vram_mgr_set_cleared(bo->resource); - amdgpu_bo_fence(abo, fence, false); - dma_fence_put(fence); - } + r = amdgpu_fill_buffer(abo, 0, &bo->base._resv, &fence, true); + if (WARN_ON(r)) + goto out; + + amdgpu_vram_mgr_set_cleared(bo->resource); + dma_resv_add_fence(&bo->base._resv, fence, DMA_RESV_USAGE_KERNEL); + dma_fence_put(fence); - dma_resv_unlock(bo->base.resv); +out: + dma_resv_unlock(&bo->base._resv); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 3c3312bbfee8..285e3aa2bb2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -2799,20 +2799,100 @@ static int amdgpu_ras_mca2pa(struct amdgpu_device *adev, return -EINVAL; } +static int __amdgpu_ras_restore_bad_pages(struct amdgpu_device *adev, + struct eeprom_table_record *bps, int count) +{ + int j; + struct amdgpu_ras *con = amdgpu_ras_get_context(adev); + struct ras_err_handler_data *data = con->eh_data; + + for (j = 0; j < count; j++) { + if (amdgpu_ras_check_bad_page_unlock(con, + bps[j].retired_page << AMDGPU_GPU_PAGE_SHIFT)) + continue; + + if (!data->space_left && + amdgpu_ras_realloc_eh_data_space(adev, data, 256)) { + return -ENOMEM; + } + + amdgpu_ras_reserve_page(adev, bps[j].retired_page); + + memcpy(&data->bps[data->count], &(bps[j]), + sizeof(struct eeprom_table_record)); + data->count++; + data->space_left--; + } + + return 0; +} + +static int __amdgpu_ras_convert_rec_array_from_rom(struct amdgpu_device *adev, + struct eeprom_table_record *bps, struct ras_err_data *err_data, + enum amdgpu_memory_partition nps) +{ + int i = 0; + enum amdgpu_memory_partition save_nps; + + save_nps = (bps[0].retired_page >> UMC_NPS_SHIFT) & UMC_NPS_MASK; + + for (i = 0; i < adev->umc.retire_unit; i++) + bps[i].retired_page &= ~(UMC_NPS_MASK << UMC_NPS_SHIFT); + + if (save_nps) { + if (save_nps == nps) { + if (amdgpu_umc_pages_in_a_row(adev, err_data, + bps[0].retired_page << AMDGPU_GPU_PAGE_SHIFT)) + return -EINVAL; + } else { + if (amdgpu_ras_mca2pa_by_idx(adev, &bps[0], err_data)) + return -EINVAL; + } + } else { + if (amdgpu_ras_mca2pa(adev, &bps[0], err_data)) { + if (nps == AMDGPU_NPS1_PARTITION_MODE) + memcpy(err_data->err_addr, bps, + sizeof(struct eeprom_table_record) * adev->umc.retire_unit); + else + return -EOPNOTSUPP; + } + } + + return __amdgpu_ras_restore_bad_pages(adev, err_data->err_addr, adev->umc.retire_unit); +} + +static int __amdgpu_ras_convert_rec_from_rom(struct amdgpu_device *adev, + struct eeprom_table_record *bps, struct ras_err_data *err_data, + enum amdgpu_memory_partition nps) +{ + enum amdgpu_memory_partition save_nps; + + save_nps = (bps->retired_page >> UMC_NPS_SHIFT) & UMC_NPS_MASK; + bps->retired_page &= ~(UMC_NPS_MASK << UMC_NPS_SHIFT); + + if (save_nps == nps) { + if (amdgpu_umc_pages_in_a_row(adev, err_data, + bps->retired_page << AMDGPU_GPU_PAGE_SHIFT)) + return -EINVAL; + } else { + if (amdgpu_ras_mca2pa_by_idx(adev, bps, err_data)) + return -EINVAL; + } + return __amdgpu_ras_restore_bad_pages(adev, err_data->err_addr, + adev->umc.retire_unit); +} + /* it deal with vram only. */ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, struct eeprom_table_record *bps, int pages, bool from_rom) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); - struct ras_err_handler_data *data; struct ras_err_data err_data; - struct eeprom_table_record *err_rec; struct amdgpu_ras_eeprom_control *control = &adev->psp.ras_context.ras->eeprom_control; enum amdgpu_memory_partition nps = AMDGPU_NPS1_PARTITION_MODE; int ret = 0; - uint32_t i, j, loop_cnt = 1; - bool find_pages_per_pa = false; + uint32_t i; if (!con || !con->eh_data || !bps || pages <= 0) return 0; @@ -2823,114 +2903,46 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, sizeof(struct eeprom_table_record), GFP_KERNEL); if (!err_data.err_addr) { dev_warn(adev->dev, "Failed to alloc UMC error address record in mca2pa conversion!\n"); - ret = -ENOMEM; - goto out; + return -ENOMEM; } - err_rec = err_data.err_addr; - loop_cnt = adev->umc.retire_unit; if (adev->gmc.gmc_funcs->query_mem_partition_mode) nps = adev->gmc.gmc_funcs->query_mem_partition_mode(adev); } mutex_lock(&con->recovery_lock); - data = con->eh_data; - if (!data) { - /* Returning 0 as the absence of eh_data is acceptable */ - goto free; - } - - for (i = 0; i < pages; i++) { - if (from_rom && - control->rec_type == AMDGPU_RAS_EEPROM_REC_MCA) { - if (!find_pages_per_pa) { - if (amdgpu_ras_mca2pa_by_idx(adev, &bps[i], &err_data)) { - if (!i && nps == AMDGPU_NPS1_PARTITION_MODE) { - /* may use old RAS TA, use PA to find pages in - * one row - */ - if (amdgpu_umc_pages_in_a_row(adev, &err_data, - bps[i].retired_page << - AMDGPU_GPU_PAGE_SHIFT)) { - ret = -EINVAL; - goto free; - } else { - find_pages_per_pa = true; - } - } else { - /* unsupported cases */ - ret = -EOPNOTSUPP; - goto free; - } - } - } else { - if (amdgpu_umc_pages_in_a_row(adev, &err_data, - bps[i].retired_page << AMDGPU_GPU_PAGE_SHIFT)) { - ret = -EINVAL; - goto free; - } - } - } else { - if (from_rom && !find_pages_per_pa) { - if (bps[i].retired_page & UMC_CHANNEL_IDX_V2) { - /* bad page in any NPS mode in eeprom */ - if (amdgpu_ras_mca2pa_by_idx(adev, &bps[i], &err_data)) { - ret = -EINVAL; + + if (from_rom) { + for (i = 0; i < pages; i++) { + if (control->ras_num_recs - i >= adev->umc.retire_unit) { + if ((bps[i].address == bps[i + 1].address) && + (bps[i].mem_channel == bps[i + 1].mem_channel)) { + //deal with retire_unit records a time + ret = __amdgpu_ras_convert_rec_array_from_rom(adev, + &bps[i], &err_data, nps); + if (ret) goto free; - } + i += (adev->umc.retire_unit - 1); } else { - /* legacy bad page in eeprom, generated only in - * NPS1 mode - */ - if (amdgpu_ras_mca2pa(adev, &bps[i], &err_data)) { - /* old RAS TA or ASICs which don't support to - * convert addrss via mca address - */ - if (!i && nps == AMDGPU_NPS1_PARTITION_MODE) { - find_pages_per_pa = true; - err_rec = &bps[i]; - loop_cnt = 1; - } else { - /* non-nps1 mode, old RAS TA - * can't support it - */ - ret = -EOPNOTSUPP; - goto free; - } - } + break; } - - if (!find_pages_per_pa) - i += (adev->umc.retire_unit - 1); } else { - err_rec = &bps[i]; + break; } } - - for (j = 0; j < loop_cnt; j++) { - if (amdgpu_ras_check_bad_page_unlock(con, - err_rec[j].retired_page << AMDGPU_GPU_PAGE_SHIFT)) - continue; - - if (!data->space_left && - amdgpu_ras_realloc_eh_data_space(adev, data, 256)) { - ret = -ENOMEM; + for (; i < pages; i++) { + ret = __amdgpu_ras_convert_rec_from_rom(adev, + &bps[i], &err_data, nps); + if (ret) goto free; - } - - amdgpu_ras_reserve_page(adev, err_rec[j].retired_page); - - memcpy(&data->bps[data->count], &(err_rec[j]), - sizeof(struct eeprom_table_record)); - data->count++; - data->space_left--; } + } else { + ret = __amdgpu_ras_restore_bad_pages(adev, bps, pages); } free: if (from_rom) kfree(err_data.err_addr); -out: mutex_unlock(&con->recovery_lock); return ret; @@ -2969,24 +2981,14 @@ int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev, /* only new entries are saved */ if (save_count > 0) { - if (control->rec_type == AMDGPU_RAS_EEPROM_REC_PA) { + for (i = 0; i < unit_num; i++) { if (amdgpu_ras_eeprom_append(control, - &data->bps[control->ras_num_recs], - save_count)) { + &data->bps[bad_page_num + i * adev->umc.retire_unit], + 1)) { dev_err(adev->dev, "Failed to save EEPROM table data!"); return -EIO; } - } else { - for (i = 0; i < unit_num; i++) { - if (amdgpu_ras_eeprom_append(control, - &data->bps[bad_page_num + i * adev->umc.retire_unit], - 1)) { - dev_err(adev->dev, "Failed to save EEPROM table data!"); - return -EIO; - } - } } - dev_info(adev->dev, "Saved %d pages to EEPROM table.\n", save_count); } @@ -3002,7 +3004,7 @@ static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev) struct amdgpu_ras_eeprom_control *control = &adev->psp.ras_context.ras->eeprom_control; struct eeprom_table_record *bps; - int ret; + int ret, i = 0; /* no bad page record, skip eeprom access */ if (control->ras_num_recs == 0 || amdgpu_bad_page_threshold == 0) @@ -3016,13 +3018,23 @@ static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev) if (ret) { dev_err(adev->dev, "Failed to load EEPROM table records!"); } else { - if (control->ras_num_recs > 1 && - adev->umc.ras && adev->umc.ras->convert_ras_err_addr) { - if ((bps[0].address == bps[1].address) && - (bps[0].mem_channel == bps[1].mem_channel)) - control->rec_type = AMDGPU_RAS_EEPROM_REC_PA; - else - control->rec_type = AMDGPU_RAS_EEPROM_REC_MCA; + if (adev->umc.ras && adev->umc.ras->convert_ras_err_addr) { + for (i = 0; i < control->ras_num_recs; i++) { + if ((control->ras_num_recs - i) >= adev->umc.retire_unit) { + if ((bps[i].address == bps[i + 1].address) && + (bps[i].mem_channel == bps[i + 1].mem_channel)) { + control->ras_num_pa_recs += adev->umc.retire_unit; + i += (adev->umc.retire_unit - 1); + } else { + control->ras_num_mca_recs += + (control->ras_num_recs - i); + break; + } + } else { + control->ras_num_mca_recs += (control->ras_num_recs - i); + break; + } + } } ret = amdgpu_ras_eeprom_check(control); @@ -3428,12 +3440,7 @@ int amdgpu_ras_init_badpage_info(struct amdgpu_device *adev) return ret; if (!adev->umc.ras || !adev->umc.ras->convert_ras_err_addr) - control->rec_type = AMDGPU_RAS_EEPROM_REC_PA; - - /* default status is MCA storage */ - if (control->ras_num_recs <= 1 && - adev->umc.ras && adev->umc.ras->convert_ras_err_addr) - control->rec_type = AMDGPU_RAS_EEPROM_REC_MCA; + control->ras_num_pa_recs = control->ras_num_recs; if (control->ras_num_recs) { ret = amdgpu_ras_load_bad_pages(adev); @@ -5131,9 +5138,9 @@ static void amdgpu_ras_boot_time_error_reporting(struct amdgpu_device *adev, "socket: %d, aid: %d, fw_status: 0x%x, data abort exception\n", socket_id, aid_id, fw_status); - if (AMDGPU_RAS_GPU_ERR_UNKNOWN(boot_error)) + if (AMDGPU_RAS_GPU_ERR_GENERIC(boot_error)) dev_info(adev->dev, - "socket: %d, aid: %d, fw_status: 0x%x, unknown boot time errors\n", + "socket: %d, aid: %d, fw_status: 0x%x, Boot Controller Generic Error\n", socket_id, aid_id, fw_status); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h index cc4586581dba..764e9fa0a914 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h @@ -47,7 +47,7 @@ struct amdgpu_iv_entry; #define AMDGPU_RAS_GPU_ERR_AID_ID(x) AMDGPU_GET_REG_FIELD(x, 12, 11) #define AMDGPU_RAS_GPU_ERR_HBM_ID(x) AMDGPU_GET_REG_FIELD(x, 14, 13) #define AMDGPU_RAS_GPU_ERR_DATA_ABORT(x) AMDGPU_GET_REG_FIELD(x, 29, 29) -#define AMDGPU_RAS_GPU_ERR_UNKNOWN(x) AMDGPU_GET_REG_FIELD(x, 30, 30) +#define AMDGPU_RAS_GPU_ERR_GENERIC(x) AMDGPU_GET_REG_FIELD(x, 30, 30) #define AMDGPU_RAS_BOOT_STATUS_POLLING_LIMIT 100 #define AMDGPU_RAS_BOOT_STEADY_STATUS 0xBA diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index 83b54efcaa87..09a6f8bc1a5a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -727,11 +727,9 @@ amdgpu_ras_eeprom_append_table(struct amdgpu_ras_eeprom_control *control, - control->ras_fri) % control->ras_max_record_count; - if (control->rec_type == AMDGPU_RAS_EEPROM_REC_PA) - control->ras_num_bad_pages = control->ras_num_recs; - else - control->ras_num_bad_pages = - control->ras_num_recs * adev->umc.retire_unit; + control->ras_num_mca_recs += num; + control->ras_num_bad_pages += num * adev->umc.retire_unit; + Out: kfree(buf); return res; @@ -749,7 +747,7 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control) /* Modify the header if it exceeds. */ if (amdgpu_bad_page_threshold != 0 && - control->ras_num_bad_pages >= ras->bad_page_cnt_threshold) { + control->ras_num_bad_pages > ras->bad_page_cnt_threshold) { dev_warn(adev->dev, "Saved bad pages %d reaches threshold value %d\n", control->ras_num_bad_pages, ras->bad_page_cnt_threshold); @@ -808,7 +806,7 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control) */ if (amdgpu_bad_page_threshold != 0 && control->tbl_hdr.version == RAS_TABLE_VER_V2_1 && - control->ras_num_bad_pages < ras->bad_page_cnt_threshold) + control->ras_num_bad_pages <= ras->bad_page_cnt_threshold) control->tbl_rai.health_percent = ((ras->bad_page_cnt_threshold - control->ras_num_bad_pages) * 100) / ras->bad_page_cnt_threshold; @@ -852,6 +850,7 @@ int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control, { struct amdgpu_device *adev = to_amdgpu_device(control); int res, i; + uint64_t nps = AMDGPU_NPS1_PARTITION_MODE; if (!__is_ras_eeprom_supported(adev)) return 0; @@ -865,9 +864,12 @@ int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control, return -EINVAL; } + if (adev->gmc.gmc_funcs->query_mem_partition_mode) + nps = adev->gmc.gmc_funcs->query_mem_partition_mode(adev); + /* set the new channel index flag */ for (i = 0; i < num; i++) - record[i].retired_page |= UMC_CHANNEL_IDX_V2; + record[i].retired_page |= (nps << UMC_NPS_SHIFT); mutex_lock(&control->ras_tbl_mutex); @@ -881,7 +883,7 @@ int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control, /* clear channel index flag, the flag is only saved on eeprom */ for (i = 0; i < num; i++) - record[i].retired_page &= ~UMC_CHANNEL_IDX_V2; + record[i].retired_page &= ~(nps << UMC_NPS_SHIFT); return res; } @@ -1392,6 +1394,8 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control) } control->ras_fri = RAS_OFFSET_TO_INDEX(control, hdr->first_rec_offset); + control->ras_num_mca_recs = 0; + control->ras_num_pa_recs = 0; return 0; } @@ -1412,11 +1416,8 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control) if (!__get_eeprom_i2c_addr(adev, control)) return -EINVAL; - if (control->rec_type == AMDGPU_RAS_EEPROM_REC_PA) - control->ras_num_bad_pages = control->ras_num_recs; - else - control->ras_num_bad_pages = - control->ras_num_recs * adev->umc.retire_unit; + control->ras_num_bad_pages = control->ras_num_pa_recs + + control->ras_num_mca_recs * adev->umc.retire_unit; if (hdr->header == RAS_TABLE_HDR_VAL) { DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records", @@ -1455,7 +1456,7 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control) res); return -EINVAL; } - if (ras->bad_page_cnt_threshold > control->ras_num_bad_pages) { + if (ras->bad_page_cnt_threshold >= control->ras_num_bad_pages) { /* This means that, the threshold was increased since * the last time the system was booted, and now, * ras->bad_page_cnt_threshold - control->num_recs > 0, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h index 81d55cb7b397..13f7eda9a696 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h @@ -43,19 +43,6 @@ enum amdgpu_ras_eeprom_err_type { AMDGPU_RAS_EEPROM_ERR_COUNT, }; -/* - * one UMC MCA address could map to multiply physical address (PA), - * such as 1:16, we use eeprom_table_record.address to store MCA - * address and use eeprom_table_record.retired_page to save PA. - * - * AMDGPU_RAS_EEPROM_REC_PA: one record store one PA - * AMDGPU_RAS_EEPROM_REC_MCA: one record store one MCA address - */ -enum amdgpu_ras_eeprom_rec_type { - AMDGPU_RAS_EEPROM_REC_PA, - AMDGPU_RAS_EEPROM_REC_MCA, -}; - struct amdgpu_ras_eeprom_table_header { uint32_t header; uint32_t version; @@ -100,6 +87,12 @@ struct amdgpu_ras_eeprom_control { */ u32 ras_num_bad_pages; + /* Number of records store mca address */ + u32 ras_num_mca_recs; + + /* Number of records store physical address */ + u32 ras_num_pa_recs; + /* First record index to read, 0-based. * Range is [0, num_recs-1]. This is * an absolute index, starting right after @@ -120,7 +113,6 @@ struct amdgpu_ras_eeprom_control { /* Record channel info which occurred bad pages */ u32 bad_channel_bitmap; - enum amdgpu_ras_eeprom_rec_type rec_type; }; /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index f53887e2f528..d55c8b7fdb59 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -349,6 +349,8 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, ring->buf_mask = (ring->ring_size / 4) - 1; ring->ptr_mask = ring->funcs->support_64bit_ptrs ? 0xffffffffffffffff : ring->buf_mask; + /* Initialize cached_rptr to 0 */ + ring->cached_rptr = 0; /* Allocate ring buffer */ if (ring->is_mes_queue) { @@ -576,12 +578,32 @@ out: return result; } +static ssize_t amdgpu_debugfs_virt_ring_read(struct file *f, char __user *buf, + size_t size, loff_t *pos) +{ + struct amdgpu_ring *ring = file_inode(f)->i_private; + + if (*pos & 3 || size & 3) + return -EINVAL; + + if (ring->funcs->type == AMDGPU_RING_TYPE_CPER) + amdgpu_virt_req_ras_cper_dump(ring->adev, false); + + return amdgpu_debugfs_ring_read(f, buf, size, pos); +} + static const struct file_operations amdgpu_debugfs_ring_fops = { .owner = THIS_MODULE, .read = amdgpu_debugfs_ring_read, .llseek = default_llseek }; +static const struct file_operations amdgpu_debugfs_virt_ring_fops = { + .owner = THIS_MODULE, + .read = amdgpu_debugfs_virt_ring_read, + .llseek = default_llseek +}; + static ssize_t amdgpu_debugfs_mqd_read(struct file *f, char __user *buf, size_t size, loff_t *pos) { @@ -669,9 +691,14 @@ void amdgpu_debugfs_ring_init(struct amdgpu_device *adev, char name[32]; sprintf(name, "amdgpu_ring_%s", ring->name); - debugfs_create_file_size(name, S_IFREG | 0444, root, ring, - &amdgpu_debugfs_ring_fops, - ring->ring_size + 12); + if (amdgpu_sriov_vf(adev)) + debugfs_create_file_size(name, S_IFREG | 0444, root, ring, + &amdgpu_debugfs_virt_ring_fops, + ring->ring_size + 12); + else + debugfs_create_file_size(name, S_IFREG | 0444, root, ring, + &amdgpu_debugfs_ring_fops, + ring->ring_size + 12); if (ring->mqd_obj) { sprintf(name, "amdgpu_mqd_%s", ring->name); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 7372e4aed6b0..b4fd1e17205e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -37,7 +37,7 @@ struct amdgpu_job; struct amdgpu_vm; /* max number of rings */ -#define AMDGPU_MAX_RINGS 132 +#define AMDGPU_MAX_RINGS 133 #define AMDGPU_MAX_HWIP_RINGS 64 #define AMDGPU_MAX_GFX_RINGS 2 #define AMDGPU_MAX_SW_GFX_RINGS 2 @@ -238,6 +238,7 @@ struct amdgpu_ring_funcs { void (*patch_de)(struct amdgpu_ring *ring, unsigned offset); int (*reset)(struct amdgpu_ring *ring, unsigned int vmid); void (*emit_cleaner_shader)(struct amdgpu_ring *ring); + bool (*is_guilty)(struct amdgpu_ring *ring); }; struct amdgpu_ring { @@ -307,6 +308,8 @@ struct amdgpu_ring { bool is_sw_ring; unsigned int entry_index; + /* store the cached rptr to restore after reset */ + uint64_t cached_rptr; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c index 174badca27e7..3a4cef896018 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c @@ -25,6 +25,7 @@ #include "amdgpu.h" #include "amdgpu_sdma.h" #include "amdgpu_ras.h" +#include "amdgpu_reset.h" #define AMDGPU_CSA_SDMA_SIZE 64 /* SDMA CSA reside in the 3rd page of CSA */ @@ -355,23 +356,44 @@ int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev) static int amdgpu_debugfs_sdma_sched_mask_set(void *data, u64 val) { struct amdgpu_device *adev = (struct amdgpu_device *)data; - u32 i; + u64 i, num_ring; u64 mask = 0; - struct amdgpu_ring *ring; + struct amdgpu_ring *ring, *page = NULL; if (!adev) return -ENODEV; - mask = BIT_ULL(adev->sdma.num_instances) - 1; + /* Determine the number of rings per SDMA instance + * (1 for sdma gfx ring, 2 if page queue exists) + */ + if (adev->sdma.has_page_queue) + num_ring = 2; + else + num_ring = 1; + + /* Calculate the maximum possible mask value + * based on the number of SDMA instances and rings + */ + mask = BIT_ULL(adev->sdma.num_instances * num_ring) - 1; + if ((val & mask) == 0) return -EINVAL; for (i = 0; i < adev->sdma.num_instances; ++i) { ring = &adev->sdma.instance[i].ring; - if (val & BIT_ULL(i)) + if (adev->sdma.has_page_queue) + page = &adev->sdma.instance[i].page; + if (val & BIT_ULL(i * num_ring)) ring->sched.ready = true; else ring->sched.ready = false; + + if (page) { + if (val & BIT_ULL(i * num_ring + 1)) + page->sched.ready = true; + else + page->sched.ready = false; + } } /* publish sched.ready flag update effective immediately across smp */ smp_rmb(); @@ -381,16 +403,37 @@ static int amdgpu_debugfs_sdma_sched_mask_set(void *data, u64 val) static int amdgpu_debugfs_sdma_sched_mask_get(void *data, u64 *val) { struct amdgpu_device *adev = (struct amdgpu_device *)data; - u32 i; + u64 i, num_ring; u64 mask = 0; - struct amdgpu_ring *ring; + struct amdgpu_ring *ring, *page = NULL; if (!adev) return -ENODEV; + + /* Determine the number of rings per SDMA instance + * (1 for sdma gfx ring, 2 if page queue exists) + */ + if (adev->sdma.has_page_queue) + num_ring = 2; + else + num_ring = 1; + for (i = 0; i < adev->sdma.num_instances; ++i) { ring = &adev->sdma.instance[i].ring; + if (adev->sdma.has_page_queue) + page = &adev->sdma.instance[i].page; + if (ring->sched.ready) - mask |= 1 << i; + mask |= BIT_ULL(i * num_ring); + else + mask &= ~BIT_ULL(i * num_ring); + + if (page) { + if (page->sched.ready) + mask |= BIT_ULL(i * num_ring + 1); + else + mask &= ~BIT_ULL(i * num_ring + 1); + } } *val = mask; @@ -460,3 +503,123 @@ void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev) device_remove_file(adev->dev, &dev_attr_sdma_reset_mask); } } + +/** + * amdgpu_sdma_register_on_reset_callbacks - Register SDMA reset callbacks + * @funcs: Pointer to the callback structure containing pre_reset and post_reset functions + * + * This function allows KFD and AMDGPU to register their own callbacks for handling + * pre-reset and post-reset operations for engine reset. These are needed because engine + * reset will stop all queues on that engine. + */ +void amdgpu_sdma_register_on_reset_callbacks(struct amdgpu_device *adev, struct sdma_on_reset_funcs *funcs) +{ + if (!funcs) + return; + + /* Ensure the reset_callback_list is initialized */ + if (!adev->sdma.reset_callback_list.next) { + INIT_LIST_HEAD(&adev->sdma.reset_callback_list); + } + /* Initialize the list node in the callback structure */ + INIT_LIST_HEAD(&funcs->list); + + /* Add the callback structure to the global list */ + list_add_tail(&funcs->list, &adev->sdma.reset_callback_list); +} + +/** + * amdgpu_sdma_reset_engine - Reset a specific SDMA engine + * @adev: Pointer to the AMDGPU device + * @instance_id: ID of the SDMA engine instance to reset + * @suspend_user_queues: check if suspend user queue. + * + * This function performs the following steps: + * 1. Calls all registered pre_reset callbacks to allow KFD and AMDGPU to save their state. + * 2. Resets the specified SDMA engine instance. + * 3. Calls all registered post_reset callbacks to allow KFD and AMDGPU to restore their state. + * + * Returns: 0 on success, or a negative error code on failure. + */ +int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id, bool suspend_user_queues) +{ + struct sdma_on_reset_funcs *funcs; + int ret = 0; + struct amdgpu_sdma_instance *sdma_instance = &adev->sdma.instance[instance_id];; + struct amdgpu_ring *gfx_ring = &sdma_instance->ring; + struct amdgpu_ring *page_ring = &sdma_instance->page; + bool gfx_sched_stopped = false, page_sched_stopped = false; + + /* Suspend KFD if suspend_user_queues is true. + * prevent the destruction of in-flight healthy user queue packets and + * avoid race conditions between KFD and KGD during the reset process. + */ + if (suspend_user_queues) + amdgpu_amdkfd_suspend(adev, false); + + /* Stop the scheduler's work queue for the GFX and page rings if they are running. + * This ensures that no new tasks are submitted to the queues while + * the reset is in progress. + */ + if (!amdgpu_ring_sched_ready(gfx_ring)) { + drm_sched_wqueue_stop(&gfx_ring->sched); + gfx_sched_stopped = true; + } + + if (adev->sdma.has_page_queue && !amdgpu_ring_sched_ready(page_ring)) { + drm_sched_wqueue_stop(&page_ring->sched); + page_sched_stopped = true; + } + + /* Invoke all registered pre_reset callbacks */ + list_for_each_entry(funcs, &adev->sdma.reset_callback_list, list) { + if (funcs->pre_reset) { + ret = funcs->pre_reset(adev, instance_id); + if (ret) { + dev_err(adev->dev, + "beforeReset callback failed for instance %u: %d\n", + instance_id, ret); + goto exit; + } + } + } + + /* Perform the SDMA reset for the specified instance */ + ret = amdgpu_dpm_reset_sdma(adev, 1 << instance_id); + if (ret) { + dev_err(adev->dev, "Failed to reset SDMA instance %u\n", instance_id); + goto exit; + } + + /* Invoke all registered post_reset callbacks */ + list_for_each_entry(funcs, &adev->sdma.reset_callback_list, list) { + if (funcs->post_reset) { + ret = funcs->post_reset(adev, instance_id); + if (ret) { + dev_err(adev->dev, + "afterReset callback failed for instance %u: %d\n", + instance_id, ret); + goto exit; + } + } + } + +exit: + /* Restart the scheduler's work queue for the GFX and page rings + * if they were stopped by this function. This allows new tasks + * to be submitted to the queues after the reset is complete. + */ + if (ret) { + if (gfx_sched_stopped && amdgpu_ring_sched_ready(gfx_ring)) { + drm_sched_wqueue_start(&gfx_ring->sched); + } + if (page_sched_stopped && amdgpu_ring_sched_ready(page_ring)) { + drm_sched_wqueue_start(&page_ring->sched); + } + } + + if (suspend_user_queues) + amdgpu_amdkfd_resume(adev, false); + + return ret; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h index 5f60736051d1..965169320065 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h @@ -98,6 +98,13 @@ struct amdgpu_sdma_ras { struct amdgpu_ras_block_object ras_block; }; +struct sdma_on_reset_funcs { + int (*pre_reset)(struct amdgpu_device *adev, uint32_t instance_id); + int (*post_reset)(struct amdgpu_device *adev, uint32_t instance_id); + /* Linked list node to store this structure in a list; */ + struct list_head list; +}; + struct amdgpu_sdma { struct amdgpu_sdma_instance instance[AMDGPU_MAX_SDMA_INSTANCES]; struct amdgpu_irq_src trap_irq; @@ -118,6 +125,10 @@ struct amdgpu_sdma { struct amdgpu_sdma_ras *ras; uint32_t *ip_dump; uint32_t supported_reset; + struct list_head reset_callback_list; + /* track guilty state of GFX and PAGE queues */ + bool gfx_guilty; + bool page_guilty; }; /* @@ -157,6 +168,9 @@ struct amdgpu_buffer_funcs { uint32_t byte_count); }; +void amdgpu_sdma_register_on_reset_callbacks(struct amdgpu_device *adev, struct sdma_on_reset_funcs *funcs); +int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id, bool suspend_user_queues); + #define amdgpu_emit_copy_buffer(adev, ib, s, d, b, t) (adev)->mman.buffer_funcs->emit_copy_buffer((ib), (s), (d), (b), (t)) #define amdgpu_emit_fill_buffer(adev, ib, s, d, b) (adev)->mman.buffer_funcs->emit_fill_buffer((ib), (s), (d), (b)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index bcb4bcc4ab75..53b71e9d8076 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -2295,7 +2295,7 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo, struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring; struct amdgpu_res_cursor cursor; u64 addr; - int r; + int r = 0; if (!adev->mman.buffer_funcs_enabled) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h index a4a7e61817aa..857693bcd8d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h @@ -71,6 +71,13 @@ */ #define UMC_CHANNEL_IDX_V2 BIT_ULL(47) +/* + * save nps value to eeprom_table_record.retired_page[47:40], + * the channel index flag above will be retired. + */ +#define UMC_NPS_SHIFT 40 +#define UMC_NPS_MASK 0xffULL + typedef int (*umc_func)(struct amdgpu_device *adev, uint32_t node_inst, uint32_t umc_inst, uint32_t ch_inst, void *data); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 83faf6e6788a..8d8b39e6d197 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -93,47 +93,53 @@ MODULE_FIRMWARE(FIRMWARE_VCN5_0_1); static void amdgpu_vcn_idle_work_handler(struct work_struct *work); -int amdgpu_vcn_early_init(struct amdgpu_device *adev) +int amdgpu_vcn_early_init(struct amdgpu_device *adev, int i) { char ucode_prefix[25]; - int r, i; + int r; + adev->vcn.inst[i].adev = adev; + adev->vcn.inst[i].inst = i; amdgpu_ucode_ip_version_decode(adev, UVD_HWIP, ucode_prefix, sizeof(ucode_prefix)); - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - if (i == 1 && amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(4, 0, 6)) - r = amdgpu_ucode_request(adev, &adev->vcn.inst[i].fw, - AMDGPU_UCODE_REQUIRED, - "amdgpu/%s_%d.bin", ucode_prefix, i); - else - r = amdgpu_ucode_request(adev, &adev->vcn.inst[i].fw, + + if (i != 0 && adev->vcn.per_inst_fw) { + r = amdgpu_ucode_request(adev, &adev->vcn.inst[i].fw, + AMDGPU_UCODE_REQUIRED, + "amdgpu/%s_%d.bin", ucode_prefix, i); + if (r) + amdgpu_ucode_release(&adev->vcn.inst[i].fw); + } else { + if (!adev->vcn.inst[0].fw) { + r = amdgpu_ucode_request(adev, &adev->vcn.inst[0].fw, AMDGPU_UCODE_REQUIRED, "amdgpu/%s.bin", ucode_prefix); - if (r) { - amdgpu_ucode_release(&adev->vcn.inst[i].fw); - return r; + if (r) + amdgpu_ucode_release(&adev->vcn.inst[0].fw); + } else { + r = 0; } + adev->vcn.inst[i].fw = adev->vcn.inst[0].fw; } + return r; } -int amdgpu_vcn_sw_init(struct amdgpu_device *adev) +int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int i) { unsigned long bo_size; const struct common_firmware_header *hdr; unsigned char fw_check; unsigned int fw_shared_size, log_offset; - int i, r; - - INIT_DELAYED_WORK(&adev->vcn.idle_work, amdgpu_vcn_idle_work_handler); - mutex_init(&adev->vcn.vcn_pg_lock); - mutex_init(&adev->vcn.vcn1_jpeg1_workaround); - atomic_set(&adev->vcn.total_submission_cnt, 0); - for (i = 0; i < adev->vcn.num_vcn_inst; i++) - atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0); + int r; + mutex_init(&adev->vcn.inst[i].vcn1_jpeg1_workaround); + mutex_init(&adev->vcn.inst[i].vcn_pg_lock); + atomic_set(&adev->vcn.inst[i].total_submission_cnt, 0); + INIT_DELAYED_WORK(&adev->vcn.inst[i].idle_work, amdgpu_vcn_idle_work_handler); + atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0); if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; + adev->vcn.inst[i].indirect_sram = true; /* * Some Steam Deck's BIOS versions are incompatible with the @@ -146,18 +152,19 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) const char *bios_ver = dmi_get_system_info(DMI_BIOS_VERSION); if (bios_ver && (!strncmp("F7A0113", bios_ver, 7) || - !strncmp("F7A0114", bios_ver, 7))) { - adev->vcn.indirect_sram = false; + !strncmp("F7A0114", bios_ver, 7))) { + adev->vcn.inst[i].indirect_sram = false; dev_info(adev->dev, - "Steam Deck quirk: indirect SRAM disabled on BIOS %s\n", bios_ver); + "Steam Deck quirk: indirect SRAM disabled on BIOS %s\n", bios_ver); } } /* from vcn4 and above, only unified queue is used */ - adev->vcn.using_unified_queue = + adev->vcn.inst[i].using_unified_queue = amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0); - hdr = (const struct common_firmware_header *)adev->vcn.inst[0].fw->data; + hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data; + adev->vcn.inst[i].fw_version = le32_to_cpu(hdr->ucode_version); adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version); /* Bit 20-23, it is encode major and non-zero for new naming convention. @@ -175,16 +182,17 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) enc_major = fw_check; dec_ver = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xf; vep = (le32_to_cpu(hdr->ucode_version) >> 28) & 0xf; - DRM_INFO("Found VCN firmware Version ENC: %u.%u DEC: %u VEP: %u Revision: %u\n", - enc_major, enc_minor, dec_ver, vep, fw_rev); + dev_info(adev->dev, + "Found VCN firmware Version ENC: %u.%u DEC: %u VEP: %u Revision: %u\n", + enc_major, enc_minor, dec_ver, vep, fw_rev); } else { unsigned int version_major, version_minor, family_id; family_id = le32_to_cpu(hdr->ucode_version) & 0xff; version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff; version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff; - DRM_INFO("Found VCN firmware Version: %u.%u Family ID: %u\n", - version_major, version_minor, family_id); + dev_info(adev->dev, "Found VCN firmware Version: %u.%u Family ID: %u\n", + version_major, version_minor, family_id); } bo_size = AMDGPU_VCN_STACK_SIZE + AMDGPU_VCN_CONTEXT_SIZE; @@ -207,80 +215,77 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) if (amdgpu_vcnfw_log) bo_size += AMDGPU_VCNFW_LOG_SIZE; - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - if (adev->vcn.harvest_config & (1 << i)) - continue; + r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, + &adev->vcn.inst[i].vcpu_bo, + &adev->vcn.inst[i].gpu_addr, + &adev->vcn.inst[i].cpu_addr); + if (r) { + dev_err(adev->dev, "(%d) failed to allocate vcn bo\n", r); + return r; + } + + adev->vcn.inst[i].fw_shared.cpu_addr = adev->vcn.inst[i].cpu_addr + + bo_size - fw_shared_size; + adev->vcn.inst[i].fw_shared.gpu_addr = adev->vcn.inst[i].gpu_addr + + bo_size - fw_shared_size; + + adev->vcn.inst[i].fw_shared.mem_size = fw_shared_size; + + if (amdgpu_vcnfw_log) { + adev->vcn.inst[i].fw_shared.cpu_addr -= AMDGPU_VCNFW_LOG_SIZE; + adev->vcn.inst[i].fw_shared.gpu_addr -= AMDGPU_VCNFW_LOG_SIZE; + adev->vcn.inst[i].fw_shared.log_offset = log_offset; + } - r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE, + if (adev->vcn.inst[i].indirect_sram) { + r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT, - &adev->vcn.inst[i].vcpu_bo, - &adev->vcn.inst[i].gpu_addr, - &adev->vcn.inst[i].cpu_addr); + &adev->vcn.inst[i].dpg_sram_bo, + &adev->vcn.inst[i].dpg_sram_gpu_addr, + &adev->vcn.inst[i].dpg_sram_cpu_addr); if (r) { - dev_err(adev->dev, "(%d) failed to allocate vcn bo\n", r); + dev_err(adev->dev, "VCN %d (%d) failed to allocate DPG bo\n", i, r); return r; } - - adev->vcn.inst[i].fw_shared.cpu_addr = adev->vcn.inst[i].cpu_addr + - bo_size - fw_shared_size; - adev->vcn.inst[i].fw_shared.gpu_addr = adev->vcn.inst[i].gpu_addr + - bo_size - fw_shared_size; - - adev->vcn.inst[i].fw_shared.mem_size = fw_shared_size; - - if (amdgpu_vcnfw_log) { - adev->vcn.inst[i].fw_shared.cpu_addr -= AMDGPU_VCNFW_LOG_SIZE; - adev->vcn.inst[i].fw_shared.gpu_addr -= AMDGPU_VCNFW_LOG_SIZE; - adev->vcn.inst[i].fw_shared.log_offset = log_offset; - } - - if (adev->vcn.indirect_sram) { - r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM | - AMDGPU_GEM_DOMAIN_GTT, - &adev->vcn.inst[i].dpg_sram_bo, - &adev->vcn.inst[i].dpg_sram_gpu_addr, - &adev->vcn.inst[i].dpg_sram_cpu_addr); - if (r) { - dev_err(adev->dev, "VCN %d (%d) failed to allocate DPG bo\n", i, r); - return r; - } - } } return 0; } -int amdgpu_vcn_sw_fini(struct amdgpu_device *adev) +int amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int i) { - int i, j; + int j; - for (j = 0; j < adev->vcn.num_vcn_inst; ++j) { - if (adev->vcn.harvest_config & (1 << j)) - continue; + if (adev->vcn.harvest_config & (1 << i)) + return 0; - amdgpu_bo_free_kernel( - &adev->vcn.inst[j].dpg_sram_bo, - &adev->vcn.inst[j].dpg_sram_gpu_addr, - (void **)&adev->vcn.inst[j].dpg_sram_cpu_addr); + amdgpu_bo_free_kernel( + &adev->vcn.inst[i].dpg_sram_bo, + &adev->vcn.inst[i].dpg_sram_gpu_addr, + (void **)&adev->vcn.inst[i].dpg_sram_cpu_addr); - kvfree(adev->vcn.inst[j].saved_bo); + kvfree(adev->vcn.inst[i].saved_bo); - amdgpu_bo_free_kernel(&adev->vcn.inst[j].vcpu_bo, - &adev->vcn.inst[j].gpu_addr, - (void **)&adev->vcn.inst[j].cpu_addr); + amdgpu_bo_free_kernel(&adev->vcn.inst[i].vcpu_bo, + &adev->vcn.inst[i].gpu_addr, + (void **)&adev->vcn.inst[i].cpu_addr); - amdgpu_ring_fini(&adev->vcn.inst[j].ring_dec); + amdgpu_ring_fini(&adev->vcn.inst[i].ring_dec); - for (i = 0; i < adev->vcn.num_enc_rings; ++i) - amdgpu_ring_fini(&adev->vcn.inst[j].ring_enc[i]); + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) + amdgpu_ring_fini(&adev->vcn.inst[i].ring_enc[j]); - amdgpu_ucode_release(&adev->vcn.inst[j].fw); + if (adev->vcn.per_inst_fw) { + amdgpu_ucode_release(&adev->vcn.inst[i].fw); + } else { + amdgpu_ucode_release(&adev->vcn.inst[0].fw); + adev->vcn.inst[i].fw = NULL; } - - mutex_destroy(&adev->vcn.vcn1_jpeg1_workaround); - mutex_destroy(&adev->vcn.vcn_pg_lock); + mutex_destroy(&adev->vcn.inst[i].vcn_pg_lock); + mutex_destroy(&adev->vcn.inst[i].vcn1_jpeg1_workaround); return 0; } @@ -300,179 +305,190 @@ bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type t return ret; } -int amdgpu_vcn_save_vcpu_bo(struct amdgpu_device *adev) +static int amdgpu_vcn_save_vcpu_bo_inst(struct amdgpu_device *adev, int i) { unsigned int size; void *ptr; - int i, idx; + int idx; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; - if (adev->vcn.inst[i].vcpu_bo == NULL) - return 0; + if (adev->vcn.harvest_config & (1 << i)) + return 0; + if (adev->vcn.inst[i].vcpu_bo == NULL) + return 0; - size = amdgpu_bo_size(adev->vcn.inst[i].vcpu_bo); - ptr = adev->vcn.inst[i].cpu_addr; + size = amdgpu_bo_size(adev->vcn.inst[i].vcpu_bo); + ptr = adev->vcn.inst[i].cpu_addr; - adev->vcn.inst[i].saved_bo = kvmalloc(size, GFP_KERNEL); - if (!adev->vcn.inst[i].saved_bo) - return -ENOMEM; + adev->vcn.inst[i].saved_bo = kvmalloc(size, GFP_KERNEL); + if (!adev->vcn.inst[i].saved_bo) + return -ENOMEM; - if (drm_dev_enter(adev_to_drm(adev), &idx)) { - memcpy_fromio(adev->vcn.inst[i].saved_bo, ptr, size); - drm_dev_exit(idx); - } + if (drm_dev_enter(adev_to_drm(adev), &idx)) { + memcpy_fromio(adev->vcn.inst[i].saved_bo, ptr, size); + drm_dev_exit(idx); } return 0; } -int amdgpu_vcn_suspend(struct amdgpu_device *adev) +int amdgpu_vcn_save_vcpu_bo(struct amdgpu_device *adev) +{ + int ret, i; + + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + ret = amdgpu_vcn_save_vcpu_bo_inst(adev, i); + if (ret) + return ret; + } + + return 0; +} + +int amdgpu_vcn_suspend(struct amdgpu_device *adev, int i) { bool in_ras_intr = amdgpu_ras_intr_triggered(); - cancel_delayed_work_sync(&adev->vcn.idle_work); + if (adev->vcn.harvest_config & (1 << i)) + return 0; + + cancel_delayed_work_sync(&adev->vcn.inst[i].idle_work); /* err_event_athub will corrupt VCPU buffer, so we need to * restore fw data and clear buffer in amdgpu_vcn_resume() */ if (in_ras_intr) return 0; - return amdgpu_vcn_save_vcpu_bo(adev); + return amdgpu_vcn_save_vcpu_bo_inst(adev, i); } -int amdgpu_vcn_resume(struct amdgpu_device *adev) +int amdgpu_vcn_resume(struct amdgpu_device *adev, int i) { unsigned int size; void *ptr; - int i, idx; + int idx; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; - if (adev->vcn.inst[i].vcpu_bo == NULL) - return -EINVAL; + if (adev->vcn.harvest_config & (1 << i)) + return 0; + if (adev->vcn.inst[i].vcpu_bo == NULL) + return -EINVAL; - size = amdgpu_bo_size(adev->vcn.inst[i].vcpu_bo); - ptr = adev->vcn.inst[i].cpu_addr; + size = amdgpu_bo_size(adev->vcn.inst[i].vcpu_bo); + ptr = adev->vcn.inst[i].cpu_addr; + + if (adev->vcn.inst[i].saved_bo != NULL) { + if (drm_dev_enter(adev_to_drm(adev), &idx)) { + memcpy_toio(ptr, adev->vcn.inst[i].saved_bo, size); + drm_dev_exit(idx); + } + kvfree(adev->vcn.inst[i].saved_bo); + adev->vcn.inst[i].saved_bo = NULL; + } else { + const struct common_firmware_header *hdr; + unsigned int offset; - if (adev->vcn.inst[i].saved_bo != NULL) { + hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data; + if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) { + offset = le32_to_cpu(hdr->ucode_array_offset_bytes); if (drm_dev_enter(adev_to_drm(adev), &idx)) { - memcpy_toio(ptr, adev->vcn.inst[i].saved_bo, size); + memcpy_toio(adev->vcn.inst[i].cpu_addr, + adev->vcn.inst[i].fw->data + offset, + le32_to_cpu(hdr->ucode_size_bytes)); drm_dev_exit(idx); } - kvfree(adev->vcn.inst[i].saved_bo); - adev->vcn.inst[i].saved_bo = NULL; - } else { - const struct common_firmware_header *hdr; - unsigned int offset; - - hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data; - if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) { - offset = le32_to_cpu(hdr->ucode_array_offset_bytes); - if (drm_dev_enter(adev_to_drm(adev), &idx)) { - memcpy_toio(adev->vcn.inst[i].cpu_addr, - adev->vcn.inst[i].fw->data + offset, - le32_to_cpu(hdr->ucode_size_bytes)); - drm_dev_exit(idx); - } - size -= le32_to_cpu(hdr->ucode_size_bytes); - ptr += le32_to_cpu(hdr->ucode_size_bytes); - } - memset_io(ptr, 0, size); + size -= le32_to_cpu(hdr->ucode_size_bytes); + ptr += le32_to_cpu(hdr->ucode_size_bytes); } + memset_io(ptr, 0, size); } + return 0; } static void amdgpu_vcn_idle_work_handler(struct work_struct *work) { - struct amdgpu_device *adev = - container_of(work, struct amdgpu_device, vcn.idle_work.work); + struct amdgpu_vcn_inst *vcn_inst = + container_of(work, struct amdgpu_vcn_inst, idle_work.work); + struct amdgpu_device *adev = vcn_inst->adev; unsigned int fences = 0, fence[AMDGPU_MAX_VCN_INSTANCES] = {0}; - unsigned int i, j; + unsigned int i = vcn_inst->inst, j; int r = 0; - for (j = 0; j < adev->vcn.num_vcn_inst; ++j) { - if (adev->vcn.harvest_config & (1 << j)) - continue; - - for (i = 0; i < adev->vcn.num_enc_rings; ++i) - fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]); + if (adev->vcn.harvest_config & (1 << i)) + return; - /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && - !adev->vcn.using_unified_queue) { - struct dpg_pause_state new_state; + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) + fence[i] += amdgpu_fence_count_emitted(&vcn_inst->ring_enc[j]); - if (fence[j] || - unlikely(atomic_read(&adev->vcn.inst[j].dpg_enc_submission_cnt))) - new_state.fw_based = VCN_DPG_STATE__PAUSE; - else - new_state.fw_based = VCN_DPG_STATE__UNPAUSE; + /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && + !adev->vcn.inst[i].using_unified_queue) { + struct dpg_pause_state new_state; - adev->vcn.pause_dpg_mode(adev, j, &new_state); - } + if (fence[i] || + unlikely(atomic_read(&vcn_inst->dpg_enc_submission_cnt))) + new_state.fw_based = VCN_DPG_STATE__PAUSE; + else + new_state.fw_based = VCN_DPG_STATE__UNPAUSE; - fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_dec); - fences += fence[j]; + adev->vcn.inst[i].pause_dpg_mode(vcn_inst, &new_state); } - if (!fences && !atomic_read(&adev->vcn.total_submission_cnt)) { - amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN, - AMD_PG_STATE_GATE); + fence[i] += amdgpu_fence_count_emitted(&vcn_inst->ring_dec); + fences += fence[i]; + + if (!fences && !atomic_read(&vcn_inst->total_submission_cnt)) { + vcn_inst->set_pg_state(vcn_inst, AMD_PG_STATE_GATE); r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO, - false); + false); if (r) dev_warn(adev->dev, "(%d) failed to disable video power profile mode\n", r); } else { - schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT); + schedule_delayed_work(&vcn_inst->idle_work, VCN_IDLE_TIMEOUT); } } void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; + struct amdgpu_vcn_inst *vcn_inst = &adev->vcn.inst[ring->me]; int r = 0; - atomic_inc(&adev->vcn.total_submission_cnt); + atomic_inc(&vcn_inst->total_submission_cnt); - if (!cancel_delayed_work_sync(&adev->vcn.idle_work)) { + if (!cancel_delayed_work_sync(&vcn_inst->idle_work)) { r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO, true); if (r) dev_warn(adev->dev, "(%d) failed to switch to video power profile mode\n", r); } - mutex_lock(&adev->vcn.vcn_pg_lock); - amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN, - AMD_PG_STATE_UNGATE); + mutex_lock(&vcn_inst->vcn_pg_lock); + vcn_inst->set_pg_state(vcn_inst, AMD_PG_STATE_UNGATE); /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && - !adev->vcn.using_unified_queue) { + !vcn_inst->using_unified_queue) { struct dpg_pause_state new_state; if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) { - atomic_inc(&adev->vcn.inst[ring->me].dpg_enc_submission_cnt); + atomic_inc(&vcn_inst->dpg_enc_submission_cnt); new_state.fw_based = VCN_DPG_STATE__PAUSE; } else { unsigned int fences = 0; unsigned int i; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) - fences += amdgpu_fence_count_emitted(&adev->vcn.inst[ring->me].ring_enc[i]); + for (i = 0; i < vcn_inst->num_enc_rings; ++i) + fences += amdgpu_fence_count_emitted(&vcn_inst->ring_enc[i]); - if (fences || atomic_read(&adev->vcn.inst[ring->me].dpg_enc_submission_cnt)) + if (fences || atomic_read(&vcn_inst->dpg_enc_submission_cnt)) new_state.fw_based = VCN_DPG_STATE__PAUSE; else new_state.fw_based = VCN_DPG_STATE__UNPAUSE; } - adev->vcn.pause_dpg_mode(adev, ring->me, &new_state); + vcn_inst->pause_dpg_mode(vcn_inst, &new_state); } - mutex_unlock(&adev->vcn.vcn_pg_lock); + mutex_unlock(&vcn_inst->vcn_pg_lock); } void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring) @@ -482,12 +498,13 @@ void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring) /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ if (ring->adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC && - !adev->vcn.using_unified_queue) + !adev->vcn.inst[ring->me].using_unified_queue) atomic_dec(&ring->adev->vcn.inst[ring->me].dpg_enc_submission_cnt); - atomic_dec(&ring->adev->vcn.total_submission_cnt); + atomic_dec(&ring->adev->vcn.inst[ring->me].total_submission_cnt); - schedule_delayed_work(&ring->adev->vcn.idle_work, VCN_IDLE_TIMEOUT); + schedule_delayed_work(&ring->adev->vcn.inst[ring->me].idle_work, + VCN_IDLE_TIMEOUT); } int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring) @@ -505,7 +522,7 @@ int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring) r = amdgpu_ring_alloc(ring, 3); if (r) return r; - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.scratch9, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.scratch9, 0)); amdgpu_ring_write(ring, 0xDEADBEEF); amdgpu_ring_commit(ring); for (i = 0; i < adev->usec_timeout; i++) { @@ -570,14 +587,14 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring, goto err; ib = &job->ibs[0]; - ib->ptr[0] = PACKET0(adev->vcn.internal.data0, 0); + ib->ptr[0] = PACKET0(adev->vcn.inst[ring->me].internal.data0, 0); ib->ptr[1] = addr; - ib->ptr[2] = PACKET0(adev->vcn.internal.data1, 0); + ib->ptr[2] = PACKET0(adev->vcn.inst[ring->me].internal.data1, 0); ib->ptr[3] = addr >> 32; - ib->ptr[4] = PACKET0(adev->vcn.internal.cmd, 0); + ib->ptr[4] = PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0); ib->ptr[5] = 0; for (i = 6; i < 16; i += 2) { - ib->ptr[i] = PACKET0(adev->vcn.internal.nop, 0); + ib->ptr[i] = PACKET0(adev->vcn.inst[ring->me].internal.nop, 0); ib->ptr[i+1] = 0; } ib->length_dw = 16; @@ -740,7 +757,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, uint32_t ib_pack_in_dw; int i, r; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) ib_size_dw += 8; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, @@ -753,7 +770,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, ib->length_dw = 0; /* single queue headers */ - if (adev->vcn.using_unified_queue) { + if (adev->vcn.inst[ring->me].using_unified_queue) { ib_pack_in_dw = sizeof(struct amdgpu_vcn_decode_buffer) / sizeof(uint32_t) + 4 + 2; /* engine info + decoding ib in dw */ ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, ib_pack_in_dw, false); @@ -772,7 +789,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, ib_pack_in_dw); r = amdgpu_job_submit_direct(job, ring, &f); @@ -870,7 +887,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand uint64_t addr; int i, r; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) ib_size_dw += 8; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, @@ -884,7 +901,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand ib->length_dw = 0; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true); ib->ptr[ib->length_dw++] = 0x00000018; @@ -906,7 +923,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11); r = amdgpu_job_submit_direct(job, ring, &f); @@ -937,7 +954,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han uint64_t addr; int i, r; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) ib_size_dw += 8; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, @@ -951,7 +968,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han ib->length_dw = 0; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true); ib->ptr[ib->length_dw++] = 0x00000018; @@ -973,7 +990,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11); r = amdgpu_job_submit_direct(job, ring, &f); @@ -1058,36 +1075,32 @@ enum amdgpu_ring_priority_level amdgpu_vcn_get_enc_ring_prio(int ring) } } -void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev) +void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev, int i) { - int i; unsigned int idx; if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { const struct common_firmware_header *hdr; - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - if (adev->vcn.harvest_config & (1 << i)) - continue; - - hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data; - /* currently only support 2 FW instances */ - if (i >= 2) { - dev_info(adev->dev, "More then 2 VCN FW instances!\n"); - break; - } - idx = AMDGPU_UCODE_ID_VCN + i; - adev->firmware.ucode[idx].ucode_id = idx; - adev->firmware.ucode[idx].fw = adev->vcn.inst[i].fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE); - - if (amdgpu_ip_version(adev, UVD_HWIP, 0) == - IP_VERSION(4, 0, 3) || - amdgpu_ip_version(adev, UVD_HWIP, 0) == - IP_VERSION(5, 0, 1)) - break; + if (adev->vcn.harvest_config & (1 << i)) + return; + + if ((amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(4, 0, 3) || + amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(5, 0, 1)) + && (i > 0)) + return; + + hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data; + /* currently only support 2 FW instances */ + if (i >= 2) { + dev_info(adev->dev, "More then 2 VCN FW instances!\n"); + return; } + idx = AMDGPU_UCODE_ID_VCN + i; + adev->firmware.ucode[idx].ucode_id = idx; + adev->firmware.ucode[idx].fw = adev->vcn.inst[i].fw; + adev->firmware.fw_size += + ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE); } } @@ -1390,10 +1403,33 @@ void amdgpu_debugfs_vcn_sched_mask_init(struct amdgpu_device *adev) struct dentry *root = minor->debugfs_root; char name[32]; - if (adev->vcn.num_vcn_inst <= 1 || !adev->vcn.using_unified_queue) + if (adev->vcn.num_vcn_inst <= 1 || !adev->vcn.inst[0].using_unified_queue) return; sprintf(name, "amdgpu_vcn_sched_mask"); debugfs_create_file(name, 0600, root, adev, &amdgpu_debugfs_vcn_sched_mask_fops); #endif } + +/** + * vcn_set_powergating_state - set VCN block powergating state + * + * @ip_block: amdgpu_ip_block pointer + * @state: power gating state + * + * Set VCN block powergating state + */ +int vcn_set_powergating_state(struct amdgpu_ip_block *ip_block, + enum amd_powergating_state state) +{ + struct amdgpu_device *adev = ip_block->adev; + int ret = 0, i; + + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + + ret |= vinst->set_pg_state(vinst, state); + } + + return ret; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index c92f683ee595..26c9c2d90f45 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -295,6 +295,8 @@ struct amdgpu_vcn_fw_shared { }; struct amdgpu_vcn_inst { + struct amdgpu_device *adev; + int inst; struct amdgpu_bo *vcpu_bo; void *cpu_addr; uint64_t gpu_addr; @@ -316,6 +318,20 @@ struct amdgpu_vcn_inst { const struct firmware *fw; /* VCN firmware */ uint8_t vcn_config; uint32_t vcn_codec_disable_mask; + atomic_t total_submission_cnt; + struct mutex vcn_pg_lock; + enum amd_powergating_state cur_state; + struct delayed_work idle_work; + unsigned fw_version; + unsigned num_enc_rings; + bool indirect_sram; + struct amdgpu_vcn_reg internal; + struct mutex vcn1_jpeg1_workaround; + int (*pause_dpg_mode)(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); + int (*set_pg_state)(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); + bool using_unified_queue; }; struct amdgpu_vcn_ras { @@ -323,35 +339,25 @@ struct amdgpu_vcn_ras { }; struct amdgpu_vcn { - unsigned fw_version; - struct delayed_work idle_work; - unsigned num_enc_rings; - enum amd_powergating_state cur_state; - bool indirect_sram; - uint8_t num_vcn_inst; struct amdgpu_vcn_inst inst[AMDGPU_MAX_VCN_INSTANCES]; - struct amdgpu_vcn_reg internal; - struct mutex vcn_pg_lock; - struct mutex vcn1_jpeg1_workaround; - atomic_t total_submission_cnt; unsigned harvest_config; - int (*pause_dpg_mode)(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); struct ras_common_if *ras_if; struct amdgpu_vcn_ras *ras; uint16_t inst_mask; uint8_t num_inst_per_aid; - bool using_unified_queue; /* IP reg dump */ uint32_t *ip_dump; uint32_t supported_reset; uint32_t caps; + + bool per_inst_fw; + unsigned fw_version; }; struct amdgpu_fw_shared_rb_ptrs_struct { @@ -500,11 +506,11 @@ enum vcn_ring_type { VCN_UNIFIED_RING, }; -int amdgpu_vcn_early_init(struct amdgpu_device *adev); -int amdgpu_vcn_sw_init(struct amdgpu_device *adev); -int amdgpu_vcn_sw_fini(struct amdgpu_device *adev); -int amdgpu_vcn_suspend(struct amdgpu_device *adev); -int amdgpu_vcn_resume(struct amdgpu_device *adev); +int amdgpu_vcn_early_init(struct amdgpu_device *adev, int i); +int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int i); +int amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int i); +int amdgpu_vcn_suspend(struct amdgpu_device *adev, int i); +int amdgpu_vcn_resume(struct amdgpu_device *adev, int i); void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring); void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring); @@ -522,7 +528,7 @@ int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout); enum amdgpu_ring_priority_level amdgpu_vcn_get_enc_ring_prio(int ring); -void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev); +void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev, int i); void amdgpu_vcn_fwlog_init(struct amdgpu_vcn_inst *vcn); void amdgpu_debugfs_vcn_fwlog_init(struct amdgpu_device *adev, @@ -542,4 +548,7 @@ int amdgpu_vcn_sysfs_reset_mask_init(struct amdgpu_device *adev); void amdgpu_vcn_sysfs_reset_mask_fini(struct amdgpu_device *adev); void amdgpu_debugfs_vcn_sched_mask_init(struct amdgpu_device *adev); +int vcn_set_powergating_state(struct amdgpu_ip_block *ip_block, + enum amd_powergating_state state); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index e6f0152e5b08..ab7e73d0e7b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -739,7 +739,7 @@ void amdgpu_virt_exchange_data(struct amdgpu_device *adev) } } -void amdgpu_detect_virtualization(struct amdgpu_device *adev) +static u32 amdgpu_virt_init_detect_asic(struct amdgpu_device *adev) { uint32_t reg; @@ -775,8 +775,17 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev) adev->virt.caps |= AMDGPU_PASSTHROUGH_MODE; } + return reg; +} + +static bool amdgpu_virt_init_req_data(struct amdgpu_device *adev, u32 reg) +{ + bool is_sriov = false; + /* we have the ability to check now */ if (amdgpu_sriov_vf(adev)) { + is_sriov = true; + switch (adev->asic_type) { case CHIP_TONGA: case CHIP_FIJI: @@ -805,10 +814,39 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev) amdgpu_virt_request_init_data(adev); break; default: /* other chip doesn't support SRIOV */ + is_sriov = false; DRM_ERROR("Unknown asic type: %d!\n", adev->asic_type); break; } } + + return is_sriov; +} + +static void amdgpu_virt_init_ras(struct amdgpu_device *adev) +{ + ratelimit_state_init(&adev->virt.ras.ras_error_cnt_rs, 5 * HZ, 1); + ratelimit_state_init(&adev->virt.ras.ras_cper_dump_rs, 5 * HZ, 1); + + ratelimit_set_flags(&adev->virt.ras.ras_error_cnt_rs, + RATELIMIT_MSG_ON_RELEASE); + ratelimit_set_flags(&adev->virt.ras.ras_cper_dump_rs, + RATELIMIT_MSG_ON_RELEASE); + + mutex_init(&adev->virt.ras.ras_telemetry_mutex); + + adev->virt.ras.cper_rptr = 0; +} + +void amdgpu_virt_init(struct amdgpu_device *adev) +{ + bool is_sriov = false; + uint32_t reg = amdgpu_virt_init_detect_asic(adev); + + is_sriov = amdgpu_virt_init_req_data(adev, reg); + + if (is_sriov) + amdgpu_virt_init_ras(adev); } static bool amdgpu_virt_access_debugfs_is_mmio(struct amdgpu_device *adev) @@ -1288,10 +1326,12 @@ static int amdgpu_virt_req_ras_err_count_internal(struct amdgpu_device *adev, bo * will ignore incoming guest messages. Ratelimit the guest messages to * prevent guest self DOS. */ - if (__ratelimit(&adev->virt.ras_telemetry_rs) || force_update) { + if (__ratelimit(&virt->ras.ras_error_cnt_rs) || force_update) { + mutex_lock(&virt->ras.ras_telemetry_mutex); if (!virt->ops->req_ras_err_count(adev)) amdgpu_virt_cache_host_error_counts(adev, - adev->virt.fw_reserve.ras_telemetry); + virt->fw_reserve.ras_telemetry); + mutex_unlock(&virt->ras.ras_telemetry_mutex); } return 0; @@ -1322,6 +1362,98 @@ int amdgpu_virt_req_ras_err_count(struct amdgpu_device *adev, enum amdgpu_ras_bl return 0; } +static int +amdgpu_virt_write_cpers_to_ring(struct amdgpu_device *adev, + struct amdsriov_ras_telemetry *host_telemetry, + u32 *more) +{ + struct amd_sriov_ras_cper_dump *cper_dump = NULL; + struct cper_hdr *entry = NULL; + struct amdgpu_ring *ring = &adev->cper.ring_buf; + uint32_t checksum, used_size, i; + int ret = 0; + + checksum = host_telemetry->header.checksum; + used_size = host_telemetry->header.used_size; + + if (used_size > (AMD_SRIOV_RAS_TELEMETRY_SIZE_KB << 10)) + return 0; + + cper_dump = kmemdup(&host_telemetry->body.cper_dump, used_size, GFP_KERNEL); + if (!cper_dump) + return -ENOMEM; + + if (checksum != amd_sriov_msg_checksum(cper_dump, used_size, 0, 0)) + goto out; + + *more = cper_dump->more; + + if (cper_dump->wptr < adev->virt.ras.cper_rptr) { + dev_warn( + adev->dev, + "guest specified rptr that was too high! guest rptr: 0x%llx, host rptr: 0x%llx\n", + adev->virt.ras.cper_rptr, cper_dump->wptr); + + adev->virt.ras.cper_rptr = cper_dump->wptr; + goto out; + } + + entry = (struct cper_hdr *)&cper_dump->buf[0]; + + for (i = 0; i < cper_dump->count; i++) { + amdgpu_cper_ring_write(ring, entry, entry->record_length); + entry = (struct cper_hdr *)((char *)entry + + entry->record_length); + } + + if (cper_dump->overflow_count) + dev_warn(adev->dev, + "host reported CPER overflow of 0x%llx entries!\n", + cper_dump->overflow_count); + + adev->virt.ras.cper_rptr = cper_dump->wptr; +out: + kfree(cper_dump); + + return ret; +} + +static int amdgpu_virt_req_ras_cper_dump_internal(struct amdgpu_device *adev) +{ + struct amdgpu_virt *virt = &adev->virt; + int ret = 0; + uint32_t more = 0; + + if (!amdgpu_sriov_ras_cper_en(adev)) + return -EOPNOTSUPP; + + do { + if (!virt->ops->req_ras_cper_dump(adev, virt->ras.cper_rptr)) + ret = amdgpu_virt_write_cpers_to_ring( + adev, virt->fw_reserve.ras_telemetry, &more); + else + ret = 0; + } while (more); + + return ret; +} + +int amdgpu_virt_req_ras_cper_dump(struct amdgpu_device *adev, bool force_update) +{ + struct amdgpu_virt *virt = &adev->virt; + int ret = 0; + + if ((__ratelimit(&virt->ras.ras_cper_dump_rs) || force_update) && + down_read_trylock(&adev->reset_domain->sem)) { + mutex_lock(&virt->ras.ras_telemetry_mutex); + ret = amdgpu_virt_req_ras_cper_dump_internal(adev); + mutex_unlock(&virt->ras.ras_telemetry_mutex); + up_read(&adev->reset_domain->sem); + } + + return ret; +} + int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev) { unsigned long ue_count, ce_count; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 0f3ccae5c1ab..9f65487e60f5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -96,6 +96,7 @@ struct amdgpu_virt_ops { enum amdgpu_ras_block block); bool (*rcvd_ras_intr)(struct amdgpu_device *adev); int (*req_ras_err_count)(struct amdgpu_device *adev); + int (*req_ras_cper_dump)(struct amdgpu_device *adev, u64 vf_rptr); }; /* @@ -140,6 +141,7 @@ enum AMDGIM_FEATURE_FLAG { AMDGIM_FEATURE_MES_INFO_ENABLE = (1 << 8), AMDGIM_FEATURE_RAS_CAPS = (1 << 9), AMDGIM_FEATURE_RAS_TELEMETRY = (1 << 10), + AMDGIM_FEATURE_RAS_CPER = (1 << 11), }; enum AMDGIM_REG_ACCESS_FLAG { @@ -242,6 +244,13 @@ struct amdgpu_virt_ras_err_handler_data { int last_reserved; }; +struct amdgpu_virt_ras { + struct ratelimit_state ras_error_cnt_rs; + struct ratelimit_state ras_cper_dump_rs; + struct mutex ras_telemetry_mutex; + uint64_t cper_rptr; +}; + /* GPU virtualization */ struct amdgpu_virt { uint32_t caps; @@ -284,8 +293,7 @@ struct amdgpu_virt { union amd_sriov_ras_caps ras_en_caps; union amd_sriov_ras_caps ras_telemetry_en_caps; - - struct ratelimit_state ras_telemetry_rs; + struct amdgpu_virt_ras ras; struct amd_sriov_ras_telemetry_error_count count_cache; }; @@ -340,6 +348,9 @@ struct amdgpu_video_codec_info; #define amdgpu_sriov_ras_telemetry_block_en(adev, sriov_blk) \ (amdgpu_sriov_ras_telemetry_en((adev)) && (adev)->virt.ras_telemetry_en_caps.all & BIT(sriov_blk)) +#define amdgpu_sriov_ras_cper_en(adev) \ +((adev)->virt.gim_feature & AMDGIM_FEATURE_RAS_CPER) + static inline bool is_virtual_machine(void) { #if defined(CONFIG_X86) @@ -378,7 +389,7 @@ void amdgpu_virt_release_ras_err_handler_data(struct amdgpu_device *adev); void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev); void amdgpu_virt_exchange_data(struct amdgpu_device *adev); void amdgpu_virt_fini_data_exchange(struct amdgpu_device *adev); -void amdgpu_detect_virtualization(struct amdgpu_device *adev); +void amdgpu_virt_init(struct amdgpu_device *adev); bool amdgpu_virt_can_access_debugfs(struct amdgpu_device *adev); int amdgpu_virt_enable_access_debugfs(struct amdgpu_device *adev); @@ -406,6 +417,7 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f bool amdgpu_virt_get_ras_capability(struct amdgpu_device *adev); int amdgpu_virt_req_ras_err_count(struct amdgpu_device *adev, enum amdgpu_ras_block block, struct ras_err_data *err_data); +int amdgpu_virt_req_ras_cper_dump(struct amdgpu_device *adev, bool force_update); int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev); bool amdgpu_virt_ras_telemetry_block_en(struct amdgpu_device *adev, enum amdgpu_ras_block block); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index 03308261f894..fc6d02d0f047 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -627,7 +627,7 @@ static int amdgpu_vkms_resume(struct amdgpu_ip_block *ip_block) return drm_mode_config_helper_resume(adev_to_drm(ip_block->adev)); } -static bool amdgpu_vkms_is_idle(void *handle) +static bool amdgpu_vkms_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index c98b6b35cfdf..7fdf30f1161c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -315,6 +315,7 @@ int amdgpu_get_xgmi_link_status(struct amdgpu_device *adev, int global_link_num) switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) { case IP_VERSION(6, 4, 0): + case IP_VERSION(6, 4, 1): xgmi_state_reg_val = xgmi_v6_4_get_link_status(adev, global_link_num); break; default: @@ -818,28 +819,69 @@ int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_dev * num_hops[2:0] = number of hops */ int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev, - struct amdgpu_device *peer_adev) + struct amdgpu_device *peer_adev) { struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info; uint8_t num_hops_mask = 0x7; int i; + if (!adev->gmc.xgmi.supported) + return 0; + for (i = 0 ; i < top->num_nodes; ++i) if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id) return top->nodes[i].num_hops & num_hops_mask; - return -EINVAL; + + dev_err(adev->dev, "Failed to get xgmi hops count for peer %d.\n", + peer_adev->gmc.xgmi.physical_node_id); + + return 0; } -int amdgpu_xgmi_get_num_links(struct amdgpu_device *adev, - struct amdgpu_device *peer_adev) +int amdgpu_xgmi_get_bandwidth(struct amdgpu_device *adev, struct amdgpu_device *peer_adev, + enum amdgpu_xgmi_bw_mode bw_mode, enum amdgpu_xgmi_bw_unit bw_unit, + uint32_t *min_bw, uint32_t *max_bw) { - struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info; - int i; + bool peer_mode = bw_mode == AMDGPU_XGMI_BW_MODE_PER_PEER; + int unit_scale = bw_unit == AMDGPU_XGMI_BW_UNIT_MBYTES ? 1000 : 1; + int speed = 25, num_lanes = 16, num_links = !peer_mode ? 1 : -1; - for (i = 0 ; i < top->num_nodes; ++i) - if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id) - return top->nodes[i].num_links; - return -EINVAL; + if (!(min_bw && max_bw)) + return -EINVAL; + + *min_bw = 0; + *max_bw = 0; + + if (!adev->gmc.xgmi.supported) + return -ENODATA; + + if (peer_mode && !peer_adev) + return -EINVAL; + + if (peer_mode) { + struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info; + int i; + + for (i = 0 ; i < top->num_nodes; ++i) { + if (top->nodes[i].node_id != peer_adev->gmc.xgmi.node_id) + continue; + + num_links = top->nodes[i].num_links; + break; + } + } + + if (num_links == -1) { + dev_err(adev->dev, "Failed to get number of xgmi links for peer %d.\n", + peer_adev->gmc.xgmi.physical_node_id); + } else if (num_links) { + int per_link_bw = (speed * num_lanes * unit_scale)/BITS_PER_BYTE; + + *min_bw = per_link_bw; + *max_bw = num_links * per_link_bw; + } + + return 0; } bool amdgpu_xgmi_get_is_sharing_enabled(struct amdgpu_device *adev, @@ -1128,8 +1170,8 @@ static int xgmi_v6_4_0_aca_bank_parser(struct aca_handle *handle, struct aca_ban break; case ACA_SMU_TYPE_CE: count = ext_error_code == 6 ? count : 0ULL; - bank->aca_err_type = ACA_ERROR_TYPE_CE; - ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE, count); + bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank); + ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, count); break; default: return -EINVAL; @@ -1164,6 +1206,7 @@ static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev, struct ras_comm switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) { case IP_VERSION(6, 4, 0): + case IP_VERSION(6, 4, 1): r = amdgpu_ras_bind_aca(adev, AMDGPU_RAS_BLOCK__XGMI_WAFL, &xgmi_v6_4_0_aca_info, NULL); if (r) @@ -1223,6 +1266,7 @@ static void amdgpu_xgmi_legacy_reset_ras_error_count(struct amdgpu_device *adev) switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) { case IP_VERSION(6, 4, 0): + case IP_VERSION(6, 4, 1): for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_v6_4); i++) pcs_clear_status(adev, xgmi3x16_pcs_err_status_reg_v6_4[i]); @@ -1257,6 +1301,7 @@ static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev) { switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) { case IP_VERSION(6, 4, 0): + case IP_VERSION(6, 4, 1): xgmi_v6_4_0_reset_ras_error_count(adev); break; default: @@ -1282,7 +1327,9 @@ static int amdgpu_xgmi_query_pcs_error_status(struct amdgpu_device *adev, if (amdgpu_ip_version(adev, XGMI_HWIP, 0) == IP_VERSION(6, 1, 0) || amdgpu_ip_version(adev, XGMI_HWIP, 0) == - IP_VERSION(6, 4, 0)) { + IP_VERSION(6, 4, 0) || + amdgpu_ip_version(adev, XGMI_HWIP, 0) == + IP_VERSION(6, 4, 1)) { pcs_ras_fields = &xgmi3x16_pcs_ras_fields[0]; field_array_size = ARRAY_SIZE(xgmi3x16_pcs_ras_fields); } else { @@ -1390,6 +1437,7 @@ static void amdgpu_xgmi_legacy_query_ras_error_count(struct amdgpu_device *adev, switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) { case IP_VERSION(6, 4, 0): + case IP_VERSION(6, 4, 1): /* check xgmi3x16 pcs error */ for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_v6_4); i++) { data = RREG32_PCIE(xgmi3x16_pcs_err_status_reg_v6_4[i]); @@ -1486,6 +1534,7 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev, { switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) { case IP_VERSION(6, 4, 0): + case IP_VERSION(6, 4, 1): xgmi_v6_4_0_query_ras_error_count(adev, ras_error_status); break; default: @@ -1673,3 +1722,34 @@ int amdgpu_xgmi_request_nps_change(struct amdgpu_device *adev, return r; } + +bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev, + struct amdgpu_device *bo_adev) +{ + return (amdgpu_use_xgmi_p2p && adev != bo_adev && + adev->gmc.xgmi.hive_id && + adev->gmc.xgmi.hive_id == bo_adev->gmc.xgmi.hive_id); +} + +void amdgpu_xgmi_early_init(struct amdgpu_device *adev) +{ + if (!adev->gmc.xgmi.supported) + return; + + switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { + case IP_VERSION(9, 4, 0): + case IP_VERSION(9, 4, 1): + case IP_VERSION(9, 4, 2): + adev->gmc.xgmi.max_speed = XGMI_SPEED_25GT; + adev->gmc.xgmi.max_width = 16; + break; + case IP_VERSION(9, 4, 3): + case IP_VERSION(9, 4, 4): + case IP_VERSION(9, 5, 0): + adev->gmc.xgmi.max_speed = XGMI_SPEED_32GT; + adev->gmc.xgmi.max_width = 16; + break; + default: + break; + } +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h index d1282b4c6348..32dabba4062f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h @@ -23,9 +23,14 @@ #define __AMDGPU_XGMI_H__ #include <drm/task_barrier.h> -#include "amdgpu_psp.h" #include "amdgpu_ras.h" +enum amdgpu_xgmi_link_speed { + XGMI_SPEED_16GT = 16, + XGMI_SPEED_25GT = 25, + XGMI_SPEED_32GT = 32 +}; + struct amdgpu_hive_info { struct kobject kobj; uint64_t hive_id; @@ -55,29 +60,63 @@ struct amdgpu_pcs_ras_field { uint32_t pcs_err_shift; }; -extern struct amdgpu_xgmi_ras xgmi_ras; +/** + * Bandwidth range reporting comes in two modes. + * + * PER_LINK - range for any xgmi link + * PER_PEER - range of max of single xgmi link to max of multiple links based on source peer + */ +enum amdgpu_xgmi_bw_mode { + AMDGPU_XGMI_BW_MODE_PER_LINK = 0, + AMDGPU_XGMI_BW_MODE_PER_PEER +}; + +enum amdgpu_xgmi_bw_unit { + AMDGPU_XGMI_BW_UNIT_GBYTES = 0, + AMDGPU_XGMI_BW_UNIT_MBYTES +}; + +struct amdgpu_xgmi_ras { + struct amdgpu_ras_block_object ras_block; +}; +extern struct amdgpu_xgmi_ras xgmi_ras; + +struct amdgpu_xgmi { + /* from psp */ + u64 node_id; + u64 hive_id; + /* fixed per family */ + u64 node_segment_size; + /* physical node (0-3) */ + unsigned physical_node_id; + /* number of nodes (0-4) */ + unsigned num_physical_nodes; + /* gpu list in the same hive */ + struct list_head head; + bool supported; + struct ras_common_if *ras_if; + bool connected_to_cpu; + struct amdgpu_xgmi_ras *ras; + enum amdgpu_xgmi_link_speed max_speed; + uint8_t max_width; +}; + struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev); void amdgpu_put_xgmi_hive(struct amdgpu_hive_info *hive); int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_device *adev); int amdgpu_xgmi_add_device(struct amdgpu_device *adev); int amdgpu_xgmi_remove_device(struct amdgpu_device *adev); int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate); -int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev, - struct amdgpu_device *peer_adev); -int amdgpu_xgmi_get_num_links(struct amdgpu_device *adev, - struct amdgpu_device *peer_adev); +int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev, struct amdgpu_device *peer_adev); +int amdgpu_xgmi_get_bandwidth(struct amdgpu_device *adev, struct amdgpu_device *peer_adev, + enum amdgpu_xgmi_bw_mode bw_mode, enum amdgpu_xgmi_bw_unit bw_unit, + uint32_t *min_bw, uint32_t *max_bw); bool amdgpu_xgmi_get_is_sharing_enabled(struct amdgpu_device *adev, struct amdgpu_device *peer_adev); uint64_t amdgpu_xgmi_get_relative_phy_addr(struct amdgpu_device *adev, uint64_t addr); -static inline bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev, - struct amdgpu_device *bo_adev) -{ - return (amdgpu_use_xgmi_p2p && - adev != bo_adev && - adev->gmc.xgmi.hive_id && - adev->gmc.xgmi.hive_id == bo_adev->gmc.xgmi.hive_id); -} +bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev, + struct amdgpu_device *bo_adev); int amdgpu_xgmi_ras_sw_init(struct amdgpu_device *adev); int amdgpu_xgmi_reset_on_init(struct amdgpu_device *adev); @@ -87,4 +126,7 @@ int amdgpu_xgmi_request_nps_change(struct amdgpu_device *adev, int amdgpu_get_xgmi_link_status(struct amdgpu_device *adev, int global_link_num); +void amdgpu_xgmi_early_init(struct amdgpu_device *adev); +uint32_t amdgpu_xgmi_get_max_bandwidth(struct amdgpu_device *adev); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h index b4f9c2f4e92c..d6ac2652f0ac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h @@ -97,11 +97,12 @@ union amd_sriov_msg_feature_flags { uint32_t pp_one_vf_mode : 1; uint32_t reg_indirect_acc : 1; uint32_t av1_support : 1; - uint32_t vcn_rb_decouple : 1; + uint32_t vcn_rb_decouple : 1; uint32_t mes_info_dump_enable : 1; uint32_t ras_caps : 1; uint32_t ras_telemetry : 1; - uint32_t reserved : 21; + uint32_t ras_cper : 1; + uint32_t reserved : 20; } flags; uint32_t all; }; @@ -328,21 +329,25 @@ enum amd_sriov_mailbox_request_message { MB_REQ_MSG_READY_TO_RESET = 201, MB_REQ_MSG_RAS_POISON = 202, MB_REQ_RAS_ERROR_COUNT = 203, + MB_REQ_RAS_CPER_DUMP = 204, }; /* mailbox message send from host to guest */ enum amd_sriov_mailbox_response_message { - MB_RES_MSG_CLR_MSG_BUF = 0, - MB_RES_MSG_READY_TO_ACCESS_GPU = 1, - MB_RES_MSG_FLR_NOTIFICATION, - MB_RES_MSG_FLR_NOTIFICATION_COMPLETION, - MB_RES_MSG_SUCCESS, - MB_RES_MSG_FAIL, - MB_RES_MSG_QUERY_ALIVE, - MB_RES_MSG_GPU_INIT_DATA_READY, - MB_RES_MSG_RAS_ERROR_COUNT_READY = 11, - - MB_RES_MSG_TEXT_MESSAGE = 255 + MB_RES_MSG_CLR_MSG_BUF = 0, + MB_RES_MSG_READY_TO_ACCESS_GPU = 1, + MB_RES_MSG_FLR_NOTIFICATION = 2, + MB_RES_MSG_FLR_NOTIFICATION_COMPLETION = 3, + MB_RES_MSG_SUCCESS = 4, + MB_RES_MSG_FAIL = 5, + MB_RES_MSG_QUERY_ALIVE = 6, + MB_RES_MSG_GPU_INIT_DATA_READY = 7, + MB_RES_MSG_RAS_POISON_READY = 8, + MB_RES_MSG_PF_SOFT_FLR_NOTIFICATION = 9, + MB_RES_MSG_GPU_RMA = 10, + MB_RES_MSG_RAS_ERROR_COUNT_READY = 11, + MB_REQ_RAS_CPER_DUMP_READY = 14, + MB_RES_MSG_TEXT_MESSAGE = 255 }; enum amd_sriov_ras_telemetry_gpu_block { @@ -386,11 +391,20 @@ struct amd_sriov_ras_telemetry_error_count { } block[RAS_TELEMETRY_GPU_BLOCK_COUNT]; }; +struct amd_sriov_ras_cper_dump { + uint32_t more; + uint64_t overflow_count; + uint64_t count; + uint64_t wptr; + uint32_t buf[]; +}; + struct amdsriov_ras_telemetry { struct amd_sriov_ras_telemetry_header header; union { struct amd_sriov_ras_telemetry_error_count error_count; + struct amd_sriov_ras_cper_dump cper_dump; } body; }; diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index 08d6787893b3..9cd63b4177bf 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -2148,7 +2148,7 @@ static int cik_common_resume(struct amdgpu_ip_block *ip_block) return cik_common_hw_init(ip_block); } -static bool cik_common_is_idle(void *handle) +static bool cik_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c index 444563486769..41f4705bdbbd 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c @@ -345,9 +345,9 @@ static int cik_ih_resume(struct amdgpu_ip_block *ip_block) return cik_ih_hw_init(ip_block); } -static bool cik_ih_is_idle(void *handle) +static bool cik_ih_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); if (tmp & SRBM_STATUS__IH_BUSY_MASK) diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index d9bd8f3f17e2..508cea965983 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -1025,9 +1025,9 @@ static int cik_sdma_resume(struct amdgpu_ip_block *ip_block) return cik_sdma_hw_init(ip_block); } -static bool cik_sdma_is_idle(void *handle) +static bool cik_sdma_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS2); if (tmp & (SRBM_STATUS2__SDMA_BUSY_MASK | diff --git a/drivers/gpu/drm/amd/amdgpu/cikd.h b/drivers/gpu/drm/amd/amdgpu/cikd.h index 06088d52d81c..279288365940 100644 --- a/drivers/gpu/drm/amd/amdgpu/cikd.h +++ b/drivers/gpu/drm/amd/amdgpu/cikd.h @@ -51,6 +51,15 @@ #define HPD4_REGISTER_OFFSET (0x1813 - 0x1807) #define HPD5_REGISTER_OFFSET (0x1816 - 0x1807) +/* audio endpt instance offsets */ +#define AUD0_REGISTER_OFFSET (0x1780 - 0x1780) +#define AUD1_REGISTER_OFFSET (0x1786 - 0x1780) +#define AUD2_REGISTER_OFFSET (0x178c - 0x1780) +#define AUD3_REGISTER_OFFSET (0x1792 - 0x1780) +#define AUD4_REGISTER_OFFSET (0x1798 - 0x1780) +#define AUD5_REGISTER_OFFSET (0x179d - 0x1780) +#define AUD6_REGISTER_OFFSET (0x17a4 - 0x1780) + #define BONAIRE_GB_ADDR_CONFIG_GOLDEN 0x12010001 #define HAWAII_GB_ADDR_CONFIG_GOLDEN 0x12011003 diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c index 82586b76aeda..2f891fb846d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c @@ -341,9 +341,9 @@ static int cz_ih_resume(struct amdgpu_ip_block *ip_block) return cz_ih_hw_init(ip_block); } -static bool cz_ih_is_idle(void *handle) +static bool cz_ih_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); if (REG_GET_FIELD(tmp, SRBM_STATUS, IH_BUSY)) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index c5e3d2251b18..df401aded662 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -2970,7 +2970,7 @@ static int dce_v10_0_resume(struct amdgpu_ip_block *ip_block) return amdgpu_display_resume_helper(adev); } -static bool dce_v10_0_is_idle(void *handle) +static bool dce_v10_0_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index ea42a4472bf6..80f01c3989cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -3108,7 +3108,7 @@ static int dce_v11_0_resume(struct amdgpu_ip_block *ip_block) return amdgpu_display_resume_helper(adev); } -static bool dce_v11_0_is_idle(void *handle) +static bool dce_v11_0_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index 915804a6a1d7..ac51b7a6e8d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -206,9 +206,9 @@ static void dce_v6_0_page_flip(struct amdgpu_device *adev, /* update the scanout addresses */ WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, upper_32_bits(crtc_base)); + /* writing to the low address triggers the update */ WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset, (u32)crtc_base); - /* post the write */ RREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset); } @@ -218,11 +218,11 @@ static int dce_v6_0_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc, { if ((crtc < 0) || (crtc >= adev->mode_info.num_crtc)) return -EINVAL; + *vbl = RREG32(mmCRTC_V_BLANK_START_END + crtc_offsets[crtc]); *position = RREG32(mmCRTC_STATUS_POSITION + crtc_offsets[crtc]); return 0; - } /** @@ -242,7 +242,8 @@ static bool dce_v6_0_hpd_sense(struct amdgpu_device *adev, if (hpd >= adev->mode_info.num_hpd) return connected; - if (RREG32(mmDC_HPD1_INT_STATUS + hpd_offsets[hpd]) & DC_HPD1_INT_STATUS__DC_HPD1_SENSE_MASK) + if (RREG32(mmDC_HPD1_INT_STATUS + hpd_offsets[hpd]) & + DC_HPD1_INT_STATUS__DC_HPD1_SENSE_MASK) connected = true; return connected; @@ -370,13 +371,41 @@ static u32 dce_v6_0_hpd_get_gpio_reg(struct amdgpu_device *adev) return mmDC_GPIO_HPD_A; } +static bool dce_v6_0_is_display_hung(struct amdgpu_device *adev) +{ + u32 crtc_hung = 0; + u32 crtc_status[6]; + u32 i, j, tmp; + + for (i = 0; i < adev->mode_info.num_crtc; i++) { + if (RREG32(mmCRTC_CONTROL + crtc_offsets[i]) & CRTC_CONTROL__CRTC_MASTER_EN_MASK) { + crtc_status[i] = RREG32(mmCRTC_STATUS_HV_COUNT + crtc_offsets[i]); + crtc_hung |= (1 << i); + } + } + + for (j = 0; j < 10; j++) { + for (i = 0; i < adev->mode_info.num_crtc; i++) { + if (crtc_hung & (1 << i)) { + tmp = RREG32(mmCRTC_STATUS_HV_COUNT + crtc_offsets[i]); + if (tmp != crtc_status[i]) + crtc_hung &= ~(1 << i); + } + } + if (crtc_hung == 0) + return false; + udelay(100); + } + + return true; +} + static void dce_v6_0_set_vga_render_state(struct amdgpu_device *adev, bool render) { if (!render) WREG32(mmVGA_RENDER_CONTROL, RREG32(mmVGA_RENDER_CONTROL) & VGA_VSTATUS_CNTL); - } static int dce_v6_0_get_num_crtc(struct amdgpu_device *adev) @@ -419,7 +448,6 @@ void dce_v6_0_disable_dce(struct amdgpu_device *adev) static void dce_v6_0_program_fmt(struct drm_encoder *encoder) { - struct drm_device *dev = encoder->dev; struct amdgpu_device *adev = drm_to_adev(dev); struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); @@ -895,8 +923,8 @@ static void dce_v6_0_program_watermarks(struct amdgpu_device *adev, wm_high.dram_channels = dram_channels; wm_high.num_heads = num_heads; - if (adev->pm.dpm_enabled) { /* watermark for low clocks */ + if (adev->pm.dpm_enabled) { wm_low.yclk = amdgpu_dpm_get_mclk(adev, true) * 10; wm_low.sclk = @@ -1006,6 +1034,20 @@ static void dce_v6_0_program_watermarks(struct amdgpu_device *adev, } /* watermark setup */ +/** + * dce_v6_0_line_buffer_adjust - Set up the line buffer + * + * @adev: amdgpu_device pointer + * @amdgpu_crtc: the selected display controller + * @mode: the current display mode on the selected display + * controller + * @other_mode: the display mode of another display controller + * that may be sharing the line buffer + * + * Setup up the line buffer allocation for + * the selected display controller (CIK). + * Returns the line buffer size in pixels. + */ static u32 dce_v6_0_line_buffer_adjust(struct amdgpu_device *adev, struct amdgpu_crtc *amdgpu_crtc, struct drm_display_mode *mode, @@ -1386,6 +1428,8 @@ static int dce_v6_0_audio_init(struct amdgpu_device *adev) adev->mode_info.audio.pin[i].connected = false; adev->mode_info.audio.pin[i].offset = pin_offsets[i]; adev->mode_info.audio.pin[i].id = i; + /* disable audio. it will be set up later */ + /* XXX remove once we switch to ip funcs */ dce_v6_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); } @@ -2865,14 +2909,35 @@ static int dce_v6_0_resume(struct amdgpu_ip_block *ip_block) return amdgpu_display_resume_helper(adev); } -static bool dce_v6_0_is_idle(void *handle) +static bool dce_v6_0_is_idle(struct amdgpu_ip_block *ip_block) { return true; } static int dce_v6_0_soft_reset(struct amdgpu_ip_block *ip_block) { - DRM_INFO("xxxx: dce_v6_0_soft_reset --- no impl!!\n"); + u32 srbm_soft_reset = 0, tmp; + struct amdgpu_device *adev = ip_block->adev; + + if (dce_v6_0_is_display_hung(adev)) + srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_DC_MASK; + + if (srbm_soft_reset) { + tmp = RREG32(mmSRBM_SOFT_RESET); + tmp |= srbm_soft_reset; + dev_info(adev->dev, "SRBM_SOFT_RESET=0x%08X\n", tmp); + WREG32(mmSRBM_SOFT_RESET, tmp); + tmp = RREG32(mmSRBM_SOFT_RESET); + + udelay(50); + + tmp &= ~srbm_soft_reset; + WREG32(mmSRBM_SOFT_RESET, tmp); + tmp = RREG32(mmSRBM_SOFT_RESET); + + /* Wait a little for things to settle down */ + udelay(50); + } return 0; } @@ -3148,7 +3213,6 @@ static int dce_v6_0_hpd_irq(struct amdgpu_device *adev, } return 0; - } static int dce_v6_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, @@ -3281,8 +3345,7 @@ static void dce_v6_0_ext_commit(struct drm_encoder *encoder) } -static void -dce_v6_0_ext_mode_set(struct drm_encoder *encoder, +static void dce_v6_0_ext_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode) { @@ -3294,8 +3357,7 @@ static void dce_v6_0_ext_disable(struct drm_encoder *encoder) } -static void -dce_v6_0_ext_dpms(struct drm_encoder *encoder, int mode) +static void dce_v6_0_ext_dpms(struct drm_encoder *encoder, int mode) { } @@ -3366,7 +3428,6 @@ static void dce_v6_0_encoder_add(struct amdgpu_device *adev, amdgpu_encoder->devices |= supported_device; return; } - } /* add a new one */ diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index f2edc0fece5b..07358546581f 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -1395,13 +1395,13 @@ static void dce_v8_0_audio_enable(struct amdgpu_device *adev, } static const u32 pin_offsets[7] = { - (0x1780 - 0x1780), - (0x1786 - 0x1780), - (0x178c - 0x1780), - (0x1792 - 0x1780), - (0x1798 - 0x1780), - (0x179d - 0x1780), - (0x17a4 - 0x1780), + AUD0_REGISTER_OFFSET, + AUD1_REGISTER_OFFSET, + AUD2_REGISTER_OFFSET, + AUD3_REGISTER_OFFSET, + AUD4_REGISTER_OFFSET, + AUD5_REGISTER_OFFSET, + AUD6_REGISTER_OFFSET, }; static int dce_v8_0_audio_init(struct amdgpu_device *adev) @@ -2887,7 +2887,7 @@ static int dce_v8_0_resume(struct amdgpu_ip_block *ip_block) return amdgpu_display_resume_helper(adev); } -static bool dce_v8_0_is_idle(void *handle) +static bool dce_v8_0_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f54617c6c071..6d514efb0a6d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -7583,9 +7583,9 @@ static int gfx_v10_0_resume(struct amdgpu_ip_block *ip_block) return gfx_v10_0_hw_init(ip_block); } -static bool gfx_v10_0_is_idle(void *handle) +static bool gfx_v10_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (REG_GET_FIELD(RREG32_SOC15(GC, 0, mmGRBM_STATUS), GRBM_STATUS, GUI_ACTIVE)) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 57f1e2b50e5a..2b3ba404955d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -4787,9 +4787,9 @@ static int gfx_v11_0_resume(struct amdgpu_ip_block *ip_block) return gfx_v11_0_hw_init(ip_block); } -static bool gfx_v11_0_is_idle(void *handle) +static bool gfx_v11_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (REG_GET_FIELD(RREG32_SOC15(GC, 0, regGRBM_STATUS), GRBM_STATUS, GUI_ACTIVE)) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 47490309045f..926fb536bbff 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -3695,9 +3695,9 @@ static int gfx_v12_0_resume(struct amdgpu_ip_block *ip_block) return gfx_v12_0_hw_init(ip_block); } -static bool gfx_v12_0_is_idle(void *handle) +static bool gfx_v12_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (REG_GET_FIELD(RREG32_SOC15(GC, 0, regGRBM_STATUS), GRBM_STATUS, GUI_ACTIVE)) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index f26e2cdec07a..2f5cf87ede88 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -3167,9 +3167,9 @@ static int gfx_v6_0_resume(struct amdgpu_ip_block *ip_block) return gfx_v6_0_hw_init(ip_block); } -static bool gfx_v6_0_is_idle(void *handle) +static bool gfx_v6_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (RREG32(mmGRBM_STATUS) & GRBM_STATUS__GUI_ACTIVE_MASK) return false; @@ -3183,7 +3183,7 @@ static int gfx_v6_0_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (gfx_v6_0_is_idle(adev)) + if (gfx_v6_0_is_idle(ip_block)) return 0; udelay(1); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 84745b2453ab..8181bd0e4f18 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -4515,9 +4515,9 @@ static int gfx_v7_0_resume(struct amdgpu_ip_block *ip_block) return gfx_v7_0_hw_init(ip_block); } -static bool gfx_v7_0_is_idle(void *handle) +static bool gfx_v7_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (RREG32(mmGRBM_STATUS) & GRBM_STATUS__GUI_ACTIVE_MASK) return false; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 6add76ef75e8..d116a2e2f469 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4851,9 +4851,9 @@ static int gfx_v8_0_kcq_disable(struct amdgpu_device *adev) return r; } -static bool gfx_v8_0_is_idle(void *handle) +static bool gfx_v8_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (REG_GET_FIELD(RREG32(mmGRBM_STATUS), GRBM_STATUS, GUI_ACTIVE) || RREG32(mmGRBM_STATUS2) != 0x8) @@ -4892,7 +4892,7 @@ static int gfx_v8_0_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (gfx_v8_0_is_idle(adev)) + if (gfx_v8_0_is_idle(ip_block)) return 0; udelay(1); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index e144bce938d5..d345285ea885 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2637,7 +2637,10 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev) u32 tmp; int i; - WREG32_FIELD15_RLC(GC, 0, GRBM_CNTL, READ_TIMEOUT, 0xff); + if (!amdgpu_sriov_vf(adev) || + amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(9, 4, 2)) { + WREG32_FIELD15_RLC(GC, 0, GRBM_CNTL, READ_TIMEOUT, 0xff); + } gfx_v9_0_tiling_mode_table_init(adev); @@ -4042,7 +4045,8 @@ static int gfx_v9_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 2)) + if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 2) && + !amdgpu_sriov_vf(adev)) gfx_v9_4_2_set_power_brake_sequence(adev); return r; @@ -4110,9 +4114,9 @@ static int gfx_v9_0_resume(struct amdgpu_ip_block *ip_block) return gfx_v9_0_hw_init(ip_block); } -static bool gfx_v9_0_is_idle(void *handle) +static bool gfx_v9_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (REG_GET_FIELD(RREG32_SOC15(GC, 0, mmGRBM_STATUS), GRBM_STATUS, GUI_ACTIVE)) @@ -4127,7 +4131,7 @@ static int gfx_v9_0_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (gfx_v9_0_is_idle(adev)) + if (gfx_v9_0_is_idle(ip_block)) return 0; udelay(1); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index c88564de50cd..476542b6e7b5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -349,18 +349,7 @@ static void gfx_v9_4_3_init_golden_registers(struct amdgpu_device *adev) WREG32_SOC15(GC, dev_inst, regGB_ADDR_CONFIG, GOLDEN_GB_ADDR_CONFIG); - if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0)) { - WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL2, SPARE, 0x1); - } else { - /* Golden settings applied by driver for ASIC with rev_id 0 */ - if (adev->rev_id == 0) { - WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL1, - REDUCE_FIFO_DEPTH_BY_2, 2); - } else { - WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL2, - SPARE, 0x1); - } - } + WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL2, SPARE, 0x1); } } @@ -563,17 +552,6 @@ out: return err; } -static bool gfx_v9_4_3_should_disable_gfxoff(struct pci_dev *pdev) -{ - return true; -} - -static void gfx_v9_4_3_check_if_need_gfxoff(struct amdgpu_device *adev) -{ - if (gfx_v9_4_3_should_disable_gfxoff(adev->pdev)) - adev->pm.pp_feature &= ~PP_GFXOFF_MASK; -} - static int gfx_v9_4_3_init_cp_compute_microcode(struct amdgpu_device *adev, const char *chip_name) { @@ -600,8 +578,6 @@ static int gfx_v9_4_3_init_cp_compute_microcode(struct amdgpu_device *adev, adev->gfx.mec2_fw_version = adev->gfx.mec_fw_version; adev->gfx.mec2_feature_version = adev->gfx.mec_feature_version; - gfx_v9_4_3_check_if_need_gfxoff(adev); - out: if (err) amdgpu_ucode_release(&adev->gfx.mec_fw); @@ -896,9 +872,10 @@ static int gfx_v9_4_3_aca_bank_parser(struct aca_handle *handle, ACA_ERROR_TYPE_UE, 1ULL); break; case ACA_SMU_TYPE_CE: - bank->aca_err_type = ACA_ERROR_TYPE_CE; + bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank); ret = aca_error_cache_log_bank_error(handle, &info, - ACA_ERROR_TYPE_CE, ACA_REG__MISC0__ERRCNT(misc0)); + bank->aca_err_type, + ACA_REG__MISC0__ERRCNT(misc0)); break; default: return -EINVAL; @@ -939,8 +916,6 @@ static const struct aca_info gfx_v9_4_3_aca_info = { static int gfx_v9_4_3_gpu_early_init(struct amdgpu_device *adev) { - u32 gb_addr_config; - adev->gfx.funcs = &gfx_v9_4_3_gfx_funcs; adev->gfx.ras = &gfx_v9_4_3_ras; @@ -949,9 +924,7 @@ static int gfx_v9_4_3_gpu_early_init(struct amdgpu_device *adev) adev->gfx.config.sc_prim_fifo_size_backend = 0x100; adev->gfx.config.sc_hiz_tile_fifo_size = 0x30; adev->gfx.config.sc_earlyz_tile_fifo_size = 0x4C0; - gb_addr_config = RREG32_SOC15(GC, GET_INST(GC, 0), regGB_ADDR_CONFIG); - - adev->gfx.config.gb_addr_config = gb_addr_config; + adev->gfx.config.gb_addr_config = GOLDEN_GB_ADDR_CONFIG; adev->gfx.config.gb_addr_config_fields.num_pipes = 1 << REG_GET_FIELD( @@ -1362,10 +1335,8 @@ static void gfx_v9_4_3_xcc_init_pg(struct amdgpu_device *adev, int xcc_id) { /* * Rlc save restore list is workable since v2_1. - * And it's needed by gfxoff feature. */ - if (adev->gfx.rlc.is_rlc_v2_1) - gfx_v9_4_3_xcc_enable_save_restore_machine(adev, xcc_id); + gfx_v9_4_3_xcc_enable_save_restore_machine(adev, xcc_id); } static void gfx_v9_4_3_xcc_disable_gpa_mode(struct amdgpu_device *adev, int xcc_id) @@ -2408,9 +2379,9 @@ static int gfx_v9_4_3_resume(struct amdgpu_ip_block *ip_block) return gfx_v9_4_3_hw_init(ip_block); } -static bool gfx_v9_4_3_is_idle(void *handle) +static bool gfx_v9_4_3_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, num_xcc; num_xcc = NUM_XCC(adev->gfx.xcc_mask); @@ -2428,7 +2399,7 @@ static int gfx_v9_4_3_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (gfx_v9_4_3_is_idle(adev)) + if (gfx_v9_4_3_is_idle(ip_block)) return 0; udelay(1); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index 0e3ddea7b8e0..a7bfc9f41d0e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -92,12 +92,12 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) { uint64_t value; - /* Program the AGP BAR */ - WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BASE, 0); - WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 24); - WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); - if (!amdgpu_sriov_vf(adev) || adev->asic_type <= CHIP_VEGA10) { + /* Program the AGP BAR */ + WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BASE, 0); + WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 24); + WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); + /* Program the system aperture low logical page number. */ WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR, min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index edf6cf42f141..95d894a231fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -1076,7 +1076,7 @@ static int gmc_v10_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v10_0_is_idle(void *handle) +static bool gmc_v10_0_is_idle(struct amdgpu_ip_block *ip_block) { /* MC is always ready in GMC v10.*/ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index f86d0650a05e..ad099f136f84 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -987,7 +987,7 @@ static int gmc_v11_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v11_0_is_idle(void *handle) +static bool gmc_v11_0_is_idle(struct amdgpu_ip_block *ip_block) { /* MC is always ready in GMC v11.*/ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c index c6d45d0fb9d1..ea7c32d8380b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c @@ -984,7 +984,7 @@ static int gmc_v12_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v12_0_is_idle(void *handle) +static bool gmc_v12_0_is_idle(struct amdgpu_ip_block *ip_block) { /* MC is always ready in GMC v11.*/ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index 2245dda92021..a992e79d9581 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -957,9 +957,9 @@ static int gmc_v6_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v6_0_is_idle(void *handle) +static bool gmc_v6_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); @@ -976,7 +976,7 @@ static int gmc_v6_0_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (gmc_v6_0_is_idle(adev)) + if (gmc_v6_0_is_idle(ip_block)) return 0; udelay(1); } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 9aac4b1101e3..83e39f16044a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -1142,9 +1142,9 @@ static int gmc_v7_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v7_0_is_idle(void *handle) +static bool gmc_v7_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); if (tmp & (SRBM_STATUS__MCB_BUSY_MASK | SRBM_STATUS__MCB_NON_DISPLAY_BUSY_MASK | diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 744081652d42..99ca08e9bdb5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -1263,9 +1263,9 @@ static int gmc_v8_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v8_0_is_idle(void *handle) +static bool gmc_v8_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); if (tmp & (SRBM_STATUS__MCB_BUSY_MASK | SRBM_STATUS__MCB_NON_DISPLAY_BUSY_MASK | diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index a80f3e2bcba8..783e0c3b86b4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1607,9 +1607,8 @@ static void gmc_v9_0_init_nps_details(struct amdgpu_device *adev) /* Mode detected by hardware and supported modes available */ if ((mode != UNKNOWN_MEMORY_PARTITION_MODE) && supp_modes) { - for (i = AMDGPU_NPS1_PARTITION_MODE; - supp_modes && i <= AMDGPU_NPS8_PARTITION_MODE; i++) { - if (supp_modes & BIT(i - 1)) + while ((i = ffs(supp_modes))) { + if (AMDGPU_ALL_NPS_MASK & BIT(i)) adev->gmc.supported_nps_modes |= BIT(i); supp_modes &= supp_modes - 1; } @@ -2543,7 +2542,7 @@ static int gmc_v9_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v9_0_is_idle(void *handle) +static bool gmc_v9_0_is_idle(struct amdgpu_ip_block *ip_block) { /* MC is always ready in GMC v9.*/ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c index 8ac3d3282268..1317ede131b6 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c @@ -335,9 +335,9 @@ static int iceland_ih_resume(struct amdgpu_ip_block *ip_block) return iceland_ih_hw_init(ip_block); } -static bool iceland_ih_is_idle(void *handle) +static bool iceland_ih_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); if (REG_GET_FIELD(tmp, SRBM_STATUS, IH_BUSY)) diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c index 7198ddfaa8f4..eb4185dcbd1d 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c @@ -652,7 +652,7 @@ static int ih_v6_0_resume(struct amdgpu_ip_block *ip_block) return ih_v6_0_hw_init(ip_block); } -static bool ih_v6_0_is_idle(void *handle) +static bool ih_v6_0_is_idle(struct amdgpu_ip_block *ip_block) { /* todo */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c index 342b166c136d..068ed849dbad 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c @@ -631,7 +631,7 @@ static int ih_v6_1_resume(struct amdgpu_ip_block *ip_block) return ih_v6_1_hw_init(ip_block); } -static bool ih_v6_1_is_idle(void *handle) +static bool ih_v6_1_is_idle(struct amdgpu_ip_block *ip_block) { /* todo */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c index 71c1c77035e0..40a3530e0453 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c @@ -621,7 +621,7 @@ static int ih_v7_0_resume(struct amdgpu_ip_block *ip_block) return ih_v7_0_hw_init(ip_block); } -static bool ih_v7_0_is_idle(void *handle) +static bool ih_v7_0_is_idle(struct amdgpu_ip_block *ip_block) { /* todo */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.c index 964c29ef25dc..0027a639c7e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.c @@ -50,26 +50,29 @@ static int isp_v4_1_0_hw_init(struct amdgpu_isp *isp) isp_base = adev->rmmio_base; - isp->isp_cell = kcalloc(2, sizeof(struct mfd_cell), GFP_KERNEL); + isp->isp_cell = kcalloc(3, sizeof(struct mfd_cell), GFP_KERNEL); if (!isp->isp_cell) { r = -ENOMEM; - DRM_ERROR("%s: isp mfd cell alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp mfd cell alloc failed\n", __func__); goto failure; } - num_res = MAX_ISP410_MEM_RES + MAX_ISP410_SENSOR_RES + MAX_ISP410_INT_SRC; + num_res = MAX_ISP410_MEM_RES + MAX_ISP410_INT_SRC; isp->isp_res = kcalloc(num_res, sizeof(struct resource), GFP_KERNEL); if (!isp->isp_res) { r = -ENOMEM; - DRM_ERROR("%s: isp mfd res alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp mfd res alloc failed\n", __func__); goto failure; } isp->isp_pdata = kzalloc(sizeof(*isp->isp_pdata), GFP_KERNEL); if (!isp->isp_pdata) { r = -ENOMEM; - DRM_ERROR("%s: isp platform data alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp platform data alloc failed\n", __func__); goto failure; } @@ -88,14 +91,7 @@ static int isp_v4_1_0_hw_init(struct amdgpu_isp *isp) isp->isp_res[1].start = isp_base + ISP410_PHY0_OFFSET; isp->isp_res[1].end = isp_base + ISP410_PHY0_OFFSET + ISP410_PHY0_SIZE; - isp->isp_res[2].name = "isp_gpio_sensor0_reg"; - isp->isp_res[2].flags = IORESOURCE_MEM; - isp->isp_res[2].start = isp_base + ISP410_GPIO_SENSOR0_OFFSET; - isp->isp_res[2].end = isp_base + ISP410_GPIO_SENSOR0_OFFSET + - ISP410_GPIO_SENSOR0_SIZE; - - for (idx = MAX_ISP410_MEM_RES + MAX_ISP410_SENSOR_RES, int_idx = 0; - idx < num_res; idx++, int_idx++) { + for (idx = MAX_ISP410_MEM_RES, int_idx = 0; idx < num_res; idx++, int_idx++) { isp->isp_res[idx].name = "isp_4_1_0_irq"; isp->isp_res[idx].flags = IORESOURCE_IRQ; isp->isp_res[idx].start = @@ -110,11 +106,12 @@ static int isp_v4_1_0_hw_init(struct amdgpu_isp *isp) isp->isp_cell[0].platform_data = isp->isp_pdata; isp->isp_cell[0].pdata_size = sizeof(struct isp_platform_data); - isp->isp_i2c_res = kcalloc(1, sizeof(struct resource), - GFP_KERNEL); + /* initialize isp i2c platform data */ + isp->isp_i2c_res = kcalloc(1, sizeof(struct resource), GFP_KERNEL); if (!isp->isp_i2c_res) { r = -ENOMEM; - DRM_ERROR("%s: isp mfd res alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp mfd res alloc failed\n", __func__); goto failure; } @@ -129,9 +126,31 @@ static int isp_v4_1_0_hw_init(struct amdgpu_isp *isp) isp->isp_cell[1].platform_data = isp->isp_pdata; isp->isp_cell[1].pdata_size = sizeof(struct isp_platform_data); - r = mfd_add_hotplug_devices(isp->parent, isp->isp_cell, 2); + /* initialize isp gpiochip platform data */ + isp->isp_gpio_res = kcalloc(1, sizeof(struct resource), GFP_KERNEL); + if (!isp->isp_gpio_res) { + r = -ENOMEM; + drm_err(&adev->ddev, + "%s: isp gpio res alloc failed\n", __func__); + goto failure; + } + + isp->isp_gpio_res[0].name = "isp_gpio_reg"; + isp->isp_gpio_res[0].flags = IORESOURCE_MEM; + isp->isp_gpio_res[0].start = isp_base + ISP410_GPIO_SENSOR_OFFSET; + isp->isp_gpio_res[0].end = isp_base + ISP410_GPIO_SENSOR_OFFSET + + ISP410_GPIO_SENSOR_SIZE; + + isp->isp_cell[2].name = "amdisp-pinctrl"; + isp->isp_cell[2].num_resources = 1; + isp->isp_cell[2].resources = &isp->isp_gpio_res[0]; + isp->isp_cell[2].platform_data = isp->isp_pdata; + isp->isp_cell[2].pdata_size = sizeof(struct isp_platform_data); + + r = mfd_add_hotplug_devices(isp->parent, isp->isp_cell, 3); if (r) { - DRM_ERROR("%s: add mfd hotplug device failed\n", __func__); + drm_err(&adev->ddev, + "%s: add mfd hotplug device failed\n", __func__); goto failure; } @@ -143,6 +162,7 @@ failure: kfree(isp->isp_res); kfree(isp->isp_cell); kfree(isp->isp_i2c_res); + kfree(isp->isp_gpio_res); return r; } @@ -155,6 +175,7 @@ static int isp_v4_1_0_hw_fini(struct amdgpu_isp *isp) kfree(isp->isp_cell); kfree(isp->isp_pdata); kfree(isp->isp_i2c_res); + kfree(isp->isp_gpio_res); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.h b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.h index 7db24c0f1080..4d239198edd0 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.h +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.h @@ -42,8 +42,8 @@ #define ISP410_I2C0_OFFSET 0x66400 #define ISP410_I2C0_SIZE 0x100 -#define ISP410_GPIO_SENSOR0_OFFSET 0x6613C -#define ISP410_GPIO_SENSOR0_SIZE 0x4 +#define ISP410_GPIO_SENSOR_OFFSET 0x6613C +#define ISP410_GPIO_SENSOR_SIZE 0x54 void isp_v4_1_0_set_isp_funcs(struct amdgpu_isp *isp); diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c index b56f27295468..69dd92f6e86d 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c @@ -50,27 +50,30 @@ static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp) isp_base = adev->rmmio_base; - isp->isp_cell = kcalloc(2, sizeof(struct mfd_cell), GFP_KERNEL); + isp->isp_cell = kcalloc(3, sizeof(struct mfd_cell), GFP_KERNEL); if (!isp->isp_cell) { r = -ENOMEM; - DRM_ERROR("%s: isp mfd cell alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp mfd cell alloc failed\n", __func__); goto failure; } - num_res = MAX_ISP411_MEM_RES + MAX_ISP411_SENSOR_RES + MAX_ISP411_INT_SRC; + num_res = MAX_ISP411_MEM_RES + MAX_ISP411_INT_SRC; isp->isp_res = kcalloc(num_res, sizeof(struct resource), GFP_KERNEL); if (!isp->isp_res) { r = -ENOMEM; - DRM_ERROR("%s: isp mfd res alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp mfd res alloc failed\n", __func__); goto failure; } isp->isp_pdata = kzalloc(sizeof(*isp->isp_pdata), GFP_KERNEL); if (!isp->isp_pdata) { r = -ENOMEM; - DRM_ERROR("%s: isp platform data alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp platform data alloc failed\n", __func__); goto failure; } @@ -89,14 +92,7 @@ static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp) isp->isp_res[1].start = isp_base + ISP411_PHY0_OFFSET; isp->isp_res[1].end = isp_base + ISP411_PHY0_OFFSET + ISP411_PHY0_SIZE; - isp->isp_res[2].name = "isp_4_1_1_sensor0_reg"; - isp->isp_res[2].flags = IORESOURCE_MEM; - isp->isp_res[2].start = isp_base + ISP411_GPIO_SENSOR0_OFFSET; - isp->isp_res[2].end = isp_base + ISP411_GPIO_SENSOR0_OFFSET + - ISP411_GPIO_SENSOR0_SIZE; - - for (idx = MAX_ISP411_MEM_RES + MAX_ISP411_SENSOR_RES, int_idx = 0; - idx < num_res; idx++, int_idx++) { + for (idx = MAX_ISP411_MEM_RES, int_idx = 0; idx < num_res; idx++, int_idx++) { isp->isp_res[idx].name = "isp_4_1_1_irq"; isp->isp_res[idx].flags = IORESOURCE_IRQ; isp->isp_res[idx].start = @@ -111,10 +107,12 @@ static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp) isp->isp_cell[0].platform_data = isp->isp_pdata; isp->isp_cell[0].pdata_size = sizeof(struct isp_platform_data); + /* initialize isp i2c platform data */ isp->isp_i2c_res = kcalloc(1, sizeof(struct resource), GFP_KERNEL); if (!isp->isp_i2c_res) { r = -ENOMEM; - DRM_ERROR("%s: isp mfd res alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp mfd res alloc failed\n", __func__); goto failure; } @@ -129,9 +127,31 @@ static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp) isp->isp_cell[1].platform_data = isp->isp_pdata; isp->isp_cell[1].pdata_size = sizeof(struct isp_platform_data); - r = mfd_add_hotplug_devices(isp->parent, isp->isp_cell, 2); + /* initialize isp gpiochip platform data */ + isp->isp_gpio_res = kcalloc(1, sizeof(struct resource), GFP_KERNEL); + if (!isp->isp_gpio_res) { + r = -ENOMEM; + drm_err(&adev->ddev, + "%s: isp gpio res alloc failed\n", __func__); + goto failure; + } + + isp->isp_gpio_res[0].name = "isp_gpio_reg"; + isp->isp_gpio_res[0].flags = IORESOURCE_MEM; + isp->isp_gpio_res[0].start = isp_base + ISP411_GPIO_SENSOR_OFFSET; + isp->isp_gpio_res[0].end = isp_base + ISP411_GPIO_SENSOR_OFFSET + + ISP411_GPIO_SENSOR_SIZE; + + isp->isp_cell[2].name = "amdisp-pinctrl"; + isp->isp_cell[2].num_resources = 1; + isp->isp_cell[2].resources = &isp->isp_gpio_res[0]; + isp->isp_cell[2].platform_data = isp->isp_pdata; + isp->isp_cell[2].pdata_size = sizeof(struct isp_platform_data); + + r = mfd_add_hotplug_devices(isp->parent, isp->isp_cell, 3); if (r) { - DRM_ERROR("%s: add mfd hotplug device failed\n", __func__); + drm_err(&adev->ddev, + "%s: add mfd hotplug device failed\n", __func__); goto failure; } @@ -143,6 +163,7 @@ failure: kfree(isp->isp_res); kfree(isp->isp_cell); kfree(isp->isp_i2c_res); + kfree(isp->isp_gpio_res); return r; } @@ -155,6 +176,7 @@ static int isp_v4_1_1_hw_fini(struct amdgpu_isp *isp) kfree(isp->isp_cell); kfree(isp->isp_pdata); kfree(isp->isp_i2c_res); + kfree(isp->isp_gpio_res); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.h b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.h index 40887ddeb08c..fe45d70d87f1 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.h +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.h @@ -33,7 +33,6 @@ #include "ivsrcid/isp/irqsrcs_isp_4_1.h" #define MAX_ISP411_MEM_RES 2 -#define MAX_ISP411_SENSOR_RES 1 #define MAX_ISP411_INT_SRC 8 #define ISP411_PHY0_OFFSET 0x66700 @@ -42,8 +41,8 @@ #define ISP411_I2C0_OFFSET 0x66400 #define ISP411_I2C0_SIZE 0x100 -#define ISP411_GPIO_SENSOR0_OFFSET 0x6613C -#define ISP411_GPIO_SENSOR0_SIZE 0x4 +#define ISP411_GPIO_SENSOR_OFFSET 0x6613C +#define ISP411_GPIO_SENSOR_SIZE 0x54 void isp_v4_1_1_set_isp_funcs(struct amdgpu_isp *isp); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c index 03b8b7cd5229..9e428e669ada 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c @@ -604,15 +604,15 @@ static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev) static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work); + bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.inst[0].idle_work); int cnt = 0; - mutex_lock(&adev->vcn.vcn1_jpeg1_workaround); + mutex_lock(&adev->vcn.inst[0].vcn1_jpeg1_workaround); if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_dec)) DRM_ERROR("JPEG dec: vcn dec ring may not be empty\n"); - for (cnt = 0; cnt < adev->vcn.num_enc_rings; cnt++) { + for (cnt = 0; cnt < adev->vcn.inst[0].num_enc_rings; cnt++) { if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_enc[cnt])) DRM_ERROR("JPEG dec: vcn enc ring[%d] may not be empty\n", cnt); } diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index 75843a0e3bfb..4cde8a8bcc83 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -680,9 +680,9 @@ void jpeg_v2_0_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count) } } -static bool jpeg_v2_0_is_idle(void *handle) +static bool jpeg_v2_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return ((RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS) & UVD_JRBC_STATUS__RB_JOB_DONE_MASK) == @@ -707,7 +707,7 @@ static int jpeg_v2_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, bool enable = (state == AMD_CG_STATE_GATE); if (enable) { - if (!jpeg_v2_0_is_idle(adev)) + if (!jpeg_v2_0_is_idle(ip_block)) return -EBUSY; jpeg_v2_0_enable_clock_gating(adev); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index 0a2c1dee2430..8b39e114f3be 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -515,9 +515,9 @@ static void jpeg_v2_6_dec_ring_insert_end(struct amdgpu_ring *ring) amdgpu_ring_write(ring, (1 << (ring->me * 2 + 14))); } -static bool jpeg_v2_5_is_idle(void *handle) +static bool jpeg_v2_5_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { @@ -563,7 +563,7 @@ static int jpeg_v2_5_set_clockgating_state(struct amdgpu_ip_block *ip_block, continue; if (enable) { - if (!jpeg_v2_5_is_idle(adev)) + if (!jpeg_v2_5_is_idle(ip_block)) return -EBUSY; jpeg_v2_5_enable_clock_gating(adev, i); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c index 9faa9c6809df..2f8510c2986b 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c @@ -470,9 +470,9 @@ static void jpeg_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring) } } -static bool jpeg_v3_0_is_idle(void *handle) +static bool jpeg_v3_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int ret = 1; ret &= (((RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS) & @@ -498,7 +498,7 @@ static int jpeg_v3_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, bool enable = state == AMD_CG_STATE_GATE; if (enable) { - if (!jpeg_v3_0_is_idle(adev)) + if (!jpeg_v3_0_is_idle(ip_block)) return -EBUSY; jpeg_v3_0_enable_clock_gating(adev); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c index 292d4a234ea6..f17ec5414fd6 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c @@ -630,9 +630,9 @@ static void jpeg_v4_0_dec_ring_set_wptr(struct amdgpu_ring *ring) } } -static bool jpeg_v4_0_is_idle(void *handle) +static bool jpeg_v4_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int ret = 1; ret &= (((RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS) & @@ -658,7 +658,7 @@ static int jpeg_v4_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, bool enable = state == AMD_CG_STATE_GATE; if (enable) { - if (!jpeg_v4_0_is_idle(adev)) + if (!jpeg_v4_0_is_idle(ip_block)) return -EBUSY; jpeg_v4_0_enable_clock_gating(adev); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c index 0588bb80f41e..5598a35f72af 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c @@ -634,12 +634,6 @@ static void jpeg_v4_0_3_stop_inst(struct amdgpu_device *adev, int inst) UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK, ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK); - WREG32_SOC15(JPEG, jpeg_inst, regUVD_PGFSM_CONFIG, - 2 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT); - SOC15_WAIT_ON_RREG(JPEG, jpeg_inst, regUVD_PGFSM_STATUS, - UVD_PGFSM_STATUS__UVDJ_PWR_OFF << - UVD_PGFSM_STATUS__UVDJ_PWR_STATUS__SHIFT, - UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK); } /** @@ -692,7 +686,7 @@ static uint64_t jpeg_v4_0_3_dec_ring_get_wptr(struct amdgpu_ring *ring) jpeg_v4_0_3_core_reg_offset(ring->pipe)); } -static void jpeg_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring) +void jpeg_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring) { /* JPEG engine access for HDP flush doesn't work when RRMT is enabled. * This is a workaround to avoid any HDP flush through JPEG ring. @@ -960,9 +954,9 @@ void jpeg_v4_0_3_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count) } } -static bool jpeg_v4_0_3_is_idle(void *handle) +static bool jpeg_v4_0_3_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; bool ret = false; int i, j; @@ -1004,7 +998,7 @@ static int jpeg_v4_0_3_set_clockgating_state(struct amdgpu_ip_block *ip_block, for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { if (enable) { - if (!jpeg_v4_0_3_is_idle(adev)) + if (!jpeg_v4_0_3_is_idle(ip_block)) return -EBUSY; jpeg_v4_0_3_enable_clock_gating(adev, i); } else { @@ -1110,24 +1104,20 @@ static void jpeg_v4_0_3_core_stall_reset(struct amdgpu_ring *ring) WREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JMI0_UVD_JMI_CLIENT_STALL, reg_offset, 0x1F); - SOC15_WAIT_ON_RREG(JPEG, jpeg_inst, - regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS, - 0x1F, 0x1F); + SOC15_WAIT_ON_RREG_OFFSET(JPEG, jpeg_inst, + regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS, + reg_offset, 0x1F, 0x1F); WREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JMI0_JPEG_LMI_DROP, reg_offset, 0x1F); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regJPEG_CORE_RST_CTRL, - reg_offset, 1 << ring->pipe); + WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 1 << ring->pipe); WREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JMI0_UVD_JMI_CLIENT_STALL, reg_offset, 0x00); WREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JMI0_JPEG_LMI_DROP, reg_offset, 0x00); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regJPEG_CORE_RST_CTRL, - reg_offset, 0x00); + WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 0x00); } static int jpeg_v4_0_3_ring_reset(struct amdgpu_ring *ring, unsigned int vmid) @@ -1338,8 +1328,8 @@ static int jpeg_v4_0_3_aca_bank_parser(struct aca_handle *handle, struct aca_ban 1ULL); break; case ACA_SMU_TYPE_CE: - bank->aca_err_type = ACA_ERROR_TYPE_CE; - ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE, + bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank); + ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, ACA_REG__MISC0__ERRCNT(misc0)); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h index 747a3e5f6856..a90bf370a002 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h @@ -56,6 +56,7 @@ void jpeg_v4_0_3_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq unsigned int flags); void jpeg_v4_0_3_dec_ring_emit_vm_flush(struct amdgpu_ring *ring, unsigned int vmid, uint64_t pd_addr); +void jpeg_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring); void jpeg_v4_0_3_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count); void jpeg_v4_0_3_dec_ring_insert_start(struct amdgpu_ring *ring); void jpeg_v4_0_3_dec_ring_insert_end(struct amdgpu_ring *ring); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c index cbba1d9e8367..974030a5c03c 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c @@ -648,9 +648,9 @@ static void jpeg_v4_0_5_dec_ring_set_wptr(struct amdgpu_ring *ring) } } -static bool jpeg_v4_0_5_is_idle(void *handle) +static bool jpeg_v4_0_5_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { @@ -693,7 +693,7 @@ static int jpeg_v4_0_5_set_clockgating_state(struct amdgpu_ip_block *ip_block, continue; if (enable) { - if (!jpeg_v4_0_5_is_idle(adev)) + if (!jpeg_v4_0_5_is_idle(ip_block)) return -EBUSY; jpeg_v4_0_5_enable_clock_gating(adev, i); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c index 4a55e0cf39e4..31d213ccbe0a 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c @@ -559,9 +559,9 @@ static void jpeg_v5_0_0_dec_ring_set_wptr(struct amdgpu_ring *ring) } } -static bool jpeg_v5_0_0_is_idle(void *handle) +static bool jpeg_v5_0_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int ret = 1; ret &= (((RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS) & @@ -587,7 +587,7 @@ static int jpeg_v5_0_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, bool enable = (state == AMD_CG_STATE_GATE) ? true : false; if (enable) { - if (!jpeg_v5_0_0_is_idle(adev)) + if (!jpeg_v5_0_0_is_idle(ip_block)) return -EBUSY; jpeg_v5_0_0_enable_clock_gating(adev); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c index 6e3f522e9133..218e16b68f1d 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c @@ -190,6 +190,13 @@ static int jpeg_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; + if (!amdgpu_sriov_vf(adev)) { + adev->jpeg.supported_reset = AMDGPU_RESET_TYPE_PER_QUEUE; + r = amdgpu_jpeg_sysfs_reset_mask_init(adev); + if (r) + return r; + } + return 0; } @@ -209,6 +216,9 @@ static int jpeg_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block) if (r) return r; + if (!amdgpu_sriov_vf(adev)) + amdgpu_jpeg_sysfs_reset_mask_fini(adev); + r = amdgpu_jpeg_sw_fini(adev); return r; @@ -239,6 +249,9 @@ static int jpeg_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block) } return 0; } + if (RREG32_SOC15(VCN, GET_INST(VCN, 0), regVCN_RRMT_CNTL) & 0x100) + adev->jpeg.caps |= AMDGPU_JPEG_CAPS(RRMT_ENABLED); + for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { jpeg_inst = GET_INST(JPEG, i); ring = adev->jpeg.inst[i].ring_dec; @@ -326,11 +339,10 @@ static int jpeg_v5_0_1_resume(struct amdgpu_ip_block *ip_block) return r; } -static int jpeg_v5_0_1_disable_antihang(struct amdgpu_device *adev, int inst_idx) +static void jpeg_v5_0_1_init_inst(struct amdgpu_device *adev, int i) { - int jpeg_inst; + int jpeg_inst = GET_INST(JPEG, i); - jpeg_inst = GET_INST(JPEG, inst_idx); /* disable anti hang mechanism */ WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JPEG_POWER_STATUS), 0, ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK); @@ -339,20 +351,75 @@ static int jpeg_v5_0_1_disable_antihang(struct amdgpu_device *adev, int inst_idx WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JPEG_POWER_STATUS), 0, ~UVD_JPEG_POWER_STATUS__JPEG_PG_MODE_MASK); - return 0; + /* MJPEG global tiling registers */ + WREG32_SOC15(JPEG, 0, regJPEG_DEC_GFX10_ADDR_CONFIG, + adev->gfx.config.gb_addr_config); + + /* enable JMI channel */ + WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL), 0, + ~UVD_JMI_CNTL__SOFT_RESET_MASK); } -static int jpeg_v5_0_1_enable_antihang(struct amdgpu_device *adev, int inst_idx) +static void jpeg_v5_0_1_deinit_inst(struct amdgpu_device *adev, int i) { - int jpeg_inst; + int jpeg_inst = GET_INST(JPEG, i); + /* reset JMI */ + WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL), + UVD_JMI_CNTL__SOFT_RESET_MASK, + ~UVD_JMI_CNTL__SOFT_RESET_MASK); - jpeg_inst = GET_INST(JPEG, inst_idx); /* enable anti hang mechanism */ WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JPEG_POWER_STATUS), UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK, - ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK); + ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK); +} - return 0; +static void jpeg_v5_0_1_init_jrbc(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + u32 reg, data, mask; + int jpeg_inst = GET_INST(JPEG, ring->me); + int reg_offset = ring->pipe ? jpeg_v5_0_1_core_reg_offset(ring->pipe) : 0; + + /* enable System Interrupt for JRBC */ + reg = SOC15_REG_OFFSET(JPEG, jpeg_inst, regJPEG_SYS_INT_EN); + if (ring->pipe < AMDGPU_MAX_JPEG_RINGS_4_0_3) { + data = JPEG_SYS_INT_EN__DJRBC0_MASK << ring->pipe; + mask = ~(JPEG_SYS_INT_EN__DJRBC0_MASK << ring->pipe); + WREG32_P(reg, data, mask); + } else { + data = JPEG_SYS_INT_EN__DJRBC0_MASK << (ring->pipe+12); + mask = ~(JPEG_SYS_INT_EN__DJRBC0_MASK << (ring->pipe+12)); + WREG32_P(reg, data, mask); + } + + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_LMI_JRBC_RB_VMID, + reg_offset, 0); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JRBC_RB_CNTL, + reg_offset, + (0x00000001L | 0x00000002L)); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_LMI_JRBC_RB_64BIT_BAR_LOW, + reg_offset, lower_32_bits(ring->gpu_addr)); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, + reg_offset, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JRBC_RB_RPTR, + reg_offset, 0); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JRBC_RB_WPTR, + reg_offset, 0); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JRBC_RB_CNTL, + reg_offset, 0x00000002L); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JRBC_RB_SIZE, + reg_offset, ring->ring_size / 4); + ring->wptr = RREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JRBC_RB_WPTR, + reg_offset); } /** @@ -365,69 +432,13 @@ static int jpeg_v5_0_1_enable_antihang(struct amdgpu_device *adev, int inst_idx) static int jpeg_v5_0_1_start(struct amdgpu_device *adev) { struct amdgpu_ring *ring; - int i, j, jpeg_inst, r; + int i, j; for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { - jpeg_inst = GET_INST(JPEG, i); - - /* disable antihang */ - r = jpeg_v5_0_1_disable_antihang(adev, i); - if (r) - return r; - - /* MJPEG global tiling registers */ - WREG32_SOC15(JPEG, 0, regJPEG_DEC_GFX10_ADDR_CONFIG, - adev->gfx.config.gb_addr_config); - - /* enable JMI channel */ - WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL), 0, - ~UVD_JMI_CNTL__SOFT_RESET_MASK); - + jpeg_v5_0_1_init_inst(adev, i); for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j) { - int reg_offset = (j ? jpeg_v5_0_1_core_reg_offset(j) : 0); - u32 reg, data, mask; - ring = &adev->jpeg.inst[i].ring_dec[j]; - - /* enable System Interrupt for JRBC */ - reg = SOC15_REG_OFFSET(JPEG, jpeg_inst, regJPEG_SYS_INT_EN); - if (j < AMDGPU_MAX_JPEG_RINGS_4_0_3) { - data = JPEG_SYS_INT_EN__DJRBC0_MASK << j; - mask = ~(JPEG_SYS_INT_EN__DJRBC0_MASK << j); - WREG32_P(reg, data, mask); - } else { - data = JPEG_SYS_INT_EN__DJRBC0_MASK << (j+12); - mask = ~(JPEG_SYS_INT_EN__DJRBC0_MASK << (j+12)); - WREG32_P(reg, data, mask); - } - - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_LMI_JRBC_RB_VMID, - reg_offset, 0); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_JRBC_RB_CNTL, - reg_offset, - (0x00000001L | 0x00000002L)); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_LMI_JRBC_RB_64BIT_BAR_LOW, - reg_offset, lower_32_bits(ring->gpu_addr)); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, - reg_offset, upper_32_bits(ring->gpu_addr)); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_JRBC_RB_RPTR, - reg_offset, 0); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_JRBC_RB_WPTR, - reg_offset, 0); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_JRBC_RB_CNTL, - reg_offset, 0x00000002L); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_JRBC_RB_SIZE, - reg_offset, ring->ring_size / 4); - ring->wptr = RREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JRBC_RB_WPTR, - reg_offset); + jpeg_v5_0_1_init_jrbc(ring); } } @@ -443,20 +454,10 @@ static int jpeg_v5_0_1_start(struct amdgpu_device *adev) */ static int jpeg_v5_0_1_stop(struct amdgpu_device *adev) { - int i, jpeg_inst, r; - - for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { - jpeg_inst = GET_INST(JPEG, i); - /* reset JMI */ - WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL), - UVD_JMI_CNTL__SOFT_RESET_MASK, - ~UVD_JMI_CNTL__SOFT_RESET_MASK); + int i; - /* enable antihang */ - r = jpeg_v5_0_1_enable_antihang(adev, i); - if (r) - return r; - } + for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) + jpeg_v5_0_1_deinit_inst(adev, i); return 0; } @@ -516,9 +517,9 @@ static void jpeg_v5_0_1_dec_ring_set_wptr(struct amdgpu_ring *ring) } } -static bool jpeg_v5_0_1_is_idle(void *handle) +static bool jpeg_v5_0_1_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; bool ret = false; int i, j; @@ -567,7 +568,7 @@ static int jpeg_v5_0_1_set_clockgating_state(struct amdgpu_ip_block *ip_block, return 0; for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { - if (!jpeg_v5_0_1_is_idle(adev)) + if (!jpeg_v5_0_1_is_idle(ip_block)) return -EBUSY; } @@ -662,6 +663,41 @@ static int jpeg_v5_0_1_process_interrupt(struct amdgpu_device *adev, return 0; } +static void jpeg_v5_0_1_core_stall_reset(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + int jpeg_inst = GET_INST(JPEG, ring->me); + int reg_offset = ring->pipe ? jpeg_v5_0_1_core_reg_offset(ring->pipe) : 0; + + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JMI0_UVD_JMI_CLIENT_STALL, + reg_offset, 0x1F); + SOC15_WAIT_ON_RREG_OFFSET(JPEG, jpeg_inst, + regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS, + reg_offset, 0x1F, 0x1F); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JMI0_JPEG_LMI_DROP, + reg_offset, 0x1F); + WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 1 << ring->pipe); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JMI0_UVD_JMI_CLIENT_STALL, + reg_offset, 0x00); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JMI0_JPEG_LMI_DROP, + reg_offset, 0x00); + WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 0x00); +} + +static int jpeg_v5_0_1_ring_reset(struct amdgpu_ring *ring, unsigned int vmid) +{ + if (amdgpu_sriov_vf(ring->adev)) + return -EOPNOTSUPP; + + jpeg_v5_0_1_core_stall_reset(ring); + jpeg_v5_0_1_init_jrbc(ring); + return amdgpu_ring_test_helper(ring); +} + static const struct amd_ip_funcs jpeg_v5_0_1_ip_funcs = { .name = "jpeg_v5_0_1", .early_init = jpeg_v5_0_1_early_init, @@ -700,6 +736,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_1_dec_ring_vm_funcs = { .emit_ib = jpeg_v4_0_3_dec_ring_emit_ib, .emit_fence = jpeg_v4_0_3_dec_ring_emit_fence, .emit_vm_flush = jpeg_v4_0_3_dec_ring_emit_vm_flush, + .emit_hdp_flush = jpeg_v4_0_3_ring_emit_hdp_flush, .test_ring = amdgpu_jpeg_dec_ring_test_ring, .test_ib = amdgpu_jpeg_dec_ring_test_ib, .insert_nop = jpeg_v4_0_3_dec_ring_nop, @@ -711,6 +748,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_1_dec_ring_vm_funcs = { .emit_wreg = jpeg_v4_0_3_dec_ring_emit_wreg, .emit_reg_wait = jpeg_v4_0_3_dec_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, + .reset = jpeg_v5_0_1_ring_reset, }; static void jpeg_v5_0_1_set_dec_ring_funcs(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.h index 9de3272ef47f..efdab57324e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.h @@ -26,65 +26,76 @@ extern const struct amdgpu_ip_block_version jpeg_v5_0_1_ip_block; -#define regUVD_JRBC0_UVD_JRBC_RB_WPTR 0x0640 -#define regUVD_JRBC0_UVD_JRBC_RB_WPTR_BASE_IDX 1 -#define regUVD_JRBC0_UVD_JRBC_STATUS 0x0649 -#define regUVD_JRBC0_UVD_JRBC_STATUS_BASE_IDX 1 -#define regUVD_JRBC0_UVD_JRBC_RB_RPTR 0x064a -#define regUVD_JRBC0_UVD_JRBC_RB_RPTR_BASE_IDX 1 -#define regUVD_JRBC1_UVD_JRBC_RB_WPTR 0x0000 -#define regUVD_JRBC1_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC1_UVD_JRBC_STATUS 0x0009 -#define regUVD_JRBC1_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC1_UVD_JRBC_RB_RPTR 0x000a -#define regUVD_JRBC1_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC2_UVD_JRBC_RB_WPTR 0x0040 -#define regUVD_JRBC2_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC2_UVD_JRBC_STATUS 0x0049 -#define regUVD_JRBC2_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC2_UVD_JRBC_RB_RPTR 0x004a -#define regUVD_JRBC2_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC3_UVD_JRBC_RB_WPTR 0x0080 -#define regUVD_JRBC3_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC3_UVD_JRBC_STATUS 0x0089 -#define regUVD_JRBC3_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC3_UVD_JRBC_RB_RPTR 0x008a -#define regUVD_JRBC3_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC4_UVD_JRBC_RB_WPTR 0x00c0 -#define regUVD_JRBC4_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC4_UVD_JRBC_STATUS 0x00c9 -#define regUVD_JRBC4_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC4_UVD_JRBC_RB_RPTR 0x00ca -#define regUVD_JRBC4_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC5_UVD_JRBC_RB_WPTR 0x0100 -#define regUVD_JRBC5_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC5_UVD_JRBC_STATUS 0x0109 -#define regUVD_JRBC5_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC5_UVD_JRBC_RB_RPTR 0x010a -#define regUVD_JRBC5_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC6_UVD_JRBC_RB_WPTR 0x0140 -#define regUVD_JRBC6_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC6_UVD_JRBC_STATUS 0x0149 -#define regUVD_JRBC6_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC6_UVD_JRBC_RB_RPTR 0x014a -#define regUVD_JRBC6_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC7_UVD_JRBC_RB_WPTR 0x0180 -#define regUVD_JRBC7_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC7_UVD_JRBC_STATUS 0x0189 -#define regUVD_JRBC7_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC7_UVD_JRBC_RB_RPTR 0x018a -#define regUVD_JRBC7_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC8_UVD_JRBC_RB_WPTR 0x01c0 -#define regUVD_JRBC8_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC8_UVD_JRBC_STATUS 0x01c9 -#define regUVD_JRBC8_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC8_UVD_JRBC_RB_RPTR 0x01ca -#define regUVD_JRBC8_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC9_UVD_JRBC_RB_WPTR 0x0440 -#define regUVD_JRBC9_UVD_JRBC_RB_WPTR_BASE_IDX 1 -#define regUVD_JRBC9_UVD_JRBC_STATUS 0x0449 -#define regUVD_JRBC9_UVD_JRBC_STATUS_BASE_IDX 1 -#define regUVD_JRBC9_UVD_JRBC_RB_RPTR 0x044a -#define regUVD_JRBC9_UVD_JRBC_RB_RPTR_BASE_IDX 1 +#define regUVD_JRBC0_UVD_JRBC_RB_WPTR 0x0640 +#define regUVD_JRBC0_UVD_JRBC_RB_WPTR_BASE_IDX 1 +#define regUVD_JRBC0_UVD_JRBC_STATUS 0x0649 +#define regUVD_JRBC0_UVD_JRBC_STATUS_BASE_IDX 1 +#define regUVD_JRBC0_UVD_JRBC_RB_RPTR 0x064a +#define regUVD_JRBC0_UVD_JRBC_RB_RPTR_BASE_IDX 1 +#define regUVD_JRBC1_UVD_JRBC_RB_WPTR 0x0000 +#define regUVD_JRBC1_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC1_UVD_JRBC_STATUS 0x0009 +#define regUVD_JRBC1_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC1_UVD_JRBC_RB_RPTR 0x000a +#define regUVD_JRBC1_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC2_UVD_JRBC_RB_WPTR 0x0040 +#define regUVD_JRBC2_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC2_UVD_JRBC_STATUS 0x0049 +#define regUVD_JRBC2_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC2_UVD_JRBC_RB_RPTR 0x004a +#define regUVD_JRBC2_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC3_UVD_JRBC_RB_WPTR 0x0080 +#define regUVD_JRBC3_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC3_UVD_JRBC_STATUS 0x0089 +#define regUVD_JRBC3_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC3_UVD_JRBC_RB_RPTR 0x008a +#define regUVD_JRBC3_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC4_UVD_JRBC_RB_WPTR 0x00c0 +#define regUVD_JRBC4_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC4_UVD_JRBC_STATUS 0x00c9 +#define regUVD_JRBC4_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC4_UVD_JRBC_RB_RPTR 0x00ca +#define regUVD_JRBC4_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC5_UVD_JRBC_RB_WPTR 0x0100 +#define regUVD_JRBC5_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC5_UVD_JRBC_STATUS 0x0109 +#define regUVD_JRBC5_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC5_UVD_JRBC_RB_RPTR 0x010a +#define regUVD_JRBC5_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC6_UVD_JRBC_RB_WPTR 0x0140 +#define regUVD_JRBC6_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC6_UVD_JRBC_STATUS 0x0149 +#define regUVD_JRBC6_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC6_UVD_JRBC_RB_RPTR 0x014a +#define regUVD_JRBC6_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC7_UVD_JRBC_RB_WPTR 0x0180 +#define regUVD_JRBC7_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC7_UVD_JRBC_STATUS 0x0189 +#define regUVD_JRBC7_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC7_UVD_JRBC_RB_RPTR 0x018a +#define regUVD_JRBC7_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC8_UVD_JRBC_RB_WPTR 0x01c0 +#define regUVD_JRBC8_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC8_UVD_JRBC_STATUS 0x01c9 +#define regUVD_JRBC8_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC8_UVD_JRBC_RB_RPTR 0x01ca +#define regUVD_JRBC8_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC9_UVD_JRBC_RB_WPTR 0x0440 +#define regUVD_JRBC9_UVD_JRBC_RB_WPTR_BASE_IDX 1 +#define regUVD_JRBC9_UVD_JRBC_STATUS 0x0449 +#define regUVD_JRBC9_UVD_JRBC_STATUS_BASE_IDX 1 +#define regUVD_JRBC9_UVD_JRBC_RB_RPTR 0x044a +#define regUVD_JRBC9_UVD_JRBC_RB_RPTR_BASE_IDX 1 +#define regUVD_JMI0_JPEG_LMI_DROP 0x0663 +#define regUVD_JMI0_JPEG_LMI_DROP_BASE_IDX 1 +#define regUVD_JMI0_UVD_JMI_CLIENT_STALL 0x067a +#define regUVD_JMI0_UVD_JMI_CLIENT_STALL_BASE_IDX 1 +#define regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS 0x067b +#define regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS_BASE_IDX 1 +#define regJPEG_CORE_RST_CTRL 0x072e +#define regJPEG_CORE_RST_CTRL_BASE_IDX 1 -#endif /* __JPEG_V5_0_0_H__ */ +#define regVCN_RRMT_CNTL 0x0940 +#define regVCN_RRMT_CNTL_BASE_IDX 1 + +#endif /* __JPEG_V5_0_1_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 747b05d9b3cf..7eee41187b7c 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -800,7 +800,7 @@ static const struct amdgpu_mes_funcs mes_v11_0_funcs = { }; static int mes_v11_0_allocate_ucode_buffer(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r; const struct mes_firmware_header_v1_0 *mes_hdr; @@ -835,7 +835,7 @@ static int mes_v11_0_allocate_ucode_buffer(struct amdgpu_device *adev, } static int mes_v11_0_allocate_ucode_data_buffer(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r; const struct mes_firmware_header_v1_0 *mes_hdr; @@ -876,7 +876,7 @@ static int mes_v11_0_allocate_ucode_data_buffer(struct amdgpu_device *adev, } static void mes_v11_0_free_ucode_buffers(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { amdgpu_bo_free_kernel(&adev->mes.data_fw_obj[pipe], &adev->mes.data_fw_gpu_addr[pipe], @@ -974,7 +974,7 @@ static void mes_v11_0_enable(struct amdgpu_device *adev, bool enable) /* This function is for backdoor MES firmware */ static int mes_v11_0_load_microcode(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe, bool prime_icache) + enum amdgpu_mes_pipe pipe, bool prime_icache) { int r; uint32_t data; @@ -1046,7 +1046,7 @@ static int mes_v11_0_load_microcode(struct amdgpu_device *adev, } static int mes_v11_0_allocate_eop_buf(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r; u32 *eop; @@ -1257,7 +1257,7 @@ static int mes_v11_0_kiq_enable_queue(struct amdgpu_device *adev) } static int mes_v11_0_queue_init(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { struct amdgpu_ring *ring; int r; @@ -1340,7 +1340,7 @@ static int mes_v11_0_kiq_ring_init(struct amdgpu_device *adev) } static int mes_v11_0_mqd_sw_init(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r, mqd_size = sizeof(struct v11_compute_mqd); struct amdgpu_ring *ring; @@ -1647,6 +1647,10 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block) goto failure; } + r = amdgpu_mes_update_enforce_isolation(adev); + if (r) + goto failure; + out: /* * Disable KIQ ring usage from the driver once MES is enabled. @@ -1670,24 +1674,12 @@ static int mes_v11_0_hw_fini(struct amdgpu_ip_block *ip_block) static int mes_v11_0_suspend(struct amdgpu_ip_block *ip_block) { - int r; - - r = amdgpu_mes_suspend(ip_block->adev); - if (r) - return r; - return mes_v11_0_hw_fini(ip_block); } static int mes_v11_0_resume(struct amdgpu_ip_block *ip_block) { - int r; - - r = mes_v11_0_hw_init(ip_block); - if (r) - return r; - - return amdgpu_mes_resume(ip_block->adev); + return mes_v11_0_hw_init(ip_block); } static int mes_v11_0_early_init(struct amdgpu_ip_block *ip_block) diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index 8d7cf40030f2..fdc435b62012 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -901,7 +901,7 @@ static const struct amdgpu_mes_funcs mes_v12_0_funcs = { }; static int mes_v12_0_allocate_ucode_buffer(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r; const struct mes_firmware_header_v1_0 *mes_hdr; @@ -935,7 +935,7 @@ static int mes_v12_0_allocate_ucode_buffer(struct amdgpu_device *adev, } static int mes_v12_0_allocate_ucode_data_buffer(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r; const struct mes_firmware_header_v1_0 *mes_hdr; @@ -969,7 +969,7 @@ static int mes_v12_0_allocate_ucode_data_buffer(struct amdgpu_device *adev, } static void mes_v12_0_free_ucode_buffers(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { amdgpu_bo_free_kernel(&adev->mes.data_fw_obj[pipe], &adev->mes.data_fw_gpu_addr[pipe], @@ -1075,7 +1075,7 @@ static void mes_v12_0_set_ucode_start_addr(struct amdgpu_device *adev) /* This function is for backdoor MES firmware */ static int mes_v12_0_load_microcode(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe, bool prime_icache) + enum amdgpu_mes_pipe pipe, bool prime_icache) { int r; uint32_t data; @@ -1139,7 +1139,7 @@ static int mes_v12_0_load_microcode(struct amdgpu_device *adev, } static int mes_v12_0_allocate_eop_buf(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r; u32 *eop; @@ -1360,7 +1360,7 @@ static int mes_v12_0_kiq_enable_queue(struct amdgpu_device *adev) } static int mes_v12_0_queue_init(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { struct amdgpu_ring *ring; int r; @@ -1460,7 +1460,7 @@ static int mes_v12_0_kiq_ring_init(struct amdgpu_device *adev) } static int mes_v12_0_mqd_sw_init(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r, mqd_size = sizeof(struct v12_compute_mqd); struct amdgpu_ring *ring; @@ -1762,6 +1762,10 @@ static int mes_v12_0_hw_init(struct amdgpu_ip_block *ip_block) goto failure; } + r = amdgpu_mes_update_enforce_isolation(adev); + if (r) + goto failure; + out: /* * Disable KIQ ring usage from the driver once MES is enabled. @@ -1785,24 +1789,12 @@ static int mes_v12_0_hw_fini(struct amdgpu_ip_block *ip_block) static int mes_v12_0_suspend(struct amdgpu_ip_block *ip_block) { - int r; - - r = amdgpu_mes_suspend(ip_block->adev); - if (r) - return r; - return mes_v12_0_hw_fini(ip_block); } static int mes_v12_0_resume(struct amdgpu_ip_block *ip_block) { - int r; - - r = mes_v12_0_hw_init(ip_block); - if (r) - return r; - - return amdgpu_mes_resume(ip_block->adev); + return mes_v12_0_hw_init(ip_block); } static int mes_v12_0_early_init(struct amdgpu_ip_block *ip_block) diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c index 58d22f0d5a68..a54e7b929295 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c @@ -751,8 +751,8 @@ static int mmhub_v1_8_aca_bank_parser(struct aca_handle *handle, struct aca_bank 1ULL); break; case ACA_SMU_TYPE_CE: - bank->aca_err_type = ACA_ERROR_TYPE_CE; - ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE, + bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank); + ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, ACA_REG__MISC0__ERRCNT(misc0)); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index 4dcb72d1bdda..5aadf24cb202 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -184,6 +184,9 @@ send_request: case IDH_REQ_RAS_ERROR_COUNT: event = IDH_RAS_ERROR_COUNT_READY; break; + case IDH_REQ_RAS_CPER_DUMP: + event = IDH_RAS_CPER_DUMP_READY; + break; default: break; } @@ -467,6 +470,16 @@ static int xgpu_nv_req_ras_err_count(struct amdgpu_device *adev) return xgpu_nv_send_access_requests(adev, IDH_REQ_RAS_ERROR_COUNT); } +static int xgpu_nv_req_ras_cper_dump(struct amdgpu_device *adev, u64 vf_rptr) +{ + uint32_t vf_rptr_hi, vf_rptr_lo; + + vf_rptr_hi = (uint32_t)(vf_rptr >> 32); + vf_rptr_lo = (uint32_t)(vf_rptr & 0xFFFFFFFF); + return xgpu_nv_send_access_requests_with_param( + adev, IDH_REQ_RAS_CPER_DUMP, vf_rptr_hi, vf_rptr_lo, 0); +} + const struct amdgpu_virt_ops xgpu_nv_virt_ops = { .req_full_gpu = xgpu_nv_request_full_gpu_access, .rel_full_gpu = xgpu_nv_release_full_gpu_access, @@ -478,4 +491,5 @@ const struct amdgpu_virt_ops xgpu_nv_virt_ops = { .ras_poison_handler = xgpu_nv_ras_poison_handler, .rcvd_ras_intr = xgpu_nv_rcvd_ras_intr, .req_ras_err_count = xgpu_nv_req_ras_err_count, + .req_ras_cper_dump = xgpu_nv_req_ras_cper_dump, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h index 9d61d76e1bf9..72c9fceb9d79 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h @@ -41,6 +41,7 @@ enum idh_request { IDH_READY_TO_RESET = 201, IDH_RAS_POISON = 202, IDH_REQ_RAS_ERROR_COUNT = 203, + IDH_REQ_RAS_CPER_DUMP = 204, }; enum idh_event { @@ -56,6 +57,7 @@ enum idh_event { IDH_PF_SOFT_FLR_NOTIFICATION, IDH_RAS_ERROR_DETECTED, IDH_RAS_ERROR_COUNT_READY = 11, + IDH_RAS_CPER_DUMP_READY = 14, IDH_TEXT_MESSAGE = 255, }; diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c index 1c727ccd03b1..4cd325149b63 100644 --- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c @@ -625,7 +625,7 @@ static int navi10_ih_resume(struct amdgpu_ip_block *ip_block) return navi10_ih_hw_init(ip_block); } -static bool navi10_ih_is_idle(void *handle) +static bool navi10_ih_is_idle(struct amdgpu_ip_block *ip_block) { /* todo */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c index 9900fe5c3bc3..9b4025c39e44 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c @@ -473,52 +473,6 @@ const struct amdgpu_nbio_funcs nbif_v6_3_1_funcs = { }; -static void nbif_v6_3_1_sriov_ih_doorbell_range(struct amdgpu_device *adev, - bool use_doorbell, int doorbell_index) -{ -} - -static void nbif_v6_3_1_sriov_sdma_doorbell_range(struct amdgpu_device *adev, - int instance, bool use_doorbell, - int doorbell_index, - int doorbell_size) -{ -} - -static void nbif_v6_3_1_sriov_vcn_doorbell_range(struct amdgpu_device *adev, - bool use_doorbell, - int doorbell_index, int instance) -{ -} - -static void nbif_v6_3_1_sriov_gc_doorbell_init(struct amdgpu_device *adev) -{ -} - -const struct amdgpu_nbio_funcs nbif_v6_3_1_sriov_funcs = { - .get_hdp_flush_req_offset = nbif_v6_3_1_get_hdp_flush_req_offset, - .get_hdp_flush_done_offset = nbif_v6_3_1_get_hdp_flush_done_offset, - .get_pcie_index_offset = nbif_v6_3_1_get_pcie_index_offset, - .get_pcie_data_offset = nbif_v6_3_1_get_pcie_data_offset, - .get_rev_id = nbif_v6_3_1_get_rev_id, - .mc_access_enable = nbif_v6_3_1_mc_access_enable, - .get_memsize = nbif_v6_3_1_get_memsize, - .sdma_doorbell_range = nbif_v6_3_1_sriov_sdma_doorbell_range, - .vcn_doorbell_range = nbif_v6_3_1_sriov_vcn_doorbell_range, - .gc_doorbell_init = nbif_v6_3_1_sriov_gc_doorbell_init, - .enable_doorbell_aperture = nbif_v6_3_1_enable_doorbell_aperture, - .enable_doorbell_selfring_aperture = nbif_v6_3_1_enable_doorbell_selfring_aperture, - .ih_doorbell_range = nbif_v6_3_1_sriov_ih_doorbell_range, - .update_medium_grain_clock_gating = nbif_v6_3_1_update_medium_grain_clock_gating, - .update_medium_grain_light_sleep = nbif_v6_3_1_update_medium_grain_light_sleep, - .get_clockgating_state = nbif_v6_3_1_get_clockgating_state, - .ih_control = nbif_v6_3_1_ih_control, - .init_registers = nbif_v6_3_1_init_registers, - .remap_hdp_registers = nbif_v6_3_1_remap_hdp_registers, - .get_rom_offset = nbif_v6_3_1_get_rom_offset, - .set_reg_remap = nbif_v6_3_1_set_reg_remap, -}; - static int nbif_v6_3_1_set_ras_err_event_athub_irq_state(struct amdgpu_device *adev, struct amdgpu_irq_src *src, unsigned type, diff --git a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.h b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.h index 9ac4831d39e1..3afec715a9fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.h +++ b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.h @@ -28,7 +28,6 @@ extern const struct nbio_hdp_flush_reg nbif_v6_3_1_hdp_flush_reg; extern const struct amdgpu_nbio_funcs nbif_v6_3_1_funcs; -extern const struct amdgpu_nbio_funcs nbif_v6_3_1_sriov_funcs; extern struct amdgpu_nbio_ras nbif_v6_3_1_ras; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 5d4a4e7fd97f..8068f384f56c 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -1035,7 +1035,7 @@ static int nv_common_resume(struct amdgpu_ip_block *ip_block) return nv_common_hw_init(ip_block); } -static bool nv_common_is_idle(void *handle) +static bool nv_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 135c5099bfb8..92ce580647cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -911,9 +911,9 @@ static int sdma_v2_4_resume(struct amdgpu_ip_block *ip_block) return sdma_v2_4_hw_init(ip_block); } -static bool sdma_v2_4_is_idle(void *handle) +static bool sdma_v2_4_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS2); if (tmp & (SRBM_STATUS2__SDMA_BUSY_MASK | diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 6e75a4a85f74..1c076bd1cf73 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -1200,9 +1200,9 @@ static int sdma_v3_0_resume(struct amdgpu_ip_block *ip_block) return sdma_v3_0_hw_init(ip_block); } -static bool sdma_v3_0_is_idle(void *handle) +static bool sdma_v3_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS2); if (tmp & (SRBM_STATUS2__SDMA_BUSY_MASK | diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index d31ee01383df..33ed2b158fcd 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -2015,9 +2015,9 @@ static int sdma_v4_0_resume(struct amdgpu_ip_block *ip_block) return sdma_v4_0_hw_init(ip_block); } -static bool sdma_v4_0_is_idle(void *handle) +static bool sdma_v4_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 i; for (i = 0; i < adev->sdma.num_instances; i++) { diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c index 23a6bb16a0b1..fd34dc138081 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c @@ -30,6 +30,7 @@ #include "amdgpu_xcp.h" #include "amdgpu_ucode.h" #include "amdgpu_trace.h" +#include "amdgpu_reset.h" #include "sdma/sdma_4_4_2_offset.h" #include "sdma/sdma_4_4_2_sh_mask.h" @@ -105,6 +106,8 @@ static void sdma_v4_4_2_set_buffer_funcs(struct amdgpu_device *adev); static void sdma_v4_4_2_set_vm_pte_funcs(struct amdgpu_device *adev); static void sdma_v4_4_2_set_irq_funcs(struct amdgpu_device *adev); static void sdma_v4_4_2_set_ras_funcs(struct amdgpu_device *adev); +static void sdma_v4_4_2_set_engine_reset_funcs(struct amdgpu_device *adev); +static void sdma_v4_4_2_update_reset_mask(struct amdgpu_device *adev); static u32 sdma_v4_4_2_get_reg_offset(struct amdgpu_device *adev, u32 instance, u32 offset) @@ -669,11 +672,12 @@ static uint32_t sdma_v4_4_2_rb_cntl(struct amdgpu_ring *ring, uint32_t rb_cntl) * @adev: amdgpu_device pointer * @i: instance to resume * @restore: used to restore wptr when restart + * @guilty: boolean indicating whether this queue is the guilty one (caused the timeout/error) * * Set up the gfx DMA ring buffers and enable them. * Returns 0 for success, error for failure. */ -static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i, bool restore) +static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i, bool restore, bool guilty) { struct amdgpu_ring *ring = &adev->sdma.instance[i].ring; u32 rb_cntl, ib_cntl, wptr_poll_cntl; @@ -681,6 +685,7 @@ static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i, b u32 doorbell; u32 doorbell_offset; u64 wptr_gpu_addr; + u64 rwptr; wb_offset = (ring->rptr_offs * 4); @@ -706,12 +711,20 @@ static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i, b /* before programing wptr to a less value, need set minor_ptr_update first */ WREG32_SDMA(i, regSDMA_GFX_MINOR_PTR_UPDATE, 1); + /* For the guilty queue, set RPTR to the current wptr to skip bad commands, + * It is not a guilty queue, restore cache_rptr and continue execution. + */ + if (guilty) + rwptr = ring->wptr; + else + rwptr = ring->cached_rptr; + /* Initialize the ring buffer's read and write pointers */ if (restore) { - WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, lower_32_bits(ring->wptr << 2)); - WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, upper_32_bits(ring->wptr << 2)); - WREG32_SDMA(i, regSDMA_GFX_RB_WPTR, lower_32_bits(ring->wptr << 2)); - WREG32_SDMA(i, regSDMA_GFX_RB_WPTR_HI, upper_32_bits(ring->wptr << 2)); + WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, lower_32_bits(rwptr << 2)); + WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, upper_32_bits(rwptr << 2)); + WREG32_SDMA(i, regSDMA_GFX_RB_WPTR, lower_32_bits(rwptr << 2)); + WREG32_SDMA(i, regSDMA_GFX_RB_WPTR_HI, upper_32_bits(rwptr << 2)); } else { WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, 0); WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, 0); @@ -766,11 +779,12 @@ static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i, b * @adev: amdgpu_device pointer * @i: instance to resume * @restore: boolean to say restore needed or not + * @guilty: boolean indicating whether this queue is the guilty one (caused the timeout/error) * * Set up the page DMA ring buffers and enable them. * Returns 0 for success, error for failure. */ -static void sdma_v4_4_2_page_resume(struct amdgpu_device *adev, unsigned int i, bool restore) +static void sdma_v4_4_2_page_resume(struct amdgpu_device *adev, unsigned int i, bool restore, bool guilty) { struct amdgpu_ring *ring = &adev->sdma.instance[i].page; u32 rb_cntl, ib_cntl, wptr_poll_cntl; @@ -778,6 +792,7 @@ static void sdma_v4_4_2_page_resume(struct amdgpu_device *adev, unsigned int i, u32 doorbell; u32 doorbell_offset; u64 wptr_gpu_addr; + u64 rwptr; wb_offset = (ring->rptr_offs * 4); @@ -785,12 +800,20 @@ static void sdma_v4_4_2_page_resume(struct amdgpu_device *adev, unsigned int i, rb_cntl = sdma_v4_4_2_rb_cntl(ring, rb_cntl); WREG32_SDMA(i, regSDMA_PAGE_RB_CNTL, rb_cntl); + /* For the guilty queue, set RPTR to the current wptr to skip bad commands, + * It is not a guilty queue, restore cache_rptr and continue execution. + */ + if (guilty) + rwptr = ring->wptr; + else + rwptr = ring->cached_rptr; + /* Initialize the ring buffer's read and write pointers */ if (restore) { - WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, lower_32_bits(ring->wptr << 2)); - WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, upper_32_bits(ring->wptr << 2)); - WREG32_SDMA(i, regSDMA_GFX_RB_WPTR, lower_32_bits(ring->wptr << 2)); - WREG32_SDMA(i, regSDMA_GFX_RB_WPTR_HI, upper_32_bits(ring->wptr << 2)); + WREG32_SDMA(i, regSDMA_PAGE_RB_RPTR, lower_32_bits(rwptr << 2)); + WREG32_SDMA(i, regSDMA_PAGE_RB_RPTR_HI, upper_32_bits(rwptr << 2)); + WREG32_SDMA(i, regSDMA_PAGE_RB_WPTR, lower_32_bits(rwptr << 2)); + WREG32_SDMA(i, regSDMA_PAGE_RB_WPTR_HI, upper_32_bits(rwptr << 2)); } else { WREG32_SDMA(i, regSDMA_PAGE_RB_RPTR, 0); WREG32_SDMA(i, regSDMA_PAGE_RB_RPTR_HI, 0); @@ -966,9 +989,9 @@ static int sdma_v4_4_2_inst_start(struct amdgpu_device *adev, uint32_t temp; WREG32_SDMA(i, regSDMA_SEM_WAIT_FAIL_TIMER_CNTL, 0); - sdma_v4_4_2_gfx_resume(adev, i, restore); + sdma_v4_4_2_gfx_resume(adev, i, restore, adev->sdma.gfx_guilty); if (adev->sdma.has_page_queue) - sdma_v4_4_2_page_resume(adev, i, restore); + sdma_v4_4_2_page_resume(adev, i, restore, adev->sdma.page_guilty); /* set utc l1 enable flag always to 1 */ temp = RREG32_SDMA(i, regSDMA_CNTL); @@ -1330,6 +1353,7 @@ static int sdma_v4_4_2_early_init(struct amdgpu_ip_block *ip_block) sdma_v4_4_2_set_vm_pte_funcs(adev); sdma_v4_4_2_set_irq_funcs(adev); sdma_v4_4_2_set_ras_funcs(adev); + sdma_v4_4_2_set_engine_reset_funcs(adev); return 0; } @@ -1351,6 +1375,12 @@ static int sdma_v4_4_2_late_init(struct amdgpu_ip_block *ip_block) if (!amdgpu_persistent_edc_harvesting_supported(adev)) amdgpu_ras_reset_error_count(adev, AMDGPU_RAS_BLOCK__SDMA); + /* The initialization is done in the late_init stage to ensure that the SMU + * initialization and capability setup are completed before we check the SDMA + * reset capability + */ + sdma_v4_4_2_update_reset_mask(adev); + return 0; } @@ -1458,7 +1488,6 @@ static int sdma_v4_4_2_sw_init(struct amdgpu_ip_block *ip_block) } } - /* TODO: Add queue reset mask when FW fully supports it */ adev->sdma.supported_reset = amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring); @@ -1477,6 +1506,9 @@ static int sdma_v4_4_2_sw_init(struct amdgpu_ip_block *ip_block) r = amdgpu_sdma_sysfs_reset_mask_init(adev); if (r) return r; + /* Initialize guilty flags for GFX and PAGE queues */ + adev->sdma.gfx_guilty = false; + adev->sdma.page_guilty = false; return r; } @@ -1561,9 +1593,9 @@ static int sdma_v4_4_2_resume(struct amdgpu_ip_block *ip_block) return sdma_v4_4_2_hw_init(ip_block); } -static bool sdma_v4_4_2_is_idle(void *handle) +static bool sdma_v4_4_2_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 i; for (i = 0; i < adev->sdma.num_instances; i++) { @@ -1602,25 +1634,83 @@ static int sdma_v4_4_2_soft_reset(struct amdgpu_ip_block *ip_block) return 0; } +static bool sdma_v4_4_2_is_queue_selected(struct amdgpu_device *adev, uint32_t instance_id, bool is_page_queue) +{ + uint32_t reg_offset = is_page_queue ? regSDMA_PAGE_CONTEXT_STATUS : regSDMA_GFX_CONTEXT_STATUS; + uint32_t context_status = RREG32(sdma_v4_4_2_get_reg_offset(adev, instance_id, reg_offset)); + + /* Check if the SELECTED bit is set */ + return (context_status & SDMA_GFX_CONTEXT_STATUS__SELECTED_MASK) != 0; +} + +static bool sdma_v4_4_2_ring_is_guilty(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + uint32_t instance_id = ring->me; + + return sdma_v4_4_2_is_queue_selected(adev, instance_id, false); +} + +static bool sdma_v4_4_2_page_ring_is_guilty(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + uint32_t instance_id = ring->me; + + if (!adev->sdma.has_page_queue) + return false; + + return sdma_v4_4_2_is_queue_selected(adev, instance_id, true); +} + static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid) { struct amdgpu_device *adev = ring->adev; - int i, r; + u32 id = GET_INST(SDMA0, ring->me); + return amdgpu_sdma_reset_engine(adev, id, true); +} + +static int sdma_v4_4_2_stop_queue(struct amdgpu_device *adev, uint32_t instance_id) +{ u32 inst_mask; + uint64_t rptr; + struct amdgpu_ring *ring = &adev->sdma.instance[instance_id].ring; if (amdgpu_sriov_vf(adev)) return -EINVAL; + /* Check if this queue is the guilty one */ + adev->sdma.gfx_guilty = sdma_v4_4_2_is_queue_selected(adev, instance_id, false); + if (adev->sdma.has_page_queue) + adev->sdma.page_guilty = sdma_v4_4_2_is_queue_selected(adev, instance_id, true); + + /* Cache the rptr before reset, after the reset, + * all of the registers will be reset to 0 + */ + rptr = amdgpu_ring_get_rptr(ring); + ring->cached_rptr = rptr; + /* Cache the rptr for the page queue if it exists */ + if (adev->sdma.has_page_queue) { + struct amdgpu_ring *page_ring = &adev->sdma.instance[instance_id].page; + rptr = amdgpu_ring_get_rptr(page_ring); + page_ring->cached_rptr = rptr; + } + /* stop queue */ inst_mask = 1 << ring->me; sdma_v4_4_2_inst_gfx_stop(adev, inst_mask); if (adev->sdma.has_page_queue) sdma_v4_4_2_inst_page_stop(adev, inst_mask); - r = amdgpu_dpm_reset_sdma(adev, 1 << GET_INST(SDMA0, ring->me)); - if (r) - return r; + return 0; +} + +static int sdma_v4_4_2_restore_queue(struct amdgpu_device *adev, uint32_t instance_id) +{ + int i; + u32 inst_mask; + struct amdgpu_ring *ring = &adev->sdma.instance[instance_id].ring; + inst_mask = 1 << ring->me; udelay(50); for (i = 0; i < adev->usec_timeout; i++) { @@ -1638,6 +1728,16 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid) return sdma_v4_4_2_inst_start(adev, inst_mask, true); } +static struct sdma_on_reset_funcs sdma_v4_4_2_engine_reset_funcs = { + .pre_reset = sdma_v4_4_2_stop_queue, + .post_reset = sdma_v4_4_2_restore_queue, +}; + +static void sdma_v4_4_2_set_engine_reset_funcs(struct amdgpu_device *adev) +{ + amdgpu_sdma_register_on_reset_callbacks(adev, &sdma_v4_4_2_engine_reset_funcs); +} + static int sdma_v4_4_2_set_trap_irq_state(struct amdgpu_device *adev, struct amdgpu_irq_src *source, unsigned type, @@ -1683,6 +1783,9 @@ static int sdma_v4_4_2_process_trap_irq(struct amdgpu_device *adev, case 0: amdgpu_fence_process(&adev->sdma.instance[i].ring); break; + case 1: + amdgpu_fence_process(&adev->sdma.instance[i].page); + break; default: break; } @@ -2029,6 +2132,7 @@ static const struct amdgpu_ring_funcs sdma_v4_4_2_ring_funcs = { .emit_reg_wait = sdma_v4_4_2_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, .reset = sdma_v4_4_2_reset_queue, + .is_guilty = sdma_v4_4_2_ring_is_guilty, }; static const struct amdgpu_ring_funcs sdma_v4_4_2_page_ring_funcs = { @@ -2060,6 +2164,8 @@ static const struct amdgpu_ring_funcs sdma_v4_4_2_page_ring_funcs = { .emit_wreg = sdma_v4_4_2_ring_emit_wreg, .emit_reg_wait = sdma_v4_4_2_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, + .reset = sdma_v4_4_2_reset_queue, + .is_guilty = sdma_v4_4_2_page_ring_is_guilty, }; static void sdma_v4_4_2_set_ring_funcs(struct amdgpu_device *adev) @@ -2231,6 +2337,35 @@ static void sdma_v4_4_2_set_vm_pte_funcs(struct amdgpu_device *adev) adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances; } +/** + * sdma_v4_4_2_update_reset_mask - update reset mask for SDMA + * @adev: Pointer to the AMDGPU device structure + * + * This function update reset mask for SDMA and sets the supported + * reset types based on the IP version and firmware versions. + * + */ +static void sdma_v4_4_2_update_reset_mask(struct amdgpu_device *adev) +{ + + /* + * the user queue relies on MEC fw and pmfw when the sdma queue do reset. + * it needs to check both of them at here to skip old mec and pmfw. + */ + switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { + case IP_VERSION(9, 4, 3): + case IP_VERSION(9, 4, 4): + if ((adev->gfx.mec_fw_version >= 0xb0) && amdgpu_dpm_reset_sdma_is_supported(adev)) + adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; + break; + case IP_VERSION(9, 5, 0): + /*TODO: enable the queue reset flag until fw supported */ + default: + break; + } + +} + const struct amdgpu_ip_block_version sdma_v4_4_2_ip_block = { .type = AMD_IP_BLOCK_TYPE_SDMA, .major = 4, @@ -2397,8 +2532,8 @@ static int sdma_v4_4_2_aca_bank_parser(struct aca_handle *handle, struct aca_ban 1ULL); break; case ACA_SMU_TYPE_CE: - bank->aca_err_type = ACA_ERROR_TYPE_CE; - ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE, + bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank); + ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, ACA_REG__MISC0__ERRCNT(misc0)); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index 377efb2b8d0e..0dce59f4f6e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -1530,9 +1530,9 @@ static int sdma_v5_0_resume(struct amdgpu_ip_block *ip_block) return sdma_v5_0_hw_init(ip_block); } -static bool sdma_v5_0_is_idle(void *handle) +static bool sdma_v5_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 i; for (i = 0; i < adev->sdma.num_instances; i++) { diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index ce05d895f977..2b39a03ff0c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -1435,9 +1435,9 @@ static int sdma_v5_2_resume(struct amdgpu_ip_block *ip_block) return sdma_v5_2_hw_init(ip_block); } -static bool sdma_v5_2_is_idle(void *handle) +static bool sdma_v5_2_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 i; for (i = 0; i < adev->sdma.num_instances; i++) { diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index 373703d1596d..c214c3d2149b 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1429,9 +1429,9 @@ static int sdma_v6_0_resume(struct amdgpu_ip_block *ip_block) return sdma_v6_0_hw_init(ip_block); } -static bool sdma_v6_0_is_idle(void *handle) +static bool sdma_v6_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 i; for (i = 0; i < adev->sdma.num_instances; i++) { diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index 9eb8f4f9f302..b2706221df99 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -1430,9 +1430,9 @@ static int sdma_v7_0_resume(struct amdgpu_ip_block *ip_block) return sdma_v7_0_hw_init(ip_block); } -static bool sdma_v7_0_is_idle(void *handle) +static bool sdma_v7_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 i; for (i = 0; i < adev->sdma.num_instances; i++) { diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c index 77ef7da2e4fe..f90e07375396 100644 --- a/drivers/gpu/drm/amd/amdgpu/si.c +++ b/drivers/gpu/drm/amd/amdgpu/si.c @@ -909,7 +909,7 @@ static const u32 hainan_mgcg_cgcg_init[] = /* XXX: update when we support VCE */ #if 0 -/* tahiti, pitcarin, verde */ +/* tahiti, pitcairn, verde */ static const struct amdgpu_video_codec_info tahiti_video_codecs_encode_array[] = { { @@ -940,7 +940,7 @@ static const struct amdgpu_video_codecs hainan_video_codecs_encode = .codec_array = NULL, }; -/* tahiti, pitcarin, verde, oland */ +/* tahiti, pitcairn, verde, oland */ static const struct amdgpu_video_codec_info tahiti_video_codecs_decode_array[] = { { @@ -1888,7 +1888,7 @@ static int si_vce_send_vcepll_ctlreq(struct amdgpu_device *adev) WREG32_SMC_P(CG_VCEPLL_FUNC_CNTL, 0, ~UPLL_CTLREQ_MASK); if (i == SI_MAX_CTLACKS_ASSERTION_WAIT) { - DRM_ERROR("Timeout setting UVD clocks!\n"); + DRM_ERROR("Timeout setting VCE clocks!\n"); return -ETIMEDOUT; } @@ -2644,7 +2644,7 @@ static int si_common_resume(struct amdgpu_ip_block *ip_block) return si_common_hw_init(ip_block); } -static bool si_common_is_idle(void *handle) +static bool si_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c index dbd78d5345a4..e2089c8da71b 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dma.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c @@ -541,9 +541,9 @@ static int si_dma_resume(struct amdgpu_ip_block *ip_block) return si_dma_hw_init(ip_block); } -static bool si_dma_is_idle(void *handle) +static bool si_dma_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(SRBM_STATUS2); @@ -559,7 +559,7 @@ static int si_dma_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (si_dma_is_idle(adev)) + if (si_dma_is_idle(ip_block)) return 0; udelay(1); } diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c index a32b6243c1f8..5c38e1fb1dca 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c @@ -210,9 +210,9 @@ static int si_ih_resume(struct amdgpu_ip_block *ip_block) return si_ih_hw_init(ip_block); } -static bool si_ih_is_idle(void *handle) +static bool si_ih_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(SRBM_STATUS); if (tmp & SRBM_STATUS__IH_BUSY_MASK) @@ -227,7 +227,7 @@ static int si_ih_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (si_ih_is_idle(adev)) + if (si_ih_is_idle(ip_block)) return 0; udelay(1); } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 2c6d2099e215..8732f766947e 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1360,7 +1360,7 @@ static int soc15_common_resume(struct amdgpu_ip_block *ip_block) return soc15_common_hw_init(ip_block); } -static bool soc15_common_is_idle(void *handle) +static bool soc15_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 7925cbb61d0d..dd5d04c068f9 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -952,7 +952,7 @@ static int soc21_common_resume(struct amdgpu_ip_block *ip_block) return soc21_common_hw_init(ip_block); } -static bool soc21_common_is_idle(void *handle) +static bool soc21_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c index 4e506c91e978..972b449ab89f 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc24.c +++ b/drivers/gpu/drm/amd/amdgpu/soc24.c @@ -531,7 +531,7 @@ static int soc24_common_resume(struct amdgpu_ip_block *ip_block) return soc24_common_hw_init(ip_block); } -static bool soc24_common_is_idle(void *handle) +static bool soc24_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c index 0968e551f7b5..7d17ae56f901 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c @@ -353,9 +353,9 @@ static int tonga_ih_resume(struct amdgpu_ip_block *ip_block) return tonga_ih_hw_init(ip_block); } -static bool tonga_ih_is_idle(void *handle) +static bool tonga_ih_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); if (REG_GET_FIELD(tmp, SRBM_STATUS, IH_BUSY)) diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c index 5830e799c0a3..5dbaebb592b3 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c @@ -98,7 +98,7 @@ static void uvd_v3_1_ring_emit_ib(struct amdgpu_ring *ring, } /** - * uvd_v3_1_ring_emit_fence - emit an fence & trap command + * uvd_v3_1_ring_emit_fence - emit a fence & trap command * * @ring: amdgpu_ring pointer * @addr: address @@ -242,7 +242,7 @@ static void uvd_v3_1_mc_resume(struct amdgpu_device *adev) uint64_t addr; uint32_t size; - /* programm the VCPU memory controller bits 0-27 */ + /* program the VCPU memory controller bits 0-27 */ addr = (adev->uvd.inst->gpu_addr + AMDGPU_UVD_FIRMWARE_OFFSET) >> 3; size = AMDGPU_UVD_FIRMWARE_SIZE(adev) >> 3; WREG32(mmUVD_VCPU_CACHE_OFFSET0, addr); @@ -416,7 +416,7 @@ static int uvd_v3_1_start(struct amdgpu_device *adev) /* Set the write pointer delay */ WREG32(mmUVD_RBC_RB_WPTR_CNTL, 0); - /* programm the 4GB memory segment for rptr and ring buffer */ + /* Program the 4GB memory segment for rptr and ring buffer */ WREG32(mmUVD_LMI_EXT40_ADDR, upper_32_bits(ring->gpu_addr) | (0x7 << 16) | (0x1 << 31)); @@ -758,9 +758,9 @@ static int uvd_v3_1_resume(struct amdgpu_ip_block *ip_block) return uvd_v3_1_hw_init(ip_block); } -static bool uvd_v3_1_is_idle(void *handle) +static bool uvd_v3_1_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK); } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c index f93079e09215..4b96fd583772 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c @@ -302,7 +302,7 @@ static int uvd_v4_2_start(struct amdgpu_device *adev) /* enable VCPU clock */ WREG32(mmUVD_VCPU_CNTL, 1 << 9); - /* disable interupt */ + /* disable interrupt */ WREG32_P(mmUVD_MASTINT_EN, 0, ~(1 << 1)); #ifdef __BIG_ENDIAN @@ -312,6 +312,7 @@ static int uvd_v4_2_start(struct amdgpu_device *adev) #endif WREG32(mmUVD_LMI_SWAP_CNTL, lmi_swap_cntl); WREG32(mmUVD_MP_SWAP_CNTL, mp_swap_cntl); + /* initialize UVD memory controller */ WREG32(mmUVD_LMI_CTRL, 0x203108); @@ -658,9 +659,9 @@ static void uvd_v4_2_set_dcm(struct amdgpu_device *adev, WREG32_UVD_CTX(ixUVD_CGC_CTRL2, tmp2); } -static bool uvd_v4_2_is_idle(void *handle) +static bool uvd_v4_2_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK); } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c index 2295c8713d61..71409ad8b7ed 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c @@ -580,9 +580,9 @@ static void uvd_v5_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count) } } -static bool uvd_v5_0_is_idle(void *handle) +static bool uvd_v5_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK); } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index 070a0624c2c5..1c07b701d0e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -1143,9 +1143,9 @@ static void uvd_v6_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring, amdgpu_ring_write(ring, vmid); } -static bool uvd_v6_0_is_idle(void *handle) +static bool uvd_v6_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK); } @@ -1156,7 +1156,7 @@ static int uvd_v6_0_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (uvd_v6_0_is_idle(adev)) + if (uvd_v6_0_is_idle(ip_block)) return 0; } return -ETIMEDOUT; diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c index c633b7ff2943..8c8c02606d25 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c @@ -201,9 +201,9 @@ static void vce_v2_0_mc_resume(struct amdgpu_device *adev) WREG32_FIELD(VCE_SYS_INT_EN, VCE_SYS_INT_TRAP_INTERRUPT_EN, 1); } -static bool vce_v2_0_is_idle(void *handle) +static bool vce_v2_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return !(RREG32(mmSRBM_STATUS2) & SRBM_STATUS2__VCE_BUSY_MASK); } @@ -214,7 +214,7 @@ static int vce_v2_0_wait_for_idle(struct amdgpu_ip_block *ip_block) unsigned i; for (i = 0; i < adev->usec_timeout; i++) { - if (vce_v2_0_is_idle(adev)) + if (vce_v2_0_is_idle(ip_block)) return 0; } return -ETIMEDOUT; @@ -280,7 +280,7 @@ static int vce_v2_0_stop(struct amdgpu_device *adev) if (vce_v2_0_lmi_clean(adev)) { - DRM_INFO("vce is not idle \n"); + DRM_INFO("VCE is not idle \n"); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c index 01248a3982ba..708123899c41 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c @@ -597,9 +597,9 @@ static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx) WREG32_FIELD(VCE_SYS_INT_EN, VCE_SYS_INT_TRAP_INTERRUPT_EN, 1); } -static bool vce_v3_0_is_idle(void *handle) +static bool vce_v3_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 mask = 0; mask |= (adev->vce.harvest_config & AMDGPU_VCE_HARVEST_VCE0) ? 0 : SRBM_STATUS2__VCE0_BUSY_MASK; @@ -614,7 +614,7 @@ static int vce_v3_0_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) - if (vce_v3_0_is_idle(adev)) + if (vce_v3_0_is_idle(ip_block)) return 0; return -ETIMEDOUT; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 5ea96c983517..21b57c29bf7d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -81,14 +81,14 @@ static const struct amdgpu_hwip_reg_entry vcn_reg_list_1_0[] = { SOC15_REG_ENTRY_STR(VCN, 0, mmUVD_DPG_PAUSE) }; -static int vcn_v1_0_stop(struct amdgpu_device *adev); +static int vcn_v1_0_stop(struct amdgpu_vcn_inst *vinst); static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev); static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v1_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v1_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v1_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static void vcn_v1_0_idle_work_handler(struct work_struct *work); static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring); @@ -105,7 +105,8 @@ static int vcn_v1_0_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; - adev->vcn.num_enc_rings = 2; + adev->vcn.inst[0].num_enc_rings = 2; + adev->vcn.inst[0].set_pg_state = vcn_v1_0_set_pg_state; vcn_v1_0_set_dec_ring_funcs(adev); vcn_v1_0_set_enc_ring_funcs(adev); @@ -113,7 +114,7 @@ static int vcn_v1_0_early_init(struct amdgpu_ip_block *ip_block) jpeg_v1_0_early_init(ip_block); - return amdgpu_vcn_early_init(adev); + return amdgpu_vcn_early_init(adev, 0); } /** @@ -138,23 +139,23 @@ static int vcn_v1_0_sw_init(struct amdgpu_ip_block *ip_block) return r; /* VCN ENC TRAP */ - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, i + VCN_1_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst->irq); if (r) return r; } - r = amdgpu_vcn_sw_init(adev); + r = amdgpu_vcn_sw_init(adev, 0); if (r) return r; /* Override the work func */ - adev->vcn.idle_work.work.func = vcn_v1_0_idle_work_handler; + adev->vcn.inst[0].idle_work.work.func = vcn_v1_0_idle_work_handler; - amdgpu_vcn_setup_ucode(adev); + amdgpu_vcn_setup_ucode(adev, 0); - r = amdgpu_vcn_resume(adev); + r = amdgpu_vcn_resume(adev, 0); if (r) return r; @@ -166,18 +167,18 @@ static int vcn_v1_0_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - adev->vcn.internal.scratch9 = adev->vcn.inst->external.scratch9 = + adev->vcn.inst[0].internal.scratch9 = adev->vcn.inst->external.scratch9 = SOC15_REG_OFFSET(UVD, 0, mmUVD_SCRATCH9); - adev->vcn.internal.data0 = adev->vcn.inst->external.data0 = + adev->vcn.inst[0].internal.data0 = adev->vcn.inst->external.data0 = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0); - adev->vcn.internal.data1 = adev->vcn.inst->external.data1 = + adev->vcn.inst[0].internal.data1 = adev->vcn.inst->external.data1 = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA1); - adev->vcn.internal.cmd = adev->vcn.inst->external.cmd = + adev->vcn.inst[0].internal.cmd = adev->vcn.inst->external.cmd = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_CMD); - adev->vcn.internal.nop = adev->vcn.inst->external.nop = + adev->vcn.inst[0].internal.nop = adev->vcn.inst->external.nop = SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP); - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(i); ring = &adev->vcn.inst->ring_enc[i]; @@ -189,7 +190,7 @@ static int vcn_v1_0_sw_init(struct amdgpu_ip_block *ip_block) return r; } - adev->vcn.pause_dpg_mode = vcn_v1_0_pause_dpg_mode; + adev->vcn.inst[0].pause_dpg_mode = vcn_v1_0_pause_dpg_mode; if (amdgpu_vcnfw_log) { volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; @@ -223,13 +224,13 @@ static int vcn_v1_0_sw_fini(struct amdgpu_ip_block *ip_block) int r; struct amdgpu_device *adev = ip_block->adev; - r = amdgpu_vcn_suspend(adev); + r = amdgpu_vcn_suspend(adev, 0); if (r) return r; jpeg_v1_0_sw_fini(ip_block); - r = amdgpu_vcn_sw_fini(adev); + r = amdgpu_vcn_sw_fini(adev, 0); kfree(adev->vcn.ip_dump); @@ -253,7 +254,7 @@ static int vcn_v1_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { ring = &adev->vcn.inst->ring_enc[i]; r = amdgpu_ring_test_helper(ring); if (r) @@ -276,13 +277,14 @@ static int vcn_v1_0_hw_init(struct amdgpu_ip_block *ip_block) static int vcn_v1_0_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_vcn_inst *vinst = adev->vcn.inst; - cancel_delayed_work_sync(&adev->vcn.idle_work); + cancel_delayed_work_sync(&vinst->idle_work); if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && - RREG32_SOC15(VCN, 0, mmUVD_STATUS))) { - vcn_v1_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + (vinst->cur_state != AMD_PG_STATE_GATE && + RREG32_SOC15(VCN, 0, mmUVD_STATUS))) { + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); } return 0; @@ -301,7 +303,7 @@ static int vcn_v1_0_suspend(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; bool idle_work_unexecuted; - idle_work_unexecuted = cancel_delayed_work_sync(&adev->vcn.idle_work); + idle_work_unexecuted = cancel_delayed_work_sync(&adev->vcn.inst[0].idle_work); if (idle_work_unexecuted) { if (adev->pm.dpm_enabled) amdgpu_dpm_enable_vcn(adev, false, 0); @@ -311,7 +313,7 @@ static int vcn_v1_0_suspend(struct amdgpu_ip_block *ip_block) if (r) return r; - r = amdgpu_vcn_suspend(adev); + r = amdgpu_vcn_suspend(adev, 0); return r; } @@ -327,7 +329,7 @@ static int vcn_v1_0_resume(struct amdgpu_ip_block *ip_block) { int r; - r = amdgpu_vcn_resume(ip_block->adev); + r = amdgpu_vcn_resume(ip_block->adev, 0); if (r) return r; @@ -339,12 +341,13 @@ static int vcn_v1_0_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v1_0_mc_resume_spg_mode - memory controller programming * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_device *adev) +static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4); uint32_t offset; @@ -410,8 +413,9 @@ static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_device *adev) adev->gfx.config.gb_addr_config); } -static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_device *adev) +static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4); uint32_t offset; @@ -485,12 +489,13 @@ static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_device *adev) /** * vcn_v1_0_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v1_0_disable_clock_gating(struct amdgpu_device *adev) +static void vcn_v1_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data; /* JPEG disable CGC */ @@ -611,12 +616,13 @@ static void vcn_v1_0_disable_clock_gating(struct amdgpu_device *adev) /** * vcn_v1_0_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer + * @vinst: Pointer to the VCN instance structure * * Enable clock gating for VCN block */ -static void vcn_v1_0_enable_clock_gating(struct amdgpu_device *adev) +static void vcn_v1_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data = 0; /* enable JPEG CGC */ @@ -680,8 +686,10 @@ static void vcn_v1_0_enable_clock_gating(struct amdgpu_device *adev) WREG32_SOC15(VCN, 0, mmUVD_SUVD_CGC_CTRL, data); } -static void vcn_v1_0_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel) +static void vcn_v1_0_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel) { + struct amdgpu_device *adev = vinst->adev; uint32_t reg_data = 0; /* disable JPEG CGC */ @@ -734,8 +742,9 @@ static void vcn_v1_0_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t s WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_SUVD_CGC_CTRL, 0, 0xFFFFFFFF, sram_sel); } -static void vcn_1_0_disable_static_power_gating(struct amdgpu_device *adev) +static void vcn_1_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data = 0; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -779,8 +788,9 @@ static void vcn_1_0_disable_static_power_gating(struct amdgpu_device *adev) WREG32_SOC15(VCN, 0, mmUVD_POWER_STATUS, data); } -static void vcn_1_0_enable_static_power_gating(struct amdgpu_device *adev) +static void vcn_1_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data = 0; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -823,12 +833,13 @@ static void vcn_1_0_enable_static_power_gating(struct amdgpu_device *adev) /** * vcn_v1_0_start_spg_mode - start VCN block * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Setup and start the VCN block */ -static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev) +static int vcn_v1_0_start_spg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec; uint32_t rb_bufsz, tmp; uint32_t lmi_swap_cntl; @@ -837,13 +848,13 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev) /* disable byte swapping */ lmi_swap_cntl = 0; - vcn_1_0_disable_static_power_gating(adev); + vcn_1_0_disable_static_power_gating(vinst); tmp = RREG32_SOC15(UVD, 0, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY; WREG32_SOC15(UVD, 0, mmUVD_STATUS, tmp); /* disable clock gating */ - vcn_v1_0_disable_clock_gating(adev); + vcn_v1_0_disable_clock_gating(vinst); /* disable interupt */ WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_MASTINT_EN), 0, @@ -885,7 +896,7 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev) (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); - vcn_v1_0_mc_resume_spg_mode(adev); + vcn_v1_0_mc_resume_spg_mode(vinst); WREG32_SOC15(UVD, 0, mmUVD_REG_XX_MASK_1_0, 0x10); WREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK_1_0, @@ -1001,8 +1012,9 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev) return 0; } -static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) +static int vcn_v1_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec; uint32_t rb_bufsz, tmp; uint32_t lmi_swap_cntl; @@ -1010,7 +1022,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) /* disable byte swapping */ lmi_swap_cntl = 0; - vcn_1_0_enable_static_power_gating(adev); + vcn_1_0_enable_static_power_gating(vinst); /* enable dynamic power gating mode */ tmp = RREG32_SOC15(UVD, 0, mmUVD_POWER_STATUS); @@ -1019,7 +1031,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) WREG32_SOC15(UVD, 0, mmUVD_POWER_STATUS, tmp); /* enable clock gating */ - vcn_v1_0_clock_gating_dpg_mode(adev, 0); + vcn_v1_0_clock_gating_dpg_mode(vinst, 0); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -1068,7 +1080,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0xFFFFFFFF, 0); - vcn_v1_0_mc_resume_dpg_mode(adev); + vcn_v1_0_mc_resume_dpg_mode(vinst); WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_REG_XX_MASK, 0x10, 0xFFFFFFFF, 0); WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK, 0x3, 0xFFFFFFFF, 0); @@ -1085,7 +1097,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MASTINT_EN, UVD_MASTINT_EN__VCPU_EN_MASK, UVD_MASTINT_EN__VCPU_EN_MASK, 0); - vcn_v1_0_clock_gating_dpg_mode(adev, 1); + vcn_v1_0_clock_gating_dpg_mode(vinst, 1); /* setup mmUVD_LMI_CTRL */ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_CTRL, (8 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) | @@ -1145,21 +1157,24 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) return 0; } -static int vcn_v1_0_start(struct amdgpu_device *adev) +static int vcn_v1_0_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + return (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ? - vcn_v1_0_start_dpg_mode(adev) : vcn_v1_0_start_spg_mode(adev); + vcn_v1_0_start_dpg_mode(vinst) : vcn_v1_0_start_spg_mode(vinst); } /** * vcn_v1_0_stop_spg_mode - stop VCN block * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * stop the VCN block */ -static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev) +static int vcn_v1_0_stop_spg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; int tmp; SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7); @@ -1199,13 +1214,14 @@ static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev) WREG32_SOC15(UVD, 0, mmUVD_STATUS, 0); - vcn_v1_0_enable_clock_gating(adev); - vcn_1_0_enable_static_power_gating(adev); + vcn_v1_0_enable_clock_gating(vinst); + vcn_1_0_enable_static_power_gating(vinst); return 0; } -static int vcn_v1_0_stop_dpg_mode(struct amdgpu_device *adev) +static int vcn_v1_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t tmp; /* Wait for power status to be UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF */ @@ -1237,21 +1253,24 @@ static int vcn_v1_0_stop_dpg_mode(struct amdgpu_device *adev) return 0; } -static int vcn_v1_0_stop(struct amdgpu_device *adev) +static int vcn_v1_0_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; int r; if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - r = vcn_v1_0_stop_dpg_mode(adev); + r = vcn_v1_0_stop_dpg_mode(vinst); else - r = vcn_v1_0_stop_spg_mode(adev); + r = vcn_v1_0_stop_spg_mode(vinst); return r; } -static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state) +static int vcn_v1_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; int ret_code; uint32_t reg_data = 0; uint32_t reg_data2 = 0; @@ -1377,9 +1396,9 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev, return 0; } -static bool vcn_v1_0_is_idle(void *handle) +static bool vcn_v1_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return (RREG32_SOC15(VCN, 0, mmUVD_STATUS) == UVD_STATUS__IDLE); } @@ -1399,16 +1418,17 @@ static int vcn_v1_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, enum amd_clockgating_state state) { struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_vcn_inst *vinst = adev->vcn.inst; bool enable = (state == AMD_CG_STATE_GATE); if (enable) { /* wait for STATUS to clear */ - if (!vcn_v1_0_is_idle(adev)) + if (!vcn_v1_0_is_idle(ip_block)) return -EBUSY; - vcn_v1_0_enable_clock_gating(adev); + vcn_v1_0_enable_clock_gating(vinst); } else { /* disable HW gating and enable Sw gating */ - vcn_v1_0_disable_clock_gating(adev); + vcn_v1_0_disable_clock_gating(vinst); } return 0; } @@ -1800,8 +1820,8 @@ static void vcn_v1_0_dec_ring_insert_nop(struct amdgpu_ring *ring, uint32_t coun } } -static int vcn_v1_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v1_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { /* This doesn't actually powergate the VCN block. * That's done in the dpm code via the SMC. This @@ -1811,28 +1831,29 @@ static int vcn_v1_0_set_powergating_state(struct amdgpu_ip_block *ip_block, * the smc and the hw blocks */ int ret; - struct amdgpu_device *adev = ip_block->adev; - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v1_0_stop(adev); + ret = vcn_v1_0_stop(vinst); else - ret = vcn_v1_0_start(adev); + ret = vcn_v1_0_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; + return ret; } static void vcn_v1_0_idle_work_handler(struct work_struct *work) { - struct amdgpu_device *adev = - container_of(work, struct amdgpu_device, vcn.idle_work.work); + struct amdgpu_vcn_inst *vcn_inst = + container_of(work, struct amdgpu_vcn_inst, idle_work.work); + struct amdgpu_device *adev = vcn_inst->adev; unsigned int fences = 0, i; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_enc[i]); if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { @@ -1848,7 +1869,7 @@ static void vcn_v1_0_idle_work_handler(struct work_struct *work) else new_state.jpeg = VCN_DPG_STATE__UNPAUSE; - adev->vcn.pause_dpg_mode(adev, 0, &new_state); + adev->vcn.inst->pause_dpg_mode(vcn_inst, &new_state); } fences += amdgpu_fence_count_emitted(adev->jpeg.inst->ring_dec); @@ -1862,16 +1883,16 @@ static void vcn_v1_0_idle_work_handler(struct work_struct *work) amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN, AMD_PG_STATE_GATE); } else { - schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT); + schedule_delayed_work(&adev->vcn.inst[0].idle_work, VCN_IDLE_TIMEOUT); } } static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work); + bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.inst[0].idle_work); - mutex_lock(&adev->vcn.vcn1_jpeg1_workaround); + mutex_lock(&adev->vcn.inst[0].vcn1_jpeg1_workaround); if (amdgpu_fence_wait_empty(ring->adev->jpeg.inst->ring_dec)) DRM_ERROR("VCN dec: jpeg dec ring may not be empty\n"); @@ -1897,7 +1918,7 @@ void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks) struct dpg_pause_state new_state; unsigned int fences = 0, i; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_enc[i]); if (fences) @@ -1915,14 +1936,14 @@ void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks) else if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) new_state.jpeg = VCN_DPG_STATE__PAUSE; - adev->vcn.pause_dpg_mode(adev, 0, &new_state); + adev->vcn.inst->pause_dpg_mode(adev->vcn.inst, &new_state); } } void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring) { - schedule_delayed_work(&ring->adev->vcn.idle_work, VCN_IDLE_TIMEOUT); - mutex_unlock(&ring->adev->vcn.vcn1_jpeg1_workaround); + schedule_delayed_work(&ring->adev->vcn.inst[0].idle_work, VCN_IDLE_TIMEOUT); + mutex_unlock(&ring->adev->vcn.inst[0].vcn1_jpeg1_workaround); } static void vcn_v1_0_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p) @@ -1997,7 +2018,7 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = { .is_idle = vcn_v1_0_is_idle, .wait_for_idle = vcn_v1_0_wait_for_idle, .set_clockgating_state = vcn_v1_0_set_clockgating_state, - .set_powergating_state = vcn_v1_0_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v1_0_dump_ip_state, .print_ip_state = vcn_v1_0_print_ip_state, }; @@ -2056,11 +2077,11 @@ static int vcn_v1_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, uint32_t reg = amdgpu_ib_get_value(ib, i); uint32_t val = amdgpu_ib_get_value(ib, i + 1); - if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) { + if (reg == PACKET0(p->adev->vcn.inst[0].internal.data0, 0)) { msg_lo = val; - } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) { + } else if (reg == PACKET0(p->adev->vcn.inst[0].internal.data1, 0)) { msg_hi = val; - } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0)) { + } else if (reg == PACKET0(p->adev->vcn.inst[0].internal.cmd, 0)) { r = vcn_v1_0_validate_bo(p, job, ((u64)msg_hi) << 32 | msg_lo); if (r) @@ -2145,7 +2166,7 @@ static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev) { int i; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) adev->vcn.inst->ring_enc[i].funcs = &vcn_v1_0_enc_ring_vm_funcs; } @@ -2156,7 +2177,7 @@ static const struct amdgpu_irq_src_funcs vcn_v1_0_irq_funcs = { static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev) { - adev->vcn.inst->irq.num_types = adev->vcn.num_enc_rings + 2; + adev->vcn.inst->irq.num_types = adev->vcn.inst[0].num_enc_rings + 2; adev->vcn.inst->irq.funcs = &vcn_v1_0_irq_funcs; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index e42cfc731ad8..8e7a36f26e9c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -92,10 +92,10 @@ static const struct amdgpu_hwip_reg_entry vcn_reg_list_2_0[] = { static void vcn_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void vcn_v2_0_set_enc_ring_funcs(struct amdgpu_device *adev); static void vcn_v2_0_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v2_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v2_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v2_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static int vcn_v2_0_start_sriov(struct amdgpu_device *adev); /** * vcn_v2_0_early_init - set function pointers and load microcode @@ -110,15 +110,16 @@ static int vcn_v2_0_early_init(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; if (amdgpu_sriov_vf(adev)) - adev->vcn.num_enc_rings = 1; + adev->vcn.inst[0].num_enc_rings = 1; else - adev->vcn.num_enc_rings = 2; + adev->vcn.inst[0].num_enc_rings = 2; + adev->vcn.inst->set_pg_state = vcn_v2_0_set_pg_state; vcn_v2_0_set_dec_ring_funcs(adev); vcn_v2_0_set_enc_ring_funcs(adev); vcn_v2_0_set_irq_funcs(adev); - return amdgpu_vcn_early_init(adev); + return amdgpu_vcn_early_init(adev, 0); } /** @@ -145,7 +146,7 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block) return r; /* VCN ENC TRAP */ - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, i + VCN_2_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst->irq); @@ -153,13 +154,13 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block) return r; } - r = amdgpu_vcn_sw_init(adev); + r = amdgpu_vcn_sw_init(adev, 0); if (r) return r; - amdgpu_vcn_setup_ucode(adev); + amdgpu_vcn_setup_ucode(adev, 0); - r = amdgpu_vcn_resume(adev); + r = amdgpu_vcn_resume(adev, 0); if (r) return r; @@ -175,25 +176,25 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - adev->vcn.internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET; - adev->vcn.internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET; - adev->vcn.internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET; - adev->vcn.internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET; - adev->vcn.internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET; - adev->vcn.internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET; - adev->vcn.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET; adev->vcn.inst->external.scratch9 = SOC15_REG_OFFSET(UVD, 0, mmUVD_SCRATCH9); - adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET; adev->vcn.inst->external.data0 = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0); - adev->vcn.internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET; adev->vcn.inst->external.data1 = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA1); - adev->vcn.internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET; adev->vcn.inst->external.cmd = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_CMD); - adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET; adev->vcn.inst->external.nop = SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP); - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(i); ring = &adev->vcn.inst->ring_enc[i]; @@ -210,7 +211,7 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block) return r; } - adev->vcn.pause_dpg_mode = vcn_v2_0_pause_dpg_mode; + adev->vcn.inst[0].pause_dpg_mode = vcn_v2_0_pause_dpg_mode; r = amdgpu_virt_alloc_mm_table(adev); if (r) @@ -254,11 +255,11 @@ static int vcn_v2_0_sw_fini(struct amdgpu_ip_block *ip_block) amdgpu_virt_free_mm_table(adev); - r = amdgpu_vcn_suspend(adev); + r = amdgpu_vcn_suspend(adev, 0); if (r) return r; - r = amdgpu_vcn_sw_fini(adev); + r = amdgpu_vcn_sw_fini(adev, 0); kfree(adev->vcn.ip_dump); @@ -292,7 +293,7 @@ static int vcn_v2_0_hw_init(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) ring->sched.ready = false; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { ring = &adev->vcn.inst->ring_enc[i]; r = amdgpu_ring_test_helper(ring); if (r) @@ -312,13 +313,14 @@ static int vcn_v2_0_hw_init(struct amdgpu_ip_block *ip_block) static int vcn_v2_0_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_vcn_inst *vinst = adev->vcn.inst; - cancel_delayed_work_sync(&adev->vcn.idle_work); + cancel_delayed_work_sync(&vinst->idle_work); if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && - RREG32_SOC15(VCN, 0, mmUVD_STATUS))) - vcn_v2_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + (vinst->cur_state != AMD_PG_STATE_GATE && + RREG32_SOC15(VCN, 0, mmUVD_STATUS))) + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); return 0; } @@ -338,7 +340,7 @@ static int vcn_v2_0_suspend(struct amdgpu_ip_block *ip_block) if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + r = amdgpu_vcn_suspend(ip_block->adev, 0); return r; } @@ -354,7 +356,7 @@ static int vcn_v2_0_resume(struct amdgpu_ip_block *ip_block) { int r; - r = amdgpu_vcn_resume(ip_block->adev); + r = amdgpu_vcn_resume(ip_block->adev, 0); if (r) return r; @@ -366,12 +368,13 @@ static int vcn_v2_0_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v2_0_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer + * @vinst: Pointer to the VCN instance structure * * Let the VCN memory controller know it's offsets */ -static void vcn_v2_0_mc_resume(struct amdgpu_device *adev) +static void vcn_v2_0_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4); uint32_t offset; @@ -426,8 +429,10 @@ static void vcn_v2_0_mc_resume(struct amdgpu_device *adev) WREG32_SOC15(UVD, 0, mmUVD_GFX10_ADDR_CONFIG, adev->gfx.config.gb_addr_config); } -static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirect) +static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4); uint32_t offset; @@ -525,12 +530,13 @@ static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirec /** * vcn_v2_0_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v2_0_disable_clock_gating(struct amdgpu_device *adev) +static void vcn_v2_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data; if (amdgpu_sriov_vf(adev)) @@ -634,9 +640,10 @@ static void vcn_v2_0_disable_clock_gating(struct amdgpu_device *adev) WREG32_SOC15(VCN, 0, mmUVD_SUVD_CGC_CTRL, data); } -static void vcn_v2_0_clock_gating_dpg_mode(struct amdgpu_device *adev, +static void vcn_v2_0_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, uint8_t sram_sel, uint8_t indirect) { + struct amdgpu_device *adev = vinst->adev; uint32_t reg_data = 0; /* enable sw clock gating control */ @@ -685,12 +692,13 @@ static void vcn_v2_0_clock_gating_dpg_mode(struct amdgpu_device *adev, /** * vcn_v2_0_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v2_0_enable_clock_gating(struct amdgpu_device *adev) +static void vcn_v2_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data = 0; if (amdgpu_sriov_vf(adev)) @@ -743,8 +751,9 @@ static void vcn_v2_0_enable_clock_gating(struct amdgpu_device *adev) WREG32_SOC15(VCN, 0, mmUVD_SUVD_CGC_CTRL, data); } -static void vcn_v2_0_disable_static_power_gating(struct amdgpu_device *adev) +static void vcn_v2_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data = 0; if (amdgpu_sriov_vf(adev)) @@ -792,8 +801,9 @@ static void vcn_v2_0_disable_static_power_gating(struct amdgpu_device *adev) WREG32_SOC15(VCN, 0, mmUVD_POWER_STATUS, data); } -static void vcn_v2_0_enable_static_power_gating(struct amdgpu_device *adev) +static void vcn_v2_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data = 0; if (amdgpu_sriov_vf(adev)) @@ -834,13 +844,14 @@ static void vcn_v2_0_enable_static_power_gating(struct amdgpu_device *adev) } } -static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) +static int vcn_v2_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) { + struct amdgpu_device *adev = vinst->adev; volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec; uint32_t rb_bufsz, tmp; - vcn_v2_0_enable_static_power_gating(adev); + vcn_v2_0_enable_static_power_gating(vinst); /* enable dynamic power gating mode */ tmp = RREG32_SOC15(UVD, 0, mmUVD_POWER_STATUS); @@ -852,7 +863,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) adev->vcn.inst->dpg_sram_curr_addr = (uint32_t *)adev->vcn.inst->dpg_sram_cpu_addr; /* enable clock gating */ - vcn_v2_0_clock_gating_dpg_mode(adev, 0, indirect); + vcn_v2_0_clock_gating_dpg_mode(vinst, 0, indirect); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -901,7 +912,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect); - vcn_v2_0_mc_resume_dpg_mode(adev, indirect); + vcn_v2_0_mc_resume_dpg_mode(vinst, indirect); WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( UVD, 0, mmUVD_REG_XX_MASK), 0x10, 0, indirect); @@ -969,8 +980,9 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) return 0; } -static int vcn_v2_0_start(struct amdgpu_device *adev) +static int vcn_v2_0_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec; uint32_t rb_bufsz, tmp; @@ -981,16 +993,16 @@ static int vcn_v2_0_start(struct amdgpu_device *adev) amdgpu_dpm_enable_vcn(adev, true, 0); if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - return vcn_v2_0_start_dpg_mode(adev, adev->vcn.indirect_sram); + return vcn_v2_0_start_dpg_mode(vinst, adev->vcn.inst->indirect_sram); - vcn_v2_0_disable_static_power_gating(adev); + vcn_v2_0_disable_static_power_gating(vinst); /* set uvd status busy */ tmp = RREG32_SOC15(UVD, 0, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY; WREG32_SOC15(UVD, 0, mmUVD_STATUS, tmp); /*SW clock gating */ - vcn_v2_0_disable_clock_gating(adev); + vcn_v2_0_disable_clock_gating(vinst); /* enable VCPU clock */ WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CNTL), @@ -1034,7 +1046,7 @@ static int vcn_v2_0_start(struct amdgpu_device *adev) (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); - vcn_v2_0_mc_resume(adev); + vcn_v2_0_mc_resume(vinst); /* release VCPU reset to boot */ WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET), 0, @@ -1142,12 +1154,13 @@ static int vcn_v2_0_start(struct amdgpu_device *adev) return 0; } -static int vcn_v2_0_stop_dpg_mode(struct amdgpu_device *adev) +static int vcn_v2_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; - vcn_v2_0_pause_dpg_mode(adev, 0, &state); + vcn_v2_0_pause_dpg_mode(vinst, &state); /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS, 1, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); @@ -1172,13 +1185,14 @@ static int vcn_v2_0_stop_dpg_mode(struct amdgpu_device *adev) return 0; } -static int vcn_v2_0_stop(struct amdgpu_device *adev) +static int vcn_v2_0_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t tmp; int r; if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v2_0_stop_dpg_mode(adev); + r = vcn_v2_0_stop_dpg_mode(vinst); if (r) return r; goto power_off; @@ -1230,8 +1244,8 @@ static int vcn_v2_0_stop(struct amdgpu_device *adev) /* clear status */ WREG32_SOC15(VCN, 0, mmUVD_STATUS, 0); - vcn_v2_0_enable_clock_gating(adev); - vcn_v2_0_enable_static_power_gating(adev); + vcn_v2_0_enable_clock_gating(vinst); + vcn_v2_0_enable_static_power_gating(vinst); power_off: if (adev->pm.dpm_enabled) @@ -1240,9 +1254,11 @@ power_off: return 0; } -static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state) +static int vcn_v2_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; struct amdgpu_ring *ring; uint32_t reg_data = 0; int ret_code; @@ -1317,9 +1333,9 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, return 0; } -static bool vcn_v2_0_is_idle(void *handle) +static bool vcn_v2_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return (RREG32_SOC15(VCN, 0, mmUVD_STATUS) == UVD_STATUS__IDLE); } @@ -1346,12 +1362,12 @@ static int vcn_v2_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, if (enable) { /* wait for STATUS to clear */ - if (!vcn_v2_0_is_idle(adev)) + if (!vcn_v2_0_is_idle(ip_block)) return -EBUSY; - vcn_v2_0_enable_clock_gating(adev); + vcn_v2_0_enable_clock_gating(&adev->vcn.inst[0]); } else { /* disable HW gating and enable Sw gating */ - vcn_v2_0_disable_clock_gating(adev); + vcn_v2_0_disable_clock_gating(&adev->vcn.inst[0]); } return 0; } @@ -1421,9 +1437,9 @@ void vcn_v2_0_dec_ring_insert_start(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0)); amdgpu_ring_write(ring, 0); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_START << 1)); } @@ -1438,7 +1454,7 @@ void vcn_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[0].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_END << 1)); } @@ -1458,7 +1474,7 @@ void vcn_v2_0_dec_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count) WARN_ON(ring->wptr % 2 || count % 2); for (i = 0; i < count / 2; i++) { - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.nop, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.nop, 0)); amdgpu_ring_write(ring, 0); } } @@ -1479,25 +1495,25 @@ void vcn_v2_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq, struct amdgpu_device *adev = ring->adev; WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.context_id, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.context_id, 0)); amdgpu_ring_write(ring, seq); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0)); amdgpu_ring_write(ring, addr & 0xffffffff); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data1, 0)); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xff); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_FENCE << 1)); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0)); amdgpu_ring_write(ring, 0); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data1, 0)); amdgpu_ring_write(ring, 0); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_TRAP << 1)); } @@ -1520,14 +1536,14 @@ void vcn_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_device *adev = ring->adev; unsigned vmid = AMDGPU_JOB_GET_VMID(job); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.ib_vmid, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.ib_vmid, 0)); amdgpu_ring_write(ring, vmid); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.ib_bar_low, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.ib_bar_low, 0)); amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr)); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.ib_bar_high, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.ib_bar_high, 0)); amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr)); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.ib_size, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.ib_size, 0)); amdgpu_ring_write(ring, ib->length_dw); } @@ -1536,16 +1552,16 @@ void vcn_v2_0_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, { struct amdgpu_device *adev = ring->adev; - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0)); amdgpu_ring_write(ring, reg << 2); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data1, 0)); amdgpu_ring_write(ring, val); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.gp_scratch8, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.gp_scratch8, 0)); amdgpu_ring_write(ring, mask); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_REG_READ_COND_WAIT << 1)); } @@ -1570,13 +1586,13 @@ void vcn_v2_0_dec_ring_emit_wreg(struct amdgpu_ring *ring, { struct amdgpu_device *adev = ring->adev; - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0)); amdgpu_ring_write(ring, reg << 2); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data1, 0)); amdgpu_ring_write(ring, val); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_WRITE_REG << 1)); } @@ -1777,9 +1793,9 @@ int vcn_v2_0_dec_ring_test_ring(struct amdgpu_ring *ring) r = amdgpu_ring_alloc(ring, 4); if (r) return r; - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_START << 1)); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.scratch9, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.scratch9, 0)); amdgpu_ring_write(ring, 0xDEADBEEF); amdgpu_ring_commit(ring); for (i = 0; i < adev->usec_timeout; i++) { @@ -1796,8 +1812,8 @@ int vcn_v2_0_dec_ring_test_ring(struct amdgpu_ring *ring) } -static int vcn_v2_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v2_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { /* This doesn't actually powergate the VCN block. * That's done in the dpm code via the SMC. This @@ -1807,23 +1823,24 @@ static int vcn_v2_0_set_powergating_state(struct amdgpu_ip_block *ip_block, * the smc and the hw blocks */ int ret; - struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_device *adev = vinst->adev; if (amdgpu_sriov_vf(adev)) { - adev->vcn.cur_state = AMD_PG_STATE_UNGATE; + vinst->cur_state = AMD_PG_STATE_UNGATE; return 0; } - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v2_0_stop(adev); + ret = vcn_v2_0_stop(vinst); else - ret = vcn_v2_0_start(adev); + ret = vcn_v2_0_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; + return ret; } @@ -1862,7 +1879,7 @@ static int vcn_v2_0_start_mmsch(struct amdgpu_device *adev, adev->vcn.inst->ring_dec.wptr_old = 0; vcn_v2_0_dec_ring_set_wptr(&adev->vcn.inst->ring_dec); - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { adev->vcn.inst->ring_enc[i].wptr = 0; adev->vcn.inst->ring_enc[i].wptr_old = 0; vcn_v2_0_enc_ring_set_wptr(&adev->vcn.inst->ring_enc[i]); @@ -1988,7 +2005,7 @@ static int vcn_v2_0_start_sriov(struct amdgpu_device *adev) SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE2), AMDGPU_VCN_CONTEXT_SIZE); - for (r = 0; r < adev->vcn.num_enc_rings; ++r) { + for (r = 0; r < adev->vcn.inst[0].num_enc_rings; ++r) { ring = &adev->vcn.inst->ring_enc[r]; ring->wptr = 0; MMSCH_V2_0_INSERT_DIRECT_WT( @@ -2104,7 +2121,7 @@ static const struct amd_ip_funcs vcn_v2_0_ip_funcs = { .is_idle = vcn_v2_0_is_idle, .wait_for_idle = vcn_v2_0_wait_for_idle, .set_clockgating_state = vcn_v2_0_set_clockgating_state, - .set_powergating_state = vcn_v2_0_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v2_0_dump_ip_state, .print_ip_state = vcn_v2_0_print_ip_state, }; @@ -2177,7 +2194,7 @@ static void vcn_v2_0_set_enc_ring_funcs(struct amdgpu_device *adev) { int i; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) adev->vcn.inst->ring_enc[i].funcs = &vcn_v2_0_enc_ring_vm_funcs; } @@ -2188,7 +2205,7 @@ static const struct amdgpu_irq_src_funcs vcn_v2_0_irq_funcs = { static void vcn_v2_0_set_irq_funcs(struct amdgpu_device *adev) { - adev->vcn.inst->irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst->irq.num_types = adev->vcn.inst[0].num_enc_rings + 1; adev->vcn.inst->irq.funcs = &vcn_v2_0_irq_funcs; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 105e59f6132b..dff1a8859036 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -95,10 +95,10 @@ static const struct amdgpu_hwip_reg_entry vcn_reg_list_2_5[] = { static void vcn_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev); static void vcn_v2_5_set_enc_ring_funcs(struct amdgpu_device *adev); static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v2_5_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v2_5_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v2_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static int vcn_v2_5_sriov_start(struct amdgpu_device *adev); static void vcn_v2_5_set_ras_funcs(struct amdgpu_device *adev); @@ -118,11 +118,13 @@ static int amdgpu_ih_clientid_vcns[] = { static int vcn_v2_5_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i, r; if (amdgpu_sriov_vf(adev)) { adev->vcn.num_vcn_inst = 2; adev->vcn.harvest_config = 0; - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) + adev->vcn.inst[i].num_enc_rings = 1; } else { u32 harvest; int i; @@ -131,13 +133,12 @@ static int vcn_v2_5_early_init(struct amdgpu_ip_block *ip_block) harvest = RREG32_SOC15(VCN, i, mmCC_UVD_HARVESTING); if (harvest & CC_UVD_HARVESTING__UVD_DISABLE_MASK) adev->vcn.harvest_config |= 1 << i; + adev->vcn.inst[i].num_enc_rings = 2; } if (adev->vcn.harvest_config == (AMDGPU_VCN_HARVEST_VCN0 | - AMDGPU_VCN_HARVEST_VCN1)) + AMDGPU_VCN_HARVEST_VCN1)) /* both instances are harvested, disable the block */ return -ENOENT; - - adev->vcn.num_enc_rings = 2; } vcn_v2_5_set_dec_ring_funcs(adev); @@ -145,7 +146,15 @@ static int vcn_v2_5_early_init(struct amdgpu_ip_block *ip_block) vcn_v2_5_set_irq_funcs(adev); vcn_v2_5_set_ras_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + adev->vcn.inst[i].set_pg_state = vcn_v2_5_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + + return 0; } /** @@ -164,6 +173,8 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (j = 0; j < adev->vcn.num_vcn_inst; j++) { + volatile struct amdgpu_fw_shared *fw_shared; + if (adev->vcn.harvest_config & (1 << j)) continue; /* VCN DEC TRAP */ @@ -173,7 +184,7 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) return r; /* VCN ENC TRAP */ - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[j].num_enc_rings; ++i) { r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[j], i + VCN_2_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst[j].irq); if (r) @@ -185,39 +196,33 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) VCN_2_6__SRCID_UVD_POISON, &adev->vcn.inst[j].ras_poison_irq); if (r) return r; - } - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; + r = amdgpu_vcn_sw_init(adev, j); + if (r) + return r; - amdgpu_vcn_setup_ucode(adev); + amdgpu_vcn_setup_ucode(adev, j); - r = amdgpu_vcn_resume(adev); - if (r) - return r; + r = amdgpu_vcn_resume(adev, j); + if (r) + return r; - for (j = 0; j < adev->vcn.num_vcn_inst; j++) { - volatile struct amdgpu_fw_shared *fw_shared; + adev->vcn.inst[j].internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET; - if (adev->vcn.harvest_config & (1 << j)) - continue; - adev->vcn.internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET; - adev->vcn.internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET; - adev->vcn.internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET; - adev->vcn.internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET; - adev->vcn.internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET; - adev->vcn.internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET; - - adev->vcn.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET; adev->vcn.inst[j].external.scratch9 = SOC15_REG_OFFSET(VCN, j, mmUVD_SCRATCH9); - adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET; adev->vcn.inst[j].external.data0 = SOC15_REG_OFFSET(VCN, j, mmUVD_GPCOM_VCPU_DATA0); - adev->vcn.internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET; adev->vcn.inst[j].external.data1 = SOC15_REG_OFFSET(VCN, j, mmUVD_GPCOM_VCPU_DATA1); - adev->vcn.internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET; adev->vcn.inst[j].external.cmd = SOC15_REG_OFFSET(VCN, j, mmUVD_GPCOM_VCPU_CMD); - adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET; adev->vcn.inst[j].external.nop = SOC15_REG_OFFSET(VCN, j, mmUVD_NO_OP); ring = &adev->vcn.inst[j].ring_dec; @@ -237,7 +242,7 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[j].num_enc_rings; ++i) { enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(i); ring = &adev->vcn.inst[j].ring_enc[i]; @@ -265,6 +270,9 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + adev->vcn.inst[j].pause_dpg_mode = vcn_v2_5_pause_dpg_mode; } if (amdgpu_sriov_vf(adev)) { @@ -273,9 +281,6 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) return r; } - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - adev->vcn.pause_dpg_mode = vcn_v2_5_pause_dpg_mode; - r = amdgpu_vcn_ras_sw_init(adev); if (r) return r; @@ -319,15 +324,18 @@ static int vcn_v2_5_sw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) amdgpu_virt_free_mm_table(adev); - r = amdgpu_vcn_suspend(adev); - if (r) - return r; - - r = amdgpu_vcn_sw_fini(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -366,7 +374,7 @@ static int vcn_v2_5_hw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[j].num_enc_rings; ++i) { ring = &adev->vcn.inst[j].ring_enc[i]; r = amdgpu_ring_test_helper(ring); if (r) @@ -390,19 +398,21 @@ static int vcn_v2_5_hw_fini(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; + cancel_delayed_work_sync(&vinst->idle_work); + if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && + (vinst->cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(VCN, i, mmUVD_STATUS))) - vcn_v2_5_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) - amdgpu_irq_put(adev, &adev->vcn.inst[i].ras_poison_irq, 0); + amdgpu_irq_put(adev, &vinst->ras_poison_irq, 0); } return 0; @@ -417,15 +427,20 @@ static int vcn_v2_5_hw_fini(struct amdgpu_ip_block *ip_block) */ static int vcn_v2_5_suspend(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; r = vcn_v2_5_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(ip_block->adev, i); + if (r) + return r; + } - return r; + return 0; } /** @@ -437,11 +452,14 @@ static int vcn_v2_5_suspend(struct amdgpu_ip_block *ip_block) */ static int vcn_v2_5_resume(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; - r = amdgpu_vcn_resume(ip_block->adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v2_5_hw_init(ip_block); @@ -451,13 +469,14 @@ static int vcn_v2_5_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v2_5_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @i: instance to resume + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v2_5_mc_resume(struct amdgpu_device *adev, int i) +static void vcn_v2_5_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; uint32_t size; uint32_t offset; @@ -510,8 +529,11 @@ static void vcn_v2_5_mc_resume(struct amdgpu_device *adev, int i) AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared))); } -static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[inst_idx].fw->size + 4); uint32_t offset; @@ -609,13 +631,14 @@ static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx /** * vcn_v2_5_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @i: instance to disable clockgating on + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v2_5_disable_clock_gating(struct amdgpu_device *adev, int i) +static void vcn_v2_5_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; uint32_t data; if (adev->vcn.harvest_config & (1 << i)) @@ -721,9 +744,11 @@ static void vcn_v2_5_disable_clock_gating(struct amdgpu_device *adev, int i) WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL, data); } -static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_device *adev, - uint8_t sram_sel, int inst_idx, uint8_t indirect) +static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel, uint8_t indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; /* enable sw clock gating control */ @@ -772,13 +797,14 @@ static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_device *adev, /** * vcn_v2_5_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @i: instance to enable clockgating on + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v2_5_enable_clock_gating(struct amdgpu_device *adev, int i) +static void vcn_v2_5_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; uint32_t data = 0; if (adev->vcn.harvest_config & (1 << i)) @@ -829,9 +855,11 @@ static void vcn_v2_5_enable_clock_gating(struct amdgpu_device *adev, int i) WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL, data); } -static void vcn_v2_6_enable_ras(struct amdgpu_device *adev, int inst_idx, +static void vcn_v2_6_enable_ras(struct amdgpu_vcn_inst *vinst, bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t tmp; if (amdgpu_ip_version(adev, UVD_HWIP, 0) != IP_VERSION(2, 6, 0)) @@ -856,8 +884,10 @@ static void vcn_v2_6_enable_ras(struct amdgpu_device *adev, int inst_idx, tmp, 0, indirect); } -static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v2_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t rb_bufsz, tmp; @@ -875,7 +905,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo adev->vcn.inst[inst_idx].dpg_sram_curr_addr = (uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr; /* enable clock gating */ - vcn_v2_5_clock_gating_dpg_mode(adev, 0, inst_idx, indirect); + vcn_v2_5_clock_gating_dpg_mode(vinst, 0, indirect); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -924,7 +954,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect); - vcn_v2_5_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v2_5_mc_resume_dpg_mode(vinst, indirect); WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, 0, mmUVD_REG_XX_MASK), 0x10, 0, indirect); @@ -935,7 +965,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, 0, mmUVD_LMI_CTRL2), 0, 0, indirect); - vcn_v2_6_enable_ras(adev, inst_idx, indirect); + vcn_v2_6_enable_ras(vinst, indirect); /* unblock VCPU register access */ WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( @@ -1000,8 +1030,10 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo return 0; } -static int vcn_v2_5_start(struct amdgpu_device *adev, int i) +static int vcn_v2_5_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; struct amdgpu_ring *ring; @@ -1015,7 +1047,7 @@ static int vcn_v2_5_start(struct amdgpu_device *adev, int i) amdgpu_dpm_enable_vcn(adev, true, i); if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - return vcn_v2_5_start_dpg_mode(adev, i, adev->vcn.indirect_sram); + return vcn_v2_5_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); /* disable register anti-hang mechanism */ WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_POWER_STATUS), 0, @@ -1029,7 +1061,7 @@ static int vcn_v2_5_start(struct amdgpu_device *adev, int i) return 0; /* SW clock gating */ - vcn_v2_5_disable_clock_gating(adev, i); + vcn_v2_5_disable_clock_gating(vinst); /* enable VCPU clock */ WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), @@ -1074,7 +1106,7 @@ static int vcn_v2_5_start(struct amdgpu_device *adev, int i) (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); - vcn_v2_5_mc_resume(adev, i); + vcn_v2_5_mc_resume(vinst); /* VCN global tiling registers */ WREG32_SOC15(VCN, i, mmUVD_GFX8_ADDR_CONFIG, @@ -1379,8 +1411,10 @@ static int vcn_v2_5_sriov_start(struct amdgpu_device *adev) return vcn_v2_5_mmsch_start(adev, &adev->virt.mm_table); } -static int vcn_v2_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static int vcn_v2_5_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t tmp; /* Wait for power status to be 1 */ @@ -1407,20 +1441,25 @@ static int vcn_v2_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) return 0; } -static int vcn_v2_5_stop(struct amdgpu_device *adev, int i) +static int vcn_v2_5_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; uint32_t tmp; int r; if (adev->vcn.harvest_config & (1 << i)) return 0; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - return vcn_v2_5_stop_dpg_mode(adev, i); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + r = vcn_v2_5_stop_dpg_mode(vinst); + goto done; + } /* wait for vcn idle */ r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7); if (r) - return r; + goto done; tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | UVD_LMI_STATUS__READ_CLEAN_MASK | @@ -1428,7 +1467,7 @@ static int vcn_v2_5_stop(struct amdgpu_device *adev, int i) UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp); if (r) - return r; + goto done; /* block LMI UMC channel */ tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2); @@ -1439,7 +1478,7 @@ static int vcn_v2_5_stop(struct amdgpu_device *adev, int i) UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp); if (r) - return r; + goto done; /* block VCPU register access */ WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), @@ -1458,22 +1497,25 @@ static int vcn_v2_5_stop(struct amdgpu_device *adev, int i) /* clear status */ WREG32_SOC15(VCN, i, mmUVD_STATUS, 0); - vcn_v2_5_enable_clock_gating(adev, i); + vcn_v2_5_enable_clock_gating(vinst); /* enable register anti-hang mechanism */ WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_POWER_STATUS), UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); +done: if (adev->pm.dpm_enabled) amdgpu_dpm_enable_vcn(adev, false, i); - return 0; + return r; } -static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state) +static int vcn_v2_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; struct amdgpu_ring *ring; uint32_t reg_data = 0; int ret_code = 0; @@ -1743,16 +1785,16 @@ static void vcn_v2_5_set_enc_ring_funcs(struct amdgpu_device *adev) for (j = 0; j < adev->vcn.num_vcn_inst; ++j) { if (adev->vcn.harvest_config & (1 << j)) continue; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[j].num_enc_rings; ++i) { adev->vcn.inst[j].ring_enc[i].funcs = &vcn_v2_5_enc_ring_vm_funcs; adev->vcn.inst[j].ring_enc[i].me = j; } } } -static bool vcn_v2_5_is_idle(void *handle) +static bool vcn_v2_5_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -1793,39 +1835,39 @@ static int vcn_v2_5_set_clockgating_state(struct amdgpu_ip_block *ip_block, return 0; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (enable) { - if (!vcn_v2_5_is_idle(adev)) + if (!vcn_v2_5_is_idle(ip_block)) return -EBUSY; - vcn_v2_5_enable_clock_gating(adev, i); + vcn_v2_5_enable_clock_gating(vinst); } else { - vcn_v2_5_disable_clock_gating(adev, i); + vcn_v2_5_disable_clock_gating(vinst); } } return 0; } -static int vcn_v2_5_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v2_5_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret = 0, i; + struct amdgpu_device *adev = vinst->adev; + int ret; if (amdgpu_sriov_vf(adev)) return 0; - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (state == AMD_PG_STATE_GATE) - ret |= vcn_v2_5_stop(adev, i); - else - ret |= vcn_v2_5_start(adev, i); - } + if (state == AMD_PG_STATE_GATE) + ret = vcn_v2_5_stop(vinst); + else + ret = vcn_v2_5_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -1902,10 +1944,10 @@ static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev) for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { if (adev->vcn.harvest_config & (1 << i)) continue; - adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v2_5_irq_funcs; - adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].ras_poison_irq.funcs = &vcn_v2_6_ras_irq_funcs; } } @@ -1982,7 +2024,7 @@ static const struct amd_ip_funcs vcn_v2_5_ip_funcs = { .is_idle = vcn_v2_5_is_idle, .wait_for_idle = vcn_v2_5_wait_for_idle, .set_clockgating_state = vcn_v2_5_set_clockgating_state, - .set_powergating_state = vcn_v2_5_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v2_5_dump_ip_state, .print_ip_state = vcn_v2_5_print_ip_state, }; @@ -1999,7 +2041,7 @@ static const struct amd_ip_funcs vcn_v2_6_ip_funcs = { .is_idle = vcn_v2_5_is_idle, .wait_for_idle = vcn_v2_5_wait_for_idle, .set_clockgating_state = vcn_v2_5_set_clockgating_state, - .set_powergating_state = vcn_v2_5_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v2_5_dump_ip_state, .print_ip_state = vcn_v2_5_print_ip_state, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 63ddd4cca910..22ae1939476f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -105,10 +105,10 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev); static void vcn_v3_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void vcn_v3_0_set_enc_ring_funcs(struct amdgpu_device *adev); static void vcn_v3_0_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v3_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v3_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v3_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static void vcn_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring); static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring); @@ -124,11 +124,13 @@ static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring); static int vcn_v3_0_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i, r; if (amdgpu_sriov_vf(adev)) { adev->vcn.num_vcn_inst = VCN_INSTANCES_SIENNA_CICHLID; adev->vcn.harvest_config = 0; - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) + adev->vcn.inst[i].num_enc_rings = 1; } else { if (adev->vcn.harvest_config == (AMDGPU_VCN_HARVEST_VCN0 | @@ -136,18 +138,27 @@ static int vcn_v3_0_early_init(struct amdgpu_ip_block *ip_block) /* both instances are harvested, disable the block */ return -ENOENT; - if (amdgpu_ip_version(adev, UVD_HWIP, 0) == - IP_VERSION(3, 0, 33)) - adev->vcn.num_enc_rings = 0; - else - adev->vcn.num_enc_rings = 2; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + if (amdgpu_ip_version(adev, UVD_HWIP, 0) == + IP_VERSION(3, 0, 33)) + adev->vcn.inst[i].num_enc_rings = 0; + else + adev->vcn.inst[i].num_enc_rings = 2; + } } vcn_v3_0_set_dec_ring_funcs(adev); vcn_v3_0_set_enc_ring_funcs(adev); vcn_v3_0_set_irq_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + adev->vcn.inst[i].set_pg_state = vcn_v3_0_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + return 0; } /** @@ -166,16 +177,6 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) uint32_t *ptr; struct amdgpu_device *adev = ip_block->adev; - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; - - amdgpu_vcn_setup_ucode(adev); - - r = amdgpu_vcn_resume(adev); - if (r) - return r; - /* * Note: doorbell assignment is fixed for SRIOV multiple VCN engines * Formula: @@ -195,22 +196,32 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) if (adev->vcn.harvest_config & (1 << i)) continue; - adev->vcn.internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET; - adev->vcn.internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET; - adev->vcn.internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET; - adev->vcn.internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET; - adev->vcn.internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET; - adev->vcn.internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET; + r = amdgpu_vcn_sw_init(adev, i); + if (r) + return r; + + amdgpu_vcn_setup_ucode(adev, i); + + r = amdgpu_vcn_resume(adev, i); + if (r) + return r; + + adev->vcn.inst[i].internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET; - adev->vcn.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET; adev->vcn.inst[i].external.scratch9 = SOC15_REG_OFFSET(VCN, i, mmUVD_SCRATCH9); - adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET; adev->vcn.inst[i].external.data0 = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_DATA0); - adev->vcn.internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET; adev->vcn.inst[i].external.data1 = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_DATA1); - adev->vcn.internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET; adev->vcn.inst[i].external.cmd = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_CMD); - adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET; adev->vcn.inst[i].external.nop = SOC15_REG_OFFSET(VCN, i, mmUVD_NO_OP); /* VCN DEC TRAP */ @@ -224,7 +235,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) ring = &adev->vcn.inst[i].ring_dec; ring->use_doorbell = true; if (amdgpu_sriov_vf(adev)) { - ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1); + ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.inst[i].num_enc_rings + 1); } else { ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i; } @@ -236,7 +247,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - for (j = 0; j < adev->vcn.num_enc_rings; ++j) { + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) { enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(j); /* VCN ENC TRAP */ @@ -248,7 +259,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) ring = &adev->vcn.inst[i].ring_enc[j]; ring->use_doorbell = true; if (amdgpu_sriov_vf(adev)) { - ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1) + 1 + j; + ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.inst[i].num_enc_rings + 1) + 1 + j; } else { ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + j + 8 * i; } @@ -274,6 +285,9 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + adev->vcn.inst[i].pause_dpg_mode = vcn_v3_0_pause_dpg_mode; } if (amdgpu_sriov_vf(adev)) { @@ -281,8 +295,6 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; } - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - adev->vcn.pause_dpg_mode = vcn_v3_0_pause_dpg_mode; /* Allocate memory for VCN IP Dump buffer */ ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL); @@ -325,14 +337,18 @@ static int vcn_v3_0_sw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) amdgpu_virt_free_mm_table(adev); - r = amdgpu_vcn_suspend(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; - r = amdgpu_vcn_sw_fini(adev); + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -370,7 +386,7 @@ static int vcn_v3_0_hw_init(struct amdgpu_ip_block *ip_block) ring->sched.ready = true; } - for (j = 0; j < adev->vcn.num_enc_rings; ++j) { + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) { ring = &adev->vcn.inst[i].ring_enc[j]; if (amdgpu_vcn_is_disabled_vcn(adev, VCN_ENCODE_RING, i)) { ring->sched.ready = false; @@ -398,7 +414,7 @@ static int vcn_v3_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - for (j = 0; j < adev->vcn.num_enc_rings; ++j) { + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) { ring = &adev->vcn.inst[i].ring_enc[j]; r = amdgpu_ring_test_helper(ring); if (r) @@ -422,17 +438,19 @@ static int vcn_v3_0_hw_fini(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; + cancel_delayed_work_sync(&vinst->idle_work); + if (!amdgpu_sriov_vf(adev)) { if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && - RREG32_SOC15(VCN, i, mmUVD_STATUS))) { - vcn_v3_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + (vinst->cur_state != AMD_PG_STATE_GATE && + RREG32_SOC15(VCN, i, mmUVD_STATUS))) { + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); } } } @@ -449,15 +467,20 @@ static int vcn_v3_0_hw_fini(struct amdgpu_ip_block *ip_block) */ static int vcn_v3_0_suspend(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; r = vcn_v3_0_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(ip_block->adev, i); + if (r) + return r; + } - return r; + return 0; } /** @@ -469,11 +492,14 @@ static int vcn_v3_0_suspend(struct amdgpu_ip_block *ip_block) */ static int vcn_v3_0_resume(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; - r = amdgpu_vcn_resume(ip_block->adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v3_0_hw_init(ip_block); @@ -483,13 +509,14 @@ static int vcn_v3_0_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v3_0_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v3_0_mc_resume(struct amdgpu_device *adev, int inst) +static void vcn_v3_0_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[inst].fw->size + 4); uint32_t offset; @@ -538,8 +565,11 @@ static void vcn_v3_0_mc_resume(struct amdgpu_device *adev, int inst) AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared))); } -static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[inst_idx].fw->size + 4); uint32_t offset; @@ -634,8 +664,10 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx 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) +static void vcn_v3_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data = 0; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -685,8 +717,10 @@ static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int WREG32_SOC15(VCN, inst, mmUVD_POWER_STATUS, data); } -static void vcn_v3_0_enable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v3_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -733,13 +767,14 @@ static void vcn_v3_0_enable_static_power_gating(struct amdgpu_device *adev, int /** * vcn_v3_0_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: Pointer to the VCN instance structure * * Disable clock gating for VCN block */ -static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v3_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; /* VCN disable CGC */ @@ -866,9 +901,12 @@ static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst) WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_CTRL, data); } -static void vcn_v3_0_clock_gating_dpg_mode(struct amdgpu_device *adev, - uint8_t sram_sel, int inst_idx, uint8_t indirect) +static void vcn_v3_0_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel, + uint8_t indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; /* enable sw clock gating control */ @@ -917,13 +955,14 @@ static void vcn_v3_0_clock_gating_dpg_mode(struct amdgpu_device *adev, /** * vcn_v3_0_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: Pointer to the VCN instance structure * * Enable clock gating for VCN block */ -static void vcn_v3_0_enable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v3_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; /* enable VCN CGC */ @@ -982,8 +1021,10 @@ static void vcn_v3_0_enable_clock_gating(struct amdgpu_device *adev, int inst) WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_CTRL, data); } -static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v3_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t rb_bufsz, tmp; @@ -1001,7 +1042,7 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo adev->vcn.inst[inst_idx].dpg_sram_curr_addr = (uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr; /* enable clock gating */ - vcn_v3_0_clock_gating_dpg_mode(adev, 0, inst_idx, indirect); + vcn_v3_0_clock_gating_dpg_mode(vinst, 0, indirect); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -1050,7 +1091,7 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect); - vcn_v3_0_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v3_0_mc_resume_dpg_mode(vinst, indirect); WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, inst_idx, mmUVD_REG_XX_MASK), 0x10, 0, indirect); @@ -1134,192 +1175,188 @@ 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_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; 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(vinst, vinst->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(vinst); - /* 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(vinst); - /* 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); - - /* 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); - - /* 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 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 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 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); - - /* release VCPU reset to boot */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_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); - for (j = 0; j < 10; ++j) { - uint32_t status; + /* disable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), 0, + ~UVD_MASTINT_EN__VCPU_EN_MASK); - for (k = 0; k < 100; ++k) { - status = RREG32_SOC15(VCN, i, mmUVD_STATUS); - if (status & 2) - break; - mdelay(10); - } - r = 0; - if (status & 2) - break; + /* enable LMI MC and UMC channels */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_CTRL2), 0, + ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); - 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); + 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_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_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))); + + vcn_v3_0_mc_resume(vinst); + + /* 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); + + /* 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 (k = 0; k < 100; ++k) { + status = RREG32_SOC15(VCN, i, mmUVD_STATUS); + if (status & 2) + break; 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); - - 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); - } + /* 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)); + + /* Initialize the ring buffer's read and write pointers */ + WREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR, 0); + + 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; @@ -1434,7 +1471,7 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) mmUVD_VCPU_CACHE_SIZE2), AMDGPU_VCN_CONTEXT_SIZE); - for (j = 0; j < adev->vcn.num_enc_rings; ++j) { + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) { ring = &adev->vcn.inst[i].ring_enc[j]; ring->wptr = 0; rb_addr = ring->gpu_addr; @@ -1534,12 +1571,14 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) return 0; } -static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static int vcn_v3_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; - vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state); + vcn_v3_0_pause_dpg_mode(vinst, &state); /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1, @@ -1565,86 +1604,87 @@ 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_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; uint32_t tmp; - int i, r = 0; - - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; + int r = 0; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v3_0_stop_dpg_mode(adev, i); - continue; - } + if (adev->vcn.harvest_config & (1 << i)) + return 0; - /* wait for vcn idle */ - r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7); - if (r) - return r; + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + r = vcn_v3_0_stop_dpg_mode(vinst); + 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, i, mmUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + /* wait for vcn idle */ + r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7); + 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) - 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) + 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); + /* 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); + /* 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)); + /* 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); + /* 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); + /* clear status */ + WREG32_SOC15(VCN, i, mmUVD_STATUS, 0); - /* apply HW clock gating */ - vcn_v3_0_enable_clock_gating(adev, i); + /* apply HW clock gating */ + vcn_v3_0_enable_clock_gating(vinst); - /* enable VCN power gating */ - vcn_v3_0_enable_static_power_gating(adev, i); - } + /* enable VCN power gating */ + vcn_v3_0_enable_static_power_gating(vinst); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pm.dpm_enabled) - amdgpu_dpm_enable_vcn(adev, false, i); - } +done: + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_vcn(adev, false, i); - return 0; + return r; } -static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state) +static int vcn_v3_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t reg_data = 0; @@ -1928,11 +1968,11 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, uint32_t reg = amdgpu_ib_get_value(ib, i); uint32_t val = amdgpu_ib_get_value(ib, i + 1); - if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) { + if (reg == PACKET0(p->adev->vcn.inst[ring->me].internal.data0, 0)) { msg_lo = val; - } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) { + } else if (reg == PACKET0(p->adev->vcn.inst[ring->me].internal.data1, 0)) { msg_hi = val; - } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0) && + } else if (reg == PACKET0(p->adev->vcn.inst[ring->me].internal.cmd, 0) && val == 0) { r = vcn_v3_0_dec_msg(p, job, ((u64)msg_hi) << 32 | msg_lo); @@ -2096,16 +2136,16 @@ static void vcn_v3_0_set_enc_ring_funcs(struct amdgpu_device *adev) if (adev->vcn.harvest_config & (1 << i)) continue; - for (j = 0; j < adev->vcn.num_enc_rings; ++j) { + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) { adev->vcn.inst[i].ring_enc[j].funcs = &vcn_v3_0_enc_ring_vm_funcs; adev->vcn.inst[i].ring_enc[j].me = i; } } } -static bool vcn_v3_0_is_idle(void *handle) +static bool vcn_v3_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -2144,46 +2184,47 @@ static int vcn_v3_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; if (adev->vcn.harvest_config & (1 << i)) continue; if (enable) { if (RREG32_SOC15(VCN, i, mmUVD_STATUS) != UVD_STATUS__IDLE) return -EBUSY; - vcn_v3_0_enable_clock_gating(adev, i); + vcn_v3_0_enable_clock_gating(vinst); } else { - vcn_v3_0_disable_clock_gating(adev, i); + vcn_v3_0_disable_clock_gating(vinst); } } return 0; } -static int vcn_v3_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v3_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret; + struct amdgpu_device *adev = vinst->adev; + int ret = 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 = AMD_PG_STATE_UNGATE; + vinst->cur_state = AMD_PG_STATE_UNGATE; return 0; } - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v3_0_stop(adev); + ret = vcn_v3_0_stop(vinst); else - ret = vcn_v3_0_start(adev); + ret = vcn_v3_0_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -2248,7 +2289,7 @@ static void vcn_v3_0_set_irq_funcs(struct amdgpu_device *adev) if (adev->vcn.harvest_config & (1 << i)) continue; - adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v3_0_irq_funcs; } } @@ -2326,7 +2367,7 @@ static const struct amd_ip_funcs vcn_v3_0_ip_funcs = { .is_idle = vcn_v3_0_is_idle, .wait_for_idle = vcn_v3_0_wait_for_idle, .set_clockgating_state = vcn_v3_0_set_clockgating_state, - .set_powergating_state = vcn_v3_0_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v3_0_dump_ip_state, .print_ip_state = vcn_v3_0_print_ip_state, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 00551d6f0370..c6f6392c1c20 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -96,10 +96,10 @@ static int amdgpu_ih_clientid_vcns[] = { static int vcn_v4_0_start_sriov(struct amdgpu_device *adev); static void vcn_v4_0_set_unified_ring_funcs(struct amdgpu_device *adev); static void vcn_v4_0_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v4_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v4_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v4_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v4_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static void vcn_v4_0_unified_ring_set_wptr(struct amdgpu_ring *ring); static void vcn_v4_0_set_ras_funcs(struct amdgpu_device *adev); @@ -114,7 +114,7 @@ static void vcn_v4_0_set_ras_funcs(struct amdgpu_device *adev); static int vcn_v4_0_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; - int i; + int i, r; if (amdgpu_sriov_vf(adev)) { adev->vcn.harvest_config = VCN_HARVEST_MMSCH; @@ -126,14 +126,23 @@ static int vcn_v4_0_early_init(struct amdgpu_ip_block *ip_block) } } - /* re-use enc ring as unified ring */ - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) + /* re-use enc ring as unified ring */ + adev->vcn.inst[i].num_enc_rings = 1; vcn_v4_0_set_unified_ring_funcs(adev); vcn_v4_0_set_irq_funcs(adev); vcn_v4_0_set_ras_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + adev->vcn.inst[i].set_pg_state = vcn_v4_0_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + + return 0; } static int vcn_v4_0_fw_shared_init(struct amdgpu_device *adev, int inst_idx) @@ -176,20 +185,20 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block) uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0); uint32_t *ptr; - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; - - amdgpu_vcn_setup_ucode(adev); - - r = amdgpu_vcn_resume(adev); - if (r) - return r; - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { if (adev->vcn.harvest_config & (1 << i)) continue; + r = amdgpu_vcn_sw_init(adev, i); + if (r) + return r; + + amdgpu_vcn_setup_ucode(adev, i); + + r = amdgpu_vcn_resume(adev, i); + if (r) + return r; + /* Init instance 0 sched_score to 1, so it's scheduled after other instances */ if (i == 0) atomic_set(&adev->vcn.inst[i].sched_score, 1); @@ -211,7 +220,8 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block) 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) + i * (adev->vcn.num_enc_rings + 1) + 1; + ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + i * + (adev->vcn.inst[i].num_enc_rings + 1) + 1; else ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + 8 * i; ring->vm_hub = AMDGPU_MMHUB0(0); @@ -223,6 +233,9 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block) return r; vcn_v4_0_fw_shared_init(adev, i); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + adev->vcn.inst[i].pause_dpg_mode = vcn_v4_0_pause_dpg_mode; } /* TODO: Add queue reset mask when FW fully supports it */ @@ -235,8 +248,6 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block) return r; } - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - adev->vcn.pause_dpg_mode = vcn_v4_0_pause_dpg_mode; r = amdgpu_vcn_ras_sw_init(adev); if (r) @@ -288,16 +299,23 @@ static int vcn_v4_0_sw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) amdgpu_virt_free_mm_table(adev); - r = amdgpu_vcn_suspend(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; + } amdgpu_vcn_sysfs_reset_mask_fini(adev); - r = amdgpu_vcn_sw_fini(adev); + + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -359,20 +377,23 @@ static int vcn_v4_0_hw_fini(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; + + cancel_delayed_work_sync(&vinst->idle_work); + if (!amdgpu_sriov_vf(adev)) { if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && + (vinst->cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(VCN, i, regUVD_STATUS))) { - vcn_v4_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); } } if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) - amdgpu_irq_put(adev, &adev->vcn.inst[i].ras_poison_irq, 0); + amdgpu_irq_put(adev, &vinst->ras_poison_irq, 0); } return 0; @@ -387,15 +408,20 @@ static int vcn_v4_0_hw_fini(struct amdgpu_ip_block *ip_block) */ static int vcn_v4_0_suspend(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; r = vcn_v4_0_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(ip_block->adev, i); + if (r) + return r; + } - return r; + return 0; } /** @@ -407,11 +433,14 @@ static int vcn_v4_0_suspend(struct amdgpu_ip_block *ip_block) */ static int vcn_v4_0_resume(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; - r = amdgpu_vcn_resume(ip_block->adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v4_0_hw_init(ip_block); @@ -421,13 +450,14 @@ static int vcn_v4_0_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v4_0_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v4_0_mc_resume(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -481,14 +511,16 @@ static void vcn_v4_0_mc_resume(struct amdgpu_device *adev, int inst) /** * vcn_v4_0_mc_resume_dpg_mode - memory controller programming for dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Let the VCN memory controller know it's offsets with dpg mode */ -static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; hdr = (const struct common_firmware_header *)adev->vcn.inst[inst_idx].fw->data; @@ -588,13 +620,14 @@ static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx /** * vcn_v4_0_disable_static_power_gating - disable VCN static power gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable static power gating for VCN block */ -static void vcn_v4_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data = 0; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -653,13 +686,14 @@ static void vcn_v4_0_disable_static_power_gating(struct amdgpu_device *adev, int /** * vcn_v4_0_enable_static_power_gating - enable VCN static power gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable static power gating for VCN block */ -static void vcn_v4_0_enable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -708,13 +742,14 @@ static void vcn_v4_0_enable_static_power_gating(struct amdgpu_device *adev, int /** * vcn_v4_0_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v4_0_disable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -819,16 +854,18 @@ static void vcn_v4_0_disable_clock_gating(struct amdgpu_device *adev, int inst) /** * vcn_v4_0_disable_clock_gating_dpg_mode - disable VCN clock gating dpg mode * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * @sram_sel: sram select - * @inst_idx: instance number index * @indirect: indirectly write sram * * Disable clock gating for VCN block with dpg mode */ -static void vcn_v4_0_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel, - int inst_idx, uint8_t indirect) +static void vcn_v4_0_disable_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel, + uint8_t indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -876,13 +913,14 @@ static void vcn_v4_0_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, u /** * vcn_v4_0_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v4_0_enable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -932,9 +970,11 @@ static void vcn_v4_0_enable_clock_gating(struct amdgpu_device *adev, int inst) WREG32_SOC15(VCN, inst, regUVD_SUVD_CGC_CTRL, data); } -static void vcn_v4_0_enable_ras(struct amdgpu_device *adev, int inst_idx, +static void vcn_v4_0_enable_ras(struct amdgpu_vcn_inst *vinst, bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t tmp; if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) @@ -957,14 +997,15 @@ static void vcn_v4_0_enable_ras(struct amdgpu_device *adev, int inst_idx, /** * vcn_v4_0_start_dpg_mode - VCN start with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Start VCN block with dpg mode */ -static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v4_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t tmp; @@ -982,7 +1023,7 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo adev->vcn.inst[inst_idx].dpg_sram_curr_addr = (uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr; /* enable clock gating */ - vcn_v4_0_disable_clock_gating_dpg_mode(adev, 0, inst_idx, indirect); + vcn_v4_0_disable_clock_gating_dpg_mode(vinst, 0, indirect); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -1030,7 +1071,7 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect); - vcn_v4_0_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v4_0_mc_resume_dpg_mode(vinst, indirect); tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); tmp |= UVD_VCPU_CNTL__CLK_EN_MASK; @@ -1042,7 +1083,7 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, inst_idx, regUVD_LMI_CTRL2), tmp, 0, indirect); - vcn_v4_0_enable_ras(adev, inst_idx, indirect); + vcn_v4_0_enable_ras(vinst, indirect); /* enable master interrupt */ WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( @@ -1086,183 +1127,179 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo /** * vcn_v4_0_start - VCN start * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Start VCN block */ -static int vcn_v4_0_start(struct amdgpu_device *adev) +static int vcn_v4_0_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t 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); - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v4_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + return vcn_v4_0_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); - /* disable VCN power gating */ - vcn_v4_0_disable_static_power_gating(adev, i); - - /* set VCN status busy */ - tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; - WREG32_SOC15(VCN, i, regUVD_STATUS, tmp); - - /*SW clock gating */ - vcn_v4_0_disable_clock_gating(adev, i); - - /* enable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); - - /* disable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0, - ~UVD_MASTINT_EN__VCPU_EN_MASK); - - /* enable LMI MC and UMC channels */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0, - ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); - - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - - /* setup regUVD_LMI_CTRL */ - tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL); - WREG32_SOC15(VCN, i, 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, i, regUVD_MPC_CNTL); - tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK; - tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT; - WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp); - - /* setup UVD_MPC_SET_MUXA0 */ - WREG32_SOC15(VCN, i, 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, i, 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, i, 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_mc_resume(adev, i); - - /* VCN global tiling registers */ - WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG, - adev->gfx.config.gb_addr_config); - - /* unblock VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - - /* release VCPU reset to boot */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, 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, i, regUVD_STATUS); - if (status & 2) - break; - mdelay(10); - if (amdgpu_emu_mode == 1) - msleep(1); - } + /* disable VCN power gating */ + vcn_v4_0_disable_static_power_gating(vinst); + + /* set VCN status busy */ + tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; + WREG32_SOC15(VCN, i, regUVD_STATUS, tmp); + + /*SW clock gating */ + vcn_v4_0_disable_clock_gating(vinst); - if (amdgpu_emu_mode == 1) { - r = -1; - if (status & 2) { - r = 0; - break; - } - } else { + /* enable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); + + /* disable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0, + ~UVD_MASTINT_EN__VCPU_EN_MASK); + + /* enable LMI MC and UMC channels */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0, + ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); + + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + + /* setup regUVD_LMI_CTRL */ + tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL); + WREG32_SOC15(VCN, i, 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, i, regUVD_MPC_CNTL); + tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK; + tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT; + WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp); + + /* setup UVD_MPC_SET_MUXA0 */ + WREG32_SOC15(VCN, i, 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, i, 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, i, 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_mc_resume(vinst); + + /* VCN global tiling registers */ + WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG, + adev->gfx.config.gb_addr_config); + + /* unblock VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + + /* release VCPU reset to boot */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, 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, i, regUVD_STATUS); + if (status & 2) + break; + mdelay(10); + if (amdgpu_emu_mode == 1) + msleep(1); + } + + if (amdgpu_emu_mode == 1) { + r = -1; + if (status & 2) { r = 0; - if (status & 2) - break; - - dev_err(adev->dev, "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i); - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - mdelay(10); - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - mdelay(10); - r = -1; + break; } + } else { + r = 0; + if (status & 2) + break; + + dev_err(adev->dev, "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i); + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + mdelay(10); + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + mdelay(10); + r = -1; } + } - if (r) { - dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); - return r; - } + if (r) { + dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); + return r; + } - /* enable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), - UVD_MASTINT_EN__VCPU_EN_MASK, - ~UVD_MASTINT_EN__VCPU_EN_MASK); + /* enable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), + UVD_MASTINT_EN__VCPU_EN_MASK, + ~UVD_MASTINT_EN__VCPU_EN_MASK); - /* clear the busy bit of VCN_STATUS */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0, - ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); + /* clear the busy bit of VCN_STATUS */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0, + ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); - ring = &adev->vcn.inst[i].ring_enc[0]; - WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL, - ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | - VCN_RB1_DB_CTRL__EN_MASK); - - WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr); - WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4); - - tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); - tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); - WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; - WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0); - WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0); - - tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR); - WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp); - ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR); - - tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); - tmp |= VCN_RB_ENABLE__RB1_EN_MASK; - WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); - } + ring = &adev->vcn.inst[i].ring_enc[0]; + WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL, + ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | + VCN_RB1_DB_CTRL__EN_MASK); + + WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr); + WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4); + + tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); + WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; + WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0); + WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0); + + tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR); + WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp); + ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR); + + tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + tmp |= VCN_RB_ENABLE__RB1_EN_MASK; + WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); return 0; } @@ -1518,17 +1555,18 @@ static int vcn_v4_0_start_sriov(struct amdgpu_device *adev) /** * vcn_v4_0_stop_dpg_mode - VCN stop with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * * Stop VCN block with dpg mode */ -static void vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static void vcn_v4_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; - vcn_v4_0_pause_dpg_mode(adev, inst_idx, &state); + vcn_v4_0_pause_dpg_mode(vinst, &state); /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, regUVD_POWER_STATUS, 1, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); @@ -1548,87 +1586,87 @@ static void vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) /** * vcn_v4_0_stop - VCN stop * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Stop VCN block */ -static int vcn_v4_0_stop(struct amdgpu_device *adev) +static int vcn_v4_0_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared; uint32_t tmp; - int i, r = 0; - - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; + int r = 0; - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; + if (adev->vcn.harvest_config & (1 << i)) + return 0; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - vcn_v4_0_stop_dpg_mode(adev, i); - continue; - } + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; - /* wait for vcn idle */ - r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); - if (r) - return r; + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + vcn_v4_0_stop_dpg_mode(vinst); + r = 0; + 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, i, regUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + /* wait for vcn idle */ + r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); + if (r) + goto done; - /* disable LMI UMC channel */ - tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2); - tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; - WREG32_SOC15(VCN, i, 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, i, regUVD_LMI_STATUS, tmp, tmp); - 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, regUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; + + /* disable LMI UMC channel */ + tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2); + tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; + WREG32_SOC15(VCN, i, 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, i, regUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; - /* block VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), - UVD_RB_ARB_CTRL__VCPU_DIS_MASK, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + /* block VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_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, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); + /* reset VCPU */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); - /* disable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~(UVD_VCPU_CNTL__CLK_EN_MASK)); + /* disable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~(UVD_VCPU_CNTL__CLK_EN_MASK)); - /* apply soft reset */ - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + /* apply soft reset */ + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - /* clear status */ - WREG32_SOC15(VCN, i, regUVD_STATUS, 0); + /* clear status */ + WREG32_SOC15(VCN, i, regUVD_STATUS, 0); - /* apply HW clock gating */ - vcn_v4_0_enable_clock_gating(adev, i); + /* apply HW clock gating */ + vcn_v4_0_enable_clock_gating(vinst); - /* enable VCN power gating */ - vcn_v4_0_enable_static_power_gating(adev, i); - } + /* enable VCN power gating */ + vcn_v4_0_enable_static_power_gating(vinst); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pm.dpm_enabled) - amdgpu_dpm_enable_vcn(adev, false, i); - } +done: + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_vcn(adev, false, i); return 0; } @@ -1636,15 +1674,16 @@ static int vcn_v4_0_stop(struct amdgpu_device *adev) /** * vcn_v4_0_pause_dpg_mode - VCN pause with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @new_state: pause state * * Pause dpg mode for VCN block */ -static int vcn_v4_0_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx, - struct dpg_pause_state *new_state) +static int vcn_v4_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; int ret_code; @@ -1964,13 +2003,13 @@ static void vcn_v4_0_set_unified_ring_funcs(struct amdgpu_device *adev) /** * vcn_v4_0_is_idle - check VCN block is idle * - * @handle: amdgpu_device pointer + * @ip_block: Pointer to the amdgpu_ip_block structure * * Check whether VCN block is idle */ -static bool vcn_v4_0_is_idle(void *handle) +static bool vcn_v4_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -2024,54 +2063,48 @@ static int vcn_v4_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; if (enable) { if (RREG32_SOC15(VCN, i, regUVD_STATUS) != UVD_STATUS__IDLE) return -EBUSY; - vcn_v4_0_enable_clock_gating(adev, i); + vcn_v4_0_enable_clock_gating(vinst); } else { - vcn_v4_0_disable_clock_gating(adev, i); + vcn_v4_0_disable_clock_gating(vinst); } } return 0; } -/** - * vcn_v4_0_set_powergating_state - set VCN block powergating state - * - * @ip_block: amdgpu_ip_block pointer - * @state: power gating state - * - * Set VCN block powergating state - */ -static int vcn_v4_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v4_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret; + struct amdgpu_device *adev = vinst->adev; + int ret = 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 = AMD_PG_STATE_UNGATE; + vinst->cur_state = AMD_PG_STATE_UNGATE; return 0; } - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v4_0_stop(adev); + ret = vcn_v4_0_stop(vinst); else - ret = vcn_v4_0_start(adev); + ret = vcn_v4_0_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -2163,10 +2196,10 @@ static void vcn_v4_0_set_irq_funcs(struct amdgpu_device *adev) if (adev->vcn.harvest_config & (1 << i)) continue; - adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v4_0_irq_funcs; - adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].ras_poison_irq.funcs = &vcn_v4_0_ras_irq_funcs; } } @@ -2244,7 +2277,7 @@ static const struct amd_ip_funcs vcn_v4_0_ip_funcs = { .is_idle = vcn_v4_0_is_idle, .wait_for_idle = vcn_v4_0_wait_for_idle, .set_clockgating_state = vcn_v4_0_set_clockgating_state, - .set_powergating_state = vcn_v4_0_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v4_0_dump_ip_state, .print_ip_state = vcn_v4_0_print_ip_state, }; 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 75211366f8f6..7446ecc55714 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c @@ -31,6 +31,7 @@ #include "soc15d.h" #include "soc15_hw_ip.h" #include "vcn_v2_0.h" +#include "vcn_v4_0_3.h" #include "mmsch_v4_0_3.h" #include "vcn/vcn_4_0_3_offset.h" @@ -87,10 +88,10 @@ static const struct amdgpu_hwip_reg_entry vcn_reg_list_4_0_3[] = { static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev); static void vcn_v4_0_3_set_unified_ring_funcs(struct amdgpu_device *adev); static void vcn_v4_0_3_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v4_0_3_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v4_0_3_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v4_0_3_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v4_0_3_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static void vcn_v4_0_3_unified_ring_set_wptr(struct amdgpu_ring *ring); static void vcn_v4_0_3_set_ras_funcs(struct amdgpu_device *adev); static void vcn_v4_0_3_enable_ras(struct amdgpu_device *adev, @@ -111,15 +112,25 @@ static inline bool vcn_v4_0_3_normalizn_reqd(struct amdgpu_device *adev) static int vcn_v4_0_3_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i, r; - /* re-use enc ring as unified ring */ - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) + /* re-use enc ring as unified ring */ + adev->vcn.inst[i].num_enc_rings = 1; vcn_v4_0_3_set_unified_ring_funcs(adev); vcn_v4_0_3_set_irq_funcs(adev); vcn_v4_0_3_set_ras_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + adev->vcn.inst[i].set_pg_state = vcn_v4_0_3_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + + return 0; } static int vcn_v4_0_3_fw_shared_init(struct amdgpu_device *adev, int inst_idx) @@ -151,16 +162,6 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block) uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_3); uint32_t *ptr; - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; - - amdgpu_vcn_setup_ucode(adev); - - r = amdgpu_vcn_resume(adev); - if (r) - return r; - /* VCN DEC TRAP */ r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, VCN_4_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst->irq); @@ -168,6 +169,17 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block) return r; for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + + r = amdgpu_vcn_sw_init(adev, i); + if (r) + return r; + + amdgpu_vcn_setup_ucode(adev, i); + + r = amdgpu_vcn_resume(adev, i); + if (r) + return r; + vcn_inst = GET_INST(VCN, i); ring = &adev->vcn.inst[i].ring_enc[0]; @@ -191,6 +203,9 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block) return r; vcn_v4_0_3_fw_shared_init(adev, i); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + adev->vcn.inst[i].pause_dpg_mode = vcn_v4_0_3_pause_dpg_mode; } /* TODO: Add queue reset mask when FW fully supports it */ @@ -203,9 +218,6 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block) return r; } - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - adev->vcn.pause_dpg_mode = vcn_v4_0_3_pause_dpg_mode; - if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) { r = amdgpu_vcn_ras_sw_init(adev); if (r) { @@ -256,16 +268,23 @@ static int vcn_v4_0_3_sw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) amdgpu_virt_free_mm_table(adev); - r = amdgpu_vcn_suspend(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; + } amdgpu_vcn_sysfs_reset_mask_fini(adev); - r = amdgpu_vcn_sw_fini(adev); + + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -349,11 +368,16 @@ static int vcn_v4_0_3_hw_init(struct amdgpu_ip_block *ip_block) static int vcn_v4_0_3_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; - if (adev->vcn.cur_state != AMD_PG_STATE_GATE) - vcn_v4_0_3_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + cancel_delayed_work_sync(&vinst->idle_work); + + if (vinst->cur_state != AMD_PG_STATE_GATE) + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); + } return 0; } @@ -367,15 +391,20 @@ static int vcn_v4_0_3_hw_fini(struct amdgpu_ip_block *ip_block) */ static int vcn_v4_0_3_suspend(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; r = vcn_v4_0_3_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; + } - return r; + return 0; } /** @@ -387,11 +416,14 @@ static int vcn_v4_0_3_suspend(struct amdgpu_ip_block *ip_block) */ static int vcn_v4_0_3_resume(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; - r = amdgpu_vcn_resume(ip_block->adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v4_0_3_hw_init(ip_block); @@ -401,13 +433,14 @@ static int vcn_v4_0_3_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v4_0_3_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @inst_idx: instance number + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v4_0_3_mc_resume(struct amdgpu_device *adev, int inst_idx) +static void vcn_v4_0_3_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t offset, size, vcn_inst; const struct common_firmware_header *hdr; @@ -475,14 +508,16 @@ static void vcn_v4_0_3_mc_resume(struct amdgpu_device *adev, int inst_idx) /** * vcn_v4_0_3_mc_resume_dpg_mode - memory controller programming for dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Let the VCN memory controller know it's offsets with dpg mode */ -static void vcn_v4_0_3_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v4_0_3_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -589,13 +624,14 @@ static void vcn_v4_0_3_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i /** * vcn_v4_0_3_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst_idx: instance number + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v4_0_3_disable_clock_gating(struct amdgpu_device *adev, int inst_idx) +static void vcn_v4_0_3_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t data; int vcn_inst; @@ -682,16 +718,18 @@ static void vcn_v4_0_3_disable_clock_gating(struct amdgpu_device *adev, int inst /** * vcn_v4_0_3_disable_clock_gating_dpg_mode - disable VCN clock gating dpg mode * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * @sram_sel: sram select - * @inst_idx: instance number index * @indirect: indirectly write sram * * Disable clock gating for VCN block with dpg mode */ -static void vcn_v4_0_3_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel, - int inst_idx, uint8_t indirect) +static void vcn_v4_0_3_disable_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel, + uint8_t indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -733,13 +771,14 @@ static void vcn_v4_0_3_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, /** * vcn_v4_0_3_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst_idx: instance number + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v4_0_3_enable_clock_gating(struct amdgpu_device *adev, int inst_idx) +static void vcn_v4_0_3_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t data; int vcn_inst; @@ -784,14 +823,16 @@ static void vcn_v4_0_3_enable_clock_gating(struct amdgpu_device *adev, int inst_ /** * vcn_v4_0_3_start_dpg_mode - VCN start with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Start VCN block with dpg mode */ -static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; @@ -819,7 +860,7 @@ static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b } /* enable clock gating */ - vcn_v4_0_3_disable_clock_gating_dpg_mode(adev, 0, inst_idx, indirect); + vcn_v4_0_3_disable_clock_gating_dpg_mode(vinst, 0, indirect); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -869,7 +910,7 @@ static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect); - vcn_v4_0_3_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v4_0_3_mc_resume_dpg_mode(vinst, indirect); tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); tmp |= UVD_VCPU_CNTL__CLK_EN_MASK; @@ -1116,186 +1157,185 @@ static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev) /** * vcn_v4_0_3_start - VCN start * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Start VCN block */ -static int vcn_v4_0_3_start(struct amdgpu_device *adev) +static int vcn_v4_0_3_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->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; - 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) + return vcn_v4_0_3_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); - 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, 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); - for (j = 0; j < 10; ++j) { - uint32_t status; + /* SW clock gating */ + vcn_v4_0_3_disable_clock_gating(vinst); - 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(vinst); + + /* 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); + + /* clear the busy bit of VCN_STATUS */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0, + ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); + + ring = &adev->vcn.inst[i].ring_enc[0]; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - /* 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)); + /* 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)); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE, - ring->ring_size / sizeof(uint32_t)); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE, + ring->ring_size / sizeof(uint32_t)); - /* 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); + /* 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); - /* 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); + /* 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); + 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)); + 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; } /** * vcn_v4_0_3_stop_dpg_mode - VCN stop with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * * Stop VCN block with dpg mode */ -static int vcn_v4_0_3_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static int vcn_v4_0_3_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t tmp; int vcn_inst; @@ -1321,82 +1361,83 @@ static int vcn_v4_0_3_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) /** * vcn_v4_0_3_stop - VCN stop * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Stop VCN block */ -static int vcn_v4_0_3_stop(struct amdgpu_device *adev) +static int vcn_v4_0_3_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->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, i); - 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[i].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(vinst); + 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(vinst); - /* apply HW clock gating */ - vcn_v4_0_3_enable_clock_gating(adev, i); - } Done: return 0; } @@ -1404,14 +1445,13 @@ Done: /** * vcn_v4_0_3_pause_dpg_mode - VCN pause with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @new_state: pause state * * Pause dpg mode for VCN block */ -static int vcn_v4_0_3_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx, - struct dpg_pause_state *new_state) +static int vcn_v4_0_3_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { return 0; @@ -1455,8 +1495,8 @@ static uint64_t vcn_v4_0_3_unified_ring_get_wptr(struct amdgpu_ring *ring) regUVD_RB_WPTR); } -static void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, - uint32_t val, uint32_t mask) +void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, + uint32_t val, uint32_t mask) { /* Use normalized offsets when required */ if (vcn_v4_0_3_normalizn_reqd(ring->adev)) @@ -1468,7 +1508,8 @@ static void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t amdgpu_ring_write(ring, val); } -static void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val) +void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, + uint32_t val) { /* Use normalized offsets when required */ if (vcn_v4_0_3_normalizn_reqd(ring->adev)) @@ -1479,8 +1520,8 @@ static void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg amdgpu_ring_write(ring, val); } -static void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring, - unsigned int vmid, uint64_t pd_addr) +void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring, + unsigned int vmid, uint64_t pd_addr) { struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->vm_hub]; @@ -1492,7 +1533,7 @@ static void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring, lower_32_bits(pd_addr), 0xffffffff); } -static void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring) +void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring) { /* VCN engine access for HDP flush doesn't work when RRMT is enabled. * This is a workaround to avoid any HDP flush through VCN ring. @@ -1575,13 +1616,13 @@ static void vcn_v4_0_3_set_unified_ring_funcs(struct amdgpu_device *adev) /** * vcn_v4_0_3_is_idle - check VCN block is idle * - * @handle: amdgpu_device pointer + * @ip_block: Pointer to the amdgpu_ip_block structure * * Check whether VCN block is idle */ -static bool vcn_v4_0_3_is_idle(void *handle) +static bool vcn_v4_0_3_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -1629,51 +1670,45 @@ static int vcn_v4_0_3_set_clockgating_state(struct amdgpu_ip_block *ip_block, int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (enable) { if (RREG32_SOC15(VCN, GET_INST(VCN, i), regUVD_STATUS) != UVD_STATUS__IDLE) return -EBUSY; - vcn_v4_0_3_enable_clock_gating(adev, i); + vcn_v4_0_3_enable_clock_gating(vinst); } else { - vcn_v4_0_3_disable_clock_gating(adev, i); + vcn_v4_0_3_disable_clock_gating(vinst); } } return 0; } -/** - * vcn_v4_0_3_set_powergating_state - set VCN block powergating state - * - * @ip_block: amdgpu_ip_block pointer - * @state: power gating state - * - * Set VCN block powergating state - */ -static int vcn_v4_0_3_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v4_0_3_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret; + struct amdgpu_device *adev = vinst->adev; + int ret = 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 = AMD_PG_STATE_UNGATE; + vinst->cur_state = AMD_PG_STATE_UNGATE; return 0; } - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v4_0_3_stop(adev); + ret = vcn_v4_0_3_stop(vinst); else - ret = vcn_v4_0_3_start(adev); + ret = vcn_v4_0_3_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -1835,7 +1870,7 @@ static const struct amd_ip_funcs vcn_v4_0_3_ip_funcs = { .is_idle = vcn_v4_0_3_is_idle, .wait_for_idle = vcn_v4_0_3_wait_for_idle, .set_clockgating_state = vcn_v4_0_3_set_clockgating_state, - .set_powergating_state = vcn_v4_0_3_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v4_0_3_dump_ip_state, .print_ip_state = vcn_v4_0_3_print_ip_state, }; @@ -1930,8 +1965,8 @@ static int vcn_v4_0_3_aca_bank_parser(struct aca_handle *handle, struct aca_bank 1ULL); break; case ACA_SMU_TYPE_CE: - bank->aca_err_type = ACA_ERROR_TYPE_CE; - ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE, + bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank); + ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, ACA_REG__MISC0__ERRCNT(misc0)); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.h b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.h index 0b046114373a..03572a1d0c9c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.h +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.h @@ -26,4 +26,13 @@ extern const struct amdgpu_ip_block_version vcn_v4_0_3_ip_block; +void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, + uint32_t val, uint32_t mask); + +void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, + uint32_t val); +void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring, + unsigned int vmid, uint64_t pd_addr); +void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring); + #endif /* __VCN_V4_0_3_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c index 5d757e7de9db..ba603b2246e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c @@ -95,10 +95,10 @@ static int amdgpu_ih_clientid_vcns[] = { static void vcn_v4_0_5_set_unified_ring_funcs(struct amdgpu_device *adev); static void vcn_v4_0_5_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v4_0_5_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v4_0_5_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v4_0_5_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v4_0_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static void vcn_v4_0_5_unified_ring_set_wptr(struct amdgpu_ring *ring); /** @@ -112,13 +112,26 @@ static void vcn_v4_0_5_unified_ring_set_wptr(struct amdgpu_ring *ring); static int vcn_v4_0_5_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i, r; + + if (amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(4, 0, 6)) + adev->vcn.per_inst_fw = true; - /* re-use enc ring as unified ring */ - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) + /* re-use enc ring as unified ring */ + adev->vcn.inst[i].num_enc_rings = 1; vcn_v4_0_5_set_unified_ring_funcs(adev); vcn_v4_0_5_set_irq_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + adev->vcn.inst[i].set_pg_state = vcn_v4_0_5_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + + return 0; } /** @@ -136,15 +149,6 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block) uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_5); uint32_t *ptr; - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; - - amdgpu_vcn_setup_ucode(adev); - - r = amdgpu_vcn_resume(adev); - if (r) - return r; for (i = 0; i < adev->vcn.num_vcn_inst; i++) { volatile struct amdgpu_vcn4_fw_shared *fw_shared; @@ -152,6 +156,16 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block) if (adev->vcn.harvest_config & (1 << i)) continue; + r = amdgpu_vcn_sw_init(adev, i); + if (r) + return r; + + amdgpu_vcn_setup_ucode(adev, i); + + r = amdgpu_vcn_resume(adev, i); + if (r) + return r; + atomic_set(&adev->vcn.inst[i].sched_score, 0); /* VCN UNIFIED TRAP */ @@ -170,7 +184,7 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block) ring->use_doorbell = true; if (amdgpu_sriov_vf(adev)) ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + - i * (adev->vcn.num_enc_rings + 1) + 1; + i * (adev->vcn.inst[i].num_enc_rings + 1) + 1; else ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + 8 * i; @@ -195,6 +209,9 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block) if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + adev->vcn.inst[i].pause_dpg_mode = vcn_v4_0_5_pause_dpg_mode; } if (amdgpu_sriov_vf(adev)) { @@ -203,9 +220,6 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block) return r; } - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - adev->vcn.pause_dpg_mode = vcn_v4_0_5_pause_dpg_mode; - /* Allocate memory for VCN IP Dump buffer */ ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL); if (!ptr) { @@ -247,15 +261,19 @@ static int vcn_v4_0_5_sw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) amdgpu_virt_free_mm_table(adev); - r = amdgpu_vcn_suspend(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; - r = amdgpu_vcn_sw_fini(adev); + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -300,16 +318,19 @@ static int vcn_v4_0_5_hw_fini(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; + + cancel_delayed_work_sync(&vinst->idle_work); + if (!amdgpu_sriov_vf(adev)) { if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && - RREG32_SOC15(VCN, i, regUVD_STATUS))) { - vcn_v4_0_5_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + (vinst->cur_state != AMD_PG_STATE_GATE && + RREG32_SOC15(VCN, i, regUVD_STATUS))) { + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); } } } @@ -326,13 +347,18 @@ static int vcn_v4_0_5_hw_fini(struct amdgpu_ip_block *ip_block) */ static int vcn_v4_0_5_suspend(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; r = vcn_v4_0_5_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(ip_block->adev, i); + if (r) + return r; + } return r; } @@ -346,11 +372,14 @@ static int vcn_v4_0_5_suspend(struct amdgpu_ip_block *ip_block) */ static int vcn_v4_0_5_resume(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; - r = amdgpu_vcn_resume(ip_block->adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v4_0_5_hw_init(ip_block); @@ -360,13 +389,14 @@ static int vcn_v4_0_5_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v4_0_5_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v4_0_5_mc_resume(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_5_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -420,14 +450,16 @@ static void vcn_v4_0_5_mc_resume(struct amdgpu_device *adev, int inst) /** * vcn_v4_0_5_mc_resume_dpg_mode - memory controller programming for dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Let the VCN memory controller know it's offsets with dpg mode */ -static void vcn_v4_0_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v4_0_5_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -534,13 +566,14 @@ static void vcn_v4_0_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i /** * vcn_v4_0_5_disable_static_power_gating - disable VCN static power gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable static power gating for VCN block */ -static void vcn_v4_0_5_disable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_5_disable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data = 0; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -593,13 +626,14 @@ static void vcn_v4_0_5_disable_static_power_gating(struct amdgpu_device *adev, i /** * vcn_v4_0_5_enable_static_power_gating - enable VCN static power gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable static power gating for VCN block */ -static void vcn_v4_0_5_enable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_5_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -635,13 +669,14 @@ static void vcn_v4_0_5_enable_static_power_gating(struct amdgpu_device *adev, in /** * vcn_v4_0_5_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v4_0_5_disable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_5_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -746,16 +781,18 @@ static void vcn_v4_0_5_disable_clock_gating(struct amdgpu_device *adev, int inst /** * vcn_v4_0_5_disable_clock_gating_dpg_mode - disable VCN clock gating dpg mode * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * @sram_sel: sram select - * @inst_idx: instance number index * @indirect: indirectly write sram * * Disable clock gating for VCN block with dpg mode */ -static void vcn_v4_0_5_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel, - int inst_idx, uint8_t indirect) +static void vcn_v4_0_5_disable_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel, + uint8_t indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -803,13 +840,14 @@ static void vcn_v4_0_5_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, /** * vcn_v4_0_5_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v4_0_5_enable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_5_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -862,14 +900,16 @@ static void vcn_v4_0_5_enable_clock_gating(struct amdgpu_device *adev, int inst) /** * vcn_v4_0_5_start_dpg_mode - VCN start with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Start VCN block with dpg mode */ -static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t tmp; @@ -888,7 +928,7 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b (uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr; /* enable clock gating */ - vcn_v4_0_5_disable_clock_gating_dpg_mode(adev, 0, inst_idx, indirect); + vcn_v4_0_5_disable_clock_gating_dpg_mode(vinst, 0, indirect); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -936,7 +976,7 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect); - vcn_v4_0_5_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v4_0_5_mc_resume_dpg_mode(vinst, indirect); tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); tmp |= UVD_VCPU_CNTL__CLK_EN_MASK; @@ -989,184 +1029,180 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b /** * vcn_v4_0_5_start - VCN start * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Start VCN block */ -static int vcn_v4_0_5_start(struct amdgpu_device *adev) +static int vcn_v4_0_5_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t 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); - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v4_0_5_start_dpg_mode(adev, i, adev->vcn.indirect_sram); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + return vcn_v4_0_5_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); - /* disable VCN power gating */ - vcn_v4_0_5_disable_static_power_gating(adev, i); - - /* set VCN status busy */ - tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; - WREG32_SOC15(VCN, i, regUVD_STATUS, tmp); - - /*SW clock gating */ - vcn_v4_0_5_disable_clock_gating(adev, i); - - /* enable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); - - /* disable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0, - ~UVD_MASTINT_EN__VCPU_EN_MASK); - - /* enable LMI MC and UMC channels */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0, - ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); - - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - - /* setup regUVD_LMI_CTRL */ - tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL); - WREG32_SOC15(VCN, i, 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, i, regUVD_MPC_CNTL); - tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK; - tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT; - WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp); - - /* setup UVD_MPC_SET_MUXA0 */ - WREG32_SOC15(VCN, i, 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, i, 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, i, 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_5_mc_resume(adev, i); - - /* VCN global tiling registers */ - WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG, - adev->gfx.config.gb_addr_config); - - /* unblock VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - - /* release VCPU reset to boot */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, 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, i, regUVD_STATUS); - if (status & 2) - break; - mdelay(10); - if (amdgpu_emu_mode == 1) - msleep(1); - } + /* disable VCN power gating */ + vcn_v4_0_5_disable_static_power_gating(vinst); + + /* set VCN status busy */ + tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; + WREG32_SOC15(VCN, i, regUVD_STATUS, tmp); + + /* SW clock gating */ + vcn_v4_0_5_disable_clock_gating(vinst); + + /* enable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); + + /* disable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0, + ~UVD_MASTINT_EN__VCPU_EN_MASK); + + /* enable LMI MC and UMC channels */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0, + ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); + + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + + /* setup regUVD_LMI_CTRL */ + tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL); + WREG32_SOC15(VCN, i, 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, i, regUVD_MPC_CNTL); + tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK; + tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT; + WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp); + + /* setup UVD_MPC_SET_MUXA0 */ + WREG32_SOC15(VCN, i, 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, i, 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, i, 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_5_mc_resume(vinst); + + /* VCN global tiling registers */ + WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG, + adev->gfx.config.gb_addr_config); + + /* unblock VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + + /* release VCPU reset to boot */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, 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, i, regUVD_STATUS); + if (status & 2) + break; + mdelay(10); + if (amdgpu_emu_mode == 1) + msleep(1); + } - if (amdgpu_emu_mode == 1) { - r = -1; - if (status & 2) { - r = 0; - break; - } - } else { + if (amdgpu_emu_mode == 1) { + r = -1; + if (status & 2) { r = 0; - if (status & 2) - break; - - dev_err(adev->dev, - "VCN[%d] is not responding, trying to reset VCPU!!!\n", i); - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - mdelay(10); - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - mdelay(10); - r = -1; + break; } + } else { + r = 0; + if (status & 2) + break; + + dev_err(adev->dev, + "VCN[%d] is not responding, trying to reset VCPU!!!\n", i); + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + mdelay(10); + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + mdelay(10); + r = -1; } + } - if (r) { - dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); - return r; - } + if (r) { + dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); + return r; + } - /* enable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), - UVD_MASTINT_EN__VCPU_EN_MASK, - ~UVD_MASTINT_EN__VCPU_EN_MASK); + /* enable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), + UVD_MASTINT_EN__VCPU_EN_MASK, + ~UVD_MASTINT_EN__VCPU_EN_MASK); - /* clear the busy bit of VCN_STATUS */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0, - ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); + /* clear the busy bit of VCN_STATUS */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0, + ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); - ring = &adev->vcn.inst[i].ring_enc[0]; - WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL, - ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | - VCN_RB1_DB_CTRL__EN_MASK); - - WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr); - WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4); - - tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); - tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); - WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; - WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0); - WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0); - - tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR); - WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp); - ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR); - - tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); - tmp |= VCN_RB_ENABLE__RB1_EN_MASK; - WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); - } + ring = &adev->vcn.inst[i].ring_enc[0]; + WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL, + ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | + VCN_RB1_DB_CTRL__EN_MASK); + + WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr); + WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4); + + tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); + WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; + WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0); + WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0); + + tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR); + WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp); + ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR); + + tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + tmp |= VCN_RB_ENABLE__RB1_EN_MASK; + WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); return 0; } @@ -1174,13 +1210,14 @@ static int vcn_v4_0_5_start(struct amdgpu_device *adev) /** * vcn_v4_0_5_stop_dpg_mode - VCN stop with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * * Stop VCN block with dpg mode */ -static void vcn_v4_0_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static void vcn_v4_0_5_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t tmp; /* Wait for power status to be 1 */ @@ -1202,103 +1239,104 @@ static void vcn_v4_0_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) /** * vcn_v4_0_5_stop - VCN stop * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Stop VCN block */ -static int vcn_v4_0_5_stop(struct amdgpu_device *adev) +static int vcn_v4_0_5_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared; 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; - 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[i].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_5_stop_dpg_mode(adev, i); - continue; - } - - /* wait for vcn idle */ - r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); - if (r) - return r; + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + vcn_v4_0_5_stop_dpg_mode(vinst); + r = 0; + 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, i, regUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + /* wait for vcn idle */ + r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); + if (r) + goto done; - /* disable LMI UMC channel */ - tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2); - tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; - WREG32_SOC15(VCN, i, 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, i, regUVD_LMI_STATUS, tmp, tmp); - 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, regUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; + + /* disable LMI UMC channel */ + tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2); + tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; + WREG32_SOC15(VCN, i, 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, i, regUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; - /* block VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), - UVD_RB_ARB_CTRL__VCPU_DIS_MASK, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + /* block VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_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, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); + /* reset VCPU */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); - /* disable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~(UVD_VCPU_CNTL__CLK_EN_MASK)); + /* disable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~(UVD_VCPU_CNTL__CLK_EN_MASK)); - /* apply soft reset */ - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + /* apply soft reset */ + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - /* clear status */ - WREG32_SOC15(VCN, i, regUVD_STATUS, 0); + /* clear status */ + WREG32_SOC15(VCN, i, regUVD_STATUS, 0); - /* apply HW clock gating */ - vcn_v4_0_5_enable_clock_gating(adev, i); + /* apply HW clock gating */ + vcn_v4_0_5_enable_clock_gating(vinst); - /* enable VCN power gating */ - vcn_v4_0_5_enable_static_power_gating(adev, i); - } + /* enable VCN power gating */ + vcn_v4_0_5_enable_static_power_gating(vinst); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pm.dpm_enabled) - amdgpu_dpm_enable_vcn(adev, false, i); - } +done: + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_vcn(adev, false, i); - return 0; + return r; } /** * vcn_v4_0_5_pause_dpg_mode - VCN pause with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @new_state: pause state * * Pause dpg mode for VCN block */ -static int vcn_v4_0_5_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx, - struct dpg_pause_state *new_state) +static int vcn_v4_0_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; int ret_code; @@ -1452,13 +1490,13 @@ static void vcn_v4_0_5_set_unified_ring_funcs(struct amdgpu_device *adev) /** * vcn_v4_0_5_is_idle - check VCN block is idle * - * @handle: amdgpu_device pointer + * @ip_block: Pointer to the amdgpu_ip_block structure * * Check whether VCN block is idle */ -static bool vcn_v4_0_5_is_idle(void *handle) +static bool vcn_v4_0_5_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -1512,45 +1550,38 @@ static int vcn_v4_0_5_set_clockgating_state(struct amdgpu_ip_block *ip_block, int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; if (enable) { if (RREG32_SOC15(VCN, i, regUVD_STATUS) != UVD_STATUS__IDLE) return -EBUSY; - vcn_v4_0_5_enable_clock_gating(adev, i); + vcn_v4_0_5_enable_clock_gating(vinst); } else { - vcn_v4_0_5_disable_clock_gating(adev, i); + vcn_v4_0_5_disable_clock_gating(vinst); } } return 0; } -/** - * vcn_v4_0_5_set_powergating_state - set VCN block powergating state - * - * @ip_block: amdgpu_ip_block pointer - * @state: power gating state - * - * Set VCN block powergating state - */ -static int vcn_v4_0_5_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v4_0_5_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret; + int ret = 0; - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v4_0_5_stop(adev); + ret = vcn_v4_0_5_stop(vinst); else - ret = vcn_v4_0_5_start(adev); + ret = vcn_v4_0_5_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -1618,7 +1649,7 @@ static void vcn_v4_0_5_set_irq_funcs(struct amdgpu_device *adev) if (adev->vcn.harvest_config & (1 << i)) continue; - adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v4_0_5_irq_funcs; } } @@ -1696,7 +1727,7 @@ static const struct amd_ip_funcs vcn_v4_0_5_ip_funcs = { .is_idle = vcn_v4_0_5_is_idle, .wait_for_idle = vcn_v4_0_5_wait_for_idle, .set_clockgating_state = vcn_v4_0_5_set_clockgating_state, - .set_powergating_state = vcn_v4_0_5_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v4_0_5_dump_ip_state, .print_ip_state = vcn_v4_0_5_print_ip_state, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c index b6d78381ebfb..d99d05f42f1d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c @@ -78,10 +78,10 @@ static int amdgpu_ih_clientid_vcns[] = { static void vcn_v5_0_0_set_unified_ring_funcs(struct amdgpu_device *adev); static void vcn_v5_0_0_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v5_0_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v5_0_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v5_0_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v5_0_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static void vcn_v5_0_0_unified_ring_set_wptr(struct amdgpu_ring *ring); /** @@ -95,14 +95,24 @@ static void vcn_v5_0_0_unified_ring_set_wptr(struct amdgpu_ring *ring); static int vcn_v5_0_0_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i, r; - /* re-use enc ring as unified ring */ - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) + /* re-use enc ring as unified ring */ + adev->vcn.inst[i].num_enc_rings = 1; vcn_v5_0_0_set_unified_ring_funcs(adev); vcn_v5_0_0_set_irq_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + adev->vcn.inst[i].set_pg_state = vcn_v5_0_0_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + + return 0; } void vcn_v5_0_0_alloc_ip_dump(struct amdgpu_device *adev) @@ -133,22 +143,22 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int i, r; - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; - - amdgpu_vcn_setup_ucode(adev); - - r = amdgpu_vcn_resume(adev); - if (r) - return r; - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { volatile struct amdgpu_vcn5_fw_shared *fw_shared; if (adev->vcn.harvest_config & (1 << i)) continue; + r = amdgpu_vcn_sw_init(adev, i); + if (r) + return r; + + amdgpu_vcn_setup_ucode(adev, i); + + r = amdgpu_vcn_resume(adev, i); + if (r) + return r; + atomic_set(&adev->vcn.inst[i].sched_score, 0); /* VCN UNIFIED TRAP */ @@ -181,15 +191,15 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block) if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + adev->vcn.inst[i].pause_dpg_mode = vcn_v5_0_0_pause_dpg_mode; } /* TODO: Add queue reset mask when FW fully supports it */ adev->vcn.supported_reset = amdgpu_get_soft_full_reset_mask(&adev->vcn.inst[0].ring_enc[0]); - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - adev->vcn.pause_dpg_mode = vcn_v5_0_0_pause_dpg_mode; - vcn_v5_0_0_alloc_ip_dump(adev); r = amdgpu_vcn_sysfs_reset_mask_init(adev); @@ -226,16 +236,23 @@ static int vcn_v5_0_0_sw_fini(struct amdgpu_ip_block *ip_block) drm_dev_exit(idx); } - r = amdgpu_vcn_suspend(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; + } amdgpu_vcn_sysfs_reset_mask_fini(adev); - r = amdgpu_vcn_sw_fini(adev); + + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -280,16 +297,19 @@ static int vcn_v5_0_0_hw_fini(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; + + cancel_delayed_work_sync(&vinst->idle_work); + if (!amdgpu_sriov_vf(adev)) { if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && - RREG32_SOC15(VCN, i, regUVD_STATUS))) { - vcn_v5_0_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + (vinst->cur_state != AMD_PG_STATE_GATE && + RREG32_SOC15(VCN, i, regUVD_STATUS))) { + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); } } } @@ -306,13 +326,18 @@ static int vcn_v5_0_0_hw_fini(struct amdgpu_ip_block *ip_block) */ static int vcn_v5_0_0_suspend(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; r = vcn_v5_0_0_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(ip_block->adev, i); + if (r) + return r; + } return r; } @@ -326,11 +351,14 @@ static int vcn_v5_0_0_suspend(struct amdgpu_ip_block *ip_block) */ static int vcn_v5_0_0_resume(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; - r = amdgpu_vcn_resume(ip_block->adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v5_0_0_hw_init(ip_block); @@ -340,13 +368,14 @@ static int vcn_v5_0_0_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v5_0_0_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v5_0_0_mc_resume(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_0_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -400,14 +429,16 @@ static void vcn_v5_0_0_mc_resume(struct amdgpu_device *adev, int inst) /** * vcn_v5_0_0_mc_resume_dpg_mode - memory controller programming for dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Let the VCN memory controller know it's offsets with dpg mode */ -static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -510,13 +541,14 @@ static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i /** * vcn_v5_0_0_disable_static_power_gating - disable VCN static power gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable static power gating for VCN block */ -static void vcn_v5_0_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data = 0; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -577,13 +609,14 @@ static void vcn_v5_0_0_disable_static_power_gating(struct amdgpu_device *adev, i /** * vcn_v5_0_0_enable_static_power_gating - enable VCN static power gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable static power gating for VCN block */ -static void vcn_v5_0_0_enable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -623,12 +656,11 @@ static void vcn_v5_0_0_enable_static_power_gating(struct amdgpu_device *adev, in /** * vcn_v5_0_0_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v5_0_0_disable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { return; } @@ -637,15 +669,15 @@ static void vcn_v5_0_0_disable_clock_gating(struct amdgpu_device *adev, int inst /** * vcn_v5_0_0_disable_clock_gating_dpg_mode - disable VCN clock gating dpg mode * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * @sram_sel: sram select - * @inst_idx: instance number index * @indirect: indirectly write sram * * Disable clock gating for VCN block with dpg mode */ -static void vcn_v5_0_0_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel, - int inst_idx, uint8_t indirect) +static void vcn_v5_0_0_disable_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel, + uint8_t indirect) { return; } @@ -654,12 +686,11 @@ static void vcn_v5_0_0_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, /** * vcn_v5_0_0_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v5_0_0_enable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { return; } @@ -667,14 +698,16 @@ static void vcn_v5_0_0_enable_clock_gating(struct amdgpu_device *adev, int inst) /** * vcn_v5_0_0_start_dpg_mode - VCN start with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Start VCN block with dpg mode */ -static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_vcn5_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t tmp; @@ -714,7 +747,7 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET( VCN, inst_idx, regUVD_LMI_CTRL), tmp, 0, indirect); - vcn_v5_0_0_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v5_0_0_mc_resume_dpg_mode(vinst, indirect); tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); tmp |= UVD_VCPU_CNTL__CLK_EN_MASK; @@ -766,155 +799,151 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b /** * vcn_v5_0_0_start - VCN start * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Start VCN block */ -static int vcn_v5_0_0_start(struct amdgpu_device *adev) +static int vcn_v5_0_0_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn5_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t 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); - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v5_0_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + return vcn_v5_0_0_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); - /* disable VCN power gating */ - vcn_v5_0_0_disable_static_power_gating(adev, i); - - /* set VCN status busy */ - tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; - WREG32_SOC15(VCN, i, regUVD_STATUS, tmp); - - /* enable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); - - /* disable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0, - ~UVD_MASTINT_EN__VCPU_EN_MASK); - - /* enable LMI MC and UMC channels */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0, - ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); - - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - - /* setup regUVD_LMI_CTRL */ - tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL); - WREG32_SOC15(VCN, i, 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); - - vcn_v5_0_0_mc_resume(adev, i); - - /* VCN global tiling registers */ - WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG, - adev->gfx.config.gb_addr_config); - - /* unblock VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - - /* release VCPU reset to boot */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, 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, i, regUVD_STATUS); - if (status & 2) - break; - mdelay(10); - if (amdgpu_emu_mode == 1) - msleep(1); - } + /* disable VCN power gating */ + vcn_v5_0_0_disable_static_power_gating(vinst); + + /* set VCN status busy */ + tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; + WREG32_SOC15(VCN, i, regUVD_STATUS, tmp); + + /* enable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); + + /* disable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0, + ~UVD_MASTINT_EN__VCPU_EN_MASK); + + /* enable LMI MC and UMC channels */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0, + ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); + + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + + /* setup regUVD_LMI_CTRL */ + tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL); + WREG32_SOC15(VCN, i, 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); + + vcn_v5_0_0_mc_resume(vinst); - if (amdgpu_emu_mode == 1) { - r = -1; - if (status & 2) { - r = 0; - break; - } - } else { + /* VCN global tiling registers */ + WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG, + adev->gfx.config.gb_addr_config); + + /* unblock VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + + /* release VCPU reset to boot */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, 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, i, regUVD_STATUS); + if (status & 2) + break; + mdelay(10); + if (amdgpu_emu_mode == 1) + msleep(1); + } + + if (amdgpu_emu_mode == 1) { + r = -1; + if (status & 2) { r = 0; - if (status & 2) - break; - - dev_err(adev->dev, - "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i); - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - mdelay(10); - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - mdelay(10); - r = -1; + break; } + } else { + r = 0; + if (status & 2) + break; + + dev_err(adev->dev, + "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i); + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + mdelay(10); + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + mdelay(10); + r = -1; } + } - if (r) { - dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); - return r; - } + if (r) { + dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); + return r; + } - /* enable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), - UVD_MASTINT_EN__VCPU_EN_MASK, - ~UVD_MASTINT_EN__VCPU_EN_MASK); + /* enable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), + UVD_MASTINT_EN__VCPU_EN_MASK, + ~UVD_MASTINT_EN__VCPU_EN_MASK); - /* clear the busy bit of VCN_STATUS */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0, - ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); + /* clear the busy bit of VCN_STATUS */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0, + ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); - ring = &adev->vcn.inst[i].ring_enc[0]; - WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL, - ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | - VCN_RB1_DB_CTRL__EN_MASK); - - WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr); - WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4); - - tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); - tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); - WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; - WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0); - WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0); - - tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR); - WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp); - ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR); - - tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); - tmp |= VCN_RB_ENABLE__RB1_EN_MASK; - WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); - } + ring = &adev->vcn.inst[i].ring_enc[0]; + WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL, + ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | + VCN_RB1_DB_CTRL__EN_MASK); + + WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr); + WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4); + + tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); + WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; + WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0); + WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0); + + tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR); + WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp); + ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR); + + tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + tmp |= VCN_RB_ENABLE__RB1_EN_MASK; + WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); return 0; } @@ -922,17 +951,18 @@ static int vcn_v5_0_0_start(struct amdgpu_device *adev) /** * vcn_v5_0_0_stop_dpg_mode - VCN stop with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * * Stop VCN block with dpg mode */ -static void vcn_v5_0_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static void vcn_v5_0_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; - vcn_v5_0_0_pause_dpg_mode(adev, inst_idx, &state); + vcn_v5_0_0_pause_dpg_mode(vinst, &state); /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, regUVD_POWER_STATUS, 1, @@ -952,100 +982,101 @@ static void vcn_v5_0_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) /** * vcn_v5_0_0_stop - VCN stop * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Stop VCN block */ -static int vcn_v5_0_0_stop(struct amdgpu_device *adev) +static int vcn_v5_0_0_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn5_fw_shared *fw_shared; 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; - 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[i].fw_shared.cpu_addr; + fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - vcn_v5_0_0_stop_dpg_mode(adev, i); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + vcn_v5_0_0_stop_dpg_mode(vinst); + r = 0; + goto done; + } - /* wait for vcn idle */ - r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); - if (r) - return r; + /* wait for vcn idle */ + r = SOC15_WAIT_ON_RREG(VCN, i, 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, i, regUVD_LMI_STATUS, tmp, tmp); - 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, regUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; + + /* disable LMI UMC channel */ + tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2); + tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; + WREG32_SOC15(VCN, i, 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, i, regUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; - /* disable LMI UMC channel */ - tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2); - tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; - WREG32_SOC15(VCN, i, 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, i, regUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + /* block VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), + UVD_RB_ARB_CTRL__VCPU_DIS_MASK, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - /* block VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_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, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - /* disable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~(UVD_VCPU_CNTL__CLK_EN_MASK)); - - /* apply soft reset */ - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - - /* clear status */ - WREG32_SOC15(VCN, i, regUVD_STATUS, 0); - - /* enable VCN power gating */ - vcn_v5_0_0_enable_static_power_gating(adev, i); - } + /* reset VCPU */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pm.dpm_enabled) - amdgpu_dpm_enable_vcn(adev, false, i); - } + /* disable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~(UVD_VCPU_CNTL__CLK_EN_MASK)); - return 0; + /* apply soft reset */ + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + + /* clear status */ + WREG32_SOC15(VCN, i, regUVD_STATUS, 0); + + /* enable VCN power gating */ + vcn_v5_0_0_enable_static_power_gating(vinst); + +done: + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_vcn(adev, false, i); + + return r; } /** * vcn_v5_0_0_pause_dpg_mode - VCN pause with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @new_state: pause state * * Pause dpg mode for VCN block */ -static int vcn_v5_0_0_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx, - struct dpg_pause_state *new_state) +static int vcn_v5_0_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; int ret_code; @@ -1192,13 +1223,13 @@ static void vcn_v5_0_0_set_unified_ring_funcs(struct amdgpu_device *adev) /** * vcn_v5_0_0_is_idle - check VCN block is idle * - * @handle: amdgpu_device pointer + * @ip_block: Pointer to the amdgpu_ip_block structure * * Check whether VCN block is idle */ -static bool vcn_v5_0_0_is_idle(void *handle) +static bool vcn_v5_0_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -1252,45 +1283,38 @@ static int vcn_v5_0_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; if (enable) { if (RREG32_SOC15(VCN, i, regUVD_STATUS) != UVD_STATUS__IDLE) return -EBUSY; - vcn_v5_0_0_enable_clock_gating(adev, i); + vcn_v5_0_0_enable_clock_gating(vinst); } else { - vcn_v5_0_0_disable_clock_gating(adev, i); + vcn_v5_0_0_disable_clock_gating(vinst); } } return 0; } -/** - * vcn_v5_0_0_set_powergating_state - set VCN block powergating state - * - * @ip_block: amdgpu_ip_block pointer - * @state: power gating state - * - * Set VCN block powergating state - */ -static int vcn_v5_0_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v5_0_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret; + int ret = 0; - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v5_0_0_stop(adev); + ret = vcn_v5_0_0_stop(vinst); else - ret = vcn_v5_0_0_start(adev); + ret = vcn_v5_0_0_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -1358,7 +1382,7 @@ static void vcn_v5_0_0_set_irq_funcs(struct amdgpu_device *adev) if (adev->vcn.harvest_config & (1 << i)) continue; - adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v5_0_0_irq_funcs; } } @@ -1436,7 +1460,7 @@ static const struct amd_ip_funcs vcn_v5_0_0_ip_funcs = { .is_idle = vcn_v5_0_0_is_idle, .wait_for_idle = vcn_v5_0_0_wait_for_idle, .set_clockgating_state = vcn_v5_0_0_set_clockgating_state, - .set_powergating_state = vcn_v5_0_0_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v5_0_0_dump_ip_state, .print_ip_state = vcn_v5_0_0_print_ip_state, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c index 288a77179036..581d8629b9d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c @@ -29,6 +29,7 @@ #include "soc15d.h" #include "soc15_hw_ip.h" #include "vcn_v2_0.h" +#include "vcn_v4_0_3.h" #include "vcn/vcn_5_0_0_offset.h" #include "vcn/vcn_5_0_0_sh_mask.h" @@ -40,8 +41,8 @@ static void vcn_v5_0_1_set_unified_ring_funcs(struct amdgpu_device *adev); static void vcn_v5_0_1_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v5_0_1_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); +static int vcn_v5_0_1_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); static void vcn_v5_0_1_unified_ring_set_wptr(struct amdgpu_ring *ring); /** @@ -55,14 +56,40 @@ static void vcn_v5_0_1_unified_ring_set_wptr(struct amdgpu_ring *ring); static int vcn_v5_0_1_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i, r; - /* re-use enc ring as unified ring */ - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) + /* re-use enc ring as unified ring */ + adev->vcn.inst[i].num_enc_rings = 1; vcn_v5_0_1_set_unified_ring_funcs(adev); vcn_v5_0_1_set_irq_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + adev->vcn.inst[i].set_pg_state = vcn_v5_0_1_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + + return 0; +} + +static void vcn_v5_0_1_fw_shared_init(struct amdgpu_device *adev, int inst_idx) +{ + struct amdgpu_vcn5_fw_shared *fw_shared; + + fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; + + if (fw_shared->sq.is_enabled) + return; + fw_shared->present_flag_0 = + cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE); + fw_shared->sq.is_enabled = 1; + + if (amdgpu_vcnfw_log) + amdgpu_vcn_fwlog_init(&adev->vcn.inst[inst_idx]); } /** @@ -78,16 +105,6 @@ static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block) struct amdgpu_ring *ring; int i, r, vcn_inst; - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; - - amdgpu_vcn_setup_ucode(adev); - - r = amdgpu_vcn_resume(adev); - if (r) - return r; - /* VCN UNIFIED TRAP */ r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, VCN_5_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst->irq); @@ -95,10 +112,18 @@ static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block) return r; for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_vcn5_fw_shared *fw_shared; - vcn_inst = GET_INST(VCN, i); + r = amdgpu_vcn_sw_init(adev, i); + if (r) + return r; + + amdgpu_vcn_setup_ucode(adev, i); + + r = amdgpu_vcn_resume(adev, i); + if (r) + return r; + ring = &adev->vcn.inst[i].ring_enc[0]; ring->use_doorbell = true; ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 9 * vcn_inst; @@ -111,12 +136,7 @@ static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - 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_vcnfw_log) - amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); + vcn_v5_0_1_fw_shared_init(adev, i); } /* TODO: Add queue reset mask when FW fully supports it */ @@ -142,7 +162,7 @@ static int vcn_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block) if (drm_dev_enter(adev_to_drm(adev), &idx)) { for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + volatile struct amdgpu_vcn5_fw_shared *fw_shared; fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; fw_shared->present_flag_0 = 0; @@ -152,17 +172,23 @@ static int vcn_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block) drm_dev_exit(idx); } - r = amdgpu_vcn_suspend(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; + } - r = amdgpu_vcn_sw_fini(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } amdgpu_vcn_sysfs_reset_mask_fini(adev); kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -178,6 +204,8 @@ static int vcn_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block) struct amdgpu_ring *ring; int i, r, vcn_inst; + if (RREG32_SOC15(VCN, GET_INST(VCN, 0), regVCN_RRMT_CNTL) & 0x100) + adev->vcn.caps |= AMDGPU_VCN_CAPS(RRMT_ENABLED); for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { vcn_inst = GET_INST(VCN, i); ring = &adev->vcn.inst[i].ring_enc[0]; @@ -188,6 +216,9 @@ static int vcn_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block) 9 * vcn_inst), adev->vcn.inst[i].aid_id); + /* Re-init fw_shared, if required */ + vcn_v5_0_1_fw_shared_init(adev, i); + r = amdgpu_ring_test_helper(ring); if (r) return r; @@ -206,8 +237,15 @@ static int vcn_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block) static int vcn_v5_0_1_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + + cancel_delayed_work_sync(&adev->vcn.inst[i].idle_work); + if (vinst->cur_state != AMD_PG_STATE_GATE) + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); + } return 0; } @@ -222,13 +260,17 @@ static int vcn_v5_0_1_hw_fini(struct amdgpu_ip_block *ip_block) static int vcn_v5_0_1_suspend(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; - int r; + int r, i; r = vcn_v5_0_1_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(ip_block->adev, i); + if (r) + return r; + } return r; } @@ -243,11 +285,18 @@ static int vcn_v5_0_1_suspend(struct amdgpu_ip_block *ip_block) static int vcn_v5_0_1_resume(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; - int r; + int r, i; - r = amdgpu_vcn_resume(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + + if (amdgpu_in_reset(adev)) + vinst->cur_state = AMD_PG_STATE_GATE; + + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v5_0_1_hw_init(ip_block); @@ -257,13 +306,14 @@ static int vcn_v5_0_1_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v5_0_1_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v5_0_1_mc_resume(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_1_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t offset, size, vcn_inst; const struct common_firmware_header *hdr; @@ -313,20 +363,22 @@ static void vcn_v5_0_1_mc_resume(struct amdgpu_device *adev, int inst) upper_32_bits(adev->vcn.inst[inst].fw_shared.gpu_addr)); WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_NONCACHE_OFFSET0, 0); WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_NONCACHE_SIZE0, - AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn4_fw_shared))); + AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn5_fw_shared))); } /** * vcn_v5_0_1_mc_resume_dpg_mode - memory controller programming for dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Let the VCN memory controller know it's offsets with dpg mode */ -static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -421,7 +473,7 @@ static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i VCN, 0, regUVD_VCPU_NONCACHE_OFFSET0), 0, 0, indirect); WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET( VCN, 0, regUVD_VCPU_NONCACHE_SIZE0), - AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn4_fw_shared)), 0, indirect); + AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn5_fw_shared)), 0, indirect); /* VCN global tiling registers */ WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET( @@ -431,39 +483,39 @@ static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i /** * vcn_v5_0_1_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v5_0_1_disable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_1_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { } /** * vcn_v5_0_1_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v5_0_1_enable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_1_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { } /** * vcn_v5_0_1_start_dpg_mode - VCN start with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Start VCN block with dpg mode */ -static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared = + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; + volatile struct amdgpu_vcn5_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; int vcn_inst; @@ -510,7 +562,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET( VCN, 0, regUVD_LMI_CTRL), tmp, 0, indirect); - vcn_v5_0_1_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v5_0_1_mc_resume_dpg_mode(vinst, indirect); tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); tmp |= UVD_VCPU_CNTL__CLK_EN_MASK; @@ -564,150 +616,148 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b /** * vcn_v5_0_1_start - VCN start * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Start VCN block */ -static int vcn_v5_0_1_start(struct amdgpu_device *adev) +static int vcn_v5_0_1_start(struct amdgpu_vcn_inst *vinst) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; + volatile struct amdgpu_vcn5_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t tmp; - int i, j, k, r, vcn_inst; + int j, k, r, vcn_inst; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v5_0_1_start_dpg_mode(adev, i, adev->vcn.indirect_sram); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + return vcn_v5_0_1_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); - vcn_inst = GET_INST(VCN, i); + 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); - - /* 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); - - vcn_v5_0_1_mc_resume(adev, i); - - /* VCN global tiling registers */ - 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(100); - if (amdgpu_emu_mode == 1) - msleep(20); - } + /* set VCN status busy */ + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; + WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp); + + /* 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); + + vcn_v5_0_1_mc_resume(vinst); - if (amdgpu_emu_mode == 1) { - r = -1; - if (status & 2) { - r = 0; - break; - } - } else { + /* VCN global tiling registers */ + 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(100); + if (amdgpu_emu_mode == 1) + msleep(20); + } + + if (amdgpu_emu_mode == 1) { + r = -1; + if (status & 2) { r = 0; - if (status & 2) - break; - - dev_err(adev->dev, - "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i); - 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); - - mdelay(10); - r = -1; + break; } + } else { + r = 0; + if (status & 2) + break; + + dev_err(adev->dev, + "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i); + 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); + + mdelay(10); + r = -1; } + } - if (r) { - dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); - return r; - } + if (r) { + dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); + return r; + } - /* 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); + /* 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); - /* clear the busy bit of VCN_STATUS */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0, - ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); + /* clear the busy bit of VCN_STATUS */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0, + ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); - ring = &adev->vcn.inst[i].ring_enc[0]; + ring = &adev->vcn.inst[i].ring_enc[0]; - WREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL, - ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | - VCN_RB1_DB_CTRL__EN_MASK); + WREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL, + ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | + VCN_RB1_DB_CTRL__EN_MASK); - /* Read DB_CTRL to flush the write DB_CTRL command. */ - RREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL); + /* Read DB_CTRL to flush the write DB_CTRL command. */ + RREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO, ring->gpu_addr); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE, ring->ring_size / 4); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO, ring->gpu_addr); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE, ring->ring_size / 4); - tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); - tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); - WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; - 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__RB1_EN_MASK); + WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0); - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, tmp); - ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR); + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, tmp); + ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR); - tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); - tmp |= VCN_RB_ENABLE__RB1_EN_MASK; - WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); - } + tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); + tmp |= VCN_RB_ENABLE__RB1_EN_MASK; + WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); return 0; } @@ -715,13 +765,14 @@ static int vcn_v5_0_1_start(struct amdgpu_device *adev) /** * vcn_v5_0_1_stop_dpg_mode - VCN stop with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * * Stop VCN block with dpg mode */ -static void vcn_v5_0_1_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static void vcn_v5_0_1_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t tmp; int vcn_inst; @@ -743,75 +794,75 @@ static void vcn_v5_0_1_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) /** * vcn_v5_0_1_stop - VCN stop * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Stop VCN block */ -static int vcn_v5_0_1_stop(struct amdgpu_device *adev) +static int vcn_v5_0_1_stop(struct amdgpu_vcn_inst *vinst) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; + volatile struct amdgpu_vcn5_fw_shared *fw_shared; uint32_t tmp; - int i, r = 0, vcn_inst; + int r = 0, vcn_inst; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - vcn_inst = GET_INST(VCN, i); + vcn_inst = GET_INST(VCN, i); - 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[i].fw_shared.cpu_addr; + fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - vcn_v5_0_1_stop_dpg_mode(adev, i); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + vcn_v5_0_1_stop_dpg_mode(vinst); + return 0; + } - /* wait for vcn idle */ - r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); - if (r) - return r; + /* wait for vcn idle */ + r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_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, vcn_inst, regUVD_LMI_STATUS, tmp, tmp); - 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, vcn_inst, regUVD_LMI_STATUS, tmp, tmp); + if (r) + return r; - /* disable LMI 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) - return r; + /* disable LMI 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) + return r; - /* block 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); - - /* reset VCPU */ - 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)); - - /* apply soft reset */ - 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); - - /* clear status */ - WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0); - } + /* block 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); + + /* reset VCPU */ + 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)); + + /* apply soft reset */ + 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); + + /* clear status */ + WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0); return 0; } @@ -883,16 +934,17 @@ static const struct amdgpu_ring_funcs vcn_v5_0_1_unified_ring_vm_funcs = { .get_rptr = vcn_v5_0_1_unified_ring_get_rptr, .get_wptr = vcn_v5_0_1_unified_ring_get_wptr, .set_wptr = vcn_v5_0_1_unified_ring_set_wptr, - .emit_frame_size = - SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 + - SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 4 + - 4 + /* vcn_v2_0_enc_ring_emit_vm_flush */ - 5 + 5 + /* vcn_v2_0_enc_ring_emit_fence x2 vm fence */ - 1, /* vcn_v2_0_enc_ring_insert_end */ + .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 + + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 4 + + 4 + /* vcn_v2_0_enc_ring_emit_vm_flush */ + 5 + + 5 + /* vcn_v2_0_enc_ring_emit_fence x2 vm fence */ + 1, /* vcn_v2_0_enc_ring_insert_end */ .emit_ib_size = 5, /* vcn_v2_0_enc_ring_emit_ib */ .emit_ib = vcn_v2_0_enc_ring_emit_ib, .emit_fence = vcn_v2_0_enc_ring_emit_fence, - .emit_vm_flush = vcn_v2_0_enc_ring_emit_vm_flush, + .emit_vm_flush = vcn_v4_0_3_enc_ring_emit_vm_flush, + .emit_hdp_flush = vcn_v4_0_3_ring_emit_hdp_flush, .test_ring = amdgpu_vcn_enc_ring_test_ring, .test_ib = amdgpu_vcn_unified_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, @@ -900,8 +952,8 @@ static const struct amdgpu_ring_funcs vcn_v5_0_1_unified_ring_vm_funcs = { .pad_ib = amdgpu_ring_generic_pad_ib, .begin_use = amdgpu_vcn_ring_begin_use, .end_use = amdgpu_vcn_ring_end_use, - .emit_wreg = vcn_v2_0_enc_ring_emit_wreg, - .emit_reg_wait = vcn_v2_0_enc_ring_emit_reg_wait, + .emit_wreg = vcn_v4_0_3_enc_ring_emit_wreg, + .emit_reg_wait = vcn_v4_0_3_enc_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, }; @@ -927,13 +979,13 @@ static void vcn_v5_0_1_set_unified_ring_funcs(struct amdgpu_device *adev) /** * vcn_v5_0_1_is_idle - check VCN block is idle * - * @handle: amdgpu_device pointer + * @ip_block: Pointer to the amdgpu_ip_block structure * * Check whether VCN block is idle */ -static bool vcn_v5_0_1_is_idle(void *handle) +static bool vcn_v5_0_1_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) @@ -980,42 +1032,35 @@ static int vcn_v5_0_1_set_clockgating_state(struct amdgpu_ip_block *ip_block, int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (enable) { if (RREG32_SOC15(VCN, GET_INST(VCN, i), regUVD_STATUS) != UVD_STATUS__IDLE) return -EBUSY; - vcn_v5_0_1_enable_clock_gating(adev, i); + vcn_v5_0_1_enable_clock_gating(vinst); } else { - vcn_v5_0_1_disable_clock_gating(adev, i); + vcn_v5_0_1_disable_clock_gating(vinst); } } return 0; } -/** - * vcn_v5_0_1_set_powergating_state - set VCN block powergating state - * - * @ip_block: Pointer to the amdgpu_ip_block for this hw instance. - * @state: power gating state - * - * Set VCN block powergating state - */ -static int vcn_v5_0_1_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v5_0_1_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret; + int ret = 0; - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v5_0_1_stop(adev); + ret = vcn_v5_0_1_stop(vinst); else - ret = vcn_v5_0_1_start(adev); + ret = vcn_v5_0_1_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -1098,7 +1143,7 @@ static const struct amd_ip_funcs vcn_v5_0_1_ip_funcs = { .soft_reset = NULL, .post_soft_reset = NULL, .set_clockgating_state = vcn_v5_0_1_set_clockgating_state, - .set_powergating_state = vcn_v5_0_1_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v5_0_0_dump_ip_state, .print_ip_state = vcn_v5_0_0_print_ip_state, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.h b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.h index 82ac709f44bf..8fd90bd10807 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.h +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.h @@ -24,6 +24,9 @@ #ifndef __VCN_v5_0_1_H__ #define __VCN_v5_0_1_H__ +#define regVCN_RRMT_CNTL 0x0940 +#define regVCN_RRMT_CNTL_BASE_IDX 1 + extern const struct amdgpu_ip_block_version vcn_v5_0_1_ip_block; #endif /* __VCN_v5_0_1_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c index 98fc6941159e..eb16916c6473 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c @@ -555,7 +555,7 @@ static int vega10_ih_resume(struct amdgpu_ip_block *ip_block) return vega10_ih_hw_init(ip_block); } -static bool vega10_ih_is_idle(void *handle) +static bool vega10_ih_is_idle(struct amdgpu_ip_block *ip_block) { /* todo */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c index e9e3b2ed4b7b..faa0dd75dd6d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c @@ -651,7 +651,7 @@ static int vega20_ih_resume(struct amdgpu_ip_block *ip_block) return vega20_ih_hw_init(ip_block); } -static bool vega20_ih_is_idle(void *handle) +static bool vega20_ih_is_idle(struct amdgpu_ip_block *ip_block) { /* todo */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 12fe571787f4..3bbbb75242d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -1736,7 +1736,7 @@ static int vi_common_resume(struct amdgpu_ip_block *ip_block) return vi_common_hw_init(ip_block); } -static bool vi_common_is_idle(void *handle) +static bool vi_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdkfd/Makefile b/drivers/gpu/drm/amd/amdkfd/Makefile index 0d3d8972240d..0ce08113c9f0 100644 --- a/drivers/gpu/drm/amd/amdkfd/Makefile +++ b/drivers/gpu/drm/amd/amdkfd/Makefile @@ -27,7 +27,6 @@ AMDKFD_FILES := $(AMDKFD_PATH)/kfd_module.o \ $(AMDKFD_PATH)/kfd_device.o \ $(AMDKFD_PATH)/kfd_chardev.o \ $(AMDKFD_PATH)/kfd_topology.o \ - $(AMDKFD_PATH)/kfd_pasid.o \ $(AMDKFD_PATH)/kfd_doorbell.o \ $(AMDKFD_PATH)/kfd_flat_memory.o \ $(AMDKFD_PATH)/kfd_process.o \ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 433de9e9a77e..1e9dd00620bf 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -212,6 +212,11 @@ static int set_queue_properties_from_user(struct queue_properties *q_properties, return -EINVAL; } + if (args->ring_size < KFD_MIN_QUEUE_RING_SIZE) { + args->ring_size = KFD_MIN_QUEUE_RING_SIZE; + pr_debug("Size lower. clamped to KFD_MIN_QUEUE_RING_SIZE"); + } + if (!access_ok((const void __user *) args->read_pointer_address, sizeof(uint32_t))) { pr_err("Can't access read pointer\n"); @@ -461,6 +466,11 @@ static int kfd_ioctl_update_queue(struct file *filp, struct kfd_process *p, return -EINVAL; } + if (args->ring_size < KFD_MIN_QUEUE_RING_SIZE) { + args->ring_size = KFD_MIN_QUEUE_RING_SIZE; + pr_debug("Size lower. clamped to KFD_MIN_QUEUE_RING_SIZE"); + } + properties.queue_address = args->ring_base_address; properties.queue_size = args->ring_size; properties.queue_percent = args->queue_percentage & 0xFF; @@ -596,7 +606,8 @@ static int kfd_ioctl_set_memory_policy(struct file *filep, default_policy, alternate_policy, (void __user *)args->alternate_aperture_base, - args->alternate_aperture_size)) + args->alternate_aperture_size, + args->misc_process_flag)) err = -EINVAL; out: diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 70b3ae0b74fe..4a7180b46b71 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -2133,9 +2133,6 @@ static int kfd_fill_gpu_direct_io_link_to_cpu(int *avail_size, bool ext_cpu = KFD_GC_VERSION(kdev) != IP_VERSION(9, 4, 3); int mem_bw = 819200, weight = ext_cpu ? KFD_CRAT_XGMI_WEIGHT : KFD_CRAT_INTRA_SOCKET_WEIGHT; - uint32_t bandwidth = ext_cpu ? amdgpu_amdkfd_get_xgmi_bandwidth_mbytes( - kdev->adev, NULL, true) : mem_bw; - /* * with host gpu xgmi link, host can access gpu memory whether * or not pcie bar type is large, so always create bidirectional @@ -2144,8 +2141,16 @@ static int kfd_fill_gpu_direct_io_link_to_cpu(int *avail_size, sub_type_hdr->flags |= CRAT_IOLINK_FLAGS_BI_DIRECTIONAL; sub_type_hdr->io_interface_type = CRAT_IOLINK_TYPE_XGMI; sub_type_hdr->weight_xgmi = weight; - sub_type_hdr->minimum_bandwidth_mbs = bandwidth; - sub_type_hdr->maximum_bandwidth_mbs = bandwidth; + if (ext_cpu) { + amdgpu_xgmi_get_bandwidth(kdev->adev, NULL, + AMDGPU_XGMI_BW_MODE_PER_LINK, + AMDGPU_XGMI_BW_UNIT_MBYTES, + &sub_type_hdr->minimum_bandwidth_mbs, + &sub_type_hdr->maximum_bandwidth_mbs); + } else { + sub_type_hdr->minimum_bandwidth_mbs = mem_bw; + sub_type_hdr->maximum_bandwidth_mbs = mem_bw; + } } else { sub_type_hdr->io_interface_type = CRAT_IOLINK_TYPE_PCIEXPRESS; sub_type_hdr->minimum_bandwidth_mbs = @@ -2198,12 +2203,12 @@ static int kfd_fill_gpu_xgmi_link_to_gpu(int *avail_size, if (use_ta_info) { sub_type_hdr->weight_xgmi = KFD_CRAT_XGMI_WEIGHT * - amdgpu_amdkfd_get_xgmi_hops_count(kdev->adev, peer_kdev->adev); - sub_type_hdr->maximum_bandwidth_mbs = - amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(kdev->adev, - peer_kdev->adev, false); - sub_type_hdr->minimum_bandwidth_mbs = sub_type_hdr->maximum_bandwidth_mbs ? - amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(kdev->adev, NULL, true) : 0; + amdgpu_xgmi_get_hops_count(kdev->adev, peer_kdev->adev); + amdgpu_xgmi_get_bandwidth(kdev->adev, peer_kdev->adev, + AMDGPU_XGMI_BW_MODE_PER_PEER, + AMDGPU_XGMI_BW_UNIT_MBYTES, + &sub_type_hdr->minimum_bandwidth_mbs, + &sub_type_hdr->maximum_bandwidth_mbs); } else { bool is_single_hop = kdev->kfd == peer_kdev->kfd; int weight = is_single_hop ? KFD_CRAT_INTRA_SOCKET_WEIGHT : diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 9d20e169ec4a..b9c82be6ce13 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -590,9 +590,13 @@ static int kfd_gws_init(struct kfd_node *node) && kfd->mec2_fw_version >= 0x6b) || (KFD_GC_VERSION(node) >= IP_VERSION(11, 0, 0) && KFD_GC_VERSION(node) < IP_VERSION(12, 0, 0) - && mes_rev >= 68)))) + && mes_rev >= 68) || + (KFD_GC_VERSION(node) >= IP_VERSION(12, 0, 0))))) { + if (KFD_GC_VERSION(node) >= IP_VERSION(12, 0, 0)) + node->adev->gds.gws_size = 64; ret = amdgpu_amdkfd_alloc_gws(node->adev, node->adev->gds.gws_size, &node->gws); + } return ret; } @@ -1600,6 +1604,11 @@ int kfd_debugfs_hang_hws(struct kfd_node *dev) return -EINVAL; } + if (dev->kfd->shared_resources.enable_mes) { + dev_err(dev->adev->dev, "Inducing MES hang is not supported\n"); + return -EINVAL; + } + return dqm_debugfs_hang_hws(dev->dqm); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 195085079eb2..2afcc1b4856a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -36,6 +36,7 @@ #include "kfd_kernel_queue.h" #include "amdgpu_amdkfd.h" #include "amdgpu_reset.h" +#include "amdgpu_sdma.h" #include "mes_v11_api_def.h" #include "kfd_debug.h" @@ -66,7 +67,8 @@ static inline void deallocate_hqd(struct device_queue_manager *dqm, static int allocate_hqd(struct device_queue_manager *dqm, struct queue *q); static int allocate_sdma_queue(struct device_queue_manager *dqm, struct queue *q, const uint32_t *restore_sdma_id); -static void kfd_process_hw_exception(struct work_struct *work); + +static int reset_queues_on_hws_hang(struct device_queue_manager *dqm, bool is_sdma); static inline enum KFD_MQD_TYPE get_mqd_type_from_queue_type(enum kfd_queue_type type) @@ -170,7 +172,7 @@ static void kfd_hws_hang(struct device_queue_manager *dqm) /* * Issue a GPU reset if HWS is unresponsive */ - schedule_work(&dqm->hw_exception_work); + amdgpu_amdkfd_gpu_reset(dqm->dev->adev); } static int convert_to_mes_queue_type(int queue_type) @@ -207,21 +209,6 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, if (!down_read_trylock(&adev->reset_domain->sem)) return -EIO; - if (!pdd->proc_ctx_cpu_ptr) { - r = amdgpu_amdkfd_alloc_gtt_mem(adev, - AMDGPU_MES_PROC_CTX_SIZE, - &pdd->proc_ctx_bo, - &pdd->proc_ctx_gpu_addr, - &pdd->proc_ctx_cpu_ptr, - false); - if (r) { - dev_err(adev->dev, - "failed to allocate process context bo\n"); - return r; - } - memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); - } - memset(&queue_input, 0x0, sizeof(struct mes_add_queue_input)); queue_input.process_id = pdd->pasid; queue_input.page_table_base_addr = qpd->page_table_base; @@ -1755,7 +1742,6 @@ static int initialize_cpsch(struct device_queue_manager *dqm) dqm->active_cp_queue_count = 0; dqm->gws_queue_count = 0; dqm->active_runlist = false; - INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception); dqm->trap_debug_vmid = 0; init_sdma_bitmaps(dqm); @@ -2222,8 +2208,7 @@ static struct queue *find_queue_by_address(struct device_queue_manager *dqm, uin return NULL; } -/* only for compute queue */ -static int reset_queues_on_hws_hang(struct device_queue_manager *dqm) +static int reset_hung_queues(struct device_queue_manager *dqm) { int r = 0, reset_count = 0, i; @@ -2276,6 +2261,104 @@ reset_fail: return r; } +static bool sdma_has_hang(struct device_queue_manager *dqm) +{ + int engine_start = dqm->dev->node_id * get_num_all_sdma_engines(dqm); + int engine_end = engine_start + get_num_all_sdma_engines(dqm); + int num_queues_per_eng = dqm->dev->kfd->device_info.num_sdma_queues_per_engine; + int i, j; + + for (i = engine_start; i < engine_end; i++) { + for (j = 0; j < num_queues_per_eng; j++) { + if (!dqm->dev->kfd2kgd->hqd_sdma_get_doorbell(dqm->dev->adev, i, j)) + continue; + + return true; + } + } + + return false; +} + +static bool set_sdma_queue_as_reset(struct device_queue_manager *dqm, + uint32_t doorbell_off) +{ + struct device_process_node *cur; + struct qcm_process_device *qpd; + struct queue *q; + + list_for_each_entry(cur, &dqm->queues, list) { + qpd = cur->qpd; + list_for_each_entry(q, &qpd->queues_list, list) { + if ((q->properties.type == KFD_QUEUE_TYPE_SDMA || + q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) && + q->properties.doorbell_off == doorbell_off) { + set_queue_as_reset(dqm, q, qpd); + return true; + } + } + } + + return false; +} + +static int reset_hung_queues_sdma(struct device_queue_manager *dqm) +{ + int engine_start = dqm->dev->node_id * get_num_all_sdma_engines(dqm); + int engine_end = engine_start + get_num_all_sdma_engines(dqm); + int num_queues_per_eng = dqm->dev->kfd->device_info.num_sdma_queues_per_engine; + int r = 0, i, j; + + if (dqm->is_hws_hang) + return -EIO; + + /* Scan for hung HW queues and reset engine. */ + dqm->detect_hang_count = 0; + for (i = engine_start; i < engine_end; i++) { + for (j = 0; j < num_queues_per_eng; j++) { + uint32_t doorbell_off = + dqm->dev->kfd2kgd->hqd_sdma_get_doorbell(dqm->dev->adev, i, j); + + if (!doorbell_off) + continue; + + /* Reset engine and check. */ + if (amdgpu_sdma_reset_engine(dqm->dev->adev, i, false) || + dqm->dev->kfd2kgd->hqd_sdma_get_doorbell(dqm->dev->adev, i, j) || + !set_sdma_queue_as_reset(dqm, doorbell_off)) { + r = -ENOTRECOVERABLE; + goto reset_fail; + } + + /* Should only expect one queue active per engine */ + dqm->detect_hang_count++; + break; + } + } + + /* Signal process reset */ + if (dqm->detect_hang_count) + kfd_signal_reset_event(dqm->dev); + else + r = -ENOTRECOVERABLE; + +reset_fail: + dqm->detect_hang_count = 0; + + return r; +} + +static int reset_queues_on_hws_hang(struct device_queue_manager *dqm, bool is_sdma) +{ + while (halt_if_hws_hang) + schedule(); + + if (!amdgpu_gpu_recovery) + return -ENOTRECOVERABLE; + + return is_sdma ? reset_hung_queues_sdma(dqm) : reset_hung_queues(dqm); +} + /* dqm->lock mutex has to be locked before calling this function */ static int unmap_queues_cpsch(struct device_queue_manager *dqm, enum kfd_unmap_queues_filter filter, @@ -2326,16 +2409,13 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, * check those fields */ mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ]; - if (mqd_mgr->check_preemption_failed(mqd_mgr, dqm->packet_mgr.priv_queue->queue->mqd)) { - while (halt_if_hws_hang) - schedule(); - if (reset_queues_on_hws_hang(dqm)) { - dqm->is_hws_hang = true; - kfd_hws_hang(dqm); - retval = -ETIME; - goto out; - } - } + if (mqd_mgr->check_preemption_failed(mqd_mgr, dqm->packet_mgr.priv_queue->queue->mqd) && + reset_queues_on_hws_hang(dqm, false)) + goto reset_fail; + + /* Check for SDMA hang and attempt SDMA reset */ + if (sdma_has_hang(dqm) && reset_queues_on_hws_hang(dqm, true)) + goto reset_fail; /* We need to reset the grace period value for this device */ if (grace_period != USE_DEFAULT_GRACE_PERIOD) { @@ -2346,10 +2426,15 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, pm_release_ib(&dqm->packet_mgr); dqm->active_runlist = false; - out: up_read(&dqm->dev->adev->reset_domain->sem); return retval; + +reset_fail: + dqm->is_hws_hang = true; + kfd_hws_hang(dqm); + up_read(&dqm->dev->adev->reset_domain->sem); + return -ETIME; } /* only for compute queue */ @@ -2506,20 +2591,13 @@ failed_try_destroy_debugged_queue: return retval; } -/* - * Low bits must be 0000/FFFF as required by HW, high bits must be 0 to - * stay in user mode. - */ -#define APE1_FIXED_BITS_MASK 0xFFFF80000000FFFFULL -/* APE1 limit is inclusive and 64K aligned. */ -#define APE1_LIMIT_ALIGNMENT 0xFFFF - static bool set_cache_memory_policy(struct device_queue_manager *dqm, struct qcm_process_device *qpd, enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size) + uint64_t alternate_aperture_size, + u32 misc_process_properties) { bool retval = true; @@ -2528,41 +2606,17 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm, dqm_lock(dqm); - if (alternate_aperture_size == 0) { - /* base > limit disables APE1 */ - qpd->sh_mem_ape1_base = 1; - qpd->sh_mem_ape1_limit = 0; - } else { - /* - * In FSA64, APE1_Base[63:0] = { 16{SH_MEM_APE1_BASE[31]}, - * SH_MEM_APE1_BASE[31:0], 0x0000 } - * APE1_Limit[63:0] = { 16{SH_MEM_APE1_LIMIT[31]}, - * SH_MEM_APE1_LIMIT[31:0], 0xFFFF } - * Verify that the base and size parameters can be - * represented in this format and convert them. - * Additionally restrict APE1 to user-mode addresses. - */ - - uint64_t base = (uintptr_t)alternate_aperture_base; - uint64_t limit = base + alternate_aperture_size - 1; - - if (limit <= base || (base & APE1_FIXED_BITS_MASK) != 0 || - (limit & APE1_FIXED_BITS_MASK) != APE1_LIMIT_ALIGNMENT) { - retval = false; - goto out; - } - - qpd->sh_mem_ape1_base = base >> 16; - qpd->sh_mem_ape1_limit = limit >> 16; - } - retval = dqm->asic_ops.set_cache_memory_policy( dqm, qpd, default_policy, alternate_policy, alternate_aperture_base, - alternate_aperture_size); + alternate_aperture_size, + misc_process_properties); + + if (retval) + goto out; if ((dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS) && (qpd->vmid != 0)) program_sh_mem_settings(dqm, qpd); @@ -3095,13 +3149,6 @@ int kfd_evict_process_device(struct kfd_process_device *pdd) return ret; } -static void kfd_process_hw_exception(struct work_struct *work) -{ - struct device_queue_manager *dqm = container_of(work, - struct device_queue_manager, hw_exception_work); - amdgpu_amdkfd_gpu_reset(dqm->dev->adev); -} - int reserve_debug_trap_vmid(struct device_queue_manager *dqm, struct qcm_process_device *qpd) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index 09ab36f8e8c6..122eb745e9c4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -174,7 +174,8 @@ struct device_queue_manager_ops { enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size); + uint64_t alternate_aperture_size, + u32 misc_process_properties); int (*process_termination)(struct device_queue_manager *dqm, struct qcm_process_device *qpd); @@ -210,7 +211,8 @@ struct device_queue_manager_asic_ops { enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size); + uint64_t alternate_aperture_size, + u32 misc_process_properties); void (*init_sdma_vm)(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd); @@ -269,7 +271,6 @@ struct device_queue_manager { /* hw exception */ bool is_hws_hang; bool is_resetting; - struct work_struct hw_exception_work; struct kfd_mem_obj hiq_sdma_mqd; bool sched_running; bool sched_halt; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c index d4d95c7f2e5d..0508ef5a41d7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c @@ -27,12 +27,21 @@ #include "oss/oss_2_4_sh_mask.h" #include "gca/gfx_7_2_sh_mask.h" +/* + * Low bits must be 0000/FFFF as required by HW, high bits must be 0 to + * stay in user mode. + */ +#define APE1_FIXED_BITS_MASK 0xFFFF80000000FFFFULL +/* APE1 limit is inclusive and 64K aligned. */ +#define APE1_LIMIT_ALIGNMENT 0xFFFF + static bool set_cache_memory_policy_cik(struct device_queue_manager *dqm, struct qcm_process_device *qpd, enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size); + uint64_t alternate_aperture_size, + u32 misc_process_properties); static int update_qpd_cik(struct device_queue_manager *dqm, struct qcm_process_device *qpd); static void init_sdma_vm(struct device_queue_manager *dqm, @@ -80,10 +89,41 @@ static bool set_cache_memory_policy_cik(struct device_queue_manager *dqm, enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size) + uint64_t alternate_aperture_size, + u32 misc_process_properties) { uint32_t default_mtype; uint32_t ape1_mtype; + unsigned int temp; + bool retval = true; + + if (alternate_aperture_size == 0) { + /* base > limit disables APE1 */ + qpd->sh_mem_ape1_base = 1; + qpd->sh_mem_ape1_limit = 0; + } else { + /* + * In FSA64, APE1_Base[63:0] = { 16{SH_MEM_APE1_BASE[31]}, + * SH_MEM_APE1_BASE[31:0], 0x0000 } + * APE1_Limit[63:0] = { 16{SH_MEM_APE1_LIMIT[31]}, + * SH_MEM_APE1_LIMIT[31:0], 0xFFFF } + * Verify that the base and size parameters can be + * represented in this format and convert them. + * Additionally restrict APE1 to user-mode addresses. + */ + + uint64_t base = (uintptr_t)alternate_aperture_base; + uint64_t limit = base + alternate_aperture_size - 1; + + if (limit <= base || (base & APE1_FIXED_BITS_MASK) != 0 || + (limit & APE1_FIXED_BITS_MASK) != APE1_LIMIT_ALIGNMENT) { + retval = false; + goto out; + } + + qpd->sh_mem_ape1_base = base >> 16; + qpd->sh_mem_ape1_limit = limit >> 16; + } default_mtype = (default_policy == cache_policy_coherent) ? MTYPE_NONCACHED : @@ -97,37 +137,22 @@ static bool set_cache_memory_policy_cik(struct device_queue_manager *dqm, | ALIGNMENT_MODE(SH_MEM_ALIGNMENT_MODE_UNALIGNED) | DEFAULT_MTYPE(default_mtype) | APE1_MTYPE(ape1_mtype); - - return true; -} - -static int update_qpd_cik(struct device_queue_manager *dqm, - struct qcm_process_device *qpd) -{ - struct kfd_process_device *pdd; - unsigned int temp; - - pdd = qpd_to_pdd(qpd); - - /* check if sh_mem_config register already configured */ - if (qpd->sh_mem_config == 0) { - qpd->sh_mem_config = - ALIGNMENT_MODE(SH_MEM_ALIGNMENT_MODE_UNALIGNED) | - DEFAULT_MTYPE(MTYPE_NONCACHED) | - APE1_MTYPE(MTYPE_NONCACHED); - qpd->sh_mem_ape1_limit = 0; - qpd->sh_mem_ape1_base = 0; - } - /* On dGPU we're always in GPUVM64 addressing mode with 64-bit * aperture addresses. */ - temp = get_sh_mem_bases_nybble_64(pdd); + temp = get_sh_mem_bases_nybble_64(qpd_to_pdd(qpd)); qpd->sh_mem_bases = compute_sh_mem_bases_64bit(temp); pr_debug("is32bit process: %d sh_mem_bases nybble: 0x%X and register 0x%X\n", qpd->pqm->process->is_32bit_user_mode, temp, qpd->sh_mem_bases); +out: + return retval; +} + +static int update_qpd_cik(struct device_queue_manager *dqm, + struct qcm_process_device *qpd) +{ return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c index 245a90dfc2f6..ba6e3d747ccd 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c @@ -31,10 +31,18 @@ static int update_qpd_v10(struct device_queue_manager *dqm, struct qcm_process_device *qpd); static void init_sdma_vm_v10(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd); +static bool set_cache_memory_policy_v10(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties); void device_queue_manager_init_v10( struct device_queue_manager_asic_ops *asic_ops) { + asic_ops->set_cache_memory_policy = set_cache_memory_policy_v10; asic_ops->update_qpd = update_qpd_v10; asic_ops->init_sdma_vm = init_sdma_vm_v10; asic_ops->mqd_manager_init = mqd_manager_init_v10; @@ -49,27 +57,28 @@ static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd) private_base; } -static int update_qpd_v10(struct device_queue_manager *dqm, - struct qcm_process_device *qpd) +static bool set_cache_memory_policy_v10(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties) { - struct kfd_process_device *pdd; - - pdd = qpd_to_pdd(qpd); - - /* check if sh_mem_config register already configured */ - if (qpd->sh_mem_config == 0) { - qpd->sh_mem_config = - (SH_MEM_ALIGNMENT_MODE_UNALIGNED << - SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | - (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); - qpd->sh_mem_ape1_limit = 0; - qpd->sh_mem_ape1_base = 0; - } - - qpd->sh_mem_bases = compute_sh_mem_bases_64bit(pdd); + qpd->sh_mem_config = (SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | + (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); + qpd->sh_mem_ape1_limit = 0; + qpd->sh_mem_ape1_base = 0; + qpd->sh_mem_bases = compute_sh_mem_bases_64bit(qpd_to_pdd(qpd)); pr_debug("sh_mem_bases 0x%X\n", qpd->sh_mem_bases); + return true; +} +static int update_qpd_v10(struct device_queue_manager *dqm, + struct qcm_process_device *qpd) +{ return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v11.c index 2e129da7acb4..8b447d04558f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v11.c @@ -30,10 +30,18 @@ static int update_qpd_v11(struct device_queue_manager *dqm, struct qcm_process_device *qpd); static void init_sdma_vm_v11(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd); +static bool set_cache_memory_policy_v11(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties); void device_queue_manager_init_v11( struct device_queue_manager_asic_ops *asic_ops) { + asic_ops->set_cache_memory_policy = set_cache_memory_policy_v11; asic_ops->update_qpd = update_qpd_v11; asic_ops->init_sdma_vm = init_sdma_vm_v11; asic_ops->mqd_manager_init = mqd_manager_init_v11; @@ -48,28 +56,29 @@ static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd) private_base; } -static int update_qpd_v11(struct device_queue_manager *dqm, - struct qcm_process_device *qpd) +static bool set_cache_memory_policy_v11(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties) { - struct kfd_process_device *pdd; - - pdd = qpd_to_pdd(qpd); - - /* check if sh_mem_config register already configured */ - if (qpd->sh_mem_config == 0) { - qpd->sh_mem_config = - (SH_MEM_ALIGNMENT_MODE_UNALIGNED << - SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | - (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); - - qpd->sh_mem_ape1_limit = 0; - qpd->sh_mem_ape1_base = 0; - } + qpd->sh_mem_config = (SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | + (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); - qpd->sh_mem_bases = compute_sh_mem_bases_64bit(pdd); + qpd->sh_mem_ape1_limit = 0; + qpd->sh_mem_ape1_base = 0; + qpd->sh_mem_bases = compute_sh_mem_bases_64bit(qpd_to_pdd(qpd)); pr_debug("sh_mem_bases 0x%X\n", qpd->sh_mem_bases); + return true; +} +static int update_qpd_v11(struct device_queue_manager *dqm, + struct qcm_process_device *qpd) +{ return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12.c index 4f3295b29dfb..3550da3a46f9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12.c @@ -30,10 +30,18 @@ static int update_qpd_v12(struct device_queue_manager *dqm, struct qcm_process_device *qpd); static void init_sdma_vm_v12(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd); +static bool set_cache_memory_policy_v12(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties); void device_queue_manager_init_v12( struct device_queue_manager_asic_ops *asic_ops) { + asic_ops->set_cache_memory_policy = set_cache_memory_policy_v12; asic_ops->update_qpd = update_qpd_v12; asic_ops->init_sdma_vm = init_sdma_vm_v12; asic_ops->mqd_manager_init = mqd_manager_init_v12; @@ -48,28 +56,29 @@ static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd) private_base; } -static int update_qpd_v12(struct device_queue_manager *dqm, - struct qcm_process_device *qpd) +static bool set_cache_memory_policy_v12(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties) { - struct kfd_process_device *pdd; - - pdd = qpd_to_pdd(qpd); - - /* check if sh_mem_config register already configured */ - if (qpd->sh_mem_config == 0) { - qpd->sh_mem_config = - (SH_MEM_ALIGNMENT_MODE_UNALIGNED << - SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | - (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); - - qpd->sh_mem_ape1_limit = 0; - qpd->sh_mem_ape1_base = 0; - } + qpd->sh_mem_config = (SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | + (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); - qpd->sh_mem_bases = compute_sh_mem_bases_64bit(pdd); + qpd->sh_mem_ape1_limit = 0; + qpd->sh_mem_ape1_base = 0; + qpd->sh_mem_bases = compute_sh_mem_bases_64bit(qpd_to_pdd(qpd)); pr_debug("sh_mem_bases 0x%X\n", qpd->sh_mem_bases); + return true; +} +static int update_qpd_v12(struct device_queue_manager *dqm, + struct qcm_process_device *qpd) +{ return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c index 67137e674f1d..d794c8172b40 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c @@ -30,10 +30,18 @@ static int update_qpd_v9(struct device_queue_manager *dqm, struct qcm_process_device *qpd); static void init_sdma_vm_v9(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd); +static bool set_cache_memory_policy_v9(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties); void device_queue_manager_init_v9( struct device_queue_manager_asic_ops *asic_ops) { + asic_ops->set_cache_memory_policy = set_cache_memory_policy_v9; asic_ops->update_qpd = update_qpd_v9; asic_ops->init_sdma_vm = init_sdma_vm_v9; asic_ops->mqd_manager_init = mqd_manager_init_v9; @@ -48,10 +56,43 @@ static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd) private_base; } +static bool set_cache_memory_policy_v9(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties) +{ + qpd->sh_mem_config = SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT; + + if (dqm->dev->kfd->noretry) + qpd->sh_mem_config |= 1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT; + + if (KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 4, 3) || + KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 4, 4) || + KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 5, 0)) + qpd->sh_mem_config |= (1 << SH_MEM_CONFIG__F8_MODE__SHIFT); + + if (KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 5, 0)) { + if (misc_process_properties & KFD_PROC_FLAG_MFMA_HIGH_PRECISION) + qpd->sh_mem_config |= 1 << SH_MEM_CONFIG__PRECISION_MODE__SHIFT; + } + + qpd->sh_mem_ape1_limit = 0; + qpd->sh_mem_ape1_base = 0; + qpd->sh_mem_bases = compute_sh_mem_bases_64bit(qpd_to_pdd(qpd)); + + pr_debug("sh_mem_bases 0x%X sh_mem_config 0x%X\n", qpd->sh_mem_bases, + qpd->sh_mem_config); + return true; +} + static int update_qpd_v9(struct device_queue_manager *dqm, struct qcm_process_device *qpd) { - struct kfd_process_device *pdd; + struct kfd_process_device *pdd = qpd_to_pdd(qpd); pdd = qpd_to_pdd(qpd); @@ -64,8 +105,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm, qpd->sh_mem_config |= 1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT; if (KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 4, 3) || - KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 4, 4) || - KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 5, 0)) + KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 4, 4)) qpd->sh_mem_config |= (1 << SH_MEM_CONFIG__F8_MODE__SHIFT); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c index b291ee0fab94..dad83356e976 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c @@ -27,12 +27,21 @@ #include "gca/gfx_8_0_sh_mask.h" #include "oss/oss_3_0_sh_mask.h" +/* + * Low bits must be 0000/FFFF as required by HW, high bits must be 0 to + * stay in user mode. + */ +#define APE1_FIXED_BITS_MASK 0xFFFF80000000FFFFULL +/* APE1 limit is inclusive and 64K aligned. */ +#define APE1_LIMIT_ALIGNMENT 0xFFFF + static bool set_cache_memory_policy_vi(struct device_queue_manager *dqm, struct qcm_process_device *qpd, enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size); + uint64_t alternate_aperture_size, + u32 misc_process_properties); static int update_qpd_vi(struct device_queue_manager *dqm, struct qcm_process_device *qpd); static void init_sdma_vm(struct device_queue_manager *dqm, @@ -81,10 +90,41 @@ static bool set_cache_memory_policy_vi(struct device_queue_manager *dqm, enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size) + uint64_t alternate_aperture_size, + u32 misc_process_properties) { uint32_t default_mtype; uint32_t ape1_mtype; + unsigned int temp; + bool retval = true; + + if (alternate_aperture_size == 0) { + /* base > limit disables APE1 */ + qpd->sh_mem_ape1_base = 1; + qpd->sh_mem_ape1_limit = 0; + } else { + /* + * In FSA64, APE1_Base[63:0] = { 16{SH_MEM_APE1_BASE[31]}, + * SH_MEM_APE1_BASE[31:0], 0x0000 } + * APE1_Limit[63:0] = { 16{SH_MEM_APE1_LIMIT[31]}, + * SH_MEM_APE1_LIMIT[31:0], 0xFFFF } + * Verify that the base and size parameters can be + * represented in this format and convert them. + * Additionally restrict APE1 to user-mode addresses. + */ + + uint64_t base = (uintptr_t)alternate_aperture_base; + uint64_t limit = base + alternate_aperture_size - 1; + + if (limit <= base || (base & APE1_FIXED_BITS_MASK) != 0 || + (limit & APE1_FIXED_BITS_MASK) != APE1_LIMIT_ALIGNMENT) { + retval = false; + goto out; + } + + qpd->sh_mem_ape1_base = base >> 16; + qpd->sh_mem_ape1_limit = limit >> 16; + } default_mtype = (default_policy == cache_policy_coherent) ? MTYPE_UC : @@ -100,40 +140,21 @@ static bool set_cache_memory_policy_vi(struct device_queue_manager *dqm, default_mtype << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT | ape1_mtype << SH_MEM_CONFIG__APE1_MTYPE__SHIFT; - return true; -} - -static int update_qpd_vi(struct device_queue_manager *dqm, - struct qcm_process_device *qpd) -{ - struct kfd_process_device *pdd; - unsigned int temp; - - pdd = qpd_to_pdd(qpd); - - /* check if sh_mem_config register already configured */ - if (qpd->sh_mem_config == 0) { - qpd->sh_mem_config = - SH_MEM_ALIGNMENT_MODE_UNALIGNED << - SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT | - MTYPE_UC << - SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT | - MTYPE_UC << - SH_MEM_CONFIG__APE1_MTYPE__SHIFT; - - qpd->sh_mem_ape1_limit = 0; - qpd->sh_mem_ape1_base = 0; - } - /* On dGPU we're always in GPUVM64 addressing mode with 64-bit * aperture addresses. */ - temp = get_sh_mem_bases_nybble_64(pdd); + temp = get_sh_mem_bases_nybble_64(qpd_to_pdd(qpd)); qpd->sh_mem_bases = compute_sh_mem_bases_64bit(temp); pr_debug("sh_mem_bases nybble: 0x%X and register 0x%X\n", temp, qpd->sh_mem_bases); +out: + return retval; +} +static int update_qpd_vi(struct device_queue_manager *dqm, + struct qcm_process_device *qpd) +{ return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c index 2eff37aaf827..1695dd78ede8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c @@ -107,6 +107,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK | 0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT; + m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT; m->cp_mqd_base_addr_lo = lower_32_bits(addr); @@ -167,10 +169,10 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, m = get_mqd(mqd); - m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK; m->cp_hqd_pq_control |= ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1; - m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; + pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control); m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c index 68dbc0399c87..3c0ae28c5923 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c @@ -154,6 +154,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK | 0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT; + m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT; m->cp_mqd_base_addr_lo = lower_32_bits(addr); @@ -221,10 +223,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, m = get_mqd(mqd); - m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK; m->cp_hqd_pq_control |= ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1; - m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control); m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c index 2b72d5b4949b..565858b9044d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c @@ -121,6 +121,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK | 0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT; + m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT; m->cp_mqd_base_addr_lo = lower_32_bits(addr); @@ -184,10 +186,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, m = get_mqd(mqd); - m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK; m->cp_hqd_pq_control |= ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1; - m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control); m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c index ff417d5361c4..3014925d95ff 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c @@ -183,6 +183,9 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK | 0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT; + m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; + m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT; m->cp_mqd_base_addr_lo = lower_32_bits(addr); @@ -245,7 +248,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, m = get_mqd(mqd); - m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK; m->cp_hqd_pq_control |= order_base_2(q->queue_size / 4) - 1; pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c deleted file mode 100644 index 8896426e0556..000000000000 --- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c +++ /dev/null @@ -1,46 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 OR MIT -/* - * Copyright 2014-2022 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - */ - -#include <linux/types.h> -#include "kfd_priv.h" -#include "amdgpu_ids.h" - -static unsigned int pasid_bits = 16; -static bool pasids_allocated; /* = false */ - -u32 kfd_pasid_alloc(void) -{ - int r = amdgpu_pasid_alloc(pasid_bits); - - if (r > 0) { - pasids_allocated = true; - return r; - } - - return 0; -} - -void kfd_pasid_free(u32 pasid) -{ - amdgpu_pasid_free(pasid); -} diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 59619f794b6b..bb09c873a9a5 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -289,7 +289,6 @@ struct kfd_node { /* Global GWS resource shared between processes */ void *gws; - bool gws_debug_workaround; /* Clients watching SMI events */ struct list_head smi_clients; @@ -1364,8 +1363,6 @@ int pqm_update_mqd(struct process_queue_manager *pqm, unsigned int qid, struct mqd_update_info *minfo); int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid, void *gws); -struct kernel_queue *pqm_get_kernel_queue(struct process_queue_manager *pqm, - unsigned int qid); struct queue *pqm_get_user_queue(struct process_queue_manager *pqm, unsigned int qid); int pqm_get_wave_state(struct process_queue_manager *pqm, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 1067afdb456e..7c0c24732481 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -35,6 +35,7 @@ #include <linux/pm_runtime.h> #include "amdgpu_amdkfd.h" #include "amdgpu.h" +#include "amdgpu_reset.h" struct mm_struct; @@ -838,6 +839,14 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) return ERR_PTR(-EINVAL); } + /* If the process just called exec(3), it is possible that the + * cleanup of the kfd_process (following the release of the mm + * of the old process image) is still in the cleanup work queue. + * Make sure to drain any job before trying to recreate any + * resource for this process. + */ + flush_workqueue(kfd_process_wq); + /* * take kfd processes mutex before starting of process creation * so there won't be a case where two threads of the same process @@ -858,14 +867,6 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) if (process) { pr_debug("Process already found\n"); } else { - /* If the process just called exec(3), it is possible that the - * cleanup of the kfd_process (following the release of the mm - * of the old process image) is still in the cleanup work queue. - * Make sure to drain any job before trying to recreate any - * resource for this process. - */ - flush_workqueue(kfd_process_wq); - process = create_process(thread); if (IS_ERR(process)) goto out; @@ -1133,6 +1134,17 @@ static void kfd_process_remove_sysfs(struct kfd_process *p) p->kobj = NULL; } +/* + * If any GPU is ongoing reset, wait for reset complete. + */ +static void kfd_process_wait_gpu_reset_complete(struct kfd_process *p) +{ + int i; + + for (i = 0; i < p->n_pdds; i++) + flush_workqueue(p->pdds[i]->dev->adev->reset_domain->wq); +} + /* No process locking is needed in this function, because the process * is not findable any more. We must assume that no other thread is * using it any more, otherwise we couldn't safely free the process @@ -1147,6 +1159,11 @@ static void kfd_process_wq_release(struct work_struct *work) kfd_process_dequeue_from_all_devices(p); pqm_uninit(&p->pqm); + /* + * If GPU in reset, user queues may still running, wait for reset complete. + */ + kfd_process_wait_gpu_reset_complete(p); + /* Signal the eviction fence after user mode queues are * destroyed. This allows any BOs to be freed without * triggering pointless evictions or waiting for fences. diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index d7947311cbbd..7eb370b68159 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -363,10 +363,26 @@ int pqm_create_queue(struct process_queue_manager *pqm, if (retval != 0) return retval; + /* Register process if this is the first queue */ if (list_empty(&pdd->qpd.queues_list) && list_empty(&pdd->qpd.priv_queue_list)) dev->dqm->ops.register_process(dev->dqm, &pdd->qpd); + /* Allocate proc_ctx_bo only if MES is enabled and this is the first queue */ + if (!pdd->proc_ctx_cpu_ptr && dev->kfd->shared_resources.enable_mes) { + retval = amdgpu_amdkfd_alloc_gtt_mem(dev->adev, + AMDGPU_MES_PROC_CTX_SIZE, + &pdd->proc_ctx_bo, + &pdd->proc_ctx_gpu_addr, + &pdd->proc_ctx_cpu_ptr, + false); + if (retval) { + dev_err(dev->adev->dev, "failed to allocate process context bo\n"); + return retval; + } + memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); + } + pqn = kzalloc(sizeof(*pqn), GFP_KERNEL); if (!pqn) { retval = -ENOMEM; @@ -532,7 +548,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) pr_err("Pasid 0x%x destroy queue %d failed, ret %d\n", pdd->pasid, pqn->q->properties.queue_id, retval); - if (retval != -ETIME) + if (retval != -ETIME && retval != -EIO) goto err_destroy_queue; } kfd_procfs_del_queue(pqn->q); @@ -652,19 +668,6 @@ int pqm_update_mqd(struct process_queue_manager *pqm, return 0; } -struct kernel_queue *pqm_get_kernel_queue( - struct process_queue_manager *pqm, - unsigned int qid) -{ - struct process_queue_node *pqn; - - pqn = get_queue_by_qid(pqm, qid); - if (pqn && pqn->kq) - return pqn->kq; - - return NULL; -} - struct queue *pqm_get_user_queue(struct process_queue_manager *pqm, unsigned int qid) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c index 62c635e9d1aa..4afff7094caf 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c @@ -276,8 +276,8 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope /* EOP buffer is not required for all ASICs */ if (properties->eop_ring_buffer_address) { if (properties->eop_ring_buffer_size != topo_dev->node_props.eop_buffer_size) { - pr_debug("queue eop bo size 0x%lx not equal to node eop buf size 0x%x\n", - properties->eop_buf_bo->tbo.base.size, + pr_debug("queue eop bo size 0x%x not equal to node eop buf size 0x%x\n", + properties->eop_ring_buffer_size, topo_dev->node_props.eop_buffer_size); err = -EINVAL; goto out_err_unreserve; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index db3034b00dac..1a38ac75abbd 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -3011,7 +3011,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, /* check if this page fault time stamp is before svms->checkpoint_ts */ if (svms->checkpoint_ts[gpuidx] != 0) { - if (amdgpu_ih_ts_after(ts, svms->checkpoint_ts[gpuidx])) { + if (amdgpu_ih_ts_after_or_equal(ts, svms->checkpoint_ts[gpuidx])) { pr_debug("draining retry fault, drop fault 0x%llx\n", addr); r = 0; goto out; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index dbc5595e999a..27e7356eed6f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -519,6 +519,8 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr, dev->gpu->kfd->mec_fw_version); sysfs_show_32bit_prop(buffer, offs, "capability", dev->node_props.capability); + sysfs_show_32bit_prop(buffer, offs, "capability2", + dev->node_props.capability2); sysfs_show_64bit_prop(buffer, offs, "debug_prop", dev->node_props.debug_prop); sysfs_show_32bit_prop(buffer, offs, "sdma_fw_version", @@ -1981,6 +1983,9 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev) if (kfd_dbg_has_ttmps_always_setup(dev->gpu)) dev->node_props.debug_prop |= HSA_DBG_DISPATCH_INFO_ALWAYS_VALID; + if (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE) + dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED; + if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(10, 0, 0)) { if (KFD_GC_VERSION(dev->gpu) == IP_VERSION(9, 4, 3) || KFD_GC_VERSION(dev->gpu) == IP_VERSION(9, 4, 4)) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h index f06c9db7ddde..3de8ec0043bb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h @@ -51,6 +51,7 @@ struct kfd_node_properties { uint32_t cpu_core_id_base; uint32_t simd_id_base; uint32_t capability; + uint32_t capability2; uint64_t debug_prop; uint32_t max_waves_per_simd; uint32_t lds_size_in_kb; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 16e4eb474eec..6a54f1cfa125 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -321,7 +321,7 @@ static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc, return 0; } -static bool dm_is_idle(void *handle) +static bool dm_is_idle(struct amdgpu_ip_block *ip_block) { /* XXX todo */ return true; @@ -1625,75 +1625,130 @@ static bool dm_should_disable_stutter(struct pci_dev *pdev) return false; } -static const struct dmi_system_id hpd_disconnect_quirk_table[] = { +struct amdgpu_dm_quirks { + bool aux_hpd_discon; + bool support_edp0_on_dp1; +}; + +static struct amdgpu_dm_quirks quirk_entries = { + .aux_hpd_discon = false, + .support_edp0_on_dp1 = false +}; + +static int edp0_on_dp1_callback(const struct dmi_system_id *id) +{ + quirk_entries.support_edp0_on_dp1 = true; + return 0; +} + +static int aux_hpd_discon_callback(const struct dmi_system_id *id) +{ + quirk_entries.aux_hpd_discon = true; + return 0; +} + +static const struct dmi_system_id dmi_quirk_table[] = { { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3660"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3260"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3460"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower Plus 7010"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower 7010"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF Plus 7010"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF 7010"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro Plus 7010"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro 7010"), }, }, + { + .callback = edp0_on_dp1_callback, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Elite mt645 G8 Mobile Thin Client"), + }, + }, + { + .callback = edp0_on_dp1_callback, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 665 16 inch G11 Notebook PC"), + }, + }, {} /* TODO: refactor this from a fixed table to a dynamic option */ }; -static void retrieve_dmi_info(struct amdgpu_display_manager *dm) +static void retrieve_dmi_info(struct amdgpu_display_manager *dm, struct dc_init_data *init_data) { - const struct dmi_system_id *dmi_id; + int dmi_id; + struct drm_device *dev = dm->ddev; dm->aux_hpd_discon_quirk = false; + init_data->flags.support_edp0_on_dp1 = false; + + dmi_id = dmi_check_system(dmi_quirk_table); - dmi_id = dmi_first_match(hpd_disconnect_quirk_table); - if (dmi_id) { + if (!dmi_id) + return; + + if (quirk_entries.aux_hpd_discon) { dm->aux_hpd_discon_quirk = true; - DRM_INFO("aux_hpd_discon_quirk attached\n"); + drm_info(dev, "aux_hpd_discon_quirk attached\n"); + } + if (quirk_entries.support_edp0_on_dp1) { + init_data->flags.support_edp0_on_dp1 = true; + drm_info(dev, "aux_hpd_discon_quirk attached\n"); } } @@ -2002,7 +2057,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 0, 0)) init_data.num_virtual_links = 1; - retrieve_dmi_info(&adev->dm); + retrieve_dmi_info(&adev->dm, &init_data); if (adev->dm.bb_from_dmub) init_data.bb_from_dmub = adev->dm.bb_from_dmub; @@ -3031,10 +3086,11 @@ static void dm_gpureset_toggle_interrupts(struct amdgpu_device *adev, } +DEFINE_FREE(state_release, struct dc_state *, if (_T) dc_state_release(_T)) + static enum dc_status amdgpu_dm_commit_zero_streams(struct dc *dc) { - struct dc_state *context = NULL; - enum dc_status res = DC_ERROR_UNEXPECTED; + struct dc_state *context __free(state_release) = NULL; int i; struct dc_stream_state *del_streams[MAX_PIPES]; int del_streams_count = 0; @@ -3044,7 +3100,7 @@ static enum dc_status amdgpu_dm_commit_zero_streams(struct dc *dc) context = dc_state_create_current_copy(dc); if (context == NULL) - goto context_alloc_fail; + return DC_ERROR_UNEXPECTED; /* First remove from context all streams */ for (i = 0; i < context->stream_count; i++) { @@ -3055,25 +3111,20 @@ static enum dc_status amdgpu_dm_commit_zero_streams(struct dc *dc) /* Remove all planes for removed streams and then remove the streams */ for (i = 0; i < del_streams_count; i++) { - if (!dc_state_rem_all_planes_for_stream(dc, del_streams[i], context)) { - res = DC_FAIL_DETACH_SURFACES; - goto fail; - } + enum dc_status res; + + if (!dc_state_rem_all_planes_for_stream(dc, del_streams[i], context)) + return DC_FAIL_DETACH_SURFACES; res = dc_state_remove_stream(dc, context, del_streams[i]); if (res != DC_OK) - goto fail; + return res; } params.streams = context->streams; params.stream_count = context->stream_count; - res = dc_commit_streams(dc, ¶ms); - -fail: - dc_state_release(context); -context_alloc_fail: - return res; + return dc_commit_streams(dc, ¶ms); } static void hpd_rx_irq_work_suspend(struct amdgpu_display_manager *dm) @@ -3090,9 +3141,10 @@ static int dm_suspend(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; struct amdgpu_display_manager *dm = &adev->dm; - int ret = 0; if (amdgpu_in_reset(adev)) { + enum dc_status res; + mutex_lock(&dm->dc_lock); dc_allow_idle_optimizations(adev->dm.dc, false); @@ -3102,13 +3154,17 @@ static int dm_suspend(struct amdgpu_ip_block *ip_block) if (dm->cached_dc_state) dm_gpureset_toggle_interrupts(adev, dm->cached_dc_state, false); - amdgpu_dm_commit_zero_streams(dm->dc); + res = amdgpu_dm_commit_zero_streams(dm->dc); + if (res != DC_OK) { + drm_err(adev_to_drm(adev), "Failed to commit zero streams: %d\n", res); + return -EINVAL; + } amdgpu_dm_irq_suspend(adev); hpd_rx_irq_work_suspend(dm); - return ret; + return 0; } WARN_ON(adev->dm.cached_state); @@ -3245,14 +3301,14 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state, struct dc_scaling_info scaling_infos[MAX_SURFACES]; struct dc_flip_addrs flip_addrs[MAX_SURFACES]; struct dc_stream_update stream_update; - } *bundle; + } *bundle __free(kfree); int k, m; bundle = kzalloc(sizeof(*bundle), GFP_KERNEL); if (!bundle) { drm_err(dm->ddev, "Failed to allocate update bundle\n"); - goto cleanup; + return; } for (k = 0; k < dc_state->stream_count; k++) { @@ -3272,9 +3328,24 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state, &bundle->stream_update, bundle->surface_updates); } +} -cleanup: - kfree(bundle); +static void apply_delay_after_dpcd_poweroff(struct amdgpu_device *adev, + struct dc_sink *sink) +{ + struct dc_panel_patch *ppatch = NULL; + + if (!sink) + return; + + ppatch = &sink->edid_caps.panel_patch; + if (ppatch->wait_after_dpcd_poweroff_ms) { + msleep(ppatch->wait_after_dpcd_poweroff_ms); + drm_dbg_driver(adev_to_drm(adev), + "%s: adding a %ds delay as w/a for panel\n", + __func__, + ppatch->wait_after_dpcd_poweroff_ms / 1000); + } } static int dm_resume(struct amdgpu_ip_block *ip_block) @@ -3323,7 +3394,7 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) r = dm_dmub_hw_init(adev); if (r) - DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r); + drm_err(adev_to_drm(adev), "DMUB interface failed to initialize: status=%d\n", r); dc_dmub_srv_set_power_state(dm->dc->ctx->dmub_srv, DC_ACPI_CM_POWER_STATE_D0); dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D0); @@ -3363,6 +3434,11 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) return 0; } + + /* leave display off for S4 sequence */ + if (adev->in_s4) + return 0; + /* Recreate dc_state - DC invalidates it when setting power state to S3. */ dc_state_release(dm_state->context); dm_state->context = dc_state_create(dm->dc, NULL); @@ -3398,6 +3474,7 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) /* Do detection*/ drm_connector_list_iter_begin(ddev, &iter); drm_for_each_connector_iter(connector, &iter) { + bool ret; if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) continue; @@ -3414,17 +3491,20 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) if (aconnector->mst_root) continue; - mutex_lock(&aconnector->hpd_lock); + guard(mutex)(&aconnector->hpd_lock); if (!dc_link_detect_connection_type(aconnector->dc_link, &new_connection_type)) - DRM_ERROR("KMS: Failed to detect connector\n"); + drm_err(adev_to_drm(adev), "KMS: Failed to detect connector\n"); if (aconnector->base.force && new_connection_type == dc_connection_none) { emulated_link_detect(aconnector->dc_link); } else { - mutex_lock(&dm->dc_lock); + guard(mutex)(&dm->dc_lock); dc_exit_ips_for_hw_access(dm->dc); - dc_link_detect(aconnector->dc_link, DETECT_REASON_RESUMEFROMS3S4); - mutex_unlock(&dm->dc_lock); + ret = dc_link_detect(aconnector->dc_link, DETECT_REASON_RESUMEFROMS3S4); + if (ret) { + /* w/a delay for certain panels */ + apply_delay_after_dpcd_poweroff(adev, aconnector->dc_sink); + } } if (aconnector->fake_enable && aconnector->dc_link->local_sink) @@ -3434,7 +3514,6 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) dc_sink_release(aconnector->dc_sink); aconnector->dc_sink = NULL; amdgpu_dm_update_connector_after_detect(aconnector); - mutex_unlock(&aconnector->hpd_lock); } drm_connector_list_iter_end(&iter); @@ -3603,12 +3682,14 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) caps->min_input_signal = min_input_signal_override; } +DEFINE_FREE(sink_release, struct dc_sink *, if (_T) dc_sink_release(_T)) + void amdgpu_dm_update_connector_after_detect( struct amdgpu_dm_connector *aconnector) { struct drm_connector *connector = &aconnector->base; + struct dc_sink *sink __free(sink_release) = NULL; struct drm_device *dev = connector->dev; - struct dc_sink *sink; /* MST handled by drm_mst framework */ if (aconnector->mst_mgr.mst_state == true) @@ -3630,7 +3711,7 @@ void amdgpu_dm_update_connector_after_detect( * For S3 resume with headless use eml_sink to fake stream * because on resume connector->sink is set to NULL */ - mutex_lock(&dev->mode_config.mutex); + guard(mutex)(&dev->mode_config.mutex); if (sink) { if (aconnector->dc_sink) { @@ -3655,10 +3736,6 @@ void amdgpu_dm_update_connector_after_detect( } } - mutex_unlock(&dev->mode_config.mutex); - - if (sink) - dc_sink_release(sink); return; } @@ -3666,10 +3743,8 @@ void amdgpu_dm_update_connector_after_detect( * TODO: temporary guard to look for proper fix * if this sink is MST sink, we should not do anything */ - if (sink && sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { - dc_sink_release(sink); + if (sink && sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT_MST) return; - } if (aconnector->dc_sink == sink) { /* @@ -3678,15 +3753,13 @@ void amdgpu_dm_update_connector_after_detect( */ drm_dbg_kms(dev, "DCHPD: connector_id=%d: dc_sink didn't change.\n", aconnector->connector_id); - if (sink) - dc_sink_release(sink); return; } drm_dbg_kms(dev, "DCHPD: connector_id=%d: Old sink=%p New sink=%p\n", aconnector->connector_id, aconnector->dc_sink, sink); - mutex_lock(&dev->mode_config.mutex); + guard(mutex)(&dev->mode_config.mutex); /* * 1. Update status of the drm connector @@ -3748,12 +3821,7 @@ void amdgpu_dm_update_connector_after_detect( connector->state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED; } - mutex_unlock(&dev->mode_config.mutex); - update_subconnector_property(aconnector); - - if (sink) - dc_sink_release(sink); } static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) @@ -3773,7 +3841,7 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) * In case of failure or MST no need to update connector status or notify the OS * since (for MST case) MST does this in its own context. */ - mutex_lock(&aconnector->hpd_lock); + guard(mutex)(&aconnector->hpd_lock); if (adev->dm.hdcp_workqueue) { hdcp_reset_display(adev->dm.hdcp_workqueue, aconnector->dc_link->link_index); @@ -3785,7 +3853,7 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) aconnector->timing_changed = false; if (!dc_link_detect_connection_type(aconnector->dc_link, &new_connection_type)) - DRM_ERROR("KMS: Failed to detect connector\n"); + drm_err(adev_to_drm(adev), "KMS: Failed to detect connector\n"); if (aconnector->base.force && new_connection_type == dc_connection_none) { emulated_link_detect(aconnector->dc_link); @@ -3797,11 +3865,13 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) if (aconnector->base.force == DRM_FORCE_UNSPECIFIED) drm_kms_helper_connector_hotplug_event(connector); } else { - mutex_lock(&adev->dm.dc_lock); - dc_exit_ips_for_hw_access(dc); - ret = dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); - mutex_unlock(&adev->dm.dc_lock); + scoped_guard(mutex, &adev->dm.dc_lock) { + dc_exit_ips_for_hw_access(dc); + ret = dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); + } if (ret) { + /* w/a delay for certain panels */ + apply_delay_after_dpcd_poweroff(adev, aconnector->dc_sink); amdgpu_dm_update_connector_after_detect(aconnector); drm_modeset_lock_all(dev); @@ -3812,8 +3882,6 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) drm_kms_helper_connector_hotplug_event(connector); } } - mutex_unlock(&aconnector->hpd_lock); - } static void handle_hpd_irq(void *param) @@ -4653,48 +4721,40 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev) static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm, int bl_idx) { -#if defined(CONFIG_ACPI) - struct amdgpu_dm_backlight_caps caps; + struct amdgpu_dm_backlight_caps *caps = &dm->backlight_caps[bl_idx]; - memset(&caps, 0, sizeof(caps)); - - if (dm->backlight_caps[bl_idx].caps_valid) + if (caps->caps_valid) return; - amdgpu_acpi_get_backlight_caps(&caps); +#if defined(CONFIG_ACPI) + amdgpu_acpi_get_backlight_caps(caps); /* validate the firmware value is sane */ - if (caps.caps_valid) { - int spread = caps.max_input_signal - caps.min_input_signal; + if (caps->caps_valid) { + int spread = caps->max_input_signal - caps->min_input_signal; - if (caps.max_input_signal > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || - caps.min_input_signal < 0 || + if (caps->max_input_signal > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || + caps->min_input_signal < 0 || spread > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || spread < AMDGPU_DM_MIN_SPREAD) { DRM_DEBUG_KMS("DM: Invalid backlight caps: min=%d, max=%d\n", - caps.min_input_signal, caps.max_input_signal); - caps.caps_valid = false; + caps->min_input_signal, caps->max_input_signal); + caps->caps_valid = false; } } - if (caps.caps_valid) { - dm->backlight_caps[bl_idx].caps_valid = true; - if (caps.aux_support) - return; - dm->backlight_caps[bl_idx].min_input_signal = caps.min_input_signal; - dm->backlight_caps[bl_idx].max_input_signal = caps.max_input_signal; - } else { - dm->backlight_caps[bl_idx].min_input_signal = - AMDGPU_DM_DEFAULT_MIN_BACKLIGHT; - dm->backlight_caps[bl_idx].max_input_signal = - AMDGPU_DM_DEFAULT_MAX_BACKLIGHT; + if (!caps->caps_valid) { + caps->min_input_signal = AMDGPU_DM_DEFAULT_MIN_BACKLIGHT; + caps->max_input_signal = AMDGPU_DM_DEFAULT_MAX_BACKLIGHT; + caps->caps_valid = true; } #else - if (dm->backlight_caps[bl_idx].aux_support) + if (caps->aux_support) return; - dm->backlight_caps[bl_idx].min_input_signal = AMDGPU_DM_DEFAULT_MIN_BACKLIGHT; - dm->backlight_caps[bl_idx].max_input_signal = AMDGPU_DM_DEFAULT_MAX_BACKLIGHT; + caps->min_input_signal = AMDGPU_DM_DEFAULT_MIN_BACKLIGHT; + caps->max_input_signal = AMDGPU_DM_DEFAULT_MAX_BACKLIGHT; + caps->caps_valid = true; #endif } @@ -4720,10 +4780,38 @@ static u32 convert_brightness_from_user(const struct amdgpu_dm_backlight_caps *c uint32_t brightness) { unsigned int min, max; + u8 prev_signal = 0, prev_lum = 0; if (!get_brightness_range(caps, &min, &max)) return brightness; + for (int i = 0; i < caps->data_points; i++) { + u8 signal, lum; + + if (amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE) + break; + + signal = caps->luminance_data[i].input_signal; + lum = caps->luminance_data[i].luminance; + + /* + * brightness == signal: luminance is percent numerator + * brightness < signal: interpolate between previous and current luminance numerator + * brightness > signal: find next data point + */ + if (brightness < signal) + lum = prev_lum + DIV_ROUND_CLOSEST((lum - prev_lum) * + (brightness - prev_signal), + signal - prev_signal); + else if (brightness > signal) { + prev_signal = signal; + prev_lum = lum; + continue; + } + brightness = DIV_ROUND_CLOSEST(lum * brightness, 101); + break; + } + // Rescale 0..255 to min..max return min + DIV_ROUND_CLOSEST((max - min) * brightness, AMDGPU_MAX_BL_LEVEL); @@ -4748,19 +4836,19 @@ static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, int bl_idx, u32 user_brightness) { - struct amdgpu_dm_backlight_caps caps; + struct amdgpu_dm_backlight_caps *caps; struct dc_link *link; u32 brightness; bool rc, reallow_idle = false; amdgpu_dm_update_backlight_caps(dm, bl_idx); - caps = dm->backlight_caps[bl_idx]; + caps = &dm->backlight_caps[bl_idx]; dm->brightness[bl_idx] = user_brightness; /* update scratch register */ if (bl_idx == 0) amdgpu_atombios_scratch_regs_set_backlight_level(dm->adev, dm->brightness[bl_idx]); - brightness = convert_brightness_from_user(&caps, dm->brightness[bl_idx]); + brightness = convert_brightness_from_user(caps, dm->brightness[bl_idx]); link = (struct dc_link *)dm->backlight_link[bl_idx]; /* Change brightness based on AUX property */ @@ -4770,7 +4858,7 @@ static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, reallow_idle = true; } - if (caps.aux_support) { + if (caps->aux_support) { rc = dc_link_set_backlight_level_nits(link, true, brightness, AUX_BL_DEFAULT_TRANSITION_TIME_MS); if (!rc) @@ -4887,6 +4975,8 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) } else props.brightness = AMDGPU_MAX_BL_LEVEL; + if (caps.data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) + drm_info(drm, "Using custom brightness curve\n"); props.max_brightness = AMDGPU_MAX_BL_LEVEL; props.type = BACKLIGHT_RAW; @@ -7295,8 +7385,14 @@ static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector) struct dc_link *dc_link = aconnector->dc_link; struct dc_sink *dc_em_sink = aconnector->dc_em_sink; const struct drm_edid *drm_edid; + struct i2c_adapter *ddc; + + if (dc_link && dc_link->aux_mode) + ddc = &aconnector->dm_dp_aux.aux.ddc; + else + ddc = &aconnector->i2c->base; - drm_edid = drm_edid_read(connector); + drm_edid = drm_edid_read_ddc(connector, ddc); drm_edid_connector_update(connector, drm_edid); if (!drm_edid) { DRM_ERROR("No EDID found on connector: %s.\n", connector->name); @@ -7341,14 +7437,21 @@ static int get_modes(struct drm_connector *connector) static void create_eml_sink(struct amdgpu_dm_connector *aconnector) { struct drm_connector *connector = &aconnector->base; + struct dc_link *dc_link = aconnector->dc_link; struct dc_sink_init_data init_params = { .link = aconnector->dc_link, .sink_signal = SIGNAL_TYPE_VIRTUAL }; const struct drm_edid *drm_edid; const struct edid *edid; + struct i2c_adapter *ddc; + + if (dc_link && dc_link->aux_mode) + ddc = &aconnector->dm_dp_aux.aux.ddc; + else + ddc = &aconnector->i2c->base; - drm_edid = drm_edid_read(connector); + drm_edid = drm_edid_read_ddc(connector, ddc); drm_edid_connector_update(connector, drm_edid); if (!drm_edid) { DRM_ERROR("No EDID found on connector: %s.\n", connector->name); @@ -12655,3 +12758,10 @@ bool dm_execute_dmub_cmd_list(const struct dc_context *ctx, unsigned int count, { return dc_dmub_srv_cmd_run_list(ctx->dmub_srv, count, cmd, wait_type); } + +void dm_acpi_process_phy_transition_interlock( + const struct dc_context *ctx, + struct dm_process_phy_transition_init_params process_phy_transition_init_params) +{ + // Not yet implemented +} diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index acead14ab45d..385faaca6e26 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -151,6 +151,18 @@ struct idle_workqueue { bool running; }; +#define MAX_LUMINANCE_DATA_POINTS 99 + +/** + * struct amdgpu_dm_luminance_data - Custom luminance data + * @luminance: Luminance in percent + * @input_signal: Input signal in range 0-255 + */ +struct amdgpu_dm_luminance_data { + u8 luminance; + u8 input_signal; +} __packed; + /** * struct amdgpu_dm_backlight_caps - Information about backlight * @@ -195,6 +207,14 @@ struct amdgpu_dm_backlight_caps { * @dc_level: the default brightness if booted on DC */ u8 dc_level; + /** + * @data_points: the number of custom luminance data points + */ + u8 data_points; + /** + * @luminance_data: custom luminance data + */ + struct amdgpu_dm_luminance_data luminance_data[MAX_LUMINANCE_DATA_POINTS]; }; /** diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index fbd80d8545a8..2cd35392e2da 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -55,16 +55,21 @@ static u32 edid_extract_panel_id(struct edid *edid) (u32)EDID_PRODUCT_ID(edid); } -static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps) +static void apply_edid_quirks(struct drm_device *dev, struct edid *edid, struct dc_edid_caps *edid_caps) { uint32_t panel_id = edid_extract_panel_id(edid); switch (panel_id) { + /* Workaround for monitors that need a delay after detecting the link */ + case drm_edid_encode_panel_id('G', 'B', 'T', 0x3215): + drm_dbg_driver(dev, "Add 10s delay for link detection for panel id %X\n", panel_id); + edid_caps->panel_patch.wait_after_dpcd_poweroff_ms = 10000; + break; /* Workaround for some monitors which does not work well with FAMS */ case drm_edid_encode_panel_id('S', 'A', 'M', 0x0E5E): case drm_edid_encode_panel_id('S', 'A', 'M', 0x7053): case drm_edid_encode_panel_id('S', 'A', 'M', 0x71AC): - DRM_DEBUG_DRIVER("Disabling FAMS on monitor with panel id %X\n", panel_id); + drm_dbg_driver(dev, "Disabling FAMS on monitor with panel id %X\n", panel_id); edid_caps->panel_patch.disable_fams = true; break; /* Workaround for some monitors that do not clear DPCD 0x317 if FreeSync is unsupported */ @@ -73,11 +78,11 @@ static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps) case drm_edid_encode_panel_id('B', 'O', 'E', 0x092A): case drm_edid_encode_panel_id('L', 'G', 'D', 0x06D1): case drm_edid_encode_panel_id('M', 'S', 'F', 0x1003): - DRM_DEBUG_DRIVER("Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id); + drm_dbg_driver(dev, "Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id); edid_caps->panel_patch.remove_sink_ext_caps = true; break; case drm_edid_encode_panel_id('S', 'D', 'C', 0x4154): - DRM_DEBUG_DRIVER("Disabling VSC on monitor with panel id %X\n", panel_id); + drm_dbg_driver(dev, "Disabling VSC on monitor with panel id %X\n", panel_id); edid_caps->panel_patch.disable_colorimetry = true; break; default: @@ -101,6 +106,7 @@ enum dc_edid_status dm_helpers_parse_edid_caps( { struct amdgpu_dm_connector *aconnector = link->priv; struct drm_connector *connector = &aconnector->base; + struct drm_device *dev = connector->dev; struct edid *edid_buf = edid ? (struct edid *) edid->raw_edid : NULL; struct cea_sad *sads; int sad_count = -1; @@ -130,7 +136,7 @@ enum dc_edid_status dm_helpers_parse_edid_caps( edid_caps->edid_hdmi = connector->display_info.is_hdmi; - apply_edid_quirks(edid_buf, edid_caps); + apply_edid_quirks(dev, edid_buf, edid_caps); sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads); if (sad_count <= 0) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c index 3390f0d8420a..2b63cbab0e87 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c @@ -473,7 +473,7 @@ void amdgpu_dm_irq_fini(struct amdgpu_device *adev) unregister_all_irq_handlers(adev); } -int amdgpu_dm_irq_suspend(struct amdgpu_device *adev) +void amdgpu_dm_irq_suspend(struct amdgpu_device *adev) { int src; struct list_head *hnd_list_h; @@ -511,10 +511,9 @@ int amdgpu_dm_irq_suspend(struct amdgpu_device *adev) } DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags); - return 0; } -int amdgpu_dm_irq_resume_early(struct amdgpu_device *adev) +void amdgpu_dm_irq_resume_early(struct amdgpu_device *adev) { int src; struct list_head *hnd_list_h, *hnd_list_l; @@ -522,7 +521,7 @@ int amdgpu_dm_irq_resume_early(struct amdgpu_device *adev) DM_IRQ_TABLE_LOCK(adev, irq_table_flags); - DRM_DEBUG_KMS("DM_IRQ: early resume\n"); + drm_dbg(adev_to_drm(adev), "DM_IRQ: early resume\n"); /* re-enable short pulse interrupts HW interrupt */ for (src = DC_IRQ_SOURCE_HPD1RX; src <= DC_IRQ_SOURCE_HPD6RX; src++) { @@ -533,11 +532,9 @@ int amdgpu_dm_irq_resume_early(struct amdgpu_device *adev) } DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags); - - return 0; } -int amdgpu_dm_irq_resume_late(struct amdgpu_device *adev) +void amdgpu_dm_irq_resume_late(struct amdgpu_device *adev) { int src; struct list_head *hnd_list_h, *hnd_list_l; @@ -545,7 +542,7 @@ int amdgpu_dm_irq_resume_late(struct amdgpu_device *adev) DM_IRQ_TABLE_LOCK(adev, irq_table_flags); - DRM_DEBUG_KMS("DM_IRQ: resume\n"); + drm_dbg(adev_to_drm(adev), "DM_IRQ: resume\n"); /** * Renable HW interrupt for HPD and only since FLIP and VBLANK @@ -559,7 +556,6 @@ int amdgpu_dm_irq_resume_late(struct amdgpu_device *adev) } DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags); - return 0; } /* @@ -894,6 +890,7 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev) struct drm_device *dev = adev_to_drm(adev); struct drm_connector *connector; struct drm_connector_list_iter iter; + int i; drm_connector_list_iter_begin(dev, &iter); drm_for_each_connector_iter(connector, &iter) { @@ -920,6 +917,12 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev) } } drm_connector_list_iter_end(&iter); + + /* Update reference counts for HPDs */ + for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) { + if (amdgpu_irq_get(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1)) + drm_err(dev, "DM_IRQ: Failed get HPD for source=%d)!\n", i); + } } /** @@ -935,6 +938,7 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev) struct drm_device *dev = adev_to_drm(adev); struct drm_connector *connector; struct drm_connector_list_iter iter; + int i; drm_connector_list_iter_begin(dev, &iter); drm_for_each_connector_iter(connector, &iter) { @@ -960,4 +964,10 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev) } } drm_connector_list_iter_end(&iter); + + /* Update reference counts for HPDs */ + for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) { + if (amdgpu_irq_put(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1)) + drm_err(dev, "DM_IRQ: Failed put HPD for source=%d!\n", i); + } } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h index 2349238a626b..ba17c23b2706 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h @@ -90,14 +90,14 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev); * amdgpu_dm_irq_suspend - disable ASIC interrupt during suspend. * */ -int amdgpu_dm_irq_suspend(struct amdgpu_device *adev); +void amdgpu_dm_irq_suspend(struct amdgpu_device *adev); /** * amdgpu_dm_irq_resume_early - enable HPDRX ASIC interrupts during resume. * amdgpu_dm_irq_resume - enable ASIC interrupt during resume. * */ -int amdgpu_dm_irq_resume_early(struct amdgpu_device *adev); -int amdgpu_dm_irq_resume_late(struct amdgpu_device *adev); +void amdgpu_dm_irq_resume_early(struct amdgpu_device *adev); +void amdgpu_dm_irq_resume_late(struct amdgpu_device *adev); #endif /* __AMDGPU_DM_IRQ_H__ */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 056b17198956..7ceedf626d23 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -1632,6 +1632,9 @@ int pre_validate_dsc(struct drm_atomic_state *state, connector = amdgpu_dm_find_first_crtc_matching_connector(state, state->crtcs[ind].ptr); + if (!connector) + continue; + drm_new_conn_state = drm_atomic_get_new_connector_state(state, connector); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index fcb0e900a38a..0090e08d5057 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -277,8 +277,11 @@ static int amdgpu_dm_plane_validate_dcc(struct amdgpu_device *adev, if (!dcc->enable) return 0; - if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN || - !dc->cap_funcs.get_dcc_compression_cap) + if (adev->family < AMDGPU_FAMILY_GC_12_0_0 && + format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) + return -EINVAL; + + if (!dc->cap_funcs.get_dcc_compression_cap) return -EINVAL; input.format = format; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c index 104f03868266..e140b7a04d72 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c @@ -30,23 +30,6 @@ #include "amdgpu_dm.h" #include "modules/power/power_helpers.h" -static bool is_specific_oled_panel(struct dc_link *link) -{ - if (!link->dpcd_sink_ext_caps.bits.oled) - return false; - - /* Disable PSR-SU for some OLED panels to avoid glitches */ - if (link->dpcd_caps.sink_dev_id == 0xBA4159) { - uint8_t sink_dev_id_str1[] = {'4', '0', 'C', 'U', '1'}; - - if (!memcmp(link->dpcd_caps.sink_dev_id_str, sink_dev_id_str1, - sizeof(sink_dev_id_str1))) - return true; - } - - return false; -} - static bool link_supports_psrsu(struct dc_link *link) { struct dc *dc = link->ctx->dc; @@ -57,9 +40,6 @@ static bool link_supports_psrsu(struct dc_link *link) if (dc->ctx->dce_version < DCN_VERSION_3_1) return false; - if (is_specific_oled_panel(link)) - return false; - if (!is_psr_su_specific_panel(link)) return false; @@ -74,7 +54,8 @@ static bool link_supports_psrsu(struct dc_link *link) if (amdgpu_dc_debug_mask & DC_DISABLE_PSR_SU) return false; - return dc_dmub_check_min_version(dc->ctx->dmub_srv->dmub); + /* Temporarily disable PSR-SU to avoid glitches */ + return false; } /* diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c index 7d18f372ce7a..2c645dffec18 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c @@ -101,7 +101,6 @@ static void init_dig_encoder_control(struct bios_parser *bp) bp->cmd_tbl.dig_encoder_control = encoder_control_digx_v1_5; break; default: - dm_output_to_console("Don't have dig_encoder_control for v%d\n", version); bp->cmd_tbl.dig_encoder_control = encoder_control_fallback; break; } @@ -210,6 +209,7 @@ static enum bp_result encoder_control_fallback( ****************************************************************************** *****************************************************************************/ + static enum bp_result transmitter_control_v1_6( struct bios_parser *bp, struct bp_transmitter_control *cntl); @@ -238,7 +238,6 @@ static void init_transmitter_control(struct bios_parser *bp) bp->cmd_tbl.transmitter_control = transmitter_control_v1_7; break; default: - dm_output_to_console("Don't have transmitter_control for v%d\n", crev); bp->cmd_tbl.transmitter_control = transmitter_control_fallback; break; } @@ -325,6 +324,21 @@ static void transmitter_control_dmcub_v1_7( dc_wake_and_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } +static struct dc_link *get_link_by_phy_id(struct dc *p_dc, uint32_t phy_id) +{ + struct dc_link *link = NULL; + + // Get Transition Bitmask from dc_link structure associated with PHY + for (uint8_t link_id = 0; link_id < MAX_LINKS; link_id++) { + if (phy_id == p_dc->links[link_id]->link_enc->transmitter) { + link = p_dc->links[link_id]; + break; + } + } + + return link; +} + static enum bp_result transmitter_control_v1_7( struct bios_parser *bp, struct bp_transmitter_control *cntl) @@ -363,7 +377,37 @@ static enum bp_result transmitter_control_v1_7( if (bp->base.ctx->dc->ctx->dmub_srv && bp->base.ctx->dc->debug.dmub_command_table) { + struct dm_process_phy_transition_init_params process_phy_transition_init_params = {0}; + struct dc_link *link = get_link_by_phy_id(bp->base.ctx->dc, dig_v1_7.phyid); + bool is_phy_transition_interlock_allowed = false; + uint8_t action = dig_v1_7.action; + + if (link) { + if (link->phy_transition_bitmask && + (action == TRANSMITTER_CONTROL_ENABLE || action == TRANSMITTER_CONTROL_DISABLE)) { + is_phy_transition_interlock_allowed = true; + + // Prepare input parameters for processing ACPI retimers + process_phy_transition_init_params.action = action; + process_phy_transition_init_params.display_port_lanes_count = cntl->lanes_number; + process_phy_transition_init_params.phy_id = dig_v1_7.phyid; + process_phy_transition_init_params.signal = cntl->signal; + process_phy_transition_init_params.sym_clock_10khz = dig_v1_7.symclk_units.symclk_10khz; + process_phy_transition_init_params.display_port_link_rate = link->cur_link_settings.link_rate; + process_phy_transition_init_params.transition_bitmask = link->phy_transition_bitmask; + } + } + + // Handle PRE_OFF_TO_ON: Process ACPI PHY Transition Interlock + if (is_phy_transition_interlock_allowed && action == TRANSMITTER_CONTROL_ENABLE) + dm_acpi_process_phy_transition_interlock(bp->base.ctx, process_phy_transition_init_params); + transmitter_control_dmcub_v1_7(bp->base.ctx->dmub_srv, &dig_v1_7); + + // Handle POST_ON_TO_OFF: Process ACPI PHY Transition Interlock + if (is_phy_transition_interlock_allowed && action == TRANSMITTER_CONTROL_DISABLE) + dm_acpi_process_phy_transition_interlock(bp->base.ctx, process_phy_transition_init_params); + return BP_RESULT_OK; } @@ -408,8 +452,6 @@ static void init_set_pixel_clock(struct bios_parser *bp) bp->cmd_tbl.set_pixel_clock = set_pixel_clock_v7; break; default: - dm_output_to_console("Don't have set_pixel_clock for v%d\n", - BIOS_CMD_TABLE_PARA_REVISION(setpixelclock)); bp->cmd_tbl.set_pixel_clock = set_pixel_clock_fallback; break; } @@ -554,7 +596,6 @@ static void init_set_crtc_timing(struct bios_parser *bp) set_crtc_using_dtd_timing_v3; break; default: - dm_output_to_console("Don't have set_crtc_timing for v%d\n", dtd_version); bp->cmd_tbl.set_crtc_timing = NULL; break; } @@ -671,8 +712,6 @@ static void init_enable_crtc(struct bios_parser *bp) bp->cmd_tbl.enable_crtc = enable_crtc_v1; break; default: - dm_output_to_console("Don't have enable_crtc for v%d\n", - BIOS_CMD_TABLE_PARA_REVISION(enablecrtc)); bp->cmd_tbl.enable_crtc = NULL; break; } @@ -864,8 +903,6 @@ static void init_set_dce_clock(struct bios_parser *bp) bp->cmd_tbl.set_dce_clock = set_dce_clock_v2_1; break; default: - dm_output_to_console("Don't have set_dce_clock for v%d\n", - BIOS_CMD_TABLE_PARA_REVISION(setdceclock)); bp->cmd_tbl.set_dce_clock = NULL; break; } @@ -1046,3 +1083,4 @@ void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp) init_enable_lvtma_control(bp); } + diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c index e317a3615147..91bc8a06e2cf 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c @@ -293,3 +293,107 @@ uint8_t dal_cmd_table_helper_encoder_id_to_atom( return ENCODER_OBJECT_ID_NONE; } } + +uint8_t phy_id_to_atom(enum transmitter t) +{ + uint8_t atom_phy_id; + + switch (t) { + case TRANSMITTER_UNIPHY_A: + atom_phy_id = ATOM_PHY_ID_UNIPHYA; + break; + case TRANSMITTER_UNIPHY_B: + atom_phy_id = ATOM_PHY_ID_UNIPHYB; + break; + case TRANSMITTER_UNIPHY_C: + atom_phy_id = ATOM_PHY_ID_UNIPHYC; + break; + case TRANSMITTER_UNIPHY_D: + atom_phy_id = ATOM_PHY_ID_UNIPHYD; + break; + case TRANSMITTER_UNIPHY_E: + atom_phy_id = ATOM_PHY_ID_UNIPHYE; + break; + case TRANSMITTER_UNIPHY_F: + atom_phy_id = ATOM_PHY_ID_UNIPHYF; + break; + case TRANSMITTER_UNIPHY_G: + atom_phy_id = ATOM_PHY_ID_UNIPHYG; + break; + default: + atom_phy_id = ATOM_PHY_ID_UNIPHYA; + break; + } + return atom_phy_id; +} + +uint8_t clock_source_id_to_atom_phy_clk_src_id( + enum clock_source_id id) +{ + uint8_t atom_phy_clk_src_id = 0; + + switch (id) { + case CLOCK_SOURCE_ID_PLL0: + atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL; + break; + case CLOCK_SOURCE_ID_PLL1: + atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; + break; + case CLOCK_SOURCE_ID_PLL2: + atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL; + break; + case CLOCK_SOURCE_ID_EXTERNAL: + atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT; + break; + default: + atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; + break; + } + + return atom_phy_clk_src_id >> 2; +} + +bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id) +{ + bool result = false; + + if (atom_engine_id != NULL) + switch (id) { + case ENGINE_ID_DIGA: + *atom_engine_id = ASIC_INT_DIG1_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DIGB: + *atom_engine_id = ASIC_INT_DIG2_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DIGC: + *atom_engine_id = ASIC_INT_DIG3_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DIGD: + *atom_engine_id = ASIC_INT_DIG4_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DIGE: + *atom_engine_id = ASIC_INT_DIG5_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DIGF: + *atom_engine_id = ASIC_INT_DIG6_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DIGG: + *atom_engine_id = ASIC_INT_DIG7_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DACA: + *atom_engine_id = ASIC_INT_DAC1_ENCODER_ID; + result = true; + break; + default: + break; + } + + return result; +} diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.h b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.h index dfd30aaf4032..547700e119a6 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.h +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.h @@ -59,4 +59,12 @@ uint8_t dal_cmd_table_helper_transmitter_bp_to_atom( uint8_t dal_cmd_table_helper_encoder_id_to_atom( enum encoder_id id); + +uint8_t phy_id_to_atom(enum transmitter t); + +uint8_t clock_source_id_to_atom_phy_clk_src_id( + enum clock_source_id id); + +bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c index bad4e4711b4f..268e2414b34f 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c @@ -88,8 +88,7 @@ bool dal_bios_parser_init_cmd_tbl_helper2( return true; default: - /* Unsupported DCE */ - BREAK_TO_DEBUGGER(); + *h = dal_cmd_tbl_helper_dce112_get_table2(); return false; } } diff --git a/drivers/gpu/drm/amd/display/dc/bios/dce110/command_table_helper_dce110.c b/drivers/gpu/drm/amd/display/dc/bios/dce110/command_table_helper_dce110.c index 11bf247bb180..3099128223df 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/dce110/command_table_helper_dce110.c +++ b/drivers/gpu/drm/amd/display/dc/bios/dce110/command_table_helper_dce110.c @@ -31,39 +31,6 @@ #include "../command_table_helper.h" -static uint8_t phy_id_to_atom(enum transmitter t) -{ - uint8_t atom_phy_id; - - switch (t) { - case TRANSMITTER_UNIPHY_A: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - case TRANSMITTER_UNIPHY_B: - atom_phy_id = ATOM_PHY_ID_UNIPHYB; - break; - case TRANSMITTER_UNIPHY_C: - atom_phy_id = ATOM_PHY_ID_UNIPHYC; - break; - case TRANSMITTER_UNIPHY_D: - atom_phy_id = ATOM_PHY_ID_UNIPHYD; - break; - case TRANSMITTER_UNIPHY_E: - atom_phy_id = ATOM_PHY_ID_UNIPHYE; - break; - case TRANSMITTER_UNIPHY_F: - atom_phy_id = ATOM_PHY_ID_UNIPHYF; - break; - case TRANSMITTER_UNIPHY_G: - atom_phy_id = ATOM_PHY_ID_UNIPHYG; - break; - default: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - } - return atom_phy_id; -} - static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) { uint8_t atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_DP; @@ -94,32 +61,6 @@ static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) return atom_dig_mode; } -static uint8_t clock_source_id_to_atom_phy_clk_src_id( - enum clock_source_id id) -{ - uint8_t atom_phy_clk_src_id = 0; - - switch (id) { - case CLOCK_SOURCE_ID_PLL0: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL; - break; - case CLOCK_SOURCE_ID_PLL1: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - case CLOCK_SOURCE_ID_PLL2: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL; - break; - case CLOCK_SOURCE_ID_EXTERNAL: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT; - break; - default: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - } - - return atom_phy_clk_src_id >> 2; -} - static uint8_t hpd_sel_to_atom(enum hpd_source_id id) { uint8_t atom_hpd_sel = 0; @@ -207,51 +148,6 @@ static bool clock_source_id_to_atom( return result; } -static bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id) -{ - bool result = false; - - if (atom_engine_id != NULL) - switch (id) { - case ENGINE_ID_DIGA: - *atom_engine_id = ASIC_INT_DIG1_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGB: - *atom_engine_id = ASIC_INT_DIG2_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGC: - *atom_engine_id = ASIC_INT_DIG3_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGD: - *atom_engine_id = ASIC_INT_DIG4_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGE: - *atom_engine_id = ASIC_INT_DIG5_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGF: - *atom_engine_id = ASIC_INT_DIG6_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGG: - *atom_engine_id = ASIC_INT_DIG7_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DACA: - *atom_engine_id = ASIC_INT_DAC1_ENCODER_ID; - result = true; - break; - default: - break; - } - - return result; -} - static uint8_t encoder_action_to_atom(enum bp_encoder_control_action action) { uint8_t atom_action = 0; diff --git a/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper2_dce112.c b/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper2_dce112.c index 755b6e33140a..349f0e5d5856 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper2_dce112.c +++ b/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper2_dce112.c @@ -29,40 +29,9 @@ #include "include/bios_parser_types.h" -#include "../command_table_helper2.h" - -static uint8_t phy_id_to_atom(enum transmitter t) -{ - uint8_t atom_phy_id; +#include "../command_table_helper.h" - switch (t) { - case TRANSMITTER_UNIPHY_A: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - case TRANSMITTER_UNIPHY_B: - atom_phy_id = ATOM_PHY_ID_UNIPHYB; - break; - case TRANSMITTER_UNIPHY_C: - atom_phy_id = ATOM_PHY_ID_UNIPHYC; - break; - case TRANSMITTER_UNIPHY_D: - atom_phy_id = ATOM_PHY_ID_UNIPHYD; - break; - case TRANSMITTER_UNIPHY_E: - atom_phy_id = ATOM_PHY_ID_UNIPHYE; - break; - case TRANSMITTER_UNIPHY_F: - atom_phy_id = ATOM_PHY_ID_UNIPHYF; - break; - case TRANSMITTER_UNIPHY_G: - atom_phy_id = ATOM_PHY_ID_UNIPHYG; - break; - default: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - } - return atom_phy_id; -} +#include "../command_table_helper2.h" static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) { @@ -91,32 +60,6 @@ static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) return atom_dig_mode; } -static uint8_t clock_source_id_to_atom_phy_clk_src_id( - enum clock_source_id id) -{ - uint8_t atom_phy_clk_src_id = 0; - - switch (id) { - case CLOCK_SOURCE_ID_PLL0: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL; - break; - case CLOCK_SOURCE_ID_PLL1: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - case CLOCK_SOURCE_ID_PLL2: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL; - break; - case CLOCK_SOURCE_ID_EXTERNAL: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT; - break; - default: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - } - - return atom_phy_clk_src_id >> 2; -} - static uint8_t hpd_sel_to_atom(enum hpd_source_id id) { uint8_t atom_hpd_sel = 0; @@ -209,51 +152,6 @@ static bool clock_source_id_to_atom( return result; } -static bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id) -{ - bool result = false; - - if (atom_engine_id != NULL) - switch (id) { - case ENGINE_ID_DIGA: - *atom_engine_id = ASIC_INT_DIG1_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGB: - *atom_engine_id = ASIC_INT_DIG2_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGC: - *atom_engine_id = ASIC_INT_DIG3_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGD: - *atom_engine_id = ASIC_INT_DIG4_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGE: - *atom_engine_id = ASIC_INT_DIG5_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGF: - *atom_engine_id = ASIC_INT_DIG6_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGG: - *atom_engine_id = ASIC_INT_DIG7_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DACA: - *atom_engine_id = ASIC_INT_DAC1_ENCODER_ID; - result = true; - break; - default: - break; - } - - return result; -} - static uint8_t encoder_action_to_atom(enum bp_encoder_control_action action) { uint8_t atom_action = 0; diff --git a/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper_dce112.c b/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper_dce112.c index 06b4f7fa4a50..1a5fefcde8af 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper_dce112.c +++ b/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper_dce112.c @@ -31,39 +31,6 @@ #include "../command_table_helper.h" -static uint8_t phy_id_to_atom(enum transmitter t) -{ - uint8_t atom_phy_id; - - switch (t) { - case TRANSMITTER_UNIPHY_A: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - case TRANSMITTER_UNIPHY_B: - atom_phy_id = ATOM_PHY_ID_UNIPHYB; - break; - case TRANSMITTER_UNIPHY_C: - atom_phy_id = ATOM_PHY_ID_UNIPHYC; - break; - case TRANSMITTER_UNIPHY_D: - atom_phy_id = ATOM_PHY_ID_UNIPHYD; - break; - case TRANSMITTER_UNIPHY_E: - atom_phy_id = ATOM_PHY_ID_UNIPHYE; - break; - case TRANSMITTER_UNIPHY_F: - atom_phy_id = ATOM_PHY_ID_UNIPHYF; - break; - case TRANSMITTER_UNIPHY_G: - atom_phy_id = ATOM_PHY_ID_UNIPHYG; - break; - default: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - } - return atom_phy_id; -} - static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) { uint8_t atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V6_DP; @@ -91,32 +58,6 @@ static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) return atom_dig_mode; } -static uint8_t clock_source_id_to_atom_phy_clk_src_id( - enum clock_source_id id) -{ - uint8_t atom_phy_clk_src_id = 0; - - switch (id) { - case CLOCK_SOURCE_ID_PLL0: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL; - break; - case CLOCK_SOURCE_ID_PLL1: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - case CLOCK_SOURCE_ID_PLL2: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL; - break; - case CLOCK_SOURCE_ID_EXTERNAL: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT; - break; - default: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - } - - return atom_phy_clk_src_id >> 2; -} - static uint8_t hpd_sel_to_atom(enum hpd_source_id id) { uint8_t atom_hpd_sel = 0; @@ -209,51 +150,6 @@ static bool clock_source_id_to_atom( return result; } -static bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id) -{ - bool result = false; - - if (atom_engine_id != NULL) - switch (id) { - case ENGINE_ID_DIGA: - *atom_engine_id = ASIC_INT_DIG1_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGB: - *atom_engine_id = ASIC_INT_DIG2_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGC: - *atom_engine_id = ASIC_INT_DIG3_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGD: - *atom_engine_id = ASIC_INT_DIG4_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGE: - *atom_engine_id = ASIC_INT_DIG5_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGF: - *atom_engine_id = ASIC_INT_DIG6_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGG: - *atom_engine_id = ASIC_INT_DIG7_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DACA: - *atom_engine_id = ASIC_INT_DAC1_ENCODER_ID; - result = true; - break; - default: - break; - } - - return result; -} - static uint8_t encoder_action_to_atom(enum bp_encoder_control_action action) { uint8_t atom_action = 0; diff --git a/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.c b/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.c index 710221b4f5c5..01ccc803040c 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.c +++ b/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.c @@ -58,51 +58,6 @@ static uint8_t encoder_action_to_atom(enum bp_encoder_control_action action) return atom_action; } -static bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id) -{ - bool result = false; - - if (atom_engine_id != NULL) - switch (id) { - case ENGINE_ID_DIGA: - *atom_engine_id = ASIC_INT_DIG1_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGB: - *atom_engine_id = ASIC_INT_DIG2_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGC: - *atom_engine_id = ASIC_INT_DIG3_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGD: - *atom_engine_id = ASIC_INT_DIG4_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGE: - *atom_engine_id = ASIC_INT_DIG5_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGF: - *atom_engine_id = ASIC_INT_DIG6_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGG: - *atom_engine_id = ASIC_INT_DIG7_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DACA: - *atom_engine_id = ASIC_INT_DAC1_ENCODER_ID; - result = true; - break; - default: - break; - } - - return result; -} - static bool clock_source_id_to_atom( enum clock_source_id id, uint32_t *atom_pll_id) @@ -149,32 +104,6 @@ static bool clock_source_id_to_atom( return result; } -static uint8_t clock_source_id_to_atom_phy_clk_src_id( - enum clock_source_id id) -{ - uint8_t atom_phy_clk_src_id = 0; - - switch (id) { - case CLOCK_SOURCE_ID_PLL0: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL; - break; - case CLOCK_SOURCE_ID_PLL1: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - case CLOCK_SOURCE_ID_PLL2: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL; - break; - case CLOCK_SOURCE_ID_EXTERNAL: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT; - break; - default: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - } - - return atom_phy_clk_src_id >> 2; -} - static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) { uint8_t atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_DP; @@ -270,39 +199,6 @@ static uint8_t dig_encoder_sel_to_atom(enum engine_id id) return atom_dig_encoder_sel; } -static uint8_t phy_id_to_atom(enum transmitter t) -{ - uint8_t atom_phy_id; - - switch (t) { - case TRANSMITTER_UNIPHY_A: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - case TRANSMITTER_UNIPHY_B: - atom_phy_id = ATOM_PHY_ID_UNIPHYB; - break; - case TRANSMITTER_UNIPHY_C: - atom_phy_id = ATOM_PHY_ID_UNIPHYC; - break; - case TRANSMITTER_UNIPHY_D: - atom_phy_id = ATOM_PHY_ID_UNIPHYD; - break; - case TRANSMITTER_UNIPHY_E: - atom_phy_id = ATOM_PHY_ID_UNIPHYE; - break; - case TRANSMITTER_UNIPHY_F: - atom_phy_id = ATOM_PHY_ID_UNIPHYF; - break; - case TRANSMITTER_UNIPHY_G: - atom_phy_id = ATOM_PHY_ID_UNIPHYG; - break; - default: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - } - return atom_phy_id; -} - static uint8_t disp_power_gating_action_to_atom( enum bp_pipe_control_action action) { diff --git a/drivers/gpu/drm/amd/display/dc/bios/dce80/command_table_helper_dce80.c b/drivers/gpu/drm/amd/display/dc/bios/dce80/command_table_helper_dce80.c index 8b30b558cf1f..2ec5264536c7 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/dce80/command_table_helper_dce80.c +++ b/drivers/gpu/drm/amd/display/dc/bios/dce80/command_table_helper_dce80.c @@ -58,51 +58,6 @@ static uint8_t encoder_action_to_atom(enum bp_encoder_control_action action) return atom_action; } -static bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id) -{ - bool result = false; - - if (atom_engine_id != NULL) - switch (id) { - case ENGINE_ID_DIGA: - *atom_engine_id = ASIC_INT_DIG1_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGB: - *atom_engine_id = ASIC_INT_DIG2_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGC: - *atom_engine_id = ASIC_INT_DIG3_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGD: - *atom_engine_id = ASIC_INT_DIG4_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGE: - *atom_engine_id = ASIC_INT_DIG5_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGF: - *atom_engine_id = ASIC_INT_DIG6_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGG: - *atom_engine_id = ASIC_INT_DIG7_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DACA: - *atom_engine_id = ASIC_INT_DAC1_ENCODER_ID; - result = true; - break; - default: - break; - } - - return result; -} - static bool clock_source_id_to_atom( enum clock_source_id id, uint32_t *atom_pll_id) @@ -149,32 +104,6 @@ static bool clock_source_id_to_atom( return result; } -static uint8_t clock_source_id_to_atom_phy_clk_src_id( - enum clock_source_id id) -{ - uint8_t atom_phy_clk_src_id = 0; - - switch (id) { - case CLOCK_SOURCE_ID_PLL0: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL; - break; - case CLOCK_SOURCE_ID_PLL1: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - case CLOCK_SOURCE_ID_PLL2: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL; - break; - case CLOCK_SOURCE_ID_EXTERNAL: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT; - break; - default: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - } - - return atom_phy_clk_src_id >> 2; -} - static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) { uint8_t atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_DP; @@ -270,39 +199,6 @@ static uint8_t dig_encoder_sel_to_atom(enum engine_id id) return atom_dig_encoder_sel; } -static uint8_t phy_id_to_atom(enum transmitter t) -{ - uint8_t atom_phy_id; - - switch (t) { - case TRANSMITTER_UNIPHY_A: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - case TRANSMITTER_UNIPHY_B: - atom_phy_id = ATOM_PHY_ID_UNIPHYB; - break; - case TRANSMITTER_UNIPHY_C: - atom_phy_id = ATOM_PHY_ID_UNIPHYC; - break; - case TRANSMITTER_UNIPHY_D: - atom_phy_id = ATOM_PHY_ID_UNIPHYD; - break; - case TRANSMITTER_UNIPHY_E: - atom_phy_id = ATOM_PHY_ID_UNIPHYE; - break; - case TRANSMITTER_UNIPHY_F: - atom_phy_id = ATOM_PHY_ID_UNIPHYF; - break; - case TRANSMITTER_UNIPHY_G: - atom_phy_id = ATOM_PHY_ID_UNIPHYG; - break; - default: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - } - return atom_phy_id; -} - static uint8_t disp_power_gating_action_to_atom( enum bp_pipe_control_action action) { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index df29d28d89c9..af722519a1fa 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -201,16 +201,26 @@ static void dcn35_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state * struct pipe_ctx *pipe = safe_to_lower ? &context->res_ctx.pipe_ctx[i] : &dc->current_state->res_ctx.pipe_ctx[i]; + struct link_encoder *new_pipe_link_enc = new_pipe->link_res.dio_link_enc; + struct link_encoder *pipe_link_enc = pipe->link_res.dio_link_enc; bool stream_changed_otg_dig_on = false; if (pipe->top_pipe || pipe->prev_odm_pipe) continue; + + if (!dc->config.unify_link_enc_assignment) { + if (new_pipe->stream) + new_pipe_link_enc = new_pipe->stream->link_enc; + if (pipe->stream) + pipe_link_enc = pipe->stream->link_enc; + } + stream_changed_otg_dig_on = old_pipe->stream && new_pipe->stream && old_pipe->stream != new_pipe->stream && old_pipe->stream_res.tg == new_pipe->stream_res.tg && - new_pipe->stream->link_enc && !new_pipe->stream->dpms_off && - new_pipe->stream->link_enc->funcs->is_dig_enabled && - new_pipe->stream->link_enc->funcs->is_dig_enabled( - new_pipe->stream->link_enc) && + new_pipe_link_enc && !new_pipe->stream->dpms_off && + new_pipe_link_enc->funcs->is_dig_enabled && + new_pipe_link_enc->funcs->is_dig_enabled( + new_pipe_link_enc) && new_pipe->stream_res.stream_enc && new_pipe->stream_res.stream_enc->funcs->is_fifo_enabled && new_pipe->stream_res.stream_enc->funcs->is_fifo_enabled(new_pipe->stream_res.stream_enc); @@ -226,7 +236,7 @@ static void dcn35_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state * if (!has_active_hpo && !dccg->ctx->dc->link_srv->dp_is_128b_132b_signal(pipe) && (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal) || - !pipe->stream->link_enc) && !stream_changed_otg_dig_on)) { + !pipe_link_enc) && !stream_changed_otg_dig_on)) { /* This w/a should not trigger when we have a dig active */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 05ad7a9af4ff..e71ea21401f5 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -905,7 +905,8 @@ void dc_stream_set_static_screen_params(struct dc *dc, static void dc_destruct(struct dc *dc) { // reset link encoder assignment table on destruct - if (dc->res_pool && dc->res_pool->funcs->link_encs_assign) + if (dc->res_pool && dc->res_pool->funcs->link_encs_assign && + !dc->config.unify_link_enc_assignment) link_enc_cfg_init(dc, dc->current_state); if (dc->current_state) { @@ -1201,6 +1202,8 @@ static void dc_update_visual_confirm_color(struct dc *dc, struct dc_state *conte get_surface_tile_visual_confirm_color(pipe_ctx, &(pipe_ctx->visual_confirm_color)); else if (dc->debug.visual_confirm == VISUAL_CONFIRM_HW_CURSOR) get_cursor_visual_confirm_color(pipe_ctx, &(pipe_ctx->visual_confirm_color)); + else if (dc->debug.visual_confirm == VISUAL_CONFIRM_DCC) + get_dcc_visual_confirm_color(dc, pipe_ctx, &(pipe_ctx->visual_confirm_color)); else { if (dc->ctx->dce_version < DCN_VERSION_2_0) color_space_to_black_color( @@ -3955,6 +3958,9 @@ static void commit_planes_for_stream(struct dc *dc, if (update_type == UPDATE_TYPE_FULL && dc->optimized_required) hwss_process_outstanding_hw_updates(dc, dc->current_state); + if (update_type != UPDATE_TYPE_FAST && dc->res_pool->funcs->prepare_mcache_programming) + dc->res_pool->funcs->prepare_mcache_programming(dc, context); + for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; @@ -4013,9 +4019,6 @@ static void commit_planes_for_stream(struct dc *dc, odm_pipe->ttu_regs.min_ttu_vblank = MAX_TTU; } - if (update_type != UPDATE_TYPE_FAST && dc->res_pool->funcs->prepare_mcache_programming) - dc->res_pool->funcs->prepare_mcache_programming(dc, context); - if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed) if (top_pipe_to_program && top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable) { @@ -4937,7 +4940,8 @@ static bool full_update_required(struct dc *dc, stream_update->lut3d_func || stream_update->pending_test_pattern || stream_update->crtc_timing_adjust || - stream_update->scaler_sharpener_update)) + stream_update->scaler_sharpener_update || + stream_update->hw_cursor_req)) return true; if (stream) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c index af1ea5792560..650e89825968 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c @@ -51,126 +51,6 @@ DC_LOG_BANDWIDTH_CALCS(__VA_ARGS__); \ } while (0) -void pre_surface_trace( - struct dc *dc, - const struct dc_plane_state *const *plane_states, - int surface_count) -{ - int i; - DC_LOGGER_INIT(dc->ctx->logger); - - for (i = 0; i < surface_count; i++) { - const struct dc_plane_state *plane_state = plane_states[i]; - - SURFACE_TRACE("Planes %d:\n", i); - - SURFACE_TRACE( - "plane_state->visible = %d;\n" - "plane_state->flip_immediate = %d;\n" - "plane_state->address.type = %d;\n" - "plane_state->address.grph.addr.quad_part = 0x%llX;\n" - "plane_state->address.grph.meta_addr.quad_part = 0x%llX;\n" - "plane_state->scaling_quality.h_taps = %d;\n" - "plane_state->scaling_quality.v_taps = %d;\n" - "plane_state->scaling_quality.h_taps_c = %d;\n" - "plane_state->scaling_quality.v_taps_c = %d;\n", - plane_state->visible, - plane_state->flip_immediate, - plane_state->address.type, - plane_state->address.grph.addr.quad_part, - plane_state->address.grph.meta_addr.quad_part, - plane_state->scaling_quality.h_taps, - plane_state->scaling_quality.v_taps, - plane_state->scaling_quality.h_taps_c, - plane_state->scaling_quality.v_taps_c); - - SURFACE_TRACE( - "plane_state->src_rect.x = %d;\n" - "plane_state->src_rect.y = %d;\n" - "plane_state->src_rect.width = %d;\n" - "plane_state->src_rect.height = %d;\n" - "plane_state->dst_rect.x = %d;\n" - "plane_state->dst_rect.y = %d;\n" - "plane_state->dst_rect.width = %d;\n" - "plane_state->dst_rect.height = %d;\n" - "plane_state->clip_rect.x = %d;\n" - "plane_state->clip_rect.y = %d;\n" - "plane_state->clip_rect.width = %d;\n" - "plane_state->clip_rect.height = %d;\n", - plane_state->src_rect.x, - plane_state->src_rect.y, - plane_state->src_rect.width, - plane_state->src_rect.height, - plane_state->dst_rect.x, - plane_state->dst_rect.y, - plane_state->dst_rect.width, - plane_state->dst_rect.height, - plane_state->clip_rect.x, - plane_state->clip_rect.y, - plane_state->clip_rect.width, - plane_state->clip_rect.height); - - SURFACE_TRACE( - "plane_state->plane_size.surface_size.x = %d;\n" - "plane_state->plane_size.surface_size.y = %d;\n" - "plane_state->plane_size.surface_size.width = %d;\n" - "plane_state->plane_size.surface_size.height = %d;\n" - "plane_state->plane_size.surface_pitch = %d;\n", - plane_state->plane_size.surface_size.x, - plane_state->plane_size.surface_size.y, - plane_state->plane_size.surface_size.width, - plane_state->plane_size.surface_size.height, - plane_state->plane_size.surface_pitch); - - - SURFACE_TRACE( - "plane_state->tiling_info.gfx8.num_banks = %d;\n" - "plane_state->tiling_info.gfx8.bank_width = %d;\n" - "plane_state->tiling_info.gfx8.bank_width_c = %d;\n" - "plane_state->tiling_info.gfx8.bank_height = %d;\n" - "plane_state->tiling_info.gfx8.bank_height_c = %d;\n" - "plane_state->tiling_info.gfx8.tile_aspect = %d;\n" - "plane_state->tiling_info.gfx8.tile_aspect_c = %d;\n" - "plane_state->tiling_info.gfx8.tile_split = %d;\n" - "plane_state->tiling_info.gfx8.tile_split_c = %d;\n" - "plane_state->tiling_info.gfx8.tile_mode = %d;\n" - "plane_state->tiling_info.gfx8.tile_mode_c = %d;\n", - plane_state->tiling_info.gfx8.num_banks, - plane_state->tiling_info.gfx8.bank_width, - plane_state->tiling_info.gfx8.bank_width_c, - plane_state->tiling_info.gfx8.bank_height, - plane_state->tiling_info.gfx8.bank_height_c, - plane_state->tiling_info.gfx8.tile_aspect, - plane_state->tiling_info.gfx8.tile_aspect_c, - plane_state->tiling_info.gfx8.tile_split, - plane_state->tiling_info.gfx8.tile_split_c, - plane_state->tiling_info.gfx8.tile_mode, - plane_state->tiling_info.gfx8.tile_mode_c); - - SURFACE_TRACE( - "plane_state->tiling_info.gfx8.pipe_config = %d;\n" - "plane_state->tiling_info.gfx8.array_mode = %d;\n" - "plane_state->color_space = %d;\n" - "plane_state->dcc.enable = %d;\n" - "plane_state->format = %d;\n" - "plane_state->rotation = %d;\n" - "plane_state->stereo_format = %d;\n", - plane_state->tiling_info.gfx8.pipe_config, - plane_state->tiling_info.gfx8.array_mode, - plane_state->color_space, - plane_state->dcc.enable, - plane_state->format, - plane_state->rotation, - plane_state->stereo_format); - - SURFACE_TRACE("plane_state->tiling_info.gfx9.swizzle = %d;\n", - plane_state->tiling_info.gfx9.swizzle); - - SURFACE_TRACE("\n"); - } - SURFACE_TRACE("\n"); -} - void update_surface_trace( struct dc *dc, const struct dc_surface_update *updates, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c index 6b514fd03f16..e0277728268a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c @@ -34,6 +34,7 @@ #include "dc_state_priv.h" #define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0])) +#define MAX_NUM_MCACHE 8 /* used as index in array of black_color_format */ enum black_color_format { @@ -553,6 +554,53 @@ void get_cursor_visual_confirm_color( } } +void get_dcc_visual_confirm_color( + struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct tg_color *color) +{ + const uint32_t MCACHE_ID_UNASSIGNED = 0xF; + + if (!pipe_ctx->plane_state->dcc.enable) { + color->color_r_cr = 0; /* black - DCC disabled */ + color->color_g_y = 0; + color->color_b_cb = 0; + return; + } + + if (dc->ctx->dce_version < DCN_VERSION_4_01) { + color->color_r_cr = MAX_TG_COLOR_VALUE; /* red - DCC enabled */ + color->color_g_y = 0; + color->color_b_cb = 0; + return; + } + + uint32_t first_id = pipe_ctx->mcache_regs.main.p0.mcache_id_first; + uint32_t second_id = pipe_ctx->mcache_regs.main.p0.mcache_id_second; + + if (first_id != MCACHE_ID_UNASSIGNED && second_id != MCACHE_ID_UNASSIGNED && first_id != second_id) { + color->color_r_cr = MAX_TG_COLOR_VALUE/2; /* grey - 2 mcache */ + color->color_g_y = MAX_TG_COLOR_VALUE/2; + color->color_b_cb = MAX_TG_COLOR_VALUE/2; + } + + else if (first_id != MCACHE_ID_UNASSIGNED || second_id != MCACHE_ID_UNASSIGNED) { + const struct tg_color id_colors[MAX_NUM_MCACHE] = { + {0, MAX_TG_COLOR_VALUE, 0}, /* green */ + {0, 0, MAX_TG_COLOR_VALUE}, /* blue */ + {MAX_TG_COLOR_VALUE, MAX_TG_COLOR_VALUE, 0}, /* yellow */ + {MAX_TG_COLOR_VALUE, 0, MAX_TG_COLOR_VALUE}, /* magenta */ + {0, MAX_TG_COLOR_VALUE, MAX_TG_COLOR_VALUE}, /* cyan */ + {MAX_TG_COLOR_VALUE, MAX_TG_COLOR_VALUE, MAX_TG_COLOR_VALUE}, /* white */ + {MAX_TG_COLOR_VALUE/2, 0, 0}, /* dark red */ + {0, MAX_TG_COLOR_VALUE/2, 0}, /* dark green */ + }; + + uint32_t assigned_id = (first_id != MCACHE_ID_UNASSIGNED) ? first_id : second_id; + *color = id_colors[assigned_id]; + } +} + void set_p_state_switch_method( struct dc *dc, struct dc_state *context, @@ -564,6 +612,7 @@ void set_p_state_switch_method( if (!dc->ctx || !dc->ctx->dmub_srv || !pipe_ctx || !vba) return; + pipe_ctx->p_state_type = P_STATE_UNKNOWN; if (vba->DRAMClockChangeSupport[vba->VoltageLevel][vba->maxMpcComb] != dm_dram_clock_change_unsupported) { /* MCLK switching is supported */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 7eb91612b60d..ea404435c9b9 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1472,7 +1472,8 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx) DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger); /* Invalid input */ - if (!plane_state->dst_rect.width || + if (!plane_state || + !plane_state->dst_rect.width || !plane_state->dst_rect.height || !plane_state->src_rect.width || !plane_state->src_rect.height) { @@ -4925,7 +4926,10 @@ bool pipe_need_reprogram( return true; /* DIG link encoder resource assignment for stream changed. */ - if (pipe_ctx_old->stream->ctx->dc->res_pool->funcs->link_encs_assign) { + if (pipe_ctx_old->stream->ctx->dc->config.unify_link_enc_assignment) { + if (pipe_ctx_old->link_res.dio_link_enc != pipe_ctx->link_res.dio_link_enc) + return true; + } else if (pipe_ctx_old->stream->ctx->dc->res_pool->funcs->link_encs_assign) { bool need_reprogram = false; struct dc *dc = pipe_ctx_old->stream->ctx->dc; struct link_encoder *link_enc_prev = @@ -5191,7 +5195,7 @@ void get_audio_check(struct audio_info *aud_modes, } } -static struct link_encoder *get_temp_dio_link_enc( +struct link_encoder *get_temp_dio_link_enc( const struct resource_context *res_ctx, const struct resource_pool *const pool, const struct dc_link *link) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index e8134c47fe0d..0478dd856d8c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -201,7 +201,8 @@ struct dc_stream_state *dc_copy_stream(const struct dc_stream_state *stream) dc_stream_assign_stream_id(new_stream); /* If using dynamic encoder assignment, wait till stream committed to assign encoder. */ - if (new_stream->ctx->dc->res_pool->funcs->link_encs_assign) + if (new_stream->ctx->dc->res_pool->funcs->link_encs_assign && + !new_stream->ctx->dc->config.unify_link_enc_assignment) new_stream->link_enc = NULL; kref_init(&new_stream->refcount); diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 5e96913bcab1..a62c4893e5ff 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -53,7 +53,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.321" +#define DC_VER "3.2.323" /** * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC @@ -495,6 +495,7 @@ enum visual_confirm { VISUAL_CONFIRM_FAMS2 = 19, VISUAL_CONFIRM_HW_CURSOR = 20, VISUAL_CONFIRM_VABC = 21, + VISUAL_CONFIRM_DCC = 22, }; enum dc_psr_power_opts { @@ -1083,6 +1084,7 @@ struct dc_debug_options { unsigned int enable_oled_edp_power_up_opt; bool enable_hblank_borrow; bool force_subvp_df_throttle; + uint32_t acpi_transition_bitmasks[MAX_PIPES]; }; @@ -1806,6 +1808,7 @@ struct dc_link { struct dc_panel_config panel_config; struct phy_state phy_state; + uint32_t phy_transition_bitmask; // BW ALLOCATON USB4 ONLY struct dc_dpia_bw_alloc dpia_bw_alloc_config; bool skip_implict_edp_power_control; diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h index ae6e2d8552ac..1f4f11adc491 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h @@ -300,6 +300,19 @@ union lane_align_status_updated { uint8_t raw; }; +union link_service_irq_vector_esi0 { + struct { + uint8_t DP_LINK_RX_CAP_CHANGED:1; + uint8_t DP_LINK_STATUS_CHANGED:1; + uint8_t DP_LINK_STREAM_STATUS_CHANGED:1; + uint8_t DP_LINK_HDMI_LINK_STATUS_CHANGED:1; + uint8_t DP_LINK_CONNECTED_OFF_ENTRY_REQUESTED:1; + uint8_t DP_LINK_TUNNELING_IRQ:1; + uint8_t reserved:2; + } bits; + uint8_t raw; +}; + union lane_adjust { struct { uint8_t VOLTAGE_SWING_LANE:2; @@ -410,14 +423,6 @@ union dwnstream_port_caps_byte3_hdmi { uint8_t raw; }; -union hdmi_sink_encoded_link_bw_support { - struct { - uint8_t HDMI_SINK_ENCODED_LINK_BW_SUPPORT:3; - uint8_t RESERVED:5; - } bits; - uint8_t raw; -}; - union hdmi_encoded_link_bw { struct { uint8_t FRL_MODE:1; // Bit 0 @@ -470,8 +475,10 @@ union sink_status { uint8_t raw; }; -/*6-byte structure corresponding to 6 registers (200h-205h) -read during handling of HPD-IRQ*/ +/* 7-byte structure corresponding to 6 registers (200h-205h) + * and LINK_SERVICE_IRQ_ESI0 (2005h) for tunneling IRQ + * read during handling of HPD-IRQ + */ union hpd_irq_data { struct { union sink_count sink_cnt;/* 200h */ @@ -479,9 +486,10 @@ union hpd_irq_data { union lane_status lane01_status;/* 202h */ union lane_status lane23_status;/* 203h */ union lane_align_status_updated lane_status_updated;/* 204h */ - union sink_status sink_status; + union sink_status sink_status;/* 205h */ + union link_service_irq_vector_esi0 link_service_irq_esi0;/* 2005h */ } bytes; - uint8_t raw[6]; + uint8_t raw[7]; }; union down_stream_port_count { @@ -1128,6 +1136,8 @@ struct dc_lttpr_caps { union dp_128b_132b_supported_lttpr_link_rates supported_128b_132b_rates; union dp_alpm_lttpr_cap alpm; uint8_t aux_rd_interval[MAX_REPEATER_CNT - 1]; + uint8_t lttpr_ieee_oui[3]; + uint8_t lttpr_device_id[6]; }; struct dc_dongle_dfp_cap_ext { @@ -1218,6 +1228,8 @@ struct dpcd_caps { struct replay_info pr_info; uint16_t edp_oled_emission_rate; union dp_receive_port0_cap receive_port0_cap; + /* Indicates the number of SST links supported by MSO (Multi-Stream Output) */ + uint8_t mso_cap_sst_links_supported; }; union dpcd_sink_ext_caps { @@ -1391,6 +1403,12 @@ struct dp_trace { #ifndef DP_BRANCH_VENDOR_SPECIFIC_START #define DP_BRANCH_VENDOR_SPECIFIC_START 0x50C #endif +#ifndef DP_LTTPR_IEEE_OUI +#define DP_LTTPR_IEEE_OUI 0xF003D +#endif +#ifndef DP_LTTPR_DEVICE_ID +#define DP_LTTPR_DEVICE_ID 0xF0040 +#endif /** USB4 DPCD BW Allocation Registers Chapter 10.7 **/ #ifndef DP_TUNNELING_CAPABILITIES #define DP_TUNNELING_CAPABILITIES 0xE000D /* 1.4a */ @@ -1428,4 +1446,20 @@ struct dp_trace { #ifndef REQUESTED_BW #define REQUESTED_BW 0xE0031 /* 1.4a */ #endif +# ifndef DP_TUNNELING_BW_ALLOC_BITS_MASK +# define DP_TUNNELING_BW_ALLOC_BITS_MASK (0x0F << 0) +# endif +# ifndef DP_TUNNELING_BW_REQUEST_FAILED +# define DP_TUNNELING_BW_REQUEST_FAILED (1 << 0) +# endif +# ifndef DP_TUNNELING_BW_REQUEST_SUCCEEDED +# define DP_TUNNELING_BW_REQUEST_SUCCEEDED (1 << 1) +# endif +# ifndef DP_TUNNELING_ESTIMATED_BW_CHANGED +# define DP_TUNNELING_ESTIMATED_BW_CHANGED (1 << 2) +# endif +# ifndef DP_TUNNELING_BW_ALLOC_CAP_CHANGED +# define DP_TUNNELING_BW_ALLOC_CAP_CHANGED (1 << 3) +# endif + #endif /* DC_DP_TYPES_H */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index e60898c2df01..acd3b373a18e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -181,6 +181,7 @@ struct dc_panel_patch { uint8_t blankstream_before_otg_off; bool oled_optimize_display_on; unsigned int force_mst_blocked_discovery; + unsigned int wait_after_dpcd_poweroff_ms; }; struct dc_edid_caps { diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h index 160c299419b7..a9b88f5e0c04 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h @@ -379,53 +379,55 @@ struct dccg_mask { DCCG401_REG_FIELD_LIST(uint32_t) }; +#define DCCG_REG_VARIABLE_LIST \ + uint32_t DPPCLK_DTO_CTRL; \ + uint32_t DPPCLK_DTO_PARAM[6]; \ + uint32_t REFCLK_CNTL; \ + uint32_t DISPCLK_FREQ_CHANGE_CNTL; \ + uint32_t OTG_PIXEL_RATE_CNTL[MAX_PIPES]; \ + uint32_t HDMICHARCLK_CLOCK_CNTL[6]; \ + uint32_t PHYASYMCLK_CLOCK_CNTL; \ + uint32_t PHYBSYMCLK_CLOCK_CNTL; \ + uint32_t PHYCSYMCLK_CLOCK_CNTL; \ + uint32_t PHYDSYMCLK_CLOCK_CNTL; \ + uint32_t PHYESYMCLK_CLOCK_CNTL; \ + uint32_t DTBCLK_DTO_MODULO[MAX_PIPES]; \ + uint32_t DTBCLK_DTO_PHASE[MAX_PIPES]; \ + uint32_t DCCG_AUDIO_DTBCLK_DTO_MODULO; \ + uint32_t DCCG_AUDIO_DTBCLK_DTO_PHASE; \ + uint32_t DCCG_AUDIO_DTO_SOURCE; \ + uint32_t DPSTREAMCLK_CNTL; \ + uint32_t HDMISTREAMCLK_CNTL; \ + uint32_t SYMCLK32_SE_CNTL; \ + uint32_t SYMCLK32_LE_CNTL; \ + uint32_t DENTIST_DISPCLK_CNTL; \ + uint32_t DSCCLK_DTO_CTRL; \ + uint32_t DSCCLK0_DTO_PARAM; \ + uint32_t DSCCLK1_DTO_PARAM; \ + uint32_t DSCCLK2_DTO_PARAM; \ + uint32_t DSCCLK3_DTO_PARAM; \ + uint32_t DPSTREAMCLK_ROOT_GATE_DISABLE; \ + uint32_t DPSTREAMCLK_GATE_DISABLE; \ + uint32_t DCCG_GATE_DISABLE_CNTL; \ + uint32_t DCCG_GATE_DISABLE_CNTL2; \ + uint32_t DCCG_GATE_DISABLE_CNTL3; \ + uint32_t HDMISTREAMCLK0_DTO_PARAM; \ + uint32_t DCCG_GATE_DISABLE_CNTL4; \ + uint32_t OTG_PIXEL_RATE_DIV; \ + uint32_t DTBCLK_P_CNTL; \ + uint32_t DPPCLK_CTRL; \ + uint32_t DCCG_GATE_DISABLE_CNTL5; \ + uint32_t DCCG_GATE_DISABLE_CNTL6; \ + uint32_t DCCG_GLOBAL_FGCG_REP_CNTL; \ + uint32_t SYMCLKA_CLOCK_ENABLE; \ + uint32_t SYMCLKB_CLOCK_ENABLE; \ + uint32_t SYMCLKC_CLOCK_ENABLE; \ + uint32_t SYMCLKD_CLOCK_ENABLE; \ + uint32_t SYMCLKE_CLOCK_ENABLE; \ + uint32_t DP_DTO_MODULO[MAX_PIPES]; \ + uint32_t DP_DTO_PHASE[MAX_PIPES] struct dccg_registers { - uint32_t DPPCLK_DTO_CTRL; - uint32_t DPPCLK_DTO_PARAM[6]; - uint32_t REFCLK_CNTL; - uint32_t DISPCLK_FREQ_CHANGE_CNTL; - uint32_t OTG_PIXEL_RATE_CNTL[MAX_PIPES]; - uint32_t HDMICHARCLK_CLOCK_CNTL[6]; - uint32_t PHYASYMCLK_CLOCK_CNTL; - uint32_t PHYBSYMCLK_CLOCK_CNTL; - uint32_t PHYCSYMCLK_CLOCK_CNTL; - uint32_t PHYDSYMCLK_CLOCK_CNTL; - uint32_t PHYESYMCLK_CLOCK_CNTL; - uint32_t DTBCLK_DTO_MODULO[MAX_PIPES]; - uint32_t DTBCLK_DTO_PHASE[MAX_PIPES]; - uint32_t DCCG_AUDIO_DTBCLK_DTO_MODULO; - uint32_t DCCG_AUDIO_DTBCLK_DTO_PHASE; - uint32_t DCCG_AUDIO_DTO_SOURCE; - uint32_t DPSTREAMCLK_CNTL; - uint32_t HDMISTREAMCLK_CNTL; - uint32_t SYMCLK32_SE_CNTL; - uint32_t SYMCLK32_LE_CNTL; - uint32_t DENTIST_DISPCLK_CNTL; - uint32_t DSCCLK_DTO_CTRL; - uint32_t DSCCLK0_DTO_PARAM; - uint32_t DSCCLK1_DTO_PARAM; - uint32_t DSCCLK2_DTO_PARAM; - uint32_t DSCCLK3_DTO_PARAM; - uint32_t DPSTREAMCLK_ROOT_GATE_DISABLE; - uint32_t DPSTREAMCLK_GATE_DISABLE; - uint32_t DCCG_GATE_DISABLE_CNTL; - uint32_t DCCG_GATE_DISABLE_CNTL2; - uint32_t DCCG_GATE_DISABLE_CNTL3; - uint32_t HDMISTREAMCLK0_DTO_PARAM; - uint32_t DCCG_GATE_DISABLE_CNTL4; - uint32_t OTG_PIXEL_RATE_DIV; - uint32_t DTBCLK_P_CNTL; - uint32_t DPPCLK_CTRL; - uint32_t DCCG_GATE_DISABLE_CNTL5; - uint32_t DCCG_GATE_DISABLE_CNTL6; - uint32_t DCCG_GLOBAL_FGCG_REP_CNTL; - uint32_t SYMCLKA_CLOCK_ENABLE; - uint32_t SYMCLKB_CLOCK_ENABLE; - uint32_t SYMCLKC_CLOCK_ENABLE; - uint32_t SYMCLKD_CLOCK_ENABLE; - uint32_t SYMCLKE_CLOCK_ENABLE; - uint32_t DP_DTO_MODULO[MAX_PIPES]; - uint32_t DP_DTO_PHASE[MAX_PIPES]; + DCCG_REG_VARIABLE_LIST; }; struct dcn_dccg { diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c index 332094ad2b05..ffd172231fdf 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c @@ -531,7 +531,7 @@ static void dccg401_enable_dpstreamclk(struct dccg *dccg, int otg_inst, int dp_h DPSTREAMCLK_ROOT_GATE_DISABLE, 1); } -static void dccg401_disable_dpstreamclk(struct dccg *dccg, int dp_hpo_inst) +void dccg401_disable_dpstreamclk(struct dccg *dccg, int dp_hpo_inst) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.h index b9905c73e754..55e8718aad22 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.h @@ -208,6 +208,8 @@ void dccg401_enable_symclk32_le( void dccg401_disable_symclk32_le( struct dccg *dccg, int hpo_le_inst); +void dccg401_disable_dpstreamclk(struct dccg *dccg, int dp_hpo_inst); +void dccg401_set_dto_dscclk(struct dccg *dccg, uint32_t inst); void dccg401_set_ref_dscclk(struct dccg *dccg, uint32_t dsc_inst); void dccg401_set_src_sel( @@ -228,14 +230,11 @@ void dccg401_set_dp_dto( const struct dp_dto_params *params); void dccg401_enable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst, uint32_t link_enc_inst); void dccg401_disable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst, uint32_t link_enc_inst); - void dccg401_set_dto_dscclk(struct dccg *dccg, uint32_t inst); void dccg401_set_dtbclk_p_src( struct dccg *dccg, enum streamclk_source src, uint32_t otg_inst); - - struct dccg *dccg401_create( struct dc_context *ctx, const struct dccg_registers *regs, diff --git a/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c index e5fb0e8333e4..e691a1cf3356 100644 --- a/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c +++ b/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c @@ -239,6 +239,7 @@ static const struct timing_generator_funcs dce60_tg_funcs = { dce60_timing_generator_enable_advanced_request, .configure_crc = dce60_configure_crc, .get_crc = dce110_get_crc, + .is_two_pixels_per_container = dce110_is_two_pixels_per_container, }; void dce60_timing_generator_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.c index ea0c9a9d0bd6..9972911330b6 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.c @@ -137,9 +137,9 @@ static const struct link_encoder_funcs dcn35_link_enc_funcs = { .hw_init = dcn35_link_encoder_init, .setup = dcn35_link_encoder_setup, .enable_tmds_output = dcn10_link_encoder_enable_tmds_output, - .enable_dp_output = dcn31_link_encoder_enable_dp_output, - .enable_dp_mst_output = dcn31_link_encoder_enable_dp_mst_output, - .disable_output = dcn31_link_encoder_disable_output, + .enable_dp_output = dcn35_link_encoder_enable_dp_output, + .enable_dp_mst_output = dcn35_link_encoder_enable_dp_mst_output, + .disable_output = dcn35_link_encoder_disable_output, .dp_set_lane_settings = dcn10_link_encoder_dp_set_lane_settings, .dp_set_phy_pattern = dcn10_link_encoder_dp_set_phy_pattern, .update_mst_stream_allocation_table = @@ -297,6 +297,50 @@ static void link_encoder_disable(struct dcn10_link_encoder *enc10) REG_UPDATE(DP_LINK_CNTL, DP_LINK_TRAINING_COMPLETE, 0); } +void dcn35_link_encoder_enable_dp_output( + struct link_encoder *enc, + const struct dc_link_settings *link_settings, + enum clock_source_id clock_source) +{ + struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); + + if (!enc->ctx->dc->config.unify_link_enc_assignment) + dcn31_link_encoder_enable_dp_output(enc, link_settings, clock_source); + else { + DC_LOG_DEBUG("%s: enc_id(%d)\n", __func__, enc->preferred_engine); + dcn20_link_encoder_enable_dp_output(enc, link_settings, clock_source); + } +} + +void dcn35_link_encoder_enable_dp_mst_output( + struct link_encoder *enc, + const struct dc_link_settings *link_settings, + enum clock_source_id clock_source) +{ + struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); + + if (!enc->ctx->dc->config.unify_link_enc_assignment) + dcn31_link_encoder_enable_dp_mst_output(enc, link_settings, clock_source); + else { + DC_LOG_DEBUG("%s: enc_id(%d)\n", __func__, enc->preferred_engine); + dcn10_link_encoder_enable_dp_mst_output(enc, link_settings, clock_source); + } +} + +void dcn35_link_encoder_disable_output( + struct link_encoder *enc, + enum signal_type signal) +{ + struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); + + if (!enc->ctx->dc->config.unify_link_enc_assignment) + dcn31_link_encoder_disable_output(enc, signal); + else { + DC_LOG_DEBUG("%s: enc_id(%d)\n", __func__, enc->preferred_engine); + dcn10_link_encoder_disable_output(enc, signal); + } +} + void dcn35_link_encoder_enable_dpia_output( struct link_encoder *enc, const struct dc_link_settings *link_settings, diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.h index f9d4221f4b43..5712e6553fab 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.h @@ -145,6 +145,29 @@ enum signal_type dcn35_get_dig_mode(struct link_encoder *enc); void dcn35_link_encoder_setup(struct link_encoder *enc, enum signal_type signal); /* + * Enable DP transmitter and its encoder. + */ +void dcn35_link_encoder_enable_dp_output( + struct link_encoder *enc, + const struct dc_link_settings *link_settings, + enum clock_source_id clock_source); + +/* + * Enable DP transmitter and its encoder in MST mode. + */ +void dcn35_link_encoder_enable_dp_mst_output( + struct link_encoder *enc, + const struct dc_link_settings *link_settings, + enum clock_source_id clock_source); + +/* + * Disable transmitter and its encoder. + */ +void dcn35_link_encoder_disable_output( + struct link_encoder *enc, + enum signal_type signal); + +/* * Enable DP transmitter and its encoder for dpia port. */ void dcn35_link_encoder_enable_dpia_output( diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c index 4bab180e1938..d5fa551dd3c9 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c @@ -100,7 +100,7 @@ void enc401_stream_encoder_dvi_set_stream_attribute( } /* setup stream encoder in hdmi mode */ -static void enc401_stream_encoder_hdmi_set_stream_attribute( +void enc401_stream_encoder_hdmi_set_stream_attribute( struct stream_encoder *enc, struct dc_crtc_timing *crtc_timing, int actual_pix_clk_khz, diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.h index 25cc8f72d8d3..d6b00cd246b1 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.h @@ -232,4 +232,9 @@ void enc401_stream_encoder_map_to_link( uint32_t stream_enc_inst, uint32_t link_enc_inst); void enc401_read_state(struct stream_encoder *enc, struct enc_state *s); +void enc401_stream_encoder_hdmi_set_stream_attribute( + struct stream_encoder *enc, + struct dc_crtc_timing *crtc_timing, + int actual_pix_clk_khz, + bool enable_audio); #endif /* __DC_DIO_STREAM_ENCODER_DCN401_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dm_services.h b/drivers/gpu/drm/amd/display/dc/dm_services.h index f81e5a4e1d6d..7b9c22c45453 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_services.h +++ b/drivers/gpu/drm/amd/display/dc/dm_services.h @@ -291,6 +291,13 @@ bool dm_execute_dmub_cmd(const struct dc_context *ctx, union dmub_rb_cmd *cmd, e bool dm_execute_dmub_cmd_list(const struct dc_context *ctx, unsigned int count, union dmub_rb_cmd *cmd, enum dm_dmub_wait_type wait_type); /* + * ACPI Interfaces + */ +void dm_acpi_process_phy_transition_interlock( + const struct dc_context *ctx, + struct dm_process_phy_transition_init_params process_phy_transition_init_params); + +/* * Debug and verification hooks */ diff --git a/drivers/gpu/drm/amd/display/dc/dm_services_types.h b/drivers/gpu/drm/amd/display/dc/dm_services_types.h index facf269c4326..bf63da266a18 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_services_types.h +++ b/drivers/gpu/drm/amd/display/dc/dm_services_types.h @@ -275,4 +275,30 @@ enum dm_dmub_wait_type { DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY, }; +enum dm_acpi_transition_link_type { + hdmi_tmds, + hdmi_frl, + dp_8b_10b, + dp_128b_132b, + none +}; + +struct dm_process_phy_transition_init_params { + uint32_t phy_id; + uint8_t action; + uint32_t sym_clock_10khz; + enum signal_type signal; + enum dc_lane_count display_port_lanes_count; + enum dc_link_rate display_port_link_rate; + uint32_t transition_bitmask; + uint8_t hdmi_frl_num_lanes; +}; + +struct dm_process_phy_transition_input_params { + uint32_t phy_id; + uint32_t transition_id; + uint32_t phy_configuration; + uint32_t data_rate; +}; + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c index aac0a0ae2966..88789987bdbc 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c @@ -178,82 +178,6 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_0_soc = { }; -void optc3_fpu_set_vrr_m_const(struct timing_generator *optc, - double vtotal_avg) -{ - struct optc *optc1 = DCN10TG_FROM_TG(optc); - double vtotal_min, vtotal_max; - double ratio, modulo, phase; - uint32_t vblank_start; - uint32_t v_total_mask_value = 0; - - dc_assert_fp_enabled(); - - /* Compute VTOTAL_MIN and VTOTAL_MAX, so that - * VOTAL_MAX - VTOTAL_MIN = 1 - */ - v_total_mask_value = 16; - vtotal_min = dcn_bw_floor(vtotal_avg); - vtotal_max = dcn_bw_ceil(vtotal_avg); - - /* Check that bottom VBLANK is at least 2 lines tall when running with - * VTOTAL_MIN. Note that VTOTAL registers are defined as 'total number - * of lines in a frame - 1'. - */ - REG_GET(OTG_V_BLANK_START_END, OTG_V_BLANK_START, - &vblank_start); - ASSERT(vtotal_min >= vblank_start + 1); - - /* Special case where the average frame rate can be achieved - * without using the DTO - */ - if (vtotal_min == vtotal_max) { - REG_SET(OTG_V_TOTAL, 0, OTG_V_TOTAL, (uint32_t)vtotal_min); - - optc->funcs->set_vtotal_min_max(optc, 0, 0); - REG_SET(OTG_M_CONST_DTO0, 0, OTG_M_CONST_DTO_PHASE, 0); - REG_SET(OTG_M_CONST_DTO1, 0, OTG_M_CONST_DTO_MODULO, 0); - REG_UPDATE_3(OTG_V_TOTAL_CONTROL, - OTG_V_TOTAL_MIN_SEL, 0, - OTG_V_TOTAL_MAX_SEL, 0, - OTG_SET_V_TOTAL_MIN_MASK_EN, 0); - return; - } - - ratio = vtotal_max - vtotal_avg; - modulo = 65536.0 * 65536.0 - 1.0; /* 2^32 - 1 */ - phase = ratio * modulo; - - /* Special cases where the DTO phase gets rounded to 0 or - * to DTO modulo - */ - if (phase <= 0 || phase >= modulo) { - REG_SET(OTG_V_TOTAL, 0, OTG_V_TOTAL, - phase <= 0 ? - (uint32_t)vtotal_max : (uint32_t)vtotal_min); - REG_SET(OTG_V_TOTAL_MIN, 0, OTG_V_TOTAL_MIN, 0); - REG_SET(OTG_V_TOTAL_MAX, 0, OTG_V_TOTAL_MAX, 0); - REG_SET(OTG_M_CONST_DTO0, 0, OTG_M_CONST_DTO_PHASE, 0); - REG_SET(OTG_M_CONST_DTO1, 0, OTG_M_CONST_DTO_MODULO, 0); - REG_UPDATE_3(OTG_V_TOTAL_CONTROL, - OTG_V_TOTAL_MIN_SEL, 0, - OTG_V_TOTAL_MAX_SEL, 0, - OTG_SET_V_TOTAL_MIN_MASK_EN, 0); - return; - } - REG_UPDATE_6(OTG_V_TOTAL_CONTROL, - OTG_V_TOTAL_MIN_SEL, 1, - OTG_V_TOTAL_MAX_SEL, 1, - OTG_SET_V_TOTAL_MIN_MASK_EN, 1, - OTG_SET_V_TOTAL_MIN_MASK, v_total_mask_value, - OTG_VTOTAL_MID_REPLACING_MIN_EN, 0, - OTG_VTOTAL_MID_REPLACING_MAX_EN, 0); - REG_SET(OTG_V_TOTAL, 0, OTG_V_TOTAL, (uint32_t)vtotal_min); - optc->funcs->set_vtotal_min_max(optc, vtotal_min, vtotal_max); - REG_SET(OTG_M_CONST_DTO0, 0, OTG_M_CONST_DTO_PHASE, (uint32_t)phase); - REG_SET(OTG_M_CONST_DTO1, 0, OTG_M_CONST_DTO_MODULO, (uint32_t)modulo); -} - void dcn30_fpu_populate_dml_writeback_from_context( struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes) { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.h index cab864095ce7..e3b6ad6a8784 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.h @@ -29,9 +29,6 @@ #include "core_types.h" #include "dcn20/dcn20_optc.h" -void optc3_fpu_set_vrr_m_const(struct timing_generator *optc, - double vtotal_avg); - void dcn30_fpu_populate_dml_writeback_from_context( struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c index cee1b351e105..f1fe49401bc0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c @@ -281,10 +281,10 @@ static void CalculateDynamicMetadataParameters( double DISPCLK, double DCFClkDeepSleep, double PixelClock, - long HTotal, - long VBlank, - long DynamicMetadataTransmittedBytes, - long DynamicMetadataLinesBeforeActiveRequired, + unsigned int HTotal, + unsigned int VBlank, + unsigned int DynamicMetadataTransmittedBytes, + int DynamicMetadataLinesBeforeActiveRequired, int InterlaceEnable, bool ProgressiveToInterlaceUnitInOPP, double *Tsetup, @@ -3265,8 +3265,8 @@ static double CalculateWriteBackDelay( static void CalculateDynamicMetadataParameters(int MaxInterDCNTileRepeaters, double DPPCLK, double DISPCLK, - double DCFClkDeepSleep, double PixelClock, long HTotal, long VBlank, long DynamicMetadataTransmittedBytes, - long DynamicMetadataLinesBeforeActiveRequired, int InterlaceEnable, bool ProgressiveToInterlaceUnitInOPP, + double DCFClkDeepSleep, double PixelClock, unsigned int HTotal, unsigned int VBlank, unsigned int DynamicMetadataTransmittedBytes, + int DynamicMetadataLinesBeforeActiveRequired, int InterlaceEnable, bool ProgressiveToInterlaceUnitInOPP, double *Tsetup, double *Tdmbf, double *Tdmec, double *Tdmsks) { double TotalRepeaterDelayTime = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 6f490d8d7038..56dda686e299 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -626,6 +626,7 @@ static bool dcn32_assign_subvp_pipe(struct dc *dc, * - Not TMZ surface */ if (pipe->plane_state && !pipe->top_pipe && !pipe->prev_odm_pipe && !dcn32_is_center_timing(pipe) && + !pipe->stream->hw_cursor_req && !(pipe->stream->timing.pix_clk_100hz / 10000 > DCN3_2_MAX_SUBVP_PIXEL_RATE_MHZ) && (!dcn32_is_psr_capable(pipe) || (context->stream_count == 1 && dc->caps.dmub_caps.subvp_psr)) && dc_state_get_pipe_subvp_type(context, pipe) == SUBVP_NONE && diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.c b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.c index 412e75eb4704..12ff65b6a7e5 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.c @@ -122,17 +122,6 @@ void print__data_rq_misc_params_st(struct display_mode_lib *mode_lib, const stru dml_print("DML_RQ_DLG_CALC: =====================================\n"); } -void print__rq_dlg_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_rq_dlg_params_st *rq_dlg_param) -{ - dml_print("DML_RQ_DLG_CALC: =====================================\n"); - dml_print("DML_RQ_DLG_CALC: DISPLAY_RQ_DLG_PARAM_ST\n"); - dml_print("DML_RQ_DLG_CALC: <LUMA>\n"); - print__data_rq_dlg_params_st(mode_lib, &rq_dlg_param->rq_l); - dml_print("DML_RQ_DLG_CALC: <CHROMA>\n"); - print__data_rq_dlg_params_st(mode_lib, &rq_dlg_param->rq_c); - dml_print("DML_RQ_DLG_CALC: =====================================\n"); -} - void print__dlg_sys_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_dlg_sys_params_st *dlg_sys_param) { dml_print("DML_RQ_DLG_CALC: =====================================\n"); diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.h b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.h index ebcd717744e5..2bc64c4081dc 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.h @@ -35,7 +35,6 @@ void print__rq_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dp void print__data_rq_sizing_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_data_rq_sizing_params_st *rq_sizing); void print__data_rq_dlg_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_data_rq_dlg_params_st *rq_dlg_param); void print__data_rq_misc_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_data_rq_misc_params_st *rq_misc_param); -void print__rq_dlg_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_rq_dlg_params_st *rq_dlg_param); void print__dlg_sys_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_dlg_sys_params_st *dlg_sys_param); void print__data_rq_regs_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_data_rq_regs_st *rq_regs); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4.c index 3664980d1574..bb863c8c6b39 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4.c @@ -44,7 +44,7 @@ struct dml2_core_ip_params core_dcn4_ip_caps_base = { .dppclk_delay_scl_lb_only = 16, .dppclk_delay_cnvc_formatter = 28, .dppclk_delay_cnvc_cursor = 6, - .cursor_buffer_size = 42, + .cursor_buffer_size = 24, .cursor_chunk_size = 2, .dispclk_delay_subtotal = 125, .max_inter_dcn_tile_repeaters = 8, @@ -141,9 +141,8 @@ bool core_dcn4_initialize(struct dml2_core_initialize_in_out *in_out) core->clean_me_up.mode_lib.ip.subvp_fw_processing_delay_us = core_dcn4_ip_caps_base.subvp_pstate_allow_width_us; core->clean_me_up.mode_lib.ip.subvp_swath_height_margin_lines = core_dcn4_ip_caps_base.subvp_swath_height_margin_lines; } else { - memcpy(&core->clean_me_up.mode_lib.ip, &core_dcn4_ip_caps_base, sizeof(struct dml2_core_ip_params)); + memcpy(&core->clean_me_up.mode_lib.ip, &core_dcn4_ip_caps_base, sizeof(struct dml2_core_ip_params)); patch_ip_params_with_ip_caps(&core->clean_me_up.mode_lib.ip, in_out->ip_caps); - core->clean_me_up.mode_lib.ip.imall_supported = false; } diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c index 78c93a502518..4c33d99ca7e8 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c @@ -5058,7 +5058,7 @@ static void CalculateExtraLatency( double HostVMInefficiencyFactorPrefetch, unsigned int HostVMMinPageSize, enum dml2_qos_param_type qos_type, - bool max_oustanding_when_urgent_expected, + bool max_outstanding_when_urgent_expected, unsigned int max_outstanding_requests, unsigned int request_size_bytes_luma[], unsigned int request_size_bytes_chroma[], @@ -5106,7 +5106,7 @@ static void CalculateExtraLatency( if (qos_type == dml2_qos_param_type_dcn4x) { *ExtraLatency_sr = dchub_arb_to_ret_delay / DCFCLK; *ExtraLatency = *ExtraLatency_sr; - if (max_oustanding_when_urgent_expected) + if (max_outstanding_when_urgent_expected) *ExtraLatency = *ExtraLatency + (ROBBufferSizeInKByte * 1024 - max_outstanding_requests * max_request_size_bytes) / ReturnBW; } else { *ExtraLatency_sr = dchub_arb_to_ret_delay / DCFCLK + RoundTripPingLatencyCycles / FabricClock + ReorderingBytes / ReturnBW; @@ -5121,7 +5121,7 @@ static void CalculateExtraLatency( dml2_printf("DML::%s: qos_type=%u\n", __func__, qos_type); dml2_printf("DML::%s: hostvm_mode=%u\n", __func__, hostvm_mode); dml2_printf("DML::%s: Tex_trips=%u\n", __func__, Tex_trips); - dml2_printf("DML::%s: max_oustanding_when_urgent_expected=%u\n", __func__, max_oustanding_when_urgent_expected); + dml2_printf("DML::%s: max_outstanding_when_urgent_expected=%u\n", __func__, max_outstanding_when_urgent_expected); dml2_printf("DML::%s: FabricClock=%f\n", __func__, FabricClock); dml2_printf("DML::%s: DCFCLK=%f\n", __func__, DCFCLK); dml2_printf("DML::%s: ReturnBW=%f\n", __func__, ReturnBW); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h index dfe54112a9c6..4e502f0a6d20 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h @@ -1571,7 +1571,7 @@ struct dml2_core_calcs_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport_param unsigned int *DSTYAfterScaler; bool UnboundedRequestEnabled; unsigned int CompressedBufferSizeInkByte; - bool max_oustanding_when_urgent_expected; + bool max_outstanding_when_urgent_expected; unsigned int max_outstanding_requests; unsigned int max_request_size_bytes; unsigned int *meta_row_height_l; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c index 1ed21c1b86a5..a966abd40788 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c @@ -532,26 +532,6 @@ static void calculate_odm_slices(const struct dc_stream_state *stream, unsigned odm_slice_end_x[odm_factor - 1] = stream->src.width - 1; } -static bool is_plane_in_odm_slice(const struct dc_plane_state *plane, unsigned int slice_index, unsigned int *odm_slice_end_x, unsigned int num_slices) -{ - unsigned int slice_start_x, slice_end_x; - - if (slice_index == 0) - slice_start_x = 0; - else - slice_start_x = odm_slice_end_x[slice_index - 1] + 1; - - slice_end_x = odm_slice_end_x[slice_index]; - - if (plane->clip_rect.x + plane->clip_rect.width < slice_start_x) - return false; - - if (plane->clip_rect.x > slice_end_x) - return false; - - return true; -} - static void add_odm_slice_to_odm_tree(struct dml2_context *ctx, struct dc_state *state, struct dc_pipe_mapping_scratch *scratch, @@ -791,12 +771,6 @@ static void map_pipes_for_plane(struct dml2_context *ctx, struct dc_state *state sort_pipes_for_splitting(&scratch->pipe_pool); for (odm_slice_index = 0; odm_slice_index < scratch->odm_info.odm_factor; odm_slice_index++) { - // We build the tree for one ODM slice at a time. - // Each ODM slice shares a common OPP - if (!is_plane_in_odm_slice(plane, odm_slice_index, scratch->odm_info.odm_slice_end_x, scratch->odm_info.odm_factor)) { - continue; - } - // Now we have a list of all pipes to be used for this plane/stream, now setup the tree. scratch->odm_info.next_higher_pipe_for_odm_slice[odm_slice_index] = add_plane_to_blend_tree(ctx, state, plane, diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c index f829d5ac7c8e..2061d43b92e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c @@ -557,6 +557,7 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc, } if (dml2->v20.dml_core_ctx.project == dml_project_dcn35 || + dml2->v20.dml_core_ctx.project == dml_project_dcn36 || dml2->v20.dml_core_ctx.project == dml_project_dcn351) { int max_dcfclk_mhz = 0, max_dispclk_mhz = 0, max_dppclk_mhz = 0, max_phyclk_mhz = 0, max_dtbclk_mhz = 0, max_fclk_mhz = 0, max_uclk_mhz = 0, max_socclk_mhz = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c index 45584e2f5dfe..939ee0708bd2 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c @@ -33,7 +33,6 @@ #include "dml2_dc_resource_mgmt.h" #include "dml21_wrapper.h" - static void initialize_dml2_ip_params(struct dml2_context *dml2, const struct dc *in_dc, struct ip_params_st *out) { if (dml2->config.use_native_soc_bb_construction) @@ -792,7 +791,7 @@ bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options // TODO : Temporarily add DCN_VERSION_3_2 for N-1 validation. Remove DCN_VERSION_3_2 after N-1 validation phase is complete. if ((in_dc->debug.using_dml21) && (in_dc->ctx->dce_version == DCN_VERSION_4_01 - )) + )) return dml21_create(in_dc, dml2, config); // Allocate Mode Lib Ctx diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c index 40acebd13e46..abf439e743f2 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c @@ -425,11 +425,6 @@ bool dpp3_get_optimal_number_of_taps( int min_taps_y, min_taps_c; enum lb_memory_config lb_config; - if (scl_data->viewport.width > scl_data->h_active && - dpp->ctx->dc->debug.max_downscale_src_width != 0 && - scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width) - return false; - /* * Set default taps if none are provided * From programming guide: taps = min{ ceil(2*H_RATIO,1), 8} for downscaling @@ -467,6 +462,12 @@ bool dpp3_get_optimal_number_of_taps( else scl_data->taps.h_taps_c = in_taps->h_taps_c; + // Avoid null data in the scl data with this early return, proceed non-adaptive calcualtion first + if (scl_data->viewport.width > scl_data->h_active && + dpp->ctx->dc->debug.max_downscale_src_width != 0 && + scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width) + return false; + /*Ensure we can support the requested number of vtaps*/ min_taps_y = dc_fixpt_ceil(scl_data->ratios.vert); min_taps_c = dc_fixpt_ceil(scl_data->ratios.vert_c); diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp.h b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp.h index 4bc85aaf17da..ecaa976e1f52 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp.h +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp.h @@ -567,80 +567,82 @@ type ISHARP_NLDELTA_SCLIP_PIVOT_N; \ type ISHARP_NLDELTA_SCLIP_SLOPE_N +#define DPP_REG_VARIABLE_LIST_DCN401 \ + DPP_DCN3_REG_VARIABLE_LIST_COMMON; \ + uint32_t CURSOR0_FP_SCALE_BIAS_G_Y; \ + uint32_t CURSOR0_FP_SCALE_BIAS_RB_CRCB; \ + uint32_t CUR0_MATRIX_MODE; \ + uint32_t CUR0_MATRIX_C11_C12_A; \ + uint32_t CUR0_MATRIX_C13_C14_A; \ + uint32_t CUR0_MATRIX_C21_C22_A; \ + uint32_t CUR0_MATRIX_C23_C24_A; \ + uint32_t CUR0_MATRIX_C31_C32_A; \ + uint32_t CUR0_MATRIX_C33_C34_A; \ + uint32_t CUR0_MATRIX_C11_C12_B; \ + uint32_t CUR0_MATRIX_C13_C14_B; \ + uint32_t CUR0_MATRIX_C21_C22_B; \ + uint32_t CUR0_MATRIX_C23_C24_B; \ + uint32_t CUR0_MATRIX_C31_C32_B; \ + uint32_t CUR0_MATRIX_C33_C34_B; \ + uint32_t DSCL_SC_MODE; \ + uint32_t DSCL_EASF_H_MODE; \ + uint32_t DSCL_EASF_H_BF_CNTL; \ + uint32_t DSCL_EASF_H_RINGEST_EVENTAP_REDUCE; \ + uint32_t DSCL_EASF_H_RINGEST_EVENTAP_GAIN; \ + uint32_t DSCL_EASF_H_BF_FINAL_MAX_MIN; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG0; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG1; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG2; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG3; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG4; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG5; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG6; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG7; \ + uint32_t DSCL_EASF_H_BF3_PWL_SEG0; \ + uint32_t DSCL_EASF_H_BF3_PWL_SEG1; \ + uint32_t DSCL_EASF_H_BF3_PWL_SEG2; \ + uint32_t DSCL_EASF_H_BF3_PWL_SEG3; \ + uint32_t DSCL_EASF_H_BF3_PWL_SEG4; \ + uint32_t DSCL_EASF_H_BF3_PWL_SEG5; \ + uint32_t DSCL_EASF_V_MODE; \ + uint32_t DSCL_EASF_V_BF_CNTL; \ + uint32_t DSCL_EASF_V_RINGEST_3TAP_CNTL1; \ + uint32_t DSCL_EASF_V_RINGEST_3TAP_CNTL2; \ + uint32_t DSCL_EASF_V_RINGEST_3TAP_CNTL3; \ + uint32_t DSCL_EASF_V_RINGEST_EVENTAP_REDUCE; \ + uint32_t DSCL_EASF_V_RINGEST_EVENTAP_GAIN; \ + uint32_t DSCL_EASF_V_BF_FINAL_MAX_MIN; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG0; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG1; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG2; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG3; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG4; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG5; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG6; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG7; \ + uint32_t DSCL_EASF_V_BF3_PWL_SEG0; \ + uint32_t DSCL_EASF_V_BF3_PWL_SEG1; \ + uint32_t DSCL_EASF_V_BF3_PWL_SEG2; \ + uint32_t DSCL_EASF_V_BF3_PWL_SEG3; \ + uint32_t DSCL_EASF_V_BF3_PWL_SEG4; \ + uint32_t DSCL_EASF_V_BF3_PWL_SEG5; \ + uint32_t DSCL_SC_MATRIX_C0C1; \ + uint32_t DSCL_SC_MATRIX_C2C3; \ + uint32_t ISHARP_MODE; \ + uint32_t ISHARP_NOISEDET_THRESHOLD; \ + uint32_t ISHARP_NOISE_GAIN_PWL; \ + uint32_t ISHARP_LBA_PWL_SEG0; \ + uint32_t ISHARP_LBA_PWL_SEG1; \ + uint32_t ISHARP_LBA_PWL_SEG2; \ + uint32_t ISHARP_LBA_PWL_SEG3; \ + uint32_t ISHARP_LBA_PWL_SEG4; \ + uint32_t ISHARP_LBA_PWL_SEG5; \ + uint32_t ISHARP_DELTA_CTRL; \ + uint32_t ISHARP_DELTA_DATA; \ + uint32_t ISHARP_DELTA_INDEX; \ + uint32_t ISHARP_NLDELTA_SOFT_CLIP struct dcn401_dpp_registers { - DPP_DCN3_REG_VARIABLE_LIST_COMMON; - uint32_t CURSOR0_FP_SCALE_BIAS_G_Y; - uint32_t CURSOR0_FP_SCALE_BIAS_RB_CRCB; - uint32_t CUR0_MATRIX_MODE; - uint32_t CUR0_MATRIX_C11_C12_A; - uint32_t CUR0_MATRIX_C13_C14_A; - uint32_t CUR0_MATRIX_C21_C22_A; - uint32_t CUR0_MATRIX_C23_C24_A; - uint32_t CUR0_MATRIX_C31_C32_A; - uint32_t CUR0_MATRIX_C33_C34_A; - uint32_t CUR0_MATRIX_C11_C12_B; - uint32_t CUR0_MATRIX_C13_C14_B; - uint32_t CUR0_MATRIX_C21_C22_B; - uint32_t CUR0_MATRIX_C23_C24_B; - uint32_t CUR0_MATRIX_C31_C32_B; - uint32_t CUR0_MATRIX_C33_C34_B; - uint32_t DSCL_SC_MODE; - uint32_t DSCL_EASF_H_MODE; - uint32_t DSCL_EASF_H_BF_CNTL; - uint32_t DSCL_EASF_H_RINGEST_EVENTAP_REDUCE; - uint32_t DSCL_EASF_H_RINGEST_EVENTAP_GAIN; - uint32_t DSCL_EASF_H_BF_FINAL_MAX_MIN; - uint32_t DSCL_EASF_H_BF1_PWL_SEG0; - uint32_t DSCL_EASF_H_BF1_PWL_SEG1; - uint32_t DSCL_EASF_H_BF1_PWL_SEG2; - uint32_t DSCL_EASF_H_BF1_PWL_SEG3; - uint32_t DSCL_EASF_H_BF1_PWL_SEG4; - uint32_t DSCL_EASF_H_BF1_PWL_SEG5; - uint32_t DSCL_EASF_H_BF1_PWL_SEG6; - uint32_t DSCL_EASF_H_BF1_PWL_SEG7; - uint32_t DSCL_EASF_H_BF3_PWL_SEG0; - uint32_t DSCL_EASF_H_BF3_PWL_SEG1; - uint32_t DSCL_EASF_H_BF3_PWL_SEG2; - uint32_t DSCL_EASF_H_BF3_PWL_SEG3; - uint32_t DSCL_EASF_H_BF3_PWL_SEG4; - uint32_t DSCL_EASF_H_BF3_PWL_SEG5; - uint32_t DSCL_EASF_V_MODE; - uint32_t DSCL_EASF_V_BF_CNTL; - uint32_t DSCL_EASF_V_RINGEST_3TAP_CNTL1; - uint32_t DSCL_EASF_V_RINGEST_3TAP_CNTL2; - uint32_t DSCL_EASF_V_RINGEST_3TAP_CNTL3; - uint32_t DSCL_EASF_V_RINGEST_EVENTAP_REDUCE; - uint32_t DSCL_EASF_V_RINGEST_EVENTAP_GAIN; - uint32_t DSCL_EASF_V_BF_FINAL_MAX_MIN; - uint32_t DSCL_EASF_V_BF1_PWL_SEG0; - uint32_t DSCL_EASF_V_BF1_PWL_SEG1; - uint32_t DSCL_EASF_V_BF1_PWL_SEG2; - uint32_t DSCL_EASF_V_BF1_PWL_SEG3; - uint32_t DSCL_EASF_V_BF1_PWL_SEG4; - uint32_t DSCL_EASF_V_BF1_PWL_SEG5; - uint32_t DSCL_EASF_V_BF1_PWL_SEG6; - uint32_t DSCL_EASF_V_BF1_PWL_SEG7; - uint32_t DSCL_EASF_V_BF3_PWL_SEG0; - uint32_t DSCL_EASF_V_BF3_PWL_SEG1; - uint32_t DSCL_EASF_V_BF3_PWL_SEG2; - uint32_t DSCL_EASF_V_BF3_PWL_SEG3; - uint32_t DSCL_EASF_V_BF3_PWL_SEG4; - uint32_t DSCL_EASF_V_BF3_PWL_SEG5; - uint32_t DSCL_SC_MATRIX_C0C1; - uint32_t DSCL_SC_MATRIX_C2C3; - uint32_t ISHARP_MODE; - uint32_t ISHARP_NOISEDET_THRESHOLD; - uint32_t ISHARP_NOISE_GAIN_PWL; - uint32_t ISHARP_LBA_PWL_SEG0; - uint32_t ISHARP_LBA_PWL_SEG1; - uint32_t ISHARP_LBA_PWL_SEG2; - uint32_t ISHARP_LBA_PWL_SEG3; - uint32_t ISHARP_LBA_PWL_SEG4; - uint32_t ISHARP_LBA_PWL_SEG5; - uint32_t ISHARP_DELTA_CTRL; - uint32_t ISHARP_DELTA_DATA; - uint32_t ISHARP_DELTA_INDEX; - uint32_t ISHARP_NLDELTA_SOFT_CLIP; + DPP_REG_VARIABLE_LIST_DCN401; }; struct dcn401_dpp_shift { diff --git a/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.c b/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.c index 03b4ac2f1991..0d2ae21abbdd 100644 --- a/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.c @@ -262,7 +262,7 @@ void dcn31_hpo_dp_link_enc_set_link_test_pattern( } } -static void fill_stream_allocation_row_info( +void dcn31_fill_stream_allocation_row_info( const struct link_mst_stream_allocation *stream_allocation, uint32_t *src, uint32_t *slots) @@ -296,7 +296,7 @@ void dcn31_hpo_dp_link_enc_update_stream_allocation_table( /* we should clean-up table each time */ if (table->stream_count >= 1) { - fill_stream_allocation_row_info( + dcn31_fill_stream_allocation_row_info( &table->stream_allocations[0], &src, &slots); @@ -310,7 +310,7 @@ void dcn31_hpo_dp_link_enc_update_stream_allocation_table( SAT_SLOT_COUNT, slots); if (table->stream_count >= 2) { - fill_stream_allocation_row_info( + dcn31_fill_stream_allocation_row_info( &table->stream_allocations[1], &src, &slots); @@ -324,7 +324,7 @@ void dcn31_hpo_dp_link_enc_update_stream_allocation_table( SAT_SLOT_COUNT, slots); if (table->stream_count >= 3) { - fill_stream_allocation_row_info( + dcn31_fill_stream_allocation_row_info( &table->stream_allocations[2], &src, &slots); @@ -338,7 +338,7 @@ void dcn31_hpo_dp_link_enc_update_stream_allocation_table( SAT_SLOT_COUNT, slots); if (table->stream_count >= 4) { - fill_stream_allocation_row_info( + dcn31_fill_stream_allocation_row_info( &table->stream_allocations[3], &src, &slots); diff --git a/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.h b/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.h index 51f5781325e8..40859660e4dc 100644 --- a/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.h @@ -226,4 +226,10 @@ void dcn31_hpo_dp_link_enc_set_ffe( const struct dc_link_settings *link_settings, uint8_t ffe_preset); + +void dcn31_fill_stream_allocation_row_info( + const struct link_mst_stream_allocation *stream_allocation, + uint32_t *src, + uint32_t *slots); + #endif // __DAL_DCN31_HPO_LINK_ENCODER_H__ diff --git a/drivers/gpu/drm/amd/display/dc/hpo/dcn32/dcn32_hpo_dp_link_encoder.h b/drivers/gpu/drm/amd/display/dc/hpo/dcn32/dcn32_hpo_dp_link_encoder.h index 48ef3d29b370..bea4e1a8ff90 100644 --- a/drivers/gpu/drm/amd/display/dc/hpo/dcn32/dcn32_hpo_dp_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/hpo/dcn32/dcn32_hpo_dp_link_encoder.h @@ -62,4 +62,7 @@ void hpo_dp_link_encoder32_construct(struct dcn31_hpo_dp_link_encoder *enc31, const struct dcn31_hpo_dp_link_encoder_shift *hpo_le_shift, const struct dcn31_hpo_dp_link_encoder_mask *hpo_le_mask); +bool dcn32_hpo_dp_link_enc_is_in_alt_mode( + struct hpo_dp_link_encoder *enc); + #endif // __DAL_DCN32_HPO_DP_LINK_ENCODER_H__ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dce/dce_hwseq.h index 09049aa3c4f3..f66a38f43a09 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce/dce_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce/dce_hwseq.h @@ -1244,6 +1244,7 @@ struct dce_hwseq_registers { type DOMAIN24_PGFSM_PWR_STATUS; \ type DOMAIN25_PGFSM_PWR_STATUS; \ type DOMAIN_DESIRED_PWR_STATE; + struct dce_hwseq_shift { HWSEQ_REG_FIELD_LIST(uint8_t) HWSEQ_DCN_REG_FIELD_LIST(uint8_t) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 8280e3652171..9c9947fc5d44 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1153,9 +1153,12 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx) struct timing_generator *tg = pipe_ctx->stream_res.tg; struct dtbclk_dto_params dto_params = {0}; int dp_hpo_inst; - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; + if (!dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal)) { pipe_ctx->stream_res.stream_enc->funcs->stop_hdmi_info_packets( pipe_ctx->stream_res.stream_enc); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index b158eb1045a1..a5a3e0823e21 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -3020,9 +3020,12 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx) enum phyd32clk_clock_source phyd32clk; int dp_hpo_inst; - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; + if (!dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) { dto_params.otg_inst = tg->inst; dto_params.pixclk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c index f698062f1e90..288e9dd9205d 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c @@ -621,7 +621,8 @@ void dcn31_reset_hw_ctx_wrap( } /* New dc_state in the process of being applied to hardware. */ - link_enc_cfg_set_transient_mode(dc, dc->current_state, context); + if (!dc->config.unify_link_enc_assignment) + link_enc_cfg_set_transient_mode(dc, dc->current_state, context); } void dcn31_setup_hpo_hw_control(const struct dce_hwseq *hws, bool enable) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c index c4a37a95e812..39668d8cc13a 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c @@ -927,9 +927,12 @@ void dcn401_enable_stream(struct pipe_ctx *pipe_ctx) int dp_hpo_inst = 0; unsigned int tmds_div = PIXEL_RATE_DIV_NA; unsigned int unused_div = PIXEL_RATE_DIV_NA; - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; + if (!dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + dcn401_enable_stream_calc(pipe_ctx, &dp_hpo_inst, &phyd32clk, &tmds_div, &early_control); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h index 599fa41fd75f..2b1a2a00648a 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h @@ -517,6 +517,11 @@ void get_cursor_visual_confirm_color( struct pipe_ctx *pipe_ctx, struct tg_color *color); +void get_dcc_visual_confirm_color( + struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct tg_color *color); + void set_p_state_switch_method( struct dc *dc, struct dc_state *context, diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index 042e04f924a2..9458187b834d 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -647,4 +647,9 @@ void resource_init_common_dml2_callbacks(struct dc *dc, struct dml2_configuratio int resource_calculate_det_for_stream(struct dc_state *state, struct pipe_ctx *otg_master); bool resource_is_hpo_acquired(struct dc_state *context); + +struct link_encoder *get_temp_dio_link_enc( + const struct resource_context *res_ctx, + const struct resource_pool *const pool, + const struct dc_link *link); #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_RESOURCE_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c index 06faa461067b..b68bcc9fca0a 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c @@ -48,9 +48,16 @@ void set_dio_throttled_vcp_size(struct pipe_ctx *pipe_ctx, void setup_dio_stream_encoder(struct pipe_ctx *pipe_ctx) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; + if (!pipe_ctx->stream->ctx->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + if (!link_enc) { + ASSERT(link_enc); + return; + } + link_enc->funcs->connect_dig_be_to_fe(link_enc, pipe_ctx->stream_res.stream_enc->id, true); if (dc_is_dp_signal(pipe_ctx->stream->signal)) @@ -71,9 +78,16 @@ void setup_dio_stream_encoder(struct pipe_ctx *pipe_ctx) void reset_dio_stream_encoder(struct pipe_ctx *pipe_ctx) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; + if (!pipe_ctx->stream->ctx->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + if (!link_enc) { + ASSERT(link_enc); + return; + } + if (!stream_enc) return; @@ -142,7 +156,14 @@ void enable_dio_dp_link_output(struct dc_link *link, enum clock_source_id clock_source, const struct dc_link_settings *link_settings) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (!link_enc) { + ASSERT(link_enc); + return; + } if (dc_is_dp_sst_signal(signal)) link_enc->funcs->enable_dp_output( @@ -162,11 +183,16 @@ void disable_dio_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; - if (link_enc != NULL) - link_enc->funcs->disable_output(link_enc, signal); + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (!link_enc) { + ASSERT(link_enc); + return; + } + link_enc->funcs->disable_output(link_enc, signal); link->dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY); } @@ -175,7 +201,14 @@ void set_dio_dp_link_test_pattern(struct dc_link *link, const struct link_resource *link_res, struct encoder_set_dp_phy_pattern_param *tp_params) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (!link_enc) { + ASSERT(link_enc); + return; + } link_enc->funcs->dp_set_phy_pattern(link_enc, tp_params); link->dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_SET_SOURCE_PATTERN); @@ -186,7 +219,14 @@ void set_dio_dp_lane_settings(struct dc_link *link, const struct dc_link_settings *link_settings, const struct dc_lane_settings lane_settings[LANE_COUNT_DP_MAX]) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (!link_enc) { + ASSERT(link_enc); + return; + } link_enc->funcs->dp_set_lane_settings(link_enc, link_settings, lane_settings); } @@ -195,9 +235,15 @@ void update_dio_stream_allocation_table(struct dc_link *link, const struct link_resource *link_res, const struct link_mst_stream_allocation_table *table) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (!link_enc) { + ASSERT(link_enc); + return; + } - ASSERT(link_enc); link_enc->funcs->update_mst_stream_allocation_table(link_enc, table); } @@ -282,7 +328,10 @@ static const struct link_hwss dio_link_hwss = { bool can_use_dio_link_hwss(const struct dc_link *link, const struct link_resource *link_res) { - return link->link_enc != NULL; + if (!link->dc->config.unify_link_enc_assignment) + return link->link_enc != NULL; + else + return link_res->dio_link_enc != NULL; } /** diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.c index a6d1d7641ab4..e1dff4e3f446 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.c @@ -127,7 +127,10 @@ static void set_dio_fixed_vs_pe_retimer_dp_link_test_pattern(struct dc_link *lin const struct link_resource *link_res, struct encoder_set_dp_phy_pattern_param *tp_params) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); if (!set_dio_fixed_vs_pe_retimer_dp_link_test_pattern_override( link, link_res, tp_params, get_dio_link_hwss())) { diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c index 36adf95744fe..81bf3c5e1fdf 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c @@ -35,12 +35,15 @@ static void update_dpia_stream_allocation_table(struct dc_link *link, const struct link_resource *link_res, const struct link_mst_stream_allocation_table *table) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; static enum dc_status status; uint8_t mst_alloc_slots = 0, prev_mst_slots_in_use = 0xFF; int i; DC_LOGGER_INIT(link->ctx->logger); + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + for (i = 0; i < table->stream_count; i++) mst_alloc_slots += table->stream_allocations[i].slot_count; @@ -61,7 +64,10 @@ static void set_dio_dpia_link_test_pattern(struct dc_link *link, if (tp_params->dp_phy_pattern != DP_TEST_PATTERN_VIDEO_MODE) return; - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); if (!link_enc) return; @@ -83,31 +89,28 @@ static void enable_dpia_link_output(struct dc_link *link, enum clock_source_id clock_source, const struct dc_link_settings *link_settings) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + DC_LOGGER_INIT(link->ctx->logger); + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); if (link_enc != NULL) { - if (link->dc->config.enable_dpia_pre_training && link_enc->funcs->enable_dpia_output) { + if (link->dc->config.enable_dpia_pre_training || link->dc->config.unify_link_enc_assignment) { uint8_t fec_rdy = link->dc->link_srv->dp_should_enable_fec(link); uint8_t digmode = dc_is_dp_sst_signal(signal) ? DIG_SST_MODE : DIG_MST_MODE; - link_enc->funcs->enable_dpia_output( - link_enc, - link_settings, - link->ddc_hw_inst, - digmode, - fec_rdy); - } else { - if (dc_is_dp_sst_signal(signal)) - link_enc->funcs->enable_dp_output( + if (link_enc->funcs->enable_dpia_output) + link_enc->funcs->enable_dpia_output( link_enc, link_settings, - clock_source); + link->ddc_hw_inst, + digmode, + fec_rdy); else - link_enc->funcs->enable_dp_mst_output( - link_enc, - link_settings, - clock_source); - } + DC_LOG_ERROR("%s: link encoder does not support enable_dpia_output\n", __func__); + } else + enable_dio_dp_link_output(link, link_res, signal, clock_source, link_settings); } @@ -119,13 +122,20 @@ static void disable_dpia_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + DC_LOGGER_INIT(link->ctx->logger); + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); if (link_enc != NULL) { - if (link->dc->config.enable_dpia_pre_training && link_enc->funcs->disable_dpia_output) { + if (link->dc->config.enable_dpia_pre_training || link->dc->config.unify_link_enc_assignment) { uint8_t digmode = dc_is_dp_sst_signal(signal) ? DIG_SST_MODE : DIG_MST_MODE; - link_enc->funcs->disable_dpia_output(link_enc, link->ddc_hw_inst, digmode); + if (link_enc->funcs->disable_dpia_output) + link_enc->funcs->disable_dpia_output(link_enc, link->ddc_hw_inst, digmode); + else + DC_LOG_ERROR("%s: link encoder does not support disable_dpia_output\n", __func__); } else link_enc->funcs->disable_output(link_enc, signal); } @@ -154,8 +164,10 @@ static const struct link_hwss dpia_link_hwss = { bool can_use_dpia_link_hwss(const struct dc_link *link, const struct link_resource *link_res) { - return link->is_dig_mapping_flexible && - link->dc->res_pool->funcs->link_encs_assign; + if (!link->dc->config.unify_link_enc_assignment) + return link->is_dig_mapping_flexible && link->dc->res_pool->funcs->link_encs_assign; + else + return link->is_dig_mapping_flexible && link_res->dio_link_enc != NULL; } const struct link_hwss *get_dpia_link_hwss(void) diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index 550e1a098fa2..cc9191a5c9e6 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -816,7 +816,10 @@ static bool should_verify_link_capability_destructively(struct dc_link *link, { bool destrictive = false; struct dc_link_settings max_link_cap; - bool is_link_enc_unavailable = link->link_enc && + bool is_link_enc_unavailable = false; + + if (!link->dc->config.unify_link_enc_assignment) + is_link_enc_unavailable = link->link_enc && link->dc->res_pool->funcs->link_encs_assign && !link_enc_cfg_is_link_enc_avail( link->ctx->dc, diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c index ec7de9c01fab..321fd1785370 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c @@ -652,15 +652,15 @@ static void write_i2c_redriver_setting( static void update_psp_stream_config(struct pipe_ctx *pipe_ctx, bool dpms_off) { struct cp_psp *cp_psp = &pipe_ctx->stream->ctx->cp_psp; - struct link_encoder *link_enc = NULL; + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct cp_psp_stream_config config = {0}; enum dp_panel_mode panel_mode = dp_get_panel_mode(pipe_ctx->stream->link); if (cp_psp == NULL || cp_psp->funcs.update_stream_config == NULL) return; - - link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + if (!pipe_ctx->stream->ctx->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); ASSERT(link_enc); if (link_enc == NULL) return; @@ -1924,7 +1924,7 @@ static void disable_link_dp(struct dc_link *link, if (link_dp_get_encoding_format(&link_settings) == DP_8b_10b_ENCODING) { - dp_set_fec_enable(link, false); + dp_set_fec_enable(link, link_res, false); dp_set_fec_ready(link, link_res, false); } } @@ -2122,7 +2122,7 @@ static enum dc_status enable_link_dp(struct dc_state *state, fec_enable = true; if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) - dp_set_fec_enable(link, fec_enable); + dp_set_fec_enable(link, &pipe_ctx->link_res, fec_enable); // during mode set we do DP_SET_POWER off then on, aux writes are lost if (link->dpcd_sink_ext_caps.bits.oled == 1 || @@ -2461,7 +2461,7 @@ void link_set_dpms_on( struct dc_stream_state *stream = pipe_ctx->stream; struct dc_link *link = stream->sink->link; enum dc_status status; - struct link_encoder *link_enc; + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; enum otg_out_mux_dest otg_out_dest = OUT_MUX_DIO; struct vpg *vpg = pipe_ctx->stream_res.stream_enc->vpg; const struct link_hwss *link_hwss = get_link_hwss(link, &pipe_ctx->link_res); @@ -2486,7 +2486,8 @@ void link_set_dpms_on( } } - link_enc = link_enc_cfg_get_link_enc(link); + if (!dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); ASSERT(link_enc); if (!dc_is_virtual_signal(pipe_ctx->stream->signal) diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index e3e7fcb07f19..a77410122636 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -250,21 +250,21 @@ static uint32_t intersect_frl_link_bw_support( { uint32_t supported_bw_in_kbps = max_supported_frl_bw_in_kbps; - // HDMI_ENCODED_LINK_BW bits are only valid if HDMI Link Configuration bit is 1 (FRL mode) - if (hdmi_encoded_link_bw.bits.FRL_MODE) { - if (hdmi_encoded_link_bw.bits.BW_48Gbps) - supported_bw_in_kbps = 48000000; - else if (hdmi_encoded_link_bw.bits.BW_40Gbps) - supported_bw_in_kbps = 40000000; - else if (hdmi_encoded_link_bw.bits.BW_32Gbps) - supported_bw_in_kbps = 32000000; - else if (hdmi_encoded_link_bw.bits.BW_24Gbps) - supported_bw_in_kbps = 24000000; - else if (hdmi_encoded_link_bw.bits.BW_18Gbps) - supported_bw_in_kbps = 18000000; - else if (hdmi_encoded_link_bw.bits.BW_9Gbps) - supported_bw_in_kbps = 9000000; - } + /* Skip checking FRL_MODE bit, as certain PCON will clear + * it despite supporting the link BW indicated in the other bits. + */ + if (hdmi_encoded_link_bw.bits.BW_48Gbps) + supported_bw_in_kbps = 48000000; + else if (hdmi_encoded_link_bw.bits.BW_40Gbps) + supported_bw_in_kbps = 40000000; + else if (hdmi_encoded_link_bw.bits.BW_32Gbps) + supported_bw_in_kbps = 32000000; + else if (hdmi_encoded_link_bw.bits.BW_24Gbps) + supported_bw_in_kbps = 24000000; + else if (hdmi_encoded_link_bw.bits.BW_18Gbps) + supported_bw_in_kbps = 18000000; + else if (hdmi_encoded_link_bw.bits.BW_9Gbps) + supported_bw_in_kbps = 9000000; return supported_bw_in_kbps; } @@ -330,9 +330,12 @@ bool dp_is_fec_supported(const struct dc_link *link) /* TODO - use asic cap instead of link_enc->features * we no longer know which link enc to use for this link before commit */ - struct link_encoder *link_enc = NULL; + struct resource_context *res_ctx = &link->dc->current_state->res_ctx; + struct resource_pool *res_pool = link->dc->res_pool; + struct link_encoder *link_enc = get_temp_dio_link_enc(res_ctx, res_pool, link); - link_enc = link_enc_cfg_get_link_enc(link); + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); ASSERT(link_enc); return (dc_is_dp_signal(link->connector_signal) && link_enc && @@ -1572,10 +1575,18 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link) /* Attempt to train in LTTPR transparent mode if repeater count exceeds 8. */ is_lttpr_present = dp_is_lttpr_present(link); - if (is_lttpr_present) + DC_LOG_DC("is_lttpr_present = %d\n", is_lttpr_present); + + if (is_lttpr_present) { CONN_DATA_DETECT(link, lttpr_dpcd_data, sizeof(lttpr_dpcd_data), "LTTPR Caps: "); - DC_LOG_DC("is_lttpr_present = %d\n", is_lttpr_present); + core_link_read_dpcd(link, DP_LTTPR_IEEE_OUI, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui)); + CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui), "LTTPR IEEE OUI: "); + + core_link_read_dpcd(link, DP_LTTPR_DEVICE_ID, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id)); + CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id), "LTTPR Device ID: "); + } + return status; } @@ -2089,18 +2100,32 @@ void detect_edp_sink_caps(struct dc_link *link) core_link_read_dpcd(link, DP_SINK_EMISSION_RATE, (uint8_t *)&link->dpcd_caps.edp_oled_emission_rate, sizeof(link->dpcd_caps.edp_oled_emission_rate)); + + /* + * Read Multi-SST (Single Stream Transport) capability + * for eDP version 1.4 or higher. + */ + if (link->dpcd_caps.dpcd_rev.raw >= DP_EDP_14) + core_link_read_dpcd( + link, + DP_EDP_MSO_LINK_CAPABILITIES, + (uint8_t *)&link->dpcd_caps.mso_cap_sst_links_supported, + sizeof(link->dpcd_caps.mso_cap_sst_links_supported)); } bool dp_get_max_link_enc_cap(const struct dc_link *link, struct dc_link_settings *max_link_enc_cap) { - struct link_encoder *link_enc = NULL; + struct resource_context *res_ctx = &link->dc->current_state->res_ctx; + struct resource_pool *res_pool = link->dc->res_pool; + struct link_encoder *link_enc = get_temp_dio_link_enc(res_ctx, res_pool, link); if (!max_link_enc_cap) { DC_LOG_ERROR("%s: Could not return max link encoder caps", __func__); return false; } - link_enc = link_enc_cfg_get_link_enc(link); + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); ASSERT(link_enc); if (link_enc && link_enc->funcs->get_max_link_cap) { @@ -2128,10 +2153,13 @@ struct dc_link_settings dp_get_max_link_cap(struct dc_link *link) struct dc_link_settings max_link_cap = {0}; enum dc_link_rate lttpr_max_link_rate; enum dc_link_rate cable_max_link_rate; - struct link_encoder *link_enc = NULL; + struct resource_context *res_ctx = &link->dc->current_state->res_ctx; + struct resource_pool *res_pool = link->dc->res_pool; + struct link_encoder *link_enc = get_temp_dio_link_enc(res_ctx, res_pool, link); bool is_uhbr13_5_supported = true; - link_enc = link_enc_cfg_get_link_enc(link); + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); ASSERT(link_enc); /* get max link encoder capability */ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h index 8f0ce97f2362..0ce0af3ddbeb 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h @@ -67,6 +67,7 @@ bool dp_is_128b_132b_signal(struct pipe_ctx *pipe_ctx); /* Initialize output parameter lt_settings. */ void dp_decide_training_settings( struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_setting, struct link_training_settings *lt_settings); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c index 0f1c411523a2..a5541b8fc95b 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c @@ -356,6 +356,32 @@ out: return ret; } +/* + * Handle DP BW allocation status register + * + * @link: pointer to the dc_link struct instance + * @status: content of DP tunneling status DPCD register + * + * return: none + */ +void link_dp_dpia_handle_bw_alloc_status(struct dc_link *link, uint8_t status) +{ + if (status & DP_TUNNELING_BW_REQUEST_SUCCEEDED) { + DC_LOG_DEBUG("%s: BW Allocation request succeeded on link(%d)", + __func__, link->link_index); + } else if (status & DP_TUNNELING_BW_REQUEST_FAILED) { + DC_LOG_DEBUG("%s: BW Allocation request failed on link(%d) allocated/estimated BW=%d", + __func__, link->link_index, link->dpia_bw_alloc_config.estimated_bw); + } else if (status & DP_TUNNELING_ESTIMATED_BW_CHANGED) { + DC_LOG_DEBUG("%s: Estimated BW changed on link(%d) new estimated BW=%d", + __func__, link->link_index, link->dpia_bw_alloc_config.estimated_bw); + } + + core_link_write_dpcd( + link, DP_TUNNELING_STATUS, + &status, sizeof(status)); +} + void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t result) { int bw_needed = 0; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h index 3b6d8494f9d5..1b240a2f6ce0 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h @@ -108,4 +108,14 @@ bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed, const unsigned */ int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link); +/* + * Handle DP BW allocation status register + * + * @link: pointer to the dc_link struct instance + * @status: content of DP tunneling status register + * + * return: none + */ +void link_dp_dpia_handle_bw_alloc_status(struct dc_link *link, uint8_t status); + #endif /* DC_INC_LINK_DP_DPIA_BW_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c index a08403c022ea..5be00e4ce10b 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c @@ -37,6 +37,7 @@ #include "link/accessories/link_dp_trace.h" #include "link/link_dpms.h" #include "dm_helpers.h" +#include "link_dp_dpia_bw.h" #define DC_LOGGER \ link->ctx->logger @@ -286,6 +287,30 @@ void dp_handle_link_loss(struct dc_link *link) } } +static void dp_handle_tunneling_irq(struct dc_link *link) +{ + enum dc_status retval; + uint8_t tunneling_status = 0; + + retval = core_link_read_dpcd( + link, DP_TUNNELING_STATUS, + &tunneling_status, + sizeof(tunneling_status)); + + if (retval == DC_OK) { + DC_LOG_HW_HPD_IRQ("%s: Got DP tunneling status on link %d status=0x%x", + __func__, link->link_index, tunneling_status); + + if (tunneling_status & DP_TUNNELING_BW_ALLOC_BITS_MASK) + link_dp_dpia_handle_bw_alloc_status(link, tunneling_status); + } + + tunneling_status = DP_TUNNELING_IRQ; + core_link_write_dpcd( + link, DP_LINK_SERVICE_IRQ_VECTOR_ESI0, + &tunneling_status, 1); +} + static void read_dpcd204h_on_irq_hpd(struct dc_link *link, union hpd_irq_data *irq_data) { enum dc_status retval; @@ -319,13 +344,19 @@ enum dc_status dp_read_hpd_rx_irq_data( * * For DP 1.4 we need to read those from 2002h range. */ - if (link->dpcd_caps.dpcd_rev.raw < DPCD_REV_14) + if (link->dpcd_caps.dpcd_rev.raw < DPCD_REV_14) { retval = core_link_read_dpcd( link, DP_SINK_COUNT, irq_data->raw, - sizeof(union hpd_irq_data)); - else { + DP_SINK_STATUS - DP_SINK_COUNT + 1); + + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + retval = core_link_read_dpcd( + link, DP_LINK_SERVICE_IRQ_VECTOR_ESI0, + &irq_data->bytes.link_service_irq_esi0.raw, 1); + } + } else { /* Read 14 bytes in a single read and then copy only the required fields. * This is more efficient than doing it in two separate AUX reads. */ @@ -346,6 +377,7 @@ enum dc_status dp_read_hpd_rx_irq_data( irq_data->bytes.lane23_status.raw = tmp[DP_LANE2_3_STATUS_ESI - DP_SINK_COUNT_ESI]; irq_data->bytes.lane_status_updated.raw = tmp[DP_LANE_ALIGN_STATUS_UPDATED_ESI - DP_SINK_COUNT_ESI]; irq_data->bytes.sink_status.raw = tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI]; + irq_data->bytes.link_service_irq_esi0.raw = tmp[DP_LINK_SERVICE_IRQ_VECTOR_ESI0 - DP_SINK_COUNT_ESI]; /* * This display doesn't have correct values in DPCD200Eh. @@ -488,6 +520,11 @@ bool dp_handle_hpd_rx_irq(struct dc_link *link, dp_trace_link_loss_increment(link); } + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + if (hpd_irq_dpcd_data.bytes.link_service_irq_esi0.bits.DP_LINK_TUNNELING_IRQ) + dp_handle_tunneling_irq(link); + } + if (link->type == dc_connection_sst_branch && hpd_irq_dpcd_data.bytes.sink_cnt.bits.SINK_COUNT != link->dpcd_sink_count) diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c index c27ffec5d84f..49521ac4b0e8 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c @@ -142,11 +142,12 @@ enum dc_status dp_set_fec_ready(struct dc_link *link, const struct link_resource * if the sink supports it and leave it enabled on link. * If FEC is not supported, disable it. */ - struct link_encoder *link_enc = NULL; + struct link_encoder *link_enc = link_res->dio_link_enc; enum dc_status status = DC_OK; uint8_t fec_config = 0; - link_enc = link_enc_cfg_get_link_enc(link); + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); ASSERT(link_enc); if (link_enc->funcs->fec_set_ready == NULL) return DC_NOT_SUPPORTED; @@ -176,13 +177,14 @@ enum dc_status dp_set_fec_ready(struct dc_link *link, const struct link_resource return status; } -void dp_set_fec_enable(struct dc_link *link, bool enable) +void dp_set_fec_enable(struct dc_link *link, const struct link_resource *link_res, bool enable) { - struct link_encoder *link_enc = NULL; + struct link_encoder *link_enc = link_res->dio_link_enc; - link_enc = link_enc_cfg_get_link_enc(link); - ASSERT(link_enc); - if (link_enc->funcs->fec_set_enable == NULL) + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + + if (link_enc == NULL || link_enc->funcs == NULL || link_enc->funcs->fec_set_enable == NULL) return; if (enable && dp_should_enable_fec(link)) { diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.h index 1eb0619d6710..ab1c1f8f1f8b 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.h @@ -52,7 +52,8 @@ void dp_set_drive_settings( enum dc_status dp_set_fec_ready(struct dc_link *link, const struct link_resource *link_res, bool ready); -void dp_set_fec_enable(struct dc_link *link, bool enable); +void dp_set_fec_enable(struct dc_link *link, + const struct link_resource *link_res, bool enable); void dpcd_write_rx_power_ctrl(struct dc_link *link, bool on); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c index 751c18e592ea..613298d21d03 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c @@ -801,19 +801,23 @@ enum dc_dp_training_pattern decide_cr_training_pattern( } enum dc_dp_training_pattern decide_eq_training_pattern(struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_settings) { - struct link_encoder *link_enc; + struct link_encoder *link_enc = link_res->dio_link_enc; struct encoder_feature_support *enc_caps; struct dpcd_caps *rx_caps = &link->dpcd_caps; enum dc_dp_training_pattern pattern = DP_TRAINING_PATTERN_SEQUENCE_2; - link_enc = link_enc_cfg_get_link_enc(link); - ASSERT(link_enc); - enc_caps = &link_enc->features; - switch (link_dp_get_encoding_format(link_settings)) { case DP_8b_10b_ENCODING: + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + + if (!link_enc) + break; + + enc_caps = &link_enc->features; if (enc_caps->flags.bits.IS_TPS4_CAPABLE && rx_caps->max_down_spread.bits.TPS4_SUPPORTED) pattern = DP_TRAINING_PATTERN_SEQUENCE_4; @@ -886,13 +890,14 @@ void dp_decide_lane_settings( void dp_decide_training_settings( struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_settings, struct link_training_settings *lt_settings) { if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) - decide_8b_10b_training_settings(link, link_settings, lt_settings); + decide_8b_10b_training_settings(link, link_res, link_settings, lt_settings); else if (link_dp_get_encoding_format(link_settings) == DP_128b_132b_ENCODING) - decide_128b_132b_training_settings(link, link_settings, lt_settings); + decide_128b_132b_training_settings(link, link_res, link_settings, lt_settings); } @@ -1556,6 +1561,7 @@ enum link_training_result dp_perform_link_training( /* decide training settings */ dp_decide_training_settings( link, + link_res, link_settings, <_settings); @@ -1569,7 +1575,8 @@ enum link_training_result dp_perform_link_training( /* configure link prior to entering training mode */ dpcd_configure_lttpr_mode(link, <_settings); - dp_set_fec_ready(link, link_res, lt_settings.should_set_fec_ready); + if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) + dp_set_fec_ready(link, link_res, lt_settings.should_set_fec_ready); dpcd_configure_channel_coding(link, <_settings); /* enter training mode: diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h index 0b18aa35c33c..574b083e0936 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h @@ -104,6 +104,7 @@ void start_clock_recovery_pattern_early(struct dc_link *link, void dp_decide_training_settings( struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_settings, struct link_training_settings *lt_settings); @@ -117,6 +118,7 @@ enum dc_dp_training_pattern decide_cr_training_pattern( const struct dc_link_settings *link_settings); enum dc_dp_training_pattern decide_eq_training_pattern(struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_settings); enum lttpr_mode dp_decide_lttpr_mode(struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.c index db87cfe37b5c..11565f187ac7 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.c @@ -204,6 +204,7 @@ enum link_training_result dp_perform_128b_132b_link_training( struct link_training_settings legacy_settings; decide_8b_10b_training_settings(link, + link_res, <_settings->link_settings, &legacy_settings); return dp_perform_8b_10b_link_training(link, link_res, &legacy_settings); @@ -227,6 +228,7 @@ enum link_training_result dp_perform_128b_132b_link_training( } void decide_128b_132b_training_settings(struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_settings, struct link_training_settings *lt_settings) { @@ -238,7 +240,7 @@ void decide_128b_132b_training_settings(struct dc_link *link, LINK_SPREAD_05_DOWNSPREAD_30KHZ; lt_settings->pattern_for_cr = decide_cr_training_pattern(link_settings); - lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_settings); + lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_res, link_settings); lt_settings->eq_pattern_time = 2500; lt_settings->eq_wait_time_limit = 400000; lt_settings->eq_loop_count_limit = 20; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.h index 2147f24efc8b..901a42edafa1 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.h @@ -34,6 +34,7 @@ enum link_training_result dp_perform_128b_132b_link_training( struct link_training_settings *lt_settings); void decide_128b_132b_training_settings(struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_settings, struct link_training_settings *lt_settings); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c index ae95ec48e572..34d2e097ca2e 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c @@ -93,7 +93,8 @@ static uint32_t get_eq_training_aux_rd_interval( } void decide_8b_10b_training_settings( - struct dc_link *link, + struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_setting, struct link_training_settings *lt_settings) { @@ -115,7 +116,7 @@ void decide_8b_10b_training_settings( LINK_SPREAD_DISABLED : LINK_SPREAD_05_DOWNSPREAD_30KHZ; lt_settings->eq_pattern_time = get_eq_training_aux_rd_interval(link, link_setting); lt_settings->pattern_for_cr = decide_cr_training_pattern(link_setting); - lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_setting); + lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_res, link_setting); lt_settings->enhanced_framing = 1; lt_settings->should_set_fec_ready = true; lt_settings->disallow_per_lane_settings = true; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.h index d26de15ce954..ea0de701d83f 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.h @@ -54,7 +54,8 @@ enum link_training_result perform_8b_10b_channel_equalization_sequence( enum lttpr_mode dp_decide_8b_10b_lttpr_mode(struct dc_link *link); void decide_8b_10b_training_settings( - struct dc_link *link, + struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_setting, struct link_training_settings *lt_settings); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_auxless.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_auxless.c index 4c6b886a9da8..f99d26290bc0 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_auxless.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_auxless.c @@ -39,6 +39,7 @@ bool dp_perform_link_training_skip_aux( dp_decide_training_settings( link, + link_res, link_setting, <_settings); override_training_settings( diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c index 39e4b7dc9588..603537ffd128 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c @@ -110,6 +110,7 @@ static enum link_training_result dpia_configure_link( dp_decide_training_settings( link, + link_res, link_setting, lt_settings); @@ -129,11 +130,14 @@ static enum link_training_result dpia_configure_link( if (status != DC_OK && link->is_hpd_pending) return LINK_TRAINING_ABORT; - if (link->preferred_training_settings.fec_enable != NULL) - fec_enable = *link->preferred_training_settings.fec_enable; - else - fec_enable = true; - status = dp_set_fec_ready(link, link_res, fec_enable); + if (link_dp_get_encoding_format(link_setting) == DP_8b_10b_ENCODING) { + if (link->preferred_training_settings.fec_enable != NULL) + fec_enable = *link->preferred_training_settings.fec_enable; + else + fec_enable = true; + status = dp_set_fec_ready(link, link_res, fec_enable); + } + if (status != DC_OK && link->is_hpd_pending) return LINK_TRAINING_ABORT; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c index ccf8096dde29..ce174ce5579c 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c @@ -270,7 +270,8 @@ enum link_training_result dp_perform_fixed_vs_pe_training_sequence( rate = get_dpcd_link_rate(<_settings->link_settings); - if (!link->dpcd_caps.lttpr_caps.main_link_channel_coding.bits.DP_128b_132b_SUPPORTED) { + // Only perform toggle if FIXED_VS LTTPR reports no IEEE OUI + if (memcmp("\x0,\x0,\x0", &link->dpcd_caps.lttpr_caps.lttpr_ieee_oui[0], 3) == 0) { /* Vendor specific: Toggle link rate */ toggle_rate = (rate == 0x6) ? 0xA : 0x6; diff --git a/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h b/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h index 9267cdf88e9a..ce6fbcf14d7a 100644 --- a/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h +++ b/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h @@ -63,8 +63,7 @@ uint32_t MPC_MCM_SECOND_GAMUT_REMAP_C31_C32_B[MAX_MPCC]; \ uint32_t MPC_MCM_SECOND_GAMUT_REMAP_C33_C34_B[MAX_MPCC]; \ uint32_t MPCC_MCM_3DLUT_FAST_LOAD_SELECT[MAX_MPCC]; \ - uint32_t MPCC_MCM_3DLUT_FAST_LOAD_STATUS[MAX_MPCC]; \ - uint32_t MPCC_CONTROL2[MAX_MPCC] + uint32_t MPCC_MCM_3DLUT_FAST_LOAD_STATUS[MAX_MPCC]; #define MPC_COMMON_MASK_SH_LIST_DCN4_01(mask_sh) \ MPC_COMMON_MASK_SH_LIST_DCN32(mask_sh), \ @@ -184,7 +183,7 @@ struct dcn401_mpc_mask { }; struct dcn401_mpc_registers { - MPC_REG_VARIABLE_LIST_DCN4_01; + MPC_REG_VARIABLE_LIST_DCN4_01 }; struct dcn401_mpc { @@ -236,7 +235,29 @@ void mpc401_get_gamut_remap( struct mpc *mpc, int mpcc_id, struct mpc_grph_gamut_adjustment *adjust); -void mpc401_update_3dlut_fast_load_select(struct mpc *mpc, int mpcc_id, int hubp_idx); -void mpc401_get_3dlut_fast_load_status(struct mpc *mpc, int mpcc_id, uint32_t *done, uint32_t *soft_underflow, uint32_t *hard_underflow); + +void mpc401_update_3dlut_fast_load_select( + struct mpc *mpc, + int mpcc_id, + int hubp_idx); + +void mpc401_get_3dlut_fast_load_status( + struct mpc *mpc, + int mpcc_id, + uint32_t *done, + uint32_t *soft_underflow, + uint32_t *hard_underflow); + +void mpc401_update_3dlut_fast_load_select( + struct mpc *mpc, + int mpcc_id, + int hubp_idx); + +void mpc401_get_3dlut_fast_load_status( + struct mpc *mpc, + int mpcc_id, + uint32_t *done, + uint32_t *soft_underflow, + uint32_t *hard_underflow); #endif diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h index a6d4dbe82c13..8b2a8455eb56 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h @@ -104,120 +104,115 @@ SRI(OTG_MANUAL_FLOW_CONTROL, OTG, inst) +#define OPTC_REG_VARIABLE_LIST_DCN \ + uint32_t OTG_GLOBAL_CONTROL1; \ + uint32_t OTG_GLOBAL_CONTROL2; \ + uint32_t OTG_VERT_SYNC_CONTROL; \ + uint32_t OTG_MASTER_UPDATE_MODE; \ + uint32_t OTG_GSL_CONTROL; \ + uint32_t OTG_VSTARTUP_PARAM; \ + uint32_t OTG_VUPDATE_PARAM; \ + uint32_t OTG_VREADY_PARAM; \ + uint32_t OTG_BLANK_CONTROL; \ + uint32_t OTG_MASTER_UPDATE_LOCK; \ + uint32_t OTG_GLOBAL_CONTROL0; \ + uint32_t OTG_DOUBLE_BUFFER_CONTROL; \ + uint32_t OTG_H_TOTAL; \ + uint32_t OTG_H_BLANK_START_END; \ + uint32_t OTG_H_SYNC_A; \ + uint32_t OTG_H_SYNC_A_CNTL; \ + uint32_t OTG_H_TIMING_CNTL; \ + uint32_t OTG_V_TOTAL; \ + uint32_t OTG_V_BLANK_START_END; \ + uint32_t OTG_V_SYNC_A; \ + uint32_t OTG_V_SYNC_A_CNTL; \ + uint32_t OTG_INTERLACE_CONTROL; \ + uint32_t OTG_CONTROL; \ + uint32_t OTG_STEREO_CONTROL; \ + uint32_t OTG_3D_STRUCTURE_CONTROL; \ + uint32_t OTG_STEREO_STATUS; \ + uint32_t OTG_V_TOTAL_MAX; \ + uint32_t OTG_V_TOTAL_MID; \ + uint32_t OTG_V_TOTAL_MIN; \ + uint32_t OTG_V_TOTAL_CONTROL; \ + uint32_t OTG_V_COUNT_STOP_CONTROL; \ + uint32_t OTG_V_COUNT_STOP_CONTROL2; \ + uint32_t OTG_TRIGA_CNTL; \ + uint32_t OTG_TRIGA_MANUAL_TRIG; \ + uint32_t OTG_MANUAL_FLOW_CONTROL; \ + uint32_t OTG_FORCE_COUNT_NOW_CNTL; \ + uint32_t OTG_STATIC_SCREEN_CONTROL; \ + uint32_t OTG_STATUS_FRAME_COUNT; \ + uint32_t OTG_STATUS; \ + uint32_t OTG_STATUS_POSITION; \ + uint32_t OTG_NOM_VERT_POSITION; \ + uint32_t OTG_BLACK_COLOR; \ + uint32_t OTG_TEST_PATTERN_PARAMETERS; \ + uint32_t OTG_TEST_PATTERN_CONTROL; \ + uint32_t OTG_TEST_PATTERN_COLOR; \ + uint32_t OTG_CLOCK_CONTROL; \ + uint32_t OTG_VERTICAL_INTERRUPT0_CONTROL; \ + uint32_t OTG_VERTICAL_INTERRUPT0_POSITION; \ + uint32_t OTG_VERTICAL_INTERRUPT1_CONTROL; \ + uint32_t OTG_VERTICAL_INTERRUPT1_POSITION; \ + uint32_t OTG_VERTICAL_INTERRUPT2_CONTROL; \ + uint32_t OTG_VERTICAL_INTERRUPT2_POSITION; \ + uint32_t OPTC_INPUT_CLOCK_CONTROL; \ + uint32_t OPTC_DATA_SOURCE_SELECT; \ + uint32_t OPTC_MEMORY_CONFIG; \ + uint32_t OPTC_INPUT_GLOBAL_CONTROL; \ + uint32_t CONTROL; \ + uint32_t OTG_GSL_WINDOW_X; \ + uint32_t OTG_GSL_WINDOW_Y; \ + uint32_t OTG_VUPDATE_KEEPOUT; \ + uint32_t OTG_CRC_CNTL; \ + uint32_t OTG_CRC_CNTL2; \ + uint32_t OTG_CRC0_DATA_RG; \ + uint32_t OTG_CRC0_DATA_B; \ + uint32_t OTG_CRC1_DATA_B; \ + uint32_t OTG_CRC2_DATA_B; \ + uint32_t OTG_CRC3_DATA_B; \ + uint32_t OTG_CRC1_DATA_RG; \ + uint32_t OTG_CRC2_DATA_RG; \ + uint32_t OTG_CRC3_DATA_RG; \ + uint32_t OTG_CRC0_WINDOWA_X_CONTROL; \ + uint32_t OTG_CRC0_WINDOWA_Y_CONTROL; \ + uint32_t OTG_CRC0_WINDOWB_X_CONTROL; \ + uint32_t OTG_CRC0_WINDOWB_Y_CONTROL; \ + uint32_t OTG_CRC1_WINDOWA_X_CONTROL; \ + uint32_t OTG_CRC1_WINDOWA_Y_CONTROL; \ + uint32_t OTG_CRC1_WINDOWB_X_CONTROL; \ + uint32_t OTG_CRC1_WINDOWB_Y_CONTROL; \ + uint32_t GSL_SOURCE_SELECT; \ + uint32_t DWB_SOURCE_SELECT; \ + uint32_t OTG_DSC_START_POSITION; \ + uint32_t OPTC_DATA_FORMAT_CONTROL; \ + uint32_t OPTC_BYTES_PER_PIXEL; \ + uint32_t OPTC_WIDTH_CONTROL; \ + uint32_t OTG_DRR_CONTROL; \ + uint32_t OTG_BLANK_DATA_COLOR; \ + uint32_t OTG_BLANK_DATA_COLOR_EXT; \ + uint32_t OTG_DRR_TRIGGER_WINDOW; \ + uint32_t OTG_M_CONST_DTO0; \ + uint32_t OTG_M_CONST_DTO1; \ + uint32_t OTG_DRR_V_TOTAL_CHANGE; \ + uint32_t OTG_GLOBAL_CONTROL4; \ + uint32_t OTG_CRC0_WINDOWA_X_CONTROL_READBACK; \ + uint32_t OTG_CRC0_WINDOWA_Y_CONTROL_READBACK; \ + uint32_t OTG_CRC0_WINDOWB_X_CONTROL_READBACK; \ + uint32_t OTG_CRC0_WINDOWB_Y_CONTROL_READBACK; \ + uint32_t OTG_CRC1_WINDOWA_X_CONTROL_READBACK; \ + uint32_t OTG_CRC1_WINDOWA_Y_CONTROL_READBACK; \ + uint32_t OTG_CRC1_WINDOWB_X_CONTROL_READBACK; \ + uint32_t OTG_CRC1_WINDOWB_Y_CONTROL_READBACK; \ + uint32_t OPTC_CLOCK_CONTROL; \ + uint32_t OPTC_WIDTH_CONTROL2; \ + uint32_t OTG_PSTATE_REGISTER; \ + uint32_t OTG_PIPE_UPDATE_STATUS; \ + uint32_t INTERRUPT_DEST + struct dcn_optc_registers { - uint32_t OTG_GLOBAL_CONTROL1; - uint32_t OTG_GLOBAL_CONTROL2; - uint32_t OTG_VERT_SYNC_CONTROL; - uint32_t OTG_MASTER_UPDATE_MODE; - uint32_t OTG_GSL_CONTROL; - uint32_t OTG_VSTARTUP_PARAM; - uint32_t OTG_VUPDATE_PARAM; - uint32_t OTG_VREADY_PARAM; - uint32_t OTG_BLANK_CONTROL; - uint32_t OTG_MASTER_UPDATE_LOCK; - uint32_t OTG_GLOBAL_CONTROL0; - uint32_t OTG_DOUBLE_BUFFER_CONTROL; - uint32_t OTG_H_TOTAL; - uint32_t OTG_H_BLANK_START_END; - uint32_t OTG_H_SYNC_A; - uint32_t OTG_H_SYNC_A_CNTL; - uint32_t OTG_H_TIMING_CNTL; - uint32_t OTG_V_TOTAL; - uint32_t OTG_V_BLANK_START_END; - uint32_t OTG_V_SYNC_A; - uint32_t OTG_V_SYNC_A_CNTL; - uint32_t OTG_INTERLACE_CONTROL; - uint32_t OTG_CONTROL; - uint32_t OTG_STEREO_CONTROL; - uint32_t OTG_3D_STRUCTURE_CONTROL; - uint32_t OTG_STEREO_STATUS; - uint32_t OTG_V_TOTAL_MAX; - uint32_t OTG_V_TOTAL_MID; - uint32_t OTG_V_TOTAL_MIN; - uint32_t OTG_V_TOTAL_CONTROL; - uint32_t OTG_V_COUNT_STOP_CONTROL; - uint32_t OTG_V_COUNT_STOP_CONTROL2; - uint32_t OTG_TRIGA_CNTL; - uint32_t OTG_TRIGA_MANUAL_TRIG; - uint32_t OTG_MANUAL_FLOW_CONTROL; - uint32_t OTG_FORCE_COUNT_NOW_CNTL; - uint32_t OTG_STATIC_SCREEN_CONTROL; - uint32_t OTG_STATUS_FRAME_COUNT; - uint32_t OTG_STATUS; - uint32_t OTG_STATUS_POSITION; - uint32_t OTG_NOM_VERT_POSITION; - uint32_t OTG_BLACK_COLOR; - uint32_t OTG_TEST_PATTERN_PARAMETERS; - uint32_t OTG_TEST_PATTERN_CONTROL; - uint32_t OTG_TEST_PATTERN_COLOR; - uint32_t OTG_CLOCK_CONTROL; - uint32_t OTG_VERTICAL_INTERRUPT0_CONTROL; - uint32_t OTG_VERTICAL_INTERRUPT0_POSITION; - uint32_t OTG_VERTICAL_INTERRUPT1_CONTROL; - uint32_t OTG_VERTICAL_INTERRUPT1_POSITION; - uint32_t OTG_VERTICAL_INTERRUPT2_CONTROL; - uint32_t OTG_VERTICAL_INTERRUPT2_POSITION; - uint32_t OPTC_INPUT_CLOCK_CONTROL; - uint32_t OPTC_DATA_SOURCE_SELECT; - uint32_t OPTC_MEMORY_CONFIG; - uint32_t OPTC_INPUT_GLOBAL_CONTROL; - uint32_t CONTROL; - uint32_t OTG_GSL_WINDOW_X; - uint32_t OTG_GSL_WINDOW_Y; - uint32_t OTG_VUPDATE_KEEPOUT; - uint32_t OTG_CRC_CNTL; - uint32_t OTG_CRC_CNTL2; - uint32_t OTG_CRC0_DATA_RG; - uint32_t OTG_CRC1_DATA_RG; - uint32_t OTG_CRC2_DATA_RG; - uint32_t OTG_CRC3_DATA_RG; - uint32_t OTG_CRC0_DATA_B; - uint32_t OTG_CRC1_DATA_B; - uint32_t OTG_CRC2_DATA_B; - uint32_t OTG_CRC3_DATA_B; - uint32_t OTG_CRC0_DATA_R; - uint32_t OTG_CRC1_DATA_R; - uint32_t OTG_CRC2_DATA_R; - uint32_t OTG_CRC3_DATA_R; - uint32_t OTG_CRC0_DATA_G; - uint32_t OTG_CRC1_DATA_G; - uint32_t OTG_CRC2_DATA_G; - uint32_t OTG_CRC3_DATA_G; - uint32_t OTG_CRC0_WINDOWA_X_CONTROL; - uint32_t OTG_CRC0_WINDOWA_Y_CONTROL; - uint32_t OTG_CRC0_WINDOWB_X_CONTROL; - uint32_t OTG_CRC0_WINDOWB_Y_CONTROL; - uint32_t OTG_CRC1_WINDOWA_X_CONTROL; - uint32_t OTG_CRC1_WINDOWA_Y_CONTROL; - uint32_t OTG_CRC1_WINDOWB_X_CONTROL; - uint32_t OTG_CRC1_WINDOWB_Y_CONTROL; - uint32_t GSL_SOURCE_SELECT; - uint32_t DWB_SOURCE_SELECT; - uint32_t OTG_DSC_START_POSITION; - uint32_t OPTC_DATA_FORMAT_CONTROL; - uint32_t OPTC_BYTES_PER_PIXEL; - uint32_t OPTC_WIDTH_CONTROL; - uint32_t OTG_DRR_CONTROL; - uint32_t OTG_BLANK_DATA_COLOR; - uint32_t OTG_BLANK_DATA_COLOR_EXT; - uint32_t OTG_DRR_TRIGGER_WINDOW; - uint32_t OTG_M_CONST_DTO0; - uint32_t OTG_M_CONST_DTO1; - uint32_t OTG_DRR_V_TOTAL_CHANGE; - uint32_t OTG_GLOBAL_CONTROL4; - uint32_t OTG_CRC0_WINDOWA_X_CONTROL_READBACK; - uint32_t OTG_CRC0_WINDOWA_Y_CONTROL_READBACK; - uint32_t OTG_CRC0_WINDOWB_X_CONTROL_READBACK; - uint32_t OTG_CRC0_WINDOWB_Y_CONTROL_READBACK; - uint32_t OTG_CRC1_WINDOWA_X_CONTROL_READBACK; - uint32_t OTG_CRC1_WINDOWA_Y_CONTROL_READBACK; - uint32_t OTG_CRC1_WINDOWB_X_CONTROL_READBACK; - uint32_t OTG_CRC1_WINDOWB_Y_CONTROL_READBACK; - uint32_t OPTC_CLOCK_CONTROL; - uint32_t OPTC_WIDTH_CONTROL2; - uint32_t OTG_PSTATE_REGISTER; - uint32_t OTG_PIPE_UPDATE_STATUS; - uint32_t INTERRUPT_DEST; + OPTC_REG_VARIABLE_LIST_DCN; }; #define TG_COMMON_MASK_SH_LIST_DCN(mask_sh)\ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c index 5c6dc710e96c..e4eca3e32c1b 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c @@ -1220,7 +1220,7 @@ static void get_pixel_clock_parameters( struct pipe_ctx *odm_pipe; int opp_cnt = 1; struct dc_link *link = stream->link; - struct link_encoder *link_enc = NULL; + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct dc *dc = pipe_ctx->stream->ctx->dc; struct dce_hwseq *hws = dc->hwseq; @@ -1229,7 +1229,8 @@ static void get_pixel_clock_parameters( pixel_clk_params->requested_pix_clk_100hz = stream->timing.pix_clk_100hz; - link_enc = link_enc_cfg_get_link_enc(link); + if (!dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); if (link_enc) pixel_clk_params->encoder_object_id = link_enc->id; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c index 911bd60d4fbc..3c42ba8566cf 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c @@ -890,7 +890,7 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_z10 = true, .enable_legacy_fast_update = true, .enable_z9_disable_interface = true, /* Allow support for the PMFW interface for disable Z9*/ - .dml_hostvm_override = DML_HOSTVM_NO_OVERRIDE, + .dml_hostvm_override = DML_HOSTVM_OVERRIDE_FALSE, .using_dml2 = false, }; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c index 4e842f29d4c4..7436dfbdf927 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c @@ -1666,12 +1666,13 @@ static void dcn401_build_pipe_pix_clk_params(struct pipe_ctx *pipe_ctx) { const struct dc_stream_state *stream = pipe_ctx->stream; struct dc_link *link = stream->link; - struct link_encoder *link_enc = NULL; + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct pixel_clk_params *pixel_clk_params = &pipe_ctx->stream_res.pix_clk_params; pixel_clk_params->requested_pix_clk_100hz = stream->timing.pix_clk_100hz; - link_enc = link_enc_cfg_get_link_enc(link); + if (!pipe_ctx->stream->ctx->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); if (link_enc) pixel_clk_params->encoder_object_id = link_enc->id; diff --git a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c index 31495c9978b0..28348734d900 100644 --- a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c +++ b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c @@ -3,12 +3,11 @@ // Copyright 2024 Advanced Micro Devices, Inc. #include "dc_spl.h" -#include "dc_spl_scl_filters.h" #include "dc_spl_scl_easf_filters.h" #include "dc_spl_isharp_filters.h" #include "spl_debug.h" -#define IDENTITY_RATIO(ratio) (spl_fixpt_u2d19(ratio) == (1 << 19)) +#define IDENTITY_RATIO(ratio) (spl_fixpt_u3d19(ratio) == (1 << 19)) #define MIN_VIEWPORT_SIZE 12 static bool spl_is_yuv420(enum spl_pixel_format format) @@ -76,6 +75,21 @@ static struct spl_rect shift_rec(const struct spl_rect *rec_in, int x, int y) return rec_out; } +static void spl_opp_adjust_rect(struct spl_rect *rec, const struct spl_opp_adjust *adjust) +{ + if ((rec->x + adjust->x) >= 0) + rec->x += adjust->x; + + if ((rec->y + adjust->y) >= 0) + rec->y += adjust->y; + + if ((rec->width + adjust->width) >= 1) + rec->width += adjust->width; + + if ((rec->height + adjust->height) >= 1) + rec->height += adjust->height; +} + static struct spl_rect calculate_plane_rec_in_timing_active( struct spl_in *spl_in, const struct spl_rect *rec_in) @@ -723,13 +737,15 @@ static void spl_handle_3d_recout(struct spl_in *spl_in, struct spl_rect *recout) } } -static void spl_clamp_viewport(struct spl_rect *viewport) +static void spl_clamp_viewport(struct spl_rect *viewport, int min_viewport_size) { + if (min_viewport_size == 0) + min_viewport_size = MIN_VIEWPORT_SIZE; /* Clamp minimum viewport size */ - if (viewport->height < MIN_VIEWPORT_SIZE) - viewport->height = MIN_VIEWPORT_SIZE; - if (viewport->width < MIN_VIEWPORT_SIZE) - viewport->width = MIN_VIEWPORT_SIZE; + if (viewport->height < min_viewport_size) + viewport->height = min_viewport_size; + if (viewport->width < min_viewport_size) + viewport->width = min_viewport_size; } static enum scl_mode spl_get_dscl_mode(const struct spl_in *spl_in, @@ -870,6 +886,8 @@ static bool spl_get_isharp_en(struct spl_in *spl_in, static void spl_get_taps_non_adaptive_scaler( struct spl_scratch *spl_scratch, const struct spl_taps *in_taps) { + bool check_max_downscale = false; + if (in_taps->h_taps == 0) { if (spl_fixpt_ceil(spl_scratch->scl_data.ratios.horz) > 1) spl_scratch->scl_data.taps.h_taps = spl_min(2 * spl_fixpt_ceil( @@ -909,6 +927,23 @@ static void spl_get_taps_non_adaptive_scaler( else spl_scratch->scl_data.taps.h_taps_c = in_taps->h_taps_c; + + /* + * Max downscale supported is 6.0x. Add ASSERT to catch if go beyond that + */ + check_max_downscale = spl_fixpt_le(spl_scratch->scl_data.ratios.horz, + spl_fixpt_from_fraction(6, 1)); + SPL_ASSERT(check_max_downscale); + check_max_downscale = spl_fixpt_le(spl_scratch->scl_data.ratios.vert, + spl_fixpt_from_fraction(6, 1)); + SPL_ASSERT(check_max_downscale); + check_max_downscale = spl_fixpt_le(spl_scratch->scl_data.ratios.horz_c, + spl_fixpt_from_fraction(6, 1)); + SPL_ASSERT(check_max_downscale); + check_max_downscale = spl_fixpt_le(spl_scratch->scl_data.ratios.vert_c, + spl_fixpt_from_fraction(6, 1)); + SPL_ASSERT(check_max_downscale); + if (IDENTITY_RATIO(spl_scratch->scl_data.ratios.horz)) spl_scratch->scl_data.taps.h_taps = 1; if (IDENTITY_RATIO(spl_scratch->scl_data.ratios.vert)) @@ -927,8 +962,8 @@ static bool spl_get_optimal_number_of_taps( bool *enable_isharp) { int num_part_y, num_part_c; - int max_taps_y, max_taps_c; - int min_taps_y, min_taps_c; + unsigned int max_taps_y, max_taps_c; + unsigned int min_taps_y, min_taps_c; enum lb_memory_config lb_config; bool skip_easf = false; bool is_subsampled = spl_is_subsampled_format(spl_in->basic_in.format); @@ -990,12 +1025,18 @@ static bool spl_get_optimal_number_of_taps( lb_config, &num_part_y, &num_part_c); /* MAX_V_TAPS = MIN (NUM_LINES - MAX(CEILING(V_RATIO,1)-2, 0), 8) */ if (spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert) > 2) - max_taps_y = num_part_y - (spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert) - 2); + if ((spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert) - 2) > num_part_y) + max_taps_y = 0; + else + max_taps_y = num_part_y - (spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert) - 2); else max_taps_y = num_part_y; if (spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert_c) > 2) - max_taps_c = num_part_c - (spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert_c) - 2); + if ((spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert_c) - 2) > num_part_c) + max_taps_c = 0; + else + max_taps_c = num_part_c - (spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert_c) - 2); else max_taps_c = num_part_c; @@ -1764,6 +1805,8 @@ static bool spl_calculate_number_of_taps(struct spl_in *spl_in, struct spl_scrat spl_calculate_recout(spl_in, spl_scratch, spl_out); /* depends on pixel format */ spl_calculate_scaling_ratios(spl_in, spl_scratch, spl_out); + /* Adjust recout for opp if needed */ + spl_opp_adjust_rect(&spl_scratch->scl_data.recout, &spl_in->basic_in.opp_recout_adjust); /* depends on scaling ratios and recout, does not calculate offset yet */ spl_calculate_viewport_size(spl_in, spl_scratch); @@ -1775,7 +1818,7 @@ static bool spl_calculate_number_of_taps(struct spl_in *spl_in, struct spl_scrat } /* Calculate scaler parameters */ -bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out) +bool SPL_NAMESPACE(spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out)) { bool res = false; bool enable_easf_v = false; @@ -1800,7 +1843,7 @@ bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out) // Handle 3d recout spl_handle_3d_recout(spl_in, &spl_scratch.scl_data.recout); // Clamp - spl_clamp_viewport(&spl_scratch.scl_data.viewport); + spl_clamp_viewport(&spl_scratch.scl_data.viewport, spl_in->min_viewport_size); // Save all calculated parameters in dscl_prog_data structure to program hw registers spl_set_dscl_prog_data(spl_in, &spl_scratch, spl_out, enable_easf_v, enable_easf_h, enable_isharp); @@ -1840,7 +1883,7 @@ bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out) } /* External interface to get number of taps only */ -bool spl_get_number_of_taps(struct spl_in *spl_in, struct spl_out *spl_out) +bool SPL_NAMESPACE(spl_get_number_of_taps(struct spl_in *spl_in, struct spl_out *spl_out)) { bool res = false; bool enable_easf_v = false; diff --git a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.h b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.h index 02a2d6725ed5..145961803a92 100644 --- a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.h +++ b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.h @@ -9,10 +9,22 @@ #define BLACK_OFFSET_RGB_Y 0x0 #define BLACK_OFFSET_CBCR 0x8000 +#ifndef SPL_PFX_ +#define SPL_PFX_ +#endif + +#define SPL_EXPAND2(a, b) a##b +#define SPL_EXPAND(a, b) SPL_EXPAND2(a, b) +#define SPL_NAMESPACE(symbol) SPL_EXPAND(SPL_PFX_, symbol) + +#ifdef __cplusplus +extern "C" { +#endif + /* SPL interfaces */ -bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out); +bool SPL_NAMESPACE(spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out)); -bool spl_get_number_of_taps(struct spl_in *spl_in, struct spl_out *spl_out); +bool SPL_NAMESPACE(spl_get_number_of_taps(struct spl_in *spl_in, struct spl_out *spl_out)); #endif /* __DC_SPL_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl_types.h b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl_types.h index 467af9dd90de..1c3949b24611 100644 --- a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl_types.h +++ b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl_types.h @@ -427,6 +427,14 @@ struct spl_out { // SPL inputs +// opp extra adjustment for rect +struct spl_opp_adjust { + int x; + int y; + int width; + int height; +}; + // Basic input information struct basic_in { enum spl_pixel_format format; // Pixel Format @@ -444,6 +452,7 @@ struct basic_in { } num_slices_recout_width; } num_h_slices_recout_width_align; int mpc_h_slice_index; // previous mpc_combine_v - split_idx + struct spl_opp_adjust opp_recout_adjust; // Inputs for adaptive scaler - TODO enum spl_transfer_func_type tf_type; /* Transfer function type */ enum spl_transfer_func_predefined tf_predefined_type; /* Transfer function predefined type */ @@ -484,7 +493,7 @@ struct spl_sharpness_range { }; struct adaptive_sharpness { bool enable; - int sharpness_level; + unsigned int sharpness_level; struct spl_sharpness_range sharpness_range; }; enum linear_light_scaling { // convert it in translation logic @@ -535,6 +544,7 @@ struct spl_in { bool is_hdr_on; int h_active; int v_active; + int min_viewport_size; int sdr_white_level_nits; enum sharpen_policy sharpen_policy; }; diff --git a/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.c b/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.c index 131f1e3949d3..52d97918a3bd 100644 --- a/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.c +++ b/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.c @@ -346,7 +346,7 @@ struct spl_fixed31_32 spl_fixpt_exp(struct spl_fixed31_32 arg) if (m > 0) return spl_fixpt_shl( spl_fixed31_32_exp_from_taylor_series(r), - (unsigned char)m); + (unsigned int)m); else return spl_fixpt_div_int( spl_fixed31_32_exp_from_taylor_series(r), diff --git a/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.h b/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.h index ed2647f9a099..9f349ffe9148 100644 --- a/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.h +++ b/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.h @@ -189,7 +189,7 @@ static inline struct spl_fixed31_32 spl_fixpt_clamp( * @brief * result = arg << shift */ -static inline struct spl_fixed31_32 spl_fixpt_shl(struct spl_fixed31_32 arg, unsigned char shift) +static inline struct spl_fixed31_32 spl_fixpt_shl(struct spl_fixed31_32 arg, unsigned int shift) { SPL_ASSERT(((arg.value >= 0) && (arg.value <= LLONG_MAX >> shift)) || ((arg.value < 0) && (arg.value >= ~(LLONG_MAX >> shift)))); @@ -203,7 +203,7 @@ static inline struct spl_fixed31_32 spl_fixpt_shl(struct spl_fixed31_32 arg, uns * @brief * result = arg >> shift */ -static inline struct spl_fixed31_32 spl_fixpt_shr(struct spl_fixed31_32 arg, unsigned char shift) +static inline struct spl_fixed31_32 spl_fixpt_shr(struct spl_fixed31_32 arg, unsigned int shift) { bool negative = arg.value < 0; diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 8cf89aed024b..f84bbc033e64 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -161,6 +161,13 @@ #endif /** + * OS/FW agnostic memcmp + */ +#ifndef dmub_memcmp +#define dmub_memcmp(lhs, rhs, bytes) memcmp((lhs), (rhs), (bytes)) +#endif + +/** * OS/FW agnostic udelay */ #ifndef dmub_udelay @@ -1460,6 +1467,11 @@ enum dmub_cmd_type { */ DMUB_CMD__PSP = 88, + /** + * Command type used for all Fused IO commands. + */ + DMUB_CMD__FUSED_IO = 89, + DMUB_CMD__VBIOS = 128, }; @@ -1491,6 +1503,10 @@ enum dmub_out_cmd_type { * Command type used for HPD redetect notification */ DMUB_OUT_CMD__HPD_SENSE_NOTIFY = 6, + /** + * Command type used for Fused IO notification + */ + DMUB_OUT_CMD__FUSED_IO = 7, }; /* DMUB_CMD__DPIA command sub-types. */ @@ -5325,6 +5341,63 @@ struct dmub_rb_cmd_get_usbc_cable_id { } data; }; +enum dmub_cmd_fused_io_sub_type { + DMUB_CMD__FUSED_IO_EXECUTE = 0, + DMUB_CMD__FUSED_IO_ABORT = 1, +}; + +enum dmub_cmd_fused_request_type { + FUSED_REQUEST_READ, + FUSED_REQUEST_WRITE, + FUSED_REQUEST_POLL, +}; + +enum dmub_cmd_fused_request_status { + FUSED_REQUEST_STATUS_SUCCESS, + FUSED_REQUEST_STATUS_BEGIN, + FUSED_REQUEST_STATUS_SUBMIT, + FUSED_REQUEST_STATUS_REPLY, + FUSED_REQUEST_STATUS_POLL, + FUSED_REQUEST_STATUS_ABORTED, + FUSED_REQUEST_STATUS_FAILED = 0x80, + FUSED_REQUEST_STATUS_INVALID, + FUSED_REQUEST_STATUS_BUSY, + FUSED_REQUEST_STATUS_TIMEOUT, + FUSED_REQUEST_STATUS_POLL_TIMEOUT, +}; + +struct dmub_cmd_fused_request { + uint8_t status; + uint8_t type : 2; + uint8_t _reserved0 : 3; + uint8_t poll_mask_msb : 3; // Number of MSB to zero out from last byte before comparing + uint8_t identifier; + uint8_t _reserved1; + uint32_t timeout_us; + union dmub_cmd_fused_request_location { + struct dmub_cmd_fused_request_location_i2c { + uint8_t is_aux : 1; // False + uint8_t ddc_line : 3; + uint8_t _reserved0 : 4; + uint8_t address; + uint8_t offset; + uint8_t length; + } i2c; + struct dmub_cmd_fused_request_location_aux { + uint32_t is_aux : 1; // True + uint32_t ddc_line : 3; + uint32_t address : 20; + uint32_t length : 8; // Automatically split into 16B transactions + } aux; + } u; + uint8_t buffer[0x30]; // Read: out, write: in, poll: expected +}; + +struct dmub_rb_cmd_fused_io { + struct dmub_cmd_header header; + struct dmub_cmd_fused_request request; +}; + /** * Command type of a DMUB_CMD__SECURE_DISPLAY command */ @@ -5738,6 +5811,8 @@ union dmub_rb_cmd { struct dmub_rb_cmd_fams2_drr_update fams2_drr_update; struct dmub_rb_cmd_fams2_flip fams2_flip; + + struct dmub_rb_cmd_fused_io fused_io; }; /** @@ -5768,6 +5843,7 @@ union dmub_rb_out_cmd { * HPD sense notification command. */ struct dmub_rb_cmd_hpd_sense_notify hpd_sense_notify; + struct dmub_rb_cmd_fused_io fused_io; }; #pragma pack(pop) diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c index 3d0bba602b53..9796077885c9 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c @@ -83,8 +83,8 @@ static inline void dmub_dcn31_translate_addr(const union dmub_addr *addr_in, void dmub_dcn31_reset(struct dmub_srv *dmub) { union dmub_gpint_data_register cmd; - const uint32_t timeout = 100; - uint32_t in_reset, scratch, i, pwait_mode; + const uint32_t timeout = 100000; + uint32_t in_reset, is_enabled, scratch, i, pwait_mode; REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &in_reset); @@ -108,7 +108,7 @@ void dmub_dcn31_reset(struct dmub_srv *dmub) } for (i = 0; i < timeout; ++i) { - scratch = dmub->hw_funcs.get_gpint_response(dmub); + scratch = REG_READ(DMCUB_SCRATCH7); if (scratch == DMUB_GPINT__STOP_FW_RESPONSE) break; @@ -125,9 +125,14 @@ void dmub_dcn31_reset(struct dmub_srv *dmub) /* Force reset in case we timed out, DMCUB is likely hung. */ } - REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1); - REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); - REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1); + REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_enabled); + + if (is_enabled) { + REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1); + REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1); + REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); + } + REG_WRITE(DMCUB_INBOX1_RPTR, 0); REG_WRITE(DMCUB_INBOX1_WPTR, 0); REG_WRITE(DMCUB_OUTBOX1_RPTR, 0); diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c index e5e77bd3c31e..01d013a12b94 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c @@ -88,7 +88,7 @@ static inline void dmub_dcn35_translate_addr(const union dmub_addr *addr_in, void dmub_dcn35_reset(struct dmub_srv *dmub) { union dmub_gpint_data_register cmd; - const uint32_t timeout = 100; + const uint32_t timeout = 100000; uint32_t in_reset, is_enabled, scratch, i, pwait_mode; REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &in_reset); @@ -113,7 +113,7 @@ void dmub_dcn35_reset(struct dmub_srv *dmub) } for (i = 0; i < timeout; ++i) { - scratch = dmub->hw_funcs.get_gpint_response(dmub); + scratch = REG_READ(DMCUB_SCRATCH7); if (scratch == DMUB_GPINT__STOP_FW_RESPONSE) break; diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.c index 39a8cb6d7523..e1c4fe1c6e3e 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.c @@ -63,8 +63,10 @@ static inline void dmub_dcn401_translate_addr(const union dmub_addr *addr_in, void dmub_dcn401_reset(struct dmub_srv *dmub) { union dmub_gpint_data_register cmd; - const uint32_t timeout = 30; - uint32_t in_reset, scratch, i; + const uint32_t timeout_us = 1 * 1000 * 1000; //1s + const uint32_t poll_delay_us = 1; //1us + uint32_t i = 0; + uint32_t in_reset, scratch, pwait_mode; REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &in_reset); @@ -75,32 +77,35 @@ void dmub_dcn401_reset(struct dmub_srv *dmub) dmub->hw_funcs.set_gpint(dmub, cmd); - /** - * Timeout covers both the ACK and the wait - * for remaining work to finish. - * - * This is mostly bound by the PHY disable sequence. - * Each register check will be greater than 1us, so - * don't bother using udelay. - */ - - for (i = 0; i < timeout; ++i) { + for (i = 0; i < timeout_us; i++) { if (dmub->hw_funcs.is_gpint_acked(dmub, cmd)) break; + + udelay(poll_delay_us); } - for (i = 0; i < timeout; ++i) { + for (; i < timeout_us; i++) { scratch = dmub->hw_funcs.get_gpint_response(dmub); if (scratch == DMUB_GPINT__STOP_FW_RESPONSE) break; + + udelay(poll_delay_us); } - /* Force reset in case we timed out, DMCUB is likely hung. */ + for (; i < timeout_us; i++) { + REG_GET(DMCUB_CNTL, DMCUB_PWAIT_MODE_STATUS, &pwait_mode); + if (pwait_mode & (1 << 0)) + break; + + udelay(poll_delay_us); + } + } + + if (i >= timeout_us) { + /* timeout should never occur */ + BREAK_TO_DEBUGGER(); } - REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1); - REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); - REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1); REG_WRITE(DMCUB_INBOX1_RPTR, 0); REG_WRITE(DMCUB_INBOX1_WPTR, 0); REG_WRITE(DMCUB_OUTBOX1_RPTR, 0); @@ -131,7 +136,10 @@ void dmub_dcn401_backdoor_load(struct dmub_srv *dmub, dmub_dcn401_get_fb_base_offset(dmub, &fb_base, &fb_offset); + /* reset and disable DMCUB and MMHUBBUB DMUIF */ REG_UPDATE(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 1); + REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1); + REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); dmub_dcn401_translate_addr(&cw0->offset, fb_base, fb_offset, &offset); @@ -151,6 +159,7 @@ void dmub_dcn401_backdoor_load(struct dmub_srv *dmub, DMCUB_REGION3_CW1_TOP_ADDRESS, cw1->region.top, DMCUB_REGION3_CW1_ENABLE, 1); + /* release DMCUB reset only to prevent premature execution */ REG_UPDATE_2(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 0, DMCUB_MEM_UNIT_ID, 0x20); } @@ -161,7 +170,10 @@ void dmub_dcn401_backdoor_load_zfb_mode(struct dmub_srv *dmub, { union dmub_addr offset; + /* reset and disable DMCUB and MMHUBBUB DMUIF */ REG_UPDATE(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 1); + REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1); + REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); offset = cw0->offset; @@ -181,6 +193,7 @@ void dmub_dcn401_backdoor_load_zfb_mode(struct dmub_srv *dmub, DMCUB_REGION3_CW1_TOP_ADDRESS, cw1->region.top, DMCUB_REGION3_CW1_ENABLE, 1); + /* release DMCUB reset only to prevent premature execution */ REG_UPDATE_2(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 0, DMCUB_MEM_UNIT_ID, 0x20); } diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.h index 4c8843b79695..31f95b27e227 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.h +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.h @@ -169,7 +169,8 @@ struct dmub_srv; DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_INBOX0_RSP_INT_EN) \ DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_OUTBOX0_RDY_INT_ACK) \ DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_OUTBOX0_RDY_INT_STAT) \ - DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_OUTBOX0_RDY_INT_EN) + DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_OUTBOX0_RDY_INT_EN) \ + DMUB_SF(DMCUB_CNTL, DMCUB_PWAIT_MODE_STATUS) struct dmub_srv_dcn401_reg_offset { #define DMUB_SR(reg) uint32_t reg; diff --git a/drivers/gpu/drm/amd/display/include/logger_interface.h b/drivers/gpu/drm/amd/display/include/logger_interface.h index 058f882d5bdd..4c01514b926c 100644 --- a/drivers/gpu/drm/amd/display/include/logger_interface.h +++ b/drivers/gpu/drm/amd/display/include/logger_interface.h @@ -40,11 +40,6 @@ struct dc_state; * */ -void pre_surface_trace( - struct dc *dc, - const struct dc_plane_state *const *plane_states, - int surface_count); - void update_surface_trace( struct dc *dc, const struct dc_surface_update *updates, diff --git a/drivers/gpu/drm/amd/include/amd_acpi.h b/drivers/gpu/drm/amd/include/amd_acpi.h index 2d089d30518f..06badbf0c5b9 100644 --- a/drivers/gpu/drm/amd/include/amd_acpi.h +++ b/drivers/gpu/drm/amd/include/amd_acpi.h @@ -61,7 +61,7 @@ struct atif_qbtc_arguments { struct atif_qbtc_data_point { u8 luminance; /* luminance in percent */ - u8 ipnut_signal; /* input signal in range 0-255 */ + u8 input_signal; /* input signal in range 0-255 */ } __packed; struct atif_qbtc_output { @@ -75,6 +75,8 @@ struct atif_qbtc_output { u8 number_of_points; /* number of data points */ struct atif_qbtc_data_point data_points[ATIF_QBTC_MAX_DATA_POINTS]; } __packed; +static_assert(ATIF_QBTC_MAX_DATA_POINTS == MAX_LUMINANCE_DATA_POINTS); +static_assert(sizeof(struct atif_qbtc_data_point) == sizeof(struct amdgpu_dm_luminance_data)); #define ATIF_NOTIFY_MASK 0x3 #define ATIF_NOTIFY_NONE 0 diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 3e86865563dc..485b713cfad0 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -354,6 +354,10 @@ enum DC_DEBUG_MASK { * @DC_DISABLE_SUBVP: If set, disable DCN Sub-Viewport feature in amdgpu driver. */ DC_DISABLE_SUBVP = 0x20000, + /** + * @DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE: If set, disable support for custom brightness curves + */ + DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE = 0x40000, }; enum amd_dpm_forced_level; @@ -405,7 +409,7 @@ struct amd_ip_funcs { int (*prepare_suspend)(struct amdgpu_ip_block *ip_block); int (*suspend)(struct amdgpu_ip_block *ip_block); int (*resume)(struct amdgpu_ip_block *ip_block); - bool (*is_idle)(void *handle); + bool (*is_idle)(struct amdgpu_ip_block *ip_block); int (*wait_for_idle)(struct amdgpu_ip_block *ip_block); bool (*check_soft_reset)(struct amdgpu_ip_block *ip_block); int (*pre_soft_reset)(struct amdgpu_ip_block *ip_block); diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_5_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_5_0_offset.h index abdb8728156e..d6c02cf815be 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_5_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_5_0_offset.h @@ -9478,6 +9478,8 @@ #define regRLC_GFX_IMU_CMD_BASE_IDX 1 #define regGFX_IMU_RLC_STATUS 0x4054 #define regGFX_IMU_RLC_STATUS_BASE_IDX 1 +#define regGFX_IMU_STATUS 0x4055 +#define regGFX_IMU_STATUS_BASE_IDX 1 #define regGFX_IMU_SOC_DATA 0x4059 #define regGFX_IMU_SOC_DATA_BASE_IDX 1 #define regGFX_IMU_SOC_ADDR 0x405a diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_3_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_3_sh_mask.h index 2bd9f3f1026f..0122a21c50cf 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_3_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_3_sh_mask.h @@ -2261,11 +2261,13 @@ #define SH_MEM_CONFIG__ADDRESS_MODE__SHIFT 0x0 #define SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT 0x3 #define SH_MEM_CONFIG__F8_MODE__SHIFT 0x8 +#define SH_MEM_CONFIG__PRECISION_MODE__SHIFT 0x9 #define SH_MEM_CONFIG__RETRY_DISABLE__SHIFT 0xc #define SH_MEM_CONFIG__PRIVATE_NV__SHIFT 0xd #define SH_MEM_CONFIG__ADDRESS_MODE_MASK 0x00000001L #define SH_MEM_CONFIG__ALIGNMENT_MODE_MASK 0x00000018L #define SH_MEM_CONFIG__F8_MODE_MASK 0x00000100L +#define SH_MEM_CONFIG__PRECISION_MODE_MASK 0x00000200L #define SH_MEM_CONFIG__RETRY_DISABLE_MASK 0x00001000L #define SH_MEM_CONFIG__PRIVATE_NV_MASK 0x00002000L //SP_MFMA_PORTD_RD_CONFIG diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h index e3e635a31b8a..1e8dfa6c0dc8 100644 --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h @@ -330,6 +330,8 @@ struct kfd2kgd_calls { uint64_t (*hqd_reset)(struct amdgpu_device *adev, uint32_t pipe_id, uint32_t queue_id, uint32_t inst, unsigned int utimeout); + uint32_t (*hqd_sdma_get_doorbell)(struct amdgpu_device *adev, + int engine, int queue); }; #endif /* KGD_KFD_INTERFACE_H_INCLUDED */ diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index faae9bf48aa4..81e9b443ca0a 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -716,8 +716,32 @@ int amdgpu_dpm_send_rma_reason(struct amdgpu_device *adev) ret = smu_send_rma_reason(smu); mutex_unlock(&adev->pm.mutex); - if (amdgpu_cper_generate_bp_threshold_record(adev)) - dev_warn(adev->dev, "fail to generate bad page threshold cper records\n"); + if (adev->cper.enabled) + if (amdgpu_cper_generate_bp_threshold_record(adev)) + dev_warn(adev->dev, "fail to generate bad page threshold cper records\n"); + + return ret; +} + +/** + * amdgpu_dpm_reset_sdma_is_supported - Check if SDMA reset is supported + * @adev: amdgpu_device pointer + * + * This function checks if the SMU supports resetting the SDMA engine. + * It returns false if the hardware does not support software SMU or + * if the feature is not supported. + */ +bool amdgpu_dpm_reset_sdma_is_supported(struct amdgpu_device *adev) +{ + struct smu_context *smu = adev->powerplay.pp_handle; + bool ret; + + if (!is_support_sw_smu(adev)) + return false; + + mutex_lock(&adev->pm.mutex); + ret = smu_reset_sdma_is_supported(smu); + mutex_unlock(&adev->pm.mutex); return ret; } diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h index 1f5ac7e0230d..9fb26b5c8ae7 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h @@ -603,5 +603,6 @@ int amdgpu_dpm_set_pm_policy(struct amdgpu_device *adev, int policy_type, ssize_t amdgpu_dpm_get_pm_policy_info(struct amdgpu_device *adev, enum pp_pm_policy p_type, char *buf); int amdgpu_dpm_reset_sdma(struct amdgpu_device *adev, uint32_t inst_mask); +bool amdgpu_dpm_reset_sdma_is_supported(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c index 67a8e22b1126..59fae668dc3f 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c @@ -3042,6 +3042,7 @@ static int kv_dpm_hw_init(struct amdgpu_ip_block *ip_block) if (!amdgpu_dpm) return 0; + mutex_lock(&adev->pm.mutex); kv_dpm_setup_asic(adev); ret = kv_dpm_enable(adev); if (ret) @@ -3049,6 +3050,8 @@ static int kv_dpm_hw_init(struct amdgpu_ip_block *ip_block) else adev->pm.dpm_enabled = true; amdgpu_legacy_dpm_compute_clocks(adev); + mutex_unlock(&adev->pm.mutex); + return ret; } @@ -3066,35 +3069,45 @@ static int kv_dpm_suspend(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + cancel_work_sync(&adev->pm.dpm.thermal.work); + if (adev->pm.dpm_enabled) { + mutex_lock(&adev->pm.mutex); + adev->pm.dpm_enabled = false; /* disable dpm */ kv_dpm_disable(adev); /* reset the power state */ adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps; + mutex_unlock(&adev->pm.mutex); } return 0; } static int kv_dpm_resume(struct amdgpu_ip_block *ip_block) { - int ret; + int ret = 0; struct amdgpu_device *adev = ip_block->adev; - if (adev->pm.dpm_enabled) { + if (!amdgpu_dpm) + return 0; + + if (!adev->pm.dpm_enabled) { + mutex_lock(&adev->pm.mutex); /* asic init will reset to the boot state */ kv_dpm_setup_asic(adev); ret = kv_dpm_enable(adev); - if (ret) + if (ret) { adev->pm.dpm_enabled = false; - else + } else { adev->pm.dpm_enabled = true; - if (adev->pm.dpm_enabled) amdgpu_legacy_dpm_compute_clocks(adev); + } + mutex_unlock(&adev->pm.mutex); } - return 0; + return ret; } -static bool kv_dpm_is_idle(void *handle) +static bool kv_dpm_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c index e861355ebd75..c7518b13e787 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c @@ -1009,9 +1009,12 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work) enum amd_pm_state_type dpm_state = POWER_STATE_TYPE_INTERNAL_THERMAL; int temp, size = sizeof(temp); - if (!adev->pm.dpm_enabled) - return; + mutex_lock(&adev->pm.mutex); + if (!adev->pm.dpm_enabled) { + mutex_unlock(&adev->pm.mutex); + return; + } if (!pp_funcs->read_sensor(adev->powerplay.pp_handle, AMDGPU_PP_SENSOR_GPU_TEMP, (void *)&temp, @@ -1033,4 +1036,5 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work) adev->pm.dpm.state = dpm_state; amdgpu_legacy_dpm_compute_clocks(adev->powerplay.pp_handle); + mutex_unlock(&adev->pm.mutex); } diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index a87dcf0974bc..1c25f3023e93 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -7786,6 +7786,7 @@ static int si_dpm_hw_init(struct amdgpu_ip_block *ip_block) if (!amdgpu_dpm) return 0; + mutex_lock(&adev->pm.mutex); si_dpm_setup_asic(adev); ret = si_dpm_enable(adev); if (ret) @@ -7793,6 +7794,7 @@ static int si_dpm_hw_init(struct amdgpu_ip_block *ip_block) else adev->pm.dpm_enabled = true; amdgpu_legacy_dpm_compute_clocks(adev); + mutex_unlock(&adev->pm.mutex); return ret; } @@ -7810,35 +7812,47 @@ static int si_dpm_suspend(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + cancel_work_sync(&adev->pm.dpm.thermal.work); + if (adev->pm.dpm_enabled) { + mutex_lock(&adev->pm.mutex); + adev->pm.dpm_enabled = false; /* disable dpm */ si_dpm_disable(adev); /* reset the power state */ adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps; + mutex_unlock(&adev->pm.mutex); } + return 0; } static int si_dpm_resume(struct amdgpu_ip_block *ip_block) { - int ret; + int ret = 0; struct amdgpu_device *adev = ip_block->adev; - if (adev->pm.dpm_enabled) { + if (!amdgpu_dpm) + return 0; + + if (!adev->pm.dpm_enabled) { /* asic init will reset to the boot state */ + mutex_lock(&adev->pm.mutex); si_dpm_setup_asic(adev); ret = si_dpm_enable(adev); - if (ret) + if (ret) { adev->pm.dpm_enabled = false; - else + } else { adev->pm.dpm_enabled = true; - if (adev->pm.dpm_enabled) amdgpu_legacy_dpm_compute_clocks(adev); + } + mutex_unlock(&adev->pm.mutex); } - return 0; + + return ret; } -static bool si_dpm_is_idle(void *handle) +static bool si_dpm_is_idle(struct amdgpu_ip_block *ip_block) { /* XXX */ return true; diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 686345f75f26..b48a031cbba0 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -51,6 +51,11 @@ static int amd_powerplay_create(struct amdgpu_device *adev) hwmgr->adev = adev; hwmgr->not_vf = !amdgpu_sriov_vf(adev); hwmgr->device = amdgpu_cgs_create_device(adev); + if (!hwmgr->device) { + kfree(hwmgr); + return -ENOMEM; + } + mutex_init(&hwmgr->msg_lock); hwmgr->chip_family = adev->family; hwmgr->chip_id = adev->asic_type; @@ -239,7 +244,7 @@ static void pp_late_fini(struct amdgpu_ip_block *ip_block) } -static bool pp_is_idle(void *handle) +static bool pp_is_idle(struct amdgpu_ip_block *ip_block) { return false; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c index 90452b66e107..a59677cf8dfc 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c @@ -149,16 +149,6 @@ int phm_apply_clock_adjust_rules(struct pp_hwmgr *hwmgr) return 0; } -int phm_powerdown_uvd(struct pp_hwmgr *hwmgr) -{ - PHM_FUNC_CHECK(hwmgr); - - if (hwmgr->hwmgr_func->powerdown_uvd != NULL) - return hwmgr->hwmgr_func->powerdown_uvd(hwmgr); - return 0; -} - - int phm_disable_clock_power_gatings(struct pp_hwmgr *hwmgr) { PHM_FUNC_CHECK(hwmgr); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c index 82d540334318..6120f14caab0 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c @@ -158,84 +158,6 @@ int pp_atomfwctrl_get_voltage_table_v4(struct pp_hwmgr *hwmgr, return result; } - -static struct atom_gpio_pin_lut_v2_1 *pp_atomfwctrl_get_gpio_lookup_table( - struct pp_hwmgr *hwmgr) -{ - const void *table_address; - uint16_t idx; - - idx = GetIndexIntoMasterDataTable(gpio_pin_lut); - table_address = smu_atom_get_data_table(hwmgr->adev, - idx, NULL, NULL, NULL); - PP_ASSERT_WITH_CODE(table_address, - "Error retrieving BIOS Table Address!", - return NULL); - - return (struct atom_gpio_pin_lut_v2_1 *)table_address; -} - -static bool pp_atomfwctrl_lookup_gpio_pin( - struct atom_gpio_pin_lut_v2_1 *gpio_lookup_table, - const uint32_t pin_id, - struct pp_atomfwctrl_gpio_pin_assignment *gpio_pin_assignment) -{ - unsigned int size = le16_to_cpu( - gpio_lookup_table->table_header.structuresize); - unsigned int offset = - offsetof(struct atom_gpio_pin_lut_v2_1, gpio_pin[0]); - unsigned long start = (unsigned long)gpio_lookup_table; - - while (offset < size) { - const struct atom_gpio_pin_assignment *pin_assignment = - (const struct atom_gpio_pin_assignment *)(start + offset); - - if (pin_id == pin_assignment->gpio_id) { - gpio_pin_assignment->uc_gpio_pin_bit_shift = - pin_assignment->gpio_bitshift; - gpio_pin_assignment->us_gpio_pin_aindex = - le16_to_cpu(pin_assignment->data_a_reg_index); - return true; - } - offset += offsetof(struct atom_gpio_pin_assignment, gpio_id) + 1; - } - return false; -} - -/* - * Returns TRUE if the given pin id find in lookup table. - */ -bool pp_atomfwctrl_get_pp_assign_pin(struct pp_hwmgr *hwmgr, - const uint32_t pin_id, - struct pp_atomfwctrl_gpio_pin_assignment *gpio_pin_assignment) -{ - bool ret = false; - struct atom_gpio_pin_lut_v2_1 *gpio_lookup_table = - pp_atomfwctrl_get_gpio_lookup_table(hwmgr); - - /* If we cannot find the table do NOT try to control this voltage. */ - PP_ASSERT_WITH_CODE(gpio_lookup_table, - "Could not find GPIO lookup Table in BIOS.", - return false); - - ret = pp_atomfwctrl_lookup_gpio_pin(gpio_lookup_table, - pin_id, gpio_pin_assignment); - - return ret; -} - -/* - * Enter to SelfRefresh mode. - * @param hwmgr - */ -int pp_atomfwctrl_enter_self_refresh(struct pp_hwmgr *hwmgr) -{ - /* 0 - no action - * 1 - leave power to video memory always on - */ - return 0; -} - /** pp_atomfwctrl_get_gpu_pll_dividers_vega10(). * * @param hwmgr input parameter: pointer to HwMgr diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.h index e86e05c786d9..0d62903d5676 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.h @@ -217,9 +217,6 @@ struct pp_atomfwctrl_smc_dpm_parameters { int pp_atomfwctrl_get_gpu_pll_dividers_vega10(struct pp_hwmgr *hwmgr, uint32_t clock_type, uint32_t clock_value, struct pp_atomfwctrl_clock_dividers_soc15 *dividers); -int pp_atomfwctrl_enter_self_refresh(struct pp_hwmgr *hwmgr); -bool pp_atomfwctrl_get_pp_assign_pin(struct pp_hwmgr *hwmgr, const uint32_t pin_id, - struct pp_atomfwctrl_gpio_pin_assignment *gpio_pin_assignment); int pp_atomfwctrl_get_voltage_table_v4(struct pp_hwmgr *hwmgr, uint8_t voltage_type, uint8_t voltage_mode, struct pp_atomfwctrl_voltage_table *voltage_table); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index a8c732e07006..9a821563bc8e 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -1642,7 +1642,6 @@ static const struct pp_hwmgr_func smu10_hwmgr_funcs = { .apply_state_adjust_rules = smu10_apply_state_adjust_rules, .force_dpm_level = smu10_dpm_force_dpm_level, .get_power_state_size = smu10_get_power_state_size, - .powerdown_uvd = NULL, .powergate_uvd = smu10_powergate_vcn, .powergate_vce = NULL, .get_mclk = smu10_dpm_get_mclk, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.c index f2bda3bcbbde..5e4c80f7b20a 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.c @@ -55,7 +55,7 @@ static int smu7_update_vce_dpm(struct pp_hwmgr *hwmgr, bool bgate) return smu7_enable_disable_vce_dpm(hwmgr, !bgate); } -int smu7_powerdown_uvd(struct pp_hwmgr *hwmgr) +static int smu7_powerdown_uvd(struct pp_hwmgr *hwmgr) { if (phm_cf_want_uvd_power_gating(hwmgr)) return smum_send_msg_to_smc(hwmgr, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.h index fc8f8a6acc72..e56abbadc78b 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.h @@ -28,7 +28,6 @@ void smu7_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate); void smu7_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate); -int smu7_powerdown_uvd(struct pp_hwmgr *hwmgr); int smu7_powergate_acp(struct pp_hwmgr *hwmgr, bool bgate); int smu7_disable_clock_power_gating(struct pp_hwmgr *hwmgr); int smu7_update_clock_gatings(struct pp_hwmgr *hwmgr, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 632a25957477..8da882c51856 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -5754,7 +5754,6 @@ static const struct pp_hwmgr_func smu7_hwmgr_funcs = { .patch_boot_state = smu7_dpm_patch_boot_state, .get_pp_table_entry = smu7_get_pp_table_entry, .get_num_of_pp_table_entries = smu7_get_number_of_powerplay_table_entries, - .powerdown_uvd = smu7_powerdown_uvd, .powergate_uvd = smu7_powergate_uvd, .powergate_vce = smu7_powergate_vce, .disable_clock_power_gating = smu7_disable_clock_power_gating, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c index 7e1197420873..9d3b33446adc 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c @@ -2044,7 +2044,6 @@ static const struct pp_hwmgr_func smu8_hwmgr_funcs = { .apply_state_adjust_rules = smu8_apply_state_adjust_rules, .force_dpm_level = smu8_dpm_force_dpm_level, .get_power_state_size = smu8_get_power_state_size, - .powerdown_uvd = smu8_dpm_powerdown_uvd, .powergate_uvd = smu8_dpm_powergate_uvd, .powergate_vce = smu8_dpm_powergate_vce, .powergate_acp = smu8_dpm_powergate_acp, diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/hardwaremanager.h b/drivers/gpu/drm/amd/pm/powerplay/inc/hardwaremanager.h index f4f9a104d170..915f1b8e4dba 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/inc/hardwaremanager.h +++ b/drivers/gpu/drm/amd/pm/powerplay/inc/hardwaremanager.h @@ -396,7 +396,6 @@ struct phm_odn_clock_levels { }; extern int phm_disable_clock_power_gatings(struct pp_hwmgr *hwmgr); -extern int phm_powerdown_uvd(struct pp_hwmgr *hwmgr); extern int phm_setup_asic(struct pp_hwmgr *hwmgr); extern int phm_enable_dynamic_state_management(struct pp_hwmgr *hwmgr); extern int phm_disable_dynamic_state_management(struct pp_hwmgr *hwmgr); diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h index 227bf0e84a13..c661185753b4 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h +++ b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h @@ -257,7 +257,6 @@ struct pp_hwmgr_func { int (*get_pp_table_entry)(struct pp_hwmgr *hwmgr, unsigned long, struct pp_power_state *); int (*get_num_of_pp_table_entries)(struct pp_hwmgr *hwmgr); - int (*powerdown_uvd)(struct pp_hwmgr *hwmgr); void (*powergate_vce)(struct pp_hwmgr *hwmgr, bool bgate); void (*powergate_uvd)(struct pp_hwmgr *hwmgr, bool bgate); void (*powergate_acp)(struct pp_hwmgr *hwmgr, bool bgate); diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 0b32c6cf6924..8cfb07549f54 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -2041,15 +2041,15 @@ static int smu_hw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev)) return 0; - for (i = 0; i < adev->vcn.num_vcn_inst; i++) + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { smu_dpm_set_vcn_enable(smu, false, i); + adev->vcn.inst[i].cur_state = AMD_PG_STATE_GATE; + } smu_dpm_set_jpeg_enable(smu, false); + adev->jpeg.cur_state = AMD_PG_STATE_GATE; smu_dpm_set_vpe_enable(smu, false); smu_dpm_set_umsch_mm_enable(smu, false); - adev->vcn.cur_state = AMD_PG_STATE_GATE; - adev->jpeg.cur_state = AMD_PG_STATE_GATE; - if (!smu->pm_enabled) return 0; @@ -2315,7 +2315,12 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu, if (smu_dpm_ctx->dpm_level != level) { ret = smu_asic_set_performance_level(smu, level); if (ret) { - dev_err(smu->adev->dev, "Failed to set performance level!"); + if (ret == -EOPNOTSUPP) + dev_info(smu->adev->dev, "set performance level %d not supported", + level); + else + dev_err(smu->adev->dev, "Failed to set performance level %d", + level); return ret; } @@ -3907,6 +3912,23 @@ int smu_send_rma_reason(struct smu_context *smu) return ret; } +/** + * smu_reset_sdma_is_supported - Check if SDMA reset is supported by SMU + * @smu: smu_context pointer + * + * This function checks if the SMU supports resetting the SDMA engine. + * It returns true if supported, false otherwise. + */ +bool smu_reset_sdma_is_supported(struct smu_context *smu) +{ + bool ret = false; + + if (smu->ppt_funcs && smu->ppt_funcs->reset_sdma_is_supported) + ret = smu->ppt_funcs->reset_sdma_is_supported(smu); + + return ret; +} + int smu_reset_sdma(struct smu_context *smu, uint32_t inst_mask) { int ret = 0; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index 3630593bce61..3ba169639f54 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -1376,6 +1376,10 @@ struct pptable_funcs { * @reset_sdma: message SMU to soft reset sdma instance. */ int (*reset_sdma)(struct smu_context *smu, uint32_t inst_mask); + /** + * @reset_sdma_is_supported: Check if support resets the SDMA engine. + */ + bool (*reset_sdma_is_supported)(struct smu_context *smu); /** * @get_ecc_table: message SMU to get ECC INFO table. @@ -1637,6 +1641,7 @@ int smu_send_hbm_bad_pages_num(struct smu_context *smu, uint32_t size); int smu_send_hbm_bad_channel_flag(struct smu_context *smu, uint32_t size); int smu_send_rma_reason(struct smu_context *smu); int smu_reset_sdma(struct smu_context *smu, uint32_t inst_mask); +bool smu_reset_sdma_is_supported(struct smu_context *smu); int smu_set_pm_policy(struct smu_context *smu, enum pp_pm_policy p_type, int level); ssize_t smu_get_pm_policy_info(struct smu_context *smu, diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h index 4a1256d29d62..d7505cfc433a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h @@ -38,6 +38,13 @@ #define NUM_SOC_P2S_TABLES 6 #define NUM_GFX_P2S_TABLES 8 #define NUM_PSM_DIDT_THRESHOLDS 3 +#define NUM_XVMIN_VMIN_THRESHOLDS 3 + +#define PRODUCT_MODEL_NUMBER_LEN 20 +#define PRODUCT_NAME_LEN 64 +#define PRODUCT_SERIAL_LEN 20 +#define PRODUCT_MANUFACTURER_NAME_LEN 32 +#define PRODUCT_FRU_ID_LEN 32 typedef enum { /*0*/ FEATURE_DATA_CALCULATION = 0, @@ -85,11 +92,11 @@ typedef enum { //enum for MPIO PCIe gen speed msgs typedef enum { + PCIE_LINK_SPEED_INDEX_TABLE_RESERVED, PCIE_LINK_SPEED_INDEX_TABLE_GEN1, PCIE_LINK_SPEED_INDEX_TABLE_GEN2, PCIE_LINK_SPEED_INDEX_TABLE_GEN3, PCIE_LINK_SPEED_INDEX_TABLE_GEN4, - PCIE_LINK_SPEED_INDEX_TABLE_GEN4_ESM, PCIE_LINK_SPEED_INDEX_TABLE_GEN5, PCIE_LINK_SPEED_INDEX_TABLE_COUNT } PCIE_LINK_SPEED_INDEX_TABLE_e; @@ -126,13 +133,149 @@ typedef enum { GFX_DVM_MARGIN_COUNT } GFX_DVM_MARGIN_e; -#define SMU_VF_METRICS_TABLE_VERSION 0x3 +#define SMU_METRICS_TABLE_VERSION 0x12 + +typedef struct __attribute__((packed, aligned(4))) { + uint64_t AccumulationCounter; + + //TEMPERATURE + uint32_t MaxSocketTemperature; + uint32_t MaxVrTemperature; + uint32_t MaxHbmTemperature; + uint64_t MaxSocketTemperatureAcc; + uint64_t MaxVrTemperatureAcc; + uint64_t MaxHbmTemperatureAcc; + + //POWER + uint32_t SocketPowerLimit; + uint32_t SocketPower; + + //ENERGY + uint64_t Timestamp; + uint64_t SocketEnergyAcc; + uint64_t XcdEnergyAcc; + uint64_t AidEnergyAcc; + uint64_t HbmEnergyAcc; + + //FREQUENCY + uint32_t GfxclkFrequencyLimit; + uint32_t FclkFrequency; + uint32_t UclkFrequency; + uint32_t SocclkFrequency[4]; + uint32_t VclkFrequency[4]; + uint32_t DclkFrequency[4]; + uint32_t LclkFrequency[4]; + uint64_t GfxclkFrequencyAcc[8]; + + //FREQUENCY RANGE + uint32_t MaxLclkDpmRange; + uint32_t MinLclkDpmRange; + + //XGMI + uint32_t XgmiWidth; + uint32_t XgmiBitrate; + uint64_t XgmiReadBandwidthAcc[8]; + uint64_t XgmiWriteBandwidthAcc[8]; + + //ACTIVITY + uint32_t SocketGfxBusy; + uint32_t DramBandwidthUtilization; + uint64_t SocketGfxBusyAcc; + uint64_t DramBandwidthAcc; + uint32_t MaxDramBandwidth; + uint64_t DramBandwidthUtilizationAcc; + uint64_t PcieBandwidthAcc[4]; + + //THROTTLERS + uint32_t ProchotResidencyAcc; + uint32_t PptResidencyAcc; + uint32_t SocketThmResidencyAcc; + uint32_t VrThmResidencyAcc; + uint32_t HbmThmResidencyAcc; + uint32_t GfxLockXCDMak; + + // New Items at end to maintain driver compatibility + uint32_t GfxclkFrequency[8]; + + //XGMI Data tranfser size + uint64_t XgmiReadDataSizeAcc[8];//in KByte + uint64_t XgmiWriteDataSizeAcc[8];//in KByte + + //PCIE BW Data and error count + uint32_t PcieBandwidth[4]; + uint32_t PCIeL0ToRecoveryCountAcc; // The Pcie counter itself is accumulated + uint32_t PCIenReplayAAcc; // The Pcie counter itself is accumulated + uint32_t PCIenReplayARolloverCountAcc; // The Pcie counter itself is accumulated + uint32_t PCIeNAKSentCountAcc; // The Pcie counter itself is accumulated + uint32_t PCIeNAKReceivedCountAcc; // The Pcie counter itself is accumulated + + // VCN/JPEG ACTIVITY + uint32_t VcnBusy[4]; + uint32_t JpegBusy[40]; + + // PCIE LINK Speed and width + uint32_t PCIeLinkSpeed; + uint32_t PCIeLinkWidth; + + // PER XCD ACTIVITY + uint32_t GfxBusy[8]; + uint64_t GfxBusyAcc[8]; + + //PCIE BW Data and error count + uint32_t PCIeOtherEndRecoveryAcc; // The Pcie counter itself is accumulated + + //Total App Clock Counter + uint64_t GfxclkBelowHostLimitPptAcc[8]; + uint64_t GfxclkBelowHostLimitThmAcc[8]; + uint64_t GfxclkBelowHostLimitTotalAcc[8]; + uint64_t GfxclkLowUtilizationAcc[8]; +} MetricsTable_t; + +#define SMU_VF_METRICS_TABLE_MASK (1 << 31) +#define SMU_VF_METRICS_TABLE_VERSION (0x6 | SMU_VF_METRICS_TABLE_MASK) typedef struct __attribute__((packed, aligned(4))) { uint32_t AccumulationCounter; uint32_t InstGfxclk_TargFreq; uint64_t AccGfxclk_TargFreq; uint64_t AccGfxRsmuDpm_Busy; + uint64_t AccGfxclkBelowHostLimitPpt; + uint64_t AccGfxclkBelowHostLimitThm; + uint64_t AccGfxclkBelowHostLimitTotal; + uint64_t AccGfxclkLowUtilization; } VfMetricsTable_t; +/* FRU product information */ +typedef struct __attribute__((packed, aligned(4))) { + uint8_t ModelNumber[PRODUCT_MODEL_NUMBER_LEN]; + uint8_t Name[PRODUCT_NAME_LEN]; + uint8_t Serial[PRODUCT_SERIAL_LEN]; + uint8_t ManufacturerName[PRODUCT_MANUFACTURER_NAME_LEN]; + uint8_t FruId[PRODUCT_FRU_ID_LEN]; +} FRUProductInfo_t; + +#pragma pack(push, 4) +typedef struct { + //FRU PRODUCT INFO + FRUProductInfo_t ProductInfo; + + //POWER + uint32_t MaxSocketPowerLimit; + + //FREQUENCY RANGE + uint32_t MaxGfxclkFrequency; + uint32_t MinGfxclkFrequency; + uint32_t FclkFrequencyTable[4]; + uint32_t UclkFrequencyTable[4]; + uint32_t SocclkFrequencyTable[4]; + uint32_t VclkFrequencyTable[4]; + uint32_t DclkFrequencyTable[4]; + uint32_t LclkFrequencyTable[4]; + + //PSNs + uint64_t PublicSerialNumber_AID[4]; + uint64_t PublicSerialNumber_XCD[8]; +} StaticMetricsTable_t; +#pragma pack(pop) + #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h new file mode 100644 index 000000000000..e1f490b6ce64 --- /dev/null +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h @@ -0,0 +1,143 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ +#ifndef SMU_13_0_12_PPSMC_H +#define SMU_13_0_12_PPSMC_H + +// SMU Response Codes: +#define PPSMC_Result_OK 0x1 +#define PPSMC_Result_Failed 0xFF +#define PPSMC_Result_UnknownCmd 0xFE +#define PPSMC_Result_CmdRejectedPrereq 0xFD +#define PPSMC_Result_CmdRejectedBusy 0xFC + +// Message Definitions: +#define PPSMC_MSG_TestMessage 0x1 +#define PPSMC_MSG_GetSmuVersion 0x2 +#define PPSMC_MSG_GfxDriverReset 0x3 +#define PPSMC_MSG_GetDriverIfVersion 0x4 +#define PPSMC_MSG_EnableAllSmuFeatures 0x5 +#define PPSMC_MSG_DisableAllSmuFeatures 0x6 +#define PPSMC_MSG_RequestI2cTransaction 0x7 +#define PPSMC_MSG_GetMetricsVersion 0x8 +#define PPSMC_MSG_GetMetricsTable 0x9 +#define PPSMC_MSG_GetEccInfoTable 0xA +#define PPSMC_MSG_GetEnabledSmuFeaturesLow 0xB +#define PPSMC_MSG_GetEnabledSmuFeaturesHigh 0xC +#define PPSMC_MSG_SetDriverDramAddrHigh 0xD +#define PPSMC_MSG_SetDriverDramAddrLow 0xE +#define PPSMC_MSG_SetToolsDramAddrHigh 0xF +#define PPSMC_MSG_SetToolsDramAddrLow 0x10 +#define PPSMC_MSG_SetSystemVirtualDramAddrHigh 0x11 +#define PPSMC_MSG_SetSystemVirtualDramAddrLow 0x12 +#define PPSMC_MSG_SetSoftMinByFreq 0x13 +#define PPSMC_MSG_SetSoftMaxByFreq 0x14 +#define PPSMC_MSG_GetMinDpmFreq 0x15 +#define PPSMC_MSG_GetMaxDpmFreq 0x16 +#define PPSMC_MSG_GetDpmFreqByIndex 0x17 +#define PPSMC_MSG_SetPptLimit 0x18 +#define PPSMC_MSG_GetPptLimit 0x19 +#define PPSMC_MSG_DramLogSetDramAddrHigh 0x1A +#define PPSMC_MSG_DramLogSetDramAddrLow 0x1B +#define PPSMC_MSG_DramLogSetDramSize 0x1C +#define PPSMC_MSG_GetDebugData 0x1D +#define PPSMC_MSG_HeavySBR 0x1E +#define PPSMC_MSG_SetNumBadHbmPagesRetired 0x1F +#define PPSMC_MSG_DFCstateControl 0x20 +#define PPSMC_MSG_GetGmiPwrDnHyst 0x21 +#define PPSMC_MSG_SetGmiPwrDnHyst 0x22 +#define PPSMC_MSG_GmiPwrDnControl 0x23 +#define PPSMC_MSG_EnterGfxoff 0x24 +#define PPSMC_MSG_ExitGfxoff 0x25 +#define PPSMC_MSG_EnableDeterminism 0x26 +#define PPSMC_MSG_DisableDeterminism 0x27 +#define PPSMC_MSG_DumpSTBtoDram 0x28 +#define PPSMC_MSG_STBtoDramLogSetDramAddrHigh 0x29 +#define PPSMC_MSG_STBtoDramLogSetDramAddrLow 0x2A +#define PPSMC_MSG_STBtoDramLogSetDramSize 0x2B +#define PPSMC_MSG_SetSystemVirtualSTBtoDramAddrHigh 0x2C +#define PPSMC_MSG_SetSystemVirtualSTBtoDramAddrLow 0x2D +#define PPSMC_MSG_GfxDriverResetRecovery 0x2E +#define PPSMC_MSG_TriggerVFFLR 0x2F +#define PPSMC_MSG_SetSoftMinGfxClk 0x30 +#define PPSMC_MSG_SetSoftMaxGfxClk 0x31 +#define PPSMC_MSG_GetMinGfxDpmFreq 0x32 +#define PPSMC_MSG_GetMaxGfxDpmFreq 0x33 +#define PPSMC_MSG_PrepareForDriverUnload 0x34 +#define PPSMC_MSG_ReadThrottlerLimit 0x35 +#define PPSMC_MSG_QueryValidMcaCount 0x36 +#define PPSMC_MSG_McaBankDumpDW 0x37 +#define PPSMC_MSG_GetCTFLimit 0x38 +#define PPSMC_MSG_ClearMcaOnRead 0x39 +#define PPSMC_MSG_QueryValidMcaCeCount 0x3A +#define PPSMC_MSG_McaBankCeDumpDW 0x3B +#define PPSMC_MSG_SelectPLPDMode 0x40 +#define PPSMC_MSG_PmLogReadSample 0x41 +#define PPSMC_MSG_PmLogGetTableVersion 0x42 +#define PPSMC_MSG_RmaDueToBadPageThreshold 0x43 +#define PPSMC_MSG_SetThrottlingPolicy 0x44 +#define PPSMC_MSG_SetPhaseDetectCSBWThreshold 0x45 +#define PPSMC_MSG_SetPhaseDetectFreqHigh 0x46 +#define PPSMC_MSG_SetPhaseDetectFreqLow 0x47 +#define PPSMC_MSG_SetPhaseDetectDownHysterisis 0x48 +#define PPSMC_MSG_SetPhaseDetectAlphaX1e6 0x49 +#define PPSMC_MSG_SetPhaseDetectOnOff 0x4A +#define PPSMC_MSG_GetPhaseDetectResidency 0x4B +#define PPSMC_MSG_UpdatePccWaitDecMaxStr 0x4C +#define PPSMC_MSG_ResetSDMA 0x4D +#define PPSMC_MSG_GetRasTableVersion 0x4E +#define PPSMC_MSG_GetRmaStatus 0x4F +#define PPSMC_MSG_GetErrorCount 0x50 +#define PPSMC_MSG_GetBadPageCount 0x51 +#define PPSMC_MSG_GetBadPageInfo 0x52 +#define PPSMC_MSG_GetBadPagePaAddrLoHi 0x53 +#define PPSMC_MSG_SetTimestampLoHi 0x54 +#define PPSMC_MSG_GetTimestampLoHi 0x55 +#define PPSMC_MSG_GetRasPolicy 0x56 +#define PPSMC_MSG_DumpErrorRecord 0x57 +#define PPSMC_MSG_EraseRasTable 0x58 +#define PPSMC_MSG_GetStaticMetricsTable 0x59 +#define PPSMC_Message_Count 0x5A + +//PPSMC Reset Types for driver msg argument +#define PPSMC_RESET_TYPE_DRIVER_MODE_1_RESET 0x1 +#define PPSMC_RESET_TYPE_DRIVER_MODE_2_RESET 0x2 +#define PPSMC_RESET_TYPE_DRIVER_MODE_3_RESET 0x3 + +//PPSMC Reset Types for driver msg argument +#define PPSMC_THROTTLING_LIMIT_TYPE_SOCKET 0x1 +#define PPSMC_THROTTLING_LIMIT_TYPE_HBM 0x2 + +//CTF/Throttle Limit types +#define PPSMC_AID_THM_TYPE 0x1 +#define PPSMC_CCD_THM_TYPE 0x2 +#define PPSMC_XCD_THM_TYPE 0x3 +#define PPSMC_HBM_THM_TYPE 0x4 + +//PLPD modes +#define PPSMC_PLPD_MODE_DEFAULT 0x1 +#define PPSMC_PLPD_MODE_OPTIMIZED 0x2 + +typedef uint32_t PPSMC_Result; +typedef uint32_t PPSMC_MSG; + +#endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h index 9ccd5a1986d3..9c8468fb203a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h @@ -276,7 +276,8 @@ __SMU_DUMMY_MAP(SetThrottlingPolicy), \ __SMU_DUMMY_MAP(MALLPowerController), \ __SMU_DUMMY_MAP(MALLPowerState), \ - __SMU_DUMMY_MAP(ResetSDMA), + __SMU_DUMMY_MAP(ResetSDMA), \ + __SMU_DUMMY_MAP(GetStaticMetricsTable), #undef __SMU_DUMMY_MAP #define __SMU_DUMMY_MAP(type) SMU_MSG_##type diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index 31166974746f..cd03caffe317 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -53,6 +53,10 @@ #define SMU_13_VCLK_SHIFT 16 +#define SMUQ10_TO_UINT(x) ((x) >> 10) +#define SMUQ10_FRAC(x) ((x) & 0x3ff) +#define SMUQ10_ROUND(x) ((SMUQ10_TO_UINT(x)) + ((SMUQ10_FRAC(x)) >= 0x200)) + extern const int pmfw_decoded_link_speed[5]; extern const int pmfw_decoded_link_width[7]; @@ -307,6 +311,13 @@ int smu_v13_0_get_boot_freq_by_index(struct smu_context *smu, void smu_v13_0_interrupt_work(struct smu_context *smu); bool smu_v13_0_12_is_dpm_running(struct smu_context *smu); +int smu_v13_0_12_get_max_metrics_size(void); +int smu_v13_0_12_setup_driver_pptable(struct smu_context *smu); +int smu_v13_0_12_get_smu_metrics_data(struct smu_context *smu, + MetricsMember_t member, + uint32_t *value); +ssize_t smu_v13_0_12_get_gpu_metrics(struct smu_context *smu, void **table); extern const struct cmn2asic_mapping smu_v13_0_12_feature_mask_map[]; +extern const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[]; #endif #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 985355bf78b2..898487ad6cd2 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -3234,4 +3234,9 @@ void smu_v13_0_0_set_ppt_funcs(struct smu_context *smu) smu->workload_map = smu_v13_0_0_workload_map; smu->smc_driver_if_version = SMU13_0_0_DRIVER_IF_VERSION; smu_v13_0_0_set_smu_mailbox_registers(smu); + + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == + IP_VERSION(13, 0, 10) && + !amdgpu_device_has_display_hardware(smu->adev)) + smu->adev->pm.pp_feature &= ~PP_GFXOFF_MASK; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c index 86852e738837..285dbfe10303 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c @@ -28,8 +28,10 @@ #include "amdgpu_smu.h" #include "smu_v13_0_12_pmfw.h" #include "smu_v13_0_6_ppt.h" +#include "smu_v13_0_12_ppsmc.h" #include "smu_v13_0.h" #include "amdgpu_xgmi.h" +#include "amdgpu_fru_eeprom.h" #include <linux/pci.h> #include "smu_cmn.h" @@ -54,6 +56,10 @@ (FEATURE_MASK(FEATURE_DATA_CALCULATION) | \ FEATURE_MASK(FEATURE_DPM_GFXCLK) | FEATURE_MASK(FEATURE_DPM_FCLK)) +#define NUM_JPEG_RINGS_FW 10 +#define NUM_JPEG_RINGS_GPU_METRICS(gpu_metrics) \ + (ARRAY_SIZE(gpu_metrics->xcp_stats[0].jpeg_busy) / 4) + const struct cmn2asic_mapping smu_v13_0_12_feature_mask_map[SMU_FEATURE_COUNT] = { SMU_13_0_12_FEA_MAP(SMU_FEATURE_DATA_CALCULATIONS_BIT, FEATURE_DATA_CALCULATION), SMU_13_0_12_FEA_MAP(SMU_FEATURE_DPM_GFXCLK_BIT, FEATURE_DPM_GFXCLK), @@ -72,6 +78,63 @@ const struct cmn2asic_mapping smu_v13_0_12_feature_mask_map[SMU_FEATURE_COUNT] = SMU_13_0_12_FEA_MAP(SMU_FEATURE_XGMI_PER_LINK_PWR_DWN_BIT, FEATURE_XGMI_PER_LINK_PWR_DOWN), }; +// clang-format off +const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[SMU_MSG_MAX_COUNT] = { + MSG_MAP(TestMessage, PPSMC_MSG_TestMessage, 0), + MSG_MAP(GetSmuVersion, PPSMC_MSG_GetSmuVersion, 1), + MSG_MAP(GetDriverIfVersion, PPSMC_MSG_GetDriverIfVersion, 1), + MSG_MAP(EnableAllSmuFeatures, PPSMC_MSG_EnableAllSmuFeatures, 0), + MSG_MAP(DisableAllSmuFeatures, PPSMC_MSG_DisableAllSmuFeatures, 0), + MSG_MAP(RequestI2cTransaction, PPSMC_MSG_RequestI2cTransaction, 0), + MSG_MAP(GetMetricsTable, PPSMC_MSG_GetMetricsTable, 1), + MSG_MAP(GetMetricsVersion, PPSMC_MSG_GetMetricsVersion, 1), + MSG_MAP(GetEnabledSmuFeaturesHigh, PPSMC_MSG_GetEnabledSmuFeaturesHigh, 1), + MSG_MAP(GetEnabledSmuFeaturesLow, PPSMC_MSG_GetEnabledSmuFeaturesLow, 1), + MSG_MAP(SetDriverDramAddrHigh, PPSMC_MSG_SetDriverDramAddrHigh, 1), + MSG_MAP(SetDriverDramAddrLow, PPSMC_MSG_SetDriverDramAddrLow, 1), + MSG_MAP(SetToolsDramAddrHigh, PPSMC_MSG_SetToolsDramAddrHigh, 0), + MSG_MAP(SetToolsDramAddrLow, PPSMC_MSG_SetToolsDramAddrLow, 0), + MSG_MAP(SetSoftMinByFreq, PPSMC_MSG_SetSoftMinByFreq, 0), + MSG_MAP(SetSoftMaxByFreq, PPSMC_MSG_SetSoftMaxByFreq, 1), + MSG_MAP(GetMinDpmFreq, PPSMC_MSG_GetMinDpmFreq, 1), + MSG_MAP(GetMaxDpmFreq, PPSMC_MSG_GetMaxDpmFreq, 1), + MSG_MAP(GetDpmFreqByIndex, PPSMC_MSG_GetDpmFreqByIndex, 1), + MSG_MAP(SetPptLimit, PPSMC_MSG_SetPptLimit, 0), + MSG_MAP(GetPptLimit, PPSMC_MSG_GetPptLimit, 1), + MSG_MAP(GfxDeviceDriverReset, PPSMC_MSG_GfxDriverReset, SMU_MSG_RAS_PRI), + MSG_MAP(DramLogSetDramAddrHigh, PPSMC_MSG_DramLogSetDramAddrHigh, 0), + MSG_MAP(DramLogSetDramAddrLow, PPSMC_MSG_DramLogSetDramAddrLow, 0), + MSG_MAP(DramLogSetDramSize, PPSMC_MSG_DramLogSetDramSize, 0), + MSG_MAP(GetDebugData, PPSMC_MSG_GetDebugData, 0), + MSG_MAP(SetNumBadHbmPagesRetired, PPSMC_MSG_SetNumBadHbmPagesRetired, 0), + MSG_MAP(DFCstateControl, PPSMC_MSG_DFCstateControl, 0), + MSG_MAP(GetGmiPwrDnHyst, PPSMC_MSG_GetGmiPwrDnHyst, 0), + MSG_MAP(SetGmiPwrDnHyst, PPSMC_MSG_SetGmiPwrDnHyst, 0), + MSG_MAP(GmiPwrDnControl, PPSMC_MSG_GmiPwrDnControl, 0), + MSG_MAP(EnterGfxoff, PPSMC_MSG_EnterGfxoff, 0), + MSG_MAP(ExitGfxoff, PPSMC_MSG_ExitGfxoff, 0), + MSG_MAP(EnableDeterminism, PPSMC_MSG_EnableDeterminism, 0), + MSG_MAP(DisableDeterminism, PPSMC_MSG_DisableDeterminism, 0), + MSG_MAP(GfxDriverResetRecovery, PPSMC_MSG_GfxDriverResetRecovery, 0), + MSG_MAP(GetMinGfxclkFrequency, PPSMC_MSG_GetMinGfxDpmFreq, 1), + MSG_MAP(GetMaxGfxclkFrequency, PPSMC_MSG_GetMaxGfxDpmFreq, 1), + MSG_MAP(SetSoftMinGfxclk, PPSMC_MSG_SetSoftMinGfxClk, 1), + MSG_MAP(SetSoftMaxGfxClk, PPSMC_MSG_SetSoftMaxGfxClk, 1), + MSG_MAP(PrepareMp1ForUnload, PPSMC_MSG_PrepareForDriverUnload, 0), + MSG_MAP(GetCTFLimit, PPSMC_MSG_GetCTFLimit, 0), + MSG_MAP(GetThermalLimit, PPSMC_MSG_ReadThrottlerLimit, 0), + MSG_MAP(ClearMcaOnRead, PPSMC_MSG_ClearMcaOnRead, 0), + MSG_MAP(QueryValidMcaCount, PPSMC_MSG_QueryValidMcaCount, SMU_MSG_RAS_PRI), + MSG_MAP(QueryValidMcaCeCount, PPSMC_MSG_QueryValidMcaCeCount, SMU_MSG_RAS_PRI), + MSG_MAP(McaBankDumpDW, PPSMC_MSG_McaBankDumpDW, SMU_MSG_RAS_PRI), + MSG_MAP(McaBankCeDumpDW, PPSMC_MSG_McaBankCeDumpDW, SMU_MSG_RAS_PRI), + MSG_MAP(SelectPLPDMode, PPSMC_MSG_SelectPLPDMode, 0), + MSG_MAP(RmaDueToBadPageThreshold, PPSMC_MSG_RmaDueToBadPageThreshold, 0), + MSG_MAP(SetThrottlingPolicy, PPSMC_MSG_SetThrottlingPolicy, 0), + MSG_MAP(ResetSDMA, PPSMC_MSG_ResetSDMA, 0), + MSG_MAP(GetStaticMetricsTable, PPSMC_MSG_GetStaticMetricsTable, 1), +}; + static int smu_v13_0_12_get_enabled_mask(struct smu_context *smu, uint64_t *feature_mask) { @@ -87,6 +150,114 @@ static int smu_v13_0_12_get_enabled_mask(struct smu_context *smu, return ret; } +static int smu_v13_0_12_fru_get_product_info(struct smu_context *smu, + StaticMetricsTable_t *static_metrics) +{ + struct amdgpu_fru_info *fru_info; + struct amdgpu_device *adev = smu->adev; + + if (!adev->fru_info) { + adev->fru_info = kzalloc(sizeof(*adev->fru_info), GFP_KERNEL); + if (!adev->fru_info) + return -ENOMEM; + } + + fru_info = adev->fru_info; + strscpy(fru_info->product_number, static_metrics->ProductInfo.ModelNumber, + sizeof(fru_info->product_number)); + strscpy(fru_info->product_name, static_metrics->ProductInfo.Name, + sizeof(fru_info->product_name)); + strscpy(fru_info->serial, static_metrics->ProductInfo.Serial, + sizeof(fru_info->serial)); + strscpy(fru_info->manufacturer_name, static_metrics->ProductInfo.ManufacturerName, + sizeof(fru_info->manufacturer_name)); + strscpy(fru_info->fru_id, static_metrics->ProductInfo.FruId, + sizeof(fru_info->fru_id)); + + return 0; +} + +int smu_v13_0_12_get_max_metrics_size(void) +{ + return max(sizeof(StaticMetricsTable_t), sizeof(MetricsTable_t)); +} + +static int smu_v13_0_12_get_static_metrics_table(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + uint32_t table_size = smu_table->tables[SMU_TABLE_SMU_METRICS].size; + struct smu_table *table = &smu_table->driver_table; + int ret; + + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GetStaticMetricsTable, NULL); + if (ret) { + dev_info(smu->adev->dev, + "Failed to export static metrics table!\n"); + return ret; + } + + amdgpu_asic_invalidate_hdp(smu->adev, NULL); + memcpy(smu_table->metrics_table, table->cpu_addr, table_size); + + return 0; +} + +int smu_v13_0_12_setup_driver_pptable(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + StaticMetricsTable_t *static_metrics = (StaticMetricsTable_t *)smu_table->metrics_table; + struct PPTable_t *pptable = + (struct PPTable_t *)smu_table->driver_pptable; + uint32_t table_version; + int ret, i; + + if (!pptable->Init) { + ret = smu_v13_0_12_get_static_metrics_table(smu); + if (ret) + return ret; + + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GetMetricsVersion, + &table_version); + if (ret) + return ret; + smu_table->tables[SMU_TABLE_SMU_METRICS].version = + table_version; + + pptable->MaxSocketPowerLimit = + SMUQ10_ROUND(static_metrics->MaxSocketPowerLimit); + pptable->MaxGfxclkFrequency = + SMUQ10_ROUND(static_metrics->MaxGfxclkFrequency); + pptable->MinGfxclkFrequency = + SMUQ10_ROUND(static_metrics->MinGfxclkFrequency); + + for (i = 0; i < 4; ++i) { + pptable->FclkFrequencyTable[i] = + SMUQ10_ROUND(static_metrics->FclkFrequencyTable[i]); + pptable->UclkFrequencyTable[i] = + SMUQ10_ROUND(static_metrics->UclkFrequencyTable[i]); + pptable->SocclkFrequencyTable[i] = + SMUQ10_ROUND(static_metrics->SocclkFrequencyTable[i]); + pptable->VclkFrequencyTable[i] = + SMUQ10_ROUND(static_metrics->VclkFrequencyTable[i]); + pptable->DclkFrequencyTable[i] = + SMUQ10_ROUND(static_metrics->DclkFrequencyTable[i]); + pptable->LclkFrequencyTable[i] = + SMUQ10_ROUND(static_metrics->LclkFrequencyTable[i]); + } + + /* use AID0 serial number by default */ + pptable->PublicSerialNumber_AID = + static_metrics->PublicSerialNumber_AID[0]; + ret = smu_v13_0_12_fru_get_product_info(smu, static_metrics); + if (ret) + return ret; + + pptable->Init = true; + } + + return 0; +} + bool smu_v13_0_12_is_dpm_running(struct smu_context *smu) { int ret; @@ -99,3 +270,216 @@ bool smu_v13_0_12_is_dpm_running(struct smu_context *smu) return !!(feature_enabled & SMC_DPM_FEATURE); } + +int smu_v13_0_12_get_smu_metrics_data(struct smu_context *smu, + MetricsMember_t member, + uint32_t *value) +{ + struct smu_table_context *smu_table = &smu->smu_table; + MetricsTable_t *metrics = (MetricsTable_t *)smu_table->metrics_table; + struct amdgpu_device *adev = smu->adev; + int ret = 0; + int xcc_id; + + /* For clocks with multiple instances, only report the first one */ + switch (member) { + case METRICS_CURR_GFXCLK: + case METRICS_AVERAGE_GFXCLK: + xcc_id = GET_INST(GC, 0); + *value = SMUQ10_ROUND(metrics->GfxclkFrequency[xcc_id]); + break; + case METRICS_CURR_SOCCLK: + case METRICS_AVERAGE_SOCCLK: + *value = SMUQ10_ROUND(metrics->SocclkFrequency[0]); + break; + case METRICS_CURR_UCLK: + case METRICS_AVERAGE_UCLK: + *value = SMUQ10_ROUND(metrics->UclkFrequency); + break; + case METRICS_CURR_VCLK: + *value = SMUQ10_ROUND(metrics->VclkFrequency[0]); + break; + case METRICS_CURR_DCLK: + *value = SMUQ10_ROUND(metrics->DclkFrequency[0]); + break; + case METRICS_CURR_FCLK: + *value = SMUQ10_ROUND(metrics->FclkFrequency); + break; + case METRICS_AVERAGE_GFXACTIVITY: + *value = SMUQ10_ROUND(metrics->SocketGfxBusy); + break; + case METRICS_AVERAGE_MEMACTIVITY: + *value = SMUQ10_ROUND(metrics->DramBandwidthUtilization); + break; + case METRICS_CURR_SOCKETPOWER: + *value = SMUQ10_ROUND(metrics->SocketPower) << 8; + break; + case METRICS_TEMPERATURE_HOTSPOT: + *value = SMUQ10_ROUND(metrics->MaxSocketTemperature) * + SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + break; + case METRICS_TEMPERATURE_MEM: + *value = SMUQ10_ROUND(metrics->MaxHbmTemperature) * + SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + break; + /* This is the max of all VRs and not just SOC VR. + * No need to define another data type for the same. + */ + case METRICS_TEMPERATURE_VRSOC: + *value = SMUQ10_ROUND(metrics->MaxVrTemperature) * + SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + break; + default: + *value = UINT_MAX; + break; + } + + return ret; +} + +ssize_t smu_v13_0_12_get_gpu_metrics(struct smu_context *smu, void **table) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct gpu_metrics_v1_7 *gpu_metrics = + (struct gpu_metrics_v1_7 *)smu_table->gpu_metrics_table; + int ret = 0, xcc_id, inst, i, j, k, idx; + struct amdgpu_device *adev = smu->adev; + u8 num_jpeg_rings_gpu_metrics; + MetricsTable_t *metrics; + struct amdgpu_xcp *xcp; + u32 inst_mask; + + metrics = kzalloc(sizeof(MetricsTable_t), GFP_KERNEL); + memcpy(metrics, smu_table->metrics_table, sizeof(MetricsTable_t)); + + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 7); + + gpu_metrics->temperature_hotspot = + SMUQ10_ROUND(metrics->MaxSocketTemperature); + /* Individual HBM stack temperature is not reported */ + gpu_metrics->temperature_mem = + SMUQ10_ROUND(metrics->MaxHbmTemperature); + /* Reports max temperature of all voltage rails */ + gpu_metrics->temperature_vrsoc = + SMUQ10_ROUND(metrics->MaxVrTemperature); + + gpu_metrics->average_gfx_activity = + SMUQ10_ROUND(metrics->SocketGfxBusy); + gpu_metrics->average_umc_activity = + SMUQ10_ROUND(metrics->DramBandwidthUtilization); + + gpu_metrics->mem_max_bandwidth = + SMUQ10_ROUND(metrics->MaxDramBandwidth); + + gpu_metrics->curr_socket_power = + SMUQ10_ROUND(metrics->SocketPower); + /* Energy counter reported in 15.259uJ (2^-16) units */ + gpu_metrics->energy_accumulator = metrics->SocketEnergyAcc; + + for (i = 0; i < MAX_GFX_CLKS; i++) { + xcc_id = GET_INST(GC, i); + if (xcc_id >= 0) + gpu_metrics->current_gfxclk[i] = + SMUQ10_ROUND(metrics->GfxclkFrequency[xcc_id]); + + if (i < MAX_CLKS) { + gpu_metrics->current_socclk[i] = + SMUQ10_ROUND(metrics->SocclkFrequency[i]); + inst = GET_INST(VCN, i); + if (inst >= 0) { + gpu_metrics->current_vclk0[i] = + SMUQ10_ROUND(metrics->VclkFrequency[inst]); + gpu_metrics->current_dclk0[i] = + SMUQ10_ROUND(metrics->DclkFrequency[inst]); + } + } + } + + gpu_metrics->current_uclk = SMUQ10_ROUND(metrics->UclkFrequency); + + /* Total accumulated cycle counter */ + gpu_metrics->accumulation_counter = metrics->AccumulationCounter; + + /* Accumulated throttler residencies */ + gpu_metrics->prochot_residency_acc = metrics->ProchotResidencyAcc; + gpu_metrics->ppt_residency_acc = metrics->PptResidencyAcc; + gpu_metrics->socket_thm_residency_acc = metrics->SocketThmResidencyAcc; + gpu_metrics->vr_thm_residency_acc = metrics->VrThmResidencyAcc; + gpu_metrics->hbm_thm_residency_acc = metrics->HbmThmResidencyAcc; + + /* Clock Lock Status. Each bit corresponds to each GFXCLK instance */ + gpu_metrics->gfxclk_lock_status = metrics->GfxLockXCDMak >> GET_INST(GC, 0); + + gpu_metrics->pcie_link_width = metrics->PCIeLinkWidth; + gpu_metrics->pcie_link_speed = + pcie_gen_to_speed(metrics->PCIeLinkSpeed); + gpu_metrics->pcie_bandwidth_acc = + SMUQ10_ROUND(metrics->PcieBandwidthAcc[0]); + gpu_metrics->pcie_bandwidth_inst = + SMUQ10_ROUND(metrics->PcieBandwidth[0]); + gpu_metrics->pcie_l0_to_recov_count_acc = metrics->PCIeL0ToRecoveryCountAcc; + gpu_metrics->pcie_replay_count_acc = metrics->PCIenReplayAAcc; + gpu_metrics->pcie_replay_rover_count_acc = + metrics->PCIenReplayARolloverCountAcc; + gpu_metrics->pcie_nak_sent_count_acc = metrics->PCIeNAKSentCountAcc; + gpu_metrics->pcie_nak_rcvd_count_acc = metrics->PCIeNAKReceivedCountAcc; + gpu_metrics->pcie_lc_perf_other_end_recovery = metrics->PCIeOtherEndRecoveryAcc; + + gpu_metrics->system_clock_counter = ktime_get_boottime_ns(); + + gpu_metrics->gfx_activity_acc = SMUQ10_ROUND(metrics->SocketGfxBusyAcc); + gpu_metrics->mem_activity_acc = SMUQ10_ROUND(metrics->DramBandwidthUtilizationAcc); + + for (i = 0; i < NUM_XGMI_LINKS; i++) { + gpu_metrics->xgmi_read_data_acc[i] = + SMUQ10_ROUND(metrics->XgmiReadDataSizeAcc[i]); + gpu_metrics->xgmi_write_data_acc[i] = + SMUQ10_ROUND(metrics->XgmiWriteDataSizeAcc[i]); + ret = amdgpu_get_xgmi_link_status(adev, i); + if (ret >= 0) + gpu_metrics->xgmi_link_status[i] = ret; + } + + gpu_metrics->num_partition = adev->xcp_mgr->num_xcps; + + num_jpeg_rings_gpu_metrics = NUM_JPEG_RINGS_GPU_METRICS(gpu_metrics); + for_each_xcp(adev->xcp_mgr, xcp, i) { + amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_VCN, &inst_mask); + idx = 0; + for_each_inst(k, inst_mask) { + /* Both JPEG and VCN has same instances */ + inst = GET_INST(VCN, k); + + for (j = 0; j < num_jpeg_rings_gpu_metrics; ++j) { + gpu_metrics->xcp_stats[i].jpeg_busy + [(idx * num_jpeg_rings_gpu_metrics) + j] = + SMUQ10_ROUND(metrics->JpegBusy + [(inst * NUM_JPEG_RINGS_FW) + j]); + } + gpu_metrics->xcp_stats[i].vcn_busy[idx] = + SMUQ10_ROUND(metrics->VcnBusy[inst]); + idx++; + } + + amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_GFX, &inst_mask); + idx = 0; + for_each_inst(k, inst_mask) { + inst = GET_INST(GC, k); + gpu_metrics->xcp_stats[i].gfx_busy_inst[idx] = + SMUQ10_ROUND(metrics->GfxBusy[inst]); + gpu_metrics->xcp_stats[i].gfx_busy_acc[idx] = + SMUQ10_ROUND(metrics->GfxBusyAcc[inst]); + idx++; + } + } + + gpu_metrics->xgmi_link_width = SMUQ10_ROUND(metrics->XgmiWidth); + gpu_metrics->xgmi_link_speed = SMUQ10_ROUND(metrics->XgmiBitrate); + + gpu_metrics->firmware_timestamp = metrics->Timestamp; + + *table = (void *)gpu_metrics; + kfree(metrics); + + return sizeof(*gpu_metrics); +} diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 9f2de69f53b2..1e1d8989c77a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -116,6 +116,7 @@ enum smu_v13_0_6_caps { SMU_CAP(RMA_MSG), SMU_CAP(ACA_SYND), SMU_CAP(SDMA_RESET), + SMU_CAP(STATIC_METRICS), SMU_CAP(ALL), }; @@ -252,25 +253,6 @@ static const uint8_t smu_v13_0_6_throttler_map[] = { [THROTTLER_PROCHOT_BIT] = (SMU_THROTTLER_PROCHOT_GFX_BIT), }; -struct PPTable_t { - uint32_t MaxSocketPowerLimit; - uint32_t MaxGfxclkFrequency; - uint32_t MinGfxclkFrequency; - uint32_t FclkFrequencyTable[4]; - uint32_t UclkFrequencyTable[4]; - uint32_t SocclkFrequencyTable[4]; - uint32_t VclkFrequencyTable[4]; - uint32_t DclkFrequencyTable[4]; - uint32_t LclkFrequencyTable[4]; - uint32_t MaxLclkDpmRange; - uint32_t MinLclkDpmRange; - uint64_t PublicSerialNumber_AID; - bool Init; -}; - -#define SMUQ10_TO_UINT(x) ((x) >> 10) -#define SMUQ10_FRAC(x) ((x) & 0x3ff) -#define SMUQ10_ROUND(x) ((SMUQ10_TO_UINT(x)) + ((SMUQ10_FRAC(x)) >= 0x200)) #define GET_GPU_METRIC_FIELD(field, version) ((version == METRICS_VERSION_V0) ?\ (metrics_v0->field) : (metrics_v2->field)) #define GET_METRIC_FIELD(field, version) ((version == METRICS_VERSION_V1) ?\ @@ -368,6 +350,9 @@ static void smu_v13_0_12_init_caps(struct smu_context *smu) if (fw_ver >= 0x00561700) smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET)); + + if (fw_ver >= 0x00561E00) + smu_v13_0_6_cap_set(smu, SMU_CAP(STATIC_METRICS)); } static void smu_v13_0_6_init_caps(struct smu_context *smu) @@ -523,13 +508,15 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu) struct smu_table_context *smu_table = &smu->smu_table; struct smu_table *tables = smu_table->tables; struct amdgpu_device *adev = smu->adev; + int gpu_metrcs_size = METRICS_TABLE_SIZE; if (!(adev->flags & AMD_IS_APU)) SMU_TABLE_INIT(tables, SMU_TABLE_PMSTATUSLOG, SMU13_TOOL_SIZE, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, - METRICS_TABLE_SIZE, + max(gpu_metrcs_size, + smu_v13_0_12_get_max_metrics_size()), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT); @@ -776,6 +763,9 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu) int ret, i, retry = 100; uint32_t table_version; + if (smu_v13_0_6_cap_supported(smu, SMU_CAP(STATIC_METRICS))) + return smu_v13_0_12_setup_driver_pptable(smu); + /* Store one-time values in driver PPTable */ if (!pptable->Init) { while (--retry) { @@ -1156,6 +1146,9 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu, if (ret) return ret; + if (smu_v13_0_6_cap_supported(smu, SMU_CAP(STATIC_METRICS))) + return smu_v13_0_12_get_smu_metrics_data(smu, member, value); + /* For clocks with multiple instances, only report the first one */ switch (member) { case METRICS_CURR_GFXCLK: @@ -1947,7 +1940,7 @@ static int smu_v13_0_6_set_performance_level(struct smu_context *smu, break; } - return -EINVAL; + return -EOPNOTSUPP; } static int smu_v13_0_6_set_soft_freq_limited_range(struct smu_context *smu, @@ -2518,6 +2511,9 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table return ret; } + if (smu_v13_0_6_cap_supported(smu, SMU_CAP(STATIC_METRICS))) + return smu_v13_0_12_get_gpu_metrics(smu, table); + metrics_v1 = (MetricsTableV1_t *)metrics_v0; metrics_v2 = (MetricsTableV2_t *)metrics_v0; @@ -2902,11 +2898,31 @@ static int smu_v13_0_6_send_rma_reason(struct smu_context *smu) return ret; } +/** + * smu_v13_0_6_reset_sdma_is_supported - Check if SDMA reset is supported + * @smu: smu_context pointer + * + * This function checks if the SMU supports resetting the SDMA engine. + * It returns false if the capability is not supported. + */ +static bool smu_v13_0_6_reset_sdma_is_supported(struct smu_context *smu) +{ + bool ret = true; + + if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(SDMA_RESET))) { + dev_info(smu->adev->dev, + "SDMA reset capability is not supported\n"); + ret = false; + } + + return ret; +} + static int smu_v13_0_6_reset_sdma(struct smu_context *smu, uint32_t inst_mask) { int ret = 0; - if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(SDMA_RESET))) + if (!smu_v13_0_6_reset_sdma_is_supported(smu)) return -EOPNOTSUPP; ret = smu_cmn_send_smc_msg_with_param(smu, @@ -3590,12 +3606,14 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = { .send_hbm_bad_pages_num = smu_v13_0_6_smu_send_hbm_bad_page_num, .send_rma_reason = smu_v13_0_6_send_rma_reason, .reset_sdma = smu_v13_0_6_reset_sdma, + .reset_sdma_is_supported = smu_v13_0_6_reset_sdma_is_supported, }; void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu) { smu->ppt_funcs = &smu_v13_0_6_ppt_funcs; - smu->message_map = smu_v13_0_6_message_map; + smu->message_map = (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 12)) ? + smu_v13_0_12_message_map : smu_v13_0_6_message_map; smu->clock_map = smu_v13_0_6_clk_map; smu->feature_map = (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 12)) ? smu_v13_0_12_feature_mask_map : smu_v13_0_6_feature_mask_map; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h index 717fe669882e..83745909e564 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h @@ -35,6 +35,22 @@ typedef enum { /*3*/ NUM_METRICS = 3 } METRICS_LIST_e; +struct PPTable_t { + uint32_t MaxSocketPowerLimit; + uint32_t MaxGfxclkFrequency; + uint32_t MinGfxclkFrequency; + uint32_t FclkFrequencyTable[4]; + uint32_t UclkFrequencyTable[4]; + uint32_t SocclkFrequencyTable[4]; + uint32_t VclkFrequencyTable[4]; + uint32_t DclkFrequencyTable[4]; + uint32_t LclkFrequencyTable[4]; + uint32_t MaxLclkDpmRange; + uint32_t MinLclkDpmRange; + uint64_t PublicSerialNumber_AID; + bool Init; +}; + extern void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu); #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c index adbb6332376e..76c1adda83db 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c @@ -950,6 +950,14 @@ static int smu_v14_0_irq_process(struct amdgpu_device *adev, uint32_t client_id = entry->client_id; uint32_t src_id = entry->src_id; + /* + * ctxid is used to distinguish different + * events for SMCToHost interrupt. + */ + uint32_t ctxid = entry->src_data[0]; + uint32_t data; + uint32_t high; + if (client_id == SOC15_IH_CLIENTID_THM) { switch (src_id) { case THM_11_0__SRCID__THM_DIG_THERM_L2H: @@ -964,6 +972,50 @@ static int smu_v14_0_irq_process(struct amdgpu_device *adev, src_id); break; } + } else if (client_id == SOC15_IH_CLIENTID_MP1) { + if (src_id == SMU_IH_INTERRUPT_ID_TO_DRIVER) { + /* ACK SMUToHost interrupt */ + data = RREG32_SOC15(MP1, 0, regMP1_SMN_IH_SW_INT_CTRL); + data = REG_SET_FIELD(data, MP1_SMN_IH_SW_INT_CTRL, INT_ACK, 1); + WREG32_SOC15(MP1, 0, regMP1_SMN_IH_SW_INT_CTRL, data); + + switch (ctxid) { + case SMU_IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL: + high = smu->thermal_range.software_shutdown_temp + + smu->thermal_range.software_shutdown_temp_offset; + high = min_t(typeof(high), + SMU_THERMAL_MAXIMUM_ALERT_TEMP, + high); + dev_emerg(adev->dev, "Reduce soft CTF limit to %d (by an offset %d)\n", + high, + smu->thermal_range.software_shutdown_temp_offset); + + data = RREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL); + data = REG_SET_FIELD(data, THM_THERMAL_INT_CTRL, + DIG_THERM_INTH, + (high & 0xff)); + data = data & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); + WREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL, data); + break; + case SMU_IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY: + high = min_t(typeof(high), + SMU_THERMAL_MAXIMUM_ALERT_TEMP, + smu->thermal_range.software_shutdown_temp); + dev_emerg(adev->dev, "Recover soft CTF limit to %d\n", high); + + data = RREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL); + data = REG_SET_FIELD(data, THM_THERMAL_INT_CTRL, + DIG_THERM_INTH, + (high & 0xff)); + data = data & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); + WREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL, data); + break; + default: + dev_dbg(adev->dev, "Unhandled context id %d from client:%d!\n", + ctxid, client_id); + break; + } + } } return 0; @@ -1897,16 +1949,6 @@ static int smu_v14_0_allow_ih_interrupt(struct smu_context *smu) NULL); } -static int smu_v14_0_process_pending_interrupt(struct smu_context *smu) -{ - int ret = 0; - - if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_ACDC_BIT)) - ret = smu_v14_0_allow_ih_interrupt(smu); - - return ret; -} - int smu_v14_0_enable_thermal_alert(struct smu_context *smu) { int ret = 0; @@ -1918,7 +1960,7 @@ int smu_v14_0_enable_thermal_alert(struct smu_context *smu) if (ret) return ret; - return smu_v14_0_process_pending_interrupt(smu); + return smu_v14_0_allow_ih_interrupt(smu); } int smu_v14_0_disable_thermal_alert(struct smu_context *smu) diff --git a/drivers/gpu/drm/drm_client_event.c b/drivers/gpu/drm/drm_client_event.c index e303de564485..bd93cd93d519 100644 --- a/drivers/gpu/drm/drm_client_event.c +++ b/drivers/gpu/drm/drm_client_event.c @@ -49,6 +49,29 @@ void drm_client_dev_unregister(struct drm_device *dev) } EXPORT_SYMBOL(drm_client_dev_unregister); +static void drm_client_hotplug(struct drm_client_dev *client) +{ + struct drm_device *dev = client->dev; + int ret; + + if (!client->funcs || !client->funcs->hotplug) + return; + + if (client->hotplug_failed) + return; + + if (client->suspended) { + client->hotplug_pending = true; + return; + } + + client->hotplug_pending = false; + ret = client->funcs->hotplug(client); + drm_dbg_kms(dev, "%s: ret=%d\n", client->name, ret); + if (ret) + client->hotplug_failed = true; +} + /** * drm_client_dev_hotplug - Send hotplug event to clients * @dev: DRM device @@ -61,7 +84,6 @@ EXPORT_SYMBOL(drm_client_dev_unregister); void drm_client_dev_hotplug(struct drm_device *dev) { struct drm_client_dev *client; - int ret; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return; @@ -72,18 +94,8 @@ void drm_client_dev_hotplug(struct drm_device *dev) } mutex_lock(&dev->clientlist_mutex); - list_for_each_entry(client, &dev->clientlist, list) { - if (!client->funcs || !client->funcs->hotplug) - continue; - - if (client->hotplug_failed) - continue; - - ret = client->funcs->hotplug(client); - drm_dbg_kms(dev, "%s: ret=%d\n", client->name, ret); - if (ret) - client->hotplug_failed = true; - } + list_for_each_entry(client, &dev->clientlist, list) + drm_client_hotplug(client); mutex_unlock(&dev->clientlist_mutex); } EXPORT_SYMBOL(drm_client_dev_hotplug); @@ -153,6 +165,9 @@ static int drm_client_resume(struct drm_client_dev *client, bool holds_console_l client->suspended = false; + if (client->hotplug_pending) + drm_client_hotplug(client); + return ret; } diff --git a/drivers/gpu/drm/drm_damage_helper.c b/drivers/gpu/drm/drm_damage_helper.c index afb02aae707b..44a5a36806e3 100644 --- a/drivers/gpu/drm/drm_damage_helper.c +++ b/drivers/gpu/drm/drm_damage_helper.c @@ -308,7 +308,7 @@ EXPORT_SYMBOL(drm_atomic_helper_damage_iter_next); * True if there is valid plane damage otherwise false. */ bool drm_atomic_helper_damage_merged(const struct drm_plane_state *old_state, - struct drm_plane_state *state, + const struct drm_plane_state *state, struct drm_rect *rect) { struct drm_atomic_helper_damage_iter iter; diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index fb3614a7ba44..937c3939e502 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -245,6 +245,9 @@ __drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper, if (do_delayed) drm_fb_helper_hotplug_event(fb_helper); + if (fb_helper->funcs->fb_restore) + fb_helper->funcs->fb_restore(fb_helper); + return ret; } @@ -754,7 +757,12 @@ EXPORT_SYMBOL(drm_fb_helper_deferred_io); */ void drm_fb_helper_set_suspend(struct drm_fb_helper *fb_helper, bool suspend) { - if (fb_helper && fb_helper->info) + if (!fb_helper || !fb_helper->info) + return; + + if (fb_helper->funcs->fb_set_suspend) + fb_helper->funcs->fb_set_suspend(fb_helper, suspend); + else fb_set_suspend(fb_helper->info, suspend); } EXPORT_SYMBOL(drm_fb_helper_set_suspend); @@ -800,7 +808,7 @@ void drm_fb_helper_set_suspend_unlocked(struct drm_fb_helper *fb_helper, } } - fb_set_suspend(fb_helper->info, suspend); + drm_fb_helper_set_suspend(fb_helper, suspend); console_unlock(); } EXPORT_SYMBOL(drm_fb_helper_set_suspend_unlocked); @@ -1626,6 +1634,9 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper) struct fb_info *info; int ret; + if (drm_WARN_ON(dev, !dev->driver->fbdev_probe)) + return -EINVAL; + ret = drm_fb_helper_find_sizes(fb_helper, &sizes); if (ret) { /* First time: disable all crtc's.. */ @@ -1635,10 +1646,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper) } /* push down into drivers */ - if (dev->driver->fbdev_probe) - ret = dev->driver->fbdev_probe(fb_helper, &sizes); - else if (fb_helper->funcs) - ret = fb_helper->funcs->fb_probe(fb_helper, &sizes); + ret = dev->driver->fbdev_probe(fb_helper, &sizes); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c index b14b581c059d..02a516e77192 100644 --- a/drivers/gpu/drm/drm_fbdev_dma.c +++ b/drivers/gpu/drm/drm_fbdev_dma.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: MIT #include <linux/fb.h> +#include <linux/vmalloc.h> #include <drm/drm_drv.h> #include <drm/drm_fbdev_dma.h> @@ -70,37 +71,102 @@ static const struct fb_ops drm_fbdev_dma_fb_ops = { .fb_destroy = drm_fbdev_dma_fb_destroy, }; -FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(drm_fbdev_dma, +FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(drm_fbdev_dma_shadowed, drm_fb_helper_damage_range, drm_fb_helper_damage_area); -static int drm_fbdev_dma_deferred_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) +static void drm_fbdev_dma_shadowed_fb_destroy(struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; - struct drm_framebuffer *fb = fb_helper->fb; - struct drm_gem_dma_object *dma = drm_fb_dma_get_gem_obj(fb, 0); + void *shadow = info->screen_buffer; + + if (!fb_helper->dev) + return; - if (!dma->map_noncoherent) - vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); + if (info->fbdefio) + fb_deferred_io_cleanup(info); + drm_fb_helper_fini(fb_helper); + vfree(shadow); - return fb_deferred_io_mmap(info, vma); + drm_client_buffer_vunmap(fb_helper->buffer); + drm_client_framebuffer_delete(fb_helper->buffer); + drm_client_release(&fb_helper->client); + drm_fb_helper_unprepare(fb_helper); + kfree(fb_helper); } -static const struct fb_ops drm_fbdev_dma_deferred_fb_ops = { +static const struct fb_ops drm_fbdev_dma_shadowed_fb_ops = { .owner = THIS_MODULE, .fb_open = drm_fbdev_dma_fb_open, .fb_release = drm_fbdev_dma_fb_release, - __FB_DEFAULT_DEFERRED_OPS_RDWR(drm_fbdev_dma), + FB_DEFAULT_DEFERRED_OPS(drm_fbdev_dma_shadowed), DRM_FB_HELPER_DEFAULT_OPS, - __FB_DEFAULT_DEFERRED_OPS_DRAW(drm_fbdev_dma), - .fb_mmap = drm_fbdev_dma_deferred_fb_mmap, - .fb_destroy = drm_fbdev_dma_fb_destroy, + .fb_destroy = drm_fbdev_dma_shadowed_fb_destroy, }; /* * struct drm_fb_helper */ +static void drm_fbdev_dma_damage_blit_real(struct drm_fb_helper *fb_helper, + struct drm_clip_rect *clip, + struct iosys_map *dst) +{ + struct drm_framebuffer *fb = fb_helper->fb; + size_t offset = clip->y1 * fb->pitches[0]; + size_t len = clip->x2 - clip->x1; + unsigned int y; + void *src; + + switch (drm_format_info_bpp(fb->format, 0)) { + case 1: + offset += clip->x1 / 8; + len = DIV_ROUND_UP(len + clip->x1 % 8, 8); + break; + case 2: + offset += clip->x1 / 4; + len = DIV_ROUND_UP(len + clip->x1 % 4, 4); + break; + case 4: + offset += clip->x1 / 2; + len = DIV_ROUND_UP(len + clip->x1 % 2, 2); + break; + default: + offset += clip->x1 * fb->format->cpp[0]; + len *= fb->format->cpp[0]; + break; + } + + src = fb_helper->info->screen_buffer + offset; + iosys_map_incr(dst, offset); /* go to first pixel within clip rect */ + + for (y = clip->y1; y < clip->y2; y++) { + iosys_map_memcpy_to(dst, 0, src, len); + iosys_map_incr(dst, fb->pitches[0]); + src += fb->pitches[0]; + } +} + +static int drm_fbdev_dma_damage_blit(struct drm_fb_helper *fb_helper, + struct drm_clip_rect *clip) +{ + struct drm_client_buffer *buffer = fb_helper->buffer; + struct iosys_map dst; + + /* + * For fbdev emulation, we only have to protect against fbdev modeset + * operations. Nothing else will involve the client buffer's BO. So it + * is sufficient to acquire struct drm_fb_helper.lock here. + */ + mutex_lock(&fb_helper->lock); + + dst = buffer->map; + drm_fbdev_dma_damage_blit_real(fb_helper, clip, &dst); + + mutex_unlock(&fb_helper->lock); + + return 0; +} static int drm_fbdev_dma_helper_fb_dirty(struct drm_fb_helper *helper, struct drm_clip_rect *clip) { @@ -112,6 +178,10 @@ static int drm_fbdev_dma_helper_fb_dirty(struct drm_fb_helper *helper, return 0; if (helper->fb->funcs->dirty) { + ret = drm_fbdev_dma_damage_blit(helper, clip); + if (drm_WARN_ONCE(dev, ret, "Damage blitter failed: ret=%d\n", ret)) + return ret; + ret = helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1); if (drm_WARN_ONCE(dev, ret, "Dirty helper failed: ret=%d\n", ret)) return ret; @@ -128,14 +198,80 @@ static const struct drm_fb_helper_funcs drm_fbdev_dma_helper_funcs = { * struct drm_fb_helper */ +static int drm_fbdev_dma_driver_fbdev_probe_tail(struct drm_fb_helper *fb_helper, + struct drm_fb_helper_surface_size *sizes) +{ + struct drm_device *dev = fb_helper->dev; + struct drm_client_buffer *buffer = fb_helper->buffer; + struct drm_gem_dma_object *dma_obj = to_drm_gem_dma_obj(buffer->gem); + struct drm_framebuffer *fb = fb_helper->fb; + struct fb_info *info = fb_helper->info; + struct iosys_map map = buffer->map; + + info->fbops = &drm_fbdev_dma_fb_ops; + + /* screen */ + info->flags |= FBINFO_VIRTFB; /* system memory */ + if (dma_obj->map_noncoherent) + info->flags |= FBINFO_READS_FAST; /* signal caching */ + info->screen_size = sizes->surface_height * fb->pitches[0]; + info->screen_buffer = map.vaddr; + if (!(info->flags & FBINFO_HIDE_SMEM_START)) { + if (!drm_WARN_ON(dev, is_vmalloc_addr(info->screen_buffer))) + info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer)); + } + info->fix.smem_len = info->screen_size; + + return 0; +} + +static int drm_fbdev_dma_driver_fbdev_probe_tail_shadowed(struct drm_fb_helper *fb_helper, + struct drm_fb_helper_surface_size *sizes) +{ + struct drm_client_buffer *buffer = fb_helper->buffer; + struct fb_info *info = fb_helper->info; + size_t screen_size = buffer->gem->size; + void *screen_buffer; + int ret; + + /* + * Deferred I/O requires struct page for framebuffer memory, + * which is not guaranteed for all DMA ranges. We thus create + * a shadow buffer in system memory. + */ + screen_buffer = vzalloc(screen_size); + if (!screen_buffer) + return -ENOMEM; + + info->fbops = &drm_fbdev_dma_shadowed_fb_ops; + + /* screen */ + info->flags |= FBINFO_VIRTFB; /* system memory */ + info->flags |= FBINFO_READS_FAST; /* signal caching */ + info->screen_buffer = screen_buffer; + info->fix.smem_len = screen_size; + + fb_helper->fbdefio.delay = HZ / 20; + fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io; + + info->fbdefio = &fb_helper->fbdefio; + ret = fb_deferred_io_init(info); + if (ret) + goto err_vfree; + + return 0; + +err_vfree: + vfree(screen_buffer); + return ret; +} + int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper, struct drm_fb_helper_surface_size *sizes) { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; - bool use_deferred_io = false; struct drm_client_buffer *buffer; - struct drm_gem_dma_object *dma_obj; struct drm_framebuffer *fb; struct fb_info *info; u32 format; @@ -152,19 +288,9 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper, sizes->surface_height, format); if (IS_ERR(buffer)) return PTR_ERR(buffer); - dma_obj = to_drm_gem_dma_obj(buffer->gem); fb = buffer->fb; - /* - * Deferred I/O requires struct page for framebuffer memory, - * which is not guaranteed for all DMA ranges. We thus only - * install deferred I/O if we have a framebuffer that requires - * it. - */ - if (fb->funcs->dirty) - use_deferred_io = true; - ret = drm_client_buffer_vmap(buffer, &map); if (ret) { goto err_drm_client_buffer_delete; @@ -185,45 +311,12 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper, drm_fb_helper_fill_info(info, fb_helper, sizes); - if (use_deferred_io) - info->fbops = &drm_fbdev_dma_deferred_fb_ops; + if (fb->funcs->dirty) + ret = drm_fbdev_dma_driver_fbdev_probe_tail_shadowed(fb_helper, sizes); else - info->fbops = &drm_fbdev_dma_fb_ops; - - /* screen */ - info->flags |= FBINFO_VIRTFB; /* system memory */ - if (dma_obj->map_noncoherent) - info->flags |= FBINFO_READS_FAST; /* signal caching */ - info->screen_size = sizes->surface_height * fb->pitches[0]; - info->screen_buffer = map.vaddr; - if (!(info->flags & FBINFO_HIDE_SMEM_START)) { - if (!drm_WARN_ON(dev, is_vmalloc_addr(info->screen_buffer))) - info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer)); - } - info->fix.smem_len = info->screen_size; - - /* - * Only set up deferred I/O if the screen buffer supports - * it. If this disagrees with the previous test for ->dirty, - * mmap on the /dev/fb file might not work correctly. - */ - if (!is_vmalloc_addr(info->screen_buffer) && info->fix.smem_start) { - unsigned long pfn = info->fix.smem_start >> PAGE_SHIFT; - - if (drm_WARN_ON(dev, !pfn_to_page(pfn))) - use_deferred_io = false; - } - - /* deferred I/O */ - if (use_deferred_io) { - fb_helper->fbdefio.delay = HZ / 20; - fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io; - - info->fbdefio = &fb_helper->fbdefio; - ret = fb_deferred_io_init(info); - if (ret) - goto err_drm_fb_helper_release_info; - } + ret = drm_fbdev_dma_driver_fbdev_probe_tail(fb_helper, sizes); + if (ret) + goto err_drm_fb_helper_release_info; return 0; diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c new file mode 100644 index 000000000000..2451c816edd5 --- /dev/null +++ b/drivers/gpu/drm/drm_gpusvm.c @@ -0,0 +1,2250 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Copyright © 2024 Intel Corporation + * + * Authors: + * Matthew Brost <matthew.brost@intel.com> + */ + +#include <linux/dma-mapping.h> +#include <linux/hmm.h> +#include <linux/memremap.h> +#include <linux/migrate.h> +#include <linux/mm_types.h> +#include <linux/pagemap.h> +#include <linux/slab.h> + +#include <drm/drm_device.h> +#include <drm/drm_gpusvm.h> +#include <drm/drm_pagemap.h> +#include <drm/drm_print.h> + +/** + * DOC: Overview + * + * GPU Shared Virtual Memory (GPU SVM) layer for the Direct Rendering Manager (DRM) + * is a component of the DRM framework designed to manage shared virtual memory + * between the CPU and GPU. It enables efficient data exchange and processing + * for GPU-accelerated applications by allowing memory sharing and + * synchronization between the CPU's and GPU's virtual address spaces. + * + * Key GPU SVM Components: + * + * - Notifiers: + * Used for tracking memory intervals and notifying the GPU of changes, + * notifiers are sized based on a GPU SVM initialization parameter, with a + * recommendation of 512M or larger. They maintain a Red-BlacK tree and a + * list of ranges that fall within the notifier interval. Notifiers are + * tracked within a GPU SVM Red-BlacK tree and list and are dynamically + * inserted or removed as ranges within the interval are created or + * destroyed. + * - Ranges: + * Represent memory ranges mapped in a DRM device and managed by GPU SVM. + * They are sized based on an array of chunk sizes, which is a GPU SVM + * initialization parameter, and the CPU address space. Upon GPU fault, + * the largest aligned chunk that fits within the faulting CPU address + * space is chosen for the range size. Ranges are expected to be + * dynamically allocated on GPU fault and removed on an MMU notifier UNMAP + * event. As mentioned above, ranges are tracked in a notifier's Red-Black + * tree. + * + * - Operations: + * Define the interface for driver-specific GPU SVM operations such as + * range allocation, notifier allocation, and invalidations. + * + * - Device Memory Allocations: + * Embedded structure containing enough information for GPU SVM to migrate + * to / from device memory. + * + * - Device Memory Operations: + * Define the interface for driver-specific device memory operations + * release memory, populate pfns, and copy to / from device memory. + * + * This layer provides interfaces for allocating, mapping, migrating, and + * releasing memory ranges between the CPU and GPU. It handles all core memory + * management interactions (DMA mapping, HMM, and migration) and provides + * driver-specific virtual functions (vfuncs). This infrastructure is sufficient + * to build the expected driver components for an SVM implementation as detailed + * below. + * + * Expected Driver Components: + * + * - GPU page fault handler: + * Used to create ranges and notifiers based on the fault address, + * optionally migrate the range to device memory, and create GPU bindings. + * + * - Garbage collector: + * Used to unmap and destroy GPU bindings for ranges. Ranges are expected + * to be added to the garbage collector upon a MMU_NOTIFY_UNMAP event in + * notifier callback. + * + * - Notifier callback: + * Used to invalidate and DMA unmap GPU bindings for ranges. + */ + +/** + * DOC: Locking + * + * GPU SVM handles locking for core MM interactions, i.e., it locks/unlocks the + * mmap lock as needed. + * + * GPU SVM introduces a global notifier lock, which safeguards the notifier's + * range RB tree and list, as well as the range's DMA mappings and sequence + * number. GPU SVM manages all necessary locking and unlocking operations, + * except for the recheck range's pages being valid + * (drm_gpusvm_range_pages_valid) when the driver is committing GPU bindings. + * This lock corresponds to the ``driver->update`` lock mentioned in + * Documentation/mm/hmm.rst. Future revisions may transition from a GPU SVM + * global lock to a per-notifier lock if finer-grained locking is deemed + * necessary. + * + * In addition to the locking mentioned above, the driver should implement a + * lock to safeguard core GPU SVM function calls that modify state, such as + * drm_gpusvm_range_find_or_insert and drm_gpusvm_range_remove. This lock is + * denoted as 'driver_svm_lock' in code examples. Finer grained driver side + * locking should also be possible for concurrent GPU fault processing within a + * single GPU SVM. The 'driver_svm_lock' can be via drm_gpusvm_driver_set_lock + * to add annotations to GPU SVM. + */ + +/** + * DOC: Migration + * + * The migration support is quite simple, allowing migration between RAM and + * device memory at the range granularity. For example, GPU SVM currently does + * not support mixing RAM and device memory pages within a range. This means + * that upon GPU fault, the entire range can be migrated to device memory, and + * upon CPU fault, the entire range is migrated to RAM. Mixed RAM and device + * memory storage within a range could be added in the future if required. + * + * The reasoning for only supporting range granularity is as follows: it + * simplifies the implementation, and range sizes are driver-defined and should + * be relatively small. + */ + +/** + * DOC: Partial Unmapping of Ranges + * + * Partial unmapping of ranges (e.g., 1M out of 2M is unmapped by CPU resulting + * in MMU_NOTIFY_UNMAP event) presents several challenges, with the main one + * being that a subset of the range still has CPU and GPU mappings. If the + * backing store for the range is in device memory, a subset of the backing + * store has references. One option would be to split the range and device + * memory backing store, but the implementation for this would be quite + * complicated. Given that partial unmappings are rare and driver-defined range + * sizes are relatively small, GPU SVM does not support splitting of ranges. + * + * With no support for range splitting, upon partial unmapping of a range, the + * driver is expected to invalidate and destroy the entire range. If the range + * has device memory as its backing, the driver is also expected to migrate any + * remaining pages back to RAM. + */ + +/** + * DOC: Examples + * + * This section provides three examples of how to build the expected driver + * components: the GPU page fault handler, the garbage collector, and the + * notifier callback. + * + * The generic code provided does not include logic for complex migration + * policies, optimized invalidations, fined grained driver locking, or other + * potentially required driver locking (e.g., DMA-resv locks). + * + * 1) GPU page fault handler + * + * .. code-block:: c + * + * int driver_bind_range(struct drm_gpusvm *gpusvm, struct drm_gpusvm_range *range) + * { + * int err = 0; + * + * driver_alloc_and_setup_memory_for_bind(gpusvm, range); + * + * drm_gpusvm_notifier_lock(gpusvm); + * if (drm_gpusvm_range_pages_valid(range)) + * driver_commit_bind(gpusvm, range); + * else + * err = -EAGAIN; + * drm_gpusvm_notifier_unlock(gpusvm); + * + * return err; + * } + * + * int driver_gpu_fault(struct drm_gpusvm *gpusvm, unsigned long fault_addr, + * unsigned long gpuva_start, unsigned long gpuva_end) + * { + * struct drm_gpusvm_ctx ctx = {}; + * int err; + * + * driver_svm_lock(); + * retry: + * // Always process UNMAPs first so view of GPU SVM ranges is current + * driver_garbage_collector(gpusvm); + * + * range = drm_gpusvm_range_find_or_insert(gpusvm, fault_addr, + * gpuva_start, gpuva_end, + * &ctx); + * if (IS_ERR(range)) { + * err = PTR_ERR(range); + * goto unlock; + * } + * + * if (driver_migration_policy(range)) { + * mmap_read_lock(mm); + * devmem = driver_alloc_devmem(); + * err = drm_gpusvm_migrate_to_devmem(gpusvm, range, + * devmem_allocation, + * &ctx); + * mmap_read_unlock(mm); + * if (err) // CPU mappings may have changed + * goto retry; + * } + * + * err = drm_gpusvm_range_get_pages(gpusvm, range, &ctx); + * if (err == -EOPNOTSUPP || err == -EFAULT || err == -EPERM) { // CPU mappings changed + * if (err == -EOPNOTSUPP) + * drm_gpusvm_range_evict(gpusvm, range); + * goto retry; + * } else if (err) { + * goto unlock; + * } + * + * err = driver_bind_range(gpusvm, range); + * if (err == -EAGAIN) // CPU mappings changed + * goto retry + * + * unlock: + * driver_svm_unlock(); + * return err; + * } + * + * 2) Garbage Collector + * + * .. code-block:: c + * + * void __driver_garbage_collector(struct drm_gpusvm *gpusvm, + * struct drm_gpusvm_range *range) + * { + * assert_driver_svm_locked(gpusvm); + * + * // Partial unmap, migrate any remaining device memory pages back to RAM + * if (range->flags.partial_unmap) + * drm_gpusvm_range_evict(gpusvm, range); + * + * driver_unbind_range(range); + * drm_gpusvm_range_remove(gpusvm, range); + * } + * + * void driver_garbage_collector(struct drm_gpusvm *gpusvm) + * { + * assert_driver_svm_locked(gpusvm); + * + * for_each_range_in_garbage_collector(gpusvm, range) + * __driver_garbage_collector(gpusvm, range); + * } + * + * 3) Notifier callback + * + * .. code-block:: c + * + * void driver_invalidation(struct drm_gpusvm *gpusvm, + * struct drm_gpusvm_notifier *notifier, + * const struct mmu_notifier_range *mmu_range) + * { + * struct drm_gpusvm_ctx ctx = { .in_notifier = true, }; + * struct drm_gpusvm_range *range = NULL; + * + * driver_invalidate_device_pages(gpusvm, mmu_range->start, mmu_range->end); + * + * drm_gpusvm_for_each_range(range, notifier, mmu_range->start, + * mmu_range->end) { + * drm_gpusvm_range_unmap_pages(gpusvm, range, &ctx); + * + * if (mmu_range->event != MMU_NOTIFY_UNMAP) + * continue; + * + * drm_gpusvm_range_set_unmapped(range, mmu_range); + * driver_garbage_collector_add(gpusvm, range); + * } + * } + */ + +/** + * npages_in_range() - Calculate the number of pages in a given range + * @start: The start address of the range + * @end: The end address of the range + * + * This macro calculates the number of pages in a given memory range, + * specified by the start and end addresses. It divides the difference + * between the end and start addresses by the page size (PAGE_SIZE) to + * determine the number of pages in the range. + * + * Return: The number of pages in the specified range. + */ +static unsigned long +npages_in_range(unsigned long start, unsigned long end) +{ + return (end - start) >> PAGE_SHIFT; +} + +/** + * struct drm_gpusvm_zdd - GPU SVM zone device data + * + * @refcount: Reference count for the zdd + * @devmem_allocation: device memory allocation + * @device_private_page_owner: Device private pages owner + * + * This structure serves as a generic wrapper installed in + * page->zone_device_data. It provides infrastructure for looking up a device + * memory allocation upon CPU page fault and asynchronously releasing device + * memory once the CPU has no page references. Asynchronous release is useful + * because CPU page references can be dropped in IRQ contexts, while releasing + * device memory likely requires sleeping locks. + */ +struct drm_gpusvm_zdd { + struct kref refcount; + struct drm_gpusvm_devmem *devmem_allocation; + void *device_private_page_owner; +}; + +/** + * drm_gpusvm_zdd_alloc() - Allocate a zdd structure. + * @device_private_page_owner: Device private pages owner + * + * This function allocates and initializes a new zdd structure. It sets up the + * reference count and initializes the destroy work. + * + * Return: Pointer to the allocated zdd on success, ERR_PTR() on failure. + */ +static struct drm_gpusvm_zdd * +drm_gpusvm_zdd_alloc(void *device_private_page_owner) +{ + struct drm_gpusvm_zdd *zdd; + + zdd = kmalloc(sizeof(*zdd), GFP_KERNEL); + if (!zdd) + return NULL; + + kref_init(&zdd->refcount); + zdd->devmem_allocation = NULL; + zdd->device_private_page_owner = device_private_page_owner; + + return zdd; +} + +/** + * drm_gpusvm_zdd_get() - Get a reference to a zdd structure. + * @zdd: Pointer to the zdd structure. + * + * This function increments the reference count of the provided zdd structure. + * + * Return: Pointer to the zdd structure. + */ +static struct drm_gpusvm_zdd *drm_gpusvm_zdd_get(struct drm_gpusvm_zdd *zdd) +{ + kref_get(&zdd->refcount); + return zdd; +} + +/** + * drm_gpusvm_zdd_destroy() - Destroy a zdd structure. + * @ref: Pointer to the reference count structure. + * + * This function queues the destroy_work of the zdd for asynchronous destruction. + */ +static void drm_gpusvm_zdd_destroy(struct kref *ref) +{ + struct drm_gpusvm_zdd *zdd = + container_of(ref, struct drm_gpusvm_zdd, refcount); + struct drm_gpusvm_devmem *devmem = zdd->devmem_allocation; + + if (devmem) { + complete_all(&devmem->detached); + if (devmem->ops->devmem_release) + devmem->ops->devmem_release(devmem); + } + kfree(zdd); +} + +/** + * drm_gpusvm_zdd_put() - Put a zdd reference. + * @zdd: Pointer to the zdd structure. + * + * This function decrements the reference count of the provided zdd structure + * and schedules its destruction if the count drops to zero. + */ +static void drm_gpusvm_zdd_put(struct drm_gpusvm_zdd *zdd) +{ + kref_put(&zdd->refcount, drm_gpusvm_zdd_destroy); +} + +/** + * drm_gpusvm_range_find() - Find GPU SVM range from GPU SVM notifier + * @notifier: Pointer to the GPU SVM notifier structure. + * @start: Start address of the range + * @end: End address of the range + * + * Return: A pointer to the drm_gpusvm_range if found or NULL + */ +struct drm_gpusvm_range * +drm_gpusvm_range_find(struct drm_gpusvm_notifier *notifier, unsigned long start, + unsigned long end) +{ + struct interval_tree_node *itree; + + itree = interval_tree_iter_first(¬ifier->root, start, end - 1); + + if (itree) + return container_of(itree, struct drm_gpusvm_range, itree); + else + return NULL; +} +EXPORT_SYMBOL_GPL(drm_gpusvm_range_find); + +/** + * drm_gpusvm_for_each_range_safe() - Safely iterate over GPU SVM ranges in a notifier + * @range__: Iterator variable for the ranges + * @next__: Iterator variable for the ranges temporay storage + * @notifier__: Pointer to the GPU SVM notifier + * @start__: Start address of the range + * @end__: End address of the range + * + * This macro is used to iterate over GPU SVM ranges in a notifier while + * removing ranges from it. + */ +#define drm_gpusvm_for_each_range_safe(range__, next__, notifier__, start__, end__) \ + for ((range__) = drm_gpusvm_range_find((notifier__), (start__), (end__)), \ + (next__) = __drm_gpusvm_range_next(range__); \ + (range__) && (drm_gpusvm_range_start(range__) < (end__)); \ + (range__) = (next__), (next__) = __drm_gpusvm_range_next(range__)) + +/** + * __drm_gpusvm_notifier_next() - get the next drm_gpusvm_notifier in the list + * @notifier: a pointer to the current drm_gpusvm_notifier + * + * Return: A pointer to the next drm_gpusvm_notifier if available, or NULL if + * the current notifier is the last one or if the input notifier is + * NULL. + */ +static struct drm_gpusvm_notifier * +__drm_gpusvm_notifier_next(struct drm_gpusvm_notifier *notifier) +{ + if (notifier && !list_is_last(¬ifier->entry, + ¬ifier->gpusvm->notifier_list)) + return list_next_entry(notifier, entry); + + return NULL; +} + +static struct drm_gpusvm_notifier * +notifier_iter_first(struct rb_root_cached *root, unsigned long start, + unsigned long last) +{ + struct interval_tree_node *itree; + + itree = interval_tree_iter_first(root, start, last); + + if (itree) + return container_of(itree, struct drm_gpusvm_notifier, itree); + else + return NULL; +} + +/** + * drm_gpusvm_for_each_notifier() - Iterate over GPU SVM notifiers in a gpusvm + * @notifier__: Iterator variable for the notifiers + * @notifier__: Pointer to the GPU SVM notifier + * @start__: Start address of the notifier + * @end__: End address of the notifier + * + * This macro is used to iterate over GPU SVM notifiers in a gpusvm. + */ +#define drm_gpusvm_for_each_notifier(notifier__, gpusvm__, start__, end__) \ + for ((notifier__) = notifier_iter_first(&(gpusvm__)->root, (start__), (end__) - 1); \ + (notifier__) && (drm_gpusvm_notifier_start(notifier__) < (end__)); \ + (notifier__) = __drm_gpusvm_notifier_next(notifier__)) + +/** + * drm_gpusvm_for_each_notifier_safe() - Safely iterate over GPU SVM notifiers in a gpusvm + * @notifier__: Iterator variable for the notifiers + * @next__: Iterator variable for the notifiers temporay storage + * @notifier__: Pointer to the GPU SVM notifier + * @start__: Start address of the notifier + * @end__: End address of the notifier + * + * This macro is used to iterate over GPU SVM notifiers in a gpusvm while + * removing notifiers from it. + */ +#define drm_gpusvm_for_each_notifier_safe(notifier__, next__, gpusvm__, start__, end__) \ + for ((notifier__) = notifier_iter_first(&(gpusvm__)->root, (start__), (end__) - 1), \ + (next__) = __drm_gpusvm_notifier_next(notifier__); \ + (notifier__) && (drm_gpusvm_notifier_start(notifier__) < (end__)); \ + (notifier__) = (next__), (next__) = __drm_gpusvm_notifier_next(notifier__)) + +/** + * drm_gpusvm_notifier_invalidate() - Invalidate a GPU SVM notifier. + * @mni: Pointer to the mmu_interval_notifier structure. + * @mmu_range: Pointer to the mmu_notifier_range structure. + * @cur_seq: Current sequence number. + * + * This function serves as a generic MMU notifier for GPU SVM. It sets the MMU + * notifier sequence number and calls the driver invalidate vfunc under + * gpusvm->notifier_lock. + * + * Return: true if the operation succeeds, false otherwise. + */ +static bool +drm_gpusvm_notifier_invalidate(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *mmu_range, + unsigned long cur_seq) +{ + struct drm_gpusvm_notifier *notifier = + container_of(mni, typeof(*notifier), notifier); + struct drm_gpusvm *gpusvm = notifier->gpusvm; + + if (!mmu_notifier_range_blockable(mmu_range)) + return false; + + down_write(&gpusvm->notifier_lock); + mmu_interval_set_seq(mni, cur_seq); + gpusvm->ops->invalidate(gpusvm, notifier, mmu_range); + up_write(&gpusvm->notifier_lock); + + return true; +} + +/* + * drm_gpusvm_notifier_ops - MMU interval notifier operations for GPU SVM + */ +static const struct mmu_interval_notifier_ops drm_gpusvm_notifier_ops = { + .invalidate = drm_gpusvm_notifier_invalidate, +}; + +/** + * drm_gpusvm_init() - Initialize the GPU SVM. + * @gpusvm: Pointer to the GPU SVM structure. + * @name: Name of the GPU SVM. + * @drm: Pointer to the DRM device structure. + * @mm: Pointer to the mm_struct for the address space. + * @device_private_page_owner: Device private pages owner. + * @mm_start: Start address of GPU SVM. + * @mm_range: Range of the GPU SVM. + * @notifier_size: Size of individual notifiers. + * @ops: Pointer to the operations structure for GPU SVM. + * @chunk_sizes: Pointer to the array of chunk sizes used in range allocation. + * Entries should be powers of 2 in descending order with last + * entry being SZ_4K. + * @num_chunks: Number of chunks. + * + * This function initializes the GPU SVM. + * + * Return: 0 on success, a negative error code on failure. + */ +int drm_gpusvm_init(struct drm_gpusvm *gpusvm, + const char *name, struct drm_device *drm, + struct mm_struct *mm, void *device_private_page_owner, + unsigned long mm_start, unsigned long mm_range, + unsigned long notifier_size, + const struct drm_gpusvm_ops *ops, + const unsigned long *chunk_sizes, int num_chunks) +{ + if (!ops->invalidate || !num_chunks) + return -EINVAL; + + gpusvm->name = name; + gpusvm->drm = drm; + gpusvm->mm = mm; + gpusvm->device_private_page_owner = device_private_page_owner; + gpusvm->mm_start = mm_start; + gpusvm->mm_range = mm_range; + gpusvm->notifier_size = notifier_size; + gpusvm->ops = ops; + gpusvm->chunk_sizes = chunk_sizes; + gpusvm->num_chunks = num_chunks; + + mmgrab(mm); + gpusvm->root = RB_ROOT_CACHED; + INIT_LIST_HEAD(&gpusvm->notifier_list); + + init_rwsem(&gpusvm->notifier_lock); + + fs_reclaim_acquire(GFP_KERNEL); + might_lock(&gpusvm->notifier_lock); + fs_reclaim_release(GFP_KERNEL); + +#ifdef CONFIG_LOCKDEP + gpusvm->lock_dep_map = NULL; +#endif + + return 0; +} +EXPORT_SYMBOL_GPL(drm_gpusvm_init); + +/** + * drm_gpusvm_notifier_find() - Find GPU SVM notifier + * @gpusvm: Pointer to the GPU SVM structure + * @fault_addr: Fault address + * + * This function finds the GPU SVM notifier associated with the fault address. + * + * Return: Pointer to the GPU SVM notifier on success, NULL otherwise. + */ +static struct drm_gpusvm_notifier * +drm_gpusvm_notifier_find(struct drm_gpusvm *gpusvm, + unsigned long fault_addr) +{ + return notifier_iter_first(&gpusvm->root, fault_addr, fault_addr + 1); +} + +/** + * to_drm_gpusvm_notifier() - retrieve the container struct for a given rbtree node + * @node: a pointer to the rbtree node embedded within a drm_gpusvm_notifier struct + * + * Return: A pointer to the containing drm_gpusvm_notifier structure. + */ +static struct drm_gpusvm_notifier *to_drm_gpusvm_notifier(struct rb_node *node) +{ + return container_of(node, struct drm_gpusvm_notifier, itree.rb); +} + +/** + * drm_gpusvm_notifier_insert() - Insert GPU SVM notifier + * @gpusvm: Pointer to the GPU SVM structure + * @notifier: Pointer to the GPU SVM notifier structure + * + * This function inserts the GPU SVM notifier into the GPU SVM RB tree and list. + */ +static void drm_gpusvm_notifier_insert(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_notifier *notifier) +{ + struct rb_node *node; + struct list_head *head; + + interval_tree_insert(¬ifier->itree, &gpusvm->root); + + node = rb_prev(¬ifier->itree.rb); + if (node) + head = &(to_drm_gpusvm_notifier(node))->entry; + else + head = &gpusvm->notifier_list; + + list_add(¬ifier->entry, head); +} + +/** + * drm_gpusvm_notifier_remove() - Remove GPU SVM notifier + * @gpusvm: Pointer to the GPU SVM tructure + * @notifier: Pointer to the GPU SVM notifier structure + * + * This function removes the GPU SVM notifier from the GPU SVM RB tree and list. + */ +static void drm_gpusvm_notifier_remove(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_notifier *notifier) +{ + interval_tree_remove(¬ifier->itree, &gpusvm->root); + list_del(¬ifier->entry); +} + +/** + * drm_gpusvm_fini() - Finalize the GPU SVM. + * @gpusvm: Pointer to the GPU SVM structure. + * + * This function finalizes the GPU SVM by cleaning up any remaining ranges and + * notifiers, and dropping a reference to struct MM. + */ +void drm_gpusvm_fini(struct drm_gpusvm *gpusvm) +{ + struct drm_gpusvm_notifier *notifier, *next; + + drm_gpusvm_for_each_notifier_safe(notifier, next, gpusvm, 0, LONG_MAX) { + struct drm_gpusvm_range *range, *__next; + + /* + * Remove notifier first to avoid racing with any invalidation + */ + mmu_interval_notifier_remove(¬ifier->notifier); + notifier->flags.removed = true; + + drm_gpusvm_for_each_range_safe(range, __next, notifier, 0, + LONG_MAX) + drm_gpusvm_range_remove(gpusvm, range); + } + + mmdrop(gpusvm->mm); + WARN_ON(!RB_EMPTY_ROOT(&gpusvm->root.rb_root)); +} +EXPORT_SYMBOL_GPL(drm_gpusvm_fini); + +/** + * drm_gpusvm_notifier_alloc() - Allocate GPU SVM notifier + * @gpusvm: Pointer to the GPU SVM structure + * @fault_addr: Fault address + * + * This function allocates and initializes the GPU SVM notifier structure. + * + * Return: Pointer to the allocated GPU SVM notifier on success, ERR_PTR() on failure. + */ +static struct drm_gpusvm_notifier * +drm_gpusvm_notifier_alloc(struct drm_gpusvm *gpusvm, unsigned long fault_addr) +{ + struct drm_gpusvm_notifier *notifier; + + if (gpusvm->ops->notifier_alloc) + notifier = gpusvm->ops->notifier_alloc(); + else + notifier = kzalloc(sizeof(*notifier), GFP_KERNEL); + + if (!notifier) + return ERR_PTR(-ENOMEM); + + notifier->gpusvm = gpusvm; + notifier->itree.start = ALIGN_DOWN(fault_addr, gpusvm->notifier_size); + notifier->itree.last = ALIGN(fault_addr + 1, gpusvm->notifier_size) - 1; + INIT_LIST_HEAD(¬ifier->entry); + notifier->root = RB_ROOT_CACHED; + INIT_LIST_HEAD(¬ifier->range_list); + + return notifier; +} + +/** + * drm_gpusvm_notifier_free() - Free GPU SVM notifier + * @gpusvm: Pointer to the GPU SVM structure + * @notifier: Pointer to the GPU SVM notifier structure + * + * This function frees the GPU SVM notifier structure. + */ +static void drm_gpusvm_notifier_free(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_notifier *notifier) +{ + WARN_ON(!RB_EMPTY_ROOT(¬ifier->root.rb_root)); + + if (gpusvm->ops->notifier_free) + gpusvm->ops->notifier_free(notifier); + else + kfree(notifier); +} + +/** + * to_drm_gpusvm_range() - retrieve the container struct for a given rbtree node + * @node: a pointer to the rbtree node embedded within a drm_gpusvm_range struct + * + * Return: A pointer to the containing drm_gpusvm_range structure. + */ +static struct drm_gpusvm_range *to_drm_gpusvm_range(struct rb_node *node) +{ + return container_of(node, struct drm_gpusvm_range, itree.rb); +} + +/** + * drm_gpusvm_range_insert() - Insert GPU SVM range + * @notifier: Pointer to the GPU SVM notifier structure + * @range: Pointer to the GPU SVM range structure + * + * This function inserts the GPU SVM range into the notifier RB tree and list. + */ +static void drm_gpusvm_range_insert(struct drm_gpusvm_notifier *notifier, + struct drm_gpusvm_range *range) +{ + struct rb_node *node; + struct list_head *head; + + drm_gpusvm_notifier_lock(notifier->gpusvm); + interval_tree_insert(&range->itree, ¬ifier->root); + + node = rb_prev(&range->itree.rb); + if (node) + head = &(to_drm_gpusvm_range(node))->entry; + else + head = ¬ifier->range_list; + + list_add(&range->entry, head); + drm_gpusvm_notifier_unlock(notifier->gpusvm); +} + +/** + * __drm_gpusvm_range_remove() - Remove GPU SVM range + * @notifier: Pointer to the GPU SVM notifier structure + * @range: Pointer to the GPU SVM range structure + * + * This macro removes the GPU SVM range from the notifier RB tree and list. + */ +static void __drm_gpusvm_range_remove(struct drm_gpusvm_notifier *notifier, + struct drm_gpusvm_range *range) +{ + interval_tree_remove(&range->itree, ¬ifier->root); + list_del(&range->entry); +} + +/** + * drm_gpusvm_range_alloc() - Allocate GPU SVM range + * @gpusvm: Pointer to the GPU SVM structure + * @notifier: Pointer to the GPU SVM notifier structure + * @fault_addr: Fault address + * @chunk_size: Chunk size + * @migrate_devmem: Flag indicating whether to migrate device memory + * + * This function allocates and initializes the GPU SVM range structure. + * + * Return: Pointer to the allocated GPU SVM range on success, ERR_PTR() on failure. + */ +static struct drm_gpusvm_range * +drm_gpusvm_range_alloc(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_notifier *notifier, + unsigned long fault_addr, unsigned long chunk_size, + bool migrate_devmem) +{ + struct drm_gpusvm_range *range; + + if (gpusvm->ops->range_alloc) + range = gpusvm->ops->range_alloc(gpusvm); + else + range = kzalloc(sizeof(*range), GFP_KERNEL); + + if (!range) + return ERR_PTR(-ENOMEM); + + kref_init(&range->refcount); + range->gpusvm = gpusvm; + range->notifier = notifier; + range->itree.start = ALIGN_DOWN(fault_addr, chunk_size); + range->itree.last = ALIGN(fault_addr + 1, chunk_size) - 1; + INIT_LIST_HEAD(&range->entry); + range->notifier_seq = LONG_MAX; + range->flags.migrate_devmem = migrate_devmem ? 1 : 0; + + return range; +} + +/** + * drm_gpusvm_check_pages() - Check pages + * @gpusvm: Pointer to the GPU SVM structure + * @notifier: Pointer to the GPU SVM notifier structure + * @start: Start address + * @end: End address + * + * Check if pages between start and end have been faulted in on the CPU. Use to + * prevent migration of pages without CPU backing store. + * + * Return: True if pages have been faulted into CPU, False otherwise + */ +static bool drm_gpusvm_check_pages(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_notifier *notifier, + unsigned long start, unsigned long end) +{ + struct hmm_range hmm_range = { + .default_flags = 0, + .notifier = ¬ifier->notifier, + .start = start, + .end = end, + .dev_private_owner = gpusvm->device_private_page_owner, + }; + unsigned long timeout = + jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); + unsigned long *pfns; + unsigned long npages = npages_in_range(start, end); + int err, i; + + mmap_assert_locked(gpusvm->mm); + + pfns = kvmalloc_array(npages, sizeof(*pfns), GFP_KERNEL); + if (!pfns) + return false; + + hmm_range.notifier_seq = mmu_interval_read_begin(¬ifier->notifier); + hmm_range.hmm_pfns = pfns; + + while (true) { + err = hmm_range_fault(&hmm_range); + if (err == -EBUSY) { + if (time_after(jiffies, timeout)) + break; + + hmm_range.notifier_seq = + mmu_interval_read_begin(¬ifier->notifier); + continue; + } + break; + } + if (err) + goto err_free; + + for (i = 0; i < npages;) { + if (!(pfns[i] & HMM_PFN_VALID)) { + err = -EFAULT; + goto err_free; + } + i += 0x1 << hmm_pfn_to_map_order(pfns[i]); + } + +err_free: + kvfree(pfns); + return err ? false : true; +} + +/** + * drm_gpusvm_range_chunk_size() - Determine chunk size for GPU SVM range + * @gpusvm: Pointer to the GPU SVM structure + * @notifier: Pointer to the GPU SVM notifier structure + * @vas: Pointer to the virtual memory area structure + * @fault_addr: Fault address + * @gpuva_start: Start address of GPUVA which mirrors CPU + * @gpuva_end: End address of GPUVA which mirrors CPU + * @check_pages_threshold: Check CPU pages for present threshold + * + * This function determines the chunk size for the GPU SVM range based on the + * fault address, GPU SVM chunk sizes, existing GPU SVM ranges, and the virtual + * memory area boundaries. + * + * Return: Chunk size on success, LONG_MAX on failure. + */ +static unsigned long +drm_gpusvm_range_chunk_size(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_notifier *notifier, + struct vm_area_struct *vas, + unsigned long fault_addr, + unsigned long gpuva_start, + unsigned long gpuva_end, + unsigned long check_pages_threshold) +{ + unsigned long start, end; + int i = 0; + +retry: + for (; i < gpusvm->num_chunks; ++i) { + start = ALIGN_DOWN(fault_addr, gpusvm->chunk_sizes[i]); + end = ALIGN(fault_addr + 1, gpusvm->chunk_sizes[i]); + + if (start >= vas->vm_start && end <= vas->vm_end && + start >= drm_gpusvm_notifier_start(notifier) && + end <= drm_gpusvm_notifier_end(notifier) && + start >= gpuva_start && end <= gpuva_end) + break; + } + + if (i == gpusvm->num_chunks) + return LONG_MAX; + + /* + * If allocation more than page, ensure not to overlap with existing + * ranges. + */ + if (end - start != SZ_4K) { + struct drm_gpusvm_range *range; + + range = drm_gpusvm_range_find(notifier, start, end); + if (range) { + ++i; + goto retry; + } + + /* + * XXX: Only create range on pages CPU has faulted in. Without + * this check, or prefault, on BMG 'xe_exec_system_allocator --r + * process-many-malloc' fails. In the failure case, each process + * mallocs 16k but the CPU VMA is ~128k which results in 64k SVM + * ranges. When migrating the SVM ranges, some processes fail in + * drm_gpusvm_migrate_to_devmem with 'migrate.cpages != npages' + * and then upon drm_gpusvm_range_get_pages device pages from + * other processes are collected + faulted in which creates all + * sorts of problems. Unsure exactly how this happening, also + * problem goes away if 'xe_exec_system_allocator --r + * process-many-malloc' mallocs at least 64k at a time. + */ + if (end - start <= check_pages_threshold && + !drm_gpusvm_check_pages(gpusvm, notifier, start, end)) { + ++i; + goto retry; + } + } + + return end - start; +} + +#ifdef CONFIG_LOCKDEP +/** + * drm_gpusvm_driver_lock_held() - Assert GPU SVM driver lock is held + * @gpusvm: Pointer to the GPU SVM structure. + * + * Ensure driver lock is held. + */ +static void drm_gpusvm_driver_lock_held(struct drm_gpusvm *gpusvm) +{ + if ((gpusvm)->lock_dep_map) + lockdep_assert(lock_is_held_type((gpusvm)->lock_dep_map, 0)); +} +#else +static void drm_gpusvm_driver_lock_held(struct drm_gpusvm *gpusvm) +{ +} +#endif + +/** + * drm_gpusvm_range_find_or_insert() - Find or insert GPU SVM range + * @gpusvm: Pointer to the GPU SVM structure + * @fault_addr: Fault address + * @gpuva_start: Start address of GPUVA which mirrors CPU + * @gpuva_end: End address of GPUVA which mirrors CPU + * @ctx: GPU SVM context + * + * This function finds or inserts a newly allocated a GPU SVM range based on the + * fault address. Caller must hold a lock to protect range lookup and insertion. + * + * Return: Pointer to the GPU SVM range on success, ERR_PTR() on failure. + */ +struct drm_gpusvm_range * +drm_gpusvm_range_find_or_insert(struct drm_gpusvm *gpusvm, + unsigned long fault_addr, + unsigned long gpuva_start, + unsigned long gpuva_end, + const struct drm_gpusvm_ctx *ctx) +{ + struct drm_gpusvm_notifier *notifier; + struct drm_gpusvm_range *range; + struct mm_struct *mm = gpusvm->mm; + struct vm_area_struct *vas; + bool notifier_alloc = false; + unsigned long chunk_size; + int err; + bool migrate_devmem; + + drm_gpusvm_driver_lock_held(gpusvm); + + if (fault_addr < gpusvm->mm_start || + fault_addr > gpusvm->mm_start + gpusvm->mm_range) + return ERR_PTR(-EINVAL); + + if (!mmget_not_zero(mm)) + return ERR_PTR(-EFAULT); + + notifier = drm_gpusvm_notifier_find(gpusvm, fault_addr); + if (!notifier) { + notifier = drm_gpusvm_notifier_alloc(gpusvm, fault_addr); + if (IS_ERR(notifier)) { + err = PTR_ERR(notifier); + goto err_mmunlock; + } + notifier_alloc = true; + err = mmu_interval_notifier_insert(¬ifier->notifier, + mm, + drm_gpusvm_notifier_start(notifier), + drm_gpusvm_notifier_size(notifier), + &drm_gpusvm_notifier_ops); + if (err) + goto err_notifier; + } + + mmap_read_lock(mm); + + vas = vma_lookup(mm, fault_addr); + if (!vas) { + err = -ENOENT; + goto err_notifier_remove; + } + + if (!ctx->read_only && !(vas->vm_flags & VM_WRITE)) { + err = -EPERM; + goto err_notifier_remove; + } + + range = drm_gpusvm_range_find(notifier, fault_addr, fault_addr + 1); + if (range) + goto out_mmunlock; + /* + * XXX: Short-circuiting migration based on migrate_vma_* current + * limitations. If/when migrate_vma_* add more support, this logic will + * have to change. + */ + migrate_devmem = ctx->devmem_possible && + vma_is_anonymous(vas) && !is_vm_hugetlb_page(vas); + + chunk_size = drm_gpusvm_range_chunk_size(gpusvm, notifier, vas, + fault_addr, gpuva_start, + gpuva_end, + ctx->check_pages_threshold); + if (chunk_size == LONG_MAX) { + err = -EINVAL; + goto err_notifier_remove; + } + + range = drm_gpusvm_range_alloc(gpusvm, notifier, fault_addr, chunk_size, + migrate_devmem); + if (IS_ERR(range)) { + err = PTR_ERR(range); + goto err_notifier_remove; + } + + drm_gpusvm_range_insert(notifier, range); + if (notifier_alloc) + drm_gpusvm_notifier_insert(gpusvm, notifier); + +out_mmunlock: + mmap_read_unlock(mm); + mmput(mm); + + return range; + +err_notifier_remove: + mmap_read_unlock(mm); + if (notifier_alloc) + mmu_interval_notifier_remove(¬ifier->notifier); +err_notifier: + if (notifier_alloc) + drm_gpusvm_notifier_free(gpusvm, notifier); +err_mmunlock: + mmput(mm); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(drm_gpusvm_range_find_or_insert); + +/** + * __drm_gpusvm_range_unmap_pages() - Unmap pages associated with a GPU SVM range (internal) + * @gpusvm: Pointer to the GPU SVM structure + * @range: Pointer to the GPU SVM range structure + * @npages: Number of pages to unmap + * + * This function unmap pages associated with a GPU SVM range. Assumes and + * asserts correct locking is in place when called. + */ +static void __drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_range *range, + unsigned long npages) +{ + unsigned long i, j; + struct drm_pagemap *dpagemap = range->dpagemap; + struct device *dev = gpusvm->drm->dev; + + lockdep_assert_held(&gpusvm->notifier_lock); + + if (range->flags.has_dma_mapping) { + for (i = 0, j = 0; i < npages; j++) { + struct drm_pagemap_device_addr *addr = &range->dma_addr[j]; + + if (addr->proto == DRM_INTERCONNECT_SYSTEM) + dma_unmap_page(dev, + addr->addr, + PAGE_SIZE << addr->order, + addr->dir); + else if (dpagemap && dpagemap->ops->device_unmap) + dpagemap->ops->device_unmap(dpagemap, + dev, *addr); + i += 1 << addr->order; + } + range->flags.has_devmem_pages = false; + range->flags.has_dma_mapping = false; + range->dpagemap = NULL; + } +} + +/** + * drm_gpusvm_range_free_pages() - Free pages associated with a GPU SVM range + * @gpusvm: Pointer to the GPU SVM structure + * @range: Pointer to the GPU SVM range structure + * + * This function frees the dma address array associated with a GPU SVM range. + */ +static void drm_gpusvm_range_free_pages(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_range *range) +{ + lockdep_assert_held(&gpusvm->notifier_lock); + + if (range->dma_addr) { + kvfree(range->dma_addr); + range->dma_addr = NULL; + } +} + +/** + * drm_gpusvm_range_remove() - Remove GPU SVM range + * @gpusvm: Pointer to the GPU SVM structure + * @range: Pointer to the GPU SVM range to be removed + * + * This function removes the specified GPU SVM range and also removes the parent + * GPU SVM notifier if no more ranges remain in the notifier. The caller must + * hold a lock to protect range and notifier removal. + */ +void drm_gpusvm_range_remove(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_range *range) +{ + unsigned long npages = npages_in_range(drm_gpusvm_range_start(range), + drm_gpusvm_range_end(range)); + struct drm_gpusvm_notifier *notifier; + + drm_gpusvm_driver_lock_held(gpusvm); + + notifier = drm_gpusvm_notifier_find(gpusvm, + drm_gpusvm_range_start(range)); + if (WARN_ON_ONCE(!notifier)) + return; + + drm_gpusvm_notifier_lock(gpusvm); + __drm_gpusvm_range_unmap_pages(gpusvm, range, npages); + drm_gpusvm_range_free_pages(gpusvm, range); + __drm_gpusvm_range_remove(notifier, range); + drm_gpusvm_notifier_unlock(gpusvm); + + drm_gpusvm_range_put(range); + + if (RB_EMPTY_ROOT(¬ifier->root.rb_root)) { + if (!notifier->flags.removed) + mmu_interval_notifier_remove(¬ifier->notifier); + drm_gpusvm_notifier_remove(gpusvm, notifier); + drm_gpusvm_notifier_free(gpusvm, notifier); + } +} +EXPORT_SYMBOL_GPL(drm_gpusvm_range_remove); + +/** + * drm_gpusvm_range_get() - Get a reference to GPU SVM range + * @range: Pointer to the GPU SVM range + * + * This function increments the reference count of the specified GPU SVM range. + * + * Return: Pointer to the GPU SVM range. + */ +struct drm_gpusvm_range * +drm_gpusvm_range_get(struct drm_gpusvm_range *range) +{ + kref_get(&range->refcount); + + return range; +} +EXPORT_SYMBOL_GPL(drm_gpusvm_range_get); + +/** + * drm_gpusvm_range_destroy() - Destroy GPU SVM range + * @refcount: Pointer to the reference counter embedded in the GPU SVM range + * + * This function destroys the specified GPU SVM range when its reference count + * reaches zero. If a custom range-free function is provided, it is invoked to + * free the range; otherwise, the range is deallocated using kfree(). + */ +static void drm_gpusvm_range_destroy(struct kref *refcount) +{ + struct drm_gpusvm_range *range = + container_of(refcount, struct drm_gpusvm_range, refcount); + struct drm_gpusvm *gpusvm = range->gpusvm; + + if (gpusvm->ops->range_free) + gpusvm->ops->range_free(range); + else + kfree(range); +} + +/** + * drm_gpusvm_range_put() - Put a reference to GPU SVM range + * @range: Pointer to the GPU SVM range + * + * This function decrements the reference count of the specified GPU SVM range + * and frees it when the count reaches zero. + */ +void drm_gpusvm_range_put(struct drm_gpusvm_range *range) +{ + kref_put(&range->refcount, drm_gpusvm_range_destroy); +} +EXPORT_SYMBOL_GPL(drm_gpusvm_range_put); + +/** + * drm_gpusvm_range_pages_valid() - GPU SVM range pages valid + * @gpusvm: Pointer to the GPU SVM structure + * @range: Pointer to the GPU SVM range structure + * + * This function determines if a GPU SVM range pages are valid. Expected be + * called holding gpusvm->notifier_lock and as the last step before committing a + * GPU binding. This is akin to a notifier seqno check in the HMM documentation + * but due to wider notifiers (i.e., notifiers which span multiple ranges) this + * function is required for finer grained checking (i.e., per range) if pages + * are valid. + * + * Return: True if GPU SVM range has valid pages, False otherwise + */ +bool drm_gpusvm_range_pages_valid(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_range *range) +{ + lockdep_assert_held(&gpusvm->notifier_lock); + + return range->flags.has_devmem_pages || range->flags.has_dma_mapping; +} +EXPORT_SYMBOL_GPL(drm_gpusvm_range_pages_valid); + +/** + * drm_gpusvm_range_pages_valid_unlocked() - GPU SVM range pages valid unlocked + * @gpusvm: Pointer to the GPU SVM structure + * @range: Pointer to the GPU SVM range structure + * + * This function determines if a GPU SVM range pages are valid. Expected be + * called without holding gpusvm->notifier_lock. + * + * Return: True if GPU SVM range has valid pages, False otherwise + */ +static bool +drm_gpusvm_range_pages_valid_unlocked(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_range *range) +{ + bool pages_valid; + + if (!range->dma_addr) + return false; + + drm_gpusvm_notifier_lock(gpusvm); + pages_valid = drm_gpusvm_range_pages_valid(gpusvm, range); + if (!pages_valid) + drm_gpusvm_range_free_pages(gpusvm, range); + drm_gpusvm_notifier_unlock(gpusvm); + + return pages_valid; +} + +/** + * drm_gpusvm_range_get_pages() - Get pages for a GPU SVM range + * @gpusvm: Pointer to the GPU SVM structure + * @range: Pointer to the GPU SVM range structure + * @ctx: GPU SVM context + * + * This function gets pages for a GPU SVM range and ensures they are mapped for + * DMA access. + * + * Return: 0 on success, negative error code on failure. + */ +int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_range *range, + const struct drm_gpusvm_ctx *ctx) +{ + struct mmu_interval_notifier *notifier = &range->notifier->notifier; + struct hmm_range hmm_range = { + .default_flags = HMM_PFN_REQ_FAULT | (ctx->read_only ? 0 : + HMM_PFN_REQ_WRITE), + .notifier = notifier, + .start = drm_gpusvm_range_start(range), + .end = drm_gpusvm_range_end(range), + .dev_private_owner = gpusvm->device_private_page_owner, + }; + struct mm_struct *mm = gpusvm->mm; + struct drm_gpusvm_zdd *zdd; + unsigned long timeout = + jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); + unsigned long i, j; + unsigned long npages = npages_in_range(drm_gpusvm_range_start(range), + drm_gpusvm_range_end(range)); + unsigned long num_dma_mapped; + unsigned int order = 0; + unsigned long *pfns; + struct page **pages; + int err = 0; + struct dev_pagemap *pagemap; + struct drm_pagemap *dpagemap; + +retry: + hmm_range.notifier_seq = mmu_interval_read_begin(notifier); + if (drm_gpusvm_range_pages_valid_unlocked(gpusvm, range)) + goto set_seqno; + + pfns = kvmalloc_array(npages, sizeof(*pfns), GFP_KERNEL); + if (!pfns) + return -ENOMEM; + + if (!mmget_not_zero(mm)) { + err = -EFAULT; + goto err_free; + } + + hmm_range.hmm_pfns = pfns; + while (true) { + mmap_read_lock(mm); + err = hmm_range_fault(&hmm_range); + mmap_read_unlock(mm); + + if (err == -EBUSY) { + if (time_after(jiffies, timeout)) + break; + + hmm_range.notifier_seq = + mmu_interval_read_begin(notifier); + continue; + } + break; + } + mmput(mm); + if (err) + goto err_free; + + pages = (struct page **)pfns; +map_pages: + /* + * Perform all dma mappings under the notifier lock to not + * access freed pages. A notifier will either block on + * the notifier lock or unmap dma. + */ + drm_gpusvm_notifier_lock(gpusvm); + + if (range->flags.unmapped) { + drm_gpusvm_notifier_unlock(gpusvm); + err = -EFAULT; + goto err_free; + } + + if (mmu_interval_read_retry(notifier, hmm_range.notifier_seq)) { + drm_gpusvm_notifier_unlock(gpusvm); + kvfree(pfns); + goto retry; + } + + if (!range->dma_addr) { + /* Unlock and restart mapping to allocate memory. */ + drm_gpusvm_notifier_unlock(gpusvm); + range->dma_addr = kvmalloc_array(npages, + sizeof(*range->dma_addr), + GFP_KERNEL); + if (!range->dma_addr) { + err = -ENOMEM; + goto err_free; + } + goto map_pages; + } + + zdd = NULL; + num_dma_mapped = 0; + for (i = 0, j = 0; i < npages; ++j) { + struct page *page = hmm_pfn_to_page(pfns[i]); + + order = hmm_pfn_to_map_order(pfns[i]); + if (is_device_private_page(page) || + is_device_coherent_page(page)) { + if (zdd != page->zone_device_data && i > 0) { + err = -EOPNOTSUPP; + goto err_unmap; + } + zdd = page->zone_device_data; + if (pagemap != page->pgmap) { + if (i > 0) { + err = -EOPNOTSUPP; + goto err_unmap; + } + + pagemap = page->pgmap; + dpagemap = zdd->devmem_allocation->dpagemap; + if (drm_WARN_ON(gpusvm->drm, !dpagemap)) { + /* + * Raced. This is not supposed to happen + * since hmm_range_fault() should've migrated + * this page to system. + */ + err = -EAGAIN; + goto err_unmap; + } + } + range->dma_addr[j] = + dpagemap->ops->device_map(dpagemap, + gpusvm->drm->dev, + page, order, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(gpusvm->drm->dev, + range->dma_addr[j].addr)) { + err = -EFAULT; + goto err_unmap; + } + + pages[i] = page; + } else { + dma_addr_t addr; + + if (is_zone_device_page(page) || zdd) { + err = -EOPNOTSUPP; + goto err_unmap; + } + + addr = dma_map_page(gpusvm->drm->dev, + page, 0, + PAGE_SIZE << order, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(gpusvm->drm->dev, addr)) { + err = -EFAULT; + goto err_unmap; + } + + range->dma_addr[j] = drm_pagemap_device_addr_encode + (addr, DRM_INTERCONNECT_SYSTEM, order, + DMA_BIDIRECTIONAL); + } + i += 1 << order; + num_dma_mapped = i; + } + + range->flags.has_dma_mapping = true; + if (zdd) { + range->flags.has_devmem_pages = true; + range->dpagemap = dpagemap; + } + + drm_gpusvm_notifier_unlock(gpusvm); + kvfree(pfns); +set_seqno: + range->notifier_seq = hmm_range.notifier_seq; + + return 0; + +err_unmap: + __drm_gpusvm_range_unmap_pages(gpusvm, range, num_dma_mapped); + drm_gpusvm_notifier_unlock(gpusvm); +err_free: + kvfree(pfns); + if (err == -EAGAIN) + goto retry; + return err; +} +EXPORT_SYMBOL_GPL(drm_gpusvm_range_get_pages); + +/** + * drm_gpusvm_range_unmap_pages() - Unmap pages associated with a GPU SVM range + * @gpusvm: Pointer to the GPU SVM structure + * @range: Pointer to the GPU SVM range structure + * @ctx: GPU SVM context + * + * This function unmaps pages associated with a GPU SVM range. If @in_notifier + * is set, it is assumed that gpusvm->notifier_lock is held in write mode; if it + * is clear, it acquires gpusvm->notifier_lock in read mode. Must be called on + * each GPU SVM range attached to notifier in gpusvm->ops->invalidate for IOMMU + * security model. + */ +void drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_range *range, + const struct drm_gpusvm_ctx *ctx) +{ + unsigned long npages = npages_in_range(drm_gpusvm_range_start(range), + drm_gpusvm_range_end(range)); + + if (ctx->in_notifier) + lockdep_assert_held_write(&gpusvm->notifier_lock); + else + drm_gpusvm_notifier_lock(gpusvm); + + __drm_gpusvm_range_unmap_pages(gpusvm, range, npages); + + if (!ctx->in_notifier) + drm_gpusvm_notifier_unlock(gpusvm); +} +EXPORT_SYMBOL_GPL(drm_gpusvm_range_unmap_pages); + +/** + * drm_gpusvm_migration_unlock_put_page() - Put a migration page + * @page: Pointer to the page to put + * + * This function unlocks and puts a page. + */ +static void drm_gpusvm_migration_unlock_put_page(struct page *page) +{ + unlock_page(page); + put_page(page); +} + +/** + * drm_gpusvm_migration_unlock_put_pages() - Put migration pages + * @npages: Number of pages + * @migrate_pfn: Array of migrate page frame numbers + * + * This function unlocks and puts an array of pages. + */ +static void drm_gpusvm_migration_unlock_put_pages(unsigned long npages, + unsigned long *migrate_pfn) +{ + unsigned long i; + + for (i = 0; i < npages; ++i) { + struct page *page; + + if (!migrate_pfn[i]) + continue; + + page = migrate_pfn_to_page(migrate_pfn[i]); + drm_gpusvm_migration_unlock_put_page(page); + migrate_pfn[i] = 0; + } +} + +/** + * drm_gpusvm_get_devmem_page() - Get a reference to a device memory page + * @page: Pointer to the page + * @zdd: Pointer to the GPU SVM zone device data + * + * This function associates the given page with the specified GPU SVM zone + * device data and initializes it for zone device usage. + */ +static void drm_gpusvm_get_devmem_page(struct page *page, + struct drm_gpusvm_zdd *zdd) +{ + page->zone_device_data = drm_gpusvm_zdd_get(zdd); + zone_device_page_init(page); +} + +/** + * drm_gpusvm_migrate_map_pages() - Map migration pages for GPU SVM migration + * @dev: The device for which the pages are being mapped + * @dma_addr: Array to store DMA addresses corresponding to mapped pages + * @migrate_pfn: Array of migrate page frame numbers to map + * @npages: Number of pages to map + * @dir: Direction of data transfer (e.g., DMA_BIDIRECTIONAL) + * + * This function maps pages of memory for migration usage in GPU SVM. It + * iterates over each page frame number provided in @migrate_pfn, maps the + * corresponding page, and stores the DMA address in the provided @dma_addr + * array. + * + * Return: 0 on success, -EFAULT if an error occurs during mapping. + */ +static int drm_gpusvm_migrate_map_pages(struct device *dev, + dma_addr_t *dma_addr, + unsigned long *migrate_pfn, + unsigned long npages, + enum dma_data_direction dir) +{ + unsigned long i; + + for (i = 0; i < npages; ++i) { + struct page *page = migrate_pfn_to_page(migrate_pfn[i]); + + if (!page) + continue; + + if (WARN_ON_ONCE(is_zone_device_page(page))) + return -EFAULT; + + dma_addr[i] = dma_map_page(dev, page, 0, PAGE_SIZE, dir); + if (dma_mapping_error(dev, dma_addr[i])) + return -EFAULT; + } + + return 0; +} + +/** + * drm_gpusvm_migrate_unmap_pages() - Unmap pages previously mapped for GPU SVM migration + * @dev: The device for which the pages were mapped + * @dma_addr: Array of DMA addresses corresponding to mapped pages + * @npages: Number of pages to unmap + * @dir: Direction of data transfer (e.g., DMA_BIDIRECTIONAL) + * + * This function unmaps previously mapped pages of memory for GPU Shared Virtual + * Memory (SVM). It iterates over each DMA address provided in @dma_addr, checks + * if it's valid and not already unmapped, and unmaps the corresponding page. + */ +static void drm_gpusvm_migrate_unmap_pages(struct device *dev, + dma_addr_t *dma_addr, + unsigned long npages, + enum dma_data_direction dir) +{ + unsigned long i; + + for (i = 0; i < npages; ++i) { + if (!dma_addr[i] || dma_mapping_error(dev, dma_addr[i])) + continue; + + dma_unmap_page(dev, dma_addr[i], PAGE_SIZE, dir); + } +} + +/** + * drm_gpusvm_migrate_to_devmem() - Migrate GPU SVM range to device memory + * @gpusvm: Pointer to the GPU SVM structure + * @range: Pointer to the GPU SVM range structure + * @devmem_allocation: Pointer to the device memory allocation. The caller + * should hold a reference to the device memory allocation, + * which should be dropped via ops->devmem_release or upon + * the failure of this function. + * @ctx: GPU SVM context + * + * This function migrates the specified GPU SVM range to device memory. It + * performs the necessary setup and invokes the driver-specific operations for + * migration to device memory. Upon successful return, @devmem_allocation can + * safely reference @range until ops->devmem_release is called which only upon + * successful return. Expected to be called while holding the mmap lock in read + * mode. + * + * Return: 0 on success, negative error code on failure. + */ +int drm_gpusvm_migrate_to_devmem(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_range *range, + struct drm_gpusvm_devmem *devmem_allocation, + const struct drm_gpusvm_ctx *ctx) +{ + const struct drm_gpusvm_devmem_ops *ops = devmem_allocation->ops; + unsigned long start = drm_gpusvm_range_start(range), + end = drm_gpusvm_range_end(range); + struct migrate_vma migrate = { + .start = start, + .end = end, + .pgmap_owner = gpusvm->device_private_page_owner, + .flags = MIGRATE_VMA_SELECT_SYSTEM, + }; + struct mm_struct *mm = gpusvm->mm; + unsigned long i, npages = npages_in_range(start, end); + struct vm_area_struct *vas; + struct drm_gpusvm_zdd *zdd = NULL; + struct page **pages; + dma_addr_t *dma_addr; + void *buf; + int err; + + mmap_assert_locked(gpusvm->mm); + + if (!range->flags.migrate_devmem) + return -EINVAL; + + if (!ops->populate_devmem_pfn || !ops->copy_to_devmem || + !ops->copy_to_ram) + return -EOPNOTSUPP; + + vas = vma_lookup(mm, start); + if (!vas) { + err = -ENOENT; + goto err_out; + } + + if (end > vas->vm_end || start < vas->vm_start) { + err = -EINVAL; + goto err_out; + } + + if (!vma_is_anonymous(vas)) { + err = -EBUSY; + goto err_out; + } + + buf = kvcalloc(npages, 2 * sizeof(*migrate.src) + sizeof(*dma_addr) + + sizeof(*pages), GFP_KERNEL); + if (!buf) { + err = -ENOMEM; + goto err_out; + } + dma_addr = buf + (2 * sizeof(*migrate.src) * npages); + pages = buf + (2 * sizeof(*migrate.src) + sizeof(*dma_addr)) * npages; + + zdd = drm_gpusvm_zdd_alloc(gpusvm->device_private_page_owner); + if (!zdd) { + err = -ENOMEM; + goto err_free; + } + + migrate.vma = vas; + migrate.src = buf; + migrate.dst = migrate.src + npages; + + err = migrate_vma_setup(&migrate); + if (err) + goto err_free; + + if (!migrate.cpages) { + err = -EFAULT; + goto err_free; + } + + if (migrate.cpages != npages) { + err = -EBUSY; + goto err_finalize; + } + + err = ops->populate_devmem_pfn(devmem_allocation, npages, migrate.dst); + if (err) + goto err_finalize; + + err = drm_gpusvm_migrate_map_pages(devmem_allocation->dev, dma_addr, + migrate.src, npages, DMA_TO_DEVICE); + if (err) + goto err_finalize; + + for (i = 0; i < npages; ++i) { + struct page *page = pfn_to_page(migrate.dst[i]); + + pages[i] = page; + migrate.dst[i] = migrate_pfn(migrate.dst[i]); + drm_gpusvm_get_devmem_page(page, zdd); + } + + err = ops->copy_to_devmem(pages, dma_addr, npages); + if (err) + goto err_finalize; + + /* Upon success bind devmem allocation to range and zdd */ + zdd->devmem_allocation = devmem_allocation; /* Owns ref */ + +err_finalize: + if (err) + drm_gpusvm_migration_unlock_put_pages(npages, migrate.dst); + migrate_vma_pages(&migrate); + migrate_vma_finalize(&migrate); + drm_gpusvm_migrate_unmap_pages(devmem_allocation->dev, dma_addr, npages, + DMA_TO_DEVICE); +err_free: + if (zdd) + drm_gpusvm_zdd_put(zdd); + kvfree(buf); +err_out: + return err; +} +EXPORT_SYMBOL_GPL(drm_gpusvm_migrate_to_devmem); + +/** + * drm_gpusvm_migrate_populate_ram_pfn() - Populate RAM PFNs for a VM area + * @vas: Pointer to the VM area structure, can be NULL + * @fault_page: Fault page + * @npages: Number of pages to populate + * @mpages: Number of pages to migrate + * @src_mpfn: Source array of migrate PFNs + * @mpfn: Array of migrate PFNs to populate + * @addr: Start address for PFN allocation + * + * This function populates the RAM migrate page frame numbers (PFNs) for the + * specified VM area structure. It allocates and locks pages in the VM area for + * RAM usage. If vas is non-NULL use alloc_page_vma for allocation, if NULL use + * alloc_page for allocation. + * + * Return: 0 on success, negative error code on failure. + */ +static int drm_gpusvm_migrate_populate_ram_pfn(struct vm_area_struct *vas, + struct page *fault_page, + unsigned long npages, + unsigned long *mpages, + unsigned long *src_mpfn, + unsigned long *mpfn, + unsigned long addr) +{ + unsigned long i; + + for (i = 0; i < npages; ++i, addr += PAGE_SIZE) { + struct page *page, *src_page; + + if (!(src_mpfn[i] & MIGRATE_PFN_MIGRATE)) + continue; + + src_page = migrate_pfn_to_page(src_mpfn[i]); + if (!src_page) + continue; + + if (fault_page) { + if (src_page->zone_device_data != + fault_page->zone_device_data) + continue; + } + + if (vas) + page = alloc_page_vma(GFP_HIGHUSER, vas, addr); + else + page = alloc_page(GFP_HIGHUSER); + + if (!page) + goto free_pages; + + mpfn[i] = migrate_pfn(page_to_pfn(page)); + } + + for (i = 0; i < npages; ++i) { + struct page *page = migrate_pfn_to_page(mpfn[i]); + + if (!page) + continue; + + WARN_ON_ONCE(!trylock_page(page)); + ++*mpages; + } + + return 0; + +free_pages: + for (i = 0; i < npages; ++i) { + struct page *page = migrate_pfn_to_page(mpfn[i]); + + if (!page) + continue; + + put_page(page); + mpfn[i] = 0; + } + return -ENOMEM; +} + +/** + * drm_gpusvm_evict_to_ram() - Evict GPU SVM range to RAM + * @devmem_allocation: Pointer to the device memory allocation + * + * Similar to __drm_gpusvm_migrate_to_ram but does not require mmap lock and + * migration done via migrate_device_* functions. + * + * Return: 0 on success, negative error code on failure. + */ +int drm_gpusvm_evict_to_ram(struct drm_gpusvm_devmem *devmem_allocation) +{ + const struct drm_gpusvm_devmem_ops *ops = devmem_allocation->ops; + unsigned long npages, mpages = 0; + struct page **pages; + unsigned long *src, *dst; + dma_addr_t *dma_addr; + void *buf; + int i, err = 0; + unsigned int retry_count = 2; + + npages = devmem_allocation->size >> PAGE_SHIFT; + +retry: + if (!mmget_not_zero(devmem_allocation->mm)) + return -EFAULT; + + buf = kvcalloc(npages, 2 * sizeof(*src) + sizeof(*dma_addr) + + sizeof(*pages), GFP_KERNEL); + if (!buf) { + err = -ENOMEM; + goto err_out; + } + src = buf; + dst = buf + (sizeof(*src) * npages); + dma_addr = buf + (2 * sizeof(*src) * npages); + pages = buf + (2 * sizeof(*src) + sizeof(*dma_addr)) * npages; + + err = ops->populate_devmem_pfn(devmem_allocation, npages, src); + if (err) + goto err_free; + + err = migrate_device_pfns(src, npages); + if (err) + goto err_free; + + err = drm_gpusvm_migrate_populate_ram_pfn(NULL, NULL, npages, &mpages, + src, dst, 0); + if (err || !mpages) + goto err_finalize; + + err = drm_gpusvm_migrate_map_pages(devmem_allocation->dev, dma_addr, + dst, npages, DMA_FROM_DEVICE); + if (err) + goto err_finalize; + + for (i = 0; i < npages; ++i) + pages[i] = migrate_pfn_to_page(src[i]); + + err = ops->copy_to_ram(pages, dma_addr, npages); + if (err) + goto err_finalize; + +err_finalize: + if (err) + drm_gpusvm_migration_unlock_put_pages(npages, dst); + migrate_device_pages(src, dst, npages); + migrate_device_finalize(src, dst, npages); + drm_gpusvm_migrate_unmap_pages(devmem_allocation->dev, dma_addr, npages, + DMA_FROM_DEVICE); +err_free: + kvfree(buf); +err_out: + mmput_async(devmem_allocation->mm); + + if (completion_done(&devmem_allocation->detached)) + return 0; + + if (retry_count--) { + cond_resched(); + goto retry; + } + + return err ?: -EBUSY; +} +EXPORT_SYMBOL_GPL(drm_gpusvm_evict_to_ram); + +/** + * __drm_gpusvm_migrate_to_ram() - Migrate GPU SVM range to RAM (internal) + * @vas: Pointer to the VM area structure + * @device_private_page_owner: Device private pages owner + * @page: Pointer to the page for fault handling (can be NULL) + * @fault_addr: Fault address + * @size: Size of migration + * + * This internal function performs the migration of the specified GPU SVM range + * to RAM. It sets up the migration, populates + dma maps RAM PFNs, and + * invokes the driver-specific operations for migration to RAM. + * + * Return: 0 on success, negative error code on failure. + */ +static int __drm_gpusvm_migrate_to_ram(struct vm_area_struct *vas, + void *device_private_page_owner, + struct page *page, + unsigned long fault_addr, + unsigned long size) +{ + struct migrate_vma migrate = { + .vma = vas, + .pgmap_owner = device_private_page_owner, + .flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE | + MIGRATE_VMA_SELECT_DEVICE_COHERENT, + .fault_page = page, + }; + struct drm_gpusvm_zdd *zdd; + const struct drm_gpusvm_devmem_ops *ops; + struct device *dev = NULL; + unsigned long npages, mpages = 0; + struct page **pages; + dma_addr_t *dma_addr; + unsigned long start, end; + void *buf; + int i, err = 0; + + start = ALIGN_DOWN(fault_addr, size); + end = ALIGN(fault_addr + 1, size); + + /* Corner where VMA area struct has been partially unmapped */ + if (start < vas->vm_start) + start = vas->vm_start; + if (end > vas->vm_end) + end = vas->vm_end; + + migrate.start = start; + migrate.end = end; + npages = npages_in_range(start, end); + + buf = kvcalloc(npages, 2 * sizeof(*migrate.src) + sizeof(*dma_addr) + + sizeof(*pages), GFP_KERNEL); + if (!buf) { + err = -ENOMEM; + goto err_out; + } + dma_addr = buf + (2 * sizeof(*migrate.src) * npages); + pages = buf + (2 * sizeof(*migrate.src) + sizeof(*dma_addr)) * npages; + + migrate.vma = vas; + migrate.src = buf; + migrate.dst = migrate.src + npages; + + err = migrate_vma_setup(&migrate); + if (err) + goto err_free; + + /* Raced with another CPU fault, nothing to do */ + if (!migrate.cpages) + goto err_free; + + if (!page) { + for (i = 0; i < npages; ++i) { + if (!(migrate.src[i] & MIGRATE_PFN_MIGRATE)) + continue; + + page = migrate_pfn_to_page(migrate.src[i]); + break; + } + + if (!page) + goto err_finalize; + } + zdd = page->zone_device_data; + ops = zdd->devmem_allocation->ops; + dev = zdd->devmem_allocation->dev; + + err = drm_gpusvm_migrate_populate_ram_pfn(vas, page, npages, &mpages, + migrate.src, migrate.dst, + start); + if (err) + goto err_finalize; + + err = drm_gpusvm_migrate_map_pages(dev, dma_addr, migrate.dst, npages, + DMA_FROM_DEVICE); + if (err) + goto err_finalize; + + for (i = 0; i < npages; ++i) + pages[i] = migrate_pfn_to_page(migrate.src[i]); + + err = ops->copy_to_ram(pages, dma_addr, npages); + if (err) + goto err_finalize; + +err_finalize: + if (err) + drm_gpusvm_migration_unlock_put_pages(npages, migrate.dst); + migrate_vma_pages(&migrate); + migrate_vma_finalize(&migrate); + if (dev) + drm_gpusvm_migrate_unmap_pages(dev, dma_addr, npages, + DMA_FROM_DEVICE); +err_free: + kvfree(buf); +err_out: + + return err; +} + +/** + * drm_gpusvm_range_evict - Evict GPU SVM range + * @range: Pointer to the GPU SVM range to be removed + * + * This function evicts the specified GPU SVM range. This function will not + * evict coherent pages. + * + * Return: 0 on success, a negative error code on failure. + */ +int drm_gpusvm_range_evict(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_range *range) +{ + struct mmu_interval_notifier *notifier = &range->notifier->notifier; + struct hmm_range hmm_range = { + .default_flags = HMM_PFN_REQ_FAULT, + .notifier = notifier, + .start = drm_gpusvm_range_start(range), + .end = drm_gpusvm_range_end(range), + .dev_private_owner = NULL, + }; + unsigned long timeout = + jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); + unsigned long *pfns; + unsigned long npages = npages_in_range(drm_gpusvm_range_start(range), + drm_gpusvm_range_end(range)); + int err = 0; + struct mm_struct *mm = gpusvm->mm; + + if (!mmget_not_zero(mm)) + return -EFAULT; + + pfns = kvmalloc_array(npages, sizeof(*pfns), GFP_KERNEL); + if (!pfns) + return -ENOMEM; + + hmm_range.hmm_pfns = pfns; + while (!time_after(jiffies, timeout)) { + hmm_range.notifier_seq = mmu_interval_read_begin(notifier); + if (time_after(jiffies, timeout)) { + err = -ETIME; + break; + } + + mmap_read_lock(mm); + err = hmm_range_fault(&hmm_range); + mmap_read_unlock(mm); + if (err != -EBUSY) + break; + } + + kvfree(pfns); + mmput(mm); + + return err; +} +EXPORT_SYMBOL_GPL(drm_gpusvm_range_evict); + +/** + * drm_gpusvm_page_free() - Put GPU SVM zone device data associated with a page + * @page: Pointer to the page + * + * This function is a callback used to put the GPU SVM zone device data + * associated with a page when it is being released. + */ +static void drm_gpusvm_page_free(struct page *page) +{ + drm_gpusvm_zdd_put(page->zone_device_data); +} + +/** + * drm_gpusvm_migrate_to_ram() - Migrate GPU SVM range to RAM (page fault handler) + * @vmf: Pointer to the fault information structure + * + * This function is a page fault handler used to migrate a GPU SVM range to RAM. + * It retrieves the GPU SVM range information from the faulting page and invokes + * the internal migration function to migrate the range back to RAM. + * + * Return: VM_FAULT_SIGBUS on failure, 0 on success. + */ +static vm_fault_t drm_gpusvm_migrate_to_ram(struct vm_fault *vmf) +{ + struct drm_gpusvm_zdd *zdd = vmf->page->zone_device_data; + int err; + + err = __drm_gpusvm_migrate_to_ram(vmf->vma, + zdd->device_private_page_owner, + vmf->page, vmf->address, + zdd->devmem_allocation->size); + + return err ? VM_FAULT_SIGBUS : 0; +} + +/* + * drm_gpusvm_pagemap_ops - Device page map operations for GPU SVM + */ +static const struct dev_pagemap_ops drm_gpusvm_pagemap_ops = { + .page_free = drm_gpusvm_page_free, + .migrate_to_ram = drm_gpusvm_migrate_to_ram, +}; + +/** + * drm_gpusvm_pagemap_ops_get() - Retrieve GPU SVM device page map operations + * + * Return: Pointer to the GPU SVM device page map operations structure. + */ +const struct dev_pagemap_ops *drm_gpusvm_pagemap_ops_get(void) +{ + return &drm_gpusvm_pagemap_ops; +} +EXPORT_SYMBOL_GPL(drm_gpusvm_pagemap_ops_get); + +/** + * drm_gpusvm_has_mapping() - Check if GPU SVM has mapping for the given address range + * @gpusvm: Pointer to the GPU SVM structure. + * @start: Start address + * @end: End address + * + * Return: True if GPU SVM has mapping, False otherwise + */ +bool drm_gpusvm_has_mapping(struct drm_gpusvm *gpusvm, unsigned long start, + unsigned long end) +{ + struct drm_gpusvm_notifier *notifier; + + drm_gpusvm_for_each_notifier(notifier, gpusvm, start, end) { + struct drm_gpusvm_range *range = NULL; + + drm_gpusvm_for_each_range(range, notifier, start, end) + return true; + } + + return false; +} +EXPORT_SYMBOL_GPL(drm_gpusvm_has_mapping); + +/** + * drm_gpusvm_range_set_unmapped() - Mark a GPU SVM range as unmapped + * @range: Pointer to the GPU SVM range structure. + * @mmu_range: Pointer to the MMU notifier range structure. + * + * This function marks a GPU SVM range as unmapped and sets the partial_unmap flag + * if the range partially falls within the provided MMU notifier range. + */ +void drm_gpusvm_range_set_unmapped(struct drm_gpusvm_range *range, + const struct mmu_notifier_range *mmu_range) +{ + lockdep_assert_held_write(&range->gpusvm->notifier_lock); + + range->flags.unmapped = true; + if (drm_gpusvm_range_start(range) < mmu_range->start || + drm_gpusvm_range_end(range) > mmu_range->end) + range->flags.partial_unmap = true; +} +EXPORT_SYMBOL_GPL(drm_gpusvm_range_set_unmapped); + +/** + * drm_gpusvm_devmem_init() - Initialize a GPU SVM device memory allocation + * + * @dev: Pointer to the device structure which device memory allocation belongs to + * @mm: Pointer to the mm_struct for the address space + * @ops: Pointer to the operations structure for GPU SVM device memory + * @dpagemap: The struct drm_pagemap we're allocating from. + * @size: Size of device memory allocation + */ +void drm_gpusvm_devmem_init(struct drm_gpusvm_devmem *devmem_allocation, + struct device *dev, struct mm_struct *mm, + const struct drm_gpusvm_devmem_ops *ops, + struct drm_pagemap *dpagemap, size_t size) +{ + init_completion(&devmem_allocation->detached); + devmem_allocation->dev = dev; + devmem_allocation->mm = mm; + devmem_allocation->ops = ops; + devmem_allocation->dpagemap = dpagemap; + devmem_allocation->size = size; +} +EXPORT_SYMBOL_GPL(drm_gpusvm_devmem_init); + +MODULE_DESCRIPTION("DRM GPUSVM"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c index 372c3683c193..55b9e9bfcc4d 100644 --- a/drivers/gpu/drm/i915/display/g4x_dp.c +++ b/drivers/gpu/drm/i915/display/g4x_dp.c @@ -1311,7 +1311,7 @@ bool g4x_dp_init(struct intel_display *display, intel_encoder->devdata = devdata; - mutex_init(&dig_port->hdcp_mutex); + mutex_init(&dig_port->hdcp.mutex); if (drm_encoder_init(display->drm, &intel_encoder->base, &intel_dp_enc_funcs, DRM_MODE_ENCODER_TMDS, diff --git a/drivers/gpu/drm/i915/display/g4x_hdmi.c b/drivers/gpu/drm/i915/display/g4x_hdmi.c index d9d1304dcc36..3dc2c59a3df0 100644 --- a/drivers/gpu/drm/i915/display/g4x_hdmi.c +++ b/drivers/gpu/drm/i915/display/g4x_hdmi.c @@ -715,7 +715,7 @@ bool g4x_hdmi_init(struct intel_display *display, intel_encoder->devdata = devdata; - mutex_init(&dig_port->hdcp_mutex); + mutex_init(&dig_port->hdcp.mutex); if (drm_encoder_init(display->drm, &intel_encoder->base, &intel_hdmi_enc_funcs, DRM_MODE_ENCODER_TMDS, diff --git a/drivers/gpu/drm/i915/display/i9xx_wm.c b/drivers/gpu/drm/i915/display/i9xx_wm.c index 497850a6ac81..7c80e37c1c5f 100644 --- a/drivers/gpu/drm/i915/display/i9xx_wm.c +++ b/drivers/gpu/drm/i915/display/i9xx_wm.c @@ -3902,12 +3902,6 @@ static void g4x_wm_sanitize(struct drm_i915_private *dev_priv) mutex_unlock(&dev_priv->display.wm.wm_mutex); } -static void g4x_wm_get_hw_state_and_sanitize(struct drm_i915_private *i915) -{ - g4x_wm_get_hw_state(i915); - g4x_wm_sanitize(i915); -} - static void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv) { struct vlv_wm_values *wm = &dev_priv->display.wm.vlv; @@ -4055,12 +4049,6 @@ static void vlv_wm_sanitize(struct drm_i915_private *dev_priv) mutex_unlock(&dev_priv->display.wm.wm_mutex); } -static void vlv_wm_get_hw_state_and_sanitize(struct drm_i915_private *i915) -{ - vlv_wm_get_hw_state(i915); - vlv_wm_sanitize(i915); -} - /* * FIXME should probably kill this and improve * the real watermark readout/sanitation instead @@ -4122,14 +4110,16 @@ static const struct intel_wm_funcs vlv_wm_funcs = { .initial_watermarks = vlv_initial_watermarks, .optimize_watermarks = vlv_optimize_watermarks, .atomic_update_watermarks = vlv_atomic_update_fifo, - .get_hw_state = vlv_wm_get_hw_state_and_sanitize, + .get_hw_state = vlv_wm_get_hw_state, + .sanitize = vlv_wm_sanitize, }; static const struct intel_wm_funcs g4x_wm_funcs = { .compute_watermarks = g4x_compute_watermarks, .initial_watermarks = g4x_initial_watermarks, .optimize_watermarks = g4x_optimize_watermarks, - .get_hw_state = g4x_wm_get_hw_state_and_sanitize, + .get_hw_state = g4x_wm_get_hw_state, + .sanitize = g4x_wm_sanitize, }; static const struct intel_wm_funcs pnv_wm_funcs = { diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index 5d3d54922d62..402b7b2e1829 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -1647,7 +1647,7 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder, if (ret) return ret; - ret = intel_panel_fitting(pipe_config, conn_state); + ret = intel_pfit_compute_config(pipe_config, conn_state); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_acpi.c b/drivers/gpu/drm/i915/display/intel_acpi.c index bbf8c5a8fdbd..1addd6288241 100644 --- a/drivers/gpu/drm/i915/display/intel_acpi.c +++ b/drivers/gpu/drm/i915/display/intel_acpi.c @@ -9,6 +9,8 @@ #include <linux/acpi.h> #include <acpi/video.h> +#include <drm/drm_print.h> + #include "i915_utils.h" #include "intel_acpi.h" #include "intel_display_core.h" diff --git a/drivers/gpu/drm/i915/display/intel_atomic.h b/drivers/gpu/drm/i915/display/intel_atomic.h index e506f6a87344..a5a7e2906ba8 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.h +++ b/drivers/gpu/drm/i915/display/intel_atomic.h @@ -14,7 +14,6 @@ struct drm_connector_state; struct drm_crtc; struct drm_crtc_state; struct drm_device; -struct drm_i915_private; struct drm_property; struct intel_atomic_state; struct intel_connector; diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c index 124cd9ddba0b..7276179df878 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c @@ -36,12 +36,15 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_blend.h> +#include <drm/drm_damage_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_gem.h> #include <drm/drm_gem_atomic_helper.h> -#include "i915_drv.h" +#include "gem/i915_gem_object.h" #include "i915_config.h" +#include "i915_scheduler_types.h" +#include "i915_vma.h" #include "i9xx_plane_regs.h" #include "intel_atomic_plane.h" #include "intel_cdclk.h" @@ -131,6 +134,7 @@ intel_plane_duplicate_state(struct drm_plane *plane) intel_state->ggtt_vma = NULL; intel_state->dpt_vma = NULL; intel_state->flags = 0; + intel_state->damage = DRM_RECT_INIT(0, 0, 0, 0); /* add reference to fb */ if (intel_state->hw.fb) @@ -164,10 +168,10 @@ intel_plane_destroy_state(struct drm_plane *plane, bool intel_plane_needs_physical(struct intel_plane *plane) { - struct drm_i915_private *i915 = to_i915(plane->base.dev); + struct intel_display *display = to_intel_display(plane); return plane->id == PLANE_CURSOR && - DISPLAY_INFO(i915)->cursor_needs_physical; + DISPLAY_INFO(display)->cursor_needs_physical; } bool intel_plane_can_async_flip(struct intel_plane *plane, u64 modifier) @@ -272,7 +276,7 @@ int intel_plane_calc_min_cdclk(struct intel_atomic_state *state, struct intel_plane *plane, bool *need_cdclk_calc) { - struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + struct intel_display *display = to_intel_display(plane); const struct intel_plane_state *plane_state = intel_atomic_get_new_plane_state(state, plane); struct intel_crtc *crtc = to_intel_crtc(plane_state->hw.crtc); @@ -317,7 +321,7 @@ int intel_plane_calc_min_cdclk(struct intel_atomic_state *state, cdclk_state->min_cdclk[crtc->pipe]) return 0; - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] min cdclk (%d kHz) > [CRTC:%d:%s] min cdclk (%d kHz)\n", plane->base.base.id, plane->base.name, new_crtc_state->min_cdclk[plane->id], @@ -336,6 +340,25 @@ static void intel_plane_clear_hw_state(struct intel_plane_state *plane_state) memset(&plane_state->hw, 0, sizeof(plane_state->hw)); } +static void +intel_plane_copy_uapi_plane_damage(struct intel_plane_state *new_plane_state, + const struct intel_plane_state *old_uapi_plane_state, + const struct intel_plane_state *new_uapi_plane_state) +{ + struct intel_display *display = to_intel_display(new_plane_state); + struct drm_rect *damage = &new_plane_state->damage; + + /* damage property tracking enabled from display version 12 onwards */ + if (DISPLAY_VER(display) < 12) + return; + + if (!drm_atomic_helper_damage_merged(&old_uapi_plane_state->uapi, + &new_uapi_plane_state->uapi, + damage)) + /* Incase helper fails, mark whole plane region as damage */ + *damage = drm_plane_state_src(&new_uapi_plane_state->uapi); +} + void intel_plane_copy_uapi_to_hw_state(struct intel_plane_state *plane_state, const struct intel_plane_state *from_plane_state, struct intel_crtc *crtc) @@ -411,7 +434,7 @@ static bool intel_plane_do_async_flip(struct intel_plane *plane, const struct intel_crtc_state *old_crtc_state, const struct intel_crtc_state *new_crtc_state) { - struct drm_i915_private *i915 = to_i915(plane->base.dev); + struct intel_display *display = to_intel_display(plane); if (!plane->async_flip) return false; @@ -432,7 +455,7 @@ static bool intel_plane_do_async_flip(struct intel_plane *plane, * extend this so other scanout parameters (stride/etc) could * be changed as well... */ - return DISPLAY_VER(i915) < 9 || old_crtc_state->uapi.async_flip; + return DISPLAY_VER(display) < 9 || old_crtc_state->uapi.async_flip; } static bool i9xx_must_disable_cxsr(const struct intel_crtc_state *new_crtc_state, @@ -536,16 +559,16 @@ static int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_cr const struct intel_plane_state *old_plane_state, struct intel_plane_state *new_plane_state) { + struct intel_display *display = to_intel_display(new_crtc_state); struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); struct intel_plane *plane = to_intel_plane(new_plane_state->uapi.plane); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); bool mode_changed = intel_crtc_needs_modeset(new_crtc_state); bool was_crtc_enabled = old_crtc_state->hw.active; bool is_crtc_enabled = new_crtc_state->hw.active; bool turn_off, turn_on, visible, was_visible; int ret; - if (DISPLAY_VER(dev_priv) >= 9 && plane->id != PLANE_CURSOR) { + if (DISPLAY_VER(display) >= 9 && plane->id != PLANE_CURSOR) { ret = skl_update_scaler_plane(new_crtc_state, new_plane_state); if (ret) return ret; @@ -554,7 +577,7 @@ static int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_cr was_visible = old_plane_state->uapi.visible; visible = new_plane_state->uapi.visible; - if (!was_crtc_enabled && drm_WARN_ON(&dev_priv->drm, was_visible)) + if (!was_crtc_enabled && drm_WARN_ON(display->drm, was_visible)) was_visible = false; /* @@ -578,7 +601,7 @@ static int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_cr turn_off = was_visible && (!visible || mode_changed); turn_on = visible && (!was_visible || mode_changed); - drm_dbg_atomic(&dev_priv->drm, + drm_dbg_atomic(display->drm, "[CRTC:%d:%s] with [PLANE:%d:%s] visible %i -> %i, off %i, on %i, ms %i\n", crtc->base.base.id, crtc->base.name, plane->base.base.id, plane->base.name, @@ -588,11 +611,11 @@ static int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_cr if (visible || was_visible) new_crtc_state->fb_bits |= plane->frontbuffer_bit; - if (HAS_GMCH(dev_priv) && + if (HAS_GMCH(display) && i9xx_must_disable_cxsr(new_crtc_state, old_plane_state, new_plane_state)) new_crtc_state->disable_cxsr = true; - if ((IS_IRONLAKE(dev_priv) || IS_SANDYBRIDGE(dev_priv) || IS_IVYBRIDGE(dev_priv)) && + if ((display->platform.ironlake || display->platform.sandybridge || display->platform.ivybridge) && ilk_must_disable_cxsr(new_crtc_state, old_plane_state, new_plane_state)) new_crtc_state->disable_cxsr = true; @@ -685,10 +708,10 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_ struct intel_plane * intel_crtc_get_plane(struct intel_crtc *crtc, enum plane_id plane_id) { - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); struct intel_plane *plane; - for_each_intel_plane_on_crtc(&i915->drm, crtc, plane) { + for_each_intel_plane_on_crtc(display->drm, crtc, plane) { if (plane->id == plane_id) return plane; } @@ -705,6 +728,7 @@ int intel_plane_atomic_check(struct intel_atomic_state *state, const struct intel_plane_state *old_plane_state = intel_atomic_get_old_plane_state(state, plane); const struct intel_plane_state *new_primary_crtc_plane_state; + const struct intel_plane_state *old_primary_crtc_plane_state; struct intel_crtc *crtc = intel_crtc_for_pipe(display, plane->pipe); const struct intel_crtc_state *old_crtc_state = intel_atomic_get_old_crtc_state(state, crtc); @@ -719,10 +743,17 @@ int intel_plane_atomic_check(struct intel_atomic_state *state, new_primary_crtc_plane_state = intel_atomic_get_new_plane_state(state, primary_crtc_plane); + old_primary_crtc_plane_state = + intel_atomic_get_old_plane_state(state, primary_crtc_plane); } else { new_primary_crtc_plane_state = new_plane_state; + old_primary_crtc_plane_state = old_plane_state; } + intel_plane_copy_uapi_plane_damage(new_plane_state, + old_primary_crtc_plane_state, + new_primary_crtc_plane_state); + intel_plane_copy_uapi_to_hw_state(new_plane_state, new_primary_crtc_plane_state, crtc); @@ -788,6 +819,9 @@ void intel_plane_update_noarm(struct intel_dsb *dsb, trace_intel_plane_update_noarm(plane_state, crtc); + if (plane->fbc) + intel_fbc_dirty_rect_update_noarm(dsb, plane); + if (plane->update_noarm) plane->update_noarm(dsb, plane, crtc_state, plane_state); } @@ -926,9 +960,9 @@ void intel_crtc_planes_update_arm(struct intel_dsb *dsb, struct intel_atomic_state *state, struct intel_crtc *crtc) { - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); - if (DISPLAY_VER(i915) >= 9) + if (DISPLAY_VER(display) >= 9) skl_crtc_planes_update_arm(dsb, state, crtc); else i9xx_crtc_planes_update_arm(dsb, state, crtc); @@ -939,7 +973,7 @@ int intel_atomic_plane_check_clipping(struct intel_plane_state *plane_state, int min_scale, int max_scale, bool can_position) { - struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); + struct intel_display *display = to_intel_display(plane_state); struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); struct drm_framebuffer *fb = plane_state->hw.fb; struct drm_rect *src = &plane_state->uapi.src; @@ -959,7 +993,7 @@ int intel_atomic_plane_check_clipping(struct intel_plane_state *plane_state, hscale = drm_rect_calc_hscale(src, dst, min_scale, max_scale); vscale = drm_rect_calc_vscale(src, dst, min_scale, max_scale); if (hscale < 0 || vscale < 0) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] invalid scaling "DRM_RECT_FP_FMT " -> " DRM_RECT_FMT "\n", plane->base.base.id, plane->base.name, DRM_RECT_FP_ARG(src), DRM_RECT_ARG(dst)); @@ -976,7 +1010,7 @@ int intel_atomic_plane_check_clipping(struct intel_plane_state *plane_state, if (!can_position && plane_state->uapi.visible && !drm_rect_equals(dst, clip)) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] plane (" DRM_RECT_FMT ") must cover entire CRTC (" DRM_RECT_FMT ")\n", plane->base.base.id, plane->base.name, DRM_RECT_ARG(dst), DRM_RECT_ARG(clip)); @@ -991,7 +1025,7 @@ int intel_atomic_plane_check_clipping(struct intel_plane_state *plane_state, int intel_plane_check_src_coordinates(struct intel_plane_state *plane_state) { - struct drm_i915_private *i915 = to_i915(plane_state->uapi.plane->dev); + struct intel_display *display = to_intel_display(plane_state); struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); const struct drm_framebuffer *fb = plane_state->hw.fb; struct drm_rect *src = &plane_state->uapi.src; @@ -1025,18 +1059,18 @@ int intel_plane_check_src_coordinates(struct intel_plane_state *plane_state) if (fb->format->format == DRM_FORMAT_RGB565 && rotated) { hsub = 2; vsub = 2; - } else if (DISPLAY_VER(i915) >= 20 && + } else if (DISPLAY_VER(display) >= 20 && intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier)) { /* * This allows NV12 and P0xx formats to have odd size and/or odd - * source coordinates on DISPLAY_VER(i915) >= 20 + * source coordinates on DISPLAY_VER(display) >= 20 */ hsub = 1; vsub = 1; /* Wa_16023981245 */ - if ((DISPLAY_VERx100(i915) == 2000 || - DISPLAY_VERx100(i915) == 3000) && + if ((DISPLAY_VERx100(display) == 2000 || + DISPLAY_VERx100(display) == 3000) && src_x % 2 != 0) hsub = 2; } else { @@ -1048,7 +1082,7 @@ int intel_plane_check_src_coordinates(struct intel_plane_state *plane_state) hsub = vsub = max(hsub, vsub); if (src_x % hsub || src_w % hsub) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] src x/w (%u, %u) must be a multiple of %u (rotated: %s)\n", plane->base.base.id, plane->base.name, src_x, src_w, hsub, str_yes_no(rotated)); @@ -1056,7 +1090,7 @@ int intel_plane_check_src_coordinates(struct intel_plane_state *plane_state) } if (src_y % vsub || src_h % vsub) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] src y/h (%u, %u) must be a multiple of %u (rotated: %s)\n", plane->base.base.id, plane->base.name, src_y, src_h, vsub, str_yes_no(rotated)); @@ -1119,11 +1153,11 @@ intel_prepare_plane_fb(struct drm_plane *_plane, { struct i915_sched_attr attr = { .priority = I915_PRIORITY_DISPLAY }; struct intel_plane *plane = to_intel_plane(_plane); + struct intel_display *display = to_intel_display(plane); struct intel_plane_state *new_plane_state = to_intel_plane_state(_new_plane_state); struct intel_atomic_state *state = to_intel_atomic_state(new_plane_state->uapi.state); - struct drm_i915_private *dev_priv = to_i915(plane->base.dev); struct intel_plane_state *old_plane_state = intel_atomic_get_old_plane_state(state, plane); struct drm_gem_object *obj = intel_fb_bo(new_plane_state->hw.fb); @@ -1181,7 +1215,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane, * that are not quite steady state without resorting to forcing * maximum clocks following a vblank miss (see do_rps_boost()). */ - intel_display_rps_mark_interactive(dev_priv, state, true); + intel_display_rps_mark_interactive(display, state, true); return 0; @@ -1202,17 +1236,17 @@ static void intel_cleanup_plane_fb(struct drm_plane *plane, struct drm_plane_state *_old_plane_state) { + struct intel_display *display = to_intel_display(plane->dev); struct intel_plane_state *old_plane_state = to_intel_plane_state(_old_plane_state); struct intel_atomic_state *state = to_intel_atomic_state(old_plane_state->uapi.state); - struct drm_i915_private *dev_priv = to_i915(plane->dev); struct drm_gem_object *obj = intel_fb_bo(old_plane_state->hw.fb); if (!obj) return; - intel_display_rps_mark_interactive(dev_priv, state, false); + intel_display_rps_mark_interactive(display, state, false); intel_plane_unpin_fb(old_plane_state); } @@ -1301,14 +1335,13 @@ static int icl_check_nv12_planes(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct intel_display *display = to_intel_display(state); - struct drm_i915_private *dev_priv = to_i915(state->base.dev); struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); struct intel_plane_state *plane_state; struct intel_plane *plane; int i; - if (DISPLAY_VER(dev_priv) < 11) + if (DISPLAY_VER(display) < 11) return 0; /* @@ -1336,7 +1369,7 @@ static int icl_check_nv12_planes(struct intel_atomic_state *state, if ((crtc_state->nv12_planes & BIT(plane->id)) == 0) continue; - for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, y_plane) { + for_each_intel_plane_on_crtc(display->drm, crtc, y_plane) { if (!icl_is_nv12_y_plane(display, y_plane->id)) continue; @@ -1351,7 +1384,7 @@ static int icl_check_nv12_planes(struct intel_atomic_state *state, } if (!y_plane_state) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] need %d free Y planes for planar YUV\n", crtc->base.base.id, crtc->base.name, hweight8(crtc_state->nv12_planes)); @@ -1368,10 +1401,10 @@ static int intel_crtc_add_planes_to_state(struct intel_atomic_state *state, struct intel_crtc *crtc, u8 plane_ids_mask) { - struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_plane *plane; - for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) { + for_each_intel_plane_on_crtc(display->drm, crtc, plane) { struct intel_plane_state *plane_state; if ((plane_ids_mask & BIT(plane->id)) == 0) @@ -1398,12 +1431,12 @@ int intel_atomic_add_affected_planes(struct intel_atomic_state *state, new_crtc_state->enabled_planes); } -static bool active_planes_affects_min_cdclk(struct drm_i915_private *dev_priv) +static bool active_planes_affects_min_cdclk(struct intel_display *display) { /* See {hsw,vlv,ivb}_plane_ratio() */ - return IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv) || - IS_CHERRYVIEW(dev_priv) || IS_VALLEYVIEW(dev_priv) || - IS_IVYBRIDGE(dev_priv); + return display->platform.broadwell || display->platform.haswell || + display->platform.cherryview || display->platform.valleyview || + display->platform.ivybridge; } static u8 intel_joiner_affected_planes(struct intel_atomic_state *state, @@ -1482,7 +1515,7 @@ static int intel_add_affected_planes(struct intel_atomic_state *state) int intel_atomic_check_planes(struct intel_atomic_state *state) { - struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_crtc_state *old_crtc_state, *new_crtc_state; struct intel_plane_state __maybe_unused *plane_state; struct intel_plane *plane; @@ -1496,7 +1529,7 @@ int intel_atomic_check_planes(struct intel_atomic_state *state) for_each_new_intel_plane_in_state(state, plane, plane_state, i) { ret = intel_plane_atomic_check(state, plane); if (ret) { - drm_dbg_atomic(&dev_priv->drm, + drm_dbg_atomic(display->drm, "[PLANE:%d:%s] atomic driver check failed\n", plane->base.base.id, plane->base.name); return ret; @@ -1516,7 +1549,7 @@ int intel_atomic_check_planes(struct intel_atomic_state *state) * the planes' minimum cdclk calculation. Add such planes * to the state before we compute the minimum cdclk. */ - if (!active_planes_affects_min_cdclk(dev_priv)) + if (!active_planes_affects_min_cdclk(display)) continue; old_active_planes = old_crtc_state->active_planes & ~BIT(PLANE_CURSOR); @@ -1532,3 +1565,8 @@ int intel_atomic_check_planes(struct intel_atomic_state *state) return 0; } + +u32 intel_plane_ggtt_offset(const struct intel_plane_state *plane_state) +{ + return i915_ggtt_offset(plane_state->ggtt_vma); +} diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.h b/drivers/gpu/drm/i915/display/intel_atomic_plane.h index 65edd88d28a9..6efac923dcbc 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.h +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.h @@ -88,4 +88,6 @@ int intel_atomic_add_affected_planes(struct intel_atomic_state *state, struct intel_crtc *crtc); int intel_atomic_check_planes(struct intel_atomic_state *state); +u32 intel_plane_ggtt_offset(const struct intel_plane_state *plane_state); + #endif /* __INTEL_ATOMIC_PLANE_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c index aaba438ab41e..ea935a5d94c8 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.c +++ b/drivers/gpu/drm/i915/display/intel_audio.c @@ -190,7 +190,9 @@ static const struct hdmi_aud_ncts hdmi_aud_ncts_36bpp[] = { */ static bool needs_wa_14020863754(struct intel_display *display) { - return DISPLAY_VER(display) == 20 || display->platform.battlemage; + return DISPLAY_VERx100(display) == 3000 || + DISPLAY_VERx100(display) == 2000 || + DISPLAY_VERx100(display) == 1401; } /* get AUD_CONFIG_PIXEL_CLOCK_HDMI_* value for mode */ diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index e0e4e9b62d8d..a8d08d7d82b3 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -2902,7 +2902,6 @@ init_vbt_panel_defaults(struct intel_panel *panel) static void init_vbt_missing_defaults(struct intel_display *display) { - struct drm_i915_private *i915 = to_i915(display->drm); unsigned int ports = DISPLAY_RUNTIME_INFO(display)->port_mask; enum port port; @@ -2912,13 +2911,13 @@ init_vbt_missing_defaults(struct intel_display *display) for_each_port_masked(port, ports) { struct intel_bios_encoder_data *devdata; struct child_device_config *child; - enum phy phy = intel_port_to_phy(i915, port); + enum phy phy = intel_port_to_phy(display, port); /* * VBT has the TypeC mode (native,TBT/USB) and we don't want * to detect it. */ - if (intel_phy_is_tc(i915, phy)) + if (intel_phy_is_tc(display, phy)) continue; /* Create fake child device config */ diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 23edc81741de..048be2872247 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -806,24 +806,6 @@ static int intel_bw_crtc_min_cdclk(const struct intel_crtc_state *crtc_state) return DIV_ROUND_UP_ULL(mul_u32_u32(intel_bw_crtc_data_rate(crtc_state), 10), 512); } -void intel_bw_crtc_update(struct intel_bw_state *bw_state, - const struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *i915 = to_i915(crtc->base.dev); - - bw_state->data_rate[crtc->pipe] = - intel_bw_crtc_data_rate(crtc_state); - bw_state->num_active_planes[crtc->pipe] = - intel_bw_crtc_num_active_planes(crtc_state); - bw_state->force_check_qgv = true; - - drm_dbg_kms(&i915->drm, "pipe %c data rate %u num active planes %u\n", - pipe_name(crtc->pipe), - bw_state->data_rate[crtc->pipe], - bw_state->num_active_planes[crtc->pipe]); -} - static unsigned int intel_bw_num_active_planes(struct drm_i915_private *dev_priv, const struct intel_bw_state *bw_state) { @@ -1422,6 +1404,62 @@ int intel_bw_atomic_check(struct intel_atomic_state *state) return 0; } +static void intel_bw_crtc_update(struct intel_bw_state *bw_state, + const struct intel_crtc_state *crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + + bw_state->data_rate[crtc->pipe] = + intel_bw_crtc_data_rate(crtc_state); + bw_state->num_active_planes[crtc->pipe] = + intel_bw_crtc_num_active_planes(crtc_state); + bw_state->force_check_qgv = true; + + drm_dbg_kms(&i915->drm, "pipe %c data rate %u num active planes %u\n", + pipe_name(crtc->pipe), + bw_state->data_rate[crtc->pipe], + bw_state->num_active_planes[crtc->pipe]); +} + +void intel_bw_update_hw_state(struct intel_display *display) +{ + struct intel_bw_state *bw_state = + to_intel_bw_state(display->bw.obj.state); + struct intel_crtc *crtc; + + if (DISPLAY_VER(display) < 9) + return; + + bw_state->active_pipes = 0; + + for_each_intel_crtc(display->drm, crtc) { + const struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + enum pipe pipe = crtc->pipe; + + if (crtc_state->hw.active) + bw_state->active_pipes |= BIT(pipe); + + if (DISPLAY_VER(display) >= 11) + intel_bw_crtc_update(bw_state, crtc_state); + } +} + +void intel_bw_crtc_disable_noatomic(struct intel_crtc *crtc) +{ + struct intel_display *display = to_intel_display(crtc); + struct intel_bw_state *bw_state = + to_intel_bw_state(display->bw.obj.state); + enum pipe pipe = crtc->pipe; + + if (DISPLAY_VER(display) < 9) + return; + + bw_state->data_rate[pipe] = 0; + bw_state->num_active_planes[pipe] = 0; +} + static struct intel_global_state * intel_bw_duplicate_state(struct intel_global_obj *obj) { diff --git a/drivers/gpu/drm/i915/display/intel_bw.h b/drivers/gpu/drm/i915/display/intel_bw.h index 161813cca473..3313e4eac4f0 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.h +++ b/drivers/gpu/drm/i915/display/intel_bw.h @@ -14,7 +14,9 @@ struct drm_i915_private; struct intel_atomic_state; +struct intel_crtc; struct intel_crtc_state; +struct intel_display; struct intel_dbuf_bw { unsigned int max_bw[I915_MAX_DBUF_SLICES]; @@ -73,13 +75,13 @@ intel_atomic_get_bw_state(struct intel_atomic_state *state); void intel_bw_init_hw(struct drm_i915_private *dev_priv); int intel_bw_init(struct drm_i915_private *dev_priv); int intel_bw_atomic_check(struct intel_atomic_state *state); -void intel_bw_crtc_update(struct intel_bw_state *bw_state, - const struct intel_crtc_state *crtc_state); int icl_pcode_restrict_qgv_points(struct drm_i915_private *dev_priv, u32 points_mask); int intel_bw_calc_min_cdclk(struct intel_atomic_state *state, bool *need_cdclk_calc); int intel_bw_min_cdclk(struct drm_i915_private *i915, const struct intel_bw_state *bw_state); +void intel_bw_update_hw_state(struct intel_display *display); +void intel_bw_crtc_disable_noatomic(struct intel_crtc *crtc); #endif /* __INTEL_BW_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index c6cfc57a0346..2a8749a0213e 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2788,7 +2788,7 @@ static int intel_planes_min_cdclk(const struct intel_crtc_state *crtc_state) return min_cdclk; } -int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state) +static int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state) { int min_cdclk; @@ -3340,6 +3340,34 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) return 0; } +void intel_cdclk_update_hw_state(struct intel_display *display) +{ + struct intel_cdclk_state *cdclk_state = + to_intel_cdclk_state(display->cdclk.obj.state); + struct intel_crtc *crtc; + + cdclk_state->active_pipes = 0; + + for_each_intel_crtc(display->drm, crtc) { + const struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + enum pipe pipe = crtc->pipe; + + if (crtc_state->hw.active) + cdclk_state->active_pipes |= BIT(pipe); + + cdclk_state->min_cdclk[pipe] = intel_crtc_compute_min_cdclk(crtc_state); + cdclk_state->min_voltage_level[pipe] = crtc_state->min_voltage_level; + } +} + +void intel_cdclk_crtc_disable_noatomic(struct intel_crtc *crtc) +{ + struct intel_display *display = to_intel_display(crtc); + + intel_cdclk_update_hw_state(display); +} + static int intel_compute_max_dotclk(struct intel_display *display) { int ppc = intel_cdclk_ppc(display, HAS_DOUBLE_WIDE(display)); diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h index 6b0e7a41eba3..a1cefd455d92 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.h +++ b/drivers/gpu/drm/i915/display/intel_cdclk.h @@ -12,6 +12,7 @@ #include "intel_global_state.h" struct intel_atomic_state; +struct intel_crtc; struct intel_crtc_state; struct intel_display; @@ -58,7 +59,6 @@ struct intel_cdclk_state { bool disable_pipes; }; -int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state); void intel_cdclk_init_hw(struct intel_display *display); void intel_cdclk_uninit_hw(struct intel_display *display); void intel_init_cdclk_hooks(struct intel_display *display); @@ -83,6 +83,8 @@ int intel_cdclk_atomic_check(struct intel_atomic_state *state, int intel_cdclk_state_set_joined_mbus(struct intel_atomic_state *state, bool joined_mbus); struct intel_cdclk_state * intel_atomic_get_cdclk_state(struct intel_atomic_state *state); +void intel_cdclk_update_hw_state(struct intel_display *display); +void intel_cdclk_crtc_disable_noatomic(struct intel_crtc *crtc); #define to_intel_cdclk_state(global_state) \ container_of_const((global_state), struct intel_cdclk_state, base) diff --git a/drivers/gpu/drm/i915/display/intel_combo_phy_regs.h b/drivers/gpu/drm/i915/display/intel_combo_phy_regs.h index 0964e392d02c..ee41acdccf4e 100644 --- a/drivers/gpu/drm/i915/display/intel_combo_phy_regs.h +++ b/drivers/gpu/drm/i915/display/intel_combo_phy_regs.h @@ -133,6 +133,8 @@ #define TX_TRAINING_EN REG_BIT(31) #define TAP2_DISABLE REG_BIT(30) #define TAP3_DISABLE REG_BIT(29) +#define CURSOR_PROGRAM REG_BIT(26) +#define COEFF_POLARITY REG_BIT(25) #define SCALING_MODE_SEL_MASK REG_GENMASK(20, 18) #define SCALING_MODE_SEL(x) REG_FIELD_PREP(SCALING_MODE_SEL_MASK, (x)) #define RTERM_SELECT_MASK REG_GENMASK(5, 3) diff --git a/drivers/gpu/drm/i915/display/intel_connector.c b/drivers/gpu/drm/i915/display/intel_connector.c index 358965fc7f55..e42357bd9e80 100644 --- a/drivers/gpu/drm/i915/display/intel_connector.c +++ b/drivers/gpu/drm/i915/display/intel_connector.c @@ -145,8 +145,8 @@ void intel_connector_destroy(struct drm_connector *connector) drm_connector_cleanup(connector); - if (intel_connector->port) - drm_dp_mst_put_port_malloc(intel_connector->port); + if (intel_connector->mst.port) + drm_dp_mst_put_port_malloc(intel_connector->mst.port); kfree(connector); } diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c index 321580b095e7..76ffb3f8467c 100644 --- a/drivers/gpu/drm/i915/display/intel_crt.c +++ b/drivers/gpu/drm/i915/display/intel_crt.c @@ -54,6 +54,7 @@ #include "intel_load_detect.h" #include "intel_pch_display.h" #include "intel_pch_refclk.h" +#include "intel_pfit.h" /* Here's the desired hotplug mode */ #define ADPA_HOTPLUG_BITS (ADPA_CRT_HOTPLUG_ENABLE | \ diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 7937f4de66cb..f38c998935b9 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -70,6 +70,7 @@ #include "intel_lspcon.h" #include "intel_mg_phy_regs.h" #include "intel_modeset_lock.h" +#include "intel_pfit.h" #include "intel_pps.h" #include "intel_psr.h" #include "intel_quirks.h" @@ -187,11 +188,8 @@ static i915_reg_t intel_ddi_buf_status_reg(struct intel_display *display, enum p return DDI_BUF_CTL(port); } -void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv, - enum port port) +void intel_wait_ddi_buf_idle(struct intel_display *display, enum port port) { - struct intel_display *display = &dev_priv->display; - /* * Bspec's platform specific timeouts: * MTL+ : 100 us @@ -890,7 +888,7 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder, encoder->base.base.id, encoder->base.name); if (!mst_pipe_mask && dp128b132b_pipe_mask) { - struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + struct intel_digital_port *dig_port = enc_to_dig_port(encoder); /* * If we don't have 8b/10b MST, but have more than one @@ -902,7 +900,8 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder, * we don't expect MST to have been enabled at that point, and * can assume it's SST. */ - if (hweight8(dp128b132b_pipe_mask) > 1 || intel_dp->is_mst) + if (hweight8(dp128b132b_pipe_mask) > 1 || + intel_dp_mst_encoder_active_links(dig_port)) mst_pipe_mask = dp128b132b_pipe_mask; } @@ -1194,7 +1193,8 @@ static void icl_ddi_combo_vswing_program(struct intel_encoder *encoder, /* Set PORT_TX_DW5 */ val = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN(0, phy)); val &= ~(SCALING_MODE_SEL_MASK | RTERM_SELECT_MASK | - TAP2_DISABLE | TAP3_DISABLE); + COEFF_POLARITY | CURSOR_PROGRAM | + TAP2_DISABLE | TAP3_DISABLE); val |= SCALING_MODE_SEL(0x2); val |= RTERM_SELECT(0x6); val |= TAP3_DISABLE; @@ -3095,7 +3095,7 @@ static void intel_ddi_buf_disable(struct intel_encoder *encoder, intel_de_rmw(dev_priv, DDI_BUF_CTL(port), DDI_BUF_CTL_ENABLE, 0); if (DISPLAY_VER(display) >= 14) - intel_wait_ddi_buf_idle(dev_priv, port); + intel_wait_ddi_buf_idle(display, port); mtl_ddi_disable_d2d(encoder); @@ -3107,7 +3107,7 @@ static void intel_ddi_buf_disable(struct intel_encoder *encoder, intel_ddi_disable_fec(encoder, crtc_state); if (DISPLAY_VER(display) < 14) - intel_wait_ddi_buf_idle(dev_priv, port); + intel_wait_ddi_buf_idle(display, port); intel_ddi_wait_for_fec_status(encoder, crtc_state, false); } @@ -4131,13 +4131,13 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder, } else if (ddi_mode == TRANS_DDI_MODE_SELECT_DP_MST) { intel_ddi_read_func_ctl_dp_mst(encoder, pipe_config, ddi_func_ctl); } else if (ddi_mode == TRANS_DDI_MODE_SELECT_FDI_OR_128B132B && HAS_DP20(display)) { - struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + struct intel_digital_port *dig_port = enc_to_dig_port(encoder); /* * If this is true, we know we're being called from mst stream * encoder's ->get_config(). */ - if (intel_dp->is_mst) + if (intel_dp_mst_encoder_active_links(dig_port)) intel_ddi_read_func_ctl_dp_mst(encoder, pipe_config, ddi_func_ctl); else intel_ddi_read_func_ctl_dp_sst(encoder, pipe_config, ddi_func_ctl); @@ -4583,7 +4583,7 @@ static void intel_ddi_encoder_destroy(struct drm_encoder *encoder) intel_display_power_flush_work(display); drm_encoder_cleanup(encoder); - kfree(dig_port->hdcp_port_data.streams); + kfree(dig_port->hdcp.port_data.streams); kfree(dig_port); } @@ -4661,6 +4661,7 @@ static int intel_ddi_init_dp_connector(struct intel_digital_port *dig_port) static int intel_hdmi_reset_link(struct intel_encoder *encoder, struct drm_modeset_acquire_ctx *ctx) { + struct intel_display *display = to_intel_display(encoder); struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_hdmi *hdmi = enc_to_intel_hdmi(encoder); struct intel_connector *connector = hdmi->attached_connector; @@ -4727,7 +4728,7 @@ static int intel_hdmi_reset_link(struct intel_encoder *encoder, * would be perfectly happy if were to just reconfigure * the SCDC settings on the fly. */ - return intel_modeset_commit_pipes(dev_priv, BIT(crtc->pipe), ctx); + return intel_modeset_commit_pipes(display, BIT(crtc->pipe), ctx); } static void intel_ddi_link_check(struct intel_encoder *encoder) @@ -5101,7 +5102,7 @@ void intel_ddi_init(struct intel_display *display, return; } - phy = intel_port_to_phy(dev_priv, port); + phy = intel_port_to_phy(display, port); /* * On platforms with HTI (aka HDPORT), if it's enabled at boot it may @@ -5138,7 +5139,7 @@ void intel_ddi_init(struct intel_display *display, return; } - if (intel_phy_is_snps(dev_priv, phy) && + if (intel_phy_is_snps(display, phy) && dev_priv->display.snps.phy_failed_calibration & BIT(phy)) { drm_dbg_kms(&dev_priv->drm, "SNPS PHY %c failed to calibrate, proceeding anyway\n", @@ -5161,7 +5162,7 @@ void intel_ddi_init(struct intel_display *display, port_name(port - PORT_D_XELPD + PORT_D), phy_name(phy)); } else if (DISPLAY_VER(dev_priv) >= 12) { - enum tc_port tc_port = intel_port_to_tc(dev_priv, port); + enum tc_port tc_port = intel_port_to_tc(display, port); drm_encoder_init(&dev_priv->drm, &encoder->base, &intel_ddi_funcs, DRM_MODE_ENCODER_TMDS, @@ -5171,7 +5172,7 @@ void intel_ddi_init(struct intel_display *display, tc_port != TC_PORT_NONE ? "TC" : "", tc_port != TC_PORT_NONE ? tc_port_name(tc_port) : phy_name(phy)); } else if (DISPLAY_VER(dev_priv) >= 11) { - enum tc_port tc_port = intel_port_to_tc(dev_priv, port); + enum tc_port tc_port = intel_port_to_tc(display, port); drm_encoder_init(&dev_priv->drm, &encoder->base, &intel_ddi_funcs, DRM_MODE_ENCODER_TMDS, @@ -5188,8 +5189,8 @@ void intel_ddi_init(struct intel_display *display, intel_encoder_link_check_init(encoder, intel_ddi_link_check); - mutex_init(&dig_port->hdcp_mutex); - dig_port->num_hdcp_streams = 0; + mutex_init(&dig_port->hdcp.mutex); + dig_port->hdcp.num_streams = 0; encoder->hotplug = intel_ddi_hotplug; encoder->compute_output_type = intel_ddi_compute_output_type; diff --git a/drivers/gpu/drm/i915/display/intel_ddi.h b/drivers/gpu/drm/i915/display/intel_ddi.h index 2faadd1441e2..353eb04079e9 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.h +++ b/drivers/gpu/drm/i915/display/intel_ddi.h @@ -9,7 +9,6 @@ #include "i915_reg_defs.h" struct drm_connector_state; -struct drm_i915_private; struct intel_atomic_state; struct intel_bios_encoder_data; struct intel_connector; @@ -54,8 +53,7 @@ void hsw_ddi_get_config(struct intel_encoder *encoder, struct intel_shared_dpll *icl_ddi_combo_get_pll(struct intel_encoder *encoder); void hsw_prepare_dp_ddi_buffers(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state); -void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv, - enum port port); +void intel_wait_ddi_buf_idle(struct intel_display *display, enum port port); void intel_ddi_init(struct intel_display *display, const struct intel_bios_encoder_data *devdata); bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe); diff --git a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h index 2133984a572b..29a190390192 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h +++ b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h @@ -8,7 +8,6 @@ #include <linux/types.h> -struct drm_i915_private; struct intel_encoder; struct intel_crtc_state; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 065fdf6dbb88..3afb85fe8536 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -104,6 +104,7 @@ #include "intel_pch_display.h" #include "intel_pch_refclk.h" #include "intel_pcode.h" +#include "intel_pfit.h" #include "intel_pipe_crc.h" #include "intel_plane_initial.h" #include "intel_pmdemand.h" @@ -181,16 +182,17 @@ int vlv_get_cck_clock_hpll(struct drm_i915_private *dev_priv, return hpll; } -void intel_update_czclk(struct drm_i915_private *dev_priv) +void intel_update_czclk(struct intel_display *display) { - if (!(IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))) + struct drm_i915_private *dev_priv = to_i915(display->drm); + + if (!display->platform.valleyview && !display->platform.cherryview) return; dev_priv->czclk_freq = vlv_get_cck_clock_hpll(dev_priv, "czclk", CCK_CZ_CLOCK_CONTROL); - drm_dbg(&dev_priv->drm, "CZ clock rate: %d kHz\n", - dev_priv->czclk_freq); + drm_dbg_kms(display->drm, "CZ clock rate: %d kHz\n", dev_priv->czclk_freq); } static bool is_hdr_mode(const struct intel_crtc_state *crtc_state) @@ -201,29 +203,29 @@ static bool is_hdr_mode(const struct intel_crtc_state *crtc_state) /* WA Display #0827: Gen9:all */ static void -skl_wa_827(struct drm_i915_private *dev_priv, enum pipe pipe, bool enable) +skl_wa_827(struct intel_display *display, enum pipe pipe, bool enable) { - intel_de_rmw(dev_priv, CLKGATE_DIS_PSL(pipe), + intel_de_rmw(display, CLKGATE_DIS_PSL(pipe), DUPS1_GATING_DIS | DUPS2_GATING_DIS, enable ? DUPS1_GATING_DIS | DUPS2_GATING_DIS : 0); } /* Wa_2006604312:icl,ehl */ static void -icl_wa_scalerclkgating(struct drm_i915_private *dev_priv, enum pipe pipe, +icl_wa_scalerclkgating(struct intel_display *display, enum pipe pipe, bool enable) { - intel_de_rmw(dev_priv, CLKGATE_DIS_PSL(pipe), + intel_de_rmw(display, CLKGATE_DIS_PSL(pipe), DPFR_GATING_DIS, enable ? DPFR_GATING_DIS : 0); } /* Wa_1604331009:icl,jsl,ehl */ static void -icl_wa_cursorclkgating(struct drm_i915_private *dev_priv, enum pipe pipe, +icl_wa_cursorclkgating(struct intel_display *display, enum pipe pipe, bool enable) { - intel_de_rmw(dev_priv, CLKGATE_DIS_PSL(pipe), + intel_de_rmw(display, CLKGATE_DIS_PSL(pipe), CURSOR_GATING_DIS, enable ? CURSOR_GATING_DIS : 0); } @@ -403,16 +405,16 @@ struct intel_crtc *intel_primary_crtc(const struct intel_crtc_state *crtc_state) static void intel_wait_for_pipe_off(const struct intel_crtc_state *old_crtc_state) { + struct intel_display *display = to_intel_display(old_crtc_state); struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - if (DISPLAY_VER(dev_priv) >= 4) { + if (DISPLAY_VER(display) >= 4) { enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder; /* Wait for the Pipe State to go off */ - if (intel_de_wait_for_clear(dev_priv, TRANSCONF(dev_priv, cpu_transcoder), + if (intel_de_wait_for_clear(display, TRANSCONF(display, cpu_transcoder), TRANSCONF_STATE_ENABLE, 100)) - drm_WARN(&dev_priv->drm, 1, "pipe_off wait timed out\n"); + drm_WARN(display->drm, 1, "pipe_off wait timed out\n"); } else { intel_wait_for_pipe_scanline_stopped(crtc); } @@ -466,10 +468,10 @@ static void assert_plane(struct intel_plane *plane, bool state) static void assert_planes_disabled(struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); struct intel_plane *plane; - for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) + for_each_intel_plane_on_crtc(display->drm, crtc, plane) assert_plane_disabled(plane); } @@ -477,7 +479,6 @@ void intel_enable_transcoder(const struct intel_crtc_state *new_crtc_state) { struct intel_display *display = to_intel_display(new_crtc_state); struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum transcoder cpu_transcoder = new_crtc_state->cpu_transcoder; enum pipe pipe = crtc->pipe; u32 val; @@ -491,7 +492,7 @@ void intel_enable_transcoder(const struct intel_crtc_state *new_crtc_state) * a plane. On ILK+ the pipe PLLs are integrated, so we don't * need the check. */ - if (HAS_GMCH(dev_priv)) { + if (HAS_GMCH(display)) { if (intel_crtc_has_type(new_crtc_state, INTEL_OUTPUT_DSI)) assert_dsi_pll_enabled(display); else @@ -508,11 +509,11 @@ void intel_enable_transcoder(const struct intel_crtc_state *new_crtc_state) } /* Wa_22012358565:adl-p */ - if (DISPLAY_VER(dev_priv) == 13) + if (DISPLAY_VER(display) == 13) intel_de_rmw(display, PIPE_ARB_CTL(display, pipe), 0, PIPE_ARB_USE_PROG_SLOTS); - if (DISPLAY_VER(dev_priv) >= 14) { + if (DISPLAY_VER(display) >= 14) { u32 clear = DP_DSC_INSERT_SF_AT_EOL_WA; u32 set = 0; @@ -526,7 +527,7 @@ void intel_enable_transcoder(const struct intel_crtc_state *new_crtc_state) val = intel_de_read(display, TRANSCONF(display, cpu_transcoder)); if (val & TRANSCONF_ENABLE) { /* we keep both pipes enabled on 830 */ - drm_WARN_ON(&dev_priv->drm, !IS_I830(dev_priv)); + drm_WARN_ON(display->drm, !display->platform.i830); return; } @@ -557,12 +558,11 @@ void intel_disable_transcoder(const struct intel_crtc_state *old_crtc_state) { struct intel_display *display = to_intel_display(old_crtc_state); struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder; enum pipe pipe = crtc->pipe; u32 val; - drm_dbg_kms(&dev_priv->drm, "disabling pipe %c\n", pipe_name(pipe)); + drm_dbg_kms(display->drm, "disabling pipe %c\n", pipe_name(pipe)); /* * Make sure planes won't keep trying to pump pixels to us, @@ -570,7 +570,7 @@ void intel_disable_transcoder(const struct intel_crtc_state *old_crtc_state) */ assert_planes_disabled(crtc); - val = intel_de_read(dev_priv, TRANSCONF(dev_priv, cpu_transcoder)); + val = intel_de_read(display, TRANSCONF(display, cpu_transcoder)); if ((val & TRANSCONF_ENABLE) == 0) return; @@ -582,17 +582,17 @@ void intel_disable_transcoder(const struct intel_crtc_state *old_crtc_state) val &= ~TRANSCONF_DOUBLE_WIDE; /* Don't disable pipe or pipe PLLs if needed */ - if (!IS_I830(dev_priv)) + if (!display->platform.i830) val &= ~TRANSCONF_ENABLE; /* Wa_1409098942:adlp+ */ - if (DISPLAY_VER(dev_priv) >= 13 && + if (DISPLAY_VER(display) >= 13 && old_crtc_state->dsc.compression_enable) val &= ~TRANSCONF_PIXEL_COUNT_SCALING_MASK; - intel_de_write(dev_priv, TRANSCONF(dev_priv, cpu_transcoder), val); + intel_de_write(display, TRANSCONF(display, cpu_transcoder), val); - if (DISPLAY_VER(dev_priv) >= 12) + if (DISPLAY_VER(display) >= 12) intel_de_rmw(display, CHICKEN_TRANS(display, cpu_transcoder), FECSTALL_DIS_DPTSTREAM_DPTTG, 0); @@ -641,7 +641,7 @@ void intel_set_plane_visible(struct intel_crtc_state *crtc_state, void intel_plane_fixup_bitmasks(struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct intel_display *display = to_intel_display(crtc_state); struct drm_plane *plane; /* @@ -652,7 +652,7 @@ void intel_plane_fixup_bitmasks(struct intel_crtc_state *crtc_state) crtc_state->enabled_planes = 0; crtc_state->active_planes = 0; - drm_for_each_plane_mask(plane, &dev_priv->drm, + drm_for_each_plane_mask(plane, display->drm, crtc_state->uapi.plane_mask) { crtc_state->enabled_planes |= BIT(to_intel_plane(plane)->id); crtc_state->active_planes |= BIT(to_intel_plane(plane)->id); @@ -669,18 +669,16 @@ void intel_plane_disable_noatomic(struct intel_crtc *crtc, struct intel_plane_state *plane_state = to_intel_plane_state(plane->base.state); - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "Disabling [PLANE:%d:%s] on [CRTC:%d:%s]\n", plane->base.base.id, plane->base.name, crtc->base.base.id, crtc->base.name); + intel_plane_set_invisible(crtc_state, plane_state); intel_set_plane_visible(crtc_state, plane_state, false); intel_plane_fixup_bitmasks(crtc_state); - crtc_state->data_rate[plane->id] = 0; - crtc_state->data_rate_y[plane->id] = 0; - crtc_state->rel_data_rate[plane->id] = 0; - crtc_state->rel_data_rate_y[plane->id] = 0; - crtc_state->min_cdclk[plane->id] = 0; + + skl_wm_plane_disable_noatomic(crtc, plane); if ((crtc_state->active_planes & ~BIT(PLANE_CURSOR)) == 0 && hsw_ips_disable(crtc_state)) { @@ -697,7 +695,7 @@ void intel_plane_disable_noatomic(struct intel_crtc *crtc, * event which is after the vblank start event, so we need to have a * wait-for-vblank between disabling the plane and the pipe. */ - if (HAS_GMCH(dev_priv) && + if (HAS_GMCH(display) && intel_set_memory_cxsr(dev_priv, false)) intel_plane_initial_vblank_wait(crtc); @@ -705,7 +703,7 @@ void intel_plane_disable_noatomic(struct intel_crtc *crtc, * Gen2 reports pipe underruns whenever all planes are disabled. * So disable underrun reporting before all the planes get disabled. */ - if (DISPLAY_VER(dev_priv) == 2 && !crtc_state->active_planes) + if (DISPLAY_VER(display) == 2 && !crtc_state->active_planes) intel_set_cpu_fifo_underrun_reporting(display, crtc->pipe, false); intel_plane_disable_arm(NULL, plane, crtc_state); @@ -725,12 +723,12 @@ intel_plane_fence_y_offset(const struct intel_plane_state *plane_state) static void icl_set_pipe_chicken(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; u32 tmp; - tmp = intel_de_read(dev_priv, PIPE_CHICKEN(pipe)); + tmp = intel_de_read(display, PIPE_CHICKEN(pipe)); /* * Display WA #1153: icl @@ -750,24 +748,24 @@ static void icl_set_pipe_chicken(const struct intel_crtc_state *crtc_state) * Underrun recovery must always be disabled on display 13+. * DG2 chicken bit meaning is inverted compared to other platforms. */ - if (IS_DG2(dev_priv)) + if (display->platform.dg2) tmp &= ~UNDERRUN_RECOVERY_ENABLE_DG2; - else if ((DISPLAY_VER(dev_priv) >= 13) && (DISPLAY_VER(dev_priv) < 30)) + else if ((DISPLAY_VER(display) >= 13) && (DISPLAY_VER(display) < 30)) tmp |= UNDERRUN_RECOVERY_DISABLE_ADLP; /* Wa_14010547955:dg2 */ - if (IS_DG2(dev_priv)) + if (display->platform.dg2) tmp |= DG2_RENDER_CCSTAG_4_3_EN; - intel_de_write(dev_priv, PIPE_CHICKEN(pipe), tmp); + intel_de_write(display, PIPE_CHICKEN(pipe), tmp); } -bool intel_has_pending_fb_unpin(struct drm_i915_private *dev_priv) +bool intel_has_pending_fb_unpin(struct intel_display *display) { struct drm_crtc *crtc; bool cleanup_done; - drm_for_each_crtc(crtc, &dev_priv->drm) { + drm_for_each_crtc(crtc, display->drm) { struct drm_crtc_commit *commit; spin_lock(&crtc->commit_lock); commit = list_first_entry_or_null(&crtc->commit_list, @@ -819,36 +817,6 @@ intel_get_crtc_new_encoder(const struct intel_atomic_state *state, return encoder; } -static void ilk_pfit_enable(const struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - const struct drm_rect *dst = &crtc_state->pch_pfit.dst; - enum pipe pipe = crtc->pipe; - int width = drm_rect_width(dst); - int height = drm_rect_height(dst); - int x = dst->x1; - int y = dst->y1; - - if (!crtc_state->pch_pfit.enabled) - return; - - /* Force use of hard-coded filter coefficients - * as some pre-programmed values are broken, - * e.g. x201. - */ - if (IS_IVYBRIDGE(dev_priv) || IS_HASWELL(dev_priv)) - intel_de_write_fw(dev_priv, PF_CTL(pipe), PF_ENABLE | - PF_FILTER_MED_3x3 | PF_PIPE_SEL_IVB(pipe)); - else - intel_de_write_fw(dev_priv, PF_CTL(pipe), PF_ENABLE | - PF_FILTER_MED_3x3); - intel_de_write_fw(dev_priv, PF_WIN_POS(pipe), - PF_WIN_XPOS(x) | PF_WIN_YPOS(y)); - intel_de_write_fw(dev_priv, PF_WIN_SZ(pipe), - PF_WIN_XSIZE(width) | PF_WIN_YSIZE(height)); -} - static void intel_crtc_dpms_overlay_disable(struct intel_crtc *crtc) { if (crtc->overlay) @@ -861,13 +829,13 @@ static void intel_crtc_dpms_overlay_disable(struct intel_crtc *crtc) static bool needs_nv12_wa(const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct intel_display *display = to_intel_display(crtc_state); if (!crtc_state->nv12_planes) return false; /* WA Display #0827: Gen9:all */ - if (DISPLAY_VER(dev_priv) == 9) + if (DISPLAY_VER(display) == 9) return true; return false; @@ -875,10 +843,10 @@ static bool needs_nv12_wa(const struct intel_crtc_state *crtc_state) static bool needs_scalerclk_wa(const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct intel_display *display = to_intel_display(crtc_state); /* Wa_2006604312:icl,ehl */ - if (crtc_state->scaler_state.scaler_users > 0 && DISPLAY_VER(dev_priv) == 11) + if (crtc_state->scaler_state.scaler_users > 0 && DISPLAY_VER(display) == 11) return true; return false; @@ -886,31 +854,31 @@ static bool needs_scalerclk_wa(const struct intel_crtc_state *crtc_state) static bool needs_cursorclk_wa(const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct intel_display *display = to_intel_display(crtc_state); /* Wa_1604331009:icl,jsl,ehl */ if (is_hdr_mode(crtc_state) && crtc_state->active_planes & BIT(PLANE_CURSOR) && - DISPLAY_VER(dev_priv) == 11) + DISPLAY_VER(display) == 11) return true; return false; } -static void intel_async_flip_vtd_wa(struct drm_i915_private *i915, +static void intel_async_flip_vtd_wa(struct intel_display *display, enum pipe pipe, bool enable) { - if (DISPLAY_VER(i915) == 9) { + if (DISPLAY_VER(display) == 9) { /* * "Plane N stretch max must be programmed to 11b (x1) * when Async flips are enabled on that plane." */ - intel_de_rmw(i915, CHICKEN_PIPESL_1(pipe), + intel_de_rmw(display, CHICKEN_PIPESL_1(pipe), SKL_PLANE1_STRETCH_MAX_MASK, enable ? SKL_PLANE1_STRETCH_MAX_X1 : SKL_PLANE1_STRETCH_MAX_X8); } else { /* Also needed on HSW/BDW albeit undocumented */ - intel_de_rmw(i915, CHICKEN_PIPESL_1(pipe), + intel_de_rmw(display, CHICKEN_PIPESL_1(pipe), HSW_PRI_STRETCH_MAX_MASK, enable ? HSW_PRI_STRETCH_MAX_X1 : HSW_PRI_STRETCH_MAX_X8); } @@ -918,10 +886,12 @@ static void intel_async_flip_vtd_wa(struct drm_i915_private *i915, static bool needs_async_flip_vtd_wa(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); return crtc_state->uapi.async_flip && i915_vtd_active(i915) && - (DISPLAY_VER(i915) == 9 || IS_BROADWELL(i915) || IS_HASWELL(i915)); + (DISPLAY_VER(display) == 9 || display->platform.broadwell || + display->platform.haswell); } static void intel_encoders_audio_enable(struct intel_atomic_state *state, @@ -1070,6 +1040,7 @@ static bool audio_disabling(const struct intel_crtc_state *old_crtc_state, static void intel_post_plane_update(struct intel_atomic_state *state, struct intel_crtc *crtc) { + struct intel_display *display = to_intel_display(state); struct drm_i915_private *dev_priv = to_i915(state->base.dev); const struct intel_crtc_state *old_crtc_state = intel_atomic_get_old_crtc_state(state, crtc); @@ -1088,19 +1059,19 @@ static void intel_post_plane_update(struct intel_atomic_state *state, if (needs_async_flip_vtd_wa(old_crtc_state) && !needs_async_flip_vtd_wa(new_crtc_state)) - intel_async_flip_vtd_wa(dev_priv, pipe, false); + intel_async_flip_vtd_wa(display, pipe, false); if (needs_nv12_wa(old_crtc_state) && !needs_nv12_wa(new_crtc_state)) - skl_wa_827(dev_priv, pipe, false); + skl_wa_827(display, pipe, false); if (needs_scalerclk_wa(old_crtc_state) && !needs_scalerclk_wa(new_crtc_state)) - icl_wa_scalerclkgating(dev_priv, pipe, false); + icl_wa_scalerclkgating(display, pipe, false); if (needs_cursorclk_wa(old_crtc_state) && !needs_cursorclk_wa(new_crtc_state)) - icl_wa_cursorclkgating(dev_priv, pipe, false); + icl_wa_cursorclkgating(display, pipe, false); if (intel_crtc_needs_color_update(new_crtc_state)) intel_color_post_update(new_crtc_state); @@ -1222,22 +1193,22 @@ static void intel_pre_plane_update(struct intel_atomic_state *state, if (!needs_async_flip_vtd_wa(old_crtc_state) && needs_async_flip_vtd_wa(new_crtc_state)) - intel_async_flip_vtd_wa(dev_priv, pipe, true); + intel_async_flip_vtd_wa(display, pipe, true); /* Display WA 827 */ if (!needs_nv12_wa(old_crtc_state) && needs_nv12_wa(new_crtc_state)) - skl_wa_827(dev_priv, pipe, true); + skl_wa_827(display, pipe, true); /* Wa_2006604312:icl,ehl */ if (!needs_scalerclk_wa(old_crtc_state) && needs_scalerclk_wa(new_crtc_state)) - icl_wa_scalerclkgating(dev_priv, pipe, true); + icl_wa_scalerclkgating(display, pipe, true); /* Wa_1604331009:icl,jsl,ehl */ if (!needs_cursorclk_wa(old_crtc_state) && needs_cursorclk_wa(new_crtc_state)) - icl_wa_cursorclkgating(dev_priv, pipe, true); + icl_wa_cursorclkgating(display, pipe, true); /* * Vblank time updates from the shadow to live plane control register @@ -1248,7 +1219,7 @@ static void intel_pre_plane_update(struct intel_atomic_state *state, * event which is after the vblank start event, so we need to have a * wait-for-vblank between disabling the plane and the pipe. */ - if (HAS_GMCH(dev_priv) && old_crtc_state->hw.active && + if (HAS_GMCH(display) && old_crtc_state->hw.active && new_crtc_state->disable_cxsr && intel_set_memory_cxsr(dev_priv, false)) intel_crtc_wait_for_next_vblank(crtc); @@ -1259,7 +1230,7 @@ static void intel_pre_plane_update(struct intel_atomic_state *state, * * WaCxSRDisabledForSpriteScaling:ivb */ - if (!HAS_GMCH(dev_priv) && old_crtc_state->hw.active && + if (!HAS_GMCH(display) && old_crtc_state->hw.active && new_crtc_state->disable_cxsr && ilk_disable_cxsr(dev_priv)) intel_crtc_wait_for_next_vblank(crtc); @@ -1295,7 +1266,7 @@ static void intel_pre_plane_update(struct intel_atomic_state *state, * chance of catching underruns with the intermediate watermarks * vs. the old plane configuration. */ - if (DISPLAY_VER(dev_priv) == 2 && planes_disabling(old_crtc_state, new_crtc_state)) + if (DISPLAY_VER(display) == 2 && planes_disabling(old_crtc_state, new_crtc_state)) intel_set_cpu_fifo_underrun_reporting(display, pipe, false); /* @@ -1336,7 +1307,7 @@ static void intel_crtc_disable_planes(struct intel_atomic_state *state, static void intel_encoders_update_prepare(struct intel_atomic_state *state) { - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_crtc_state *new_crtc_state, *old_crtc_state; struct intel_crtc *crtc; int i; @@ -1345,7 +1316,7 @@ static void intel_encoders_update_prepare(struct intel_atomic_state *state) * Make sure the DPLL state is up-to-date for fastset TypeC ports after non-blocking commits. * TODO: Update the DPLL state for all cases in the encoder->update_prepare() hook. */ - if (i915->display.dpll.mgr) { + if (display->dpll.mgr) { for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { if (intel_crtc_needs_modeset(new_crtc_state)) continue; @@ -1541,7 +1512,7 @@ static void ilk_crtc_enable(struct intel_atomic_state *state, struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; - if (drm_WARN_ON(&dev_priv->drm, crtc->active)) + if (drm_WARN_ON(display->drm, crtc->active)) return; /* @@ -1568,8 +1539,8 @@ static void ilk_crtc_enable(struct intel_atomic_state *state, if (new_crtc_state->has_pch_encoder) { ilk_pch_pre_enable(state, crtc); } else { - assert_fdi_tx_disabled(dev_priv, pipe); - assert_fdi_rx_disabled(dev_priv, pipe); + assert_fdi_tx_disabled(display, pipe); + assert_fdi_rx_disabled(display, pipe); } ilk_pfit_enable(new_crtc_state); @@ -1610,26 +1581,26 @@ static void ilk_crtc_enable(struct intel_atomic_state *state, /* Display WA #1180: WaDisableScalarClockGating: glk */ static bool glk_need_scaler_clock_gating_wa(const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + struct intel_display *display = to_intel_display(crtc_state); - return DISPLAY_VER(i915) == 10 && crtc_state->pch_pfit.enabled; + return DISPLAY_VER(display) == 10 && crtc_state->pch_pfit.enabled; } static void glk_pipe_scaler_clock_gating_wa(struct intel_crtc *crtc, bool enable) { - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); u32 mask = DPF_GATING_DIS | DPF_RAM_GATING_DIS | DPFR_GATING_DIS; - intel_de_rmw(i915, CLKGATE_DIS_PSL(crtc->pipe), + intel_de_rmw(display, CLKGATE_DIS_PSL(crtc->pipe), mask, enable ? mask : 0); } static void hsw_set_linetime_wm(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - intel_de_write(dev_priv, WM_LINETIME(crtc->pipe), + intel_de_write(display, WM_LINETIME(crtc->pipe), HSW_LINETIME(crtc_state->linetime) | HSW_IPS_LINETIME(crtc_state->ips_linetime)); } @@ -1645,8 +1616,8 @@ static void hsw_set_frame_start_delay(const struct intel_crtc_state *crtc_state) static void hsw_configure_cpu_transcoder(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; if (crtc_state->has_pch_encoder) { @@ -1660,11 +1631,11 @@ static void hsw_configure_cpu_transcoder(const struct intel_crtc_state *crtc_sta } intel_set_transcoder_timings(crtc_state); - if (HAS_VRR(dev_priv)) + if (HAS_VRR(display)) intel_vrr_set_transcoder_timings(crtc_state); if (cpu_transcoder != TRANSCODER_EDP) - intel_de_write(dev_priv, TRANS_MULT(dev_priv, cpu_transcoder), + intel_de_write(display, TRANS_MULT(display, cpu_transcoder), crtc_state->pixel_multiplier - 1); hsw_set_frame_start_delay(crtc_state); @@ -1678,12 +1649,11 @@ static void hsw_crtc_enable(struct intel_atomic_state *state, struct intel_display *display = to_intel_display(state); const struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum transcoder cpu_transcoder = new_crtc_state->cpu_transcoder; struct intel_crtc *pipe_crtc; int i; - if (drm_WARN_ON(&dev_priv->drm, crtc->active)) + if (drm_WARN_ON(display->drm, crtc->active)) return; for_each_pipe_crtc_modeset_enable(display, pipe_crtc, new_crtc_state, i) intel_dmc_enable_pipe(display, pipe_crtc->pipe); @@ -1706,12 +1676,12 @@ static void hsw_crtc_enable(struct intel_atomic_state *state, intel_dsc_enable(pipe_crtc_state); - if (HAS_UNCOMPRESSED_JOINER(dev_priv)) + if (HAS_UNCOMPRESSED_JOINER(display)) intel_uncompressed_joiner_enable(pipe_crtc_state); intel_set_pipe_src_size(pipe_crtc_state); - if (DISPLAY_VER(dev_priv) >= 9 || IS_BROADWELL(dev_priv)) + if (DISPLAY_VER(display) >= 9 || display->platform.broadwell) bdw_set_pipe_misc(NULL, pipe_crtc_state); } @@ -1727,7 +1697,7 @@ static void hsw_crtc_enable(struct intel_atomic_state *state, if (glk_need_scaler_clock_gating_wa(pipe_crtc_state)) glk_pipe_scaler_clock_gating_wa(pipe_crtc, true); - if (DISPLAY_VER(dev_priv) >= 9) + if (DISPLAY_VER(display) >= 9) skl_pfit_enable(pipe_crtc_state); else ilk_pfit_enable(pipe_crtc_state); @@ -1740,7 +1710,7 @@ static void hsw_crtc_enable(struct intel_atomic_state *state, hsw_set_linetime_wm(pipe_crtc_state); - if (DISPLAY_VER(dev_priv) >= 11) + if (DISPLAY_VER(display) >= 11) icl_set_pipe_chicken(pipe_crtc_state); intel_initial_watermarks(state, pipe_crtc); @@ -1763,7 +1733,7 @@ static void hsw_crtc_enable(struct intel_atomic_state *state, * enabling, we need to change the workaround. */ hsw_workaround_pipe = pipe_crtc_state->hsw_workaround_pipe; - if (IS_HASWELL(dev_priv) && hsw_workaround_pipe != INVALID_PIPE) { + if (display->platform.haswell && hsw_workaround_pipe != INVALID_PIPE) { struct intel_crtc *wa_crtc = intel_crtc_for_pipe(display, hsw_workaround_pipe); @@ -1773,22 +1743,6 @@ static void hsw_crtc_enable(struct intel_atomic_state *state, } } -void ilk_pfit_disable(const struct intel_crtc_state *old_crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - enum pipe pipe = crtc->pipe; - - /* To avoid upsetting the power well on haswell only disable the pfit if - * it's in use. The hw state code will make sure we get this right. */ - if (!old_crtc_state->pch_pfit.enabled) - return; - - intel_de_write_fw(dev_priv, PF_CTL(pipe), 0); - intel_de_write_fw(dev_priv, PF_WIN_POS(pipe), 0); - intel_de_write_fw(dev_priv, PF_WIN_SZ(pipe), 0); -} - static void ilk_crtc_disable(struct intel_atomic_state *state, struct intel_crtc *crtc) { @@ -1856,32 +1810,6 @@ static void hsw_crtc_disable(struct intel_atomic_state *state, intel_dmc_disable_pipe(display, pipe_crtc->pipe); } -static void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state) -{ - struct intel_display *display = to_intel_display(crtc_state); - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - - if (!crtc_state->gmch_pfit.control) - return; - - /* - * The panel fitter should only be adjusted whilst the pipe is disabled, - * according to register description and PRM. - */ - drm_WARN_ON(display->drm, - intel_de_read(display, PFIT_CONTROL(display)) & PFIT_ENABLE); - assert_transcoder_disabled(display, crtc_state->cpu_transcoder); - - intel_de_write(display, PFIT_PGM_RATIOS(display), - crtc_state->gmch_pfit.pgm_ratios); - intel_de_write(display, PFIT_CONTROL(display), - crtc_state->gmch_pfit.control); - - /* Border color in case we don't scale up to the full screen. Black by - * default, change to something else for debugging. */ - intel_de_write(display, BCLRPAT(display, crtc->pipe), 0); -} - /* Prefer intel_encoder_is_combo() */ bool intel_phy_is_combo(struct intel_display *display, enum phy phy) { @@ -1905,47 +1833,47 @@ bool intel_phy_is_combo(struct intel_display *display, enum phy phy) } /* Prefer intel_encoder_is_tc() */ -bool intel_phy_is_tc(struct drm_i915_private *dev_priv, enum phy phy) +bool intel_phy_is_tc(struct intel_display *display, enum phy phy) { /* * Discrete GPU phy's are not attached to FIA's to support TC * subsystem Legacy or non-legacy, and only support native DP/HDMI */ - if (IS_DGFX(dev_priv)) + if (display->platform.dgfx) return false; - if (DISPLAY_VER(dev_priv) >= 13) + if (DISPLAY_VER(display) >= 13) return phy >= PHY_F && phy <= PHY_I; - else if (IS_TIGERLAKE(dev_priv)) + else if (display->platform.tigerlake) return phy >= PHY_D && phy <= PHY_I; - else if (IS_ICELAKE(dev_priv)) + else if (display->platform.icelake) return phy >= PHY_C && phy <= PHY_F; return false; } /* Prefer intel_encoder_is_snps() */ -bool intel_phy_is_snps(struct drm_i915_private *dev_priv, enum phy phy) +bool intel_phy_is_snps(struct intel_display *display, enum phy phy) { /* * For DG2, and for DG2 only, all four "combo" ports and the TC1 port * (PHY E) use Synopsis PHYs. See intel_phy_is_tc(). */ - return IS_DG2(dev_priv) && phy > PHY_NONE && phy <= PHY_E; + return display->platform.dg2 && phy > PHY_NONE && phy <= PHY_E; } /* Prefer intel_encoder_to_phy() */ -enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port) +enum phy intel_port_to_phy(struct intel_display *display, enum port port) { - if (DISPLAY_VER(i915) >= 13 && port >= PORT_D_XELPD) + if (DISPLAY_VER(display) >= 13 && port >= PORT_D_XELPD) return PHY_D + port - PORT_D_XELPD; - else if (DISPLAY_VER(i915) >= 13 && port >= PORT_TC1) + else if (DISPLAY_VER(display) >= 13 && port >= PORT_TC1) return PHY_F + port - PORT_TC1; - else if (IS_ALDERLAKE_S(i915) && port >= PORT_TC1) + else if (display->platform.alderlake_s && port >= PORT_TC1) return PHY_B + port - PORT_TC1; - else if ((IS_DG1(i915) || IS_ROCKETLAKE(i915)) && port >= PORT_TC1) + else if ((display->platform.dg1 || display->platform.rocketlake) && port >= PORT_TC1) return PHY_C + port - PORT_TC1; - else if ((IS_JASPERLAKE(i915) || IS_ELKHARTLAKE(i915)) && + else if ((display->platform.jasperlake || display->platform.elkhartlake) && port == PORT_D) return PHY_A; @@ -1953,12 +1881,12 @@ enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port) } /* Prefer intel_encoder_to_tc() */ -enum tc_port intel_port_to_tc(struct drm_i915_private *dev_priv, enum port port) +enum tc_port intel_port_to_tc(struct intel_display *display, enum port port) { - if (!intel_phy_is_tc(dev_priv, intel_port_to_phy(dev_priv, port))) + if (!intel_phy_is_tc(display, intel_port_to_phy(display, port))) return TC_PORT_NONE; - if (DISPLAY_VER(dev_priv) >= 12) + if (DISPLAY_VER(display) >= 12) return TC_PORT_1 + port - PORT_TC1; else return TC_PORT_1 + port - PORT_C; @@ -1966,9 +1894,9 @@ enum tc_port intel_port_to_tc(struct drm_i915_private *dev_priv, enum port port) enum phy intel_encoder_to_phy(struct intel_encoder *encoder) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_display *display = to_intel_display(encoder); - return intel_port_to_phy(i915, encoder->port); + return intel_port_to_phy(display, encoder->port); } bool intel_encoder_is_combo(struct intel_encoder *encoder) @@ -1980,23 +1908,23 @@ bool intel_encoder_is_combo(struct intel_encoder *encoder) bool intel_encoder_is_snps(struct intel_encoder *encoder) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_display *display = to_intel_display(encoder); - return intel_phy_is_snps(i915, intel_encoder_to_phy(encoder)); + return intel_phy_is_snps(display, intel_encoder_to_phy(encoder)); } bool intel_encoder_is_tc(struct intel_encoder *encoder) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_display *display = to_intel_display(encoder); - return intel_phy_is_tc(i915, intel_encoder_to_phy(encoder)); + return intel_phy_is_tc(display, intel_encoder_to_phy(encoder)); } enum tc_port intel_encoder_to_tc(struct intel_encoder *encoder) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_display *display = to_intel_display(encoder); - return intel_port_to_tc(i915, encoder->port); + return intel_port_to_tc(display, encoder->port); } enum intel_display_power_domain @@ -2013,8 +1941,8 @@ intel_aux_power_domain(struct intel_digital_port *dig_port) static void get_crtc_power_domains(struct intel_crtc_state *crtc_state, struct intel_power_domain_mask *mask) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; struct drm_encoder *encoder; enum pipe pipe = crtc->pipe; @@ -2030,14 +1958,14 @@ static void get_crtc_power_domains(struct intel_crtc_state *crtc_state, crtc_state->pch_pfit.force_thru) set_bit(POWER_DOMAIN_PIPE_PANEL_FITTER(pipe), mask->bits); - drm_for_each_encoder_mask(encoder, &dev_priv->drm, + drm_for_each_encoder_mask(encoder, display->drm, crtc_state->uapi.encoder_mask) { struct intel_encoder *intel_encoder = to_intel_encoder(encoder); set_bit(intel_encoder->power_domain, mask->bits); } - if (HAS_DDI(dev_priv) && crtc_state->has_audio) + if (HAS_DDI(display) && crtc_state->has_audio) set_bit(POWER_DOMAIN_AUDIO_MMIO, mask->bits); if (crtc_state->shared_dpll) @@ -2105,22 +2033,21 @@ static void valleyview_crtc_enable(struct intel_atomic_state *state, struct intel_display *display = to_intel_display(crtc); const struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; - if (drm_WARN_ON(&dev_priv->drm, crtc->active)) + if (drm_WARN_ON(display->drm, crtc->active)) return; i9xx_configure_cpu_transcoder(new_crtc_state); intel_set_pipe_src_size(new_crtc_state); - intel_de_write(dev_priv, VLV_PIPE_MSA_MISC(pipe), 0); + intel_de_write(display, VLV_PIPE_MSA_MISC(display, pipe), 0); - if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_B) { - intel_de_write(dev_priv, CHV_BLEND(dev_priv, pipe), + if (display->platform.cherryview && pipe == PIPE_B) { + intel_de_write(display, CHV_BLEND(display, pipe), CHV_BLEND_LEGACY); - intel_de_write(dev_priv, CHV_CANVAS(dev_priv, pipe), 0); + intel_de_write(display, CHV_CANVAS(display, pipe), 0); } crtc->active = true; @@ -2129,7 +2056,7 @@ static void valleyview_crtc_enable(struct intel_atomic_state *state, intel_encoders_pre_pll_enable(state, crtc); - if (IS_CHERRYVIEW(dev_priv)) + if (display->platform.cherryview) chv_enable_pll(new_crtc_state); else vlv_enable_pll(new_crtc_state); @@ -2157,7 +2084,7 @@ static void i9xx_crtc_enable(struct intel_atomic_state *state, struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; - if (drm_WARN_ON(&dev_priv->drm, crtc->active)) + if (drm_WARN_ON(display->drm, crtc->active)) return; i9xx_configure_cpu_transcoder(new_crtc_state); @@ -2166,7 +2093,7 @@ static void i9xx_crtc_enable(struct intel_atomic_state *state, crtc->active = true; - if (DISPLAY_VER(dev_priv) != 2) + if (DISPLAY_VER(display) != 2) intel_set_cpu_fifo_underrun_reporting(display, pipe, true); intel_encoders_pre_enable(state, crtc); @@ -2186,24 +2113,10 @@ static void i9xx_crtc_enable(struct intel_atomic_state *state, intel_encoders_enable(state, crtc); /* prevents spurious underruns */ - if (DISPLAY_VER(dev_priv) == 2) + if (DISPLAY_VER(display) == 2) intel_crtc_wait_for_next_vblank(crtc); } -static void i9xx_pfit_disable(const struct intel_crtc_state *old_crtc_state) -{ - struct intel_display *display = to_intel_display(old_crtc_state); - - if (!old_crtc_state->gmch_pfit.control) - return; - - assert_transcoder_disabled(display, old_crtc_state->cpu_transcoder); - - drm_dbg_kms(display->drm, "disabling pfit, current: 0x%08x\n", - intel_de_read(display, PFIT_CONTROL(display))); - intel_de_write(display, PFIT_CONTROL(display), 0); -} - static void i9xx_crtc_disable(struct intel_atomic_state *state, struct intel_crtc *crtc) { @@ -2217,7 +2130,7 @@ static void i9xx_crtc_disable(struct intel_atomic_state *state, * On gen2 planes are double buffered but the pipe isn't, so we must * wait for planes to fully turn off before disabling the pipe. */ - if (DISPLAY_VER(dev_priv) == 2) + if (DISPLAY_VER(display) == 2) intel_crtc_wait_for_next_vblank(crtc); intel_encoders_disable(state, crtc); @@ -2231,9 +2144,9 @@ static void i9xx_crtc_disable(struct intel_atomic_state *state, intel_encoders_post_disable(state, crtc); if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DSI)) { - if (IS_CHERRYVIEW(dev_priv)) + if (display->platform.cherryview) chv_disable_pll(dev_priv, pipe); - else if (IS_VALLEYVIEW(dev_priv)) + else if (display->platform.valleyview) vlv_disable_pll(dev_priv, pipe); else i9xx_disable_pll(old_crtc_state); @@ -2241,14 +2154,14 @@ static void i9xx_crtc_disable(struct intel_atomic_state *state, intel_encoders_post_pll_disable(state, crtc); - if (DISPLAY_VER(dev_priv) != 2) + if (DISPLAY_VER(display) != 2) intel_set_cpu_fifo_underrun_reporting(display, pipe, false); - if (!dev_priv->display.funcs.wm->initial_watermarks) + if (!display->funcs.wm->initial_watermarks) intel_update_watermarks(dev_priv); /* clock the pipe down to 640x480@60 to potentially save power */ - if (IS_I830(dev_priv)) + if (display->platform.i830) i830_enable_pipe(display, pipe); } @@ -2262,11 +2175,11 @@ void intel_encoder_destroy(struct drm_encoder *encoder) static bool intel_crtc_supports_double_wide(const struct intel_crtc *crtc) { - const struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); /* GDG double wide on either pipe, otherwise pipe A only */ - return HAS_DOUBLE_WIDE(dev_priv) && - (crtc->pipe == PIPE_A || IS_I915G(dev_priv)); + return HAS_DOUBLE_WIDE(display) && + (crtc->pipe == PIPE_A || display->platform.i915g); } static u32 ilk_pipe_pixel_rate(const struct intel_crtc_state *crtc_state) @@ -2313,9 +2226,9 @@ static void intel_mode_from_crtc_timings(struct drm_display_mode *mode, static void intel_crtc_compute_pixel_rate(struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct intel_display *display = to_intel_display(crtc_state); - if (HAS_GMCH(dev_priv)) + if (HAS_GMCH(display)) /* FIXME calculate proper pipe pixel rate for GMCH pfit */ crtc_state->pixel_rate = crtc_state->hw.pipe_mode.crtc_clock; @@ -2426,6 +2339,7 @@ static void intel_joiner_compute_pipe_src(struct intel_crtc_state *crtc_state) static int intel_crtc_compute_pipe_src(struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *i915 = to_i915(crtc->base.dev); @@ -2439,7 +2353,7 @@ static int intel_crtc_compute_pipe_src(struct intel_crtc_state *crtc_state) */ if (drm_rect_width(&crtc_state->pipe_src) & 1) { if (crtc_state->double_wide) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] Odd pipe source width not supported with double wide pipe\n", crtc->base.base.id, crtc->base.name); return -EINVAL; @@ -2447,7 +2361,7 @@ static int intel_crtc_compute_pipe_src(struct intel_crtc_state *crtc_state) if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS) && intel_is_dual_link_lvds(i915)) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] Odd pipe source width not supported with dual link LVDS\n", crtc->base.base.id, crtc->base.name); return -EINVAL; @@ -2459,11 +2373,11 @@ static int intel_crtc_compute_pipe_src(struct intel_crtc_state *crtc_state) static int intel_crtc_compute_pipe_mode(struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *i915 = to_i915(crtc->base.dev); struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; struct drm_display_mode *pipe_mode = &crtc_state->hw.pipe_mode; - int clock_limit = i915->display.cdclk.max_dotclk_freq; + int clock_limit = display->cdclk.max_dotclk_freq; /* * Start with the adjusted_mode crtc timings, which @@ -2478,8 +2392,8 @@ static int intel_crtc_compute_pipe_mode(struct intel_crtc_state *crtc_state) intel_joiner_adjust_timings(crtc_state, pipe_mode); intel_mode_from_crtc_timings(pipe_mode, pipe_mode); - if (DISPLAY_VER(i915) < 4) { - clock_limit = i915->display.cdclk.max_cdclk_freq * 9 / 10; + if (DISPLAY_VER(display) < 4) { + clock_limit = display->cdclk.max_cdclk_freq * 9 / 10; /* * Enable double wide mode when the dot clock @@ -2487,13 +2401,13 @@ static int intel_crtc_compute_pipe_mode(struct intel_crtc_state *crtc_state) */ if (intel_crtc_supports_double_wide(crtc) && pipe_mode->crtc_clock > clock_limit) { - clock_limit = i915->display.cdclk.max_dotclk_freq; + clock_limit = display->cdclk.max_dotclk_freq; crtc_state->double_wide = true; } } if (pipe_mode->crtc_clock > clock_limit) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] requested pixel clock (%d kHz) too high (max: %d kHz, double wide: %s)\n", crtc->base.base.id, crtc->base.name, pipe_mode->crtc_clock, clock_limit, @@ -2632,8 +2546,10 @@ intel_link_compute_m_n(u16 bits_per_pixel_x16, int nlanes, 0x80000); } -void intel_panel_sanitize_ssc(struct drm_i915_private *dev_priv) +void intel_panel_sanitize_ssc(struct intel_display *display) { + struct drm_i915_private *dev_priv = to_i915(display->drm); + /* * There may be no VBT; and if the BIOS enabled SSC we can * just keep using it to avoid unnecessary flicker. Whereas if the @@ -2641,16 +2557,16 @@ void intel_panel_sanitize_ssc(struct drm_i915_private *dev_priv) * indicates as much. */ if (HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv)) { - bool bios_lvds_use_ssc = intel_de_read(dev_priv, + bool bios_lvds_use_ssc = intel_de_read(display, PCH_DREF_CONTROL) & DREF_SSC1_ENABLE; - if (dev_priv->display.vbt.lvds_use_ssc != bios_lvds_use_ssc) { - drm_dbg_kms(&dev_priv->drm, + if (display->vbt.lvds_use_ssc != bios_lvds_use_ssc) { + drm_dbg_kms(display->drm, "SSC %s by BIOS, overriding VBT which says %s\n", str_enabled_disabled(bios_lvds_use_ssc), - str_enabled_disabled(dev_priv->display.vbt.lvds_use_ssc)); - dev_priv->display.vbt.lvds_use_ssc = bios_lvds_use_ssc; + str_enabled_disabled(display->vbt.lvds_use_ssc)); + display->vbt.lvds_use_ssc = bios_lvds_use_ssc; } } } @@ -2662,45 +2578,45 @@ void intel_zero_m_n(struct intel_link_m_n *m_n) m_n->tu = 1; } -void intel_set_m_n(struct drm_i915_private *i915, +void intel_set_m_n(struct intel_display *display, const struct intel_link_m_n *m_n, i915_reg_t data_m_reg, i915_reg_t data_n_reg, i915_reg_t link_m_reg, i915_reg_t link_n_reg) { - intel_de_write(i915, data_m_reg, TU_SIZE(m_n->tu) | m_n->data_m); - intel_de_write(i915, data_n_reg, m_n->data_n); - intel_de_write(i915, link_m_reg, m_n->link_m); + intel_de_write(display, data_m_reg, TU_SIZE(m_n->tu) | m_n->data_m); + intel_de_write(display, data_n_reg, m_n->data_n); + intel_de_write(display, link_m_reg, m_n->link_m); /* * On BDW+ writing LINK_N arms the double buffered update * of all the M/N registers, so it must be written last. */ - intel_de_write(i915, link_n_reg, m_n->link_n); + intel_de_write(display, link_n_reg, m_n->link_n); } -bool intel_cpu_transcoder_has_m2_n2(struct drm_i915_private *dev_priv, +bool intel_cpu_transcoder_has_m2_n2(struct intel_display *display, enum transcoder transcoder) { - if (IS_HASWELL(dev_priv)) + if (display->platform.haswell) return transcoder == TRANSCODER_EDP; - return IS_DISPLAY_VER(dev_priv, 5, 7) || IS_CHERRYVIEW(dev_priv); + return IS_DISPLAY_VER(display, 5, 7) || display->platform.cherryview; } void intel_cpu_transcoder_set_m1_n1(struct intel_crtc *crtc, enum transcoder transcoder, const struct intel_link_m_n *m_n) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); enum pipe pipe = crtc->pipe; - if (DISPLAY_VER(dev_priv) >= 5) - intel_set_m_n(dev_priv, m_n, - PIPE_DATA_M1(dev_priv, transcoder), - PIPE_DATA_N1(dev_priv, transcoder), - PIPE_LINK_M1(dev_priv, transcoder), - PIPE_LINK_N1(dev_priv, transcoder)); + if (DISPLAY_VER(display) >= 5) + intel_set_m_n(display, m_n, + PIPE_DATA_M1(display, transcoder), + PIPE_DATA_N1(display, transcoder), + PIPE_LINK_M1(display, transcoder), + PIPE_LINK_N1(display, transcoder)); else - intel_set_m_n(dev_priv, m_n, + intel_set_m_n(display, m_n, PIPE_DATA_M_G4X(pipe), PIPE_DATA_N_G4X(pipe), PIPE_LINK_M_G4X(pipe), PIPE_LINK_N_G4X(pipe)); } @@ -2709,29 +2625,29 @@ void intel_cpu_transcoder_set_m2_n2(struct intel_crtc *crtc, enum transcoder transcoder, const struct intel_link_m_n *m_n) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); - if (!intel_cpu_transcoder_has_m2_n2(dev_priv, transcoder)) + if (!intel_cpu_transcoder_has_m2_n2(display, transcoder)) return; - intel_set_m_n(dev_priv, m_n, - PIPE_DATA_M2(dev_priv, transcoder), - PIPE_DATA_N2(dev_priv, transcoder), - PIPE_LINK_M2(dev_priv, transcoder), - PIPE_LINK_N2(dev_priv, transcoder)); + intel_set_m_n(display, m_n, + PIPE_DATA_M2(display, transcoder), + PIPE_DATA_N2(display, transcoder), + PIPE_LINK_M2(display, transcoder), + PIPE_LINK_N2(display, transcoder)); } static void intel_set_transcoder_timings(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; u32 crtc_vdisplay, crtc_vtotal, crtc_vblank_start, crtc_vblank_end; int vsyncshift = 0; - drm_WARN_ON(&dev_priv->drm, transcoder_is_dsi(cpu_transcoder)); + drm_WARN_ON(display->drm, transcoder_is_dsi(cpu_transcoder)); /* We need to be careful not to changed the adjusted mode, for otherwise * the hw state checker will get angry at the mismatch. */ @@ -2758,9 +2674,9 @@ static void intel_set_transcoder_timings(const struct intel_crtc_state *crtc_sta * VBLANK_START no longer works on ADL+, instead we must use * TRANS_SET_CONTEXT_LATENCY to configure the pipe vblank start. */ - if (DISPLAY_VER(dev_priv) >= 13) { - intel_de_write(dev_priv, - TRANS_SET_CONTEXT_LATENCY(dev_priv, cpu_transcoder), + if (DISPLAY_VER(display) >= 13) { + intel_de_write(display, + TRANS_SET_CONTEXT_LATENCY(display, cpu_transcoder), crtc_vblank_start - crtc_vdisplay); /* @@ -2770,28 +2686,28 @@ static void intel_set_transcoder_timings(const struct intel_crtc_state *crtc_sta crtc_vblank_start = 1; } - if (DISPLAY_VER(dev_priv) >= 4) - intel_de_write(dev_priv, - TRANS_VSYNCSHIFT(dev_priv, cpu_transcoder), + if (DISPLAY_VER(display) >= 4) + intel_de_write(display, + TRANS_VSYNCSHIFT(display, cpu_transcoder), vsyncshift); - intel_de_write(dev_priv, TRANS_HTOTAL(dev_priv, cpu_transcoder), + intel_de_write(display, TRANS_HTOTAL(display, cpu_transcoder), HACTIVE(adjusted_mode->crtc_hdisplay - 1) | HTOTAL(adjusted_mode->crtc_htotal - 1)); - intel_de_write(dev_priv, TRANS_HBLANK(dev_priv, cpu_transcoder), + intel_de_write(display, TRANS_HBLANK(display, cpu_transcoder), HBLANK_START(adjusted_mode->crtc_hblank_start - 1) | HBLANK_END(adjusted_mode->crtc_hblank_end - 1)); - intel_de_write(dev_priv, TRANS_HSYNC(dev_priv, cpu_transcoder), + intel_de_write(display, TRANS_HSYNC(display, cpu_transcoder), HSYNC_START(adjusted_mode->crtc_hsync_start - 1) | HSYNC_END(adjusted_mode->crtc_hsync_end - 1)); - intel_de_write(dev_priv, TRANS_VTOTAL(dev_priv, cpu_transcoder), + intel_de_write(display, TRANS_VTOTAL(display, cpu_transcoder), VACTIVE(crtc_vdisplay - 1) | VTOTAL(crtc_vtotal - 1)); - intel_de_write(dev_priv, TRANS_VBLANK(dev_priv, cpu_transcoder), + intel_de_write(display, TRANS_VBLANK(display, cpu_transcoder), VBLANK_START(crtc_vblank_start - 1) | VBLANK_END(crtc_vblank_end - 1)); - intel_de_write(dev_priv, TRANS_VSYNC(dev_priv, cpu_transcoder), + intel_de_write(display, TRANS_VSYNC(display, cpu_transcoder), VSYNC_START(adjusted_mode->crtc_vsync_start - 1) | VSYNC_END(adjusted_mode->crtc_vsync_end - 1)); @@ -2799,22 +2715,21 @@ static void intel_set_transcoder_timings(const struct intel_crtc_state *crtc_sta * programmed with the VTOTAL_EDP value. Same for VTOTAL_C. This is * documented on the DDI_FUNC_CTL register description, EDP Input Select * bits. */ - if (IS_HASWELL(dev_priv) && cpu_transcoder == TRANSCODER_EDP && + if (display->platform.haswell && cpu_transcoder == TRANSCODER_EDP && (pipe == PIPE_B || pipe == PIPE_C)) - intel_de_write(dev_priv, TRANS_VTOTAL(dev_priv, pipe), + intel_de_write(display, TRANS_VTOTAL(display, pipe), VACTIVE(crtc_vdisplay - 1) | VTOTAL(crtc_vtotal - 1)); } static void intel_set_transcoder_timings_lrr(const struct intel_crtc_state *crtc_state) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc_state); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; u32 crtc_vdisplay, crtc_vtotal, crtc_vblank_start, crtc_vblank_end; - drm_WARN_ON(&dev_priv->drm, transcoder_is_dsi(cpu_transcoder)); + drm_WARN_ON(display->drm, transcoder_is_dsi(cpu_transcoder)); crtc_vdisplay = adjusted_mode->crtc_vdisplay; crtc_vtotal = adjusted_mode->crtc_vtotal; @@ -2827,9 +2742,9 @@ static void intel_set_transcoder_timings_lrr(const struct intel_crtc_state *crtc crtc_vblank_end -= 1; } - if (DISPLAY_VER(dev_priv) >= 13) { - intel_de_write(dev_priv, - TRANS_SET_CONTEXT_LATENCY(dev_priv, cpu_transcoder), + if (DISPLAY_VER(display) >= 13) { + intel_de_write(display, + TRANS_SET_CONTEXT_LATENCY(display, cpu_transcoder), crtc_vblank_start - crtc_vdisplay); /* @@ -2843,22 +2758,22 @@ static void intel_set_transcoder_timings_lrr(const struct intel_crtc_state *crtc * The hardware actually ignores TRANS_VBLANK.VBLANK_END in DP mode. * But let's write it anyway to keep the state checker happy. */ - intel_de_write(dev_priv, TRANS_VBLANK(dev_priv, cpu_transcoder), + intel_de_write(display, TRANS_VBLANK(display, cpu_transcoder), VBLANK_START(crtc_vblank_start - 1) | VBLANK_END(crtc_vblank_end - 1)); /* * The double buffer latch point for TRANS_VTOTAL * is the transcoder's undelayed vblank. */ - intel_de_write(dev_priv, TRANS_VTOTAL(dev_priv, cpu_transcoder), + intel_de_write(display, TRANS_VTOTAL(display, cpu_transcoder), VACTIVE(crtc_vdisplay - 1) | VTOTAL(crtc_vtotal - 1)); } static void intel_set_pipe_src_size(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); int width = drm_rect_width(&crtc_state->pipe_src); int height = drm_rect_height(&crtc_state->pipe_src); enum pipe pipe = crtc->pipe; @@ -2866,63 +2781,62 @@ static void intel_set_pipe_src_size(const struct intel_crtc_state *crtc_state) /* pipesrc controls the size that is scaled from, which should * always be the user's requested size. */ - intel_de_write(dev_priv, PIPESRC(dev_priv, pipe), + intel_de_write(display, PIPESRC(display, pipe), PIPESRC_WIDTH(width - 1) | PIPESRC_HEIGHT(height - 1)); } static bool intel_pipe_is_interlaced(const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + struct intel_display *display = to_intel_display(crtc_state); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; - if (DISPLAY_VER(dev_priv) == 2) + if (DISPLAY_VER(display) == 2) return false; - if (DISPLAY_VER(dev_priv) >= 9 || - IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) - return intel_de_read(dev_priv, - TRANSCONF(dev_priv, cpu_transcoder)) & TRANSCONF_INTERLACE_MASK_HSW; + if (DISPLAY_VER(display) >= 9 || + display->platform.broadwell || display->platform.haswell) + return intel_de_read(display, + TRANSCONF(display, cpu_transcoder)) & TRANSCONF_INTERLACE_MASK_HSW; else - return intel_de_read(dev_priv, - TRANSCONF(dev_priv, cpu_transcoder)) & TRANSCONF_INTERLACE_MASK; + return intel_de_read(display, + TRANSCONF(display, cpu_transcoder)) & TRANSCONF_INTERLACE_MASK; } static void intel_get_transcoder_timings(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config) { - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_display *display = to_intel_display(crtc); enum transcoder cpu_transcoder = pipe_config->cpu_transcoder; struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; u32 tmp; - tmp = intel_de_read(dev_priv, TRANS_HTOTAL(dev_priv, cpu_transcoder)); + tmp = intel_de_read(display, TRANS_HTOTAL(display, cpu_transcoder)); adjusted_mode->crtc_hdisplay = REG_FIELD_GET(HACTIVE_MASK, tmp) + 1; adjusted_mode->crtc_htotal = REG_FIELD_GET(HTOTAL_MASK, tmp) + 1; if (!transcoder_is_dsi(cpu_transcoder)) { - tmp = intel_de_read(dev_priv, - TRANS_HBLANK(dev_priv, cpu_transcoder)); + tmp = intel_de_read(display, + TRANS_HBLANK(display, cpu_transcoder)); adjusted_mode->crtc_hblank_start = REG_FIELD_GET(HBLANK_START_MASK, tmp) + 1; adjusted_mode->crtc_hblank_end = REG_FIELD_GET(HBLANK_END_MASK, tmp) + 1; } - tmp = intel_de_read(dev_priv, TRANS_HSYNC(dev_priv, cpu_transcoder)); + tmp = intel_de_read(display, TRANS_HSYNC(display, cpu_transcoder)); adjusted_mode->crtc_hsync_start = REG_FIELD_GET(HSYNC_START_MASK, tmp) + 1; adjusted_mode->crtc_hsync_end = REG_FIELD_GET(HSYNC_END_MASK, tmp) + 1; - tmp = intel_de_read(dev_priv, TRANS_VTOTAL(dev_priv, cpu_transcoder)); + tmp = intel_de_read(display, TRANS_VTOTAL(display, cpu_transcoder)); adjusted_mode->crtc_vdisplay = REG_FIELD_GET(VACTIVE_MASK, tmp) + 1; adjusted_mode->crtc_vtotal = REG_FIELD_GET(VTOTAL_MASK, tmp) + 1; /* FIXME TGL+ DSI transcoders have this! */ if (!transcoder_is_dsi(cpu_transcoder)) { - tmp = intel_de_read(dev_priv, - TRANS_VBLANK(dev_priv, cpu_transcoder)); + tmp = intel_de_read(display, + TRANS_VBLANK(display, cpu_transcoder)); adjusted_mode->crtc_vblank_start = REG_FIELD_GET(VBLANK_START_MASK, tmp) + 1; adjusted_mode->crtc_vblank_end = REG_FIELD_GET(VBLANK_END_MASK, tmp) + 1; } - tmp = intel_de_read(dev_priv, TRANS_VSYNC(dev_priv, cpu_transcoder)); + tmp = intel_de_read(display, TRANS_VSYNC(display, cpu_transcoder)); adjusted_mode->crtc_vsync_start = REG_FIELD_GET(VSYNC_START_MASK, tmp) + 1; adjusted_mode->crtc_vsync_end = REG_FIELD_GET(VSYNC_END_MASK, tmp) + 1; @@ -2932,11 +2846,11 @@ static void intel_get_transcoder_timings(struct intel_crtc *crtc, adjusted_mode->crtc_vblank_end += 1; } - if (DISPLAY_VER(dev_priv) >= 13 && !transcoder_is_dsi(cpu_transcoder)) + if (DISPLAY_VER(display) >= 13 && !transcoder_is_dsi(cpu_transcoder)) adjusted_mode->crtc_vblank_start = adjusted_mode->crtc_vdisplay + - intel_de_read(dev_priv, - TRANS_SET_CONTEXT_LATENCY(dev_priv, cpu_transcoder)); + intel_de_read(display, + TRANS_SET_CONTEXT_LATENCY(display, cpu_transcoder)); } static void intel_joiner_adjust_pipe_src(struct intel_crtc_state *crtc_state) @@ -2959,11 +2873,10 @@ static void intel_joiner_adjust_pipe_src(struct intel_crtc_state *crtc_state) static void intel_get_pipe_src_size(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config) { - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_display *display = to_intel_display(crtc); u32 tmp; - tmp = intel_de_read(dev_priv, PIPESRC(dev_priv, crtc->pipe)); + tmp = intel_de_read(display, PIPESRC(display, crtc->pipe)); drm_rect_init(&pipe_config->pipe_src, 0, 0, REG_FIELD_GET(PIPESRC_WIDTH_MASK, tmp) + 1, @@ -2974,8 +2887,7 @@ static void intel_get_pipe_src_size(struct intel_crtc *crtc, void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc_state); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; u32 val = 0; @@ -2984,15 +2896,15 @@ void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state) * - During modeset the pipe is still disabled and must remain so * - During fastset the pipe is already enabled and must remain so */ - if (IS_I830(dev_priv) || !intel_crtc_needs_modeset(crtc_state)) + if (display->platform.i830 || !intel_crtc_needs_modeset(crtc_state)) val |= TRANSCONF_ENABLE; if (crtc_state->double_wide) val |= TRANSCONF_DOUBLE_WIDE; /* only g4x and later have fancy bpc/dither controls */ - if (IS_G4X(dev_priv) || IS_VALLEYVIEW(dev_priv) || - IS_CHERRYVIEW(dev_priv)) { + if (display->platform.g4x || display->platform.valleyview || + display->platform.cherryview) { /* Bspec claims that we can't use dithering for 30bpp pipes. */ if (crtc_state->dither && crtc_state->pipe_bpp != 30) val |= TRANSCONF_DITHER_EN | @@ -3016,7 +2928,7 @@ void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state) } if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE) { - if (DISPLAY_VER(dev_priv) < 4 || + if (DISPLAY_VER(display) < 4 || intel_crtc_has_type(crtc_state, INTEL_OUTPUT_SDVO)) val |= TRANSCONF_INTERLACE_W_FIELD_INDICATION; else @@ -3025,8 +2937,8 @@ void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state) val |= TRANSCONF_INTERLACE_PROGRESSIVE; } - if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) && - crtc_state->limited_color_range) + if ((display->platform.valleyview || display->platform.cherryview) && + crtc_state->limited_color_range) val |= TRANSCONF_COLOR_RANGE_SELECT; val |= TRANSCONF_GAMMA_MODE(crtc_state->gamma_mode); @@ -3036,54 +2948,17 @@ void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state) val |= TRANSCONF_FRAME_START_DELAY(crtc_state->framestart_delay - 1); - intel_de_write(dev_priv, TRANSCONF(dev_priv, cpu_transcoder), val); - intel_de_posting_read(dev_priv, TRANSCONF(dev_priv, cpu_transcoder)); -} - -static bool i9xx_has_pfit(struct drm_i915_private *dev_priv) -{ - if (IS_I830(dev_priv)) - return false; - - return DISPLAY_VER(dev_priv) >= 4 || - IS_PINEVIEW(dev_priv) || IS_MOBILE(dev_priv); -} - -static void i9xx_get_pfit_config(struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - enum pipe pipe; - u32 tmp; - - if (!i9xx_has_pfit(dev_priv)) - return; - - tmp = intel_de_read(dev_priv, PFIT_CONTROL(dev_priv)); - if (!(tmp & PFIT_ENABLE)) - return; - - /* Check whether the pfit is attached to our pipe. */ - if (DISPLAY_VER(dev_priv) >= 4) - pipe = REG_FIELD_GET(PFIT_PIPE_MASK, tmp); - else - pipe = PIPE_B; - - if (pipe != crtc->pipe) - return; - - crtc_state->gmch_pfit.control = tmp; - crtc_state->gmch_pfit.pgm_ratios = - intel_de_read(dev_priv, PFIT_PGM_RATIOS(dev_priv)); + intel_de_write(display, TRANSCONF(display, cpu_transcoder), val); + intel_de_posting_read(display, TRANSCONF(display, cpu_transcoder)); } static enum intel_output_format bdw_get_pipe_misc_output_format(struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); u32 tmp; - tmp = intel_de_read(dev_priv, PIPE_MISC(crtc->pipe)); + tmp = intel_de_read(display, PIPE_MISC(crtc->pipe)); if (tmp & PIPE_MISC_YUV420_ENABLE) { /* @@ -3091,8 +2966,8 @@ bdw_get_pipe_misc_output_format(struct intel_crtc *crtc) * For xe3_lpd+ this is implied in YUV420 Enable bit. * Ensure the same for prior platforms in YUV420 Mode bit. */ - if (DISPLAY_VER(dev_priv) < 30) - drm_WARN_ON(&dev_priv->drm, + if (DISPLAY_VER(display) < 30) + drm_WARN_ON(display->drm, (tmp & PIPE_MISC_YUV420_MODE_FULL_BLEND) == 0); return INTEL_OUTPUT_FORMAT_YCBCR420; @@ -3107,31 +2982,28 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config) { struct intel_display *display = to_intel_display(crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum intel_display_power_domain power_domain; + enum transcoder cpu_transcoder = (enum transcoder)crtc->pipe; intel_wakeref_t wakeref; + bool ret = false; u32 tmp; - bool ret; power_domain = POWER_DOMAIN_PIPE(crtc->pipe); wakeref = intel_display_power_get_if_enabled(display, power_domain); if (!wakeref) return false; - pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB; - pipe_config->sink_format = pipe_config->output_format; - pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; - pipe_config->shared_dpll = NULL; - - ret = false; - - tmp = intel_de_read(dev_priv, - TRANSCONF(dev_priv, pipe_config->cpu_transcoder)); + tmp = intel_de_read(display, TRANSCONF(display, cpu_transcoder)); if (!(tmp & TRANSCONF_ENABLE)) goto out; - if (IS_G4X(dev_priv) || IS_VALLEYVIEW(dev_priv) || - IS_CHERRYVIEW(dev_priv)) { + pipe_config->cpu_transcoder = cpu_transcoder; + + pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB; + pipe_config->sink_format = pipe_config->output_format; + + if (display->platform.g4x || display->platform.valleyview || + display->platform.cherryview) { switch (tmp & TRANSCONF_BPC_MASK) { case TRANSCONF_BPC_6: pipe_config->pipe_bpp = 18; @@ -3148,7 +3020,7 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, } } - if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) && + if ((display->platform.valleyview || display->platform.cherryview) && (tmp & TRANSCONF_COLOR_RANGE_SELECT)) pipe_config->limited_color_range = true; @@ -3156,29 +3028,29 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, pipe_config->framestart_delay = REG_FIELD_GET(TRANSCONF_FRAME_START_DELAY_MASK, tmp) + 1; - if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) && + if ((display->platform.valleyview || display->platform.cherryview) && (tmp & TRANSCONF_WGC_ENABLE)) pipe_config->wgc_enable = true; intel_color_get_config(pipe_config); - if (HAS_DOUBLE_WIDE(dev_priv)) + if (HAS_DOUBLE_WIDE(display)) pipe_config->double_wide = tmp & TRANSCONF_DOUBLE_WIDE; intel_get_transcoder_timings(crtc, pipe_config); intel_get_pipe_src_size(crtc, pipe_config); - i9xx_get_pfit_config(pipe_config); + i9xx_pfit_get_config(pipe_config); i9xx_dpll_get_hw_state(crtc, &pipe_config->dpll_hw_state); - if (DISPLAY_VER(dev_priv) >= 4) { + if (DISPLAY_VER(display) >= 4) { tmp = pipe_config->dpll_hw_state.i9xx.dpll_md; pipe_config->pixel_multiplier = ((tmp & DPLL_MD_UDI_MULTIPLIER_MASK) >> DPLL_MD_UDI_MULTIPLIER_SHIFT) + 1; - } else if (IS_I945G(dev_priv) || IS_I945GM(dev_priv) || - IS_G33(dev_priv) || IS_PINEVIEW(dev_priv)) { + } else if (display->platform.i945g || display->platform.i945gm || + display->platform.g33 || display->platform.pineview) { tmp = pipe_config->dpll_hw_state.i9xx.dpll; pipe_config->pixel_multiplier = ((tmp & SDVO_MULTIPLIER_MASK) @@ -3190,9 +3062,9 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, pipe_config->pixel_multiplier = 1; } - if (IS_CHERRYVIEW(dev_priv)) + if (display->platform.cherryview) chv_crtc_clock_get(pipe_config); - else if (IS_VALLEYVIEW(dev_priv)) + else if (display->platform.valleyview) vlv_crtc_clock_get(pipe_config); else i9xx_crtc_clock_get(pipe_config); @@ -3215,8 +3087,7 @@ out: void ilk_set_pipeconf(const struct intel_crtc_state *crtc_state) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc_state); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; u32 val = 0; @@ -3258,7 +3129,7 @@ void ilk_set_pipeconf(const struct intel_crtc_state *crtc_state) * This would end up with an odd purple hue over * the entire display. Make sure we don't do it. */ - drm_WARN_ON(&dev_priv->drm, crtc_state->limited_color_range && + drm_WARN_ON(display->drm, crtc_state->limited_color_range && crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB); if (crtc_state->limited_color_range && @@ -3273,14 +3144,13 @@ void ilk_set_pipeconf(const struct intel_crtc_state *crtc_state) val |= TRANSCONF_FRAME_START_DELAY(crtc_state->framestart_delay - 1); val |= TRANSCONF_MSA_TIMING_DELAY(crtc_state->msa_timing_delay); - intel_de_write(dev_priv, TRANSCONF(dev_priv, cpu_transcoder), val); - intel_de_posting_read(dev_priv, TRANSCONF(dev_priv, cpu_transcoder)); + intel_de_write(display, TRANSCONF(display, cpu_transcoder), val); + intel_de_posting_read(display, TRANSCONF(display, cpu_transcoder)); } static void hsw_set_transconf(const struct intel_crtc_state *crtc_state) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc_state); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; u32 val = 0; @@ -3291,7 +3161,7 @@ static void hsw_set_transconf(const struct intel_crtc_state *crtc_state) if (!intel_crtc_needs_modeset(crtc_state)) val |= TRANSCONF_ENABLE; - if (IS_HASWELL(dev_priv) && crtc_state->dither) + if (display->platform.haswell && crtc_state->dither) val |= TRANSCONF_DITHER_EN | TRANSCONF_DITHER_TYPE_SP; if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE) @@ -3299,20 +3169,19 @@ static void hsw_set_transconf(const struct intel_crtc_state *crtc_state) else val |= TRANSCONF_INTERLACE_PF_PD_ILK; - if (IS_HASWELL(dev_priv) && + if (display->platform.haswell && crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB) val |= TRANSCONF_OUTPUT_COLORSPACE_YUV_HSW; - intel_de_write(dev_priv, TRANSCONF(dev_priv, cpu_transcoder), val); - intel_de_posting_read(dev_priv, TRANSCONF(dev_priv, cpu_transcoder)); + intel_de_write(display, TRANSCONF(display, cpu_transcoder), val); + intel_de_posting_read(display, TRANSCONF(display, cpu_transcoder)); } static void bdw_set_pipe_misc(struct intel_dsb *dsb, const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct intel_display *display = to_intel_display(crtc->base.dev); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); u32 val = 0; switch (crtc_state->pipe_bpp) { @@ -3327,7 +3196,7 @@ static void bdw_set_pipe_misc(struct intel_dsb *dsb, break; case 36: /* Port output 12BPC defined for ADLP+ */ - if (DISPLAY_VER(dev_priv) >= 13) + if (DISPLAY_VER(display) >= 13) val |= PIPE_MISC_BPC_12_ADLP; break; default: @@ -3346,14 +3215,14 @@ static void bdw_set_pipe_misc(struct intel_dsb *dsb, val |= DISPLAY_VER(display) >= 30 ? PIPE_MISC_YUV420_ENABLE : PIPE_MISC_YUV420_ENABLE | PIPE_MISC_YUV420_MODE_FULL_BLEND; - if (DISPLAY_VER(dev_priv) >= 11 && is_hdr_mode(crtc_state)) + if (DISPLAY_VER(display) >= 11 && is_hdr_mode(crtc_state)) val |= PIPE_MISC_HDR_MODE_PRECISION; - if (DISPLAY_VER(dev_priv) >= 12) + if (DISPLAY_VER(display) >= 12) val |= PIPE_MISC_PIXEL_ROUNDING_TRUNC; /* allow PSR with sprite enabled */ - if (IS_BROADWELL(dev_priv)) + if (display->platform.broadwell) val |= PIPE_MISC_PSR_MASK_SPRITE_ENABLE; intel_de_write_dsb(display, dsb, PIPE_MISC(crtc->pipe), val); @@ -3361,10 +3230,10 @@ static void bdw_set_pipe_misc(struct intel_dsb *dsb, int bdw_get_pipe_misc_bpp(struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); u32 tmp; - tmp = intel_de_read(dev_priv, PIPE_MISC(crtc->pipe)); + tmp = intel_de_read(display, PIPE_MISC(crtc->pipe)); switch (tmp & PIPE_MISC_BPC_MASK) { case PIPE_MISC_BPC_6: @@ -3384,7 +3253,7 @@ int bdw_get_pipe_misc_bpp(struct intel_crtc *crtc) * MIPI DSI HW readout. */ case PIPE_MISC_BPC_12_ADLP: - if (DISPLAY_VER(dev_priv) >= 13) + if (DISPLAY_VER(display) >= 13) return 36; fallthrough; default: @@ -3404,33 +3273,33 @@ int ilk_get_lanes_required(int target_clock, int link_bw, int bpp) return DIV_ROUND_UP(bps, link_bw * 8); } -void intel_get_m_n(struct drm_i915_private *i915, +void intel_get_m_n(struct intel_display *display, struct intel_link_m_n *m_n, i915_reg_t data_m_reg, i915_reg_t data_n_reg, i915_reg_t link_m_reg, i915_reg_t link_n_reg) { - m_n->link_m = intel_de_read(i915, link_m_reg) & DATA_LINK_M_N_MASK; - m_n->link_n = intel_de_read(i915, link_n_reg) & DATA_LINK_M_N_MASK; - m_n->data_m = intel_de_read(i915, data_m_reg) & DATA_LINK_M_N_MASK; - m_n->data_n = intel_de_read(i915, data_n_reg) & DATA_LINK_M_N_MASK; - m_n->tu = REG_FIELD_GET(TU_SIZE_MASK, intel_de_read(i915, data_m_reg)) + 1; + m_n->link_m = intel_de_read(display, link_m_reg) & DATA_LINK_M_N_MASK; + m_n->link_n = intel_de_read(display, link_n_reg) & DATA_LINK_M_N_MASK; + m_n->data_m = intel_de_read(display, data_m_reg) & DATA_LINK_M_N_MASK; + m_n->data_n = intel_de_read(display, data_n_reg) & DATA_LINK_M_N_MASK; + m_n->tu = REG_FIELD_GET(TU_SIZE_MASK, intel_de_read(display, data_m_reg)) + 1; } void intel_cpu_transcoder_get_m1_n1(struct intel_crtc *crtc, enum transcoder transcoder, struct intel_link_m_n *m_n) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); enum pipe pipe = crtc->pipe; - if (DISPLAY_VER(dev_priv) >= 5) - intel_get_m_n(dev_priv, m_n, - PIPE_DATA_M1(dev_priv, transcoder), - PIPE_DATA_N1(dev_priv, transcoder), - PIPE_LINK_M1(dev_priv, transcoder), - PIPE_LINK_N1(dev_priv, transcoder)); + if (DISPLAY_VER(display) >= 5) + intel_get_m_n(display, m_n, + PIPE_DATA_M1(display, transcoder), + PIPE_DATA_N1(display, transcoder), + PIPE_LINK_M1(display, transcoder), + PIPE_LINK_N1(display, transcoder)); else - intel_get_m_n(dev_priv, m_n, + intel_get_m_n(display, m_n, PIPE_DATA_M_G4X(pipe), PIPE_DATA_N_G4X(pipe), PIPE_LINK_M_G4X(pipe), PIPE_LINK_N_G4X(pipe)); } @@ -3439,78 +3308,39 @@ void intel_cpu_transcoder_get_m2_n2(struct intel_crtc *crtc, enum transcoder transcoder, struct intel_link_m_n *m_n) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - - if (!intel_cpu_transcoder_has_m2_n2(dev_priv, transcoder)) - return; - - intel_get_m_n(dev_priv, m_n, - PIPE_DATA_M2(dev_priv, transcoder), - PIPE_DATA_N2(dev_priv, transcoder), - PIPE_LINK_M2(dev_priv, transcoder), - PIPE_LINK_N2(dev_priv, transcoder)); -} - -static void ilk_get_pfit_config(struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - u32 ctl, pos, size; - enum pipe pipe; + struct intel_display *display = to_intel_display(crtc); - ctl = intel_de_read(dev_priv, PF_CTL(crtc->pipe)); - if ((ctl & PF_ENABLE) == 0) + if (!intel_cpu_transcoder_has_m2_n2(display, transcoder)) return; - if (IS_IVYBRIDGE(dev_priv) || IS_HASWELL(dev_priv)) - pipe = REG_FIELD_GET(PF_PIPE_SEL_MASK_IVB, ctl); - else - pipe = crtc->pipe; - - crtc_state->pch_pfit.enabled = true; - - pos = intel_de_read(dev_priv, PF_WIN_POS(crtc->pipe)); - size = intel_de_read(dev_priv, PF_WIN_SZ(crtc->pipe)); - - drm_rect_init(&crtc_state->pch_pfit.dst, - REG_FIELD_GET(PF_WIN_XPOS_MASK, pos), - REG_FIELD_GET(PF_WIN_YPOS_MASK, pos), - REG_FIELD_GET(PF_WIN_XSIZE_MASK, size), - REG_FIELD_GET(PF_WIN_YSIZE_MASK, size)); - - /* - * We currently do not free assignments of panel fitters on - * ivb/hsw (since we don't use the higher upscaling modes which - * differentiates them) so just WARN about this case for now. - */ - drm_WARN_ON(&dev_priv->drm, pipe != crtc->pipe); + intel_get_m_n(display, m_n, + PIPE_DATA_M2(display, transcoder), + PIPE_DATA_N2(display, transcoder), + PIPE_LINK_M2(display, transcoder), + PIPE_LINK_N2(display, transcoder)); } static bool ilk_get_pipe_config(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config) { struct intel_display *display = to_intel_display(crtc); - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); enum intel_display_power_domain power_domain; + enum transcoder cpu_transcoder = (enum transcoder)crtc->pipe; intel_wakeref_t wakeref; + bool ret = false; u32 tmp; - bool ret; power_domain = POWER_DOMAIN_PIPE(crtc->pipe); wakeref = intel_display_power_get_if_enabled(display, power_domain); if (!wakeref) return false; - pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; - pipe_config->shared_dpll = NULL; - - ret = false; - tmp = intel_de_read(dev_priv, - TRANSCONF(dev_priv, pipe_config->cpu_transcoder)); + tmp = intel_de_read(display, TRANSCONF(display, cpu_transcoder)); if (!(tmp & TRANSCONF_ENABLE)) goto out; + pipe_config->cpu_transcoder = cpu_transcoder; + switch (tmp & TRANSCONF_BPC_MASK) { case TRANSCONF_BPC_6: pipe_config->pipe_bpp = 18; @@ -3558,7 +3388,7 @@ static bool ilk_get_pipe_config(struct intel_crtc *crtc, intel_get_transcoder_timings(crtc, pipe_config); intel_get_pipe_src_size(crtc, pipe_config); - ilk_get_pfit_config(pipe_config); + ilk_pfit_get_config(pipe_config); ret = true; @@ -3568,24 +3398,23 @@ out: return ret; } -static u8 joiner_pipes(struct drm_i915_private *i915) +static u8 joiner_pipes(struct intel_display *display) { u8 pipes; - if (DISPLAY_VER(i915) >= 12) + if (DISPLAY_VER(display) >= 12) pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D); - else if (DISPLAY_VER(i915) >= 11) + else if (DISPLAY_VER(display) >= 11) pipes = BIT(PIPE_B) | BIT(PIPE_C); else pipes = 0; - return pipes & DISPLAY_RUNTIME_INFO(i915)->pipe_mask; + return pipes & DISPLAY_RUNTIME_INFO(display)->pipe_mask; } -static bool transcoder_ddi_func_is_enabled(struct drm_i915_private *dev_priv, +static bool transcoder_ddi_func_is_enabled(struct intel_display *display, enum transcoder cpu_transcoder) { - struct intel_display *display = &dev_priv->display; enum intel_display_power_domain power_domain; intel_wakeref_t wakeref; u32 tmp = 0; @@ -3593,8 +3422,8 @@ static bool transcoder_ddi_func_is_enabled(struct drm_i915_private *dev_priv, power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder); with_intel_display_power_if_enabled(display, power_domain, wakeref) - tmp = intel_de_read(dev_priv, - TRANS_DDI_FUNC_CTL(dev_priv, cpu_transcoder)); + tmp = intel_de_read(display, + TRANS_DDI_FUNC_CTL(display, cpu_transcoder)); return tmp & TRANS_DDI_FUNC_ENABLE; } @@ -3602,7 +3431,6 @@ static bool transcoder_ddi_func_is_enabled(struct drm_i915_private *dev_priv, static void enabled_uncompressed_joiner_pipes(struct intel_display *display, u8 *primary_pipes, u8 *secondary_pipes) { - struct drm_i915_private *i915 = to_i915(display->drm); struct intel_crtc *crtc; *primary_pipes = 0; @@ -3611,8 +3439,8 @@ static void enabled_uncompressed_joiner_pipes(struct intel_display *display, if (!HAS_UNCOMPRESSED_JOINER(display)) return; - for_each_intel_crtc_in_pipe_mask(&i915->drm, crtc, - joiner_pipes(i915)) { + for_each_intel_crtc_in_pipe_mask(display->drm, crtc, + joiner_pipes(display)) { enum intel_display_power_domain power_domain; enum pipe pipe = crtc->pipe; intel_wakeref_t wakeref; @@ -3632,7 +3460,6 @@ static void enabled_uncompressed_joiner_pipes(struct intel_display *display, static void enabled_bigjoiner_pipes(struct intel_display *display, u8 *primary_pipes, u8 *secondary_pipes) { - struct drm_i915_private *i915 = to_i915(display->drm); struct intel_crtc *crtc; *primary_pipes = 0; @@ -3641,8 +3468,8 @@ static void enabled_bigjoiner_pipes(struct intel_display *display, if (!HAS_BIGJOINER(display)) return; - for_each_intel_crtc_in_pipe_mask(&i915->drm, crtc, - joiner_pipes(i915)) { + for_each_intel_crtc_in_pipe_mask(display->drm, crtc, + joiner_pipes(display)) { enum intel_display_power_domain power_domain; enum pipe pipe = crtc->pipe; intel_wakeref_t wakeref; @@ -3700,10 +3527,9 @@ static u8 fixup_ultrajoiner_secondary_pipes(u8 ultrajoiner_primary_pipes, return ultrajoiner_secondary_pipes | ultrajoiner_primary_pipes << 3; } -static void enabled_ultrajoiner_pipes(struct drm_i915_private *i915, +static void enabled_ultrajoiner_pipes(struct intel_display *display, u8 *primary_pipes, u8 *secondary_pipes) { - struct intel_display *display = &i915->display; struct intel_crtc *crtc; *primary_pipes = 0; @@ -3712,15 +3538,15 @@ static void enabled_ultrajoiner_pipes(struct drm_i915_private *i915, if (!HAS_ULTRAJOINER(display)) return; - for_each_intel_crtc_in_pipe_mask(&i915->drm, crtc, - joiner_pipes(i915)) { + for_each_intel_crtc_in_pipe_mask(display->drm, crtc, + joiner_pipes(display)) { enum intel_display_power_domain power_domain; enum pipe pipe = crtc->pipe; intel_wakeref_t wakeref; power_domain = intel_dsc_power_domain(crtc, (enum transcoder)pipe); with_intel_display_power_if_enabled(display, power_domain, wakeref) { - u32 tmp = intel_de_read(i915, ICL_PIPE_DSS_CTL1(pipe)); + u32 tmp = intel_de_read(display, ICL_PIPE_DSS_CTL1(pipe)); if (!(tmp & ULTRA_JOINER_ENABLE)) continue; @@ -3733,11 +3559,10 @@ static void enabled_ultrajoiner_pipes(struct drm_i915_private *i915, } } -static void enabled_joiner_pipes(struct drm_i915_private *dev_priv, +static void enabled_joiner_pipes(struct intel_display *display, enum pipe pipe, u8 *primary_pipe, u8 *secondary_pipes) { - struct intel_display *display = to_intel_display(&dev_priv->drm); u8 primary_ultrajoiner_pipes; u8 primary_uncompressed_joiner_pipes, primary_bigjoiner_pipes; u8 secondary_ultrajoiner_pipes; @@ -3745,21 +3570,21 @@ static void enabled_joiner_pipes(struct drm_i915_private *dev_priv, u8 ultrajoiner_pipes; u8 uncompressed_joiner_pipes, bigjoiner_pipes; - enabled_ultrajoiner_pipes(dev_priv, &primary_ultrajoiner_pipes, + enabled_ultrajoiner_pipes(display, &primary_ultrajoiner_pipes, &secondary_ultrajoiner_pipes); /* * For some strange reason the last pipe in the set of four * shouldn't have ultrajoiner enable bit set in hardware. * Set the bit anyway to make life easier. */ - drm_WARN_ON(&dev_priv->drm, + drm_WARN_ON(display->drm, expected_secondary_pipes(primary_ultrajoiner_pipes, 3) != secondary_ultrajoiner_pipes); secondary_ultrajoiner_pipes = fixup_ultrajoiner_secondary_pipes(primary_ultrajoiner_pipes, secondary_ultrajoiner_pipes); - drm_WARN_ON(&dev_priv->drm, (primary_ultrajoiner_pipes & secondary_ultrajoiner_pipes) != 0); + drm_WARN_ON(display->drm, (primary_ultrajoiner_pipes & secondary_ultrajoiner_pipes) != 0); enabled_uncompressed_joiner_pipes(display, &primary_uncompressed_joiner_pipes, &secondary_uncompressed_joiner_pipes); @@ -3853,11 +3678,11 @@ static void enabled_joiner_pipes(struct drm_i915_private *dev_priv, } } -static u8 hsw_panel_transcoders(struct drm_i915_private *i915) +static u8 hsw_panel_transcoders(struct intel_display *display) { u8 panel_transcoder_mask = BIT(TRANSCODER_EDP); - if (DISPLAY_VER(i915) >= 11) + if (DISPLAY_VER(display) >= 11) panel_transcoder_mask |= BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1); return panel_transcoder_mask; @@ -3866,9 +3691,7 @@ static u8 hsw_panel_transcoders(struct drm_i915_private *i915) static u8 hsw_enabled_transcoders(struct intel_crtc *crtc) { struct intel_display *display = to_intel_display(crtc); - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); - u8 panel_transcoder_mask = hsw_panel_transcoders(dev_priv); + u8 panel_transcoder_mask = hsw_panel_transcoders(display); enum transcoder cpu_transcoder; u8 primary_pipe, secondary_pipes; u8 enabled_transcoders = 0; @@ -3877,7 +3700,7 @@ static u8 hsw_enabled_transcoders(struct intel_crtc *crtc) * XXX: Do intel_display_power_get_if_enabled before reading this (for * consistency and less surprising code; it's in always on power). */ - for_each_cpu_transcoder_masked(dev_priv, cpu_transcoder, + for_each_cpu_transcoder_masked(display, cpu_transcoder, panel_transcoder_mask) { enum intel_display_power_domain power_domain; intel_wakeref_t wakeref; @@ -3886,15 +3709,15 @@ static u8 hsw_enabled_transcoders(struct intel_crtc *crtc) power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder); with_intel_display_power_if_enabled(display, power_domain, wakeref) - tmp = intel_de_read(dev_priv, - TRANS_DDI_FUNC_CTL(dev_priv, cpu_transcoder)); + tmp = intel_de_read(display, + TRANS_DDI_FUNC_CTL(display, cpu_transcoder)); if (!(tmp & TRANS_DDI_FUNC_ENABLE)) continue; switch (tmp & TRANS_DDI_EDP_INPUT_MASK) { default: - drm_WARN(dev, 1, + drm_WARN(display->drm, 1, "unknown pipe linked to transcoder %s\n", transcoder_name(cpu_transcoder)); fallthrough; @@ -3919,14 +3742,14 @@ static u8 hsw_enabled_transcoders(struct intel_crtc *crtc) /* single pipe or joiner primary */ cpu_transcoder = (enum transcoder) crtc->pipe; - if (transcoder_ddi_func_is_enabled(dev_priv, cpu_transcoder)) + if (transcoder_ddi_func_is_enabled(display, cpu_transcoder)) enabled_transcoders |= BIT(cpu_transcoder); /* joiner secondary -> consider the primary pipe's transcoder as well */ - enabled_joiner_pipes(dev_priv, crtc->pipe, &primary_pipe, &secondary_pipes); + enabled_joiner_pipes(display, crtc->pipe, &primary_pipe, &secondary_pipes); if (secondary_pipes & BIT(crtc->pipe)) { cpu_transcoder = (enum transcoder)ffs(primary_pipe) - 1; - if (transcoder_ddi_func_is_enabled(dev_priv, cpu_transcoder)) + if (transcoder_ddi_func_is_enabled(display, cpu_transcoder)) enabled_transcoders |= BIT(cpu_transcoder); } @@ -3951,17 +3774,17 @@ static bool has_pipe_transcoders(u8 enabled_transcoders) BIT(TRANSCODER_DSI_1)); } -static void assert_enabled_transcoders(struct drm_i915_private *i915, +static void assert_enabled_transcoders(struct intel_display *display, u8 enabled_transcoders) { /* Only one type of transcoder please */ - drm_WARN_ON(&i915->drm, + drm_WARN_ON(display->drm, has_edp_transcoders(enabled_transcoders) + has_dsi_transcoders(enabled_transcoders) + has_pipe_transcoders(enabled_transcoders) > 1); /* Only DSI transcoders can be ganged */ - drm_WARN_ON(&i915->drm, + drm_WARN_ON(display->drm, !has_dsi_transcoders(enabled_transcoders) && !is_power_of_2(enabled_transcoders)); } @@ -3971,8 +3794,6 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc, struct intel_display_power_domain_set *power_domain_set) { struct intel_display *display = to_intel_display(crtc); - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); unsigned long enabled_transcoders; u32 tmp; @@ -3980,7 +3801,7 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc, if (!enabled_transcoders) return false; - assert_enabled_transcoders(dev_priv, enabled_transcoders); + assert_enabled_transcoders(display, enabled_transcoders); /* * With the exception of DSI we should only ever have @@ -3993,16 +3814,16 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc, POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder))) return false; - if (hsw_panel_transcoders(dev_priv) & BIT(pipe_config->cpu_transcoder)) { - tmp = intel_de_read(dev_priv, - TRANS_DDI_FUNC_CTL(dev_priv, pipe_config->cpu_transcoder)); + if (hsw_panel_transcoders(display) & BIT(pipe_config->cpu_transcoder)) { + tmp = intel_de_read(display, + TRANS_DDI_FUNC_CTL(display, pipe_config->cpu_transcoder)); if ((tmp & TRANS_DDI_EDP_INPUT_MASK) == TRANS_DDI_EDP_INPUT_A_ONOFF) pipe_config->pch_pfit.force_thru = true; } - tmp = intel_de_read(dev_priv, - TRANSCONF(dev_priv, pipe_config->cpu_transcoder)); + tmp = intel_de_read(display, + TRANSCONF(display, pipe_config->cpu_transcoder)); return tmp & TRANSCONF_ENABLE; } @@ -4055,12 +3876,12 @@ static bool bxt_get_dsi_transcoder_state(struct intel_crtc *crtc, static void intel_joiner_get_config(struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *i915 = to_i915(crtc->base.dev); u8 primary_pipe, secondary_pipes; enum pipe pipe = crtc->pipe; - enabled_joiner_pipes(i915, pipe, &primary_pipe, &secondary_pipes); + enabled_joiner_pipes(display, pipe, &primary_pipe, &secondary_pipes); if (((primary_pipe | secondary_pipes) & BIT(pipe)) == 0) return; @@ -4072,7 +3893,6 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config) { struct intel_display *display = to_intel_display(crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); bool active; u32 tmp; @@ -4080,13 +3900,11 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, POWER_DOMAIN_PIPE(crtc->pipe))) return false; - pipe_config->shared_dpll = NULL; - active = hsw_get_transcoder_state(crtc, pipe_config, &crtc->hw_readout_power_domains); - if ((IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) && + if ((display->platform.geminilake || display->platform.broxton) && bxt_get_dsi_transcoder_state(crtc, pipe_config, &crtc->hw_readout_power_domains)) { - drm_WARN_ON(&dev_priv->drm, active); + drm_WARN_ON(display->drm, active); active = true; } @@ -4097,17 +3915,17 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, intel_dsc_get_config(pipe_config); if (!transcoder_is_dsi(pipe_config->cpu_transcoder) || - DISPLAY_VER(dev_priv) >= 11) + DISPLAY_VER(display) >= 11) intel_get_transcoder_timings(crtc, pipe_config); - if (HAS_VRR(dev_priv) && !transcoder_is_dsi(pipe_config->cpu_transcoder)) + if (HAS_VRR(display) && !transcoder_is_dsi(pipe_config->cpu_transcoder)) intel_vrr_get_config(pipe_config); intel_get_pipe_src_size(crtc, pipe_config); - if (IS_HASWELL(dev_priv)) { - u32 tmp = intel_de_read(dev_priv, - TRANSCONF(dev_priv, pipe_config->cpu_transcoder)); + if (display->platform.haswell) { + u32 tmp = intel_de_read(display, + TRANSCONF(display, pipe_config->cpu_transcoder)); if (tmp & TRANSCONF_OUTPUT_COLORSPACE_YUV_HSW) pipe_config->output_format = INTEL_OUTPUT_FORMAT_YCBCR444; @@ -4122,18 +3940,18 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, intel_color_get_config(pipe_config); - tmp = intel_de_read(dev_priv, WM_LINETIME(crtc->pipe)); + tmp = intel_de_read(display, WM_LINETIME(crtc->pipe)); pipe_config->linetime = REG_FIELD_GET(HSW_LINETIME_MASK, tmp); - if (IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) + if (display->platform.broadwell || display->platform.haswell) pipe_config->ips_linetime = REG_FIELD_GET(HSW_IPS_LINETIME_MASK, tmp); if (intel_display_power_get_in_set_if_enabled(display, &crtc->hw_readout_power_domains, POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe))) { - if (DISPLAY_VER(dev_priv) >= 9) + if (DISPLAY_VER(display) >= 9) skl_scaler_get_config(pipe_config); else - ilk_get_pfit_config(pipe_config); + ilk_pfit_get_config(pipe_config); } hsw_ips_get_config(pipe_config); @@ -4141,8 +3959,8 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, if (pipe_config->cpu_transcoder != TRANSCODER_EDP && !transcoder_is_dsi(pipe_config->cpu_transcoder)) { pipe_config->pixel_multiplier = - intel_de_read(dev_priv, - TRANS_MULT(dev_priv, pipe_config->cpu_transcoder)) + 1; + intel_de_read(display, + TRANS_MULT(display, pipe_config->cpu_transcoder)) + 1; } else { pipe_config->pixel_multiplier = 1; } @@ -4164,10 +3982,10 @@ out: bool intel_crtc_get_pipe_config(struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *i915 = to_i915(crtc->base.dev); - if (!i915->display.funcs.display->get_pipe_config(crtc, crtc_state)) + if (!display->funcs.display->get_pipe_config(crtc, crtc_state)) return false; crtc_state->hw.active = true; @@ -4326,6 +4144,7 @@ static u16 hsw_ips_linetime_wm(const struct intel_crtc_state *crtc_state, static u16 skl_linetime_wm(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); const struct drm_display_mode *pipe_mode = @@ -4339,7 +4158,7 @@ static u16 skl_linetime_wm(const struct intel_crtc_state *crtc_state) crtc_state->pixel_rate); /* Display WA #1135: BXT:ALL GLK:ALL */ - if ((IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) && + if ((display->platform.geminilake || display->platform.broxton) && skl_watermark_ipc_enabled(dev_priv)) linetime_wm /= 2; @@ -4349,12 +4168,12 @@ static u16 skl_linetime_wm(const struct intel_crtc_state *crtc_state) static int hsw_compute_linetime_wm(struct intel_atomic_state *state, struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); const struct intel_cdclk_state *cdclk_state; - if (DISPLAY_VER(dev_priv) >= 9) + if (DISPLAY_VER(display) >= 9) crtc_state->linetime = skl_linetime_wm(crtc_state); else crtc_state->linetime = hsw_linetime_wm(crtc_state); @@ -4376,12 +4195,11 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct intel_display *display = to_intel_display(crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); int ret; - if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv) && + if (DISPLAY_VER(display) < 5 && !display->platform.g4x && intel_crtc_needs_modeset(crtc_state) && !crtc_state->hw.active) crtc_state->update_wm_post = true; @@ -4398,13 +4216,13 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state, ret = intel_wm_compute(state, crtc); if (ret) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] watermarks are invalid\n", crtc->base.base.id, crtc->base.name); return ret; } - if (DISPLAY_VER(dev_priv) >= 9) { + if (DISPLAY_VER(display) >= 9) { if (intel_crtc_needs_modeset(crtc_state) || intel_crtc_needs_fastset(crtc_state)) { ret = skl_update_scaler_crtc(crtc_state); @@ -4423,8 +4241,8 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state, return ret; } - if (DISPLAY_VER(dev_priv) >= 9 || - IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) { + if (DISPLAY_VER(display) >= 9 || + display->platform.broadwell || display->platform.haswell) { ret = hsw_compute_linetime_wm(state, crtc); if (ret) return ret; @@ -4442,8 +4260,8 @@ static int compute_sink_pipe_bpp(const struct drm_connector_state *conn_state, struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct drm_connector *connector = conn_state->connector; - struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); const struct drm_display_info *info = &connector->display_info; int bpp; @@ -4466,7 +4284,7 @@ compute_sink_pipe_bpp(const struct drm_connector_state *conn_state, } if (bpp < crtc_state->pipe_bpp) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CONNECTOR:%d:%s] Limiting display bpp to %d " "(EDID bpp %d, max requested bpp %d, max platform bpp %d)\n", connector->base.id, connector->name, @@ -4484,17 +4302,17 @@ static int compute_baseline_pipe_bpp(struct intel_atomic_state *state, struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); struct drm_connector *connector; struct drm_connector_state *connector_state; int bpp, i; - if ((IS_G4X(dev_priv) || IS_VALLEYVIEW(dev_priv) || - IS_CHERRYVIEW(dev_priv))) + if (display->platform.g4x || display->platform.valleyview || + display->platform.cherryview) bpp = 10*3; - else if (DISPLAY_VER(dev_priv) >= 5) + else if (DISPLAY_VER(display) >= 5) bpp = 12*3; else bpp = 8*3; @@ -4518,7 +4336,7 @@ compute_baseline_pipe_bpp(struct intel_atomic_state *state, static bool check_digital_port_conflicts(struct intel_atomic_state *state) { - struct drm_device *dev = state->base.dev; + struct intel_display *display = to_intel_display(state); struct drm_connector *connector; struct drm_connector_list_iter conn_iter; unsigned int used_ports = 0; @@ -4529,14 +4347,14 @@ static bool check_digital_port_conflicts(struct intel_atomic_state *state) * We're going to peek into connector->state, * hence connection_mutex must be held. */ - drm_modeset_lock_assert_held(&dev->mode_config.connection_mutex); + drm_modeset_lock_assert_held(&display->drm->mode_config.connection_mutex); /* * Walk the connector list instead of the encoder * list to detect the problem on ddi platforms * where there's just one encoder per digital port. */ - drm_connector_list_iter_begin(dev, &conn_iter); + drm_connector_list_iter_begin(display->drm, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { struct drm_connector_state *connector_state; struct intel_encoder *encoder; @@ -4552,11 +4370,11 @@ static bool check_digital_port_conflicts(struct intel_atomic_state *state) encoder = to_intel_encoder(connector_state->best_encoder); - drm_WARN_ON(dev, !connector_state->crtc); + drm_WARN_ON(display->drm, !connector_state->crtc); switch (encoder->type) { case INTEL_OUTPUT_DDI: - if (drm_WARN_ON(dev, !HAS_DDI(to_i915(dev)))) + if (drm_WARN_ON(display->drm, !HAS_DDI(display))) break; fallthrough; case INTEL_OUTPUT_DP: @@ -4704,9 +4522,9 @@ static int intel_crtc_prepare_cleared_state(struct intel_atomic_state *state, struct intel_crtc *crtc) { + struct intel_display *display = to_intel_display(state); struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); struct intel_crtc_state *saved_state; saved_state = intel_crtc_state_alloc(crtc); @@ -4731,8 +4549,8 @@ intel_crtc_prepare_cleared_state(struct intel_atomic_state *state, memcpy(saved_state->icl_port_dplls, crtc_state->icl_port_dplls, sizeof(saved_state->icl_port_dplls)); saved_state->crc_enabled = crtc_state->crc_enabled; - if (IS_G4X(dev_priv) || - IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) + if (display->platform.g4x || + display->platform.valleyview || display->platform.cherryview) saved_state->wm = crtc_state->wm; memcpy(crtc_state, saved_state, sizeof(*crtc_state)); @@ -4748,7 +4566,7 @@ intel_modeset_pipe_config(struct intel_atomic_state *state, struct intel_crtc *crtc, const struct intel_link_bw_limits *limits) { - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); struct drm_connector *connector; @@ -4781,7 +4599,7 @@ intel_modeset_pipe_config(struct intel_atomic_state *state, crtc_state->max_link_bpp_x16 = limits->max_bpp_x16[crtc->pipe]; if (crtc_state->pipe_bpp > fxp_q4_to_int(crtc_state->max_link_bpp_x16)) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] Link bpp limited to " FXP_Q4_FMT "\n", crtc->base.base.id, crtc->base.name, FXP_Q4_ARGS(crtc_state->max_link_bpp_x16)); @@ -4811,7 +4629,7 @@ intel_modeset_pipe_config(struct intel_atomic_state *state, continue; if (!check_single_encoder_cloning(state, crtc, encoder)) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[ENCODER:%d:%s] rejecting invalid cloning configuration\n", encoder->base.base.id, encoder->base.name); return -EINVAL; @@ -4853,7 +4671,7 @@ intel_modeset_pipe_config(struct intel_atomic_state *state, if (ret == -EDEADLK) return ret; if (ret < 0) { - drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] config failure: %d\n", + drm_dbg_kms(display->drm, "[ENCODER:%d:%s] config failure: %d\n", encoder->base.base.id, encoder->base.name, ret); return ret; } @@ -4869,7 +4687,7 @@ intel_modeset_pipe_config(struct intel_atomic_state *state, if (ret == -EDEADLK) return ret; if (ret < 0) { - drm_dbg_kms(&i915->drm, "[CRTC:%d:%s] config failure: %d\n", + drm_dbg_kms(display->drm, "[CRTC:%d:%s] config failure: %d\n", crtc->base.base.id, crtc->base.name, ret); return ret; } @@ -4880,7 +4698,7 @@ intel_modeset_pipe_config(struct intel_atomic_state *state, */ crtc_state->dither = (crtc_state->pipe_bpp == 6*3) && !crtc_state->dither_force_disable; - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] hw max bpp: %i, pipe bpp: %i, dithering: %i\n", crtc->base.base.id, crtc->base.name, base_bpp, crtc_state->pipe_bpp, crtc_state->dither); @@ -5012,7 +4830,7 @@ pipe_config_infoframe_mismatch(struct drm_printer *p, bool fastset, const union hdmi_infoframe *a, const union hdmi_infoframe *b) { - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); const char *loglevel; if (fastset) { @@ -5027,9 +4845,9 @@ pipe_config_infoframe_mismatch(struct drm_printer *p, bool fastset, pipe_config_mismatch(p, fastset, crtc, name, "infoframe"); drm_printf(p, "expected:\n"); - hdmi_infoframe_log(loglevel, i915->drm.dev, a); + hdmi_infoframe_log(loglevel, display->drm->dev, a); drm_printf(p, "found:\n"); - hdmi_infoframe_log(loglevel, i915->drm.dev, b); + hdmi_infoframe_log(loglevel, display->drm->dev, b); } static void @@ -5145,16 +4963,15 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, bool fastset) { struct intel_display *display = to_intel_display(current_config); - struct drm_i915_private *dev_priv = to_i915(current_config->uapi.crtc->dev); struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc); struct drm_printer p; u32 exclude_infoframes = 0; bool ret = true; if (fastset) - p = drm_dbg_printer(&dev_priv->drm, DRM_UT_KMS, NULL); + p = drm_dbg_printer(display->drm, DRM_UT_KMS, NULL); else - p = drm_err_printer(&dev_priv->drm, NULL); + p = drm_err_printer(display->drm, NULL); #define PIPE_CONF_CHECK_X(name) do { \ if (current_config->name != pipe_config->name) { \ @@ -5421,8 +5238,8 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_I(output_format); PIPE_CONF_CHECK_BOOL(has_hdmi_sink); - if ((DISPLAY_VER(dev_priv) < 8 && !IS_HASWELL(dev_priv)) || - IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) + if ((DISPLAY_VER(display) < 8 && !display->platform.haswell) || + display->platform.valleyview || display->platform.cherryview) PIPE_CONF_CHECK_BOOL(limited_color_range); PIPE_CONF_CHECK_BOOL(hdmi_scrambling); @@ -5438,7 +5255,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_X(gmch_pfit.control); /* pfit ratios are autocomputed by the hw on gen4+ */ - if (DISPLAY_VER(dev_priv) < 4) + if (DISPLAY_VER(display) < 4) PIPE_CONF_CHECK_X(gmch_pfit.pgm_ratios); PIPE_CONF_CHECK_X(gmch_pfit.lvds_border_bits); @@ -5458,7 +5275,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_I(pixel_rate); PIPE_CONF_CHECK_X(gamma_mode); - if (IS_CHERRYVIEW(dev_priv)) + if (display->platform.cherryview) PIPE_CONF_CHECK_X(cgm_mode); else PIPE_CONF_CHECK_X(csc_mode); @@ -5478,21 +5295,21 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_BOOL(double_wide); - if (dev_priv->display.dpll.mgr) + if (display->dpll.mgr) PIPE_CONF_CHECK_P(shared_dpll); /* FIXME convert everything over the dpll_mgr */ - if (dev_priv->display.dpll.mgr || HAS_GMCH(dev_priv)) + if (display->dpll.mgr || HAS_GMCH(display)) PIPE_CONF_CHECK_PLL(dpll_hw_state); /* FIXME convert MTL+ platforms over to dpll_mgr */ - if (DISPLAY_VER(dev_priv) >= 14) + if (DISPLAY_VER(display) >= 14) PIPE_CONF_CHECK_PLL_CX0(dpll_hw_state.cx0pll); PIPE_CONF_CHECK_X(dsi_pll.ctrl); PIPE_CONF_CHECK_X(dsi_pll.div); - if (IS_G4X(dev_priv) || DISPLAY_VER(dev_priv) >= 5) + if (display->platform.g4x || DISPLAY_VER(display) >= 5) PIPE_CONF_CHECK_I(pipe_bpp); if (!fastset || !pipe_config->update_m_n) { @@ -5608,11 +5425,11 @@ static int intel_modeset_pipe(struct intel_atomic_state *state, struct intel_crtc_state *crtc_state, const char *reason) { - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); int ret; - drm_dbg_kms(&i915->drm, "[CRTC:%d:%s] Full modeset due to %s\n", + drm_dbg_kms(display->drm, "[CRTC:%d:%s] Full modeset due to %s\n", crtc->base.base.id, crtc->base.name, reason); ret = drm_atomic_add_affected_connectors(&state->base, @@ -5652,10 +5469,10 @@ static int intel_modeset_pipe(struct intel_atomic_state *state, int intel_modeset_pipes_in_mask_early(struct intel_atomic_state *state, const char *reason, u8 mask) { - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_crtc *crtc; - for_each_intel_crtc_in_pipe_mask(&i915->drm, crtc, mask) { + for_each_intel_crtc_in_pipe_mask(display->drm, crtc, mask) { struct intel_crtc_state *crtc_state; int ret; @@ -5699,10 +5516,10 @@ intel_crtc_flag_modeset(struct intel_crtc_state *crtc_state) int intel_modeset_all_pipes_late(struct intel_atomic_state *state, const char *reason) { - struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_crtc *crtc; - for_each_intel_crtc(&dev_priv->drm, crtc) { + for_each_intel_crtc(display->drm, crtc) { struct intel_crtc_state *crtc_state; int ret; @@ -5728,7 +5545,7 @@ int intel_modeset_all_pipes_late(struct intel_atomic_state *state, return 0; } -int intel_modeset_commit_pipes(struct drm_i915_private *i915, +int intel_modeset_commit_pipes(struct intel_display *display, u8 pipe_mask, struct drm_modeset_acquire_ctx *ctx) { @@ -5736,14 +5553,14 @@ int intel_modeset_commit_pipes(struct drm_i915_private *i915, struct intel_crtc *crtc; int ret; - state = drm_atomic_state_alloc(&i915->drm); + state = drm_atomic_state_alloc(display->drm); if (!state) return -ENOMEM; state->acquire_ctx = ctx; to_intel_atomic_state(state)->internal = true; - for_each_intel_crtc_in_pipe_mask(&i915->drm, crtc, pipe_mask) { + for_each_intel_crtc_in_pipe_mask(display->drm, crtc, pipe_mask) { struct intel_crtc_state *crtc_state = intel_atomic_get_crtc_state(state, crtc); @@ -5842,11 +5659,11 @@ u8 intel_calc_active_pipes(struct intel_atomic_state *state, static int intel_modeset_checks(struct intel_atomic_state *state) { - struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); state->modeset = true; - if (IS_HASWELL(dev_priv)) + if (display->platform.haswell) return hsw_mode_set_planes_workaround(state); return 0; @@ -5863,15 +5680,15 @@ static bool lrr_params_changed(const struct drm_display_mode *old_adjusted_mode, static void intel_crtc_check_fastset(const struct intel_crtc_state *old_crtc_state, struct intel_crtc_state *new_crtc_state) { + struct intel_display *display = to_intel_display(new_crtc_state); struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); - struct drm_i915_private *i915 = to_i915(crtc->base.dev); /* only allow LRR when the timings stay within the VRR range */ if (old_crtc_state->vrr.in_range != new_crtc_state->vrr.in_range) new_crtc_state->update_lrr = false; if (!intel_pipe_config_compare(old_crtc_state, new_crtc_state, true)) { - drm_dbg_kms(&i915->drm, "[CRTC:%d:%s] fastset requirement not met, forcing full modeset\n", + drm_dbg_kms(display->drm, "[CRTC:%d:%s] fastset requirement not met, forcing full modeset\n", crtc->base.base.id, crtc->base.name); } else { if (allow_vblank_delay_fastset(old_crtc_state)) @@ -5895,17 +5712,17 @@ static void intel_crtc_check_fastset(const struct intel_crtc_state *old_crtc_sta static int intel_atomic_check_crtcs(struct intel_atomic_state *state) { + struct intel_display *display = to_intel_display(state); struct intel_crtc_state __maybe_unused *crtc_state; struct intel_crtc *crtc; int i; for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) { - struct drm_i915_private *i915 = to_i915(crtc->base.dev); int ret; ret = intel_crtc_atomic_check(state, crtc); if (ret) { - drm_dbg_atomic(&i915->drm, + drm_dbg_atomic(display->drm, "[CRTC:%d:%s] atomic driver check failed\n", crtc->base.base.id, crtc->base.name); return ret; @@ -5952,7 +5769,7 @@ static bool intel_pipes_need_modeset(struct intel_atomic_state *state, static int intel_atomic_check_joiner(struct intel_atomic_state *state, struct intel_crtc *primary_crtc) { - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_crtc_state *primary_crtc_state = intel_atomic_get_new_crtc_state(state, primary_crtc); struct intel_crtc *secondary_crtc; @@ -5961,20 +5778,20 @@ static int intel_atomic_check_joiner(struct intel_atomic_state *state, return 0; /* sanity check */ - if (drm_WARN_ON(&i915->drm, + if (drm_WARN_ON(display->drm, primary_crtc->pipe != joiner_primary_pipe(primary_crtc_state))) return -EINVAL; - if (primary_crtc_state->joiner_pipes & ~joiner_pipes(i915)) { - drm_dbg_kms(&i915->drm, + if (primary_crtc_state->joiner_pipes & ~joiner_pipes(display)) { + drm_dbg_kms(display->drm, "[CRTC:%d:%s] Cannot act as joiner primary " "(need 0x%x as pipes, only 0x%x possible)\n", primary_crtc->base.base.id, primary_crtc->base.name, - primary_crtc_state->joiner_pipes, joiner_pipes(i915)); + primary_crtc_state->joiner_pipes, joiner_pipes(display)); return -EINVAL; } - for_each_intel_crtc_in_pipe_mask(&i915->drm, secondary_crtc, + for_each_intel_crtc_in_pipe_mask(display->drm, secondary_crtc, intel_crtc_joiner_secondary_pipes(primary_crtc_state)) { struct intel_crtc_state *secondary_crtc_state; int ret; @@ -5985,7 +5802,7 @@ static int intel_atomic_check_joiner(struct intel_atomic_state *state, /* primary being enabled, secondary was already configured? */ if (secondary_crtc_state->uapi.enable) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] secondary is enabled as normal CRTC, but " "[CRTC:%d:%s] claiming this CRTC for joiner.\n", secondary_crtc->base.base.id, secondary_crtc->base.name, @@ -6004,7 +5821,7 @@ static int intel_atomic_check_joiner(struct intel_atomic_state *state, drm_crtc_index(&secondary_crtc->base))) return -EINVAL; - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] Used as secondary for joiner primary [CRTC:%d:%s]\n", secondary_crtc->base.base.id, secondary_crtc->base.name, primary_crtc->base.base.id, primary_crtc->base.name); @@ -6023,12 +5840,12 @@ static int intel_atomic_check_joiner(struct intel_atomic_state *state, static void kill_joiner_secondaries(struct intel_atomic_state *state, struct intel_crtc *primary_crtc) { - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_crtc_state *primary_crtc_state = intel_atomic_get_new_crtc_state(state, primary_crtc); struct intel_crtc *secondary_crtc; - for_each_intel_crtc_in_pipe_mask(&i915->drm, secondary_crtc, + for_each_intel_crtc_in_pipe_mask(display->drm, secondary_crtc, intel_crtc_joiner_secondary_pipes(primary_crtc_state)) { struct intel_crtc_state *secondary_crtc_state = intel_atomic_get_new_crtc_state(state, secondary_crtc); @@ -6062,7 +5879,7 @@ static void kill_joiner_secondaries(struct intel_atomic_state *state, static int intel_async_flip_check_uapi(struct intel_atomic_state *state, struct intel_crtc *crtc) { - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); const struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); const struct intel_plane_state *old_plane_state; @@ -6074,14 +5891,14 @@ static int intel_async_flip_check_uapi(struct intel_atomic_state *state, return 0; if (!new_crtc_state->uapi.active) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] not active\n", crtc->base.base.id, crtc->base.name); return -EINVAL; } if (intel_crtc_needs_modeset(new_crtc_state)) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] modeset required\n", crtc->base.base.id, crtc->base.name); return -EINVAL; @@ -6092,7 +5909,7 @@ static int intel_async_flip_check_uapi(struct intel_atomic_state *state, * Remove this check once the issues are fixed. */ if (new_crtc_state->joiner_pipes) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] async flip disallowed with joiner\n", crtc->base.base.id, crtc->base.name); return -EINVAL; @@ -6111,14 +5928,14 @@ static int intel_async_flip_check_uapi(struct intel_atomic_state *state, * enabled in the atomic IOCTL path. */ if (!plane->async_flip) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] async flip not supported\n", plane->base.base.id, plane->base.name); return -EINVAL; } if (!old_plane_state->uapi.fb || !new_plane_state->uapi.fb) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] no old or new framebuffer\n", plane->base.base.id, plane->base.name); return -EINVAL; @@ -6130,7 +5947,7 @@ static int intel_async_flip_check_uapi(struct intel_atomic_state *state, static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct intel_crtc *crtc) { - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); const struct intel_crtc_state *old_crtc_state, *new_crtc_state; const struct intel_plane_state *new_plane_state, *old_plane_state; struct intel_plane *plane; @@ -6143,21 +5960,21 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in return 0; if (!new_crtc_state->hw.active) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] not active\n", crtc->base.base.id, crtc->base.name); return -EINVAL; } if (intel_crtc_needs_modeset(new_crtc_state)) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] modeset required\n", crtc->base.base.id, crtc->base.name); return -EINVAL; } if (old_crtc_state->active_planes != new_crtc_state->active_planes) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[CRTC:%d:%s] Active planes cannot be in async flip\n", crtc->base.base.id, crtc->base.name); return -EINVAL; @@ -6173,7 +5990,7 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in * if we're really about to ask the hardware to perform * an async flip. We should never get this far otherwise. */ - if (drm_WARN_ON(&i915->drm, + if (drm_WARN_ON(display->drm, new_crtc_state->do_async_flip && !plane->async_flip)) return -EINVAL; @@ -6189,7 +6006,7 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in continue; if (!intel_plane_can_async_flip(plane, new_plane_state->hw.fb->modifier)) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] Modifier 0x%llx does not support async flip\n", plane->base.base.id, plane->base.name, new_plane_state->hw.fb->modifier); @@ -6198,7 +6015,7 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in if (intel_format_info_is_yuv_semiplanar(new_plane_state->hw.fb->format, new_plane_state->hw.fb->modifier)) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] Planar formats do not support async flips\n", plane->base.base.id, plane->base.name); return -EINVAL; @@ -6213,7 +6030,7 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in if (old_plane_state->view.color_plane[0].mapping_stride != new_plane_state->view.color_plane[0].mapping_stride) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] Stride cannot be changed in async flip\n", plane->base.base.id, plane->base.name); return -EINVAL; @@ -6221,7 +6038,7 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in if (old_plane_state->hw.fb->modifier != new_plane_state->hw.fb->modifier) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] Modifier cannot be changed in async flip\n", plane->base.base.id, plane->base.name); return -EINVAL; @@ -6229,7 +6046,7 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in if (old_plane_state->hw.fb->format != new_plane_state->hw.fb->format) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] Pixel format cannot be changed in async flip\n", plane->base.base.id, plane->base.name); return -EINVAL; @@ -6237,7 +6054,7 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in if (old_plane_state->hw.rotation != new_plane_state->hw.rotation) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] Rotation cannot be changed in async flip\n", plane->base.base.id, plane->base.name); return -EINVAL; @@ -6245,7 +6062,7 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in if (skl_plane_aux_dist(old_plane_state, 0) != skl_plane_aux_dist(new_plane_state, 0)) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] AUX_DIST cannot be changed in async flip\n", plane->base.base.id, plane->base.name); return -EINVAL; @@ -6253,14 +6070,14 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in if (!drm_rect_equals(&old_plane_state->uapi.src, &new_plane_state->uapi.src) || !drm_rect_equals(&old_plane_state->uapi.dst, &new_plane_state->uapi.dst)) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] Size/co-ordinates cannot be changed in async flip\n", plane->base.base.id, plane->base.name); return -EINVAL; } if (old_plane_state->hw.alpha != new_plane_state->hw.alpha) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANES:%d:%s] Alpha value cannot be changed in async flip\n", plane->base.base.id, plane->base.name); return -EINVAL; @@ -6268,21 +6085,21 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in if (old_plane_state->hw.pixel_blend_mode != new_plane_state->hw.pixel_blend_mode) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] Pixel blend mode cannot be changed in async flip\n", plane->base.base.id, plane->base.name); return -EINVAL; } if (old_plane_state->hw.color_encoding != new_plane_state->hw.color_encoding) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] Color encoding cannot be changed in async flip\n", plane->base.base.id, plane->base.name); return -EINVAL; } if (old_plane_state->hw.color_range != new_plane_state->hw.color_range) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] Color range cannot be changed in async flip\n", plane->base.base.id, plane->base.name); return -EINVAL; @@ -6290,7 +6107,7 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in /* plane decryption is allow to change only in synchronous flips */ if (old_plane_state->decrypt != new_plane_state->decrypt) { - drm_dbg_kms(&i915->drm, + drm_dbg_kms(display->drm, "[PLANE:%d:%s] Decryption cannot be changed in async flip\n", plane->base.base.id, plane->base.name); return -EINVAL; @@ -6302,7 +6119,7 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in static int intel_joiner_add_affected_crtcs(struct intel_atomic_state *state) { - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); const struct intel_plane_state *plane_state; struct intel_crtc_state *crtc_state; struct intel_plane *plane; @@ -6333,13 +6150,13 @@ static int intel_joiner_add_affected_crtcs(struct intel_atomic_state *state) modeset_pipes |= crtc_state->joiner_pipes; } - for_each_intel_crtc_in_pipe_mask(&i915->drm, crtc, affected_pipes) { + for_each_intel_crtc_in_pipe_mask(display->drm, crtc, affected_pipes) { crtc_state = intel_atomic_get_crtc_state(&state->base, crtc); if (IS_ERR(crtc_state)) return PTR_ERR(crtc_state); } - for_each_intel_crtc_in_pipe_mask(&i915->drm, crtc, modeset_pipes) { + for_each_intel_crtc_in_pipe_mask(display->drm, crtc, modeset_pipes) { int ret; crtc_state = intel_atomic_get_new_crtc_state(state, crtc); @@ -6369,7 +6186,7 @@ static int intel_atomic_check_config(struct intel_atomic_state *state, struct intel_link_bw_limits *limits, enum pipe *failed_pipe) { - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_crtc_state *new_crtc_state; struct intel_crtc *crtc; int ret; @@ -6394,7 +6211,7 @@ static int intel_atomic_check_config(struct intel_atomic_state *state, continue; } - if (drm_WARN_ON(&i915->drm, intel_crtc_is_joiner_secondary(new_crtc_state))) + if (drm_WARN_ON(display->drm, intel_crtc_is_joiner_secondary(new_crtc_state))) continue; ret = intel_crtc_prepare_cleared_state(state, crtc); @@ -6413,7 +6230,7 @@ static int intel_atomic_check_config(struct intel_atomic_state *state, if (!intel_crtc_needs_modeset(new_crtc_state)) continue; - if (drm_WARN_ON(&i915->drm, intel_crtc_is_joiner_secondary(new_crtc_state))) + if (drm_WARN_ON(display->drm, intel_crtc_is_joiner_secondary(new_crtc_state))) continue; if (!new_crtc_state->hw.enable) @@ -6478,7 +6295,6 @@ int intel_atomic_check(struct drm_device *dev, struct drm_atomic_state *_state) { struct intel_display *display = to_intel_display(dev); - struct drm_i915_private *dev_priv = to_i915(dev); struct intel_atomic_state *state = to_intel_atomic_state(_state); struct intel_crtc_state *old_crtc_state, *new_crtc_state; struct intel_crtc *crtc; @@ -6526,7 +6342,7 @@ int intel_atomic_check(struct drm_device *dev, continue; if (intel_crtc_is_joiner_secondary(new_crtc_state)) { - drm_WARN_ON(&dev_priv->drm, new_crtc_state->uapi.enable); + drm_WARN_ON(display->drm, new_crtc_state->uapi.enable); continue; } @@ -6597,7 +6413,7 @@ int intel_atomic_check(struct drm_device *dev, } if (any_ms && !check_digital_port_conflicts(state)) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "rejecting conflicting digital port configuration\n"); ret = -EINVAL; goto fail; @@ -6653,7 +6469,7 @@ int intel_atomic_check(struct drm_device *dev, goto fail; /* Either full modeset or fastset (or neither), never both */ - drm_WARN_ON(&dev_priv->drm, + drm_WARN_ON(display->drm, intel_crtc_needs_modeset(new_crtc_state) && intel_crtc_needs_fastset(new_crtc_state)); @@ -6713,6 +6529,7 @@ void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc, static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state, const struct intel_crtc_state *new_crtc_state) { + struct intel_display *display = to_intel_display(new_crtc_state); struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); @@ -6727,7 +6544,7 @@ static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state, intel_set_pipe_src_size(new_crtc_state); /* on skylake this is done by detaching scalers */ - if (DISPLAY_VER(dev_priv) >= 9) { + if (DISPLAY_VER(display) >= 9) { if (new_crtc_state->pch_pfit.enabled) skl_pfit_enable(new_crtc_state); } else if (HAS_PCH_SPLIT(dev_priv)) { @@ -6745,8 +6562,8 @@ static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state, * HSW/BDW only really need this here for fastboot, after * that the value should not change without a full modeset. */ - if (DISPLAY_VER(dev_priv) >= 9 || - IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) + if (DISPLAY_VER(display) >= 9 || + display->platform.broadwell || display->platform.haswell) hsw_set_linetime_wm(new_crtc_state); if (new_crtc_state->update_m_n) @@ -6760,14 +6577,14 @@ static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state, static void commit_pipe_pre_planes(struct intel_atomic_state *state, struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); const struct intel_crtc_state *old_crtc_state = intel_atomic_get_old_crtc_state(state, crtc); const struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); bool modeset = intel_crtc_needs_modeset(new_crtc_state); - drm_WARN_ON(&dev_priv->drm, new_crtc_state->use_dsb); + drm_WARN_ON(display->drm, new_crtc_state->use_dsb); /* * During modesets pipe configuration was programmed as the @@ -6777,7 +6594,7 @@ static void commit_pipe_pre_planes(struct intel_atomic_state *state, if (intel_crtc_needs_color_update(new_crtc_state)) intel_color_commit_arm(NULL, new_crtc_state); - if (DISPLAY_VER(dev_priv) >= 9 || IS_BROADWELL(dev_priv)) + if (DISPLAY_VER(display) >= 9 || display->platform.broadwell) bdw_set_pipe_misc(NULL, new_crtc_state); if (intel_crtc_needs_fastset(new_crtc_state)) @@ -6792,20 +6609,20 @@ static void commit_pipe_pre_planes(struct intel_atomic_state *state, static void commit_pipe_post_planes(struct intel_atomic_state *state, struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); const struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); - drm_WARN_ON(&dev_priv->drm, new_crtc_state->use_dsb); + drm_WARN_ON(display->drm, new_crtc_state->use_dsb); /* * Disable the scaler(s) after the plane(s) so that we don't * get a catastrophic underrun even if the two operations * end up happening in two different frames. */ - if (DISPLAY_VER(dev_priv) >= 9 && + if (DISPLAY_VER(display) >= 9 && !intel_crtc_needs_modeset(new_crtc_state)) - skl_detach_scalers(new_crtc_state); + skl_detach_scalers(NULL, new_crtc_state); if (intel_crtc_vrr_enabling(state, crtc)) intel_vrr_enable(new_crtc_state); @@ -6814,7 +6631,7 @@ static void commit_pipe_post_planes(struct intel_atomic_state *state, static void intel_enable_crtc(struct intel_atomic_state *state, struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); const struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); struct intel_crtc *pipe_crtc; @@ -6822,7 +6639,7 @@ static void intel_enable_crtc(struct intel_atomic_state *state, if (!intel_crtc_needs_modeset(new_crtc_state)) return; - for_each_intel_crtc_in_pipe_mask_reverse(&dev_priv->drm, pipe_crtc, + for_each_intel_crtc_in_pipe_mask_reverse(display->drm, pipe_crtc, intel_crtc_joined_pipe_mask(new_crtc_state)) { const struct intel_crtc_state *pipe_crtc_state = intel_atomic_get_new_crtc_state(state, pipe_crtc); @@ -6831,7 +6648,7 @@ static void intel_enable_crtc(struct intel_atomic_state *state, intel_crtc_update_active_timings(pipe_crtc_state, false); } - dev_priv->display.funcs.display->crtc_enable(state, crtc); + display->funcs.display->crtc_enable(state, crtc); /* vblanks work again, re-enable pipe CRC. */ intel_crtc_enable_pipe_crc(crtc); @@ -6841,7 +6658,6 @@ static void intel_pre_update_crtc(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct intel_display *display = to_intel_display(state); - struct drm_i915_private *i915 = to_i915(state->base.dev); const struct intel_crtc_state *old_crtc_state = intel_atomic_get_old_crtc_state(state, crtc); struct intel_crtc_state *new_crtc_state = @@ -6850,7 +6666,7 @@ static void intel_pre_update_crtc(struct intel_atomic_state *state, if (old_crtc_state->inherited || intel_crtc_needs_modeset(new_crtc_state)) { - if (HAS_DPT(i915)) + if (HAS_DPT(display)) intel_dpt_configure(crtc); } @@ -6864,7 +6680,7 @@ static void intel_pre_update_crtc(struct intel_atomic_state *state, if (intel_crtc_needs_fastset(new_crtc_state)) intel_encoders_update_pipe(state, crtc); - if (DISPLAY_VER(i915) >= 11 && + if (DISPLAY_VER(display) >= 11 && intel_crtc_needs_fastset(new_crtc_state)) icl_set_pipe_chicken(new_crtc_state); @@ -6938,7 +6754,7 @@ static void intel_update_crtc(struct intel_atomic_state *state, static void intel_old_crtc_state_disables(struct intel_atomic_state *state, struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); const struct intel_crtc_state *old_crtc_state = intel_atomic_get_old_crtc_state(state, crtc); struct intel_crtc *pipe_crtc; @@ -6947,13 +6763,13 @@ static void intel_old_crtc_state_disables(struct intel_atomic_state *state, * We need to disable pipe CRC before disabling the pipe, * or we race against vblank off. */ - for_each_intel_crtc_in_pipe_mask(&dev_priv->drm, pipe_crtc, + for_each_intel_crtc_in_pipe_mask(display->drm, pipe_crtc, intel_crtc_joined_pipe_mask(old_crtc_state)) intel_crtc_disable_pipe_crc(pipe_crtc); - dev_priv->display.funcs.display->crtc_disable(state, crtc); + display->funcs.display->crtc_disable(state, crtc); - for_each_intel_crtc_in_pipe_mask(&dev_priv->drm, pipe_crtc, + for_each_intel_crtc_in_pipe_mask(display->drm, pipe_crtc, intel_crtc_joined_pipe_mask(old_crtc_state)) { const struct intel_crtc_state *new_pipe_crtc_state = intel_atomic_get_new_crtc_state(state, pipe_crtc); @@ -6968,7 +6784,7 @@ static void intel_old_crtc_state_disables(struct intel_atomic_state *state, static void intel_commit_modeset_disables(struct intel_atomic_state *state) { - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); const struct intel_crtc_state *new_crtc_state, *old_crtc_state; struct intel_crtc *crtc; u8 disable_pipes = 0; @@ -7035,7 +6851,7 @@ static void intel_commit_modeset_disables(struct intel_atomic_state *state) disable_pipes &= ~intel_crtc_joined_pipe_mask(old_crtc_state); } - drm_WARN_ON(&i915->drm, disable_pipes); + drm_WARN_ON(display->drm, disable_pipes); } static void intel_commit_modeset_enables(struct intel_atomic_state *state) @@ -7062,7 +6878,7 @@ static void intel_commit_modeset_enables(struct intel_atomic_state *state) static void skl_commit_modeset_enables(struct intel_atomic_state *state) { - struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_crtc *crtc; struct intel_crtc_state *old_crtc_state, *new_crtc_state; struct skl_ddb_entry entries[I915_MAX_PIPES] = {}; @@ -7204,8 +7020,9 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state) if ((update_pipes & BIT(pipe)) == 0) continue; - drm_WARN_ON(&dev_priv->drm, skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb, - entries, I915_MAX_PIPES, pipe)); + drm_WARN_ON(display->drm, + skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb, + entries, I915_MAX_PIPES, pipe)); entries[pipe] = new_crtc_state->wm.skl.ddb; update_pipes &= ~BIT(pipe); @@ -7213,8 +7030,8 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state) intel_update_crtc(state, crtc); } - drm_WARN_ON(&dev_priv->drm, modeset_pipes); - drm_WARN_ON(&dev_priv->drm, update_pipes); + drm_WARN_ON(display->drm, modeset_pipes); + drm_WARN_ON(display->drm, update_pipes); } static void intel_atomic_commit_fence_wait(struct intel_atomic_state *intel_state) @@ -7259,7 +7076,7 @@ static void intel_atomic_cleanup_work(struct work_struct *work) { struct intel_atomic_state *state = container_of(work, struct intel_atomic_state, cleanup_work); - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_crtc_state *old_crtc_state; struct intel_crtc *crtc; int i; @@ -7267,14 +7084,14 @@ static void intel_atomic_cleanup_work(struct work_struct *work) for_each_old_intel_crtc_in_state(state, crtc, old_crtc_state, i) intel_atomic_dsb_cleanup(old_crtc_state); - drm_atomic_helper_cleanup_planes(&i915->drm, &state->base); + drm_atomic_helper_cleanup_planes(display->drm, &state->base); drm_atomic_helper_commit_cleanup_done(&state->base); drm_atomic_state_put(&state->base); } static void intel_atomic_prepare_plane_clear_colors(struct intel_atomic_state *state) { - struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_display *display = to_intel_display(state); struct intel_plane *plane; struct intel_plane_state *plane_state; int i; @@ -7311,7 +7128,7 @@ static void intel_atomic_prepare_plane_clear_colors(struct intel_atomic_state *s &plane_state->ccval, sizeof(plane_state->ccval)); /* The above could only fail if the FB obj has an unexpected backing store type. */ - drm_WARN_ON(&i915->drm, ret); + drm_WARN_ON(display->drm, ret); } } @@ -7319,8 +7136,6 @@ static void intel_atomic_dsb_prepare(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct intel_display *display = to_intel_display(state); - const struct intel_crtc_state *old_crtc_state = - intel_atomic_get_old_crtc_state(state, crtc); struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); @@ -7332,11 +7147,8 @@ static void intel_atomic_dsb_prepare(struct intel_atomic_state *state, /* FIXME deal with everything */ new_crtc_state->use_dsb = - new_crtc_state->update_planes && !new_crtc_state->do_async_flip && (DISPLAY_VER(display) >= 20 || !new_crtc_state->has_psr) && - !new_crtc_state->scaler_state.scaler_users && - !old_crtc_state->scaler_state.scaler_users && !intel_crtc_needs_modeset(new_crtc_state) && !intel_crtc_needs_fastset(new_crtc_state); @@ -7346,6 +7158,7 @@ static void intel_atomic_dsb_prepare(struct intel_atomic_state *state, static void intel_atomic_dsb_finish(struct intel_atomic_state *state, struct intel_crtc *crtc) { + struct intel_display *display = to_intel_display(state); struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); @@ -7392,6 +7205,10 @@ static void intel_atomic_dsb_finish(struct intel_atomic_state *state, intel_crtc_planes_update_arm(new_crtc_state->dsb_commit, state, crtc); + if (DISPLAY_VER(display) >= 9) + skl_detach_scalers(new_crtc_state->dsb_commit, + new_crtc_state); + if (!new_crtc_state->dsb_color_vblank) { intel_dsb_wait_vblanks(new_crtc_state->dsb_commit, 1); @@ -7412,8 +7229,7 @@ static void intel_atomic_dsb_finish(struct intel_atomic_state *state, static void intel_atomic_commit_tail(struct intel_atomic_state *state) { struct intel_display *display = to_intel_display(state); - struct drm_device *dev = state->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = to_i915(display->drm); struct intel_crtc_state *new_crtc_state, *old_crtc_state; struct intel_crtc *crtc; struct intel_power_domain_mask put_domains[I915_MAX_PIPES] = {}; @@ -7425,11 +7241,14 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) intel_atomic_commit_fence_wait(state); - intel_td_flush(dev_priv); + intel_td_flush(display); intel_atomic_prepare_plane_clear_colors(state); for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) + intel_fbc_prepare_dirty_rect(state, crtc); + + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) intel_atomic_dsb_finish(state, crtc); drm_atomic_helper_wait_for_dependencies(&state->base); @@ -7489,7 +7308,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) intel_pmdemand_pre_plane_update(state); if (state->modeset) { - drm_atomic_helper_update_legacy_modeset_state(dev, &state->base); + drm_atomic_helper_update_legacy_modeset_state(display->drm, &state->base); intel_set_cdclk_pre_plane_update(state); @@ -7504,10 +7323,10 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) /* Complete events for now disable pipes here. */ if (modeset && !new_crtc_state->hw.active && new_crtc_state->uapi.event) { - spin_lock_irq(&dev->event_lock); + spin_lock_irq(&display->drm->event_lock); drm_crtc_send_vblank_event(&crtc->base, new_crtc_state->uapi.event); - spin_unlock_irq(&dev->event_lock); + spin_unlock_irq(&display->drm->event_lock); new_crtc_state->uapi.event = NULL; } @@ -7523,13 +7342,10 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) } /* Now enable the clocks, plane, pipe, and connectors that we set up. */ - dev_priv->display.funcs.display->commit_modeset_enables(state); + display->funcs.display->commit_modeset_enables(state); intel_program_dpkgc_latency(state); - if (state->modeset) - intel_set_cdclk_post_plane_update(state); - intel_wait_for_vblank_workers(state); /* FIXME: We should call drm_atomic_helper_commit_hw_done() here @@ -7541,7 +7357,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) * - switch over to the vblank wait helper in the core after that since * we don't need out special handling any more. */ - drm_atomic_helper_wait_for_flip_done(dev, &state->base); + drm_atomic_helper_wait_for_flip_done(display->drm, &state->base); for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { if (new_crtc_state->do_async_flip) @@ -7570,7 +7386,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) * chance of catching underruns with the intermediate watermarks * vs. the new plane configuration. */ - if (DISPLAY_VER(dev_priv) == 2 && planes_enabling(old_crtc_state, new_crtc_state)) + if (DISPLAY_VER(display) == 2 && planes_enabling(old_crtc_state, new_crtc_state)) intel_set_cpu_fifo_underrun_reporting(display, crtc->pipe, true); intel_optimize_watermarks(state, crtc); @@ -7606,6 +7422,8 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) intel_verify_planes(state); intel_sagv_post_plane_update(state); + if (state->modeset) + intel_set_cdclk_post_plane_update(state); intel_pmdemand_post_plane_update(state); drm_atomic_helper_commit_hw_done(&state->base); @@ -7636,7 +7454,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) * down. */ INIT_WORK(&state->cleanup_work, intel_atomic_cleanup_work); - queue_work(dev_priv->display.wq.cleanup, &state->cleanup_work); + queue_work(display->wq.cleanup, &state->cleanup_work); } static void intel_atomic_commit_work(struct work_struct *work) @@ -7695,6 +7513,7 @@ static int intel_atomic_swap_state(struct intel_atomic_state *state) int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state, bool nonblock) { + struct intel_display *display = to_intel_display(dev); struct intel_atomic_state *state = to_intel_atomic_state(_state); struct drm_i915_private *dev_priv = to_i915(dev); int ret = 0; @@ -7718,7 +7537,7 @@ int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state, * FIXME doing watermarks and fb cleanup from a vblank worker * (assuming we had any) would solve these problems. */ - if (DISPLAY_VER(dev_priv) < 9 && state->base.legacy_cursor_update) { + if (DISPLAY_VER(display) < 9 && state->base.legacy_cursor_update) { struct intel_crtc_state *new_crtc_state; struct intel_crtc *crtc; int i; @@ -7731,7 +7550,7 @@ int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state, ret = intel_atomic_prepare_commit(state); if (ret) { - drm_dbg_atomic(&dev_priv->drm, + drm_dbg_atomic(display->drm, "Preparing state failed with %i\n", ret); intel_runtime_pm_put(&dev_priv->runtime_pm, state->wakeref); return ret; @@ -7751,12 +7570,12 @@ int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state, INIT_WORK(&state->base.commit_work, intel_atomic_commit_work); if (nonblock && state->modeset) { - queue_work(dev_priv->display.wq.modeset, &state->base.commit_work); + queue_work(display->wq.modeset, &state->base.commit_work); } else if (nonblock) { - queue_work(dev_priv->display.wq.flip, &state->base.commit_work); + queue_work(display->wq.flip, &state->base.commit_work); } else { if (state->modeset) - flush_workqueue(dev_priv->display.wq.modeset); + flush_workqueue(display->wq.modeset); intel_atomic_commit_tail(state); } @@ -7765,11 +7584,11 @@ int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state, static u32 intel_encoder_possible_clones(struct intel_encoder *encoder) { - struct drm_device *dev = encoder->base.dev; + struct intel_display *display = to_intel_display(encoder); struct intel_encoder *source_encoder; u32 possible_clones = 0; - for_each_intel_encoder(dev, source_encoder) { + for_each_intel_encoder(display->drm, source_encoder) { if (encoders_cloneable(encoder, source_encoder)) possible_clones |= drm_encoder_mask(&source_encoder->base); } @@ -7779,47 +7598,49 @@ static u32 intel_encoder_possible_clones(struct intel_encoder *encoder) static u32 intel_encoder_possible_crtcs(struct intel_encoder *encoder) { - struct drm_device *dev = encoder->base.dev; + struct intel_display *display = to_intel_display(encoder); struct intel_crtc *crtc; u32 possible_crtcs = 0; - for_each_intel_crtc_in_pipe_mask(dev, crtc, encoder->pipe_mask) + for_each_intel_crtc_in_pipe_mask(display->drm, crtc, encoder->pipe_mask) possible_crtcs |= drm_crtc_mask(&crtc->base); return possible_crtcs; } -static bool ilk_has_edp_a(struct drm_i915_private *dev_priv) +static bool ilk_has_edp_a(struct intel_display *display) { - if (!IS_MOBILE(dev_priv)) + if (!display->platform.mobile) return false; - if ((intel_de_read(dev_priv, DP_A) & DP_DETECTED) == 0) + if ((intel_de_read(display, DP_A) & DP_DETECTED) == 0) return false; - if (IS_IRONLAKE(dev_priv) && (intel_de_read(dev_priv, FUSE_STRAP) & ILK_eDP_A_DISABLE)) + if (display->platform.ironlake && (intel_de_read(display, FUSE_STRAP) & ILK_eDP_A_DISABLE)) return false; return true; } -static bool intel_ddi_crt_present(struct drm_i915_private *dev_priv) +static bool intel_ddi_crt_present(struct intel_display *display) { - if (DISPLAY_VER(dev_priv) >= 9) + struct drm_i915_private *dev_priv = to_i915(display->drm); + + if (DISPLAY_VER(display) >= 9) return false; - if (IS_HASWELL_ULT(dev_priv) || IS_BROADWELL_ULT(dev_priv)) + if (display->platform.haswell_ult || display->platform.broadwell_ult) return false; if (HAS_PCH_LPT_H(dev_priv) && - intel_de_read(dev_priv, SFUSE_STRAP) & SFUSE_STRAP_CRT_DISABLED) + intel_de_read(display, SFUSE_STRAP) & SFUSE_STRAP_CRT_DISABLED) return false; /* DDI E can't be used if DDI A requires 4 lanes */ - if (intel_de_read(dev_priv, DDI_BUF_CTL(PORT_A)) & DDI_A_4_LANES) + if (intel_de_read(display, DDI_BUF_CTL(PORT_A)) & DDI_A_4_LANES) return false; - if (!dev_priv->display.vbt.int_crt_support) + if (!display->vbt.int_crt_support) return false; return true; @@ -7831,24 +7652,24 @@ bool assert_port_valid(struct intel_display *display, enum port port) "Platform does not support port %c\n", port_name(port)); } -void intel_setup_outputs(struct drm_i915_private *dev_priv) +void intel_setup_outputs(struct intel_display *display) { - struct intel_display *display = &dev_priv->display; + struct drm_i915_private *dev_priv = to_i915(display->drm); struct intel_encoder *encoder; bool dpd_is_edp = false; intel_pps_unlock_regs_wa(display); - if (!HAS_DISPLAY(dev_priv)) + if (!HAS_DISPLAY(display)) return; - if (HAS_DDI(dev_priv)) { - if (intel_ddi_crt_present(dev_priv)) + if (HAS_DDI(display)) { + if (intel_ddi_crt_present(display)) intel_crt_init(display); intel_bios_for_each_encoder(display, intel_ddi_init); - if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) + if (display->platform.geminilake || display->platform.broxton) vlv_dsi_init(dev_priv); } else if (HAS_PCH_SPLIT(dev_priv)) { int found; @@ -7863,33 +7684,33 @@ void intel_setup_outputs(struct drm_i915_private *dev_priv) dpd_is_edp = intel_dp_is_port_edp(display, PORT_D); - if (ilk_has_edp_a(dev_priv)) + if (ilk_has_edp_a(display)) g4x_dp_init(display, DP_A, PORT_A); - if (intel_de_read(dev_priv, PCH_HDMIB) & SDVO_DETECTED) { + if (intel_de_read(display, PCH_HDMIB) & SDVO_DETECTED) { /* PCH SDVOB multiplex with HDMIB */ found = intel_sdvo_init(display, PCH_SDVOB, PORT_B); if (!found) g4x_hdmi_init(display, PCH_HDMIB, PORT_B); - if (!found && (intel_de_read(dev_priv, PCH_DP_B) & DP_DETECTED)) + if (!found && (intel_de_read(display, PCH_DP_B) & DP_DETECTED)) g4x_dp_init(display, PCH_DP_B, PORT_B); } - if (intel_de_read(dev_priv, PCH_HDMIC) & SDVO_DETECTED) + if (intel_de_read(display, PCH_HDMIC) & SDVO_DETECTED) g4x_hdmi_init(display, PCH_HDMIC, PORT_C); - if (!dpd_is_edp && intel_de_read(dev_priv, PCH_HDMID) & SDVO_DETECTED) + if (!dpd_is_edp && intel_de_read(display, PCH_HDMID) & SDVO_DETECTED) g4x_hdmi_init(display, PCH_HDMID, PORT_D); - if (intel_de_read(dev_priv, PCH_DP_C) & DP_DETECTED) + if (intel_de_read(display, PCH_DP_C) & DP_DETECTED) g4x_dp_init(display, PCH_DP_C, PORT_C); - if (intel_de_read(dev_priv, PCH_DP_D) & DP_DETECTED) + if (intel_de_read(display, PCH_DP_D) & DP_DETECTED) g4x_dp_init(display, PCH_DP_D, PORT_D); - } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { + } else if (display->platform.valleyview || display->platform.cherryview) { bool has_edp, has_port; - if (IS_VALLEYVIEW(dev_priv) && dev_priv->display.vbt.int_crt_support) + if (display->platform.valleyview && display->vbt.int_crt_support) intel_crt_init(display); /* @@ -7909,87 +7730,87 @@ void intel_setup_outputs(struct drm_i915_private *dev_priv) */ has_edp = intel_dp_is_port_edp(display, PORT_B); has_port = intel_bios_is_port_present(display, PORT_B); - if (intel_de_read(dev_priv, VLV_DP_B) & DP_DETECTED || has_port) + if (intel_de_read(display, VLV_DP_B) & DP_DETECTED || has_port) has_edp &= g4x_dp_init(display, VLV_DP_B, PORT_B); - if ((intel_de_read(dev_priv, VLV_HDMIB) & SDVO_DETECTED || has_port) && !has_edp) + if ((intel_de_read(display, VLV_HDMIB) & SDVO_DETECTED || has_port) && !has_edp) g4x_hdmi_init(display, VLV_HDMIB, PORT_B); has_edp = intel_dp_is_port_edp(display, PORT_C); has_port = intel_bios_is_port_present(display, PORT_C); - if (intel_de_read(dev_priv, VLV_DP_C) & DP_DETECTED || has_port) + if (intel_de_read(display, VLV_DP_C) & DP_DETECTED || has_port) has_edp &= g4x_dp_init(display, VLV_DP_C, PORT_C); - if ((intel_de_read(dev_priv, VLV_HDMIC) & SDVO_DETECTED || has_port) && !has_edp) + if ((intel_de_read(display, VLV_HDMIC) & SDVO_DETECTED || has_port) && !has_edp) g4x_hdmi_init(display, VLV_HDMIC, PORT_C); - if (IS_CHERRYVIEW(dev_priv)) { + if (display->platform.cherryview) { /* * eDP not supported on port D, * so no need to worry about it */ has_port = intel_bios_is_port_present(display, PORT_D); - if (intel_de_read(dev_priv, CHV_DP_D) & DP_DETECTED || has_port) + if (intel_de_read(display, CHV_DP_D) & DP_DETECTED || has_port) g4x_dp_init(display, CHV_DP_D, PORT_D); - if (intel_de_read(dev_priv, CHV_HDMID) & SDVO_DETECTED || has_port) + if (intel_de_read(display, CHV_HDMID) & SDVO_DETECTED || has_port) g4x_hdmi_init(display, CHV_HDMID, PORT_D); } vlv_dsi_init(dev_priv); - } else if (IS_PINEVIEW(dev_priv)) { + } else if (display->platform.pineview) { intel_lvds_init(dev_priv); intel_crt_init(display); - } else if (IS_DISPLAY_VER(dev_priv, 3, 4)) { + } else if (IS_DISPLAY_VER(display, 3, 4)) { bool found = false; - if (IS_MOBILE(dev_priv)) + if (display->platform.mobile) intel_lvds_init(dev_priv); intel_crt_init(display); - if (intel_de_read(dev_priv, GEN3_SDVOB) & SDVO_DETECTED) { - drm_dbg_kms(&dev_priv->drm, "probing SDVOB\n"); + if (intel_de_read(display, GEN3_SDVOB) & SDVO_DETECTED) { + drm_dbg_kms(display->drm, "probing SDVOB\n"); found = intel_sdvo_init(display, GEN3_SDVOB, PORT_B); - if (!found && IS_G4X(dev_priv)) { - drm_dbg_kms(&dev_priv->drm, + if (!found && display->platform.g4x) { + drm_dbg_kms(display->drm, "probing HDMI on SDVOB\n"); g4x_hdmi_init(display, GEN4_HDMIB, PORT_B); } - if (!found && IS_G4X(dev_priv)) + if (!found && display->platform.g4x) g4x_dp_init(display, DP_B, PORT_B); } /* Before G4X SDVOC doesn't have its own detect register */ - if (intel_de_read(dev_priv, GEN3_SDVOB) & SDVO_DETECTED) { - drm_dbg_kms(&dev_priv->drm, "probing SDVOC\n"); + if (intel_de_read(display, GEN3_SDVOB) & SDVO_DETECTED) { + drm_dbg_kms(display->drm, "probing SDVOC\n"); found = intel_sdvo_init(display, GEN3_SDVOC, PORT_C); } - if (!found && (intel_de_read(dev_priv, GEN3_SDVOC) & SDVO_DETECTED)) { + if (!found && (intel_de_read(display, GEN3_SDVOC) & SDVO_DETECTED)) { - if (IS_G4X(dev_priv)) { - drm_dbg_kms(&dev_priv->drm, + if (display->platform.g4x) { + drm_dbg_kms(display->drm, "probing HDMI on SDVOC\n"); g4x_hdmi_init(display, GEN4_HDMIC, PORT_C); } - if (IS_G4X(dev_priv)) + if (display->platform.g4x) g4x_dp_init(display, DP_C, PORT_C); } - if (IS_G4X(dev_priv) && (intel_de_read(dev_priv, DP_D) & DP_DETECTED)) + if (display->platform.g4x && (intel_de_read(display, DP_D) & DP_DETECTED)) g4x_dp_init(display, DP_D, PORT_D); - if (SUPPORTS_TV(dev_priv)) + if (SUPPORTS_TV(display)) intel_tv_init(display); - } else if (DISPLAY_VER(dev_priv) == 2) { - if (IS_I85X(dev_priv)) + } else if (DISPLAY_VER(display) == 2) { + if (display->platform.i85x) intel_lvds_init(dev_priv); intel_crt_init(display); intel_dvo_init(dev_priv); } - for_each_intel_encoder(&dev_priv->drm, encoder) { + for_each_intel_encoder(display->drm, encoder) { encoder->base.possible_crtcs = intel_encoder_possible_crtcs(encoder); encoder->base.possible_clones = @@ -7998,12 +7819,11 @@ void intel_setup_outputs(struct drm_i915_private *dev_priv) intel_init_pch_refclk(dev_priv); - drm_helper_move_panel_connectors_to_head(&dev_priv->drm); + drm_helper_move_panel_connectors_to_head(display->drm); } -static int max_dotclock(struct drm_i915_private *i915) +static int max_dotclock(struct intel_display *display) { - struct intel_display *display = &i915->display; int max_dotclock = display->cdclk.max_dotclk_freq; if (HAS_ULTRAJOINER(display)) @@ -8017,7 +7837,7 @@ static int max_dotclock(struct drm_i915_private *i915) enum drm_mode_status intel_mode_valid(struct drm_device *dev, const struct drm_display_mode *mode) { - struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_display *display = to_intel_display(dev); int hdisplay_max, htotal_max; int vdisplay_max, vtotal_max; @@ -8054,22 +7874,22 @@ enum drm_mode_status intel_mode_valid(struct drm_device *dev, * Reject clearly excessive dotclocks early to * avoid having to worry about huge integers later. */ - if (mode->clock > max_dotclock(dev_priv)) + if (mode->clock > max_dotclock(display)) return MODE_CLOCK_HIGH; /* Transcoder timing limits */ - if (DISPLAY_VER(dev_priv) >= 11) { + if (DISPLAY_VER(display) >= 11) { hdisplay_max = 16384; vdisplay_max = 8192; htotal_max = 16384; vtotal_max = 8192; - } else if (DISPLAY_VER(dev_priv) >= 9 || - IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) { + } else if (DISPLAY_VER(display) >= 9 || + display->platform.broadwell || display->platform.haswell) { hdisplay_max = 8192; /* FDI max 4096 handled elsewhere */ vdisplay_max = 4096; htotal_max = 8192; vtotal_max = 8192; - } else if (DISPLAY_VER(dev_priv) >= 3) { + } else if (DISPLAY_VER(display) >= 3) { hdisplay_max = 4096; vdisplay_max = 4096; htotal_max = 8192; @@ -8215,32 +8035,34 @@ static const struct intel_display_funcs i9xx_display_funcs = { /** * intel_init_display_hooks - initialize the display modesetting hooks - * @dev_priv: device private + * @display: display device private */ -void intel_init_display_hooks(struct drm_i915_private *dev_priv) +void intel_init_display_hooks(struct intel_display *display) { - if (DISPLAY_VER(dev_priv) >= 9) { - dev_priv->display.funcs.display = &skl_display_funcs; - } else if (HAS_DDI(dev_priv)) { - dev_priv->display.funcs.display = &ddi_display_funcs; + struct drm_i915_private *dev_priv = to_i915(display->drm); + + if (DISPLAY_VER(display) >= 9) { + display->funcs.display = &skl_display_funcs; + } else if (HAS_DDI(display)) { + display->funcs.display = &ddi_display_funcs; } else if (HAS_PCH_SPLIT(dev_priv)) { - dev_priv->display.funcs.display = &pch_split_display_funcs; - } else if (IS_CHERRYVIEW(dev_priv) || - IS_VALLEYVIEW(dev_priv)) { - dev_priv->display.funcs.display = &vlv_display_funcs; + display->funcs.display = &pch_split_display_funcs; + } else if (display->platform.cherryview || + display->platform.valleyview) { + display->funcs.display = &vlv_display_funcs; } else { - dev_priv->display.funcs.display = &i9xx_display_funcs; + display->funcs.display = &i9xx_display_funcs; } } -int intel_initial_commit(struct drm_device *dev) +int intel_initial_commit(struct intel_display *display) { struct drm_atomic_state *state = NULL; struct drm_modeset_acquire_ctx ctx; struct intel_crtc *crtc; int ret = 0; - state = drm_atomic_state_alloc(dev); + state = drm_atomic_state_alloc(display->drm); if (!state) return -ENOMEM; @@ -8250,7 +8072,7 @@ int intel_initial_commit(struct drm_device *dev) to_intel_atomic_state(state)->internal = true; retry: - for_each_intel_crtc(dev, crtc) { + for_each_intel_crtc(display->drm, crtc) { struct intel_crtc_state *crtc_state = intel_atomic_get_crtc_state(state, crtc); @@ -8274,7 +8096,7 @@ retry: */ crtc_state->uapi.color_mgmt_changed = true; - for_each_intel_encoder_mask(dev, encoder, + for_each_intel_encoder_mask(display->drm, encoder, crtc_state->uapi.encoder_mask) { if (encoder->initial_fastset_check && !encoder->initial_fastset_check(encoder, crtc_state)) { diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index e58daefc978e..3b54a62c290a 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -426,7 +426,7 @@ intel_mode_valid_max_plane_size(struct intel_display *display, enum drm_mode_status intel_cpu_transcoder_mode_valid(struct intel_display *display, const struct drm_display_mode *mode); -enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port); +enum phy intel_port_to_phy(struct intel_display *display, enum port port); bool is_trans_port_sync_mode(const struct intel_crtc_state *state); bool is_trans_port_sync_master(const struct intel_crtc_state *state); u8 intel_crtc_joined_pipe_mask(const struct intel_crtc_state *crtc_state); @@ -457,18 +457,16 @@ int vlv_get_cck_clock(struct drm_i915_private *dev_priv, const char *name, u32 reg, int ref_freq); int vlv_get_cck_clock_hpll(struct drm_i915_private *dev_priv, const char *name, u32 reg); -void intel_init_display_hooks(struct drm_i915_private *dev_priv); -bool intel_has_pending_fb_unpin(struct drm_i915_private *dev_priv); +bool intel_has_pending_fb_unpin(struct intel_display *display); void intel_encoder_destroy(struct drm_encoder *encoder); struct drm_display_mode * intel_encoder_current_mode(struct intel_encoder *encoder); void intel_encoder_get_config(struct intel_encoder *encoder, struct intel_crtc_state *crtc_state); bool intel_phy_is_combo(struct intel_display *display, enum phy phy); -bool intel_phy_is_tc(struct drm_i915_private *dev_priv, enum phy phy); -bool intel_phy_is_snps(struct drm_i915_private *dev_priv, enum phy phy); -enum tc_port intel_port_to_tc(struct drm_i915_private *dev_priv, - enum port port); +bool intel_phy_is_tc(struct intel_display *display, enum phy phy); +bool intel_phy_is_snps(struct intel_display *display, enum phy phy); +enum tc_port intel_port_to_tc(struct intel_display *display, enum port port); enum phy intel_encoder_to_phy(struct intel_encoder *encoder); bool intel_encoder_is_combo(struct intel_encoder *encoder); @@ -481,15 +479,15 @@ int ilk_get_lanes_required(int target_clock, int link_bw, int bpp); bool intel_fuzzy_clock_check(int clock1, int clock2); void intel_zero_m_n(struct intel_link_m_n *m_n); -void intel_set_m_n(struct drm_i915_private *i915, +void intel_set_m_n(struct intel_display *display, const struct intel_link_m_n *m_n, i915_reg_t data_m_reg, i915_reg_t data_n_reg, i915_reg_t link_m_reg, i915_reg_t link_n_reg); -void intel_get_m_n(struct drm_i915_private *i915, +void intel_get_m_n(struct intel_display *display, struct intel_link_m_n *m_n, i915_reg_t data_m_reg, i915_reg_t data_n_reg, i915_reg_t link_m_reg, i915_reg_t link_n_reg); -bool intel_cpu_transcoder_has_m2_n2(struct drm_i915_private *dev_priv, +bool intel_cpu_transcoder_has_m2_n2(struct intel_display *display, enum transcoder transcoder); void intel_cpu_transcoder_set_m1_n1(struct intel_crtc *crtc, enum transcoder cpu_transcoder, @@ -510,8 +508,6 @@ enum intel_display_power_domain intel_aux_power_domain(struct intel_digital_port *dig_port); void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state); -void ilk_pfit_disable(const struct intel_crtc_state *old_crtc_state); - int bdw_get_pipe_misc_bpp(struct intel_crtc *crtc); unsigned int intel_plane_fence_y_offset(const struct intel_plane_state *plane_state); @@ -525,8 +521,6 @@ void intel_set_plane_visible(struct intel_crtc_state *crtc_state, bool visible); void intel_plane_fixup_bitmasks(struct intel_crtc_state *crtc_state); -void intel_update_watermarks(struct drm_i915_private *i915); - bool intel_crtc_vrr_disabling(struct intel_atomic_state *state, struct intel_crtc *crtc); @@ -535,7 +529,7 @@ int intel_modeset_pipes_in_mask_early(struct intel_atomic_state *state, const char *reason, u8 pipe_mask); int intel_modeset_all_pipes_late(struct intel_atomic_state *state, const char *reason); -int intel_modeset_commit_pipes(struct drm_i915_private *i915, +int intel_modeset_commit_pipes(struct intel_display *display, u8 pipe_mask, struct drm_modeset_acquire_ctx *ctx); void intel_modeset_get_crtc_power_domains(struct intel_crtc_state *crtc_state, @@ -544,11 +538,11 @@ void intel_modeset_put_crtc_power_domains(struct intel_crtc *crtc, struct intel_power_domain_mask *domains); /* interface for intel_display_driver.c */ -void intel_setup_outputs(struct drm_i915_private *i915); -int intel_initial_commit(struct drm_device *dev); -void intel_panel_sanitize_ssc(struct drm_i915_private *i915); -void intel_update_czclk(struct drm_i915_private *i915); -void intel_atomic_helper_free_state_worker(struct work_struct *work); +void intel_init_display_hooks(struct intel_display *display); +void intel_setup_outputs(struct intel_display *display); +int intel_initial_commit(struct intel_display *display); +void intel_panel_sanitize_ssc(struct intel_display *display); +void intel_update_czclk(struct intel_display *display); enum drm_mode_status intel_mode_valid(struct drm_device *dev, const struct drm_display_mode *mode); int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state, diff --git a/drivers/gpu/drm/i915/display/intel_display_core.h b/drivers/gpu/drm/i915/display/intel_display_core.h index 554870d2494b..eeb7ae3eaea8 100644 --- a/drivers/gpu/drm/i915/display/intel_display_core.h +++ b/drivers/gpu/drm/i915/display/intel_display_core.h @@ -91,6 +91,7 @@ struct intel_wm_funcs { struct intel_crtc *crtc); int (*compute_global_watermarks)(struct intel_atomic_state *state); void (*get_hw_state)(struct drm_i915_private *i915); + void (*sanitize)(struct drm_i915_private *i915); }; struct intel_audio_state { @@ -386,7 +387,6 @@ struct intel_display { struct { /* list of fbdev register on this device */ struct intel_fbdev *fbdev; - struct work_struct suspend_work; } fbdev; struct { @@ -512,6 +512,8 @@ struct intel_display { /* restore state for suspend/resume and display reset */ struct drm_atomic_state *modeset_state; struct drm_modeset_acquire_ctx reset_ctx; + /* modeset stuck tracking for reset */ + atomic_t pending_fb_pin; u32 saveDSPARB; u32 saveSWF0[16]; u32 saveSWF1[16]; diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c index 9de7e512c0ab..fdedf65bee53 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c @@ -49,11 +49,6 @@ static struct intel_display *node_to_intel_display(struct drm_info_node *node) return to_intel_display(node->minor->dev); } -static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node) -{ - return to_i915(node->minor->dev); -} - static int intel_display_caps(struct seq_file *m, void *data) { struct intel_display *display = node_to_intel_display(m->private); @@ -85,8 +80,8 @@ static int i915_frontbuffer_tracking(struct seq_file *m, void *unused) static int i915_sr_status(struct seq_file *m, void *unused) { - struct drm_i915_private *dev_priv = node_to_i915(m->private); struct intel_display *display = node_to_intel_display(m->private); + struct drm_i915_private *dev_priv = to_i915(display->drm); intel_wakeref_t wakeref; bool sr_enabled = false; @@ -102,7 +97,7 @@ static int i915_sr_status(struct seq_file *m, void *unused) else if (display->platform.i915gm) sr_enabled = intel_de_read(display, INSTPM) & INSTPM_SELF_EN; else if (display->platform.pineview) - sr_enabled = intel_de_read(display, DSPFW3(dev_priv)) & PINEVIEW_SELF_REFRESH_EN; + sr_enabled = intel_de_read(display, DSPFW3(display)) & PINEVIEW_SELF_REFRESH_EN; else if (display->platform.valleyview || display->platform.cherryview) sr_enabled = intel_de_read(display, FW_BLC_SELF_VLV) & FW_CSPWRDWNEN; @@ -119,7 +114,6 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data) struct intel_framebuffer *fbdev_fb = NULL; struct drm_framebuffer *drm_fb; -#ifdef CONFIG_DRM_FBDEV_EMULATION fbdev_fb = intel_fbdev_framebuffer(display->fbdev.fbdev); if (fbdev_fb) { seq_printf(m, "fbcon size: %d x %d, depth %d, %d bpp, modifier 0x%llx, refcount %d, obj ", @@ -132,7 +126,6 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data) intel_bo_describe(m, intel_fb_bo(&fbdev_fb->base)); seq_putc(m, '\n'); } -#endif mutex_lock(&display->drm->mode_config.fb_lock); drm_for_each_fb(drm_fb, display->drm) { @@ -157,8 +150,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data) static int i915_power_domain_info(struct seq_file *m, void *unused) { - struct drm_i915_private *i915 = node_to_i915(m->private); - struct intel_display *display = &i915->display; + struct intel_display *display = node_to_intel_display(m->private); intel_display_power_debug(display, m); @@ -267,7 +259,7 @@ static void intel_connector_info(struct seq_file *m, switch (connector->connector_type) { case DRM_MODE_CONNECTOR_DisplayPort: case DRM_MODE_CONNECTOR_eDP: - if (intel_connector->mst_port) + if (intel_connector->mst.dp) intel_dp_mst_info(m, intel_connector); else intel_dp_info(m, intel_connector); @@ -588,7 +580,7 @@ static void intel_crtc_info(struct seq_file *m, struct intel_crtc *crtc) static int i915_display_info(struct seq_file *m, void *unused) { struct intel_display *display = node_to_intel_display(m->private); - struct drm_i915_private *dev_priv = node_to_i915(m->private); + struct drm_i915_private *dev_priv = to_i915(display->drm); struct intel_crtc *crtc; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; @@ -713,14 +705,13 @@ intel_lpsp_power_well_enabled(struct intel_display *display, static int i915_lpsp_status(struct seq_file *m, void *unused) { struct intel_display *display = node_to_intel_display(m->private); - struct drm_i915_private *i915 = node_to_i915(m->private); bool lpsp_enabled = false; if (DISPLAY_VER(display) >= 13 || IS_DISPLAY_VER(display, 9, 10)) { lpsp_enabled = !intel_lpsp_power_well_enabled(display, SKL_DISP_PW_2); } else if (IS_DISPLAY_VER(display, 11, 12)) { lpsp_enabled = !intel_lpsp_power_well_enabled(display, ICL_DISP_PW_3); - } else if (IS_HASWELL(i915) || IS_BROADWELL(i915)) { + } else if (display->platform.haswell || display->platform.broadwell) { lpsp_enabled = !intel_lpsp_power_well_enabled(display, HSW_DISP_PW_GLOBAL); } else { seq_puts(m, "LPSP: not supported\n"); @@ -756,7 +747,7 @@ static int i915_dp_mst_info(struct seq_file *m, void *unused) seq_printf(m, "MST Source Port [ENCODER:%d:%s]\n", dig_port->base.base.base.id, dig_port->base.base.name); - drm_dp_mst_dump_topology(m, &dig_port->dp.mst_mgr); + drm_dp_mst_dump_topology(m, &dig_port->dp.mst.mgr); } drm_connector_list_iter_end(&conn_iter); @@ -836,10 +827,10 @@ static const struct drm_info_list intel_display_debugfs_list[] = { {"i915_lpsp_status", i915_lpsp_status, 0}, }; -void intel_display_debugfs_register(struct drm_i915_private *i915) +void intel_display_debugfs_register(struct intel_display *display) { - struct intel_display *display = &i915->display; - struct drm_minor *minor = i915->drm.primary; + struct drm_i915_private *i915 = to_i915(display->drm); + struct drm_minor *minor = display->drm->primary; debugfs_create_file("i915_fifo_underrun_reset", 0644, minor->debugfs_root, display, &i915_fifo_underrun_reset_ops); @@ -865,7 +856,6 @@ static int i915_lpsp_capability_show(struct seq_file *m, void *data) struct intel_connector *connector = m->private; struct intel_display *display = to_intel_display(connector); struct intel_encoder *encoder = intel_attached_encoder(connector); - struct drm_i915_private *i915 = to_i915(connector->base.dev); int connector_type = connector->base.connector_type; bool lpsp_capable = false; @@ -892,7 +882,7 @@ static int i915_lpsp_capability_show(struct seq_file *m, void *data) (connector_type == DRM_MODE_CONNECTOR_DSI || connector_type == DRM_MODE_CONNECTOR_eDP || connector_type == DRM_MODE_CONNECTOR_DisplayPort)); - else if (IS_HASWELL(i915) || IS_BROADWELL(i915)) + else if (display->platform.haswell || display->platform.broadwell) lpsp_capable = connector_type == DRM_MODE_CONNECTOR_eDP; seq_printf(m, "LPSP: %s\n", lpsp_capable ? "capable" : "incapable"); @@ -1349,7 +1339,7 @@ void intel_connector_debugfs_add(struct intel_connector *connector) intel_dp_link_training_debugfs_add(connector); if (DISPLAY_VER(display) >= 11 && - ((connector_type == DRM_MODE_CONNECTOR_DisplayPort && !connector->mst_port) || + ((connector_type == DRM_MODE_CONNECTOR_DisplayPort && !connector->mst.dp) || connector_type == DRM_MODE_CONNECTOR_eDP)) { debugfs_create_file("i915_dsc_fec_support", 0644, root, connector, &i915_dsc_fec_support_fops); diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.h b/drivers/gpu/drm/i915/display/intel_display_debugfs.h index e1f479b7acd1..82af2f608111 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.h +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.h @@ -6,16 +6,16 @@ #ifndef __INTEL_DISPLAY_DEBUGFS_H__ #define __INTEL_DISPLAY_DEBUGFS_H__ -struct drm_i915_private; struct intel_connector; struct intel_crtc; +struct intel_display; #ifdef CONFIG_DEBUG_FS -void intel_display_debugfs_register(struct drm_i915_private *i915); +void intel_display_debugfs_register(struct intel_display *display); void intel_connector_debugfs_add(struct intel_connector *connector); void intel_crtc_debugfs_add(struct intel_crtc *crtc); #else -static inline void intel_display_debugfs_register(struct drm_i915_private *i915) {} +static inline void intel_display_debugfs_register(struct intel_display *display) {} static inline void intel_connector_debugfs_add(struct intel_connector *connector) {} static inline void intel_crtc_debugfs_add(struct intel_crtc *crtc) {} #endif diff --git a/drivers/gpu/drm/i915/display/intel_display_device.h b/drivers/gpu/drm/i915/display/intel_display_device.h index fc33791f02b9..717286981687 100644 --- a/drivers/gpu/drm/i915/display/intel_display_device.h +++ b/drivers/gpu/drm/i915/display/intel_display_device.h @@ -163,6 +163,7 @@ struct intel_display_platforms { #define HAS_DSC(__display) (DISPLAY_RUNTIME_INFO(__display)->has_dsc) #define HAS_DSC_MST(__display) (DISPLAY_VER(__display) >= 12 && HAS_DSC(__display)) #define HAS_FBC(__display) (DISPLAY_RUNTIME_INFO(__display)->fbc_mask != 0) +#define HAS_FBC_DIRTY_RECT(__display) (DISPLAY_VER(__display) >= 30) #define HAS_FPGA_DBG_UNCLAIMED(__display) (DISPLAY_INFO(__display)->has_fpga_dbg) #define HAS_FW_BLC(__display) (DISPLAY_VER(__display) >= 3) #define HAS_GMBUS_IRQ(__display) (DISPLAY_VER(__display) >= 4) diff --git a/drivers/gpu/drm/i915/display/intel_display_driver.c b/drivers/gpu/drm/i915/display/intel_display_driver.c index b72b07329fbf..31740a677dd8 100644 --- a/drivers/gpu/drm/i915/display/intel_display_driver.c +++ b/drivers/gpu/drm/i915/display/intel_display_driver.c @@ -194,13 +194,13 @@ void intel_display_driver_early_probe(struct intel_display *display) mutex_init(&display->hdcp.hdcp_mutex); intel_display_irq_init(i915); - intel_dkl_phy_init(i915); + intel_dkl_phy_init(display); intel_color_init_hooks(display); intel_init_cdclk_hooks(display); intel_audio_hooks_init(display); intel_dpll_init_clock_hook(i915); - intel_init_display_hooks(i915); - intel_fdi_init_hook(i915); + intel_init_display_hooks(display); + intel_fdi_init_hook(display); intel_dmc_wl_init(display); } @@ -431,7 +431,7 @@ int intel_display_driver_probe_nogem(struct intel_display *display) intel_wm_init(i915); - intel_panel_sanitize_ssc(i915); + intel_panel_sanitize_ssc(display); intel_pps_setup(display); @@ -449,9 +449,9 @@ int intel_display_driver_probe_nogem(struct intel_display *display) intel_plane_possible_crtcs_init(display); intel_shared_dpll_init(display); - intel_fdi_pll_freq_update(i915); + intel_fdi_pll_freq_update(display); - intel_update_czclk(i915); + intel_update_czclk(display); intel_display_driver_init_hw(display); intel_dpll_update_ref_clks(display); @@ -462,7 +462,7 @@ int intel_display_driver_probe_nogem(struct intel_display *display) /* Just disable it once at startup */ intel_vga_disable(display); - intel_setup_outputs(i915); + intel_setup_outputs(display); ret = intel_dp_tunnel_mgr_init(display); if (ret) @@ -517,7 +517,7 @@ int intel_display_driver_probe(struct intel_display *display) * are already calculated and there is no assert_plane warnings * during bootup. */ - ret = intel_initial_commit(display->drm); + ret = intel_initial_commit(display); if (ret) drm_dbg_kms(display->drm, "Initial modeset failed, %d\n", ret); @@ -550,7 +550,7 @@ void intel_display_driver_register(struct intel_display *display) intel_audio_register(display); - intel_display_debugfs_register(i915); + intel_display_debugfs_register(display); /* * We need to coordinate the hotplugs with the asynchronous diff --git a/drivers/gpu/drm/i915/display/intel_display_irq.c b/drivers/gpu/drm/i915/display/intel_display_irq.c index 99fb7fc7be39..aa23bb817805 100644 --- a/drivers/gpu/drm/i915/display/intel_display_irq.c +++ b/drivers/gpu/drm/i915/display/intel_display_irq.c @@ -1101,7 +1101,7 @@ static bool handle_plane_ats_fault(struct intel_crtc *crtc, enum plane_id plane_ "[CRTC:%d:%s] PLANE ATS fault\n", crtc->base.base.id, crtc->base.name); - return false; + return true; } static bool handle_pipedmc_ats_fault(struct intel_crtc *crtc, enum plane_id plane_id) @@ -1112,7 +1112,7 @@ static bool handle_pipedmc_ats_fault(struct intel_crtc *crtc, enum plane_id plan "[CRTC:%d:%s] PIPEDMC ATS fault\n", crtc->base.base.id, crtc->base.name); - return false; + return true; } static bool handle_pipedmc_fault(struct intel_crtc *crtc, enum plane_id plane_id) @@ -1123,7 +1123,7 @@ static bool handle_pipedmc_fault(struct intel_crtc *crtc, enum plane_id plane_id "[CRTC:%d:%s] PIPEDMC fault\n", crtc->base.base.id, crtc->base.name); - return false; + return true; } static const struct pipe_fault_handler mtl_pipe_fault_handlers[] = { diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 396930937d98..f7171e6932dc 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -1684,7 +1684,7 @@ static void icl_display_core_init(struct intel_display *display, /* 8. Ensure PHYs have completed calibration and adaptation */ if (display->platform.dg2) - intel_snps_phy_wait_for_calibration(dev_priv); + intel_snps_phy_wait_for_calibration(display); /* 9. XE2_HPD: Program CHICKEN_MISC_2 before any cursor or planes are enabled */ if (DISPLAY_VERx100(display) == 1401) @@ -2317,6 +2317,9 @@ void intel_display_power_debug(struct intel_display *display, struct seq_file *m mutex_lock(&power_domains->lock); + seq_printf(m, "Runtime power status: %s\n", + str_enabled_disabled(!power_domains->init_wakeref)); + seq_printf(m, "%-25s %s\n", "Power well/domain", "Use count"); for (i = 0; i < power_domains->power_well_count; i++) { struct i915_power_well *power_well; diff --git a/drivers/gpu/drm/i915/display/intel_display_power.h b/drivers/gpu/drm/i915/display/intel_display_power.h index a3a5c1be8bab..1b53d67f9b60 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.h +++ b/drivers/gpu/drm/i915/display/intel_display_power.h @@ -117,12 +117,13 @@ enum intel_display_power_domain { POWER_DOMAIN_INVALID = POWER_DOMAIN_NUM, }; -#define POWER_DOMAIN_PIPE(pipe) ((pipe) + POWER_DOMAIN_PIPE_A) +#define POWER_DOMAIN_PIPE(pipe) \ + ((enum intel_display_power_domain)((pipe) - PIPE_A + POWER_DOMAIN_PIPE_A)) #define POWER_DOMAIN_PIPE_PANEL_FITTER(pipe) \ - ((pipe) + POWER_DOMAIN_PIPE_PANEL_FITTER_A) + ((enum intel_display_power_domain)((pipe) - PIPE_A + POWER_DOMAIN_PIPE_PANEL_FITTER_A)) #define POWER_DOMAIN_TRANSCODER(tran) \ ((tran) == TRANSCODER_EDP ? POWER_DOMAIN_TRANSCODER_EDP : \ - (tran) + POWER_DOMAIN_TRANSCODER_A) + (enum intel_display_power_domain)((tran) - TRANSCODER_A + POWER_DOMAIN_TRANSCODER_A)) struct intel_power_domain_mask { DECLARE_BITMAP(bits, POWER_DOMAIN_NUM); diff --git a/drivers/gpu/drm/i915/display/intel_display_power_map.c b/drivers/gpu/drm/i915/display/intel_display_power_map.c index 0c8ac1af6db7..e80e1fd611ca 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power_map.c +++ b/drivers/gpu/drm/i915/display/intel_display_power_map.c @@ -3,6 +3,8 @@ * Copyright © 2022 Intel Corporation */ +#include <drm/drm_print.h> + #include "i915_reg.h" #include "intel_display_core.h" #include "intel_display_power_map.h" diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c index 5b60db597329..8ec87ffd87d2 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power_well.c +++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c @@ -549,10 +549,9 @@ static void icl_aux_power_well_enable(struct intel_display *display, struct i915_power_well *power_well) { - struct drm_i915_private *dev_priv = to_i915(display->drm); enum phy phy = icl_aux_pw_to_phy(display, power_well); - if (intel_phy_is_tc(dev_priv, phy)) + if (intel_phy_is_tc(display, phy)) return icl_tc_phy_aux_power_well_enable(display, power_well); else if (display->platform.icelake) return icl_combo_phy_aux_power_well_enable(display, @@ -565,10 +564,9 @@ static void icl_aux_power_well_disable(struct intel_display *display, struct i915_power_well *power_well) { - struct drm_i915_private *dev_priv = to_i915(display->drm); enum phy phy = icl_aux_pw_to_phy(display, power_well); - if (intel_phy_is_tc(dev_priv, phy)) + if (intel_phy_is_tc(display, phy)) return hsw_power_well_disable(display, power_well); else if (display->platform.icelake) return icl_combo_phy_aux_power_well_disable(display, @@ -1829,11 +1827,10 @@ tgl_tc_cold_off_power_well_is_enabled(struct intel_display *display, static void xelpdp_aux_power_well_enable(struct intel_display *display, struct i915_power_well *power_well) { - struct drm_i915_private *dev_priv = to_i915(display->drm); enum aux_ch aux_ch = i915_power_well_instance(power_well)->xelpdp.aux_ch; enum phy phy = icl_aux_pw_to_phy(display, power_well); - if (intel_phy_is_tc(dev_priv, phy)) + if (intel_phy_is_tc(display, phy)) icl_tc_port_assert_ref_held(display, power_well, aux_ch_to_digital_port(display, aux_ch)); diff --git a/drivers/gpu/drm/i915/display/intel_display_reset.c b/drivers/gpu/drm/i915/display/intel_display_reset.c index a690968885bf..1f2798404f2c 100644 --- a/drivers/gpu/drm/i915/display/intel_display_reset.c +++ b/drivers/gpu/drm/i915/display/intel_display_reset.c @@ -14,45 +14,36 @@ #include "intel_hotplug.h" #include "intel_pps.h" -static bool gpu_reset_clobbers_display(struct drm_i915_private *dev_priv) +bool intel_display_reset_test(struct intel_display *display) { - return (INTEL_INFO(dev_priv)->gpu_reset_clobbers_display && - intel_has_gpu_reset(to_gt(dev_priv))); + return display->params.force_reset_modeset_test; } -void intel_display_reset_prepare(struct drm_i915_private *dev_priv) +/* returns true if intel_display_reset_finish() needs to be called */ +bool intel_display_reset_prepare(struct intel_display *display, + modeset_stuck_fn modeset_stuck, void *context) { - struct drm_modeset_acquire_ctx *ctx = &dev_priv->display.restore.reset_ctx; + struct drm_modeset_acquire_ctx *ctx = &display->restore.reset_ctx; struct drm_atomic_state *state; int ret; - if (!HAS_DISPLAY(dev_priv)) - return; + if (!HAS_DISPLAY(display)) + return false; - /* reset doesn't touch the display */ - if (!dev_priv->display.params.force_reset_modeset_test && - !gpu_reset_clobbers_display(dev_priv)) - return; - - /* We have a modeset vs reset deadlock, defensively unbreak it. */ - set_bit(I915_RESET_MODESET, &to_gt(dev_priv)->reset.flags); - smp_mb__after_atomic(); - wake_up_bit(&to_gt(dev_priv)->reset.flags, I915_RESET_MODESET); - - if (atomic_read(&dev_priv->gpu_error.pending_fb_pin)) { - drm_dbg_kms(&dev_priv->drm, + if (atomic_read(&display->restore.pending_fb_pin)) { + drm_dbg_kms(display->drm, "Modeset potentially stuck, unbreaking through wedging\n"); - intel_gt_set_wedged(to_gt(dev_priv)); + modeset_stuck(context); } /* * Need mode_config.mutex so that we don't * trample ongoing ->detect() and whatnot. */ - mutex_lock(&dev_priv->drm.mode_config.mutex); + mutex_lock(&display->drm->mode_config.mutex); drm_modeset_acquire_init(ctx, 0); while (1) { - ret = drm_modeset_lock_all_ctx(&dev_priv->drm, ctx); + ret = drm_modeset_lock_all_ctx(display->drm, ctx); if (ret != -EDEADLK) break; @@ -62,38 +53,36 @@ void intel_display_reset_prepare(struct drm_i915_private *dev_priv) * Disabling the crtcs gracefully seems nicer. Also the * g33 docs say we should at least disable all the planes. */ - state = drm_atomic_helper_duplicate_state(&dev_priv->drm, ctx); + state = drm_atomic_helper_duplicate_state(display->drm, ctx); if (IS_ERR(state)) { ret = PTR_ERR(state); - drm_err(&dev_priv->drm, "Duplicating state failed with %i\n", + drm_err(display->drm, "Duplicating state failed with %i\n", ret); - return; + return true; } - ret = drm_atomic_helper_disable_all(&dev_priv->drm, ctx); + ret = drm_atomic_helper_disable_all(display->drm, ctx); if (ret) { - drm_err(&dev_priv->drm, "Suspending crtc's failed with %i\n", + drm_err(display->drm, "Suspending crtc's failed with %i\n", ret); drm_atomic_state_put(state); - return; + return true; } - dev_priv->display.restore.modeset_state = state; + display->restore.modeset_state = state; state->acquire_ctx = ctx; + + return true; } -void intel_display_reset_finish(struct drm_i915_private *i915) +void intel_display_reset_finish(struct intel_display *display, bool test_only) { - struct intel_display *display = &i915->display; + struct drm_i915_private *i915 = to_i915(display->drm); struct drm_modeset_acquire_ctx *ctx = &display->restore.reset_ctx; struct drm_atomic_state *state; int ret; - if (!HAS_DISPLAY(i915)) - return; - - /* reset doesn't touch the display */ - if (!test_bit(I915_RESET_MODESET, &to_gt(i915)->reset.flags)) + if (!HAS_DISPLAY(display)) return; state = fetch_and_zero(&display->restore.modeset_state); @@ -101,12 +90,12 @@ void intel_display_reset_finish(struct drm_i915_private *i915) goto unlock; /* reset doesn't touch the display */ - if (!gpu_reset_clobbers_display(i915)) { + if (test_only) { /* for testing only restore the display */ ret = drm_atomic_helper_commit_duplicated_state(state, ctx); if (ret) { - drm_WARN_ON(&i915->drm, ret == -EDEADLK); - drm_err(&i915->drm, + drm_WARN_ON(display->drm, ret == -EDEADLK); + drm_err(display->drm, "Restoring old state failed with %i\n", ret); } } else { @@ -122,7 +111,7 @@ void intel_display_reset_finish(struct drm_i915_private *i915) ret = __intel_display_driver_resume(display, state, ctx); if (ret) - drm_err(&i915->drm, + drm_err(display->drm, "Restoring old state failed with %i\n", ret); intel_hpd_poll_disable(i915); @@ -132,7 +121,5 @@ void intel_display_reset_finish(struct drm_i915_private *i915) unlock: drm_modeset_drop_locks(ctx); drm_modeset_acquire_fini(ctx); - mutex_unlock(&i915->drm.mode_config.mutex); - - clear_bit_unlock(I915_RESET_MODESET, &to_gt(i915)->reset.flags); + mutex_unlock(&display->drm->mode_config.mutex); } diff --git a/drivers/gpu/drm/i915/display/intel_display_reset.h b/drivers/gpu/drm/i915/display/intel_display_reset.h index f06d0d35b86b..8b3bda134454 100644 --- a/drivers/gpu/drm/i915/display/intel_display_reset.h +++ b/drivers/gpu/drm/i915/display/intel_display_reset.h @@ -6,9 +6,15 @@ #ifndef __INTEL_RESET_H__ #define __INTEL_RESET_H__ -struct drm_i915_private; +#include <linux/types.h> -void intel_display_reset_prepare(struct drm_i915_private *i915); -void intel_display_reset_finish(struct drm_i915_private *i915); +struct intel_display; + +typedef void modeset_stuck_fn(void *context); + +bool intel_display_reset_test(struct intel_display *display); +bool intel_display_reset_prepare(struct intel_display *display, + modeset_stuck_fn modeset_stuck, void *context); +void intel_display_reset_finish(struct intel_display *display, bool test_only); #endif /* __INTEL_RESET_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_display_rps.c b/drivers/gpu/drm/i915/display/intel_display_rps.c index 918d0327169a..4074a1879828 100644 --- a/drivers/gpu/drm/i915/display/intel_display_rps.c +++ b/drivers/gpu/drm/i915/display/intel_display_rps.c @@ -69,10 +69,12 @@ void intel_display_rps_boost_after_vblank(struct drm_crtc *crtc, add_wait_queue(drm_crtc_vblank_waitqueue(crtc), &wait->wait); } -void intel_display_rps_mark_interactive(struct drm_i915_private *i915, +void intel_display_rps_mark_interactive(struct intel_display *display, struct intel_atomic_state *state, bool interactive) { + struct drm_i915_private *i915 = to_i915(display->drm); + if (state->rps_interactive == interactive) return; diff --git a/drivers/gpu/drm/i915/display/intel_display_rps.h b/drivers/gpu/drm/i915/display/intel_display_rps.h index e19009c2371a..556891edb2dd 100644 --- a/drivers/gpu/drm/i915/display/intel_display_rps.h +++ b/drivers/gpu/drm/i915/display/intel_display_rps.h @@ -10,12 +10,12 @@ struct dma_fence; struct drm_crtc; -struct drm_i915_private; struct intel_atomic_state; +struct intel_display; void intel_display_rps_boost_after_vblank(struct drm_crtc *crtc, struct dma_fence *fence); -void intel_display_rps_mark_interactive(struct drm_i915_private *i915, +void intel_display_rps_mark_interactive(struct intel_display *display, struct intel_atomic_state *state, bool interactive); diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 4440521e3e9e..99a6fd2900b9 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -40,9 +40,9 @@ #include <drm/drm_rect.h> #include <drm/drm_vblank_work.h> #include <drm/intel/i915_hdcp_interface.h> +#include <uapi/drm/i915_drm.h> -#include "i915_vma.h" -#include "i915_vma_types.h" +#include "i915_gtt_view_types.h" #include "intel_bios.h" #include "intel_display.h" #include "intel_display_conversion.h" @@ -534,10 +534,6 @@ struct intel_connector { state of connector->polled in case hotplug storm detection changes it */ u8 polled; - struct drm_dp_mst_port *port; - - struct intel_dp *mst_port; - int force_joined_pipes; struct { @@ -549,6 +545,11 @@ struct intel_connector { u8 dsc_decompression_enabled:1; } dp; + struct { + struct drm_dp_mst_port *port; + struct intel_dp *dp; + } mst; + /* Work struct to schedule a uevent on link train failure */ struct work_struct modeset_retry_work; @@ -692,6 +693,8 @@ struct intel_plane_state { u64 ccval; const char *no_fbc_reason; + + struct drm_rect damage; }; struct intel_initial_plane_config { @@ -1724,7 +1727,6 @@ struct intel_dp { struct intel_pps pps; bool is_mst; - int active_mst_links; enum drm_dp_mst_mode mst_detect; /* connector directly attached - won't be use for modeset in mst world */ @@ -1734,9 +1736,11 @@ struct intel_dp { struct drm_dp_tunnel *tunnel; bool tunnel_suspended:1; - /* mst connector list */ - struct intel_dp_mst_encoder *mst_encoders[I915_MAX_PIPES]; - struct drm_dp_mst_topology_mgr mst_mgr; + struct { + struct intel_dp_mst_encoder *stream_encoders[I915_MAX_PIPES]; + struct drm_dp_mst_topology_mgr mgr; + int active_links; + } mst; u32 (*get_aux_clock_divider)(struct intel_dp *dp, int index); /* @@ -1847,16 +1851,18 @@ struct intel_digital_port { struct intel_tc_port *tc; - /* protects num_hdcp_streams reference count, hdcp_port_data and hdcp_auth_status */ - struct mutex hdcp_mutex; - /* the number of pipes using HDCP signalling out of this port */ - unsigned int num_hdcp_streams; - /* port HDCP auth status */ - bool hdcp_auth_status; - /* HDCP port data need to pass to security f/w */ - struct hdcp_port_data hdcp_port_data; - /* Whether the MST topology supports HDCP Type 1 Content */ - bool hdcp_mst_type1_capable; + struct { + /* protects num_streams reference count, port_data and auth_status */ + struct mutex mutex; + /* the number of pipes using HDCP signalling out of this port */ + unsigned int num_streams; + /* port HDCP auth status */ + bool auth_status; + /* HDCP port data need to pass to security f/w */ + struct hdcp_port_data port_data; + /* Whether the MST topology supports HDCP Type 1 Content */ + bool mst_type1_capable; + } hdcp; void (*write_infoframe)(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, @@ -1955,8 +1961,8 @@ static inline struct intel_dp *enc_to_intel_dp(struct intel_encoder *encoder) static inline struct intel_dp *intel_attached_dp(struct intel_connector *connector) { - if (connector->mst_port) - return connector->mst_port; + if (connector->mst.dp) + return connector->mst.dp; else return enc_to_intel_dp(intel_attached_encoder(connector)); } @@ -2100,11 +2106,6 @@ intel_crtc_needs_color_update(const struct intel_crtc_state *crtc_state) intel_crtc_needs_modeset(crtc_state); } -static inline u32 intel_plane_ggtt_offset(const struct intel_plane_state *plane_state) -{ - return i915_ggtt_offset(plane_state->ggtt_vma); -} - static inline struct intel_frontbuffer * to_intel_frontbuffer(struct drm_framebuffer *fb) { diff --git a/drivers/gpu/drm/i915/display/intel_dkl_phy.c b/drivers/gpu/drm/i915/display/intel_dkl_phy.c index 0920f78f182e..0813fb9b5823 100644 --- a/drivers/gpu/drm/i915/display/intel_dkl_phy.c +++ b/drivers/gpu/drm/i915/display/intel_dkl_phy.c @@ -3,7 +3,7 @@ * Copyright © 2022 Intel Corporation */ -#include "i915_drv.h" +#include <drm/drm_device.h> #include "intel_de.h" #include "intel_display.h" @@ -12,11 +12,11 @@ /** * intel_dkl_phy_init - initialize Dekel PHY - * @i915: i915 device instance + * @display: display device instance */ -void intel_dkl_phy_init(struct drm_i915_private *i915) +void intel_dkl_phy_init(struct intel_display *display) { - spin_lock_init(&i915->display.dkl.phy_lock); + spin_lock_init(&display->dkl.phy_lock); } static void diff --git a/drivers/gpu/drm/i915/display/intel_dkl_phy.h b/drivers/gpu/drm/i915/display/intel_dkl_phy.h index 1d96e6be657c..ccb445c0022b 100644 --- a/drivers/gpu/drm/i915/display/intel_dkl_phy.h +++ b/drivers/gpu/drm/i915/display/intel_dkl_phy.h @@ -10,10 +10,9 @@ #include "intel_dkl_phy_regs.h" -struct drm_i915_private; struct intel_display; -void intel_dkl_phy_init(struct drm_i915_private *i915); +void intel_dkl_phy_init(struct intel_display *display); u32 intel_dkl_phy_read(struct intel_display *display, struct intel_dkl_phy_reg reg); void diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 03ca2e02ab02..a236b5fc7a3d 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1376,7 +1376,7 @@ bool intel_dp_has_dsc(const struct intel_connector *connector) if (!HAS_DSC(display)) return false; - if (connector->mst_port && !HAS_DSC_MST(display)) + if (connector->mst.dp && !HAS_DSC_MST(display)) return false; if (connector->base.connector_type == DRM_MODE_CONNECTOR_eDP && @@ -2912,7 +2912,7 @@ static bool can_enable_drrs(struct intel_connector *connector, const struct intel_crtc_state *pipe_config, const struct drm_display_mode *downclock_mode) { - struct drm_i915_private *i915 = to_i915(connector->base.dev); + struct intel_display *display = to_intel_display(connector); if (pipe_config->vrr.enable) return false; @@ -2930,7 +2930,7 @@ static bool can_enable_drrs(struct intel_connector *connector, if (pipe_config->has_pch_encoder) return false; - if (!intel_cpu_transcoder_has_drrs(i915, pipe_config->cpu_transcoder)) + if (!intel_cpu_transcoder_has_drrs(display, pipe_config->cpu_transcoder)) return false; return downclock_mode && @@ -2943,7 +2943,6 @@ intel_dp_drrs_compute_config(struct intel_connector *connector, int link_bpp_x16) { struct intel_display *display = to_intel_display(connector); - struct drm_i915_private *i915 = to_i915(connector->base.dev); const struct drm_display_mode *downclock_mode = intel_panel_downclock_mode(connector, &pipe_config->hw.adjusted_mode); int pixel_clock; @@ -2956,7 +2955,7 @@ intel_dp_drrs_compute_config(struct intel_connector *connector, pipe_config->update_m_n = true; if (!can_enable_drrs(connector, pipe_config, downclock_mode)) { - if (intel_cpu_transcoder_has_m2_n2(i915, pipe_config->cpu_transcoder)) + if (intel_cpu_transcoder_has_m2_n2(display, pipe_config->cpu_transcoder)) intel_zero_m_n(&pipe_config->dp_m2_n2); return; } @@ -3081,7 +3080,7 @@ intel_dp_queue_modeset_retry_for_link(struct intel_atomic_state *state, if (!conn_state->base.crtc) continue; - if (connector->mst_port == intel_dp) + if (connector->mst.dp == intel_dp) intel_connector_queue_modeset_retry_work(connector); } } @@ -3131,7 +3130,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, if ((intel_dp_is_edp(intel_dp) && fixed_mode) || pipe_config->output_format == INTEL_OUTPUT_FORMAT_YCBCR420) { - ret = intel_panel_fitting(pipe_config, conn_state); + ret = intel_pfit_compute_config(pipe_config, conn_state); if (ret) return ret; } @@ -3303,8 +3302,8 @@ intel_dp_sink_set_dsc_passthrough(const struct intel_connector *connector, bool enable) { struct intel_display *display = to_intel_display(connector); - struct drm_dp_aux *aux = connector->port ? - connector->port->passthrough_aux : NULL; + struct drm_dp_aux *aux = connector->mst.port ? + connector->mst.port->passthrough_aux : NULL; if (!aux) return; @@ -3331,7 +3330,7 @@ static int intel_dp_dsc_aux_ref_count(struct intel_atomic_state *state, * On SST the decompression AUX device won't be shared, each connector * uses for this its own AUX targeting the sink device. */ - if (!connector->mst_port) + if (!connector->mst.dp) return connector->dp.dsc_decompression_enabled ? 1 : 0; for_each_oldnew_connector_in_state(&state->base, _connector_iter, @@ -3339,7 +3338,7 @@ static int intel_dp_dsc_aux_ref_count(struct intel_atomic_state *state, const struct intel_connector * connector_iter = to_intel_connector(_connector_iter); - if (connector_iter->mst_port != connector->mst_port) + if (connector_iter->mst.dp != connector->mst.dp) continue; if (!connector_iter->dp.dsc_decompression_enabled) @@ -4397,7 +4396,7 @@ intel_dp_mst_configure(struct intel_dp *intel_dp) if (intel_dp->is_mst) intel_dp_mst_prepare_probe(intel_dp); - drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst_mgr, intel_dp->is_mst); + drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst.mgr, intel_dp->is_mst); /* Avoid stale info on the next detect cycle. */ intel_dp->mst_detect = DRM_DP_SST; @@ -4413,9 +4412,9 @@ intel_dp_mst_disconnect(struct intel_dp *intel_dp) drm_dbg_kms(display->drm, "MST device may have disappeared %d vs %d\n", - intel_dp->is_mst, intel_dp->mst_mgr.mst_state); + intel_dp->is_mst, intel_dp->mst.mgr.mst_state); intel_dp->is_mst = false; - drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst_mgr, intel_dp->is_mst); + drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst.mgr, intel_dp->is_mst); } static bool @@ -4921,7 +4920,7 @@ intel_dp_mst_hpd_irq(struct intel_dp *intel_dp, u8 *esi, u8 *ack) { bool handled = false; - drm_dp_mst_hpd_irq_handle_event(&intel_dp->mst_mgr, esi, ack, &handled); + drm_dp_mst_hpd_irq_handle_event(&intel_dp->mst.mgr, esi, ack, &handled); if (esi[1] & DP_CP_IRQ) { intel_hdcp_handle_cp_irq(intel_dp->attached_connector); @@ -4970,7 +4969,7 @@ intel_dp_check_mst_status(struct intel_dp *intel_dp) bool link_ok = true; bool reprobe_needed = false; - drm_WARN_ON_ONCE(display->drm, intel_dp->active_mst_links < 0); + drm_WARN_ON_ONCE(display->drm, intel_dp->mst.active_links < 0); for (;;) { u8 esi[4] = {}; @@ -4986,7 +4985,7 @@ intel_dp_check_mst_status(struct intel_dp *intel_dp) drm_dbg_kms(display->drm, "DPRX ESI: %4ph\n", esi); - if (intel_dp->active_mst_links > 0 && link_ok && + if (intel_dp->mst.active_links > 0 && link_ok && esi[3] & LINK_STATUS_CHANGED) { if (!intel_dp_mst_link_status(intel_dp)) link_ok = false; @@ -5009,7 +5008,7 @@ intel_dp_check_mst_status(struct intel_dp *intel_dp) drm_dbg_kms(display->drm, "Failed to ack ESI\n"); if (ack[1] & (DP_DOWN_REP_MSG_RDY | DP_UP_REQ_MSG_RDY)) - drm_dp_mst_hpd_irq_send_new_request(&intel_dp->mst_mgr); + drm_dp_mst_hpd_irq_send_new_request(&intel_dp->mst.mgr); } if (!link_ok || intel_dp->link.force_retrain) @@ -5108,7 +5107,7 @@ bool intel_dp_has_connector(struct intel_dp *intel_dp, /* MST */ for_each_pipe(display, pipe) { - encoder = &intel_dp->mst_encoders[pipe]->base; + encoder = &intel_dp->mst.stream_encoders[pipe]->base; if (conn_state->best_encoder == &encoder->base) return true; } @@ -5194,7 +5193,6 @@ static int intel_dp_retrain_link(struct intel_encoder *encoder, struct drm_modeset_acquire_ctx *ctx) { struct intel_display *display = to_intel_display(encoder); - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_dp *intel_dp = enc_to_intel_dp(encoder); u8 pipe_mask; int ret; @@ -5225,7 +5223,7 @@ static int intel_dp_retrain_link(struct intel_encoder *encoder, encoder->base.base.id, encoder->base.name, str_yes_no(intel_dp->link.force_retrain)); - ret = intel_modeset_commit_pipes(dev_priv, pipe_mask, ctx); + ret = intel_modeset_commit_pipes(display, pipe_mask, ctx); if (ret == -EDEADLK) return ret; @@ -6067,7 +6065,7 @@ static int intel_dp_connector_atomic_check(struct drm_connector *conn, return ret; if (intel_dp_mst_source_support(intel_dp)) { - ret = drm_dp_mst_root_conn_atomic_check(conn_state, &intel_dp->mst_mgr); + ret = drm_dp_mst_root_conn_atomic_check(conn_state, &intel_dp->mst.mgr); if (ret) return ret; } @@ -6605,7 +6603,7 @@ void intel_dp_mst_suspend(struct intel_display *display) continue; if (intel_dp->is_mst) - drm_dp_mst_topology_mgr_suspend(&intel_dp->mst_mgr); + drm_dp_mst_topology_mgr_suspend(&intel_dp->mst.mgr); } } @@ -6628,12 +6626,10 @@ void intel_dp_mst_resume(struct intel_display *display) if (!intel_dp_mst_source_support(intel_dp)) continue; - ret = drm_dp_mst_topology_mgr_resume(&intel_dp->mst_mgr, - true); + ret = drm_dp_mst_topology_mgr_resume(&intel_dp->mst.mgr, true); if (ret) { intel_dp->is_mst = false; - drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst_mgr, - false); + drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst.mgr, false); } } } diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index f53c8355d5be..8173de8aec63 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -34,6 +34,8 @@ * for some reason. */ +#include <drm/drm_print.h> + #include "i915_utils.h" #include "intel_backlight.h" #include "intel_display_core.h" diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c index 00c493cc8a4b..cc312596fb77 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c @@ -705,10 +705,10 @@ int intel_dp_hdcp_get_remote_capability(struct intel_connector *connector, *hdcp_capable = false; *hdcp2_capable = false; - if (!connector->mst_port) + if (!connector->mst.dp) return -EINVAL; - aux = &connector->port->aux; + aux = &connector->mst.port->aux; ret = _intel_dp_hdcp2_get_capability(aux, hdcp2_capable); if (ret) drm_dbg_kms(display->drm, @@ -799,7 +799,7 @@ intel_dp_mst_hdcp2_stream_encryption(struct intel_connector *connector, { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct intel_hdcp *hdcp = &connector->hdcp; enum transcoder cpu_transcoder = hdcp->stream_transcoder; enum pipe pipe = (enum pipe)cpu_transcoder; @@ -883,7 +883,7 @@ int intel_dp_hdcp_init(struct intel_digital_port *dig_port, if (!is_hdcp_supported(display, port)) return 0; - if (intel_connector->mst_port) + if (intel_connector->mst.dp) return intel_hdcp_init(intel_connector, dig_port, &intel_dp_mst_hdcp_shim); else if (!intel_dp_is_edp(intel_dp)) diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 66fcd90f0028..2966f5b39392 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -24,6 +24,7 @@ #include <linux/debugfs.h> #include <drm/display/drm_dp_helper.h> +#include <drm/drm_print.h> #include "i915_utils.h" #include "intel_display_core.h" diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 167e4a70ab12..02f95108c637 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -49,6 +49,7 @@ #include "intel_hdcp.h" #include "intel_hotplug.h" #include "intel_link_bw.h" +#include "intel_pfit.h" #include "intel_psr.h" #include "intel_vdsc.h" #include "skl_scaler.h" @@ -252,7 +253,7 @@ int intel_dp_mtp_tu_compute_config(struct intel_dp *intel_dp, fxp_q4_to_frac(bpp_step_x16))); if (is_mst) { - mst_state = drm_atomic_get_mst_topology_state(state, &intel_dp->mst_mgr); + mst_state = drm_atomic_get_mst_topology_state(state, &intel_dp->mst.mgr); if (IS_ERR(mst_state)) return PTR_ERR(mst_state); @@ -354,8 +355,8 @@ int intel_dp_mtp_tu_compute_config(struct intel_dp *intel_dp, drm_WARN_ON(display->drm, remote_tu < crtc_state->dp_m_n.tu); crtc_state->dp_m_n.tu = remote_tu; - slots = drm_dp_atomic_find_time_slots(state, &intel_dp->mst_mgr, - connector->port, + slots = drm_dp_atomic_find_time_slots(state, &intel_dp->mst.mgr, + connector->mst.port, dfixed_trunc(pbn)); } else { /* Same as above for remote_tu */ @@ -478,7 +479,7 @@ static int mst_stream_update_slots(struct intel_dp *intel_dp, struct drm_connector_state *conn_state) { struct intel_display *display = to_intel_display(intel_dp); - struct drm_dp_mst_topology_mgr *mgr = &intel_dp->mst_mgr; + struct drm_dp_mst_topology_mgr *mgr = &intel_dp->mst.mgr; struct drm_dp_mst_topology_state *topology_state; u8 link_coding_cap = intel_dp_is_uhbr(crtc_state) ? DP_CAP_ANSI_128B132B : DP_CAP_ANSI_8B10B; @@ -508,8 +509,8 @@ hblank_expansion_quirk_needs_dsc(const struct intel_connector *connector, { const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; - bool is_uhbr_sink = connector->mst_port && - drm_dp_128b132b_supported(connector->mst_port->dpcd); + bool is_uhbr_sink = connector->mst.dp && + drm_dp_128b132b_supported(connector->mst.dp->dpcd); int hblank_limit = is_uhbr_sink ? 500 : 300; if (!connector->dp.dsc_hblank_expansion_quirk) @@ -740,7 +741,7 @@ intel_dp_mst_transcoder_mask(struct intel_atomic_state *state, const struct intel_crtc_state *crtc_state; struct intel_crtc *crtc; - if (connector->mst_port != mst_port || !conn_state->base.crtc) + if (connector->mst.dp != mst_port || !conn_state->base.crtc) continue; crtc = to_intel_crtc(conn_state->base.crtc); @@ -768,12 +769,12 @@ static u8 get_pipes_downstream_of_mst_port(struct intel_atomic_state *state, if (!conn_state->base.crtc) continue; - if (&connector->mst_port->mst_mgr != mst_mgr) + if (&connector->mst.dp->mst.mgr != mst_mgr) continue; - if (connector->port != parent_port && + if (connector->mst.port != parent_port && !drm_dp_mst_port_downstream_of_parent(mst_mgr, - connector->port, + connector->mst.port, parent_port)) continue; @@ -924,7 +925,7 @@ mst_connector_atomic_topology_check(struct intel_connector *connector, struct intel_crtc_state *crtc_state; struct intel_crtc *crtc; - if (connector_iter->mst_port != connector->mst_port || + if (connector_iter->mst.dp != connector->mst.dp || connector_iter == connector) continue; @@ -973,15 +974,15 @@ mst_connector_atomic_check(struct drm_connector *_connector, if (intel_connector_needs_modeset(state, &connector->base)) { ret = intel_dp_tunnel_atomic_check_state(state, - connector->mst_port, + connector->mst.dp, connector); if (ret) return ret; } return drm_dp_atomic_release_time_slots(&state->base, - &connector->mst_port->mst_mgr, - connector->port); + &connector->mst.dp->mst.mgr, + connector->mst.port); } static void mst_stream_disable(struct intel_atomic_state *state, @@ -997,9 +998,9 @@ static void mst_stream_disable(struct intel_atomic_state *state, enum transcoder trans = old_crtc_state->cpu_transcoder; drm_dbg_kms(display->drm, "active links %d\n", - intel_dp->active_mst_links); + intel_dp->mst.active_links); - if (intel_dp->active_mst_links == 1) + if (intel_dp->mst.active_links == 1) intel_dp->link_trained = false; intel_hdcp_disable(intel_mst->connector); @@ -1022,19 +1023,19 @@ static void mst_stream_post_disable(struct intel_atomic_state *state, struct intel_connector *connector = to_intel_connector(old_conn_state->connector); struct drm_dp_mst_topology_state *old_mst_state = - drm_atomic_get_old_mst_topology_state(&state->base, &intel_dp->mst_mgr); + drm_atomic_get_old_mst_topology_state(&state->base, &intel_dp->mst.mgr); struct drm_dp_mst_topology_state *new_mst_state = - drm_atomic_get_new_mst_topology_state(&state->base, &intel_dp->mst_mgr); + drm_atomic_get_new_mst_topology_state(&state->base, &intel_dp->mst.mgr); const struct drm_dp_mst_atomic_payload *old_payload = - drm_atomic_get_mst_payload_state(old_mst_state, connector->port); + drm_atomic_get_mst_payload_state(old_mst_state, connector->mst.port); struct drm_dp_mst_atomic_payload *new_payload = - drm_atomic_get_mst_payload_state(new_mst_state, connector->port); + drm_atomic_get_mst_payload_state(new_mst_state, connector->mst.port); struct intel_crtc *pipe_crtc; bool last_mst_stream; int i; - intel_dp->active_mst_links--; - last_mst_stream = intel_dp->active_mst_links == 0; + intel_dp->mst.active_links--; + last_mst_stream = intel_dp->mst.active_links == 0; drm_WARN_ON(display->drm, DISPLAY_VER(display) >= 12 && last_mst_stream && !intel_dp_mst_is_master_trans(old_crtc_state)); @@ -1047,7 +1048,7 @@ static void mst_stream_post_disable(struct intel_atomic_state *state, intel_disable_transcoder(old_crtc_state); - drm_dp_remove_payload_part1(&intel_dp->mst_mgr, new_mst_state, new_payload); + drm_dp_remove_payload_part1(&intel_dp->mst.mgr, new_mst_state, new_payload); intel_ddi_clear_act_sent(encoder, old_crtc_state); @@ -1056,9 +1057,9 @@ static void mst_stream_post_disable(struct intel_atomic_state *state, TRANS_DDI_DP_VC_PAYLOAD_ALLOC, 0); intel_ddi_wait_for_act_sent(encoder, old_crtc_state); - drm_dp_check_act_status(&intel_dp->mst_mgr); + drm_dp_check_act_status(&intel_dp->mst.mgr); - drm_dp_remove_payload_part2(&intel_dp->mst_mgr, new_mst_state, + drm_dp_remove_payload_part2(&intel_dp->mst.mgr, new_mst_state, old_payload, new_payload); intel_ddi_disable_transcoder_func(old_crtc_state); @@ -1079,7 +1080,7 @@ static void mst_stream_post_disable(struct intel_atomic_state *state, * Power down mst path before disabling the port, otherwise we end * up getting interrupts from the sink upon detecting link loss. */ - drm_dp_send_power_updown_phy(&intel_dp->mst_mgr, connector->port, + drm_dp_send_power_updown_phy(&intel_dp->mst.mgr, connector->mst.port, false); /* @@ -1104,7 +1105,7 @@ static void mst_stream_post_disable(struct intel_atomic_state *state, old_crtc_state, NULL); drm_dbg_kms(display->drm, "active links %d\n", - intel_dp->active_mst_links); + intel_dp->mst.active_links); } static void mst_stream_post_pll_disable(struct intel_atomic_state *state, @@ -1115,7 +1116,7 @@ static void mst_stream_post_pll_disable(struct intel_atomic_state *state, struct intel_encoder *primary_encoder = to_primary_encoder(encoder); struct intel_dp *intel_dp = to_primary_dp(encoder); - if (intel_dp->active_mst_links == 0 && + if (intel_dp->mst.active_links == 0 && primary_encoder->post_pll_disable) primary_encoder->post_pll_disable(state, primary_encoder, old_crtc_state, old_conn_state); } @@ -1128,7 +1129,7 @@ static void mst_stream_pre_pll_enable(struct intel_atomic_state *state, struct intel_encoder *primary_encoder = to_primary_encoder(encoder); struct intel_dp *intel_dp = to_primary_dp(encoder); - if (intel_dp->active_mst_links == 0) + if (intel_dp->mst.active_links == 0) primary_encoder->pre_pll_enable(state, primary_encoder, pipe_config, NULL); else @@ -1161,7 +1162,7 @@ static void intel_mst_reprobe_topology(struct intel_dp *intel_dp, crtc_state->port_clock, crtc_state->lane_count)) return; - drm_dp_mst_topology_queue_probe(&intel_dp->mst_mgr); + drm_dp_mst_topology_queue_probe(&intel_dp->mst.mgr); intel_mst_set_probed_link_params(intel_dp, crtc_state->port_clock, crtc_state->lane_count); @@ -1179,7 +1180,7 @@ static void mst_stream_pre_enable(struct intel_atomic_state *state, struct intel_connector *connector = to_intel_connector(conn_state->connector); struct drm_dp_mst_topology_state *mst_state = - drm_atomic_get_new_mst_topology_state(&state->base, &intel_dp->mst_mgr); + drm_atomic_get_new_mst_topology_state(&state->base, &intel_dp->mst.mgr); int ret; bool first_mst_stream; @@ -1188,17 +1189,17 @@ static void mst_stream_pre_enable(struct intel_atomic_state *state, */ connector->encoder = encoder; intel_mst->connector = connector; - first_mst_stream = intel_dp->active_mst_links == 0; + first_mst_stream = intel_dp->mst.active_links == 0; drm_WARN_ON(display->drm, DISPLAY_VER(display) >= 12 && first_mst_stream && !intel_dp_mst_is_master_trans(pipe_config)); drm_dbg_kms(display->drm, "active links %d\n", - intel_dp->active_mst_links); + intel_dp->mst.active_links); if (first_mst_stream) intel_dp_set_power(intel_dp, DP_SET_POWER_D0); - drm_dp_send_power_updown_phy(&intel_dp->mst_mgr, connector->port, true); + drm_dp_send_power_updown_phy(&intel_dp->mst.mgr, connector->mst.port, true); intel_dp_sink_enable_decompression(state, connector, pipe_config); @@ -1209,10 +1210,10 @@ static void mst_stream_pre_enable(struct intel_atomic_state *state, intel_mst_reprobe_topology(intel_dp, pipe_config); } - intel_dp->active_mst_links++; + intel_dp->mst.active_links++; - ret = drm_dp_add_payload_part1(&intel_dp->mst_mgr, mst_state, - drm_atomic_get_mst_payload_state(mst_state, connector->port)); + ret = drm_dp_add_payload_part1(&intel_dp->mst.mgr, mst_state, + drm_atomic_get_mst_payload_state(mst_state, connector->mst.port)); if (ret < 0) intel_dp_queue_modeset_retry_for_link(state, primary_encoder, pipe_config); @@ -1276,9 +1277,9 @@ static void mst_stream_enable(struct intel_atomic_state *state, struct intel_dp *intel_dp = to_primary_dp(encoder); struct intel_connector *connector = to_intel_connector(conn_state->connector); struct drm_dp_mst_topology_state *mst_state = - drm_atomic_get_new_mst_topology_state(&state->base, &intel_dp->mst_mgr); + drm_atomic_get_new_mst_topology_state(&state->base, &intel_dp->mst.mgr); enum transcoder trans = pipe_config->cpu_transcoder; - bool first_mst_stream = intel_dp->active_mst_links == 1; + bool first_mst_stream = intel_dp->mst.active_links == 1; struct intel_crtc *pipe_crtc; int ret, i, min_hblank; @@ -1328,17 +1329,17 @@ static void mst_stream_enable(struct intel_atomic_state *state, TRANS_DDI_DP_VC_PAYLOAD_ALLOC); drm_dbg_kms(display->drm, "active links %d\n", - intel_dp->active_mst_links); + intel_dp->mst.active_links); intel_ddi_wait_for_act_sent(encoder, pipe_config); - drm_dp_check_act_status(&intel_dp->mst_mgr); + drm_dp_check_act_status(&intel_dp->mst.mgr); if (first_mst_stream) intel_ddi_wait_for_fec_status(encoder, pipe_config, true); - ret = drm_dp_add_payload_part2(&intel_dp->mst_mgr, + ret = drm_dp_add_payload_part2(&intel_dp->mst.mgr, drm_atomic_get_mst_payload_state(mst_state, - connector->port)); + connector->mst.port)); if (ret < 0) intel_dp_queue_modeset_retry_for_link(state, primary_encoder, pipe_config); @@ -1391,7 +1392,7 @@ static int mst_connector_get_ddc_modes(struct drm_connector *_connector) { struct intel_connector *connector = to_intel_connector(_connector); struct intel_display *display = to_intel_display(connector); - struct intel_dp *intel_dp = connector->mst_port; + struct intel_dp *intel_dp = connector->mst.dp; const struct drm_edid *drm_edid; int ret; @@ -1401,7 +1402,7 @@ static int mst_connector_get_ddc_modes(struct drm_connector *_connector) if (!intel_display_driver_check_access(display)) return drm_edid_connector_add_modes(&connector->base); - drm_edid = drm_dp_mst_edid_read(&connector->base, &intel_dp->mst_mgr, connector->port); + drm_edid = drm_dp_mst_edid_read(&connector->base, &intel_dp->mst.mgr, connector->mst.port); ret = intel_connector_update_modes(&connector->base, drm_edid); @@ -1416,13 +1417,13 @@ mst_connector_late_register(struct drm_connector *_connector) struct intel_connector *connector = to_intel_connector(_connector); int ret; - ret = drm_dp_mst_connector_late_register(&connector->base, connector->port); + ret = drm_dp_mst_connector_late_register(&connector->base, connector->mst.port); if (ret < 0) return ret; ret = intel_connector_register(&connector->base); if (ret < 0) - drm_dp_mst_connector_early_unregister(&connector->base, connector->port); + drm_dp_mst_connector_early_unregister(&connector->base, connector->mst.port); return ret; } @@ -1433,7 +1434,7 @@ mst_connector_early_unregister(struct drm_connector *_connector) struct intel_connector *connector = to_intel_connector(_connector); intel_connector_unregister(&connector->base); - drm_dp_mst_connector_early_unregister(&connector->base, connector->port); + drm_dp_mst_connector_early_unregister(&connector->base, connector->mst.port); } static const struct drm_connector_funcs mst_connector_funcs = { @@ -1462,9 +1463,9 @@ mst_connector_mode_valid_ctx(struct drm_connector *_connector, { struct intel_connector *connector = to_intel_connector(_connector); struct intel_display *display = to_intel_display(connector); - struct intel_dp *intel_dp = connector->mst_port; - struct drm_dp_mst_topology_mgr *mgr = &intel_dp->mst_mgr; - struct drm_dp_mst_port *port = connector->port; + struct intel_dp *intel_dp = connector->mst.dp; + struct drm_dp_mst_topology_mgr *mgr = &intel_dp->mst.mgr; + struct drm_dp_mst_port *port = connector->mst.port; const int min_bpp = 18; int max_dotclk = display->cdclk.max_dotclk_freq; int max_rate, mode_rate, max_lanes, max_link_clock; @@ -1575,10 +1576,10 @@ mst_connector_atomic_best_encoder(struct drm_connector *_connector, struct intel_connector *connector = to_intel_connector(_connector); struct drm_connector_state *connector_state = drm_atomic_get_new_connector_state(state, &connector->base); - struct intel_dp *intel_dp = connector->mst_port; + struct intel_dp *intel_dp = connector->mst.dp; struct intel_crtc *crtc = to_intel_crtc(connector_state->crtc); - return &intel_dp->mst_encoders[crtc->pipe]->base.base; + return &intel_dp->mst.stream_encoders[crtc->pipe]->base.base; } static int @@ -1587,7 +1588,7 @@ mst_connector_detect_ctx(struct drm_connector *_connector, { struct intel_connector *connector = to_intel_connector(_connector); struct intel_display *display = to_intel_display(connector); - struct intel_dp *intel_dp = connector->mst_port; + struct intel_dp *intel_dp = connector->mst.dp; if (!intel_display_device_enabled(display)) return connector_status_disconnected; @@ -1600,8 +1601,8 @@ mst_connector_detect_ctx(struct drm_connector *_connector, intel_dp_flush_connector_commits(connector); - return drm_dp_mst_detect_port(&connector->base, ctx, &intel_dp->mst_mgr, - connector->port); + return drm_dp_mst_detect_port(&connector->base, ctx, &intel_dp->mst.mgr, + connector->mst.port); } static const struct drm_connector_helper_funcs mst_connector_helper_funcs = { @@ -1692,10 +1693,10 @@ static bool detect_dsc_hblank_expansion_quirk(const struct intel_connector *conn * A logical port's OUI (at least for affected sinks) is all 0, so * instead of that the parent port's OUI is used for identification. */ - if (drm_dp_mst_port_is_logical(connector->port)) { - aux = drm_dp_mst_aux_for_parent(connector->port); + if (drm_dp_mst_port_is_logical(connector->mst.port)) { + aux = drm_dp_mst_aux_for_parent(connector->mst.port); if (!aux) - aux = &connector->mst_port->aux; + aux = &connector->mst.dp->aux; } if (drm_dp_read_dpcd_caps(aux, dpcd) < 0) @@ -1730,7 +1731,7 @@ mst_topology_add_connector(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, const char *pathprop) { - struct intel_dp *intel_dp = container_of(mgr, struct intel_dp, mst_mgr); + struct intel_dp *intel_dp = container_of(mgr, struct intel_dp, mst.mgr); struct intel_display *display = to_intel_display(intel_dp); struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct intel_connector *connector; @@ -1743,8 +1744,8 @@ mst_topology_add_connector(struct drm_dp_mst_topology_mgr *mgr, connector->get_hw_state = mst_connector_get_hw_state; connector->sync_state = intel_dp_connector_sync_state; - connector->mst_port = intel_dp; - connector->port = port; + connector->mst.dp = intel_dp; + connector->mst.port = port; drm_dp_mst_get_port_malloc(port); ret = drm_connector_dynamic_init(display->drm, &connector->base, &mst_connector_funcs, @@ -1761,7 +1762,7 @@ mst_topology_add_connector(struct drm_dp_mst_topology_mgr *mgr, for_each_pipe(display, pipe) { struct drm_encoder *enc = - &intel_dp->mst_encoders[pipe]->base.base; + &intel_dp->mst.stream_encoders[pipe]->base.base; ret = drm_connector_attach_encoder(&connector->base, enc); if (ret) @@ -1791,7 +1792,7 @@ err_put_port: static void mst_topology_poll_hpd_irq(struct drm_dp_mst_topology_mgr *mgr) { - struct intel_dp *intel_dp = container_of(mgr, struct intel_dp, mst_mgr); + struct intel_dp *intel_dp = container_of(mgr, struct intel_dp, mst.mgr); intel_hpd_trigger_irq(dp_to_dig_port(intel_dp)); } @@ -1864,14 +1865,14 @@ mst_stream_encoders_create(struct intel_digital_port *dig_port) enum pipe pipe; for_each_pipe(display, pipe) - intel_dp->mst_encoders[pipe] = mst_stream_encoder_create(dig_port, pipe); + intel_dp->mst.stream_encoders[pipe] = mst_stream_encoder_create(dig_port, pipe); return true; } int intel_dp_mst_encoder_active_links(struct intel_digital_port *dig_port) { - return dig_port->dp.active_mst_links; + return dig_port->dp.mst.active_links; } int @@ -1891,14 +1892,15 @@ intel_dp_mst_encoder_init(struct intel_digital_port *dig_port, int conn_base_id) if (DISPLAY_VER(display) < 11 && port == PORT_E) return 0; - intel_dp->mst_mgr.cbs = &mst_topology_cbs; + intel_dp->mst.mgr.cbs = &mst_topology_cbs; /* create encoders */ mst_stream_encoders_create(dig_port); - ret = drm_dp_mst_topology_mgr_init(&intel_dp->mst_mgr, display->drm, - &intel_dp->aux, 16, 3, conn_base_id); + ret = drm_dp_mst_topology_mgr_init(&intel_dp->mst.mgr, display->drm, + &intel_dp->aux, 16, + INTEL_NUM_PIPES(display), conn_base_id); if (ret) { - intel_dp->mst_mgr.cbs = NULL; + intel_dp->mst.mgr.cbs = NULL; return ret; } @@ -1907,7 +1909,7 @@ intel_dp_mst_encoder_init(struct intel_digital_port *dig_port, int conn_base_id) bool intel_dp_mst_source_support(struct intel_dp *intel_dp) { - return intel_dp->mst_mgr.cbs; + return intel_dp->mst.mgr.cbs; } void @@ -1918,10 +1920,10 @@ intel_dp_mst_encoder_cleanup(struct intel_digital_port *dig_port) if (!intel_dp_mst_source_support(intel_dp)) return; - drm_dp_mst_topology_mgr_destroy(&intel_dp->mst_mgr); + drm_dp_mst_topology_mgr_destroy(&intel_dp->mst.mgr); /* encoders will get killed by normal cleanup */ - intel_dp->mst_mgr.cbs = NULL; + intel_dp->mst.mgr.cbs = NULL; } bool intel_dp_mst_is_master_trans(const struct intel_crtc_state *crtc_state) @@ -1952,11 +1954,11 @@ intel_dp_mst_add_topology_state_for_connector(struct intel_atomic_state *state, { struct drm_dp_mst_topology_state *mst_state; - if (!connector->mst_port) + if (!connector->mst.dp) return 0; mst_state = drm_atomic_get_mst_topology_state(&state->base, - &connector->mst_port->mst_mgr); + &connector->mst.dp->mst.mgr); if (IS_ERR(mst_state)) return PTR_ERR(mst_state); @@ -2054,7 +2056,7 @@ bool intel_dp_mst_crtc_needs_modeset(struct intel_atomic_state *state, const struct intel_crtc_state *old_crtc_state; struct intel_crtc *crtc_iter; - if (connector->mst_port != crtc_connector->mst_port || + if (connector->mst.dp != crtc_connector->mst.dp || !conn_state->crtc) continue; @@ -2077,7 +2079,7 @@ bool intel_dp_mst_crtc_needs_modeset(struct intel_atomic_state *state, * case. */ if (connector->dp.dsc_decompression_aux == - &connector->mst_port->aux) + &connector->mst.dp->aux) return true; } @@ -2138,7 +2140,7 @@ bool intel_dp_mst_verify_dpcd_state(struct intel_dp *intel_dp) if (!intel_dp->is_mst) return true; - ret = drm_dp_dpcd_readb(intel_dp->mst_mgr.aux, DP_MSTM_CTRL, &val); + ret = drm_dp_dpcd_readb(intel_dp->mst.mgr.aux, DP_MSTM_CTRL, &val); /* Adjust the expected register value for SST + SideBand. */ if (ret < 0 || val != (DP_MST_EN | DP_UP_REQ_EN | DP_UPSTREAM_IS_SRC)) { diff --git a/drivers/gpu/drm/i915/display/intel_dp_test.c b/drivers/gpu/drm/i915/display/intel_dp_test.c index 614b90d6938f..bd61f3c3ec91 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_test.c +++ b/drivers/gpu/drm/i915/display/intel_dp_test.c @@ -6,6 +6,8 @@ #include <drm/display/drm_dp.h> #include <drm/display/drm_dp_helper.h> #include <drm/drm_edid.h> +#include <drm/drm_file.h> +#include <drm/drm_print.h> #include <drm/drm_probe_helper.h> #include "i915_reg.h" diff --git a/drivers/gpu/drm/i915/display/intel_dp_tunnel.c b/drivers/gpu/drm/i915/display/intel_dp_tunnel.c index 280f302967e3..faa2b7a46699 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_tunnel.c +++ b/drivers/gpu/drm/i915/display/intel_dp_tunnel.c @@ -4,6 +4,7 @@ */ #include <drm/display/drm_dp_tunnel.h> +#include <drm/drm_print.h> #include "intel_atomic.h" #include "intel_display_core.h" diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c index 8b1f0e92a11c..0d8ebe38226e 100644 --- a/drivers/gpu/drm/i915/display/intel_dpt.c +++ b/drivers/gpu/drm/i915/display/intel_dpt.c @@ -125,6 +125,7 @@ struct i915_vma *intel_dpt_pin_to_ggtt(struct i915_address_space *vm, unsigned int alignment) { struct drm_i915_private *i915 = vm->i915; + struct intel_display *display = &i915->display; struct i915_dpt *dpt = i915_vm_to_dpt(vm); intel_wakeref_t wakeref; struct i915_vma *vma; @@ -137,7 +138,7 @@ struct i915_vma *intel_dpt_pin_to_ggtt(struct i915_address_space *vm, pin_flags |= PIN_MAPPABLE; wakeref = intel_runtime_pm_get(&i915->runtime_pm); - atomic_inc(&i915->gpu_error.pending_fb_pin); + atomic_inc(&display->restore.pending_fb_pin); for_i915_gem_ww(&ww, err, true) { err = i915_gem_object_lock(dpt->obj, &ww); @@ -167,7 +168,7 @@ struct i915_vma *intel_dpt_pin_to_ggtt(struct i915_address_space *vm, dpt->obj->mm.dirty = true; - atomic_dec(&i915->gpu_error.pending_fb_pin); + atomic_dec(&display->restore.pending_fb_pin); intel_runtime_pm_put(&i915->runtime_pm, wakeref); return err ? ERR_PTR(err) : vma; @@ -183,7 +184,7 @@ void intel_dpt_unpin_from_ggtt(struct i915_address_space *vm) /** * intel_dpt_resume - restore the memory mapping for all DPT FBs during system resume - * @i915: device instance + * @display: display device instance * * Restore the memory mapping during system resume for all framebuffers which * are mapped to HW via a GGTT->DPT page table. The content of these page @@ -193,26 +194,26 @@ void intel_dpt_unpin_from_ggtt(struct i915_address_space *vm) * This function must be called after the mappings in GGTT have been restored calling * i915_ggtt_resume(). */ -void intel_dpt_resume(struct drm_i915_private *i915) +void intel_dpt_resume(struct intel_display *display) { struct drm_framebuffer *drm_fb; - if (!HAS_DISPLAY(i915)) + if (!HAS_DISPLAY(display)) return; - mutex_lock(&i915->drm.mode_config.fb_lock); - drm_for_each_fb(drm_fb, &i915->drm) { + mutex_lock(&display->drm->mode_config.fb_lock); + drm_for_each_fb(drm_fb, display->drm) { struct intel_framebuffer *fb = to_intel_framebuffer(drm_fb); if (fb->dpt_vm) i915_ggtt_resume_vm(fb->dpt_vm, true); } - mutex_unlock(&i915->drm.mode_config.fb_lock); + mutex_unlock(&display->drm->mode_config.fb_lock); } /** * intel_dpt_suspend - suspend the memory mapping for all DPT FBs during system suspend - * @i915: device instance + * @display: display device instance * * Suspend the memory mapping during system suspend for all framebuffers which * are mapped to HW via a GGTT->DPT page table. @@ -220,23 +221,23 @@ void intel_dpt_resume(struct drm_i915_private *i915) * This function must be called before the mappings in GGTT are suspended calling * i915_ggtt_suspend(). */ -void intel_dpt_suspend(struct drm_i915_private *i915) +void intel_dpt_suspend(struct intel_display *display) { struct drm_framebuffer *drm_fb; - if (!HAS_DISPLAY(i915)) + if (!HAS_DISPLAY(display)) return; - mutex_lock(&i915->drm.mode_config.fb_lock); + mutex_lock(&display->drm->mode_config.fb_lock); - drm_for_each_fb(drm_fb, &i915->drm) { + drm_for_each_fb(drm_fb, display->drm) { struct intel_framebuffer *fb = to_intel_framebuffer(drm_fb); if (fb->dpt_vm) i915_ggtt_suspend_vm(fb->dpt_vm, true); } - mutex_unlock(&i915->drm.mode_config.fb_lock); + mutex_unlock(&display->drm->mode_config.fb_lock); } struct i915_address_space * diff --git a/drivers/gpu/drm/i915/display/intel_dpt.h b/drivers/gpu/drm/i915/display/intel_dpt.h index 1f88b0ee17e7..db521401b828 100644 --- a/drivers/gpu/drm/i915/display/intel_dpt.h +++ b/drivers/gpu/drm/i915/display/intel_dpt.h @@ -8,18 +8,17 @@ #include <linux/types.h> -struct drm_i915_private; - struct i915_address_space; struct i915_vma; +struct intel_display; struct intel_framebuffer; void intel_dpt_destroy(struct i915_address_space *vm); struct i915_vma *intel_dpt_pin_to_ggtt(struct i915_address_space *vm, unsigned int alignment); void intel_dpt_unpin_from_ggtt(struct i915_address_space *vm); -void intel_dpt_suspend(struct drm_i915_private *i915); -void intel_dpt_resume(struct drm_i915_private *i915); +void intel_dpt_suspend(struct intel_display *display); +void intel_dpt_resume(struct intel_display *display); struct i915_address_space * intel_dpt_create(struct intel_framebuffer *fb); u64 intel_dpt_offset(struct i915_vma *dpt_vma); diff --git a/drivers/gpu/drm/i915/display/intel_drrs.c b/drivers/gpu/drm/i915/display/intel_drrs.c index 0fec01b79b23..05cd0f6e6d71 100644 --- a/drivers/gpu/drm/i915/display/intel_drrs.c +++ b/drivers/gpu/drm/i915/display/intel_drrs.c @@ -65,31 +65,29 @@ const char *intel_drrs_type_str(enum drrs_type drrs_type) return str[drrs_type]; } -bool intel_cpu_transcoder_has_drrs(struct drm_i915_private *i915, +bool intel_cpu_transcoder_has_drrs(struct intel_display *display, enum transcoder cpu_transcoder) { - struct intel_display *display = &i915->display; - if (HAS_DOUBLE_BUFFERED_M_N(display)) return true; - return intel_cpu_transcoder_has_m2_n2(i915, cpu_transcoder); + return intel_cpu_transcoder_has_m2_n2(display, cpu_transcoder); } static void intel_drrs_set_refresh_rate_pipeconf(struct intel_crtc *crtc, enum drrs_refresh_rate refresh_rate) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); enum transcoder cpu_transcoder = crtc->drrs.cpu_transcoder; u32 bit; - if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) + if (display->platform.valleyview || display->platform.cherryview) bit = TRANSCONF_REFRESH_RATE_ALT_VLV; else bit = TRANSCONF_REFRESH_RATE_ALT_ILK; - intel_de_rmw(dev_priv, TRANSCONF(dev_priv, cpu_transcoder), + intel_de_rmw(display, TRANSCONF(display, cpu_transcoder), bit, refresh_rate == DRRS_REFRESH_RATE_LOW ? bit : 0); } @@ -110,12 +108,12 @@ bool intel_drrs_is_active(struct intel_crtc *crtc) static void intel_drrs_set_state(struct intel_crtc *crtc, enum drrs_refresh_rate refresh_rate) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); if (refresh_rate == crtc->drrs.refresh_rate) return; - if (intel_cpu_transcoder_has_m2_n2(dev_priv, crtc->drrs.cpu_transcoder)) + if (intel_cpu_transcoder_has_m2_n2(display, crtc->drrs.cpu_transcoder)) intel_drrs_set_refresh_rate_pipeconf(crtc, refresh_rate); else intel_drrs_set_refresh_rate_m_n(crtc, refresh_rate); @@ -132,13 +130,13 @@ static void intel_drrs_schedule_work(struct intel_crtc *crtc) static unsigned int intel_drrs_frontbuffer_bits(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *i915 = to_i915(crtc->base.dev); unsigned int frontbuffer_bits; frontbuffer_bits = INTEL_FRONTBUFFER_ALL_MASK(crtc->pipe); - for_each_intel_crtc_in_pipe_mask(&i915->drm, crtc, + for_each_intel_crtc_in_pipe_mask(display->drm, crtc, crtc_state->joiner_pipes) frontbuffer_bits |= INTEL_FRONTBUFFER_ALL_MASK(crtc->pipe); @@ -222,13 +220,13 @@ static void intel_drrs_downclock_work(struct work_struct *work) mutex_unlock(&crtc->drrs.mutex); } -static void intel_drrs_frontbuffer_update(struct drm_i915_private *dev_priv, +static void intel_drrs_frontbuffer_update(struct intel_display *display, unsigned int all_frontbuffer_bits, bool invalidate) { struct intel_crtc *crtc; - for_each_intel_crtc(&dev_priv->drm, crtc) { + for_each_intel_crtc(display->drm, crtc) { unsigned int frontbuffer_bits; mutex_lock(&crtc->drrs.mutex); @@ -262,7 +260,7 @@ static void intel_drrs_frontbuffer_update(struct drm_i915_private *dev_priv, /** * intel_drrs_invalidate - Disable Idleness DRRS - * @dev_priv: i915 device + * @display: display device * @frontbuffer_bits: frontbuffer plane tracking bits * * This function gets called everytime rendering on the given planes start. @@ -270,15 +268,15 @@ static void intel_drrs_frontbuffer_update(struct drm_i915_private *dev_priv, * * Dirty frontbuffers relevant to DRRS are tracked in busy_frontbuffer_bits. */ -void intel_drrs_invalidate(struct drm_i915_private *dev_priv, +void intel_drrs_invalidate(struct intel_display *display, unsigned int frontbuffer_bits) { - intel_drrs_frontbuffer_update(dev_priv, frontbuffer_bits, true); + intel_drrs_frontbuffer_update(display, frontbuffer_bits, true); } /** * intel_drrs_flush - Restart Idleness DRRS - * @dev_priv: i915 device + * @display: display device * @frontbuffer_bits: frontbuffer plane tracking bits * * This function gets called every time rendering on the given planes has @@ -288,10 +286,10 @@ void intel_drrs_invalidate(struct drm_i915_private *dev_priv, * * Dirty frontbuffers relevant to DRRS are tracked in busy_frontbuffer_bits. */ -void intel_drrs_flush(struct drm_i915_private *dev_priv, +void intel_drrs_flush(struct intel_display *display, unsigned int frontbuffer_bits) { - intel_drrs_frontbuffer_update(dev_priv, frontbuffer_bits, false); + intel_drrs_frontbuffer_update(display, frontbuffer_bits, false); } /** @@ -312,7 +310,7 @@ void intel_drrs_crtc_init(struct intel_crtc *crtc) static int intel_drrs_debugfs_status_show(struct seq_file *m, void *unused) { struct intel_crtc *crtc = m->private; - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); const struct intel_crtc_state *crtc_state; int ret; @@ -325,7 +323,7 @@ static int intel_drrs_debugfs_status_show(struct seq_file *m, void *unused) mutex_lock(&crtc->drrs.mutex); seq_printf(m, "DRRS capable: %s\n", - str_yes_no(intel_cpu_transcoder_has_drrs(i915, + str_yes_no(intel_cpu_transcoder_has_drrs(display, crtc_state->cpu_transcoder))); seq_printf(m, "DRRS enabled: %s\n", @@ -353,7 +351,7 @@ DEFINE_SHOW_ATTRIBUTE(intel_drrs_debugfs_status); static int intel_drrs_debugfs_ctl_set(void *data, u64 val) { struct intel_crtc *crtc = data; - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); struct intel_crtc_state *crtc_state; struct drm_crtc_commit *commit; int ret; @@ -375,8 +373,7 @@ static int intel_drrs_debugfs_ctl_set(void *data, u64 val) goto out; } - drm_dbg(&i915->drm, - "Manually %sactivating DRRS\n", val ? "" : "de"); + drm_dbg_kms(display->drm, "Manually %sactivating DRRS\n", val ? "" : "de"); if (val) intel_drrs_activate(crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_drrs.h b/drivers/gpu/drm/i915/display/intel_drrs.h index 0982f95eab72..32b45a93a68f 100644 --- a/drivers/gpu/drm/i915/display/intel_drrs.h +++ b/drivers/gpu/drm/i915/display/intel_drrs.h @@ -10,21 +10,21 @@ enum drrs_type; enum transcoder; -struct drm_i915_private; struct intel_atomic_state; +struct intel_connector; struct intel_crtc; struct intel_crtc_state; -struct intel_connector; +struct intel_display; -bool intel_cpu_transcoder_has_drrs(struct drm_i915_private *i915, +bool intel_cpu_transcoder_has_drrs(struct intel_display *display, enum transcoder cpu_transcoder); const char *intel_drrs_type_str(enum drrs_type drrs_type); bool intel_drrs_is_active(struct intel_crtc *crtc); void intel_drrs_activate(const struct intel_crtc_state *crtc_state); void intel_drrs_deactivate(const struct intel_crtc_state *crtc_state); -void intel_drrs_invalidate(struct drm_i915_private *dev_priv, +void intel_drrs_invalidate(struct intel_display *display, unsigned int frontbuffer_bits); -void intel_drrs_flush(struct drm_i915_private *dev_priv, +void intel_drrs_flush(struct intel_display *display, unsigned int frontbuffer_bits); void intel_drrs_crtc_init(struct intel_crtc *crtc); void intel_drrs_crtc_debugfs_add(struct intel_crtc *crtc); diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c index 204e7e3e48ca..30ac9b089ad6 100644 --- a/drivers/gpu/drm/i915/display/intel_fb_pin.c +++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c @@ -25,6 +25,7 @@ intel_fb_pin_to_dpt(const struct drm_framebuffer *fb, struct i915_address_space *vm) { struct drm_device *dev = fb->dev; + struct intel_display *display = to_intel_display(dev); struct drm_i915_private *dev_priv = to_i915(dev); struct drm_gem_object *_obj = intel_fb_bo(fb); struct drm_i915_gem_object *obj = to_intel_bo(_obj); @@ -42,7 +43,7 @@ intel_fb_pin_to_dpt(const struct drm_framebuffer *fb, if (WARN_ON(!i915_gem_object_is_framebuffer(obj))) return ERR_PTR(-EINVAL); - atomic_inc(&dev_priv->gpu_error.pending_fb_pin); + atomic_inc(&display->restore.pending_fb_pin); for_i915_gem_ww(&ww, ret, true) { ret = i915_gem_object_lock(obj, &ww); @@ -97,7 +98,7 @@ intel_fb_pin_to_dpt(const struct drm_framebuffer *fb, i915_vma_get(vma); err: - atomic_dec(&dev_priv->gpu_error.pending_fb_pin); + atomic_dec(&display->restore.pending_fb_pin); return vma; } @@ -112,6 +113,7 @@ intel_fb_pin_to_ggtt(const struct drm_framebuffer *fb, unsigned long *out_flags) { struct drm_device *dev = fb->dev; + struct intel_display *display = to_intel_display(dev); struct drm_i915_private *dev_priv = to_i915(dev); struct drm_gem_object *_obj = intel_fb_bo(fb); struct drm_i915_gem_object *obj = to_intel_bo(_obj); @@ -136,7 +138,7 @@ intel_fb_pin_to_ggtt(const struct drm_framebuffer *fb, */ wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm); - atomic_inc(&dev_priv->gpu_error.pending_fb_pin); + atomic_inc(&display->restore.pending_fb_pin); /* * Valleyview is definitely limited to scanning out the first @@ -212,7 +214,7 @@ err: if (ret) vma = ERR_PTR(ret); - atomic_dec(&dev_priv->gpu_error.pending_fb_pin); + atomic_dec(&display->restore.pending_fb_pin); intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref); return vma; } diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index df05904bac8a..b6978135e8ad 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -88,6 +88,7 @@ struct intel_fbc_state { u16 override_cfb_stride; u16 interval; s8 fence_id; + struct drm_rect dirty_rect; }; struct intel_fbc { @@ -215,11 +216,9 @@ static unsigned int intel_fbc_cfb_stride(const struct intel_plane_state *plane_s */ static unsigned int intel_fbc_max_cfb_height(struct intel_display *display) { - struct drm_i915_private *i915 = to_i915(display->drm); - if (DISPLAY_VER(display) >= 8) return 2560; - else if (DISPLAY_VER(display) >= 5 || IS_G4X(i915)) + else if (DISPLAY_VER(display) >= 5 || display->platform.g4x) return 2048; else return 1536; @@ -269,9 +268,8 @@ static bool intel_fbc_has_fences(struct intel_display *display) static u32 i8xx_fbc_ctl(struct intel_fbc *fbc) { - const struct intel_fbc_state *fbc_state = &fbc->state; struct intel_display *display = fbc->display; - struct drm_i915_private *i915 = to_i915(display->drm); + const struct intel_fbc_state *fbc_state = &fbc->state; unsigned int cfb_stride; u32 fbc_ctl; @@ -287,7 +285,7 @@ static u32 i8xx_fbc_ctl(struct intel_fbc *fbc) FBC_CTL_INTERVAL(fbc_state->interval) | FBC_CTL_STRIDE(cfb_stride); - if (IS_I945GM(i915)) + if (display->platform.i945gm) fbc_ctl |= FBC_CTL_C3_IDLE; /* 945 needs special SR handling */ if (fbc_state->fence_id >= 0) @@ -333,8 +331,8 @@ static void i8xx_fbc_deactivate(struct intel_fbc *fbc) static void i8xx_fbc_activate(struct intel_fbc *fbc) { - const struct intel_fbc_state *fbc_state = &fbc->state; struct intel_display *display = fbc->display; + const struct intel_fbc_state *fbc_state = &fbc->state; int i; /* Clear old tags */ @@ -365,12 +363,12 @@ static bool i8xx_fbc_is_compressing(struct intel_fbc *fbc) static void i8xx_fbc_nuke(struct intel_fbc *fbc) { + struct intel_display *display = fbc->display; struct intel_fbc_state *fbc_state = &fbc->state; enum i9xx_plane_id i9xx_plane = fbc_state->plane->i9xx_plane; - struct drm_i915_private *dev_priv = to_i915(fbc->display->drm); - intel_de_write_fw(dev_priv, DSPADDR(dev_priv, i9xx_plane), - intel_de_read_fw(dev_priv, DSPADDR(dev_priv, i9xx_plane))); + intel_de_write_fw(display, DSPADDR(display, i9xx_plane), + intel_de_read_fw(display, DSPADDR(display, i9xx_plane))); } static void i8xx_fbc_program_cfb(struct intel_fbc *fbc) @@ -386,9 +384,9 @@ static void i8xx_fbc_program_cfb(struct intel_fbc *fbc) range_overflows_end_t(u64, i915_gem_stolen_area_address(i915), i915_gem_stolen_node_offset(&fbc->compressed_llb), U32_MAX)); - intel_de_write(i915, FBC_CFB_BASE, + intel_de_write(display, FBC_CFB_BASE, i915_gem_stolen_node_address(i915, &fbc->compressed_fb)); - intel_de_write(i915, FBC_LL_BASE, + intel_de_write(display, FBC_LL_BASE, i915_gem_stolen_node_address(i915, &fbc->compressed_llb)); } @@ -403,12 +401,12 @@ static const struct intel_fbc_funcs i8xx_fbc_funcs = { static void i965_fbc_nuke(struct intel_fbc *fbc) { + struct intel_display *display = fbc->display; struct intel_fbc_state *fbc_state = &fbc->state; enum i9xx_plane_id i9xx_plane = fbc_state->plane->i9xx_plane; - struct drm_i915_private *dev_priv = to_i915(fbc->display->drm); - intel_de_write_fw(dev_priv, DSPSURF(dev_priv, i9xx_plane), - intel_de_read_fw(dev_priv, DSPSURF(dev_priv, i9xx_plane))); + intel_de_write_fw(display, DSPSURF(display, i9xx_plane), + intel_de_read_fw(display, DSPSURF(display, i9xx_plane))); } static const struct intel_fbc_funcs i965_fbc_funcs = { @@ -437,15 +435,14 @@ static u32 g4x_dpfc_ctl_limit(struct intel_fbc *fbc) static u32 g4x_dpfc_ctl(struct intel_fbc *fbc) { - const struct intel_fbc_state *fbc_state = &fbc->state; struct intel_display *display = fbc->display; - struct drm_i915_private *i915 = to_i915(display->drm); + const struct intel_fbc_state *fbc_state = &fbc->state; u32 dpfc_ctl; dpfc_ctl = g4x_dpfc_ctl_limit(fbc) | DPFC_CTL_PLANE_G4X(fbc_state->plane->i9xx_plane); - if (IS_G4X(i915)) + if (display->platform.g4x) dpfc_ctl |= DPFC_CTL_SR_EN; if (fbc_state->fence_id >= 0) { @@ -460,8 +457,8 @@ static u32 g4x_dpfc_ctl(struct intel_fbc *fbc) static void g4x_fbc_activate(struct intel_fbc *fbc) { - const struct intel_fbc_state *fbc_state = &fbc->state; struct intel_display *display = fbc->display; + const struct intel_fbc_state *fbc_state = &fbc->state; intel_de_write(display, DPFC_FENCE_YOFF, fbc_state->fence_y_offset); @@ -512,8 +509,8 @@ static const struct intel_fbc_funcs g4x_fbc_funcs = { static void ilk_fbc_activate(struct intel_fbc *fbc) { - struct intel_fbc_state *fbc_state = &fbc->state; struct intel_display *display = fbc->display; + struct intel_fbc_state *fbc_state = &fbc->state; intel_de_write(display, ILK_DPFC_FENCE_YOFF(fbc->id), fbc_state->fence_y_offset); @@ -527,6 +524,9 @@ static void ilk_fbc_deactivate(struct intel_fbc *fbc) struct intel_display *display = fbc->display; u32 dpfc_ctl; + if (HAS_FBC_DIRTY_RECT(display)) + intel_de_write(display, XE3_FBC_DIRTY_CTL(fbc->id), 0); + /* Disable compression */ dpfc_ctl = intel_de_read(display, ILK_DPFC_CONTROL(fbc->id)); if (dpfc_ctl & DPFC_CTL_EN) { @@ -564,8 +564,8 @@ static const struct intel_fbc_funcs ilk_fbc_funcs = { static void snb_fbc_program_fence(struct intel_fbc *fbc) { - const struct intel_fbc_state *fbc_state = &fbc->state; struct intel_display *display = fbc->display; + const struct intel_fbc_state *fbc_state = &fbc->state; u32 ctl = 0; if (fbc_state->fence_id >= 0) @@ -601,8 +601,8 @@ static const struct intel_fbc_funcs snb_fbc_funcs = { static void glk_fbc_program_cfb_stride(struct intel_fbc *fbc) { - const struct intel_fbc_state *fbc_state = &fbc->state; struct intel_display *display = fbc->display; + const struct intel_fbc_state *fbc_state = &fbc->state; u32 val = 0; if (fbc_state->override_cfb_stride) @@ -614,8 +614,8 @@ static void glk_fbc_program_cfb_stride(struct intel_fbc *fbc) static void skl_fbc_program_cfb_stride(struct intel_fbc *fbc) { - const struct intel_fbc_state *fbc_state = &fbc->state; struct intel_display *display = fbc->display; + const struct intel_fbc_state *fbc_state = &fbc->state; u32 val = 0; /* Display WA #0529: skl, kbl, bxt. */ @@ -630,14 +630,13 @@ static void skl_fbc_program_cfb_stride(struct intel_fbc *fbc) static u32 ivb_dpfc_ctl(struct intel_fbc *fbc) { - const struct intel_fbc_state *fbc_state = &fbc->state; struct intel_display *display = fbc->display; - struct drm_i915_private *i915 = to_i915(display->drm); + const struct intel_fbc_state *fbc_state = &fbc->state; u32 dpfc_ctl; dpfc_ctl = g4x_dpfc_ctl_limit(fbc); - if (IS_IVYBRIDGE(i915)) + if (display->platform.ivybridge) dpfc_ctl |= DPFC_CTL_PLANE_IVB(fbc_state->plane->i9xx_plane); if (DISPLAY_VER(display) >= 20) @@ -670,6 +669,10 @@ static void ivb_fbc_activate(struct intel_fbc *fbc) if (DISPLAY_VER(display) >= 20) intel_de_write(display, ILK_DPFC_CONTROL(fbc->id), dpfc_ctl); + if (HAS_FBC_DIRTY_RECT(display)) + intel_de_write(display, XE3_FBC_DIRTY_CTL(fbc->id), + FBC_DIRTY_RECT_EN); + intel_de_write(display, ILK_DPFC_CONTROL(fbc->id), DPFC_CTL_EN | dpfc_ctl); } @@ -739,8 +742,19 @@ static void intel_fbc_nuke(struct intel_fbc *fbc) static void intel_fbc_activate(struct intel_fbc *fbc) { + struct intel_display *display = fbc->display; + lockdep_assert_held(&fbc->lock); + /* only the fence can change for a flip nuke */ + if (fbc->active && !intel_fbc_has_fences(display)) + return; + /* + * In case of FBC dirt rect, any updates to the FBC registers will + * trigger the nuke. + */ + drm_WARN_ON(display->drm, fbc->active && HAS_FBC_DIRTY_RECT(display)); + intel_fbc_hw_activate(fbc); intel_fbc_nuke(fbc); @@ -759,9 +773,7 @@ static void intel_fbc_deactivate(struct intel_fbc *fbc, const char *reason) static u64 intel_fbc_cfb_base_max(struct intel_display *display) { - struct drm_i915_private *i915 = to_i915(display->drm); - - if (DISPLAY_VER(display) >= 5 || IS_G4X(i915)) + if (DISPLAY_VER(display) >= 5 || display->platform.g4x) return BIT_ULL(28); else return BIT_ULL(32); @@ -776,8 +788,8 @@ static u64 intel_fbc_stolen_end(struct intel_display *display) * reserved range size, so it always assumes the maximum (8mb) is used. * If we enable FBC using a CFB on that memory range we'll get FIFO * underruns, even if that range is not reserved by the BIOS. */ - if (IS_BROADWELL(i915) || - (DISPLAY_VER(display) == 9 && !IS_BROXTON(i915))) + if (display->platform.broadwell || + (DISPLAY_VER(display) == 9 && !display->platform.broxton)) end = i915_gem_stolen_area_size(i915) - 8 * 1024 * 1024; else end = U64_MAX; @@ -792,10 +804,8 @@ static int intel_fbc_min_limit(const struct intel_plane_state *plane_state) static int intel_fbc_max_limit(struct intel_display *display) { - struct drm_i915_private *i915 = to_i915(display->drm); - /* WaFbcOnly1to1Ratio:ctg */ - if (IS_G4X(i915)) + if (display->platform.g4x) return 1; /* @@ -843,7 +853,7 @@ static int intel_fbc_alloc_cfb(struct intel_fbc *fbc, drm_WARN_ON(display->drm, i915_gem_stolen_node_allocated(&fbc->compressed_llb)); - if (DISPLAY_VER(display) < 5 && !IS_G4X(i915)) { + if (DISPLAY_VER(display) < 5 && !display->platform.g4x) { ret = i915_gem_stolen_insert_node(i915, &fbc->compressed_llb, 4096, 4096); if (ret) @@ -882,9 +892,8 @@ static void intel_fbc_program_cfb(struct intel_fbc *fbc) static void intel_fbc_program_workarounds(struct intel_fbc *fbc) { struct intel_display *display = fbc->display; - struct drm_i915_private *i915 = to_i915(display->drm); - if (IS_SKYLAKE(i915) || IS_BROXTON(i915)) { + if (display->platform.skylake || display->platform.broxton) { /* * WaFbcHighMemBwCorruptionAvoidance:skl,bxt * Display WA #0883: skl,bxt @@ -893,8 +902,8 @@ static void intel_fbc_program_workarounds(struct intel_fbc *fbc) 0, DPFC_DISABLE_DUMMY0); } - if (IS_SKYLAKE(i915) || IS_KABYLAKE(i915) || - IS_COFFEELAKE(i915) || IS_COMETLAKE(i915)) { + if (display->platform.skylake || display->platform.kabylake || + display->platform.coffeelake || display->platform.cometlake) { /* * WaFbcNukeOnHostModify:skl,kbl,cfl * Display WA #0873: skl,kbl,cfl @@ -909,7 +918,7 @@ static void intel_fbc_program_workarounds(struct intel_fbc *fbc) 0, DPFC_CHICKEN_COMP_DUMMY_PIXEL); /* Wa_22014263786:icl,jsl,tgl,dg1,rkl,adls,adlp,mtl */ - if (DISPLAY_VER(display) >= 11 && !IS_DG2(i915)) + if (DISPLAY_VER(display) >= 11 && !display->platform.dg2) intel_de_rmw(display, ILK_DPFC_CHICKEN(fbc->id), 0, DPFC_CHICKEN_FORCE_SLB_INVALIDATION); } @@ -986,13 +995,12 @@ static bool icl_fbc_stride_is_valid(const struct intel_plane_state *plane_state) static bool stride_is_valid(const struct intel_plane_state *plane_state) { struct intel_display *display = to_intel_display(plane_state->uapi.plane->dev); - struct drm_i915_private *i915 = to_i915(display->drm); if (DISPLAY_VER(display) >= 11) return icl_fbc_stride_is_valid(plane_state); else if (DISPLAY_VER(display) >= 9) return skl_fbc_stride_is_valid(plane_state); - else if (DISPLAY_VER(display) >= 5 || IS_G4X(i915)) + else if (DISPLAY_VER(display) >= 5 || display->platform.g4x) return g4x_fbc_stride_is_valid(plane_state); else if (DISPLAY_VER(display) == 4) return i965_fbc_stride_is_valid(plane_state); @@ -1023,7 +1031,6 @@ static bool i8xx_fbc_pixel_format_is_valid(const struct intel_plane_state *plane static bool g4x_fbc_pixel_format_is_valid(const struct intel_plane_state *plane_state) { struct intel_display *display = to_intel_display(plane_state->uapi.plane->dev); - struct drm_i915_private *i915 = to_i915(display->drm); const struct drm_framebuffer *fb = plane_state->hw.fb; switch (fb->format->format) { @@ -1032,7 +1039,7 @@ static bool g4x_fbc_pixel_format_is_valid(const struct intel_plane_state *plane_ return true; case DRM_FORMAT_RGB565: /* WaFbcOnly1to1Ratio:ctg */ - if (IS_G4X(i915)) + if (display->platform.g4x) return false; return true; default: @@ -1059,11 +1066,10 @@ static bool lnl_fbc_pixel_format_is_valid(const struct intel_plane_state *plane_ static bool pixel_format_is_valid(const struct intel_plane_state *plane_state) { struct intel_display *display = to_intel_display(plane_state->uapi.plane->dev); - struct drm_i915_private *i915 = to_i915(display->drm); if (DISPLAY_VER(display) >= 20) return lnl_fbc_pixel_format_is_valid(plane_state); - else if (DISPLAY_VER(display) >= 5 || IS_G4X(i915)) + else if (DISPLAY_VER(display) >= 5 || display->platform.g4x) return g4x_fbc_pixel_format_is_valid(plane_state); else return i8xx_fbc_pixel_format_is_valid(plane_state); @@ -1094,11 +1100,10 @@ static bool skl_fbc_rotation_is_valid(const struct intel_plane_state *plane_stat static bool rotation_is_valid(const struct intel_plane_state *plane_state) { struct intel_display *display = to_intel_display(plane_state->uapi.plane->dev); - struct drm_i915_private *i915 = to_i915(display->drm); if (DISPLAY_VER(display) >= 9) return skl_fbc_rotation_is_valid(plane_state); - else if (DISPLAY_VER(display) >= 5 || IS_G4X(i915)) + else if (DISPLAY_VER(display) >= 5 || display->platform.g4x) return g4x_fbc_rotation_is_valid(plane_state); else return i8xx_fbc_rotation_is_valid(plane_state); @@ -1107,8 +1112,6 @@ static bool rotation_is_valid(const struct intel_plane_state *plane_state) static void intel_fbc_max_surface_size(struct intel_display *display, unsigned int *w, unsigned int *h) { - struct drm_i915_private *i915 = to_i915(display->drm); - if (DISPLAY_VER(display) >= 11) { *w = 8192; *h = 4096; @@ -1118,7 +1121,7 @@ static void intel_fbc_max_surface_size(struct intel_display *display, } else if (DISPLAY_VER(display) >= 7) { *w = 4096; *h = 4096; - } else if (DISPLAY_VER(display) >= 5 || IS_G4X(i915)) { + } else if (DISPLAY_VER(display) >= 5 || display->platform.g4x) { *w = 4096; *h = 2048; } else { @@ -1151,15 +1154,13 @@ static bool intel_fbc_surface_size_ok(const struct intel_plane_state *plane_stat static void intel_fbc_max_plane_size(struct intel_display *display, unsigned int *w, unsigned int *h) { - struct drm_i915_private *i915 = to_i915(display->drm); - if (DISPLAY_VER(display) >= 10) { *w = 5120; *h = 4096; - } else if (DISPLAY_VER(display) >= 8 || IS_HASWELL(i915)) { + } else if (DISPLAY_VER(display) >= 8 || display->platform.haswell) { *w = 4096; *h = 4096; - } else if (DISPLAY_VER(display) >= 5 || IS_G4X(i915)) { + } else if (DISPLAY_VER(display) >= 5 || display->platform.g4x) { *w = 4096; *h = 2048; } else { @@ -1203,6 +1204,74 @@ static bool tiling_is_valid(const struct intel_plane_state *plane_state) return i8xx_fbc_tiling_valid(plane_state); } +static void +intel_fbc_invalidate_dirty_rect(struct intel_fbc *fbc) +{ + lockdep_assert_held(&fbc->lock); + + fbc->state.dirty_rect = DRM_RECT_INIT(0, 0, 0, 0); +} + +static void +intel_fbc_program_dirty_rect(struct intel_dsb *dsb, struct intel_fbc *fbc, + const struct drm_rect *fbc_dirty_rect) +{ + struct intel_display *display = fbc->display; + + drm_WARN_ON(display->drm, fbc_dirty_rect->y2 == 0); + + intel_de_write_dsb(display, dsb, XE3_FBC_DIRTY_RECT(fbc->id), + FBC_DIRTY_RECT_START_LINE(fbc_dirty_rect->y1) | + FBC_DIRTY_RECT_END_LINE(fbc_dirty_rect->y2 - 1)); +} + +static void +intel_fbc_dirty_rect_update(struct intel_dsb *dsb, struct intel_fbc *fbc) +{ + const struct drm_rect *fbc_dirty_rect = &fbc->state.dirty_rect; + + lockdep_assert_held(&fbc->lock); + + if (!drm_rect_visible(fbc_dirty_rect)) + return; + + intel_fbc_program_dirty_rect(dsb, fbc, fbc_dirty_rect); +} + +void +intel_fbc_dirty_rect_update_noarm(struct intel_dsb *dsb, + struct intel_plane *plane) +{ + struct intel_display *display = to_intel_display(plane); + struct intel_fbc *fbc = plane->fbc; + + if (!HAS_FBC_DIRTY_RECT(display)) + return; + + mutex_lock(&fbc->lock); + + if (fbc->state.plane == plane) + intel_fbc_dirty_rect_update(dsb, fbc); + + mutex_unlock(&fbc->lock); +} + +static void +intel_fbc_hw_intialize_dirty_rect(struct intel_fbc *fbc, + const struct intel_plane_state *plane_state) +{ + struct drm_rect src; + + /* + * Initializing the FBC HW with the whole plane area as the dirty rect. + * This is to ensure that we have valid coords be written to the + * HW as dirty rect. + */ + drm_rect_fp_to_int(&src, &plane_state->uapi.src); + + intel_fbc_program_dirty_rect(NULL, fbc, &src); +} + static void intel_fbc_update_state(struct intel_atomic_state *state, struct intel_crtc *crtc, struct intel_plane *plane) @@ -1276,6 +1345,62 @@ static bool intel_fbc_is_ok(const struct intel_plane_state *plane_state) intel_fbc_is_cfb_ok(plane_state); } +static void +__intel_fbc_prepare_dirty_rect(const struct intel_plane_state *plane_state, + const struct intel_crtc_state *crtc_state) +{ + struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); + struct intel_fbc *fbc = plane->fbc; + struct drm_rect *fbc_dirty_rect = &fbc->state.dirty_rect; + int width = drm_rect_width(&plane_state->uapi.src) >> 16; + const struct drm_rect *damage = &plane_state->damage; + int y_offset = plane_state->view.color_plane[0].y; + + lockdep_assert_held(&fbc->lock); + + if (intel_crtc_needs_modeset(crtc_state) || + !intel_fbc_is_ok(plane_state)) { + intel_fbc_invalidate_dirty_rect(fbc); + return; + } + + if (drm_rect_visible(damage)) + *fbc_dirty_rect = *damage; + else + /* dirty rect must cover at least one line */ + *fbc_dirty_rect = DRM_RECT_INIT(0, y_offset, width, 1); +} + +void +intel_fbc_prepare_dirty_rect(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct intel_display *display = to_intel_display(state); + const struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + struct intel_plane_state *plane_state; + struct intel_plane *plane; + int i; + + if (!HAS_FBC_DIRTY_RECT(display)) + return; + + for_each_new_intel_plane_in_state(state, plane, plane_state, i) { + struct intel_fbc *fbc = plane->fbc; + + if (!fbc || plane->pipe != crtc->pipe) + continue; + + mutex_lock(&fbc->lock); + + if (fbc->state.plane == plane) + __intel_fbc_prepare_dirty_rect(plane_state, + crtc_state); + + mutex_unlock(&fbc->lock); + } +} + static int intel_fbc_check_plane(struct intel_atomic_state *state, struct intel_plane *plane) { @@ -1317,7 +1442,7 @@ static int intel_fbc_check_plane(struct intel_atomic_state *state, } /* WaFbcTurnOffFbcWhenHyperVisorIsUsed:skl,bxt */ - if (i915_vtd_active(i915) && (IS_SKYLAKE(i915) || IS_BROXTON(i915))) { + if (i915_vtd_active(i915) && (display->platform.skylake || display->platform.broxton)) { plane_state->no_fbc_reason = "VT-d enabled"; return 0; } @@ -1338,16 +1463,21 @@ static int intel_fbc_check_plane(struct intel_atomic_state *state, * Display 12+ is not supporting FBC with PSR2. * Recommendation is to keep this combination disabled * Bspec: 50422 HSD: 14010260002 + * + * In Xe3, PSR2 selective fetch and FBC dirty rect feature cannot + * coexist. So if PSR2 selective fetch is supported then mark that + * FBC is not supported. + * TODO: Need a logic to decide between PSR2 and FBC Dirty rect */ - if (IS_DISPLAY_VER(display, 12, 14) && crtc_state->has_sel_update && - !crtc_state->has_panel_replay) { + if ((IS_DISPLAY_VER(display, 12, 14) || HAS_FBC_DIRTY_RECT(display)) && + crtc_state->has_sel_update && !crtc_state->has_panel_replay) { plane_state->no_fbc_reason = "PSR2 enabled"; return 0; } /* Wa_14016291713 */ if ((IS_DISPLAY_VER(display, 12, 13) || - IS_DISPLAY_VERx100_STEP(i915, 1400, STEP_A0, STEP_C0)) && + IS_DISPLAY_VERx100_STEP(display, 1400, STEP_A0, STEP_C0)) && crtc_state->has_psr && !crtc_state->has_panel_replay) { plane_state->no_fbc_reason = "PSR1 enabled (Wa_14016291713)"; return 0; @@ -1410,7 +1540,7 @@ static int intel_fbc_check_plane(struct intel_atomic_state *state, } /* WaFbcExceedCdClockThreshold:hsw,bdw */ - if (IS_HASWELL(i915) || IS_BROADWELL(i915)) { + if (display->platform.haswell || display->platform.broadwell) { const struct intel_cdclk_state *cdclk_state; cdclk_state = intel_atomic_get_cdclk_state(state); @@ -1547,6 +1677,8 @@ static void __intel_fbc_disable(struct intel_fbc *fbc) drm_dbg_kms(display->drm, "Disabling FBC on [PLANE:%d:%s]\n", plane->base.base.id, plane->base.name); + intel_fbc_invalidate_dirty_rect(fbc); + __intel_fbc_cleanup_cfb(fbc); fbc->state.plane = NULL; @@ -1614,14 +1746,14 @@ out: mutex_unlock(&fbc->lock); } -void intel_fbc_invalidate(struct drm_i915_private *i915, +void intel_fbc_invalidate(struct intel_display *display, unsigned int frontbuffer_bits, enum fb_op_origin origin) { struct intel_fbc *fbc; enum intel_fbc_id fbc_id; - for_each_intel_fbc(&i915->display, fbc, fbc_id) + for_each_intel_fbc(display, fbc, fbc_id) __intel_fbc_invalidate(fbc, frontbuffer_bits, origin); } @@ -1653,14 +1785,14 @@ out: mutex_unlock(&fbc->lock); } -void intel_fbc_flush(struct drm_i915_private *i915, +void intel_fbc_flush(struct intel_display *display, unsigned int frontbuffer_bits, enum fb_op_origin origin) { struct intel_fbc *fbc; enum intel_fbc_id fbc_id; - for_each_intel_fbc(&i915->display, fbc, fbc_id) + for_each_intel_fbc(display, fbc, fbc_id) __intel_fbc_flush(fbc, frontbuffer_bits, origin); } @@ -1732,6 +1864,9 @@ static void __intel_fbc_enable(struct intel_atomic_state *state, intel_fbc_update_state(state, crtc, plane); + if (HAS_FBC_DIRTY_RECT(display)) + intel_fbc_hw_intialize_dirty_rect(fbc, plane_state); + intel_fbc_program_workarounds(fbc); intel_fbc_program_cfb(fbc); } @@ -1897,15 +2032,13 @@ void intel_fbc_handle_fifo_underrun_irq(struct intel_display *display) */ static int intel_sanitize_fbc_option(struct intel_display *display) { - struct drm_i915_private *i915 = to_i915(display->drm); - if (display->params.enable_fbc >= 0) return !!display->params.enable_fbc; if (!HAS_FBC(display)) return 0; - if (IS_BROADWELL(i915) || DISPLAY_VER(display) >= 9) + if (display->platform.broadwell || DISPLAY_VER(display) >= 9) return 1; return 0; @@ -1919,7 +2052,6 @@ void intel_fbc_add_plane(struct intel_fbc *fbc, struct intel_plane *plane) static struct intel_fbc *intel_fbc_create(struct intel_display *display, enum intel_fbc_id fbc_id) { - struct drm_i915_private *i915 = to_i915(display->drm); struct intel_fbc *fbc; fbc = kzalloc(sizeof(*fbc), GFP_KERNEL); @@ -1937,7 +2069,7 @@ static struct intel_fbc *intel_fbc_create(struct intel_display *display, fbc->funcs = &snb_fbc_funcs; else if (DISPLAY_VER(display) == 5) fbc->funcs = &ilk_fbc_funcs; - else if (IS_G4X(i915)) + else if (display->platform.g4x) fbc->funcs = &g4x_fbc_funcs; else if (DISPLAY_VER(display) == 4) fbc->funcs = &i965_fbc_funcs; diff --git a/drivers/gpu/drm/i915/display/intel_fbc.h b/drivers/gpu/drm/i915/display/intel_fbc.h index ceae55458e14..0e715cb6b4e6 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.h +++ b/drivers/gpu/drm/i915/display/intel_fbc.h @@ -9,11 +9,11 @@ #include <linux/types.h> enum fb_op_origin; -struct drm_i915_private; struct intel_atomic_state; struct intel_crtc; struct intel_crtc_state; struct intel_display; +struct intel_dsb; struct intel_fbc; struct intel_plane; struct intel_plane_state; @@ -38,15 +38,19 @@ void intel_fbc_sanitize(struct intel_display *display); void intel_fbc_update(struct intel_atomic_state *state, struct intel_crtc *crtc); void intel_fbc_disable(struct intel_crtc *crtc); -void intel_fbc_invalidate(struct drm_i915_private *dev_priv, +void intel_fbc_invalidate(struct intel_display *display, unsigned int frontbuffer_bits, enum fb_op_origin origin); -void intel_fbc_flush(struct drm_i915_private *dev_priv, +void intel_fbc_flush(struct intel_display *display, unsigned int frontbuffer_bits, enum fb_op_origin origin); void intel_fbc_add_plane(struct intel_fbc *fbc, struct intel_plane *plane); void intel_fbc_handle_fifo_underrun_irq(struct intel_display *display); void intel_fbc_reset_underrun(struct intel_display *display); void intel_fbc_crtc_debugfs_add(struct intel_crtc *crtc); void intel_fbc_debugfs_register(struct intel_display *display); +void intel_fbc_prepare_dirty_rect(struct intel_atomic_state *state, + struct intel_crtc *crtc); +void intel_fbc_dirty_rect_update_noarm(struct intel_dsb *dsb, + struct intel_plane *plane); #endif /* __INTEL_FBC_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_fbc_regs.h b/drivers/gpu/drm/i915/display/intel_fbc_regs.h index ae0699c3c2fe..b1d0161a3196 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc_regs.h +++ b/drivers/gpu/drm/i915/display/intel_fbc_regs.h @@ -100,6 +100,15 @@ #define FBC_STRIDE_MASK REG_GENMASK(14, 0) #define FBC_STRIDE(x) REG_FIELD_PREP(FBC_STRIDE_MASK, (x)) +#define XE3_FBC_DIRTY_RECT(fbc_id) _MMIO_PIPE((fbc_id), 0x43230, 0x43270) +#define FBC_DIRTY_RECT_END_LINE_MASK REG_GENMASK(31, 16) +#define FBC_DIRTY_RECT_END_LINE(val) REG_FIELD_PREP(FBC_DIRTY_RECT_END_LINE_MASK, (val)) +#define FBC_DIRTY_RECT_START_LINE_MASK REG_GENMASK(15, 0) +#define FBC_DIRTY_RECT_START_LINE(val) REG_FIELD_PREP(FBC_DIRTY_RECT_START_LINE_MASK, (val)) + +#define XE3_FBC_DIRTY_CTL(fbc_id) _MMIO_PIPE((fbc_id), 0x43234, 0x43274) +#define FBC_DIRTY_RECT_EN REG_BIT(31) + #define ILK_FBC_RT_BASE _MMIO(0x2128) #define ILK_FBC_RT_VALID REG_BIT(0) #define SNB_FBC_FRONT_BUFFER REG_BIT(1) diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index 301b5fd301a2..adc19d5607de 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -37,14 +37,18 @@ #include <linux/tty.h> #include <linux/vga_switcheroo.h> +#include <drm/clients/drm_client_setup.h> #include <drm/drm_crtc.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_gem.h> #include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_managed.h> +#include <drm/drm_print.h> #include "i915_drv.h" +#include "i915_vma.h" #include "intel_bo.h" #include "intel_display_types.h" #include "intel_fb.h" @@ -54,24 +58,16 @@ #include "intel_frontbuffer.h" struct intel_fbdev { - struct drm_fb_helper helper; struct intel_framebuffer *fb; struct i915_vma *vma; unsigned long vma_flags; - int preferred_bpp; - - /* Whether or not fbdev hpd processing is temporarily suspended */ - bool hpd_suspended: 1; - /* Set when a hotplug was received while HPD processing was suspended */ - bool hpd_waiting: 1; - - /* Protects hpd_suspended */ - struct mutex hpd_lock; }; static struct intel_fbdev *to_intel_fbdev(struct drm_fb_helper *fb_helper) { - return container_of(fb_helper, struct intel_fbdev, helper); + struct drm_i915_private *i915 = to_i915(fb_helper->client.dev); + + return i915->display.fbdev.fbdev; } static struct intel_frontbuffer *to_frontbuffer(struct intel_fbdev *ifbdev) @@ -127,8 +123,8 @@ static int intel_fbdev_pan_display(struct fb_var_screeninfo *var, static int intel_fbdev_mmap(struct fb_info *info, struct vm_area_struct *vma) { - struct intel_fbdev *fbdev = to_intel_fbdev(info->par); - struct drm_gem_object *obj = drm_gem_fb_get_obj(&fbdev->fb->base, 0); + struct drm_fb_helper *fb_helper = info->par; + struct drm_gem_object *obj = drm_gem_fb_get_obj(fb_helper->fb, 0); return intel_bo_fb_mmap(obj, vma); } @@ -136,9 +132,9 @@ static int intel_fbdev_mmap(struct fb_info *info, struct vm_area_struct *vma) static void intel_fbdev_fb_destroy(struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; - struct intel_fbdev *ifbdev = container_of(fb_helper, struct intel_fbdev, helper); + struct intel_fbdev *ifbdev = to_intel_fbdev(fb_helper); - drm_fb_helper_fini(&ifbdev->helper); + drm_fb_helper_fini(fb_helper); /* * We rely on the object-free to release the VMA pinning for @@ -146,11 +142,11 @@ static void intel_fbdev_fb_destroy(struct fb_info *info) * trying to rectify all the possible error paths leading here. */ intel_fb_unpin_vma(ifbdev->vma, ifbdev->vma_flags); - drm_framebuffer_remove(&ifbdev->fb->base); + drm_framebuffer_remove(fb_helper->fb); drm_client_release(&fb_helper->client); - drm_fb_helper_unprepare(&ifbdev->helper); - kfree(ifbdev); + drm_fb_helper_unprepare(fb_helper); + kfree(fb_helper); } __diag_push(); @@ -170,8 +166,48 @@ static const struct fb_ops intelfb_ops = { __diag_pop(); -static int intelfb_create(struct drm_fb_helper *helper, - struct drm_fb_helper_surface_size *sizes) +static int intelfb_dirty(struct drm_fb_helper *helper, struct drm_clip_rect *clip) +{ + if (!(clip->x1 < clip->x2 && clip->y1 < clip->y2)) + return 0; + + if (helper->fb->funcs->dirty) + return helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1); + + return 0; +} + +static void intelfb_restore(struct drm_fb_helper *fb_helper) +{ + struct intel_fbdev *ifbdev = to_intel_fbdev(fb_helper); + + intel_fbdev_invalidate(ifbdev); +} + +static void intelfb_set_suspend(struct drm_fb_helper *fb_helper, bool suspend) +{ + struct fb_info *info = fb_helper->info; + + /* + * When resuming from hibernation, Linux restores the object's + * content from swap if the buffer is backed by shmemfs. If the + * object is stolen however, it will be full of whatever garbage + * was left in there. Clear it to zero in this case. + */ + if (!suspend && !intel_bo_is_shmem(intel_fb_bo(fb_helper->fb))) + memset_io(info->screen_base, 0, info->screen_size); + + fb_set_suspend(info, suspend); +} + +static const struct drm_fb_helper_funcs intel_fb_helper_funcs = { + .fb_dirty = intelfb_dirty, + .fb_restore = intelfb_restore, + .fb_set_suspend = intelfb_set_suspend, +}; + +int intel_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, + struct drm_fb_helper_surface_size *sizes) { struct intel_fbdev *ifbdev = to_intel_fbdev(helper); struct intel_framebuffer *fb = ifbdev->fb; @@ -185,12 +221,6 @@ static int intelfb_create(struct drm_fb_helper *helper, struct drm_gem_object *obj; int ret; - mutex_lock(&ifbdev->hpd_lock); - ret = ifbdev->hpd_suspended ? -EAGAIN : 0; - mutex_unlock(&ifbdev->hpd_lock); - if (ret) - return ret; - ifbdev->fb = NULL; if (fb && @@ -240,7 +270,8 @@ static int intelfb_create(struct drm_fb_helper *helper, goto out_unpin; } - ifbdev->helper.fb = &fb->base; + helper->funcs = &intel_fb_helper_funcs; + helper->fb = &fb->base; info->fbops = &intelfb_ops; @@ -250,7 +281,7 @@ static int intelfb_create(struct drm_fb_helper *helper, if (ret) goto out_unpin; - drm_fb_helper_fill_info(info, &ifbdev->helper, sizes); + drm_fb_helper_fill_info(info, dev->fb_helper, sizes); /* If the object is shmemfs backed, it will have given us zeroed pages. * If the object is stolen however, it will be full of whatever @@ -279,22 +310,6 @@ out_unlock: return ret; } -static int intelfb_dirty(struct drm_fb_helper *helper, struct drm_clip_rect *clip) -{ - if (!(clip->x1 < clip->x2 && clip->y1 < clip->y2)) - return 0; - - if (helper->fb->funcs->dirty) - return helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1); - - return 0; -} - -static const struct drm_fb_helper_funcs intel_fb_helper_funcs = { - .fb_probe = intelfb_create, - .fb_dirty = intelfb_dirty, -}; - /* * Build an intel_fbdev struct using a BIOS allocated framebuffer, if possible. * The core display code will have read out the current plane configuration, @@ -417,7 +432,6 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, goto out; } - ifbdev->preferred_bpp = fb->base.format->cpp[0] * 8; ifbdev->fb = fb; drm_framebuffer_get(&ifbdev->fb->base); @@ -448,251 +462,51 @@ out: return false; } -static void intel_fbdev_suspend_worker(struct work_struct *work) -{ - intel_fbdev_set_suspend(&container_of(work, - struct drm_i915_private, - display.fbdev.suspend_work)->drm, - FBINFO_STATE_RUNNING, - true); -} - -/* Suspends/resumes fbdev processing of incoming HPD events. When resuming HPD - * processing, fbdev will perform a full connector reprobe if a hotplug event - * was received while HPD was suspended. - */ -static void intel_fbdev_hpd_set_suspend(struct drm_i915_private *i915, int state) -{ - struct intel_fbdev *ifbdev = i915->display.fbdev.fbdev; - bool send_hpd = false; - - mutex_lock(&ifbdev->hpd_lock); - ifbdev->hpd_suspended = state == FBINFO_STATE_SUSPENDED; - send_hpd = !ifbdev->hpd_suspended && ifbdev->hpd_waiting; - ifbdev->hpd_waiting = false; - mutex_unlock(&ifbdev->hpd_lock); - - if (send_hpd) { - drm_dbg_kms(&i915->drm, "Handling delayed fbcon HPD event\n"); - drm_fb_helper_hotplug_event(&ifbdev->helper); - } -} - -void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous) -{ - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_fbdev *ifbdev = dev_priv->display.fbdev.fbdev; - struct fb_info *info; - - if (!ifbdev) - return; - - if (drm_WARN_ON(&dev_priv->drm, !HAS_DISPLAY(dev_priv))) - return; - - if (!ifbdev->vma) - goto set_suspend; - - info = ifbdev->helper.info; - - if (synchronous) { - /* Flush any pending work to turn the console on, and then - * wait to turn it off. It must be synchronous as we are - * about to suspend or unload the driver. - * - * Note that from within the work-handler, we cannot flush - * ourselves, so only flush outstanding work upon suspend! - */ - if (state != FBINFO_STATE_RUNNING) - flush_work(&dev_priv->display.fbdev.suspend_work); - - console_lock(); - } else { - /* - * The console lock can be pretty contented on resume due - * to all the printk activity. Try to keep it out of the hot - * path of resume if possible. - */ - drm_WARN_ON(dev, state != FBINFO_STATE_RUNNING); - if (!console_trylock()) { - /* Don't block our own workqueue as this can - * be run in parallel with other i915.ko tasks. - */ - queue_work(dev_priv->unordered_wq, - &dev_priv->display.fbdev.suspend_work); - return; - } - } - - /* On resume from hibernation: If the object is shmemfs backed, it has - * been restored from swap. If the object is stolen however, it will be - * full of whatever garbage was left in there. - */ - if (state == FBINFO_STATE_RUNNING && - !intel_bo_is_shmem(intel_fb_bo(&ifbdev->fb->base))) - memset_io(info->screen_base, 0, info->screen_size); - - drm_fb_helper_set_suspend(&ifbdev->helper, state); - console_unlock(); - -set_suspend: - intel_fbdev_hpd_set_suspend(dev_priv, state); -} - -static int intel_fbdev_output_poll_changed(struct drm_device *dev) +static unsigned int intel_fbdev_color_mode(const struct drm_format_info *info) { - struct intel_fbdev *ifbdev = to_i915(dev)->display.fbdev.fbdev; - bool send_hpd; - - if (!ifbdev) - return -EINVAL; - - mutex_lock(&ifbdev->hpd_lock); - send_hpd = !ifbdev->hpd_suspended; - ifbdev->hpd_waiting = true; - mutex_unlock(&ifbdev->hpd_lock); - - if (send_hpd && (ifbdev->vma || ifbdev->helper.deferred_setup)) - drm_fb_helper_hotplug_event(&ifbdev->helper); + unsigned int bpp; - return 0; -} - -static int intel_fbdev_restore_mode(struct drm_i915_private *dev_priv) -{ - struct intel_fbdev *ifbdev = dev_priv->display.fbdev.fbdev; - int ret; - - if (!ifbdev) - return -EINVAL; - - if (!ifbdev->vma) - return -ENOMEM; - - ret = drm_fb_helper_restore_fbdev_mode_unlocked(&ifbdev->helper); - if (ret) - return ret; - - intel_fbdev_invalidate(ifbdev); - - return 0; -} - -/* - * Fbdev client and struct drm_client_funcs - */ + if (!info->depth || info->num_planes != 1 || info->has_alpha || info->is_yuv) + return 0; -static void intel_fbdev_client_unregister(struct drm_client_dev *client) -{ - struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client); - struct drm_device *dev = fb_helper->dev; - struct pci_dev *pdev = to_pci_dev(dev->dev); + bpp = drm_format_info_bpp(info, 0); - if (fb_helper->info) { - vga_switcheroo_client_fb_set(pdev, NULL); - drm_fb_helper_unregister_info(fb_helper); - } else { - drm_fb_helper_unprepare(fb_helper); - drm_client_release(&fb_helper->client); - kfree(fb_helper); + switch (bpp) { + case 16: + return info->depth; // 15 or 16 + default: + return bpp; } } -static int intel_fbdev_client_restore(struct drm_client_dev *client) -{ - struct drm_i915_private *dev_priv = to_i915(client->dev); - int ret; - - ret = intel_fbdev_restore_mode(dev_priv); - if (ret) - return ret; - - vga_switcheroo_process_delayed_switch(); - - return 0; -} - -static int intel_fbdev_client_hotplug(struct drm_client_dev *client) -{ - struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client); - struct drm_device *dev = client->dev; - struct pci_dev *pdev = to_pci_dev(dev->dev); - int ret; - - if (dev->fb_helper) - return intel_fbdev_output_poll_changed(dev); - - ret = drm_fb_helper_init(dev, fb_helper); - if (ret) - goto err_drm_err; - - ret = drm_fb_helper_initial_config(fb_helper); - if (ret) - goto err_drm_fb_helper_fini; - - vga_switcheroo_client_fb_set(pdev, fb_helper->info); - - return 0; - -err_drm_fb_helper_fini: - drm_fb_helper_fini(fb_helper); -err_drm_err: - drm_err(dev, "Failed to setup i915 fbdev emulation (ret=%d)\n", ret); - return ret; -} - -static const struct drm_client_funcs intel_fbdev_client_funcs = { - .owner = THIS_MODULE, - .unregister = intel_fbdev_client_unregister, - .restore = intel_fbdev_client_restore, - .hotplug = intel_fbdev_client_hotplug, -}; - void intel_fbdev_setup(struct drm_i915_private *i915) { struct drm_device *dev = &i915->drm; struct intel_fbdev *ifbdev; - int ret; + unsigned int preferred_bpp = 0; if (!HAS_DISPLAY(i915)) return; - ifbdev = kzalloc(sizeof(*ifbdev), GFP_KERNEL); + ifbdev = drmm_kzalloc(dev, sizeof(*ifbdev), GFP_KERNEL); if (!ifbdev) return; - drm_fb_helper_prepare(dev, &ifbdev->helper, 32, &intel_fb_helper_funcs); i915->display.fbdev.fbdev = ifbdev; - INIT_WORK(&i915->display.fbdev.suspend_work, intel_fbdev_suspend_worker); - mutex_init(&ifbdev->hpd_lock); if (intel_fbdev_init_bios(dev, ifbdev)) - ifbdev->helper.preferred_bpp = ifbdev->preferred_bpp; - else - ifbdev->preferred_bpp = ifbdev->helper.preferred_bpp; - - ret = drm_client_init(dev, &ifbdev->helper.client, "intel-fbdev", - &intel_fbdev_client_funcs); - if (ret) { - drm_err(dev, "Failed to register client: %d\n", ret); - goto err_drm_fb_helper_unprepare; - } - - drm_client_register(&ifbdev->helper.client); - - return; + preferred_bpp = intel_fbdev_color_mode(ifbdev->fb->base.format); + if (!preferred_bpp) + preferred_bpp = 32; -err_drm_fb_helper_unprepare: - drm_fb_helper_unprepare(&ifbdev->helper); - mutex_destroy(&ifbdev->hpd_lock); - kfree(ifbdev); + drm_client_setup_with_color_mode(dev, preferred_bpp); } struct intel_framebuffer *intel_fbdev_framebuffer(struct intel_fbdev *fbdev) { - if (!fbdev || !fbdev->helper.fb) + if (!fbdev) return NULL; - return to_intel_framebuffer(fbdev->helper.fb); + return fbdev->fb; } struct i915_vma *intel_fbdev_vma_pointer(struct intel_fbdev *fbdev) diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.h b/drivers/gpu/drm/i915/display/intel_fbdev.h index 24a3434558cb..ca2c8c438f02 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.h +++ b/drivers/gpu/drm/i915/display/intel_fbdev.h @@ -6,28 +6,27 @@ #ifndef __INTEL_FBDEV_H__ #define __INTEL_FBDEV_H__ -#include <linux/types.h> - -struct drm_device; +struct drm_fb_helper; +struct drm_fb_helper_surface_size; struct drm_i915_private; struct intel_fbdev; struct intel_framebuffer; #ifdef CONFIG_DRM_FBDEV_EMULATION +int intel_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, + struct drm_fb_helper_surface_size *sizes); +#define INTEL_FBDEV_DRIVER_OPS \ + .fbdev_probe = intel_fbdev_driver_fbdev_probe void intel_fbdev_setup(struct drm_i915_private *dev_priv); -void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous); struct intel_framebuffer *intel_fbdev_framebuffer(struct intel_fbdev *fbdev); struct i915_vma *intel_fbdev_vma_pointer(struct intel_fbdev *fbdev); #else +#define INTEL_FBDEV_DRIVER_OPS \ + .fbdev_probe = NULL static inline void intel_fbdev_setup(struct drm_i915_private *dev_priv) { } - -static inline void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous) -{ -} - static inline struct intel_framebuffer *intel_fbdev_framebuffer(struct intel_fbdev *fbdev) { return NULL; diff --git a/drivers/gpu/drm/i915/display/intel_fdi.c b/drivers/gpu/drm/i915/display/intel_fdi.c index 024d0c7e0a88..40deee0769ae 100644 --- a/drivers/gpu/drm/i915/display/intel_fdi.c +++ b/drivers/gpu/drm/i915/display/intel_fdi.c @@ -24,10 +24,9 @@ struct intel_fdi_funcs { const struct intel_crtc_state *crtc_state); }; -static void assert_fdi_tx(struct drm_i915_private *dev_priv, +static void assert_fdi_tx(struct intel_display *display, enum pipe pipe, bool state) { - struct intel_display *display = &dev_priv->display; bool cur_state; if (HAS_DDI(display)) { @@ -48,20 +47,19 @@ static void assert_fdi_tx(struct drm_i915_private *dev_priv, str_on_off(state), str_on_off(cur_state)); } -void assert_fdi_tx_enabled(struct drm_i915_private *i915, enum pipe pipe) +void assert_fdi_tx_enabled(struct intel_display *display, enum pipe pipe) { - assert_fdi_tx(i915, pipe, true); + assert_fdi_tx(display, pipe, true); } -void assert_fdi_tx_disabled(struct drm_i915_private *i915, enum pipe pipe) +void assert_fdi_tx_disabled(struct intel_display *display, enum pipe pipe) { - assert_fdi_tx(i915, pipe, false); + assert_fdi_tx(display, pipe, false); } -static void assert_fdi_rx(struct drm_i915_private *dev_priv, +static void assert_fdi_rx(struct intel_display *display, enum pipe pipe, bool state) { - struct intel_display *display = &dev_priv->display; bool cur_state; cur_state = intel_de_read(display, FDI_RX_CTL(pipe)) & FDI_RX_ENABLE; @@ -70,18 +68,17 @@ static void assert_fdi_rx(struct drm_i915_private *dev_priv, str_on_off(state), str_on_off(cur_state)); } -void assert_fdi_rx_enabled(struct drm_i915_private *i915, enum pipe pipe) +void assert_fdi_rx_enabled(struct intel_display *display, enum pipe pipe) { - assert_fdi_rx(i915, pipe, true); + assert_fdi_rx(display, pipe, true); } -void assert_fdi_rx_disabled(struct drm_i915_private *i915, enum pipe pipe) +void assert_fdi_rx_disabled(struct intel_display *display, enum pipe pipe) { - assert_fdi_rx(i915, pipe, false); + assert_fdi_rx(display, pipe, false); } -void assert_fdi_tx_pll_enabled(struct intel_display *display, - enum pipe pipe) +void assert_fdi_tx_pll_enabled(struct intel_display *display, enum pipe pipe) { bool cur_state; @@ -122,9 +119,9 @@ void assert_fdi_rx_pll_disabled(struct intel_display *display, enum pipe pipe) void intel_fdi_link_train(struct intel_crtc *crtc, const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); - dev_priv->display.funcs.fdi->fdi_link_train(crtc, crtc_state); + display->funcs.fdi->fdi_link_train(crtc, crtc_state); } /** @@ -141,12 +138,11 @@ void intel_fdi_link_train(struct intel_crtc *crtc, int intel_fdi_add_affected_crtcs(struct intel_atomic_state *state) { struct intel_display *display = to_intel_display(state); - struct drm_i915_private *i915 = to_i915(state->base.dev); const struct intel_crtc_state *old_crtc_state; const struct intel_crtc_state *new_crtc_state; struct intel_crtc *crtc; - if (!IS_IVYBRIDGE(i915) || INTEL_NUM_PIPES(i915) != 3) + if (!display->platform.ivybridge || INTEL_NUM_PIPES(display) != 3) return 0; crtc = intel_crtc_for_pipe(display, PIPE_C); @@ -184,31 +180,29 @@ static int pipe_required_fdi_lanes(struct intel_crtc_state *crtc_state) return 0; } -static int ilk_check_fdi_lanes(struct drm_device *dev, enum pipe pipe, +static int ilk_check_fdi_lanes(struct intel_display *display, enum pipe pipe, struct intel_crtc_state *pipe_config, enum pipe *pipe_to_reduce) { - struct intel_display *display = to_intel_display(dev); - struct drm_i915_private *dev_priv = to_i915(dev); struct drm_atomic_state *state = pipe_config->uapi.state; struct intel_crtc *other_crtc; struct intel_crtc_state *other_crtc_state; *pipe_to_reduce = pipe; - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "checking fdi config on pipe %c, lanes %i\n", pipe_name(pipe), pipe_config->fdi_lanes); if (pipe_config->fdi_lanes > 4) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "invalid fdi lane config on pipe %c: %i lanes\n", pipe_name(pipe), pipe_config->fdi_lanes); return -EINVAL; } - if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { + if (display->platform.haswell || display->platform.broadwell) { if (pipe_config->fdi_lanes > 2) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "only 2 lanes on haswell, required: %i lanes\n", pipe_config->fdi_lanes); return -EINVAL; @@ -217,7 +211,7 @@ static int ilk_check_fdi_lanes(struct drm_device *dev, enum pipe pipe, } } - if (INTEL_NUM_PIPES(dev_priv) == 2) + if (INTEL_NUM_PIPES(display) == 2) return 0; /* Ivybridge 3 pipe is really complicated */ @@ -235,7 +229,7 @@ static int ilk_check_fdi_lanes(struct drm_device *dev, enum pipe pipe, return PTR_ERR(other_crtc_state); if (pipe_required_fdi_lanes(other_crtc_state) > 0) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "invalid shared fdi lane config on pipe %c: %i lanes\n", pipe_name(pipe), pipe_config->fdi_lanes); return -EINVAL; @@ -243,7 +237,7 @@ static int ilk_check_fdi_lanes(struct drm_device *dev, enum pipe pipe, return 0; case PIPE_C: if (pipe_config->fdi_lanes > 2) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "only 2 lanes on pipe %c: required %i lanes\n", pipe_name(pipe), pipe_config->fdi_lanes); return -EINVAL; @@ -256,7 +250,7 @@ static int ilk_check_fdi_lanes(struct drm_device *dev, enum pipe pipe, return PTR_ERR(other_crtc_state); if (pipe_required_fdi_lanes(other_crtc_state) > 2) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "fdi link B uses too many lanes to enable link C\n"); *pipe_to_reduce = PIPE_B; @@ -270,29 +264,30 @@ static int ilk_check_fdi_lanes(struct drm_device *dev, enum pipe pipe, } } -void intel_fdi_pll_freq_update(struct drm_i915_private *i915) +void intel_fdi_pll_freq_update(struct intel_display *display) { - if (IS_IRONLAKE(i915)) { - u32 fdi_pll_clk = - intel_de_read(i915, FDI_PLL_BIOS_0) & FDI_PLL_FB_CLOCK_MASK; + if (display->platform.ironlake) { + u32 fdi_pll_clk; - i915->display.fdi.pll_freq = (fdi_pll_clk + 2) * 10000; - } else if (IS_SANDYBRIDGE(i915) || IS_IVYBRIDGE(i915)) { - i915->display.fdi.pll_freq = 270000; + fdi_pll_clk = intel_de_read(display, FDI_PLL_BIOS_0) & FDI_PLL_FB_CLOCK_MASK; + + display->fdi.pll_freq = (fdi_pll_clk + 2) * 10000; + } else if (display->platform.sandybridge || display->platform.ivybridge) { + display->fdi.pll_freq = 270000; } else { return; } - drm_dbg(&i915->drm, "FDI PLL freq=%d\n", i915->display.fdi.pll_freq); + drm_dbg(display->drm, "FDI PLL freq=%d\n", display->fdi.pll_freq); } -int intel_fdi_link_freq(struct drm_i915_private *i915, +int intel_fdi_link_freq(struct intel_display *display, const struct intel_crtc_state *pipe_config) { - if (HAS_DDI(i915)) + if (HAS_DDI(display)) return pipe_config->port_clock; /* SPLL */ else - return i915->display.fdi.pll_freq; + return display->fdi.pll_freq; } /** @@ -326,8 +321,7 @@ bool intel_fdi_compute_pipe_bpp(struct intel_crtc_state *crtc_state) int ilk_fdi_compute_config(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config) { - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *i915 = to_i915(dev); + struct intel_display *display = to_intel_display(crtc); const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; int lane, link_bw, fdi_dotclock; @@ -338,7 +332,7 @@ int ilk_fdi_compute_config(struct intel_crtc *crtc, * Hence the bw of each lane in terms of the mode signal * is: */ - link_bw = intel_fdi_link_freq(i915, pipe_config); + link_bw = intel_fdi_link_freq(display, pipe_config); fdi_dotclock = adjusted_mode->crtc_clock; @@ -361,11 +355,11 @@ static int intel_fdi_atomic_check_bw(struct intel_atomic_state *state, struct intel_crtc_state *pipe_config, struct intel_link_bw_limits *limits) { - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); enum pipe pipe_to_reduce; int ret; - ret = ilk_check_fdi_lanes(&i915->drm, crtc->pipe, pipe_config, + ret = ilk_check_fdi_lanes(display, crtc->pipe, pipe_config, &pipe_to_reduce); if (ret != -EINVAL) return ret; @@ -418,48 +412,48 @@ int intel_fdi_atomic_check_link(struct intel_atomic_state *state, return 0; } -static void cpt_set_fdi_bc_bifurcation(struct drm_i915_private *dev_priv, bool enable) +static void cpt_set_fdi_bc_bifurcation(struct intel_display *display, bool enable) { u32 temp; - temp = intel_de_read(dev_priv, SOUTH_CHICKEN1); + temp = intel_de_read(display, SOUTH_CHICKEN1); if (!!(temp & FDI_BC_BIFURCATION_SELECT) == enable) return; - drm_WARN_ON(&dev_priv->drm, - intel_de_read(dev_priv, FDI_RX_CTL(PIPE_B)) & + drm_WARN_ON(display->drm, + intel_de_read(display, FDI_RX_CTL(PIPE_B)) & FDI_RX_ENABLE); - drm_WARN_ON(&dev_priv->drm, - intel_de_read(dev_priv, FDI_RX_CTL(PIPE_C)) & + drm_WARN_ON(display->drm, + intel_de_read(display, FDI_RX_CTL(PIPE_C)) & FDI_RX_ENABLE); temp &= ~FDI_BC_BIFURCATION_SELECT; if (enable) temp |= FDI_BC_BIFURCATION_SELECT; - drm_dbg_kms(&dev_priv->drm, "%sabling fdi C rx\n", + drm_dbg_kms(display->drm, "%sabling fdi C rx\n", enable ? "en" : "dis"); - intel_de_write(dev_priv, SOUTH_CHICKEN1, temp); - intel_de_posting_read(dev_priv, SOUTH_CHICKEN1); + intel_de_write(display, SOUTH_CHICKEN1, temp); + intel_de_posting_read(display, SOUTH_CHICKEN1); } static void ivb_update_fdi_bc_bifurcation(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); switch (crtc->pipe) { case PIPE_A: break; case PIPE_B: if (crtc_state->fdi_lanes > 2) - cpt_set_fdi_bc_bifurcation(dev_priv, false); + cpt_set_fdi_bc_bifurcation(display, false); else - cpt_set_fdi_bc_bifurcation(dev_priv, true); + cpt_set_fdi_bc_bifurcation(display, true); break; case PIPE_C: - cpt_set_fdi_bc_bifurcation(dev_priv, true); + cpt_set_fdi_bc_bifurcation(display, true); break; default: @@ -469,26 +463,26 @@ static void ivb_update_fdi_bc_bifurcation(const struct intel_crtc_state *crtc_st void intel_fdi_normal_train(struct intel_crtc *crtc) { - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_display *display = to_intel_display(crtc); + struct drm_i915_private *dev_priv = to_i915(display->drm); enum pipe pipe = crtc->pipe; i915_reg_t reg; u32 temp; /* enable normal train */ reg = FDI_TX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); - if (IS_IVYBRIDGE(dev_priv)) { + temp = intel_de_read(display, reg); + if (display->platform.ivybridge) { temp &= ~FDI_LINK_TRAIN_NONE_IVB; temp |= FDI_LINK_TRAIN_NONE_IVB | FDI_TX_ENHANCE_FRAME_ENABLE; } else { temp &= ~FDI_LINK_TRAIN_NONE; temp |= FDI_LINK_TRAIN_NONE | FDI_TX_ENHANCE_FRAME_ENABLE; } - intel_de_write(dev_priv, reg, temp); + intel_de_write(display, reg, temp); reg = FDI_RX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); if (HAS_PCH_CPT(dev_priv)) { temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT; temp |= FDI_LINK_TRAIN_NORMAL_CPT; @@ -496,15 +490,15 @@ void intel_fdi_normal_train(struct intel_crtc *crtc) temp &= ~FDI_LINK_TRAIN_NONE; temp |= FDI_LINK_TRAIN_NONE; } - intel_de_write(dev_priv, reg, temp | FDI_RX_ENHANCE_FRAME_ENABLE); + intel_de_write(display, reg, temp | FDI_RX_ENHANCE_FRAME_ENABLE); /* wait one idle pattern time */ - intel_de_posting_read(dev_priv, reg); + intel_de_posting_read(display, reg); udelay(1000); /* IVB wants error correction enabled */ - if (IS_IVYBRIDGE(dev_priv)) - intel_de_rmw(dev_priv, reg, 0, FDI_FS_ERRC_ENABLE | FDI_FE_ERRC_ENABLE); + if (display->platform.ivybridge) + intel_de_rmw(display, reg, 0, FDI_FS_ERRC_ENABLE | FDI_FE_ERRC_ENABLE); } /* The FDI link training functions for ILK/Ibexpeak. */ @@ -512,8 +506,6 @@ static void ilk_fdi_link_train(struct intel_crtc *crtc, const struct intel_crtc_state *crtc_state) { struct intel_display *display = to_intel_display(crtc); - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); enum pipe pipe = crtc->pipe; i915_reg_t reg; u32 temp, tries; @@ -522,8 +514,8 @@ static void ilk_fdi_link_train(struct intel_crtc *crtc, * Write the TU size bits before fdi link training, so that error * detection works. */ - intel_de_write(dev_priv, FDI_RX_TUSIZE1(pipe), - intel_de_read(dev_priv, PIPE_DATA_M1(dev_priv, pipe)) & TU_SIZE_MASK); + intel_de_write(display, FDI_RX_TUSIZE1(pipe), + intel_de_read(display, PIPE_DATA_M1(display, pipe)) & TU_SIZE_MASK); /* FDI needs bits from pipe first */ assert_transcoder_enabled(display, crtc_state->cpu_transcoder); @@ -531,75 +523,75 @@ static void ilk_fdi_link_train(struct intel_crtc *crtc, /* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit for train result */ reg = FDI_RX_IMR(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp &= ~FDI_RX_SYMBOL_LOCK; temp &= ~FDI_RX_BIT_LOCK; - intel_de_write(dev_priv, reg, temp); - intel_de_read(dev_priv, reg); + intel_de_write(display, reg, temp); + intel_de_read(display, reg); udelay(150); /* enable CPU FDI TX and PCH FDI RX */ reg = FDI_TX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp &= ~FDI_DP_PORT_WIDTH_MASK; temp |= FDI_DP_PORT_WIDTH(crtc_state->fdi_lanes); temp &= ~FDI_LINK_TRAIN_NONE; temp |= FDI_LINK_TRAIN_PATTERN_1; - intel_de_write(dev_priv, reg, temp | FDI_TX_ENABLE); + intel_de_write(display, reg, temp | FDI_TX_ENABLE); reg = FDI_RX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp &= ~FDI_LINK_TRAIN_NONE; temp |= FDI_LINK_TRAIN_PATTERN_1; - intel_de_write(dev_priv, reg, temp | FDI_RX_ENABLE); + intel_de_write(display, reg, temp | FDI_RX_ENABLE); - intel_de_posting_read(dev_priv, reg); + intel_de_posting_read(display, reg); udelay(150); /* Ironlake workaround, enable clock pointer after FDI enable*/ - intel_de_write(dev_priv, FDI_RX_CHICKEN(pipe), + intel_de_write(display, FDI_RX_CHICKEN(pipe), FDI_RX_PHASE_SYNC_POINTER_OVR); - intel_de_write(dev_priv, FDI_RX_CHICKEN(pipe), + intel_de_write(display, FDI_RX_CHICKEN(pipe), FDI_RX_PHASE_SYNC_POINTER_OVR | FDI_RX_PHASE_SYNC_POINTER_EN); reg = FDI_RX_IIR(pipe); for (tries = 0; tries < 5; tries++) { - temp = intel_de_read(dev_priv, reg); - drm_dbg_kms(&dev_priv->drm, "FDI_RX_IIR 0x%x\n", temp); + temp = intel_de_read(display, reg); + drm_dbg_kms(display->drm, "FDI_RX_IIR 0x%x\n", temp); if ((temp & FDI_RX_BIT_LOCK)) { - drm_dbg_kms(&dev_priv->drm, "FDI train 1 done.\n"); - intel_de_write(dev_priv, reg, temp | FDI_RX_BIT_LOCK); + drm_dbg_kms(display->drm, "FDI train 1 done.\n"); + intel_de_write(display, reg, temp | FDI_RX_BIT_LOCK); break; } } if (tries == 5) - drm_err(&dev_priv->drm, "FDI train 1 fail!\n"); + drm_err(display->drm, "FDI train 1 fail!\n"); /* Train 2 */ - intel_de_rmw(dev_priv, FDI_TX_CTL(pipe), + intel_de_rmw(display, FDI_TX_CTL(pipe), FDI_LINK_TRAIN_NONE, FDI_LINK_TRAIN_PATTERN_2); - intel_de_rmw(dev_priv, FDI_RX_CTL(pipe), + intel_de_rmw(display, FDI_RX_CTL(pipe), FDI_LINK_TRAIN_NONE, FDI_LINK_TRAIN_PATTERN_2); - intel_de_posting_read(dev_priv, FDI_RX_CTL(pipe)); + intel_de_posting_read(display, FDI_RX_CTL(pipe)); udelay(150); reg = FDI_RX_IIR(pipe); for (tries = 0; tries < 5; tries++) { - temp = intel_de_read(dev_priv, reg); - drm_dbg_kms(&dev_priv->drm, "FDI_RX_IIR 0x%x\n", temp); + temp = intel_de_read(display, reg); + drm_dbg_kms(display->drm, "FDI_RX_IIR 0x%x\n", temp); if (temp & FDI_RX_SYMBOL_LOCK) { - intel_de_write(dev_priv, reg, + intel_de_write(display, reg, temp | FDI_RX_SYMBOL_LOCK); - drm_dbg_kms(&dev_priv->drm, "FDI train 2 done.\n"); + drm_dbg_kms(display->drm, "FDI train 2 done.\n"); break; } } if (tries == 5) - drm_err(&dev_priv->drm, "FDI train 2 fail!\n"); + drm_err(display->drm, "FDI train 2 fail!\n"); - drm_dbg_kms(&dev_priv->drm, "FDI train done\n"); + drm_dbg_kms(display->drm, "FDI train done\n"); } @@ -614,8 +606,8 @@ static const int snb_b_fdi_train_param[] = { static void gen6_fdi_link_train(struct intel_crtc *crtc, const struct intel_crtc_state *crtc_state) { - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_display *display = to_intel_display(crtc); + struct drm_i915_private *dev_priv = to_i915(display->drm); enum pipe pipe = crtc->pipe; i915_reg_t reg; u32 temp, i, retry; @@ -624,23 +616,23 @@ static void gen6_fdi_link_train(struct intel_crtc *crtc, * Write the TU size bits before fdi link training, so that error * detection works. */ - intel_de_write(dev_priv, FDI_RX_TUSIZE1(pipe), - intel_de_read(dev_priv, PIPE_DATA_M1(dev_priv, pipe)) & TU_SIZE_MASK); + intel_de_write(display, FDI_RX_TUSIZE1(pipe), + intel_de_read(display, PIPE_DATA_M1(display, pipe)) & TU_SIZE_MASK); /* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit for train result */ reg = FDI_RX_IMR(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp &= ~FDI_RX_SYMBOL_LOCK; temp &= ~FDI_RX_BIT_LOCK; - intel_de_write(dev_priv, reg, temp); + intel_de_write(display, reg, temp); - intel_de_posting_read(dev_priv, reg); + intel_de_posting_read(display, reg); udelay(150); /* enable CPU FDI TX and PCH FDI RX */ reg = FDI_TX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp &= ~FDI_DP_PORT_WIDTH_MASK; temp |= FDI_DP_PORT_WIDTH(crtc_state->fdi_lanes); temp &= ~FDI_LINK_TRAIN_NONE; @@ -648,13 +640,13 @@ static void gen6_fdi_link_train(struct intel_crtc *crtc, temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK; /* SNB-B */ temp |= FDI_LINK_TRAIN_400MV_0DB_SNB_B; - intel_de_write(dev_priv, reg, temp | FDI_TX_ENABLE); + intel_de_write(display, reg, temp | FDI_TX_ENABLE); - intel_de_write(dev_priv, FDI_RX_MISC(pipe), + intel_de_write(display, FDI_RX_MISC(pipe), FDI_RX_TP1_TO_TP2_48 | FDI_RX_FDI_DELAY_90); reg = FDI_RX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); if (HAS_PCH_CPT(dev_priv)) { temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT; temp |= FDI_LINK_TRAIN_PATTERN_1_CPT; @@ -662,25 +654,25 @@ static void gen6_fdi_link_train(struct intel_crtc *crtc, temp &= ~FDI_LINK_TRAIN_NONE; temp |= FDI_LINK_TRAIN_PATTERN_1; } - intel_de_write(dev_priv, reg, temp | FDI_RX_ENABLE); + intel_de_write(display, reg, temp | FDI_RX_ENABLE); - intel_de_posting_read(dev_priv, reg); + intel_de_posting_read(display, reg); udelay(150); for (i = 0; i < 4; i++) { - intel_de_rmw(dev_priv, FDI_TX_CTL(pipe), + intel_de_rmw(display, FDI_TX_CTL(pipe), FDI_LINK_TRAIN_VOL_EMP_MASK, snb_b_fdi_train_param[i]); - intel_de_posting_read(dev_priv, FDI_TX_CTL(pipe)); + intel_de_posting_read(display, FDI_TX_CTL(pipe)); udelay(500); for (retry = 0; retry < 5; retry++) { reg = FDI_RX_IIR(pipe); - temp = intel_de_read(dev_priv, reg); - drm_dbg_kms(&dev_priv->drm, "FDI_RX_IIR 0x%x\n", temp); + temp = intel_de_read(display, reg); + drm_dbg_kms(display->drm, "FDI_RX_IIR 0x%x\n", temp); if (temp & FDI_RX_BIT_LOCK) { - intel_de_write(dev_priv, reg, + intel_de_write(display, reg, temp | FDI_RX_BIT_LOCK); - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "FDI train 1 done.\n"); break; } @@ -690,22 +682,22 @@ static void gen6_fdi_link_train(struct intel_crtc *crtc, break; } if (i == 4) - drm_err(&dev_priv->drm, "FDI train 1 fail!\n"); + drm_err(display->drm, "FDI train 1 fail!\n"); /* Train 2 */ reg = FDI_TX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp &= ~FDI_LINK_TRAIN_NONE; temp |= FDI_LINK_TRAIN_PATTERN_2; - if (IS_SANDYBRIDGE(dev_priv)) { + if (display->platform.sandybridge) { temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK; /* SNB-B */ temp |= FDI_LINK_TRAIN_400MV_0DB_SNB_B; } - intel_de_write(dev_priv, reg, temp); + intel_de_write(display, reg, temp); reg = FDI_RX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); if (HAS_PCH_CPT(dev_priv)) { temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT; temp |= FDI_LINK_TRAIN_PATTERN_2_CPT; @@ -713,25 +705,25 @@ static void gen6_fdi_link_train(struct intel_crtc *crtc, temp &= ~FDI_LINK_TRAIN_NONE; temp |= FDI_LINK_TRAIN_PATTERN_2; } - intel_de_write(dev_priv, reg, temp); + intel_de_write(display, reg, temp); - intel_de_posting_read(dev_priv, reg); + intel_de_posting_read(display, reg); udelay(150); for (i = 0; i < 4; i++) { - intel_de_rmw(dev_priv, FDI_TX_CTL(pipe), + intel_de_rmw(display, FDI_TX_CTL(pipe), FDI_LINK_TRAIN_VOL_EMP_MASK, snb_b_fdi_train_param[i]); - intel_de_posting_read(dev_priv, FDI_TX_CTL(pipe)); + intel_de_posting_read(display, FDI_TX_CTL(pipe)); udelay(500); for (retry = 0; retry < 5; retry++) { reg = FDI_RX_IIR(pipe); - temp = intel_de_read(dev_priv, reg); - drm_dbg_kms(&dev_priv->drm, "FDI_RX_IIR 0x%x\n", temp); + temp = intel_de_read(display, reg); + drm_dbg_kms(display->drm, "FDI_RX_IIR 0x%x\n", temp); if (temp & FDI_RX_SYMBOL_LOCK) { - intel_de_write(dev_priv, reg, + intel_de_write(display, reg, temp | FDI_RX_SYMBOL_LOCK); - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "FDI train 2 done.\n"); break; } @@ -741,17 +733,16 @@ static void gen6_fdi_link_train(struct intel_crtc *crtc, break; } if (i == 4) - drm_err(&dev_priv->drm, "FDI train 2 fail!\n"); + drm_err(display->drm, "FDI train 2 fail!\n"); - drm_dbg_kms(&dev_priv->drm, "FDI train done.\n"); + drm_dbg_kms(display->drm, "FDI train done.\n"); } /* Manual link training for Ivy Bridge A0 parts */ static void ivb_manual_fdi_link_train(struct intel_crtc *crtc, const struct intel_crtc_state *crtc_state) { - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_display *display = to_intel_display(crtc); enum pipe pipe = crtc->pipe; i915_reg_t reg; u32 temp, i, j; @@ -762,72 +753,72 @@ static void ivb_manual_fdi_link_train(struct intel_crtc *crtc, * Write the TU size bits before fdi link training, so that error * detection works. */ - intel_de_write(dev_priv, FDI_RX_TUSIZE1(pipe), - intel_de_read(dev_priv, PIPE_DATA_M1(dev_priv, pipe)) & TU_SIZE_MASK); + intel_de_write(display, FDI_RX_TUSIZE1(pipe), + intel_de_read(display, PIPE_DATA_M1(display, pipe)) & TU_SIZE_MASK); /* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit for train result */ reg = FDI_RX_IMR(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp &= ~FDI_RX_SYMBOL_LOCK; temp &= ~FDI_RX_BIT_LOCK; - intel_de_write(dev_priv, reg, temp); + intel_de_write(display, reg, temp); - intel_de_posting_read(dev_priv, reg); + intel_de_posting_read(display, reg); udelay(150); - drm_dbg_kms(&dev_priv->drm, "FDI_RX_IIR before link train 0x%x\n", - intel_de_read(dev_priv, FDI_RX_IIR(pipe))); + drm_dbg_kms(display->drm, "FDI_RX_IIR before link train 0x%x\n", + intel_de_read(display, FDI_RX_IIR(pipe))); /* Try each vswing and preemphasis setting twice before moving on */ for (j = 0; j < ARRAY_SIZE(snb_b_fdi_train_param) * 2; j++) { /* disable first in case we need to retry */ reg = FDI_TX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp &= ~(FDI_LINK_TRAIN_AUTO | FDI_LINK_TRAIN_NONE_IVB); temp &= ~FDI_TX_ENABLE; - intel_de_write(dev_priv, reg, temp); + intel_de_write(display, reg, temp); reg = FDI_RX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp &= ~FDI_LINK_TRAIN_AUTO; temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT; temp &= ~FDI_RX_ENABLE; - intel_de_write(dev_priv, reg, temp); + intel_de_write(display, reg, temp); /* enable CPU FDI TX and PCH FDI RX */ reg = FDI_TX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp &= ~FDI_DP_PORT_WIDTH_MASK; temp |= FDI_DP_PORT_WIDTH(crtc_state->fdi_lanes); temp |= FDI_LINK_TRAIN_PATTERN_1_IVB; temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK; temp |= snb_b_fdi_train_param[j/2]; temp |= FDI_COMPOSITE_SYNC; - intel_de_write(dev_priv, reg, temp | FDI_TX_ENABLE); + intel_de_write(display, reg, temp | FDI_TX_ENABLE); - intel_de_write(dev_priv, FDI_RX_MISC(pipe), + intel_de_write(display, FDI_RX_MISC(pipe), FDI_RX_TP1_TO_TP2_48 | FDI_RX_FDI_DELAY_90); reg = FDI_RX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp |= FDI_LINK_TRAIN_PATTERN_1_CPT; temp |= FDI_COMPOSITE_SYNC; - intel_de_write(dev_priv, reg, temp | FDI_RX_ENABLE); + intel_de_write(display, reg, temp | FDI_RX_ENABLE); - intel_de_posting_read(dev_priv, reg); + intel_de_posting_read(display, reg); udelay(1); /* should be 0.5us */ for (i = 0; i < 4; i++) { reg = FDI_RX_IIR(pipe); - temp = intel_de_read(dev_priv, reg); - drm_dbg_kms(&dev_priv->drm, "FDI_RX_IIR 0x%x\n", temp); + temp = intel_de_read(display, reg); + drm_dbg_kms(display->drm, "FDI_RX_IIR 0x%x\n", temp); if (temp & FDI_RX_BIT_LOCK || - (intel_de_read(dev_priv, reg) & FDI_RX_BIT_LOCK)) { - intel_de_write(dev_priv, reg, + (intel_de_read(display, reg) & FDI_RX_BIT_LOCK)) { + intel_de_write(display, reg, temp | FDI_RX_BIT_LOCK); - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "FDI train 1 done, level %i.\n", i); break; @@ -835,31 +826,31 @@ static void ivb_manual_fdi_link_train(struct intel_crtc *crtc, udelay(1); /* should be 0.5us */ } if (i == 4) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "FDI train 1 fail on vswing %d\n", j / 2); continue; } /* Train 2 */ - intel_de_rmw(dev_priv, FDI_TX_CTL(pipe), + intel_de_rmw(display, FDI_TX_CTL(pipe), FDI_LINK_TRAIN_NONE_IVB, FDI_LINK_TRAIN_PATTERN_2_IVB); - intel_de_rmw(dev_priv, FDI_RX_CTL(pipe), + intel_de_rmw(display, FDI_RX_CTL(pipe), FDI_LINK_TRAIN_PATTERN_MASK_CPT, FDI_LINK_TRAIN_PATTERN_2_CPT); - intel_de_posting_read(dev_priv, FDI_RX_CTL(pipe)); + intel_de_posting_read(display, FDI_RX_CTL(pipe)); udelay(2); /* should be 1.5us */ for (i = 0; i < 4; i++) { reg = FDI_RX_IIR(pipe); - temp = intel_de_read(dev_priv, reg); - drm_dbg_kms(&dev_priv->drm, "FDI_RX_IIR 0x%x\n", temp); + temp = intel_de_read(display, reg); + drm_dbg_kms(display->drm, "FDI_RX_IIR 0x%x\n", temp); if (temp & FDI_RX_SYMBOL_LOCK || - (intel_de_read(dev_priv, reg) & FDI_RX_SYMBOL_LOCK)) { - intel_de_write(dev_priv, reg, + (intel_de_read(display, reg) & FDI_RX_SYMBOL_LOCK)) { + intel_de_write(display, reg, temp | FDI_RX_SYMBOL_LOCK); - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "FDI train 2 done, level %i.\n", i); goto train_done; @@ -867,12 +858,12 @@ static void ivb_manual_fdi_link_train(struct intel_crtc *crtc, udelay(2); /* should be 1.5us */ } if (i == 4) - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "FDI train 2 fail on vswing %d\n", j / 2); } train_done: - drm_dbg_kms(&dev_priv->drm, "FDI train done.\n"); + drm_dbg_kms(display->drm, "FDI train done.\n"); } /* Starting with Haswell, different DDI ports can work in FDI mode for @@ -886,8 +877,7 @@ train_done: void hsw_fdi_link_train(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc_state); u32 temp, i, rx_ctl_val; int n_entries; @@ -902,33 +892,33 @@ void hsw_fdi_link_train(struct intel_encoder *encoder, * * WaFDIAutoLinkSetTimingOverrride:hsw */ - intel_de_write(dev_priv, FDI_RX_MISC(PIPE_A), + intel_de_write(display, FDI_RX_MISC(PIPE_A), FDI_RX_PWRDN_LANE1_VAL(2) | FDI_RX_PWRDN_LANE0_VAL(2) | FDI_RX_TP1_TO_TP2_48 | FDI_RX_FDI_DELAY_90); /* Enable the PCH Receiver FDI PLL */ - rx_ctl_val = dev_priv->display.fdi.rx_config | FDI_RX_ENHANCE_FRAME_ENABLE | + rx_ctl_val = display->fdi.rx_config | FDI_RX_ENHANCE_FRAME_ENABLE | FDI_RX_PLL_ENABLE | FDI_DP_PORT_WIDTH(crtc_state->fdi_lanes); - intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), rx_ctl_val); - intel_de_posting_read(dev_priv, FDI_RX_CTL(PIPE_A)); + intel_de_write(display, FDI_RX_CTL(PIPE_A), rx_ctl_val); + intel_de_posting_read(display, FDI_RX_CTL(PIPE_A)); udelay(220); /* Switch from Rawclk to PCDclk */ rx_ctl_val |= FDI_PCDCLK; - intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), rx_ctl_val); + intel_de_write(display, FDI_RX_CTL(PIPE_A), rx_ctl_val); /* Configure Port Clock Select */ - drm_WARN_ON(&dev_priv->drm, crtc_state->shared_dpll->info->id != DPLL_ID_SPLL); + drm_WARN_ON(display->drm, crtc_state->shared_dpll->info->id != DPLL_ID_SPLL); intel_ddi_enable_clock(encoder, crtc_state); /* Start the training iterating through available voltages and emphasis, * testing each value twice. */ for (i = 0; i < n_entries * 2; i++) { /* Configure DP_TP_CTL with auto-training */ - intel_de_write(dev_priv, DP_TP_CTL(PORT_E), + intel_de_write(display, DP_TP_CTL(PORT_E), DP_TP_CTL_FDI_AUTOTRAIN | DP_TP_CTL_ENHANCED_FRAME_ENABLE | DP_TP_CTL_LINK_TRAIN_PAT1 | @@ -938,36 +928,36 @@ void hsw_fdi_link_train(struct intel_encoder *encoder, * DDI E does not support port reversal, the functionality is * achieved on the PCH side in FDI_RX_CTL, so no need to set the * port reversal bit */ - intel_de_write(dev_priv, DDI_BUF_CTL(PORT_E), + intel_de_write(display, DDI_BUF_CTL(PORT_E), DDI_BUF_CTL_ENABLE | ((crtc_state->fdi_lanes - 1) << 1) | DDI_BUF_TRANS_SELECT(i / 2)); - intel_de_posting_read(dev_priv, DDI_BUF_CTL(PORT_E)); + intel_de_posting_read(display, DDI_BUF_CTL(PORT_E)); udelay(600); /* Program PCH FDI Receiver TU */ - intel_de_write(dev_priv, FDI_RX_TUSIZE1(PIPE_A), TU_SIZE(64)); + intel_de_write(display, FDI_RX_TUSIZE1(PIPE_A), TU_SIZE(64)); /* Enable PCH FDI Receiver with auto-training */ rx_ctl_val |= FDI_RX_ENABLE | FDI_LINK_TRAIN_AUTO; - intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), rx_ctl_val); - intel_de_posting_read(dev_priv, FDI_RX_CTL(PIPE_A)); + intel_de_write(display, FDI_RX_CTL(PIPE_A), rx_ctl_val); + intel_de_posting_read(display, FDI_RX_CTL(PIPE_A)); /* Wait for FDI receiver lane calibration */ udelay(30); /* Unset FDI_RX_MISC pwrdn lanes */ - intel_de_rmw(dev_priv, FDI_RX_MISC(PIPE_A), + intel_de_rmw(display, FDI_RX_MISC(PIPE_A), FDI_RX_PWRDN_LANE1_MASK | FDI_RX_PWRDN_LANE0_MASK, 0); - intel_de_posting_read(dev_priv, FDI_RX_MISC(PIPE_A)); + intel_de_posting_read(display, FDI_RX_MISC(PIPE_A)); /* Wait for FDI auto training time */ udelay(5); - temp = intel_de_read(dev_priv, DP_TP_STATUS(PORT_E)); + temp = intel_de_read(display, DP_TP_STATUS(PORT_E)); if (temp & DP_TP_STATUS_AUTOTRAIN_DONE) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(display->drm, "FDI link training done on step %d\n", i); break; } @@ -977,32 +967,32 @@ void hsw_fdi_link_train(struct intel_encoder *encoder, * Results in less fireworks from the state checker. */ if (i == n_entries * 2 - 1) { - drm_err(&dev_priv->drm, "FDI link training failed!\n"); + drm_err(display->drm, "FDI link training failed!\n"); break; } rx_ctl_val &= ~FDI_RX_ENABLE; - intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), rx_ctl_val); - intel_de_posting_read(dev_priv, FDI_RX_CTL(PIPE_A)); + intel_de_write(display, FDI_RX_CTL(PIPE_A), rx_ctl_val); + intel_de_posting_read(display, FDI_RX_CTL(PIPE_A)); - intel_de_rmw(dev_priv, DDI_BUF_CTL(PORT_E), DDI_BUF_CTL_ENABLE, 0); - intel_de_posting_read(dev_priv, DDI_BUF_CTL(PORT_E)); + intel_de_rmw(display, DDI_BUF_CTL(PORT_E), DDI_BUF_CTL_ENABLE, 0); + intel_de_posting_read(display, DDI_BUF_CTL(PORT_E)); /* Disable DP_TP_CTL and FDI_RX_CTL and retry */ - intel_de_rmw(dev_priv, DP_TP_CTL(PORT_E), DP_TP_CTL_ENABLE, 0); - intel_de_posting_read(dev_priv, DP_TP_CTL(PORT_E)); + intel_de_rmw(display, DP_TP_CTL(PORT_E), DP_TP_CTL_ENABLE, 0); + intel_de_posting_read(display, DP_TP_CTL(PORT_E)); - intel_wait_ddi_buf_idle(dev_priv, PORT_E); + intel_wait_ddi_buf_idle(display, PORT_E); /* Reset FDI_RX_MISC pwrdn lanes */ - intel_de_rmw(dev_priv, FDI_RX_MISC(PIPE_A), + intel_de_rmw(display, FDI_RX_MISC(PIPE_A), FDI_RX_PWRDN_LANE1_MASK | FDI_RX_PWRDN_LANE0_MASK, FDI_RX_PWRDN_LANE1_VAL(2) | FDI_RX_PWRDN_LANE0_VAL(2)); - intel_de_posting_read(dev_priv, FDI_RX_MISC(PIPE_A)); + intel_de_posting_read(display, FDI_RX_MISC(PIPE_A)); } /* Enable normal pixel sending for FDI */ - intel_de_write(dev_priv, DP_TP_CTL(PORT_E), + intel_de_write(display, DP_TP_CTL(PORT_E), DP_TP_CTL_FDI_AUTOTRAIN | DP_TP_CTL_LINK_TRAIN_NORMAL | DP_TP_CTL_ENHANCED_FRAME_ENABLE | @@ -1011,7 +1001,7 @@ void hsw_fdi_link_train(struct intel_encoder *encoder, void hsw_fdi_disable(struct intel_encoder *encoder) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_display *display = to_intel_display(encoder); /* * Bspec lists this as both step 13 (before DDI_BUF_CTL disable) @@ -1019,103 +1009,103 @@ void hsw_fdi_disable(struct intel_encoder *encoder) * step 13 is the correct place for it. Step 18 is where it was * originally before the BUN. */ - intel_de_rmw(dev_priv, FDI_RX_CTL(PIPE_A), FDI_RX_ENABLE, 0); - intel_de_rmw(dev_priv, DDI_BUF_CTL(PORT_E), DDI_BUF_CTL_ENABLE, 0); - intel_wait_ddi_buf_idle(dev_priv, PORT_E); + intel_de_rmw(display, FDI_RX_CTL(PIPE_A), FDI_RX_ENABLE, 0); + intel_de_rmw(display, DDI_BUF_CTL(PORT_E), DDI_BUF_CTL_ENABLE, 0); + intel_wait_ddi_buf_idle(display, PORT_E); intel_ddi_disable_clock(encoder); - intel_de_rmw(dev_priv, FDI_RX_MISC(PIPE_A), + intel_de_rmw(display, FDI_RX_MISC(PIPE_A), FDI_RX_PWRDN_LANE1_MASK | FDI_RX_PWRDN_LANE0_MASK, FDI_RX_PWRDN_LANE1_VAL(2) | FDI_RX_PWRDN_LANE0_VAL(2)); - intel_de_rmw(dev_priv, FDI_RX_CTL(PIPE_A), FDI_PCDCLK, 0); - intel_de_rmw(dev_priv, FDI_RX_CTL(PIPE_A), FDI_RX_PLL_ENABLE, 0); + intel_de_rmw(display, FDI_RX_CTL(PIPE_A), FDI_PCDCLK, 0); + intel_de_rmw(display, FDI_RX_CTL(PIPE_A), FDI_RX_PLL_ENABLE, 0); } void ilk_fdi_pll_enable(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; i915_reg_t reg; u32 temp; /* enable PCH FDI RX PLL, wait warmup plus DMI latency */ reg = FDI_RX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp &= ~(FDI_DP_PORT_WIDTH_MASK | (0x7 << 16)); temp |= FDI_DP_PORT_WIDTH(crtc_state->fdi_lanes); - temp |= (intel_de_read(dev_priv, TRANSCONF(dev_priv, pipe)) & TRANSCONF_BPC_MASK) << 11; - intel_de_write(dev_priv, reg, temp | FDI_RX_PLL_ENABLE); + temp |= (intel_de_read(display, TRANSCONF(display, pipe)) & TRANSCONF_BPC_MASK) << 11; + intel_de_write(display, reg, temp | FDI_RX_PLL_ENABLE); - intel_de_posting_read(dev_priv, reg); + intel_de_posting_read(display, reg); udelay(200); /* Switch from Rawclk to PCDclk */ - intel_de_rmw(dev_priv, reg, 0, FDI_PCDCLK); - intel_de_posting_read(dev_priv, reg); + intel_de_rmw(display, reg, 0, FDI_PCDCLK); + intel_de_posting_read(display, reg); udelay(200); /* Enable CPU FDI TX PLL, always on for Ironlake */ reg = FDI_TX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); if ((temp & FDI_TX_PLL_ENABLE) == 0) { - intel_de_write(dev_priv, reg, temp | FDI_TX_PLL_ENABLE); + intel_de_write(display, reg, temp | FDI_TX_PLL_ENABLE); - intel_de_posting_read(dev_priv, reg); + intel_de_posting_read(display, reg); udelay(100); } } void ilk_fdi_pll_disable(struct intel_crtc *crtc) { - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_display *display = to_intel_display(crtc); enum pipe pipe = crtc->pipe; /* Switch from PCDclk to Rawclk */ - intel_de_rmw(dev_priv, FDI_RX_CTL(pipe), FDI_PCDCLK, 0); + intel_de_rmw(display, FDI_RX_CTL(pipe), FDI_PCDCLK, 0); /* Disable CPU FDI TX PLL */ - intel_de_rmw(dev_priv, FDI_TX_CTL(pipe), FDI_TX_PLL_ENABLE, 0); - intel_de_posting_read(dev_priv, FDI_TX_CTL(pipe)); + intel_de_rmw(display, FDI_TX_CTL(pipe), FDI_TX_PLL_ENABLE, 0); + intel_de_posting_read(display, FDI_TX_CTL(pipe)); udelay(100); /* Wait for the clocks to turn off. */ - intel_de_rmw(dev_priv, FDI_RX_CTL(pipe), FDI_RX_PLL_ENABLE, 0); - intel_de_posting_read(dev_priv, FDI_RX_CTL(pipe)); + intel_de_rmw(display, FDI_RX_CTL(pipe), FDI_RX_PLL_ENABLE, 0); + intel_de_posting_read(display, FDI_RX_CTL(pipe)); udelay(100); } void ilk_fdi_disable(struct intel_crtc *crtc) { + struct intel_display *display = to_intel_display(crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; i915_reg_t reg; u32 temp; /* disable CPU FDI tx and PCH FDI rx */ - intel_de_rmw(dev_priv, FDI_TX_CTL(pipe), FDI_TX_ENABLE, 0); - intel_de_posting_read(dev_priv, FDI_TX_CTL(pipe)); + intel_de_rmw(display, FDI_TX_CTL(pipe), FDI_TX_ENABLE, 0); + intel_de_posting_read(display, FDI_TX_CTL(pipe)); reg = FDI_RX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); temp &= ~(0x7 << 16); - temp |= (intel_de_read(dev_priv, TRANSCONF(dev_priv, pipe)) & TRANSCONF_BPC_MASK) << 11; - intel_de_write(dev_priv, reg, temp & ~FDI_RX_ENABLE); + temp |= (intel_de_read(display, TRANSCONF(display, pipe)) & TRANSCONF_BPC_MASK) << 11; + intel_de_write(display, reg, temp & ~FDI_RX_ENABLE); - intel_de_posting_read(dev_priv, reg); + intel_de_posting_read(display, reg); udelay(100); /* Ironlake workaround, disable clock pointer after downing FDI */ if (HAS_PCH_IBX(dev_priv)) - intel_de_write(dev_priv, FDI_RX_CHICKEN(pipe), + intel_de_write(display, FDI_RX_CHICKEN(pipe), FDI_RX_PHASE_SYNC_POINTER_OVR); /* still set train pattern 1 */ - intel_de_rmw(dev_priv, FDI_TX_CTL(pipe), + intel_de_rmw(display, FDI_TX_CTL(pipe), FDI_LINK_TRAIN_NONE, FDI_LINK_TRAIN_PATTERN_1); reg = FDI_RX_CTL(pipe); - temp = intel_de_read(dev_priv, reg); + temp = intel_de_read(display, reg); if (HAS_PCH_CPT(dev_priv)) { temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT; temp |= FDI_LINK_TRAIN_PATTERN_1_CPT; @@ -1125,10 +1115,10 @@ void ilk_fdi_disable(struct intel_crtc *crtc) } /* BPC in FDI rx is consistent with that in TRANSCONF */ temp &= ~(0x07 << 16); - temp |= (intel_de_read(dev_priv, TRANSCONF(dev_priv, pipe)) & TRANSCONF_BPC_MASK) << 11; - intel_de_write(dev_priv, reg, temp); + temp |= (intel_de_read(display, TRANSCONF(display, pipe)) & TRANSCONF_BPC_MASK) << 11; + intel_de_write(display, reg, temp); - intel_de_posting_read(dev_priv, reg); + intel_de_posting_read(display, reg); udelay(100); } @@ -1145,14 +1135,14 @@ static const struct intel_fdi_funcs ivb_funcs = { }; void -intel_fdi_init_hook(struct drm_i915_private *dev_priv) +intel_fdi_init_hook(struct intel_display *display) { - if (IS_IRONLAKE(dev_priv)) { - dev_priv->display.funcs.fdi = &ilk_funcs; - } else if (IS_SANDYBRIDGE(dev_priv)) { - dev_priv->display.funcs.fdi = &gen6_funcs; - } else if (IS_IVYBRIDGE(dev_priv)) { + if (display->platform.ironlake) { + display->funcs.fdi = &ilk_funcs; + } else if (display->platform.sandybridge) { + display->funcs.fdi = &gen6_funcs; + } else if (display->platform.ivybridge) { /* FIXME: detect B0+ stepping and use auto training */ - dev_priv->display.funcs.fdi = &ivb_funcs; + display->funcs.fdi = &ivb_funcs; } } diff --git a/drivers/gpu/drm/i915/display/intel_fdi.h b/drivers/gpu/drm/i915/display/intel_fdi.h index b5be09efb36f..ad5e103c38a8 100644 --- a/drivers/gpu/drm/i915/display/intel_fdi.h +++ b/drivers/gpu/drm/i915/display/intel_fdi.h @@ -9,16 +9,16 @@ #include <linux/types.h> enum pipe; -struct drm_i915_private; struct intel_atomic_state; struct intel_crtc; struct intel_crtc_state; struct intel_display; +struct intel_display; struct intel_encoder; struct intel_link_bw_limits; int intel_fdi_add_affected_crtcs(struct intel_atomic_state *state); -int intel_fdi_link_freq(struct drm_i915_private *i915, +int intel_fdi_link_freq(struct intel_display *display, const struct intel_crtc_state *pipe_config); bool intel_fdi_compute_pipe_bpp(struct intel_crtc_state *crtc_state); int ilk_fdi_compute_config(struct intel_crtc *intel_crtc, @@ -29,19 +29,19 @@ void intel_fdi_normal_train(struct intel_crtc *crtc); void ilk_fdi_disable(struct intel_crtc *crtc); void ilk_fdi_pll_disable(struct intel_crtc *intel_crtc); void ilk_fdi_pll_enable(const struct intel_crtc_state *crtc_state); -void intel_fdi_init_hook(struct drm_i915_private *dev_priv); +void intel_fdi_init_hook(struct intel_display *display); void hsw_fdi_link_train(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state); void hsw_fdi_disable(struct intel_encoder *encoder); -void intel_fdi_pll_freq_update(struct drm_i915_private *i915); +void intel_fdi_pll_freq_update(struct intel_display *display); void intel_fdi_link_train(struct intel_crtc *crtc, const struct intel_crtc_state *crtc_state); -void assert_fdi_tx_enabled(struct drm_i915_private *i915, enum pipe pipe); -void assert_fdi_tx_disabled(struct drm_i915_private *i915, enum pipe pipe); -void assert_fdi_rx_enabled(struct drm_i915_private *i915, enum pipe pipe); -void assert_fdi_rx_disabled(struct drm_i915_private *i915, enum pipe pipe); +void assert_fdi_tx_enabled(struct intel_display *display, enum pipe pipe); +void assert_fdi_tx_disabled(struct intel_display *display, enum pipe pipe); +void assert_fdi_rx_enabled(struct intel_display *display, enum pipe pipe); +void assert_fdi_rx_disabled(struct intel_display *display, enum pipe pipe); void assert_fdi_tx_pll_enabled(struct intel_display *display, enum pipe pipe); void assert_fdi_rx_pll_enabled(struct intel_display *display, enum pipe pipe); void assert_fdi_rx_pll_disabled(struct intel_display *display, enum pipe pipe); diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c index 26128c610cb4..ba2f88ca6117 100644 --- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c +++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c @@ -59,6 +59,7 @@ #include "i915_active.h" #include "i915_drv.h" +#include "i915_vma.h" #include "intel_bo.h" #include "intel_display_trace.h" #include "intel_display_types.h" @@ -98,10 +99,10 @@ static void frontbuffer_flush(struct drm_i915_private *i915, trace_intel_frontbuffer_flush(display, frontbuffer_bits, origin); might_sleep(); - intel_td_flush(i915); - intel_drrs_flush(i915, frontbuffer_bits); + intel_td_flush(display); + intel_drrs_flush(display, frontbuffer_bits); intel_psr_flush(display, frontbuffer_bits, origin); - intel_fbc_flush(i915, frontbuffer_bits, origin); + intel_fbc_flush(display, frontbuffer_bits, origin); } /** @@ -176,7 +177,6 @@ void __intel_fb_invalidate(struct intel_frontbuffer *front, unsigned int frontbuffer_bits) { struct intel_display *display = to_intel_display(front->obj->dev); - struct drm_i915_private *i915 = to_i915(display->drm); if (origin == ORIGIN_CS) { spin_lock(&display->fb_tracking.lock); @@ -189,8 +189,8 @@ void __intel_fb_invalidate(struct intel_frontbuffer *front, might_sleep(); intel_psr_invalidate(display, frontbuffer_bits, origin); - intel_drrs_invalidate(i915, frontbuffer_bits); - intel_fbc_invalidate(i915, frontbuffer_bits, origin); + intel_drrs_invalidate(display, frontbuffer_bits); + intel_fbc_invalidate(display, frontbuffer_bits, origin); } void __intel_fb_flush(struct intel_frontbuffer *front, diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 7063e3f5c538..1bf424a822f3 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -70,13 +70,13 @@ static int intel_conn_to_vcpi(struct intel_atomic_state *state, int vcpi = 0; /* For HDMI this is forced to be 0x0. For DP SST also this is 0x0. */ - if (!connector->port) + if (!connector->mst.port) return 0; - mgr = connector->port->mgr; + mgr = connector->mst.port->mgr; drm_modeset_lock(&mgr->base.lock, state->base.acquire_ctx); mst_state = to_drm_dp_mst_topology_state(mgr->base.state); - payload = drm_atomic_get_mst_payload_state(mst_state, connector->port); + payload = drm_atomic_get_mst_payload_state(mst_state, connector->mst.port); if (drm_WARN_ON(mgr->dev, !payload)) goto out; @@ -107,16 +107,16 @@ intel_hdcp_required_content_stream(struct intel_atomic_state *state, struct drm_connector_list_iter conn_iter; struct intel_digital_port *conn_dig_port; struct intel_connector *connector; - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; bool enforce_type0 = false; int k; - if (dig_port->hdcp_auth_status) + if (dig_port->hdcp.auth_status) return 0; data->k = 0; - if (!dig_port->hdcp_mst_type1_capable) + if (!dig_port->hdcp.mst_type1_capable) enforce_type0 = true; drm_connector_list_iter_begin(display->drm, &conn_iter); @@ -136,7 +136,7 @@ intel_hdcp_required_content_stream(struct intel_atomic_state *state, data->k++; /* if there is only one active stream */ - if (dig_port->dp.active_mst_links <= 1) + if (dig_port->dp.mst.active_links <= 1) break; } drm_connector_list_iter_end(&conn_iter); @@ -159,7 +159,7 @@ static int intel_hdcp_prepare_streams(struct intel_atomic_state *state, struct intel_connector *connector) { struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct intel_hdcp *hdcp = &connector->hdcp; if (intel_encoder_is_mst(intel_attached_encoder(connector))) @@ -1001,7 +1001,7 @@ static int _intel_hdcp_disable(struct intel_connector *connector) * don't disable it until it disabled HDCP encryption for * all connectors in MST topology. */ - if (dig_port->num_hdcp_streams > 0) + if (dig_port->hdcp.num_streams > 0) return 0; } @@ -1094,13 +1094,13 @@ static void intel_hdcp_update_value(struct intel_connector *connector, if (hdcp->value == value) return; - drm_WARN_ON(display->drm, !mutex_is_locked(&dig_port->hdcp_mutex)); + drm_WARN_ON(display->drm, !mutex_is_locked(&dig_port->hdcp.mutex)); if (hdcp->value == DRM_MODE_CONTENT_PROTECTION_ENABLED) { - if (!drm_WARN_ON(display->drm, dig_port->num_hdcp_streams == 0)) - dig_port->num_hdcp_streams--; + if (!drm_WARN_ON(display->drm, dig_port->hdcp.num_streams == 0)) + dig_port->hdcp.num_streams--; } else if (value == DRM_MODE_CONTENT_PROTECTION_ENABLED) { - dig_port->num_hdcp_streams++; + dig_port->hdcp.num_streams++; } hdcp->value = value; @@ -1122,7 +1122,7 @@ static int intel_hdcp_check_link(struct intel_connector *connector) int ret = 0; mutex_lock(&hdcp->mutex); - mutex_lock(&dig_port->hdcp_mutex); + mutex_lock(&dig_port->hdcp.mutex); cpu_transcoder = hdcp->cpu_transcoder; @@ -1177,7 +1177,7 @@ static int intel_hdcp_check_link(struct intel_connector *connector) } out: - mutex_unlock(&dig_port->hdcp_mutex); + mutex_unlock(&dig_port->hdcp.mutex); mutex_unlock(&hdcp->mutex); return ret; } @@ -1219,7 +1219,7 @@ hdcp2_prepare_ake_init(struct intel_connector *connector, { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct i915_hdcp_arbiter *arbiter; int ret; @@ -1249,7 +1249,7 @@ hdcp2_verify_rx_cert_prepare_km(struct intel_connector *connector, { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct i915_hdcp_arbiter *arbiter; int ret; @@ -1277,7 +1277,7 @@ static int hdcp2_verify_hprime(struct intel_connector *connector, { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct i915_hdcp_arbiter *arbiter; int ret; @@ -1303,7 +1303,7 @@ hdcp2_store_pairing_info(struct intel_connector *connector, { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct i915_hdcp_arbiter *arbiter; int ret; @@ -1330,7 +1330,7 @@ hdcp2_prepare_lc_init(struct intel_connector *connector, { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct i915_hdcp_arbiter *arbiter; int ret; @@ -1357,7 +1357,7 @@ hdcp2_verify_lprime(struct intel_connector *connector, { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct i915_hdcp_arbiter *arbiter; int ret; @@ -1383,7 +1383,7 @@ static int hdcp2_prepare_skey(struct intel_connector *connector, { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct i915_hdcp_arbiter *arbiter; int ret; @@ -1412,7 +1412,7 @@ hdcp2_verify_rep_topology_prepare_ack(struct intel_connector *connector, { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct i915_hdcp_arbiter *arbiter; int ret; @@ -1442,7 +1442,7 @@ hdcp2_verify_mprime(struct intel_connector *connector, { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct i915_hdcp_arbiter *arbiter; int ret; @@ -1466,7 +1466,7 @@ static int hdcp2_authenticate_port(struct intel_connector *connector) { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct i915_hdcp_arbiter *arbiter; int ret; @@ -1503,7 +1503,7 @@ static int hdcp2_close_session(struct intel_connector *connector) } ret = arbiter->ops->close_hdcp_session(arbiter->hdcp_dev, - &dig_port->hdcp_port_data); + &dig_port->hdcp.port_data); mutex_unlock(&display->hdcp.hdcp_mutex); return ret; @@ -1691,7 +1691,7 @@ static int _hdcp2_propagate_stream_management_info(struct intel_connector *connector) { struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct intel_hdcp *hdcp = &connector->hdcp; union { struct hdcp2_rep_stream_manage stream_manage; @@ -1769,11 +1769,11 @@ int hdcp2_authenticate_repeater_topology(struct intel_connector *connector) * MST topology is not Type 1 capable if it contains a downstream * device that is only HDCP 1.x or Legacy HDCP 2.0/2.1 compliant. */ - dig_port->hdcp_mst_type1_capable = + dig_port->hdcp.mst_type1_capable = !HDCP_2_2_HDCP1_DEVICE_CONNECTED(rx_info[1]) && !HDCP_2_2_HDCP_2_0_REP_CONNECTED(rx_info[1]); - if (!dig_port->hdcp_mst_type1_capable && hdcp->content_type) { + if (!dig_port->hdcp.mst_type1_capable && hdcp->content_type) { drm_dbg_kms(display->drm, "HDCP1.x or 2.0 Legacy Device Downstream\n"); return -EINVAL; @@ -1869,7 +1869,7 @@ static int hdcp2_enable_stream_encryption(struct intel_connector *connector) { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct intel_hdcp *hdcp = &connector->hdcp; enum transcoder cpu_transcoder = hdcp->cpu_transcoder; enum port port = dig_port->base.port; @@ -1900,7 +1900,7 @@ link_recover: if (hdcp2_deauthenticate_port(connector) < 0) drm_dbg_kms(display->drm, "Port deauth failed.\n"); - dig_port->hdcp_auth_status = false; + dig_port->hdcp.auth_status = false; data->k = 0; return ret; @@ -1940,7 +1940,7 @@ static int hdcp2_enable_encryption(struct intel_connector *connector) port), LINK_ENCRYPTION_STATUS, HDCP_ENCRYPT_STATUS_CHANGE_TIMEOUT_MS); - dig_port->hdcp_auth_status = true; + dig_port->hdcp.auth_status = true; return ret; } @@ -2019,7 +2019,7 @@ static int hdcp2_authenticate_and_encrypt(struct intel_atomic_state *state, struct intel_digital_port *dig_port = intel_attached_dig_port(connector); int ret = 0, i, tries = 3; - for (i = 0; i < tries && !dig_port->hdcp_auth_status; i++) { + for (i = 0; i < tries && !dig_port->hdcp.auth_status; i++) { ret = hdcp2_authenticate_sink(connector); if (!ret) { ret = intel_hdcp_prepare_streams(state, connector); @@ -2052,7 +2052,7 @@ static int hdcp2_authenticate_and_encrypt(struct intel_atomic_state *state, drm_dbg_kms(display->drm, "Port deauth failed.\n"); } - if (!ret && !dig_port->hdcp_auth_status) { + if (!ret && !dig_port->hdcp.auth_status) { /* * Ensuring the required 200mSec min time interval between * Session Key Exchange and encryption. @@ -2106,7 +2106,7 @@ _intel_hdcp2_disable(struct intel_connector *connector, bool hdcp2_link_recovery { struct intel_display *display = to_intel_display(connector); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; struct intel_hdcp *hdcp = &connector->hdcp; int ret; @@ -2123,7 +2123,7 @@ _intel_hdcp2_disable(struct intel_connector *connector, bool hdcp2_link_recovery drm_dbg_kms(display->drm, "HDCP 2.2 transcoder: %s stream encryption disabled\n", transcoder_name(hdcp->stream_transcoder)); - if (dig_port->num_hdcp_streams > 0 && !hdcp2_link_recovery) + if (dig_port->hdcp.num_streams > 0 && !hdcp2_link_recovery) return 0; } @@ -2133,7 +2133,7 @@ _intel_hdcp2_disable(struct intel_connector *connector, bool hdcp2_link_recovery drm_dbg_kms(display->drm, "Port deauth failed.\n"); connector->hdcp.hdcp2_encrypted = false; - dig_port->hdcp_auth_status = false; + dig_port->hdcp.auth_status = false; data->k = 0; return ret; @@ -2150,7 +2150,7 @@ static int intel_hdcp2_check_link(struct intel_connector *connector) int ret = 0; mutex_lock(&hdcp->mutex); - mutex_lock(&dig_port->hdcp_mutex); + mutex_lock(&dig_port->hdcp.mutex); cpu_transcoder = hdcp->cpu_transcoder; /* hdcp2_check_link is expected only when HDCP2.2 is Enabled */ @@ -2221,7 +2221,7 @@ static int intel_hdcp2_check_link(struct intel_connector *connector) intel_hdcp_update_value(connector, DRM_MODE_CONTENT_PROTECTION_DESIRED, true); out: - mutex_unlock(&dig_port->hdcp_mutex); + mutex_unlock(&dig_port->hdcp.mutex); mutex_unlock(&hdcp->mutex); return ret; } @@ -2303,7 +2303,7 @@ static int initialize_hdcp_port_data(struct intel_connector *connector, const struct intel_hdcp_shim *shim) { struct intel_display *display = to_intel_display(connector); - struct hdcp_port_data *data = &dig_port->hdcp_port_data; + struct hdcp_port_data *data = &dig_port->hdcp.port_data; enum port port = dig_port->base.port; if (DISPLAY_VER(display) < 12) @@ -2414,7 +2414,7 @@ int intel_hdcp_init(struct intel_connector *connector, hdcp->hdcp2_supported); if (ret) { hdcp->hdcp2_supported = false; - kfree(dig_port->hdcp_port_data.streams); + kfree(dig_port->hdcp.port_data.streams); return ret; } @@ -2451,7 +2451,7 @@ static int _intel_hdcp_enable(struct intel_atomic_state *state, } mutex_lock(&hdcp->mutex); - mutex_lock(&dig_port->hdcp_mutex); + mutex_lock(&dig_port->hdcp.mutex); drm_WARN_ON(display->drm, hdcp->value == DRM_MODE_CONTENT_PROTECTION_ENABLED); hdcp->content_type = (u8)conn_state->hdcp_content_type; @@ -2465,7 +2465,7 @@ static int _intel_hdcp_enable(struct intel_atomic_state *state, } if (DISPLAY_VER(display) >= 12) - dig_port->hdcp_port_data.hdcp_transcoder = + dig_port->hdcp.port_data.hdcp_transcoder = intel_get_hdcp_transcoder(hdcp->cpu_transcoder); /* @@ -2499,7 +2499,7 @@ static int _intel_hdcp_enable(struct intel_atomic_state *state, true); } - mutex_unlock(&dig_port->hdcp_mutex); + mutex_unlock(&dig_port->hdcp.mutex); mutex_unlock(&hdcp->mutex); return ret; } @@ -2535,7 +2535,7 @@ int intel_hdcp_disable(struct intel_connector *connector) return -ENOENT; mutex_lock(&hdcp->mutex); - mutex_lock(&dig_port->hdcp_mutex); + mutex_lock(&dig_port->hdcp.mutex); if (hdcp->value == DRM_MODE_CONTENT_PROTECTION_UNDESIRED) goto out; @@ -2548,7 +2548,7 @@ int intel_hdcp_disable(struct intel_connector *connector) ret = _intel_hdcp_disable(connector); out: - mutex_unlock(&dig_port->hdcp_mutex); + mutex_unlock(&dig_port->hdcp.mutex); mutex_unlock(&hdcp->mutex); cancel_delayed_work_sync(&hdcp->check_work); return ret; @@ -2775,7 +2775,7 @@ out: void intel_hdcp_info(struct seq_file *m, struct intel_connector *connector) { seq_puts(m, "\tHDCP version: "); - if (connector->mst_port) { + if (connector->mst.dp) { __intel_hdcp_info(m, connector, true); seq_puts(m, "\tMST Hub HDCP version: "); } diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index ed017d9de920..33b8d5229db0 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -2360,7 +2360,7 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder, } if (intel_hdmi_is_ycbcr420(pipe_config)) { - ret = intel_panel_fitting(pipe_config, conn_state); + ret = intel_pfit_compute_config(pipe_config, conn_state); if (ret) return ret; } diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.h b/drivers/gpu/drm/i915/display/intel_hdmi.h index d237fe08c3e6..dec2ad7dd8a2 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.h +++ b/drivers/gpu/drm/i915/display/intel_hdmi.h @@ -14,7 +14,6 @@ enum port; struct drm_connector; struct drm_connector_state; struct drm_encoder; -struct drm_i915_private; struct intel_connector; struct intel_crtc_state; struct intel_digital_port; diff --git a/drivers/gpu/drm/i915/display/intel_link_bw.c b/drivers/gpu/drm/i915/display/intel_link_bw.c index f4d60e77aa18..a10cd3992607 100644 --- a/drivers/gpu/drm/i915/display/intel_link_bw.c +++ b/drivers/gpu/drm/i915/display/intel_link_bw.c @@ -4,6 +4,7 @@ */ #include <drm/drm_fixed.h> +#include <drm/drm_print.h> #include "intel_atomic.h" #include "intel_crtc.h" diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c index 7ed8625193fe..19f52d1659fa 100644 --- a/drivers/gpu/drm/i915/display/intel_lvds.c +++ b/drivers/gpu/drm/i915/display/intel_lvds.c @@ -53,6 +53,7 @@ #include "intel_lvds_regs.h" #include "intel_panel.h" #include "intel_pfit.h" +#include "intel_pfit_regs.h" #include "intel_pps_regs.h" /* Private structure for the integrated LVDS support */ @@ -468,7 +469,7 @@ static int intel_lvds_compute_config(struct intel_encoder *encoder, if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) return -EINVAL; - ret = intel_panel_fitting(crtc_state, conn_state); + ret = intel_pfit_compute_config(crtc_state, conn_state); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_modeset_setup.c b/drivers/gpu/drm/i915/display/intel_modeset_setup.c index a5a00b3ce98f..312b21b1ab59 100644 --- a/drivers/gpu/drm/i915/display/intel_modeset_setup.c +++ b/drivers/gpu/drm/i915/display/intel_modeset_setup.c @@ -156,12 +156,6 @@ static void intel_crtc_disable_noatomic_complete(struct intel_crtc *crtc) { struct intel_display *display = to_intel_display(crtc); struct drm_i915_private *i915 = to_i915(crtc->base.dev); - struct intel_bw_state *bw_state = - to_intel_bw_state(i915->display.bw.obj.state); - struct intel_cdclk_state *cdclk_state = - to_intel_cdclk_state(i915->display.cdclk.obj.state); - struct intel_dbuf_state *dbuf_state = - to_intel_dbuf_state(i915->display.dbuf.obj.state); struct intel_pmdemand_state *pmdemand_state = to_intel_pmdemand_state(i915->display.pmdemand.obj.state); struct intel_crtc_state *crtc_state = @@ -179,14 +173,9 @@ static void intel_crtc_disable_noatomic_complete(struct intel_crtc *crtc) intel_display_power_put_all_in_set(display, &crtc->enabled_power_domains); - cdclk_state->min_cdclk[pipe] = 0; - cdclk_state->min_voltage_level[pipe] = 0; - cdclk_state->active_pipes &= ~BIT(pipe); - - dbuf_state->active_pipes &= ~BIT(pipe); - - bw_state->data_rate[pipe] = 0; - bw_state->num_active_planes[pipe] = 0; + intel_cdclk_crtc_disable_noatomic(crtc); + skl_wm_crtc_disable_noatomic(crtc); + intel_bw_crtc_disable_noatomic(crtc); intel_pmdemand_update_port_clock(display, pmdemand_state, pipe, 0); } @@ -704,10 +693,6 @@ static void readout_plane_state(struct drm_i915_private *i915) static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) { struct intel_display *display = &i915->display; - struct intel_cdclk_state *cdclk_state = - to_intel_cdclk_state(i915->display.cdclk.obj.state); - struct intel_dbuf_state *dbuf_state = - to_intel_dbuf_state(i915->display.dbuf.obj.state); struct intel_pmdemand_state *pmdemand_state = to_intel_pmdemand_state(i915->display.pmdemand.obj.state); enum pipe pipe; @@ -715,7 +700,6 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) struct intel_encoder *encoder; struct intel_connector *connector; struct drm_connector_list_iter conn_iter; - u8 active_pipes = 0; for_each_intel_crtc(&i915->drm, crtc) { struct intel_crtc_state *crtc_state = @@ -732,18 +716,12 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) crtc->base.enabled = crtc_state->hw.enable; crtc->active = crtc_state->hw.active; - if (crtc_state->hw.active) - active_pipes |= BIT(crtc->pipe); - drm_dbg_kms(&i915->drm, "[CRTC:%d:%s] hw state readout: %s\n", crtc->base.base.id, crtc->base.name, str_enabled_disabled(crtc_state->hw.active)); } - cdclk_state->active_pipes = active_pipes; - dbuf_state->active_pipes = active_pipes; - readout_plane_state(i915); for_each_intel_encoder(&i915->drm, encoder) { @@ -839,12 +817,9 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) drm_connector_list_iter_end(&conn_iter); for_each_intel_crtc(&i915->drm, crtc) { - struct intel_bw_state *bw_state = - to_intel_bw_state(i915->display.bw.obj.state); struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); struct intel_plane *plane; - int min_cdclk = 0; if (crtc_state->hw.active) { /* @@ -893,22 +868,17 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) crtc_state->min_cdclk[plane->id]); } - if (crtc_state->hw.active) { - min_cdclk = intel_crtc_compute_min_cdclk(crtc_state); - if (drm_WARN_ON(&i915->drm, min_cdclk < 0)) - min_cdclk = 0; - } - - cdclk_state->min_cdclk[crtc->pipe] = min_cdclk; - cdclk_state->min_voltage_level[crtc->pipe] = - crtc_state->min_voltage_level; - intel_pmdemand_update_port_clock(display, pmdemand_state, pipe, crtc_state->port_clock); - - intel_bw_crtc_update(bw_state, crtc_state); } + /* TODO move here (or even earlier?) on all platforms */ + if (DISPLAY_VER(display) >= 9) + intel_wm_get_hw_state(i915); + + intel_bw_update_hw_state(display); + intel_cdclk_update_hw_state(display); + intel_pmdemand_init_pmdemand_params(display, pmdemand_state); } @@ -1016,7 +986,10 @@ void intel_modeset_setup_hw_state(struct drm_i915_private *i915, intel_dpll_sanitize_state(display); - intel_wm_get_hw_state(i915); + /* TODO move earlier on all platforms */ + if (DISPLAY_VER(display) < 9) + intel_wm_get_hw_state(i915); + intel_wm_sanitize(i915); for_each_intel_crtc(&i915->drm, crtc) { struct intel_crtc_state *crtc_state = diff --git a/drivers/gpu/drm/i915/display/intel_modeset_verify.c b/drivers/gpu/drm/i915/display/intel_modeset_verify.c index bc70e72ccc2e..a008412fdd04 100644 --- a/drivers/gpu/drm/i915/display/intel_modeset_verify.c +++ b/drivers/gpu/drm/i915/display/intel_modeset_verify.c @@ -90,10 +90,11 @@ verify_connector_state(struct intel_atomic_state *state, static void intel_pipe_config_sanity_check(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); if (crtc_state->has_pch_encoder) { - int fdi_dotclock = intel_dotclock_calculate(intel_fdi_link_freq(i915, crtc_state), + int fdi_dotclock = intel_dotclock_calculate(intel_fdi_link_freq(display, crtc_state), &crtc_state->fdi_m_n); int dotclock = crtc_state->hw.adjusted_mode.crtc_clock; diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c index 4d00db86131b..aff9a3455c1b 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.c +++ b/drivers/gpu/drm/i915/display/intel_overlay.c @@ -42,6 +42,7 @@ #include "intel_frontbuffer.h" #include "intel_overlay.h" #include "intel_pci_config.h" +#include "intel_pfit_regs.h" /* Limits for overlay size. According to intel doc, the real limits are: * Y width: 4095, UV width (planar): 2047, Y height: 2047, @@ -799,7 +800,6 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, struct drm_intel_overlay_put_image *params) { struct intel_display *display = overlay->display; - struct drm_i915_private *dev_priv = to_i915(display->drm); struct overlay_registers __iomem *regs = overlay->regs; u32 swidth, swidthsw, sheight, ostride; enum pipe pipe = overlay->crtc->pipe; @@ -814,7 +814,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, if (ret != 0) return ret; - atomic_inc(&dev_priv->gpu_error.pending_fb_pin); + atomic_inc(&display->restore.pending_fb_pin); vma = intel_overlay_pin_fb(new_bo); if (IS_ERR(vma)) { @@ -902,7 +902,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, out_unpin: i915_vma_unpin(vma); out_pin_section: - atomic_dec(&dev_priv->gpu_error.pending_fb_pin); + atomic_dec(&display->restore.pending_fb_pin); return ret; } diff --git a/drivers/gpu/drm/i915/display/intel_overlay.h b/drivers/gpu/drm/i915/display/intel_overlay.h index 45a42fce754e..d259e4c74b03 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.h +++ b/drivers/gpu/drm/i915/display/intel_overlay.h @@ -10,7 +10,6 @@ struct drm_device; struct drm_file; -struct drm_i915_private; struct drm_printer; struct intel_display; struct intel_overlay; diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c index 4e6c5592c7ae..f5c972880391 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.c +++ b/drivers/gpu/drm/i915/display/intel_panel.c @@ -32,6 +32,7 @@ #include <linux/pwm.h> #include <drm/drm_edid.h> +#include <drm/drm_print.h> #include "intel_backlight.h" #include "intel_connector.h" diff --git a/drivers/gpu/drm/i915/display/intel_pch_display.c b/drivers/gpu/drm/i915/display/intel_pch_display.c index 1abe0a784570..99f6d6f53fa7 100644 --- a/drivers/gpu/drm/i915/display/intel_pch_display.c +++ b/drivers/gpu/drm/i915/display/intel_pch_display.c @@ -181,10 +181,10 @@ static void ibx_sanitize_pch_ports(struct drm_i915_private *dev_priv) static void intel_pch_transcoder_set_m1_n1(struct intel_crtc *crtc, const struct intel_link_m_n *m_n) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); enum pipe pipe = crtc->pipe; - intel_set_m_n(dev_priv, m_n, + intel_set_m_n(display, m_n, PCH_TRANS_DATA_M1(pipe), PCH_TRANS_DATA_N1(pipe), PCH_TRANS_LINK_M1(pipe), PCH_TRANS_LINK_N1(pipe)); } @@ -192,10 +192,10 @@ static void intel_pch_transcoder_set_m1_n1(struct intel_crtc *crtc, static void intel_pch_transcoder_set_m2_n2(struct intel_crtc *crtc, const struct intel_link_m_n *m_n) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); enum pipe pipe = crtc->pipe; - intel_set_m_n(dev_priv, m_n, + intel_set_m_n(display, m_n, PCH_TRANS_DATA_M2(pipe), PCH_TRANS_DATA_N2(pipe), PCH_TRANS_LINK_M2(pipe), PCH_TRANS_LINK_N2(pipe)); } @@ -203,10 +203,10 @@ static void intel_pch_transcoder_set_m2_n2(struct intel_crtc *crtc, void intel_pch_transcoder_get_m1_n1(struct intel_crtc *crtc, struct intel_link_m_n *m_n) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); enum pipe pipe = crtc->pipe; - intel_get_m_n(dev_priv, m_n, + intel_get_m_n(display, m_n, PCH_TRANS_DATA_M1(pipe), PCH_TRANS_DATA_N1(pipe), PCH_TRANS_LINK_M1(pipe), PCH_TRANS_LINK_N1(pipe)); } @@ -214,10 +214,10 @@ void intel_pch_transcoder_get_m1_n1(struct intel_crtc *crtc, void intel_pch_transcoder_get_m2_n2(struct intel_crtc *crtc, struct intel_link_m_n *m_n) { - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); enum pipe pipe = crtc->pipe; - intel_get_m_n(dev_priv, m_n, + intel_get_m_n(display, m_n, PCH_TRANS_DATA_M2(pipe), PCH_TRANS_DATA_N2(pipe), PCH_TRANS_LINK_M2(pipe), PCH_TRANS_LINK_N2(pipe)); } @@ -259,8 +259,8 @@ static void ilk_enable_pch_transcoder(const struct intel_crtc_state *crtc_state) assert_shared_dpll_enabled(display, crtc_state->shared_dpll); /* FDI must be feeding us bits for PCH ports */ - assert_fdi_tx_enabled(dev_priv, pipe); - assert_fdi_rx_enabled(dev_priv, pipe); + assert_fdi_tx_enabled(display, pipe); + assert_fdi_rx_enabled(display, pipe); if (HAS_PCH_CPT(dev_priv)) { reg = TRANS_CHICKEN2(pipe); @@ -316,13 +316,14 @@ static void ilk_enable_pch_transcoder(const struct intel_crtc_state *crtc_state) static void ilk_disable_pch_transcoder(struct intel_crtc *crtc) { + struct intel_display *display = to_intel_display(crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; i915_reg_t reg; /* FDI relies on the transcoder */ - assert_fdi_tx_disabled(dev_priv, pipe); - assert_fdi_rx_disabled(dev_priv, pipe); + assert_fdi_tx_disabled(display, pipe); + assert_fdi_rx_disabled(display, pipe); /* Ports must be off as well */ assert_pch_ports_disabled(dev_priv, pipe); @@ -479,8 +480,7 @@ void ilk_pch_post_disable(struct intel_atomic_state *state, static void ilk_pch_clock_get(struct intel_crtc_state *crtc_state) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc_state); /* read out port_clock from the DPLL */ i9xx_crtc_clock_get(crtc_state); @@ -491,7 +491,7 @@ static void ilk_pch_clock_get(struct intel_crtc_state *crtc_state) * Calculate one based on the FDI configuration. */ crtc_state->hw.adjusted_mode.crtc_clock = - intel_dotclock_calculate(intel_fdi_link_freq(dev_priv, crtc_state), + intel_dotclock_calculate(intel_fdi_link_freq(display, crtc_state), &crtc_state->fdi_m_n); } @@ -549,14 +549,15 @@ void ilk_pch_get_config(struct intel_crtc_state *crtc_state) static void lpt_enable_pch_transcoder(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; u32 val, pipeconf_val; /* FDI must be feeding us bits for PCH ports */ - assert_fdi_tx_enabled(dev_priv, (enum pipe) cpu_transcoder); - assert_fdi_rx_enabled(dev_priv, PIPE_A); + assert_fdi_tx_enabled(display, (enum pipe)cpu_transcoder); + assert_fdi_rx_enabled(display, PIPE_A); val = intel_de_read(dev_priv, TRANS_CHICKEN2(PIPE_A)); /* Workaround: set timing override bit. */ diff --git a/drivers/gpu/drm/i915/display/intel_pfit.c b/drivers/gpu/drm/i915/display/intel_pfit.c index 4ee03d9d14ad..3c3ecf288570 100644 --- a/drivers/gpu/drm/i915/display/intel_pfit.c +++ b/drivers/gpu/drm/i915/display/intel_pfit.c @@ -3,13 +3,17 @@ * Copyright © 2024 Intel Corporation */ +#include <drm/drm_print.h> + #include "i915_reg.h" #include "i915_utils.h" +#include "intel_de.h" #include "intel_display_core.h" #include "intel_display_driver.h" #include "intel_display_types.h" #include "intel_lvds_regs.h" #include "intel_pfit.h" +#include "intel_pfit_regs.h" static int intel_pch_pfit_check_dst_window(const struct intel_crtc_state *crtc_state) { @@ -542,8 +546,8 @@ out: return intel_gmch_pfit_check_timings(crtc_state); } -int intel_panel_fitting(struct intel_crtc_state *crtc_state, - const struct drm_connector_state *conn_state) +int intel_pfit_compute_config(struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state) { struct intel_display *display = to_intel_display(crtc_state); @@ -552,3 +556,165 @@ int intel_panel_fitting(struct intel_crtc_state *crtc_state, else return pch_panel_fitting(crtc_state, conn_state); } + +void ilk_pfit_enable(const struct intel_crtc_state *crtc_state) +{ + struct intel_display *display = to_intel_display(crtc_state); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + const struct drm_rect *dst = &crtc_state->pch_pfit.dst; + enum pipe pipe = crtc->pipe; + int width = drm_rect_width(dst); + int height = drm_rect_height(dst); + int x = dst->x1; + int y = dst->y1; + + if (!crtc_state->pch_pfit.enabled) + return; + + /* + * Force use of hard-coded filter coefficients as some pre-programmed + * values are broken, e.g. x201. + */ + if (display->platform.ivybridge || display->platform.haswell) + intel_de_write_fw(display, PF_CTL(pipe), PF_ENABLE | + PF_FILTER_MED_3x3 | PF_PIPE_SEL_IVB(pipe)); + else + intel_de_write_fw(display, PF_CTL(pipe), PF_ENABLE | + PF_FILTER_MED_3x3); + intel_de_write_fw(display, PF_WIN_POS(pipe), + PF_WIN_XPOS(x) | PF_WIN_YPOS(y)); + intel_de_write_fw(display, PF_WIN_SZ(pipe), + PF_WIN_XSIZE(width) | PF_WIN_YSIZE(height)); +} + +void ilk_pfit_disable(const struct intel_crtc_state *old_crtc_state) +{ + struct intel_display *display = to_intel_display(old_crtc_state); + struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); + enum pipe pipe = crtc->pipe; + + /* + * To avoid upsetting the power well on haswell only disable the pfit if + * it's in use. The hw state code will make sure we get this right. + */ + if (!old_crtc_state->pch_pfit.enabled) + return; + + intel_de_write_fw(display, PF_CTL(pipe), 0); + intel_de_write_fw(display, PF_WIN_POS(pipe), 0); + intel_de_write_fw(display, PF_WIN_SZ(pipe), 0); +} + +void ilk_pfit_get_config(struct intel_crtc_state *crtc_state) +{ + struct intel_display *display = to_intel_display(crtc_state); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + u32 ctl, pos, size; + enum pipe pipe; + + ctl = intel_de_read(display, PF_CTL(crtc->pipe)); + if ((ctl & PF_ENABLE) == 0) + return; + + if (display->platform.ivybridge || display->platform.haswell) + pipe = REG_FIELD_GET(PF_PIPE_SEL_MASK_IVB, ctl); + else + pipe = crtc->pipe; + + crtc_state->pch_pfit.enabled = true; + + pos = intel_de_read(display, PF_WIN_POS(crtc->pipe)); + size = intel_de_read(display, PF_WIN_SZ(crtc->pipe)); + + drm_rect_init(&crtc_state->pch_pfit.dst, + REG_FIELD_GET(PF_WIN_XPOS_MASK, pos), + REG_FIELD_GET(PF_WIN_YPOS_MASK, pos), + REG_FIELD_GET(PF_WIN_XSIZE_MASK, size), + REG_FIELD_GET(PF_WIN_YSIZE_MASK, size)); + + /* + * We currently do not free assignments of panel fitters on + * ivb/hsw (since we don't use the higher upscaling modes which + * differentiates them) so just WARN about this case for now. + */ + drm_WARN_ON(display->drm, pipe != crtc->pipe); +} + +void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state) +{ + struct intel_display *display = to_intel_display(crtc_state); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + + if (!crtc_state->gmch_pfit.control) + return; + + /* + * The panel fitter should only be adjusted whilst the pipe is disabled, + * according to register description and PRM. + */ + drm_WARN_ON(display->drm, + intel_de_read(display, PFIT_CONTROL(display)) & PFIT_ENABLE); + assert_transcoder_disabled(display, crtc_state->cpu_transcoder); + + intel_de_write(display, PFIT_PGM_RATIOS(display), + crtc_state->gmch_pfit.pgm_ratios); + intel_de_write(display, PFIT_CONTROL(display), + crtc_state->gmch_pfit.control); + + /* + * Border color in case we don't scale up to the full screen. Black by + * default, change to something else for debugging. + */ + intel_de_write(display, BCLRPAT(display, crtc->pipe), 0); +} + +void i9xx_pfit_disable(const struct intel_crtc_state *old_crtc_state) +{ + struct intel_display *display = to_intel_display(old_crtc_state); + + if (!old_crtc_state->gmch_pfit.control) + return; + + assert_transcoder_disabled(display, old_crtc_state->cpu_transcoder); + + drm_dbg_kms(display->drm, "disabling pfit, current: 0x%08x\n", + intel_de_read(display, PFIT_CONTROL(display))); + intel_de_write(display, PFIT_CONTROL(display), 0); +} + +static bool i9xx_has_pfit(struct intel_display *display) +{ + if (display->platform.i830) + return false; + + return DISPLAY_VER(display) >= 4 || + display->platform.pineview || display->platform.mobile; +} + +void i9xx_pfit_get_config(struct intel_crtc_state *crtc_state) +{ + struct intel_display *display = to_intel_display(crtc_state); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + enum pipe pipe; + u32 tmp; + + if (!i9xx_has_pfit(display)) + return; + + tmp = intel_de_read(display, PFIT_CONTROL(display)); + if (!(tmp & PFIT_ENABLE)) + return; + + /* Check whether the pfit is attached to our pipe. */ + if (DISPLAY_VER(display) >= 4) + pipe = REG_FIELD_GET(PFIT_PIPE_MASK, tmp); + else + pipe = PIPE_B; + + if (pipe != crtc->pipe) + return; + + crtc_state->gmch_pfit.control = tmp; + crtc_state->gmch_pfit.pgm_ratios = + intel_de_read(display, PFIT_PGM_RATIOS(display)); +} diff --git a/drivers/gpu/drm/i915/display/intel_pfit.h b/drivers/gpu/drm/i915/display/intel_pfit.h index add8d78de2c9..ef34f9b49d09 100644 --- a/drivers/gpu/drm/i915/display/intel_pfit.h +++ b/drivers/gpu/drm/i915/display/intel_pfit.h @@ -9,7 +9,13 @@ struct drm_connector_state; struct intel_crtc_state; -int intel_panel_fitting(struct intel_crtc_state *crtc_state, - const struct drm_connector_state *conn_state); +int intel_pfit_compute_config(struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state); +void ilk_pfit_enable(const struct intel_crtc_state *crtc_state); +void ilk_pfit_disable(const struct intel_crtc_state *old_crtc_state); +void ilk_pfit_get_config(struct intel_crtc_state *crtc_state); +void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state); +void i9xx_pfit_disable(const struct intel_crtc_state *old_crtc_state); +void i9xx_pfit_get_config(struct intel_crtc_state *crtc_state); #endif /* __INTEL_PFIT_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_pfit_regs.h b/drivers/gpu/drm/i915/display/intel_pfit_regs.h new file mode 100644 index 000000000000..add8ce28004e --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_pfit_regs.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright © 2025 Intel Corporation */ + +#ifndef __INTEL_PFIT_REGS_H__ +#define __INTEL_PFIT_REGS_H__ + +#include "intel_display_reg_defs.h" + +/* Panel fitting */ +#define PFIT_CONTROL(dev_priv) _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61230) +#define PFIT_ENABLE REG_BIT(31) +#define PFIT_PIPE_MASK REG_GENMASK(30, 29) /* 965+ */ +#define PFIT_PIPE(pipe) REG_FIELD_PREP(PFIT_PIPE_MASK, (pipe)) +#define PFIT_SCALING_MASK REG_GENMASK(28, 26) /* 965+ */ +#define PFIT_SCALING_AUTO REG_FIELD_PREP(PFIT_SCALING_MASK, 0) +#define PFIT_SCALING_PROGRAMMED REG_FIELD_PREP(PFIT_SCALING_MASK, 1) +#define PFIT_SCALING_PILLAR REG_FIELD_PREP(PFIT_SCALING_MASK, 2) +#define PFIT_SCALING_LETTER REG_FIELD_PREP(PFIT_SCALING_MASK, 3) +#define PFIT_FILTER_MASK REG_GENMASK(25, 24) /* 965+ */ +#define PFIT_FILTER_FUZZY REG_FIELD_PREP(PFIT_FILTER_MASK, 0) +#define PFIT_FILTER_CRISP REG_FIELD_PREP(PFIT_FILTER_MASK, 1) +#define PFIT_FILTER_MEDIAN REG_FIELD_PREP(PFIT_FILTER_MASK, 2) +#define PFIT_VERT_INTERP_MASK REG_GENMASK(11, 10) /* pre-965 */ +#define PFIT_VERT_INTERP_BILINEAR REG_FIELD_PREP(PFIT_VERT_INTERP_MASK, 1) +#define PFIT_VERT_AUTO_SCALE REG_BIT(9) /* pre-965 */ +#define PFIT_HORIZ_INTERP_MASK REG_GENMASK(7, 6) /* pre-965 */ +#define PFIT_HORIZ_INTERP_BILINEAR REG_FIELD_PREP(PFIT_HORIZ_INTERP_MASK, 1) +#define PFIT_HORIZ_AUTO_SCALE REG_BIT(5) /* pre-965 */ +#define PFIT_PANEL_8TO6_DITHER_ENABLE REG_BIT(3) /* pre-965 */ + +#define PFIT_PGM_RATIOS(dev_priv) _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61234) +#define PFIT_VERT_SCALE_MASK REG_GENMASK(31, 20) /* pre-965 */ +#define PFIT_VERT_SCALE(x) REG_FIELD_PREP(PFIT_VERT_SCALE_MASK, (x)) +#define PFIT_HORIZ_SCALE_MASK REG_GENMASK(15, 4) /* pre-965 */ +#define PFIT_HORIZ_SCALE(x) REG_FIELD_PREP(PFIT_HORIZ_SCALE_MASK, (x)) +#define PFIT_VERT_SCALE_MASK_965 REG_GENMASK(28, 16) /* 965+ */ +#define PFIT_HORIZ_SCALE_MASK_965 REG_GENMASK(12, 0) /* 965+ */ + +#define PFIT_AUTO_RATIOS(dev_priv) _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61238) + +/* CPU panel fitter */ +/* IVB+ has 3 fitters, 0 is 7x5 capable, the other two only 3x3 */ +#define _PFA_CTL_1 0x68080 +#define _PFB_CTL_1 0x68880 +#define PF_CTL(pipe) _MMIO_PIPE(pipe, _PFA_CTL_1, _PFB_CTL_1) +#define PF_ENABLE REG_BIT(31) +#define PF_PIPE_SEL_MASK_IVB REG_GENMASK(30, 29) /* ivb/hsw */ +#define PF_PIPE_SEL_IVB(pipe) REG_FIELD_PREP(PF_PIPE_SEL_MASK_IVB, (pipe)) +#define PF_FILTER_MASK REG_GENMASK(24, 23) +#define PF_FILTER_PROGRAMMED REG_FIELD_PREP(PF_FILTER_MASK, 0) +#define PF_FILTER_MED_3x3 REG_FIELD_PREP(PF_FILTER_MASK, 1) +#define PF_FILTER_EDGE_ENHANCE REG_FIELD_PREP(PF_FILTER_EDGE_MASK, 2) +#define PF_FILTER_EDGE_SOFTEN REG_FIELD_PREP(PF_FILTER_EDGE_MASK, 3) + +#define _PFA_WIN_SZ 0x68074 +#define _PFB_WIN_SZ 0x68874 +#define PF_WIN_SZ(pipe) _MMIO_PIPE(pipe, _PFA_WIN_SZ, _PFB_WIN_SZ) +#define PF_WIN_XSIZE_MASK REG_GENMASK(31, 16) +#define PF_WIN_XSIZE(w) REG_FIELD_PREP(PF_WIN_XSIZE_MASK, (w)) +#define PF_WIN_YSIZE_MASK REG_GENMASK(15, 0) +#define PF_WIN_YSIZE(h) REG_FIELD_PREP(PF_WIN_YSIZE_MASK, (h)) + +#define _PFA_WIN_POS 0x68070 +#define _PFB_WIN_POS 0x68870 +#define PF_WIN_POS(pipe) _MMIO_PIPE(pipe, _PFA_WIN_POS, _PFB_WIN_POS) +#define PF_WIN_XPOS_MASK REG_GENMASK(31, 16) +#define PF_WIN_XPOS(x) REG_FIELD_PREP(PF_WIN_XPOS_MASK, (x)) +#define PF_WIN_YPOS_MASK REG_GENMASK(15, 0) +#define PF_WIN_YPOS(y) REG_FIELD_PREP(PF_WIN_YPOS_MASK, (y)) + +#define _PFA_VSCALE 0x68084 +#define _PFB_VSCALE 0x68884 +#define PF_VSCALE(pipe) _MMIO_PIPE(pipe, _PFA_VSCALE, _PFB_VSCALE) + +#define _PFA_HSCALE 0x68090 +#define _PFB_HSCALE 0x68890 +#define PF_HSCALE(pipe) _MMIO_PIPE(pipe, _PFA_HSCALE, _PFB_HSCALE) + +#endif /* __INTEL_PFIT_REGS_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_pipe_crc.h b/drivers/gpu/drm/i915/display/intel_pipe_crc.h index 43012b189415..6ddcea38488b 100644 --- a/drivers/gpu/drm/i915/display/intel_pipe_crc.h +++ b/drivers/gpu/drm/i915/display/intel_pipe_crc.h @@ -9,7 +9,6 @@ #include <linux/types.h> struct drm_crtc; -struct drm_i915_private; struct intel_crtc; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/gpu/drm/i915/display/intel_quirks.c b/drivers/gpu/drm/i915/display/intel_quirks.c index 8b30e9fd936e..a32fae510ed2 100644 --- a/drivers/gpu/drm/i915/display/intel_quirks.c +++ b/drivers/gpu/drm/i915/display/intel_quirks.c @@ -5,6 +5,8 @@ #include <linux/dmi.h> +#include <drm/drm_print.h> + #include "intel_display_core.h" #include "intel_display_types.h" #include "intel_quirks.h" diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy.c b/drivers/gpu/drm/i915/display/intel_snps_phy.c index 353221d3e29f..b9acd9fe160c 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_phy.c +++ b/drivers/gpu/drm/i915/display/intel_snps_phy.c @@ -5,8 +5,8 @@ #include <linux/math.h> -#include "i915_drv.h" #include "i915_reg.h" +#include "i915_utils.h" #include "intel_ddi.h" #include "intel_ddi_buf_trans.h" #include "intel_de.h" @@ -27,12 +27,12 @@ * since it is not handled by the shared DPLL framework as on other platforms. */ -void intel_snps_phy_wait_for_calibration(struct drm_i915_private *i915) +void intel_snps_phy_wait_for_calibration(struct intel_display *display) { enum phy phy; for_each_phy_masked(phy, ~0) { - if (!intel_phy_is_snps(i915, phy)) + if (!intel_phy_is_snps(display, phy)) continue; /* @@ -40,16 +40,16 @@ void intel_snps_phy_wait_for_calibration(struct drm_i915_private *i915) * which phy was affected and skip setup of the corresponding * output later. */ - if (intel_de_wait_for_clear(i915, DG2_PHY_MISC(phy), + if (intel_de_wait_for_clear(display, DG2_PHY_MISC(phy), DG2_PHY_DP_TX_ACK_MASK, 25)) - i915->display.snps.phy_failed_calibration |= BIT(phy); + display->snps.phy_failed_calibration |= BIT(phy); } } void intel_snps_phy_update_psr_power_state(struct intel_encoder *encoder, bool enable) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_display *display = to_intel_display(encoder); enum phy phy = intel_encoder_to_phy(encoder); u32 val; @@ -58,20 +58,20 @@ void intel_snps_phy_update_psr_power_state(struct intel_encoder *encoder, val = REG_FIELD_PREP(SNPS_PHY_TX_REQ_LN_DIS_PWR_STATE_PSR, enable ? 2 : 3); - intel_de_rmw(i915, SNPS_PHY_TX_REQ(phy), + intel_de_rmw(display, SNPS_PHY_TX_REQ(phy), SNPS_PHY_TX_REQ_LN_DIS_PWR_STATE_PSR, val); } void intel_snps_phy_set_signal_levels(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_display *display = to_intel_display(encoder); const struct intel_ddi_buf_trans *trans; enum phy phy = intel_encoder_to_phy(encoder); int n_entries, ln; trans = encoder->get_buf_trans(encoder, crtc_state, &n_entries); - if (drm_WARN_ON_ONCE(&dev_priv->drm, !trans)) + if (drm_WARN_ON_ONCE(display->drm, !trans)) return; for (ln = 0; ln < 4; ln++) { @@ -82,7 +82,7 @@ void intel_snps_phy_set_signal_levels(struct intel_encoder *encoder, val |= REG_FIELD_PREP(SNPS_PHY_TX_EQ_PRE, trans->entries[level].snps.pre_cursor); val |= REG_FIELD_PREP(SNPS_PHY_TX_EQ_POST, trans->entries[level].snps.post_cursor); - intel_de_write(dev_priv, SNPS_PHY_TX_EQ(ln, phy), val); + intel_de_write(display, SNPS_PHY_TX_EQ(ln, phy), val); } } @@ -1817,7 +1817,7 @@ int intel_mpllb_calc_state(struct intel_crtc_state *crtc_state, void intel_mpllb_enable(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_display *display = to_intel_display(encoder); const struct intel_mpllb_state *pll_state = &crtc_state->dpll_hw_state.mpllb; enum phy phy = intel_encoder_to_phy(encoder); i915_reg_t enable_reg = (phy <= PHY_D ? @@ -1827,13 +1827,13 @@ void intel_mpllb_enable(struct intel_encoder *encoder, * 3. Software programs the following PLL registers for the desired * frequency. */ - intel_de_write(dev_priv, SNPS_PHY_MPLLB_CP(phy), pll_state->mpllb_cp); - intel_de_write(dev_priv, SNPS_PHY_MPLLB_DIV(phy), pll_state->mpllb_div); - intel_de_write(dev_priv, SNPS_PHY_MPLLB_DIV2(phy), pll_state->mpllb_div2); - intel_de_write(dev_priv, SNPS_PHY_MPLLB_SSCEN(phy), pll_state->mpllb_sscen); - intel_de_write(dev_priv, SNPS_PHY_MPLLB_SSCSTEP(phy), pll_state->mpllb_sscstep); - intel_de_write(dev_priv, SNPS_PHY_MPLLB_FRACN1(phy), pll_state->mpllb_fracn1); - intel_de_write(dev_priv, SNPS_PHY_MPLLB_FRACN2(phy), pll_state->mpllb_fracn2); + intel_de_write(display, SNPS_PHY_MPLLB_CP(phy), pll_state->mpllb_cp); + intel_de_write(display, SNPS_PHY_MPLLB_DIV(phy), pll_state->mpllb_div); + intel_de_write(display, SNPS_PHY_MPLLB_DIV2(phy), pll_state->mpllb_div2); + intel_de_write(display, SNPS_PHY_MPLLB_SSCEN(phy), pll_state->mpllb_sscen); + intel_de_write(display, SNPS_PHY_MPLLB_SSCSTEP(phy), pll_state->mpllb_sscstep); + intel_de_write(display, SNPS_PHY_MPLLB_FRACN1(phy), pll_state->mpllb_fracn1); + intel_de_write(display, SNPS_PHY_MPLLB_FRACN2(phy), pll_state->mpllb_fracn2); /* * 4. If the frequency will result in a change to the voltage @@ -1844,7 +1844,7 @@ void intel_mpllb_enable(struct intel_encoder *encoder, */ /* 5. Software sets DPLL_ENABLE [PLL Enable] to "1". */ - intel_de_rmw(dev_priv, enable_reg, 0, PLL_ENABLE); + intel_de_rmw(display, enable_reg, 0, PLL_ENABLE); /* * 9. Software sets SNPS_PHY_MPLLB_DIV dp_mpllb_force_en to "1". This @@ -1853,7 +1853,7 @@ void intel_mpllb_enable(struct intel_encoder *encoder, * PLL because that will start the PLL before it has sampled the * divider values. */ - intel_de_write(dev_priv, SNPS_PHY_MPLLB_DIV(phy), + intel_de_write(display, SNPS_PHY_MPLLB_DIV(phy), pll_state->mpllb_div | SNPS_PHY_MPLLB_FORCE_EN); /* @@ -1861,8 +1861,8 @@ void intel_mpllb_enable(struct intel_encoder *encoder, * is locked at new settings. This register bit is sampling PHY * dp_mpllb_state interface signal. */ - if (intel_de_wait_for_set(dev_priv, enable_reg, PLL_LOCK, 5)) - drm_dbg_kms(&dev_priv->drm, "Port %c PLL not locked\n", phy_name(phy)); + if (intel_de_wait_for_set(display, enable_reg, PLL_LOCK, 5)) + drm_dbg_kms(display->drm, "Port %c PLL not locked\n", phy_name(phy)); /* * 11. If the frequency will result in a change to the voltage @@ -1875,7 +1875,7 @@ void intel_mpllb_enable(struct intel_encoder *encoder, void intel_mpllb_disable(struct intel_encoder *encoder) { - struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_display *display = to_intel_display(encoder); enum phy phy = intel_encoder_to_phy(encoder); i915_reg_t enable_reg = (phy <= PHY_D ? DG2_PLL_ENABLE(phy) : MG_PLL_ENABLE(0)); @@ -1889,20 +1889,20 @@ void intel_mpllb_disable(struct intel_encoder *encoder) */ /* 2. Software programs DPLL_ENABLE [PLL Enable] to "0" */ - intel_de_rmw(i915, enable_reg, PLL_ENABLE, 0); + intel_de_rmw(display, enable_reg, PLL_ENABLE, 0); /* * 4. Software programs SNPS_PHY_MPLLB_DIV dp_mpllb_force_en to "0". * This will allow the PLL to stop running. */ - intel_de_rmw(i915, SNPS_PHY_MPLLB_DIV(phy), SNPS_PHY_MPLLB_FORCE_EN, 0); + intel_de_rmw(display, SNPS_PHY_MPLLB_DIV(phy), SNPS_PHY_MPLLB_FORCE_EN, 0); /* * 5. Software polls DPLL_ENABLE [PLL Lock] for PHY acknowledgment * (dp_txX_ack) that the new transmitter setting request is completed. */ - if (intel_de_wait_for_clear(i915, enable_reg, PLL_LOCK, 5)) - drm_err(&i915->drm, "Port %c PLL not locked\n", phy_name(phy)); + if (intel_de_wait_for_clear(display, enable_reg, PLL_LOCK, 5)) + drm_err(display->drm, "Port %c PLL not locked\n", phy_name(phy)); /* * 6. If the frequency will result in a change to the voltage @@ -1947,16 +1947,16 @@ int intel_mpllb_calc_port_clock(struct intel_encoder *encoder, void intel_mpllb_readout_hw_state(struct intel_encoder *encoder, struct intel_mpllb_state *pll_state) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_display *display = to_intel_display(encoder); enum phy phy = intel_encoder_to_phy(encoder); - pll_state->mpllb_cp = intel_de_read(dev_priv, SNPS_PHY_MPLLB_CP(phy)); - pll_state->mpllb_div = intel_de_read(dev_priv, SNPS_PHY_MPLLB_DIV(phy)); - pll_state->mpllb_div2 = intel_de_read(dev_priv, SNPS_PHY_MPLLB_DIV2(phy)); - pll_state->mpllb_sscen = intel_de_read(dev_priv, SNPS_PHY_MPLLB_SSCEN(phy)); - pll_state->mpllb_sscstep = intel_de_read(dev_priv, SNPS_PHY_MPLLB_SSCSTEP(phy)); - pll_state->mpllb_fracn1 = intel_de_read(dev_priv, SNPS_PHY_MPLLB_FRACN1(phy)); - pll_state->mpllb_fracn2 = intel_de_read(dev_priv, SNPS_PHY_MPLLB_FRACN2(phy)); + pll_state->mpllb_cp = intel_de_read(display, SNPS_PHY_MPLLB_CP(phy)); + pll_state->mpllb_div = intel_de_read(display, SNPS_PHY_MPLLB_DIV(phy)); + pll_state->mpllb_div2 = intel_de_read(display, SNPS_PHY_MPLLB_DIV2(phy)); + pll_state->mpllb_sscen = intel_de_read(display, SNPS_PHY_MPLLB_SSCEN(phy)); + pll_state->mpllb_sscstep = intel_de_read(display, SNPS_PHY_MPLLB_SSCSTEP(phy)); + pll_state->mpllb_fracn1 = intel_de_read(display, SNPS_PHY_MPLLB_FRACN1(phy)); + pll_state->mpllb_fracn2 = intel_de_read(display, SNPS_PHY_MPLLB_FRACN2(phy)); /* * REF_CONTROL is under firmware control and never programmed by the @@ -1964,7 +1964,7 @@ void intel_mpllb_readout_hw_state(struct intel_encoder *encoder, * only tells us the expected value for one field in this register, * so we'll only read out those specific bits here. */ - pll_state->ref_control = intel_de_read(dev_priv, SNPS_PHY_REF_CONTROL(phy)) & + pll_state->ref_control = intel_de_read(display, SNPS_PHY_REF_CONTROL(phy)) & SNPS_PHY_REF_CONTROL_REF_RANGE; /* @@ -1980,14 +1980,13 @@ void intel_mpllb_state_verify(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct intel_display *display = to_intel_display(state); - struct drm_i915_private *i915 = to_i915(state->base.dev); const struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); struct intel_mpllb_state mpllb_hw_state = {}; const struct intel_mpllb_state *mpllb_sw_state = &new_crtc_state->dpll_hw_state.mpllb; struct intel_encoder *encoder; - if (!IS_DG2(i915)) + if (!display->platform.dg2) return; if (!new_crtc_state->hw.active) diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy.h b/drivers/gpu/drm/i915/display/intel_snps_phy.h index 1dd564ed9fa8..7f96da22d028 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_phy.h +++ b/drivers/gpu/drm/i915/display/intel_snps_phy.h @@ -8,15 +8,15 @@ #include <linux/types.h> -struct drm_i915_private; +enum phy; struct intel_atomic_state; struct intel_crtc; struct intel_crtc_state; +struct intel_display; struct intel_encoder; struct intel_mpllb_state; -enum phy; -void intel_snps_phy_wait_for_calibration(struct drm_i915_private *dev_priv); +void intel_snps_phy_wait_for_calibration(struct intel_display *display); void intel_snps_phy_update_psr_power_state(struct intel_encoder *encoder, bool enable); diff --git a/drivers/gpu/drm/i915/display/intel_tdf.h b/drivers/gpu/drm/i915/display/intel_tdf.h index 353cde21f6c2..0862c2bfd9cd 100644 --- a/drivers/gpu/drm/i915/display/intel_tdf.h +++ b/drivers/gpu/drm/i915/display/intel_tdf.h @@ -14,12 +14,12 @@ * the display flip, since display engine is never coherent with CPU/GPU caches. */ -struct drm_i915_private; +struct intel_display; #ifdef I915 -static inline void intel_td_flush(struct drm_i915_private *i915) {} +static inline void intel_td_flush(struct intel_display *display) {} #else -void intel_td_flush(struct drm_i915_private *i915); +void intel_td_flush(struct intel_display *display); #endif #endif diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index 6e7151346382..3ed64c17bdff 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -10,7 +10,7 @@ #include <drm/display/drm_dsc_helper.h> #include <drm/drm_fixed.h> -#include "i915_drv.h" +#include "i915_utils.h" #include "intel_crtc.h" #include "intel_de.h" #include "intel_display_types.h" @@ -22,14 +22,13 @@ bool intel_dsc_source_support(const struct intel_crtc_state *crtc_state) { - const struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc_state); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; - if (!HAS_DSC(i915)) + if (!HAS_DSC(display)) return false; - if (DISPLAY_VER(i915) == 11 && cpu_transcoder == TRANSCODER_A) + if (DISPLAY_VER(display) == 11 && cpu_transcoder == TRANSCODER_A) return false; return true; @@ -37,9 +36,9 @@ bool intel_dsc_source_support(const struct intel_crtc_state *crtc_state) static bool is_pipe_dsc(struct intel_crtc *crtc, enum transcoder cpu_transcoder) { - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); - if (DISPLAY_VER(i915) >= 12) + if (DISPLAY_VER(display) >= 12) return true; if (cpu_transcoder == TRANSCODER_EDP || @@ -48,7 +47,7 @@ static bool is_pipe_dsc(struct intel_crtc *crtc, enum transcoder cpu_transcoder) return false; /* There's no pipe A DSC engine on ICL */ - drm_WARN_ON(&i915->drm, crtc->pipe == PIPE_A); + drm_WARN_ON(display->drm, crtc->pipe == PIPE_A); return true; } @@ -262,8 +261,7 @@ static int intel_dsc_slice_dimensions_valid(struct intel_crtc_state *pipe_config int intel_dsc_compute_params(struct intel_crtc_state *pipe_config) { - struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(pipe_config); struct drm_dsc_config *vdsc_cfg = &pipe_config->dsc.config; u16 compressed_bpp = fxp_q4_to_int(pipe_config->dsc.compressed_bpp_x16); int err; @@ -276,7 +274,7 @@ int intel_dsc_compute_params(struct intel_crtc_state *pipe_config) err = intel_dsc_slice_dimensions_valid(pipe_config, vdsc_cfg); if (err) { - drm_dbg_kms(&dev_priv->drm, "Slice dimension requirements not met\n"); + drm_dbg_kms(display->drm, "Slice dimension requirements not met\n"); return err; } @@ -287,7 +285,7 @@ int intel_dsc_compute_params(struct intel_crtc_state *pipe_config) vdsc_cfg->convert_rgb = pipe_config->output_format != INTEL_OUTPUT_FORMAT_YCBCR420 && pipe_config->output_format != INTEL_OUTPUT_FORMAT_YCBCR444; - if (DISPLAY_VER(dev_priv) >= 14 && + if (DISPLAY_VER(display) >= 14 && pipe_config->output_format == INTEL_OUTPUT_FORMAT_YCBCR420) vdsc_cfg->native_420 = true; /* We do not support YcBCr422 as of now */ @@ -308,7 +306,7 @@ int intel_dsc_compute_params(struct intel_crtc_state *pipe_config) vdsc_cfg->bits_per_component = pipe_config->pipe_bpp / 3; if (vdsc_cfg->bits_per_component < 8) { - drm_dbg_kms(&dev_priv->drm, "DSC bpc requirements not met bpc: %d\n", + drm_dbg_kms(display->drm, "DSC bpc requirements not met bpc: %d\n", vdsc_cfg->bits_per_component); return -EINVAL; } @@ -320,7 +318,7 @@ int intel_dsc_compute_params(struct intel_crtc_state *pipe_config) * upto uncompressed bpp-1, hence add calculations for all the rc * parameters */ - if (DISPLAY_VER(dev_priv) >= 13) { + if (DISPLAY_VER(display) >= 13) { calculate_rc_params(vdsc_cfg); } else { if ((compressed_bpp == 8 || @@ -356,7 +354,7 @@ int intel_dsc_compute_params(struct intel_crtc_state *pipe_config) enum intel_display_power_domain intel_dsc_power_domain(struct intel_crtc *crtc, enum transcoder cpu_transcoder) { - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc); enum pipe pipe = crtc->pipe; /* @@ -370,7 +368,8 @@ intel_dsc_power_domain(struct intel_crtc *crtc, enum transcoder cpu_transcoder) * the pipe in use. Hence another reference on the pipe power domain * will suffice. (Except no VDSC/joining on ICL pipe A.) */ - if (DISPLAY_VER(i915) == 12 && !IS_ROCKETLAKE(i915) && pipe == PIPE_A) + if (DISPLAY_VER(display) == 12 && !display->platform.rocketlake && + pipe == PIPE_A) return POWER_DOMAIN_TRANSCODER_VDSC_PW2; else if (is_pipe_dsc(crtc, cpu_transcoder)) return POWER_DOMAIN_PIPE(pipe); @@ -416,26 +415,25 @@ static void intel_dsc_get_pps_reg(const struct intel_crtc_state *crtc_state, int static void intel_dsc_pps_write(const struct intel_crtc_state *crtc_state, int pps, u32 pps_val) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc_state); i915_reg_t dsc_reg[3]; int i, vdsc_per_pipe, dsc_reg_num; vdsc_per_pipe = intel_dsc_get_vdsc_per_pipe(crtc_state); dsc_reg_num = min_t(int, ARRAY_SIZE(dsc_reg), vdsc_per_pipe); - drm_WARN_ON_ONCE(&i915->drm, dsc_reg_num < vdsc_per_pipe); + drm_WARN_ON_ONCE(display->drm, dsc_reg_num < vdsc_per_pipe); intel_dsc_get_pps_reg(crtc_state, pps, dsc_reg, dsc_reg_num); for (i = 0; i < dsc_reg_num; i++) - intel_de_write(i915, dsc_reg[i], pps_val); + intel_de_write(display, dsc_reg[i], pps_val); } static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; enum pipe pipe = crtc->pipe; @@ -529,7 +527,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) vdsc_cfg->slice_height); intel_dsc_pps_write(crtc_state, 16, pps_val); - if (DISPLAY_VER(dev_priv) >= 14) { + if (DISPLAY_VER(display) >= 14) { /* PPS 17 */ pps_val = DSC_PPS17_SL_BPG_OFFSET(vdsc_cfg->second_line_bpg_offset); intel_dsc_pps_write(crtc_state, 17, pps_val); @@ -547,44 +545,44 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) (u32)(vdsc_cfg->rc_buf_thresh[i] << BITS_PER_BYTE * (i % 4)); if (!is_pipe_dsc(crtc, cpu_transcoder)) { - intel_de_write(dev_priv, DSCA_RC_BUF_THRESH_0, + intel_de_write(display, DSCA_RC_BUF_THRESH_0, rc_buf_thresh_dword[0]); - intel_de_write(dev_priv, DSCA_RC_BUF_THRESH_0_UDW, + intel_de_write(display, DSCA_RC_BUF_THRESH_0_UDW, rc_buf_thresh_dword[1]); - intel_de_write(dev_priv, DSCA_RC_BUF_THRESH_1, + intel_de_write(display, DSCA_RC_BUF_THRESH_1, rc_buf_thresh_dword[2]); - intel_de_write(dev_priv, DSCA_RC_BUF_THRESH_1_UDW, + intel_de_write(display, DSCA_RC_BUF_THRESH_1_UDW, rc_buf_thresh_dword[3]); if (vdsc_instances_per_pipe > 1) { - intel_de_write(dev_priv, DSCC_RC_BUF_THRESH_0, + intel_de_write(display, DSCC_RC_BUF_THRESH_0, rc_buf_thresh_dword[0]); - intel_de_write(dev_priv, DSCC_RC_BUF_THRESH_0_UDW, + intel_de_write(display, DSCC_RC_BUF_THRESH_0_UDW, rc_buf_thresh_dword[1]); - intel_de_write(dev_priv, DSCC_RC_BUF_THRESH_1, + intel_de_write(display, DSCC_RC_BUF_THRESH_1, rc_buf_thresh_dword[2]); - intel_de_write(dev_priv, DSCC_RC_BUF_THRESH_1_UDW, + intel_de_write(display, DSCC_RC_BUF_THRESH_1_UDW, rc_buf_thresh_dword[3]); } } else { - intel_de_write(dev_priv, ICL_DSC0_RC_BUF_THRESH_0(pipe), + intel_de_write(display, ICL_DSC0_RC_BUF_THRESH_0(pipe), rc_buf_thresh_dword[0]); - intel_de_write(dev_priv, ICL_DSC0_RC_BUF_THRESH_0_UDW(pipe), + intel_de_write(display, ICL_DSC0_RC_BUF_THRESH_0_UDW(pipe), rc_buf_thresh_dword[1]); - intel_de_write(dev_priv, ICL_DSC0_RC_BUF_THRESH_1(pipe), + intel_de_write(display, ICL_DSC0_RC_BUF_THRESH_1(pipe), rc_buf_thresh_dword[2]); - intel_de_write(dev_priv, ICL_DSC0_RC_BUF_THRESH_1_UDW(pipe), + intel_de_write(display, ICL_DSC0_RC_BUF_THRESH_1_UDW(pipe), rc_buf_thresh_dword[3]); if (vdsc_instances_per_pipe > 1) { - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC1_RC_BUF_THRESH_0(pipe), rc_buf_thresh_dword[0]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC1_RC_BUF_THRESH_0_UDW(pipe), rc_buf_thresh_dword[1]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC1_RC_BUF_THRESH_1(pipe), rc_buf_thresh_dword[2]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC1_RC_BUF_THRESH_1_UDW(pipe), rc_buf_thresh_dword[3]); } @@ -601,88 +599,88 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) (vdsc_cfg->rc_range_params[i].range_min_qp << RC_MIN_QP_SHIFT)) << 16 * (i % 2)); if (!is_pipe_dsc(crtc, cpu_transcoder)) { - intel_de_write(dev_priv, DSCA_RC_RANGE_PARAMETERS_0, + intel_de_write(display, DSCA_RC_RANGE_PARAMETERS_0, rc_range_params_dword[0]); - intel_de_write(dev_priv, DSCA_RC_RANGE_PARAMETERS_0_UDW, + intel_de_write(display, DSCA_RC_RANGE_PARAMETERS_0_UDW, rc_range_params_dword[1]); - intel_de_write(dev_priv, DSCA_RC_RANGE_PARAMETERS_1, + intel_de_write(display, DSCA_RC_RANGE_PARAMETERS_1, rc_range_params_dword[2]); - intel_de_write(dev_priv, DSCA_RC_RANGE_PARAMETERS_1_UDW, + intel_de_write(display, DSCA_RC_RANGE_PARAMETERS_1_UDW, rc_range_params_dword[3]); - intel_de_write(dev_priv, DSCA_RC_RANGE_PARAMETERS_2, + intel_de_write(display, DSCA_RC_RANGE_PARAMETERS_2, rc_range_params_dword[4]); - intel_de_write(dev_priv, DSCA_RC_RANGE_PARAMETERS_2_UDW, + intel_de_write(display, DSCA_RC_RANGE_PARAMETERS_2_UDW, rc_range_params_dword[5]); - intel_de_write(dev_priv, DSCA_RC_RANGE_PARAMETERS_3, + intel_de_write(display, DSCA_RC_RANGE_PARAMETERS_3, rc_range_params_dword[6]); - intel_de_write(dev_priv, DSCA_RC_RANGE_PARAMETERS_3_UDW, + intel_de_write(display, DSCA_RC_RANGE_PARAMETERS_3_UDW, rc_range_params_dword[7]); if (vdsc_instances_per_pipe > 1) { - intel_de_write(dev_priv, DSCC_RC_RANGE_PARAMETERS_0, + intel_de_write(display, DSCC_RC_RANGE_PARAMETERS_0, rc_range_params_dword[0]); - intel_de_write(dev_priv, + intel_de_write(display, DSCC_RC_RANGE_PARAMETERS_0_UDW, rc_range_params_dword[1]); - intel_de_write(dev_priv, DSCC_RC_RANGE_PARAMETERS_1, + intel_de_write(display, DSCC_RC_RANGE_PARAMETERS_1, rc_range_params_dword[2]); - intel_de_write(dev_priv, + intel_de_write(display, DSCC_RC_RANGE_PARAMETERS_1_UDW, rc_range_params_dword[3]); - intel_de_write(dev_priv, DSCC_RC_RANGE_PARAMETERS_2, + intel_de_write(display, DSCC_RC_RANGE_PARAMETERS_2, rc_range_params_dword[4]); - intel_de_write(dev_priv, + intel_de_write(display, DSCC_RC_RANGE_PARAMETERS_2_UDW, rc_range_params_dword[5]); - intel_de_write(dev_priv, DSCC_RC_RANGE_PARAMETERS_3, + intel_de_write(display, DSCC_RC_RANGE_PARAMETERS_3, rc_range_params_dword[6]); - intel_de_write(dev_priv, + intel_de_write(display, DSCC_RC_RANGE_PARAMETERS_3_UDW, rc_range_params_dword[7]); } } else { - intel_de_write(dev_priv, ICL_DSC0_RC_RANGE_PARAMETERS_0(pipe), + intel_de_write(display, ICL_DSC0_RC_RANGE_PARAMETERS_0(pipe), rc_range_params_dword[0]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW(pipe), rc_range_params_dword[1]); - intel_de_write(dev_priv, ICL_DSC0_RC_RANGE_PARAMETERS_1(pipe), + intel_de_write(display, ICL_DSC0_RC_RANGE_PARAMETERS_1(pipe), rc_range_params_dword[2]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW(pipe), rc_range_params_dword[3]); - intel_de_write(dev_priv, ICL_DSC0_RC_RANGE_PARAMETERS_2(pipe), + intel_de_write(display, ICL_DSC0_RC_RANGE_PARAMETERS_2(pipe), rc_range_params_dword[4]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW(pipe), rc_range_params_dword[5]); - intel_de_write(dev_priv, ICL_DSC0_RC_RANGE_PARAMETERS_3(pipe), + intel_de_write(display, ICL_DSC0_RC_RANGE_PARAMETERS_3(pipe), rc_range_params_dword[6]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW(pipe), rc_range_params_dword[7]); if (vdsc_instances_per_pipe > 1) { - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC1_RC_RANGE_PARAMETERS_0(pipe), rc_range_params_dword[0]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW(pipe), rc_range_params_dword[1]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC1_RC_RANGE_PARAMETERS_1(pipe), rc_range_params_dword[2]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW(pipe), rc_range_params_dword[3]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC1_RC_RANGE_PARAMETERS_2(pipe), rc_range_params_dword[4]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW(pipe), rc_range_params_dword[5]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC1_RC_RANGE_PARAMETERS_3(pipe), rc_range_params_dword[6]); - intel_de_write(dev_priv, + intel_de_write(display, ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW(pipe), rc_range_params_dword[7]); } @@ -746,8 +744,8 @@ static i915_reg_t dss_ctl2_reg(struct intel_crtc *crtc, enum transcoder cpu_tran void intel_uncompressed_joiner_enable(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); u32 dss_ctl1_val = 0; if (crtc_state->joiner_pipes && !crtc_state->dsc.compression_enable) { @@ -756,14 +754,15 @@ void intel_uncompressed_joiner_enable(const struct intel_crtc_state *crtc_state) else dss_ctl1_val |= UNCOMPRESSED_JOINER_PRIMARY; - intel_de_write(dev_priv, dss_ctl1_reg(crtc, crtc_state->cpu_transcoder), dss_ctl1_val); + intel_de_write(display, dss_ctl1_reg(crtc, crtc_state->cpu_transcoder), + dss_ctl1_val); } } void intel_dsc_enable(const struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); u32 dss_ctl1_val = 0; u32 dss_ctl2_val = 0; int vdsc_instances_per_pipe = intel_dsc_get_vdsc_per_pipe(crtc_state); @@ -796,28 +795,27 @@ void intel_dsc_enable(const struct intel_crtc_state *crtc_state) if (intel_crtc_is_bigjoiner_primary(crtc_state)) dss_ctl1_val |= PRIMARY_BIG_JOINER_ENABLE; } - intel_de_write(dev_priv, dss_ctl1_reg(crtc, crtc_state->cpu_transcoder), dss_ctl1_val); - intel_de_write(dev_priv, dss_ctl2_reg(crtc, crtc_state->cpu_transcoder), dss_ctl2_val); + intel_de_write(display, dss_ctl1_reg(crtc, crtc_state->cpu_transcoder), dss_ctl1_val); + intel_de_write(display, dss_ctl2_reg(crtc, crtc_state->cpu_transcoder), dss_ctl2_val); } void intel_dsc_disable(const struct intel_crtc_state *old_crtc_state) { + struct intel_display *display = to_intel_display(old_crtc_state); struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); /* Disable only if either of them is enabled */ if (old_crtc_state->dsc.compression_enable || old_crtc_state->joiner_pipes) { - intel_de_write(dev_priv, dss_ctl1_reg(crtc, old_crtc_state->cpu_transcoder), 0); - intel_de_write(dev_priv, dss_ctl2_reg(crtc, old_crtc_state->cpu_transcoder), 0); + intel_de_write(display, dss_ctl1_reg(crtc, old_crtc_state->cpu_transcoder), 0); + intel_de_write(display, dss_ctl2_reg(crtc, old_crtc_state->cpu_transcoder), 0); } } static u32 intel_dsc_pps_read(struct intel_crtc_state *crtc_state, int pps, bool *all_equal) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc_state); i915_reg_t dsc_reg[3]; int i, vdsc_per_pipe, dsc_reg_num; u32 val; @@ -825,16 +823,16 @@ static u32 intel_dsc_pps_read(struct intel_crtc_state *crtc_state, int pps, vdsc_per_pipe = intel_dsc_get_vdsc_per_pipe(crtc_state); dsc_reg_num = min_t(int, ARRAY_SIZE(dsc_reg), vdsc_per_pipe); - drm_WARN_ON_ONCE(&i915->drm, dsc_reg_num < vdsc_per_pipe); + drm_WARN_ON_ONCE(display->drm, dsc_reg_num < vdsc_per_pipe); intel_dsc_get_pps_reg(crtc_state, pps, dsc_reg, dsc_reg_num); *all_equal = true; - val = intel_de_read(i915, dsc_reg[0]); + val = intel_de_read(display, dsc_reg[0]); for (i = 1; i < dsc_reg_num; i++) { - if (intel_de_read(i915, dsc_reg[i]) != val) { + if (intel_de_read(display, dsc_reg[i]) != val) { *all_equal = false; break; } @@ -845,22 +843,20 @@ static u32 intel_dsc_pps_read(struct intel_crtc_state *crtc_state, int pps, static u32 intel_dsc_pps_read_and_verify(struct intel_crtc_state *crtc_state, int pps) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_display *display = to_intel_display(crtc_state); u32 val; bool all_equal; val = intel_dsc_pps_read(crtc_state, pps, &all_equal); - drm_WARN_ON(&i915->drm, !all_equal); + drm_WARN_ON(display->drm, !all_equal); return val; } static void intel_dsc_get_pps_config(struct intel_crtc_state *crtc_state) { + struct intel_display *display = to_intel_display(crtc_state); struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *i915 = to_i915(crtc->base.dev); int num_vdsc_instances = intel_dsc_get_num_vdsc_instances(crtc_state); u32 pps_temp; @@ -946,7 +942,7 @@ static void intel_dsc_get_pps_config(struct intel_crtc_state *crtc_state) vdsc_cfg->slice_chunk_size = REG_FIELD_GET(DSC_PPS16_SLICE_CHUNK_SIZE_MASK, pps_temp); - if (DISPLAY_VER(i915) >= 14) { + if (DISPLAY_VER(display) >= 14) { /* PPS 17 */ pps_temp = intel_dsc_pps_read_and_verify(crtc_state, 17); @@ -964,7 +960,6 @@ void intel_dsc_get_config(struct intel_crtc_state *crtc_state) { struct intel_display *display = to_intel_display(crtc_state); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; enum intel_display_power_domain power_domain; intel_wakeref_t wakeref; @@ -979,8 +974,8 @@ void intel_dsc_get_config(struct intel_crtc_state *crtc_state) if (!wakeref) return; - dss_ctl1 = intel_de_read(dev_priv, dss_ctl1_reg(crtc, cpu_transcoder)); - dss_ctl2 = intel_de_read(dev_priv, dss_ctl2_reg(crtc, cpu_transcoder)); + dss_ctl1 = intel_de_read(display, dss_ctl1_reg(crtc, cpu_transcoder)); + dss_ctl2 = intel_de_read(display, dss_ctl2_reg(crtc, cpu_transcoder)); crtc_state->dsc.compression_enable = dss_ctl2 & VDSC0_ENABLE; if (!crtc_state->dsc.compression_enable) @@ -1020,8 +1015,7 @@ void intel_vdsc_state_dump(struct drm_printer *p, int indent, int intel_vdsc_min_cdclk(const struct intel_crtc_state *crtc_state) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct intel_display *display = to_intel_display(crtc); + struct intel_display *display = to_intel_display(crtc_state); int num_vdsc_instances = intel_dsc_get_num_vdsc_instances(crtc_state); int min_cdclk; diff --git a/drivers/gpu/drm/i915/display/intel_wm.c b/drivers/gpu/drm/i915/display/intel_wm.c index d7dc49aecd27..f00f4cfc58e5 100644 --- a/drivers/gpu/drm/i915/display/intel_wm.c +++ b/drivers/gpu/drm/i915/display/intel_wm.c @@ -108,6 +108,12 @@ void intel_wm_get_hw_state(struct drm_i915_private *i915) return i915->display.funcs.wm->get_hw_state(i915); } +void intel_wm_sanitize(struct drm_i915_private *i915) +{ + if (i915->display.funcs.wm->sanitize) + return i915->display.funcs.wm->sanitize(i915); +} + bool intel_wm_plane_visible(const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { diff --git a/drivers/gpu/drm/i915/display/intel_wm.h b/drivers/gpu/drm/i915/display/intel_wm.h index e97cdca89a5c..7d3a447054b3 100644 --- a/drivers/gpu/drm/i915/display/intel_wm.h +++ b/drivers/gpu/drm/i915/display/intel_wm.h @@ -25,6 +25,7 @@ void intel_optimize_watermarks(struct intel_atomic_state *state, struct intel_crtc *crtc); int intel_compute_global_watermarks(struct intel_atomic_state *state); void intel_wm_get_hw_state(struct drm_i915_private *i915); +void intel_wm_sanitize(struct drm_i915_private *i915); bool intel_wm_plane_visible(const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state); void intel_print_wm_latency(struct drm_i915_private *i915, diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c index 3d24fa773094..ee81220a7c88 100644 --- a/drivers/gpu/drm/i915/display/skl_scaler.c +++ b/drivers/gpu/drm/i915/display/skl_scaler.c @@ -666,12 +666,14 @@ static u16 glk_nearest_filter_coef(int t) */ static void glk_program_nearest_filter_coefs(struct intel_display *display, + struct intel_dsb *dsb, enum pipe pipe, int id, int set) { int i; - intel_de_write_fw(display, GLK_PS_COEF_INDEX_SET(pipe, id, set), - PS_COEF_INDEX_AUTO_INC); + intel_de_write_dsb(display, dsb, + GLK_PS_COEF_INDEX_SET(pipe, id, set), + PS_COEF_INDEX_AUTO_INC); for (i = 0; i < 17 * 7; i += 2) { u32 tmp; @@ -683,11 +685,12 @@ static void glk_program_nearest_filter_coefs(struct intel_display *display, t = glk_coef_tap(i + 1); tmp |= glk_nearest_filter_coef(t) << 16; - intel_de_write_fw(display, GLK_PS_COEF_DATA_SET(pipe, id, set), - tmp); + intel_de_write_dsb(display, dsb, + GLK_PS_COEF_DATA_SET(pipe, id, set), tmp); } - intel_de_write_fw(display, GLK_PS_COEF_INDEX_SET(pipe, id, set), 0); + intel_de_write_dsb(display, dsb, + GLK_PS_COEF_INDEX_SET(pipe, id, set), 0); } static u32 skl_scaler_get_filter_select(enum drm_scaling_filter filter, int set) @@ -703,14 +706,15 @@ static u32 skl_scaler_get_filter_select(enum drm_scaling_filter filter, int set) return PS_FILTER_MEDIUM; } -static void skl_scaler_setup_filter(struct intel_display *display, enum pipe pipe, +static void skl_scaler_setup_filter(struct intel_display *display, + struct intel_dsb *dsb, enum pipe pipe, int id, int set, enum drm_scaling_filter filter) { switch (filter) { case DRM_SCALING_FILTER_DEFAULT: break; case DRM_SCALING_FILTER_NEAREST_NEIGHBOR: - glk_program_nearest_filter_coefs(display, pipe, id, set); + glk_program_nearest_filter_coefs(display, dsb, pipe, id, set); break; default: MISSING_CASE(filter); @@ -759,7 +763,7 @@ void skl_pfit_enable(const struct intel_crtc_state *crtc_state) trace_intel_pipe_scaler_update_arm(crtc, id, x, y, width, height); - skl_scaler_setup_filter(display, pipe, id, 0, + skl_scaler_setup_filter(display, NULL, pipe, id, 0, crtc_state->hw.scaling_filter); intel_de_write_fw(display, SKL_PS_CTRL(pipe, id), ps_ctrl); @@ -775,7 +779,8 @@ void skl_pfit_enable(const struct intel_crtc_state *crtc_state) } void -skl_program_plane_scaler(struct intel_plane *plane, +skl_program_plane_scaler(struct intel_dsb *dsb, + struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { @@ -825,35 +830,38 @@ skl_program_plane_scaler(struct intel_plane *plane, trace_intel_plane_scaler_update_arm(plane, scaler_id, crtc_x, crtc_y, crtc_w, crtc_h); - skl_scaler_setup_filter(display, pipe, scaler_id, 0, + skl_scaler_setup_filter(display, dsb, pipe, scaler_id, 0, plane_state->hw.scaling_filter); - intel_de_write_fw(display, SKL_PS_CTRL(pipe, scaler_id), ps_ctrl); - intel_de_write_fw(display, SKL_PS_VPHASE(pipe, scaler_id), - PS_Y_PHASE(y_vphase) | PS_UV_RGB_PHASE(uv_rgb_vphase)); - intel_de_write_fw(display, SKL_PS_HPHASE(pipe, scaler_id), - PS_Y_PHASE(y_hphase) | PS_UV_RGB_PHASE(uv_rgb_hphase)); - intel_de_write_fw(display, SKL_PS_WIN_POS(pipe, scaler_id), - PS_WIN_XPOS(crtc_x) | PS_WIN_YPOS(crtc_y)); - intel_de_write_fw(display, SKL_PS_WIN_SZ(pipe, scaler_id), - PS_WIN_XSIZE(crtc_w) | PS_WIN_YSIZE(crtc_h)); + intel_de_write_dsb(display, dsb, SKL_PS_CTRL(pipe, scaler_id), + ps_ctrl); + intel_de_write_dsb(display, dsb, SKL_PS_VPHASE(pipe, scaler_id), + PS_Y_PHASE(y_vphase) | PS_UV_RGB_PHASE(uv_rgb_vphase)); + intel_de_write_dsb(display, dsb, SKL_PS_HPHASE(pipe, scaler_id), + PS_Y_PHASE(y_hphase) | PS_UV_RGB_PHASE(uv_rgb_hphase)); + intel_de_write_dsb(display, dsb, SKL_PS_WIN_POS(pipe, scaler_id), + PS_WIN_XPOS(crtc_x) | PS_WIN_YPOS(crtc_y)); + intel_de_write_dsb(display, dsb, SKL_PS_WIN_SZ(pipe, scaler_id), + PS_WIN_XSIZE(crtc_w) | PS_WIN_YSIZE(crtc_h)); } -static void skl_detach_scaler(struct intel_crtc *crtc, int id) +static void skl_detach_scaler(struct intel_dsb *dsb, + struct intel_crtc *crtc, int id) { struct intel_display *display = to_intel_display(crtc); trace_intel_scaler_disable_arm(crtc, id); - intel_de_write_fw(display, SKL_PS_CTRL(crtc->pipe, id), 0); - intel_de_write_fw(display, SKL_PS_WIN_POS(crtc->pipe, id), 0); - intel_de_write_fw(display, SKL_PS_WIN_SZ(crtc->pipe, id), 0); + intel_de_write_dsb(display, dsb, SKL_PS_CTRL(crtc->pipe, id), 0); + intel_de_write_dsb(display, dsb, SKL_PS_WIN_POS(crtc->pipe, id), 0); + intel_de_write_dsb(display, dsb, SKL_PS_WIN_SZ(crtc->pipe, id), 0); } /* * This function detaches (aka. unbinds) unused scalers in hardware */ -void skl_detach_scalers(const struct intel_crtc_state *crtc_state) +void skl_detach_scalers(struct intel_dsb *dsb, + const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); const struct intel_crtc_scaler_state *scaler_state = @@ -863,7 +871,7 @@ void skl_detach_scalers(const struct intel_crtc_state *crtc_state) /* loop through and disable scalers that aren't in use */ for (i = 0; i < crtc->num_scalers; i++) { if (!scaler_state->scalers[i].in_use) - skl_detach_scaler(crtc, i); + skl_detach_scaler(dsb, crtc, i); } } @@ -873,7 +881,7 @@ void skl_scaler_disable(const struct intel_crtc_state *old_crtc_state) int i; for (i = 0; i < crtc->num_scalers; i++) - skl_detach_scaler(crtc, i); + skl_detach_scaler(NULL, crtc, i); } void skl_scaler_get_config(struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/skl_scaler.h b/drivers/gpu/drm/i915/display/skl_scaler.h index 4d2e2dbb1666..355ea15260ca 100644 --- a/drivers/gpu/drm/i915/display/skl_scaler.h +++ b/drivers/gpu/drm/i915/display/skl_scaler.h @@ -8,6 +8,7 @@ struct intel_atomic_state; struct intel_crtc; struct intel_crtc_state; +struct intel_dsb; struct intel_plane; struct intel_plane_state; @@ -21,10 +22,12 @@ int intel_atomic_setup_scalers(struct intel_atomic_state *state, void skl_pfit_enable(const struct intel_crtc_state *crtc_state); -void skl_program_plane_scaler(struct intel_plane *plane, +void skl_program_plane_scaler(struct intel_dsb *dsb, + struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state); -void skl_detach_scalers(const struct intel_crtc_state *crtc_state); +void skl_detach_scalers(struct intel_dsb *dsb, + const struct intel_crtc_state *crtc_state); void skl_scaler_disable(const struct intel_crtc_state *old_crtc_state); void skl_scaler_get_config(struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index cd9762947f1d..70e550539bb2 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -1466,7 +1466,7 @@ skl_plane_update_arm(struct intel_dsb *dsb, * TODO: split into noarm+arm pair */ if (plane_state->scaler_id >= 0) - skl_program_plane_scaler(plane, crtc_state, plane_state); + skl_program_plane_scaler(dsb, plane, crtc_state, plane_state); /* * The control register self-arms if the plane was previously @@ -1646,7 +1646,7 @@ icl_plane_update_arm(struct intel_dsb *dsb, * TODO: split into noarm+arm pair */ if (plane_state->scaler_id >= 0) - skl_program_plane_scaler(plane, crtc_state, plane_state); + skl_program_plane_scaler(dsb, plane, crtc_state, plane_state); icl_plane_update_sel_fetch_arm(dsb, plane, crtc_state, plane_state); @@ -2258,18 +2258,55 @@ static bool skl_fb_scalable(const struct drm_framebuffer *fb) static void check_protection(struct intel_plane_state *plane_state) { struct intel_display *display = to_intel_display(plane_state); - struct drm_i915_private *i915 = to_i915(display->drm); const struct drm_framebuffer *fb = plane_state->hw.fb; struct drm_gem_object *obj = intel_fb_bo(fb); if (DISPLAY_VER(display) < 11) return; - plane_state->decrypt = intel_pxp_key_check(i915->pxp, obj, false) == 0; + plane_state->decrypt = intel_pxp_key_check(obj, false) == 0; plane_state->force_black = intel_bo_is_protected(obj) && !plane_state->decrypt; } +static void +make_damage_viewport_relative(struct intel_plane_state *plane_state) +{ + const struct drm_framebuffer *fb = plane_state->hw.fb; + const struct drm_rect *src = &plane_state->uapi.src; + unsigned int rotation = plane_state->hw.rotation; + struct drm_rect *damage = &plane_state->damage; + + if (!drm_rect_visible(damage)) + return; + + if (!fb || !plane_state->uapi.visible) { + plane_state->damage = DRM_RECT_INIT(0, 0, 0, 0); + return; + } + + if (drm_rotation_90_or_270(rotation)) { + drm_rect_rotate(damage, fb->width, fb->height, + DRM_MODE_ROTATE_270); + drm_rect_translate(damage, -(src->y1 >> 16), -(src->x1 >> 16)); + } else { + drm_rect_translate(damage, -(src->x1 >> 16), -(src->y1 >> 16)); + } +} + +static void clip_damage(struct intel_plane_state *plane_state) +{ + struct drm_rect *damage = &plane_state->damage; + struct drm_rect src; + + if (!drm_rect_visible(damage)) + return; + + drm_rect_fp_to_int(&src, &plane_state->uapi.src); + drm_rect_translate(damage, src.x1, src.y1); + drm_rect_intersect(damage, &src); +} + static int skl_plane_check(struct intel_crtc_state *crtc_state, struct intel_plane_state *plane_state) { @@ -2295,6 +2332,8 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state, if (ret) return ret; + make_damage_viewport_relative(plane_state); + ret = skl_check_plane_surface(plane_state); if (ret) return ret; @@ -2310,6 +2349,8 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state, if (ret) return ret; + clip_damage(plane_state); + ret = skl_plane_check_nv12_rotation(plane_state); if (ret) return ret; @@ -2317,8 +2358,10 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state, check_protection(plane_state); /* HW only has 8 bits pixel precision, disable plane if invisible */ - if (!(plane_state->hw.alpha >> 8)) + if (!(plane_state->hw.alpha >> 8)) { plane_state->uapi.visible = false; + plane_state->damage = DRM_RECT_INIT(0, 0, 0, 0); + } plane_state->ctl = skl_plane_ctl(crtc_state, plane_state); diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c index 10a1daad28eb..2d0de1c63308 100644 --- a/drivers/gpu/drm/i915/display/skl_watermark.c +++ b/drivers/gpu/drm/i915/display/skl_watermark.c @@ -3157,6 +3157,7 @@ static void skl_wm_get_hw_state(struct drm_i915_private *i915) dbuf_state->joined_mbus = intel_de_read(display, MBUS_CTL) & MBUS_JOIN; dbuf_state->mdclk_cdclk_ratio = intel_mdclk_cdclk_ratio(display, &display->cdclk.hw); + dbuf_state->active_pipes = 0; for_each_intel_crtc(display->drm, crtc) { struct intel_crtc_state *crtc_state = @@ -3168,8 +3169,10 @@ static void skl_wm_get_hw_state(struct drm_i915_private *i915) memset(&crtc_state->wm.skl.optimal, 0, sizeof(crtc_state->wm.skl.optimal)); - if (crtc_state->hw.active) + if (crtc_state->hw.active) { skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal); + dbuf_state->active_pipes |= BIT(pipe); + } crtc_state->wm.skl.raw = crtc_state->wm.skl.optimal; memset(&dbuf_state->ddb[pipe], 0, sizeof(dbuf_state->ddb[pipe])); @@ -3837,14 +3840,56 @@ static void skl_dbuf_sanitize(struct drm_i915_private *i915) } } -static void skl_wm_get_hw_state_and_sanitize(struct drm_i915_private *i915) +static void skl_wm_sanitize(struct drm_i915_private *i915) { - skl_wm_get_hw_state(i915); - skl_mbus_sanitize(i915); skl_dbuf_sanitize(i915); } +void skl_wm_crtc_disable_noatomic(struct intel_crtc *crtc) +{ + struct intel_display *display = to_intel_display(crtc); + struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + struct intel_dbuf_state *dbuf_state = + to_intel_dbuf_state(display->dbuf.obj.state); + enum pipe pipe = crtc->pipe; + + if (DISPLAY_VER(display) < 9) + return; + + dbuf_state->active_pipes &= ~BIT(pipe); + + dbuf_state->weight[pipe] = 0; + dbuf_state->slices[pipe] = 0; + + memset(&dbuf_state->ddb[pipe], 0, sizeof(dbuf_state->ddb[pipe])); + + memset(&crtc_state->wm.skl.ddb, 0, sizeof(crtc_state->wm.skl.ddb)); +} + +void skl_wm_plane_disable_noatomic(struct intel_crtc *crtc, + struct intel_plane *plane) +{ + struct intel_display *display = to_intel_display(crtc); + struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + + if (DISPLAY_VER(display) < 9) + return; + + skl_ddb_entry_init(&crtc_state->wm.skl.plane_ddb[plane->id], 0, 0); + skl_ddb_entry_init(&crtc_state->wm.skl.plane_ddb[plane->id], 0, 0); + + crtc_state->wm.skl.plane_min_ddb[plane->id] = 0; + crtc_state->wm.skl.plane_interim_ddb[plane->id] = 0; + + memset(&crtc_state->wm.skl.raw.planes[plane->id], 0, + sizeof(crtc_state->wm.skl.raw.planes[plane->id])); + memset(&crtc_state->wm.skl.optimal.planes[plane->id], 0, + sizeof(crtc_state->wm.skl.optimal.planes[plane->id])); +} + void intel_wm_state_verify(struct intel_atomic_state *state, struct intel_crtc *crtc) { @@ -3972,7 +4017,8 @@ void intel_wm_state_verify(struct intel_atomic_state *state, static const struct intel_wm_funcs skl_wm_funcs = { .compute_global_watermarks = skl_compute_wm, - .get_hw_state = skl_wm_get_hw_state_and_sanitize, + .get_hw_state = skl_wm_get_hw_state, + .sanitize = skl_wm_sanitize, }; void skl_wm_init(struct drm_i915_private *i915) diff --git a/drivers/gpu/drm/i915/display/skl_watermark.h b/drivers/gpu/drm/i915/display/skl_watermark.h index c5547485225a..d9cff6c54310 100644 --- a/drivers/gpu/drm/i915/display/skl_watermark.h +++ b/drivers/gpu/drm/i915/display/skl_watermark.h @@ -41,6 +41,10 @@ bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry *ddb, void intel_wm_state_verify(struct intel_atomic_state *state, struct intel_crtc *crtc); +void skl_wm_crtc_disable_noatomic(struct intel_crtc *crtc); +void skl_wm_plane_disable_noatomic(struct intel_crtc *crtc, + struct intel_plane *plane); + void skl_watermark_ipc_init(struct drm_i915_private *i915); void skl_watermark_ipc_update(struct drm_i915_private *i915); bool skl_watermark_ipc_enabled(struct drm_i915_private *i915); diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index 7414794889e9..af717df83197 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -283,7 +283,7 @@ static int intel_dsi_compute_config(struct intel_encoder *encoder, if (ret) return ret; - ret = intel_panel_fitting(pipe_config, conn_state); + ret = intel_pfit_compute_config(pipe_config, conn_state); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_pll.h b/drivers/gpu/drm/i915/display/vlv_dsi_pll.h index a032cc2a2524..f975660fa609 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi_pll.h +++ b/drivers/gpu/drm/i915/display/vlv_dsi_pll.h @@ -23,7 +23,6 @@ u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, struct intel_crtc_state *config); void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port); -bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv); int bxt_dsi_pll_compute(struct intel_encoder *encoder, struct intel_crtc_state *config); void bxt_dsi_pll_enable(struct intel_encoder *encoder, @@ -34,9 +33,14 @@ u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port); #ifdef I915 +bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv); void assert_dsi_pll_enabled(struct intel_display *display); void assert_dsi_pll_disabled(struct intel_display *display); #else +static inline bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv) +{ + return false; +} static inline void assert_dsi_pll_enabled(struct intel_display *display) { } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index c8107502190d..7796c4119ef5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -915,7 +915,7 @@ static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle) */ if (i915_gem_context_uses_protected_content(eb->gem_context) && i915_gem_object_is_protected(obj)) { - err = intel_pxp_key_check(eb->i915->pxp, intel_bo_to_drm_bo(obj), true); + err = intel_pxp_key_check(intel_bo_to_drm_bo(obj), true); if (err) { i915_gem_object_put(obj); return ERR_PTR(err); diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c index 2b0327cc47c2..fd8babb513e5 100644 --- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c @@ -108,44 +108,6 @@ err_ctx: } struct i915_gem_context * -live_context_for_engine(struct intel_engine_cs *engine, struct file *file) -{ - struct i915_gem_engines *engines; - struct i915_gem_context *ctx; - struct intel_sseu null_sseu = {}; - struct intel_context *ce; - - engines = alloc_engines(1); - if (!engines) - return ERR_PTR(-ENOMEM); - - ctx = live_context(engine->i915, file); - if (IS_ERR(ctx)) { - __free_engines(engines, 0); - return ctx; - } - - ce = intel_context_create(engine); - if (IS_ERR(ce)) { - __free_engines(engines, 0); - return ERR_CAST(ce); - } - - intel_context_set_gem(ce, ctx, null_sseu); - engines->engines[0] = ce; - engines->num_engines = 1; - - mutex_lock(&ctx->engines_mutex); - i915_gem_context_set_user_engines(ctx); - engines = rcu_replace_pointer(ctx->engines, engines, 1); - mutex_unlock(&ctx->engines_mutex); - - engines_idle_release(ctx, engines); - - return ctx; -} - -struct i915_gem_context * kernel_context(struct drm_i915_private *i915, struct i915_address_space *vm) { diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.h b/drivers/gpu/drm/i915/gem/selftests/mock_context.h index 7a02fd9b5866..bc8fb37d2d24 100644 --- a/drivers/gpu/drm/i915/gem/selftests/mock_context.h +++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.h @@ -23,9 +23,6 @@ void mock_context_close(struct i915_gem_context *ctx); struct i915_gem_context * live_context(struct drm_i915_private *i915, struct file *file); -struct i915_gem_context * -live_context_for_engine(struct intel_engine_cs *engine, struct file *file); - struct i915_gem_context *kernel_context(struct drm_i915_private *i915, struct i915_address_space *vm); void kernel_context_close(struct i915_gem_context *ctx); diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c index 075657018739..5cd58e0f0dcf 100644 --- a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c @@ -103,8 +103,7 @@ static struct dma_buf *mock_dmabuf(int npages) struct dma_buf *dmabuf; int i; - mock = kmalloc(sizeof(*mock) + npages * sizeof(struct page *), - GFP_KERNEL); + mock = kmalloc(struct_size(mock, pages, npages), GFP_KERNEL); if (!mock) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index ec136eb12d48..39f6ba4bf1ab 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -677,7 +677,7 @@ void intel_engines_release(struct intel_gt *gt) * in case we aborted before completely initialising the engines. */ GEM_BUG_ON(intel_gt_pm_is_awake(gt)); - if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) + if (!intel_gt_gpu_reset_clobbers_display(gt)) intel_gt_reset_all_engines(gt); /* Decouple the backend; but keep the layout for late GPU resets */ diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index 0ffba50981e3..0c723e7c71a2 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -328,6 +328,7 @@ static bool fence_is_active(const struct i915_fence_reg *fence) static struct i915_fence_reg *fence_find(struct i915_ggtt *ggtt) { + struct intel_display *display = &ggtt->vm.i915->display; struct i915_fence_reg *active = NULL; struct i915_fence_reg *fence, *fn; @@ -353,7 +354,7 @@ static struct i915_fence_reg *fence_find(struct i915_ggtt *ggtt) } /* Wait for completion of pending flips which consume fences */ - if (intel_has_pending_fb_unpin(ggtt->vm.i915)) + if (intel_has_pending_fb_unpin(display)) return ERR_PTR(-EAGAIN); return ERR_PTR(-ENOBUFS); @@ -749,7 +750,7 @@ static void swizzle_page(struct page *page) char *vaddr; int i; - vaddr = kmap(page); + vaddr = kmap_local_page(page); for (i = 0; i < PAGE_SIZE; i += 128) { memcpy(temp, &vaddr[i], 64); @@ -757,7 +758,7 @@ static void swizzle_page(struct page *page) memcpy(&vaddr[i + 64], temp, 64); } - kunmap(page); + kunmap_local(vaddr); } /** diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index 175fa2db0551..3182f19b9837 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -158,7 +158,7 @@ void intel_gt_pm_init(struct intel_gt *gt) static bool reset_engines(struct intel_gt *gt) { - if (INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) + if (intel_gt_gpu_reset_clobbers_display(gt)) return false; return intel_gt_reset_all_engines(gt) == 0; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 6dba65e54cdb..a6e50af44b46 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -409,6 +409,9 @@ #define GEN7_SO_PRIM_STORAGE_NEEDED(n) _MMIO(0x5240 + (n) * 8) #define GEN7_SO_PRIM_STORAGE_NEEDED_UDW(n) _MMIO(0x5240 + (n) * 8 + 4) +#define GEN8_WM_CHICKEN2 MCR_REG(0x5584) +#define WAIT_ON_DEPTH_STALL_DONE_DISABLE REG_BIT(5) + #define GEN9_WM_CHICKEN3 _MMIO(0x5588) #define GEN9_FACTOR_IN_CLR_VAL_HIZ (1 << 9) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c index d7784650e4d9..1154cd2b7c34 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c @@ -464,6 +464,45 @@ static ssize_t slpc_ignore_eff_freq_store(struct kobject *kobj, return err ?: count; } +static ssize_t slpc_power_profile_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buff) +{ + struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); + struct intel_guc_slpc *slpc = >->uc.guc.slpc; + + switch (slpc->power_profile) { + case SLPC_POWER_PROFILES_BASE: + return sysfs_emit(buff, "[%s] %s\n", "base", "power_saving"); + case SLPC_POWER_PROFILES_POWER_SAVING: + return sysfs_emit(buff, "%s [%s]\n", "base", "power_saving"); + } + + return sysfs_emit(buff, "%u\n", slpc->power_profile); +} + +static ssize_t slpc_power_profile_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buff, size_t count) +{ + struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); + struct intel_guc_slpc *slpc = >->uc.guc.slpc; + char power_saving[] = "power_saving"; + char base[] = "base"; + int err; + u32 val; + + if (!strncmp(buff, power_saving, sizeof(power_saving) - 1)) + val = SLPC_POWER_PROFILES_POWER_SAVING; + else if (!strncmp(buff, base, sizeof(base) - 1)) + val = SLPC_POWER_PROFILES_BASE; + else + return -EINVAL; + + err = intel_guc_slpc_set_power_profile(slpc, val); + return err ?: count; +} + struct intel_gt_bool_throttle_attr { struct attribute attr; ssize_t (*show)(struct kobject *kobj, struct kobj_attribute *attr, @@ -668,6 +707,7 @@ INTEL_GT_ATTR_RO(media_RP0_freq_mhz); INTEL_GT_ATTR_RO(media_RPn_freq_mhz); INTEL_GT_ATTR_RW(slpc_ignore_eff_freq); +INTEL_GT_ATTR_RW(slpc_power_profile); static const struct attribute *media_perf_power_attrs[] = { &attr_media_freq_factor.attr, @@ -864,6 +904,13 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj) gt_warn(gt, "failed to create ignore_eff_freq sysfs (%pe)", ERR_PTR(ret)); } + if (intel_uc_uses_guc_slpc(>->uc)) { + ret = sysfs_create_file(kobj, &attr_slpc_power_profile.attr); + if (ret) + gt_warn(gt, "failed to create slpc_power_profile sysfs (%pe)", + ERR_PTR(ret)); + } + if (i915_mmio_reg_valid(intel_gt_perf_limit_reasons_reg(gt))) { ret = sysfs_create_files(kobj, throttle_reason_attrs); if (ret) diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index b33007cd1504..dbdcfe130ad4 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -986,7 +986,7 @@ static void __intel_gt_set_wedged(struct intel_gt *gt) awake = reset_prepare(gt); /* Even if the GPU reset fails, it should still stop the engines */ - if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) + if (!intel_gt_gpu_reset_clobbers_display(gt)) intel_gt_reset_all_engines(gt); for_each_engine(engine, gt, id) @@ -1106,14 +1106,13 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt) /* We must reset pending GPU events before restoring our submission */ ok = !HAS_EXECLISTS(gt->i915); /* XXX better agnosticism desired */ - if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) + if (!intel_gt_gpu_reset_clobbers_display(gt)) ok = intel_gt_reset_all_engines(gt) == 0; if (!ok) { /* * Warn CI about the unrecoverable wedged condition. * Time for a reboot. */ - gt_err(gt, "Unrecoverable wedged condition\n"); add_taint_for_CI(gt->i915, TAINT_WARN); return false; } @@ -1178,6 +1177,13 @@ static int resume(struct intel_gt *gt) return 0; } +bool intel_gt_gpu_reset_clobbers_display(struct intel_gt *gt) +{ + struct drm_i915_private *i915 = gt->i915; + + return INTEL_INFO(i915)->gpu_reset_clobbers_display; +} + /** * intel_gt_reset - reset chip after a hang * @gt: #intel_gt to reset @@ -1234,7 +1240,7 @@ void intel_gt_reset(struct intel_gt *gt, goto error; } - if (INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) + if (intel_gt_gpu_reset_clobbers_display(gt)) intel_irq_suspend(gt->i915); if (do_reset(gt, stalled_mask)) { @@ -1242,7 +1248,7 @@ void intel_gt_reset(struct intel_gt *gt, goto taint; } - if (INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) + if (intel_gt_gpu_reset_clobbers_display(gt)) intel_irq_resume(gt->i915); intel_overlay_reset(display); @@ -1265,10 +1271,8 @@ void intel_gt_reset(struct intel_gt *gt, } ret = resume(gt); - if (ret) { - gt_err(gt, "Failed to resume (%d)\n", ret); + if (ret) goto taint; - } finish: reset_finish(gt, awake); @@ -1396,6 +1400,11 @@ int intel_engine_reset(struct intel_engine_cs *engine, const char *msg) return err; } +static void display_reset_modeset_stuck(void *gt) +{ + intel_gt_set_wedged(gt); +} + static void intel_gt_reset_global(struct intel_gt *gt, u32 engine_mask, const char *reason) @@ -1413,11 +1422,26 @@ static void intel_gt_reset_global(struct intel_gt *gt, /* Use a watchdog to ensure that our reset completes */ intel_wedge_on_timeout(&w, gt, 60 * HZ) { - intel_display_reset_prepare(gt->i915); + struct drm_i915_private *i915 = gt->i915; + struct intel_display *display = &i915->display; + bool need_display_reset; + bool reset_display; + + need_display_reset = intel_gt_gpu_reset_clobbers_display(gt) && + intel_has_gpu_reset(gt); + + reset_display = intel_display_reset_test(display) || + need_display_reset; + + if (reset_display) + reset_display = intel_display_reset_prepare(display, + display_reset_modeset_stuck, + gt); intel_gt_reset(gt, engine_mask, reason); - intel_display_reset_finish(gt->i915); + if (reset_display) + intel_display_reset_finish(display, !need_display_reset); } if (!test_bit(I915_WEDGED, >->reset.flags)) @@ -1485,7 +1509,7 @@ void intel_gt_handle_error(struct intel_gt *gt, intel_has_reset_engine(gt) && !intel_gt_is_wedged(gt)) { local_bh_disable(); for_each_engine_masked(engine, gt, engine_mask, tmp) { - BUILD_BUG_ON(I915_RESET_MODESET >= I915_RESET_ENGINE); + BUILD_BUG_ON(I915_RESET_BACKOFF >= I915_RESET_ENGINE); if (test_and_set_bit(I915_RESET_ENGINE + engine->id, >->reset.flags)) continue; @@ -1614,7 +1638,6 @@ void intel_gt_set_wedged_on_init(struct intel_gt *gt) set_bit(I915_WEDGED_ON_INIT, >->reset.flags); /* Wedged on init is non-recoverable */ - gt_err(gt, "Non-recoverable wedged on init\n"); add_taint_for_CI(gt->i915, TAINT_WARN); } diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h index c00de353075c..724ea6d64f33 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.h +++ b/drivers/gpu/drm/i915/gt/intel_reset.h @@ -28,6 +28,8 @@ void intel_gt_handle_error(struct intel_gt *gt, const char *fmt, ...); #define I915_ERROR_CAPTURE BIT(0) +bool intel_gt_gpu_reset_clobbers_display(struct intel_gt *gt); + void intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask, const char *reason); diff --git a/drivers/gpu/drm/i915/gt/intel_reset_types.h b/drivers/gpu/drm/i915/gt/intel_reset_types.h index 80351f0a856c..4f5fd393af6f 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset_types.h +++ b/drivers/gpu/drm/i915/gt/intel_reset_types.h @@ -41,8 +41,7 @@ struct intel_reset { */ unsigned long flags; #define I915_RESET_BACKOFF 0 -#define I915_RESET_MODESET 1 -#define I915_RESET_ENGINE 2 +#define I915_RESET_ENGINE 1 #define I915_WEDGED_ON_INIT (BITS_PER_LONG - 3) #define I915_WEDGED_ON_FINI (BITS_PER_LONG - 2) #define I915_WEDGED (BITS_PER_LONG - 1) diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index fa304ea088e4..2cfaedb04876 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -1025,6 +1025,10 @@ void intel_rps_boost(struct i915_request *rq) if (rps_uses_slpc(rps)) { slpc = rps_to_slpc(rps); + /* Waitboost should not be done with power saving profile */ + if (slpc->power_profile == SLPC_POWER_PROFILES_POWER_SAVING) + return; + if (slpc->min_freq_softlimit >= slpc->boost_freq) return; diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 3ea9b06de1be..116683ebe074 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -691,16 +691,17 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine, struct drm_i915_private *i915 = engine->i915; /* - * Wa_1409142259:tgl,dg1,adl-p + * Wa_1409142259:tgl,dg1,adl-p,adl-n * Wa_1409347922:tgl,dg1,adl-p * Wa_1409252684:tgl,dg1,adl-p * Wa_1409217633:tgl,dg1,adl-p * Wa_1409207793:tgl,dg1,adl-p - * Wa_1409178076:tgl,dg1,adl-p - * Wa_1408979724:tgl,dg1,adl-p - * Wa_14010443199:tgl,rkl,dg1,adl-p - * Wa_14010698770:tgl,rkl,dg1,adl-s,adl-p - * Wa_1409342910:tgl,rkl,dg1,adl-s,adl-p + * Wa_1409178076:tgl,dg1,adl-p,adl-n + * Wa_1408979724:tgl,dg1,adl-p,adl-n + * Wa_14010443199:tgl,rkl,dg1,adl-p,adl-n + * Wa_14010698770:tgl,rkl,dg1,adl-s,adl-p,adl-n + * Wa_1409342910:tgl,rkl,dg1,adl-s,adl-p,adl-n + * Wa_22010465259:tgl,rkl,dg1,adl-s,adl-p,adl-n */ wa_masked_en(wal, GEN11_COMMON_SLICE_CHICKEN3, GEN12_DISABLE_CPS_AWARE_COLOR_PIPE); @@ -741,6 +742,12 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine, /* Wa_1606376872 */ wa_masked_en(wal, COMMON_SLICE_CHICKEN4, DISABLE_TDC_LOAD_BALANCING_CALC); } + + /* + * This bit must be set to enable performance optimization for fast + * clears. + */ + wa_mcr_write_or(wal, GEN8_WM_CHICKEN2, WAIT_ON_DEPTH_STALL_DONE_DISABLE); } static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine, diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c index 78c03e6c0861..73bc91c6ea07 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rps.c +++ b/drivers/gpu/drm/i915/gt/selftest_rps.c @@ -477,12 +477,13 @@ int live_rps_control(void *arg) limit, intel_gpu_freq(rps, limit), min, max, ktime_to_ns(min_dt), ktime_to_ns(max_dt)); - if (limit == rps->min_freq) { - pr_err("%s: GPU throttled to minimum!\n", - engine->name); + if (limit != rps->max_freq) { + u32 throttle = intel_uncore_read(gt->uncore, + intel_gt_perf_limit_reasons_reg(gt)); + + pr_warn("%s: GPU throttled with reasons 0x%08x\n", + engine->name, throttle & GT0_PERF_LIMIT_REASONS_MASK); show_pstate_limits(rps); - err = -ENODEV; - break; } if (igt_flush_test(gt->i915)) { @@ -1115,7 +1116,7 @@ static u64 measure_power(struct intel_rps *rps, int *freq) for (i = 0; i < 5; i++) x[i] = __measure_power(5); - *freq = (*freq + intel_rps_read_actual_frequency(rps)) / 2; + *freq = (*freq + read_cagf(rps)) / 2; /* A simple triangle filter for better result stability */ sort(x, 5, sizeof(*x), cmp_u64, NULL); diff --git a/drivers/gpu/drm/i915/gt/selftest_slpc.c b/drivers/gpu/drm/i915/gt/selftest_slpc.c index e218b229681f..e61bb0bad12c 100644 --- a/drivers/gpu/drm/i915/gt/selftest_slpc.c +++ b/drivers/gpu/drm/i915/gt/selftest_slpc.c @@ -95,6 +95,21 @@ static int slpc_restore_freq(struct intel_guc_slpc *slpc, u32 min, u32 max) return 0; } +static u64 slpc_measure_power(struct intel_rps *rps, int *freq) +{ + u64 x[5]; + int i; + + for (i = 0; i < 5; i++) + x[i] = __measure_power(5); + + *freq = (*freq + intel_rps_read_actual_frequency(rps)) / 2; + + /* A simple triangle filter for better result stability */ + sort(x, 5, sizeof(*x), cmp_u64, NULL); + return div_u64(x[1] + 2 * x[2] + x[3], 4); +} + static u64 measure_power_at_freq(struct intel_gt *gt, int *freq, u64 *power) { int err = 0; @@ -103,7 +118,7 @@ static u64 measure_power_at_freq(struct intel_gt *gt, int *freq, u64 *power) if (err) return err; *freq = intel_rps_read_actual_frequency(>->rps); - *power = measure_power(>->rps, freq); + *power = slpc_measure_power(>->rps, freq); return err; } diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index bb696b29ee2c..365c4b8b04f4 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -108,7 +108,7 @@ static int __shmem_rw(struct file *file, loff_t off, if (IS_ERR(page)) return PTR_ERR(page); - vaddr = kmap(page); + vaddr = kmap_local_page(page); if (write) { memcpy(vaddr + offset_in_page(off), ptr, this); set_page_dirty(page); @@ -116,7 +116,7 @@ static int __shmem_rw(struct file *file, loff_t off, memcpy(ptr, vaddr + offset_in_page(off), this); } mark_page_accessed(page); - kunmap(page); + kunmap_local(vaddr); put_page(page); len -= this; @@ -143,11 +143,11 @@ int shmem_read_to_iosys_map(struct file *file, loff_t off, if (IS_ERR(page)) return PTR_ERR(page); - vaddr = kmap(page); + vaddr = kmap_local_page(page); iosys_map_memcpy_to(map, map_off, vaddr + offset_in_page(off), this); mark_page_accessed(page); - kunmap(page); + kunmap_local(vaddr); put_page(page); len -= this; diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h index c34674e797c6..6de87ae5669e 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h @@ -228,6 +228,11 @@ struct slpc_optimized_strategies { #define SLPC_OPTIMIZED_STRATEGY_COMPUTE REG_BIT(0) +enum slpc_power_profiles { + SLPC_POWER_PROFILES_BASE = 0x0, + SLPC_POWER_PROFILES_POWER_SAVING = 0x1 +}; + /** * DOC: SLPC H2G MESSAGE FORMAT * diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c index fe53e8eccf4b..e7ccfa520df3 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c @@ -259,13 +259,14 @@ static int guc_wait_ucode(struct intel_guc *guc) } else if (delta_ms > 200) { guc_warn(guc, "excessive init time: %lldms! [status = 0x%08X, count = %d, ret = %d]\n", delta_ms, status, count, ret); - guc_warn(guc, "excessive init time: [freq = %dMHz, before = %dMHz, perf_limit_reasons = 0x%08X]\n", - intel_rps_read_actual_frequency(>->rps), before_freq, + guc_warn(guc, "excessive init time: [freq = %dMHz -> %dMHz vs %dMHz, perf_limit_reasons = 0x%08X]\n", + before_freq, intel_rps_read_actual_frequency(>->rps), + intel_rps_get_requested_frequency(>->rps), intel_uncore_read(uncore, intel_gt_perf_limit_reasons_reg(gt))); } else { - guc_dbg(guc, "init took %lldms, freq = %dMHz, before = %dMHz, status = 0x%08X, count = %d, ret = %d\n", - delta_ms, intel_rps_read_actual_frequency(>->rps), - before_freq, status, count, ret); + guc_dbg(guc, "init took %lldms, freq = %dMHz -> %dMHz vs %dMHz, status = 0x%08X, count = %d, ret = %d\n", + delta_ms, before_freq, intel_rps_read_actual_frequency(>->rps), + intel_rps_get_requested_frequency(>->rps), status, count, ret); } return ret; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c index b67a15f74276..868195c33f5b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c @@ -7,6 +7,7 @@ #include "gt/intel_hwconfig.h" #include "i915_drv.h" #include "i915_memcpy.h" +#include "intel_guc_print.h" /* * GuC has a blob containing hardware configuration information (HWConfig). @@ -42,6 +43,8 @@ static int __guc_action_get_hwconfig(struct intel_guc *guc, }; int ret; + guc_dbg(guc, "Querying HW config table: size = %d, offset = 0x%08X\n", + ggtt_size, ggtt_offset); ret = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0); if (ret == -ENXIO) return -ENOENT; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c index 1a0e1a412fdb..d5ee6e5e1443 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c @@ -15,6 +15,34 @@ #include "gt/intel_gt_regs.h" #include "gt/intel_rps.h" +/** + * DOC: SLPC - Dynamic Frequency management + * + * Single Loop Power Control (SLPC) is a GuC algorithm that manages + * GT frequency based on busyness and how KMD initializes it. SLPC is + * almost completely in control after initialization except for a few + * scenarios mentioned below. + * + * KMD uses the concept of waitboost to ramp frequency to RP0 when there + * are pending submissions for a context. It achieves this by sending GuC a + * request to update the min frequency to RP0. Waitboost is disabled + * when the request retires. + * + * Another form of frequency control happens through per-context hints. + * A context can be marked as low latency during creation. That will ensure + * that SLPC uses an aggressive frequency ramp when that context is active. + * + * Power profiles add another level of control to these mechanisms. + * When power saving profile is chosen, SLPC will use conservative + * thresholds to ramp frequency, thus saving power. KMD will disable + * waitboosts as well, which achieves further power savings. Base profile + * is default and ensures balanced performance for any workload. + * + * Lastly, users have some level of control through sysfs, where min/max + * frequency values can be altered and the use of efficient freq + * can be toggled. + */ + static inline struct intel_guc *slpc_to_guc(struct intel_guc_slpc *slpc) { return container_of(slpc, struct intel_guc, slpc); @@ -265,6 +293,8 @@ int intel_guc_slpc_init(struct intel_guc_slpc *slpc) slpc->num_boosts = 0; slpc->media_ratio_mode = SLPC_MEDIA_RATIO_MODE_DYNAMIC_CONTROL; + slpc->power_profile = SLPC_POWER_PROFILES_BASE; + mutex_init(&slpc->lock); INIT_WORK(&slpc->boost_work, slpc_boost_work); @@ -575,6 +605,34 @@ int intel_guc_slpc_set_media_ratio_mode(struct intel_guc_slpc *slpc, u32 val) return ret; } +int intel_guc_slpc_set_power_profile(struct intel_guc_slpc *slpc, u32 val) +{ + struct drm_i915_private *i915 = slpc_to_i915(slpc); + intel_wakeref_t wakeref; + int ret = 0; + + if (val > SLPC_POWER_PROFILES_POWER_SAVING) + return -EINVAL; + + mutex_lock(&slpc->lock); + wakeref = intel_runtime_pm_get(&i915->runtime_pm); + + ret = slpc_set_param(slpc, + SLPC_PARAM_POWER_PROFILE, + val); + if (ret) + guc_err(slpc_to_guc(slpc), + "Failed to set power profile to %d: %pe\n", + val, ERR_PTR(ret)); + else + slpc->power_profile = val; + + intel_runtime_pm_put(&i915->runtime_pm, wakeref); + mutex_unlock(&slpc->lock); + + return ret; +} + void intel_guc_pm_intrmsk_enable(struct intel_gt *gt) { u32 pm_intrmsk_mbz = 0; @@ -736,6 +794,13 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) /* Enable SLPC Optimized Strategy for compute */ intel_guc_slpc_set_strategy(slpc, SLPC_OPTIMIZED_STRATEGY_COMPUTE); + /* Set cached value of power_profile */ + ret = intel_guc_slpc_set_power_profile(slpc, slpc->power_profile); + if (unlikely(ret)) { + guc_probe_error(guc, "Failed to set SLPC power profile: %pe\n", ERR_PTR(ret)); + return ret; + } + return 0; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h index 1cb5fd44f05c..fc9f761b4372 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h @@ -46,5 +46,6 @@ void intel_guc_slpc_boost(struct intel_guc_slpc *slpc); void intel_guc_slpc_dec_waiters(struct intel_guc_slpc *slpc); int intel_guc_slpc_set_ignore_eff_freq(struct intel_guc_slpc *slpc, bool val); int intel_guc_slpc_set_strategy(struct intel_guc_slpc *slpc, u32 val); +int intel_guc_slpc_set_power_profile(struct intel_guc_slpc *slpc, u32 val); #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h index a88651331497..83673b10ac4e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h @@ -33,6 +33,9 @@ struct intel_guc_slpc { u32 max_freq_softlimit; bool ignore_eff_freq; + /* Base or power saving */ + u32 power_profile; + /* cached media ratio mode */ u32 media_ratio_mode; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index b3cbf85c00cb..f30c90650b7e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -489,13 +489,15 @@ int intel_huc_wait_for_auth_complete(struct intel_huc *huc, if (delta_ms > 50) { huc_warn(huc, "excessive auth time: %lldms! [status = 0x%08X, count = %d, ret = %d]\n", delta_ms, huc->status[type].reg.reg, count, ret); - huc_warn(huc, "excessive auth time: [freq = %dMHz, before = %dMHz, perf_limit_reasons = 0x%08X]\n", - intel_rps_read_actual_frequency(>->rps), before_freq, + huc_warn(huc, "excessive auth time: [freq = %dMHz -> %dMHz vs %dMHz, perf_limit_reasons = 0x%08X]\n", + before_freq, intel_rps_read_actual_frequency(>->rps), + intel_rps_get_requested_frequency(>->rps), intel_uncore_read(uncore, intel_gt_perf_limit_reasons_reg(gt))); } else { - huc_dbg(huc, "auth took %lldms, freq = %dMHz, before = %dMHz, status = 0x%08X, count = %d, ret = %d\n", - delta_ms, intel_rps_read_actual_frequency(>->rps), - before_freq, huc->status[type].reg.reg, count, ret); + huc_dbg(huc, "auth took %lldms, freq = %dMHz -> %dMHz vs %dMHz, status = 0x%08X, count = %d, ret = %d\n", + delta_ms, before_freq, intel_rps_read_actual_frequency(>->rps), + intel_rps_get_requested_frequency(>->rps), + huc->status[type].reg.reg, count, ret); } /* mark the load process as complete even if the wait failed */ diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 1c2a97f593c7..0d9e263913ff 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -411,9 +411,6 @@ static int i915_runtime_pm_status(struct seq_file *m, void *unused) if (!HAS_RUNTIME_PM(dev_priv)) seq_puts(m, "Runtime power management not supported\n"); - seq_printf(m, "Runtime power status: %s\n", - str_enabled_disabled(!dev_priv->display.power.domains.init_wakeref)); - seq_printf(m, "GPU idle: %s\n", str_yes_no(!to_gt(dev_priv)->awake)); seq_printf(m, "IRQs disabled: %s\n", str_yes_no(!intel_irqs_enabled(dev_priv))); diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 1dfd6269b355..ce3cc93ea211 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -41,6 +41,8 @@ #include <linux/vt.h> #include <drm/drm_atomic_helper.h> +#include <drm/drm_client.h> +#include <drm/drm_client_event.h> #include <drm/drm_ioctl.h> #include <drm/drm_managed.h> #include <drm/drm_probe_helper.h> @@ -200,7 +202,7 @@ static void intel_detect_preproduction_hw(struct drm_i915_private *dev_priv) static void sanitize_gpu(struct drm_i915_private *i915) { - if (!INTEL_INFO(i915)->gpu_reset_clobbers_display) { + if (!intel_gt_gpu_reset_clobbers_display(to_gt(i915))) { struct intel_gt *gt; unsigned int i; @@ -968,7 +970,7 @@ void i915_driver_shutdown(struct drm_i915_private *i915) intel_runtime_pm_disable(&i915->runtime_pm); intel_power_domains_disable(display); - intel_fbdev_set_suspend(&i915->drm, FBINFO_STATE_SUSPENDED, true); + drm_client_dev_suspend(&i915->drm, false); if (HAS_DISPLAY(i915)) { drm_kms_helper_poll_disable(&i915->drm); intel_display_driver_disable_user_access(display); @@ -1051,7 +1053,7 @@ static int i915_drm_suspend(struct drm_device *dev) /* We do a lot of poking in a lot of registers, make sure they work * properly. */ intel_power_domains_disable(display); - intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED, true); + drm_client_dev_suspend(dev, false); if (HAS_DISPLAY(dev_priv)) { drm_kms_helper_poll_disable(dev); intel_display_driver_disable_user_access(display); @@ -1070,7 +1072,7 @@ static int i915_drm_suspend(struct drm_device *dev) intel_encoder_suspend_all(&dev_priv->display); /* Must be called before GGTT is suspended. */ - intel_dpt_suspend(dev_priv); + intel_dpt_suspend(display); i915_ggtt_suspend(to_gt(dev_priv)->ggtt); i9xx_display_sr_save(display); @@ -1187,7 +1189,7 @@ static int i915_drm_resume(struct drm_device *dev) setup_private_pat(gt); /* Must be called after GGTT is resumed. */ - intel_dpt_resume(dev_priv); + intel_dpt_resume(display); intel_dmc_resume(display); @@ -1237,7 +1239,7 @@ static int i915_drm_resume(struct drm_device *dev) intel_opregion_resume(display); - intel_fbdev_set_suspend(dev, FBINFO_STATE_RUNNING, false); + drm_client_dev_resume(dev, false); intel_power_domains_enable(display); @@ -1807,6 +1809,8 @@ static const struct drm_driver i915_drm_driver = { .dumb_create = i915_gem_dumb_create, .dumb_map_offset = i915_gem_dumb_mmap_offset, + INTEL_FBDEV_DRIVER_OPS, + .ioctls = i915_ioctls, .num_ioctls = ARRAY_SIZE(i915_ioctls), .fops = &i915_driver_fops, diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index 78a8928562a9..749e1c55613e 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -224,8 +224,6 @@ struct i915_gpu_error { /* Protected by the above dev->gpu_error.lock. */ struct i915_gpu_coredump *first_error; - atomic_t pending_fb_pin; - /** Number of times the device has been reset (global) */ atomic_t reset_count; diff --git a/drivers/gpu/drm/i915/i915_gtt_view_types.h b/drivers/gpu/drm/i915/i915_gtt_view_types.h new file mode 100644 index 000000000000..c084f67bc880 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_gtt_view_types.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright © 2025 Intel Corporation */ + +#ifndef __I915_GTT_VIEW_TYPES_H__ +#define __I915_GTT_VIEW_TYPES_H__ + +#include <linux/types.h> + +struct intel_remapped_plane_info { + /* in gtt pages */ + u32 offset:31; + u32 linear:1; + union { + /* in gtt pages for !linear */ + struct { + u16 width; + u16 height; + u16 src_stride; + u16 dst_stride; + }; + + /* in gtt pages for linear */ + u32 size; + }; +} __packed; + +struct intel_rotation_info { + struct intel_remapped_plane_info plane[2]; +} __packed; + +struct intel_partial_info { + u64 offset; + unsigned int size; +} __packed; + +struct intel_remapped_info { + struct intel_remapped_plane_info plane[4]; + /* in gtt pages */ + u32 plane_alignment; +} __packed; + +enum i915_gtt_view_type { + I915_GTT_VIEW_NORMAL = 0, + I915_GTT_VIEW_ROTATED = sizeof(struct intel_rotation_info), + I915_GTT_VIEW_PARTIAL = sizeof(struct intel_partial_info), + I915_GTT_VIEW_REMAPPED = sizeof(struct intel_remapped_info), +}; + +struct i915_gtt_view { + enum i915_gtt_view_type type; + union { + /* Members need to contain no holes/padding */ + struct intel_partial_info partial; + struct intel_rotation_info rotated; + struct intel_remapped_info remapped; + }; +}; + +#endif /* __I915_GTT_VIEW_TYPES_H__ */ diff --git a/drivers/gpu/drm/i915/i915_module.c b/drivers/gpu/drm/i915/i915_module.c index 2f88970cc0a9..5862754c662c 100644 --- a/drivers/gpu/drm/i915/i915_module.c +++ b/drivers/gpu/drm/i915/i915_module.c @@ -71,8 +71,6 @@ static const struct { { .init = i915_vma_resource_module_init, .exit = i915_vma_resource_module_exit }, { .init = i915_mock_selftests }, - { .init = i915_pmu_init, - .exit = i915_pmu_exit }, { .init = i915_pci_register_driver, .exit = i915_pci_unregister_driver }, { .init = i915_perf_sysctl_register, diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index e55db036be1b..69a109d02116 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -28,9 +28,6 @@ BIT(I915_SAMPLE_WAIT) | \ BIT(I915_SAMPLE_SEMA)) -static cpumask_t i915_pmu_cpumask; -static unsigned int i915_pmu_target_cpu = -1; - static struct i915_pmu *event_to_pmu(struct perf_event *event) { return container_of(event->pmu, struct i915_pmu, base); @@ -642,10 +639,6 @@ static int i915_pmu_event_init(struct perf_event *event) if (event->cpu < 0) return -EINVAL; - /* only allow running on one cpu at a time */ - if (!cpumask_test_cpu(event->cpu, &i915_pmu_cpumask)) - return -EINVAL; - if (is_engine_event(event)) ret = engine_event_init(event); else @@ -891,11 +884,6 @@ static void i915_pmu_event_del(struct perf_event *event, int flags) i915_pmu_event_stop(event, PERF_EF_UPDATE); } -static int i915_pmu_event_event_idx(struct perf_event *event) -{ - return 0; -} - struct i915_str_attribute { struct device_attribute attr; const char *str; @@ -940,23 +928,6 @@ static ssize_t i915_pmu_event_show(struct device *dev, return sprintf(buf, "config=0x%lx\n", eattr->val); } -static ssize_t cpumask_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return cpumap_print_to_pagebuf(true, buf, &i915_pmu_cpumask); -} - -static DEVICE_ATTR_RO(cpumask); - -static struct attribute *i915_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL, -}; - -static const struct attribute_group i915_pmu_cpumask_attr_group = { - .attrs = i915_cpumask_attrs, -}; - #define __event(__counter, __name, __unit) \ { \ .counter = (__counter), \ @@ -1173,92 +1144,12 @@ static void free_event_attributes(struct i915_pmu *pmu) pmu->pmu_attr = NULL; } -static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node) -{ - struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node); - - /* Select the first online CPU as a designated reader. */ - if (cpumask_empty(&i915_pmu_cpumask)) - cpumask_set_cpu(cpu, &i915_pmu_cpumask); - - return 0; -} - -static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node) -{ - struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node); - unsigned int target = i915_pmu_target_cpu; - - /* - * Unregistering an instance generates a CPU offline event which we must - * ignore to avoid incorrectly modifying the shared i915_pmu_cpumask. - */ - if (!pmu->registered) - return 0; - - if (cpumask_test_and_clear_cpu(cpu, &i915_pmu_cpumask)) { - target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu); - - /* Migrate events if there is a valid target */ - if (target < nr_cpu_ids) { - cpumask_set_cpu(target, &i915_pmu_cpumask); - i915_pmu_target_cpu = target; - } - } - - if (target < nr_cpu_ids && target != pmu->cpuhp.cpu) { - perf_pmu_migrate_context(&pmu->base, cpu, target); - pmu->cpuhp.cpu = target; - } - - return 0; -} - -static enum cpuhp_state cpuhp_state = CPUHP_INVALID; - -int i915_pmu_init(void) -{ - int ret; - - ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, - "perf/x86/intel/i915:online", - i915_pmu_cpu_online, - i915_pmu_cpu_offline); - if (ret < 0) - pr_notice("Failed to setup cpuhp state for i915 PMU! (%d)\n", - ret); - else - cpuhp_state = ret; - - return 0; -} - -void i915_pmu_exit(void) -{ - if (cpuhp_state != CPUHP_INVALID) - cpuhp_remove_multi_state(cpuhp_state); -} - -static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu) -{ - if (cpuhp_state == CPUHP_INVALID) - return -EINVAL; - - return cpuhp_state_add_instance(cpuhp_state, &pmu->cpuhp.node); -} - -static void i915_pmu_unregister_cpuhp_state(struct i915_pmu *pmu) -{ - cpuhp_state_remove_instance(cpuhp_state, &pmu->cpuhp.node); -} - void i915_pmu_register(struct drm_i915_private *i915) { struct i915_pmu *pmu = &i915->pmu; const struct attribute_group *attr_groups[] = { &i915_pmu_format_attr_group, &pmu->events_attr_group, - &i915_pmu_cpumask_attr_group, NULL }; int ret = -ENOMEM; @@ -1266,7 +1157,6 @@ void i915_pmu_register(struct drm_i915_private *i915) spin_lock_init(&pmu->lock); hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); pmu->timer.function = i915_sample; - pmu->cpuhp.cpu = -1; init_rc6(pmu); if (IS_DGFX(i915)) { @@ -1295,28 +1185,22 @@ void i915_pmu_register(struct drm_i915_private *i915) pmu->base.module = THIS_MODULE; pmu->base.task_ctx_nr = perf_invalid_context; + pmu->base.scope = PERF_PMU_SCOPE_SYS_WIDE; pmu->base.event_init = i915_pmu_event_init; pmu->base.add = i915_pmu_event_add; pmu->base.del = i915_pmu_event_del; pmu->base.start = i915_pmu_event_start; pmu->base.stop = i915_pmu_event_stop; pmu->base.read = i915_pmu_event_read; - pmu->base.event_idx = i915_pmu_event_event_idx; ret = perf_pmu_register(&pmu->base, pmu->name, -1); if (ret) goto err_groups; - ret = i915_pmu_register_cpuhp_state(pmu); - if (ret) - goto err_unreg; - pmu->registered = true; return; -err_unreg: - perf_pmu_unregister(&pmu->base); err_groups: kfree(pmu->base.attr_groups); err_attr: @@ -1340,8 +1224,6 @@ void i915_pmu_unregister(struct drm_i915_private *i915) hrtimer_cancel(&pmu->timer); - i915_pmu_unregister_cpuhp_state(pmu); - perf_pmu_unregister(&pmu->base); kfree(pmu->base.attr_groups); if (IS_DGFX(i915)) diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h index 0ec78c2b4f20..5826cc81858c 100644 --- a/drivers/gpu/drm/i915/i915_pmu.h +++ b/drivers/gpu/drm/i915/i915_pmu.h @@ -57,13 +57,6 @@ struct i915_pmu_sample { struct i915_pmu { /** - * @cpuhp: Struct used for CPU hotplug handling. - */ - struct { - struct hlist_node node; - unsigned int cpu; - } cpuhp; - /** * @base: PMU base. */ struct pmu base; @@ -155,15 +148,11 @@ struct i915_pmu { }; #ifdef CONFIG_PERF_EVENTS -int i915_pmu_init(void); -void i915_pmu_exit(void); void i915_pmu_register(struct drm_i915_private *i915); void i915_pmu_unregister(struct drm_i915_private *i915); void i915_pmu_gt_parked(struct intel_gt *gt); void i915_pmu_gt_unparked(struct intel_gt *gt); #else -static inline int i915_pmu_init(void) { return 0; } -static inline void i915_pmu_exit(void) {} static inline void i915_pmu_register(struct drm_i915_private *i915) {} static inline void i915_pmu_unregister(struct drm_i915_private *i915) {} static inline void i915_pmu_gt_parked(struct intel_gt *gt) {} diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index b31b26e9a685..c5064eebe063 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1385,38 +1385,6 @@ /* ADL and later: */ #define VIDEO_DIP_ENABLE_AS_ADL REG_BIT(23) -/* Panel fitting */ -#define PFIT_CONTROL(dev_priv) _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61230) -#define PFIT_ENABLE REG_BIT(31) -#define PFIT_PIPE_MASK REG_GENMASK(30, 29) /* 965+ */ -#define PFIT_PIPE(pipe) REG_FIELD_PREP(PFIT_PIPE_MASK, (pipe)) -#define PFIT_SCALING_MASK REG_GENMASK(28, 26) /* 965+ */ -#define PFIT_SCALING_AUTO REG_FIELD_PREP(PFIT_SCALING_MASK, 0) -#define PFIT_SCALING_PROGRAMMED REG_FIELD_PREP(PFIT_SCALING_MASK, 1) -#define PFIT_SCALING_PILLAR REG_FIELD_PREP(PFIT_SCALING_MASK, 2) -#define PFIT_SCALING_LETTER REG_FIELD_PREP(PFIT_SCALING_MASK, 3) -#define PFIT_FILTER_MASK REG_GENMASK(25, 24) /* 965+ */ -#define PFIT_FILTER_FUZZY REG_FIELD_PREP(PFIT_FILTER_MASK, 0) -#define PFIT_FILTER_CRISP REG_FIELD_PREP(PFIT_FILTER_MASK, 1) -#define PFIT_FILTER_MEDIAN REG_FIELD_PREP(PFIT_FILTER_MASK, 2) -#define PFIT_VERT_INTERP_MASK REG_GENMASK(11, 10) /* pre-965 */ -#define PFIT_VERT_INTERP_BILINEAR REG_FIELD_PREP(PFIT_VERT_INTERP_MASK, 1) -#define PFIT_VERT_AUTO_SCALE REG_BIT(9) /* pre-965 */ -#define PFIT_HORIZ_INTERP_MASK REG_GENMASK(7, 6) /* pre-965 */ -#define PFIT_HORIZ_INTERP_BILINEAR REG_FIELD_PREP(PFIT_HORIZ_INTERP_MASK, 1) -#define PFIT_HORIZ_AUTO_SCALE REG_BIT(5) /* pre-965 */ -#define PFIT_PANEL_8TO6_DITHER_ENABLE REG_BIT(3) /* pre-965 */ - -#define PFIT_PGM_RATIOS(dev_priv) _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61234) -#define PFIT_VERT_SCALE_MASK REG_GENMASK(31, 20) /* pre-965 */ -#define PFIT_VERT_SCALE(x) REG_FIELD_PREP(PFIT_VERT_SCALE_MASK, (x)) -#define PFIT_HORIZ_SCALE_MASK REG_GENMASK(15, 4) /* pre-965 */ -#define PFIT_HORIZ_SCALE(x) REG_FIELD_PREP(PFIT_HORIZ_SCALE_MASK, (x)) -#define PFIT_VERT_SCALE_MASK_965 REG_GENMASK(28, 16) /* 965+ */ -#define PFIT_HORIZ_SCALE_MASK_965 REG_GENMASK(12, 0) /* 965+ */ - -#define PFIT_AUTO_RATIOS(dev_priv) _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61238) - #define PCH_GTC_CTL _MMIO(0xe7000) #define PCH_GTC_ENABLE (1 << 31) @@ -1911,44 +1879,6 @@ #define _PIPEB_LINK_N2 0x6104c #define PIPE_LINK_N2(dev_priv, tran) _MMIO_TRANS2(dev_priv, tran, _PIPEA_LINK_N2) -/* CPU panel fitter */ -/* IVB+ has 3 fitters, 0 is 7x5 capable, the other two only 3x3 */ -#define _PFA_CTL_1 0x68080 -#define _PFB_CTL_1 0x68880 -#define PF_CTL(pipe) _MMIO_PIPE(pipe, _PFA_CTL_1, _PFB_CTL_1) -#define PF_ENABLE REG_BIT(31) -#define PF_PIPE_SEL_MASK_IVB REG_GENMASK(30, 29) /* ivb/hsw */ -#define PF_PIPE_SEL_IVB(pipe) REG_FIELD_PREP(PF_PIPE_SEL_MASK_IVB, (pipe)) -#define PF_FILTER_MASK REG_GENMASK(24, 23) -#define PF_FILTER_PROGRAMMED REG_FIELD_PREP(PF_FILTER_MASK, 0) -#define PF_FILTER_MED_3x3 REG_FIELD_PREP(PF_FILTER_MASK, 1) -#define PF_FILTER_EDGE_ENHANCE REG_FIELD_PREP(PF_FILTER_EDGE_MASK, 2) -#define PF_FILTER_EDGE_SOFTEN REG_FIELD_PREP(PF_FILTER_EDGE_MASK, 3) - -#define _PFA_WIN_SZ 0x68074 -#define _PFB_WIN_SZ 0x68874 -#define PF_WIN_SZ(pipe) _MMIO_PIPE(pipe, _PFA_WIN_SZ, _PFB_WIN_SZ) -#define PF_WIN_XSIZE_MASK REG_GENMASK(31, 16) -#define PF_WIN_XSIZE(w) REG_FIELD_PREP(PF_WIN_XSIZE_MASK, (w)) -#define PF_WIN_YSIZE_MASK REG_GENMASK(15, 0) -#define PF_WIN_YSIZE(h) REG_FIELD_PREP(PF_WIN_YSIZE_MASK, (h)) - -#define _PFA_WIN_POS 0x68070 -#define _PFB_WIN_POS 0x68870 -#define PF_WIN_POS(pipe) _MMIO_PIPE(pipe, _PFA_WIN_POS, _PFB_WIN_POS) -#define PF_WIN_XPOS_MASK REG_GENMASK(31, 16) -#define PF_WIN_XPOS(x) REG_FIELD_PREP(PF_WIN_XPOS_MASK, (x)) -#define PF_WIN_YPOS_MASK REG_GENMASK(15, 0) -#define PF_WIN_YPOS(y) REG_FIELD_PREP(PF_WIN_YPOS_MASK, (y)) - -#define _PFA_VSCALE 0x68084 -#define _PFB_VSCALE 0x68884 -#define PF_VSCALE(pipe) _MMIO_PIPE(pipe, _PFA_VSCALE, _PFB_VSCALE) - -#define _PFA_HSCALE 0x68090 -#define _PFB_HSCALE 0x68890 -#define PF_HSCALE(pipe) _MMIO_PIPE(pipe, _PFA_HSCALE, _PFB_HSCALE) - /* * Skylake scalers */ @@ -4235,8 +4165,8 @@ enum skl_power_gate { _MMIO_PIPE(pipe, _PIPE_FLIPDONETMSTMP_A, _PIPE_FLIPDONETMSTMP_B) #define _VLV_PIPE_MSA_MISC_A 0x70048 -#define VLV_PIPE_MSA_MISC(pipe) \ - _MMIO_PIPE2(dev_priv, pipe, _VLV_PIPE_MSA_MISC_A) +#define VLV_PIPE_MSA_MISC(__display, pipe) \ + _MMIO_PIPE2(__display, pipe, _VLV_PIPE_MSA_MISC_A) #define VLV_MSA_MISC1_HW_ENABLE REG_BIT(31) #define VLV_MSA_MISC1_SW_S3D_MASK REG_GENMASK(2, 0) /* MSA MISC1 3:1 */ diff --git a/drivers/gpu/drm/i915/i915_vma_types.h b/drivers/gpu/drm/i915/i915_vma_types.h index 559de74d0b11..a499a3bea874 100644 --- a/drivers/gpu/drm/i915/i915_vma_types.h +++ b/drivers/gpu/drm/i915/i915_vma_types.h @@ -32,6 +32,8 @@ #include "gem/i915_gem_object_types.h" +#include "i915_gtt_view_types.h" + /** * DOC: Global GTT views * @@ -95,46 +97,6 @@ struct i915_vma_resource; -struct intel_remapped_plane_info { - /* in gtt pages */ - u32 offset:31; - u32 linear:1; - union { - /* in gtt pages for !linear */ - struct { - u16 width; - u16 height; - u16 src_stride; - u16 dst_stride; - }; - - /* in gtt pages for linear */ - u32 size; - }; -} __packed; - -struct intel_remapped_info { - struct intel_remapped_plane_info plane[4]; - /* in gtt pages */ - u32 plane_alignment; -} __packed; - -struct intel_rotation_info { - struct intel_remapped_plane_info plane[2]; -} __packed; - -struct intel_partial_info { - u64 offset; - unsigned int size; -} __packed; - -enum i915_gtt_view_type { - I915_GTT_VIEW_NORMAL = 0, - I915_GTT_VIEW_ROTATED = sizeof(struct intel_rotation_info), - I915_GTT_VIEW_PARTIAL = sizeof(struct intel_partial_info), - I915_GTT_VIEW_REMAPPED = sizeof(struct intel_remapped_info), -}; - static inline void assert_i915_gem_gtt_types(void) { BUILD_BUG_ON(sizeof(struct intel_rotation_info) != 2 * sizeof(u32) + 8 * sizeof(u16)); @@ -160,16 +122,6 @@ static inline void assert_i915_gem_gtt_types(void) } } -struct i915_gtt_view { - enum i915_gtt_view_type type; - union { - /* Members need to contain no holes/padding */ - struct intel_partial_info partial; - struct intel_rotation_info rotated; - struct intel_remapped_info remapped; - }; -}; - /** * DOC: Virtual Memory Address * diff --git a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c index 04076316e139..76d84cbb8361 100644 --- a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c +++ b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c @@ -18,6 +18,7 @@ #include "display/intel_fbc_regs.h" #include "display/intel_fdi_regs.h" #include "display/intel_lvds_regs.h" +#include "display/intel_pfit_regs.h" #include "display/intel_psr_regs.h" #include "display/intel_sprite_regs.h" #include "display/skl_universal_plane_regs.h" diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c index 9cf169665d7c..f8da693ad3ce 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c @@ -460,11 +460,11 @@ void intel_pxp_fini_hw(struct intel_pxp *pxp) intel_pxp_irq_disable(pxp); } -int intel_pxp_key_check(struct intel_pxp *pxp, - struct drm_gem_object *_obj, - bool assign) +int intel_pxp_key_check(struct drm_gem_object *_obj, bool assign) { struct drm_i915_gem_object *obj = to_intel_bo(_obj); + struct drm_i915_private *i915 = to_i915(_obj->dev); + struct intel_pxp *pxp = i915->pxp; if (!intel_pxp_is_active(pxp)) return -ENODEV; diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.h b/drivers/gpu/drm/i915/pxp/intel_pxp.h index 4ed97db5e7c6..7b19109845a3 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.h @@ -31,9 +31,7 @@ int intel_pxp_get_backend_timeout_ms(struct intel_pxp *pxp); int intel_pxp_start(struct intel_pxp *pxp); void intel_pxp_end(struct intel_pxp *pxp); -int intel_pxp_key_check(struct intel_pxp *pxp, - struct drm_gem_object *obj, - bool assign); +int intel_pxp_key_check(struct drm_gem_object *obj, bool assign); void intel_pxp_invalidate(struct intel_pxp *pxp); diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c index e817d233df61..ad650f67114a 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem.c @@ -45,13 +45,15 @@ static void trash_stolen(struct drm_i915_private *i915) struct i915_ggtt *ggtt = to_gt(i915)->ggtt; const u64 slot = ggtt->error_capture.start; const resource_size_t size = resource_size(&i915->dsm.stolen); + struct rnd_state prng; unsigned long page; - u32 prng = 0x12345678; /* XXX: fsck. needs some more thought... */ if (!i915_ggtt_has_aperture(ggtt)) return; + prandom_seed_state(&prng, 0x12345678); + for (page = 0; page < size; page += PAGE_SIZE) { const dma_addr_t dma = i915->dsm.stolen.start + page; u32 __iomem *s; @@ -64,8 +66,7 @@ static void trash_stolen(struct drm_i915_private *i915) s = io_mapping_map_atomic_wc(&ggtt->iomap, slot); for (x = 0; x < PAGE_SIZE / sizeof(u32); x++) { - prng = next_pseudo_random32(prng); - iowrite32(prng, &s[x]); + iowrite32(prandom_u32_state(&prng), &s[x]); } io_mapping_unmap_atomic(s); } diff --git a/drivers/gpu/drm/imagination/Makefile b/drivers/gpu/drm/imagination/Makefile index 9bc6a3884c22..3d9d4d40fb80 100644 --- a/drivers/gpu/drm/imagination/Makefile +++ b/drivers/gpu/drm/imagination/Makefile @@ -1,8 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only OR MIT # Copyright (c) 2023 Imagination Technologies Ltd. -subdir-ccflags-y := -I$(src) - powervr-y := \ pvr_ccb.o \ pvr_cccb.o \ diff --git a/drivers/gpu/drm/imagination/pvr_fw_meta.c b/drivers/gpu/drm/imagination/pvr_fw_meta.c index c39beb70c317..6d13864851fc 100644 --- a/drivers/gpu/drm/imagination/pvr_fw_meta.c +++ b/drivers/gpu/drm/imagination/pvr_fw_meta.c @@ -527,8 +527,10 @@ pvr_meta_vm_map(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj) static void pvr_meta_vm_unmap(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj) { - pvr_vm_unmap(pvr_dev->kernel_vm_ctx, fw_obj->fw_mm_node.start, - fw_obj->fw_mm_node.size); + struct pvr_gem_object *pvr_obj = fw_obj->gem; + + pvr_vm_unmap_obj(pvr_dev->kernel_vm_ctx, pvr_obj, + fw_obj->fw_mm_node.start, fw_obj->fw_mm_node.size); } static bool diff --git a/drivers/gpu/drm/imagination/pvr_fw_trace.c b/drivers/gpu/drm/imagination/pvr_fw_trace.c index 73707daa4e52..5dbb636d7d4f 100644 --- a/drivers/gpu/drm/imagination/pvr_fw_trace.c +++ b/drivers/gpu/drm/imagination/pvr_fw_trace.c @@ -333,8 +333,8 @@ static int fw_trace_seq_show(struct seq_file *s, void *v) if (sf_id == ROGUE_FW_SF_LAST) return -EINVAL; - timestamp = read_fw_trace(trace_seq_data, 1) | - ((u64)read_fw_trace(trace_seq_data, 2) << 32); + timestamp = ((u64)read_fw_trace(trace_seq_data, 1) << 32) | + read_fw_trace(trace_seq_data, 2); timestamp = (timestamp & ~ROGUE_FWT_TIMESTAMP_TIME_CLRMSK) >> ROGUE_FWT_TIMESTAMP_TIME_SHIFT; diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c index 21c185d18bb2..eba69309bb6c 100644 --- a/drivers/gpu/drm/imagination/pvr_queue.c +++ b/drivers/gpu/drm/imagination/pvr_queue.c @@ -109,12 +109,20 @@ pvr_queue_fence_get_driver_name(struct dma_fence *f) return PVR_DRIVER_NAME; } +static void pvr_queue_fence_release_work(struct work_struct *w) +{ + struct pvr_queue_fence *fence = container_of(w, struct pvr_queue_fence, release_work); + + pvr_context_put(fence->queue->ctx); + dma_fence_free(&fence->base); +} + static void pvr_queue_fence_release(struct dma_fence *f) { struct pvr_queue_fence *fence = container_of(f, struct pvr_queue_fence, base); + struct pvr_device *pvr_dev = fence->queue->ctx->pvr_dev; - pvr_context_put(fence->queue->ctx); - dma_fence_free(f); + queue_work(pvr_dev->sched_wq, &fence->release_work); } static const char * @@ -268,6 +276,7 @@ pvr_queue_fence_init(struct dma_fence *f, pvr_context_get(queue->ctx); fence->queue = queue; + INIT_WORK(&fence->release_work, pvr_queue_fence_release_work); dma_fence_init(&fence->base, fence_ops, &fence_ctx->lock, fence_ctx->id, atomic_inc_return(&fence_ctx->seqno)); @@ -304,8 +313,9 @@ pvr_queue_cccb_fence_init(struct dma_fence *fence, struct pvr_queue *queue) static void pvr_queue_job_fence_init(struct dma_fence *fence, struct pvr_queue *queue) { - pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops, - &queue->job_fence_ctx); + if (!fence->ops) + pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops, + &queue->job_fence_ctx); } /** diff --git a/drivers/gpu/drm/imagination/pvr_queue.h b/drivers/gpu/drm/imagination/pvr_queue.h index e06ced69302f..93fe9ac9f58c 100644 --- a/drivers/gpu/drm/imagination/pvr_queue.h +++ b/drivers/gpu/drm/imagination/pvr_queue.h @@ -5,6 +5,7 @@ #define PVR_QUEUE_H #include <drm/gpu_scheduler.h> +#include <linux/workqueue.h> #include "pvr_cccb.h" #include "pvr_device.h" @@ -63,6 +64,9 @@ struct pvr_queue_fence { /** @queue: Queue that created this fence. */ struct pvr_queue *queue; + + /** @release_work: Fence release work structure. */ + struct work_struct release_work; }; /** diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c index 363f885a7098..2896fa7501b1 100644 --- a/drivers/gpu/drm/imagination/pvr_vm.c +++ b/drivers/gpu/drm/imagination/pvr_vm.c @@ -293,8 +293,9 @@ err_bind_op_fini: static int pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op, - struct pvr_vm_context *vm_ctx, u64 device_addr, - u64 size) + struct pvr_vm_context *vm_ctx, + struct pvr_gem_object *pvr_obj, + u64 device_addr, u64 size) { int err; @@ -318,6 +319,7 @@ pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op, goto err_bind_op_fini; } + bind_op->pvr_obj = pvr_obj; bind_op->vm_ctx = vm_ctx; bind_op->device_addr = device_addr; bind_op->size = size; @@ -598,20 +600,6 @@ err_free: } /** - * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context. - * @vm_ctx: Target VM context. - * - * This function ensures that no mappings are left dangling by unmapping them - * all in order of ascending device-virtual address. - */ -void -pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx) -{ - WARN_ON(pvr_vm_unmap(vm_ctx, vm_ctx->gpuvm_mgr.mm_start, - vm_ctx->gpuvm_mgr.mm_range)); -} - -/** * pvr_vm_context_release() - Teardown a VM context. * @ref_count: Pointer to reference counter of the VM context. * @@ -703,11 +691,7 @@ pvr_vm_lock_extra(struct drm_gpuvm_exec *vm_exec) struct pvr_vm_bind_op *bind_op = vm_exec->extra.priv; struct pvr_gem_object *pvr_obj = bind_op->pvr_obj; - /* Unmap operations don't have an object to lock. */ - if (!pvr_obj) - return 0; - - /* Acquire lock on the GEM being mapped. */ + /* Acquire lock on the GEM object being mapped/unmapped. */ return drm_exec_lock_obj(&vm_exec->exec, gem_from_pvr_gem(pvr_obj)); } @@ -772,8 +756,10 @@ err_cleanup: } /** - * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory. + * pvr_vm_unmap_obj_locked() - Unmap an already mapped section of device-virtual + * memory. * @vm_ctx: Target VM context. + * @pvr_obj: Target PowerVR memory object. * @device_addr: Virtual device address at the start of the target mapping. * @size: Size of the target mapping. * @@ -784,9 +770,13 @@ err_cleanup: * * Any error encountered while performing internal operations required to * destroy the mapping (returned from pvr_vm_gpuva_unmap or * pvr_vm_gpuva_remap). + * + * The vm_ctx->lock must be held when calling this function. */ -int -pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size) +static int +pvr_vm_unmap_obj_locked(struct pvr_vm_context *vm_ctx, + struct pvr_gem_object *pvr_obj, + u64 device_addr, u64 size) { struct pvr_vm_bind_op bind_op = {0}; struct drm_gpuvm_exec vm_exec = { @@ -799,11 +789,13 @@ pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size) }, }; - int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, device_addr, - size); + int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, pvr_obj, + device_addr, size); if (err) return err; + pvr_gem_object_get(pvr_obj); + err = drm_gpuvm_exec_lock(&vm_exec); if (err) goto err_cleanup; @@ -818,6 +810,96 @@ err_cleanup: return err; } +/** + * pvr_vm_unmap_obj() - Unmap an already mapped section of device-virtual + * memory. + * @vm_ctx: Target VM context. + * @pvr_obj: Target PowerVR memory object. + * @device_addr: Virtual device address at the start of the target mapping. + * @size: Size of the target mapping. + * + * Return: + * * 0 on success, + * * Any error encountered by pvr_vm_unmap_obj_locked. + */ +int +pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj, + u64 device_addr, u64 size) +{ + int err; + + mutex_lock(&vm_ctx->lock); + err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj, device_addr, size); + mutex_unlock(&vm_ctx->lock); + + return err; +} + +/** + * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory. + * @vm_ctx: Target VM context. + * @device_addr: Virtual device address at the start of the target mapping. + * @size: Size of the target mapping. + * + * Return: + * * 0 on success, + * * Any error encountered by drm_gpuva_find, + * * Any error encountered by pvr_vm_unmap_obj_locked. + */ +int +pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size) +{ + struct pvr_gem_object *pvr_obj; + struct drm_gpuva *va; + int err; + + mutex_lock(&vm_ctx->lock); + + va = drm_gpuva_find(&vm_ctx->gpuvm_mgr, device_addr, size); + if (va) { + pvr_obj = gem_to_pvr_gem(va->gem.obj); + err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj, + va->va.addr, va->va.range); + } else { + err = -ENOENT; + } + + mutex_unlock(&vm_ctx->lock); + + return err; +} + +/** + * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context. + * @vm_ctx: Target VM context. + * + * This function ensures that no mappings are left dangling by unmapping them + * all in order of ascending device-virtual address. + */ +void +pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx) +{ + mutex_lock(&vm_ctx->lock); + + for (;;) { + struct pvr_gem_object *pvr_obj; + struct drm_gpuva *va; + + va = drm_gpuva_find_first(&vm_ctx->gpuvm_mgr, + vm_ctx->gpuvm_mgr.mm_start, + vm_ctx->gpuvm_mgr.mm_range); + if (!va) + break; + + pvr_obj = gem_to_pvr_gem(va->gem.obj); + + WARN_ON(pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj, + va->va.addr, va->va.range)); + } + + mutex_unlock(&vm_ctx->lock); +} + /* Static data areas are determined by firmware. */ static const struct drm_pvr_static_data_area static_data_areas[] = { { diff --git a/drivers/gpu/drm/imagination/pvr_vm.h b/drivers/gpu/drm/imagination/pvr_vm.h index 79406243617c..b0528dffa7f1 100644 --- a/drivers/gpu/drm/imagination/pvr_vm.h +++ b/drivers/gpu/drm/imagination/pvr_vm.h @@ -38,6 +38,9 @@ struct pvr_vm_context *pvr_vm_create_context(struct pvr_device *pvr_dev, int pvr_vm_map(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj, u64 pvr_obj_offset, u64 device_addr, u64 size); +int pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx, + struct pvr_gem_object *pvr_obj, + u64 device_addr, u64 size); int pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size); void pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx); diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c index 5674f5707cca..8f6fba4217ec 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_crtc.c @@ -620,13 +620,16 @@ static void mtk_crtc_update_config(struct mtk_crtc *mtk_crtc, bool needs_vblank) mbox_send_message(mtk_crtc->cmdq_client.chan, cmdq_handle); mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0); + goto update_config_out; } -#else +#endif spin_lock_irqsave(&mtk_crtc->config_lock, flags); mtk_crtc->config_updating = false; spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); -#endif +#if IS_REACHABLE(CONFIG_MTK_CMDQ) +update_config_out: +#endif mutex_unlock(&mtk_crtc->hw_lock); } diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index 3d4648d2e15f..ccdc57cef3ea 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -1766,7 +1766,7 @@ static int mtk_dp_parse_capabilities(struct mtk_dp *mtk_dp) ret = drm_dp_dpcd_readb(&mtk_dp->aux, DP_MSTM_CAP, &val); if (ret < 1) { - drm_err(mtk_dp->drm_dev, "Read mstm cap failed\n"); + dev_err(mtk_dp->dev, "Read mstm cap failed: %zd\n", ret); return ret == 0 ? -EIO : ret; } @@ -1776,7 +1776,7 @@ static int mtk_dp_parse_capabilities(struct mtk_dp *mtk_dp) DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0, &val); if (ret < 1) { - drm_err(mtk_dp->drm_dev, "Read irq vector failed\n"); + dev_err(mtk_dp->dev, "Read irq vector failed: %zd\n", ret); return ret == 0 ? -EIO : ret; } @@ -2059,7 +2059,7 @@ static int mtk_dp_wait_hpd_asserted(struct drm_dp_aux *mtk_aux, unsigned long wa ret = mtk_dp_parse_capabilities(mtk_dp); if (ret) { - drm_err(mtk_dp->drm_dev, "Can't parse capabilities\n"); + dev_err(mtk_dp->dev, "Can't parse capabilities: %d\n", ret); return ret; } diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index 1864eb02dbf5..0fd13e6dd3f1 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -4,8 +4,10 @@ * Author: Jie Qiu <jie.qiu@mediatek.com> */ +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/component.h> +#include <linux/debugfs.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/media-bus-format.h> @@ -116,9 +118,15 @@ struct mtk_dpi_yc_limit { u16 c_bottom; }; +struct mtk_dpi_factor { + u32 clock; + u8 factor; +}; + /** * struct mtk_dpi_conf - Configuration of mediatek dpi. - * @cal_factor: Callback function to calculate factor value. + * @dpi_factor: SoC-specific pixel clock PLL factor values. + * @num_dpi_factor: Number of pixel clock PLL factor values. * @reg_h_fre_con: Register address of frequency control. * @max_clock_khz: Max clock frequency supported for this SoCs in khz units. * @edge_sel_en: Enable of edge selection. @@ -127,19 +135,24 @@ struct mtk_dpi_yc_limit { * @is_ck_de_pol: Support CK/DE polarity. * @swap_input_support: Support input swap function. * @support_direct_pin: IP supports direct connection to dpi panels. - * @input_2pixel: Input pixel of dp_intf is 2 pixel per round, so enable this - * config to enable this feature. * @dimension_mask: Mask used for HWIDTH, HPORCH, VSYNC_WIDTH and VSYNC_PORCH * (no shift). * @hvsize_mask: Mask of HSIZE and VSIZE mask (no shift). * @channel_swap_shift: Shift value of channel swap. * @yuv422_en_bit: Enable bit of yuv422. * @csc_enable_bit: Enable bit of CSC. + * @input_2p_en_bit: Enable bit for input two pixel per round feature. + * If present, implies that the feature must be enabled. * @pixels_per_iter: Quantity of transferred pixels per iteration. * @edge_cfg_in_mmsys: If the edge configuration for DPI's output needs to be set in MMSYS. + * @clocked_by_hdmi: HDMI IP outputs clock to dpi_pixel_clk input clock, needed + * for DPI registers access. + * @output_1pixel: Enable outputting one pixel per round; if the input is two pixel per + * round, the DPI hardware will internally transform it to 1T1P. */ struct mtk_dpi_conf { - unsigned int (*cal_factor)(int clock); + const struct mtk_dpi_factor *dpi_factor; + const u8 num_dpi_factor; u32 reg_h_fre_con; u32 max_clock_khz; bool edge_sel_en; @@ -148,14 +161,16 @@ struct mtk_dpi_conf { bool is_ck_de_pol; bool swap_input_support; bool support_direct_pin; - bool input_2pixel; u32 dimension_mask; u32 hvsize_mask; u32 channel_swap_shift; u32 yuv422_en_bit; u32 csc_enable_bit; + u32 input_2p_en_bit; u32 pixels_per_iter; bool edge_cfg_in_mmsys; + bool clocked_by_hdmi; + bool output_1pixel; }; static void mtk_dpi_mask(struct mtk_dpi *dpi, u32 offset, u32 val, u32 mask) @@ -166,6 +181,18 @@ static void mtk_dpi_mask(struct mtk_dpi *dpi, u32 offset, u32 val, u32 mask) writel(tmp, dpi->regs + offset); } +static void mtk_dpi_test_pattern_en(struct mtk_dpi *dpi, u8 type, bool enable) +{ + u32 val; + + if (enable) + val = FIELD_PREP(DPI_PAT_SEL, type) | DPI_PAT_EN; + else + val = 0; + + mtk_dpi_mask(dpi, DPI_PATTERN0, val, DPI_PAT_SEL | DPI_PAT_EN); +} + static void mtk_dpi_sw_reset(struct mtk_dpi *dpi, bool reset) { mtk_dpi_mask(dpi, DPI_RET, reset ? RST : 0, RST); @@ -410,12 +437,13 @@ static void mtk_dpi_config_swap_input(struct mtk_dpi *dpi, bool enable) static void mtk_dpi_config_2n_h_fre(struct mtk_dpi *dpi) { - mtk_dpi_mask(dpi, dpi->conf->reg_h_fre_con, H_FRE_2N, H_FRE_2N); + if (dpi->conf->reg_h_fre_con) + mtk_dpi_mask(dpi, dpi->conf->reg_h_fre_con, H_FRE_2N, H_FRE_2N); } static void mtk_dpi_config_disable_edge(struct mtk_dpi *dpi) { - if (dpi->conf->edge_sel_en) + if (dpi->conf->edge_sel_en && dpi->conf->reg_h_fre_con) mtk_dpi_mask(dpi, dpi->conf->reg_h_fre_con, 0, EDGE_SEL_EN); } @@ -471,6 +499,7 @@ static void mtk_dpi_power_off(struct mtk_dpi *dpi) mtk_dpi_disable(dpi); clk_disable_unprepare(dpi->pixel_clk); + clk_disable_unprepare(dpi->tvd_clk); clk_disable_unprepare(dpi->engine_clk); } @@ -487,6 +516,12 @@ static int mtk_dpi_power_on(struct mtk_dpi *dpi) goto err_refcount; } + ret = clk_prepare_enable(dpi->tvd_clk); + if (ret) { + dev_err(dpi->dev, "Failed to enable tvd pll: %d\n", ret); + goto err_engine; + } + ret = clk_prepare_enable(dpi->pixel_clk); if (ret) { dev_err(dpi->dev, "Failed to enable pixel clock: %d\n", ret); @@ -496,32 +531,39 @@ static int mtk_dpi_power_on(struct mtk_dpi *dpi) return 0; err_pixel: + clk_disable_unprepare(dpi->tvd_clk); +err_engine: clk_disable_unprepare(dpi->engine_clk); err_refcount: dpi->refcount--; return ret; } -static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi, - struct drm_display_mode *mode) +static unsigned int mtk_dpi_calculate_factor(struct mtk_dpi *dpi, int mode_clk) +{ + const struct mtk_dpi_factor *dpi_factor = dpi->conf->dpi_factor; + int i; + + for (i = 0; i < dpi->conf->num_dpi_factor; i++) { + if (mode_clk <= dpi_factor[i].clock) + return dpi_factor[i].factor; + } + + /* If no match try the lowest possible factor */ + return dpi_factor[dpi->conf->num_dpi_factor - 1].factor; +} + +static void mtk_dpi_set_pixel_clk(struct mtk_dpi *dpi, struct videomode *vm, int mode_clk) { - struct mtk_dpi_polarities dpi_pol; - struct mtk_dpi_sync_param hsync; - struct mtk_dpi_sync_param vsync_lodd = { 0 }; - struct mtk_dpi_sync_param vsync_leven = { 0 }; - struct mtk_dpi_sync_param vsync_rodd = { 0 }; - struct mtk_dpi_sync_param vsync_reven = { 0 }; - struct videomode vm = { 0 }; unsigned long pll_rate; unsigned int factor; /* let pll_rate can fix the valid range of tvdpll (1G~2GHz) */ - factor = dpi->conf->cal_factor(mode->clock); - drm_display_mode_to_videomode(mode, &vm); - pll_rate = vm.pixelclock * factor; + factor = mtk_dpi_calculate_factor(dpi, mode_clk); + pll_rate = vm->pixelclock * factor; dev_dbg(dpi->dev, "Want PLL %lu Hz, pixel clock %lu Hz\n", - pll_rate, vm.pixelclock); + pll_rate, vm->pixelclock); clk_set_rate(dpi->tvd_clk, pll_rate); pll_rate = clk_get_rate(dpi->tvd_clk); @@ -531,20 +573,36 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi, * pixels for each iteration: divide the clock by this number and * adjust the display porches accordingly. */ - vm.pixelclock = pll_rate / factor; - vm.pixelclock /= dpi->conf->pixels_per_iter; + vm->pixelclock = pll_rate / factor; + vm->pixelclock /= dpi->conf->pixels_per_iter; if ((dpi->output_fmt == MEDIA_BUS_FMT_RGB888_2X12_LE) || (dpi->output_fmt == MEDIA_BUS_FMT_RGB888_2X12_BE)) - clk_set_rate(dpi->pixel_clk, vm.pixelclock * 2); + clk_set_rate(dpi->pixel_clk, vm->pixelclock * 2); else - clk_set_rate(dpi->pixel_clk, vm.pixelclock); - + clk_set_rate(dpi->pixel_clk, vm->pixelclock); - vm.pixelclock = clk_get_rate(dpi->pixel_clk); + vm->pixelclock = clk_get_rate(dpi->pixel_clk); dev_dbg(dpi->dev, "Got PLL %lu Hz, pixel clock %lu Hz\n", - pll_rate, vm.pixelclock); + pll_rate, vm->pixelclock); +} + +static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi, + struct drm_display_mode *mode) +{ + struct mtk_dpi_polarities dpi_pol; + struct mtk_dpi_sync_param hsync; + struct mtk_dpi_sync_param vsync_lodd = { 0 }; + struct mtk_dpi_sync_param vsync_leven = { 0 }; + struct mtk_dpi_sync_param vsync_rodd = { 0 }; + struct mtk_dpi_sync_param vsync_reven = { 0 }; + struct videomode vm = { 0 }; + + drm_display_mode_to_videomode(mode, &vm); + + if (!dpi->conf->clocked_by_hdmi) + mtk_dpi_set_pixel_clk(dpi, &vm, mode->clock); dpi_pol.ck_pol = MTK_DPI_POLARITY_FALLING; dpi_pol.de_pol = MTK_DPI_POLARITY_RISING; @@ -607,12 +665,18 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi, if (dpi->conf->support_direct_pin) { mtk_dpi_config_yc_map(dpi, dpi->yc_map); mtk_dpi_config_2n_h_fre(dpi); - mtk_dpi_dual_edge(dpi); + + /* DPI can connect to either an external bridge or the internal HDMI encoder */ + if (dpi->conf->output_1pixel) + mtk_dpi_mask(dpi, DPI_CON, DPI_OUTPUT_1T1P_EN, DPI_OUTPUT_1T1P_EN); + else + mtk_dpi_dual_edge(dpi); + mtk_dpi_config_disable_edge(dpi); } - if (dpi->conf->input_2pixel) { - mtk_dpi_mask(dpi, DPI_CON, DPINTF_INPUT_2P_EN, - DPINTF_INPUT_2P_EN); + if (dpi->conf->input_2p_en_bit) { + mtk_dpi_mask(dpi, DPI_CON, dpi->conf->input_2p_en_bit, + dpi->conf->input_2p_en_bit); } mtk_dpi_sw_reset(dpi, false); @@ -767,6 +831,99 @@ mtk_dpi_bridge_mode_valid(struct drm_bridge *bridge, return MODE_OK; } +static int mtk_dpi_debug_tp_show(struct seq_file *m, void *arg) +{ + struct mtk_dpi *dpi = m->private; + bool en; + u32 val; + + if (!dpi) + return -EINVAL; + + val = readl(dpi->regs + DPI_PATTERN0); + en = val & DPI_PAT_EN; + val = FIELD_GET(DPI_PAT_SEL, val); + + seq_printf(m, "DPI Test Pattern: %s\n", en ? "Enabled" : "Disabled"); + + if (en) { + seq_printf(m, "Internal pattern %d: ", val); + switch (val) { + case 0: + seq_puts(m, "256 Vertical Gray\n"); + break; + case 1: + seq_puts(m, "1024 Vertical Gray\n"); + break; + case 2: + seq_puts(m, "256 Horizontal Gray\n"); + break; + case 3: + seq_puts(m, "1024 Horizontal Gray\n"); + break; + case 4: + seq_puts(m, "Vertical Color bars\n"); + break; + case 6: + seq_puts(m, "Frame border\n"); + break; + case 7: + seq_puts(m, "Dot moire\n"); + break; + default: + seq_puts(m, "Invalid selection\n"); + break; + } + } + + return 0; +} + +static ssize_t mtk_dpi_debug_tp_write(struct file *file, const char __user *ubuf, + size_t len, loff_t *offp) +{ + struct seq_file *m = file->private_data; + u32 en, type; + char buf[6]; + + if (!m || !m->private || *offp || len > sizeof(buf) - 1) + return -EINVAL; + + memset(buf, 0, sizeof(buf)); + if (copy_from_user(buf, ubuf, len)) + return -EFAULT; + + if (sscanf(buf, "%u %u", &en, &type) != 2) + return -EINVAL; + + if (en < 0 || en > 1 || type < 0 || type > 7) + return -EINVAL; + + mtk_dpi_test_pattern_en((struct mtk_dpi *)m->private, type, en); + return len; +} + +static int mtk_dpi_debug_tp_open(struct inode *inode, struct file *file) +{ + return single_open(file, mtk_dpi_debug_tp_show, inode->i_private); +} + +static const struct file_operations mtk_dpi_debug_tp_fops = { + .owner = THIS_MODULE, + .open = mtk_dpi_debug_tp_open, + .read = seq_read, + .write = mtk_dpi_debug_tp_write, + .llseek = seq_lseek, + .release = single_release, +}; + +static void mtk_dpi_debugfs_init(struct drm_bridge *bridge, struct dentry *root) +{ + struct mtk_dpi *dpi = bridge_to_dpi(bridge); + + debugfs_create_file("dpi_test_pattern", 0640, root, dpi, &mtk_dpi_debug_tp_fops); +} + static const struct drm_bridge_funcs mtk_dpi_bridge_funcs = { .attach = mtk_dpi_bridge_attach, .mode_set = mtk_dpi_bridge_mode_set, @@ -779,20 +936,23 @@ static const struct drm_bridge_funcs mtk_dpi_bridge_funcs = { .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, .atomic_reset = drm_atomic_helper_bridge_reset, + .debugfs_init = mtk_dpi_debugfs_init, }; void mtk_dpi_start(struct device *dev) { struct mtk_dpi *dpi = dev_get_drvdata(dev); - mtk_dpi_power_on(dpi); + if (!dpi->conf->clocked_by_hdmi) + mtk_dpi_power_on(dpi); } void mtk_dpi_stop(struct device *dev) { struct mtk_dpi *dpi = dev_get_drvdata(dev); - mtk_dpi_power_off(dpi); + if (!dpi->conf->clocked_by_hdmi) + mtk_dpi_power_off(dpi); } unsigned int mtk_dpi_encoder_index(struct device *dev) @@ -857,48 +1017,6 @@ static const struct component_ops mtk_dpi_component_ops = { .unbind = mtk_dpi_unbind, }; -static unsigned int mt8173_calculate_factor(int clock) -{ - if (clock <= 27000) - return 3 << 4; - else if (clock <= 84000) - return 3 << 3; - else if (clock <= 167000) - return 3 << 2; - else - return 3 << 1; -} - -static unsigned int mt2701_calculate_factor(int clock) -{ - if (clock <= 64000) - return 4; - else if (clock <= 128000) - return 2; - else - return 1; -} - -static unsigned int mt8183_calculate_factor(int clock) -{ - if (clock <= 27000) - return 8; - else if (clock <= 167000) - return 4; - else - return 2; -} - -static unsigned int mt8195_dpintf_calculate_factor(int clock) -{ - if (clock < 70000) - return 4; - else if (clock < 200000) - return 2; - else - return 1; -} - static const u32 mt8173_output_fmts[] = { MEDIA_BUS_FMT_RGB888_1X24, }; @@ -913,8 +1031,25 @@ static const u32 mt8195_output_fmts[] = { MEDIA_BUS_FMT_YUYV8_1X16, }; +static const struct mtk_dpi_factor dpi_factor_mt2701[] = { + { 64000, 4 }, { 128000, 2 }, { U32_MAX, 1 } +}; + +static const struct mtk_dpi_factor dpi_factor_mt8173[] = { + { 27000, 48 }, { 84000, 24 }, { 167000, 12 }, { U32_MAX, 6 } +}; + +static const struct mtk_dpi_factor dpi_factor_mt8183[] = { + { 27000, 8 }, { 167000, 4 }, { U32_MAX, 2 } +}; + +static const struct mtk_dpi_factor dpi_factor_mt8195_dp_intf[] = { + { 70000 - 1, 4 }, { 200000 - 1, 2 }, { U32_MAX, 1 } +}; + static const struct mtk_dpi_conf mt8173_conf = { - .cal_factor = mt8173_calculate_factor, + .dpi_factor = dpi_factor_mt8173, + .num_dpi_factor = ARRAY_SIZE(dpi_factor_mt8173), .reg_h_fre_con = 0xe0, .max_clock_khz = 300000, .output_fmts = mt8173_output_fmts, @@ -931,7 +1066,8 @@ static const struct mtk_dpi_conf mt8173_conf = { }; static const struct mtk_dpi_conf mt2701_conf = { - .cal_factor = mt2701_calculate_factor, + .dpi_factor = dpi_factor_mt2701, + .num_dpi_factor = ARRAY_SIZE(dpi_factor_mt2701), .reg_h_fre_con = 0xb0, .edge_sel_en = true, .max_clock_khz = 150000, @@ -949,7 +1085,8 @@ static const struct mtk_dpi_conf mt2701_conf = { }; static const struct mtk_dpi_conf mt8183_conf = { - .cal_factor = mt8183_calculate_factor, + .dpi_factor = dpi_factor_mt8183, + .num_dpi_factor = ARRAY_SIZE(dpi_factor_mt8183), .reg_h_fre_con = 0xe0, .max_clock_khz = 100000, .output_fmts = mt8183_output_fmts, @@ -966,7 +1103,8 @@ static const struct mtk_dpi_conf mt8183_conf = { }; static const struct mtk_dpi_conf mt8186_conf = { - .cal_factor = mt8183_calculate_factor, + .dpi_factor = dpi_factor_mt8183, + .num_dpi_factor = ARRAY_SIZE(dpi_factor_mt8183), .reg_h_fre_con = 0xe0, .max_clock_khz = 150000, .output_fmts = mt8183_output_fmts, @@ -984,7 +1122,8 @@ static const struct mtk_dpi_conf mt8186_conf = { }; static const struct mtk_dpi_conf mt8192_conf = { - .cal_factor = mt8183_calculate_factor, + .dpi_factor = dpi_factor_mt8183, + .num_dpi_factor = ARRAY_SIZE(dpi_factor_mt8183), .reg_h_fre_con = 0xe0, .max_clock_khz = 150000, .output_fmts = mt8183_output_fmts, @@ -1000,18 +1139,37 @@ static const struct mtk_dpi_conf mt8192_conf = { .csc_enable_bit = CSC_ENABLE, }; +static const struct mtk_dpi_conf mt8195_conf = { + .max_clock_khz = 594000, + .output_fmts = mt8183_output_fmts, + .num_output_fmts = ARRAY_SIZE(mt8183_output_fmts), + .pixels_per_iter = 1, + .is_ck_de_pol = true, + .swap_input_support = true, + .support_direct_pin = true, + .dimension_mask = HPW_MASK, + .hvsize_mask = HSIZE_MASK, + .channel_swap_shift = CH_SWAP, + .yuv422_en_bit = YUV422_EN, + .csc_enable_bit = CSC_ENABLE, + .input_2p_en_bit = DPI_INPUT_2P_EN, + .clocked_by_hdmi = true, + .output_1pixel = true, +}; + static const struct mtk_dpi_conf mt8195_dpintf_conf = { - .cal_factor = mt8195_dpintf_calculate_factor, + .dpi_factor = dpi_factor_mt8195_dp_intf, + .num_dpi_factor = ARRAY_SIZE(dpi_factor_mt8195_dp_intf), .max_clock_khz = 600000, .output_fmts = mt8195_output_fmts, .num_output_fmts = ARRAY_SIZE(mt8195_output_fmts), .pixels_per_iter = 4, - .input_2pixel = true, .dimension_mask = DPINTF_HPW_MASK, .hvsize_mask = DPINTF_HSIZE_MASK, .channel_swap_shift = DPINTF_CH_SWAP, .yuv422_en_bit = DPINTF_YUV422_EN, .csc_enable_bit = DPINTF_CSC_ENABLE, + .input_2p_en_bit = DPINTF_INPUT_2P_EN, }; static int mtk_dpi_probe(struct platform_device *pdev) @@ -1102,6 +1260,7 @@ static const struct of_device_id mtk_dpi_of_ids[] = { { .compatible = "mediatek,mt8188-dp-intf", .data = &mt8195_dpintf_conf }, { .compatible = "mediatek,mt8192-dpi", .data = &mt8192_conf }, { .compatible = "mediatek,mt8195-dp-intf", .data = &mt8195_dpintf_conf }, + { .compatible = "mediatek,mt8195-dpi", .data = &mt8195_conf }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, mtk_dpi_of_ids); diff --git a/drivers/gpu/drm/mediatek/mtk_dpi_regs.h b/drivers/gpu/drm/mediatek/mtk_dpi_regs.h index 62bd4931b344..23eeefce8fd2 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi_regs.h +++ b/drivers/gpu/drm/mediatek/mtk_dpi_regs.h @@ -40,6 +40,11 @@ #define FAKE_DE_LEVEN BIT(21) #define FAKE_DE_RODD BIT(22) #define FAKE_DE_REVEN BIT(23) + +/* DPI_CON: DPI instances */ +#define DPI_OUTPUT_1T1P_EN BIT(24) +#define DPI_INPUT_2P_EN BIT(25) +/* DPI_CON: DPINTF instances */ #define DPINTF_YUV422_EN BIT(24) #define DPINTF_CSC_ENABLE BIT(26) #define DPINTF_INPUT_2P_EN BIT(29) @@ -235,4 +240,8 @@ #define MATRIX_SEL_RGB_TO_JPEG 0 #define MATRIX_SEL_RGB_TO_BT601 2 +#define DPI_PATTERN0 0xf00 +#define DPI_PAT_EN BIT(0) +#define DPI_PAT_SEL GENMASK(6, 4) + #endif /* __MTK_DPI_REGS_H */ diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index f22ad2882697..74158b9d6503 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -327,6 +327,10 @@ static const struct mtk_mmsys_driver_data mt8195_vdosys1_driver_data = { .min_height = 1, }; +static const struct mtk_mmsys_driver_data mt8365_mmsys_driver_data = { + .mmsys_dev_num = 1, +}; + static const struct of_device_id mtk_drm_of_ids[] = { { .compatible = "mediatek,mt2701-mmsys", .data = &mt2701_mmsys_driver_data}, @@ -354,6 +358,8 @@ static const struct of_device_id mtk_drm_of_ids[] = { .data = &mt8195_vdosys0_driver_data}, { .compatible = "mediatek,mt8195-vdosys1", .data = &mt8195_vdosys1_driver_data}, + { .compatible = "mediatek,mt8365-mmsys", + .data = &mt8365_mmsys_driver_data}, { } }; MODULE_DEVICE_TABLE(of, mtk_drm_of_ids); @@ -754,6 +760,8 @@ static const struct of_device_id mtk_ddp_comp_dt_ids[] = { .data = (void *)MTK_DISP_MUTEX }, { .compatible = "mediatek,mt8195-disp-mutex", .data = (void *)MTK_DISP_MUTEX }, + { .compatible = "mediatek,mt8365-disp-mutex", + .data = (void *)MTK_DISP_MUTEX }, { .compatible = "mediatek,mt8173-disp-od", .data = (void *)MTK_DISP_OD }, { .compatible = "mediatek,mt2701-disp-ovl", @@ -810,6 +818,8 @@ static const struct of_device_id mtk_ddp_comp_dt_ids[] = { .data = (void *)MTK_DPI }, { .compatible = "mediatek,mt8195-dp-intf", .data = (void *)MTK_DP_INTF }, + { .compatible = "mediatek,mt8195-dpi", + .data = (void *)MTK_DPI }, { .compatible = "mediatek,mt2701-dsi", .data = (void *)MTK_DSI }, { .compatible = "mediatek,mt8173-dsi", diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 0683c2b3ca5b..d1f407fb7eb1 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -1116,12 +1116,12 @@ static ssize_t mtk_dsi_host_transfer(struct mipi_dsi_host *host, const struct mipi_dsi_msg *msg) { struct mtk_dsi *dsi = host_to_dsi(host); - u32 recv_cnt, i; + ssize_t recv_cnt; u8 read_data[16]; void *src_addr; u8 irq_flag = CMD_DONE_INT_FLAG; u32 dsi_mode; - int ret; + int ret, i; dsi_mode = readl(dsi->regs + DSI_MODE_CTRL); if (dsi_mode & MODE) { @@ -1170,7 +1170,7 @@ static ssize_t mtk_dsi_host_transfer(struct mipi_dsi_host *host, if (recv_cnt) memcpy(msg->rx_buf, src_addr, recv_cnt); - DRM_INFO("dsi get %d byte data from the panel address(0x%x)\n", + DRM_INFO("dsi get %zd byte data from the panel address(0x%x)\n", recv_cnt, *((u8 *)(msg->tx_buf))); restore_dsi_mode: diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index d4ab098e1174..06e4fac152b7 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -137,7 +137,7 @@ enum hdmi_aud_channel_swap_type { struct hdmi_audio_param { enum hdmi_audio_coding_type aud_codec; - enum hdmi_audio_sample_size aud_sampe_size; + enum hdmi_audio_sample_size aud_sample_size; enum hdmi_aud_input_type aud_input_type; enum hdmi_aud_i2s_fmt aud_i2s_fmt; enum hdmi_aud_mclk aud_mclk; @@ -163,16 +163,10 @@ struct mtk_hdmi { struct clk *clk[MTK_HDMI_CLK_COUNT]; struct drm_display_mode mode; bool dvi_mode; - u32 min_clock; - u32 max_clock; - u32 max_hdisplay; - u32 max_vdisplay; - u32 ibias; - u32 ibias_up; struct regmap *sys_regmap; unsigned int sys_offset; void __iomem *regs; - enum hdmi_colorspace csp; + struct platform_device *audio_pdev; struct hdmi_audio_param aud_param; bool audio_enable; bool powered; @@ -987,15 +981,14 @@ static int mtk_hdmi_setup_avi_infoframe(struct mtk_hdmi *hdmi, return 0; } -static int mtk_hdmi_setup_spd_infoframe(struct mtk_hdmi *hdmi, - const char *vendor, - const char *product) +static int mtk_hdmi_setup_spd_infoframe(struct mtk_hdmi *hdmi) { + struct drm_bridge *bridge = &hdmi->bridge; struct hdmi_spd_infoframe frame; u8 buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_SPD_INFOFRAME_SIZE]; ssize_t err; - err = hdmi_spd_infoframe_init(&frame, vendor, product); + err = hdmi_spd_infoframe_init(&frame, bridge->vendor, bridge->product); if (err < 0) { dev_err(hdmi->dev, "Failed to initialize SPD infoframe: %zd\n", err); @@ -1072,9 +1065,8 @@ static int mtk_hdmi_output_init(struct mtk_hdmi *hdmi) { struct hdmi_audio_param *aud_param = &hdmi->aud_param; - hdmi->csp = HDMI_COLORSPACE_RGB; aud_param->aud_codec = HDMI_AUDIO_CODING_TYPE_PCM; - aud_param->aud_sampe_size = HDMI_AUDIO_SAMPLE_SIZE_16; + aud_param->aud_sample_size = HDMI_AUDIO_SAMPLE_SIZE_16; aud_param->aud_input_type = HDMI_AUD_INPUT_I2S; aud_param->aud_i2s_fmt = HDMI_I2S_MODE_I2S_24BIT; aud_param->aud_mclk = HDMI_AUD_MCLK_128FS; @@ -1167,13 +1159,12 @@ static int mtk_hdmi_clk_enable_audio(struct mtk_hdmi *hdmi) return ret; ret = clk_prepare_enable(hdmi->clk[MTK_HDMI_CLK_AUD_SPDIF]); - if (ret) - goto err; + if (ret) { + clk_disable_unprepare(hdmi->clk[MTK_HDMI_CLK_AUD_BCLK]); + return ret; + } return 0; -err: - clk_disable_unprepare(hdmi->clk[MTK_HDMI_CLK_AUD_BCLK]); - return ret; } static void mtk_hdmi_clk_disable_audio(struct mtk_hdmi *hdmi) @@ -1377,7 +1368,7 @@ static void mtk_hdmi_send_infoframe(struct mtk_hdmi *hdmi, { mtk_hdmi_setup_audio_infoframe(hdmi); mtk_hdmi_setup_avi_infoframe(hdmi, mode); - mtk_hdmi_setup_spd_infoframe(hdmi, "mediatek", "On-chip HDMI"); + mtk_hdmi_setup_spd_infoframe(hdmi); if (mode->flags & DRM_MODE_FLAG_3D_MASK) mtk_hdmi_setup_vendor_specific_infoframe(hdmi, mode); } @@ -1569,14 +1560,14 @@ static int mtk_hdmi_audio_hw_params(struct device *dev, void *data, switch (daifmt->fmt) { case HDMI_I2S: hdmi_params.aud_codec = HDMI_AUDIO_CODING_TYPE_PCM; - hdmi_params.aud_sampe_size = HDMI_AUDIO_SAMPLE_SIZE_16; + hdmi_params.aud_sample_size = HDMI_AUDIO_SAMPLE_SIZE_16; hdmi_params.aud_input_type = HDMI_AUD_INPUT_I2S; hdmi_params.aud_i2s_fmt = HDMI_I2S_MODE_I2S_24BIT; hdmi_params.aud_mclk = HDMI_AUD_MCLK_128FS; break; case HDMI_SPDIF: hdmi_params.aud_codec = HDMI_AUDIO_CODING_TYPE_PCM; - hdmi_params.aud_sampe_size = HDMI_AUDIO_SAMPLE_SIZE_16; + hdmi_params.aud_sample_size = HDMI_AUDIO_SAMPLE_SIZE_16; hdmi_params.aud_input_type = HDMI_AUD_INPUT_SPDIF; break; default: @@ -1659,6 +1650,11 @@ static const struct hdmi_codec_ops mtk_hdmi_audio_codec_ops = { .hook_plugged_cb = mtk_hdmi_audio_hook_plugged_cb, }; +static void mtk_hdmi_unregister_audio_driver(void *data) +{ + platform_device_unregister(data); +} + static int mtk_hdmi_register_audio_driver(struct device *dev) { struct mtk_hdmi *hdmi = dev_get_drvdata(dev); @@ -1669,15 +1665,21 @@ static int mtk_hdmi_register_audio_driver(struct device *dev) .data = hdmi, .no_capture_mute = 1, }; - struct platform_device *pdev; + int ret; - pdev = platform_device_register_data(dev, HDMI_CODEC_DRV_NAME, - PLATFORM_DEVID_AUTO, &codec_data, - sizeof(codec_data)); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); + hdmi->audio_pdev = platform_device_register_data(dev, + HDMI_CODEC_DRV_NAME, + PLATFORM_DEVID_AUTO, + &codec_data, + sizeof(codec_data)); + if (IS_ERR(hdmi->audio_pdev)) + return PTR_ERR(hdmi->audio_pdev); + + ret = devm_add_action_or_reset(dev, mtk_hdmi_unregister_audio_driver, + hdmi->audio_pdev); + if (ret) + return ret; - DRM_INFO("%s driver bound to HDMI\n", HDMI_CODEC_DRV_NAME); return 0; } @@ -1721,14 +1723,17 @@ static int mtk_hdmi_probe(struct platform_device *pdev) hdmi->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_HPD; hdmi->bridge.type = DRM_MODE_CONNECTOR_HDMIA; - drm_bridge_add(&hdmi->bridge); + hdmi->bridge.vendor = "MediaTek"; + hdmi->bridge.product = "On-Chip HDMI"; + + ret = devm_drm_bridge_add(dev, &hdmi->bridge); + if (ret) + return dev_err_probe(dev, ret, "Failed to add bridge\n"); ret = mtk_hdmi_clk_enable_audio(hdmi); - if (ret) { - drm_bridge_remove(&hdmi->bridge); + if (ret) return dev_err_probe(dev, ret, "Failed to enable audio clocks\n"); - } return 0; } @@ -1737,12 +1742,10 @@ static void mtk_hdmi_remove(struct platform_device *pdev) { struct mtk_hdmi *hdmi = platform_get_drvdata(pdev); - drm_bridge_remove(&hdmi->bridge); mtk_hdmi_clk_disable_audio(hdmi); } -#ifdef CONFIG_PM_SLEEP -static int mtk_hdmi_suspend(struct device *dev) +static __maybe_unused int mtk_hdmi_suspend(struct device *dev) { struct mtk_hdmi *hdmi = dev_get_drvdata(dev); @@ -1751,22 +1754,14 @@ static int mtk_hdmi_suspend(struct device *dev) return 0; } -static int mtk_hdmi_resume(struct device *dev) +static __maybe_unused int mtk_hdmi_resume(struct device *dev) { struct mtk_hdmi *hdmi = dev_get_drvdata(dev); - int ret = 0; - - ret = mtk_hdmi_clk_enable_audio(hdmi); - if (ret) { - dev_err(dev, "hdmi resume failed!\n"); - return ret; - } - return 0; + return mtk_hdmi_clk_enable_audio(hdmi); } -#endif -static SIMPLE_DEV_PM_OPS(mtk_hdmi_pm_ops, - mtk_hdmi_suspend, mtk_hdmi_resume); + +static SIMPLE_DEV_PM_OPS(mtk_hdmi_pm_ops, mtk_hdmi_suspend, mtk_hdmi_resume); static const struct mtk_hdmi_conf mtk_hdmi_conf_mt2701 = { .tz_disabled = true, @@ -1778,15 +1773,10 @@ static const struct mtk_hdmi_conf mtk_hdmi_conf_mt8167 = { }; static const struct of_device_id mtk_hdmi_of_ids[] = { - { .compatible = "mediatek,mt2701-hdmi", - .data = &mtk_hdmi_conf_mt2701, - }, - { .compatible = "mediatek,mt8167-hdmi", - .data = &mtk_hdmi_conf_mt8167, - }, - { .compatible = "mediatek,mt8173-hdmi", - }, - {} + { .compatible = "mediatek,mt2701-hdmi", .data = &mtk_hdmi_conf_mt2701 }, + { .compatible = "mediatek,mt8167-hdmi", .data = &mtk_hdmi_conf_mt8167 }, + { .compatible = "mediatek,mt8173-hdmi" }, + { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, mtk_hdmi_of_ids); diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index 7ec833b6d829..974bc7c0ea76 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -170,6 +170,8 @@ config DRM_MSM_HDMI bool "Enable HDMI support in MSM DRM driver" depends on DRM_MSM default y + select DRM_DISPLAY_HDMI_HELPER + select DRM_DISPLAY_HDMI_STATE_HELPER help Compile in support for the HDMI output MSM DRM driver. It can be a primary or a secondary display on device. Note that this is used diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index edffb7737a97..53e2ff4406d8 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -880,6 +880,35 @@ static const struct adreno_info a6xx_gpus[] = { { 137, 1 }, ), }, { + .chip_ids = ADRENO_CHIP_IDS(0x06020300), + .family = ADRENO_6XX_GEN3, + .fw = { + [ADRENO_FW_SQE] = "a650_sqe.fw", + [ADRENO_FW_GMU] = "a623_gmu.bin", + }, + .gmem = SZ_512K, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_HAS_HW_APRIV, + .init = a6xx_gpu_init, + .a6xx = &(const struct a6xx_info) { + .hwcg = a690_hwcg, + .protect = &a650_protect, + .gmu_cgc_mode = 0x00020200, + .prim_fifo_threshold = 0x00010000, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(3), + }, + { /* sentinel */ }, + }, + }, + .address_space_size = SZ_16G, + }, { .chip_ids = ADRENO_CHIP_IDS( 0x06030001, 0x06030002 diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 699b0dd34b18..38c94915d4c9 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -1169,49 +1169,50 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; u32 val; + int ret; /* - * The GMU may still be in slumber unless the GPU started so check and - * skip putting it back into slumber if so + * GMU firmware's internal power state gets messed up if we send "prepare_slumber" hfi when + * oob_gpu handshake wasn't done after the last wake up. So do a dummy handshake here when + * required */ - val = gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE); + if (adreno_gpu->base.needs_hw_init) { + if (a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET)) + goto force_off; - if (val != 0xf) { - int ret = a6xx_gmu_wait_for_idle(gmu); + a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + } - /* If the GMU isn't responding assume it is hung */ - if (ret) { - a6xx_gmu_force_off(gmu); - return; - } + ret = a6xx_gmu_wait_for_idle(gmu); - a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung); + /* If the GMU isn't responding assume it is hung */ + if (ret) + goto force_off; - /* tell the GMU we want to slumber */ - ret = a6xx_gmu_notify_slumber(gmu); - if (ret) { - a6xx_gmu_force_off(gmu); - return; - } + a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung); - ret = gmu_poll_timeout(gmu, - REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS, val, - !(val & A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS_GPUBUSYIGNAHB), - 100, 10000); + /* tell the GMU we want to slumber */ + ret = a6xx_gmu_notify_slumber(gmu); + if (ret) + goto force_off; - /* - * Let the user know we failed to slumber but don't worry too - * much because we are powering down anyway - */ + ret = gmu_poll_timeout(gmu, + REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS, val, + !(val & A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS_GPUBUSYIGNAHB), + 100, 10000); - if (ret) - DRM_DEV_ERROR(gmu->dev, - "Unable to slumber GMU: status = 0%x/0%x\n", - gmu_read(gmu, - REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS), - gmu_read(gmu, - REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS2)); - } + /* + * Let the user know we failed to slumber but don't worry too + * much because we are powering down anyway + */ + + if (ret) + DRM_DEV_ERROR(gmu->dev, + "Unable to slumber GMU: status = 0%x/0%x\n", + gmu_read(gmu, + REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS), + gmu_read(gmu, + REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS2)); /* Turn off HFI */ a6xx_hfi_stop(gmu); @@ -1221,6 +1222,11 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) /* Tell RPMh to power off the GPU */ a6xx_rpmh_stop(gmu); + + return; + +force_off: + a6xx_gmu_force_off(gmu); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 0ae29a7c8a4d..1820c167fcee 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -616,6 +616,14 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu) gpu->ubwc_config.uavflagprd_inv = 2; } + if (adreno_is_a623(gpu)) { + gpu->ubwc_config.highest_bank_bit = 16; + gpu->ubwc_config.amsbc = 1; + gpu->ubwc_config.rgb565_predicator = 1; + gpu->ubwc_config.uavflagprd_inv = 2; + gpu->ubwc_config.macrotile_mode = 1; + } + if (adreno_is_a640_family(gpu)) gpu->ubwc_config.amsbc = 1; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 0fcae53c0b14..341a72a67401 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -1214,12 +1214,12 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); a6xx_state->gmu_registers = state_kcalloc(a6xx_state, - 3, sizeof(*a6xx_state->gmu_registers)); + 4, sizeof(*a6xx_state->gmu_registers)); if (!a6xx_state->gmu_registers) return; - a6xx_state->nr_gmu_registers = 3; + a6xx_state->nr_gmu_registers = 4; /* Get the CX GMU registers from AHB */ _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[0], @@ -1227,6 +1227,13 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[1], &a6xx_state->gmu_registers[1], true); + if (adreno_is_a621(adreno_gpu) || adreno_is_a623(adreno_gpu)) + _a6xx_get_gmu_registers(gpu, a6xx_state, &a621_gpucc_reg, + &a6xx_state->gmu_registers[2], false); + else + _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gpucc_reg, + &a6xx_state->gmu_registers[2], false); + if (!a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) return; @@ -1234,7 +1241,7 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, gpu_write(gpu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[2], - &a6xx_state->gmu_registers[2], false); + &a6xx_state->gmu_registers[3], false); } static struct msm_gpu_state_bo *a6xx_snapshot_gmu_bo( @@ -1507,6 +1514,8 @@ static void a6xx_get_indexed_registers(struct msm_gpu *gpu, /* Restore the size in the hardware */ gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, mempool_size); + + a6xx_state->nr_indexed_regs = count; } static void a7xx_get_indexed_registers(struct msm_gpu *gpu, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index dd4c28a8d923..e545106c70be 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -363,6 +363,9 @@ static const u32 a6xx_gmu_cx_registers[] = { 0x51e0, 0x51e2, 0x51f0, 0x51f0, 0x5200, 0x5201, /* GMU AO */ 0x9300, 0x9316, 0x9400, 0x9400, +}; + +static const u32 a6xx_gmu_gpucc_registers[] = { /* GPU CC */ 0x9800, 0x9812, 0x9840, 0x9852, 0x9c00, 0x9c04, 0x9c07, 0x9c0b, 0x9c15, 0x9c1c, 0x9c1e, 0x9c2d, 0x9c3c, 0x9c3d, 0x9c3f, 0x9c40, @@ -373,6 +376,17 @@ static const u32 a6xx_gmu_cx_registers[] = { 0xbc00, 0xbc16, 0xbc20, 0xbc27, }; +static const u32 a621_gmu_gpucc_registers[] = { + /* GPU CC */ + 0x9800, 0x980e, 0x9c00, 0x9c0e, 0xb000, 0xb004, 0xb400, 0xb404, + 0xb800, 0xb804, 0xbc00, 0xbc05, 0xbc14, 0xbc1d, 0xbc2a, 0xbc30, + 0xbc32, 0xbc32, 0xbc41, 0xbc55, 0xbc66, 0xbc68, 0xbc78, 0xbc7a, + 0xbc89, 0xbc8a, 0xbc9c, 0xbc9e, 0xbca0, 0xbca3, 0xbcb3, 0xbcb5, + 0xbcc5, 0xbcc7, 0xbcd6, 0xbcd8, 0xbce8, 0xbce9, 0xbcf9, 0xbcfc, + 0xbd0b, 0xbd0c, 0xbd1c, 0xbd1e, 0xbd40, 0xbd70, 0xbe00, 0xbe16, + 0xbe20, 0xbe2d, +}; + static const u32 a6xx_gmu_cx_rscc_registers[] = { /* GPU RSCC */ 0x008c, 0x008c, 0x0101, 0x0102, 0x0340, 0x0342, 0x0344, 0x0347, @@ -386,6 +400,9 @@ static const struct a6xx_registers a6xx_gmu_reglist[] = { REGS(a6xx_gmu_gx_registers, 0, 0), }; +static const struct a6xx_registers a6xx_gpucc_reg = REGS(a6xx_gmu_gpucc_registers, 0, 0); +static const struct a6xx_registers a621_gpucc_reg = REGS(a621_gmu_gpucc_registers, 0, 0); + static u32 a6xx_get_cp_roq_size(struct msm_gpu *gpu); static u32 a7xx_get_cp_roq_size(struct msm_gpu *gpu); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 1238f3265978..7156cda07b03 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -883,6 +883,16 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state, drm_printf(p, " - dir=%s\n", info->flags & IOMMU_FAULT_WRITE ? "WRITE" : "READ"); drm_printf(p, " - type=%s\n", info->type); drm_printf(p, " - source=%s\n", info->block); + + /* Information extracted from what we think are the current + * pgtables. Hopefully the TTBR0 matches what we've extracted + * from the SMMU registers in smmu_info! + */ + drm_puts(p, "pgtable-fault-info:\n"); + drm_printf(p, " - ttbr0: %.16llx\n", (u64)info->pgtbl_ttbr0); + drm_printf(p, " - asid: %d\n", info->asid); + drm_printf(p, " - ptes: %.16llx %.16llx %.16llx %.16llx\n", + info->ptes[0], info->ptes[1], info->ptes[2], info->ptes[3]); } drm_printf(p, "rbbm-status: 0x%08x\n", state->rbbm_status); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index dcf454629ce0..92caba3584da 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -442,6 +442,11 @@ static inline int adreno_is_a621(const struct adreno_gpu *gpu) return gpu->info->chip_ids[0] == 0x06020100; } +static inline int adreno_is_a623(const struct adreno_gpu *gpu) +{ + return gpu->info->chip_ids[0] == 0x06020300; +} + static inline int adreno_is_a630(const struct adreno_gpu *gpu) { return adreno_is_revn(gpu, 630); diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h index bcb39807fe61..6ac97c378056 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h @@ -343,8 +343,8 @@ static const struct dpu_wb_cfg sm8650_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .xin_id = 6, .vbif_idx = VBIF_RT, .maxlinewidth = 4096, @@ -452,6 +452,7 @@ const struct dpu_mdss_cfg dpu_sm8650_cfg = { .mdss_ver = &sm8650_mdss_ver, .caps = &sm8650_dpu_caps, .mdp = &sm8650_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8650_ctl), .ctl = sm8650_ctl, .sspp_count = ARRAY_SIZE(sm8650_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h index ab3dfb0b374e..1f32807bb5e5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h @@ -190,6 +190,7 @@ const struct dpu_mdss_cfg dpu_msm8937_cfg = { .mdss_ver = &msm8937_mdss_ver, .caps = &msm8937_dpu_caps, .mdp = msm8937_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8937_ctl), .ctl = msm8937_ctl, .sspp_count = ARRAY_SIZE(msm8937_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h index 6bdaecca6761..42131959ff22 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h @@ -167,6 +167,7 @@ const struct dpu_mdss_cfg dpu_msm8917_cfg = { .mdss_ver = &msm8917_mdss_ver, .caps = &msm8917_dpu_caps, .mdp = msm8917_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8917_ctl), .ctl = msm8917_ctl, .sspp_count = ARRAY_SIZE(msm8917_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h index 14f36ea6ad0e..2b4723a5c676 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h @@ -198,6 +198,7 @@ const struct dpu_mdss_cfg dpu_msm8953_cfg = { .mdss_ver = &msm8953_mdss_ver, .caps = &msm8953_dpu_caps, .mdp = msm8953_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8953_ctl), .ctl = msm8953_ctl, .sspp_count = ARRAY_SIZE(msm8953_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h index 491f6f5827d1..5cf19de71f06 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h @@ -316,6 +316,7 @@ const struct dpu_mdss_cfg dpu_msm8996_cfg = { .mdss_ver = &msm8996_mdss_ver, .caps = &msm8996_dpu_caps, .mdp = msm8996_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8996_ctl), .ctl = msm8996_ctl, .sspp_count = ARRAY_SIZE(msm8996_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h index 64c94e919a69..746474679ef5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h @@ -302,6 +302,7 @@ const struct dpu_mdss_cfg dpu_msm8998_cfg = { .mdss_ver = &msm8998_mdss_ver, .caps = &msm8998_dpu_caps, .mdp = &msm8998_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8998_ctl), .ctl = msm8998_ctl, .sspp_count = ARRAY_SIZE(msm8998_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h index 424815e7fb7d..4f2f68b07f20 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h @@ -269,6 +269,7 @@ const struct dpu_mdss_cfg dpu_sdm660_cfg = { .mdss_ver = &sdm660_mdss_ver, .caps = &sdm660_dpu_caps, .mdp = &sdm660_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(sdm660_ctl), .ctl = sdm660_ctl, .sspp_count = ARRAY_SIZE(sdm660_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h index df01227fc364..c70bef025ac4 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h @@ -205,6 +205,7 @@ const struct dpu_mdss_cfg dpu_sdm630_cfg = { .mdss_ver = &sdm630_mdss_ver, .caps = &sdm630_dpu_caps, .mdp = &sdm630_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(sdm630_ctl), .ctl = sdm630_ctl, .sspp_count = ARRAY_SIZE(sdm630_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h index 72bd4f7e9e50..ab7b4822ca63 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h @@ -319,6 +319,7 @@ const struct dpu_mdss_cfg dpu_sdm845_cfg = { .mdss_ver = &sdm845_mdss_ver, .caps = &sdm845_dpu_caps, .mdp = &sdm845_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(sdm845_ctl), .ctl = sdm845_ctl, .sspp_count = ARRAY_SIZE(sdm845_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h index daef07924886..c2fde980fb52 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h @@ -132,6 +132,7 @@ const struct dpu_mdss_cfg dpu_sdm670_cfg = { .mdss_ver = &sdm670_mdss_ver, .caps = &sdm845_dpu_caps, .mdp = &sdm670_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(sdm845_ctl), .ctl = sdm845_ctl, .sspp_count = ARRAY_SIZE(sdm670_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h index 36cc9dbc00b5..979527d98fbc 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h @@ -298,8 +298,8 @@ static const struct dpu_wb_cfg sm8150_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -388,6 +388,7 @@ const struct dpu_mdss_cfg dpu_sm8150_cfg = { .mdss_ver = &sm8150_mdss_ver, .caps = &sm8150_dpu_caps, .mdp = &sm8150_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8150_ctl), .ctl = sm8150_ctl, .sspp_count = ARRAY_SIZE(sm8150_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h index e8eacdb47967..d76b8992a6c1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h @@ -305,8 +305,8 @@ static const struct dpu_wb_cfg sc8180x_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -414,6 +414,7 @@ const struct dpu_mdss_cfg dpu_sc8180x_cfg = { .mdss_ver = &sc8180x_mdss_ver, .caps = &sc8180x_dpu_caps, .mdp = &sc8180x_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sc8180x_ctl), .ctl = sc8180x_ctl, .sspp_count = ARRAY_SIZE(sc8180x_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_2_sm7150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_2_sm7150.h index 2fe674d1e059..83db11339b29 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_2_sm7150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_2_sm7150.h @@ -261,8 +261,8 @@ static const struct dpu_wb_cfg sm7150_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -309,6 +309,7 @@ const struct dpu_mdss_cfg dpu_sm7150_cfg = { .mdss_ver = &sm7150_mdss_ver, .caps = &sm7150_dpu_caps, .mdp = &sm7150_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm7150_ctl), .ctl = sm7150_ctl, .sspp_count = ARRAY_SIZE(sm7150_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h index d761ed705bac..da11830d4407 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h @@ -27,6 +27,7 @@ static const struct dpu_mdp_cfg sm6150_mdp = { [DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2b4, .bit_off = 8 }, [DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2bc, .bit_off = 8 }, [DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2c4, .bit_off = 8 }, + [DPU_CLK_CTRL_WB2] = { .reg_off = 0x2bc, .bit_off = 16 }, }, }; @@ -162,6 +163,21 @@ static const struct dpu_pingpong_cfg sm6150_pp[] = { }, }; +static const struct dpu_wb_cfg sm6150_wb[] = { + { + .name = "wb_2", .id = WB_2, + .base = 0x65000, .len = 0x2c8, + .features = WB_SM8250_MASK, + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), + .clk_ctrl = DPU_CLK_CTRL_WB2, + .xin_id = 6, + .vbif_idx = VBIF_RT, + .maxlinewidth = 2160, + .intr_wb_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 4), + }, +}; + static const struct dpu_intf_cfg sm6150_intf[] = { { .name = "intf_0", .id = INTF_0, @@ -232,6 +248,7 @@ const struct dpu_mdss_cfg dpu_sm6150_cfg = { .mdss_ver = &sm6150_mdss_ver, .caps = &sm6150_dpu_caps, .mdp = &sm6150_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm6150_ctl), .ctl = sm6150_ctl, .sspp_count = ARRAY_SIZE(sm6150_sspp), @@ -242,6 +259,8 @@ const struct dpu_mdss_cfg dpu_sm6150_cfg = { .dspp = sm6150_dspp, .pingpong_count = ARRAY_SIZE(sm6150_pp), .pingpong = sm6150_pp, + .wb_count = ARRAY_SIZE(sm6150_wb), + .wb = sm6150_wb, .intf_count = ARRAY_SIZE(sm6150_intf), .intf = sm6150_intf, .vbif_count = ARRAY_SIZE(sdm845_vbif), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h index 76f60a2df7a8..d3d3a34d0b45 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h @@ -145,8 +145,8 @@ static const struct dpu_wb_cfg sm6125_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -216,6 +216,7 @@ const struct dpu_mdss_cfg dpu_sm6125_cfg = { .mdss_ver = &sm6125_mdss_ver, .caps = &sm6125_dpu_caps, .mdp = &sm6125_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm6125_ctl), .ctl = sm6125_ctl, .sspp_count = ARRAY_SIZE(sm6125_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h index e8916ae826a6..47e01c3c242f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h @@ -386,7 +386,7 @@ const struct dpu_mdss_cfg dpu_sm8250_cfg = { .mdss_ver = &sm8250_mdss_ver, .caps = &sm8250_dpu_caps, .mdp = &sm8250_mdp, - .cdm = &sc7280_cdm, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8250_ctl), .ctl = sm8250_ctl, .sspp_count = ARRAY_SIZE(sm8250_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h index 7382ebb6e5b2..040c94c0bb66 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h @@ -157,8 +157,8 @@ static const struct dpu_wb_cfg sc7180_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -204,6 +204,7 @@ const struct dpu_mdss_cfg dpu_sc7180_cfg = { .mdss_ver = &sc7180_mdss_ver, .caps = &sc7180_dpu_caps, .mdp = &sc7180_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sc7180_ctl), .ctl = sc7180_ctl, .sspp_count = ARRAY_SIZE(sc7180_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h index 0502cee2f116..397278ba999b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h @@ -151,8 +151,8 @@ static const struct dpu_wb_cfg sm6350_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -222,6 +222,7 @@ const struct dpu_mdss_cfg dpu_sm6350_cfg = { .mdss_ver = &sm6350_mdss_ver, .caps = &sm6350_dpu_caps, .mdp = &sm6350_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm6350_ctl), .ctl = sm6350_ctl, .sspp_count = ARRAY_SIZE(sm6350_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index f7c08e89c882..0c860e804cab 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -305,8 +305,8 @@ static const struct dpu_wb_cfg sm8350_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -396,6 +396,7 @@ const struct dpu_mdss_cfg dpu_sm8350_cfg = { .mdss_ver = &sm8350_mdss_ver, .caps = &sm8350_dpu_caps, .mdp = &sm8350_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8350_ctl), .ctl = sm8350_ctl, .sspp_count = ARRAY_SIZE(sm8350_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h index 2f153e0b5c6a..e9625c48c567 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h @@ -248,7 +248,7 @@ const struct dpu_mdss_cfg dpu_sc7280_cfg = { .mdss_ver = &sc7280_mdss_ver, .caps = &sc7280_dpu_caps, .mdp = &sc7280_mdp, - .cdm = &sc7280_cdm, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sc7280_ctl), .ctl = sc7280_ctl, .sspp_count = ARRAY_SIZE(sc7280_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index 0d143e390eca..fcee1c3665f8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -435,6 +435,7 @@ const struct dpu_mdss_cfg dpu_sc8280xp_cfg = { .mdss_ver = &sc8280xp_mdss_ver, .caps = &sc8280xp_dpu_caps, .mdp = &sc8280xp_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sc8280xp_ctl), .ctl = sc8280xp_ctl, .sspp_count = ARRAY_SIZE(sc8280xp_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index 08742472f9cc..19b2ee8bbd5f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -321,8 +321,8 @@ static const struct dpu_wb_cfg sm8450_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -412,6 +412,7 @@ const struct dpu_mdss_cfg dpu_sm8450_cfg = { .mdss_ver = &sm8450_mdss_ver, .caps = &sm8450_dpu_caps, .mdp = &sm8450_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8450_ctl), .ctl = sm8450_ctl, .sspp_count = ARRAY_SIZE(sm8450_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h index 76ec72a32378..4d96ce71746f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h @@ -458,7 +458,7 @@ const struct dpu_mdss_cfg dpu_sa8775p_cfg = { .mdss_ver = &sa8775p_mdss_ver, .caps = &sa8775p_dpu_caps, .mdp = &sa8775p_mdp, - .cdm = &sc7280_cdm, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sa8775p_ctl), .ctl = sa8775p_ctl, .sspp_count = ARRAY_SIZE(sa8775p_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h index 4d3787fceb72..24f988465bf6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h @@ -317,8 +317,8 @@ static const struct dpu_wb_cfg sm8550_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .xin_id = 6, .vbif_idx = VBIF_RT, .maxlinewidth = 4096, @@ -407,6 +407,7 @@ const struct dpu_mdss_cfg dpu_sm8550_cfg = { .mdss_ver = &sm8550_mdss_ver, .caps = &sm8550_dpu_caps, .mdp = &sm8550_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8550_ctl), .ctl = sm8550_ctl, .sspp_count = ARRAY_SIZE(sm8550_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h index 6b112e3d17da..6417baa84f82 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h @@ -317,8 +317,8 @@ static const struct dpu_wb_cfg x1e80100_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .xin_id = 6, .vbif_idx = VBIF_RT, .maxlinewidth = 4096, @@ -453,6 +453,7 @@ const struct dpu_mdss_cfg dpu_x1e80100_cfg = { .mdss_ver = &x1e80100_mdss_ver, .caps = &x1e80100_dpu_caps, .mdp = &x1e80100_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(x1e80100_ctl), .ctl = x1e80100_ctl, .sspp_count = ARRAY_SIZE(x1e80100_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c index 6f0a37f954fe..0fb5789c60d0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -118,26 +118,38 @@ static void _dpu_core_perf_calc_crtc(const struct dpu_core_perf *core_perf, return; } - memset(perf, 0, sizeof(struct dpu_core_perf_params)); - - if (core_perf->perf_tune.mode == DPU_PERF_MODE_MINIMUM) { - perf->bw_ctl = 0; - perf->max_per_pipe_ib = 0; - perf->core_clk_rate = 0; - } else if (core_perf->perf_tune.mode == DPU_PERF_MODE_FIXED) { - perf->bw_ctl = core_perf->fix_core_ab_vote; - perf->max_per_pipe_ib = core_perf->fix_core_ib_vote; - perf->core_clk_rate = core_perf->fix_core_clk_rate; - } else { - perf->bw_ctl = _dpu_core_perf_calc_bw(perf_cfg, crtc); - perf->max_per_pipe_ib = perf_cfg->min_dram_ib; - perf->core_clk_rate = _dpu_core_perf_calc_clk(perf_cfg, crtc, state); - } - + perf->bw_ctl = _dpu_core_perf_calc_bw(perf_cfg, crtc); + perf->max_per_pipe_ib = perf_cfg->min_dram_ib; + perf->core_clk_rate = _dpu_core_perf_calc_clk(perf_cfg, crtc, state); DRM_DEBUG_ATOMIC( - "crtc=%d clk_rate=%llu core_ib=%llu core_ab=%llu\n", + "crtc=%d clk_rate=%llu core_ib=%u core_ab=%u\n", crtc->base.id, perf->core_clk_rate, - perf->max_per_pipe_ib, perf->bw_ctl); + perf->max_per_pipe_ib, + (u32)DIV_ROUND_UP_ULL(perf->bw_ctl, 1000)); +} + +static void dpu_core_perf_aggregate(struct drm_device *ddev, + enum dpu_crtc_client_type curr_client_type, + struct dpu_core_perf_params *perf) +{ + struct dpu_crtc_state *dpu_cstate; + struct drm_crtc *tmp_crtc; + + drm_for_each_crtc(tmp_crtc, ddev) { + if (tmp_crtc->enabled && + curr_client_type == dpu_crtc_get_client_type(tmp_crtc)) { + dpu_cstate = to_dpu_crtc_state(tmp_crtc->state); + + perf->max_per_pipe_ib = max(perf->max_per_pipe_ib, + dpu_cstate->new_perf.max_per_pipe_ib); + + perf->bw_ctl += dpu_cstate->new_perf.bw_ctl; + + DRM_DEBUG_ATOMIC("crtc=%d bw=%llu\n", + tmp_crtc->base.id, + dpu_cstate->new_perf.bw_ctl); + } + } } /** @@ -150,11 +162,9 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc, struct drm_crtc_state *state) { u32 bw, threshold; - u64 bw_sum_of_intfs = 0; - enum dpu_crtc_client_type curr_client_type; struct dpu_crtc_state *dpu_cstate; - struct drm_crtc *tmp_crtc; struct dpu_kms *kms; + struct dpu_core_perf_params perf = { 0 }; if (!crtc || !state) { DPU_ERROR("invalid crtc\n"); @@ -172,80 +182,56 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc, /* obtain new values */ _dpu_core_perf_calc_crtc(&kms->perf, crtc, state, &dpu_cstate->new_perf); - bw_sum_of_intfs = dpu_cstate->new_perf.bw_ctl; - curr_client_type = dpu_crtc_get_client_type(crtc); - - drm_for_each_crtc(tmp_crtc, crtc->dev) { - if (tmp_crtc->enabled && - dpu_crtc_get_client_type(tmp_crtc) == curr_client_type && - tmp_crtc != crtc) { - struct dpu_crtc_state *tmp_cstate = - to_dpu_crtc_state(tmp_crtc->state); - - DRM_DEBUG_ATOMIC("crtc:%d bw:%llu ctrl:%d\n", - tmp_crtc->base.id, tmp_cstate->new_perf.bw_ctl, - tmp_cstate->bw_control); + dpu_core_perf_aggregate(crtc->dev, dpu_crtc_get_client_type(crtc), &perf); - bw_sum_of_intfs += tmp_cstate->new_perf.bw_ctl; - } - - /* convert bandwidth to kb */ - bw = DIV_ROUND_UP_ULL(bw_sum_of_intfs, 1000); - DRM_DEBUG_ATOMIC("calculated bandwidth=%uk\n", bw); + /* convert bandwidth to kb */ + bw = DIV_ROUND_UP_ULL(perf.bw_ctl, 1000); + DRM_DEBUG_ATOMIC("calculated bandwidth=%uk\n", bw); - threshold = kms->perf.perf_cfg->max_bw_high; + threshold = kms->perf.perf_cfg->max_bw_high; - DRM_DEBUG_ATOMIC("final threshold bw limit = %d\n", threshold); + DRM_DEBUG_ATOMIC("final threshold bw limit = %d\n", threshold); - if (!threshold) { - DPU_ERROR("no bandwidth limits specified\n"); - return -E2BIG; - } else if (bw > threshold) { - DPU_ERROR("exceeds bandwidth: %ukb > %ukb\n", bw, - threshold); - return -E2BIG; - } + if (!threshold) { + DPU_ERROR("no bandwidth limits specified\n"); + return -E2BIG; + } else if (bw > threshold) { + DPU_ERROR("exceeds bandwidth: %ukb > %ukb\n", bw, + threshold); + return -E2BIG; } return 0; } static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms, - struct drm_crtc *crtc) + struct drm_crtc *crtc) { struct dpu_core_perf_params perf = { 0 }; - enum dpu_crtc_client_type curr_client_type - = dpu_crtc_get_client_type(crtc); - struct drm_crtc *tmp_crtc; - struct dpu_crtc_state *dpu_cstate; int i, ret = 0; - u64 avg_bw; + u32 avg_bw; + u32 peak_bw; if (!kms->num_paths) return 0; - drm_for_each_crtc(tmp_crtc, crtc->dev) { - if (tmp_crtc->enabled && - curr_client_type == - dpu_crtc_get_client_type(tmp_crtc)) { - dpu_cstate = to_dpu_crtc_state(tmp_crtc->state); - - perf.max_per_pipe_ib = max(perf.max_per_pipe_ib, - dpu_cstate->new_perf.max_per_pipe_ib); - - perf.bw_ctl += dpu_cstate->new_perf.bw_ctl; + if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM) { + avg_bw = 0; + peak_bw = 0; + } else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED) { + avg_bw = kms->perf.fix_core_ab_vote; + peak_bw = kms->perf.fix_core_ib_vote; + } else { + dpu_core_perf_aggregate(crtc->dev, dpu_crtc_get_client_type(crtc), &perf); - DRM_DEBUG_ATOMIC("crtc=%d bw=%llu paths:%d\n", - tmp_crtc->base.id, - dpu_cstate->new_perf.bw_ctl, kms->num_paths); - } + avg_bw = div_u64(perf.bw_ctl, 1000); /*Bps_to_icc*/ + peak_bw = perf.max_per_pipe_ib; } - avg_bw = perf.bw_ctl; - do_div(avg_bw, (kms->num_paths * 1000)); /*Bps_to_icc*/ + avg_bw /= kms->num_paths; for (i = 0; i < kms->num_paths; i++) - icc_set_bw(kms->path[i], avg_bw, perf.max_per_pipe_ib); + icc_set_bw(kms->path[i], avg_bw, peak_bw); return ret; } @@ -476,9 +462,9 @@ int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent) &perf->core_clk_rate); debugfs_create_u32("enable_bw_release", 0600, entry, (u32 *)&perf->enable_bw_release); - debugfs_create_u32("threshold_low", 0400, entry, + debugfs_create_u32("low_core_ab", 0400, entry, (u32 *)&perf->perf_cfg->max_bw_low); - debugfs_create_u32("threshold_high", 0400, entry, + debugfs_create_u32("max_core_ab", 0400, entry, (u32 *)&perf->perf_cfg->max_bw_high); debugfs_create_u32("min_core_ib", 0400, entry, (u32 *)&perf->perf_cfg->min_core_ib); @@ -490,9 +476,9 @@ int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent) (u32 *)perf, &dpu_core_perf_mode_fops); debugfs_create_u64("fix_core_clk_rate", 0600, entry, &perf->fix_core_clk_rate); - debugfs_create_u64("fix_core_ib_vote", 0600, entry, + debugfs_create_u32("fix_core_ib_vote", 0600, entry, &perf->fix_core_ib_vote); - debugfs_create_u64("fix_core_ab_vote", 0600, entry, + debugfs_create_u32("fix_core_ab_vote", 0600, entry, &perf->fix_core_ab_vote); return 0; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h index 451bf8021114..d2f21d34e501 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h @@ -19,7 +19,7 @@ * @core_clk_rate: core clock rate request */ struct dpu_core_perf_params { - u64 max_per_pipe_ib; + u32 max_per_pipe_ib; u64 bw_ctl; u64 core_clk_rate; }; @@ -40,8 +40,8 @@ struct dpu_core_perf_tune { * @perf_tune: debug control for performance tuning * @enable_bw_release: debug control for bandwidth release * @fix_core_clk_rate: fixed core clock request in Hz used in mode 2 - * @fix_core_ib_vote: fixed core ib vote in bps used in mode 2 - * @fix_core_ab_vote: fixed core ab vote in bps used in mode 2 + * @fix_core_ib_vote: fixed core ib vote in KBps used in mode 2 + * @fix_core_ab_vote: fixed core ab vote in KBps used in mode 2 */ struct dpu_core_perf { const struct dpu_perf_cfg *perf_cfg; @@ -50,8 +50,8 @@ struct dpu_core_perf { struct dpu_core_perf_tune perf_tune; u32 enable_bw_release; u64 fix_core_clk_rate; - u64 fix_core_ib_vote; - u64 fix_core_ab_vote; + u32 fix_core_ib_vote; + u32 fix_core_ab_vote; }; int dpu_core_perf_crtc_check(struct drm_crtc *crtc, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index e5dcd41a361f..0714936d8835 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -953,6 +953,45 @@ static int _dpu_crtc_wait_for_frame_done(struct drm_crtc *crtc) return rc; } +static int dpu_crtc_kickoff_clone_mode(struct drm_crtc *crtc) +{ + struct drm_encoder *encoder; + struct drm_encoder *rt_encoder = NULL, *wb_encoder = NULL; + struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc); + + /* Find encoder for real time display */ + drm_for_each_encoder_mask(encoder, crtc->dev, + crtc->state->encoder_mask) { + if (encoder->encoder_type == DRM_MODE_ENCODER_VIRTUAL) + wb_encoder = encoder; + else + rt_encoder = encoder; + } + + if (!rt_encoder || !wb_encoder) { + DRM_DEBUG_ATOMIC("real time or wb encoder not found\n"); + return -EINVAL; + } + + dpu_encoder_prepare_for_kickoff(wb_encoder); + dpu_encoder_prepare_for_kickoff(rt_encoder); + + dpu_vbif_clear_errors(dpu_kms); + + /* + * Kickoff real time encoder last as it's the encoder that + * will do the flush + */ + dpu_encoder_kickoff(wb_encoder); + dpu_encoder_kickoff(rt_encoder); + + /* Don't start frame done timers until the kickoffs have finished */ + dpu_encoder_start_frame_done_timer(wb_encoder); + dpu_encoder_start_frame_done_timer(rt_encoder); + + return 0; +} + /** * dpu_crtc_commit_kickoff - trigger kickoff of the commit for this crtc * @crtc: Pointer to drm crtc object @@ -981,13 +1020,27 @@ void dpu_crtc_commit_kickoff(struct drm_crtc *crtc) goto end; } } - /* - * Encoder will flush/start now, unless it has a tx pending. If so, it - * may delay and flush at an irq event (e.g. ppdone) - */ - drm_for_each_encoder_mask(encoder, crtc->dev, - crtc->state->encoder_mask) - dpu_encoder_prepare_for_kickoff(encoder); + + if (drm_crtc_in_clone_mode(crtc->state)) { + if (dpu_crtc_kickoff_clone_mode(crtc)) + goto end; + } else { + /* + * Encoder will flush/start now, unless it has a tx pending. + * If so, it may delay and flush at an irq event (e.g. ppdone) + */ + drm_for_each_encoder_mask(encoder, crtc->dev, + crtc->state->encoder_mask) + dpu_encoder_prepare_for_kickoff(encoder); + + dpu_vbif_clear_errors(dpu_kms); + + drm_for_each_encoder_mask(encoder, crtc->dev, + crtc->state->encoder_mask) { + dpu_encoder_kickoff(encoder); + dpu_encoder_start_frame_done_timer(encoder); + } + } if (atomic_inc_return(&dpu_crtc->frame_pending) == 1) { /* acquire bandwidth and other resources */ @@ -997,11 +1050,6 @@ void dpu_crtc_commit_kickoff(struct drm_crtc *crtc) dpu_crtc->play_count++; - dpu_vbif_clear_errors(dpu_kms); - - drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask) - dpu_encoder_kickoff(encoder); - reinit_completion(&dpu_crtc->frame_done_comp); end: @@ -1230,6 +1278,151 @@ done: return ret; } +#define MAX_CHANNELS_PER_CRTC 2 +#define MAX_HDISPLAY_SPLIT 1080 + +static struct msm_display_topology dpu_crtc_get_topology( + struct drm_crtc *crtc, + struct dpu_kms *dpu_kms, + struct drm_crtc_state *crtc_state) +{ + struct drm_display_mode *mode = &crtc_state->adjusted_mode; + struct msm_display_topology topology = {0}; + struct drm_encoder *drm_enc; + + drm_for_each_encoder_mask(drm_enc, crtc->dev, crtc_state->encoder_mask) + dpu_encoder_update_topology(drm_enc, &topology, crtc_state->state, + &crtc_state->adjusted_mode); + + topology.cwb_enabled = drm_crtc_in_clone_mode(crtc_state); + + /* + * Datapath topology selection + * + * Dual display + * 2 LM, 2 INTF ( Split display using 2 interfaces) + * + * Single display + * 1 LM, 1 INTF + * 2 LM, 1 INTF (stream merge to support high resolution interfaces) + * + * If DSC is enabled, use 2 LMs for 2:2:1 topology + * + * Add dspps to the reservation requirements if ctm is requested + * + * Only hardcode num_lm to 2 for cases where num_intf == 2 and CWB is not + * enabled. This is because in cases where CWB is enabled, num_intf will + * count both the WB and real-time phys encoders. + * + * For non-DSC CWB usecases, have the num_lm be decided by the + * (mode->hdisplay > MAX_HDISPLAY_SPLIT) check. + */ + + if (topology.num_intf == 2 && !topology.cwb_enabled) + topology.num_lm = 2; + else if (topology.num_dsc == 2) + topology.num_lm = 2; + else if (dpu_kms->catalog->caps->has_3d_merge) + topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1; + else + topology.num_lm = 1; + + if (crtc_state->ctm) + topology.num_dspp = topology.num_lm; + + return topology; +} + +static int dpu_crtc_assign_resources(struct drm_crtc *crtc, + struct drm_crtc_state *crtc_state) +{ + struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_CRTC]; + struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_CRTC]; + struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_CRTC]; + int i, num_lm, num_ctl, num_dspp; + struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc); + struct dpu_global_state *global_state; + struct dpu_crtc_state *cstate; + struct msm_display_topology topology; + int ret; + + /* + * Release and Allocate resources on every modeset + */ + global_state = dpu_kms_get_global_state(crtc_state->state); + if (IS_ERR(global_state)) + return PTR_ERR(global_state); + + dpu_rm_release(global_state, crtc); + + if (!crtc_state->enable) + return 0; + + topology = dpu_crtc_get_topology(crtc, dpu_kms, crtc_state); + ret = dpu_rm_reserve(&dpu_kms->rm, global_state, + crtc_state->crtc, &topology); + if (ret) + return ret; + + cstate = to_dpu_crtc_state(crtc_state); + + num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + crtc_state->crtc, + DPU_HW_BLK_CTL, hw_ctl, + ARRAY_SIZE(hw_ctl)); + num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + crtc_state->crtc, + DPU_HW_BLK_LM, hw_lm, + ARRAY_SIZE(hw_lm)); + num_dspp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + crtc_state->crtc, + DPU_HW_BLK_DSPP, hw_dspp, + ARRAY_SIZE(hw_dspp)); + + for (i = 0; i < num_lm; i++) { + int ctl_idx = (i < num_ctl) ? i : (num_ctl-1); + + cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]); + cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]); + if (i < num_dspp) + cstate->mixers[i].hw_dspp = to_dpu_hw_dspp(hw_dspp[i]); + } + + cstate->num_mixers = num_lm; + + return 0; +} + +/** + * dpu_crtc_check_mode_changed: check if full modeset is required + * @old_crtc_state: Previous CRTC state + * @new_crtc_state: Corresponding CRTC state to be checked + * + * Check if the changes in the object properties demand full mode set. + */ +int dpu_crtc_check_mode_changed(struct drm_crtc_state *old_crtc_state, + struct drm_crtc_state *new_crtc_state) +{ + struct drm_encoder *drm_enc; + struct drm_crtc *crtc = new_crtc_state->crtc; + bool clone_mode_enabled = drm_crtc_in_clone_mode(old_crtc_state); + bool clone_mode_requested = drm_crtc_in_clone_mode(new_crtc_state); + + DRM_DEBUG_ATOMIC("%d\n", crtc->base.id); + + /* there might be cases where encoder needs a modeset too */ + drm_for_each_encoder_mask(drm_enc, crtc->dev, new_crtc_state->encoder_mask) { + if (dpu_encoder_needs_modeset(drm_enc, new_crtc_state->state)) + new_crtc_state->mode_changed = true; + } + + if ((clone_mode_requested && !clone_mode_enabled) || + (!clone_mode_requested && clone_mode_enabled)) + new_crtc_state->mode_changed = true; + + return 0; +} + static int dpu_crtc_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state) { @@ -1245,6 +1438,13 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, bool needs_dirtyfb = dpu_crtc_needs_dirtyfb(crtc_state); + /* don't reallocate resources if only ACTIVE has beeen changed */ + if (crtc_state->mode_changed || crtc_state->connectors_changed) { + rc = dpu_crtc_assign_resources(crtc, crtc_state); + if (rc < 0) + return rc; + } + if (dpu_use_virtual_planes && (crtc_state->planes_changed || crtc_state->zpos_changed)) { rc = dpu_crtc_reassign_planes(crtc, crtc_state); @@ -1262,10 +1462,6 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, DRM_DEBUG_ATOMIC("%s: check\n", dpu_crtc->name); - /* force a full mode set if active state changed */ - if (crtc_state->active_changed) - crtc_state->mode_changed = true; - if (cstate->num_mixers) { rc = _dpu_crtc_check_and_setup_lm_bounds(crtc, crtc_state); if (rc) @@ -1484,8 +1680,9 @@ static int dpu_crtc_debugfs_state_show(struct seq_file *s, void *v) seq_printf(s, "intf_mode: %d\n", dpu_crtc_get_intf_mode(crtc)); seq_printf(s, "core_clk_rate: %llu\n", dpu_crtc->cur_perf.core_clk_rate); - seq_printf(s, "bw_ctl: %llu\n", dpu_crtc->cur_perf.bw_ctl); - seq_printf(s, "max_per_pipe_ib: %llu\n", + seq_printf(s, "bw_ctl: %uk\n", + (u32)DIV_ROUND_UP_ULL(dpu_crtc->cur_perf.bw_ctl, 1000)); + seq_printf(s, "max_per_pipe_ib: %u\n", dpu_crtc->cur_perf.max_per_pipe_ib); return 0; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h index 0b148f3ce0d7..94392b9b9245 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h @@ -239,6 +239,9 @@ static inline int dpu_crtc_frame_pending(struct drm_crtc *crtc) return crtc ? atomic_read(&to_dpu_crtc(crtc)->frame_pending) : -EINVAL; } +int dpu_crtc_check_mode_changed(struct drm_crtc_state *old_crtc_state, + struct drm_crtc_state *new_crtc_state); + int dpu_crtc_vblank(struct drm_crtc *crtc, bool en); void dpu_crtc_vblank_callback(struct drm_crtc *crtc); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 48e6e8d74c85..284e69bb47c1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2013 Red Hat * Copyright (c) 2014-2018, 2020-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. * * Author: Rob Clark <robdclark@gmail.com> */ @@ -24,6 +24,7 @@ #include "dpu_hw_catalog.h" #include "dpu_hw_intf.h" #include "dpu_hw_ctl.h" +#include "dpu_hw_cwb.h" #include "dpu_hw_dspp.h" #include "dpu_hw_dsc.h" #include "dpu_hw_merge3d.h" @@ -58,8 +59,6 @@ #define IDLE_SHORT_TIMEOUT 1 -#define MAX_HDISPLAY_SPLIT 1080 - /* timeout in frames waiting for frame done */ #define DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES 5 @@ -135,8 +134,12 @@ enum dpu_enc_rc_states { * @cur_slave: As above but for the slave encoder. * @hw_pp: Handle to the pingpong blocks used for the display. No. * pingpong blocks can be different than num_phys_encs. + * @hw_cwb: Handle to the CWB muxes used for concurrent writeback + * display. Number of CWB muxes can be different than + * num_phys_encs. * @hw_dsc: Handle to the DSC blocks used for the display. * @dsc_mask: Bitmask of used DSC blocks. + * @cwb_mask: Bitmask of used CWB muxes * @intfs_swapped: Whether or not the phys_enc interfaces have been swapped * for partial update right-only cases, such as pingpong * split where virtual pingpong does not generate IRQs @@ -179,9 +182,11 @@ struct dpu_encoder_virt { struct dpu_encoder_phys *cur_master; struct dpu_encoder_phys *cur_slave; struct dpu_hw_pingpong *hw_pp[MAX_CHANNELS_PER_ENC]; + struct dpu_hw_cwb *hw_cwb[MAX_CHANNELS_PER_ENC]; struct dpu_hw_dsc *hw_dsc[MAX_CHANNELS_PER_ENC]; unsigned int dsc_mask; + unsigned int cwb_mask; bool intfs_swapped; @@ -622,9 +627,9 @@ bool dpu_encoder_use_dsc_merge(struct drm_encoder *drm_enc) if (dpu_enc->phys_encs[i]) intf_count++; - /* See dpu_encoder_get_topology, we only support 2:2:1 topology */ - if (dpu_enc->dsc) - num_dsc = 2; + for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) + if (dpu_enc->hw_dsc[i]) + num_dsc++; return (num_dsc > 0) && (num_dsc > intf_count); } @@ -647,130 +652,51 @@ struct drm_dsc_config *dpu_encoder_get_dsc_config(struct drm_encoder *drm_enc) return NULL; } -static struct msm_display_topology dpu_encoder_get_topology( - struct dpu_encoder_virt *dpu_enc, - struct dpu_kms *dpu_kms, - struct drm_display_mode *mode, - struct drm_crtc_state *crtc_state, - struct drm_dsc_config *dsc) +void dpu_encoder_update_topology(struct drm_encoder *drm_enc, + struct msm_display_topology *topology, + struct drm_atomic_state *state, + const struct drm_display_mode *adj_mode) { - struct msm_display_topology topology = {0}; - int i, intf_count = 0; + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); + struct msm_drm_private *priv = dpu_enc->base.dev->dev_private; + struct msm_display_info *disp_info = &dpu_enc->disp_info; + struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms); + struct drm_connector *connector; + struct drm_connector_state *conn_state; + struct drm_framebuffer *fb; + struct drm_dsc_config *dsc; + + int i; for (i = 0; i < MAX_PHYS_ENCODERS_PER_VIRTUAL; i++) if (dpu_enc->phys_encs[i]) - intf_count++; + topology->num_intf++; - /* Datapath topology selection - * - * Dual display - * 2 LM, 2 INTF ( Split display using 2 interfaces) - * - * Single display - * 1 LM, 1 INTF - * 2 LM, 1 INTF (stream merge to support high resolution interfaces) - * - * Add dspps to the reservation requirements if ctm is requested - */ - if (intf_count == 2) - topology.num_lm = 2; - else if (!dpu_kms->catalog->caps->has_3d_merge) - topology.num_lm = 1; - else - topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1; - - if (crtc_state->ctm) - topology.num_dspp = topology.num_lm; - - topology.num_intf = intf_count; + dsc = dpu_encoder_get_dsc_config(drm_enc); + /* We only support 2 DSC mode (with 2 LM and 1 INTF) */ if (dsc) { /* - * In case of Display Stream Compression (DSC), we would use - * 2 DSC encoders, 2 layer mixers and 1 interface - * this is power optimal and can drive up to (including) 4k - * screens + * Use 2 DSC encoders, 2 layer mixers and 1 or 2 interfaces + * when Display Stream Compression (DSC) is enabled, + * and when enough DSC blocks are available. + * This is power-optimal and can drive up to (including) 4k + * screens. */ - topology.num_dsc = 2; - topology.num_lm = 2; - topology.num_intf = 1; - } - - return topology; -} - -static void dpu_encoder_assign_crtc_resources(struct dpu_kms *dpu_kms, - struct drm_encoder *drm_enc, - struct dpu_global_state *global_state, - struct drm_crtc_state *crtc_state) -{ - struct dpu_crtc_state *cstate; - struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC]; - struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC]; - struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_ENC]; - int num_lm, num_ctl, num_dspp, i; - - cstate = to_dpu_crtc_state(crtc_state); - - memset(cstate->mixers, 0, sizeof(cstate->mixers)); - - num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl)); - num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm)); - num_dspp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_DSPP, hw_dspp, - ARRAY_SIZE(hw_dspp)); - - for (i = 0; i < num_lm; i++) { - int ctl_idx = (i < num_ctl) ? i : (num_ctl-1); - - cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]); - cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]); - cstate->mixers[i].hw_dspp = i < num_dspp ? to_dpu_hw_dspp(hw_dspp[i]) : NULL; - } - - cstate->num_mixers = num_lm; -} - -static int dpu_encoder_virt_atomic_check( - struct drm_encoder *drm_enc, - struct drm_crtc_state *crtc_state, - struct drm_connector_state *conn_state) -{ - struct dpu_encoder_virt *dpu_enc; - struct msm_drm_private *priv; - struct dpu_kms *dpu_kms; - struct drm_display_mode *adj_mode; - struct msm_display_topology topology; - struct msm_display_info *disp_info; - struct dpu_global_state *global_state; - struct drm_framebuffer *fb; - struct drm_dsc_config *dsc; - int ret = 0; - - if (!drm_enc || !crtc_state || !conn_state) { - DPU_ERROR("invalid arg(s), drm_enc %d, crtc/conn state %d/%d\n", - drm_enc != NULL, crtc_state != NULL, conn_state != NULL); - return -EINVAL; + WARN(topology->num_intf > 2, + "DSC topology cannot support more than 2 interfaces\n"); + if (topology->num_intf >= 2 || dpu_kms->catalog->dsc_count >= 2) + topology->num_dsc = 2; + else + topology->num_dsc = 1; } - dpu_enc = to_dpu_encoder_virt(drm_enc); - DPU_DEBUG_ENC(dpu_enc, "\n"); - - priv = drm_enc->dev->dev_private; - disp_info = &dpu_enc->disp_info; - dpu_kms = to_dpu_kms(priv->kms); - adj_mode = &crtc_state->adjusted_mode; - global_state = dpu_kms_get_global_state(crtc_state->state); - if (IS_ERR(global_state)) - return PTR_ERR(global_state); - - trace_dpu_enc_atomic_check(DRMID(drm_enc)); - - dsc = dpu_encoder_get_dsc_config(drm_enc); - - topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode, crtc_state, dsc); + connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc); + if (!connector) + return; + conn_state = drm_atomic_get_new_connector_state(state, connector); + if (!conn_state) + return; /* * Use CDM only for writeback or DP at the moment as other interfaces cannot handle it. @@ -781,34 +707,45 @@ static int dpu_encoder_virt_atomic_check( fb = conn_state->writeback_job->fb; if (fb && MSM_FORMAT_IS_YUV(msm_framebuffer_format(fb))) - topology.needs_cdm = true; + topology->num_cdm++; } else if (disp_info->intf_type == INTF_DP) { if (msm_dp_is_yuv_420_enabled(priv->dp[disp_info->h_tile_instance[0]], adj_mode)) - topology.needs_cdm = true; + topology->num_cdm++; } +} - if (topology.needs_cdm && !dpu_enc->cur_master->hw_cdm) - crtc_state->mode_changed = true; - else if (!topology.needs_cdm && dpu_enc->cur_master->hw_cdm) - crtc_state->mode_changed = true; - /* - * Release and Allocate resources on every modeset - * Dont allocate when active is false. - */ - if (drm_atomic_crtc_needs_modeset(crtc_state)) { - dpu_rm_release(global_state, drm_enc); +bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_state *state) +{ + struct drm_connector *connector; + struct drm_connector_state *conn_state; + struct drm_framebuffer *fb; + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); - if (!crtc_state->active_changed || crtc_state->enable) - ret = dpu_rm_reserve(&dpu_kms->rm, global_state, - drm_enc, crtc_state, &topology); - if (!ret) - dpu_encoder_assign_crtc_resources(dpu_kms, drm_enc, - global_state, crtc_state); - } + if (!drm_enc || !state) + return false; - trace_dpu_enc_atomic_check_flags(DRMID(drm_enc), adj_mode->flags); + connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc); + if (!connector) + return false; - return ret; + conn_state = drm_atomic_get_new_connector_state(state, connector); + + /** + * These checks are duplicated from dpu_encoder_update_topology() since + * CRTC and encoder don't hold topology information + */ + if (dpu_enc->disp_info.intf_type == INTF_WB && conn_state->writeback_job) { + fb = conn_state->writeback_job->fb; + if (fb && MSM_FORMAT_IS_YUV(msm_framebuffer_format(fb))) { + if (!dpu_enc->cur_master->hw_cdm) + return true; + } else { + if (dpu_enc->cur_master->hw_cdm) + return true; + } + } + + return false; } static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc, @@ -1219,8 +1156,12 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, struct dpu_hw_blk *hw_pp[MAX_CHANNELS_PER_ENC]; struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC]; struct dpu_hw_blk *hw_dsc[MAX_CHANNELS_PER_ENC]; + struct dpu_hw_blk *hw_cwb[MAX_CHANNELS_PER_ENC]; int num_ctl, num_pp, num_dsc; + int num_cwb = 0; + bool is_cwb_encoder; unsigned int dsc_mask = 0; + unsigned int cwb_mask = 0; int i; if (!drm_enc) { @@ -1233,6 +1174,8 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, priv = drm_enc->dev->dev_private; dpu_kms = to_dpu_kms(priv->kms); + is_cwb_encoder = drm_crtc_in_clone_mode(crtc_state) && + dpu_enc->disp_info.intf_type == INTF_WB; global_state = dpu_kms_get_existing_global_state(dpu_kms); if (IS_ERR_OR_NULL(global_state)) { @@ -1243,18 +1186,38 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, trace_dpu_enc_mode_set(DRMID(drm_enc)); /* Query resource that have been reserved in atomic check step. */ - num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_PINGPONG, hw_pp, - ARRAY_SIZE(hw_pp)); + if (is_cwb_encoder) { + num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + drm_enc->crtc, + DPU_HW_BLK_DCWB_PINGPONG, + hw_pp, ARRAY_SIZE(hw_pp)); + num_cwb = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + drm_enc->crtc, + DPU_HW_BLK_CWB, + hw_cwb, ARRAY_SIZE(hw_cwb)); + } else { + num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + drm_enc->crtc, + DPU_HW_BLK_PINGPONG, hw_pp, + ARRAY_SIZE(hw_pp)); + } + + for (i = 0; i < num_cwb; i++) { + dpu_enc->hw_cwb[i] = to_dpu_hw_cwb(hw_cwb[i]); + cwb_mask |= BIT(dpu_enc->hw_cwb[i]->idx - CWB_0); + } + + dpu_enc->cwb_mask = cwb_mask; + num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl)); + drm_enc->crtc, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl)); for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) dpu_enc->hw_pp[i] = i < num_pp ? to_dpu_hw_pingpong(hw_pp[i]) : NULL; num_dsc = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_DSC, + drm_enc->crtc, DPU_HW_BLK_DSC, hw_dsc, ARRAY_SIZE(hw_dsc)); for (i = 0; i < num_dsc; i++) { dpu_enc->hw_dsc[i] = to_dpu_hw_dsc(hw_dsc[i]); @@ -1268,7 +1231,7 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, struct dpu_hw_blk *hw_cdm = NULL; dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_CDM, + drm_enc->crtc, DPU_HW_BLK_CDM, &hw_cdm, 1); dpu_enc->cur_master->hw_cdm = hw_cdm ? to_dpu_hw_cdm(hw_cdm) : NULL; } @@ -1654,6 +1617,7 @@ static void dpu_encoder_off_work(struct work_struct *work) static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc, struct dpu_encoder_phys *phys, uint32_t extra_flush_bits) { + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); struct dpu_hw_ctl *ctl; int pending_kickoff_cnt; u32 ret = UINT_MAX; @@ -1671,6 +1635,15 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc, pending_kickoff_cnt = dpu_encoder_phys_inc_pending(phys); + /* Return early if encoder is writeback and in clone mode */ + if (drm_enc->encoder_type == DRM_MODE_ENCODER_VIRTUAL && + dpu_enc->cwb_mask) { + DPU_DEBUG("encoder %d skip flush for concurrent writeback encoder\n", + DRMID(drm_enc)); + return; + } + + if (extra_flush_bits && ctl->ops.update_pending_flush) ctl->ops.update_pending_flush(ctl, extra_flush_bits); @@ -1693,6 +1666,8 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc, */ static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys) { + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(phys->parent); + if (!phys) { DPU_ERROR("invalid argument(s)\n"); return; @@ -1703,6 +1678,12 @@ static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys) return; } + if (phys->parent->encoder_type == DRM_MODE_ENCODER_VIRTUAL && + dpu_enc->cwb_mask) { + DPU_DEBUG("encoder %d CWB enabled, skipping\n", DRMID(phys->parent)); + return; + } + if (phys->ops.trigger_start && phys->enable_state != DPU_ENC_DISABLED) phys->ops.trigger_start(phys); } @@ -2020,7 +2001,6 @@ static void dpu_encoder_dsc_pipe_cfg(struct dpu_hw_ctl *ctl, static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, struct drm_dsc_config *dsc) { - /* coding only for 2LM, 2enc, 1 dsc config */ struct dpu_encoder_phys *enc_master = dpu_enc->cur_master; struct dpu_hw_ctl *ctl = enc_master->hw_ctl; struct dpu_hw_dsc *hw_dsc[MAX_CHANNELS_PER_ENC]; @@ -2030,22 +2010,24 @@ static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, int dsc_common_mode; int pic_width; u32 initial_lines; + int num_dsc = 0; int i; for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) { hw_pp[i] = dpu_enc->hw_pp[i]; hw_dsc[i] = dpu_enc->hw_dsc[i]; - if (!hw_pp[i] || !hw_dsc[i]) { - DPU_ERROR_ENC(dpu_enc, "invalid params for DSC\n"); - return; - } + if (!hw_pp[i] || !hw_dsc[i]) + break; + + num_dsc++; } - dsc_common_mode = 0; pic_width = dsc->pic_width; - dsc_common_mode = DSC_MODE_SPLIT_PANEL; + dsc_common_mode = 0; + if (num_dsc > 1) + dsc_common_mode |= DSC_MODE_SPLIT_PANEL; if (dpu_encoder_use_dsc_merge(enc_master->parent)) dsc_common_mode |= DSC_MODE_MULTIPLEX; if (enc_master->intf_mode == INTF_MODE_VIDEO) @@ -2054,14 +2036,10 @@ static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, this_frame_slices = pic_width / dsc->slice_width; intf_ip_w = this_frame_slices * dsc->slice_width; - /* - * dsc merge case: when using 2 encoders for the same stream, - * no. of slices need to be same on both the encoders. - */ - enc_ip_w = intf_ip_w / 2; + enc_ip_w = intf_ip_w / num_dsc; initial_lines = dpu_encoder_dsc_initial_line_calc(dsc, enc_ip_w); - for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) + for (i = 0; i < num_dsc; i++) dpu_encoder_dsc_pipe_cfg(ctl, hw_dsc[i], hw_pp[i], dsc, dsc_common_mode, initial_lines); } @@ -2135,6 +2113,25 @@ bool dpu_encoder_is_valid_for_commit(struct drm_encoder *drm_enc) } /** + * dpu_encoder_start_frame_done_timer - Start the encoder frame done timer + * @drm_enc: Pointer to drm encoder structure + */ +void dpu_encoder_start_frame_done_timer(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc; + unsigned long timeout_ms; + + dpu_enc = to_dpu_encoder_virt(drm_enc); + timeout_ms = DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES * 1000 / + drm_mode_vrefresh(&drm_enc->crtc->state->adjusted_mode); + + atomic_set(&dpu_enc->frame_done_timeout_ms, timeout_ms); + mod_timer(&dpu_enc->frame_done_timer, + jiffies + msecs_to_jiffies(timeout_ms)); + +} + +/** * dpu_encoder_kickoff - trigger a double buffer flip of the ctl path * (i.e. ctl flush and start) immediately. * @drm_enc: encoder pointer @@ -2143,7 +2140,6 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc) { struct dpu_encoder_virt *dpu_enc; struct dpu_encoder_phys *phys; - unsigned long timeout_ms; unsigned int i; DPU_ATRACE_BEGIN("encoder_kickoff"); @@ -2151,13 +2147,6 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc) trace_dpu_enc_kickoff(DRMID(drm_enc)); - timeout_ms = DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES * 1000 / - drm_mode_vrefresh(&drm_enc->crtc->state->adjusted_mode); - - atomic_set(&dpu_enc->frame_done_timeout_ms, timeout_ms); - mod_timer(&dpu_enc->frame_done_timer, - jiffies + msecs_to_jiffies(timeout_ms)); - /* All phys encs are ready to go, trigger the kickoff */ _dpu_encoder_kickoff_phys(dpu_enc); @@ -2183,22 +2172,22 @@ static void dpu_encoder_helper_reset_mixers(struct dpu_encoder_phys *phys_enc) memset(&mixer, 0, sizeof(mixer)); /* reset all mixers for this encoder */ - if (phys_enc->hw_ctl->ops.clear_all_blendstages) - phys_enc->hw_ctl->ops.clear_all_blendstages(phys_enc->hw_ctl); + if (ctl->ops.clear_all_blendstages) + ctl->ops.clear_all_blendstages(ctl); global_state = dpu_kms_get_existing_global_state(phys_enc->dpu_kms); num_lm = dpu_rm_get_assigned_resources(&phys_enc->dpu_kms->rm, global_state, - phys_enc->parent->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm)); + phys_enc->parent->crtc, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm)); for (i = 0; i < num_lm; i++) { hw_mixer[i] = to_dpu_hw_mixer(hw_lm[i]); - if (phys_enc->hw_ctl->ops.update_pending_flush_mixer) - phys_enc->hw_ctl->ops.update_pending_flush_mixer(ctl, hw_mixer[i]->idx); + if (ctl->ops.update_pending_flush_mixer) + ctl->ops.update_pending_flush_mixer(ctl, hw_mixer[i]->idx); /* clear all blendstages */ - if (phys_enc->hw_ctl->ops.setup_blendstage) - phys_enc->hw_ctl->ops.setup_blendstage(ctl, hw_mixer[i]->idx, NULL); + if (ctl->ops.setup_blendstage) + ctl->ops.setup_blendstage(ctl, hw_mixer[i]->idx, NULL); } } @@ -2250,7 +2239,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) dpu_enc = to_dpu_encoder_virt(phys_enc->parent); - phys_enc->hw_ctl->ops.reset(ctl); + ctl->ops.reset(ctl); dpu_encoder_helper_reset_mixers(phys_enc); @@ -2265,8 +2254,8 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) phys_enc->hw_wb->ops.bind_pingpong_blk(phys_enc->hw_wb, PINGPONG_NONE); /* mark WB flush as pending */ - if (phys_enc->hw_ctl->ops.update_pending_flush_wb) - phys_enc->hw_ctl->ops.update_pending_flush_wb(ctl, phys_enc->hw_wb->idx); + if (ctl->ops.update_pending_flush_wb) + ctl->ops.update_pending_flush_wb(ctl, phys_enc->hw_wb->idx); } else { for (i = 0; i < dpu_enc->num_phys_encs; i++) { if (dpu_enc->phys_encs[i] && phys_enc->hw_intf->ops.bind_pingpong_blk) @@ -2275,8 +2264,8 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) PINGPONG_NONE); /* mark INTF flush as pending */ - if (phys_enc->hw_ctl->ops.update_pending_flush_intf) - phys_enc->hw_ctl->ops.update_pending_flush_intf(phys_enc->hw_ctl, + if (ctl->ops.update_pending_flush_intf) + ctl->ops.update_pending_flush_intf(ctl, dpu_enc->phys_encs[i]->hw_intf->idx); } } @@ -2284,12 +2273,15 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) if (phys_enc->hw_pp && phys_enc->hw_pp->ops.setup_dither) phys_enc->hw_pp->ops.setup_dither(phys_enc->hw_pp, NULL); + if (dpu_enc->cwb_mask) + dpu_encoder_helper_phys_setup_cwb(phys_enc, false); + /* reset the merge 3D HW block */ if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) { phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d, BLEND_3D_NONE); - if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d) - phys_enc->hw_ctl->ops.update_pending_flush_merge_3d(ctl, + if (ctl->ops.update_pending_flush_merge_3d) + ctl->ops.update_pending_flush_merge_3d(ctl, phys_enc->hw_pp->merge_3d->idx); } @@ -2297,9 +2289,9 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) if (phys_enc->hw_cdm->ops.bind_pingpong_blk && phys_enc->hw_pp) phys_enc->hw_cdm->ops.bind_pingpong_blk(phys_enc->hw_cdm, PINGPONG_NONE); - if (phys_enc->hw_ctl->ops.update_pending_flush_cdm) - phys_enc->hw_ctl->ops.update_pending_flush_cdm(phys_enc->hw_ctl, - phys_enc->hw_cdm->idx); + if (ctl->ops.update_pending_flush_cdm) + ctl->ops.update_pending_flush_cdm(ctl, + phys_enc->hw_cdm->idx); } if (dpu_enc->dsc) { @@ -2310,6 +2302,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) intf_cfg.stream_sel = 0; /* Don't care value for video mode */ intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc); intf_cfg.dsc = dpu_encoder_helper_get_dsc(phys_enc); + intf_cfg.cwb = dpu_enc->cwb_mask; if (phys_enc->hw_intf) intf_cfg.intf = phys_enc->hw_intf->idx; @@ -2327,6 +2320,68 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) ctl->ops.clear_pending_flush(ctl); } +void dpu_encoder_helper_phys_setup_cwb(struct dpu_encoder_phys *phys_enc, + bool enable) +{ + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(phys_enc->parent); + struct dpu_hw_cwb *hw_cwb; + struct dpu_hw_ctl *hw_ctl; + struct dpu_hw_cwb_setup_cfg cwb_cfg; + + struct dpu_kms *dpu_kms; + struct dpu_global_state *global_state; + struct dpu_hw_blk *rt_pp_list[MAX_CHANNELS_PER_ENC]; + int num_pp; + + if (!phys_enc->hw_wb) + return; + + hw_ctl = phys_enc->hw_ctl; + + if (!phys_enc->hw_ctl) { + DPU_DEBUG("[wb:%d] no ctl assigned\n", + phys_enc->hw_wb->idx - WB_0); + return; + } + + dpu_kms = phys_enc->dpu_kms; + global_state = dpu_kms_get_existing_global_state(dpu_kms); + num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + phys_enc->parent->crtc, + DPU_HW_BLK_PINGPONG, rt_pp_list, + ARRAY_SIZE(rt_pp_list)); + + if (num_pp == 0 || num_pp > MAX_CHANNELS_PER_ENC) { + DPU_DEBUG_ENC(dpu_enc, "invalid num_pp %d\n", num_pp); + return; + } + + /* + * The CWB mux supports using LM or DSPP as tap points. For now, + * always use LM tap point + */ + cwb_cfg.input = INPUT_MODE_LM_OUT; + + for (int i = 0; i < MAX_CHANNELS_PER_ENC; i++) { + hw_cwb = dpu_enc->hw_cwb[i]; + if (!hw_cwb) + continue; + + if (enable) { + struct dpu_hw_pingpong *hw_pp = + to_dpu_hw_pingpong(rt_pp_list[i]); + cwb_cfg.pp_idx = hw_pp->idx; + } else { + cwb_cfg.pp_idx = PINGPONG_NONE; + } + + hw_cwb->ops.config_cwb(hw_cwb, &cwb_cfg); + + if (hw_ctl->ops.update_pending_flush_cwb) + hw_ctl->ops.update_pending_flush_cwb(hw_ctl, hw_cwb->idx); + } +} + /** * dpu_encoder_helper_phys_setup_cdm - setup chroma down sampling block * @phys_enc: Pointer to physical encoder @@ -2513,6 +2568,38 @@ static int dpu_encoder_virt_add_phys_encs( return 0; } +/** + * dpu_encoder_get_clones - Calculate the possible_clones for DPU encoder + * @drm_enc: DRM encoder pointer + * Returns: possible_clones mask + */ +uint32_t dpu_encoder_get_clones(struct drm_encoder *drm_enc) +{ + struct drm_encoder *curr; + int type = drm_enc->encoder_type; + uint32_t clone_mask = drm_encoder_mask(drm_enc); + + /* + * Set writeback as possible clones of real-time DSI encoders and vice + * versa + * + * Writeback encoders can't be clones of each other and DSI + * encoders can't be clones of each other. + * + * TODO: Add DP encoders as valid possible clones for writeback encoders + * (and vice versa) once concurrent writeback has been validated for DP + */ + drm_for_each_encoder(curr, drm_enc->dev) { + if ((type == DRM_MODE_ENCODER_VIRTUAL && + curr->encoder_type == DRM_MODE_ENCODER_DSI) || + (type == DRM_MODE_ENCODER_DSI && + curr->encoder_type == DRM_MODE_ENCODER_VIRTUAL)) + clone_mask |= drm_encoder_mask(curr); + } + + return clone_mask; +} + static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc, struct dpu_kms *dpu_kms, struct msm_display_info *disp_info) @@ -2630,7 +2717,6 @@ static const struct drm_encoder_helper_funcs dpu_encoder_helper_funcs = { .atomic_mode_set = dpu_encoder_virt_atomic_mode_set, .atomic_disable = dpu_encoder_virt_atomic_disable, .atomic_enable = dpu_encoder_virt_atomic_enable, - .atomic_check = dpu_encoder_virt_atomic_check, }; static const struct drm_encoder_funcs dpu_encoder_funcs = { @@ -2789,6 +2875,18 @@ enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder) } /** + * dpu_encoder_helper_get_cwb_mask - get CWB blocks mask for the DPU encoder + * @phys_enc: Pointer to physical encoder structure + */ +unsigned int dpu_encoder_helper_get_cwb_mask(struct dpu_encoder_phys *phys_enc) +{ + struct drm_encoder *encoder = phys_enc->parent; + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(encoder); + + return dpu_enc->cwb_mask; +} + +/** * dpu_encoder_helper_get_dsc - get DSC blocks mask for the DPU encoder * This helper function is used by physical encoder to get DSC blocks mask * used for this encoder. diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h index 92b5ee390788..ca1ca2e51d7e 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. * Copyright (C) 2013 Red Hat * Author: Rob Clark <robdclark@gmail.com> @@ -60,6 +60,8 @@ enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder); void dpu_encoder_virt_runtime_resume(struct drm_encoder *encoder); +uint32_t dpu_encoder_get_clones(struct drm_encoder *drm_enc); + struct drm_encoder *dpu_encoder_init(struct drm_device *dev, int drm_enc_mode, struct msm_display_info *disp_info); @@ -80,6 +82,13 @@ int dpu_encoder_get_crc(const struct drm_encoder *drm_enc, u32 *crcs, int pos); bool dpu_encoder_use_dsc_merge(struct drm_encoder *drm_enc); +void dpu_encoder_update_topology(struct drm_encoder *drm_enc, + struct msm_display_topology *topology, + struct drm_atomic_state *state, + const struct drm_display_mode *adj_mode); + +bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_state *state); + void dpu_encoder_prepare_wb_job(struct drm_encoder *drm_enc, struct drm_writeback_job *job); @@ -88,4 +97,5 @@ void dpu_encoder_cleanup_wb_job(struct drm_encoder *drm_enc, bool dpu_encoder_is_valid_for_commit(struct drm_encoder *drm_enc); +void dpu_encoder_start_frame_done_timer(struct drm_encoder *drm_enc); #endif /* __DPU_ENCODER_H__ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h index 63f09857025c..61b22d949454 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved. */ @@ -309,6 +309,8 @@ static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode( return BLEND_3D_NONE; } +unsigned int dpu_encoder_helper_get_cwb_mask(struct dpu_encoder_phys *phys_enc); + unsigned int dpu_encoder_helper_get_dsc(struct dpu_encoder_phys *phys_enc); struct drm_dsc_config *dpu_encoder_get_dsc_config(struct drm_encoder *drm_enc); @@ -331,6 +333,9 @@ int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc, void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc); +void dpu_encoder_helper_phys_setup_cwb(struct dpu_encoder_phys *phys_enc, + bool enable); + void dpu_encoder_helper_phys_setup_cdm(struct dpu_encoder_phys *phys_enc, const struct msm_format *dpu_fmt, u32 output_type); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c index e9bbccc44dad..da9994a79ca2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c @@ -5,6 +5,7 @@ #define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ #include <linux/delay.h> +#include <linux/string_choices.h> #include "dpu_encoder_phys.h" #include "dpu_hw_interrupts.h" #include "dpu_hw_pingpong.h" @@ -261,7 +262,7 @@ static int dpu_encoder_phys_cmd_control_vblank_irq( DRM_DEBUG_KMS("id:%u pp:%d enable=%s/%d\n", DRMID(phys_enc->parent), phys_enc->hw_pp->idx - PINGPONG_0, - enable ? "true" : "false", refcount); + str_true_false(enable), refcount); if (enable) { if (phys_enc->vblank_refcount == 0) @@ -285,7 +286,7 @@ end: DRM_ERROR("vblank irq err id:%u pp:%d ret:%d, enable %s/%d\n", DRMID(phys_enc->parent), phys_enc->hw_pp->idx - PINGPONG_0, ret, - enable ? "true" : "false", refcount); + str_true_false(enable), refcount); } return ret; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c index 4c006ec74575..849fea580a4c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ @@ -68,7 +68,7 @@ static void dpu_encoder_phys_wb_set_ot_limit( ot_params.num = hw_wb->idx - WB_0; ot_params.width = phys_enc->cached_mode.hdisplay; ot_params.height = phys_enc->cached_mode.vdisplay; - ot_params.is_wfd = true; + ot_params.is_wfd = !dpu_encoder_helper_get_cwb_mask(phys_enc); ot_params.frame_rate = drm_mode_vrefresh(&phys_enc->cached_mode); ot_params.vbif_idx = hw_wb->caps->vbif_idx; ot_params.rd = false; @@ -111,7 +111,7 @@ static void dpu_encoder_phys_wb_set_qos_remap( qos_params.vbif_idx = hw_wb->caps->vbif_idx; qos_params.xin_id = hw_wb->caps->xin_id; qos_params.num = hw_wb->idx - WB_0; - qos_params.is_rt = false; + qos_params.is_rt = dpu_encoder_helper_get_cwb_mask(phys_enc); DPU_DEBUG("[qos_remap] wb:%d vbif:%d xin:%d is_rt:%d\n", qos_params.num, @@ -174,6 +174,7 @@ static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc, struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc); struct dpu_hw_wb *hw_wb; struct dpu_hw_wb_cfg *wb_cfg; + u32 cdp_usage; if (!phys_enc || !phys_enc->dpu_kms || !phys_enc->dpu_kms->catalog) { DPU_ERROR("invalid encoder\n"); @@ -182,6 +183,10 @@ static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc, hw_wb = phys_enc->hw_wb; wb_cfg = &wb_enc->wb_cfg; + if (dpu_encoder_helper_get_cwb_mask(phys_enc)) + cdp_usage = DPU_PERF_CDP_USAGE_RT; + else + cdp_usage = DPU_PERF_CDP_USAGE_NRT; wb_cfg->intf_mode = phys_enc->intf_mode; wb_cfg->roi.x1 = 0; @@ -199,7 +204,7 @@ static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc, const struct dpu_perf_cfg *perf = phys_enc->dpu_kms->catalog->perf; hw_wb->ops.setup_cdp(hw_wb, format, - perf->cdp_cfg[DPU_PERF_CDP_USAGE_NRT].wr_enable); + perf->cdp_cfg[cdp_usage].wr_enable); } if (hw_wb->ops.setup_outaddress) @@ -236,6 +241,7 @@ static void dpu_encoder_phys_wb_setup_ctl(struct dpu_encoder_phys *phys_enc) intf_cfg.intf = DPU_NONE; intf_cfg.wb = hw_wb->idx; + intf_cfg.cwb = dpu_encoder_helper_get_cwb_mask(phys_enc); if (mode_3d && hw_pp && hw_pp->merge_3d) intf_cfg.merge_3d = hw_pp->merge_3d->idx; @@ -340,6 +346,8 @@ static void dpu_encoder_phys_wb_setup( dpu_encoder_helper_phys_setup_cdm(phys_enc, format, CDM_CDWN_OUTPUT_WB); + dpu_encoder_helper_phys_setup_cwb(phys_enc, true); + dpu_encoder_phys_wb_setup_ctl(phys_enc); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 0b342c043875..64265ca4656a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -232,37 +232,6 @@ static const u32 rotation_v2_formats[] = { /* TODO add formats after validation */ }; -static const u32 wb2_formats_rgb[] = { - DRM_FORMAT_RGB565, - DRM_FORMAT_BGR565, - DRM_FORMAT_RGB888, - DRM_FORMAT_ARGB8888, - DRM_FORMAT_RGBA8888, - DRM_FORMAT_ABGR8888, - DRM_FORMAT_XRGB8888, - DRM_FORMAT_RGBX8888, - DRM_FORMAT_XBGR8888, - DRM_FORMAT_ARGB1555, - DRM_FORMAT_RGBA5551, - DRM_FORMAT_XRGB1555, - DRM_FORMAT_RGBX5551, - DRM_FORMAT_ARGB4444, - DRM_FORMAT_RGBA4444, - DRM_FORMAT_RGBX4444, - DRM_FORMAT_XRGB4444, - DRM_FORMAT_BGR888, - DRM_FORMAT_BGRA8888, - DRM_FORMAT_BGRX8888, - DRM_FORMAT_ABGR1555, - DRM_FORMAT_BGRA5551, - DRM_FORMAT_XBGR1555, - DRM_FORMAT_BGRX5551, - DRM_FORMAT_ABGR4444, - DRM_FORMAT_BGRA4444, - DRM_FORMAT_BGRX4444, - DRM_FORMAT_XBGR4444, -}; - static const u32 wb2_formats_rgb_yuv[] = { DRM_FORMAT_RGB565, DRM_FORMAT_BGR565, @@ -507,7 +476,14 @@ static const struct dpu_dsc_sub_blks dsc_sblk_1 = { /************************************************************* * CDM block config *************************************************************/ -static const struct dpu_cdm_cfg sc7280_cdm = { +static const struct dpu_cdm_cfg dpu_cdm_1_x_4_x = { + .name = "cdm_0", + .id = CDM_0, + .len = 0x224, + .base = 0x79200, +}; + +static const struct dpu_cdm_cfg dpu_cdm_5_x = { .name = "cdm_0", .id = CDM_0, .len = 0x228, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c index ae1534c49ae0..3f88c3641d4a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c @@ -214,7 +214,9 @@ static void dpu_hw_cdm_bind_pingpong_blk(struct dpu_hw_cdm *ctx, const enum dpu_ mux_cfg = DPU_REG_READ(c, CDM_MUX); mux_cfg &= ~0xf; - if (pp) + if (pp >= PINGPONG_CWB_0) + mux_cfg |= 0xd; + else if (pp) mux_cfg |= (pp - PINGPONG_0) & 0x7; else mux_cfg |= 0xf; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c index 4893f10d6a58..411a7cf088eb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include <linux/delay.h> @@ -31,12 +31,14 @@ #define CTL_MERGE_3D_ACTIVE 0x0E4 #define CTL_DSC_ACTIVE 0x0E8 #define CTL_WB_ACTIVE 0x0EC +#define CTL_CWB_ACTIVE 0x0F0 #define CTL_INTF_ACTIVE 0x0F4 #define CTL_CDM_ACTIVE 0x0F8 #define CTL_FETCH_PIPE_ACTIVE 0x0FC #define CTL_MERGE_3D_FLUSH 0x100 #define CTL_DSC_FLUSH 0x104 #define CTL_WB_FLUSH 0x108 +#define CTL_CWB_FLUSH 0x10C #define CTL_INTF_FLUSH 0x110 #define CTL_CDM_FLUSH 0x114 #define CTL_PERIPH_FLUSH 0x128 @@ -53,6 +55,7 @@ #define PERIPH_IDX 30 #define INTF_IDX 31 #define WB_IDX 16 +#define CWB_IDX 28 #define DSPP_IDX 29 /* From DPU hw rev 7.x.x */ #define CTL_INVALID_BIT 0xffff #define CTL_DEFAULT_GROUP_ID 0xf @@ -110,6 +113,7 @@ static inline void dpu_hw_ctl_clear_pending_flush(struct dpu_hw_ctl *ctx) ctx->pending_flush_mask = 0x0; ctx->pending_intf_flush_mask = 0; ctx->pending_wb_flush_mask = 0; + ctx->pending_cwb_flush_mask = 0; ctx->pending_merge_3d_flush_mask = 0; ctx->pending_dsc_flush_mask = 0; ctx->pending_cdm_flush_mask = 0; @@ -144,6 +148,9 @@ static inline void dpu_hw_ctl_trigger_flush_v1(struct dpu_hw_ctl *ctx) if (ctx->pending_flush_mask & BIT(WB_IDX)) DPU_REG_WRITE(&ctx->hw, CTL_WB_FLUSH, ctx->pending_wb_flush_mask); + if (ctx->pending_flush_mask & BIT(CWB_IDX)) + DPU_REG_WRITE(&ctx->hw, CTL_CWB_FLUSH, + ctx->pending_cwb_flush_mask); if (ctx->pending_flush_mask & BIT(DSPP_IDX)) for (dspp = DSPP_0; dspp < DSPP_MAX; dspp++) { @@ -310,6 +317,13 @@ static void dpu_hw_ctl_update_pending_flush_wb_v1(struct dpu_hw_ctl *ctx, ctx->pending_flush_mask |= BIT(WB_IDX); } +static void dpu_hw_ctl_update_pending_flush_cwb_v1(struct dpu_hw_ctl *ctx, + enum dpu_cwb cwb) +{ + ctx->pending_cwb_flush_mask |= BIT(cwb - CWB_0); + ctx->pending_flush_mask |= BIT(CWB_IDX); +} + static void dpu_hw_ctl_update_pending_flush_intf_v1(struct dpu_hw_ctl *ctx, enum dpu_intf intf) { @@ -547,6 +561,7 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, u32 intf_active = 0; u32 dsc_active = 0; u32 wb_active = 0; + u32 cwb_active = 0; u32 mode_sel = 0; /* CTL_TOP[31:28] carries group_id to collate CTL paths @@ -561,6 +576,7 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, intf_active = DPU_REG_READ(c, CTL_INTF_ACTIVE); wb_active = DPU_REG_READ(c, CTL_WB_ACTIVE); + cwb_active = DPU_REG_READ(c, CTL_CWB_ACTIVE); dsc_active = DPU_REG_READ(c, CTL_DSC_ACTIVE); if (cfg->intf) @@ -569,12 +585,16 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, if (cfg->wb) wb_active |= BIT(cfg->wb - WB_0); + if (cfg->cwb) + cwb_active |= cfg->cwb; + if (cfg->dsc) dsc_active |= cfg->dsc; DPU_REG_WRITE(c, CTL_TOP, mode_sel); DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active); DPU_REG_WRITE(c, CTL_WB_ACTIVE, wb_active); + DPU_REG_WRITE(c, CTL_CWB_ACTIVE, cwb_active); DPU_REG_WRITE(c, CTL_DSC_ACTIVE, dsc_active); if (cfg->merge_3d) @@ -624,6 +644,7 @@ static void dpu_hw_ctl_reset_intf_cfg_v1(struct dpu_hw_ctl *ctx, struct dpu_hw_blk_reg_map *c = &ctx->hw; u32 intf_active = 0; u32 wb_active = 0; + u32 cwb_active = 0; u32 merge3d_active = 0; u32 dsc_active; u32 cdm_active; @@ -651,6 +672,12 @@ static void dpu_hw_ctl_reset_intf_cfg_v1(struct dpu_hw_ctl *ctx, DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active); } + if (cfg->cwb) { + cwb_active = DPU_REG_READ(c, CTL_CWB_ACTIVE); + cwb_active &= ~cfg->cwb; + DPU_REG_WRITE(c, CTL_CWB_ACTIVE, cwb_active); + } + if (cfg->wb) { wb_active = DPU_REG_READ(c, CTL_WB_ACTIVE); wb_active &= ~BIT(cfg->wb - WB_0); @@ -703,6 +730,7 @@ static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops, ops->update_pending_flush_merge_3d = dpu_hw_ctl_update_pending_flush_merge_3d_v1; ops->update_pending_flush_wb = dpu_hw_ctl_update_pending_flush_wb_v1; + ops->update_pending_flush_cwb = dpu_hw_ctl_update_pending_flush_cwb_v1; ops->update_pending_flush_dsc = dpu_hw_ctl_update_pending_flush_dsc_v1; ops->update_pending_flush_cdm = dpu_hw_ctl_update_pending_flush_cdm_v1; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h index 85c6c835cc87..080a9550a0cc 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #ifndef _DPU_HW_CTL_H @@ -42,6 +42,7 @@ struct dpu_hw_stage_cfg { * @cdm: CDM block used * @stream_sel: Stream selection for multi-stream interfaces * @dsc: DSC BIT masks used + * @cwb: CWB BIT masks used */ struct dpu_hw_intf_cfg { enum dpu_intf intf; @@ -51,6 +52,7 @@ struct dpu_hw_intf_cfg { enum dpu_ctl_mode_sel intf_mode_sel; enum dpu_cdm cdm; int stream_sel; + unsigned int cwb; unsigned int dsc; }; @@ -115,6 +117,15 @@ struct dpu_hw_ctl_ops { enum dpu_wb blk); /** + * OR in the given flushbits to the cached pending_(cwb_)flush_mask + * No effect on hardware + * @ctx : ctl path ctx pointer + * @blk : concurrent writeback block index + */ + void (*update_pending_flush_cwb)(struct dpu_hw_ctl *ctx, + enum dpu_cwb blk); + + /** * OR in the given flushbits to the cached pending_(intf_)flush_mask * No effect on hardware * @ctx : ctl path ctx pointer @@ -258,6 +269,7 @@ struct dpu_hw_ctl_ops { * @pending_flush_mask: storage for pending ctl_flush managed via ops * @pending_intf_flush_mask: pending INTF flush * @pending_wb_flush_mask: pending WB flush + * @pending_cwb_flush_mask: pending CWB flush * @pending_dsc_flush_mask: pending DSC flush * @pending_cdm_flush_mask: pending CDM flush * @ops: operation list @@ -274,6 +286,7 @@ struct dpu_hw_ctl { u32 pending_flush_mask; u32 pending_intf_flush_mask; u32 pending_wb_flush_mask; + u32 pending_cwb_flush_mask; u32 pending_periph_flush_mask; u32 pending_merge_3d_flush_mask; u32 pending_dspp_flush_mask[DSPP_MAX - DSPP_0]; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h index ba7bb05efe9b..8d820cd1b554 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h @@ -77,12 +77,14 @@ enum dpu_hw_blk_type { DPU_HW_BLK_LM, DPU_HW_BLK_CTL, DPU_HW_BLK_PINGPONG, + DPU_HW_BLK_DCWB_PINGPONG, DPU_HW_BLK_INTF, DPU_HW_BLK_WB, DPU_HW_BLK_DSPP, DPU_HW_BLK_MERGE_3D, DPU_HW_BLK_DSC, DPU_HW_BLK_CDM, + DPU_HW_BLK_CWB, DPU_HW_BLK_MAX, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 97e9cb8c2b09..3305ad0623ca 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2013 Red Hat * Copyright (c) 2014-2018, The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. * * Author: Rob Clark <robdclark@gmail.com> */ @@ -446,6 +446,19 @@ static void dpu_kms_disable_commit(struct msm_kms *kms) pm_runtime_put_sync(&dpu_kms->pdev->dev); } +static int dpu_kms_check_mode_changed(struct msm_kms *kms, struct drm_atomic_state *state) +{ + struct drm_crtc_state *new_crtc_state; + struct drm_crtc_state *old_crtc_state; + struct drm_crtc *crtc; + int i; + + for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) + dpu_crtc_check_mode_changed(old_crtc_state, new_crtc_state); + + return 0; +} + static void dpu_kms_flush_commit(struct msm_kms *kms, unsigned crtc_mask) { struct dpu_kms *dpu_kms = to_dpu_kms(kms); @@ -811,8 +824,11 @@ static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms) return ret; num_encoders = 0; - drm_for_each_encoder(encoder, dev) + drm_for_each_encoder(encoder, dev) { num_encoders++; + if (catalog->cwb_count > 0) + encoder->possible_clones = dpu_encoder_get_clones(encoder); + } max_crtc_count = min(catalog->mixer_count, num_encoders); @@ -1062,6 +1078,7 @@ static const struct msm_kms_funcs kms_funcs = { .irq = dpu_core_irq, .enable_commit = dpu_kms_enable_commit, .disable_commit = dpu_kms_disable_commit, + .check_mode_changed = dpu_kms_check_mode_changed, .flush_commit = dpu_kms_flush_commit, .wait_flush = dpu_kms_wait_flush, .complete_commit = dpu_kms_complete_commit, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index 547cdb2c0c78..a57ec2ec1060 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -124,14 +124,15 @@ struct dpu_global_state { struct dpu_rm *rm; - uint32_t pingpong_to_enc_id[PINGPONG_MAX - PINGPONG_0]; - uint32_t mixer_to_enc_id[LM_MAX - LM_0]; - uint32_t ctl_to_enc_id[CTL_MAX - CTL_0]; - uint32_t dspp_to_enc_id[DSPP_MAX - DSPP_0]; - uint32_t dsc_to_enc_id[DSC_MAX - DSC_0]; - uint32_t cdm_to_enc_id; + uint32_t pingpong_to_crtc_id[PINGPONG_MAX - PINGPONG_0]; + uint32_t mixer_to_crtc_id[LM_MAX - LM_0]; + uint32_t ctl_to_crtc_id[CTL_MAX - CTL_0]; + uint32_t dspp_to_crtc_id[DSPP_MAX - DSPP_0]; + uint32_t dsc_to_crtc_id[DSC_MAX - DSC_0]; + uint32_t cdm_to_crtc_id; uint32_t sspp_to_crtc_id[SSPP_MAX - SSPP_NONE]; + uint32_t cwb_to_crtc_id[CWB_MAX - CWB_0]; }; struct dpu_global_state diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index 5baf9df702b8..3efbba425ca6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -22,9 +22,9 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx, - uint32_t enc_id) + uint32_t crtc_id) { - return res_map[idx] && res_map[idx] != enc_id; + return res_map[idx] && res_map[idx] != crtc_id; } /** @@ -233,13 +233,66 @@ static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx) return -EINVAL; } +static int _dpu_rm_reserve_cwb_mux_and_pingpongs(struct dpu_rm *rm, + struct dpu_global_state *global_state, + uint32_t crtc_id, + struct msm_display_topology *topology) +{ + int num_cwb_mux = topology->num_lm, cwb_mux_count = 0; + int cwb_pp_start_idx = PINGPONG_CWB_0 - PINGPONG_0; + int cwb_pp_idx[MAX_BLOCKS]; + int cwb_mux_idx[MAX_BLOCKS]; + + /* + * Reserve additional dedicated CWB PINGPONG blocks and muxes for each + * mixer + * + * TODO: add support reserving resources for platforms with no + * PINGPONG_CWB + */ + for (int i = 0; i < ARRAY_SIZE(rm->mixer_blks) && + cwb_mux_count < num_cwb_mux; i++) { + for (int j = 0; j < ARRAY_SIZE(rm->cwb_blks); j++) { + /* + * Odd LMs must be assigned to odd CWB muxes and even + * LMs with even CWB muxes. + * + * Since the RM HW block array index is based on the HW + * block ids, we can also use the array index to enforce + * the odd/even rule. See dpu_rm_init() for more + * information + */ + if (reserved_by_other(global_state->cwb_to_crtc_id, j, crtc_id) || + i % 2 != j % 2) + continue; + + cwb_mux_idx[cwb_mux_count] = j; + cwb_pp_idx[cwb_mux_count] = j + cwb_pp_start_idx; + cwb_mux_count++; + break; + } + } + + if (cwb_mux_count != num_cwb_mux) { + DPU_ERROR("Unable to reserve all CWB PINGPONGs\n"); + return -ENAVAIL; + } + + for (int i = 0; i < cwb_mux_count; i++) { + global_state->pingpong_to_crtc_id[cwb_pp_idx[i]] = crtc_id; + global_state->cwb_to_crtc_id[cwb_mux_idx[i]] = crtc_id; + } + + return 0; +} + /** * _dpu_rm_check_lm_and_get_connected_blks - check if proposed layer mixer meets * proposed use case requirements, incl. hardwired dependent blocks like * pingpong * @rm: dpu resource manager handle * @global_state: resources shared across multiple kms objects - * @enc_id: encoder id requesting for allocation + * @crtc_id: crtc id requesting for allocation * @lm_idx: index of proposed layer mixer in rm->mixer_blks[], function checks * if lm, and all other hardwired blocks connected to the lm (pp) is * available and appropriate @@ -252,14 +305,14 @@ static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx) */ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, int lm_idx, int *pp_idx, int *dspp_idx, + uint32_t crtc_id, int lm_idx, int *pp_idx, int *dspp_idx, struct msm_display_topology *topology) { const struct dpu_lm_cfg *lm_cfg; int idx; /* Already reserved? */ - if (reserved_by_other(global_state->mixer_to_enc_id, lm_idx, enc_id)) { + if (reserved_by_other(global_state->mixer_to_crtc_id, lm_idx, crtc_id)) { DPU_DEBUG("lm %d already reserved\n", lm_idx + LM_0); return false; } @@ -271,7 +324,7 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, return false; } - if (reserved_by_other(global_state->pingpong_to_enc_id, idx, enc_id)) { + if (reserved_by_other(global_state->pingpong_to_crtc_id, idx, crtc_id)) { DPU_DEBUG("lm %d pp %d already reserved\n", lm_cfg->id, lm_cfg->pingpong); return false; @@ -287,7 +340,7 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, return false; } - if (reserved_by_other(global_state->dspp_to_enc_id, idx, enc_id)) { + if (reserved_by_other(global_state->dspp_to_crtc_id, idx, crtc_id)) { DPU_DEBUG("lm %d dspp %d already reserved\n", lm_cfg->id, lm_cfg->dspp); return false; @@ -299,7 +352,7 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, static int _dpu_rm_reserve_lms(struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, + uint32_t crtc_id, struct msm_display_topology *topology) { @@ -323,7 +376,7 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, lm_idx[lm_count] = i; if (!_dpu_rm_check_lm_and_get_connected_blks(rm, global_state, - enc_id, i, &pp_idx[lm_count], + crtc_id, i, &pp_idx[lm_count], &dspp_idx[lm_count], topology)) { continue; } @@ -342,7 +395,7 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, continue; if (!_dpu_rm_check_lm_and_get_connected_blks(rm, - global_state, enc_id, j, + global_state, crtc_id, j, &pp_idx[lm_count], &dspp_idx[lm_count], topology)) { continue; @@ -359,12 +412,12 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, } for (i = 0; i < lm_count; i++) { - global_state->mixer_to_enc_id[lm_idx[i]] = enc_id; - global_state->pingpong_to_enc_id[pp_idx[i]] = enc_id; - global_state->dspp_to_enc_id[dspp_idx[i]] = - topology->num_dspp ? enc_id : 0; + global_state->mixer_to_crtc_id[lm_idx[i]] = crtc_id; + global_state->pingpong_to_crtc_id[pp_idx[i]] = crtc_id; + global_state->dspp_to_crtc_id[dspp_idx[i]] = + topology->num_dspp ? crtc_id : 0; - trace_dpu_rm_reserve_lms(lm_idx[i] + LM_0, enc_id, + trace_dpu_rm_reserve_lms(lm_idx[i] + LM_0, crtc_id, pp_idx[i] + PINGPONG_0); } @@ -374,15 +427,25 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, static int _dpu_rm_reserve_ctls( struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, + uint32_t crtc_id, const struct msm_display_topology *top) { int ctl_idx[MAX_BLOCKS]; int i = 0, j, num_ctls; bool needs_split_display; - /* each hw_intf needs its own hw_ctrl to program its control path */ - num_ctls = top->num_intf; + /* + * For non-CWB mode, each hw_intf needs its own hw_ctl to program its + * control path. + * + * Hardcode num_ctls to 1 if CWB is enabled because in CWB, both the + * writeback and real-time encoders must be driven by the same control + * path + */ + if (top->cwb_enabled) + num_ctls = 1; + else + num_ctls = top->num_intf; needs_split_display = _dpu_rm_needs_split_display(top); @@ -393,7 +456,7 @@ static int _dpu_rm_reserve_ctls( if (!rm->ctl_blks[j]) continue; - if (reserved_by_other(global_state->ctl_to_enc_id, j, enc_id)) + if (reserved_by_other(global_state->ctl_to_crtc_id, j, crtc_id)) continue; ctl = to_dpu_hw_ctl(rm->ctl_blks[j]); @@ -417,8 +480,8 @@ static int _dpu_rm_reserve_ctls( return -ENAVAIL; for (i = 0; i < ARRAY_SIZE(ctl_idx) && i < num_ctls; i++) { - global_state->ctl_to_enc_id[ctl_idx[i]] = enc_id; - trace_dpu_rm_reserve_ctls(i + CTL_0, enc_id); + global_state->ctl_to_crtc_id[ctl_idx[i]] = crtc_id; + trace_dpu_rm_reserve_ctls(i + CTL_0, crtc_id); } return 0; @@ -426,12 +489,12 @@ static int _dpu_rm_reserve_ctls( static int _dpu_rm_pingpong_next_index(struct dpu_global_state *global_state, int start, - uint32_t enc_id) + uint32_t crtc_id) { int i; for (i = start; i < (PINGPONG_MAX - PINGPONG_0); i++) { - if (global_state->pingpong_to_enc_id[i] == enc_id) + if (global_state->pingpong_to_crtc_id[i] == crtc_id) return i; } @@ -452,7 +515,7 @@ static int _dpu_rm_pingpong_dsc_check(int dsc_idx, int pp_idx) static int _dpu_rm_dsc_alloc(struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, + uint32_t crtc_id, const struct msm_display_topology *top) { int num_dsc = 0; @@ -465,10 +528,10 @@ static int _dpu_rm_dsc_alloc(struct dpu_rm *rm, if (!rm->dsc_blks[dsc_idx]) continue; - if (reserved_by_other(global_state->dsc_to_enc_id, dsc_idx, enc_id)) + if (reserved_by_other(global_state->dsc_to_crtc_id, dsc_idx, crtc_id)) continue; - pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx, enc_id); + pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx, crtc_id); if (pp_idx < 0) return -ENAVAIL; @@ -476,7 +539,7 @@ static int _dpu_rm_dsc_alloc(struct dpu_rm *rm, if (ret) return -ENAVAIL; - global_state->dsc_to_enc_id[dsc_idx] = enc_id; + global_state->dsc_to_crtc_id[dsc_idx] = crtc_id; num_dsc++; pp_idx++; } @@ -492,7 +555,7 @@ static int _dpu_rm_dsc_alloc(struct dpu_rm *rm, static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, + uint32_t crtc_id, const struct msm_display_topology *top) { int num_dsc = 0; @@ -507,11 +570,11 @@ static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, continue; /* consective dsc index to be paired */ - if (reserved_by_other(global_state->dsc_to_enc_id, dsc_idx, enc_id) || - reserved_by_other(global_state->dsc_to_enc_id, dsc_idx + 1, enc_id)) + if (reserved_by_other(global_state->dsc_to_crtc_id, dsc_idx, crtc_id) || + reserved_by_other(global_state->dsc_to_crtc_id, dsc_idx + 1, crtc_id)) continue; - pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx, enc_id); + pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx, crtc_id); if (pp_idx < 0) return -ENAVAIL; @@ -521,7 +584,7 @@ static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, continue; } - pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx + 1, enc_id); + pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx + 1, crtc_id); if (pp_idx < 0) return -ENAVAIL; @@ -531,8 +594,8 @@ static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, continue; } - global_state->dsc_to_enc_id[dsc_idx] = enc_id; - global_state->dsc_to_enc_id[dsc_idx + 1] = enc_id; + global_state->dsc_to_crtc_id[dsc_idx] = crtc_id; + global_state->dsc_to_crtc_id[dsc_idx + 1] = crtc_id; num_dsc += 2; pp_idx++; /* start for next pair */ } @@ -548,11 +611,9 @@ static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, static int _dpu_rm_reserve_dsc(struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *enc, + uint32_t crtc_id, const struct msm_display_topology *top) { - uint32_t enc_id = enc->base.id; - if (!top->num_dsc || !top->num_intf) return 0; @@ -568,16 +629,17 @@ static int _dpu_rm_reserve_dsc(struct dpu_rm *rm, /* num_dsc should be either 1, 2 or 4 */ if (top->num_dsc > top->num_intf) /* merge mode */ - return _dpu_rm_dsc_alloc_pair(rm, global_state, enc_id, top); + return _dpu_rm_dsc_alloc_pair(rm, global_state, crtc_id, top); else - return _dpu_rm_dsc_alloc(rm, global_state, enc_id, top); + return _dpu_rm_dsc_alloc(rm, global_state, crtc_id, top); return 0; } static int _dpu_rm_reserve_cdm(struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *enc) + uint32_t crtc_id, + int num_cdm) { /* try allocating only one CDM block */ if (!rm->cdm_blk) { @@ -585,12 +647,17 @@ static int _dpu_rm_reserve_cdm(struct dpu_rm *rm, return -EIO; } - if (global_state->cdm_to_enc_id) { + if (num_cdm > 1) { + DPU_ERROR("More than 1 INTF requesting CDM\n"); + return -EINVAL; + } + + if (global_state->cdm_to_crtc_id) { DPU_ERROR("CDM_0 is already allocated\n"); return -EIO; } - global_state->cdm_to_enc_id = enc->base.id; + global_state->cdm_to_crtc_id = crtc_id; return 0; } @@ -598,30 +665,37 @@ static int _dpu_rm_reserve_cdm(struct dpu_rm *rm, static int _dpu_rm_make_reservation( struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *enc, + uint32_t crtc_id, struct msm_display_topology *topology) { int ret; - ret = _dpu_rm_reserve_lms(rm, global_state, enc->base.id, topology); + ret = _dpu_rm_reserve_lms(rm, global_state, crtc_id, topology); if (ret) { DPU_ERROR("unable to find appropriate mixers\n"); return ret; } - ret = _dpu_rm_reserve_ctls(rm, global_state, enc->base.id, + if (topology->cwb_enabled) { + ret = _dpu_rm_reserve_cwb_mux_and_pingpongs(rm, global_state, + crtc_id, topology); + if (ret) + return ret; + } + + ret = _dpu_rm_reserve_ctls(rm, global_state, crtc_id, topology); if (ret) { DPU_ERROR("unable to find appropriate CTL\n"); return ret; } - ret = _dpu_rm_reserve_dsc(rm, global_state, enc, topology); + ret = _dpu_rm_reserve_dsc(rm, global_state, crtc_id, topology); if (ret) return ret; - if (topology->needs_cdm) { - ret = _dpu_rm_reserve_cdm(rm, global_state, enc); + if (topology->num_cdm > 0) { + ret = _dpu_rm_reserve_cdm(rm, global_state, crtc_id, topology->num_cdm); if (ret) { DPU_ERROR("unable to find CDM blk\n"); return ret; @@ -632,12 +706,12 @@ static int _dpu_rm_make_reservation( } static void _dpu_rm_clear_mapping(uint32_t *res_mapping, int cnt, - uint32_t enc_id) + uint32_t crtc_id) { int i; for (i = 0; i < cnt; i++) { - if (res_mapping[i] == enc_id) + if (res_mapping[i] == crtc_id) res_mapping[i] = 0; } } @@ -646,23 +720,27 @@ static void _dpu_rm_clear_mapping(uint32_t *res_mapping, int cnt, * dpu_rm_release - Given the encoder for the display chain, release any * HW blocks previously reserved for that use case. * @global_state: resources shared across multiple kms objects - * @enc: DRM Encoder handle + * @crtc: DRM CRTC handle * @return: 0 on Success otherwise -ERROR */ void dpu_rm_release(struct dpu_global_state *global_state, - struct drm_encoder *enc) + struct drm_crtc *crtc) { - _dpu_rm_clear_mapping(global_state->pingpong_to_enc_id, - ARRAY_SIZE(global_state->pingpong_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(global_state->mixer_to_enc_id, - ARRAY_SIZE(global_state->mixer_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(global_state->ctl_to_enc_id, - ARRAY_SIZE(global_state->ctl_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(global_state->dsc_to_enc_id, - ARRAY_SIZE(global_state->dsc_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(global_state->dspp_to_enc_id, - ARRAY_SIZE(global_state->dspp_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(&global_state->cdm_to_enc_id, 1, enc->base.id); + uint32_t crtc_id = crtc->base.id; + + _dpu_rm_clear_mapping(global_state->pingpong_to_crtc_id, + ARRAY_SIZE(global_state->pingpong_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(global_state->mixer_to_crtc_id, + ARRAY_SIZE(global_state->mixer_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(global_state->ctl_to_crtc_id, + ARRAY_SIZE(global_state->ctl_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(global_state->dsc_to_crtc_id, + ARRAY_SIZE(global_state->dsc_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(global_state->dspp_to_crtc_id, + ARRAY_SIZE(global_state->dspp_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(&global_state->cdm_to_crtc_id, 1, crtc_id); + _dpu_rm_clear_mapping(global_state->cwb_to_crtc_id, + ARRAY_SIZE(global_state->cwb_to_crtc_id), crtc_id); } /** @@ -674,42 +752,33 @@ void dpu_rm_release(struct dpu_global_state *global_state, * HW Reservations should be released via dpu_rm_release_hw. * @rm: DPU Resource Manager handle * @global_state: resources shared across multiple kms objects - * @enc: DRM Encoder handle - * @crtc_state: Proposed Atomic DRM CRTC State handle + * @crtc: DRM CRTC handle * @topology: Pointer to topology info for the display * @return: 0 on Success otherwise -ERROR */ int dpu_rm_reserve( struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *enc, - struct drm_crtc_state *crtc_state, + struct drm_crtc *crtc, struct msm_display_topology *topology) { int ret; - /* Check if this is just a page-flip */ - if (!drm_atomic_crtc_needs_modeset(crtc_state)) - return 0; - if (IS_ERR(global_state)) { DPU_ERROR("failed to global state\n"); return PTR_ERR(global_state); } - DRM_DEBUG_KMS("reserving hw for enc %d crtc %d\n", - enc->base.id, crtc_state->crtc->base.id); + DRM_DEBUG_KMS("reserving hw for crtc %d\n", crtc->base.id); DRM_DEBUG_KMS("num_lm: %d num_dsc: %d num_intf: %d\n", topology->num_lm, topology->num_dsc, topology->num_intf); - ret = _dpu_rm_make_reservation(rm, global_state, enc, topology); + ret = _dpu_rm_make_reservation(rm, global_state, crtc->base.id, topology); if (ret) DPU_ERROR("failed to reserve hw resources: %d\n", ret); - - return ret; } @@ -800,50 +869,57 @@ void dpu_rm_release_all_sspp(struct dpu_global_state *global_state, * assigned to this encoder * @rm: DPU Resource Manager handle * @global_state: resources shared across multiple kms objects - * @enc_id: encoder id requesting for allocation + * @crtc: DRM CRTC handle * @type: resource type to return data for * @blks: pointer to the array to be filled by HW resources * @blks_size: size of the @blks array */ int dpu_rm_get_assigned_resources(struct dpu_rm *rm, - struct dpu_global_state *global_state, uint32_t enc_id, + struct dpu_global_state *global_state, struct drm_crtc *crtc, enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size) { + uint32_t crtc_id = crtc->base.id; struct dpu_hw_blk **hw_blks; - uint32_t *hw_to_enc_id; + uint32_t *hw_to_crtc_id; int i, num_blks, max_blks; switch (type) { case DPU_HW_BLK_PINGPONG: + case DPU_HW_BLK_DCWB_PINGPONG: hw_blks = rm->pingpong_blks; - hw_to_enc_id = global_state->pingpong_to_enc_id; + hw_to_crtc_id = global_state->pingpong_to_crtc_id; max_blks = ARRAY_SIZE(rm->pingpong_blks); break; case DPU_HW_BLK_LM: hw_blks = rm->mixer_blks; - hw_to_enc_id = global_state->mixer_to_enc_id; + hw_to_crtc_id = global_state->mixer_to_crtc_id; max_blks = ARRAY_SIZE(rm->mixer_blks); break; case DPU_HW_BLK_CTL: hw_blks = rm->ctl_blks; - hw_to_enc_id = global_state->ctl_to_enc_id; + hw_to_crtc_id = global_state->ctl_to_crtc_id; max_blks = ARRAY_SIZE(rm->ctl_blks); break; case DPU_HW_BLK_DSPP: hw_blks = rm->dspp_blks; - hw_to_enc_id = global_state->dspp_to_enc_id; + hw_to_crtc_id = global_state->dspp_to_crtc_id; max_blks = ARRAY_SIZE(rm->dspp_blks); break; case DPU_HW_BLK_DSC: hw_blks = rm->dsc_blks; - hw_to_enc_id = global_state->dsc_to_enc_id; + hw_to_crtc_id = global_state->dsc_to_crtc_id; max_blks = ARRAY_SIZE(rm->dsc_blks); break; case DPU_HW_BLK_CDM: hw_blks = &rm->cdm_blk; - hw_to_enc_id = &global_state->cdm_to_enc_id; + hw_to_crtc_id = &global_state->cdm_to_crtc_id; max_blks = 1; break; + case DPU_HW_BLK_CWB: + hw_blks = rm->cwb_blks; + hw_to_crtc_id = global_state->cwb_to_crtc_id; + max_blks = ARRAY_SIZE(rm->cwb_blks); + break; default: DPU_ERROR("blk type %d not managed by rm\n", type); return 0; @@ -851,17 +927,31 @@ int dpu_rm_get_assigned_resources(struct dpu_rm *rm, num_blks = 0; for (i = 0; i < max_blks; i++) { - if (hw_to_enc_id[i] != enc_id) + if (hw_to_crtc_id[i] != crtc_id) continue; + if (type == DPU_HW_BLK_PINGPONG) { + struct dpu_hw_pingpong *pp = to_dpu_hw_pingpong(hw_blks[i]); + + if (pp->idx >= PINGPONG_CWB_0) + continue; + } + + if (type == DPU_HW_BLK_DCWB_PINGPONG) { + struct dpu_hw_pingpong *pp = to_dpu_hw_pingpong(hw_blks[i]); + + if (pp->idx < PINGPONG_CWB_0) + continue; + } + if (num_blks == blks_size) { - DPU_ERROR("More than %d resources assigned to enc %d\n", - blks_size, enc_id); + DPU_ERROR("More than %d resources assigned to crtc %d\n", + blks_size, crtc_id); break; } if (!hw_blks[i]) { - DPU_ERROR("Allocated resource %d unavailable to assign to enc %d\n", - type, enc_id); + DPU_ERROR("Allocated resource %d unavailable to assign to crtc %d\n", + type, crtc_id); break; } blks[num_blks++] = hw_blks[i]; @@ -896,38 +986,38 @@ void dpu_rm_print_state(struct drm_printer *p, drm_puts(p, "resource mapping:\n"); drm_puts(p, "\tpingpong="); - for (i = 0; i < ARRAY_SIZE(global_state->pingpong_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->pingpong_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->pingpong_blks[i], - global_state->pingpong_to_enc_id[i]); + global_state->pingpong_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tmixer="); - for (i = 0; i < ARRAY_SIZE(global_state->mixer_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->mixer_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->mixer_blks[i], - global_state->mixer_to_enc_id[i]); + global_state->mixer_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tctl="); - for (i = 0; i < ARRAY_SIZE(global_state->ctl_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->ctl_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->ctl_blks[i], - global_state->ctl_to_enc_id[i]); + global_state->ctl_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tdspp="); - for (i = 0; i < ARRAY_SIZE(global_state->dspp_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->dspp_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->dspp_blks[i], - global_state->dspp_to_enc_id[i]); + global_state->dspp_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tdsc="); - for (i = 0; i < ARRAY_SIZE(global_state->dsc_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->dsc_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->dsc_blks[i], - global_state->dsc_to_enc_id[i]); + global_state->dsc_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tcdm="); dpu_rm_print_state_helper(p, rm->cdm_blk, - global_state->cdm_to_enc_id); + global_state->cdm_to_crtc_id); drm_puts(p, "\n"); drm_puts(p, "\tsspp="); @@ -936,4 +1026,10 @@ void dpu_rm_print_state(struct drm_printer *p, dpu_rm_print_state_helper(p, rm->hw_sspp[i] ? &rm->hw_sspp[i]->base : NULL, global_state->sspp_to_crtc_id[i]); drm_puts(p, "\n"); + + drm_puts(p, "\tcwb="); + for (i = 0; i < ARRAY_SIZE(global_state->cwb_to_crtc_id); i++) + dpu_rm_print_state_helper(p, rm->cwb_blks[i], + global_state->cwb_to_crtc_id[i]); + drm_puts(p, "\n"); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h index 99bd594ee0d1..a19dbdb1b6f4 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h @@ -51,14 +51,17 @@ struct dpu_rm_sspp_requirements { * @num_intf: number of interfaces the panel is mounted on * @num_dspp: number of dspp blocks used * @num_dsc: number of Display Stream Compression (DSC) blocks used - * @needs_cdm: indicates whether cdm block is needed for this display topology + * @num_cdm: indicates how many outputs are requesting cdm block for + * this display topology + * @cwb_enabled: indicates whether CWB is enabled for this display topology */ struct msm_display_topology { u32 num_lm; u32 num_intf; u32 num_dspp; u32 num_dsc; - bool needs_cdm; + int num_cdm; + bool cwb_enabled; }; int dpu_rm_init(struct drm_device *dev, @@ -69,12 +72,11 @@ int dpu_rm_init(struct drm_device *dev, int dpu_rm_reserve(struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *drm_enc, - struct drm_crtc_state *crtc_state, + struct drm_crtc *crtc, struct msm_display_topology *topology); void dpu_rm_release(struct dpu_global_state *global_state, - struct drm_encoder *enc); + struct drm_crtc *crtc); struct dpu_hw_sspp *dpu_rm_reserve_sspp(struct dpu_rm *rm, struct dpu_global_state *global_state, @@ -85,7 +87,7 @@ void dpu_rm_release_all_sspp(struct dpu_global_state *global_state, struct drm_crtc *crtc); int dpu_rm_get_assigned_resources(struct dpu_rm *rm, - struct dpu_global_state *global_state, uint32_t enc_id, + struct dpu_global_state *global_state, struct drm_crtc *crtc, enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size); void dpu_rm_print_state(struct drm_printer *p, diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c index 666de99a46a5..fc183fe37f56 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c @@ -3,6 +3,7 @@ * Copyright (c) 2014-2015 The Linux Foundation. All rights reserved. */ +#include <linux/string_choices.h> #include "mdp5_kms.h" #include "mdp5_ctl.h" @@ -233,7 +234,7 @@ int mdp5_ctl_set_encoder_state(struct mdp5_ctl *ctl, return -EINVAL; ctl->encoder_enabled = enabled; - DBG("intf_%d: %s", intf->num, enabled ? "on" : "off"); + DBG("intf_%d: %s", intf->num, str_on_off(enabled)); if (start_signal_needed(ctl, pipeline)) { send_start_signal(ctl); diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 9c463ae2f8fa..d8633a596f8d 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -11,6 +11,7 @@ #include <linux/phy/phy.h> #include <linux/phy/phy-dp.h> #include <linux/pm_opp.h> +#include <linux/string_choices.h> #include <drm/display/drm_dp_helper.h> #include <drm/drm_fixed.h> @@ -1366,9 +1367,9 @@ int msm_dp_ctrl_core_clk_enable(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "enable core clocks \n"); drm_dbg_dp(ctrl->drm_dev, "stream_clks:%s link_clks:%s core_clks:%s\n", - ctrl->stream_clks_on ? "on" : "off", - ctrl->link_clks_on ? "on" : "off", - ctrl->core_clks_on ? "on" : "off"); + str_on_off(ctrl->stream_clks_on), + str_on_off(ctrl->link_clks_on), + str_on_off(ctrl->core_clks_on)); return 0; } @@ -1385,9 +1386,9 @@ void msm_dp_ctrl_core_clk_disable(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "disable core clocks \n"); drm_dbg_dp(ctrl->drm_dev, "stream_clks:%s link_clks:%s core_clks:%s\n", - ctrl->stream_clks_on ? "on" : "off", - ctrl->link_clks_on ? "on" : "off", - ctrl->core_clks_on ? "on" : "off"); + str_on_off(ctrl->stream_clks_on), + str_on_off(ctrl->link_clks_on), + str_on_off(ctrl->core_clks_on)); } static int msm_dp_ctrl_link_clk_enable(struct msm_dp_ctrl *msm_dp_ctrl) @@ -1416,9 +1417,9 @@ static int msm_dp_ctrl_link_clk_enable(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "enable link clocks\n"); drm_dbg_dp(ctrl->drm_dev, "stream_clks:%s link_clks:%s core_clks:%s\n", - ctrl->stream_clks_on ? "on" : "off", - ctrl->link_clks_on ? "on" : "off", - ctrl->core_clks_on ? "on" : "off"); + str_on_off(ctrl->stream_clks_on), + str_on_off(ctrl->link_clks_on), + str_on_off(ctrl->core_clks_on)); return 0; } @@ -1435,9 +1436,9 @@ static void msm_dp_ctrl_link_clk_disable(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "disabled link clocks\n"); drm_dbg_dp(ctrl->drm_dev, "stream_clks:%s link_clks:%s core_clks:%s\n", - ctrl->stream_clks_on ? "on" : "off", - ctrl->link_clks_on ? "on" : "off", - ctrl->core_clks_on ? "on" : "off"); + str_on_off(ctrl->stream_clks_on), + str_on_off(ctrl->link_clks_on), + str_on_off(ctrl->core_clks_on)); } static int msm_dp_ctrl_enable_mainlink_clocks(struct msm_dp_ctrl_private *ctrl) diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 9aa8bbd73d86..bbc47d86ae9e 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -11,6 +11,7 @@ #include <linux/of_irq.h> #include <linux/phy/phy.h> #include <linux/delay.h> +#include <linux/string_choices.h> #include <drm/display/drm_dp_aux_bus.h> #include <drm/drm_edid.h> @@ -343,8 +344,7 @@ static int msm_dp_display_send_hpd_notification(struct msm_dp_display_private *d { if ((hpd && dp->msm_dp_display.link_ready) || (!hpd && !dp->msm_dp_display.link_ready)) { - drm_dbg_dp(dp->drm_dev, "HPD already %s\n", - (hpd ? "on" : "off")); + drm_dbg_dp(dp->drm_dev, "HPD already %s\n", str_on_off(hpd)); return 0; } diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c index 022b3e815cf3..cca57e56c906 100644 --- a/drivers/gpu/drm/msm/dp/dp_drm.c +++ b/drivers/gpu/drm/msm/dp/dp_drm.c @@ -3,6 +3,7 @@ * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. */ +#include <linux/string_choices.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_atomic.h> #include <drm/drm_bridge.h> @@ -25,7 +26,7 @@ static enum drm_connector_status msm_dp_bridge_detect(struct drm_bridge *bridge) dp = to_dp_bridge(bridge)->msm_dp_display; drm_dbg_dp(dp->drm_dev, "link_ready = %s\n", - (dp->link_ready) ? "true" : "false"); + str_true_false(dp->link_ready)); return (dp->link_ready) ? connector_status_connected : connector_status_disconnected; @@ -41,7 +42,7 @@ static int msm_dp_bridge_atomic_check(struct drm_bridge *bridge, dp = to_dp_bridge(bridge)->msm_dp_display; drm_dbg_dp(dp->drm_dev, "link_ready = %s\n", - (dp->link_ready) ? "true" : "false"); + str_true_false(dp->link_ready)); /* * There is no protection in the DRM framework to check if the display diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 007311c21fda..4d75529c0e85 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -179,18 +179,18 @@ struct msm_dsi_host { int irq; }; - static inline u32 dsi_read(struct msm_dsi_host *msm_host, u32 reg) { return readl(msm_host->ctrl_base + reg); } + static inline void dsi_write(struct msm_dsi_host *msm_host, u32 reg, u32 data) { writel(data, msm_host->ctrl_base + reg); } -static const struct msm_dsi_cfg_handler *dsi_get_config( - struct msm_dsi_host *msm_host) +static const struct msm_dsi_cfg_handler * +dsi_get_config(struct msm_dsi_host *msm_host) { const struct msm_dsi_cfg_handler *cfg_hnd = NULL; struct device *dev = &msm_host->pdev->dev; @@ -200,7 +200,8 @@ static const struct msm_dsi_cfg_handler *dsi_get_config( ahb_clk = msm_clk_get(msm_host->pdev, "iface"); if (IS_ERR(ahb_clk)) { - pr_err("%s: cannot get interface clock\n", __func__); + dev_err_probe(dev, PTR_ERR(ahb_clk), "%s: cannot get interface clock\n", + __func__); goto exit; } @@ -208,13 +209,13 @@ static const struct msm_dsi_cfg_handler *dsi_get_config( ret = clk_prepare_enable(ahb_clk); if (ret) { - pr_err("%s: unable to enable ahb_clk\n", __func__); + dev_err_probe(dev, ret, "%s: unable to enable ahb_clk\n", __func__); goto runtime_put; } ret = dsi_get_version(msm_host->ctrl_base, &major, &minor); if (ret) { - pr_err("%s: Invalid version\n", __func__); + dev_err_probe(dev, ret, "%s: Invalid version\n", __func__); goto disable_clks; } @@ -281,42 +282,31 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host) msm_host->num_bus_clks = cfg->num_bus_clks; ret = devm_clk_bulk_get(&pdev->dev, msm_host->num_bus_clks, msm_host->bus_clks); - if (ret < 0) { - dev_err(&pdev->dev, "Unable to get clocks, ret = %d\n", ret); - goto exit; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, "Unable to get clocks\n"); /* get link and source clocks */ msm_host->byte_clk = msm_clk_get(pdev, "byte"); - if (IS_ERR(msm_host->byte_clk)) { - ret = PTR_ERR(msm_host->byte_clk); - pr_err("%s: can't find dsi_byte clock. ret=%d\n", - __func__, ret); - msm_host->byte_clk = NULL; - goto exit; - } + if (IS_ERR(msm_host->byte_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(msm_host->byte_clk), + "%s: can't find dsi_byte clock\n", + __func__); msm_host->pixel_clk = msm_clk_get(pdev, "pixel"); - if (IS_ERR(msm_host->pixel_clk)) { - ret = PTR_ERR(msm_host->pixel_clk); - pr_err("%s: can't find dsi_pixel clock. ret=%d\n", - __func__, ret); - msm_host->pixel_clk = NULL; - goto exit; - } + if (IS_ERR(msm_host->pixel_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(msm_host->pixel_clk), + "%s: can't find dsi_pixel clock\n", + __func__); msm_host->esc_clk = msm_clk_get(pdev, "core"); - if (IS_ERR(msm_host->esc_clk)) { - ret = PTR_ERR(msm_host->esc_clk); - pr_err("%s: can't find dsi_esc clock. ret=%d\n", - __func__, ret); - msm_host->esc_clk = NULL; - goto exit; - } + if (IS_ERR(msm_host->esc_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(msm_host->esc_clk), + "%s: can't find dsi_esc clock\n", + __func__); if (cfg_hnd->ops->clk_init_ver) ret = cfg_hnd->ops->clk_init_ver(msm_host); -exit: + return ret; } @@ -380,7 +370,6 @@ int dsi_link_clk_set_rate_6g(struct msm_dsi_host *msm_host) return 0; } - int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host) { int ret; @@ -598,7 +587,6 @@ static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_bonded_dsi) DBG("pclk=%lu, bclk=%lu", msm_host->pixel_clk_rate, msm_host->byte_clk_rate); - } int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_bonded_dsi) @@ -687,8 +675,8 @@ static inline enum dsi_traffic_mode dsi_get_traffic_mode(const u32 mode_flags) return NON_BURST_SYNCH_EVENT; } -static inline enum dsi_vid_dst_format dsi_get_vid_fmt( - const enum mipi_dsi_pixel_format mipi_fmt) +static inline enum dsi_vid_dst_format +dsi_get_vid_fmt(const enum mipi_dsi_pixel_format mipi_fmt) { switch (mipi_fmt) { case MIPI_DSI_FMT_RGB888: return VID_DST_FORMAT_RGB888; @@ -699,8 +687,8 @@ static inline enum dsi_vid_dst_format dsi_get_vid_fmt( } } -static inline enum dsi_cmd_dst_format dsi_get_cmd_fmt( - const enum mipi_dsi_pixel_format mipi_fmt) +static inline enum dsi_cmd_dst_format +dsi_get_cmd_fmt(const enum mipi_dsi_pixel_format mipi_fmt) { switch (mipi_fmt) { case MIPI_DSI_FMT_RGB888: return CMD_DST_FORMAT_RGB888; @@ -846,7 +834,7 @@ static void dsi_ctrl_enable(struct msm_dsi_host *msm_host, dsi_write(msm_host, REG_DSI_CPHY_MODE_CTRL, BIT(0)); } -static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mode, u32 hdisplay) +static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mode) { struct drm_dsc_config *dsc = msm_host->dsc; u32 reg, reg_ctrl, reg_ctrl2; @@ -858,7 +846,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod /* first calculate dsc parameters and then program * compress mode registers */ - slice_per_intf = msm_dsc_get_slices_per_intf(dsc, hdisplay); + slice_per_intf = dsc->slice_count; total_bytes_per_intf = dsc->slice_chunk_size * slice_per_intf; bytes_per_pkt = dsc->slice_chunk_size; /* * slice_per_pkt; */ @@ -991,7 +979,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) if (msm_host->mode_flags & MIPI_DSI_MODE_VIDEO) { if (msm_host->dsc) - dsi_update_dsc_timing(msm_host, false, mode->hdisplay); + dsi_update_dsc_timing(msm_host, false); dsi_write(msm_host, REG_DSI_ACTIVE_H, DSI_ACTIVE_H_START(ha_start) | @@ -1012,7 +1000,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) DSI_ACTIVE_VSYNC_VPOS_END(vs_end)); } else { /* command mode */ if (msm_host->dsc) - dsi_update_dsc_timing(msm_host, true, mode->hdisplay); + dsi_update_dsc_timing(msm_host, true); /* image data and 1 byte write_memory_start cmd */ if (!msm_host->dsc) @@ -1292,14 +1280,15 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host, static int dsi_short_read1_resp(u8 *buf, const struct mipi_dsi_msg *msg) { u8 *data = msg->rx_buf; + if (data && (msg->rx_len >= 1)) { *data = buf[1]; /* strip out dcs type */ return 1; - } else { - pr_err("%s: read data does not match with rx_buf len %zu\n", - __func__, msg->rx_len); - return -EINVAL; } + + pr_err("%s: read data does not match with rx_buf len %zu\n", + __func__, msg->rx_len); + return -EINVAL; } /* @@ -1308,15 +1297,16 @@ static int dsi_short_read1_resp(u8 *buf, const struct mipi_dsi_msg *msg) static int dsi_short_read2_resp(u8 *buf, const struct mipi_dsi_msg *msg) { u8 *data = msg->rx_buf; + if (data && (msg->rx_len >= 2)) { data[0] = buf[1]; /* strip out dcs type */ data[1] = buf[2]; return 2; - } else { - pr_err("%s: read data does not match with rx_buf len %zu\n", - __func__, msg->rx_len); - return -EINVAL; } + + pr_err("%s: read data does not match with rx_buf len %zu\n", + __func__, msg->rx_len); + return -EINVAL; } static int dsi_long_read_resp(u8 *buf, const struct mipi_dsi_msg *msg) @@ -1376,8 +1366,9 @@ static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len) ret = -ETIMEDOUT; else ret = len; - } else + } else { ret = len; + } return ret; } @@ -1445,11 +1436,12 @@ static int dsi_cmds2buf_tx(struct msm_dsi_host *msm_host, return len; } - /* for video mode, do not send cmds more than - * one pixel line, since it only transmit it - * during BLLP. - */ - /* TODO: if the command is sent in LP mode, the bit rate is only + /* + * for video mode, do not send cmds more than + * one pixel line, since it only transmit it + * during BLLP. + * + * TODO: if the command is sent in LP mode, the bit rate is only * half of esc clk rate. In this case, if the video is already * actively streaming, we need to check more carefully if the * command can be fit into one BLLP. @@ -1767,8 +1759,20 @@ static int dsi_populate_dsc_params(struct msm_dsi_host *msm_host, struct drm_dsc return -EINVAL; } - if (dsc->bits_per_component != 8) { - DRM_DEV_ERROR(&msm_host->pdev->dev, "DSI does not support bits_per_component != 8 yet\n"); + switch (dsc->bits_per_component) { + case 8: + case 10: + case 12: + /* + * Only 8, 10, and 12 bpc are supported for DSC 1.1 block. + * If additional bpc values need to be supported, update + * this quard with the appropriate DSC version verification. + */ + break; + default: + DRM_DEV_ERROR(&msm_host->pdev->dev, + "Unsupported bits_per_component value: %d\n", + dsc->bits_per_component); return -EOPNOTSUPP; } @@ -1779,7 +1783,7 @@ static int dsi_populate_dsc_params(struct msm_dsi_host *msm_host, struct drm_dsc drm_dsc_set_const_params(dsc); drm_dsc_set_rc_buf_thresh(dsc); - /* handle only bpp = bpc = 8, pre-SCR panels */ + /* DPU supports only pre-SCR panels */ ret = drm_dsc_setup_rc_params(dsc, DRM_DSC_1_1_PRE_SCR); if (ret) { DRM_DEV_ERROR(&msm_host->pdev->dev, "could not find DSC RC parameters\n"); @@ -1827,8 +1831,15 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host) __func__, ret); goto err; } - if (!ret) + if (!ret) { msm_dsi->te_source = devm_kstrdup(dev, te_source, GFP_KERNEL); + if (!msm_dsi->te_source) { + DRM_DEV_ERROR(dev, "%s: failed to allocate te_source\n", + __func__); + ret = -ENOMEM; + goto err; + } + } ret = 0; if (of_property_present(np, "syscon-sfpb")) { @@ -1874,39 +1885,35 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) int ret; msm_host = devm_kzalloc(&pdev->dev, sizeof(*msm_host), GFP_KERNEL); - if (!msm_host) { + if (!msm_host) return -ENOMEM; - } msm_host->pdev = pdev; msm_dsi->host = &msm_host->base; ret = dsi_host_parse_dt(msm_host); - if (ret) { - pr_err("%s: failed to parse dt\n", __func__); - return ret; - } + if (ret) + return dev_err_probe(&pdev->dev, ret, "%s: failed to parse dt\n", + __func__); msm_host->ctrl_base = msm_ioremap_size(pdev, "dsi_ctrl", &msm_host->ctrl_size); - if (IS_ERR(msm_host->ctrl_base)) { - pr_err("%s: unable to map Dsi ctrl base\n", __func__); - return PTR_ERR(msm_host->ctrl_base); - } + if (IS_ERR(msm_host->ctrl_base)) + return dev_err_probe(&pdev->dev, PTR_ERR(msm_host->ctrl_base), + "%s: unable to map Dsi ctrl base\n", __func__); pm_runtime_enable(&pdev->dev); msm_host->cfg_hnd = dsi_get_config(msm_host); - if (!msm_host->cfg_hnd) { - pr_err("%s: get config failed\n", __func__); - return -EINVAL; - } + if (!msm_host->cfg_hnd) + return dev_err_probe(&pdev->dev, -EINVAL, + "%s: get config failed\n", __func__); cfg = msm_host->cfg_hnd->cfg; msm_host->id = dsi_host_get_id(msm_host); - if (msm_host->id < 0) { - pr_err("%s: unable to identify DSI host index\n", __func__); - return msm_host->id; - } + if (msm_host->id < 0) + return dev_err_probe(&pdev->dev, msm_host->id, + "%s: unable to identify DSI host index\n", + __func__); /* fixup base address by io offset */ msm_host->ctrl_base += cfg->io_offset; @@ -1918,42 +1925,32 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) return ret; ret = dsi_clk_init(msm_host); - if (ret) { - pr_err("%s: unable to initialize dsi clks\n", __func__); - return ret; - } + if (ret) + return dev_err_probe(&pdev->dev, ret, "%s: unable to initialize dsi clks\n", __func__); msm_host->rx_buf = devm_kzalloc(&pdev->dev, SZ_4K, GFP_KERNEL); - if (!msm_host->rx_buf) { - pr_err("%s: alloc rx temp buf failed\n", __func__); + if (!msm_host->rx_buf) return -ENOMEM; - } ret = devm_pm_opp_set_clkname(&pdev->dev, "byte"); if (ret) return ret; /* OPP table is optional */ ret = devm_pm_opp_of_add_table(&pdev->dev); - if (ret && ret != -ENODEV) { - dev_err(&pdev->dev, "invalid OPP table in device tree\n"); - return ret; - } + if (ret && ret != -ENODEV) + return dev_err_probe(&pdev->dev, ret, "invalid OPP table in device tree\n"); msm_host->irq = irq_of_parse_and_map(pdev->dev.of_node, 0); - if (!msm_host->irq) { - dev_err(&pdev->dev, "failed to get irq\n"); - return -EINVAL; - } + if (!msm_host->irq) + return dev_err_probe(&pdev->dev, -EINVAL, "failed to get irq\n"); /* do not autoenable, will be enabled later */ ret = devm_request_irq(&pdev->dev, msm_host->irq, dsi_host_irq, IRQF_TRIGGER_HIGH | IRQF_NO_AUTOEN, "dsi_isr", msm_host); - if (ret < 0) { - dev_err(&pdev->dev, "failed to request IRQ%u: %d\n", - msm_host->irq, ret); - return ret; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, "failed to request IRQ%u\n", + msm_host->irq); init_completion(&msm_host->dma_comp); init_completion(&msm_host->video_comp); diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index a210b7c9e5ca..4fabb01345aa 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -74,17 +74,35 @@ static int dsi_mgr_setup_components(int id) int ret; if (!IS_BONDED_DSI()) { + /* + * Set the usecase before calling msm_dsi_host_register(), which would + * already program the PLL source mux based on a default usecase. + */ + msm_dsi_phy_set_usecase(msm_dsi->phy, MSM_DSI_PHY_STANDALONE); + msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy); + ret = msm_dsi_host_register(msm_dsi->host); if (ret) return ret; - - msm_dsi_phy_set_usecase(msm_dsi->phy, MSM_DSI_PHY_STANDALONE); - msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy); } else if (other_dsi) { struct msm_dsi *master_link_dsi = IS_MASTER_DSI_LINK(id) ? msm_dsi : other_dsi; struct msm_dsi *slave_link_dsi = IS_MASTER_DSI_LINK(id) ? other_dsi : msm_dsi; + + /* + * PLL0 is to drive both DSI link clocks in bonded DSI mode. + * + * Set the usecase before calling msm_dsi_host_register(), which would + * already program the PLL source mux based on a default usecase. + */ + msm_dsi_phy_set_usecase(clk_master_dsi->phy, + MSM_DSI_PHY_MASTER); + msm_dsi_phy_set_usecase(clk_slave_dsi->phy, + MSM_DSI_PHY_SLAVE); + msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy); + msm_dsi_host_set_phy_mode(other_dsi->host, other_dsi->phy); + /* Register slave host first, so that slave DSI device * has a chance to probe, and do not block the master * DSI device's probe. @@ -98,14 +116,6 @@ static int dsi_mgr_setup_components(int id) ret = msm_dsi_host_register(master_link_dsi->host); if (ret) return ret; - - /* PLL0 is to drive both 2 DSI link clocks in bonded DSI mode. */ - msm_dsi_phy_set_usecase(clk_master_dsi->phy, - MSM_DSI_PHY_MASTER); - msm_dsi_phy_set_usecase(clk_slave_dsi->phy, - MSM_DSI_PHY_SLAVE); - msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy); - msm_dsi_host_set_phy_mode(other_dsi->host, other_dsi->phy); } return 0; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index 8985818bb2e0..1925418d9999 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -6,6 +6,7 @@ #ifndef __DSI_PHY_H__ #define __DSI_PHY_H__ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk-provider.h> #include <linux/delay.h> #include <linux/regulator/consumer.h> @@ -84,9 +85,7 @@ struct msm_dsi_dphy_timing { u8 hs_halfbyte_en_ckln; }; -#define DSI_BYTE_PLL_CLK 0 -#define DSI_PIXEL_PLL_CLK 1 -#define NUM_PROVIDED_CLKS 2 +#define NUM_PROVIDED_CLKS (DSI_PIXEL_PLL_CLK + 1) #define DSI_LANE_MAX 5 diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c index 677c62571811..9812b4d69197 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c @@ -3,6 +3,7 @@ * Copyright (c) 2018, The Linux Foundation */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/iopoll.h> diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c index 2c3cbe0f2870..3a1c8ece6657 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c @@ -3,6 +3,7 @@ * Copyright (c) 2016, The Linux Foundation. All rights reserved. */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/delay.h> diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c index 1383e3a4e050..90348a2af3e9 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c @@ -3,6 +3,7 @@ * Copyright (c) 2015, The Linux Foundation. All rights reserved. */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk.h> #include <linux/clk-provider.h> diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c index 5311ab7f3c70..f3643320ff2f 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c @@ -3,6 +3,7 @@ * Copyright (c) 2012-2015, The Linux Foundation. All rights reserved. */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk-provider.h> #include <linux/delay.h> diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index 798168180c1a..a92decbee5b5 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -3,6 +3,8 @@ * Copyright (c) 2018, The Linux Foundation */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/iopoll.h> @@ -305,7 +307,7 @@ static void dsi_pll_commit(struct dsi_pll_7nm *pll, struct dsi_pll_config *confi writel(pll->phy->cphy_mode ? 0x00 : 0x10, base + REG_DSI_7nm_PHY_PLL_CMODE_1); writel(config->pll_clock_inverters, - base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS); + base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS_1); } static int dsi_pll_7nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, @@ -572,11 +574,11 @@ static void dsi_7nm_pll_save_state(struct msm_dsi_phy *phy) cached->pll_out_div &= 0x3; cmn_clk_cfg0 = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0); - cached->bit_clk_div = cmn_clk_cfg0 & 0xf; - cached->pix_clk_div = (cmn_clk_cfg0 & 0xf0) >> 4; + cached->bit_clk_div = FIELD_GET(DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_3_0__MASK, cmn_clk_cfg0); + cached->pix_clk_div = FIELD_GET(DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_7_4__MASK, cmn_clk_cfg0); cmn_clk_cfg1 = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - cached->pll_mux = cmn_clk_cfg1 & 0x3; + cached->pll_mux = FIELD_GET(DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL__MASK, cmn_clk_cfg1); DBG("DSI PLL%d outdiv %x bit_clk_div %x pix_clk_div %x pll_mux %x", pll_7nm->phy->id, cached->pll_out_div, cached->bit_clk_div, @@ -598,7 +600,8 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy) dsi_pll_cmn_clk_cfg0_write(pll_7nm, DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_3_0(cached->bit_clk_div) | DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_7_4(cached->pix_clk_div)); - dsi_pll_cmn_clk_cfg1_update(pll_7nm, 0x3, cached->pll_mux); + dsi_pll_cmn_clk_cfg1_update(pll_7nm, DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL__MASK, + cached->pll_mux); ret = dsi_pll_7nm_vco_set_rate(phy->vco_hw, pll_7nm->vco_current_rate, @@ -736,11 +739,9 @@ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provide * don't register a pclk_mux clock and just use post_out_div instead */ if (pll_7nm->phy->cphy_mode) { - u32 data; - - data = readl(pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - writel(data | 3, pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - + dsi_pll_cmn_clk_cfg1_update(pll_7nm, + DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL__MASK, + DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL(3)); phy_pll_out_dsi_parent = pll_post_out_div; } else { snprintf(clk_name, sizeof(clk_name), "dsi%d_pclk_mux", pll_7nm->phy->id); diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 37b3809c6bdd..248541ff4492 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -12,8 +12,8 @@ #include <drm/drm_bridge_connector.h> #include <drm/drm_of.h> +#include <drm/display/drm_hdmi_state_helper.h> -#include <sound/hdmi-codec.h> #include "hdmi.h" void msm_hdmi_set_mode(struct hdmi *hdmi, bool power_on) @@ -24,7 +24,7 @@ void msm_hdmi_set_mode(struct hdmi *hdmi, bool power_on) spin_lock_irqsave(&hdmi->reg_lock, flags); if (power_on) { ctrl |= HDMI_CTRL_ENABLE; - if (!hdmi->hdmi_mode) { + if (!hdmi->connector->display_info.is_hdmi) { ctrl |= HDMI_CTRL_HDMI; hdmi_write(hdmi, REG_HDMI_CTRL, ctrl); ctrl &= ~HDMI_CTRL_HDMI; @@ -165,8 +165,6 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, hdmi->dev = dev; hdmi->encoder = encoder; - hdmi_audio_infoframe_init(&hdmi->audio.infoframe); - ret = msm_hdmi_bridge_init(hdmi); if (ret) { DRM_DEV_ERROR(dev->dev, "failed to create HDMI bridge: %d\n", ret); @@ -246,111 +244,6 @@ static const struct hdmi_platform_config hdmi_tx_8974_config = { .hpd_freq = hpd_clk_freq_8x74, }; -/* - * HDMI audio codec callbacks - */ -static int msm_hdmi_audio_hw_params(struct device *dev, void *data, - struct hdmi_codec_daifmt *daifmt, - struct hdmi_codec_params *params) -{ - struct hdmi *hdmi = dev_get_drvdata(dev); - unsigned int chan; - unsigned int channel_allocation = 0; - unsigned int rate; - unsigned int level_shift = 0; /* 0dB */ - bool down_mix = false; - - DRM_DEV_DEBUG(dev, "%u Hz, %d bit, %d channels\n", params->sample_rate, - params->sample_width, params->cea.channels); - - switch (params->cea.channels) { - case 2: - /* FR and FL speakers */ - channel_allocation = 0; - chan = MSM_HDMI_AUDIO_CHANNEL_2; - break; - case 4: - /* FC, LFE, FR and FL speakers */ - channel_allocation = 0x3; - chan = MSM_HDMI_AUDIO_CHANNEL_4; - break; - case 6: - /* RR, RL, FC, LFE, FR and FL speakers */ - channel_allocation = 0x0B; - chan = MSM_HDMI_AUDIO_CHANNEL_6; - break; - case 8: - /* FRC, FLC, RR, RL, FC, LFE, FR and FL speakers */ - channel_allocation = 0x1F; - chan = MSM_HDMI_AUDIO_CHANNEL_8; - break; - default: - return -EINVAL; - } - - switch (params->sample_rate) { - case 32000: - rate = HDMI_SAMPLE_RATE_32KHZ; - break; - case 44100: - rate = HDMI_SAMPLE_RATE_44_1KHZ; - break; - case 48000: - rate = HDMI_SAMPLE_RATE_48KHZ; - break; - case 88200: - rate = HDMI_SAMPLE_RATE_88_2KHZ; - break; - case 96000: - rate = HDMI_SAMPLE_RATE_96KHZ; - break; - case 176400: - rate = HDMI_SAMPLE_RATE_176_4KHZ; - break; - case 192000: - rate = HDMI_SAMPLE_RATE_192KHZ; - break; - default: - DRM_DEV_ERROR(dev, "rate[%d] not supported!\n", - params->sample_rate); - return -EINVAL; - } - - msm_hdmi_audio_set_sample_rate(hdmi, rate); - msm_hdmi_audio_info_setup(hdmi, 1, chan, channel_allocation, - level_shift, down_mix); - - return 0; -} - -static void msm_hdmi_audio_shutdown(struct device *dev, void *data) -{ - struct hdmi *hdmi = dev_get_drvdata(dev); - - msm_hdmi_audio_info_setup(hdmi, 0, 0, 0, 0, 0); -} - -static const struct hdmi_codec_ops msm_hdmi_audio_codec_ops = { - .hw_params = msm_hdmi_audio_hw_params, - .audio_shutdown = msm_hdmi_audio_shutdown, -}; - -static struct hdmi_codec_pdata codec_data = { - .ops = &msm_hdmi_audio_codec_ops, - .max_i2s_channels = 8, - .i2s = 1, -}; - -static int msm_hdmi_register_audio_driver(struct hdmi *hdmi, struct device *dev) -{ - hdmi->audio_pdev = platform_device_register_data(dev, - HDMI_CODEC_DRV_NAME, - PLATFORM_DEVID_AUTO, - &codec_data, - sizeof(codec_data)); - return PTR_ERR_OR_ZERO(hdmi->audio_pdev); -} - static int msm_hdmi_bind(struct device *dev, struct device *master, void *data) { struct msm_drm_private *priv = dev_get_drvdata(master); @@ -362,12 +255,6 @@ static int msm_hdmi_bind(struct device *dev, struct device *master, void *data) return err; priv->hdmi = hdmi; - err = msm_hdmi_register_audio_driver(hdmi, dev); - if (err) { - DRM_ERROR("Failed to attach an audio codec %d\n", err); - hdmi->audio_pdev = NULL; - } - return 0; } @@ -377,9 +264,6 @@ static void msm_hdmi_unbind(struct device *dev, struct device *master, struct msm_drm_private *priv = dev_get_drvdata(master); if (priv->hdmi) { - if (priv->hdmi->audio_pdev) - platform_device_unregister(priv->hdmi->audio_pdev); - if (priv->hdmi->bridge) msm_hdmi_hpd_disable(priv->hdmi); diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h index a62d2aedfbb7..a5f481c39277 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.h +++ b/drivers/gpu/drm/msm/hdmi/hdmi.h @@ -24,8 +24,8 @@ struct hdmi_platform_config; struct hdmi_audio { bool enabled; - struct hdmi_audio_infoframe infoframe; int rate; + int channels; }; struct hdmi_hdcp_ctrl; @@ -33,7 +33,6 @@ struct hdmi_hdcp_ctrl; struct hdmi { struct drm_device *dev; struct platform_device *pdev; - struct platform_device *audio_pdev; const struct hdmi_platform_config *config; @@ -67,8 +66,6 @@ struct hdmi { /* the encoder we are hooked to (outside of hdmi block) */ struct drm_encoder *encoder; - bool hdmi_mode; /* are we in hdmi mode? */ - int irq; struct workqueue_struct *workq; @@ -207,26 +204,16 @@ static inline int msm_hdmi_pll_8998_init(struct platform_device *pdev) /* * audio: */ -/* Supported HDMI Audio channels and rates */ -#define MSM_HDMI_AUDIO_CHANNEL_2 0 -#define MSM_HDMI_AUDIO_CHANNEL_4 1 -#define MSM_HDMI_AUDIO_CHANNEL_6 2 -#define MSM_HDMI_AUDIO_CHANNEL_8 3 - -#define HDMI_SAMPLE_RATE_32KHZ 0 -#define HDMI_SAMPLE_RATE_44_1KHZ 1 -#define HDMI_SAMPLE_RATE_48KHZ 2 -#define HDMI_SAMPLE_RATE_88_2KHZ 3 -#define HDMI_SAMPLE_RATE_96KHZ 4 -#define HDMI_SAMPLE_RATE_176_4KHZ 5 -#define HDMI_SAMPLE_RATE_192KHZ 6 +struct hdmi_codec_daifmt; +struct hdmi_codec_params; int msm_hdmi_audio_update(struct hdmi *hdmi); -int msm_hdmi_audio_info_setup(struct hdmi *hdmi, bool enabled, - uint32_t num_of_channels, uint32_t channel_allocation, - uint32_t level_shift, bool down_mix); -void msm_hdmi_audio_set_sample_rate(struct hdmi *hdmi, int rate); - +int msm_hdmi_bridge_audio_prepare(struct drm_connector *connector, + struct drm_bridge *bridge, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params); +void msm_hdmi_bridge_audio_shutdown(struct drm_connector *connector, + struct drm_bridge *bridge); /* * hdmi bridge: diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_audio.c b/drivers/gpu/drm/msm/hdmi/hdmi_audio.c index 4c2058c4adc1..8bb975e82c17 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_audio.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_audio.c @@ -4,11 +4,13 @@ * Author: Rob Clark <robdclark@gmail.com> */ +#include <drm/display/drm_hdmi_state_helper.h> + #include <linux/hdmi.h> -#include "hdmi.h" -/* maps MSM_HDMI_AUDIO_CHANNEL_n consts used by audio driver to # of channels: */ -static int nchannels[] = { 2, 4, 6, 8 }; +#include <sound/hdmi-codec.h> + +#include "hdmi.h" /* Supported HDMI Audio sample rates */ #define MSM_HDMI_SAMPLE_RATE_32KHZ 0 @@ -74,16 +76,17 @@ static const struct hdmi_msm_audio_arcs *get_arcs(unsigned long int pixclock) int msm_hdmi_audio_update(struct hdmi *hdmi) { struct hdmi_audio *audio = &hdmi->audio; - struct hdmi_audio_infoframe *info = &audio->infoframe; const struct hdmi_msm_audio_arcs *arcs = NULL; bool enabled = audio->enabled; uint32_t acr_pkt_ctrl, vbi_pkt_ctrl, aud_pkt_ctrl; - uint32_t infofrm_ctrl, audio_config; + uint32_t audio_config; + + if (!hdmi->connector->display_info.is_hdmi) + return -EINVAL; + + DBG("audio: enabled=%d, channels=%d, rate=%d", + audio->enabled, audio->channels, audio->rate); - DBG("audio: enabled=%d, channels=%d, channel_allocation=0x%x, " - "level_shift_value=%d, downmix_inhibit=%d, rate=%d", - audio->enabled, info->channels, info->channel_allocation, - info->level_shift_value, info->downmix_inhibit, audio->rate); DBG("video: power_on=%d, pixclock=%lu", hdmi->power_on, hdmi->pixclock); if (enabled && !(hdmi->power_on && hdmi->pixclock)) { @@ -104,7 +107,6 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) acr_pkt_ctrl = hdmi_read(hdmi, REG_HDMI_ACR_PKT_CTRL); vbi_pkt_ctrl = hdmi_read(hdmi, REG_HDMI_VBI_PKT_CTRL); aud_pkt_ctrl = hdmi_read(hdmi, REG_HDMI_AUDIO_PKT_CTRL1); - infofrm_ctrl = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); audio_config = hdmi_read(hdmi, REG_HDMI_AUDIO_CFG); /* Clear N/CTS selection bits */ @@ -113,7 +115,6 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) if (enabled) { uint32_t n, cts, multiplier; enum hdmi_acr_cts select; - uint8_t buf[14]; n = arcs->lut[audio->rate].n; cts = arcs->lut[audio->rate].cts; @@ -155,20 +156,12 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) HDMI_ACR_1_N(n)); hdmi_write(hdmi, REG_HDMI_AUDIO_PKT_CTRL2, - COND(info->channels != 2, HDMI_AUDIO_PKT_CTRL2_LAYOUT) | + COND(audio->channels != 2, HDMI_AUDIO_PKT_CTRL2_LAYOUT) | HDMI_AUDIO_PKT_CTRL2_OVERRIDE); acr_pkt_ctrl |= HDMI_ACR_PKT_CTRL_CONT; acr_pkt_ctrl |= HDMI_ACR_PKT_CTRL_SEND; - /* configure infoframe: */ - hdmi_audio_infoframe_pack(info, buf, sizeof(buf)); - hdmi_write(hdmi, REG_HDMI_AUDIO_INFO0, - (buf[3] << 0) | (buf[4] << 8) | - (buf[5] << 16) | (buf[6] << 24)); - hdmi_write(hdmi, REG_HDMI_AUDIO_INFO1, - (buf[7] << 0) | (buf[8] << 8)); - hdmi_write(hdmi, REG_HDMI_GC, 0); vbi_pkt_ctrl |= HDMI_VBI_PKT_CTRL_GC_ENABLE; @@ -176,11 +169,6 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) aud_pkt_ctrl |= HDMI_AUDIO_PKT_CTRL1_AUDIO_SAMPLE_SEND; - infofrm_ctrl |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND; - infofrm_ctrl |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT; - infofrm_ctrl |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE; - infofrm_ctrl |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE; - audio_config &= ~HDMI_AUDIO_CFG_FIFO_WATERMARK__MASK; audio_config |= HDMI_AUDIO_CFG_FIFO_WATERMARK(4); audio_config |= HDMI_AUDIO_CFG_ENGINE_ENABLE; @@ -190,17 +178,12 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) vbi_pkt_ctrl &= ~HDMI_VBI_PKT_CTRL_GC_ENABLE; vbi_pkt_ctrl &= ~HDMI_VBI_PKT_CTRL_GC_EVERY_FRAME; aud_pkt_ctrl &= ~HDMI_AUDIO_PKT_CTRL1_AUDIO_SAMPLE_SEND; - infofrm_ctrl &= ~HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND; - infofrm_ctrl &= ~HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT; - infofrm_ctrl &= ~HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE; - infofrm_ctrl &= ~HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE; audio_config &= ~HDMI_AUDIO_CFG_ENGINE_ENABLE; } hdmi_write(hdmi, REG_HDMI_ACR_PKT_CTRL, acr_pkt_ctrl); hdmi_write(hdmi, REG_HDMI_VBI_PKT_CTRL, vbi_pkt_ctrl); hdmi_write(hdmi, REG_HDMI_AUDIO_PKT_CTRL1, aud_pkt_ctrl); - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, infofrm_ctrl); hdmi_write(hdmi, REG_HDMI_AUD_INT, COND(enabled, HDMI_AUD_INT_AUD_FIFO_URUN_INT) | @@ -214,41 +197,72 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) return 0; } -int msm_hdmi_audio_info_setup(struct hdmi *hdmi, bool enabled, - uint32_t num_of_channels, uint32_t channel_allocation, - uint32_t level_shift, bool down_mix) +int msm_hdmi_bridge_audio_prepare(struct drm_connector *connector, + struct drm_bridge *bridge, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params) { - struct hdmi_audio *audio; - - if (!hdmi) - return -ENXIO; - - audio = &hdmi->audio; - - if (num_of_channels >= ARRAY_SIZE(nchannels)) + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; + unsigned int rate; + int ret; + + drm_dbg_driver(bridge->dev, "%u Hz, %d bit, %d channels\n", + params->sample_rate, + params->sample_width, + params->cea.channels); + + switch (params->sample_rate) { + case 32000: + rate = MSM_HDMI_SAMPLE_RATE_32KHZ; + break; + case 44100: + rate = MSM_HDMI_SAMPLE_RATE_44_1KHZ; + break; + case 48000: + rate = MSM_HDMI_SAMPLE_RATE_48KHZ; + break; + case 88200: + rate = MSM_HDMI_SAMPLE_RATE_88_2KHZ; + break; + case 96000: + rate = MSM_HDMI_SAMPLE_RATE_96KHZ; + break; + case 176400: + rate = MSM_HDMI_SAMPLE_RATE_176_4KHZ; + break; + case 192000: + rate = MSM_HDMI_SAMPLE_RATE_192KHZ; + break; + default: + drm_err(bridge->dev, "rate[%d] not supported!\n", + params->sample_rate); return -EINVAL; + } + + ret = drm_atomic_helper_connector_hdmi_update_audio_infoframe(connector, + ¶ms->cea); + if (ret) + return ret; - audio->enabled = enabled; - audio->infoframe.channels = nchannels[num_of_channels]; - audio->infoframe.channel_allocation = channel_allocation; - audio->infoframe.level_shift_value = level_shift; - audio->infoframe.downmix_inhibit = down_mix; + hdmi->audio.rate = rate; + hdmi->audio.channels = params->cea.channels; + hdmi->audio.enabled = true; return msm_hdmi_audio_update(hdmi); } -void msm_hdmi_audio_set_sample_rate(struct hdmi *hdmi, int rate) +void msm_hdmi_bridge_audio_shutdown(struct drm_connector *connector, + struct drm_bridge *bridge) { - struct hdmi_audio *audio; - - if (!hdmi) - return; + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; - audio = &hdmi->audio; + drm_atomic_helper_connector_hdmi_clear_audio_infoframe(connector); - if ((rate < 0) || (rate >= MSM_HDMI_SAMPLE_RATE_MAX)) - return; + hdmi->audio.rate = 0; + hdmi->audio.channels = 2; + hdmi->audio.enabled = false; - audio->rate = rate; msm_hdmi_audio_update(hdmi); } diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c index 4a5b5112227f..1456354c8af4 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c @@ -7,6 +7,8 @@ #include <linux/delay.h> #include <drm/drm_bridge_connector.h> #include <drm/drm_edid.h> +#include <drm/display/drm_hdmi_helper.h> +#include <drm/display/drm_hdmi_state_helper.h> #include "msm_kms.h" #include "hdmi.h" @@ -67,24 +69,20 @@ static void power_off(struct drm_bridge *bridge) } #define AVI_IFRAME_LINE_NUMBER 1 +#define SPD_IFRAME_LINE_NUMBER 1 +#define VENSPEC_IFRAME_LINE_NUMBER 3 -static void msm_hdmi_config_avi_infoframe(struct hdmi *hdmi) +static int msm_hdmi_config_avi_infoframe(struct hdmi *hdmi, + const u8 *buffer, size_t len) { - struct drm_crtc *crtc = hdmi->encoder->crtc; - const struct drm_display_mode *mode = &crtc->state->adjusted_mode; - union hdmi_infoframe frame; - u8 buffer[HDMI_INFOFRAME_SIZE(AVI)]; + u32 buf[4] = {}; u32 val; - int len; + int i; - drm_hdmi_avi_infoframe_from_display_mode(&frame.avi, - hdmi->connector, mode); - - len = hdmi_infoframe_pack(&frame, buffer, sizeof(buffer)); - if (len < 0) { + if (len != HDMI_INFOFRAME_SIZE(AVI) || len - 3 > sizeof(buf)) { DRM_DEV_ERROR(&hdmi->pdev->dev, "failed to configure avi infoframe\n"); - return; + return -EINVAL; } /* @@ -93,57 +91,245 @@ static void msm_hdmi_config_avi_infoframe(struct hdmi *hdmi) * written to the LSB byte of AVI_INFO0 and the version is written to * the third byte from the LSB of AVI_INFO3 */ - hdmi_write(hdmi, REG_HDMI_AVI_INFO(0), + memcpy(buf, &buffer[3], len - 3); + + buf[3] |= buffer[1] << 24; + + for (i = 0; i < ARRAY_SIZE(buf); i++) + hdmi_write(hdmi, REG_HDMI_AVI_INFO(i), buf[i]); + + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val |= HDMI_INFOFRAME_CTRL0_AVI_SEND | + HDMI_INFOFRAME_CTRL0_AVI_CONT; + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val &= ~HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK; + val |= HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE(AVI_IFRAME_LINE_NUMBER); + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + + return 0; +} + +static int msm_hdmi_config_audio_infoframe(struct hdmi *hdmi, + const u8 *buffer, size_t len) +{ + u32 val; + + if (len != HDMI_INFOFRAME_SIZE(AUDIO)) { + DRM_DEV_ERROR(&hdmi->pdev->dev, + "failed to configure audio infoframe\n"); + return -EINVAL; + } + + hdmi_write(hdmi, REG_HDMI_AUDIO_INFO0, buffer[3] | buffer[4] << 8 | buffer[5] << 16 | buffer[6] << 24); - hdmi_write(hdmi, REG_HDMI_AVI_INFO(1), + hdmi_write(hdmi, REG_HDMI_AUDIO_INFO1, buffer[7] | buffer[8] << 8 | buffer[9] << 16 | buffer[10] << 24); - hdmi_write(hdmi, REG_HDMI_AVI_INFO(2), - buffer[11] | - buffer[12] << 8 | - buffer[13] << 16 | - buffer[14] << 24); + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE; + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); - hdmi_write(hdmi, REG_HDMI_AVI_INFO(3), - buffer[15] | - buffer[16] << 8 | - buffer[1] << 24); + return 0; +} - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, - HDMI_INFOFRAME_CTRL0_AVI_SEND | - HDMI_INFOFRAME_CTRL0_AVI_CONT); +static int msm_hdmi_config_spd_infoframe(struct hdmi *hdmi, + const u8 *buffer, size_t len) +{ + u32 buf[7] = {}; + u32 val; + int i; - val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); - val &= ~HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK; - val |= HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE(AVI_IFRAME_LINE_NUMBER); - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + if (len != HDMI_INFOFRAME_SIZE(SPD) || len - 3 > sizeof(buf)) { + DRM_DEV_ERROR(&hdmi->pdev->dev, + "failed to configure SPD infoframe\n"); + return -EINVAL; + } + + /* checksum gets written together with the body of the frame */ + hdmi_write(hdmi, REG_HDMI_GENERIC1_HDR, + buffer[0] | + buffer[1] << 8 | + buffer[2] << 16); + + memcpy(buf, &buffer[3], len - 3); + + for (i = 0; i < ARRAY_SIZE(buf); i++) + hdmi_write(hdmi, REG_HDMI_GENERIC1(i), buf[i]); + + val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); + val |= HDMI_GEN_PKT_CTRL_GENERIC1_SEND | + HDMI_GEN_PKT_CTRL_GENERIC1_CONT | + HDMI_GEN_PKT_CTRL_GENERIC1_LINE(SPD_IFRAME_LINE_NUMBER); + hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + + return 0; } -static void msm_hdmi_bridge_pre_enable(struct drm_bridge *bridge) +static int msm_hdmi_config_hdmi_infoframe(struct hdmi *hdmi, + const u8 *buffer, size_t len) +{ + u32 buf[7] = {}; + u32 val; + int i; + + if (len < HDMI_INFOFRAME_HEADER_SIZE + HDMI_VENDOR_INFOFRAME_SIZE || + len - 3 > sizeof(buf)) { + DRM_DEV_ERROR(&hdmi->pdev->dev, + "failed to configure HDMI infoframe\n"); + return -EINVAL; + } + + /* checksum gets written together with the body of the frame */ + hdmi_write(hdmi, REG_HDMI_GENERIC0_HDR, + buffer[0] | + buffer[1] << 8 | + buffer[2] << 16); + + memcpy(buf, &buffer[3], len - 3); + + for (i = 0; i < ARRAY_SIZE(buf); i++) + hdmi_write(hdmi, REG_HDMI_GENERIC0(i), buf[i]); + + val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); + val |= HDMI_GEN_PKT_CTRL_GENERIC0_SEND | + HDMI_GEN_PKT_CTRL_GENERIC0_CONT | + HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE | + HDMI_GEN_PKT_CTRL_GENERIC0_LINE(VENSPEC_IFRAME_LINE_NUMBER); + hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + + return 0; +} + +static int msm_hdmi_bridge_clear_infoframe(struct drm_bridge *bridge, + enum hdmi_infoframe_type type) +{ + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; + u32 val; + + switch (type) { + case HDMI_INFOFRAME_TYPE_AVI: + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); + val &= ~(HDMI_INFOFRAME_CTRL0_AVI_SEND | + HDMI_INFOFRAME_CTRL0_AVI_CONT); + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val &= ~HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK; + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + + break; + + case HDMI_INFOFRAME_TYPE_AUDIO: + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); + val &= ~(HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE); + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val &= ~HDMI_INFOFRAME_CTRL1_AUDIO_INFO_LINE__MASK; + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + + break; + + case HDMI_INFOFRAME_TYPE_SPD: + val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); + val &= ~(HDMI_GEN_PKT_CTRL_GENERIC1_SEND | + HDMI_GEN_PKT_CTRL_GENERIC1_CONT | + HDMI_GEN_PKT_CTRL_GENERIC1_LINE__MASK); + hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + + break; + + case HDMI_INFOFRAME_TYPE_VENDOR: + val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); + val &= ~(HDMI_GEN_PKT_CTRL_GENERIC0_SEND | + HDMI_GEN_PKT_CTRL_GENERIC0_CONT | + HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE | + HDMI_GEN_PKT_CTRL_GENERIC0_LINE__MASK); + hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + + break; + + default: + drm_dbg_driver(hdmi_bridge->base.dev, "Unsupported infoframe type %x\n", type); + } + + return 0; +} + +static int msm_hdmi_bridge_write_infoframe(struct drm_bridge *bridge, + enum hdmi_infoframe_type type, + const u8 *buffer, size_t len) +{ + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; + + msm_hdmi_bridge_clear_infoframe(bridge, type); + + switch (type) { + case HDMI_INFOFRAME_TYPE_AVI: + return msm_hdmi_config_avi_infoframe(hdmi, buffer, len); + case HDMI_INFOFRAME_TYPE_AUDIO: + return msm_hdmi_config_audio_infoframe(hdmi, buffer, len); + case HDMI_INFOFRAME_TYPE_SPD: + return msm_hdmi_config_spd_infoframe(hdmi, buffer, len); + case HDMI_INFOFRAME_TYPE_VENDOR: + return msm_hdmi_config_hdmi_infoframe(hdmi, buffer, len); + default: + drm_dbg_driver(hdmi_bridge->base.dev, "Unsupported infoframe type %x\n", type); + return 0; + } +} + +static void msm_hdmi_set_timings(struct hdmi *hdmi, + const struct drm_display_mode *mode); + +static void msm_hdmi_bridge_atomic_pre_enable(struct drm_bridge *bridge, + struct drm_atomic_state *state) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; struct hdmi_phy *phy = hdmi->phy; + struct drm_encoder *encoder = bridge->encoder; + struct drm_connector *connector; + struct drm_connector_state *conn_state; + struct drm_crtc_state *crtc_state; DBG("power up"); + connector = drm_atomic_get_new_connector_for_encoder(state, encoder); + conn_state = drm_atomic_get_new_connector_state(state, connector); + crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc); + + hdmi->pixclock = conn_state->hdmi.tmds_char_rate; + + msm_hdmi_set_timings(hdmi, &crtc_state->adjusted_mode); + if (!hdmi->power_on) { msm_hdmi_phy_resource_enable(phy); msm_hdmi_power_on(bridge); hdmi->power_on = true; - if (hdmi->hdmi_mode) { - msm_hdmi_config_avi_infoframe(hdmi); + if (connector->display_info.is_hdmi) msm_hdmi_audio_update(hdmi); - } } + drm_atomic_helper_connector_hdmi_update_infoframes(connector, state); + msm_hdmi_phy_powerup(phy, hdmi->pixclock); msm_hdmi_set_mode(hdmi, true); @@ -152,7 +338,8 @@ static void msm_hdmi_bridge_pre_enable(struct drm_bridge *bridge) msm_hdmi_hdcp_on(hdmi->hdcp_ctrl); } -static void msm_hdmi_bridge_post_disable(struct drm_bridge *bridge) +static void msm_hdmi_bridge_atomic_post_disable(struct drm_bridge *bridge, + struct drm_atomic_state *state) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; @@ -169,25 +356,18 @@ static void msm_hdmi_bridge_post_disable(struct drm_bridge *bridge) if (hdmi->power_on) { power_off(bridge); hdmi->power_on = false; - if (hdmi->hdmi_mode) + if (hdmi->connector->display_info.is_hdmi) msm_hdmi_audio_update(hdmi); msm_hdmi_phy_resource_disable(phy); } } -static void msm_hdmi_bridge_mode_set(struct drm_bridge *bridge, - const struct drm_display_mode *mode, - const struct drm_display_mode *adjusted_mode) +static void msm_hdmi_set_timings(struct hdmi *hdmi, + const struct drm_display_mode *mode) { - struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); - struct hdmi *hdmi = hdmi_bridge->hdmi; int hstart, hend, vstart, vend; uint32_t frame_ctrl; - mode = adjusted_mode; - - hdmi->pixclock = mode->clock * 1000; - hstart = mode->htotal - mode->hsync_start; hend = mode->htotal - mode->hsync_start + mode->hdisplay; @@ -232,7 +412,7 @@ static void msm_hdmi_bridge_mode_set(struct drm_bridge *bridge, DBG("frame_ctrl=%08x", frame_ctrl); hdmi_write(hdmi, REG_HDMI_FRAME_CTRL, frame_ctrl); - if (hdmi->hdmi_mode) + if (hdmi->connector->display_info.is_hdmi) msm_hdmi_audio_update(hdmi); } @@ -251,32 +431,19 @@ static const struct drm_edid *msm_hdmi_bridge_edid_read(struct drm_bridge *bridg hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl); - if (drm_edid) { - /* - * FIXME: This should use connector->display_info.is_hdmi from a - * path that has read the EDID and called - * drm_edid_connector_update(). - */ - const struct edid *edid = drm_edid_raw(drm_edid); - - hdmi->hdmi_mode = drm_detect_hdmi_monitor(edid); - } - return drm_edid; } -static enum drm_mode_status msm_hdmi_bridge_mode_valid(struct drm_bridge *bridge, - const struct drm_display_info *info, - const struct drm_display_mode *mode) +static enum drm_mode_status msm_hdmi_bridge_tmds_char_rate_valid(const struct drm_bridge *bridge, + const struct drm_display_mode *mode, + unsigned long long tmds_rate) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; const struct hdmi_platform_config *config = hdmi->config; struct msm_drm_private *priv = bridge->dev->dev_private; struct msm_kms *kms = priv->kms; - long actual, requested; - - requested = 1000 * mode->clock; + long actual; /* for mdp5/apq8074, we manage our own pixel clk (as opposed to * mdp4/dtv stuff where pixel clk is assigned to mdp/encoder @@ -284,27 +451,34 @@ static enum drm_mode_status msm_hdmi_bridge_mode_valid(struct drm_bridge *bridge */ if (kms->funcs->round_pixclk) actual = kms->funcs->round_pixclk(kms, - requested, hdmi_bridge->hdmi->encoder); + tmds_rate, + hdmi_bridge->hdmi->encoder); else if (config->pwr_clk_cnt > 0) - actual = clk_round_rate(hdmi->pwr_clks[0], requested); + actual = clk_round_rate(hdmi->pwr_clks[0], tmds_rate); else - actual = requested; + actual = tmds_rate; - DBG("requested=%ld, actual=%ld", requested, actual); + DBG("requested=%lld, actual=%ld", tmds_rate, actual); - if (actual != requested) + if (actual != tmds_rate) return MODE_CLOCK_RANGE; return 0; } static const struct drm_bridge_funcs msm_hdmi_bridge_funcs = { - .pre_enable = msm_hdmi_bridge_pre_enable, - .post_disable = msm_hdmi_bridge_post_disable, - .mode_set = msm_hdmi_bridge_mode_set, - .mode_valid = msm_hdmi_bridge_mode_valid, + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, + .atomic_pre_enable = msm_hdmi_bridge_atomic_pre_enable, + .atomic_post_disable = msm_hdmi_bridge_atomic_post_disable, .edid_read = msm_hdmi_bridge_edid_read, .detect = msm_hdmi_bridge_detect, + .hdmi_tmds_char_rate_valid = msm_hdmi_bridge_tmds_char_rate_valid, + .hdmi_clear_infoframe = msm_hdmi_bridge_clear_infoframe, + .hdmi_write_infoframe = msm_hdmi_bridge_write_infoframe, + .hdmi_audio_prepare = msm_hdmi_bridge_audio_prepare, + .hdmi_audio_shutdown = msm_hdmi_bridge_audio_shutdown, }; static void @@ -336,9 +510,15 @@ int msm_hdmi_bridge_init(struct hdmi *hdmi) bridge->funcs = &msm_hdmi_bridge_funcs; bridge->ddc = hdmi->i2c; bridge->type = DRM_MODE_CONNECTOR_HDMIA; + bridge->vendor = "Qualcomm"; + bridge->product = "Snapdragon"; bridge->ops = DRM_BRIDGE_OP_HPD | DRM_BRIDGE_OP_DETECT | + DRM_BRIDGE_OP_HDMI | DRM_BRIDGE_OP_EDID; + bridge->hdmi_audio_max_i2s_playback_channels = 8; + bridge->hdmi_audio_dev = &hdmi->pdev->dev; + bridge->hdmi_audio_dai_port = -1; ret = devm_drm_bridge_add(hdmi->dev->dev, bridge); if (ret) diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index a7a2384044ff..87a91148a731 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -183,10 +183,16 @@ static unsigned get_crtc_mask(struct drm_atomic_state *state) int msm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) { + struct msm_drm_private *priv = dev->dev_private; + struct msm_kms *kms = priv->kms; struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct drm_crtc *crtc; - int i; + int i, ret = 0; + /* + * FIXME: stop setting allow_modeset and move this check to the DPU + * driver. + */ for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { if ((old_crtc_state->ctm && !new_crtc_state->ctm) || @@ -196,6 +202,11 @@ int msm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) } } + if (kms && kms->funcs && kms->funcs->check_mode_changed) + ret = kms->funcs->check_mode_changed(kms, state); + if (ret) + return ret; + return drm_atomic_helper_check(dev, state); } @@ -221,6 +232,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state) kms->funcs->wait_flush(kms, crtc_mask); trace_msm_atomic_wait_flush_finish(crtc_mask); + atomic_set(&kms->fault_snapshot_capture, 0); + /* * Now that there is no in-progress flush, prepare the * current update: diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index ff7a7a9f7b0d..c3588dc9e537 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -894,6 +894,7 @@ static const struct drm_driver msm_driver = { DRIVER_RENDER | DRIVER_ATOMIC | DRIVER_MODESET | + DRIVER_SYNCOBJ_TIMELINE | DRIVER_SYNCOBJ, .open = msm_open, .postclose = msm_postclose, diff --git a/drivers/gpu/drm/msm/msm_dsc_helper.h b/drivers/gpu/drm/msm/msm_dsc_helper.h index b9049fe1e279..63f95523b2cb 100644 --- a/drivers/gpu/drm/msm/msm_dsc_helper.h +++ b/drivers/gpu/drm/msm/msm_dsc_helper.h @@ -13,17 +13,6 @@ #include <drm/display/drm_dsc_helper.h> /** - * msm_dsc_get_slices_per_intf() - calculate number of slices per interface - * @dsc: Pointer to drm dsc config struct - * @intf_width: interface width in pixels - * Returns: Integer representing the number of slices for the given interface - */ -static inline u32 msm_dsc_get_slices_per_intf(const struct drm_dsc_config *dsc, u32 intf_width) -{ - return DIV_ROUND_UP(intf_width, dsc->slice_width); -} - -/** * msm_dsc_get_bytes_per_line() - calculate bytes per line * @dsc: Pointer to drm dsc config struct * Returns: Integer value representing bytes per line. DSI and DP need diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index dee470403036..3e9aa2cc38ef 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -509,7 +509,7 @@ static struct drm_syncobj **msm_parse_deps(struct msm_gem_submit *submit, } if (syncobj_desc.flags & ~MSM_SUBMIT_SYNCOBJ_FLAGS) { - ret = -SUBMIT_ERROR(EINVAL, submit, "invalid syncobj flags: %x", syncobj_desc.flags); + ret = SUBMIT_ERROR(EINVAL, submit, "invalid syncobj flags: %x", syncobj_desc.flags); break; } diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 8557998e0c92..c380d9d9f5af 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -281,6 +281,15 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, if (submit) { int i; + if (state->fault_info.ttbr0) { + struct msm_gpu_fault_info *info = &state->fault_info; + struct msm_mmu *mmu = submit->aspace->mmu; + + msm_iommu_pagetable_params(mmu, &info->pgtbl_ttbr0, + &info->asid); + msm_iommu_pagetable_walk(mmu, info->iova, info->ptes); + } + state->bos = kcalloc(submit->nr_bos, sizeof(struct msm_gpu_state_bo), GFP_KERNEL); diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 7cabc8480d7c..e25009150579 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -101,6 +101,14 @@ struct msm_gpu_fault_info { int flags; const char *type; const char *block; + + /* Information about what we think/expect is the current SMMU state, + * for example expected_ttbr0 should match smmu_info.ttbr0 which + * was read back from SMMU registers. + */ + phys_addr_t pgtbl_ttbr0; + u64 ptes[4]; + int asid; }; /** diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 2a94e82316f9..fd73dcd3f30e 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -195,6 +195,28 @@ struct iommu_domain_geometry *msm_iommu_get_geometry(struct msm_mmu *mmu) return &iommu->domain->geometry; } +int +msm_iommu_pagetable_walk(struct msm_mmu *mmu, unsigned long iova, uint64_t ptes[4]) +{ + struct msm_iommu_pagetable *pagetable; + struct arm_lpae_io_pgtable_walk_data wd = {}; + + if (mmu->type != MSM_MMU_IOMMU_PAGETABLE) + return -EINVAL; + + pagetable = to_pagetable(mmu); + + if (!pagetable->pgtbl_ops->pgtable_walk) + return -EINVAL; + + pagetable->pgtbl_ops->pgtable_walk(pagetable->pgtbl_ops, iova, &wd); + + for (int i = 0; i < ARRAY_SIZE(wd.ptes); i++) + ptes[i] = wd.ptes[i]; + + return 0; +} + static const struct msm_mmu_funcs pagetable_funcs = { .map = msm_iommu_pagetable_map, .unmap = msm_iommu_pagetable_unmap, @@ -243,7 +265,7 @@ static const struct iommu_flush_ops tlb_ops = { .tlb_add_page = msm_iommu_tlb_add_page, }; -static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, +static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags, void *arg); struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) @@ -319,7 +341,7 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) return &pagetable->base; } -static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, +static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags, void *arg) { struct msm_iommu *iommu = arg; @@ -343,6 +365,17 @@ static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, return 0; } +static int msm_disp_fault_handler(struct iommu_domain *domain, struct device *dev, + unsigned long iova, int flags, void *arg) +{ + struct msm_iommu *iommu = arg; + + if (iommu->base.handler) + return iommu->base.handler(iommu->base.arg, iova, flags, NULL); + + return -ENOSYS; +} + static void msm_iommu_resume_translation(struct msm_mmu *mmu) { struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(mmu->dev); @@ -437,6 +470,21 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) return &iommu->base; } +struct msm_mmu *msm_iommu_disp_new(struct device *dev, unsigned long quirks) +{ + struct msm_iommu *iommu; + struct msm_mmu *mmu; + + mmu = msm_iommu_new(dev, quirks); + if (IS_ERR_OR_NULL(mmu)) + return mmu; + + iommu = to_msm_iommu(mmu); + iommu_set_fault_handler(iommu->domain, msm_disp_fault_handler, iommu); + + return mmu; +} + struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsigned long quirks) { struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(dev); @@ -448,7 +496,7 @@ struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsig return mmu; iommu = to_msm_iommu(mmu); - iommu_set_fault_handler(iommu->domain, msm_fault_handler, iommu); + iommu_set_fault_handler(iommu->domain, msm_gpu_fault_handler, iommu); /* Enable stall on iommu fault: */ if (adreno_smmu->set_stall) diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c index 38965e12a6bf..35d5397e73b4 100644 --- a/drivers/gpu/drm/msm/msm_kms.c +++ b/drivers/gpu/drm/msm/msm_kms.c @@ -164,12 +164,26 @@ void msm_crtc_disable_vblank(struct drm_crtc *crtc) vblank_ctrl_queue_work(priv, crtc, false); } +static int msm_kms_fault_handler(void *arg, unsigned long iova, int flags, void *data) +{ + struct msm_kms *kms = arg; + + if (atomic_read(&kms->fault_snapshot_capture) == 0) { + msm_disp_snapshot_state(kms->dev); + atomic_inc(&kms->fault_snapshot_capture); + } + + return -ENOSYS; +} + struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev) { struct msm_gem_address_space *aspace; struct msm_mmu *mmu; struct device *mdp_dev = dev->dev; struct device *mdss_dev = mdp_dev->parent; + struct msm_drm_private *priv = dev->dev_private; + struct msm_kms *kms = priv->kms; struct device *iommu_dev; /* @@ -181,7 +195,7 @@ struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev) else iommu_dev = mdss_dev; - mmu = msm_iommu_new(iommu_dev, 0); + mmu = msm_iommu_disp_new(iommu_dev, 0); if (IS_ERR(mmu)) return ERR_CAST(mmu); @@ -195,8 +209,11 @@ struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev) if (IS_ERR(aspace)) { dev_err(mdp_dev, "aspace create, error %pe\n", aspace); mmu->funcs->destroy(mmu); + return aspace; } + msm_mmu_set_fault_handler(aspace->mmu, kms, msm_kms_fault_handler); + return aspace; } diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h index e60162744c66..43b58d052ee6 100644 --- a/drivers/gpu/drm/msm/msm_kms.h +++ b/drivers/gpu/drm/msm/msm_kms.h @@ -60,6 +60,13 @@ struct msm_kms_funcs { void (*disable_commit)(struct msm_kms *kms); /** + * @check_mode_changed: + * + * Verify if the commit requires a full modeset on one of CRTCs. + */ + int (*check_mode_changed)(struct msm_kms *kms, struct drm_atomic_state *state); + + /** * Prepare for atomic commit. This is called after any previous * (async or otherwise) commit has completed. */ @@ -128,6 +135,9 @@ struct msm_kms { int irq; bool irq_requested; + /* rate limit the snapshot capture to once per attach */ + atomic_t fault_snapshot_capture; + /* mapper-id used to request GEM buffer mapped for scanout: */ struct msm_gem_address_space *aspace; diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h index 88af4f490881..daf91529e02b 100644 --- a/drivers/gpu/drm/msm/msm_mmu.h +++ b/drivers/gpu/drm/msm/msm_mmu.h @@ -42,6 +42,7 @@ static inline void msm_mmu_init(struct msm_mmu *mmu, struct device *dev, struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks); struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsigned long quirks); +struct msm_mmu *msm_iommu_disp_new(struct device *dev, unsigned long quirks); static inline void msm_mmu_set_fault_handler(struct msm_mmu *mmu, void *arg, int (*handler)(void *arg, unsigned long iova, int flags, void *data)) @@ -53,7 +54,8 @@ static inline void msm_mmu_set_fault_handler(struct msm_mmu *mmu, void *arg, struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent); int msm_iommu_pagetable_params(struct msm_mmu *mmu, phys_addr_t *ttbr, - int *asid); + int *asid); +int msm_iommu_pagetable_walk(struct msm_mmu *mmu, unsigned long iova, uint64_t ptes[4]); struct iommu_domain_geometry *msm_iommu_get_geometry(struct msm_mmu *mmu); #endif /* __MSM_MMU_H__ */ diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml index 35f7f40e405b..d2c8c46bb041 100644 --- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml +++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml @@ -17,6 +17,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="CLK_EN" pos="5" type="boolean"/> <bitfield name="CLK_EN_SEL" pos="4" type="boolean"/> <bitfield name="BITCLK_SEL" low="2" high="3" type="uint"/> + <bitfield name="DSICLK_SEL" low="0" high="1" type="uint"/> </reg32> <reg32 offset="0x00018" name="GLBL_CTRL"/> <reg32 offset="0x0001c" name="RBUF_CTRL"/> diff --git a/drivers/gpu/drm/msm/registers/display/hdmi.xml b/drivers/gpu/drm/msm/registers/display/hdmi.xml index 1cf1b14fbd91..0ebb96297dae 100644 --- a/drivers/gpu/drm/msm/registers/display/hdmi.xml +++ b/drivers/gpu/drm/msm/registers/display/hdmi.xml @@ -131,7 +131,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> --> <bitfield name="GENERIC0_SEND" pos="0" type="boolean"/> <bitfield name="GENERIC0_CONT" pos="1" type="boolean"/> - <bitfield name="GENERIC0_UPDATE" low="2" high="3" type="uint"/> <!-- ??? --> + <bitfield name="GENERIC0_UPDATE" pos="2" type="boolean"/> <bitfield name="GENERIC1_SEND" pos="4" type="boolean"/> <bitfield name="GENERIC1_CONT" pos="5" type="boolean"/> <bitfield name="GENERIC0_LINE" low="16" high="21" type="uint"/> diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig index ac76c0787010..7b3e979c51ec 100644 --- a/drivers/gpu/drm/nouveau/Kconfig +++ b/drivers/gpu/drm/nouveau/Kconfig @@ -4,6 +4,7 @@ config DRM_NOUVEAU depends on DRM && PCI && MMU select IOMMU_API select FW_LOADER + select FW_CACHE if PM_SLEEP select DRM_CLIENT_SELECTION select DRM_DISPLAY_DP_HELPER select DRM_DISPLAY_HDMI_HELPER diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 6fb9719d721f..1b10c6c12f46 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -775,7 +775,6 @@ nouveau_connector_force(struct drm_connector *connector) if (!nv_encoder) { NV_ERROR(drm, "can't find encoder to force %s on!\n", connector->name); - connector->status = connector_status_disconnected; return; } diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c index 05c13102a8cb..d22889fbfa9c 100644 --- a/drivers/gpu/drm/radeon/r300.c +++ b/drivers/gpu/drm/radeon/r300.c @@ -359,7 +359,8 @@ int r300_mc_wait_for_idle(struct radeon_device *rdev) return -1; } -static void r300_gpu_init(struct radeon_device *rdev) +/* rs400_gpu_init also calls this! */ +void r300_gpu_init(struct radeon_device *rdev) { uint32_t gb_tile_config, tmp; diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index 1e00f6b99f94..8f5e07834fcc 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -165,6 +165,7 @@ void r200_set_safe_registers(struct radeon_device *rdev); */ extern int r300_init(struct radeon_device *rdev); extern void r300_fini(struct radeon_device *rdev); +extern void r300_gpu_init(struct radeon_device *rdev); extern int r300_suspend(struct radeon_device *rdev); extern int r300_resume(struct radeon_device *rdev); extern int r300_asic_reset(struct radeon_device *rdev, bool hard); diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 6f071e61f764..bbd39348a7ab 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -530,7 +530,7 @@ int radeon_wb_init(struct radeon_device *rdev) * @mc: memory controller structure holding memory informations * @base: base address at which to put VRAM * - * Function will place try to place VRAM at base address provided + * Function will try to place VRAM at base address provided * as parameter (which is so far either PCI aperture address or * for IGP TOM base address). * @@ -557,7 +557,7 @@ int radeon_wb_init(struct radeon_device *rdev) * * Note 3: when limiting vram it's safe to overwritte real_vram_size because * we are not in case where real_vram_size is inferior to mc_vram_size (ie - * note afected by bogus hw of Novell bug 204882 + along with lots of ubuntu + * not affected by bogus hw of Novell bug 204882 + along with lots of ubuntu * ones) * * Note 4: IGP TOM addr should be the same as the aperture addr, we don't @@ -594,7 +594,7 @@ void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64 * @rdev: radeon device structure holding all necessary informations * @mc: memory controller structure holding memory informations * - * Function will place try to place GTT before or after VRAM. + * Function will try to place GTT before or after VRAM. * * If GTT size is bigger than space left then we ajust GTT size. * Thus function will never fails. diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index daff61586be5..8ff4f18b51a9 100644 --- a/drivers/gpu/drm/radeon/radeon_fence.c +++ b/drivers/gpu/drm/radeon/radeon_fence.c @@ -840,7 +840,7 @@ int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring) } radeon_fence_write(rdev, atomic64_read(&rdev->fence_drv[ring].last_seq), ring); rdev->fence_drv[ring].initialized = true; - dev_info(rdev->dev, "fence driver on ring %d use gpu addr 0x%016llx\n", + dev_info(rdev->dev, "fence driver on ring %d uses gpu addr 0x%016llx\n", ring, rdev->fence_drv[ring].gpu_addr); return 0; } diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c index d6c18fd740ec..13cd0a688a65 100644 --- a/drivers/gpu/drm/radeon/rs400.c +++ b/drivers/gpu/drm/radeon/rs400.c @@ -256,8 +256,22 @@ int rs400_mc_wait_for_idle(struct radeon_device *rdev) static void rs400_gpu_init(struct radeon_device *rdev) { - /* FIXME: is this correct ? */ - r420_pipes_init(rdev); + /* Earlier code was calling r420_pipes_init and then + * rs400_mc_wait_for_idle(rdev). The problem is that + * at least on my Mobility Radeon Xpress 200M RC410 card + * that ends up in this code path ends up num_gb_pipes == 3 + * while the card seems to have only one pipe. With the + * r420 pipe initialization method. + * + * Problems shown up as HyperZ glitches, see: + * https://bugs.freedesktop.org/show_bug.cgi?id=110897 + * + * Delegating initialization to r300 code seems to work + * and results in proper pipe numbers. The rs400 cards + * are said to be not r400, but r300 kind of cards. + */ + r300_gpu_init(rdev); + if (rs400_mc_wait_for_idle(rdev)) { pr_warn("rs400: Failed to wait MC idle while programming pipes. Bad things might happen. %08x\n", RREG32(RADEON_MC_STATUS)); diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index 6c95575ce109..26197aceb001 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -6198,7 +6198,7 @@ static inline u32 si_get_ih_wptr(struct radeon_device *rdev) if (wptr & RB_OVERFLOW) { wptr &= ~RB_OVERFLOW; - /* When a ring buffer overflow happen start parsing interrupt + /* When a ring buffer overflow happens, start parsing interrupts * from the last not overwritten vector (wptr + 16). Hopefully * this should allow us to catchup. */ diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h index c75302ca3427..f56e77e7f6d0 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h +++ b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h @@ -21,7 +21,7 @@ * */ -#if !defined(_GPU_SCHED_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#if !defined(_GPU_SCHED_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) #define _GPU_SCHED_TRACE_H_ #include <linux/stringify.h> @@ -106,7 +106,7 @@ TRACE_EVENT(drm_sched_job_wait_dep, __entry->seqno) ); -#endif +#endif /* _GPU_SCHED_TRACE_H_ */ /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c index c67e1f906785..8706763af8fb 100644 --- a/drivers/gpu/drm/tiny/bochs.c +++ b/drivers/gpu/drm/tiny/bochs.c @@ -335,8 +335,6 @@ static void bochs_hw_setmode(struct bochs_device *bochs, struct drm_display_mode bochs->xres, bochs->yres, bochs->bpp, bochs->yres_virtual); - bochs_hw_blank(bochs, false); - bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE, 0); bochs_dispi_write(bochs, VBE_DISPI_INDEX_BPP, bochs->bpp); bochs_dispi_write(bochs, VBE_DISPI_INDEX_XRES, bochs->xres); @@ -506,6 +504,9 @@ static int bochs_crtc_helper_atomic_check(struct drm_crtc *crtc, static void bochs_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_atomic_state *state) { + struct bochs_device *bochs = to_bochs_device(crtc->dev); + + bochs_hw_blank(bochs, false); } static void bochs_crtc_helper_atomic_disable(struct drm_crtc *crtc, diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c index b20ac1705726..fa269d279e25 100644 --- a/drivers/gpu/drm/vkms/vkms_composer.c +++ b/drivers/gpu/drm/vkms/vkms_composer.c @@ -67,7 +67,7 @@ static u16 lerp_u16(u16 a, u16 b, s64 t) s64 delta = drm_fixp_mul(b_fp - a_fp, t); - return drm_fixp2int(a_fp + delta); + return drm_fixp2int_round(a_fp + delta); } static s64 get_lut_index(const struct vkms_color_lut *lut, u16 channel_value) diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig index 99219c16e8aa..7d7995196702 100644 --- a/drivers/gpu/drm/xe/Kconfig +++ b/drivers/gpu/drm/xe/Kconfig @@ -39,6 +39,7 @@ config DRM_XE select DRM_TTM_HELPER select DRM_EXEC select DRM_GPUVM + select DRM_GPUSVM if !UML && DEVICE_PRIVATE select DRM_SCHED select MMU_NOTIFIER select WANT_DEV_COREDUMP @@ -73,6 +74,15 @@ config DRM_XE_DP_TUNNEL If in doubt say "Y". +config DRM_XE_DEVMEM_MIRROR + bool "Enable device memory mirror" + depends on DRM_XE + select GET_FREE_REGION + default y + help + Disable this option only if you want to compile out without device + memory mirror. Will reduce KMD memory footprint when disabled. + config DRM_XE_FORCE_PROBE string "Force probe xe for selected Intel hardware IDs" depends on DRM_XE diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index 81b8914b877c..9699b08585f7 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -33,6 +33,7 @@ xe-y += xe_bb.o \ xe_device_sysfs.o \ xe_dma_buf.o \ xe_drm_client.o \ + xe_eu_stall.o \ xe_exec.o \ xe_exec_queue.o \ xe_execlist.o \ @@ -60,6 +61,7 @@ xe-y += xe_bb.o \ xe_guc_capture.o \ xe_guc_ct.o \ xe_guc_db_mgr.o \ + xe_guc_engine_activity.o \ xe_guc_hwconfig.o \ xe_guc_id_mgr.o \ xe_guc_klv_helpers.o \ @@ -123,6 +125,7 @@ xe-y += xe_bb.o \ xe_wopcm.o xe-$(CONFIG_HMM_MIRROR) += xe_hmm.o +xe-$(CONFIG_DRM_GPUSVM) += xe_svm.o # graphics hardware monitoring (HWMON) support xe-$(CONFIG_HWMON) += xe_hwmon.o diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h index fee385532fb0..ec516e838ee8 100644 --- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h +++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h @@ -140,6 +140,7 @@ enum xe_guc_action { XE_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC = 0x4601, XE_GUC_ACTION_CLIENT_SOFT_RESET = 0x5507, XE_GUC_ACTION_SET_ENG_UTIL_BUFF = 0x550A, + XE_GUC_ACTION_SET_DEVICE_ENGINE_ACTIVITY_BUFFER = 0x550C, XE_GUC_ACTION_NOTIFY_MEMORY_CAT_ERROR = 0x6000, XE_GUC_ACTION_REPORT_PAGE_FAULT_REQ_DESC = 0x6002, XE_GUC_ACTION_PAGE_FAULT_RES_DESC = 0x6003, diff --git a/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h index 85abe4f09ae2..b28c8fa061f7 100644 --- a/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h +++ b/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h @@ -174,6 +174,9 @@ struct slpc_task_state_data { }; } __packed; +#define SLPC_CTX_FREQ_REQ_IS_COMPUTE REG_BIT(28) +#define SLPC_OPTIMIZED_STRATEGY_COMPUTE REG_BIT(0) + struct slpc_shared_data_header { /* Total size in bytes of this shared buffer. */ u32 size; diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h new file mode 100644 index 000000000000..8a048980ea38 --- /dev/null +++ b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright © 2025 Intel Corporation */ + +#ifndef __I915_GEM_OBJECT_H__ +#define __I915_GEM_OBJECT_H__ + +struct dma_fence; +struct i915_sched_attr; + +static inline void i915_gem_fence_wait_priority(struct dma_fence *fence, + const struct i915_sched_attr *attr) +{ +} + +#endif diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h index 84b0991b35b3..dfec5108d2c3 100644 --- a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h +++ b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h @@ -95,14 +95,6 @@ static inline struct drm_i915_private *to_i915(const struct drm_device *dev) #define HAS_128_BYTE_Y_TILING(xe) (xe || 1) -#define I915_PRIORITY_DISPLAY 0 -struct i915_sched_attr { - int priority; -}; -#define i915_gem_fence_wait_priority(fence, attr) do { (void) attr; } while (0) - -#define FORCEWAKE_ALL XE_FORCEWAKE_ALL - #ifdef CONFIG_ARM64 /* * arm64 indirectly includes linux/rtc.h, diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_gtt_view_types.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_gtt_view_types.h new file mode 100644 index 000000000000..b261910cd6f9 --- /dev/null +++ b/drivers/gpu/drm/xe/compat-i915-headers/i915_gtt_view_types.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright © 2025 Intel Corporation */ + +#include "../../i915/i915_gtt_view_types.h" + +/* Partial view not supported in xe, fail build if used. */ +#define I915_GTT_VIEW_PARTIAL diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_scheduler_types.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_scheduler_types.h new file mode 100644 index 000000000000..c11130440d31 --- /dev/null +++ b/drivers/gpu/drm/xe/compat-i915-headers/i915_scheduler_types.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright © 2025 Intel Corporation */ + +#ifndef __I915_SCHEDULER_TYPES_H__ +#define __I915_SCHEDULER_TYPES_H__ + +#define I915_PRIORITY_DISPLAY 0 + +struct i915_sched_attr { + int priority; +}; + +#endif diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_vma_types.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_vma_types.h deleted file mode 100644 index e7aaf50f5485..000000000000 --- a/drivers/gpu/drm/xe/compat-i915-headers/i915_vma_types.h +++ /dev/null @@ -1,74 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2023 Intel Corporation - */ - -#include <linux/types.h> -#include <linux/build_bug.h> - -/* XX: Figure out how to handle this vma mapping in xe */ -struct intel_remapped_plane_info { - /* in gtt pages */ - u32 offset:31; - u32 linear:1; - union { - /* in gtt pages for !linear */ - struct { - u16 width; - u16 height; - u16 src_stride; - u16 dst_stride; - }; - - /* in gtt pages for linear */ - u32 size; - }; -} __packed; - -struct intel_remapped_info { - struct intel_remapped_plane_info plane[4]; - /* in gtt pages */ - u32 plane_alignment; -} __packed; - -struct intel_rotation_info { - struct intel_remapped_plane_info plane[2]; -} __packed; - -enum i915_gtt_view_type { - I915_GTT_VIEW_NORMAL = 0, - I915_GTT_VIEW_ROTATED = sizeof(struct intel_rotation_info), - I915_GTT_VIEW_REMAPPED = sizeof(struct intel_remapped_info), -}; - -static inline void assert_i915_gem_gtt_types(void) -{ - BUILD_BUG_ON(sizeof(struct intel_rotation_info) != 2 * sizeof(u32) + 8 * sizeof(u16)); - BUILD_BUG_ON(sizeof(struct intel_remapped_info) != 5 * sizeof(u32) + 16 * sizeof(u16)); - - /* Check that rotation/remapped shares offsets for simplicity */ - BUILD_BUG_ON(offsetof(struct intel_remapped_info, plane[0]) != - offsetof(struct intel_rotation_info, plane[0])); - BUILD_BUG_ON(offsetofend(struct intel_remapped_info, plane[1]) != - offsetofend(struct intel_rotation_info, plane[1])); - - /* As we encode the size of each branch inside the union into its type, - * we have to be careful that each branch has a unique size. - */ - switch ((enum i915_gtt_view_type)0) { - case I915_GTT_VIEW_NORMAL: - case I915_GTT_VIEW_ROTATED: - case I915_GTT_VIEW_REMAPPED: - /* gcc complains if these are identical cases */ - break; - } -} - -struct i915_gtt_view { - enum i915_gtt_view_type type; - union { - /* Members need to contain no holes/padding */ - struct intel_rotation_info rotated; - struct intel_remapped_info remapped; - }; -}; diff --git a/drivers/gpu/drm/xe/compat-i915-headers/intel_uncore.h b/drivers/gpu/drm/xe/compat-i915-headers/intel_uncore.h index 4fc3e535de91..0c1e88e36a1e 100644 --- a/drivers/gpu/drm/xe/compat-i915-headers/intel_uncore.h +++ b/drivers/gpu/drm/xe/compat-i915-headers/intel_uncore.h @@ -10,6 +10,8 @@ #include "xe_device_types.h" #include "xe_mmio.h" +#define FORCEWAKE_ALL XE_FORCEWAKE_ALL + static inline struct intel_uncore *to_intel_uncore(struct drm_device *drm) { return &to_xe_device(drm)->uncore; diff --git a/drivers/gpu/drm/xe/compat-i915-headers/pxp/intel_pxp.h b/drivers/gpu/drm/xe/compat-i915-headers/pxp/intel_pxp.h index d2eb8e1f6c4b..97fd0ddf0b3a 100644 --- a/drivers/gpu/drm/xe/compat-i915-headers/pxp/intel_pxp.h +++ b/drivers/gpu/drm/xe/compat-i915-headers/pxp/intel_pxp.h @@ -12,11 +12,8 @@ #include "xe_pxp.h" struct drm_gem_object; -struct xe_pxp; -static inline int intel_pxp_key_check(struct xe_pxp *pxp, - struct drm_gem_object *obj, - bool assign) +static inline int intel_pxp_key_check(struct drm_gem_object *obj, bool assign) { /* * The assign variable is used in i915 to assign the key to the BO at @@ -26,7 +23,7 @@ static inline int intel_pxp_key_check(struct xe_pxp *pxp, if (assign) return -EINVAL; - return xe_pxp_obj_key_check(pxp, obj); + return xe_pxp_obj_key_check(obj); } #endif diff --git a/drivers/gpu/drm/xe/display/intel_fbdev_fb.c b/drivers/gpu/drm/xe/display/intel_fbdev_fb.c index ca95fcd098ec..3a1e505ff182 100644 --- a/drivers/gpu/drm/xe/display/intel_fbdev_fb.c +++ b/drivers/gpu/drm/xe/display/intel_fbdev_fb.c @@ -45,7 +45,7 @@ struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_fb_helper *helper, NULL, size, ttm_bo_type_kernel, XE_BO_FLAG_SCANOUT | XE_BO_FLAG_STOLEN | - XE_BO_FLAG_PINNED); + XE_BO_FLAG_GGTT | XE_BO_FLAG_PINNED); if (!IS_ERR(obj)) drm_info(&xe->drm, "Allocated fbdev into stolen\n"); else @@ -56,7 +56,7 @@ struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_fb_helper *helper, obj = xe_bo_create_pin_map(xe, xe_device_get_root_tile(xe), NULL, size, ttm_bo_type_kernel, XE_BO_FLAG_SCANOUT | XE_BO_FLAG_VRAM_IF_DGFX(xe_device_get_root_tile(xe)) | - XE_BO_FLAG_PINNED); + XE_BO_FLAG_GGTT | XE_BO_FLAG_PINNED); } if (IS_ERR(obj)) { diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c index 02a413a07382..0b0aca7a25af 100644 --- a/drivers/gpu/drm/xe/display/xe_display.c +++ b/drivers/gpu/drm/xe/display/xe_display.c @@ -8,6 +8,8 @@ #include <linux/fb.h> +#include <drm/drm_client.h> +#include <drm/drm_client_event.h> #include <drm/drm_drv.h> #include <drm/drm_managed.h> #include <drm/drm_probe_helper.h> @@ -67,6 +69,10 @@ void xe_display_driver_set_hooks(struct drm_driver *driver) if (!xe_modparam.probe_display) return; +#ifdef CONFIG_DRM_FBDEV_EMULATION + driver->fbdev_probe = intel_fbdev_driver_fbdev_probe; +#endif + driver->driver_features |= DRIVER_MODESET | DRIVER_ATOMIC; } @@ -170,6 +176,7 @@ static void xe_display_fini(void *arg) intel_hpd_poll_fini(xe); intel_hdcp_component_fini(display); intel_audio_deinit(display); + intel_display_driver_remove(display); } int xe_display_init(struct xe_device *xe) @@ -184,7 +191,7 @@ int xe_display_init(struct xe_device *xe) if (err) return err; - return xe_device_add_action_or_reset(xe, xe_display_fini, xe); + return devm_add_action_or_reset(xe->drm.dev, xe_display_fini, xe); } void xe_display_register(struct xe_device *xe) @@ -209,16 +216,6 @@ void xe_display_unregister(struct xe_device *xe) intel_display_driver_unregister(display); } -void xe_display_driver_remove(struct xe_device *xe) -{ - struct intel_display *display = &xe->display; - - if (!xe->info.probe_display) - return; - - intel_display_driver_remove(display); -} - /* IRQ-related functions */ void xe_display_irq_handler(struct xe_device *xe, u32 master_ctl) @@ -348,7 +345,7 @@ void xe_display_pm_suspend(struct xe_device *xe) * properly. */ intel_power_domains_disable(display); - intel_fbdev_set_suspend(&xe->drm, FBINFO_STATE_SUSPENDED, true); + drm_client_dev_suspend(&xe->drm, false); if (has_display(xe)) { drm_kms_helper_poll_disable(&xe->drm); @@ -378,7 +375,8 @@ void xe_display_pm_shutdown(struct xe_device *xe) return; intel_power_domains_disable(display); - intel_fbdev_set_suspend(&xe->drm, FBINFO_STATE_SUSPENDED, true); + drm_client_dev_suspend(&xe->drm, false); + if (has_display(xe)) { drm_kms_helper_poll_disable(&xe->drm); intel_display_driver_disable_user_access(display); @@ -497,7 +495,7 @@ void xe_display_pm_resume(struct xe_device *xe) intel_opregion_resume(display); - intel_fbdev_set_suspend(&xe->drm, FBINFO_STATE_RUNNING, false); + drm_client_dev_resume(&xe->drm, false); intel_power_domains_enable(display); } diff --git a/drivers/gpu/drm/xe/display/xe_display.h b/drivers/gpu/drm/xe/display/xe_display.h index 685dc74402fb..46e14f8dee28 100644 --- a/drivers/gpu/drm/xe/display/xe_display.h +++ b/drivers/gpu/drm/xe/display/xe_display.h @@ -14,7 +14,6 @@ struct drm_driver; bool xe_display_driver_probe_defer(struct pci_dev *pdev); void xe_display_driver_set_hooks(struct drm_driver *driver); -void xe_display_driver_remove(struct xe_device *xe); int xe_display_create(struct xe_device *xe); diff --git a/drivers/gpu/drm/xe/display/xe_display_rps.c b/drivers/gpu/drm/xe/display/xe_display_rps.c index ab21c581c192..fa616f9688a5 100644 --- a/drivers/gpu/drm/xe/display/xe_display_rps.c +++ b/drivers/gpu/drm/xe/display/xe_display_rps.c @@ -10,7 +10,7 @@ void intel_display_rps_boost_after_vblank(struct drm_crtc *crtc, { } -void intel_display_rps_mark_interactive(struct drm_i915_private *i915, +void intel_display_rps_mark_interactive(struct intel_display *display, struct intel_atomic_state *state, bool interactive) { diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c index 11a6b996d739..d918ae1c8061 100644 --- a/drivers/gpu/drm/xe/display/xe_fb_pin.c +++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c @@ -5,6 +5,7 @@ #include <drm/ttm/ttm_bo.h> +#include "i915_vma.h" #include "intel_display_types.h" #include "intel_dpt.h" #include "intel_fb.h" @@ -81,7 +82,7 @@ write_dpt_remapped(struct xe_bo *bo, struct iosys_map *map, u32 *dpt_ofs, static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb, const struct i915_gtt_view *view, struct i915_vma *vma, - u64 physical_alignment) + unsigned int alignment) { struct xe_device *xe = to_xe_device(fb->base.dev); struct xe_tile *tile0 = xe_device_get_root_tile(xe); @@ -107,7 +108,7 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb, XE_BO_FLAG_VRAM0 | XE_BO_FLAG_GGTT | XE_BO_FLAG_PAGETABLE, - physical_alignment); + alignment); else dpt = xe_bo_create_pin_map_at_aligned(xe, tile0, NULL, dpt_size, ~0ull, @@ -115,7 +116,7 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb, XE_BO_FLAG_STOLEN | XE_BO_FLAG_GGTT | XE_BO_FLAG_PAGETABLE, - physical_alignment); + alignment); if (IS_ERR(dpt)) dpt = xe_bo_create_pin_map_at_aligned(xe, tile0, NULL, dpt_size, ~0ull, @@ -123,7 +124,7 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb, XE_BO_FLAG_SYSTEM | XE_BO_FLAG_GGTT | XE_BO_FLAG_PAGETABLE, - physical_alignment); + alignment); if (IS_ERR(dpt)) return PTR_ERR(dpt); @@ -193,7 +194,7 @@ write_ggtt_rotated(struct xe_bo *bo, struct xe_ggtt *ggtt, u32 *ggtt_ofs, u32 bo static int __xe_pin_fb_vma_ggtt(const struct intel_framebuffer *fb, const struct i915_gtt_view *view, struct i915_vma *vma, - u64 physical_alignment) + unsigned int alignment) { struct drm_gem_object *obj = intel_fb_bo(&fb->base); struct xe_bo *bo = gem_to_xe_bo(obj); @@ -276,7 +277,7 @@ out: static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb, const struct i915_gtt_view *view, - u64 physical_alignment) + unsigned int alignment) { struct drm_device *dev = fb->base.dev; struct xe_device *xe = to_xe_device(dev); @@ -326,9 +327,9 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb, vma->bo = bo; if (intel_fb_uses_dpt(&fb->base)) - ret = __xe_pin_fb_vma_dpt(fb, view, vma, physical_alignment); + ret = __xe_pin_fb_vma_dpt(fb, view, vma, alignment); else - ret = __xe_pin_fb_vma_ggtt(fb, view, vma, physical_alignment); + ret = __xe_pin_fb_vma_ggtt(fb, view, vma, alignment); if (ret) goto err_unpin; @@ -421,7 +422,7 @@ int intel_plane_pin_fb(struct intel_plane_state *new_plane_state, struct i915_vma *vma; struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); struct intel_plane *plane = to_intel_plane(new_plane_state->uapi.plane); - u64 phys_alignment = plane->min_alignment(plane, fb, 0); + unsigned int alignment = plane->min_alignment(plane, fb, 0); if (reuse_vma(new_plane_state, old_plane_state)) return 0; @@ -429,7 +430,7 @@ int intel_plane_pin_fb(struct intel_plane_state *new_plane_state, /* We reject creating !SCANOUT fb's, so this is weird.. */ drm_WARN_ON(bo->ttm.base.dev, !(bo->flags & XE_BO_FLAG_SCANOUT)); - vma = __xe_pin_fb_vma(intel_fb, &new_plane_state->view.gtt, phys_alignment); + vma = __xe_pin_fb_vma(intel_fb, &new_plane_state->view.gtt, alignment); if (IS_ERR(vma)) return PTR_ERR(vma); diff --git a/drivers/gpu/drm/xe/display/xe_tdf.c b/drivers/gpu/drm/xe/display/xe_tdf.c index 2c0d4e144e09..2a7fccbeb1d5 100644 --- a/drivers/gpu/drm/xe/display/xe_tdf.c +++ b/drivers/gpu/drm/xe/display/xe_tdf.c @@ -7,7 +7,9 @@ #include "intel_display_types.h" #include "intel_tdf.h" -void intel_td_flush(struct drm_i915_private *i915) +void intel_td_flush(struct intel_display *display) { - xe_device_td_flush(i915); + struct xe_device *xe = to_xe_device(display->drm); + + xe_device_td_flush(xe); } diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h index c8fd3d5ca502..4f372dc2cb89 100644 --- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h @@ -53,7 +53,6 @@ #define RING_CTL(base) XE_REG((base) + 0x3c) #define RING_CTL_SIZE(size) ((size) - PAGE_SIZE) /* in bytes -> pages */ -#define RING_CTL_SIZE(size) ((size) - PAGE_SIZE) /* in bytes -> pages */ #define RING_START_UDW(base) XE_REG((base) + 0x48) diff --git a/drivers/gpu/drm/xe/regs/xe_eu_stall_regs.h b/drivers/gpu/drm/xe/regs/xe_eu_stall_regs.h new file mode 100644 index 000000000000..c53f57fdde65 --- /dev/null +++ b/drivers/gpu/drm/xe/regs/xe_eu_stall_regs.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2025 Intel Corporation + */ + +#ifndef _XE_EU_STALL_REGS_H_ +#define _XE_EU_STALL_REGS_H_ + +#include "regs/xe_reg_defs.h" + +#define XEHPC_EUSTALL_BASE XE_REG_MCR(0xe520) +#define XEHPC_EUSTALL_BASE_BUF_ADDR REG_GENMASK(31, 6) +#define XEHPC_EUSTALL_BASE_XECORE_BUF_SZ REG_GENMASK(5, 3) +#define XEHPC_EUSTALL_BASE_ENABLE_SAMPLING REG_BIT(1) + +#define XEHPC_EUSTALL_BASE_UPPER XE_REG_MCR(0xe524) + +#define XEHPC_EUSTALL_REPORT XE_REG_MCR(0xe528, XE_REG_OPTION_MASKED) +#define XEHPC_EUSTALL_REPORT_WRITE_PTR_MASK REG_GENMASK(15, 2) +#define XEHPC_EUSTALL_REPORT_OVERFLOW_DROP REG_BIT(1) + +#define XEHPC_EUSTALL_REPORT1 XE_REG_MCR(0xe52c, XE_REG_OPTION_MASKED) +#define XEHPC_EUSTALL_REPORT1_READ_PTR_MASK REG_GENMASK(15, 2) + +#define XEHPC_EUSTALL_CTRL XE_REG_MCR(0xe53c, XE_REG_OPTION_MASKED) +#define EUSTALL_MOCS REG_GENMASK(9, 3) +#define EUSTALL_SAMPLE_RATE REG_GENMASK(2, 0) + +#endif diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h index 096859072396..da1f198ac107 100644 --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h @@ -358,14 +358,18 @@ #define RENDER_AWAKE_STATUS REG_BIT(1) #define MEDIA_SLICE0_AWAKE_STATUS REG_BIT(0) +#define MISC_STATUS_0 XE_REG(0xa500) + #define FORCEWAKE_MEDIA_VDBOX(n) XE_REG(0xa540 + (n) * 4) #define FORCEWAKE_MEDIA_VEBOX(n) XE_REG(0xa560 + (n) * 4) #define FORCEWAKE_GSC XE_REG(0xa618) +#define XELP_GARBCNTL XE_REG(0xb004) +#define XELP_BUS_HASH_CTL_BIT_EXC REG_BIT(7) + #define XEHPC_LNCFMISCCFGREG0 XE_REG_MCR(0xb01c, XE_REG_OPTION_MASKED) #define XEHPC_OVRLSCCC REG_BIT(0) -/* L3 Cache Control */ #define LNCFCMOCS_REG_COUNT 32 #define XELP_LNCFCMOCS(i) XE_REG(0xb020 + (i) * 4) #define XEHP_LNCFCMOCS(i) XE_REG_MCR(0xb020 + (i) * 4) @@ -478,6 +482,7 @@ #define TDL_TSL_CHICKEN XE_REG_MCR(0xe4c4, XE_REG_OPTION_MASKED) #define STK_ID_RESTRICT REG_BIT(12) #define SLM_WMTP_RESTORE REG_BIT(11) +#define RES_CHK_SPR_DIS REG_BIT(6) #define ROW_CHICKEN XE_REG_MCR(0xe4f0, XE_REG_OPTION_MASKED) #define UGM_BACKUP_MODE REG_BIT(13) diff --git a/drivers/gpu/drm/xe/regs/xe_regs.h b/drivers/gpu/drm/xe/regs/xe_regs.h index 6cf282618836..3abb17d2ca33 100644 --- a/drivers/gpu/drm/xe/regs/xe_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_regs.h @@ -7,10 +7,6 @@ #include "regs/xe_reg_defs.h" -#define TIMESTAMP_OVERRIDE XE_REG(0x44074) -#define TIMESTAMP_OVERRIDE_US_COUNTER_DENOMINATOR_MASK REG_GENMASK(15, 12) -#define TIMESTAMP_OVERRIDE_US_COUNTER_DIVIDER_MASK REG_GENMASK(9, 0) - #define GU_CNTL_PROTECTED XE_REG(0x10100C) #define DRIVERINT_FLR_DIS REG_BIT(31) diff --git a/drivers/gpu/drm/xe/tests/xe_pci.c b/drivers/gpu/drm/xe/tests/xe_pci.c index 67404863087e..1d3e2e50c355 100644 --- a/drivers/gpu/drm/xe/tests/xe_pci.c +++ b/drivers/gpu/drm/xe/tests/xe_pci.c @@ -21,15 +21,15 @@ */ void xe_call_for_each_graphics_ip(xe_graphics_fn xe_fn) { - const struct xe_graphics_desc *ip, *last = NULL; + const struct xe_graphics_desc *desc, *last = NULL; - for (int i = 0; i < ARRAY_SIZE(graphics_ip_map); i++) { - ip = graphics_ip_map[i].ip; - if (ip == last) + for (int i = 0; i < ARRAY_SIZE(graphics_ips); i++) { + desc = graphics_ips[i].desc; + if (desc == last) continue; - xe_fn(ip); - last = ip; + xe_fn(desc); + last = desc; } } EXPORT_SYMBOL_IF_KUNIT(xe_call_for_each_graphics_ip); @@ -43,15 +43,15 @@ EXPORT_SYMBOL_IF_KUNIT(xe_call_for_each_graphics_ip); */ void xe_call_for_each_media_ip(xe_media_fn xe_fn) { - const struct xe_media_desc *ip, *last = NULL; + const struct xe_media_desc *desc, *last = NULL; - for (int i = 0; i < ARRAY_SIZE(media_ip_map); i++) { - ip = media_ip_map[i].ip; - if (ip == last) + for (int i = 0; i < ARRAY_SIZE(media_ips); i++) { + desc = media_ips[i].desc; + if (desc == last) continue; - xe_fn(ip); - last = ip; + xe_fn(desc); + last = desc; } } EXPORT_SYMBOL_IF_KUNIT(xe_call_for_each_media_ip); @@ -110,7 +110,7 @@ done: kunit_activate_static_stub(test, read_gmdid, fake_read_gmdid); xe_info_init_early(xe, desc, subplatform_desc); - xe_info_init(xe, desc->graphics, desc->media); + xe_info_init(xe, desc); return 0; } diff --git a/drivers/gpu/drm/xe/tests/xe_rtp_test.c b/drivers/gpu/drm/xe/tests/xe_rtp_test.c index 36a3b5420fef..b0254b014fe4 100644 --- a/drivers/gpu/drm/xe/tests/xe_rtp_test.c +++ b/drivers/gpu/drm/xe/tests/xe_rtp_test.c @@ -320,7 +320,7 @@ static void xe_rtp_process_to_sr_tests(struct kunit *test) count_rtp_entries++; xe_rtp_process_ctx_enable_active_tracking(&ctx, &active, count_rtp_entries); - xe_rtp_process_to_sr(&ctx, param->entries, reg_sr); + xe_rtp_process_to_sr(&ctx, param->entries, count_rtp_entries, reg_sr); xa_for_each(®_sr->xa, idx, sre) { if (idx == param->expected_reg.addr) diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index c21e6bca3141..64f9c936eea0 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -281,6 +281,8 @@ int xe_bo_placement_for_flags(struct xe_device *xe, struct xe_bo *bo, static void xe_evict_flags(struct ttm_buffer_object *tbo, struct ttm_placement *placement) { + struct xe_bo *bo; + if (!xe_bo_is_xe_bo(tbo)) { /* Don't handle scatter gather BOs */ if (tbo->type == ttm_bo_type_sg) { @@ -292,6 +294,12 @@ static void xe_evict_flags(struct ttm_buffer_object *tbo, return; } + bo = ttm_to_xe_bo(tbo); + if (bo->flags & XE_BO_FLAG_CPU_ADDR_MIRROR) { + *placement = sys_placement; + return; + } + /* * For xe, sg bos that are evicted to system just triggers a * rebind of the sg list upon subsequent validation to XE_PL_TT. @@ -789,6 +797,20 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, goto out; } + if (!move_lacks_source && (bo->flags & XE_BO_FLAG_CPU_ADDR_MIRROR) && + new_mem->mem_type == XE_PL_SYSTEM) { + ret = xe_svm_bo_evict(bo); + if (!ret) { + drm_dbg(&xe->drm, "Evict system allocator BO success\n"); + ttm_bo_move_null(ttm_bo, new_mem); + } else { + drm_dbg(&xe->drm, "Evict system allocator BO failed=%pe\n", + ERR_PTR(ret)); + } + + goto out; + } + if (old_mem_type == XE_PL_SYSTEM && new_mem->mem_type == XE_PL_TT && !handle_system_ccs) { ttm_bo_move_null(ttm_bo, new_mem); goto out; @@ -2441,6 +2463,7 @@ int xe_gem_create_ioctl(struct drm_device *dev, void *data, struct xe_file *xef = to_xe_file(file); struct drm_xe_gem_create *args = data; struct xe_vm *vm = NULL; + ktime_t end = 0; struct xe_bo *bo; unsigned int bo_flags; u32 handle; @@ -2512,6 +2535,10 @@ int xe_gem_create_ioctl(struct drm_device *dev, void *data, vm = xe_vm_lookup(xef, args->vm_id); if (XE_IOCTL_DBG(xe, !vm)) return -ENOENT; + } + +retry: + if (vm) { err = xe_vm_lock(vm, true); if (err) goto out_vm; @@ -2525,6 +2552,8 @@ int xe_gem_create_ioctl(struct drm_device *dev, void *data, if (IS_ERR(bo)) { err = PTR_ERR(bo); + if (xe_vm_validate_should_retry(NULL, err, &end)) + goto retry; goto out_vm; } @@ -2821,6 +2850,31 @@ void xe_bo_put_commit(struct llist_head *deferred) drm_gem_object_free(&bo->ttm.base.refcount); } +static void xe_bo_dev_work_func(struct work_struct *work) +{ + struct xe_bo_dev *bo_dev = container_of(work, typeof(*bo_dev), async_free); + + xe_bo_put_commit(&bo_dev->async_list); +} + +/** + * xe_bo_dev_init() - Initialize BO dev to manage async BO freeing + * @bo_dev: The BO dev structure + */ +void xe_bo_dev_init(struct xe_bo_dev *bo_dev) +{ + INIT_WORK(&bo_dev->async_free, xe_bo_dev_work_func); +} + +/** + * xe_bo_dev_fini() - Finalize BO dev managing async BO freeing + * @bo_dev: The BO dev structure + */ +void xe_bo_dev_fini(struct xe_bo_dev *bo_dev) +{ + flush_work(&bo_dev->async_free); +} + void xe_bo_put(struct xe_bo *bo) { struct xe_tile *tile; diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 2a7240c45511..bda3fdd408da 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -47,6 +47,7 @@ XE_BO_FLAG_GGTT1 | \ XE_BO_FLAG_GGTT2 | \ XE_BO_FLAG_GGTT3) +#define XE_BO_FLAG_CPU_ADDR_MIRROR BIT(22) /* this one is trigger internally only */ #define XE_BO_FLAG_INTERNAL_TEST BIT(30) @@ -345,6 +346,25 @@ xe_bo_put_deferred(struct xe_bo *bo, struct llist_head *deferred) void xe_bo_put_commit(struct llist_head *deferred); +/** + * xe_bo_put_async() - Put BO async + * @bo: The bo to put. + * + * Put BO async, the final put is deferred to a worker to exit an IRQ context. + */ +static inline void +xe_bo_put_async(struct xe_bo *bo) +{ + struct xe_bo_dev *bo_device = &xe_bo_device(bo)->bo_device; + + if (xe_bo_put_deferred(bo, &bo_device->async_list)) + schedule_work(&bo_device->async_free); +} + +void xe_bo_dev_init(struct xe_bo_dev *bo_device); + +void xe_bo_dev_fini(struct xe_bo_dev *bo_device); + struct sg_table *xe_bo_sg(struct xe_bo *bo); /* diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h index 60c522866500..15a92e3d4898 100644 --- a/drivers/gpu/drm/xe/xe_bo_types.h +++ b/drivers/gpu/drm/xe/xe_bo_types.h @@ -8,6 +8,7 @@ #include <linux/iosys-map.h> +#include <drm/drm_gpusvm.h> #include <drm/ttm/ttm_bo.h> #include <drm/ttm/ttm_device.h> #include <drm/ttm/ttm_placement.h> @@ -80,6 +81,9 @@ struct xe_bo { */ u16 cpu_caching; + /** @devmem_allocation: SVM device memory allocation */ + struct drm_gpusvm_devmem devmem_allocation; + /** @vram_userfault_link: Link into @mem_access.vram_userfault.list */ struct list_head vram_userfault_link; diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c index 39fe485d2085..81b9d9bb3f57 100644 --- a/drivers/gpu/drm/xe/xe_devcoredump.c +++ b/drivers/gpu/drm/xe/xe_devcoredump.c @@ -237,7 +237,7 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work) /* * NB: Despite passing a GFP_ flags parameter here, more allocations are done - * internally using GFP_KERNEL expliictly. Hence this call must be in the worker + * internally using GFP_KERNEL explicitly. Hence this call must be in the worker * thread and not in the initial capture call. */ dev_coredumpm_timeout(gt_to_xe(ss->gt)->drm.dev, THIS_MODULE, coredump, 0, GFP_KERNEL, @@ -423,11 +423,11 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char suffi if (size & 3) drm_printf(p, "Size not word aligned: %zu", size); if (offset & 3) - drm_printf(p, "Offset not word aligned: %zu", size); + drm_printf(p, "Offset not word aligned: %zu", offset); line_buff = kzalloc(DMESG_MAX_LINE_LEN, GFP_KERNEL); - if (IS_ERR_OR_NULL(line_buff)) { - drm_printf(p, "Failed to allocate line buffer: %pe", line_buff); + if (!line_buff) { + drm_printf(p, "Failed to allocate line buffer\n"); return; } diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 68ef12b57344..5d79b439dd62 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -54,7 +54,6 @@ #include "xe_query.h" #include "xe_shrinker.h" #include "xe_sriov.h" -#include "xe_survivability_mode.h" #include "xe_tile.h" #include "xe_ttm_stolen_mgr.h" #include "xe_ttm_sys_mgr.h" @@ -66,12 +65,6 @@ #include <generated/xe_wa_oob.h> -struct xe_device_remove_action { - struct list_head node; - void (*action)(void *); - void *data; -}; - static int xe_file_open(struct drm_device *dev, struct drm_file *file) { struct xe_device *xe = to_xe_device(dev); @@ -395,6 +388,8 @@ static void xe_device_destroy(struct drm_device *dev, void *dummy) { struct xe_device *xe = to_xe_device(dev); + xe_bo_dev_fini(&xe->bo_device); + if (xe->preempt_fence_wq) destroy_workqueue(xe->preempt_fence_wq); @@ -435,6 +430,7 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, if (WARN_ON(err)) goto err; + xe_bo_dev_init(&xe->bo_device); err = drmm_add_action_or_reset(&xe->drm, xe_device_destroy, NULL); if (err) goto err; @@ -675,7 +671,7 @@ static int wait_for_lmem_ready(struct xe_device *xe) } ALLOW_ERROR_INJECTION(wait_for_lmem_ready, ERRNO); /* See xe_pci_probe() */ -static void update_device_info(struct xe_device *xe) +static void sriov_update_device_info(struct xe_device *xe) { /* disable features that are not available/applicable to VFs */ if (IS_SRIOV_VF(xe)) { @@ -706,15 +702,11 @@ int xe_device_probe_early(struct xe_device *xe) xe_sriov_probe_early(xe); - update_device_info(xe); + sriov_update_device_info(xe); err = xe_pcode_probe_early(xe); - if (err) { - if (xe_survivability_mode_required(xe)) - xe_survivability_mode_init(xe); - + if (err) return err; - } err = wait_for_lmem_ready(xe); if (err) @@ -760,9 +752,6 @@ int xe_device_probe(struct xe_device *xe) int err; u8 id; - xe->probing = true; - INIT_LIST_HEAD(&xe->remove_action_list); - xe_pat_init_early(xe); err = xe_sriov_init(xe); @@ -770,6 +759,7 @@ int xe_device_probe(struct xe_device *xe) return err; xe->info.mem_region_mask = 1; + err = xe_set_dma_info(xe); if (err) return err; @@ -778,7 +768,9 @@ int xe_device_probe(struct xe_device *xe) if (err) return err; - xe_ttm_sys_mgr_init(xe); + err = xe_ttm_sys_mgr_init(xe); + if (err) + return err; for_each_gt(gt, xe, id) { err = xe_gt_init_early(gt); @@ -873,7 +865,9 @@ int xe_device_probe(struct xe_device *xe) return err; } - xe_heci_gsc_init(xe); + err = xe_heci_gsc_init(xe); + if (err) + return err; err = xe_oa_init(xe); if (err) @@ -885,11 +879,11 @@ int xe_device_probe(struct xe_device *xe) err = xe_pxp_init(xe); if (err) - goto err_remove_display; + return err; err = drm_dev_register(&xe->drm, 0); if (err) - goto err_remove_display; + return err; xe_display_register(xe); @@ -912,84 +906,19 @@ int xe_device_probe(struct xe_device *xe) xe_vsec_init(xe); - xe->probing = false; - return devm_add_action_or_reset(xe->drm.dev, xe_device_sanitize, xe); err_unregister_display: xe_display_unregister(xe); -err_remove_display: - xe_display_driver_remove(xe); return err; } -/** - * xe_device_call_remove_actions - Call the remove actions - * @xe: xe device instance - * - * This is only to be used by xe_pci and xe_device to call the remove actions - * while removing the driver or handling probe failures. - */ -void xe_device_call_remove_actions(struct xe_device *xe) -{ - struct xe_device_remove_action *ra, *tmp; - - list_for_each_entry_safe(ra, tmp, &xe->remove_action_list, node) { - ra->action(ra->data); - list_del(&ra->node); - kfree(ra); - } - - xe->probing = false; -} - -/** - * xe_device_add_action_or_reset - Add an action to run on driver removal - * @xe: xe device instance - * @action: Function that should be called on device remove - * @data: Pointer to data passed to @action implementation - * - * This adds a custom action to the list of remove callbacks executed on device - * remove, before any dev or drm managed resources are removed. This is only - * needed if the action leads to component_del()/component_master_del() since - * that is not compatible with devres cleanup. - * - * Returns: 0 on success or a negative error code on failure, in which case - * @action is already called. - */ -int xe_device_add_action_or_reset(struct xe_device *xe, - void (*action)(void *), void *data) -{ - struct xe_device_remove_action *ra; - - drm_WARN_ON(&xe->drm, !xe->probing); - - ra = kmalloc(sizeof(*ra), GFP_KERNEL); - if (!ra) { - action(data); - return -ENOMEM; - } - - INIT_LIST_HEAD(&ra->node); - ra->action = action; - ra->data = data; - list_add(&ra->node, &xe->remove_action_list); - - return 0; -} - void xe_device_remove(struct xe_device *xe) { xe_display_unregister(xe); drm_dev_unplug(&xe->drm); - - xe_display_driver_remove(xe); - - xe_heci_gsc_fini(xe); - - xe_device_call_remove_actions(xe); } void xe_device_shutdown(struct xe_device *xe) diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h index 079dad32a6f5..0bc3bc8e6803 100644 --- a/drivers/gpu/drm/xe/xe_device.h +++ b/drivers/gpu/drm/xe/xe_device.h @@ -45,9 +45,6 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, const struct pci_device_id *ent); int xe_device_probe_early(struct xe_device *xe); int xe_device_probe(struct xe_device *xe); -int xe_device_add_action_or_reset(struct xe_device *xe, - void (*action)(void *), void *data); -void xe_device_call_remove_actions(struct xe_device *xe); void xe_device_remove(struct xe_device *xe); void xe_device_shutdown(struct xe_device *xe); diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.c b/drivers/gpu/drm/xe/xe_device_sysfs.c index 7375937934fa..7efbd4c52791 100644 --- a/drivers/gpu/drm/xe/xe_device_sysfs.c +++ b/drivers/gpu/drm/xe/xe_device_sysfs.c @@ -32,9 +32,6 @@ vram_d3cold_threshold_show(struct device *dev, struct xe_device *xe = pdev_to_xe_device(pdev); int ret; - if (!xe) - return -EINVAL; - xe_pm_runtime_get(xe); ret = sysfs_emit(buf, "%d\n", xe->d3cold.vram_threshold); xe_pm_runtime_put(xe); @@ -51,9 +48,6 @@ vram_d3cold_threshold_store(struct device *dev, struct device_attribute *attr, u32 vram_d3cold_threshold; int ret; - if (!xe) - return -EINVAL; - ret = kstrtou32(buff, 0, &vram_d3cold_threshold); if (ret) return ret; diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index e312595dda7e..72ef0b6fc425 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -10,6 +10,7 @@ #include <drm/drm_device.h> #include <drm/drm_file.h> +#include <drm/drm_pagemap.h> #include <drm/ttm/ttm_device.h> #include "xe_devcoredump_types.h" @@ -106,6 +107,19 @@ struct xe_vram_region { resource_size_t actual_physical_size; /** @mapping: pointer to VRAM mappable space */ void __iomem *mapping; + /** @pagemap: Used to remap device memory as ZONE_DEVICE */ + struct dev_pagemap pagemap; + /** + * @dpagemap: The struct drm_pagemap of the ZONE_DEVICE memory + * pages of this tile. + */ + struct drm_pagemap dpagemap; + /** + * @hpa_base: base host physical address + * + * This is generated when remap device memory as ZONE_DEVICE + */ + resource_size_t hpa_base; /** @ttm: VRAM TTM manager */ struct xe_ttm_vram_mgr ttm; }; @@ -431,20 +445,6 @@ struct xe_device { struct xe_tile tiles[XE_MAX_TILES_PER_DEVICE]; /** - * @remove_action_list: list of actions to execute on device remove. - * Use xe_device_add_remove_action() for that. Actions can only be added - * during probe and are executed during the call from PCI subsystem to - * remove the driver from the device. - */ - struct list_head remove_action_list; - - /** - * @probing: cover the section in which @remove_action_list can be used - * to post cleaning actions - */ - bool probing; - - /** * @mem_access: keep track of memory access in the device, possibly * triggering additional actions when they occur. */ @@ -541,6 +541,14 @@ struct xe_device { int mode; } wedged; + /** @bo_device: Struct to control async free of BOs */ + struct xe_bo_dev { + /** @bo_device.async_free: Free worker */ + struct work_struct async_free; + /** @bo_device.async_list: List of BOs to be freed */ + struct llist_head async_list; + } bo_device; + /** @pmu: performance monitoring unit */ struct xe_pmu pmu; diff --git a/drivers/gpu/drm/xe/xe_eu_stall.c b/drivers/gpu/drm/xe/xe_eu_stall.c new file mode 100644 index 000000000000..88a92baf5c95 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_eu_stall.c @@ -0,0 +1,960 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2025 Intel Corporation + */ + +#include <linux/anon_inodes.h> +#include <linux/fs.h> +#include <linux/poll.h> +#include <linux/types.h> + +#include <drm/drm_drv.h> +#include <generated/xe_wa_oob.h> +#include <uapi/drm/xe_drm.h> + +#include "xe_bo.h" +#include "xe_device.h" +#include "xe_eu_stall.h" +#include "xe_force_wake.h" +#include "xe_gt_mcr.h" +#include "xe_gt_printk.h" +#include "xe_gt_topology.h" +#include "xe_macros.h" +#include "xe_observation.h" +#include "xe_pm.h" +#include "xe_trace.h" +#include "xe_wa.h" + +#include "regs/xe_eu_stall_regs.h" +#include "regs/xe_gt_regs.h" + +#define POLL_PERIOD_MS 5 + +static size_t per_xecore_buf_size = SZ_512K; + +struct per_xecore_buf { + /* Buffer vaddr */ + u8 *vaddr; + /* Write pointer */ + u32 write; + /* Read pointer */ + u32 read; +}; + +struct xe_eu_stall_data_stream { + bool pollin; + bool enabled; + int wait_num_reports; + int sampling_rate_mult; + wait_queue_head_t poll_wq; + size_t data_record_size; + size_t per_xecore_buf_size; + + struct xe_gt *gt; + struct xe_bo *bo; + struct per_xecore_buf *xecore_buf; + struct { + bool reported_to_user; + xe_dss_mask_t mask; + } data_drop; + struct delayed_work buf_poll_work; +}; + +struct xe_eu_stall_gt { + /* Lock to protect stream */ + struct mutex stream_lock; + /* EU stall data stream */ + struct xe_eu_stall_data_stream *stream; + /* Workqueue to schedule buffer pointers polling work */ + struct workqueue_struct *buf_ptr_poll_wq; +}; + +/** + * struct eu_stall_open_properties - EU stall sampling properties received + * from user space at open. + * @sampling_rate_mult: EU stall sampling rate multiplier. + * HW will sample every (sampling_rate_mult x 251) cycles. + * @wait_num_reports: Minimum number of EU stall data reports to unblock poll(). + * @gt: GT on which EU stall data will be captured. + */ +struct eu_stall_open_properties { + int sampling_rate_mult; + int wait_num_reports; + struct xe_gt *gt; +}; + +/* + * EU stall data format for PVC + */ +struct xe_eu_stall_data_pvc { + __u64 ip_addr:29; /* Bits 0 to 28 */ + __u64 active_count:8; /* Bits 29 to 36 */ + __u64 other_count:8; /* Bits 37 to 44 */ + __u64 control_count:8; /* Bits 45 to 52 */ + __u64 pipestall_count:8; /* Bits 53 to 60 */ + __u64 send_count:8; /* Bits 61 to 68 */ + __u64 dist_acc_count:8; /* Bits 69 to 76 */ + __u64 sbid_count:8; /* Bits 77 to 84 */ + __u64 sync_count:8; /* Bits 85 to 92 */ + __u64 inst_fetch_count:8; /* Bits 93 to 100 */ + __u64 unused_bits:27; + __u64 unused[6]; +} __packed; + +/* + * EU stall data format for Xe2 arch GPUs (LNL, BMG). + */ +struct xe_eu_stall_data_xe2 { + __u64 ip_addr:29; /* Bits 0 to 28 */ + __u64 tdr_count:8; /* Bits 29 to 36 */ + __u64 other_count:8; /* Bits 37 to 44 */ + __u64 control_count:8; /* Bits 45 to 52 */ + __u64 pipestall_count:8; /* Bits 53 to 60 */ + __u64 send_count:8; /* Bits 61 to 68 */ + __u64 dist_acc_count:8; /* Bits 69 to 76 */ + __u64 sbid_count:8; /* Bits 77 to 84 */ + __u64 sync_count:8; /* Bits 85 to 92 */ + __u64 inst_fetch_count:8; /* Bits 93 to 100 */ + __u64 active_count:8; /* Bits 101 to 108 */ + __u64 ex_id:3; /* Bits 109 to 111 */ + __u64 end_flag:1; /* Bit 112 */ + __u64 unused_bits:15; + __u64 unused[6]; +} __packed; + +const u64 eu_stall_sampling_rates[] = {251, 251 * 2, 251 * 3, 251 * 4, 251 * 5, 251 * 6, 251 * 7}; + +/** + * xe_eu_stall_get_sampling_rates - get EU stall sampling rates information. + * + * @num_rates: Pointer to a u32 to return the number of sampling rates. + * @rates: double u64 pointer to point to an array of sampling rates. + * + * Stores the number of sampling rates and pointer to the array of + * sampling rates in the input pointers. + * + * Returns: Size of the EU stall sampling rates array. + */ +size_t xe_eu_stall_get_sampling_rates(u32 *num_rates, const u64 **rates) +{ + *num_rates = ARRAY_SIZE(eu_stall_sampling_rates); + *rates = eu_stall_sampling_rates; + + return sizeof(eu_stall_sampling_rates); +} + +/** + * xe_eu_stall_get_per_xecore_buf_size - get per XeCore buffer size. + * + * Returns: The per XeCore buffer size used to allocate the per GT + * EU stall data buffer. + */ +size_t xe_eu_stall_get_per_xecore_buf_size(void) +{ + return per_xecore_buf_size; +} + +/** + * xe_eu_stall_data_record_size - get EU stall data record size. + * + * @xe: Pointer to a Xe device. + * + * Returns: EU stall data record size. + */ +size_t xe_eu_stall_data_record_size(struct xe_device *xe) +{ + size_t record_size = 0; + + if (xe->info.platform == XE_PVC) + record_size = sizeof(struct xe_eu_stall_data_pvc); + else if (GRAPHICS_VER(xe) >= 20) + record_size = sizeof(struct xe_eu_stall_data_xe2); + + xe_assert(xe, is_power_of_2(record_size)); + + return record_size; +} + +/** + * num_data_rows - Return the number of EU stall data rows of 64B each + * for a given data size. + * + * @data_size: EU stall data size + */ +static u32 num_data_rows(u32 data_size) +{ + return data_size >> 6; +} + +static void xe_eu_stall_fini(void *arg) +{ + struct xe_gt *gt = arg; + + destroy_workqueue(gt->eu_stall->buf_ptr_poll_wq); + mutex_destroy(>->eu_stall->stream_lock); + kfree(gt->eu_stall); +} + +/** + * xe_eu_stall_init() - Allocate and initialize GT level EU stall data + * structure xe_eu_stall_gt within struct xe_gt. + * + * @gt: GT being initialized. + * + * Returns: zero on success or a negative error code. + */ +int xe_eu_stall_init(struct xe_gt *gt) +{ + struct xe_device *xe = gt_to_xe(gt); + int ret; + + gt->eu_stall = kzalloc(sizeof(*gt->eu_stall), GFP_KERNEL); + if (!gt->eu_stall) { + ret = -ENOMEM; + goto exit; + } + + mutex_init(>->eu_stall->stream_lock); + + gt->eu_stall->buf_ptr_poll_wq = alloc_ordered_workqueue("xe_eu_stall", 0); + if (!gt->eu_stall->buf_ptr_poll_wq) { + ret = -ENOMEM; + goto exit_free; + } + + ret = devm_add_action_or_reset(xe->drm.dev, xe_eu_stall_fini, gt); + if (ret) + goto exit_destroy; + + return 0; +exit_destroy: + destroy_workqueue(gt->eu_stall->buf_ptr_poll_wq); +exit_free: + mutex_destroy(>->eu_stall->stream_lock); + kfree(gt->eu_stall); +exit: + return ret; +} + +static int set_prop_eu_stall_sampling_rate(struct xe_device *xe, u64 value, + struct eu_stall_open_properties *props) +{ + value = div_u64(value, 251); + if (value == 0 || value > 7) { + drm_dbg(&xe->drm, "Invalid EU stall sampling rate %llu\n", value); + return -EINVAL; + } + props->sampling_rate_mult = value; + return 0; +} + +static int set_prop_eu_stall_wait_num_reports(struct xe_device *xe, u64 value, + struct eu_stall_open_properties *props) +{ + props->wait_num_reports = value; + + return 0; +} + +static int set_prop_eu_stall_gt_id(struct xe_device *xe, u64 value, + struct eu_stall_open_properties *props) +{ + if (value >= xe->info.gt_count) { + drm_dbg(&xe->drm, "Invalid GT ID %llu for EU stall sampling\n", value); + return -EINVAL; + } + props->gt = xe_device_get_gt(xe, value); + return 0; +} + +typedef int (*set_eu_stall_property_fn)(struct xe_device *xe, u64 value, + struct eu_stall_open_properties *props); + +static const set_eu_stall_property_fn xe_set_eu_stall_property_funcs[] = { + [DRM_XE_EU_STALL_PROP_SAMPLE_RATE] = set_prop_eu_stall_sampling_rate, + [DRM_XE_EU_STALL_PROP_WAIT_NUM_REPORTS] = set_prop_eu_stall_wait_num_reports, + [DRM_XE_EU_STALL_PROP_GT_ID] = set_prop_eu_stall_gt_id, +}; + +static int xe_eu_stall_user_ext_set_property(struct xe_device *xe, u64 extension, + struct eu_stall_open_properties *props) +{ + u64 __user *address = u64_to_user_ptr(extension); + struct drm_xe_ext_set_property ext; + int err; + u32 idx; + + err = __copy_from_user(&ext, address, sizeof(ext)); + if (XE_IOCTL_DBG(xe, err)) + return -EFAULT; + + if (XE_IOCTL_DBG(xe, ext.property >= ARRAY_SIZE(xe_set_eu_stall_property_funcs)) || + XE_IOCTL_DBG(xe, ext.pad)) + return -EINVAL; + + idx = array_index_nospec(ext.property, ARRAY_SIZE(xe_set_eu_stall_property_funcs)); + return xe_set_eu_stall_property_funcs[idx](xe, ext.value, props); +} + +typedef int (*xe_eu_stall_user_extension_fn)(struct xe_device *xe, u64 extension, + struct eu_stall_open_properties *props); +static const xe_eu_stall_user_extension_fn xe_eu_stall_user_extension_funcs[] = { + [DRM_XE_EU_STALL_EXTENSION_SET_PROPERTY] = xe_eu_stall_user_ext_set_property, +}; + +#define MAX_USER_EXTENSIONS 5 +static int xe_eu_stall_user_extensions(struct xe_device *xe, u64 extension, + int ext_number, struct eu_stall_open_properties *props) +{ + u64 __user *address = u64_to_user_ptr(extension); + struct drm_xe_user_extension ext; + int err; + u32 idx; + + if (XE_IOCTL_DBG(xe, ext_number >= MAX_USER_EXTENSIONS)) + return -E2BIG; + + err = __copy_from_user(&ext, address, sizeof(ext)); + if (XE_IOCTL_DBG(xe, err)) + return -EFAULT; + + if (XE_IOCTL_DBG(xe, ext.pad) || + XE_IOCTL_DBG(xe, ext.name >= ARRAY_SIZE(xe_eu_stall_user_extension_funcs))) + return -EINVAL; + + idx = array_index_nospec(ext.name, ARRAY_SIZE(xe_eu_stall_user_extension_funcs)); + err = xe_eu_stall_user_extension_funcs[idx](xe, extension, props); + if (XE_IOCTL_DBG(xe, err)) + return err; + + if (ext.next_extension) + return xe_eu_stall_user_extensions(xe, ext.next_extension, ++ext_number, props); + + return 0; +} + +/** + * buf_data_size - Calculate the number of bytes in a circular buffer + * given the read and write pointers and the size of + * the buffer. + * + * @buf_size: Size of the circular buffer + * @read_ptr: Read pointer with an additional overflow bit + * @write_ptr: Write pointer with an additional overflow bit + * + * Since the read and write pointers have an additional overflow bit, + * this function calculates the offsets from the pointers and use the + * offsets to calculate the data size in the buffer. + * + * Returns: number of bytes of data in the buffer + */ +static u32 buf_data_size(size_t buf_size, u32 read_ptr, u32 write_ptr) +{ + u32 read_offset, write_offset, size = 0; + + if (read_ptr == write_ptr) + goto exit; + + read_offset = read_ptr & (buf_size - 1); + write_offset = write_ptr & (buf_size - 1); + + if (write_offset > read_offset) + size = write_offset - read_offset; + else + size = buf_size - read_offset + write_offset; +exit: + return size; +} + +/** + * eu_stall_data_buf_poll - Poll for EU stall data in the buffer. + * + * @stream: xe EU stall data stream instance + * + * Returns: true if the EU stall buffer contains minimum stall data as + * specified by the event report count, else false. + */ +static bool eu_stall_data_buf_poll(struct xe_eu_stall_data_stream *stream) +{ + u32 read_ptr, write_ptr_reg, write_ptr, total_data = 0; + u32 buf_size = stream->per_xecore_buf_size; + struct per_xecore_buf *xecore_buf; + struct xe_gt *gt = stream->gt; + bool min_data_present = false; + u16 group, instance; + unsigned int xecore; + + mutex_lock(>->eu_stall->stream_lock); + for_each_dss_steering(xecore, gt, group, instance) { + xecore_buf = &stream->xecore_buf[xecore]; + read_ptr = xecore_buf->read; + write_ptr_reg = xe_gt_mcr_unicast_read(gt, XEHPC_EUSTALL_REPORT, + group, instance); + write_ptr = REG_FIELD_GET(XEHPC_EUSTALL_REPORT_WRITE_PTR_MASK, write_ptr_reg); + write_ptr <<= 6; + write_ptr &= ((buf_size << 1) - 1); + if (!min_data_present) { + total_data += buf_data_size(buf_size, read_ptr, write_ptr); + if (num_data_rows(total_data) >= stream->wait_num_reports) + min_data_present = true; + } + if (write_ptr_reg & XEHPC_EUSTALL_REPORT_OVERFLOW_DROP) + set_bit(xecore, stream->data_drop.mask); + xecore_buf->write = write_ptr; + } + mutex_unlock(>->eu_stall->stream_lock); + + return min_data_present; +} + +static void clear_dropped_eviction_line_bit(struct xe_gt *gt, u16 group, u16 instance) +{ + struct xe_device *xe = gt_to_xe(gt); + u32 write_ptr_reg; + + /* On PVC, the overflow bit has to be cleared by writing 1 to it. + * On Xe2 and later GPUs, the bit has to be cleared by writing 0 to it. + */ + if (GRAPHICS_VER(xe) >= 20) + write_ptr_reg = _MASKED_BIT_DISABLE(XEHPC_EUSTALL_REPORT_OVERFLOW_DROP); + else + write_ptr_reg = _MASKED_BIT_ENABLE(XEHPC_EUSTALL_REPORT_OVERFLOW_DROP); + + xe_gt_mcr_unicast_write(gt, XEHPC_EUSTALL_REPORT, write_ptr_reg, group, instance); +} + +static int xe_eu_stall_data_buf_read(struct xe_eu_stall_data_stream *stream, + char __user *buf, size_t count, + size_t *total_data_size, struct xe_gt *gt, + u16 group, u16 instance, unsigned int xecore) +{ + size_t read_data_size, copy_size, buf_size; + u32 read_ptr_reg, read_ptr, write_ptr; + u8 *xecore_start_vaddr, *read_vaddr; + struct per_xecore_buf *xecore_buf; + u32 read_offset, write_offset; + + /* Hardware increments the read and write pointers such that they can + * overflow into one additional bit. For example, a 256KB size buffer + * offset pointer needs 18 bits. But HW uses 19 bits for the read and + * write pointers. This technique avoids wasting a slot in the buffer. + * Read and write offsets are calculated from the pointers in order to + * check if the write pointer has wrapped around the array. + */ + xecore_buf = &stream->xecore_buf[xecore]; + xecore_start_vaddr = xecore_buf->vaddr; + read_ptr = xecore_buf->read; + write_ptr = xecore_buf->write; + buf_size = stream->per_xecore_buf_size; + + read_data_size = buf_data_size(buf_size, read_ptr, write_ptr); + /* Read only the data that the user space buffer can accommodate */ + read_data_size = min_t(size_t, count - *total_data_size, read_data_size); + if (read_data_size == 0) + goto exit_drop; + + read_offset = read_ptr & (buf_size - 1); + write_offset = write_ptr & (buf_size - 1); + read_vaddr = xecore_start_vaddr + read_offset; + + if (write_offset > read_offset) { + if (copy_to_user(buf + *total_data_size, read_vaddr, read_data_size)) + return -EFAULT; + } else { + if (read_data_size >= buf_size - read_offset) + copy_size = buf_size - read_offset; + else + copy_size = read_data_size; + if (copy_to_user(buf + *total_data_size, read_vaddr, copy_size)) + return -EFAULT; + if (copy_to_user(buf + *total_data_size + copy_size, + xecore_start_vaddr, read_data_size - copy_size)) + return -EFAULT; + } + + *total_data_size += read_data_size; + read_ptr += read_data_size; + + /* Read pointer can overflow into one additional bit */ + read_ptr &= (buf_size << 1) - 1; + read_ptr_reg = REG_FIELD_PREP(XEHPC_EUSTALL_REPORT1_READ_PTR_MASK, (read_ptr >> 6)); + read_ptr_reg = _MASKED_FIELD(XEHPC_EUSTALL_REPORT1_READ_PTR_MASK, read_ptr_reg); + xe_gt_mcr_unicast_write(gt, XEHPC_EUSTALL_REPORT1, read_ptr_reg, group, instance); + xecore_buf->read = read_ptr; + trace_xe_eu_stall_data_read(group, instance, read_ptr, write_ptr, + read_data_size, *total_data_size); +exit_drop: + /* Clear drop bit (if set) after any data was read or if the buffer was empty. + * Drop bit can be set even if the buffer is empty as the buffer may have been emptied + * in the previous read() and the data drop bit was set during the previous read(). + */ + if (test_bit(xecore, stream->data_drop.mask)) { + clear_dropped_eviction_line_bit(gt, group, instance); + clear_bit(xecore, stream->data_drop.mask); + } + return 0; +} + +/** + * xe_eu_stall_stream_read_locked - copy EU stall counters data from the + * per xecore buffers to the userspace buffer + * @stream: A stream opened for EU stall count metrics + * @file: An xe EU stall data stream file + * @buf: destination buffer given by userspace + * @count: the number of bytes userspace wants to read + * + * Returns: Number of bytes copied or a negative error code + * If we've successfully copied any data then reporting that takes + * precedence over any internal error status, so the data isn't lost. + */ +static ssize_t xe_eu_stall_stream_read_locked(struct xe_eu_stall_data_stream *stream, + struct file *file, char __user *buf, + size_t count) +{ + struct xe_gt *gt = stream->gt; + size_t total_size = 0; + u16 group, instance; + unsigned int xecore; + int ret = 0; + + if (bitmap_weight(stream->data_drop.mask, XE_MAX_DSS_FUSE_BITS)) { + if (!stream->data_drop.reported_to_user) { + stream->data_drop.reported_to_user = true; + xe_gt_dbg(gt, "EU stall data dropped in XeCores: %*pb\n", + XE_MAX_DSS_FUSE_BITS, stream->data_drop.mask); + return -EIO; + } + stream->data_drop.reported_to_user = false; + } + + for_each_dss_steering(xecore, gt, group, instance) { + ret = xe_eu_stall_data_buf_read(stream, buf, count, &total_size, + gt, group, instance, xecore); + if (ret || count == total_size) + break; + } + return total_size ?: (ret ?: -EAGAIN); +} + +/* + * Userspace must enable the EU stall stream with DRM_XE_OBSERVATION_IOCTL_ENABLE + * before calling read(). + * + * Returns: The number of bytes copied or a negative error code on failure. + * -EIO if HW drops any EU stall data when the buffer is full. + */ +static ssize_t xe_eu_stall_stream_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct xe_eu_stall_data_stream *stream = file->private_data; + struct xe_gt *gt = stream->gt; + ssize_t ret, aligned_count; + + aligned_count = ALIGN_DOWN(count, stream->data_record_size); + if (aligned_count == 0) + return -EINVAL; + + if (!stream->enabled) { + xe_gt_dbg(gt, "EU stall data stream not enabled to read\n"); + return -EINVAL; + } + + if (!(file->f_flags & O_NONBLOCK)) { + do { + ret = wait_event_interruptible(stream->poll_wq, stream->pollin); + if (ret) + return -EINTR; + + mutex_lock(>->eu_stall->stream_lock); + ret = xe_eu_stall_stream_read_locked(stream, file, buf, aligned_count); + mutex_unlock(>->eu_stall->stream_lock); + } while (ret == -EAGAIN); + } else { + mutex_lock(>->eu_stall->stream_lock); + ret = xe_eu_stall_stream_read_locked(stream, file, buf, aligned_count); + mutex_unlock(>->eu_stall->stream_lock); + } + + /* + * This may not work correctly if the user buffer is very small. + * We don't want to block the next read() when there is data in the buffer + * now, but couldn't be accommodated in the small user buffer. + */ + stream->pollin = false; + + return ret; +} + +static void xe_eu_stall_stream_free(struct xe_eu_stall_data_stream *stream) +{ + struct xe_gt *gt = stream->gt; + + gt->eu_stall->stream = NULL; + kfree(stream); +} + +static void xe_eu_stall_data_buf_destroy(struct xe_eu_stall_data_stream *stream) +{ + xe_bo_unpin_map_no_vm(stream->bo); + kfree(stream->xecore_buf); +} + +static int xe_eu_stall_data_buf_alloc(struct xe_eu_stall_data_stream *stream, + u16 last_xecore) +{ + struct xe_tile *tile = stream->gt->tile; + struct xe_bo *bo; + u32 size; + + stream->xecore_buf = kcalloc(last_xecore, sizeof(*stream->xecore_buf), GFP_KERNEL); + if (!stream->xecore_buf) + return -ENOMEM; + + size = stream->per_xecore_buf_size * last_xecore; + + bo = xe_bo_create_pin_map_at_aligned(tile->xe, tile, NULL, + size, ~0ull, ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | XE_BO_FLAG_GGTT, SZ_64); + if (IS_ERR(bo)) { + kfree(stream->xecore_buf); + return PTR_ERR(bo); + } + + XE_WARN_ON(!IS_ALIGNED(xe_bo_ggtt_addr(bo), SZ_64)); + stream->bo = bo; + + return 0; +} + +static int xe_eu_stall_stream_enable(struct xe_eu_stall_data_stream *stream) +{ + u32 write_ptr_reg, write_ptr, read_ptr_reg, reg_value; + struct per_xecore_buf *xecore_buf; + struct xe_gt *gt = stream->gt; + u16 group, instance; + unsigned int fw_ref; + int xecore; + + /* Take runtime pm ref and forcewake to disable RC6 */ + xe_pm_runtime_get(gt_to_xe(gt)); + fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_RENDER); + if (!xe_force_wake_ref_has_domain(fw_ref, XE_FW_RENDER)) { + xe_gt_err(gt, "Failed to get RENDER forcewake\n"); + xe_pm_runtime_put(gt_to_xe(gt)); + return -ETIMEDOUT; + } + + if (XE_WA(gt, 22016596838)) + xe_gt_mcr_multicast_write(gt, ROW_CHICKEN2, + _MASKED_BIT_ENABLE(DISABLE_DOP_GATING)); + + for_each_dss_steering(xecore, gt, group, instance) { + write_ptr_reg = xe_gt_mcr_unicast_read(gt, XEHPC_EUSTALL_REPORT, group, instance); + /* Clear any drop bits set and not cleared in the previous session. */ + if (write_ptr_reg & XEHPC_EUSTALL_REPORT_OVERFLOW_DROP) + clear_dropped_eviction_line_bit(gt, group, instance); + write_ptr = REG_FIELD_GET(XEHPC_EUSTALL_REPORT_WRITE_PTR_MASK, write_ptr_reg); + read_ptr_reg = REG_FIELD_PREP(XEHPC_EUSTALL_REPORT1_READ_PTR_MASK, write_ptr); + read_ptr_reg = _MASKED_FIELD(XEHPC_EUSTALL_REPORT1_READ_PTR_MASK, read_ptr_reg); + /* Initialize the read pointer to the write pointer */ + xe_gt_mcr_unicast_write(gt, XEHPC_EUSTALL_REPORT1, read_ptr_reg, group, instance); + write_ptr <<= 6; + write_ptr &= (stream->per_xecore_buf_size << 1) - 1; + xecore_buf = &stream->xecore_buf[xecore]; + xecore_buf->write = write_ptr; + xecore_buf->read = write_ptr; + } + stream->data_drop.reported_to_user = false; + bitmap_zero(stream->data_drop.mask, XE_MAX_DSS_FUSE_BITS); + + reg_value = _MASKED_FIELD(EUSTALL_MOCS | EUSTALL_SAMPLE_RATE, + REG_FIELD_PREP(EUSTALL_MOCS, gt->mocs.uc_index << 1) | + REG_FIELD_PREP(EUSTALL_SAMPLE_RATE, + stream->sampling_rate_mult)); + xe_gt_mcr_multicast_write(gt, XEHPC_EUSTALL_CTRL, reg_value); + /* GGTT addresses can never be > 32 bits */ + xe_gt_mcr_multicast_write(gt, XEHPC_EUSTALL_BASE_UPPER, 0); + reg_value = xe_bo_ggtt_addr(stream->bo); + reg_value |= REG_FIELD_PREP(XEHPC_EUSTALL_BASE_XECORE_BUF_SZ, + stream->per_xecore_buf_size / SZ_256K); + reg_value |= XEHPC_EUSTALL_BASE_ENABLE_SAMPLING; + xe_gt_mcr_multicast_write(gt, XEHPC_EUSTALL_BASE, reg_value); + + return 0; +} + +static void eu_stall_data_buf_poll_work_fn(struct work_struct *work) +{ + struct xe_eu_stall_data_stream *stream = + container_of(work, typeof(*stream), buf_poll_work.work); + struct xe_gt *gt = stream->gt; + + if (eu_stall_data_buf_poll(stream)) { + stream->pollin = true; + wake_up(&stream->poll_wq); + } + queue_delayed_work(gt->eu_stall->buf_ptr_poll_wq, + &stream->buf_poll_work, + msecs_to_jiffies(POLL_PERIOD_MS)); +} + +static int xe_eu_stall_stream_init(struct xe_eu_stall_data_stream *stream, + struct eu_stall_open_properties *props) +{ + unsigned int max_wait_num_reports, xecore, last_xecore, num_xecores; + struct per_xecore_buf *xecore_buf; + struct xe_gt *gt = stream->gt; + xe_dss_mask_t all_xecores; + u16 group, instance; + u32 vaddr_offset; + int ret; + + bitmap_or(all_xecores, gt->fuse_topo.g_dss_mask, gt->fuse_topo.c_dss_mask, + XE_MAX_DSS_FUSE_BITS); + num_xecores = bitmap_weight(all_xecores, XE_MAX_DSS_FUSE_BITS); + last_xecore = xe_gt_topology_mask_last_dss(all_xecores) + 1; + + max_wait_num_reports = num_data_rows(per_xecore_buf_size * num_xecores); + if (props->wait_num_reports == 0 || props->wait_num_reports > max_wait_num_reports) { + xe_gt_dbg(gt, "Invalid EU stall event report count %u\n", + props->wait_num_reports); + xe_gt_dbg(gt, "Minimum event report count is 1, maximum is %u\n", + max_wait_num_reports); + return -EINVAL; + } + + init_waitqueue_head(&stream->poll_wq); + INIT_DELAYED_WORK(&stream->buf_poll_work, eu_stall_data_buf_poll_work_fn); + stream->per_xecore_buf_size = per_xecore_buf_size; + stream->sampling_rate_mult = props->sampling_rate_mult; + stream->wait_num_reports = props->wait_num_reports; + stream->data_record_size = xe_eu_stall_data_record_size(gt_to_xe(gt)); + + ret = xe_eu_stall_data_buf_alloc(stream, last_xecore); + if (ret) + return ret; + + for_each_dss_steering(xecore, gt, group, instance) { + xecore_buf = &stream->xecore_buf[xecore]; + vaddr_offset = xecore * stream->per_xecore_buf_size; + xecore_buf->vaddr = stream->bo->vmap.vaddr + vaddr_offset; + } + return 0; +} + +static __poll_t xe_eu_stall_stream_poll_locked(struct xe_eu_stall_data_stream *stream, + struct file *file, poll_table *wait) +{ + __poll_t events = 0; + + poll_wait(file, &stream->poll_wq, wait); + + if (stream->pollin) + events |= EPOLLIN; + + return events; +} + +static __poll_t xe_eu_stall_stream_poll(struct file *file, poll_table *wait) +{ + struct xe_eu_stall_data_stream *stream = file->private_data; + struct xe_gt *gt = stream->gt; + __poll_t ret; + + mutex_lock(>->eu_stall->stream_lock); + ret = xe_eu_stall_stream_poll_locked(stream, file, wait); + mutex_unlock(>->eu_stall->stream_lock); + + return ret; +} + +static int xe_eu_stall_enable_locked(struct xe_eu_stall_data_stream *stream) +{ + struct xe_gt *gt = stream->gt; + int ret = 0; + + if (stream->enabled) + return ret; + + stream->enabled = true; + + ret = xe_eu_stall_stream_enable(stream); + + queue_delayed_work(gt->eu_stall->buf_ptr_poll_wq, + &stream->buf_poll_work, + msecs_to_jiffies(POLL_PERIOD_MS)); + return ret; +} + +static int xe_eu_stall_disable_locked(struct xe_eu_stall_data_stream *stream) +{ + struct xe_gt *gt = stream->gt; + + if (!stream->enabled) + return 0; + + stream->enabled = false; + + xe_gt_mcr_multicast_write(gt, XEHPC_EUSTALL_BASE, 0); + + cancel_delayed_work_sync(&stream->buf_poll_work); + + if (XE_WA(gt, 22016596838)) + xe_gt_mcr_multicast_write(gt, ROW_CHICKEN2, + _MASKED_BIT_DISABLE(DISABLE_DOP_GATING)); + + xe_force_wake_put(gt_to_fw(gt), XE_FW_RENDER); + xe_pm_runtime_put(gt_to_xe(gt)); + + return 0; +} + +static long xe_eu_stall_stream_ioctl_locked(struct xe_eu_stall_data_stream *stream, + unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + case DRM_XE_OBSERVATION_IOCTL_ENABLE: + return xe_eu_stall_enable_locked(stream); + case DRM_XE_OBSERVATION_IOCTL_DISABLE: + return xe_eu_stall_disable_locked(stream); + } + + return -EINVAL; +} + +static long xe_eu_stall_stream_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct xe_eu_stall_data_stream *stream = file->private_data; + struct xe_gt *gt = stream->gt; + long ret; + + mutex_lock(>->eu_stall->stream_lock); + ret = xe_eu_stall_stream_ioctl_locked(stream, cmd, arg); + mutex_unlock(>->eu_stall->stream_lock); + + return ret; +} + +static int xe_eu_stall_stream_close(struct inode *inode, struct file *file) +{ + struct xe_eu_stall_data_stream *stream = file->private_data; + struct xe_gt *gt = stream->gt; + + drm_dev_put(>->tile->xe->drm); + + mutex_lock(>->eu_stall->stream_lock); + xe_eu_stall_disable_locked(stream); + xe_eu_stall_data_buf_destroy(stream); + xe_eu_stall_stream_free(stream); + mutex_unlock(>->eu_stall->stream_lock); + + return 0; +} + +static const struct file_operations fops_eu_stall = { + .owner = THIS_MODULE, + .llseek = noop_llseek, + .release = xe_eu_stall_stream_close, + .poll = xe_eu_stall_stream_poll, + .read = xe_eu_stall_stream_read, + .unlocked_ioctl = xe_eu_stall_stream_ioctl, + .compat_ioctl = xe_eu_stall_stream_ioctl, +}; + +static int xe_eu_stall_stream_open_locked(struct drm_device *dev, + struct eu_stall_open_properties *props, + struct drm_file *file) +{ + struct xe_eu_stall_data_stream *stream; + struct xe_gt *gt = props->gt; + unsigned long f_flags = 0; + int ret, stream_fd; + + /* Only one session can be active at any time */ + if (gt->eu_stall->stream) { + xe_gt_dbg(gt, "EU stall sampling session already active\n"); + return -EBUSY; + } + + stream = kzalloc(sizeof(*stream), GFP_KERNEL); + if (!stream) + return -ENOMEM; + + gt->eu_stall->stream = stream; + stream->gt = gt; + + ret = xe_eu_stall_stream_init(stream, props); + if (ret) { + xe_gt_dbg(gt, "EU stall stream init failed : %d\n", ret); + goto err_free; + } + + stream_fd = anon_inode_getfd("[xe_eu_stall]", &fops_eu_stall, stream, f_flags); + if (stream_fd < 0) { + ret = stream_fd; + xe_gt_dbg(gt, "EU stall inode get fd failed : %d\n", ret); + goto err_destroy; + } + + /* Take a reference on the driver that will be kept with stream_fd + * until its release. + */ + drm_dev_get(>->tile->xe->drm); + + return stream_fd; + +err_destroy: + xe_eu_stall_data_buf_destroy(stream); +err_free: + xe_eu_stall_stream_free(stream); + return ret; +} + +/** + * xe_eu_stall_stream_open - Open a xe EU stall data stream fd + * + * @dev: DRM device pointer + * @data: pointer to first struct @drm_xe_ext_set_property in + * the chain of input properties from the user space. + * @file: DRM file pointer + * + * This function opens a EU stall data stream with input properties from + * the user space. + * + * Returns: EU stall data stream fd on success or a negative error code. + */ +int xe_eu_stall_stream_open(struct drm_device *dev, u64 data, struct drm_file *file) +{ + struct xe_device *xe = to_xe_device(dev); + struct eu_stall_open_properties props = {}; + int ret; + + if (!xe_eu_stall_supported_on_platform(xe)) { + drm_dbg(&xe->drm, "EU stall monitoring is not supported on this platform\n"); + return -ENODEV; + } + + if (xe_observation_paranoid && !perfmon_capable()) { + drm_dbg(&xe->drm, "Insufficient privileges for EU stall monitoring\n"); + return -EACCES; + } + + /* Initialize and set default values */ + props.wait_num_reports = 1; + props.sampling_rate_mult = 4; + + ret = xe_eu_stall_user_extensions(xe, data, 0, &props); + if (ret) + return ret; + + if (!props.gt) { + drm_dbg(&xe->drm, "GT ID not provided for EU stall sampling\n"); + return -EINVAL; + } + + mutex_lock(&props.gt->eu_stall->stream_lock); + ret = xe_eu_stall_stream_open_locked(dev, &props, file); + mutex_unlock(&props.gt->eu_stall->stream_lock); + + return ret; +} diff --git a/drivers/gpu/drm/xe/xe_eu_stall.h b/drivers/gpu/drm/xe/xe_eu_stall.h new file mode 100644 index 000000000000..ed9d0f233566 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_eu_stall.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2025 Intel Corporation + */ + +#ifndef __XE_EU_STALL_H__ +#define __XE_EU_STALL_H__ + +#include "xe_gt_types.h" + +size_t xe_eu_stall_get_per_xecore_buf_size(void); +size_t xe_eu_stall_data_record_size(struct xe_device *xe); +size_t xe_eu_stall_get_sampling_rates(u32 *num_rates, const u64 **rates); + +int xe_eu_stall_init(struct xe_gt *gt); +int xe_eu_stall_stream_open(struct drm_device *dev, + u64 data, + struct drm_file *file); + +static inline bool xe_eu_stall_supported_on_platform(struct xe_device *xe) +{ + return xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20; +} +#endif diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 23a9f519ce1c..606922d9dd73 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -203,6 +203,7 @@ err_post_alloc: __xe_exec_queue_free(q); return ERR_PTR(err); } +ALLOW_ERROR_INJECTION(xe_exec_queue_create, ERRNO); struct xe_exec_queue *xe_exec_queue_create_class(struct xe_device *xe, struct xe_gt *gt, struct xe_vm *vm, @@ -604,11 +605,12 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, struct xe_tile *tile; struct xe_exec_queue *q = NULL; u32 logical_mask; + u32 flags = 0; u32 id; u32 len; int err; - if (XE_IOCTL_DBG(xe, args->flags) || + if (XE_IOCTL_DBG(xe, args->flags & ~DRM_XE_EXEC_QUEUE_LOW_LATENCY_HINT) || XE_IOCTL_DBG(xe, args->reserved[0] || args->reserved[1])) return -EINVAL; @@ -625,6 +627,9 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, if (XE_IOCTL_DBG(xe, eci[0].gt_id >= xe->info.gt_count)) return -EINVAL; + if (args->flags & DRM_XE_EXEC_QUEUE_LOW_LATENCY_HINT) + flags |= EXEC_QUEUE_FLAG_LOW_LATENCY; + if (eci[0].engine_class == DRM_XE_ENGINE_CLASS_VM_BIND) { if (XE_IOCTL_DBG(xe, args->width != 1) || XE_IOCTL_DBG(xe, args->num_placements != 1) || @@ -633,8 +638,8 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, for_each_tile(tile, xe, id) { struct xe_exec_queue *new; - u32 flags = EXEC_QUEUE_FLAG_VM; + flags |= EXEC_QUEUE_FLAG_VM; if (id) flags |= EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD; @@ -680,7 +685,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, } q = xe_exec_queue_create(xe, vm, logical_mask, - args->width, hwe, 0, + args->width, hwe, flags, args->extensions); up_read(&vm->lock); xe_vm_put(vm); diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 6eb7ff091534..cc1cffb5c87f 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -85,6 +85,8 @@ struct xe_exec_queue { #define EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD BIT(3) /* kernel exec_queue only, set priority to highest level */ #define EXEC_QUEUE_FLAG_HIGH_PRIORITY BIT(4) +/* flag to indicate low latency hint to guc */ +#define EXEC_QUEUE_FLAG_LOW_LATENCY BIT(5) /** * @flags: flags for this exec queue, should statically setup aside from ban diff --git a/drivers/gpu/drm/xe/xe_gen_wa_oob.c b/drivers/gpu/drm/xe/xe_gen_wa_oob.c index 904cf47925aa..ed9183599e31 100644 --- a/drivers/gpu/drm/xe/xe_gen_wa_oob.c +++ b/drivers/gpu/drm/xe/xe_gen_wa_oob.c @@ -28,10 +28,10 @@ "\n" \ "#endif\n" -static void print_usage(FILE *f) +static void print_usage(FILE *f, const char *progname) { fprintf(f, "usage: %s <input-rule-file> <generated-c-source-file> <generated-c-header-file>\n", - program_invocation_short_name); + progname); } static void print_parse_error(const char *err_msg, const char *line, @@ -144,7 +144,7 @@ int main(int argc, const char *argv[]) if (argc < 3) { fprintf(stderr, "ERROR: wrong arguments\n"); - print_usage(stderr); + print_usage(stderr, argv[0]); return 1; } diff --git a/drivers/gpu/drm/xe/xe_gsc_proxy.c b/drivers/gpu/drm/xe/xe_gsc_proxy.c index 31c90577faf0..8cf70b228ff3 100644 --- a/drivers/gpu/drm/xe/xe_gsc_proxy.c +++ b/drivers/gpu/drm/xe/xe_gsc_proxy.c @@ -490,7 +490,7 @@ int xe_gsc_proxy_init(struct xe_gsc *gsc) gsc->proxy.component_added = true; - return xe_device_add_action_or_reset(xe, xe_gsc_proxy_remove, gsc); + return devm_add_action_or_reset(xe->drm.dev, xe_gsc_proxy_remove, gsc); } /** diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 650a0ee56e97..10a9e3c72b36 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -19,6 +19,7 @@ #include "xe_bb.h" #include "xe_bo.h" #include "xe_device.h" +#include "xe_eu_stall.h" #include "xe_exec_queue.h" #include "xe_execlist.h" #include "xe_force_wake.h" @@ -361,9 +362,11 @@ int xe_gt_init_early(struct xe_gt *gt) if (err) return err; - xe_wa_process_gt(gt); + err = xe_tuning_init(gt); + if (err) + return err; + xe_wa_process_oob(gt); - xe_tuning_process_gt(gt); xe_force_wake_init_gt(gt, gt_to_fw(gt)); spin_lock_init(>->global_invl_lock); @@ -450,6 +453,8 @@ static int all_fw_domain_init(struct xe_gt *gt) } xe_gt_mcr_set_implicit_defaults(gt); + xe_wa_process_gt(gt); + xe_tuning_process_gt(gt); xe_reg_sr_apply_mmio(>->reg_sr, gt); err = xe_gt_clock_init(gt); @@ -613,6 +618,10 @@ int xe_gt_init(struct xe_gt *gt) xe_gt_record_user_engines(gt); + err = xe_eu_stall_init(gt); + if (err) + return err; + return 0; } diff --git a/drivers/gpu/drm/xe/xe_gt_clock.c b/drivers/gpu/drm/xe/xe_gt_clock.c index cc2ae159298e..2a958c92d8ea 100644 --- a/drivers/gpu/drm/xe/xe_gt_clock.c +++ b/drivers/gpu/drm/xe/xe_gt_clock.c @@ -12,25 +12,10 @@ #include "xe_assert.h" #include "xe_device.h" #include "xe_gt.h" +#include "xe_gt_printk.h" #include "xe_macros.h" #include "xe_mmio.h" -static u32 read_reference_ts_freq(struct xe_gt *gt) -{ - u32 ts_override = xe_mmio_read32(>->mmio, TIMESTAMP_OVERRIDE); - u32 base_freq, frac_freq; - - base_freq = REG_FIELD_GET(TIMESTAMP_OVERRIDE_US_COUNTER_DIVIDER_MASK, - ts_override) + 1; - base_freq *= 1000000; - - frac_freq = REG_FIELD_GET(TIMESTAMP_OVERRIDE_US_COUNTER_DENOMINATOR_MASK, - ts_override); - frac_freq = 1000000 / (frac_freq + 1); - - return base_freq + frac_freq; -} - static u32 get_crystal_clock_freq(u32 rpm_config_reg) { const u32 f19_2_mhz = 19200000; @@ -57,26 +42,30 @@ static u32 get_crystal_clock_freq(u32 rpm_config_reg) int xe_gt_clock_init(struct xe_gt *gt) { - u32 ctc_reg = xe_mmio_read32(>->mmio, CTC_MODE); + u32 c0 = xe_mmio_read32(>->mmio, RPM_CONFIG0); u32 freq = 0; - /* Assuming gen11+ so assert this assumption is correct */ - xe_gt_assert(gt, GRAPHICS_VER(gt_to_xe(gt)) >= 11); - - if (ctc_reg & CTC_SOURCE_DIVIDE_LOGIC) { - freq = read_reference_ts_freq(gt); - } else { - u32 c0 = xe_mmio_read32(>->mmio, RPM_CONFIG0); - - freq = get_crystal_clock_freq(c0); - - /* - * Now figure out how the command stream's timestamp - * register increments from this frequency (it might - * increment only every few clock cycle). - */ - freq >>= 3 - REG_FIELD_GET(RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK, c0); - } + /* + * CTC_MODE[0] = 1 is definitely not supported for Xe2 and later + * platforms. In theory it could be a valid setting for pre-Xe2 + * platforms, but there's no documentation on how to properly handle + * this case. Reading TIMESTAMP_OVERRIDE, as the driver attempted in + * the past has been confirmed as incorrect by the hardware architects. + * + * For now just warn if we ever encounter hardware in the wild that + * has this setting and move on as if it hadn't been set. + */ + if (xe_mmio_read32(>->mmio, CTC_MODE) & CTC_SOURCE_DIVIDE_LOGIC) + xe_gt_warn(gt, "CTC_MODE[0] is set; this is unexpected and undocumented\n"); + + freq = get_crystal_clock_freq(c0); + + /* + * Now figure out how the command stream's timestamp + * register increments from this frequency (it might + * increment only every few clock cycle). + */ + freq >>= 3 - REG_FIELD_GET(RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK, c0); gt->info.reference_clock = freq; return 0; diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c index e7792858b1e4..2d63a69cbfa3 100644 --- a/drivers/gpu/drm/xe/xe_gt_debugfs.c +++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c @@ -30,6 +30,7 @@ #include "xe_reg_sr.h" #include "xe_reg_whitelist.h" #include "xe_sriov.h" +#include "xe_tuning.h" #include "xe_uc_debugfs.h" #include "xe_wa.h" @@ -217,6 +218,15 @@ static int workarounds(struct xe_gt *gt, struct drm_printer *p) return 0; } +static int tunings(struct xe_gt *gt, struct drm_printer *p) +{ + xe_pm_runtime_get(gt_to_xe(gt)); + xe_tuning_dump(gt, p); + xe_pm_runtime_put(gt_to_xe(gt)); + + return 0; +} + static int pat(struct xe_gt *gt, struct drm_printer *p) { xe_pm_runtime_get(gt_to_xe(gt)); @@ -300,6 +310,7 @@ static const struct drm_info_list debugfs_list[] = { {"powergate_info", .show = xe_gt_debugfs_simple_show, .data = powergate_info}, {"register-save-restore", .show = xe_gt_debugfs_simple_show, .data = register_save_restore}, {"workarounds", .show = xe_gt_debugfs_simple_show, .data = workarounds}, + {"tunings", .show = xe_gt_debugfs_simple_show, .data = tunings}, {"pat", .show = xe_gt_debugfs_simple_show, .data = pat}, {"mocs", .show = xe_gt_debugfs_simple_show, .data = mocs}, {"default_lrc_rcs", .show = xe_gt_debugfs_simple_show, .data = rcs_default_lrc}, diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index 46701ca11ce0..c5ad9a0a89c2 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -19,6 +19,7 @@ #include "xe_guc.h" #include "xe_guc_ct.h" #include "xe_migrate.h" +#include "xe_svm.h" #include "xe_trace_bo.h" #include "xe_vm.h" @@ -125,8 +126,8 @@ static int xe_pf_begin(struct drm_exec *exec, struct xe_vma *vma, return 0; } -static int handle_vma_pagefault(struct xe_gt *gt, struct pagefault *pf, - struct xe_vma *vma) +static int handle_vma_pagefault(struct xe_gt *gt, struct xe_vma *vma, + bool atomic) { struct xe_vm *vm = xe_vma_vm(vma); struct xe_tile *tile = gt_to_tile(gt); @@ -134,13 +135,13 @@ static int handle_vma_pagefault(struct xe_gt *gt, struct pagefault *pf, struct dma_fence *fence; ktime_t end = 0; int err; - bool atomic; + + lockdep_assert_held_write(&vm->lock); xe_gt_stats_incr(gt, XE_GT_STATS_ID_VMA_PAGEFAULT_COUNT, 1); - xe_gt_stats_incr(gt, XE_GT_STATS_ID_VMA_PAGEFAULT_BYTES, xe_vma_size(vma)); + xe_gt_stats_incr(gt, XE_GT_STATS_ID_VMA_PAGEFAULT_KB, xe_vma_size(vma) / 1024); trace_xe_vma_pagefault(vma); - atomic = access_is_atomic(pf->access_type); /* Check if VMA is valid */ if (vma_is_valid(tile, vma) && !atomic) @@ -210,6 +211,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf) struct xe_vm *vm; struct xe_vma *vma = NULL; int err; + bool atomic; /* SW isn't expected to handle TRTT faults */ if (pf->trva_fault) @@ -235,7 +237,13 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf) goto unlock_vm; } - err = handle_vma_pagefault(gt, pf, vma); + atomic = access_is_atomic(pf->access_type); + + if (xe_vma_is_cpu_addr_mirror(vma)) + err = xe_svm_handle_pagefault(vm, vma, gt_to_tile(gt), + pf->page_addr, atomic); + else + err = handle_vma_pagefault(gt, vma, atomic); unlock_vm: if (!err) diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_service.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_service.c index 6b5f849a0722..4efde5f46b43 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_service.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_service.c @@ -114,7 +114,6 @@ static const struct xe_reg tgl_runtime_regs[] = { GT_VEBOX_VDBOX_DISABLE, /* _MMIO(0x9140) */ CTC_MODE, /* _MMIO(0xa26c) */ HUC_KERNEL_LOAD_INFO, /* _MMIO(0xc1dc) */ - TIMESTAMP_OVERRIDE, /* _MMIO(0x44074) */ }; static const struct xe_reg ats_m_runtime_regs[] = { @@ -127,7 +126,6 @@ static const struct xe_reg ats_m_runtime_regs[] = { XEHP_GT_COMPUTE_DSS_ENABLE, /* _MMIO(0x9144) */ CTC_MODE, /* _MMIO(0xa26c) */ HUC_KERNEL_LOAD_INFO, /* _MMIO(0xc1dc) */ - TIMESTAMP_OVERRIDE, /* _MMIO(0x44074) */ }; static const struct xe_reg pvc_runtime_regs[] = { @@ -140,7 +138,6 @@ static const struct xe_reg pvc_runtime_regs[] = { XEHPC_GT_COMPUTE_DSS_ENABLE_EXT,/* _MMIO(0x9148) */ CTC_MODE, /* _MMIO(0xA26C) */ HUC_KERNEL_LOAD_INFO, /* _MMIO(0xc1dc) */ - TIMESTAMP_OVERRIDE, /* _MMIO(0x44074) */ }; static const struct xe_reg ver_1270_runtime_regs[] = { @@ -155,7 +152,6 @@ static const struct xe_reg ver_1270_runtime_regs[] = { XEHPC_GT_COMPUTE_DSS_ENABLE_EXT,/* _MMIO(0x9148) */ CTC_MODE, /* _MMIO(0xa26c) */ HUC_KERNEL_LOAD_INFO, /* _MMIO(0xc1dc) */ - TIMESTAMP_OVERRIDE, /* _MMIO(0x44074) */ }; static const struct xe_reg ver_2000_runtime_regs[] = { @@ -173,7 +169,6 @@ static const struct xe_reg ver_2000_runtime_regs[] = { XE2_GT_GEOMETRY_DSS_2, /* _MMIO(0x9154) */ CTC_MODE, /* _MMIO(0xa26c) */ HUC_KERNEL_LOAD_INFO, /* _MMIO(0xc1dc) */ - TIMESTAMP_OVERRIDE, /* _MMIO(0x44074) */ }; static const struct xe_reg ver_3000_runtime_regs[] = { diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c index 4831549da319..a439261bf4d7 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c @@ -47,12 +47,19 @@ static int guc_action_vf_reset(struct xe_guc *guc) return ret > 0 ? -EPROTO : ret; } +#define GUC_RESET_VF_STATE_RETRY_MAX 10 static int vf_reset_guc_state(struct xe_gt *gt) { + unsigned int retry = GUC_RESET_VF_STATE_RETRY_MAX; struct xe_guc *guc = >->uc.guc; int err; - err = guc_action_vf_reset(guc); + do { + err = guc_action_vf_reset(guc); + if (!err || err != -ETIMEDOUT) + break; + } while (--retry); + if (unlikely(err)) xe_gt_sriov_err(gt, "Failed to reset GuC state (%pe)\n", ERR_PTR(err)); return err; diff --git a/drivers/gpu/drm/xe/xe_gt_stats.c b/drivers/gpu/drm/xe/xe_gt_stats.c index 2e9879ea4674..6155ea354432 100644 --- a/drivers/gpu/drm/xe/xe_gt_stats.c +++ b/drivers/gpu/drm/xe/xe_gt_stats.c @@ -23,13 +23,13 @@ void xe_gt_stats_incr(struct xe_gt *gt, const enum xe_gt_stats_id id, int incr) if (id >= __XE_GT_STATS_NUM_IDS) return; - atomic_add(incr, >->stats.counters[id]); + atomic64_add(incr, >->stats.counters[id]); } static const char *const stat_description[__XE_GT_STATS_NUM_IDS] = { "tlb_inval_count", "vma_pagefault_count", - "vma_pagefault_bytes", + "vma_pagefault_kb", }; /** @@ -44,8 +44,8 @@ int xe_gt_stats_print_info(struct xe_gt *gt, struct drm_printer *p) enum xe_gt_stats_id id; for (id = 0; id < __XE_GT_STATS_NUM_IDS; ++id) - drm_printf(p, "%s: %d\n", stat_description[id], - atomic_read(>->stats.counters[id])); + drm_printf(p, "%s: %lld\n", stat_description[id], + atomic64_read(>->stats.counters[id])); return 0; } diff --git a/drivers/gpu/drm/xe/xe_gt_stats_types.h b/drivers/gpu/drm/xe/xe_gt_stats_types.h index b072bd80c4b9..d556771f99d6 100644 --- a/drivers/gpu/drm/xe/xe_gt_stats_types.h +++ b/drivers/gpu/drm/xe/xe_gt_stats_types.h @@ -9,7 +9,7 @@ enum xe_gt_stats_id { XE_GT_STATS_ID_TLB_INVAL, XE_GT_STATS_ID_VMA_PAGEFAULT_COUNT, - XE_GT_STATS_ID_VMA_PAGEFAULT_BYTES, + XE_GT_STATS_ID_VMA_PAGEFAULT_KB, /* must be the last entry */ __XE_GT_STATS_NUM_IDS, }; diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index 0a93831c0a02..03072e094991 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -411,6 +411,28 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt, } /** + * xe_gt_tlb_invalidation_vm - Issue a TLB invalidation on this GT for a VM + * @gt: graphics tile + * @vm: VM to invalidate + * + * Invalidate entire VM's address space + */ +void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm) +{ + struct xe_gt_tlb_invalidation_fence fence; + u64 range = 1ull << vm->xe->info.va_bits; + int ret; + + xe_gt_tlb_invalidation_fence_init(gt, &fence, true); + + ret = xe_gt_tlb_invalidation_range(gt, &fence, 0, range, vm->usm.asid); + if (ret < 0) + return; + + xe_gt_tlb_invalidation_fence_wait(&fence); +} + +/** * xe_gt_tlb_invalidation_vma - Issue a TLB invalidation on this GT for a VMA * @gt: GT structure * @fence: invalidation fence which will be signal on TLB invalidation diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h index 672acfcdf0d7..abe9b03d543e 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h @@ -12,6 +12,7 @@ struct xe_gt; struct xe_guc; +struct xe_vm; struct xe_vma; int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt); @@ -21,6 +22,7 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt); int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence, struct xe_vma *vma); +void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm); int xe_gt_tlb_invalidation_range(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence, u64 start, u64 end, u32 asid); diff --git a/drivers/gpu/drm/xe/xe_gt_topology.h b/drivers/gpu/drm/xe/xe_gt_topology.h index 746b325bbf6e..a72d26ba0653 100644 --- a/drivers/gpu/drm/xe/xe_gt_topology.h +++ b/drivers/gpu/drm/xe/xe_gt_topology.h @@ -25,6 +25,19 @@ void xe_gt_topology_init(struct xe_gt *gt); void xe_gt_topology_dump(struct xe_gt *gt, struct drm_printer *p); +/** + * xe_gt_topology_mask_last_dss() - Returns the index of the last DSS in a mask. + * @mask: Input DSS mask + * + * Return: Index of the last DSS in the input DSS mask, + * XE_MAX_DSS_FUSE_BITS if DSS mask is empty. + */ +static inline unsigned int +xe_gt_topology_mask_last_dss(const xe_dss_mask_t mask) +{ + return find_last_bit(mask, XE_MAX_DSS_FUSE_BITS); +} + unsigned int xe_dss_mask_group_ffs(const xe_dss_mask_t mask, int groupsize, int groupnum); diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h index 6e66bf0e8b3f..e3cfb026ac88 100644 --- a/drivers/gpu/drm/xe/xe_gt_types.h +++ b/drivers/gpu/drm/xe/xe_gt_types.h @@ -139,7 +139,7 @@ struct xe_gt { /** @stats: GT stats */ struct { /** @stats.counters: counters for various GT stats */ - atomic_t counters[__XE_GT_STATS_NUM_IDS]; + atomic64_t counters[__XE_GT_STATS_NUM_IDS]; } stats; #endif @@ -413,6 +413,16 @@ struct xe_gt { bool oob_initialized; } wa_active; + /** @tuning_active: keep track of active tunings */ + struct { + /** @tuning_active.gt: bitmap with active GT tunings */ + unsigned long *gt; + /** @tuning_active.engine: bitmap with active engine tunings */ + unsigned long *engine; + /** @tuning_active.lrc: bitmap with active LRC tunings */ + unsigned long *lrc; + } tuning_active; + /** @user_engines: engines present in GT and available to userspace */ struct { /** @@ -430,6 +440,9 @@ struct xe_gt { /** @oa: oa observation subsystem per gt info */ struct xe_oa_gt oa; + + /** @eu_stall: EU stall counters subsystem per gt info */ + struct xe_eu_stall_gt *eu_stall; }; #endif diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c index 1619c0a52db9..bc5714a5b36b 100644 --- a/drivers/gpu/drm/xe/xe_guc.c +++ b/drivers/gpu/drm/xe/xe_guc.c @@ -27,6 +27,7 @@ #include "xe_guc_capture.h" #include "xe_guc_ct.h" #include "xe_guc_db_mgr.h" +#include "xe_guc_engine_activity.h" #include "xe_guc_hwconfig.h" #include "xe_guc_log.h" #include "xe_guc_pc.h" @@ -744,6 +745,10 @@ int xe_guc_init_post_hwconfig(struct xe_guc *guc) if (ret) return ret; + ret = xe_guc_engine_activity_init(guc); + if (ret) + return ret; + ret = xe_guc_buf_cache_init(&guc->buf); if (ret) return ret; @@ -1491,14 +1496,6 @@ void xe_guc_stop(struct xe_guc *guc) int xe_guc_start(struct xe_guc *guc) { - if (!IS_SRIOV_VF(guc_to_xe(guc))) { - int err; - - err = xe_guc_pc_start(&guc->pc); - xe_gt_WARN(guc_to_gt(guc), err, "Failed to start GuC PC: %pe\n", - ERR_PTR(err)); - } - return xe_guc_submit_start(guc); } diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c index fab259adc380..e7c9e095a19f 100644 --- a/drivers/gpu/drm/xe/xe_guc_ads.c +++ b/drivers/gpu/drm/xe/xe_guc_ads.c @@ -342,7 +342,7 @@ static void guc_waklv_init(struct xe_guc_ads *ads) offset = guc_ads_waklv_offset(ads); remain = guc_ads_waklv_size(ads); - if (XE_WA(gt, 14019882105)) + if (XE_WA(gt, 14019882105) || XE_WA(gt, 16021333562)) guc_waklv_enable_simple(ads, GUC_WORKAROUND_KLV_BLOCK_INTERRUPTS_WHEN_MGSR_BLOCKED, &offset, &remain); diff --git a/drivers/gpu/drm/xe/xe_guc_engine_activity.c b/drivers/gpu/drm/xe/xe_guc_engine_activity.c new file mode 100644 index 000000000000..2a457dcf31d5 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_guc_engine_activity.c @@ -0,0 +1,373 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2025 Intel Corporation + */ + +#include <drm/drm_managed.h> + +#include "abi/guc_actions_abi.h" +#include "regs/xe_gt_regs.h" + +#include "xe_bo.h" +#include "xe_force_wake.h" +#include "xe_gt_printk.h" +#include "xe_guc.h" +#include "xe_guc_engine_activity.h" +#include "xe_guc_ct.h" +#include "xe_hw_engine.h" +#include "xe_map.h" +#include "xe_mmio.h" +#include "xe_trace_guc.h" + +#define TOTAL_QUANTA 0x8000 + +static struct iosys_map engine_activity_map(struct xe_guc *guc, struct xe_hw_engine *hwe) +{ + struct xe_guc_engine_activity *engine_activity = &guc->engine_activity; + struct engine_activity_buffer *buffer = &engine_activity->device_buffer; + u16 guc_class = xe_engine_class_to_guc_class(hwe->class); + size_t offset; + + offset = offsetof(struct guc_engine_activity_data, + engine_activity[guc_class][hwe->logical_instance]); + + return IOSYS_MAP_INIT_OFFSET(&buffer->activity_bo->vmap, offset); +} + +static struct iosys_map engine_metadata_map(struct xe_guc *guc) +{ + struct xe_guc_engine_activity *engine_activity = &guc->engine_activity; + struct engine_activity_buffer *buffer = &engine_activity->device_buffer; + + return buffer->metadata_bo->vmap; +} + +static int allocate_engine_activity_group(struct xe_guc *guc) +{ + struct xe_guc_engine_activity *engine_activity = &guc->engine_activity; + struct xe_device *xe = guc_to_xe(guc); + u32 num_activity_group = 1; /* Will be modified for VF */ + + engine_activity->eag = drmm_kcalloc(&xe->drm, num_activity_group, + sizeof(struct engine_activity_group), GFP_KERNEL); + + if (!engine_activity->eag) + return -ENOMEM; + + engine_activity->num_activity_group = num_activity_group; + + return 0; +} + +static int allocate_engine_activity_buffers(struct xe_guc *guc, + struct engine_activity_buffer *buffer) +{ + u32 metadata_size = sizeof(struct guc_engine_activity_metadata); + u32 size = sizeof(struct guc_engine_activity_data); + struct xe_gt *gt = guc_to_gt(guc); + struct xe_tile *tile = gt_to_tile(gt); + struct xe_bo *bo, *metadata_bo; + + metadata_bo = xe_bo_create_pin_map(gt_to_xe(gt), tile, NULL, PAGE_ALIGN(metadata_size), + ttm_bo_type_kernel, XE_BO_FLAG_SYSTEM | + XE_BO_FLAG_GGTT | XE_BO_FLAG_GGTT_INVALIDATE); + + if (IS_ERR(metadata_bo)) + return PTR_ERR(metadata_bo); + + bo = xe_bo_create_pin_map(gt_to_xe(gt), tile, NULL, PAGE_ALIGN(size), + ttm_bo_type_kernel, XE_BO_FLAG_VRAM_IF_DGFX(tile) | + XE_BO_FLAG_GGTT | XE_BO_FLAG_GGTT_INVALIDATE); + + if (IS_ERR(bo)) { + xe_bo_unpin_map_no_vm(metadata_bo); + return PTR_ERR(bo); + } + + buffer->metadata_bo = metadata_bo; + buffer->activity_bo = bo; + return 0; +} + +static void free_engine_activity_buffers(struct engine_activity_buffer *buffer) +{ + xe_bo_unpin_map_no_vm(buffer->metadata_bo); + xe_bo_unpin_map_no_vm(buffer->activity_bo); +} + +static bool is_engine_activity_supported(struct xe_guc *guc) +{ + struct xe_uc_fw_version *version = &guc->fw.versions.found[XE_UC_FW_VER_COMPATIBILITY]; + struct xe_uc_fw_version required = { 1, 14, 1 }; + struct xe_gt *gt = guc_to_gt(guc); + + if (IS_SRIOV_VF(gt_to_xe(gt))) { + xe_gt_info(gt, "engine activity stats not supported on VFs\n"); + return false; + } + + /* engine activity stats is supported from GuC interface version (1.14.1) */ + if (GUC_SUBMIT_VER(guc) < MAKE_GUC_VER_STRUCT(required)) { + xe_gt_info(gt, + "engine activity stats unsupported in GuC interface v%u.%u.%u, need v%u.%u.%u or higher\n", + version->major, version->minor, version->patch, required.major, + required.minor, required.patch); + return false; + } + + return true; +} + +static struct engine_activity *hw_engine_to_engine_activity(struct xe_hw_engine *hwe) +{ + struct xe_guc *guc = &hwe->gt->uc.guc; + struct engine_activity_group *eag = &guc->engine_activity.eag[0]; + u16 guc_class = xe_engine_class_to_guc_class(hwe->class); + + return &eag->engine[guc_class][hwe->logical_instance]; +} + +static u64 cpu_ns_to_guc_tsc_tick(ktime_t ns, u32 freq) +{ + return mul_u64_u32_div(ns, freq, NSEC_PER_SEC); +} + +#define read_engine_activity_record(xe_, map_, field_) \ + xe_map_rd_field(xe_, map_, 0, struct guc_engine_activity, field_) + +#define read_metadata_record(xe_, map_, field_) \ + xe_map_rd_field(xe_, map_, 0, struct guc_engine_activity_metadata, field_) + +static u64 get_engine_active_ticks(struct xe_guc *guc, struct xe_hw_engine *hwe) +{ + struct engine_activity *ea = hw_engine_to_engine_activity(hwe); + struct guc_engine_activity *cached_activity = &ea->activity; + struct guc_engine_activity_metadata *cached_metadata = &ea->metadata; + struct xe_guc_engine_activity *engine_activity = &guc->engine_activity; + struct iosys_map activity_map, metadata_map; + struct xe_device *xe = guc_to_xe(guc); + struct xe_gt *gt = guc_to_gt(guc); + u32 last_update_tick, global_change_num; + u64 active_ticks, gpm_ts; + u16 change_num; + + activity_map = engine_activity_map(guc, hwe); + metadata_map = engine_metadata_map(guc); + global_change_num = read_metadata_record(xe, &metadata_map, global_change_num); + + /* GuC has not initialized activity data yet, return 0 */ + if (!global_change_num) + goto update; + + if (global_change_num == cached_metadata->global_change_num) + goto update; + + cached_metadata->global_change_num = global_change_num; + change_num = read_engine_activity_record(xe, &activity_map, change_num); + + if (!change_num || change_num == cached_activity->change_num) + goto update; + + /* read engine activity values */ + last_update_tick = read_engine_activity_record(xe, &activity_map, last_update_tick); + active_ticks = read_engine_activity_record(xe, &activity_map, active_ticks); + + /* activity calculations */ + ea->running = !!last_update_tick; + ea->total += active_ticks - cached_activity->active_ticks; + ea->active = 0; + + /* cache the counter */ + cached_activity->change_num = change_num; + cached_activity->last_update_tick = last_update_tick; + cached_activity->active_ticks = active_ticks; + +update: + if (ea->running) { + gpm_ts = xe_mmio_read64_2x32(>->mmio, MISC_STATUS_0) >> + engine_activity->gpm_timestamp_shift; + ea->active = lower_32_bits(gpm_ts) - cached_activity->last_update_tick; + } + + trace_xe_guc_engine_activity(xe, ea, hwe->name, hwe->instance); + + return ea->total + ea->active; +} + +static u64 get_engine_total_ticks(struct xe_guc *guc, struct xe_hw_engine *hwe) +{ + struct engine_activity *ea = hw_engine_to_engine_activity(hwe); + struct guc_engine_activity_metadata *cached_metadata = &ea->metadata; + struct guc_engine_activity *cached_activity = &ea->activity; + struct iosys_map activity_map, metadata_map; + struct xe_device *xe = guc_to_xe(guc); + ktime_t now, cpu_delta; + u64 numerator; + u16 quanta_ratio; + + activity_map = engine_activity_map(guc, hwe); + metadata_map = engine_metadata_map(guc); + + if (!cached_metadata->guc_tsc_frequency_hz) + cached_metadata->guc_tsc_frequency_hz = read_metadata_record(xe, &metadata_map, + guc_tsc_frequency_hz); + + quanta_ratio = read_engine_activity_record(xe, &activity_map, quanta_ratio); + cached_activity->quanta_ratio = quanta_ratio; + + /* Total ticks calculations */ + now = ktime_get(); + cpu_delta = now - ea->last_cpu_ts; + ea->last_cpu_ts = now; + numerator = (ea->quanta_remainder_ns + cpu_delta) * cached_activity->quanta_ratio; + ea->quanta_ns += numerator / TOTAL_QUANTA; + ea->quanta_remainder_ns = numerator % TOTAL_QUANTA; + ea->quanta = cpu_ns_to_guc_tsc_tick(ea->quanta_ns, cached_metadata->guc_tsc_frequency_hz); + + trace_xe_guc_engine_activity(xe, ea, hwe->name, hwe->instance); + + return ea->quanta; +} + +static int enable_engine_activity_stats(struct xe_guc *guc) +{ + struct xe_guc_engine_activity *engine_activity = &guc->engine_activity; + struct engine_activity_buffer *buffer = &engine_activity->device_buffer; + u32 action[] = { + XE_GUC_ACTION_SET_DEVICE_ENGINE_ACTIVITY_BUFFER, + xe_bo_ggtt_addr(buffer->metadata_bo), + 0, + xe_bo_ggtt_addr(buffer->activity_bo), + 0, + }; + + /* Blocking here to ensure the buffers are ready before reading them */ + return xe_guc_ct_send_block(&guc->ct, action, ARRAY_SIZE(action)); +} + +static void engine_activity_set_cpu_ts(struct xe_guc *guc) +{ + struct xe_guc_engine_activity *engine_activity = &guc->engine_activity; + struct engine_activity_group *eag = &engine_activity->eag[0]; + int i, j; + + for (i = 0; i < GUC_MAX_ENGINE_CLASSES; i++) + for (j = 0; j < GUC_MAX_INSTANCES_PER_CLASS; j++) + eag->engine[i][j].last_cpu_ts = ktime_get(); +} + +static u32 gpm_timestamp_shift(struct xe_gt *gt) +{ + u32 reg; + + reg = xe_mmio_read32(>->mmio, RPM_CONFIG0); + + return 3 - REG_FIELD_GET(RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK, reg); +} + +/** + * xe_guc_engine_activity_active_ticks - Get engine active ticks + * @guc: The GuC object + * @hwe: The hw_engine object + * + * Return: accumulated ticks @hwe was active since engine activity stats were enabled. + */ +u64 xe_guc_engine_activity_active_ticks(struct xe_guc *guc, struct xe_hw_engine *hwe) +{ + if (!xe_guc_engine_activity_supported(guc)) + return 0; + + return get_engine_active_ticks(guc, hwe); +} + +/** + * xe_guc_engine_activity_total_ticks - Get engine total ticks + * @guc: The GuC object + * @hwe: The hw_engine object + * + * Return: accumulated quanta of ticks allocated for the engine + */ +u64 xe_guc_engine_activity_total_ticks(struct xe_guc *guc, struct xe_hw_engine *hwe) +{ + if (!xe_guc_engine_activity_supported(guc)) + return 0; + + return get_engine_total_ticks(guc, hwe); +} + +/** + * xe_guc_engine_activity_supported - Check support for engine activity stats + * @guc: The GuC object + * + * Engine activity stats is supported from GuC interface version (1.14.1) + * + * Return: true if engine activity stats supported, false otherwise + */ +bool xe_guc_engine_activity_supported(struct xe_guc *guc) +{ + struct xe_guc_engine_activity *engine_activity = &guc->engine_activity; + + return engine_activity->supported; +} + +/** + * xe_guc_engine_activity_enable_stats - Enable engine activity stats + * @guc: The GuC object + * + * Enable engine activity stats and set initial timestamps + */ +void xe_guc_engine_activity_enable_stats(struct xe_guc *guc) +{ + int ret; + + if (!xe_guc_engine_activity_supported(guc)) + return; + + ret = enable_engine_activity_stats(guc); + if (ret) + xe_gt_err(guc_to_gt(guc), "failed to enable activity stats%d\n", ret); + else + engine_activity_set_cpu_ts(guc); +} + +static void engine_activity_fini(void *arg) +{ + struct xe_guc_engine_activity *engine_activity = arg; + struct engine_activity_buffer *buffer = &engine_activity->device_buffer; + + free_engine_activity_buffers(buffer); +} + +/** + * xe_guc_engine_activity_init - Initialize the engine activity data + * @guc: The GuC object + * + * Return: 0 on success, negative error code otherwise. + */ +int xe_guc_engine_activity_init(struct xe_guc *guc) +{ + struct xe_guc_engine_activity *engine_activity = &guc->engine_activity; + struct xe_gt *gt = guc_to_gt(guc); + int ret; + + engine_activity->supported = is_engine_activity_supported(guc); + if (!engine_activity->supported) + return 0; + + ret = allocate_engine_activity_group(guc); + if (ret) { + xe_gt_err(gt, "failed to allocate engine activity group (%pe)\n", ERR_PTR(ret)); + return ret; + } + + ret = allocate_engine_activity_buffers(guc, &engine_activity->device_buffer); + if (ret) { + xe_gt_err(gt, "failed to allocate engine activity buffers (%pe)\n", ERR_PTR(ret)); + return ret; + } + + engine_activity->gpm_timestamp_shift = gpm_timestamp_shift(gt); + + return devm_add_action_or_reset(gt_to_xe(gt)->drm.dev, engine_activity_fini, + engine_activity); +} diff --git a/drivers/gpu/drm/xe/xe_guc_engine_activity.h b/drivers/gpu/drm/xe/xe_guc_engine_activity.h new file mode 100644 index 000000000000..a042d4cb404c --- /dev/null +++ b/drivers/gpu/drm/xe/xe_guc_engine_activity.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2025 Intel Corporation + */ + +#ifndef _XE_GUC_ENGINE_ACTIVITY_H_ +#define _XE_GUC_ENGINE_ACTIVITY_H_ + +#include <linux/types.h> + +struct xe_hw_engine; +struct xe_guc; + +int xe_guc_engine_activity_init(struct xe_guc *guc); +bool xe_guc_engine_activity_supported(struct xe_guc *guc); +void xe_guc_engine_activity_enable_stats(struct xe_guc *guc); +u64 xe_guc_engine_activity_active_ticks(struct xe_guc *guc, struct xe_hw_engine *hwe); +u64 xe_guc_engine_activity_total_ticks(struct xe_guc *guc, struct xe_hw_engine *hwe); +#endif diff --git a/drivers/gpu/drm/xe/xe_guc_engine_activity_types.h b/drivers/gpu/drm/xe/xe_guc_engine_activity_types.h new file mode 100644 index 000000000000..5cdd034b6b70 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_guc_engine_activity_types.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2025 Intel Corporation + */ + +#ifndef _XE_GUC_ENGINE_ACTIVITY_TYPES_H_ +#define _XE_GUC_ENGINE_ACTIVITY_TYPES_H_ + +#include <linux/types.h> + +#include "xe_guc_fwif.h" +/** + * struct engine_activity - Engine specific activity data + * + * Contains engine specific activity data and snapshot of the + * structures from GuC + */ +struct engine_activity { + /** @active: current activity */ + u64 active; + + /** @last_cpu_ts: cpu timestamp in nsec of previous sample */ + u64 last_cpu_ts; + + /** @quanta: total quanta used on HW */ + u64 quanta; + + /** @quanta_ns: total quanta_ns used on HW */ + u64 quanta_ns; + + /** + * @quanta_remainder_ns: remainder when the CPU time is scaled as + * per the quanta_ratio. This remainder is used in subsequent + * quanta calculations. + */ + u64 quanta_remainder_ns; + + /** @total: total engine activity */ + u64 total; + + /** @running: true if engine is running some work */ + bool running; + + /** @metadata: snapshot of engine activity metadata */ + struct guc_engine_activity_metadata metadata; + + /** @activity: snapshot of engine activity counter */ + struct guc_engine_activity activity; +}; + +/** + * struct engine_activity_group - Activity data for all engines + */ +struct engine_activity_group { + /** @engine: engine specific activity data */ + struct engine_activity engine[GUC_MAX_ENGINE_CLASSES][GUC_MAX_INSTANCES_PER_CLASS]; +}; + +/** + * struct engine_activity_buffer - engine activity buffers + * + * This contains the buffers allocated for metadata and activity data + */ +struct engine_activity_buffer { + /** @activity_bo: object allocated to hold activity data */ + struct xe_bo *activity_bo; + + /** @metadata_bo: object allocated to hold activity metadata */ + struct xe_bo *metadata_bo; +}; + +/** + * struct xe_guc_engine_activity - Data used by engine activity implementation + */ +struct xe_guc_engine_activity { + /** @gpm_timestamp_shift: Right shift value for the gpm timestamp */ + u32 gpm_timestamp_shift; + + /** @num_activity_group: number of activity groups */ + u32 num_activity_group; + + /** @supported: indicates support for engine activity stats */ + bool supported; + + /** @eag: holds the device level engine activity data */ + struct engine_activity_group *eag; + + /** @device_buffer: buffer object for global engine activity */ + struct engine_activity_buffer device_buffer; +}; +#endif + diff --git a/drivers/gpu/drm/xe/xe_guc_fwif.h b/drivers/gpu/drm/xe/xe_guc_fwif.h index 057153f89b30..6f57578b07cb 100644 --- a/drivers/gpu/drm/xe/xe_guc_fwif.h +++ b/drivers/gpu/drm/xe/xe_guc_fwif.h @@ -208,6 +208,25 @@ struct guc_engine_usage { struct guc_engine_usage_record engines[GUC_MAX_ENGINE_CLASSES][GUC_MAX_INSTANCES_PER_CLASS]; } __packed; +/* Engine Activity stats */ +struct guc_engine_activity { + u16 change_num; + u16 quanta_ratio; + u32 last_update_tick; + u64 active_ticks; +} __packed; + +struct guc_engine_activity_data { + struct guc_engine_activity engine_activity[GUC_MAX_ENGINE_CLASSES][GUC_MAX_INSTANCES_PER_CLASS]; +} __packed; + +struct guc_engine_activity_metadata { + u32 guc_tsc_frequency_hz; + u32 lag_latency_usec; + u32 global_change_num; + u32 reserved; +} __packed; + /* This action will be programmed in C1BC - SOFT_SCRATCH_15_REG */ enum xe_guc_recv_message { XE_GUC_RECV_MSG_CRASH_DUMP_POSTED = BIT(1), diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c index 02409eedb914..25040efa043f 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc.c +++ b/drivers/gpu/drm/xe/xe_guc_pc.c @@ -995,6 +995,17 @@ out: return ret; } +static int pc_action_set_strategy(struct xe_guc_pc *pc, u32 val) +{ + int ret = 0; + + ret = pc_action_set_param(pc, + SLPC_PARAM_STRATEGIES, + val); + + return ret; +} + /** * xe_guc_pc_start - Start GuC's Power Conservation component * @pc: Xe_GuC_PC instance @@ -1054,6 +1065,11 @@ int xe_guc_pc_start(struct xe_guc_pc *pc) } ret = pc_action_setup_gucrc(pc, GUCRC_FIRMWARE_CONTROL); + if (ret) + goto out; + + /* Enable SLPC Optimized Strategy for compute */ + ret = pc_action_set_strategy(pc, SLPC_OPTIMIZED_STRATEGY_COMPUTE); out: xe_force_wake_put(gt_to_fw(gt), fw_ref); diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 913c74d6e2ae..b95934055f72 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -15,6 +15,7 @@ #include <drm/drm_managed.h> #include "abi/guc_actions_abi.h" +#include "abi/guc_actions_slpc_abi.h" #include "abi/guc_klvs_abi.h" #include "regs/xe_lrc_layout.h" #include "xe_assert.h" @@ -400,6 +401,7 @@ static void __guc_exec_queue_policy_add_##func(struct exec_queue_policy *policy, MAKE_EXEC_QUEUE_POLICY_ADD(execution_quantum, EXECUTION_QUANTUM) MAKE_EXEC_QUEUE_POLICY_ADD(preemption_timeout, PREEMPTION_TIMEOUT) MAKE_EXEC_QUEUE_POLICY_ADD(priority, SCHEDULING_PRIORITY) +MAKE_EXEC_QUEUE_POLICY_ADD(slpc_exec_queue_freq_req, SLPM_GT_FREQUENCY) #undef MAKE_EXEC_QUEUE_POLICY_ADD static const int xe_exec_queue_prio_to_guc[] = { @@ -414,14 +416,20 @@ static void init_policies(struct xe_guc *guc, struct xe_exec_queue *q) struct exec_queue_policy policy; enum xe_exec_queue_priority prio = q->sched_props.priority; u32 timeslice_us = q->sched_props.timeslice_us; + u32 slpc_exec_queue_freq_req = 0; u32 preempt_timeout_us = q->sched_props.preempt_timeout_us; xe_gt_assert(guc_to_gt(guc), exec_queue_registered(q)); + if (q->flags & EXEC_QUEUE_FLAG_LOW_LATENCY) + slpc_exec_queue_freq_req |= SLPC_CTX_FREQ_REQ_IS_COMPUTE; + __guc_exec_queue_policy_start_klv(&policy, q->guc->id); __guc_exec_queue_policy_add_priority(&policy, xe_exec_queue_prio_to_guc[prio]); __guc_exec_queue_policy_add_execution_quantum(&policy, timeslice_us); __guc_exec_queue_policy_add_preemption_timeout(&policy, preempt_timeout_us); + __guc_exec_queue_policy_add_slpc_exec_queue_freq_req(&policy, + slpc_exec_queue_freq_req); xe_guc_ct_send(&guc->ct, (u32 *)&policy.h2g, __guc_exec_queue_policy_action_size(&policy), 0, 0); @@ -1248,6 +1256,8 @@ static void __guc_exec_queue_fini_async(struct work_struct *w) if (xe_exec_queue_is_lr(q)) cancel_work_sync(&ge->lr_tdr); + /* Confirm no work left behind accessing device structures */ + cancel_delayed_work_sync(&ge->sched.base.work_tdr); release_guc_id(guc, q); xe_sched_entity_fini(&ge->entity); xe_sched_fini(&ge->sched); diff --git a/drivers/gpu/drm/xe/xe_guc_types.h b/drivers/gpu/drm/xe/xe_guc_types.h index 573aa6308380..63bac64429a5 100644 --- a/drivers/gpu/drm/xe/xe_guc_types.h +++ b/drivers/gpu/drm/xe/xe_guc_types.h @@ -13,6 +13,7 @@ #include "xe_guc_ads_types.h" #include "xe_guc_buf_types.h" #include "xe_guc_ct_types.h" +#include "xe_guc_engine_activity_types.h" #include "xe_guc_fwif.h" #include "xe_guc_log_types.h" #include "xe_guc_pc_types.h" @@ -103,6 +104,9 @@ struct xe_guc { /** @relay: GuC Relay Communication used in SR-IOV */ struct xe_guc_relay relay; + /** @engine_activity: Device specific engine activity */ + struct xe_guc_engine_activity engine_activity; + /** * @notify_reg: Register which is written to notify GuC of H2G messages */ diff --git a/drivers/gpu/drm/xe/xe_heci_gsc.c b/drivers/gpu/drm/xe/xe_heci_gsc.c index 06dc78d3a812..27d11e06a82b 100644 --- a/drivers/gpu/drm/xe/xe_heci_gsc.c +++ b/drivers/gpu/drm/xe/xe_heci_gsc.c @@ -89,12 +89,9 @@ static void heci_gsc_release_dev(struct device *dev) kfree(adev); } -void xe_heci_gsc_fini(struct xe_device *xe) +static void xe_heci_gsc_fini(void *arg) { - struct xe_heci_gsc *heci_gsc = &xe->heci_gsc; - - if (!xe->info.has_heci_gscfi && !xe->info.has_heci_cscfi) - return; + struct xe_heci_gsc *heci_gsc = arg; if (heci_gsc->adev) { struct auxiliary_device *aux_dev = &heci_gsc->adev->aux_dev; @@ -106,6 +103,7 @@ void xe_heci_gsc_fini(struct xe_device *xe) if (heci_gsc->irq >= 0) irq_free_desc(heci_gsc->irq); + heci_gsc->irq = -1; } @@ -172,14 +170,14 @@ static int heci_gsc_add_device(struct xe_device *xe, const struct heci_gsc_def * return ret; } -void xe_heci_gsc_init(struct xe_device *xe) +int xe_heci_gsc_init(struct xe_device *xe) { struct xe_heci_gsc *heci_gsc = &xe->heci_gsc; - const struct heci_gsc_def *def; + const struct heci_gsc_def *def = NULL; int ret; if (!xe->info.has_heci_gscfi && !xe->info.has_heci_cscfi) - return; + return 0; heci_gsc->irq = -1; @@ -191,29 +189,24 @@ void xe_heci_gsc_init(struct xe_device *xe) def = &heci_gsc_def_dg2; } else if (xe->info.platform == XE_DG1) { def = &heci_gsc_def_dg1; - } else { - drm_warn_once(&xe->drm, "Unknown platform\n"); - return; } - if (!def->name) { - drm_warn_once(&xe->drm, "HECI is not implemented!\n"); - return; + if (!def || !def->name) { + drm_warn(&xe->drm, "HECI is not implemented!\n"); + return 0; } - if (!def->use_polling && !xe_survivability_mode_enabled(xe)) { + ret = devm_add_action_or_reset(xe->drm.dev, xe_heci_gsc_fini, heci_gsc); + if (ret) + return ret; + + if (!def->use_polling && !xe_survivability_mode_is_enabled(xe)) { ret = heci_gsc_irq_setup(xe); if (ret) - goto fail; + return ret; } - ret = heci_gsc_add_device(xe, def); - if (ret) - goto fail; - - return; -fail: - xe_heci_gsc_fini(xe); + return heci_gsc_add_device(xe, def); } void xe_heci_gsc_irq_handler(struct xe_device *xe, u32 iir) diff --git a/drivers/gpu/drm/xe/xe_heci_gsc.h b/drivers/gpu/drm/xe/xe_heci_gsc.h index 48b3b1838045..745eb6783942 100644 --- a/drivers/gpu/drm/xe/xe_heci_gsc.h +++ b/drivers/gpu/drm/xe/xe_heci_gsc.h @@ -33,8 +33,7 @@ struct xe_heci_gsc { int irq; }; -void xe_heci_gsc_init(struct xe_device *xe); -void xe_heci_gsc_fini(struct xe_device *xe); +int xe_heci_gsc_init(struct xe_device *xe); void xe_heci_gsc_irq_handler(struct xe_device *xe, u32 iir); void xe_heci_csc_irq_handler(struct xe_device *xe, u32 iir); diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c index 089834467880..392102515f3d 100644 --- a/drivers/gpu/drm/xe/xe_hmm.c +++ b/drivers/gpu/drm/xe/xe_hmm.c @@ -19,11 +19,10 @@ static u64 xe_npages_in_range(unsigned long start, unsigned long end) return (end - start) >> PAGE_SHIFT; } -/* +/** * xe_mark_range_accessed() - mark a range is accessed, so core mm * have such information for memory eviction or write back to * hard disk - * * @range: the range to mark * @write: if write to this range, we mark pages in this range * as dirty @@ -43,15 +42,51 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write) } } -/* +static int xe_alloc_sg(struct xe_device *xe, struct sg_table *st, + struct hmm_range *range, struct rw_semaphore *notifier_sem) +{ + unsigned long i, npages, hmm_pfn; + unsigned long num_chunks = 0; + int ret; + + /* HMM docs says this is needed. */ + ret = down_read_interruptible(notifier_sem); + if (ret) + return ret; + + if (mmu_interval_read_retry(range->notifier, range->notifier_seq)) { + up_read(notifier_sem); + return -EAGAIN; + } + + npages = xe_npages_in_range(range->start, range->end); + for (i = 0; i < npages;) { + unsigned long len; + + hmm_pfn = range->hmm_pfns[i]; + xe_assert(xe, hmm_pfn & HMM_PFN_VALID); + + len = 1UL << hmm_pfn_to_map_order(hmm_pfn); + + /* If order > 0 the page may extend beyond range->start */ + len -= (hmm_pfn & ~HMM_PFN_FLAGS) & (len - 1); + i += len; + num_chunks++; + } + up_read(notifier_sem); + + return sg_alloc_table(st, num_chunks, GFP_KERNEL); +} + +/** * xe_build_sg() - build a scatter gather table for all the physical pages/pfn * in a hmm_range. dma-map pages if necessary. dma-address is save in sg table * and will be used to program GPU page table later. - * * @xe: the xe device who will access the dma-address in sg table * @range: the hmm range that we build the sg table from. range->hmm_pfns[] * has the pfn numbers of pages that back up this hmm address range. * @st: pointer to the sg table. + * @notifier_sem: The xe notifier lock. * @write: whether we write to this range. This decides dma map direction * for system pages. If write we map it bi-diretional; otherwise * DMA_TO_DEVICE @@ -78,43 +113,84 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write) * Returns 0 if successful; -ENOMEM if fails to allocate memory */ static int xe_build_sg(struct xe_device *xe, struct hmm_range *range, - struct sg_table *st, bool write) + struct sg_table *st, + struct rw_semaphore *notifier_sem, + bool write) { + unsigned long npages = xe_npages_in_range(range->start, range->end); struct device *dev = xe->drm.dev; - struct page **pages; - u64 i, npages; - int ret; + struct scatterlist *sgl; + struct page *page; + unsigned long i, j; - npages = xe_npages_in_range(range->start, range->end); - pages = kvmalloc_array(npages, sizeof(*pages), GFP_KERNEL); - if (!pages) - return -ENOMEM; + lockdep_assert_held(notifier_sem); - for (i = 0; i < npages; i++) { - pages[i] = hmm_pfn_to_page(range->hmm_pfns[i]); - xe_assert(xe, !is_device_private_page(pages[i])); + i = 0; + for_each_sg(st->sgl, sgl, st->nents, j) { + unsigned long hmm_pfn, size; + + hmm_pfn = range->hmm_pfns[i]; + page = hmm_pfn_to_page(hmm_pfn); + xe_assert(xe, !is_device_private_page(page)); + + size = 1UL << hmm_pfn_to_map_order(hmm_pfn); + size -= page_to_pfn(page) & (size - 1); + i += size; + + if (unlikely(j == st->nents - 1)) { + if (i > npages) + size -= (i - npages); + sg_mark_end(sgl); + } + sg_set_page(sgl, page, size << PAGE_SHIFT, 0); } + xe_assert(xe, i == npages); - ret = sg_alloc_table_from_pages_segment(st, pages, npages, 0, npages << PAGE_SHIFT, - xe_sg_segment_size(dev), GFP_KERNEL); - if (ret) - goto free_pages; + return dma_map_sgtable(dev, st, write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING); +} + +static void xe_hmm_userptr_set_mapped(struct xe_userptr_vma *uvma) +{ + struct xe_userptr *userptr = &uvma->userptr; + struct xe_vm *vm = xe_vma_vm(&uvma->vma); + + lockdep_assert_held_write(&vm->lock); + lockdep_assert_held(&vm->userptr.notifier_lock); + + mutex_lock(&userptr->unmap_mutex); + xe_assert(vm->xe, !userptr->mapped); + userptr->mapped = true; + mutex_unlock(&userptr->unmap_mutex); +} + +void xe_hmm_userptr_unmap(struct xe_userptr_vma *uvma) +{ + struct xe_userptr *userptr = &uvma->userptr; + struct xe_vma *vma = &uvma->vma; + bool write = !xe_vma_read_only(vma); + struct xe_vm *vm = xe_vma_vm(vma); + struct xe_device *xe = vm->xe; - ret = dma_map_sgtable(dev, st, write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING); - if (ret) { - sg_free_table(st); - st = NULL; + if (!lockdep_is_held_type(&vm->userptr.notifier_lock, 0) && + !lockdep_is_held_type(&vm->lock, 0) && + !(vma->gpuva.flags & XE_VMA_DESTROYED)) { + /* Don't unmap in exec critical section. */ + xe_vm_assert_held(vm); + /* Don't unmap while mapping the sg. */ + lockdep_assert_held(&vm->lock); } -free_pages: - kvfree(pages); - return ret; + mutex_lock(&userptr->unmap_mutex); + if (userptr->sg && userptr->mapped) + dma_unmap_sgtable(xe->drm.dev, userptr->sg, + write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, 0); + userptr->mapped = false; + mutex_unlock(&userptr->unmap_mutex); } -/* +/** * xe_hmm_userptr_free_sg() - Free the scatter gather table of userptr - * * @uvma: the userptr vma which hold the scatter gather table * * With function xe_userptr_populate_range, we allocate storage of @@ -124,16 +200,9 @@ free_pages: void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma) { struct xe_userptr *userptr = &uvma->userptr; - struct xe_vma *vma = &uvma->vma; - bool write = !xe_vma_read_only(vma); - struct xe_vm *vm = xe_vma_vm(vma); - struct xe_device *xe = vm->xe; - struct device *dev = xe->drm.dev; - - xe_assert(xe, userptr->sg); - dma_unmap_sgtable(dev, userptr->sg, - write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, 0); + xe_assert(xe_vma_vm(&uvma->vma)->xe, userptr->sg); + xe_hmm_userptr_unmap(uvma); sg_free_table(userptr->sg); userptr->sg = NULL; } @@ -166,13 +235,20 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, { unsigned long timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); - unsigned long *pfns, flags = HMM_PFN_REQ_FAULT; + unsigned long *pfns; struct xe_userptr *userptr; struct xe_vma *vma = &uvma->vma; u64 userptr_start = xe_vma_userptr(vma); u64 userptr_end = userptr_start + xe_vma_size(vma); struct xe_vm *vm = xe_vma_vm(vma); - struct hmm_range hmm_range; + struct hmm_range hmm_range = { + .pfn_flags_mask = 0, /* ignore pfns */ + .default_flags = HMM_PFN_REQ_FAULT, + .start = userptr_start, + .end = userptr_end, + .notifier = &uvma->userptr.notifier, + .dev_private_owner = vm->xe, + }; bool write = !xe_vma_read_only(vma); unsigned long notifier_seq; u64 npages; @@ -199,19 +275,14 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, return -ENOMEM; if (write) - flags |= HMM_PFN_REQ_WRITE; + hmm_range.default_flags |= HMM_PFN_REQ_WRITE; if (!mmget_not_zero(userptr->notifier.mm)) { ret = -EFAULT; goto free_pfns; } - hmm_range.default_flags = flags; hmm_range.hmm_pfns = pfns; - hmm_range.notifier = &userptr->notifier; - hmm_range.start = userptr_start; - hmm_range.end = userptr_end; - hmm_range.dev_private_owner = vm->xe; while (true) { hmm_range.notifier_seq = mmu_interval_read_begin(&userptr->notifier); @@ -238,16 +309,37 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, if (ret) goto free_pfns; - ret = xe_build_sg(vm->xe, &hmm_range, &userptr->sgt, write); + ret = xe_alloc_sg(vm->xe, &userptr->sgt, &hmm_range, &vm->userptr.notifier_lock); if (ret) goto free_pfns; + ret = down_read_interruptible(&vm->userptr.notifier_lock); + if (ret) + goto free_st; + + if (mmu_interval_read_retry(hmm_range.notifier, hmm_range.notifier_seq)) { + ret = -EAGAIN; + goto out_unlock; + } + + ret = xe_build_sg(vm->xe, &hmm_range, &userptr->sgt, + &vm->userptr.notifier_lock, write); + if (ret) + goto out_unlock; + xe_mark_range_accessed(&hmm_range, write); userptr->sg = &userptr->sgt; + xe_hmm_userptr_set_mapped(uvma); userptr->notifier_seq = hmm_range.notifier_seq; + up_read(&vm->userptr.notifier_lock); + kvfree(pfns); + return 0; +out_unlock: + up_read(&vm->userptr.notifier_lock); +free_st: + sg_free_table(&userptr->sgt); free_pfns: kvfree(pfns); return ret; } - diff --git a/drivers/gpu/drm/xe/xe_hmm.h b/drivers/gpu/drm/xe/xe_hmm.h index 909dc2bdcd97..0ea98d8e7bbc 100644 --- a/drivers/gpu/drm/xe/xe_hmm.h +++ b/drivers/gpu/drm/xe/xe_hmm.h @@ -3,9 +3,16 @@ * Copyright © 2024 Intel Corporation */ +#ifndef _XE_HMM_H_ +#define _XE_HMM_H_ + #include <linux/types.h> struct xe_userptr_vma; int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, bool is_mm_mmap_locked); + void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma); + +void xe_hmm_userptr_unmap(struct xe_userptr_vma *uvma); +#endif diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c index fc447751fe78..223b95de388c 100644 --- a/drivers/gpu/drm/xe/xe_hw_engine.c +++ b/drivers/gpu/drm/xe/xe_hw_engine.c @@ -400,10 +400,9 @@ xe_hw_engine_setup_default_lrc_state(struct xe_hw_engine *hwe) PREEMPT_GPGPU_THREAD_GROUP_LEVEL)), XE_RTP_ENTRY_FLAG(FOREACH_ENGINE) }, - {} }; - xe_rtp_process_to_sr(&ctx, lrc_setup, &hwe->reg_lrc); + xe_rtp_process_to_sr(&ctx, lrc_setup, ARRAY_SIZE(lrc_setup), &hwe->reg_lrc); } static void @@ -459,10 +458,9 @@ hw_engine_setup_default_state(struct xe_hw_engine *hwe) XE_RTP_ACTIONS(SET(CSFE_CHICKEN1(0), CS_PRIORITY_MEM_READ, XE_RTP_ACTION_FLAG(ENGINE_BASE))) }, - {} }; - xe_rtp_process_to_sr(&ctx, engine_entries, &hwe->reg_sr); + xe_rtp_process_to_sr(&ctx, engine_entries, ARRAY_SIZE(engine_entries), &hwe->reg_sr); } static const struct engine_info *find_engine_info(enum xe_engine_class class, int instance) diff --git a/drivers/gpu/drm/xe/xe_hw_engine_group.c b/drivers/gpu/drm/xe/xe_hw_engine_group.c index 82750520a90a..2d68c5b5262a 100644 --- a/drivers/gpu/drm/xe/xe_hw_engine_group.c +++ b/drivers/gpu/drm/xe/xe_hw_engine_group.c @@ -178,6 +178,7 @@ err_suspend: up_write(&group->mode_sem); return err; } +ALLOW_ERROR_INJECTION(xe_hw_engine_group_add_exec_queue, ERRNO); /** * xe_hw_engine_group_del_exec_queue() - Delete an exec queue from a hw engine group diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 278bc96cf593..df4282c71bf0 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -1544,6 +1544,181 @@ void xe_migrate_wait(struct xe_migrate *m) dma_fence_wait(m->fence, false); } +static u32 pte_update_cmd_size(u64 size) +{ + u32 num_dword; + u64 entries = DIV_ROUND_UP(size, XE_PAGE_SIZE); + + XE_WARN_ON(size > MAX_PREEMPTDISABLE_TRANSFER); + /* + * MI_STORE_DATA_IMM command is used to update page table. Each + * instruction can update maximumly 0x1ff pte entries. To update + * n (n <= 0x1ff) pte entries, we need: + * 1 dword for the MI_STORE_DATA_IMM command header (opcode etc) + * 2 dword for the page table's physical location + * 2*n dword for value of pte to fill (each pte entry is 2 dwords) + */ + num_dword = (1 + 2) * DIV_ROUND_UP(entries, 0x1ff); + num_dword += entries * 2; + + return num_dword; +} + +static void build_pt_update_batch_sram(struct xe_migrate *m, + struct xe_bb *bb, u32 pt_offset, + dma_addr_t *sram_addr, u32 size) +{ + u16 pat_index = tile_to_xe(m->tile)->pat.idx[XE_CACHE_WB]; + u32 ptes; + int i = 0; + + ptes = DIV_ROUND_UP(size, XE_PAGE_SIZE); + while (ptes) { + u32 chunk = min(0x1ffU, ptes); + + bb->cs[bb->len++] = MI_STORE_DATA_IMM | MI_SDI_NUM_QW(chunk); + bb->cs[bb->len++] = pt_offset; + bb->cs[bb->len++] = 0; + + pt_offset += chunk * 8; + ptes -= chunk; + + while (chunk--) { + u64 addr = sram_addr[i++] & PAGE_MASK; + + xe_tile_assert(m->tile, addr); + addr = m->q->vm->pt_ops->pte_encode_addr(m->tile->xe, + addr, pat_index, + 0, false, 0); + bb->cs[bb->len++] = lower_32_bits(addr); + bb->cs[bb->len++] = upper_32_bits(addr); + } + } +} + +enum xe_migrate_copy_dir { + XE_MIGRATE_COPY_TO_VRAM, + XE_MIGRATE_COPY_TO_SRAM, +}; + +static struct dma_fence *xe_migrate_vram(struct xe_migrate *m, + unsigned long npages, + dma_addr_t *sram_addr, u64 vram_addr, + const enum xe_migrate_copy_dir dir) +{ + struct xe_gt *gt = m->tile->primary_gt; + struct xe_device *xe = gt_to_xe(gt); + struct dma_fence *fence = NULL; + u32 batch_size = 2; + u64 src_L0_ofs, dst_L0_ofs; + u64 round_update_size; + struct xe_sched_job *job; + struct xe_bb *bb; + u32 update_idx, pt_slot = 0; + int err; + + if (npages * PAGE_SIZE > MAX_PREEMPTDISABLE_TRANSFER) + return ERR_PTR(-EINVAL); + + round_update_size = npages * PAGE_SIZE; + batch_size += pte_update_cmd_size(round_update_size); + batch_size += EMIT_COPY_DW; + + bb = xe_bb_new(gt, batch_size, true); + if (IS_ERR(bb)) { + err = PTR_ERR(bb); + return ERR_PTR(err); + } + + build_pt_update_batch_sram(m, bb, pt_slot * XE_PAGE_SIZE, + sram_addr, round_update_size); + + if (dir == XE_MIGRATE_COPY_TO_VRAM) { + src_L0_ofs = xe_migrate_vm_addr(pt_slot, 0); + dst_L0_ofs = xe_migrate_vram_ofs(xe, vram_addr, false); + + } else { + src_L0_ofs = xe_migrate_vram_ofs(xe, vram_addr, false); + dst_L0_ofs = xe_migrate_vm_addr(pt_slot, 0); + } + + bb->cs[bb->len++] = MI_BATCH_BUFFER_END; + update_idx = bb->len; + + emit_copy(gt, bb, src_L0_ofs, dst_L0_ofs, round_update_size, + XE_PAGE_SIZE); + + job = xe_bb_create_migration_job(m->q, bb, + xe_migrate_batch_base(m, true), + update_idx); + if (IS_ERR(job)) { + err = PTR_ERR(job); + goto err; + } + + xe_sched_job_add_migrate_flush(job, 0); + + mutex_lock(&m->job_mutex); + xe_sched_job_arm(job); + fence = dma_fence_get(&job->drm.s_fence->finished); + xe_sched_job_push(job); + + dma_fence_put(m->fence); + m->fence = dma_fence_get(fence); + mutex_unlock(&m->job_mutex); + + xe_bb_free(bb, fence); + + return fence; + +err: + xe_bb_free(bb, NULL); + + return ERR_PTR(err); +} + +/** + * xe_migrate_to_vram() - Migrate to VRAM + * @m: The migration context. + * @npages: Number of pages to migrate. + * @src_addr: Array of dma addresses (source of migrate) + * @dst_addr: Device physical address of VRAM (destination of migrate) + * + * Copy from an array dma addresses to a VRAM device physical address + * + * Return: dma fence for migrate to signal completion on succees, ERR_PTR on + * failure + */ +struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, + unsigned long npages, + dma_addr_t *src_addr, + u64 dst_addr) +{ + return xe_migrate_vram(m, npages, src_addr, dst_addr, + XE_MIGRATE_COPY_TO_VRAM); +} + +/** + * xe_migrate_from_vram() - Migrate from VRAM + * @m: The migration context. + * @npages: Number of pages to migrate. + * @src_addr: Device physical address of VRAM (source of migrate) + * @dst_addr: Array of dma addresses (destination of migrate) + * + * Copy from a VRAM device physical address to an array dma addresses + * + * Return: dma fence for migrate to signal completion on succees, ERR_PTR on + * failure + */ +struct dma_fence *xe_migrate_from_vram(struct xe_migrate *m, + unsigned long npages, + u64 src_addr, + dma_addr_t *dst_addr) +{ + return xe_migrate_vram(m, npages, dst_addr, src_addr, + XE_MIGRATE_COPY_TO_SRAM); +} + #if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST) #include "tests/xe_migrate.c" #endif diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h index 0109866e398a..6ff9a963425c 100644 --- a/drivers/gpu/drm/xe/xe_migrate.h +++ b/drivers/gpu/drm/xe/xe_migrate.h @@ -95,6 +95,16 @@ struct xe_migrate_pt_update { struct xe_migrate *xe_migrate_init(struct xe_tile *tile); +struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, + unsigned long npages, + dma_addr_t *src_addr, + u64 dst_addr); + +struct dma_fence *xe_migrate_from_vram(struct xe_migrate *m, + unsigned long npages, + u64 src_addr, + dma_addr_t *dst_addr); + struct dma_fence *xe_migrate_copy(struct xe_migrate *m, struct xe_bo *src_bo, struct xe_bo *dst_bo, diff --git a/drivers/gpu/drm/xe/xe_mocs.c b/drivers/gpu/drm/xe/xe_mocs.c index 54d199b5cfb2..31dade91a089 100644 --- a/drivers/gpu/drm/xe/xe_mocs.c +++ b/drivers/gpu/drm/xe/xe_mocs.c @@ -781,7 +781,9 @@ void xe_mocs_dump(struct xe_gt *gt, struct drm_printer *p) flags = get_mocs_settings(xe, &table); xe_pm_runtime_get_noresume(xe); - fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); + fw_ref = xe_force_wake_get(gt_to_fw(gt), + flags & HAS_LNCF_MOCS ? + XE_FORCEWAKE_ALL : XE_FW_GT); if (!fw_ref) goto err_fw; diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c index 7185a2cdf6e3..9f4632e39a1a 100644 --- a/drivers/gpu/drm/xe/xe_module.c +++ b/drivers/gpu/drm/xe/xe_module.c @@ -22,9 +22,16 @@ struct xe_modparam xe_modparam = { .guc_log_level = 3, .force_probe = CONFIG_DRM_XE_FORCE_PROBE, .wedged_mode = 1, + .svm_notifier_size = 512, /* the rest are 0 by default */ }; +module_param_named(svm_notifier_size, xe_modparam.svm_notifier_size, uint, 0600); +MODULE_PARM_DESC(svm_notifier_size, "Set the svm notifier size(in MiB), must be power of 2"); + +module_param_named(always_migrate_to_vram, xe_modparam.always_migrate_to_vram, bool, 0444); +MODULE_PARM_DESC(always_migrate_to_vram, "Always migrate to VRAM on GPU fault"); + module_param_named_unsafe(force_execlist, xe_modparam.force_execlist, bool, 0444); MODULE_PARM_DESC(force_execlist, "Force Execlist submission"); diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm/xe/xe_module.h index 161a5e6f717f..84339e509c80 100644 --- a/drivers/gpu/drm/xe/xe_module.h +++ b/drivers/gpu/drm/xe/xe_module.h @@ -12,6 +12,7 @@ struct xe_modparam { bool force_execlist; bool probe_display; + bool always_migrate_to_vram; u32 force_vram_bar_size; int guc_log_level; char *guc_firmware_path; @@ -22,6 +23,7 @@ struct xe_modparam { unsigned int max_vfs; #endif int wedged_mode; + u32 svm_notifier_size; }; extern struct xe_modparam xe_modparam; diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index 2c5a24a13e87..6f185632da14 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -12,6 +12,8 @@ #include <drm/drm_managed.h> #include <uapi/drm/xe_drm.h> +#include <generated/xe_wa_oob.h> + #include "abi/guc_actions_slpc_abi.h" #include "instructions/xe_mi_commands.h" #include "regs/xe_engine_regs.h" @@ -35,6 +37,7 @@ #include "xe_sched_job.h" #include "xe_sriov.h" #include "xe_sync.h" +#include "xe_wa.h" #define DEFAULT_POLL_FREQUENCY_HZ 200 #define DEFAULT_POLL_PERIOD_NS (NSEC_PER_SEC / DEFAULT_POLL_FREQUENCY_HZ) @@ -812,11 +815,8 @@ static void xe_oa_disable_metric_set(struct xe_oa_stream *stream) struct xe_mmio *mmio = &stream->gt->mmio; u32 sqcnt1; - /* - * Wa_1508761755:xehpsdv, dg2 - * Enable thread stall DOP gating and EU DOP gating. - */ - if (stream->oa->xe->info.platform == XE_DG2) { + /* Enable thread stall DOP gating and EU DOP gating. */ + if (XE_WA(stream->gt, 1508761755)) { xe_gt_mcr_multicast_write(stream->gt, ROW_CHICKEN, _MASKED_BIT_DISABLE(STALL_DOP_GATING_DISABLE)); xe_gt_mcr_multicast_write(stream->gt, ROW_CHICKEN2, @@ -1065,11 +1065,10 @@ static int xe_oa_enable_metric_set(struct xe_oa_stream *stream) int ret; /* - * Wa_1508761755:xehpsdv, dg2 * EU NOA signals behave incorrectly if EU clock gating is enabled. * Disable thread stall DOP gating and EU DOP gating. */ - if (stream->oa->xe->info.platform == XE_DG2) { + if (XE_WA(stream->gt, 1508761755)) { xe_gt_mcr_multicast_write(stream->gt, ROW_CHICKEN, _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE)); xe_gt_mcr_multicast_write(stream->gt, ROW_CHICKEN2, @@ -1690,7 +1689,7 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream, stream->oa_buffer.format = &stream->oa->oa_formats[param->oa_format]; stream->sample = param->sample; - stream->periodic = param->period_exponent > 0; + stream->periodic = param->period_exponent >= 0; stream->period_exponent = param->period_exponent; stream->no_preempt = param->no_preempt; stream->wait_num_reports = param->wait_num_reports; @@ -1720,12 +1719,10 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream, } /* - * Wa_1509372804:pvc - * * GuC reset of engines causes OA to lose configuration * state. Prevent this by overriding GUCRC mode. */ - if (stream->oa->xe->info.platform == XE_PVC) { + if (XE_WA(stream->gt, 1509372804)) { ret = xe_guc_pc_override_gucrc_mode(>->uc.guc.pc, SLPC_GUCRC_MODE_GUCRC_NO_RC6); if (ret) @@ -1857,23 +1854,14 @@ u32 xe_oa_timestamp_frequency(struct xe_gt *gt) { u32 reg, shift; - /* - * Wa_18013179988:dg2 - * Wa_14015568240:pvc - * Wa_14015846243:mtl - */ - switch (gt_to_xe(gt)->info.platform) { - case XE_DG2: - case XE_PVC: - case XE_METEORLAKE: + if (XE_WA(gt, 18013179988) || XE_WA(gt, 14015568240)) { xe_pm_runtime_get(gt_to_xe(gt)); reg = xe_mmio_read32(>->mmio, RPM_CONFIG0); xe_pm_runtime_put(gt_to_xe(gt)); shift = REG_FIELD_GET(RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK, reg); return gt->info.reference_clock << (3 - shift); - - default: + } else { return gt->info.reference_clock; } } @@ -1971,6 +1959,7 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f } param.xef = xef; + param.period_exponent = -1; ret = xe_oa_user_extensions(oa, XE_OA_USER_EXTN_FROM_OPEN, data, 0, ¶m); if (ret) return ret; @@ -2025,7 +2014,7 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f goto err_exec_q; } - if (param.period_exponent > 0) { + if (param.period_exponent >= 0) { u64 oa_period, oa_freq_hz; /* Requesting samples from OAG buffer is a privileged operation */ diff --git a/drivers/gpu/drm/xe/xe_observation.c b/drivers/gpu/drm/xe/xe_observation.c index 57cf01efc07f..e3f9b546207e 100644 --- a/drivers/gpu/drm/xe/xe_observation.c +++ b/drivers/gpu/drm/xe/xe_observation.c @@ -8,6 +8,7 @@ #include <uapi/drm/xe_drm.h> +#include "xe_eu_stall.h" #include "xe_oa.h" #include "xe_observation.h" @@ -29,6 +30,17 @@ static int xe_oa_ioctl(struct drm_device *dev, struct drm_xe_observation_param * } } +static int xe_eu_stall_ioctl(struct drm_device *dev, struct drm_xe_observation_param *arg, + struct drm_file *file) +{ + switch (arg->observation_op) { + case DRM_XE_OBSERVATION_OP_STREAM_OPEN: + return xe_eu_stall_stream_open(dev, arg->param, file); + default: + return -EINVAL; + } +} + /** * xe_observation_ioctl - The top level observation layer ioctl * @dev: @drm_device @@ -51,6 +63,8 @@ int xe_observation_ioctl(struct drm_device *dev, void *data, struct drm_file *fi switch (arg->observation_type) { case DRM_XE_OBSERVATION_TYPE_OA: return xe_oa_ioctl(dev, arg, file); + case DRM_XE_OBSERVATION_TYPE_EU_STALL: + return xe_eu_stall_ioctl(dev, arg, file); default: return -EINVAL; } diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index f8417f4d8ce6..da9679c8cf26 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -46,9 +46,9 @@ struct xe_subplatform_desc { struct xe_device_desc { /* Should only ever be set for platforms without GMD_ID */ - const struct xe_graphics_desc *graphics; + const struct xe_ip *pre_gmdid_graphics_ip; /* Should only ever be set for platforms without GMD_ID */ - const struct xe_media_desc *media; + const struct xe_ip *pre_gmdid_media_ip; const char *platform_name; const struct xe_subplatform_desc *subplatforms; @@ -82,21 +82,6 @@ __diag_ignore_all("-Woverride-init", "Allow field overrides in table"); #define NOP(x) x static const struct xe_graphics_desc graphics_xelp = { - .name = "Xe_LP", - .ver = 12, - .rel = 0, - - .hw_engine_mask = BIT(XE_HW_ENGINE_RCS0) | BIT(XE_HW_ENGINE_BCS0), - - .va_bits = 48, - .vm_max_level = 3, -}; - -static const struct xe_graphics_desc graphics_xelpp = { - .name = "Xe_LP+", - .ver = 12, - .rel = 10, - .hw_engine_mask = BIT(XE_HW_ENGINE_RCS0) | BIT(XE_HW_ENGINE_BCS0), .va_bits = 48, @@ -109,10 +94,6 @@ static const struct xe_graphics_desc graphics_xelpp = { .vm_max_level = 3 static const struct xe_graphics_desc graphics_xehpg = { - .name = "Xe_HPG", - .ver = 12, - .rel = 55, - .hw_engine_mask = BIT(XE_HW_ENGINE_RCS0) | BIT(XE_HW_ENGINE_BCS0) | BIT(XE_HW_ENGINE_CCS0) | BIT(XE_HW_ENGINE_CCS1) | @@ -125,10 +106,6 @@ static const struct xe_graphics_desc graphics_xehpg = { }; static const struct xe_graphics_desc graphics_xehpc = { - .name = "Xe_HPC", - .ver = 12, - .rel = 60, - .hw_engine_mask = BIT(XE_HW_ENGINE_BCS0) | BIT(XE_HW_ENGINE_BCS1) | BIT(XE_HW_ENGINE_BCS2) | BIT(XE_HW_ENGINE_BCS3) | @@ -149,7 +126,6 @@ static const struct xe_graphics_desc graphics_xehpc = { }; static const struct xe_graphics_desc graphics_xelpg = { - .name = "Xe_LPG", .hw_engine_mask = BIT(XE_HW_ENGINE_RCS0) | BIT(XE_HW_ENGINE_BCS0) | BIT(XE_HW_ENGINE_CCS0), @@ -172,50 +148,54 @@ static const struct xe_graphics_desc graphics_xelpg = { GENMASK(XE_HW_ENGINE_CCS3, XE_HW_ENGINE_CCS0) static const struct xe_graphics_desc graphics_xe2 = { - .name = "Xe2_LPG / Xe2_HPG / Xe3_LPG", - XE2_GFX_FEATURES, }; static const struct xe_media_desc media_xem = { - .name = "Xe_M", - .ver = 12, - .rel = 0, - - .hw_engine_mask = - GENMASK(XE_HW_ENGINE_VCS7, XE_HW_ENGINE_VCS0) | - GENMASK(XE_HW_ENGINE_VECS3, XE_HW_ENGINE_VECS0), -}; - -static const struct xe_media_desc media_xehpm = { - .name = "Xe_HPM", - .ver = 12, - .rel = 55, - .hw_engine_mask = GENMASK(XE_HW_ENGINE_VCS7, XE_HW_ENGINE_VCS0) | GENMASK(XE_HW_ENGINE_VECS3, XE_HW_ENGINE_VECS0), }; static const struct xe_media_desc media_xelpmp = { - .name = "Xe_LPM+", .hw_engine_mask = GENMASK(XE_HW_ENGINE_VCS7, XE_HW_ENGINE_VCS0) | GENMASK(XE_HW_ENGINE_VECS3, XE_HW_ENGINE_VECS0) | BIT(XE_HW_ENGINE_GSCCS0) }; -static const struct xe_media_desc media_xe2 = { - .name = "Xe2_LPM / Xe2_HPM / Xe3_LPM", - .hw_engine_mask = - GENMASK(XE_HW_ENGINE_VCS7, XE_HW_ENGINE_VCS0) | - GENMASK(XE_HW_ENGINE_VECS3, XE_HW_ENGINE_VECS0) | - BIT(XE_HW_ENGINE_GSCCS0) +/* Pre-GMDID Graphics IPs */ +static const struct xe_ip graphics_ip_xelp = { 1200, "Xe_LP", &graphics_xelp }; +static const struct xe_ip graphics_ip_xelpp = { 1210, "Xe_LP+", &graphics_xelp }; +static const struct xe_ip graphics_ip_xehpg = { 1255, "Xe_HPG", &graphics_xehpg }; +static const struct xe_ip graphics_ip_xehpc = { 1260, "Xe_HPC", &graphics_xehpc }; + +/* GMDID-based Graphics IPs */ +static const struct xe_ip graphics_ips[] = { + { 1270, "Xe_LPG", &graphics_xelpg }, + { 1271, "Xe_LPG", &graphics_xelpg }, + { 1274, "Xe_LPG+", &graphics_xelpg }, + { 2001, "Xe2_HPG", &graphics_xe2 }, + { 2004, "Xe2_LPG", &graphics_xe2 }, + { 3000, "Xe3_LPG", &graphics_xe2 }, + { 3001, "Xe3_LPG", &graphics_xe2 }, +}; + +/* Pre-GMDID Media IPs */ +static const struct xe_ip media_ip_xem = { 1200, "Xe_M", &media_xem }; +static const struct xe_ip media_ip_xehpm = { 1255, "Xe_HPM", &media_xem }; + +/* GMDID-based Media IPs */ +static const struct xe_ip media_ips[] = { + { 1300, "Xe_LPM+", &media_xelpmp }, + { 1301, "Xe2_HPM", &media_xelpmp }, + { 2000, "Xe2_LPM", &media_xelpmp }, + { 3000, "Xe3_LPM", &media_xelpmp }, }; static const struct xe_device_desc tgl_desc = { - .graphics = &graphics_xelp, - .media = &media_xem, + .pre_gmdid_graphics_ip = &graphics_ip_xelp, + .pre_gmdid_media_ip = &media_ip_xem, PLATFORM(TIGERLAKE), .dma_mask_size = 39, .has_display = true, @@ -224,8 +204,8 @@ static const struct xe_device_desc tgl_desc = { }; static const struct xe_device_desc rkl_desc = { - .graphics = &graphics_xelp, - .media = &media_xem, + .pre_gmdid_graphics_ip = &graphics_ip_xelp, + .pre_gmdid_media_ip = &media_ip_xem, PLATFORM(ROCKETLAKE), .dma_mask_size = 39, .has_display = true, @@ -236,8 +216,8 @@ static const struct xe_device_desc rkl_desc = { static const u16 adls_rpls_ids[] = { INTEL_RPLS_IDS(NOP), 0 }; static const struct xe_device_desc adl_s_desc = { - .graphics = &graphics_xelp, - .media = &media_xem, + .pre_gmdid_graphics_ip = &graphics_ip_xelp, + .pre_gmdid_media_ip = &media_ip_xem, PLATFORM(ALDERLAKE_S), .dma_mask_size = 39, .has_display = true, @@ -252,8 +232,8 @@ static const struct xe_device_desc adl_s_desc = { static const u16 adlp_rplu_ids[] = { INTEL_RPLU_IDS(NOP), 0 }; static const struct xe_device_desc adl_p_desc = { - .graphics = &graphics_xelp, - .media = &media_xem, + .pre_gmdid_graphics_ip = &graphics_ip_xelp, + .pre_gmdid_media_ip = &media_ip_xem, PLATFORM(ALDERLAKE_P), .dma_mask_size = 39, .has_display = true, @@ -266,8 +246,8 @@ static const struct xe_device_desc adl_p_desc = { }; static const struct xe_device_desc adl_n_desc = { - .graphics = &graphics_xelp, - .media = &media_xem, + .pre_gmdid_graphics_ip = &graphics_ip_xelp, + .pre_gmdid_media_ip = &media_ip_xem, PLATFORM(ALDERLAKE_N), .dma_mask_size = 39, .has_display = true, @@ -279,8 +259,8 @@ static const struct xe_device_desc adl_n_desc = { .is_dgfx = 1 static const struct xe_device_desc dg1_desc = { - .graphics = &graphics_xelpp, - .media = &media_xem, + .pre_gmdid_graphics_ip = &graphics_ip_xelpp, + .pre_gmdid_media_ip = &media_ip_xem, DGFX_FEATURES, PLATFORM(DG1), .dma_mask_size = 39, @@ -305,8 +285,8 @@ static const u16 dg2_g12_ids[] = { INTEL_DG2_G12_IDS(NOP), 0 }; } static const struct xe_device_desc ats_m_desc = { - .graphics = &graphics_xehpg, - .media = &media_xehpm, + .pre_gmdid_graphics_ip = &graphics_ip_xehpg, + .pre_gmdid_media_ip = &media_ip_xehpm, .dma_mask_size = 46, .require_force_probe = true, @@ -315,8 +295,8 @@ static const struct xe_device_desc ats_m_desc = { }; static const struct xe_device_desc dg2_desc = { - .graphics = &graphics_xehpg, - .media = &media_xehpm, + .pre_gmdid_graphics_ip = &graphics_ip_xehpg, + .pre_gmdid_media_ip = &media_ip_xehpm, .dma_mask_size = 46, .require_force_probe = true, @@ -325,7 +305,7 @@ static const struct xe_device_desc dg2_desc = { }; static const __maybe_unused struct xe_device_desc pvc_desc = { - .graphics = &graphics_xehpc, + .pre_gmdid_graphics_ip = &graphics_ip_xehpc, DGFX_FEATURES, PLATFORM(PVC), .dma_mask_size = 52, @@ -370,25 +350,6 @@ static const struct xe_device_desc ptl_desc = { #undef PLATFORM __diag_pop(); -/* Map of GMD_ID values to graphics IP */ -static const struct gmdid_map graphics_ip_map[] = { - { 1270, &graphics_xelpg }, - { 1271, &graphics_xelpg }, - { 1274, &graphics_xelpg }, /* Xe_LPG+ */ - { 2001, &graphics_xe2 }, - { 2004, &graphics_xe2 }, - { 3000, &graphics_xe2 }, - { 3001, &graphics_xe2 }, -}; - -/* Map of GMD_ID values to media IP */ -static const struct gmdid_map media_ip_map[] = { - { 1300, &media_xelpmp }, - { 1301, &media_xe2 }, - { 2000, &media_xe2 }, - { 3000, &media_xe2 }, -}; - /* * Make sure any device matches here are from most specific to most * general. For example, since the Quanta match is based on the subsystem @@ -549,66 +510,49 @@ static void read_gmdid(struct xe_device *xe, enum xe_gmdid_type type, u32 *ver, } /* - * Pre-GMD_ID platform: device descriptor already points to the appropriate - * graphics descriptor. Simply forward the description and calculate the version - * appropriately. "graphics" should be present in all such platforms, while - * media is optional. - */ -static void handle_pre_gmdid(struct xe_device *xe, - const struct xe_graphics_desc *graphics, - const struct xe_media_desc *media) -{ - xe->info.graphics_verx100 = graphics->ver * 100 + graphics->rel; - - if (media) - xe->info.media_verx100 = media->ver * 100 + media->rel; - -} - -/* - * GMD_ID platform: read IP version from hardware and select graphics descriptor + * Read IP version from hardware and select graphics/media IP descriptors * based on the result. */ static void handle_gmdid(struct xe_device *xe, - const struct xe_graphics_desc **graphics, - const struct xe_media_desc **media, + const struct xe_ip **graphics_ip, + const struct xe_ip **media_ip, u32 *graphics_revid, u32 *media_revid) { u32 ver; + *graphics_ip = NULL; + *media_ip = NULL; + read_gmdid(xe, GMDID_GRAPHICS, &ver, graphics_revid); - for (int i = 0; i < ARRAY_SIZE(graphics_ip_map); i++) { - if (ver == graphics_ip_map[i].ver) { - xe->info.graphics_verx100 = ver; - *graphics = graphics_ip_map[i].ip; + for (int i = 0; i < ARRAY_SIZE(graphics_ips); i++) { + if (ver == graphics_ips[i].verx100) { + *graphics_ip = &graphics_ips[i]; break; } } - if (!xe->info.graphics_verx100) { + if (!*graphics_ip) { drm_err(&xe->drm, "Hardware reports unknown graphics version %u.%02u\n", ver / 100, ver % 100); } read_gmdid(xe, GMDID_MEDIA, &ver, media_revid); - /* Media may legitimately be fused off / not present */ if (ver == 0) return; - for (int i = 0; i < ARRAY_SIZE(media_ip_map); i++) { - if (ver == media_ip_map[i].ver) { - xe->info.media_verx100 = ver; - *media = media_ip_map[i].ip; + for (int i = 0; i < ARRAY_SIZE(media_ips); i++) { + if (ver == media_ips[i].verx100) { + *media_ip = &media_ips[i]; break; } } - if (!xe->info.media_verx100) { + if (!*media_ip) { drm_err(&xe->drm, "Hardware reports unknown media version %u.%02u\n", ver / 100, ver % 100); } @@ -659,26 +603,31 @@ static int xe_info_init_early(struct xe_device *xe, * present in device info. */ static int xe_info_init(struct xe_device *xe, - const struct xe_graphics_desc *graphics_desc, - const struct xe_media_desc *media_desc) + const struct xe_device_desc *desc) { u32 graphics_gmdid_revid = 0, media_gmdid_revid = 0; + const struct xe_ip *graphics_ip; + const struct xe_ip *media_ip; + const struct xe_graphics_desc *graphics_desc; + const struct xe_media_desc *media_desc; struct xe_tile *tile; struct xe_gt *gt; u8 id; /* * If this platform supports GMD_ID, we'll detect the proper IP - * descriptor to use from hardware registers. desc->graphics will only - * ever be set at this point for platforms before GMD_ID. In that case - * the IP descriptions and versions are simply derived from that. + * descriptor to use from hardware registers. + * desc->pre_gmdid_graphics_ip will only ever be set at this point for + * platforms before GMD_ID. In that case the IP descriptions and + * versions are simply derived from that. */ - if (graphics_desc) { - handle_pre_gmdid(xe, graphics_desc, media_desc); + if (desc->pre_gmdid_graphics_ip) { + graphics_ip = desc->pre_gmdid_graphics_ip; + media_ip = desc->pre_gmdid_media_ip; xe->info.step = xe_step_pre_gmdid_get(xe); } else { - xe_assert(xe, !media_desc); - handle_gmdid(xe, &graphics_desc, &media_desc, + xe_assert(xe, !desc->pre_gmdid_media_ip); + handle_gmdid(xe, &graphics_ip, &media_ip, &graphics_gmdid_revid, &media_gmdid_revid); xe->info.step = xe_step_gmdid_get(xe, graphics_gmdid_revid, @@ -690,11 +639,21 @@ static int xe_info_init(struct xe_device *xe, * error and we should abort driver load. Failing to detect media * IP is non-fatal; we'll just proceed without enabling media support. */ - if (!graphics_desc) + if (!graphics_ip) return -ENODEV; - xe->info.graphics_name = graphics_desc->name; - xe->info.media_name = media_desc ? media_desc->name : "none"; + xe->info.graphics_verx100 = graphics_ip->verx100; + xe->info.graphics_name = graphics_ip->name; + graphics_desc = graphics_ip->desc; + + if (media_ip) { + xe->info.media_verx100 = media_ip->verx100; + xe->info.media_name = media_ip->name; + media_desc = media_ip->desc; + } else { + xe->info.media_name = "none"; + media_desc = NULL; + } xe->info.vram_flags = graphics_desc->vram_flags; xe->info.va_bits = graphics_desc->va_bits; @@ -765,21 +724,16 @@ static int xe_info_init(struct xe_device *xe, static void xe_pci_remove(struct pci_dev *pdev) { - struct xe_device *xe; - - xe = pdev_to_xe_device(pdev); - if (!xe) /* driver load aborted, nothing to cleanup */ - return; + struct xe_device *xe = pdev_to_xe_device(pdev); if (IS_SRIOV_PF(xe)) xe_pci_sriov_configure(pdev, 0); - if (xe_survivability_mode_enabled(xe)) - return xe_survivability_mode_remove(xe); + if (xe_survivability_mode_is_enabled(xe)) + return; xe_device_remove(xe); xe_pm_runtime_fini(xe); - pci_set_drvdata(pdev, NULL); } /* @@ -851,19 +805,20 @@ static int xe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = xe_device_probe_early(xe); /* - * In Boot Survivability mode, no drm card is exposed - * and driver is loaded with bare minimum to allow - * for firmware to be flashed through mei. Return - * success if survivability mode is enabled. + * In Boot Survivability mode, no drm card is exposed and driver is + * loaded with bare minimum to allow for firmware to be flashed through + * mei. If early probe fails, check if survivability mode is flagged by + * HW to be enabled. In that case enable it and return success. */ if (err) { - if (xe_survivability_mode_enabled(xe)) + if (xe_survivability_mode_required(xe) && + xe_survivability_mode_enable(xe)) return 0; return err; } - err = xe_info_init(xe, desc->graphics, desc->media); + err = xe_info_init(xe, desc); if (err) return err; @@ -900,10 +855,8 @@ static int xe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return err; err = xe_device_probe(xe); - if (err) { - xe_device_call_remove_actions(xe); + if (err) return err; - } err = xe_pm_init(xe); if (err) @@ -953,7 +906,7 @@ static int xe_pci_suspend(struct device *dev) struct xe_device *xe = pdev_to_xe_device(pdev); int err; - if (xe_survivability_mode_enabled(xe)) + if (xe_survivability_mode_is_enabled(xe)) return -EBUSY; err = xe_pm_suspend(xe); diff --git a/drivers/gpu/drm/xe/xe_pci_sriov.c b/drivers/gpu/drm/xe/xe_pci_sriov.c index aaceee748287..09ee8a06fe2e 100644 --- a/drivers/gpu/drm/xe/xe_pci_sriov.c +++ b/drivers/gpu/drm/xe/xe_pci_sriov.c @@ -62,6 +62,55 @@ static void pf_reset_vfs(struct xe_device *xe, unsigned int num_vfs) xe_gt_sriov_pf_control_trigger_flr(gt, n); } +static struct pci_dev *xe_pci_pf_get_vf_dev(struct xe_device *xe, unsigned int vf_id) +{ + struct pci_dev *pdev = to_pci_dev(xe->drm.dev); + + xe_assert(xe, IS_SRIOV_PF(xe)); + + /* caller must use pci_dev_put() */ + return pci_get_domain_bus_and_slot(pci_domain_nr(pdev->bus), + pdev->bus->number, + pci_iov_virtfn_devfn(pdev, vf_id)); +} + +static void pf_link_vfs(struct xe_device *xe, int num_vfs) +{ + struct pci_dev *pdev_pf = to_pci_dev(xe->drm.dev); + struct device_link *link; + struct pci_dev *pdev_vf; + unsigned int n; + + /* + * When both PF and VF devices are enabled on the host, during system + * resume they are resuming in parallel. + * + * But PF has to complete the provision of VF first to allow any VFs to + * successfully resume. + * + * Create a parent-child device link between PF and VF devices that will + * enforce correct resume order. + */ + for (n = 1; n <= num_vfs; n++) { + pdev_vf = xe_pci_pf_get_vf_dev(xe, n - 1); + + /* unlikely, something weird is happening, abort */ + if (!pdev_vf) { + xe_sriov_err(xe, "Cannot find VF%u device, aborting link%s creation!\n", + n, str_plural(num_vfs)); + break; + } + + link = device_link_add(&pdev_vf->dev, &pdev_pf->dev, + DL_FLAG_AUTOREMOVE_CONSUMER); + /* unlikely and harmless, continue with other VFs */ + if (!link) + xe_sriov_notice(xe, "Failed linking VF%u\n", n); + + pci_dev_put(pdev_vf); + } +} + static int pf_enable_vfs(struct xe_device *xe, int num_vfs) { struct pci_dev *pdev = to_pci_dev(xe->drm.dev); @@ -92,6 +141,8 @@ static int pf_enable_vfs(struct xe_device *xe, int num_vfs) if (err < 0) goto failed; + pf_link_vfs(xe, num_vfs); + xe_sriov_info(xe, "Enabled %u of %u VF%s\n", num_vfs, total_vfs, str_plural(total_vfs)); return num_vfs; diff --git a/drivers/gpu/drm/xe/xe_pci_types.h b/drivers/gpu/drm/xe/xe_pci_types.h index b96423844952..e9b9bbc138d3 100644 --- a/drivers/gpu/drm/xe/xe_pci_types.h +++ b/drivers/gpu/drm/xe/xe_pci_types.h @@ -9,10 +9,6 @@ #include <linux/types.h> struct xe_graphics_desc { - const char *name; - u8 ver; - u8 rel; - u8 va_bits; u8 vm_max_level; u8 vram_flags; @@ -28,18 +24,15 @@ struct xe_graphics_desc { }; struct xe_media_desc { - const char *name; - u8 ver; - u8 rel; - u64 hw_engine_mask; /* hardware engines provided by media IP */ u8 has_indirect_ring_state:1; }; -struct gmdid_map { - unsigned int ver; - const void *ip; +struct xe_ip { + unsigned int verx100; + const char *name; + const void *desc; }; #endif diff --git a/drivers/gpu/drm/xe/xe_pmu.c b/drivers/gpu/drm/xe/xe_pmu.c index 3910a82328ee..4f62a6e515d6 100644 --- a/drivers/gpu/drm/xe/xe_pmu.c +++ b/drivers/gpu/drm/xe/xe_pmu.c @@ -7,16 +7,18 @@ #include <linux/device.h> #include "xe_device.h" +#include "xe_force_wake.h" #include "xe_gt_idle.h" +#include "xe_guc_engine_activity.h" +#include "xe_hw_engine.h" #include "xe_pm.h" #include "xe_pmu.h" /** * DOC: Xe PMU (Performance Monitoring Unit) * - * Expose events/counters like GT-C6 residency and GT frequency to user land via - * the perf interface. Events are per device. The GT can be selected with an - * extra config sub-field (bits 60-63). + * Expose events/counters like GT-C6 residency, GT frequency and per-class-engine + * activity to user land via the perf interface. Events are per device. * * All events are listed in sysfs: * @@ -24,7 +26,18 @@ * $ ls /sys/bus/event_source/devices/xe_0000_00_02.0/events/ * $ ls /sys/bus/event_source/devices/xe_0000_00_02.0/format/ * - * The format directory has info regarding the configs that can be used. + * The following format parameters are available to read events, + * but only few are valid with each event: + * + * gt[60:63] Selects gt for the event + * engine_class[20:27] Selects engine-class for event + * engine_instance[12:19] Selects the engine-instance for the event + * + * For engine specific events (engine-*), gt, engine_class and engine_instance parameters must be + * set as populated by DRM_XE_DEVICE_QUERY_ENGINES. + * + * For gt specific events (gt-*) gt parameter must be passed. All other parameters will be 0. + * * The standard perf tool can be used to grep for a certain event as well. * Example: * @@ -35,20 +48,34 @@ * $ perf stat -e <event_name,gt=> -I <interval> */ -#define XE_PMU_EVENT_GT_MASK GENMASK_ULL(63, 60) -#define XE_PMU_EVENT_ID_MASK GENMASK_ULL(11, 0) +#define XE_PMU_EVENT_GT_MASK GENMASK_ULL(63, 60) +#define XE_PMU_EVENT_ENGINE_CLASS_MASK GENMASK_ULL(27, 20) +#define XE_PMU_EVENT_ENGINE_INSTANCE_MASK GENMASK_ULL(19, 12) +#define XE_PMU_EVENT_ID_MASK GENMASK_ULL(11, 0) static unsigned int config_to_event_id(u64 config) { return FIELD_GET(XE_PMU_EVENT_ID_MASK, config); } +static unsigned int config_to_engine_class(u64 config) +{ + return FIELD_GET(XE_PMU_EVENT_ENGINE_CLASS_MASK, config); +} + +static unsigned int config_to_engine_instance(u64 config) +{ + return FIELD_GET(XE_PMU_EVENT_ENGINE_INSTANCE_MASK, config); +} + static unsigned int config_to_gt_id(u64 config) { return FIELD_GET(XE_PMU_EVENT_GT_MASK, config); } -#define XE_PMU_EVENT_GT_C6_RESIDENCY 0x01 +#define XE_PMU_EVENT_GT_C6_RESIDENCY 0x01 +#define XE_PMU_EVENT_ENGINE_ACTIVE_TICKS 0x02 +#define XE_PMU_EVENT_ENGINE_TOTAL_TICKS 0x03 static struct xe_gt *event_to_gt(struct perf_event *event) { @@ -58,6 +85,59 @@ static struct xe_gt *event_to_gt(struct perf_event *event) return xe_device_get_gt(xe, gt); } +static struct xe_hw_engine *event_to_hwe(struct perf_event *event) +{ + struct xe_device *xe = container_of(event->pmu, typeof(*xe), pmu.base); + struct drm_xe_engine_class_instance eci; + u64 config = event->attr.config; + struct xe_hw_engine *hwe; + + eci.engine_class = config_to_engine_class(config); + eci.engine_instance = config_to_engine_instance(config); + eci.gt_id = config_to_gt_id(config); + + hwe = xe_hw_engine_lookup(xe, eci); + if (!hwe || xe_hw_engine_is_reserved(hwe)) + return NULL; + + return hwe; +} + +static bool is_engine_event(u64 config) +{ + unsigned int event_id = config_to_event_id(config); + + return (event_id == XE_PMU_EVENT_ENGINE_TOTAL_TICKS || + event_id == XE_PMU_EVENT_ENGINE_ACTIVE_TICKS); +} + +static bool event_gt_forcewake(struct perf_event *event) +{ + struct xe_device *xe = container_of(event->pmu, typeof(*xe), pmu.base); + u64 config = event->attr.config; + struct xe_gt *gt; + unsigned int *fw_ref; + + if (!is_engine_event(config)) + return true; + + gt = xe_device_get_gt(xe, config_to_gt_id(config)); + + fw_ref = kzalloc(sizeof(*fw_ref), GFP_KERNEL); + if (!fw_ref) + return false; + + *fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); + if (!*fw_ref) { + kfree(fw_ref); + return false; + } + + event->pmu_private = fw_ref; + + return true; +} + static bool event_supported(struct xe_pmu *pmu, unsigned int gt, unsigned int id) { @@ -68,9 +148,47 @@ static bool event_supported(struct xe_pmu *pmu, unsigned int gt, pmu->supported_events & BIT_ULL(id); } +static bool event_param_valid(struct perf_event *event) +{ + struct xe_device *xe = container_of(event->pmu, typeof(*xe), pmu.base); + unsigned int engine_class, engine_instance; + u64 config = event->attr.config; + struct xe_gt *gt; + + gt = xe_device_get_gt(xe, config_to_gt_id(config)); + if (!gt) + return false; + + engine_class = config_to_engine_class(config); + engine_instance = config_to_engine_instance(config); + + switch (config_to_event_id(config)) { + case XE_PMU_EVENT_GT_C6_RESIDENCY: + if (engine_class || engine_instance) + return false; + break; + case XE_PMU_EVENT_ENGINE_ACTIVE_TICKS: + case XE_PMU_EVENT_ENGINE_TOTAL_TICKS: + if (!event_to_hwe(event)) + return false; + break; + } + + return true; +} + static void xe_pmu_event_destroy(struct perf_event *event) { struct xe_device *xe = container_of(event->pmu, typeof(*xe), pmu.base); + struct xe_gt *gt; + unsigned int *fw_ref = event->pmu_private; + + if (fw_ref) { + gt = xe_device_get_gt(xe, config_to_gt_id(event->attr.config)); + xe_force_wake_put(gt_to_fw(gt), *fw_ref); + kfree(fw_ref); + event->pmu_private = NULL; + } drm_WARN_ON(&xe->drm, event->parent); xe_pm_runtime_put(xe); @@ -104,15 +222,37 @@ static int xe_pmu_event_init(struct perf_event *event) if (has_branch_stack(event)) return -EOPNOTSUPP; + if (!event_param_valid(event)) + return -ENOENT; + if (!event->parent) { drm_dev_get(&xe->drm); xe_pm_runtime_get(xe); + if (!event_gt_forcewake(event)) { + xe_pm_runtime_put(xe); + drm_dev_put(&xe->drm); + return -EINVAL; + } event->destroy = xe_pmu_event_destroy; } return 0; } +static u64 read_engine_events(struct xe_gt *gt, struct perf_event *event) +{ + struct xe_hw_engine *hwe; + u64 val = 0; + + hwe = event_to_hwe(event); + if (config_to_event_id(event->attr.config) == XE_PMU_EVENT_ENGINE_ACTIVE_TICKS) + val = xe_guc_engine_activity_active_ticks(>->uc.guc, hwe); + else + val = xe_guc_engine_activity_total_ticks(>->uc.guc, hwe); + + return val; +} + static u64 __xe_pmu_event_read(struct perf_event *event) { struct xe_gt *gt = event_to_gt(event); @@ -123,6 +263,9 @@ static u64 __xe_pmu_event_read(struct perf_event *event) switch (config_to_event_id(event->attr.config)) { case XE_PMU_EVENT_GT_C6_RESIDENCY: return xe_gt_idle_residency_msec(>->gtidle); + case XE_PMU_EVENT_ENGINE_ACTIVE_TICKS: + case XE_PMU_EVENT_ENGINE_TOTAL_TICKS: + return read_engine_events(gt, event); } return 0; @@ -207,11 +350,15 @@ static void xe_pmu_event_del(struct perf_event *event, int flags) xe_pmu_event_stop(event, PERF_EF_UPDATE); } -PMU_FORMAT_ATTR(gt, "config:60-63"); -PMU_FORMAT_ATTR(event, "config:0-11"); +PMU_FORMAT_ATTR(gt, "config:60-63"); +PMU_FORMAT_ATTR(engine_class, "config:20-27"); +PMU_FORMAT_ATTR(engine_instance, "config:12-19"); +PMU_FORMAT_ATTR(event, "config:0-11"); static struct attribute *pmu_format_attrs[] = { &format_attr_event.attr, + &format_attr_engine_class.attr, + &format_attr_engine_instance.attr, &format_attr_gt.attr, NULL, }; @@ -270,6 +417,8 @@ static ssize_t event_attr_show(struct device *dev, XE_EVENT_ATTR_GROUP(v_, id_, &pmu_event_ ##v_.attr.attr) XE_EVENT_ATTR_SIMPLE(gt-c6-residency, gt_c6_residency, XE_PMU_EVENT_GT_C6_RESIDENCY, "ms"); +XE_EVENT_ATTR_NOUNIT(engine-active-ticks, engine_active_ticks, XE_PMU_EVENT_ENGINE_ACTIVE_TICKS); +XE_EVENT_ATTR_NOUNIT(engine-total-ticks, engine_total_ticks, XE_PMU_EVENT_ENGINE_TOTAL_TICKS); static struct attribute *pmu_empty_event_attrs[] = { /* Empty - all events are added as groups with .attr_update() */ @@ -283,15 +432,23 @@ static const struct attribute_group pmu_events_attr_group = { static const struct attribute_group *pmu_events_attr_update[] = { &pmu_group_gt_c6_residency, + &pmu_group_engine_active_ticks, + &pmu_group_engine_total_ticks, NULL, }; static void set_supported_events(struct xe_pmu *pmu) { struct xe_device *xe = container_of(pmu, typeof(*xe), pmu); + struct xe_gt *gt = xe_device_get_gt(xe, 0); if (!xe->info.skip_guc_pc) pmu->supported_events |= BIT_ULL(XE_PMU_EVENT_GT_C6_RESIDENCY); + + if (xe_guc_engine_activity_supported(>->uc.guc)) { + pmu->supported_events |= BIT_ULL(XE_PMU_EVENT_ENGINE_ACTIVE_TICKS); + pmu->supported_events |= BIT_ULL(XE_PMU_EVENT_ENGINE_TOTAL_TICKS); + } } /** diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index 1ddcc7e79a93..ffaf0d02dc7d 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -20,6 +20,7 @@ #include "xe_res_cursor.h" #include "xe_sched_job.h" #include "xe_sync.h" +#include "xe_svm.h" #include "xe_trace.h" #include "xe_ttm_stolen_mgr.h" #include "xe_vm.h" @@ -28,6 +29,8 @@ struct xe_pt_dir { struct xe_pt pt; /** @children: Array of page-table child nodes */ struct xe_ptw *children[XE_PDES]; + /** @staging: Array of page-table staging nodes */ + struct xe_ptw *staging[XE_PDES]; }; #if IS_ENABLED(CONFIG_DRM_XE_DEBUG_VM) @@ -48,9 +51,10 @@ static struct xe_pt_dir *as_xe_pt_dir(struct xe_pt *pt) return container_of(pt, struct xe_pt_dir, pt); } -static struct xe_pt *xe_pt_entry(struct xe_pt_dir *pt_dir, unsigned int index) +static struct xe_pt * +xe_pt_entry_staging(struct xe_pt_dir *pt_dir, unsigned int index) { - return container_of(pt_dir->children[index], struct xe_pt, base); + return container_of(pt_dir->staging[index], struct xe_pt, base); } static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm, @@ -125,6 +129,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile, } pt->bo = bo; pt->base.children = level ? as_xe_pt_dir(pt)->children : NULL; + pt->base.staging = level ? as_xe_pt_dir(pt)->staging : NULL; if (vm->xef) xe_drm_client_add_bo(vm->xef->client, pt->bo); @@ -206,8 +211,8 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred) struct xe_pt_dir *pt_dir = as_xe_pt_dir(pt); for (i = 0; i < XE_PDES; i++) { - if (xe_pt_entry(pt_dir, i)) - xe_pt_destroy(xe_pt_entry(pt_dir, i), flags, + if (xe_pt_entry_staging(pt_dir, i)) + xe_pt_destroy(xe_pt_entry_staging(pt_dir, i), flags, deferred); } } @@ -215,6 +220,20 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred) } /** + * xe_pt_clear() - Clear a page-table. + * @xe: xe device. + * @pt: The page-table. + * + * Clears page-table by setting to zero. + */ +void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt) +{ + struct iosys_map *map = &pt->bo->vmap; + + xe_map_memset(xe, map, 0, 0, SZ_4K); +} + +/** * DOC: Pagetable building * * Below we use the term "page-table" for both page-directories, containing @@ -376,8 +395,10 @@ xe_pt_insert_entry(struct xe_pt_stage_bind_walk *xe_walk, struct xe_pt *parent, /* Continue building a non-connected subtree. */ struct iosys_map *map = &parent->bo->vmap; - if (unlikely(xe_child)) + if (unlikely(xe_child)) { parent->base.children[offset] = &xe_child->base; + parent->base.staging[offset] = &xe_child->base; + } xe_pt_write(xe_walk->vm->xe, map, offset, pte); parent->num_live++; @@ -587,6 +608,7 @@ static const struct xe_pt_walk_ops xe_pt_stage_bind_ops = { * range. * @tile: The tile we're building for. * @vma: The vma indicating the address range. + * @range: The range indicating the address range. * @entries: Storage for the update entries used for connecting the tree to * the main tree at commit time. * @num_entries: On output contains the number of @entries used. @@ -602,6 +624,7 @@ static const struct xe_pt_walk_ops xe_pt_stage_bind_ops = { */ static int xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, + struct xe_svm_range *range, struct xe_vm_pgtable_update *entries, u32 *num_entries) { struct xe_device *xe = tile_to_xe(tile); @@ -614,18 +637,48 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, .ops = &xe_pt_stage_bind_ops, .shifts = xe_normal_pt_shifts, .max_level = XE_PT_HIGHEST_LEVEL, + .staging = true, }, .vm = xe_vma_vm(vma), .tile = tile, .curs = &curs, - .va_curs_start = xe_vma_start(vma), + .va_curs_start = range ? range->base.itree.start : + xe_vma_start(vma), .vma = vma, .wupd.entries = entries, - .needs_64K = (xe_vma_vm(vma)->flags & XE_VM_FLAG_64K) && is_devmem, }; struct xe_pt *pt = xe_vma_vm(vma)->pt_root[tile->id]; int ret; + if (range) { + /* Move this entire thing to xe_svm.c? */ + xe_svm_notifier_lock(xe_vma_vm(vma)); + if (!xe_svm_range_pages_valid(range)) { + xe_svm_range_debug(range, "BIND PREPARE - RETRY"); + xe_svm_notifier_unlock(xe_vma_vm(vma)); + return -EAGAIN; + } + if (xe_svm_range_has_dma_mapping(range)) { + xe_res_first_dma(range->base.dma_addr, 0, + range->base.itree.last + 1 - range->base.itree.start, + &curs); + is_devmem = xe_res_is_vram(&curs); + if (is_devmem) + xe_svm_range_debug(range, "BIND PREPARE - DMA VRAM"); + else + xe_svm_range_debug(range, "BIND PREPARE - DMA"); + } else { + xe_assert(xe, false); + } + /* + * Note, when unlocking the resource cursor dma addresses may become + * stale, but the bind will be aborted anyway at commit time. + */ + xe_svm_notifier_unlock(xe_vma_vm(vma)); + } + + xe_walk.needs_64K = (xe_vma_vm(vma)->flags & XE_VM_FLAG_64K) && is_devmem; + /** * Default atomic expectations for different allocation scenarios are as follows: * @@ -647,7 +700,7 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, * gets migrated to LMEM, bind such allocations with * device atomics enabled. */ - else if (is_devmem && !xe_bo_has_single_placement(bo)) + else if (is_devmem) xe_walk.default_pte |= XE_USM_PPGTT_PTE_AE; } else { xe_walk.default_pte |= XE_USM_PPGTT_PTE_AE; @@ -663,15 +716,16 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, if (is_devmem) { xe_walk.default_pte |= XE_PPGTT_PTE_DM; - xe_walk.dma_offset = vram_region_gpu_offset(bo->ttm.resource); + xe_walk.dma_offset = bo ? vram_region_gpu_offset(bo->ttm.resource) : 0; } if (!xe_vma_has_no_bo(vma) && xe_bo_is_stolen(bo)) xe_walk.dma_offset = xe_ttm_stolen_gpu_offset(xe_bo_device(bo)); - xe_bo_assert_held(bo); + if (!range) + xe_bo_assert_held(bo); - if (!xe_vma_is_null(vma)) { + if (!xe_vma_is_null(vma) && !range) { if (xe_vma_is_userptr(vma)) xe_res_first_sg(to_userptr_vma(vma)->userptr.sg, 0, xe_vma_size(vma), &curs); @@ -681,12 +735,14 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, else xe_res_first_sg(xe_bo_sg(bo), xe_vma_bo_offset(vma), xe_vma_size(vma), &curs); - } else { + } else if (!range) { curs.size = xe_vma_size(vma); } - ret = xe_pt_walk_range(&pt->base, pt->level, xe_vma_start(vma), - xe_vma_end(vma), &xe_walk.base); + ret = xe_pt_walk_range(&pt->base, pt->level, + range ? range->base.itree.start : xe_vma_start(vma), + range ? range->base.itree.last + 1 : xe_vma_end(vma), + &xe_walk.base); *num_entries = xe_walk.wupd.num_used_entries; return ret; @@ -830,6 +886,46 @@ bool xe_pt_zap_ptes(struct xe_tile *tile, struct xe_vma *vma) return xe_walk.needs_invalidate; } +/** + * xe_pt_zap_ptes_range() - Zap (zero) gpu ptes of a SVM range + * @tile: The tile we're zapping for. + * @vm: The VM we're zapping for. + * @range: The SVM range we're zapping for. + * + * SVM invalidation needs to be able to zap the gpu ptes of a given address + * range. In order to be able to do that, that function needs access to the + * shared page-table entries so it can either clear the leaf PTEs or + * clear the pointers to lower-level page-tables. The caller is required + * to hold the SVM notifier lock. + * + * Return: Whether ptes were actually updated and a TLB invalidation is + * required. + */ +bool xe_pt_zap_ptes_range(struct xe_tile *tile, struct xe_vm *vm, + struct xe_svm_range *range) +{ + struct xe_pt_zap_ptes_walk xe_walk = { + .base = { + .ops = &xe_pt_zap_ptes_ops, + .shifts = xe_normal_pt_shifts, + .max_level = XE_PT_HIGHEST_LEVEL, + }, + .tile = tile, + }; + struct xe_pt *pt = vm->pt_root[tile->id]; + u8 pt_mask = (range->tile_present & ~range->tile_invalidated); + + xe_svm_assert_in_notifier(vm); + + if (!(pt_mask & BIT(tile->id))) + return false; + + (void)xe_pt_walk_shared(&pt->base, pt->level, range->base.itree.start, + range->base.itree.last + 1, &xe_walk.base); + + return xe_walk.needs_invalidate; +} + static void xe_vm_populate_pgtable(struct xe_migrate_pt_update *pt_update, struct xe_tile *tile, struct iosys_map *map, void *data, @@ -873,18 +969,38 @@ static void xe_pt_cancel_bind(struct xe_vma *vma, } } -static void xe_pt_commit_locks_assert(struct xe_vma *vma) +#define XE_INVALID_VMA ((struct xe_vma *)(0xdeaddeadull)) + +static void xe_pt_commit_prepare_locks_assert(struct xe_vma *vma) { - struct xe_vm *vm = xe_vma_vm(vma); + struct xe_vm *vm; + if (vma == XE_INVALID_VMA) + return; + + vm = xe_vma_vm(vma); lockdep_assert_held(&vm->lock); - if (!xe_vma_is_userptr(vma) && !xe_vma_is_null(vma)) + if (!xe_vma_has_no_bo(vma)) dma_resv_assert_held(xe_vma_bo(vma)->ttm.base.resv); xe_vm_assert_held(vm); } +static void xe_pt_commit_locks_assert(struct xe_vma *vma) +{ + struct xe_vm *vm; + + if (vma == XE_INVALID_VMA) + return; + + vm = xe_vma_vm(vma); + xe_pt_commit_prepare_locks_assert(vma); + + if (xe_vma_is_userptr(vma)) + lockdep_assert_held_read(&vm->userptr.notifier_lock); +} + static void xe_pt_commit(struct xe_vma *vma, struct xe_vm_pgtable_update *entries, u32 num_entries, struct llist_head *deferred) @@ -895,14 +1011,19 @@ static void xe_pt_commit(struct xe_vma *vma, for (i = 0; i < num_entries; i++) { struct xe_pt *pt = entries[i].pt; + struct xe_pt_dir *pt_dir; if (!pt->level) continue; + pt_dir = as_xe_pt_dir(pt); for (j = 0; j < entries[i].qwords; j++) { struct xe_pt *oldpte = entries[i].pt_entries[j].pt; + int j_ = j + entries[i].ofs; - xe_pt_destroy(oldpte, xe_vma_vm(vma)->flags, deferred); + pt_dir->children[j_] = pt_dir->staging[j_]; + xe_pt_destroy(oldpte, (vma == XE_INVALID_VMA) ? 0 : + xe_vma_vm(vma)->flags, deferred); } } } @@ -913,7 +1034,7 @@ static void xe_pt_abort_bind(struct xe_vma *vma, { int i, j; - xe_pt_commit_locks_assert(vma); + xe_pt_commit_prepare_locks_assert(vma); for (i = num_entries - 1; i >= 0; --i) { struct xe_pt *pt = entries[i].pt; @@ -928,10 +1049,10 @@ static void xe_pt_abort_bind(struct xe_vma *vma, pt_dir = as_xe_pt_dir(pt); for (j = 0; j < entries[i].qwords; j++) { u32 j_ = j + entries[i].ofs; - struct xe_pt *newpte = xe_pt_entry(pt_dir, j_); + struct xe_pt *newpte = xe_pt_entry_staging(pt_dir, j_); struct xe_pt *oldpte = entries[i].pt_entries[j].pt; - pt_dir->children[j_] = oldpte ? &oldpte->base : 0; + pt_dir->staging[j_] = oldpte ? &oldpte->base : 0; xe_pt_destroy(newpte, xe_vma_vm(vma)->flags, NULL); } } @@ -943,7 +1064,7 @@ static void xe_pt_commit_prepare_bind(struct xe_vma *vma, { u32 i, j; - xe_pt_commit_locks_assert(vma); + xe_pt_commit_prepare_locks_assert(vma); for (i = 0; i < num_entries; i++) { struct xe_pt *pt = entries[i].pt; @@ -961,10 +1082,10 @@ static void xe_pt_commit_prepare_bind(struct xe_vma *vma, struct xe_pt *newpte = entries[i].pt_entries[j].pt; struct xe_pt *oldpte = NULL; - if (xe_pt_entry(pt_dir, j_)) - oldpte = xe_pt_entry(pt_dir, j_); + if (xe_pt_entry_staging(pt_dir, j_)) + oldpte = xe_pt_entry_staging(pt_dir, j_); - pt_dir->children[j_] = &newpte->base; + pt_dir->staging[j_] = &newpte->base; entries[i].pt_entries[j].pt = oldpte; } } @@ -981,12 +1102,13 @@ static void xe_pt_free_bind(struct xe_vm_pgtable_update *entries, static int xe_pt_prepare_bind(struct xe_tile *tile, struct xe_vma *vma, + struct xe_svm_range *range, struct xe_vm_pgtable_update *entries, u32 *num_entries) { int err; *num_entries = 0; - err = xe_pt_stage_bind(tile, vma, entries, num_entries); + err = xe_pt_stage_bind(tile, vma, range, entries, num_entries); if (!err) xe_tile_assert(tile, *num_entries); @@ -1069,6 +1191,11 @@ static int op_add_deps(struct xe_vm *vm, struct xe_vma_op *op, { int err = 0; + /* + * No need to check for is_cpu_addr_mirror here as vma_add_deps is a + * NOP if VMA is_cpu_addr_mirror + */ + switch (op->base.op) { case DRM_GPUVA_OP_MAP: if (!op->map.immediate && xe_vm_in_fault_mode(vm)) @@ -1087,6 +1214,8 @@ static int op_add_deps(struct xe_vm *vm, struct xe_vma_op *op, case DRM_GPUVA_OP_PREFETCH: err = vma_add_deps(gpuva_to_vma(op->base.prefetch.va), job); break; + case DRM_GPUVA_OP_DRIVER: + break; default: drm_warn(&vm->xe->drm, "NOT POSSIBLE"); } @@ -1213,42 +1342,22 @@ static int vma_check_userptr(struct xe_vm *vm, struct xe_vma *vma, return 0; uvma = to_userptr_vma(vma); - notifier_seq = uvma->userptr.notifier_seq; + if (xe_pt_userptr_inject_eagain(uvma)) + xe_vma_userptr_force_invalidate(uvma); - if (uvma->userptr.initial_bind && !xe_vm_in_fault_mode(vm)) - return 0; + notifier_seq = uvma->userptr.notifier_seq; if (!mmu_interval_read_retry(&uvma->userptr.notifier, - notifier_seq) && - !xe_pt_userptr_inject_eagain(uvma)) + notifier_seq)) return 0; - if (xe_vm_in_fault_mode(vm)) { + if (xe_vm_in_fault_mode(vm)) return -EAGAIN; - } else { - spin_lock(&vm->userptr.invalidated_lock); - list_move_tail(&uvma->userptr.invalidate_link, - &vm->userptr.invalidated); - spin_unlock(&vm->userptr.invalidated_lock); - - if (xe_vm_in_preempt_fence_mode(vm)) { - struct dma_resv_iter cursor; - struct dma_fence *fence; - long err; - - dma_resv_iter_begin(&cursor, xe_vm_resv(vm), - DMA_RESV_USAGE_BOOKKEEP); - dma_resv_for_each_fence_unlocked(&cursor, fence) - dma_fence_enable_sw_signaling(fence); - dma_resv_iter_end(&cursor); - - err = dma_resv_wait_timeout(xe_vm_resv(vm), - DMA_RESV_USAGE_BOOKKEEP, - false, MAX_SCHEDULE_TIMEOUT); - XE_WARN_ON(err <= 0); - } - } + /* + * Just continue the operation since exec or rebind worker + * will take care of rebinding. + */ return 0; } @@ -1311,6 +1420,40 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update) return err; } +static int xe_pt_svm_pre_commit(struct xe_migrate_pt_update *pt_update) +{ + struct xe_vm *vm = pt_update->vops->vm; + struct xe_vma_ops *vops = pt_update->vops; + struct xe_vma_op *op; + int err; + + err = xe_pt_pre_commit(pt_update); + if (err) + return err; + + xe_svm_notifier_lock(vm); + + list_for_each_entry(op, &vops->list, link) { + struct xe_svm_range *range = op->map_range.range; + + if (op->subop == XE_VMA_SUBOP_UNMAP_RANGE) + continue; + + xe_svm_range_debug(range, "PRE-COMMIT"); + + xe_assert(vm->xe, xe_vma_is_cpu_addr_mirror(op->map_range.vma)); + xe_assert(vm->xe, op->subop == XE_VMA_SUBOP_MAP_RANGE); + + if (!xe_svm_range_pages_valid(range)) { + xe_svm_range_debug(range, "PRE-COMMIT - RETRY"); + xe_svm_notifier_unlock(vm); + return -EAGAIN; + } + } + + return 0; +} + struct invalidation_fence { struct xe_gt_tlb_invalidation_fence base; struct xe_gt *gt; @@ -1496,7 +1639,9 @@ static const struct xe_pt_walk_ops xe_pt_stage_unbind_ops = { * xe_pt_stage_unbind() - Build page-table update structures for an unbind * operation * @tile: The tile we're unbinding for. + * @vm: The vm * @vma: The vma we're unbinding. + * @range: The range we're unbinding. * @entries: Caller-provided storage for the update structures. * * Builds page-table update structures for an unbind operation. The function @@ -1506,24 +1651,30 @@ static const struct xe_pt_walk_ops xe_pt_stage_unbind_ops = { * * Return: The number of entries used. */ -static unsigned int xe_pt_stage_unbind(struct xe_tile *tile, struct xe_vma *vma, +static unsigned int xe_pt_stage_unbind(struct xe_tile *tile, + struct xe_vm *vm, + struct xe_vma *vma, + struct xe_svm_range *range, struct xe_vm_pgtable_update *entries) { + u64 start = range ? range->base.itree.start : xe_vma_start(vma); + u64 end = range ? range->base.itree.last + 1 : xe_vma_end(vma); struct xe_pt_stage_unbind_walk xe_walk = { .base = { .ops = &xe_pt_stage_unbind_ops, .shifts = xe_normal_pt_shifts, .max_level = XE_PT_HIGHEST_LEVEL, + .staging = true, }, .tile = tile, - .modified_start = xe_vma_start(vma), - .modified_end = xe_vma_end(vma), + .modified_start = start, + .modified_end = end, .wupd.entries = entries, }; - struct xe_pt *pt = xe_vma_vm(vma)->pt_root[tile->id]; + struct xe_pt *pt = vm->pt_root[tile->id]; - (void)xe_pt_walk_shared(&pt->base, pt->level, xe_vma_start(vma), - xe_vma_end(vma), &xe_walk.base); + (void)xe_pt_walk_shared(&pt->base, pt->level, start, end, + &xe_walk.base); return xe_walk.wupd.num_used_entries; } @@ -1555,7 +1706,7 @@ static void xe_pt_abort_unbind(struct xe_vma *vma, { int i, j; - xe_pt_commit_locks_assert(vma); + xe_pt_commit_prepare_locks_assert(vma); for (i = num_entries - 1; i >= 0; --i) { struct xe_vm_pgtable_update *entry = &entries[i]; @@ -1568,7 +1719,7 @@ static void xe_pt_abort_unbind(struct xe_vma *vma, continue; for (j = entry->ofs; j < entry->ofs + entry->qwords; j++) - pt_dir->children[j] = + pt_dir->staging[j] = entries[i].pt_entries[j - entry->ofs].pt ? &entries[i].pt_entries[j - entry->ofs].pt->base : NULL; } @@ -1581,7 +1732,7 @@ xe_pt_commit_prepare_unbind(struct xe_vma *vma, { int i, j; - xe_pt_commit_locks_assert(vma); + xe_pt_commit_prepare_locks_assert(vma); for (i = 0; i < num_entries; ++i) { struct xe_vm_pgtable_update *entry = &entries[i]; @@ -1595,20 +1746,20 @@ xe_pt_commit_prepare_unbind(struct xe_vma *vma, pt_dir = as_xe_pt_dir(pt); for (j = entry->ofs; j < entry->ofs + entry->qwords; j++) { entry->pt_entries[j - entry->ofs].pt = - xe_pt_entry(pt_dir, j); - pt_dir->children[j] = NULL; + xe_pt_entry_staging(pt_dir, j); + pt_dir->staging[j] = NULL; } } } static void xe_pt_update_ops_rfence_interval(struct xe_vm_pgtable_update_ops *pt_update_ops, - struct xe_vma *vma) + u64 start, u64 end) { + u64 last; u32 current_op = pt_update_ops->current_op; struct xe_vm_pgtable_update_op *pt_op = &pt_update_ops->ops[current_op]; int i, level = 0; - u64 start, last; for (i = 0; i < pt_op->num_entries; i++) { const struct xe_vm_pgtable_update *entry = &pt_op->entries[i]; @@ -1618,8 +1769,8 @@ xe_pt_update_ops_rfence_interval(struct xe_vm_pgtable_update_ops *pt_update_ops, } /* Greedy (non-optimal) calculation but simple */ - start = ALIGN_DOWN(xe_vma_start(vma), 0x1ull << xe_pt_shift(level)); - last = ALIGN(xe_vma_end(vma), 0x1ull << xe_pt_shift(level)) - 1; + start = ALIGN_DOWN(start, 0x1ull << xe_pt_shift(level)); + last = ALIGN(end, 0x1ull << xe_pt_shift(level)) - 1; if (start < pt_update_ops->start) pt_update_ops->start = start; @@ -1646,6 +1797,7 @@ static int bind_op_prepare(struct xe_vm *vm, struct xe_tile *tile, struct xe_vm_pgtable_update_op *pt_op = &pt_update_ops->ops[current_op]; int err; + xe_tile_assert(tile, !xe_vma_is_cpu_addr_mirror(vma)); xe_bo_assert_held(xe_vma_bo(vma)); vm_dbg(&xe_vma_vm(vma)->xe->drm, @@ -1660,7 +1812,7 @@ static int bind_op_prepare(struct xe_vm *vm, struct xe_tile *tile, if (err) return err; - err = xe_pt_prepare_bind(tile, vma, pt_op->entries, + err = xe_pt_prepare_bind(tile, vma, NULL, pt_op->entries, &pt_op->num_entries); if (!err) { xe_tile_assert(tile, pt_op->num_entries <= @@ -1668,7 +1820,9 @@ static int bind_op_prepare(struct xe_vm *vm, struct xe_tile *tile, xe_vm_dbg_print_entries(tile_to_xe(tile), pt_op->entries, pt_op->num_entries, true); - xe_pt_update_ops_rfence_interval(pt_update_ops, vma); + xe_pt_update_ops_rfence_interval(pt_update_ops, + xe_vma_start(vma), + xe_vma_end(vma)); ++pt_update_ops->current_op; pt_update_ops->needs_userptr_lock |= xe_vma_is_userptr(vma); @@ -1702,6 +1856,48 @@ static int bind_op_prepare(struct xe_vm *vm, struct xe_tile *tile, return err; } +static int bind_range_prepare(struct xe_vm *vm, struct xe_tile *tile, + struct xe_vm_pgtable_update_ops *pt_update_ops, + struct xe_vma *vma, struct xe_svm_range *range) +{ + u32 current_op = pt_update_ops->current_op; + struct xe_vm_pgtable_update_op *pt_op = &pt_update_ops->ops[current_op]; + int err; + + xe_tile_assert(tile, xe_vma_is_cpu_addr_mirror(vma)); + + vm_dbg(&xe_vma_vm(vma)->xe->drm, + "Preparing bind, with range [%lx...%lx)\n", + range->base.itree.start, range->base.itree.last); + + pt_op->vma = NULL; + pt_op->bind = true; + pt_op->rebind = BIT(tile->id) & range->tile_present; + + err = xe_pt_prepare_bind(tile, vma, range, pt_op->entries, + &pt_op->num_entries); + if (!err) { + xe_tile_assert(tile, pt_op->num_entries <= + ARRAY_SIZE(pt_op->entries)); + xe_vm_dbg_print_entries(tile_to_xe(tile), pt_op->entries, + pt_op->num_entries, true); + + xe_pt_update_ops_rfence_interval(pt_update_ops, + range->base.itree.start, + range->base.itree.last + 1); + ++pt_update_ops->current_op; + pt_update_ops->needs_svm_lock = true; + + pt_op->vma = vma; + xe_pt_commit_prepare_bind(vma, pt_op->entries, + pt_op->num_entries, pt_op->rebind); + } else { + xe_pt_cancel_bind(vma, pt_op->entries, pt_op->num_entries); + } + + return err; +} + static int unbind_op_prepare(struct xe_tile *tile, struct xe_vm_pgtable_update_ops *pt_update_ops, struct xe_vma *vma) @@ -1713,19 +1909,13 @@ static int unbind_op_prepare(struct xe_tile *tile, if (!((vma->tile_present | vma->tile_staged) & BIT(tile->id))) return 0; + xe_tile_assert(tile, !xe_vma_is_cpu_addr_mirror(vma)); xe_bo_assert_held(xe_vma_bo(vma)); vm_dbg(&xe_vma_vm(vma)->xe->drm, "Preparing unbind, with range [%llx...%llx)\n", xe_vma_start(vma), xe_vma_end(vma) - 1); - /* - * Wait for invalidation to complete. Can corrupt internal page table - * state if an invalidation is running while preparing an unbind. - */ - if (xe_vma_is_userptr(vma) && xe_vm_in_fault_mode(xe_vma_vm(vma))) - mmu_interval_read_begin(&to_userptr_vma(vma)->userptr.notifier); - pt_op->vma = vma; pt_op->bind = false; pt_op->rebind = false; @@ -1734,11 +1924,13 @@ static int unbind_op_prepare(struct xe_tile *tile, if (err) return err; - pt_op->num_entries = xe_pt_stage_unbind(tile, vma, pt_op->entries); + pt_op->num_entries = xe_pt_stage_unbind(tile, xe_vma_vm(vma), + vma, NULL, pt_op->entries); xe_vm_dbg_print_entries(tile_to_xe(tile), pt_op->entries, pt_op->num_entries, false); - xe_pt_update_ops_rfence_interval(pt_update_ops, vma); + xe_pt_update_ops_rfence_interval(pt_update_ops, xe_vma_start(vma), + xe_vma_end(vma)); ++pt_update_ops->current_op; pt_update_ops->needs_userptr_lock |= xe_vma_is_userptr(vma); pt_update_ops->needs_invalidation = true; @@ -1748,6 +1940,42 @@ static int unbind_op_prepare(struct xe_tile *tile, return 0; } +static int unbind_range_prepare(struct xe_vm *vm, + struct xe_tile *tile, + struct xe_vm_pgtable_update_ops *pt_update_ops, + struct xe_svm_range *range) +{ + u32 current_op = pt_update_ops->current_op; + struct xe_vm_pgtable_update_op *pt_op = &pt_update_ops->ops[current_op]; + + if (!(range->tile_present & BIT(tile->id))) + return 0; + + vm_dbg(&vm->xe->drm, + "Preparing unbind, with range [%lx...%lx)\n", + range->base.itree.start, range->base.itree.last); + + pt_op->vma = XE_INVALID_VMA; + pt_op->bind = false; + pt_op->rebind = false; + + pt_op->num_entries = xe_pt_stage_unbind(tile, vm, NULL, range, + pt_op->entries); + + xe_vm_dbg_print_entries(tile_to_xe(tile), pt_op->entries, + pt_op->num_entries, false); + xe_pt_update_ops_rfence_interval(pt_update_ops, range->base.itree.start, + range->base.itree.last + 1); + ++pt_update_ops->current_op; + pt_update_ops->needs_svm_lock = true; + pt_update_ops->needs_invalidation = true; + + xe_pt_commit_prepare_unbind(XE_INVALID_VMA, pt_op->entries, + pt_op->num_entries); + + return 0; +} + static int op_prepare(struct xe_vm *vm, struct xe_tile *tile, struct xe_vm_pgtable_update_ops *pt_update_ops, @@ -1759,15 +1987,21 @@ static int op_prepare(struct xe_vm *vm, switch (op->base.op) { case DRM_GPUVA_OP_MAP: - if (!op->map.immediate && xe_vm_in_fault_mode(vm)) + if ((!op->map.immediate && xe_vm_in_fault_mode(vm)) || + op->map.is_cpu_addr_mirror) break; err = bind_op_prepare(vm, tile, pt_update_ops, op->map.vma); pt_update_ops->wait_vm_kernel = true; break; case DRM_GPUVA_OP_REMAP: - err = unbind_op_prepare(tile, pt_update_ops, - gpuva_to_vma(op->base.remap.unmap->va)); + { + struct xe_vma *old = gpuva_to_vma(op->base.remap.unmap->va); + + if (xe_vma_is_cpu_addr_mirror(old)) + break; + + err = unbind_op_prepare(tile, pt_update_ops, old); if (!err && op->remap.prev) { err = bind_op_prepare(vm, tile, pt_update_ops, @@ -1780,15 +2014,40 @@ static int op_prepare(struct xe_vm *vm, pt_update_ops->wait_vm_bookkeep = true; } break; + } case DRM_GPUVA_OP_UNMAP: - err = unbind_op_prepare(tile, pt_update_ops, - gpuva_to_vma(op->base.unmap.va)); + { + struct xe_vma *vma = gpuva_to_vma(op->base.unmap.va); + + if (xe_vma_is_cpu_addr_mirror(vma)) + break; + + err = unbind_op_prepare(tile, pt_update_ops, vma); break; + } case DRM_GPUVA_OP_PREFETCH: - err = bind_op_prepare(vm, tile, pt_update_ops, - gpuva_to_vma(op->base.prefetch.va)); + { + struct xe_vma *vma = gpuva_to_vma(op->base.prefetch.va); + + if (xe_vma_is_cpu_addr_mirror(vma)) + break; + + err = bind_op_prepare(vm, tile, pt_update_ops, vma); pt_update_ops->wait_vm_kernel = true; break; + } + case DRM_GPUVA_OP_DRIVER: + if (op->subop == XE_VMA_SUBOP_MAP_RANGE) { + xe_assert(vm->xe, xe_vma_is_cpu_addr_mirror(op->map_range.vma)); + + err = bind_range_prepare(vm, tile, pt_update_ops, + op->map_range.vma, + op->map_range.range); + } else if (op->subop == XE_VMA_SUBOP_UNMAP_RANGE) { + err = unbind_range_prepare(vm, tile, pt_update_ops, + op->unmap_range.range); + } + break; default: drm_warn(&vm->xe->drm, "NOT POSSIBLE"); } @@ -1858,6 +2117,8 @@ static void bind_op_commit(struct xe_vm *vm, struct xe_tile *tile, struct xe_vma *vma, struct dma_fence *fence, struct dma_fence *fence2) { + xe_tile_assert(tile, !xe_vma_is_cpu_addr_mirror(vma)); + if (!xe_vma_has_no_bo(vma) && !xe_vma_bo(vma)->vm) { dma_resv_add_fence(xe_vma_bo(vma)->ttm.base.resv, fence, pt_update_ops->wait_vm_bookkeep ? @@ -1891,6 +2152,8 @@ static void unbind_op_commit(struct xe_vm *vm, struct xe_tile *tile, struct xe_vma *vma, struct dma_fence *fence, struct dma_fence *fence2) { + xe_tile_assert(tile, !xe_vma_is_cpu_addr_mirror(vma)); + if (!xe_vma_has_no_bo(vma) && !xe_vma_bo(vma)->vm) { dma_resv_add_fence(xe_vma_bo(vma)->ttm.base.resv, fence, pt_update_ops->wait_vm_bookkeep ? @@ -1925,16 +2188,21 @@ static void op_commit(struct xe_vm *vm, switch (op->base.op) { case DRM_GPUVA_OP_MAP: - if (!op->map.immediate && xe_vm_in_fault_mode(vm)) + if ((!op->map.immediate && xe_vm_in_fault_mode(vm)) || + op->map.is_cpu_addr_mirror) break; bind_op_commit(vm, tile, pt_update_ops, op->map.vma, fence, fence2); break; case DRM_GPUVA_OP_REMAP: - unbind_op_commit(vm, tile, pt_update_ops, - gpuva_to_vma(op->base.remap.unmap->va), fence, - fence2); + { + struct xe_vma *old = gpuva_to_vma(op->base.remap.unmap->va); + + if (xe_vma_is_cpu_addr_mirror(old)) + break; + + unbind_op_commit(vm, tile, pt_update_ops, old, fence, fence2); if (op->remap.prev) bind_op_commit(vm, tile, pt_update_ops, op->remap.prev, @@ -1943,14 +2211,35 @@ static void op_commit(struct xe_vm *vm, bind_op_commit(vm, tile, pt_update_ops, op->remap.next, fence, fence2); break; + } case DRM_GPUVA_OP_UNMAP: - unbind_op_commit(vm, tile, pt_update_ops, - gpuva_to_vma(op->base.unmap.va), fence, fence2); + { + struct xe_vma *vma = gpuva_to_vma(op->base.unmap.va); + + if (!xe_vma_is_cpu_addr_mirror(vma)) + unbind_op_commit(vm, tile, pt_update_ops, vma, fence, + fence2); break; + } case DRM_GPUVA_OP_PREFETCH: - bind_op_commit(vm, tile, pt_update_ops, - gpuva_to_vma(op->base.prefetch.va), fence, fence2); + { + struct xe_vma *vma = gpuva_to_vma(op->base.prefetch.va); + + if (!xe_vma_is_cpu_addr_mirror(vma)) + bind_op_commit(vm, tile, pt_update_ops, vma, fence, + fence2); + break; + } + case DRM_GPUVA_OP_DRIVER: + { + if (op->subop == XE_VMA_SUBOP_MAP_RANGE) { + op->map_range.range->tile_present |= BIT(tile->id); + op->map_range.range->tile_invalidated &= ~BIT(tile->id); + } else if (op->subop == XE_VMA_SUBOP_UNMAP_RANGE) { + op->unmap_range.range->tile_present &= ~BIT(tile->id); + } break; + } default: drm_warn(&vm->xe->drm, "NOT POSSIBLE"); } @@ -1968,6 +2257,12 @@ static const struct xe_migrate_pt_update_ops userptr_migrate_ops = { .pre_commit = xe_pt_userptr_pre_commit, }; +static const struct xe_migrate_pt_update_ops svm_migrate_ops = { + .populate = xe_vm_populate_pgtable, + .clear = xe_migrate_clear_pgtable_callback, + .pre_commit = xe_pt_svm_pre_commit, +}; + /** * xe_pt_update_ops_run() - Run PT update operations * @tile: Tile of PT update operations @@ -1993,7 +2288,9 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops) struct xe_vma_op *op; int err = 0, i; struct xe_migrate_pt_update update = { - .ops = pt_update_ops->needs_userptr_lock ? + .ops = pt_update_ops->needs_svm_lock ? + &svm_migrate_ops : + pt_update_ops->needs_userptr_lock ? &userptr_migrate_ops : &migrate_ops, .vops = vops, @@ -2114,6 +2411,8 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops) &ifence->base.base, &mfence->base.base); } + if (pt_update_ops->needs_svm_lock) + xe_svm_notifier_unlock(vm); if (pt_update_ops->needs_userptr_lock) up_read(&vm->userptr.notifier_lock); diff --git a/drivers/gpu/drm/xe/xe_pt.h b/drivers/gpu/drm/xe/xe_pt.h index 9ab386431cad..5ecf003d513c 100644 --- a/drivers/gpu/drm/xe/xe_pt.h +++ b/drivers/gpu/drm/xe/xe_pt.h @@ -13,6 +13,7 @@ struct dma_fence; struct xe_bo; struct xe_device; struct xe_exec_queue; +struct xe_svm_range; struct xe_sync_entry; struct xe_tile; struct xe_vm; @@ -35,6 +36,8 @@ void xe_pt_populate_empty(struct xe_tile *tile, struct xe_vm *vm, void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred); +void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt); + int xe_pt_update_ops_prepare(struct xe_tile *tile, struct xe_vma_ops *vops); struct dma_fence *xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops); @@ -42,5 +45,7 @@ void xe_pt_update_ops_fini(struct xe_tile *tile, struct xe_vma_ops *vops); void xe_pt_update_ops_abort(struct xe_tile *tile, struct xe_vma_ops *vops); bool xe_pt_zap_ptes(struct xe_tile *tile, struct xe_vma *vma); +bool xe_pt_zap_ptes_range(struct xe_tile *tile, struct xe_vm *vm, + struct xe_svm_range *range); #endif diff --git a/drivers/gpu/drm/xe/xe_pt_types.h b/drivers/gpu/drm/xe/xe_pt_types.h index 384cc04de719..69eab6f37cfe 100644 --- a/drivers/gpu/drm/xe/xe_pt_types.h +++ b/drivers/gpu/drm/xe/xe_pt_types.h @@ -104,6 +104,8 @@ struct xe_vm_pgtable_update_ops { u32 num_ops; /** @current_op: current operations */ u32 current_op; + /** @needs_svm_lock: Needs SVM lock */ + bool needs_svm_lock; /** @needs_userptr_lock: Needs userptr lock */ bool needs_userptr_lock; /** @needs_invalidation: Needs invalidation */ diff --git a/drivers/gpu/drm/xe/xe_pt_walk.c b/drivers/gpu/drm/xe/xe_pt_walk.c index b8b3d2aea492..be602a763ff3 100644 --- a/drivers/gpu/drm/xe/xe_pt_walk.c +++ b/drivers/gpu/drm/xe/xe_pt_walk.c @@ -74,7 +74,8 @@ int xe_pt_walk_range(struct xe_ptw *parent, unsigned int level, u64 addr, u64 end, struct xe_pt_walk *walk) { pgoff_t offset = xe_pt_offset(addr, level, walk); - struct xe_ptw **entries = parent->children ? parent->children : NULL; + struct xe_ptw **entries = walk->staging ? (parent->staging ?: NULL) : + (parent->children ?: NULL); const struct xe_pt_walk_ops *ops = walk->ops; enum page_walk_action action; struct xe_ptw *child; diff --git a/drivers/gpu/drm/xe/xe_pt_walk.h b/drivers/gpu/drm/xe/xe_pt_walk.h index 5ecc4d2f0f65..5c02c244f7de 100644 --- a/drivers/gpu/drm/xe/xe_pt_walk.h +++ b/drivers/gpu/drm/xe/xe_pt_walk.h @@ -11,12 +11,14 @@ /** * struct xe_ptw - base class for driver pagetable subclassing. * @children: Pointer to an array of children if any. + * @staging: Pointer to an array of staging if any. * * Drivers could subclass this, and if it's a page-directory, typically * embed an array of xe_ptw pointers. */ struct xe_ptw { struct xe_ptw **children; + struct xe_ptw **staging; }; /** @@ -41,6 +43,8 @@ struct xe_pt_walk { * as shared pagetables. */ bool shared_pt_mode; + /** @staging: Walk staging PT structure */ + bool staging; }; /** diff --git a/drivers/gpu/drm/xe/xe_pxp.c b/drivers/gpu/drm/xe/xe_pxp.c index 3cd3f83e86b0..454ea7dc08ac 100644 --- a/drivers/gpu/drm/xe/xe_pxp.c +++ b/drivers/gpu/drm/xe/xe_pxp.c @@ -132,14 +132,6 @@ static int pxp_wait_for_session_state(struct xe_pxp *pxp, u32 id, bool in_play) static void pxp_invalidate_queues(struct xe_pxp *pxp); -static void pxp_invalidate_state(struct xe_pxp *pxp) -{ - pxp_invalidate_queues(pxp); - - if (pxp->status == XE_PXP_ACTIVE) - pxp->key_instance++; -} - static int pxp_terminate_hw(struct xe_pxp *pxp) { struct xe_gt *gt = pxp->gt; @@ -193,7 +185,8 @@ static void pxp_terminate(struct xe_pxp *pxp) mutex_lock(&pxp->mutex); - pxp_invalidate_state(pxp); + if (pxp->status == XE_PXP_ACTIVE) + pxp->key_instance++; /* * we'll mark the status as needing termination on resume, so no need to @@ -220,6 +213,8 @@ static void pxp_terminate(struct xe_pxp *pxp) mutex_unlock(&pxp->mutex); + pxp_invalidate_queues(pxp); + ret = pxp_terminate_hw(pxp); if (ret) { drm_err(&xe->drm, "PXP termination failed: %pe\n", ERR_PTR(ret)); @@ -665,23 +660,15 @@ out: return ret; } -/** - * xe_pxp_exec_queue_remove - remove a queue from the PXP list - * @pxp: the xe->pxp pointer (it will be NULL if PXP is disabled) - * @q: the queue to remove from the list - * - * If PXP is enabled and the exec_queue is in the list, the queue will be - * removed from the list and its PM reference will be released. It is safe to - * call this function multiple times for the same queue. - */ -void xe_pxp_exec_queue_remove(struct xe_pxp *pxp, struct xe_exec_queue *q) +static void __pxp_exec_queue_remove(struct xe_pxp *pxp, struct xe_exec_queue *q, bool lock) { bool need_pm_put = false; if (!xe_pxp_is_enabled(pxp)) return; - spin_lock_irq(&pxp->queues.lock); + if (lock) + spin_lock_irq(&pxp->queues.lock); if (!list_empty(&q->pxp.link)) { list_del_init(&q->pxp.link); @@ -690,36 +677,54 @@ void xe_pxp_exec_queue_remove(struct xe_pxp *pxp, struct xe_exec_queue *q) q->pxp.type = DRM_XE_PXP_TYPE_NONE; - spin_unlock_irq(&pxp->queues.lock); + if (lock) + spin_unlock_irq(&pxp->queues.lock); if (need_pm_put) xe_pm_runtime_put(pxp->xe); } +/** + * xe_pxp_exec_queue_remove - remove a queue from the PXP list + * @pxp: the xe->pxp pointer (it will be NULL if PXP is disabled) + * @q: the queue to remove from the list + * + * If PXP is enabled and the exec_queue is in the list, the queue will be + * removed from the list and its PM reference will be released. It is safe to + * call this function multiple times for the same queue. + */ +void xe_pxp_exec_queue_remove(struct xe_pxp *pxp, struct xe_exec_queue *q) +{ + __pxp_exec_queue_remove(pxp, q, true); +} + static void pxp_invalidate_queues(struct xe_pxp *pxp) { struct xe_exec_queue *tmp, *q; + LIST_HEAD(to_clean); spin_lock_irq(&pxp->queues.lock); - /* - * Removing a queue from the PXP list requires a put of the RPM ref that - * the queue holds to keep the PXP session alive, which can't be done - * under spinlock. Since it is safe to kill a queue multiple times, we - * can leave the invalid queue in the list for now and postpone the - * removal and associated RPM put to when the queue is destroyed. - */ - list_for_each_entry(tmp, &pxp->queues.list, pxp.link) { - q = xe_exec_queue_get_unless_zero(tmp); - + list_for_each_entry_safe(q, tmp, &pxp->queues.list, pxp.link) { + q = xe_exec_queue_get_unless_zero(q); if (!q) continue; + list_move_tail(&q->pxp.link, &to_clean); + } + spin_unlock_irq(&pxp->queues.lock); + + list_for_each_entry_safe(q, tmp, &to_clean, pxp.link) { xe_exec_queue_kill(q); + + /* + * We hold a ref to the queue so there is no risk of racing with + * the calls to exec_queue_remove coming from exec_queue_destroy. + */ + __pxp_exec_queue_remove(pxp, q, false); + xe_exec_queue_put(q); } - - spin_unlock_irq(&pxp->queues.lock); } /** @@ -791,7 +796,6 @@ int xe_pxp_bo_key_check(struct xe_pxp *pxp, struct xe_bo *bo) /** * xe_pxp_obj_key_check - check if the key used by a drm_gem_obj is valid - * @pxp: the xe->pxp pointer (it will be NULL if PXP is disabled) * @obj: the drm_gem_obj we want to check * * Checks whether a drm_gem_obj was encrypted with the current key or an @@ -800,9 +804,13 @@ int xe_pxp_bo_key_check(struct xe_pxp *pxp, struct xe_bo *bo) * Returns: 0 if the key is valid, -ENODEV if PXP is disabled, -EINVAL if the * obj is not using PXP, -ENOEXEC if the key is not valid. */ -int xe_pxp_obj_key_check(struct xe_pxp *pxp, struct drm_gem_object *obj) +int xe_pxp_obj_key_check(struct drm_gem_object *obj) { - return xe_pxp_bo_key_check(pxp, gem_to_xe_bo(obj)); + struct xe_bo *bo = gem_to_xe_bo(obj); + struct xe_device *xe = xe_bo_device(bo); + struct xe_pxp *pxp = xe->pxp; + + return xe_pxp_bo_key_check(pxp, bo); } /** @@ -816,6 +824,7 @@ int xe_pxp_obj_key_check(struct xe_pxp *pxp, struct drm_gem_object *obj) */ int xe_pxp_pm_suspend(struct xe_pxp *pxp) { + bool needs_queue_inval = false; int ret = 0; if (!xe_pxp_is_enabled(pxp)) @@ -848,7 +857,8 @@ wait_for_activation: break; fallthrough; case XE_PXP_ACTIVE: - pxp_invalidate_state(pxp); + pxp->key_instance++; + needs_queue_inval = true; break; default: drm_err(&pxp->xe->drm, "unexpected state during PXP suspend: %u", @@ -865,6 +875,9 @@ wait_for_activation: mutex_unlock(&pxp->mutex); + if (needs_queue_inval) + pxp_invalidate_queues(pxp); + /* * if there is a termination in progress, wait for it. * We need to wait outside the lock because the completion is done from diff --git a/drivers/gpu/drm/xe/xe_pxp.h b/drivers/gpu/drm/xe/xe_pxp.h index 546b156d63aa..71a23280b900 100644 --- a/drivers/gpu/drm/xe/xe_pxp.h +++ b/drivers/gpu/drm/xe/xe_pxp.h @@ -30,6 +30,6 @@ void xe_pxp_exec_queue_remove(struct xe_pxp *pxp, struct xe_exec_queue *q); int xe_pxp_key_assign(struct xe_pxp *pxp, struct xe_bo *bo); int xe_pxp_bo_key_check(struct xe_pxp *pxp, struct xe_bo *bo); -int xe_pxp_obj_key_check(struct xe_pxp *pxp, struct drm_gem_object *obj); +int xe_pxp_obj_key_check(struct drm_gem_object *obj); #endif /* __XE_PXP_H__ */ diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c index ebfae746f861..5e65830dad25 100644 --- a/drivers/gpu/drm/xe/xe_query.c +++ b/drivers/gpu/drm/xe/xe_query.c @@ -16,6 +16,7 @@ #include "regs/xe_gt_regs.h" #include "xe_bo.h" #include "xe_device.h" +#include "xe_eu_stall.h" #include "xe_exec_queue.h" #include "xe_force_wake.h" #include "xe_ggtt.h" @@ -337,8 +338,13 @@ static int query_config(struct xe_device *xe, struct drm_xe_device_query *query) config->info[DRM_XE_QUERY_CONFIG_REV_AND_DEVICE_ID] = xe->info.devid | (xe->info.revid << 16); if (xe_device_get_root_tile(xe)->mem.vram.usable_size) - config->info[DRM_XE_QUERY_CONFIG_FLAGS] = + config->info[DRM_XE_QUERY_CONFIG_FLAGS] |= DRM_XE_QUERY_CONFIG_FLAG_HAS_VRAM; + if (xe->info.has_usm && IS_ENABLED(CONFIG_DRM_GPUSVM)) + config->info[DRM_XE_QUERY_CONFIG_FLAGS] |= + DRM_XE_QUERY_CONFIG_FLAG_HAS_CPU_ADDR_MIRROR; + config->info[DRM_XE_QUERY_CONFIG_FLAGS] |= + DRM_XE_QUERY_CONFIG_FLAG_HAS_LOW_LATENCY; config->info[DRM_XE_QUERY_CONFIG_MIN_ALIGNMENT] = xe->info.vram_flags & XE_VRAM_FLAGS_NEED64K ? SZ_64K : SZ_4K; config->info[DRM_XE_QUERY_CONFIG_VA_BITS] = xe->info.va_bits; @@ -729,6 +735,47 @@ static int query_pxp_status(struct xe_device *xe, struct drm_xe_device_query *qu return 0; } +static int query_eu_stall(struct xe_device *xe, + struct drm_xe_device_query *query) +{ + void __user *query_ptr = u64_to_user_ptr(query->data); + struct drm_xe_query_eu_stall *info; + size_t size, array_size; + const u64 *rates; + u32 num_rates; + int ret; + + if (!xe_eu_stall_supported_on_platform(xe)) { + drm_dbg(&xe->drm, "EU stall monitoring is not supported on this platform\n"); + return -ENODEV; + } + + array_size = xe_eu_stall_get_sampling_rates(&num_rates, &rates); + size = sizeof(struct drm_xe_query_eu_stall) + array_size; + + if (query->size == 0) { + query->size = size; + return 0; + } else if (XE_IOCTL_DBG(xe, query->size != size)) { + return -EINVAL; + } + + info = kzalloc(size, GFP_KERNEL); + if (!info) + return -ENOMEM; + + info->num_sampling_rates = num_rates; + info->capabilities = DRM_XE_EU_STALL_CAPS_BASE; + info->record_size = xe_eu_stall_data_record_size(xe); + info->per_xecore_buf_size = xe_eu_stall_get_per_xecore_buf_size(); + memcpy(info->sampling_rates, rates, array_size); + + ret = copy_to_user(query_ptr, info, size); + kfree(info); + + return ret ? -EFAULT : 0; +} + static int (* const xe_query_funcs[])(struct xe_device *xe, struct drm_xe_device_query *query) = { query_engines, @@ -741,6 +788,7 @@ static int (* const xe_query_funcs[])(struct xe_device *xe, query_uc_fw_version, query_oa_units, query_pxp_status, + query_eu_stall, }; int xe_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file) diff --git a/drivers/gpu/drm/xe/xe_reg_whitelist.c b/drivers/gpu/drm/xe/xe_reg_whitelist.c index edab5d4e3ba5..23f6c81d9994 100644 --- a/drivers/gpu/drm/xe/xe_reg_whitelist.c +++ b/drivers/gpu/drm/xe/xe_reg_whitelist.c @@ -88,7 +88,6 @@ static const struct xe_rtp_entry_sr register_whitelist[] = { RING_FORCE_TO_NONPRIV_ACCESS_RD | RING_FORCE_TO_NONPRIV_RANGE_4)) }, - {} }; static void whitelist_apply_to_hwe(struct xe_hw_engine *hwe) @@ -137,7 +136,8 @@ void xe_reg_whitelist_process_engine(struct xe_hw_engine *hwe) { struct xe_rtp_process_ctx ctx = XE_RTP_PROCESS_CTX_INITIALIZER(hwe); - xe_rtp_process_to_sr(&ctx, register_whitelist, &hwe->reg_whitelist); + xe_rtp_process_to_sr(&ctx, register_whitelist, ARRAY_SIZE(register_whitelist), + &hwe->reg_whitelist); whitelist_apply_to_hwe(hwe); } diff --git a/drivers/gpu/drm/xe/xe_res_cursor.h b/drivers/gpu/drm/xe/xe_res_cursor.h index dca374b6521c..d1a403cfb628 100644 --- a/drivers/gpu/drm/xe/xe_res_cursor.h +++ b/drivers/gpu/drm/xe/xe_res_cursor.h @@ -26,6 +26,7 @@ #include <linux/scatterlist.h> +#include <drm/drm_pagemap.h> #include <drm/ttm/ttm_placement.h> #include <drm/ttm/ttm_range_manager.h> #include <drm/ttm/ttm_resource.h> @@ -34,17 +35,38 @@ #include "xe_bo.h" #include "xe_device.h" #include "xe_macros.h" +#include "xe_svm.h" #include "xe_ttm_vram_mgr.h" -/* state back for walking over vram_mgr, stolen_mgr, and gtt_mgr allocations */ +/** + * struct xe_res_cursor - state for walking over dma mapping, vram_mgr, + * stolen_mgr, and gtt_mgr allocations + */ struct xe_res_cursor { + /** @start: Start of cursor */ u64 start; + /** @size: Size of the current segment. */ u64 size; + /** @remaining: Remaining bytes in cursor */ u64 remaining; + /** @node: Opaque point current node cursor */ void *node; + /** @mem_type: Memory type */ u32 mem_type; + /** @sgl: Scatterlist for cursor */ struct scatterlist *sgl; + /** @dma_addr: Current element in a struct drm_pagemap_device_addr array */ + const struct drm_pagemap_device_addr *dma_addr; + /** @mm: Buddy allocator for VRAM cursor */ struct drm_buddy *mm; + /** + * @dma_start: DMA start address for the current segment. + * This may be different to @dma_addr.addr since elements in + * the array may be coalesced to a single segment. + */ + u64 dma_start; + /** @dma_seg_size: Size of the current DMA segment. */ + u64 dma_seg_size; }; static struct drm_buddy *xe_res_get_buddy(struct ttm_resource *res) @@ -70,6 +92,7 @@ static inline void xe_res_first(struct ttm_resource *res, struct xe_res_cursor *cur) { cur->sgl = NULL; + cur->dma_addr = NULL; if (!res) goto fallback; @@ -142,6 +165,36 @@ static inline void __xe_res_sg_next(struct xe_res_cursor *cur) } /** + * __xe_res_dma_next() - Advance the cursor when end-of-segment is reached + * @cur: The cursor + */ +static inline void __xe_res_dma_next(struct xe_res_cursor *cur) +{ + const struct drm_pagemap_device_addr *addr = cur->dma_addr; + u64 start = cur->start; + + while (start >= cur->dma_seg_size) { + start -= cur->dma_seg_size; + addr++; + cur->dma_seg_size = PAGE_SIZE << addr->order; + } + cur->dma_start = addr->addr; + + /* Coalesce array_elements */ + while (cur->dma_seg_size - start < cur->remaining) { + if (cur->dma_start + cur->dma_seg_size != addr[1].addr || + addr->proto != addr[1].proto) + break; + addr++; + cur->dma_seg_size += PAGE_SIZE << addr->order; + } + + cur->dma_addr = addr; + cur->start = start; + cur->size = cur->dma_seg_size - start; +} + +/** * xe_res_first_sg - initialize a xe_res_cursor with a scatter gather table * * @sg: scatter gather table to walk @@ -160,12 +213,43 @@ static inline void xe_res_first_sg(const struct sg_table *sg, cur->start = start; cur->remaining = size; cur->size = 0; + cur->dma_addr = NULL; cur->sgl = sg->sgl; cur->mem_type = XE_PL_TT; __xe_res_sg_next(cur); } /** + * xe_res_first_dma - initialize a xe_res_cursor with dma_addr array + * + * @dma_addr: struct drm_pagemap_device_addr array to walk + * @start: Start of the range + * @size: Size of the range + * @cur: cursor object to initialize + * + * Start walking over the range of allocations between @start and @size. + */ +static inline void xe_res_first_dma(const struct drm_pagemap_device_addr *dma_addr, + u64 start, u64 size, + struct xe_res_cursor *cur) +{ + XE_WARN_ON(!dma_addr); + XE_WARN_ON(!IS_ALIGNED(start, PAGE_SIZE) || + !IS_ALIGNED(size, PAGE_SIZE)); + + cur->node = NULL; + cur->start = start; + cur->remaining = size; + cur->dma_seg_size = PAGE_SIZE << dma_addr->order; + cur->dma_start = 0; + cur->size = 0; + cur->dma_addr = dma_addr; + __xe_res_dma_next(cur); + cur->sgl = NULL; + cur->mem_type = XE_PL_TT; +} + +/** * xe_res_next - advance the cursor * * @cur: the cursor to advance @@ -191,6 +275,12 @@ static inline void xe_res_next(struct xe_res_cursor *cur, u64 size) return; } + if (cur->dma_addr) { + cur->start += size; + __xe_res_dma_next(cur); + return; + } + if (cur->sgl) { cur->start += size; __xe_res_sg_next(cur); @@ -232,6 +322,35 @@ static inline void xe_res_next(struct xe_res_cursor *cur, u64 size) */ static inline u64 xe_res_dma(const struct xe_res_cursor *cur) { - return cur->sgl ? sg_dma_address(cur->sgl) + cur->start : cur->start; + if (cur->dma_addr) + return cur->dma_start + cur->start; + else if (cur->sgl) + return sg_dma_address(cur->sgl) + cur->start; + else + return cur->start; +} + +/** + * xe_res_is_vram() - Whether the cursor current dma address points to + * same-device VRAM + * @cur: The cursor. + * + * Return: true iff the address returned by xe_res_dma() points to internal vram. + */ +static inline bool xe_res_is_vram(const struct xe_res_cursor *cur) +{ + if (cur->dma_addr) + return cur->dma_addr->proto == XE_INTERCONNECT_VRAM; + + switch (cur->mem_type) { + case XE_PL_STOLEN: + case XE_PL_VRAM0: + case XE_PL_VRAM1: + return true; + default: + break; + } + + return false; } #endif diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index 0c230ee53bba..917fc16de866 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -90,11 +90,10 @@ static int emit_flush_dw(u32 *dw, int i) return i; } -static int emit_flush_imm_ggtt(u32 addr, u32 value, bool invalidate_tlb, - u32 *dw, int i) +static int emit_flush_imm_ggtt(u32 addr, u32 value, u32 flags, u32 *dw, int i) { dw[i++] = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_IMM_DW | - (invalidate_tlb ? MI_INVALIDATE_TLB : 0); + flags; dw[i++] = addr | MI_FLUSH_DW_USE_GTT; dw[i++] = 0; dw[i++] = value; @@ -111,16 +110,13 @@ static int emit_bb_start(u64 batch_addr, u32 ppgtt_flag, u32 *dw, int i) return i; } -static int emit_flush_invalidate(u32 flag, u32 *dw, int i) +static int emit_flush_invalidate(u32 *dw, int i) { - dw[i] = MI_FLUSH_DW; - dw[i] |= flag; - dw[i++] |= MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_IMM_DW | - MI_FLUSH_DW_STORE_INDEX; - - dw[i++] = LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT; + dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW | + MI_FLUSH_IMM_DW | MI_FLUSH_DW_STORE_INDEX; + dw[i++] = LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR; + dw[i++] = 0; dw[i++] = 0; - dw[i++] = ~0U; return i; } @@ -177,6 +173,10 @@ static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i) bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK); u32 flags; + if (XE_WA(gt, 14016712196)) + i = emit_pipe_control(dw, i, 0, PIPE_CONTROL_DEPTH_CACHE_FLUSH, + LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR, 0); + flags = (PIPE_CONTROL_CS_STALL | PIPE_CONTROL_TILE_CACHE_FLUSH | PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | @@ -253,7 +253,7 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc if (job->ring_ops_flush_tlb) { dw[i++] = preparser_disable(true); i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc), - seqno, true, dw, i); + seqno, MI_INVALIDATE_TLB, dw, i); dw[i++] = preparser_disable(false); } else { i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc), @@ -269,7 +269,7 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc dw, i); } - i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i); + i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, 0, dw, i); i = emit_user_interrupt(dw, i); @@ -315,7 +315,7 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc, if (job->ring_ops_flush_tlb) i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc), - seqno, true, dw, i); + seqno, MI_INVALIDATE_TLB, dw, i); dw[i++] = preparser_disable(false); @@ -332,7 +332,7 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc, dw, i); } - i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i); + i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, 0, dw, i); i = emit_user_interrupt(dw, i); @@ -409,7 +409,7 @@ static void emit_migration_job_gen12(struct xe_sched_job *job, if (!IS_SRIOV_VF(gt_to_xe(job->q->gt))) { /* XXX: Do we need this? Leaving for now. */ dw[i++] = preparser_disable(true); - i = emit_flush_invalidate(0, dw, i); + i = emit_flush_invalidate(dw, i); dw[i++] = preparser_disable(false); } diff --git a/drivers/gpu/drm/xe/xe_rtp.c b/drivers/gpu/drm/xe/xe_rtp.c index 7a1c78fdfc92..13bb62d3e615 100644 --- a/drivers/gpu/drm/xe/xe_rtp.c +++ b/drivers/gpu/drm/xe/xe_rtp.c @@ -237,6 +237,7 @@ static void rtp_mark_active(struct xe_device *xe, * the save-restore argument. * @ctx: The context for processing the table, with one of device, gt or hwe * @entries: Table with RTP definitions + * @n_entries: Number of entries to process, usually ARRAY_SIZE(entries) * @sr: Save-restore struct where matching rules execute the action. This can be * viewed as the "coalesced view" of multiple the tables. The bits for each * register set are expected not to collide with previously added entries @@ -247,6 +248,7 @@ static void rtp_mark_active(struct xe_device *xe, */ void xe_rtp_process_to_sr(struct xe_rtp_process_ctx *ctx, const struct xe_rtp_entry_sr *entries, + size_t n_entries, struct xe_reg_sr *sr) { const struct xe_rtp_entry_sr *entry; @@ -259,7 +261,9 @@ void xe_rtp_process_to_sr(struct xe_rtp_process_ctx *ctx, if (IS_SRIOV_VF(xe)) return; - for (entry = entries; entry && entry->name; entry++) { + xe_assert(xe, entries); + + for (entry = entries; entry - entries < n_entries; entry++) { bool match = false; if (entry->flags & XE_RTP_ENTRY_FLAG_FOREACH_ENGINE) { diff --git a/drivers/gpu/drm/xe/xe_rtp.h b/drivers/gpu/drm/xe/xe_rtp.h index 38b9f13bba5e..4fe736a11c42 100644 --- a/drivers/gpu/drm/xe/xe_rtp.h +++ b/drivers/gpu/drm/xe/xe_rtp.h @@ -430,7 +430,7 @@ void xe_rtp_process_ctx_enable_active_tracking(struct xe_rtp_process_ctx *ctx, void xe_rtp_process_to_sr(struct xe_rtp_process_ctx *ctx, const struct xe_rtp_entry_sr *entries, - struct xe_reg_sr *sr); + size_t n_entries, struct xe_reg_sr *sr); void xe_rtp_process(struct xe_rtp_process_ctx *ctx, const struct xe_rtp_entry *entries); diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c index 02b4eadf8407..d939ce70e6fa 100644 --- a/drivers/gpu/drm/xe/xe_survivability_mode.c +++ b/drivers/gpu/drm/xe/xe_survivability_mode.c @@ -127,40 +127,55 @@ static ssize_t survivability_mode_show(struct device *dev, static DEVICE_ATTR_ADMIN_RO(survivability_mode); -static void enable_survivability_mode(struct pci_dev *pdev) +static void xe_survivability_mode_fini(void *arg) +{ + struct xe_device *xe = arg; + struct pci_dev *pdev = to_pci_dev(xe->drm.dev); + struct device *dev = &pdev->dev; + + sysfs_remove_file(&dev->kobj, &dev_attr_survivability_mode.attr); +} + +static int enable_survivability_mode(struct pci_dev *pdev) { struct device *dev = &pdev->dev; struct xe_device *xe = pdev_to_xe_device(pdev); struct xe_survivability *survivability = &xe->survivability; int ret = 0; - /* set survivability mode */ - survivability->mode = true; - dev_info(dev, "In Survivability Mode\n"); - /* create survivability mode sysfs */ ret = sysfs_create_file(&dev->kobj, &dev_attr_survivability_mode.attr); if (ret) { dev_warn(dev, "Failed to create survivability sysfs files\n"); - return; + return ret; } - xe_heci_gsc_init(xe); + ret = devm_add_action_or_reset(xe->drm.dev, + xe_survivability_mode_fini, xe); + if (ret) + return ret; + + ret = xe_heci_gsc_init(xe); + if (ret) + return ret; xe_vsec_init(xe); + + survivability->mode = true; + dev_err(dev, "In Survivability Mode\n"); + + return 0; } /** - * xe_survivability_mode_enabled - check if survivability mode is enabled + * xe_survivability_mode_is_enabled - check if survivability mode is enabled * @xe: xe device instance * * Returns true if in survivability mode, false otherwise */ -bool xe_survivability_mode_enabled(struct xe_device *xe) +bool xe_survivability_mode_is_enabled(struct xe_device *xe) { - struct xe_survivability *survivability = &xe->survivability; - - return survivability->mode; + return xe->survivability.mode; } /** @@ -183,35 +198,19 @@ bool xe_survivability_mode_required(struct xe_device *xe) data = xe_mmio_read32(mmio, PCODE_SCRATCH(0)); survivability->boot_status = REG_FIELD_GET(BOOT_STATUS, data); - return (survivability->boot_status == NON_CRITICAL_FAILURE || - survivability->boot_status == CRITICAL_FAILURE); + return survivability->boot_status == NON_CRITICAL_FAILURE || + survivability->boot_status == CRITICAL_FAILURE; } /** - * xe_survivability_mode_remove - remove survivability mode + * xe_survivability_mode_enable - Initialize and enable the survivability mode * @xe: xe device instance * - * clean up sysfs entries of survivability mode - */ -void xe_survivability_mode_remove(struct xe_device *xe) -{ - struct xe_survivability *survivability = &xe->survivability; - struct pci_dev *pdev = to_pci_dev(xe->drm.dev); - struct device *dev = &pdev->dev; - - sysfs_remove_file(&dev->kobj, &dev_attr_survivability_mode.attr); - xe_heci_gsc_fini(xe); - kfree(survivability->info); - pci_set_drvdata(pdev, NULL); -} - -/** - * xe_survivability_mode_init - Initialize the survivability mode - * @xe: xe device instance + * Initialize survivability information and enable survivability mode * - * Initializes survivability information and enables survivability mode + * Return: 0 for success, negative error code otherwise. */ -void xe_survivability_mode_init(struct xe_device *xe) +int xe_survivability_mode_enable(struct xe_device *xe) { struct xe_survivability *survivability = &xe->survivability; struct xe_survivability_info *info; @@ -219,9 +218,10 @@ void xe_survivability_mode_init(struct xe_device *xe) survivability->size = MAX_SCRATCH_MMIO; - info = kcalloc(survivability->size, sizeof(*info), GFP_KERNEL); + info = devm_kcalloc(xe->drm.dev, survivability->size, sizeof(*info), + GFP_KERNEL); if (!info) - return; + return -ENOMEM; survivability->info = info; @@ -230,9 +230,8 @@ void xe_survivability_mode_init(struct xe_device *xe) /* Only log debug information and exit if it is a critical failure */ if (survivability->boot_status == CRITICAL_FAILURE) { log_survivability_info(pdev); - kfree(survivability->info); - return; + return -ENXIO; } - enable_survivability_mode(pdev); + return enable_survivability_mode(pdev); } diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.h b/drivers/gpu/drm/xe/xe_survivability_mode.h index f530507a22c6..f4df5f9025ce 100644 --- a/drivers/gpu/drm/xe/xe_survivability_mode.h +++ b/drivers/gpu/drm/xe/xe_survivability_mode.h @@ -10,9 +10,8 @@ struct xe_device; -void xe_survivability_mode_init(struct xe_device *xe); -void xe_survivability_mode_remove(struct xe_device *xe); -bool xe_survivability_mode_enabled(struct xe_device *xe); +int xe_survivability_mode_enable(struct xe_device *xe); +bool xe_survivability_mode_is_enabled(struct xe_device *xe); bool xe_survivability_mode_required(struct xe_device *xe); #endif /* _XE_SURVIVABILITY_MODE_H_ */ diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c new file mode 100644 index 000000000000..516898e99b26 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_svm.c @@ -0,0 +1,946 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2024 Intel Corporation + */ + +#include "xe_bo.h" +#include "xe_gt_tlb_invalidation.h" +#include "xe_migrate.h" +#include "xe_module.h" +#include "xe_pt.h" +#include "xe_svm.h" +#include "xe_ttm_vram_mgr.h" +#include "xe_vm.h" +#include "xe_vm_types.h" + +static bool xe_svm_range_in_vram(struct xe_svm_range *range) +{ + /* Not reliable without notifier lock */ + return range->base.flags.has_devmem_pages; +} + +static bool xe_svm_range_has_vram_binding(struct xe_svm_range *range) +{ + /* Not reliable without notifier lock */ + return xe_svm_range_in_vram(range) && range->tile_present; +} + +static struct xe_vm *gpusvm_to_vm(struct drm_gpusvm *gpusvm) +{ + return container_of(gpusvm, struct xe_vm, svm.gpusvm); +} + +static struct xe_vm *range_to_vm(struct drm_gpusvm_range *r) +{ + return gpusvm_to_vm(r->gpusvm); +} + +static unsigned long xe_svm_range_start(struct xe_svm_range *range) +{ + return drm_gpusvm_range_start(&range->base); +} + +static unsigned long xe_svm_range_end(struct xe_svm_range *range) +{ + return drm_gpusvm_range_end(&range->base); +} + +static unsigned long xe_svm_range_size(struct xe_svm_range *range) +{ + return drm_gpusvm_range_size(&range->base); +} + +#define range_debug(r__, operaton__) \ + vm_dbg(&range_to_vm(&(r__)->base)->xe->drm, \ + "%s: asid=%u, gpusvm=%p, vram=%d,%d, seqno=%lu, " \ + "start=0x%014lx, end=0x%014lx, size=%lu", \ + (operaton__), range_to_vm(&(r__)->base)->usm.asid, \ + (r__)->base.gpusvm, \ + xe_svm_range_in_vram((r__)) ? 1 : 0, \ + xe_svm_range_has_vram_binding((r__)) ? 1 : 0, \ + (r__)->base.notifier_seq, \ + xe_svm_range_start((r__)), xe_svm_range_end((r__)), \ + xe_svm_range_size((r__))) + +void xe_svm_range_debug(struct xe_svm_range *range, const char *operation) +{ + range_debug(range, operation); +} + +static void *xe_svm_devm_owner(struct xe_device *xe) +{ + return xe; +} + +static struct drm_gpusvm_range * +xe_svm_range_alloc(struct drm_gpusvm *gpusvm) +{ + struct xe_svm_range *range; + + range = kzalloc(sizeof(*range), GFP_KERNEL); + if (!range) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&range->garbage_collector_link); + xe_vm_get(gpusvm_to_vm(gpusvm)); + + return &range->base; +} + +static void xe_svm_range_free(struct drm_gpusvm_range *range) +{ + xe_vm_put(range_to_vm(range)); + kfree(range); +} + +static struct xe_svm_range *to_xe_range(struct drm_gpusvm_range *r) +{ + return container_of(r, struct xe_svm_range, base); +} + +static void +xe_svm_garbage_collector_add_range(struct xe_vm *vm, struct xe_svm_range *range, + const struct mmu_notifier_range *mmu_range) +{ + struct xe_device *xe = vm->xe; + + range_debug(range, "GARBAGE COLLECTOR ADD"); + + drm_gpusvm_range_set_unmapped(&range->base, mmu_range); + + spin_lock(&vm->svm.garbage_collector.lock); + if (list_empty(&range->garbage_collector_link)) + list_add_tail(&range->garbage_collector_link, + &vm->svm.garbage_collector.range_list); + spin_unlock(&vm->svm.garbage_collector.lock); + + queue_work(xe_device_get_root_tile(xe)->primary_gt->usm.pf_wq, + &vm->svm.garbage_collector.work); +} + +static u8 +xe_svm_range_notifier_event_begin(struct xe_vm *vm, struct drm_gpusvm_range *r, + const struct mmu_notifier_range *mmu_range, + u64 *adj_start, u64 *adj_end) +{ + struct xe_svm_range *range = to_xe_range(r); + struct xe_device *xe = vm->xe; + struct xe_tile *tile; + u8 tile_mask = 0; + u8 id; + + xe_svm_assert_in_notifier(vm); + + range_debug(range, "NOTIFIER"); + + /* Skip if already unmapped or if no binding exist */ + if (range->base.flags.unmapped || !range->tile_present) + return 0; + + range_debug(range, "NOTIFIER - EXECUTE"); + + /* Adjust invalidation to range boundaries */ + *adj_start = min(xe_svm_range_start(range), mmu_range->start); + *adj_end = max(xe_svm_range_end(range), mmu_range->end); + + /* + * XXX: Ideally would zap PTEs in one shot in xe_svm_invalidate but the + * invalidation code can't correctly cope with sparse ranges or + * invalidations spanning multiple ranges. + */ + for_each_tile(tile, xe, id) + if (xe_pt_zap_ptes_range(tile, vm, range)) { + tile_mask |= BIT(id); + range->tile_invalidated |= BIT(id); + } + + return tile_mask; +} + +static void +xe_svm_range_notifier_event_end(struct xe_vm *vm, struct drm_gpusvm_range *r, + const struct mmu_notifier_range *mmu_range) +{ + struct drm_gpusvm_ctx ctx = { .in_notifier = true, }; + + xe_svm_assert_in_notifier(vm); + + drm_gpusvm_range_unmap_pages(&vm->svm.gpusvm, r, &ctx); + if (!xe_vm_is_closed(vm) && mmu_range->event == MMU_NOTIFY_UNMAP) + xe_svm_garbage_collector_add_range(vm, to_xe_range(r), + mmu_range); +} + +static void xe_svm_invalidate(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_notifier *notifier, + const struct mmu_notifier_range *mmu_range) +{ + struct xe_vm *vm = gpusvm_to_vm(gpusvm); + struct xe_device *xe = vm->xe; + struct xe_tile *tile; + struct drm_gpusvm_range *r, *first; + struct xe_gt_tlb_invalidation_fence + fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE]; + u64 adj_start = mmu_range->start, adj_end = mmu_range->end; + u8 tile_mask = 0; + u8 id; + u32 fence_id = 0; + long err; + + xe_svm_assert_in_notifier(vm); + + vm_dbg(&gpusvm_to_vm(gpusvm)->xe->drm, + "INVALIDATE: asid=%u, gpusvm=%p, seqno=%lu, start=0x%016lx, end=0x%016lx, event=%d", + vm->usm.asid, gpusvm, notifier->notifier.invalidate_seq, + mmu_range->start, mmu_range->end, mmu_range->event); + + /* Adjust invalidation to notifier boundaries */ + adj_start = max(drm_gpusvm_notifier_start(notifier), adj_start); + adj_end = min(drm_gpusvm_notifier_end(notifier), adj_end); + + first = drm_gpusvm_range_find(notifier, adj_start, adj_end); + if (!first) + return; + + /* + * PTs may be getting destroyed so not safe to touch these but PT should + * be invalidated at this point in time. Regardless we still need to + * ensure any dma mappings are unmapped in the here. + */ + if (xe_vm_is_closed(vm)) + goto range_notifier_event_end; + + /* + * XXX: Less than ideal to always wait on VM's resv slots if an + * invalidation is not required. Could walk range list twice to figure + * out if an invalidations is need, but also not ideal. + */ + err = dma_resv_wait_timeout(xe_vm_resv(vm), + DMA_RESV_USAGE_BOOKKEEP, + false, MAX_SCHEDULE_TIMEOUT); + XE_WARN_ON(err <= 0); + + r = first; + drm_gpusvm_for_each_range(r, notifier, adj_start, adj_end) + tile_mask |= xe_svm_range_notifier_event_begin(vm, r, mmu_range, + &adj_start, + &adj_end); + if (!tile_mask) + goto range_notifier_event_end; + + xe_device_wmb(xe); + + for_each_tile(tile, xe, id) { + if (tile_mask & BIT(id)) { + int err; + + xe_gt_tlb_invalidation_fence_init(tile->primary_gt, + &fence[fence_id], true); + + err = xe_gt_tlb_invalidation_range(tile->primary_gt, + &fence[fence_id], + adj_start, + adj_end, + vm->usm.asid); + if (WARN_ON_ONCE(err < 0)) + goto wait; + ++fence_id; + + if (!tile->media_gt) + continue; + + xe_gt_tlb_invalidation_fence_init(tile->media_gt, + &fence[fence_id], true); + + err = xe_gt_tlb_invalidation_range(tile->media_gt, + &fence[fence_id], + adj_start, + adj_end, + vm->usm.asid); + if (WARN_ON_ONCE(err < 0)) + goto wait; + ++fence_id; + } + } + +wait: + for (id = 0; id < fence_id; ++id) + xe_gt_tlb_invalidation_fence_wait(&fence[id]); + +range_notifier_event_end: + r = first; + drm_gpusvm_for_each_range(r, notifier, adj_start, adj_end) + xe_svm_range_notifier_event_end(vm, r, mmu_range); +} + +static int __xe_svm_garbage_collector(struct xe_vm *vm, + struct xe_svm_range *range) +{ + struct dma_fence *fence; + + range_debug(range, "GARBAGE COLLECTOR"); + + xe_vm_lock(vm, false); + fence = xe_vm_range_unbind(vm, range); + xe_vm_unlock(vm); + if (IS_ERR(fence)) + return PTR_ERR(fence); + dma_fence_put(fence); + + drm_gpusvm_range_remove(&vm->svm.gpusvm, &range->base); + + return 0; +} + +static int xe_svm_garbage_collector(struct xe_vm *vm) +{ + struct xe_svm_range *range; + int err; + + lockdep_assert_held_write(&vm->lock); + + if (xe_vm_is_closed_or_banned(vm)) + return -ENOENT; + + spin_lock(&vm->svm.garbage_collector.lock); + for (;;) { + range = list_first_entry_or_null(&vm->svm.garbage_collector.range_list, + typeof(*range), + garbage_collector_link); + if (!range) + break; + + list_del(&range->garbage_collector_link); + spin_unlock(&vm->svm.garbage_collector.lock); + + err = __xe_svm_garbage_collector(vm, range); + if (err) { + drm_warn(&vm->xe->drm, + "Garbage collection failed: %pe\n", + ERR_PTR(err)); + xe_vm_kill(vm, true); + return err; + } + + spin_lock(&vm->svm.garbage_collector.lock); + } + spin_unlock(&vm->svm.garbage_collector.lock); + + return 0; +} + +static void xe_svm_garbage_collector_work_func(struct work_struct *w) +{ + struct xe_vm *vm = container_of(w, struct xe_vm, + svm.garbage_collector.work); + + down_write(&vm->lock); + xe_svm_garbage_collector(vm); + up_write(&vm->lock); +} + +static struct xe_vram_region *page_to_vr(struct page *page) +{ + return container_of(page->pgmap, struct xe_vram_region, pagemap); +} + +static struct xe_tile *vr_to_tile(struct xe_vram_region *vr) +{ + return container_of(vr, struct xe_tile, mem.vram); +} + +static u64 xe_vram_region_page_to_dpa(struct xe_vram_region *vr, + struct page *page) +{ + u64 dpa; + struct xe_tile *tile = vr_to_tile(vr); + u64 pfn = page_to_pfn(page); + u64 offset; + + xe_tile_assert(tile, is_device_private_page(page)); + xe_tile_assert(tile, (pfn << PAGE_SHIFT) >= vr->hpa_base); + + offset = (pfn << PAGE_SHIFT) - vr->hpa_base; + dpa = vr->dpa_base + offset; + + return dpa; +} + +enum xe_svm_copy_dir { + XE_SVM_COPY_TO_VRAM, + XE_SVM_COPY_TO_SRAM, +}; + +static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr, + unsigned long npages, const enum xe_svm_copy_dir dir) +{ + struct xe_vram_region *vr = NULL; + struct xe_tile *tile; + struct dma_fence *fence = NULL; + unsigned long i; +#define XE_VRAM_ADDR_INVALID ~0x0ull + u64 vram_addr = XE_VRAM_ADDR_INVALID; + int err = 0, pos = 0; + bool sram = dir == XE_SVM_COPY_TO_SRAM; + + /* + * This flow is complex: it locates physically contiguous device pages, + * derives the starting physical address, and performs a single GPU copy + * to for every 8M chunk in a DMA address array. Both device pages and + * DMA addresses may be sparsely populated. If either is NULL, a copy is + * triggered based on the current search state. The last GPU copy is + * waited on to ensure all copies are complete. + */ + + for (i = 0; i < npages; ++i) { + struct page *spage = pages[i]; + struct dma_fence *__fence; + u64 __vram_addr; + bool match = false, chunk, last; + +#define XE_MIGRATE_CHUNK_SIZE SZ_8M + chunk = (i - pos) == (XE_MIGRATE_CHUNK_SIZE / PAGE_SIZE); + last = (i + 1) == npages; + + /* No CPU page and no device pages queue'd to copy */ + if (!dma_addr[i] && vram_addr == XE_VRAM_ADDR_INVALID) + continue; + + if (!vr && spage) { + vr = page_to_vr(spage); + tile = vr_to_tile(vr); + } + XE_WARN_ON(spage && page_to_vr(spage) != vr); + + /* + * CPU page and device page valid, capture physical address on + * first device page, check if physical contiguous on subsequent + * device pages. + */ + if (dma_addr[i] && spage) { + __vram_addr = xe_vram_region_page_to_dpa(vr, spage); + if (vram_addr == XE_VRAM_ADDR_INVALID) { + vram_addr = __vram_addr; + pos = i; + } + + match = vram_addr + PAGE_SIZE * (i - pos) == __vram_addr; + } + + /* + * Mismatched physical address, 8M copy chunk, or last page - + * trigger a copy. + */ + if (!match || chunk || last) { + /* + * Extra page for first copy if last page and matching + * physical address. + */ + int incr = (match && last) ? 1 : 0; + + if (vram_addr != XE_VRAM_ADDR_INVALID) { + if (sram) { + vm_dbg(&tile->xe->drm, + "COPY TO SRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld", + vram_addr, (u64)dma_addr[pos], i - pos + incr); + __fence = xe_migrate_from_vram(tile->migrate, + i - pos + incr, + vram_addr, + dma_addr + pos); + } else { + vm_dbg(&tile->xe->drm, + "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld", + (u64)dma_addr[pos], vram_addr, i - pos + incr); + __fence = xe_migrate_to_vram(tile->migrate, + i - pos + incr, + dma_addr + pos, + vram_addr); + } + if (IS_ERR(__fence)) { + err = PTR_ERR(__fence); + goto err_out; + } + + dma_fence_put(fence); + fence = __fence; + } + + /* Setup physical address of next device page */ + if (dma_addr[i] && spage) { + vram_addr = __vram_addr; + pos = i; + } else { + vram_addr = XE_VRAM_ADDR_INVALID; + } + + /* Extra mismatched device page, copy it */ + if (!match && last && vram_addr != XE_VRAM_ADDR_INVALID) { + if (sram) { + vm_dbg(&tile->xe->drm, + "COPY TO SRAM - 0x%016llx -> 0x%016llx, NPAGES=%d", + vram_addr, (u64)dma_addr[pos], 1); + __fence = xe_migrate_from_vram(tile->migrate, 1, + vram_addr, + dma_addr + pos); + } else { + vm_dbg(&tile->xe->drm, + "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%d", + (u64)dma_addr[pos], vram_addr, 1); + __fence = xe_migrate_to_vram(tile->migrate, 1, + dma_addr + pos, + vram_addr); + } + if (IS_ERR(__fence)) { + err = PTR_ERR(__fence); + goto err_out; + } + + dma_fence_put(fence); + fence = __fence; + } + } + } + +err_out: + /* Wait for all copies to complete */ + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + + return err; +#undef XE_MIGRATE_CHUNK_SIZE +#undef XE_VRAM_ADDR_INVALID +} + +static int xe_svm_copy_to_devmem(struct page **pages, dma_addr_t *dma_addr, + unsigned long npages) +{ + return xe_svm_copy(pages, dma_addr, npages, XE_SVM_COPY_TO_VRAM); +} + +static int xe_svm_copy_to_ram(struct page **pages, dma_addr_t *dma_addr, + unsigned long npages) +{ + return xe_svm_copy(pages, dma_addr, npages, XE_SVM_COPY_TO_SRAM); +} + +static struct xe_bo *to_xe_bo(struct drm_gpusvm_devmem *devmem_allocation) +{ + return container_of(devmem_allocation, struct xe_bo, devmem_allocation); +} + +static void xe_svm_devmem_release(struct drm_gpusvm_devmem *devmem_allocation) +{ + struct xe_bo *bo = to_xe_bo(devmem_allocation); + + xe_bo_put_async(bo); +} + +static u64 block_offset_to_pfn(struct xe_vram_region *vr, u64 offset) +{ + return PHYS_PFN(offset + vr->hpa_base); +} + +static struct drm_buddy *tile_to_buddy(struct xe_tile *tile) +{ + return &tile->mem.vram.ttm.mm; +} + +static int xe_svm_populate_devmem_pfn(struct drm_gpusvm_devmem *devmem_allocation, + unsigned long npages, unsigned long *pfn) +{ + struct xe_bo *bo = to_xe_bo(devmem_allocation); + struct ttm_resource *res = bo->ttm.resource; + struct list_head *blocks = &to_xe_ttm_vram_mgr_resource(res)->blocks; + struct drm_buddy_block *block; + int j = 0; + + list_for_each_entry(block, blocks, link) { + struct xe_vram_region *vr = block->private; + struct xe_tile *tile = vr_to_tile(vr); + struct drm_buddy *buddy = tile_to_buddy(tile); + u64 block_pfn = block_offset_to_pfn(vr, drm_buddy_block_offset(block)); + int i; + + for (i = 0; i < drm_buddy_block_size(buddy, block) >> PAGE_SHIFT; ++i) + pfn[j++] = block_pfn + i; + } + + return 0; +} + +static const struct drm_gpusvm_devmem_ops gpusvm_devmem_ops = { + .devmem_release = xe_svm_devmem_release, + .populate_devmem_pfn = xe_svm_populate_devmem_pfn, + .copy_to_devmem = xe_svm_copy_to_devmem, + .copy_to_ram = xe_svm_copy_to_ram, +}; + +static const struct drm_gpusvm_ops gpusvm_ops = { + .range_alloc = xe_svm_range_alloc, + .range_free = xe_svm_range_free, + .invalidate = xe_svm_invalidate, +}; + +static const unsigned long fault_chunk_sizes[] = { + SZ_2M, + SZ_64K, + SZ_4K, +}; + +/** + * xe_svm_init() - SVM initialize + * @vm: The VM. + * + * Initialize SVM state which is embedded within the VM. + * + * Return: 0 on success, negative error code on error. + */ +int xe_svm_init(struct xe_vm *vm) +{ + int err; + + spin_lock_init(&vm->svm.garbage_collector.lock); + INIT_LIST_HEAD(&vm->svm.garbage_collector.range_list); + INIT_WORK(&vm->svm.garbage_collector.work, + xe_svm_garbage_collector_work_func); + + err = drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM", &vm->xe->drm, + current->mm, xe_svm_devm_owner(vm->xe), 0, + vm->size, xe_modparam.svm_notifier_size * SZ_1M, + &gpusvm_ops, fault_chunk_sizes, + ARRAY_SIZE(fault_chunk_sizes)); + if (err) + return err; + + drm_gpusvm_driver_set_lock(&vm->svm.gpusvm, &vm->lock); + + return 0; +} + +/** + * xe_svm_close() - SVM close + * @vm: The VM. + * + * Close SVM state (i.e., stop and flush all SVM actions). + */ +void xe_svm_close(struct xe_vm *vm) +{ + xe_assert(vm->xe, xe_vm_is_closed(vm)); + flush_work(&vm->svm.garbage_collector.work); +} + +/** + * xe_svm_fini() - SVM finalize + * @vm: The VM. + * + * Finalize SVM state which is embedded within the VM. + */ +void xe_svm_fini(struct xe_vm *vm) +{ + xe_assert(vm->xe, xe_vm_is_closed(vm)); + + drm_gpusvm_fini(&vm->svm.gpusvm); +} + +static bool xe_svm_range_is_valid(struct xe_svm_range *range, + struct xe_tile *tile) +{ + return (range->tile_present & ~range->tile_invalidated) & BIT(tile->id); +} + +static struct xe_vram_region *tile_to_vr(struct xe_tile *tile) +{ + return &tile->mem.vram; +} + +static int xe_svm_alloc_vram(struct xe_vm *vm, struct xe_tile *tile, + struct xe_svm_range *range, + const struct drm_gpusvm_ctx *ctx) +{ + struct mm_struct *mm = vm->svm.gpusvm.mm; + struct xe_vram_region *vr = tile_to_vr(tile); + struct drm_buddy_block *block; + struct list_head *blocks; + struct xe_bo *bo; + ktime_t end = 0; + int err; + + range_debug(range, "ALLOCATE VRAM"); + + if (!mmget_not_zero(mm)) + return -EFAULT; + mmap_read_lock(mm); + +retry: + bo = xe_bo_create_locked(tile_to_xe(tile), NULL, NULL, + xe_svm_range_size(range), + ttm_bo_type_device, + XE_BO_FLAG_VRAM_IF_DGFX(tile) | + XE_BO_FLAG_CPU_ADDR_MIRROR); + if (IS_ERR(bo)) { + err = PTR_ERR(bo); + if (xe_vm_validate_should_retry(NULL, err, &end)) + goto retry; + goto unlock; + } + + drm_gpusvm_devmem_init(&bo->devmem_allocation, + vm->xe->drm.dev, mm, + &gpusvm_devmem_ops, + &tile->mem.vram.dpagemap, + xe_svm_range_size(range)); + + blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)->blocks; + list_for_each_entry(block, blocks, link) + block->private = vr; + + err = drm_gpusvm_migrate_to_devmem(&vm->svm.gpusvm, &range->base, + &bo->devmem_allocation, ctx); + xe_bo_unlock(bo); + if (err) + xe_bo_put(bo); /* Creation ref */ + +unlock: + mmap_read_unlock(mm); + mmput(mm); + + return err; +} + +/** + * xe_svm_handle_pagefault() - SVM handle page fault + * @vm: The VM. + * @vma: The CPU address mirror VMA. + * @tile: The tile upon the fault occurred. + * @fault_addr: The GPU fault address. + * @atomic: The fault atomic access bit. + * + * Create GPU bindings for a SVM page fault. Optionally migrate to device + * memory. + * + * Return: 0 on success, negative error code on error. + */ +int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma, + struct xe_tile *tile, u64 fault_addr, + bool atomic) +{ + struct drm_gpusvm_ctx ctx = { + .read_only = xe_vma_read_only(vma), + .devmem_possible = IS_DGFX(vm->xe) && + IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR), + .check_pages_threshold = IS_DGFX(vm->xe) && + IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ? SZ_64K : 0, + }; + struct xe_svm_range *range; + struct drm_gpusvm_range *r; + struct drm_exec exec; + struct dma_fence *fence; + ktime_t end = 0; + int err; + + lockdep_assert_held_write(&vm->lock); + xe_assert(vm->xe, xe_vma_is_cpu_addr_mirror(vma)); + +retry: + /* Always process UNMAPs first so view SVM ranges is current */ + err = xe_svm_garbage_collector(vm); + if (err) + return err; + + r = drm_gpusvm_range_find_or_insert(&vm->svm.gpusvm, fault_addr, + xe_vma_start(vma), xe_vma_end(vma), + &ctx); + if (IS_ERR(r)) + return PTR_ERR(r); + + range = to_xe_range(r); + if (xe_svm_range_is_valid(range, tile)) + return 0; + + range_debug(range, "PAGE FAULT"); + + /* XXX: Add migration policy, for now migrate range once */ + if (!range->skip_migrate && range->base.flags.migrate_devmem && + xe_svm_range_size(range) >= SZ_64K) { + range->skip_migrate = true; + + err = xe_svm_alloc_vram(vm, tile, range, &ctx); + if (err) { + drm_dbg(&vm->xe->drm, + "VRAM allocation failed, falling back to " + "retrying fault, asid=%u, errno=%pe\n", + vm->usm.asid, ERR_PTR(err)); + goto retry; + } + } + + range_debug(range, "GET PAGES"); + err = drm_gpusvm_range_get_pages(&vm->svm.gpusvm, r, &ctx); + /* Corner where CPU mappings have changed */ + if (err == -EOPNOTSUPP || err == -EFAULT || err == -EPERM) { + if (err == -EOPNOTSUPP) { + range_debug(range, "PAGE FAULT - EVICT PAGES"); + drm_gpusvm_range_evict(&vm->svm.gpusvm, &range->base); + } + drm_dbg(&vm->xe->drm, + "Get pages failed, falling back to retrying, asid=%u, gpusvm=%p, errno=%pe\n", + vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err)); + range_debug(range, "PAGE FAULT - RETRY PAGES"); + goto retry; + } + if (err) { + range_debug(range, "PAGE FAULT - FAIL PAGE COLLECT"); + goto err_out; + } + + range_debug(range, "PAGE FAULT - BIND"); + +retry_bind: + drm_exec_init(&exec, 0, 0); + drm_exec_until_all_locked(&exec) { + err = drm_exec_lock_obj(&exec, vm->gpuvm.r_obj); + drm_exec_retry_on_contention(&exec); + if (err) { + drm_exec_fini(&exec); + goto err_out; + } + + fence = xe_vm_range_rebind(vm, vma, range, BIT(tile->id)); + if (IS_ERR(fence)) { + drm_exec_fini(&exec); + err = PTR_ERR(fence); + if (err == -EAGAIN) { + range_debug(range, "PAGE FAULT - RETRY BIND"); + goto retry; + } + if (xe_vm_validate_should_retry(&exec, err, &end)) + goto retry_bind; + goto err_out; + } + } + drm_exec_fini(&exec); + + if (xe_modparam.always_migrate_to_vram) + range->skip_migrate = false; + + dma_fence_wait(fence, false); + dma_fence_put(fence); + +err_out: + + return err; +} + +/** + * xe_svm_has_mapping() - SVM has mappings + * @vm: The VM. + * @start: Start address. + * @end: End address. + * + * Check if an address range has SVM mappings. + * + * Return: True if address range has a SVM mapping, False otherwise + */ +bool xe_svm_has_mapping(struct xe_vm *vm, u64 start, u64 end) +{ + return drm_gpusvm_has_mapping(&vm->svm.gpusvm, start, end); +} + +/** + * xe_svm_bo_evict() - SVM evict BO to system memory + * @bo: BO to evict + * + * SVM evict BO to system memory. GPU SVM layer ensures all device pages + * are evicted before returning. + * + * Return: 0 on success standard error code otherwise + */ +int xe_svm_bo_evict(struct xe_bo *bo) +{ + return drm_gpusvm_evict_to_ram(&bo->devmem_allocation); +} + +#if IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) +static struct drm_pagemap_device_addr +xe_drm_pagemap_device_map(struct drm_pagemap *dpagemap, + struct device *dev, + struct page *page, + unsigned int order, + enum dma_data_direction dir) +{ + struct device *pgmap_dev = dpagemap->dev; + enum drm_interconnect_protocol prot; + dma_addr_t addr; + + if (pgmap_dev == dev) { + addr = xe_vram_region_page_to_dpa(page_to_vr(page), page); + prot = XE_INTERCONNECT_VRAM; + } else { + addr = DMA_MAPPING_ERROR; + prot = 0; + } + + return drm_pagemap_device_addr_encode(addr, prot, order, dir); +} + +static const struct drm_pagemap_ops xe_drm_pagemap_ops = { + .device_map = xe_drm_pagemap_device_map, +}; + +/** + * xe_devm_add: Remap and provide memmap backing for device memory + * @tile: tile that the memory region belongs to + * @vr: vram memory region to remap + * + * This remap device memory to host physical address space and create + * struct page to back device memory + * + * Return: 0 on success standard error code otherwise + */ +int xe_devm_add(struct xe_tile *tile, struct xe_vram_region *vr) +{ + struct xe_device *xe = tile_to_xe(tile); + struct device *dev = &to_pci_dev(xe->drm.dev)->dev; + struct resource *res; + void *addr; + int ret; + + res = devm_request_free_mem_region(dev, &iomem_resource, + vr->usable_size); + if (IS_ERR(res)) { + ret = PTR_ERR(res); + return ret; + } + + vr->pagemap.type = MEMORY_DEVICE_PRIVATE; + vr->pagemap.range.start = res->start; + vr->pagemap.range.end = res->end; + vr->pagemap.nr_range = 1; + vr->pagemap.ops = drm_gpusvm_pagemap_ops_get(); + vr->pagemap.owner = xe_svm_devm_owner(xe); + addr = devm_memremap_pages(dev, &vr->pagemap); + + vr->dpagemap.dev = dev; + vr->dpagemap.ops = &xe_drm_pagemap_ops; + + if (IS_ERR(addr)) { + devm_release_mem_region(dev, res->start, resource_size(res)); + ret = PTR_ERR(addr); + drm_err(&xe->drm, "Failed to remap tile %d memory, errno %pe\n", + tile->id, ERR_PTR(ret)); + return ret; + } + vr->hpa_base = res->start; + + drm_dbg(&xe->drm, "Added tile %d memory [%llx-%llx] to devm, remapped to %pr\n", + tile->id, vr->io_start, vr->io_start + vr->usable_size, res); + return 0; +} +#else +int xe_devm_add(struct xe_tile *tile, struct xe_vram_region *vr) +{ + return 0; +} +#endif diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h new file mode 100644 index 000000000000..e059590e5076 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_svm.h @@ -0,0 +1,150 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2024 Intel Corporation + */ + +#ifndef _XE_SVM_H_ +#define _XE_SVM_H_ + +#include <drm/drm_pagemap.h> +#include <drm/drm_gpusvm.h> + +#define XE_INTERCONNECT_VRAM DRM_INTERCONNECT_DRIVER + +struct xe_bo; +struct xe_vram_region; +struct xe_tile; +struct xe_vm; +struct xe_vma; + +/** struct xe_svm_range - SVM range */ +struct xe_svm_range { + /** @base: base drm_gpusvm_range */ + struct drm_gpusvm_range base; + /** + * @garbage_collector_link: Link into VM's garbage collect SVM range + * list. Protected by VM's garbage collect lock. + */ + struct list_head garbage_collector_link; + /** + * @tile_present: Tile mask of binding is present for this range. + * Protected by GPU SVM notifier lock. + */ + u8 tile_present; + /** + * @tile_invalidated: Tile mask of binding is invalidated for this + * range. Protected by GPU SVM notifier lock. + */ + u8 tile_invalidated; + /** + * @skip_migrate: Skip migration to VRAM, protected by GPU fault handler + * locking. + */ + u8 skip_migrate :1; +}; + +#if IS_ENABLED(CONFIG_DRM_GPUSVM) +/** + * xe_svm_range_pages_valid() - SVM range pages valid + * @range: SVM range + * + * Return: True if SVM range pages are valid, False otherwise + */ +static inline bool xe_svm_range_pages_valid(struct xe_svm_range *range) +{ + return drm_gpusvm_range_pages_valid(range->base.gpusvm, &range->base); +} + +int xe_devm_add(struct xe_tile *tile, struct xe_vram_region *vr); + +int xe_svm_init(struct xe_vm *vm); + +void xe_svm_fini(struct xe_vm *vm); + +void xe_svm_close(struct xe_vm *vm); + +int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma, + struct xe_tile *tile, u64 fault_addr, + bool atomic); + +bool xe_svm_has_mapping(struct xe_vm *vm, u64 start, u64 end); + +int xe_svm_bo_evict(struct xe_bo *bo); + +void xe_svm_range_debug(struct xe_svm_range *range, const char *operation); +#else +static inline bool xe_svm_range_pages_valid(struct xe_svm_range *range) +{ + return false; +} + +static inline +int xe_devm_add(struct xe_tile *tile, struct xe_vram_region *vr) +{ + return 0; +} + +static inline +int xe_svm_init(struct xe_vm *vm) +{ + return 0; +} + +static inline +void xe_svm_fini(struct xe_vm *vm) +{ +} + +static inline +void xe_svm_close(struct xe_vm *vm) +{ +} + +static inline +int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma, + struct xe_tile *tile, u64 fault_addr, + bool atomic) +{ + return 0; +} + +static inline +bool xe_svm_has_mapping(struct xe_vm *vm, u64 start, u64 end) +{ + return false; +} + +static inline +int xe_svm_bo_evict(struct xe_bo *bo) +{ + return 0; +} + +static inline +void xe_svm_range_debug(struct xe_svm_range *range, const char *operation) +{ +} +#endif + +/** + * xe_svm_range_has_dma_mapping() - SVM range has DMA mapping + * @range: SVM range + * + * Return: True if SVM range has a DMA mapping, False otherwise + */ +static inline bool xe_svm_range_has_dma_mapping(struct xe_svm_range *range) +{ + lockdep_assert_held(&range->base.gpusvm->notifier_lock); + return range->base.flags.has_dma_mapping; +} + +#define xe_svm_assert_in_notifier(vm__) \ + lockdep_assert_held_write(&(vm__)->svm.gpusvm.notifier_lock) + +#define xe_svm_notifier_lock(vm__) \ + drm_gpusvm_notifier_lock(&(vm__)->svm.gpusvm) + +#define xe_svm_notifier_unlock(vm__) \ + drm_gpusvm_notifier_unlock(&(vm__)->svm.gpusvm) + +#endif diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c index d29658ff4dd4..0771acbbf367 100644 --- a/drivers/gpu/drm/xe/xe_tile.c +++ b/drivers/gpu/drm/xe/xe_tile.c @@ -13,6 +13,7 @@ #include "xe_migrate.h" #include "xe_pcode.h" #include "xe_sa.h" +#include "xe_svm.h" #include "xe_tile.h" #include "xe_tile_sysfs.h" #include "xe_ttm_vram_mgr.h" @@ -160,6 +161,7 @@ static int tile_ttm_mgr_init(struct xe_tile *tile) */ int xe_tile_init_noalloc(struct xe_tile *tile) { + struct xe_device *xe = tile_to_xe(tile); int err; err = tile_ttm_mgr_init(tile); @@ -168,6 +170,9 @@ int xe_tile_init_noalloc(struct xe_tile *tile) xe_wa_apply_tile_workarounds(tile); + if (xe->info.has_usm && IS_DGFX(xe)) + xe_devm_add(tile, &tile->mem.vram); + return xe_tile_sysfs_init(tile); } diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h index d5281de04d54..b4a3577df70c 100644 --- a/drivers/gpu/drm/xe/xe_trace.h +++ b/drivers/gpu/drm/xe/xe_trace.h @@ -427,6 +427,36 @@ DEFINE_EVENT(xe_pm_runtime, xe_pm_runtime_get_ioctl, TP_ARGS(xe, caller) ); +TRACE_EVENT(xe_eu_stall_data_read, + TP_PROTO(u8 slice, u8 subslice, + u32 read_ptr, u32 write_ptr, + size_t read_size, size_t total_size), + TP_ARGS(slice, subslice, + read_ptr, write_ptr, + read_size, total_size), + + TP_STRUCT__entry(__field(u8, slice) + __field(u8, subslice) + __field(u32, read_ptr) + __field(u32, write_ptr) + __field(size_t, read_size) + __field(size_t, total_size) + ), + + TP_fast_assign(__entry->slice = slice; + __entry->subslice = subslice; + __entry->read_ptr = read_ptr; + __entry->write_ptr = write_ptr; + __entry->read_size = read_size; + __entry->total_size = total_size; + ), + + TP_printk("slice: %u subslice: %u read ptr: 0x%x write ptr: 0x%x read size: %zu total read size: %zu", + __entry->slice, __entry->subslice, + __entry->read_ptr, __entry->write_ptr, + __entry->read_size, __entry->total_size) +); + #endif /* This part must be outside protection */ diff --git a/drivers/gpu/drm/xe/xe_trace_guc.h b/drivers/gpu/drm/xe/xe_trace_guc.h index 23abdd55dc62..78949db9cfce 100644 --- a/drivers/gpu/drm/xe/xe_trace_guc.h +++ b/drivers/gpu/drm/xe/xe_trace_guc.h @@ -14,6 +14,7 @@ #include "xe_device_types.h" #include "xe_guc_exec_queue_types.h" +#include "xe_guc_engine_activity_types.h" #define __dev_name_xe(xe) dev_name((xe)->drm.dev) @@ -100,6 +101,54 @@ DEFINE_EVENT_PRINT(xe_guc_ctb, xe_guc_ctb_g2h, ); +TRACE_EVENT(xe_guc_engine_activity, + TP_PROTO(struct xe_device *xe, struct engine_activity *ea, const char *name, + u16 instance), + TP_ARGS(xe, ea, name, instance), + + TP_STRUCT__entry( + __string(dev, __dev_name_xe(xe)) + __string(name, name) + __field(u32, global_change_num) + __field(u32, guc_tsc_frequency_hz) + __field(u32, lag_latency_usec) + __field(u16, instance) + __field(u16, change_num) + __field(u16, quanta_ratio) + __field(u32, last_update_tick) + __field(u64, active_ticks) + __field(u64, active) + __field(u64, total) + __field(u64, quanta) + __field(u64, last_cpu_ts) + ), + + TP_fast_assign( + __assign_str(dev); + __assign_str(name); + __entry->global_change_num = ea->metadata.global_change_num; + __entry->guc_tsc_frequency_hz = ea->metadata.guc_tsc_frequency_hz; + __entry->lag_latency_usec = ea->metadata.lag_latency_usec; + __entry->instance = instance; + __entry->change_num = ea->activity.change_num; + __entry->quanta_ratio = ea->activity.quanta_ratio; + __entry->last_update_tick = ea->activity.last_update_tick; + __entry->active_ticks = ea->activity.active_ticks; + __entry->active = ea->active; + __entry->total = ea->total; + __entry->quanta = ea->quanta; + __entry->last_cpu_ts = ea->last_cpu_ts; + ), + + TP_printk("dev=%s engine %s:%d Active=%llu, quanta=%llu, last_cpu_ts=%llu\n" + "Activity metadata: global_change_num=%u, guc_tsc_frequency_hz=%u lag_latency_usec=%u\n" + "Activity data: change_num=%u, quanta_ratio=0x%x, last_update_tick=%u, active_ticks=%llu\n", + __get_str(dev), __get_str(name), __entry->instance, + (__entry->active + __entry->total), __entry->quanta, __entry->last_cpu_ts, + __entry->global_change_num, __entry->guc_tsc_frequency_hz, + __entry->lag_latency_usec, __entry->change_num, __entry->quanta_ratio, + __entry->last_update_tick, __entry->active_ticks) +); #endif /* This part must be outside protection */ diff --git a/drivers/gpu/drm/xe/xe_tuning.c b/drivers/gpu/drm/xe/xe_tuning.c index d449de0fb6ec..49ddbda7cdef 100644 --- a/drivers/gpu/drm/xe/xe_tuning.c +++ b/drivers/gpu/drm/xe/xe_tuning.c @@ -7,6 +7,8 @@ #include <kunit/visibility.h> +#include <drm/drm_managed.h> + #include "regs/xe_gt_regs.h" #include "xe_gt_types.h" #include "xe_platform_types.h" @@ -83,28 +85,22 @@ static const struct xe_rtp_entry_sr gt_tunings[] = { XE_RTP_RULES(MEDIA_VERSION(2000)), XE_RTP_ACTIONS(SET(XE2LPM_SCRATCH3_LBCF, RWFLUSHALLEN)) }, - - {} }; static const struct xe_rtp_entry_sr engine_tunings[] = { + { XE_RTP_NAME("Tuning: L3 Hashing Mask"), + XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, 1210), + FUNC(xe_rtp_match_first_render_or_compute)), + XE_RTP_ACTIONS(CLR(XELP_GARBCNTL, XELP_BUS_HASH_CTL_BIT_EXC)) + }, { XE_RTP_NAME("Tuning: Set Indirect State Override"), XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, 1274), ENGINE_CLASS(RENDER)), XE_RTP_ACTIONS(SET(SAMPLER_MODE, INDIRECT_STATE_BASE_ADDR_OVERRIDE)) }, - {} }; static const struct xe_rtp_entry_sr lrc_tunings[] = { - { XE_RTP_NAME("Tuning: ganged timer, also known as 16011163337"), - XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, 1210), ENGINE_CLASS(RENDER)), - /* read verification is ignored due to 1608008084. */ - XE_RTP_ACTIONS(FIELD_SET_NO_READ_MASK(FF_MODE2, - FF_MODE2_GS_TIMER_MASK, - FF_MODE2_GS_TIMER_224)) - }, - /* DG2 */ { XE_RTP_NAME("Tuning: L3 cache"), @@ -139,15 +135,47 @@ static const struct xe_rtp_entry_sr lrc_tunings[] = { XE_RTP_ACTIONS(FIELD_SET(FF_MODE, VS_HIT_MAX_VALUE_MASK, REG_FIELD_PREP(VS_HIT_MAX_VALUE_MASK, 0x3f))) }, - - {} }; +/** + * xe_tuning_init - initialize gt with tunings bookkeeping + * @gt: GT instance to initialize + * + * Returns 0 for success, negative error code otherwise. + */ +int xe_tuning_init(struct xe_gt *gt) +{ + struct xe_device *xe = gt_to_xe(gt); + size_t n_lrc, n_engine, n_gt, total; + unsigned long *p; + + n_gt = BITS_TO_LONGS(ARRAY_SIZE(gt_tunings)); + n_engine = BITS_TO_LONGS(ARRAY_SIZE(engine_tunings)); + n_lrc = BITS_TO_LONGS(ARRAY_SIZE(lrc_tunings)); + total = n_gt + n_engine + n_lrc; + + p = drmm_kzalloc(&xe->drm, sizeof(*p) * total, GFP_KERNEL); + if (!p) + return -ENOMEM; + + gt->tuning_active.gt = p; + p += n_gt; + gt->tuning_active.engine = p; + p += n_engine; + gt->tuning_active.lrc = p; + + return 0; +} +ALLOW_ERROR_INJECTION(xe_tuning_init, ERRNO); /* See xe_pci_probe() */ + void xe_tuning_process_gt(struct xe_gt *gt) { struct xe_rtp_process_ctx ctx = XE_RTP_PROCESS_CTX_INITIALIZER(gt); - xe_rtp_process_to_sr(&ctx, gt_tunings, >->reg_sr); + xe_rtp_process_ctx_enable_active_tracking(&ctx, + gt->tuning_active.gt, + ARRAY_SIZE(gt_tunings)); + xe_rtp_process_to_sr(&ctx, gt_tunings, ARRAY_SIZE(gt_tunings), >->reg_sr); } EXPORT_SYMBOL_IF_KUNIT(xe_tuning_process_gt); @@ -155,7 +183,11 @@ void xe_tuning_process_engine(struct xe_hw_engine *hwe) { struct xe_rtp_process_ctx ctx = XE_RTP_PROCESS_CTX_INITIALIZER(hwe); - xe_rtp_process_to_sr(&ctx, engine_tunings, &hwe->reg_sr); + xe_rtp_process_ctx_enable_active_tracking(&ctx, + hwe->gt->tuning_active.engine, + ARRAY_SIZE(engine_tunings)); + xe_rtp_process_to_sr(&ctx, engine_tunings, ARRAY_SIZE(engine_tunings), + &hwe->reg_sr); } EXPORT_SYMBOL_IF_KUNIT(xe_tuning_process_engine); @@ -171,5 +203,25 @@ void xe_tuning_process_lrc(struct xe_hw_engine *hwe) { struct xe_rtp_process_ctx ctx = XE_RTP_PROCESS_CTX_INITIALIZER(hwe); - xe_rtp_process_to_sr(&ctx, lrc_tunings, &hwe->reg_lrc); + xe_rtp_process_ctx_enable_active_tracking(&ctx, + hwe->gt->tuning_active.lrc, + ARRAY_SIZE(lrc_tunings)); + xe_rtp_process_to_sr(&ctx, lrc_tunings, ARRAY_SIZE(lrc_tunings), &hwe->reg_lrc); +} + +void xe_tuning_dump(struct xe_gt *gt, struct drm_printer *p) +{ + size_t idx; + + drm_printf(p, "GT Tunings\n"); + for_each_set_bit(idx, gt->tuning_active.gt, ARRAY_SIZE(gt_tunings)) + drm_printf_indent(p, 1, "%s\n", gt_tunings[idx].name); + + drm_printf(p, "\nEngine Tunings\n"); + for_each_set_bit(idx, gt->tuning_active.engine, ARRAY_SIZE(engine_tunings)) + drm_printf_indent(p, 1, "%s\n", engine_tunings[idx].name); + + drm_printf(p, "\nLRC Tunings\n"); + for_each_set_bit(idx, gt->tuning_active.lrc, ARRAY_SIZE(lrc_tunings)) + drm_printf_indent(p, 1, "%s\n", lrc_tunings[idx].name); } diff --git a/drivers/gpu/drm/xe/xe_tuning.h b/drivers/gpu/drm/xe/xe_tuning.h index 4f9c3ac3b516..dd0d3ccc9c65 100644 --- a/drivers/gpu/drm/xe/xe_tuning.h +++ b/drivers/gpu/drm/xe/xe_tuning.h @@ -6,11 +6,14 @@ #ifndef _XE_TUNING_ #define _XE_TUNING_ +struct drm_printer; struct xe_gt; struct xe_hw_engine; +int xe_tuning_init(struct xe_gt *gt); void xe_tuning_process_gt(struct xe_gt *gt); void xe_tuning_process_engine(struct xe_hw_engine *hwe); void xe_tuning_process_lrc(struct xe_hw_engine *hwe); +void xe_tuning_dump(struct xe_gt *gt, struct drm_printer *p); #endif diff --git a/drivers/gpu/drm/xe/xe_uc.c b/drivers/gpu/drm/xe/xe_uc.c index d8167e818280..c14bd2282044 100644 --- a/drivers/gpu/drm/xe/xe_uc.c +++ b/drivers/gpu/drm/xe/xe_uc.c @@ -14,6 +14,7 @@ #include "xe_gt_sriov_vf.h" #include "xe_guc.h" #include "xe_guc_pc.h" +#include "xe_guc_engine_activity.h" #include "xe_huc.h" #include "xe_sriov.h" #include "xe_uc_fw.h" @@ -210,6 +211,8 @@ int xe_uc_init_hw(struct xe_uc *uc) if (ret) return ret; + xe_guc_engine_activity_enable_stats(&uc->guc); + /* We don't fail the driver load if HuC fails to auth, but let's warn */ ret = xe_huc_auth(&uc->huc, XE_HUC_AUTH_VIA_GUC); xe_gt_assert(uc_to_gt(uc), !ret); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index d664f2e418b2..22a26aff3a6e 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -8,6 +8,7 @@ #include <linux/dma-fence-array.h> #include <linux/nospec.h> +#include <drm/drm_drv.h> #include <drm/drm_exec.h> #include <drm/drm_print.h> #include <drm/ttm/ttm_tt.h> @@ -35,6 +36,7 @@ #include "xe_pt.h" #include "xe_pxp.h" #include "xe_res_cursor.h" +#include "xe_svm.h" #include "xe_sync.h" #include "xe_trace_bo.h" #include "xe_wa.h" @@ -270,6 +272,7 @@ out_up_write: return err; } +ALLOW_ERROR_INJECTION(xe_vm_add_compute_exec_queue, ERRNO); /** * xe_vm_remove_compute_exec_queue() - Remove compute exec queue from VM @@ -580,51 +583,26 @@ out_unlock_outer: trace_xe_vm_rebind_worker_exit(vm); } -static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni, - const struct mmu_notifier_range *range, - unsigned long cur_seq) +static void __vma_userptr_invalidate(struct xe_vm *vm, struct xe_userptr_vma *uvma) { - struct xe_userptr *userptr = container_of(mni, typeof(*userptr), notifier); - struct xe_userptr_vma *uvma = container_of(userptr, typeof(*uvma), userptr); + struct xe_userptr *userptr = &uvma->userptr; struct xe_vma *vma = &uvma->vma; - struct xe_vm *vm = xe_vma_vm(vma); struct dma_resv_iter cursor; struct dma_fence *fence; long err; - xe_assert(vm->xe, xe_vma_is_userptr(vma)); - trace_xe_vma_userptr_invalidate(vma); - - if (!mmu_notifier_range_blockable(range)) - return false; - - vm_dbg(&xe_vma_vm(vma)->xe->drm, - "NOTIFIER: addr=0x%016llx, range=0x%016llx", - xe_vma_start(vma), xe_vma_size(vma)); - - down_write(&vm->userptr.notifier_lock); - mmu_interval_set_seq(mni, cur_seq); - - /* No need to stop gpu access if the userptr is not yet bound. */ - if (!userptr->initial_bind) { - up_write(&vm->userptr.notifier_lock); - return true; - } - /* * Tell exec and rebind worker they need to repin and rebind this * userptr. */ if (!xe_vm_in_fault_mode(vm) && - !(vma->gpuva.flags & XE_VMA_DESTROYED) && vma->tile_present) { + !(vma->gpuva.flags & XE_VMA_DESTROYED)) { spin_lock(&vm->userptr.invalidated_lock); list_move_tail(&userptr->invalidate_link, &vm->userptr.invalidated); spin_unlock(&vm->userptr.invalidated_lock); } - up_write(&vm->userptr.notifier_lock); - /* * Preempt fences turn into schedule disables, pipeline these. * Note that even in fault mode, we need to wait for binds and @@ -642,11 +620,37 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni, false, MAX_SCHEDULE_TIMEOUT); XE_WARN_ON(err <= 0); - if (xe_vm_in_fault_mode(vm)) { + if (xe_vm_in_fault_mode(vm) && userptr->initial_bind) { err = xe_vm_invalidate_vma(vma); XE_WARN_ON(err); } + xe_hmm_userptr_unmap(uvma); +} + +static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *range, + unsigned long cur_seq) +{ + struct xe_userptr_vma *uvma = container_of(mni, typeof(*uvma), userptr.notifier); + struct xe_vma *vma = &uvma->vma; + struct xe_vm *vm = xe_vma_vm(vma); + + xe_assert(vm->xe, xe_vma_is_userptr(vma)); + trace_xe_vma_userptr_invalidate(vma); + + if (!mmu_notifier_range_blockable(range)) + return false; + + vm_dbg(&xe_vma_vm(vma)->xe->drm, + "NOTIFIER: addr=0x%016llx, range=0x%016llx", + xe_vma_start(vma), xe_vma_size(vma)); + + down_write(&vm->userptr.notifier_lock); + mmu_interval_set_seq(mni, cur_seq); + + __vma_userptr_invalidate(vm, uvma); + up_write(&vm->userptr.notifier_lock); trace_xe_vma_userptr_invalidate_complete(vma); return true; @@ -656,31 +660,71 @@ static const struct mmu_interval_notifier_ops vma_userptr_notifier_ops = { .invalidate = vma_userptr_invalidate, }; +#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT) +/** + * xe_vma_userptr_force_invalidate() - force invalidate a userptr + * @uvma: The userptr vma to invalidate + * + * Perform a forced userptr invalidation for testing purposes. + */ +void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma) +{ + struct xe_vm *vm = xe_vma_vm(&uvma->vma); + + /* Protect against concurrent userptr pinning */ + lockdep_assert_held(&vm->lock); + /* Protect against concurrent notifiers */ + lockdep_assert_held(&vm->userptr.notifier_lock); + /* + * Protect against concurrent instances of this function and + * the critical exec sections + */ + xe_vm_assert_held(vm); + + if (!mmu_interval_read_retry(&uvma->userptr.notifier, + uvma->userptr.notifier_seq)) + uvma->userptr.notifier_seq -= 2; + __vma_userptr_invalidate(vm, uvma); +} +#endif + int xe_vm_userptr_pin(struct xe_vm *vm) { struct xe_userptr_vma *uvma, *next; int err = 0; - LIST_HEAD(tmp_evict); xe_assert(vm->xe, !xe_vm_in_fault_mode(vm)); lockdep_assert_held_write(&vm->lock); /* Collect invalidated userptrs */ spin_lock(&vm->userptr.invalidated_lock); + xe_assert(vm->xe, list_empty(&vm->userptr.repin_list)); list_for_each_entry_safe(uvma, next, &vm->userptr.invalidated, userptr.invalidate_link) { list_del_init(&uvma->userptr.invalidate_link); - list_move_tail(&uvma->userptr.repin_link, - &vm->userptr.repin_list); + list_add_tail(&uvma->userptr.repin_link, + &vm->userptr.repin_list); } spin_unlock(&vm->userptr.invalidated_lock); - /* Pin and move to temporary list */ + /* Pin and move to bind list */ list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list, userptr.repin_link) { err = xe_vma_userptr_pin_pages(uvma); if (err == -EFAULT) { list_del_init(&uvma->userptr.repin_link); + /* + * We might have already done the pin once already, but + * then had to retry before the re-bind happened, due + * some other condition in the caller, but in the + * meantime the userptr got dinged by the notifier such + * that we need to revalidate here, but this time we hit + * the EFAULT. In such a case make sure we remove + * ourselves from the rebind list to avoid going down in + * flames. + */ + if (!list_empty(&uvma->vma.combined_links.rebind)) + list_del_init(&uvma->vma.combined_links.rebind); /* Wait for pending binds */ xe_vm_lock(vm, false); @@ -691,10 +735,10 @@ int xe_vm_userptr_pin(struct xe_vm *vm) err = xe_vm_invalidate_vma(&uvma->vma); xe_vm_unlock(vm); if (err) - return err; + break; } else { - if (err < 0) - return err; + if (err) + break; list_del_init(&uvma->userptr.repin_link); list_move_tail(&uvma->vma.combined_links.rebind, @@ -702,7 +746,19 @@ int xe_vm_userptr_pin(struct xe_vm *vm) } } - return 0; + if (err) { + down_write(&vm->userptr.notifier_lock); + spin_lock(&vm->userptr.invalidated_lock); + list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list, + userptr.repin_link) { + list_del_init(&uvma->userptr.repin_link); + list_move_tail(&uvma->userptr.invalidate_link, + &vm->userptr.invalidated); + } + spin_unlock(&vm->userptr.invalidated_lock); + up_write(&vm->userptr.notifier_lock); + } + return err; } /** @@ -894,6 +950,179 @@ free_ops: return fence; } +static void xe_vm_populate_range_rebind(struct xe_vma_op *op, + struct xe_vma *vma, + struct xe_svm_range *range, + u8 tile_mask) +{ + INIT_LIST_HEAD(&op->link); + op->tile_mask = tile_mask; + op->base.op = DRM_GPUVA_OP_DRIVER; + op->subop = XE_VMA_SUBOP_MAP_RANGE; + op->map_range.vma = vma; + op->map_range.range = range; +} + +static int +xe_vm_ops_add_range_rebind(struct xe_vma_ops *vops, + struct xe_vma *vma, + struct xe_svm_range *range, + u8 tile_mask) +{ + struct xe_vma_op *op; + + op = kzalloc(sizeof(*op), GFP_KERNEL); + if (!op) + return -ENOMEM; + + xe_vm_populate_range_rebind(op, vma, range, tile_mask); + list_add_tail(&op->link, &vops->list); + xe_vma_ops_incr_pt_update_ops(vops, tile_mask); + + return 0; +} + +/** + * xe_vm_range_rebind() - VM range (re)bind + * @vm: The VM which the range belongs to. + * @vma: The VMA which the range belongs to. + * @range: SVM range to rebind. + * @tile_mask: Tile mask to bind the range to. + * + * (re)bind SVM range setting up GPU page tables for the range. + * + * Return: dma fence for rebind to signal completion on succees, ERR_PTR on + * failure + */ +struct dma_fence *xe_vm_range_rebind(struct xe_vm *vm, + struct xe_vma *vma, + struct xe_svm_range *range, + u8 tile_mask) +{ + struct dma_fence *fence = NULL; + struct xe_vma_ops vops; + struct xe_vma_op *op, *next_op; + struct xe_tile *tile; + u8 id; + int err; + + lockdep_assert_held(&vm->lock); + xe_vm_assert_held(vm); + xe_assert(vm->xe, xe_vm_in_fault_mode(vm)); + xe_assert(vm->xe, xe_vma_is_cpu_addr_mirror(vma)); + + xe_vma_ops_init(&vops, vm, NULL, NULL, 0); + for_each_tile(tile, vm->xe, id) { + vops.pt_update_ops[id].wait_vm_bookkeep = true; + vops.pt_update_ops[tile->id].q = + xe_tile_migrate_exec_queue(tile); + } + + err = xe_vm_ops_add_range_rebind(&vops, vma, range, tile_mask); + if (err) + return ERR_PTR(err); + + err = xe_vma_ops_alloc(&vops, false); + if (err) { + fence = ERR_PTR(err); + goto free_ops; + } + + fence = ops_execute(vm, &vops); + +free_ops: + list_for_each_entry_safe(op, next_op, &vops.list, link) { + list_del(&op->link); + kfree(op); + } + xe_vma_ops_fini(&vops); + + return fence; +} + +static void xe_vm_populate_range_unbind(struct xe_vma_op *op, + struct xe_svm_range *range) +{ + INIT_LIST_HEAD(&op->link); + op->tile_mask = range->tile_present; + op->base.op = DRM_GPUVA_OP_DRIVER; + op->subop = XE_VMA_SUBOP_UNMAP_RANGE; + op->unmap_range.range = range; +} + +static int +xe_vm_ops_add_range_unbind(struct xe_vma_ops *vops, + struct xe_svm_range *range) +{ + struct xe_vma_op *op; + + op = kzalloc(sizeof(*op), GFP_KERNEL); + if (!op) + return -ENOMEM; + + xe_vm_populate_range_unbind(op, range); + list_add_tail(&op->link, &vops->list); + xe_vma_ops_incr_pt_update_ops(vops, range->tile_present); + + return 0; +} + +/** + * xe_vm_range_unbind() - VM range unbind + * @vm: The VM which the range belongs to. + * @range: SVM range to rebind. + * + * Unbind SVM range removing the GPU page tables for the range. + * + * Return: dma fence for unbind to signal completion on succees, ERR_PTR on + * failure + */ +struct dma_fence *xe_vm_range_unbind(struct xe_vm *vm, + struct xe_svm_range *range) +{ + struct dma_fence *fence = NULL; + struct xe_vma_ops vops; + struct xe_vma_op *op, *next_op; + struct xe_tile *tile; + u8 id; + int err; + + lockdep_assert_held(&vm->lock); + xe_vm_assert_held(vm); + xe_assert(vm->xe, xe_vm_in_fault_mode(vm)); + + if (!range->tile_present) + return dma_fence_get_stub(); + + xe_vma_ops_init(&vops, vm, NULL, NULL, 0); + for_each_tile(tile, vm->xe, id) { + vops.pt_update_ops[id].wait_vm_bookkeep = true; + vops.pt_update_ops[tile->id].q = + xe_tile_migrate_exec_queue(tile); + } + + err = xe_vm_ops_add_range_unbind(&vops, range); + if (err) + return ERR_PTR(err); + + err = xe_vma_ops_alloc(&vops, false); + if (err) { + fence = ERR_PTR(err); + goto free_ops; + } + + fence = ops_execute(vm, &vops); + +free_ops: + list_for_each_entry_safe(op, next_op, &vops.list, link) { + list_del(&op->link); + kfree(op); + } + xe_vma_ops_fini(&vops); + + return fence; +} + static void xe_vma_free(struct xe_vma *vma) { if (xe_vma_is_userptr(vma)) @@ -902,9 +1131,10 @@ static void xe_vma_free(struct xe_vma *vma) kfree(vma); } -#define VMA_CREATE_FLAG_READ_ONLY BIT(0) -#define VMA_CREATE_FLAG_IS_NULL BIT(1) -#define VMA_CREATE_FLAG_DUMPABLE BIT(2) +#define VMA_CREATE_FLAG_READ_ONLY BIT(0) +#define VMA_CREATE_FLAG_IS_NULL BIT(1) +#define VMA_CREATE_FLAG_DUMPABLE BIT(2) +#define VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR BIT(3) static struct xe_vma *xe_vma_create(struct xe_vm *vm, struct xe_bo *bo, @@ -918,6 +1148,8 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm, bool read_only = (flags & VMA_CREATE_FLAG_READ_ONLY); bool is_null = (flags & VMA_CREATE_FLAG_IS_NULL); bool dumpable = (flags & VMA_CREATE_FLAG_DUMPABLE); + bool is_cpu_addr_mirror = + (flags & VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR); xe_assert(vm->xe, start < end); xe_assert(vm->xe, end < vm->size); @@ -926,7 +1158,7 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm, * Allocate and ensure that the xe_vma_is_userptr() return * matches what was allocated. */ - if (!bo && !is_null) { + if (!bo && !is_null && !is_cpu_addr_mirror) { struct xe_userptr_vma *uvma = kzalloc(sizeof(*uvma), GFP_KERNEL); if (!uvma) @@ -938,6 +1170,8 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm, if (!vma) return ERR_PTR(-ENOMEM); + if (is_cpu_addr_mirror) + vma->gpuva.flags |= XE_VMA_SYSTEM_ALLOCATOR; if (is_null) vma->gpuva.flags |= DRM_GPUVA_SPARSE; if (bo) @@ -980,7 +1214,7 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm, drm_gpuva_link(&vma->gpuva, vm_bo); drm_gpuvm_bo_put(vm_bo); } else /* userptr or null */ { - if (!is_null) { + if (!is_null && !is_cpu_addr_mirror) { struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr; u64 size = end - start + 1; int err; @@ -988,6 +1222,7 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm, INIT_LIST_HEAD(&userptr->invalidate_link); INIT_LIST_HEAD(&userptr->repin_link); vma->gpuva.gem.offset = bo_offset_or_userptr; + mutex_init(&userptr->unmap_mutex); err = mmu_interval_notifier_insert(&userptr->notifier, current->mm, @@ -1029,8 +1264,9 @@ static void xe_vma_destroy_late(struct xe_vma *vma) * them anymore */ mmu_interval_notifier_remove(&userptr->notifier); + mutex_destroy(&userptr->unmap_mutex); xe_vm_put(vm); - } else if (xe_vma_is_null(vma)) { + } else if (xe_vma_is_null(vma) || xe_vma_is_cpu_addr_mirror(vma)) { xe_vm_put(vm); } else { xe_bo_put(xe_vma_bo(vma)); @@ -1067,9 +1303,10 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence) xe_assert(vm->xe, vma->gpuva.flags & XE_VMA_DESTROYED); spin_lock(&vm->userptr.invalidated_lock); + xe_assert(vm->xe, list_empty(&to_userptr_vma(vma)->userptr.repin_link)); list_del(&to_userptr_vma(vma)->userptr.invalidate_link); spin_unlock(&vm->userptr.invalidated_lock); - } else if (!xe_vma_is_null(vma)) { + } else if (!xe_vma_is_null(vma) && !xe_vma_is_cpu_addr_mirror(vma)) { xe_bo_assert_held(xe_vma_bo(vma)); drm_gpuva_unlink(&vma->gpuva); @@ -1520,6 +1757,12 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) } } + if (flags & XE_VM_FLAG_FAULT_MODE) { + err = xe_svm_init(vm); + if (err) + goto err_close; + } + if (number_tiles > 1) vm->composite_fence_ctx = dma_fence_context_alloc(1); @@ -1546,9 +1789,44 @@ err_no_resv: static void xe_vm_close(struct xe_vm *vm) { + struct xe_device *xe = vm->xe; + bool bound; + int idx; + + bound = drm_dev_enter(&xe->drm, &idx); + down_write(&vm->lock); + if (xe_vm_in_fault_mode(vm)) + xe_svm_notifier_lock(vm); + vm->size = 0; + + if (!((vm->flags & XE_VM_FLAG_MIGRATION))) { + struct xe_tile *tile; + struct xe_gt *gt; + u8 id; + + /* Wait for pending binds */ + dma_resv_wait_timeout(xe_vm_resv(vm), + DMA_RESV_USAGE_BOOKKEEP, + false, MAX_SCHEDULE_TIMEOUT); + + if (bound) { + for_each_tile(tile, xe, id) + if (vm->pt_root[id]) + xe_pt_clear(xe, vm->pt_root[id]); + + for_each_gt(gt, xe, id) + xe_gt_tlb_invalidation_vm(gt, vm); + } + } + + if (xe_vm_in_fault_mode(vm)) + xe_svm_notifier_unlock(vm); up_write(&vm->lock); + + if (bound) + drm_dev_exit(idx); } void xe_vm_close_and_put(struct xe_vm *vm) @@ -1565,6 +1843,8 @@ void xe_vm_close_and_put(struct xe_vm *vm) xe_vm_close(vm); if (xe_vm_in_preempt_fence_mode(vm)) flush_work(&vm->preempt.rebind_work); + if (xe_vm_in_fault_mode(vm)) + xe_svm_close(vm); down_write(&vm->lock); for_each_tile(tile, xe, id) { @@ -1633,6 +1913,9 @@ void xe_vm_close_and_put(struct xe_vm *vm) xe_vma_destroy_unlocked(vma); } + if (xe_vm_in_fault_mode(vm)) + xe_svm_fini(vm); + up_write(&vm->lock); down_write(&xe->usm.lock); @@ -1989,6 +2272,8 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo, op->map.read_only = flags & DRM_XE_VM_BIND_FLAG_READONLY; op->map.is_null = flags & DRM_XE_VM_BIND_FLAG_NULL; + op->map.is_cpu_addr_mirror = flags & + DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR; op->map.dumpable = flags & DRM_XE_VM_BIND_FLAG_DUMPABLE; op->map.pat_index = pat_index; } else if (__op->op == DRM_GPUVA_OP_PREFETCH) { @@ -2181,6 +2466,8 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops, VMA_CREATE_FLAG_IS_NULL : 0; flags |= op->map.dumpable ? VMA_CREATE_FLAG_DUMPABLE : 0; + flags |= op->map.is_cpu_addr_mirror ? + VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR : 0; vma = new_vma(vm, &op->base.map, op->map.pat_index, flags); @@ -2188,7 +2475,8 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops, return PTR_ERR(vma); op->map.vma = vma; - if (op->map.immediate || !xe_vm_in_fault_mode(vm)) + if ((op->map.immediate || !xe_vm_in_fault_mode(vm)) && + !op->map.is_cpu_addr_mirror) xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask); break; @@ -2197,21 +2485,35 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops, { struct xe_vma *old = gpuva_to_vma(op->base.remap.unmap->va); + bool skip = xe_vma_is_cpu_addr_mirror(old); + u64 start = xe_vma_start(old), end = xe_vma_end(old); + + if (op->base.remap.prev) + start = op->base.remap.prev->va.addr + + op->base.remap.prev->va.range; + if (op->base.remap.next) + end = op->base.remap.next->va.addr; + + if (xe_vma_is_cpu_addr_mirror(old) && + xe_svm_has_mapping(vm, start, end)) + return -EBUSY; op->remap.start = xe_vma_start(old); op->remap.range = xe_vma_size(old); - if (op->base.remap.prev) { - flags |= op->base.remap.unmap->va->flags & - XE_VMA_READ_ONLY ? - VMA_CREATE_FLAG_READ_ONLY : 0; - flags |= op->base.remap.unmap->va->flags & - DRM_GPUVA_SPARSE ? - VMA_CREATE_FLAG_IS_NULL : 0; - flags |= op->base.remap.unmap->va->flags & - XE_VMA_DUMPABLE ? - VMA_CREATE_FLAG_DUMPABLE : 0; + flags |= op->base.remap.unmap->va->flags & + XE_VMA_READ_ONLY ? + VMA_CREATE_FLAG_READ_ONLY : 0; + flags |= op->base.remap.unmap->va->flags & + DRM_GPUVA_SPARSE ? + VMA_CREATE_FLAG_IS_NULL : 0; + flags |= op->base.remap.unmap->va->flags & + XE_VMA_DUMPABLE ? + VMA_CREATE_FLAG_DUMPABLE : 0; + flags |= xe_vma_is_cpu_addr_mirror(old) ? + VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR : 0; + if (op->base.remap.prev) { vma = new_vma(vm, op->base.remap.prev, old->pat_index, flags); if (IS_ERR(vma)) @@ -2223,9 +2525,10 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops, * Userptr creates a new SG mapping so * we must also rebind. */ - op->remap.skip_prev = !xe_vma_is_userptr(old) && + op->remap.skip_prev = skip || + (!xe_vma_is_userptr(old) && IS_ALIGNED(xe_vma_end(vma), - xe_vma_max_pte_size(old)); + xe_vma_max_pte_size(old))); if (op->remap.skip_prev) { xe_vma_set_pte_size(vma, xe_vma_max_pte_size(old)); op->remap.range -= @@ -2241,16 +2544,6 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops, } if (op->base.remap.next) { - flags |= op->base.remap.unmap->va->flags & - XE_VMA_READ_ONLY ? - VMA_CREATE_FLAG_READ_ONLY : 0; - flags |= op->base.remap.unmap->va->flags & - DRM_GPUVA_SPARSE ? - VMA_CREATE_FLAG_IS_NULL : 0; - flags |= op->base.remap.unmap->va->flags & - XE_VMA_DUMPABLE ? - VMA_CREATE_FLAG_DUMPABLE : 0; - vma = new_vma(vm, op->base.remap.next, old->pat_index, flags); if (IS_ERR(vma)) @@ -2262,9 +2555,10 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops, * Userptr creates a new SG mapping so * we must also rebind. */ - op->remap.skip_next = !xe_vma_is_userptr(old) && + op->remap.skip_next = skip || + (!xe_vma_is_userptr(old) && IS_ALIGNED(xe_vma_start(vma), - xe_vma_max_pte_size(old)); + xe_vma_max_pte_size(old))); if (op->remap.skip_next) { xe_vma_set_pte_size(vma, xe_vma_max_pte_size(old)); op->remap.range -= @@ -2277,13 +2571,32 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops, xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask); } } - xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask); + if (!skip) + xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask); break; } case DRM_GPUVA_OP_UNMAP: + vma = gpuva_to_vma(op->base.unmap.va); + + if (xe_vma_is_cpu_addr_mirror(vma) && + xe_svm_has_mapping(vm, xe_vma_start(vma), + xe_vma_end(vma))) + return -EBUSY; + + if (!xe_vma_is_cpu_addr_mirror(vma)) + xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask); + break; case DRM_GPUVA_OP_PREFETCH: - /* FIXME: Need to skip some prefetch ops */ - xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask); + vma = gpuva_to_vma(op->base.prefetch.va); + + if (xe_vma_is_userptr(vma)) { + err = xe_vma_userptr_pin_pages(to_userptr_vma(vma)); + if (err) + return err; + } + + if (!xe_vma_is_cpu_addr_mirror(vma)) + xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask); break; default: drm_warn(&vm->xe->drm, "NOT POSSIBLE"); @@ -2509,6 +2822,8 @@ static void op_trace(struct xe_vma_op *op) case DRM_GPUVA_OP_PREFETCH: trace_xe_vma_bind(gpuva_to_vma(op->base.prefetch.va)); break; + case DRM_GPUVA_OP_DRIVER: + break; default: XE_WARN_ON("NOT POSSIBLE"); } @@ -2686,9 +3001,11 @@ static void vm_bind_ioctl_ops_fini(struct xe_vm *vm, struct xe_vma_ops *vops, } if (ufence) xe_sync_ufence_put(ufence); - for (i = 0; i < vops->num_syncs; i++) - xe_sync_entry_signal(vops->syncs + i, fence); - xe_exec_queue_last_fence_set(wait_exec_queue, vm, fence); + if (fence) { + for (i = 0; i < vops->num_syncs; i++) + xe_sync_entry_signal(vops->syncs + i, fence); + xe_exec_queue_last_fence_set(wait_exec_queue, vm, fence); + } } static struct dma_fence *vm_bind_ioctl_ops_execute(struct xe_vm *vm, @@ -2711,8 +3028,11 @@ static struct dma_fence *vm_bind_ioctl_ops_execute(struct xe_vm *vm, } fence = ops_execute(vm, vops); - if (IS_ERR(fence)) + if (IS_ERR(fence)) { + if (PTR_ERR(fence) == -ENODATA) + vm_bind_ioctl_ops_fini(vm, vops, NULL); goto unlock; + } vm_bind_ioctl_ops_fini(vm, vops, fence); } @@ -2728,7 +3048,8 @@ ALLOW_ERROR_INJECTION(vm_bind_ioctl_ops_execute, ERRNO); DRM_XE_VM_BIND_FLAG_IMMEDIATE | \ DRM_XE_VM_BIND_FLAG_NULL | \ DRM_XE_VM_BIND_FLAG_DUMPABLE | \ - DRM_XE_VM_BIND_FLAG_CHECK_PXP) + DRM_XE_VM_BIND_FLAG_CHECK_PXP | \ + DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR) #ifdef TEST_VM_OPS_ERROR #define SUPPORTED_FLAGS (SUPPORTED_FLAGS_STUB | FORCE_OP_ERROR) @@ -2739,7 +3060,7 @@ ALLOW_ERROR_INJECTION(vm_bind_ioctl_ops_execute, ERRNO); #define XE_64K_PAGE_MASK 0xffffull #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP) -static int vm_bind_ioctl_check_args(struct xe_device *xe, +static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm, struct drm_xe_vm_bind *args, struct drm_xe_vm_bind_op **bind_ops) { @@ -2784,9 +3105,18 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, u64 obj_offset = (*bind_ops)[i].obj_offset; u32 prefetch_region = (*bind_ops)[i].prefetch_mem_region_instance; bool is_null = flags & DRM_XE_VM_BIND_FLAG_NULL; + bool is_cpu_addr_mirror = flags & + DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR; u16 pat_index = (*bind_ops)[i].pat_index; u16 coh_mode; + if (XE_IOCTL_DBG(xe, is_cpu_addr_mirror && + (!xe_vm_in_fault_mode(vm) || + !IS_ENABLED(CONFIG_DRM_GPUSVM)))) { + err = -EINVAL; + goto free_bind_ops; + } + if (XE_IOCTL_DBG(xe, pat_index >= xe->pat.n_entries)) { err = -EINVAL; goto free_bind_ops; @@ -2807,13 +3137,14 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, if (XE_IOCTL_DBG(xe, op > DRM_XE_VM_BIND_OP_PREFETCH) || XE_IOCTL_DBG(xe, flags & ~SUPPORTED_FLAGS) || - XE_IOCTL_DBG(xe, obj && is_null) || - XE_IOCTL_DBG(xe, obj_offset && is_null) || + XE_IOCTL_DBG(xe, obj && (is_null || is_cpu_addr_mirror)) || + XE_IOCTL_DBG(xe, obj_offset && (is_null || + is_cpu_addr_mirror)) || XE_IOCTL_DBG(xe, op != DRM_XE_VM_BIND_OP_MAP && - is_null) || + (is_null || is_cpu_addr_mirror)) || XE_IOCTL_DBG(xe, !obj && op == DRM_XE_VM_BIND_OP_MAP && - !is_null) || + !is_null && !is_cpu_addr_mirror) || XE_IOCTL_DBG(xe, !obj && op == DRM_XE_VM_BIND_OP_UNMAP_ALL) || XE_IOCTL_DBG(xe, addr && @@ -2962,15 +3293,19 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) int err; int i; - err = vm_bind_ioctl_check_args(xe, args, &bind_ops); + vm = xe_vm_lookup(xef, args->vm_id); + if (XE_IOCTL_DBG(xe, !vm)) + return -EINVAL; + + err = vm_bind_ioctl_check_args(xe, vm, args, &bind_ops); if (err) - return err; + goto put_vm; if (args->exec_queue_id) { q = xe_exec_queue_lookup(xef, args->exec_queue_id); if (XE_IOCTL_DBG(xe, !q)) { err = -ENOENT; - goto free_objs; + goto put_vm; } if (XE_IOCTL_DBG(xe, !(q->flags & EXEC_QUEUE_FLAG_VM))) { @@ -2979,15 +3314,13 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) } } - vm = xe_vm_lookup(xef, args->vm_id); - if (XE_IOCTL_DBG(xe, !vm)) { - err = -EINVAL; - goto put_exec_queue; - } + /* Ensure all UNMAPs visible */ + if (xe_vm_in_fault_mode(vm)) + flush_work(&vm->svm.garbage_collector.work); err = down_write_killable(&vm->lock); if (err) - goto put_vm; + goto put_exec_queue; if (XE_IOCTL_DBG(xe, xe_vm_is_closed_or_banned(vm))) { err = -ENOENT; @@ -3151,12 +3484,11 @@ put_obj: xe_bo_put(bos[i]); release_vm_lock: up_write(&vm->lock); -put_vm: - xe_vm_put(vm); put_exec_queue: if (q) xe_exec_queue_put(q); -free_objs: +put_vm: + xe_vm_put(vm); kvfree(bos); kvfree(ops); if (args->num_binds > 1) @@ -3288,6 +3620,7 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) int ret = 0; xe_assert(xe, !xe_vma_is_null(vma)); + xe_assert(xe, !xe_vma_is_cpu_addr_mirror(vma)); trace_xe_vma_invalidate(vma); vm_dbg(&xe_vma_vm(vma)->xe->drm, diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index f66075f8a6fe..0ef811fc2bde 100644 --- a/drivers/gpu/drm/xe/xe_vm.h +++ b/drivers/gpu/drm/xe/xe_vm.h @@ -23,6 +23,7 @@ struct dma_fence; struct xe_exec_queue; struct xe_file; struct xe_sync_entry; +struct xe_svm_range; struct drm_exec; struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags); @@ -152,6 +153,11 @@ static inline bool xe_vma_is_null(struct xe_vma *vma) return vma->gpuva.flags & DRM_GPUVA_SPARSE; } +static inline bool xe_vma_is_cpu_addr_mirror(struct xe_vma *vma) +{ + return vma->gpuva.flags & XE_VMA_SYSTEM_ALLOCATOR; +} + static inline bool xe_vma_has_no_bo(struct xe_vma *vma) { return !xe_vma_bo(vma); @@ -159,7 +165,8 @@ static inline bool xe_vma_has_no_bo(struct xe_vma *vma) static inline bool xe_vma_is_userptr(struct xe_vma *vma) { - return xe_vma_has_no_bo(vma) && !xe_vma_is_null(vma); + return xe_vma_has_no_bo(vma) && !xe_vma_is_null(vma) && + !xe_vma_is_cpu_addr_mirror(vma); } /** @@ -212,6 +219,12 @@ int xe_vm_userptr_check_repin(struct xe_vm *vm); int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker); struct dma_fence *xe_vma_rebind(struct xe_vm *vm, struct xe_vma *vma, u8 tile_mask); +struct dma_fence *xe_vm_range_rebind(struct xe_vm *vm, + struct xe_vma *vma, + struct xe_svm_range *range, + u8 tile_mask); +struct dma_fence *xe_vm_range_unbind(struct xe_vm *vm, + struct xe_svm_range *range); int xe_vm_invalidate_vma(struct xe_vma *vma); @@ -282,9 +295,17 @@ static inline void vm_dbg(const struct drm_device *dev, const char *format, ...) { /* noop */ } #endif -#endif struct xe_vm_snapshot *xe_vm_snapshot_capture(struct xe_vm *vm); void xe_vm_snapshot_capture_delayed(struct xe_vm_snapshot *snap); void xe_vm_snapshot_print(struct xe_vm_snapshot *snap, struct drm_printer *p); void xe_vm_snapshot_free(struct xe_vm_snapshot *snap); + +#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT) +void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma); +#else +static inline void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma) +{ +} +#endif +#endif diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index 52467b9b5348..84fa41b9fa20 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -6,6 +6,7 @@ #ifndef _XE_VM_TYPES_H_ #define _XE_VM_TYPES_H_ +#include <drm/drm_gpusvm.h> #include <drm/drm_gpuvm.h> #include <linux/dma-resv.h> @@ -18,6 +19,7 @@ #include "xe_range_fence.h" struct xe_bo; +struct xe_svm_range; struct xe_sync_entry; struct xe_user_fence; struct xe_vm; @@ -42,6 +44,7 @@ struct xe_vm_pgtable_update_op; #define XE_VMA_PTE_64K (DRM_GPUVA_USERBITS << 6) #define XE_VMA_PTE_COMPACT (DRM_GPUVA_USERBITS << 7) #define XE_VMA_DUMPABLE (DRM_GPUVA_USERBITS << 8) +#define XE_VMA_SYSTEM_ALLOCATOR (DRM_GPUVA_USERBITS << 9) /** struct xe_userptr - User pointer */ struct xe_userptr { @@ -59,12 +62,16 @@ struct xe_userptr { struct sg_table *sg; /** @notifier_seq: notifier sequence number */ unsigned long notifier_seq; + /** @unmap_mutex: Mutex protecting dma-unmapping */ + struct mutex unmap_mutex; /** * @initial_bind: user pointer has been bound at least once. * write: vm->userptr.notifier_lock in read mode and vm->resv held. * read: vm->userptr.notifier_lock in write mode or vm->resv held. */ bool initial_bind; + /** @mapped: Whether the @sgt sg-table is dma-mapped. Protected by @unmap_mutex. */ + bool mapped; #if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT) u32 divisor; #endif @@ -139,6 +146,30 @@ struct xe_vm { /** @gpuvm: base GPUVM used to track VMAs */ struct drm_gpuvm gpuvm; + /** @svm: Shared virtual memory state */ + struct { + /** @svm.gpusvm: base GPUSVM used to track fault allocations */ + struct drm_gpusvm gpusvm; + /** + * @svm.garbage_collector: Garbage collector which is used unmap + * SVM range's GPU bindings and destroy the ranges. + */ + struct { + /** @svm.garbage_collector.lock: Protect's range list */ + spinlock_t lock; + /** + * @svm.garbage_collector.range_list: List of SVM ranges + * in the garbage collector. + */ + struct list_head range_list; + /** + * @svm.garbage_collector.work: Worker which the + * garbage collector runs on. + */ + struct work_struct work; + } garbage_collector; + } svm; + struct xe_device *xe; /* exec queue used for (un)binding vma's */ @@ -228,8 +259,8 @@ struct xe_vm { * up for revalidation. Protected from access with the * @invalidated_lock. Removing items from the list * additionally requires @lock in write mode, and adding - * items to the list requires the @userptr.notifer_lock in - * write mode. + * items to the list requires either the @userptr.notifer_lock in + * write mode, OR @lock in write mode. */ struct list_head invalidated; } userptr; @@ -295,6 +326,8 @@ struct xe_vma_op_map { bool read_only; /** @is_null: is NULL binding */ bool is_null; + /** @is_cpu_addr_mirror: is CPU address mirror binding */ + bool is_cpu_addr_mirror; /** @dumpable: whether BO is dumped on GPU hang */ bool dumpable; /** @pat_index: The pat index to use for this operation. */ @@ -325,6 +358,20 @@ struct xe_vma_op_prefetch { u32 region; }; +/** struct xe_vma_op_map_range - VMA map range operation */ +struct xe_vma_op_map_range { + /** @vma: VMA to map (system allocator VMA) */ + struct xe_vma *vma; + /** @range: SVM range to map */ + struct xe_svm_range *range; +}; + +/** struct xe_vma_op_unmap_range - VMA unmap range operation */ +struct xe_vma_op_unmap_range { + /** @range: SVM range to unmap */ + struct xe_svm_range *range; +}; + /** enum xe_vma_op_flags - flags for VMA operation */ enum xe_vma_op_flags { /** @XE_VMA_OP_COMMITTED: VMA operation committed */ @@ -335,6 +382,14 @@ enum xe_vma_op_flags { XE_VMA_OP_NEXT_COMMITTED = BIT(2), }; +/** enum xe_vma_subop - VMA sub-operation */ +enum xe_vma_subop { + /** @XE_VMA_SUBOP_MAP_RANGE: Map range */ + XE_VMA_SUBOP_MAP_RANGE, + /** @XE_VMA_SUBOP_UNMAP_RANGE: Unmap range */ + XE_VMA_SUBOP_UNMAP_RANGE, +}; + /** struct xe_vma_op - VMA operation */ struct xe_vma_op { /** @base: GPUVA base operation */ @@ -343,6 +398,8 @@ struct xe_vma_op { struct list_head link; /** @flags: operation flags */ enum xe_vma_op_flags flags; + /** @subop: user defined sub-operation */ + enum xe_vma_subop subop; /** @tile_mask: Tile mask for operation */ u8 tile_mask; @@ -353,6 +410,10 @@ struct xe_vma_op { struct xe_vma_op_remap remap; /** @prefetch: VMA prefetch operation specific data */ struct xe_vma_op_prefetch prefetch; + /** @map_range: VMA map range operation specific data */ + struct xe_vma_op_map_range map_range; + /** @unmap_range: VMA unmap range operation specific data */ + struct xe_vma_op_unmap_range unmap_range; }; }; diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index d4982799383c..a25afb757f70 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -279,8 +279,6 @@ static const struct xe_rtp_entry_sr gt_was[] = { XE_RTP_ACTIONS(SET(VDBOX_CGCTL3F10(0), RAMDFTUNIT_CLKGATE_DIS)), XE_RTP_ENTRY_FLAG(FOREACH_ENGINE), }, - - {} }; static const struct xe_rtp_entry_sr engine_was[] = { @@ -619,11 +617,28 @@ static const struct xe_rtp_entry_sr engine_was[] = { FUNC(xe_rtp_match_first_render_or_compute)), XE_RTP_ACTIONS(SET(TDL_CHICKEN, QID_WAIT_FOR_THREAD_NOT_RUN_DISABLE)) }, - - {} + { XE_RTP_NAME("13012615864"), + XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3001), + FUNC(xe_rtp_match_first_render_or_compute)), + XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, RES_CHK_SPR_DIS)) + }, }; static const struct xe_rtp_entry_sr lrc_was[] = { + { XE_RTP_NAME("16011163337"), + XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, 1210), ENGINE_CLASS(RENDER)), + /* read verification is ignored due to 1608008084. */ + XE_RTP_ACTIONS(FIELD_SET_NO_READ_MASK(FF_MODE2, + FF_MODE2_GS_TIMER_MASK, + FF_MODE2_GS_TIMER_224)) + }, + { XE_RTP_NAME("1604555607"), + XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, 1210), ENGINE_CLASS(RENDER)), + /* read verification is ignored due to 1608008084. */ + XE_RTP_ACTIONS(FIELD_SET_NO_READ_MASK(FF_MODE2, + FF_MODE2_TDS_TIMER_MASK, + FF_MODE2_TDS_TIMER_128)) + }, { XE_RTP_NAME("1409342910, 14010698770, 14010443199, 1408979724, 1409178076, 1409207793, 1409217633, 1409252684, 1409347922, 1409142259"), XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, 1210)), XE_RTP_ACTIONS(SET(COMMON_SLICE_CHICKEN3, @@ -806,8 +821,6 @@ static const struct xe_rtp_entry_sr lrc_was[] = { DIS_PARTIAL_AUTOSTRIP | DIS_AUTOSTRIP)) }, - - {} }; static __maybe_unused const struct xe_rtp_entry oob_was[] = { @@ -849,7 +862,7 @@ void xe_wa_process_gt(struct xe_gt *gt) xe_rtp_process_ctx_enable_active_tracking(&ctx, gt->wa_active.gt, ARRAY_SIZE(gt_was)); - xe_rtp_process_to_sr(&ctx, gt_was, >->reg_sr); + xe_rtp_process_to_sr(&ctx, gt_was, ARRAY_SIZE(gt_was), >->reg_sr); } EXPORT_SYMBOL_IF_KUNIT(xe_wa_process_gt); @@ -867,7 +880,7 @@ void xe_wa_process_engine(struct xe_hw_engine *hwe) xe_rtp_process_ctx_enable_active_tracking(&ctx, hwe->gt->wa_active.engine, ARRAY_SIZE(engine_was)); - xe_rtp_process_to_sr(&ctx, engine_was, &hwe->reg_sr); + xe_rtp_process_to_sr(&ctx, engine_was, ARRAY_SIZE(engine_was), &hwe->reg_sr); } /** @@ -884,7 +897,7 @@ void xe_wa_process_lrc(struct xe_hw_engine *hwe) xe_rtp_process_ctx_enable_active_tracking(&ctx, hwe->gt->wa_active.lrc, ARRAY_SIZE(lrc_was)); - xe_rtp_process_to_sr(&ctx, lrc_was, &hwe->reg_lrc); + xe_rtp_process_to_sr(&ctx, lrc_was, ARRAY_SIZE(lrc_was), &hwe->reg_lrc); } /** diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index 228436532282..e0c5fa460487 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -5,6 +5,7 @@ 22011391025 PLATFORM(DG2) 22012727170 SUBPLATFORM(DG2, G11) 22012727685 SUBPLATFORM(DG2, G11) +22016596838 PLATFORM(PVC) 18020744125 PLATFORM(PVC) 1509372804 PLATFORM(PVC), GRAPHICS_STEP(A0, C0) 1409600907 GRAPHICS_VERSION_RANGE(1200, 1250) @@ -43,3 +44,12 @@ no_media_l3 MEDIA_VERSION(3000) 14022866841 GRAPHICS_VERSION(3000), GRAPHICS_STEP(A0, B0) MEDIA_VERSION(3000), MEDIA_STEP(A0, B0) +16021333562 GRAPHICS_VERSION_RANGE(1200, 1274) + MEDIA_VERSION(1300) +14016712196 GRAPHICS_VERSION(1255) + GRAPHICS_VERSION_RANGE(1270, 1274) +14015568240 GRAPHICS_VERSION_RANGE(1255, 1260) +18013179988 GRAPHICS_VERSION(1255) + GRAPHICS_VERSION_RANGE(1270, 1274) +1508761755 GRAPHICS_VERSION(1255) + GRAPHICS_VERSION(1260), GRAPHICS_STEP(A0, B0) diff --git a/drivers/gpu/nova-core/Kconfig b/drivers/gpu/nova-core/Kconfig new file mode 100644 index 000000000000..ad0c06756516 --- /dev/null +++ b/drivers/gpu/nova-core/Kconfig @@ -0,0 +1,14 @@ +config NOVA_CORE + tristate "Nova Core GPU driver" + depends on PCI + depends on RUST + depends on RUST_FW_LOADER_ABSTRACTIONS + default n + help + Choose this if you want to build the Nova Core driver for Nvidia + GPUs based on the GPU System Processor (GSP). This is true for Turing + and later GPUs. + + This driver is work in progress and may not be functional. + + If M is selected, the module will be called nova_core. diff --git a/drivers/gpu/nova-core/Makefile b/drivers/gpu/nova-core/Makefile new file mode 100644 index 000000000000..2d78c50126e1 --- /dev/null +++ b/drivers/gpu/nova-core/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_NOVA_CORE) += nova_core.o diff --git a/drivers/gpu/nova-core/driver.rs b/drivers/gpu/nova-core/driver.rs new file mode 100644 index 000000000000..63c19f140fbd --- /dev/null +++ b/drivers/gpu/nova-core/driver.rs @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 + +use kernel::{bindings, c_str, pci, prelude::*}; + +use crate::gpu::Gpu; + +#[pin_data] +pub(crate) struct NovaCore { + #[pin] + pub(crate) gpu: Gpu, +} + +const BAR0_SIZE: usize = 8; +pub(crate) type Bar0 = pci::Bar<BAR0_SIZE>; + +kernel::pci_device_table!( + PCI_TABLE, + MODULE_PCI_TABLE, + <NovaCore as pci::Driver>::IdInfo, + [( + pci::DeviceId::from_id(bindings::PCI_VENDOR_ID_NVIDIA, bindings::PCI_ANY_ID as _), + () + )] +); + +impl pci::Driver for NovaCore { + type IdInfo = (); + const ID_TABLE: pci::IdTable<Self::IdInfo> = &PCI_TABLE; + + fn probe(pdev: &mut pci::Device, _info: &Self::IdInfo) -> Result<Pin<KBox<Self>>> { + dev_dbg!(pdev.as_ref(), "Probe Nova Core GPU driver.\n"); + + pdev.enable_device_mem()?; + pdev.set_master(); + + let bar = pdev.iomap_region_sized::<BAR0_SIZE>(0, c_str!("nova-core/bar0"))?; + + let this = KBox::pin_init( + try_pin_init!(Self { + gpu <- Gpu::new(pdev, bar)?, + }), + GFP_KERNEL, + )?; + + Ok(this) + } +} diff --git a/drivers/gpu/nova-core/firmware.rs b/drivers/gpu/nova-core/firmware.rs new file mode 100644 index 000000000000..6e6361c59ca1 --- /dev/null +++ b/drivers/gpu/nova-core/firmware.rs @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 + +use crate::gpu; +use kernel::firmware; + +pub(crate) struct ModInfoBuilder<const N: usize>(firmware::ModInfoBuilder<N>); + +impl<const N: usize> ModInfoBuilder<N> { + const VERSION: &'static str = "535.113.01"; + + const fn make_entry_file(self, chipset: &str, fw: &str) -> Self { + ModInfoBuilder( + self.0 + .new_entry() + .push("nvidia/") + .push(chipset) + .push("/gsp/") + .push(fw) + .push("-") + .push(Self::VERSION) + .push(".bin"), + ) + } + + const fn make_entry_chipset(self, chipset: &str) -> Self { + self.make_entry_file(chipset, "booter_load") + .make_entry_file(chipset, "booter_unload") + .make_entry_file(chipset, "bootloader") + .make_entry_file(chipset, "gsp") + } + + pub(crate) const fn create( + module_name: &'static kernel::str::CStr, + ) -> firmware::ModInfoBuilder<N> { + let mut this = Self(firmware::ModInfoBuilder::new(module_name)); + let mut i = 0; + + while i < gpu::Chipset::NAMES.len() { + this = this.make_entry_chipset(gpu::Chipset::NAMES[i]); + i += 1; + } + + this.0 + } +} diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs new file mode 100644 index 000000000000..17c9660da450 --- /dev/null +++ b/drivers/gpu/nova-core/gpu.rs @@ -0,0 +1,199 @@ +// SPDX-License-Identifier: GPL-2.0 + +use kernel::{ + device, devres::Devres, error::code::*, firmware, fmt, pci, prelude::*, str::CString, +}; + +use crate::driver::Bar0; +use crate::regs; +use crate::util; +use core::fmt; + +macro_rules! define_chipset { + ({ $($variant:ident = $value:expr),* $(,)* }) => + { + /// Enum representation of the GPU chipset. + #[derive(fmt::Debug)] + pub(crate) enum Chipset { + $($variant = $value),*, + } + + impl Chipset { + pub(crate) const ALL: &'static [Chipset] = &[ + $( Chipset::$variant, )* + ]; + + pub(crate) const NAMES: [&'static str; Self::ALL.len()] = [ + $( util::const_bytes_to_str( + util::to_lowercase_bytes::<{ stringify!($variant).len() }>( + stringify!($variant) + ).as_slice() + ), )* + ]; + } + + // TODO replace with something like derive(FromPrimitive) + impl TryFrom<u32> for Chipset { + type Error = kernel::error::Error; + + fn try_from(value: u32) -> Result<Self, Self::Error> { + match value { + $( $value => Ok(Chipset::$variant), )* + _ => Err(ENODEV), + } + } + } + } +} + +define_chipset!({ + // Turing + TU102 = 0x162, + TU104 = 0x164, + TU106 = 0x166, + TU117 = 0x167, + TU116 = 0x168, + // Ampere + GA102 = 0x172, + GA103 = 0x173, + GA104 = 0x174, + GA106 = 0x176, + GA107 = 0x177, + // Ada + AD102 = 0x192, + AD103 = 0x193, + AD104 = 0x194, + AD106 = 0x196, + AD107 = 0x197, +}); + +impl Chipset { + pub(crate) fn arch(&self) -> Architecture { + match self { + Self::TU102 | Self::TU104 | Self::TU106 | Self::TU117 | Self::TU116 => { + Architecture::Turing + } + Self::GA102 | Self::GA103 | Self::GA104 | Self::GA106 | Self::GA107 => { + Architecture::Ampere + } + Self::AD102 | Self::AD103 | Self::AD104 | Self::AD106 | Self::AD107 => { + Architecture::Ada + } + } + } +} + +// TODO +// +// The resulting strings are used to generate firmware paths, hence the +// generated strings have to be stable. +// +// Hence, replace with something like strum_macros derive(Display). +// +// For now, redirect to fmt::Debug for convenience. +impl fmt::Display for Chipset { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + write!(f, "{:?}", self) + } +} + +/// Enum representation of the GPU generation. +#[derive(fmt::Debug)] +pub(crate) enum Architecture { + Turing, + Ampere, + Ada, +} + +pub(crate) struct Revision { + major: u8, + minor: u8, +} + +impl Revision { + fn from_boot0(boot0: regs::Boot0) -> Self { + Self { + major: boot0.major_rev(), + minor: boot0.minor_rev(), + } + } +} + +impl fmt::Display for Revision { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + write!(f, "{:x}.{:x}", self.major, self.minor) + } +} + +/// Structure holding the metadata of the GPU. +pub(crate) struct Spec { + chipset: Chipset, + /// The revision of the chipset. + revision: Revision, +} + +impl Spec { + fn new(bar: &Devres<Bar0>) -> Result<Spec> { + let bar = bar.try_access().ok_or(ENXIO)?; + let boot0 = regs::Boot0::read(&bar); + + Ok(Self { + chipset: boot0.chipset().try_into()?, + revision: Revision::from_boot0(boot0), + }) + } +} + +/// Structure encapsulating the firmware blobs required for the GPU to operate. +#[expect(dead_code)] +pub(crate) struct Firmware { + booter_load: firmware::Firmware, + booter_unload: firmware::Firmware, + bootloader: firmware::Firmware, + gsp: firmware::Firmware, +} + +impl Firmware { + fn new(dev: &device::Device, spec: &Spec, ver: &str) -> Result<Firmware> { + let mut chip_name = CString::try_from_fmt(fmt!("{}", spec.chipset))?; + chip_name.make_ascii_lowercase(); + + let request = |name_| { + CString::try_from_fmt(fmt!("nvidia/{}/gsp/{}-{}.bin", &*chip_name, name_, ver)) + .and_then(|path| firmware::Firmware::request(&path, dev)) + }; + + Ok(Firmware { + booter_load: request("booter_load")?, + booter_unload: request("booter_unload")?, + bootloader: request("bootloader")?, + gsp: request("gsp")?, + }) + } +} + +/// Structure holding the resources required to operate the GPU. +#[pin_data] +pub(crate) struct Gpu { + spec: Spec, + /// MMIO mapping of PCI BAR 0 + bar: Devres<Bar0>, + fw: Firmware, +} + +impl Gpu { + pub(crate) fn new(pdev: &pci::Device, bar: Devres<Bar0>) -> Result<impl PinInit<Self>> { + let spec = Spec::new(&bar)?; + let fw = Firmware::new(pdev.as_ref(), &spec, "535.113.01")?; + + dev_info!( + pdev.as_ref(), + "NVIDIA (Chipset: {}, Architecture: {:?}, Revision: {})\n", + spec.chipset, + spec.chipset.arch(), + spec.revision + ); + + Ok(pin_init!(Self { spec, bar, fw })) + } +} diff --git a/drivers/gpu/nova-core/nova_core.rs b/drivers/gpu/nova-core/nova_core.rs new file mode 100644 index 000000000000..a91cd924054b --- /dev/null +++ b/drivers/gpu/nova-core/nova_core.rs @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Nova Core GPU Driver + +mod driver; +mod firmware; +mod gpu; +mod regs; +mod util; + +kernel::module_pci_driver! { + type: driver::NovaCore, + name: "NovaCore", + author: "Danilo Krummrich", + description: "Nova Core GPU driver", + license: "GPL v2", + firmware: [], +} + +kernel::module_firmware!(firmware::ModInfoBuilder); diff --git a/drivers/gpu/nova-core/regs.rs b/drivers/gpu/nova-core/regs.rs new file mode 100644 index 000000000000..50aefb150b0b --- /dev/null +++ b/drivers/gpu/nova-core/regs.rs @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 + +use crate::driver::Bar0; + +// TODO +// +// Create register definitions via generic macros. See task "Generic register +// abstraction" in Documentation/gpu/nova/core/todo.rst. + +const BOOT0_OFFSET: usize = 0x00000000; + +// 3:0 - chipset minor revision +const BOOT0_MINOR_REV_SHIFT: u8 = 0; +const BOOT0_MINOR_REV_MASK: u32 = 0x0000000f; + +// 7:4 - chipset major revision +const BOOT0_MAJOR_REV_SHIFT: u8 = 4; +const BOOT0_MAJOR_REV_MASK: u32 = 0x000000f0; + +// 23:20 - chipset implementation Identifier (depends on architecture) +const BOOT0_IMPL_SHIFT: u8 = 20; +const BOOT0_IMPL_MASK: u32 = 0x00f00000; + +// 28:24 - chipset architecture identifier +const BOOT0_ARCH_MASK: u32 = 0x1f000000; + +// 28:20 - chipset identifier (virtual register field combining BOOT0_IMPL and +// BOOT0_ARCH) +const BOOT0_CHIPSET_SHIFT: u8 = BOOT0_IMPL_SHIFT; +const BOOT0_CHIPSET_MASK: u32 = BOOT0_IMPL_MASK | BOOT0_ARCH_MASK; + +#[derive(Copy, Clone)] +pub(crate) struct Boot0(u32); + +impl Boot0 { + #[inline] + pub(crate) fn read(bar: &Bar0) -> Self { + Self(bar.readl(BOOT0_OFFSET)) + } + + #[inline] + pub(crate) fn chipset(&self) -> u32 { + (self.0 & BOOT0_CHIPSET_MASK) >> BOOT0_CHIPSET_SHIFT + } + + #[inline] + pub(crate) fn minor_rev(&self) -> u8 { + ((self.0 & BOOT0_MINOR_REV_MASK) >> BOOT0_MINOR_REV_SHIFT) as u8 + } + + #[inline] + pub(crate) fn major_rev(&self) -> u8 { + ((self.0 & BOOT0_MAJOR_REV_MASK) >> BOOT0_MAJOR_REV_SHIFT) as u8 + } +} diff --git a/drivers/gpu/nova-core/util.rs b/drivers/gpu/nova-core/util.rs new file mode 100644 index 000000000000..332a64cfc6a9 --- /dev/null +++ b/drivers/gpu/nova-core/util.rs @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 + +pub(crate) const fn to_lowercase_bytes<const N: usize>(s: &str) -> [u8; N] { + let src = s.as_bytes(); + let mut dst = [0; N]; + let mut i = 0; + + while i < src.len() && i < N { + dst[i] = (src[i] as char).to_ascii_lowercase() as u8; + i += 1; + } + + dst +} + +pub(crate) const fn const_bytes_to_str(bytes: &[u8]) -> &str { + match core::str::from_utf8(bytes) { + Ok(string) => string, + Err(_) => kernel::build_error!("Bytes are not valid UTF-8."), + } +} |