diff options
| author | Jani Nikula <jani.nikula@intel.com> | 2022-04-11 16:01:56 +0300 |
|---|---|---|
| committer | Jani Nikula <jani.nikula@intel.com> | 2022-04-11 16:01:56 +0300 |
| commit | 83970cd63b9f864525761137b500113ab0b49c94 (patch) | |
| tree | 747b97113d60666cbb44f8a5633b961b7eda3c86 /drivers/gpu | |
| parent | 618f5df1f6a5a3f29fad824116da291a7d14ab5e (diff) | |
| parent | 3123109284176b1532874591f7c81f3837bbdc17 (diff) | |
Merge drm/drm-next into drm-intel-next
Sync up with v5.18-rc1, in particular to get 5e3094cfd9fb
("drm/i915/xehpsdv: Add has_flat_ccs to device info").
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Diffstat (limited to 'drivers/gpu')
482 files changed, 11016 insertions, 9462 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 5dfe08cb045e..40e2c6e2df79 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -53,11 +53,11 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \ amdgpu_ucode.o amdgpu_bo_list.o amdgpu_ctx.o amdgpu_sync.o \ amdgpu_gtt_mgr.o amdgpu_preempt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o \ amdgpu_atomfirmware.o amdgpu_vf_error.o amdgpu_sched.o \ - amdgpu_debugfs.o amdgpu_ids.o amdgpu_gmc.o amdgpu_mmhub.o \ + amdgpu_debugfs.o amdgpu_ids.o amdgpu_gmc.o \ amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \ amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o amdgpu_nbio.o \ amdgpu_umc.o smu_v11_0_i2c.o amdgpu_fru_eeprom.o amdgpu_rap.o \ - amdgpu_fw_attestation.o amdgpu_securedisplay.o amdgpu_hdp.o \ + amdgpu_fw_attestation.o amdgpu_securedisplay.o \ amdgpu_eeprom.o amdgpu_mca.o amdgpu-$(CONFIG_PROC_FS) += amdgpu_fdinfo.o diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.c b/drivers/gpu/drm/amd/amdgpu/aldebaran.c index a545df4efce1..c6cc493a5486 100644 --- a/drivers/gpu/drm/amd/amdgpu/aldebaran.c +++ b/drivers/gpu/drm/amd/amdgpu/aldebaran.c @@ -31,6 +31,17 @@ #include "amdgpu_psp.h" #include "amdgpu_xgmi.h" +static bool aldebaran_is_mode2_default(struct amdgpu_reset_control *reset_ctl) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle; + + if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2) && + adev->gmc.xgmi.connected_to_cpu)) + return true; + + return false; +} + static struct amdgpu_reset_handler * aldebaran_get_reset_handler(struct amdgpu_reset_control *reset_ctl, struct amdgpu_reset_context *reset_context) @@ -48,7 +59,7 @@ aldebaran_get_reset_handler(struct amdgpu_reset_control *reset_ctl, } } - if (adev->gmc.xgmi.connected_to_cpu) { + if (aldebaran_is_mode2_default(reset_ctl)) { list_for_each_entry(handler, &reset_ctl->reset_handlers, handler_list) { if (handler->reset_method == AMD_RESET_METHOD_MODE2) { @@ -136,18 +147,31 @@ static int aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl, struct amdgpu_reset_context *reset_context) { - struct amdgpu_device *tmp_adev = NULL; struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle; + struct amdgpu_device *tmp_adev = NULL; + struct list_head reset_device_list; int r = 0; dev_dbg(adev->dev, "aldebaran perform hw reset\n"); - if (reset_context->hive == NULL) { + if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2) && + reset_context->hive == NULL) { /* Wrong context, return error */ return -EINVAL; } - list_for_each_entry(tmp_adev, &reset_context->hive->device_list, - gmc.xgmi.head) { + INIT_LIST_HEAD(&reset_device_list); + if (reset_context->hive) { + list_for_each_entry (tmp_adev, + &reset_context->hive->device_list, + gmc.xgmi.head) + list_add_tail(&tmp_adev->reset_list, + &reset_device_list); + } else { + list_add_tail(&reset_context->reset_req_dev->reset_list, + &reset_device_list); + } + + list_for_each_entry (tmp_adev, &reset_device_list, reset_list) { mutex_lock(&tmp_adev->reset_cntl->reset_lock); tmp_adev->reset_cntl->active_reset = AMD_RESET_METHOD_MODE2; } @@ -155,8 +179,7 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl, * Mode2 reset doesn't need any sync between nodes in XGMI hive, instead launch * them together so that they can be completed asynchronously on multiple nodes */ - list_for_each_entry(tmp_adev, &reset_context->hive->device_list, - gmc.xgmi.head) { + list_for_each_entry (tmp_adev, &reset_device_list, reset_list) { /* For XGMI run all resets in parallel to speed up the process */ if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) { if (!queue_work(system_unbound_wq, @@ -174,9 +197,7 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl, /* For XGMI wait for all resets to complete before proceed */ if (!r) { - list_for_each_entry(tmp_adev, - &reset_context->hive->device_list, - gmc.xgmi.head) { + list_for_each_entry (tmp_adev, &reset_device_list, reset_list) { if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) { flush_work(&tmp_adev->reset_cntl->reset_work); r = tmp_adev->asic_reset_res; @@ -186,8 +207,7 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl, } } - list_for_each_entry(tmp_adev, &reset_context->hive->device_list, - gmc.xgmi.head) { + list_for_each_entry (tmp_adev, &reset_device_list, reset_list) { mutex_unlock(&tmp_adev->reset_cntl->reset_lock); tmp_adev->reset_cntl->active_reset = AMD_RESET_METHOD_NONE; } @@ -319,16 +339,30 @@ static int aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl, struct amdgpu_reset_context *reset_context) { - int r; struct amdgpu_device *tmp_adev = NULL; + struct list_head reset_device_list; + int r; - if (reset_context->hive == NULL) { + if (reset_context->reset_req_dev->ip_versions[MP1_HWIP][0] == + IP_VERSION(13, 0, 2) && + reset_context->hive == NULL) { /* Wrong context, return error */ return -EINVAL; } - list_for_each_entry(tmp_adev, &reset_context->hive->device_list, - gmc.xgmi.head) { + INIT_LIST_HEAD(&reset_device_list); + if (reset_context->hive) { + list_for_each_entry (tmp_adev, + &reset_context->hive->device_list, + gmc.xgmi.head) + list_add_tail(&tmp_adev->reset_list, + &reset_device_list); + } else { + list_add_tail(&reset_context->reset_req_dev->reset_list, + &reset_device_list); + } + + list_for_each_entry (tmp_adev, &reset_device_list, reset_list) { dev_info(tmp_adev->dev, "GPU reset succeeded, trying to resume\n"); r = aldebaran_mode2_restore_ip(tmp_adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 37ff8cf5bbed..cdf0818088b3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -60,7 +60,6 @@ #include <drm/amdgpu_drm.h> #include <drm/drm_gem.h> #include <drm/drm_ioctl.h> -#include <drm/gpu_scheduler.h> #include <kgd_kfd_interface.h> #include "dm_pp_interface.h" @@ -233,6 +232,9 @@ extern int amdgpu_cik_support; #endif extern int amdgpu_num_kcq; +#define AMDGPU_VCNFW_LOG_SIZE (32 * 1024) +extern int amdgpu_vcnfw_log; + #define AMDGPU_VM_MAX_NUM_CTX 4096 #define AMDGPU_SG_THRESHOLD (256*1024*1024) #define AMDGPU_DEFAULT_GTT_SIZE_MB 3072ULL /* 3GB by default */ @@ -274,9 +276,6 @@ extern int amdgpu_num_kcq; #define AMDGPU_SMARTSHIFT_MIN_BIAS (-100) struct amdgpu_device; -struct amdgpu_ib; -struct amdgpu_cs_parser; -struct amdgpu_job; struct amdgpu_irq_src; struct amdgpu_fpriv; struct amdgpu_bo_va_mapping; @@ -465,20 +464,6 @@ struct amdgpu_flip_work { /* - * CP & rings. - */ - -struct amdgpu_ib { - struct amdgpu_sa_bo *sa_bo; - uint32_t length_dw; - uint64_t gpu_addr; - uint32_t *ptr; - uint32_t flags; -}; - -extern const struct drm_sched_backend_ops amdgpu_sched_ops; - -/* * file private structure */ @@ -493,79 +478,6 @@ struct amdgpu_fpriv { int amdgpu_file_to_fpriv(struct file *filp, struct amdgpu_fpriv **fpriv); -int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm, - unsigned size, - enum amdgpu_ib_pool_type pool, - struct amdgpu_ib *ib); -void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib, - struct dma_fence *f); -int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, - struct amdgpu_ib *ibs, struct amdgpu_job *job, - struct dma_fence **f); -int amdgpu_ib_pool_init(struct amdgpu_device *adev); -void amdgpu_ib_pool_fini(struct amdgpu_device *adev); -int amdgpu_ib_ring_tests(struct amdgpu_device *adev); - -/* - * CS. - */ -struct amdgpu_cs_chunk { - uint32_t chunk_id; - uint32_t length_dw; - void *kdata; -}; - -struct amdgpu_cs_post_dep { - struct drm_syncobj *syncobj; - struct dma_fence_chain *chain; - u64 point; -}; - -struct amdgpu_cs_parser { - struct amdgpu_device *adev; - struct drm_file *filp; - struct amdgpu_ctx *ctx; - - /* chunks */ - unsigned nchunks; - struct amdgpu_cs_chunk *chunks; - - /* scheduler job object */ - struct amdgpu_job *job; - struct drm_sched_entity *entity; - - /* buffer objects */ - struct ww_acquire_ctx ticket; - struct amdgpu_bo_list *bo_list; - struct amdgpu_mn *mn; - struct amdgpu_bo_list_entry vm_pd; - struct list_head validated; - struct dma_fence *fence; - uint64_t bytes_moved_threshold; - uint64_t bytes_moved_vis_threshold; - uint64_t bytes_moved; - uint64_t bytes_moved_vis; - - /* user fence */ - struct amdgpu_bo_list_entry uf_entry; - - unsigned num_post_deps; - struct amdgpu_cs_post_dep *post_deps; -}; - -static inline u32 amdgpu_get_ib_value(struct amdgpu_cs_parser *p, - uint32_t ib_idx, int idx) -{ - return p->job->ibs[ib_idx].ptr[idx]; -} - -static inline void amdgpu_set_ib_value(struct amdgpu_cs_parser *p, - uint32_t ib_idx, int idx, - uint32_t value) -{ - p->job->ibs[ib_idx].ptr[idx] = value; -} - /* * Writeback */ @@ -1436,10 +1348,6 @@ static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { retu static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; } #endif -int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser, - uint64_t addr, struct amdgpu_bo **bo, - struct amdgpu_bo_va_mapping **mapping); - #if defined(CONFIG_DRM_AMD_DC) int amdgpu_dm_display_resume(struct amdgpu_device *adev ); #else 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 e9c80ce13f3e..ba21ec6b35e0 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 @@ -26,6 +26,8 @@ #include "gc/gc_10_3_0_sh_mask.h" #include "oss/osssys_5_0_0_offset.h" #include "oss/osssys_5_0_0_sh_mask.h" +#include "athub/athub_2_1_0_offset.h" +#include "athub/athub_2_1_0_sh_mask.h" #include "soc15_common.h" #include "v10_structs.h" #include "nv.h" @@ -606,6 +608,18 @@ static int wave_control_execute_v10_3(struct amdgpu_device *adev, return 0; } +static bool get_atc_vmid_pasid_mapping_info_v10_3(struct amdgpu_device *adev, + uint8_t vmid, uint16_t *p_pasid) +{ + uint32_t value; + + value = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING) + + vmid); + *p_pasid = value & ATC_VMID0_PASID_MAPPING__PASID_MASK; + + return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK); +} + static void set_vm_context_page_table_base_v10_3(struct amdgpu_device *adev, uint32_t vmid, uint64_t page_table_base) { @@ -788,7 +802,7 @@ const struct kfd2kgd_calls gfx_v10_3_kfd2kgd = { .hqd_destroy = hqd_destroy_v10_3, .hqd_sdma_destroy = hqd_sdma_destroy_v10_3, .wave_control_execute = wave_control_execute_v10_3, - .get_atc_vmid_pasid_mapping_info = NULL, + .get_atc_vmid_pasid_mapping_info = get_atc_vmid_pasid_mapping_info_v10_3, .set_vm_context_page_table_base = set_vm_context_page_table_base_v10_3, .program_trap_handler_settings = program_trap_handler_settings_v10_3, #if 0 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index fa20261aa928..673078faa27a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -626,7 +626,7 @@ amdgpu_connector_fixup_lcd_native_mode(struct drm_encoder *encoder, if (mode->type & DRM_MODE_TYPE_PREFERRED) { if (mode->hdisplay != native_mode->hdisplay || mode->vdisplay != native_mode->vdisplay) - memcpy(native_mode, mode, sizeof(*mode)); + drm_mode_copy(native_mode, mode); } } @@ -635,7 +635,7 @@ amdgpu_connector_fixup_lcd_native_mode(struct drm_encoder *encoder, list_for_each_entry_safe(mode, t, &connector->probed_modes, head) { if (mode->hdisplay == native_mode->hdisplay && mode->vdisplay == native_mode->vdisplay) { - *native_mode = *mode; + drm_mode_copy(native_mode, mode); drm_mode_set_crtcinfo(native_mode, CRTC_INTERLACE_HALVE_V); DRM_DEBUG_KMS("Determined LVDS native mode details from EDID\n"); break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index e762e45b7b85..970b065e9a6b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -32,6 +32,7 @@ #include <drm/amdgpu_drm.h> #include <drm/drm_syncobj.h> +#include "amdgpu_cs.h" #include "amdgpu.h" #include "amdgpu_trace.h" #include "amdgpu_gmc.h" @@ -339,7 +340,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev, if (free_vram >= 128 * 1024 * 1024 || free_vram >= total_vram / 8) { s64 min_us; - /* Be more aggresive on dGPUs. Try to fill a portion of free + /* Be more aggressive on dGPUs. Try to fill a portion of free * VRAM now. */ if (!(adev->flags & AMD_IS_APU)) @@ -782,12 +783,12 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) memcpy(ib->ptr, kptr, chunk_ib->ib_bytes); amdgpu_bo_kunmap(aobj); - r = amdgpu_ring_parse_cs(ring, p, j); + r = amdgpu_ring_parse_cs(ring, p, p->job, ib); if (r) return r; } else { ib->ptr = (uint32_t *)kptr; - r = amdgpu_ring_patch_cs_in_place(ring, p, j); + r = amdgpu_ring_patch_cs_in_place(ring, p, p->job, ib); amdgpu_bo_kunmap(aobj); if (r) return r; @@ -1279,7 +1280,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, continue; /* - * Work around dma_resv shortcommings by wrapping up the + * Work around dma_resv shortcomings by wrapping up the * submission in a dma_fence_chain and add it as exclusive * fence. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h new file mode 100644 index 000000000000..30ecc4917f81 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h @@ -0,0 +1,80 @@ +/* + * Copyright 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. + * + */ +#ifndef __AMDGPU_CS_H__ +#define __AMDGPU_CS_H__ + +#include "amdgpu_job.h" +#include "amdgpu_bo_list.h" +#include "amdgpu_ring.h" + +struct amdgpu_bo_va_mapping; + +struct amdgpu_cs_chunk { + uint32_t chunk_id; + uint32_t length_dw; + void *kdata; +}; + +struct amdgpu_cs_post_dep { + struct drm_syncobj *syncobj; + struct dma_fence_chain *chain; + u64 point; +}; + +struct amdgpu_cs_parser { + struct amdgpu_device *adev; + struct drm_file *filp; + struct amdgpu_ctx *ctx; + + /* chunks */ + unsigned nchunks; + struct amdgpu_cs_chunk *chunks; + + /* scheduler job object */ + struct amdgpu_job *job; + struct drm_sched_entity *entity; + + /* buffer objects */ + struct ww_acquire_ctx ticket; + struct amdgpu_bo_list *bo_list; + struct amdgpu_mn *mn; + struct amdgpu_bo_list_entry vm_pd; + struct list_head validated; + struct dma_fence *fence; + uint64_t bytes_moved_threshold; + uint64_t bytes_moved_vis_threshold; + uint64_t bytes_moved; + uint64_t bytes_moved_vis; + + /* user fence */ + struct amdgpu_bo_list_entry uf_entry; + + unsigned num_post_deps; + struct amdgpu_cs_post_dep *post_deps; +}; + +int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser, + uint64_t addr, struct amdgpu_bo **bo, + struct amdgpu_bo_va_mapping **mapping); + +#endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index f522b52725e4..5981c7d9bd48 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -23,6 +23,7 @@ */ #include <drm/drm_auth.h> +#include <drm/drm_drv.h> #include "amdgpu.h" #include "amdgpu_sched.h" #include "amdgpu_ras.h" @@ -204,9 +205,15 @@ static int amdgpu_ctx_init_entity(struct amdgpu_ctx *ctx, u32 hw_ip, if (r) goto error_free_entity; - ctx->entities[hw_ip][ring] = entity; + /* It's not an error if we fail to install the new entity */ + if (cmpxchg(&ctx->entities[hw_ip][ring], NULL, entity)) + goto cleanup_entity; + return 0; +cleanup_entity: + drm_sched_entity_fini(&entity->entity); + error_free_entity: kfree(entity); @@ -261,9 +268,6 @@ static int amdgpu_ctx_get_stable_pstate(struct amdgpu_ctx *ctx, struct amdgpu_device *adev = ctx->adev; enum amd_dpm_forced_level current_level; - if (!ctx) - return -EINVAL; - current_level = amdgpu_dpm_get_performance_level(adev); switch (current_level) { @@ -293,9 +297,6 @@ static int amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, enum amd_dpm_forced_level level; int r; - if (!ctx) - return -EINVAL; - mutex_lock(&adev->pm.stable_pstate_ctx_lock); if (adev->pm.stable_pstate_ctx && adev->pm.stable_pstate_ctx != ctx) { r = -EBUSY; @@ -339,7 +340,7 @@ static void amdgpu_ctx_fini(struct kref *ref) { struct amdgpu_ctx *ctx = container_of(ref, struct amdgpu_ctx, refcount); struct amdgpu_device *adev = ctx->adev; - unsigned i, j; + unsigned i, j, idx; if (!adev) return; @@ -350,7 +351,12 @@ static void amdgpu_ctx_fini(struct kref *ref) ctx->entities[i][j] = NULL; } } - amdgpu_ctx_set_stable_pstate(ctx, AMDGPU_CTX_STABLE_PSTATE_NONE); + + if (drm_dev_enter(&adev->ddev, &idx)) { + amdgpu_ctx_set_stable_pstate(ctx, AMDGPU_CTX_STABLE_PSTATE_NONE); + drm_dev_exit(idx); + } + kfree(ctx); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 426b63e4f1f6..5d04d24a0d5f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -1678,7 +1678,7 @@ static ssize_t amdgpu_reset_dump_register_list_write(struct file *f, { struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private; char reg_offset[11]; - uint32_t *tmp; + uint32_t *new, *tmp = NULL; int ret, i = 0, len = 0; do { @@ -1689,7 +1689,12 @@ static ssize_t amdgpu_reset_dump_register_list_write(struct file *f, goto error_free; } - tmp = krealloc_array(tmp, i + 1, sizeof(uint32_t), GFP_KERNEL); + new = krealloc_array(tmp, i + 1, sizeof(uint32_t), GFP_KERNEL); + if (!new) { + ret = -ENOMEM; + goto error_free; + } + tmp = new; if (sscanf(reg_offset, "%X %n", &tmp[i], &ret) != 1) { ret = -EINVAL; goto error_free; @@ -1773,6 +1778,16 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev) amdgpu_debugfs_ring_init(adev, ring); } + for ( i = 0; i < adev->vcn.num_vcn_inst; i++) { + if (!amdgpu_vcnfw_log) + break; + + if (adev->vcn.harvest_config & (1 << i)) + continue; + + amdgpu_debugfs_vcn_fwlog_init(adev, i, &adev->vcn.inst[i]); + } + amdgpu_ras_debugfs_create_all(adev); amdgpu_rap_debugfs_init(adev); amdgpu_securedisplay_debugfs_init(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index ca854626a108..3987ecb24ef4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -80,12 +80,7 @@ MODULE_FIRMWARE("amdgpu/raven_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/picasso_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/raven2_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/arcturus_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/renoir_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/vangogh_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/yellow_carp_gpu_info.bin"); #define AMDGPU_RESUME_MS 2000 #define AMDGPU_MAX_RETRY_LIMIT 2 @@ -1554,7 +1549,6 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev) amdgpu_gmc_tmz_set(adev); - amdgpu_gmc_noretry_set(adev); return 0; } @@ -1992,27 +1986,9 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) case CHIP_ARCTURUS: chip_name = "arcturus"; break; - case CHIP_RENOIR: - if (adev->apu_flags & AMD_APU_IS_RENOIR) - chip_name = "renoir"; - else - chip_name = "green_sardine"; - break; - case CHIP_NAVI10: - chip_name = "navi10"; - break; - case CHIP_NAVI14: - chip_name = "navi14"; - break; case CHIP_NAVI12: chip_name = "navi12"; break; - case CHIP_VANGOGH: - chip_name = "vangogh"; - break; - case CHIP_YELLOW_CARP: - chip_name = "yellow_carp"; - break; } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_gpu_info.bin", chip_name); @@ -2183,8 +2159,10 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) !pci_is_thunderbolt_attached(to_pci_dev(dev->dev))) adev->flags |= AMD_IS_PX; - parent = pci_upstream_bridge(adev->pdev); - adev->has_pr3 = parent ? pci_pr3_present(parent) : false; + if (!(adev->flags & AMD_IS_APU)) { + parent = pci_upstream_bridge(adev->pdev); + adev->has_pr3 = parent ? pci_pr3_present(parent) : false; + } amdgpu_amdkfd_device_probe(adev); @@ -3688,6 +3666,15 @@ int amdgpu_device_init(struct amdgpu_device *adev, if (amdgpu_mes && adev->asic_type >= CHIP_NAVI10) adev->enable_mes = true; + /* + * Reset domain needs to be present early, before XGMI hive discovered + * (if any) and intitialized to use reset sem and in_gpu reset flag + * early on during init and before calling to RREG32. + */ + adev->reset_domain = amdgpu_reset_create_reset_domain(SINGLE_DEVICE, "amdgpu-reset-dev"); + if (!adev->reset_domain) + return -ENOMEM; + /* detect hw virtualization here */ amdgpu_detect_virtualization(adev); @@ -3697,20 +3684,12 @@ int amdgpu_device_init(struct amdgpu_device *adev, return r; } - /* - * Reset domain needs to be present early, before XGMI hive discovered - * (if any) and intitialized to use reset sem and in_gpu reset flag - * early on during init. - */ - adev->reset_domain = amdgpu_reset_create_reset_domain(SINGLE_DEVICE ,"amdgpu-reset-dev"); - if (!adev->reset_domain) - return -ENOMEM; - /* early init functions */ r = amdgpu_device_ip_early_init(adev); if (r) return r; + amdgpu_gmc_noretry_set(adev); /* Need to get xgmi info early to decide the reset behavior*/ if (adev->gmc.xgmi.supported) { r = adev->gfxhub.funcs->get_xgmi_info(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index cae57d3b317a..fae5c1debfad 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -691,9 +691,9 @@ static int convert_tiling_flags_to_modifier(struct amdgpu_framebuffer *afb) return -EINVAL; } - if (adev->asic_type >= CHIP_SIENNA_CICHLID) + if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(10, 3, 0)) version = AMD_FMT_MOD_TILE_VER_GFX10_RBPLUS; - else if (adev->family == AMDGPU_FAMILY_NV) + else if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(10, 0, 0)) version = AMD_FMT_MOD_TILE_VER_GFX10; else version = AMD_FMT_MOD_TILE_VER_GFX9; @@ -787,7 +787,7 @@ static int convert_tiling_flags_to_modifier(struct amdgpu_framebuffer *afb) if (adev->family >= AMDGPU_FAMILY_NV) { int extra_pipe = 0; - if (adev->asic_type >= CHIP_SIENNA_CICHLID && + if ((adev->ip_versions[GC_HWIP][0] >= IP_VERSION(10, 3, 0)) && pipes == packers && pipes > 1) extra_pipe = 1; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 2ab675123ae3..bb1c025d9001 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -100,9 +100,10 @@ * - 3.43.0 - Add device hot plug/unplug support * - 3.44.0 - DCN3 supports DCC independent block settings: !64B && 128B, 64B && 128B * - 3.45.0 - Add context ioctl stable pstate interface + * * 3.46.0 - To enable hot plug amdgpu tests in libdrm */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 45 +#define KMS_DRIVER_MINOR 46 #define KMS_DRIVER_PATCHLEVEL 0 int amdgpu_vram_limit; @@ -177,6 +178,7 @@ int amdgpu_reset_method = -1; /* auto */ int amdgpu_num_kcq = -1; int amdgpu_smartshift_bias; int amdgpu_use_xgmi_p2p = 1; +int amdgpu_vcnfw_log; static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work); @@ -855,6 +857,13 @@ MODULE_PARM_DESC(num_kcq, "number of kernel compute queue user want to setup (8 module_param_named(num_kcq, amdgpu_num_kcq, int, 0444); /** + * DOC: vcnfw_log (int) + * Enable vcnfw log output for debugging, the default is disabled. + */ +MODULE_PARM_DESC(vcnfw_log, "Enable vcnfw log(0 = disable (default value), 1 = enable)"); +module_param_named(vcnfw_log, amdgpu_vcnfw_log, int, 0444); + +/** * DOC: smu_pptable_id (int) * Used to override pptable id. id = 0 use VBIOS pptable. * id > 0 use the soft pptable with specicfied id. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 52912b6bcb20..8fe939976224 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -644,13 +644,6 @@ late_fini: return r; } -void amdgpu_gfx_ras_fini(struct amdgpu_device *adev) -{ - if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX) && - adev->gfx.ras_if) - amdgpu_ras_block_late_fini(adev, adev->gfx.ras_if); -} - int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev, void *err_data, struct amdgpu_iv_entry *entry) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index ccca0a85b982..dcb3c7871c73 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -387,7 +387,6 @@ bool amdgpu_gfx_is_me_queue_enabled(struct amdgpu_device *adev, int me, void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable); int amdgpu_get_gfx_off_status(struct amdgpu_device *adev, uint32_t *value); int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block); -void amdgpu_gfx_ras_fini(struct amdgpu_device *adev); int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev, void *err_data, struct amdgpu_iv_entry *entry); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 78498d1d1769..ca2cfb65f976 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -454,17 +454,7 @@ int amdgpu_gmc_ras_late_init(struct amdgpu_device *adev) void amdgpu_gmc_ras_fini(struct amdgpu_device *adev) { - if (adev->umc.ras && adev->umc.ras->ras_block.ras_fini) - adev->umc.ras->ras_block.ras_fini(adev); - if (adev->mmhub.ras && adev->mmhub.ras->ras_block.ras_fini) - adev->mmhub.ras->ras_block.ras_fini(adev); - - if (adev->gmc.xgmi.ras && adev->gmc.xgmi.ras->ras_block.ras_fini) - adev->gmc.xgmi.ras->ras_block.ras_fini(adev); - - if (adev->hdp.ras && adev->hdp.ras->ras_block.ras_fini) - adev->hdp.ras->ras_block.ras_fini(adev); } /* @@ -569,11 +559,11 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) { struct amdgpu_gmc *gmc = &adev->gmc; - switch (adev->asic_type) { - case CHIP_VEGA10: - case CHIP_VEGA20: - case CHIP_ARCTURUS: - case CHIP_ALDEBARAN: + switch (adev->ip_versions[GC_HWIP][0]) { + case IP_VERSION(9, 0, 1): + case IP_VERSION(9, 4, 0): + case IP_VERSION(9, 4, 1): + case IP_VERSION(9, 4, 2): /* * noretry = 0 will cause kfd page fault tests fail * for some ASICs, so set default to 1 for these ASICs. @@ -583,7 +573,6 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) else gmc->noretry = amdgpu_noretry; break; - case CHIP_RAVEN: default: /* Raven currently has issues with noretry * regardless of what we decide for other @@ -634,6 +623,13 @@ void amdgpu_gmc_get_vbios_allocations(struct amdgpu_device *adev) unsigned size; /* + * Some ASICs need to reserve a region of video memory to avoid access + * from driver + */ + adev->mman.stolen_reserved_offset = 0; + adev->mman.stolen_reserved_size = 0; + + /* * TODO: * Currently there is a bug where some memory client outside * of the driver writes to first 8M of VRAM on S3 resume, @@ -643,10 +639,25 @@ void amdgpu_gmc_get_vbios_allocations(struct amdgpu_device *adev) */ switch (adev->asic_type) { case CHIP_VEGA10: + adev->mman.keep_stolen_vga_memory = true; + /* + * VEGA10 SRIOV VF needs some firmware reserved area. + */ + if (amdgpu_sriov_vf(adev)) { + adev->mman.stolen_reserved_offset = 0x100000; + adev->mman.stolen_reserved_size = 0x600000; + } + break; case CHIP_RAVEN: case CHIP_RENOIR: adev->mman.keep_stolen_vga_memory = true; break; + case CHIP_YELLOW_CARP: + if (amdgpu_discovery == 0) { + adev->mman.stolen_reserved_offset = 0x1ffb0000; + adev->mman.stolen_reserved_size = 64 * PAGE_SIZE; + } + break; default: adev->mman.keep_stolen_vga_memory = false; break; @@ -767,25 +778,6 @@ uint64_t amdgpu_gmc_vram_cpu_pa(struct amdgpu_device *adev, struct amdgpu_bo *bo return amdgpu_bo_gpu_offset(bo) - adev->gmc.vram_start + adev->gmc.aper_base; } -void amdgpu_gmc_get_reserved_allocation(struct amdgpu_device *adev) -{ - /* Some ASICs need to reserve a region of video memory to avoid access - * from driver */ - adev->mman.stolen_reserved_offset = 0; - adev->mman.stolen_reserved_size = 0; - - switch (adev->asic_type) { - case CHIP_YELLOW_CARP: - if (amdgpu_discovery == 0) { - adev->mman.stolen_reserved_offset = 0x1ffb0000; - adev->mman.stolen_reserved_size = 64 * PAGE_SIZE; - } - break; - default: - break; - } -} - int amdgpu_gmc_vram_checking(struct amdgpu_device *adev) { struct amdgpu_bo *vram_bo = NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h index 93505bb0a36c..032b0313f277 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h @@ -331,7 +331,6 @@ amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type, bool enable); void amdgpu_gmc_get_vbios_allocations(struct amdgpu_device *adev); -void amdgpu_gmc_get_reserved_allocation(struct amdgpu_device *adev); void amdgpu_gmc_init_pdb0(struct amdgpu_device *adev); uint64_t amdgpu_gmc_vram_mc2pa(struct amdgpu_device *adev, uint64_t mc_addr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hdp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_hdp.h index aabd59aa5213..9181c7bef7c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hdp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hdp.h @@ -44,5 +44,4 @@ struct amdgpu_hdp { }; int amdgpu_hdp_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block); -void amdgpu_hdp_ras_fini(struct amdgpu_device *adev); #endif /* __AMDGPU_HDP_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index bc1297dcdf97..d583766ea392 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -166,8 +166,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, } if ((ib->flags & AMDGPU_IB_FLAGS_SECURE) && - (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE)) { - dev_err(adev->dev, "secure submissions not supported on compute rings\n"); + (!ring->funcs->secure_submission_supported)) { + dev_err(adev->dev, "secure submissions not supported on ring <%s>\n", ring->name); return -EINVAL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index be48487e2ca7..92a70fb57fa3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -204,7 +204,7 @@ static int amdgpu_vmid_grab_idle(struct amdgpu_vm *vm, unsigned i; int r; - if (ring->vmid_wait && !dma_fence_is_signaled(ring->vmid_wait)) + if (!dma_fence_is_signaled(ring->vmid_wait)) return amdgpu_sync_fence(sync, ring->vmid_wait); fences = kmalloc_array(id_mgr->num_ids, sizeof(void *), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index d970336d2261..67f66f2f1809 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -81,14 +81,10 @@ exit: int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs, struct amdgpu_job **job, struct amdgpu_vm *vm) { - size_t size = sizeof(struct amdgpu_job); - if (num_ibs == 0) return -EINVAL; - size += sizeof(struct amdgpu_ib) * num_ibs; - - *job = kzalloc(size, GFP_KERNEL); + *job = kzalloc(struct_size(*job, ibs, num_ibs), GFP_KERNEL); if (!*job) return -ENOMEM; @@ -98,7 +94,6 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs, */ (*job)->base.sched = &adev->rings[0]->sched; (*job)->vm = vm; - (*job)->ibs = (void *)&(*job)[1]; (*job)->num_ibs = num_ibs; amdgpu_sync_create(&(*job)->sync); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h index 9e65730193b8..d599c0540b46 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h @@ -23,6 +23,10 @@ #ifndef __AMDGPU_JOB_H__ #define __AMDGPU_JOB_H__ +#include <drm/gpu_scheduler.h> +#include "amdgpu_sync.h" +#include "amdgpu_ring.h" + /* bit set means command submit involves a preamble IB */ #define AMDGPU_PREAMBLE_IB_PRESENT (1 << 0) /* bit set means preamble IB is first presented in belonging context */ @@ -45,12 +49,10 @@ struct amdgpu_job { struct amdgpu_vm *vm; struct amdgpu_sync sync; struct amdgpu_sync sched_sync; - struct amdgpu_ib *ibs; struct dma_fence hw_fence; struct dma_fence *external_hw_fence; uint32_t preamble_status; uint32_t preemption_status; - uint32_t num_ibs; bool vm_needs_flush; uint64_t vm_pd_addr; unsigned vmid; @@ -66,6 +68,9 @@ struct amdgpu_job { /* job_run_counter >= 1 means a resubmit job */ uint32_t job_run_counter; + + uint32_t num_ibs; + struct amdgpu_ib ibs[]; }; int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c index e2607d9f5cf4..51c2a82e2fa4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c @@ -70,9 +70,3 @@ void amdgpu_mca_query_ras_error_count(struct amdgpu_device *adev, amdgpu_mca_reset_error_count(adev, mc_status_addr); } - -void amdgpu_mca_ras_fini(struct amdgpu_device *adev, - struct amdgpu_mca_ras *mca_dev) -{ - amdgpu_ras_block_late_fini(adev, mca_dev->ras_if); -}
\ No newline at end of file diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h index 15e1a1efeb4f..7ce16d16e34b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h @@ -56,7 +56,4 @@ void amdgpu_mca_query_ras_error_count(struct amdgpu_device *adev, uint64_t mc_status_addr, void *ras_error_status); -void amdgpu_mca_ras_fini(struct amdgpu_device *adev, - struct amdgpu_mca_ras *mca_dev); - #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h index 240b26d9a388..9f1540f0ebf9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h @@ -47,6 +47,5 @@ struct amdgpu_mmhub { struct amdgpu_mmhub_ras *ras; }; -void amdgpu_mmhub_ras_fini(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c index f09ad80f0772..37d779b8e4a6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c @@ -43,10 +43,3 @@ late_fini: amdgpu_ras_block_late_fini(adev, ras_block); return r; } - -void amdgpu_nbio_ras_fini(struct amdgpu_device *adev) -{ - if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__PCIE_BIF) && - adev->nbio.ras_if) - amdgpu_ras_block_late_fini(adev, adev->nbio.ras_if); -} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h index f9546c7341b8..3d13e601fc35 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h @@ -105,5 +105,4 @@ struct amdgpu_nbio { }; int amdgpu_nbio_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block); -void amdgpu_nbio_ras_fini(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 94bfe502b55e..a6acec1a6155 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -277,7 +277,7 @@ static int psp_init_sriov_microcode(struct psp_context *psp) ret = psp_init_cap_microcode(psp, "sienna_cichlid"); break; case IP_VERSION(13, 0, 2): - ret = psp_init_ta_microcode(psp, "aldebaran"); + ret = psp_init_cap_microcode(psp, "aldebaran"); break; default: BUG(); @@ -310,6 +310,10 @@ static int psp_sw_init(void *handle) return ret; } + adev->psp.xgmi_context.supports_extended_data = + !adev->gmc.xgmi.connected_to_cpu && + adev->ip_versions[MP0_HWIP][0] == IP_VERSION(13, 0, 2); + memset(&boot_cfg_entry, 0, sizeof(boot_cfg_entry)); if (psp_get_runtime_db_entry(adev, PSP_RUNTIME_ENTRY_TYPE_BOOT_CONFIG, @@ -3008,7 +3012,6 @@ static int psp_init_sos_base_fw(struct amdgpu_device *adev) adev->psp.sos.size_bytes = le32_to_cpu(sos_hdr->sos.size_bytes); adev->psp.sos.start_addr = ucode_array_start_addr + le32_to_cpu(sos_hdr->sos.offset_bytes); - adev->psp.xgmi_context.supports_extended_data = false; } else { /* Load alternate PSP SOS FW */ sos_hdr_v1_3 = (const struct psp_firmware_header_v1_3 *)adev->psp.sos_fw->data; @@ -3023,7 +3026,6 @@ static int psp_init_sos_base_fw(struct amdgpu_device *adev) adev->psp.sos.size_bytes = le32_to_cpu(sos_hdr_v1_3->sos_aux.size_bytes); adev->psp.sos.start_addr = ucode_array_start_addr + le32_to_cpu(sos_hdr_v1_3->sos_aux.offset_bytes); - adev->psp.xgmi_context.supports_extended_data = true; } if ((adev->psp.sys.size_bytes == 0) || (adev->psp.sos.size_bytes == 0)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index b53abc15a830..424c22a841f4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -2068,6 +2068,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev) mutex_init(&con->recovery_lock); INIT_WORK(&con->recovery_work, amdgpu_ras_do_recovery); atomic_set(&con->in_recovery, 0); + con->eeprom_control.bad_channel_bitmap = 0; max_eeprom_records_count = amdgpu_ras_eeprom_max_record_count(); amdgpu_ras_validate_threshold(adev, max_eeprom_records_count); @@ -2092,6 +2093,11 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev) goto free; amdgpu_dpm_send_hbm_bad_pages_num(adev, con->eeprom_control.ras_num_recs); + + if (con->update_channel_flag == true) { + amdgpu_dpm_send_hbm_bad_channel_flag(adev, con->eeprom_control.bad_channel_bitmap); + con->update_channel_flag = false; + } } #ifdef CONFIG_X86_MCE_AMD @@ -2285,6 +2291,7 @@ int amdgpu_ras_init(struct amdgpu_device *adev) goto release_con; } + con->update_channel_flag = false; con->features = 0; INIT_LIST_HEAD(&con->head); /* Might need get this flag from vbios. */ @@ -2477,6 +2484,12 @@ void amdgpu_ras_block_late_fini(struct amdgpu_device *adev, amdgpu_ras_interrupt_remove_handler(adev, ras_block); } +static void amdgpu_ras_block_late_fini_default(struct amdgpu_device *adev, + struct ras_common_if *ras_block) +{ + return amdgpu_ras_block_late_fini(adev, ras_block); +} + /* do some init work after IP late init as dependence. * and it runs in resume/gpu reset/booting up cases. */ @@ -2572,11 +2585,27 @@ int amdgpu_ras_pre_fini(struct amdgpu_device *adev) int amdgpu_ras_fini(struct amdgpu_device *adev) { struct amdgpu_ras_block_list *ras_node, *tmp; + struct amdgpu_ras_block_object *obj = NULL; struct amdgpu_ras *con = amdgpu_ras_get_context(adev); if (!adev->ras_enabled || !con) return 0; + list_for_each_entry_safe(ras_node, tmp, &adev->ras_list, node) { + if (ras_node->ras_obj) { + obj = ras_node->ras_obj; + if (amdgpu_ras_is_supported(adev, obj->ras_comm.block) && + obj->ras_fini) + obj->ras_fini(adev, &obj->ras_comm); + else + amdgpu_ras_block_late_fini_default(adev, &obj->ras_comm); + } + + /* Clear ras blocks from ras_list and free ras block list node */ + list_del(&ras_node->node); + kfree(ras_node); + } + amdgpu_ras_fs_fini(adev); amdgpu_ras_interrupt_remove_all(adev); @@ -2590,12 +2619,6 @@ int amdgpu_ras_fini(struct amdgpu_device *adev) amdgpu_ras_set_context(adev, NULL); kfree(con); - /* Clear ras blocks from ras_list and free ras block list node */ - list_for_each_entry_safe(ras_node, tmp, &adev->ras_list, node) { - list_del(&ras_node->node); - kfree(ras_node); - } - return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h index 143a83043d7c..9314fde81e68 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h @@ -374,6 +374,9 @@ struct amdgpu_ras { /* record umc error info queried from smu */ struct umc_ecc_info umc_ecc; + + /* Indicates smu whether need update bad channel info */ + bool update_channel_flag; }; struct ras_fs_data { @@ -491,7 +494,7 @@ struct amdgpu_ras_block_object { int (*ras_block_match)(struct amdgpu_ras_block_object *block_obj, enum amdgpu_ras_block block, uint32_t sub_block_index); int (*ras_late_init)(struct amdgpu_device *adev, struct ras_common_if *ras_block); - void (*ras_fini)(struct amdgpu_device *adev); + void (*ras_fini)(struct amdgpu_device *adev, struct ras_common_if *ras_block); ras_ih_cb ras_cb; const struct amdgpu_ras_block_hw_ops *hw_ops; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index a44f2eeed6ef..c4283987bb1e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -267,6 +267,7 @@ int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control) { struct amdgpu_device *adev = to_amdgpu_device(control); struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr; + struct amdgpu_ras *con = amdgpu_ras_get_context(adev); u8 csum; int res; @@ -287,6 +288,10 @@ int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control) amdgpu_dpm_send_hbm_bad_pages_num(adev, control->ras_num_recs); + control->bad_channel_bitmap = 0; + amdgpu_dpm_send_hbm_bad_channel_flag(adev, control->bad_channel_bitmap); + con->update_channel_flag = false; + amdgpu_ras_debugfs_set_ret_size(control); mutex_unlock(&control->ras_tbl_mutex); @@ -420,6 +425,7 @@ amdgpu_ras_eeprom_append_table(struct amdgpu_ras_eeprom_control *control, struct eeprom_table_record *record, const u32 num) { + struct amdgpu_ras *con = amdgpu_ras_get_context(to_amdgpu_device(control)); u32 a, b, i; u8 *buf, *pp; int res; @@ -431,9 +437,16 @@ amdgpu_ras_eeprom_append_table(struct amdgpu_ras_eeprom_control *control, /* Encode all of them in one go. */ pp = buf; - for (i = 0; i < num; i++, pp += RAS_TABLE_RECORD_SIZE) + for (i = 0; i < num; i++, pp += RAS_TABLE_RECORD_SIZE) { __encode_table_record_to_buf(control, &record[i], pp); + /* update bad channel bitmap */ + if (!(control->bad_channel_bitmap & (1 << record[i].mem_channel))) { + control->bad_channel_bitmap |= 1 << record[i].mem_channel; + con->update_channel_flag = true; + } + } + /* a, first record index to write into. * b, last record index to write into. * a = first index to read (fri) + number of records in the table, @@ -686,6 +699,7 @@ int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control, const u32 num) { struct amdgpu_device *adev = to_amdgpu_device(control); + struct amdgpu_ras *con = amdgpu_ras_get_context(adev); int i, res; u8 *buf, *pp; u32 g0, g1; @@ -753,8 +767,15 @@ int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control, /* Read up everything? Then transform. */ pp = buf; - for (i = 0; i < num; i++, pp += RAS_TABLE_RECORD_SIZE) + for (i = 0; i < num; i++, pp += RAS_TABLE_RECORD_SIZE) { __decode_table_record_from_buf(control, &record[i], pp); + + /* update bad channel bitmap */ + if (!(control->bad_channel_bitmap & (1 << record[i].mem_channel))) { + control->bad_channel_bitmap |= 1 << record[i].mem_channel; + con->update_channel_flag = true; + } + } Out: kfree(buf); mutex_unlock(&control->ras_tbl_mutex); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h index 6bb00578bfbb..54d9bfe0881d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h @@ -80,6 +80,10 @@ struct amdgpu_ras_eeprom_control { /* Protect table access via this mutex. */ struct mutex ras_tbl_mutex; + + /* Record channel info which occurred bad pages + */ + u32 bad_channel_bitmap; }; /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c index 248d64158721..c80af0889773 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c @@ -36,8 +36,8 @@ int amdgpu_reset_init(struct amdgpu_device *adev) { int ret = 0; - switch (adev->asic_type) { - case CHIP_ALDEBARAN: + switch (adev->ip_versions[MP1_HWIP][0]) { + case IP_VERSION(13, 0, 2): ret = aldebaran_reset_init(adev); break; default: @@ -51,8 +51,8 @@ int amdgpu_reset_fini(struct amdgpu_device *adev) { int ret = 0; - switch (adev->asic_type) { - case CHIP_ALDEBARAN: + switch (adev->ip_versions[MP1_HWIP][0]) { + case IP_VERSION(13, 0, 2): ret = aldebaran_reset_fini(adev); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 35bcb6dc1816..7f33ae87cb41 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -193,6 +193,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, adev->rings[ring->idx] = ring; ring->num_hw_submission = sched_hw_submission; ring->sched_score = sched_score; + ring->vmid_wait = dma_fence_get_stub(); r = amdgpu_fence_driver_init_ring(ring); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 48365da213dc..5320bb0883d8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -28,6 +28,13 @@ #include <drm/gpu_scheduler.h> #include <drm/drm_print.h> +struct amdgpu_device; +struct amdgpu_ring; +struct amdgpu_ib; +struct amdgpu_cs_parser; +struct amdgpu_job; +struct amdgpu_vm; + /* max number of rings */ #define AMDGPU_MAX_RINGS 28 #define AMDGPU_MAX_HWIP_RINGS 8 @@ -82,11 +89,13 @@ enum amdgpu_ib_pool_type { AMDGPU_IB_POOL_MAX }; -struct amdgpu_device; -struct amdgpu_ring; -struct amdgpu_ib; -struct amdgpu_cs_parser; -struct amdgpu_job; +struct amdgpu_ib { + struct amdgpu_sa_bo *sa_bo; + uint32_t length_dw; + uint64_t gpu_addr; + uint32_t *ptr; + uint32_t flags; +}; struct amdgpu_sched { u32 num_scheds; @@ -111,6 +120,8 @@ struct amdgpu_fence_driver { struct dma_fence **fences; }; +extern const struct drm_sched_backend_ops amdgpu_sched_ops; + void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring); void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring); @@ -144,6 +155,7 @@ struct amdgpu_ring_funcs { u32 nop; bool support_64bit_ptrs; bool no_user_fence; + bool secure_submission_supported; unsigned vmhub; unsigned extra_dw; @@ -152,8 +164,12 @@ struct amdgpu_ring_funcs { u64 (*get_wptr)(struct amdgpu_ring *ring); void (*set_wptr)(struct amdgpu_ring *ring); /* validating and patching of IBs */ - int (*parse_cs)(struct amdgpu_cs_parser *p, uint32_t ib_idx); - int (*patch_cs_in_place)(struct amdgpu_cs_parser *p, uint32_t ib_idx); + int (*parse_cs)(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib); + int (*patch_cs_in_place)(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib); /* constants to calculate how many DW are needed for an emit */ unsigned emit_frame_size; unsigned emit_ib_size; @@ -253,8 +269,8 @@ struct amdgpu_ring { atomic_t *sched_score; }; -#define amdgpu_ring_parse_cs(r, p, ib) ((r)->funcs->parse_cs((p), (ib))) -#define amdgpu_ring_patch_cs_in_place(r, p, ib) ((r)->funcs->patch_cs_in_place((p), (ib))) +#define amdgpu_ring_parse_cs(r, p, job, ib) ((r)->funcs->parse_cs((p), (job), (ib))) +#define amdgpu_ring_patch_cs_in_place(r, p, job, ib) ((r)->funcs->patch_cs_in_place((p), (job), (ib))) #define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r)) #define amdgpu_ring_test_ib(r, t) (r)->funcs->test_ib((r), (t)) #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r)) @@ -352,4 +368,29 @@ int amdgpu_ring_test_helper(struct amdgpu_ring *ring); void amdgpu_debugfs_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring); + +static inline u32 amdgpu_ib_get_value(struct amdgpu_ib *ib, int idx) +{ + return ib->ptr[idx]; +} + +static inline void amdgpu_ib_set_value(struct amdgpu_ib *ib, int idx, + uint32_t value) +{ + ib->ptr[idx] = value; +} + +int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm, + unsigned size, + enum amdgpu_ib_pool_type pool, + struct amdgpu_ib *ib); +void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib, + struct dma_fence *f); +int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, + struct amdgpu_ib *ibs, struct amdgpu_job *job, + struct dma_fence **f); +int amdgpu_ib_pool_init(struct amdgpu_device *adev); +void amdgpu_ib_pool_fini(struct amdgpu_device *adev); +int amdgpu_ib_ring_tests(struct amdgpu_device *adev); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c index 3b5c43575aa3..e1835fd4b237 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c @@ -111,13 +111,6 @@ late_fini: return r; } -void amdgpu_sdma_ras_fini(struct amdgpu_device *adev) -{ - if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA) && - adev->sdma.ras_if) - amdgpu_ras_block_late_fini(adev, adev->sdma.ras_if); -} - int amdgpu_sdma_process_ras_data_cb(struct amdgpu_device *adev, void *err_data, struct amdgpu_iv_entry *entry) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h index 8b226ffee32c..53ac3ebae8d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h @@ -118,7 +118,6 @@ int amdgpu_sdma_get_index_from_ring(struct amdgpu_ring *ring, uint32_t *index); uint64_t amdgpu_sdma_get_csa_mc_addr(struct amdgpu_ring *ring, unsigned vmid); int amdgpu_sdma_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block); -void amdgpu_sdma_ras_fini(struct amdgpu_device *adev); int amdgpu_sdma_process_ras_data_cb(struct amdgpu_device *adev, void *err_data, struct amdgpu_iv_entry *entry); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace_points.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace_points.c index 57c6c39ba064..b96d885f6e33 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace_points.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace_points.c @@ -23,6 +23,7 @@ */ #include <drm/amdgpu_drm.h> +#include "amdgpu_cs.h" #include "amdgpu.h" #define CREATE_TRACE_POINTS diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 428f4df184d0..40dffbac85a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -343,7 +343,8 @@ union amdgpu_firmware_header { * fw loading support */ enum AMDGPU_UCODE_ID { - AMDGPU_UCODE_ID_SDMA0 = 0, + AMDGPU_UCODE_ID_CAP = 0, + AMDGPU_UCODE_ID_SDMA0, AMDGPU_UCODE_ID_SDMA1, AMDGPU_UCODE_ID_SDMA2, AMDGPU_UCODE_ID_SDMA3, @@ -378,7 +379,6 @@ enum AMDGPU_UCODE_ID { AMDGPU_UCODE_ID_VCN0_RAM, AMDGPU_UCODE_ID_VCN1_RAM, AMDGPU_UCODE_ID_DMCUB, - AMDGPU_UCODE_ID_CAP, AMDGPU_UCODE_ID_MAXIMUM, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c index 9400260e3263..aad3c8b4c810 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c @@ -97,6 +97,11 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev, amdgpu_ras_save_bad_pages(adev); amdgpu_dpm_send_hbm_bad_pages_num(adev, con->eeprom_control.ras_num_recs); + + if (con->update_channel_flag == true) { + amdgpu_dpm_send_hbm_bad_channel_flag(adev, con->eeprom_control.bad_channel_bitmap); + con->update_channel_flag = false; + } } if (reset) @@ -162,13 +167,6 @@ late_fini: return r; } -void amdgpu_umc_ras_fini(struct amdgpu_device *adev) -{ - if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC) && - adev->umc.ras_if) - amdgpu_ras_block_late_fini(adev, adev->umc.ras_if); -} - int amdgpu_umc_process_ecc_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h index e4b3678a6685..2ec6698aa1fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h @@ -73,7 +73,6 @@ struct amdgpu_umc { }; int amdgpu_umc_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block); -void amdgpu_umc_ras_fini(struct amdgpu_device *adev); int amdgpu_umc_poison_handler(struct amdgpu_device *adev, void *ras_error_status, bool reset); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 9cc23b220537..39c74d9fa7cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -37,6 +37,7 @@ #include "amdgpu.h" #include "amdgpu_pm.h" #include "amdgpu_uvd.h" +#include "amdgpu_cs.h" #include "cikd.h" #include "uvd/uvd_4_2_d.h" @@ -98,7 +99,7 @@ struct amdgpu_uvd_cs_ctx { unsigned reg, count; unsigned data0, data1; unsigned idx; - unsigned ib_idx; + struct amdgpu_ib *ib; /* does the IB has a msg command */ bool has_msg_cmd; @@ -557,8 +558,8 @@ static u64 amdgpu_uvd_get_addr_from_ctx(struct amdgpu_uvd_cs_ctx *ctx) uint32_t lo, hi; uint64_t addr; - lo = amdgpu_get_ib_value(ctx->parser, ctx->ib_idx, ctx->data0); - hi = amdgpu_get_ib_value(ctx->parser, ctx->ib_idx, ctx->data1); + lo = amdgpu_ib_get_value(ctx->ib, ctx->data0); + hi = amdgpu_ib_get_value(ctx->ib, ctx->data1); addr = ((uint64_t)lo) | (((uint64_t)hi) << 32); return addr; @@ -589,7 +590,7 @@ static int amdgpu_uvd_cs_pass1(struct amdgpu_uvd_cs_ctx *ctx) if (!ctx->parser->adev->uvd.address_64_bit) { /* check if it's a message or feedback command */ - cmd = amdgpu_get_ib_value(ctx->parser, ctx->ib_idx, ctx->idx) >> 1; + cmd = amdgpu_ib_get_value(ctx->ib, ctx->idx) >> 1; if (cmd == 0x0 || cmd == 0x3) { /* yes, force it into VRAM */ uint32_t domain = AMDGPU_GEM_DOMAIN_VRAM; @@ -927,12 +928,10 @@ static int amdgpu_uvd_cs_pass2(struct amdgpu_uvd_cs_ctx *ctx) addr -= mapping->start * AMDGPU_GPU_PAGE_SIZE; start += addr; - amdgpu_set_ib_value(ctx->parser, ctx->ib_idx, ctx->data0, - lower_32_bits(start)); - amdgpu_set_ib_value(ctx->parser, ctx->ib_idx, ctx->data1, - upper_32_bits(start)); + amdgpu_ib_set_value(ctx->ib, ctx->data0, lower_32_bits(start)); + amdgpu_ib_set_value(ctx->ib, ctx->data1, upper_32_bits(start)); - cmd = amdgpu_get_ib_value(ctx->parser, ctx->ib_idx, ctx->idx) >> 1; + cmd = amdgpu_ib_get_value(ctx->ib, ctx->idx) >> 1; if (cmd < 0x4) { if ((end - start) < ctx->buf_sizes[cmd]) { DRM_ERROR("buffer (%d) to small (%d / %d)!\n", cmd, @@ -992,14 +991,13 @@ static int amdgpu_uvd_cs_pass2(struct amdgpu_uvd_cs_ctx *ctx) static int amdgpu_uvd_cs_reg(struct amdgpu_uvd_cs_ctx *ctx, int (*cb)(struct amdgpu_uvd_cs_ctx *ctx)) { - struct amdgpu_ib *ib = &ctx->parser->job->ibs[ctx->ib_idx]; int i, r; ctx->idx++; for (i = 0; i <= ctx->count; ++i) { unsigned reg = ctx->reg + i; - if (ctx->idx >= ib->length_dw) { + if (ctx->idx >= ctx->ib->length_dw) { DRM_ERROR("Register command after end of CS!\n"); return -EINVAL; } @@ -1039,11 +1037,10 @@ static int amdgpu_uvd_cs_reg(struct amdgpu_uvd_cs_ctx *ctx, static int amdgpu_uvd_cs_packets(struct amdgpu_uvd_cs_ctx *ctx, int (*cb)(struct amdgpu_uvd_cs_ctx *ctx)) { - struct amdgpu_ib *ib = &ctx->parser->job->ibs[ctx->ib_idx]; int r; - for (ctx->idx = 0 ; ctx->idx < ib->length_dw; ) { - uint32_t cmd = amdgpu_get_ib_value(ctx->parser, ctx->ib_idx, ctx->idx); + for (ctx->idx = 0 ; ctx->idx < ctx->ib->length_dw; ) { + uint32_t cmd = amdgpu_ib_get_value(ctx->ib, ctx->idx); unsigned type = CP_PACKET_GET_TYPE(cmd); switch (type) { case PACKET_TYPE0: @@ -1068,11 +1065,14 @@ static int amdgpu_uvd_cs_packets(struct amdgpu_uvd_cs_ctx *ctx, * amdgpu_uvd_ring_parse_cs - UVD command submission parser * * @parser: Command submission parser context - * @ib_idx: Which indirect buffer to use + * @job: the job to parse + * @ib: the IB to patch * * Parse the command stream, patch in addresses as necessary. */ -int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx) +int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib) { struct amdgpu_uvd_cs_ctx ctx = {}; unsigned buf_sizes[] = { @@ -1082,10 +1082,9 @@ int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx) [0x00000003] = 2048, [0x00000004] = 0xFFFFFFFF, }; - struct amdgpu_ib *ib = &parser->job->ibs[ib_idx]; int r; - parser->job->vm = NULL; + job->vm = NULL; ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo); if (ib->length_dw % 16) { @@ -1096,7 +1095,7 @@ int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx) ctx.parser = parser; ctx.buf_sizes = buf_sizes; - ctx.ib_idx = ib_idx; + ctx.ib = ib; /* first round only required on chips without UVD 64 bit address support */ if (!parser->adev->uvd.address_64_bit) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h index 76ac9699885d..9f89bb7cd60b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h @@ -82,7 +82,9 @@ int amdgpu_uvd_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, bool direct, struct dma_fence **fence); void amdgpu_uvd_free_handles(struct amdgpu_device *adev, struct drm_file *filp); -int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx); +int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib); void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring); void amdgpu_uvd_ring_end_use(struct amdgpu_ring *ring); int amdgpu_uvd_ring_test_ib(struct amdgpu_ring *ring, long timeout); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 344f711ad144..02cb3a12dd76 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -34,6 +34,7 @@ #include "amdgpu.h" #include "amdgpu_pm.h" #include "amdgpu_vce.h" +#include "amdgpu_cs.h" #include "cikd.h" /* 1 second timeout */ @@ -587,8 +588,7 @@ err: /** * amdgpu_vce_validate_bo - make sure not to cross 4GB boundary * - * @p: parser context - * @ib_idx: indirect buffer to use + * @ib: indirect buffer to use * @lo: address of lower dword * @hi: address of higher dword * @size: minimum size @@ -596,8 +596,9 @@ err: * * Make sure that no BO cross a 4GB boundary. */ -static int amdgpu_vce_validate_bo(struct amdgpu_cs_parser *p, uint32_t ib_idx, - int lo, int hi, unsigned size, int32_t index) +static int amdgpu_vce_validate_bo(struct amdgpu_cs_parser *p, + struct amdgpu_ib *ib, int lo, int hi, + unsigned size, int32_t index) { int64_t offset = ((uint64_t)size) * ((int64_t)index); struct ttm_operation_ctx ctx = { false, false }; @@ -607,8 +608,8 @@ static int amdgpu_vce_validate_bo(struct amdgpu_cs_parser *p, uint32_t ib_idx, uint64_t addr; int r; - addr = ((uint64_t)amdgpu_get_ib_value(p, ib_idx, lo)) | - ((uint64_t)amdgpu_get_ib_value(p, ib_idx, hi)) << 32; + addr = ((uint64_t)amdgpu_ib_get_value(ib, lo)) | + ((uint64_t)amdgpu_ib_get_value(ib, hi)) << 32; if (index >= 0) { addr += offset; fpfn = PAGE_ALIGN(offset) >> PAGE_SHIFT; @@ -638,7 +639,7 @@ static int amdgpu_vce_validate_bo(struct amdgpu_cs_parser *p, uint32_t ib_idx, * amdgpu_vce_cs_reloc - command submission relocation * * @p: parser context - * @ib_idx: indirect buffer to use + * @ib: indirect buffer to use * @lo: address of lower dword * @hi: address of higher dword * @size: minimum size @@ -646,7 +647,7 @@ static int amdgpu_vce_validate_bo(struct amdgpu_cs_parser *p, uint32_t ib_idx, * * Patch relocation inside command stream with real buffer address */ -static int amdgpu_vce_cs_reloc(struct amdgpu_cs_parser *p, uint32_t ib_idx, +static int amdgpu_vce_cs_reloc(struct amdgpu_cs_parser *p, struct amdgpu_ib *ib, int lo, int hi, unsigned size, uint32_t index) { struct amdgpu_bo_va_mapping *mapping; @@ -657,8 +658,8 @@ static int amdgpu_vce_cs_reloc(struct amdgpu_cs_parser *p, uint32_t ib_idx, if (index == 0xffffffff) index = 0; - addr = ((uint64_t)amdgpu_get_ib_value(p, ib_idx, lo)) | - ((uint64_t)amdgpu_get_ib_value(p, ib_idx, hi)) << 32; + addr = ((uint64_t)amdgpu_ib_get_value(ib, lo)) | + ((uint64_t)amdgpu_ib_get_value(ib, hi)) << 32; addr += ((uint64_t)size) * ((uint64_t)index); r = amdgpu_cs_find_mapping(p, addr, &bo, &mapping); @@ -679,8 +680,8 @@ static int amdgpu_vce_cs_reloc(struct amdgpu_cs_parser *p, uint32_t ib_idx, addr += amdgpu_bo_gpu_offset(bo); addr -= ((uint64_t)size) * ((uint64_t)index); - amdgpu_set_ib_value(p, ib_idx, lo, lower_32_bits(addr)); - amdgpu_set_ib_value(p, ib_idx, hi, upper_32_bits(addr)); + amdgpu_ib_set_value(ib, lo, lower_32_bits(addr)); + amdgpu_ib_set_value(ib, hi, upper_32_bits(addr)); return 0; } @@ -729,11 +730,13 @@ static int amdgpu_vce_validate_handle(struct amdgpu_cs_parser *p, * amdgpu_vce_ring_parse_cs - parse and validate the command stream * * @p: parser context - * @ib_idx: indirect buffer to use + * @job: the job to parse + * @ib: the IB to patch */ -int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) +int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib) { - struct amdgpu_ib *ib = &p->job->ibs[ib_idx]; unsigned fb_idx = 0, bs_idx = 0; int session_idx = -1; uint32_t destroyed = 0; @@ -744,12 +747,12 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) unsigned idx; int i, r = 0; - p->job->vm = NULL; + job->vm = NULL; ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo); for (idx = 0; idx < ib->length_dw;) { - uint32_t len = amdgpu_get_ib_value(p, ib_idx, idx); - uint32_t cmd = amdgpu_get_ib_value(p, ib_idx, idx + 1); + uint32_t len = amdgpu_ib_get_value(ib, idx); + uint32_t cmd = amdgpu_ib_get_value(ib, idx + 1); if ((len < 8) || (len & 3)) { DRM_ERROR("invalid VCE command length (%d)!\n", len); @@ -759,52 +762,52 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) switch (cmd) { case 0x00000002: /* task info */ - fb_idx = amdgpu_get_ib_value(p, ib_idx, idx + 6); - bs_idx = amdgpu_get_ib_value(p, ib_idx, idx + 7); + fb_idx = amdgpu_ib_get_value(ib, idx + 6); + bs_idx = amdgpu_ib_get_value(ib, idx + 7); break; case 0x03000001: /* encode */ - r = amdgpu_vce_validate_bo(p, ib_idx, idx + 10, - idx + 9, 0, 0); + r = amdgpu_vce_validate_bo(p, ib, idx + 10, idx + 9, + 0, 0); if (r) goto out; - r = amdgpu_vce_validate_bo(p, ib_idx, idx + 12, - idx + 11, 0, 0); + r = amdgpu_vce_validate_bo(p, ib, idx + 12, idx + 11, + 0, 0); if (r) goto out; break; case 0x05000001: /* context buffer */ - r = amdgpu_vce_validate_bo(p, ib_idx, idx + 3, - idx + 2, 0, 0); + r = amdgpu_vce_validate_bo(p, ib, idx + 3, idx + 2, + 0, 0); if (r) goto out; break; case 0x05000004: /* video bitstream buffer */ - tmp = amdgpu_get_ib_value(p, ib_idx, idx + 4); - r = amdgpu_vce_validate_bo(p, ib_idx, idx + 3, idx + 2, + tmp = amdgpu_ib_get_value(ib, idx + 4); + r = amdgpu_vce_validate_bo(p, ib, idx + 3, idx + 2, tmp, bs_idx); if (r) goto out; break; case 0x05000005: /* feedback buffer */ - r = amdgpu_vce_validate_bo(p, ib_idx, idx + 3, idx + 2, + r = amdgpu_vce_validate_bo(p, ib, idx + 3, idx + 2, 4096, fb_idx); if (r) goto out; break; case 0x0500000d: /* MV buffer */ - r = amdgpu_vce_validate_bo(p, ib_idx, idx + 3, - idx + 2, 0, 0); + r = amdgpu_vce_validate_bo(p, ib, idx + 3, idx + 2, + 0, 0); if (r) goto out; - r = amdgpu_vce_validate_bo(p, ib_idx, idx + 8, - idx + 7, 0, 0); + r = amdgpu_vce_validate_bo(p, ib, idx + 8, idx + 7, + 0, 0); if (r) goto out; break; @@ -814,12 +817,12 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) } for (idx = 0; idx < ib->length_dw;) { - uint32_t len = amdgpu_get_ib_value(p, ib_idx, idx); - uint32_t cmd = amdgpu_get_ib_value(p, ib_idx, idx + 1); + uint32_t len = amdgpu_ib_get_value(ib, idx); + uint32_t cmd = amdgpu_ib_get_value(ib, idx + 1); switch (cmd) { case 0x00000001: /* session */ - handle = amdgpu_get_ib_value(p, ib_idx, idx + 2); + handle = amdgpu_ib_get_value(ib, idx + 2); session_idx = amdgpu_vce_validate_handle(p, handle, &allocated); if (session_idx < 0) { @@ -830,8 +833,8 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) break; case 0x00000002: /* task info */ - fb_idx = amdgpu_get_ib_value(p, ib_idx, idx + 6); - bs_idx = amdgpu_get_ib_value(p, ib_idx, idx + 7); + fb_idx = amdgpu_ib_get_value(ib, idx + 6); + bs_idx = amdgpu_ib_get_value(ib, idx + 7); break; case 0x01000001: /* create */ @@ -846,8 +849,8 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) goto out; } - *size = amdgpu_get_ib_value(p, ib_idx, idx + 8) * - amdgpu_get_ib_value(p, ib_idx, idx + 10) * + *size = amdgpu_ib_get_value(ib, idx + 8) * + amdgpu_ib_get_value(ib, idx + 10) * 8 * 3 / 2; break; @@ -876,12 +879,12 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) break; case 0x03000001: /* encode */ - r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 10, idx + 9, + r = amdgpu_vce_cs_reloc(p, ib, idx + 10, idx + 9, *size, 0); if (r) goto out; - r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 12, idx + 11, + r = amdgpu_vce_cs_reloc(p, ib, idx + 12, idx + 11, *size / 3, 0); if (r) goto out; @@ -892,35 +895,35 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) break; case 0x05000001: /* context buffer */ - r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2, + r = amdgpu_vce_cs_reloc(p, ib, idx + 3, idx + 2, *size * 2, 0); if (r) goto out; break; case 0x05000004: /* video bitstream buffer */ - tmp = amdgpu_get_ib_value(p, ib_idx, idx + 4); - r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2, + tmp = amdgpu_ib_get_value(ib, idx + 4); + r = amdgpu_vce_cs_reloc(p, ib, idx + 3, idx + 2, tmp, bs_idx); if (r) goto out; break; case 0x05000005: /* feedback buffer */ - r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2, + r = amdgpu_vce_cs_reloc(p, ib, idx + 3, idx + 2, 4096, fb_idx); if (r) goto out; break; case 0x0500000d: /* MV buffer */ - r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, - idx + 2, *size, 0); + r = amdgpu_vce_cs_reloc(p, ib, idx + 3, + idx + 2, *size, 0); if (r) goto out; - r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 8, - idx + 7, *size / 12, 0); + r = amdgpu_vce_cs_reloc(p, ib, idx + 8, + idx + 7, *size / 12, 0); if (r) goto out; break; @@ -965,11 +968,13 @@ out: * amdgpu_vce_ring_parse_cs_vm - parse the command stream in VM mode * * @p: parser context - * @ib_idx: indirect buffer to use + * @job: the job to parse + * @ib: the IB to patch */ -int amdgpu_vce_ring_parse_cs_vm(struct amdgpu_cs_parser *p, uint32_t ib_idx) +int amdgpu_vce_ring_parse_cs_vm(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib) { - struct amdgpu_ib *ib = &p->job->ibs[ib_idx]; int session_idx = -1; uint32_t destroyed = 0; uint32_t created = 0; @@ -978,8 +983,8 @@ int amdgpu_vce_ring_parse_cs_vm(struct amdgpu_cs_parser *p, uint32_t ib_idx) int i, r = 0, idx = 0; while (idx < ib->length_dw) { - uint32_t len = amdgpu_get_ib_value(p, ib_idx, idx); - uint32_t cmd = amdgpu_get_ib_value(p, ib_idx, idx + 1); + uint32_t len = amdgpu_ib_get_value(ib, idx); + uint32_t cmd = amdgpu_ib_get_value(ib, idx + 1); if ((len < 8) || (len & 3)) { DRM_ERROR("invalid VCE command length (%d)!\n", len); @@ -989,7 +994,7 @@ int amdgpu_vce_ring_parse_cs_vm(struct amdgpu_cs_parser *p, uint32_t ib_idx) switch (cmd) { case 0x00000001: /* session */ - handle = amdgpu_get_ib_value(p, ib_idx, idx + 2); + handle = amdgpu_ib_get_value(ib, idx + 2); session_idx = amdgpu_vce_validate_handle(p, handle, &allocated); if (session_idx < 0) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h index be4a6e773c5b..ea680fc9a6c3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h @@ -59,8 +59,11 @@ int amdgpu_vce_entity_init(struct amdgpu_device *adev); int amdgpu_vce_suspend(struct amdgpu_device *adev); int amdgpu_vce_resume(struct amdgpu_device *adev); void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp); -int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx); -int amdgpu_vce_ring_parse_cs_vm(struct amdgpu_cs_parser *p, uint32_t ib_idx); +int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, struct amdgpu_job *job, + struct amdgpu_ib *ib); +int amdgpu_vce_ring_parse_cs_vm(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib); void amdgpu_vce_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_job *job, struct amdgpu_ib *ib, uint32_t flags); void amdgpu_vce_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 5e0dbf54d561..f99093f2ebc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -27,6 +27,7 @@ #include <linux/firmware.h> #include <linux/module.h> #include <linux/pci.h> +#include <linux/debugfs.h> #include <drm/drm_drv.h> #include "amdgpu.h" @@ -79,6 +80,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) const char *fw_name; 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); @@ -226,7 +228,12 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) bo_size = AMDGPU_VCN_STACK_SIZE + AMDGPU_VCN_CONTEXT_SIZE; if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) bo_size += AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8); - bo_size += AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)); + fw_shared_size = AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)); + log_offset = offsetof(struct amdgpu_fw_shared, fw_log); + bo_size += fw_shared_size; + + 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)) @@ -240,10 +247,18 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) return r; } - adev->vcn.inst[i].fw_shared_cpu_addr = adev->vcn.inst[i].cpu_addr + - bo_size - AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)); - adev->vcn.inst[i].fw_shared_gpu_addr = adev->vcn.inst[i].gpu_addr + - bo_size - AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)); + 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, @@ -979,3 +994,112 @@ void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev) dev_info(adev->dev, "Will use PSP to load VCN firmware\n"); } } + +/* + * debugfs for mapping vcn firmware log buffer. + */ +#if defined(CONFIG_DEBUG_FS) +static ssize_t amdgpu_debugfs_vcn_fwlog_read(struct file *f, char __user *buf, + size_t size, loff_t *pos) +{ + struct amdgpu_vcn_inst *vcn; + void *log_buf; + volatile struct amdgpu_vcn_fwlog *plog; + unsigned int read_pos, write_pos, available, i, read_bytes = 0; + unsigned int read_num[2] = {0}; + + vcn = file_inode(f)->i_private; + if (!vcn) + return -ENODEV; + + if (!vcn->fw_shared.cpu_addr || !amdgpu_vcnfw_log) + return -EFAULT; + + log_buf = vcn->fw_shared.cpu_addr + vcn->fw_shared.mem_size; + + plog = (volatile struct amdgpu_vcn_fwlog *)log_buf; + read_pos = plog->rptr; + write_pos = plog->wptr; + + if (read_pos > AMDGPU_VCNFW_LOG_SIZE || write_pos > AMDGPU_VCNFW_LOG_SIZE) + return -EFAULT; + + if (!size || (read_pos == write_pos)) + return 0; + + if (write_pos > read_pos) { + available = write_pos - read_pos; + read_num[0] = min(size, (size_t)available); + } else { + read_num[0] = AMDGPU_VCNFW_LOG_SIZE - read_pos; + available = read_num[0] + write_pos - plog->header_size; + if (size > available) + read_num[1] = write_pos - plog->header_size; + else if (size > read_num[0]) + read_num[1] = size - read_num[0]; + else + read_num[0] = size; + } + + for (i = 0; i < 2; i++) { + if (read_num[i]) { + if (read_pos == AMDGPU_VCNFW_LOG_SIZE) + read_pos = plog->header_size; + if (read_num[i] == copy_to_user((buf + read_bytes), + (log_buf + read_pos), read_num[i])) + return -EFAULT; + + read_bytes += read_num[i]; + read_pos += read_num[i]; + } + } + + plog->rptr = read_pos; + *pos += read_bytes; + return read_bytes; +} + +static const struct file_operations amdgpu_debugfs_vcnfwlog_fops = { + .owner = THIS_MODULE, + .read = amdgpu_debugfs_vcn_fwlog_read, + .llseek = default_llseek +}; +#endif + +void amdgpu_debugfs_vcn_fwlog_init(struct amdgpu_device *adev, uint8_t i, + struct amdgpu_vcn_inst *vcn) +{ +#if defined(CONFIG_DEBUG_FS) + struct drm_minor *minor = adev_to_drm(adev)->primary; + struct dentry *root = minor->debugfs_root; + char name[32]; + + sprintf(name, "amdgpu_vcn_%d_fwlog", i); + debugfs_create_file_size(name, S_IFREG | S_IRUGO, root, vcn, + &amdgpu_debugfs_vcnfwlog_fops, + AMDGPU_VCNFW_LOG_SIZE); +#endif +} + +void amdgpu_vcn_fwlog_init(struct amdgpu_vcn_inst *vcn) +{ +#if defined(CONFIG_DEBUG_FS) + volatile uint32_t *flag = vcn->fw_shared.cpu_addr; + void *fw_log_cpu_addr = vcn->fw_shared.cpu_addr + vcn->fw_shared.mem_size; + uint64_t fw_log_gpu_addr = vcn->fw_shared.gpu_addr + vcn->fw_shared.mem_size; + volatile struct amdgpu_vcn_fwlog *log_buf = fw_log_cpu_addr; + volatile struct amdgpu_fw_shared_fw_logging *fw_log = vcn->fw_shared.cpu_addr + + vcn->fw_shared.log_offset; + *flag |= cpu_to_le32(AMDGPU_VCN_FW_LOGGING_FLAG); + fw_log->is_enabled = 1; + fw_log->addr_lo = cpu_to_le32(fw_log_gpu_addr & 0xFFFFFFFF); + fw_log->addr_hi = cpu_to_le32(fw_log_gpu_addr >> 32); + fw_log->size = cpu_to_le32(AMDGPU_VCNFW_LOG_SIZE); + + log_buf->header_size = sizeof(struct amdgpu_vcn_fwlog); + log_buf->buffer_size = AMDGPU_VCNFW_LOG_SIZE; + log_buf->rptr = log_buf->header_size; + log_buf->wptr = log_buf->header_size; + log_buf->wrapped = 0; +#endif +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index 5d3728b027d3..e2fde88aaf5e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -158,6 +158,7 @@ #define AMDGPU_VCN_FW_SHARED_FLAG_0_RB (1 << 6) #define AMDGPU_VCN_MULTI_QUEUE_FLAG (1 << 8) #define AMDGPU_VCN_SW_RING_FLAG (1 << 9) +#define AMDGPU_VCN_FW_LOGGING_FLAG (1 << 10) #define AMDGPU_VCN_IB_FLAG_DECODE_BUFFER 0x00000001 #define AMDGPU_VCN_CMD_FLAG_MSG_BUFFER 0x00000001 @@ -205,6 +206,13 @@ struct amdgpu_vcn_reg{ unsigned scratch9; }; +struct amdgpu_vcn_fw_shared { + void *cpu_addr; + uint64_t gpu_addr; + uint32_t mem_size; + uint32_t log_offset; +}; + struct amdgpu_vcn_inst { struct amdgpu_bo *vcpu_bo; void *cpu_addr; @@ -221,8 +229,7 @@ struct amdgpu_vcn_inst { uint64_t dpg_sram_gpu_addr; uint32_t *dpg_sram_curr_addr; atomic_t dpg_enc_submission_cnt; - void *fw_shared_cpu_addr; - uint64_t fw_shared_gpu_addr; + struct amdgpu_vcn_fw_shared fw_shared; }; struct amdgpu_vcn { @@ -265,6 +272,13 @@ struct amdgpu_fw_shared_sw_ring { uint8_t padding[3]; }; +struct amdgpu_fw_shared_fw_logging { + uint8_t is_enabled; + uint32_t addr_lo; + uint32_t addr_hi; + uint32_t size; +}; + struct amdgpu_fw_shared { uint32_t present_flag_0; uint8_t pad[44]; @@ -272,6 +286,15 @@ struct amdgpu_fw_shared { uint8_t pad1[1]; struct amdgpu_fw_shared_multi_queue multi_queue; struct amdgpu_fw_shared_sw_ring sw_ring; + struct amdgpu_fw_shared_fw_logging fw_log; +}; + +struct amdgpu_vcn_fwlog { + uint32_t rptr; + uint32_t wptr; + uint32_t buffer_size; + uint32_t header_size; + uint8_t wrapped; }; struct amdgpu_vcn_decode_buffer { @@ -313,4 +336,7 @@ 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_fwlog_init(struct amdgpu_vcn_inst *vcn); +void amdgpu_debugfs_vcn_fwlog_init(struct amdgpu_device *adev, + uint8_t i, struct amdgpu_vcn_inst *vcn); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 2cd9f1a2e5fa..fc4563cf2828 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -779,7 +779,8 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm) amdgpu_vm_eviction_lock(vm); ret = !vm->evicting; amdgpu_vm_eviction_unlock(vm); - return ret; + + return ret && list_empty(&vm->evicted); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index 91817a31f3e1..1b108d03e785 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -34,7 +34,6 @@ #include "amdgpu_reset.h" -#define smnPCS_XGMI23_PCS_ERROR_STATUS 0x11a01210 #define smnPCS_XGMI3X16_PCS_ERROR_STATUS 0x11a0020c #define smnPCS_GOPX1_PCS_ERROR_STATUS 0x12200210 @@ -69,17 +68,6 @@ static const int wafl_pcs_err_status_reg_arct[] = { smnPCS_GOPX1_0_PCS_GOPX1_PCS_ERROR_STATUS + 0x100000, }; -static const int xgmi23_pcs_err_status_reg_aldebaran[] = { - smnPCS_XGMI23_PCS_ERROR_STATUS, - smnPCS_XGMI23_PCS_ERROR_STATUS + 0x100000, - smnPCS_XGMI23_PCS_ERROR_STATUS + 0x200000, - smnPCS_XGMI23_PCS_ERROR_STATUS + 0x300000, - smnPCS_XGMI23_PCS_ERROR_STATUS + 0x400000, - smnPCS_XGMI23_PCS_ERROR_STATUS + 0x500000, - smnPCS_XGMI23_PCS_ERROR_STATUS + 0x600000, - smnPCS_XGMI23_PCS_ERROR_STATUS + 0x700000 -}; - static const int xgmi3x16_pcs_err_status_reg_aldebaran[] = { smnPCS_XGMI3X16_PCS_ERROR_STATUS, smnPCS_XGMI3X16_PCS_ERROR_STATUS + 0x100000, @@ -768,13 +756,6 @@ static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev, struct ras_comm return amdgpu_ras_block_late_init(adev, ras_block); } -static void amdgpu_xgmi_ras_fini(struct amdgpu_device *adev) -{ - if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__XGMI_WAFL) && - adev->gmc.xgmi.ras_if) - amdgpu_ras_block_late_fini(adev, adev->gmc.xgmi.ras_if); -} - uint64_t amdgpu_xgmi_get_relative_phy_addr(struct amdgpu_device *adev, uint64_t addr) { @@ -804,9 +785,6 @@ static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev) xgmi_pcs_err_status_reg_vg20[i]); break; case CHIP_ALDEBARAN: - for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++) - pcs_clear_status(adev, - xgmi23_pcs_err_status_reg_aldebaran[i]); for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_aldebaran); i++) pcs_clear_status(adev, xgmi3x16_pcs_err_status_reg_aldebaran[i]); @@ -907,13 +885,6 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev, } break; case CHIP_ALDEBARAN: - /* check xgmi23 pcs error */ - for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++) { - data = RREG32_PCIE(xgmi23_pcs_err_status_reg_aldebaran[i]); - if (data) - amdgpu_xgmi_query_pcs_error_status(adev, - data, &ue_cnt, &ce_cnt, true); - } /* check xgmi3x16 pcs error */ for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_aldebaran); i++) { data = RREG32_PCIE(xgmi3x16_pcs_err_status_reg_aldebaran[i]); @@ -982,6 +953,5 @@ struct amdgpu_xgmi_ras xgmi_ras = { }, .hw_ops = &xgmi_ras_hw_ops, .ras_late_init = amdgpu_xgmi_ras_late_init, - .ras_fini = amdgpu_xgmi_ras_fini, }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 90158289cd30..f4c6accd3226 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -250,13 +250,6 @@ MODULE_FIRMWARE("amdgpu/yellow_carp_mec.bin"); MODULE_FIRMWARE("amdgpu/yellow_carp_mec2.bin"); MODULE_FIRMWARE("amdgpu/yellow_carp_rlc.bin"); -MODULE_FIRMWARE("amdgpu/cyan_skillfish_ce.bin"); -MODULE_FIRMWARE("amdgpu/cyan_skillfish_pfp.bin"); -MODULE_FIRMWARE("amdgpu/cyan_skillfish_me.bin"); -MODULE_FIRMWARE("amdgpu/cyan_skillfish_mec.bin"); -MODULE_FIRMWARE("amdgpu/cyan_skillfish_mec2.bin"); -MODULE_FIRMWARE("amdgpu/cyan_skillfish_rlc.bin"); - MODULE_FIRMWARE("amdgpu/cyan_skillfish2_ce.bin"); MODULE_FIRMWARE("amdgpu/cyan_skillfish2_pfp.bin"); MODULE_FIRMWARE("amdgpu/cyan_skillfish2_me.bin"); @@ -4043,10 +4036,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) break; case IP_VERSION(10, 1, 3): case IP_VERSION(10, 1, 4): - if (adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2) - chip_name = "cyan_skillfish2"; - else - chip_name = "cyan_skillfish"; + chip_name = "cyan_skillfish2"; break; case IP_VERSION(10, 3, 7): chip_name = "gc_10_3_7"; @@ -6557,6 +6547,7 @@ static void gfx_v10_0_kiq_setting(struct amdgpu_ring *ring) case IP_VERSION(10, 3, 5): case IP_VERSION(10, 3, 6): case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 7): tmp = RREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS_Sienna_Cichlid); tmp &= 0xffffff00; tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue); @@ -7857,6 +7848,7 @@ static void gfx_v10_0_set_safe_mode(struct amdgpu_device *adev) case IP_VERSION(10, 3, 5): case IP_VERSION(10, 3, 6): case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 7): WREG32_SOC15(GC, 0, mmRLC_SAFE_MODE_Sienna_Cichlid, data); /* wait for RLC_SAFE_MODE */ @@ -7894,6 +7886,7 @@ static void gfx_v10_0_unset_safe_mode(struct amdgpu_device *adev) case IP_VERSION(10, 3, 5): case IP_VERSION(10, 3, 6): case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 7): WREG32_SOC15(GC, 0, mmRLC_SAFE_MODE_Sienna_Cichlid, data); break; default: @@ -8348,6 +8341,7 @@ static void gfx_v10_cntl_power_gating(struct amdgpu_device *adev, bool enable) case IP_VERSION(10, 3, 1): case IP_VERSION(10, 3, 3): case IP_VERSION(10, 3, 6): + case IP_VERSION(10, 3, 7): data = 0x4E20 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh; WREG32_SOC15(GC, 0, mmRLC_PG_DELAY_3, data); break; @@ -8417,6 +8411,7 @@ static int gfx_v10_0_set_powergating_state(void *handle, case IP_VERSION(10, 3, 1): case IP_VERSION(10, 3, 3): case IP_VERSION(10, 3, 6): + case IP_VERSION(10, 3, 7): gfx_v10_cntl_pg(adev, enable); amdgpu_gfx_off_ctrl(adev, enable); break; @@ -8445,6 +8440,7 @@ static int gfx_v10_0_set_clockgating_state(void *handle, case IP_VERSION(10, 3, 5): case IP_VERSION(10, 3, 6): case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 7): gfx_v10_0_update_gfx_clock_gating(adev, state == AMD_CG_STATE_GATE); break; @@ -9381,6 +9377,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = { .align_mask = 0xff, .nop = PACKET3(PACKET3_NOP, 0x3FFF), .support_64bit_ptrs = true, + .secure_submission_supported = true, .vmhub = AMDGPU_GFXHUB_0, .get_rptr = gfx_v10_0_ring_get_rptr_gfx, .get_wptr = gfx_v10_0_ring_get_wptr_gfx, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 1997f129db9c..46d4bf27ebbb 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2204,10 +2204,6 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev) if (!adev->gfx.ras->ras_block.ras_late_init) adev->gfx.ras->ras_block.ras_late_init = amdgpu_gfx_ras_late_init; - /* If not define special ras_fini function, use gfx default ras_fini */ - if (!adev->gfx.ras->ras_block.ras_fini) - adev->gfx.ras->ras_block.ras_fini = amdgpu_gfx_ras_fini; - /* If not defined special ras_cb function, use default ras_cb */ if (!adev->gfx.ras->ras_block.ras_cb) adev->gfx.ras->ras_block.ras_cb = amdgpu_gfx_process_ras_data_cb; @@ -2432,9 +2428,6 @@ static int gfx_v9_0_sw_fini(void *handle) int i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (adev->gfx.ras && adev->gfx.ras->ras_block.ras_fini) - adev->gfx.ras->ras_block.ras_fini(adev); - for (i = 0; i < adev->gfx.num_gfx_rings; i++) amdgpu_ring_fini(&adev->gfx.gfx_ring[i]); for (i = 0; i < adev->gfx.num_compute_rings; i++) @@ -6872,6 +6865,7 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_gfx = { .align_mask = 0xff, .nop = PACKET3(PACKET3_NOP, 0x3FFF), .support_64bit_ptrs = true, + .secure_submission_supported = true, .vmhub = AMDGPU_GFXHUB_0, .get_rptr = gfx_v9_0_ring_get_rptr_gfx, .get_wptr = gfx_v9_0_ring_get_wptr_gfx, diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 3dcd82b49481..3c1d440824a7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -683,10 +683,6 @@ static void gmc_v10_0_set_umc_funcs(struct amdgpu_device *adev) if (!adev->umc.ras->ras_block.ras_late_init) adev->umc.ras->ras_block.ras_late_init = amdgpu_umc_ras_late_init; - /* If don't define special ras_fini function, use default ras_fini */ - if (!adev->umc.ras->ras_block.ras_fini) - adev->umc.ras->ras_block.ras_fini = amdgpu_umc_ras_fini; - /* If not defined special ras_cb function, use default ras_cb */ if (!adev->umc.ras->ras_block.ras_cb) adev->umc.ras->ras_block.ras_cb = amdgpu_umc_process_ras_data_cb; @@ -952,7 +948,6 @@ static int gmc_v10_0_sw_init(void *handle) return r; amdgpu_gmc_get_vbios_allocations(adev); - amdgpu_gmc_get_reserved_allocation(adev); /* Memory manager */ r = amdgpu_bo_init(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index df35f0252eea..431742eb7811 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1243,10 +1243,6 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev) if (!adev->umc.ras->ras_block.ras_late_init) adev->umc.ras->ras_block.ras_late_init = amdgpu_umc_ras_late_init; - /* If don't define special ras_fini function, use default ras_fini */ - if (!adev->umc.ras->ras_block.ras_fini) - adev->umc.ras->ras_block.ras_fini = amdgpu_umc_ras_fini; - /* If not defined special ras_cb function, use default ras_cb */ if (!adev->umc.ras->ras_block.ras_cb) adev->umc.ras->ras_block.ras_cb = amdgpu_umc_process_ras_data_cb; @@ -1292,10 +1288,6 @@ static void gmc_v9_0_set_mmhub_ras_funcs(struct amdgpu_device *adev) adev->mmhub.ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__MMHUB; adev->mmhub.ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE; adev->mmhub.ras_if = &adev->mmhub.ras->ras_block.ras_comm; - - /* If don't define special ras_fini function, use default ras_fini */ - if (!adev->mmhub.ras->ras_block.ras_fini) - adev->mmhub.ras->ras_block.ras_fini = amdgpu_mmhub_ras_fini; } } @@ -1561,7 +1553,7 @@ static void gmc_v9_0_save_registers(struct amdgpu_device *adev) static int gmc_v9_0_sw_init(void *handle) { - int r, vram_width = 0, vram_type = 0, vram_vendor = 0; + int r, vram_width = 0, vram_type = 0, vram_vendor = 0, dma_addr_bits; struct amdgpu_device *adev = (struct amdgpu_device *)handle; adev->gfxhub.funcs->init(adev); @@ -1677,12 +1669,13 @@ static int gmc_v9_0_sw_init(void *handle) */ adev->gmc.mc_mask = 0xffffffffffffULL; /* 48 bit MC */ - r = dma_set_mask_and_coherent(adev->dev, DMA_BIT_MASK(44)); + dma_addr_bits = adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2) ? 48:44; + r = dma_set_mask_and_coherent(adev->dev, DMA_BIT_MASK(dma_addr_bits)); if (r) { printk(KERN_WARNING "amdgpu: No suitable DMA available.\n"); return r; } - adev->need_swiotlb = drm_need_swiotlb(44); + adev->need_swiotlb = drm_need_swiotlb(dma_addr_bits); r = gmc_v9_0_mc_init(adev); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c index 02400d97a95c..046216635262 100644 --- a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c @@ -166,7 +166,6 @@ struct amdgpu_hdp_ras hdp_v4_0_ras = { .type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE, }, .hw_ops = &hdp_v4_0_ras_hw_ops, - .ras_fini = amdgpu_hdp_ras_fini, }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mca_v3_0.c b/drivers/gpu/drm/amd/amdgpu/mca_v3_0.c index b4b36899f5c6..d4bd7d1d2649 100644 --- a/drivers/gpu/drm/amd/amdgpu/mca_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mca_v3_0.c @@ -37,11 +37,6 @@ static void mca_v3_0_mp0_query_ras_error_count(struct amdgpu_device *adev, ras_error_status); } -static void mca_v3_0_mp0_ras_fini(struct amdgpu_device *adev) -{ - amdgpu_mca_ras_fini(adev, &adev->mca.mp0); -} - static int mca_v3_0_ras_block_match(struct amdgpu_ras_block_object *block_obj, enum amdgpu_ras_block block, uint32_t sub_block_index) { @@ -71,7 +66,6 @@ struct amdgpu_mca_ras_block mca_v3_0_mp0_ras = { }, .hw_ops = &mca_v3_0_mp0_hw_ops, .ras_block_match = mca_v3_0_ras_block_match, - .ras_fini = mca_v3_0_mp0_ras_fini, }, }; @@ -83,11 +77,6 @@ static void mca_v3_0_mp1_query_ras_error_count(struct amdgpu_device *adev, ras_error_status); } -static void mca_v3_0_mp1_ras_fini(struct amdgpu_device *adev) -{ - amdgpu_mca_ras_fini(adev, &adev->mca.mp1); -} - const struct amdgpu_ras_block_hw_ops mca_v3_0_mp1_hw_ops = { .query_ras_error_count = mca_v3_0_mp1_query_ras_error_count, .query_ras_error_address = NULL, @@ -103,7 +92,6 @@ struct amdgpu_mca_ras_block mca_v3_0_mp1_ras = { }, .hw_ops = &mca_v3_0_mp1_hw_ops, .ras_block_match = mca_v3_0_ras_block_match, - .ras_fini = mca_v3_0_mp1_ras_fini, }, }; @@ -115,11 +103,6 @@ static void mca_v3_0_mpio_query_ras_error_count(struct amdgpu_device *adev, ras_error_status); } -static void mca_v3_0_mpio_ras_fini(struct amdgpu_device *adev) -{ - amdgpu_mca_ras_fini(adev, &adev->mca.mpio); -} - const struct amdgpu_ras_block_hw_ops mca_v3_0_mpio_hw_ops = { .query_ras_error_count = mca_v3_0_mpio_query_ras_error_count, .query_ras_error_address = NULL, @@ -135,7 +118,6 @@ struct amdgpu_mca_ras_block mca_v3_0_mpio_ras = { }, .hw_ops = &mca_v3_0_mpio_hw_ops, .ras_block_match = mca_v3_0_ras_block_match, - .ras_fini = mca_v3_0_mpio_ras_fini, }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index 14768570c298..c2357e83a8c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -362,9 +362,24 @@ const struct nbio_hdp_flush_reg nbio_v7_4_hdp_flush_reg_ald = { static void nbio_v7_4_init_registers(struct amdgpu_device *adev) { + uint32_t baco_cntl; + if (amdgpu_sriov_vf(adev)) adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2; + + if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(7, 4, 4) && + !amdgpu_sriov_vf(adev)) { + baco_cntl = RREG32_SOC15(NBIO, 0, mmBACO_CNTL); + if (baco_cntl & + (BACO_CNTL__BACO_DUMMY_EN_MASK | BACO_CNTL__BACO_EN_MASK)) { + baco_cntl &= ~(BACO_CNTL__BACO_DUMMY_EN_MASK | + BACO_CNTL__BACO_EN_MASK); + dev_dbg(adev->dev, "Unsetting baco dummy mode %x", + baco_cntl); + WREG32_SOC15(NBIO, 0, mmBACO_CNTL, baco_cntl); + } + } } static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device *adev) @@ -671,7 +686,6 @@ struct amdgpu_nbio_ras nbio_v7_4_ras = { }, .hw_ops = &nbio_v7_4_ras_hw_ops, .ras_late_init = amdgpu_nbio_ras_late_init, - .ras_fini = amdgpu_nbio_ras_fini, }, .handle_ras_controller_intr_no_bifring = nbio_v7_4_handle_ras_controller_intr_no_bifring, .handle_ras_err_event_athub_intr_no_bifring = nbio_v7_4_handle_ras_err_event_athub_intr_no_bifring, diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index f6aeef759ee1..e19f14c3ef59 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -946,10 +946,21 @@ static int nv_common_early_init(void *handle) AMD_CG_SUPPORT_GFX_3D_CGLS | AMD_CG_SUPPORT_GFX_RLC_LS | AMD_CG_SUPPORT_GFX_CP_LS | - AMD_CG_SUPPORT_GFX_FGCG; + AMD_CG_SUPPORT_GFX_FGCG | + AMD_CG_SUPPORT_MC_MGCG | + AMD_CG_SUPPORT_MC_LS | + AMD_CG_SUPPORT_SDMA_LS | + AMD_CG_SUPPORT_HDP_MGCG | + AMD_CG_SUPPORT_HDP_LS | + AMD_CG_SUPPORT_ATHUB_MGCG | + AMD_CG_SUPPORT_ATHUB_LS | + AMD_CG_SUPPORT_IH_CG | + AMD_CG_SUPPORT_VCN_MGCG | + AMD_CG_SUPPORT_JPEG_MGCG; adev->pg_flags = AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_VCN_DPG | - AMD_PG_SUPPORT_JPEG; + AMD_PG_SUPPORT_JPEG | + AMD_PG_SUPPORT_GFX_PG; adev->external_rev_id = adev->rev_id + 0x01; break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index 2c6070b90dcf..024f60631faf 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -31,6 +31,7 @@ MODULE_FIRMWARE("amdgpu/aldebaran_sos.bin"); MODULE_FIRMWARE("amdgpu/aldebaran_ta.bin"); +MODULE_FIRMWARE("amdgpu/aldebaran_cap.bin"); MODULE_FIRMWARE("amdgpu/yellow_carp_asd.bin"); MODULE_FIRMWARE("amdgpu/yellow_carp_toc.bin"); MODULE_FIRMWARE("amdgpu/yellow_carp_ta.bin"); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 4509bd4cce2d..1d8bbcbd7a37 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -1142,6 +1142,7 @@ static const struct amdgpu_ring_funcs sdma_v2_4_ring_funcs = { .align_mask = 0xf, .nop = SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), .support_64bit_ptrs = false, + .secure_submission_supported = true, .get_rptr = sdma_v2_4_ring_get_rptr, .get_wptr = sdma_v2_4_ring_get_wptr, .set_wptr = sdma_v2_4_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 135727b59c41..4ef4feff5649 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -1580,6 +1580,7 @@ static const struct amdgpu_ring_funcs sdma_v3_0_ring_funcs = { .align_mask = 0xf, .nop = SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), .support_64bit_ptrs = false, + .secure_submission_supported = true, .get_rptr = sdma_v3_0_ring_get_rptr, .get_wptr = sdma_v3_0_ring_get_wptr, .set_wptr = sdma_v3_0_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index e26c39fcd336..d7e8f7232364 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1995,10 +1995,6 @@ static int sdma_v4_0_sw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int i; - if (adev->sdma.ras && adev->sdma.ras->ras_block.hw_ops && - adev->sdma.ras->ras_block.ras_fini) - adev->sdma.ras->ras_block.ras_fini(adev); - for (i = 0; i < adev->sdma.num_instances; i++) { amdgpu_ring_fini(&adev->sdma.instance[i].ring); if (adev->sdma.has_page_queue) @@ -2418,6 +2414,7 @@ static const struct amdgpu_ring_funcs sdma_v4_0_ring_funcs = { .align_mask = 0xf, .nop = SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), .support_64bit_ptrs = true, + .secure_submission_supported = true, .vmhub = AMDGPU_MMHUB_0, .get_rptr = sdma_v4_0_ring_get_rptr, .get_wptr = sdma_v4_0_ring_get_wptr, @@ -2454,6 +2451,7 @@ static const struct amdgpu_ring_funcs sdma_v4_0_ring_funcs_2nd_mmhub = { .align_mask = 0xf, .nop = SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), .support_64bit_ptrs = true, + .secure_submission_supported = true, .vmhub = AMDGPU_MMHUB_1, .get_rptr = sdma_v4_0_ring_get_rptr, .get_wptr = sdma_v4_0_ring_get_wptr, @@ -2486,6 +2484,7 @@ static const struct amdgpu_ring_funcs sdma_v4_0_page_ring_funcs = { .align_mask = 0xf, .nop = SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), .support_64bit_ptrs = true, + .secure_submission_supported = true, .vmhub = AMDGPU_MMHUB_0, .get_rptr = sdma_v4_0_ring_get_rptr, .get_wptr = sdma_v4_0_page_ring_get_wptr, @@ -2518,6 +2517,7 @@ static const struct amdgpu_ring_funcs sdma_v4_0_page_ring_funcs_2nd_mmhub = { .align_mask = 0xf, .nop = SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), .support_64bit_ptrs = true, + .secure_submission_supported = true, .vmhub = AMDGPU_MMHUB_1, .get_rptr = sdma_v4_0_ring_get_rptr, .get_wptr = sdma_v4_0_page_ring_get_wptr, @@ -2826,10 +2826,6 @@ static void sdma_v4_0_set_ras_funcs(struct amdgpu_device *adev) if (!adev->sdma.ras->ras_block.ras_late_init) adev->sdma.ras->ras_block.ras_late_init = amdgpu_sdma_ras_late_init; - /* If don't define special ras_fini function, use default ras_fini */ - if (!adev->sdma.ras->ras_block.ras_fini) - adev->sdma.ras->ras_block.ras_fini = amdgpu_sdma_ras_fini; - /* If not defined special ras_cb function, use default ras_cb */ if (!adev->sdma.ras->ras_block.ras_cb) adev->sdma.ras->ras_block.ras_cb = amdgpu_sdma_process_ras_data_cb; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index 81e033549dda..a8d49c005f73 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -51,9 +51,6 @@ MODULE_FIRMWARE("amdgpu/navi14_sdma1.bin"); MODULE_FIRMWARE("amdgpu/navi12_sdma.bin"); MODULE_FIRMWARE("amdgpu/navi12_sdma1.bin"); -MODULE_FIRMWARE("amdgpu/cyan_skillfish_sdma.bin"); -MODULE_FIRMWARE("amdgpu/cyan_skillfish_sdma1.bin"); - MODULE_FIRMWARE("amdgpu/cyan_skillfish2_sdma.bin"); MODULE_FIRMWARE("amdgpu/cyan_skillfish2_sdma1.bin"); @@ -264,10 +261,7 @@ static int sdma_v5_0_init_microcode(struct amdgpu_device *adev) chip_name = "navi12"; break; case IP_VERSION(5, 0, 1): - if (adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2) - chip_name = "cyan_skillfish2"; - else - chip_name = "cyan_skillfish"; + chip_name = "cyan_skillfish2"; break; default: BUG(); @@ -1696,6 +1690,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = { .align_mask = 0xf, .nop = SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), .support_64bit_ptrs = true, + .secure_submission_supported = true, .vmhub = AMDGPU_GFXHUB_0, .get_rptr = sdma_v5_0_ring_get_rptr, .get_wptr = sdma_v5_0_ring_get_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index dcc622e18d45..824eace69884 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -1687,6 +1687,7 @@ static const struct amdgpu_ring_funcs sdma_v5_2_ring_funcs = { .align_mask = 0xf, .nop = SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), .support_64bit_ptrs = true, + .secure_submission_supported = true, .vmhub = AMDGPU_GFXHUB_0, .get_rptr = sdma_v5_2_ring_get_rptr, .get_wptr = sdma_v5_2_ring_get_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index b7c24149a6bd..3d0251ef8d79 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -853,6 +853,10 @@ static bool soc15_need_reset_on_init(struct amdgpu_device *adev) { u32 sol_reg; + /* CP hangs in IGT reloading test on RN, reset to WA */ + if (adev->asic_type == CHIP_RENOIR) + return true; + /* Just return false for soc15 GPUs. Reset does not seem to * be necessary. */ @@ -1214,9 +1218,6 @@ static int soc15_common_sw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (adev->nbio.ras && adev->nbio.ras->ras_block.ras_fini) - adev->nbio.ras->ras_block.ras_fini(adev); - if (adev->df.funcs && adev->df.funcs->sw_fini) adev->df.funcs->sw_fini(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index b483f03b4591..2f15b8e0f7d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -25,6 +25,7 @@ #include "amdgpu.h" #include "amdgpu_uvd.h" +#include "amdgpu_cs.h" #include "soc15.h" #include "soc15d.h" #include "soc15_common.h" @@ -1275,14 +1276,15 @@ static int uvd_v7_0_ring_test_ring(struct amdgpu_ring *ring) * uvd_v7_0_ring_patch_cs_in_place - Patch the IB for command submission. * * @p: the CS parser with the IBs - * @ib_idx: which IB to patch + * @job: which job this ib is in + * @ib: which IB to patch * */ static int uvd_v7_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, - uint32_t ib_idx) + struct amdgpu_job *job, + struct amdgpu_ib *ib) { - struct amdgpu_ring *ring = to_amdgpu_ring(p->entity->rq->sched); - struct amdgpu_ib *ib = &p->job->ibs[ib_idx]; + struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched); unsigned i; /* No patching necessary for the first instance */ @@ -1290,12 +1292,12 @@ static int uvd_v7_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, return 0; for (i = 0; i < ib->length_dw; i += 2) { - uint32_t reg = amdgpu_get_ib_value(p, ib_idx, i); + uint32_t reg = amdgpu_ib_get_value(ib, i); reg -= p->adev->reg_offset[UVD_HWIP][0][1]; reg += p->adev->reg_offset[UVD_HWIP][1][1]; - amdgpu_set_ib_value(p, ib_idx, i, reg); + amdgpu_ib_set_value(ib, i, reg); } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 3799226defc0..dff54190b96c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -148,6 +148,13 @@ static int vcn_v1_0_sw_init(void *handle) adev->vcn.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; + + fw_shared->present_flag_0 = 0; + amdgpu_vcn_fwlog_init(adev->vcn.inst); + } + r = jpeg_v1_0_sw_init(handle); return r; @@ -1095,13 +1102,8 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) static int vcn_v1_0_start(struct amdgpu_device *adev) { - int r; - - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - r = vcn_v1_0_start_dpg_mode(adev); - else - r = vcn_v1_0_start_spg_mode(adev); - return r; + return (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ? + vcn_v1_0_start_dpg_mode(adev) : vcn_v1_0_start_spg_mode(adev); } /** @@ -1903,6 +1905,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .align_mask = 0xf, .support_64bit_ptrs = false, .no_user_fence = true, + .secure_submission_supported = true, .vmhub = AMDGPU_MMHUB_0, .get_rptr = vcn_v1_0_dec_ring_get_rptr, .get_wptr = vcn_v1_0_dec_ring_get_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index 313fc1b53999..7a7f35e83dd5 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -172,8 +172,12 @@ static int vcn_v2_0_sw_init(void *handle) if (r) return r; - fw_shared = adev->vcn.inst->fw_shared_cpu_addr; + fw_shared = adev->vcn.inst->fw_shared.cpu_addr; fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG); + + if (amdgpu_vcnfw_log) + amdgpu_vcn_fwlog_init(adev->vcn.inst); + return 0; } @@ -188,7 +192,7 @@ static int vcn_v2_0_sw_fini(void *handle) { int r, idx; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared_cpu_addr; + volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; if (drm_dev_enter(adev_to_drm(adev), &idx)) { fw_shared->present_flag_0 = 0; @@ -364,9 +368,9 @@ static void vcn_v2_0_mc_resume(struct amdgpu_device *adev) /* non-cache window */ WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW, - lower_32_bits(adev->vcn.inst->fw_shared_gpu_addr)); + lower_32_bits(adev->vcn.inst->fw_shared.gpu_addr)); WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH, - upper_32_bits(adev->vcn.inst->fw_shared_gpu_addr)); + upper_32_bits(adev->vcn.inst->fw_shared.gpu_addr)); WREG32_SOC15(UVD, 0, mmUVD_VCPU_NONCACHE_OFFSET0, 0); WREG32_SOC15(UVD, 0, mmUVD_VCPU_NONCACHE_SIZE0, AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared))); @@ -455,10 +459,10 @@ static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirec /* non-cache window */ WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( UVD, 0, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW), - lower_32_bits(adev->vcn.inst->fw_shared_gpu_addr), 0, indirect); + lower_32_bits(adev->vcn.inst->fw_shared.gpu_addr), 0, indirect); WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( UVD, 0, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH), - upper_32_bits(adev->vcn.inst->fw_shared_gpu_addr), 0, indirect); + upper_32_bits(adev->vcn.inst->fw_shared.gpu_addr), 0, indirect); WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( UVD, 0, mmUVD_VCPU_NONCACHE_OFFSET0), 0, 0, indirect); WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( @@ -784,7 +788,7 @@ 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) { - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared_cpu_addr; + 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; @@ -921,7 +925,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) static int vcn_v2_0_start(struct amdgpu_device *adev) { - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared_cpu_addr; + 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; uint32_t lmi_swap_cntl; @@ -1094,8 +1098,10 @@ static int vcn_v2_0_start(struct amdgpu_device *adev) static int vcn_v2_0_stop_dpg_mode(struct amdgpu_device *adev) { + struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; + vcn_v2_0_pause_dpg_mode(adev, 0, &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); @@ -1207,7 +1213,7 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); if (!ret_code) { - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared_cpu_addr; + volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; /* pause DPG */ reg_data |= UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK; WREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE, reg_data); @@ -2003,6 +2009,7 @@ static const struct amd_ip_funcs vcn_v2_0_ip_funcs = { static const struct amdgpu_ring_funcs vcn_v2_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .secure_submission_supported = true, .vmhub = AMDGPU_MMHUB_0, .get_rptr = vcn_v2_0_dec_ring_get_rptr, .get_wptr = vcn_v2_0_dec_ring_get_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 44fc4c218433..1bf672966a62 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -196,8 +196,11 @@ static int vcn_v2_5_sw_init(void *handle) return r; } - fw_shared = adev->vcn.inst[j].fw_shared_cpu_addr; + fw_shared = adev->vcn.inst[j].fw_shared.cpu_addr; fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG); + + if (amdgpu_vcnfw_log) + amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); } if (amdgpu_sriov_vf(adev)) { @@ -229,7 +232,7 @@ static int vcn_v2_5_sw_fini(void *handle) for (i = 0; i < adev->vcn.num_vcn_inst; i++) { if (adev->vcn.harvest_config & (1 << i)) continue; - fw_shared = adev->vcn.inst[i].fw_shared_cpu_addr; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; fw_shared->present_flag_0 = 0; } drm_dev_exit(idx); @@ -423,9 +426,9 @@ static void vcn_v2_5_mc_resume(struct amdgpu_device *adev) /* non-cache window */ WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW, - lower_32_bits(adev->vcn.inst[i].fw_shared_gpu_addr)); + lower_32_bits(adev->vcn.inst[i].fw_shared.gpu_addr)); WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH, - upper_32_bits(adev->vcn.inst[i].fw_shared_gpu_addr)); + upper_32_bits(adev->vcn.inst[i].fw_shared.gpu_addr)); WREG32_SOC15(VCN, i, mmUVD_VCPU_NONCACHE_OFFSET0, 0); WREG32_SOC15(VCN, i, mmUVD_VCPU_NONCACHE_SIZE0, AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared))); @@ -513,10 +516,10 @@ static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx /* non-cache window */ WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, 0, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW), - lower_32_bits(adev->vcn.inst[inst_idx].fw_shared_gpu_addr), 0, indirect); + lower_32_bits(adev->vcn.inst[inst_idx].fw_shared.gpu_addr), 0, indirect); WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, 0, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH), - upper_32_bits(adev->vcn.inst[inst_idx].fw_shared_gpu_addr), 0, indirect); + upper_32_bits(adev->vcn.inst[inst_idx].fw_shared.gpu_addr), 0, indirect); WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, 0, mmUVD_VCPU_NONCACHE_OFFSET0), 0, 0, indirect); WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( @@ -757,7 +760,7 @@ static void vcn_v2_5_enable_clock_gating(struct amdgpu_device *adev) static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) { - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared_cpu_addr; + 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; @@ -981,7 +984,7 @@ static int vcn_v2_5_start(struct amdgpu_device *adev) vcn_v2_5_mc_resume(adev); for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[i].fw_shared_cpu_addr; + volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; if (adev->vcn.harvest_config & (1 << i)) continue; /* VCN global tiling registers */ @@ -1403,7 +1406,7 @@ static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); if (!ret_code) { - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared_cpu_addr; + volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; /* pause DPG */ reg_data |= UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK; @@ -1512,6 +1515,7 @@ static void vcn_v2_5_dec_ring_set_wptr(struct amdgpu_ring *ring) static const struct amdgpu_ring_funcs vcn_v2_5_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .secure_submission_supported = true, .vmhub = AMDGPU_MMHUB_1, .get_rptr = vcn_v2_5_dec_ring_get_rptr, .get_wptr = vcn_v2_5_dec_ring_get_wptr, @@ -1542,6 +1546,7 @@ static const struct amdgpu_ring_funcs vcn_v2_5_dec_ring_vm_funcs = { static const struct amdgpu_ring_funcs vcn_v2_6_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .secure_submission_supported = true, .vmhub = AMDGPU_MMHUB_0, .get_rptr = vcn_v2_5_dec_ring_get_rptr, .get_wptr = vcn_v2_5_dec_ring_get_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index da11ceba0698..c87263ed20ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -25,6 +25,7 @@ #include "amdgpu.h" #include "amdgpu_vcn.h" #include "amdgpu_pm.h" +#include "amdgpu_cs.h" #include "soc15.h" #include "soc15d.h" #include "vcn_v2_0.h" @@ -213,11 +214,14 @@ static int vcn_v3_0_sw_init(void *handle) return r; } - fw_shared = adev->vcn.inst[i].fw_shared_cpu_addr; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_SW_RING_FLAG) | cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) | cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB); fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED); + + if (amdgpu_vcnfw_log) + amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); } if (amdgpu_sriov_vf(adev)) { @@ -249,7 +253,7 @@ static int vcn_v3_0_sw_fini(void *handle) if (adev->vcn.harvest_config & (1 << i)) continue; - fw_shared = adev->vcn.inst[i].fw_shared_cpu_addr; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; fw_shared->present_flag_0 = 0; fw_shared->sw_ring.is_enabled = false; } @@ -295,6 +299,7 @@ static int vcn_v3_0_hw_init(void *handle) ring = &adev->vcn.inst[i].ring_dec; if (amdgpu_vcn_is_disabled_vcn(adev, VCN_DECODE_RING, i)) { ring->sched.ready = false; + ring->no_scheduler = true; dev_info(adev->dev, "ring %s is disabled by hypervisor\n", ring->name); } else { ring->wptr = 0; @@ -307,6 +312,7 @@ static int vcn_v3_0_hw_init(void *handle) ring = &adev->vcn.inst[i].ring_enc[j]; if (amdgpu_vcn_is_disabled_vcn(adev, VCN_ENCODE_RING, i)) { ring->sched.ready = false; + ring->no_scheduler = true; dev_info(adev->dev, "ring %s is disabled by hypervisor\n", ring->name); } else { ring->wptr = 0; @@ -469,9 +475,9 @@ static void vcn_v3_0_mc_resume(struct amdgpu_device *adev, int inst) /* non-cache window */ WREG32_SOC15(VCN, inst, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW, - lower_32_bits(adev->vcn.inst[inst].fw_shared_gpu_addr)); + lower_32_bits(adev->vcn.inst[inst].fw_shared.gpu_addr)); WREG32_SOC15(VCN, inst, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH, - upper_32_bits(adev->vcn.inst[inst].fw_shared_gpu_addr)); + upper_32_bits(adev->vcn.inst[inst].fw_shared.gpu_addr)); WREG32_SOC15(VCN, inst, mmUVD_VCPU_NONCACHE_OFFSET0, 0); WREG32_SOC15(VCN, inst, mmUVD_VCPU_NONCACHE_SIZE0, AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared))); @@ -558,10 +564,10 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx /* non-cache window */ WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, inst_idx, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW), - lower_32_bits(adev->vcn.inst[inst_idx].fw_shared_gpu_addr), 0, indirect); + lower_32_bits(adev->vcn.inst[inst_idx].fw_shared.gpu_addr), 0, indirect); WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, inst_idx, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH), - upper_32_bits(adev->vcn.inst[inst_idx].fw_shared_gpu_addr), 0, indirect); + upper_32_bits(adev->vcn.inst[inst_idx].fw_shared.gpu_addr), 0, indirect); WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, inst_idx, mmUVD_VCPU_NONCACHE_OFFSET0), 0, 0, indirect); WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( @@ -923,7 +929,7 @@ static void vcn_v3_0_enable_clock_gating(struct amdgpu_device *adev, int inst) static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) { - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared_cpu_addr; + 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; @@ -1220,7 +1226,7 @@ static int vcn_v3_0_start(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1); WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp); - fw_shared = adev->vcn.inst[i].fw_shared_cpu_addr; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; fw_shared->multi_queue.decode_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET); /* programm the RB_BASE for ring buffer */ @@ -1611,7 +1617,7 @@ static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev, if (adev->ip_versions[UVD_HWIP][0] != IP_VERSION(3, 0, 33)) { /* Restore */ - fw_shared = adev->vcn.inst[inst_idx].fw_shared_cpu_addr; + fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET); ring = &adev->vcn.inst[inst_idx].ring_enc[0]; ring->wptr = 0; @@ -1700,7 +1706,7 @@ static void vcn_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring) if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { /*whenever update RBC_RB_WPTR, we save the wptr in shared rb.wptr and scratch2 */ - fw_shared = adev->vcn.inst[ring->me].fw_shared_cpu_addr; + fw_shared = adev->vcn.inst[ring->me].fw_shared.cpu_addr; fw_shared->rb.wptr = lower_32_bits(ring->wptr); WREG32_SOC15(VCN, ring->me, mmUVD_SCRATCH2, lower_32_bits(ring->wptr)); @@ -1780,6 +1786,7 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_sw_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0x3f, .nop = VCN_DEC_SW_CMD_NO_OP, + .secure_submission_supported = true, .vmhub = AMDGPU_MMHUB_0, .get_rptr = vcn_v3_0_dec_ring_get_rptr, .get_wptr = vcn_v3_0_dec_ring_get_wptr, @@ -1806,21 +1813,23 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_sw_ring_vm_funcs = { .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, }; -static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p) +static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p, + struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; /* The create msg must be in the first IB submitted */ - if (atomic_read(&p->entity->fence_seq)) + if (atomic_read(&job->base.entity->fence_seq)) return -EINVAL; scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC] [AMDGPU_RING_PRIO_DEFAULT].sched; - drm_sched_entity_modify_sched(p->entity, scheds, 1); + drm_sched_entity_modify_sched(job->base.entity, scheds, 1); return 0; } -static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr) +static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, + uint64_t addr) { struct ttm_operation_ctx ctx = { false, false }; struct amdgpu_bo_va_mapping *map; @@ -1891,7 +1900,7 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr) if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11) continue; - r = vcn_v3_0_limit_sched(p); + r = vcn_v3_0_limit_sched(p, job); if (r) goto out; } @@ -1902,10 +1911,10 @@ out: } static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, - uint32_t ib_idx) + struct amdgpu_job *job, + struct amdgpu_ib *ib) { - struct amdgpu_ring *ring = to_amdgpu_ring(p->entity->rq->sched); - struct amdgpu_ib *ib = &p->job->ibs[ib_idx]; + struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched); uint32_t msg_lo = 0, msg_hi = 0; unsigned i; int r; @@ -1915,8 +1924,8 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, return 0; for (i = 0; i < ib->length_dw; i += 2) { - uint32_t reg = amdgpu_get_ib_value(p, ib_idx, i); - uint32_t val = amdgpu_get_ib_value(p, ib_idx, i + 1); + 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)) { msg_lo = val; @@ -1924,7 +1933,8 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, msg_hi = val; } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0) && val == 0) { - r = vcn_v3_0_dec_msg(p, ((u64)msg_hi) << 32 | msg_lo); + r = vcn_v3_0_dec_msg(p, job, + ((u64)msg_hi) << 32 | msg_lo); if (r) return r; } @@ -1935,6 +1945,7 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, static const struct amdgpu_ring_funcs vcn_v3_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .secure_submission_supported = true, .vmhub = AMDGPU_MMHUB_0, .get_rptr = vcn_v3_0_dec_ring_get_rptr, .get_wptr = vcn_v3_0_dec_ring_get_wptr, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 59d3fe269e7c..607f65ab39ac 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1759,14 +1759,18 @@ static int criu_checkpoint_bos(struct kfd_process *p, goto exit; } } - if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { + if (bo_bucket->alloc_flags + & (KFD_IOC_ALLOC_MEM_FLAGS_VRAM | KFD_IOC_ALLOC_MEM_FLAGS_GTT)) { ret = criu_get_prime_handle(&dumper_bo->tbo.base, bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE ? DRM_RDWR : 0, &bo_bucket->dmabuf_fd); if (ret) goto exit; + } else { + bo_bucket->dmabuf_fd = KFD_INVALID_FD; } + if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) bo_bucket->offset = KFD_MMAP_TYPE_DOORBELL | KFD_MMAP_GPU_ID(pdd->dev->id); @@ -1812,7 +1816,8 @@ static int criu_checkpoint_bos(struct kfd_process *p, exit: while (ret && bo_index--) { - if (bo_buckets[bo_index].alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) + if (bo_buckets[bo_index].alloc_flags + & (KFD_IOC_ALLOC_MEM_FLAGS_VRAM | KFD_IOC_ALLOC_MEM_FLAGS_GTT)) close_fd(bo_buckets[bo_index].dmabuf_fd); } @@ -2094,6 +2099,136 @@ exit: return ret; } +static int criu_restore_memory_of_gpu(struct kfd_process_device *pdd, + struct kfd_criu_bo_bucket *bo_bucket, + struct kfd_criu_bo_priv_data *bo_priv, + struct kgd_mem **kgd_mem) +{ + int idr_handle; + int ret; + const bool criu_resume = true; + u64 offset; + + if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) { + if (bo_bucket->size != kfd_doorbell_process_slice(pdd->dev)) + return -EINVAL; + + offset = kfd_get_process_doorbells(pdd); + } else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) { + /* MMIO BOs need remapped bus address */ + if (bo_bucket->size != PAGE_SIZE) { + pr_err("Invalid page size\n"); + return -EINVAL; + } + offset = pdd->dev->adev->rmmio_remap.bus_addr; + if (!offset) { + pr_err("amdgpu_amdkfd_get_mmio_remap_phys_addr failed\n"); + return -ENOMEM; + } + } else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) { + offset = bo_priv->user_addr; + } + /* Create the BO */ + ret = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(pdd->dev->adev, bo_bucket->addr, + bo_bucket->size, pdd->drm_priv, kgd_mem, + &offset, bo_bucket->alloc_flags, criu_resume); + if (ret) { + pr_err("Could not create the BO\n"); + return ret; + } + pr_debug("New BO created: size:0x%llx addr:0x%llx offset:0x%llx\n", + bo_bucket->size, bo_bucket->addr, offset); + + /* Restore previous IDR handle */ + pr_debug("Restoring old IDR handle for the BO"); + idr_handle = idr_alloc(&pdd->alloc_idr, *kgd_mem, bo_priv->idr_handle, + bo_priv->idr_handle + 1, GFP_KERNEL); + + if (idr_handle < 0) { + pr_err("Could not allocate idr\n"); + amdgpu_amdkfd_gpuvm_free_memory_of_gpu(pdd->dev->adev, *kgd_mem, pdd->drm_priv, + NULL); + return -ENOMEM; + } + + if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) + bo_bucket->restored_offset = KFD_MMAP_TYPE_DOORBELL | KFD_MMAP_GPU_ID(pdd->dev->id); + if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) { + bo_bucket->restored_offset = KFD_MMAP_TYPE_MMIO | KFD_MMAP_GPU_ID(pdd->dev->id); + } else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_GTT) { + bo_bucket->restored_offset = offset; + } else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { + bo_bucket->restored_offset = offset; + /* Update the VRAM usage count */ + WRITE_ONCE(pdd->vram_usage, pdd->vram_usage + bo_bucket->size); + } + return 0; +} + +static int criu_restore_bo(struct kfd_process *p, + struct kfd_criu_bo_bucket *bo_bucket, + struct kfd_criu_bo_priv_data *bo_priv) +{ + struct kfd_process_device *pdd; + struct kgd_mem *kgd_mem; + int ret; + int j; + + pr_debug("Restoring BO size:0x%llx addr:0x%llx gpu_id:0x%x flags:0x%x idr_handle:0x%x\n", + bo_bucket->size, bo_bucket->addr, bo_bucket->gpu_id, bo_bucket->alloc_flags, + bo_priv->idr_handle); + + pdd = kfd_process_device_data_by_id(p, bo_bucket->gpu_id); + if (!pdd) { + pr_err("Failed to get pdd\n"); + return -ENODEV; + } + + ret = criu_restore_memory_of_gpu(pdd, bo_bucket, bo_priv, &kgd_mem); + if (ret) + return ret; + + /* now map these BOs to GPU/s */ + for (j = 0; j < p->n_pdds; j++) { + struct kfd_dev *peer; + struct kfd_process_device *peer_pdd; + + if (!bo_priv->mapped_gpuids[j]) + break; + + peer_pdd = kfd_process_device_data_by_id(p, bo_priv->mapped_gpuids[j]); + if (!peer_pdd) + return -EINVAL; + + peer = peer_pdd->dev; + + peer_pdd = kfd_bind_process_to_device(peer, p); + if (IS_ERR(peer_pdd)) + return PTR_ERR(peer_pdd); + + ret = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(peer->adev, kgd_mem, peer_pdd->drm_priv, + NULL); + if (ret) { + pr_err("Failed to map to gpu %d/%d\n", j, p->n_pdds); + return ret; + } + } + + pr_debug("map memory was successful for the BO\n"); + /* create the dmabuf object and export the bo */ + if (bo_bucket->alloc_flags + & (KFD_IOC_ALLOC_MEM_FLAGS_VRAM | KFD_IOC_ALLOC_MEM_FLAGS_GTT)) { + ret = criu_get_prime_handle(&kgd_mem->bo->tbo.base, DRM_RDWR, + &bo_bucket->dmabuf_fd); + if (ret) + return ret; + } else { + bo_bucket->dmabuf_fd = KFD_INVALID_FD; + } + + return 0; +} + static int criu_restore_bos(struct kfd_process *p, struct kfd_ioctl_criu_args *args, uint64_t *priv_offset, @@ -2101,9 +2236,7 @@ static int criu_restore_bos(struct kfd_process *p, { struct kfd_criu_bo_bucket *bo_buckets = NULL; struct kfd_criu_bo_priv_data *bo_privs = NULL; - const bool criu_resume = true; - bool flush_tlbs = false; - int ret = 0, j = 0; + int ret = 0; uint32_t i = 0; if (*priv_offset + (args->num_bos * sizeof(*bo_privs)) > max_priv_data_size) @@ -2141,178 +2274,13 @@ static int criu_restore_bos(struct kfd_process *p, /* Create and map new BOs */ for (; i < args->num_bos; i++) { - struct kfd_criu_bo_bucket *bo_bucket; - struct kfd_criu_bo_priv_data *bo_priv; - struct kfd_dev *dev; - struct kfd_process_device *pdd; - struct kgd_mem *kgd_mem; - void *mem; - u64 offset; - int idr_handle; - - bo_bucket = &bo_buckets[i]; - bo_priv = &bo_privs[i]; - - pr_debug("kfd restore ioctl - bo_bucket[%d]:\n", i); - pr_debug("size = 0x%llx, bo_addr = 0x%llx bo_offset = 0x%llx\n" - "gpu_id = 0x%x alloc_flags = 0x%x\n" - "idr_handle = 0x%x\n", - bo_bucket->size, - bo_bucket->addr, - bo_bucket->offset, - bo_bucket->gpu_id, - bo_bucket->alloc_flags, - bo_priv->idr_handle); - - pdd = kfd_process_device_data_by_id(p, bo_bucket->gpu_id); - if (!pdd) { - pr_err("Failed to get pdd\n"); - ret = -ENODEV; - goto exit; - } - dev = pdd->dev; - - if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) { - pr_debug("restore ioctl: KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL\n"); - if (bo_bucket->size != kfd_doorbell_process_slice(dev)) { - ret = -EINVAL; - goto exit; - } - offset = kfd_get_process_doorbells(pdd); - } else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) { - /* MMIO BOs need remapped bus address */ - pr_debug("restore ioctl :KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP\n"); - if (bo_bucket->size != PAGE_SIZE) { - pr_err("Invalid page size\n"); - ret = -EINVAL; - goto exit; - } - offset = dev->adev->rmmio_remap.bus_addr; - if (!offset) { - pr_err("amdgpu_amdkfd_get_mmio_remap_phys_addr failed\n"); - ret = -ENOMEM; - goto exit; - } - } else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) { - offset = bo_priv->user_addr; - } - /* Create the BO */ - ret = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(dev->adev, - bo_bucket->addr, - bo_bucket->size, - pdd->drm_priv, - (struct kgd_mem **) &mem, - &offset, - bo_bucket->alloc_flags, - criu_resume); - if (ret) { - pr_err("Could not create the BO\n"); - ret = -ENOMEM; - goto exit; - } - pr_debug("New BO created: size = 0x%llx, bo_addr = 0x%llx bo_offset = 0x%llx\n", - bo_bucket->size, bo_bucket->addr, offset); - - /* Restore previuos IDR handle */ - pr_debug("Restoring old IDR handle for the BO"); - idr_handle = idr_alloc(&pdd->alloc_idr, mem, - bo_priv->idr_handle, - bo_priv->idr_handle + 1, GFP_KERNEL); - - if (idr_handle < 0) { - pr_err("Could not allocate idr\n"); - amdgpu_amdkfd_gpuvm_free_memory_of_gpu(dev->adev, - (struct kgd_mem *)mem, - pdd->drm_priv, NULL); - ret = -ENOMEM; - goto exit; - } - - if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) - bo_bucket->restored_offset = KFD_MMAP_TYPE_DOORBELL | - KFD_MMAP_GPU_ID(pdd->dev->id); - if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) { - bo_bucket->restored_offset = KFD_MMAP_TYPE_MMIO | - KFD_MMAP_GPU_ID(pdd->dev->id); - } else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_GTT) { - bo_bucket->restored_offset = offset; - pr_debug("updating offset for GTT\n"); - } else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { - bo_bucket->restored_offset = offset; - /* Update the VRAM usage count */ - WRITE_ONCE(pdd->vram_usage, pdd->vram_usage + bo_bucket->size); - pr_debug("updating offset for VRAM\n"); - } - - /* now map these BOs to GPU/s */ - for (j = 0; j < p->n_pdds; j++) { - struct kfd_dev *peer; - struct kfd_process_device *peer_pdd; - bool table_freed = false; - - if (!bo_priv->mapped_gpuids[j]) - break; - - peer_pdd = kfd_process_device_data_by_id(p, bo_priv->mapped_gpuids[j]); - if (!peer_pdd) { - ret = -EINVAL; - goto exit; - } - peer = peer_pdd->dev; - - peer_pdd = kfd_bind_process_to_device(peer, p); - if (IS_ERR(peer_pdd)) { - ret = PTR_ERR(peer_pdd); - goto exit; - } - pr_debug("map mem in restore ioctl -> 0x%llx\n", - ((struct kgd_mem *)mem)->va); - ret = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(peer->adev, - (struct kgd_mem *)mem, peer_pdd->drm_priv, &table_freed); - if (ret) { - pr_err("Failed to map to gpu %d/%d\n", j, p->n_pdds); - goto exit; - } - if (table_freed) - flush_tlbs = true; - } - - ret = amdgpu_amdkfd_gpuvm_sync_memory(dev->adev, - (struct kgd_mem *) mem, true); + ret = criu_restore_bo(p, &bo_buckets[i], &bo_privs[i]); if (ret) { - pr_debug("Sync memory failed, wait interrupted by user signal\n"); + pr_debug("Failed to restore BO[%d] ret%d\n", i, ret); goto exit; } - - pr_debug("map memory was successful for the BO\n"); - /* create the dmabuf object and export the bo */ - kgd_mem = (struct kgd_mem *)mem; - if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { - ret = criu_get_prime_handle(&kgd_mem->bo->tbo.base, - DRM_RDWR, - &bo_bucket->dmabuf_fd); - if (ret) - goto exit; - } } /* done */ - if (flush_tlbs) { - /* Flush TLBs after waiting for the page table updates to complete */ - for (j = 0; j < p->n_pdds; j++) { - struct kfd_dev *peer; - struct kfd_process_device *pdd = p->pdds[j]; - struct kfd_process_device *peer_pdd; - - peer = kfd_device_by_id(pdd->dev->id); - if (WARN_ON_ONCE(!peer)) - continue; - peer_pdd = kfd_get_process_device_data(peer, p); - if (WARN_ON_ONCE(!peer_pdd)) - continue; - kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY); - } - } - /* Copy only the buckets back so user can read bo_buckets[N].restored_offset */ ret = copy_to_user((void __user *)args->bos, bo_buckets, @@ -2322,7 +2290,8 @@ static int criu_restore_bos(struct kfd_process *p, exit: while (ret && i--) { - if (bo_buckets[i].alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) + if (bo_buckets[i].alloc_flags + & (KFD_IOC_ALLOC_MEM_FLAGS_VRAM | KFD_IOC_ALLOC_MEM_FLAGS_GTT)) close_fd(bo_buckets[i].dmabuf_fd); } kvfree(bo_buckets); 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 1cd2ea536bd0..acf4f7975850 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -500,6 +500,11 @@ static int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process pr_debug("Killing all process wavefronts\n"); + if (!dev->kfd2kgd->get_atc_vmid_pasid_mapping_info) { + pr_err("no vmid pasid mapping supported \n"); + return -EOPNOTSUPP; + } + /* Scan all registers in the range ATC_VMID8_PASID_MAPPING .. * ATC_VMID15_PASID_MAPPING * to check which VMID the current process is mapped to. diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 7f689094be5a..7e3a7fcb9fe6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -24,6 +24,7 @@ #include <linux/hmm.h> #include <linux/dma-direction.h> #include <linux/dma-mapping.h> +#include <linux/migrate.h> #include "amdgpu_sync.h" #include "amdgpu_object.h" #include "amdgpu_vm.h" @@ -221,7 +222,6 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn) page = pfn_to_page(pfn); svm_range_bo_ref(prange->svm_bo); page->zone_device_data = prange->svm_bo; - get_page(page); lock_page(page); } @@ -638,6 +638,22 @@ out_oom: return r; } +/** + * svm_migrate_vma_to_ram - migrate range inside one vma from device to system + * + * @adev: amdgpu device to migrate from + * @prange: svm range structure + * @vma: vm_area_struct that range [start, end] belongs to + * @start: range start virtual address in pages + * @end: range end virtual address in pages + * + * Context: Process context, caller hold mmap read lock, prange->migrate_mutex + * + * Return: + * 0 - success with all pages migrated + * negative values - indicate error + * positive values - partial migration, number of pages not migrated + */ static long svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, struct vm_area_struct *vma, uint64_t start, uint64_t end) @@ -709,8 +725,6 @@ out: pdd = svm_range_get_pdd_by_adev(prange, adev); if (pdd) WRITE_ONCE(pdd->page_out, pdd->page_out + cpages); - - return upages; } return r ? r : upages; } @@ -720,7 +734,7 @@ out: * @prange: range structure * @mm: process mm, use current->mm if NULL * - * Context: Process context, caller hold mmap read lock, svms lock, prange lock + * Context: Process context, caller hold mmap read lock, prange->migrate_mutex * * Return: * 0 - OK, otherwise error code @@ -759,13 +773,16 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm) unsigned long next; vma = find_vma(mm, addr); - if (!vma || addr < vma->vm_start) + if (!vma || addr < vma->vm_start) { + pr_debug("failed to find vma for prange %p\n", prange); + r = -EFAULT; break; + } next = min(vma->vm_end, end); r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next); if (r < 0) { - pr_debug("failed %ld to migrate\n", r); + pr_debug("failed %ld to migrate prange %p\n", r, prange); break; } else { upages += r; @@ -773,7 +790,7 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm) addr = next; } - if (!upages) { + if (r >= 0 && !upages) { svm_range_vram_node_free(prange); prange->actual_loc = 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index f36062be9ca8..9967a73d5b0f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -26,6 +26,7 @@ #include <linux/hashtable.h> #include <linux/mmu_notifier.h> +#include <linux/memremap.h> #include <linux/mutex.h> #include <linux/types.h> #include <linux/atomic.h> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index f9eafc796e70..e4beebb1c80a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -82,7 +82,8 @@ static ssize_t kfd_smi_ev_read(struct file *filep, char __user *user, struct kfd_smi_client *client = filep->private_data; unsigned char *buf; - buf = kmalloc_array(MAX_KFIFO_SIZE, sizeof(*buf), GFP_KERNEL); + size = min_t(size_t, size, MAX_KFIFO_SIZE); + buf = kmalloc(size, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -96,7 +97,7 @@ static ssize_t kfd_smi_ev_read(struct file *filep, char __user *user, ret = -EAGAIN; goto ret_err; } - to_copy = min3(size, sizeof(buf), to_copy); + to_copy = min(size, to_copy); ret = kfifo_out(&client->fifo, buf, to_copy); spin_unlock(&client->lock); if (ret <= 0) { @@ -175,22 +176,29 @@ static void add_event_to_kfifo(struct kfd_dev *dev, unsigned int smi_event, rcu_read_unlock(); } -void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset) +__printf(3, 4) +static void kfd_smi_event_add(struct kfd_dev *dev, unsigned int event, + char *fmt, ...) { - /* - * GpuReset msg = Reset seq number (incremented for - * every reset message sent before GPU reset). - * 1 byte event + 1 byte space + 8 bytes seq num + - * 1 byte \n + 1 byte \0 = 12 - */ - char fifo_in[12]; + char fifo_in[KFD_SMI_EVENT_MSG_SIZE]; int len; - unsigned int event; + va_list args; if (list_empty(&dev->smi_clients)) return; - memset(fifo_in, 0x0, sizeof(fifo_in)); + len = snprintf(fifo_in, sizeof(fifo_in), "%x ", event); + + va_start(args, fmt); + len += vsnprintf(fifo_in + len, sizeof(fifo_in) - len, fmt, args); + va_end(args); + + add_event_to_kfifo(dev, event, fifo_in, len); +} + +void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset) +{ + unsigned int event; if (post_reset) { event = KFD_SMI_EVENT_GPU_POST_RESET; @@ -198,48 +206,20 @@ void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset) event = KFD_SMI_EVENT_GPU_PRE_RESET; ++(dev->reset_seq_num); } - - len = snprintf(fifo_in, sizeof(fifo_in), "%x %x\n", event, - dev->reset_seq_num); - - add_event_to_kfifo(dev, event, fifo_in, len); + kfd_smi_event_add(dev, event, "%x\n", dev->reset_seq_num); } void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev, uint64_t throttle_bitmask) { - /* - * ThermalThrottle msg = throttle_bitmask(8): - * thermal_interrupt_count(16): - * 1 byte event + 1 byte space + 16 byte throttle_bitmask + - * 1 byte : + 16 byte thermal_interupt_counter + 1 byte \n + - * 1 byte \0 = 37 - */ - char fifo_in[37]; - int len; - - if (list_empty(&dev->smi_clients)) - return; - - len = snprintf(fifo_in, sizeof(fifo_in), "%x %llx:%llx\n", - KFD_SMI_EVENT_THERMAL_THROTTLE, throttle_bitmask, - amdgpu_dpm_get_thermal_throttling_counter(dev->adev)); - - add_event_to_kfifo(dev, KFD_SMI_EVENT_THERMAL_THROTTLE, fifo_in, len); + kfd_smi_event_add(dev, KFD_SMI_EVENT_THERMAL_THROTTLE, "%llx:%llx\n", + throttle_bitmask, + amdgpu_dpm_get_thermal_throttling_counter(dev->adev)); } void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid) { struct amdgpu_task_info task_info; - /* VmFault msg = (hex)uint32_pid(8) + :(1) + task name(16) = 25 */ - /* 1 byte event + 1 byte space + 25 bytes msg + 1 byte \n + - * 1 byte \0 = 29 - */ - char fifo_in[29]; - int len; - - if (list_empty(&dev->smi_clients)) - return; memset(&task_info, 0, sizeof(struct amdgpu_task_info)); amdgpu_vm_get_task_info(dev->adev, pasid, &task_info); @@ -247,10 +227,8 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid) if (!task_info.pid) return; - len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT, - task_info.pid, task_info.task_name); - - add_event_to_kfifo(dev, KFD_SMI_EVENT_VMFAULT, fifo_in, len); + kfd_smi_event_add(dev, KFD_SMI_EVENT_VMFAULT, "%x:%s\n", + task_info.pid, task_info.task_name); } int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index b71d47afd243..3b8856b4cece 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1629,6 +1629,7 @@ retry_flush_work: static void svm_range_restore_work(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); + struct amdkfd_process_info *process_info; struct svm_range_list *svms; struct svm_range *prange; struct kfd_process *p; @@ -1645,6 +1646,7 @@ static void svm_range_restore_work(struct work_struct *work) pr_debug("restore svm ranges\n"); p = container_of(svms, struct kfd_process, svms); + process_info = p->kgd_process_info; /* Keep mm reference when svm_range_validate_and_map ranges */ mm = get_task_mm(p->lead_thread); @@ -1653,6 +1655,7 @@ static void svm_range_restore_work(struct work_struct *work) return; } + mutex_lock(&process_info->lock); svm_range_list_lock_and_flush_work(svms, mm); mutex_lock(&svms->lock); @@ -1705,6 +1708,7 @@ static void svm_range_restore_work(struct work_struct *work) out_reschedule: mutex_unlock(&svms->lock); mmap_write_unlock(mm); + mutex_unlock(&process_info->lock); mmput(mm); /* If validation failed, reschedule another attempt */ @@ -3151,6 +3155,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) struct svm_range_bo *svm_bo; struct kfd_process *p; struct mm_struct *mm; + int r = 0; svm_bo = container_of(work, struct svm_range_bo, eviction_work); if (!svm_bo_ref_unless_zero(svm_bo)) @@ -3166,7 +3171,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) mmap_read_lock(mm); spin_lock(&svm_bo->list_lock); - while (!list_empty(&svm_bo->range_list)) { + while (!list_empty(&svm_bo->range_list) && !r) { struct svm_range *prange = list_first_entry(&svm_bo->range_list, struct svm_range, svm_bo_list); @@ -3180,15 +3185,18 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) mutex_lock(&prange->migrate_mutex); do { - svm_migrate_vram_to_ram(prange, + r = svm_migrate_vram_to_ram(prange, svm_bo->eviction_fence->mm); - } while (prange->actual_loc && --retries); - WARN(prange->actual_loc, "Migration failed during eviction"); + } while (!r && prange->actual_loc && --retries); - mutex_lock(&prange->lock); - prange->svm_bo = NULL; - mutex_unlock(&prange->lock); + if (!r && prange->actual_loc) + pr_info_once("Migration failed during eviction"); + if (!prange->actual_loc) { + mutex_lock(&prange->lock); + prange->svm_bo = NULL; + mutex_unlock(&prange->lock); + } mutex_unlock(&prange->migrate_mutex); spin_lock(&svm_bo->list_lock); @@ -3197,10 +3205,11 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) mmap_read_unlock(mm); dma_fence_signal(&svm_bo->eviction_fence->base); + /* This is the last reference to svm_bo, after svm_range_vram_node_free * has been called in svm_migrate_vram_to_ram */ - WARN_ONCE(kref_read(&svm_bo->kref) != 1, "This was not the last reference\n"); + WARN_ONCE(!r && kref_read(&svm_bo->kref) != 1, "This was not the last reference\n"); svm_range_bo_unref(svm_bo); } @@ -3209,6 +3218,7 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm, uint64_t start, uint64_t size, uint32_t nattr, struct kfd_ioctl_svm_attribute *attrs) { + struct amdkfd_process_info *process_info = p->kgd_process_info; struct list_head update_list; struct list_head insert_list; struct list_head remove_list; @@ -3226,6 +3236,8 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm, svms = &p->svms; + mutex_lock(&process_info->lock); + svm_range_list_lock_and_flush_work(svms, mm); r = svm_range_is_valid(p, start, size); @@ -3300,6 +3312,8 @@ out_unlock_range: mutex_unlock(&svms->lock); mmap_read_unlock(mm); out: + mutex_unlock(&process_info->lock); + pr_debug("pasid 0x%x svms 0x%p [0x%llx 0x%llx] done, r=%d\n", p->pasid, &p->svms, start, start + size - 1, r); 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 e1d3db3fe8de..b30656959fd8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1481,6 +1481,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) case IP_VERSION(3, 1, 2): case IP_VERSION(3, 1, 3): case IP_VERSION(3, 1, 5): + case IP_VERSION(3, 1, 6): init_data.flags.gpu_vm_support = true; break; default: @@ -2633,10 +2634,13 @@ static int dm_resume(void *handle) * before the 0 streams commit. * * DC expects that link encoder assignments are *not* valid - * when committing a state, so as a workaround it needs to be - * cleared here. + * when committing a state, so as a workaround we can copy + * off of the current state. + * + * We lose the previous assignments, but we had already + * commit 0 streams anyway. */ - link_enc_cfg_init(dm->dc, dc_state); + link_enc_cfg_copy(adev->dm.dc->current_state, dc_state); if (dc_enable_dmub_notifications(adev->dm.dc)) amdgpu_dm_outbox_init(adev); @@ -6356,7 +6360,7 @@ get_highest_refresh_rate_mode(struct amdgpu_dm_connector *aconnector, } } - aconnector->freesync_vid_base = *m_pref; + drm_mode_copy(&aconnector->freesync_vid_base, m_pref); return m_pref; } @@ -6469,8 +6473,8 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, recalculate_timing = is_freesync_video_mode(&mode, aconnector); if (recalculate_timing) { freesync_mode = get_highest_refresh_rate_mode(aconnector, false); - saved_mode = mode; - mode = *freesync_mode; + drm_mode_copy(&saved_mode, &mode); + drm_mode_copy(&mode, freesync_mode); } else { decide_crtc_timing_for_drm_display_mode( &mode, preferred_mode, scale); @@ -10177,27 +10181,27 @@ static bool is_timing_unchanged_for_freesync(struct drm_crtc_state *old_crtc_state, struct drm_crtc_state *new_crtc_state) { - struct drm_display_mode old_mode, new_mode; + const struct drm_display_mode *old_mode, *new_mode; if (!old_crtc_state || !new_crtc_state) return false; - old_mode = old_crtc_state->mode; - new_mode = new_crtc_state->mode; - - if (old_mode.clock == new_mode.clock && - old_mode.hdisplay == new_mode.hdisplay && - old_mode.vdisplay == new_mode.vdisplay && - old_mode.htotal == new_mode.htotal && - old_mode.vtotal != new_mode.vtotal && - old_mode.hsync_start == new_mode.hsync_start && - old_mode.vsync_start != new_mode.vsync_start && - old_mode.hsync_end == new_mode.hsync_end && - old_mode.vsync_end != new_mode.vsync_end && - old_mode.hskew == new_mode.hskew && - old_mode.vscan == new_mode.vscan && - (old_mode.vsync_end - old_mode.vsync_start) == - (new_mode.vsync_end - new_mode.vsync_start)) + old_mode = &old_crtc_state->mode; + new_mode = &new_crtc_state->mode; + + if (old_mode->clock == new_mode->clock && + old_mode->hdisplay == new_mode->hdisplay && + old_mode->vdisplay == new_mode->vdisplay && + old_mode->htotal == new_mode->htotal && + old_mode->vtotal != new_mode->vtotal && + old_mode->hsync_start == new_mode->hsync_start && + old_mode->vsync_start != new_mode->vsync_start && + old_mode->hsync_end == new_mode->hsync_end && + old_mode->vsync_end != new_mode->vsync_end && + old_mode->hskew == new_mode->hskew && + old_mode->vscan == new_mode->vscan && + (old_mode->vsync_end - old_mode->vsync_start) == + (new_mode->vsync_end - new_mode->vsync_start)) return true; return false; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 777210811311..da17ece1a2c5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -243,6 +243,7 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf, { struct amdgpu_dm_connector *connector = file_inode(f)->i_private; struct dc_link *link = connector->dc_link; + struct amdgpu_device *adev = drm_to_adev(connector->base.dev); struct dc *dc = (struct dc *)link->dc; struct dc_link_settings prefer_link_settings; char *wr_buf = NULL; @@ -302,6 +303,9 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf, if (!valid_input) { kfree(wr_buf); DRM_DEBUG_DRIVER("Invalid Input value No HW will be programmed\n"); + mutex_lock(&adev->dm.dc_lock); + dc_link_set_preferred_training_settings(dc, NULL, NULL, link, false); + mutex_unlock(&adev->dm.dc_lock); return size; } @@ -313,7 +317,9 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf, prefer_link_settings.lane_count = param[0]; prefer_link_settings.link_rate = param[1]; - dc_link_set_preferred_training_settings(dc, &prefer_link_settings, NULL, link, true); + mutex_lock(&adev->dm.dc_lock); + dc_link_set_preferred_training_settings(dc, &prefer_link_settings, NULL, link, false); + mutex_unlock(&adev->dm.dc_lock); kfree(wr_buf); return size; @@ -2883,7 +2889,9 @@ static ssize_t edp_ilr_write(struct file *f, const char __user *buf, kfree(wr_buf); DRM_DEBUG_DRIVER("Invalid Input value. No HW will be programmed\n"); prefer_link_settings.use_link_rate_set = false; + mutex_lock(&adev->dm.dc_lock); dc_link_set_preferred_training_settings(dc, NULL, NULL, link, false); + mutex_unlock(&adev->dm.dc_lock); return size; } 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 740435ae3997..31ac1fce36f8 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 @@ -1198,11 +1198,11 @@ void pre_validate_dsc(struct drm_atomic_state *state, struct dc_state *local_dc_state = NULL; if (!is_dsc_precompute_needed(state)) { - DRM_DEBUG_DRIVER("DSC precompute is not needed.\n"); + DRM_INFO_ONCE("DSC precompute is not needed.\n"); return; } if (dm_atomic_get_state(state, dm_state_ptr)) { - DRM_DEBUG_DRIVER("dm_atomic_get_state() failed\n"); + DRM_INFO_ONCE("dm_atomic_get_state() failed\n"); return; } dm_state = *dm_state_ptr; @@ -1245,7 +1245,7 @@ void pre_validate_dsc(struct drm_atomic_state *state, } if (!pre_compute_mst_dsc_configs_for_state(state, local_dc_state, vars)) { - DRM_DEBUG_DRIVER("pre_compute_mst_dsc_configs_for_state() failed\n"); + DRM_INFO_ONCE("pre_compute_mst_dsc_configs_for_state() failed\n"); goto clean_exit; } @@ -1258,7 +1258,7 @@ void pre_validate_dsc(struct drm_atomic_state *state, if (local_dc_state->streams[i] && is_timing_changed(stream, local_dc_state->streams[i])) { - DRM_DEBUG_DRIVER("crtc[%d] needs mode_changed\n", i); + DRM_INFO_ONCE("crtc[%d] needs mode_changed\n", i); } else { int ind = find_crtc_index_in_state_by_stream(state, stream); diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c index ad13e4e36d77..0e36cd800fc9 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c @@ -456,7 +456,7 @@ static enum bp_result transmitter_control_v2( if ((CONNECTOR_ID_DUAL_LINK_DVII == connector_id) || (CONNECTOR_ID_DUAL_LINK_DVID == connector_id)) /* on INIT this bit should be set according to the - * phisycal connector + * physical connector * Bit0: dual link connector flag * =0 connector is single link connector * =1 connector is dual link connector @@ -468,7 +468,7 @@ static enum bp_result transmitter_control_v2( cpu_to_le16((uint8_t)cntl->connector_obj_id.id); break; case TRANSMITTER_CONTROL_SET_VOLTAGE_AND_PREEMPASIS: - /* votage swing and pre-emphsis */ + /* voltage swing and pre-emphsis */ params.asMode.ucLaneSel = (uint8_t)cntl->lane_select; params.asMode.ucLaneSet = (uint8_t)cntl->lane_settings; break; @@ -2120,7 +2120,7 @@ static enum bp_result program_clock_v5( memset(¶ms, 0, sizeof(params)); if (!bp->cmd_helper->clock_source_id_to_atom( bp_params->pll_id, &atom_pll_id)) { - BREAK_TO_DEBUGGER(); /* Invalid Inpute!! */ + BREAK_TO_DEBUGGER(); /* Invalid Input!! */ return BP_RESULT_BADINPUT; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c index 220682e45b8d..5ed6a93d1708 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c @@ -25,30 +25,23 @@ #include "dccg.h" #include "clk_mgr_internal.h" - #include "dcn30_clk_mgr_smu_msg.h" #include "dcn20/dcn20_clk_mgr.h" #include "dce100/dce_clk_mgr.h" +#include "dcn30/dcn30_clk_mgr.h" #include "reg_helper.h" #include "core_types.h" #include "dm_helpers.h" - #include "atomfirmware.h" - - #include "sienna_cichlid_ip_offset.h" #include "dcn/dcn_3_0_0_offset.h" #include "dcn/dcn_3_0_0_sh_mask.h" - #include "nbio/nbio_7_4_offset.h" - #include "dpcs/dpcs_3_0_0_offset.h" #include "dpcs/dpcs_3_0_0_sh_mask.h" - #include "mmhub/mmhub_2_0_0_offset.h" #include "mmhub/mmhub_2_0_0_sh_mask.h" -/*we don't have clk folder yet*/ -#include "dcn30/dcn30_clk_mgr.h" +#include "dcn30_smu11_driver_if.h" #undef FN #define FN(reg_name, field_name) \ @@ -83,7 +76,7 @@ static const struct clk_mgr_mask clk_mgr_mask = { /* Query SMU for all clock states for a particular clock */ -static void dcn3_init_single_clock(struct clk_mgr_internal *clk_mgr, PPCLK_e clk, unsigned int *entry_0, unsigned int *num_levels) +static void dcn3_init_single_clock(struct clk_mgr_internal *clk_mgr, uint32_t clk, unsigned int *entry_0, unsigned int *num_levels) { unsigned int i; char *entry_i = (char *)entry_0; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c index 8ecc708bcd9e..bfc960579760 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c @@ -29,6 +29,7 @@ #include "clk_mgr_internal.h" #include "reg_helper.h" #include "dalsmc.h" +#include "dcn30_smu11_driver_if.h" #define mmDAL_MSG_REG 0x1628A #define mmDAL_ARG_REG 0x16273 @@ -197,7 +198,7 @@ void dcn30_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr) } /* Returns the actual frequency that was set in MHz, 0 on failure */ -unsigned int dcn30_smu_set_hard_min_by_freq(struct clk_mgr_internal *clk_mgr, PPCLK_e clk, uint16_t freq_mhz) +unsigned int dcn30_smu_set_hard_min_by_freq(struct clk_mgr_internal *clk_mgr, uint32_t clk, uint16_t freq_mhz) { uint32_t response = 0; @@ -215,7 +216,7 @@ unsigned int dcn30_smu_set_hard_min_by_freq(struct clk_mgr_internal *clk_mgr, PP } /* Returns the actual frequency that was set in MHz, 0 on failure */ -unsigned int dcn30_smu_set_hard_max_by_freq(struct clk_mgr_internal *clk_mgr, PPCLK_e clk, uint16_t freq_mhz) +unsigned int dcn30_smu_set_hard_max_by_freq(struct clk_mgr_internal *clk_mgr, uint32_t clk, uint16_t freq_mhz) { uint32_t response = 0; @@ -246,7 +247,7 @@ unsigned int dcn30_smu_set_hard_max_by_freq(struct clk_mgr_internal *clk_mgr, PP * * Returns 0 on failure */ -unsigned int dcn30_smu_get_dpm_freq_by_index(struct clk_mgr_internal *clk_mgr, PPCLK_e clk, uint8_t dpm_level) +unsigned int dcn30_smu_get_dpm_freq_by_index(struct clk_mgr_internal *clk_mgr, uint32_t clk, uint8_t dpm_level) { uint32_t response = 0; @@ -264,7 +265,7 @@ unsigned int dcn30_smu_get_dpm_freq_by_index(struct clk_mgr_internal *clk_mgr, P } /* Returns the max DPM frequency in DC mode in MHz, 0 on failure */ -unsigned int dcn30_smu_get_dc_mode_max_dpm_freq(struct clk_mgr_internal *clk_mgr, PPCLK_e clk) +unsigned int dcn30_smu_get_dc_mode_max_dpm_freq(struct clk_mgr_internal *clk_mgr, uint32_t clk) { uint32_t response = 0; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.h index dd2640a3ce5d..ca9f5296be94 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.h @@ -28,65 +28,6 @@ #include "core_types.h" -#define SMU11_DRIVER_IF_VERSION 0x1F - -typedef enum { - PPCLK_GFXCLK = 0, - PPCLK_SOCCLK, - PPCLK_UCLK, - PPCLK_FCLK, - PPCLK_DCLK_0, - PPCLK_VCLK_0, - PPCLK_DCLK_1, - PPCLK_VCLK_1, - PPCLK_DCEFCLK, - PPCLK_DISPCLK, - PPCLK_PIXCLK, - PPCLK_PHYCLK, - PPCLK_DTBCLK, - PPCLK_COUNT, -} PPCLK_e; - -typedef struct { - uint16_t MinClock; // This is either DCEFCLK or SOCCLK (in MHz) - uint16_t MaxClock; // This is either DCEFCLK or SOCCLK (in MHz) - uint16_t MinUclk; - uint16_t MaxUclk; - - uint8_t WmSetting; - uint8_t Flags; - uint8_t Padding[2]; - -} WatermarkRowGeneric_t; - -#define NUM_WM_RANGES 4 - -typedef enum { - WM_SOCCLK = 0, - WM_DCEFCLK, - WM_COUNT, -} WM_CLOCK_e; - -typedef enum { - WATERMARKS_CLOCK_RANGE = 0, - WATERMARKS_DUMMY_PSTATE, - WATERMARKS_MALL, - WATERMARKS_COUNT, -} WATERMARKS_FLAGS_e; - -typedef struct { - // Watermarks - WatermarkRowGeneric_t WatermarkRow[WM_COUNT][NUM_WM_RANGES]; -} Watermarks_t; - -typedef struct { - Watermarks_t Watermarks; - - uint32_t MmHubPadding[8]; // SMU internal use -} WatermarksExternal_t; - -#define TABLE_WATERMARKS 1 - struct clk_mgr_internal; bool dcn30_smu_test_message(struct clk_mgr_internal *clk_mgr, uint32_t input); @@ -97,10 +38,10 @@ void dcn30_smu_set_dram_addr_high(struct clk_mgr_internal *clk_mgr, uint void dcn30_smu_set_dram_addr_low(struct clk_mgr_internal *clk_mgr, uint32_t addr_low); void dcn30_smu_transfer_wm_table_smu_2_dram(struct clk_mgr_internal *clk_mgr); void dcn30_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr); -unsigned int dcn30_smu_set_hard_min_by_freq(struct clk_mgr_internal *clk_mgr, PPCLK_e clk, uint16_t freq_mhz); -unsigned int dcn30_smu_set_hard_max_by_freq(struct clk_mgr_internal *clk_mgr, PPCLK_e clk, uint16_t freq_mhz); -unsigned int dcn30_smu_get_dpm_freq_by_index(struct clk_mgr_internal *clk_mgr, PPCLK_e clk, uint8_t dpm_level); -unsigned int dcn30_smu_get_dc_mode_max_dpm_freq(struct clk_mgr_internal *clk_mgr, PPCLK_e clk); +unsigned int dcn30_smu_set_hard_min_by_freq(struct clk_mgr_internal *clk_mgr, uint32_t clk, uint16_t freq_mhz); +unsigned int dcn30_smu_set_hard_max_by_freq(struct clk_mgr_internal *clk_mgr, uint32_t clk, uint16_t freq_mhz); +unsigned int dcn30_smu_get_dpm_freq_by_index(struct clk_mgr_internal *clk_mgr, uint32_t clk, uint8_t dpm_level); +unsigned int dcn30_smu_get_dc_mode_max_dpm_freq(struct clk_mgr_internal *clk_mgr, uint32_t clk); void dcn30_smu_set_min_deep_sleep_dcef_clk(struct clk_mgr_internal *clk_mgr, uint32_t freq_mhz); void dcn30_smu_set_num_of_displays(struct clk_mgr_internal *clk_mgr, uint32_t num_displays); void dcn30_smu_set_display_refresh_from_mall(struct clk_mgr_internal *clk_mgr, bool enable, uint8_t cache_timer_delay, uint8_t cache_timer_scale); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_smu11_driver_if.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_smu11_driver_if.h new file mode 100644 index 000000000000..8ea8ee57b39f --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_smu11_driver_if.h @@ -0,0 +1,74 @@ +// This is a stripped-down version of the smu11_driver_if.h file for the relevant DAL interfaces. + +#define SMU11_DRIVER_IF_VERSION 0x40 + +//Only Clks that have DPM descriptors are listed here +typedef enum { + PPCLK_GFXCLK = 0, + PPCLK_SOCCLK, + PPCLK_UCLK, + PPCLK_FCLK, + PPCLK_DCLK_0, + PPCLK_VCLK_0, + PPCLK_DCLK_1, + PPCLK_VCLK_1, + PPCLK_DCEFCLK, + PPCLK_DISPCLK, + PPCLK_PIXCLK, + PPCLK_PHYCLK, + PPCLK_DTBCLK, + PPCLK_COUNT, +} PPCLK_e; + +typedef struct { + uint16_t MinClock; // This is either DCEFCLK or SOCCLK (in MHz) + uint16_t MaxClock; // This is either DCEFCLK or SOCCLK (in MHz) + uint16_t MinUclk; + uint16_t MaxUclk; + + uint8_t WmSetting; + uint8_t Flags; + uint8_t Padding[2]; + +} WatermarkRowGeneric_t; + +#define NUM_WM_RANGES 4 + +typedef enum { + WM_SOCCLK = 0, + WM_DCEFCLK, + WM_COUNT, +} WM_CLOCK_e; + +typedef enum { + WATERMARKS_CLOCK_RANGE = 0, + WATERMARKS_DUMMY_PSTATE, + WATERMARKS_MALL, + WATERMARKS_COUNT, +} WATERMARKS_FLAGS_e; + +typedef struct { + // Watermarks + WatermarkRowGeneric_t WatermarkRow[WM_COUNT][NUM_WM_RANGES]; +} Watermarks_t; + +typedef struct { + Watermarks_t Watermarks; + + uint32_t MmHubPadding[8]; // SMU internal use +} WatermarksExternal_t; + +// Table types +#define TABLE_PPTABLE 0 +#define TABLE_WATERMARKS 1 +#define TABLE_AVFS_PSM_DEBUG 2 +#define TABLE_AVFS_FUSE_OVERRIDE 3 +#define TABLE_PMSTATUSLOG 4 +#define TABLE_SMU_METRICS 5 +#define TABLE_DRIVER_SMU_CONFIG 6 +#define TABLE_ACTIVITY_MONITOR_COEFF 7 +#define TABLE_OVERDRIVE 8 +#define TABLE_I2C_COMMANDS 9 +#define TABLE_PACE 10 +#define TABLE_ECCINFO 11 +#define TABLE_COUNT 12 diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index 357f89b4a8e0..edda572dc570 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -131,6 +131,7 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, union display_idle_optimization_u idle_info = { 0 }; idle_info.idle_info.df_request_disabled = 1; idle_info.idle_info.phy_ref_clk_off = 1; + idle_info.idle_info.s0i2_rdy = 1; dcn315_smu_set_display_idle_optimization(clk_mgr, idle_info.data); /* update power state */ clk_mgr_base->clks.pwr_state = DCN_PWR_STATE_LOW_POWER; @@ -586,8 +587,10 @@ void dcn315_clk_mgr_construct( } clk_mgr->base.base.dprefclk_khz = 600000; - clk_mgr->base.dccg->ref_dtbclk_khz = 600000; + clk_mgr->base.base.dprefclk_khz = dcn315_smu_get_dpref_clk(&clk_mgr->base); + clk_mgr->base.dccg->ref_dtbclk_khz = clk_mgr->base.base.dprefclk_khz; dce_clock_read_ss_info(&clk_mgr->base); + clk_mgr->base.dccg->ref_dtbclk_khz = dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz); clk_mgr->base.base.bw_params = &dcn315_bw_params; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c index 1420eb5097d3..880ffea2afc6 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c @@ -312,3 +312,27 @@ void dcn315_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr) VBIOSSMC_MSG_TransferTableDram2Smu, TABLE_WATERMARKS); } +int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr) +{ + int dprefclk_get_mhz = -1; + if (clk_mgr->smu_present) { + dprefclk_get_mhz = dcn315_smu_send_msg_with_param( + clk_mgr, + VBIOSSMC_MSG_GetDprefclkFreq, + 0); + } + return (dprefclk_get_mhz * 1000); +} + +int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr) +{ + int fclk_get_mhz = -1; + + if (clk_mgr->smu_present) { + fclk_get_mhz = dcn315_smu_send_msg_with_param( + clk_mgr, + VBIOSSMC_MSG_GetFclkFrequency, + 0); + } + return (fclk_get_mhz * 1000); +} diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h index 96ec6bfcad22..66fa42f8dd18 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h @@ -123,4 +123,6 @@ void dcn315_smu_transfer_dpm_table_smu_2_dram(struct clk_mgr_internal *clk_mgr); void dcn315_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr); void dcn315_smu_request_voltage_via_phyclk(struct clk_mgr_internal *clk_mgr, int requested_phyclk_khz); void dcn315_smu_enable_pme_wa(struct clk_mgr_internal *clk_mgr); +int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr); +int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr); #endif /* DAL_DC_315_SMU_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index c940635b7a74..702d00ce7da4 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -172,8 +172,7 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base, union display_idle_optimization_u idle_info = { 0 }; idle_info.idle_info.df_request_disabled = 1; idle_info.idle_info.phy_ref_clk_off = 1; - // Todo DCN316 set this to 1 if any no issue - idle_info.idle_info.s0i2_rdy = 0; + idle_info.idle_info.s0i2_rdy = 1; dcn316_smu_set_display_idle_optimization(clk_mgr, idle_info.data); /* update power state */ clk_mgr_base->clks.pwr_state = DCN_PWR_STATE_LOW_POWER; @@ -684,8 +683,11 @@ void dcn316_clk_mgr_construct( } clk_mgr->base.base.dprefclk_khz = 600000; - clk_mgr->base.dccg->ref_dtbclk_khz = 600000; + clk_mgr->base.base.dprefclk_khz = dcn316_smu_get_dpref_clk(&clk_mgr->base); + clk_mgr->base.dccg->ref_dtbclk_khz = clk_mgr->base.base.dprefclk_khz; dce_clock_read_ss_info(&clk_mgr->base); + clk_mgr->base.dccg->ref_dtbclk_khz = + dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz); clk_mgr->base.base.bw_params = &dcn316_bw_params; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.c index 128614dff108..dceec4b96052 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.c @@ -310,3 +310,29 @@ void dcn316_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable) VBIOSSMC_MSG_SetDtbclkFreq, enable); } + +int dcn316_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr) +{ + int dprefclk_get_mhz = -1; + + if (clk_mgr->smu_present) { + dprefclk_get_mhz = dcn316_smu_send_msg_with_param( + clk_mgr, + VBIOSSMC_MSG_GetDprefclkFreq, + 0); + } + return (dprefclk_get_mhz * 1000); +} + +int dcn316_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr) +{ + int fclk_get_mhz = -1; + + if (clk_mgr->smu_present) { + fclk_get_mhz = dcn316_smu_send_msg_with_param( + clk_mgr, + VBIOSSMC_MSG_GetFclkFrequency, + 0); + } + return (fclk_get_mhz * 1000); +} diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.h index 658b36d0e107..2a7293f66515 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.h @@ -133,5 +133,7 @@ void dcn316_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr); void dcn316_smu_request_voltage_via_phyclk(struct clk_mgr_internal *clk_mgr, int requested_phyclk_khz); void dcn316_smu_enable_pme_wa(struct clk_mgr_internal *clk_mgr); void dcn316_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable); +int dcn316_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr); +int dcn316_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr); #endif /* DAL_DC_316_SMU_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 61e3bb99375f..f6e19efea756 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1082,7 +1082,8 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) break; } } - if (!should_disable && pipe_split_change) + if (!should_disable && pipe_split_change && + dc->current_state->stream_count != context->stream_count) should_disable = true; if (should_disable && old_stream) { @@ -1690,6 +1691,7 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c struct pipe_ctx *pipe; int i, k, l; struct dc_stream_state *dc_streams[MAX_STREAMS] = {0}; + struct dc_state *old_state; #if defined(CONFIG_DRM_AMD_DC_DCN) dc_z10_restore(dc); @@ -1808,10 +1810,11 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c for (i = 0; i < context->stream_count; i++) context->streams[i]->mode_changed = false; - dc_release_state(dc->current_state); - + old_state = dc->current_state; dc->current_state = context; + dc_release_state(old_state); + dc_retain_state(dc->current_state); return result; @@ -3360,6 +3363,19 @@ bool dc_is_dmcu_initialized(struct dc *dc) return false; } +bool dc_is_oem_i2c_device_present( + struct dc *dc, + size_t slave_address) +{ + if (dc->res_pool->oem_device) + return dce_i2c_oem_device_present( + dc->res_pool, + dc->res_pool->oem_device, + slave_address); + + return false; +} + bool dc_submit_i2c( struct dc *dc, uint32_t link_index, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 27f3fc416448..cb87dd643180 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -50,6 +50,7 @@ #include "inc/hw/panel_cntl.h" #include "inc/link_enc_cfg.h" #include "inc/link_dpcd.h" +#include "link/link_dp_trace.h" #include "dc/dcn30/dcn30_vpg.h" @@ -730,6 +731,7 @@ static bool detect_dp(struct dc_link *link, sink_caps, audio_support); link->dpcd_caps.dongle_type = sink_caps->dongle_type; + link->dpcd_caps.is_dongle_type_one = sink_caps->is_dongle_type_one; link->dpcd_caps.dpcd_rev.raw = 0; } @@ -981,7 +983,8 @@ static bool should_verify_link_capability_destructively(struct dc_link *link, destrictive = false; } } - } + } else if (dc_is_hdmi_signal(link->local_sink->sink_signal)) + destrictive = true; return destrictive; } @@ -1180,6 +1183,9 @@ static bool detect_link_and_local_sink(struct dc_link *link, case EDID_BAD_CHECKSUM: DC_LOG_ERROR("EDID checksum invalid.\n"); break; + case EDID_PARTIAL_VALID: + DC_LOG_ERROR("Partial EDID valid, abandon invalid blocks.\n"); + break; case EDID_NO_RESPONSE: DC_LOG_ERROR("No EDID read.\n"); /* @@ -1254,6 +1260,9 @@ static bool detect_link_and_local_sink(struct dc_link *link, !sink->edid_caps.edid_hdmi) sink->sink_signal = SIGNAL_TYPE_DVI_SINGLE_LINK; + if (link->local_sink && dc_is_dp_signal(sink_caps.signal)) + dp_trace_init(link); + /* Connectivity log: detection */ for (i = 0; i < sink->dc_edid.length / DC_EDID_BLOCK_SIZE; i++) { CONN_DATA_DETECT(link, @@ -1306,6 +1315,7 @@ static bool detect_link_and_local_sink(struct dc_link *link, link->dongle_max_pix_clk = 0; dc_link_clear_dprx_states(link); + dp_trace_reset(link); } LINK_INFO("link=%d, dc_sink_in=%p is now %s prev_sink=%p edid same=%d\n", @@ -2801,6 +2811,17 @@ static bool dp_active_dongle_validate_timing( return false; } + /* Check 3D format */ + switch (timing->timing_3d_format) { + case TIMING_3D_FORMAT_NONE: + case TIMING_3D_FORMAT_FRAME_ALTERNATE: + /*Only frame alternate 3D is supported on active dongle*/ + break; + default: + /*other 3D formats are not supported due to bad infoframe translation */ + return false; + } + #if defined(CONFIG_DRM_AMD_DC_DCN) if (dongle_caps->dp_hdmi_frl_max_link_bw_in_kbps > 0) { // DP to HDMI FRL converter struct dc_crtc_timing outputTiming = *timing; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index f1bbd918de35..1d4863763df9 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -493,6 +493,7 @@ void dal_ddc_service_i2c_query_dp_dual_mode_adaptor( sink_cap->max_hdmi_pixel_clock = max_tmds_clk * 1000; } + sink_cap->is_dongle_type_one = false; } else { if (is_valid_hdmi_signature == true) { @@ -510,6 +511,7 @@ void dal_ddc_service_i2c_query_dp_dual_mode_adaptor( "Type 1 DP-HDMI passive dongle (no signature) %dMhz: ", sink_cap->max_hdmi_pixel_clock / 1000); } + sink_cap->is_dongle_type_one = true; } return; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 5688b15ca9e6..351081f574cb 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -39,6 +39,7 @@ #include "dce/dmub_hw_lock_mgr.h" #include "inc/dc_link_dpia.h" #include "inc/link_enc_cfg.h" +#include "link/link_dp_trace.h" /*Travis*/ static const uint8_t DP_VGA_LVDS_CONVERTER_ID_2[] = "sivarT"; @@ -347,29 +348,6 @@ static void vendor_specific_lttpr_wa_one_start(struct dc_link *link) sizeof(vendor_lttpr_write_data)); } -static void vendor_specific_lttpr_wa_one_end( - struct dc_link *link, - uint8_t retry_count) -{ - const uint8_t vendor_lttpr_write_data[4] = {0x1, 0x50, 0x63, 0x0}; - const uint8_t offset = dp_convert_to_count( - link->dpcd_caps.lttpr_caps.phy_repeater_cnt); - uint32_t vendor_lttpr_write_address = 0xF004F; - - if (!retry_count) { - if (offset != 0xFF) - vendor_lttpr_write_address += - ((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1)); - - /* W/A for certain LTTPR to reset their lane settings, part two of two */ - core_link_write_dpcd( - link, - vendor_lttpr_write_address, - &vendor_lttpr_write_data[0], - sizeof(vendor_lttpr_write_data)); - } -} - static void vendor_specific_lttpr_wa_one_two( struct dc_link *link, const uint8_t rate) @@ -396,9 +374,9 @@ static void vendor_specific_lttpr_wa_one_two( } } -static void vendor_specific_lttpr_wa_three( +static void dp_fixed_vs_pe_read_lane_adjust( struct dc_link *link, - union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX]) + union dpcd_training_lane dpcd_lane_adjust[LANE_COUNT_DP_MAX]) { const uint8_t vendor_lttpr_write_data_vs[3] = {0x0, 0x53, 0x63}; const uint8_t vendor_lttpr_write_data_pe[3] = {0x0, 0x54, 0x63}; @@ -440,23 +418,8 @@ static void vendor_specific_lttpr_wa_three( 1); for (lane = 0; lane < LANE_COUNT_DP_MAX; lane++) { - dpcd_lane_adjust[lane].bits.VOLTAGE_SWING_LANE = (dprx_vs >> (2 * lane)) & 0x3; - dpcd_lane_adjust[lane].bits.PRE_EMPHASIS_LANE = (dprx_pe >> (2 * lane)) & 0x3; - } -} - -static void vendor_specific_lttpr_wa_three_dpcd( - struct dc_link *link, - union dpcd_training_lane dpcd_lane_adjust[LANE_COUNT_DP_MAX]) -{ - union lane_adjust lane_adjust[LANE_COUNT_DP_MAX]; - uint8_t lane = 0; - - vendor_specific_lttpr_wa_three(link, lane_adjust); - - for (lane = 0; lane < LANE_COUNT_DP_MAX; lane++) { - dpcd_lane_adjust[lane].bits.VOLTAGE_SWING_SET = lane_adjust[lane].bits.VOLTAGE_SWING_LANE; - dpcd_lane_adjust[lane].bits.PRE_EMPHASIS_SET = lane_adjust[lane].bits.PRE_EMPHASIS_LANE; + dpcd_lane_adjust[lane].bits.VOLTAGE_SWING_SET = (dprx_vs >> (2 * lane)) & 0x3; + dpcd_lane_adjust[lane].bits.PRE_EMPHASIS_SET = (dprx_pe >> (2 * lane)) & 0x3; } } @@ -505,17 +468,24 @@ static void vendor_specific_lttpr_wa_four( } } -static void vendor_specific_lttpr_wa_five( +static void dp_fixed_vs_pe_set_retimer_lane_settings( struct dc_link *link, const union dpcd_training_lane dpcd_lane_adjust[LANE_COUNT_DP_MAX], uint8_t lane_count) { - const uint32_t vendor_lttpr_write_address = 0xF004F; + const uint8_t offset = dp_convert_to_count( + link->dpcd_caps.lttpr_caps.phy_repeater_cnt); const uint8_t vendor_lttpr_write_data_reset[4] = {0x1, 0x50, 0x63, 0xFF}; + uint32_t vendor_lttpr_write_address = 0xF004F; uint8_t vendor_lttpr_write_data_vs[4] = {0x1, 0x51, 0x63, 0x0}; uint8_t vendor_lttpr_write_data_pe[4] = {0x1, 0x52, 0x63, 0x0}; uint8_t lane = 0; + if (offset != 0xFF) { + vendor_lttpr_write_address += + ((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1)); + } + for (lane = 0; lane < lane_count; lane++) { vendor_lttpr_write_data_vs[3] |= dpcd_lane_adjust[lane].bits.VOLTAGE_SWING_SET << (2 * lane); @@ -1014,6 +984,14 @@ enum dc_status dp_get_lane_status_and_lane_adjust( (uint8_t *)(dpcd_buf), sizeof(dpcd_buf)); + if (status != DC_OK) { + DC_LOG_HW_LINK_TRAINING("%s:\n Failed to read from address 0x%X," + " keep current lane status and lane adjust unchanged", + __func__, + lane01_status_address); + return status; + } + for (lane = 0; lane < (uint32_t)(link_training_setting->link_settings.lane_count); lane++) { @@ -1154,6 +1132,9 @@ static bool perform_post_lt_adj_req_sequence( uint32_t adj_req_timer; bool req_drv_setting_changed; uint32_t lane; + union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {0}; + union lane_align_status_updated dpcd_lane_status_updated = {0}; + union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = {0}; req_drv_setting_changed = false; for (adj_req_count = 0; adj_req_count < POST_LT_ADJ_REQ_LIMIT; @@ -1165,11 +1146,6 @@ static bool perform_post_lt_adj_req_sequence( adj_req_timer < POST_LT_ADJ_REQ_TIMEOUT; adj_req_timer++) { - union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX]; - union lane_align_status_updated - dpcd_lane_status_updated; - union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } }; - dp_get_lane_status_and_lane_adjust( link, lt_settings, @@ -1396,6 +1372,10 @@ static enum link_training_result perform_clock_recovery_sequence( retries_cr = 0; retry_count = 0; + memset(&dpcd_lane_status, '\0', sizeof(dpcd_lane_status)); + memset(&dpcd_lane_status_updated, '\0', + sizeof(dpcd_lane_status_updated)); + if (!link->ctx->dc->work_arounds.lt_early_cr_pattern) dp_set_hw_training_pattern(link, link_res, lt_settings->pattern_for_cr, offset); @@ -1407,9 +1387,6 @@ static enum link_training_result perform_clock_recovery_sequence( while ((retries_cr < LINK_TRAINING_MAX_RETRY_COUNT) && (retry_count < LINK_TRAINING_MAX_CR_RETRY)) { - memset(&dpcd_lane_status, '\0', sizeof(dpcd_lane_status)); - memset(&dpcd_lane_status_updated, '\0', - sizeof(dpcd_lane_status_updated)); /* 1. call HWSS to set lane settings*/ dp_set_hw_lane_settings( @@ -1456,13 +1433,6 @@ static enum link_training_result perform_clock_recovery_sequence( dpcd_lane_adjust, offset); - if (link->dc->debug.apply_vendor_specific_lttpr_wa && - (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && - link->lttpr_mode == LTTPR_MODE_TRANSPARENT) { - vendor_specific_lttpr_wa_one_end(link, retry_count); - vendor_specific_lttpr_wa_three(link, dpcd_lane_adjust); - } - /* 5. check CR done*/ if (dp_is_cr_done(lane_count, dpcd_lane_status)) return LINK_TRAINING_SUCCESS; @@ -2512,12 +2482,13 @@ static enum link_training_result dp_perform_fixed_vs_pe_training_sequence( retries_cr = 0; retry_count = 0; + memset(&dpcd_lane_status, '\0', sizeof(dpcd_lane_status)); + memset(&dpcd_lane_status_updated, '\0', + sizeof(dpcd_lane_status_updated)); + while ((retries_cr < LINK_TRAINING_MAX_RETRY_COUNT) && (retry_count < LINK_TRAINING_MAX_CR_RETRY)) { - memset(&dpcd_lane_status, '\0', sizeof(dpcd_lane_status)); - memset(&dpcd_lane_status_updated, '\0', - sizeof(dpcd_lane_status_updated)); /* 1. call HWSS to set lane settings */ dp_set_hw_lane_settings( @@ -2814,6 +2785,10 @@ bool perform_link_training_with_retries( enum link_training_result status = LINK_TRAINING_CR_FAIL_LANE0; struct dc_link_settings current_setting = *link_setting; const struct link_hwss *link_hwss = get_link_hwss(link, &pipe_ctx->link_res); + int fail_count = 0; + + dp_trace_commit_lt_init(link); + if (dp_get_link_encoding_format(¤t_setting) == DP_8b_10b_ENCODING) /* We need to do this before the link training to ensure the idle @@ -2821,6 +2796,7 @@ bool perform_link_training_with_retries( */ link_hwss->setup_stream_encoder(pipe_ctx); + dp_trace_set_lt_start_timestamp(link, false); for (j = 0; j < attempts; ++j) { DC_LOG_HW_LINK_TRAINING("%s: Beginning link training attempt %u of %d\n", @@ -2876,10 +2852,15 @@ bool perform_link_training_with_retries( skip_video_pattern); } + dp_trace_lt_total_count_increment(link, false); + dp_trace_lt_result_update(link, status, false); + dp_trace_set_lt_end_timestamp(link, false); if (status == LINK_TRAINING_SUCCESS) return true; } + fail_count++; + dp_trace_lt_fail_count_update(link, fail_count, false); /* latest link training still fail, skip delay and keep PHY on */ if (j == (attempts - 1) && link->ep_type == DISPLAY_ENDPOINT_PHY) @@ -3347,6 +3328,8 @@ static bool dp_verify_link_cap( } else { (*fail_count)++; } + dp_trace_lt_total_count_increment(link, true); + dp_trace_lt_result_update(link, status, true); dp_disable_link_phy(link, &link_res, link->connector_signal); } while (!success && decide_fallback_link_setting(link, initial_link_settings, &cur_link_settings, status)); @@ -3378,13 +3361,16 @@ bool dp_verify_link_cap_with_retries( { int i = 0; bool success = false; + int fail_count = 0; + + dp_trace_detect_lt_init(link); if (link->link_enc && link->link_enc->features.flags.bits.DP_IS_USB_C && link->dc->debug.usbc_combo_phy_reset_wa) apply_usbc_combo_phy_reset_wa(link, known_limit_link_setting); + dp_trace_set_lt_start_timestamp(link, false); for (i = 0; i < attempts; i++) { - int fail_count = 0; enum dc_connection_type type = dc_connection_none; memset(&link->verified_link_cap, 0, @@ -3399,6 +3385,10 @@ bool dp_verify_link_cap_with_retries( } msleep(10); } + + dp_trace_lt_fail_count_update(link, fail_count, true); + dp_trace_set_lt_end_timestamp(link, true); + return success; } @@ -3488,7 +3478,8 @@ static enum dc_lane_count increase_lane_count(enum dc_lane_count lane_count) } } -static enum dc_link_rate increase_link_rate(enum dc_link_rate link_rate) +static enum dc_link_rate increase_link_rate(struct dc_link *link, + enum dc_link_rate link_rate) { switch (link_rate) { case LINK_RATE_LOW: @@ -3500,7 +3491,15 @@ static enum dc_link_rate increase_link_rate(enum dc_link_rate link_rate) case LINK_RATE_HIGH3: return LINK_RATE_UHBR10; case LINK_RATE_UHBR10: - return LINK_RATE_UHBR13_5; + /* upto DP2.x specs UHBR13.5 is the only link rate that could be + * not supported by DPRX when higher link rate is supported. + * so we treat it as a special case for code simplicity. When we + * have new specs with more link rates like this, we should + * consider a more generic solution to handle discrete link + * rate capabilities. + */ + return link->dpcd_caps.dp_128b_132b_supported_link_rates.bits.UHBR13_5 ? + LINK_RATE_UHBR13_5 : LINK_RATE_UHBR20; case LINK_RATE_UHBR13_5: return LINK_RATE_UHBR20; default: @@ -3509,12 +3508,17 @@ static enum dc_link_rate increase_link_rate(enum dc_link_rate link_rate) } static bool decide_fallback_link_setting_max_bw_policy( + struct dc_link *link, const struct dc_link_settings *max, - struct dc_link_settings *cur) + struct dc_link_settings *cur, + enum link_training_result training_result) { uint8_t cur_idx = 0, next_idx; bool found = false; + if (training_result == LINK_TRAINING_ABORT) + return false; + while (cur_idx < ARRAY_SIZE(dp_lt_fallbacks)) /* find current index */ if (dp_lt_fallbacks[cur_idx].lane_count == cur->lane_count && @@ -3527,11 +3531,22 @@ static bool decide_fallback_link_setting_max_bw_policy( while (next_idx < ARRAY_SIZE(dp_lt_fallbacks)) /* find next index */ - if (dp_lt_fallbacks[next_idx].lane_count <= max->lane_count && - dp_lt_fallbacks[next_idx].link_rate <= max->link_rate) - break; - else + if (dp_lt_fallbacks[next_idx].lane_count > max->lane_count || + dp_lt_fallbacks[next_idx].link_rate > max->link_rate) + next_idx++; + else if (dp_lt_fallbacks[next_idx].link_rate == LINK_RATE_UHBR13_5 && + link->dpcd_caps.dp_128b_132b_supported_link_rates.bits.UHBR13_5 == 0) + /* upto DP2.x specs UHBR13.5 is the only link rate that + * could be not supported by DPRX when higher link rate + * is supported. so we treat it as a special case for + * code simplicity. When we have new specs with more + * link rates like this, we should consider a more + * generic solution to handle discrete link rate + * capabilities. + */ next_idx++; + else + break; if (next_idx < ARRAY_SIZE(dp_lt_fallbacks)) { cur->lane_count = dp_lt_fallbacks[next_idx].lane_count; @@ -3560,8 +3575,8 @@ static bool decide_fallback_link_setting( return false; if (dp_get_link_encoding_format(&initial_link_settings) == DP_128b_132b_ENCODING || link->dc->debug.force_dp2_lt_fallback_method) - return decide_fallback_link_setting_max_bw_policy(&initial_link_settings, - current_link_setting); + return decide_fallback_link_setting_max_bw_policy(link, &initial_link_settings, + current_link_setting, training_result); switch (training_result) { case LINK_TRAINING_CR_FAIL_LANE0: @@ -3716,7 +3731,7 @@ static bool decide_dp_link_settings(struct dc_link *link, struct dc_link_setting current_link_setting.lane_count); } else { current_link_setting.link_rate = - increase_link_rate( + increase_link_rate(link, current_link_setting.link_rate); current_link_setting.lane_count = initial_link_setting.lane_count; @@ -3831,7 +3846,7 @@ static bool decide_edp_link_settings_with_dsc(struct dc_link *link, /* minimize lane */ if (current_link_setting.link_rate < max_link_rate) { current_link_setting.link_rate = - increase_link_rate( + increase_link_rate(link, current_link_setting.link_rate); } else { if (current_link_setting.lane_count < @@ -3852,7 +3867,7 @@ static bool decide_edp_link_settings_with_dsc(struct dc_link *link, current_link_setting.lane_count); } else { current_link_setting.link_rate = - increase_link_rate( + increase_link_rate(link, current_link_setting.link_rate); current_link_setting.lane_count = initial_link_setting.lane_count; @@ -4129,7 +4144,7 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link) if (link->dc->debug.apply_vendor_specific_lttpr_wa && (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && link->lttpr_mode == LTTPR_MODE_TRANSPARENT) - vendor_specific_lttpr_wa_three_dpcd( + dp_fixed_vs_pe_read_lane_adjust( link, link_training_settings.dpcd_lane_settings); @@ -4665,6 +4680,8 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd status = false; if (out_link_loss) *out_link_loss = true; + + dp_trace_link_loss_increment(link); } if (link->type == dc_connection_sst_branch && @@ -5101,6 +5118,7 @@ bool dp_retrieve_lttpr_cap(struct dc_link *link) sizeof(lttpr_dpcd_data)); if (status != DC_OK) { DC_LOG_DP2("%s: Read LTTPR caps data failed.\n", __func__); + link->lttpr_mode = LTTPR_MODE_NON_LTTPR; return false; } @@ -5989,15 +6007,14 @@ bool dc_link_dp_set_test_pattern( if (link->dc->debug.apply_vendor_specific_lttpr_wa && (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && link->lttpr_mode == LTTPR_MODE_TRANSPARENT) { - dpcd_set_lane_settings(link, p_link_settings, DPRX); - vendor_specific_lttpr_wa_five( + dp_fixed_vs_pe_set_retimer_lane_settings( link, p_link_settings->dpcd_lane_settings, p_link_settings->link_settings.lane_count); } else { dp_set_hw_lane_settings(link, &pipe_ctx->link_res, p_link_settings, DPRX); - dpcd_set_lane_settings(link, p_link_settings, DPRX); } + dpcd_set_lane_settings(link, p_link_settings, DPRX); } /* Blank stream if running test pattern */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c index 047c626a4a34..42da7f430113 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c @@ -272,6 +272,13 @@ void link_enc_cfg_init( state->res_ctx.link_enc_cfg_ctx.mode = LINK_ENC_CFG_STEADY; } +void link_enc_cfg_copy(const struct dc_state *src_ctx, struct dc_state *dst_ctx) +{ + memcpy(&dst_ctx->res_ctx.link_enc_cfg_ctx, + &src_ctx->res_ctx.link_enc_cfg_ctx, + sizeof(dst_ctx->res_ctx.link_enc_cfg_ctx)); +} + void link_enc_cfg_link_encs_assign( struct dc *dc, struct dc_state *state, 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 cc8e60ec35c6..7af153434e9e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -2335,6 +2335,9 @@ void dc_resource_state_construct( bool dc_resource_is_dsc_encoding_supported(const struct dc *dc) { + if (dc->res_pool == NULL) + return false; + return dc->res_pool->res_cap->num_dsc > 0; } @@ -2615,6 +2618,8 @@ static void set_avi_info_frame( hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE; ///VIC + if (pipe_ctx->stream->timing.hdmi_vic != 0) + vic = 0; format = stream->timing.timing_3d_format; /*todo, add 3DStereo support*/ if (format != TIMING_3D_FORMAT_NONE) { 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 dc5fd27b031a..c4e871f358ab 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -718,6 +718,20 @@ enum dc_status dc_stream_add_dsc_to_resource(struct dc *dc, } } +struct pipe_ctx *dc_stream_get_pipe_ctx(struct dc_stream_state *stream) +{ + int i = 0; + + for (i = 0; i < MAX_PIPES; i++) { + struct pipe_ctx *pipe = &stream->ctx->dc->current_state->res_ctx.pipe_ctx[i]; + + if (pipe->stream == stream) + return pipe; + } + + return NULL; +} + void dc_stream_log(const struct dc *dc, const struct dc_stream_state *stream) { DC_LOG_DC( diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 55d43d642b38..4ffab7bb1098 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -47,7 +47,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.174" +#define DC_VER "3.2.177" #define MAX_SURFACES 3 #define MAX_PLANES 6 @@ -354,6 +354,7 @@ enum dc_psr_power_opts { psr_power_opt_invalid = 0x0, psr_power_opt_smu_opt_static_screen = 0x1, psr_power_opt_z10_static_screen = 0x10, + psr_power_opt_ds_disable_allow = 0x100, }; enum dcc_option { @@ -710,6 +711,7 @@ struct dc_debug_options { #endif bool apply_vendor_specific_lttpr_wa; bool ignore_dpref_ss; + uint8_t psr_power_use_phy_fsm; }; struct gpu_info_soc_bounding_box_v1_0; @@ -1204,6 +1206,7 @@ struct dpcd_caps { /* dongle type (DP converter, CV smart dongle) */ enum display_dongle_type dongle_type; + bool is_dongle_type_one; /* branch device or sink device */ bool is_branch_dev; /* Dongle's downstream count. */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index ce6e8d013459..aa818bf840eb 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -76,6 +76,28 @@ struct link_trace { struct time_stamp time_stamp; }; +struct dp_trace_lt_counts { + unsigned int total; + unsigned int fail; +}; + +struct dp_trace_lt { + struct dp_trace_lt_counts counts; + struct dp_trace_timestamps { + unsigned long long start; + unsigned long long end; + } timestamps; + enum link_training_result result; + bool is_logged; +}; + +struct dp_trace { + struct dp_trace_lt detect_lt_trace; + struct dp_trace_lt commit_lt_trace; + unsigned int link_loss_count; + bool is_initialized; +}; + /* PSR feature flags */ struct psr_settings { bool psr_feature_enabled; // PSR is supported by sink @@ -121,6 +143,8 @@ struct dc_link { bool edp_sink_present; + struct dp_trace dp_trace; + /* caps is the same as reported_link_cap. link_traing use * reported_link_cap. Will clean up. TODO */ @@ -442,6 +466,11 @@ const struct dc_link_settings *dc_link_get_link_cap( void dc_link_overwrite_extended_receiver_cap( struct dc_link *link); +bool dc_is_oem_i2c_device_present( + struct dc *dc, + size_t slave_address +); + bool dc_submit_i2c( struct dc *dc, uint32_t link_index, @@ -470,4 +499,16 @@ void dc_link_clear_dprx_states(struct dc_link *link); struct gpio *get_hpd_gpio(struct dc_bios *dcb, struct graphics_object_id link_id, struct gpio_service *gpio_service); +void dp_trace_reset(struct dc_link *link); +bool dc_dp_trace_is_initialized(struct dc_link *link); +unsigned long long dc_dp_trace_get_lt_end_timestamp(struct dc_link *link, + bool in_detection); +void dc_dp_trace_set_is_logged_flag(struct dc_link *link, + bool in_detection, + bool is_logged); +bool dc_dp_trace_is_logged(struct dc_link *link, + bool in_detection); +struct dp_trace_lt_counts *dc_dp_trace_get_lt_counts(struct dc_link *link, + bool in_detection); +unsigned int dc_dp_trace_get_link_loss_count(struct dc_link *link); #endif /* DC_LINK_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index f631b61abedd..99a750f561f8 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -524,4 +524,6 @@ bool dc_stream_get_crtc_position(struct dc *dc, unsigned int *v_pos, unsigned int *nom_v_pos); +struct pipe_ctx *dc_stream_get_pipe_ctx(struct dc_stream_state *stream); + #endif /* DC_STREAM_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index 48859d5fc172..2ba9f528c0fe 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -138,6 +138,7 @@ enum dc_edid_status { EDID_BAD_CHECKSUM, EDID_THE_SAME, EDID_FALL_BACK, + EDID_PARTIAL_VALID, }; enum act_return_status { diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c index 74b05b3aef08..8e814000db62 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -413,7 +413,8 @@ static bool acquire( return false; if (!acquire_engine(engine)) { - dal_ddc_close(ddc); + engine->ddc = ddc; + release_engine(engine); return false; } diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c index 1435d7bc1f21..07359eb89efc 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c @@ -450,6 +450,8 @@ void dce_clock_read_ss_info(struct dce_clk_mgr *clk_mgr_dce) clk_mgr_dce->dprefclk_ss_percentage = info.spread_spectrum_percentage; } + if (clk_mgr_dce->base.ctx->dc->debug.ignore_dpref_ss) + clk_mgr_dce->dprefclk_ss_percentage = 0; } } } diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c index 2c7eb982eabc..cc5128e67daf 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c @@ -971,6 +971,98 @@ static bool dce112_program_pix_clk( return true; } +#if defined(CONFIG_DRM_AMD_DC_DCN) +static bool dcn31_program_pix_clk( + struct clock_source *clock_source, + struct pixel_clk_params *pix_clk_params, + struct pll_settings *pll_settings) +{ + struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(clock_source); + unsigned int inst = pix_clk_params->controller_id - CONTROLLER_ID_D0; + unsigned int dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dprefclk_khz; + const struct pixel_rate_range_table_entry *e = + look_up_in_video_optimized_rate_tlb(pix_clk_params->requested_pix_clk_100hz / 10); + struct bp_pixel_clock_parameters bp_pc_params = {0}; + enum transmitter_color_depth bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_24; + // For these signal types Driver to program DP_DTO without calling VBIOS Command table + if (dc_is_dp_signal(pix_clk_params->signal_type)) { + if (e) { + /* Set DTO values: phase = target clock, modulo = reference clock*/ + REG_WRITE(PHASE[inst], e->target_pixel_rate_khz * e->mult_factor); + REG_WRITE(MODULO[inst], dp_dto_ref_khz * e->div_factor); + } else { + /* Set DTO values: phase = target clock, modulo = reference clock*/ + REG_WRITE(PHASE[inst], pll_settings->actual_pix_clk_100hz * 100); + REG_WRITE(MODULO[inst], dp_dto_ref_khz * 1000); + } + REG_UPDATE(PIXEL_RATE_CNTL[inst], DP_DTO0_ENABLE, 1); + } else { + if (IS_FPGA_MAXIMUS_DC(clock_source->ctx->dce_environment)) { + unsigned int inst = pix_clk_params->controller_id - CONTROLLER_ID_D0; + unsigned dp_dto_ref_100hz = 7000000; + unsigned clock_100hz = pll_settings->actual_pix_clk_100hz; + + /* Set DTO values: phase = target clock, modulo = reference clock */ + REG_WRITE(PHASE[inst], clock_100hz); + REG_WRITE(MODULO[inst], dp_dto_ref_100hz); + + /* Enable DTO */ + REG_UPDATE(PIXEL_RATE_CNTL[inst], DP_DTO0_ENABLE, 1); + return true; + } + + /*ATOMBIOS expects pixel rate adjusted by deep color ratio)*/ + bp_pc_params.controller_id = pix_clk_params->controller_id; + bp_pc_params.pll_id = clock_source->id; + bp_pc_params.target_pixel_clock_100hz = pll_settings->actual_pix_clk_100hz; + bp_pc_params.encoder_object_id = pix_clk_params->encoder_object_id; + bp_pc_params.signal_type = pix_clk_params->signal_type; + + // Make sure we send the correct color depth to DMUB for HDMI + if (pix_clk_params->signal_type == SIGNAL_TYPE_HDMI_TYPE_A) { + switch (pix_clk_params->color_depth) { + case COLOR_DEPTH_888: + bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_24; + break; + case COLOR_DEPTH_101010: + bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_30; + break; + case COLOR_DEPTH_121212: + bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_36; + break; + case COLOR_DEPTH_161616: + bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_48; + break; + default: + bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_24; + break; + } + bp_pc_params.color_depth = bp_pc_colour_depth; + } + + if (clock_source->id != CLOCK_SOURCE_ID_DP_DTO) { + bp_pc_params.flags.SET_GENLOCK_REF_DIV_SRC = + pll_settings->use_external_clk; + bp_pc_params.flags.SET_XTALIN_REF_SRC = + !pll_settings->use_external_clk; + if (pix_clk_params->flags.SUPPORT_YCBCR420) { + bp_pc_params.flags.SUPPORT_YUV_420 = 1; + } + } + if (clk_src->bios->funcs->set_pixel_clock( + clk_src->bios, &bp_pc_params) != BP_RESULT_OK) + return false; + /* Resync deep color DTO */ + if (clock_source->id != CLOCK_SOURCE_ID_DP_DTO) + dce112_program_pixel_clk_resync(clk_src, + pix_clk_params->signal_type, + pix_clk_params->color_depth, + pix_clk_params->flags.SUPPORT_YCBCR420); + } + + return true; +} +#endif static bool dce110_clock_source_power_down( struct clock_source *clk_src) @@ -1205,6 +1297,13 @@ static const struct clock_source_funcs dcn3_clk_src_funcs = { .get_pix_clk_dividers = dcn3_get_pix_clk_dividers, .get_pixel_clk_frequency_100hz = get_pixel_clk_frequency_100hz }; + +static const struct clock_source_funcs dcn31_clk_src_funcs = { + .cs_power_down = dce110_clock_source_power_down, + .program_pix_clk = dcn31_program_pix_clk, + .get_pix_clk_dividers = dcn3_get_pix_clk_dividers, + .get_pixel_clk_frequency_100hz = get_pixel_clk_frequency_100hz +}; #endif /*****************************************/ /* Constructor */ @@ -1610,6 +1709,24 @@ bool dcn3_clk_src_construct( #endif #if defined(CONFIG_DRM_AMD_DC_DCN) +bool dcn31_clk_src_construct( + struct dce110_clk_src *clk_src, + struct dc_context *ctx, + struct dc_bios *bios, + enum clock_source_id id, + const struct dce110_clk_src_regs *regs, + const struct dce110_clk_src_shift *cs_shift, + const struct dce110_clk_src_mask *cs_mask) +{ + bool ret = dce112_clk_src_construct(clk_src, ctx, bios, id, regs, cs_shift, cs_mask); + + clk_src->base.funcs = &dcn31_clk_src_funcs; + + return ret; +} +#endif + +#if defined(CONFIG_DRM_AMD_DC_DCN) bool dcn301_clk_src_construct( struct dce110_clk_src *clk_src, struct dc_context *ctx, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h index 692fa23ca02b..069de7649c8c 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h @@ -292,6 +292,15 @@ bool dcn301_clk_src_construct( const struct dce110_clk_src_regs *regs, const struct dce110_clk_src_shift *cs_shift, const struct dce110_clk_src_mask *cs_mask); + +bool dcn31_clk_src_construct( + struct dce110_clk_src *clk_src, + struct dc_context *ctx, + struct dc_bios *bios, + enum clock_source_id id, + const struct dce110_clk_src_regs *regs, + const struct dce110_clk_src_shift *cs_shift, + const struct dce110_clk_src_mask *cs_mask); #endif /* this table is use to find *1.001 and /1.001 pixel rates from non-precise pixel rate */ diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.c b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.c index dd41736bb5c4..f5cd2392fc5f 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.c @@ -25,6 +25,32 @@ #include "dce_i2c.h" #include "reg_helper.h" +bool dce_i2c_oem_device_present( + struct resource_pool *pool, + struct ddc_service *ddc, + size_t slave_address +) +{ + struct dc *dc = ddc->ctx->dc; + struct dc_bios *dcb = dc->ctx->dc_bios; + struct graphics_object_id id = {0}; + struct graphics_object_i2c_info i2c_info; + + if (!dc->ctx->dc_bios->fw_info.oem_i2c_present) + return false; + + id.id = dc->ctx->dc_bios->fw_info.oem_i2c_obj_id; + id.enum_id = 0; + id.type = OBJECT_TYPE_GENERIC; + if (dcb->funcs->get_i2c_info(dcb, id, &i2c_info) != BP_RESULT_OK) + return false; + + if (i2c_info.i2c_slave_address != slave_address) + return false; + + return true; +} + bool dce_i2c_submit_command( struct resource_pool *pool, struct ddc *ddc, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.h b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.h index a171c5cd8439..535fd58de450 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.h @@ -30,6 +30,12 @@ #include "dce_i2c_hw.h" #include "dce_i2c_sw.h" +bool dce_i2c_oem_device_present( + struct resource_pool *pool, + struct ddc_service *ddc, + size_t slave_address +); + bool dce_i2c_submit_command( struct resource_pool *pool, struct ddc *ddc, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c index 8bd265b40847..312c68172689 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c @@ -320,6 +320,7 @@ static bool dmub_psr_copy_settings(struct dmub_psr *dmub, copy_settings_data->otg_inst = 0; // Misc + copy_settings_data->use_phy_fsm = link->ctx->dc->debug.psr_power_use_phy_fsm; copy_settings_data->psr_level = psr_context->psr_level.u32all; copy_settings_data->smu_optimizations_en = psr_context->allow_smu_optimizations; copy_settings_data->multi_disp_optimizations_en = psr_context->allow_multi_disp_optimizations; diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 8378b80e8517..248602c15f3a 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1509,6 +1509,31 @@ static enum dc_status apply_single_controller_ctx_to_hw( if (!pipe_ctx->stream->apply_seamless_boot_optimization && dc->config.use_pipe_ctx_sync_logic) check_syncd_pipes_for_disabled_master_pipe(dc, context, pipe_ctx->pipe_idx); + pipe_ctx->stream_res.opp->funcs->opp_program_fmt( + pipe_ctx->stream_res.opp, + &stream->bit_depth_params, + &stream->clamping); + + pipe_ctx->stream_res.opp->funcs->opp_set_dyn_expansion( + pipe_ctx->stream_res.opp, + COLOR_SPACE_YCBCR601, + stream->timing.display_color_depth, + stream->signal); + + while (odm_pipe) { + odm_pipe->stream_res.opp->funcs->opp_set_dyn_expansion( + odm_pipe->stream_res.opp, + COLOR_SPACE_YCBCR601, + stream->timing.display_color_depth, + stream->signal); + + odm_pipe->stream_res.opp->funcs->opp_program_fmt( + odm_pipe->stream_res.opp, + &stream->bit_depth_params, + &stream->clamping); + odm_pipe = odm_pipe->next_odm_pipe; + } + /* DCN3.1 FPGA Workaround * Need to enable HPO DP Stream Encoder before setting OTG master enable. * To do so, move calling function enable_stream_timing to only be done AFTER calling @@ -1548,30 +1573,6 @@ static enum dc_status apply_single_controller_ctx_to_hw( if (dc_is_dp_signal(pipe_ctx->stream->signal)) dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_CONNECT_DIG_FE_OTG); - pipe_ctx->stream_res.opp->funcs->opp_set_dyn_expansion( - pipe_ctx->stream_res.opp, - COLOR_SPACE_YCBCR601, - stream->timing.display_color_depth, - stream->signal); - - pipe_ctx->stream_res.opp->funcs->opp_program_fmt( - pipe_ctx->stream_res.opp, - &stream->bit_depth_params, - &stream->clamping); - while (odm_pipe) { - odm_pipe->stream_res.opp->funcs->opp_set_dyn_expansion( - odm_pipe->stream_res.opp, - COLOR_SPACE_YCBCR601, - stream->timing.display_color_depth, - stream->signal); - - odm_pipe->stream_res.opp->funcs->opp_program_fmt( - odm_pipe->stream_res.opp, - &stream->bit_depth_params, - &stream->clamping); - odm_pipe = odm_pipe->next_odm_pipe; - } - if (!stream->dpms_off) core_link_enable_stream(context, pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c index f4f423d0b8c3..80595d7f060c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c @@ -940,6 +940,7 @@ static const struct hubbub_funcs hubbub1_funcs = { .program_watermarks = hubbub1_program_watermarks, .is_allow_self_refresh_enabled = hubbub1_is_allow_self_refresh_enabled, .allow_self_refresh_control = hubbub1_allow_self_refresh_control, + .verify_allow_pstate_change_high = hubbub1_verify_allow_pstate_change_high, }; void hubbub1_construct(struct hubbub *hubbub, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c index ea185c877323..fbff6beb78be 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c @@ -1311,6 +1311,20 @@ void hubp1_set_flip_int(struct hubp *hubp) return; } +/** + * hubp1_wait_pipe_read_start - wait for hubp ret path starting read. + * + * @hubp: hubp struct reference. + */ +void hubp1_wait_pipe_read_start(struct hubp *hubp) +{ + struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp); + + REG_WAIT(HUBPRET_READ_LINE_STATUS, + PIPE_READ_VBLANK, 0, + 1, 1000); +} + void hubp1_init(struct hubp *hubp) { //do nothing @@ -1345,6 +1359,7 @@ static const struct hubp_funcs dcn10_hubp_funcs = { .hubp_soft_reset = hubp1_soft_reset, .hubp_in_blank = hubp1_in_blank, .hubp_set_flip_int = hubp1_set_flip_int, + .hubp_wait_pipe_read_start = hubp1_wait_pipe_read_start, }; /*****************************************/ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h index 9cb8c383d673..0b17c2993ca5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h @@ -76,6 +76,7 @@ SRI(DCSURF_SURFACE_CONTROL, HUBPREQ, id),\ SRI(DCSURF_SURFACE_FLIP_INTERRUPT, HUBPREQ, id),\ SRI(HUBPRET_CONTROL, HUBPRET, id),\ + SRI(HUBPRET_READ_LINE_STATUS, HUBPRET, id),\ SRI(DCN_EXPANSION_MODE, HUBPREQ, id),\ SRI(DCHUBP_REQ_SIZE_CONFIG, HUBP, id),\ SRI(DCHUBP_REQ_SIZE_CONFIG_C, HUBP, id),\ @@ -186,6 +187,7 @@ uint32_t DCSURF_SURFACE_CONTROL; \ uint32_t DCSURF_SURFACE_FLIP_INTERRUPT; \ uint32_t HUBPRET_CONTROL; \ + uint32_t HUBPRET_READ_LINE_STATUS; \ uint32_t DCN_EXPANSION_MODE; \ uint32_t DCHUBP_REQ_SIZE_CONFIG; \ uint32_t DCHUBP_REQ_SIZE_CONFIG_C; \ @@ -338,6 +340,7 @@ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\ + HUBP_SF(HUBPRET0_HUBPRET_READ_LINE_STATUS, PIPE_READ_VBLANK, mask_sh),\ HUBP_SF(HUBPREQ0_DCN_EXPANSION_MODE, DRQ_EXPANSION_MODE, mask_sh),\ HUBP_SF(HUBPREQ0_DCN_EXPANSION_MODE, PRQ_EXPANSION_MODE, mask_sh),\ HUBP_SF(HUBPREQ0_DCN_EXPANSION_MODE, MRQ_EXPANSION_MODE, mask_sh),\ @@ -538,6 +541,7 @@ type DET_BUF_PLANE1_BASE_ADDRESS;\ type CROSSBAR_SRC_CB_B;\ type CROSSBAR_SRC_CR_R;\ + type PIPE_READ_VBLANK;\ type DRQ_EXPANSION_MODE;\ type PRQ_EXPANSION_MODE;\ type MRQ_EXPANSION_MODE;\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 559aa45f27e7..c3e141c19a77 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -107,7 +107,7 @@ void dcn10_lock_all_pipes(struct dc *dc, * (un)locking. Also skip if pipe is disabled. */ if (pipe_ctx->top_pipe || - !pipe_ctx->stream || !pipe_ctx->plane_state || + !pipe_ctx->stream || !tg->funcs->is_tg_enabled(tg)) continue; @@ -1112,9 +1112,13 @@ static bool dcn10_hw_wa_force_recovery(struct dc *dc) void dcn10_verify_allow_pstate_change_high(struct dc *dc) { + struct hubbub *hubbub = dc->res_pool->hubbub; static bool should_log_hw_state; /* prevent hw state log by default */ - if (!hubbub1_verify_allow_pstate_change_high(dc->res_pool->hubbub)) { + if (!hubbub->funcs->verify_allow_pstate_change_high) + return; + + if (!hubbub->funcs->verify_allow_pstate_change_high(hubbub)) { int i = 0; if (should_log_hw_state) @@ -1123,8 +1127,8 @@ void dcn10_verify_allow_pstate_change_high(struct dc *dc) TRACE_DC_PIPE_STATE(pipe_ctx, i, MAX_PIPES); BREAK_TO_DEBUGGER(); if (dcn10_hw_wa_force_recovery(dc)) { - /*check again*/ - if (!hubbub1_verify_allow_pstate_change_high(dc->res_pool->hubbub)) + /*check again*/ + if (!hubbub->funcs->verify_allow_pstate_change_high(hubbub)) BREAK_TO_DEBUGGER(); } } @@ -3093,7 +3097,8 @@ static void dcn10_config_stereo_parameters( flags->PROGRAM_STEREO = 1; flags->PROGRAM_POLARITY = 1; - if (timing_3d_format == TIMING_3D_FORMAT_INBAND_FA || + if (timing_3d_format == TIMING_3D_FORMAT_FRAME_ALTERNATE || + timing_3d_format == TIMING_3D_FORMAT_INBAND_FA || timing_3d_format == TIMING_3D_FORMAT_DP_HDMI_INBAND_FA || timing_3d_format == TIMING_3D_FORMAT_SIDEBAND_FA) { enum display_dongle_type dongle = \ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 858b72149897..4048908dd265 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -70,68 +70,6 @@ #include "dce/dce_aux.h" #include "dce/dce_i2c.h" -const struct _vcs_dpi_ip_params_st dcn1_0_ip = { - .rob_buffer_size_kbytes = 64, - .det_buffer_size_kbytes = 164, - .dpte_buffer_size_in_pte_reqs_luma = 42, - .dpp_output_buffer_pixels = 2560, - .opp_output_buffer_lines = 1, - .pixel_chunk_size_kbytes = 8, - .pte_enable = 1, - .pte_chunk_size_kbytes = 2, - .meta_chunk_size_kbytes = 2, - .writeback_chunk_size_kbytes = 2, - .line_buffer_size_bits = 589824, - .max_line_buffer_lines = 12, - .IsLineBufferBppFixed = 0, - .LineBufferFixedBpp = -1, - .writeback_luma_buffer_size_kbytes = 12, - .writeback_chroma_buffer_size_kbytes = 8, - .max_num_dpp = 4, - .max_num_wb = 2, - .max_dchub_pscl_bw_pix_per_clk = 4, - .max_pscl_lb_bw_pix_per_clk = 2, - .max_lb_vscl_bw_pix_per_clk = 4, - .max_vscl_hscl_bw_pix_per_clk = 4, - .max_hscl_ratio = 4, - .max_vscl_ratio = 4, - .hscl_mults = 4, - .vscl_mults = 4, - .max_hscl_taps = 8, - .max_vscl_taps = 8, - .dispclk_ramp_margin_percent = 1, - .underscan_factor = 1.10, - .min_vblank_lines = 14, - .dppclk_delay_subtotal = 90, - .dispclk_delay_subtotal = 42, - .dcfclk_cstate_latency = 10, - .max_inter_dcn_tile_repeaters = 8, - .can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one = 0, - .bug_forcing_LC_req_same_size_fixed = 0, -}; - -const struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc = { - .sr_exit_time_us = 9.0, - .sr_enter_plus_exit_time_us = 11.0, - .urgent_latency_us = 4.0, - .writeback_latency_us = 12.0, - .ideal_dram_bw_after_urgent_percent = 80.0, - .max_request_size_bytes = 256, - .downspread_percent = 0.5, - .dram_page_open_time_ns = 50.0, - .dram_rw_turnaround_time_ns = 17.5, - .dram_return_buffer_per_channel_bytes = 8192, - .round_trip_ping_latency_dcfclk_cycles = 128, - .urgent_out_of_order_return_per_channel_bytes = 256, - .channel_interleave_bytes = 256, - .num_banks = 8, - .num_chans = 2, - .vmm_page_size_bytes = 4096, - .dram_clock_change_latency_us = 17.0, - .writeback_dram_clock_change_latency_us = 23.0, - .return_bus_width_bytes = 64, -}; - #ifndef mmDP0_DP_DPHY_INTERNAL_CTRL #define mmDP0_DP_DPHY_INTERNAL_CTRL 0x210f #define mmDP0_DP_DPHY_INTERNAL_CTRL_BASE_IDX 2 @@ -925,6 +863,21 @@ static struct dce_hwseq *dcn10_hwseq_create( hws->wa.DEGVIDCN10_253 = true; hws->wa.false_optc_underflow = true; hws->wa.DEGVIDCN10_254 = true; + + if ((ctx->asic_id.chip_family == FAMILY_RV) && + ASICREV_IS_RAVEN2(ctx->asic_id.hw_internal_rev)) + switch (ctx->asic_id.pci_revision_id) { + case PRID_POLLOCK_94: + case PRID_POLLOCK_95: + case PRID_POLLOCK_E9: + case PRID_POLLOCK_EA: + case PRID_POLLOCK_EB: + hws->wa.wait_hubpret_read_start_during_mpo_transition = true; + break; + default: + hws->wa.wait_hubpret_read_start_during_mpo_transition = false; + break; + } } return hws; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.h index 633025ccb870..bf8e33cd8147 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.h @@ -27,6 +27,7 @@ #define __DC_RESOURCE_DCN10_H__ #include "core_types.h" +#include "dml/dcn10/dcn10_fpu.h" #define TO_DCN10_RES_POOL(pool)\ container_of(pool, struct dcn10_resource_pool, base) @@ -35,6 +36,9 @@ struct dc; struct resource_pool; struct _vcs_dpi_display_pipe_params_st; +extern struct _vcs_dpi_ip_params_st dcn1_0_ip; +extern struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc; + struct dcn10_resource_pool { struct resource_pool base; }; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile index 5fcaf78334ff..abaed2121feb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile @@ -9,31 +9,6 @@ DCN20 = dcn20_resource.o dcn20_init.o dcn20_hwseq.o dcn20_dpp.o dcn20_dpp_cm.o d DCN20 += dcn20_dsc.o -ifdef CONFIG_X86 -CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse -endif - -ifdef CONFIG_PPC64 -CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -maltivec -endif - -ifdef CONFIG_CC_IS_GCC -ifeq ($(call cc-ifversion, -lt, 0701, y), y) -IS_OLD_GCC = 1 -endif -endif - -ifdef CONFIG_X86 -ifdef IS_OLD_GCC -# Stack alignment mismatch, proceed with caution. -# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 -# (8B stack alignment). -CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -mpreferred-stack-boundary=4 -else -CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -msse2 -endif -endif - AMD_DAL_DCN20 = $(addprefix $(AMDDALPATH)/dc/dcn20/,$(DCN20)) AMD_DISPLAY_FILES += $(AMD_DAL_DCN20) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index dc1752e9f461..a665af19f201 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -707,17 +707,6 @@ bool hubp2_program_surface_flip_and_addr( REG_UPDATE(VMID_SETTINGS_0, VMID, address->vmid); - if (address->type == PLN_ADDR_TYPE_GRPH_STEREO) { - REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_MODE_FOR_STEREOSYNC, 0x1); - REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_IN_STEREOSYNC, 0x1); - - } else { - // turn off stereo if not in stereo - REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_MODE_FOR_STEREOSYNC, 0x0); - REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_IN_STEREOSYNC, 0x0); - } - - /* HW automatically latch rest of address register on write to * DCSURF_PRIMARY_SURFACE_ADDRESS if SURFACE_UPDATE_LOCK is not used @@ -942,10 +931,6 @@ void hubp2_set_blank_regs(struct hubp *hubp, bool blank) struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); uint32_t blank_en = blank ? 1 : 0; - REG_UPDATE_2(DCHUBP_CNTL, - HUBP_BLANK_EN, blank_en, - HUBP_TTU_DISABLE, blank_en); - if (blank) { uint32_t reg_val = REG_READ(DCHUBP_CNTL); @@ -958,9 +943,13 @@ void hubp2_set_blank_regs(struct hubp *hubp, bool blank) */ REG_WAIT(DCHUBP_CNTL, HUBP_NO_OUTSTANDING_REQ, 1, - 1, 200); + 1, 100000); } } + + REG_UPDATE_2(DCHUBP_CNTL, + HUBP_BLANK_EN, blank_en, + HUBP_TTU_DISABLE, 0); } void hubp2_cursor_set_position( diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 1ef880fed776..ab910deed481 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1739,6 +1739,16 @@ void dcn20_program_front_end_for_ctx( || pipe->stream->update_flags.raw) && hws->funcs.program_all_writeback_pipes_in_tree) hws->funcs.program_all_writeback_pipes_in_tree(dc, pipe->stream, context); + + /* Avoid underflow by check of pipe line read when adding 2nd plane. */ + if (hws->wa.wait_hubpret_read_start_during_mpo_transition && + !pipe->top_pipe && + pipe->stream && + pipe->plane_res.hubp->funcs->hubp_wait_pipe_read_start && + dc->current_state->stream_status[0].plane_count == 1 && + context->stream_status[0].plane_count > 1) { + pipe->plane_res.hubp->funcs->hubp_wait_pipe_read_start(pipe->plane_res.hubp); + } } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index dfe2e1c25a26..d473708d5399 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -63,7 +63,6 @@ #include "dcn20_dccg.h" #include "dcn20_vmid.h" #include "dc_link_ddc.h" -#include "dc_link_dp.h" #include "dce/dce_panel_cntl.h" #include "navi10_ip_offset.h" @@ -93,367 +92,6 @@ #define DC_LOGGER_INIT(logger) -struct _vcs_dpi_ip_params_st dcn2_0_ip = { - .odm_capable = 1, - .gpuvm_enable = 0, - .hostvm_enable = 0, - .gpuvm_max_page_table_levels = 4, - .hostvm_max_page_table_levels = 4, - .hostvm_cached_page_table_levels = 0, - .pte_group_size_bytes = 2048, - .num_dsc = 6, - .rob_buffer_size_kbytes = 168, - .det_buffer_size_kbytes = 164, - .dpte_buffer_size_in_pte_reqs_luma = 84, - .pde_proc_buffer_size_64k_reqs = 48, - .dpp_output_buffer_pixels = 2560, - .opp_output_buffer_lines = 1, - .pixel_chunk_size_kbytes = 8, - .pte_chunk_size_kbytes = 2, - .meta_chunk_size_kbytes = 2, - .writeback_chunk_size_kbytes = 2, - .line_buffer_size_bits = 789504, - .is_line_buffer_bpp_fixed = 0, - .line_buffer_fixed_bpp = 0, - .dcc_supported = true, - .max_line_buffer_lines = 12, - .writeback_luma_buffer_size_kbytes = 12, - .writeback_chroma_buffer_size_kbytes = 8, - .writeback_chroma_line_buffer_width_pixels = 4, - .writeback_max_hscl_ratio = 1, - .writeback_max_vscl_ratio = 1, - .writeback_min_hscl_ratio = 1, - .writeback_min_vscl_ratio = 1, - .writeback_max_hscl_taps = 12, - .writeback_max_vscl_taps = 12, - .writeback_line_buffer_luma_buffer_size = 0, - .writeback_line_buffer_chroma_buffer_size = 14643, - .cursor_buffer_size = 8, - .cursor_chunk_size = 2, - .max_num_otg = 6, - .max_num_dpp = 6, - .max_num_wb = 1, - .max_dchub_pscl_bw_pix_per_clk = 4, - .max_pscl_lb_bw_pix_per_clk = 2, - .max_lb_vscl_bw_pix_per_clk = 4, - .max_vscl_hscl_bw_pix_per_clk = 4, - .max_hscl_ratio = 8, - .max_vscl_ratio = 8, - .hscl_mults = 4, - .vscl_mults = 4, - .max_hscl_taps = 8, - .max_vscl_taps = 8, - .dispclk_ramp_margin_percent = 1, - .underscan_factor = 1.10, - .min_vblank_lines = 32, // - .dppclk_delay_subtotal = 77, // - .dppclk_delay_scl_lb_only = 16, - .dppclk_delay_scl = 50, - .dppclk_delay_cnvc_formatter = 8, - .dppclk_delay_cnvc_cursor = 6, - .dispclk_delay_subtotal = 87, // - .dcfclk_cstate_latency = 10, // SRExitTime - .max_inter_dcn_tile_repeaters = 8, - .xfc_supported = true, - .xfc_fill_bw_overhead_percent = 10.0, - .xfc_fill_constant_bytes = 0, - .number_of_cursors = 1, -}; - -static struct _vcs_dpi_ip_params_st dcn2_0_nv14_ip = { - .odm_capable = 1, - .gpuvm_enable = 0, - .hostvm_enable = 0, - .gpuvm_max_page_table_levels = 4, - .hostvm_max_page_table_levels = 4, - .hostvm_cached_page_table_levels = 0, - .num_dsc = 5, - .rob_buffer_size_kbytes = 168, - .det_buffer_size_kbytes = 164, - .dpte_buffer_size_in_pte_reqs_luma = 84, - .dpte_buffer_size_in_pte_reqs_chroma = 42,//todo - .dpp_output_buffer_pixels = 2560, - .opp_output_buffer_lines = 1, - .pixel_chunk_size_kbytes = 8, - .pte_enable = 1, - .max_page_table_levels = 4, - .pte_chunk_size_kbytes = 2, - .meta_chunk_size_kbytes = 2, - .writeback_chunk_size_kbytes = 2, - .line_buffer_size_bits = 789504, - .is_line_buffer_bpp_fixed = 0, - .line_buffer_fixed_bpp = 0, - .dcc_supported = true, - .max_line_buffer_lines = 12, - .writeback_luma_buffer_size_kbytes = 12, - .writeback_chroma_buffer_size_kbytes = 8, - .writeback_chroma_line_buffer_width_pixels = 4, - .writeback_max_hscl_ratio = 1, - .writeback_max_vscl_ratio = 1, - .writeback_min_hscl_ratio = 1, - .writeback_min_vscl_ratio = 1, - .writeback_max_hscl_taps = 12, - .writeback_max_vscl_taps = 12, - .writeback_line_buffer_luma_buffer_size = 0, - .writeback_line_buffer_chroma_buffer_size = 14643, - .cursor_buffer_size = 8, - .cursor_chunk_size = 2, - .max_num_otg = 5, - .max_num_dpp = 5, - .max_num_wb = 1, - .max_dchub_pscl_bw_pix_per_clk = 4, - .max_pscl_lb_bw_pix_per_clk = 2, - .max_lb_vscl_bw_pix_per_clk = 4, - .max_vscl_hscl_bw_pix_per_clk = 4, - .max_hscl_ratio = 8, - .max_vscl_ratio = 8, - .hscl_mults = 4, - .vscl_mults = 4, - .max_hscl_taps = 8, - .max_vscl_taps = 8, - .dispclk_ramp_margin_percent = 1, - .underscan_factor = 1.10, - .min_vblank_lines = 32, // - .dppclk_delay_subtotal = 77, // - .dppclk_delay_scl_lb_only = 16, - .dppclk_delay_scl = 50, - .dppclk_delay_cnvc_formatter = 8, - .dppclk_delay_cnvc_cursor = 6, - .dispclk_delay_subtotal = 87, // - .dcfclk_cstate_latency = 10, // SRExitTime - .max_inter_dcn_tile_repeaters = 8, - .xfc_supported = true, - .xfc_fill_bw_overhead_percent = 10.0, - .xfc_fill_constant_bytes = 0, - .ptoi_supported = 0, - .number_of_cursors = 1, -}; - -static struct _vcs_dpi_soc_bounding_box_st dcn2_0_soc = { - /* Defaults that get patched on driver load from firmware. */ - .clock_limits = { - { - .state = 0, - .dcfclk_mhz = 560.0, - .fabricclk_mhz = 560.0, - .dispclk_mhz = 513.0, - .dppclk_mhz = 513.0, - .phyclk_mhz = 540.0, - .socclk_mhz = 560.0, - .dscclk_mhz = 171.0, - .dram_speed_mts = 8960.0, - }, - { - .state = 1, - .dcfclk_mhz = 694.0, - .fabricclk_mhz = 694.0, - .dispclk_mhz = 642.0, - .dppclk_mhz = 642.0, - .phyclk_mhz = 600.0, - .socclk_mhz = 694.0, - .dscclk_mhz = 214.0, - .dram_speed_mts = 11104.0, - }, - { - .state = 2, - .dcfclk_mhz = 875.0, - .fabricclk_mhz = 875.0, - .dispclk_mhz = 734.0, - .dppclk_mhz = 734.0, - .phyclk_mhz = 810.0, - .socclk_mhz = 875.0, - .dscclk_mhz = 245.0, - .dram_speed_mts = 14000.0, - }, - { - .state = 3, - .dcfclk_mhz = 1000.0, - .fabricclk_mhz = 1000.0, - .dispclk_mhz = 1100.0, - .dppclk_mhz = 1100.0, - .phyclk_mhz = 810.0, - .socclk_mhz = 1000.0, - .dscclk_mhz = 367.0, - .dram_speed_mts = 16000.0, - }, - { - .state = 4, - .dcfclk_mhz = 1200.0, - .fabricclk_mhz = 1200.0, - .dispclk_mhz = 1284.0, - .dppclk_mhz = 1284.0, - .phyclk_mhz = 810.0, - .socclk_mhz = 1200.0, - .dscclk_mhz = 428.0, - .dram_speed_mts = 16000.0, - }, - /*Extra state, no dispclk ramping*/ - { - .state = 5, - .dcfclk_mhz = 1200.0, - .fabricclk_mhz = 1200.0, - .dispclk_mhz = 1284.0, - .dppclk_mhz = 1284.0, - .phyclk_mhz = 810.0, - .socclk_mhz = 1200.0, - .dscclk_mhz = 428.0, - .dram_speed_mts = 16000.0, - }, - }, - .num_states = 5, - .sr_exit_time_us = 8.6, - .sr_enter_plus_exit_time_us = 10.9, - .urgent_latency_us = 4.0, - .urgent_latency_pixel_data_only_us = 4.0, - .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, - .urgent_latency_vm_data_only_us = 4.0, - .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, - .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, - .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, - .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0, - .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0, - .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, - .max_avg_sdp_bw_use_normal_percent = 40.0, - .max_avg_dram_bw_use_normal_percent = 40.0, - .writeback_latency_us = 12.0, - .ideal_dram_bw_after_urgent_percent = 40.0, - .max_request_size_bytes = 256, - .dram_channel_width_bytes = 2, - .fabric_datapath_to_dcn_data_return_bytes = 64, - .dcn_downspread_percent = 0.5, - .downspread_percent = 0.38, - .dram_page_open_time_ns = 50.0, - .dram_rw_turnaround_time_ns = 17.5, - .dram_return_buffer_per_channel_bytes = 8192, - .round_trip_ping_latency_dcfclk_cycles = 131, - .urgent_out_of_order_return_per_channel_bytes = 256, - .channel_interleave_bytes = 256, - .num_banks = 8, - .num_chans = 16, - .vmm_page_size_bytes = 4096, - .dram_clock_change_latency_us = 404.0, - .dummy_pstate_latency_us = 5.0, - .writeback_dram_clock_change_latency_us = 23.0, - .return_bus_width_bytes = 64, - .dispclk_dppclk_vco_speed_mhz = 3850, - .xfc_bus_transport_time_us = 20, - .xfc_xbuf_latency_tolerance_us = 4, - .use_urgent_burst_bw = 0 -}; - -static struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { - .clock_limits = { - { - .state = 0, - .dcfclk_mhz = 560.0, - .fabricclk_mhz = 560.0, - .dispclk_mhz = 513.0, - .dppclk_mhz = 513.0, - .phyclk_mhz = 540.0, - .socclk_mhz = 560.0, - .dscclk_mhz = 171.0, - .dram_speed_mts = 8960.0, - }, - { - .state = 1, - .dcfclk_mhz = 694.0, - .fabricclk_mhz = 694.0, - .dispclk_mhz = 642.0, - .dppclk_mhz = 642.0, - .phyclk_mhz = 600.0, - .socclk_mhz = 694.0, - .dscclk_mhz = 214.0, - .dram_speed_mts = 11104.0, - }, - { - .state = 2, - .dcfclk_mhz = 875.0, - .fabricclk_mhz = 875.0, - .dispclk_mhz = 734.0, - .dppclk_mhz = 734.0, - .phyclk_mhz = 810.0, - .socclk_mhz = 875.0, - .dscclk_mhz = 245.0, - .dram_speed_mts = 14000.0, - }, - { - .state = 3, - .dcfclk_mhz = 1000.0, - .fabricclk_mhz = 1000.0, - .dispclk_mhz = 1100.0, - .dppclk_mhz = 1100.0, - .phyclk_mhz = 810.0, - .socclk_mhz = 1000.0, - .dscclk_mhz = 367.0, - .dram_speed_mts = 16000.0, - }, - { - .state = 4, - .dcfclk_mhz = 1200.0, - .fabricclk_mhz = 1200.0, - .dispclk_mhz = 1284.0, - .dppclk_mhz = 1284.0, - .phyclk_mhz = 810.0, - .socclk_mhz = 1200.0, - .dscclk_mhz = 428.0, - .dram_speed_mts = 16000.0, - }, - /*Extra state, no dispclk ramping*/ - { - .state = 5, - .dcfclk_mhz = 1200.0, - .fabricclk_mhz = 1200.0, - .dispclk_mhz = 1284.0, - .dppclk_mhz = 1284.0, - .phyclk_mhz = 810.0, - .socclk_mhz = 1200.0, - .dscclk_mhz = 428.0, - .dram_speed_mts = 16000.0, - }, - }, - .num_states = 5, - .sr_exit_time_us = 11.6, - .sr_enter_plus_exit_time_us = 13.9, - .urgent_latency_us = 4.0, - .urgent_latency_pixel_data_only_us = 4.0, - .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, - .urgent_latency_vm_data_only_us = 4.0, - .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, - .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, - .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, - .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0, - .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0, - .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, - .max_avg_sdp_bw_use_normal_percent = 40.0, - .max_avg_dram_bw_use_normal_percent = 40.0, - .writeback_latency_us = 12.0, - .ideal_dram_bw_after_urgent_percent = 40.0, - .max_request_size_bytes = 256, - .dram_channel_width_bytes = 2, - .fabric_datapath_to_dcn_data_return_bytes = 64, - .dcn_downspread_percent = 0.5, - .downspread_percent = 0.38, - .dram_page_open_time_ns = 50.0, - .dram_rw_turnaround_time_ns = 17.5, - .dram_return_buffer_per_channel_bytes = 8192, - .round_trip_ping_latency_dcfclk_cycles = 131, - .urgent_out_of_order_return_per_channel_bytes = 256, - .channel_interleave_bytes = 256, - .num_banks = 8, - .num_chans = 8, - .vmm_page_size_bytes = 4096, - .dram_clock_change_latency_us = 404.0, - .dummy_pstate_latency_us = 5.0, - .writeback_dram_clock_change_latency_us = 23.0, - .return_bus_width_bytes = 64, - .dispclk_dppclk_vco_speed_mhz = 3850, - .xfc_bus_transport_time_us = 20, - .xfc_xbuf_latency_tolerance_us = 4, - .use_urgent_burst_bw = 0 -}; - -static struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 }; - #ifndef mmDP0_DP_DPHY_INTERNAL_CTRL #define mmDP0_DP_DPHY_INTERNAL_CTRL 0x210f #define mmDP0_DP_DPHY_INTERNAL_CTRL_BASE_IDX 2 @@ -1810,69 +1448,6 @@ enum dc_status dcn20_remove_stream_from_ctx(struct dc *dc, struct dc_state *new_ return result; } - -static void swizzle_to_dml_params( - enum swizzle_mode_values swizzle, - unsigned int *sw_mode) -{ - switch (swizzle) { - case DC_SW_LINEAR: - *sw_mode = dm_sw_linear; - break; - case DC_SW_4KB_S: - *sw_mode = dm_sw_4kb_s; - break; - case DC_SW_4KB_S_X: - *sw_mode = dm_sw_4kb_s_x; - break; - case DC_SW_4KB_D: - *sw_mode = dm_sw_4kb_d; - break; - case DC_SW_4KB_D_X: - *sw_mode = dm_sw_4kb_d_x; - break; - case DC_SW_64KB_S: - *sw_mode = dm_sw_64kb_s; - break; - case DC_SW_64KB_S_X: - *sw_mode = dm_sw_64kb_s_x; - break; - case DC_SW_64KB_S_T: - *sw_mode = dm_sw_64kb_s_t; - break; - case DC_SW_64KB_D: - *sw_mode = dm_sw_64kb_d; - break; - case DC_SW_64KB_D_X: - *sw_mode = dm_sw_64kb_d_x; - break; - case DC_SW_64KB_D_T: - *sw_mode = dm_sw_64kb_d_t; - break; - case DC_SW_64KB_R_X: - *sw_mode = dm_sw_64kb_r_x; - break; - case DC_SW_VAR_S: - *sw_mode = dm_sw_var_s; - break; - case DC_SW_VAR_S_X: - *sw_mode = dm_sw_var_s_x; - break; - case DC_SW_VAR_D: - *sw_mode = dm_sw_var_d; - break; - case DC_SW_VAR_D_X: - *sw_mode = dm_sw_var_d_x; - break; - case DC_SW_VAR_R_X: - *sw_mode = dm_sw_var_r_x; - break; - default: - ASSERT(0); /* Not supported */ - break; - } -} - bool dcn20_split_stream_for_odm( const struct dc *dc, struct resource_context *res_ctx, @@ -1988,394 +1563,6 @@ void dcn20_split_stream_for_mpc( ASSERT(primary_pipe->plane_state); } -int dcn20_populate_dml_pipes_from_context( - struct dc *dc, - struct dc_state *context, - display_e2e_pipe_params_st *pipes, - bool fast_validate) -{ - int pipe_cnt, i; - bool synchronized_vblank = true; - struct resource_context *res_ctx = &context->res_ctx; - - for (i = 0, pipe_cnt = -1; i < dc->res_pool->pipe_count; i++) { - if (!res_ctx->pipe_ctx[i].stream) - continue; - - if (pipe_cnt < 0) { - pipe_cnt = i; - continue; - } - - if (res_ctx->pipe_ctx[pipe_cnt].stream == res_ctx->pipe_ctx[i].stream) - continue; - - if (dc->debug.disable_timing_sync || - (!resource_are_streams_timing_synchronizable( - res_ctx->pipe_ctx[pipe_cnt].stream, - res_ctx->pipe_ctx[i].stream) && - !resource_are_vblanks_synchronizable( - res_ctx->pipe_ctx[pipe_cnt].stream, - res_ctx->pipe_ctx[i].stream))) { - synchronized_vblank = false; - break; - } - } - - for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { - struct dc_crtc_timing *timing = &res_ctx->pipe_ctx[i].stream->timing; - unsigned int v_total; - unsigned int front_porch; - int output_bpc; - struct audio_check aud_check = {0}; - - if (!res_ctx->pipe_ctx[i].stream) - continue; - - v_total = timing->v_total; - front_porch = timing->v_front_porch; - - /* todo: - pipes[pipe_cnt].pipe.src.dynamic_metadata_enable = 0; - pipes[pipe_cnt].pipe.src.dcc = 0; - pipes[pipe_cnt].pipe.src.vm = 0;*/ - - pipes[pipe_cnt].clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0; - - pipes[pipe_cnt].dout.dsc_enable = res_ctx->pipe_ctx[i].stream->timing.flags.DSC; - /* todo: rotation?*/ - pipes[pipe_cnt].dout.dsc_slices = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.num_slices_h; - if (res_ctx->pipe_ctx[i].stream->use_dynamic_meta) { - pipes[pipe_cnt].pipe.src.dynamic_metadata_enable = true; - /* 1/2 vblank */ - pipes[pipe_cnt].pipe.src.dynamic_metadata_lines_before_active = - (v_total - timing->v_addressable - - timing->v_border_top - timing->v_border_bottom) / 2; - /* 36 bytes dp, 32 hdmi */ - pipes[pipe_cnt].pipe.src.dynamic_metadata_xmit_bytes = - dc_is_dp_signal(res_ctx->pipe_ctx[i].stream->signal) ? 36 : 32; - } - pipes[pipe_cnt].pipe.src.dcc = false; - pipes[pipe_cnt].pipe.src.dcc_rate = 1; - pipes[pipe_cnt].pipe.dest.synchronized_vblank_all_planes = synchronized_vblank; - pipes[pipe_cnt].pipe.dest.hblank_start = timing->h_total - timing->h_front_porch; - pipes[pipe_cnt].pipe.dest.hblank_end = pipes[pipe_cnt].pipe.dest.hblank_start - - timing->h_addressable - - timing->h_border_left - - timing->h_border_right; - pipes[pipe_cnt].pipe.dest.vblank_start = v_total - front_porch; - pipes[pipe_cnt].pipe.dest.vblank_end = pipes[pipe_cnt].pipe.dest.vblank_start - - timing->v_addressable - - timing->v_border_top - - timing->v_border_bottom; - pipes[pipe_cnt].pipe.dest.htotal = timing->h_total; - pipes[pipe_cnt].pipe.dest.vtotal = v_total; - pipes[pipe_cnt].pipe.dest.hactive = - timing->h_addressable + timing->h_border_left + timing->h_border_right; - pipes[pipe_cnt].pipe.dest.vactive = - timing->v_addressable + timing->v_border_top + timing->v_border_bottom; - pipes[pipe_cnt].pipe.dest.interlaced = timing->flags.INTERLACE; - pipes[pipe_cnt].pipe.dest.pixel_rate_mhz = timing->pix_clk_100hz/10000.0; - if (timing->timing_3d_format == TIMING_3D_FORMAT_HW_FRAME_PACKING) - pipes[pipe_cnt].pipe.dest.pixel_rate_mhz *= 2; - pipes[pipe_cnt].pipe.dest.otg_inst = res_ctx->pipe_ctx[i].stream_res.tg->inst; - pipes[pipe_cnt].dout.dp_lanes = 4; - pipes[pipe_cnt].dout.is_virtual = 0; - pipes[pipe_cnt].pipe.dest.vtotal_min = res_ctx->pipe_ctx[i].stream->adjust.v_total_min; - pipes[pipe_cnt].pipe.dest.vtotal_max = res_ctx->pipe_ctx[i].stream->adjust.v_total_max; - switch (get_num_odm_splits(&res_ctx->pipe_ctx[i])) { - case 1: - pipes[pipe_cnt].pipe.dest.odm_combine = dm_odm_combine_mode_2to1; - break; - case 3: - pipes[pipe_cnt].pipe.dest.odm_combine = dm_odm_combine_mode_4to1; - break; - default: - pipes[pipe_cnt].pipe.dest.odm_combine = dm_odm_combine_mode_disabled; - } - pipes[pipe_cnt].pipe.src.hsplit_grp = res_ctx->pipe_ctx[i].pipe_idx; - if (res_ctx->pipe_ctx[i].top_pipe && res_ctx->pipe_ctx[i].top_pipe->plane_state - == res_ctx->pipe_ctx[i].plane_state) { - struct pipe_ctx *first_pipe = res_ctx->pipe_ctx[i].top_pipe; - int split_idx = 0; - - while (first_pipe->top_pipe && first_pipe->top_pipe->plane_state - == res_ctx->pipe_ctx[i].plane_state) { - first_pipe = first_pipe->top_pipe; - split_idx++; - } - /* Treat 4to1 mpc combine as an mpo of 2 2-to-1 combines */ - if (split_idx == 0) - pipes[pipe_cnt].pipe.src.hsplit_grp = first_pipe->pipe_idx; - else if (split_idx == 1) - pipes[pipe_cnt].pipe.src.hsplit_grp = res_ctx->pipe_ctx[i].pipe_idx; - else if (split_idx == 2) - pipes[pipe_cnt].pipe.src.hsplit_grp = res_ctx->pipe_ctx[i].top_pipe->pipe_idx; - } else if (res_ctx->pipe_ctx[i].prev_odm_pipe) { - struct pipe_ctx *first_pipe = res_ctx->pipe_ctx[i].prev_odm_pipe; - - while (first_pipe->prev_odm_pipe) - first_pipe = first_pipe->prev_odm_pipe; - pipes[pipe_cnt].pipe.src.hsplit_grp = first_pipe->pipe_idx; - } - - switch (res_ctx->pipe_ctx[i].stream->signal) { - case SIGNAL_TYPE_DISPLAY_PORT_MST: - case SIGNAL_TYPE_DISPLAY_PORT: - pipes[pipe_cnt].dout.output_type = dm_dp; - break; - case SIGNAL_TYPE_EDP: - pipes[pipe_cnt].dout.output_type = dm_edp; - break; - case SIGNAL_TYPE_HDMI_TYPE_A: - case SIGNAL_TYPE_DVI_SINGLE_LINK: - case SIGNAL_TYPE_DVI_DUAL_LINK: - pipes[pipe_cnt].dout.output_type = dm_hdmi; - break; - default: - /* In case there is no signal, set dp with 4 lanes to allow max config */ - pipes[pipe_cnt].dout.is_virtual = 1; - pipes[pipe_cnt].dout.output_type = dm_dp; - pipes[pipe_cnt].dout.dp_lanes = 4; - } - - switch (res_ctx->pipe_ctx[i].stream->timing.display_color_depth) { - case COLOR_DEPTH_666: - output_bpc = 6; - break; - case COLOR_DEPTH_888: - output_bpc = 8; - break; - case COLOR_DEPTH_101010: - output_bpc = 10; - break; - case COLOR_DEPTH_121212: - output_bpc = 12; - break; - case COLOR_DEPTH_141414: - output_bpc = 14; - break; - case COLOR_DEPTH_161616: - output_bpc = 16; - break; - case COLOR_DEPTH_999: - output_bpc = 9; - break; - case COLOR_DEPTH_111111: - output_bpc = 11; - break; - default: - output_bpc = 8; - break; - } - - switch (res_ctx->pipe_ctx[i].stream->timing.pixel_encoding) { - case PIXEL_ENCODING_RGB: - case PIXEL_ENCODING_YCBCR444: - pipes[pipe_cnt].dout.output_format = dm_444; - pipes[pipe_cnt].dout.output_bpp = output_bpc * 3; - break; - case PIXEL_ENCODING_YCBCR420: - pipes[pipe_cnt].dout.output_format = dm_420; - pipes[pipe_cnt].dout.output_bpp = (output_bpc * 3.0) / 2; - break; - case PIXEL_ENCODING_YCBCR422: - if (res_ctx->pipe_ctx[i].stream->timing.flags.DSC && - !res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.ycbcr422_simple) - pipes[pipe_cnt].dout.output_format = dm_n422; - else - pipes[pipe_cnt].dout.output_format = dm_s422; - pipes[pipe_cnt].dout.output_bpp = output_bpc * 2; - break; - default: - pipes[pipe_cnt].dout.output_format = dm_444; - pipes[pipe_cnt].dout.output_bpp = output_bpc * 3; - } - - if (res_ctx->pipe_ctx[i].stream->timing.flags.DSC) - pipes[pipe_cnt].dout.output_bpp = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.bits_per_pixel / 16.0; - - /* todo: default max for now, until there is logic reflecting this in dc*/ - pipes[pipe_cnt].dout.dsc_input_bpc = 12; - /*fill up the audio sample rate (unit in kHz)*/ - get_audio_check(&res_ctx->pipe_ctx[i].stream->audio_info, &aud_check); - pipes[pipe_cnt].dout.max_audio_sample_rate = aud_check.max_audiosample_rate / 1000; - /* - * For graphic plane, cursor number is 1, nv12 is 0 - * bw calculations due to cursor on/off - */ - if (res_ctx->pipe_ctx[i].plane_state && - res_ctx->pipe_ctx[i].plane_state->address.type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) - pipes[pipe_cnt].pipe.src.num_cursors = 0; - else - pipes[pipe_cnt].pipe.src.num_cursors = dc->dml.ip.number_of_cursors; - - pipes[pipe_cnt].pipe.src.cur0_src_width = 256; - pipes[pipe_cnt].pipe.src.cur0_bpp = dm_cur_32bit; - - if (!res_ctx->pipe_ctx[i].plane_state) { - pipes[pipe_cnt].pipe.src.is_hsplit = pipes[pipe_cnt].pipe.dest.odm_combine != dm_odm_combine_mode_disabled; - pipes[pipe_cnt].pipe.src.source_scan = dm_horz; - pipes[pipe_cnt].pipe.src.sw_mode = dm_sw_4kb_s; - pipes[pipe_cnt].pipe.src.macro_tile_size = dm_64k_tile; - pipes[pipe_cnt].pipe.src.viewport_width = timing->h_addressable; - if (pipes[pipe_cnt].pipe.src.viewport_width > 1920) - pipes[pipe_cnt].pipe.src.viewport_width = 1920; - pipes[pipe_cnt].pipe.src.viewport_height = timing->v_addressable; - if (pipes[pipe_cnt].pipe.src.viewport_height > 1080) - pipes[pipe_cnt].pipe.src.viewport_height = 1080; - pipes[pipe_cnt].pipe.src.surface_height_y = pipes[pipe_cnt].pipe.src.viewport_height; - pipes[pipe_cnt].pipe.src.surface_width_y = pipes[pipe_cnt].pipe.src.viewport_width; - pipes[pipe_cnt].pipe.src.surface_height_c = pipes[pipe_cnt].pipe.src.viewport_height; - pipes[pipe_cnt].pipe.src.surface_width_c = pipes[pipe_cnt].pipe.src.viewport_width; - pipes[pipe_cnt].pipe.src.data_pitch = ((pipes[pipe_cnt].pipe.src.viewport_width + 255) / 256) * 256; - pipes[pipe_cnt].pipe.src.source_format = dm_444_32; - pipes[pipe_cnt].pipe.dest.recout_width = pipes[pipe_cnt].pipe.src.viewport_width; /*vp_width/hratio*/ - pipes[pipe_cnt].pipe.dest.recout_height = pipes[pipe_cnt].pipe.src.viewport_height; /*vp_height/vratio*/ - pipes[pipe_cnt].pipe.dest.full_recout_width = pipes[pipe_cnt].pipe.dest.recout_width; /*when is_hsplit != 1*/ - pipes[pipe_cnt].pipe.dest.full_recout_height = pipes[pipe_cnt].pipe.dest.recout_height; /*when is_hsplit != 1*/ - pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_16; - pipes[pipe_cnt].pipe.scale_ratio_depth.hscl_ratio = 1.0; - pipes[pipe_cnt].pipe.scale_ratio_depth.vscl_ratio = 1.0; - pipes[pipe_cnt].pipe.scale_ratio_depth.scl_enable = 0; /*Lb only or Full scl*/ - pipes[pipe_cnt].pipe.scale_taps.htaps = 1; - pipes[pipe_cnt].pipe.scale_taps.vtaps = 1; - pipes[pipe_cnt].pipe.dest.vtotal_min = v_total; - pipes[pipe_cnt].pipe.dest.vtotal_max = v_total; - - if (pipes[pipe_cnt].pipe.dest.odm_combine == dm_odm_combine_mode_2to1) { - pipes[pipe_cnt].pipe.src.viewport_width /= 2; - pipes[pipe_cnt].pipe.dest.recout_width /= 2; - } else if (pipes[pipe_cnt].pipe.dest.odm_combine == dm_odm_combine_mode_4to1) { - pipes[pipe_cnt].pipe.src.viewport_width /= 4; - pipes[pipe_cnt].pipe.dest.recout_width /= 4; - } - } else { - struct dc_plane_state *pln = res_ctx->pipe_ctx[i].plane_state; - struct scaler_data *scl = &res_ctx->pipe_ctx[i].plane_res.scl_data; - - pipes[pipe_cnt].pipe.src.immediate_flip = pln->flip_immediate; - pipes[pipe_cnt].pipe.src.is_hsplit = (res_ctx->pipe_ctx[i].bottom_pipe && res_ctx->pipe_ctx[i].bottom_pipe->plane_state == pln) - || (res_ctx->pipe_ctx[i].top_pipe && res_ctx->pipe_ctx[i].top_pipe->plane_state == pln) - || pipes[pipe_cnt].pipe.dest.odm_combine != dm_odm_combine_mode_disabled; - - /* stereo is not split */ - if (pln->stereo_format == PLANE_STEREO_FORMAT_SIDE_BY_SIDE || - pln->stereo_format == PLANE_STEREO_FORMAT_TOP_AND_BOTTOM) { - pipes[pipe_cnt].pipe.src.is_hsplit = false; - pipes[pipe_cnt].pipe.src.hsplit_grp = res_ctx->pipe_ctx[i].pipe_idx; - } - - pipes[pipe_cnt].pipe.src.source_scan = pln->rotation == ROTATION_ANGLE_90 - || pln->rotation == ROTATION_ANGLE_270 ? dm_vert : dm_horz; - pipes[pipe_cnt].pipe.src.viewport_y_y = scl->viewport.y; - pipes[pipe_cnt].pipe.src.viewport_y_c = scl->viewport_c.y; - pipes[pipe_cnt].pipe.src.viewport_width = scl->viewport.width; - pipes[pipe_cnt].pipe.src.viewport_width_c = scl->viewport_c.width; - pipes[pipe_cnt].pipe.src.viewport_height = scl->viewport.height; - pipes[pipe_cnt].pipe.src.viewport_height_c = scl->viewport_c.height; - pipes[pipe_cnt].pipe.src.viewport_width_max = pln->src_rect.width; - pipes[pipe_cnt].pipe.src.viewport_height_max = pln->src_rect.height; - pipes[pipe_cnt].pipe.src.surface_width_y = pln->plane_size.surface_size.width; - pipes[pipe_cnt].pipe.src.surface_height_y = pln->plane_size.surface_size.height; - pipes[pipe_cnt].pipe.src.surface_width_c = pln->plane_size.chroma_size.width; - pipes[pipe_cnt].pipe.src.surface_height_c = pln->plane_size.chroma_size.height; - if (pln->format == SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA - || pln->format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) { - pipes[pipe_cnt].pipe.src.data_pitch = pln->plane_size.surface_pitch; - pipes[pipe_cnt].pipe.src.data_pitch_c = pln->plane_size.chroma_pitch; - pipes[pipe_cnt].pipe.src.meta_pitch = pln->dcc.meta_pitch; - pipes[pipe_cnt].pipe.src.meta_pitch_c = pln->dcc.meta_pitch_c; - } else { - pipes[pipe_cnt].pipe.src.data_pitch = pln->plane_size.surface_pitch; - pipes[pipe_cnt].pipe.src.meta_pitch = pln->dcc.meta_pitch; - } - pipes[pipe_cnt].pipe.src.dcc = pln->dcc.enable; - pipes[pipe_cnt].pipe.dest.recout_width = scl->recout.width; - pipes[pipe_cnt].pipe.dest.recout_height = scl->recout.height; - pipes[pipe_cnt].pipe.dest.full_recout_height = scl->recout.height; - pipes[pipe_cnt].pipe.dest.full_recout_width = scl->recout.width; - if (pipes[pipe_cnt].pipe.dest.odm_combine == dm_odm_combine_mode_2to1) - pipes[pipe_cnt].pipe.dest.full_recout_width *= 2; - else if (pipes[pipe_cnt].pipe.dest.odm_combine == dm_odm_combine_mode_4to1) - pipes[pipe_cnt].pipe.dest.full_recout_width *= 4; - else { - struct pipe_ctx *split_pipe = res_ctx->pipe_ctx[i].bottom_pipe; - - while (split_pipe && split_pipe->plane_state == pln) { - pipes[pipe_cnt].pipe.dest.full_recout_width += split_pipe->plane_res.scl_data.recout.width; - split_pipe = split_pipe->bottom_pipe; - } - split_pipe = res_ctx->pipe_ctx[i].top_pipe; - while (split_pipe && split_pipe->plane_state == pln) { - pipes[pipe_cnt].pipe.dest.full_recout_width += split_pipe->plane_res.scl_data.recout.width; - split_pipe = split_pipe->top_pipe; - } - } - - pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_16; - pipes[pipe_cnt].pipe.scale_ratio_depth.hscl_ratio = (double) scl->ratios.horz.value / (1ULL<<32); - pipes[pipe_cnt].pipe.scale_ratio_depth.hscl_ratio_c = (double) scl->ratios.horz_c.value / (1ULL<<32); - pipes[pipe_cnt].pipe.scale_ratio_depth.vscl_ratio = (double) scl->ratios.vert.value / (1ULL<<32); - pipes[pipe_cnt].pipe.scale_ratio_depth.vscl_ratio_c = (double) scl->ratios.vert_c.value / (1ULL<<32); - pipes[pipe_cnt].pipe.scale_ratio_depth.scl_enable = - scl->ratios.vert.value != dc_fixpt_one.value - || scl->ratios.horz.value != dc_fixpt_one.value - || scl->ratios.vert_c.value != dc_fixpt_one.value - || scl->ratios.horz_c.value != dc_fixpt_one.value /*Lb only or Full scl*/ - || dc->debug.always_scale; /*support always scale*/ - pipes[pipe_cnt].pipe.scale_taps.htaps = scl->taps.h_taps; - pipes[pipe_cnt].pipe.scale_taps.htaps_c = scl->taps.h_taps_c; - pipes[pipe_cnt].pipe.scale_taps.vtaps = scl->taps.v_taps; - pipes[pipe_cnt].pipe.scale_taps.vtaps_c = scl->taps.v_taps_c; - - pipes[pipe_cnt].pipe.src.macro_tile_size = - swizzle_mode_to_macro_tile_size(pln->tiling_info.gfx9.swizzle); - swizzle_to_dml_params(pln->tiling_info.gfx9.swizzle, - &pipes[pipe_cnt].pipe.src.sw_mode); - - switch (pln->format) { - case SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr: - case SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb: - pipes[pipe_cnt].pipe.src.source_format = dm_420_8; - break; - case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr: - case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb: - pipes[pipe_cnt].pipe.src.source_format = dm_420_10; - break; - case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616: - case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616: - case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F: - case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F: - pipes[pipe_cnt].pipe.src.source_format = dm_444_64; - break; - case SURFACE_PIXEL_FORMAT_GRPH_ARGB1555: - case SURFACE_PIXEL_FORMAT_GRPH_RGB565: - pipes[pipe_cnt].pipe.src.source_format = dm_444_16; - break; - case SURFACE_PIXEL_FORMAT_GRPH_PALETA_256_COLORS: - pipes[pipe_cnt].pipe.src.source_format = dm_444_8; - break; - case SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA: - pipes[pipe_cnt].pipe.src.source_format = dm_rgbe_alpha; - break; - default: - pipes[pipe_cnt].pipe.src.source_format = dm_444_32; - break; - } - } - - pipe_cnt++; - } - - /* populate writeback information */ - DC_FP_START(); - dc->res_pool->funcs->populate_dml_writeback_from_context(dc, res_ctx, pipes); - DC_FP_END(); - - return pipe_cnt; -} - unsigned int dcn20_calc_max_scaled_time( unsigned int time_per_pixel, enum mmhubbub_wbif_mode mode, @@ -2413,7 +1600,7 @@ void dcn20_set_mcif_arb_params( { enum mmhubbub_wbif_mode wbif_mode; struct mcif_arb_params *wb_arb_params; - int i, j, k, dwb_pipe; + int i, j, dwb_pipe; /* Writeback MCIF_WB arbitration parameters */ dwb_pipe = 0; @@ -2437,11 +1624,10 @@ void dcn20_set_mcif_arb_params( } else wbif_mode = PACKED_444; - for (k = 0; k < sizeof(wb_arb_params->cli_watermark)/sizeof(wb_arb_params->cli_watermark[0]); k++) { - wb_arb_params->cli_watermark[k] = get_wm_writeback_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - wb_arb_params->pstate_watermark[k] = get_wm_writeback_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - } - wb_arb_params->time_per_pixel = 16.0 * 1000 / (context->res_ctx.pipe_ctx[i].stream->phy_pix_clk / 1000); /* 4 bit fraction, ms */ + DC_FP_START(); + dcn20_fpu_set_wb_arb_params(wb_arb_params, context, pipes, pipe_cnt, i); + DC_FP_END(); + wb_arb_params->slice_lines = 32; wb_arb_params->arbitration_slice = 2; wb_arb_params->max_scaled_time = dcn20_calc_max_scaled_time(wb_arb_params->time_per_pixel, @@ -2808,8 +1994,11 @@ int dcn20_validate_apply_pipe_split_flags( } /* Adjust dppclk when split is forced, do not bother with dispclk */ - if (split[i] != 0 && v->NoOfDPP[vlevel][max_mpc_comb][pipe_idx] == 1) - v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] /= 2; + if (split[i] != 0 && v->NoOfDPP[vlevel][max_mpc_comb][pipe_idx] == 1) { + DC_FP_START(); + dcn20_fpu_adjust_dppclk(v, vlevel, max_mpc_comb, pipe_idx, false); + DC_FP_END(); + } pipe_idx++; } @@ -2835,7 +2024,9 @@ bool dcn20_fast_validate_bw( dcn20_merge_pipes_for_validate(dc, context); + DC_FP_START(); pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate); + DC_FP_END(); *pipe_cnt_out = pipe_cnt; @@ -2892,7 +2083,9 @@ bool dcn20_fast_validate_bw( hsplit_pipe = dcn20_find_secondary_pipe(dc, &context->res_ctx, dc->res_pool, pipe); ASSERT(hsplit_pipe); if (!hsplit_pipe) { - context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx] *= 2; + DC_FP_START(); + dcn20_fpu_adjust_dppclk(&context->bw_ctx.dml.vba, vlevel, context->bw_ctx.dml.vba.maxMpcComb, pipe_idx, true); + DC_FP_END(); continue; } if (context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx]) { @@ -2934,369 +2127,6 @@ validate_out: return out; } -static void dcn20_calculate_wm( - struct dc *dc, struct dc_state *context, - display_e2e_pipe_params_st *pipes, - int *out_pipe_cnt, - int *pipe_split_from, - int vlevel, - bool fast_validate) -{ - int pipe_cnt, i, pipe_idx; - - for (i = 0, pipe_idx = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { - if (!context->res_ctx.pipe_ctx[i].stream) - continue; - - pipes[pipe_cnt].clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0; - pipes[pipe_cnt].clks_cfg.dispclk_mhz = context->bw_ctx.dml.vba.RequiredDISPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; - - if (pipe_split_from[i] < 0) { - pipes[pipe_cnt].clks_cfg.dppclk_mhz = - context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx]; - if (context->bw_ctx.dml.vba.BlendingAndTiming[pipe_idx] == pipe_idx) - pipes[pipe_cnt].pipe.dest.odm_combine = - context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx]; - else - pipes[pipe_cnt].pipe.dest.odm_combine = 0; - pipe_idx++; - } else { - pipes[pipe_cnt].clks_cfg.dppclk_mhz = - context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_split_from[i]]; - if (context->bw_ctx.dml.vba.BlendingAndTiming[pipe_split_from[i]] == pipe_split_from[i]) - pipes[pipe_cnt].pipe.dest.odm_combine = - context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_split_from[i]]; - else - pipes[pipe_cnt].pipe.dest.odm_combine = 0; - } - - if (dc->config.forced_clocks) { - pipes[pipe_cnt].clks_cfg.dispclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dispclk_mhz; - pipes[pipe_cnt].clks_cfg.dppclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dppclk_mhz; - } - if (dc->debug.min_disp_clk_khz > pipes[pipe_cnt].clks_cfg.dispclk_mhz * 1000) - pipes[pipe_cnt].clks_cfg.dispclk_mhz = dc->debug.min_disp_clk_khz / 1000.0; - if (dc->debug.min_dpp_clk_khz > pipes[pipe_cnt].clks_cfg.dppclk_mhz * 1000) - pipes[pipe_cnt].clks_cfg.dppclk_mhz = dc->debug.min_dpp_clk_khz / 1000.0; - - pipe_cnt++; - } - - if (pipe_cnt != pipe_idx) { - if (dc->res_pool->funcs->populate_dml_pipes) - pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, - context, pipes, fast_validate); - else - pipe_cnt = dcn20_populate_dml_pipes_from_context(dc, - context, pipes, fast_validate); - } - - *out_pipe_cnt = pipe_cnt; - - pipes[0].clks_cfg.voltage = vlevel; - pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].dcfclk_mhz; - pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].socclk_mhz; - - /* only pipe 0 is read for voltage and dcf/soc clocks */ - if (vlevel < 1) { - pipes[0].clks_cfg.voltage = 1; - pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[1].dcfclk_mhz; - pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[1].socclk_mhz; - } - context->bw_ctx.bw.dcn.watermarks.b.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - - if (vlevel < 2) { - pipes[0].clks_cfg.voltage = 2; - pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[2].dcfclk_mhz; - pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[2].socclk_mhz; - } - context->bw_ctx.bw.dcn.watermarks.c.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - - if (vlevel < 3) { - pipes[0].clks_cfg.voltage = 3; - pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[2].dcfclk_mhz; - pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[2].socclk_mhz; - } - context->bw_ctx.bw.dcn.watermarks.d.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - - pipes[0].clks_cfg.voltage = vlevel; - pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].dcfclk_mhz; - pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].socclk_mhz; - context->bw_ctx.bw.dcn.watermarks.a.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; -} - -static bool is_dtbclk_required(struct dc *dc, struct dc_state *context) -{ - int i; - for (i = 0; i < dc->res_pool->pipe_count; i++) { - if (!context->res_ctx.pipe_ctx[i].stream) - continue; - if (is_dp_128b_132b_signal(&context->res_ctx.pipe_ctx[i])) - return true; - } - return false; -} - -static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struct dc_state *context) -{ - int plane_count; - int i; - - plane_count = 0; - for (i = 0; i < dc->res_pool->pipe_count; i++) { - if (context->res_ctx.pipe_ctx[i].plane_state) - plane_count++; - } - - /* - * Zstate is allowed in following scenarios: - * 1. Single eDP with PSR enabled - * 2. 0 planes (No memory requests) - * 3. Single eDP without PSR but > 5ms stutter period - */ - if (plane_count == 0) - return DCN_ZSTATE_SUPPORT_ALLOW; - else if (context->stream_count == 1 && context->streams[0]->signal == SIGNAL_TYPE_EDP) { - struct dc_link *link = context->streams[0]->sink->link; - - /* zstate only supported on PWRSEQ0 */ - if (link->link_index != 0) - return DCN_ZSTATE_SUPPORT_DISALLOW; - - if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) - return DCN_ZSTATE_SUPPORT_ALLOW; - else if (link->psr_settings.psr_version == DC_PSR_VERSION_1 && !dc->debug.disable_psr) - return DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; - else - return DCN_ZSTATE_SUPPORT_DISALLOW; - } else - return DCN_ZSTATE_SUPPORT_DISALLOW; -} - -void dcn20_calculate_dlg_params( - struct dc *dc, struct dc_state *context, - display_e2e_pipe_params_st *pipes, - int pipe_cnt, - int vlevel) -{ - int i, pipe_idx; - - /* Writeback MCIF_WB arbitration parameters */ - dc->res_pool->funcs->set_mcif_arb_params(dc, context, pipes, pipe_cnt); - - context->bw_ctx.bw.dcn.clk.dispclk_khz = context->bw_ctx.dml.vba.DISPCLK * 1000; - context->bw_ctx.bw.dcn.clk.dcfclk_khz = context->bw_ctx.dml.vba.DCFCLK * 1000; - context->bw_ctx.bw.dcn.clk.socclk_khz = context->bw_ctx.dml.vba.SOCCLK * 1000; - context->bw_ctx.bw.dcn.clk.dramclk_khz = context->bw_ctx.dml.vba.DRAMSpeed * 1000 / 16; - - if (dc->debug.min_dram_clk_khz > context->bw_ctx.bw.dcn.clk.dramclk_khz) - context->bw_ctx.bw.dcn.clk.dramclk_khz = dc->debug.min_dram_clk_khz; - - context->bw_ctx.bw.dcn.clk.dcfclk_deep_sleep_khz = context->bw_ctx.dml.vba.DCFCLKDeepSleep * 1000; - context->bw_ctx.bw.dcn.clk.fclk_khz = context->bw_ctx.dml.vba.FabricClock * 1000; - context->bw_ctx.bw.dcn.clk.p_state_change_support = - context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] - != dm_dram_clock_change_unsupported; - context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; - - context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); - - context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context); - - if (context->bw_ctx.bw.dcn.clk.dispclk_khz < dc->debug.min_disp_clk_khz) - context->bw_ctx.bw.dcn.clk.dispclk_khz = dc->debug.min_disp_clk_khz; - - for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { - if (!context->res_ctx.pipe_ctx[i].stream) - continue; - pipes[pipe_idx].pipe.dest.vstartup_start = get_vstartup(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); - pipes[pipe_idx].pipe.dest.vupdate_offset = get_vupdate_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); - pipes[pipe_idx].pipe.dest.vupdate_width = get_vupdate_width(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); - pipes[pipe_idx].pipe.dest.vready_offset = get_vready_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); - context->res_ctx.pipe_ctx[i].det_buffer_size_kb = context->bw_ctx.dml.ip.det_buffer_size_kbytes; - context->res_ctx.pipe_ctx[i].unbounded_req = pipes[pipe_idx].pipe.src.unbounded_req_mode; - - if (context->bw_ctx.bw.dcn.clk.dppclk_khz < pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000) - context->bw_ctx.bw.dcn.clk.dppclk_khz = pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000; - context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz = - pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000; - context->res_ctx.pipe_ctx[i].pipe_dlg_param = pipes[pipe_idx].pipe.dest; - pipe_idx++; - } - /*save a original dppclock copy*/ - context->bw_ctx.bw.dcn.clk.bw_dppclk_khz = context->bw_ctx.bw.dcn.clk.dppclk_khz; - context->bw_ctx.bw.dcn.clk.bw_dispclk_khz = context->bw_ctx.bw.dcn.clk.dispclk_khz; - context->bw_ctx.bw.dcn.clk.max_supported_dppclk_khz = context->bw_ctx.dml.soc.clock_limits[vlevel].dppclk_mhz * 1000; - context->bw_ctx.bw.dcn.clk.max_supported_dispclk_khz = context->bw_ctx.dml.soc.clock_limits[vlevel].dispclk_mhz * 1000; - - context->bw_ctx.bw.dcn.compbuf_size_kb = context->bw_ctx.dml.ip.config_return_buffer_size_in_kbytes - - context->bw_ctx.dml.ip.det_buffer_size_kbytes * pipe_idx; - - for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { - bool cstate_en = context->bw_ctx.dml.vba.PrefetchMode[vlevel][context->bw_ctx.dml.vba.maxMpcComb] != 2; - - if (!context->res_ctx.pipe_ctx[i].stream) - continue; - - if (dc->ctx->dce_version == DCN_VERSION_2_01) - cstate_en = false; - - context->bw_ctx.dml.funcs.rq_dlg_get_dlg_reg(&context->bw_ctx.dml, - &context->res_ctx.pipe_ctx[i].dlg_regs, - &context->res_ctx.pipe_ctx[i].ttu_regs, - pipes, - pipe_cnt, - pipe_idx, - cstate_en, - context->bw_ctx.bw.dcn.clk.p_state_change_support, - false, false, true); - - context->bw_ctx.dml.funcs.rq_dlg_get_rq_reg(&context->bw_ctx.dml, - &context->res_ctx.pipe_ctx[i].rq_regs, - &pipes[pipe_idx].pipe); - pipe_idx++; - } -} - -static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *context, - bool fast_validate) -{ - bool out = false; - - BW_VAL_TRACE_SETUP(); - - int vlevel = 0; - int pipe_split_from[MAX_PIPES]; - int pipe_cnt = 0; - display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC); - DC_LOGGER_INIT(dc->ctx->logger); - - BW_VAL_TRACE_COUNT(); - - out = dcn20_fast_validate_bw(dc, context, pipes, &pipe_cnt, pipe_split_from, &vlevel, fast_validate); - - if (pipe_cnt == 0) - goto validate_out; - - if (!out) - goto validate_fail; - - BW_VAL_TRACE_END_VOLTAGE_LEVEL(); - - if (fast_validate) { - BW_VAL_TRACE_SKIP(fast); - goto validate_out; - } - - dcn20_calculate_wm(dc, context, pipes, &pipe_cnt, pipe_split_from, vlevel, fast_validate); - dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); - - BW_VAL_TRACE_END_WATERMARKS(); - - goto validate_out; - -validate_fail: - DC_LOG_WARNING("Mode Validation Warning: %s failed validation.\n", - dml_get_status_message(context->bw_ctx.dml.vba.ValidationStatus[context->bw_ctx.dml.vba.soc.num_states])); - - BW_VAL_TRACE_SKIP(fail); - out = false; - -validate_out: - kfree(pipes); - - BW_VAL_TRACE_FINISH(); - - return out; -} - -/* - * This must be noinline to ensure anything that deals with FP registers - * is contained within this call; previously our compiling with hard-float - * would result in fp instructions being emitted outside of the boundaries - * of the DC_FP_START/END macros, which makes sense as the compiler has no - * idea about what is wrapped and what is not - * - * This is largely just a workaround to avoid breakage introduced with 5.6, - * ideally all fp-using code should be moved into its own file, only that - * should be compiled with hard-float, and all code exported from there - * should be strictly wrapped with DC_FP_START/END - */ -static noinline bool dcn20_validate_bandwidth_fp(struct dc *dc, - struct dc_state *context, bool fast_validate) -{ - bool voltage_supported = false; - bool full_pstate_supported = false; - bool dummy_pstate_supported = false; - double p_state_latency_us; - - p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us; - context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support = - dc->debug.disable_dram_clock_change_vactive_support; - context->bw_ctx.dml.soc.allow_dram_clock_one_display_vactive = - dc->debug.enable_dram_clock_change_one_display_vactive; - - /*Unsafe due to current pipe merge and split logic*/ - ASSERT(context != dc->current_state); - - if (fast_validate) { - return dcn20_validate_bandwidth_internal(dc, context, true); - } - - // Best case, we support full UCLK switch latency - voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false); - full_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support; - - if (context->bw_ctx.dml.soc.dummy_pstate_latency_us == 0 || - (voltage_supported && full_pstate_supported)) { - context->bw_ctx.bw.dcn.clk.p_state_change_support = full_pstate_supported; - goto restore_dml_state; - } - - // Fallback: Try to only support G6 temperature read latency - context->bw_ctx.dml.soc.dram_clock_change_latency_us = context->bw_ctx.dml.soc.dummy_pstate_latency_us; - - voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false); - dummy_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support; - - if (voltage_supported && (dummy_pstate_supported || !(context->stream_count))) { - context->bw_ctx.bw.dcn.clk.p_state_change_support = false; - goto restore_dml_state; - } - - // ERROR: fallback is supposed to always work. - ASSERT(false); - -restore_dml_state: - context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us; - return voltage_supported; -} - bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, bool fast_validate) { @@ -3464,170 +2294,6 @@ static void dcn20_pp_smu_destroy(struct pp_smu_funcs **pp_smu) } } -void dcn20_cap_soc_clocks( - struct _vcs_dpi_soc_bounding_box_st *bb, - struct pp_smu_nv_clock_table max_clocks) -{ - int i; - - // First pass - cap all clocks higher than the reported max - for (i = 0; i < bb->num_states; i++) { - if ((bb->clock_limits[i].dcfclk_mhz > (max_clocks.dcfClockInKhz / 1000)) - && max_clocks.dcfClockInKhz != 0) - bb->clock_limits[i].dcfclk_mhz = (max_clocks.dcfClockInKhz / 1000); - - if ((bb->clock_limits[i].dram_speed_mts > (max_clocks.uClockInKhz / 1000) * 16) - && max_clocks.uClockInKhz != 0) - bb->clock_limits[i].dram_speed_mts = (max_clocks.uClockInKhz / 1000) * 16; - - if ((bb->clock_limits[i].fabricclk_mhz > (max_clocks.fabricClockInKhz / 1000)) - && max_clocks.fabricClockInKhz != 0) - bb->clock_limits[i].fabricclk_mhz = (max_clocks.fabricClockInKhz / 1000); - - if ((bb->clock_limits[i].dispclk_mhz > (max_clocks.displayClockInKhz / 1000)) - && max_clocks.displayClockInKhz != 0) - bb->clock_limits[i].dispclk_mhz = (max_clocks.displayClockInKhz / 1000); - - if ((bb->clock_limits[i].dppclk_mhz > (max_clocks.dppClockInKhz / 1000)) - && max_clocks.dppClockInKhz != 0) - bb->clock_limits[i].dppclk_mhz = (max_clocks.dppClockInKhz / 1000); - - if ((bb->clock_limits[i].phyclk_mhz > (max_clocks.phyClockInKhz / 1000)) - && max_clocks.phyClockInKhz != 0) - bb->clock_limits[i].phyclk_mhz = (max_clocks.phyClockInKhz / 1000); - - if ((bb->clock_limits[i].socclk_mhz > (max_clocks.socClockInKhz / 1000)) - && max_clocks.socClockInKhz != 0) - bb->clock_limits[i].socclk_mhz = (max_clocks.socClockInKhz / 1000); - - if ((bb->clock_limits[i].dscclk_mhz > (max_clocks.dscClockInKhz / 1000)) - && max_clocks.dscClockInKhz != 0) - bb->clock_limits[i].dscclk_mhz = (max_clocks.dscClockInKhz / 1000); - } - - // Second pass - remove all duplicate clock states - for (i = bb->num_states - 1; i > 1; i--) { - bool duplicate = true; - - if (bb->clock_limits[i-1].dcfclk_mhz != bb->clock_limits[i].dcfclk_mhz) - duplicate = false; - if (bb->clock_limits[i-1].dispclk_mhz != bb->clock_limits[i].dispclk_mhz) - duplicate = false; - if (bb->clock_limits[i-1].dppclk_mhz != bb->clock_limits[i].dppclk_mhz) - duplicate = false; - if (bb->clock_limits[i-1].dram_speed_mts != bb->clock_limits[i].dram_speed_mts) - duplicate = false; - if (bb->clock_limits[i-1].dscclk_mhz != bb->clock_limits[i].dscclk_mhz) - duplicate = false; - if (bb->clock_limits[i-1].fabricclk_mhz != bb->clock_limits[i].fabricclk_mhz) - duplicate = false; - if (bb->clock_limits[i-1].phyclk_mhz != bb->clock_limits[i].phyclk_mhz) - duplicate = false; - if (bb->clock_limits[i-1].socclk_mhz != bb->clock_limits[i].socclk_mhz) - duplicate = false; - - if (duplicate) - bb->num_states--; - } -} - -void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb, - struct pp_smu_nv_clock_table *max_clocks, unsigned int *uclk_states, unsigned int num_states) -{ - struct _vcs_dpi_voltage_scaling_st calculated_states[DC__VOLTAGE_STATES]; - int i; - int num_calculated_states = 0; - int min_dcfclk = 0; - - if (num_states == 0) - return; - - memset(calculated_states, 0, sizeof(calculated_states)); - - if (dc->bb_overrides.min_dcfclk_mhz > 0) - min_dcfclk = dc->bb_overrides.min_dcfclk_mhz; - else { - if (ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) - min_dcfclk = 310; - else - // Accounting for SOC/DCF relationship, we can go as high as - // 506Mhz in Vmin. - min_dcfclk = 506; - } - - for (i = 0; i < num_states; i++) { - int min_fclk_required_by_uclk; - calculated_states[i].state = i; - calculated_states[i].dram_speed_mts = uclk_states[i] * 16 / 1000; - - // FCLK:UCLK ratio is 1.08 - min_fclk_required_by_uclk = div_u64(((unsigned long long)uclk_states[i]) * 1080, - 1000000); - - calculated_states[i].fabricclk_mhz = (min_fclk_required_by_uclk < min_dcfclk) ? - min_dcfclk : min_fclk_required_by_uclk; - - calculated_states[i].socclk_mhz = (calculated_states[i].fabricclk_mhz > max_clocks->socClockInKhz / 1000) ? - max_clocks->socClockInKhz / 1000 : calculated_states[i].fabricclk_mhz; - - calculated_states[i].dcfclk_mhz = (calculated_states[i].fabricclk_mhz > max_clocks->dcfClockInKhz / 1000) ? - max_clocks->dcfClockInKhz / 1000 : calculated_states[i].fabricclk_mhz; - - calculated_states[i].dispclk_mhz = max_clocks->displayClockInKhz / 1000; - calculated_states[i].dppclk_mhz = max_clocks->displayClockInKhz / 1000; - calculated_states[i].dscclk_mhz = max_clocks->displayClockInKhz / (1000 * 3); - - calculated_states[i].phyclk_mhz = max_clocks->phyClockInKhz / 1000; - - num_calculated_states++; - } - - calculated_states[num_calculated_states - 1].socclk_mhz = max_clocks->socClockInKhz / 1000; - calculated_states[num_calculated_states - 1].fabricclk_mhz = max_clocks->socClockInKhz / 1000; - calculated_states[num_calculated_states - 1].dcfclk_mhz = max_clocks->dcfClockInKhz / 1000; - - memcpy(bb->clock_limits, calculated_states, sizeof(bb->clock_limits)); - bb->num_states = num_calculated_states; - - // Duplicate the last state, DML always an extra state identical to max state to work - memcpy(&bb->clock_limits[num_calculated_states], &bb->clock_limits[num_calculated_states - 1], sizeof(struct _vcs_dpi_voltage_scaling_st)); - bb->clock_limits[num_calculated_states].state = bb->num_states; -} - -void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb) -{ - if ((int)(bb->sr_exit_time_us * 1000) != dc->bb_overrides.sr_exit_time_ns - && dc->bb_overrides.sr_exit_time_ns) { - bb->sr_exit_time_us = dc->bb_overrides.sr_exit_time_ns / 1000.0; - } - - if ((int)(bb->sr_enter_plus_exit_time_us * 1000) - != dc->bb_overrides.sr_enter_plus_exit_time_ns - && dc->bb_overrides.sr_enter_plus_exit_time_ns) { - bb->sr_enter_plus_exit_time_us = - dc->bb_overrides.sr_enter_plus_exit_time_ns / 1000.0; - } - - if ((int)(bb->urgent_latency_us * 1000) != dc->bb_overrides.urgent_latency_ns - && dc->bb_overrides.urgent_latency_ns) { - bb->urgent_latency_us = dc->bb_overrides.urgent_latency_ns / 1000.0; - } - - if ((int)(bb->dram_clock_change_latency_us * 1000) - != dc->bb_overrides.dram_clock_change_latency_ns - && dc->bb_overrides.dram_clock_change_latency_ns) { - bb->dram_clock_change_latency_us = - dc->bb_overrides.dram_clock_change_latency_ns / 1000.0; - } - - if ((int)(bb->dummy_pstate_latency_us * 1000) - != dc->bb_overrides.dummy_clock_change_latency_ns - && dc->bb_overrides.dummy_clock_change_latency_ns) { - bb->dummy_pstate_latency_us = - dc->bb_overrides.dummy_clock_change_latency_ns / 1000.0; - } -} - static struct _vcs_dpi_soc_bounding_box_st *get_asic_rev_soc_bb( uint32_t hw_internal_rev) { @@ -3910,8 +2576,9 @@ static bool dcn20_resource_construct( ranges.reader_wm_sets[i].wm_inst = i; ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN; ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX; - ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0; - ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16; + DC_FP_START(); + dcn20_fpu_set_wm_ranges(i, &ranges, loaded_bb); + DC_FP_END(); ranges.num_reader_wm_sets = i + 1; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h index 6ec8ff45f0f7..7cbe1e9daa36 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h @@ -27,6 +27,7 @@ #define __DC_RESOURCE_DCN20_H__ #include "core_types.h" +#include "dml/dcn20/dcn20_fpu.h" #define TO_DCN20_RES_POOL(pool)\ container_of(pool, struct dcn20_resource_pool, base) @@ -35,6 +36,12 @@ struct dc; struct resource_pool; struct _vcs_dpi_display_pipe_params_st; +extern struct _vcs_dpi_ip_params_st dcn2_0_ip; +extern struct _vcs_dpi_ip_params_st dcn2_0_nv14_ip; +extern struct _vcs_dpi_soc_bounding_box_st dcn2_0_soc; +extern struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc; +extern struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc; + struct dcn20_resource_pool { struct resource_pool base; }; @@ -49,11 +56,7 @@ unsigned int dcn20_calc_max_scaled_time( unsigned int time_per_pixel, enum mmhubbub_wbif_mode mode, unsigned int urgent_watermark); -int dcn20_populate_dml_pipes_from_context( - struct dc *dc, - struct dc_state *context, - display_e2e_pipe_params_st *pipes, - bool fast_validate); + struct pipe_ctx *dcn20_acquire_idle_pipe_for_layer( struct dc_state *state, const struct resource_pool *pool, @@ -79,7 +82,6 @@ struct dpp *dcn20_dpp_create( struct input_pixel_processor *dcn20_ipp_create( struct dc_context *ctx, uint32_t inst); - struct output_pixel_processor *dcn20_opp_create( struct dc_context *ctx, uint32_t inst); @@ -96,11 +98,6 @@ struct display_stream_compressor *dcn20_dsc_create( struct dc_context *ctx, uint32_t inst); void dcn20_dsc_destroy(struct display_stream_compressor **dsc); -void dcn20_cap_soc_clocks( - struct _vcs_dpi_soc_bounding_box_st *bb, - struct pp_smu_nv_clock_table max_clocks); -void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb, - struct pp_smu_nv_clock_table *max_clocks, unsigned int *uclk_states, unsigned int num_states); struct hubp *dcn20_hubp_create( struct dc_context *ctx, uint32_t inst); @@ -158,11 +155,6 @@ bool dcn20_fast_validate_bw( int *pipe_split_from, int *vlevel_out, bool fast_validate); -void dcn20_calculate_dlg_params( - struct dc *dc, struct dc_state *context, - display_e2e_pipe_params_st *pipes, - int pipe_cnt, - int vlevel); enum dc_status dcn20_build_mapped_resource(const struct dc *dc, struct dc_state *context, struct dc_stream_state *stream); enum dc_status dcn20_add_stream_to_ctx(struct dc *dc, struct dc_state *new_ctx, struct dc_stream_state *dc_stream); @@ -170,12 +162,5 @@ enum dc_status dcn20_add_dsc_to_stream_resource(struct dc *dc, struct dc_state * enum dc_status dcn20_remove_stream_from_ctx(struct dc *dc, struct dc_state *new_ctx, struct dc_stream_state *dc_stream); enum dc_status dcn20_patch_unknown_plane_state(struct dc_plane_state *plane_state); -void dcn20_patch_bounding_box( - struct dc *dc, - struct _vcs_dpi_soc_bounding_box_st *bb); -void dcn20_cap_soc_clocks( - struct _vcs_dpi_soc_bounding_box_st *bb, - struct pp_smu_nv_clock_table max_clocks); - #endif /* __DC_RESOURCE_DCN20_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile index bb8c95141082..0dc06e428999 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile @@ -5,31 +5,6 @@ DCN21 = dcn21_init.o dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o \ dcn21_hwseq.o dcn21_link_encoder.o dcn21_dccg.o -ifdef CONFIG_X86 -CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse -endif - -ifdef CONFIG_PPC64 -CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -maltivec -endif - -ifdef CONFIG_CC_IS_GCC -ifeq ($(call cc-ifversion, -lt, 0701, y), y) -IS_OLD_GCC = 1 -endif -endif - -ifdef CONFIG_X86 -ifdef IS_OLD_GCC -# Stack alignment mismatch, proceed with caution. -# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 -# (8B stack alignment). -CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -mpreferred-stack-boundary=4 -else -CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2 -endif -endif - AMD_DAL_DCN21 = $(addprefix $(AMDDALPATH)/dc/dcn21/,$(DCN21)) AMD_DISPLAY_FILES += $(AMD_DAL_DCN21) diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index e5cc6bf45743..612732656772 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -34,6 +34,7 @@ #include "resource.h" #include "include/irq_service_interface.h" #include "dcn20/dcn20_resource.h" +#include "dcn21/dcn21_resource.h" #include "dml/dcn20/dcn20_fpu.h" @@ -89,230 +90,6 @@ #include "dce/dmub_psr.h" #include "dce/dmub_abm.h" -#define DC_LOGGER_INIT(logger) - - -struct _vcs_dpi_ip_params_st dcn2_1_ip = { - .odm_capable = 1, - .gpuvm_enable = 1, - .hostvm_enable = 1, - .gpuvm_max_page_table_levels = 1, - .hostvm_max_page_table_levels = 4, - .hostvm_cached_page_table_levels = 2, - .num_dsc = 3, - .rob_buffer_size_kbytes = 168, - .det_buffer_size_kbytes = 164, - .dpte_buffer_size_in_pte_reqs_luma = 44, - .dpte_buffer_size_in_pte_reqs_chroma = 42,//todo - .dpp_output_buffer_pixels = 2560, - .opp_output_buffer_lines = 1, - .pixel_chunk_size_kbytes = 8, - .pte_enable = 1, - .max_page_table_levels = 4, - .pte_chunk_size_kbytes = 2, - .meta_chunk_size_kbytes = 2, - .min_meta_chunk_size_bytes = 256, - .writeback_chunk_size_kbytes = 2, - .line_buffer_size_bits = 789504, - .is_line_buffer_bpp_fixed = 0, - .line_buffer_fixed_bpp = 0, - .dcc_supported = true, - .max_line_buffer_lines = 12, - .writeback_luma_buffer_size_kbytes = 12, - .writeback_chroma_buffer_size_kbytes = 8, - .writeback_chroma_line_buffer_width_pixels = 4, - .writeback_max_hscl_ratio = 1, - .writeback_max_vscl_ratio = 1, - .writeback_min_hscl_ratio = 1, - .writeback_min_vscl_ratio = 1, - .writeback_max_hscl_taps = 12, - .writeback_max_vscl_taps = 12, - .writeback_line_buffer_luma_buffer_size = 0, - .writeback_line_buffer_chroma_buffer_size = 14643, - .cursor_buffer_size = 8, - .cursor_chunk_size = 2, - .max_num_otg = 4, - .max_num_dpp = 4, - .max_num_wb = 1, - .max_dchub_pscl_bw_pix_per_clk = 4, - .max_pscl_lb_bw_pix_per_clk = 2, - .max_lb_vscl_bw_pix_per_clk = 4, - .max_vscl_hscl_bw_pix_per_clk = 4, - .max_hscl_ratio = 4, - .max_vscl_ratio = 4, - .hscl_mults = 4, - .vscl_mults = 4, - .max_hscl_taps = 8, - .max_vscl_taps = 8, - .dispclk_ramp_margin_percent = 1, - .underscan_factor = 1.10, - .min_vblank_lines = 32, // - .dppclk_delay_subtotal = 77, // - .dppclk_delay_scl_lb_only = 16, - .dppclk_delay_scl = 50, - .dppclk_delay_cnvc_formatter = 8, - .dppclk_delay_cnvc_cursor = 6, - .dispclk_delay_subtotal = 87, // - .dcfclk_cstate_latency = 10, // SRExitTime - .max_inter_dcn_tile_repeaters = 8, - - .xfc_supported = false, - .xfc_fill_bw_overhead_percent = 10.0, - .xfc_fill_constant_bytes = 0, - .ptoi_supported = 0, - .number_of_cursors = 1, -}; - -struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { - .clock_limits = { - { - .state = 0, - .dcfclk_mhz = 400.0, - .fabricclk_mhz = 400.0, - .dispclk_mhz = 600.0, - .dppclk_mhz = 400.00, - .phyclk_mhz = 600.0, - .socclk_mhz = 278.0, - .dscclk_mhz = 205.67, - .dram_speed_mts = 1600.0, - }, - { - .state = 1, - .dcfclk_mhz = 464.52, - .fabricclk_mhz = 800.0, - .dispclk_mhz = 654.55, - .dppclk_mhz = 626.09, - .phyclk_mhz = 600.0, - .socclk_mhz = 278.0, - .dscclk_mhz = 205.67, - .dram_speed_mts = 1600.0, - }, - { - .state = 2, - .dcfclk_mhz = 514.29, - .fabricclk_mhz = 933.0, - .dispclk_mhz = 757.89, - .dppclk_mhz = 685.71, - .phyclk_mhz = 600.0, - .socclk_mhz = 278.0, - .dscclk_mhz = 287.67, - .dram_speed_mts = 1866.0, - }, - { - .state = 3, - .dcfclk_mhz = 576.00, - .fabricclk_mhz = 1067.0, - .dispclk_mhz = 847.06, - .dppclk_mhz = 757.89, - .phyclk_mhz = 600.0, - .socclk_mhz = 715.0, - .dscclk_mhz = 318.334, - .dram_speed_mts = 2134.0, - }, - { - .state = 4, - .dcfclk_mhz = 626.09, - .fabricclk_mhz = 1200.0, - .dispclk_mhz = 900.00, - .dppclk_mhz = 847.06, - .phyclk_mhz = 810.0, - .socclk_mhz = 953.0, - .dscclk_mhz = 489.0, - .dram_speed_mts = 2400.0, - }, - { - .state = 5, - .dcfclk_mhz = 685.71, - .fabricclk_mhz = 1333.0, - .dispclk_mhz = 1028.57, - .dppclk_mhz = 960.00, - .phyclk_mhz = 810.0, - .socclk_mhz = 278.0, - .dscclk_mhz = 287.67, - .dram_speed_mts = 2666.0, - }, - { - .state = 6, - .dcfclk_mhz = 757.89, - .fabricclk_mhz = 1467.0, - .dispclk_mhz = 1107.69, - .dppclk_mhz = 1028.57, - .phyclk_mhz = 810.0, - .socclk_mhz = 715.0, - .dscclk_mhz = 318.334, - .dram_speed_mts = 3200.0, - }, - { - .state = 7, - .dcfclk_mhz = 847.06, - .fabricclk_mhz = 1600.0, - .dispclk_mhz = 1395.0, - .dppclk_mhz = 1285.00, - .phyclk_mhz = 1325.0, - .socclk_mhz = 953.0, - .dscclk_mhz = 489.0, - .dram_speed_mts = 4266.0, - }, - /*Extra state, no dispclk ramping*/ - { - .state = 8, - .dcfclk_mhz = 847.06, - .fabricclk_mhz = 1600.0, - .dispclk_mhz = 1395.0, - .dppclk_mhz = 1285.0, - .phyclk_mhz = 1325.0, - .socclk_mhz = 953.0, - .dscclk_mhz = 489.0, - .dram_speed_mts = 4266.0, - }, - - }, - - .sr_exit_time_us = 12.5, - .sr_enter_plus_exit_time_us = 17.0, - .urgent_latency_us = 4.0, - .urgent_latency_pixel_data_only_us = 4.0, - .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, - .urgent_latency_vm_data_only_us = 4.0, - .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, - .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, - .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, - .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 80.0, - .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 75.0, - .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, - .max_avg_sdp_bw_use_normal_percent = 60.0, - .max_avg_dram_bw_use_normal_percent = 100.0, - .writeback_latency_us = 12.0, - .max_request_size_bytes = 256, - .dram_channel_width_bytes = 4, - .fabric_datapath_to_dcn_data_return_bytes = 32, - .dcn_downspread_percent = 0.5, - .downspread_percent = 0.38, - .dram_page_open_time_ns = 50.0, - .dram_rw_turnaround_time_ns = 17.5, - .dram_return_buffer_per_channel_bytes = 8192, - .round_trip_ping_latency_dcfclk_cycles = 128, - .urgent_out_of_order_return_per_channel_bytes = 4096, - .channel_interleave_bytes = 256, - .num_banks = 8, - .num_chans = 4, - .vmm_page_size_bytes = 4096, - .dram_clock_change_latency_us = 23.84, - .return_bus_width_bytes = 64, - .dispclk_dppclk_vco_speed_mhz = 3600, - .xfc_bus_transport_time_us = 4, - .xfc_xbuf_latency_tolerance_us = 4, - .use_urgent_burst_bw = 1, - .num_states = 8 -}; - -#ifndef MAX -#define MAX(X, Y) ((X) > (Y) ? (X) : (Y)) -#endif -#ifndef MIN -#define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) -#endif - /* begin ********************* * macros to expend register list macro defined in HW object header file */ @@ -705,12 +482,6 @@ static const struct dcn10_stream_encoder_mask se_mask = { static void dcn21_pp_smu_destroy(struct pp_smu_funcs **pp_smu); -static int dcn21_populate_dml_pipes_from_context( - struct dc *dc, - struct dc_state *context, - display_e2e_pipe_params_st *pipes, - bool fast_validate); - static struct input_pixel_processor *dcn21_ipp_create( struct dc_context *ctx, uint32_t inst) { @@ -1029,163 +800,13 @@ static void dcn21_resource_destruct(struct dcn21_resource_pool *pool) dcn21_pp_smu_destroy(&pool->base.pp_smu); } - -static void calculate_wm_set_for_vlevel( - int vlevel, - struct wm_range_table_entry *table_entry, - struct dcn_watermarks *wm_set, - struct display_mode_lib *dml, - display_e2e_pipe_params_st *pipes, - int pipe_cnt) -{ - double dram_clock_change_latency_cached = dml->soc.dram_clock_change_latency_us; - - ASSERT(vlevel < dml->soc.num_states); - /* only pipe 0 is read for voltage and dcf/soc clocks */ - pipes[0].clks_cfg.voltage = vlevel; - pipes[0].clks_cfg.dcfclk_mhz = dml->soc.clock_limits[vlevel].dcfclk_mhz; - pipes[0].clks_cfg.socclk_mhz = dml->soc.clock_limits[vlevel].socclk_mhz; - - dml->soc.dram_clock_change_latency_us = table_entry->pstate_latency_us; - dml->soc.sr_exit_time_us = table_entry->sr_exit_time_us; - dml->soc.sr_enter_plus_exit_time_us = table_entry->sr_enter_plus_exit_time_us; - - wm_set->urgent_ns = get_wm_urgent(dml, pipes, pipe_cnt) * 1000; - wm_set->cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(dml, pipes, pipe_cnt) * 1000; - wm_set->cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(dml, pipes, pipe_cnt) * 1000; - wm_set->cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(dml, pipes, pipe_cnt) * 1000; - wm_set->pte_meta_urgent_ns = get_wm_memory_trip(dml, pipes, pipe_cnt) * 1000; - wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000; - wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000; - wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000; - dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached; - -} - -static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb) -{ - int i; - - if (dc->bb_overrides.sr_exit_time_ns) { - for (i = 0; i < WM_SET_COUNT; i++) { - dc->clk_mgr->bw_params->wm_table.entries[i].sr_exit_time_us = - dc->bb_overrides.sr_exit_time_ns / 1000.0; - } - } - - if (dc->bb_overrides.sr_enter_plus_exit_time_ns) { - for (i = 0; i < WM_SET_COUNT; i++) { - dc->clk_mgr->bw_params->wm_table.entries[i].sr_enter_plus_exit_time_us = - dc->bb_overrides.sr_enter_plus_exit_time_ns / 1000.0; - } - } - - if (dc->bb_overrides.urgent_latency_ns) { - bb->urgent_latency_us = dc->bb_overrides.urgent_latency_ns / 1000.0; - } - - if (dc->bb_overrides.dram_clock_change_latency_ns) { - for (i = 0; i < WM_SET_COUNT; i++) { - dc->clk_mgr->bw_params->wm_table.entries[i].pstate_latency_us = - dc->bb_overrides.dram_clock_change_latency_ns / 1000.0; - } - } -} - -static void dcn21_calculate_wm( - struct dc *dc, struct dc_state *context, - display_e2e_pipe_params_st *pipes, - int *out_pipe_cnt, - int *pipe_split_from, - int vlevel_req, - bool fast_validate) -{ - int pipe_cnt, i, pipe_idx; - int vlevel, vlevel_max; - struct wm_range_table_entry *table_entry; - struct clk_bw_params *bw_params = dc->clk_mgr->bw_params; - - ASSERT(bw_params); - - patch_bounding_box(dc, &context->bw_ctx.dml.soc); - - for (i = 0, pipe_idx = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { - if (!context->res_ctx.pipe_ctx[i].stream) - continue; - - pipes[pipe_cnt].clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0; - pipes[pipe_cnt].clks_cfg.dispclk_mhz = context->bw_ctx.dml.vba.RequiredDISPCLK[vlevel_req][context->bw_ctx.dml.vba.maxMpcComb]; - - if (pipe_split_from[i] < 0) { - pipes[pipe_cnt].clks_cfg.dppclk_mhz = - context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel_req][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx]; - if (context->bw_ctx.dml.vba.BlendingAndTiming[pipe_idx] == pipe_idx) - pipes[pipe_cnt].pipe.dest.odm_combine = - context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel_req][pipe_idx]; - else - pipes[pipe_cnt].pipe.dest.odm_combine = 0; - pipe_idx++; - } else { - pipes[pipe_cnt].clks_cfg.dppclk_mhz = - context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel_req][context->bw_ctx.dml.vba.maxMpcComb][pipe_split_from[i]]; - if (context->bw_ctx.dml.vba.BlendingAndTiming[pipe_split_from[i]] == pipe_split_from[i]) - pipes[pipe_cnt].pipe.dest.odm_combine = - context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel_req][pipe_split_from[i]]; - else - pipes[pipe_cnt].pipe.dest.odm_combine = 0; - } - pipe_cnt++; - } - - if (pipe_cnt != pipe_idx) { - if (dc->res_pool->funcs->populate_dml_pipes) - pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, - context, pipes, fast_validate); - else - pipe_cnt = dcn21_populate_dml_pipes_from_context(dc, - context, pipes, fast_validate); - } - - *out_pipe_cnt = pipe_cnt; - - vlevel_max = bw_params->clk_table.num_entries - 1; - - - /* WM Set D */ - table_entry = &bw_params->wm_table.entries[WM_D]; - if (table_entry->wm_type == WM_TYPE_RETRAINING) - vlevel = 0; - else - vlevel = vlevel_max; - calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.d, - &context->bw_ctx.dml, pipes, pipe_cnt); - /* WM Set C */ - table_entry = &bw_params->wm_table.entries[WM_C]; - vlevel = MIN(MAX(vlevel_req, 3), vlevel_max); - calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.c, - &context->bw_ctx.dml, pipes, pipe_cnt); - /* WM Set B */ - table_entry = &bw_params->wm_table.entries[WM_B]; - vlevel = MIN(MAX(vlevel_req, 2), vlevel_max); - calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.b, - &context->bw_ctx.dml, pipes, pipe_cnt); - - /* WM Set A */ - table_entry = &bw_params->wm_table.entries[WM_A]; - vlevel = MIN(vlevel_req, vlevel_max); - calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.a, - &context->bw_ctx.dml, pipes, pipe_cnt); -} - - -static bool dcn21_fast_validate_bw( - struct dc *dc, - struct dc_state *context, - display_e2e_pipe_params_st *pipes, - int *pipe_cnt_out, - int *pipe_split_from, - int *vlevel_out, - bool fast_validate) +bool dcn21_fast_validate_bw(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int *pipe_cnt_out, + int *pipe_split_from, + int *vlevel_out, + bool fast_validate) { bool out = false; int split[MAX_PIPES] = { 0 }; @@ -1197,7 +818,9 @@ static bool dcn21_fast_validate_bw( dcn20_merge_pipes_for_validate(dc, context); + DC_FP_START(); pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate); + DC_FP_END(); *pipe_cnt_out = pipe_cnt; @@ -1287,7 +910,9 @@ static bool dcn21_fast_validate_bw( hsplit_pipe = dcn20_find_secondary_pipe(dc, &context->res_ctx, dc->res_pool, pipe); ASSERT(hsplit_pipe); if (!hsplit_pipe) { - context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx] *= 2; + DC_FP_START(); + dcn20_fpu_adjust_dppclk(&context->bw_ctx.dml.vba, vlevel, context->bw_ctx.dml.vba.maxMpcComb, pipe_idx, true); + DC_FP_END(); continue; } if (context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx]) { @@ -1329,61 +954,6 @@ validate_out: return out; } -static noinline bool dcn21_validate_bandwidth_fp(struct dc *dc, - struct dc_state *context, bool fast_validate) -{ - bool out = false; - - BW_VAL_TRACE_SETUP(); - - int vlevel = 0; - int pipe_split_from[MAX_PIPES]; - int pipe_cnt = 0; - display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC); - DC_LOGGER_INIT(dc->ctx->logger); - - BW_VAL_TRACE_COUNT(); - - /*Unsafe due to current pipe merge and split logic*/ - ASSERT(context != dc->current_state); - - out = dcn21_fast_validate_bw(dc, context, pipes, &pipe_cnt, pipe_split_from, &vlevel, fast_validate); - - if (pipe_cnt == 0) - goto validate_out; - - if (!out) - goto validate_fail; - - BW_VAL_TRACE_END_VOLTAGE_LEVEL(); - - if (fast_validate) { - BW_VAL_TRACE_SKIP(fast); - goto validate_out; - } - - dcn21_calculate_wm(dc, context, pipes, &pipe_cnt, pipe_split_from, vlevel, fast_validate); - dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); - - BW_VAL_TRACE_END_WATERMARKS(); - - goto validate_out; - -validate_fail: - DC_LOG_WARNING("Mode Validation Warning: %s failed validation.\n", - dml_get_status_message(context->bw_ctx.dml.vba.ValidationStatus[context->bw_ctx.dml.vba.soc.num_states])); - - BW_VAL_TRACE_SKIP(fail); - out = false; - -validate_out: - kfree(pipes); - - BW_VAL_TRACE_FINISH(); - - return out; -} - /* * Some of the functions further below use the FPU, so we need to wrap this * with DC_FP_START()/DC_FP_END(). Use the same approach as for @@ -1558,94 +1128,6 @@ static struct display_stream_compressor *dcn21_dsc_create(struct dc_context *ctx return &dsc->base; } -static struct _vcs_dpi_voltage_scaling_st construct_low_pstate_lvl(struct clk_limit_table *clk_table, unsigned int high_voltage_lvl) -{ - struct _vcs_dpi_voltage_scaling_st low_pstate_lvl; - int i; - - low_pstate_lvl.state = 1; - low_pstate_lvl.dcfclk_mhz = clk_table->entries[0].dcfclk_mhz; - low_pstate_lvl.fabricclk_mhz = clk_table->entries[0].fclk_mhz; - low_pstate_lvl.socclk_mhz = clk_table->entries[0].socclk_mhz; - low_pstate_lvl.dram_speed_mts = clk_table->entries[0].memclk_mhz * 2; - - low_pstate_lvl.dispclk_mhz = dcn2_1_soc.clock_limits[high_voltage_lvl].dispclk_mhz; - low_pstate_lvl.dppclk_mhz = dcn2_1_soc.clock_limits[high_voltage_lvl].dppclk_mhz; - low_pstate_lvl.dram_bw_per_chan_gbps = dcn2_1_soc.clock_limits[high_voltage_lvl].dram_bw_per_chan_gbps; - low_pstate_lvl.dscclk_mhz = dcn2_1_soc.clock_limits[high_voltage_lvl].dscclk_mhz; - low_pstate_lvl.dtbclk_mhz = dcn2_1_soc.clock_limits[high_voltage_lvl].dtbclk_mhz; - low_pstate_lvl.phyclk_d18_mhz = dcn2_1_soc.clock_limits[high_voltage_lvl].phyclk_d18_mhz; - low_pstate_lvl.phyclk_mhz = dcn2_1_soc.clock_limits[high_voltage_lvl].phyclk_mhz; - - for (i = clk_table->num_entries; i > 1; i--) - clk_table->entries[i] = clk_table->entries[i-1]; - clk_table->entries[1] = clk_table->entries[0]; - clk_table->num_entries++; - - return low_pstate_lvl; -} - -static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) -{ - struct dcn21_resource_pool *pool = TO_DCN21_RES_POOL(dc->res_pool); - struct clk_limit_table *clk_table = &bw_params->clk_table; - struct _vcs_dpi_voltage_scaling_st clock_limits[DC__VOLTAGE_STATES]; - unsigned int i, closest_clk_lvl = 0, k = 0; - int j; - - dcn2_1_ip.max_num_otg = pool->base.res_cap->num_timing_generator; - dcn2_1_ip.max_num_dpp = pool->base.pipe_count; - dcn2_1_soc.num_chans = bw_params->num_channels; - - ASSERT(clk_table->num_entries); - /* Copy dcn2_1_soc.clock_limits to clock_limits to avoid copying over null states later */ - for (i = 0; i < dcn2_1_soc.num_states + 1; i++) { - clock_limits[i] = dcn2_1_soc.clock_limits[i]; - } - - for (i = 0; i < clk_table->num_entries; i++) { - /* loop backwards*/ - for (closest_clk_lvl = 0, j = dcn2_1_soc.num_states - 1; j >= 0; j--) { - if ((unsigned int) dcn2_1_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) { - closest_clk_lvl = j; - break; - } - } - - /* clk_table[1] is reserved for min DF PState. skip here to fill in later. */ - if (i == 1) - k++; - - clock_limits[k].state = k; - clock_limits[k].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz; - clock_limits[k].fabricclk_mhz = clk_table->entries[i].fclk_mhz; - clock_limits[k].socclk_mhz = clk_table->entries[i].socclk_mhz; - clock_limits[k].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2; - - clock_limits[k].dispclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dispclk_mhz; - clock_limits[k].dppclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dppclk_mhz; - clock_limits[k].dram_bw_per_chan_gbps = dcn2_1_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps; - clock_limits[k].dscclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dscclk_mhz; - clock_limits[k].dtbclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dtbclk_mhz; - clock_limits[k].phyclk_d18_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz; - clock_limits[k].phyclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_mhz; - - k++; - } - for (i = 0; i < clk_table->num_entries + 1; i++) - dcn2_1_soc.clock_limits[i] = clock_limits[i]; - if (clk_table->num_entries) { - dcn2_1_soc.num_states = clk_table->num_entries + 1; - /* fill in min DF PState */ - dcn2_1_soc.clock_limits[1] = construct_low_pstate_lvl(clk_table, closest_clk_lvl); - /* duplicate last level */ - dcn2_1_soc.clock_limits[dcn2_1_soc.num_states] = dcn2_1_soc.clock_limits[dcn2_1_soc.num_states - 1]; - dcn2_1_soc.clock_limits[dcn2_1_soc.num_states].state = dcn2_1_soc.num_states; - } - - dml_init_instance(&dc->dml, &dcn2_1_soc, &dcn2_1_ip, DML_PROJECT_DCN21); -} - static struct pp_smu_funcs *dcn21_pp_smu_create(struct dc_context *ctx) { struct pp_smu_funcs *pp_smu = kzalloc(sizeof(*pp_smu), GFP_KERNEL); @@ -1896,24 +1378,6 @@ static uint32_t read_pipe_fuses(struct dc_context *ctx) return value; } -static int dcn21_populate_dml_pipes_from_context( - struct dc *dc, - struct dc_state *context, - display_e2e_pipe_params_st *pipes, - bool fast_validate) -{ - uint32_t pipe_cnt = dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); - int i; - - for (i = 0; i < pipe_cnt; i++) { - - pipes[i].pipe.src.hostvm = dc->res_pool->hubbub->riommu_active; - pipes[i].pipe.src.gpuvm = 1; - } - - return pipe_cnt; -} - static enum dc_status dcn21_patch_unknown_plane_state(struct dc_plane_state *plane_state) { enum dc_status result = DC_OK; @@ -1941,7 +1405,7 @@ static const struct resource_funcs dcn21_res_pool_funcs = { .patch_unknown_plane_state = dcn21_patch_unknown_plane_state, .set_mcif_arb_params = dcn20_set_mcif_arb_params, .find_first_free_match_stream_enc_for_link = dcn10_find_first_free_match_stream_enc_for_link, - .update_bw_bounding_box = update_bw_bounding_box + .update_bw_bounding_box = dcn21_update_bw_bounding_box, }; static bool dcn21_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.h index a27355171bca..f7ecc002c2f7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.h @@ -35,11 +35,22 @@ struct dc; struct resource_pool; struct _vcs_dpi_display_pipe_params_st; +extern struct _vcs_dpi_ip_params_st dcn2_1_ip; +extern struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc; + struct dcn21_resource_pool { struct resource_pool base; }; struct resource_pool *dcn21_create_resource_pool( const struct dc_init_data *init_data, struct dc *dc); +bool dcn21_fast_validate_bw( + struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int *pipe_cnt_out, + int *pipe_split_from, + int *vlevel_out, + bool fast_validate); #endif /* _DCN21_RESOURCE_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c index 387eec616162..87dbeca18984 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c @@ -408,6 +408,6 @@ void dpp3_cm_set_gamut_remap( gamut_mode = 1; //follow dcn2 approach for now - using only coefficient set A - program_gamut_remap(dpp, arr_reg_val, GAMUT_REMAP_COEFF); + program_gamut_remap(dpp, arr_reg_val, gamut_mode); } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubbub.c index f4414de96acc..152c9c5733f1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubbub.c @@ -448,6 +448,7 @@ static const struct hubbub_funcs hubbub30_funcs = { .program_watermarks = hubbub3_program_watermarks, .allow_self_refresh_control = hubbub1_allow_self_refresh_control, .is_allow_self_refresh_enabled = hubbub1_is_allow_self_refresh_enabled, + .verify_allow_pstate_change_high = hubbub1_verify_allow_pstate_change_high, .force_wm_propagate_to_pipes = hubbub3_force_wm_propagate_to_pipes, .force_pstate_change_control = hubbub3_force_pstate_change_control, .init_watermarks = hubbub3_init_watermarks, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index f10f7a0ca02a..e6a62cc75139 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -1462,7 +1462,9 @@ int dcn30_populate_dml_pipes_from_context( int i, pipe_cnt; struct resource_context *res_ctx = &context->res_ctx; + DC_FP_START(); dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); + DC_FP_END(); for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { if (!res_ctx->pipe_ctx[i].stream) @@ -1731,7 +1733,10 @@ static bool init_soc_bounding_box(struct dc *dc, loaded_ip->max_num_otg = pool->base.res_cap->num_timing_generator; loaded_ip->max_num_dpp = pool->base.pipe_count; loaded_ip->clamp_min_dcfclk = dc->config.clamp_min_dcfclk; + + DC_FP_START(); dcn20_patch_bounding_box(dc, loaded_bb); + DC_FP_END(); if (dc->ctx->dc_bios->funcs->get_soc_bb_info) { struct bp_soc_bb_info bb_info = {0}; @@ -2261,7 +2266,9 @@ static noinline void dcn30_calculate_wm_and_dlg_fp( pipe_idx++; } + DC_FP_START(); dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); + DC_FP_END(); if (!pstate_en) /* Restore full p-state latency */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_hubbub.c index 1e3bd2e9cdcc..a046664e2031 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_hubbub.c @@ -60,6 +60,7 @@ static const struct hubbub_funcs hubbub301_funcs = { .program_watermarks = hubbub3_program_watermarks, .allow_self_refresh_control = hubbub1_allow_self_refresh_control, .is_allow_self_refresh_enabled = hubbub1_is_allow_self_refresh_enabled, + .verify_allow_pstate_change_high = hubbub1_verify_allow_pstate_change_high, .force_wm_propagate_to_pipes = hubbub3_force_wm_propagate_to_pipes, .force_pstate_change_control = hubbub3_force_pstate_change_control, .hubbub_read_state = hubbub2_read_state, diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/Makefile b/drivers/gpu/drm/amd/display/dc/dcn303/Makefile index 6f7a1f2b49f0..8702e0b7fda3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn303/Makefile @@ -8,32 +8,6 @@ DCN3_03 = dcn303_init.o dcn303_hwseq.o dcn303_resource.o -ifdef CONFIG_X86 -CFLAGS_$(AMDDALPATH)/dc/dcn303/dcn303_resource.o := -msse -endif - -ifdef CONFIG_PPC64 -CFLAGS_$(AMDDALPATH)/dc/dcn303/dcn303_resource.o := -mhard-float -maltivec -endif - -ifdef CONFIG_CC_IS_GCC -ifeq ($(call cc-ifversion, -lt, 0701, y), y) -IS_OLD_GCC = 1 -endif -CFLAGS_$(AMDDALPATH)/dc/dcn303/dcn303_resource.o += -mhard-float -endif - -ifdef CONFIG_X86 -ifdef IS_OLD_GCC -# Stack alignment mismatch, proceed with caution. -# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 -# (8B stack alignment). -CFLAGS_$(AMDDALPATH)/dc/dcn303/dcn303_resource.o += -mpreferred-stack-boundary=4 -else -CFLAGS_$(AMDDALPATH)/dc/dcn303/dcn303_resource.o += -msse2 -endif -endif - AMD_DAL_DCN3_03 = $(addprefix $(AMDDALPATH)/dc/dcn303/,$(DCN3_03)) AMD_DISPLAY_FILES += $(AMD_DAL_DCN3_03) diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c index 36649716e991..4fcbc0502808 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c @@ -52,140 +52,10 @@ #include "dpcs/dpcs_3_0_3_sh_mask.h" #include "nbio/nbio_2_3_offset.h" -#define DC_LOGGER_INIT(logger) +#include "dml/dcn303/dcn303_fpu.h" -struct _vcs_dpi_ip_params_st dcn3_03_ip = { - .use_min_dcfclk = 0, - .clamp_min_dcfclk = 0, - .odm_capable = 1, - .gpuvm_enable = 1, - .hostvm_enable = 0, - .gpuvm_max_page_table_levels = 4, - .hostvm_max_page_table_levels = 4, - .hostvm_cached_page_table_levels = 0, - .pte_group_size_bytes = 2048, - .num_dsc = 2, - .rob_buffer_size_kbytes = 184, - .det_buffer_size_kbytes = 184, - .dpte_buffer_size_in_pte_reqs_luma = 64, - .dpte_buffer_size_in_pte_reqs_chroma = 34, - .pde_proc_buffer_size_64k_reqs = 48, - .dpp_output_buffer_pixels = 2560, - .opp_output_buffer_lines = 1, - .pixel_chunk_size_kbytes = 8, - .pte_enable = 1, - .max_page_table_levels = 2, - .pte_chunk_size_kbytes = 2, // ? - .meta_chunk_size_kbytes = 2, - .writeback_chunk_size_kbytes = 8, - .line_buffer_size_bits = 789504, - .is_line_buffer_bpp_fixed = 0, // ? - .line_buffer_fixed_bpp = 0, // ? - .dcc_supported = true, - .writeback_interface_buffer_size_kbytes = 90, - .writeback_line_buffer_buffer_size = 0, - .max_line_buffer_lines = 12, - .writeback_luma_buffer_size_kbytes = 12, // writeback_line_buffer_buffer_size = 656640 - .writeback_chroma_buffer_size_kbytes = 8, - .writeback_chroma_line_buffer_width_pixels = 4, - .writeback_max_hscl_ratio = 1, - .writeback_max_vscl_ratio = 1, - .writeback_min_hscl_ratio = 1, - .writeback_min_vscl_ratio = 1, - .writeback_max_hscl_taps = 1, - .writeback_max_vscl_taps = 1, - .writeback_line_buffer_luma_buffer_size = 0, - .writeback_line_buffer_chroma_buffer_size = 14643, - .cursor_buffer_size = 8, - .cursor_chunk_size = 2, - .max_num_otg = 2, - .max_num_dpp = 2, - .max_num_wb = 1, - .max_dchub_pscl_bw_pix_per_clk = 4, - .max_pscl_lb_bw_pix_per_clk = 2, - .max_lb_vscl_bw_pix_per_clk = 4, - .max_vscl_hscl_bw_pix_per_clk = 4, - .max_hscl_ratio = 6, - .max_vscl_ratio = 6, - .hscl_mults = 4, - .vscl_mults = 4, - .max_hscl_taps = 8, - .max_vscl_taps = 8, - .dispclk_ramp_margin_percent = 1, - .underscan_factor = 1.11, - .min_vblank_lines = 32, - .dppclk_delay_subtotal = 46, - .dynamic_metadata_vm_enabled = true, - .dppclk_delay_scl_lb_only = 16, - .dppclk_delay_scl = 50, - .dppclk_delay_cnvc_formatter = 27, - .dppclk_delay_cnvc_cursor = 6, - .dispclk_delay_subtotal = 119, - .dcfclk_cstate_latency = 5.2, // SRExitTime - .max_inter_dcn_tile_repeaters = 8, - .max_num_hdmi_frl_outputs = 1, - .odm_combine_4to1_supported = false, - .xfc_supported = false, - .xfc_fill_bw_overhead_percent = 10.0, - .xfc_fill_constant_bytes = 0, - .gfx7_compat_tiling_supported = 0, - .number_of_cursors = 1, -}; - -struct _vcs_dpi_soc_bounding_box_st dcn3_03_soc = { - .clock_limits = { - { - .state = 0, - .dispclk_mhz = 1217.0, - .dppclk_mhz = 1217.0, - .phyclk_mhz = 810.0, - .phyclk_d18_mhz = 667.0, - .dscclk_mhz = 405.6, - }, - }, +#define DC_LOGGER_INIT(logger) - .min_dcfclk = 500.0, /* TODO: set this to actual min DCFCLK */ - .num_states = 1, - .sr_exit_time_us = 35.5, - .sr_enter_plus_exit_time_us = 40, - .urgent_latency_us = 4.0, - .urgent_latency_pixel_data_only_us = 4.0, - .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, - .urgent_latency_vm_data_only_us = 4.0, - .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, - .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, - .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, - .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 80.0, - .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 60.0, - .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, - .max_avg_sdp_bw_use_normal_percent = 60.0, - .max_avg_dram_bw_use_normal_percent = 40.0, - .writeback_latency_us = 12.0, - .max_request_size_bytes = 256, - .fabric_datapath_to_dcn_data_return_bytes = 64, - .dcn_downspread_percent = 0.5, - .downspread_percent = 0.38, - .dram_page_open_time_ns = 50.0, - .dram_rw_turnaround_time_ns = 17.5, - .dram_return_buffer_per_channel_bytes = 8192, - .round_trip_ping_latency_dcfclk_cycles = 156, - .urgent_out_of_order_return_per_channel_bytes = 4096, - .channel_interleave_bytes = 256, - .num_banks = 8, - .gpuvm_min_page_size_bytes = 4096, - .hostvm_min_page_size_bytes = 4096, - .dram_clock_change_latency_us = 404, - .dummy_pstate_latency_us = 5, - .writeback_dram_clock_change_latency_us = 23.0, - .return_bus_width_bytes = 64, - .dispclk_dppclk_vco_speed_mhz = 3650, - .xfc_bus_transport_time_us = 20, // ? - .xfc_xbuf_latency_tolerance_us = 4, // ? - .use_urgent_burst_bw = 1, // ? - .do_urgent_latency_adjustment = true, - .urgent_latency_adjustment_fabric_clock_component_us = 1.0, - .urgent_latency_adjustment_fabric_clock_reference_mhz = 1000, -}; static const struct dc_debug_options debug_defaults_drv = { .disable_dmcu = true, @@ -1031,24 +901,18 @@ static bool init_soc_bounding_box(struct dc *dc, struct resource_pool *pool) loaded_ip->max_num_otg = pool->pipe_count; loaded_ip->max_num_dpp = pool->pipe_count; loaded_ip->clamp_min_dcfclk = dc->config.clamp_min_dcfclk; + DC_FP_START(); dcn20_patch_bounding_box(dc, loaded_bb); + DC_FP_END(); if (dc->ctx->dc_bios->funcs->get_soc_bb_info) { struct bp_soc_bb_info bb_info = { 0 }; if (dc->ctx->dc_bios->funcs->get_soc_bb_info( dc->ctx->dc_bios, &bb_info) == BP_RESULT_OK) { - if (bb_info.dram_clock_change_latency_100ns > 0) - dcn3_03_soc.dram_clock_change_latency_us = - bb_info.dram_clock_change_latency_100ns * 10; - - if (bb_info.dram_sr_enter_exit_latency_100ns > 0) - dcn3_03_soc.sr_enter_plus_exit_time_us = - bb_info.dram_sr_enter_exit_latency_100ns * 10; - - if (bb_info.dram_sr_exit_latency_100ns > 0) - dcn3_03_soc.sr_exit_time_us = - bb_info.dram_sr_exit_latency_100ns * 10; + DC_FP_START(); + dcn303_fpu_init_soc_bounding_box(bb_info); + DC_FP_END(); } } @@ -1186,183 +1050,12 @@ static void dcn303_destroy_resource_pool(struct resource_pool **pool) *pool = NULL; } -static void dcn303_get_optimal_dcfclk_fclk_for_uclk(unsigned int uclk_mts, - unsigned int *optimal_dcfclk, - unsigned int *optimal_fclk) -{ - double bw_from_dram, bw_from_dram1, bw_from_dram2; - - bw_from_dram1 = uclk_mts * dcn3_03_soc.num_chans * - dcn3_03_soc.dram_channel_width_bytes * (dcn3_03_soc.max_avg_dram_bw_use_normal_percent / 100); - bw_from_dram2 = uclk_mts * dcn3_03_soc.num_chans * - dcn3_03_soc.dram_channel_width_bytes * (dcn3_03_soc.max_avg_sdp_bw_use_normal_percent / 100); - - bw_from_dram = (bw_from_dram1 < bw_from_dram2) ? bw_from_dram1 : bw_from_dram2; - - if (optimal_fclk) - *optimal_fclk = bw_from_dram / - (dcn3_03_soc.fabric_datapath_to_dcn_data_return_bytes * - (dcn3_03_soc.max_avg_sdp_bw_use_normal_percent / 100)); - - if (optimal_dcfclk) - *optimal_dcfclk = bw_from_dram / - (dcn3_03_soc.return_bus_width_bytes * (dcn3_03_soc.max_avg_sdp_bw_use_normal_percent / 100)); -} void dcn303_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) { - unsigned int i, j; - unsigned int num_states = 0; - - unsigned int dcfclk_mhz[DC__VOLTAGE_STATES] = {0}; - unsigned int dram_speed_mts[DC__VOLTAGE_STATES] = {0}; - unsigned int optimal_uclk_for_dcfclk_sta_targets[DC__VOLTAGE_STATES] = {0}; - unsigned int optimal_dcfclk_for_uclk[DC__VOLTAGE_STATES] = {0}; - - unsigned int dcfclk_sta_targets[DC__VOLTAGE_STATES] = {694, 875, 1000, 1200}; - unsigned int num_dcfclk_sta_targets = 4; - unsigned int num_uclk_states; - - - if (dc->ctx->dc_bios->vram_info.num_chans) - dcn3_03_soc.num_chans = dc->ctx->dc_bios->vram_info.num_chans; - - if (dc->ctx->dc_bios->vram_info.dram_channel_width_bytes) - dcn3_03_soc.dram_channel_width_bytes = dc->ctx->dc_bios->vram_info.dram_channel_width_bytes; - - dcn3_03_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; - dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; - - if (bw_params->clk_table.entries[0].memclk_mhz) { - int max_dcfclk_mhz = 0, max_dispclk_mhz = 0, max_dppclk_mhz = 0, max_phyclk_mhz = 0; - - for (i = 0; i < MAX_NUM_DPM_LVL; i++) { - if (bw_params->clk_table.entries[i].dcfclk_mhz > max_dcfclk_mhz) - max_dcfclk_mhz = bw_params->clk_table.entries[i].dcfclk_mhz; - if (bw_params->clk_table.entries[i].dispclk_mhz > max_dispclk_mhz) - max_dispclk_mhz = bw_params->clk_table.entries[i].dispclk_mhz; - if (bw_params->clk_table.entries[i].dppclk_mhz > max_dppclk_mhz) - max_dppclk_mhz = bw_params->clk_table.entries[i].dppclk_mhz; - if (bw_params->clk_table.entries[i].phyclk_mhz > max_phyclk_mhz) - max_phyclk_mhz = bw_params->clk_table.entries[i].phyclk_mhz; - } - if (!max_dcfclk_mhz) - max_dcfclk_mhz = dcn3_03_soc.clock_limits[0].dcfclk_mhz; - if (!max_dispclk_mhz) - max_dispclk_mhz = dcn3_03_soc.clock_limits[0].dispclk_mhz; - if (!max_dppclk_mhz) - max_dppclk_mhz = dcn3_03_soc.clock_limits[0].dppclk_mhz; - if (!max_phyclk_mhz) - max_phyclk_mhz = dcn3_03_soc.clock_limits[0].phyclk_mhz; - - if (max_dcfclk_mhz > dcfclk_sta_targets[num_dcfclk_sta_targets-1]) { - dcfclk_sta_targets[num_dcfclk_sta_targets] = max_dcfclk_mhz; - num_dcfclk_sta_targets++; - } else if (max_dcfclk_mhz < dcfclk_sta_targets[num_dcfclk_sta_targets-1]) { - for (i = 0; i < num_dcfclk_sta_targets; i++) { - if (dcfclk_sta_targets[i] > max_dcfclk_mhz) { - dcfclk_sta_targets[i] = max_dcfclk_mhz; - break; - } - } - /* Update size of array since we "removed" duplicates */ - num_dcfclk_sta_targets = i + 1; - } - - num_uclk_states = bw_params->clk_table.num_entries; - - /* Calculate optimal dcfclk for each uclk */ - for (i = 0; i < num_uclk_states; i++) { - dcn303_get_optimal_dcfclk_fclk_for_uclk(bw_params->clk_table.entries[i].memclk_mhz * 16, - &optimal_dcfclk_for_uclk[i], NULL); - if (optimal_dcfclk_for_uclk[i] < bw_params->clk_table.entries[0].dcfclk_mhz) - optimal_dcfclk_for_uclk[i] = bw_params->clk_table.entries[0].dcfclk_mhz; - } - - /* Calculate optimal uclk for each dcfclk sta target */ - for (i = 0; i < num_dcfclk_sta_targets; i++) { - for (j = 0; j < num_uclk_states; j++) { - if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j]) { - optimal_uclk_for_dcfclk_sta_targets[i] = - bw_params->clk_table.entries[j].memclk_mhz * 16; - break; - } - } - } - - i = 0; - j = 0; - /* create the final dcfclk and uclk table */ - while (i < num_dcfclk_sta_targets && j < num_uclk_states && num_states < DC__VOLTAGE_STATES) { - if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j] && i < num_dcfclk_sta_targets) { - dcfclk_mhz[num_states] = dcfclk_sta_targets[i]; - dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++]; - } else { - if (j < num_uclk_states && optimal_dcfclk_for_uclk[j] <= max_dcfclk_mhz) { - dcfclk_mhz[num_states] = optimal_dcfclk_for_uclk[j]; - dram_speed_mts[num_states++] = - bw_params->clk_table.entries[j++].memclk_mhz * 16; - } else { - j = num_uclk_states; - } - } - } - - while (i < num_dcfclk_sta_targets && num_states < DC__VOLTAGE_STATES) { - dcfclk_mhz[num_states] = dcfclk_sta_targets[i]; - dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++]; - } - - while (j < num_uclk_states && num_states < DC__VOLTAGE_STATES && - optimal_dcfclk_for_uclk[j] <= max_dcfclk_mhz) { - dcfclk_mhz[num_states] = optimal_dcfclk_for_uclk[j]; - dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16; - } - - dcn3_03_soc.num_states = num_states; - for (i = 0; i < dcn3_03_soc.num_states; i++) { - dcn3_03_soc.clock_limits[i].state = i; - dcn3_03_soc.clock_limits[i].dcfclk_mhz = dcfclk_mhz[i]; - dcn3_03_soc.clock_limits[i].fabricclk_mhz = dcfclk_mhz[i]; - dcn3_03_soc.clock_limits[i].dram_speed_mts = dram_speed_mts[i]; - - /* Fill all states with max values of all other clocks */ - dcn3_03_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz; - dcn3_03_soc.clock_limits[i].dppclk_mhz = max_dppclk_mhz; - dcn3_03_soc.clock_limits[i].phyclk_mhz = max_phyclk_mhz; - /* Populate from bw_params for DTBCLK, SOCCLK */ - if (!bw_params->clk_table.entries[i].dtbclk_mhz && i > 0) - dcn3_03_soc.clock_limits[i].dtbclk_mhz = dcn3_03_soc.clock_limits[i-1].dtbclk_mhz; - else - dcn3_03_soc.clock_limits[i].dtbclk_mhz = bw_params->clk_table.entries[i].dtbclk_mhz; - if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0) - dcn3_03_soc.clock_limits[i].socclk_mhz = dcn3_03_soc.clock_limits[i-1].socclk_mhz; - else - dcn3_03_soc.clock_limits[i].socclk_mhz = bw_params->clk_table.entries[i].socclk_mhz; - /* These clocks cannot come from bw_params, always fill from dcn3_03_soc[1] */ - /* FCLK, PHYCLK_D18, DSCCLK */ - dcn3_03_soc.clock_limits[i].phyclk_d18_mhz = dcn3_03_soc.clock_limits[0].phyclk_d18_mhz; - dcn3_03_soc.clock_limits[i].dscclk_mhz = dcn3_03_soc.clock_limits[0].dscclk_mhz; - } - - // WA: patch strobe modes to compensate for DCN303 BW issue - if (dcn3_03_soc.num_chans <= 4) { - for (i = 0; i < dcn3_03_soc.num_states; i++) { - if (dcn3_03_soc.clock_limits[i].dram_speed_mts > 1700) - break; - - if (dcn3_03_soc.clock_limits[i].dram_speed_mts >= 1500) { - dcn3_03_soc.clock_limits[i].dcfclk_mhz = 100; - dcn3_03_soc.clock_limits[i].fabricclk_mhz = 100; - } - } - } - - /* re-init DML with updated bb */ - dml_init_instance(&dc->dml, &dcn3_03_soc, &dcn3_03_ip, DML_PROJECT_DCN30); - if (dc->current_state) - dml_init_instance(&dc->current_state->bw_ctx.dml, &dcn3_03_soc, &dcn3_03_ip, DML_PROJECT_DCN30); - } + DC_FP_START(); + dcn303_fpu_update_bw_bounding_box(dc, bw_params); + DC_FP_END(); } static struct resource_funcs dcn303_res_pool_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.h b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.h index 5b590c169763..9c7d79540900 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.h @@ -10,6 +10,9 @@ #include "core_types.h" +extern struct _vcs_dpi_ip_params_st dcn3_03_ip; +extern struct _vcs_dpi_soc_bounding_box_st dcn3_03_soc; + struct resource_pool *dcn303_create_resource_pool(const struct dc_init_data *init_data, struct dc *dc); void dcn303_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params); diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c index 8b9b1a5309ba..d94fd1010deb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c @@ -240,18 +240,9 @@ static void enc31_hw_init(struct link_encoder *enc) // 100MHz -> 0x32 // 48MHz -> 0x18 -#ifdef CLEANUP_FIXME - /*from display_init*/ - REG_WRITE(RDPCSTX_DEBUG_CONFIG, 0); -#endif - // Set TMDS_CTL0 to 1. This is a legacy setting. REG_UPDATE(TMDS_CTL_BITS, TMDS_CTL0, 1); - /*HW default is 5*/ - REG_UPDATE(RDPCSTX_CNTL, - RDPCS_TX_FIFO_RD_START_DELAY, 4); - dcn10_aux_initialize(enc10); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c index 5e3bcaf12cac..3e6d6ebd199e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c @@ -949,6 +949,65 @@ static void hubbub31_get_dchub_ref_freq(struct hubbub *hubbub, } } +static bool hubbub31_verify_allow_pstate_change_high(struct hubbub *hubbub) +{ + struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub); + + /* + * Pstate latency is ~20us so if we wait over 40us and pstate allow + * still not asserted, we are probably stuck and going to hang + */ + const unsigned int pstate_wait_timeout_us = 100; + const unsigned int pstate_wait_expected_timeout_us = 40; + + static unsigned int max_sampled_pstate_wait_us; /* data collection */ + static bool forced_pstate_allow; /* help with revert wa */ + + unsigned int debug_data = 0; + unsigned int i; + + if (forced_pstate_allow) { + /* we hacked to force pstate allow to prevent hang last time + * we verify_allow_pstate_change_high. so disable force + * here so we can check status + */ + REG_UPDATE_2(DCHUBBUB_ARB_DRAM_STATE_CNTL, + DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_VALUE, 0, + DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_ENABLE, 0); + forced_pstate_allow = false; + } + + REG_WRITE(DCHUBBUB_TEST_DEBUG_INDEX, hubbub2->debug_test_index_pstate); + + for (i = 0; i < pstate_wait_timeout_us; i++) { + debug_data = REG_READ(DCHUBBUB_TEST_DEBUG_DATA); + + /* Debug bit is specific to ASIC. */ + if (debug_data & (1 << 26)) { + if (i > pstate_wait_expected_timeout_us) + DC_LOG_WARNING("pstate took longer than expected ~%dus\n", i); + return true; + } + if (max_sampled_pstate_wait_us < i) + max_sampled_pstate_wait_us = i; + + udelay(1); + } + + /* force pstate allow to prevent system hang + * and break to debugger to investigate + */ + REG_UPDATE_2(DCHUBBUB_ARB_DRAM_STATE_CNTL, + DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_VALUE, 1, + DCHUBBUB_ARB_ALLOW_PSTATE_CHANGE_FORCE_ENABLE, 1); + forced_pstate_allow = true; + + DC_LOG_WARNING("pstate TEST_DEBUG_DATA: 0x%X\n", + debug_data); + + return false; +} + static const struct hubbub_funcs hubbub31_funcs = { .update_dchub = hubbub2_update_dchub, .init_dchub_sys_ctx = hubbub31_init_dchub_sys_ctx, @@ -961,6 +1020,7 @@ static const struct hubbub_funcs hubbub31_funcs = { .program_watermarks = hubbub31_program_watermarks, .allow_self_refresh_control = hubbub1_allow_self_refresh_control, .is_allow_self_refresh_enabled = hubbub1_is_allow_self_refresh_enabled, + .verify_allow_pstate_change_high = hubbub31_verify_allow_pstate_change_high, .program_det_size = dcn31_program_det_size, .program_compbuf_size = dcn31_program_compbuf_size, .init_crb = dcn31_init_crb, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c index 83ece02380a8..11ea9d13e312 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c @@ -83,7 +83,8 @@ static uint32_t dcn31_panel_cntl_hw_init(struct panel_cntl *panel_cntl) cmd.panel_cntl.data.bl_pwm_period_cntl = panel_cntl->stored_backlight_registers.BL_PWM_PERIOD_CNTL; cmd.panel_cntl.data.bl_pwm_ref_div1 = panel_cntl->stored_backlight_registers.LVTMA_PWRSEQ_REF_DIV_BL_PWM_REF_DIV; - + cmd.panel_cntl.data.bl_pwm_ref_div2 = + panel_cntl->stored_backlight_registers.PANEL_PWRSEQ_REF_DIV2; if (!dc_dmub_srv_cmd_with_reply_data(dc_dmub_srv, &cmd)) return 0; @@ -92,6 +93,8 @@ static uint32_t dcn31_panel_cntl_hw_init(struct panel_cntl *panel_cntl) panel_cntl->stored_backlight_registers.BL_PWM_PERIOD_CNTL = cmd.panel_cntl.data.bl_pwm_period_cntl; panel_cntl->stored_backlight_registers.LVTMA_PWRSEQ_REF_DIV_BL_PWM_REF_DIV = cmd.panel_cntl.data.bl_pwm_ref_div1; + panel_cntl->stored_backlight_registers.PANEL_PWRSEQ_REF_DIV2 = + cmd.panel_cntl.data.bl_pwm_ref_div2; return cmd.panel_cntl.data.current_backlight; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 660e96a7fe7f..89b7b6b7254a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -1011,7 +1011,7 @@ static const struct dc_debug_options debug_defaults_drv = { .max_downscale_src_width = 4096,/*upto true 4K*/ .disable_pplib_wm_range = false, .scl_reset_length10 = true, - .sanity_checks = false, + .sanity_checks = true, .underflow_assert_delay_us = 0xFFFFFFFF, .dwb_fi_phase = -1, // -1 = disable, .dmub_command_table = true, @@ -1777,7 +1777,7 @@ static bool is_dual_plane(enum surface_pixel_format format) return format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN || format == SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA; } -static int dcn31_populate_dml_pipes_from_context( +int dcn31_populate_dml_pipes_from_context( struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, bool fast_validate) @@ -1787,7 +1787,9 @@ static int dcn31_populate_dml_pipes_from_context( struct pipe_ctx *pipe; bool upscaled = false; + DC_FP_START(); dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); + DC_FP_END(); for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { struct dc_crtc_timing *timing; @@ -1810,6 +1812,7 @@ static int dcn31_populate_dml_pipes_from_context( pipes[pipe_cnt].pipe.src.immediate_flip = true; pipes[pipe_cnt].pipe.src.unbounded_req_mode = false; + pipes[pipe_cnt].pipe.src.hostvm = dc->res_pool->hubbub->riommu_active; pipes[pipe_cnt].pipe.src.gpuvm = true; pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_luma = 0; pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_chroma = 0; @@ -1998,7 +2001,9 @@ static void dcn31_calculate_wm_and_dlg_fp( pipe_idx++; } + DC_FP_START(); dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); + DC_FP_END(); } void dcn31_calculate_wm_and_dlg( @@ -2068,7 +2073,7 @@ static struct dc_cap_funcs cap_funcs = { .get_dcc_compression_cap = dcn20_get_dcc_compression_cap }; -static void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) +void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) { struct clk_limit_table *clk_table = &bw_params->clk_table; struct _vcs_dpi_voltage_scaling_st clock_limits[DC__VOLTAGE_STATES]; @@ -2176,7 +2181,7 @@ static struct clock_source *dcn30_clock_source_create( if (!clk_src) return NULL; - if (dcn3_clk_src_construct(clk_src, ctx, bios, id, + if (dcn31_clk_src_construct(clk_src, ctx, bios, id, regs, &cs_shift, &cs_mask)) { clk_src->base.dp_clk_src = dp_clk_src; return &clk_src->base; diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h index a513363b3326..4b7ab21ea15b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h @@ -43,6 +43,11 @@ void dcn31_calculate_wm_and_dlg( display_e2e_pipe_params_st *pipes, int pipe_cnt, int vlevel); +int dcn31_populate_dml_pipes_from_context( + struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes, + bool fast_validate); +void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params); void dcn31_update_soc_for_wm_a(struct dc *dc, struct dc_state *context); struct resource_pool *dcn31_create_resource_pool( diff --git a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c index a71073482881..06adb77c206b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c @@ -1035,6 +1035,7 @@ static const struct dc_debug_options debug_defaults_drv = { }, .optimize_edp_link_rate = true, .enable_sw_cntl_psr = true, + .psr_power_use_phy_fsm = 0, }; static const struct dc_debug_options debug_defaults_diags = { @@ -1759,7 +1760,7 @@ static struct clock_source *dcn31_clock_source_create( if (!clk_src) return NULL; - if (dcn3_clk_src_construct(clk_src, ctx, bios, id, + if (dcn31_clk_src_construct(clk_src, ctx, bios, id, regs, &cs_shift, &cs_mask)) { clk_src->base.dp_clk_src = dp_clk_src; return &clk_src->base; @@ -1784,7 +1785,9 @@ static int dcn315_populate_dml_pipes_from_context( struct pipe_ctx *pipe; const int max_usable_det = context->bw_ctx.dml.ip.config_return_buffer_size_in_kbytes - DCN3_15_MIN_COMPBUF_SIZE_KB; + DC_FP_START(); dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); + DC_FP_END(); for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { struct dc_crtc_timing *timing; @@ -1962,29 +1965,6 @@ static struct resource_funcs dcn315_res_pool_funcs = { .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, }; -static struct clock_source *dcn30_clock_source_create( - struct dc_context *ctx, - struct dc_bios *bios, - enum clock_source_id id, - const struct dce110_clk_src_regs *regs, - bool dp_clk_src) -{ - struct dce110_clk_src *clk_src = - kzalloc(sizeof(struct dce110_clk_src), GFP_KERNEL); - - if (!clk_src) - return NULL; - - if (dcn3_clk_src_construct(clk_src, ctx, bios, id, - regs, &cs_shift, &cs_mask)) { - clk_src->base.dp_clk_src = dp_clk_src; - return &clk_src->base; - } - - BREAK_TO_DEBUGGER(); - return NULL; -} - static bool dcn315_resource_construct( uint8_t num_virtual_links, struct dc *dc, @@ -2090,23 +2070,23 @@ static bool dcn315_resource_construct( /* Clock Sources for Pixel Clock*/ pool->base.clock_sources[DCN31_CLK_SRC_PLL0] = - dcn30_clock_source_create(ctx, ctx->dc_bios, + dcn31_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL0, &clk_src_regs[0], false); pool->base.clock_sources[DCN31_CLK_SRC_PLL1] = - dcn30_clock_source_create(ctx, ctx->dc_bios, + dcn31_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL1, &clk_src_regs[1], false); pool->base.clock_sources[DCN31_CLK_SRC_PLL2] = - dcn30_clock_source_create(ctx, ctx->dc_bios, + dcn31_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL2, &clk_src_regs[2], false); pool->base.clock_sources[DCN31_CLK_SRC_PLL3] = - dcn30_clock_source_create(ctx, ctx->dc_bios, + dcn31_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL3, &clk_src_regs[3], false); pool->base.clock_sources[DCN31_CLK_SRC_PLL4] = - dcn30_clock_source_create(ctx, ctx->dc_bios, + dcn31_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL4, &clk_src_regs[4], false); diff --git a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c index 72d581c6092f..8decc3ccf8ca 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c @@ -1759,7 +1759,7 @@ static struct clock_source *dcn31_clock_source_create( if (!clk_src) return NULL; - if (dcn3_clk_src_construct(clk_src, ctx, bios, id, + if (dcn31_clk_src_construct(clk_src, ctx, bios, id, regs, &cs_shift, &cs_mask)) { clk_src->base.dp_clk_src = dp_clk_src; return &clk_src->base; @@ -1786,7 +1786,9 @@ static int dcn316_populate_dml_pipes_from_context( struct pipe_ctx *pipe; const int max_usable_det = context->bw_ctx.dml.ip.config_return_buffer_size_in_kbytes - DCN3_16_MIN_COMPBUF_SIZE_KB; + DC_FP_START(); dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); + DC_FP_END(); for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { struct dc_crtc_timing *timing; @@ -1964,29 +1966,6 @@ static struct resource_funcs dcn316_res_pool_funcs = { .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, }; -static struct clock_source *dcn30_clock_source_create( - struct dc_context *ctx, - struct dc_bios *bios, - enum clock_source_id id, - const struct dce110_clk_src_regs *regs, - bool dp_clk_src) -{ - struct dce110_clk_src *clk_src = - kzalloc(sizeof(struct dce110_clk_src), GFP_KERNEL); - - if (!clk_src) - return NULL; - - if (dcn3_clk_src_construct(clk_src, ctx, bios, id, - regs, &cs_shift, &cs_mask)) { - clk_src->base.dp_clk_src = dp_clk_src; - return &clk_src->base; - } - - BREAK_TO_DEBUGGER(); - return NULL; -} - static bool dcn316_resource_construct( uint8_t num_virtual_links, struct dc *dc, @@ -2092,23 +2071,23 @@ static bool dcn316_resource_construct( /* Clock Sources for Pixel Clock*/ pool->base.clock_sources[DCN31_CLK_SRC_PLL0] = - dcn30_clock_source_create(ctx, ctx->dc_bios, + dcn31_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL0, &clk_src_regs[0], false); pool->base.clock_sources[DCN31_CLK_SRC_PLL1] = - dcn30_clock_source_create(ctx, ctx->dc_bios, + dcn31_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL1, &clk_src_regs[1], false); pool->base.clock_sources[DCN31_CLK_SRC_PLL2] = - dcn30_clock_source_create(ctx, ctx->dc_bios, + dcn31_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL2, &clk_src_regs[2], false); pool->base.clock_sources[DCN31_CLK_SRC_PLL3] = - dcn30_clock_source_create(ctx, ctx->dc_bios, + dcn31_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL3, &clk_src_regs[3], false); pool->base.clock_sources[DCN31_CLK_SRC_PLL4] = - dcn30_clock_source_create(ctx, ctx->dc_bios, + dcn31_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL4, &clk_src_regs[4], false); diff --git a/drivers/gpu/drm/amd/display/dc/dm_helpers.h b/drivers/gpu/drm/amd/display/dc/dm_helpers.h index b71b5fb894e2..31109db02e93 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_helpers.h +++ b/drivers/gpu/drm/amd/display/dc/dm_helpers.h @@ -184,4 +184,7 @@ int dm_helpers_dmub_set_config_sync(struct dc_context *ctx, const struct dc_link *link, struct set_config_cmd_payload *payload, enum set_config_status *operation_result); + +enum dc_edid_status dm_helpers_get_sbios_edid(struct dc_link *link, struct dc_edid *edid); + #endif /* __DM_HELPERS__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index b16c492593e2..28978ce62f87 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -58,6 +58,7 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags) ifdef CONFIG_DRM_AMD_DC_DCN CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) @@ -72,6 +73,7 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) $(fram CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn301/dcn301_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn302/dcn302_fpu.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn303/dcn303_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dsc/rc_calc_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/calcs/dcn_calcs.o := $(dml_ccflags) @@ -105,6 +107,7 @@ DML = calcs/dce_calcs.o calcs/custom_float.o calcs/bw_fixed.o ifdef CONFIG_DRM_AMD_DC_DCN DML += display_mode_lib.o display_rq_dlg_helpers.o dml1_display_rq_dlg_calc.o +DML += dcn10/dcn10_fpu.o DML += dcn20/dcn20_fpu.o DML += display_mode_vba.o dcn20/display_rq_dlg_calc_20.o dcn20/display_mode_vba_20.o DML += dcn20/display_rq_dlg_calc_20v2.o dcn20/display_mode_vba_20v2.o @@ -113,6 +116,7 @@ DML += dcn30/display_mode_vba_30.o dcn30/display_rq_dlg_calc_30.o DML += dcn31/display_mode_vba_31.o dcn31/display_rq_dlg_calc_31.o DML += dcn301/dcn301_fpu.o DML += dcn302/dcn302_fpu.o +DML += dcn303/dcn303_fpu.o DML += dsc/rc_calc_fpu.o DML += calcs/dcn_calcs.o calcs/dcn_calc_math.o calcs/dcn_calc_auto.o endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.c new file mode 100644 index 000000000000..99644d896222 --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: MIT +/* + * 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. + * + * Authors: AMD + * + */ + +#include "dcn10/dcn10_resource.h" + +#include "dcn10_fpu.h" + +/** + * DOC: DCN10 FPU manipulation Overview + * + * The DCN architecture relies on FPU operations, which require special + * compilation flags and the use of kernel_fpu_begin/end functions; ideally, we + * want to avoid spreading FPU access across multiple files. With this idea in + * mind, this file aims to centralize DCN10 functions that require FPU access + * in a single place. Code in this file follows the following code pattern: + * + * 1. Functions that use FPU operations should be isolated in static functions. + * 2. The FPU functions should have the noinline attribute to ensure anything + * that deals with FP register is contained within this call. + * 3. All function that needs to be accessed outside this file requires a + * public interface that not uses any FPU reference. + * 4. Developers **must not** use DC_FP_START/END in this file, but they need + * to ensure that the caller invokes it before access any function available + * in this file. For this reason, public functions in this file must invoke + * dc_assert_fp_enabled(); + * + * Let's expand a little bit more the idea in the code pattern. To fully + * isolate FPU operations in a single place, we must avoid situations where + * compilers spill FP values to registers due to FP enable in a specific C + * file. Note that even if we isolate all FPU functions in a single file and + * call its interface from other files, the compiler might enable the use of + * FPU before we call DC_FP_START. Nevertheless, it is the programmer's + * responsibility to invoke DC_FP_START/END in the correct place. To highlight + * situations where developers forgot to use the FP protection before calling + * the DC FPU interface functions, we introduce a helper that checks if the + * function is invoked under FP protection. If not, it will trigger a kernel + * warning. + */ + +struct _vcs_dpi_ip_params_st dcn1_0_ip = { + .rob_buffer_size_kbytes = 64, + .det_buffer_size_kbytes = 164, + .dpte_buffer_size_in_pte_reqs_luma = 42, + .dpp_output_buffer_pixels = 2560, + .opp_output_buffer_lines = 1, + .pixel_chunk_size_kbytes = 8, + .pte_enable = 1, + .pte_chunk_size_kbytes = 2, + .meta_chunk_size_kbytes = 2, + .writeback_chunk_size_kbytes = 2, + .line_buffer_size_bits = 589824, + .max_line_buffer_lines = 12, + .IsLineBufferBppFixed = 0, + .LineBufferFixedBpp = -1, + .writeback_luma_buffer_size_kbytes = 12, + .writeback_chroma_buffer_size_kbytes = 8, + .max_num_dpp = 4, + .max_num_wb = 2, + .max_dchub_pscl_bw_pix_per_clk = 4, + .max_pscl_lb_bw_pix_per_clk = 2, + .max_lb_vscl_bw_pix_per_clk = 4, + .max_vscl_hscl_bw_pix_per_clk = 4, + .max_hscl_ratio = 4, + .max_vscl_ratio = 4, + .hscl_mults = 4, + .vscl_mults = 4, + .max_hscl_taps = 8, + .max_vscl_taps = 8, + .dispclk_ramp_margin_percent = 1, + .underscan_factor = 1.10, + .min_vblank_lines = 14, + .dppclk_delay_subtotal = 90, + .dispclk_delay_subtotal = 42, + .dcfclk_cstate_latency = 10, + .max_inter_dcn_tile_repeaters = 8, + .can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one = 0, + .bug_forcing_LC_req_same_size_fixed = 0, +}; + +struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc = { + .sr_exit_time_us = 9.0, + .sr_enter_plus_exit_time_us = 11.0, + .urgent_latency_us = 4.0, + .writeback_latency_us = 12.0, + .ideal_dram_bw_after_urgent_percent = 80.0, + .max_request_size_bytes = 256, + .downspread_percent = 0.5, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 128, + .urgent_out_of_order_return_per_channel_bytes = 256, + .channel_interleave_bytes = 256, + .num_banks = 8, + .num_chans = 2, + .vmm_page_size_bytes = 4096, + .dram_clock_change_latency_us = 17.0, + .writeback_dram_clock_change_latency_us = 23.0, + .return_bus_width_bytes = 64, +}; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hdp.c b/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.h index b7fbc114a175..e74ed4b4ce5b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hdp.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /* * Copyright 2021 Advanced Micro Devices, Inc. * @@ -19,14 +20,11 @@ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR * OTHER DEALINGS IN THE SOFTWARE. * + * Authors: AMD + * */ -#include "amdgpu.h" -#include "amdgpu_ras.h" +#ifndef __DCN10_FPU_H__ +#define __DCN10_FPU_H__ -void amdgpu_hdp_ras_fini(struct amdgpu_device *adev) -{ - if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__HDP) && - adev->hdp.ras_if) - amdgpu_ras_block_late_fini(adev, adev->hdp.ras_if); -} +#endif /* __DCN20_FPU_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index d590dc917363..2f6122153bdb 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -25,9 +25,23 @@ */ #include "resource.h" +#include "clk_mgr.h" +#include "dc_link_dp.h" +#include "dchubbub.h" +#include "dcn20/dcn20_resource.h" +#include "dcn21/dcn21_resource.h" #include "dcn20_fpu.h" +#define DC_LOGGER_INIT(logger) + +#ifndef MAX +#define MAX(X, Y) ((X) > (Y) ? (X) : (Y)) +#endif +#ifndef MIN +#define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) +#endif + /** * DOC: DCN2x FPU manipulation Overview * @@ -61,6 +75,581 @@ * warning. */ +struct _vcs_dpi_ip_params_st dcn2_0_ip = { + .odm_capable = 1, + .gpuvm_enable = 0, + .hostvm_enable = 0, + .gpuvm_max_page_table_levels = 4, + .hostvm_max_page_table_levels = 4, + .hostvm_cached_page_table_levels = 0, + .pte_group_size_bytes = 2048, + .num_dsc = 6, + .rob_buffer_size_kbytes = 168, + .det_buffer_size_kbytes = 164, + .dpte_buffer_size_in_pte_reqs_luma = 84, + .pde_proc_buffer_size_64k_reqs = 48, + .dpp_output_buffer_pixels = 2560, + .opp_output_buffer_lines = 1, + .pixel_chunk_size_kbytes = 8, + .pte_chunk_size_kbytes = 2, + .meta_chunk_size_kbytes = 2, + .writeback_chunk_size_kbytes = 2, + .line_buffer_size_bits = 789504, + .is_line_buffer_bpp_fixed = 0, + .line_buffer_fixed_bpp = 0, + .dcc_supported = true, + .max_line_buffer_lines = 12, + .writeback_luma_buffer_size_kbytes = 12, + .writeback_chroma_buffer_size_kbytes = 8, + .writeback_chroma_line_buffer_width_pixels = 4, + .writeback_max_hscl_ratio = 1, + .writeback_max_vscl_ratio = 1, + .writeback_min_hscl_ratio = 1, + .writeback_min_vscl_ratio = 1, + .writeback_max_hscl_taps = 12, + .writeback_max_vscl_taps = 12, + .writeback_line_buffer_luma_buffer_size = 0, + .writeback_line_buffer_chroma_buffer_size = 14643, + .cursor_buffer_size = 8, + .cursor_chunk_size = 2, + .max_num_otg = 6, + .max_num_dpp = 6, + .max_num_wb = 1, + .max_dchub_pscl_bw_pix_per_clk = 4, + .max_pscl_lb_bw_pix_per_clk = 2, + .max_lb_vscl_bw_pix_per_clk = 4, + .max_vscl_hscl_bw_pix_per_clk = 4, + .max_hscl_ratio = 8, + .max_vscl_ratio = 8, + .hscl_mults = 4, + .vscl_mults = 4, + .max_hscl_taps = 8, + .max_vscl_taps = 8, + .dispclk_ramp_margin_percent = 1, + .underscan_factor = 1.10, + .min_vblank_lines = 32, // + .dppclk_delay_subtotal = 77, // + .dppclk_delay_scl_lb_only = 16, + .dppclk_delay_scl = 50, + .dppclk_delay_cnvc_formatter = 8, + .dppclk_delay_cnvc_cursor = 6, + .dispclk_delay_subtotal = 87, // + .dcfclk_cstate_latency = 10, // SRExitTime + .max_inter_dcn_tile_repeaters = 8, + .xfc_supported = true, + .xfc_fill_bw_overhead_percent = 10.0, + .xfc_fill_constant_bytes = 0, + .number_of_cursors = 1, +}; + +struct _vcs_dpi_ip_params_st dcn2_0_nv14_ip = { + .odm_capable = 1, + .gpuvm_enable = 0, + .hostvm_enable = 0, + .gpuvm_max_page_table_levels = 4, + .hostvm_max_page_table_levels = 4, + .hostvm_cached_page_table_levels = 0, + .num_dsc = 5, + .rob_buffer_size_kbytes = 168, + .det_buffer_size_kbytes = 164, + .dpte_buffer_size_in_pte_reqs_luma = 84, + .dpte_buffer_size_in_pte_reqs_chroma = 42,//todo + .dpp_output_buffer_pixels = 2560, + .opp_output_buffer_lines = 1, + .pixel_chunk_size_kbytes = 8, + .pte_enable = 1, + .max_page_table_levels = 4, + .pte_chunk_size_kbytes = 2, + .meta_chunk_size_kbytes = 2, + .writeback_chunk_size_kbytes = 2, + .line_buffer_size_bits = 789504, + .is_line_buffer_bpp_fixed = 0, + .line_buffer_fixed_bpp = 0, + .dcc_supported = true, + .max_line_buffer_lines = 12, + .writeback_luma_buffer_size_kbytes = 12, + .writeback_chroma_buffer_size_kbytes = 8, + .writeback_chroma_line_buffer_width_pixels = 4, + .writeback_max_hscl_ratio = 1, + .writeback_max_vscl_ratio = 1, + .writeback_min_hscl_ratio = 1, + .writeback_min_vscl_ratio = 1, + .writeback_max_hscl_taps = 12, + .writeback_max_vscl_taps = 12, + .writeback_line_buffer_luma_buffer_size = 0, + .writeback_line_buffer_chroma_buffer_size = 14643, + .cursor_buffer_size = 8, + .cursor_chunk_size = 2, + .max_num_otg = 5, + .max_num_dpp = 5, + .max_num_wb = 1, + .max_dchub_pscl_bw_pix_per_clk = 4, + .max_pscl_lb_bw_pix_per_clk = 2, + .max_lb_vscl_bw_pix_per_clk = 4, + .max_vscl_hscl_bw_pix_per_clk = 4, + .max_hscl_ratio = 8, + .max_vscl_ratio = 8, + .hscl_mults = 4, + .vscl_mults = 4, + .max_hscl_taps = 8, + .max_vscl_taps = 8, + .dispclk_ramp_margin_percent = 1, + .underscan_factor = 1.10, + .min_vblank_lines = 32, // + .dppclk_delay_subtotal = 77, // + .dppclk_delay_scl_lb_only = 16, + .dppclk_delay_scl = 50, + .dppclk_delay_cnvc_formatter = 8, + .dppclk_delay_cnvc_cursor = 6, + .dispclk_delay_subtotal = 87, // + .dcfclk_cstate_latency = 10, // SRExitTime + .max_inter_dcn_tile_repeaters = 8, + .xfc_supported = true, + .xfc_fill_bw_overhead_percent = 10.0, + .xfc_fill_constant_bytes = 0, + .ptoi_supported = 0, + .number_of_cursors = 1, +}; + +struct _vcs_dpi_soc_bounding_box_st dcn2_0_soc = { + /* Defaults that get patched on driver load from firmware. */ + .clock_limits = { + { + .state = 0, + .dcfclk_mhz = 560.0, + .fabricclk_mhz = 560.0, + .dispclk_mhz = 513.0, + .dppclk_mhz = 513.0, + .phyclk_mhz = 540.0, + .socclk_mhz = 560.0, + .dscclk_mhz = 171.0, + .dram_speed_mts = 8960.0, + }, + { + .state = 1, + .dcfclk_mhz = 694.0, + .fabricclk_mhz = 694.0, + .dispclk_mhz = 642.0, + .dppclk_mhz = 642.0, + .phyclk_mhz = 600.0, + .socclk_mhz = 694.0, + .dscclk_mhz = 214.0, + .dram_speed_mts = 11104.0, + }, + { + .state = 2, + .dcfclk_mhz = 875.0, + .fabricclk_mhz = 875.0, + .dispclk_mhz = 734.0, + .dppclk_mhz = 734.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 875.0, + .dscclk_mhz = 245.0, + .dram_speed_mts = 14000.0, + }, + { + .state = 3, + .dcfclk_mhz = 1000.0, + .fabricclk_mhz = 1000.0, + .dispclk_mhz = 1100.0, + .dppclk_mhz = 1100.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1000.0, + .dscclk_mhz = 367.0, + .dram_speed_mts = 16000.0, + }, + { + .state = 4, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 16000.0, + }, + /*Extra state, no dispclk ramping*/ + { + .state = 5, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 16000.0, + }, + }, + .num_states = 5, + .sr_exit_time_us = 8.6, + .sr_enter_plus_exit_time_us = 10.9, + .urgent_latency_us = 4.0, + .urgent_latency_pixel_data_only_us = 4.0, + .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, + .urgent_latency_vm_data_only_us = 4.0, + .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, + .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, + .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, + .max_avg_sdp_bw_use_normal_percent = 40.0, + .max_avg_dram_bw_use_normal_percent = 40.0, + .writeback_latency_us = 12.0, + .ideal_dram_bw_after_urgent_percent = 40.0, + .max_request_size_bytes = 256, + .dram_channel_width_bytes = 2, + .fabric_datapath_to_dcn_data_return_bytes = 64, + .dcn_downspread_percent = 0.5, + .downspread_percent = 0.38, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 131, + .urgent_out_of_order_return_per_channel_bytes = 256, + .channel_interleave_bytes = 256, + .num_banks = 8, + .num_chans = 16, + .vmm_page_size_bytes = 4096, + .dram_clock_change_latency_us = 404.0, + .dummy_pstate_latency_us = 5.0, + .writeback_dram_clock_change_latency_us = 23.0, + .return_bus_width_bytes = 64, + .dispclk_dppclk_vco_speed_mhz = 3850, + .xfc_bus_transport_time_us = 20, + .xfc_xbuf_latency_tolerance_us = 4, + .use_urgent_burst_bw = 0 +}; + +struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { + .clock_limits = { + { + .state = 0, + .dcfclk_mhz = 560.0, + .fabricclk_mhz = 560.0, + .dispclk_mhz = 513.0, + .dppclk_mhz = 513.0, + .phyclk_mhz = 540.0, + .socclk_mhz = 560.0, + .dscclk_mhz = 171.0, + .dram_speed_mts = 8960.0, + }, + { + .state = 1, + .dcfclk_mhz = 694.0, + .fabricclk_mhz = 694.0, + .dispclk_mhz = 642.0, + .dppclk_mhz = 642.0, + .phyclk_mhz = 600.0, + .socclk_mhz = 694.0, + .dscclk_mhz = 214.0, + .dram_speed_mts = 11104.0, + }, + { + .state = 2, + .dcfclk_mhz = 875.0, + .fabricclk_mhz = 875.0, + .dispclk_mhz = 734.0, + .dppclk_mhz = 734.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 875.0, + .dscclk_mhz = 245.0, + .dram_speed_mts = 14000.0, + }, + { + .state = 3, + .dcfclk_mhz = 1000.0, + .fabricclk_mhz = 1000.0, + .dispclk_mhz = 1100.0, + .dppclk_mhz = 1100.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1000.0, + .dscclk_mhz = 367.0, + .dram_speed_mts = 16000.0, + }, + { + .state = 4, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 16000.0, + }, + /*Extra state, no dispclk ramping*/ + { + .state = 5, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 16000.0, + }, + }, + .num_states = 5, + .sr_exit_time_us = 11.6, + .sr_enter_plus_exit_time_us = 13.9, + .urgent_latency_us = 4.0, + .urgent_latency_pixel_data_only_us = 4.0, + .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, + .urgent_latency_vm_data_only_us = 4.0, + .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, + .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, + .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, + .max_avg_sdp_bw_use_normal_percent = 40.0, + .max_avg_dram_bw_use_normal_percent = 40.0, + .writeback_latency_us = 12.0, + .ideal_dram_bw_after_urgent_percent = 40.0, + .max_request_size_bytes = 256, + .dram_channel_width_bytes = 2, + .fabric_datapath_to_dcn_data_return_bytes = 64, + .dcn_downspread_percent = 0.5, + .downspread_percent = 0.38, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 131, + .urgent_out_of_order_return_per_channel_bytes = 256, + .channel_interleave_bytes = 256, + .num_banks = 8, + .num_chans = 8, + .vmm_page_size_bytes = 4096, + .dram_clock_change_latency_us = 404.0, + .dummy_pstate_latency_us = 5.0, + .writeback_dram_clock_change_latency_us = 23.0, + .return_bus_width_bytes = 64, + .dispclk_dppclk_vco_speed_mhz = 3850, + .xfc_bus_transport_time_us = 20, + .xfc_xbuf_latency_tolerance_us = 4, + .use_urgent_burst_bw = 0 +}; + +struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 }; + +struct _vcs_dpi_ip_params_st dcn2_1_ip = { + .odm_capable = 1, + .gpuvm_enable = 1, + .hostvm_enable = 1, + .gpuvm_max_page_table_levels = 1, + .hostvm_max_page_table_levels = 4, + .hostvm_cached_page_table_levels = 2, + .num_dsc = 3, + .rob_buffer_size_kbytes = 168, + .det_buffer_size_kbytes = 164, + .dpte_buffer_size_in_pte_reqs_luma = 44, + .dpte_buffer_size_in_pte_reqs_chroma = 42,//todo + .dpp_output_buffer_pixels = 2560, + .opp_output_buffer_lines = 1, + .pixel_chunk_size_kbytes = 8, + .pte_enable = 1, + .max_page_table_levels = 4, + .pte_chunk_size_kbytes = 2, + .meta_chunk_size_kbytes = 2, + .min_meta_chunk_size_bytes = 256, + .writeback_chunk_size_kbytes = 2, + .line_buffer_size_bits = 789504, + .is_line_buffer_bpp_fixed = 0, + .line_buffer_fixed_bpp = 0, + .dcc_supported = true, + .max_line_buffer_lines = 12, + .writeback_luma_buffer_size_kbytes = 12, + .writeback_chroma_buffer_size_kbytes = 8, + .writeback_chroma_line_buffer_width_pixels = 4, + .writeback_max_hscl_ratio = 1, + .writeback_max_vscl_ratio = 1, + .writeback_min_hscl_ratio = 1, + .writeback_min_vscl_ratio = 1, + .writeback_max_hscl_taps = 12, + .writeback_max_vscl_taps = 12, + .writeback_line_buffer_luma_buffer_size = 0, + .writeback_line_buffer_chroma_buffer_size = 14643, + .cursor_buffer_size = 8, + .cursor_chunk_size = 2, + .max_num_otg = 4, + .max_num_dpp = 4, + .max_num_wb = 1, + .max_dchub_pscl_bw_pix_per_clk = 4, + .max_pscl_lb_bw_pix_per_clk = 2, + .max_lb_vscl_bw_pix_per_clk = 4, + .max_vscl_hscl_bw_pix_per_clk = 4, + .max_hscl_ratio = 4, + .max_vscl_ratio = 4, + .hscl_mults = 4, + .vscl_mults = 4, + .max_hscl_taps = 8, + .max_vscl_taps = 8, + .dispclk_ramp_margin_percent = 1, + .underscan_factor = 1.10, + .min_vblank_lines = 32, // + .dppclk_delay_subtotal = 77, // + .dppclk_delay_scl_lb_only = 16, + .dppclk_delay_scl = 50, + .dppclk_delay_cnvc_formatter = 8, + .dppclk_delay_cnvc_cursor = 6, + .dispclk_delay_subtotal = 87, // + .dcfclk_cstate_latency = 10, // SRExitTime + .max_inter_dcn_tile_repeaters = 8, + + .xfc_supported = false, + .xfc_fill_bw_overhead_percent = 10.0, + .xfc_fill_constant_bytes = 0, + .ptoi_supported = 0, + .number_of_cursors = 1, +}; + +struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { + .clock_limits = { + { + .state = 0, + .dcfclk_mhz = 400.0, + .fabricclk_mhz = 400.0, + .dispclk_mhz = 600.0, + .dppclk_mhz = 400.00, + .phyclk_mhz = 600.0, + .socclk_mhz = 278.0, + .dscclk_mhz = 205.67, + .dram_speed_mts = 1600.0, + }, + { + .state = 1, + .dcfclk_mhz = 464.52, + .fabricclk_mhz = 800.0, + .dispclk_mhz = 654.55, + .dppclk_mhz = 626.09, + .phyclk_mhz = 600.0, + .socclk_mhz = 278.0, + .dscclk_mhz = 205.67, + .dram_speed_mts = 1600.0, + }, + { + .state = 2, + .dcfclk_mhz = 514.29, + .fabricclk_mhz = 933.0, + .dispclk_mhz = 757.89, + .dppclk_mhz = 685.71, + .phyclk_mhz = 600.0, + .socclk_mhz = 278.0, + .dscclk_mhz = 287.67, + .dram_speed_mts = 1866.0, + }, + { + .state = 3, + .dcfclk_mhz = 576.00, + .fabricclk_mhz = 1067.0, + .dispclk_mhz = 847.06, + .dppclk_mhz = 757.89, + .phyclk_mhz = 600.0, + .socclk_mhz = 715.0, + .dscclk_mhz = 318.334, + .dram_speed_mts = 2134.0, + }, + { + .state = 4, + .dcfclk_mhz = 626.09, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 900.00, + .dppclk_mhz = 847.06, + .phyclk_mhz = 810.0, + .socclk_mhz = 953.0, + .dscclk_mhz = 489.0, + .dram_speed_mts = 2400.0, + }, + { + .state = 5, + .dcfclk_mhz = 685.71, + .fabricclk_mhz = 1333.0, + .dispclk_mhz = 1028.57, + .dppclk_mhz = 960.00, + .phyclk_mhz = 810.0, + .socclk_mhz = 278.0, + .dscclk_mhz = 287.67, + .dram_speed_mts = 2666.0, + }, + { + .state = 6, + .dcfclk_mhz = 757.89, + .fabricclk_mhz = 1467.0, + .dispclk_mhz = 1107.69, + .dppclk_mhz = 1028.57, + .phyclk_mhz = 810.0, + .socclk_mhz = 715.0, + .dscclk_mhz = 318.334, + .dram_speed_mts = 3200.0, + }, + { + .state = 7, + .dcfclk_mhz = 847.06, + .fabricclk_mhz = 1600.0, + .dispclk_mhz = 1395.0, + .dppclk_mhz = 1285.00, + .phyclk_mhz = 1325.0, + .socclk_mhz = 953.0, + .dscclk_mhz = 489.0, + .dram_speed_mts = 4266.0, + }, + /*Extra state, no dispclk ramping*/ + { + .state = 8, + .dcfclk_mhz = 847.06, + .fabricclk_mhz = 1600.0, + .dispclk_mhz = 1395.0, + .dppclk_mhz = 1285.0, + .phyclk_mhz = 1325.0, + .socclk_mhz = 953.0, + .dscclk_mhz = 489.0, + .dram_speed_mts = 4266.0, + }, + + }, + + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 17.0, + .urgent_latency_us = 4.0, + .urgent_latency_pixel_data_only_us = 4.0, + .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, + .urgent_latency_vm_data_only_us = 4.0, + .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, + .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, + .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 80.0, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 75.0, + .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, + .max_avg_sdp_bw_use_normal_percent = 60.0, + .max_avg_dram_bw_use_normal_percent = 100.0, + .writeback_latency_us = 12.0, + .max_request_size_bytes = 256, + .dram_channel_width_bytes = 4, + .fabric_datapath_to_dcn_data_return_bytes = 32, + .dcn_downspread_percent = 0.5, + .downspread_percent = 0.38, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 128, + .urgent_out_of_order_return_per_channel_bytes = 4096, + .channel_interleave_bytes = 256, + .num_banks = 8, + .num_chans = 4, + .vmm_page_size_bytes = 4096, + .dram_clock_change_latency_us = 23.84, + .return_bus_width_bytes = 64, + .dispclk_dppclk_vco_speed_mhz = 3600, + .xfc_bus_transport_time_us = 4, + .xfc_xbuf_latency_tolerance_us = 4, + .use_urgent_burst_bw = 1, + .num_states = 8 +}; + void dcn20_populate_dml_writeback_from_context(struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes) @@ -100,3 +689,1340 @@ void dcn20_populate_dml_writeback_from_context(struct dc *dc, pipe_cnt++; } } + +void dcn20_fpu_set_wb_arb_params(struct mcif_arb_params *wb_arb_params, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, int i) +{ + int k; + + dc_assert_fp_enabled(); + + for (k = 0; k < sizeof(wb_arb_params->cli_watermark)/sizeof(wb_arb_params->cli_watermark[0]); k++) { + wb_arb_params->cli_watermark[k] = get_wm_writeback_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + wb_arb_params->pstate_watermark[k] = get_wm_writeback_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + } + wb_arb_params->time_per_pixel = 16.0 * 1000 / (context->res_ctx.pipe_ctx[i].stream->phy_pix_clk / 1000); /* 4 bit fraction, ms */ +} + +static bool is_dtbclk_required(struct dc *dc, struct dc_state *context) +{ + int i; + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (!context->res_ctx.pipe_ctx[i].stream) + continue; + if (is_dp_128b_132b_signal(&context->res_ctx.pipe_ctx[i])) + return true; + } + return false; +} + +static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struct dc_state *context) +{ + int plane_count; + int i; + + plane_count = 0; + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (context->res_ctx.pipe_ctx[i].plane_state) + plane_count++; + } + + /* + * Z9 and Z10 allowed cases: + * 1. 0 Planes enabled + * 2. single eDP, on link 0, 1 plane and stutter period > 5ms + * Z10 only cases: + * 1. single eDP, on link 0, 1 plane and stutter period >= 5ms + * Zstate not allowed cases: + * 1. Everything else + */ + if (plane_count == 0) + return DCN_ZSTATE_SUPPORT_ALLOW; + else if (context->stream_count == 1 && context->streams[0]->signal == SIGNAL_TYPE_EDP) { + struct dc_link *link = context->streams[0]->sink->link; + struct dc_stream_status *stream_status = &context->stream_status[0]; + + /* zstate only supported on PWRSEQ0 and when there's <2 planes*/ + if (link->link_index != 0 || stream_status->plane_count > 1) + return DCN_ZSTATE_SUPPORT_DISALLOW; + + if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) + return DCN_ZSTATE_SUPPORT_ALLOW; + else if (link->psr_settings.psr_version == DC_PSR_VERSION_1 && !dc->debug.disable_psr) + return DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; + else + return DCN_ZSTATE_SUPPORT_DISALLOW; + } else + return DCN_ZSTATE_SUPPORT_DISALLOW; +} + +void dcn20_calculate_dlg_params( + struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel) +{ + int i, pipe_idx; + + dc_assert_fp_enabled(); + + /* Writeback MCIF_WB arbitration parameters */ + dc->res_pool->funcs->set_mcif_arb_params(dc, context, pipes, pipe_cnt); + + context->bw_ctx.bw.dcn.clk.dispclk_khz = context->bw_ctx.dml.vba.DISPCLK * 1000; + context->bw_ctx.bw.dcn.clk.dcfclk_khz = context->bw_ctx.dml.vba.DCFCLK * 1000; + context->bw_ctx.bw.dcn.clk.socclk_khz = context->bw_ctx.dml.vba.SOCCLK * 1000; + context->bw_ctx.bw.dcn.clk.dramclk_khz = context->bw_ctx.dml.vba.DRAMSpeed * 1000 / 16; + + if (dc->debug.min_dram_clk_khz > context->bw_ctx.bw.dcn.clk.dramclk_khz) + context->bw_ctx.bw.dcn.clk.dramclk_khz = dc->debug.min_dram_clk_khz; + + context->bw_ctx.bw.dcn.clk.dcfclk_deep_sleep_khz = context->bw_ctx.dml.vba.DCFCLKDeepSleep * 1000; + context->bw_ctx.bw.dcn.clk.fclk_khz = context->bw_ctx.dml.vba.FabricClock * 1000; + context->bw_ctx.bw.dcn.clk.p_state_change_support = + context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] + != dm_dram_clock_change_unsupported; + context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; + + context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); + + context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context); + + if (context->bw_ctx.bw.dcn.clk.dispclk_khz < dc->debug.min_disp_clk_khz) + context->bw_ctx.bw.dcn.clk.dispclk_khz = dc->debug.min_disp_clk_khz; + + for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { + if (!context->res_ctx.pipe_ctx[i].stream) + continue; + pipes[pipe_idx].pipe.dest.vstartup_start = get_vstartup(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); + pipes[pipe_idx].pipe.dest.vupdate_offset = get_vupdate_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); + pipes[pipe_idx].pipe.dest.vupdate_width = get_vupdate_width(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); + pipes[pipe_idx].pipe.dest.vready_offset = get_vready_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); + context->res_ctx.pipe_ctx[i].det_buffer_size_kb = context->bw_ctx.dml.ip.det_buffer_size_kbytes; + context->res_ctx.pipe_ctx[i].unbounded_req = pipes[pipe_idx].pipe.src.unbounded_req_mode; + + if (context->bw_ctx.bw.dcn.clk.dppclk_khz < pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000) + context->bw_ctx.bw.dcn.clk.dppclk_khz = pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000; + context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz = + pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000; + context->res_ctx.pipe_ctx[i].pipe_dlg_param = pipes[pipe_idx].pipe.dest; + pipe_idx++; + } + /*save a original dppclock copy*/ + context->bw_ctx.bw.dcn.clk.bw_dppclk_khz = context->bw_ctx.bw.dcn.clk.dppclk_khz; + context->bw_ctx.bw.dcn.clk.bw_dispclk_khz = context->bw_ctx.bw.dcn.clk.dispclk_khz; + context->bw_ctx.bw.dcn.clk.max_supported_dppclk_khz = context->bw_ctx.dml.soc.clock_limits[vlevel].dppclk_mhz * 1000; + context->bw_ctx.bw.dcn.clk.max_supported_dispclk_khz = context->bw_ctx.dml.soc.clock_limits[vlevel].dispclk_mhz * 1000; + + context->bw_ctx.bw.dcn.compbuf_size_kb = context->bw_ctx.dml.ip.config_return_buffer_size_in_kbytes + - context->bw_ctx.dml.ip.det_buffer_size_kbytes * pipe_idx; + + for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { + bool cstate_en = context->bw_ctx.dml.vba.PrefetchMode[vlevel][context->bw_ctx.dml.vba.maxMpcComb] != 2; + + if (!context->res_ctx.pipe_ctx[i].stream) + continue; + + if (dc->ctx->dce_version == DCN_VERSION_2_01) + cstate_en = false; + + context->bw_ctx.dml.funcs.rq_dlg_get_dlg_reg(&context->bw_ctx.dml, + &context->res_ctx.pipe_ctx[i].dlg_regs, + &context->res_ctx.pipe_ctx[i].ttu_regs, + pipes, + pipe_cnt, + pipe_idx, + cstate_en, + context->bw_ctx.bw.dcn.clk.p_state_change_support, + false, false, true); + + context->bw_ctx.dml.funcs.rq_dlg_get_rq_reg(&context->bw_ctx.dml, + &context->res_ctx.pipe_ctx[i].rq_regs, + &pipes[pipe_idx].pipe); + pipe_idx++; + } +} + +static void swizzle_to_dml_params( + enum swizzle_mode_values swizzle, + unsigned int *sw_mode) +{ + switch (swizzle) { + case DC_SW_LINEAR: + *sw_mode = dm_sw_linear; + break; + case DC_SW_4KB_S: + *sw_mode = dm_sw_4kb_s; + break; + case DC_SW_4KB_S_X: + *sw_mode = dm_sw_4kb_s_x; + break; + case DC_SW_4KB_D: + *sw_mode = dm_sw_4kb_d; + break; + case DC_SW_4KB_D_X: + *sw_mode = dm_sw_4kb_d_x; + break; + case DC_SW_64KB_S: + *sw_mode = dm_sw_64kb_s; + break; + case DC_SW_64KB_S_X: + *sw_mode = dm_sw_64kb_s_x; + break; + case DC_SW_64KB_S_T: + *sw_mode = dm_sw_64kb_s_t; + break; + case DC_SW_64KB_D: + *sw_mode = dm_sw_64kb_d; + break; + case DC_SW_64KB_D_X: + *sw_mode = dm_sw_64kb_d_x; + break; + case DC_SW_64KB_D_T: + *sw_mode = dm_sw_64kb_d_t; + break; + case DC_SW_64KB_R_X: + *sw_mode = dm_sw_64kb_r_x; + break; + case DC_SW_VAR_S: + *sw_mode = dm_sw_var_s; + break; + case DC_SW_VAR_S_X: + *sw_mode = dm_sw_var_s_x; + break; + case DC_SW_VAR_D: + *sw_mode = dm_sw_var_d; + break; + case DC_SW_VAR_D_X: + *sw_mode = dm_sw_var_d_x; + break; + case DC_SW_VAR_R_X: + *sw_mode = dm_sw_var_r_x; + break; + default: + ASSERT(0); /* Not supported */ + break; + } +} + +int dcn20_populate_dml_pipes_from_context( + struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + bool fast_validate) +{ + int pipe_cnt, i; + bool synchronized_vblank = true; + struct resource_context *res_ctx = &context->res_ctx; + + dc_assert_fp_enabled(); + + for (i = 0, pipe_cnt = -1; i < dc->res_pool->pipe_count; i++) { + if (!res_ctx->pipe_ctx[i].stream) + continue; + + if (pipe_cnt < 0) { + pipe_cnt = i; + continue; + } + + if (res_ctx->pipe_ctx[pipe_cnt].stream == res_ctx->pipe_ctx[i].stream) + continue; + + if (dc->debug.disable_timing_sync || + (!resource_are_streams_timing_synchronizable( + res_ctx->pipe_ctx[pipe_cnt].stream, + res_ctx->pipe_ctx[i].stream) && + !resource_are_vblanks_synchronizable( + res_ctx->pipe_ctx[pipe_cnt].stream, + res_ctx->pipe_ctx[i].stream))) { + synchronized_vblank = false; + break; + } + } + + for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { + struct dc_crtc_timing *timing = &res_ctx->pipe_ctx[i].stream->timing; + unsigned int v_total; + unsigned int front_porch; + int output_bpc; + struct audio_check aud_check = {0}; + + if (!res_ctx->pipe_ctx[i].stream) + continue; + + v_total = timing->v_total; + front_porch = timing->v_front_porch; + + /* todo: + pipes[pipe_cnt].pipe.src.dynamic_metadata_enable = 0; + pipes[pipe_cnt].pipe.src.dcc = 0; + pipes[pipe_cnt].pipe.src.vm = 0;*/ + + pipes[pipe_cnt].clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0; + + pipes[pipe_cnt].dout.dsc_enable = res_ctx->pipe_ctx[i].stream->timing.flags.DSC; + /* todo: rotation?*/ + pipes[pipe_cnt].dout.dsc_slices = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.num_slices_h; + if (res_ctx->pipe_ctx[i].stream->use_dynamic_meta) { + pipes[pipe_cnt].pipe.src.dynamic_metadata_enable = true; + /* 1/2 vblank */ + pipes[pipe_cnt].pipe.src.dynamic_metadata_lines_before_active = + (v_total - timing->v_addressable + - timing->v_border_top - timing->v_border_bottom) / 2; + /* 36 bytes dp, 32 hdmi */ + pipes[pipe_cnt].pipe.src.dynamic_metadata_xmit_bytes = + dc_is_dp_signal(res_ctx->pipe_ctx[i].stream->signal) ? 36 : 32; + } + pipes[pipe_cnt].pipe.src.dcc = false; + pipes[pipe_cnt].pipe.src.dcc_rate = 1; + pipes[pipe_cnt].pipe.dest.synchronized_vblank_all_planes = synchronized_vblank; + pipes[pipe_cnt].pipe.dest.hblank_start = timing->h_total - timing->h_front_porch; + pipes[pipe_cnt].pipe.dest.hblank_end = pipes[pipe_cnt].pipe.dest.hblank_start + - timing->h_addressable + - timing->h_border_left + - timing->h_border_right; + pipes[pipe_cnt].pipe.dest.vblank_start = v_total - front_porch; + pipes[pipe_cnt].pipe.dest.vblank_end = pipes[pipe_cnt].pipe.dest.vblank_start + - timing->v_addressable + - timing->v_border_top + - timing->v_border_bottom; + pipes[pipe_cnt].pipe.dest.htotal = timing->h_total; + pipes[pipe_cnt].pipe.dest.vtotal = v_total; + pipes[pipe_cnt].pipe.dest.hactive = + timing->h_addressable + timing->h_border_left + timing->h_border_right; + pipes[pipe_cnt].pipe.dest.vactive = + timing->v_addressable + timing->v_border_top + timing->v_border_bottom; + pipes[pipe_cnt].pipe.dest.interlaced = timing->flags.INTERLACE; + pipes[pipe_cnt].pipe.dest.pixel_rate_mhz = timing->pix_clk_100hz/10000.0; + if (timing->timing_3d_format == TIMING_3D_FORMAT_HW_FRAME_PACKING) + pipes[pipe_cnt].pipe.dest.pixel_rate_mhz *= 2; + pipes[pipe_cnt].pipe.dest.otg_inst = res_ctx->pipe_ctx[i].stream_res.tg->inst; + pipes[pipe_cnt].dout.dp_lanes = 4; + pipes[pipe_cnt].dout.is_virtual = 0; + pipes[pipe_cnt].pipe.dest.vtotal_min = res_ctx->pipe_ctx[i].stream->adjust.v_total_min; + pipes[pipe_cnt].pipe.dest.vtotal_max = res_ctx->pipe_ctx[i].stream->adjust.v_total_max; + switch (get_num_odm_splits(&res_ctx->pipe_ctx[i])) { + case 1: + pipes[pipe_cnt].pipe.dest.odm_combine = dm_odm_combine_mode_2to1; + break; + case 3: + pipes[pipe_cnt].pipe.dest.odm_combine = dm_odm_combine_mode_4to1; + break; + default: + pipes[pipe_cnt].pipe.dest.odm_combine = dm_odm_combine_mode_disabled; + } + pipes[pipe_cnt].pipe.src.hsplit_grp = res_ctx->pipe_ctx[i].pipe_idx; + if (res_ctx->pipe_ctx[i].top_pipe && res_ctx->pipe_ctx[i].top_pipe->plane_state + == res_ctx->pipe_ctx[i].plane_state) { + struct pipe_ctx *first_pipe = res_ctx->pipe_ctx[i].top_pipe; + int split_idx = 0; + + while (first_pipe->top_pipe && first_pipe->top_pipe->plane_state + == res_ctx->pipe_ctx[i].plane_state) { + first_pipe = first_pipe->top_pipe; + split_idx++; + } + /* Treat 4to1 mpc combine as an mpo of 2 2-to-1 combines */ + if (split_idx == 0) + pipes[pipe_cnt].pipe.src.hsplit_grp = first_pipe->pipe_idx; + else if (split_idx == 1) + pipes[pipe_cnt].pipe.src.hsplit_grp = res_ctx->pipe_ctx[i].pipe_idx; + else if (split_idx == 2) + pipes[pipe_cnt].pipe.src.hsplit_grp = res_ctx->pipe_ctx[i].top_pipe->pipe_idx; + } else if (res_ctx->pipe_ctx[i].prev_odm_pipe) { + struct pipe_ctx *first_pipe = res_ctx->pipe_ctx[i].prev_odm_pipe; + + while (first_pipe->prev_odm_pipe) + first_pipe = first_pipe->prev_odm_pipe; + pipes[pipe_cnt].pipe.src.hsplit_grp = first_pipe->pipe_idx; + } + + switch (res_ctx->pipe_ctx[i].stream->signal) { + case SIGNAL_TYPE_DISPLAY_PORT_MST: + case SIGNAL_TYPE_DISPLAY_PORT: + pipes[pipe_cnt].dout.output_type = dm_dp; + break; + case SIGNAL_TYPE_EDP: + pipes[pipe_cnt].dout.output_type = dm_edp; + break; + case SIGNAL_TYPE_HDMI_TYPE_A: + case SIGNAL_TYPE_DVI_SINGLE_LINK: + case SIGNAL_TYPE_DVI_DUAL_LINK: + pipes[pipe_cnt].dout.output_type = dm_hdmi; + break; + default: + /* In case there is no signal, set dp with 4 lanes to allow max config */ + pipes[pipe_cnt].dout.is_virtual = 1; + pipes[pipe_cnt].dout.output_type = dm_dp; + pipes[pipe_cnt].dout.dp_lanes = 4; + } + + switch (res_ctx->pipe_ctx[i].stream->timing.display_color_depth) { + case COLOR_DEPTH_666: + output_bpc = 6; + break; + case COLOR_DEPTH_888: + output_bpc = 8; + break; + case COLOR_DEPTH_101010: + output_bpc = 10; + break; + case COLOR_DEPTH_121212: + output_bpc = 12; + break; + case COLOR_DEPTH_141414: + output_bpc = 14; + break; + case COLOR_DEPTH_161616: + output_bpc = 16; + break; + case COLOR_DEPTH_999: + output_bpc = 9; + break; + case COLOR_DEPTH_111111: + output_bpc = 11; + break; + default: + output_bpc = 8; + break; + } + + switch (res_ctx->pipe_ctx[i].stream->timing.pixel_encoding) { + case PIXEL_ENCODING_RGB: + case PIXEL_ENCODING_YCBCR444: + pipes[pipe_cnt].dout.output_format = dm_444; + pipes[pipe_cnt].dout.output_bpp = output_bpc * 3; + break; + case PIXEL_ENCODING_YCBCR420: + pipes[pipe_cnt].dout.output_format = dm_420; + pipes[pipe_cnt].dout.output_bpp = (output_bpc * 3.0) / 2; + break; + case PIXEL_ENCODING_YCBCR422: + if (res_ctx->pipe_ctx[i].stream->timing.flags.DSC && + !res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.ycbcr422_simple) + pipes[pipe_cnt].dout.output_format = dm_n422; + else + pipes[pipe_cnt].dout.output_format = dm_s422; + pipes[pipe_cnt].dout.output_bpp = output_bpc * 2; + break; + default: + pipes[pipe_cnt].dout.output_format = dm_444; + pipes[pipe_cnt].dout.output_bpp = output_bpc * 3; + } + + if (res_ctx->pipe_ctx[i].stream->timing.flags.DSC) + pipes[pipe_cnt].dout.output_bpp = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.bits_per_pixel / 16.0; + + /* todo: default max for now, until there is logic reflecting this in dc*/ + pipes[pipe_cnt].dout.dsc_input_bpc = 12; + /*fill up the audio sample rate (unit in kHz)*/ + get_audio_check(&res_ctx->pipe_ctx[i].stream->audio_info, &aud_check); + pipes[pipe_cnt].dout.max_audio_sample_rate = aud_check.max_audiosample_rate / 1000; + /* + * For graphic plane, cursor number is 1, nv12 is 0 + * bw calculations due to cursor on/off + */ + if (res_ctx->pipe_ctx[i].plane_state && + res_ctx->pipe_ctx[i].plane_state->address.type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) + pipes[pipe_cnt].pipe.src.num_cursors = 0; + else + pipes[pipe_cnt].pipe.src.num_cursors = dc->dml.ip.number_of_cursors; + + pipes[pipe_cnt].pipe.src.cur0_src_width = 256; + pipes[pipe_cnt].pipe.src.cur0_bpp = dm_cur_32bit; + + if (!res_ctx->pipe_ctx[i].plane_state) { + pipes[pipe_cnt].pipe.src.is_hsplit = pipes[pipe_cnt].pipe.dest.odm_combine != dm_odm_combine_mode_disabled; + pipes[pipe_cnt].pipe.src.source_scan = dm_horz; + pipes[pipe_cnt].pipe.src.sw_mode = dm_sw_4kb_s; + pipes[pipe_cnt].pipe.src.macro_tile_size = dm_64k_tile; + pipes[pipe_cnt].pipe.src.viewport_width = timing->h_addressable; + if (pipes[pipe_cnt].pipe.src.viewport_width > 1920) + pipes[pipe_cnt].pipe.src.viewport_width = 1920; + pipes[pipe_cnt].pipe.src.viewport_height = timing->v_addressable; + if (pipes[pipe_cnt].pipe.src.viewport_height > 1080) + pipes[pipe_cnt].pipe.src.viewport_height = 1080; + pipes[pipe_cnt].pipe.src.surface_height_y = pipes[pipe_cnt].pipe.src.viewport_height; + pipes[pipe_cnt].pipe.src.surface_width_y = pipes[pipe_cnt].pipe.src.viewport_width; + pipes[pipe_cnt].pipe.src.surface_height_c = pipes[pipe_cnt].pipe.src.viewport_height; + pipes[pipe_cnt].pipe.src.surface_width_c = pipes[pipe_cnt].pipe.src.viewport_width; + pipes[pipe_cnt].pipe.src.data_pitch = ((pipes[pipe_cnt].pipe.src.viewport_width + 255) / 256) * 256; + pipes[pipe_cnt].pipe.src.source_format = dm_444_32; + pipes[pipe_cnt].pipe.dest.recout_width = pipes[pipe_cnt].pipe.src.viewport_width; /*vp_width/hratio*/ + pipes[pipe_cnt].pipe.dest.recout_height = pipes[pipe_cnt].pipe.src.viewport_height; /*vp_height/vratio*/ + pipes[pipe_cnt].pipe.dest.full_recout_width = pipes[pipe_cnt].pipe.dest.recout_width; /*when is_hsplit != 1*/ + pipes[pipe_cnt].pipe.dest.full_recout_height = pipes[pipe_cnt].pipe.dest.recout_height; /*when is_hsplit != 1*/ + pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_16; + pipes[pipe_cnt].pipe.scale_ratio_depth.hscl_ratio = 1.0; + pipes[pipe_cnt].pipe.scale_ratio_depth.vscl_ratio = 1.0; + pipes[pipe_cnt].pipe.scale_ratio_depth.scl_enable = 0; /*Lb only or Full scl*/ + pipes[pipe_cnt].pipe.scale_taps.htaps = 1; + pipes[pipe_cnt].pipe.scale_taps.vtaps = 1; + pipes[pipe_cnt].pipe.dest.vtotal_min = v_total; + pipes[pipe_cnt].pipe.dest.vtotal_max = v_total; + + if (pipes[pipe_cnt].pipe.dest.odm_combine == dm_odm_combine_mode_2to1) { + pipes[pipe_cnt].pipe.src.viewport_width /= 2; + pipes[pipe_cnt].pipe.dest.recout_width /= 2; + } else if (pipes[pipe_cnt].pipe.dest.odm_combine == dm_odm_combine_mode_4to1) { + pipes[pipe_cnt].pipe.src.viewport_width /= 4; + pipes[pipe_cnt].pipe.dest.recout_width /= 4; + } + } else { + struct dc_plane_state *pln = res_ctx->pipe_ctx[i].plane_state; + struct scaler_data *scl = &res_ctx->pipe_ctx[i].plane_res.scl_data; + + pipes[pipe_cnt].pipe.src.immediate_flip = pln->flip_immediate; + pipes[pipe_cnt].pipe.src.is_hsplit = (res_ctx->pipe_ctx[i].bottom_pipe && res_ctx->pipe_ctx[i].bottom_pipe->plane_state == pln) + || (res_ctx->pipe_ctx[i].top_pipe && res_ctx->pipe_ctx[i].top_pipe->plane_state == pln) + || pipes[pipe_cnt].pipe.dest.odm_combine != dm_odm_combine_mode_disabled; + + /* stereo is not split */ + if (pln->stereo_format == PLANE_STEREO_FORMAT_SIDE_BY_SIDE || + pln->stereo_format == PLANE_STEREO_FORMAT_TOP_AND_BOTTOM) { + pipes[pipe_cnt].pipe.src.is_hsplit = false; + pipes[pipe_cnt].pipe.src.hsplit_grp = res_ctx->pipe_ctx[i].pipe_idx; + } + + pipes[pipe_cnt].pipe.src.source_scan = pln->rotation == ROTATION_ANGLE_90 + || pln->rotation == ROTATION_ANGLE_270 ? dm_vert : dm_horz; + pipes[pipe_cnt].pipe.src.viewport_y_y = scl->viewport.y; + pipes[pipe_cnt].pipe.src.viewport_y_c = scl->viewport_c.y; + pipes[pipe_cnt].pipe.src.viewport_width = scl->viewport.width; + pipes[pipe_cnt].pipe.src.viewport_width_c = scl->viewport_c.width; + pipes[pipe_cnt].pipe.src.viewport_height = scl->viewport.height; + pipes[pipe_cnt].pipe.src.viewport_height_c = scl->viewport_c.height; + pipes[pipe_cnt].pipe.src.viewport_width_max = pln->src_rect.width; + pipes[pipe_cnt].pipe.src.viewport_height_max = pln->src_rect.height; + pipes[pipe_cnt].pipe.src.surface_width_y = pln->plane_size.surface_size.width; + pipes[pipe_cnt].pipe.src.surface_height_y = pln->plane_size.surface_size.height; + pipes[pipe_cnt].pipe.src.surface_width_c = pln->plane_size.chroma_size.width; + pipes[pipe_cnt].pipe.src.surface_height_c = pln->plane_size.chroma_size.height; + if (pln->format == SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA + || pln->format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) { + pipes[pipe_cnt].pipe.src.data_pitch = pln->plane_size.surface_pitch; + pipes[pipe_cnt].pipe.src.data_pitch_c = pln->plane_size.chroma_pitch; + pipes[pipe_cnt].pipe.src.meta_pitch = pln->dcc.meta_pitch; + pipes[pipe_cnt].pipe.src.meta_pitch_c = pln->dcc.meta_pitch_c; + } else { + pipes[pipe_cnt].pipe.src.data_pitch = pln->plane_size.surface_pitch; + pipes[pipe_cnt].pipe.src.meta_pitch = pln->dcc.meta_pitch; + } + pipes[pipe_cnt].pipe.src.dcc = pln->dcc.enable; + pipes[pipe_cnt].pipe.dest.recout_width = scl->recout.width; + pipes[pipe_cnt].pipe.dest.recout_height = scl->recout.height; + pipes[pipe_cnt].pipe.dest.full_recout_height = scl->recout.height; + pipes[pipe_cnt].pipe.dest.full_recout_width = scl->recout.width; + if (pipes[pipe_cnt].pipe.dest.odm_combine == dm_odm_combine_mode_2to1) + pipes[pipe_cnt].pipe.dest.full_recout_width *= 2; + else if (pipes[pipe_cnt].pipe.dest.odm_combine == dm_odm_combine_mode_4to1) + pipes[pipe_cnt].pipe.dest.full_recout_width *= 4; + else { + struct pipe_ctx *split_pipe = res_ctx->pipe_ctx[i].bottom_pipe; + + while (split_pipe && split_pipe->plane_state == pln) { + pipes[pipe_cnt].pipe.dest.full_recout_width += split_pipe->plane_res.scl_data.recout.width; + split_pipe = split_pipe->bottom_pipe; + } + split_pipe = res_ctx->pipe_ctx[i].top_pipe; + while (split_pipe && split_pipe->plane_state == pln) { + pipes[pipe_cnt].pipe.dest.full_recout_width += split_pipe->plane_res.scl_data.recout.width; + split_pipe = split_pipe->top_pipe; + } + } + + pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_16; + pipes[pipe_cnt].pipe.scale_ratio_depth.hscl_ratio = (double) scl->ratios.horz.value / (1ULL<<32); + pipes[pipe_cnt].pipe.scale_ratio_depth.hscl_ratio_c = (double) scl->ratios.horz_c.value / (1ULL<<32); + pipes[pipe_cnt].pipe.scale_ratio_depth.vscl_ratio = (double) scl->ratios.vert.value / (1ULL<<32); + pipes[pipe_cnt].pipe.scale_ratio_depth.vscl_ratio_c = (double) scl->ratios.vert_c.value / (1ULL<<32); + pipes[pipe_cnt].pipe.scale_ratio_depth.scl_enable = + scl->ratios.vert.value != dc_fixpt_one.value + || scl->ratios.horz.value != dc_fixpt_one.value + || scl->ratios.vert_c.value != dc_fixpt_one.value + || scl->ratios.horz_c.value != dc_fixpt_one.value /*Lb only or Full scl*/ + || dc->debug.always_scale; /*support always scale*/ + pipes[pipe_cnt].pipe.scale_taps.htaps = scl->taps.h_taps; + pipes[pipe_cnt].pipe.scale_taps.htaps_c = scl->taps.h_taps_c; + pipes[pipe_cnt].pipe.scale_taps.vtaps = scl->taps.v_taps; + pipes[pipe_cnt].pipe.scale_taps.vtaps_c = scl->taps.v_taps_c; + + pipes[pipe_cnt].pipe.src.macro_tile_size = + swizzle_mode_to_macro_tile_size(pln->tiling_info.gfx9.swizzle); + swizzle_to_dml_params(pln->tiling_info.gfx9.swizzle, + &pipes[pipe_cnt].pipe.src.sw_mode); + + switch (pln->format) { + case SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr: + case SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb: + pipes[pipe_cnt].pipe.src.source_format = dm_420_8; + break; + case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr: + case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb: + pipes[pipe_cnt].pipe.src.source_format = dm_420_10; + break; + case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616: + case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616: + case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F: + case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F: + pipes[pipe_cnt].pipe.src.source_format = dm_444_64; + break; + case SURFACE_PIXEL_FORMAT_GRPH_ARGB1555: + case SURFACE_PIXEL_FORMAT_GRPH_RGB565: + pipes[pipe_cnt].pipe.src.source_format = dm_444_16; + break; + case SURFACE_PIXEL_FORMAT_GRPH_PALETA_256_COLORS: + pipes[pipe_cnt].pipe.src.source_format = dm_444_8; + break; + case SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA: + pipes[pipe_cnt].pipe.src.source_format = dm_rgbe_alpha; + break; + default: + pipes[pipe_cnt].pipe.src.source_format = dm_444_32; + break; + } + } + + pipe_cnt++; + } + + /* populate writeback information */ + DC_FP_START(); + dc->res_pool->funcs->populate_dml_writeback_from_context(dc, res_ctx, pipes); + DC_FP_END(); + + return pipe_cnt; +} + +void dcn20_calculate_wm( + struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int *out_pipe_cnt, + int *pipe_split_from, + int vlevel, + bool fast_validate) +{ + int pipe_cnt, i, pipe_idx; + + dc_assert_fp_enabled(); + + for (i = 0, pipe_idx = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { + if (!context->res_ctx.pipe_ctx[i].stream) + continue; + + pipes[pipe_cnt].clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0; + pipes[pipe_cnt].clks_cfg.dispclk_mhz = context->bw_ctx.dml.vba.RequiredDISPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; + + if (pipe_split_from[i] < 0) { + pipes[pipe_cnt].clks_cfg.dppclk_mhz = + context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx]; + if (context->bw_ctx.dml.vba.BlendingAndTiming[pipe_idx] == pipe_idx) + pipes[pipe_cnt].pipe.dest.odm_combine = + context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx]; + else + pipes[pipe_cnt].pipe.dest.odm_combine = 0; + pipe_idx++; + } else { + pipes[pipe_cnt].clks_cfg.dppclk_mhz = + context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_split_from[i]]; + if (context->bw_ctx.dml.vba.BlendingAndTiming[pipe_split_from[i]] == pipe_split_from[i]) + pipes[pipe_cnt].pipe.dest.odm_combine = + context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_split_from[i]]; + else + pipes[pipe_cnt].pipe.dest.odm_combine = 0; + } + + if (dc->config.forced_clocks) { + pipes[pipe_cnt].clks_cfg.dispclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dispclk_mhz; + pipes[pipe_cnt].clks_cfg.dppclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dppclk_mhz; + } + if (dc->debug.min_disp_clk_khz > pipes[pipe_cnt].clks_cfg.dispclk_mhz * 1000) + pipes[pipe_cnt].clks_cfg.dispclk_mhz = dc->debug.min_disp_clk_khz / 1000.0; + if (dc->debug.min_dpp_clk_khz > pipes[pipe_cnt].clks_cfg.dppclk_mhz * 1000) + pipes[pipe_cnt].clks_cfg.dppclk_mhz = dc->debug.min_dpp_clk_khz / 1000.0; + + pipe_cnt++; + } + + if (pipe_cnt != pipe_idx) { + if (dc->res_pool->funcs->populate_dml_pipes) + pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, + context, pipes, fast_validate); + else + pipe_cnt = dcn20_populate_dml_pipes_from_context(dc, + context, pipes, fast_validate); + } + + *out_pipe_cnt = pipe_cnt; + + pipes[0].clks_cfg.voltage = vlevel; + pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].dcfclk_mhz; + pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].socclk_mhz; + + /* only pipe 0 is read for voltage and dcf/soc clocks */ + if (vlevel < 1) { + pipes[0].clks_cfg.voltage = 1; + pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[1].dcfclk_mhz; + pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[1].socclk_mhz; + } + context->bw_ctx.bw.dcn.watermarks.b.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.b.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.b.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + + if (vlevel < 2) { + pipes[0].clks_cfg.voltage = 2; + pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[2].dcfclk_mhz; + pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[2].socclk_mhz; + } + context->bw_ctx.bw.dcn.watermarks.c.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + + if (vlevel < 3) { + pipes[0].clks_cfg.voltage = 3; + pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[2].dcfclk_mhz; + pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[2].socclk_mhz; + } + context->bw_ctx.bw.dcn.watermarks.d.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.d.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + + pipes[0].clks_cfg.voltage = vlevel; + pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].dcfclk_mhz; + pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].socclk_mhz; + context->bw_ctx.bw.dcn.watermarks.a.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; +} + +void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb, + struct pp_smu_nv_clock_table *max_clocks, unsigned int *uclk_states, unsigned int num_states) +{ + struct _vcs_dpi_voltage_scaling_st calculated_states[DC__VOLTAGE_STATES]; + int i; + int num_calculated_states = 0; + int min_dcfclk = 0; + + dc_assert_fp_enabled(); + + if (num_states == 0) + return; + + memset(calculated_states, 0, sizeof(calculated_states)); + + if (dc->bb_overrides.min_dcfclk_mhz > 0) + min_dcfclk = dc->bb_overrides.min_dcfclk_mhz; + else { + if (ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) + min_dcfclk = 310; + else + // Accounting for SOC/DCF relationship, we can go as high as + // 506Mhz in Vmin. + min_dcfclk = 506; + } + + for (i = 0; i < num_states; i++) { + int min_fclk_required_by_uclk; + calculated_states[i].state = i; + calculated_states[i].dram_speed_mts = uclk_states[i] * 16 / 1000; + + // FCLK:UCLK ratio is 1.08 + min_fclk_required_by_uclk = div_u64(((unsigned long long)uclk_states[i]) * 1080, + 1000000); + + calculated_states[i].fabricclk_mhz = (min_fclk_required_by_uclk < min_dcfclk) ? + min_dcfclk : min_fclk_required_by_uclk; + + calculated_states[i].socclk_mhz = (calculated_states[i].fabricclk_mhz > max_clocks->socClockInKhz / 1000) ? + max_clocks->socClockInKhz / 1000 : calculated_states[i].fabricclk_mhz; + + calculated_states[i].dcfclk_mhz = (calculated_states[i].fabricclk_mhz > max_clocks->dcfClockInKhz / 1000) ? + max_clocks->dcfClockInKhz / 1000 : calculated_states[i].fabricclk_mhz; + + calculated_states[i].dispclk_mhz = max_clocks->displayClockInKhz / 1000; + calculated_states[i].dppclk_mhz = max_clocks->displayClockInKhz / 1000; + calculated_states[i].dscclk_mhz = max_clocks->displayClockInKhz / (1000 * 3); + + calculated_states[i].phyclk_mhz = max_clocks->phyClockInKhz / 1000; + + num_calculated_states++; + } + + calculated_states[num_calculated_states - 1].socclk_mhz = max_clocks->socClockInKhz / 1000; + calculated_states[num_calculated_states - 1].fabricclk_mhz = max_clocks->socClockInKhz / 1000; + calculated_states[num_calculated_states - 1].dcfclk_mhz = max_clocks->dcfClockInKhz / 1000; + + memcpy(bb->clock_limits, calculated_states, sizeof(bb->clock_limits)); + bb->num_states = num_calculated_states; + + // Duplicate the last state, DML always an extra state identical to max state to work + memcpy(&bb->clock_limits[num_calculated_states], &bb->clock_limits[num_calculated_states - 1], sizeof(struct _vcs_dpi_voltage_scaling_st)); + bb->clock_limits[num_calculated_states].state = bb->num_states; +} + +void dcn20_cap_soc_clocks( + struct _vcs_dpi_soc_bounding_box_st *bb, + struct pp_smu_nv_clock_table max_clocks) +{ + int i; + + dc_assert_fp_enabled(); + + // First pass - cap all clocks higher than the reported max + for (i = 0; i < bb->num_states; i++) { + if ((bb->clock_limits[i].dcfclk_mhz > (max_clocks.dcfClockInKhz / 1000)) + && max_clocks.dcfClockInKhz != 0) + bb->clock_limits[i].dcfclk_mhz = (max_clocks.dcfClockInKhz / 1000); + + if ((bb->clock_limits[i].dram_speed_mts > (max_clocks.uClockInKhz / 1000) * 16) + && max_clocks.uClockInKhz != 0) + bb->clock_limits[i].dram_speed_mts = (max_clocks.uClockInKhz / 1000) * 16; + + if ((bb->clock_limits[i].fabricclk_mhz > (max_clocks.fabricClockInKhz / 1000)) + && max_clocks.fabricClockInKhz != 0) + bb->clock_limits[i].fabricclk_mhz = (max_clocks.fabricClockInKhz / 1000); + + if ((bb->clock_limits[i].dispclk_mhz > (max_clocks.displayClockInKhz / 1000)) + && max_clocks.displayClockInKhz != 0) + bb->clock_limits[i].dispclk_mhz = (max_clocks.displayClockInKhz / 1000); + + if ((bb->clock_limits[i].dppclk_mhz > (max_clocks.dppClockInKhz / 1000)) + && max_clocks.dppClockInKhz != 0) + bb->clock_limits[i].dppclk_mhz = (max_clocks.dppClockInKhz / 1000); + + if ((bb->clock_limits[i].phyclk_mhz > (max_clocks.phyClockInKhz / 1000)) + && max_clocks.phyClockInKhz != 0) + bb->clock_limits[i].phyclk_mhz = (max_clocks.phyClockInKhz / 1000); + + if ((bb->clock_limits[i].socclk_mhz > (max_clocks.socClockInKhz / 1000)) + && max_clocks.socClockInKhz != 0) + bb->clock_limits[i].socclk_mhz = (max_clocks.socClockInKhz / 1000); + + if ((bb->clock_limits[i].dscclk_mhz > (max_clocks.dscClockInKhz / 1000)) + && max_clocks.dscClockInKhz != 0) + bb->clock_limits[i].dscclk_mhz = (max_clocks.dscClockInKhz / 1000); + } + + // Second pass - remove all duplicate clock states + for (i = bb->num_states - 1; i > 1; i--) { + bool duplicate = true; + + if (bb->clock_limits[i-1].dcfclk_mhz != bb->clock_limits[i].dcfclk_mhz) + duplicate = false; + if (bb->clock_limits[i-1].dispclk_mhz != bb->clock_limits[i].dispclk_mhz) + duplicate = false; + if (bb->clock_limits[i-1].dppclk_mhz != bb->clock_limits[i].dppclk_mhz) + duplicate = false; + if (bb->clock_limits[i-1].dram_speed_mts != bb->clock_limits[i].dram_speed_mts) + duplicate = false; + if (bb->clock_limits[i-1].dscclk_mhz != bb->clock_limits[i].dscclk_mhz) + duplicate = false; + if (bb->clock_limits[i-1].fabricclk_mhz != bb->clock_limits[i].fabricclk_mhz) + duplicate = false; + if (bb->clock_limits[i-1].phyclk_mhz != bb->clock_limits[i].phyclk_mhz) + duplicate = false; + if (bb->clock_limits[i-1].socclk_mhz != bb->clock_limits[i].socclk_mhz) + duplicate = false; + + if (duplicate) + bb->num_states--; + } +} + +void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb) +{ + dc_assert_fp_enabled(); + + if ((int)(bb->sr_exit_time_us * 1000) != dc->bb_overrides.sr_exit_time_ns + && dc->bb_overrides.sr_exit_time_ns) { + bb->sr_exit_time_us = dc->bb_overrides.sr_exit_time_ns / 1000.0; + } + + if ((int)(bb->sr_enter_plus_exit_time_us * 1000) + != dc->bb_overrides.sr_enter_plus_exit_time_ns + && dc->bb_overrides.sr_enter_plus_exit_time_ns) { + bb->sr_enter_plus_exit_time_us = + dc->bb_overrides.sr_enter_plus_exit_time_ns / 1000.0; + } + + if ((int)(bb->urgent_latency_us * 1000) != dc->bb_overrides.urgent_latency_ns + && dc->bb_overrides.urgent_latency_ns) { + bb->urgent_latency_us = dc->bb_overrides.urgent_latency_ns / 1000.0; + } + + if ((int)(bb->dram_clock_change_latency_us * 1000) + != dc->bb_overrides.dram_clock_change_latency_ns + && dc->bb_overrides.dram_clock_change_latency_ns) { + bb->dram_clock_change_latency_us = + dc->bb_overrides.dram_clock_change_latency_ns / 1000.0; + } + + if ((int)(bb->dummy_pstate_latency_us * 1000) + != dc->bb_overrides.dummy_clock_change_latency_ns + && dc->bb_overrides.dummy_clock_change_latency_ns) { + bb->dummy_pstate_latency_us = + dc->bb_overrides.dummy_clock_change_latency_ns / 1000.0; + } +} + +static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *context, + bool fast_validate) +{ + bool out = false; + + BW_VAL_TRACE_SETUP(); + + int vlevel = 0; + int pipe_split_from[MAX_PIPES]; + int pipe_cnt = 0; + display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC); + DC_LOGGER_INIT(dc->ctx->logger); + + BW_VAL_TRACE_COUNT(); + + out = dcn20_fast_validate_bw(dc, context, pipes, &pipe_cnt, pipe_split_from, &vlevel, fast_validate); + + if (pipe_cnt == 0) + goto validate_out; + + if (!out) + goto validate_fail; + + BW_VAL_TRACE_END_VOLTAGE_LEVEL(); + + if (fast_validate) { + BW_VAL_TRACE_SKIP(fast); + goto validate_out; + } + + dcn20_calculate_wm(dc, context, pipes, &pipe_cnt, pipe_split_from, vlevel, fast_validate); + dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); + + BW_VAL_TRACE_END_WATERMARKS(); + + goto validate_out; + +validate_fail: + DC_LOG_WARNING("Mode Validation Warning: %s failed validation.\n", + dml_get_status_message(context->bw_ctx.dml.vba.ValidationStatus[context->bw_ctx.dml.vba.soc.num_states])); + + BW_VAL_TRACE_SKIP(fail); + out = false; + +validate_out: + kfree(pipes); + + BW_VAL_TRACE_FINISH(); + + return out; +} + +bool dcn20_validate_bandwidth_fp(struct dc *dc, + struct dc_state *context, + bool fast_validate) +{ + bool voltage_supported = false; + bool full_pstate_supported = false; + bool dummy_pstate_supported = false; + double p_state_latency_us; + + dc_assert_fp_enabled(); + + p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us; + context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support = + dc->debug.disable_dram_clock_change_vactive_support; + context->bw_ctx.dml.soc.allow_dram_clock_one_display_vactive = + dc->debug.enable_dram_clock_change_one_display_vactive; + + /*Unsafe due to current pipe merge and split logic*/ + ASSERT(context != dc->current_state); + + if (fast_validate) { + return dcn20_validate_bandwidth_internal(dc, context, true); + } + + // Best case, we support full UCLK switch latency + voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false); + full_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support; + + if (context->bw_ctx.dml.soc.dummy_pstate_latency_us == 0 || + (voltage_supported && full_pstate_supported)) { + context->bw_ctx.bw.dcn.clk.p_state_change_support = full_pstate_supported; + goto restore_dml_state; + } + + // Fallback: Try to only support G6 temperature read latency + context->bw_ctx.dml.soc.dram_clock_change_latency_us = context->bw_ctx.dml.soc.dummy_pstate_latency_us; + + voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false); + dummy_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support; + + if (voltage_supported && (dummy_pstate_supported || !(context->stream_count))) { + context->bw_ctx.bw.dcn.clk.p_state_change_support = false; + goto restore_dml_state; + } + + // ERROR: fallback is supposed to always work. + ASSERT(false); + +restore_dml_state: + context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us; + return voltage_supported; +} + +void dcn20_fpu_set_wm_ranges(int i, + struct pp_smu_wm_range_sets *ranges, + struct _vcs_dpi_soc_bounding_box_st *loaded_bb) +{ + dc_assert_fp_enabled(); + + ranges->reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0; + ranges->reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16; +} + +void dcn20_fpu_adjust_dppclk(struct vba_vars_st *v, + int vlevel, + int max_mpc_comb, + int pipe_idx, + bool is_validating_bw) +{ + dc_assert_fp_enabled(); + + if (is_validating_bw) + v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] *= 2; + else + v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] /= 2; +} + +int dcn21_populate_dml_pipes_from_context(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + bool fast_validate) +{ + uint32_t pipe_cnt; + int i; + + dc_assert_fp_enabled(); + + pipe_cnt = dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); + + for (i = 0; i < pipe_cnt; i++) { + + pipes[i].pipe.src.hostvm = dc->res_pool->hubbub->riommu_active; + pipes[i].pipe.src.gpuvm = 1; + } + + return pipe_cnt; +} + +static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb) +{ + int i; + + if (dc->bb_overrides.sr_exit_time_ns) { + for (i = 0; i < WM_SET_COUNT; i++) { + dc->clk_mgr->bw_params->wm_table.entries[i].sr_exit_time_us = + dc->bb_overrides.sr_exit_time_ns / 1000.0; + } + } + + if (dc->bb_overrides.sr_enter_plus_exit_time_ns) { + for (i = 0; i < WM_SET_COUNT; i++) { + dc->clk_mgr->bw_params->wm_table.entries[i].sr_enter_plus_exit_time_us = + dc->bb_overrides.sr_enter_plus_exit_time_ns / 1000.0; + } + } + + if (dc->bb_overrides.urgent_latency_ns) { + bb->urgent_latency_us = dc->bb_overrides.urgent_latency_ns / 1000.0; + } + + if (dc->bb_overrides.dram_clock_change_latency_ns) { + for (i = 0; i < WM_SET_COUNT; i++) { + dc->clk_mgr->bw_params->wm_table.entries[i].pstate_latency_us = + dc->bb_overrides.dram_clock_change_latency_ns / 1000.0; + } + } +} + +static void calculate_wm_set_for_vlevel(int vlevel, + struct wm_range_table_entry *table_entry, + struct dcn_watermarks *wm_set, + struct display_mode_lib *dml, + display_e2e_pipe_params_st *pipes, + int pipe_cnt) +{ + double dram_clock_change_latency_cached = dml->soc.dram_clock_change_latency_us; + + ASSERT(vlevel < dml->soc.num_states); + /* only pipe 0 is read for voltage and dcf/soc clocks */ + pipes[0].clks_cfg.voltage = vlevel; + pipes[0].clks_cfg.dcfclk_mhz = dml->soc.clock_limits[vlevel].dcfclk_mhz; + pipes[0].clks_cfg.socclk_mhz = dml->soc.clock_limits[vlevel].socclk_mhz; + + dml->soc.dram_clock_change_latency_us = table_entry->pstate_latency_us; + dml->soc.sr_exit_time_us = table_entry->sr_exit_time_us; + dml->soc.sr_enter_plus_exit_time_us = table_entry->sr_enter_plus_exit_time_us; + + wm_set->urgent_ns = get_wm_urgent(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(dml, pipes, pipe_cnt) * 1000; + wm_set->pte_meta_urgent_ns = get_wm_memory_trip(dml, pipes, pipe_cnt) * 1000; + wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000; + wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000; + wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000; + dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached; +} + +static void dcn21_calculate_wm(struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int *out_pipe_cnt, + int *pipe_split_from, + int vlevel_req, + bool fast_validate) +{ + int pipe_cnt, i, pipe_idx; + int vlevel, vlevel_max; + struct wm_range_table_entry *table_entry; + struct clk_bw_params *bw_params = dc->clk_mgr->bw_params; + + ASSERT(bw_params); + + patch_bounding_box(dc, &context->bw_ctx.dml.soc); + + for (i = 0, pipe_idx = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { + if (!context->res_ctx.pipe_ctx[i].stream) + continue; + + pipes[pipe_cnt].clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0; + pipes[pipe_cnt].clks_cfg.dispclk_mhz = context->bw_ctx.dml.vba.RequiredDISPCLK[vlevel_req][context->bw_ctx.dml.vba.maxMpcComb]; + + if (pipe_split_from[i] < 0) { + pipes[pipe_cnt].clks_cfg.dppclk_mhz = + context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel_req][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx]; + if (context->bw_ctx.dml.vba.BlendingAndTiming[pipe_idx] == pipe_idx) + pipes[pipe_cnt].pipe.dest.odm_combine = + context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel_req][pipe_idx]; + else + pipes[pipe_cnt].pipe.dest.odm_combine = 0; + pipe_idx++; + } else { + pipes[pipe_cnt].clks_cfg.dppclk_mhz = + context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel_req][context->bw_ctx.dml.vba.maxMpcComb][pipe_split_from[i]]; + if (context->bw_ctx.dml.vba.BlendingAndTiming[pipe_split_from[i]] == pipe_split_from[i]) + pipes[pipe_cnt].pipe.dest.odm_combine = + context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel_req][pipe_split_from[i]]; + else + pipes[pipe_cnt].pipe.dest.odm_combine = 0; + } + pipe_cnt++; + } + + if (pipe_cnt != pipe_idx) { + if (dc->res_pool->funcs->populate_dml_pipes) + pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, + context, pipes, fast_validate); + else + pipe_cnt = dcn21_populate_dml_pipes_from_context(dc, + context, pipes, fast_validate); + } + + *out_pipe_cnt = pipe_cnt; + + vlevel_max = bw_params->clk_table.num_entries - 1; + + + /* WM Set D */ + table_entry = &bw_params->wm_table.entries[WM_D]; + if (table_entry->wm_type == WM_TYPE_RETRAINING) + vlevel = 0; + else + vlevel = vlevel_max; + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.d, + &context->bw_ctx.dml, pipes, pipe_cnt); + /* WM Set C */ + table_entry = &bw_params->wm_table.entries[WM_C]; + vlevel = MIN(MAX(vlevel_req, 3), vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.c, + &context->bw_ctx.dml, pipes, pipe_cnt); + /* WM Set B */ + table_entry = &bw_params->wm_table.entries[WM_B]; + vlevel = MIN(MAX(vlevel_req, 2), vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.b, + &context->bw_ctx.dml, pipes, pipe_cnt); + + /* WM Set A */ + table_entry = &bw_params->wm_table.entries[WM_A]; + vlevel = MIN(vlevel_req, vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.a, + &context->bw_ctx.dml, pipes, pipe_cnt); +} + +bool dcn21_validate_bandwidth_fp(struct dc *dc, + struct dc_state *context, + bool fast_validate) +{ + bool out = false; + + BW_VAL_TRACE_SETUP(); + + int vlevel = 0; + int pipe_split_from[MAX_PIPES]; + int pipe_cnt = 0; + display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC); + DC_LOGGER_INIT(dc->ctx->logger); + + BW_VAL_TRACE_COUNT(); + + dc_assert_fp_enabled(); + + /*Unsafe due to current pipe merge and split logic*/ + ASSERT(context != dc->current_state); + + out = dcn21_fast_validate_bw(dc, context, pipes, &pipe_cnt, pipe_split_from, &vlevel, fast_validate); + + if (pipe_cnt == 0) + goto validate_out; + + if (!out) + goto validate_fail; + + BW_VAL_TRACE_END_VOLTAGE_LEVEL(); + + if (fast_validate) { + BW_VAL_TRACE_SKIP(fast); + goto validate_out; + } + + dcn21_calculate_wm(dc, context, pipes, &pipe_cnt, pipe_split_from, vlevel, fast_validate); + dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); + + BW_VAL_TRACE_END_WATERMARKS(); + + goto validate_out; + +validate_fail: + DC_LOG_WARNING("Mode Validation Warning: %s failed validation.\n", + dml_get_status_message(context->bw_ctx.dml.vba.ValidationStatus[context->bw_ctx.dml.vba.soc.num_states])); + + BW_VAL_TRACE_SKIP(fail); + out = false; + +validate_out: + kfree(pipes); + + BW_VAL_TRACE_FINISH(); + + return out; +} + +static struct _vcs_dpi_voltage_scaling_st construct_low_pstate_lvl(struct clk_limit_table *clk_table, unsigned int high_voltage_lvl) +{ + struct _vcs_dpi_voltage_scaling_st low_pstate_lvl; + int i; + + low_pstate_lvl.state = 1; + low_pstate_lvl.dcfclk_mhz = clk_table->entries[0].dcfclk_mhz; + low_pstate_lvl.fabricclk_mhz = clk_table->entries[0].fclk_mhz; + low_pstate_lvl.socclk_mhz = clk_table->entries[0].socclk_mhz; + low_pstate_lvl.dram_speed_mts = clk_table->entries[0].memclk_mhz * 2; + + low_pstate_lvl.dispclk_mhz = dcn2_1_soc.clock_limits[high_voltage_lvl].dispclk_mhz; + low_pstate_lvl.dppclk_mhz = dcn2_1_soc.clock_limits[high_voltage_lvl].dppclk_mhz; + low_pstate_lvl.dram_bw_per_chan_gbps = dcn2_1_soc.clock_limits[high_voltage_lvl].dram_bw_per_chan_gbps; + low_pstate_lvl.dscclk_mhz = dcn2_1_soc.clock_limits[high_voltage_lvl].dscclk_mhz; + low_pstate_lvl.dtbclk_mhz = dcn2_1_soc.clock_limits[high_voltage_lvl].dtbclk_mhz; + low_pstate_lvl.phyclk_d18_mhz = dcn2_1_soc.clock_limits[high_voltage_lvl].phyclk_d18_mhz; + low_pstate_lvl.phyclk_mhz = dcn2_1_soc.clock_limits[high_voltage_lvl].phyclk_mhz; + + for (i = clk_table->num_entries; i > 1; i--) + clk_table->entries[i] = clk_table->entries[i-1]; + clk_table->entries[1] = clk_table->entries[0]; + clk_table->num_entries++; + + return low_pstate_lvl; +} + +void dcn21_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) +{ + struct dcn21_resource_pool *pool = TO_DCN21_RES_POOL(dc->res_pool); + struct clk_limit_table *clk_table = &bw_params->clk_table; + struct _vcs_dpi_voltage_scaling_st clock_limits[DC__VOLTAGE_STATES]; + unsigned int i, closest_clk_lvl = 0, k = 0; + int j; + + dc_assert_fp_enabled(); + + dcn2_1_ip.max_num_otg = pool->base.res_cap->num_timing_generator; + dcn2_1_ip.max_num_dpp = pool->base.pipe_count; + dcn2_1_soc.num_chans = bw_params->num_channels; + + ASSERT(clk_table->num_entries); + /* Copy dcn2_1_soc.clock_limits to clock_limits to avoid copying over null states later */ + for (i = 0; i < dcn2_1_soc.num_states + 1; i++) { + clock_limits[i] = dcn2_1_soc.clock_limits[i]; + } + + for (i = 0; i < clk_table->num_entries; i++) { + /* loop backwards*/ + for (closest_clk_lvl = 0, j = dcn2_1_soc.num_states - 1; j >= 0; j--) { + if ((unsigned int) dcn2_1_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) { + closest_clk_lvl = j; + break; + } + } + + /* clk_table[1] is reserved for min DF PState. skip here to fill in later. */ + if (i == 1) + k++; + + clock_limits[k].state = k; + clock_limits[k].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz; + clock_limits[k].fabricclk_mhz = clk_table->entries[i].fclk_mhz; + clock_limits[k].socclk_mhz = clk_table->entries[i].socclk_mhz; + clock_limits[k].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2; + + clock_limits[k].dispclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dispclk_mhz; + clock_limits[k].dppclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dppclk_mhz; + clock_limits[k].dram_bw_per_chan_gbps = dcn2_1_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps; + clock_limits[k].dscclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dscclk_mhz; + clock_limits[k].dtbclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dtbclk_mhz; + clock_limits[k].phyclk_d18_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz; + clock_limits[k].phyclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_mhz; + + k++; + } + for (i = 0; i < clk_table->num_entries + 1; i++) + dcn2_1_soc.clock_limits[i] = clock_limits[i]; + if (clk_table->num_entries) { + dcn2_1_soc.num_states = clk_table->num_entries + 1; + /* fill in min DF PState */ + dcn2_1_soc.clock_limits[1] = construct_low_pstate_lvl(clk_table, closest_clk_lvl); + /* duplicate last level */ + dcn2_1_soc.clock_limits[dcn2_1_soc.num_states] = dcn2_1_soc.clock_limits[dcn2_1_soc.num_states - 1]; + dcn2_1_soc.clock_limits[dcn2_1_soc.num_states].state = dcn2_1_soc.num_states; + } + + dml_init_instance(&dc->dml, &dcn2_1_soc, &dcn2_1_ip, DML_PROJECT_DCN21); +} diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h index 36f26126d574..aa892193e485 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.h @@ -23,6 +23,7 @@ * Authors: AMD * */ +#include "core_types.h" #ifndef __DCN20_FPU_H__ #define __DCN20_FPU_H__ @@ -31,4 +32,54 @@ void dcn20_populate_dml_writeback_from_context(struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes); +void dcn20_fpu_set_wb_arb_params(struct mcif_arb_params *wb_arb_params, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, int i); +void dcn20_calculate_dlg_params(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel); +int dcn20_populate_dml_pipes_from_context(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + bool fast_validate); +void dcn20_calculate_wm(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int *out_pipe_cnt, + int *pipe_split_from, + int vlevel, + bool fast_validate); +void dcn20_cap_soc_clocks(struct _vcs_dpi_soc_bounding_box_st *bb, + struct pp_smu_nv_clock_table max_clocks); +void dcn20_update_bounding_box(struct dc *dc, + struct _vcs_dpi_soc_bounding_box_st *bb, + struct pp_smu_nv_clock_table *max_clocks, + unsigned int *uclk_states, + unsigned int num_states); +void dcn20_patch_bounding_box(struct dc *dc, + struct _vcs_dpi_soc_bounding_box_st *bb); +bool dcn20_validate_bandwidth_fp(struct dc *dc, + struct dc_state *context, + bool fast_validate); +void dcn20_fpu_set_wm_ranges(int i, + struct pp_smu_wm_range_sets *ranges, + struct _vcs_dpi_soc_bounding_box_st *loaded_bb); +void dcn20_fpu_adjust_dppclk(struct vba_vars_st *v, + int vlevel, + int max_mpc_comb, + int pipe_idx, + bool is_validating_bw); + +int dcn21_populate_dml_pipes_from_context(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + bool fast_validate); +bool dcn21_validate_bandwidth_fp(struct dc *dc, + struct dc_state *context, + bool fast_validate); +void dcn21_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params); + #endif /* __DCN20_FPU_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c new file mode 100644 index 000000000000..8fb14baed208 --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c @@ -0,0 +1,362 @@ +/* + * Copyright 2019-2021 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. + * + * Authors: AMD + * + */ +#include "resource.h" +#include "clk_mgr.h" +#include "dcn20/dcn20_resource.h" +#include "dcn303/dcn303_resource.h" + +#include "dml/dcn20/dcn20_fpu.h" +#include "dcn303_fpu.h" + +struct _vcs_dpi_ip_params_st dcn3_03_ip = { + .use_min_dcfclk = 0, + .clamp_min_dcfclk = 0, + .odm_capable = 1, + .gpuvm_enable = 1, + .hostvm_enable = 0, + .gpuvm_max_page_table_levels = 4, + .hostvm_max_page_table_levels = 4, + .hostvm_cached_page_table_levels = 0, + .pte_group_size_bytes = 2048, + .num_dsc = 2, + .rob_buffer_size_kbytes = 184, + .det_buffer_size_kbytes = 184, + .dpte_buffer_size_in_pte_reqs_luma = 64, + .dpte_buffer_size_in_pte_reqs_chroma = 34, + .pde_proc_buffer_size_64k_reqs = 48, + .dpp_output_buffer_pixels = 2560, + .opp_output_buffer_lines = 1, + .pixel_chunk_size_kbytes = 8, + .pte_enable = 1, + .max_page_table_levels = 2, + .pte_chunk_size_kbytes = 2, // ? + .meta_chunk_size_kbytes = 2, + .writeback_chunk_size_kbytes = 8, + .line_buffer_size_bits = 789504, + .is_line_buffer_bpp_fixed = 0, // ? + .line_buffer_fixed_bpp = 0, // ? + .dcc_supported = true, + .writeback_interface_buffer_size_kbytes = 90, + .writeback_line_buffer_buffer_size = 0, + .max_line_buffer_lines = 12, + .writeback_luma_buffer_size_kbytes = 12, // writeback_line_buffer_buffer_size = 656640 + .writeback_chroma_buffer_size_kbytes = 8, + .writeback_chroma_line_buffer_width_pixels = 4, + .writeback_max_hscl_ratio = 1, + .writeback_max_vscl_ratio = 1, + .writeback_min_hscl_ratio = 1, + .writeback_min_vscl_ratio = 1, + .writeback_max_hscl_taps = 1, + .writeback_max_vscl_taps = 1, + .writeback_line_buffer_luma_buffer_size = 0, + .writeback_line_buffer_chroma_buffer_size = 14643, + .cursor_buffer_size = 8, + .cursor_chunk_size = 2, + .max_num_otg = 2, + .max_num_dpp = 2, + .max_num_wb = 1, + .max_dchub_pscl_bw_pix_per_clk = 4, + .max_pscl_lb_bw_pix_per_clk = 2, + .max_lb_vscl_bw_pix_per_clk = 4, + .max_vscl_hscl_bw_pix_per_clk = 4, + .max_hscl_ratio = 6, + .max_vscl_ratio = 6, + .hscl_mults = 4, + .vscl_mults = 4, + .max_hscl_taps = 8, + .max_vscl_taps = 8, + .dispclk_ramp_margin_percent = 1, + .underscan_factor = 1.11, + .min_vblank_lines = 32, + .dppclk_delay_subtotal = 46, + .dynamic_metadata_vm_enabled = true, + .dppclk_delay_scl_lb_only = 16, + .dppclk_delay_scl = 50, + .dppclk_delay_cnvc_formatter = 27, + .dppclk_delay_cnvc_cursor = 6, + .dispclk_delay_subtotal = 119, + .dcfclk_cstate_latency = 5.2, // SRExitTime + .max_inter_dcn_tile_repeaters = 8, + .max_num_hdmi_frl_outputs = 1, + .odm_combine_4to1_supported = false, + + .xfc_supported = false, + .xfc_fill_bw_overhead_percent = 10.0, + .xfc_fill_constant_bytes = 0, + .gfx7_compat_tiling_supported = 0, + .number_of_cursors = 1, +}; + +struct _vcs_dpi_soc_bounding_box_st dcn3_03_soc = { + .clock_limits = { + { + .state = 0, + .dispclk_mhz = 562.0, + .dppclk_mhz = 300.0, + .phyclk_mhz = 300.0, + .phyclk_d18_mhz = 667.0, + .dscclk_mhz = 405.6, + }, + }, + + .min_dcfclk = 500.0, /* TODO: set this to actual min DCFCLK */ + .num_states = 1, + .sr_exit_time_us = 35.5, + .sr_enter_plus_exit_time_us = 40, + .urgent_latency_us = 4.0, + .urgent_latency_pixel_data_only_us = 4.0, + .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, + .urgent_latency_vm_data_only_us = 4.0, + .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, + .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, + .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 80.0, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 60.0, + .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, + .max_avg_sdp_bw_use_normal_percent = 60.0, + .max_avg_dram_bw_use_normal_percent = 40.0, + .writeback_latency_us = 12.0, + .max_request_size_bytes = 256, + .fabric_datapath_to_dcn_data_return_bytes = 64, + .dcn_downspread_percent = 0.5, + .downspread_percent = 0.38, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 156, + .urgent_out_of_order_return_per_channel_bytes = 4096, + .channel_interleave_bytes = 256, + .num_banks = 8, + .gpuvm_min_page_size_bytes = 4096, + .hostvm_min_page_size_bytes = 4096, + .dram_clock_change_latency_us = 404, + .dummy_pstate_latency_us = 5, + .writeback_dram_clock_change_latency_us = 23.0, + .return_bus_width_bytes = 64, + .dispclk_dppclk_vco_speed_mhz = 3650, + .xfc_bus_transport_time_us = 20, // ? + .xfc_xbuf_latency_tolerance_us = 4, // ? + .use_urgent_burst_bw = 1, // ? + .do_urgent_latency_adjustment = true, + .urgent_latency_adjustment_fabric_clock_component_us = 1.0, + .urgent_latency_adjustment_fabric_clock_reference_mhz = 1000, +}; + +static void dcn303_get_optimal_dcfclk_fclk_for_uclk(unsigned int uclk_mts, + unsigned int *optimal_dcfclk, + unsigned int *optimal_fclk) +{ + double bw_from_dram, bw_from_dram1, bw_from_dram2; + + bw_from_dram1 = uclk_mts * dcn3_03_soc.num_chans * + dcn3_03_soc.dram_channel_width_bytes * (dcn3_03_soc.max_avg_dram_bw_use_normal_percent / 100); + bw_from_dram2 = uclk_mts * dcn3_03_soc.num_chans * + dcn3_03_soc.dram_channel_width_bytes * (dcn3_03_soc.max_avg_sdp_bw_use_normal_percent / 100); + + bw_from_dram = (bw_from_dram1 < bw_from_dram2) ? bw_from_dram1 : bw_from_dram2; + + if (optimal_fclk) + *optimal_fclk = bw_from_dram / + (dcn3_03_soc.fabric_datapath_to_dcn_data_return_bytes * + (dcn3_03_soc.max_avg_sdp_bw_use_normal_percent / 100)); + + if (optimal_dcfclk) + *optimal_dcfclk = bw_from_dram / + (dcn3_03_soc.return_bus_width_bytes * (dcn3_03_soc.max_avg_sdp_bw_use_normal_percent / 100)); +} + + +void dcn303_fpu_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) +{ + unsigned int i, j; + unsigned int num_states = 0; + + unsigned int dcfclk_mhz[DC__VOLTAGE_STATES] = {0}; + unsigned int dram_speed_mts[DC__VOLTAGE_STATES] = {0}; + unsigned int optimal_uclk_for_dcfclk_sta_targets[DC__VOLTAGE_STATES] = {0}; + unsigned int optimal_dcfclk_for_uclk[DC__VOLTAGE_STATES] = {0}; + + unsigned int dcfclk_sta_targets[DC__VOLTAGE_STATES] = {694, 875, 1000, 1200}; + unsigned int num_dcfclk_sta_targets = 4; + unsigned int num_uclk_states; + + dc_assert_fp_enabled(); + + if (dc->ctx->dc_bios->vram_info.num_chans) + dcn3_03_soc.num_chans = dc->ctx->dc_bios->vram_info.num_chans; + + if (dc->ctx->dc_bios->vram_info.dram_channel_width_bytes) + dcn3_03_soc.dram_channel_width_bytes = dc->ctx->dc_bios->vram_info.dram_channel_width_bytes; + + dcn3_03_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; + dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; + + if (bw_params->clk_table.entries[0].memclk_mhz) { + int max_dcfclk_mhz = 0, max_dispclk_mhz = 0, max_dppclk_mhz = 0, max_phyclk_mhz = 0; + + for (i = 0; i < MAX_NUM_DPM_LVL; i++) { + if (bw_params->clk_table.entries[i].dcfclk_mhz > max_dcfclk_mhz) + max_dcfclk_mhz = bw_params->clk_table.entries[i].dcfclk_mhz; + if (bw_params->clk_table.entries[i].dispclk_mhz > max_dispclk_mhz) + max_dispclk_mhz = bw_params->clk_table.entries[i].dispclk_mhz; + if (bw_params->clk_table.entries[i].dppclk_mhz > max_dppclk_mhz) + max_dppclk_mhz = bw_params->clk_table.entries[i].dppclk_mhz; + if (bw_params->clk_table.entries[i].phyclk_mhz > max_phyclk_mhz) + max_phyclk_mhz = bw_params->clk_table.entries[i].phyclk_mhz; + } + if (!max_dcfclk_mhz) + max_dcfclk_mhz = dcn3_03_soc.clock_limits[0].dcfclk_mhz; + if (!max_dispclk_mhz) + max_dispclk_mhz = dcn3_03_soc.clock_limits[0].dispclk_mhz; + if (!max_dppclk_mhz) + max_dppclk_mhz = dcn3_03_soc.clock_limits[0].dppclk_mhz; + if (!max_phyclk_mhz) + max_phyclk_mhz = dcn3_03_soc.clock_limits[0].phyclk_mhz; + + if (max_dcfclk_mhz > dcfclk_sta_targets[num_dcfclk_sta_targets-1]) { + dcfclk_sta_targets[num_dcfclk_sta_targets] = max_dcfclk_mhz; + num_dcfclk_sta_targets++; + } else if (max_dcfclk_mhz < dcfclk_sta_targets[num_dcfclk_sta_targets-1]) { + for (i = 0; i < num_dcfclk_sta_targets; i++) { + if (dcfclk_sta_targets[i] > max_dcfclk_mhz) { + dcfclk_sta_targets[i] = max_dcfclk_mhz; + break; + } + } + /* Update size of array since we "removed" duplicates */ + num_dcfclk_sta_targets = i + 1; + } + + num_uclk_states = bw_params->clk_table.num_entries; + + /* Calculate optimal dcfclk for each uclk */ + for (i = 0; i < num_uclk_states; i++) { + dcn303_get_optimal_dcfclk_fclk_for_uclk(bw_params->clk_table.entries[i].memclk_mhz * 16, + &optimal_dcfclk_for_uclk[i], NULL); + if (optimal_dcfclk_for_uclk[i] < bw_params->clk_table.entries[0].dcfclk_mhz) + optimal_dcfclk_for_uclk[i] = bw_params->clk_table.entries[0].dcfclk_mhz; + } + + /* Calculate optimal uclk for each dcfclk sta target */ + for (i = 0; i < num_dcfclk_sta_targets; i++) { + for (j = 0; j < num_uclk_states; j++) { + if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j]) { + optimal_uclk_for_dcfclk_sta_targets[i] = + bw_params->clk_table.entries[j].memclk_mhz * 16; + break; + } + } + } + + i = 0; + j = 0; + /* create the final dcfclk and uclk table */ + while (i < num_dcfclk_sta_targets && j < num_uclk_states && num_states < DC__VOLTAGE_STATES) { + if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j] && i < num_dcfclk_sta_targets) { + dcfclk_mhz[num_states] = dcfclk_sta_targets[i]; + dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++]; + } else { + if (j < num_uclk_states && optimal_dcfclk_for_uclk[j] <= max_dcfclk_mhz) { + dcfclk_mhz[num_states] = optimal_dcfclk_for_uclk[j]; + dram_speed_mts[num_states++] = + bw_params->clk_table.entries[j++].memclk_mhz * 16; + } else { + j = num_uclk_states; + } + } + } + + while (i < num_dcfclk_sta_targets && num_states < DC__VOLTAGE_STATES) { + dcfclk_mhz[num_states] = dcfclk_sta_targets[i]; + dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++]; + } + + while (j < num_uclk_states && num_states < DC__VOLTAGE_STATES && + optimal_dcfclk_for_uclk[j] <= max_dcfclk_mhz) { + dcfclk_mhz[num_states] = optimal_dcfclk_for_uclk[j]; + dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16; + } + + dcn3_03_soc.num_states = num_states; + for (i = 0; i < dcn3_03_soc.num_states; i++) { + dcn3_03_soc.clock_limits[i].state = i; + dcn3_03_soc.clock_limits[i].dcfclk_mhz = dcfclk_mhz[i]; + dcn3_03_soc.clock_limits[i].fabricclk_mhz = dcfclk_mhz[i]; + dcn3_03_soc.clock_limits[i].dram_speed_mts = dram_speed_mts[i]; + + /* Fill all states with max values of all other clocks */ + dcn3_03_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz; + dcn3_03_soc.clock_limits[i].dppclk_mhz = max_dppclk_mhz; + dcn3_03_soc.clock_limits[i].phyclk_mhz = max_phyclk_mhz; + /* Populate from bw_params for DTBCLK, SOCCLK */ + if (!bw_params->clk_table.entries[i].dtbclk_mhz && i > 0) + dcn3_03_soc.clock_limits[i].dtbclk_mhz = dcn3_03_soc.clock_limits[i-1].dtbclk_mhz; + else + dcn3_03_soc.clock_limits[i].dtbclk_mhz = bw_params->clk_table.entries[i].dtbclk_mhz; + if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0) + dcn3_03_soc.clock_limits[i].socclk_mhz = dcn3_03_soc.clock_limits[i-1].socclk_mhz; + else + dcn3_03_soc.clock_limits[i].socclk_mhz = bw_params->clk_table.entries[i].socclk_mhz; + /* These clocks cannot come from bw_params, always fill from dcn3_03_soc[1] */ + /* FCLK, PHYCLK_D18, DSCCLK */ + dcn3_03_soc.clock_limits[i].phyclk_d18_mhz = dcn3_03_soc.clock_limits[0].phyclk_d18_mhz; + dcn3_03_soc.clock_limits[i].dscclk_mhz = dcn3_03_soc.clock_limits[0].dscclk_mhz; + } + + if (dcn3_03_soc.num_chans <= 4) { + for (i = 0; i < dcn3_03_soc.num_states; i++) { + if (dcn3_03_soc.clock_limits[i].dram_speed_mts > 1700) + break; + + if (dcn3_03_soc.clock_limits[i].dram_speed_mts >= 1500) { + dcn3_03_soc.clock_limits[i].dcfclk_mhz = 100; + dcn3_03_soc.clock_limits[i].fabricclk_mhz = 100; + } + } + } + + /* re-init DML with updated bb */ + dml_init_instance(&dc->dml, &dcn3_03_soc, &dcn3_03_ip, DML_PROJECT_DCN30); + if (dc->current_state) + dml_init_instance(&dc->current_state->bw_ctx.dml, &dcn3_03_soc, &dcn3_03_ip, DML_PROJECT_DCN30); + } +} + +void dcn303_fpu_init_soc_bounding_box(struct bp_soc_bb_info bb_info) +{ + dc_assert_fp_enabled(); + + if (bb_info.dram_clock_change_latency_100ns > 0) + dcn3_03_soc.dram_clock_change_latency_us = + bb_info.dram_clock_change_latency_100ns * 10; + + if (bb_info.dram_sr_enter_exit_latency_100ns > 0) + dcn3_03_soc.sr_enter_plus_exit_time_us = + bb_info.dram_sr_enter_exit_latency_100ns * 10; + + if (bb_info.dram_sr_exit_latency_100ns > 0) + dcn3_03_soc.sr_exit_time_us = + bb_info.dram_sr_exit_latency_100ns * 10; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c b/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.h index 42413813765a..92ec833fa528 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.h @@ -1,5 +1,5 @@ /* - * Copyright 2019 Advanced Micro Devices, Inc. + * Copyright 2019-2021 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"), @@ -19,14 +19,14 @@ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR * OTHER DEALINGS IN THE SOFTWARE. * + * Authors: AMD + * */ -#include "amdgpu.h" -#include "amdgpu_ras.h" +#ifndef __DCN303_FPU_H__ +#define __DCN303_FPU_H__ + +void dcn303_fpu_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params); +void dcn303_fpu_init_soc_bounding_box(struct bp_soc_bb_info bb_info); -void amdgpu_mmhub_ras_fini(struct amdgpu_device *adev) -{ - if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__MMHUB) && - adev->mmhub.ras_if) - amdgpu_ras_block_late_fini(adev, adev->mmhub.ras_if); -} +#endif /* __DCN303_FPU_H__*/ diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c index dae8e489c8cf..778c206f754d 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c @@ -647,7 +647,9 @@ enum gpio_result dal_ddc_set_config( void dal_ddc_close( struct ddc *ddc) { - dal_gpio_close(ddc->pin_clock); - dal_gpio_close(ddc->pin_data); + if (ddc != NULL) { + dal_gpio_close(ddc->pin_clock); + dal_gpio_close(ddc->pin_data); + } } diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h index 713f5558f5e1..9195dec294c2 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h @@ -154,6 +154,8 @@ struct hubbub_funcs { bool (*is_allow_self_refresh_enabled)(struct hubbub *hubbub); void (*allow_self_refresh_control)(struct hubbub *hubbub, bool allow); + bool (*verify_allow_pstate_change_high)(struct hubbub *hubbub); + void (*apply_DEDCN21_147_wa)(struct hubbub *hubbub); void (*force_wm_propagate_to_pipes)(struct hubbub *hubbub); diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index 2c031586f4e6..e45b7993c5c5 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -195,6 +195,7 @@ struct hubp_funcs { void (*hubp_set_flip_int)(struct hubp *hubp); + void (*hubp_wait_pipe_read_start)(struct hubp *hubp); }; #endif diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h index 48eac622c6a0..24af9d80b937 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h @@ -39,6 +39,7 @@ struct panel_cntl_backlight_registers { unsigned int BL_PWM_CNTL2; unsigned int BL_PWM_PERIOD_CNTL; unsigned int LVTMA_PWRSEQ_REF_DIV_BL_PWM_REF_DIV; + unsigned int PANEL_PWRSEQ_REF_DIV2; }; struct panel_cntl_funcs { diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h index 280c8764b636..8c2f190c4712 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h @@ -42,6 +42,7 @@ struct dce_hwseq_wa { bool DEGVIDCN21; bool disallow_self_refresh_during_multi_plane_transition; bool dp_hpo_and_otg_sequence; + bool wait_hubpret_read_start_during_mpo_transition; }; struct hwseq_wa_state { diff --git a/drivers/gpu/drm/amd/display/dc/inc/link_enc_cfg.h b/drivers/gpu/drm/amd/display/dc/inc/link_enc_cfg.h index c2f08514a1d9..c6f6baa6e677 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/link_enc_cfg.h +++ b/drivers/gpu/drm/amd/display/dc/inc/link_enc_cfg.h @@ -40,6 +40,11 @@ void link_enc_cfg_init( struct dc_state *state); /* + * Copies a link encoder assignment from another state. + */ +void link_enc_cfg_copy(const struct dc_state *src_ctx, struct dc_state *dst_ctx); + +/* * Algorithm for assigning available DIG link encoders to streams. * * Update link_enc_assignments table and link_enc_avail list accordingly in diff --git a/drivers/gpu/drm/amd/display/dc/link/Makefile b/drivers/gpu/drm/amd/display/dc/link/Makefile index c4a69ba7cb62..054c2a727eb2 100644 --- a/drivers/gpu/drm/amd/display/dc/link/Makefile +++ b/drivers/gpu/drm/amd/display/dc/link/Makefile @@ -23,7 +23,7 @@ # It abstracts the control and status of back end pipe such as DIO, HPO, DPIA, # PHY, HPD, DDC and etc). -LINK = link_hwss_dio.o link_hwss_dpia.o link_hwss_hpo_dp.o +LINK = link_hwss_dio.o link_hwss_dpia.o link_hwss_hpo_dp.o link_dp_trace.o AMD_DAL_LINK = $(addprefix $(AMDDALPATH)/dc/link/,$(LINK)) diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dp_trace.c b/drivers/gpu/drm/amd/display/dc/link/link_dp_trace.c new file mode 100644 index 000000000000..e7047391934b --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/link/link_dp_trace.c @@ -0,0 +1,146 @@ +/* + * Copyright 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. + * + * Authors: AMD + * + */ +#include "dc_link.h" +#include "link_dp_trace.h" + +void dp_trace_init(struct dc_link *link) +{ + memset(&link->dp_trace, 0, sizeof(link->dp_trace)); + link->dp_trace.is_initialized = true; +} + +void dp_trace_reset(struct dc_link *link) +{ + memset(&link->dp_trace, 0, sizeof(link->dp_trace)); +} + +bool dc_dp_trace_is_initialized(struct dc_link *link) +{ + return link->dp_trace.is_initialized; +} + +void dp_trace_detect_lt_init(struct dc_link *link) +{ + memset(&link->dp_trace.detect_lt_trace, 0, sizeof(link->dp_trace.detect_lt_trace)); +} + +void dp_trace_commit_lt_init(struct dc_link *link) +{ + memset(&link->dp_trace.commit_lt_trace, 0, sizeof(link->dp_trace.commit_lt_trace)); +} + +void dp_trace_link_loss_increment(struct dc_link *link) +{ + link->dp_trace.link_loss_count++; +} + +void dp_trace_lt_fail_count_update(struct dc_link *link, + unsigned int fail_count, + bool in_detection) +{ + if (in_detection) + link->dp_trace.detect_lt_trace.counts.fail = fail_count; + else + link->dp_trace.commit_lt_trace.counts.fail = fail_count; +} + +void dp_trace_lt_total_count_increment(struct dc_link *link, + bool in_detection) +{ + if (in_detection) + link->dp_trace.detect_lt_trace.counts.total++; + else + link->dp_trace.commit_lt_trace.counts.total++; +} + +void dc_dp_trace_set_is_logged_flag(struct dc_link *link, + bool in_detection, + bool is_logged) +{ + if (in_detection) + link->dp_trace.detect_lt_trace.is_logged = is_logged; + else + link->dp_trace.commit_lt_trace.is_logged = is_logged; +} + +bool dc_dp_trace_is_logged(struct dc_link *link, + bool in_detection) +{ + if (in_detection) + return link->dp_trace.detect_lt_trace.is_logged; + else + return link->dp_trace.commit_lt_trace.is_logged; +} + +void dp_trace_lt_result_update(struct dc_link *link, + enum link_training_result result, + bool in_detection) +{ + if (in_detection) + link->dp_trace.detect_lt_trace.result = result; + else + link->dp_trace.commit_lt_trace.result = result; +} + +void dp_trace_set_lt_start_timestamp(struct dc_link *link, + bool in_detection) +{ + if (in_detection) + link->dp_trace.detect_lt_trace.timestamps.start = dm_get_timestamp(link->dc->ctx); + else + link->dp_trace.commit_lt_trace.timestamps.start = dm_get_timestamp(link->dc->ctx); +} + +void dp_trace_set_lt_end_timestamp(struct dc_link *link, + bool in_detection) +{ + if (in_detection) + link->dp_trace.detect_lt_trace.timestamps.end = dm_get_timestamp(link->dc->ctx); + else + link->dp_trace.commit_lt_trace.timestamps.end = dm_get_timestamp(link->dc->ctx); +} + +unsigned long long dc_dp_trace_get_lt_end_timestamp(struct dc_link *link, + bool in_detection) +{ + if (in_detection) + return link->dp_trace.detect_lt_trace.timestamps.end; + else + return link->dp_trace.commit_lt_trace.timestamps.end; +} + +struct dp_trace_lt_counts *dc_dp_trace_get_lt_counts(struct dc_link *link, + bool in_detection) +{ + if (in_detection) + return &link->dp_trace.detect_lt_trace.counts; + else + return &link->dp_trace.commit_lt_trace.counts; +} + +unsigned int dc_dp_trace_get_link_loss_count(struct dc_link *link) +{ + return link->dp_trace.link_loss_count; +} diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dp_trace.h b/drivers/gpu/drm/amd/display/dc/link/link_dp_trace.h new file mode 100644 index 000000000000..702f97c6ead0 --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/link/link_dp_trace.h @@ -0,0 +1,57 @@ +/* + * Copyright 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. + * + * Authors: AMD + * + */ +#ifndef __LINK_DP_TRACE_H__ +#define __LINK_DP_TRACE_H__ + +void dp_trace_init(struct dc_link *link); +void dp_trace_reset(struct dc_link *link); +bool dc_dp_trace_is_initialized(struct dc_link *link); +void dp_trace_detect_lt_init(struct dc_link *link); +void dp_trace_commit_lt_init(struct dc_link *link); +void dp_trace_link_loss_increment(struct dc_link *link); +void dp_trace_lt_fail_count_update(struct dc_link *link, + unsigned int fail_count, + bool in_detection); +void dp_trace_lt_total_count_increment(struct dc_link *link, + bool in_detection); +void dc_dp_trace_set_is_logged_flag(struct dc_link *link, + bool in_detection, + bool is_logged); +bool dc_dp_trace_is_logged(struct dc_link *link, + bool in_detection); +void dp_trace_lt_result_update(struct dc_link *link, + enum link_training_result result, + bool in_detection); +void dp_trace_set_lt_start_timestamp(struct dc_link *link, + bool in_detection); +void dp_trace_set_lt_end_timestamp(struct dc_link *link, + bool in_detection); +unsigned long long dc_dp_trace_get_lt_end_timestamp(struct dc_link *link, + bool in_detection); +struct dp_trace_lt_counts *dc_dp_trace_get_lt_counts(struct dc_link *link, + bool in_detection); +unsigned int dc_dp_trace_get_link_loss_count(struct dc_link *link); + +#endif /* __LINK_DP_TRACE_H__ */ 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 34fb148474cc..71214c7a60fc 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -46,10 +46,10 @@ /* Firmware versioning. */ #ifdef DMUB_EXPOSE_VERSION -#define DMUB_FW_VERSION_GIT_HASH 0x1422ef84 +#define DMUB_FW_VERSION_GIT_HASH 0x929554ba #define DMUB_FW_VERSION_MAJOR 0 #define DMUB_FW_VERSION_MINOR 0 -#define DMUB_FW_VERSION_REVISION 104 +#define DMUB_FW_VERSION_REVISION 108 #define DMUB_FW_VERSION_TEST 0 #define DMUB_FW_VERSION_VBIOS 0 #define DMUB_FW_VERSION_HOTFIX 0 @@ -1450,6 +1450,80 @@ enum dmub_cmd_mall_type { DMUB_CMD__MALL_ACTION_NO_DF_REQ = 3, }; +/** + * PHY Link rate for DP. + */ +enum phy_link_rate { + /** + * not supported. + */ + PHY_RATE_UNKNOWN = 0, + /** + * Rate_1 (RBR) - 1.62 Gbps/Lane + */ + PHY_RATE_162 = 1, + /** + * Rate_2 - 2.16 Gbps/Lane + */ + PHY_RATE_216 = 2, + /** + * Rate_3 - 2.43 Gbps/Lane + */ + PHY_RATE_243 = 3, + /** + * Rate_4 (HBR) - 2.70 Gbps/Lane + */ + PHY_RATE_270 = 4, + /** + * Rate_5 (RBR2)- 3.24 Gbps/Lane + */ + PHY_RATE_324 = 5, + /** + * Rate_6 - 4.32 Gbps/Lane + */ + PHY_RATE_432 = 6, + /** + * Rate_7 (HBR2)- 5.40 Gbps/Lane + */ + PHY_RATE_540 = 7, + /** + * Rate_8 (HBR3)- 8.10 Gbps/Lane + */ + PHY_RATE_810 = 8, + /** + * UHBR10 - 10.0 Gbps/Lane + */ + PHY_RATE_1000 = 9, + /** + * UHBR13.5 - 13.5 Gbps/Lane + */ + PHY_RATE_1350 = 10, + /** + * UHBR10 - 20.0 Gbps/Lane + */ + PHY_RATE_2000 = 11, +}; + +/** + * enum dmub_phy_fsm_state - PHY FSM states. + * PHY FSM state to transit to during PSR enable/disable. + */ +enum dmub_phy_fsm_state { + DMUB_PHY_FSM_POWER_UP_DEFAULT = 0, + DMUB_PHY_FSM_RESET, + DMUB_PHY_FSM_RESET_RELEASED, + DMUB_PHY_FSM_SRAM_LOAD_DONE, + DMUB_PHY_FSM_INITIALIZED, + DMUB_PHY_FSM_CALIBRATED, + DMUB_PHY_FSM_CALIBRATED_LP, + DMUB_PHY_FSM_CALIBRATED_PG, + DMUB_PHY_FSM_POWER_DOWN, + DMUB_PHY_FSM_PLL_EN, + DMUB_PHY_FSM_TX_EN, + DMUB_PHY_FSM_FAST_LP, +}; + + /** * Data passed from driver to FW in a DMUB_CMD__PSR_COPY_SETTINGS command. @@ -1560,10 +1634,14 @@ struct dmub_cmd_psr_copy_settings_data { * DSC enable status in driver */ uint8_t dsc_enable_status; + /* + * Use FSM state for PSR power up/down + */ + uint8_t use_phy_fsm; /** - * Explicit padding to 3 byte boundary. + * Explicit padding to 2 byte boundary. */ - uint8_t pad3[3]; + uint8_t pad3[2]; }; /** @@ -1694,9 +1772,16 @@ struct dmub_cmd_psr_force_static_data { */ uint8_t panel_inst; /** - * Explicit padding to 4 byte boundary. + * Phy state to enter. + * Values to use are defined in dmub_phy_fsm_state */ - uint8_t pad[2]; + uint8_t phy_fsm_state; + /** + * Phy rate for DP - RBR/HBR/HBR2/HBR3. + * Set this using enum phy_link_rate. + * This does not support HDMI/DP2 for now. + */ + uint8_t phy_rate; }; /** @@ -2373,6 +2458,9 @@ struct dmub_cmd_panel_cntl_data { uint32_t bl_pwm_ref_div1; /* in/out */ uint8_t is_backlight_on : 1; /* in/out */ uint8_t is_powered_on : 1; /* in/out */ + uint8_t padding[3]; + uint32_t bl_pwm_ref_div2; /* in/out */ + uint8_t reserved[4]; }; /** diff --git a/drivers/gpu/drm/amd/display/include/ddc_service_types.h b/drivers/gpu/drm/amd/display/include/ddc_service_types.h index f561e213bf98..f883d87791fe 100644 --- a/drivers/gpu/drm/amd/display/include/ddc_service_types.h +++ b/drivers/gpu/drm/amd/display/include/ddc_service_types.h @@ -64,6 +64,7 @@ enum ddc_service_type { struct display_sink_capability { /* dongle type (DP converter, CV smart dongle) */ enum display_dongle_type dongle_type; + bool is_dongle_type_one; /********************************************************** capabilities going INTO SINK DEVICE (stream capabilities) diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h index dd974c428d23..bc96d0211360 100644 --- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h +++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h @@ -419,28 +419,6 @@ struct integrated_info { struct edp_info edp2_info; }; -/** -* Power source ids. -*/ -enum power_source { - POWER_SOURCE_AC = 0, - POWER_SOURCE_DC, - POWER_SOURCE_LIMITED_POWER, - POWER_SOURCE_LIMITED_POWER_2, - POWER_SOURCE_MAX -}; - -struct bios_event_info { - uint32_t thermal_state; - uint32_t backlight_level; - enum power_source powerSource; - bool has_thermal_state_changed; - bool has_power_source_changed; - bool has_forced_mode_changed; - bool forced_mode; - bool backlight_changed; -}; - /* * DFS-bypass flag */ diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 1d63f1e8884c..89fbee568be4 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -507,6 +507,18 @@ int amdgpu_dpm_send_hbm_bad_pages_num(struct amdgpu_device *adev, uint32_t size) return ret; } +int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t size) +{ + struct smu_context *smu = adev->powerplay.pp_handle; + int ret = 0; + + mutex_lock(&adev->pm.mutex); + ret = smu_send_hbm_bad_channel_flag(smu, size); + mutex_unlock(&adev->pm.mutex); + + return ret; +} + int amdgpu_dpm_get_dpm_freq_range(struct amdgpu_device *adev, enum pp_clock_type type, uint32_t *min, @@ -631,11 +643,16 @@ int amdgpu_dpm_get_ecc_info(struct amdgpu_device *adev, void *umc_ecc) { struct smu_context *smu = adev->powerplay.pp_handle; + int ret = 0; if (!is_support_sw_smu(adev)) return -EOPNOTSUPP; - return smu_get_ecc_info(smu, umc_ecc); + mutex_lock(&adev->pm.mutex); + ret = smu_get_ecc_info(smu, umc_ecc); + mutex_unlock(&adev->pm.mutex); + + return ret; } struct amd_vce_state *amdgpu_dpm_get_vce_clock_state(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index cbbbd4079249..5cd67ddf8495 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -1870,7 +1870,7 @@ static ssize_t amdgpu_set_smartshift_bias(struct device *dev, amdgpu_smartshift_bias = bias; r = count; - /* TODO: upadte bias level with SMU message */ + /* TODO: update bias level with SMU message */ out: pm_runtime_mark_last_busy(ddev->dev); diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h index ddfa55b59d02..3e78b3057277 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h @@ -412,6 +412,7 @@ void amdgpu_dpm_enable_jpeg(struct amdgpu_device *adev, bool enable); int amdgpu_pm_load_smu_firmware(struct amdgpu_device *adev, uint32_t *smu_version); int amdgpu_dpm_handle_passthrough_sbr(struct amdgpu_device *adev, bool enable); int amdgpu_dpm_send_hbm_bad_pages_num(struct amdgpu_device *adev, uint32_t size); +int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t size); int amdgpu_dpm_get_dpm_freq_range(struct amdgpu_device *adev, enum pp_clock_type type, uint32_t *min, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index 3f040be0d158..37324f2009ca 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -3095,7 +3095,7 @@ static int vega10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr, void *pp_table, uint32_t classification_flag) { ATOM_Vega10_GFXCLK_Dependency_Record_V2 *patom_record_V2; - struct vega10_power_state *vega10_power_state = + struct vega10_power_state *vega10_ps = cast_phw_vega10_power_state(&(power_state->hardware)); struct vega10_performance_level *performance_level; ATOM_Vega10_State *state_entry = (ATOM_Vega10_State *)state; @@ -3145,17 +3145,17 @@ static int vega10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr, power_state->temperatures.min = 0; power_state->temperatures.max = 0; - performance_level = &(vega10_power_state->performance_levels - [vega10_power_state->performance_level_count++]); + performance_level = &(vega10_ps->performance_levels + [vega10_ps->performance_level_count++]); PP_ASSERT_WITH_CODE( - (vega10_power_state->performance_level_count < + (vega10_ps->performance_level_count < NUM_GFXCLK_DPM_LEVELS), "Performance levels exceeds SMC limit!", return -1); PP_ASSERT_WITH_CODE( - (vega10_power_state->performance_level_count <= + (vega10_ps->performance_level_count <= hwmgr->platform_descriptor. hardwareActivityPerformanceLevels), "Performance levels exceeds Driver limit!", @@ -3169,8 +3169,8 @@ static int vega10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr, performance_level->mem_clock = mclk_dep_table->entries [state_entry->ucMemClockIndexLow].ulMemClk; - performance_level = &(vega10_power_state->performance_levels - [vega10_power_state->performance_level_count++]); + performance_level = &(vega10_ps->performance_levels + [vega10_ps->performance_level_count++]); performance_level->soc_clock = socclk_dep_table->entries [state_entry->ucSocClockIndexHigh].ulClk; if (gfxclk_dep_table->ucRevId == 0) { @@ -3201,11 +3201,11 @@ static int vega10_get_pp_table_entry(struct pp_hwmgr *hwmgr, unsigned long entry_index, struct pp_power_state *state) { int result; - struct vega10_power_state *ps; + struct vega10_power_state *vega10_ps; state->hardware.magic = PhwVega10_Magic; - ps = cast_phw_vega10_power_state(&state->hardware); + vega10_ps = cast_phw_vega10_power_state(&state->hardware); result = vega10_get_powerplay_table_entry(hwmgr, entry_index, state, vega10_get_pp_table_entry_callback_func); @@ -3218,10 +3218,10 @@ static int vega10_get_pp_table_entry(struct pp_hwmgr *hwmgr, */ /* set DC compatible flag if this state supports DC */ if (!state->validation.disallowOnDC) - ps->dc_compatible = true; + vega10_ps->dc_compatible = true; - ps->uvd_clks.vclk = state->uvd_clocks.VCLK; - ps->uvd_clks.dclk = state->uvd_clocks.DCLK; + vega10_ps->uvd_clks.vclk = state->uvd_clocks.VCLK; + vega10_ps->uvd_clks.dclk = state->uvd_clocks.DCLK; return 0; } @@ -4823,33 +4823,41 @@ static int vega10_check_states_equal(struct pp_hwmgr *hwmgr, const struct pp_hw_power_state *pstate1, const struct pp_hw_power_state *pstate2, bool *equal) { - const struct vega10_power_state *psa; - const struct vega10_power_state *psb; + const struct vega10_power_state *vega10_psa; + const struct vega10_power_state *vega10_psb; int i; if (pstate1 == NULL || pstate2 == NULL || equal == NULL) return -EINVAL; - psa = cast_const_phw_vega10_power_state(pstate1); - psb = cast_const_phw_vega10_power_state(pstate2); - /* If the two states don't even have the same number of performance levels they cannot be the same state. */ - if (psa->performance_level_count != psb->performance_level_count) { + vega10_psa = cast_const_phw_vega10_power_state(pstate1); + vega10_psb = cast_const_phw_vega10_power_state(pstate2); + + /* If the two states don't even have the same number of performance levels + * they cannot be the same state. + */ + if (vega10_psa->performance_level_count != vega10_psb->performance_level_count) { *equal = false; return 0; } - for (i = 0; i < psa->performance_level_count; i++) { - if (!vega10_are_power_levels_equal(&(psa->performance_levels[i]), &(psb->performance_levels[i]))) { - /* If we have found even one performance level pair that is different the states are different. */ + for (i = 0; i < vega10_psa->performance_level_count; i++) { + if (!vega10_are_power_levels_equal(&(vega10_psa->performance_levels[i]), + &(vega10_psb->performance_levels[i]))) { + /* If we have found even one performance level pair + * that is different the states are different. + */ *equal = false; return 0; } } /* If all performance levels are the same try to use the UVD clocks to break the tie.*/ - *equal = ((psa->uvd_clks.vclk == psb->uvd_clks.vclk) && (psa->uvd_clks.dclk == psb->uvd_clks.dclk)); - *equal &= ((psa->vce_clks.evclk == psb->vce_clks.evclk) && (psa->vce_clks.ecclk == psb->vce_clks.ecclk)); - *equal &= (psa->sclk_threshold == psb->sclk_threshold); + *equal = ((vega10_psa->uvd_clks.vclk == vega10_psb->uvd_clks.vclk) && + (vega10_psa->uvd_clks.dclk == vega10_psb->uvd_clks.dclk)); + *equal &= ((vega10_psa->vce_clks.evclk == vega10_psb->vce_clks.evclk) && + (vega10_psa->vce_clks.ecclk == vega10_psb->vce_clks.ecclk)); + *equal &= (vega10_psa->sclk_threshold == vega10_psb->sclk_threshold); return 0; } @@ -5444,19 +5452,19 @@ static int vega10_get_performance_level(struct pp_hwmgr *hwmgr, const struct pp_ PHM_PerformanceLevelDesignation designation, uint32_t index, PHM_PerformanceLevel *level) { - const struct vega10_power_state *ps; + const struct vega10_power_state *vega10_ps; uint32_t i; if (level == NULL || hwmgr == NULL || state == NULL) return -EINVAL; - ps = cast_const_phw_vega10_power_state(state); + vega10_ps = cast_const_phw_vega10_power_state(state); - i = index > ps->performance_level_count - 1 ? - ps->performance_level_count - 1 : index; + i = index > vega10_ps->performance_level_count - 1 ? + vega10_ps->performance_level_count - 1 : index; - level->coreClock = ps->performance_levels[i].gfx_clock; - level->memory_clock = ps->performance_levels[i].mem_clock; + level->coreClock = vega10_ps->performance_levels[i].gfx_clock; + level->memory_clock = vega10_ps->performance_levels[i].mem_clock; return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 7e79a67bb8ef..f1544755d8b4 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -3052,3 +3052,13 @@ int smu_send_hbm_bad_pages_num(struct smu_context *smu, uint32_t size) return ret; } + +int smu_send_hbm_bad_channel_flag(struct smu_context *smu, uint32_t size) +{ + int ret = 0; + + if (smu->ppt_funcs && smu->ppt_funcs->send_hbm_bad_channel_flag) + ret = smu->ppt_funcs->send_hbm_bad_channel_flag(smu, size); + + return ret; +} 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 fbef3ab8d487..ef57b6089c69 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -1292,6 +1292,12 @@ struct pptable_funcs { * @set_config_table: Apply the input DriverSmuConfig table settings. */ int (*set_config_table)(struct smu_context *smu, struct config_table_setting *table); + + /** + * @sned_hbm_bad_channel_flag: message SMU to update bad channel info + * of SMUBUS table. + */ + int (*send_hbm_bad_channel_flag)(struct smu_context *smu, uint32_t size); }; typedef enum { @@ -1428,5 +1434,6 @@ int smu_get_ecc_info(struct smu_context *smu, void *umc_ecc); int smu_stb_collect_info(struct smu_context *smu, void *buff, uint32_t size); void amdgpu_smu_stb_debug_fs_init(struct amdgpu_device *adev); 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); #endif #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/aldebaran_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/aldebaran_ppsmc.h index ab66a4b9e438..0f498baf6838 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/aldebaran_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/aldebaran_ppsmc.h @@ -103,7 +103,8 @@ #define PPSMC_MSG_GfxDriverResetRecovery 0x42 #define PPSMC_MSG_BoardPowerCalibration 0x43 #define PPSMC_MSG_HeavySBR 0x45 -#define PPSMC_Message_Count 0x46 +#define PPSMC_MSG_SetBadHBMPagesRetiredFlagsPerChannel 0x46 +#define PPSMC_Message_Count 0x47 //PPSMC Reset Types diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu11_driver_if_sienna_cichlid.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu11_driver_if_sienna_cichlid.h index b253be602cc2..3e4a314ef925 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu11_driver_if_sienna_cichlid.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu11_driver_if_sienna_cichlid.h @@ -1481,9 +1481,67 @@ typedef struct { } SmuMetrics_V2_t; typedef struct { + uint32_t CurrClock[PPCLK_COUNT]; + + uint16_t AverageGfxclkFrequencyPreDs; + uint16_t AverageGfxclkFrequencyPostDs; + uint16_t AverageFclkFrequencyPreDs; + uint16_t AverageFclkFrequencyPostDs; + uint16_t AverageUclkFrequencyPreDs; + uint16_t AverageUclkFrequencyPostDs; + + + uint16_t AverageGfxActivity; + uint16_t AverageUclkActivity; + uint8_t CurrSocVoltageOffset; + uint8_t CurrGfxVoltageOffset; + uint8_t CurrMemVidOffset; + uint8_t Padding8; + uint16_t AverageSocketPower; + uint16_t TemperatureEdge; + uint16_t TemperatureHotspot; + uint16_t TemperatureMem; + uint16_t TemperatureVrGfx; + uint16_t TemperatureVrMem0; + uint16_t TemperatureVrMem1; + uint16_t TemperatureVrSoc; + uint16_t TemperatureLiquid0; + uint16_t TemperatureLiquid1; + uint16_t TemperaturePlx; + uint16_t Padding16; + uint32_t AccCnt; + uint8_t ThrottlingPercentage[THROTTLER_COUNT]; + + + uint8_t LinkDpmLevel; + uint8_t CurrFanPwm; + uint16_t CurrFanSpeed; + + //BACO metrics, PMFW-1721 + //metrics for D3hot entry/exit and driver ARM msgs + uint8_t D3HotEntryCountPerMode[D3HOT_SEQUENCE_COUNT]; + uint8_t D3HotExitCountPerMode[D3HOT_SEQUENCE_COUNT]; + uint8_t ArmMsgReceivedCountPerMode[D3HOT_SEQUENCE_COUNT]; + + //PMFW-4362 + uint32_t EnergyAccumulator; + uint16_t AverageVclk0Frequency; + uint16_t AverageDclk0Frequency; + uint16_t AverageVclk1Frequency; + uint16_t AverageDclk1Frequency; + uint16_t VcnUsagePercentage0; + uint16_t VcnUsagePercentage1; + uint8_t PcieRate; + uint8_t PcieWidth; + uint16_t AverageGfxclkFrequencyTarget; + +} SmuMetrics_V3_t; + +typedef struct { union { SmuMetrics_t SmuMetrics; SmuMetrics_V2_t SmuMetrics_V2; + SmuMetrics_V3_t SmuMetrics_V3; }; uint32_t Spare[1]; 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 d787c3b9fc52..9f6f306eeca0 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h @@ -232,7 +232,8 @@ __SMU_DUMMY_MAP(ForceGfxVid), \ __SMU_DUMMY_MAP(Spare0), \ __SMU_DUMMY_MAP(UnforceGfxVid), \ - __SMU_DUMMY_MAP(HeavySBR), + __SMU_DUMMY_MAP(HeavySBR), \ + __SMU_DUMMY_MAP(SetBadHBMPagesRetiredFlagsPerChannel), #undef __SMU_DUMMY_MAP #define __SMU_DUMMY_MAP(type) SMU_MSG_##type diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index d9d634ce9575..38f04836c82f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -554,6 +554,11 @@ static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *s int i; if ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && + (smu->smc_fw_version >= 0x3A4900)) { + for (i = 0; i < THROTTLER_COUNT; i++) + throttler_status |= + (metrics_ext->SmuMetrics_V3.ThrottlingPercentage[i] ? 1U << i : 0); + } else if ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && (smu->smc_fw_version >= 0x3A4300)) { for (i = 0; i < THROTTLER_COUNT; i++) throttler_status |= @@ -574,11 +579,20 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu, &(((SmuMetricsExternal_t *)(smu_table->metrics_table))->SmuMetrics); SmuMetrics_V2_t *metrics_v2 = &(((SmuMetricsExternal_t *)(smu_table->metrics_table))->SmuMetrics_V2); - bool use_metrics_v2 = ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && - (smu->smc_fw_version >= 0x3A4300)) ? true : false; + SmuMetrics_V3_t *metrics_v3 = + &(((SmuMetricsExternal_t *)(smu_table->metrics_table))->SmuMetrics_V3); + bool use_metrics_v2 = false; + bool use_metrics_v3 = false; uint16_t average_gfx_activity; int ret = 0; + if ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && + (smu->smc_fw_version >= 0x3A4900)) + use_metrics_v3 = true; + else if ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && + (smu->smc_fw_version >= 0x3A4300)) + use_metrics_v2 = true; + ret = smu_cmn_get_metrics_table(smu, NULL, false); @@ -587,96 +601,119 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu, switch (member) { case METRICS_CURR_GFXCLK: - *value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_GFXCLK] : + *value = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_GFXCLK] : + use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_GFXCLK] : metrics->CurrClock[PPCLK_GFXCLK]; break; case METRICS_CURR_SOCCLK: - *value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_SOCCLK] : + *value = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_SOCCLK] : + use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_SOCCLK] : metrics->CurrClock[PPCLK_SOCCLK]; break; case METRICS_CURR_UCLK: - *value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_UCLK] : + *value = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_UCLK] : + use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_UCLK] : metrics->CurrClock[PPCLK_UCLK]; break; case METRICS_CURR_VCLK: - *value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_VCLK_0] : + *value = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_VCLK_0] : + use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_VCLK_0] : metrics->CurrClock[PPCLK_VCLK_0]; break; case METRICS_CURR_VCLK1: - *value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_VCLK_1] : + *value = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_VCLK_1] : + use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_VCLK_1] : metrics->CurrClock[PPCLK_VCLK_1]; break; case METRICS_CURR_DCLK: - *value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_0] : + *value = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_DCLK_0] : + use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_0] : metrics->CurrClock[PPCLK_DCLK_0]; break; case METRICS_CURR_DCLK1: - *value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_1] : + *value = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_DCLK_1] : + use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_1] : metrics->CurrClock[PPCLK_DCLK_1]; break; case METRICS_CURR_DCEFCLK: - *value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCEFCLK] : + *value = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_DCEFCLK] : + use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCEFCLK] : metrics->CurrClock[PPCLK_DCEFCLK]; break; case METRICS_CURR_FCLK: - *value = use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_FCLK] : + *value = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_FCLK] : + use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_FCLK] : metrics->CurrClock[PPCLK_FCLK]; break; case METRICS_AVERAGE_GFXCLK: - average_gfx_activity = use_metrics_v2 ? metrics_v2->AverageGfxActivity : + average_gfx_activity = use_metrics_v3 ? metrics_v3->AverageGfxActivity : + use_metrics_v2 ? metrics_v2->AverageGfxActivity : metrics->AverageGfxActivity; if (average_gfx_activity <= SMU_11_0_7_GFX_BUSY_THRESHOLD) - *value = use_metrics_v2 ? metrics_v2->AverageGfxclkFrequencyPostDs : + *value = use_metrics_v3 ? metrics_v3->AverageGfxclkFrequencyPostDs : + use_metrics_v2 ? metrics_v2->AverageGfxclkFrequencyPostDs : metrics->AverageGfxclkFrequencyPostDs; else - *value = use_metrics_v2 ? metrics_v2->AverageGfxclkFrequencyPreDs : + *value = use_metrics_v3 ? metrics_v3->AverageGfxclkFrequencyPreDs : + use_metrics_v2 ? metrics_v2->AverageGfxclkFrequencyPreDs : metrics->AverageGfxclkFrequencyPreDs; break; case METRICS_AVERAGE_FCLK: - *value = use_metrics_v2 ? metrics_v2->AverageFclkFrequencyPostDs : + *value = use_metrics_v3 ? metrics_v3->AverageFclkFrequencyPostDs : + use_metrics_v2 ? metrics_v2->AverageFclkFrequencyPostDs : metrics->AverageFclkFrequencyPostDs; break; case METRICS_AVERAGE_UCLK: - *value = use_metrics_v2 ? metrics_v2->AverageUclkFrequencyPostDs : + *value = use_metrics_v3 ? metrics_v3->AverageUclkFrequencyPostDs : + use_metrics_v2 ? metrics_v2->AverageUclkFrequencyPostDs : metrics->AverageUclkFrequencyPostDs; break; case METRICS_AVERAGE_GFXACTIVITY: - *value = use_metrics_v2 ? metrics_v2->AverageGfxActivity : + *value = use_metrics_v3 ? metrics_v3->AverageGfxActivity : + use_metrics_v2 ? metrics_v2->AverageGfxActivity : metrics->AverageGfxActivity; break; case METRICS_AVERAGE_MEMACTIVITY: - *value = use_metrics_v2 ? metrics_v2->AverageUclkActivity : + *value = use_metrics_v3 ? metrics_v3->AverageUclkActivity : + use_metrics_v2 ? metrics_v2->AverageUclkActivity : metrics->AverageUclkActivity; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = use_metrics_v2 ? metrics_v2->AverageSocketPower << 8 : + *value = use_metrics_v3 ? metrics_v3->AverageSocketPower << 8 : + use_metrics_v2 ? metrics_v2->AverageSocketPower << 8 : metrics->AverageSocketPower << 8; break; case METRICS_TEMPERATURE_EDGE: - *value = (use_metrics_v2 ? metrics_v2->TemperatureEdge : metrics->TemperatureEdge) * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + *value = (use_metrics_v3 ? metrics_v3->TemperatureEdge : + use_metrics_v2 ? metrics_v2->TemperatureEdge : + metrics->TemperatureEdge) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; case METRICS_TEMPERATURE_HOTSPOT: - *value = (use_metrics_v2 ? metrics_v2->TemperatureHotspot : metrics->TemperatureHotspot) * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + *value = (use_metrics_v3 ? metrics_v3->TemperatureHotspot : + use_metrics_v2 ? metrics_v2->TemperatureHotspot : + metrics->TemperatureHotspot) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; case METRICS_TEMPERATURE_MEM: - *value = (use_metrics_v2 ? metrics_v2->TemperatureMem : metrics->TemperatureMem) * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + *value = (use_metrics_v3 ? metrics_v3->TemperatureMem : + use_metrics_v2 ? metrics_v2->TemperatureMem : + metrics->TemperatureMem) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; case METRICS_TEMPERATURE_VRGFX: - *value = (use_metrics_v2 ? metrics_v2->TemperatureVrGfx : metrics->TemperatureVrGfx) * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + *value = (use_metrics_v3 ? metrics_v3->TemperatureVrGfx : + use_metrics_v2 ? metrics_v2->TemperatureVrGfx : + metrics->TemperatureVrGfx) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; case METRICS_TEMPERATURE_VRSOC: - *value = (use_metrics_v2 ? metrics_v2->TemperatureVrSoc : metrics->TemperatureVrSoc) * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + *value = (use_metrics_v3 ? metrics_v3->TemperatureVrSoc : + use_metrics_v2 ? metrics_v2->TemperatureVrSoc : + metrics->TemperatureVrSoc) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; case METRICS_THROTTLER_STATUS: *value = sienna_cichlid_get_throttler_status_locked(smu); break; case METRICS_CURR_FANSPEED: - *value = use_metrics_v2 ? metrics_v2->CurrFanSpeed : metrics->CurrFanSpeed; + *value = use_metrics_v3 ? metrics_v3->CurrFanSpeed : + use_metrics_v2 ? metrics_v2->CurrFanSpeed : metrics->CurrFanSpeed; break; default: *value = UINT_MAX; @@ -3656,12 +3693,22 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu, &(metrics_external.SmuMetrics); SmuMetrics_V2_t *metrics_v2 = &(metrics_external.SmuMetrics_V2); + SmuMetrics_V3_t *metrics_v3 = + &(metrics_external.SmuMetrics_V3); struct amdgpu_device *adev = smu->adev; - bool use_metrics_v2 = ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && - (smu->smc_fw_version >= 0x3A4300)) ? true : false; + bool use_metrics_v2 = false; + bool use_metrics_v3 = false; uint16_t average_gfx_activity; int ret = 0; + if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && + (smu->smc_fw_version >= 0x3A4900)) + use_metrics_v3 = true; + else if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && + (smu->smc_fw_version >= 0x3A4300)) + use_metrics_v2 = true; + + ret = smu_cmn_get_metrics_table(smu, &metrics_external, true); @@ -3670,29 +3717,30 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu, smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 3); - gpu_metrics->temperature_edge = + gpu_metrics->temperature_edge = use_metrics_v3 ? metrics_v3->TemperatureEdge : use_metrics_v2 ? metrics_v2->TemperatureEdge : metrics->TemperatureEdge; - gpu_metrics->temperature_hotspot = + gpu_metrics->temperature_hotspot = use_metrics_v3 ? metrics_v3->TemperatureHotspot : use_metrics_v2 ? metrics_v2->TemperatureHotspot : metrics->TemperatureHotspot; - gpu_metrics->temperature_mem = + gpu_metrics->temperature_mem = use_metrics_v3 ? metrics_v3->TemperatureMem : use_metrics_v2 ? metrics_v2->TemperatureMem : metrics->TemperatureMem; - gpu_metrics->temperature_vrgfx = + gpu_metrics->temperature_vrgfx = use_metrics_v3 ? metrics_v3->TemperatureVrGfx : use_metrics_v2 ? metrics_v2->TemperatureVrGfx : metrics->TemperatureVrGfx; - gpu_metrics->temperature_vrsoc = + gpu_metrics->temperature_vrsoc = use_metrics_v3 ? metrics_v3->TemperatureVrSoc : use_metrics_v2 ? metrics_v2->TemperatureVrSoc : metrics->TemperatureVrSoc; - gpu_metrics->temperature_vrmem = + gpu_metrics->temperature_vrmem = use_metrics_v3 ? metrics_v3->TemperatureVrMem0 : use_metrics_v2 ? metrics_v2->TemperatureVrMem0 : metrics->TemperatureVrMem0; - gpu_metrics->average_gfx_activity = + gpu_metrics->average_gfx_activity = use_metrics_v3 ? metrics_v3->AverageGfxActivity : use_metrics_v2 ? metrics_v2->AverageGfxActivity : metrics->AverageGfxActivity; - gpu_metrics->average_umc_activity = + gpu_metrics->average_umc_activity = use_metrics_v3 ? metrics_v3->AverageUclkActivity : use_metrics_v2 ? metrics_v2->AverageUclkActivity : metrics->AverageUclkActivity; - gpu_metrics->average_mm_activity = + gpu_metrics->average_mm_activity = use_metrics_v3 ? + (metrics_v3->VcnUsagePercentage0 + metrics_v3->VcnUsagePercentage1) / 2 : use_metrics_v2 ? metrics_v2->VcnActivityPercentage : metrics->VcnActivityPercentage; - gpu_metrics->average_socket_power = + gpu_metrics->average_socket_power = use_metrics_v3 ? metrics_v3->AverageSocketPower : use_metrics_v2 ? metrics_v2->AverageSocketPower : metrics->AverageSocketPower; - gpu_metrics->energy_accumulator = + gpu_metrics->energy_accumulator = use_metrics_v3 ? metrics_v3->EnergyAccumulator : use_metrics_v2 ? metrics_v2->EnergyAccumulator : metrics->EnergyAccumulator; if (metrics->CurrGfxVoltageOffset) @@ -3705,37 +3753,45 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu, gpu_metrics->voltage_soc = (155000 - 625 * metrics->CurrSocVoltageOffset) / 100; - average_gfx_activity = use_metrics_v2 ? metrics_v2->AverageGfxActivity : metrics->AverageGfxActivity; + average_gfx_activity = use_metrics_v3 ? metrics_v3->AverageGfxActivity : + use_metrics_v2 ? metrics_v2->AverageGfxActivity : metrics->AverageGfxActivity; if (average_gfx_activity <= SMU_11_0_7_GFX_BUSY_THRESHOLD) gpu_metrics->average_gfxclk_frequency = - use_metrics_v2 ? metrics_v2->AverageGfxclkFrequencyPostDs : metrics->AverageGfxclkFrequencyPostDs; + use_metrics_v3 ? metrics_v3->AverageGfxclkFrequencyPostDs : + use_metrics_v2 ? metrics_v2->AverageGfxclkFrequencyPostDs : + metrics->AverageGfxclkFrequencyPostDs; else gpu_metrics->average_gfxclk_frequency = - use_metrics_v2 ? metrics_v2->AverageGfxclkFrequencyPreDs : metrics->AverageGfxclkFrequencyPreDs; + use_metrics_v3 ? metrics_v3->AverageGfxclkFrequencyPreDs : + use_metrics_v2 ? metrics_v2->AverageGfxclkFrequencyPreDs : + metrics->AverageGfxclkFrequencyPreDs; + gpu_metrics->average_uclk_frequency = - use_metrics_v2 ? metrics_v2->AverageUclkFrequencyPostDs : metrics->AverageUclkFrequencyPostDs; - gpu_metrics->average_vclk0_frequency = + use_metrics_v3 ? metrics_v3->AverageUclkFrequencyPostDs : + use_metrics_v2 ? metrics_v2->AverageUclkFrequencyPostDs : + metrics->AverageUclkFrequencyPostDs; + gpu_metrics->average_vclk0_frequency = use_metrics_v3 ? metrics_v3->AverageVclk0Frequency : use_metrics_v2 ? metrics_v2->AverageVclk0Frequency : metrics->AverageVclk0Frequency; - gpu_metrics->average_dclk0_frequency = + gpu_metrics->average_dclk0_frequency = use_metrics_v3 ? metrics_v3->AverageDclk0Frequency : use_metrics_v2 ? metrics_v2->AverageDclk0Frequency : metrics->AverageDclk0Frequency; - gpu_metrics->average_vclk1_frequency = + gpu_metrics->average_vclk1_frequency = use_metrics_v3 ? metrics_v3->AverageVclk1Frequency : use_metrics_v2 ? metrics_v2->AverageVclk1Frequency : metrics->AverageVclk1Frequency; - gpu_metrics->average_dclk1_frequency = + gpu_metrics->average_dclk1_frequency = use_metrics_v3 ? metrics_v3->AverageDclk1Frequency : use_metrics_v2 ? metrics_v2->AverageDclk1Frequency : metrics->AverageDclk1Frequency; - gpu_metrics->current_gfxclk = + gpu_metrics->current_gfxclk = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_GFXCLK] : use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_GFXCLK] : metrics->CurrClock[PPCLK_GFXCLK]; - gpu_metrics->current_socclk = + gpu_metrics->current_socclk = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_SOCCLK] : use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_SOCCLK] : metrics->CurrClock[PPCLK_SOCCLK]; - gpu_metrics->current_uclk = + gpu_metrics->current_uclk = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_UCLK] : use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_UCLK] : metrics->CurrClock[PPCLK_UCLK]; - gpu_metrics->current_vclk0 = + gpu_metrics->current_vclk0 = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_VCLK_0] : use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_VCLK_0] : metrics->CurrClock[PPCLK_VCLK_0]; - gpu_metrics->current_dclk0 = + gpu_metrics->current_dclk0 = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_DCLK_0] : use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_0] : metrics->CurrClock[PPCLK_DCLK_0]; - gpu_metrics->current_vclk1 = + gpu_metrics->current_vclk1 = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_VCLK_1] : use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_VCLK_1] : metrics->CurrClock[PPCLK_VCLK_1]; - gpu_metrics->current_dclk1 = + gpu_metrics->current_dclk1 = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_DCLK_1] : use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_1] : metrics->CurrClock[PPCLK_DCLK_1]; gpu_metrics->throttle_status = sienna_cichlid_get_throttler_status_locked(smu); @@ -3743,12 +3799,15 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu, smu_cmn_get_indep_throttler_status(gpu_metrics->throttle_status, sienna_cichlid_throttler_map); - gpu_metrics->current_fan_speed = use_metrics_v2 ? metrics_v2->CurrFanSpeed : metrics->CurrFanSpeed; + gpu_metrics->current_fan_speed = use_metrics_v3 ? metrics_v3->CurrFanSpeed : + use_metrics_v2 ? metrics_v2->CurrFanSpeed : metrics->CurrFanSpeed; if (((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && smu->smc_fw_version > 0x003A1E00) || ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 11)) && smu->smc_fw_version > 0x00410400)) { - gpu_metrics->pcie_link_width = use_metrics_v2 ? metrics_v2->PcieWidth : metrics->PcieWidth; - gpu_metrics->pcie_link_speed = link_speed[use_metrics_v2 ? metrics_v2->PcieRate : metrics->PcieRate]; + gpu_metrics->pcie_link_width = use_metrics_v3 ? metrics_v3->PcieWidth : + use_metrics_v2 ? metrics_v2->PcieWidth : metrics->PcieWidth; + gpu_metrics->pcie_link_speed = link_speed[use_metrics_v3 ? metrics_v3->PcieRate : + use_metrics_v2 ? metrics_v2->PcieRate : metrics->PcieRate]; } else { gpu_metrics->pcie_link_width = smu_v11_0_get_current_pcie_link_width(smu); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index 890acc4e2cb8..cd81f848d45a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -82,6 +82,12 @@ */ #define SUPPORT_ECCTABLE_SMU_VERSION 0x00442a00 +/* + * SMU support BAD CHENNEL info MSG since version 68.51.00, + * use this to check ECCTALE feature whether support + */ +#define SUPPORT_BAD_CHANNEL_INFO_MSG_VERSION 0x00443300 + static const struct smu_temperature_range smu13_thermal_policy[] = { {-273150, 99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000}, @@ -140,6 +146,7 @@ static const struct cmn2asic_msg_mapping aldebaran_message_map[SMU_MSG_MAX_COUNT MSG_MAP(GfxDriverResetRecovery, PPSMC_MSG_GfxDriverResetRecovery, 0), MSG_MAP(BoardPowerCalibration, PPSMC_MSG_BoardPowerCalibration, 0), MSG_MAP(HeavySBR, PPSMC_MSG_HeavySBR, 0), + MSG_MAP(SetBadHBMPagesRetiredFlagsPerChannel, PPSMC_MSG_SetBadHBMPagesRetiredFlagsPerChannel, 0), }; static const struct cmn2asic_mapping aldebaran_clk_map[SMU_CLK_COUNT] = { @@ -1997,6 +2004,41 @@ static int aldebaran_smu_send_hbm_bad_page_num(struct smu_context *smu, return ret; } +static int aldebaran_check_bad_channel_info_support(struct smu_context *smu) +{ + uint32_t if_version = 0xff, smu_version = 0xff; + int ret = 0; + + ret = smu_cmn_get_smc_version(smu, &if_version, &smu_version); + if (ret) { + /* return not support if failed get smu_version */ + ret = -EOPNOTSUPP; + } + + if (smu_version < SUPPORT_BAD_CHANNEL_INFO_MSG_VERSION) + ret = -EOPNOTSUPP; + + return ret; +} + +static int aldebaran_send_hbm_bad_channel_flag(struct smu_context *smu, + uint32_t size) +{ + int ret = 0; + + ret = aldebaran_check_bad_channel_info_support(smu); + if (ret) + return ret; + + /* message SMU to update the bad channel info on SMUBUS */ + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetBadHBMPagesRetiredFlagsPerChannel, size, NULL); + if (ret) + dev_err(smu->adev->dev, "[%s] failed to message SMU to update HBM bad channel info\n", + __func__); + + return ret; +} + static const struct pptable_funcs aldebaran_ppt_funcs = { /* init dpm */ .get_allowed_feature_mask = aldebaran_get_allowed_feature_mask, @@ -2062,6 +2104,7 @@ static const struct pptable_funcs aldebaran_ppt_funcs = { .i2c_fini = aldebaran_i2c_control_fini, .send_hbm_bad_pages_num = aldebaran_smu_send_hbm_bad_page_num, .get_ecc_info = aldebaran_get_ecc_info, + .send_hbm_bad_channel_flag = aldebaran_send_hbm_bad_channel_flag, }; void aldebaran_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 4e557f4f7c4d..cf09e30bdfe0 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -752,6 +752,7 @@ int smu_v13_0_gfx_off_control(struct smu_context *smu, bool enable) case IP_VERSION(13, 0, 1): case IP_VERSION(13, 0, 3): case IP_VERSION(13, 0, 5): + case IP_VERSION(13, 0, 8): if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) return 0; if (enable) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index 590a6ed12d54..b8d0c70ff668 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -160,15 +160,21 @@ static void __smu_cmn_reg_print_error(struct smu_context *smu, { struct amdgpu_device *adev = smu->adev; const char *message = smu_get_message_name(smu, msg); + u32 msg_idx, prm; switch (reg_c2pmsg_90) { case SMU_RESP_NONE: { - u32 msg_idx = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66); - u32 prm = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82); + if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 5)) { + msg_idx = RREG32_SOC15(MP1, 0, mmMP1_C2PMSG_2); + prm = RREG32_SOC15(MP1, 0, mmMP1_C2PMSG_34); + } else { + msg_idx = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66); + prm = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82); + } dev_err_ratelimited(adev->dev, "SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x%08X SMN_C2PMSG_82:0x%08X", msg_idx, prm); - } + } break; case SMU_RESP_OK: /* The SMU executed the command. It completed with a @@ -297,7 +303,6 @@ int smu_cmn_send_msg_without_waiting(struct smu_context *smu, reg = __smu_cmn_poll_stat(smu); res = __smu_cmn_reg2errno(smu, reg); if (reg == SMU_RESP_NONE || - reg == SMU_RESP_BUSY_OTHER || res == -EREMOTEIO) goto Out; __smu_cmn_send_msg(smu, msg_index, param); @@ -391,7 +396,6 @@ int smu_cmn_send_smc_msg_with_param(struct smu_context *smu, reg = __smu_cmn_poll_stat(smu); res = __smu_cmn_reg2errno(smu, reg); if (reg == SMU_RESP_NONE || - reg == SMU_RESP_BUSY_OTHER || res == -EREMOTEIO) { __smu_cmn_reg_print_error(smu, reg, index, param, msg); goto Out; diff --git a/drivers/gpu/drm/arm/Kconfig b/drivers/gpu/drm/arm/Kconfig index 58a242871b28..6e3f1d600541 100644 --- a/drivers/gpu/drm/arm/Kconfig +++ b/drivers/gpu/drm/arm/Kconfig @@ -6,6 +6,7 @@ config DRM_HDLCD depends on DRM && OF && (ARM || ARM64 || COMPILE_TEST) depends on COMMON_CLK select DRM_KMS_HELPER + select DRM_GEM_CMA_HELPER help Choose this option if you have an ARM High Definition Colour LCD controller. diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c index 51e51ff299b7..ba16895690f1 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c @@ -93,11 +93,6 @@ static const struct component_master_ops komeda_master_ops = { .unbind = komeda_unbind, }; -static int compare_of(struct device *dev, void *data) -{ - return dev->of_node == data; -} - static void komeda_add_slave(struct device *master, struct component_match **match, struct device_node *np, @@ -107,7 +102,7 @@ static void komeda_add_slave(struct device *master, remote = of_graph_get_remote_node(np, port, endpoint); if (remote) { - drm_of_component_match_add(master, match, compare_of, remote); + drm_of_component_match_add(master, match, component_compare_of, remote); of_node_put(remote); } } diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 4f9b0a9f13e3..0643887800b4 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -177,17 +177,6 @@ static void armada_drm_unbind(struct device *dev) drm_mm_takedown(&priv->linear); } -static int compare_of(struct device *dev, void *data) -{ - return dev->of_node == data; -} - -static int compare_dev_name(struct device *dev, void *data) -{ - const char *name = data; - return !strcmp(dev_name(dev), name); -} - static void armada_add_endpoints(struct device *dev, struct component_match **match, struct device_node *dev_node) { @@ -196,7 +185,7 @@ static void armada_add_endpoints(struct device *dev, for_each_endpoint_of_node(dev_node, ep) { remote = of_graph_get_remote_port_parent(ep); if (remote && of_device_is_available(remote)) - drm_of_component_match_add(dev, match, compare_of, + drm_of_component_match_add(dev, match, component_compare_of, remote); of_node_put(remote); } @@ -213,7 +202,7 @@ static int armada_drm_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; int ret; - ret = drm_of_component_probe(dev, compare_dev_name, &armada_master_ops); + ret = drm_of_component_probe(dev, component_compare_dev_name, &armada_master_ops); if (ret != -EINVAL) return ret; @@ -223,7 +212,7 @@ static int armada_drm_probe(struct platform_device *pdev) int i; for (i = 0; devices[i]; i++) - component_match_add(dev, &match, compare_dev_name, + component_match_add(dev, &match, component_compare_dev_name, devices[i]); if (i == 0) { diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx.h b/drivers/gpu/drm/aspeed/aspeed_gfx.h index 96501152bafa..4e6a442c3886 100644 --- a/drivers/gpu/drm/aspeed/aspeed_gfx.h +++ b/drivers/gpu/drm/aspeed/aspeed_gfx.h @@ -12,6 +12,7 @@ struct aspeed_gfx { struct regmap *scu; u32 dac_reg; + u32 int_clr_reg; u32 vga_scratch_reg; u32 throd_val; u32 scan_line_max; diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c index 13f496473b9e..7780b72de9e8 100644 --- a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c +++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c @@ -61,6 +61,7 @@ struct aspeed_gfx_config { u32 dac_reg; /* DAC register in SCU */ + u32 int_clear_reg; /* Interrupt clear register */ u32 vga_scratch_reg; /* VGA scratch register in SCU */ u32 throd_val; /* Default Threshold Seting */ u32 scan_line_max; /* Max memory size of one scan line */ @@ -68,6 +69,7 @@ struct aspeed_gfx_config { static const struct aspeed_gfx_config ast2400_config = { .dac_reg = 0x2c, + .int_clear_reg = 0x60, .vga_scratch_reg = 0x50, .throd_val = CRT_THROD_LOW(0x1e) | CRT_THROD_HIGH(0x12), .scan_line_max = 64, @@ -75,14 +77,24 @@ static const struct aspeed_gfx_config ast2400_config = { static const struct aspeed_gfx_config ast2500_config = { .dac_reg = 0x2c, + .int_clear_reg = 0x60, .vga_scratch_reg = 0x50, .throd_val = CRT_THROD_LOW(0x24) | CRT_THROD_HIGH(0x3c), .scan_line_max = 128, }; +static const struct aspeed_gfx_config ast2600_config = { + .dac_reg = 0xc0, + .int_clear_reg = 0x68, + .vga_scratch_reg = 0x50, + .throd_val = CRT_THROD_LOW(0x50) | CRT_THROD_HIGH(0x70), + .scan_line_max = 128, +}; + static const struct of_device_id aspeed_gfx_match[] = { { .compatible = "aspeed,ast2400-gfx", .data = &ast2400_config }, { .compatible = "aspeed,ast2500-gfx", .data = &ast2500_config }, + { .compatible = "aspeed,ast2600-gfx", .data = &ast2600_config }, { }, }; MODULE_DEVICE_TABLE(of, aspeed_gfx_match); @@ -120,7 +132,7 @@ static irqreturn_t aspeed_gfx_irq_handler(int irq, void *data) if (reg & CRT_CTRL_VERTICAL_INTR_STS) { drm_crtc_handle_vblank(&priv->pipe.crtc); - writel(reg, priv->base + CRT_CTRL1); + writel(reg, priv->base + priv->int_clr_reg); return IRQ_HANDLED; } @@ -148,6 +160,7 @@ static int aspeed_gfx_load(struct drm_device *drm) config = match->data; priv->dac_reg = config->dac_reg; + priv->int_clr_reg = config->int_clear_reg; priv->vga_scratch_reg = config->vga_scratch_reg; priv->throd_val = config->throd_val; priv->scan_line_max = config->scan_line_max; diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index c86f5be4dfe0..007e5a282f67 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -8,7 +8,6 @@ config DRM_BRIDGE config DRM_PANEL_BRIDGE def_bool y depends on DRM_BRIDGE - depends on DRM_KMS_HELPER select DRM_PANEL help DRM bridge wrapper of DRM panels @@ -30,7 +29,7 @@ config DRM_CDNS_DSI config DRM_CHIPONE_ICN6211 tristate "Chipone ICN6211 MIPI-DSI/RGB Converter bridge" depends on OF - depends on DRM_KMS_HELPER + select DRM_KMS_HELPER select DRM_MIPI_DSI select DRM_PANEL_BRIDGE help diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index 633618bafd75..31ecf5626f1d 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -253,6 +253,8 @@ static int anx7625_aux_trans(struct anx7625_data *ctx, u8 op, u32 address, addrm = (address >> 8) & 0xFF; addrh = (address >> 16) & 0xFF; + if (!is_write) + op &= ~DP_AUX_I2C_MOT; cmd = DPCD_CMD(len, op); /* Set command and length */ @@ -2736,8 +2738,8 @@ static int anx7625_i2c_remove(struct i2c_client *client) if (platform->hdcp_workqueue) { cancel_delayed_work(&platform->hdcp_work); - flush_workqueue(platform->workqueue); - destroy_workqueue(platform->workqueue); + flush_workqueue(platform->hdcp_workqueue); + destroy_workqueue(platform->hdcp_workqueue); } if (!platform->pdata.low_power_mode) diff --git a/drivers/gpu/drm/bridge/cdns-dsi.c b/drivers/gpu/drm/bridge/cdns-dsi.c index d8a15c459b42..829e1a144656 100644 --- a/drivers/gpu/drm/bridge/cdns-dsi.c +++ b/drivers/gpu/drm/bridge/cdns-dsi.c @@ -1284,6 +1284,7 @@ static const struct of_device_id cdns_dsi_of_match[] = { { .compatible = "cdns,dsi" }, { }, }; +MODULE_DEVICE_TABLE(of, cdns_dsi_of_match); static struct platform_driver cdns_dsi_platform_driver = { .probe = cdns_dsi_drm_probe, diff --git a/drivers/gpu/drm/bridge/chipone-icn6211.c b/drivers/gpu/drm/bridge/chipone-icn6211.c index e8f36dca56b3..d9b7f48b99fb 100644 --- a/drivers/gpu/drm/bridge/chipone-icn6211.c +++ b/drivers/gpu/drm/bridge/chipone-icn6211.c @@ -191,7 +191,6 @@ static const struct drm_bridge_funcs chipone_bridge_funcs = { static int chipone_parse_dt(struct chipone *icn) { struct device *dev = icn->dev; - struct drm_panel *panel; int ret; icn->vdd1 = devm_regulator_get_optional(dev, "vdd1"); @@ -227,11 +226,7 @@ static int chipone_parse_dt(struct chipone *icn) return PTR_ERR(icn->enable_gpio); } - ret = drm_of_find_panel_or_bridge(dev->of_node, 1, 0, &panel, NULL); - if (ret) - return ret; - - icn->panel_bridge = devm_drm_panel_bridge_add(dev, panel); + icn->panel_bridge = devm_drm_of_get_bridge(dev, dev->of_node, 1, 0); if (IS_ERR(icn->panel_bridge)) return PTR_ERR(icn->panel_bridge); diff --git a/drivers/gpu/drm/bridge/ite-it6505.c b/drivers/gpu/drm/bridge/ite-it6505.c index fb16a176822d..f2f101220ade 100644 --- a/drivers/gpu/drm/bridge/ite-it6505.c +++ b/drivers/gpu/drm/bridge/ite-it6505.c @@ -289,7 +289,7 @@ #define WORD_LENGTH_20BIT 2 #define WORD_LENGTH_24BIT 3 #define DEBUGFS_DIR_NAME "it6505-debugfs" -#define READ_BUFFER_SIZE 200 +#define READ_BUFFER_SIZE 400 /* Vendor option */ #define HDCP_DESIRED 1 @@ -3074,7 +3074,7 @@ static ssize_t receive_timing_debugfs_show(struct file *file, char __user *buf, struct it6505 *it6505 = file->private_data; struct drm_display_mode *vid = &it6505->video_info; u8 read_buf[READ_BUFFER_SIZE]; - u8 *str = read_buf, *end = read_buf + PAGE_SIZE; + u8 *str = read_buf, *end = read_buf + READ_BUFFER_SIZE; ssize_t ret, count; if (!it6505) diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c index 963a6794735f..d5945501a5ee 100644 --- a/drivers/gpu/drm/bridge/nwl-dsi.c +++ b/drivers/gpu/drm/bridge/nwl-dsi.c @@ -332,17 +332,13 @@ static int nwl_dsi_config_dpi(struct nwl_dsi *dsi) static int nwl_dsi_init_interrupts(struct nwl_dsi *dsi) { - u32 irq_enable; - - nwl_dsi_write(dsi, NWL_DSI_IRQ_MASK, 0xffffffff); - nwl_dsi_write(dsi, NWL_DSI_IRQ_MASK2, 0x7); - - irq_enable = ~(u32)(NWL_DSI_TX_PKT_DONE_MASK | - NWL_DSI_RX_PKT_HDR_RCVD_MASK | - NWL_DSI_TX_FIFO_OVFLW_MASK | - NWL_DSI_HS_TX_TIMEOUT_MASK); + u32 irq_enable = ~(u32)(NWL_DSI_TX_PKT_DONE_MASK | + NWL_DSI_RX_PKT_HDR_RCVD_MASK | + NWL_DSI_TX_FIFO_OVFLW_MASK | + NWL_DSI_HS_TX_TIMEOUT_MASK); nwl_dsi_write(dsi, NWL_DSI_IRQ_MASK, irq_enable); + nwl_dsi_write(dsi, NWL_DSI_IRQ_MASK2, 0x7); return nwl_dsi_clear_error(dsi); } diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 38616aab12ac..fb6c588b0f71 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -1758,6 +1758,7 @@ static inline void ti_sn_gpio_unregister(void) {} static void ti_sn65dsi86_runtime_disable(void *data) { + pm_runtime_dont_use_autosuspend(data); pm_runtime_disable(data); } @@ -1817,11 +1818,11 @@ static int ti_sn65dsi86_probe(struct i2c_client *client, "failed to get reference clock\n"); pm_runtime_enable(dev); + pm_runtime_set_autosuspend_delay(pdata->dev, 500); + pm_runtime_use_autosuspend(pdata->dev); ret = devm_add_action_or_reset(dev, ti_sn65dsi86_runtime_disable, dev); if (ret) return ret; - pm_runtime_set_autosuspend_delay(pdata->dev, 500); - pm_runtime_use_autosuspend(pdata->dev); ti_sn65dsi86_debugfs_init(pdata); diff --git a/drivers/gpu/drm/dp/drm_dp.c b/drivers/gpu/drm/dp/drm_dp.c index b9e5c0bd0d63..580016a1b9eb 100644 --- a/drivers/gpu/drm/dp/drm_dp.c +++ b/drivers/gpu/drm/dp/drm_dp.c @@ -208,16 +208,6 @@ bool drm_dp_128b132b_link_training_failed(const u8 link_status[DP_LINK_STATUS_SI } EXPORT_SYMBOL(drm_dp_128b132b_link_training_failed); -u8 drm_dp_get_adjust_request_post_cursor(const u8 link_status[DP_LINK_STATUS_SIZE], - unsigned int lane) -{ - unsigned int offset = DP_ADJUST_REQUEST_POST_CURSOR2; - u8 value = dp_link_status(link_status, offset); - - return (value >> (lane << 1)) & 0x3; -} -EXPORT_SYMBOL(drm_dp_get_adjust_request_post_cursor); - static int __8b10b_clock_recovery_delay_us(const struct drm_dp_aux *aux, u8 rd_interval) { if (rd_interval > 4) diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c index ddcf5c2c8e6a..3b6d3bdbd099 100644 --- a/drivers/gpu/drm/drm_atomic_state_helper.c +++ b/drivers/gpu/drm/drm_atomic_state_helper.c @@ -243,11 +243,36 @@ EXPORT_SYMBOL(drm_atomic_helper_crtc_destroy_state); void __drm_atomic_helper_plane_state_reset(struct drm_plane_state *plane_state, struct drm_plane *plane) { + u64 val; + plane_state->plane = plane; plane_state->rotation = DRM_MODE_ROTATE_0; plane_state->alpha = DRM_BLEND_ALPHA_OPAQUE; plane_state->pixel_blend_mode = DRM_MODE_BLEND_PREMULTI; + + if (plane->color_encoding_property) { + if (!drm_object_property_get_default_value(&plane->base, + plane->color_encoding_property, + &val)) + plane_state->color_encoding = val; + } + + if (plane->color_range_property) { + if (!drm_object_property_get_default_value(&plane->base, + plane->color_range_property, + &val)) + plane_state->color_range = val; + } + + if (plane->zpos_property) { + if (!drm_object_property_get_default_value(&plane->base, + plane->zpos_property, + &val)) { + plane_state->zpos = val; + plane_state->normalized_zpos = val; + } + } } EXPORT_SYMBOL(__drm_atomic_helper_plane_state_reset); diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index c3e6e615bf09..7051c9c909c2 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -27,10 +27,10 @@ /* * Authors: Thomas Hellström <thomas-at-tungstengraphics-dot-com> */ - #include <linux/cc_platform.h> #include <linux/export.h> #include <linux/highmem.h> +#include <linux/ioport.h> #include <linux/iosys-map.h> #include <xen/xen.h> diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index a50c82bc2b2f..76a8c707c34b 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -2330,6 +2330,9 @@ EXPORT_SYMBOL(drm_connector_atomic_hdr_metadata_equal); void drm_connector_set_vrr_capable_property( struct drm_connector *connector, bool capable) { + if (!connector->vrr_capable_property) + return; + drm_object_property_set_value(&connector->base, connector->vrr_capable_property, capable); diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 561f53831e29..cc7bd58369df 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -4859,7 +4859,8 @@ bool drm_detect_monitor_audio(struct edid *edid) if (!edid_ext) goto end; - has_audio = ((edid_ext[3] & EDID_BASIC_AUDIO) != 0); + has_audio = (edid_ext[0] == CEA_EXT && + (edid_ext[3] & EDID_BASIC_AUDIO) != 0); if (has_audio) { DRM_DEBUG_KMS("Monitor has basic audio support\n"); @@ -5187,10 +5188,14 @@ static void drm_parse_cea_ext(struct drm_connector *connector, /* The existence of a CEA block should imply RGB support */ info->color_formats = DRM_COLOR_FORMAT_RGB444; - if (edid_ext[3] & EDID_CEA_YCRCB444) - info->color_formats |= DRM_COLOR_FORMAT_YCBCR444; - if (edid_ext[3] & EDID_CEA_YCRCB422) - info->color_formats |= DRM_COLOR_FORMAT_YCBCR422; + + /* CTA DisplayID Data Block does not have byte #3 */ + if (edid_ext[0] == CEA_EXT) { + if (edid_ext[3] & EDID_CEA_YCRCB444) + info->color_formats |= DRM_COLOR_FORMAT_YCBCR444; + if (edid_ext[3] & EDID_CEA_YCRCB422) + info->color_formats |= DRM_COLOR_FORMAT_YCBCR422; + } if (cea_db_offsets(edid_ext, &start, &end)) return; diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c index 86d9e907c0b2..ba1608effc0f 100644 --- a/drivers/gpu/drm/drm_mode_object.c +++ b/drivers/gpu/drm/drm_mode_object.c @@ -297,11 +297,26 @@ int drm_object_property_set_value(struct drm_mode_object *obj, } EXPORT_SYMBOL(drm_object_property_set_value); +static int __drm_object_property_get_prop_value(struct drm_mode_object *obj, + struct drm_property *property, + uint64_t *val) +{ + int i; + + for (i = 0; i < obj->properties->count; i++) { + if (obj->properties->properties[i] == property) { + *val = obj->properties->values[i]; + return 0; + } + } + + return -EINVAL; +} + static int __drm_object_property_get_value(struct drm_mode_object *obj, struct drm_property *property, uint64_t *val) { - int i; /* read-only properties bypass atomic mechanism and still store * their value in obj->properties->values[].. mostly to avoid @@ -311,15 +326,7 @@ static int __drm_object_property_get_value(struct drm_mode_object *obj, !(property->flags & DRM_MODE_PROP_IMMUTABLE)) return drm_atomic_get_property(obj, property, val); - for (i = 0; i < obj->properties->count; i++) { - if (obj->properties->properties[i] == property) { - *val = obj->properties->values[i]; - return 0; - } - - } - - return -EINVAL; + return __drm_object_property_get_prop_value(obj, property, val); } /** @@ -348,6 +355,32 @@ int drm_object_property_get_value(struct drm_mode_object *obj, } EXPORT_SYMBOL(drm_object_property_get_value); +/** + * drm_object_property_get_default_value - retrieve the default value of a + * property when in atomic mode. + * @obj: drm mode object to get property value from + * @property: property to retrieve + * @val: storage for the property value + * + * This function retrieves the default state of the given property as passed in + * to drm_object_attach_property + * + * Only atomic drivers should call this function directly, as for non-atomic + * drivers it will return the current value. + * + * Returns: + * Zero on success, error code on failure. + */ +int drm_object_property_get_default_value(struct drm_mode_object *obj, + struct drm_property *property, + uint64_t *val) +{ + WARN_ON(!drm_drv_uses_atomic_modeset(property->dev)); + + return __drm_object_property_get_prop_value(obj, property, val); +} +EXPORT_SYMBOL(drm_object_property_get_default_value); + /* helper for getconnector and getproperties ioctls */ int drm_mode_object_get_properties(struct drm_mode_object *obj, bool atomic, uint32_t __user *prop_ptr, diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 96b13e36293c..3f819c7a021b 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -35,6 +35,7 @@ #include <linux/list_sort.h> #include <linux/export.h> +#include <video/of_display_timing.h> #include <video/of_videomode.h> #include <video/videomode.h> @@ -127,7 +128,7 @@ EXPORT_SYMBOL(drm_mode_probed_add); * according to the hdisplay, vdisplay, vrefresh. * It is based from the VESA(TM) Coordinated Video Timing Generator by * Graham Loveridge April 9, 2003 available at - * http://www.elo.utfsm.cl/~elo212/docs/CVTd6r1.xls + * http://www.elo.utfsm.cl/~elo212/docs/CVTd6r1.xls * * And it is copied from xf86CVTmode in xserver/hw/xfree86/modes/xf86cvt.c. * What I have done is to translate it by using integer calculation. @@ -727,6 +728,54 @@ int of_get_drm_display_mode(struct device_node *np, return 0; } EXPORT_SYMBOL_GPL(of_get_drm_display_mode); + +/** + * of_get_drm_panel_display_mode - get a panel-timing drm_display_mode from devicetree + * @np: device_node with the panel-timing specification + * @dmode: will be set to the return value + * @bus_flags: information about pixelclk, sync and DE polarity + * + * The Device Tree properties width-mm and height-mm will be read and set on + * the display mode if they are present. + * + * Returns: + * Zero on success, negative error code on failure. + */ +int of_get_drm_panel_display_mode(struct device_node *np, + struct drm_display_mode *dmode, u32 *bus_flags) +{ + u32 width_mm = 0, height_mm = 0; + struct display_timing timing; + struct videomode vm; + int ret; + + ret = of_get_display_timing(np, "panel-timing", &timing); + if (ret) + return ret; + + videomode_from_timing(&timing, &vm); + + memset(dmode, 0, sizeof(*dmode)); + drm_display_mode_from_videomode(&vm, dmode); + if (bus_flags) + drm_bus_flags_from_videomode(&vm, bus_flags); + + ret = of_property_read_u32(np, "width-mm", &width_mm); + if (ret && ret != -EINVAL) + return ret; + + ret = of_property_read_u32(np, "height-mm", &height_mm); + if (ret && ret != -EINVAL) + return ret; + + dmode->width_mm = width_mm; + dmode->height_mm = height_mm; + + drm_mode_debug_printmodeline(dmode); + + return 0; +} +EXPORT_SYMBOL_GPL(of_get_drm_panel_display_mode); #endif /* CONFIG_OF */ #endif /* CONFIG_VIDEOMODE_HELPERS */ diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index 59d368ea006b..026e4e29a0f3 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -18,11 +18,6 @@ * properties. */ -static void drm_release_of(struct device *dev, void *data) -{ - of_node_put(data); -} - /** * drm_of_crtc_port_mask - find the mask of a registered CRTC by port OF node * @dev: DRM device @@ -94,7 +89,7 @@ void drm_of_component_match_add(struct device *master, struct device_node *node) { of_node_get(node); - component_match_add_release(master, matchptr, drm_release_of, + component_match_add_release(master, matchptr, component_release_of, compare, node); } EXPORT_SYMBOL_GPL(drm_of_component_match_add); @@ -249,6 +244,21 @@ int drm_of_find_panel_or_bridge(const struct device_node *np, if (panel) *panel = NULL; + /** + * Devices can also be child nodes when we also control that device + * through the upstream device (ie, MIPI-DCS for a MIPI-DSI device). + * + * Lookup for a child node of the given parent that isn't either port + * or ports. + */ + for_each_available_child_of_node(np, remote) { + if (of_node_name_eq(remote, "port") || + of_node_name_eq(remote, "ports")) + continue; + + goto of_find_panel_or_bridge; + } + /* * of_graph_get_remote_node() produces a noisy error message if port * node isn't found and the absence of the port is a legit case here, @@ -259,6 +269,8 @@ int drm_of_find_panel_or_bridge(const struct device_node *np, return -ENODEV; remote = of_graph_get_remote_node(np, port, endpoint); + +of_find_panel_or_bridge: if (!remote) return -ENODEV; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 0b756ecb1bc2..1d2b4fb4bcf8 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -574,18 +574,6 @@ static const struct component_master_ops etnaviv_master_ops = { .unbind = etnaviv_unbind, }; -static int compare_of(struct device *dev, void *data) -{ - struct device_node *np = data; - - return dev->of_node == np; -} - -static int compare_str(struct device *dev, void *data) -{ - return !strcmp(dev_name(dev), data); -} - static int etnaviv_pdev_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -603,14 +591,14 @@ static int etnaviv_pdev_probe(struct platform_device *pdev) first_node = core_node; drm_of_component_match_add(&pdev->dev, &match, - compare_of, core_node); + component_compare_of, core_node); } } else { char **names = dev->platform_data; unsigned i; for (i = 0; names[i]; i++) - component_match_add(dev, &match, compare_str, names[i]); + component_match_add(dev, &match, component_compare_dev_name, names[i]); } /* diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index 12571ac45540..c04264f70ad1 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -678,7 +678,6 @@ static int decon_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct decon_context *ctx; struct device_node *i80_if_timings; - struct resource *res; int ret; if (!dev->of_node) @@ -728,16 +727,11 @@ static int decon_probe(struct platform_device *pdev) goto err_iounmap; } - res = platform_get_resource_byname(pdev, IORESOURCE_IRQ, - ctx->i80_if ? "lcd_sys" : "vsync"); - if (!res) { - dev_err(dev, "irq request failed.\n"); - ret = -ENXIO; + ret = platform_get_irq_byname(pdev, ctx->i80_if ? "lcd_sys" : "vsync"); + if (ret < 0) goto err_iounmap; - } - ret = devm_request_irq(dev, res->start, decon_irq_handler, - 0, "drm_decon", ctx); + ret = devm_request_irq(dev, ret, decon_irq_handler, 0, "drm_decon", ctx); if (ret) { dev_err(dev, "irq request failed.\n"); goto err_iounmap; diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index c68498497c0b..424ea23eec32 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -212,11 +212,6 @@ static struct exynos_drm_driver_info exynos_drm_drivers[] = { } }; -static int compare_dev(struct device *dev, void *data) -{ - return dev == (struct device *)data; -} - static struct component_match *exynos_drm_match_add(struct device *dev) { struct component_match *match = NULL; @@ -234,8 +229,7 @@ static struct component_match *exynos_drm_match_add(struct device *dev) if (!(info->flags & DRM_FIMC_DEVICE) || exynos_drm_check_fimc_device(d) == 0) - component_match_add(dev, &match, - compare_dev, d); + component_match_add(dev, &match, component_compare_dev, d); p = d; } put_device(p); diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index b7d0a4aead0a..334862d422e2 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1335,8 +1335,10 @@ static int exynos_dsi_register_te_irq(struct exynos_dsi *dsi, int ret; int te_gpio_irq; - dsi->te_gpio = devm_gpiod_get_optional(dsi->dev, "te", GPIOD_IN); - if (IS_ERR(dsi->te_gpio)) { + dsi->te_gpio = gpiod_get_optional(panel, "te", GPIOD_IN); + if (!dsi->te_gpio) { + return 0; + } else if (IS_ERR(dsi->te_gpio)) { dev_err(dsi->dev, "gpio request failed with %ld\n", PTR_ERR(dsi->te_gpio)); return PTR_ERR(dsi->te_gpio); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index 023f54ee61a8..0ee32e4b1e43 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -1267,7 +1267,6 @@ static int fimc_probe(struct platform_device *pdev) struct exynos_drm_ipp_formats *formats; struct device *dev = &pdev->dev; struct fimc_context *ctx; - struct resource *res; int ret; int i, j, num_limits, num_formats; @@ -1330,14 +1329,12 @@ static int fimc_probe(struct platform_device *pdev) return PTR_ERR(ctx->regs); /* resource irq */ - res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (!res) { - dev_err(dev, "failed to request irq resource.\n"); - return -ENOENT; - } + ret = platform_get_irq(pdev, 0); + if (ret < 0) + return ret; - ret = devm_request_irq(dev, res->start, fimc_irq_handler, - 0, dev_name(dev), ctx); + ret = devm_request_irq(dev, ret, fimc_irq_handler, + 0, dev_name(dev), ctx); if (ret < 0) { dev_err(dev, "failed to request irq.\n"); return ret; diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index c735e53939d8..d5720fab510c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -109,6 +109,7 @@ struct fimd_driver_data { unsigned int has_dp_clk:1; unsigned int has_hw_trigger:1; unsigned int has_trigger_per_te:1; + unsigned int has_bgr_support:1; }; static struct fimd_driver_data s3c64xx_fimd_driver_data = { @@ -138,6 +139,7 @@ static struct fimd_driver_data exynos4_fimd_driver_data = { .lcdblk_bypass_shift = 1, .has_shadowcon = 1, .has_vtsel = 1, + .has_bgr_support = 1, }; static struct fimd_driver_data exynos5_fimd_driver_data = { @@ -149,6 +151,7 @@ static struct fimd_driver_data exynos5_fimd_driver_data = { .has_vidoutcon = 1, .has_vtsel = 1, .has_dp_clk = 1, + .has_bgr_support = 1, }; static struct fimd_driver_data exynos5420_fimd_driver_data = { @@ -162,6 +165,7 @@ static struct fimd_driver_data exynos5420_fimd_driver_data = { .has_vtsel = 1, .has_mic_bypass = 1, .has_dp_clk = 1, + .has_bgr_support = 1, }; struct fimd_context { @@ -226,6 +230,18 @@ static const uint32_t fimd_formats[] = { DRM_FORMAT_ARGB8888, }; +static const uint32_t fimd_extended_formats[] = { + DRM_FORMAT_C8, + DRM_FORMAT_XRGB1555, + DRM_FORMAT_XBGR1555, + DRM_FORMAT_RGB565, + DRM_FORMAT_BGR565, + DRM_FORMAT_XRGB8888, + DRM_FORMAT_XBGR8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_ABGR8888, +}; + static const unsigned int capabilities[WINDOWS_NR] = { 0, EXYNOS_DRM_PLANE_CAP_WIN_BLEND | EXYNOS_DRM_PLANE_CAP_PIX_BLEND, @@ -673,21 +689,25 @@ static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win, val |= WINCONx_BYTSWP; break; case DRM_FORMAT_XRGB1555: + case DRM_FORMAT_XBGR1555: val |= WINCON0_BPPMODE_16BPP_1555; val |= WINCONx_HAWSWP; val |= WINCONx_BURSTLEN_16WORD; break; case DRM_FORMAT_RGB565: + case DRM_FORMAT_BGR565: val |= WINCON0_BPPMODE_16BPP_565; val |= WINCONx_HAWSWP; val |= WINCONx_BURSTLEN_16WORD; break; case DRM_FORMAT_XRGB8888: + case DRM_FORMAT_XBGR8888: val |= WINCON0_BPPMODE_24BPP_888; val |= WINCONx_WSWP; val |= WINCONx_BURSTLEN_16WORD; break; case DRM_FORMAT_ARGB8888: + case DRM_FORMAT_ABGR8888: default: val |= WINCON1_BPPMODE_25BPP_A1888; val |= WINCONx_WSWP; @@ -695,6 +715,18 @@ static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win, break; } + switch (pixel_format) { + case DRM_FORMAT_XBGR1555: + case DRM_FORMAT_XBGR8888: + case DRM_FORMAT_ABGR8888: + case DRM_FORMAT_BGR565: + writel(WIN_RGB_ORDER_REVERSE, ctx->regs + WIN_RGB_ORDER(win)); + break; + default: + writel(WIN_RGB_ORDER_FORWARD, ctx->regs + WIN_RGB_ORDER(win)); + break; + } + /* * Setting dma-burst to 16Word causes permanent tearing for very small * buffers, e.g. cursor buffer. Burst Mode switching which based on @@ -1074,8 +1106,14 @@ static int fimd_bind(struct device *dev, struct device *master, void *data) ctx->drm_dev = drm_dev; for (i = 0; i < WINDOWS_NR; i++) { - ctx->configs[i].pixel_formats = fimd_formats; - ctx->configs[i].num_pixel_formats = ARRAY_SIZE(fimd_formats); + if (ctx->driver_data->has_bgr_support) { + ctx->configs[i].pixel_formats = fimd_extended_formats; + ctx->configs[i].num_pixel_formats = ARRAY_SIZE(fimd_extended_formats); + } else { + ctx->configs[i].pixel_formats = fimd_formats; + ctx->configs[i].num_pixel_formats = ARRAY_SIZE(fimd_formats); + } + ctx->configs[i].zpos = i; ctx->configs[i].type = fimd_win_types[i]; ctx->configs[i].capabilities = capabilities[i]; @@ -1133,7 +1171,6 @@ static int fimd_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct fimd_context *ctx; struct device_node *i80_if_timings; - struct resource *res; int ret; if (!dev->of_node) @@ -1206,15 +1243,11 @@ static int fimd_probe(struct platform_device *pdev) if (IS_ERR(ctx->regs)) return PTR_ERR(ctx->regs); - res = platform_get_resource_byname(pdev, IORESOURCE_IRQ, - ctx->i80_if ? "lcd_sys" : "vsync"); - if (!res) { - dev_err(dev, "irq request failed.\n"); - return -ENXIO; - } + ret = platform_get_irq_byname(pdev, ctx->i80_if ? "lcd_sys" : "vsync"); + if (ret < 0) + return ret; - ret = devm_request_irq(dev, res->start, fimd_irq_handler, - 0, "drm_fimd", ctx); + ret = devm_request_irq(dev, ret, fimd_irq_handler, 0, "drm_fimd", ctx); if (ret) { dev_err(dev, "irq request failed.\n"); return ret; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 166a80262896..964dceb28c1e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -1220,7 +1220,6 @@ static int gsc_probe(struct platform_device *pdev) struct gsc_driverdata *driver_data; struct exynos_drm_ipp_formats *formats; struct gsc_context *ctx; - struct resource *res; int num_formats, ret, i, j; ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL); @@ -1275,13 +1274,10 @@ static int gsc_probe(struct platform_device *pdev) return PTR_ERR(ctx->regs); /* resource irq */ - res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (!res) { - dev_err(dev, "failed to request irq resource.\n"); - return -ENOENT; - } + ctx->irq = platform_get_irq(pdev, 0); + if (ctx->irq < 0) + return ctx->irq; - ctx->irq = res->start; ret = devm_request_irq(dev, ctx->irq, gsc_irq_handler, 0, dev_name(dev), ctx); if (ret < 0) { diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c index 41c54f1f60bc..e5204be86093 100644 --- a/drivers/gpu/drm/exynos/exynos_mixer.c +++ b/drivers/gpu/drm/exynos/exynos_mixer.c @@ -809,19 +809,17 @@ static int mixer_resources_init(struct mixer_context *mixer_ctx) return -ENXIO; } - res = platform_get_resource(mixer_ctx->pdev, IORESOURCE_IRQ, 0); - if (res == NULL) { - dev_err(dev, "get interrupt resource failed.\n"); - return -ENXIO; - } + ret = platform_get_irq(mixer_ctx->pdev, 0); + if (ret < 0) + return ret; + mixer_ctx->irq = ret; - ret = devm_request_irq(dev, res->start, mixer_irq_handler, - 0, "drm_mixer", mixer_ctx); + ret = devm_request_irq(dev, mixer_ctx->irq, mixer_irq_handler, + 0, "drm_mixer", mixer_ctx); if (ret) { dev_err(dev, "request interrupt failed.\n"); return ret; } - mixer_ctx->irq = res->start; return 0; } diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c index 3cf057269f2a..2af51df6dca7 100644 --- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c +++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c @@ -204,11 +204,6 @@ err_mode_config_cleanup: return ret; } -static int compare_of(struct device *dev, void *data) -{ - return dev->of_node == data; -} - static int kirin_drm_kms_cleanup(struct drm_device *dev) { drm_kms_helper_poll_fini(dev); @@ -279,7 +274,7 @@ static int kirin_drm_platform_probe(struct platform_device *pdev) if (!remote) return -ENODEV; - drm_of_component_match_add(dev, &match, compare_of, remote); + drm_of_component_match_add(dev, &match, component_compare_of, remote); of_node_put(remote); return component_master_add_with_match(dev, &kirin_drm_ops, match); diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 42b5400f0fef..98c5450b8eac 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -3,6 +3,7 @@ config DRM_I915 tristate "Intel 8xx/9xx/G3x/G4x/HD Graphics" depends on DRM depends on X86 && PCI + depends on !PREEMPT_RT select INTEL_GTT select INTERVAL_TREE # we need shmfs for the swappable backing store, and in particular diff --git a/drivers/gpu/drm/i915/Kconfig.unstable b/drivers/gpu/drm/i915/Kconfig.unstable index 0c2276155c2b..cf151a297ed7 100644 --- a/drivers/gpu/drm/i915/Kconfig.unstable +++ b/drivers/gpu/drm/i915/Kconfig.unstable @@ -19,11 +19,3 @@ config DRM_I915_UNSTABLE Recommended for driver developers _only_. If in the slightest bit of doubt, say "N". - -config DRM_I915_UNSTABLE_FAKE_LMEM - bool "Enable the experimental fake lmem" - depends on DRM_I915_UNSTABLE - default n - help - Convert some system memory into a fake local memory region for - testing. diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 1a771ee5b1d0..815589f8658c 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -18,6 +18,7 @@ subdir-ccflags-y += -Wno-unused-parameter subdir-ccflags-y += -Wno-type-limits subdir-ccflags-y += -Wno-missing-field-initializers subdir-ccflags-y += -Wno-sign-compare +subdir-ccflags-y += -Wno-shift-negative-value subdir-ccflags-y += $(call cc-disable-warning, unused-but-set-variable) subdir-ccflags-y += $(call cc-disable-warning, frame-address) subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror diff --git a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c index fca8f5b3cffe..94e64661b4fd 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c +++ b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c @@ -1349,7 +1349,7 @@ tgl_get_combo_buf_trans_dp(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); if (crtc_state->port_clock > 270000) { - if (IS_TGL_U(dev_priv) || IS_TGL_Y(dev_priv)) { + if (IS_TGL_UY(dev_priv)) { return intel_get_buf_trans(&tgl_uy_combo_phy_trans_dp_hbr2, n_entries); } else { diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index fd5bc7acf08d..2cd62a187df3 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -265,7 +265,7 @@ static int intelfb_create(struct drm_fb_helper *helper, struct intel_memory_region *mem = obj->mm.region; info->apertures->ranges[0].base = mem->io_start; - info->apertures->ranges[0].size = mem->total; + info->apertures->ranges[0].size = mem->io_size; /* Use fbdev's framebuffer from lmem for discrete */ info->fix.smem_start = diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 7087fdf191e6..5db83aaf93ee 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -671,6 +671,16 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base, goto out_err; } + /* + * We don't support breadcrumb handshake on these + * classes + */ + if (siblings[n]->class == RENDER_CLASS || + siblings[n]->class == COMPUTE_CLASS) { + err = -EINVAL; + goto out_err; + } + if (n) { if (prev_engine.engine_class != ci.engine_class) { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index efe69d6b86f4..c3ea243d414d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -455,7 +455,7 @@ vm_access(struct vm_area_struct *area, unsigned long addr, return -EACCES; addr -= area->vm_start; - if (addr >= obj->base.size) + if (range_overflows_t(u64, addr, len, obj->base.size)) return -EINVAL; i915_gem_ww_ctx_init(&ww, true); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 9aad7ebde3e7..c1c3b510b9e2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -273,12 +273,6 @@ void __i915_gem_object_pages_fini(struct drm_i915_gem_object *obj) if (!list_empty(&obj->vma.list)) { struct i915_vma *vma; - /* - * Note that the vma keeps an object reference while - * it is active, so it *should* not sleep while we - * destroy it. Our debug code errs insits it *might*. - * For the moment, play along. - */ spin_lock(&obj->vma.lock); while ((vma = list_first_entry_or_null(&obj->vma.list, struct i915_vma, @@ -286,13 +280,7 @@ void __i915_gem_object_pages_fini(struct drm_i915_gem_object *obj) GEM_BUG_ON(vma->obj != obj); spin_unlock(&obj->vma.lock); - /* Verify that the vma is unbound under the vm mutex. */ - mutex_lock(&vma->vm->mutex); - atomic_and(~I915_VMA_PIN_MASK, &vma->flags); - __i915_vma_unbind(vma); - mutex_unlock(&vma->vm->mutex); - - __i915_vma_put(vma); + i915_vma_destroy(vma); spin_lock(&obj->vma.lock); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 0098a32490f0..fd54eb8f4826 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -319,16 +319,23 @@ struct drm_i915_gem_object { #define I915_BO_ALLOC_PM_VOLATILE BIT(4) /* Object needs to be restored early using memcpy during resume */ #define I915_BO_ALLOC_PM_EARLY BIT(5) +/* + * Object is likely never accessed by the CPU. This will prioritise the BO to be + * allocated in the non-mappable portion of lmem. This is merely a hint, and if + * dealing with userspace objects the CPU fault handler is free to ignore this. + */ +#define I915_BO_ALLOC_GPU_ONLY BIT(6) #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \ I915_BO_ALLOC_VOLATILE | \ I915_BO_ALLOC_CPU_CLEAR | \ I915_BO_ALLOC_USER | \ I915_BO_ALLOC_PM_VOLATILE | \ - I915_BO_ALLOC_PM_EARLY) -#define I915_BO_READONLY BIT(6) -#define I915_TILING_QUIRK_BIT 7 /* unknown swizzling; do not release! */ -#define I915_BO_PROTECTED BIT(8) -#define I915_BO_WAS_BOUND_BIT 9 + I915_BO_ALLOC_PM_EARLY | \ + I915_BO_ALLOC_GPU_ONLY) +#define I915_BO_READONLY BIT(7) +#define I915_TILING_QUIRK_BIT 8 /* unknown swizzling; do not release! */ +#define I915_BO_PROTECTED BIT(9) +#define I915_BO_WAS_BOUND_BIT 10 /** * @mem_flags - Mutable placement-related flags * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 183b861620b8..97c820eee115 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -358,6 +358,9 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, !i915_gem_object_has_iomem(obj)) return ERR_PTR(-ENXIO); + if (WARN_ON_ONCE(obj->flags & I915_BO_ALLOC_GPU_ONLY)) + return ERR_PTR(-EINVAL); + assert_object_held(obj); pinned = !(type & I915_MAP_OVERRIDE); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c index 60e63182bfa3..5866c88e4d02 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_region.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c @@ -47,6 +47,11 @@ i915_gem_object_create_region(struct intel_memory_region *mem, GEM_BUG_ON(flags & ~I915_BO_ALLOC_FLAGS); + if (WARN_ON_ONCE(flags & I915_BO_ALLOC_GPU_ONLY && + (flags & I915_BO_ALLOC_CPU_CLEAR || + flags & I915_BO_ALLOC_PM_EARLY))) + return ERR_PTR(-EINVAL); + if (!mem) return ERR_PTR(-ENODEV); @@ -69,6 +74,17 @@ i915_gem_object_create_region(struct intel_memory_region *mem, if (!obj) return ERR_PTR(-ENOMEM); + /* + * Anything smaller than the min_page_size can't be freely inserted into + * the GTT, due to alignemnt restrictions. For such special objects, + * make sure we force memcpy based suspend-resume. In the future we can + * revisit this, either by allowing special mis-aligned objects in the + * migration path, or by mapping all of LMEM upfront using cheap 1G + * GTT entries. + */ + if (default_page_size < mem->min_page_size) + flags |= I915_BO_ALLOC_PM_EARLY; + err = mem->ops->init_object(mem, obj, size, page_size, flags); if (err) goto err_object_free; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index c42e1e1c90be..c7541dc687c1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -700,7 +700,7 @@ struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915, { return intel_memory_region_create(i915, 0, totalram_pages() << PAGE_SHIFT, - PAGE_SIZE, 0, + PAGE_SIZE, 0, 0, type, instance, &shmem_region_ops); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index f1011a80d4c3..2a225daa2b12 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -493,18 +493,22 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem) /* Exclude the reserved region from driver use */ mem->region.end = reserved_base - 1; + mem->io_size = resource_size(&mem->region); /* It is possible for the reserved area to end before the end of stolen * memory, so just consider the start. */ reserved_total = stolen_top - reserved_base; + i915->stolen_usable_size = + resource_size(&i915->dsm) - reserved_total; + drm_dbg(&i915->drm, "Memory reserved for graphics device: %lluK, usable: %lluK\n", (u64)resource_size(&i915->dsm) >> 10, - ((u64)resource_size(&i915->dsm) - reserved_total) >> 10); + (u64)i915->stolen_usable_size >> 10); - i915->stolen_usable_size = - resource_size(&i915->dsm) - reserved_total; + if (i915->stolen_usable_size == 0) + return 0; /* Basic memrange allocator for stolen space. */ drm_mm_init(&i915->mm.stolen, 0, i915->stolen_usable_size); @@ -749,7 +753,7 @@ static int init_stolen_lmem(struct intel_memory_region *mem) if (!io_mapping_init_wc(&mem->iomap, mem->io_start, - resource_size(&mem->region))) + mem->io_size)) return -EIO; /* @@ -804,7 +808,8 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, I915_GTT_PAGE_SIZE_4K; mem = intel_memory_region_create(i915, lmem_base, lmem_size, - min_page_size, io_start, + min_page_size, + io_start, lmem_size, type, instance, &i915_region_stolen_lmem_ops); if (IS_ERR(mem)) @@ -835,7 +840,7 @@ i915_gem_stolen_smem_setup(struct drm_i915_private *i915, u16 type, mem = intel_memory_region_create(i915, intel_graphics_stolen_res.start, resource_size(&intel_graphics_stolen_res), - PAGE_SIZE, 0, type, instance, + PAGE_SIZE, 0, 0, type, instance, &i915_region_stolen_smem_ops); if (IS_ERR(mem)) return mem; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 8419096d4056..45cc5837ce00 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -7,8 +7,10 @@ #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/drm_buddy.h> #include "i915_drv.h" +#include "i915_ttm_buddy_manager.h" #include "intel_memory_region.h" #include "intel_region_ttm.h" @@ -22,6 +24,7 @@ #define I915_TTM_PRIO_PURGE 0 #define I915_TTM_PRIO_NO_PAGES 1 #define I915_TTM_PRIO_HAS_PAGES 2 +#define I915_TTM_PRIO_NEEDS_CPU_ACCESS 3 /* * Size of struct ttm_place vector in on-stack struct ttm_placement allocs @@ -129,7 +132,15 @@ i915_ttm_place_from_region(const struct intel_memory_region *mr, place->mem_type = intel_region_to_ttm_type(mr); if (flags & I915_BO_ALLOC_CONTIGUOUS) - place->flags = TTM_PL_FLAG_CONTIGUOUS; + place->flags |= TTM_PL_FLAG_CONTIGUOUS; + if (mr->io_size && mr->io_size < mr->total) { + if (flags & I915_BO_ALLOC_GPU_ONLY) { + place->flags |= TTM_PL_FLAG_TOPDOWN; + } else { + place->fpfn = 0; + place->lpfn = mr->io_size >> PAGE_SHIFT; + } + } } static void @@ -331,6 +342,7 @@ static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo, const struct ttm_place *place) { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + struct ttm_resource *res = bo->resource; if (!obj) return false; @@ -344,7 +356,48 @@ static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo, return false; /* Will do for now. Our pinned objects are still on TTM's LRU lists */ - return i915_gem_object_evictable(obj); + if (!i915_gem_object_evictable(obj)) + return false; + + switch (res->mem_type) { + case I915_PL_LMEM0: { + struct ttm_resource_manager *man = + ttm_manager_type(bo->bdev, res->mem_type); + struct i915_ttm_buddy_resource *bman_res = + to_ttm_buddy_resource(res); + struct drm_buddy *mm = bman_res->mm; + struct drm_buddy_block *block; + + if (!place->fpfn && !place->lpfn) + return true; + + GEM_BUG_ON(!place->lpfn); + + /* + * If we just want something mappable then we can quickly check + * if the current victim resource is using any of the CPU + * visible portion. + */ + if (!place->fpfn && + place->lpfn == i915_ttm_buddy_man_visible_size(man)) + return bman_res->used_visible_size > 0; + + /* Real range allocation */ + list_for_each_entry(block, &bman_res->blocks, link) { + unsigned long fpfn = + drm_buddy_block_offset(block) >> PAGE_SHIFT; + unsigned long lpfn = fpfn + + (drm_buddy_block_size(mm, block) >> PAGE_SHIFT); + + if (place->fpfn < lpfn && place->lpfn > fpfn) + return true; + } + return false; + } default: + break; + } + + return true; } static void i915_ttm_evict_flags(struct ttm_buffer_object *bo, @@ -585,11 +638,24 @@ static void i915_ttm_swap_notify(struct ttm_buffer_object *bo) i915_ttm_purge(obj); } +static bool i915_ttm_resource_mappable(struct ttm_resource *res) +{ + struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res); + + if (!i915_ttm_cpu_maps_iomem(res)) + return true; + + return bman_res->used_visible_size == bman_res->base.num_pages; +} + static int i915_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem) { if (!i915_ttm_cpu_maps_iomem(mem)) return 0; + if (!i915_ttm_resource_mappable(mem)) + return -EINVAL; + mem->bus.caching = ttm_write_combined; mem->bus.is_iomem = true; @@ -728,14 +794,15 @@ static int i915_ttm_get_pages(struct drm_i915_gem_object *obj) * Gem forced migration using the i915_ttm_migrate() op, is allowed even * to regions that are not in the object's list of allowable placements. */ -static int i915_ttm_migrate(struct drm_i915_gem_object *obj, - struct intel_memory_region *mr) +static int __i915_ttm_migrate(struct drm_i915_gem_object *obj, + struct intel_memory_region *mr, + unsigned int flags) { struct ttm_place requested; struct ttm_placement placement; int ret; - i915_ttm_place_from_region(mr, &requested, obj->flags); + i915_ttm_place_from_region(mr, &requested, flags); placement.num_placement = 1; placement.num_busy_placement = 1; placement.placement = &requested; @@ -758,6 +825,12 @@ static int i915_ttm_migrate(struct drm_i915_gem_object *obj, return 0; } +static int i915_ttm_migrate(struct drm_i915_gem_object *obj, + struct intel_memory_region *mr) +{ + return __i915_ttm_migrate(obj, mr, obj->flags); +} + static void i915_ttm_put_pages(struct drm_i915_gem_object *obj, struct sg_table *st) { @@ -844,7 +917,23 @@ void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj) } else if (!i915_gem_object_has_pages(obj)) { bo->priority = I915_TTM_PRIO_NO_PAGES; } else { - bo->priority = I915_TTM_PRIO_HAS_PAGES; + struct ttm_resource_manager *man = + ttm_manager_type(bo->bdev, bo->resource->mem_type); + + /* + * If we need to place an LMEM resource which doesn't need CPU + * access then we should try not to victimize mappable objects + * first, since we likely end up stealing more of the mappable + * portion. And likewise when we try to find space for a mappble + * object, we know not to ever victimize objects that don't + * occupy any mappable pages. + */ + if (i915_ttm_cpu_maps_iomem(bo->resource) && + i915_ttm_buddy_man_visible_size(man) < man->size && + !(obj->flags & I915_BO_ALLOC_GPU_ONLY)) + bo->priority = I915_TTM_PRIO_NEEDS_CPU_ACCESS; + else + bo->priority = I915_TTM_PRIO_HAS_PAGES; } ttm_bo_move_to_lru_tail(bo, bo->resource, NULL); @@ -900,6 +989,31 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } + if (!i915_ttm_resource_mappable(bo->resource)) { + int err = -ENODEV; + int i; + + for (i = 0; i < obj->mm.n_placements; i++) { + struct intel_memory_region *mr = obj->mm.placements[i]; + unsigned int flags; + + if (!mr->io_size && mr->type != INTEL_MEMORY_SYSTEM) + continue; + + flags = obj->flags; + flags &= ~I915_BO_ALLOC_GPU_ONLY; + err = __i915_ttm_migrate(obj, mr, flags); + if (!err) + break; + } + + if (err) { + drm_dbg(dev, "Unable to make resource CPU accessible\n"); + dma_resv_unlock(bo->base.resv); + return VM_FAULT_SIGBUS; + } + } + if (drm_dev_enter(dev, &idx)) { ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot, TTM_BO_VM_NUM_PREFAULT); @@ -1103,7 +1217,7 @@ i915_gem_ttm_system_setup(struct drm_i915_private *i915, mr = intel_memory_region_create(i915, 0, totalram_pages() << PAGE_SHIFT, - PAGE_SIZE, 0, + PAGE_SIZE, 0, 0, type, instance, &ttm_system_region_ops); if (IS_ERR(mr)) diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index e2eb5a2dfb30..ef15967be51a 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -502,7 +502,7 @@ static int igt_mock_memory_region_huge_pages(void *arg) int bit; int err = 0; - mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0); + mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0, 0); if (IS_ERR(mem)) { pr_err("%s failed to create memory region\n", __func__); return PTR_ERR(mem); @@ -1347,7 +1347,7 @@ try_again: err = i915_gem_object_pin_pages_unlocked(obj); if (err) { - if (err == -ENXIO || err == -E2BIG) { + if (err == -ENXIO || err == -E2BIG || err == -ENOMEM) { i915_gem_object_put(obj); size >>= 1; goto try_again; @@ -1481,6 +1481,65 @@ out: return err; } +static int igt_ppgtt_compact(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct drm_i915_gem_object *obj; + int err; + + /* + * Simple test to catch issues with compact 64K pages -- since the pt is + * compacted to 256B that gives us 32 entries per pt, however since the + * backing page for the pt is 4K, any extra entries we might incorrectly + * write out should be ignored by the HW. If ever hit such a case this + * test should catch it since some of our writes would land in scratch. + */ + + if (!HAS_64K_PAGES(i915)) { + pr_info("device lacks compact 64K page support, skipping\n"); + return 0; + } + + if (!HAS_LMEM(i915)) { + pr_info("device lacks LMEM support, skipping\n"); + return 0; + } + + /* We want the range to cover multiple page-table boundaries. */ + obj = i915_gem_object_create_lmem(i915, SZ_4M, 0); + if (IS_ERR(obj)) + return PTR_ERR(obj); + + err = i915_gem_object_pin_pages_unlocked(obj); + if (err) + goto out_put; + + if (obj->mm.page_sizes.phys < I915_GTT_PAGE_SIZE_64K) { + pr_info("LMEM compact unable to allocate huge-page(s)\n"); + goto out_unpin; + } + + /* + * Disable 2M GTT pages by forcing the page-size to 64K for the GTT + * insertion. + */ + obj->mm.page_sizes.sg = I915_GTT_PAGE_SIZE_64K; + + err = igt_write_huge(i915, obj); + if (err) + pr_err("LMEM compact write-huge failed\n"); + +out_unpin: + i915_gem_object_unpin_pages(obj); +out_put: + i915_gem_object_put(obj); + + if (err == -ENOMEM) + err = 0; + + return err; +} + static int igt_tmpfs_fallback(void *arg) { struct drm_i915_private *i915 = arg; @@ -1738,6 +1797,7 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_tmpfs_fallback), SUBTEST(igt_ppgtt_smoke_huge), SUBTEST(igt_ppgtt_sanity_check), + SUBTEST(igt_ppgtt_compact), }; if (!HAS_PPGTT(i915)) { diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c index 8f28e46e8ee5..ddd0772fd828 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c @@ -40,6 +40,7 @@ struct tiled_blits { struct blit_buffer scratch; struct i915_vma *batch; u64 hole; + u64 align; u32 width; u32 height; }; @@ -411,14 +412,19 @@ tiled_blits_create(struct intel_engine_cs *engine, struct rnd_state *prng) goto err_free; } - hole_size = 2 * PAGE_ALIGN(WIDTH * HEIGHT * 4); + t->align = i915_vm_min_alignment(t->ce->vm, INTEL_MEMORY_LOCAL); + t->align = max(t->align, + i915_vm_min_alignment(t->ce->vm, INTEL_MEMORY_SYSTEM)); + + hole_size = 2 * round_up(WIDTH * HEIGHT * 4, t->align); hole_size *= 2; /* room to maneuver */ - hole_size += 2 * I915_GTT_MIN_ALIGNMENT; + hole_size += 2 * t->align; /* padding on either side */ mutex_lock(&t->ce->vm->mutex); memset(&hole, 0, sizeof(hole)); err = drm_mm_insert_node_in_range(&t->ce->vm->mm, &hole, - hole_size, 0, I915_COLOR_UNEVICTABLE, + hole_size, t->align, + I915_COLOR_UNEVICTABLE, 0, U64_MAX, DRM_MM_INSERT_BEST); if (!err) @@ -429,7 +435,7 @@ tiled_blits_create(struct intel_engine_cs *engine, struct rnd_state *prng) goto err_put; } - t->hole = hole.start + I915_GTT_MIN_ALIGNMENT; + t->hole = hole.start + t->align; pr_info("Using hole at %llx\n", t->hole); err = tiled_blits_create_buffers(t, WIDTH, HEIGHT, prng); @@ -456,7 +462,7 @@ static void tiled_blits_destroy(struct tiled_blits *t) static int tiled_blits_prepare(struct tiled_blits *t, struct rnd_state *prng) { - u64 offset = PAGE_ALIGN(t->width * t->height * 4); + u64 offset = round_up(t->width * t->height * 4, t->align); u32 *map; int err; int i; @@ -487,8 +493,7 @@ static int tiled_blits_prepare(struct tiled_blits *t, static int tiled_blits_bounce(struct tiled_blits *t, struct rnd_state *prng) { - u64 offset = - round_up(t->width * t->height * 4, 2 * I915_GTT_MIN_ALIGNMENT); + u64 offset = round_up(t->width * t->height * 4, 2 * t->align); int err; /* We want to check position invariant tiling across GTT eviction */ @@ -501,7 +506,7 @@ static int tiled_blits_bounce(struct tiled_blits *t, struct rnd_state *prng) /* Reposition so that we overlap the old addresses, and slightly off */ err = tiled_blit(t, - &t->buffers[2], t->hole + I915_GTT_MIN_ALIGNMENT, + &t->buffers[2], t->hole + t->align, &t->buffers[1], t->hole + 3 * offset / 2); if (err) return err; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c index 2cdd8f2c002f..93a67422ca3b 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c @@ -886,7 +886,9 @@ out_file: return err; } -static int rpcs_query_batch(struct drm_i915_gem_object *rpcs, struct i915_vma *vma) +static int rpcs_query_batch(struct drm_i915_gem_object *rpcs, + struct i915_vma *vma, + struct intel_engine_cs *engine) { u32 *cmd; @@ -897,7 +899,7 @@ static int rpcs_query_batch(struct drm_i915_gem_object *rpcs, struct i915_vma *v return PTR_ERR(cmd); *cmd++ = MI_STORE_REGISTER_MEM_GEN8; - *cmd++ = i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE(RENDER_RING_BASE)); + *cmd++ = i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE(engine->mmio_base)); *cmd++ = lower_32_bits(vma->node.start); *cmd++ = upper_32_bits(vma->node.start); *cmd = MI_BATCH_BUFFER_END; @@ -958,7 +960,7 @@ retry: if (err) goto err_vma; - err = rpcs_query_batch(rpcs, vma); + err = rpcs_query_batch(rpcs, vma, ce->engine); if (err) goto err_batch; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index 6dc83255e4f3..c4c2c91a2ee7 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -9,10 +9,13 @@ #include "gem/i915_gem_internal.h" #include "gem/i915_gem_region.h" +#include "gem/i915_gem_ttm.h" #include "gt/intel_engine_pm.h" #include "gt/intel_gpu_commands.h" #include "gt/intel_gt.h" #include "gt/intel_gt_pm.h" +#include "gt/intel_migrate.h" +#include "i915_ttm_buddy_manager.h" #include "huge_gem_object.h" #include "i915_selftest.h" @@ -170,7 +173,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj, out: i915_gem_object_lock(obj, NULL); - __i915_vma_put(vma); + i915_vma_destroy(vma); i915_gem_object_unlock(obj); return err; } @@ -267,7 +270,7 @@ static int check_partial_mappings(struct drm_i915_gem_object *obj, return err; i915_gem_object_lock(obj, NULL); - __i915_vma_put(vma); + i915_vma_destroy(vma); i915_gem_object_unlock(obj); if (igt_timeout(end_time, @@ -1002,6 +1005,331 @@ static int igt_mmap(void *arg) return 0; } +static void igt_close_objects(struct drm_i915_private *i915, + struct list_head *objects) +{ + struct drm_i915_gem_object *obj, *on; + + list_for_each_entry_safe(obj, on, objects, st_link) { + i915_gem_object_lock(obj, NULL); + if (i915_gem_object_has_pinned_pages(obj)) + i915_gem_object_unpin_pages(obj); + /* No polluting the memory region between tests */ + __i915_gem_object_put_pages(obj); + i915_gem_object_unlock(obj); + list_del(&obj->st_link); + i915_gem_object_put(obj); + } + + cond_resched(); + + i915_gem_drain_freed_objects(i915); +} + +static void igt_make_evictable(struct list_head *objects) +{ + struct drm_i915_gem_object *obj; + + list_for_each_entry(obj, objects, st_link) { + i915_gem_object_lock(obj, NULL); + if (i915_gem_object_has_pinned_pages(obj)) + i915_gem_object_unpin_pages(obj); + i915_gem_object_unlock(obj); + } + + cond_resched(); +} + +static int igt_fill_mappable(struct intel_memory_region *mr, + struct list_head *objects) +{ + u64 size, total; + int err; + + total = 0; + size = mr->io_size; + do { + struct drm_i915_gem_object *obj; + + obj = i915_gem_object_create_region(mr, size, 0, 0); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + goto err_close; + } + + list_add(&obj->st_link, objects); + + err = i915_gem_object_pin_pages_unlocked(obj); + if (err) { + if (err != -ENXIO && err != -ENOMEM) + goto err_close; + + if (size == mr->min_page_size) { + err = 0; + break; + } + + size >>= 1; + continue; + } + + total += obj->base.size; + } while (1); + + pr_info("%s filled=%lluMiB\n", __func__, total >> 20); + return 0; + +err_close: + igt_close_objects(mr->i915, objects); + return err; +} + +static int ___igt_mmap_migrate(struct drm_i915_private *i915, + struct drm_i915_gem_object *obj, + unsigned long addr, + bool unfaultable) +{ + struct vm_area_struct *area; + int err = 0, i; + + pr_info("igt_mmap(%s, %d) @ %lx\n", + obj->mm.region->name, I915_MMAP_TYPE_FIXED, addr); + + mmap_read_lock(current->mm); + area = vma_lookup(current->mm, addr); + mmap_read_unlock(current->mm); + if (!area) { + pr_err("%s: Did not create a vm_area_struct for the mmap\n", + obj->mm.region->name); + err = -EINVAL; + goto out_unmap; + } + + for (i = 0; i < obj->base.size / sizeof(u32); i++) { + u32 __user *ux = u64_to_user_ptr((u64)(addr + i * sizeof(*ux))); + u32 x; + + if (get_user(x, ux)) { + err = -EFAULT; + if (!unfaultable) { + pr_err("%s: Unable to read from mmap, offset:%zd\n", + obj->mm.region->name, i * sizeof(x)); + goto out_unmap; + } + + continue; + } + + if (unfaultable) { + pr_err("%s: Faulted unmappable memory\n", + obj->mm.region->name); + err = -EINVAL; + goto out_unmap; + } + + if (x != expand32(POISON_INUSE)) { + pr_err("%s: Read incorrect value from mmap, offset:%zd, found:%x, expected:%x\n", + obj->mm.region->name, + i * sizeof(x), x, expand32(POISON_INUSE)); + err = -EINVAL; + goto out_unmap; + } + + x = expand32(POISON_FREE); + if (put_user(x, ux)) { + pr_err("%s: Unable to write to mmap, offset:%zd\n", + obj->mm.region->name, i * sizeof(x)); + err = -EFAULT; + goto out_unmap; + } + } + + if (unfaultable) { + if (err == -EFAULT) + err = 0; + } else { + obj->flags &= ~I915_BO_ALLOC_GPU_ONLY; + err = wc_check(obj); + } +out_unmap: + vm_munmap(addr, obj->base.size); + return err; +} + +#define IGT_MMAP_MIGRATE_TOPDOWN (1 << 0) +#define IGT_MMAP_MIGRATE_FILL (1 << 1) +#define IGT_MMAP_MIGRATE_EVICTABLE (1 << 2) +#define IGT_MMAP_MIGRATE_UNFAULTABLE (1 << 3) +static int __igt_mmap_migrate(struct intel_memory_region **placements, + int n_placements, + struct intel_memory_region *expected_mr, + unsigned int flags) +{ + struct drm_i915_private *i915 = placements[0]->i915; + struct drm_i915_gem_object *obj; + struct i915_request *rq = NULL; + unsigned long addr; + LIST_HEAD(objects); + u64 offset; + int err; + + obj = __i915_gem_object_create_user(i915, PAGE_SIZE, + placements, + n_placements); + if (IS_ERR(obj)) + return PTR_ERR(obj); + + if (flags & IGT_MMAP_MIGRATE_TOPDOWN) + obj->flags |= I915_BO_ALLOC_GPU_ONLY; + + err = __assign_mmap_offset(obj, I915_MMAP_TYPE_FIXED, &offset, NULL); + if (err) + goto out_put; + + /* + * This will eventually create a GEM context, due to opening dummy drm + * file, which needs a tiny amount of mappable device memory for the top + * level paging structures(and perhaps scratch), so make sure we + * allocate early, to avoid tears. + */ + addr = igt_mmap_offset(i915, offset, obj->base.size, + PROT_WRITE, MAP_SHARED); + if (IS_ERR_VALUE(addr)) { + err = addr; + goto out_put; + } + + if (flags & IGT_MMAP_MIGRATE_FILL) { + err = igt_fill_mappable(placements[0], &objects); + if (err) + goto out_put; + } + + err = i915_gem_object_lock(obj, NULL); + if (err) + goto out_put; + + err = i915_gem_object_pin_pages(obj); + if (err) { + i915_gem_object_unlock(obj); + goto out_put; + } + + err = intel_context_migrate_clear(to_gt(i915)->migrate.context, NULL, + obj->mm.pages->sgl, obj->cache_level, + i915_gem_object_is_lmem(obj), + expand32(POISON_INUSE), &rq); + i915_gem_object_unpin_pages(obj); + if (rq) { + dma_resv_add_excl_fence(obj->base.resv, &rq->fence); + i915_gem_object_set_moving_fence(obj, &rq->fence); + i915_request_put(rq); + } + i915_gem_object_unlock(obj); + if (err) + goto out_put; + + if (flags & IGT_MMAP_MIGRATE_EVICTABLE) + igt_make_evictable(&objects); + + err = ___igt_mmap_migrate(i915, obj, addr, + flags & IGT_MMAP_MIGRATE_UNFAULTABLE); + if (!err && obj->mm.region != expected_mr) { + pr_err("%s region mismatch %s\n", __func__, expected_mr->name); + err = -EINVAL; + } + +out_put: + i915_gem_object_put(obj); + igt_close_objects(i915, &objects); + return err; +} + +static int igt_mmap_migrate(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct intel_memory_region *system = i915->mm.regions[INTEL_REGION_SMEM]; + struct intel_memory_region *mr; + enum intel_region_id id; + + for_each_memory_region(mr, i915, id) { + struct intel_memory_region *mixed[] = { mr, system }; + struct intel_memory_region *single[] = { mr }; + struct ttm_resource_manager *man = mr->region_private; + resource_size_t saved_io_size; + int err; + + if (mr->private) + continue; + + if (!mr->io_size) + continue; + + /* + * For testing purposes let's force small BAR, if not already + * present. + */ + saved_io_size = mr->io_size; + if (mr->io_size == mr->total) { + resource_size_t io_size = mr->io_size; + + io_size = rounddown_pow_of_two(io_size >> 1); + if (io_size < PAGE_SIZE) + continue; + + mr->io_size = io_size; + i915_ttm_buddy_man_force_visible_size(man, + io_size >> PAGE_SHIFT); + } + + /* + * Allocate in the mappable portion, should be no suprises here. + */ + err = __igt_mmap_migrate(mixed, ARRAY_SIZE(mixed), mr, 0); + if (err) + goto out_io_size; + + /* + * Allocate in the non-mappable portion, but force migrating to + * the mappable portion on fault (LMEM -> LMEM) + */ + err = __igt_mmap_migrate(single, ARRAY_SIZE(single), mr, + IGT_MMAP_MIGRATE_TOPDOWN | + IGT_MMAP_MIGRATE_FILL | + IGT_MMAP_MIGRATE_EVICTABLE); + if (err) + goto out_io_size; + + /* + * Allocate in the non-mappable portion, but force spilling into + * system memory on fault (LMEM -> SMEM) + */ + err = __igt_mmap_migrate(mixed, ARRAY_SIZE(mixed), system, + IGT_MMAP_MIGRATE_TOPDOWN | + IGT_MMAP_MIGRATE_FILL); + if (err) + goto out_io_size; + + /* + * Allocate in the non-mappable portion, but since the mappable + * portion is already full, and we can't spill to system memory, + * then we should expect the fault to fail. + */ + err = __igt_mmap_migrate(single, ARRAY_SIZE(single), mr, + IGT_MMAP_MIGRATE_TOPDOWN | + IGT_MMAP_MIGRATE_FILL | + IGT_MMAP_MIGRATE_UNFAULTABLE); +out_io_size: + mr->io_size = saved_io_size; + i915_ttm_buddy_man_force_visible_size(man, + mr->io_size >> PAGE_SHIFT); + if (err) + return err; + } + + return 0; +} + static const char *repr_mmap_type(enum i915_mmap_type type) { switch (type) { @@ -1427,6 +1755,7 @@ int i915_gem_mman_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_smoke_tiling), SUBTEST(igt_mmap_offset_exhaustion), SUBTEST(igt_mmap), + SUBTEST(igt_mmap_migrate), SUBTEST(igt_mmap_access), SUBTEST(igt_mmap_revoke), SUBTEST(igt_mmap_gpu), diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 1f8cf4f790b2..b1b9c3fd7bf9 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -201,6 +201,8 @@ static u32 *gen12_emit_aux_table_inv(const i915_reg_t inv_reg, u32 *cs) int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) { + struct intel_engine_cs *engine = rq->engine; + if (mode & EMIT_FLUSH) { u32 flags = 0; u32 *cs; @@ -219,6 +221,9 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) flags |= PIPE_CONTROL_CS_STALL; + if (engine->class == COMPUTE_CLASS) + flags &= ~PIPE_CONTROL_3D_FLAGS; + cs = intel_ring_begin(rq, 6); if (IS_ERR(cs)) return PTR_ERR(cs); @@ -246,6 +251,9 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) flags |= PIPE_CONTROL_CS_STALL; + if (engine->class == COMPUTE_CLASS) + flags &= ~PIPE_CONTROL_3D_FLAGS; + cs = intel_ring_begin(rq, 8 + 4); if (IS_ERR(cs)) return PTR_ERR(cs); @@ -618,19 +626,27 @@ u32 *gen12_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs) u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs) { + struct drm_i915_private *i915 = rq->engine->i915; + u32 flags = (PIPE_CONTROL_CS_STALL | + PIPE_CONTROL_TILE_CACHE_FLUSH | + PIPE_CONTROL_FLUSH_L3 | + PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | + PIPE_CONTROL_DEPTH_CACHE_FLUSH | + PIPE_CONTROL_DC_FLUSH_ENABLE | + PIPE_CONTROL_FLUSH_ENABLE); + + if (GRAPHICS_VER(i915) == 12 && GRAPHICS_VER_FULL(i915) < IP_VER(12, 50)) + /* Wa_1409600907 */ + flags |= PIPE_CONTROL_DEPTH_STALL; + + if (rq->engine->class == COMPUTE_CLASS) + flags &= ~PIPE_CONTROL_3D_FLAGS; + cs = gen12_emit_ggtt_write_rcs(cs, rq->fence.seqno, hwsp_offset(rq), PIPE_CONTROL0_HDC_PIPELINE_FLUSH, - PIPE_CONTROL_CS_STALL | - PIPE_CONTROL_TILE_CACHE_FLUSH | - PIPE_CONTROL_FLUSH_L3 | - PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | - PIPE_CONTROL_DEPTH_CACHE_FLUSH | - /* Wa_1409600907:tgl */ - PIPE_CONTROL_DEPTH_STALL | - PIPE_CONTROL_DC_FLUSH_ENABLE | - PIPE_CONTROL_FLUSH_ENABLE); + flags); return gen12_emit_fini_breadcrumb_tail(rq, cs); } diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index c43e724afa9f..f574da00eff1 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -233,6 +233,8 @@ static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm, start, end, lvl); } else { unsigned int count; + unsigned int pte = gen8_pd_index(start, 0); + unsigned int num_ptes; u64 *vaddr; count = gen8_pt_count(start, end); @@ -242,10 +244,18 @@ static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm, atomic_read(&pt->used)); GEM_BUG_ON(!count || count >= atomic_read(&pt->used)); + num_ptes = count; + if (pt->is_compact) { + GEM_BUG_ON(num_ptes % 16); + GEM_BUG_ON(pte % 16); + num_ptes /= 16; + pte /= 16; + } + vaddr = px_vaddr(pt); - memset64(vaddr + gen8_pd_index(start, 0), + memset64(vaddr + pte, vm->scratch[0]->encode, - count); + num_ptes); atomic_sub(count, &pt->used); start += count; @@ -453,6 +463,95 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt, return idx; } +static void +xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm, + struct i915_vma_resource *vma_res, + struct sgt_dma *iter, + enum i915_cache_level cache_level, + u32 flags) +{ + const gen8_pte_t pte_encode = vm->pte_encode(0, cache_level, flags); + unsigned int rem = sg_dma_len(iter->sg); + u64 start = vma_res->start; + + GEM_BUG_ON(!i915_vm_is_4lvl(vm)); + + do { + struct i915_page_directory * const pdp = + gen8_pdp_for_page_address(vm, start); + struct i915_page_directory * const pd = + i915_pd_entry(pdp, __gen8_pte_index(start, 2)); + struct i915_page_table *pt = + i915_pt_entry(pd, __gen8_pte_index(start, 1)); + gen8_pte_t encode = pte_encode; + unsigned int page_size; + gen8_pte_t *vaddr; + u16 index, max; + + max = I915_PDES; + + if (vma_res->bi.page_sizes.sg & I915_GTT_PAGE_SIZE_2M && + IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_2M) && + rem >= I915_GTT_PAGE_SIZE_2M && + !__gen8_pte_index(start, 0)) { + index = __gen8_pte_index(start, 1); + encode |= GEN8_PDE_PS_2M; + page_size = I915_GTT_PAGE_SIZE_2M; + + vaddr = px_vaddr(pd); + } else { + if (encode & GEN12_PPGTT_PTE_LM) { + GEM_BUG_ON(__gen8_pte_index(start, 0) % 16); + GEM_BUG_ON(rem < I915_GTT_PAGE_SIZE_64K); + GEM_BUG_ON(!IS_ALIGNED(iter->dma, + I915_GTT_PAGE_SIZE_64K)); + + index = __gen8_pte_index(start, 0) / 16; + page_size = I915_GTT_PAGE_SIZE_64K; + + max /= 16; + + vaddr = px_vaddr(pd); + vaddr[__gen8_pte_index(start, 1)] |= GEN12_PDE_64K; + + pt->is_compact = true; + } else { + GEM_BUG_ON(pt->is_compact); + index = __gen8_pte_index(start, 0); + page_size = I915_GTT_PAGE_SIZE; + } + + vaddr = px_vaddr(pt); + } + + do { + GEM_BUG_ON(rem < page_size); + vaddr[index++] = encode | iter->dma; + + start += page_size; + iter->dma += page_size; + rem -= page_size; + if (iter->dma >= iter->max) { + iter->sg = __sg_next(iter->sg); + if (!iter->sg) + break; + + rem = sg_dma_len(iter->sg); + if (!rem) + break; + + iter->dma = sg_dma_address(iter->sg); + iter->max = iter->dma + rem; + + if (unlikely(!IS_ALIGNED(iter->dma, page_size))) + break; + } + } while (rem >= page_size && index < max); + + vma_res->page_sizes_gtt |= page_size; + } while (iter->sg && sg_dma_len(iter->sg)); +} + static void gen8_ppgtt_insert_huge(struct i915_address_space *vm, struct i915_vma_resource *vma_res, struct sgt_dma *iter, @@ -586,7 +685,10 @@ static void gen8_ppgtt_insert(struct i915_address_space *vm, struct sgt_dma iter = sgt_dma(vma_res); if (vma_res->bi.page_sizes.sg > I915_GTT_PAGE_SIZE) { - gen8_ppgtt_insert_huge(vm, vma_res, &iter, cache_level, flags); + if (HAS_64K_PAGES(vm->i915)) + xehpsdv_ppgtt_insert_huge(vm, vma_res, &iter, cache_level, flags); + else + gen8_ppgtt_insert_huge(vm, vma_res, &iter, cache_level, flags); } else { u64 idx = vma_res->start >> GEN8_PTE_SHIFT; @@ -613,13 +715,56 @@ static void gen8_ppgtt_insert_entry(struct i915_address_space *vm, gen8_pdp_for_page_index(vm, idx); struct i915_page_directory *pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2)); + struct i915_page_table *pt = i915_pt_entry(pd, gen8_pd_index(idx, 1)); gen8_pte_t *vaddr; - vaddr = px_vaddr(i915_pt_entry(pd, gen8_pd_index(idx, 1))); + GEM_BUG_ON(pt->is_compact); + + vaddr = px_vaddr(pt); vaddr[gen8_pd_index(idx, 0)] = gen8_pte_encode(addr, level, flags); clflush_cache_range(&vaddr[gen8_pd_index(idx, 0)], sizeof(*vaddr)); } +static void __xehpsdv_ppgtt_insert_entry_lm(struct i915_address_space *vm, + dma_addr_t addr, + u64 offset, + enum i915_cache_level level, + u32 flags) +{ + u64 idx = offset >> GEN8_PTE_SHIFT; + struct i915_page_directory * const pdp = + gen8_pdp_for_page_index(vm, idx); + struct i915_page_directory *pd = + i915_pd_entry(pdp, gen8_pd_index(idx, 2)); + struct i915_page_table *pt = i915_pt_entry(pd, gen8_pd_index(idx, 1)); + gen8_pte_t *vaddr; + + GEM_BUG_ON(!IS_ALIGNED(addr, SZ_64K)); + GEM_BUG_ON(!IS_ALIGNED(offset, SZ_64K)); + + if (!pt->is_compact) { + vaddr = px_vaddr(pd); + vaddr[gen8_pd_index(idx, 1)] |= GEN12_PDE_64K; + pt->is_compact = true; + } + + vaddr = px_vaddr(pt); + vaddr[gen8_pd_index(idx, 0) / 16] = gen8_pte_encode(addr, level, flags); +} + +static void xehpsdv_ppgtt_insert_entry(struct i915_address_space *vm, + dma_addr_t addr, + u64 offset, + enum i915_cache_level level, + u32 flags) +{ + if (flags & PTE_LM) + return __xehpsdv_ppgtt_insert_entry_lm(vm, addr, offset, + level, flags); + + return gen8_ppgtt_insert_entry(vm, addr, offset, level, flags); +} + static int gen8_init_scratch(struct i915_address_space *vm) { u32 pte_flags; @@ -819,7 +964,10 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt, ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND; ppgtt->vm.insert_entries = gen8_ppgtt_insert; - ppgtt->vm.insert_page = gen8_ppgtt_insert_entry; + if (HAS_64K_PAGES(gt->i915)) + ppgtt->vm.insert_page = xehpsdv_ppgtt_insert_entry; + else + ppgtt->vm.insert_page = gen8_ppgtt_insert_entry; ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc; ppgtt->vm.clear_range = gen8_ppgtt_clear; ppgtt->vm.foreach = gen8_ppgtt_foreach; diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index be4b1e65442f..1c0ab05c3c40 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -265,6 +265,8 @@ intel_engine_create_pinned_context(struct intel_engine_cs *engine, void intel_engine_destroy_pinned_context(struct intel_context *ce); +void xehp_enable_ccs_engines(struct intel_engine_cs *engine); + #define ENGINE_PHYSICAL 0 #define ENGINE_MOCK 1 #define ENGINE_VIRTUAL 2 diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 501e7b37bc26..7447411a5b26 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -23,6 +23,7 @@ #include "intel_gt.h" #include "intel_gt_requests.h" #include "intel_gt_pm.h" +#include "intel_lrc.h" #include "intel_lrc_reg.h" #include "intel_reset.h" #include "intel_ring.h" @@ -158,6 +159,34 @@ static const struct engine_info intel_engines[] = { { .graphics_ver = 12, .base = XEHP_VEBOX4_RING_BASE } }, }, + [CCS0] = { + .class = COMPUTE_CLASS, + .instance = 0, + .mmio_bases = { + { .graphics_ver = 12, .base = GEN12_COMPUTE0_RING_BASE } + } + }, + [CCS1] = { + .class = COMPUTE_CLASS, + .instance = 1, + .mmio_bases = { + { .graphics_ver = 12, .base = GEN12_COMPUTE1_RING_BASE } + } + }, + [CCS2] = { + .class = COMPUTE_CLASS, + .instance = 2, + .mmio_bases = { + { .graphics_ver = 12, .base = GEN12_COMPUTE2_RING_BASE } + } + }, + [CCS3] = { + .class = COMPUTE_CLASS, + .instance = 3, + .mmio_bases = { + { .graphics_ver = 12, .base = GEN12_COMPUTE3_RING_BASE } + } + }, }; /** @@ -182,6 +211,8 @@ u32 intel_engine_context_size(struct intel_gt *gt, u8 class) BUILD_BUG_ON(I915_GTT_PAGE_SIZE != PAGE_SIZE); switch (class) { + case COMPUTE_CLASS: + fallthrough; case RENDER_CLASS: switch (GRAPHICS_VER(gt->i915)) { default: @@ -295,6 +326,50 @@ static void nop_irq_handler(struct intel_engine_cs *engine, u16 iir) GEM_DEBUG_WARN_ON(iir); } +static u32 get_reset_domain(u8 ver, enum intel_engine_id id) +{ + u32 reset_domain; + + if (ver >= 11) { + static const u32 engine_reset_domains[] = { + [RCS0] = GEN11_GRDOM_RENDER, + [BCS0] = GEN11_GRDOM_BLT, + [VCS0] = GEN11_GRDOM_MEDIA, + [VCS1] = GEN11_GRDOM_MEDIA2, + [VCS2] = GEN11_GRDOM_MEDIA3, + [VCS3] = GEN11_GRDOM_MEDIA4, + [VCS4] = GEN11_GRDOM_MEDIA5, + [VCS5] = GEN11_GRDOM_MEDIA6, + [VCS6] = GEN11_GRDOM_MEDIA7, + [VCS7] = GEN11_GRDOM_MEDIA8, + [VECS0] = GEN11_GRDOM_VECS, + [VECS1] = GEN11_GRDOM_VECS2, + [VECS2] = GEN11_GRDOM_VECS3, + [VECS3] = GEN11_GRDOM_VECS4, + [CCS0] = GEN11_GRDOM_RENDER, + [CCS1] = GEN11_GRDOM_RENDER, + [CCS2] = GEN11_GRDOM_RENDER, + [CCS3] = GEN11_GRDOM_RENDER, + }; + GEM_BUG_ON(id >= ARRAY_SIZE(engine_reset_domains) || + !engine_reset_domains[id]); + reset_domain = engine_reset_domains[id]; + } else { + static const u32 engine_reset_domains[] = { + [RCS0] = GEN6_GRDOM_RENDER, + [BCS0] = GEN6_GRDOM_BLT, + [VCS0] = GEN6_GRDOM_MEDIA, + [VCS1] = GEN8_GRDOM_MEDIA2, + [VECS0] = GEN6_GRDOM_VECS, + }; + GEM_BUG_ON(id >= ARRAY_SIZE(engine_reset_domains) || + !engine_reset_domains[id]); + reset_domain = engine_reset_domains[id]; + } + + return reset_domain; +} + static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, u8 logical_instance) { @@ -330,38 +405,8 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, engine->id = id; engine->legacy_idx = INVALID_ENGINE; engine->mask = BIT(id); - if (GRAPHICS_VER(gt->i915) >= 11) { - static const u32 engine_reset_domains[] = { - [RCS0] = GEN11_GRDOM_RENDER, - [BCS0] = GEN11_GRDOM_BLT, - [VCS0] = GEN11_GRDOM_MEDIA, - [VCS1] = GEN11_GRDOM_MEDIA2, - [VCS2] = GEN11_GRDOM_MEDIA3, - [VCS3] = GEN11_GRDOM_MEDIA4, - [VCS4] = GEN11_GRDOM_MEDIA5, - [VCS5] = GEN11_GRDOM_MEDIA6, - [VCS6] = GEN11_GRDOM_MEDIA7, - [VCS7] = GEN11_GRDOM_MEDIA8, - [VECS0] = GEN11_GRDOM_VECS, - [VECS1] = GEN11_GRDOM_VECS2, - [VECS2] = GEN11_GRDOM_VECS3, - [VECS3] = GEN11_GRDOM_VECS4, - }; - GEM_BUG_ON(id >= ARRAY_SIZE(engine_reset_domains) || - !engine_reset_domains[id]); - engine->reset_domain = engine_reset_domains[id]; - } else { - static const u32 engine_reset_domains[] = { - [RCS0] = GEN6_GRDOM_RENDER, - [BCS0] = GEN6_GRDOM_BLT, - [VCS0] = GEN6_GRDOM_MEDIA, - [VCS1] = GEN8_GRDOM_MEDIA2, - [VECS0] = GEN6_GRDOM_VECS, - }; - GEM_BUG_ON(id >= ARRAY_SIZE(engine_reset_domains) || - !engine_reset_domains[id]); - engine->reset_domain = engine_reset_domains[id]; - } + engine->reset_domain = get_reset_domain(GRAPHICS_VER(gt->i915), + id); engine->i915 = i915; engine->gt = gt; engine->uncore = gt->uncore; @@ -391,6 +436,12 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, if (GRAPHICS_VER(i915) == 12 && engine->class == RENDER_CLASS) engine->props.preempt_timeout_ms = 0; + /* features common between engines sharing EUs */ + if (engine->class == RENDER_CLASS || engine->class == COMPUTE_CLASS) { + engine->flags |= I915_ENGINE_HAS_RCS_REG_STATE; + engine->flags |= I915_ENGINE_HAS_EU_PRIORITY; + } + engine->defaults = engine->props; /* never to change again */ engine->context_size = intel_engine_context_size(gt, engine->class); @@ -543,6 +594,29 @@ bool gen11_vdbox_has_sfc(struct intel_gt *gt, return false; } +static void engine_mask_apply_compute_fuses(struct intel_gt *gt) +{ + struct drm_i915_private *i915 = gt->i915; + struct intel_gt_info *info = >->info; + int ss_per_ccs = info->sseu.max_subslices / I915_MAX_CCS; + unsigned long ccs_mask; + unsigned int i; + + if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 50)) + return; + + ccs_mask = intel_slicemask_from_dssmask(intel_sseu_get_compute_subslices(&info->sseu), + ss_per_ccs); + /* + * If all DSS in a quadrant are fused off, the corresponding CCS + * engine is not available for use. + */ + for_each_clear_bit(i, &ccs_mask, I915_MAX_CCS) { + info->engine_mask &= ~BIT(_CCS(i)); + drm_dbg(&i915->drm, "ccs%u fused off\n", i); + } +} + /* * Determine which engines are fused off in our particular hardware. * Note that we have a catch-22 situation where we need to be able to access @@ -624,6 +698,8 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt) vebox_mask, VEBOX_MASK(gt)); GEM_BUG_ON(vebox_mask != VEBOX_MASK(gt)); + engine_mask_apply_compute_fuses(gt); + return info->engine_mask; } @@ -2020,6 +2096,23 @@ intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine) return active; } +void xehp_enable_ccs_engines(struct intel_engine_cs *engine) +{ + /* + * If there are any non-fused-off CCS engines, we need to enable CCS + * support in the RCU_MODE register. This only needs to be done once, + * so for simplicity we'll take care of this in the RCS engine's + * resume handler; since the RCS and all CCS engines belong to the + * same reset domain and are reset together, this will also take care + * of re-applying the setting after i915-triggered resets. + */ + if (!CCS_MASK(engine->gt)) + return; + + intel_uncore_write(engine->uncore, GEN12_RCU_MODE, + _MASKED_BIT_ENABLE(GEN12_RCU_MODE_CCS_ENABLE)); +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "mock_engine.c" #include "selftest_engine.c" diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 36365bdbe1ee..19ff8758e34d 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -33,7 +33,8 @@ #define VIDEO_ENHANCEMENT_CLASS 2 #define COPY_ENGINE_CLASS 3 #define OTHER_CLASS 4 -#define MAX_ENGINE_CLASS 4 +#define COMPUTE_CLASS 5 +#define MAX_ENGINE_CLASS 5 #define MAX_ENGINE_INSTANCE 7 #define I915_MAX_SLICES 3 @@ -95,6 +96,7 @@ struct i915_ctx_workarounds { #define I915_MAX_VCS 8 #define I915_MAX_VECS 4 +#define I915_MAX_CCS 4 /* * Engine IDs definitions. @@ -117,6 +119,11 @@ enum intel_engine_id { VECS2, VECS3, #define _VECS(n) (VECS0 + (n)) + CCS0, + CCS1, + CCS2, + CCS3, +#define _CCS(n) (CCS0 + (n)) I915_NUM_ENGINES #define INVALID_ENGINE ((enum intel_engine_id)-1) }; @@ -517,6 +524,8 @@ struct intel_engine_cs { #define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6) #define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7) #define I915_ENGINE_WANT_FORCED_PREEMPTION BIT(8) +#define I915_ENGINE_HAS_RCS_REG_STATE BIT(9) +#define I915_ENGINE_HAS_EU_PRIORITY BIT(10) unsigned int flags; /* diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c index 9ce85a845105..b8c9b6b89003 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_user.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c @@ -47,6 +47,7 @@ static const u8 uabi_classes[] = { [COPY_ENGINE_CLASS] = I915_ENGINE_CLASS_COPY, [VIDEO_DECODE_CLASS] = I915_ENGINE_CLASS_VIDEO, [VIDEO_ENHANCEMENT_CLASS] = I915_ENGINE_CLASS_VIDEO_ENHANCE, + /* TODO: Add COMPUTE_CLASS mapping once ABI is available */ }; static int engine_cmp(void *priv, const struct list_head *A, @@ -139,6 +140,7 @@ const char *intel_engine_class_repr(u8 class) [COPY_ENGINE_CLASS] = "bcs", [VIDEO_DECODE_CLASS] = "vcs", [VIDEO_ENHANCEMENT_CLASS] = "vecs", + [COMPUTE_CLASS] = "ccs", }; if (class >= ARRAY_SIZE(uabi_names) || !uabi_names[class]) @@ -162,6 +164,7 @@ static int legacy_ring_idx(const struct legacy_ring *ring) [COPY_ENGINE_CLASS] = { BCS0, 1 }, [VIDEO_DECODE_CLASS] = { VCS0, I915_MAX_VCS }, [VIDEO_ENHANCEMENT_CLASS] = { VECS0, I915_MAX_VECS }, + [COMPUTE_CLASS] = { CCS0, I915_MAX_CCS }, }; if (GEM_DEBUG_WARN_ON(ring->class >= ARRAY_SIZE(map))) @@ -190,7 +193,7 @@ static void add_legacy_ring(struct legacy_ring *ring, void intel_engines_driver_register(struct drm_i915_private *i915) { struct legacy_ring ring = {}; - u8 uabi_instances[4] = {}; + u8 uabi_instances[5] = {}; struct list_head *it, *next; struct rb_node **p, *prev; LIST_HEAD(engines); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 42bfbafad32a..1c602d4ae297 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -666,9 +666,13 @@ static inline void execlists_schedule_out(struct i915_request *rq) static u64 execlists_update_context(struct i915_request *rq) { struct intel_context *ce = rq->context; - u64 desc = ce->lrc.desc; + u64 desc; u32 tail, prev; + desc = ce->lrc.desc; + if (rq->engine->flags & I915_ENGINE_HAS_EU_PRIORITY) + desc |= lrc_desc_priority(rq_prio(rq)); + /* * WaIdleLiteRestore:bdw,skl * @@ -2908,6 +2912,9 @@ static int execlists_resume(struct intel_engine_cs *engine) enable_execlists(engine); + if (engine->class == RENDER_CLASS) + xehp_enable_ccs_engines(engine); + return 0; } @@ -3481,7 +3488,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) logical_ring_default_vfuncs(engine); logical_ring_default_irqs(engine); - if (engine->class == RENDER_CLASS) + if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE) rcs_submission_override(engine); lrc_init_wa_ctx(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h index f8253012d166..d112ffd56418 100644 --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h @@ -228,11 +228,14 @@ #define PIPE_CONTROL_COMMAND_CACHE_INVALIDATE (1<<29) /* gen11+ */ #define PIPE_CONTROL_TILE_CACHE_FLUSH (1<<28) /* gen11+ */ #define PIPE_CONTROL_FLUSH_L3 (1<<27) +#define PIPE_CONTROL_AMFS_FLUSH (1<<25) /* gen12+ */ #define PIPE_CONTROL_GLOBAL_GTT_IVB (1<<24) /* gen7+ */ #define PIPE_CONTROL_MMIO_WRITE (1<<23) #define PIPE_CONTROL_STORE_DATA_INDEX (1<<21) #define PIPE_CONTROL_CS_STALL (1<<20) +#define PIPE_CONTROL_GLOBAL_SNAPSHOT_RESET (1<<19) #define PIPE_CONTROL_TLB_INVALIDATE (1<<18) +#define PIPE_CONTROL_PSD_SYNC (1<<17) /* gen11+ */ #define PIPE_CONTROL_MEDIA_STATE_CLEAR (1<<16) #define PIPE_CONTROL_WRITE_TIMESTAMP (3<<14) #define PIPE_CONTROL_QW_WRITE (1<<14) @@ -254,6 +257,18 @@ #define PIPE_CONTROL_DEPTH_CACHE_FLUSH (1<<0) #define PIPE_CONTROL_GLOBAL_GTT (1<<2) /* in addr dword */ +/* 3D-related flags can't be set on compute engine */ +#define PIPE_CONTROL_3D_FLAGS (\ + PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | \ + PIPE_CONTROL_DEPTH_CACHE_FLUSH | \ + PIPE_CONTROL_TILE_CACHE_FLUSH | \ + PIPE_CONTROL_DEPTH_STALL | \ + PIPE_CONTROL_STALL_AT_SCOREBOARD | \ + PIPE_CONTROL_PSD_SYNC | \ + PIPE_CONTROL_AMFS_FLUSH | \ + PIPE_CONTROL_VF_CACHE_INVALIDATE | \ + PIPE_CONTROL_GLOBAL_SNAPSHOT_RESET) + #define MI_MATH(x) MI_INSTR(0x1a, (x) - 1) #define MI_MATH_INSTR(opcode, op1, op2) ((opcode) << 20 | (op1) << 10 | (op2)) /* Opcodes for MI_MATH_INSTR */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index e8403fa53909..8a2483ccbfb9 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -65,8 +65,6 @@ int intel_gt_probe_lmem(struct intel_gt *gt) int err; mem = intel_gt_setup_lmem(gt); - if (mem == ERR_PTR(-ENODEV)) - mem = intel_gt_setup_fake_lmem(gt); if (IS_ERR(mem)) { err = PTR_ERR(mem); if (err == -ENODEV) @@ -458,7 +456,9 @@ static int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size) struct i915_vma *vma; int ret; - obj = i915_gem_object_create_lmem(i915, size, I915_BO_ALLOC_VOLATILE); + obj = i915_gem_object_create_lmem(i915, size, + I915_BO_ALLOC_VOLATILE | + I915_BO_ALLOC_GPU_ONLY); if (IS_ERR(obj)) obj = i915_gem_object_create_stolen(i915, size); if (IS_ERR(obj)) @@ -913,6 +913,25 @@ u32 intel_gt_read_register_fw(struct intel_gt *gt, i915_reg_t reg) return intel_uncore_read_fw(gt->uncore, reg); } +u32 intel_gt_read_register(struct intel_gt *gt, i915_reg_t reg) +{ + int type; + u8 sliceid, subsliceid; + + for (type = 0; type < NUM_STEERING_TYPES; type++) { + if (intel_gt_reg_needs_read_steering(gt, reg, type)) { + intel_gt_get_valid_steering(gt, type, &sliceid, + &subsliceid); + return intel_uncore_read_with_mcr_steering(gt->uncore, + reg, + sliceid, + subsliceid); + } + } + + return intel_uncore_read(gt->uncore, reg); +} + void intel_gt_info_print(const struct intel_gt_info *info, struct drm_printer *p) { diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 2dad46c3eff2..0f571c8ee22b 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -85,6 +85,7 @@ static inline bool intel_gt_needs_read_steering(struct intel_gt *gt, } u32 intel_gt_read_register_fw(struct intel_gt *gt, i915_reg_t reg); +u32 intel_gt_read_register(struct intel_gt *gt, i915_reg_t reg); void intel_gt_info_print(const struct intel_gt_info *info, struct drm_printer *p); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index 983264e10e0a..e443ac4c8059 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -100,7 +100,7 @@ gen11_gt_identity_handler(struct intel_gt *gt, const u32 identity) if (unlikely(!intr)) return; - if (class <= COPY_ENGINE_CLASS) + if (class <= COPY_ENGINE_CLASS || class == COMPUTE_CLASS) return gen11_engine_irq_handler(gt, class, instance, intr); if (class == OTHER_CLASS) @@ -182,6 +182,8 @@ void gen11_gt_irq_reset(struct intel_gt *gt) /* Disable RCS, BCS, VCS and VECS class engines. */ intel_uncore_write(uncore, GEN11_RENDER_COPY_INTR_ENABLE, 0); intel_uncore_write(uncore, GEN11_VCS_VECS_INTR_ENABLE, 0); + if (CCS_MASK(gt)) + intel_uncore_write(uncore, GEN12_CCS_RSVD_INTR_ENABLE, 0); /* Restore masks irqs on RCS, BCS, VCS and VECS engines. */ intel_uncore_write(uncore, GEN11_RCS0_RSVD_INTR_MASK, ~0); @@ -195,6 +197,10 @@ void gen11_gt_irq_reset(struct intel_gt *gt) intel_uncore_write(uncore, GEN11_VECS0_VECS1_INTR_MASK, ~0); if (HAS_ENGINE(gt, VECS2) || HAS_ENGINE(gt, VECS3)) intel_uncore_write(uncore, GEN12_VECS2_VECS3_INTR_MASK, ~0); + if (HAS_ENGINE(gt, CCS0) || HAS_ENGINE(gt, CCS1)) + intel_uncore_write(uncore, GEN12_CCS0_CCS1_INTR_MASK, ~0); + if (HAS_ENGINE(gt, CCS2) || HAS_ENGINE(gt, CCS3)) + intel_uncore_write(uncore, GEN12_CCS2_CCS3_INTR_MASK, ~0); intel_uncore_write(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE, 0); intel_uncore_write(uncore, GEN11_GPM_WGBOXPERF_INTR_MASK, ~0); @@ -225,6 +231,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) /* Enable RCS, BCS, VCS and VECS class interrupts. */ intel_uncore_write(uncore, GEN11_RENDER_COPY_INTR_ENABLE, dmask); intel_uncore_write(uncore, GEN11_VCS_VECS_INTR_ENABLE, dmask); + if (CCS_MASK(gt)) + intel_uncore_write(uncore, GEN12_CCS_RSVD_INTR_ENABLE, smask); /* Unmask irqs on RCS, BCS, VCS and VECS engines. */ intel_uncore_write(uncore, GEN11_RCS0_RSVD_INTR_MASK, ~smask); @@ -238,6 +246,11 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) intel_uncore_write(uncore, GEN11_VECS0_VECS1_INTR_MASK, ~dmask); if (HAS_ENGINE(gt, VECS2) || HAS_ENGINE(gt, VECS3)) intel_uncore_write(uncore, GEN12_VECS2_VECS3_INTR_MASK, ~dmask); + if (HAS_ENGINE(gt, CCS0) || HAS_ENGINE(gt, CCS1)) + intel_uncore_write(uncore, GEN12_CCS0_CCS1_INTR_MASK, ~dmask); + if (HAS_ENGINE(gt, CCS2) || HAS_ENGINE(gt, CCS3)) + intel_uncore_write(uncore, GEN12_CCS2_CCS3_INTR_MASK, ~dmask); + /* * RPS interrupts will get enabled/disabled on demand when RPS itself * is enabled/disabled. diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 1545867c6da1..201b507c9dde 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -465,6 +465,9 @@ #define GEN9_PGCTL_SSB_EU210_ACK (1 << 12) #define GEN9_PGCTL_SSB_EU311_ACK (1 << 14) +#define VF_PREEMPTION _MMIO(0x83a4) +#define PREEMPTION_VERTEX_COUNT REG_GENMASK(15, 0) + #define GEN8_RC6_CTX_INFO _MMIO(0x8504) #define GEN12_SQCM _MMIO(0x8724) @@ -1057,6 +1060,7 @@ #define FLOW_CONTROL_ENABLE REG_BIT(15) #define UGM_BACKUP_MODE REG_BIT(13) #define MDQ_ARBITRATION_MODE REG_BIT(12) +#define SYSTOLIC_DOP_CLOCK_GATING_DIS REG_BIT(10) #define PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE REG_BIT(8) #define STALL_DOP_GATING_DISABLE REG_BIT(5) #define THROTTLE_12_5 REG_GENMASK(4, 2) @@ -1324,6 +1328,9 @@ #define ECOBITS_PPGTT_CACHE64B (3 << 8) #define ECOBITS_PPGTT_CACHE4B (0 << 8) +#define GEN12_RCU_MODE _MMIO(0x14800) +#define GEN12_RCU_MODE_CCS_ENABLE REG_BIT(0) + #define CHV_FUSE_GT _MMIO(VLV_DISPLAY_BASE + 0x2168) #define CHV_FGT_DISABLE_SS0 (1 << 10) #define CHV_FGT_DISABLE_SS1 (1 << 11) @@ -1448,6 +1455,10 @@ #define GEN11_KCR (19) #define GEN11_GTPM (16) #define GEN11_BCS (15) +#define GEN12_CCS3 (7) +#define GEN12_CCS2 (6) +#define GEN12_CCS1 (5) +#define GEN12_CCS0 (4) #define GEN11_RCS0 (0) #define GEN11_VECS(x) (31 - (x)) #define GEN11_VCS(x) (x) @@ -1460,6 +1471,7 @@ #define GEN11_GPM_WGBOXPERF_INTR_ENABLE _MMIO(0x19003c) #define GEN11_CRYPTO_RSVD_INTR_ENABLE _MMIO(0x190040) #define GEN11_GUNIT_CSME_INTR_ENABLE _MMIO(0x190044) +#define GEN12_CCS_RSVD_INTR_ENABLE _MMIO(0x190048) #define GEN11_INTR_IDENTITY_REG(x) _MMIO(0x190060 + ((x) * 4)) #define GEN11_INTR_DATA_VALID (1 << 31) @@ -1485,41 +1497,9 @@ #define GEN11_GPM_WGBOXPERF_INTR_MASK _MMIO(0x1900ec) #define GEN11_CRYPTO_RSVD_INTR_MASK _MMIO(0x1900f0) #define GEN11_GUNIT_CSME_INTR_MASK _MMIO(0x1900f4) +#define GEN12_CCS0_CCS1_INTR_MASK _MMIO(0x190100) +#define GEN12_CCS2_CCS3_INTR_MASK _MMIO(0x190104) #define GEN12_SFC_DONE(n) _MMIO(0x1cc000 + (n) * 0x1000) -enum { - INTEL_ADVANCED_CONTEXT = 0, - INTEL_LEGACY_32B_CONTEXT, - INTEL_ADVANCED_AD_CONTEXT, - INTEL_LEGACY_64B_CONTEXT -}; - -enum { - FAULT_AND_HANG = 0, - FAULT_AND_HALT, /* Debug only */ - FAULT_AND_STREAM, - FAULT_AND_CONTINUE /* Unsupported */ -}; - -#define CTX_GTT_ADDRESS_MASK GENMASK(31, 12) -#define GEN8_CTX_VALID (1 << 0) -#define GEN8_CTX_FORCE_PD_RESTORE (1 << 1) -#define GEN8_CTX_FORCE_RESTORE (1 << 2) -#define GEN8_CTX_L3LLC_COHERENT (1 << 5) -#define GEN8_CTX_PRIVILEGE (1 << 8) -#define GEN8_CTX_ADDRESSING_MODE_SHIFT 3 -#define GEN8_CTX_ID_SHIFT 32 -#define GEN8_CTX_ID_WIDTH 21 -#define GEN11_SW_CTX_ID_SHIFT 37 -#define GEN11_SW_CTX_ID_WIDTH 11 -#define GEN11_ENGINE_CLASS_SHIFT 61 -#define GEN11_ENGINE_CLASS_WIDTH 3 -#define GEN11_ENGINE_INSTANCE_SHIFT 48 -#define GEN11_ENGINE_INSTANCE_WIDTH 6 -#define XEHP_SW_CTX_ID_SHIFT 39 -#define XEHP_SW_CTX_ID_WIDTH 16 -#define XEHP_SW_COUNTER_SHIFT 58 -#define XEHP_SW_COUNTER_WIDTH 6 - #endif /* __INTEL_GT_REGS__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index 2f9b6694ebdd..cc53b481a1c5 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -119,14 +119,19 @@ void __i915_vm_close(struct i915_address_space *vm) list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link) { struct drm_i915_gem_object *obj = vma->obj; - /* Keep the obj (and hence the vma) alive as _we_ destroy it */ - if (!kref_get_unless_zero(&obj->base.refcount)) + if (!kref_get_unless_zero(&obj->base.refcount)) { + /* + * Unbind the dying vma to ensure the bound_list + * is completely drained. We leave the destruction to + * the object destructor. + */ + atomic_and(~I915_VMA_PIN_MASK, &vma->flags); + WARN_ON(__i915_vma_unbind(vma)); continue; + } - atomic_and(~I915_VMA_PIN_MASK, &vma->flags); - WARN_ON(__i915_vma_unbind(vma)); - __i915_vma_put(vma); - + /* Keep the obj (and hence the vma) alive as _we_ destroy it */ + i915_vma_destroy_locked(vma); i915_gem_object_put(obj); } GEM_BUG_ON(!list_empty(&vm->bound_list)); @@ -237,6 +242,19 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass) GEM_BUG_ON(!vm->total); drm_mm_init(&vm->mm, 0, vm->total); + + memset64(vm->min_alignment, I915_GTT_MIN_ALIGNMENT, + ARRAY_SIZE(vm->min_alignment)); + + if (HAS_64K_PAGES(vm->i915) && NEEDS_COMPACT_PT(vm->i915) && + subclass == VM_CLASS_PPGTT) { + vm->min_alignment[INTEL_MEMORY_LOCAL] = I915_GTT_PAGE_SIZE_2M; + vm->min_alignment[INTEL_MEMORY_STOLEN_LOCAL] = I915_GTT_PAGE_SIZE_2M; + } else if (HAS_64K_PAGES(vm->i915)) { + vm->min_alignment[INTEL_MEMORY_LOCAL] = I915_GTT_PAGE_SIZE_64K; + vm->min_alignment[INTEL_MEMORY_STOLEN_LOCAL] = I915_GTT_PAGE_SIZE_64K; + } + vm->mm.head_node.color = I915_COLOR_UNEVICTABLE; INIT_LIST_HEAD(&vm->bound_list); diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index b12ecee49de0..ba7025388a5e 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -29,6 +29,8 @@ #include "i915_selftest.h" #include "i915_vma_resource.h" #include "i915_vma_types.h" +#include "i915_params.h" +#include "intel_memory_region.h" #define I915_GFP_ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN) @@ -90,6 +92,8 @@ typedef u64 gen8_pte_t; #define GEN12_GGTT_PTE_LM BIT_ULL(1) +#define GEN12_PDE_64K BIT(6) + /* * Cacheability Control is a 4-bit value. The low three bits are stored in bits * 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE. @@ -158,6 +162,7 @@ struct i915_page_table { atomic_t used; struct i915_page_table *stash; }; + bool is_compact; }; struct i915_page_directory { @@ -195,6 +200,14 @@ void *__px_vaddr(struct drm_i915_gem_object *p); struct i915_vm_pt_stash { /* preallocated chains of page tables/directories */ struct i915_page_table *pt[2]; + /* + * Optionally override the alignment/size of the physical page that + * contains each PT. If not set defaults back to the usual + * I915_GTT_PAGE_SIZE_4K. This does not influence the other paging + * structures. MUST be a power-of-two. ONLY applicable on discrete + * platforms. + */ + int pt_sz; }; struct i915_vma_ops { @@ -223,6 +236,7 @@ struct i915_address_space { struct device *dma; u64 total; /* size addr space maps (ex. 2GB for ggtt) */ u64 reserved; /* size addr space reserved */ + u64 min_alignment[INTEL_MEMORY_STOLEN_LOCAL + 1]; unsigned int bind_async_flags; @@ -386,6 +400,25 @@ i915_vm_has_scratch_64K(struct i915_address_space *vm) return vm->scratch_order == get_order(I915_GTT_PAGE_SIZE_64K); } +static inline u64 i915_vm_min_alignment(struct i915_address_space *vm, + enum intel_memory_type type) +{ + /* avoid INTEL_MEMORY_MOCK overflow */ + if ((int)type >= ARRAY_SIZE(vm->min_alignment)) + type = INTEL_MEMORY_SYSTEM; + + return vm->min_alignment[type]; +} + +static inline u64 i915_vm_obj_min_alignment(struct i915_address_space *vm, + struct drm_i915_gem_object *obj) +{ + struct intel_memory_region *mr = READ_ONCE(obj->mm.region); + enum intel_memory_type type = mr ? mr->type : INTEL_MEMORY_SYSTEM; + + return i915_vm_min_alignment(vm, type); +} + static inline bool i915_vm_has_cache_coloring(struct i915_address_space *vm) { @@ -572,7 +605,7 @@ void free_scratch(struct i915_address_space *vm); struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz); struct drm_i915_gem_object *alloc_pt_lmem(struct i915_address_space *vm, int sz); -struct i915_page_table *alloc_pt(struct i915_address_space *vm); +struct i915_page_table *alloc_pt(struct i915_address_space *vm, int sz); struct i915_page_directory *alloc_pd(struct i915_address_space *vm); struct i915_page_directory *__alloc_pd(int npde); diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 004e1216e654..07bef7128fdb 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -623,7 +623,7 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine) GEM_BUG_ON(GRAPHICS_VER(engine->i915) >= 12 && !intel_engine_has_relative_mmio(engine)); - if (engine->class == RENDER_CLASS) { + if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE) { if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55)) return dg2_rcs_offsets; else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50)) @@ -1217,6 +1217,14 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs) cs = gen12_emit_timestamp_wa(ce, cs); cs = gen12_emit_restore_scratch(ce, cs); + /* Wa_16013000631:dg2 */ + if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_B0, STEP_C0) || + IS_DG2_G11(ce->engine->i915)) + if (ce->engine->class == COMPUTE_CLASS) + cs = gen8_emit_pipe_control(cs, + PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, + 0); + return cs; } @@ -1619,7 +1627,7 @@ void lrc_init_wa_ctx(struct intel_engine_cs *engine) unsigned int i; int err; - if (engine->class != RENDER_CLASS) + if (!(engine->flags & I915_ENGINE_HAS_RCS_REG_STATE)) return; switch (GRAPHICS_VER(engine->i915)) { diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h index 0b76f096b559..6e4f9f58fca5 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.h +++ b/drivers/gpu/drm/i915/gt/intel_lrc.h @@ -6,6 +6,9 @@ #ifndef __INTEL_LRC_H__ #define __INTEL_LRC_H__ +#include "i915_priolist_types.h" + +#include <linux/bitfield.h> #include <linux/types.h> struct drm_i915_gem_object; @@ -69,4 +72,52 @@ void lrc_check_regs(const struct intel_context *ce, void lrc_update_runtime(struct intel_context *ce); +enum { + INTEL_ADVANCED_CONTEXT = 0, + INTEL_LEGACY_32B_CONTEXT, + INTEL_ADVANCED_AD_CONTEXT, + INTEL_LEGACY_64B_CONTEXT +}; + +enum { + FAULT_AND_HANG = 0, + FAULT_AND_HALT, /* Debug only */ + FAULT_AND_STREAM, + FAULT_AND_CONTINUE /* Unsupported */ +}; + +#define CTX_GTT_ADDRESS_MASK GENMASK(31, 12) +#define GEN8_CTX_VALID (1 << 0) +#define GEN8_CTX_FORCE_PD_RESTORE (1 << 1) +#define GEN8_CTX_FORCE_RESTORE (1 << 2) +#define GEN8_CTX_L3LLC_COHERENT (1 << 5) +#define GEN8_CTX_PRIVILEGE (1 << 8) +#define GEN8_CTX_ADDRESSING_MODE_SHIFT 3 +#define GEN12_CTX_PRIORITY_MASK GENMASK(10, 9) +#define GEN12_CTX_PRIORITY_HIGH FIELD_PREP(GEN12_CTX_PRIORITY_MASK, 2) +#define GEN12_CTX_PRIORITY_NORMAL FIELD_PREP(GEN12_CTX_PRIORITY_MASK, 1) +#define GEN12_CTX_PRIORITY_LOW FIELD_PREP(GEN12_CTX_PRIORITY_MASK, 0) +#define GEN8_CTX_ID_SHIFT 32 +#define GEN8_CTX_ID_WIDTH 21 +#define GEN11_SW_CTX_ID_SHIFT 37 +#define GEN11_SW_CTX_ID_WIDTH 11 +#define GEN11_ENGINE_CLASS_SHIFT 61 +#define GEN11_ENGINE_CLASS_WIDTH 3 +#define GEN11_ENGINE_INSTANCE_SHIFT 48 +#define GEN11_ENGINE_INSTANCE_WIDTH 6 +#define XEHP_SW_CTX_ID_SHIFT 39 +#define XEHP_SW_CTX_ID_WIDTH 16 +#define XEHP_SW_COUNTER_SHIFT 58 +#define XEHP_SW_COUNTER_WIDTH 6 + +static inline u32 lrc_desc_priority(int prio) +{ + if (prio > I915_PRIORITY_NORMAL) + return GEN12_CTX_PRIORITY_HIGH; + else if (prio < I915_PRIORITY_NORMAL) + return GEN12_CTX_PRIORITY_LOW; + else + return GEN12_CTX_PRIORITY_NORMAL; +} + #endif /* __INTEL_LRC_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c index 18b44af56969..20444d6ceb3c 100644 --- a/drivers/gpu/drm/i915/gt/intel_migrate.c +++ b/drivers/gpu/drm/i915/gt/intel_migrate.c @@ -32,6 +32,38 @@ static bool engine_supports_migration(struct intel_engine_cs *engine) return true; } +static void xehpsdv_toggle_pdes(struct i915_address_space *vm, + struct i915_page_table *pt, + void *data) +{ + struct insert_pte_data *d = data; + + /* + * Insert a dummy PTE into every PT that will map to LMEM to ensure + * we have a correctly setup PDE structure for later use. + */ + vm->insert_page(vm, 0, d->offset, I915_CACHE_NONE, PTE_LM); + GEM_BUG_ON(!pt->is_compact); + d->offset += SZ_2M; +} + +static void xehpsdv_insert_pte(struct i915_address_space *vm, + struct i915_page_table *pt, + void *data) +{ + struct insert_pte_data *d = data; + + /* + * We are playing tricks here, since the actual pt, from the hw + * pov, is only 256bytes with 32 entries, or 4096bytes with 512 + * entries, but we are still guaranteed that the physical + * alignment is 64K underneath for the pt, and we are careful + * not to access the space in the void. + */ + vm->insert_page(vm, px_dma(pt), d->offset, I915_CACHE_NONE, PTE_LM); + d->offset += SZ_64K; +} + static void insert_pte(struct i915_address_space *vm, struct i915_page_table *pt, void *data) @@ -74,7 +106,32 @@ static struct i915_address_space *migrate_vm(struct intel_gt *gt) * i.e. within the same non-preemptible window so that we do not switch * to another migration context that overwrites the PTE. * - * TODO: Add support for huge LMEM PTEs + * This changes quite a bit on platforms with HAS_64K_PAGES support, + * where we instead have three windows, each CHUNK_SIZE in size. The + * first is reserved for mapping system-memory, and that just uses the + * 512 entry layout using 4K GTT pages. The other two windows just map + * lmem pages and must use the new compact 32 entry layout using 64K GTT + * pages, which ensures we can address any lmem object that the user + * throws at us. We then also use the xehpsdv_toggle_pdes as a way of + * just toggling the PDE bit(GEN12_PDE_64K) for us, to enable the + * compact layout for each of these page-tables, that fall within the + * [CHUNK_SIZE, 3 * CHUNK_SIZE) range. + * + * We lay the ppGTT out as: + * + * [0, CHUNK_SZ) -> first window/object, maps smem + * [CHUNK_SZ, 2 * CHUNK_SZ) -> second window/object, maps lmem src + * [2 * CHUNK_SZ, 3 * CHUNK_SZ) -> third window/object, maps lmem dst + * + * For the PTE window it's also quite different, since each PTE must + * point to some 64K page, one for each PT(since it's in lmem), and yet + * each is only <= 4096bytes, but since the unused space within that PTE + * range is never touched, this should be fine. + * + * So basically each PT now needs 64K of virtual memory, instead of 4K, + * which looks like: + * + * [3 * CHUNK_SZ, 3 * CHUNK_SZ + ((3 * CHUNK_SZ / SZ_2M) * SZ_64K)] -> PTE */ vm = i915_ppgtt_create(gt, I915_BO_ALLOC_PM_EARLY); @@ -86,6 +143,9 @@ static struct i915_address_space *migrate_vm(struct intel_gt *gt) goto err_vm; } + if (HAS_64K_PAGES(gt->i915)) + stash.pt_sz = I915_GTT_PAGE_SIZE_64K; + /* * Each engine instance is assigned its own chunk in the VM, so * that we can run multiple instances concurrently @@ -105,14 +165,20 @@ static struct i915_address_space *migrate_vm(struct intel_gt *gt) * We copy in 8MiB chunks. Each PDE covers 2MiB, so we need * 4x2 page directories for source/destination. */ - sz = 2 * CHUNK_SZ; + if (HAS_64K_PAGES(gt->i915)) + sz = 3 * CHUNK_SZ; + else + sz = 2 * CHUNK_SZ; d.offset = base + sz; /* * We need another page directory setup so that we can write * the 8x512 PTE in each chunk. */ - sz += (sz >> 12) * sizeof(u64); + if (HAS_64K_PAGES(gt->i915)) + sz += (sz / SZ_2M) * SZ_64K; + else + sz += (sz >> 12) * sizeof(u64); err = i915_vm_alloc_pt_stash(&vm->vm, &stash, sz); if (err) @@ -133,7 +199,18 @@ static struct i915_address_space *migrate_vm(struct intel_gt *gt) goto err_vm; /* Now allow the GPU to rewrite the PTE via its own ppGTT */ - vm->vm.foreach(&vm->vm, base, d.offset - base, insert_pte, &d); + if (HAS_64K_PAGES(gt->i915)) { + vm->vm.foreach(&vm->vm, base, d.offset - base, + xehpsdv_insert_pte, &d); + d.offset = base + CHUNK_SZ; + vm->vm.foreach(&vm->vm, + d.offset, + 2 * CHUNK_SZ, + xehpsdv_toggle_pdes, &d); + } else { + vm->vm.foreach(&vm->vm, base, d.offset - base, + insert_pte, &d); + } } return &vm->vm; @@ -269,19 +346,38 @@ static int emit_pte(struct i915_request *rq, u64 offset, int length) { + bool has_64K_pages = HAS_64K_PAGES(rq->engine->i915); const u64 encode = rq->context->vm->pte_encode(0, cache_level, is_lmem ? PTE_LM : 0); struct intel_ring *ring = rq->ring; - int total = 0; + int pkt, dword_length; + u32 total = 0; + u32 page_size; u32 *hdr, *cs; - int pkt; GEM_BUG_ON(GRAPHICS_VER(rq->engine->i915) < 8); + page_size = I915_GTT_PAGE_SIZE; + dword_length = 0x400; + /* Compute the page directory offset for the target address range */ - offset >>= 12; - offset *= sizeof(u64); - offset += 2 * CHUNK_SZ; + if (has_64K_pages) { + GEM_BUG_ON(!IS_ALIGNED(offset, SZ_2M)); + + offset /= SZ_2M; + offset *= SZ_64K; + offset += 3 * CHUNK_SZ; + + if (is_lmem) { + page_size = I915_GTT_PAGE_SIZE_64K; + dword_length = 0x40; + } + } else { + offset >>= 12; + offset *= sizeof(u64); + offset += 2 * CHUNK_SZ; + } + offset += (u64)rq->engine->instance << 32; cs = intel_ring_begin(rq, 6); @@ -289,7 +385,7 @@ static int emit_pte(struct i915_request *rq, return PTR_ERR(cs); /* Pack as many PTE updates as possible into a single MI command */ - pkt = min_t(int, 0x400, ring->space / sizeof(u32) + 5); + pkt = min_t(int, dword_length, ring->space / sizeof(u32) + 5); pkt = min_t(int, pkt, (ring->size - ring->emit) / sizeof(u32) + 5); hdr = cs; @@ -299,6 +395,8 @@ static int emit_pte(struct i915_request *rq, do { if (cs - hdr >= pkt) { + int dword_rem; + *hdr += cs - hdr - 2; *cs++ = MI_NOOP; @@ -310,7 +408,18 @@ static int emit_pte(struct i915_request *rq, if (IS_ERR(cs)) return PTR_ERR(cs); - pkt = min_t(int, 0x400, ring->space / sizeof(u32) + 5); + dword_rem = dword_length; + if (has_64K_pages) { + if (IS_ALIGNED(total, SZ_2M)) { + offset = round_up(offset, SZ_64K); + } else { + dword_rem = SZ_2M - (total & (SZ_2M - 1)); + dword_rem /= page_size; + dword_rem *= 2; + } + } + + pkt = min_t(int, dword_rem, ring->space / sizeof(u32) + 5); pkt = min_t(int, pkt, (ring->size - ring->emit) / sizeof(u32) + 5); hdr = cs; @@ -319,13 +428,15 @@ static int emit_pte(struct i915_request *rq, *cs++ = upper_32_bits(offset); } + GEM_BUG_ON(!IS_ALIGNED(it->dma, page_size)); + *cs++ = lower_32_bits(encode | it->dma); *cs++ = upper_32_bits(encode | it->dma); offset += 8; - total += I915_GTT_PAGE_SIZE; + total += page_size; - it->dma += I915_GTT_PAGE_SIZE; + it->dma += page_size; if (it->dma >= it->max) { it->sg = __sg_next(it->sg); if (!it->sg || sg_dma_len(it->sg) == 0) @@ -356,7 +467,8 @@ static bool wa_1209644611_applies(int ver, u32 size) return height % 4 == 3 && height <= 8; } -static int emit_copy(struct i915_request *rq, int size) +static int emit_copy(struct i915_request *rq, + u32 dst_offset, u32 src_offset, int size) { const int ver = GRAPHICS_VER(rq->engine->i915); u32 instance = rq->engine->instance; @@ -371,31 +483,31 @@ static int emit_copy(struct i915_request *rq, int size) *cs++ = BLT_DEPTH_32 | PAGE_SIZE; *cs++ = 0; *cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4; - *cs++ = CHUNK_SZ; /* dst offset */ + *cs++ = dst_offset; *cs++ = instance; *cs++ = 0; *cs++ = PAGE_SIZE; - *cs++ = 0; /* src offset */ + *cs++ = src_offset; *cs++ = instance; } else if (ver >= 8) { *cs++ = XY_SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (10 - 2); *cs++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | PAGE_SIZE; *cs++ = 0; *cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4; - *cs++ = CHUNK_SZ; /* dst offset */ + *cs++ = dst_offset; *cs++ = instance; *cs++ = 0; *cs++ = PAGE_SIZE; - *cs++ = 0; /* src offset */ + *cs++ = src_offset; *cs++ = instance; } else { GEM_BUG_ON(instance); *cs++ = SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (6 - 2); *cs++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | PAGE_SIZE; *cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE; - *cs++ = CHUNK_SZ; /* dst offset */ + *cs++ = dst_offset; *cs++ = PAGE_SIZE; - *cs++ = 0; /* src offset */ + *cs++ = src_offset; } intel_ring_advance(rq, cs); @@ -423,6 +535,7 @@ intel_context_migrate_copy(struct intel_context *ce, GEM_BUG_ON(ce->ring->size < SZ_64K); do { + u32 src_offset, dst_offset; int len; rq = i915_request_create(ce); @@ -450,15 +563,28 @@ intel_context_migrate_copy(struct intel_context *ce, if (err) goto out_rq; - len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem, 0, - CHUNK_SZ); + src_offset = 0; + dst_offset = CHUNK_SZ; + if (HAS_64K_PAGES(ce->engine->i915)) { + GEM_BUG_ON(!src_is_lmem && !dst_is_lmem); + + src_offset = 0; + dst_offset = 0; + if (src_is_lmem) + src_offset = CHUNK_SZ; + if (dst_is_lmem) + dst_offset = 2 * CHUNK_SZ; + } + + len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem, + src_offset, CHUNK_SZ); if (len <= 0) { err = len; goto out_rq; } err = emit_pte(rq, &it_dst, dst_cache_level, dst_is_lmem, - CHUNK_SZ, len); + dst_offset, len); if (err < 0) goto out_rq; if (err < len) { @@ -470,7 +596,7 @@ intel_context_migrate_copy(struct intel_context *ce, if (err) goto out_rq; - err = emit_copy(rq, len); + err = emit_copy(rq, dst_offset, src_offset, len); /* Arbitration is re-enabled between requests. */ out_rq: @@ -488,14 +614,15 @@ out_ce: return err; } -static int emit_clear(struct i915_request *rq, int size, u32 value) +static int emit_clear(struct i915_request *rq, u64 offset, int size, u32 value) { const int ver = GRAPHICS_VER(rq->engine->i915); - u32 instance = rq->engine->instance; u32 *cs; GEM_BUG_ON(size >> PAGE_SHIFT > S16_MAX); + offset += (u64)rq->engine->instance << 32; + cs = intel_ring_begin(rq, ver >= 8 ? 8 : 6); if (IS_ERR(cs)) return PTR_ERR(cs); @@ -505,17 +632,17 @@ static int emit_clear(struct i915_request *rq, int size, u32 value) *cs++ = BLT_DEPTH_32 | BLT_ROP_COLOR_COPY | PAGE_SIZE; *cs++ = 0; *cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4; - *cs++ = 0; /* offset */ - *cs++ = instance; + *cs++ = lower_32_bits(offset); + *cs++ = upper_32_bits(offset); *cs++ = value; *cs++ = MI_NOOP; } else { - GEM_BUG_ON(instance); + GEM_BUG_ON(upper_32_bits(offset)); *cs++ = XY_COLOR_BLT_CMD | BLT_WRITE_RGBA | (6 - 2); *cs++ = BLT_DEPTH_32 | BLT_ROP_COLOR_COPY | PAGE_SIZE; *cs++ = 0; *cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4; - *cs++ = 0; + *cs++ = lower_32_bits(offset); *cs++ = value; } @@ -542,6 +669,7 @@ intel_context_migrate_clear(struct intel_context *ce, GEM_BUG_ON(ce->ring->size < SZ_64K); do { + u32 offset; int len; rq = i915_request_create(ce); @@ -569,7 +697,11 @@ intel_context_migrate_clear(struct intel_context *ce, if (err) goto out_rq; - len = emit_pte(rq, &it, cache_level, is_lmem, 0, CHUNK_SZ); + offset = 0; + if (HAS_64K_PAGES(ce->engine->i915) && is_lmem) + offset = CHUNK_SZ; + + len = emit_pte(rq, &it, cache_level, is_lmem, offset, CHUNK_SZ); if (len <= 0) { err = len; goto out_rq; @@ -579,7 +711,7 @@ intel_context_migrate_clear(struct intel_context *ce, if (err) goto out_rq; - err = emit_clear(rq, len, value); + err = emit_clear(rq, offset, len, value); /* Arbitration is re-enabled between requests. */ out_rq: diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c index 48e6e2f87700..d91e2beb7517 100644 --- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c @@ -12,7 +12,7 @@ #include "gen6_ppgtt.h" #include "gen8_ppgtt.h" -struct i915_page_table *alloc_pt(struct i915_address_space *vm) +struct i915_page_table *alloc_pt(struct i915_address_space *vm, int sz) { struct i915_page_table *pt; @@ -20,12 +20,13 @@ struct i915_page_table *alloc_pt(struct i915_address_space *vm) if (unlikely(!pt)) return ERR_PTR(-ENOMEM); - pt->base = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K); + pt->base = vm->alloc_pt_dma(vm, sz); if (IS_ERR(pt->base)) { kfree(pt); return ERR_PTR(-ENOMEM); } + pt->is_compact = false; atomic_set(&pt->used, 0); return pt; } @@ -220,17 +221,25 @@ int i915_vm_alloc_pt_stash(struct i915_address_space *vm, u64 size) { unsigned long count; - int shift, n; + int shift, n, pt_sz; shift = vm->pd_shift; if (!shift) return 0; + pt_sz = stash->pt_sz; + if (!pt_sz) + pt_sz = I915_GTT_PAGE_SIZE_4K; + else + GEM_BUG_ON(!IS_DGFX(vm->i915)); + + GEM_BUG_ON(!is_power_of_2(pt_sz)); + count = pd_count(size, shift); while (count--) { struct i915_page_table *pt; - pt = alloc_pt(vm); + pt = alloc_pt(vm, pt_sz); if (IS_ERR(pt)) { i915_vm_free_pt_stash(vm, stash); return PTR_ERR(pt); diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c index a04e0cf4a94b..6cecfdae07ad 100644 --- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c +++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c @@ -14,60 +14,6 @@ #include "gt/intel_gt.h" #include "gt/intel_gt_regs.h" -static int init_fake_lmem_bar(struct intel_memory_region *mem) -{ - struct drm_i915_private *i915 = mem->i915; - struct i915_ggtt *ggtt = to_gt(i915)->ggtt; - unsigned long n; - int ret; - - /* We want to 1:1 map the mappable aperture to our reserved region */ - - mem->fake_mappable.start = 0; - mem->fake_mappable.size = resource_size(&mem->region); - mem->fake_mappable.color = I915_COLOR_UNEVICTABLE; - - ret = drm_mm_reserve_node(&ggtt->vm.mm, &mem->fake_mappable); - if (ret) - return ret; - - mem->remap_addr = dma_map_resource(i915->drm.dev, - mem->region.start, - mem->fake_mappable.size, - DMA_BIDIRECTIONAL, - DMA_ATTR_FORCE_CONTIGUOUS); - if (dma_mapping_error(i915->drm.dev, mem->remap_addr)) { - drm_mm_remove_node(&mem->fake_mappable); - return -EINVAL; - } - - for (n = 0; n < mem->fake_mappable.size >> PAGE_SHIFT; ++n) { - ggtt->vm.insert_page(&ggtt->vm, - mem->remap_addr + (n << PAGE_SHIFT), - n << PAGE_SHIFT, - I915_CACHE_NONE, 0); - } - - mem->region = (struct resource)DEFINE_RES_MEM(mem->remap_addr, - mem->fake_mappable.size); - - return 0; -} - -static void release_fake_lmem_bar(struct intel_memory_region *mem) -{ - if (!drm_mm_node_allocated(&mem->fake_mappable)) - return; - - drm_mm_remove_node(&mem->fake_mappable); - - dma_unmap_resource(mem->i915->drm.dev, - mem->remap_addr, - mem->fake_mappable.size, - DMA_BIDIRECTIONAL, - DMA_ATTR_FORCE_CONTIGUOUS); -} - static int region_lmem_release(struct intel_memory_region *mem) { @@ -75,7 +21,6 @@ region_lmem_release(struct intel_memory_region *mem) ret = intel_region_ttm_fini(mem); io_mapping_fini(&mem->iomap); - release_fake_lmem_bar(mem); return ret; } @@ -85,17 +30,10 @@ region_lmem_init(struct intel_memory_region *mem) { int ret; - if (mem->i915->params.fake_lmem_start) { - ret = init_fake_lmem_bar(mem); - GEM_BUG_ON(ret); - } - if (!io_mapping_init_wc(&mem->iomap, mem->io_start, - resource_size(&mem->region))) { - ret = -EIO; - goto out_no_io; - } + mem->io_size)) + return -EIO; ret = intel_region_ttm_init(mem); if (ret) @@ -105,8 +43,6 @@ region_lmem_init(struct intel_memory_region *mem) out_no_buddy: io_mapping_fini(&mem->iomap); -out_no_io: - release_fake_lmem_bar(mem); return ret; } @@ -117,50 +53,6 @@ static const struct intel_memory_region_ops intel_region_lmem_ops = { .init_object = __i915_gem_ttm_object_init, }; -struct intel_memory_region * -intel_gt_setup_fake_lmem(struct intel_gt *gt) -{ - struct drm_i915_private *i915 = gt->i915; - struct pci_dev *pdev = to_pci_dev(i915->drm.dev); - struct intel_memory_region *mem; - resource_size_t mappable_end; - resource_size_t io_start; - resource_size_t start; - - if (!HAS_LMEM(i915)) - return ERR_PTR(-ENODEV); - - if (!i915->params.fake_lmem_start) - return ERR_PTR(-ENODEV); - - GEM_BUG_ON(i915_ggtt_has_aperture(to_gt(i915)->ggtt)); - - /* Your mappable aperture belongs to me now! */ - mappable_end = pci_resource_len(pdev, 2); - io_start = pci_resource_start(pdev, 2); - start = i915->params.fake_lmem_start; - - mem = intel_memory_region_create(i915, - start, - mappable_end, - PAGE_SIZE, - io_start, - INTEL_MEMORY_LOCAL, - 0, - &intel_region_lmem_ops); - if (!IS_ERR(mem)) { - drm_info(&i915->drm, "Intel graphics fake LMEM: %pR\n", - &mem->region); - drm_info(&i915->drm, - "Intel graphics fake LMEM IO start: %llx\n", - (u64)mem->io_start); - drm_info(&i915->drm, "Intel graphics fake LMEM size: %llx\n", - (u64)resource_size(&mem->region)); - } - - return mem; -} - static bool get_legacy_lowmem_region(struct intel_uncore *uncore, u64 *start, u32 *size) { @@ -207,8 +99,29 @@ static struct intel_memory_region *setup_lmem(struct intel_gt *gt) if (!IS_DGFX(i915)) return ERR_PTR(-ENODEV); - /* Stolen starts from GSMBASE on DG1 */ - lmem_size = intel_uncore_read64(uncore, GEN12_GSMBASE); + if (HAS_FLAT_CCS(i915)) { + u64 tile_stolen, flat_ccs_base; + + lmem_size = pci_resource_len(pdev, 2); + flat_ccs_base = intel_gt_read_register(gt, XEHPSDV_FLAT_CCS_BASE_ADDR); + flat_ccs_base = (flat_ccs_base >> XEHPSDV_CCS_BASE_SHIFT) * SZ_64K; + + if (GEM_WARN_ON(lmem_size < flat_ccs_base)) + return ERR_PTR(-ENODEV); + + tile_stolen = lmem_size - flat_ccs_base; + + /* If the FLAT_CCS_BASE_ADDR register is not populated, flag an error */ + if (tile_stolen == lmem_size) + drm_err(&i915->drm, + "CCS_BASE_ADDR register did not have expected value\n"); + + lmem_size -= tile_stolen; + } else { + /* Stolen starts from GSMBASE without CCS */ + lmem_size = intel_uncore_read64(&i915->uncore, GEN12_GSMBASE); + } + io_start = pci_resource_start(pdev, 2); if (GEM_WARN_ON(lmem_size > pci_resource_len(pdev, 2))) @@ -221,6 +134,7 @@ static struct intel_memory_region *setup_lmem(struct intel_gt *gt) lmem_size, min_page_size, io_start, + lmem_size, INTEL_MEMORY_LOCAL, 0, &intel_region_lmem_ops); @@ -234,6 +148,8 @@ static struct intel_memory_region *setup_lmem(struct intel_gt *gt) drm_dbg(&i915->drm, "Local memory: %pR\n", &mem->region); drm_dbg(&i915->drm, "Local memory IO start: %pa\n", &mem->io_start); + drm_info(&i915->drm, "Local memory IO size: %pa\n", + &mem->io_size); drm_info(&i915->drm, "Local memory available: %pa\n", &lmem_size); diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.h b/drivers/gpu/drm/i915/gt/intel_region_lmem.h index 062d0542ae34..1438576b527a 100644 --- a/drivers/gpu/drm/i915/gt/intel_region_lmem.h +++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.h @@ -10,7 +10,4 @@ struct intel_gt; struct intel_memory_region *intel_gt_setup_lmem(struct intel_gt *gt); -struct intel_memory_region * -intel_gt_setup_fake_lmem(struct intel_gt *gt); - #endif /* !__INTEL_REGION_LMEM_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index f691b7614437..a9c13b1a3018 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -1491,7 +1491,7 @@ void intel_rps_enable(struct intel_rps *rps) if (has_busy_stats(rps)) intel_rps_set_timer(rps); - else if (GRAPHICS_VER(i915) >= 6) + else if (GRAPHICS_VER(i915) >= 6 && GRAPHICS_VER(i915) <= 11) intel_rps_set_interrupts(rps); else /* Ironlake currently uses intel_ips.ko */ {} diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c index 4ae8356dcc2a..614915ffbd37 100644 --- a/drivers/gpu/drm/i915/gt/intel_sseu.c +++ b/drivers/gpu/drm/i915/gt/intel_sseu.c @@ -34,7 +34,9 @@ intel_sseu_subslice_total(const struct sseu_dev_info *sseu) return total; } -u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice) +static u32 +_intel_sseu_get_subslices(const struct sseu_dev_info *sseu, + const u8 *subslice_mask, u8 slice) { int i, offset = slice * sseu->ss_stride; u32 mask = 0; @@ -42,12 +44,21 @@ u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice) GEM_BUG_ON(slice >= sseu->max_slices); for (i = 0; i < sseu->ss_stride; i++) - mask |= (u32)sseu->subslice_mask[offset + i] << - i * BITS_PER_BYTE; + mask |= (u32)subslice_mask[offset + i] << i * BITS_PER_BYTE; return mask; } +u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice) +{ + return _intel_sseu_get_subslices(sseu, sseu->subslice_mask, slice); +} + +u32 intel_sseu_get_compute_subslices(const struct sseu_dev_info *sseu) +{ + return _intel_sseu_get_subslices(sseu, sseu->compute_subslice_mask, 0); +} + void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice, u8 *subslice_mask, u32 ss_mask) { diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h index 60882a74741e..8a79cd8eaab4 100644 --- a/drivers/gpu/drm/i915/gt/intel_sseu.h +++ b/drivers/gpu/drm/i915/gt/intel_sseu.h @@ -103,7 +103,9 @@ intel_sseu_subslice_total(const struct sseu_dev_info *sseu); unsigned int intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice); -u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice); +u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice); + +u32 intel_sseu_get_compute_subslices(const struct sseu_dev_info *sseu); void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice, u8 *subslice_mask, u32 ss_mask); diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 26038066e90b..c014b40d2e9f 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -684,11 +684,10 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine, wa_masked_en(wal, SLICE_COMMON_ECO_CHICKEN1, MSC_MSAA_REODER_BUF_BYPASS_DISABLE); - /* Wa_22012532006:dg2 */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) - wa_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, - DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA); + /* Wa_14014947963:dg2 */ + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_FOREVER) || + IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915)) + wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000); } static void fakewa_disable_nestedbb_mode(struct intel_engine_cs *engine, @@ -1344,12 +1343,6 @@ xehpsdv_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) /* Wa_1409757795:xehpsdv */ wa_write_or(wal, SCCGCTL94DC, CG3DDISURB); - /* Wa_18011725039:xehpsdv */ - if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A1, STEP_B0)) { - wa_masked_dis(wal, MLTICTXCTL, TDONRENDER); - wa_write_or(wal, L3SQCREG1_CCS0, FLUSHALLNONCOH); - } - /* Wa_16011155590:xehpsdv */ if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, @@ -1386,19 +1379,12 @@ xehpsdv_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) GAMTLBVEBOX0_CLKGATE_DIS); } - /* Wa_14012362059:xehpsdv */ - wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB); - /* Wa_16012725990:xehpsdv */ if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A1, STEP_FOREVER)) wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, VFUNIT_CLKGATE_DIS); /* Wa_14011060649:xehpsdv */ wa_14011060649(gt, wal); - - /* Wa_14014368820:xehpsdv */ - wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS | - GLOBAL_INVALIDATION_MODE); } static void @@ -1440,10 +1426,6 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) } if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) { - /* Wa_14010680813:dg2_g10 */ - wa_write_or(wal, GEN12_GAMSTLB_CTRL, CONTROL_BLOCK_CLKGATE_DIS | - EGRESS_BLOCK_CLKGATE_DIS | TAG_BLOCK_CLKGATE_DIS); - /* Wa_14010948348:dg2_g10 */ wa_write_or(wal, UNSLCGCTL9430, MSQDUNIT_CLKGATE_DIS); @@ -1490,16 +1472,6 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) wa_write_or(wal, SSMCGCTL9530, RTFUNIT_CLKGATE_DIS); } - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0) || - IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0)) { - /* Wa_14012362059:dg2 */ - wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB); - } - - /* Wa_1509235366:dg2 */ - wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS | - GLOBAL_INVALIDATION_MODE); - /* Wa_14014830051:dg2 */ wa_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN); @@ -1508,14 +1480,7 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) * recommended tuning settings documented in the bspec's * performance guide section. */ - wa_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); wa_write_or(wal, GEN12_SQCM, EN_32B_ACCESS); - - /* Wa_18018781329:dg2 */ - wa_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); - wa_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB); - wa_write_or(wal, VDBX_MOD_CTRL, FORCE_MISS_FTLB); - wa_write_or(wal, VEBX_MOD_CTRL, FORCE_MISS_FTLB); } static void @@ -1943,6 +1908,11 @@ static void dg2_whitelist_build(struct intel_engine_cs *engine) RING_FORCE_TO_NONPRIV_RANGE_4); break; + case COMPUTE_CLASS: + /* Wa_16011157294:dg2_g10 */ + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) + whitelist_reg(w, GEN9_CTX_PREEMPT_REG); + break; default: break; } @@ -2049,6 +2019,23 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_DG2(i915)) { /* Wa_14015227452:dg2 */ wa_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE); + + /* Wa_1509235366:dg2 */ + wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS | + GLOBAL_INVALIDATION_MODE); + + /* + * The following are not actually "workarounds" but rather + * recommended tuning settings documented in the bspec's + * performance guide section. + */ + wa_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); + + /* Wa_18018781329:dg2 */ + wa_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); + wa_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB); + wa_write_or(wal, VDBX_MOD_CTRL, FORCE_MISS_FTLB); + wa_write_or(wal, VEBX_MOD_CTRL, FORCE_MISS_FTLB); } if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) { @@ -2149,6 +2136,24 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) wa_write_or(wal, RT_CTRL, DIS_NULL_QUERY); + /* Wa_22012532006:dg2 */ + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_C0) || + IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) + wa_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, + DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA); + + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) { + /* Wa_14010680813:dg2_g10 */ + wa_write_or(wal, GEN12_GAMSTLB_CTRL, CONTROL_BLOCK_CLKGATE_DIS | + EGRESS_BLOCK_CLKGATE_DIS | TAG_BLOCK_CLKGATE_DIS); + } + + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0) || + IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) { + /* Wa_14012362059:dg2 */ + wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB); + } + if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) || IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) { /* @@ -2568,6 +2573,53 @@ xcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) } } +/* + * The workarounds in this function apply to shared registers in + * the general render reset domain that aren't tied to a + * specific engine. Since all render+compute engines get reset + * together, and the contents of these registers are lost during + * the shared render domain reset, we'll define such workarounds + * here and then add them to just a single RCS or CCS engine's + * workaround list (whichever engine has the XXXX flag). + */ +static void +general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) +{ + struct drm_i915_private *i915 = engine->i915; + + if (IS_XEHPSDV(i915)) { + /* Wa_1409954639 */ + wa_masked_en(wal, + GEN8_ROW_CHICKEN, + SYSTOLIC_DOP_CLOCK_GATING_DIS); + + /* Wa_1607196519 */ + wa_masked_en(wal, + GEN9_ROW_CHICKEN4, + GEN12_DISABLE_GRF_CLEAR); + + /* Wa_14010670810:xehpsdv */ + wa_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); + + /* Wa_14010449647:xehpsdv */ + wa_masked_en(wal, GEN7_HALF_SLICE_CHICKEN1, + GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE); + + /* Wa_18011725039:xehpsdv */ + if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A1, STEP_B0)) { + wa_masked_dis(wal, MLTICTXCTL, TDONRENDER); + wa_write_or(wal, L3SQCREG1_CCS0, FLUSHALLNONCOH); + } + + /* Wa_14012362059:xehpsdv */ + wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB); + + /* Wa_14014368820:xehpsdv */ + wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS | + GLOBAL_INVALIDATION_MODE); + } +} + static void engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal) { @@ -2576,6 +2628,14 @@ engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal engine_fake_wa_init(engine, wal); + /* + * These are common workarounds that just need to applied + * to a single RCS/CCS engine's workaround list since + * they're reset as part of the general render domain reset. + */ + if (engine->class == RENDER_CLASS) + general_render_compute_wa_init(engine, wal); + if (engine->class == RENDER_CLASS) rcs_engine_wa_init(engine, wal); else diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index 0683b27a3890..402f085f3a02 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -3,6 +3,7 @@ * Copyright © 2020 Intel Corporation */ +#include <linux/iosys-map.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/shmem_fs.h> @@ -123,6 +124,37 @@ static int __shmem_rw(struct file *file, loff_t off, return 0; } +int shmem_read_to_iosys_map(struct file *file, loff_t off, + struct iosys_map *map, size_t map_off, size_t len) +{ + unsigned long pfn; + + for (pfn = off >> PAGE_SHIFT; len; pfn++) { + unsigned int this = + min_t(size_t, PAGE_SIZE - offset_in_page(off), len); + struct page *page; + void *vaddr; + + page = shmem_read_mapping_page_gfp(file->f_mapping, pfn, + GFP_KERNEL); + if (IS_ERR(page)) + return PTR_ERR(page); + + vaddr = kmap(page); + iosys_map_memcpy_to(map, map_off, vaddr + offset_in_page(off), + this); + mark_page_accessed(page); + kunmap(page); + put_page(page); + + len -= this; + map_off += this; + off = 0; + } + + return 0; +} + int shmem_read(struct file *file, loff_t off, void *dst, size_t len) { return __shmem_rw(file, off, dst, len, false); diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.h b/drivers/gpu/drm/i915/gt/shmem_utils.h index c1669170c351..b2b04d88c6e5 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.h +++ b/drivers/gpu/drm/i915/gt/shmem_utils.h @@ -8,6 +8,7 @@ #include <linux/types.h> +struct iosys_map; struct drm_i915_gem_object; struct file; @@ -17,6 +18,8 @@ struct file *shmem_create_from_object(struct drm_i915_gem_object *obj); void *shmem_pin_map(struct file *file); void shmem_unpin_map(struct file *file, void *ptr); +int shmem_read_to_iosys_map(struct file *file, loff_t off, + struct iosys_map *map, size_t map_off, size_t len); int shmem_read(struct file *file, loff_t off, void *dst, size_t len); int shmem_write(struct file *file, loff_t off, void *src, size_t len); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 9d779de16613..bf7079480d47 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -6,8 +6,9 @@ #ifndef _INTEL_GUC_H_ #define _INTEL_GUC_H_ -#include <linux/xarray.h> #include <linux/delay.h> +#include <linux/iosys-map.h> +#include <linux/xarray.h> #include "intel_uncore.h" #include "intel_guc_fw.h" @@ -146,8 +147,8 @@ struct intel_guc { /** @ads_vma: object allocated to hold the GuC ADS */ struct i915_vma *ads_vma; - /** @ads_blob: contents of the GuC ADS */ - struct __guc_ads_blob *ads_blob; + /** @ads_map: contents of the GuC ADS */ + struct iosys_map ads_map; /** @ads_regset_size: size of the save/restore regsets in the ADS */ u32 ads_regset_size; /** diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c index 7e41175618f5..92cb88248391 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c @@ -57,9 +57,22 @@ struct __guc_ads_blob { struct guc_gt_system_info system_info; struct guc_engine_usage engine_usage; /* From here on, location is dynamic! Refer to above diagram. */ - struct guc_mmio_reg regset[0]; + struct guc_mmio_reg regset[]; } __packed; +#define ads_blob_read(guc_, field_) \ + iosys_map_rd_field(&(guc_)->ads_map, 0, struct __guc_ads_blob, field_) + +#define ads_blob_write(guc_, field_, val_) \ + iosys_map_wr_field(&(guc_)->ads_map, 0, struct __guc_ads_blob, \ + field_, val_) + +#define info_map_write(map_, field_, val_) \ + iosys_map_wr_field(map_, 0, struct guc_gt_system_info, field_, val_) + +#define info_map_read(map_, field_) \ + iosys_map_rd_field(map_, 0, struct guc_gt_system_info, field_) + static u32 guc_ads_regset_size(struct intel_guc *guc) { GEM_BUG_ON(!guc->ads_regset_size); @@ -123,33 +136,37 @@ static u32 guc_ads_blob_size(struct intel_guc *guc) guc_ads_private_data_size(guc); } -static void guc_policies_init(struct intel_guc *guc, struct guc_policies *policies) +static void guc_policies_init(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); struct drm_i915_private *i915 = gt->i915; + u32 global_flags = 0; - policies->dpc_promote_time = GLOBAL_POLICY_DEFAULT_DPC_PROMOTE_TIME_US; - policies->max_num_work_items = GLOBAL_POLICY_MAX_NUM_WI; + ads_blob_write(guc, policies.dpc_promote_time, + GLOBAL_POLICY_DEFAULT_DPC_PROMOTE_TIME_US); + ads_blob_write(guc, policies.max_num_work_items, + GLOBAL_POLICY_MAX_NUM_WI); - policies->global_flags = 0; if (i915->params.reset < 2) - policies->global_flags |= GLOBAL_POLICY_DISABLE_ENGINE_RESET; + global_flags |= GLOBAL_POLICY_DISABLE_ENGINE_RESET; - policies->is_valid = 1; + ads_blob_write(guc, policies.global_flags, global_flags); + ads_blob_write(guc, policies.is_valid, 1); } void intel_guc_ads_print_policy_info(struct intel_guc *guc, struct drm_printer *dp) { - struct __guc_ads_blob *blob = guc->ads_blob; - - if (unlikely(!blob)) + if (unlikely(iosys_map_is_null(&guc->ads_map))) return; drm_printf(dp, "Global scheduling policies:\n"); - drm_printf(dp, " DPC promote time = %u\n", blob->policies.dpc_promote_time); - drm_printf(dp, " Max num work items = %u\n", blob->policies.max_num_work_items); - drm_printf(dp, " Flags = %u\n", blob->policies.global_flags); + drm_printf(dp, " DPC promote time = %u\n", + ads_blob_read(guc, policies.dpc_promote_time)); + drm_printf(dp, " Max num work items = %u\n", + ads_blob_read(guc, policies.max_num_work_items)); + drm_printf(dp, " Flags = %u\n", + ads_blob_read(guc, policies.global_flags)); } static int guc_action_policies_update(struct intel_guc *guc, u32 policy_offset) @@ -164,29 +181,30 @@ static int guc_action_policies_update(struct intel_guc *guc, u32 policy_offset) int intel_guc_global_policies_update(struct intel_guc *guc) { - struct __guc_ads_blob *blob = guc->ads_blob; struct intel_gt *gt = guc_to_gt(guc); + u32 scheduler_policies; intel_wakeref_t wakeref; int ret; - if (!blob) + if (iosys_map_is_null(&guc->ads_map)) return -EOPNOTSUPP; - GEM_BUG_ON(!blob->ads.scheduler_policies); + scheduler_policies = ads_blob_read(guc, ads.scheduler_policies); + GEM_BUG_ON(!scheduler_policies); - guc_policies_init(guc, &blob->policies); + guc_policies_init(guc); if (!intel_guc_is_ready(guc)) return 0; with_intel_runtime_pm(>->i915->runtime_pm, wakeref) - ret = guc_action_policies_update(guc, blob->ads.scheduler_policies); + ret = guc_action_policies_update(guc, scheduler_policies); return ret; } static void guc_mapping_table_init(struct intel_gt *gt, - struct guc_gt_system_info *system_info) + struct iosys_map *info_map) { unsigned int i, j; struct intel_engine_cs *engine; @@ -195,14 +213,14 @@ static void guc_mapping_table_init(struct intel_gt *gt, /* Table must be set to invalid values for entries not used */ for (i = 0; i < GUC_MAX_ENGINE_CLASSES; ++i) for (j = 0; j < GUC_MAX_INSTANCES_PER_CLASS; ++j) - system_info->mapping_table[i][j] = - GUC_MAX_INSTANCES_PER_CLASS; + info_map_write(info_map, mapping_table[i][j], + GUC_MAX_INSTANCES_PER_CLASS); for_each_engine(engine, gt, id) { u8 guc_class = engine_class_to_guc_class(engine->class); - system_info->mapping_table[guc_class][ilog2(engine->logical_mask)] = - engine->instance; + info_map_write(info_map, mapping_table[guc_class][ilog2(engine->logical_mask)], + engine->instance); } } @@ -317,6 +335,10 @@ static int guc_mmio_regset_init(struct temp_regset *regset, ret |= GUC_MMIO_REG_ADD(regset, RING_HWS_PGA(base), false); ret |= GUC_MMIO_REG_ADD(regset, RING_IMR(base), false); + if (engine->class == RENDER_CLASS && + CCS_MASK(engine->gt)) + ret |= GUC_MMIO_REG_ADD(regset, GEN12_RCU_MODE, true); + for (i = 0, wa = wal->list; i < wal->count; i++, wa++) ret |= GUC_MMIO_REG_ADD(regset, wa->reg, wa->masked_reg); @@ -365,64 +387,69 @@ fail_regset_init: return ret; } -static void guc_mmio_reg_state_init(struct intel_guc *guc, - struct __guc_ads_blob *blob) +static void guc_mmio_reg_state_init(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); struct intel_engine_cs *engine; - struct guc_mmio_reg *ads_registers; enum intel_engine_id id; u32 addr_ggtt, offset; offset = guc_ads_regset_offset(guc); addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset; - ads_registers = (struct guc_mmio_reg *)(((u8 *)blob) + offset); - memcpy(ads_registers, guc->ads_regset, guc->ads_regset_size); + iosys_map_memcpy_to(&guc->ads_map, offset, guc->ads_regset, + guc->ads_regset_size); for_each_engine(engine, gt, id) { u32 count = guc->ads_regset_count[id]; - struct guc_mmio_reg_set *ads_reg_set; u8 guc_class; /* Class index is checked in class converter */ GEM_BUG_ON(engine->instance >= GUC_MAX_INSTANCES_PER_CLASS); guc_class = engine_class_to_guc_class(engine->class); - ads_reg_set = &blob->ads.reg_state_list[guc_class][engine->instance]; if (!count) { - ads_reg_set->address = 0; - ads_reg_set->count = 0; + ads_blob_write(guc, + ads.reg_state_list[guc_class][engine->instance].address, + 0); + ads_blob_write(guc, + ads.reg_state_list[guc_class][engine->instance].count, + 0); continue; } - ads_reg_set->address = addr_ggtt; - ads_reg_set->count = count; + ads_blob_write(guc, + ads.reg_state_list[guc_class][engine->instance].address, + addr_ggtt); + ads_blob_write(guc, + ads.reg_state_list[guc_class][engine->instance].count, + count); addr_ggtt += count * sizeof(struct guc_mmio_reg); } } static void fill_engine_enable_masks(struct intel_gt *gt, - struct guc_gt_system_info *info) + struct iosys_map *info_map) { - info->engine_enabled_masks[GUC_RENDER_CLASS] = 1; - info->engine_enabled_masks[GUC_BLITTER_CLASS] = 1; - info->engine_enabled_masks[GUC_VIDEO_CLASS] = VDBOX_MASK(gt); - info->engine_enabled_masks[GUC_VIDEOENHANCE_CLASS] = VEBOX_MASK(gt); + info_map_write(info_map, engine_enabled_masks[GUC_RENDER_CLASS], 1); + info_map_write(info_map, engine_enabled_masks[GUC_COMPUTE_CLASS], CCS_MASK(gt)); + info_map_write(info_map, engine_enabled_masks[GUC_BLITTER_CLASS], 1); + info_map_write(info_map, engine_enabled_masks[GUC_VIDEO_CLASS], VDBOX_MASK(gt)); + info_map_write(info_map, engine_enabled_masks[GUC_VIDEOENHANCE_CLASS], VEBOX_MASK(gt)); } #define LR_HW_CONTEXT_SIZE (80 * sizeof(u32)) #define LRC_SKIP_SIZE (LRC_PPHWSP_SZ * PAGE_SIZE + LR_HW_CONTEXT_SIZE) -static int guc_prep_golden_context(struct intel_guc *guc, - struct __guc_ads_blob *blob) +static int guc_prep_golden_context(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); u32 addr_ggtt, offset; u32 total_size = 0, alloc_size, real_size; u8 engine_class, guc_class; - struct guc_gt_system_info *info, local_info; + struct guc_gt_system_info local_info; + struct iosys_map info_map; /* * Reserve the memory for the golden contexts and point GuC at it but @@ -436,14 +463,15 @@ static int guc_prep_golden_context(struct intel_guc *guc, * GuC will also validate that the LRC base + size fall within the * allowed GGTT range. */ - if (blob) { + if (!iosys_map_is_null(&guc->ads_map)) { offset = guc_ads_golden_ctxt_offset(guc); addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset; - info = &blob->system_info; + info_map = IOSYS_MAP_INIT_OFFSET(&guc->ads_map, + offsetof(struct __guc_ads_blob, system_info)); } else { memset(&local_info, 0, sizeof(local_info)); - info = &local_info; - fill_engine_enable_masks(gt, info); + iosys_map_set_vaddr(&info_map, &local_info); + fill_engine_enable_masks(gt, &info_map); } for (engine_class = 0; engine_class <= MAX_ENGINE_CLASS; ++engine_class) { @@ -452,14 +480,14 @@ static int guc_prep_golden_context(struct intel_guc *guc, guc_class = engine_class_to_guc_class(engine_class); - if (!info->engine_enabled_masks[guc_class]) + if (!info_map_read(&info_map, engine_enabled_masks[guc_class])) continue; real_size = intel_engine_context_size(gt, engine_class); alloc_size = PAGE_ALIGN(real_size); total_size += alloc_size; - if (!blob) + if (iosys_map_is_null(&guc->ads_map)) continue; /* @@ -473,15 +501,18 @@ static int guc_prep_golden_context(struct intel_guc *guc, * what comes before it in the context image (which is identical * on all engines). */ - blob->ads.eng_state_size[guc_class] = real_size - LRC_SKIP_SIZE; - blob->ads.golden_context_lrca[guc_class] = addr_ggtt; + ads_blob_write(guc, ads.eng_state_size[guc_class], + real_size - LRC_SKIP_SIZE); + ads_blob_write(guc, ads.golden_context_lrca[guc_class], + addr_ggtt); + addr_ggtt += alloc_size; } - if (!blob) - return total_size; + /* Make sure current size matches what we calculated previously */ + if (guc->ads_golden_ctxt_size) + GEM_BUG_ON(guc->ads_golden_ctxt_size != total_size); - GEM_BUG_ON(guc->ads_golden_ctxt_size != total_size); return total_size; } @@ -505,18 +536,16 @@ static struct intel_engine_cs *find_engine_state(struct intel_gt *gt, u8 engine_ static void guc_init_golden_context(struct intel_guc *guc) { - struct __guc_ads_blob *blob = guc->ads_blob; struct intel_engine_cs *engine; struct intel_gt *gt = guc_to_gt(guc); - u32 addr_ggtt, offset; - u32 total_size = 0, alloc_size, real_size; + unsigned long offset; + u32 addr_ggtt, total_size = 0, alloc_size, real_size; u8 engine_class, guc_class; - u8 *ptr; if (!intel_uc_uses_guc_submission(>->uc)) return; - GEM_BUG_ON(!blob); + GEM_BUG_ON(iosys_map_is_null(&guc->ads_map)); /* * Go back and fill in the golden context data now that it is @@ -524,15 +553,13 @@ static void guc_init_golden_context(struct intel_guc *guc) */ offset = guc_ads_golden_ctxt_offset(guc); addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset; - ptr = ((u8 *)blob) + offset; for (engine_class = 0; engine_class <= MAX_ENGINE_CLASS; ++engine_class) { if (engine_class == OTHER_CLASS) continue; guc_class = engine_class_to_guc_class(engine_class); - - if (!blob->system_info.engine_enabled_masks[guc_class]) + if (!ads_blob_read(guc, system_info.engine_enabled_masks[guc_class])) continue; real_size = intel_engine_context_size(gt, engine_class); @@ -543,24 +570,26 @@ static void guc_init_golden_context(struct intel_guc *guc) if (!engine) { drm_err(>->i915->drm, "No engine state recorded for class %d!\n", engine_class); - blob->ads.eng_state_size[guc_class] = 0; - blob->ads.golden_context_lrca[guc_class] = 0; + ads_blob_write(guc, ads.eng_state_size[guc_class], 0); + ads_blob_write(guc, ads.golden_context_lrca[guc_class], 0); continue; } - GEM_BUG_ON(blob->ads.eng_state_size[guc_class] != + GEM_BUG_ON(ads_blob_read(guc, ads.eng_state_size[guc_class]) != real_size - LRC_SKIP_SIZE); - GEM_BUG_ON(blob->ads.golden_context_lrca[guc_class] != addr_ggtt); + GEM_BUG_ON(ads_blob_read(guc, ads.golden_context_lrca[guc_class]) != addr_ggtt); + addr_ggtt += alloc_size; - shmem_read(engine->default_state, 0, ptr, real_size); - ptr += alloc_size; + shmem_read_to_iosys_map(engine->default_state, 0, &guc->ads_map, + offset, real_size); + offset += alloc_size; } GEM_BUG_ON(guc->ads_golden_ctxt_size != total_size); } -static void guc_capture_list_init(struct intel_guc *guc, struct __guc_ads_blob *blob) +static void guc_capture_list_init(struct intel_guc *guc) { int i, j; u32 addr_ggtt, offset; @@ -572,11 +601,11 @@ static void guc_capture_list_init(struct intel_guc *guc, struct __guc_ads_blob * for (i = 0; i < GUC_CAPTURE_LIST_INDEX_MAX; i++) { for (j = 0; j < GUC_MAX_ENGINE_CLASSES; j++) { - blob->ads.capture_instance[i][j] = addr_ggtt; - blob->ads.capture_class[i][j] = addr_ggtt; + ads_blob_write(guc, ads.capture_instance[i][j], addr_ggtt); + ads_blob_write(guc, ads.capture_class[i][j], addr_ggtt); } - blob->ads.capture_global[i] = addr_ggtt; + ads_blob_write(guc, ads.capture_global[i], addr_ggtt); } } @@ -584,47 +613,52 @@ static void __guc_ads_init(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); struct drm_i915_private *i915 = gt->i915; - struct __guc_ads_blob *blob = guc->ads_blob; + struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(&guc->ads_map, + offsetof(struct __guc_ads_blob, system_info)); u32 base; /* GuC scheduling policies */ - guc_policies_init(guc, &blob->policies); + guc_policies_init(guc); /* System info */ - fill_engine_enable_masks(gt, &blob->system_info); + fill_engine_enable_masks(gt, &info_map); - blob->system_info.generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_SLICE_ENABLED] = - hweight8(gt->info.sseu.slice_mask); - blob->system_info.generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_VDBOX_SFC_SUPPORT_MASK] = - gt->info.vdbox_sfc_access; + ads_blob_write(guc, system_info.generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_SLICE_ENABLED], + hweight8(gt->info.sseu.slice_mask)); + ads_blob_write(guc, system_info.generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_VDBOX_SFC_SUPPORT_MASK], + gt->info.vdbox_sfc_access); if (GRAPHICS_VER(i915) >= 12 && !IS_DGFX(i915)) { u32 distdbreg = intel_uncore_read(gt->uncore, GEN12_DIST_DBS_POPULATED); - blob->system_info.generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_DOORBELL_COUNT_PER_SQIDI] = - ((distdbreg >> GEN12_DOORBELLS_PER_SQIDI_SHIFT) & - GEN12_DOORBELLS_PER_SQIDI) + 1; + ads_blob_write(guc, + system_info.generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_DOORBELL_COUNT_PER_SQIDI], + ((distdbreg >> GEN12_DOORBELLS_PER_SQIDI_SHIFT) + & GEN12_DOORBELLS_PER_SQIDI) + 1); } /* Golden contexts for re-initialising after a watchdog reset */ - guc_prep_golden_context(guc, blob); + guc_prep_golden_context(guc); - guc_mapping_table_init(guc_to_gt(guc), &blob->system_info); + guc_mapping_table_init(guc_to_gt(guc), &info_map); base = intel_guc_ggtt_offset(guc, guc->ads_vma); /* Capture list for hang debug */ - guc_capture_list_init(guc, blob); + guc_capture_list_init(guc); /* ADS */ - blob->ads.scheduler_policies = base + ptr_offset(blob, policies); - blob->ads.gt_system_info = base + ptr_offset(blob, system_info); + ads_blob_write(guc, ads.scheduler_policies, base + + offsetof(struct __guc_ads_blob, policies)); + ads_blob_write(guc, ads.gt_system_info, base + + offsetof(struct __guc_ads_blob, system_info)); /* MMIO save/restore list */ - guc_mmio_reg_state_init(guc, blob); + guc_mmio_reg_state_init(guc); /* Private Data */ - blob->ads.private_data = base + guc_ads_private_data_offset(guc); + ads_blob_write(guc, ads.private_data, base + + guc_ads_private_data_offset(guc)); i915_gem_object_flush_map(guc->ads_vma->obj); } @@ -638,6 +672,7 @@ static void __guc_ads_init(struct intel_guc *guc) */ int intel_guc_ads_create(struct intel_guc *guc) { + void *ads_blob; u32 size; int ret; @@ -653,7 +688,7 @@ int intel_guc_ads_create(struct intel_guc *guc) guc->ads_regset_size = ret; /* Likewise the golden contexts: */ - ret = guc_prep_golden_context(guc, NULL); + ret = guc_prep_golden_context(guc); if (ret < 0) return ret; guc->ads_golden_ctxt_size = ret; @@ -662,10 +697,15 @@ int intel_guc_ads_create(struct intel_guc *guc) size = guc_ads_blob_size(guc); ret = intel_guc_allocate_and_map_vma(guc, size, &guc->ads_vma, - (void **)&guc->ads_blob); + &ads_blob); if (ret) return ret; + if (i915_gem_object_is_lmem(guc->ads_vma->obj)) + iosys_map_set_vaddr_iomem(&guc->ads_map, (void __iomem *)ads_blob); + else + iosys_map_set_vaddr(&guc->ads_map, ads_blob); + __guc_ads_init(guc); return 0; @@ -686,7 +726,7 @@ void intel_guc_ads_init_late(struct intel_guc *guc) void intel_guc_ads_destroy(struct intel_guc *guc) { i915_vma_unpin_and_release(&guc->ads_vma, I915_VMA_RELEASE_MAP); - guc->ads_blob = NULL; + iosys_map_clear(&guc->ads_map); kfree(guc->ads_regset); } @@ -698,8 +738,8 @@ static void guc_ads_private_data_reset(struct intel_guc *guc) if (!size) return; - memset((void *)guc->ads_blob + guc_ads_private_data_offset(guc), 0, - size); + iosys_map_memset(&guc->ads_map, guc_ads_private_data_offset(guc), + 0, size); } /** @@ -722,18 +762,16 @@ void intel_guc_ads_reset(struct intel_guc *guc) u32 intel_guc_engine_usage_offset(struct intel_guc *guc) { - struct __guc_ads_blob *blob = guc->ads_blob; - u32 base = intel_guc_ggtt_offset(guc, guc->ads_vma); - u32 offset = base + ptr_offset(blob, engine_usage); - - return offset; + return intel_guc_ggtt_offset(guc, guc->ads_vma) + + offsetof(struct __guc_ads_blob, engine_usage); } -struct guc_engine_usage_record *intel_guc_engine_usage(struct intel_engine_cs *engine) +struct iosys_map intel_guc_engine_usage_record_map(struct intel_engine_cs *engine) { struct intel_guc *guc = &engine->gt->uc.guc; - struct __guc_ads_blob *blob = guc->ads_blob; u8 guc_class = engine_class_to_guc_class(engine->class); + size_t offset = offsetof(struct __guc_ads_blob, + engine_usage.engines[guc_class][ilog2(engine->logical_mask)]); - return &blob->engine_usage.engines[guc_class][ilog2(engine->logical_mask)]; + return IOSYS_MAP_INIT_OFFSET(&guc->ads_map, offset); } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h index e74c110facff..1c64f4d6ea21 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h @@ -7,6 +7,7 @@ #define _INTEL_GUC_ADS_H_ #include <linux/types.h> +#include <linux/iosys-map.h> struct intel_guc; struct drm_printer; @@ -18,7 +19,7 @@ void intel_guc_ads_init_late(struct intel_guc *guc); void intel_guc_ads_reset(struct intel_guc *guc); void intel_guc_ads_print_policy_info(struct intel_guc *guc, struct drm_printer *p); -struct guc_engine_usage_record *intel_guc_engine_usage(struct intel_engine_cs *engine); +struct iosys_map intel_guc_engine_usage_record_map(struct intel_engine_cs *engine); u32 intel_guc_engine_usage_offset(struct intel_guc *guc); #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h index 6a4612a852e2..4b300b6cc0f9 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h @@ -46,8 +46,8 @@ #define GUC_VIDEO_CLASS 1 #define GUC_VIDEOENHANCE_CLASS 2 #define GUC_BLITTER_CLASS 3 -#define GUC_RESERVED_CLASS 4 -#define GUC_LAST_ENGINE_CLASS GUC_RESERVED_CLASS +#define GUC_COMPUTE_CLASS 4 +#define GUC_LAST_ENGINE_CLASS GUC_COMPUTE_CLASS #define GUC_MAX_ENGINE_CLASSES 16 #define GUC_MAX_INSTANCES_PER_CLASS 32 @@ -156,23 +156,37 @@ FIELD_PREP(HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID, id) | \ FIELD_PREP(HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC, c) \ ) +/* the GuC arrays don't include OTHER_CLASS */ +static u8 engine_class_guc_class_map[] = { + [RENDER_CLASS] = GUC_RENDER_CLASS, + [COPY_ENGINE_CLASS] = GUC_BLITTER_CLASS, + [VIDEO_DECODE_CLASS] = GUC_VIDEO_CLASS, + [VIDEO_ENHANCEMENT_CLASS] = GUC_VIDEOENHANCE_CLASS, + [COMPUTE_CLASS] = GUC_COMPUTE_CLASS, +}; + +static u8 guc_class_engine_class_map[] = { + [GUC_RENDER_CLASS] = RENDER_CLASS, + [GUC_BLITTER_CLASS] = COPY_ENGINE_CLASS, + [GUC_VIDEO_CLASS] = VIDEO_DECODE_CLASS, + [GUC_VIDEOENHANCE_CLASS] = VIDEO_ENHANCEMENT_CLASS, + [GUC_COMPUTE_CLASS] = COMPUTE_CLASS, +}; + static inline u8 engine_class_to_guc_class(u8 class) { - BUILD_BUG_ON(GUC_RENDER_CLASS != RENDER_CLASS); - BUILD_BUG_ON(GUC_BLITTER_CLASS != COPY_ENGINE_CLASS); - BUILD_BUG_ON(GUC_VIDEO_CLASS != VIDEO_DECODE_CLASS); - BUILD_BUG_ON(GUC_VIDEOENHANCE_CLASS != VIDEO_ENHANCEMENT_CLASS); + BUILD_BUG_ON(ARRAY_SIZE(engine_class_guc_class_map) != MAX_ENGINE_CLASS + 1); GEM_BUG_ON(class > MAX_ENGINE_CLASS || class == OTHER_CLASS); - return class; + return engine_class_guc_class_map[class]; } static inline u8 guc_class_to_engine_class(u8 guc_class) { + BUILD_BUG_ON(ARRAY_SIZE(guc_class_engine_class_map) != GUC_LAST_ENGINE_CLASS + 1); GEM_BUG_ON(guc_class > GUC_LAST_ENGINE_CLASS); - GEM_BUG_ON(guc_class == GUC_RESERVED_CLASS); - return guc_class; + return guc_class_engine_class_map[guc_class]; } /* Work item for submitting workloads into work queue of GuC. */ 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 766744602d75..9f032c65a488 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c @@ -12,6 +12,7 @@ #include "intel_mchbar_regs.h" #include "gt/intel_gt.h" #include "gt/intel_gt_regs.h" +#include "gt/intel_rps.h" static inline struct intel_guc *slpc_to_guc(struct intel_guc_slpc *slpc) { @@ -116,7 +117,7 @@ static int guc_action_slpc_unset_param(struct intel_guc *guc, u8 id) { u32 request[] = { GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST, - SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 2), + SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 1), id, }; @@ -580,10 +581,10 @@ static int slpc_use_fused_rp0(struct intel_guc_slpc *slpc) static void slpc_get_rp_values(struct intel_guc_slpc *slpc) { + struct intel_rps *rps = &slpc_to_gt(slpc)->rps; u32 rp_state_cap; - rp_state_cap = intel_uncore_read(slpc_to_gt(slpc)->uncore, - GEN6_RP_STATE_CAP); + rp_state_cap = intel_rps_read_state_cap(rps); slpc->rp0_freq = REG_FIELD_GET(RP0_CAP_MASK, rp_state_cap) * GT_FREQUENCY_MULTIPLIER; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index b3a429a92c0d..1ce7e04aa837 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -174,11 +174,8 @@ static inline void init_sched_state(struct intel_context *ce) __maybe_unused static bool sched_state_is_init(struct intel_context *ce) { - /* - * XXX: Kernel contexts can have SCHED_STATE_NO_LOCK_REGISTERED after - * suspend. - */ - return !(ce->guc_state.sched_state &= + /* Kernel contexts can have SCHED_STATE_REGISTERED after suspend. */ + return !(ce->guc_state.sched_state & ~(SCHED_STATE_BLOCKED_MASK | SCHED_STATE_REGISTERED)); } @@ -1139,6 +1136,9 @@ __extend_last_switch(struct intel_guc *guc, u64 *prev_start, u32 new_start) *prev_start = ((u64)gt_stamp_hi << 32) | new_start; } +#define record_read(map_, field_) \ + iosys_map_rd_field(map_, 0, struct guc_engine_usage_record, field_) + /* * GuC updates shared memory and KMD reads it. Since this is not synchronized, * we run into a race where the value read is inconsistent. Sometimes the @@ -1153,17 +1153,17 @@ __extend_last_switch(struct intel_guc *guc, u64 *prev_start, u32 new_start) static void __get_engine_usage_record(struct intel_engine_cs *engine, u32 *last_in, u32 *id, u32 *total) { - struct guc_engine_usage_record *rec = intel_guc_engine_usage(engine); + struct iosys_map rec_map = intel_guc_engine_usage_record_map(engine); int i = 0; do { - *last_in = READ_ONCE(rec->last_switch_in_stamp); - *id = READ_ONCE(rec->current_context_index); - *total = READ_ONCE(rec->total_runtime); + *last_in = record_read(&rec_map, last_switch_in_stamp); + *id = record_read(&rec_map, current_context_index); + *total = record_read(&rec_map, total_runtime); - if (READ_ONCE(rec->last_switch_in_stamp) == *last_in && - READ_ONCE(rec->current_context_index) == *id && - READ_ONCE(rec->total_runtime) == *total) + if (record_read(&rec_map, last_switch_in_stamp) == *last_in && + record_read(&rec_map, current_context_index) == *id && + record_read(&rec_map, total_runtime) == *total) break; } while (++i < 6); } @@ -1818,24 +1818,11 @@ int intel_guc_submission_init(struct intel_guc *guc) */ GEM_BUG_ON(!guc->lrc_desc_pool); - xa_init_flags(&guc->context_lookup, XA_FLAGS_LOCK_IRQ); - - spin_lock_init(&guc->submission_state.lock); - INIT_LIST_HEAD(&guc->submission_state.guc_id_list); - ida_init(&guc->submission_state.guc_ids); - INIT_LIST_HEAD(&guc->submission_state.destroyed_contexts); - INIT_WORK(&guc->submission_state.destroyed_worker, - destroyed_worker_func); - INIT_WORK(&guc->submission_state.reset_fail_worker, - reset_fail_worker_func); - guc->submission_state.guc_ids_bitmap = bitmap_zalloc(NUMBER_MULTI_LRC_GUC_ID(guc), GFP_KERNEL); if (!guc->submission_state.guc_ids_bitmap) return -ENOMEM; - spin_lock_init(&guc->timestamp.lock); - INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping); guc->timestamp.ping_delay = (POLL_TIME_CLKS / gt->clock_frequency + 1) * HZ; guc->timestamp.shift = gpm_timestamp_shift(gt); @@ -3608,6 +3595,9 @@ static int guc_resume(struct intel_engine_cs *engine) setup_hwsp(engine); start_engine(engine); + if (engine->class == RENDER_CLASS) + xehp_enable_ccs_engines(engine); + return 0; } @@ -3789,7 +3779,7 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine) guc_default_irqs(engine); guc_init_breadcrumbs(engine); - if (engine->class == RENDER_CLASS) + if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE) rcs_submission_override(engine); lrc_init_wa_ctx(engine); @@ -3831,6 +3821,20 @@ static bool __guc_submission_selected(struct intel_guc *guc) void intel_guc_submission_init_early(struct intel_guc *guc) { + xa_init_flags(&guc->context_lookup, XA_FLAGS_LOCK_IRQ); + + spin_lock_init(&guc->submission_state.lock); + INIT_LIST_HEAD(&guc->submission_state.guc_id_list); + ida_init(&guc->submission_state.guc_ids); + INIT_LIST_HEAD(&guc->submission_state.destroyed_contexts); + INIT_WORK(&guc->submission_state.destroyed_worker, + destroyed_worker_func); + INIT_WORK(&guc->submission_state.reset_fail_worker, + reset_fail_worker_func); + + spin_lock_init(&guc->timestamp.lock); + INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping); + guc->submission_state.num_guc_ids = GUC_MAX_LRC_DESCRIPTORS; guc->submission_supported = __guc_submission_supported(guc); guc->submission_selected = __guc_submission_selected(guc); @@ -4022,10 +4026,9 @@ static void guc_handle_context_reset(struct intel_guc *guc, capture_error_state(guc, ce); guc_context_replay(ce); } else { - drm_err(&guc_to_gt(guc)->i915->drm, - "Invalid GuC engine reset notificaion for 0x%04X on %s: banned = %d, blocked = %d", - ce->guc_id.id, ce->engine->name, intel_context_is_banned(ce), - context_blocked(ce)); + drm_info(&guc_to_gt(guc)->i915->drm, + "Ignoring context reset notification of banned context 0x%04X on %s", + ce->guc_id.id, ce->engine->name); } } diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c index 1297ddbf7f88..812220a43df8 100644 --- a/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c +++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c @@ -154,6 +154,10 @@ static int intel_guc_multi_lrc_basic(void *arg) int ret; for (class = 0; class < MAX_ENGINE_CLASS + 1; ++class) { + /* We don't support breadcrumb handshake on these classes */ + if (class == COMPUTE_CLASS || class == RENDER_CLASS) + continue; + ret = __intel_guc_multi_lrc_basic(gt, class); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index e8d6c76e9234..057ec4490104 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -188,14 +188,29 @@ static ssize_t description_show(struct mdev_type *mtype, type->weight); } +static ssize_t name_show(struct mdev_type *mtype, + struct mdev_type_attribute *attr, char *buf) +{ + struct intel_vgpu_type *type; + struct intel_gvt *gvt = kdev_to_i915(mtype_get_parent_dev(mtype))->gvt; + + type = &gvt->types[mtype_get_type_group_id(mtype)]; + if (!type) + return 0; + + return sprintf(buf, "%s\n", type->name); +} + static MDEV_TYPE_ATTR_RO(available_instances); static MDEV_TYPE_ATTR_RO(device_api); static MDEV_TYPE_ATTR_RO(description); +static MDEV_TYPE_ATTR_RO(name); static struct attribute *gvt_type_attrs[] = { &mdev_type_attr_available_instances.attr, &mdev_type_attr_device_api.attr, &mdev_type_attr_description.attr, + &mdev_type_attr_name.attr, NULL, }; diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 3b8850bb3152..09de45d3e274 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -838,21 +838,6 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!i915->params.nuclear_pageflip && match_info->graphics.ver < 5) i915->drm.driver_features &= ~DRIVER_ATOMIC; - /* - * Check if we support fake LMEM -- for now we only unleash this for - * the live selftests(test-and-exit). - */ -#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) - if (IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM)) { - if (GRAPHICS_VER(i915) >= 9 && i915_selftest.live < 0 && - i915->params.fake_lmem_start) { - mkwrite_device_info(i915)->memory_regions = - REGION_SMEM | REGION_LMEM | REGION_STOLEN_SMEM; - GEM_BUG_ON(!HAS_LMEM(i915)); - } - } -#endif - ret = pci_enable_device(pdev); if (ret) goto out_fini; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index d813240caca7..865f989f6841 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -910,7 +910,7 @@ static inline struct intel_gt *to_gt(struct drm_i915_private *i915) (GRAPHICS_VER(i915) >= (from) && GRAPHICS_VER(i915) <= (until)) #define MEDIA_VER(i915) (INTEL_INFO(i915)->media.ver) -#define MEDIA_VER_FULL(i915) IP_VER(INTEL_INFO(i915)->media.arch, \ +#define MEDIA_VER_FULL(i915) IP_VER(INTEL_INFO(i915)->media.ver, \ INTEL_INFO(i915)->media.rel) #define IS_MEDIA_VER(i915, from, until) \ (MEDIA_VER(i915) >= (from) && MEDIA_VER(i915) <= (until)) @@ -1110,11 +1110,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define IS_ICL_WITH_PORT_F(dev_priv) \ IS_SUBPLATFORM(dev_priv, INTEL_ICELAKE, INTEL_SUBPLATFORM_PORTF) -#define IS_TGL_U(dev_priv) \ - IS_SUBPLATFORM(dev_priv, INTEL_TIGERLAKE, INTEL_SUBPLATFORM_ULT) - -#define IS_TGL_Y(dev_priv) \ - IS_SUBPLATFORM(dev_priv, INTEL_TIGERLAKE, INTEL_SUBPLATFORM_ULX) +#define IS_TGL_UY(dev_priv) \ + IS_SUBPLATFORM(dev_priv, INTEL_TIGERLAKE, INTEL_SUBPLATFORM_UY) #define IS_SKL_GRAPHICS_STEP(p, since, until) (IS_SKYLAKE(p) && IS_GRAPHICS_STEP(p, since, until)) @@ -1133,11 +1130,11 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, IS_DISPLAY_STEP(__i915, since, until)) #define IS_TGL_UY_GRAPHICS_STEP(__i915, since, until) \ - ((IS_TGL_U(__i915) || IS_TGL_Y(__i915)) && \ + (IS_TGL_UY(__i915) && \ IS_GRAPHICS_STEP(__i915, since, until)) #define IS_TGL_GRAPHICS_STEP(__i915, since, until) \ - (IS_TIGERLAKE(__i915) && !(IS_TGL_U(__i915) || IS_TGL_Y(__i915)) && \ + (IS_TIGERLAKE(__i915) && !IS_TGL_UY(__i915)) && \ IS_GRAPHICS_STEP(__i915, since, until)) #define IS_RKL_DISPLAY_STEP(p, since, until) \ @@ -1207,6 +1204,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, ENGINE_INSTANCES_MASK(gt, VCS0, I915_MAX_VCS) #define VEBOX_MASK(gt) \ ENGINE_INSTANCES_MASK(gt, VECS0, I915_MAX_VECS) +#define CCS_MASK(gt) \ + ENGINE_INSTANCES_MASK(gt, CCS0, I915_MAX_CCS) /* * The Gen7 cmdparser copies the scanned buffer to the ggtt for execution @@ -1304,17 +1303,28 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, /* * Set this flag, when platform requires 64K GTT page sizes or larger for - * device local memory access. Also this flag implies that we require or - * at least support the compact PT layout for the ppGTT when using the 64K - * GTT pages. + * device local memory access. */ #define HAS_64K_PAGES(dev_priv) (INTEL_INFO(dev_priv)->has_64k_pages) +/* + * Set this flag when platform doesn't allow both 64k pages and 4k pages in + * the same PT. this flag means we need to support compact PT layout for the + * ppGTT when using the 64K GTT pages. + */ +#define NEEDS_COMPACT_PT(dev_priv) (INTEL_INFO(dev_priv)->needs_compact_pt) + #define HAS_IPC(dev_priv) (INTEL_INFO(dev_priv)->display.has_ipc) #define HAS_REGION(i915, i) (INTEL_INFO(i915)->memory_regions & (i)) #define HAS_LMEM(i915) HAS_REGION(i915, REGION_LMEM) +/* + * Platform has the dedicated compression control state for each lmem surfaces + * stored in lmem to support the 3D and media compression formats. + */ +#define HAS_FLAT_CCS(dev_priv) (INTEL_INFO(dev_priv)->has_flat_ccs) + #define HAS_GT_UC(dev_priv) (INTEL_INFO(dev_priv)->has_gt_uc) #define HAS_POOLED_EU(dev_priv) (INTEL_INFO(dev_priv)->has_pooled_eu) diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index 1930487e5f09..5ad071e09301 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -197,11 +197,6 @@ i915_param_named(enable_gvt, bool, 0400, "Enable support for Intel GVT-g graphics virtualization host support(default:false)"); #endif -#if IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM) -i915_param_named_unsafe(fake_lmem_start, ulong, 0400, - "Fake LMEM start offset (default: 0)"); -#endif - #if CONFIG_DRM_I915_REQUEST_TIMEOUT i915_param_named_unsafe(request_timeout_ms, uint, 0600, "Default request/fence/batch buffer expiration timeout."); diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h index c9d53ff910a0..c779a6f85c7e 100644 --- a/drivers/gpu/drm/i915/i915_params.h +++ b/drivers/gpu/drm/i915/i915_params.h @@ -72,7 +72,6 @@ struct drm_printer; param(int, fastboot, -1, 0600) \ param(int, enable_dpcd_backlight, -1, 0600) \ param(char *, force_probe, CONFIG_DRM_I915_FORCE_PROBE, 0400) \ - param(unsigned long, fake_lmem_start, 0, IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM) ? 0400 : 0) \ param(unsigned int, request_timeout_ms, CONFIG_DRM_I915_REQUEST_TIMEOUT, CONFIG_DRM_I915_REQUEST_TIMEOUT ? 0600 : 0) \ /* leave bools at the end to not create holes */ \ param(bool, enable_hangcheck, true, 0600) \ diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 8e321d300e0c..9e077929ed67 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -1005,6 +1005,7 @@ static const struct intel_device_info adl_p_info = { XE_HP_PAGE_SIZES, \ .dma_mask_size = 46, \ .has_64bit_reloc = 1, \ + .has_flat_ccs = 1, \ .has_global_mocs = 1, \ .has_gt_uc = 1, \ .has_llc = 1, \ @@ -1030,6 +1031,7 @@ static const struct intel_device_info xehpsdv_info = { PLATFORM(INTEL_XEHPSDV), .display = { }, .has_64k_pages = 1, + .needs_compact_pt = 1, .platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VECS1) | BIT(VECS2) | BIT(VECS3) | @@ -1048,6 +1050,7 @@ static const struct intel_device_info xehpsdv_info = { .has_4tile = 1, \ .has_64k_pages = 1, \ .has_guc_deprivilege = 1, \ + .needs_compact_pt = 1, \ .platform_engine_mask = \ BIT(RCS0) | BIT(BCS0) | \ BIT(VECS0) | BIT(VECS1) | \ diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 00fb40029f43..0a9c3fcc09b1 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -4374,6 +4374,10 @@ void i915_perf_init(struct drm_i915_private *i915) /* XXX const struct i915_perf_ops! */ + /* i915_perf is not enabled for DG2 yet */ + if (IS_DG2(i915)) + return; + perf->oa_formats = oa_formats; if (IS_HASWELL(i915)) { perf->ops.is_valid_b_counter_reg = gen7_is_valid_b_counter_addr; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index a0dba005e997..51f46fe45c72 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -971,6 +971,10 @@ #define GEN11_VEBOX2_RING_BASE 0x1d8000 #define XEHP_VEBOX3_RING_BASE 0x1e8000 #define XEHP_VEBOX4_RING_BASE 0x1f8000 +#define GEN12_COMPUTE0_RING_BASE 0x1a000 +#define GEN12_COMPUTE1_RING_BASE 0x1c000 +#define GEN12_COMPUTE2_RING_BASE 0x1e000 +#define GEN12_COMPUTE3_RING_BASE 0x26000 #define BLT_RING_BASE 0x22000 @@ -8456,6 +8460,20 @@ enum skl_power_gate { #define SGGI_DIS REG_BIT(15) #define SGR_DIS REG_BIT(13) +#define XEHPSDV_FLAT_CCS_BASE_ADDR _MMIO(0x4910) +#define XEHPSDV_CCS_BASE_SHIFT 8 + +/* gamt regs */ +#define GEN8_L3_LRA_1_GPGPU _MMIO(0x4dd4) +#define GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW 0x67F1427F /* max/min for LRA1/2 */ +#define GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV 0x5FF101FF /* max/min for LRA1/2 */ +#define GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL 0x67F1427F /* " " */ +#define GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT 0x5FF101FF /* " " */ + +#define MMCD_MISC_CTRL _MMIO(0x4ddc) /* skl+ */ +#define MMCD_PCLA (1 << 31) +#define MMCD_HOTSPOT_EN (1 << 27) + #define _ICL_PHY_MISC_A 0x64C00 #define _ICL_PHY_MISC_B 0x64C04 #define _DG2_PHY_MISC_TC1 0x64C14 /* TC1="PHY E" but offset as if "PHY F" */ @@ -8819,12 +8837,6 @@ enum skl_power_gate { #define DSB_ENABLE (1 << 31) #define DSB_STATUS (1 << 0) -#define TGL_ROOT_DEVICE_ID 0x9A00 -#define TGL_ROOT_DEVICE_MASK 0xFF00 -#define TGL_ROOT_DEVICE_SKU_MASK 0xF -#define TGL_ROOT_DEVICE_SKU_ULX 0x2 -#define TGL_ROOT_DEVICE_SKU_ULT 0x4 - #define CLKREQ_POLICY _MMIO(0x101038) #define CLKREQ_POLICY_MEM_UP_OVRD REG_BIT(1) diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c index 76d5211c25eb..129f668f21ff 100644 --- a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c +++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c @@ -19,6 +19,9 @@ struct i915_ttm_buddy_manager { struct drm_buddy mm; struct list_head reserved; struct mutex lock; + unsigned long visible_size; + unsigned long visible_avail; + unsigned long visible_reserved; u64 default_page_size; }; @@ -79,7 +82,7 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man, lpfn = pages; } - if (size > mm->size) { + if (size > lpfn << PAGE_SHIFT) { err = -E2BIG; goto err_free_res; } @@ -87,6 +90,12 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man, n_pages = size >> ilog2(mm->chunk_size); mutex_lock(&bman->lock); + if (lpfn <= bman->visible_size && n_pages > bman->visible_avail) { + mutex_unlock(&bman->lock); + err = -ENOSPC; + goto err_free_res; + } + err = drm_buddy_alloc_blocks(mm, (u64)place->fpfn << PAGE_SHIFT, (u64)lpfn << PAGE_SHIFT, (u64)n_pages << PAGE_SHIFT, @@ -107,6 +116,38 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man, mutex_unlock(&bman->lock); } + if (lpfn <= bman->visible_size) { + bman_res->used_visible_size = bman_res->base.num_pages; + } else { + struct drm_buddy_block *block; + + list_for_each_entry(block, &bman_res->blocks, link) { + unsigned long start = + drm_buddy_block_offset(block) >> PAGE_SHIFT; + + if (start < bman->visible_size) { + unsigned long end = start + + (drm_buddy_block_size(mm, block) >> PAGE_SHIFT); + + bman_res->used_visible_size += + min(end, bman->visible_size) - start; + } + } + } + + if (bman_res->used_visible_size) { + mutex_lock(&bman->lock); + bman->visible_avail -= bman_res->used_visible_size; + mutex_unlock(&bman->lock); + } + + if (place->lpfn - place->fpfn == n_pages) + bman_res->base.start = place->fpfn; + else if (lpfn <= bman->visible_size) + bman_res->base.start = 0; + else + bman_res->base.start = bman->visible_size; + *res = &bman_res->base; return 0; @@ -128,6 +169,7 @@ static void i915_ttm_buddy_man_free(struct ttm_resource_manager *man, mutex_lock(&bman->lock); drm_buddy_free_list(&bman->mm, &bman_res->blocks); + bman->visible_avail += bman_res->used_visible_size; mutex_unlock(&bman->lock); ttm_resource_fini(man, res); @@ -143,6 +185,12 @@ static void i915_ttm_buddy_man_debug(struct ttm_resource_manager *man, mutex_lock(&bman->lock); drm_printf(printer, "default_page_size: %lluKiB\n", bman->default_page_size >> 10); + drm_printf(printer, "visible_avail: %lluMiB\n", + (u64)bman->visible_avail << PAGE_SHIFT >> 20); + drm_printf(printer, "visible_size: %lluMiB\n", + (u64)bman->visible_size << PAGE_SHIFT >> 20); + drm_printf(printer, "visible_reserved: %lluMiB\n", + (u64)bman->visible_reserved << PAGE_SHIFT >> 20); drm_buddy_print(&bman->mm, printer); @@ -164,6 +212,7 @@ static const struct ttm_resource_manager_func i915_ttm_buddy_manager_func = { * @type: Memory type we want to manage * @use_tt: Set use_tt for the manager * @size: The size in bytes to manage + * @visible_size: The CPU visible size in bytes to manage * @default_page_size: The default minimum page size in bytes for allocations, * this must be at least as large as @chunk_size, and can be overridden by * setting the BO page_alignment, to be larger or smaller as needed. @@ -187,7 +236,7 @@ static const struct ttm_resource_manager_func i915_ttm_buddy_manager_func = { */ int i915_ttm_buddy_man_init(struct ttm_device *bdev, unsigned int type, bool use_tt, - u64 size, u64 default_page_size, + u64 size, u64 visible_size, u64 default_page_size, u64 chunk_size) { struct ttm_resource_manager *man; @@ -206,6 +255,8 @@ int i915_ttm_buddy_man_init(struct ttm_device *bdev, INIT_LIST_HEAD(&bman->reserved); GEM_BUG_ON(default_page_size < chunk_size); bman->default_page_size = default_page_size; + bman->visible_size = visible_size >> PAGE_SHIFT; + bman->visible_avail = bman->visible_size; man = &bman->manager; man->use_tt = use_tt; @@ -250,6 +301,8 @@ int i915_ttm_buddy_man_fini(struct ttm_device *bdev, unsigned int type) mutex_lock(&bman->lock); drm_buddy_free_list(mm, &bman->reserved); drm_buddy_fini(mm); + bman->visible_avail += bman->visible_reserved; + WARN_ON_ONCE(bman->visible_avail != bman->visible_size); mutex_unlock(&bman->lock); ttm_resource_manager_cleanup(man); @@ -273,6 +326,7 @@ int i915_ttm_buddy_man_reserve(struct ttm_resource_manager *man, { struct i915_ttm_buddy_manager *bman = to_buddy_manager(man); struct drm_buddy *mm = &bman->mm; + unsigned long fpfn = start >> PAGE_SHIFT; unsigned long flags = 0; int ret; @@ -284,8 +338,37 @@ int i915_ttm_buddy_man_reserve(struct ttm_resource_manager *man, size, mm->chunk_size, &bman->reserved, flags); + + if (fpfn < bman->visible_size) { + unsigned long lpfn = fpfn + (size >> PAGE_SHIFT); + unsigned long visible = min(lpfn, bman->visible_size) - fpfn; + + bman->visible_reserved += visible; + bman->visible_avail -= visible; + } mutex_unlock(&bman->lock); return ret; } +/** + * i915_ttm_buddy_man_visible_size - Return the size of the CPU visible portion + * in pages. + * @man: The buddy allocator ttm manager + */ +u64 i915_ttm_buddy_man_visible_size(struct ttm_resource_manager *man) +{ + struct i915_ttm_buddy_manager *bman = to_buddy_manager(man); + + return bman->visible_size; +} + +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +void i915_ttm_buddy_man_force_visible_size(struct ttm_resource_manager *man, + u64 size) +{ + struct i915_ttm_buddy_manager *bman = to_buddy_manager(man); + + bman->visible_size = size; +} +#endif diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h index 72c90b432e87..52d9586d242c 100644 --- a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h +++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h @@ -21,6 +21,8 @@ struct drm_buddy; * @base: struct ttm_resource base class we extend * @blocks: the list of struct i915_buddy_block for this resource/allocation * @flags: DRM_BUDDY_*_ALLOCATION flags + * @used_visible_size: How much of this resource, if any, uses the CPU visible + * portion, in pages. * @mm: the struct i915_buddy_mm for this resource * * Extends the struct ttm_resource to manage an address space allocation with @@ -30,6 +32,7 @@ struct i915_ttm_buddy_resource { struct ttm_resource base; struct list_head blocks; unsigned long flags; + unsigned long used_visible_size; struct drm_buddy *mm; }; @@ -48,11 +51,19 @@ to_ttm_buddy_resource(struct ttm_resource *res) int i915_ttm_buddy_man_init(struct ttm_device *bdev, unsigned type, bool use_tt, - u64 size, u64 default_page_size, u64 chunk_size); + u64 size, u64 visible_size, + u64 default_page_size, u64 chunk_size); int i915_ttm_buddy_man_fini(struct ttm_device *bdev, unsigned int type); int i915_ttm_buddy_man_reserve(struct ttm_resource_manager *man, u64 start, u64 size); +u64 i915_ttm_buddy_man_visible_size(struct ttm_resource_manager *man); + +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +void i915_ttm_buddy_man_force_visible_size(struct ttm_resource_manager *man, + u64 size); +#endif + #endif diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 845cd88f8313..94fcdb7bd21d 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -540,6 +540,9 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma) void __iomem *ptr; int err; + if (WARN_ON_ONCE(vma->obj->flags & I915_BO_ALLOC_GPU_ONLY)) + return IO_ERR_PTR(-EINVAL); + if (!i915_gem_object_is_lmem(vma->obj)) { if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) { err = -ENODEV; @@ -757,6 +760,14 @@ i915_vma_insert(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, end = min_t(u64, end, (1ULL << 32) - I915_GTT_PAGE_SIZE); GEM_BUG_ON(!IS_ALIGNED(end, I915_GTT_PAGE_SIZE)); + alignment = max(alignment, i915_vm_obj_min_alignment(vma->vm, vma->obj)); + /* + * for compact-pt we round up the reservation to prevent + * any smaller pages being used within the same PDE + */ + if (NEEDS_COMPACT_PT(vma->vm->i915)) + size = round_up(size, alignment); + /* If binding the object/GGTT view requires more space than the entire * aperture has, reject it early before evicting everything in a vain * attempt to find space. @@ -769,6 +780,7 @@ i915_vma_insert(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, } color = 0; + if (i915_vm_has_cache_coloring(vma->vm)) color = vma->obj->cache_level; @@ -1609,15 +1621,27 @@ void i915_vma_reopen(struct i915_vma *vma) void i915_vma_release(struct kref *ref) { struct i915_vma *vma = container_of(ref, typeof(*vma), ref); + + i915_vm_put(vma->vm); + i915_active_fini(&vma->active); + GEM_WARN_ON(vma->resource); + i915_vma_free(vma); +} + +static void force_unbind(struct i915_vma *vma) +{ + if (!drm_mm_node_allocated(&vma->node)) + return; + + atomic_and(~I915_VMA_PIN_MASK, &vma->flags); + WARN_ON(__i915_vma_unbind(vma)); + GEM_BUG_ON(drm_mm_node_allocated(&vma->node)); +} + +static void release_references(struct i915_vma *vma) +{ struct drm_i915_gem_object *obj = vma->obj; - if (drm_mm_node_allocated(&vma->node)) { - mutex_lock(&vma->vm->mutex); - atomic_and(~I915_VMA_PIN_MASK, &vma->flags); - WARN_ON(__i915_vma_unbind(vma)); - mutex_unlock(&vma->vm->mutex); - GEM_BUG_ON(drm_mm_node_allocated(&vma->node)); - } GEM_BUG_ON(i915_vma_is_active(vma)); spin_lock(&obj->vma.lock); @@ -1627,11 +1651,49 @@ void i915_vma_release(struct kref *ref) spin_unlock(&obj->vma.lock); __i915_vma_remove_closed(vma); - i915_vm_put(vma->vm); - i915_active_fini(&vma->active); - GEM_WARN_ON(vma->resource); - i915_vma_free(vma); + __i915_vma_put(vma); +} + +/** + * i915_vma_destroy_locked - Remove all weak reference to the vma and put + * the initial reference. + * + * This function should be called when it's decided the vma isn't needed + * anymore. The caller must assure that it doesn't race with another lookup + * plus destroy, typically by taking an appropriate reference. + * + * Current callsites are + * - __i915_gem_object_pages_fini() + * - __i915_vm_close() - Blocks the above function by taking a reference on + * the object. + * - __i915_vma_parked() - Blocks the above functions by taking an open-count on + * the vm and a reference on the object. + * + * Because of locks taken during destruction, a vma is also guaranteed to + * stay alive while the following locks are held if it was looked up while + * holding one of the locks: + * - vm->mutex + * - obj->vma.lock + * - gt->closed_lock + * + * A vma user can also temporarily keep the vma alive while holding a vma + * reference. + */ +void i915_vma_destroy_locked(struct i915_vma *vma) +{ + lockdep_assert_held(&vma->vm->mutex); + + force_unbind(vma); + release_references(vma); +} + +void i915_vma_destroy(struct i915_vma *vma) +{ + mutex_lock(&vma->vm->mutex); + force_unbind(vma); + mutex_unlock(&vma->vm->mutex); + release_references(vma); } void i915_vma_parked(struct intel_gt *gt) @@ -1665,7 +1727,7 @@ void i915_vma_parked(struct intel_gt *gt) if (i915_gem_object_trylock(obj, NULL)) { INIT_LIST_HEAD(&vma->closed_link); - __i915_vma_put(vma); + i915_vma_destroy(vma); i915_gem_object_unlock(obj); } else { /* back you go.. */ diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index 011af044ad4f..67ae7341c7e0 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -236,6 +236,9 @@ static inline void __i915_vma_put(struct i915_vma *vma) kref_put(&vma->ref, i915_vma_release); } +void i915_vma_destroy_locked(struct i915_vma *vma); +void i915_vma_destroy(struct i915_vma *vma); + #define assert_vma_held(vma) dma_resv_assert_held((vma)->obj->base.resv) static inline void i915_vma_lock(struct i915_vma *vma) diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index 98861642e275..41a5b98d1342 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -173,6 +173,10 @@ static const u16 subplatform_portf_ids[] = { INTEL_ICL_PORT_F_IDS(0), }; +static const u16 subplatform_uy_ids[] = { + INTEL_TGL_12_GT2_IDS(0), +}; + static const u16 subplatform_n_ids[] = { INTEL_ADLN_IDS(0), }; @@ -217,6 +221,9 @@ void intel_device_info_subplatform_init(struct drm_i915_private *i915) } else if (find_devid(devid, subplatform_portf_ids, ARRAY_SIZE(subplatform_portf_ids))) { mask = BIT(INTEL_SUBPLATFORM_PORTF); + } else if (find_devid(devid, subplatform_uy_ids, + ARRAY_SIZE(subplatform_uy_ids))) { + mask = BIT(INTEL_SUBPLATFORM_UY); } else if (find_devid(devid, subplatform_n_ids, ARRAY_SIZE(subplatform_n_ids))) { mask = BIT(INTEL_SUBPLATFORM_N); @@ -225,25 +232,6 @@ void intel_device_info_subplatform_init(struct drm_i915_private *i915) mask = BIT(INTEL_SUBPLATFORM_RPL_S); } - if (IS_TIGERLAKE(i915)) { - struct pci_dev *root, *pdev = to_pci_dev(i915->drm.dev); - - root = list_first_entry(&pdev->bus->devices, typeof(*root), bus_list); - - drm_WARN_ON(&i915->drm, mask); - drm_WARN_ON(&i915->drm, (root->device & TGL_ROOT_DEVICE_MASK) != - TGL_ROOT_DEVICE_ID); - - switch (root->device & TGL_ROOT_DEVICE_SKU_MASK) { - case TGL_ROOT_DEVICE_SKU_ULX: - mask = BIT(INTEL_SUBPLATFORM_ULX); - break; - case TGL_ROOT_DEVICE_SKU_ULT: - mask = BIT(INTEL_SUBPLATFORM_ULT); - break; - } - } - GEM_BUG_ON(mask & ~INTEL_SUBPLATFORM_MASK); RUNTIME_INFO(i915)->platform_mask[pi] |= mask; diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h index 8026e805ff12..f9b955810593 100644 --- a/drivers/gpu/drm/i915/intel_device_info.h +++ b/drivers/gpu/drm/i915/intel_device_info.h @@ -106,6 +106,9 @@ enum intel_platform { /* ICL */ #define INTEL_SUBPLATFORM_PORTF (0) +/* TGL */ +#define INTEL_SUBPLATFORM_UY (0) + /* DG2 */ #define INTEL_SUBPLATFORM_G10 0 #define INTEL_SUBPLATFORM_G11 1 @@ -131,9 +134,11 @@ enum intel_ppgtt_type { /* Keep has_* in alphabetical order */ \ func(has_64bit_reloc); \ func(has_64k_pages); \ + func(needs_compact_pt); \ func(gpu_reset_clobbers_display); \ func(has_reset_engine); \ func(has_4tile); \ + func(has_flat_ccs); \ func(has_global_mocs); \ func(has_gt_uc); \ func(has_guc_deprivilege); \ diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c index 49ccafc224b7..ded78b83e0b5 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.c +++ b/drivers/gpu/drm/i915/intel_memory_region.c @@ -99,10 +99,14 @@ static int iomemtest(struct intel_memory_region *mem, bool test_all, const void *caller) { - resource_size_t last = resource_size(&mem->region) - PAGE_SIZE; - resource_size_t page; + resource_size_t last, page; int err; + if (mem->io_size < PAGE_SIZE) + return 0; + + last = mem->io_size - PAGE_SIZE; + /* * Quick test to check read/write access to the iomap (backing store). * @@ -219,6 +223,7 @@ intel_memory_region_create(struct drm_i915_private *i915, resource_size_t size, resource_size_t min_page_size, resource_size_t io_start, + resource_size_t io_size, u16 type, u16 instance, const struct intel_memory_region_ops *ops) @@ -233,6 +238,7 @@ intel_memory_region_create(struct drm_i915_private *i915, mem->i915 = i915; mem->region = (struct resource)DEFINE_RES_MEM(start, size); mem->io_start = io_start; + mem->io_size = io_size; mem->min_page_size = min_page_size; mem->ops = ops; mem->total = size; diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h index 385c32b0709d..bbc35ec5c090 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.h +++ b/drivers/gpu/drm/i915/intel_memory_region.h @@ -67,10 +67,8 @@ struct intel_memory_region { struct io_mapping iomap; struct resource region; - /* For fake LMEM */ - struct drm_mm_node fake_mappable; - resource_size_t io_start; + resource_size_t io_size; resource_size_t min_page_size; resource_size_t total; resource_size_t avail; @@ -81,8 +79,6 @@ struct intel_memory_region { char name[16]; bool private; /* not for userspace */ - dma_addr_t remap_addr; - struct { struct mutex lock; /* Protects access to objects */ struct list_head list; @@ -103,6 +99,7 @@ intel_memory_region_create(struct drm_i915_private *i915, resource_size_t size, resource_size_t min_page_size, resource_size_t io_start, + resource_size_t io_size, u16 type, u16 instance, const struct intel_memory_region_ops *ops); diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c index f2b888c16958..737ef3f4ab54 100644 --- a/drivers/gpu/drm/i915/intel_region_ttm.c +++ b/drivers/gpu/drm/i915/intel_region_ttm.c @@ -87,6 +87,7 @@ int intel_region_ttm_init(struct intel_memory_region *mem) ret = i915_ttm_buddy_man_init(bdev, mem_type, false, resource_size(&mem->region), + mem->io_size, mem->min_page_size, PAGE_SIZE); if (ret) return ret; @@ -199,12 +200,25 @@ intel_region_ttm_resource_alloc(struct intel_memory_region *mem, struct ttm_resource *res; int ret; + if (flags & I915_BO_ALLOC_CONTIGUOUS) + place.flags |= TTM_PL_FLAG_CONTIGUOUS; + if (mem->io_size && mem->io_size < mem->total) { + if (flags & I915_BO_ALLOC_GPU_ONLY) { + place.flags |= TTM_PL_FLAG_TOPDOWN; + } else { + place.fpfn = 0; + place.lpfn = mem->io_size >> PAGE_SHIFT; + } + } + mock_bo.base.size = size; - place.flags = flags; + mock_bo.bdev = &mem->i915->bdev; ret = man->func->alloc(man, &mock_bo, &place, &res); if (ret == -ENOSPC) ret = -ENXIO; + if (!ret) + res->bo = NULL; /* Rather blow up, then some uaf */ return ret ? ERR_PTR(ret) : res; } @@ -219,6 +233,11 @@ void intel_region_ttm_resource_free(struct intel_memory_region *mem, struct ttm_resource *res) { struct ttm_resource_manager *man = mem->region_private; + struct ttm_buffer_object mock_bo = {}; + + mock_bo.base.size = res->num_pages << PAGE_SHIFT; + mock_bo.bdev = &mem->i915->bdev; + res->bo = &mock_bo; man->func->free(man, res); } diff --git a/drivers/gpu/drm/i915/intel_step.c b/drivers/gpu/drm/i915/intel_step.c index b6561f97578d..74e8e4680028 100644 --- a/drivers/gpu/drm/i915/intel_step.c +++ b/drivers/gpu/drm/i915/intel_step.c @@ -172,7 +172,7 @@ void intel_step_init(struct drm_i915_private *i915) } else if (IS_ROCKETLAKE(i915)) { revids = rkl_revids; size = ARRAY_SIZE(rkl_revids); - } else if (IS_TGL_U(i915) || IS_TGL_Y(i915)) { + } else if (IS_TGL_UY(i915)) { revids = tgl_uy_revids; size = ARRAY_SIZE(tgl_uy_revids); } else if (IS_TIGERLAKE(i915)) { diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index e7e6c4b2c81d..ab751192eb3b 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -27,9 +27,11 @@ #include "gem/i915_gem_context.h" #include "gem/i915_gem_internal.h" +#include "gem/i915_gem_region.h" #include "gem/selftests/mock_context.h" #include "gt/intel_context.h" #include "gt/intel_gpu_commands.h" +#include "gt/intel_gtt.h" #include "i915_random.h" #include "i915_selftest.h" @@ -239,6 +241,8 @@ static int lowlevel_hole(struct i915_address_space *vm, u64 hole_start, u64 hole_end, unsigned long end_time) { + const unsigned int min_alignment = + i915_vm_min_alignment(vm, INTEL_MEMORY_SYSTEM); I915_RND_STATE(seed_prng); struct i915_vma_resource *mock_vma_res; unsigned int size; @@ -252,9 +256,10 @@ static int lowlevel_hole(struct i915_address_space *vm, I915_RND_SUBSTATE(prng, seed_prng); struct drm_i915_gem_object *obj; unsigned int *order, count, n; - u64 hole_size; + u64 hole_size, aligned_size; - hole_size = (hole_end - hole_start) >> size; + aligned_size = max_t(u32, ilog2(min_alignment), size); + hole_size = (hole_end - hole_start) >> aligned_size; if (hole_size > KMALLOC_MAX_SIZE / sizeof(u32)) hole_size = KMALLOC_MAX_SIZE / sizeof(u32); count = hole_size >> 1; @@ -275,8 +280,8 @@ static int lowlevel_hole(struct i915_address_space *vm, } GEM_BUG_ON(!order); - GEM_BUG_ON(count * BIT_ULL(size) > vm->total); - GEM_BUG_ON(hole_start + count * BIT_ULL(size) > hole_end); + GEM_BUG_ON(count * BIT_ULL(aligned_size) > vm->total); + GEM_BUG_ON(hole_start + count * BIT_ULL(aligned_size) > hole_end); /* Ignore allocation failures (i.e. don't report them as * a test failure) as we are purposefully allocating very @@ -299,10 +304,10 @@ static int lowlevel_hole(struct i915_address_space *vm, } for (n = 0; n < count; n++) { - u64 addr = hole_start + order[n] * BIT_ULL(size); + u64 addr = hole_start + order[n] * BIT_ULL(aligned_size); intel_wakeref_t wakeref; - GEM_BUG_ON(addr + BIT_ULL(size) > vm->total); + GEM_BUG_ON(addr + BIT_ULL(aligned_size) > vm->total); if (igt_timeout(end_time, "%s timed out before %d/%d\n", @@ -345,7 +350,7 @@ alloc_vm_end: } mock_vma_res->bi.pages = obj->mm.pages; - mock_vma_res->node_size = BIT_ULL(size); + mock_vma_res->node_size = BIT_ULL(aligned_size); mock_vma_res->start = addr; with_intel_runtime_pm(vm->gt->uncore->rpm, wakeref) @@ -356,7 +361,7 @@ alloc_vm_end: i915_random_reorder(order, count, &prng); for (n = 0; n < count; n++) { - u64 addr = hole_start + order[n] * BIT_ULL(size); + u64 addr = hole_start + order[n] * BIT_ULL(aligned_size); intel_wakeref_t wakeref; GEM_BUG_ON(addr + BIT_ULL(size) > vm->total); @@ -400,8 +405,10 @@ static int fill_hole(struct i915_address_space *vm, { const u64 hole_size = hole_end - hole_start; struct drm_i915_gem_object *obj; + const unsigned int min_alignment = + i915_vm_min_alignment(vm, INTEL_MEMORY_SYSTEM); const unsigned long max_pages = - min_t(u64, ULONG_MAX - 1, hole_size/2 >> PAGE_SHIFT); + min_t(u64, ULONG_MAX - 1, (hole_size / 2) >> ilog2(min_alignment)); const unsigned long max_step = max(int_sqrt(max_pages), 2UL); unsigned long npages, prime, flags; struct i915_vma *vma; @@ -442,14 +449,17 @@ static int fill_hole(struct i915_address_space *vm, offset = p->offset; list_for_each_entry(obj, &objects, st_link) { + u64 aligned_size = round_up(obj->base.size, + min_alignment); + vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) continue; if (p->step < 0) { - if (offset < hole_start + obj->base.size) + if (offset < hole_start + aligned_size) break; - offset -= obj->base.size; + offset -= aligned_size; } err = i915_vma_pin(vma, 0, 0, offset | flags); @@ -471,22 +481,25 @@ static int fill_hole(struct i915_address_space *vm, i915_vma_unpin(vma); if (p->step > 0) { - if (offset + obj->base.size > hole_end) + if (offset + aligned_size > hole_end) break; - offset += obj->base.size; + offset += aligned_size; } } offset = p->offset; list_for_each_entry(obj, &objects, st_link) { + u64 aligned_size = round_up(obj->base.size, + min_alignment); + vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) continue; if (p->step < 0) { - if (offset < hole_start + obj->base.size) + if (offset < hole_start + aligned_size) break; - offset -= obj->base.size; + offset -= aligned_size; } if (!drm_mm_node_allocated(&vma->node) || @@ -507,22 +520,25 @@ static int fill_hole(struct i915_address_space *vm, } if (p->step > 0) { - if (offset + obj->base.size > hole_end) + if (offset + aligned_size > hole_end) break; - offset += obj->base.size; + offset += aligned_size; } } offset = p->offset; list_for_each_entry_reverse(obj, &objects, st_link) { + u64 aligned_size = round_up(obj->base.size, + min_alignment); + vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) continue; if (p->step < 0) { - if (offset < hole_start + obj->base.size) + if (offset < hole_start + aligned_size) break; - offset -= obj->base.size; + offset -= aligned_size; } err = i915_vma_pin(vma, 0, 0, offset | flags); @@ -544,22 +560,25 @@ static int fill_hole(struct i915_address_space *vm, i915_vma_unpin(vma); if (p->step > 0) { - if (offset + obj->base.size > hole_end) + if (offset + aligned_size > hole_end) break; - offset += obj->base.size; + offset += aligned_size; } } offset = p->offset; list_for_each_entry_reverse(obj, &objects, st_link) { + u64 aligned_size = round_up(obj->base.size, + min_alignment); + vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) continue; if (p->step < 0) { - if (offset < hole_start + obj->base.size) + if (offset < hole_start + aligned_size) break; - offset -= obj->base.size; + offset -= aligned_size; } if (!drm_mm_node_allocated(&vma->node) || @@ -580,9 +599,9 @@ static int fill_hole(struct i915_address_space *vm, } if (p->step > 0) { - if (offset + obj->base.size > hole_end) + if (offset + aligned_size > hole_end) break; - offset += obj->base.size; + offset += aligned_size; } } } @@ -612,6 +631,7 @@ static int walk_hole(struct i915_address_space *vm, const u64 hole_size = hole_end - hole_start; const unsigned long max_pages = min_t(u64, ULONG_MAX - 1, hole_size >> PAGE_SHIFT); + unsigned long min_alignment; unsigned long flags; u64 size; @@ -621,6 +641,8 @@ static int walk_hole(struct i915_address_space *vm, if (i915_is_ggtt(vm)) flags |= PIN_GLOBAL; + min_alignment = i915_vm_min_alignment(vm, INTEL_MEMORY_SYSTEM); + for_each_prime_number_from(size, 1, max_pages) { struct drm_i915_gem_object *obj; struct i915_vma *vma; @@ -639,7 +661,7 @@ static int walk_hole(struct i915_address_space *vm, for (addr = hole_start; addr + obj->base.size < hole_end; - addr += obj->base.size) { + addr += round_up(obj->base.size, min_alignment)) { err = i915_vma_pin(vma, 0, 0, addr | flags); if (err) { pr_err("%s bind failed at %llx + %llx [hole %llx- %llx] with err=%d\n", @@ -691,6 +713,7 @@ static int pot_hole(struct i915_address_space *vm, { struct drm_i915_gem_object *obj; struct i915_vma *vma; + unsigned int min_alignment; unsigned long flags; unsigned int pot; int err = 0; @@ -699,6 +722,8 @@ static int pot_hole(struct i915_address_space *vm, if (i915_is_ggtt(vm)) flags |= PIN_GLOBAL; + min_alignment = i915_vm_min_alignment(vm, INTEL_MEMORY_SYSTEM); + obj = i915_gem_object_create_internal(vm->i915, 2 * I915_GTT_PAGE_SIZE); if (IS_ERR(obj)) return PTR_ERR(obj); @@ -711,13 +736,13 @@ static int pot_hole(struct i915_address_space *vm, /* Insert a pair of pages across every pot boundary within the hole */ for (pot = fls64(hole_end - 1) - 1; - pot > ilog2(2 * I915_GTT_PAGE_SIZE); + pot > ilog2(2 * min_alignment); pot--) { u64 step = BIT_ULL(pot); u64 addr; - for (addr = round_up(hole_start + I915_GTT_PAGE_SIZE, step) - I915_GTT_PAGE_SIZE; - addr <= round_down(hole_end - 2*I915_GTT_PAGE_SIZE, step) - I915_GTT_PAGE_SIZE; + for (addr = round_up(hole_start + min_alignment, step) - min_alignment; + addr <= round_down(hole_end - (2 * min_alignment), step) - min_alignment; addr += step) { err = i915_vma_pin(vma, 0, 0, addr | flags); if (err) { @@ -762,6 +787,7 @@ static int drunk_hole(struct i915_address_space *vm, unsigned long end_time) { I915_RND_STATE(prng); + unsigned int min_alignment; unsigned int size; unsigned long flags; @@ -769,15 +795,18 @@ static int drunk_hole(struct i915_address_space *vm, if (i915_is_ggtt(vm)) flags |= PIN_GLOBAL; + min_alignment = i915_vm_min_alignment(vm, INTEL_MEMORY_SYSTEM); + /* Keep creating larger objects until one cannot fit into the hole */ for (size = 12; (hole_end - hole_start) >> size; size++) { struct drm_i915_gem_object *obj; unsigned int *order, count, n; struct i915_vma *vma; - u64 hole_size; + u64 hole_size, aligned_size; int err = -ENODEV; - hole_size = (hole_end - hole_start) >> size; + aligned_size = max_t(u32, ilog2(min_alignment), size); + hole_size = (hole_end - hole_start) >> aligned_size; if (hole_size > KMALLOC_MAX_SIZE / sizeof(u32)) hole_size = KMALLOC_MAX_SIZE / sizeof(u32); count = hole_size >> 1; @@ -817,7 +846,7 @@ static int drunk_hole(struct i915_address_space *vm, GEM_BUG_ON(vma->size != BIT_ULL(size)); for (n = 0; n < count; n++) { - u64 addr = hole_start + order[n] * BIT_ULL(size); + u64 addr = hole_start + order[n] * BIT_ULL(aligned_size); err = i915_vma_pin(vma, 0, 0, addr | flags); if (err) { @@ -869,11 +898,14 @@ static int __shrink_hole(struct i915_address_space *vm, { struct drm_i915_gem_object *obj; unsigned long flags = PIN_OFFSET_FIXED | PIN_USER; + unsigned int min_alignment; unsigned int order = 12; LIST_HEAD(objects); int err = 0; u64 addr; + min_alignment = i915_vm_min_alignment(vm, INTEL_MEMORY_SYSTEM); + /* Keep creating larger objects until one cannot fit into the hole */ for (addr = hole_start; addr < hole_end; ) { struct i915_vma *vma; @@ -914,7 +946,7 @@ static int __shrink_hole(struct i915_address_space *vm, } i915_vma_unpin(vma); - addr += size; + addr += round_up(size, min_alignment); /* * Since we are injecting allocation faults at random intervals, @@ -1038,6 +1070,118 @@ err_purge: return err; } +static int misaligned_case(struct i915_address_space *vm, struct intel_memory_region *mr, + u64 addr, u64 size, unsigned long flags) +{ + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + int err = 0; + u64 expected_vma_size, expected_node_size; + bool is_stolen = mr->type == INTEL_MEMORY_STOLEN_SYSTEM || + mr->type == INTEL_MEMORY_STOLEN_LOCAL; + + obj = i915_gem_object_create_region(mr, size, 0, 0); + if (IS_ERR(obj)) { + /* if iGVT-g or DMAR is active, stolen mem will be uninitialized */ + if (PTR_ERR(obj) == -ENODEV && is_stolen) + return 0; + return PTR_ERR(obj); + } + + vma = i915_vma_instance(obj, vm, NULL); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + goto err_put; + } + + err = i915_vma_pin(vma, 0, 0, addr | flags); + if (err) + goto err_put; + i915_vma_unpin(vma); + + if (!drm_mm_node_allocated(&vma->node)) { + err = -EINVAL; + goto err_put; + } + + if (i915_vma_misplaced(vma, 0, 0, addr | flags)) { + err = -EINVAL; + goto err_put; + } + + expected_vma_size = round_up(size, 1 << (ffs(vma->resource->page_sizes_gtt) - 1)); + expected_node_size = expected_vma_size; + + if (NEEDS_COMPACT_PT(vm->i915) && i915_gem_object_is_lmem(obj)) { + /* compact-pt should expand lmem node to 2MB */ + expected_vma_size = round_up(size, I915_GTT_PAGE_SIZE_64K); + expected_node_size = round_up(size, I915_GTT_PAGE_SIZE_2M); + } + + if (vma->size != expected_vma_size || vma->node.size != expected_node_size) { + err = i915_vma_unbind_unlocked(vma); + err = -EBADSLT; + goto err_put; + } + + err = i915_vma_unbind_unlocked(vma); + if (err) + goto err_put; + + GEM_BUG_ON(drm_mm_node_allocated(&vma->node)); + +err_put: + i915_gem_object_put(obj); + cleanup_freed_objects(vm->i915); + return err; +} + +static int misaligned_pin(struct i915_address_space *vm, + u64 hole_start, u64 hole_end, + unsigned long end_time) +{ + struct intel_memory_region *mr; + enum intel_region_id id; + unsigned long flags = PIN_OFFSET_FIXED | PIN_USER; + int err = 0; + u64 hole_size = hole_end - hole_start; + + if (i915_is_ggtt(vm)) + flags |= PIN_GLOBAL; + + for_each_memory_region(mr, vm->i915, id) { + u64 min_alignment = i915_vm_min_alignment(vm, (enum intel_memory_type)id); + u64 size = min_alignment; + u64 addr = round_down(hole_start + (hole_size / 2), min_alignment); + + /* avoid -ENOSPC on very small hole setups */ + if (hole_size < 3 * min_alignment) + continue; + + /* we can't test < 4k alignment due to flags being encoded in lower bits */ + if (min_alignment != I915_GTT_PAGE_SIZE_4K) { + err = misaligned_case(vm, mr, addr + (min_alignment / 2), size, flags); + /* misaligned should error with -EINVAL*/ + if (!err) + err = -EBADSLT; + if (err != -EINVAL) + return err; + } + + /* test for vma->size expansion to min page size */ + err = misaligned_case(vm, mr, addr, PAGE_SIZE, flags); + if (err) + return err; + + /* test for intermediate size not expanding vma->size for large alignments */ + err = misaligned_case(vm, mr, addr, size / 2, flags); + if (err) + return err; + } + + return 0; +} + static int exercise_ppgtt(struct drm_i915_private *dev_priv, int (*func)(struct i915_address_space *vm, u64 hole_start, u64 hole_end, @@ -1107,6 +1251,11 @@ static int igt_ppgtt_shrink_boom(void *arg) return exercise_ppgtt(arg, shrink_boom); } +static int igt_ppgtt_misaligned_pin(void *arg) +{ + return exercise_ppgtt(arg, misaligned_pin); +} + static int sort_holes(void *priv, const struct list_head *A, const struct list_head *B) { @@ -1179,6 +1328,11 @@ static int igt_ggtt_lowlevel(void *arg) return exercise_ggtt(arg, lowlevel_hole); } +static int igt_ggtt_misaligned_pin(void *arg) +{ + return exercise_ggtt(arg, misaligned_pin); +} + static int igt_ggtt_page(void *arg) { const unsigned int count = PAGE_SIZE/sizeof(u32); @@ -2151,12 +2305,14 @@ int i915_gem_gtt_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_ppgtt_fill), SUBTEST(igt_ppgtt_shrink), SUBTEST(igt_ppgtt_shrink_boom), + SUBTEST(igt_ppgtt_misaligned_pin), SUBTEST(igt_ggtt_lowlevel), SUBTEST(igt_ggtt_drunk), SUBTEST(igt_ggtt_walk), SUBTEST(igt_ggtt_pot), SUBTEST(igt_ggtt_fill), SUBTEST(igt_ggtt_page), + SUBTEST(igt_ggtt_misaligned_pin), SUBTEST(igt_cs_tlb), }; diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c index 7acba1d2135e..ba32893e0873 100644 --- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c +++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c @@ -17,6 +17,7 @@ #include "gem/i915_gem_context.h" #include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" +#include "gem/i915_gem_ttm.h" #include "gem/selftests/igt_gem_utils.h" #include "gem/selftests/mock_context.h" #include "gt/intel_engine_pm.h" @@ -170,7 +171,7 @@ static int igt_mock_reserve(void *arg) if (!order) return 0; - mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0); + mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0, 0); if (IS_ERR(mem)) { pr_err("failed to create memory region\n"); err = PTR_ERR(mem); @@ -383,7 +384,7 @@ static int igt_mock_splintered_region(void *arg) */ size = (SZ_4G - 1) & PAGE_MASK; - mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0); + mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0, 0); if (IS_ERR(mem)) return PTR_ERR(mem); @@ -471,7 +472,7 @@ static int igt_mock_max_segment(void *arg) */ size = SZ_8G; - mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0); + mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0, 0); if (IS_ERR(mem)) return PTR_ERR(mem); @@ -512,6 +513,147 @@ out_put: return err; } +static u64 igt_object_mappable_total(struct drm_i915_gem_object *obj) +{ + struct intel_memory_region *mr = obj->mm.region; + struct i915_ttm_buddy_resource *bman_res = + to_ttm_buddy_resource(obj->mm.res); + struct drm_buddy *mm = bman_res->mm; + struct drm_buddy_block *block; + u64 total; + + total = 0; + list_for_each_entry(block, &bman_res->blocks, link) { + u64 start = drm_buddy_block_offset(block); + u64 end = start + drm_buddy_block_size(mm, block); + + if (start < mr->io_size) + total += min_t(u64, end, mr->io_size) - start; + } + + return total; +} + +static int igt_mock_io_size(void *arg) +{ + struct intel_memory_region *mr = arg; + struct drm_i915_private *i915 = mr->i915; + struct drm_i915_gem_object *obj; + u64 mappable_theft_total; + u64 io_size; + u64 total; + u64 ps; + u64 rem; + u64 size; + I915_RND_STATE(prng); + LIST_HEAD(objects); + int err = 0; + + ps = SZ_4K; + if (i915_prandom_u64_state(&prng) & 1) + ps = SZ_64K; /* For something like DG2 */ + + div64_u64_rem(i915_prandom_u64_state(&prng), SZ_8G, &total); + total = round_down(total, ps); + total = max_t(u64, total, SZ_1G); + + div64_u64_rem(i915_prandom_u64_state(&prng), total - ps, &io_size); + io_size = round_down(io_size, ps); + io_size = max_t(u64, io_size, SZ_256M); /* 256M seems to be the common lower limit */ + + pr_info("%s with ps=%llx, io_size=%llx, total=%llx\n", + __func__, ps, io_size, total); + + mr = mock_region_create(i915, 0, total, ps, 0, io_size); + if (IS_ERR(mr)) { + err = PTR_ERR(mr); + goto out_err; + } + + mappable_theft_total = 0; + rem = total - io_size; + do { + div64_u64_rem(i915_prandom_u64_state(&prng), rem, &size); + size = round_down(size, ps); + size = max(size, ps); + + obj = igt_object_create(mr, &objects, size, + I915_BO_ALLOC_GPU_ONLY); + if (IS_ERR(obj)) { + pr_err("%s TOPDOWN failed with rem=%llx, size=%llx\n", + __func__, rem, size); + err = PTR_ERR(obj); + goto out_close; + } + + mappable_theft_total += igt_object_mappable_total(obj); + rem -= size; + } while (rem); + + pr_info("%s mappable theft=(%lluMiB/%lluMiB), total=%lluMiB\n", + __func__, + (u64)mappable_theft_total >> 20, + (u64)io_size >> 20, + (u64)total >> 20); + + /* + * Even if we allocate all of the non-mappable portion, we should still + * be able to dip into the mappable portion. + */ + obj = igt_object_create(mr, &objects, io_size, + I915_BO_ALLOC_GPU_ONLY); + if (IS_ERR(obj)) { + pr_err("%s allocation unexpectedly failed\n", __func__); + err = PTR_ERR(obj); + goto out_close; + } + + close_objects(mr, &objects); + + rem = io_size; + do { + div64_u64_rem(i915_prandom_u64_state(&prng), rem, &size); + size = round_down(size, ps); + size = max(size, ps); + + obj = igt_object_create(mr, &objects, size, 0); + if (IS_ERR(obj)) { + pr_err("%s MAPPABLE failed with rem=%llx, size=%llx\n", + __func__, rem, size); + err = PTR_ERR(obj); + goto out_close; + } + + if (igt_object_mappable_total(obj) != size) { + pr_err("%s allocation is not mappable(size=%llx)\n", + __func__, size); + err = -EINVAL; + goto out_close; + } + rem -= size; + } while (rem); + + /* + * We assume CPU access is required by default, which should result in a + * failure here, even though the non-mappable portion is free. + */ + obj = igt_object_create(mr, &objects, ps, 0); + if (!IS_ERR(obj)) { + pr_err("%s allocation unexpectedly succeeded\n", __func__); + err = -EINVAL; + goto out_close; + } + +out_close: + close_objects(mr, &objects); + intel_memory_region_destroy(mr); +out_err: + if (err == -ENOMEM) + err = 0; + + return err; +} + static int igt_gpu_write_dw(struct intel_context *ce, struct i915_vma *vma, u32 dword, @@ -680,8 +822,14 @@ static int igt_lmem_create_with_ps(void *arg) i915_gem_object_lock(obj, NULL); err = i915_gem_object_pin_pages(obj); - if (err) + if (err) { + if (err == -ENXIO || err == -E2BIG || err == -ENOMEM) { + pr_info("%s not enough lmem for ps(%u) err=%d\n", + __func__, ps, err); + err = 0; + } goto out_put; + } daddr = i915_gem_object_get_dma_address(obj, 0); if (!IS_ALIGNED(daddr, ps)) { @@ -1179,6 +1327,7 @@ int intel_memory_region_mock_selftests(void) SUBTEST(igt_mock_contiguous), SUBTEST(igt_mock_splintered_region), SUBTEST(igt_mock_max_segment), + SUBTEST(igt_mock_io_size), }; struct intel_memory_region *mem; struct drm_i915_private *i915; @@ -1188,7 +1337,7 @@ int intel_memory_region_mock_selftests(void) if (!i915) return -ENOMEM; - mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0); + mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0, 0); if (IS_ERR(mem)) { pr_err("failed to create memory region\n"); err = PTR_ERR(mem); diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c index 19bff8afcaaa..f64325491f35 100644 --- a/drivers/gpu/drm/i915/selftests/mock_region.c +++ b/drivers/gpu/drm/i915/selftests/mock_region.c @@ -22,17 +22,12 @@ static void mock_region_put_pages(struct drm_i915_gem_object *obj, static int mock_region_get_pages(struct drm_i915_gem_object *obj) { - unsigned int flags; struct sg_table *pages; int err; - flags = 0; - if (obj->flags & I915_BO_ALLOC_CONTIGUOUS) - flags |= TTM_PL_FLAG_CONTIGUOUS; - obj->mm.res = intel_region_ttm_resource_alloc(obj->mm.region, obj->base.size, - flags); + obj->flags); if (IS_ERR(obj->mm.res)) return PTR_ERR(obj->mm.res); @@ -107,7 +102,8 @@ mock_region_create(struct drm_i915_private *i915, resource_size_t start, resource_size_t size, resource_size_t min_page_size, - resource_size_t io_start) + resource_size_t io_start, + resource_size_t io_size) { int instance = ida_alloc_max(&i915->selftest.mock_region_instances, TTM_NUM_MEM_TYPES - TTM_PL_PRIV - 1, @@ -117,6 +113,7 @@ mock_region_create(struct drm_i915_private *i915, return ERR_PTR(instance); return intel_memory_region_create(i915, start, size, min_page_size, - io_start, INTEL_MEMORY_MOCK, instance, + io_start, io_size, + INTEL_MEMORY_MOCK, instance, &mock_region_ops); } diff --git a/drivers/gpu/drm/i915/selftests/mock_region.h b/drivers/gpu/drm/i915/selftests/mock_region.h index 329bf74dfaca..e36c3a433551 100644 --- a/drivers/gpu/drm/i915/selftests/mock_region.h +++ b/drivers/gpu/drm/i915/selftests/mock_region.h @@ -16,6 +16,7 @@ mock_region_create(struct drm_i915_private *i915, resource_size_t start, resource_size_t size, resource_size_t min_page_size, - resource_size_t io_start); + resource_size_t io_start, + resource_size_t io_size); #endif /* !__MOCK_REGION_H */ diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index a8aba0141ce7..06cb1a59b9bc 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -217,14 +217,6 @@ static int imx_pd_bridge_atomic_check(struct drm_bridge *bridge, if (!imx_pd_format_supported(bus_fmt)) return -EINVAL; - if (bus_flags & - ~(DRM_BUS_FLAG_DE_LOW | DRM_BUS_FLAG_DE_HIGH | - DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE | - DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE)) { - dev_warn(imxpd->dev, "invalid bus_flags (%x)\n", bus_flags); - return -EINVAL; - } - bridge_state->output_bus_cfg.flags = bus_flags; bridge_state->input_bus_cfg.flags = bus_flags; imx_crtc_state->bus_flags = bus_flags; diff --git a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c index dcf44cb00821..ac52b49bf901 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c @@ -1371,11 +1371,6 @@ static int ingenic_drm_bind_with_components(struct device *dev) return ingenic_drm_bind(dev, true); } -static int compare_of(struct device *dev, void *data) -{ - return dev->of_node == data; -} - static void ingenic_drm_unbind(struct device *dev) { struct ingenic_drm *priv = dev_get_drvdata(dev); @@ -1409,7 +1404,7 @@ static int ingenic_drm_probe(struct platform_device *pdev) if (!np) return ingenic_drm_bind(dev, false); - drm_of_component_match_add(dev, &match, compare_of, np); + drm_of_component_match_add(dev, &match, component_compare_of, np); of_node_put(np); return component_master_add_with_match(dev, &ingenic_master_ops, match); diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c index 0b2910e69b42..e601baa87e55 100644 --- a/drivers/gpu/drm/mcde/mcde_drv.c +++ b/drivers/gpu/drm/mcde/mcde_drv.c @@ -265,11 +265,6 @@ static struct platform_driver *const mcde_component_drivers[] = { &mcde_dsi_driver, }; -static int mcde_compare_dev(struct device *dev, void *data) -{ - return dev == data; -} - static int mcde_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -399,7 +394,7 @@ static int mcde_probe(struct platform_device *pdev) while ((d = platform_find_device_by_driver(p, drv))) { put_device(p); - component_match_add(dev, &match, mcde_compare_dev, d); + component_match_add(dev, &match, component_compare_dev, d); p = d; } put_device(p); diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index 2146299e5f52..17cd9b932298 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -11,6 +11,7 @@ #include <linux/of_device.h> #include <linux/of_irq.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/soc/mediatek/mtk-cmdq.h> #include "mtk_disp_drv.h" @@ -414,9 +415,13 @@ static int mtk_disp_ovl_probe(struct platform_device *pdev) return ret; } + pm_runtime_enable(dev); + ret = component_add(dev, &mtk_disp_ovl_component_ops); - if (ret) + if (ret) { + pm_runtime_disable(dev); dev_err(dev, "Failed to add component: %d\n", ret); + } return ret; } @@ -424,6 +429,7 @@ static int mtk_disp_ovl_probe(struct platform_device *pdev) static int mtk_disp_ovl_remove(struct platform_device *pdev) { component_del(&pdev->dev, &mtk_disp_ovl_component_ops); + pm_runtime_disable(&pdev->dev); return 0; } diff --git a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c index d41a3970b944..662e91d9d45f 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c @@ -9,6 +9,7 @@ #include <linux/of_device.h> #include <linux/of_irq.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/soc/mediatek/mtk-cmdq.h> #include "mtk_disp_drv.h" @@ -327,9 +328,13 @@ static int mtk_disp_rdma_probe(struct platform_device *pdev) platform_set_drvdata(pdev, priv); + pm_runtime_enable(dev); + ret = component_add(dev, &mtk_disp_rdma_component_ops); - if (ret) + if (ret) { + pm_runtime_disable(dev); dev_err(dev, "Failed to add component: %d\n", ret); + } return ret; } @@ -338,6 +343,8 @@ static int mtk_disp_rdma_remove(struct platform_device *pdev) { component_del(&pdev->dev, &mtk_disp_rdma_component_ops); + pm_runtime_disable(&pdev->dev); + return 0; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 8cc0a1283d7c..ede435d2c1ef 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -12,7 +12,6 @@ #include <linux/soc/mediatek/mtk-mutex.h> #include <asm/barrier.h> -#include <soc/mediatek/smi.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> @@ -663,15 +662,15 @@ static void mtk_drm_crtc_atomic_enable(struct drm_crtc *crtc, DRM_DEBUG_DRIVER("%s %d\n", __func__, crtc->base.id); - ret = mtk_smi_larb_get(comp->larb_dev); - if (ret) { - DRM_ERROR("Failed to get larb: %d\n", ret); + ret = pm_runtime_resume_and_get(comp->dev); + if (ret < 0) { + DRM_DEV_ERROR(comp->dev, "Failed to enable power domain: %d\n", ret); return; } ret = mtk_crtc_ddp_hw_init(mtk_crtc); if (ret) { - mtk_smi_larb_put(comp->larb_dev); + pm_runtime_put(comp->dev); return; } @@ -684,7 +683,7 @@ static void mtk_drm_crtc_atomic_disable(struct drm_crtc *crtc, { struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[0]; - int i; + int i, ret; DRM_DEBUG_DRIVER("%s %d\n", __func__, crtc->base.id); if (!mtk_crtc->enabled) @@ -714,7 +713,9 @@ static void mtk_drm_crtc_atomic_disable(struct drm_crtc *crtc, drm_crtc_vblank_off(crtc); mtk_crtc_ddp_hw_fini(mtk_crtc); - mtk_smi_larb_put(comp->larb_dev); + ret = pm_runtime_put(comp->dev); + if (ret < 0) + DRM_DEV_ERROR(comp->dev, "Failed to disable power domain: %d\n", ret); mtk_crtc->enabled = false; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c index b4b682bc1991..2e99aee13dfe 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c @@ -447,37 +447,15 @@ unsigned int mtk_drm_find_possible_crtc_by_comp(struct drm_device *drm, return ret; } -static int mtk_ddp_get_larb_dev(struct device_node *node, struct mtk_ddp_comp *comp, - struct device *dev) -{ - struct device_node *larb_node; - struct platform_device *larb_pdev; - - larb_node = of_parse_phandle(node, "mediatek,larb", 0); - if (!larb_node) { - dev_err(dev, "Missing mediadek,larb phandle in %pOF node\n", node); - return -EINVAL; - } - - larb_pdev = of_find_device_by_node(larb_node); - if (!larb_pdev) { - dev_warn(dev, "Waiting for larb device %pOF\n", larb_node); - of_node_put(larb_node); - return -EPROBE_DEFER; - } - of_node_put(larb_node); - comp->larb_dev = &larb_pdev->dev; - - return 0; -} - int mtk_ddp_comp_init(struct device_node *node, struct mtk_ddp_comp *comp, enum mtk_ddp_comp_id comp_id) { struct platform_device *comp_pdev; enum mtk_ddp_comp_type type; struct mtk_ddp_comp_dev *priv; +#if IS_REACHABLE(CONFIG_MTK_CMDQ) int ret; +#endif if (comp_id < 0 || comp_id >= DDP_COMPONENT_ID_MAX) return -EINVAL; @@ -493,16 +471,6 @@ int mtk_ddp_comp_init(struct device_node *node, struct mtk_ddp_comp *comp, } comp->dev = &comp_pdev->dev; - /* Only DMA capable components need the LARB property */ - if (type == MTK_DISP_OVL || - type == MTK_DISP_OVL_2L || - type == MTK_DISP_RDMA || - type == MTK_DISP_WDMA) { - ret = mtk_ddp_get_larb_dev(node, comp, comp->dev); - if (ret) - return ret; - } - if (type == MTK_DISP_AAL || type == MTK_DISP_BLS || type == MTK_DISP_CCORR || diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h index 4c6a98662305..ad267bb8fc9b 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h @@ -71,7 +71,6 @@ struct mtk_ddp_comp_funcs { struct mtk_ddp_comp { struct device *dev; int irq; - struct device *larb_dev; enum mtk_ddp_comp_id id; const struct mtk_ddp_comp_funcs *funcs; }; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index dd029307be7d..247c6ff277ef 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -372,11 +372,6 @@ static const struct drm_driver mtk_drm_driver = { .minor = DRIVER_MINOR, }; -static int compare_of(struct device *dev, void *data) -{ - return dev->of_node == data; -} - static int mtk_drm_bind(struct device *dev) { struct mtk_drm_private *private = dev_get_drvdata(dev); @@ -617,7 +612,7 @@ static int mtk_drm_probe(struct platform_device *pdev) comp_type == MTK_DSI) { dev_info(dev, "Adding component match for %pOF\n", node); - drm_of_component_match_add(dev, &match, compare_of, + drm_of_component_match_add(dev, &match, component_compare_of, node); } @@ -648,11 +643,8 @@ err_pm: pm_runtime_disable(dev); err_node: of_node_put(private->mutex_node); - for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) { + for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) of_node_put(private->comp_node[i]); - if (private->ddp_comp[i].larb_dev) - put_device(private->ddp_comp[i].larb_dev); - } return ret; } diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 93a7a033a3e8..edae79f41153 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -425,14 +425,6 @@ static int __maybe_unused meson_drv_pm_resume(struct device *dev) return drm_mode_config_helper_resume(priv->drm); } -static int compare_of(struct device *dev, void *data) -{ - DRM_DEBUG_DRIVER("Comparing of node %pOF with %pOF\n", - dev->of_node, data); - - return dev->of_node == data; -} - static void meson_drv_shutdown(struct platform_device *pdev) { struct meson_drm *priv = dev_get_drvdata(&pdev->dev); @@ -475,7 +467,7 @@ static int meson_drv_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "parent %pOF remote match add %pOF parent %s\n", np, remote, dev_name(&pdev->dev)); - component_match_add(&pdev->dev, &match, compare_of, remote); + component_match_add(&pdev->dev, &match, component_compare_of, remote); of_node_put(remote); diff --git a/drivers/gpu/drm/mgag200/mgag200_pll.c b/drivers/gpu/drm/mgag200/mgag200_pll.c index e9ae22b4f813..52be08b744ad 100644 --- a/drivers/gpu/drm/mgag200/mgag200_pll.c +++ b/drivers/gpu/drm/mgag200/mgag200_pll.c @@ -404,9 +404,9 @@ mgag200_pixpll_update_g200wb(struct mgag200_pll *pixpll, const struct mgag200_pl udelay(50); /* program pixel pll register */ - WREG_DAC(MGA1064_PIX_PLLC_N, xpixpllcn); - WREG_DAC(MGA1064_PIX_PLLC_M, xpixpllcm); - WREG_DAC(MGA1064_PIX_PLLC_P, xpixpllcp); + WREG_DAC(MGA1064_WB_PIX_PLLC_N, xpixpllcn); + WREG_DAC(MGA1064_WB_PIX_PLLC_M, xpixpllcm); + WREG_DAC(MGA1064_WB_PIX_PLLC_P, xpixpllcp); udelay(50); diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index 4fd931413705..c79502525963 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -34,15 +34,6 @@ config DRM_MSM_GPU_STATE depends on DRM_MSM && (DEBUG_FS || DEV_COREDUMP) default y -config DRM_MSM_REGISTER_LOGGING - bool "MSM DRM register logging" - depends on DRM_MSM - default n - help - Compile in support for logging register reads/writes in a format - that can be parsed by envytools demsm tool. If enabled, register - logging can be switched on via msm.reglog=y module param. - config DRM_MSM_GPU_SUDO bool "Enable SUDO flag on submits" depends on DRM_MSM && EXPERT diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 03ab55c37beb..e9cc7d8ac301 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -66,7 +66,6 @@ msm-y := \ disp/dpu1/dpu_hw_top.o \ disp/dpu1/dpu_hw_util.o \ disp/dpu1/dpu_hw_vbif.o \ - disp/dpu1/dpu_io_util.o \ disp/dpu1/dpu_kms.o \ disp/dpu1/dpu_mdss.o \ disp/dpu1/dpu_plane.o \ @@ -87,6 +86,7 @@ msm-y := \ msm_gem_vma.o \ msm_gpu.o \ msm_gpu_devfreq.o \ + msm_io_utils.o \ msm_iommu.o \ msm_perf.o \ msm_rd.o \ @@ -102,6 +102,7 @@ msm-$(CONFIG_DRM_MSM_GPU_STATE) += adreno/a6xx_gpu_state.o msm-$(CONFIG_DRM_MSM_DP)+= dp/dp_aux.o \ dp/dp_catalog.o \ + dp/dp_clk_util.o \ dp/dp_ctrl.o \ dp/dp_display.o \ dp/dp_drm.o \ diff --git a/drivers/gpu/drm/msm/adreno/a2xx.xml.h b/drivers/gpu/drm/msm/adreno/a2xx.xml.h index 4ff529576093..afa6023346c4 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a2xx.xml.h @@ -8,19 +8,19 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14386 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 67699 bytes, from 2021-05-31 20:21:57) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84226 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a4xx.xml ( 112551 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a5xx.xml ( 150713 bytes, from 2021-06-10 22:34:02) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx.xml ( 180049 bytes, from 2021-06-02 21:44:19) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-05-27 20:22:36) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-05-27 20:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-06-21 15:24:24) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14609 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 69086 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84231 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a4xx.xml ( 113358 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a5xx.xml ( 149512 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx.xml ( 184954 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-07-22 15:21:56) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c index 22e8295a5e2b..6c9a747eb4ad 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c @@ -471,6 +471,7 @@ static u32 a2xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) static const struct adreno_gpu_funcs funcs = { .base = { .get_param = adreno_get_param, + .set_param = adreno_set_param, .hw_init = a2xx_hw_init, .pm_suspend = msm_gpu_pm_suspend, .pm_resume = msm_gpu_pm_resume, diff --git a/drivers/gpu/drm/msm/adreno/a3xx.xml.h b/drivers/gpu/drm/msm/adreno/a3xx.xml.h index e106b65abe26..520ae3f375a1 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a3xx.xml.h @@ -8,19 +8,19 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14386 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 67699 bytes, from 2021-05-31 20:21:57) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84226 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a4xx.xml ( 112551 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a5xx.xml ( 150713 bytes, from 2021-06-10 22:34:02) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx.xml ( 180049 bytes, from 2021-06-02 21:44:19) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-05-27 20:22:36) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-05-27 20:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-06-21 15:24:24) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14609 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 69086 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84231 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a4xx.xml ( 113358 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a5xx.xml ( 149512 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx.xml ( 184954 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-07-22 15:21:56) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) @@ -1466,7 +1466,7 @@ static inline uint32_t A3XX_RB_COPY_DEST_INFO_ENDIAN(enum adreno_rb_surface_endi #define REG_A3XX_RB_DEPTH_CONTROL 0x00002100 #define A3XX_RB_DEPTH_CONTROL_FRAG_WRITES_Z 0x00000001 -#define A3XX_RB_DEPTH_CONTROL_Z_ENABLE 0x00000002 +#define A3XX_RB_DEPTH_CONTROL_Z_TEST_ENABLE 0x00000002 #define A3XX_RB_DEPTH_CONTROL_Z_WRITE_ENABLE 0x00000004 #define A3XX_RB_DEPTH_CONTROL_EARLY_Z_DISABLE 0x00000008 #define A3XX_RB_DEPTH_CONTROL_ZFUNC__MASK 0x00000070 @@ -1476,7 +1476,7 @@ static inline uint32_t A3XX_RB_DEPTH_CONTROL_ZFUNC(enum adreno_compare_func val) return ((val) << A3XX_RB_DEPTH_CONTROL_ZFUNC__SHIFT) & A3XX_RB_DEPTH_CONTROL_ZFUNC__MASK; } #define A3XX_RB_DEPTH_CONTROL_Z_CLAMP_ENABLE 0x00000080 -#define A3XX_RB_DEPTH_CONTROL_Z_TEST_ENABLE 0x80000000 +#define A3XX_RB_DEPTH_CONTROL_Z_READ_ENABLE 0x80000000 #define REG_A3XX_RB_DEPTH_CLEAR 0x00002101 diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index 2e481e2692ba..0ab0e1dd8bbb 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -486,6 +486,7 @@ static u32 a3xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) static const struct adreno_gpu_funcs funcs = { .base = { .get_param = adreno_get_param, + .set_param = adreno_set_param, .hw_init = a3xx_hw_init, .pm_suspend = msm_gpu_pm_suspend, .pm_resume = msm_gpu_pm_resume, diff --git a/drivers/gpu/drm/msm/adreno/a4xx.xml.h b/drivers/gpu/drm/msm/adreno/a4xx.xml.h index b26ede96ae2a..7e5c21015d10 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a4xx.xml.h @@ -8,21 +8,21 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14386 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 67699 bytes, from 2021-05-31 20:21:57) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84226 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a4xx.xml ( 112551 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a5xx.xml ( 150713 bytes, from 2021-06-10 22:34:02) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx.xml ( 180049 bytes, from 2021-06-02 21:44:19) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-05-27 20:22:36) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-05-27 20:18:13) - -Copyright (C) 2013-2021 by the following authors: +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-06-21 15:24:24) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14609 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 69086 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84231 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a4xx.xml ( 113358 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a5xx.xml ( 149512 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx.xml ( 184954 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-07-22 15:21:56) + +Copyright (C) 2013-2022 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin) @@ -837,6 +837,7 @@ enum a4xx_tex_type { A4XX_TEX_2D = 1, A4XX_TEX_CUBE = 2, A4XX_TEX_3D = 3, + A4XX_TEX_BUFFER = 4, }; #define A4XX_CGC_HLSQ_EARLY_CYC__MASK 0x00700000 @@ -1360,7 +1361,7 @@ static inline uint32_t A4XX_RB_FS_OUTPUT_REG_MRT(uint32_t val) #define REG_A4XX_RB_DEPTH_CONTROL 0x00002101 #define A4XX_RB_DEPTH_CONTROL_FRAG_WRITES_Z 0x00000001 -#define A4XX_RB_DEPTH_CONTROL_Z_ENABLE 0x00000002 +#define A4XX_RB_DEPTH_CONTROL_Z_TEST_ENABLE 0x00000002 #define A4XX_RB_DEPTH_CONTROL_Z_WRITE_ENABLE 0x00000004 #define A4XX_RB_DEPTH_CONTROL_ZFUNC__MASK 0x00000070 #define A4XX_RB_DEPTH_CONTROL_ZFUNC__SHIFT 4 @@ -1371,7 +1372,7 @@ static inline uint32_t A4XX_RB_DEPTH_CONTROL_ZFUNC(enum adreno_compare_func val) #define A4XX_RB_DEPTH_CONTROL_Z_CLAMP_ENABLE 0x00000080 #define A4XX_RB_DEPTH_CONTROL_EARLY_Z_DISABLE 0x00010000 #define A4XX_RB_DEPTH_CONTROL_FORCE_FRAGZ_TO_FS 0x00020000 -#define A4XX_RB_DEPTH_CONTROL_Z_TEST_ENABLE 0x80000000 +#define A4XX_RB_DEPTH_CONTROL_Z_READ_ENABLE 0x80000000 #define REG_A4XX_RB_DEPTH_CLEAR 0x00002102 @@ -2541,6 +2542,8 @@ static inline uint32_t A4XX_SP_FS_MRT_REG_REGID(uint32_t val) return ((val) << A4XX_SP_FS_MRT_REG_REGID__SHIFT) & A4XX_SP_FS_MRT_REG_REGID__MASK; } #define A4XX_SP_FS_MRT_REG_HALF_PRECISION 0x00000100 +#define A4XX_SP_FS_MRT_REG_COLOR_SINT 0x00000400 +#define A4XX_SP_FS_MRT_REG_COLOR_UINT 0x00000800 #define A4XX_SP_FS_MRT_REG_MRTFORMAT__MASK 0x0003f000 #define A4XX_SP_FS_MRT_REG_MRTFORMAT__SHIFT 12 static inline uint32_t A4XX_SP_FS_MRT_REG_MRTFORMAT(enum a4xx_color_fmt val) @@ -2550,6 +2553,40 @@ static inline uint32_t A4XX_SP_FS_MRT_REG_MRTFORMAT(enum a4xx_color_fmt val) #define A4XX_SP_FS_MRT_REG_COLOR_SRGB 0x00040000 #define REG_A4XX_SP_CS_CTRL_REG0 0x00002300 +#define A4XX_SP_CS_CTRL_REG0_THREADMODE__MASK 0x00000001 +#define A4XX_SP_CS_CTRL_REG0_THREADMODE__SHIFT 0 +static inline uint32_t A4XX_SP_CS_CTRL_REG0_THREADMODE(enum a3xx_threadmode val) +{ + return ((val) << A4XX_SP_CS_CTRL_REG0_THREADMODE__SHIFT) & A4XX_SP_CS_CTRL_REG0_THREADMODE__MASK; +} +#define A4XX_SP_CS_CTRL_REG0_VARYING 0x00000002 +#define A4XX_SP_CS_CTRL_REG0_CACHEINVALID 0x00000004 +#define A4XX_SP_CS_CTRL_REG0_HALFREGFOOTPRINT__MASK 0x000003f0 +#define A4XX_SP_CS_CTRL_REG0_HALFREGFOOTPRINT__SHIFT 4 +static inline uint32_t A4XX_SP_CS_CTRL_REG0_HALFREGFOOTPRINT(uint32_t val) +{ + return ((val) << A4XX_SP_CS_CTRL_REG0_HALFREGFOOTPRINT__SHIFT) & A4XX_SP_CS_CTRL_REG0_HALFREGFOOTPRINT__MASK; +} +#define A4XX_SP_CS_CTRL_REG0_FULLREGFOOTPRINT__MASK 0x0000fc00 +#define A4XX_SP_CS_CTRL_REG0_FULLREGFOOTPRINT__SHIFT 10 +static inline uint32_t A4XX_SP_CS_CTRL_REG0_FULLREGFOOTPRINT(uint32_t val) +{ + return ((val) << A4XX_SP_CS_CTRL_REG0_FULLREGFOOTPRINT__SHIFT) & A4XX_SP_CS_CTRL_REG0_FULLREGFOOTPRINT__MASK; +} +#define A4XX_SP_CS_CTRL_REG0_INOUTREGOVERLAP__MASK 0x000c0000 +#define A4XX_SP_CS_CTRL_REG0_INOUTREGOVERLAP__SHIFT 18 +static inline uint32_t A4XX_SP_CS_CTRL_REG0_INOUTREGOVERLAP(uint32_t val) +{ + return ((val) << A4XX_SP_CS_CTRL_REG0_INOUTREGOVERLAP__SHIFT) & A4XX_SP_CS_CTRL_REG0_INOUTREGOVERLAP__MASK; +} +#define A4XX_SP_CS_CTRL_REG0_THREADSIZE__MASK 0x00100000 +#define A4XX_SP_CS_CTRL_REG0_THREADSIZE__SHIFT 20 +static inline uint32_t A4XX_SP_CS_CTRL_REG0_THREADSIZE(enum a3xx_threadsize val) +{ + return ((val) << A4XX_SP_CS_CTRL_REG0_THREADSIZE__SHIFT) & A4XX_SP_CS_CTRL_REG0_THREADSIZE__MASK; +} +#define A4XX_SP_CS_CTRL_REG0_SUPERTHREADMODE 0x00200000 +#define A4XX_SP_CS_CTRL_REG0_PIXLODENABLE 0x00400000 #define REG_A4XX_SP_CS_OBJ_OFFSET_REG 0x00002301 @@ -3795,12 +3832,18 @@ static inline uint32_t A4XX_HLSQ_CL_NDRANGE_5_SIZE_Z(uint32_t val) #define REG_A4XX_HLSQ_CL_NDRANGE_6 0x000023d3 #define REG_A4XX_HLSQ_CL_CONTROL_0 0x000023d4 -#define A4XX_HLSQ_CL_CONTROL_0_WGIDCONSTID__MASK 0x000000ff +#define A4XX_HLSQ_CL_CONTROL_0_WGIDCONSTID__MASK 0x00000fff #define A4XX_HLSQ_CL_CONTROL_0_WGIDCONSTID__SHIFT 0 static inline uint32_t A4XX_HLSQ_CL_CONTROL_0_WGIDCONSTID(uint32_t val) { return ((val) << A4XX_HLSQ_CL_CONTROL_0_WGIDCONSTID__SHIFT) & A4XX_HLSQ_CL_CONTROL_0_WGIDCONSTID__MASK; } +#define A4XX_HLSQ_CL_CONTROL_0_KERNELDIMCONSTID__MASK 0x00fff000 +#define A4XX_HLSQ_CL_CONTROL_0_KERNELDIMCONSTID__SHIFT 12 +static inline uint32_t A4XX_HLSQ_CL_CONTROL_0_KERNELDIMCONSTID(uint32_t val) +{ + return ((val) << A4XX_HLSQ_CL_CONTROL_0_KERNELDIMCONSTID__SHIFT) & A4XX_HLSQ_CL_CONTROL_0_KERNELDIMCONSTID__MASK; +} #define A4XX_HLSQ_CL_CONTROL_0_LOCALIDREGID__MASK 0xff000000 #define A4XX_HLSQ_CL_CONTROL_0_LOCALIDREGID__SHIFT 24 static inline uint32_t A4XX_HLSQ_CL_CONTROL_0_LOCALIDREGID(uint32_t val) @@ -3809,8 +3852,32 @@ static inline uint32_t A4XX_HLSQ_CL_CONTROL_0_LOCALIDREGID(uint32_t val) } #define REG_A4XX_HLSQ_CL_CONTROL_1 0x000023d5 +#define A4XX_HLSQ_CL_CONTROL_1_UNK0CONSTID__MASK 0x00000fff +#define A4XX_HLSQ_CL_CONTROL_1_UNK0CONSTID__SHIFT 0 +static inline uint32_t A4XX_HLSQ_CL_CONTROL_1_UNK0CONSTID(uint32_t val) +{ + return ((val) << A4XX_HLSQ_CL_CONTROL_1_UNK0CONSTID__SHIFT) & A4XX_HLSQ_CL_CONTROL_1_UNK0CONSTID__MASK; +} +#define A4XX_HLSQ_CL_CONTROL_1_WORKGROUPSIZECONSTID__MASK 0x00fff000 +#define A4XX_HLSQ_CL_CONTROL_1_WORKGROUPSIZECONSTID__SHIFT 12 +static inline uint32_t A4XX_HLSQ_CL_CONTROL_1_WORKGROUPSIZECONSTID(uint32_t val) +{ + return ((val) << A4XX_HLSQ_CL_CONTROL_1_WORKGROUPSIZECONSTID__SHIFT) & A4XX_HLSQ_CL_CONTROL_1_WORKGROUPSIZECONSTID__MASK; +} #define REG_A4XX_HLSQ_CL_KERNEL_CONST 0x000023d6 +#define A4XX_HLSQ_CL_KERNEL_CONST_UNK0CONSTID__MASK 0x00000fff +#define A4XX_HLSQ_CL_KERNEL_CONST_UNK0CONSTID__SHIFT 0 +static inline uint32_t A4XX_HLSQ_CL_KERNEL_CONST_UNK0CONSTID(uint32_t val) +{ + return ((val) << A4XX_HLSQ_CL_KERNEL_CONST_UNK0CONSTID__SHIFT) & A4XX_HLSQ_CL_KERNEL_CONST_UNK0CONSTID__MASK; +} +#define A4XX_HLSQ_CL_KERNEL_CONST_NUMWGCONSTID__MASK 0x00fff000 +#define A4XX_HLSQ_CL_KERNEL_CONST_NUMWGCONSTID__SHIFT 12 +static inline uint32_t A4XX_HLSQ_CL_KERNEL_CONST_NUMWGCONSTID(uint32_t val) +{ + return ((val) << A4XX_HLSQ_CL_KERNEL_CONST_NUMWGCONSTID__SHIFT) & A4XX_HLSQ_CL_KERNEL_CONST_NUMWGCONSTID__MASK; +} #define REG_A4XX_HLSQ_CL_KERNEL_GROUP_X 0x000023d7 @@ -3819,6 +3886,12 @@ static inline uint32_t A4XX_HLSQ_CL_CONTROL_0_LOCALIDREGID(uint32_t val) #define REG_A4XX_HLSQ_CL_KERNEL_GROUP_Z 0x000023d9 #define REG_A4XX_HLSQ_CL_WG_OFFSET 0x000023da +#define A4XX_HLSQ_CL_WG_OFFSET_UNK0CONSTID__MASK 0x00000fff +#define A4XX_HLSQ_CL_WG_OFFSET_UNK0CONSTID__SHIFT 0 +static inline uint32_t A4XX_HLSQ_CL_WG_OFFSET_UNK0CONSTID(uint32_t val) +{ + return ((val) << A4XX_HLSQ_CL_WG_OFFSET_UNK0CONSTID__SHIFT) & A4XX_HLSQ_CL_WG_OFFSET_UNK0CONSTID__MASK; +} #define REG_A4XX_HLSQ_UPDATE_CONTROL 0x000023db @@ -4130,7 +4203,7 @@ static inline uint32_t A4XX_TEX_CONST_0_FMT(enum a4xx_tex_fmt val) { return ((val) << A4XX_TEX_CONST_0_FMT__SHIFT) & A4XX_TEX_CONST_0_FMT__MASK; } -#define A4XX_TEX_CONST_0_TYPE__MASK 0x60000000 +#define A4XX_TEX_CONST_0_TYPE__MASK 0xe0000000 #define A4XX_TEX_CONST_0_TYPE__SHIFT 29 static inline uint32_t A4XX_TEX_CONST_0_TYPE(enum a4xx_tex_type val) { @@ -4158,6 +4231,7 @@ static inline uint32_t A4XX_TEX_CONST_2_PITCHALIGN(uint32_t val) { return ((val) << A4XX_TEX_CONST_2_PITCHALIGN__SHIFT) & A4XX_TEX_CONST_2_PITCHALIGN__MASK; } +#define A4XX_TEX_CONST_2_BUFFER 0x00000040 #define A4XX_TEX_CONST_2_PITCH__MASK 0x3ffffe00 #define A4XX_TEX_CONST_2_PITCH__SHIFT 9 static inline uint32_t A4XX_TEX_CONST_2_PITCH(uint32_t val) diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index c5524d6e8705..0c6b2a6d0b4c 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -621,6 +621,7 @@ static u32 a4xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) static const struct adreno_gpu_funcs funcs = { .base = { .get_param = adreno_get_param, + .set_param = adreno_set_param, .hw_init = a4xx_hw_init, .pm_suspend = a4xx_pm_suspend, .pm_resume = a4xx_pm_resume, diff --git a/drivers/gpu/drm/msm/adreno/a5xx.xml.h b/drivers/gpu/drm/msm/adreno/a5xx.xml.h index 1e575ca1f270..2505b4e43ca0 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a5xx.xml.h @@ -8,21 +8,21 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14386 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 67699 bytes, from 2021-05-31 20:21:57) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84226 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a4xx.xml ( 112551 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a5xx.xml ( 150713 bytes, from 2021-06-10 22:34:02) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx.xml ( 180049 bytes, from 2021-06-02 21:44:19) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-05-27 20:22:36) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-05-27 20:18:13) - -Copyright (C) 2013-2021 by the following authors: +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-06-21 15:24:24) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14609 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 69086 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84231 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a4xx.xml ( 113358 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a5xx.xml ( 149512 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx.xml ( 184954 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-07-22 15:21:56) + +Copyright (C) 2013-2022 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin) @@ -872,6 +872,7 @@ enum a5xx_tex_type { A5XX_TEX_2D = 1, A5XX_TEX_CUBE = 2, A5XX_TEX_3D = 3, + A5XX_TEX_BUFFER = 4, }; #define A5XX_INT0_RBBM_GPU_IDLE 0x00000001 @@ -2830,7 +2831,9 @@ static inline uint32_t A5XX_GRAS_VS_CL_CNTL_CULL_MASK(uint32_t val) #define A5XX_GRAS_CNTL_IJ_PERSP_PIXEL 0x00000001 #define A5XX_GRAS_CNTL_IJ_PERSP_CENTROID 0x00000002 #define A5XX_GRAS_CNTL_IJ_PERSP_SAMPLE 0x00000004 -#define A5XX_GRAS_CNTL_SIZE 0x00000008 +#define A5XX_GRAS_CNTL_IJ_LINEAR_PIXEL 0x00000008 +#define A5XX_GRAS_CNTL_IJ_LINEAR_CENTROID 0x00000010 +#define A5XX_GRAS_CNTL_IJ_LINEAR_SAMPLE 0x00000020 #define A5XX_GRAS_CNTL_COORD_MASK__MASK 0x000003c0 #define A5XX_GRAS_CNTL_COORD_MASK__SHIFT 6 static inline uint32_t A5XX_GRAS_CNTL_COORD_MASK(uint32_t val) @@ -2911,7 +2914,12 @@ static inline uint32_t A5XX_GRAS_SU_CNTL_LINEHALFWIDTH(float val) return ((((int32_t)(val * 4.0))) << A5XX_GRAS_SU_CNTL_LINEHALFWIDTH__SHIFT) & A5XX_GRAS_SU_CNTL_LINEHALFWIDTH__MASK; } #define A5XX_GRAS_SU_CNTL_POLY_OFFSET 0x00000800 -#define A5XX_GRAS_SU_CNTL_MSAA_ENABLE 0x00002000 +#define A5XX_GRAS_SU_CNTL_LINE_MODE__MASK 0x00002000 +#define A5XX_GRAS_SU_CNTL_LINE_MODE__SHIFT 13 +static inline uint32_t A5XX_GRAS_SU_CNTL_LINE_MODE(enum a5xx_line_mode val) +{ + return ((val) << A5XX_GRAS_SU_CNTL_LINE_MODE__SHIFT) & A5XX_GRAS_SU_CNTL_LINE_MODE__MASK; +} #define REG_A5XX_GRAS_SU_POINT_MINMAX 0x0000e091 #define A5XX_GRAS_SU_POINT_MINMAX_MIN__MASK 0x0000ffff @@ -3166,7 +3174,9 @@ static inline uint32_t A5XX_RB_DEST_MSAA_CNTL_SAMPLES(enum a3xx_msaa_samples val #define A5XX_RB_RENDER_CONTROL0_IJ_PERSP_PIXEL 0x00000001 #define A5XX_RB_RENDER_CONTROL0_IJ_PERSP_CENTROID 0x00000002 #define A5XX_RB_RENDER_CONTROL0_IJ_PERSP_SAMPLE 0x00000004 -#define A5XX_RB_RENDER_CONTROL0_SIZE 0x00000008 +#define A5XX_RB_RENDER_CONTROL0_IJ_LINEAR_PIXEL 0x00000008 +#define A5XX_RB_RENDER_CONTROL0_IJ_LINEAR_CENTROID 0x00000010 +#define A5XX_RB_RENDER_CONTROL0_IJ_LINEAR_SAMPLE 0x00000020 #define A5XX_RB_RENDER_CONTROL0_COORD_MASK__MASK 0x000003c0 #define A5XX_RB_RENDER_CONTROL0_COORD_MASK__SHIFT 6 static inline uint32_t A5XX_RB_RENDER_CONTROL0_COORD_MASK(uint32_t val) @@ -3490,7 +3500,7 @@ static inline uint32_t A5XX_RB_BLEND_CNTL_SAMPLE_MASK(uint32_t val) #define A5XX_RB_DEPTH_PLANE_CNTL_UNK1 0x00000002 #define REG_A5XX_RB_DEPTH_CNTL 0x0000e1b1 -#define A5XX_RB_DEPTH_CNTL_Z_ENABLE 0x00000001 +#define A5XX_RB_DEPTH_CNTL_Z_TEST_ENABLE 0x00000001 #define A5XX_RB_DEPTH_CNTL_Z_WRITE_ENABLE 0x00000002 #define A5XX_RB_DEPTH_CNTL_ZFUNC__MASK 0x0000001c #define A5XX_RB_DEPTH_CNTL_ZFUNC__SHIFT 2 @@ -3498,7 +3508,7 @@ static inline uint32_t A5XX_RB_DEPTH_CNTL_ZFUNC(enum adreno_compare_func val) { return ((val) << A5XX_RB_DEPTH_CNTL_ZFUNC__SHIFT) & A5XX_RB_DEPTH_CNTL_ZFUNC__MASK; } -#define A5XX_RB_DEPTH_CNTL_Z_TEST_ENABLE 0x00000040 +#define A5XX_RB_DEPTH_CNTL_Z_READ_ENABLE 0x00000040 #define REG_A5XX_RB_DEPTH_BUFFER_INFO 0x0000e1b2 #define A5XX_RB_DEPTH_BUFFER_INFO_DEPTH_FORMAT__MASK 0x00000007 @@ -5034,6 +5044,7 @@ static inline uint32_t A5XX_RB_2D_SRC_INFO_COLOR_SWAP(enum a3xx_color_swap val) return ((val) << A5XX_RB_2D_SRC_INFO_COLOR_SWAP__SHIFT) & A5XX_RB_2D_SRC_INFO_COLOR_SWAP__MASK; } #define A5XX_RB_2D_SRC_INFO_FLAGS 0x00001000 +#define A5XX_RB_2D_SRC_INFO_SRGB 0x00002000 #define REG_A5XX_RB_2D_SRC_LO 0x00002108 @@ -5073,6 +5084,7 @@ static inline uint32_t A5XX_RB_2D_DST_INFO_COLOR_SWAP(enum a3xx_color_swap val) return ((val) << A5XX_RB_2D_DST_INFO_COLOR_SWAP__SHIFT) & A5XX_RB_2D_DST_INFO_COLOR_SWAP__MASK; } #define A5XX_RB_2D_DST_INFO_FLAGS 0x00001000 +#define A5XX_RB_2D_DST_INFO_SRGB 0x00002000 #define REG_A5XX_RB_2D_DST_LO 0x00002111 @@ -5138,6 +5150,7 @@ static inline uint32_t A5XX_GRAS_2D_SRC_INFO_COLOR_SWAP(enum a3xx_color_swap val return ((val) << A5XX_GRAS_2D_SRC_INFO_COLOR_SWAP__SHIFT) & A5XX_GRAS_2D_SRC_INFO_COLOR_SWAP__MASK; } #define A5XX_GRAS_2D_SRC_INFO_FLAGS 0x00001000 +#define A5XX_GRAS_2D_SRC_INFO_SRGB 0x00002000 #define REG_A5XX_GRAS_2D_DST_INFO 0x00002182 #define A5XX_GRAS_2D_DST_INFO_COLOR_FORMAT__MASK 0x000000ff @@ -5159,10 +5172,7 @@ static inline uint32_t A5XX_GRAS_2D_DST_INFO_COLOR_SWAP(enum a3xx_color_swap val return ((val) << A5XX_GRAS_2D_DST_INFO_COLOR_SWAP__SHIFT) & A5XX_GRAS_2D_DST_INFO_COLOR_SWAP__MASK; } #define A5XX_GRAS_2D_DST_INFO_FLAGS 0x00001000 - -#define REG_A5XX_UNKNOWN_2100 0x00002100 - -#define REG_A5XX_UNKNOWN_2180 0x00002180 +#define A5XX_GRAS_2D_DST_INFO_SRGB 0x00002000 #define REG_A5XX_UNKNOWN_2184 0x00002184 @@ -5316,7 +5326,7 @@ static inline uint32_t A5XX_TEX_CONST_1_HEIGHT(uint32_t val) } #define REG_A5XX_TEX_CONST_2 0x00000002 -#define A5XX_TEX_CONST_2_UNK4 0x00000010 +#define A5XX_TEX_CONST_2_BUFFER 0x00000010 #define A5XX_TEX_CONST_2_PITCHALIGN__MASK 0x0000000f #define A5XX_TEX_CONST_2_PITCHALIGN__SHIFT 0 static inline uint32_t A5XX_TEX_CONST_2_PITCHALIGN(uint32_t val) @@ -5329,13 +5339,12 @@ static inline uint32_t A5XX_TEX_CONST_2_PITCH(uint32_t val) { return ((val) << A5XX_TEX_CONST_2_PITCH__SHIFT) & A5XX_TEX_CONST_2_PITCH__MASK; } -#define A5XX_TEX_CONST_2_TYPE__MASK 0x60000000 +#define A5XX_TEX_CONST_2_TYPE__MASK 0xe0000000 #define A5XX_TEX_CONST_2_TYPE__SHIFT 29 static inline uint32_t A5XX_TEX_CONST_2_TYPE(enum a5xx_tex_type val) { return ((val) << A5XX_TEX_CONST_2_TYPE__SHIFT) & A5XX_TEX_CONST_2_TYPE__MASK; } -#define A5XX_TEX_CONST_2_UNK31 0x80000000 #define REG_A5XX_TEX_CONST_3 0x00000003 #define A5XX_TEX_CONST_3_ARRAY_PITCH__MASK 0x00003fff diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 3d28fcf841a6..407f50a15faa 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1700,6 +1700,7 @@ static uint32_t a5xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) static const struct adreno_gpu_funcs funcs = { .base = { .get_param = adreno_get_param, + .set_param = adreno_set_param, .hw_init = a5xx_hw_init, .pm_suspend = a5xx_pm_suspend, .pm_resume = a5xx_pm_resume, diff --git a/drivers/gpu/drm/msm/adreno/a6xx.xml.h b/drivers/gpu/drm/msm/adreno/a6xx.xml.h index a3cb3d988ba4..b03e2c413ab1 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a6xx.xml.h @@ -8,21 +8,21 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14386 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 67699 bytes, from 2021-05-31 20:21:57) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84226 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a4xx.xml ( 112551 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a5xx.xml ( 150713 bytes, from 2021-06-10 22:34:02) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx.xml ( 180049 bytes, from 2021-06-02 21:44:19) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-05-27 20:22:36) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-05-27 20:18:13) - -Copyright (C) 2013-2021 by the following authors: +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-06-21 15:24:24) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14609 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 69086 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84231 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a4xx.xml ( 113358 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a5xx.xml ( 149512 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx.xml ( 184954 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-07-22 15:21:56) + +Copyright (C) 2013-2022 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin) @@ -132,9 +132,21 @@ enum a6xx_format { FMT6_G8R8B8R8_422_UNORM = 140, FMT6_R8G8R8B8_422_UNORM = 141, FMT6_R8_G8B8_2PLANE_420_UNORM = 142, + FMT6_NV21 = 143, FMT6_R8_G8_B8_3PLANE_420_UNORM = 144, FMT6_Z24_UNORM_S8_UINT_AS_R8G8B8A8 = 145, - FMT6_8_PLANE_UNORM = 148, + FMT6_NV12_Y = 148, + FMT6_NV12_UV = 149, + FMT6_NV12_VU = 150, + FMT6_NV12_4R = 151, + FMT6_NV12_4R_Y = 152, + FMT6_NV12_4R_UV = 153, + FMT6_P010 = 154, + FMT6_P010_Y = 155, + FMT6_P010_UV = 156, + FMT6_TP10 = 157, + FMT6_TP10_Y = 158, + FMT6_TP10_UV = 159, FMT6_Z24_UNORM_S8_UINT = 160, FMT6_ETC2_RG11_UNORM = 171, FMT6_ETC2_RG11_SNORM = 172, @@ -885,6 +897,44 @@ enum a6xx_ztest_mode { A6XX_EARLY_LRZ_LATE_Z = 2, }; +enum a6xx_sequenced_thread_dist { + DIST_SCREEN_COORD = 0, + DIST_ALL_TO_RB0 = 1, +}; + +enum a6xx_single_prim_mode { + NO_FLUSH = 0, + FLUSH_PER_OVERLAP_AND_OVERWRITE = 1, + FLUSH_PER_OVERLAP = 3, +}; + +enum a6xx_raster_mode { + TYPE_TILED = 0, + TYPE_WRITER = 1, +}; + +enum a6xx_raster_direction { + LR_TB = 0, + RL_TB = 1, + LR_BT = 2, + RB_BT = 3, +}; + +enum a6xx_render_mode { + RENDERING_PASS = 0, + BINNING_PASS = 1, +}; + +enum a6xx_buffers_location { + BUFFERS_IN_GMEM = 0, + BUFFERS_IN_SYSMEM = 3, +}; + +enum a6xx_fragcoord_sample_mode { + FRAGCOORD_CENTER = 0, + FRAGCOORD_SAMPLE = 3, +}; + enum a6xx_rotation { ROTATE_0 = 0, ROTATE_90 = 1, @@ -912,6 +962,10 @@ enum a6xx_threadsize { THREAD128 = 1, }; +enum a6xx_isam_mode { + ISAMMODE_GL = 2, +}; + enum a6xx_tex_filter { A6XX_TEX_NEAREST = 0, A6XX_TEX_LINEAR = 1, @@ -955,6 +1009,7 @@ enum a6xx_tex_type { A6XX_TEX_2D = 1, A6XX_TEX_CUBE = 2, A6XX_TEX_3D = 3, + A6XX_TEX_BUFFER = 4, }; #define A6XX_RBBM_INT_0_MASK_RBBM_GPU_IDLE 0x00000001 @@ -1292,6 +1347,10 @@ static inline uint32_t REG_A6XX_RBBM_PERFCTR_RBBM_SEL(uint32_t i0) { return 0x00 #define REG_A6XX_RBBM_PERFCTR_GPU_BUSY_MASKED 0x0000050b +#define REG_A6XX_RBBM_PERFCTR_SRAM_INIT_CMD 0x0000050e + +#define REG_A6XX_RBBM_PERFCTR_SRAM_INIT_STATUS 0x0000050f + #define REG_A6XX_RBBM_ISDB_CNT 0x00000533 #define REG_A6XX_RBBM_PRIMCTR_0_LO 0x00000540 @@ -1934,6 +1993,8 @@ static inline uint32_t A6XX_VBIF_TEST_BUS2_CTRL1_DATA_SEL(uint32_t val) #define REG_A6XX_GBIF_PWR_CNT_HIGH2 0x00003cd1 +#define REG_A6XX_VSC_DBG_ECO_CNTL 0x00000c00 + #define REG_A6XX_VSC_BIN_SIZE 0x00000c02 #define A6XX_VSC_BIN_SIZE_WIDTH__MASK 0x000000ff #define A6XX_VSC_BIN_SIZE_WIDTH__SHIFT 0 @@ -2076,9 +2137,9 @@ static inline uint32_t A6XX_GRAS_GS_CL_CNTL_CULL_MASK(uint32_t val) #define A6XX_GRAS_CNTL_IJ_PERSP_PIXEL 0x00000001 #define A6XX_GRAS_CNTL_IJ_PERSP_CENTROID 0x00000002 #define A6XX_GRAS_CNTL_IJ_PERSP_SAMPLE 0x00000004 -#define A6XX_GRAS_CNTL_SIZE 0x00000008 -#define A6XX_GRAS_CNTL_UNK4 0x00000010 -#define A6XX_GRAS_CNTL_SIZE_PERSAMP 0x00000020 +#define A6XX_GRAS_CNTL_IJ_LINEAR_PIXEL 0x00000008 +#define A6XX_GRAS_CNTL_IJ_LINEAR_CENTROID 0x00000010 +#define A6XX_GRAS_CNTL_IJ_LINEAR_SAMPLE 0x00000020 #define A6XX_GRAS_CNTL_COORD_MASK__MASK 0x000003c0 #define A6XX_GRAS_CNTL_COORD_MASK__SHIFT 6 static inline uint32_t A6XX_GRAS_CNTL_COORD_MASK(uint32_t val) @@ -2185,7 +2246,12 @@ static inline uint32_t A6XX_GRAS_SU_CNTL_UNK12(uint32_t val) { return ((val) << A6XX_GRAS_SU_CNTL_UNK12__SHIFT) & A6XX_GRAS_SU_CNTL_UNK12__MASK; } -#define A6XX_GRAS_SU_CNTL_MSAA_ENABLE 0x00002000 +#define A6XX_GRAS_SU_CNTL_LINE_MODE__MASK 0x00002000 +#define A6XX_GRAS_SU_CNTL_LINE_MODE__SHIFT 13 +static inline uint32_t A6XX_GRAS_SU_CNTL_LINE_MODE(enum a5xx_line_mode val) +{ + return ((val) << A6XX_GRAS_SU_CNTL_LINE_MODE__SHIFT) & A6XX_GRAS_SU_CNTL_LINE_MODE__MASK; +} #define A6XX_GRAS_SU_CNTL_UNK15__MASK 0x00018000 #define A6XX_GRAS_SU_CNTL_UNK15__SHIFT 15 static inline uint32_t A6XX_GRAS_SU_CNTL_UNK15(uint32_t val) @@ -2269,9 +2335,25 @@ static inline uint32_t A6XX_GRAS_SU_DEPTH_BUFFER_INFO_UNK3(uint32_t val) return ((val) << A6XX_GRAS_SU_DEPTH_BUFFER_INFO_UNK3__SHIFT) & A6XX_GRAS_SU_DEPTH_BUFFER_INFO_UNK3__MASK; } -#define REG_A6XX_GRAS_UNKNOWN_8099 0x00008099 +#define REG_A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL 0x00008099 +#define A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL_CONSERVATIVERASEN 0x00000001 +#define A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL_SHIFTAMOUNT__MASK 0x00000006 +#define A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL_SHIFTAMOUNT__SHIFT 1 +static inline uint32_t A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL_SHIFTAMOUNT(uint32_t val) +{ + return ((val) << A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL_SHIFTAMOUNT__SHIFT) & A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL_SHIFTAMOUNT__MASK; +} +#define A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL_INNERCONSERVATIVERASEN 0x00000008 +#define A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL_UNK4__MASK 0x00000030 +#define A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL_UNK4__SHIFT 4 +static inline uint32_t A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL_UNK4(uint32_t val) +{ + return ((val) << A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL_UNK4__SHIFT) & A6XX_GRAS_SU_CONSERVATIVE_RAS_CNTL_UNK4__MASK; +} -#define REG_A6XX_GRAS_UNKNOWN_809A 0x0000809a +#define REG_A6XX_GRAS_SU_PATH_RENDERING_CNTL 0x0000809a +#define A6XX_GRAS_SU_PATH_RENDERING_CNTL_UNK0 0x00000001 +#define A6XX_GRAS_SU_PATH_RENDERING_CNTL_LINELENGTHEN 0x00000002 #define REG_A6XX_GRAS_VS_LAYER_CNTL 0x0000809b #define A6XX_GRAS_VS_LAYER_CNTL_WRITES_LAYER 0x00000001 @@ -2285,7 +2367,44 @@ static inline uint32_t A6XX_GRAS_SU_DEPTH_BUFFER_INFO_UNK3(uint32_t val) #define A6XX_GRAS_DS_LAYER_CNTL_WRITES_LAYER 0x00000001 #define A6XX_GRAS_DS_LAYER_CNTL_WRITES_VIEW 0x00000002 -#define REG_A6XX_GRAS_UNKNOWN_80A0 0x000080a0 +#define REG_A6XX_GRAS_SC_CNTL 0x000080a0 +#define A6XX_GRAS_SC_CNTL_CCUSINGLECACHELINESIZE__MASK 0x00000007 +#define A6XX_GRAS_SC_CNTL_CCUSINGLECACHELINESIZE__SHIFT 0 +static inline uint32_t A6XX_GRAS_SC_CNTL_CCUSINGLECACHELINESIZE(uint32_t val) +{ + return ((val) << A6XX_GRAS_SC_CNTL_CCUSINGLECACHELINESIZE__SHIFT) & A6XX_GRAS_SC_CNTL_CCUSINGLECACHELINESIZE__MASK; +} +#define A6XX_GRAS_SC_CNTL_SINGLE_PRIM_MODE__MASK 0x00000018 +#define A6XX_GRAS_SC_CNTL_SINGLE_PRIM_MODE__SHIFT 3 +static inline uint32_t A6XX_GRAS_SC_CNTL_SINGLE_PRIM_MODE(enum a6xx_single_prim_mode val) +{ + return ((val) << A6XX_GRAS_SC_CNTL_SINGLE_PRIM_MODE__SHIFT) & A6XX_GRAS_SC_CNTL_SINGLE_PRIM_MODE__MASK; +} +#define A6XX_GRAS_SC_CNTL_RASTER_MODE__MASK 0x00000020 +#define A6XX_GRAS_SC_CNTL_RASTER_MODE__SHIFT 5 +static inline uint32_t A6XX_GRAS_SC_CNTL_RASTER_MODE(enum a6xx_raster_mode val) +{ + return ((val) << A6XX_GRAS_SC_CNTL_RASTER_MODE__SHIFT) & A6XX_GRAS_SC_CNTL_RASTER_MODE__MASK; +} +#define A6XX_GRAS_SC_CNTL_RASTER_DIRECTION__MASK 0x000000c0 +#define A6XX_GRAS_SC_CNTL_RASTER_DIRECTION__SHIFT 6 +static inline uint32_t A6XX_GRAS_SC_CNTL_RASTER_DIRECTION(enum a6xx_raster_direction val) +{ + return ((val) << A6XX_GRAS_SC_CNTL_RASTER_DIRECTION__SHIFT) & A6XX_GRAS_SC_CNTL_RASTER_DIRECTION__MASK; +} +#define A6XX_GRAS_SC_CNTL_SEQUENCED_THREAD_DISTRIBUTION__MASK 0x00000100 +#define A6XX_GRAS_SC_CNTL_SEQUENCED_THREAD_DISTRIBUTION__SHIFT 8 +static inline uint32_t A6XX_GRAS_SC_CNTL_SEQUENCED_THREAD_DISTRIBUTION(enum a6xx_sequenced_thread_dist val) +{ + return ((val) << A6XX_GRAS_SC_CNTL_SEQUENCED_THREAD_DISTRIBUTION__SHIFT) & A6XX_GRAS_SC_CNTL_SEQUENCED_THREAD_DISTRIBUTION__MASK; +} +#define A6XX_GRAS_SC_CNTL_UNK9__MASK 0x00000e00 +#define A6XX_GRAS_SC_CNTL_UNK9__SHIFT 9 +static inline uint32_t A6XX_GRAS_SC_CNTL_UNK9(uint32_t val) +{ + return ((val) << A6XX_GRAS_SC_CNTL_UNK9__SHIFT) & A6XX_GRAS_SC_CNTL_UNK9__MASK; +} +#define A6XX_GRAS_SC_CNTL_EARLYVIZOUTEN 0x00001000 #define REG_A6XX_GRAS_BIN_CONTROL 0x000080a1 #define A6XX_GRAS_BIN_CONTROL_BINW__MASK 0x0000003f @@ -2300,25 +2419,30 @@ static inline uint32_t A6XX_GRAS_BIN_CONTROL_BINH(uint32_t val) { return ((val >> 4) << A6XX_GRAS_BIN_CONTROL_BINH__SHIFT) & A6XX_GRAS_BIN_CONTROL_BINH__MASK; } -#define A6XX_GRAS_BIN_CONTROL_BINNING_PASS 0x00040000 -#define A6XX_GRAS_BIN_CONTROL_UNK19__MASK 0x00080000 -#define A6XX_GRAS_BIN_CONTROL_UNK19__SHIFT 19 -static inline uint32_t A6XX_GRAS_BIN_CONTROL_UNK19(uint32_t val) +#define A6XX_GRAS_BIN_CONTROL_RENDER_MODE__MASK 0x001c0000 +#define A6XX_GRAS_BIN_CONTROL_RENDER_MODE__SHIFT 18 +static inline uint32_t A6XX_GRAS_BIN_CONTROL_RENDER_MODE(enum a6xx_render_mode val) +{ + return ((val) << A6XX_GRAS_BIN_CONTROL_RENDER_MODE__SHIFT) & A6XX_GRAS_BIN_CONTROL_RENDER_MODE__MASK; +} +#define A6XX_GRAS_BIN_CONTROL_FORCE_LRZ_WRITE_DIS 0x00200000 +#define A6XX_GRAS_BIN_CONTROL_BUFFERS_LOCATION__MASK 0x00c00000 +#define A6XX_GRAS_BIN_CONTROL_BUFFERS_LOCATION__SHIFT 22 +static inline uint32_t A6XX_GRAS_BIN_CONTROL_BUFFERS_LOCATION(enum a6xx_buffers_location val) { - return ((val) << A6XX_GRAS_BIN_CONTROL_UNK19__SHIFT) & A6XX_GRAS_BIN_CONTROL_UNK19__MASK; + return ((val) << A6XX_GRAS_BIN_CONTROL_BUFFERS_LOCATION__SHIFT) & A6XX_GRAS_BIN_CONTROL_BUFFERS_LOCATION__MASK; } -#define A6XX_GRAS_BIN_CONTROL_UNK20__MASK 0x00100000 -#define A6XX_GRAS_BIN_CONTROL_UNK20__SHIFT 20 -static inline uint32_t A6XX_GRAS_BIN_CONTROL_UNK20(uint32_t val) +#define A6XX_GRAS_BIN_CONTROL_LRZ_FEEDBACK_ZMODE_MASK__MASK 0x07000000 +#define A6XX_GRAS_BIN_CONTROL_LRZ_FEEDBACK_ZMODE_MASK__SHIFT 24 +static inline uint32_t A6XX_GRAS_BIN_CONTROL_LRZ_FEEDBACK_ZMODE_MASK(uint32_t val) { - return ((val) << A6XX_GRAS_BIN_CONTROL_UNK20__SHIFT) & A6XX_GRAS_BIN_CONTROL_UNK20__MASK; + return ((val) << A6XX_GRAS_BIN_CONTROL_LRZ_FEEDBACK_ZMODE_MASK__SHIFT) & A6XX_GRAS_BIN_CONTROL_LRZ_FEEDBACK_ZMODE_MASK__MASK; } -#define A6XX_GRAS_BIN_CONTROL_USE_VIZ 0x00200000 -#define A6XX_GRAS_BIN_CONTROL_UNK22__MASK 0x0fc00000 -#define A6XX_GRAS_BIN_CONTROL_UNK22__SHIFT 22 -static inline uint32_t A6XX_GRAS_BIN_CONTROL_UNK22(uint32_t val) +#define A6XX_GRAS_BIN_CONTROL_UNK27__MASK 0x08000000 +#define A6XX_GRAS_BIN_CONTROL_UNK27__SHIFT 27 +static inline uint32_t A6XX_GRAS_BIN_CONTROL_UNK27(uint32_t val) { - return ((val) << A6XX_GRAS_BIN_CONTROL_UNK22__SHIFT) & A6XX_GRAS_BIN_CONTROL_UNK22__MASK; + return ((val) << A6XX_GRAS_BIN_CONTROL_UNK27__SHIFT) & A6XX_GRAS_BIN_CONTROL_UNK27__MASK; } #define REG_A6XX_GRAS_RAS_MSAA_CNTL 0x000080a2 @@ -2558,14 +2682,21 @@ static inline uint32_t A6XX_GRAS_LRZ_CNTL_UNK6(uint32_t val) return ((val) << A6XX_GRAS_LRZ_CNTL_UNK6__SHIFT) & A6XX_GRAS_LRZ_CNTL_UNK6__MASK; } -#define REG_A6XX_GRAS_UNKNOWN_8101 0x00008101 +#define REG_A6XX_GRAS_LRZ_PS_INPUT_CNTL 0x00008101 +#define A6XX_GRAS_LRZ_PS_INPUT_CNTL_SAMPLEID 0x00000001 +#define A6XX_GRAS_LRZ_PS_INPUT_CNTL_FRAGCOORDSAMPLEMODE__MASK 0x00000006 +#define A6XX_GRAS_LRZ_PS_INPUT_CNTL_FRAGCOORDSAMPLEMODE__SHIFT 1 +static inline uint32_t A6XX_GRAS_LRZ_PS_INPUT_CNTL_FRAGCOORDSAMPLEMODE(enum a6xx_fragcoord_sample_mode val) +{ + return ((val) << A6XX_GRAS_LRZ_PS_INPUT_CNTL_FRAGCOORDSAMPLEMODE__SHIFT) & A6XX_GRAS_LRZ_PS_INPUT_CNTL_FRAGCOORDSAMPLEMODE__MASK; +} -#define REG_A6XX_GRAS_2D_BLIT_INFO 0x00008102 -#define A6XX_GRAS_2D_BLIT_INFO_COLOR_FORMAT__MASK 0x000000ff -#define A6XX_GRAS_2D_BLIT_INFO_COLOR_FORMAT__SHIFT 0 -static inline uint32_t A6XX_GRAS_2D_BLIT_INFO_COLOR_FORMAT(enum a6xx_format val) +#define REG_A6XX_GRAS_LRZ_MRT_BUF_INFO_0 0x00008102 +#define A6XX_GRAS_LRZ_MRT_BUF_INFO_0_COLOR_FORMAT__MASK 0x000000ff +#define A6XX_GRAS_LRZ_MRT_BUF_INFO_0_COLOR_FORMAT__SHIFT 0 +static inline uint32_t A6XX_GRAS_LRZ_MRT_BUF_INFO_0_COLOR_FORMAT(enum a6xx_format val) { - return ((val) << A6XX_GRAS_2D_BLIT_INFO_COLOR_FORMAT__SHIFT) & A6XX_GRAS_2D_BLIT_INFO_COLOR_FORMAT__MASK; + return ((val) << A6XX_GRAS_LRZ_MRT_BUF_INFO_0_COLOR_FORMAT__SHIFT) & A6XX_GRAS_LRZ_MRT_BUF_INFO_0_COLOR_FORMAT__MASK; } #define REG_A6XX_GRAS_LRZ_BUFFER_BASE 0x00008103 @@ -2630,11 +2761,12 @@ static inline uint32_t A6XX_GRAS_2D_BLIT_CNTL_ROTATE(enum a6xx_rotation val) { return ((val) << A6XX_GRAS_2D_BLIT_CNTL_ROTATE__SHIFT) & A6XX_GRAS_2D_BLIT_CNTL_ROTATE__MASK; } -#define A6XX_GRAS_2D_BLIT_CNTL_UNK3__MASK 0x00000078 -#define A6XX_GRAS_2D_BLIT_CNTL_UNK3__SHIFT 3 -static inline uint32_t A6XX_GRAS_2D_BLIT_CNTL_UNK3(uint32_t val) +#define A6XX_GRAS_2D_BLIT_CNTL_OVERWRITEEN 0x00000008 +#define A6XX_GRAS_2D_BLIT_CNTL_UNK4__MASK 0x00000070 +#define A6XX_GRAS_2D_BLIT_CNTL_UNK4__SHIFT 4 +static inline uint32_t A6XX_GRAS_2D_BLIT_CNTL_UNK4(uint32_t val) { - return ((val) << A6XX_GRAS_2D_BLIT_CNTL_UNK3__SHIFT) & A6XX_GRAS_2D_BLIT_CNTL_UNK3__MASK; + return ((val) << A6XX_GRAS_2D_BLIT_CNTL_UNK4__SHIFT) & A6XX_GRAS_2D_BLIT_CNTL_UNK4__MASK; } #define A6XX_GRAS_2D_BLIT_CNTL_SOLID_COLOR 0x00000080 #define A6XX_GRAS_2D_BLIT_CNTL_COLOR_FORMAT__MASK 0x0000ff00 @@ -2663,11 +2795,11 @@ static inline uint32_t A6XX_GRAS_2D_BLIT_CNTL_IFMT(enum a6xx_2d_ifmt val) { return ((val) << A6XX_GRAS_2D_BLIT_CNTL_IFMT__SHIFT) & A6XX_GRAS_2D_BLIT_CNTL_IFMT__MASK; } -#define A6XX_GRAS_2D_BLIT_CNTL_UNK29__MASK 0x20000000 -#define A6XX_GRAS_2D_BLIT_CNTL_UNK29__SHIFT 29 -static inline uint32_t A6XX_GRAS_2D_BLIT_CNTL_UNK29(uint32_t val) +#define A6XX_GRAS_2D_BLIT_CNTL_RASTER_MODE__MASK 0x20000000 +#define A6XX_GRAS_2D_BLIT_CNTL_RASTER_MODE__SHIFT 29 +static inline uint32_t A6XX_GRAS_2D_BLIT_CNTL_RASTER_MODE(enum a6xx_raster_mode val) { - return ((val) << A6XX_GRAS_2D_BLIT_CNTL_UNK29__SHIFT) & A6XX_GRAS_2D_BLIT_CNTL_UNK29__MASK; + return ((val) << A6XX_GRAS_2D_BLIT_CNTL_RASTER_MODE__SHIFT) & A6XX_GRAS_2D_BLIT_CNTL_RASTER_MODE__MASK; } #define REG_A6XX_GRAS_2D_SRC_TL_X 0x00008401 @@ -2740,7 +2872,9 @@ static inline uint32_t A6XX_GRAS_2D_RESOLVE_CNTL_2_Y(uint32_t val) return ((val) << A6XX_GRAS_2D_RESOLVE_CNTL_2_Y__SHIFT) & A6XX_GRAS_2D_RESOLVE_CNTL_2_Y__MASK; } -#define REG_A6XX_GRAS_UNKNOWN_8600 0x00008600 +#define REG_A6XX_GRAS_DBG_ECO_CNTL 0x00008600 +#define A6XX_GRAS_DBG_ECO_CNTL_UNK7 0x00000080 +#define A6XX_GRAS_DBG_ECO_CNTL_LRZCACHELOCKDIS 0x00000800 #define REG_A6XX_GRAS_ADDR_MODE_CNTL 0x00008601 @@ -2763,43 +2897,55 @@ static inline uint32_t A6XX_RB_BIN_CONTROL_BINH(uint32_t val) { return ((val >> 4) << A6XX_RB_BIN_CONTROL_BINH__SHIFT) & A6XX_RB_BIN_CONTROL_BINH__MASK; } -#define A6XX_RB_BIN_CONTROL_BINNING_PASS 0x00040000 -#define A6XX_RB_BIN_CONTROL_UNK19__MASK 0x00080000 -#define A6XX_RB_BIN_CONTROL_UNK19__SHIFT 19 -static inline uint32_t A6XX_RB_BIN_CONTROL_UNK19(uint32_t val) +#define A6XX_RB_BIN_CONTROL_RENDER_MODE__MASK 0x001c0000 +#define A6XX_RB_BIN_CONTROL_RENDER_MODE__SHIFT 18 +static inline uint32_t A6XX_RB_BIN_CONTROL_RENDER_MODE(enum a6xx_render_mode val) { - return ((val) << A6XX_RB_BIN_CONTROL_UNK19__SHIFT) & A6XX_RB_BIN_CONTROL_UNK19__MASK; + return ((val) << A6XX_RB_BIN_CONTROL_RENDER_MODE__SHIFT) & A6XX_RB_BIN_CONTROL_RENDER_MODE__MASK; } -#define A6XX_RB_BIN_CONTROL_UNK20__MASK 0x00100000 -#define A6XX_RB_BIN_CONTROL_UNK20__SHIFT 20 -static inline uint32_t A6XX_RB_BIN_CONTROL_UNK20(uint32_t val) +#define A6XX_RB_BIN_CONTROL_FORCE_LRZ_WRITE_DIS 0x00200000 +#define A6XX_RB_BIN_CONTROL_BUFFERS_LOCATION__MASK 0x00c00000 +#define A6XX_RB_BIN_CONTROL_BUFFERS_LOCATION__SHIFT 22 +static inline uint32_t A6XX_RB_BIN_CONTROL_BUFFERS_LOCATION(enum a6xx_buffers_location val) { - return ((val) << A6XX_RB_BIN_CONTROL_UNK20__SHIFT) & A6XX_RB_BIN_CONTROL_UNK20__MASK; + return ((val) << A6XX_RB_BIN_CONTROL_BUFFERS_LOCATION__SHIFT) & A6XX_RB_BIN_CONTROL_BUFFERS_LOCATION__MASK; } -#define A6XX_RB_BIN_CONTROL_USE_VIZ 0x00200000 -#define A6XX_RB_BIN_CONTROL_UNK22__MASK 0x07c00000 -#define A6XX_RB_BIN_CONTROL_UNK22__SHIFT 22 -static inline uint32_t A6XX_RB_BIN_CONTROL_UNK22(uint32_t val) +#define A6XX_RB_BIN_CONTROL_LRZ_FEEDBACK_ZMODE_MASK__MASK 0x07000000 +#define A6XX_RB_BIN_CONTROL_LRZ_FEEDBACK_ZMODE_MASK__SHIFT 24 +static inline uint32_t A6XX_RB_BIN_CONTROL_LRZ_FEEDBACK_ZMODE_MASK(uint32_t val) { - return ((val) << A6XX_RB_BIN_CONTROL_UNK22__SHIFT) & A6XX_RB_BIN_CONTROL_UNK22__MASK; + return ((val) << A6XX_RB_BIN_CONTROL_LRZ_FEEDBACK_ZMODE_MASK__SHIFT) & A6XX_RB_BIN_CONTROL_LRZ_FEEDBACK_ZMODE_MASK__MASK; } #define REG_A6XX_RB_RENDER_CNTL 0x00008801 -#define A6XX_RB_RENDER_CNTL_UNK3 0x00000008 -#define A6XX_RB_RENDER_CNTL_UNK4 0x00000010 -#define A6XX_RB_RENDER_CNTL_UNK5__MASK 0x00000060 -#define A6XX_RB_RENDER_CNTL_UNK5__SHIFT 5 -static inline uint32_t A6XX_RB_RENDER_CNTL_UNK5(uint32_t val) +#define A6XX_RB_RENDER_CNTL_CCUSINGLECACHELINESIZE__MASK 0x00000038 +#define A6XX_RB_RENDER_CNTL_CCUSINGLECACHELINESIZE__SHIFT 3 +static inline uint32_t A6XX_RB_RENDER_CNTL_CCUSINGLECACHELINESIZE(uint32_t val) { - return ((val) << A6XX_RB_RENDER_CNTL_UNK5__SHIFT) & A6XX_RB_RENDER_CNTL_UNK5__MASK; + return ((val) << A6XX_RB_RENDER_CNTL_CCUSINGLECACHELINESIZE__SHIFT) & A6XX_RB_RENDER_CNTL_CCUSINGLECACHELINESIZE__MASK; } +#define A6XX_RB_RENDER_CNTL_EARLYVIZOUTEN 0x00000040 #define A6XX_RB_RENDER_CNTL_BINNING 0x00000080 -#define A6XX_RB_RENDER_CNTL_UNK8__MASK 0x00001f00 +#define A6XX_RB_RENDER_CNTL_UNK8__MASK 0x00000700 #define A6XX_RB_RENDER_CNTL_UNK8__SHIFT 8 static inline uint32_t A6XX_RB_RENDER_CNTL_UNK8(uint32_t val) { return ((val) << A6XX_RB_RENDER_CNTL_UNK8__SHIFT) & A6XX_RB_RENDER_CNTL_UNK8__MASK; } +#define A6XX_RB_RENDER_CNTL_RASTER_MODE__MASK 0x00000100 +#define A6XX_RB_RENDER_CNTL_RASTER_MODE__SHIFT 8 +static inline uint32_t A6XX_RB_RENDER_CNTL_RASTER_MODE(enum a6xx_raster_mode val) +{ + return ((val) << A6XX_RB_RENDER_CNTL_RASTER_MODE__SHIFT) & A6XX_RB_RENDER_CNTL_RASTER_MODE__MASK; +} +#define A6XX_RB_RENDER_CNTL_RASTER_DIRECTION__MASK 0x00000600 +#define A6XX_RB_RENDER_CNTL_RASTER_DIRECTION__SHIFT 9 +static inline uint32_t A6XX_RB_RENDER_CNTL_RASTER_DIRECTION(enum a6xx_raster_direction val) +{ + return ((val) << A6XX_RB_RENDER_CNTL_RASTER_DIRECTION__SHIFT) & A6XX_RB_RENDER_CNTL_RASTER_DIRECTION__MASK; +} +#define A6XX_RB_RENDER_CNTL_CONSERVATIVERASEN 0x00000800 +#define A6XX_RB_RENDER_CNTL_INNERCONSERVATIVERASEN 0x00001000 #define A6XX_RB_RENDER_CNTL_FLAG_DEPTH 0x00004000 #define A6XX_RB_RENDER_CNTL_FLAG_MRTS__MASK 0x00ff0000 #define A6XX_RB_RENDER_CNTL_FLAG_MRTS__SHIFT 16 @@ -2945,9 +3091,9 @@ static inline uint32_t A6XX_RB_SAMPLE_LOCATION_1_SAMPLE_3_Y(float val) #define A6XX_RB_RENDER_CONTROL0_IJ_PERSP_PIXEL 0x00000001 #define A6XX_RB_RENDER_CONTROL0_IJ_PERSP_CENTROID 0x00000002 #define A6XX_RB_RENDER_CONTROL0_IJ_PERSP_SAMPLE 0x00000004 -#define A6XX_RB_RENDER_CONTROL0_SIZE 0x00000008 -#define A6XX_RB_RENDER_CONTROL0_UNK4 0x00000010 -#define A6XX_RB_RENDER_CONTROL0_SIZE_PERSAMP 0x00000020 +#define A6XX_RB_RENDER_CONTROL0_IJ_LINEAR_PIXEL 0x00000008 +#define A6XX_RB_RENDER_CONTROL0_IJ_LINEAR_CENTROID 0x00000010 +#define A6XX_RB_RENDER_CONTROL0_IJ_LINEAR_SAMPLE 0x00000020 #define A6XX_RB_RENDER_CONTROL0_COORD_MASK__MASK 0x000003c0 #define A6XX_RB_RENDER_CONTROL0_COORD_MASK__SHIFT 6 static inline uint32_t A6XX_RB_RENDER_CONTROL0_COORD_MASK(uint32_t val) @@ -2961,11 +3107,15 @@ static inline uint32_t A6XX_RB_RENDER_CONTROL0_COORD_MASK(uint32_t val) #define A6XX_RB_RENDER_CONTROL1_UNK1 0x00000002 #define A6XX_RB_RENDER_CONTROL1_FACENESS 0x00000004 #define A6XX_RB_RENDER_CONTROL1_SAMPLEID 0x00000008 -#define A6XX_RB_RENDER_CONTROL1_UNK4 0x00000010 -#define A6XX_RB_RENDER_CONTROL1_UNK5 0x00000020 +#define A6XX_RB_RENDER_CONTROL1_FRAGCOORDSAMPLEMODE__MASK 0x00000030 +#define A6XX_RB_RENDER_CONTROL1_FRAGCOORDSAMPLEMODE__SHIFT 4 +static inline uint32_t A6XX_RB_RENDER_CONTROL1_FRAGCOORDSAMPLEMODE(enum a6xx_fragcoord_sample_mode val) +{ + return ((val) << A6XX_RB_RENDER_CONTROL1_FRAGCOORDSAMPLEMODE__SHIFT) & A6XX_RB_RENDER_CONTROL1_FRAGCOORDSAMPLEMODE__MASK; +} #define A6XX_RB_RENDER_CONTROL1_SIZE 0x00000040 -#define A6XX_RB_RENDER_CONTROL1_UNK7 0x00000080 -#define A6XX_RB_RENDER_CONTROL1_UNK8 0x00000100 +#define A6XX_RB_RENDER_CONTROL1_LINELENGTHEN 0x00000080 +#define A6XX_RB_RENDER_CONTROL1_FOVEATION 0x00000100 #define REG_A6XX_RB_FS_OUTPUT_CNTL0 0x0000880b #define A6XX_RB_FS_OUTPUT_CNTL0_DUAL_COLOR_IN_ENABLE 0x00000001 @@ -3299,7 +3449,7 @@ static inline uint32_t A6XX_RB_DEPTH_PLANE_CNTL_Z_MODE(enum a6xx_ztest_mode val) } #define REG_A6XX_RB_DEPTH_CNTL 0x00008871 -#define A6XX_RB_DEPTH_CNTL_Z_ENABLE 0x00000001 +#define A6XX_RB_DEPTH_CNTL_Z_TEST_ENABLE 0x00000001 #define A6XX_RB_DEPTH_CNTL_Z_WRITE_ENABLE 0x00000002 #define A6XX_RB_DEPTH_CNTL_ZFUNC__MASK 0x0000001c #define A6XX_RB_DEPTH_CNTL_ZFUNC__SHIFT 2 @@ -3308,7 +3458,7 @@ static inline uint32_t A6XX_RB_DEPTH_CNTL_ZFUNC(enum adreno_compare_func val) return ((val) << A6XX_RB_DEPTH_CNTL_ZFUNC__SHIFT) & A6XX_RB_DEPTH_CNTL_ZFUNC__MASK; } #define A6XX_RB_DEPTH_CNTL_Z_CLAMP_ENABLE 0x00000020 -#define A6XX_RB_DEPTH_CNTL_Z_TEST_ENABLE 0x00000040 +#define A6XX_RB_DEPTH_CNTL_Z_READ_ENABLE 0x00000040 #define A6XX_RB_DEPTH_CNTL_Z_BOUNDS_ENABLE 0x00000080 #define REG_A6XX_RB_DEPTH_BUFFER_INFO 0x00008872 @@ -3819,6 +3969,14 @@ static inline uint32_t A6XX_RB_SAMPLE_COUNT_ADDR(uint32_t val) return ((val) << A6XX_RB_SAMPLE_COUNT_ADDR__SHIFT) & A6XX_RB_SAMPLE_COUNT_ADDR__MASK; } +#define REG_A6XX_RB_UNKNOWN_8A00 0x00008a00 + +#define REG_A6XX_RB_UNKNOWN_8A10 0x00008a10 + +#define REG_A6XX_RB_UNKNOWN_8A20 0x00008a20 + +#define REG_A6XX_RB_UNKNOWN_8A30 0x00008a30 + #define REG_A6XX_RB_2D_BLIT_CNTL 0x00008c00 #define A6XX_RB_2D_BLIT_CNTL_ROTATE__MASK 0x00000007 #define A6XX_RB_2D_BLIT_CNTL_ROTATE__SHIFT 0 @@ -3826,11 +3984,12 @@ static inline uint32_t A6XX_RB_2D_BLIT_CNTL_ROTATE(enum a6xx_rotation val) { return ((val) << A6XX_RB_2D_BLIT_CNTL_ROTATE__SHIFT) & A6XX_RB_2D_BLIT_CNTL_ROTATE__MASK; } -#define A6XX_RB_2D_BLIT_CNTL_UNK3__MASK 0x00000078 -#define A6XX_RB_2D_BLIT_CNTL_UNK3__SHIFT 3 -static inline uint32_t A6XX_RB_2D_BLIT_CNTL_UNK3(uint32_t val) +#define A6XX_RB_2D_BLIT_CNTL_OVERWRITEEN 0x00000008 +#define A6XX_RB_2D_BLIT_CNTL_UNK4__MASK 0x00000070 +#define A6XX_RB_2D_BLIT_CNTL_UNK4__SHIFT 4 +static inline uint32_t A6XX_RB_2D_BLIT_CNTL_UNK4(uint32_t val) { - return ((val) << A6XX_RB_2D_BLIT_CNTL_UNK3__SHIFT) & A6XX_RB_2D_BLIT_CNTL_UNK3__MASK; + return ((val) << A6XX_RB_2D_BLIT_CNTL_UNK4__SHIFT) & A6XX_RB_2D_BLIT_CNTL_UNK4__MASK; } #define A6XX_RB_2D_BLIT_CNTL_SOLID_COLOR 0x00000080 #define A6XX_RB_2D_BLIT_CNTL_COLOR_FORMAT__MASK 0x0000ff00 @@ -3859,11 +4018,11 @@ static inline uint32_t A6XX_RB_2D_BLIT_CNTL_IFMT(enum a6xx_2d_ifmt val) { return ((val) << A6XX_RB_2D_BLIT_CNTL_IFMT__SHIFT) & A6XX_RB_2D_BLIT_CNTL_IFMT__MASK; } -#define A6XX_RB_2D_BLIT_CNTL_UNK29__MASK 0x20000000 -#define A6XX_RB_2D_BLIT_CNTL_UNK29__SHIFT 29 -static inline uint32_t A6XX_RB_2D_BLIT_CNTL_UNK29(uint32_t val) +#define A6XX_RB_2D_BLIT_CNTL_RASTER_MODE__MASK 0x20000000 +#define A6XX_RB_2D_BLIT_CNTL_RASTER_MODE__SHIFT 29 +static inline uint32_t A6XX_RB_2D_BLIT_CNTL_RASTER_MODE(enum a6xx_raster_mode val) { - return ((val) << A6XX_RB_2D_BLIT_CNTL_UNK29__SHIFT) & A6XX_RB_2D_BLIT_CNTL_UNK29__MASK; + return ((val) << A6XX_RB_2D_BLIT_CNTL_RASTER_MODE__SHIFT) & A6XX_RB_2D_BLIT_CNTL_RASTER_MODE__MASK; } #define REG_A6XX_RB_2D_UNKNOWN_8C01 0x00008c01 @@ -3997,11 +4156,17 @@ static inline uint32_t A6XX_RB_2D_DST_FLAGS_PLANE_PITCH(uint32_t val) #define REG_A6XX_RB_ADDR_MODE_CNTL 0x00008e05 #define REG_A6XX_RB_CCU_CNTL 0x00008e07 -#define A6XX_RB_CCU_CNTL_OFFSET__MASK 0xff800000 -#define A6XX_RB_CCU_CNTL_OFFSET__SHIFT 23 -static inline uint32_t A6XX_RB_CCU_CNTL_OFFSET(uint32_t val) +#define A6XX_RB_CCU_CNTL_COLOR_OFFSET__MASK 0xff800000 +#define A6XX_RB_CCU_CNTL_COLOR_OFFSET__SHIFT 23 +static inline uint32_t A6XX_RB_CCU_CNTL_COLOR_OFFSET(uint32_t val) { - return ((val >> 12) << A6XX_RB_CCU_CNTL_OFFSET__SHIFT) & A6XX_RB_CCU_CNTL_OFFSET__MASK; + return ((val >> 12) << A6XX_RB_CCU_CNTL_COLOR_OFFSET__SHIFT) & A6XX_RB_CCU_CNTL_COLOR_OFFSET__MASK; +} +#define A6XX_RB_CCU_CNTL_DEPTH_OFFSET__MASK 0x001ff000 +#define A6XX_RB_CCU_CNTL_DEPTH_OFFSET__SHIFT 12 +static inline uint32_t A6XX_RB_CCU_CNTL_DEPTH_OFFSET(uint32_t val) +{ + return ((val >> 12) << A6XX_RB_CCU_CNTL_DEPTH_OFFSET__SHIFT) & A6XX_RB_CCU_CNTL_DEPTH_OFFSET__MASK; } #define A6XX_RB_CCU_CNTL_GMEM 0x00400000 #define A6XX_RB_CCU_CNTL_UNK2 0x00000004 @@ -4052,7 +4217,13 @@ static inline uint32_t A6XX_RB_UNKNOWN_8E51(uint32_t val) return ((val) << A6XX_RB_UNKNOWN_8E51__SHIFT) & A6XX_RB_UNKNOWN_8E51__MASK; } -#define REG_A6XX_VPC_UNKNOWN_9100 0x00009100 +#define REG_A6XX_VPC_GS_PARAM 0x00009100 +#define A6XX_VPC_GS_PARAM_LINELENGTHLOC__MASK 0x000000ff +#define A6XX_VPC_GS_PARAM_LINELENGTHLOC__SHIFT 0 +static inline uint32_t A6XX_VPC_GS_PARAM_LINELENGTHLOC(uint32_t val) +{ + return ((val) << A6XX_VPC_GS_PARAM_LINELENGTHLOC__SHIFT) & A6XX_VPC_GS_PARAM_LINELENGTHLOC__MASK; +} #define REG_A6XX_VPC_VS_CLIP_CNTL 0x00009101 #define A6XX_VPC_VS_CLIP_CNTL_CLIP_MASK__MASK 0x000000ff @@ -4448,10 +4619,16 @@ static inline uint32_t A6XX_PC_TESS_CNTL_OUTPUT(enum a6xx_tess_output val) #define REG_A6XX_PC_MODE_CNTL 0x00009804 -#define REG_A6XX_PC_UNKNOWN_9805 0x00009805 +#define REG_A6XX_PC_POWER_CNTL 0x00009805 #define REG_A6XX_PC_PRIMID_PASSTHRU 0x00009806 +#define REG_A6XX_PC_SO_STREAM_CNTL 0x00009808 +#define A6XX_PC_SO_STREAM_CNTL_STREAM_ENABLE 0x00008000 + +#define REG_A6XX_PC_DGEN_SU_CONSERVATIVE_RAS_CNTL 0x0000980a +#define A6XX_PC_DGEN_SU_CONSERVATIVE_RAS_CNTL_CONSERVATIVERASEN 0x00000001 + #define REG_A6XX_PC_DRAW_CMD 0x00009840 #define A6XX_PC_DRAW_CMD_STATE_ID__MASK 0x000000ff #define A6XX_PC_DRAW_CMD_STATE_ID__SHIFT 0 @@ -4543,7 +4720,23 @@ static inline uint32_t A6XX_PC_GS_OUT_CNTL_CLIP_MASK(uint32_t val) return ((val) << A6XX_PC_GS_OUT_CNTL_CLIP_MASK__SHIFT) & A6XX_PC_GS_OUT_CNTL_CLIP_MASK__MASK; } -#define REG_A6XX_PC_PRIMITIVE_CNTL_3 0x00009b03 +#define REG_A6XX_PC_HS_OUT_CNTL 0x00009b03 +#define A6XX_PC_HS_OUT_CNTL_STRIDE_IN_VPC__MASK 0x000000ff +#define A6XX_PC_HS_OUT_CNTL_STRIDE_IN_VPC__SHIFT 0 +static inline uint32_t A6XX_PC_HS_OUT_CNTL_STRIDE_IN_VPC(uint32_t val) +{ + return ((val) << A6XX_PC_HS_OUT_CNTL_STRIDE_IN_VPC__SHIFT) & A6XX_PC_HS_OUT_CNTL_STRIDE_IN_VPC__MASK; +} +#define A6XX_PC_HS_OUT_CNTL_PSIZE 0x00000100 +#define A6XX_PC_HS_OUT_CNTL_LAYER 0x00000200 +#define A6XX_PC_HS_OUT_CNTL_VIEW 0x00000400 +#define A6XX_PC_HS_OUT_CNTL_PRIMITIVE_ID 0x00000800 +#define A6XX_PC_HS_OUT_CNTL_CLIP_MASK__MASK 0x00ff0000 +#define A6XX_PC_HS_OUT_CNTL_CLIP_MASK__SHIFT 16 +static inline uint32_t A6XX_PC_HS_OUT_CNTL_CLIP_MASK(uint32_t val) +{ + return ((val) << A6XX_PC_HS_OUT_CNTL_CLIP_MASK__SHIFT) & A6XX_PC_HS_OUT_CNTL_CLIP_MASK__MASK; +} #define REG_A6XX_PC_DS_OUT_CNTL 0x00009b04 #define A6XX_PC_DS_OUT_CNTL_STRIDE_IN_VPC__MASK 0x000000ff @@ -4576,6 +4769,7 @@ static inline uint32_t A6XX_PC_PRIMITIVE_CNTL_5_GS_INVOCATIONS(uint32_t val) { return ((val) << A6XX_PC_PRIMITIVE_CNTL_5_GS_INVOCATIONS__SHIFT) & A6XX_PC_PRIMITIVE_CNTL_5_GS_INVOCATIONS__MASK; } +#define A6XX_PC_PRIMITIVE_CNTL_5_LINELENGTHEN 0x00008000 #define A6XX_PC_PRIMITIVE_CNTL_5_GS_OUTPUT__MASK 0x00030000 #define A6XX_PC_PRIMITIVE_CNTL_5_GS_OUTPUT__SHIFT 16 static inline uint32_t A6XX_PC_PRIMITIVE_CNTL_5_GS_OUTPUT(enum a6xx_tess_output val) @@ -4763,11 +4957,11 @@ static inline uint32_t A6XX_VFD_CONTROL_1_REGID4VIEWID(uint32_t val) } #define REG_A6XX_VFD_CONTROL_2 0x0000a002 -#define A6XX_VFD_CONTROL_2_REGID_HSPATCHID__MASK 0x000000ff -#define A6XX_VFD_CONTROL_2_REGID_HSPATCHID__SHIFT 0 -static inline uint32_t A6XX_VFD_CONTROL_2_REGID_HSPATCHID(uint32_t val) +#define A6XX_VFD_CONTROL_2_REGID_HSRELPATCHID__MASK 0x000000ff +#define A6XX_VFD_CONTROL_2_REGID_HSRELPATCHID__SHIFT 0 +static inline uint32_t A6XX_VFD_CONTROL_2_REGID_HSRELPATCHID(uint32_t val) { - return ((val) << A6XX_VFD_CONTROL_2_REGID_HSPATCHID__SHIFT) & A6XX_VFD_CONTROL_2_REGID_HSPATCHID__MASK; + return ((val) << A6XX_VFD_CONTROL_2_REGID_HSRELPATCHID__SHIFT) & A6XX_VFD_CONTROL_2_REGID_HSRELPATCHID__MASK; } #define A6XX_VFD_CONTROL_2_REGID_INVOCATIONID__MASK 0x0000ff00 #define A6XX_VFD_CONTROL_2_REGID_INVOCATIONID__SHIFT 8 @@ -4777,17 +4971,17 @@ static inline uint32_t A6XX_VFD_CONTROL_2_REGID_INVOCATIONID(uint32_t val) } #define REG_A6XX_VFD_CONTROL_3 0x0000a003 -#define A6XX_VFD_CONTROL_3_UNK0__MASK 0x000000ff -#define A6XX_VFD_CONTROL_3_UNK0__SHIFT 0 -static inline uint32_t A6XX_VFD_CONTROL_3_UNK0(uint32_t val) +#define A6XX_VFD_CONTROL_3_REGID_DSPRIMID__MASK 0x000000ff +#define A6XX_VFD_CONTROL_3_REGID_DSPRIMID__SHIFT 0 +static inline uint32_t A6XX_VFD_CONTROL_3_REGID_DSPRIMID(uint32_t val) { - return ((val) << A6XX_VFD_CONTROL_3_UNK0__SHIFT) & A6XX_VFD_CONTROL_3_UNK0__MASK; + return ((val) << A6XX_VFD_CONTROL_3_REGID_DSPRIMID__SHIFT) & A6XX_VFD_CONTROL_3_REGID_DSPRIMID__MASK; } -#define A6XX_VFD_CONTROL_3_REGID_DSPATCHID__MASK 0x0000ff00 -#define A6XX_VFD_CONTROL_3_REGID_DSPATCHID__SHIFT 8 -static inline uint32_t A6XX_VFD_CONTROL_3_REGID_DSPATCHID(uint32_t val) +#define A6XX_VFD_CONTROL_3_REGID_DSRELPATCHID__MASK 0x0000ff00 +#define A6XX_VFD_CONTROL_3_REGID_DSRELPATCHID__SHIFT 8 +static inline uint32_t A6XX_VFD_CONTROL_3_REGID_DSRELPATCHID(uint32_t val) { - return ((val) << A6XX_VFD_CONTROL_3_REGID_DSPATCHID__SHIFT) & A6XX_VFD_CONTROL_3_REGID_DSPATCHID__MASK; + return ((val) << A6XX_VFD_CONTROL_3_REGID_DSRELPATCHID__SHIFT) & A6XX_VFD_CONTROL_3_REGID_DSRELPATCHID__MASK; } #define A6XX_VFD_CONTROL_3_REGID_TESSX__MASK 0x00ff0000 #define A6XX_VFD_CONTROL_3_REGID_TESSX__SHIFT 16 @@ -4828,9 +5022,12 @@ static inline uint32_t A6XX_VFD_CONTROL_5_UNK8(uint32_t val) #define A6XX_VFD_CONTROL_6_PRIMID_PASSTHRU 0x00000001 #define REG_A6XX_VFD_MODE_CNTL 0x0000a007 -#define A6XX_VFD_MODE_CNTL_BINNING_PASS 0x00000001 -#define A6XX_VFD_MODE_CNTL_UNK1 0x00000002 -#define A6XX_VFD_MODE_CNTL_UNK2 0x00000004 +#define A6XX_VFD_MODE_CNTL_RENDER_MODE__MASK 0x00000007 +#define A6XX_VFD_MODE_CNTL_RENDER_MODE__SHIFT 0 +static inline uint32_t A6XX_VFD_MODE_CNTL_RENDER_MODE(enum a6xx_render_mode val) +{ + return ((val) << A6XX_VFD_MODE_CNTL_RENDER_MODE__SHIFT) & A6XX_VFD_MODE_CNTL_RENDER_MODE__MASK; +} #define REG_A6XX_VFD_MULTIVIEW_CNTL 0x0000a008 #define A6XX_VFD_MULTIVIEW_CNTL_ENABLE 0x00000001 @@ -4913,7 +5110,7 @@ static inline uint32_t A6XX_VFD_DEST_CNTL_INSTR_REGID(uint32_t val) return ((val) << A6XX_VFD_DEST_CNTL_INSTR_REGID__SHIFT) & A6XX_VFD_DEST_CNTL_INSTR_REGID__MASK; } -#define REG_A6XX_SP_UNKNOWN_A0F8 0x0000a0f8 +#define REG_A6XX_VFD_POWER_CNTL 0x0000a0f8 #define REG_A6XX_VFD_ADDR_MODE_CNTL 0x0000a601 @@ -5091,11 +5288,11 @@ static inline uint32_t A6XX_SP_VS_CONFIG_NIBO(uint32_t val) #define REG_A6XX_SP_VS_INSTRLEN 0x0000a824 #define REG_A6XX_SP_VS_PVT_MEM_HW_STACK_OFFSET 0x0000a825 -#define A6XX_SP_VS_PVT_MEM_HW_STACK_OFFSET__MASK 0x0007ffff -#define A6XX_SP_VS_PVT_MEM_HW_STACK_OFFSET__SHIFT 0 -static inline uint32_t A6XX_SP_VS_PVT_MEM_HW_STACK_OFFSET(uint32_t val) +#define A6XX_SP_VS_PVT_MEM_HW_STACK_OFFSET_OFFSET__MASK 0x0007ffff +#define A6XX_SP_VS_PVT_MEM_HW_STACK_OFFSET_OFFSET__SHIFT 0 +static inline uint32_t A6XX_SP_VS_PVT_MEM_HW_STACK_OFFSET_OFFSET(uint32_t val) { - return ((val >> 11) << A6XX_SP_VS_PVT_MEM_HW_STACK_OFFSET__SHIFT) & A6XX_SP_VS_PVT_MEM_HW_STACK_OFFSET__MASK; + return ((val >> 11) << A6XX_SP_VS_PVT_MEM_HW_STACK_OFFSET_OFFSET__SHIFT) & A6XX_SP_VS_PVT_MEM_HW_STACK_OFFSET_OFFSET__MASK; } #define REG_A6XX_SP_HS_CTRL_REG0 0x0000a830 @@ -5201,11 +5398,11 @@ static inline uint32_t A6XX_SP_HS_CONFIG_NIBO(uint32_t val) #define REG_A6XX_SP_HS_INSTRLEN 0x0000a83c #define REG_A6XX_SP_HS_PVT_MEM_HW_STACK_OFFSET 0x0000a83d -#define A6XX_SP_HS_PVT_MEM_HW_STACK_OFFSET__MASK 0x0007ffff -#define A6XX_SP_HS_PVT_MEM_HW_STACK_OFFSET__SHIFT 0 -static inline uint32_t A6XX_SP_HS_PVT_MEM_HW_STACK_OFFSET(uint32_t val) +#define A6XX_SP_HS_PVT_MEM_HW_STACK_OFFSET_OFFSET__MASK 0x0007ffff +#define A6XX_SP_HS_PVT_MEM_HW_STACK_OFFSET_OFFSET__SHIFT 0 +static inline uint32_t A6XX_SP_HS_PVT_MEM_HW_STACK_OFFSET_OFFSET(uint32_t val) { - return ((val >> 11) << A6XX_SP_HS_PVT_MEM_HW_STACK_OFFSET__SHIFT) & A6XX_SP_HS_PVT_MEM_HW_STACK_OFFSET__MASK; + return ((val >> 11) << A6XX_SP_HS_PVT_MEM_HW_STACK_OFFSET_OFFSET__SHIFT) & A6XX_SP_HS_PVT_MEM_HW_STACK_OFFSET_OFFSET__MASK; } #define REG_A6XX_SP_DS_CTRL_REG0 0x0000a840 @@ -5379,11 +5576,11 @@ static inline uint32_t A6XX_SP_DS_CONFIG_NIBO(uint32_t val) #define REG_A6XX_SP_DS_INSTRLEN 0x0000a864 #define REG_A6XX_SP_DS_PVT_MEM_HW_STACK_OFFSET 0x0000a865 -#define A6XX_SP_DS_PVT_MEM_HW_STACK_OFFSET__MASK 0x0007ffff -#define A6XX_SP_DS_PVT_MEM_HW_STACK_OFFSET__SHIFT 0 -static inline uint32_t A6XX_SP_DS_PVT_MEM_HW_STACK_OFFSET(uint32_t val) +#define A6XX_SP_DS_PVT_MEM_HW_STACK_OFFSET_OFFSET__MASK 0x0007ffff +#define A6XX_SP_DS_PVT_MEM_HW_STACK_OFFSET_OFFSET__SHIFT 0 +static inline uint32_t A6XX_SP_DS_PVT_MEM_HW_STACK_OFFSET_OFFSET(uint32_t val) { - return ((val >> 11) << A6XX_SP_DS_PVT_MEM_HW_STACK_OFFSET__SHIFT) & A6XX_SP_DS_PVT_MEM_HW_STACK_OFFSET__MASK; + return ((val >> 11) << A6XX_SP_DS_PVT_MEM_HW_STACK_OFFSET_OFFSET__SHIFT) & A6XX_SP_DS_PVT_MEM_HW_STACK_OFFSET_OFFSET__MASK; } #define REG_A6XX_SP_GS_CTRL_REG0 0x0000a870 @@ -5559,11 +5756,11 @@ static inline uint32_t A6XX_SP_GS_CONFIG_NIBO(uint32_t val) #define REG_A6XX_SP_GS_INSTRLEN 0x0000a895 #define REG_A6XX_SP_GS_PVT_MEM_HW_STACK_OFFSET 0x0000a896 -#define A6XX_SP_GS_PVT_MEM_HW_STACK_OFFSET__MASK 0x0007ffff -#define A6XX_SP_GS_PVT_MEM_HW_STACK_OFFSET__SHIFT 0 -static inline uint32_t A6XX_SP_GS_PVT_MEM_HW_STACK_OFFSET(uint32_t val) +#define A6XX_SP_GS_PVT_MEM_HW_STACK_OFFSET_OFFSET__MASK 0x0007ffff +#define A6XX_SP_GS_PVT_MEM_HW_STACK_OFFSET_OFFSET__SHIFT 0 +static inline uint32_t A6XX_SP_GS_PVT_MEM_HW_STACK_OFFSET_OFFSET(uint32_t val) { - return ((val >> 11) << A6XX_SP_GS_PVT_MEM_HW_STACK_OFFSET__SHIFT) & A6XX_SP_GS_PVT_MEM_HW_STACK_OFFSET__MASK; + return ((val >> 11) << A6XX_SP_GS_PVT_MEM_HW_STACK_OFFSET_OFFSET__SHIFT) & A6XX_SP_GS_PVT_MEM_HW_STACK_OFFSET_OFFSET__MASK; } #define REG_A6XX_SP_VS_TEX_SAMP 0x0000a8a0 @@ -5926,11 +6123,11 @@ static inline uint32_t A6XX_SP_FS_BINDLESS_PREFETCH_CMD_TEX_ID(uint32_t val) #define REG_A6XX_SP_UNKNOWN_A9A8 0x0000a9a8 #define REG_A6XX_SP_FS_PVT_MEM_HW_STACK_OFFSET 0x0000a9a9 -#define A6XX_SP_FS_PVT_MEM_HW_STACK_OFFSET__MASK 0x0007ffff -#define A6XX_SP_FS_PVT_MEM_HW_STACK_OFFSET__SHIFT 0 -static inline uint32_t A6XX_SP_FS_PVT_MEM_HW_STACK_OFFSET(uint32_t val) +#define A6XX_SP_FS_PVT_MEM_HW_STACK_OFFSET_OFFSET__MASK 0x0007ffff +#define A6XX_SP_FS_PVT_MEM_HW_STACK_OFFSET_OFFSET__SHIFT 0 +static inline uint32_t A6XX_SP_FS_PVT_MEM_HW_STACK_OFFSET_OFFSET(uint32_t val) { - return ((val >> 11) << A6XX_SP_FS_PVT_MEM_HW_STACK_OFFSET__SHIFT) & A6XX_SP_FS_PVT_MEM_HW_STACK_OFFSET__MASK; + return ((val >> 11) << A6XX_SP_FS_PVT_MEM_HW_STACK_OFFSET_OFFSET__SHIFT) & A6XX_SP_FS_PVT_MEM_HW_STACK_OFFSET_OFFSET__MASK; } #define REG_A6XX_SP_CS_CTRL_REG0 0x0000a9b0 @@ -6053,12 +6250,54 @@ static inline uint32_t A6XX_SP_CS_CONFIG_NIBO(uint32_t val) #define REG_A6XX_SP_CS_INSTRLEN 0x0000a9bc #define REG_A6XX_SP_CS_PVT_MEM_HW_STACK_OFFSET 0x0000a9bd -#define A6XX_SP_CS_PVT_MEM_HW_STACK_OFFSET__MASK 0x0007ffff -#define A6XX_SP_CS_PVT_MEM_HW_STACK_OFFSET__SHIFT 0 -static inline uint32_t A6XX_SP_CS_PVT_MEM_HW_STACK_OFFSET(uint32_t val) +#define A6XX_SP_CS_PVT_MEM_HW_STACK_OFFSET_OFFSET__MASK 0x0007ffff +#define A6XX_SP_CS_PVT_MEM_HW_STACK_OFFSET_OFFSET__SHIFT 0 +static inline uint32_t A6XX_SP_CS_PVT_MEM_HW_STACK_OFFSET_OFFSET(uint32_t val) +{ + return ((val >> 11) << A6XX_SP_CS_PVT_MEM_HW_STACK_OFFSET_OFFSET__SHIFT) & A6XX_SP_CS_PVT_MEM_HW_STACK_OFFSET_OFFSET__MASK; +} + +#define REG_A6XX_SP_CS_CNTL_0 0x0000a9c2 +#define A6XX_SP_CS_CNTL_0_WGIDCONSTID__MASK 0x000000ff +#define A6XX_SP_CS_CNTL_0_WGIDCONSTID__SHIFT 0 +static inline uint32_t A6XX_SP_CS_CNTL_0_WGIDCONSTID(uint32_t val) +{ + return ((val) << A6XX_SP_CS_CNTL_0_WGIDCONSTID__SHIFT) & A6XX_SP_CS_CNTL_0_WGIDCONSTID__MASK; +} +#define A6XX_SP_CS_CNTL_0_WGSIZECONSTID__MASK 0x0000ff00 +#define A6XX_SP_CS_CNTL_0_WGSIZECONSTID__SHIFT 8 +static inline uint32_t A6XX_SP_CS_CNTL_0_WGSIZECONSTID(uint32_t val) +{ + return ((val) << A6XX_SP_CS_CNTL_0_WGSIZECONSTID__SHIFT) & A6XX_SP_CS_CNTL_0_WGSIZECONSTID__MASK; +} +#define A6XX_SP_CS_CNTL_0_WGOFFSETCONSTID__MASK 0x00ff0000 +#define A6XX_SP_CS_CNTL_0_WGOFFSETCONSTID__SHIFT 16 +static inline uint32_t A6XX_SP_CS_CNTL_0_WGOFFSETCONSTID(uint32_t val) { - return ((val >> 11) << A6XX_SP_CS_PVT_MEM_HW_STACK_OFFSET__SHIFT) & A6XX_SP_CS_PVT_MEM_HW_STACK_OFFSET__MASK; + return ((val) << A6XX_SP_CS_CNTL_0_WGOFFSETCONSTID__SHIFT) & A6XX_SP_CS_CNTL_0_WGOFFSETCONSTID__MASK; } +#define A6XX_SP_CS_CNTL_0_LOCALIDREGID__MASK 0xff000000 +#define A6XX_SP_CS_CNTL_0_LOCALIDREGID__SHIFT 24 +static inline uint32_t A6XX_SP_CS_CNTL_0_LOCALIDREGID(uint32_t val) +{ + return ((val) << A6XX_SP_CS_CNTL_0_LOCALIDREGID__SHIFT) & A6XX_SP_CS_CNTL_0_LOCALIDREGID__MASK; +} + +#define REG_A6XX_SP_CS_CNTL_1 0x0000a9c3 +#define A6XX_SP_CS_CNTL_1_LINEARLOCALIDREGID__MASK 0x000000ff +#define A6XX_SP_CS_CNTL_1_LINEARLOCALIDREGID__SHIFT 0 +static inline uint32_t A6XX_SP_CS_CNTL_1_LINEARLOCALIDREGID(uint32_t val) +{ + return ((val) << A6XX_SP_CS_CNTL_1_LINEARLOCALIDREGID__SHIFT) & A6XX_SP_CS_CNTL_1_LINEARLOCALIDREGID__MASK; +} +#define A6XX_SP_CS_CNTL_1_SINGLE_SP_CORE 0x00000100 +#define A6XX_SP_CS_CNTL_1_THREADSIZE__MASK 0x00000200 +#define A6XX_SP_CS_CNTL_1_THREADSIZE__SHIFT 9 +static inline uint32_t A6XX_SP_CS_CNTL_1_THREADSIZE(enum a6xx_threadsize val) +{ + return ((val) << A6XX_SP_CS_CNTL_1_THREADSIZE__SHIFT) & A6XX_SP_CS_CNTL_1_THREADSIZE__MASK; +} +#define A6XX_SP_CS_CNTL_1_THREADSIZE_SCALAR 0x00000400 #define REG_A6XX_SP_FS_TEX_SAMP 0x0000a9e0 #define A6XX_SP_FS_TEX_SAMP__MASK 0xffffffff @@ -6108,8 +6347,12 @@ static inline uint32_t A6XX_SP_CS_IBO(uint32_t val) #define REG_A6XX_SP_MODE_CONTROL 0x0000ab00 #define A6XX_SP_MODE_CONTROL_CONSTANT_DEMOTION_ENABLE 0x00000001 -#define A6XX_SP_MODE_CONTROL_UNK1 0x00000002 -#define A6XX_SP_MODE_CONTROL_UNK2 0x00000004 +#define A6XX_SP_MODE_CONTROL_ISAMMODE__MASK 0x00000006 +#define A6XX_SP_MODE_CONTROL_ISAMMODE__SHIFT 1 +static inline uint32_t A6XX_SP_MODE_CONTROL_ISAMMODE(enum a6xx_isam_mode val) +{ + return ((val) << A6XX_SP_MODE_CONTROL_ISAMMODE__SHIFT) & A6XX_SP_MODE_CONTROL_ISAMMODE__MASK; +} #define A6XX_SP_MODE_CONTROL_SHARED_CONSTS_ENABLE 0x00000008 #define REG_A6XX_SP_FS_CONFIG 0x0000ab04 @@ -6177,7 +6420,7 @@ static inline uint32_t A6XX_SP_2D_DST_FORMAT_MASK(uint32_t val) #define REG_A6XX_SP_NC_MODE_CNTL 0x0000ae02 -#define REG_A6XX_SP_UNKNOWN_AE03 0x0000ae03 +#define REG_A6XX_SP_CHICKEN_BITS 0x0000ae03 #define REG_A6XX_SP_FLOAT_CNTL 0x0000ae04 #define A6XX_SP_FLOAT_CNTL_F16_NO_INF 0x00000008 @@ -6192,6 +6435,8 @@ static inline uint32_t A6XX_SP_2D_DST_FORMAT_MASK(uint32_t val) static inline uint32_t REG_A6XX_SP_PERFCTR_SP_SEL(uint32_t i0) { return 0x0000ae10 + 0x1*i0; } +#define REG_A6XX_SP_CONTEXT_SWITCH_GFX_PREEMPTION_SAFE_MODE 0x0000be22 + #define REG_A6XX_SP_PS_TP_BORDER_COLOR_BASE_ADDR 0x0000b180 #define A6XX_SP_PS_TP_BORDER_COLOR_BASE_ADDR__MASK 0xffffffff #define A6XX_SP_PS_TP_BORDER_COLOR_BASE_ADDR__SHIFT 0 @@ -6357,7 +6602,19 @@ static inline uint32_t A6XX_SP_TP_WINDOW_OFFSET_Y(uint32_t val) return ((val) << A6XX_SP_TP_WINDOW_OFFSET_Y__SHIFT) & A6XX_SP_TP_WINDOW_OFFSET_Y__MASK; } -#define REG_A6XX_SP_TP_UNKNOWN_B309 0x0000b309 +#define REG_A6XX_SP_TP_MODE_CNTL 0x0000b309 +#define A6XX_SP_TP_MODE_CNTL_ISAMMODE__MASK 0x00000003 +#define A6XX_SP_TP_MODE_CNTL_ISAMMODE__SHIFT 0 +static inline uint32_t A6XX_SP_TP_MODE_CNTL_ISAMMODE(enum a6xx_isam_mode val) +{ + return ((val) << A6XX_SP_TP_MODE_CNTL_ISAMMODE__SHIFT) & A6XX_SP_TP_MODE_CNTL_ISAMMODE__MASK; +} +#define A6XX_SP_TP_MODE_CNTL_UNK3__MASK 0x000000fc +#define A6XX_SP_TP_MODE_CNTL_UNK3__SHIFT 2 +static inline uint32_t A6XX_SP_TP_MODE_CNTL_UNK3(uint32_t val) +{ + return ((val) << A6XX_SP_TP_MODE_CNTL_UNK3__SHIFT) & A6XX_SP_TP_MODE_CNTL_UNK3__MASK; +} #define REG_A6XX_SP_PS_2D_SRC_INFO 0x0000b4c0 #define A6XX_SP_PS_2D_SRC_INFO_COLOR_FORMAT__MASK 0x000000ff @@ -6499,7 +6756,7 @@ static inline uint32_t A6XX_SP_WINDOW_OFFSET_Y(uint32_t val) return ((val) << A6XX_SP_WINDOW_OFFSET_Y__SHIFT) & A6XX_SP_WINDOW_OFFSET_Y__MASK; } -#define REG_A6XX_TPL1_UNKNOWN_B600 0x0000b600 +#define REG_A6XX_TPL1_DBG_ECO_CNTL 0x0000b600 #define REG_A6XX_TPL1_ADDR_MODE_CNTL 0x0000b601 @@ -6687,17 +6944,17 @@ static inline uint32_t A6XX_HLSQ_CONTROL_4_REG_ZWCOORDREGID(uint32_t val) } #define REG_A6XX_HLSQ_CONTROL_5_REG 0x0000b986 -#define A6XX_HLSQ_CONTROL_5_REG_UNK0__MASK 0x000000ff -#define A6XX_HLSQ_CONTROL_5_REG_UNK0__SHIFT 0 -static inline uint32_t A6XX_HLSQ_CONTROL_5_REG_UNK0(uint32_t val) +#define A6XX_HLSQ_CONTROL_5_REG_LINELENGTHREGID__MASK 0x000000ff +#define A6XX_HLSQ_CONTROL_5_REG_LINELENGTHREGID__SHIFT 0 +static inline uint32_t A6XX_HLSQ_CONTROL_5_REG_LINELENGTHREGID(uint32_t val) { - return ((val) << A6XX_HLSQ_CONTROL_5_REG_UNK0__SHIFT) & A6XX_HLSQ_CONTROL_5_REG_UNK0__MASK; + return ((val) << A6XX_HLSQ_CONTROL_5_REG_LINELENGTHREGID__SHIFT) & A6XX_HLSQ_CONTROL_5_REG_LINELENGTHREGID__MASK; } -#define A6XX_HLSQ_CONTROL_5_REG_UNK8__MASK 0x0000ff00 -#define A6XX_HLSQ_CONTROL_5_REG_UNK8__SHIFT 8 -static inline uint32_t A6XX_HLSQ_CONTROL_5_REG_UNK8(uint32_t val) +#define A6XX_HLSQ_CONTROL_5_REG_FOVEATIONQUALITYREGID__MASK 0x0000ff00 +#define A6XX_HLSQ_CONTROL_5_REG_FOVEATIONQUALITYREGID__SHIFT 8 +static inline uint32_t A6XX_HLSQ_CONTROL_5_REG_FOVEATIONQUALITYREGID(uint32_t val) { - return ((val) << A6XX_HLSQ_CONTROL_5_REG_UNK8__SHIFT) & A6XX_HLSQ_CONTROL_5_REG_UNK8__MASK; + return ((val) << A6XX_HLSQ_CONTROL_5_REG_FOVEATIONQUALITYREGID__SHIFT) & A6XX_HLSQ_CONTROL_5_REG_FOVEATIONQUALITYREGID__MASK; } #define REG_A6XX_HLSQ_CS_CNTL 0x0000b987 @@ -6847,6 +7104,16 @@ static inline uint32_t REG_A6XX_HLSQ_CS_BINDLESS_BASE(uint32_t i0) { return 0x00 static inline uint32_t REG_A6XX_HLSQ_CS_BINDLESS_BASE_ADDR(uint32_t i0) { return 0x0000b9c0 + 0x2*i0; } +#define REG_A6XX_HLSQ_CS_UNKNOWN_B9D0 0x0000b9d0 +#define A6XX_HLSQ_CS_UNKNOWN_B9D0_SHARED_SIZE__MASK 0x0000001f +#define A6XX_HLSQ_CS_UNKNOWN_B9D0_SHARED_SIZE__SHIFT 0 +static inline uint32_t A6XX_HLSQ_CS_UNKNOWN_B9D0_SHARED_SIZE(uint32_t val) +{ + return ((val) << A6XX_HLSQ_CS_UNKNOWN_B9D0_SHARED_SIZE__SHIFT) & A6XX_HLSQ_CS_UNKNOWN_B9D0_SHARED_SIZE__MASK; +} +#define A6XX_HLSQ_CS_UNKNOWN_B9D0_UNK5 0x00000020 +#define A6XX_HLSQ_CS_UNKNOWN_B9D0_UNK6 0x00000040 + #define REG_A6XX_HLSQ_DRAW_CMD 0x0000bb00 #define A6XX_HLSQ_DRAW_CMD_STATE_ID__MASK 0x000000ff #define A6XX_HLSQ_DRAW_CMD_STATE_ID__SHIFT 0 @@ -6943,6 +7210,8 @@ static inline uint32_t A6XX_HLSQ_2D_EVENT_CMD_EVENT(enum vgt_event_type val) static inline uint32_t REG_A6XX_HLSQ_PERFCTR_HLSQ_SEL(uint32_t i0) { return 0x0000be10 + 0x1*i0; } +#define REG_A6XX_HLSQ_CONTEXT_SWITCH_GFX_PREEMPTION_SAFE_MODE 0x0000be22 + #define REG_A6XX_CP_EVENT_START 0x0000d600 #define A6XX_CP_EVENT_START_STATE_ID__MASK 0x000000ff #define A6XX_CP_EVENT_START_STATE_ID__SHIFT 0 @@ -7021,7 +7290,7 @@ static inline uint32_t A6XX_TEX_SAMP_0_LOD_BIAS(float val) } #define REG_A6XX_TEX_SAMP_1 0x00000001 -#define A6XX_TEX_SAMP_1_UNK0 0x00000001 +#define A6XX_TEX_SAMP_1_CLAMPENABLE 0x00000001 #define A6XX_TEX_SAMP_1_COMPARE_FUNC__MASK 0x0000000e #define A6XX_TEX_SAMP_1_COMPARE_FUNC__SHIFT 1 static inline uint32_t A6XX_TEX_SAMP_1_COMPARE_FUNC(enum adreno_compare_func val) @@ -7135,7 +7404,7 @@ static inline uint32_t A6XX_TEX_CONST_1_HEIGHT(uint32_t val) } #define REG_A6XX_TEX_CONST_2 0x00000002 -#define A6XX_TEX_CONST_2_UNK4 0x00000010 +#define A6XX_TEX_CONST_2_BUFFER 0x00000010 #define A6XX_TEX_CONST_2_PITCHALIGN__MASK 0x0000000f #define A6XX_TEX_CONST_2_PITCHALIGN__SHIFT 0 static inline uint32_t A6XX_TEX_CONST_2_PITCHALIGN(uint32_t val) @@ -7148,13 +7417,12 @@ static inline uint32_t A6XX_TEX_CONST_2_PITCH(uint32_t val) { return ((val) << A6XX_TEX_CONST_2_PITCH__SHIFT) & A6XX_TEX_CONST_2_PITCH__MASK; } -#define A6XX_TEX_CONST_2_TYPE__MASK 0x60000000 +#define A6XX_TEX_CONST_2_TYPE__MASK 0xe0000000 #define A6XX_TEX_CONST_2_TYPE__SHIFT 29 static inline uint32_t A6XX_TEX_CONST_2_TYPE(enum a6xx_tex_type val) { return ((val) << A6XX_TEX_CONST_2_TYPE__SHIFT) & A6XX_TEX_CONST_2_TYPE__MASK; } -#define A6XX_TEX_CONST_2_UNK31 0x80000000 #define REG_A6XX_TEX_CONST_3 0x00000003 #define A6XX_TEX_CONST_3_ARRAY_PITCH__MASK 0x00003fff @@ -7256,104 +7524,6 @@ static inline uint32_t A6XX_TEX_CONST_10_FLAG_BUFFER_LOGH(uint32_t val) #define REG_A6XX_TEX_CONST_15 0x0000000f -#define REG_A6XX_IBO_0 0x00000000 -#define A6XX_IBO_0_TILE_MODE__MASK 0x00000003 -#define A6XX_IBO_0_TILE_MODE__SHIFT 0 -static inline uint32_t A6XX_IBO_0_TILE_MODE(enum a6xx_tile_mode val) -{ - return ((val) << A6XX_IBO_0_TILE_MODE__SHIFT) & A6XX_IBO_0_TILE_MODE__MASK; -} -#define A6XX_IBO_0_FMT__MASK 0x3fc00000 -#define A6XX_IBO_0_FMT__SHIFT 22 -static inline uint32_t A6XX_IBO_0_FMT(enum a6xx_format val) -{ - return ((val) << A6XX_IBO_0_FMT__SHIFT) & A6XX_IBO_0_FMT__MASK; -} - -#define REG_A6XX_IBO_1 0x00000001 -#define A6XX_IBO_1_WIDTH__MASK 0x00007fff -#define A6XX_IBO_1_WIDTH__SHIFT 0 -static inline uint32_t A6XX_IBO_1_WIDTH(uint32_t val) -{ - return ((val) << A6XX_IBO_1_WIDTH__SHIFT) & A6XX_IBO_1_WIDTH__MASK; -} -#define A6XX_IBO_1_HEIGHT__MASK 0x3fff8000 -#define A6XX_IBO_1_HEIGHT__SHIFT 15 -static inline uint32_t A6XX_IBO_1_HEIGHT(uint32_t val) -{ - return ((val) << A6XX_IBO_1_HEIGHT__SHIFT) & A6XX_IBO_1_HEIGHT__MASK; -} - -#define REG_A6XX_IBO_2 0x00000002 -#define A6XX_IBO_2_UNK4 0x00000010 -#define A6XX_IBO_2_PITCH__MASK 0x1fffff80 -#define A6XX_IBO_2_PITCH__SHIFT 7 -static inline uint32_t A6XX_IBO_2_PITCH(uint32_t val) -{ - return ((val) << A6XX_IBO_2_PITCH__SHIFT) & A6XX_IBO_2_PITCH__MASK; -} -#define A6XX_IBO_2_TYPE__MASK 0x60000000 -#define A6XX_IBO_2_TYPE__SHIFT 29 -static inline uint32_t A6XX_IBO_2_TYPE(enum a6xx_tex_type val) -{ - return ((val) << A6XX_IBO_2_TYPE__SHIFT) & A6XX_IBO_2_TYPE__MASK; -} -#define A6XX_IBO_2_UNK31 0x80000000 - -#define REG_A6XX_IBO_3 0x00000003 -#define A6XX_IBO_3_ARRAY_PITCH__MASK 0x00003fff -#define A6XX_IBO_3_ARRAY_PITCH__SHIFT 0 -static inline uint32_t A6XX_IBO_3_ARRAY_PITCH(uint32_t val) -{ - return ((val >> 12) << A6XX_IBO_3_ARRAY_PITCH__SHIFT) & A6XX_IBO_3_ARRAY_PITCH__MASK; -} -#define A6XX_IBO_3_UNK27 0x08000000 -#define A6XX_IBO_3_FLAG 0x10000000 - -#define REG_A6XX_IBO_4 0x00000004 -#define A6XX_IBO_4_BASE_LO__MASK 0xffffffff -#define A6XX_IBO_4_BASE_LO__SHIFT 0 -static inline uint32_t A6XX_IBO_4_BASE_LO(uint32_t val) -{ - return ((val) << A6XX_IBO_4_BASE_LO__SHIFT) & A6XX_IBO_4_BASE_LO__MASK; -} - -#define REG_A6XX_IBO_5 0x00000005 -#define A6XX_IBO_5_BASE_HI__MASK 0x0001ffff -#define A6XX_IBO_5_BASE_HI__SHIFT 0 -static inline uint32_t A6XX_IBO_5_BASE_HI(uint32_t val) -{ - return ((val) << A6XX_IBO_5_BASE_HI__SHIFT) & A6XX_IBO_5_BASE_HI__MASK; -} -#define A6XX_IBO_5_DEPTH__MASK 0x3ffe0000 -#define A6XX_IBO_5_DEPTH__SHIFT 17 -static inline uint32_t A6XX_IBO_5_DEPTH(uint32_t val) -{ - return ((val) << A6XX_IBO_5_DEPTH__SHIFT) & A6XX_IBO_5_DEPTH__MASK; -} - -#define REG_A6XX_IBO_6 0x00000006 - -#define REG_A6XX_IBO_7 0x00000007 - -#define REG_A6XX_IBO_8 0x00000008 - -#define REG_A6XX_IBO_9 0x00000009 -#define A6XX_IBO_9_FLAG_BUFFER_ARRAY_PITCH__MASK 0x0001ffff -#define A6XX_IBO_9_FLAG_BUFFER_ARRAY_PITCH__SHIFT 0 -static inline uint32_t A6XX_IBO_9_FLAG_BUFFER_ARRAY_PITCH(uint32_t val) -{ - return ((val >> 4) << A6XX_IBO_9_FLAG_BUFFER_ARRAY_PITCH__SHIFT) & A6XX_IBO_9_FLAG_BUFFER_ARRAY_PITCH__MASK; -} - -#define REG_A6XX_IBO_10 0x0000000a -#define A6XX_IBO_10_FLAG_BUFFER_PITCH__MASK 0x0000007f -#define A6XX_IBO_10_FLAG_BUFFER_PITCH__SHIFT 0 -static inline uint32_t A6XX_IBO_10_FLAG_BUFFER_PITCH(uint32_t val) -{ - return ((val >> 6) << A6XX_IBO_10_FLAG_BUFFER_PITCH__SHIFT) & A6XX_IBO_10_FLAG_BUFFER_PITCH__MASK; -} - #define REG_A6XX_UBO_0 0x00000000 #define A6XX_UBO_0_BASE_LO__MASK 0xffffffff #define A6XX_UBO_0_BASE_LO__SHIFT 0 diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h index 811589215834..4a3230978c0e 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h @@ -8,19 +8,19 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14386 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 67699 bytes, from 2021-05-31 20:21:57) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84226 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a4xx.xml ( 112551 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a5xx.xml ( 150713 bytes, from 2021-06-10 22:34:02) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx.xml ( 180049 bytes, from 2021-06-02 21:44:19) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-05-27 20:22:36) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-05-27 20:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-06-21 15:24:24) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14609 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 69086 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84231 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a4xx.xml ( 113358 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a5xx.xml ( 149512 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx.xml ( 184954 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-07-22 15:21:56) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 17cfad6424db..83c31b2ad865 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -10,7 +10,6 @@ #include <linux/bitfield.h> #include <linux/devfreq.h> -#include <linux/nvmem-consumer.h> #include <linux/soc/qcom/llcc-qcom.h> #define GPU_PAS_ID 13 @@ -102,6 +101,7 @@ static void get_stats_counter(struct msm_ringbuffer *ring, u32 counter, static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, struct msm_ringbuffer *ring, struct msm_file_private *ctx) { + bool sysprof = refcount_read(&a6xx_gpu->base.base.sysprof_active) > 1; phys_addr_t ttbr; u32 asid; u64 memptr = rbmemptr(ring, ttbr0); @@ -112,6 +112,15 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid)) return; + if (!sysprof) { + /* Turn off protected mode to write to special registers */ + OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 0); + + OUT_PKT4(ring, REG_A6XX_RBBM_PERFCTR_SRAM_INIT_CMD, 1); + OUT_RING(ring, 1); + } + /* Execute the table update */ OUT_PKT7(ring, CP_SMMU_TABLE_UPDATE, 4); OUT_RING(ring, CP_SMMU_TABLE_UPDATE_0_TTBR0_LO(lower_32_bits(ttbr))); @@ -138,6 +147,25 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, OUT_PKT7(ring, CP_EVENT_WRITE, 1); OUT_RING(ring, 0x31); + + if (!sysprof) { + /* + * Wait for SRAM clear after the pgtable update, so the + * two can happen in parallel: + */ + OUT_PKT7(ring, CP_WAIT_REG_MEM, 6); + OUT_RING(ring, CP_WAIT_REG_MEM_0_FUNCTION(WRITE_EQ)); + OUT_RING(ring, CP_WAIT_REG_MEM_1_POLL_ADDR_LO( + REG_A6XX_RBBM_PERFCTR_SRAM_INIT_STATUS)); + OUT_RING(ring, CP_WAIT_REG_MEM_2_POLL_ADDR_HI(0)); + OUT_RING(ring, CP_WAIT_REG_MEM_3_REF(0x1)); + OUT_RING(ring, CP_WAIT_REG_MEM_4_MASK(0x1)); + OUT_RING(ring, CP_WAIT_REG_MEM_5_DELAY_LOOP_CYCLES(0)); + + /* Re-enable protected mode: */ + OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 1); + } } static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) @@ -655,19 +683,23 @@ static void a6xx_set_cp_protect(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); const u32 *regs = a6xx_protect; - unsigned i, count = ARRAY_SIZE(a6xx_protect), count_max = 32; - - BUILD_BUG_ON(ARRAY_SIZE(a6xx_protect) > 32); - BUILD_BUG_ON(ARRAY_SIZE(a650_protect) > 48); + unsigned i, count, count_max; if (adreno_is_a650(adreno_gpu)) { regs = a650_protect; count = ARRAY_SIZE(a650_protect); count_max = 48; + BUILD_BUG_ON(ARRAY_SIZE(a650_protect) > 48); } else if (adreno_is_a660_family(adreno_gpu)) { regs = a660_protect; count = ARRAY_SIZE(a660_protect); count_max = 48; + BUILD_BUG_ON(ARRAY_SIZE(a660_protect) > 48); + } else { + regs = a6xx_protect; + count = ARRAY_SIZE(a6xx_protect); + count_max = 32; + BUILD_BUG_ON(ARRAY_SIZE(a6xx_protect) > 32); } /* @@ -1506,7 +1538,7 @@ static void a6xx_llc_slices_init(struct platform_device *pdev, if (a6xx_gpu->have_mmu500) a6xx_gpu->llc_mmio = NULL; else - a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem", "gpu_cx"); + a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem"); a6xx_gpu->llc_slice = llcc_slice_getd(LLCC_GPU); a6xx_gpu->htw_llc_slice = llcc_slice_getd(LLCC_GPUHTW); @@ -1736,6 +1768,18 @@ static u32 a618_get_speed_bin(u32 fuse) return UINT_MAX; } +static u32 adreno_7c3_get_speed_bin(u32 fuse) +{ + if (fuse == 0) + return 0; + else if (fuse == 117) + return 0; + else if (fuse == 190) + return 1; + + return UINT_MAX; +} + static u32 fuse_to_supp_hw(struct device *dev, struct adreno_rev rev, u32 fuse) { u32 val = UINT_MAX; @@ -1743,6 +1787,9 @@ static u32 fuse_to_supp_hw(struct device *dev, struct adreno_rev rev, u32 fuse) if (adreno_cmp_rev(ADRENO_REV(6, 1, 8, ANY_ID), rev)) val = a618_get_speed_bin(fuse); + if (adreno_cmp_rev(ADRENO_REV(6, 3, 5, ANY_ID), rev)) + val = adreno_7c3_get_speed_bin(fuse); + if (val == UINT_MAX) { DRM_DEV_ERROR(dev, "missing support for speed-bin: %u. Some OPPs may not be supported by hardware", @@ -1759,7 +1806,7 @@ static int a6xx_set_supported_hw(struct device *dev, struct adreno_rev rev) u32 speedbin; int ret; - ret = nvmem_cell_read_variable_le_u32(dev, "speed_bin", &speedbin); + ret = adreno_read_speedbin(dev, &speedbin); /* * -ENOENT means that the platform doesn't support speedbin which is * fine @@ -1786,6 +1833,7 @@ done: static const struct adreno_gpu_funcs funcs = { .base = { .get_param = adreno_get_param, + .set_param = adreno_set_param, .hw_init = a6xx_hw_init, .pm_suspend = a6xx_pm_suspend, .pm_resume = a6xx_pm_resume, diff --git a/drivers/gpu/drm/msm/adreno/adreno_common.xml.h b/drivers/gpu/drm/msm/adreno/adreno_common.xml.h index c9389d9fb599..abb037ccc02b 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_common.xml.h +++ b/drivers/gpu/drm/msm/adreno/adreno_common.xml.h @@ -8,19 +8,19 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14386 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 67699 bytes, from 2021-05-31 20:21:57) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84226 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a4xx.xml ( 112551 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a5xx.xml ( 150713 bytes, from 2021-06-10 22:34:02) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx.xml ( 180049 bytes, from 2021-06-02 21:44:19) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-05-27 20:22:36) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-05-27 20:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-06-21 15:24:24) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14609 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 69086 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84231 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a4xx.xml ( 113358 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a5xx.xml ( 149512 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx.xml ( 184954 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-07-22 15:21:56) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) @@ -205,6 +205,11 @@ enum a5xx_address_mode { ADDR_64B = 1, }; +enum a5xx_line_mode { + BRESENHAM = 0, + RECTANGULAR = 1, +}; + #define REG_AXXX_CP_RB_BASE 0x000001c0 #define REG_AXXX_CP_RB_CNTL 0x000001c1 diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index fb261930ad1c..89cfd84760d7 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -318,7 +318,6 @@ static const struct adreno_info gpulist[] = { .hwcg = a660_hwcg, }, { .rev = ADRENO_REV(6, 3, 5, ANY_ID), - .name = "Adreno 7c Gen 3", .fw = { [ADRENO_FW_SQE] = "a660_sqe.fw", [ADRENO_FW_GMU] = "a660_gmu.bin", diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index f33cfa4ef1c8..9efc84929be0 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -14,6 +14,7 @@ #include <linux/pm_opp.h> #include <linux/slab.h> #include <linux/soc/qcom/mdt_loader.h> +#include <linux/nvmem-consumer.h> #include <soc/qcom/ocmem.h> #include "adreno_gpu.h" #include "a6xx_gpu.h" @@ -227,7 +228,8 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu, return aspace; } -int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value) +int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx, + uint32_t param, uint64_t *value) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -242,10 +244,12 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value) *value = !adreno_is_a650_family(adreno_gpu) ? 0x100000 : 0; return 0; case MSM_PARAM_CHIP_ID: - *value = adreno_gpu->rev.patchid | - (adreno_gpu->rev.minor << 8) | - (adreno_gpu->rev.major << 16) | - (adreno_gpu->rev.core << 24); + *value = (uint64_t)adreno_gpu->rev.patchid | + ((uint64_t)adreno_gpu->rev.minor << 8) | + ((uint64_t)adreno_gpu->rev.major << 16) | + ((uint64_t)adreno_gpu->rev.core << 24); + if (!adreno_gpu->info->revn) + *value |= ((uint64_t) adreno_gpu->speedbin) << 32; return 0; case MSM_PARAM_MAX_FREQ: *value = adreno_gpu->base.fast_rate; @@ -268,7 +272,7 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value) *value = 0; return 0; case MSM_PARAM_FAULTS: - *value = gpu->global_faults; + *value = gpu->global_faults + ctx->aspace->faults; return 0; case MSM_PARAM_SUSPENDS: *value = gpu->suspend_count; @@ -279,6 +283,20 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value) } } +int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx, + uint32_t param, uint64_t value) +{ + switch (param) { + case MSM_PARAM_SYSPROF: + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + return msm_file_private_set_sysprof(ctx, gpu, value); + default: + DBG("%s: invalid param: %u", gpu->name, param); + return -EINVAL; + } +} + const struct firmware * adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname) { @@ -921,6 +939,11 @@ void adreno_gpu_ocmem_cleanup(struct adreno_ocmem *adreno_ocmem) adreno_ocmem->hdl); } +int adreno_read_speedbin(struct device *dev, u32 *speedbin) +{ + return nvmem_cell_read_variable_le_u32(dev, "speed_bin", speedbin); +} + int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, struct adreno_gpu *adreno_gpu, const struct adreno_gpu_funcs *funcs, int nr_rings) @@ -929,12 +952,28 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, struct adreno_platform_config *config = dev->platform_data; struct msm_gpu_config adreno_gpu_config = { 0 }; struct msm_gpu *gpu = &adreno_gpu->base; + struct adreno_rev *rev = &config->rev; + const char *gpu_name; + u32 speedbin; adreno_gpu->funcs = funcs; adreno_gpu->info = adreno_info(config->rev); adreno_gpu->gmem = adreno_gpu->info->gmem; adreno_gpu->revn = adreno_gpu->info->revn; - adreno_gpu->rev = config->rev; + adreno_gpu->rev = *rev; + + if (adreno_read_speedbin(dev, &speedbin) || !speedbin) + speedbin = 0xffff; + adreno_gpu->speedbin = (uint16_t) (0xffff & speedbin); + + gpu_name = adreno_gpu->info->name; + if (!gpu_name) { + gpu_name = devm_kasprintf(dev, GFP_KERNEL, "%d.%d.%d.%d", + rev->core, rev->major, rev->minor, + rev->patchid); + if (!gpu_name) + return -ENOMEM; + } adreno_gpu_config.ioname = "kgsl_3d0_reg_memory"; @@ -948,7 +987,7 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, pm_runtime_enable(dev); return msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base, - adreno_gpu->info->name, &adreno_gpu_config); + gpu_name, &adreno_gpu_config); } void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu) diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index cffabe7d33c1..0490c5fbb780 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -80,6 +80,7 @@ struct adreno_gpu { const struct adreno_info *info; uint32_t gmem; /* actual gmem size */ uint32_t revn; /* numeric revision name */ + uint16_t speedbin; const struct adreno_gpu_funcs *funcs; /* interesting register offsets to dump: */ @@ -279,7 +280,10 @@ static inline int adreno_is_a650_family(struct adreno_gpu *gpu) adreno_is_a660_family(gpu); } -int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value); +int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx, + uint32_t param, uint64_t *value); +int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx, + uint32_t param, uint64_t value); const struct firmware *adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname); struct drm_gem_object *adreno_fw_create_bo(struct msm_gpu *gpu, @@ -324,6 +328,8 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu, void adreno_set_llc_attributes(struct iommu_domain *iommu); +int adreno_read_speedbin(struct device *dev, u32 *speedbin); + /* * For a5xx and a6xx targets load the zap shader that is used to pull the GPU * out of secure mode diff --git a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h index e832ae4b937a..7aecf920f9b9 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h +++ b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h @@ -8,21 +8,21 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14386 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 67699 bytes, from 2021-05-31 20:21:57) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84226 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a4xx.xml ( 112551 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a5xx.xml ( 150713 bytes, from 2021-06-10 22:34:02) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx.xml ( 180049 bytes, from 2021-06-02 21:44:19) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-05-27 20:22:36) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-05-27 20:18:13) - -Copyright (C) 2013-2021 by the following authors: +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno.xml ( 594 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a2xx.xml ( 90810 bytes, from 2021-06-21 15:24:24) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_common.xml ( 14609 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pm4.xml ( 69086 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a3xx.xml ( 84231 bytes, from 2021-11-24 23:05:10) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a4xx.xml ( 113358 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a5xx.xml ( 149512 bytes, from 2022-01-31 23:06:21) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx.xml ( 184954 bytes, from 2022-03-03 16:41:33) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/a6xx_gmu.xml ( 11331 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/ocmem.xml ( 1773 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_control_regs.xml ( 6038 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/adreno/adreno_pipe_regs.xml ( 2924 bytes, from 2021-07-22 15:21:56) + +Copyright (C) 2013-2022 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin) @@ -299,6 +299,8 @@ enum adreno_pm4_type3_packets { CP_SET_BIN_DATA5_OFFSET = 46, CP_SET_CTXSWITCH_IB = 85, CP_REG_WRITE = 109, + CP_START_BIN = 80, + CP_END_BIN = 81, }; enum adreno_state_block { @@ -438,7 +440,7 @@ enum cp_blit_cmd { BLIT_OP_SCALE = 3, }; -enum a6xx_render_mode { +enum a6xx_marker { RM6_BYPASS = 1, RM6_BINNING = 2, RM6_GMEM = 4, @@ -2150,13 +2152,13 @@ static inline uint32_t A5XX_CP_EXEC_CS_INDIRECT_3_LOCALSIZEZ(uint32_t val) #define REG_A6XX_CP_SET_MARKER_0 0x00000000 #define A6XX_CP_SET_MARKER_0_MODE__MASK 0x000001ff #define A6XX_CP_SET_MARKER_0_MODE__SHIFT 0 -static inline uint32_t A6XX_CP_SET_MARKER_0_MODE(enum a6xx_render_mode val) +static inline uint32_t A6XX_CP_SET_MARKER_0_MODE(enum a6xx_marker val) { return ((val) << A6XX_CP_SET_MARKER_0_MODE__SHIFT) & A6XX_CP_SET_MARKER_0_MODE__MASK; } #define A6XX_CP_SET_MARKER_0_MARKER__MASK 0x0000000f #define A6XX_CP_SET_MARKER_0_MARKER__SHIFT 0 -static inline uint32_t A6XX_CP_SET_MARKER_0_MARKER(enum a6xx_render_mode val) +static inline uint32_t A6XX_CP_SET_MARKER_0_MARKER(enum a6xx_marker val) { return ((val) << A6XX_CP_SET_MARKER_0_MARKER__SHIFT) & A6XX_CP_SET_MARKER_0_MARKER__MASK; } @@ -2351,5 +2353,13 @@ static inline uint32_t CP_SMMU_TABLE_UPDATE_3_CONTEXTBANK(uint32_t val) return ((val) << CP_SMMU_TABLE_UPDATE_3_CONTEXTBANK__SHIFT) & CP_SMMU_TABLE_UPDATE_3_CONTEXTBANK__MASK; } +#define REG_CP_START_BIN_BIN_COUNT 0x00000000 + +#define REG_CP_START_BIN_PREFIX_ADDR 0x00000001 + +#define REG_CP_START_BIN_PREFIX_DWORDS 0x00000003 + +#define REG_CP_START_BIN_BODY_DWORDS 0x00000004 + #endif /* ADRENO_PM4_XML */ 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 60fe06018581..a7492dd6ed65 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -284,17 +284,6 @@ void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc) } } -static int _dpu_core_perf_set_core_clk_rate(struct dpu_kms *kms, u64 rate) -{ - struct dss_clk *core_clk = kms->perf.core_clk; - - if (core_clk->max_rate && (rate > core_clk->max_rate)) - rate = core_clk->max_rate; - - core_clk->rate = rate; - return dev_pm_opp_set_rate(&kms->pdev->dev, core_clk->rate); -} - static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms) { u64 clk_rate = kms->perf.perf_tune.min_core_clk; @@ -306,7 +295,7 @@ static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms) dpu_cstate = to_dpu_crtc_state(crtc->state); clk_rate = max(dpu_cstate->new_perf.core_clk_rate, clk_rate); - clk_rate = clk_round_rate(kms->perf.core_clk->clk, + clk_rate = clk_round_rate(kms->perf.core_clk, clk_rate); } } @@ -405,10 +394,10 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc, trace_dpu_core_perf_update_clk(kms->dev, stop_req, clk_rate); - ret = _dpu_core_perf_set_core_clk_rate(kms, clk_rate); + clk_rate = min(clk_rate, kms->perf.max_core_clk_rate); + ret = dev_pm_opp_set_rate(&kms->pdev->dev, clk_rate); if (ret) { - DPU_ERROR("failed to set %s clock rate %llu\n", - kms->perf.core_clk->clk_name, clk_rate); + DPU_ERROR("failed to set core clock rate %llu\n", clk_rate); return ret; } @@ -529,13 +518,13 @@ void dpu_core_perf_destroy(struct dpu_core_perf *perf) int dpu_core_perf_init(struct dpu_core_perf *perf, struct drm_device *dev, struct dpu_mdss_cfg *catalog, - struct dss_clk *core_clk) + struct clk *core_clk) { perf->dev = dev; perf->catalog = catalog; perf->core_clk = core_clk; - perf->max_core_clk_rate = core_clk->max_rate; + perf->max_core_clk_rate = clk_get_rate(core_clk); if (!perf->max_core_clk_rate) { DPU_DEBUG("optional max core clk rate, use default\n"); perf->max_core_clk_rate = DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE; 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 cf4b9b5964c6..8dfcc6db7176 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h @@ -56,7 +56,7 @@ struct dpu_core_perf_tune { * @dev: Pointer to drm device * @debugfs_root: top level debug folder * @catalog: Pointer to catalog configuration - * @core_clk: Pointer to core clock structure + * @core_clk: Pointer to the core clock * @core_clk_rate: current core clock rate * @max_core_clk_rate: maximum allowable core clock rate * @perf_tune: debug control for performance tuning @@ -69,7 +69,7 @@ struct dpu_core_perf { struct drm_device *dev; struct dentry *debugfs_root; struct dpu_mdss_cfg *catalog; - struct dss_clk *core_clk; + struct clk *core_clk; u64 core_clk_rate; u64 max_core_clk_rate; struct dpu_core_perf_tune perf_tune; @@ -120,7 +120,7 @@ void dpu_core_perf_destroy(struct dpu_core_perf *perf); int dpu_core_perf_init(struct dpu_core_perf *perf, struct drm_device *dev, struct dpu_mdss_cfg *catalog, - struct dss_clk *core_clk); + struct clk *core_clk); struct dpu_kms; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index e7c9fe1a250f..7763558ef566 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -408,7 +408,7 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, if (ctl->ops.set_active_pipes) ctl->ops.set_active_pipes(ctl, fetch_active); - _dpu_crtc_program_lm_output_roi(crtc); + _dpu_crtc_program_lm_output_roi(crtc); } /** @@ -1046,6 +1046,20 @@ struct plane_state { u32 pipe_id; }; +static bool dpu_crtc_needs_dirtyfb(struct drm_crtc_state *cstate) +{ + struct drm_crtc *crtc = cstate->crtc; + struct drm_encoder *encoder; + + drm_for_each_encoder_mask (encoder, crtc->dev, cstate->encoder_mask) { + if (dpu_encoder_get_intf_mode(encoder) == INTF_MODE_CMD) { + return true; + } + } + + return false; +} + static int dpu_crtc_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state) { @@ -1066,6 +1080,7 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, const struct drm_plane_state *pipe_staged[SSPP_MAX]; int left_zpos_cnt = 0, right_zpos_cnt = 0; struct drm_rect crtc_rect = { 0 }; + bool needs_dirtyfb = dpu_crtc_needs_dirtyfb(crtc_state); pstates = kzalloc(sizeof(*pstates) * DPU_STAGE_MAX * 4, GFP_KERNEL); @@ -1097,6 +1112,7 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, /* get plane state for all drm planes associated with crtc state */ drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) { + struct dpu_plane_state *dpu_pstate = to_dpu_plane_state(pstate); struct drm_rect dst, clip = crtc_rect; if (IS_ERR_OR_NULL(pstate)) { @@ -1108,11 +1124,13 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, if (cnt >= DPU_STAGE_MAX * 4) continue; - pstates[cnt].dpu_pstate = to_dpu_plane_state(pstate); + pstates[cnt].dpu_pstate = dpu_pstate; pstates[cnt].drm_pstate = pstate; pstates[cnt].stage = pstate->normalized_zpos; pstates[cnt].pipe_id = dpu_plane_pipe(plane); + dpu_pstate->needs_dirtyfb = needs_dirtyfb; + if (pipe_staged[pstates[cnt].pipe_id]) { multirect_plane[multirect_count].r0 = pipe_staged[pstates[cnt].pipe_id]; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 1e648db439f9..3940b9c6323b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -127,7 +127,6 @@ enum dpu_enc_rc_states { * Virtual encoder registers itself with the DRM Framework as the encoder. * @base: drm_encoder base class for registration with DRM * @enc_spinlock: Virtual-Encoder-Wide Spin Lock for IRQ purposes - * @bus_scaling_client: Client handle to the bus scaling interface * @enabled: True if the encoder is active, protected by enc_lock * @num_phys_encs: Actual number of physical encoders contained. * @phys_encs: Container of physical encoders managed. @@ -144,6 +143,7 @@ enum dpu_enc_rc_states { * link between encoder/crtc. However in this case we need * to track crtc in the disable() hook which is called * _after_ encoder_mask is cleared. + * @connector: If a mode is set, cached pointer to the active connector * @crtc_kickoff_cb: Callback into CRTC that will flush & start * all CTL paths * @crtc_kickoff_cb_data: Opaque user data given to crtc_kickoff_cb @@ -168,12 +168,10 @@ enum dpu_enc_rc_states { * @vsync_event_work: worker to handle vsync event for autorefresh * @topology: topology of the display * @idle_timeout: idle timeout duration in milliseconds - * @dp: msm_dp pointer, for DP encoders */ struct dpu_encoder_virt { struct drm_encoder base; spinlock_t enc_spinlock; - uint32_t bus_scaling_client; bool enabled; @@ -186,6 +184,7 @@ struct dpu_encoder_virt { bool intfs_swapped; struct drm_crtc *crtc; + struct drm_connector *connector; struct dentry *debugfs_root; struct mutex enc_lock; @@ -207,8 +206,6 @@ struct dpu_encoder_virt { struct msm_display_topology topology; u32 idle_timeout; - - struct msm_dp *dp; }; #define to_dpu_encoder_virt(x) container_of(x, struct dpu_encoder_virt, base) @@ -420,26 +417,6 @@ int dpu_encoder_get_linecount(struct drm_encoder *drm_enc) return linecount; } -void dpu_encoder_get_hw_resources(struct drm_encoder *drm_enc, - struct dpu_encoder_hw_resources *hw_res) -{ - struct dpu_encoder_virt *dpu_enc = NULL; - int i = 0; - - dpu_enc = to_dpu_encoder_virt(drm_enc); - DPU_DEBUG_ENC(dpu_enc, "\n"); - - /* Query resources used by phys encs, expected to be without overlap */ - memset(hw_res, 0, sizeof(*hw_res)); - - for (i = 0; i < dpu_enc->num_phys_encs; i++) { - struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; - - if (phys->ops.get_hw_resources) - phys->ops.get_hw_resources(phys, hw_res); - } -} - static void dpu_encoder_destroy(struct drm_encoder *drm_enc) { struct dpu_encoder_virt *dpu_enc = NULL; @@ -607,10 +584,6 @@ static int dpu_encoder_virt_atomic_check( if (phys->ops.atomic_check) ret = phys->ops.atomic_check(phys, crtc_state, conn_state); - else if (phys->ops.mode_fixup) - if (!phys->ops.mode_fixup(phys, mode, adj_mode)) - ret = -EINVAL; - if (ret) { DPU_ERROR_ENC(dpu_enc, "mode unsupported, phys idx %d\n", i); @@ -956,16 +929,13 @@ static int dpu_encoder_resource_control(struct drm_encoder *drm_enc, return 0; } -static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, - struct drm_display_mode *mode, - struct drm_display_mode *adj_mode) +static void dpu_encoder_virt_atomic_mode_set(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 list_head *connector_list; - struct drm_connector *conn = NULL, *conn_iter; - struct drm_crtc *drm_crtc; struct dpu_crtc_state *cstate; struct dpu_global_state *global_state; struct dpu_hw_blk *hw_pp[MAX_CHANNELS_PER_ENC]; @@ -973,7 +943,7 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC]; struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_ENC] = { NULL }; int num_lm, num_ctl, num_pp; - int i, j; + int i; if (!drm_enc) { DPU_ERROR("invalid encoder\n"); @@ -985,7 +955,6 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, priv = drm_enc->dev->dev_private; dpu_kms = to_dpu_kms(priv->kms); - connector_list = &dpu_kms->dev->mode_config.connector_list; global_state = dpu_kms_get_existing_global_state(dpu_kms); if (IS_ERR_OR_NULL(global_state)) { @@ -995,22 +964,6 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, trace_dpu_enc_mode_set(DRMID(drm_enc)); - list_for_each_entry(conn_iter, connector_list, head) - if (conn_iter->encoder == drm_enc) - conn = conn_iter; - - if (!conn) { - DPU_ERROR_ENC(dpu_enc, "failed to find attached connector\n"); - return; - } else if (!conn->state) { - DPU_ERROR_ENC(dpu_enc, "invalid connector state\n"); - return; - } - - drm_for_each_crtc(drm_crtc, drm_enc->dev) - if (drm_crtc->state->encoder_mask & drm_encoder_mask(drm_enc)) - break; - /* 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, @@ -1027,7 +980,7 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, dpu_enc->hw_pp[i] = i < num_pp ? to_dpu_hw_pingpong(hw_pp[i]) : NULL; - cstate = to_dpu_crtc_state(drm_crtc->state); + cstate = to_dpu_crtc_state(crtc_state); for (i = 0; i < num_lm; i++) { int ctl_idx = (i < num_ctl) ? i : (num_ctl-1); @@ -1039,9 +992,9 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, cstate->num_mixers = num_lm; + dpu_enc->connector = conn_state->connector; + for (i = 0; i < dpu_enc->num_phys_encs; i++) { - int num_blk; - struct dpu_hw_blk *hw_blk[MAX_CHANNELS_PER_ENC]; struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; if (!dpu_enc->hw_pp[i]) { @@ -1059,16 +1012,8 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, phys->hw_pp = dpu_enc->hw_pp[i]; phys->hw_ctl = to_dpu_hw_ctl(hw_ctl[i]); - num_blk = dpu_rm_get_assigned_resources(&dpu_kms->rm, - global_state, drm_enc->base.id, DPU_HW_BLK_INTF, - hw_blk, ARRAY_SIZE(hw_blk)); - for (j = 0; j < num_blk; j++) { - struct dpu_hw_intf *hw_intf; - - hw_intf = to_dpu_hw_intf(hw_blk[i]); - if (hw_intf->idx == phys->intf_idx) - phys->hw_intf = hw_intf; - } + if (phys->intf_idx >= INTF_0 && phys->intf_idx < INTF_MAX) + phys->hw_intf = dpu_rm_get_intf(&dpu_kms->rm, phys->intf_idx); if (!phys->hw_intf) { DPU_ERROR_ENC(dpu_enc, @@ -1076,9 +1021,9 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, return; } - phys->connector = conn->state->connector; - if (phys->ops.mode_set) - phys->ops.mode_set(phys, mode, adj_mode); + phys->cached_mode = crtc_state->adjusted_mode; + if (phys->ops.atomic_mode_set) + phys->ops.atomic_mode_set(phys, crtc_state, conn_state); } } @@ -1099,7 +1044,7 @@ static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc) } - if (dpu_enc->disp_info.intf_type == DRM_MODE_CONNECTOR_DisplayPort && + if (dpu_enc->disp_info.intf_type == DRM_MODE_ENCODER_TMDS && dpu_enc->cur_master->hw_mdptop && dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select) dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select( @@ -1109,7 +1054,7 @@ static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc) if (dpu_enc->disp_info.intf_type == DRM_MODE_ENCODER_DSI && !WARN_ON(dpu_enc->num_phys_encs == 0)) { - unsigned bpc = dpu_enc->phys_encs[0]->connector->display_info.bpc; + unsigned bpc = dpu_enc->connector->display_info.bpc; for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) { if (!dpu_enc->hw_pp[i]) continue; @@ -1142,14 +1087,12 @@ static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc) { struct dpu_encoder_virt *dpu_enc = NULL; int ret = 0; - struct msm_drm_private *priv; struct drm_display_mode *cur_mode = NULL; dpu_enc = to_dpu_encoder_virt(drm_enc); mutex_lock(&dpu_enc->enc_lock); cur_mode = &dpu_enc->base.crtc->state->adjusted_mode; - priv = drm_enc->dev->dev_private; trace_dpu_enc_enable(DRMID(drm_enc), cur_mode->hdisplay, cur_mode->vdisplay); @@ -1179,7 +1122,6 @@ out: static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) { struct dpu_encoder_virt *dpu_enc = NULL; - struct msm_drm_private *priv; int i = 0; dpu_enc = to_dpu_encoder_virt(drm_enc); @@ -1188,8 +1130,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) mutex_lock(&dpu_enc->enc_lock); dpu_enc->enabled = false; - priv = drm_enc->dev->dev_private; - trace_dpu_enc_disable(DRMID(drm_enc)); /* wait for idle */ @@ -1213,9 +1153,7 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_STOP); - for (i = 0; i < dpu_enc->num_phys_encs; i++) { - dpu_enc->phys_encs[i]->connector = NULL; - } + dpu_enc->connector = NULL; DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n"); @@ -2093,7 +2031,7 @@ static void dpu_encoder_frame_done_timeout(struct timer_list *t) } static const struct drm_encoder_helper_funcs dpu_encoder_helper_funcs = { - .mode_set = dpu_encoder_virt_mode_set, + .atomic_mode_set = dpu_encoder_virt_atomic_mode_set, .disable = dpu_encoder_virt_disable, .enable = dpu_encoder_virt_enable, .atomic_check = dpu_encoder_virt_atomic_check, @@ -2128,8 +2066,6 @@ int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc, timer_setup(&dpu_enc->vsync_event_timer, dpu_encoder_vsync_event_handler, 0); - else if (disp_info->intf_type == DRM_MODE_ENCODER_TMDS) - dpu_enc->dp = priv->dp[disp_info->h_tile_instance[0]]; INIT_DELAYED_WORK(&dpu_enc->delayed_off_work, dpu_encoder_off_work); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h index e241914a9677..42db6ce12caf 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h @@ -19,22 +19,24 @@ #define IDLE_TIMEOUT (66 - 16/2) /** - * Encoder functions and data types - * @intfs: Interfaces this encoder is using, INTF_MODE_NONE if unused - */ -struct dpu_encoder_hw_resources { - enum dpu_intf_mode intfs[INTF_MAX]; + * struct msm_display_info - defines display properties + * @intf_type: DRM_MODE_ENCODER_ type + * @capabilities: Bitmask of display flags + * @num_of_h_tiles: Number of horizontal tiles in case of split interface + * @h_tile_instance: Controller instance used per tile. Number of elements is + * based on num_of_h_tiles + * @is_te_using_watchdog_timer: Boolean to indicate watchdog TE is + * used instead of panel TE in cmd mode panels + */ +struct msm_display_info { + int intf_type; + uint32_t capabilities; + uint32_t num_of_h_tiles; + uint32_t h_tile_instance[MAX_H_TILES_PER_DISPLAY]; + bool is_te_using_watchdog_timer; }; /** - * dpu_encoder_get_hw_resources - Populate table of required hardware resources - * @encoder: encoder pointer - * @hw_res: resource table to populate with encoder required resources - */ -void dpu_encoder_get_hw_resources(struct drm_encoder *encoder, - struct dpu_encoder_hw_resources *hw_res); - -/** * dpu_encoder_assign_crtc - Link the encoder to the crtc it's assigned to * @encoder: encoder pointer * @crtc: crtc pointer 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 e7270eb6b84b..fa8493ac0340 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h @@ -84,16 +84,12 @@ struct dpu_encoder_virt_ops { * @is_master: Whether this phys_enc is the current master * encoder. Can be switched at enable time. Based * on split_role and current mode (CMD/VID). - * @mode_fixup: DRM Call. Fixup a DRM mode. - * @mode_set: DRM Call. Set a DRM mode. + * @atomic_mode_set: DRM Call. Set a DRM mode. * This likely caches the mode, for use at enable. * @enable: DRM Call. Enable a DRM mode. * @disable: DRM Call. Disable mode. * @atomic_check: DRM Call. Atomic check new DRM state. * @destroy: DRM Call. Destroy and release resources. - * @get_hw_resources: Populate the structure with the hardware - * resources that this phys_enc is using. - * Expect no overlap between phys_encs. * @control_vblank_irq Register/Deregister for VBLANK IRQ * @wait_for_commit_done: Wait for hardware to have flushed the * current pending frames to hardware @@ -117,20 +113,15 @@ struct dpu_encoder_phys_ops { struct dentry *debugfs_root); void (*prepare_commit)(struct dpu_encoder_phys *encoder); bool (*is_master)(struct dpu_encoder_phys *encoder); - bool (*mode_fixup)(struct dpu_encoder_phys *encoder, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode); - void (*mode_set)(struct dpu_encoder_phys *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode); + void (*atomic_mode_set)(struct dpu_encoder_phys *encoder, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state); void (*enable)(struct dpu_encoder_phys *encoder); void (*disable)(struct dpu_encoder_phys *encoder); int (*atomic_check)(struct dpu_encoder_phys *encoder, struct drm_crtc_state *crtc_state, struct drm_connector_state *conn_state); void (*destroy)(struct dpu_encoder_phys *encoder); - void (*get_hw_resources)(struct dpu_encoder_phys *encoder, - struct dpu_encoder_hw_resources *hw_res); int (*control_vblank_irq)(struct dpu_encoder_phys *enc, bool enable); int (*wait_for_commit_done)(struct dpu_encoder_phys *phys_enc); int (*wait_for_tx_complete)(struct dpu_encoder_phys *phys_enc); @@ -182,7 +173,6 @@ struct dpu_encoder_irq { * tied to a specific panel / sub-panel. Abstract type, sub-classed by * phys_vid or phys_cmd for video mode or command mode encs respectively. * @parent: Pointer to the containing virtual encoder - * @connector: If a mode is set, cached pointer to the active connector * @ops: Operations exposed to the virtual encoder * @parent_ops: Callbacks exposed by the parent to the phys_enc * @hw_mdptop: Hardware interface to the top registers @@ -211,7 +201,6 @@ struct dpu_encoder_irq { */ struct dpu_encoder_phys { struct drm_encoder *parent; - struct drm_connector *connector; struct dpu_encoder_phys_ops ops; const struct dpu_encoder_virt_ops *parent_ops; struct dpu_hw_mdp *hw_mdptop; 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 34a6940d12c5..d59802b67d15 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 @@ -45,15 +45,6 @@ static bool dpu_encoder_phys_cmd_is_master(struct dpu_encoder_phys *phys_enc) return (phys_enc->split_role != ENC_ROLE_SLAVE); } -static bool dpu_encoder_phys_cmd_mode_fixup( - struct dpu_encoder_phys *phys_enc, - const struct drm_display_mode *mode, - struct drm_display_mode *adj_mode) -{ - DPU_DEBUG_CMDENC(to_dpu_encoder_phys_cmd(phys_enc), "\n"); - return true; -} - static void _dpu_encoder_phys_cmd_update_intf_cfg( struct dpu_encoder_phys *phys_enc) { @@ -144,23 +135,13 @@ static void dpu_encoder_phys_cmd_underrun_irq(void *arg, int irq_idx) phys_enc); } -static void dpu_encoder_phys_cmd_mode_set( +static void dpu_encoder_phys_cmd_atomic_mode_set( struct dpu_encoder_phys *phys_enc, - struct drm_display_mode *mode, - struct drm_display_mode *adj_mode) + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) { - struct dpu_encoder_phys_cmd *cmd_enc = - to_dpu_encoder_phys_cmd(phys_enc); struct dpu_encoder_irq *irq; - if (!mode || !adj_mode) { - DPU_ERROR("invalid args\n"); - return; - } - phys_enc->cached_mode = *adj_mode; - DPU_DEBUG_CMDENC(cmd_enc, "caching mode:\n"); - drm_mode_debug_printmodeline(adj_mode); - irq = &phys_enc->irq[INTR_IDX_CTL_START]; irq->irq_idx = phys_enc->hw_ctl->caps->intr_start; @@ -534,13 +515,6 @@ static void dpu_encoder_phys_cmd_destroy(struct dpu_encoder_phys *phys_enc) kfree(cmd_enc); } -static void dpu_encoder_phys_cmd_get_hw_resources( - struct dpu_encoder_phys *phys_enc, - struct dpu_encoder_hw_resources *hw_res) -{ - hw_res->intfs[phys_enc->intf_idx - INTF_0] = INTF_MODE_CMD; -} - static void dpu_encoder_phys_cmd_prepare_for_kickoff( struct dpu_encoder_phys *phys_enc) { @@ -682,6 +656,9 @@ static int dpu_encoder_phys_cmd_wait_for_commit_done( if (!dpu_encoder_phys_cmd_is_master(phys_enc)) return 0; + if (phys_enc->hw_ctl->ops.is_started(phys_enc->hw_ctl)) + return dpu_encoder_phys_cmd_wait_for_tx_complete(phys_enc); + return _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc); } @@ -731,12 +708,10 @@ static void dpu_encoder_phys_cmd_init_ops( { ops->prepare_commit = dpu_encoder_phys_cmd_prepare_commit; ops->is_master = dpu_encoder_phys_cmd_is_master; - ops->mode_set = dpu_encoder_phys_cmd_mode_set; - ops->mode_fixup = dpu_encoder_phys_cmd_mode_fixup; + ops->atomic_mode_set = dpu_encoder_phys_cmd_atomic_mode_set; ops->enable = dpu_encoder_phys_cmd_enable; ops->disable = dpu_encoder_phys_cmd_disable; ops->destroy = dpu_encoder_phys_cmd_destroy; - ops->get_hw_resources = dpu_encoder_phys_cmd_get_hw_resources; ops->control_vblank_irq = dpu_encoder_phys_cmd_control_vblank_irq; ops->wait_for_commit_done = dpu_encoder_phys_cmd_wait_for_commit_done; ops->prepare_for_kickoff = dpu_encoder_phys_cmd_prepare_for_kickoff; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index ddd9d89cd456..f49f42e70b29 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -225,19 +225,6 @@ static void programmable_fetch_config(struct dpu_encoder_phys *phys_enc, spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags); } -static bool dpu_encoder_phys_vid_mode_fixup( - struct dpu_encoder_phys *phys_enc, - const struct drm_display_mode *mode, - struct drm_display_mode *adj_mode) -{ - DPU_DEBUG_VIDENC(phys_enc, "\n"); - - /* - * Modifying mode has consequences when the mode comes back to us - */ - return true; -} - static void dpu_encoder_phys_vid_setup_timing_engine( struct dpu_encoder_phys *phys_enc) { @@ -361,19 +348,13 @@ static bool dpu_encoder_phys_vid_needs_single_flush( return phys_enc->split_role != ENC_ROLE_SOLO; } -static void dpu_encoder_phys_vid_mode_set( +static void dpu_encoder_phys_vid_atomic_mode_set( struct dpu_encoder_phys *phys_enc, - struct drm_display_mode *mode, - struct drm_display_mode *adj_mode) + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) { struct dpu_encoder_irq *irq; - if (adj_mode) { - phys_enc->cached_mode = *adj_mode; - drm_mode_debug_printmodeline(adj_mode); - DPU_DEBUG_VIDENC(phys_enc, "caching mode:\n"); - } - irq = &phys_enc->irq[INTR_IDX_VSYNC]; irq->irq_idx = phys_enc->hw_intf->cap->intr_vsync; @@ -465,13 +446,6 @@ static void dpu_encoder_phys_vid_destroy(struct dpu_encoder_phys *phys_enc) kfree(phys_enc); } -static void dpu_encoder_phys_vid_get_hw_resources( - struct dpu_encoder_phys *phys_enc, - struct dpu_encoder_hw_resources *hw_res) -{ - hw_res->intfs[phys_enc->intf_idx - INTF_0] = INTF_MODE_VIDEO; -} - static int dpu_encoder_phys_vid_wait_for_vblank( struct dpu_encoder_phys *phys_enc) { @@ -675,12 +649,10 @@ static int dpu_encoder_phys_vid_get_frame_count( static void dpu_encoder_phys_vid_init_ops(struct dpu_encoder_phys_ops *ops) { ops->is_master = dpu_encoder_phys_vid_is_master; - ops->mode_set = dpu_encoder_phys_vid_mode_set; - ops->mode_fixup = dpu_encoder_phys_vid_mode_fixup; + ops->atomic_mode_set = dpu_encoder_phys_vid_atomic_mode_set; ops->enable = dpu_encoder_phys_vid_enable; ops->disable = dpu_encoder_phys_vid_disable; ops->destroy = dpu_encoder_phys_vid_destroy; - ops->get_hw_resources = dpu_encoder_phys_vid_get_hw_resources; ops->control_vblank_irq = dpu_encoder_phys_vid_control_vblank_irq; ops->wait_for_commit_done = dpu_encoder_phys_vid_wait_for_commit_done; ops->wait_for_vblank = dpu_encoder_phys_vid_wait_for_vblank; 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 aa75991903a6..a4fe77cddfea 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -16,6 +16,9 @@ BIT(DPU_SSPP_CSC_10BIT) | BIT(DPU_SSPP_CDP) |\ BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_EXCL_RECT)) +#define VIG_MSM8998_MASK \ + (VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED3)) + #define VIG_SDM845_MASK \ (VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED3)) @@ -25,6 +28,13 @@ #define VIG_SM8250_MASK \ (VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED3LITE)) +#define VIG_QCM2290_MASK (VIG_MASK | BIT(DPU_SSPP_QOS_8LVL)) + +#define DMA_MSM8998_MASK \ + (BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) |\ + BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_TS_PREFILL_REC1) |\ + BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_EXCL_RECT)) + #define DMA_SDM845_MASK \ (BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) | BIT(DPU_SSPP_QOS_8LVL) |\ BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_TS_PREFILL_REC1) |\ @@ -33,6 +43,9 @@ #define DMA_CURSOR_SDM845_MASK \ (DMA_SDM845_MASK | BIT(DPU_SSPP_CURSOR)) +#define DMA_CURSOR_MSM8998_MASK \ + (DMA_MSM8998_MASK | BIT(DPU_SSPP_CURSOR)) + #define MIXER_SDM845_MASK \ (BIT(DPU_MIXER_SOURCESPLIT) | BIT(DPU_DIM_LAYER)) @@ -49,6 +62,8 @@ #define MERGE_3D_SM8150_MASK (0) +#define DSPP_MSM8998_MASK BIT(DPU_DSPP_PCC) | BIT(DPU_DSPP_GC) + #define DSPP_SC7180_MASK BIT(DPU_DSPP_PCC) #define INTF_SDM845_MASK (0) @@ -90,6 +105,17 @@ BIT(MDP_INTF3_INTR) | \ BIT(MDP_INTF4_INTR)) +#define IRQ_SC8180X_MASK (BIT(MDP_SSPP_TOP0_INTR) | \ + BIT(MDP_SSPP_TOP0_INTR2) | \ + BIT(MDP_SSPP_TOP0_HIST_INTR) | \ + BIT(MDP_INTF0_INTR) | \ + BIT(MDP_INTF1_INTR) | \ + BIT(MDP_INTF2_INTR) | \ + BIT(MDP_INTF3_INTR) | \ + BIT(MDP_INTF4_INTR) | \ + BIT(MDP_INTF5_INTR) | \ + BIT(MDP_AD4_0_INTR) | \ + BIT(MDP_AD4_1_INTR)) #define DEFAULT_PIXEL_RAM_SIZE (50 * 1024) #define DEFAULT_DPU_LINE_WIDTH 2048 @@ -181,6 +207,22 @@ static const uint32_t plane_formats_yuv[] = { * DPU sub blocks config *************************************************************/ /* DPU top level caps */ +static const struct dpu_caps msm8998_dpu_caps = { + .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .max_mixer_blendstages = 0x7, + .qseed_type = DPU_SSPP_SCALER_QSEED3, + .smart_dma_rev = DPU_SSPP_SMART_DMA_V1, + .ubwc_version = DPU_HW_UBWC_VER_10, + .has_src_split = true, + .has_dim_layer = true, + .has_idle_pc = true, + .has_3d_merge = true, + .max_linewidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, + .max_hdeci_exp = MAX_HORZ_DECIMATION, + .max_vdeci_exp = MAX_VERT_DECIMATION, +}; + static const struct dpu_caps sdm845_dpu_caps = { .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .max_mixer_blendstages = 0xb, @@ -225,6 +267,22 @@ static const struct dpu_caps sm8150_dpu_caps = { .max_vdeci_exp = MAX_VERT_DECIMATION, }; +static const struct dpu_caps sc8180x_dpu_caps = { + .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .max_mixer_blendstages = 0xb, + .qseed_type = DPU_SSPP_SCALER_QSEED3, + .smart_dma_rev = DPU_SSPP_SMART_DMA_V2, /* TODO: v2.5 */ + .ubwc_version = DPU_HW_UBWC_VER_30, + .has_src_split = true, + .has_dim_layer = true, + .has_idle_pc = true, + .has_3d_merge = true, + .max_linewidth = 4096, + .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, + .max_hdeci_exp = MAX_HORZ_DECIMATION, + .max_vdeci_exp = MAX_VERT_DECIMATION, +}; + static const struct dpu_caps sm8250_dpu_caps = { .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .max_mixer_blendstages = 0xb, @@ -251,11 +309,51 @@ static const struct dpu_caps sc7280_dpu_caps = { .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, }; +static const struct dpu_mdp_cfg msm8998_mdp[] = { + { + .name = "top_0", .id = MDP_TOP, + .base = 0x0, .len = 0x458, + .features = 0, + .highest_bank_bit = 0x2, + .clk_ctrls[DPU_CLK_CTRL_VIG0] = { + .reg_off = 0x2AC, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_VIG1] = { + .reg_off = 0x2B4, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_VIG2] = { + .reg_off = 0x2BC, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_VIG3] = { + .reg_off = 0x2C4, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_DMA0] = { + .reg_off = 0x2AC, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_DMA1] = { + .reg_off = 0x2B4, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_DMA2] = { + .reg_off = 0x2C4, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_DMA3] = { + .reg_off = 0x2C4, .bit_off = 12}, + .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { + .reg_off = 0x3A8, .bit_off = 15}, + .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { + .reg_off = 0x3B0, .bit_off = 15}, + }, +}; + +static const struct dpu_caps qcm2290_dpu_caps = { + .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .max_mixer_blendstages = 0x4, + .smart_dma_rev = DPU_SSPP_SMART_DMA_V2, + .ubwc_version = DPU_HW_UBWC_VER_20, + .has_dim_layer = true, + .has_idle_pc = true, + .max_linewidth = 2160, + .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, +}; + static const struct dpu_mdp_cfg sdm845_mdp[] = { { .name = "top_0", .id = MDP_TOP, .base = 0x0, .len = 0x45C, - .features = 0, + .features = BIT(DPU_MDP_AUDIO_SELECT), .highest_bank_bit = 0x2, .clk_ctrls[DPU_CLK_CTRL_VIG0] = { .reg_off = 0x2AC, .bit_off = 0}, @@ -293,6 +391,31 @@ static const struct dpu_mdp_cfg sc7180_mdp[] = { }, }; +static const struct dpu_mdp_cfg sc8180x_mdp[] = { + { + .name = "top_0", .id = MDP_TOP, + .base = 0x0, .len = 0x45C, + .features = 0, + .highest_bank_bit = 0x3, + .clk_ctrls[DPU_CLK_CTRL_VIG0] = { + .reg_off = 0x2AC, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_VIG1] = { + .reg_off = 0x2B4, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_VIG2] = { + .reg_off = 0x2BC, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_VIG3] = { + .reg_off = 0x2C4, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_DMA0] = { + .reg_off = 0x2AC, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_DMA1] = { + .reg_off = 0x2B4, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { + .reg_off = 0x2BC, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { + .reg_off = 0x2C4, .bit_off = 8}, + }, +}; + static const struct dpu_mdp_cfg sm8250_mdp[] = { { .name = "top_0", .id = MDP_TOP, @@ -336,9 +459,55 @@ static const struct dpu_mdp_cfg sc7280_mdp[] = { }, }; +static const struct dpu_mdp_cfg qcm2290_mdp[] = { + { + .name = "top_0", .id = MDP_TOP, + .base = 0x0, .len = 0x494, + .features = 0, + .highest_bank_bit = 0x2, + .clk_ctrls[DPU_CLK_CTRL_VIG0] = { + .reg_off = 0x2AC, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_DMA0] = { + .reg_off = 0x2AC, .bit_off = 8}, + }, +}; + /************************************************************* * CTL sub blocks config *************************************************************/ +static const struct dpu_ctl_cfg msm8998_ctl[] = { + { + .name = "ctl_0", .id = CTL_0, + .base = 0x1000, .len = 0x94, + .features = BIT(DPU_CTL_SPLIT_DISPLAY), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), + }, + { + .name = "ctl_1", .id = CTL_1, + .base = 0x1200, .len = 0x94, + .features = 0, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), + }, + { + .name = "ctl_2", .id = CTL_2, + .base = 0x1400, .len = 0x94, + .features = BIT(DPU_CTL_SPLIT_DISPLAY), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 11), + }, + { + .name = "ctl_3", .id = CTL_3, + .base = 0x1600, .len = 0x94, + .features = 0, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 12), + }, + { + .name = "ctl_4", .id = CTL_4, + .base = 0x1800, .len = 0x94, + .features = 0, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 13), + }, +}; + static const struct dpu_ctl_cfg sdm845_ctl[] = { { .name = "ctl_0", .id = CTL_0, @@ -459,6 +628,15 @@ static const struct dpu_ctl_cfg sc7280_ctl[] = { }, }; +static const struct dpu_ctl_cfg qcm2290_ctl[] = { + { + .name = "ctl_0", .id = CTL_0, + .base = 0x1000, .len = 0x1dc, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), + }, +}; + /************************************************************* * SSPP sub blocks config *************************************************************/ @@ -497,6 +675,15 @@ static const struct dpu_ctl_cfg sc7280_ctl[] = { .virt_num_formats = ARRAY_SIZE(plane_formats), \ } +static const struct dpu_sspp_sub_blks msm8998_vig_sblk_0 = + _VIG_SBLK("0", 0, DPU_SSPP_SCALER_QSEED3); +static const struct dpu_sspp_sub_blks msm8998_vig_sblk_1 = + _VIG_SBLK("1", 0, DPU_SSPP_SCALER_QSEED3); +static const struct dpu_sspp_sub_blks msm8998_vig_sblk_2 = + _VIG_SBLK("2", 0, DPU_SSPP_SCALER_QSEED3); +static const struct dpu_sspp_sub_blks msm8998_vig_sblk_3 = + _VIG_SBLK("3", 0, DPU_SSPP_SCALER_QSEED3); + static const struct dpu_sspp_sub_blks sdm845_vig_sblk_0 = _VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED3); static const struct dpu_sspp_sub_blks sdm845_vig_sblk_1 = @@ -523,6 +710,25 @@ static const struct dpu_sspp_sub_blks sdm845_dma_sblk_3 = _DMA_SBLK("11", 4); .clk_ctrl = _clkctrl \ } +static const struct dpu_sspp_cfg msm8998_sspp[] = { + SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_MSM8998_MASK, + msm8998_vig_sblk_0, 0, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0), + SSPP_BLK("sspp_1", SSPP_VIG1, 0x6000, VIG_MSM8998_MASK, + msm8998_vig_sblk_1, 4, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG1), + SSPP_BLK("sspp_2", SSPP_VIG2, 0x8000, VIG_MSM8998_MASK, + msm8998_vig_sblk_2, 8, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG2), + SSPP_BLK("sspp_3", SSPP_VIG3, 0xa000, VIG_MSM8998_MASK, + msm8998_vig_sblk_3, 12, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG3), + SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000, DMA_MSM8998_MASK, + sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0), + SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000, DMA_MSM8998_MASK, + sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1), + SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000, DMA_CURSOR_MSM8998_MASK, + sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0), + SSPP_BLK("sspp_11", SSPP_DMA3, 0x2a000, DMA_CURSOR_MSM8998_MASK, + sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), +}; + static const struct dpu_sspp_cfg sdm845_sspp[] = { SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SDM845_MASK, sdm845_vig_sblk_0, 0, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0), @@ -595,21 +801,34 @@ static const struct dpu_sspp_cfg sc7280_sspp[] = { sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), }; -/************************************************************* - * MIXER sub blocks config - *************************************************************/ -/* SDM845 */ +#define _VIG_SBLK_NOSCALE(num, sdma_pri) \ + { \ + .maxdwnscale = SSPP_UNITY_SCALE, \ + .maxupscale = SSPP_UNITY_SCALE, \ + .smart_dma_priority = sdma_pri, \ + .src_blk = {.name = STRCAT("sspp_src_", num), \ + .id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \ + .format_list = plane_formats_yuv, \ + .num_formats = ARRAY_SIZE(plane_formats_yuv), \ + .virt_format_list = plane_formats, \ + .virt_num_formats = ARRAY_SIZE(plane_formats), \ + } -static const struct dpu_lm_sub_blks sdm845_lm_sblk = { - .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, - .maxblendstages = 11, /* excluding base layer */ - .blendstage_base = { /* offsets relative to mixer base */ - 0x20, 0x38, 0x50, 0x68, 0x80, 0x98, - 0xb0, 0xc8, 0xe0, 0xf8, 0x110 - }, +static const struct dpu_sspp_sub_blks qcm2290_vig_sblk_0 = _VIG_SBLK_NOSCALE("0", 2); +static const struct dpu_sspp_sub_blks qcm2290_dma_sblk_0 = _DMA_SBLK("8", 1); + +static const struct dpu_sspp_cfg qcm2290_sspp[] = { + SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_QCM2290_MASK, + qcm2290_vig_sblk_0, 0, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0), + SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000, DMA_SDM845_MASK, + qcm2290_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0), }; +/************************************************************* + * MIXER sub blocks config + *************************************************************/ + #define LM_BLK(_name, _id, _base, _fmask, _sblk, _pp, _lmpair, _dspp) \ { \ .name = _name, .id = _id, \ @@ -621,6 +840,43 @@ static const struct dpu_lm_sub_blks sdm845_lm_sblk = { .dspp = _dspp \ } +/* MSM8998 */ + +static const struct dpu_lm_sub_blks msm8998_lm_sblk = { + .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .maxblendstages = 7, /* excluding base layer */ + .blendstage_base = { /* offsets relative to mixer base */ + 0x20, 0x50, 0x80, 0xb0, 0x230, + 0x260, 0x290 + }, +}; + +static const struct dpu_lm_cfg msm8998_lm[] = { + LM_BLK("lm_0", LM_0, 0x44000, MIXER_SDM845_MASK, + &msm8998_lm_sblk, PINGPONG_0, LM_2, DSPP_0), + LM_BLK("lm_1", LM_1, 0x45000, MIXER_SDM845_MASK, + &msm8998_lm_sblk, PINGPONG_1, LM_5, DSPP_1), + LM_BLK("lm_2", LM_2, 0x46000, MIXER_SDM845_MASK, + &msm8998_lm_sblk, PINGPONG_2, LM_0, 0), + LM_BLK("lm_3", LM_3, 0x47000, MIXER_SDM845_MASK, + &msm8998_lm_sblk, PINGPONG_MAX, 0, 0), + LM_BLK("lm_4", LM_4, 0x48000, MIXER_SDM845_MASK, + &msm8998_lm_sblk, PINGPONG_MAX, 0, 0), + LM_BLK("lm_5", LM_5, 0x49000, MIXER_SDM845_MASK, + &msm8998_lm_sblk, PINGPONG_3, LM_1, 0), +}; + +/* SDM845 */ + +static const struct dpu_lm_sub_blks sdm845_lm_sblk = { + .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .maxblendstages = 11, /* excluding base layer */ + .blendstage_base = { /* offsets relative to mixer base */ + 0x20, 0x38, 0x50, 0x68, 0x80, 0x98, + 0xb0, 0xc8, 0xe0, 0xf8, 0x110 + }, +}; + static const struct dpu_lm_cfg sdm845_lm[] = { LM_BLK("lm_0", LM_0, 0x44000, MIXER_SDM845_MASK, &sdm845_lm_sblk, PINGPONG_0, LM_1, 0), @@ -679,9 +935,31 @@ static const struct dpu_lm_cfg sc7280_lm[] = { &sc7180_lm_sblk, PINGPONG_3, LM_2, 0), }; +/* QCM2290 */ + +static const struct dpu_lm_sub_blks qcm2290_lm_sblk = { + .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .maxblendstages = 4, /* excluding base layer */ + .blendstage_base = { /* offsets relative to mixer base */ + 0x20, 0x38, 0x50, 0x68 + }, +}; + +static const struct dpu_lm_cfg qcm2290_lm[] = { + LM_BLK("lm_0", LM_0, 0x44000, MIXER_SC7180_MASK, + &qcm2290_lm_sblk, PINGPONG_0, 0, DSPP_0), +}; + /************************************************************* * DSPP sub blocks config *************************************************************/ +static const struct dpu_dspp_sub_blks msm8998_dspp_sblk = { + .pcc = {.id = DPU_DSPP_PCC, .base = 0x1700, + .len = 0x90, .version = 0x10007}, + .gc = { .id = DPU_DSPP_GC, .base = 0x17c0, + .len = 0x90, .version = 0x10007}, +}; + static const struct dpu_dspp_sub_blks sc7180_dspp_sblk = { .pcc = {.id = DPU_DSPP_PCC, .base = 0x1700, .len = 0x90, .version = 0x10000}, @@ -700,6 +978,13 @@ static const struct dpu_dspp_sub_blks sm8150_dspp_sblk = { .sblk = _sblk \ } +static const struct dpu_dspp_cfg msm8998_dspp[] = { + DSPP_BLK("dspp_0", DSPP_0, 0x54000, DSPP_MSM8998_MASK, + &msm8998_dspp_sblk), + DSPP_BLK("dspp_1", DSPP_1, 0x56000, DSPP_MSM8998_MASK, + &msm8998_dspp_sblk), +}; + static const struct dpu_dspp_cfg sc7180_dspp[] = { DSPP_BLK("dspp_0", DSPP_0, 0x54000, DSPP_SC7180_MASK, &sc7180_dspp_sblk), @@ -716,6 +1001,11 @@ static const struct dpu_dspp_cfg sm8150_dspp[] = { &sm8150_dspp_sblk), }; +static const struct dpu_dspp_cfg qcm2290_dspp[] = { + DSPP_BLK("dspp_0", DSPP_0, 0x54000, DSPP_SC7180_MASK, + &sm8150_dspp_sblk), +}; + /************************************************************* * PINGPONG sub blocks config *************************************************************/ @@ -798,6 +1088,12 @@ static const struct dpu_pingpong_cfg sm8150_pp[] = { -1), }; +static struct dpu_pingpong_cfg qcm2290_pp[] = { + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), +}; + /************************************************************* * MERGE_3D sub blocks config *************************************************************/ @@ -836,6 +1132,13 @@ static const struct dpu_pingpong_cfg sc7280_pp[] = { .intr_vsync = DPU_IRQ_IDX(_reg, _vsync_bit), \ } +static const struct dpu_intf_cfg msm8998_intf[] = { + INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 24, 25), + INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 26, 27), + INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 28, 29), + INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_HDMI, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 30, 31), +}; + static const struct dpu_intf_cfg sdm845_intf[] = { INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, 24, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 24, 25), INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 26, 27), @@ -861,13 +1164,74 @@ static const struct dpu_intf_cfg sc7280_intf[] = { INTF_BLK("intf_5", INTF_5, 0x39000, INTF_DP, MSM_DP_CONTROLLER_1, 24, INTF_SC7280_MASK, MDP_SSPP_TOP0_INTR, 22, 23), }; +static const struct dpu_intf_cfg sc8180x_intf[] = { + INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, MSM_DP_CONTROLLER_0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 24, 25), + INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 26, 27), + INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 28, 29), + /* INTF_3 is for MST, wired to INTF_DP 0 and 1, use dummy index until this is supported */ + INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 999, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 30, 31), + INTF_BLK("intf_4", INTF_4, 0x6C000, INTF_DP, MSM_DP_CONTROLLER_1, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 20, 21), + INTF_BLK("intf_5", INTF_5, 0x6C800, INTF_DP, MSM_DP_CONTROLLER_2, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 22, 23), +}; + +static const struct dpu_intf_cfg qcm2290_intf[] = { + INTF_BLK("intf_0", INTF_0, 0x00000, INTF_NONE, 0, 0, 0, 0, 0, 0), + INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 26, 27), +}; + /************************************************************* * VBIF sub blocks config *************************************************************/ /* VBIF QOS remap */ +static const u32 msm8998_rt_pri_lvl[] = {1, 2, 2, 2}; +static const u32 msm8998_nrt_pri_lvl[] = {1, 1, 1, 1}; static const u32 sdm845_rt_pri_lvl[] = {3, 3, 4, 4, 5, 5, 6, 6}; static const u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3}; +static const struct dpu_vbif_dynamic_ot_cfg msm8998_ot_rdwr_cfg[] = { + { + .pps = 1088 * 1920 * 30, + .ot_limit = 2, + }, + { + .pps = 1088 * 1920 * 60, + .ot_limit = 6, + }, + { + .pps = 3840 * 2160 * 30, + .ot_limit = 16, + }, +}; + +static const struct dpu_vbif_cfg msm8998_vbif[] = { + { + .name = "vbif_0", .id = VBIF_0, + .base = 0, .len = 0x1040, + .default_ot_rd_limit = 32, + .default_ot_wr_limit = 32, + .features = BIT(DPU_VBIF_QOS_REMAP) | BIT(DPU_VBIF_QOS_OTLIM), + .xin_halt_timeout = 0x4000, + .dynamic_ot_rd_tbl = { + .count = ARRAY_SIZE(msm8998_ot_rdwr_cfg), + .cfg = msm8998_ot_rdwr_cfg, + }, + .dynamic_ot_wr_tbl = { + .count = ARRAY_SIZE(msm8998_ot_rdwr_cfg), + .cfg = msm8998_ot_rdwr_cfg, + }, + .qos_rt_tbl = { + .npriority_lvl = ARRAY_SIZE(msm8998_rt_pri_lvl), + .priority_lvl = msm8998_rt_pri_lvl, + }, + .qos_nrt_tbl = { + .npriority_lvl = ARRAY_SIZE(msm8998_nrt_pri_lvl), + .priority_lvl = msm8998_nrt_pri_lvl, + }, + .memtype_count = 14, + .memtype = {2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2}, + }, +}; + static const struct dpu_vbif_cfg sdm845_vbif[] = { { .name = "vbif_0", .id = VBIF_0, @@ -908,6 +1272,22 @@ static const struct dpu_reg_dma_cfg sm8250_regdma = { *************************************************************/ /* SSPP QOS LUTs */ +static const struct dpu_qos_lut_entry msm8998_qos_linear[] = { + {.fl = 4, .lut = 0x1b}, + {.fl = 5, .lut = 0x5b}, + {.fl = 6, .lut = 0x15b}, + {.fl = 7, .lut = 0x55b}, + {.fl = 8, .lut = 0x155b}, + {.fl = 9, .lut = 0x555b}, + {.fl = 10, .lut = 0x1555b}, + {.fl = 11, .lut = 0x5555b}, + {.fl = 12, .lut = 0x15555b}, + {.fl = 13, .lut = 0x55555b}, + {.fl = 14, .lut = 0}, + {.fl = 1, .lut = 0x1b}, + {.fl = 0, .lut = 0} +}; + static const struct dpu_qos_lut_entry sdm845_qos_linear[] = { {.fl = 4, .lut = 0x357}, {.fl = 5, .lut = 0x3357}, @@ -923,6 +1303,15 @@ static const struct dpu_qos_lut_entry sdm845_qos_linear[] = { {.fl = 0, .lut = 0x11222222223357} }; +static const struct dpu_qos_lut_entry msm8998_qos_macrotile[] = { + {.fl = 10, .lut = 0x1aaff}, + {.fl = 11, .lut = 0x5aaff}, + {.fl = 12, .lut = 0x15aaff}, + {.fl = 13, .lut = 0x55aaff}, + {.fl = 1, .lut = 0x1aaff}, + {.fl = 0, .lut = 0}, +}; + static const struct dpu_qos_lut_entry sc7180_qos_linear[] = { {.fl = 0, .lut = 0x0011222222335777}, }; @@ -931,6 +1320,14 @@ static const struct dpu_qos_lut_entry sm8150_qos_linear[] = { {.fl = 0, .lut = 0x0011222222223357 }, }; +static const struct dpu_qos_lut_entry sc8180x_qos_linear[] = { + {.fl = 4, .lut = 0x0000000000000357 }, +}; + +static const struct dpu_qos_lut_entry qcm2290_qos_linear[] = { + {.fl = 0, .lut = 0x0011222222335777}, +}; + static const struct dpu_qos_lut_entry sdm845_qos_macrotile[] = { {.fl = 10, .lut = 0x344556677}, {.fl = 11, .lut = 0x3344556677}, @@ -944,6 +1341,14 @@ static const struct dpu_qos_lut_entry sc7180_qos_macrotile[] = { {.fl = 0, .lut = 0x0011223344556677}, }; +static const struct dpu_qos_lut_entry sc8180x_qos_macrotile[] = { + {.fl = 10, .lut = 0x0000000344556677}, +}; + +static const struct dpu_qos_lut_entry msm8998_qos_nrt[] = { + {.fl = 0, .lut = 0x0}, +}; + static const struct dpu_qos_lut_entry sdm845_qos_nrt[] = { {.fl = 0, .lut = 0x0}, }; @@ -952,6 +1357,42 @@ static const struct dpu_qos_lut_entry sc7180_qos_nrt[] = { {.fl = 0, .lut = 0x0}, }; +static const struct dpu_perf_cfg msm8998_perf_data = { + .max_bw_low = 6700000, + .max_bw_high = 6700000, + .min_core_ib = 2400000, + .min_llcc_ib = 800000, + .min_dram_ib = 800000, + .undersized_prefill_lines = 2, + .xtra_prefill_lines = 2, + .dest_scale_prefill_lines = 3, + .macrotile_prefill_lines = 4, + .yuv_nv12_prefill_lines = 8, + .linear_prefill_lines = 1, + .downscaling_prefill_lines = 1, + .amortizable_threshold = 25, + .min_prefill_lines = 25, + .danger_lut_tbl = {0xf, 0xffff, 0x0}, + .safe_lut_tbl = {0xfffc, 0xff00, 0xffff}, + .qos_lut_tbl = { + {.nentry = ARRAY_SIZE(msm8998_qos_linear), + .entries = msm8998_qos_linear + }, + {.nentry = ARRAY_SIZE(msm8998_qos_macrotile), + .entries = msm8998_qos_macrotile + }, + {.nentry = ARRAY_SIZE(msm8998_qos_nrt), + .entries = msm8998_qos_nrt + }, + }, + .cdp_cfg = { + {.rd_enable = 1, .wr_enable = 1}, + {.rd_enable = 1, .wr_enable = 0} + }, + .clk_inefficiency_factor = 200, + .bw_inefficiency_factor = 120, +}; + static const struct dpu_perf_cfg sdm845_perf_data = { .max_bw_low = 6800000, .max_bw_high = 6800000, @@ -1045,6 +1486,33 @@ static const struct dpu_perf_cfg sm8150_perf_data = { .bw_inefficiency_factor = 120, }; +static const struct dpu_perf_cfg sc8180x_perf_data = { + .max_bw_low = 9600000, + .max_bw_high = 9600000, + .min_core_ib = 2400000, + .min_llcc_ib = 800000, + .min_dram_ib = 800000, + .danger_lut_tbl = {0xf, 0xffff, 0x0}, + .qos_lut_tbl = { + {.nentry = ARRAY_SIZE(sc8180x_qos_linear), + .entries = sc8180x_qos_linear + }, + {.nentry = ARRAY_SIZE(sc8180x_qos_macrotile), + .entries = sc8180x_qos_macrotile + }, + {.nentry = ARRAY_SIZE(sc7180_qos_nrt), + .entries = sc7180_qos_nrt + }, + /* TODO: macrotile-qseed is different from macrotile */ + }, + .cdp_cfg = { + {.rd_enable = 1, .wr_enable = 1}, + {.rd_enable = 1, .wr_enable = 0} + }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, +}; + static const struct dpu_perf_cfg sm8250_perf_data = { .max_bw_low = 13700000, .max_bw_high = 16600000, @@ -1102,11 +1570,62 @@ static const struct dpu_perf_cfg sc7280_perf_data = { .bw_inefficiency_factor = 120, }; +static const struct dpu_perf_cfg qcm2290_perf_data = { + .max_bw_low = 2700000, + .max_bw_high = 2700000, + .min_core_ib = 1300000, + .min_llcc_ib = 0, + .min_dram_ib = 1600000, + .min_prefill_lines = 24, + .danger_lut_tbl = {0xff, 0x0, 0x0}, + .safe_lut_tbl = {0xfff0, 0x0, 0x0}, + .qos_lut_tbl = { + {.nentry = ARRAY_SIZE(qcm2290_qos_linear), + .entries = qcm2290_qos_linear + }, + }, + .cdp_cfg = { + {.rd_enable = 1, .wr_enable = 1}, + {.rd_enable = 1, .wr_enable = 0} + }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, +}; /************************************************************* * Hardware catalog init *************************************************************/ /* + * msm8998_cfg_init(): populate sdm845 dpu sub-blocks reg offsets + * and instance counts. + */ +static void msm8998_cfg_init(struct dpu_mdss_cfg *dpu_cfg) +{ + *dpu_cfg = (struct dpu_mdss_cfg){ + .caps = &msm8998_dpu_caps, + .mdp_count = ARRAY_SIZE(msm8998_mdp), + .mdp = msm8998_mdp, + .ctl_count = ARRAY_SIZE(msm8998_ctl), + .ctl = msm8998_ctl, + .sspp_count = ARRAY_SIZE(msm8998_sspp), + .sspp = msm8998_sspp, + .mixer_count = ARRAY_SIZE(msm8998_lm), + .mixer = msm8998_lm, + .dspp_count = ARRAY_SIZE(msm8998_dspp), + .dspp = msm8998_dspp, + .pingpong_count = ARRAY_SIZE(sdm845_pp), + .pingpong = sdm845_pp, + .intf_count = ARRAY_SIZE(msm8998_intf), + .intf = msm8998_intf, + .vbif_count = ARRAY_SIZE(msm8998_vbif), + .vbif = msm8998_vbif, + .reg_dma_count = 0, + .perf = msm8998_perf_data, + .mdss_irqs = IRQ_SM8250_MASK, + }; +} + +/* * sdm845_cfg_init(): populate sdm845 dpu sub-blocks reg offsets * and instance counts. */ @@ -1200,6 +1719,37 @@ static void sm8150_cfg_init(struct dpu_mdss_cfg *dpu_cfg) } /* + * sc8180x_cfg_init(): populate sc8180 dpu sub-blocks reg offsets + * and instance counts. + */ +static void sc8180x_cfg_init(struct dpu_mdss_cfg *dpu_cfg) +{ + *dpu_cfg = (struct dpu_mdss_cfg){ + .caps = &sc8180x_dpu_caps, + .mdp_count = ARRAY_SIZE(sc8180x_mdp), + .mdp = sc8180x_mdp, + .ctl_count = ARRAY_SIZE(sm8150_ctl), + .ctl = sm8150_ctl, + .sspp_count = ARRAY_SIZE(sdm845_sspp), + .sspp = sdm845_sspp, + .mixer_count = ARRAY_SIZE(sm8150_lm), + .mixer = sm8150_lm, + .pingpong_count = ARRAY_SIZE(sm8150_pp), + .pingpong = sm8150_pp, + .merge_3d_count = ARRAY_SIZE(sm8150_merge_3d), + .merge_3d = sm8150_merge_3d, + .intf_count = ARRAY_SIZE(sc8180x_intf), + .intf = sc8180x_intf, + .vbif_count = ARRAY_SIZE(sdm845_vbif), + .vbif = sdm845_vbif, + .reg_dma_count = 1, + .dma_cfg = sm8150_regdma, + .perf = sc8180x_perf_data, + .mdss_irqs = IRQ_SC8180X_MASK, + }; +} + +/* * sm8250_cfg_init(): populate sm8250 dpu sub-blocks reg offsets * and instance counts. */ @@ -1255,13 +1805,49 @@ static void sc7280_cfg_init(struct dpu_mdss_cfg *dpu_cfg) }; } + +/* + * qcm2290_cfg_init(): populate qcm2290 dpu sub-blocks reg offsets + * and instance counts. + */ +static void qcm2290_cfg_init(struct dpu_mdss_cfg *dpu_cfg) +{ + *dpu_cfg = (struct dpu_mdss_cfg){ + .caps = &qcm2290_dpu_caps, + .mdp_count = ARRAY_SIZE(qcm2290_mdp), + .mdp = qcm2290_mdp, + .ctl_count = ARRAY_SIZE(qcm2290_ctl), + .ctl = qcm2290_ctl, + .sspp_count = ARRAY_SIZE(qcm2290_sspp), + .sspp = qcm2290_sspp, + .mixer_count = ARRAY_SIZE(qcm2290_lm), + .mixer = qcm2290_lm, + .dspp_count = ARRAY_SIZE(qcm2290_dspp), + .dspp = qcm2290_dspp, + .pingpong_count = ARRAY_SIZE(qcm2290_pp), + .pingpong = qcm2290_pp, + .intf_count = ARRAY_SIZE(qcm2290_intf), + .intf = qcm2290_intf, + .vbif_count = ARRAY_SIZE(sdm845_vbif), + .vbif = sdm845_vbif, + .reg_dma_count = 1, + .dma_cfg = sdm845_regdma, + .perf = qcm2290_perf_data, + .mdss_irqs = IRQ_SC7180_MASK, + }; +} + static const struct dpu_mdss_hw_cfg_handler cfg_handler[] = { + { .hw_rev = DPU_HW_VER_300, .cfg_init = msm8998_cfg_init}, + { .hw_rev = DPU_HW_VER_301, .cfg_init = msm8998_cfg_init}, { .hw_rev = DPU_HW_VER_400, .cfg_init = sdm845_cfg_init}, { .hw_rev = DPU_HW_VER_401, .cfg_init = sdm845_cfg_init}, { .hw_rev = DPU_HW_VER_500, .cfg_init = sm8150_cfg_init}, { .hw_rev = DPU_HW_VER_501, .cfg_init = sm8150_cfg_init}, + { .hw_rev = DPU_HW_VER_510, .cfg_init = sc8180x_cfg_init}, { .hw_rev = DPU_HW_VER_600, .cfg_init = sm8250_cfg_init}, { .hw_rev = DPU_HW_VER_620, .cfg_init = sc7180_cfg_init}, + { .hw_rev = DPU_HW_VER_650, .cfg_init = qcm2290_cfg_init}, { .hw_rev = DPU_HW_VER_720, .cfg_init = sc7280_cfg_init}, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h index 31af04afda7d..b85b24bd3f53 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -39,8 +39,10 @@ #define DPU_HW_VER_410 DPU_HW_VER(4, 1, 0) /* sdm670 v1.0 */ #define DPU_HW_VER_500 DPU_HW_VER(5, 0, 0) /* sm8150 v1.0 */ #define DPU_HW_VER_501 DPU_HW_VER(5, 0, 1) /* sm8150 v2.0 */ +#define DPU_HW_VER_510 DPU_HW_VER(5, 1, 1) /* sc8180 */ #define DPU_HW_VER_600 DPU_HW_VER(6, 0, 0) /* sm8250 */ #define DPU_HW_VER_620 DPU_HW_VER(6, 2, 0) /* sc7180 v1.0 */ +#define DPU_HW_VER_650 DPU_HW_VER(6, 5, 0) /* qcm2290|sm4125 */ #define DPU_HW_VER_720 DPU_HW_VER(7, 2, 0) /* sc7280 */ #define IS_MSM8996_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_170) @@ -87,6 +89,7 @@ enum { DPU_MDP_BWC, DPU_MDP_UBWC_1_0, DPU_MDP_UBWC_1_5, + DPU_MDP_AUDIO_SELECT, DPU_MDP_MAX }; @@ -435,6 +438,8 @@ enum dpu_clk_ctrl_type { DPU_CLK_CTRL_RGB3, DPU_CLK_CTRL_DMA0, DPU_CLK_CTRL_DMA1, + DPU_CLK_CTRL_DMA2, + DPU_CLK_CTRL_DMA3, DPU_CLK_CTRL_CURSOR0, DPU_CLK_CTRL_CURSOR1, DPU_CLK_CTRL_INLINE_ROT0_SSPP, @@ -781,22 +786,6 @@ struct dpu_mdss_hw_cfg_handler { void (*cfg_init)(struct dpu_mdss_cfg *dpu_cfg); }; -/* - * Access Macros - */ -#define BLK_MDP(s) ((s)->mdp) -#define BLK_CTL(s) ((s)->ctl) -#define BLK_VIG(s) ((s)->vig) -#define BLK_RGB(s) ((s)->rgb) -#define BLK_DMA(s) ((s)->dma) -#define BLK_CURSOR(s) ((s)->cursor) -#define BLK_MIXER(s) ((s)->mixer) -#define BLK_PINGPONG(s) ((s)->pingpong) -#define BLK_INTF(s) ((s)->intf) -#define BLK_AD(s) ((s)->ad) -#define BLK_DSPP(s) ((s)->dspp) -#define BLK_MERGE3d(s) ((s)->merge_3d) - /** * dpu_hw_catalog_init - dpu hardware catalog init API retrieves * hardcoded target specific catalog information in config structure 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 02da9ecf71f1..3584f5ee6bb3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c @@ -92,6 +92,11 @@ static inline void dpu_hw_ctl_trigger_start(struct dpu_hw_ctl *ctx) DPU_REG_WRITE(&ctx->hw, CTL_START, 0x1); } +static inline bool dpu_hw_ctl_is_started(struct dpu_hw_ctl *ctx) +{ + return !!(DPU_REG_READ(&ctx->hw, CTL_START) & BIT(0)); +} + static inline void dpu_hw_ctl_trigger_pending(struct dpu_hw_ctl *ctx) { trace_dpu_hw_ctl_trigger_prepare(ctx->pending_flush_mask, @@ -587,6 +592,7 @@ static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops, ops->get_pending_flush = dpu_hw_ctl_get_pending_flush; ops->get_flush_register = dpu_hw_ctl_get_flush_register; ops->trigger_start = dpu_hw_ctl_trigger_start; + ops->is_started = dpu_hw_ctl_is_started; ops->trigger_pending = dpu_hw_ctl_trigger_pending; ops->reset = dpu_hw_ctl_reset_control; ops->wait_reset_status = dpu_hw_ctl_wait_reset_status; 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 806c171e5df2..ac1544474022 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h @@ -62,6 +62,13 @@ struct dpu_hw_ctl_ops { void (*trigger_start)(struct dpu_hw_ctl *ctx); /** + * check if the ctl is started + * @ctx : ctl path ctx pointer + * @Return: true if started, false if stopped + */ + bool (*is_started)(struct dpu_hw_ctl *ctx); + + /** * kickoff prepare is in progress hw operation for sw * controlled interfaces: DSI cmd mode and WB interface * are SW controlled diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index a77a5eaa78ad..c515b7cf922c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -13,7 +13,7 @@ #include "dpu_hw_mdss.h" #include "dpu_trace.h" -/** +/* * Register offsets in MDSS register file for the interrupt registers * w.r.t. to the MDP base */ @@ -23,6 +23,7 @@ #define MDP_INTF_2_OFF 0x6B000 #define MDP_INTF_3_OFF 0x6B800 #define MDP_INTF_4_OFF 0x6C000 +#define MDP_INTF_5_OFF 0x6C800 #define MDP_AD4_0_OFF 0x7C000 #define MDP_AD4_1_OFF 0x7D000 #define MDP_AD4_INTR_EN_OFF 0x41c @@ -94,6 +95,11 @@ static const struct dpu_intr_reg dpu_intr_set[] = { MDP_INTF_4_OFF+INTF_INTR_STATUS }, { + MDP_INTF_5_OFF+INTF_INTR_CLEAR, + MDP_INTF_5_OFF+INTF_INTR_EN, + MDP_INTF_5_OFF+INTF_INTR_STATUS + }, + { MDP_AD4_0_OFF + MDP_AD4_INTR_CLEAR_OFF, MDP_AD4_0_OFF + MDP_AD4_INTR_EN_OFF, MDP_AD4_0_OFF + MDP_AD4_INTR_STATUS_OFF, @@ -140,7 +146,7 @@ static const struct dpu_intr_reg dpu_intr_set[] = { /** * dpu_core_irq_callback_handler - dispatch core interrupts - * @arg: private data of callback handler + * @dpu_kms: Pointer to DPU's KMS structure * @irq_idx: interrupt index */ static void dpu_core_irq_callback_handler(struct dpu_kms *dpu_kms, int irq_idx) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h index 1ab75cccd145..37379966d8ec 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h @@ -22,6 +22,7 @@ enum dpu_hw_intr_reg { MDP_INTF2_INTR, MDP_INTF3_INTR, MDP_INTF4_INTR, + MDP_INTF5_INTR, MDP_AD4_0_INTR, MDP_AD4_1_INTR, MDP_INTF0_7xxx_INTR, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h index 3568be80dab5..230d122fa43b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h @@ -78,7 +78,6 @@ struct dpu_hw_intf_ops { }; struct dpu_hw_intf { - struct dpu_hw_blk base; struct dpu_hw_blk_reg_map hw; /* intf */ @@ -91,16 +90,6 @@ struct dpu_hw_intf { }; /** - * to_dpu_hw_intf - convert base object dpu_hw_base to container - * @hw: Pointer to base hardware block - * return: Pointer to hardware block container - */ -static inline struct dpu_hw_intf *to_dpu_hw_intf(struct dpu_hw_blk *hw) -{ - return container_of(hw, struct dpu_hw_intf, base); -} - -/** * dpu_hw_intf_init(): Initializes the intf driver for the passed * interface idx. * @idx: interface index for which driver object is required diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c index 282e3c6c6d48..ab3ef162b666 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c @@ -268,7 +268,9 @@ static void _setup_mdp_ops(struct dpu_hw_mdp_ops *ops, ops->get_danger_status = dpu_hw_get_danger_status; ops->setup_vsync_source = dpu_hw_setup_vsync_source; ops->get_safe_status = dpu_hw_get_safe_status; - ops->intf_audio_select = dpu_hw_intf_audio_select; + + if (cap & BIT(DPU_MDP_AUDIO_SELECT)) + ops->intf_audio_select = dpu_hw_intf_audio_select; } static const struct dpu_mdp_cfg *_top_offset(enum dpu_mdp mdp, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 47fe11a84a77..e29796c4f27b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -271,6 +271,10 @@ static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor) if (!p) return -EINVAL; + /* Only create a set of debugfs for the primary node, ignore render nodes */ + if (minor->type != DRM_MINOR_PRIMARY) + return 0; + dev = dpu_kms->dev; priv = dev->dev_private; @@ -774,12 +778,6 @@ fail: return ret; } -static long dpu_kms_round_pixclk(struct msm_kms *kms, unsigned long rate, - struct drm_encoder *encoder) -{ - return rate; -} - static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms) { int i; @@ -948,7 +946,6 @@ static const struct msm_kms_funcs kms_funcs = { .disable_vblank = dpu_kms_disable_vblank, .check_modified_format = dpu_format_check_modified_format, .get_format = dpu_get_msm_format, - .round_pixclk = dpu_kms_round_pixclk, .destroy = dpu_kms_destroy, .snapshot = dpu_kms_mdp_snapshot, #ifdef CONFIG_DEBUG_FS @@ -998,29 +995,15 @@ static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms) return 0; } -static struct dss_clk *_dpu_kms_get_clk(struct dpu_kms *dpu_kms, - char *clock_name) -{ - struct dss_module_power *mp = &dpu_kms->mp; - int i; - - for (i = 0; i < mp->num_clk; i++) { - if (!strcmp(mp->clk_config[i].clk_name, clock_name)) - return &mp->clk_config[i]; - } - - return NULL; -} - u64 dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name) { - struct dss_clk *clk; + struct clk *clk; - clk = _dpu_kms_get_clk(dpu_kms, clock_name); + clk = msm_clk_bulk_get_clock(dpu_kms->clocks, dpu_kms->num_clocks, clock_name); if (!clk) return -EINVAL; - return clk_get_rate(clk->clk); + return clk_get_rate(clk); } static int dpu_kms_hw_init(struct msm_kms *kms) @@ -1043,7 +1026,7 @@ static int dpu_kms_hw_init(struct msm_kms *kms) atomic_set(&dpu_kms->bandwidth_ref, 0); - dpu_kms->mmio = msm_ioremap(dpu_kms->pdev, "mdp", "mdp"); + dpu_kms->mmio = msm_ioremap(dpu_kms->pdev, "mdp"); if (IS_ERR(dpu_kms->mmio)) { rc = PTR_ERR(dpu_kms->mmio); DPU_ERROR("mdp register memory map failed: %d\n", rc); @@ -1052,20 +1035,20 @@ static int dpu_kms_hw_init(struct msm_kms *kms) } DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio); - dpu_kms->vbif[VBIF_RT] = msm_ioremap(dpu_kms->pdev, "vbif", "vbif"); + dpu_kms->vbif[VBIF_RT] = msm_ioremap(dpu_kms->pdev, "vbif"); if (IS_ERR(dpu_kms->vbif[VBIF_RT])) { rc = PTR_ERR(dpu_kms->vbif[VBIF_RT]); DPU_ERROR("vbif register memory map failed: %d\n", rc); dpu_kms->vbif[VBIF_RT] = NULL; goto error; } - dpu_kms->vbif[VBIF_NRT] = msm_ioremap_quiet(dpu_kms->pdev, "vbif_nrt", "vbif_nrt"); + dpu_kms->vbif[VBIF_NRT] = msm_ioremap_quiet(dpu_kms->pdev, "vbif_nrt"); if (IS_ERR(dpu_kms->vbif[VBIF_NRT])) { dpu_kms->vbif[VBIF_NRT] = NULL; DPU_DEBUG("VBIF NRT is not defined"); } - dpu_kms->reg_dma = msm_ioremap_quiet(dpu_kms->pdev, "regdma", "regdma"); + dpu_kms->reg_dma = msm_ioremap_quiet(dpu_kms->pdev, "regdma"); if (IS_ERR(dpu_kms->reg_dma)) { dpu_kms->reg_dma = NULL; DPU_DEBUG("REG_DMA is not defined"); @@ -1132,7 +1115,7 @@ static int dpu_kms_hw_init(struct msm_kms *kms) } rc = dpu_core_perf_init(&dpu_kms->perf, dev, dpu_kms->catalog, - _dpu_kms_get_clk(dpu_kms, "core")); + msm_clk_bulk_get_clock(dpu_kms->clocks, dpu_kms->num_clocks, "core")); if (rc) { DPU_ERROR("failed to init perf %d\n", rc); goto perf_err; @@ -1219,7 +1202,6 @@ static int dpu_bind(struct device *dev, struct device *master, void *data) struct platform_device *pdev = to_platform_device(dev); struct drm_device *ddev = priv->dev; struct dpu_kms *dpu_kms; - struct dss_module_power *mp; int ret = 0; dpu_kms = devm_kzalloc(&pdev->dev, sizeof(*dpu_kms), GFP_KERNEL); @@ -1236,12 +1218,12 @@ static int dpu_bind(struct device *dev, struct device *master, void *data) return ret; } - mp = &dpu_kms->mp; - ret = msm_dss_parse_clock(pdev, mp); - if (ret) { + ret = devm_clk_bulk_get_all(&pdev->dev, &dpu_kms->clocks); + if (ret < 0) { DPU_ERROR("failed to parse clocks, ret=%d\n", ret); return ret; } + dpu_kms->num_clocks = ret; platform_set_drvdata(pdev, dpu_kms); @@ -1265,11 +1247,6 @@ static void dpu_unbind(struct device *dev, struct device *master, void *data) { struct platform_device *pdev = to_platform_device(dev); struct dpu_kms *dpu_kms = platform_get_drvdata(pdev); - struct dss_module_power *mp = &dpu_kms->mp; - - msm_dss_put_clk(mp->clk_config, mp->num_clk); - devm_kfree(&pdev->dev, mp->clk_config); - mp->num_clk = 0; if (dpu_kms->rpm_enabled) pm_runtime_disable(&pdev->dev); @@ -1293,21 +1270,18 @@ static int dpu_dev_remove(struct platform_device *pdev) static int __maybe_unused dpu_runtime_suspend(struct device *dev) { - int i, rc = -1; + int i; struct platform_device *pdev = to_platform_device(dev); struct dpu_kms *dpu_kms = platform_get_drvdata(pdev); - struct dss_module_power *mp = &dpu_kms->mp; /* Drop the performance state vote */ dev_pm_opp_set_rate(dev, 0); - rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false); - if (rc) - DPU_ERROR("clock disable failed rc:%d\n", rc); + clk_bulk_disable_unprepare(dpu_kms->num_clocks, dpu_kms->clocks); for (i = 0; i < dpu_kms->num_paths; i++) icc_set_bw(dpu_kms->path[i], 0, 0); - return rc; + return 0; } static int __maybe_unused dpu_runtime_resume(struct device *dev) @@ -1317,7 +1291,6 @@ static int __maybe_unused dpu_runtime_resume(struct device *dev) struct dpu_kms *dpu_kms = platform_get_drvdata(pdev); struct drm_encoder *encoder; struct drm_device *ddev; - struct dss_module_power *mp = &dpu_kms->mp; int i; ddev = dpu_kms->dev; @@ -1327,7 +1300,7 @@ static int __maybe_unused dpu_runtime_resume(struct device *dev) for (i = 0; i < dpu_kms->num_paths; i++) icc_set_bw(dpu_kms->path[i], 0, Bps_to_icc(MIN_IB_BW)); - rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true); + rc = clk_bulk_prepare_enable(dpu_kms->num_clocks, dpu_kms->clocks); if (rc) { DPU_ERROR("clock enable failed rc:%d\n", rc); return rc; @@ -1348,9 +1321,12 @@ static const struct dev_pm_ops dpu_pm_ops = { }; const struct of_device_id dpu_dt_match[] = { + { .compatible = "qcom,msm8998-dpu", }, + { .compatible = "qcom,qcm2290-dpu", }, { .compatible = "qcom,sdm845-dpu", }, { .compatible = "qcom,sc7180-dpu", }, { .compatible = "qcom,sc7280-dpu", }, + { .compatible = "qcom,sc8180x-dpu", }, { .compatible = "qcom,sm8150-dpu", }, { .compatible = "qcom,sm8250-dpu", }, {} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index 2d385b4b7f5e..779e7bd01efd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -21,7 +21,6 @@ #include "dpu_hw_lm.h" #include "dpu_hw_interrupts.h" #include "dpu_hw_top.h" -#include "dpu_io_util.h" #include "dpu_rm.h" #include "dpu_core_perf.h" @@ -113,7 +112,8 @@ struct dpu_kms { struct platform_device *pdev; bool rpm_enabled; - struct dss_module_power mp; + struct clk_bulk_data *clocks; + size_t num_clocks; /* reference count bandwidth requests, so we know when we can * release bandwidth. Each atomic update increments, and frame- @@ -144,7 +144,6 @@ struct dpu_global_state { 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 intf_to_enc_id[INTF_MAX - INTF_0]; uint32_t dspp_to_enc_id[DSPP_MAX - DSPP_0]; }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c index 131c1f1a869c..b10ca505f9ac 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c @@ -29,7 +29,8 @@ struct dpu_irq_controller { struct dpu_mdss { struct msm_mdss base; void __iomem *mmio; - struct dss_module_power mp; + struct clk_bulk_data *clocks; + size_t num_clocks; struct dpu_irq_controller irq_controller; }; @@ -136,10 +137,9 @@ static void _dpu_mdss_irq_domain_fini(struct dpu_mdss *dpu_mdss) static int dpu_mdss_enable(struct msm_mdss *mdss) { struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss); - struct dss_module_power *mp = &dpu_mdss->mp; int ret; - ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true); + ret = clk_bulk_prepare_enable(dpu_mdss->num_clocks, dpu_mdss->clocks); if (ret) { DPU_ERROR("clock enable failed, ret:%d\n", ret); return ret; @@ -174,21 +174,16 @@ static int dpu_mdss_enable(struct msm_mdss *mdss) static int dpu_mdss_disable(struct msm_mdss *mdss) { struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss); - struct dss_module_power *mp = &dpu_mdss->mp; - int ret; - ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false); - if (ret) - DPU_ERROR("clock disable failed, ret:%d\n", ret); + clk_bulk_disable_unprepare(dpu_mdss->num_clocks, dpu_mdss->clocks); - return ret; + return 0; } static void dpu_mdss_destroy(struct msm_mdss *mdss) { struct platform_device *pdev = to_platform_device(mdss->dev); struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss); - struct dss_module_power *mp = &dpu_mdss->mp; int irq; pm_runtime_suspend(mdss->dev); @@ -196,8 +191,6 @@ static void dpu_mdss_destroy(struct msm_mdss *mdss) _dpu_mdss_irq_domain_fini(dpu_mdss); irq = platform_get_irq(pdev, 0); irq_set_chained_handler_and_data(irq, NULL, NULL); - msm_dss_put_clk(mp->clk_config, mp->num_clk); - devm_kfree(&pdev->dev, mp->clk_config); if (dpu_mdss->mmio) devm_iounmap(&pdev->dev, dpu_mdss->mmio); @@ -214,7 +207,6 @@ int dpu_mdss_init(struct platform_device *pdev) { struct msm_drm_private *priv = platform_get_drvdata(pdev); struct dpu_mdss *dpu_mdss; - struct dss_module_power *mp; int ret; int irq; @@ -222,18 +214,18 @@ int dpu_mdss_init(struct platform_device *pdev) if (!dpu_mdss) return -ENOMEM; - dpu_mdss->mmio = msm_ioremap(pdev, "mdss", "mdss"); + dpu_mdss->mmio = msm_ioremap(pdev, "mdss"); if (IS_ERR(dpu_mdss->mmio)) return PTR_ERR(dpu_mdss->mmio); DRM_DEBUG("mapped mdss address space @%pK\n", dpu_mdss->mmio); - mp = &dpu_mdss->mp; - ret = msm_dss_parse_clock(pdev, mp); - if (ret) { + ret = devm_clk_bulk_get_all(&pdev->dev, &dpu_mdss->clocks); + if (ret < 0) { DPU_ERROR("failed to parse clocks, ret=%d\n", ret); goto clk_parse_err; } + dpu_mdss->num_clocks = ret; dpu_mdss->base.dev = &pdev->dev; dpu_mdss->base.funcs = &mdss_funcs; @@ -260,9 +252,7 @@ int dpu_mdss_init(struct platform_device *pdev) irq_error: _dpu_mdss_irq_domain_fini(dpu_mdss); irq_domain_error: - msm_dss_put_clk(mp->clk_config, mp->num_clk); clk_parse_err: - devm_kfree(&pdev->dev, mp->clk_config); if (dpu_mdss->mmio) devm_iounmap(&pdev->dev, dpu_mdss->mmio); dpu_mdss->mmio = NULL; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index ca75089c9d61..6565682fe227 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -902,7 +902,7 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane, if (pstate->aspace) { ret = msm_framebuffer_prepare(new_state->fb, - pstate->aspace); + pstate->aspace, pstate->needs_dirtyfb); if (ret) { DPU_ERROR("failed to prepare framebuffer\n"); return ret; @@ -933,7 +933,8 @@ static void dpu_plane_cleanup_fb(struct drm_plane *plane, DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", old_state->fb->base.id); - msm_framebuffer_cleanup(old_state->fb, old_pstate->aspace); + msm_framebuffer_cleanup(old_state->fb, old_pstate->aspace, + old_pstate->needs_dirtyfb); } static bool dpu_plane_validate_src(struct drm_rect *src, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h index 9d51dad5c6a5..50781e2d3577 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h @@ -25,6 +25,7 @@ * @pending: whether the current update is still pending * @plane_fetch_bw: calculated BW per plane * @plane_clk: calculated clk per plane + * @needs_dirtyfb: whether attached CRTC needs pixel data explicitly flushed */ struct dpu_plane_state { struct drm_plane_state base; @@ -37,6 +38,8 @@ struct dpu_plane_state { u64 plane_fetch_bw; u64 plane_clk; + + bool needs_dirtyfb; }; /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index f9c83d6e427a..7497538adae1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -28,13 +28,20 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx, */ struct dpu_rm_requirements { struct msm_display_topology topology; - struct dpu_encoder_hw_resources hw_res; }; int dpu_rm_destroy(struct dpu_rm *rm) { int i; + for (i = 0; i < ARRAY_SIZE(rm->dspp_blks); i++) { + struct dpu_hw_dspp *hw; + + if (rm->dspp_blks[i]) { + hw = to_dpu_hw_dspp(rm->dspp_blks[i]); + dpu_hw_dspp_destroy(hw); + } + } for (i = 0; i < ARRAY_SIZE(rm->pingpong_blks); i++) { struct dpu_hw_pingpong *hw; @@ -67,14 +74,8 @@ int dpu_rm_destroy(struct dpu_rm *rm) dpu_hw_ctl_destroy(hw); } } - for (i = 0; i < ARRAY_SIZE(rm->intf_blks); i++) { - struct dpu_hw_intf *hw; - - if (rm->intf_blks[i]) { - hw = to_dpu_hw_intf(rm->intf_blks[i]); - dpu_hw_intf_destroy(hw); - } - } + for (i = 0; i < ARRAY_SIZE(rm->hw_intf); i++) + dpu_hw_intf_destroy(rm->hw_intf[i]); return 0; } @@ -108,24 +109,12 @@ int dpu_rm_init(struct dpu_rm *rm, continue; } hw = dpu_hw_lm_init(lm->id, mmio, cat); - if (IS_ERR_OR_NULL(hw)) { + if (IS_ERR(hw)) { rc = PTR_ERR(hw); DPU_ERROR("failed lm object creation: err %d\n", rc); goto fail; } rm->mixer_blks[lm->id - LM_0] = &hw->base; - - if (!rm->lm_max_width) { - rm->lm_max_width = lm->sblk->maxwidth; - } else if (rm->lm_max_width != lm->sblk->maxwidth) { - /* - * Don't expect to have hw where lm max widths differ. - * If found, take the min. - */ - DPU_ERROR("unsupported: lm maxwidth differs\n"); - if (rm->lm_max_width > lm->sblk->maxwidth) - rm->lm_max_width = lm->sblk->maxwidth; - } } for (i = 0; i < cat->merge_3d_count; i++) { @@ -137,7 +126,7 @@ int dpu_rm_init(struct dpu_rm *rm, continue; } hw = dpu_hw_merge_3d_init(merge_3d->id, mmio, cat); - if (IS_ERR_OR_NULL(hw)) { + if (IS_ERR(hw)) { rc = PTR_ERR(hw); DPU_ERROR("failed merge_3d object creation: err %d\n", rc); @@ -155,7 +144,7 @@ int dpu_rm_init(struct dpu_rm *rm, continue; } hw = dpu_hw_pingpong_init(pp->id, mmio, cat); - if (IS_ERR_OR_NULL(hw)) { + if (IS_ERR(hw)) { rc = PTR_ERR(hw); DPU_ERROR("failed pingpong object creation: err %d\n", rc); @@ -179,12 +168,12 @@ int dpu_rm_init(struct dpu_rm *rm, continue; } hw = dpu_hw_intf_init(intf->id, mmio, cat); - if (IS_ERR_OR_NULL(hw)) { + if (IS_ERR(hw)) { rc = PTR_ERR(hw); DPU_ERROR("failed intf object creation: err %d\n", rc); goto fail; } - rm->intf_blks[intf->id - INTF_0] = &hw->base; + rm->hw_intf[intf->id - INTF_0] = hw; } for (i = 0; i < cat->ctl_count; i++) { @@ -196,7 +185,7 @@ int dpu_rm_init(struct dpu_rm *rm, continue; } hw = dpu_hw_ctl_init(ctl->id, mmio, cat); - if (IS_ERR_OR_NULL(hw)) { + if (IS_ERR(hw)) { rc = PTR_ERR(hw); DPU_ERROR("failed ctl object creation: err %d\n", rc); goto fail; @@ -213,7 +202,7 @@ int dpu_rm_init(struct dpu_rm *rm, continue; } hw = dpu_hw_dspp_init(dspp->id, mmio, cat); - if (IS_ERR_OR_NULL(hw)) { + if (IS_ERR(hw)) { rc = PTR_ERR(hw); DPU_ERROR("failed dspp object creation: err %d\n", rc); goto fail; @@ -452,54 +441,6 @@ static int _dpu_rm_reserve_ctls( return 0; } -static int _dpu_rm_reserve_intf( - struct dpu_rm *rm, - struct dpu_global_state *global_state, - uint32_t enc_id, - uint32_t id) -{ - int idx = id - INTF_0; - - if (idx < 0 || idx >= ARRAY_SIZE(rm->intf_blks)) { - DPU_ERROR("invalid intf id: %d", id); - return -EINVAL; - } - - if (!rm->intf_blks[idx]) { - DPU_ERROR("couldn't find intf id %d\n", id); - return -EINVAL; - } - - if (reserved_by_other(global_state->intf_to_enc_id, idx, enc_id)) { - DPU_ERROR("intf id %d already reserved\n", id); - return -ENAVAIL; - } - - global_state->intf_to_enc_id[idx] = enc_id; - return 0; -} - -static int _dpu_rm_reserve_intf_related_hw( - struct dpu_rm *rm, - struct dpu_global_state *global_state, - uint32_t enc_id, - struct dpu_encoder_hw_resources *hw_res) -{ - int i, ret = 0; - u32 id; - - for (i = 0; i < ARRAY_SIZE(hw_res->intfs); i++) { - if (hw_res->intfs[i] == INTF_MODE_NONE) - continue; - id = i + INTF_0; - ret = _dpu_rm_reserve_intf(rm, global_state, enc_id, id); - if (ret) - return ret; - } - - return ret; -} - static int _dpu_rm_make_reservation( struct dpu_rm *rm, struct dpu_global_state *global_state, @@ -521,11 +462,6 @@ static int _dpu_rm_make_reservation( return ret; } - ret = _dpu_rm_reserve_intf_related_hw(rm, global_state, enc->base.id, - &reqs->hw_res); - if (ret) - return ret; - return ret; } @@ -534,8 +470,6 @@ static int _dpu_rm_populate_requirements( struct dpu_rm_requirements *reqs, struct msm_display_topology req_topology) { - dpu_encoder_get_hw_resources(enc, &reqs->hw_res); - reqs->topology = req_topology; DRM_DEBUG_KMS("num_lm: %d num_enc: %d num_intf: %d\n", @@ -565,8 +499,6 @@ void dpu_rm_release(struct dpu_global_state *global_state, 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->intf_to_enc_id, - ARRAY_SIZE(global_state->intf_to_enc_id), enc->base.id); } int dpu_rm_reserve( @@ -630,11 +562,6 @@ int dpu_rm_get_assigned_resources(struct dpu_rm *rm, hw_to_enc_id = global_state->ctl_to_enc_id; max_blks = ARRAY_SIZE(rm->ctl_blks); break; - case DPU_HW_BLK_INTF: - hw_blks = rm->intf_blks; - hw_to_enc_id = global_state->intf_to_enc_id; - max_blks = ARRAY_SIZE(rm->intf_blks); - break; case DPU_HW_BLK_DSPP: hw_blks = rm->dspp_blks; hw_to_enc_id = global_state->dspp_to_enc_id; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h index 1f12c8d5b8aa..9b13200a050a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h @@ -18,20 +18,16 @@ struct dpu_global_state; * @pingpong_blks: array of pingpong hardware resources * @mixer_blks: array of layer mixer hardware resources * @ctl_blks: array of ctl hardware resources - * @intf_blks: array of intf hardware resources + * @hw_intf: array of intf hardware resources * @dspp_blks: array of dspp hardware resources - * @lm_max_width: cached layer mixer maximum width - * @rm_lock: resource manager mutex */ struct dpu_rm { struct dpu_hw_blk *pingpong_blks[PINGPONG_MAX - PINGPONG_0]; struct dpu_hw_blk *mixer_blks[LM_MAX - LM_0]; struct dpu_hw_blk *ctl_blks[CTL_MAX - CTL_0]; - struct dpu_hw_blk *intf_blks[INTF_MAX - INTF_0]; + struct dpu_hw_intf *hw_intf[INTF_MAX - INTF_0]; struct dpu_hw_blk *dspp_blks[DSPP_MAX - DSPP_0]; struct dpu_hw_blk *merge_3d_blks[MERGE_3D_MAX - MERGE_3D_0]; - - uint32_t lm_max_width; }; /** @@ -88,5 +84,16 @@ void dpu_rm_release(struct dpu_global_state *global_state, int dpu_rm_get_assigned_resources(struct dpu_rm *rm, struct dpu_global_state *global_state, uint32_t enc_id, enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size); + +/** + * dpu_rm_get_intf - Return a struct dpu_hw_intf instance given it's index. + * @rm: DPU Resource Manager handle + * @intf_idx: INTF's index + */ +static inline struct dpu_hw_intf *dpu_rm_get_intf(struct dpu_rm *rm, enum dpu_intf intf_idx) +{ + return rm->hw_intf[intf_idx - INTF_0]; +} + #endif /* __DPU_RM_H__ */ diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4.xml.h b/drivers/gpu/drm/msm/disp/mdp4/mdp4.xml.h index c82d1bd09359..a2b6422948ec 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4.xml.h +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c index 5a33bb148e9e..3cf476c55158 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c @@ -418,7 +418,7 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev) mdp4_kms->dev = dev; - mdp4_kms->mmio = msm_ioremap(pdev, NULL, "MDP4"); + mdp4_kms->mmio = msm_ioremap(pdev, NULL); if (IS_ERR(mdp4_kms->mmio)) { ret = PTR_ERR(mdp4_kms->mmio); goto fail; diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c index 49bdabea8ed5..3e20f72d75ef 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c @@ -7,6 +7,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_damage_helper.h> #include <drm/drm_fourcc.h> +#include <drm/drm_gem_atomic_helper.h> #include "mdp4_kms.h" @@ -90,6 +91,20 @@ static const struct drm_plane_funcs mdp4_plane_funcs = { .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, }; +static int mdp4_plane_prepare_fb(struct drm_plane *plane, + struct drm_plane_state *new_state) +{ + struct msm_drm_private *priv = plane->dev->dev_private; + struct msm_kms *kms = priv->kms; + + if (!new_state->fb) + return 0; + + drm_gem_plane_helper_prepare_fb(plane, new_state); + + return msm_framebuffer_prepare(new_state->fb, kms->aspace, false); +} + static void mdp4_plane_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *old_state) { @@ -102,7 +117,7 @@ static void mdp4_plane_cleanup_fb(struct drm_plane *plane, return; DBG("%s: cleanup: FB[%u]", mdp4_plane->name, fb->base.id); - msm_framebuffer_cleanup(fb, kms->aspace); + msm_framebuffer_cleanup(fb, kms->aspace, false); } @@ -130,7 +145,7 @@ static void mdp4_plane_atomic_update(struct drm_plane *plane, } static const struct drm_plane_helper_funcs mdp4_plane_helper_funcs = { - .prepare_fb = msm_atomic_prepare_fb, + .prepare_fb = mdp4_plane_prepare_fb, .cleanup_fb = mdp4_plane_cleanup_fb, .atomic_check = mdp4_plane_atomic_check, .atomic_update = mdp4_plane_atomic_update, diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5.xml.h b/drivers/gpu/drm/msm/disp/mdp5/mdp5.xml.h index 0e21cf3f9e2e..86fc44b518cb 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5.xml.h +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c index bb7d066618e6..b966cd69f99d 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c @@ -690,6 +690,8 @@ static int mdp5_crtc_atomic_check(struct drm_crtc *crtc, { struct drm_crtc_state *crtc_state = drm_atomic_get_new_crtc_state(state, crtc); + struct mdp5_crtc_state *mdp5_cstate = to_mdp5_crtc_state(crtc_state); + struct mdp5_interface *intf = mdp5_cstate->pipeline.intf; struct mdp5_kms *mdp5_kms = get_kms(crtc); struct drm_plane *plane; struct drm_device *dev = crtc->dev; @@ -706,12 +708,18 @@ static int mdp5_crtc_atomic_check(struct drm_crtc *crtc, DBG("%s: check", crtc->name); drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) { + struct mdp5_plane_state *mdp5_pstate = + to_mdp5_plane_state(pstate); + if (!pstate->visible) continue; pstates[cnt].plane = plane; pstates[cnt].state = to_mdp5_plane_state(pstate); + mdp5_pstate->needs_dirtyfb = + intf->mode == MDP5_INTF_DSI_MODE_COMMAND; + /* * if any plane on this crtc uses 2 hwpipes, then we need * the crtc to have a right hwmixer. diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index 12a5f81e402b..3b92372e7bdf 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -190,12 +190,6 @@ static void mdp5_complete_commit(struct msm_kms *kms, unsigned crtc_mask) mdp5_smp_complete_commit(mdp5_kms->smp, &global_state->smp); } -static long mdp5_round_pixclk(struct msm_kms *kms, unsigned long rate, - struct drm_encoder *encoder) -{ - return rate; -} - static int mdp5_set_split_display(struct msm_kms *kms, struct drm_encoder *encoder, struct drm_encoder *slave_encoder, @@ -278,7 +272,6 @@ static const struct mdp_kms_funcs kms_funcs = { .wait_flush = mdp5_wait_flush, .complete_commit = mdp5_complete_commit, .get_format = mdp_get_format, - .round_pixclk = mdp5_round_pixclk, .set_split_display = mdp5_set_split_display, .destroy = mdp5_kms_destroy, #ifdef CONFIG_DEBUG_FS @@ -827,7 +820,7 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev) if (ret) goto fail; - mdp5_kms->mmio = msm_ioremap(pdev, "mdp_phys", "MDP5"); + mdp5_kms->mmio = msm_ioremap(pdev, "mdp_phys"); if (IS_ERR(mdp5_kms->mmio)) { ret = PTR_ERR(mdp5_kms->mmio); goto fail; diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h index ac269a6802df..29bf11f08601 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h @@ -100,6 +100,11 @@ struct mdp5_plane_state { /* assigned by crtc blender */ enum mdp_mixer_stage_id stage; + + /* whether attached CRTC needs pixel data explicitly flushed to + * display (ex. DSI command mode display) + */ + bool needs_dirtyfb; }; #define to_mdp5_plane_state(x) \ container_of(x, struct mdp5_plane_state, base) diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c index b3f79c2277e9..049c6784a531 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c @@ -210,13 +210,13 @@ int mdp5_mdss_init(struct platform_device *pdev) mdp5_mdss->base.dev = &pdev->dev; - mdp5_mdss->mmio = msm_ioremap(pdev, "mdss_phys", "MDSS"); + mdp5_mdss->mmio = msm_ioremap(pdev, "mdss_phys"); if (IS_ERR(mdp5_mdss->mmio)) { ret = PTR_ERR(mdp5_mdss->mmio); goto fail; } - mdp5_mdss->vbif = msm_ioremap(pdev, "vbif_phys", "VBIF"); + mdp5_mdss->vbif = msm_ioremap(pdev, "vbif_phys"); if (IS_ERR(mdp5_mdss->vbif)) { ret = PTR_ERR(mdp5_mdss->vbif); goto fail; diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c index c6b69afcbac8..1ee824600995 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c @@ -8,6 +8,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_damage_helper.h> #include <drm/drm_fourcc.h> +#include <drm/drm_gem_atomic_helper.h> #include <drm/drm_print.h> #include "mdp5_kms.h" @@ -48,6 +49,8 @@ static void mdp5_plane_destroy(struct drm_plane *plane) static void mdp5_plane_install_properties(struct drm_plane *plane, struct drm_mode_object *obj) { + unsigned int zpos; + drm_plane_create_rotation_property(plane, DRM_MODE_ROTATE_0, DRM_MODE_ROTATE_0 | @@ -59,7 +62,12 @@ static void mdp5_plane_install_properties(struct drm_plane *plane, BIT(DRM_MODE_BLEND_PIXEL_NONE) | BIT(DRM_MODE_BLEND_PREMULTI) | BIT(DRM_MODE_BLEND_COVERAGE)); - drm_plane_create_zpos_property(plane, 1, 1, 255); + + if (plane->type == DRM_PLANE_TYPE_PRIMARY) + zpos = STAGE_BASE; + else + zpos = STAGE0 + drm_plane_index(plane); + drm_plane_create_zpos_property(plane, zpos, 1, 255); } static void @@ -91,13 +99,6 @@ static void mdp5_plane_reset(struct drm_plane *plane) kfree(to_mdp5_plane_state(plane->state)); mdp5_state = kzalloc(sizeof(*mdp5_state), GFP_KERNEL); - - if (plane->type == DRM_PLANE_TYPE_PRIMARY) - mdp5_state->base.zpos = STAGE_BASE; - else - mdp5_state->base.zpos = STAGE0 + drm_plane_index(plane); - mdp5_state->base.normalized_zpos = mdp5_state->base.zpos; - __drm_atomic_helper_plane_reset(plane, &mdp5_state->base); } @@ -140,18 +141,34 @@ static const struct drm_plane_funcs mdp5_plane_funcs = { .atomic_print_state = mdp5_plane_atomic_print_state, }; +static int mdp5_plane_prepare_fb(struct drm_plane *plane, + struct drm_plane_state *new_state) +{ + struct msm_drm_private *priv = plane->dev->dev_private; + struct msm_kms *kms = priv->kms; + bool needs_dirtyfb = to_mdp5_plane_state(new_state)->needs_dirtyfb; + + if (!new_state->fb) + return 0; + + drm_gem_plane_helper_prepare_fb(plane, new_state); + + return msm_framebuffer_prepare(new_state->fb, kms->aspace, needs_dirtyfb); +} + static void mdp5_plane_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *old_state) { struct mdp5_kms *mdp5_kms = get_kms(plane); struct msm_kms *kms = &mdp5_kms->base.base; struct drm_framebuffer *fb = old_state->fb; + bool needed_dirtyfb = to_mdp5_plane_state(old_state)->needs_dirtyfb; if (!fb) return; DBG("%s: cleanup: FB[%u]", plane->name, fb->base.id); - msm_framebuffer_cleanup(fb, kms->aspace); + msm_framebuffer_cleanup(fb, kms->aspace, needed_dirtyfb); } static int mdp5_plane_atomic_check_with_state(struct drm_crtc_state *crtc_state, @@ -437,7 +454,7 @@ static void mdp5_plane_atomic_async_update(struct drm_plane *plane, } static const struct drm_plane_helper_funcs mdp5_plane_helper_funcs = { - .prepare_fb = msm_atomic_prepare_fb, + .prepare_fb = mdp5_plane_prepare_fb, .cleanup_fb = mdp5_plane_cleanup_fb, .atomic_check = mdp5_plane_atomic_check, .atomic_update = mdp5_plane_atomic_update, diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c index d7fa2c49e741..56a3063545ec 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c @@ -68,7 +68,7 @@ static int smp_request_block(struct mdp5_smp *smp, uint8_t reserved; /* we shouldn't be requesting blocks for an in-use client: */ - WARN_ON(bitmap_weight(cs, cnt) > 0); + WARN_ON(!bitmap_empty(cs, cnt)); reserved = smp->reserved[cid]; diff --git a/drivers/gpu/drm/msm/disp/mdp_common.xml.h b/drivers/gpu/drm/msm/disp/mdp_common.xml.h index bb0066a63732..be759106b621 100644 --- a/drivers/gpu/drm/msm/disp/mdp_common.xml.h +++ b/drivers/gpu/drm/msm/disp/mdp_common.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c index 8a6d3ead3440..fac815fb6d91 100644 --- a/drivers/gpu/drm/msm/dp/dp_catalog.c +++ b/drivers/gpu/drm/msm/dp/dp_catalog.c @@ -456,19 +456,19 @@ void dp_catalog_ctrl_config_msa(struct dp_catalog *dp_catalog, dp_write_p0(catalog, MMSS_DP_DSC_DTO, 0x0); } -int dp_catalog_ctrl_set_pattern(struct dp_catalog *dp_catalog, - u32 pattern) +int dp_catalog_ctrl_set_pattern_state_bit(struct dp_catalog *dp_catalog, + u32 state_bit) { int bit, ret; u32 data; struct dp_catalog_private *catalog = container_of(dp_catalog, struct dp_catalog_private, dp_catalog); - bit = BIT(pattern - 1); - DRM_DEBUG_DP("hw: bit=%d train=%d\n", bit, pattern); + bit = BIT(state_bit - 1); + DRM_DEBUG_DP("hw: bit=%d train=%d\n", bit, state_bit); dp_catalog_ctrl_state_ctrl(dp_catalog, bit); - bit = BIT(pattern - 1) << DP_MAINLINK_READY_LINK_TRAINING_SHIFT; + bit = BIT(state_bit - 1) << DP_MAINLINK_READY_LINK_TRAINING_SHIFT; /* Poll for mainlink ready status */ ret = readx_poll_timeout(readl, catalog->io->dp_controller.link.base + @@ -476,7 +476,7 @@ int dp_catalog_ctrl_set_pattern(struct dp_catalog *dp_catalog, data, data & bit, POLLING_SLEEP_US, POLLING_TIMEOUT_US); if (ret < 0) { - DRM_ERROR("set pattern for link_train=%d failed\n", pattern); + DRM_ERROR("set state_bit for link_train=%d failed\n", state_bit); return ret; } return 0; diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.h b/drivers/gpu/drm/msm/dp/dp_catalog.h index 6965afa81aad..7dea1012ae66 100644 --- a/drivers/gpu/drm/msm/dp/dp_catalog.h +++ b/drivers/gpu/drm/msm/dp/dp_catalog.h @@ -94,7 +94,7 @@ void dp_catalog_ctrl_mainlink_ctrl(struct dp_catalog *dp_catalog, bool enable); void dp_catalog_ctrl_config_misc(struct dp_catalog *dp_catalog, u32 cc, u32 tb); void dp_catalog_ctrl_config_msa(struct dp_catalog *dp_catalog, u32 rate, u32 stream_rate_khz, bool fixed_nvid); -int dp_catalog_ctrl_set_pattern(struct dp_catalog *dp_catalog, u32 pattern); +int dp_catalog_ctrl_set_pattern_state_bit(struct dp_catalog *dp_catalog, u32 pattern); void dp_catalog_ctrl_reset(struct dp_catalog *dp_catalog); bool dp_catalog_ctrl_mainlink_ready(struct dp_catalog *dp_catalog); void dp_catalog_ctrl_enable_irq(struct dp_catalog *dp_catalog, bool enable); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c b/drivers/gpu/drm/msm/dp/dp_clk_util.c index 078afc5f5882..44a4fc59ff31 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c +++ b/drivers/gpu/drm/msm/dp/dp_clk_util.c @@ -11,7 +11,7 @@ #include <drm/drm_print.h> -#include "dpu_io_util.h" +#include "dp_clk_util.h" void msm_dss_put_clk(struct dss_clk *clk_arry, int num_clk) { @@ -118,70 +118,3 @@ int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable) return rc; } - -int msm_dss_parse_clock(struct platform_device *pdev, - struct dss_module_power *mp) -{ - u32 i, rc = 0; - const char *clock_name; - int num_clk = 0; - - if (!pdev || !mp) - return -EINVAL; - - mp->num_clk = 0; - num_clk = of_property_count_strings(pdev->dev.of_node, "clock-names"); - if (num_clk <= 0) { - pr_debug("clocks are not defined\n"); - return 0; - } - - mp->clk_config = devm_kcalloc(&pdev->dev, - num_clk, sizeof(struct dss_clk), - GFP_KERNEL); - if (!mp->clk_config) - return -ENOMEM; - - for (i = 0; i < num_clk; i++) { - rc = of_property_read_string_index(pdev->dev.of_node, - "clock-names", i, - &clock_name); - if (rc) { - DRM_DEV_ERROR(&pdev->dev, "Failed to get clock name for %d\n", - i); - break; - } - strlcpy(mp->clk_config[i].clk_name, clock_name, - sizeof(mp->clk_config[i].clk_name)); - - mp->clk_config[i].type = DSS_CLK_AHB; - } - - rc = msm_dss_get_clk(&pdev->dev, mp->clk_config, num_clk); - if (rc) { - DRM_DEV_ERROR(&pdev->dev, "Failed to get clock refs %d\n", rc); - goto err; - } - - rc = of_clk_set_defaults(pdev->dev.of_node, false); - if (rc) { - DRM_DEV_ERROR(&pdev->dev, "Failed to set clock defaults %d\n", rc); - goto err; - } - - for (i = 0; i < num_clk; i++) { - u32 rate = clk_get_rate(mp->clk_config[i].clk); - if (!rate) - continue; - mp->clk_config[i].rate = rate; - mp->clk_config[i].type = DSS_CLK_PCLK; - mp->clk_config[i].max_rate = rate; - } - - mp->num_clk = num_clk; - return 0; - -err: - msm_dss_put_clk(mp->clk_config, num_clk); - return rc; -} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h b/drivers/gpu/drm/msm/dp/dp_clk_util.h index e6b5c772fa3b..067bf87f3d97 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h +++ b/drivers/gpu/drm/msm/dp/dp_clk_util.h @@ -2,8 +2,8 @@ /* Copyright (c) 2012, 2017-2018, The Linux Foundation. All rights reserved. */ -#ifndef __DPU_IO_UTIL_H__ -#define __DPU_IO_UTIL_H__ +#ifndef __DP_CLK_UTIL_H__ +#define __DP_CLK_UTIL_H__ #include <linux/platform_device.h> #include <linux/types.h> @@ -35,6 +35,4 @@ int msm_dss_get_clk(struct device *dev, struct dss_clk *clk_arry, int num_clk); void msm_dss_put_clk(struct dss_clk *clk_arry, int num_clk); int msm_dss_clk_set_rate(struct dss_clk *clk_arry, int num_clk); int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable); -int msm_dss_parse_clock(struct platform_device *pdev, - struct dss_module_power *mp); -#endif /* __DPU_IO_UTIL_H__ */ +#endif /* __DP_CLK_UTIL_H__ */ diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 88ca6c3aedd3..53568567e05b 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -1083,7 +1083,7 @@ static int dp_ctrl_link_train_1(struct dp_ctrl_private *ctrl, *training_step = DP_TRAINING_1; - ret = dp_catalog_ctrl_set_pattern(ctrl->catalog, DP_TRAINING_PATTERN_1); + ret = dp_catalog_ctrl_set_pattern_state_bit(ctrl->catalog, 1); if (ret) return ret; dp_ctrl_train_pattern_set(ctrl, DP_TRAINING_PATTERN_1 | @@ -1181,7 +1181,8 @@ static int dp_ctrl_link_train_2(struct dp_ctrl_private *ctrl, int *training_step) { int tries = 0, ret = 0; - char pattern; + u8 pattern; + u32 state_ctrl_bit; int const maximum_retries = 5; u8 link_status[DP_LINK_STATUS_SIZE]; @@ -1189,12 +1190,18 @@ static int dp_ctrl_link_train_2(struct dp_ctrl_private *ctrl, *training_step = DP_TRAINING_2; - if (drm_dp_tps3_supported(ctrl->panel->dpcd)) + if (drm_dp_tps4_supported(ctrl->panel->dpcd)) { + pattern = DP_TRAINING_PATTERN_4; + state_ctrl_bit = 4; + } else if (drm_dp_tps3_supported(ctrl->panel->dpcd)) { pattern = DP_TRAINING_PATTERN_3; - else + state_ctrl_bit = 3; + } else { pattern = DP_TRAINING_PATTERN_2; + state_ctrl_bit = 2; + } - ret = dp_catalog_ctrl_set_pattern(ctrl->catalog, pattern); + ret = dp_catalog_ctrl_set_pattern_state_bit(ctrl->catalog, state_ctrl_bit); if (ret) return ret; @@ -1365,60 +1372,48 @@ static int dp_ctrl_enable_stream_clocks(struct dp_ctrl_private *ctrl) return ret; } -int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip, bool reset) +void dp_ctrl_reset_irq_ctrl(struct dp_ctrl *dp_ctrl, bool enable) +{ + struct dp_ctrl_private *ctrl; + + ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); + + dp_catalog_ctrl_reset(ctrl->catalog); + + if (enable) + dp_catalog_ctrl_enable_irq(ctrl->catalog, enable); +} + +void dp_ctrl_phy_init(struct dp_ctrl *dp_ctrl) { struct dp_ctrl_private *ctrl; struct dp_io *dp_io; struct phy *phy; - if (!dp_ctrl) { - DRM_ERROR("Invalid input data\n"); - return -EINVAL; - } - ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); dp_io = &ctrl->parser->io; phy = dp_io->phy; - ctrl->dp_ctrl.orientation = flip; - - if (reset) - dp_catalog_ctrl_reset(ctrl->catalog); - - DRM_DEBUG_DP("flip=%d\n", flip); dp_catalog_ctrl_phy_reset(ctrl->catalog); phy_init(phy); - dp_catalog_ctrl_enable_irq(ctrl->catalog, true); - - return 0; + DRM_DEBUG_DP("phy=%p init=%d power_on=%d\n", + phy, phy->init_count, phy->power_count); } -/** - * dp_ctrl_host_deinit() - Uninitialize DP controller - * @dp_ctrl: Display Port Driver data - * - * Perform required steps to uninitialize DP controller - * and its resources. - */ -void dp_ctrl_host_deinit(struct dp_ctrl *dp_ctrl) +void dp_ctrl_phy_exit(struct dp_ctrl *dp_ctrl) { struct dp_ctrl_private *ctrl; struct dp_io *dp_io; struct phy *phy; - if (!dp_ctrl) { - DRM_ERROR("Invalid input data\n"); - return; - } - ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); dp_io = &ctrl->parser->io; phy = dp_io->phy; - dp_catalog_ctrl_enable_irq(ctrl->catalog, false); + dp_catalog_ctrl_phy_reset(ctrl->catalog); phy_exit(phy); - - DRM_DEBUG_DP("Host deinitialized successfully\n"); + DRM_DEBUG_DP("phy=%p init=%d power_on=%d\n", + phy, phy->init_count, phy->power_count); } static bool dp_ctrl_use_fixed_nvid(struct dp_ctrl_private *ctrl) @@ -1488,8 +1483,13 @@ static int dp_ctrl_deinitialize_mainlink(struct dp_ctrl_private *ctrl) } phy_power_off(phy); + + /* aux channel down, reinit phy */ phy_exit(phy); + phy_init(phy); + DRM_DEBUG_DP("phy=%p init=%d power_on=%d\n", + phy, phy->init_count, phy->power_count); return 0; } @@ -1761,6 +1761,9 @@ int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl) /* end with failure */ break; /* lane == 1 already */ } + + /* stop link training before start re training */ + dp_ctrl_clear_training_pattern(ctrl); } } @@ -1893,33 +1896,20 @@ int dp_ctrl_off_link_stream(struct dp_ctrl *dp_ctrl) return ret; } + DRM_DEBUG_DP("Before, phy=%x init_count=%d power_on=%d\n", + (u32)(uintptr_t)phy, phy->init_count, phy->power_count); + phy_power_off(phy); /* aux channel down, reinit phy */ phy_exit(phy); phy_init(phy); - DRM_DEBUG_DP("DP off link/stream done\n"); + DRM_DEBUG_DP("phy=%p init=%d power_on=%d\n", + phy, phy->init_count, phy->power_count); return ret; } -void dp_ctrl_off_phy(struct dp_ctrl *dp_ctrl) -{ - struct dp_ctrl_private *ctrl; - struct dp_io *dp_io; - struct phy *phy; - - ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); - dp_io = &ctrl->parser->io; - phy = dp_io->phy; - - dp_catalog_ctrl_reset(ctrl->catalog); - - phy_exit(phy); - - DRM_DEBUG_DP("DP off phy done\n"); -} - int dp_ctrl_off(struct dp_ctrl *dp_ctrl) { struct dp_ctrl_private *ctrl; @@ -1948,9 +1938,9 @@ int dp_ctrl_off(struct dp_ctrl *dp_ctrl) } phy_power_off(phy); - phy_exit(phy); + DRM_DEBUG_DP("phy=%p init=%d power_on=%d\n", + phy, phy->init_count, phy->power_count); - DRM_DEBUG_DP("DP off done\n"); return ret; } diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.h b/drivers/gpu/drm/msm/dp/dp_ctrl.h index 2363a2df9597..2433edbc70a6 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.h +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.h @@ -19,12 +19,9 @@ struct dp_ctrl { u32 pixel_rate; }; -int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip, bool reset); -void dp_ctrl_host_deinit(struct dp_ctrl *dp_ctrl); int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl); int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl); int dp_ctrl_off_link_stream(struct dp_ctrl *dp_ctrl); -void dp_ctrl_off_phy(struct dp_ctrl *dp_ctrl); int dp_ctrl_off(struct dp_ctrl *dp_ctrl); void dp_ctrl_push_idle(struct dp_ctrl *dp_ctrl); void dp_ctrl_isr(struct dp_ctrl *dp_ctrl); @@ -34,4 +31,9 @@ struct dp_ctrl *dp_ctrl_get(struct device *dev, struct dp_link *link, struct dp_power *power, struct dp_catalog *catalog, struct dp_parser *parser); +void dp_ctrl_reset_irq_ctrl(struct dp_ctrl *dp_ctrl, bool enable); +void dp_ctrl_phy_init(struct dp_ctrl *dp_ctrl); +void dp_ctrl_phy_exit(struct dp_ctrl *dp_ctrl); +void dp_ctrl_irq_phy_exit(struct dp_ctrl *dp_ctrl); + #endif /* _DP_CTRL_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_debug.c b/drivers/gpu/drm/msm/dp/dp_debug.c index da4323556ef3..2f9c943f12d5 100644 --- a/drivers/gpu/drm/msm/dp/dp_debug.c +++ b/drivers/gpu/drm/msm/dp/dp_debug.c @@ -207,39 +207,39 @@ static const struct file_operations test_active_fops = { .write = dp_test_active_write }; -static int dp_debug_init(struct dp_debug *dp_debug, struct drm_minor *minor) +static void dp_debug_init(struct dp_debug *dp_debug, struct drm_minor *minor) { - int rc = 0; + char path[64]; struct dp_debug_private *debug = container_of(dp_debug, struct dp_debug_private, dp_debug); - debugfs_create_file("dp_debug", 0444, minor->debugfs_root, + snprintf(path, sizeof(path), "msm_dp-%s", debug->connector->name); + + debug->root = debugfs_create_dir(path, minor->debugfs_root); + + debugfs_create_file("dp_debug", 0444, debug->root, debug, &dp_debug_fops); debugfs_create_file("msm_dp_test_active", 0444, - minor->debugfs_root, + debug->root, debug, &test_active_fops); debugfs_create_file("msm_dp_test_data", 0444, - minor->debugfs_root, + debug->root, debug, &dp_test_data_fops); debugfs_create_file("msm_dp_test_type", 0444, - minor->debugfs_root, + debug->root, debug, &dp_test_type_fops); - - debug->root = minor->debugfs_root; - - return rc; } struct dp_debug *dp_debug_get(struct device *dev, struct dp_panel *panel, struct dp_usbpd *usbpd, struct dp_link *link, struct drm_connector *connector, struct drm_minor *minor) { - int rc = 0; struct dp_debug_private *debug; struct dp_debug *dp_debug; + int rc; if (!dev || !panel || !usbpd || !link) { DRM_ERROR("invalid input\n"); @@ -266,11 +266,7 @@ struct dp_debug *dp_debug_get(struct device *dev, struct dp_panel *panel, dp_debug->hdisplay = 0; dp_debug->vrefresh = 0; - rc = dp_debug_init(dp_debug, minor); - if (rc) { - devm_kfree(dev, debug); - goto error; - } + dp_debug_init(dp_debug, minor); return dp_debug; error: diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 7cc4d21f2091..178b774a5fbd 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -83,6 +83,7 @@ struct dp_display_private { /* state variables */ bool core_initialized; + bool phy_initialized; bool hpd_irq_on; bool audio_supported; @@ -143,10 +144,29 @@ static const struct msm_dp_config sc7280_dp_cfg = { .num_descs = 2, }; +static const struct msm_dp_config sc8180x_dp_cfg = { + .descs = (const struct msm_dp_desc[]) { + [MSM_DP_CONTROLLER_0] = { .io_start = 0x0ae90000, .connector_type = DRM_MODE_CONNECTOR_DisplayPort }, + [MSM_DP_CONTROLLER_1] = { .io_start = 0x0ae98000, .connector_type = DRM_MODE_CONNECTOR_DisplayPort }, + [MSM_DP_CONTROLLER_2] = { .io_start = 0x0ae9a000, .connector_type = DRM_MODE_CONNECTOR_eDP }, + }, + .num_descs = 3, +}; + +static const struct msm_dp_config sm8350_dp_cfg = { + .descs = (const struct msm_dp_desc[]) { + [MSM_DP_CONTROLLER_0] = { .io_start = 0x0ae90000, .connector_type = DRM_MODE_CONNECTOR_DisplayPort }, + }, + .num_descs = 1, +}; + static const struct of_device_id dp_dt_match[] = { { .compatible = "qcom,sc7180-dp", .data = &sc7180_dp_cfg }, { .compatible = "qcom,sc7280-dp", .data = &sc7280_dp_cfg }, { .compatible = "qcom,sc7280-edp", .data = &sc7280_dp_cfg }, + { .compatible = "qcom,sc8180x-dp", .data = &sc8180x_dp_cfg }, + { .compatible = "qcom,sc8180x-edp", .data = &sc8180x_dp_cfg }, + { .compatible = "qcom,sm8350-dp", .data = &sm8350_dp_cfg }, {} }; @@ -246,7 +266,7 @@ static int dp_display_bind(struct device *dev, struct device *master, goto end; } - dp->dp_display.panel_bridge = dp->parser->panel_bridge; + dp->dp_display.next_bridge = dp->parser->next_bridge; dp->aux->drm_dev = drm; rc = dp_aux_register(dp->aux); @@ -372,36 +392,51 @@ end: return rc; } -static void dp_display_host_init(struct dp_display_private *dp, int reset) +static void dp_display_host_phy_init(struct dp_display_private *dp) { - bool flip = false; + DRM_DEBUG_DP("type=%d core_init=%d phy_init=%d\n", + dp->dp_display.connector_type, dp->core_initialized, + dp->phy_initialized); - DRM_DEBUG_DP("core_initialized=%d\n", dp->core_initialized); - if (dp->core_initialized) { - DRM_DEBUG_DP("DP core already initialized\n"); - return; + if (!dp->phy_initialized) { + dp_ctrl_phy_init(dp->ctrl); + dp->phy_initialized = true; + } +} + +static void dp_display_host_phy_exit(struct dp_display_private *dp) +{ + DRM_DEBUG_DP("type=%d core_init=%d phy_init=%d\n", + dp->dp_display.connector_type, dp->core_initialized, + dp->phy_initialized); + + if (dp->phy_initialized) { + dp_ctrl_phy_exit(dp->ctrl); + dp->phy_initialized = false; } +} - if (dp->usbpd->orientation == ORIENTATION_CC2) - flip = true; +static void dp_display_host_init(struct dp_display_private *dp) +{ + DRM_DEBUG_DP("type=%d core_init=%d phy_init=%d\n", + dp->dp_display.connector_type, dp->core_initialized, + dp->phy_initialized); - dp_power_init(dp->power, flip); - dp_ctrl_host_init(dp->ctrl, flip, reset); + dp_power_init(dp->power, false); + dp_ctrl_reset_irq_ctrl(dp->ctrl, true); dp_aux_init(dp->aux); dp->core_initialized = true; } static void dp_display_host_deinit(struct dp_display_private *dp) { - if (!dp->core_initialized) { - DRM_DEBUG_DP("DP core not initialized\n"); - return; - } + DRM_DEBUG_DP("type=%d core_init=%d phy_init=%d\n", + dp->dp_display.connector_type, dp->core_initialized, + dp->phy_initialized); - dp_ctrl_host_deinit(dp->ctrl); + dp_ctrl_reset_irq_ctrl(dp->ctrl, false); dp_aux_deinit(dp->aux); dp_power_deinit(dp->power); - dp->core_initialized = false; } @@ -409,7 +444,7 @@ static int dp_display_usbpd_configure_cb(struct device *dev) { struct dp_display_private *dp = dev_get_dp_display_private(dev); - dp_display_host_init(dp, false); + dp_display_host_phy_init(dp); return dp_display_process_hpd_high(dp); } @@ -507,7 +542,9 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data) mutex_lock(&dp->event_mutex); state = dp->hpd_state; - DRM_DEBUG_DP("hpd_state=%d\n", state); + DRM_DEBUG_DP("Before, type=%d hpd_state=%d\n", + dp->dp_display.connector_type, state); + if (state == ST_DISPLAY_OFF || state == ST_SUSPENDED) { mutex_unlock(&dp->event_mutex); return 0; @@ -530,11 +567,6 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data) ret = dp_display_usbpd_configure_cb(&dp->pdev->dev); if (ret) { /* link train failed */ dp->hpd_state = ST_DISCONNECTED; - - if (ret == -ECONNRESET) { /* cable unplugged */ - dp->core_initialized = false; - } - } else { /* start sentinel checking in case of missing uevent */ dp_add_event(dp, EV_CONNECT_PENDING_TIMEOUT, 0, tout); @@ -544,6 +576,8 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data) dp_catalog_hpd_config_intr(dp->catalog, DP_DP_IRQ_HPD_INT_MASK | DP_DP_HPD_REPLUG_INT_MASK, true); + DRM_DEBUG_DP("After, type=%d hpd_state=%d\n", + dp->dp_display.connector_type, state); mutex_unlock(&dp->event_mutex); /* uevent will complete connection part */ @@ -560,8 +594,10 @@ static int dp_connect_pending_timeout(struct dp_display_private *dp, u32 data) mutex_lock(&dp->event_mutex); state = dp->hpd_state; - if (state == ST_CONNECT_PENDING) + if (state == ST_CONNECT_PENDING) { dp->hpd_state = ST_CONNECTED; + DRM_DEBUG_DP("type=%d\n", dp->dp_display.connector_type); + } mutex_unlock(&dp->event_mutex); @@ -594,6 +630,9 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data) state = dp->hpd_state; + DRM_DEBUG_DP("Before, type=%d hpd_state=%d\n", + dp->dp_display.connector_type, state); + /* disable irq_hpd/replug interrupts */ dp_catalog_hpd_config_intr(dp->catalog, DP_DP_IRQ_HPD_INT_MASK | DP_DP_HPD_REPLUG_INT_MASK, false); @@ -604,8 +643,7 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data) if (state == ST_DISCONNECTED) { /* triggered by irq_hdp with sink_count = 0 */ if (dp->link->sink_count == 0) { - dp_ctrl_off_phy(dp->ctrl); - dp->core_initialized = false; + dp_display_host_phy_exit(dp); } mutex_unlock(&dp->event_mutex); return 0; @@ -637,13 +675,15 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data) /* start sentinel checking in case of missing uevent */ dp_add_event(dp, EV_DISCONNECT_PENDING_TIMEOUT, 0, DP_TIMEOUT_5_SECOND); - DRM_DEBUG_DP("hpd_state=%d\n", state); /* signal the disconnect event early to ensure proper teardown */ dp_display_handle_plugged_change(&dp->dp_display, false); /* enable HDP plug interrupt to prepare for next plugin */ dp_catalog_hpd_config_intr(dp->catalog, DP_DP_HPD_PLUG_INT_MASK, true); + DRM_DEBUG_DP("After, type=%d hpd_state=%d\n", + dp->dp_display.connector_type, state); + /* uevent will complete disconnection part */ mutex_unlock(&dp->event_mutex); return 0; @@ -656,8 +696,10 @@ static int dp_disconnect_pending_timeout(struct dp_display_private *dp, u32 data mutex_lock(&dp->event_mutex); state = dp->hpd_state; - if (state == ST_DISCONNECT_PENDING) + if (state == ST_DISCONNECT_PENDING) { dp->hpd_state = ST_DISCONNECTED; + DRM_DEBUG_DP("type=%d\n", dp->dp_display.connector_type); + } mutex_unlock(&dp->event_mutex); @@ -667,12 +709,14 @@ static int dp_disconnect_pending_timeout(struct dp_display_private *dp, u32 data static int dp_irq_hpd_handle(struct dp_display_private *dp, u32 data) { u32 state; - int ret; mutex_lock(&dp->event_mutex); /* irq_hpd can happen at either connected or disconnected state */ state = dp->hpd_state; + DRM_DEBUG_DP("Before, type=%d hpd_state=%d\n", + dp->dp_display.connector_type, state); + if (state == ST_DISPLAY_OFF || state == ST_SUSPENDED) { mutex_unlock(&dp->event_mutex); return 0; @@ -692,17 +736,10 @@ static int dp_irq_hpd_handle(struct dp_display_private *dp, u32 data) return 0; } - /* - * dp core (ahb/aux clks) must be initialized before - * irq_hpd be handled - */ - if (dp->core_initialized) { - ret = dp_display_usbpd_attention_cb(&dp->pdev->dev); - if (ret == -ECONNRESET) { /* cable unplugged */ - dp->core_initialized = false; - } - } - DRM_DEBUG_DP("hpd_state=%d\n", state); + dp_display_usbpd_attention_cb(&dp->pdev->dev); + + DRM_DEBUG_DP("After, type=%d hpd_state=%d\n", + dp->dp_display.connector_type, state); mutex_unlock(&dp->event_mutex); @@ -892,12 +929,19 @@ static int dp_display_disable(struct dp_display_private *dp, u32 data) dp_display->audio_enabled = false; - /* triggered by irq_hpd with sink_count = 0 */ if (dp->link->sink_count == 0) { + /* + * irq_hpd with sink_count = 0 + * hdmi unplugged out of dongle + */ dp_ctrl_off_link_stream(dp->ctrl); } else { + /* + * unplugged interrupt + * dongle unplugged out of DUT + */ dp_ctrl_off(dp->ctrl); - dp->core_initialized = false; + dp_display_host_phy_exit(dp); } dp_display->power_on = false; @@ -1027,7 +1071,7 @@ void msm_dp_snapshot(struct msm_disp_state *disp_state, struct msm_dp *dp) static void dp_display_config_hpd(struct dp_display_private *dp) { - dp_display_host_init(dp, true); + dp_display_host_init(dp); dp_catalog_ctrl_hpd_config(dp->catalog); /* Enable interrupt first time @@ -1145,8 +1189,9 @@ static irqreturn_t dp_display_irq_handler(int irq, void *dev_id) hpd_isr_status = dp_catalog_hpd_get_intr_status(dp->catalog); - DRM_DEBUG_DP("hpd isr status=%#x\n", hpd_isr_status); if (hpd_isr_status & 0x0F) { + DRM_DEBUG_DP("type=%d isr=0x%x\n", + dp->dp_display.connector_type, hpd_isr_status); /* hpd related interrupts */ if (hpd_isr_status & DP_DP_HPD_PLUG_INT_MASK) dp_add_event(dp, EV_HPD_PLUG_INT, 0, 0); @@ -1299,27 +1344,31 @@ static int dp_pm_resume(struct device *dev) mutex_lock(&dp->event_mutex); - DRM_DEBUG_DP("Before, core_inited=%d power_on=%d\n", - dp->core_initialized, dp_display->power_on); + DRM_DEBUG_DP("Before, type=%d core_inited=%d phy_inited=%d power_on=%d\n", + dp->dp_display.connector_type, dp->core_initialized, + dp->phy_initialized, dp_display->power_on); /* start from disconnected state */ dp->hpd_state = ST_DISCONNECTED; /* turn on dp ctrl/phy */ - dp_display_host_init(dp, true); + dp_display_host_init(dp); dp_catalog_ctrl_hpd_config(dp->catalog); - /* - * set sink to normal operation mode -- D0 - * before dpcd read - */ - dp_link_psm_config(dp->link, &dp->panel->link_info, false); if (dp_catalog_link_is_connected(dp->catalog)) { + /* + * set sink to normal operation mode -- D0 + * before dpcd read + */ + dp_display_host_phy_init(dp); + dp_link_psm_config(dp->link, &dp->panel->link_info, false); sink_count = drm_dp_read_sink_count(dp->aux); if (sink_count < 0) sink_count = 0; + + dp_display_host_phy_exit(dp); } dp->link->sink_count = sink_count; @@ -1336,9 +1385,11 @@ static int dp_pm_resume(struct device *dev) dp_display_handle_plugged_change(dp_display, false); } - DRM_DEBUG_DP("After, sink_count=%d is_connected=%d core_inited=%d power_on=%d\n", - dp->link->sink_count, dp->dp_display.is_connected, - dp->core_initialized, dp_display->power_on); + DRM_DEBUG_DP("After, type=%d sink_count=%d is_connected=%d \ + core_inited=%d phy_inited=%d power_on=%d\n", + dp->dp_display.connector_type, dp->link->sink_count, + dp->dp_display.is_connected, dp->core_initialized, + dp->phy_initialized, dp_display->power_on); mutex_unlock(&dp->event_mutex); @@ -1355,24 +1406,24 @@ static int dp_pm_suspend(struct device *dev) mutex_lock(&dp->event_mutex); - DRM_DEBUG_DP("Before, core_inited=%d power_on=%d\n", - dp->core_initialized, dp_display->power_on); - - if (dp->core_initialized == true) { - /* mainlink enabled */ - if (dp_power_clk_status(dp->power, DP_CTRL_PM)) - dp_ctrl_off_link_stream(dp->ctrl); + DRM_DEBUG_DP("Before, type=%d core_inited=%d phy_inited=%d power_on=%d\n", + dp->dp_display.connector_type, dp->core_initialized, + dp->phy_initialized, dp_display->power_on); - dp_display_host_deinit(dp); - } + /* mainlink enabled */ + if (dp_power_clk_status(dp->power, DP_CTRL_PM)) + dp_ctrl_off_link_stream(dp->ctrl); - dp->hpd_state = ST_SUSPENDED; + dp_display_host_phy_exit(dp); /* host_init will be called at pm_resume */ - dp->core_initialized = false; + dp_display_host_deinit(dp); + + dp->hpd_state = ST_SUSPENDED; - DRM_DEBUG_DP("After, core_inited=%d power_on=%d\n", - dp->core_initialized, dp_display->power_on); + DRM_DEBUG_DP("After, type=%d core_inited=%d phy_inited=%d power_on=%d\n", + dp->dp_display.connector_type, dp->core_initialized, + dp->phy_initialized, dp_display->power_on); mutex_unlock(&dp->event_mutex); @@ -1460,6 +1511,7 @@ int msm_dp_modeset_init(struct msm_dp *dp_display, struct drm_device *dev, struct drm_encoder *encoder) { struct msm_drm_private *priv; + struct dp_display_private *dp_priv; int ret; if (WARN_ON(!encoder) || WARN_ON(!dp_display) || WARN_ON(!dev)) @@ -1468,6 +1520,8 @@ int msm_dp_modeset_init(struct msm_dp *dp_display, struct drm_device *dev, priv = dev->dev_private; dp_display->drm_dev = dev; + dp_priv = container_of(dp_display, struct dp_display_private, dp_display); + ret = dp_display_request_irq(dp_display); if (ret) { DRM_ERROR("request_irq failed, ret=%d\n", ret); @@ -1485,6 +1539,8 @@ int msm_dp_modeset_init(struct msm_dp *dp_display, struct drm_device *dev, return ret; } + dp_priv->panel->connector = dp_display->connector; + priv->connectors[priv->num_connectors++] = dp_display->connector; dp_display->bridge = msm_dp_bridge_init(dp_display, dev, encoder); @@ -1535,7 +1591,7 @@ int msm_dp_display_enable(struct msm_dp *dp, struct drm_encoder *encoder) state = dp_display->hpd_state; if (state == ST_DISPLAY_OFF) - dp_display_host_init(dp_display, true); + dp_display_host_phy_init(dp_display); dp_display_enable(dp_display, 0); diff --git a/drivers/gpu/drm/msm/dp/dp_display.h b/drivers/gpu/drm/msm/dp/dp_display.h index e3adcd578a90..7af2b186d2d9 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.h +++ b/drivers/gpu/drm/msm/dp/dp_display.h @@ -16,7 +16,7 @@ struct msm_dp { struct drm_bridge *bridge; struct drm_connector *connector; struct drm_encoder *encoder; - struct drm_bridge *panel_bridge; + struct drm_bridge *next_bridge; bool is_connected; bool audio_enabled; bool power_on; diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c index d4d360d19eba..80f59cf99089 100644 --- a/drivers/gpu/drm/msm/dp/dp_drm.c +++ b/drivers/gpu/drm/msm/dp/dp_drm.c @@ -169,16 +169,6 @@ struct drm_connector *dp_drm_connector_init(struct msm_dp *dp_display) drm_connector_attach_encoder(connector, dp_display->encoder); - if (dp_display->panel_bridge) { - ret = drm_bridge_attach(dp_display->encoder, - dp_display->panel_bridge, NULL, - DRM_BRIDGE_ATTACH_NO_CONNECTOR); - if (ret < 0) { - DRM_ERROR("failed to attach panel bridge: %d\n", ret); - return ERR_PTR(ret); - } - } - return connector; } @@ -246,5 +236,16 @@ struct drm_bridge *msm_dp_bridge_init(struct msm_dp *dp_display, struct drm_devi return ERR_PTR(rc); } + if (dp_display->next_bridge) { + rc = drm_bridge_attach(dp_display->encoder, + dp_display->next_bridge, bridge, + DRM_BRIDGE_ATTACH_NO_CONNECTOR); + if (rc < 0) { + DRM_ERROR("failed to attach panel bridge: %d\n", rc); + drm_bridge_remove(bridge); + return ERR_PTR(rc); + } + } + return bridge; } diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index 71db10c0f262..f1418722c549 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -212,6 +212,11 @@ int dp_panel_read_sink_caps(struct dp_panel *dp_panel, if (drm_add_modes_noedid(connector, 640, 480)) drm_set_preferred_mode(connector, 640, 480); mutex_unlock(&connector->dev->mode_config.mutex); + } else { + /* always add fail-safe mode as backup mode */ + mutex_lock(&connector->dev->mode_config.mutex); + drm_add_modes_noedid(connector, 640, 480); + mutex_unlock(&connector->dev->mode_config.mutex); } if (panel->aux_cfg_update_done) { diff --git a/drivers/gpu/drm/msm/dp/dp_parser.c b/drivers/gpu/drm/msm/dp/dp_parser.c index a7acc23f742b..1056b8d5755b 100644 --- a/drivers/gpu/drm/msm/dp/dp_parser.c +++ b/drivers/gpu/drm/msm/dp/dp_parser.c @@ -265,23 +265,16 @@ static int dp_parser_clock(struct dp_parser *parser) return 0; } -static int dp_parser_find_panel(struct dp_parser *parser) +static int dp_parser_find_next_bridge(struct dp_parser *parser) { struct device *dev = &parser->pdev->dev; - struct drm_panel *panel; - int rc; + struct drm_bridge *bridge; - rc = drm_of_find_panel_or_bridge(dev->of_node, 1, 0, &panel, NULL); - if (rc) { - DRM_ERROR("failed to acquire DRM panel: %d\n", rc); - return rc; - } + bridge = devm_drm_of_get_bridge(dev, dev->of_node, 1, 0); + if (IS_ERR(bridge)) + return PTR_ERR(bridge); - parser->panel_bridge = devm_drm_panel_bridge_add(dev, panel); - if (IS_ERR(parser->panel_bridge)) { - DRM_ERROR("failed to create panel bridge\n"); - return PTR_ERR(parser->panel_bridge); - } + parser->next_bridge = bridge; return 0; } @@ -307,10 +300,23 @@ static int dp_parser_parse(struct dp_parser *parser, int connector_type) if (rc) return rc; - if (connector_type == DRM_MODE_CONNECTOR_eDP) { - rc = dp_parser_find_panel(parser); - if (rc) + /* + * External bridges are mandatory for eDP interfaces: one has to + * provide at least an eDP panel (which gets wrapped into panel-bridge). + * + * For DisplayPort interfaces external bridges are optional, so + * silently ignore an error if one is not present (-ENODEV). + */ + rc = dp_parser_find_next_bridge(parser); + if (rc == -ENODEV) { + if (connector_type == DRM_MODE_CONNECTOR_eDP) { + DRM_ERROR("eDP: next bridge is not present\n"); return rc; + } + } else if (rc) { + if (rc != -EPROBE_DEFER) + DRM_ERROR("DP: error parsing next bridge: %d\n", rc); + return rc; } /* Map the corresponding regulator information according to diff --git a/drivers/gpu/drm/msm/dp/dp_parser.h b/drivers/gpu/drm/msm/dp/dp_parser.h index 3172da089421..d371bae1c968 100644 --- a/drivers/gpu/drm/msm/dp/dp_parser.h +++ b/drivers/gpu/drm/msm/dp/dp_parser.h @@ -10,7 +10,7 @@ #include <linux/phy/phy.h> #include <linux/phy/phy-dp.h> -#include "dpu_io_util.h" +#include "dp_clk_util.h" #include "msm_drv.h" #define DP_LABEL "MDSS DP DISPLAY" @@ -123,7 +123,7 @@ struct dp_parser { struct dp_display_data disp_data; const struct dp_regulator_cfg *regulator_cfg; u32 max_dp_lanes; - struct drm_bridge *panel_bridge; + struct drm_bridge *next_bridge; int (*parse)(struct dp_parser *parser, int connector_type); }; diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c index 0fe02529b5e7..c12e66aa42a3 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.c +++ b/drivers/gpu/drm/msm/dsi/dsi.c @@ -4,6 +4,7 @@ */ #include "dsi.h" +#include "dsi_cfg.h" struct drm_encoder *msm_dsi_get_encoder(struct msm_dsi *msm_dsi) { @@ -175,7 +176,8 @@ static int dsi_dev_remove(struct platform_device *pdev) } static const struct of_device_id dt_match[] = { - { .compatible = "qcom,mdss-dsi-ctrl" }, + { .compatible = "qcom,mdss-dsi-ctrl", .data = NULL /* autodetect cfg */ }, + { .compatible = "qcom,dsi-ctrl-6g-qcm2290", .data = &qcm2290_dsi_cfg_handler }, {} }; diff --git a/drivers/gpu/drm/msm/dsi/dsi.xml.h b/drivers/gpu/drm/msm/dsi/dsi.xml.h index 49b551ad1bff..4dee6f0bdda6 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.xml.h +++ b/drivers/gpu/drm/msm/dsi/dsi.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c index 96bbc8b6d009..2c23324a2296 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c @@ -213,6 +213,24 @@ static const struct msm_dsi_config sc7280_dsi_cfg = { .num_dsi = 1, }; +static const char * const dsi_qcm2290_bus_clk_names[] = { + "iface", "bus", +}; + +static const struct msm_dsi_config qcm2290_dsi_cfg = { + .io_offset = DSI_6G_REG_SHIFT, + .reg_cfg = { + .num = 1, + .regs = { + {"vdda", 21800, 4 }, /* 1.2 V */ + }, + }, + .bus_clk_names = dsi_qcm2290_bus_clk_names, + .num_bus_clks = ARRAY_SIZE(dsi_qcm2290_bus_clk_names), + .io_start = { 0x5e94000 }, + .num_dsi = 1, +}; + static const struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = { .link_clk_set_rate = dsi_link_clk_set_rate_v2, .link_clk_enable = dsi_link_clk_enable_v2, @@ -300,3 +318,8 @@ const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor) return cfg_hnd; } +/* Non autodetect configs */ +const struct msm_dsi_cfg_handler qcm2290_dsi_cfg_handler = { + .cfg = &qcm2290_dsi_cfg, + .ops = &msm_dsi_6g_v2_host_ops, +}; diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h index 41e99a9fb5de..fe54a999968b 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h @@ -60,5 +60,8 @@ struct msm_dsi_cfg_handler { const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor); +/* Non autodetect configs */ +extern const struct msm_dsi_cfg_handler qcm2290_dsi_cfg_handler; + #endif /* __MSM_DSI_CFG_H__ */ diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 6b3ced4aaaf5..d51e70fab93d 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -212,6 +212,10 @@ static const struct msm_dsi_cfg_handler *dsi_get_config( int ret; u32 major = 0, minor = 0; + cfg_hnd = device_get_match_data(dev); + if (cfg_hnd) + return cfg_hnd; + ahb_clk = msm_clk_get(msm_host->pdev, "iface"); if (IS_ERR(ahb_clk)) { pr_err("%s: cannot get interface clock\n", __func__); @@ -1813,7 +1817,7 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) goto fail; } - msm_host->ctrl_base = msm_ioremap_size(pdev, "dsi_ctrl", "DSI CTRL", &msm_host->ctrl_size); + 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__); ret = PTR_ERR(msm_host->ctrl_base); @@ -1877,7 +1881,7 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) /* do not autoenable, will be enabled later */ ret = devm_request_irq(&pdev->dev, msm_host->irq, dsi_host_irq, - IRQF_TRIGGER_HIGH | IRQF_ONESHOT | IRQF_NO_AUTOEN, + IRQF_TRIGGER_HIGH | IRQF_NO_AUTOEN, "dsi_isr", msm_host); if (ret < 0) { dev_err(&pdev->dev, "failed to request IRQ%u: %d\n", diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index f19bae475c96..0c1b7dde377c 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -305,27 +305,6 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector) return num; } -static enum drm_mode_status dsi_mgr_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) -{ - int id = dsi_mgr_connector_get_id(connector); - struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); - struct drm_encoder *encoder = msm_dsi_get_encoder(msm_dsi); - struct msm_drm_private *priv = connector->dev->dev_private; - struct msm_kms *kms = priv->kms; - long actual, requested; - - DBG(""); - requested = 1000 * mode->clock; - actual = kms->funcs->round_pixclk(kms, requested, encoder); - - DBG("requested=%ld, actual=%ld", requested, actual); - if (actual != requested) - return MODE_CLOCK_RANGE; - - return MODE_OK; -} - static struct drm_encoder * dsi_mgr_connector_best_encoder(struct drm_connector *connector) { @@ -336,13 +315,12 @@ dsi_mgr_connector_best_encoder(struct drm_connector *connector) return msm_dsi_get_encoder(msm_dsi); } -static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge) +static void dsi_mgr_bridge_power_on(struct drm_bridge *bridge) { int id = dsi_mgr_bridge_get_id(bridge); struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1); struct mipi_dsi_host *host = msm_dsi->host; - struct drm_panel *panel = msm_dsi->panel; struct msm_dsi_phy_shared_timings phy_shared_timings[DSI_MAX]; bool is_bonded_dsi = IS_BONDED_DSI(); int ret; @@ -383,6 +361,34 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge) if (is_bonded_dsi && msm_dsi1) msm_dsi_host_enable_irq(msm_dsi1->host); + return; + +host1_on_fail: + msm_dsi_host_power_off(host); +host_on_fail: + dsi_mgr_phy_disable(id); +phy_en_fail: + return; +} + +static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge) +{ + int id = dsi_mgr_bridge_get_id(bridge); + struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); + struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1); + struct mipi_dsi_host *host = msm_dsi->host; + struct drm_panel *panel = msm_dsi->panel; + bool is_bonded_dsi = IS_BONDED_DSI(); + int ret; + + DBG("id=%d", id); + if (!msm_dsi_device_connected(msm_dsi)) + return; + + /* Do nothing with the host if it is slave-DSI in case of bonded DSI */ + if (is_bonded_dsi && !IS_MASTER_DSI_LINK(id)) + return; + /* Always call panel functions once, because even for dual panels, * there is only one drm_panel instance. */ @@ -417,17 +423,7 @@ host_en_fail: if (panel) drm_panel_unprepare(panel); panel_prep_fail: - msm_dsi_host_disable_irq(host); - if (is_bonded_dsi && msm_dsi1) - msm_dsi_host_disable_irq(msm_dsi1->host); - if (is_bonded_dsi && msm_dsi1) - msm_dsi_host_power_off(msm_dsi1->host); -host1_on_fail: - msm_dsi_host_power_off(host); -host_on_fail: - dsi_mgr_phy_disable(id); -phy_en_fail: return; } @@ -573,6 +569,8 @@ static void dsi_mgr_bridge_mode_set(struct drm_bridge *bridge, msm_dsi_host_set_display_mode(host, adjusted_mode); if (is_bonded_dsi && other_dsi) msm_dsi_host_set_display_mode(other_dsi->host, adjusted_mode); + + dsi_mgr_bridge_power_on(bridge); } static const struct drm_connector_funcs dsi_mgr_connector_funcs = { @@ -586,7 +584,6 @@ static const struct drm_connector_funcs dsi_mgr_connector_funcs = { static const struct drm_connector_helper_funcs dsi_mgr_conn_helper_funcs = { .get_modes = dsi_mgr_connector_get_modes, - .mode_valid = dsi_mgr_connector_mode_valid, .best_encoder = dsi_mgr_connector_best_encoder, }; diff --git a/drivers/gpu/drm/msm/dsi/dsi_phy_10nm.xml.h b/drivers/gpu/drm/msm/dsi/dsi_phy_10nm.xml.h index 8872d77027dd..8b1be69ccf89 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_phy_10nm.xml.h +++ b/drivers/gpu/drm/msm/dsi/dsi_phy_10nm.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/dsi/dsi_phy_14nm.xml.h b/drivers/gpu/drm/msm/dsi/dsi_phy_14nm.xml.h index 0d9a5ccfb808..515f1fa605bf 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_phy_14nm.xml.h +++ b/drivers/gpu/drm/msm/dsi/dsi_phy_14nm.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/dsi/dsi_phy_20nm.xml.h b/drivers/gpu/drm/msm/dsi/dsi_phy_20nm.xml.h index 15c7a5852c7a..81e4622eb358 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_phy_20nm.xml.h +++ b/drivers/gpu/drm/msm/dsi/dsi_phy_20nm.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/dsi/dsi_phy_28nm.xml.h b/drivers/gpu/drm/msm/dsi/dsi_phy_28nm.xml.h index 5148f4d5b182..8c7db35c12c8 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_phy_28nm.xml.h +++ b/drivers/gpu/drm/msm/dsi/dsi_phy_28nm.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/dsi/dsi_phy_28nm_8960.xml.h b/drivers/gpu/drm/msm/dsi/dsi_phy_28nm_8960.xml.h index 446fe9ffc9c4..44eeca31a811 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_phy_28nm_8960.xml.h +++ b/drivers/gpu/drm/msm/dsi/dsi_phy_28nm_8960.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/dsi/dsi_phy_5nm.xml.h b/drivers/gpu/drm/msm/dsi/dsi_phy_5nm.xml.h deleted file mode 100644 index 404c890a29f1..000000000000 --- a/drivers/gpu/drm/msm/dsi/dsi_phy_5nm.xml.h +++ /dev/null @@ -1,480 +0,0 @@ -#ifndef DSI_PHY_5NM_XML -#define DSI_PHY_5NM_XML - -/* Autogenerated file, DO NOT EDIT manually! - -This file was generated by the rules-ng-ng headergen tool in this git repository: -http://github.com/freedreno/envytools/ -git clone https://github.com/freedreno/envytools.git - -The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) - -Copyright (C) 2013-2021 by the following authors: -- Rob Clark <robdclark@gmail.com> (robclark) -- Ilia Mirkin <imirkin@alum.mit.edu> (imirkin) - -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 (including the -next paragraph) 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 OWNER(S) AND/OR ITS SUPPLIERS 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. -*/ - - -#define REG_DSI_5nm_PHY_CMN_REVISION_ID0 0x00000000 - -#define REG_DSI_5nm_PHY_CMN_REVISION_ID1 0x00000004 - -#define REG_DSI_5nm_PHY_CMN_REVISION_ID2 0x00000008 - -#define REG_DSI_5nm_PHY_CMN_REVISION_ID3 0x0000000c - -#define REG_DSI_5nm_PHY_CMN_CLK_CFG0 0x00000010 - -#define REG_DSI_5nm_PHY_CMN_CLK_CFG1 0x00000014 - -#define REG_DSI_5nm_PHY_CMN_GLBL_CTRL 0x00000018 - -#define REG_DSI_5nm_PHY_CMN_RBUF_CTRL 0x0000001c - -#define REG_DSI_5nm_PHY_CMN_VREG_CTRL_0 0x00000020 - -#define REG_DSI_5nm_PHY_CMN_CTRL_0 0x00000024 - -#define REG_DSI_5nm_PHY_CMN_CTRL_1 0x00000028 - -#define REG_DSI_5nm_PHY_CMN_CTRL_2 0x0000002c - -#define REG_DSI_5nm_PHY_CMN_CTRL_3 0x00000030 - -#define REG_DSI_5nm_PHY_CMN_LANE_CFG0 0x00000034 - -#define REG_DSI_5nm_PHY_CMN_LANE_CFG1 0x00000038 - -#define REG_DSI_5nm_PHY_CMN_PLL_CNTRL 0x0000003c - -#define REG_DSI_5nm_PHY_CMN_DPHY_SOT 0x00000040 - -#define REG_DSI_5nm_PHY_CMN_LANE_CTRL0 0x000000a0 - -#define REG_DSI_5nm_PHY_CMN_LANE_CTRL1 0x000000a4 - -#define REG_DSI_5nm_PHY_CMN_LANE_CTRL2 0x000000a8 - -#define REG_DSI_5nm_PHY_CMN_LANE_CTRL3 0x000000ac - -#define REG_DSI_5nm_PHY_CMN_LANE_CTRL4 0x000000b0 - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_0 0x000000b4 - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_1 0x000000b8 - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_2 0x000000bc - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_3 0x000000c0 - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_4 0x000000c4 - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_5 0x000000c8 - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_6 0x000000cc - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_7 0x000000d0 - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_8 0x000000d4 - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_9 0x000000d8 - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_10 0x000000dc - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_11 0x000000e0 - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_12 0x000000e4 - -#define REG_DSI_5nm_PHY_CMN_TIMING_CTRL_13 0x000000e8 - -#define REG_DSI_5nm_PHY_CMN_GLBL_HSTX_STR_CTRL_0 0x000000ec - -#define REG_DSI_5nm_PHY_CMN_GLBL_HSTX_STR_CTRL_1 0x000000f0 - -#define REG_DSI_5nm_PHY_CMN_GLBL_RESCODE_OFFSET_TOP_CTRL 0x000000f4 - -#define REG_DSI_5nm_PHY_CMN_GLBL_RESCODE_OFFSET_BOT_CTRL 0x000000f8 - -#define REG_DSI_5nm_PHY_CMN_GLBL_RESCODE_OFFSET_MID_CTRL 0x000000fc - -#define REG_DSI_5nm_PHY_CMN_GLBL_LPTX_STR_CTRL 0x00000100 - -#define REG_DSI_5nm_PHY_CMN_GLBL_PEMPH_CTRL_0 0x00000104 - -#define REG_DSI_5nm_PHY_CMN_GLBL_PEMPH_CTRL_1 0x00000108 - -#define REG_DSI_5nm_PHY_CMN_GLBL_STR_SWI_CAL_SEL_CTRL 0x0000010c - -#define REG_DSI_5nm_PHY_CMN_VREG_CTRL_1 0x00000110 - -#define REG_DSI_5nm_PHY_CMN_CTRL_4 0x00000114 - -#define REG_DSI_5nm_PHY_CMN_PHY_STATUS 0x00000140 - -#define REG_DSI_5nm_PHY_CMN_LANE_STATUS0 0x00000148 - -#define REG_DSI_5nm_PHY_CMN_LANE_STATUS1 0x0000014c - -static inline uint32_t REG_DSI_5nm_PHY_LN(uint32_t i0) { return 0x00000000 + 0x80*i0; } - -static inline uint32_t REG_DSI_5nm_PHY_LN_CFG0(uint32_t i0) { return 0x00000000 + 0x80*i0; } - -static inline uint32_t REG_DSI_5nm_PHY_LN_CFG1(uint32_t i0) { return 0x00000004 + 0x80*i0; } - -static inline uint32_t REG_DSI_5nm_PHY_LN_CFG2(uint32_t i0) { return 0x00000008 + 0x80*i0; } - -static inline uint32_t REG_DSI_5nm_PHY_LN_TEST_DATAPATH(uint32_t i0) { return 0x0000000c + 0x80*i0; } - -static inline uint32_t REG_DSI_5nm_PHY_LN_PIN_SWAP(uint32_t i0) { return 0x00000010 + 0x80*i0; } - -static inline uint32_t REG_DSI_5nm_PHY_LN_LPRX_CTRL(uint32_t i0) { return 0x00000014 + 0x80*i0; } - -static inline uint32_t REG_DSI_5nm_PHY_LN_TX_DCTRL(uint32_t i0) { return 0x00000018 + 0x80*i0; } - -#define REG_DSI_5nm_PHY_PLL_ANALOG_CONTROLS_ONE 0x00000000 - -#define REG_DSI_5nm_PHY_PLL_ANALOG_CONTROLS_TWO 0x00000004 - -#define REG_DSI_5nm_PHY_PLL_INT_LOOP_SETTINGS 0x00000008 - -#define REG_DSI_5nm_PHY_PLL_INT_LOOP_SETTINGS_TWO 0x0000000c - -#define REG_DSI_5nm_PHY_PLL_ANALOG_CONTROLS_THREE 0x00000010 - -#define REG_DSI_5nm_PHY_PLL_ANALOG_CONTROLS_FOUR 0x00000014 - -#define REG_DSI_5nm_PHY_PLL_ANALOG_CONTROLS_FIVE 0x00000018 - -#define REG_DSI_5nm_PHY_PLL_INT_LOOP_CONTROLS 0x0000001c - -#define REG_DSI_5nm_PHY_PLL_DSM_DIVIDER 0x00000020 - -#define REG_DSI_5nm_PHY_PLL_FEEDBACK_DIVIDER 0x00000024 - -#define REG_DSI_5nm_PHY_PLL_SYSTEM_MUXES 0x00000028 - -#define REG_DSI_5nm_PHY_PLL_FREQ_UPDATE_CONTROL_OVERRIDES 0x0000002c - -#define REG_DSI_5nm_PHY_PLL_CMODE 0x00000030 - -#define REG_DSI_5nm_PHY_PLL_PSM_CTRL 0x00000034 - -#define REG_DSI_5nm_PHY_PLL_RSM_CTRL 0x00000038 - -#define REG_DSI_5nm_PHY_PLL_VCO_TUNE_MAP 0x0000003c - -#define REG_DSI_5nm_PHY_PLL_PLL_CNTRL 0x00000040 - -#define REG_DSI_5nm_PHY_PLL_CALIBRATION_SETTINGS 0x00000044 - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_CAL_TIMER_LOW 0x00000048 - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_CAL_TIMER_HIGH 0x0000004c - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_CAL_SETTINGS 0x00000050 - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_MIN 0x00000054 - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_MAX 0x00000058 - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_PFILT 0x0000005c - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_IFILT 0x00000060 - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_CAL_SETTINGS_TWO 0x00000064 - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_CAL_SETTINGS_THREE 0x00000068 - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_CAL_SETTINGS_FOUR 0x0000006c - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_ICODE_HIGH 0x00000070 - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_ICODE_LOW 0x00000074 - -#define REG_DSI_5nm_PHY_PLL_FREQ_DETECT_SETTINGS_ONE 0x00000078 - -#define REG_DSI_5nm_PHY_PLL_FREQ_DETECT_THRESH 0x0000007c - -#define REG_DSI_5nm_PHY_PLL_FREQ_DET_REFCLK_HIGH 0x00000080 - -#define REG_DSI_5nm_PHY_PLL_FREQ_DET_REFCLK_LOW 0x00000084 - -#define REG_DSI_5nm_PHY_PLL_FREQ_DET_PLLCLK_HIGH 0x00000088 - -#define REG_DSI_5nm_PHY_PLL_FREQ_DET_PLLCLK_LOW 0x0000008c - -#define REG_DSI_5nm_PHY_PLL_PFILT 0x00000090 - -#define REG_DSI_5nm_PHY_PLL_IFILT 0x00000094 - -#define REG_DSI_5nm_PHY_PLL_PLL_GAIN 0x00000098 - -#define REG_DSI_5nm_PHY_PLL_ICODE_LOW 0x0000009c - -#define REG_DSI_5nm_PHY_PLL_ICODE_HIGH 0x000000a0 - -#define REG_DSI_5nm_PHY_PLL_LOCKDET 0x000000a4 - -#define REG_DSI_5nm_PHY_PLL_OUTDIV 0x000000a8 - -#define REG_DSI_5nm_PHY_PLL_FASTLOCK_CONTROL 0x000000ac - -#define REG_DSI_5nm_PHY_PLL_PASS_OUT_OVERRIDE_ONE 0x000000b0 - -#define REG_DSI_5nm_PHY_PLL_PASS_OUT_OVERRIDE_TWO 0x000000b4 - -#define REG_DSI_5nm_PHY_PLL_CORE_OVERRIDE 0x000000b8 - -#define REG_DSI_5nm_PHY_PLL_CORE_INPUT_OVERRIDE 0x000000bc - -#define REG_DSI_5nm_PHY_PLL_RATE_CHANGE 0x000000c0 - -#define REG_DSI_5nm_PHY_PLL_PLL_DIGITAL_TIMERS 0x000000c4 - -#define REG_DSI_5nm_PHY_PLL_PLL_DIGITAL_TIMERS_TWO 0x000000c8 - -#define REG_DSI_5nm_PHY_PLL_DECIMAL_DIV_START 0x000000cc - -#define REG_DSI_5nm_PHY_PLL_FRAC_DIV_START_LOW 0x000000d0 - -#define REG_DSI_5nm_PHY_PLL_FRAC_DIV_START_MID 0x000000d4 - -#define REG_DSI_5nm_PHY_PLL_FRAC_DIV_START_HIGH 0x000000d8 - -#define REG_DSI_5nm_PHY_PLL_DEC_FRAC_MUXES 0x000000dc - -#define REG_DSI_5nm_PHY_PLL_DECIMAL_DIV_START_1 0x000000e0 - -#define REG_DSI_5nm_PHY_PLL_FRAC_DIV_START_LOW_1 0x000000e4 - -#define REG_DSI_5nm_PHY_PLL_FRAC_DIV_START_MID_1 0x000000e8 - -#define REG_DSI_5nm_PHY_PLL_FRAC_DIV_START_HIGH_1 0x000000ec - -#define REG_DSI_5nm_PHY_PLL_DECIMAL_DIV_START_2 0x000000f0 - -#define REG_DSI_5nm_PHY_PLL_FRAC_DIV_START_LOW_2 0x000000f4 - -#define REG_DSI_5nm_PHY_PLL_FRAC_DIV_START_MID_2 0x000000f8 - -#define REG_DSI_5nm_PHY_PLL_FRAC_DIV_START_HIGH_2 0x000000fc - -#define REG_DSI_5nm_PHY_PLL_MASH_CONTROL 0x00000100 - -#define REG_DSI_5nm_PHY_PLL_SSC_STEPSIZE_LOW 0x00000104 - -#define REG_DSI_5nm_PHY_PLL_SSC_STEPSIZE_HIGH 0x00000108 - -#define REG_DSI_5nm_PHY_PLL_SSC_DIV_PER_LOW 0x0000010c - -#define REG_DSI_5nm_PHY_PLL_SSC_DIV_PER_HIGH 0x00000110 - -#define REG_DSI_5nm_PHY_PLL_SSC_ADJPER_LOW 0x00000114 - -#define REG_DSI_5nm_PHY_PLL_SSC_ADJPER_HIGH 0x00000118 - -#define REG_DSI_5nm_PHY_PLL_SSC_MUX_CONTROL 0x0000011c - -#define REG_DSI_5nm_PHY_PLL_SSC_STEPSIZE_LOW_1 0x00000120 - -#define REG_DSI_5nm_PHY_PLL_SSC_STEPSIZE_HIGH_1 0x00000124 - -#define REG_DSI_5nm_PHY_PLL_SSC_DIV_PER_LOW_1 0x00000128 - -#define REG_DSI_5nm_PHY_PLL_SSC_DIV_PER_HIGH_1 0x0000012c - -#define REG_DSI_5nm_PHY_PLL_SSC_ADJPER_LOW_1 0x00000130 - -#define REG_DSI_5nm_PHY_PLL_SSC_ADJPER_HIGH_1 0x00000134 - -#define REG_DSI_5nm_PHY_PLL_SSC_STEPSIZE_LOW_2 0x00000138 - -#define REG_DSI_5nm_PHY_PLL_SSC_STEPSIZE_HIGH_2 0x0000013c - -#define REG_DSI_5nm_PHY_PLL_SSC_DIV_PER_LOW_2 0x00000140 - -#define REG_DSI_5nm_PHY_PLL_SSC_DIV_PER_HIGH_2 0x00000144 - -#define REG_DSI_5nm_PHY_PLL_SSC_ADJPER_LOW_2 0x00000148 - -#define REG_DSI_5nm_PHY_PLL_SSC_ADJPER_HIGH_2 0x0000014c - -#define REG_DSI_5nm_PHY_PLL_SSC_CONTROL 0x00000150 - -#define REG_DSI_5nm_PHY_PLL_PLL_OUTDIV_RATE 0x00000154 - -#define REG_DSI_5nm_PHY_PLL_PLL_LOCKDET_RATE_1 0x00000158 - -#define REG_DSI_5nm_PHY_PLL_PLL_LOCKDET_RATE_2 0x0000015c - -#define REG_DSI_5nm_PHY_PLL_PLL_PROP_GAIN_RATE_1 0x00000160 - -#define REG_DSI_5nm_PHY_PLL_PLL_PROP_GAIN_RATE_2 0x00000164 - -#define REG_DSI_5nm_PHY_PLL_PLL_BAND_SEL_RATE_1 0x00000168 - -#define REG_DSI_5nm_PHY_PLL_PLL_BAND_SEL_RATE_2 0x0000016c - -#define REG_DSI_5nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_1 0x00000170 - -#define REG_DSI_5nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_2 0x00000174 - -#define REG_DSI_5nm_PHY_PLL_PLL_FL_INT_GAIN_PFILT_BAND_1 0x00000178 - -#define REG_DSI_5nm_PHY_PLL_PLL_FL_INT_GAIN_PFILT_BAND_2 0x0000017c - -#define REG_DSI_5nm_PHY_PLL_PLL_FASTLOCK_EN_BAND 0x00000180 - -#define REG_DSI_5nm_PHY_PLL_FREQ_TUNE_ACCUM_INIT_MID 0x00000184 - -#define REG_DSI_5nm_PHY_PLL_FREQ_TUNE_ACCUM_INIT_HIGH 0x00000188 - -#define REG_DSI_5nm_PHY_PLL_FREQ_TUNE_ACCUM_INIT_MUX 0x0000018c - -#define REG_DSI_5nm_PHY_PLL_PLL_LOCK_OVERRIDE 0x00000190 - -#define REG_DSI_5nm_PHY_PLL_PLL_LOCK_DELAY 0x00000194 - -#define REG_DSI_5nm_PHY_PLL_PLL_LOCK_MIN_DELAY 0x00000198 - -#define REG_DSI_5nm_PHY_PLL_CLOCK_INVERTERS 0x0000019c - -#define REG_DSI_5nm_PHY_PLL_SPARE_AND_JPC_OVERRIDES 0x000001a0 - -#define REG_DSI_5nm_PHY_PLL_BIAS_CONTROL_1 0x000001a4 - -#define REG_DSI_5nm_PHY_PLL_BIAS_CONTROL_2 0x000001a8 - -#define REG_DSI_5nm_PHY_PLL_ALOG_OBSV_BUS_CTRL_1 0x000001ac - -#define REG_DSI_5nm_PHY_PLL_COMMON_STATUS_ONE 0x000001b0 - -#define REG_DSI_5nm_PHY_PLL_COMMON_STATUS_TWO 0x000001b4 - -#define REG_DSI_5nm_PHY_PLL_BAND_SEL_CAL 0x000001b8 - -#define REG_DSI_5nm_PHY_PLL_ICODE_ACCUM_STATUS_LOW 0x000001bc - -#define REG_DSI_5nm_PHY_PLL_ICODE_ACCUM_STATUS_HIGH 0x000001c0 - -#define REG_DSI_5nm_PHY_PLL_FD_OUT_LOW 0x000001c4 - -#define REG_DSI_5nm_PHY_PLL_FD_OUT_HIGH 0x000001c8 - -#define REG_DSI_5nm_PHY_PLL_ALOG_OBSV_BUS_STATUS_1 0x000001cc - -#define REG_DSI_5nm_PHY_PLL_PLL_MISC_CONFIG 0x000001d0 - -#define REG_DSI_5nm_PHY_PLL_FLL_CONFIG 0x000001d4 - -#define REG_DSI_5nm_PHY_PLL_FLL_FREQ_ACQ_TIME 0x000001d8 - -#define REG_DSI_5nm_PHY_PLL_FLL_CODE0 0x000001dc - -#define REG_DSI_5nm_PHY_PLL_FLL_CODE1 0x000001e0 - -#define REG_DSI_5nm_PHY_PLL_FLL_GAIN0 0x000001e4 - -#define REG_DSI_5nm_PHY_PLL_FLL_GAIN1 0x000001e8 - -#define REG_DSI_5nm_PHY_PLL_SW_RESET 0x000001ec - -#define REG_DSI_5nm_PHY_PLL_FAST_PWRUP 0x000001f0 - -#define REG_DSI_5nm_PHY_PLL_LOCKTIME0 0x000001f4 - -#define REG_DSI_5nm_PHY_PLL_LOCKTIME1 0x000001f8 - -#define REG_DSI_5nm_PHY_PLL_DEBUG_BUS_SEL 0x000001fc - -#define REG_DSI_5nm_PHY_PLL_DEBUG_BUS0 0x00000200 - -#define REG_DSI_5nm_PHY_PLL_DEBUG_BUS1 0x00000204 - -#define REG_DSI_5nm_PHY_PLL_DEBUG_BUS2 0x00000208 - -#define REG_DSI_5nm_PHY_PLL_DEBUG_BUS3 0x0000020c - -#define REG_DSI_5nm_PHY_PLL_ANALOG_FLL_CONTROL_OVERRIDES 0x00000210 - -#define REG_DSI_5nm_PHY_PLL_VCO_CONFIG 0x00000214 - -#define REG_DSI_5nm_PHY_PLL_VCO_CAL_CODE1_MODE0_STATUS 0x00000218 - -#define REG_DSI_5nm_PHY_PLL_VCO_CAL_CODE1_MODE1_STATUS 0x0000021c - -#define REG_DSI_5nm_PHY_PLL_RESET_SM_STATUS 0x00000220 - -#define REG_DSI_5nm_PHY_PLL_TDC_OFFSET 0x00000224 - -#define REG_DSI_5nm_PHY_PLL_PS3_PWRDOWN_CONTROLS 0x00000228 - -#define REG_DSI_5nm_PHY_PLL_PS4_PWRDOWN_CONTROLS 0x0000022c - -#define REG_DSI_5nm_PHY_PLL_PLL_RST_CONTROLS 0x00000230 - -#define REG_DSI_5nm_PHY_PLL_GEAR_BAND_SELECT_CONTROLS 0x00000234 - -#define REG_DSI_5nm_PHY_PLL_PSM_CLK_CONTROLS 0x00000238 - -#define REG_DSI_5nm_PHY_PLL_SYSTEM_MUXES_2 0x0000023c - -#define REG_DSI_5nm_PHY_PLL_VCO_CONFIG_1 0x00000240 - -#define REG_DSI_5nm_PHY_PLL_VCO_CONFIG_2 0x00000244 - -#define REG_DSI_5nm_PHY_PLL_CLOCK_INVERTERS_1 0x00000248 - -#define REG_DSI_5nm_PHY_PLL_CLOCK_INVERTERS_2 0x0000024c - -#define REG_DSI_5nm_PHY_PLL_CMODE_1 0x00000250 - -#define REG_DSI_5nm_PHY_PLL_CMODE_2 0x00000254 - -#define REG_DSI_5nm_PHY_PLL_ANALOG_CONTROLS_FIVE_1 0x00000258 - -#define REG_DSI_5nm_PHY_PLL_ANALOG_CONTROLS_FIVE_2 0x0000025c - -#define REG_DSI_5nm_PHY_PLL_PERF_OPTIMIZE 0x00000260 - - -#endif /* DSI_PHY_5NM_XML */ diff --git a/drivers/gpu/drm/msm/dsi/dsi_phy_7nm.xml.h b/drivers/gpu/drm/msm/dsi/dsi_phy_7nm.xml.h index 782f6b332baf..5bc061797003 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_phy_7nm.xml.h +++ b/drivers/gpu/drm/msm/dsi/dsi_phy_7nm.xml.h @@ -8,27 +8,26 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) - -Copyright (C) 2013-2021 by the following authors: +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) + +Copyright (C) 2013-2022 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin) @@ -156,6 +155,8 @@ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. #define REG_DSI_7nm_PHY_CMN_LANE_STATUS1 0x0000014c +#define REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE10 0x000001ac + static inline uint32_t REG_DSI_7nm_PHY_LN(uint32_t i0) { return 0x00000000 + 0x80*i0; } static inline uint32_t REG_DSI_7nm_PHY_LN_CFG0(uint32_t i0) { return 0x00000000 + 0x80*i0; } diff --git a/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h b/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h index fbb6a7a6b940..03bc322d0487 100644 --- a/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h +++ b/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 2027b38617ab..a39de3bdc7fa 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -709,14 +709,14 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) if (!of_property_read_u32(dev->of_node, "phy-type", &phy_type)) phy->cphy_mode = (phy_type == PHY_TYPE_CPHY); - phy->base = msm_ioremap_size(pdev, "dsi_phy", "DSI_PHY", &phy->base_size); + phy->base = msm_ioremap_size(pdev, "dsi_phy", &phy->base_size); if (IS_ERR(phy->base)) { DRM_DEV_ERROR(dev, "%s: failed to map phy base\n", __func__); ret = -ENOMEM; goto fail; } - phy->pll_base = msm_ioremap_size(pdev, "dsi_pll", "DSI_PLL", &phy->pll_size); + phy->pll_base = msm_ioremap_size(pdev, "dsi_pll", &phy->pll_size); if (IS_ERR(phy->pll_base)) { DRM_DEV_ERROR(&pdev->dev, "%s: failed to map pll base\n", __func__); ret = -ENOMEM; @@ -724,7 +724,7 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) } if (phy->cfg->has_phy_lane) { - phy->lane_base = msm_ioremap_size(pdev, "dsi_phy_lane", "DSI_PHY_LANE", &phy->lane_size); + phy->lane_base = msm_ioremap_size(pdev, "dsi_phy_lane", &phy->lane_size); if (IS_ERR(phy->lane_base)) { DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy lane base\n", __func__); ret = -ENOMEM; @@ -733,7 +733,7 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) } if (phy->cfg->has_phy_regulator) { - phy->reg_base = msm_ioremap_size(pdev, "dsi_phy_regulator", "DSI_PHY_REG", &phy->reg_size); + phy->reg_base = msm_ioremap_size(pdev, "dsi_phy_regulator", &phy->reg_size); if (IS_ERR(phy->reg_base)) { DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy regulator base\n", __func__); ret = -ENOMEM; @@ -741,6 +741,12 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) } } + if (phy->cfg->ops.parse_dt_properties) { + ret = phy->cfg->ops.parse_dt_properties(phy); + if (ret) + goto fail; + } + ret = dsi_phy_regulator_init(phy); if (ret) goto fail; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index 4c8257581bfc..dc91b43d5a38 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -25,6 +25,7 @@ struct msm_dsi_phy_ops { void (*save_pll_state)(struct msm_dsi_phy *phy); int (*restore_pll_state)(struct msm_dsi_phy *phy); bool (*set_continuous_clock)(struct msm_dsi_phy *phy, bool enable); + int (*parse_dt_properties)(struct msm_dsi_phy *phy); }; struct msm_dsi_phy_cfg { @@ -82,6 +83,8 @@ struct msm_dsi_dphy_timing { #define DSI_PIXEL_PLL_CLK 1 #define NUM_PROVIDED_CLKS 2 +#define DSI_LANE_MAX 5 + struct msm_dsi_phy { struct platform_device *pdev; void __iomem *base; @@ -99,6 +102,7 @@ struct msm_dsi_phy { struct msm_dsi_dphy_timing timing; const struct msm_dsi_phy_cfg *cfg; + void *tuning_cfg; enum msm_dsi_phy_usecase usecase; bool regulator_ldo_mode; 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 d8128f50b0dd..08b015ea1b1e 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c @@ -83,6 +83,18 @@ struct dsi_pll_10nm { #define to_pll_10nm(x) container_of(x, struct dsi_pll_10nm, clk_hw) +/** + * struct dsi_phy_10nm_tuning_cfg - Holds 10nm PHY tuning config parameters. + * @rescode_offset_top: Offset for pull-up legs rescode. + * @rescode_offset_bot: Offset for pull-down legs rescode. + * @vreg_ctrl: vreg ctrl to drive LDO level + */ +struct dsi_phy_10nm_tuning_cfg { + u8 rescode_offset_top[DSI_LANE_MAX]; + u8 rescode_offset_bot[DSI_LANE_MAX]; + u8 vreg_ctrl; +}; + /* * Global list of private DSI PLL struct pointers. We need this for bonded DSI * mode, where the master PLL's clk_ops needs access the slave's private data @@ -562,7 +574,9 @@ static int pll_10nm_register(struct dsi_pll_10nm *pll_10nm, struct clk_hw **prov char clk_name[32], parent[32], vco_name[32]; char parent2[32], parent3[32], parent4[32]; struct clk_init_data vco_init = { - .parent_names = (const char *[]){ "xo" }, + .parent_data = &(const struct clk_parent_data) { + .fw_name = "ref", + }, .num_parents = 1, .name = vco_name, .flags = CLK_IGNORE_UNUSED, @@ -747,6 +761,7 @@ static void dsi_phy_hw_v3_0_lane_settings(struct msm_dsi_phy *phy) int i; u8 tx_dctrl[] = { 0x00, 0x00, 0x00, 0x04, 0x01 }; void __iomem *lane_base = phy->lane_base; + struct dsi_phy_10nm_tuning_cfg *tuning_cfg = phy->tuning_cfg; if (phy->cfg->quirks & DSI_PHY_10NM_QUIRK_OLD_TIMINGS) tx_dctrl[3] = 0x02; @@ -775,10 +790,13 @@ static void dsi_phy_hw_v3_0_lane_settings(struct msm_dsi_phy *phy) dsi_phy_write(lane_base + REG_DSI_10nm_PHY_LN_CFG2(i), 0x0); dsi_phy_write(lane_base + REG_DSI_10nm_PHY_LN_CFG3(i), i == 4 ? 0x80 : 0x0); - dsi_phy_write(lane_base + - REG_DSI_10nm_PHY_LN_OFFSET_TOP_CTRL(i), 0x0); - dsi_phy_write(lane_base + - REG_DSI_10nm_PHY_LN_OFFSET_BOT_CTRL(i), 0x0); + + /* platform specific dsi phy drive strength adjustment */ + dsi_phy_write(lane_base + REG_DSI_10nm_PHY_LN_OFFSET_TOP_CTRL(i), + tuning_cfg->rescode_offset_top[i]); + dsi_phy_write(lane_base + REG_DSI_10nm_PHY_LN_OFFSET_BOT_CTRL(i), + tuning_cfg->rescode_offset_bot[i]); + dsi_phy_write(lane_base + REG_DSI_10nm_PHY_LN_TX_DCTRL(i), tx_dctrl[i]); } @@ -799,6 +817,7 @@ static int dsi_10nm_phy_enable(struct msm_dsi_phy *phy, u32 const timeout_us = 1000; struct msm_dsi_dphy_timing *timing = &phy->timing; void __iomem *base = phy->base; + struct dsi_phy_10nm_tuning_cfg *tuning_cfg = phy->tuning_cfg; u32 data; DBG(""); @@ -834,8 +853,9 @@ static int dsi_10nm_phy_enable(struct msm_dsi_phy *phy, /* Select MS1 byte-clk */ dsi_phy_write(base + REG_DSI_10nm_PHY_CMN_GLBL_CTRL, 0x10); - /* Enable LDO */ - dsi_phy_write(base + REG_DSI_10nm_PHY_CMN_VREG_CTRL, 0x59); + /* Enable LDO with platform specific drive level/amplitude adjustment */ + dsi_phy_write(base + REG_DSI_10nm_PHY_CMN_VREG_CTRL, + tuning_cfg->vreg_ctrl); /* Configure PHY lane swap (TODO: we need to calculate this) */ dsi_phy_write(base + REG_DSI_10nm_PHY_CMN_LANE_CFG0, 0x21); @@ -922,6 +942,92 @@ static void dsi_10nm_phy_disable(struct msm_dsi_phy *phy) DBG("DSI%d PHY disabled", phy->id); } +static int dsi_10nm_phy_parse_dt(struct msm_dsi_phy *phy) +{ + struct device *dev = &phy->pdev->dev; + struct dsi_phy_10nm_tuning_cfg *tuning_cfg; + s8 offset_top[DSI_LANE_MAX] = { 0 }; /* No offset */ + s8 offset_bot[DSI_LANE_MAX] = { 0 }; /* No offset */ + u32 ldo_level = 400; /* 400mV */ + u8 level; + int ret, i; + + tuning_cfg = devm_kzalloc(dev, sizeof(*tuning_cfg), GFP_KERNEL); + if (!tuning_cfg) + return -ENOMEM; + + /* Drive strength adjustment parameters */ + ret = of_property_read_u8_array(dev->of_node, "qcom,phy-rescode-offset-top", + offset_top, DSI_LANE_MAX); + if (ret && ret != -EINVAL) { + DRM_DEV_ERROR(dev, "failed to parse qcom,phy-rescode-offset-top, %d\n", ret); + return ret; + } + + for (i = 0; i < DSI_LANE_MAX; i++) { + if (offset_top[i] < -32 || offset_top[i] > 31) { + DRM_DEV_ERROR(dev, + "qcom,phy-rescode-offset-top value %d is not in range [-32..31]\n", + offset_top[i]); + return -EINVAL; + } + tuning_cfg->rescode_offset_top[i] = 0x3f & offset_top[i]; + } + + ret = of_property_read_u8_array(dev->of_node, "qcom,phy-rescode-offset-bot", + offset_bot, DSI_LANE_MAX); + if (ret && ret != -EINVAL) { + DRM_DEV_ERROR(dev, "failed to parse qcom,phy-rescode-offset-bot, %d\n", ret); + return ret; + } + + for (i = 0; i < DSI_LANE_MAX; i++) { + if (offset_bot[i] < -32 || offset_bot[i] > 31) { + DRM_DEV_ERROR(dev, + "qcom,phy-rescode-offset-bot value %d is not in range [-32..31]\n", + offset_bot[i]); + return -EINVAL; + } + tuning_cfg->rescode_offset_bot[i] = 0x3f & offset_bot[i]; + } + + /* Drive level/amplitude adjustment parameters */ + ret = of_property_read_u32(dev->of_node, "qcom,phy-drive-ldo-level", &ldo_level); + if (ret && ret != -EINVAL) { + DRM_DEV_ERROR(dev, "failed to parse qcom,phy-drive-ldo-level, %d\n", ret); + return ret; + } + + switch (ldo_level) { + case 375: + level = 0; + break; + case 400: + level = 1; + break; + case 425: + level = 2; + break; + case 450: + level = 3; + break; + case 475: + level = 4; + break; + case 500: + level = 5; + break; + default: + DRM_DEV_ERROR(dev, "qcom,phy-drive-ldo-level %d is not supported\n", ldo_level); + return -EINVAL; + } + tuning_cfg->vreg_ctrl = 0x58 | (0x7 & level); + + phy->tuning_cfg = tuning_cfg; + + return 0; +} + const struct msm_dsi_phy_cfg dsi_phy_10nm_cfgs = { .has_phy_lane = true, .reg_cfg = { @@ -936,6 +1042,7 @@ const struct msm_dsi_phy_cfg dsi_phy_10nm_cfgs = { .pll_init = dsi_pll_10nm_init, .save_pll_state = dsi_10nm_pll_save_state, .restore_pll_state = dsi_10nm_pll_restore_state, + .parse_dt_properties = dsi_10nm_phy_parse_dt, }, .min_pll_rate = 1000000000UL, .max_pll_rate = 3500000000UL, @@ -957,6 +1064,7 @@ const struct msm_dsi_phy_cfg dsi_phy_10nm_8998_cfgs = { .pll_init = dsi_pll_10nm_init, .save_pll_state = dsi_10nm_pll_save_state, .restore_pll_state = dsi_10nm_pll_restore_state, + .parse_dt_properties = dsi_10nm_phy_parse_dt, }, .min_pll_rate = 1000000000UL, .max_pll_rate = 3500000000UL, 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 7414966f198e..75557ac99adf 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c @@ -802,7 +802,9 @@ static int pll_14nm_register(struct dsi_pll_14nm *pll_14nm, struct clk_hw **prov { char clk_name[32], parent[32], vco_name[32]; struct clk_init_data vco_init = { - .parent_names = (const char *[]){ "xo" }, + .parent_data = &(const struct clk_parent_data) { + .fw_name = "ref", + }, .num_parents = 1, .name = vco_name, .flags = CLK_IGNORE_UNUSED, 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 2da673a2add6..48eab80b548e 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c @@ -521,7 +521,9 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **prov { char clk_name[32], parent1[32], parent2[32], vco_name[32]; struct clk_init_data vco_init = { - .parent_names = (const char *[]){ "xo" }, + .parent_data = &(const struct clk_parent_data) { + .fw_name = "ref", .name = "xo", + }, .num_parents = 1, .name = vco_name, .flags = CLK_IGNORE_UNUSED, 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 71ed4aa0dc67..fc56cdcc9ad6 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 @@ -385,7 +385,9 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **prov { char *clk_name, *parent_name, *vco_name; struct clk_init_data vco_init = { - .parent_names = (const char *[]){ "pxo" }, + .parent_data = &(const struct clk_parent_data) { + .fw_name = "ref", + }, .num_parents = 1, .flags = CLK_IGNORE_UNUSED, .ops = &clk_ops_dsi_pll_28nm_vco, 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 079613d2aaa9..6e506feb111f 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -588,7 +588,9 @@ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provide char clk_name[32], parent[32], vco_name[32]; char parent2[32], parent3[32], parent4[32]; struct clk_init_data vco_init = { - .parent_names = (const char *[]){ "bi_tcxo" }, + .parent_data = &(const struct clk_parent_data) { + .fw_name = "ref", + }, .num_parents = 1, .name = vco_name, .flags = CLK_IGNORE_UNUSED, @@ -862,20 +864,26 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, /* Alter PHY configurations if data rate less than 1.5GHZ*/ less_than_1500_mhz = (clk_req->bitclk_rate <= 1500000000); - /* For C-PHY, no low power settings for lower clk rate */ - if (phy->cphy_mode) - less_than_1500_mhz = false; - if (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_1) { vreg_ctrl_0 = less_than_1500_mhz ? 0x53 : 0x52; - glbl_rescode_top_ctrl = less_than_1500_mhz ? 0x3d : 0x00; - glbl_rescode_bot_ctrl = less_than_1500_mhz ? 0x39 : 0x3c; + if (phy->cphy_mode) { + glbl_rescode_top_ctrl = 0x00; + glbl_rescode_bot_ctrl = 0x3c; + } else { + glbl_rescode_top_ctrl = less_than_1500_mhz ? 0x3d : 0x00; + glbl_rescode_bot_ctrl = less_than_1500_mhz ? 0x39 : 0x3c; + } glbl_str_swi_cal_sel_ctrl = 0x00; glbl_hstx_str_ctrl_0 = 0x88; } else { vreg_ctrl_0 = less_than_1500_mhz ? 0x5B : 0x59; - glbl_str_swi_cal_sel_ctrl = less_than_1500_mhz ? 0x03 : 0x00; - glbl_hstx_str_ctrl_0 = less_than_1500_mhz ? 0x66 : 0x88; + if (phy->cphy_mode) { + glbl_str_swi_cal_sel_ctrl = 0x03; + glbl_hstx_str_ctrl_0 = 0x66; + } else { + glbl_str_swi_cal_sel_ctrl = less_than_1500_mhz ? 0x03 : 0x00; + glbl_hstx_str_ctrl_0 = less_than_1500_mhz ? 0x66 : 0x88; + } glbl_rescode_top_ctrl = 0x03; glbl_rescode_bot_ctrl = 0x3c; } diff --git a/drivers/gpu/drm/msm/dsi/sfpb.xml.h b/drivers/gpu/drm/msm/dsi/sfpb.xml.h index 1f5e9e9f9803..2ae711cbec36 100644 --- a/drivers/gpu/drm/msm/dsi/sfpb.xml.h +++ b/drivers/gpu/drm/msm/dsi/sfpb.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 719720709e9e..ec324352e862 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -133,7 +133,7 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev) hdmi->config = config; spin_lock_init(&hdmi->reg_lock); - hdmi->mmio = msm_ioremap(pdev, config->mmio_name, "HDMI"); + hdmi->mmio = msm_ioremap(pdev, config->mmio_name); if (IS_ERR(hdmi->mmio)) { ret = PTR_ERR(hdmi->mmio); goto fail; @@ -144,8 +144,7 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev) config->mmio_name); hdmi->mmio_phy_addr = res->start; - hdmi->qfprom_mmio = msm_ioremap(pdev, - config->qfprom_mmio_name, "HDMI_QFPROM"); + hdmi->qfprom_mmio = msm_ioremap(pdev, config->qfprom_mmio_name); if (IS_ERR(hdmi->qfprom_mmio)) { DRM_DEV_INFO(&pdev->dev, "can't find qfprom resource\n"); hdmi->qfprom_mmio = NULL; @@ -306,7 +305,7 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, } ret = devm_request_irq(&pdev->dev, hdmi->irq, - msm_hdmi_irq, IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + msm_hdmi_irq, IRQF_TRIGGER_HIGH, "hdmi_isr", hdmi); if (ret < 0) { DRM_DEV_ERROR(dev->dev, "failed to request IRQ%u: %d\n", diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.xml.h b/drivers/gpu/drm/msm/hdmi/hdmi.xml.h index a1cede6cfd02..c9eb26df67c0 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.xml.h +++ b/drivers/gpu/drm/msm/hdmi/hdmi.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c index 68fba4bf7212..10ebe2089cb6 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c @@ -282,15 +282,18 @@ static enum drm_mode_status msm_hdmi_bridge_mode_valid(struct drm_bridge *bridge long actual, requested; requested = 1000 * mode->clock; - actual = kms->funcs->round_pixclk(kms, - requested, hdmi_bridge->hdmi->encoder); /* for mdp5/apq8074, we manage our own pixel clk (as opposed to * mdp4/dtv stuff where pixel clk is assigned to mdp/encoder * instead): */ - if (config->pwr_clk_cnt > 0) - actual = clk_round_rate(hdmi->pwr_clks[0], actual); + if (kms->funcs->round_pixclk) + actual = kms->funcs->round_pixclk(kms, + requested, hdmi_bridge->hdmi->encoder); + else if (config->pwr_clk_cnt > 0) + actual = clk_round_rate(hdmi->pwr_clks[0], requested); + else + actual = requested; DBG("requested=%ld, actual=%ld", requested, actual); diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c index 16b0e8836d27..9780107e1cc9 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c @@ -144,7 +144,7 @@ static int msm_hdmi_phy_probe(struct platform_device *pdev) if (!phy->cfg) return -ENODEV; - phy->mmio = msm_ioremap(pdev, "hdmi_phy", "HDMI_PHY"); + phy->mmio = msm_ioremap(pdev, "hdmi_phy"); if (IS_ERR(phy->mmio)) { DRM_DEV_ERROR(dev, "%s: failed to map phy base\n", __func__); return -ENOMEM; diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c index 99c7853353fd..b06d9d25a189 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c @@ -716,19 +716,18 @@ int msm_hdmi_pll_8996_init(struct platform_device *pdev) pll->pdev = pdev; - pll->mmio_qserdes_com = msm_ioremap(pdev, "hdmi_pll", "HDMI_PLL"); + pll->mmio_qserdes_com = msm_ioremap(pdev, "hdmi_pll"); if (IS_ERR(pll->mmio_qserdes_com)) { DRM_DEV_ERROR(dev, "failed to map pll base\n"); return -ENOMEM; } for (i = 0; i < HDMI_NUM_TX_CHANNEL; i++) { - char name[32], label[32]; + char name[32]; snprintf(name, sizeof(name), "hdmi_tx_l%d", i); - snprintf(label, sizeof(label), "HDMI_TX_L%d", i); - pll->mmio_qserdes_tx[i] = msm_ioremap(pdev, name, label); + pll->mmio_qserdes_tx[i] = msm_ioremap(pdev, name); if (IS_ERR(pll->mmio_qserdes_tx[i])) { DRM_DEV_ERROR(dev, "failed to map pll base\n"); return -ENOMEM; diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c b/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c index 562dfac67792..be4b0b67e797 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c @@ -434,7 +434,7 @@ int msm_hdmi_pll_8960_init(struct platform_device *pdev) if (!pll) return -ENOMEM; - pll->mmio = msm_ioremap(pdev, "hdmi_pll", "HDMI_PLL"); + pll->mmio = msm_ioremap(pdev, "hdmi_pll"); if (IS_ERR(pll->mmio)) { DRM_DEV_ERROR(dev, "failed to map pll base\n"); return -ENOMEM; diff --git a/drivers/gpu/drm/msm/hdmi/qfprom.xml.h b/drivers/gpu/drm/msm/hdmi/qfprom.xml.h index 4bf34cea1c89..3edc698c4df5 100644 --- a/drivers/gpu/drm/msm/hdmi/qfprom.xml.h +++ b/drivers/gpu/drm/msm/hdmi/qfprom.xml.h @@ -8,25 +8,24 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/mesa/mesa/src/freedreno/registers/msm.xml ( 981 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi.xml ( 15291 bytes, from 2021-06-15 22:36:13) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-06-05 21:37:42) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 10953 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/dsi_phy_5nm.xml ( 10900 bytes, from 2021-05-21 19:18:08) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-02-18 16:45:44) -- /home/robclark/src/mesa/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-02-18 16:45:44) +- /home/robclark/tmp/mesa/src/freedreno/registers/msm.xml ( 944 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/freedreno_copyright.xml ( 1572 bytes, from 2020-12-31 19:26:32) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp4.xml ( 20912 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp_common.xml ( 2849 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/mdp/mdp5.xml ( 37461 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi.xml ( 17560 bytes, from 2021-09-16 22:37:02) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_v2.xml ( 3236 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm_8960.xml ( 4935 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_28nm.xml ( 7004 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_20nm.xml ( 3712 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_14nm.xml ( 5381 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_10nm.xml ( 4499 bytes, from 2021-07-22 15:21:56) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/dsi_phy_7nm.xml ( 11007 bytes, from 2022-03-03 01:18:13) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/sfpb.xml ( 602 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/dsi/mmss_cc.xml ( 1686 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/qfprom.xml ( 600 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/hdmi/hdmi.xml ( 41874 bytes, from 2021-01-30 18:25:22) +- /home/robclark/tmp/mesa/src/freedreno/registers/edp/edp.xml ( 10416 bytes, from 2021-01-30 18:25:22) Copyright (C) 2013-2021 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index 27c9ae563f2f..1686fbb611fd 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -5,7 +5,6 @@ */ #include <drm/drm_atomic_uapi.h> -#include <drm/drm_gem_atomic_helper.h> #include <drm/drm_vblank.h> #include "msm_atomic_trace.h" @@ -13,20 +12,6 @@ #include "msm_gem.h" #include "msm_kms.h" -int msm_atomic_prepare_fb(struct drm_plane *plane, - struct drm_plane_state *new_state) -{ - struct msm_drm_private *priv = plane->dev->dev_private; - struct msm_kms *kms = priv->kms; - - if (!new_state->fb) - return 0; - - drm_gem_plane_helper_prepare_fb(plane, new_state); - - return msm_framebuffer_prepare(new_state->fb, kms->aspace); -} - /* * Helpers to control vblanks while we flush.. basically just to ensure * that vblank accounting is switched on, so we get valid seqn/timestamp diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index 0804c31e8962..ea2a20699cb4 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -201,9 +201,9 @@ shrink_set(void *data, u64 val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(shrink_fops, - shrink_get, shrink_set, - "0x%08llx\n"); +DEFINE_DEBUGFS_ATTRIBUTE(shrink_fops, + shrink_get, shrink_set, + "0x%08llx\n"); static int msm_gem_show(struct seq_file *m, void *arg) diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index ff19c5a94d6f..affa95eb05fc 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -41,9 +41,10 @@ * - 1.6.0 - Syncobj support * - 1.7.0 - Add MSM_PARAM_SUSPENDS to access suspend count * - 1.8.0 - Add MSM_BO_CACHED_COHERENT for supported GPUs (a6xx) + * - 1.9.0 - Add MSM_SUBMIT_FENCE_SN_IN */ #define MSM_VERSION_MAJOR 1 -#define MSM_VERSION_MINOR 8 +#define MSM_VERSION_MINOR 9 #define MSM_VERSION_PATCHLEVEL 0 static const struct drm_mode_config_funcs mode_config_funcs = { @@ -57,14 +58,6 @@ static const struct drm_mode_config_helper_funcs mode_config_helper_funcs = { .atomic_commit_tail = msm_atomic_commit_tail, }; -#ifdef CONFIG_DRM_MSM_REGISTER_LOGGING -static bool reglog; -MODULE_PARM_DESC(reglog, "Enable register read/write logging"); -module_param(reglog, bool, 0600); -#else -#define reglog 0 -#endif - #ifdef CONFIG_DRM_FBDEV_EMULATION static bool fbdev = true; MODULE_PARM_DESC(fbdev, "Enable fbdev compat layer"); @@ -83,152 +76,6 @@ static bool modeset = true; MODULE_PARM_DESC(modeset, "Use kernel modesetting [KMS] (1=on (default), 0=disable)"); module_param(modeset, bool, 0600); -/* - * Util/helpers: - */ - -struct clk *msm_clk_bulk_get_clock(struct clk_bulk_data *bulk, int count, - const char *name) -{ - int i; - char n[32]; - - snprintf(n, sizeof(n), "%s_clk", name); - - for (i = 0; bulk && i < count; i++) { - if (!strcmp(bulk[i].id, name) || !strcmp(bulk[i].id, n)) - return bulk[i].clk; - } - - - return NULL; -} - -struct clk *msm_clk_get(struct platform_device *pdev, const char *name) -{ - struct clk *clk; - char name2[32]; - - clk = devm_clk_get(&pdev->dev, name); - if (!IS_ERR(clk) || PTR_ERR(clk) == -EPROBE_DEFER) - return clk; - - snprintf(name2, sizeof(name2), "%s_clk", name); - - clk = devm_clk_get(&pdev->dev, name2); - if (!IS_ERR(clk)) - dev_warn(&pdev->dev, "Using legacy clk name binding. Use " - "\"%s\" instead of \"%s\"\n", name, name2); - - return clk; -} - -static void __iomem *_msm_ioremap(struct platform_device *pdev, const char *name, - const char *dbgname, bool quiet, phys_addr_t *psize) -{ - struct resource *res; - unsigned long size; - void __iomem *ptr; - - if (name) - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, name); - else - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - - if (!res) { - if (!quiet) - DRM_DEV_ERROR(&pdev->dev, "failed to get memory resource: %s\n", name); - return ERR_PTR(-EINVAL); - } - - size = resource_size(res); - - ptr = devm_ioremap(&pdev->dev, res->start, size); - if (!ptr) { - if (!quiet) - DRM_DEV_ERROR(&pdev->dev, "failed to ioremap: %s\n", name); - return ERR_PTR(-ENOMEM); - } - - if (reglog) - printk(KERN_DEBUG "IO:region %s %p %08lx\n", dbgname, ptr, size); - - if (psize) - *psize = size; - - return ptr; -} - -void __iomem *msm_ioremap(struct platform_device *pdev, const char *name, - const char *dbgname) -{ - return _msm_ioremap(pdev, name, dbgname, false, NULL); -} - -void __iomem *msm_ioremap_quiet(struct platform_device *pdev, const char *name, - const char *dbgname) -{ - return _msm_ioremap(pdev, name, dbgname, true, NULL); -} - -void __iomem *msm_ioremap_size(struct platform_device *pdev, const char *name, - const char *dbgname, phys_addr_t *psize) -{ - return _msm_ioremap(pdev, name, dbgname, false, psize); -} - -void msm_writel(u32 data, void __iomem *addr) -{ - if (reglog) - printk(KERN_DEBUG "IO:W %p %08x\n", addr, data); - writel(data, addr); -} - -u32 msm_readl(const void __iomem *addr) -{ - u32 val = readl(addr); - if (reglog) - pr_err("IO:R %p %08x\n", addr, val); - return val; -} - -void msm_rmw(void __iomem *addr, u32 mask, u32 or) -{ - u32 val = msm_readl(addr); - - val &= ~mask; - msm_writel(val | or, addr); -} - -static enum hrtimer_restart msm_hrtimer_worktimer(struct hrtimer *t) -{ - struct msm_hrtimer_work *work = container_of(t, - struct msm_hrtimer_work, timer); - - kthread_queue_work(work->worker, &work->work); - - return HRTIMER_NORESTART; -} - -void msm_hrtimer_queue_work(struct msm_hrtimer_work *work, - ktime_t wakeup_time, - enum hrtimer_mode mode) -{ - hrtimer_start(&work->timer, wakeup_time, mode); -} - -void msm_hrtimer_work_init(struct msm_hrtimer_work *work, - struct kthread_worker *worker, - kthread_work_func_t fn, - clockid_t clock_id, - enum hrtimer_mode mode) -{ - hrtimer_init(&work->timer, clock_id, mode); - work->timer.function = msm_hrtimer_worktimer; - work->worker = worker; - kthread_init_work(&work->work, fn); -} - static irqreturn_t msm_irq(int irq, void *arg) { struct drm_device *dev = arg; @@ -715,8 +562,16 @@ static void context_close(struct msm_file_private *ctx) static void msm_postclose(struct drm_device *dev, struct drm_file *file) { + struct msm_drm_private *priv = dev->dev_private; struct msm_file_private *ctx = file->driver_priv; + /* + * It is not possible to set sysprof param to non-zero if gpu + * is not initialized: + */ + if (priv->gpu) + msm_file_private_set_sysprof(ctx, priv->gpu, 0); + context_close(ctx); } @@ -766,7 +621,27 @@ static int msm_ioctl_get_param(struct drm_device *dev, void *data, if (!gpu) return -ENXIO; - return gpu->funcs->get_param(gpu, args->param, &args->value); + return gpu->funcs->get_param(gpu, file->driver_priv, + args->param, &args->value); +} + +static int msm_ioctl_set_param(struct drm_device *dev, void *data, + struct drm_file *file) +{ + struct msm_drm_private *priv = dev->dev_private; + struct drm_msm_param *args = data; + struct msm_gpu *gpu; + + if (args->pipe != MSM_PIPE_3D0) + return -EINVAL; + + gpu = priv->gpu; + + if (!gpu) + return -ENXIO; + + return gpu->funcs->set_param(gpu, file->driver_priv, + args->param, args->value); } static int msm_ioctl_gem_new(struct drm_device *dev, void *data, @@ -1054,6 +929,7 @@ static int msm_ioctl_submitqueue_close(struct drm_device *dev, void *data, static const struct drm_ioctl_desc msm_ioctls[] = { DRM_IOCTL_DEF_DRV(MSM_GET_PARAM, msm_ioctl_get_param, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(MSM_SET_PARAM, msm_ioctl_set_param, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(MSM_GEM_NEW, msm_ioctl_gem_new, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(MSM_GEM_INFO, msm_ioctl_gem_info, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(MSM_GEM_CPU_PREP, msm_ioctl_gem_cpu_prep, DRM_RENDER_ALLOW), @@ -1174,15 +1050,6 @@ static const struct dev_pm_ops msm_pm_ops = { */ /* - * NOTE: duplication of the same code as exynos or imx (or probably any other). - * so probably some room for some helpers - */ -static int compare_of(struct device *dev, void *data) -{ - return dev->of_node == data; -} - -/* * Identify what components need to be added by parsing what remote-endpoints * our MDP output ports are connected to. In the case of LVDS on MDP4, there * is no external component that we need to add since LVDS is within MDP4 @@ -1239,7 +1106,7 @@ static int add_components_mdp(struct device *mdp_dev, if (of_device_is_available(intf)) drm_of_component_match_add(master_dev, matchptr, - compare_of, intf); + component_compare_of, intf); of_node_put(intf); } @@ -1285,7 +1152,7 @@ static int add_display_components(struct platform_device *pdev, put_device(mdp_dev); /* add the MDP component itself */ - drm_of_component_match_add(dev, matchptr, compare_of, + drm_of_component_match_add(dev, matchptr, component_compare_of, mdp_dev->of_node); break; case KMS_MDP4: @@ -1324,7 +1191,7 @@ static int add_gpu_components(struct device *dev, return 0; if (of_device_is_available(np)) - drm_of_component_match_add(dev, matchptr, compare_of, np); + drm_of_component_match_add(dev, matchptr, component_compare_of, np); of_node_put(np); @@ -1438,9 +1305,12 @@ static void msm_pdev_shutdown(struct platform_device *pdev) static const struct of_device_id dt_match[] = { { .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 }, { .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 }, + { .compatible = "qcom,msm8998-mdss", .data = (void *)KMS_DPU }, + { .compatible = "qcom,qcm2290-mdss", .data = (void *)KMS_DPU }, { .compatible = "qcom,sdm845-mdss", .data = (void *)KMS_DPU }, { .compatible = "qcom,sc7180-mdss", .data = (void *)KMS_DPU }, { .compatible = "qcom,sc7280-mdss", .data = (void *)KMS_DPU }, + { .compatible = "qcom,sc8180x-mdss", .data = (void *)KMS_DPU }, { .compatible = "qcom,sm8150-mdss", .data = (void *)KMS_DPU }, { .compatible = "qcom,sm8250-mdss", .data = (void *)KMS_DPU }, {} diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index ae52412d529a..d661debb50f1 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -109,24 +109,6 @@ struct msm_display_topology { u32 num_dspp; }; -/** - * struct msm_display_info - defines display properties - * @intf_type: DRM_MODE_ENCODER_ type - * @capabilities: Bitmask of display flags - * @num_of_h_tiles: Number of horizontal tiles in case of split interface - * @h_tile_instance: Controller instance used per tile. Number of elements is - * based on num_of_h_tiles - * @is_te_using_watchdog_timer: Boolean to indicate watchdog TE is - * used instead of panel TE in cmd mode panels - */ -struct msm_display_info { - int intf_type; - uint32_t capabilities; - uint32_t num_of_h_tiles; - uint32_t h_tile_instance[MAX_H_TILES_PER_DISPLAY]; - bool is_te_using_watchdog_timer; -}; - /* Commit/Event thread specific structure */ struct msm_drm_thread { struct drm_device *dev; @@ -257,8 +239,6 @@ struct msm_format { struct msm_pending_timer; -int msm_atomic_prepare_fb(struct drm_plane *plane, - struct drm_plane_state *new_state); int msm_atomic_init_pending_timer(struct msm_pending_timer *timer, struct msm_kms *kms, int crtc_idx); void msm_atomic_destroy_pending_timer(struct msm_pending_timer *timer); @@ -317,9 +297,9 @@ int msm_gem_prime_pin(struct drm_gem_object *obj); void msm_gem_prime_unpin(struct drm_gem_object *obj); int msm_framebuffer_prepare(struct drm_framebuffer *fb, - struct msm_gem_address_space *aspace); + struct msm_gem_address_space *aspace, bool needs_dirtyfb); void msm_framebuffer_cleanup(struct drm_framebuffer *fb, - struct msm_gem_address_space *aspace); + struct msm_gem_address_space *aspace, bool needed_dirtyfb); uint32_t msm_framebuffer_iova(struct drm_framebuffer *fb, struct msm_gem_address_space *aspace, int plane); struct drm_gem_object *msm_framebuffer_bo(struct drm_framebuffer *fb, int plane); @@ -480,15 +460,21 @@ struct clk *msm_clk_get(struct platform_device *pdev, const char *name); struct clk *msm_clk_bulk_get_clock(struct clk_bulk_data *bulk, int count, const char *name); -void __iomem *msm_ioremap(struct platform_device *pdev, const char *name, - const char *dbgname); +void __iomem *msm_ioremap(struct platform_device *pdev, const char *name); void __iomem *msm_ioremap_size(struct platform_device *pdev, const char *name, - const char *dbgname, phys_addr_t *size); -void __iomem *msm_ioremap_quiet(struct platform_device *pdev, const char *name, - const char *dbgname); -void msm_writel(u32 data, void __iomem *addr); -u32 msm_readl(const void __iomem *addr); -void msm_rmw(void __iomem *addr, u32 mask, u32 or); + phys_addr_t *size); +void __iomem *msm_ioremap_quiet(struct platform_device *pdev, const char *name); + +#define msm_writel(data, addr) writel((data), (addr)) +#define msm_readl(addr) readl((addr)) + +static inline void msm_rmw(void __iomem *addr, u32 mask, u32 or) +{ + u32 val = msm_readl(addr); + + val &= ~mask; + msm_writel(val | or, addr); +} /** * struct msm_hrtimer_work - a helper to combine an hrtimer with kthread_work diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c index 4d34df5354e0..7137492fe78e 100644 --- a/drivers/gpu/drm/msm/msm_fb.c +++ b/drivers/gpu/drm/msm/msm_fb.c @@ -18,16 +18,36 @@ struct msm_framebuffer { struct drm_framebuffer base; const struct msm_format *format; + + /* Count of # of attached planes which need dirtyfb: */ + refcount_t dirtyfb; }; #define to_msm_framebuffer(x) container_of(x, struct msm_framebuffer, base) static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos); +static int msm_framebuffer_dirtyfb(struct drm_framebuffer *fb, + struct drm_file *file_priv, unsigned int flags, + unsigned int color, struct drm_clip_rect *clips, + unsigned int num_clips) +{ + struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb); + + /* If this fb is not used on any display requiring pixel data to be + * flushed, then skip dirtyfb + */ + if (refcount_read(&msm_fb->dirtyfb) == 1) + return 0; + + return drm_atomic_helper_dirtyfb(fb, file_priv, flags, color, + clips, num_clips); +} + static const struct drm_framebuffer_funcs msm_framebuffer_funcs = { .create_handle = drm_gem_fb_create_handle, .destroy = drm_gem_fb_destroy, - .dirty = drm_atomic_helper_dirtyfb, + .dirty = msm_framebuffer_dirtyfb, }; #ifdef CONFIG_DEBUG_FS @@ -48,17 +68,19 @@ void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m) } #endif -/* prepare/pin all the fb's bo's for scanout. Note that it is not valid - * to prepare an fb more multiple different initiator 'id's. But that - * should be fine, since only the scanout (mdpN) side of things needs - * this, the gpu doesn't care about fb's. +/* prepare/pin all the fb's bo's for scanout. */ int msm_framebuffer_prepare(struct drm_framebuffer *fb, - struct msm_gem_address_space *aspace) + struct msm_gem_address_space *aspace, + bool needs_dirtyfb) { + struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb); int ret, i, n = fb->format->num_planes; uint64_t iova; + if (needs_dirtyfb) + refcount_inc(&msm_fb->dirtyfb); + for (i = 0; i < n; i++) { ret = msm_gem_get_and_pin_iova(fb->obj[i], aspace, &iova); drm_dbg_state(fb->dev, "FB[%u]: iova[%d]: %08llx (%d)", fb->base.id, i, iova, ret); @@ -70,10 +92,15 @@ int msm_framebuffer_prepare(struct drm_framebuffer *fb, } void msm_framebuffer_cleanup(struct drm_framebuffer *fb, - struct msm_gem_address_space *aspace) + struct msm_gem_address_space *aspace, + bool needed_dirtyfb) { + struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb); int i, n = fb->format->num_planes; + if (needed_dirtyfb) + refcount_dec(&msm_fb->dirtyfb); + for (i = 0; i < n; i++) msm_gem_unpin_iova(fb->obj[i], aspace); } @@ -194,6 +221,8 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev, goto fail; } + refcount_set(&msm_fb->dirtyfb, 1); + drm_dbg_state(dev, "create: FB ID: %d (%p)", fb->base.id, fb); return fb; diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index 54ca0817d807..af612add5264 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -35,6 +35,9 @@ struct msm_gem_address_space { * will be non-NULL: */ struct pid *pid; + + /* @faults: the number of GPU hangs associated with this address space */ + int faults; }; struct msm_gem_vma { diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 6cfa984dee6a..c6d60c8d286d 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -872,16 +872,46 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, submit->nr_cmds = i; + /* + * If using userspace provided seqno fence, validate that the id + * is available before arming sched job. Since access to fence_idr + * is serialized on the queue lock, the slot should be still avail + * after the job is armed + */ + if ((args->flags & MSM_SUBMIT_FENCE_SN_IN) && + idr_find(&queue->fence_idr, args->fence)) { + ret = -EINVAL; + goto out; + } + drm_sched_job_arm(&submit->base); submit->user_fence = dma_fence_get(&submit->base.s_fence->finished); - /* - * Allocate an id which can be used by WAIT_FENCE ioctl to map back - * to the underlying fence. - */ - submit->fence_id = idr_alloc_cyclic(&queue->fence_idr, - submit->user_fence, 1, INT_MAX, GFP_KERNEL); + if (args->flags & MSM_SUBMIT_FENCE_SN_IN) { + /* + * Userspace has assigned the seqno fence that it wants + * us to use. It is an error to pick a fence sequence + * number that is not available. + */ + submit->fence_id = args->fence; + ret = idr_alloc_u32(&queue->fence_idr, submit->user_fence, + &submit->fence_id, submit->fence_id, + GFP_KERNEL); + /* + * We've already validated that the fence_id slot is valid, + * so if idr_alloc_u32 failed, it is a kernel bug + */ + WARN_ON(ret); + } else { + /* + * Allocate an id which can be used by WAIT_FENCE ioctl to map + * back to the underlying fence. + */ + submit->fence_id = idr_alloc_cyclic(&queue->fence_idr, + submit->user_fence, 1, + INT_MAX, GFP_KERNEL); + } if (submit->fence_id < 0) { ret = submit->fence_id = 0; submit->fence_id = 0; diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 2c1049c0ea14..faf0c242874e 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -370,8 +370,8 @@ static void recover_worker(struct kthread_work *work) struct task_struct *task; /* Increment the fault counts */ - gpu->global_faults++; submit->queue->faults++; + submit->aspace->faults++; task = get_pid_task(submit->pid, PIDTYPE_PID); if (task) { @@ -389,6 +389,12 @@ static void recover_worker(struct kthread_work *work) } else { msm_rd_dump_submit(priv->hangrd, submit, NULL); } + } else { + /* + * We couldn't attribute this fault to any particular context, + * so increment the global fault count instead. + */ + gpu->global_faults++; } /* Record the crash state */ @@ -838,7 +844,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, gpu->funcs = funcs; gpu->name = name; - gpu->worker = kthread_create_worker(0, "%s-worker", gpu->name); + gpu->worker = kthread_create_worker(0, "gpu-worker"); if (IS_ERR(gpu->worker)) { ret = PTR_ERR(gpu->worker); gpu->worker = NULL; @@ -861,7 +867,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, /* Map registers: */ - gpu->mmio = msm_ioremap(pdev, config->ioname, name); + gpu->mmio = msm_ioremap(pdev, config->ioname); if (IS_ERR(gpu->mmio)) { ret = PTR_ERR(gpu->mmio); goto fail; @@ -876,7 +882,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, } ret = devm_request_irq(&pdev->dev, gpu->irq, irq_handler, - IRQF_TRIGGER_HIGH, gpu->name, gpu); + IRQF_TRIGGER_HIGH, "gpu-irq", gpu); if (ret) { DRM_DEV_ERROR(drm->dev, "failed to request IRQ%u: %d\n", gpu->irq, ret); goto fail; @@ -953,6 +959,8 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, gpu->nr_rings = nr_rings; + refcount_set(&gpu->sysprof_active, 1); + return 0; fail: diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 92aa1e9196c6..02419f2ca2bc 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -42,7 +42,10 @@ struct msm_gpu_config { * + z180_gpu */ struct msm_gpu_funcs { - int (*get_param)(struct msm_gpu *gpu, uint32_t param, uint64_t *value); + int (*get_param)(struct msm_gpu *gpu, struct msm_file_private *ctx, + uint32_t param, uint64_t *value); + int (*set_param)(struct msm_gpu *gpu, struct msm_file_private *ctx, + uint32_t param, uint64_t value); int (*hw_init)(struct msm_gpu *gpu); int (*pm_suspend)(struct msm_gpu *gpu); int (*pm_resume)(struct msm_gpu *gpu); @@ -157,6 +160,13 @@ struct msm_gpu { int nr_rings; /** + * sysprof_active: + * + * The count of contexts that have enabled system profiling. + */ + refcount_t sysprof_active; + + /** * cur_ctx_seqno: * * The ctx->seqno value of the last context to submit rendering, @@ -199,7 +209,10 @@ struct msm_gpu { /* does gpu need hw_init? */ bool needs_hw_init; - /* number of GPU hangs (for all contexts) */ + /** + * global_faults: number of GPU hangs not attributed to a particular + * address space + */ int global_faults; void __iomem *mmio; @@ -324,6 +337,24 @@ struct msm_file_private { int seqno; /** + * sysprof: + * + * The value of MSM_PARAM_SYSPROF set by userspace. This is + * intended to be used by system profiling tools like Mesa's + * pps-producer (perfetto), and restricted to CAP_SYS_ADMIN. + * + * Setting a value of 1 will preserve performance counters across + * context switches. Setting a value of 2 will in addition + * suppress suspend. (Performance counters lose state across + * power collapse, which is undesirable for profiling in some + * cases.) + * + * The value automatically reverts to zero when the drm device + * file is closed. + */ + int sysprof; + + /** * entities: * * Table of per-priority-level sched entities used by submitqueues @@ -519,6 +550,8 @@ void msm_submitqueue_close(struct msm_file_private *ctx); void msm_submitqueue_destroy(struct kref *kref); +int msm_file_private_set_sysprof(struct msm_file_private *ctx, + struct msm_gpu *gpu, int sysprof); void __msm_file_private_destroy(struct kref *kref); static inline void msm_file_private_put(struct msm_file_private *ctx) diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c index 9bf319be11f6..12641616acd3 100644 --- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c +++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c @@ -83,6 +83,12 @@ static struct devfreq_dev_profile msm_devfreq_profile = { static void msm_devfreq_boost_work(struct kthread_work *work); static void msm_devfreq_idle_work(struct kthread_work *work); +static bool has_devfreq(struct msm_gpu *gpu) +{ + struct msm_gpu_devfreq *df = &gpu->devfreq; + return !!df->devfreq; +} + void msm_devfreq_init(struct msm_gpu *gpu) { struct msm_gpu_devfreq *df = &gpu->devfreq; @@ -149,6 +155,9 @@ void msm_devfreq_cleanup(struct msm_gpu *gpu) { struct msm_gpu_devfreq *df = &gpu->devfreq; + if (!has_devfreq(gpu)) + return; + devfreq_cooling_unregister(gpu->cooling); dev_pm_qos_remove_request(&df->boost_freq); dev_pm_qos_remove_request(&df->idle_freq); @@ -156,16 +165,24 @@ void msm_devfreq_cleanup(struct msm_gpu *gpu) void msm_devfreq_resume(struct msm_gpu *gpu) { - gpu->devfreq.busy_cycles = 0; - gpu->devfreq.time = ktime_get(); + struct msm_gpu_devfreq *df = &gpu->devfreq; - devfreq_resume_device(gpu->devfreq.devfreq); + if (!has_devfreq(gpu)) + return; + + df->busy_cycles = 0; + df->time = ktime_get(); + + devfreq_resume_device(df->devfreq); } void msm_devfreq_suspend(struct msm_gpu *gpu) { struct msm_gpu_devfreq *df = &gpu->devfreq; + if (!has_devfreq(gpu)) + return; + devfreq_suspend_device(df->devfreq); cancel_idle_work(df); @@ -185,6 +202,9 @@ void msm_devfreq_boost(struct msm_gpu *gpu, unsigned factor) struct msm_gpu_devfreq *df = &gpu->devfreq; uint64_t freq; + if (!has_devfreq(gpu)) + return; + freq = get_freq(gpu); freq *= factor; @@ -207,7 +227,7 @@ void msm_devfreq_active(struct msm_gpu *gpu) struct devfreq_dev_status status; unsigned int idle_time; - if (!df->devfreq) + if (!has_devfreq(gpu)) return; /* @@ -253,7 +273,7 @@ void msm_devfreq_idle(struct msm_gpu *gpu) { struct msm_gpu_devfreq *df = &gpu->devfreq; - if (!df->devfreq) + if (!has_devfreq(gpu)) return; msm_hrtimer_queue_work(&df->idle_work, ms_to_ktime(1), diff --git a/drivers/gpu/drm/msm/msm_io_utils.c b/drivers/gpu/drm/msm/msm_io_utils.c new file mode 100644 index 000000000000..7b504617833a --- /dev/null +++ b/drivers/gpu/drm/msm/msm_io_utils.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2016-2018, 2020-2021 The Linux Foundation. All rights reserved. + * Copyright (C) 2013 Red Hat + * Author: Rob Clark <robdclark@gmail.com> + */ + +#include "msm_drv.h" + +/* + * Util/helpers: + */ + +struct clk *msm_clk_bulk_get_clock(struct clk_bulk_data *bulk, int count, + const char *name) +{ + int i; + char n[32]; + + snprintf(n, sizeof(n), "%s_clk", name); + + for (i = 0; bulk && i < count; i++) { + if (!strcmp(bulk[i].id, name) || !strcmp(bulk[i].id, n)) + return bulk[i].clk; + } + + + return NULL; +} + +struct clk *msm_clk_get(struct platform_device *pdev, const char *name) +{ + struct clk *clk; + char name2[32]; + + clk = devm_clk_get(&pdev->dev, name); + if (!IS_ERR(clk) || PTR_ERR(clk) == -EPROBE_DEFER) + return clk; + + snprintf(name2, sizeof(name2), "%s_clk", name); + + clk = devm_clk_get(&pdev->dev, name2); + if (!IS_ERR(clk)) + dev_warn(&pdev->dev, "Using legacy clk name binding. Use " + "\"%s\" instead of \"%s\"\n", name, name2); + + return clk; +} + +static void __iomem *_msm_ioremap(struct platform_device *pdev, const char *name, + bool quiet, phys_addr_t *psize) +{ + struct resource *res; + unsigned long size; + void __iomem *ptr; + + if (name) + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, name); + else + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + + if (!res) { + if (!quiet) + DRM_DEV_ERROR(&pdev->dev, "failed to get memory resource: %s\n", name); + return ERR_PTR(-EINVAL); + } + + size = resource_size(res); + + ptr = devm_ioremap(&pdev->dev, res->start, size); + if (!ptr) { + if (!quiet) + DRM_DEV_ERROR(&pdev->dev, "failed to ioremap: %s\n", name); + return ERR_PTR(-ENOMEM); + } + + if (psize) + *psize = size; + + return ptr; +} + +void __iomem *msm_ioremap(struct platform_device *pdev, const char *name) +{ + return _msm_ioremap(pdev, name, false, NULL); +} + +void __iomem *msm_ioremap_quiet(struct platform_device *pdev, const char *name) +{ + return _msm_ioremap(pdev, name, true, NULL); +} + +void __iomem *msm_ioremap_size(struct platform_device *pdev, const char *name, + phys_addr_t *psize) +{ + return _msm_ioremap(pdev, name, false, psize); +} + +static enum hrtimer_restart msm_hrtimer_worktimer(struct hrtimer *t) +{ + struct msm_hrtimer_work *work = container_of(t, + struct msm_hrtimer_work, timer); + + kthread_queue_work(work->worker, &work->work); + + return HRTIMER_NORESTART; +} + +void msm_hrtimer_queue_work(struct msm_hrtimer_work *work, + ktime_t wakeup_time, + enum hrtimer_mode mode) +{ + hrtimer_start(&work->timer, wakeup_time, mode); +} + +void msm_hrtimer_work_init(struct msm_hrtimer_work *work, + struct kthread_worker *worker, + kthread_work_func_t fn, + clockid_t clock_id, + enum hrtimer_mode mode) +{ + hrtimer_init(&work->timer, clock_id, mode); + work->timer.function = msm_hrtimer_worktimer; + work->worker = worker; + kthread_init_work(&work->work, fn); +} diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c index 81432ec07012..9d835331f214 100644 --- a/drivers/gpu/drm/msm/msm_rd.c +++ b/drivers/gpu/drm/msm/msm_rd.c @@ -62,6 +62,7 @@ enum rd_sect_type { RD_FRAG_SHADER, RD_BUFFER_CONTENTS, RD_GPU_ID, + RD_CHIP_ID, }; #define BUF_SZ 512 /* should be power of 2 */ @@ -196,12 +197,17 @@ static int rd_open(struct inode *inode, struct file *file) /* the parsing tools need to know gpu-id to know which * register database to load. + * + * Note: These particular params do not require a context */ - gpu->funcs->get_param(gpu, MSM_PARAM_GPU_ID, &val); + gpu->funcs->get_param(gpu, NULL, MSM_PARAM_GPU_ID, &val); gpu_id = val; rd_write_section(rd, RD_GPU_ID, &gpu_id, sizeof(gpu_id)); + gpu->funcs->get_param(gpu, NULL, MSM_PARAM_CHIP_ID, &val); + rd_write_section(rd, RD_CHIP_ID, &val, sizeof(val)); + out: mutex_unlock(&gpu->lock); return ret; diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index 7cb158bcbcf6..79b6ccd6ce64 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -7,6 +7,45 @@ #include "msm_gpu.h" +int msm_file_private_set_sysprof(struct msm_file_private *ctx, + struct msm_gpu *gpu, int sysprof) +{ + /* + * Since pm_runtime and sysprof_active are both refcounts, we + * call apply the new value first, and then unwind the previous + * value + */ + + switch (sysprof) { + default: + return -EINVAL; + case 2: + pm_runtime_get_sync(&gpu->pdev->dev); + fallthrough; + case 1: + refcount_inc(&gpu->sysprof_active); + fallthrough; + case 0: + break; + } + + /* unwind old value: */ + switch (ctx->sysprof) { + case 2: + pm_runtime_put_autosuspend(&gpu->pdev->dev); + fallthrough; + case 1: + refcount_dec(&gpu->sysprof_active); + fallthrough; + case 0: + break; + } + + ctx->sysprof = sysprof; + + return 0; +} + void __msm_file_private_destroy(struct kref *kref) { struct msm_file_private *ctx = container_of(kref, diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 133c8736426a..0c1a2ea0ed04 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -635,8 +635,6 @@ nv50_wndw_reset(struct drm_plane *plane) plane->funcs->atomic_destroy_state(plane, plane->state); __drm_atomic_helper_plane_reset(plane, &asyw->state); - plane->state->zpos = nv50_wndw_zpos_default(plane); - plane->state->normalized_zpos = nv50_wndw_zpos_default(plane); } static void diff --git a/drivers/gpu/drm/nouveau/include/nvfw/hs.h b/drivers/gpu/drm/nouveau/include/nvfw/hs.h index 64d0d32200c2..b53bbc4cd130 100644 --- a/drivers/gpu/drm/nouveau/include/nvfw/hs.h +++ b/drivers/gpu/drm/nouveau/include/nvfw/hs.h @@ -23,7 +23,7 @@ struct nvfw_hs_load_header { u32 data_dma_base; u32 data_size; u32 num_apps; - u32 apps[0]; + u32 apps[]; }; const struct nvfw_hs_load_header * diff --git a/drivers/gpu/drm/nouveau/include/nvif/list.h b/drivers/gpu/drm/nouveau/include/nvif/list.h deleted file mode 100644 index 8af5d144ecb0..000000000000 --- a/drivers/gpu/drm/nouveau/include/nvif/list.h +++ /dev/null @@ -1,353 +0,0 @@ -/* - * Copyright © 2010 Intel Corporation - * Copyright © 2010 Francisco Jerez <currojerez@riseup.net> - * - * 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 (including the next - * paragraph) 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 AUTHORS OR COPYRIGHT HOLDERS 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. - * - */ - -/* Modified by Ben Skeggs <bskeggs@redhat.com> to match kernel list APIs */ - -#ifndef _XORG_LIST_H_ -#define _XORG_LIST_H_ - -/** - * @file Classic doubly-link circular list implementation. - * For real usage examples of the linked list, see the file test/list.c - * - * Example: - * We need to keep a list of struct foo in the parent struct bar, i.e. what - * we want is something like this. - * - * struct bar { - * ... - * struct foo *list_of_foos; -----> struct foo {}, struct foo {}, struct foo{} - * ... - * } - * - * We need one list head in bar and a list element in all list_of_foos (both are of - * data type 'struct list_head'). - * - * struct bar { - * ... - * struct list_head list_of_foos; - * ... - * } - * - * struct foo { - * ... - * struct list_head entry; - * ... - * } - * - * Now we initialize the list head: - * - * struct bar bar; - * ... - * INIT_LIST_HEAD(&bar.list_of_foos); - * - * Then we create the first element and add it to this list: - * - * struct foo *foo = malloc(...); - * .... - * list_add(&foo->entry, &bar.list_of_foos); - * - * Repeat the above for each element you want to add to the list. Deleting - * works with the element itself. - * list_del(&foo->entry); - * free(foo); - * - * Note: calling list_del(&bar.list_of_foos) will set bar.list_of_foos to an empty - * list again. - * - * Looping through the list requires a 'struct foo' as iterator and the - * name of the field the subnodes use. - * - * struct foo *iterator; - * list_for_each_entry(iterator, &bar.list_of_foos, entry) { - * if (iterator->something == ...) - * ... - * } - * - * Note: You must not call list_del() on the iterator if you continue the - * loop. You need to run the safe for-each loop instead: - * - * struct foo *iterator, *next; - * list_for_each_entry_safe(iterator, next, &bar.list_of_foos, entry) { - * if (...) - * list_del(&iterator->entry); - * } - * - */ - -/** - * The linkage struct for list nodes. This struct must be part of your - * to-be-linked struct. struct list_head is required for both the head of the - * list and for each list node. - * - * Position and name of the struct list_head field is irrelevant. - * There are no requirements that elements of a list are of the same type. - * There are no requirements for a list head, any struct list_head can be a list - * head. - */ -struct list_head { - struct list_head *next, *prev; -}; - -/** - * Initialize the list as an empty list. - * - * Example: - * INIT_LIST_HEAD(&bar->list_of_foos); - * - * @param The list to initialized. - */ -#define LIST_HEAD_INIT(name) { &(name), &(name) } - -#define LIST_HEAD(name) \ - struct list_head name = LIST_HEAD_INIT(name) - -static inline void -INIT_LIST_HEAD(struct list_head *list) -{ - list->next = list->prev = list; -} - -static inline void -__list_add(struct list_head *entry, - struct list_head *prev, struct list_head *next) -{ - next->prev = entry; - entry->next = next; - entry->prev = prev; - prev->next = entry; -} - -/** - * Insert a new element after the given list head. The new element does not - * need to be initialised as empty list. - * The list changes from: - * head → some element → ... - * to - * head → new element → older element → ... - * - * Example: - * struct foo *newfoo = malloc(...); - * list_add(&newfoo->entry, &bar->list_of_foos); - * - * @param entry The new element to prepend to the list. - * @param head The existing list. - */ -static inline void -list_add(struct list_head *entry, struct list_head *head) -{ - __list_add(entry, head, head->next); -} - -/** - * Append a new element to the end of the list given with this list head. - * - * The list changes from: - * head → some element → ... → lastelement - * to - * head → some element → ... → lastelement → new element - * - * Example: - * struct foo *newfoo = malloc(...); - * list_add_tail(&newfoo->entry, &bar->list_of_foos); - * - * @param entry The new element to prepend to the list. - * @param head The existing list. - */ -static inline void -list_add_tail(struct list_head *entry, struct list_head *head) -{ - __list_add(entry, head->prev, head); -} - -static inline void -__list_del(struct list_head *prev, struct list_head *next) -{ - next->prev = prev; - prev->next = next; -} - -/** - * Remove the element from the list it is in. Using this function will reset - * the pointers to/from this element so it is removed from the list. It does - * NOT free the element itself or manipulate it otherwise. - * - * Using list_del on a pure list head (like in the example at the top of - * this file) will NOT remove the first element from - * the list but rather reset the list as empty list. - * - * Example: - * list_del(&foo->entry); - * - * @param entry The element to remove. - */ -static inline void -list_del(struct list_head *entry) -{ - __list_del(entry->prev, entry->next); -} - -static inline void -list_del_init(struct list_head *entry) -{ - __list_del(entry->prev, entry->next); - INIT_LIST_HEAD(entry); -} - -static inline void list_move_tail(struct list_head *list, - struct list_head *head) -{ - __list_del(list->prev, list->next); - list_add_tail(list, head); -} - -/** - * Check if the list is empty. - * - * Example: - * list_empty(&bar->list_of_foos); - * - * @return True if the list contains one or more elements or False otherwise. - */ -static inline bool -list_empty(struct list_head *head) -{ - return head->next == head; -} - -/** - * Returns a pointer to the container of this list element. - * - * Example: - * struct foo* f; - * f = container_of(&foo->entry, struct foo, entry); - * assert(f == foo); - * - * @param ptr Pointer to the struct list_head. - * @param type Data type of the list element. - * @param member Member name of the struct list_head field in the list element. - * @return A pointer to the data struct containing the list head. - */ -#ifndef container_of -#define container_of(ptr, type, member) \ - (type *)((char *)(ptr) - (char *) &((type *)0)->member) -#endif - -/** - * Alias of container_of - */ -#define list_entry(ptr, type, member) \ - container_of(ptr, type, member) - -/** - * Retrieve the first list entry for the given list pointer. - * - * Example: - * struct foo *first; - * first = list_first_entry(&bar->list_of_foos, struct foo, list_of_foos); - * - * @param ptr The list head - * @param type Data type of the list element to retrieve - * @param member Member name of the struct list_head field in the list element. - * @return A pointer to the first list element. - */ -#define list_first_entry(ptr, type, member) \ - list_entry((ptr)->next, type, member) - -/** - * Retrieve the last list entry for the given listpointer. - * - * Example: - * struct foo *first; - * first = list_last_entry(&bar->list_of_foos, struct foo, list_of_foos); - * - * @param ptr The list head - * @param type Data type of the list element to retrieve - * @param member Member name of the struct list_head field in the list element. - * @return A pointer to the last list element. - */ -#define list_last_entry(ptr, type, member) \ - list_entry((ptr)->prev, type, member) - -#define __container_of(ptr, sample, member) \ - (void *)container_of((ptr), typeof(*(sample)), member) - -/** - * Loop through the list given by head and set pos to struct in the list. - * - * Example: - * struct foo *iterator; - * list_for_each_entry(iterator, &bar->list_of_foos, entry) { - * [modify iterator] - * } - * - * This macro is not safe for node deletion. Use list_for_each_entry_safe - * instead. - * - * @param pos Iterator variable of the type of the list elements. - * @param head List head - * @param member Member name of the struct list_head in the list elements. - * - */ -#define list_for_each_entry(pos, head, member) \ - for (pos = __container_of((head)->next, pos, member); \ - &pos->member != (head); \ - pos = __container_of(pos->member.next, pos, member)) - -/** - * Loop through the list, keeping a backup pointer to the element. This - * macro allows for the deletion of a list element while looping through the - * list. - * - * See list_for_each_entry for more details. - */ -#define list_for_each_entry_safe(pos, tmp, head, member) \ - for (pos = __container_of((head)->next, pos, member), \ - tmp = __container_of(pos->member.next, pos, member); \ - &pos->member != (head); \ - pos = tmp, tmp = __container_of(pos->member.next, tmp, member)) - - -#define list_for_each_entry_reverse(pos, head, member) \ - for (pos = __container_of((head)->prev, pos, member); \ - &pos->member != (head); \ - pos = __container_of(pos->member.prev, pos, member)) - -#define list_for_each_entry_continue(pos, head, member) \ - for (pos = __container_of(pos->member.next, pos, member); \ - &pos->member != (head); \ - pos = __container_of(pos->member.next, pos, member)) - -#define list_for_each_entry_continue_reverse(pos, head, member) \ - for (pos = __container_of(pos->member.prev, pos, member); \ - &pos->member != (head); \ - pos = __container_of(pos->member.prev, pos, member)) - -#define list_for_each_entry_from(pos, head, member) \ - for (; \ - &pos->member != (head); \ - pos = __container_of(pos->member.next, pos, member)) - -#endif diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 3828aafd3ac4..7ba66ad68a8a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -39,6 +39,8 @@ #include <linux/sched/mm.h> #include <linux/hmm.h> +#include <linux/memremap.h> +#include <linux/migrate.h> /* * FIXME: this is ugly right now we are using TTM to allocate vram and we pin @@ -324,7 +326,6 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm) return NULL; } - get_page(page); lock_page(page); return page; } diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 46a5a1016e37..31a5b81ee9fc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -35,6 +35,7 @@ #include <linux/sched/mm.h> #include <linux/sort.h> #include <linux/hmm.h> +#include <linux/memremap.h> #include <linux/rmap.h> struct nouveau_svm { diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c index d0d52c1d4aee..992cc285f2fe 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c @@ -133,7 +133,7 @@ nvkm_device_tegra_probe_iommu(struct nvkm_device_tegra *tdev) * or equal to the system's PAGE_SIZE, with a preference if * both are equal. */ - pgsize_bitmap = tdev->iommu.domain->ops->pgsize_bitmap; + pgsize_bitmap = tdev->iommu.domain->pgsize_bitmap; if (pgsize_bitmap & PAGE_SIZE) { tdev->iommu.pgshift = PAGE_SHIFT; } else { diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c index 69b3e15b9356..0399f3390a0a 100644 --- a/drivers/gpu/drm/omapdrm/dss/dss.c +++ b/drivers/gpu/drm/omapdrm/dss/dss.c @@ -1344,12 +1344,6 @@ static const struct component_master_ops dss_component_ops = { .unbind = dss_unbind, }; -static int dss_component_compare(struct device *dev, void *data) -{ - struct device *child = data; - return dev == child; -} - struct dss_component_match_data { struct device *dev; struct component_match **match; @@ -1379,7 +1373,7 @@ static int dss_add_child_component(struct device *dev, void *data) return device_for_each_child(dev, cmatch, dss_add_child_component); - component_match_add(cmatch->dev, match, dss_component_compare, dev); + component_match_add(cmatch->dev, match, component_compare_dev, dev); return 0; } diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c index b35205c4e979..b83d91ec030a 100644 --- a/drivers/gpu/drm/omapdrm/omap_plane.c +++ b/drivers/gpu/drm/omapdrm/omap_plane.c @@ -403,7 +403,6 @@ void omap_plane_install_properties(struct drm_plane *plane, static void omap_plane_reset(struct drm_plane *plane) { - struct omap_plane *omap_plane = to_omap_plane(plane); struct omap_plane_state *omap_state; if (plane->state) @@ -414,15 +413,6 @@ static void omap_plane_reset(struct drm_plane *plane) return; __drm_atomic_helper_plane_reset(plane, &omap_state->base); - - /* - * Set the zpos default depending on whether we are a primary or overlay - * plane. - */ - plane->state->zpos = plane->type == DRM_PLANE_TYPE_PRIMARY - ? 0 : omap_plane->id; - plane->state->color_encoding = DRM_COLOR_YCBCR_BT601; - plane->state->color_range = DRM_COLOR_YCBCR_FULL_RANGE; } static struct drm_plane_state * @@ -533,6 +523,7 @@ struct drm_plane *omap_plane_init(struct drm_device *dev, unsigned int num_planes = dispc_get_num_ovls(priv->dispc); struct drm_plane *plane; struct omap_plane *omap_plane; + unsigned int zpos; int ret; u32 nformats; const u32 *formats; @@ -564,7 +555,16 @@ struct drm_plane *omap_plane_init(struct drm_device *dev, drm_plane_helper_add(plane, &omap_plane_helper_funcs); omap_plane_install_properties(plane, &plane->base); - drm_plane_create_zpos_property(plane, 0, 0, num_planes - 1); + + /* + * Set the zpos default depending on whether we are a primary or overlay + * plane. + */ + if (plane->type == DRM_PLANE_TYPE_PRIMARY) + zpos = 0; + else + zpos = omap_plane->id; + drm_plane_create_zpos_property(plane, zpos, 0, num_planes - 1); drm_plane_create_alpha_property(plane); drm_plane_create_blend_mode_property(plane, BIT(DRM_MODE_BLEND_PREMULTI) | BIT(DRM_MODE_BLEND_COVERAGE)); diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index bb2e47229c68..ddf5f38e8731 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -107,6 +107,7 @@ config DRM_PANEL_EDP select VIDEOMODE_HELPERS select DRM_DP_AUX_BUS select DRM_DP_HELPER + select DRM_KMS_HELPER help DRM panel driver for dumb eDP panels that need at most a regulator and a GPIO to be powered up. Optionally a backlight can be attached so diff --git a/drivers/gpu/drm/panel/panel-abt-y030xx067a.c b/drivers/gpu/drm/panel/panel-abt-y030xx067a.c index f043b484055b..ed626fdc08e8 100644 --- a/drivers/gpu/drm/panel/panel-abt-y030xx067a.c +++ b/drivers/gpu/drm/panel/panel-abt-y030xx067a.c @@ -293,15 +293,13 @@ static int y030xx067a_probe(struct spi_device *spi) return 0; } -static int y030xx067a_remove(struct spi_device *spi) +static void y030xx067a_remove(struct spi_device *spi) { struct y030xx067a *priv = spi_get_drvdata(spi); drm_panel_remove(&priv->panel); drm_panel_disable(&priv->panel); drm_panel_unprepare(&priv->panel); - - return 0; } static const struct drm_display_mode y030xx067a_modes[] = { diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9322.c b/drivers/gpu/drm/panel/panel-ilitek-ili9322.c index 8e84df9a0033..3dfafa585127 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9322.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9322.c @@ -896,14 +896,12 @@ static int ili9322_probe(struct spi_device *spi) return 0; } -static int ili9322_remove(struct spi_device *spi) +static void ili9322_remove(struct spi_device *spi) { struct ili9322 *ili = spi_get_drvdata(spi); ili9322_power_off(ili); drm_panel_remove(&ili->panel); - - return 0; } /* diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c index 2c3378a259b1..a07ef26234e5 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c @@ -728,7 +728,7 @@ static int ili9341_probe(struct spi_device *spi) return -1; } -static int ili9341_remove(struct spi_device *spi) +static void ili9341_remove(struct spi_device *spi) { const struct spi_device_id *id = spi_get_device_id(spi); struct ili9341 *ili = spi_get_drvdata(spi); @@ -741,7 +741,6 @@ static int ili9341_remove(struct spi_device *spi) drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); } - return 0; } static void ili9341_shutdown(struct spi_device *spi) diff --git a/drivers/gpu/drm/panel/panel-innolux-ej030na.c b/drivers/gpu/drm/panel/panel-innolux-ej030na.c index c558de3f99be..e3b1daa0cb72 100644 --- a/drivers/gpu/drm/panel/panel-innolux-ej030na.c +++ b/drivers/gpu/drm/panel/panel-innolux-ej030na.c @@ -219,15 +219,13 @@ static int ej030na_probe(struct spi_device *spi) return 0; } -static int ej030na_remove(struct spi_device *spi) +static void ej030na_remove(struct spi_device *spi) { struct ej030na *priv = spi_get_drvdata(spi); drm_panel_remove(&priv->panel); drm_panel_disable(&priv->panel); drm_panel_unprepare(&priv->panel); - - return 0; } static const struct drm_display_mode ej030na_modes[] = { diff --git a/drivers/gpu/drm/panel/panel-lg-lb035q02.c b/drivers/gpu/drm/panel/panel-lg-lb035q02.c index f3183b68704f..9d0d4faa3f58 100644 --- a/drivers/gpu/drm/panel/panel-lg-lb035q02.c +++ b/drivers/gpu/drm/panel/panel-lg-lb035q02.c @@ -203,14 +203,12 @@ static int lb035q02_probe(struct spi_device *spi) return 0; } -static int lb035q02_remove(struct spi_device *spi) +static void lb035q02_remove(struct spi_device *spi) { struct lb035q02_device *lcd = spi_get_drvdata(spi); drm_panel_remove(&lcd->panel); drm_panel_disable(&lcd->panel); - - return 0; } static const struct of_device_id lb035q02_of_match[] = { diff --git a/drivers/gpu/drm/panel/panel-lg-lg4573.c b/drivers/gpu/drm/panel/panel-lg-lg4573.c index 8e5160af1de5..cf246d15b7b6 100644 --- a/drivers/gpu/drm/panel/panel-lg-lg4573.c +++ b/drivers/gpu/drm/panel/panel-lg-lg4573.c @@ -266,14 +266,12 @@ static int lg4573_probe(struct spi_device *spi) return 0; } -static int lg4573_remove(struct spi_device *spi) +static void lg4573_remove(struct spi_device *spi) { struct lg4573 *ctx = spi_get_drvdata(spi); lg4573_display_off(ctx); drm_panel_remove(&ctx->panel); - - return 0; } static const struct of_device_id lg4573_of_match[] = { diff --git a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c index 6e5ab1debc8b..81c5c541a351 100644 --- a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c +++ b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c @@ -212,15 +212,13 @@ static int nl8048_probe(struct spi_device *spi) return 0; } -static int nl8048_remove(struct spi_device *spi) +static void nl8048_remove(struct spi_device *spi) { struct nl8048_panel *lcd = spi_get_drvdata(spi); drm_panel_remove(&lcd->panel); drm_panel_disable(&lcd->panel); drm_panel_unprepare(&lcd->panel); - - return 0; } static const struct of_device_id nl8048_of_match[] = { diff --git a/drivers/gpu/drm/panel/panel-novatek-nt39016.c b/drivers/gpu/drm/panel/panel-novatek-nt39016.c index d036853db865..f58cfb10b58a 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt39016.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt39016.c @@ -292,7 +292,7 @@ static int nt39016_probe(struct spi_device *spi) return 0; } -static int nt39016_remove(struct spi_device *spi) +static void nt39016_remove(struct spi_device *spi) { struct nt39016 *panel = spi_get_drvdata(spi); @@ -300,8 +300,6 @@ static int nt39016_remove(struct spi_device *spi) nt39016_disable(&panel->drm_panel); nt39016_unprepare(&panel->drm_panel); - - return 0; } static const struct drm_display_mode kd035g6_display_modes[] = { diff --git a/drivers/gpu/drm/panel/panel-samsung-db7430.c b/drivers/gpu/drm/panel/panel-samsung-db7430.c index ead479719f00..04640c5256a8 100644 --- a/drivers/gpu/drm/panel/panel-samsung-db7430.c +++ b/drivers/gpu/drm/panel/panel-samsung-db7430.c @@ -314,12 +314,11 @@ static int db7430_probe(struct spi_device *spi) return 0; } -static int db7430_remove(struct spi_device *spi) +static void db7430_remove(struct spi_device *spi) { struct db7430 *db = spi_get_drvdata(spi); drm_panel_remove(&db->panel); - return 0; } /* diff --git a/drivers/gpu/drm/panel/panel-samsung-ld9040.c b/drivers/gpu/drm/panel/panel-samsung-ld9040.c index c4b388850a13..01eb211f32f7 100644 --- a/drivers/gpu/drm/panel/panel-samsung-ld9040.c +++ b/drivers/gpu/drm/panel/panel-samsung-ld9040.c @@ -358,14 +358,12 @@ static int ld9040_probe(struct spi_device *spi) return 0; } -static int ld9040_remove(struct spi_device *spi) +static void ld9040_remove(struct spi_device *spi) { struct ld9040 *ctx = spi_get_drvdata(spi); ld9040_power_off(ctx); drm_panel_remove(&ctx->panel); - - return 0; } static const struct of_device_id ld9040_of_match[] = { diff --git a/drivers/gpu/drm/panel/panel-samsung-s6d27a1.c b/drivers/gpu/drm/panel/panel-samsung-s6d27a1.c index 1696ceb36aa0..2adb223a895c 100644 --- a/drivers/gpu/drm/panel/panel-samsung-s6d27a1.c +++ b/drivers/gpu/drm/panel/panel-samsung-s6d27a1.c @@ -291,12 +291,11 @@ static int s6d27a1_probe(struct spi_device *spi) return 0; } -static int s6d27a1_remove(struct spi_device *spi) +static void s6d27a1_remove(struct spi_device *spi) { struct s6d27a1 *ctx = spi_get_drvdata(spi); drm_panel_remove(&ctx->panel); - return 0; } static const struct of_device_id s6d27a1_match[] = { diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c index c178d962b0d5..d99afcc672ca 100644 --- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c +++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c @@ -62,10 +62,9 @@ static int s6e63m0_spi_probe(struct spi_device *spi) s6e63m0_spi_dcs_write, false); } -static int s6e63m0_spi_remove(struct spi_device *spi) +static void s6e63m0_spi_remove(struct spi_device *spi) { s6e63m0_remove(&spi->dev); - return 0; } static const struct of_device_id s6e63m0_spi_of_match[] = { diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index c324a3ed34b9..a34f4198a534 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2017,7 +2017,7 @@ static const struct display_timing innolux_g070y2_l01_timing = { static const struct panel_desc innolux_g070y2_l01 = { .timings = &innolux_g070y2_l01_timing, .num_timings = 1, - .bpc = 6, + .bpc = 8, .size = { .width = 152, .height = 91, @@ -3058,6 +3058,7 @@ static const struct drm_display_mode rocktech_rk101ii01d_ct_mode = { static const struct panel_desc rocktech_rk101ii01d_ct = { .modes = &rocktech_rk101ii01d_ct_mode, + .bpc = 8, .num_modes = 1, .size = { .width = 217, diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c index 61e565524542..bbc4569cbcdc 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c @@ -387,13 +387,11 @@ static int st7789v_probe(struct spi_device *spi) return 0; } -static int st7789v_remove(struct spi_device *spi) +static void st7789v_remove(struct spi_device *spi) { struct st7789v *ctx = spi_get_drvdata(spi); drm_panel_remove(&ctx->panel); - - return 0; } static const struct of_device_id st7789v_of_match[] = { diff --git a/drivers/gpu/drm/panel/panel-sony-acx565akm.c b/drivers/gpu/drm/panel/panel-sony-acx565akm.c index ba0b3ead150f..0d7541a33f87 100644 --- a/drivers/gpu/drm/panel/panel-sony-acx565akm.c +++ b/drivers/gpu/drm/panel/panel-sony-acx565akm.c @@ -655,7 +655,7 @@ static int acx565akm_probe(struct spi_device *spi) return 0; } -static int acx565akm_remove(struct spi_device *spi) +static void acx565akm_remove(struct spi_device *spi) { struct acx565akm_panel *lcd = spi_get_drvdata(spi); @@ -666,8 +666,6 @@ static int acx565akm_remove(struct spi_device *spi) drm_panel_disable(&lcd->panel); drm_panel_unprepare(&lcd->panel); - - return 0; } static const struct of_device_id acx565akm_of_match[] = { diff --git a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c index ba0c00d1a001..4dbf8b88f264 100644 --- a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c +++ b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c @@ -350,15 +350,13 @@ static int td028ttec1_probe(struct spi_device *spi) return 0; } -static int td028ttec1_remove(struct spi_device *spi) +static void td028ttec1_remove(struct spi_device *spi) { struct td028ttec1_panel *lcd = spi_get_drvdata(spi); drm_panel_remove(&lcd->panel); drm_panel_disable(&lcd->panel); drm_panel_unprepare(&lcd->panel); - - return 0; } static const struct of_device_id td028ttec1_of_match[] = { diff --git a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c index 1866cdb8f9c1..cf4609bb9b1d 100644 --- a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c +++ b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c @@ -463,7 +463,7 @@ static int td043mtea1_probe(struct spi_device *spi) return 0; } -static int td043mtea1_remove(struct spi_device *spi) +static void td043mtea1_remove(struct spi_device *spi) { struct td043mtea1_panel *lcd = spi_get_drvdata(spi); @@ -472,8 +472,6 @@ static int td043mtea1_remove(struct spi_device *spi) drm_panel_unprepare(&lcd->panel); sysfs_remove_group(&spi->dev.kobj, &td043mtea1_attr_group); - - return 0; } static const struct of_device_id td043mtea1_of_match[] = { diff --git a/drivers/gpu/drm/panel/panel-tpo-tpg110.c b/drivers/gpu/drm/panel/panel-tpo-tpg110.c index e3791dad6830..0b1f5a11a055 100644 --- a/drivers/gpu/drm/panel/panel-tpo-tpg110.c +++ b/drivers/gpu/drm/panel/panel-tpo-tpg110.c @@ -450,12 +450,11 @@ static int tpg110_probe(struct spi_device *spi) return 0; } -static int tpg110_remove(struct spi_device *spi) +static void tpg110_remove(struct spi_device *spi) { struct tpg110 *tpg = spi_get_drvdata(spi); drm_panel_remove(&tpg->panel); - return 0; } static const struct of_device_id tpg110_match[] = { diff --git a/drivers/gpu/drm/panel/panel-widechips-ws2401.c b/drivers/gpu/drm/panel/panel-widechips-ws2401.c index 8bc976f54b80..236f3cb2b594 100644 --- a/drivers/gpu/drm/panel/panel-widechips-ws2401.c +++ b/drivers/gpu/drm/panel/panel-widechips-ws2401.c @@ -407,12 +407,11 @@ static int ws2401_probe(struct spi_device *spi) return 0; } -static int ws2401_remove(struct spi_device *spi) +static void ws2401_remove(struct spi_device *spi) { struct ws2401 *ws = spi_get_drvdata(spi); drm_panel_remove(&ws->panel); - return 0; } /* diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 96bb5a465627..94b6f0a19c83 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -562,7 +562,7 @@ static int panfrost_probe(struct platform_device *pdev) pfdev->coherent = device_get_dma_attr(&pdev->dev) == DEV_DMA_COHERENT; - /* Allocate and initialze the DRM device. */ + /* Allocate and initialize the DRM device. */ ddev = drm_dev_alloc(&panfrost_drm_driver, &pdev->dev); if (IS_ERR(ddev)) return PTR_ERR(ddev); diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c index b0142341e223..77e7cb6d1ae3 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +// SPDX-License-Identifier: GPL-2.0 /* Copyright (C) 2019 Arm Ltd. * * Based on msm_gem_freedreno.c: diff --git a/drivers/gpu/drm/panfrost/panfrost_issues.h b/drivers/gpu/drm/panfrost/panfrost_issues.h index 8e59d765bf19..501a76c5e95f 100644 --- a/drivers/gpu/drm/panfrost/panfrost_issues.h +++ b/drivers/gpu/drm/panfrost/panfrost_issues.h @@ -14,7 +14,7 @@ */ enum panfrost_hw_issue { /* Need way to guarantee that all previously-translated memory accesses - * are commited */ + * are committed */ HW_ISSUE_6367, /* On job complete with non-done the cache is not flushed */ diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 39562f2d11a4..d3f82b26a631 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0 /* Copyright 2019 Linaro, Ltd, Rob Herring <robh@kernel.org> */ #include <drm/panfrost_drm.h> diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h index 16e776cc82ea..0b6cd8fdcb47 100644 --- a/drivers/gpu/drm/panfrost/panfrost_regs.h +++ b/drivers/gpu/drm/panfrost/panfrost_regs.h @@ -293,7 +293,7 @@ #define AS_FAULTADDRESS_LO(as) (MMU_AS(as) + 0x20) /* (RO) Fault Address for address space n, low word */ #define AS_FAULTADDRESS_HI(as) (MMU_AS(as) + 0x24) /* (RO) Fault Address for address space n, high word */ #define AS_STATUS(as) (MMU_AS(as) + 0x28) /* (RO) Status flags for address space n */ -/* Additional Bifrost AS regsiters */ +/* Additional Bifrost AS registers */ #define AS_TRANSCFG_LO(as) (MMU_AS(as) + 0x30) /* (RW) Translation table configuration for address space n, low word */ #define AS_TRANSCFG_HI(as) (MMU_AS(as) + 0x34) /* (RW) Translation table configuration for address space n, high word */ #define AS_FAULTEXTRA_LO(as) (MMU_AS(as) + 0x38) /* (RO) Secondary fault address for address space n, low word */ diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index a7925a8290b2..0cb1345c6ba4 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -777,7 +777,7 @@ static void radeon_fixup_lvds_native_mode(struct drm_encoder *encoder, if (mode->type & DRM_MODE_TYPE_PREFERRED) { if (mode->hdisplay != native_mode->hdisplay || mode->vdisplay != native_mode->vdisplay) - memcpy(native_mode, mode, sizeof(*mode)); + drm_mode_copy(native_mode, mode); } } @@ -786,7 +786,7 @@ static void radeon_fixup_lvds_native_mode(struct drm_encoder *encoder, list_for_each_entry_safe(mode, t, &connector->probed_modes, head) { if (mode->hdisplay == native_mode->hdisplay && mode->vdisplay == native_mode->vdisplay) { - *native_mode = *mode; + drm_mode_copy(native_mode, mode); drm_mode_set_crtcinfo(native_mode, CRTC_INTERLACE_HALVE_V); DRM_DEBUG_KMS("Determined LVDS native mode details from EDID\n"); break; diff --git a/drivers/gpu/drm/rcar-du/Makefile b/drivers/gpu/drm/rcar-du/Makefile index 286bc81b3e7c..e7275b5e7ec8 100644 --- a/drivers/gpu/drm/rcar-du/Makefile +++ b/drivers/gpu/drm/rcar-du/Makefile @@ -6,12 +6,6 @@ rcar-du-drm-y := rcar_du_crtc.o \ rcar_du_kms.o \ rcar_du_plane.o \ -rcar-du-drm-$(CONFIG_DRM_RCAR_LVDS) += rcar_du_of.o \ - rcar_du_of_lvds_r8a7790.dtb.o \ - rcar_du_of_lvds_r8a7791.dtb.o \ - rcar_du_of_lvds_r8a7793.dtb.o \ - rcar_du_of_lvds_r8a7795.dtb.o \ - rcar_du_of_lvds_r8a7796.dtb.o rcar-du-drm-$(CONFIG_DRM_RCAR_VSP) += rcar_du_vsp.o rcar-du-drm-$(CONFIG_DRM_RCAR_WRITEBACK) += rcar_du_writeback.o diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c index 982e450233ed..957ea97541d5 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c @@ -28,7 +28,6 @@ #include "rcar_du_drv.h" #include "rcar_du_kms.h" -#include "rcar_du_of.h" #include "rcar_du_regs.h" /* ----------------------------------------------------------------------------- @@ -634,6 +633,9 @@ static int rcar_du_probe(struct platform_device *pdev) unsigned int mask; int ret; + if (drm_firmware_drivers_only()) + return -ENODEV; + /* Allocate and initialize the R-Car device structure. */ rcdu = devm_drm_dev_alloc(&pdev->dev, &rcar_du_driver, struct rcar_du_device, ddev); @@ -699,22 +701,7 @@ static struct platform_driver rcar_du_platform_driver = { }, }; -static int __init rcar_du_init(void) -{ - if (drm_firmware_drivers_only()) - return -ENODEV; - - rcar_du_of_init(rcar_du_of_table); - - return platform_driver_register(&rcar_du_platform_driver); -} -module_init(rcar_du_init); - -static void __exit rcar_du_exit(void) -{ - platform_driver_unregister(&rcar_du_platform_driver); -} -module_exit(rcar_du_exit); +module_platform_driver(rcar_du_platform_driver); MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>"); MODULE_DESCRIPTION("Renesas R-Car Display Unit DRM Driver"); diff --git a/drivers/gpu/drm/rcar-du/rcar_du_of.c b/drivers/gpu/drm/rcar-du/rcar_du_of.c deleted file mode 100644 index afef69669bb4..000000000000 --- a/drivers/gpu/drm/rcar-du/rcar_du_of.c +++ /dev/null @@ -1,323 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * rcar_du_of.c - Legacy DT bindings compatibility - * - * Copyright (C) 2018 Laurent Pinchart <laurent.pinchart@ideasonboard.com> - * - * Based on work from Jyri Sarha <jsarha@ti.com> - * Copyright (C) 2015 Texas Instruments - */ - -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/of.h> -#include <linux/of_address.h> -#include <linux/of_fdt.h> -#include <linux/of_graph.h> -#include <linux/slab.h> - -#include "rcar_du_crtc.h" -#include "rcar_du_drv.h" -#include "rcar_du_of.h" - -/* ----------------------------------------------------------------------------- - * Generic Overlay Handling - */ - -struct rcar_du_of_overlay { - const char *compatible; - void *begin; - void *end; -}; - -#define RCAR_DU_OF_DTB(type, soc) \ - extern char __dtb_rcar_du_of_##type##_##soc##_begin[]; \ - extern char __dtb_rcar_du_of_##type##_##soc##_end[] - -#define RCAR_DU_OF_OVERLAY(type, soc) \ - { \ - .compatible = "renesas,du-" #soc, \ - .begin = __dtb_rcar_du_of_##type##_##soc##_begin, \ - .end = __dtb_rcar_du_of_##type##_##soc##_end, \ - } - -static int __init rcar_du_of_apply_overlay(const struct rcar_du_of_overlay *dtbs, - const char *compatible) -{ - const struct rcar_du_of_overlay *dtb = NULL; - unsigned int i; - int ovcs_id; - - for (i = 0; dtbs[i].compatible; ++i) { - if (!strcmp(dtbs[i].compatible, compatible)) { - dtb = &dtbs[i]; - break; - } - } - - if (!dtb) - return -ENODEV; - - ovcs_id = 0; - return of_overlay_fdt_apply(dtb->begin, dtb->end - dtb->begin, - &ovcs_id); -} - -static int __init rcar_du_of_add_property(struct of_changeset *ocs, - struct device_node *np, - const char *name, const void *value, - int length) -{ - struct property *prop; - int ret = -ENOMEM; - - prop = kzalloc(sizeof(*prop), GFP_KERNEL); - if (!prop) - return -ENOMEM; - - prop->name = kstrdup(name, GFP_KERNEL); - if (!prop->name) - goto out_err; - - prop->value = kmemdup(value, length, GFP_KERNEL); - if (!prop->value) - goto out_err; - - of_property_set_flag(prop, OF_DYNAMIC); - - prop->length = length; - - ret = of_changeset_add_property(ocs, np, prop); - if (!ret) - return 0; - -out_err: - kfree(prop->value); - kfree(prop->name); - kfree(prop); - return ret; -} - -/* ----------------------------------------------------------------------------- - * LVDS Overlays - */ - -RCAR_DU_OF_DTB(lvds, r8a7790); -RCAR_DU_OF_DTB(lvds, r8a7791); -RCAR_DU_OF_DTB(lvds, r8a7793); -RCAR_DU_OF_DTB(lvds, r8a7795); -RCAR_DU_OF_DTB(lvds, r8a7796); - -static const struct rcar_du_of_overlay rcar_du_lvds_overlays[] __initconst = { - RCAR_DU_OF_OVERLAY(lvds, r8a7790), - RCAR_DU_OF_OVERLAY(lvds, r8a7791), - RCAR_DU_OF_OVERLAY(lvds, r8a7793), - RCAR_DU_OF_OVERLAY(lvds, r8a7795), - RCAR_DU_OF_OVERLAY(lvds, r8a7796), - { /* Sentinel */ }, -}; - -static struct of_changeset rcar_du_lvds_changeset; - -static void __init rcar_du_of_lvds_patch_one(struct device_node *lvds, - const struct of_phandle_args *clk, - struct device_node *local, - struct device_node *remote) -{ - unsigned int psize; - unsigned int i; - __be32 value[4]; - int ret; - - /* - * Set the LVDS clocks property. This can't be performed by the overlay - * as the structure of the clock specifier has changed over time, and we - * don't know at compile time which binding version the system we will - * run on uses. - */ - if (clk->args_count >= ARRAY_SIZE(value) - 1) - return; - - of_changeset_init(&rcar_du_lvds_changeset); - - value[0] = cpu_to_be32(clk->np->phandle); - for (i = 0; i < clk->args_count; ++i) - value[i + 1] = cpu_to_be32(clk->args[i]); - - psize = (clk->args_count + 1) * 4; - ret = rcar_du_of_add_property(&rcar_du_lvds_changeset, lvds, - "clocks", value, psize); - if (ret < 0) - goto done; - - /* - * Insert the node in the OF graph: patch the LVDS ports remote-endpoint - * properties to point to the endpoints of the sibling nodes in the - * graph. This can't be performed by the overlay: on the input side the - * overlay would contain a phandle for the DU LVDS output port that - * would clash with the system DT, and on the output side the connection - * is board-specific. - */ - value[0] = cpu_to_be32(local->phandle); - value[1] = cpu_to_be32(remote->phandle); - - for (i = 0; i < 2; ++i) { - struct device_node *endpoint; - - endpoint = of_graph_get_endpoint_by_regs(lvds, i, 0); - if (!endpoint) { - ret = -EINVAL; - goto done; - } - - ret = rcar_du_of_add_property(&rcar_du_lvds_changeset, - endpoint, "remote-endpoint", - &value[i], sizeof(value[i])); - of_node_put(endpoint); - if (ret < 0) - goto done; - } - - ret = of_changeset_apply(&rcar_du_lvds_changeset); - -done: - if (ret < 0) - of_changeset_destroy(&rcar_du_lvds_changeset); -} - -struct lvds_of_data { - struct resource res; - struct of_phandle_args clkspec; - struct device_node *local; - struct device_node *remote; -}; - -static void __init rcar_du_of_lvds_patch(const struct of_device_id *of_ids) -{ - const struct rcar_du_device_info *info; - const struct of_device_id *match; - struct lvds_of_data lvds_data[2] = { }; - struct device_node *lvds_node; - struct device_node *soc_node; - struct device_node *du_node; - char compatible[22]; - const char *soc_name; - unsigned int i; - int ret; - - /* Get the DU node and exit if not present or disabled. */ - du_node = of_find_matching_node_and_match(NULL, of_ids, &match); - if (!du_node || !of_device_is_available(du_node)) { - of_node_put(du_node); - return; - } - - info = match->data; - soc_node = of_get_parent(du_node); - - if (WARN_ON(info->num_lvds > ARRAY_SIZE(lvds_data))) - goto done; - - /* - * Skip if the LVDS nodes already exists. - * - * The nodes are searched based on the compatible string, which we - * construct from the SoC name found in the DU compatible string. As a - * match has been found we know the compatible string matches the - * expected format and can thus skip some of the string manipulation - * normal safety checks. - */ - soc_name = strchr(match->compatible, '-') + 1; - sprintf(compatible, "renesas,%s-lvds", soc_name); - lvds_node = of_find_compatible_node(NULL, NULL, compatible); - if (lvds_node) { - of_node_put(lvds_node); - return; - } - - /* - * Parse the DU node and store the register specifier, the clock - * specifier and the local and remote endpoint of the LVDS link for - * later use. - */ - for (i = 0; i < info->num_lvds; ++i) { - struct lvds_of_data *lvds = &lvds_data[i]; - unsigned int port; - char name[7]; - int index; - - sprintf(name, "lvds.%u", i); - index = of_property_match_string(du_node, "clock-names", name); - if (index < 0) - continue; - - ret = of_parse_phandle_with_args(du_node, "clocks", - "#clock-cells", index, - &lvds->clkspec); - if (ret < 0) - continue; - - port = info->routes[RCAR_DU_OUTPUT_LVDS0 + i].port; - - lvds->local = of_graph_get_endpoint_by_regs(du_node, port, 0); - if (!lvds->local) - continue; - - lvds->remote = of_graph_get_remote_endpoint(lvds->local); - if (!lvds->remote) - continue; - - index = of_property_match_string(du_node, "reg-names", name); - if (index < 0) - continue; - - of_address_to_resource(du_node, index, &lvds->res); - } - - /* Parse and apply the overlay. This will resolve phandles. */ - ret = rcar_du_of_apply_overlay(rcar_du_lvds_overlays, - match->compatible); - if (ret < 0) - goto done; - - /* Patch the newly created LVDS encoder nodes. */ - for_each_child_of_node(soc_node, lvds_node) { - struct resource res; - - if (!of_device_is_compatible(lvds_node, compatible)) - continue; - - /* Locate the lvds_data entry based on the resource start. */ - ret = of_address_to_resource(lvds_node, 0, &res); - if (ret < 0) - continue; - - for (i = 0; i < ARRAY_SIZE(lvds_data); ++i) { - if (lvds_data[i].res.start == res.start) - break; - } - - if (i == ARRAY_SIZE(lvds_data)) - continue; - - /* Patch the LVDS encoder. */ - rcar_du_of_lvds_patch_one(lvds_node, &lvds_data[i].clkspec, - lvds_data[i].local, - lvds_data[i].remote); - } - -done: - for (i = 0; i < info->num_lvds; ++i) { - of_node_put(lvds_data[i].clkspec.np); - of_node_put(lvds_data[i].local); - of_node_put(lvds_data[i].remote); - } - - of_node_put(soc_node); - of_node_put(du_node); -} - -void __init rcar_du_of_init(const struct of_device_id *of_ids) -{ - rcar_du_of_lvds_patch(of_ids); -} diff --git a/drivers/gpu/drm/rcar-du/rcar_du_of.h b/drivers/gpu/drm/rcar-du/rcar_du_of.h deleted file mode 100644 index 8dd3fbe96650..000000000000 --- a/drivers/gpu/drm/rcar-du/rcar_du_of.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * rcar_du_of.h - Legacy DT bindings compatibility - * - * Copyright (C) 2018 Laurent Pinchart <laurent.pinchart@ideasonboard.com> - */ -#ifndef __RCAR_DU_OF_H__ -#define __RCAR_DU_OF_H__ - -#include <linux/init.h> - -struct of_device_id; - -#if IS_ENABLED(CONFIG_DRM_RCAR_LVDS) -void __init rcar_du_of_init(const struct of_device_id *of_ids); -#else -static inline void rcar_du_of_init(const struct of_device_id *of_ids) { } -#endif /* CONFIG_DRM_RCAR_LVDS */ - -#endif /* __RCAR_DU_OF_H__ */ diff --git a/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7790.dts b/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7790.dts deleted file mode 100644 index 8bee4e787a0a..000000000000 --- a/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7790.dts +++ /dev/null @@ -1,69 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * rcar_du_of_lvds_r8a7790.dts - Legacy LVDS DT bindings conversion for R8A7790 - * - * Copyright (C) 2018 Laurent Pinchart <laurent.pinchart@ideasonboard.com> - */ - -/dts-v1/; -/plugin/; - -&{/} { - #address-cells = <2>; - #size-cells = <2>; - - lvds@feb90000 { - compatible = "renesas,r8a7790-lvds"; - reg = <0 0xfeb90000 0 0x1c>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - lvds0_input: endpoint { - }; - }; - port@1 { - reg = <1>; - lvds0_out: endpoint { - }; - }; - }; - }; - - lvds@feb94000 { - compatible = "renesas,r8a7790-lvds"; - reg = <0 0xfeb94000 0 0x1c>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - lvds1_input: endpoint { - }; - }; - port@1 { - reg = <1>; - lvds1_out: endpoint { - }; - }; - }; - }; -}; - -&{/display@feb00000/ports} { - port@1 { - endpoint { - remote-endpoint = <&lvds0_input>; - }; - }; - port@2 { - endpoint { - remote-endpoint = <&lvds1_input>; - }; - }; -}; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7791.dts b/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7791.dts deleted file mode 100644 index 92c0509971ec..000000000000 --- a/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7791.dts +++ /dev/null @@ -1,43 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * rcar_du_of_lvds_r8a7791.dts - Legacy LVDS DT bindings conversion for R8A7791 - * - * Copyright (C) 2018 Laurent Pinchart <laurent.pinchart@ideasonboard.com> - */ - -/dts-v1/; -/plugin/; - -&{/} { - #address-cells = <2>; - #size-cells = <2>; - - lvds@feb90000 { - compatible = "renesas,r8a7791-lvds"; - reg = <0 0xfeb90000 0 0x1c>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - lvds0_input: endpoint { - }; - }; - port@1 { - reg = <1>; - lvds0_out: endpoint { - }; - }; - }; - }; -}; - -&{/display@feb00000/ports} { - port@1 { - endpoint { - remote-endpoint = <&lvds0_input>; - }; - }; -}; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7793.dts b/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7793.dts deleted file mode 100644 index c8b93f21de0f..000000000000 --- a/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7793.dts +++ /dev/null @@ -1,43 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * rcar_du_of_lvds_r8a7793.dts - Legacy LVDS DT bindings conversion for R8A7793 - * - * Copyright (C) 2018 Laurent Pinchart <laurent.pinchart@ideasonboard.com> - */ - -/dts-v1/; -/plugin/; - -&{/} { - #address-cells = <2>; - #size-cells = <2>; - - lvds@feb90000 { - compatible = "renesas,r8a7793-lvds"; - reg = <0 0xfeb90000 0 0x1c>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - lvds0_input: endpoint { - }; - }; - port@1 { - reg = <1>; - lvds0_out: endpoint { - }; - }; - }; - }; -}; - -&{/display@feb00000/ports} { - port@1 { - endpoint { - remote-endpoint = <&lvds0_input>; - }; - }; -}; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7795.dts b/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7795.dts deleted file mode 100644 index 16c2d03cb016..000000000000 --- a/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7795.dts +++ /dev/null @@ -1,43 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * rcar_du_of_lvds_r8a7795.dts - Legacy LVDS DT bindings conversion for R8A7795 - * - * Copyright (C) 2018 Laurent Pinchart <laurent.pinchart@ideasonboard.com> - */ - -/dts-v1/; -/plugin/; - -&{/soc} { - #address-cells = <2>; - #size-cells = <2>; - - lvds@feb90000 { - compatible = "renesas,r8a7795-lvds"; - reg = <0 0xfeb90000 0 0x14>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - lvds0_input: endpoint { - }; - }; - port@1 { - reg = <1>; - lvds0_out: endpoint { - }; - }; - }; - }; -}; - -&{/soc/display@feb00000/ports} { - port@3 { - endpoint { - remote-endpoint = <&lvds0_input>; - }; - }; -}; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7796.dts b/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7796.dts deleted file mode 100644 index 680e923ac036..000000000000 --- a/drivers/gpu/drm/rcar-du/rcar_du_of_lvds_r8a7796.dts +++ /dev/null @@ -1,43 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * rcar_du_of_lvds_r8a7796.dts - Legacy LVDS DT bindings conversion for R8A7796 - * - * Copyright (C) 2018 Laurent Pinchart <laurent.pinchart@ideasonboard.com> - */ - -/dts-v1/; -/plugin/; - -&{/soc} { - #address-cells = <2>; - #size-cells = <2>; - - lvds@feb90000 { - compatible = "renesas,r8a7796-lvds"; - reg = <0 0xfeb90000 0 0x14>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - lvds0_input: endpoint { - }; - }; - port@1 { - reg = <1>; - lvds0_out: endpoint { - }; - }; - }; - }; -}; - -&{/soc/display@feb00000/ports} { - port@3 { - endpoint { - remote-endpoint = <&lvds0_input>; - }; - }; -}; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.c b/drivers/gpu/drm/rcar-du/rcar_du_plane.c index 862197be1e01..5c1c7bb04f3f 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_plane.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.c @@ -549,8 +549,10 @@ void __rcar_du_plane_setup(struct rcar_du_group *rgrp, rcar_du_plane_setup_format(rgrp, (state->hwindex + 1) % 8, state); - if (rcdu->info->gen < 3) - rcar_du_plane_setup_scanout(rgrp, state); + if (rcdu->info->gen >= 3) + return; + + rcar_du_plane_setup_scanout(rgrp, state); if (state->source == RCAR_DU_PLANE_VSPD1) { unsigned int vspd1_sink = rgrp->index ? 2 : 0; @@ -558,6 +560,12 @@ void __rcar_du_plane_setup(struct rcar_du_group *rgrp, if (rcdu->vspd1_sink != vspd1_sink) { rcdu->vspd1_sink = vspd1_sink; rcar_du_set_dpad0_vsp1_routing(rcdu); + + /* + * Changes to the VSP1 sink take effect on DRES and thus + * need a restart of the group. + */ + rgrp->need_restart = true; } } } @@ -696,7 +704,6 @@ static void rcar_du_plane_reset(struct drm_plane *plane) state->hwindex = -1; state->source = RCAR_DU_PLANE_MEMORY; state->colorkey = RCAR_DU_COLORKEY_NONE; - state->state.zpos = plane->type == DRM_PLANE_TYPE_PRIMARY ? 0 : 1; } static int rcar_du_plane_atomic_set_property(struct drm_plane *plane, diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c index b7fc5b069cbc..8eb9b2b097ae 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c @@ -84,15 +84,6 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc) __rcar_du_plane_setup(crtc->group, &state); - /* - * Ensure that the plane source configuration takes effect by requesting - * a restart of the group. See rcar_du_plane_atomic_update() for a more - * detailed explanation. - * - * TODO: Check whether this is still needed on Gen3. - */ - crtc->group->need_restart = true; - vsp1_du_setup_lif(crtc->vsp->vsp, crtc->vsp_pipe, &cfg); } @@ -362,7 +353,6 @@ static void rcar_du_vsp_plane_reset(struct drm_plane *plane) return; __drm_atomic_helper_plane_reset(plane, &state->state); - state->state.zpos = plane->type == DRM_PLANE_TYPE_PRIMARY ? 0 : 1; } static const struct drm_plane_funcs rcar_du_vsp_plane_funcs = { diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c index 72a272cfc11e..8dbfbbd3cad1 100644 --- a/drivers/gpu/drm/rcar-du/rcar_lvds.c +++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c @@ -901,6 +901,7 @@ static const struct of_device_id rcar_lvds_of_table[] = { { .compatible = "renesas,r8a7793-lvds", .data = &rcar_lvds_gen2_info }, { .compatible = "renesas,r8a7795-lvds", .data = &rcar_lvds_gen3_info }, { .compatible = "renesas,r8a7796-lvds", .data = &rcar_lvds_gen3_info }, + { .compatible = "renesas,r8a77961-lvds", .data = &rcar_lvds_gen3_info }, { .compatible = "renesas,r8a77965-lvds", .data = &rcar_lvds_gen3_info }, { .compatible = "renesas,r8a77970-lvds", .data = &rcar_lvds_r8a77970_info }, { .compatible = "renesas,r8a77980-lvds", .data = &rcar_lvds_gen3_info }, diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c index 4740cc14beb8..d3e6c93739bf 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c @@ -586,6 +586,13 @@ static bool cdn_dp_check_link_status(struct cdn_dp_device *dp) return drm_dp_channel_eq_ok(link_status, min(port->lanes, sink_lanes)); } +static void cdn_dp_audio_handle_plugged_change(struct cdn_dp_device *dp, + bool plugged) +{ + if (dp->codec_dev) + dp->plugged_cb(dp->codec_dev, plugged); +} + static void cdn_dp_encoder_enable(struct drm_encoder *encoder) { struct cdn_dp_device *dp = encoder_to_dp(encoder); @@ -641,6 +648,9 @@ static void cdn_dp_encoder_enable(struct drm_encoder *encoder) DRM_DEV_ERROR(dp->dev, "Failed to valid video %d\n", ret); goto out; } + + cdn_dp_audio_handle_plugged_change(dp, true); + out: mutex_unlock(&dp->lock); } @@ -651,6 +661,8 @@ static void cdn_dp_encoder_disable(struct drm_encoder *encoder) int ret; mutex_lock(&dp->lock); + cdn_dp_audio_handle_plugged_change(dp, false); + if (dp->active) { ret = cdn_dp_disable(dp); if (ret) { @@ -846,11 +858,27 @@ static int cdn_dp_audio_get_eld(struct device *dev, void *data, return 0; } +static int cdn_dp_audio_hook_plugged_cb(struct device *dev, void *data, + hdmi_codec_plugged_cb fn, + struct device *codec_dev) +{ + struct cdn_dp_device *dp = dev_get_drvdata(dev); + + mutex_lock(&dp->lock); + dp->plugged_cb = fn; + dp->codec_dev = codec_dev; + cdn_dp_audio_handle_plugged_change(dp, dp->connected); + mutex_unlock(&dp->lock); + + return 0; +} + static const struct hdmi_codec_ops audio_codec_ops = { .hw_params = cdn_dp_audio_hw_params, .audio_shutdown = cdn_dp_audio_shutdown, .mute_stream = cdn_dp_audio_mute_stream, .get_eld = cdn_dp_audio_get_eld, + .hook_plugged_cb = cdn_dp_audio_hook_plugged_cb, .no_capture_mute = 1, }; diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.h b/drivers/gpu/drm/rockchip/cdn-dp-core.h index 0d044146f4e9..6d0c5032ef3a 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.h +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.h @@ -10,6 +10,7 @@ #include <drm/dp/drm_dp_helper.h> #include <drm/drm_panel.h> #include <drm/drm_probe_helper.h> +#include <sound/hdmi-codec.h> #include "rockchip_drm_drv.h" @@ -101,5 +102,8 @@ struct cdn_dp_device { u8 dpcd[DP_RECEIVER_CAP_SIZE]; bool sink_has_audio; + + hdmi_codec_plugged_cb plugged_cb; + struct device *codec_dev; }; #endif /* _CDN_DP_CORE_H */ diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index ac190e2b1f7a..4eaeb430c83a 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -290,11 +290,6 @@ int rockchip_drm_endpoint_is_subdriver(struct device_node *ep) return false; } -static int compare_dev(struct device *dev, void *data) -{ - return dev == (struct device *)data; -} - static void rockchip_drm_match_remove(struct device *dev) { struct device_link *link; @@ -321,7 +316,7 @@ static struct component_match *rockchip_drm_match_add(struct device *dev) break; device_link_add(dev, d, DL_FLAG_STATELESS); - component_match_add(dev, &match, compare_dev, d); + component_match_add(dev, &match, component_compare_dev, d); } while (true); } diff --git a/drivers/gpu/drm/selftests/test-drm_plane_helper.c b/drivers/gpu/drm/selftests/test-drm_plane_helper.c index ceebeede55ea..b61273e9c403 100644 --- a/drivers/gpu/drm/selftests/test-drm_plane_helper.c +++ b/drivers/gpu/drm/selftests/test-drm_plane_helper.c @@ -77,7 +77,7 @@ int igt_check_plane_state(void *ignored) { int ret; - const struct drm_crtc_state crtc_state = { + static const struct drm_crtc_state crtc_state = { .crtc = ZERO_SIZE_PTR, .enable = true, .active = true, @@ -87,14 +87,14 @@ int igt_check_plane_state(void *ignored) DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) }, }; - struct drm_plane plane = { + static struct drm_plane plane = { .dev = NULL }; - struct drm_framebuffer fb = { + static struct drm_framebuffer fb = { .width = 2048, .height = 2048 }; - struct drm_plane_state plane_state = { + static struct drm_plane_state plane_state = { .plane = &plane, .crtc = ZERO_SIZE_PTR, .fb = &fb, diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c index 92c1902f53e4..ce4dc20412e0 100644 --- a/drivers/gpu/drm/solomon/ssd130x.c +++ b/drivers/gpu/drm/solomon/ssd130x.c @@ -579,7 +579,7 @@ static const struct drm_simple_display_pipe_funcs ssd130x_pipe_funcs = { static int ssd130x_connector_get_modes(struct drm_connector *connector) { struct ssd130x_device *ssd130x = drm_to_ssd130x(connector->dev); - struct drm_display_mode *mode = &ssd130x->mode; + struct drm_display_mode *mode; struct device *dev = ssd130x->dev; mode = drm_mode_duplicate(connector->dev, &ssd130x->mode); diff --git a/drivers/gpu/drm/sprd/sprd_drm.c b/drivers/gpu/drm/sprd/sprd_drm.c index a60ecdd67d98..b8fc1c6a0cb8 100644 --- a/drivers/gpu/drm/sprd/sprd_drm.c +++ b/drivers/gpu/drm/sprd/sprd_drm.c @@ -133,14 +133,9 @@ static const struct component_master_ops drm_component_ops = { .unbind = sprd_drm_unbind, }; -static int compare_of(struct device *dev, void *data) -{ - return dev->of_node == data; -} - static int sprd_drm_probe(struct platform_device *pdev) { - return drm_of_component_probe(&pdev->dev, compare_of, &drm_component_ops); + return drm_of_component_probe(&pdev->dev, component_compare_of, &drm_component_ops); } static int sprd_drm_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/sti/sti_cursor.c b/drivers/gpu/drm/sti/sti_cursor.c index 1d6051b4f6fe..414c9973aa6d 100644 --- a/drivers/gpu/drm/sti/sti_cursor.c +++ b/drivers/gpu/drm/sti/sti_cursor.c @@ -351,7 +351,7 @@ static const struct drm_plane_funcs sti_cursor_plane_helpers_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, .destroy = drm_plane_cleanup, - .reset = sti_plane_reset, + .reset = drm_atomic_helper_plane_reset, .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, .late_register = sti_cursor_late_register, diff --git a/drivers/gpu/drm/sti/sti_drv.c b/drivers/gpu/drm/sti/sti_drv.c index 860b2230aa08..d858209cf8de 100644 --- a/drivers/gpu/drm/sti/sti_drv.c +++ b/drivers/gpu/drm/sti/sti_drv.c @@ -144,11 +144,6 @@ static const struct drm_driver sti_driver = { .minor = DRIVER_MINOR, }; -static int compare_of(struct device *dev, void *data) -{ - return dev->of_node == data; -} - static int sti_init(struct drm_device *ddev) { struct sti_private *private; @@ -244,7 +239,7 @@ static int sti_platform_probe(struct platform_device *pdev) child_np = of_get_next_available_child(node, NULL); while (child_np) { - drm_of_component_match_add(dev, &match, compare_of, + drm_of_component_match_add(dev, &match, component_compare_of, child_np); child_np = of_get_next_available_child(node, child_np); } diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c index d1a35d97bc45..3db3768a3241 100644 --- a/drivers/gpu/drm/sti/sti_gdp.c +++ b/drivers/gpu/drm/sti/sti_gdp.c @@ -905,7 +905,7 @@ static const struct drm_plane_funcs sti_gdp_plane_helpers_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, .destroy = drm_plane_cleanup, - .reset = sti_plane_reset, + .reset = drm_atomic_helper_plane_reset, .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, .late_register = sti_gdp_late_register, diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c index 3c61ba8b43e0..2201a50353eb 100644 --- a/drivers/gpu/drm/sti/sti_hqvdp.c +++ b/drivers/gpu/drm/sti/sti_hqvdp.c @@ -1283,7 +1283,7 @@ static const struct drm_plane_funcs sti_hqvdp_plane_helpers_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, .destroy = drm_plane_cleanup, - .reset = sti_plane_reset, + .reset = drm_atomic_helper_plane_reset, .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, .late_register = sti_hqvdp_late_register, diff --git a/drivers/gpu/drm/sti/sti_plane.c b/drivers/gpu/drm/sti/sti_plane.c index 3da4a46df2f2..173409cdb99e 100644 --- a/drivers/gpu/drm/sti/sti_plane.c +++ b/drivers/gpu/drm/sti/sti_plane.c @@ -112,12 +112,6 @@ static int sti_plane_get_default_zpos(enum drm_plane_type type) return 0; } -void sti_plane_reset(struct drm_plane *plane) -{ - drm_atomic_helper_plane_reset(plane); - plane->state->zpos = sti_plane_get_default_zpos(plane->type); -} - static void sti_plane_attach_zorder_property(struct drm_plane *drm_plane, enum drm_plane_type type) { diff --git a/drivers/gpu/drm/sti/sti_plane.h b/drivers/gpu/drm/sti/sti_plane.h index 065ffffbfb4a..8e33e629d9b0 100644 --- a/drivers/gpu/drm/sti/sti_plane.h +++ b/drivers/gpu/drm/sti/sti_plane.h @@ -81,5 +81,4 @@ void sti_plane_update_fps(struct sti_plane *plane, void sti_plane_init_property(struct sti_plane *plane, enum drm_plane_type type); -void sti_plane_reset(struct drm_plane *plane); #endif diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index 5eeb32c9c9ce..17cc050207f4 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -77,6 +77,7 @@ #define LTDC_CPSR 0x0044 /* Current Position Status */ #define LTDC_CDSR 0x0048 /* Current Display Status */ #define LTDC_EDCR 0x0060 /* External Display Control */ +#define LTDC_CCRCR 0x007C /* Computed CRC value */ #define LTDC_FUT 0x0090 /* Fifo underrun Threshold */ /* Layer register offsets */ @@ -121,6 +122,7 @@ #define GCR_LTDCEN BIT(0) /* LTDC ENable */ #define GCR_DEN BIT(16) /* Dither ENable */ +#define GCR_CRCEN BIT(19) /* CRC ENable */ #define GCR_PCPOL BIT(28) /* Pixel Clock POLarity-Inverted */ #define GCR_DEPOL BIT(29) /* Data Enable POLarity-High */ #define GCR_VSPOL BIT(30) /* Vertical Synchro POLarity-High */ @@ -227,6 +229,13 @@ #define NB_PF 8 /* Max nb of HW pixel format */ +/* + * Skip the first value and the second in case CRC was enabled during + * the thread irq. This is to be sure CRC value is relevant for the + * frame. + */ +#define CRC_SKIP_FRAMES 2 + enum ltdc_pix_fmt { PF_NONE, /* RGB formats */ @@ -624,7 +633,8 @@ static inline void ltdc_set_ycbcr_config(struct drm_plane *plane, u32 drm_pix_fm break; default: /* RGB or not a YCbCr supported format */ - break; + DRM_ERROR("Unsupported pixel format: %u\n", drm_pix_fmt); + return; } /* Enable limited range */ @@ -664,6 +674,26 @@ static inline void ltdc_set_ycbcr_coeffs(struct drm_plane *plane) ltdc_ycbcr2rgb_coeffs[enc][ran][1]); } +static inline void ltdc_irq_crc_handle(struct ltdc_device *ldev, + struct drm_crtc *crtc) +{ + u32 crc; + int ret; + + if (ldev->crc_skip_count < CRC_SKIP_FRAMES) { + ldev->crc_skip_count++; + return; + } + + /* Get the CRC of the frame */ + ret = regmap_read(ldev->regmap, LTDC_CCRCR, &crc); + if (ret) + return; + + /* Report to DRM the CRC (hw dependent feature) */ + drm_crtc_add_crc_entry(crtc, true, drm_crtc_accurate_vblank_count(crtc), &crc); +} + static irqreturn_t ltdc_irq_thread(int irq, void *arg) { struct drm_device *ddev = arg; @@ -671,9 +701,14 @@ static irqreturn_t ltdc_irq_thread(int irq, void *arg) struct drm_crtc *crtc = drm_crtc_from_index(ddev, 0); /* Line IRQ : trigger the vblank event */ - if (ldev->irq_status & ISR_LIF) + if (ldev->irq_status & ISR_LIF) { drm_crtc_handle_vblank(crtc); + /* Early return if CRC is not active */ + if (ldev->crc_active) + ltdc_irq_crc_handle(ldev, crtc); + } + /* Save FIFO Underrun & Transfer Error status */ mutex_lock(&ldev->err_lock); if (ldev->irq_status & ISR_FUIF) @@ -1079,6 +1114,48 @@ static void ltdc_crtc_disable_vblank(struct drm_crtc *crtc) regmap_clear_bits(ldev->regmap, LTDC_IER, IER_LIE); } +static int ltdc_crtc_set_crc_source(struct drm_crtc *crtc, const char *source) +{ + struct ltdc_device *ldev = crtc_to_ltdc(crtc); + int ret; + + DRM_DEBUG_DRIVER("\n"); + + if (!crtc) + return -ENODEV; + + if (source && strcmp(source, "auto") == 0) { + ldev->crc_active = true; + ret = regmap_set_bits(ldev->regmap, LTDC_GCR, GCR_CRCEN); + } else if (!source) { + ldev->crc_active = false; + ret = regmap_clear_bits(ldev->regmap, LTDC_GCR, GCR_CRCEN); + } else { + ret = -EINVAL; + } + + ldev->crc_skip_count = 0; + return ret; +} + +static int ltdc_crtc_verify_crc_source(struct drm_crtc *crtc, + const char *source, size_t *values_cnt) +{ + DRM_DEBUG_DRIVER("\n"); + + if (!crtc) + return -ENODEV; + + if (source && strcmp(source, "auto") != 0) { + DRM_DEBUG_DRIVER("Unknown CRC source %s for %s\n", + source, crtc->name); + return -EINVAL; + } + + *values_cnt = 1; + return 0; +} + static const struct drm_crtc_funcs ltdc_crtc_funcs = { .destroy = drm_crtc_cleanup, .set_config = drm_atomic_helper_set_config, @@ -1091,6 +1168,20 @@ static const struct drm_crtc_funcs ltdc_crtc_funcs = { .get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp, }; +static const struct drm_crtc_funcs ltdc_crtc_with_crc_support_funcs = { + .destroy = drm_crtc_cleanup, + .set_config = drm_atomic_helper_set_config, + .page_flip = drm_atomic_helper_page_flip, + .reset = drm_atomic_helper_crtc_reset, + .atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, + .enable_vblank = ltdc_crtc_enable_vblank, + .disable_vblank = ltdc_crtc_disable_vblank, + .get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp, + .set_crc_source = ltdc_crtc_set_crc_source, + .verify_crc_source = ltdc_crtc_verify_crc_source, +}; + /* * DRM_PLANE */ @@ -1478,8 +1569,13 @@ static int ltdc_crtc_init(struct drm_device *ddev, struct drm_crtc *crtc) drm_plane_create_zpos_immutable_property(primary, 0); - ret = drm_crtc_init_with_planes(ddev, crtc, primary, NULL, - <dc_crtc_funcs, NULL); + /* Init CRTC according to its hardware features */ + if (ldev->caps.crc) + ret = drm_crtc_init_with_planes(ddev, crtc, primary, NULL, + <dc_crtc_with_crc_support_funcs, NULL); + else + ret = drm_crtc_init_with_planes(ddev, crtc, primary, NULL, + <dc_crtc_funcs, NULL); if (ret) { DRM_ERROR("Can not initialize CRTC\n"); goto cleanup; @@ -1629,6 +1725,7 @@ static int ltdc_get_caps(struct drm_device *ddev) ldev->caps.ycbcr_input = false; ldev->caps.ycbcr_output = false; ldev->caps.plane_reg_shadow = false; + ldev->caps.crc = false; break; case HWVER_20101: ldev->caps.layer_ofs = LAY_OFS_0; @@ -1643,6 +1740,7 @@ static int ltdc_get_caps(struct drm_device *ddev) ldev->caps.ycbcr_input = false; ldev->caps.ycbcr_output = false; ldev->caps.plane_reg_shadow = false; + ldev->caps.crc = false; break; case HWVER_40100: ldev->caps.layer_ofs = LAY_OFS_1; @@ -1657,6 +1755,7 @@ static int ltdc_get_caps(struct drm_device *ddev) ldev->caps.ycbcr_input = true; ldev->caps.ycbcr_output = true; ldev->caps.plane_reg_shadow = true; + ldev->caps.crc = true; break; default: return -ENODEV; diff --git a/drivers/gpu/drm/stm/ltdc.h b/drivers/gpu/drm/stm/ltdc.h index 6968d1ca5149..59fc5d1bbbab 100644 --- a/drivers/gpu/drm/stm/ltdc.h +++ b/drivers/gpu/drm/stm/ltdc.h @@ -27,6 +27,7 @@ struct ltdc_caps { bool ycbcr_input; /* ycbcr input converter supported */ bool ycbcr_output; /* ycbcr output converter supported */ bool plane_reg_shadow; /* plane shadow registers ability */ + bool crc; /* cyclic redundancy check supported */ }; #define LTDC_MAX_LAYER 4 @@ -46,6 +47,8 @@ struct ltdc_device { u32 irq_status; struct fps_info plane_fpsi[LTDC_MAX_LAYER]; struct drm_atomic_state *suspend_state; + int crc_skip_count; + bool crc_active; }; int ltdc_load(struct drm_device *ddev); diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index a3fd441dd9ad..6a9ba8a77c77 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -202,15 +202,6 @@ static bool sun4i_drv_node_is_tcon_top(struct device_node *node) !!of_match_node(sun8i_tcon_top_of_table, node); } -static int compare_of(struct device *dev, void *data) -{ - DRM_DEBUG_DRIVER("Comparing of node %pOF with %pOF\n", - dev->of_node, - data); - - return dev->of_node == data; -} - /* * The encoder drivers use drm_of_find_possible_crtcs to get upstream * crtcs from the device tree using of_graph. For the results to be @@ -330,7 +321,7 @@ static int sun4i_drv_add_endpoints(struct device *dev, of_device_is_available(node))) { /* Add current component */ DRM_DEBUG_DRIVER("Adding component %pOF\n", node); - drm_of_component_match_add(dev, match, compare_of, node); + drm_of_component_match_add(dev, match, component_compare_of, node); count++; } diff --git a/drivers/gpu/drm/sun4i/sun4i_layer.c b/drivers/gpu/drm/sun4i/sun4i_layer.c index 929e95f86b5b..6d43080791a0 100644 --- a/drivers/gpu/drm/sun4i/sun4i_layer.c +++ b/drivers/gpu/drm/sun4i/sun4i_layer.c @@ -18,7 +18,6 @@ static void sun4i_backend_layer_reset(struct drm_plane *plane) { - struct sun4i_layer *layer = plane_to_sun4i_layer(plane); struct sun4i_layer_state *state; if (plane->state) { @@ -31,10 +30,8 @@ static void sun4i_backend_layer_reset(struct drm_plane *plane) } state = kzalloc(sizeof(*state), GFP_KERNEL); - if (state) { + if (state) __drm_atomic_helper_plane_reset(plane, &state->state); - plane->state->zpos = layer->id; - } } static struct drm_plane_state * @@ -192,7 +189,8 @@ static const uint64_t sun4i_layer_modifiers[] = { static struct sun4i_layer *sun4i_layer_init_one(struct drm_device *drm, struct sun4i_backend *backend, - enum drm_plane_type type) + enum drm_plane_type type, + unsigned int id) { const uint64_t *modifiers = sun4i_layer_modifiers; const uint32_t *formats = sun4i_layer_formats; @@ -204,6 +202,7 @@ static struct sun4i_layer *sun4i_layer_init_one(struct drm_device *drm, if (!layer) return ERR_PTR(-ENOMEM); + layer->id = id; layer->backend = backend; if (IS_ERR_OR_NULL(backend->frontend)) { @@ -226,8 +225,8 @@ static struct sun4i_layer *sun4i_layer_init_one(struct drm_device *drm, &sun4i_backend_layer_helper_funcs); drm_plane_create_alpha_property(&layer->plane); - drm_plane_create_zpos_property(&layer->plane, 0, 0, - SUN4I_BACKEND_NUM_LAYERS - 1); + drm_plane_create_zpos_property(&layer->plane, layer->id, + 0, SUN4I_BACKEND_NUM_LAYERS - 1); return layer; } @@ -249,14 +248,13 @@ struct drm_plane **sun4i_layers_init(struct drm_device *drm, enum drm_plane_type type = i ? DRM_PLANE_TYPE_OVERLAY : DRM_PLANE_TYPE_PRIMARY; struct sun4i_layer *layer; - layer = sun4i_layer_init_one(drm, backend, type); + layer = sun4i_layer_init_one(drm, backend, type, i); if (IS_ERR(layer)) { dev_err(drm->dev, "Couldn't initialize %s plane\n", i ? "overlay" : "primary"); return ERR_CAST(layer); } - layer->id = i; planes[i] = &layer->plane; } diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.h b/drivers/gpu/drm/sun4i/sun8i_mixer.h index 145833a9d82d..5b3fbee18671 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.h +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.h @@ -111,10 +111,10 @@ /* format 13 is semi-planar YUV411 VUVU */ #define SUN8I_MIXER_FBFMT_YUV411 14 /* format 15 doesn't exist */ -/* format 16 is P010 YVU */ -#define SUN8I_MIXER_FBFMT_P010_YUV 17 -/* format 18 is P210 YVU */ -#define SUN8I_MIXER_FBFMT_P210_YUV 19 +#define SUN8I_MIXER_FBFMT_P010_YUV 16 +/* format 17 is P010 YVU */ +#define SUN8I_MIXER_FBFMT_P210_YUV 18 +/* format 19 is P210 YVU */ /* format 20 is packed YVU444 10-bit */ /* format 21 is packed YUV444 10-bit */ diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index eb70eee8992a..c6951cf5d2ca 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -345,18 +345,19 @@ static void tegra_dc_setup_window(struct tegra_plane *plane, { unsigned h_offset, v_offset, h_size, v_size, h_dda, v_dda, bpp; struct tegra_dc *dc = plane->dc; - bool yuv, planar; + unsigned int planes; u32 value; + bool yuv; /* * For YUV planar modes, the number of bytes per pixel takes into * account only the luma component and therefore is 1. */ - yuv = tegra_plane_format_is_yuv(window->format, &planar, NULL); + yuv = tegra_plane_format_is_yuv(window->format, &planes, NULL); if (!yuv) bpp = window->bits_per_pixel / 8; else - bpp = planar ? 1 : 2; + bpp = (planes > 1) ? 1 : 2; tegra_plane_writel(plane, window->format, DC_WIN_COLOR_DEPTH); tegra_plane_writel(plane, window->swap, DC_WIN_BYTE_SWAP); @@ -385,7 +386,7 @@ static void tegra_dc_setup_window(struct tegra_plane *plane, * For DDA computations the number of bytes per pixel for YUV planar * modes needs to take into account all Y, U and V components. */ - if (yuv && planar) + if (yuv && planes > 1) bpp = 2; h_dda = compute_dda_inc(window->src.w, window->dst.w, false, bpp); @@ -405,9 +406,12 @@ static void tegra_dc_setup_window(struct tegra_plane *plane, tegra_plane_writel(plane, window->base[0], DC_WINBUF_START_ADDR); - if (yuv && planar) { + if (yuv && planes > 1) { tegra_plane_writel(plane, window->base[1], DC_WINBUF_START_ADDR_U); - tegra_plane_writel(plane, window->base[2], DC_WINBUF_START_ADDR_V); + + if (planes > 2) + tegra_plane_writel(plane, window->base[2], DC_WINBUF_START_ADDR_V); + value = window->stride[1] << 16 | window->stride[0]; tegra_plane_writel(plane, value, DC_WIN_LINE_STRIDE); } else { @@ -1193,6 +1197,13 @@ static const u32 tegra114_overlay_formats[] = { DRM_FORMAT_YUYV, DRM_FORMAT_YUV420, DRM_FORMAT_YUV422, + /* semi-planar formats */ + DRM_FORMAT_NV12, + DRM_FORMAT_NV21, + DRM_FORMAT_NV16, + DRM_FORMAT_NV61, + DRM_FORMAT_NV24, + DRM_FORMAT_NV42, }; static const u32 tegra124_overlay_formats[] = { @@ -1221,8 +1232,18 @@ static const u32 tegra124_overlay_formats[] = { /* planar formats */ DRM_FORMAT_UYVY, DRM_FORMAT_YUYV, - DRM_FORMAT_YUV420, - DRM_FORMAT_YUV422, + DRM_FORMAT_YVYU, + DRM_FORMAT_VYUY, + DRM_FORMAT_YUV420, /* YU12 */ + DRM_FORMAT_YUV422, /* YU16 */ + DRM_FORMAT_YUV444, /* YU24 */ + /* semi-planar formats */ + DRM_FORMAT_NV12, + DRM_FORMAT_NV21, + DRM_FORMAT_NV16, + DRM_FORMAT_NV61, + DRM_FORMAT_NV24, + DRM_FORMAT_NV42, }; static struct drm_plane *tegra_dc_overlay_plane_create(struct drm_device *drm, @@ -3211,16 +3232,9 @@ static int tegra_dc_probe(struct platform_device *pdev) return -ENXIO; err = tegra_dc_rgb_probe(dc); - if (err < 0 && err != -ENODEV) { - const char *level = KERN_ERR; - - if (err == -EPROBE_DEFER) - level = KERN_DEBUG; - - dev_printk(level, dc->dev, "failed to probe RGB output: %d\n", - err); - return err; - } + if (err < 0 && err != -ENODEV) + return dev_err_probe(&pdev->dev, err, + "failed to probe RGB output\n"); platform_set_drvdata(pdev, dc); pm_runtime_enable(&pdev->dev); diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h index 3f91a10ea6c7..f902794d42cc 100644 --- a/drivers/gpu/drm/tegra/dc.h +++ b/drivers/gpu/drm/tegra/dc.h @@ -637,6 +637,13 @@ int tegra_dc_rgb_exit(struct tegra_dc *dc); #define WIN_COLOR_DEPTH_A8B8G8R8 36 #define WIN_COLOR_DEPTH_B8G8R8X8 37 #define WIN_COLOR_DEPTH_R8G8B8X8 38 +#define WIN_COLOR_DEPTH_YCbCr444P 41 +#define WIN_COLOR_DEPTH_YCrCb420SP 42 +#define WIN_COLOR_DEPTH_YCbCr420SP 43 +#define WIN_COLOR_DEPTH_YCrCb422SP 44 +#define WIN_COLOR_DEPTH_YCbCr422SP 45 +#define WIN_COLOR_DEPTH_YCrCb444SP 48 +#define WIN_COLOR_DEPTH_YCbCr444SP 49 #define WIN_COLOR_DEPTH_X8B8G8R8 65 #define WIN_COLOR_DEPTH_X8R8G8B8 66 diff --git a/drivers/gpu/drm/tegra/dp.c b/drivers/gpu/drm/tegra/dp.c index e4369e5b2943..7295975e5733 100644 --- a/drivers/gpu/drm/tegra/dp.c +++ b/drivers/gpu/drm/tegra/dp.c @@ -549,6 +549,15 @@ static void drm_dp_link_get_adjustments(struct drm_dp_link *link, { struct drm_dp_link_train_set *adjust = &link->train.adjust; unsigned int i; + u8 post_cursor; + int err; + + err = drm_dp_dpcd_read(link->aux, DP_ADJUST_REQUEST_POST_CURSOR2, + &post_cursor, sizeof(post_cursor)); + if (err < 0) { + DRM_ERROR("failed to read post_cursor2: %d\n", err); + post_cursor = 0; + } for (i = 0; i < link->lanes; i++) { adjust->voltage_swing[i] = @@ -560,7 +569,7 @@ static void drm_dp_link_get_adjustments(struct drm_dp_link *link, DP_TRAIN_PRE_EMPHASIS_SHIFT; adjust->post_cursor[i] = - drm_dp_get_adjust_request_post_cursor(status, i); + (post_cursor >> (i << 1)) & 0x3; } } diff --git a/drivers/gpu/drm/tegra/dpaux.c b/drivers/gpu/drm/tegra/dpaux.c index 5847dcad2478..20e1dd6b3bf0 100644 --- a/drivers/gpu/drm/tegra/dpaux.c +++ b/drivers/gpu/drm/tegra/dpaux.c @@ -280,7 +280,6 @@ static void tegra_dpaux_hotplug(struct work_struct *work) static irqreturn_t tegra_dpaux_irq(int irq, void *data) { struct tegra_dpaux *dpaux = data; - irqreturn_t ret = IRQ_HANDLED; u32 value; /* clear interrupts */ @@ -297,7 +296,7 @@ static irqreturn_t tegra_dpaux_irq(int irq, void *data) if (value & DPAUX_INTR_AUX_DONE) complete(&dpaux->complete); - return ret; + return IRQ_HANDLED; } enum tegra_dpaux_functions { diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index f46d377f0c30..de1333dc0d86 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -1538,8 +1538,10 @@ static int tegra_dsi_ganged_probe(struct tegra_dsi *dsi) dsi->slave = platform_get_drvdata(gangster); of_node_put(np); - if (!dsi->slave) + if (!dsi->slave) { + put_device(&gangster->dev); return -EPROBE_DEFER; + } dsi->slave->master = dsi; } diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c index 8845af5d325f..bf240767dad9 100644 --- a/drivers/gpu/drm/tegra/hdmi.c +++ b/drivers/gpu/drm/tegra/hdmi.c @@ -1775,7 +1775,6 @@ static irqreturn_t tegra_hdmi_irq(int irq, void *data) static int tegra_hdmi_probe(struct platform_device *pdev) { - const char *level = KERN_ERR; struct tegra_hdmi *hdmi; struct resource *regs; int err; @@ -1817,36 +1816,21 @@ static int tegra_hdmi_probe(struct platform_device *pdev) hdmi->hdmi = devm_regulator_get(&pdev->dev, "hdmi"); err = PTR_ERR_OR_ZERO(hdmi->hdmi); - if (err) { - if (err == -EPROBE_DEFER) - level = KERN_DEBUG; - - dev_printk(level, &pdev->dev, - "failed to get HDMI regulator: %d\n", err); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, + "failed to get HDMI regulator\n"); hdmi->pll = devm_regulator_get(&pdev->dev, "pll"); err = PTR_ERR_OR_ZERO(hdmi->pll); - if (err) { - if (err == -EPROBE_DEFER) - level = KERN_DEBUG; - - dev_printk(level, &pdev->dev, - "failed to get PLL regulator: %d\n", err); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, + "failed to get PLL regulator\n"); hdmi->vdd = devm_regulator_get(&pdev->dev, "vdd"); err = PTR_ERR_OR_ZERO(hdmi->vdd); - if (err) { - if (err == -EPROBE_DEFER) - level = KERN_DEBUG; - - dev_printk(level, &pdev->dev, - "failed to get VDD regulator: %d\n", err); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, + "failed to get VDD regulator\n"); hdmi->output.dev = &pdev->dev; diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c index b910155f80c4..b8d3174c04c9 100644 --- a/drivers/gpu/drm/tegra/hub.c +++ b/drivers/gpu/drm/tegra/hub.c @@ -540,8 +540,8 @@ static void tegra_shared_plane_atomic_update(struct drm_plane *plane, struct tegra_plane *p = to_tegra_plane(plane); u32 value, min_width, bypass = 0; dma_addr_t base, addr_flag = 0; - unsigned int bpc; - bool yuv, planar; + unsigned int bpc, planes; + bool yuv; int err; /* rien ne va plus */ @@ -559,7 +559,7 @@ static void tegra_shared_plane_atomic_update(struct drm_plane *plane, return; } - yuv = tegra_plane_format_is_yuv(tegra_plane_state->format, &planar, &bpc); + yuv = tegra_plane_format_is_yuv(tegra_plane_state->format, &planes, &bpc); tegra_dc_assign_shared_plane(dc, p); @@ -660,20 +660,26 @@ static void tegra_shared_plane_atomic_update(struct drm_plane *plane, value = PITCH(fb->pitches[0]); tegra_plane_writel(p, value, DC_WIN_PLANAR_STORAGE); - if (yuv && planar) { + if (yuv && planes > 1) { base = tegra_plane_state->iova[1] + fb->offsets[1]; base |= addr_flag; tegra_plane_writel(p, upper_32_bits(base), DC_WINBUF_START_ADDR_HI_U); tegra_plane_writel(p, lower_32_bits(base), DC_WINBUF_START_ADDR_U); - base = tegra_plane_state->iova[2] + fb->offsets[2]; - base |= addr_flag; + if (planes > 2) { + base = tegra_plane_state->iova[2] + fb->offsets[2]; + base |= addr_flag; + + tegra_plane_writel(p, upper_32_bits(base), DC_WINBUF_START_ADDR_HI_V); + tegra_plane_writel(p, lower_32_bits(base), DC_WINBUF_START_ADDR_V); + } + + value = PITCH_U(fb->pitches[1]); - tegra_plane_writel(p, upper_32_bits(base), DC_WINBUF_START_ADDR_HI_V); - tegra_plane_writel(p, lower_32_bits(base), DC_WINBUF_START_ADDR_V); + if (planes > 2) + value |= PITCH_V(fb->pitches[2]); - value = PITCH_U(fb->pitches[2]) | PITCH_V(fb->pitches[2]); tegra_plane_writel(p, value, DC_WIN_PLANAR_STORAGE_UV); } else { tegra_plane_writel(p, 0, DC_WINBUF_START_ADDR_U); diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c index 321cb1f13da6..e0e6938c6200 100644 --- a/drivers/gpu/drm/tegra/plane.c +++ b/drivers/gpu/drm/tegra/plane.c @@ -413,6 +413,22 @@ int tegra_plane_format(u32 fourcc, u32 *format, u32 *swap) *swap = BYTE_SWAP_SWAP2; break; + case DRM_FORMAT_YVYU: + if (!swap) + return -EINVAL; + + *format = WIN_COLOR_DEPTH_YCbCr422; + *swap = BYTE_SWAP_SWAP4; + break; + + case DRM_FORMAT_VYUY: + if (!swap) + return -EINVAL; + + *format = WIN_COLOR_DEPTH_YCbCr422; + *swap = BYTE_SWAP_SWAP4HW; + break; + case DRM_FORMAT_YUV420: *format = WIN_COLOR_DEPTH_YCbCr420P; break; @@ -421,6 +437,34 @@ int tegra_plane_format(u32 fourcc, u32 *format, u32 *swap) *format = WIN_COLOR_DEPTH_YCbCr422P; break; + case DRM_FORMAT_YUV444: + *format = WIN_COLOR_DEPTH_YCbCr444P; + break; + + case DRM_FORMAT_NV12: + *format = WIN_COLOR_DEPTH_YCbCr420SP; + break; + + case DRM_FORMAT_NV21: + *format = WIN_COLOR_DEPTH_YCrCb420SP; + break; + + case DRM_FORMAT_NV16: + *format = WIN_COLOR_DEPTH_YCbCr422SP; + break; + + case DRM_FORMAT_NV61: + *format = WIN_COLOR_DEPTH_YCrCb422SP; + break; + + case DRM_FORMAT_NV24: + *format = WIN_COLOR_DEPTH_YCbCr444SP; + break; + + case DRM_FORMAT_NV42: + *format = WIN_COLOR_DEPTH_YCrCb444SP; + break; + default: return -EINVAL; } @@ -441,13 +485,13 @@ bool tegra_plane_format_is_indexed(unsigned int format) return false; } -bool tegra_plane_format_is_yuv(unsigned int format, bool *planar, unsigned int *bpc) +bool tegra_plane_format_is_yuv(unsigned int format, unsigned int *planes, unsigned int *bpc) { switch (format) { case WIN_COLOR_DEPTH_YCbCr422: case WIN_COLOR_DEPTH_YUV422: - if (planar) - *planar = false; + if (planes) + *planes = 1; if (bpc) *bpc = 8; @@ -462,8 +506,23 @@ bool tegra_plane_format_is_yuv(unsigned int format, bool *planar, unsigned int * case WIN_COLOR_DEPTH_YUV422R: case WIN_COLOR_DEPTH_YCbCr422RA: case WIN_COLOR_DEPTH_YUV422RA: - if (planar) - *planar = true; + case WIN_COLOR_DEPTH_YCbCr444P: + if (planes) + *planes = 3; + + if (bpc) + *bpc = 8; + + return true; + + case WIN_COLOR_DEPTH_YCrCb420SP: + case WIN_COLOR_DEPTH_YCbCr420SP: + case WIN_COLOR_DEPTH_YCrCb422SP: + case WIN_COLOR_DEPTH_YCbCr422SP: + case WIN_COLOR_DEPTH_YCrCb444SP: + case WIN_COLOR_DEPTH_YCbCr444SP: + if (planes) + *planes = 2; if (bpc) *bpc = 8; @@ -471,8 +530,8 @@ bool tegra_plane_format_is_yuv(unsigned int format, bool *planar, unsigned int * return true; } - if (planar) - *planar = false; + if (planes) + *planes = 1; return false; } diff --git a/drivers/gpu/drm/tegra/plane.h b/drivers/gpu/drm/tegra/plane.h index dfb20712fbd7..e33a581e6490 100644 --- a/drivers/gpu/drm/tegra/plane.h +++ b/drivers/gpu/drm/tegra/plane.h @@ -90,7 +90,7 @@ int tegra_plane_state_add(struct tegra_plane *plane, int tegra_plane_format(u32 fourcc, u32 *format, u32 *swap); bool tegra_plane_format_is_indexed(unsigned int format); -bool tegra_plane_format_is_yuv(unsigned int format, bool *planar, unsigned int *bpc); +bool tegra_plane_format_is_yuv(unsigned int format, unsigned int *planes, unsigned int *bpc); int tegra_plane_setup_legacy_state(struct tegra_plane *tegra, struct tegra_plane_state *state); int tegra_plane_interconnect_init(struct tegra_plane *plane); diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig index 712e0004e96e..627d637a1e7e 100644 --- a/drivers/gpu/drm/tiny/Kconfig +++ b/drivers/gpu/drm/tiny/Kconfig @@ -51,6 +51,21 @@ config DRM_GM12U320 This is a KMS driver for projectors which use the GM12U320 chipset for video transfer over USB2/3, such as the Acer C120 mini projector. +config DRM_PANEL_MIPI_DBI + tristate "DRM support for MIPI DBI compatible panels" + depends on DRM && SPI + select DRM_KMS_HELPER + select DRM_GEM_CMA_HELPER + select DRM_MIPI_DBI + select BACKLIGHT_CLASS_DEVICE + select VIDEOMODE_HELPERS + help + Say Y here if you want to enable support for MIPI DBI compatible + panels. The controller command setup can be provided using a + firmware file. For more information see + https://github.com/notro/panel-mipi-dbi/wiki. + To compile this driver as a module, choose M here. + config DRM_SIMPLEDRM tristate "Simple framebuffer driver" depends on DRM && MMU diff --git a/drivers/gpu/drm/tiny/Makefile b/drivers/gpu/drm/tiny/Makefile index 5d5505d40e7b..1d9d6227e7ab 100644 --- a/drivers/gpu/drm/tiny/Makefile +++ b/drivers/gpu/drm/tiny/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_DRM_ARCPGU) += arcpgu.o obj-$(CONFIG_DRM_BOCHS) += bochs.o obj-$(CONFIG_DRM_CIRRUS_QEMU) += cirrus.o obj-$(CONFIG_DRM_GM12U320) += gm12u320.o +obj-$(CONFIG_DRM_PANEL_MIPI_DBI) += panel-mipi-dbi.o obj-$(CONFIG_DRM_SIMPLEDRM) += simpledrm.o obj-$(CONFIG_TINYDRM_HX8357D) += hx8357d.o obj-$(CONFIG_TINYDRM_ILI9163) += ili9163.o diff --git a/drivers/gpu/drm/tiny/hx8357d.c b/drivers/gpu/drm/tiny/hx8357d.c index 9b33c05732aa..ebb025543f8d 100644 --- a/drivers/gpu/drm/tiny/hx8357d.c +++ b/drivers/gpu/drm/tiny/hx8357d.c @@ -263,14 +263,12 @@ static int hx8357d_probe(struct spi_device *spi) return 0; } -static int hx8357d_remove(struct spi_device *spi) +static void hx8357d_remove(struct spi_device *spi) { struct drm_device *drm = spi_get_drvdata(spi); drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); - - return 0; } static void hx8357d_shutdown(struct spi_device *spi) diff --git a/drivers/gpu/drm/tiny/ili9163.c b/drivers/gpu/drm/tiny/ili9163.c index bcc181351236..fc8ed245b0bc 100644 --- a/drivers/gpu/drm/tiny/ili9163.c +++ b/drivers/gpu/drm/tiny/ili9163.c @@ -193,14 +193,12 @@ static int ili9163_probe(struct spi_device *spi) return 0; } -static int ili9163_remove(struct spi_device *spi) +static void ili9163_remove(struct spi_device *spi) { struct drm_device *drm = spi_get_drvdata(spi); drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); - - return 0; } static void ili9163_shutdown(struct spi_device *spi) diff --git a/drivers/gpu/drm/tiny/ili9225.c b/drivers/gpu/drm/tiny/ili9225.c index 976d3209f164..cc92eb9f2a07 100644 --- a/drivers/gpu/drm/tiny/ili9225.c +++ b/drivers/gpu/drm/tiny/ili9225.c @@ -411,14 +411,12 @@ static int ili9225_probe(struct spi_device *spi) return 0; } -static int ili9225_remove(struct spi_device *spi) +static void ili9225_remove(struct spi_device *spi) { struct drm_device *drm = spi_get_drvdata(spi); drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); - - return 0; } static void ili9225_shutdown(struct spi_device *spi) diff --git a/drivers/gpu/drm/tiny/ili9341.c b/drivers/gpu/drm/tiny/ili9341.c index 37e0c33399c8..5b8cc770ee7b 100644 --- a/drivers/gpu/drm/tiny/ili9341.c +++ b/drivers/gpu/drm/tiny/ili9341.c @@ -225,14 +225,12 @@ static int ili9341_probe(struct spi_device *spi) return 0; } -static int ili9341_remove(struct spi_device *spi) +static void ili9341_remove(struct spi_device *spi) { struct drm_device *drm = spi_get_drvdata(spi); drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); - - return 0; } static void ili9341_shutdown(struct spi_device *spi) diff --git a/drivers/gpu/drm/tiny/ili9486.c b/drivers/gpu/drm/tiny/ili9486.c index e9a63f4b2993..6d655e18e0aa 100644 --- a/drivers/gpu/drm/tiny/ili9486.c +++ b/drivers/gpu/drm/tiny/ili9486.c @@ -243,14 +243,12 @@ static int ili9486_probe(struct spi_device *spi) return 0; } -static int ili9486_remove(struct spi_device *spi) +static void ili9486_remove(struct spi_device *spi) { struct drm_device *drm = spi_get_drvdata(spi); drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); - - return 0; } static void ili9486_shutdown(struct spi_device *spi) diff --git a/drivers/gpu/drm/tiny/mi0283qt.c b/drivers/gpu/drm/tiny/mi0283qt.c index 023de49e7a8e..5e060f6910bb 100644 --- a/drivers/gpu/drm/tiny/mi0283qt.c +++ b/drivers/gpu/drm/tiny/mi0283qt.c @@ -233,14 +233,12 @@ static int mi0283qt_probe(struct spi_device *spi) return 0; } -static int mi0283qt_remove(struct spi_device *spi) +static void mi0283qt_remove(struct spi_device *spi) { struct drm_device *drm = spi_get_drvdata(spi); drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); - - return 0; } static void mi0283qt_shutdown(struct spi_device *spi) diff --git a/drivers/gpu/drm/tiny/panel-mipi-dbi.c b/drivers/gpu/drm/tiny/panel-mipi-dbi.c new file mode 100644 index 000000000000..c759ff9c2c87 --- /dev/null +++ b/drivers/gpu/drm/tiny/panel-mipi-dbi.c @@ -0,0 +1,396 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DRM driver for MIPI DBI compatible display panels + * + * Copyright 2022 Noralf Trønnes + */ + +#include <linux/backlight.h> +#include <linux/delay.h> +#include <linux/firmware.h> +#include <linux/gpio/consumer.h> +#include <linux/module.h> +#include <linux/property.h> +#include <linux/regulator/consumer.h> +#include <linux/spi/spi.h> + +#include <drm/drm_atomic_helper.h> +#include <drm/drm_drv.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_gem_atomic_helper.h> +#include <drm/drm_gem_cma_helper.h> +#include <drm/drm_managed.h> +#include <drm/drm_mipi_dbi.h> +#include <drm/drm_modes.h> +#include <drm/drm_modeset_helper.h> + +#include <video/mipi_display.h> + +static const u8 panel_mipi_dbi_magic[15] = { 'M', 'I', 'P', 'I', ' ', 'D', 'B', 'I', + 0, 0, 0, 0, 0, 0, 0 }; + +/* + * The display controller configuration is stored in a firmware file. + * The Device Tree 'compatible' property value with a '.bin' suffix is passed + * to request_firmware() to fetch this file. + */ +struct panel_mipi_dbi_config { + /* Magic string: panel_mipi_dbi_magic */ + u8 magic[15]; + + /* Config file format version */ + u8 file_format_version; + + /* + * MIPI commands to execute when the display pipeline is enabled. + * This is used to configure the display controller. + * + * The commands are stored in a byte array with the format: + * command, num_parameters, [ parameter, ...], command, ... + * + * Some commands require a pause before the next command can be received. + * Inserting a delay in the command sequence is done by using the NOP command with one + * parameter: delay in miliseconds (the No Operation command is part of the MIPI Display + * Command Set where it has no parameters). + * + * Example: + * command 0x11 + * sleep 120ms + * command 0xb1 parameters 0x01, 0x2c, 0x2d + * command 0x29 + * + * Byte sequence: + * 0x11 0x00 + * 0x00 0x01 0x78 + * 0xb1 0x03 0x01 0x2c 0x2d + * 0x29 0x00 + */ + u8 commands[]; +}; + +struct panel_mipi_dbi_commands { + const u8 *buf; + size_t len; +}; + +static struct panel_mipi_dbi_commands * +panel_mipi_dbi_check_commands(struct device *dev, const struct firmware *fw) +{ + const struct panel_mipi_dbi_config *config = (struct panel_mipi_dbi_config *)fw->data; + struct panel_mipi_dbi_commands *commands; + size_t size = fw->size, commands_len; + unsigned int i = 0; + + if (size < sizeof(*config) + 2) { /* At least 1 command */ + dev_err(dev, "config: file size=%zu is too small\n", size); + return ERR_PTR(-EINVAL); + } + + if (memcmp(config->magic, panel_mipi_dbi_magic, sizeof(config->magic))) { + dev_err(dev, "config: Bad magic: %15ph\n", config->magic); + return ERR_PTR(-EINVAL); + } + + if (config->file_format_version != 1) { + dev_err(dev, "config: version=%u is not supported\n", config->file_format_version); + return ERR_PTR(-EINVAL); + } + + drm_dev_dbg(dev, DRM_UT_DRIVER, "size=%zu version=%u\n", size, config->file_format_version); + + commands_len = size - sizeof(*config); + + while ((i + 1) < commands_len) { + u8 command = config->commands[i++]; + u8 num_parameters = config->commands[i++]; + const u8 *parameters = &config->commands[i]; + + i += num_parameters; + if (i > commands_len) { + dev_err(dev, "config: command=0x%02x num_parameters=%u overflows\n", + command, num_parameters); + return ERR_PTR(-EINVAL); + } + + if (command == 0x00 && num_parameters == 1) + drm_dev_dbg(dev, DRM_UT_DRIVER, "sleep %ums\n", parameters[0]); + else + drm_dev_dbg(dev, DRM_UT_DRIVER, "command %02x %*ph\n", + command, num_parameters, parameters); + } + + if (i != commands_len) { + dev_err(dev, "config: malformed command array\n"); + return ERR_PTR(-EINVAL); + } + + commands = devm_kzalloc(dev, sizeof(*commands), GFP_KERNEL); + if (!commands) + return ERR_PTR(-ENOMEM); + + commands->len = commands_len; + commands->buf = devm_kmemdup(dev, config->commands, commands->len, GFP_KERNEL); + if (!commands->buf) + return ERR_PTR(-ENOMEM); + + return commands; +} + +static struct panel_mipi_dbi_commands *panel_mipi_dbi_commands_from_fw(struct device *dev) +{ + struct panel_mipi_dbi_commands *commands; + const struct firmware *fw; + const char *compatible; + char fw_name[40]; + int ret; + + ret = of_property_read_string_index(dev->of_node, "compatible", 0, &compatible); + if (ret) + return ERR_PTR(ret); + + snprintf(fw_name, sizeof(fw_name), "%s.bin", compatible); + ret = request_firmware(&fw, fw_name, dev); + if (ret) { + dev_err(dev, "No config file found for compatible '%s' (error=%d)\n", + compatible, ret); + + return ERR_PTR(ret); + } + + commands = panel_mipi_dbi_check_commands(dev, fw); + release_firmware(fw); + + return commands; +} + +static void panel_mipi_dbi_commands_execute(struct mipi_dbi *dbi, + struct panel_mipi_dbi_commands *commands) +{ + unsigned int i = 0; + + if (!commands) + return; + + while (i < commands->len) { + u8 command = commands->buf[i++]; + u8 num_parameters = commands->buf[i++]; + const u8 *parameters = &commands->buf[i]; + + if (command == 0x00 && num_parameters == 1) + msleep(parameters[0]); + else if (num_parameters) + mipi_dbi_command_stackbuf(dbi, command, parameters, num_parameters); + else + mipi_dbi_command(dbi, command); + + i += num_parameters; + } +} + +static void panel_mipi_dbi_enable(struct drm_simple_display_pipe *pipe, + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) +{ + struct mipi_dbi_dev *dbidev = drm_to_mipi_dbi_dev(pipe->crtc.dev); + struct mipi_dbi *dbi = &dbidev->dbi; + int ret, idx; + + if (!drm_dev_enter(pipe->crtc.dev, &idx)) + return; + + drm_dbg(pipe->crtc.dev, "\n"); + + ret = mipi_dbi_poweron_conditional_reset(dbidev); + if (ret < 0) + goto out_exit; + if (!ret) + panel_mipi_dbi_commands_execute(dbi, dbidev->driver_private); + + mipi_dbi_enable_flush(dbidev, crtc_state, plane_state); +out_exit: + drm_dev_exit(idx); +} + +static const struct drm_simple_display_pipe_funcs panel_mipi_dbi_pipe_funcs = { + .enable = panel_mipi_dbi_enable, + .disable = mipi_dbi_pipe_disable, + .update = mipi_dbi_pipe_update, +}; + +DEFINE_DRM_GEM_CMA_FOPS(panel_mipi_dbi_fops); + +static const struct drm_driver panel_mipi_dbi_driver = { + .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, + .fops = &panel_mipi_dbi_fops, + DRM_GEM_CMA_DRIVER_OPS_VMAP, + .debugfs_init = mipi_dbi_debugfs_init, + .name = "panel-mipi-dbi", + .desc = "MIPI DBI compatible display panel", + .date = "20220103", + .major = 1, + .minor = 0, +}; + +static int panel_mipi_dbi_get_mode(struct mipi_dbi_dev *dbidev, struct drm_display_mode *mode) +{ + struct device *dev = dbidev->drm.dev; + u16 hback_porch, vback_porch; + int ret; + + ret = of_get_drm_panel_display_mode(dev->of_node, mode, NULL); + if (ret) { + dev_err(dev, "%pOF: failed to get panel-timing (error=%d)\n", dev->of_node, ret); + return ret; + } + + mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; + + hback_porch = mode->htotal - mode->hsync_end; + vback_porch = mode->vtotal - mode->vsync_end; + + /* + * Make sure width and height are set and that only back porch and + * pixelclock are set in the other timing values. Also check that + * width and height don't exceed the 16-bit value specified by MIPI DCS. + */ + if (!mode->hdisplay || !mode->vdisplay || mode->flags || + mode->hsync_end > mode->hdisplay || (hback_porch + mode->hdisplay) > 0xffff || + mode->vsync_end > mode->vdisplay || (vback_porch + mode->vdisplay) > 0xffff) { + dev_err(dev, "%pOF: panel-timing out of bounds\n", dev->of_node); + return -EINVAL; + } + + /* The driver doesn't use the pixel clock but it is mandatory so fake one if not set */ + if (!mode->clock) + mode->clock = mode->htotal * mode->vtotal * 60 / 1000; + + dbidev->top_offset = vback_porch; + dbidev->left_offset = hback_porch; + + return 0; +} + +static int panel_mipi_dbi_spi_probe(struct spi_device *spi) +{ + struct device *dev = &spi->dev; + struct drm_display_mode mode; + struct mipi_dbi_dev *dbidev; + struct drm_device *drm; + struct mipi_dbi *dbi; + struct gpio_desc *dc; + int ret; + + dbidev = devm_drm_dev_alloc(dev, &panel_mipi_dbi_driver, struct mipi_dbi_dev, drm); + if (IS_ERR(dbidev)) + return PTR_ERR(dbidev); + + dbi = &dbidev->dbi; + drm = &dbidev->drm; + + ret = panel_mipi_dbi_get_mode(dbidev, &mode); + if (ret) + return ret; + + dbidev->regulator = devm_regulator_get(dev, "power"); + if (IS_ERR(dbidev->regulator)) + return dev_err_probe(dev, PTR_ERR(dbidev->regulator), + "Failed to get regulator 'power'\n"); + + dbidev->backlight = devm_of_find_backlight(dev); + if (IS_ERR(dbidev->backlight)) + return dev_err_probe(dev, PTR_ERR(dbidev->backlight), "Failed to get backlight\n"); + + dbi->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(dbi->reset)) + return dev_err_probe(dev, PTR_ERR(dbi->reset), "Failed to get GPIO 'reset'\n"); + + dc = devm_gpiod_get_optional(dev, "dc", GPIOD_OUT_LOW); + if (IS_ERR(dc)) + return dev_err_probe(dev, PTR_ERR(dc), "Failed to get GPIO 'dc'\n"); + + ret = mipi_dbi_spi_init(spi, dbi, dc); + if (ret) + return ret; + + if (device_property_present(dev, "write-only")) + dbi->read_commands = NULL; + + dbidev->driver_private = panel_mipi_dbi_commands_from_fw(dev); + if (IS_ERR(dbidev->driver_private)) + return PTR_ERR(dbidev->driver_private); + + ret = mipi_dbi_dev_init(dbidev, &panel_mipi_dbi_pipe_funcs, &mode, 0); + if (ret) + return ret; + + drm_mode_config_reset(drm); + + ret = drm_dev_register(drm, 0); + if (ret) + return ret; + + spi_set_drvdata(spi, drm); + + drm_fbdev_generic_setup(drm, 0); + + return 0; +} + +static void panel_mipi_dbi_spi_remove(struct spi_device *spi) +{ + struct drm_device *drm = spi_get_drvdata(spi); + + drm_dev_unplug(drm); + drm_atomic_helper_shutdown(drm); +} + +static void panel_mipi_dbi_spi_shutdown(struct spi_device *spi) +{ + drm_atomic_helper_shutdown(spi_get_drvdata(spi)); +} + +static int __maybe_unused panel_mipi_dbi_pm_suspend(struct device *dev) +{ + return drm_mode_config_helper_suspend(dev_get_drvdata(dev)); +} + +static int __maybe_unused panel_mipi_dbi_pm_resume(struct device *dev) +{ + drm_mode_config_helper_resume(dev_get_drvdata(dev)); + + return 0; +} + +static const struct dev_pm_ops panel_mipi_dbi_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(panel_mipi_dbi_pm_suspend, panel_mipi_dbi_pm_resume) +}; + +static const struct of_device_id panel_mipi_dbi_spi_of_match[] = { + { .compatible = "panel-mipi-dbi-spi" }, + {}, +}; +MODULE_DEVICE_TABLE(of, panel_mipi_dbi_spi_of_match); + +static const struct spi_device_id panel_mipi_dbi_spi_id[] = { + { "panel-mipi-dbi-spi", 0 }, + { }, +}; +MODULE_DEVICE_TABLE(spi, panel_mipi_dbi_spi_id); + +static struct spi_driver panel_mipi_dbi_spi_driver = { + .driver = { + .name = "panel-mipi-dbi-spi", + .owner = THIS_MODULE, + .of_match_table = panel_mipi_dbi_spi_of_match, + .pm = &panel_mipi_dbi_pm_ops, + }, + .id_table = panel_mipi_dbi_spi_id, + .probe = panel_mipi_dbi_spi_probe, + .remove = panel_mipi_dbi_spi_remove, + .shutdown = panel_mipi_dbi_spi_shutdown, +}; +module_spi_driver(panel_mipi_dbi_spi_driver); + +MODULE_DESCRIPTION("MIPI DBI compatible display panel driver"); +MODULE_AUTHOR("Noralf Trønnes"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/tiny/repaper.c b/drivers/gpu/drm/tiny/repaper.c index 97a775c48cea..37b6bb90e46e 100644 --- a/drivers/gpu/drm/tiny/repaper.c +++ b/drivers/gpu/drm/tiny/repaper.c @@ -508,26 +508,6 @@ static void repaper_get_temperature(struct repaper_epd *epd) epd->factored_stage_time = epd->stage_time * factor10x / 10; } -static void repaper_gray8_to_mono_reversed(u8 *buf, u32 width, u32 height) -{ - u8 *gray8 = buf, *mono = buf; - int y, xb, i; - - for (y = 0; y < height; y++) - for (xb = 0; xb < width / 8; xb++) { - u8 byte = 0x00; - - for (i = 0; i < 8; i++) { - int x = xb * 8 + i; - - byte >>= 1; - if (gray8[y * width + x] >> 7) - byte |= BIT(7); - } - *mono++ = byte; - } -} - static int repaper_fb_dirty(struct drm_framebuffer *fb) { struct drm_gem_cma_object *cma_obj = drm_fb_cma_get_gem_obj(fb, 0); @@ -560,12 +540,10 @@ static int repaper_fb_dirty(struct drm_framebuffer *fb) if (ret) goto out_free; - drm_fb_xrgb8888_to_gray8(buf, 0, cma_obj->vaddr, fb, &clip); + drm_fb_xrgb8888_to_mono_reversed(buf, 0, cma_obj->vaddr, fb, &clip); drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE); - repaper_gray8_to_mono_reversed(buf, fb->width, fb->height); - if (epd->partial) { repaper_frame_data_repeat(epd, buf, epd->current_frame, REPAPER_NORMAL); @@ -1140,14 +1118,12 @@ static int repaper_probe(struct spi_device *spi) return 0; } -static int repaper_remove(struct spi_device *spi) +static void repaper_remove(struct spi_device *spi) { struct drm_device *drm = spi_get_drvdata(spi); drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); - - return 0; } static void repaper_shutdown(struct spi_device *spi) diff --git a/drivers/gpu/drm/tiny/simpledrm.c b/drivers/gpu/drm/tiny/simpledrm.c index d191e87a37b5..f5b8e864a5cd 100644 --- a/drivers/gpu/drm/tiny/simpledrm.c +++ b/drivers/gpu/drm/tiny/simpledrm.c @@ -810,6 +810,9 @@ static int simpledrm_device_init_modeset(struct simpledrm_device *sdev) if (ret) return ret; drm_connector_helper_add(connector, &simpledrm_connector_helper_funcs); + drm_connector_set_panel_orientation_with_quirk(connector, + DRM_MODE_PANEL_ORIENTATION_UNKNOWN, + mode->hdisplay, mode->vdisplay); formats = simpledrm_device_formats(sdev, &nformats); diff --git a/drivers/gpu/drm/tiny/st7586.c b/drivers/gpu/drm/tiny/st7586.c index 51b9b9fb3ead..3f38faa1cd8c 100644 --- a/drivers/gpu/drm/tiny/st7586.c +++ b/drivers/gpu/drm/tiny/st7586.c @@ -360,14 +360,12 @@ static int st7586_probe(struct spi_device *spi) return 0; } -static int st7586_remove(struct spi_device *spi) +static void st7586_remove(struct spi_device *spi) { struct drm_device *drm = spi_get_drvdata(spi); drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); - - return 0; } static void st7586_shutdown(struct spi_device *spi) diff --git a/drivers/gpu/drm/tiny/st7735r.c b/drivers/gpu/drm/tiny/st7735r.c index fc40dd10efa8..29d618093e94 100644 --- a/drivers/gpu/drm/tiny/st7735r.c +++ b/drivers/gpu/drm/tiny/st7735r.c @@ -247,14 +247,12 @@ static int st7735r_probe(struct spi_device *spi) return 0; } -static int st7735r_remove(struct spi_device *spi) +static void st7735r_remove(struct spi_device *spi) { struct drm_device *drm = spi_get_drvdata(spi); drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); - - return 0; } static void st7735r_shutdown(struct spi_device *spi) diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c index 8cd4f3fb9f79..d91666721dc6 100644 --- a/drivers/gpu/drm/ttm/ttm_range_manager.c +++ b/drivers/gpu/drm/ttm/ttm_range_manager.c @@ -89,7 +89,7 @@ static int ttm_range_man_alloc(struct ttm_resource_manager *man, spin_unlock(&rman->lock); if (unlikely(ret)) { - ttm_resource_fini(man, *res); + ttm_resource_fini(man, &node->base); kfree(node); return ret; } diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 39459ae96f30..06238e6d7f5c 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -392,34 +392,24 @@ v3d_sched_init(struct v3d_dev *v3d) hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_bin", v3d->drm.dev); - if (ret) { - dev_err(v3d->drm.dev, "Failed to create bin scheduler: %d.", ret); + if (ret) return ret; - } ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched, &v3d_render_sched_ops, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_render", v3d->drm.dev); - if (ret) { - dev_err(v3d->drm.dev, "Failed to create render scheduler: %d.", - ret); - v3d_sched_fini(v3d); - return ret; - } + if (ret) + goto fail; ret = drm_sched_init(&v3d->queue[V3D_TFU].sched, &v3d_tfu_sched_ops, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_tfu", v3d->drm.dev); - if (ret) { - dev_err(v3d->drm.dev, "Failed to create TFU scheduler: %d.", - ret); - v3d_sched_fini(v3d); - return ret; - } + if (ret) + goto fail; if (v3d_has_csd(v3d)) { ret = drm_sched_init(&v3d->queue[V3D_CSD].sched, @@ -427,27 +417,23 @@ v3d_sched_init(struct v3d_dev *v3d) hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_csd", v3d->drm.dev); - if (ret) { - dev_err(v3d->drm.dev, "Failed to create CSD scheduler: %d.", - ret); - v3d_sched_fini(v3d); - return ret; - } + if (ret) + goto fail; ret = drm_sched_init(&v3d->queue[V3D_CACHE_CLEAN].sched, &v3d_cache_clean_sched_ops, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_cache_clean", v3d->drm.dev); - if (ret) { - dev_err(v3d->drm.dev, "Failed to create CACHE_CLEAN scheduler: %d.", - ret); - v3d_sched_fini(v3d); - return ret; - } + if (ret) + goto fail; } return 0; + +fail: + v3d_sched_fini(v3d); + return ret; } void diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index a03053c8e22c..162bc18e7497 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -189,11 +189,6 @@ static struct drm_driver vc4_drm_driver = { .patchlevel = DRIVER_PATCHLEVEL, }; -static int compare_dev(struct device *dev, void *data) -{ - return dev == data; -} - static void vc4_match_add_drivers(struct device *dev, struct component_match **match, struct platform_driver *const *drivers, @@ -207,7 +202,7 @@ static void vc4_match_add_drivers(struct device *dev, while ((d = platform_find_device_by_driver(p, drv))) { put_device(p); - component_match_add(dev, match, compare_dev, d); + component_match_add(dev, match, component_compare_dev, d); p = d; } put_device(p); diff --git a/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c b/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c index e10d95dddb99..08b526eeec16 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c +++ b/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c @@ -148,7 +148,7 @@ static void evtchnl_free(struct xen_drm_front_info *front_info, /* end access and free the page */ if (evtchnl->gref != GRANT_INVALID_REF) - gnttab_end_foreign_access(evtchnl->gref, 0, page); + gnttab_end_foreign_access(evtchnl->gref, page); memset(evtchnl, 0, sizeof(*evtchnl)); } diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 6994f8c0e02e..80c685ab3e30 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -447,7 +447,6 @@ static int host1x_probe(struct platform_device *pdev) if (syncpt_irq < 0) return syncpt_irq; - host1x_bo_cache_init(&host->cache); mutex_init(&host->devices_lock); INIT_LIST_HEAD(&host->devices); INIT_LIST_HEAD(&host->list); @@ -489,10 +488,12 @@ static int host1x_probe(struct platform_device *pdev) if (err) return err; + host1x_bo_cache_init(&host->cache); + err = host1x_iommu_init(host); if (err < 0) { dev_err(&pdev->dev, "failed to setup IOMMU: %d\n", err); - return err; + goto destroy_cache; } err = host1x_channel_list_init(&host->channel_list, @@ -553,6 +554,8 @@ free_channels: host1x_channel_list_free(&host->channel_list); iommu_exit: host1x_iommu_exit(host); +destroy_cache: + host1x_bo_cache_destroy(&host->cache); return err; } @@ -568,6 +571,7 @@ static int host1x_remove(struct platform_device *pdev) host1x_intr_deinit(host); host1x_syncpt_deinit(host); + host1x_channel_list_free(&host->channel_list); host1x_iommu_exit(host); host1x_bo_cache_destroy(&host->cache); diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c index a9639d098893..778bc26d3ba5 100644 --- a/drivers/gpu/ipu-v3/ipu-csi.c +++ b/drivers/gpu/ipu-v3/ipu-csi.c @@ -357,11 +357,11 @@ static int fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg, switch (mbus_cfg->type) { case V4L2_MBUS_PARALLEL: csicfg->ext_vsync = 1; - csicfg->vsync_pol = (mbus_cfg->flags & + csicfg->vsync_pol = (mbus_cfg->bus.parallel.flags & V4L2_MBUS_VSYNC_ACTIVE_LOW) ? 1 : 0; - csicfg->hsync_pol = (mbus_cfg->flags & + csicfg->hsync_pol = (mbus_cfg->bus.parallel.flags & V4L2_MBUS_HSYNC_ACTIVE_LOW) ? 1 : 0; - csicfg->pixclk_pol = (mbus_cfg->flags & + csicfg->pixclk_pol = (mbus_cfg->bus.parallel.flags & V4L2_MBUS_PCLK_SAMPLE_FALLING) ? 1 : 0; csicfg->clk_mode = IPU_CSI_CLK_MODE_GATED_CLK; break; diff --git a/drivers/gpu/vga/Kconfig b/drivers/gpu/vga/Kconfig index 1ad4c4ef0b5e..eb8b14ab22c3 100644 --- a/drivers/gpu/vga/Kconfig +++ b/drivers/gpu/vga/Kconfig @@ -1,23 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -config VGA_ARB - bool "VGA Arbitration" if EXPERT - default y - depends on (PCI && !S390) - help - Some "legacy" VGA devices implemented on PCI typically have the same - hard-decoded addresses as they did on ISA. When multiple PCI devices - are accessed at same time they need some kind of coordination. Please - see Documentation/gpu/vgaarbiter.rst for more details. Select this to - enable VGA arbiter. - -config VGA_ARB_MAX_GPUS - int "Maximum number of GPUs" - default 16 - depends on VGA_ARB - help - Reserves space in the kernel to maintain resource locking for - multiple GPUS. The overhead for each GPU is very small. - config VGA_SWITCHEROO bool "Laptop Hybrid Graphics - GPU switching support" depends on X86 diff --git a/drivers/gpu/vga/Makefile b/drivers/gpu/vga/Makefile index e92064442d60..9800620deda3 100644 --- a/drivers/gpu/vga/Makefile +++ b/drivers/gpu/vga/Makefile @@ -1,3 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_VGA_ARB) += vgaarb.o obj-$(CONFIG_VGA_SWITCHEROO) += vga_switcheroo.o diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c deleted file mode 100644 index 569930552957..000000000000 --- a/drivers/gpu/vga/vgaarb.c +++ /dev/null @@ -1,1567 +0,0 @@ -/* - * vgaarb.c: Implements the VGA arbitration. For details refer to - * Documentation/gpu/vgaarbiter.rst - * - * - * (C) Copyright 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org> - * (C) Copyright 2007 Paulo R. Zanoni <przanoni@gmail.com> - * (C) Copyright 2007, 2009 Tiago Vignatti <vignatti@freedesktop.org> - * - * 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 (including the next - * paragraph) 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 AUTHORS OR COPYRIGHT HOLDERS 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. - * - */ - -#define pr_fmt(fmt) "vgaarb: " fmt - -#define vgaarb_dbg(dev, fmt, arg...) dev_dbg(dev, "vgaarb: " fmt, ##arg) -#define vgaarb_info(dev, fmt, arg...) dev_info(dev, "vgaarb: " fmt, ##arg) -#define vgaarb_err(dev, fmt, arg...) dev_err(dev, "vgaarb: " fmt, ##arg) - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/errno.h> -#include <linux/init.h> -#include <linux/list.h> -#include <linux/sched/signal.h> -#include <linux/wait.h> -#include <linux/spinlock.h> -#include <linux/poll.h> -#include <linux/miscdevice.h> -#include <linux/slab.h> -#include <linux/screen_info.h> -#include <linux/vt.h> -#include <linux/console.h> -#include <linux/acpi.h> - -#include <linux/uaccess.h> - -#include <linux/vgaarb.h> - -static void vga_arbiter_notify_clients(void); -/* - * We keep a list of all vga devices in the system to speed - * up the various operations of the arbiter - */ -struct vga_device { - struct list_head list; - struct pci_dev *pdev; - unsigned int decodes; /* what does it decodes */ - unsigned int owns; /* what does it owns */ - unsigned int locks; /* what does it locks */ - unsigned int io_lock_cnt; /* legacy IO lock count */ - unsigned int mem_lock_cnt; /* legacy MEM lock count */ - unsigned int io_norm_cnt; /* normal IO count */ - unsigned int mem_norm_cnt; /* normal MEM count */ - bool bridge_has_one_vga; - unsigned int (*set_decode)(struct pci_dev *pdev, bool decode); -}; - -static LIST_HEAD(vga_list); -static int vga_count, vga_decode_count; -static bool vga_arbiter_used; -static DEFINE_SPINLOCK(vga_lock); -static DECLARE_WAIT_QUEUE_HEAD(vga_wait_queue); - - -static const char *vga_iostate_to_str(unsigned int iostate) -{ - /* Ignore VGA_RSRC_IO and VGA_RSRC_MEM */ - iostate &= VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM; - switch (iostate) { - case VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM: - return "io+mem"; - case VGA_RSRC_LEGACY_IO: - return "io"; - case VGA_RSRC_LEGACY_MEM: - return "mem"; - } - return "none"; -} - -static int vga_str_to_iostate(char *buf, int str_size, int *io_state) -{ - /* we could in theory hand out locks on IO and mem - * separately to userspace but it can cause deadlocks */ - if (strncmp(buf, "none", 4) == 0) { - *io_state = VGA_RSRC_NONE; - return 1; - } - - /* XXX We're not chekcing the str_size! */ - if (strncmp(buf, "io+mem", 6) == 0) - goto both; - else if (strncmp(buf, "io", 2) == 0) - goto both; - else if (strncmp(buf, "mem", 3) == 0) - goto both; - return 0; -both: - *io_state = VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM; - return 1; -} - -/* this is only used a cookie - it should not be dereferenced */ -static struct pci_dev *vga_default; - -static void vga_arb_device_card_gone(struct pci_dev *pdev); - -/* Find somebody in our list */ -static struct vga_device *vgadev_find(struct pci_dev *pdev) -{ - struct vga_device *vgadev; - - list_for_each_entry(vgadev, &vga_list, list) - if (pdev == vgadev->pdev) - return vgadev; - return NULL; -} - -/** - * vga_default_device - return the default VGA device, for vgacon - * - * This can be defined by the platform. The default implementation - * is rather dumb and will probably only work properly on single - * vga card setups and/or x86 platforms. - * - * If your VGA default device is not PCI, you'll have to return - * NULL here. In this case, I assume it will not conflict with - * any PCI card. If this is not true, I'll have to define two archs - * hooks for enabling/disabling the VGA default device if that is - * possible. This may be a problem with real _ISA_ VGA cards, in - * addition to a PCI one. I don't know at this point how to deal - * with that card. Can theirs IOs be disabled at all ? If not, then - * I suppose it's a matter of having the proper arch hook telling - * us about it, so we basically never allow anybody to succeed a - * vga_get()... - */ -struct pci_dev *vga_default_device(void) -{ - return vga_default; -} -EXPORT_SYMBOL_GPL(vga_default_device); - -void vga_set_default_device(struct pci_dev *pdev) -{ - if (vga_default == pdev) - return; - - pci_dev_put(vga_default); - vga_default = pci_dev_get(pdev); -} - -/** - * vga_remove_vgacon - deactivete vga console - * - * Unbind and unregister vgacon in case pdev is the default vga - * device. Can be called by gpu drivers on initialization to make - * sure vga register access done by vgacon will not disturb the - * device. - * - * @pdev: pci device. - */ -#if !defined(CONFIG_VGA_CONSOLE) -int vga_remove_vgacon(struct pci_dev *pdev) -{ - return 0; -} -#elif !defined(CONFIG_DUMMY_CONSOLE) -int vga_remove_vgacon(struct pci_dev *pdev) -{ - return -ENODEV; -} -#else -int vga_remove_vgacon(struct pci_dev *pdev) -{ - int ret = 0; - - if (pdev != vga_default) - return 0; - vgaarb_info(&pdev->dev, "deactivate vga console\n"); - - console_lock(); - if (con_is_bound(&vga_con)) - ret = do_take_over_console(&dummy_con, 0, - MAX_NR_CONSOLES - 1, 1); - if (ret == 0) { - ret = do_unregister_con_driver(&vga_con); - - /* Ignore "already unregistered". */ - if (ret == -ENODEV) - ret = 0; - } - console_unlock(); - - return ret; -} -#endif -EXPORT_SYMBOL(vga_remove_vgacon); - -/* If we don't ever use VGA arb we should avoid - turning off anything anywhere due to old X servers getting - confused about the boot device not being VGA */ -static void vga_check_first_use(void) -{ - /* we should inform all GPUs in the system that - * VGA arb has occurred and to try and disable resources - * if they can */ - if (!vga_arbiter_used) { - vga_arbiter_used = true; - vga_arbiter_notify_clients(); - } -} - -static struct vga_device *__vga_tryget(struct vga_device *vgadev, - unsigned int rsrc) -{ - struct device *dev = &vgadev->pdev->dev; - unsigned int wants, legacy_wants, match; - struct vga_device *conflict; - unsigned int pci_bits; - u32 flags = 0; - - /* Account for "normal" resources to lock. If we decode the legacy, - * counterpart, we need to request it as well - */ - if ((rsrc & VGA_RSRC_NORMAL_IO) && - (vgadev->decodes & VGA_RSRC_LEGACY_IO)) - rsrc |= VGA_RSRC_LEGACY_IO; - if ((rsrc & VGA_RSRC_NORMAL_MEM) && - (vgadev->decodes & VGA_RSRC_LEGACY_MEM)) - rsrc |= VGA_RSRC_LEGACY_MEM; - - vgaarb_dbg(dev, "%s: %d\n", __func__, rsrc); - vgaarb_dbg(dev, "%s: owns: %d\n", __func__, vgadev->owns); - - /* Check what resources we need to acquire */ - wants = rsrc & ~vgadev->owns; - - /* We already own everything, just mark locked & bye bye */ - if (wants == 0) - goto lock_them; - - /* We don't need to request a legacy resource, we just enable - * appropriate decoding and go - */ - legacy_wants = wants & VGA_RSRC_LEGACY_MASK; - if (legacy_wants == 0) - goto enable_them; - - /* Ok, we don't, let's find out how we need to kick off */ - list_for_each_entry(conflict, &vga_list, list) { - unsigned int lwants = legacy_wants; - unsigned int change_bridge = 0; - - /* Don't conflict with myself */ - if (vgadev == conflict) - continue; - - /* We have a possible conflict. before we go further, we must - * check if we sit on the same bus as the conflicting device. - * if we don't, then we must tie both IO and MEM resources - * together since there is only a single bit controlling - * VGA forwarding on P2P bridges - */ - if (vgadev->pdev->bus != conflict->pdev->bus) { - change_bridge = 1; - lwants = VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM; - } - - /* Check if the guy has a lock on the resource. If he does, - * return the conflicting entry - */ - if (conflict->locks & lwants) - return conflict; - - /* Ok, now check if it owns the resource we want. We can - * lock resources that are not decoded, therefore a device - * can own resources it doesn't decode. - */ - match = lwants & conflict->owns; - if (!match) - continue; - - /* looks like he doesn't have a lock, we can steal - * them from him - */ - - flags = 0; - pci_bits = 0; - - /* If we can't control legacy resources via the bridge, we - * also need to disable normal decoding. - */ - if (!conflict->bridge_has_one_vga) { - if ((match & conflict->decodes) & VGA_RSRC_LEGACY_MEM) - pci_bits |= PCI_COMMAND_MEMORY; - if ((match & conflict->decodes) & VGA_RSRC_LEGACY_IO) - pci_bits |= PCI_COMMAND_IO; - - if (pci_bits) - flags |= PCI_VGA_STATE_CHANGE_DECODES; - } - - if (change_bridge) - flags |= PCI_VGA_STATE_CHANGE_BRIDGE; - - pci_set_vga_state(conflict->pdev, false, pci_bits, flags); - conflict->owns &= ~match; - - /* If we disabled normal decoding, reflect it in owns */ - if (pci_bits & PCI_COMMAND_MEMORY) - conflict->owns &= ~VGA_RSRC_NORMAL_MEM; - if (pci_bits & PCI_COMMAND_IO) - conflict->owns &= ~VGA_RSRC_NORMAL_IO; - } - -enable_them: - /* ok dude, we got it, everybody conflicting has been disabled, let's - * enable us. Mark any bits in "owns" regardless of whether we - * decoded them. We can lock resources we don't decode, therefore - * we must track them via "owns". - */ - flags = 0; - pci_bits = 0; - - if (!vgadev->bridge_has_one_vga) { - flags |= PCI_VGA_STATE_CHANGE_DECODES; - if (wants & (VGA_RSRC_LEGACY_MEM|VGA_RSRC_NORMAL_MEM)) - pci_bits |= PCI_COMMAND_MEMORY; - if (wants & (VGA_RSRC_LEGACY_IO|VGA_RSRC_NORMAL_IO)) - pci_bits |= PCI_COMMAND_IO; - } - if (wants & VGA_RSRC_LEGACY_MASK) - flags |= PCI_VGA_STATE_CHANGE_BRIDGE; - - pci_set_vga_state(vgadev->pdev, true, pci_bits, flags); - - vgadev->owns |= wants; -lock_them: - vgadev->locks |= (rsrc & VGA_RSRC_LEGACY_MASK); - if (rsrc & VGA_RSRC_LEGACY_IO) - vgadev->io_lock_cnt++; - if (rsrc & VGA_RSRC_LEGACY_MEM) - vgadev->mem_lock_cnt++; - if (rsrc & VGA_RSRC_NORMAL_IO) - vgadev->io_norm_cnt++; - if (rsrc & VGA_RSRC_NORMAL_MEM) - vgadev->mem_norm_cnt++; - - return NULL; -} - -static void __vga_put(struct vga_device *vgadev, unsigned int rsrc) -{ - struct device *dev = &vgadev->pdev->dev; - unsigned int old_locks = vgadev->locks; - - vgaarb_dbg(dev, "%s\n", __func__); - - /* Update our counters, and account for equivalent legacy resources - * if we decode them - */ - if ((rsrc & VGA_RSRC_NORMAL_IO) && vgadev->io_norm_cnt > 0) { - vgadev->io_norm_cnt--; - if (vgadev->decodes & VGA_RSRC_LEGACY_IO) - rsrc |= VGA_RSRC_LEGACY_IO; - } - if ((rsrc & VGA_RSRC_NORMAL_MEM) && vgadev->mem_norm_cnt > 0) { - vgadev->mem_norm_cnt--; - if (vgadev->decodes & VGA_RSRC_LEGACY_MEM) - rsrc |= VGA_RSRC_LEGACY_MEM; - } - if ((rsrc & VGA_RSRC_LEGACY_IO) && vgadev->io_lock_cnt > 0) - vgadev->io_lock_cnt--; - if ((rsrc & VGA_RSRC_LEGACY_MEM) && vgadev->mem_lock_cnt > 0) - vgadev->mem_lock_cnt--; - - /* Just clear lock bits, we do lazy operations so we don't really - * have to bother about anything else at this point - */ - if (vgadev->io_lock_cnt == 0) - vgadev->locks &= ~VGA_RSRC_LEGACY_IO; - if (vgadev->mem_lock_cnt == 0) - vgadev->locks &= ~VGA_RSRC_LEGACY_MEM; - - /* Kick the wait queue in case somebody was waiting if we actually - * released something - */ - if (old_locks != vgadev->locks) - wake_up_all(&vga_wait_queue); -} - -/** - * vga_get - acquire & locks VGA resources - * @pdev: pci device of the VGA card or NULL for the system default - * @rsrc: bit mask of resources to acquire and lock - * @interruptible: blocking should be interruptible by signals ? - * - * This function acquires VGA resources for the given card and mark those - * resources locked. If the resource requested are "normal" (and not legacy) - * resources, the arbiter will first check whether the card is doing legacy - * decoding for that type of resource. If yes, the lock is "converted" into a - * legacy resource lock. - * - * The arbiter will first look for all VGA cards that might conflict and disable - * their IOs and/or Memory access, including VGA forwarding on P2P bridges if - * necessary, so that the requested resources can be used. Then, the card is - * marked as locking these resources and the IO and/or Memory accesses are - * enabled on the card (including VGA forwarding on parent P2P bridges if any). - * - * This function will block if some conflicting card is already locking one of - * the required resources (or any resource on a different bus segment, since P2P - * bridges don't differentiate VGA memory and IO afaik). You can indicate - * whether this blocking should be interruptible by a signal (for userland - * interface) or not. - * - * Must not be called at interrupt time or in atomic context. If the card - * already owns the resources, the function succeeds. Nested calls are - * supported (a per-resource counter is maintained) - * - * On success, release the VGA resource again with vga_put(). - * - * Returns: - * - * 0 on success, negative error code on failure. - */ -int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interruptible) -{ - struct vga_device *vgadev, *conflict; - unsigned long flags; - wait_queue_entry_t wait; - int rc = 0; - - vga_check_first_use(); - /* The one who calls us should check for this, but lets be sure... */ - if (pdev == NULL) - pdev = vga_default_device(); - if (pdev == NULL) - return 0; - - for (;;) { - spin_lock_irqsave(&vga_lock, flags); - vgadev = vgadev_find(pdev); - if (vgadev == NULL) { - spin_unlock_irqrestore(&vga_lock, flags); - rc = -ENODEV; - break; - } - conflict = __vga_tryget(vgadev, rsrc); - spin_unlock_irqrestore(&vga_lock, flags); - if (conflict == NULL) - break; - - - /* We have a conflict, we wait until somebody kicks the - * work queue. Currently we have one work queue that we - * kick each time some resources are released, but it would - * be fairly easy to have a per device one so that we only - * need to attach to the conflicting device - */ - init_waitqueue_entry(&wait, current); - add_wait_queue(&vga_wait_queue, &wait); - set_current_state(interruptible ? - TASK_INTERRUPTIBLE : - TASK_UNINTERRUPTIBLE); - if (interruptible && signal_pending(current)) { - __set_current_state(TASK_RUNNING); - remove_wait_queue(&vga_wait_queue, &wait); - rc = -ERESTARTSYS; - break; - } - schedule(); - remove_wait_queue(&vga_wait_queue, &wait); - } - return rc; -} -EXPORT_SYMBOL(vga_get); - -/** - * vga_tryget - try to acquire & lock legacy VGA resources - * @pdev: pci devivce of VGA card or NULL for system default - * @rsrc: bit mask of resources to acquire and lock - * - * This function performs the same operation as vga_get(), but will return an - * error (-EBUSY) instead of blocking if the resources are already locked by - * another card. It can be called in any context - * - * On success, release the VGA resource again with vga_put(). - * - * Returns: - * - * 0 on success, negative error code on failure. - */ -static int vga_tryget(struct pci_dev *pdev, unsigned int rsrc) -{ - struct vga_device *vgadev; - unsigned long flags; - int rc = 0; - - vga_check_first_use(); - - /* The one who calls us should check for this, but lets be sure... */ - if (pdev == NULL) - pdev = vga_default_device(); - if (pdev == NULL) - return 0; - spin_lock_irqsave(&vga_lock, flags); - vgadev = vgadev_find(pdev); - if (vgadev == NULL) { - rc = -ENODEV; - goto bail; - } - if (__vga_tryget(vgadev, rsrc)) - rc = -EBUSY; -bail: - spin_unlock_irqrestore(&vga_lock, flags); - return rc; -} - -/** - * vga_put - release lock on legacy VGA resources - * @pdev: pci device of VGA card or NULL for system default - * @rsrc: but mask of resource to release - * - * This fuction releases resources previously locked by vga_get() or - * vga_tryget(). The resources aren't disabled right away, so that a subsequence - * vga_get() on the same card will succeed immediately. Resources have a - * counter, so locks are only released if the counter reaches 0. - */ -void vga_put(struct pci_dev *pdev, unsigned int rsrc) -{ - struct vga_device *vgadev; - unsigned long flags; - - /* The one who calls us should check for this, but lets be sure... */ - if (pdev == NULL) - pdev = vga_default_device(); - if (pdev == NULL) - return; - spin_lock_irqsave(&vga_lock, flags); - vgadev = vgadev_find(pdev); - if (vgadev == NULL) - goto bail; - __vga_put(vgadev, rsrc); -bail: - spin_unlock_irqrestore(&vga_lock, flags); -} -EXPORT_SYMBOL(vga_put); - -/* - * Rules for using a bridge to control a VGA descendant decoding: if a bridge - * has only one VGA descendant then it can be used to control the VGA routing - * for that device. It should always use the bridge closest to the device to - * control it. If a bridge has a direct VGA descendant, but also have a sub- - * bridge VGA descendant then we cannot use that bridge to control the direct - * VGA descendant. So for every device we register, we need to iterate all - * its parent bridges so we can invalidate any devices using them properly. - */ -static void vga_arbiter_check_bridge_sharing(struct vga_device *vgadev) -{ - struct vga_device *same_bridge_vgadev; - struct pci_bus *new_bus, *bus; - struct pci_dev *new_bridge, *bridge; - - vgadev->bridge_has_one_vga = true; - - if (list_empty(&vga_list)) - return; - - /* okay iterate the new devices bridge hierarachy */ - new_bus = vgadev->pdev->bus; - while (new_bus) { - new_bridge = new_bus->self; - - /* go through list of devices already registered */ - list_for_each_entry(same_bridge_vgadev, &vga_list, list) { - bus = same_bridge_vgadev->pdev->bus; - bridge = bus->self; - - /* see if the share a bridge with this device */ - if (new_bridge == bridge) { - /* - * If their direct parent bridge is the same - * as any bridge of this device then it can't - * be used for that device. - */ - same_bridge_vgadev->bridge_has_one_vga = false; - } - - /* - * Now iterate the previous devices bridge hierarchy. - * If the new devices parent bridge is in the other - * devices hierarchy then we can't use it to control - * this device - */ - while (bus) { - bridge = bus->self; - - if (bridge && bridge == vgadev->pdev->bus->self) - vgadev->bridge_has_one_vga = false; - - bus = bus->parent; - } - } - new_bus = new_bus->parent; - } -} - -/* - * Currently, we assume that the "initial" setup of the system is - * not sane, that is we come up with conflicting devices and let - * the arbiter's client decides if devices decodes or not legacy - * things. - */ -static bool vga_arbiter_add_pci_device(struct pci_dev *pdev) -{ - struct vga_device *vgadev; - unsigned long flags; - struct pci_bus *bus; - struct pci_dev *bridge; - u16 cmd; - - /* Only deal with VGA class devices */ - if ((pdev->class >> 8) != PCI_CLASS_DISPLAY_VGA) - return false; - - /* Allocate structure */ - vgadev = kzalloc(sizeof(struct vga_device), GFP_KERNEL); - if (vgadev == NULL) { - vgaarb_err(&pdev->dev, "failed to allocate VGA arbiter data\n"); - /* - * What to do on allocation failure ? For now, let's just do - * nothing, I'm not sure there is anything saner to be done. - */ - return false; - } - - /* Take lock & check for duplicates */ - spin_lock_irqsave(&vga_lock, flags); - if (vgadev_find(pdev) != NULL) { - BUG_ON(1); - goto fail; - } - vgadev->pdev = pdev; - - /* By default, assume we decode everything */ - vgadev->decodes = VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM | - VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM; - - /* by default mark it as decoding */ - vga_decode_count++; - /* Mark that we "own" resources based on our enables, we will - * clear that below if the bridge isn't forwarding - */ - pci_read_config_word(pdev, PCI_COMMAND, &cmd); - if (cmd & PCI_COMMAND_IO) - vgadev->owns |= VGA_RSRC_LEGACY_IO; - if (cmd & PCI_COMMAND_MEMORY) - vgadev->owns |= VGA_RSRC_LEGACY_MEM; - - /* Check if VGA cycles can get down to us */ - bus = pdev->bus; - while (bus) { - bridge = bus->self; - if (bridge) { - u16 l; - - pci_read_config_word(bridge, PCI_BRIDGE_CONTROL, &l); - if (!(l & PCI_BRIDGE_CTL_VGA)) { - vgadev->owns = 0; - break; - } - } - bus = bus->parent; - } - - /* Deal with VGA default device. Use first enabled one - * by default if arch doesn't have it's own hook - */ - if (vga_default == NULL && - ((vgadev->owns & VGA_RSRC_LEGACY_MASK) == VGA_RSRC_LEGACY_MASK)) { - vgaarb_info(&pdev->dev, "setting as boot VGA device\n"); - vga_set_default_device(pdev); - } - - vga_arbiter_check_bridge_sharing(vgadev); - - /* Add to the list */ - list_add_tail(&vgadev->list, &vga_list); - vga_count++; - vgaarb_info(&pdev->dev, "VGA device added: decodes=%s,owns=%s,locks=%s\n", - vga_iostate_to_str(vgadev->decodes), - vga_iostate_to_str(vgadev->owns), - vga_iostate_to_str(vgadev->locks)); - - spin_unlock_irqrestore(&vga_lock, flags); - return true; -fail: - spin_unlock_irqrestore(&vga_lock, flags); - kfree(vgadev); - return false; -} - -static bool vga_arbiter_del_pci_device(struct pci_dev *pdev) -{ - struct vga_device *vgadev; - unsigned long flags; - bool ret = true; - - spin_lock_irqsave(&vga_lock, flags); - vgadev = vgadev_find(pdev); - if (vgadev == NULL) { - ret = false; - goto bail; - } - - if (vga_default == pdev) - vga_set_default_device(NULL); - - if (vgadev->decodes & (VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM)) - vga_decode_count--; - - /* Remove entry from list */ - list_del(&vgadev->list); - vga_count--; - /* Notify userland driver that the device is gone so it discards - * it's copies of the pci_dev pointer - */ - vga_arb_device_card_gone(pdev); - - /* Wake up all possible waiters */ - wake_up_all(&vga_wait_queue); -bail: - spin_unlock_irqrestore(&vga_lock, flags); - kfree(vgadev); - return ret; -} - -/* this is called with the lock */ -static inline void vga_update_device_decodes(struct vga_device *vgadev, - int new_decodes) -{ - struct device *dev = &vgadev->pdev->dev; - int old_decodes, decodes_removed, decodes_unlocked; - - old_decodes = vgadev->decodes; - decodes_removed = ~new_decodes & old_decodes; - decodes_unlocked = vgadev->locks & decodes_removed; - vgadev->decodes = new_decodes; - - vgaarb_info(dev, "changed VGA decodes: olddecodes=%s,decodes=%s:owns=%s\n", - vga_iostate_to_str(old_decodes), - vga_iostate_to_str(vgadev->decodes), - vga_iostate_to_str(vgadev->owns)); - - /* if we removed locked decodes, lock count goes to zero, and release */ - if (decodes_unlocked) { - if (decodes_unlocked & VGA_RSRC_LEGACY_IO) - vgadev->io_lock_cnt = 0; - if (decodes_unlocked & VGA_RSRC_LEGACY_MEM) - vgadev->mem_lock_cnt = 0; - __vga_put(vgadev, decodes_unlocked); - } - - /* change decodes counter */ - if (old_decodes & VGA_RSRC_LEGACY_MASK && - !(new_decodes & VGA_RSRC_LEGACY_MASK)) - vga_decode_count--; - if (!(old_decodes & VGA_RSRC_LEGACY_MASK) && - new_decodes & VGA_RSRC_LEGACY_MASK) - vga_decode_count++; - vgaarb_dbg(dev, "decoding count now is: %d\n", vga_decode_count); -} - -static void __vga_set_legacy_decoding(struct pci_dev *pdev, - unsigned int decodes, - bool userspace) -{ - struct vga_device *vgadev; - unsigned long flags; - - decodes &= VGA_RSRC_LEGACY_MASK; - - spin_lock_irqsave(&vga_lock, flags); - vgadev = vgadev_find(pdev); - if (vgadev == NULL) - goto bail; - - /* don't let userspace futz with kernel driver decodes */ - if (userspace && vgadev->set_decode) - goto bail; - - /* update the device decodes + counter */ - vga_update_device_decodes(vgadev, decodes); - - /* XXX if somebody is going from "doesn't decode" to "decodes" state - * here, additional care must be taken as we may have pending owner - * ship of non-legacy region ... - */ -bail: - spin_unlock_irqrestore(&vga_lock, flags); -} - -/** - * vga_set_legacy_decoding - * @pdev: pci device of the VGA card - * @decodes: bit mask of what legacy regions the card decodes - * - * Indicates to the arbiter if the card decodes legacy VGA IOs, legacy VGA - * Memory, both, or none. All cards default to both, the card driver (fbdev for - * example) should tell the arbiter if it has disabled legacy decoding, so the - * card can be left out of the arbitration process (and can be safe to take - * interrupts at any time. - */ -void vga_set_legacy_decoding(struct pci_dev *pdev, unsigned int decodes) -{ - __vga_set_legacy_decoding(pdev, decodes, false); -} -EXPORT_SYMBOL(vga_set_legacy_decoding); - -/** - * vga_client_register - register or unregister a VGA arbitration client - * @pdev: pci device of the VGA client - * @set_decode: vga decode change callback - * - * Clients have two callback mechanisms they can use. - * - * @set_decode callback: If a client can disable its GPU VGA resource, it - * will get a callback from this to set the encode/decode state. - * - * Rationale: we cannot disable VGA decode resources unconditionally some single - * GPU laptops seem to require ACPI or BIOS access to the VGA registers to - * control things like backlights etc. Hopefully newer multi-GPU laptops do - * something saner, and desktops won't have any special ACPI for this. The - * driver will get a callback when VGA arbitration is first used by userspace - * since some older X servers have issues. - * - * This function does not check whether a client for @pdev has been registered - * already. - * - * To unregister just call vga_client_unregister(). - * - * Returns: 0 on success, -1 on failure - */ -int vga_client_register(struct pci_dev *pdev, - unsigned int (*set_decode)(struct pci_dev *pdev, bool decode)) -{ - int ret = -ENODEV; - struct vga_device *vgadev; - unsigned long flags; - - spin_lock_irqsave(&vga_lock, flags); - vgadev = vgadev_find(pdev); - if (!vgadev) - goto bail; - - vgadev->set_decode = set_decode; - ret = 0; - -bail: - spin_unlock_irqrestore(&vga_lock, flags); - return ret; - -} -EXPORT_SYMBOL(vga_client_register); - -/* - * Char driver implementation - * - * Semantics is: - * - * open : open user instance of the arbitrer. by default, it's - * attached to the default VGA device of the system. - * - * close : close user instance, release locks - * - * read : return a string indicating the status of the target. - * an IO state string is of the form {io,mem,io+mem,none}, - * mc and ic are respectively mem and io lock counts (for - * debugging/diagnostic only). "decodes" indicate what the - * card currently decodes, "owns" indicates what is currently - * enabled on it, and "locks" indicates what is locked by this - * card. If the card is unplugged, we get "invalid" then for - * card_ID and an -ENODEV error is returned for any command - * until a new card is targeted - * - * "<card_ID>,decodes=<io_state>,owns=<io_state>,locks=<io_state> (ic,mc)" - * - * write : write a command to the arbiter. List of commands is: - * - * target <card_ID> : switch target to card <card_ID> (see below) - * lock <io_state> : acquires locks on target ("none" is invalid io_state) - * trylock <io_state> : non-blocking acquire locks on target - * unlock <io_state> : release locks on target - * unlock all : release all locks on target held by this user - * decodes <io_state> : set the legacy decoding attributes for the card - * - * poll : event if something change on any card (not just the target) - * - * card_ID is of the form "PCI:domain:bus:dev.fn". It can be set to "default" - * to go back to the system default card (TODO: not implemented yet). - * Currently, only PCI is supported as a prefix, but the userland API may - * support other bus types in the future, even if the current kernel - * implementation doesn't. - * - * Note about locks: - * - * The driver keeps track of which user has what locks on which card. It - * supports stacking, like the kernel one. This complexifies the implementation - * a bit, but makes the arbiter more tolerant to userspace problems and able - * to properly cleanup in all cases when a process dies. - * Currently, a max of 16 cards simultaneously can have locks issued from - * userspace for a given user (file descriptor instance) of the arbiter. - * - * If the device is hot-unplugged, there is a hook inside the module to notify - * they being added/removed in the system and automatically added/removed in - * the arbiter. - */ - -#define MAX_USER_CARDS CONFIG_VGA_ARB_MAX_GPUS -#define PCI_INVALID_CARD ((struct pci_dev *)-1UL) - -/* - * Each user has an array of these, tracking which cards have locks - */ -struct vga_arb_user_card { - struct pci_dev *pdev; - unsigned int mem_cnt; - unsigned int io_cnt; -}; - -struct vga_arb_private { - struct list_head list; - struct pci_dev *target; - struct vga_arb_user_card cards[MAX_USER_CARDS]; - spinlock_t lock; -}; - -static LIST_HEAD(vga_user_list); -static DEFINE_SPINLOCK(vga_user_lock); - - -/* - * This function gets a string in the format: "PCI:domain:bus:dev.fn" and - * returns the respective values. If the string is not in this format, - * it returns 0. - */ -static int vga_pci_str_to_vars(char *buf, int count, unsigned int *domain, - unsigned int *bus, unsigned int *devfn) -{ - int n; - unsigned int slot, func; - - - n = sscanf(buf, "PCI:%x:%x:%x.%x", domain, bus, &slot, &func); - if (n != 4) - return 0; - - *devfn = PCI_DEVFN(slot, func); - - return 1; -} - -static ssize_t vga_arb_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) -{ - struct vga_arb_private *priv = file->private_data; - struct vga_device *vgadev; - struct pci_dev *pdev; - unsigned long flags; - size_t len; - int rc; - char *lbuf; - - lbuf = kmalloc(1024, GFP_KERNEL); - if (lbuf == NULL) - return -ENOMEM; - - /* Shields against vga_arb_device_card_gone (pci_dev going - * away), and allows access to vga list - */ - spin_lock_irqsave(&vga_lock, flags); - - /* If we are targeting the default, use it */ - pdev = priv->target; - if (pdev == NULL || pdev == PCI_INVALID_CARD) { - spin_unlock_irqrestore(&vga_lock, flags); - len = sprintf(lbuf, "invalid"); - goto done; - } - - /* Find card vgadev structure */ - vgadev = vgadev_find(pdev); - if (vgadev == NULL) { - /* Wow, it's not in the list, that shouldn't happen, - * let's fix us up and return invalid card - */ - if (pdev == priv->target) - vga_arb_device_card_gone(pdev); - spin_unlock_irqrestore(&vga_lock, flags); - len = sprintf(lbuf, "invalid"); - goto done; - } - - /* Fill the buffer with infos */ - len = snprintf(lbuf, 1024, - "count:%d,PCI:%s,decodes=%s,owns=%s,locks=%s(%d:%d)\n", - vga_decode_count, pci_name(pdev), - vga_iostate_to_str(vgadev->decodes), - vga_iostate_to_str(vgadev->owns), - vga_iostate_to_str(vgadev->locks), - vgadev->io_lock_cnt, vgadev->mem_lock_cnt); - - spin_unlock_irqrestore(&vga_lock, flags); -done: - - /* Copy that to user */ - if (len > count) - len = count; - rc = copy_to_user(buf, lbuf, len); - kfree(lbuf); - if (rc) - return -EFAULT; - return len; -} - -/* - * TODO: To avoid parsing inside kernel and to improve the speed we may - * consider use ioctl here - */ -static ssize_t vga_arb_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct vga_arb_private *priv = file->private_data; - struct vga_arb_user_card *uc = NULL; - struct pci_dev *pdev; - - unsigned int io_state; - - char kbuf[64], *curr_pos; - size_t remaining = count; - - int ret_val; - int i; - - if (count >= sizeof(kbuf)) - return -EINVAL; - if (copy_from_user(kbuf, buf, count)) - return -EFAULT; - curr_pos = kbuf; - kbuf[count] = '\0'; /* Just to make sure... */ - - if (strncmp(curr_pos, "lock ", 5) == 0) { - curr_pos += 5; - remaining -= 5; - - pr_debug("client 0x%p called 'lock'\n", priv); - - if (!vga_str_to_iostate(curr_pos, remaining, &io_state)) { - ret_val = -EPROTO; - goto done; - } - if (io_state == VGA_RSRC_NONE) { - ret_val = -EPROTO; - goto done; - } - - pdev = priv->target; - if (priv->target == NULL) { - ret_val = -ENODEV; - goto done; - } - - vga_get_uninterruptible(pdev, io_state); - - /* Update the client's locks lists... */ - for (i = 0; i < MAX_USER_CARDS; i++) { - if (priv->cards[i].pdev == pdev) { - if (io_state & VGA_RSRC_LEGACY_IO) - priv->cards[i].io_cnt++; - if (io_state & VGA_RSRC_LEGACY_MEM) - priv->cards[i].mem_cnt++; - break; - } - } - - ret_val = count; - goto done; - } else if (strncmp(curr_pos, "unlock ", 7) == 0) { - curr_pos += 7; - remaining -= 7; - - pr_debug("client 0x%p called 'unlock'\n", priv); - - if (strncmp(curr_pos, "all", 3) == 0) - io_state = VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM; - else { - if (!vga_str_to_iostate - (curr_pos, remaining, &io_state)) { - ret_val = -EPROTO; - goto done; - } - /* TODO: Add this? - if (io_state == VGA_RSRC_NONE) { - ret_val = -EPROTO; - goto done; - } - */ - } - - pdev = priv->target; - if (priv->target == NULL) { - ret_val = -ENODEV; - goto done; - } - for (i = 0; i < MAX_USER_CARDS; i++) { - if (priv->cards[i].pdev == pdev) - uc = &priv->cards[i]; - } - - if (!uc) { - ret_val = -EINVAL; - goto done; - } - - if (io_state & VGA_RSRC_LEGACY_IO && uc->io_cnt == 0) { - ret_val = -EINVAL; - goto done; - } - - if (io_state & VGA_RSRC_LEGACY_MEM && uc->mem_cnt == 0) { - ret_val = -EINVAL; - goto done; - } - - vga_put(pdev, io_state); - - if (io_state & VGA_RSRC_LEGACY_IO) - uc->io_cnt--; - if (io_state & VGA_RSRC_LEGACY_MEM) - uc->mem_cnt--; - - ret_val = count; - goto done; - } else if (strncmp(curr_pos, "trylock ", 8) == 0) { - curr_pos += 8; - remaining -= 8; - - pr_debug("client 0x%p called 'trylock'\n", priv); - - if (!vga_str_to_iostate(curr_pos, remaining, &io_state)) { - ret_val = -EPROTO; - goto done; - } - /* TODO: Add this? - if (io_state == VGA_RSRC_NONE) { - ret_val = -EPROTO; - goto done; - } - */ - - pdev = priv->target; - if (priv->target == NULL) { - ret_val = -ENODEV; - goto done; - } - - if (vga_tryget(pdev, io_state)) { - /* Update the client's locks lists... */ - for (i = 0; i < MAX_USER_CARDS; i++) { - if (priv->cards[i].pdev == pdev) { - if (io_state & VGA_RSRC_LEGACY_IO) - priv->cards[i].io_cnt++; - if (io_state & VGA_RSRC_LEGACY_MEM) - priv->cards[i].mem_cnt++; - break; - } - } - ret_val = count; - goto done; - } else { - ret_val = -EBUSY; - goto done; - } - - } else if (strncmp(curr_pos, "target ", 7) == 0) { - unsigned int domain, bus, devfn; - struct vga_device *vgadev; - - curr_pos += 7; - remaining -= 7; - pr_debug("client 0x%p called 'target'\n", priv); - /* if target is default */ - if (!strncmp(curr_pos, "default", 7)) - pdev = pci_dev_get(vga_default_device()); - else { - if (!vga_pci_str_to_vars(curr_pos, remaining, - &domain, &bus, &devfn)) { - ret_val = -EPROTO; - goto done; - } - pdev = pci_get_domain_bus_and_slot(domain, bus, devfn); - if (!pdev) { - pr_debug("invalid PCI address %04x:%02x:%02x.%x\n", - domain, bus, PCI_SLOT(devfn), - PCI_FUNC(devfn)); - ret_val = -ENODEV; - goto done; - } - - pr_debug("%s ==> %04x:%02x:%02x.%x pdev %p\n", curr_pos, - domain, bus, PCI_SLOT(devfn), PCI_FUNC(devfn), - pdev); - } - - vgadev = vgadev_find(pdev); - pr_debug("vgadev %p\n", vgadev); - if (vgadev == NULL) { - if (pdev) { - vgaarb_dbg(&pdev->dev, "not a VGA device\n"); - pci_dev_put(pdev); - } - - ret_val = -ENODEV; - goto done; - } - - priv->target = pdev; - for (i = 0; i < MAX_USER_CARDS; i++) { - if (priv->cards[i].pdev == pdev) - break; - if (priv->cards[i].pdev == NULL) { - priv->cards[i].pdev = pdev; - priv->cards[i].io_cnt = 0; - priv->cards[i].mem_cnt = 0; - break; - } - } - if (i == MAX_USER_CARDS) { - vgaarb_dbg(&pdev->dev, "maximum user cards (%d) number reached, ignoring this one!\n", - MAX_USER_CARDS); - pci_dev_put(pdev); - /* XXX: which value to return? */ - ret_val = -ENOMEM; - goto done; - } - - ret_val = count; - pci_dev_put(pdev); - goto done; - - - } else if (strncmp(curr_pos, "decodes ", 8) == 0) { - curr_pos += 8; - remaining -= 8; - pr_debug("client 0x%p called 'decodes'\n", priv); - - if (!vga_str_to_iostate(curr_pos, remaining, &io_state)) { - ret_val = -EPROTO; - goto done; - } - pdev = priv->target; - if (priv->target == NULL) { - ret_val = -ENODEV; - goto done; - } - - __vga_set_legacy_decoding(pdev, io_state, true); - ret_val = count; - goto done; - } - /* If we got here, the message written is not part of the protocol! */ - return -EPROTO; - -done: - return ret_val; -} - -static __poll_t vga_arb_fpoll(struct file *file, poll_table *wait) -{ - pr_debug("%s\n", __func__); - - poll_wait(file, &vga_wait_queue, wait); - return EPOLLIN; -} - -static int vga_arb_open(struct inode *inode, struct file *file) -{ - struct vga_arb_private *priv; - unsigned long flags; - - pr_debug("%s\n", __func__); - - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (priv == NULL) - return -ENOMEM; - spin_lock_init(&priv->lock); - file->private_data = priv; - - spin_lock_irqsave(&vga_user_lock, flags); - list_add(&priv->list, &vga_user_list); - spin_unlock_irqrestore(&vga_user_lock, flags); - - /* Set the client' lists of locks */ - priv->target = vga_default_device(); /* Maybe this is still null! */ - priv->cards[0].pdev = priv->target; - priv->cards[0].io_cnt = 0; - priv->cards[0].mem_cnt = 0; - - - return 0; -} - -static int vga_arb_release(struct inode *inode, struct file *file) -{ - struct vga_arb_private *priv = file->private_data; - struct vga_arb_user_card *uc; - unsigned long flags; - int i; - - pr_debug("%s\n", __func__); - - spin_lock_irqsave(&vga_user_lock, flags); - list_del(&priv->list); - for (i = 0; i < MAX_USER_CARDS; i++) { - uc = &priv->cards[i]; - if (uc->pdev == NULL) - continue; - vgaarb_dbg(&uc->pdev->dev, "uc->io_cnt == %d, uc->mem_cnt == %d\n", - uc->io_cnt, uc->mem_cnt); - while (uc->io_cnt--) - vga_put(uc->pdev, VGA_RSRC_LEGACY_IO); - while (uc->mem_cnt--) - vga_put(uc->pdev, VGA_RSRC_LEGACY_MEM); - } - spin_unlock_irqrestore(&vga_user_lock, flags); - - kfree(priv); - - return 0; -} - -static void vga_arb_device_card_gone(struct pci_dev *pdev) -{ -} - -/* - * callback any registered clients to let them know we have a - * change in VGA cards - */ -static void vga_arbiter_notify_clients(void) -{ - struct vga_device *vgadev; - unsigned long flags; - uint32_t new_decodes; - bool new_state; - - if (!vga_arbiter_used) - return; - - spin_lock_irqsave(&vga_lock, flags); - list_for_each_entry(vgadev, &vga_list, list) { - if (vga_count > 1) - new_state = false; - else - new_state = true; - if (vgadev->set_decode) { - new_decodes = vgadev->set_decode(vgadev->pdev, - new_state); - vga_update_device_decodes(vgadev, new_decodes); - } - } - spin_unlock_irqrestore(&vga_lock, flags); -} - -static int pci_notify(struct notifier_block *nb, unsigned long action, - void *data) -{ - struct device *dev = data; - struct pci_dev *pdev = to_pci_dev(dev); - bool notify = false; - - vgaarb_dbg(dev, "%s\n", __func__); - - /* For now we're only intereted in devices added and removed. I didn't - * test this thing here, so someone needs to double check for the - * cases of hotplugable vga cards. */ - if (action == BUS_NOTIFY_ADD_DEVICE) - notify = vga_arbiter_add_pci_device(pdev); - else if (action == BUS_NOTIFY_DEL_DEVICE) - notify = vga_arbiter_del_pci_device(pdev); - - if (notify) - vga_arbiter_notify_clients(); - return 0; -} - -static struct notifier_block pci_notifier = { - .notifier_call = pci_notify, -}; - -static const struct file_operations vga_arb_device_fops = { - .read = vga_arb_read, - .write = vga_arb_write, - .poll = vga_arb_fpoll, - .open = vga_arb_open, - .release = vga_arb_release, - .llseek = noop_llseek, -}; - -static struct miscdevice vga_arb_device = { - MISC_DYNAMIC_MINOR, "vga_arbiter", &vga_arb_device_fops -}; - -#if defined(CONFIG_ACPI) -static bool vga_arb_integrated_gpu(struct device *dev) -{ - struct acpi_device *adev = ACPI_COMPANION(dev); - - return adev && !strcmp(acpi_device_hid(adev), ACPI_VIDEO_HID); -} -#else -static bool vga_arb_integrated_gpu(struct device *dev) -{ - return false; -} -#endif - -static void __init vga_arb_select_default_device(void) -{ - struct pci_dev *pdev, *found = NULL; - struct vga_device *vgadev; - -#if defined(CONFIG_X86) || defined(CONFIG_IA64) - u64 base = screen_info.lfb_base; - u64 size = screen_info.lfb_size; - u64 limit; - resource_size_t start, end; - unsigned long flags; - int i; - - if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE) - base |= (u64)screen_info.ext_lfb_base << 32; - - limit = base + size; - - list_for_each_entry(vgadev, &vga_list, list) { - struct device *dev = &vgadev->pdev->dev; - /* - * Override vga_arbiter_add_pci_device()'s I/O based detection - * as it may take the wrong device (e.g. on Apple system under - * EFI). - * - * Select the device owning the boot framebuffer if there is - * one. - */ - - /* Does firmware framebuffer belong to us? */ - for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { - flags = pci_resource_flags(vgadev->pdev, i); - - if ((flags & IORESOURCE_MEM) == 0) - continue; - - start = pci_resource_start(vgadev->pdev, i); - end = pci_resource_end(vgadev->pdev, i); - - if (!start || !end) - continue; - - if (base < start || limit >= end) - continue; - - if (!vga_default_device()) - vgaarb_info(dev, "setting as boot device\n"); - else if (vgadev->pdev != vga_default_device()) - vgaarb_info(dev, "overriding boot device\n"); - vga_set_default_device(vgadev->pdev); - } - } -#endif - - if (!vga_default_device()) { - list_for_each_entry_reverse(vgadev, &vga_list, list) { - struct device *dev = &vgadev->pdev->dev; - u16 cmd; - - pdev = vgadev->pdev; - pci_read_config_word(pdev, PCI_COMMAND, &cmd); - if (cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) { - found = pdev; - if (vga_arb_integrated_gpu(dev)) - break; - } - } - } - - if (found) { - vgaarb_info(&found->dev, "setting as boot device (VGA legacy resources not available)\n"); - vga_set_default_device(found); - return; - } - - if (!vga_default_device()) { - vgadev = list_first_entry_or_null(&vga_list, - struct vga_device, list); - if (vgadev) { - struct device *dev = &vgadev->pdev->dev; - vgaarb_info(dev, "setting as boot device (VGA legacy resources not available)\n"); - vga_set_default_device(vgadev->pdev); - } - } -} - -static int __init vga_arb_device_init(void) -{ - int rc; - struct pci_dev *pdev; - struct vga_device *vgadev; - - rc = misc_register(&vga_arb_device); - if (rc < 0) - pr_err("error %d registering device\n", rc); - - bus_register_notifier(&pci_bus_type, &pci_notifier); - - /* We add all PCI devices satisfying VGA class in the arbiter by - * default */ - pdev = NULL; - while ((pdev = - pci_get_subsys(PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, - PCI_ANY_ID, pdev)) != NULL) - vga_arbiter_add_pci_device(pdev); - - list_for_each_entry(vgadev, &vga_list, list) { - struct device *dev = &vgadev->pdev->dev; - - if (vgadev->bridge_has_one_vga) - vgaarb_info(dev, "bridge control possible\n"); - else - vgaarb_info(dev, "no bridge control possible\n"); - } - - vga_arb_select_default_device(); - - pr_info("loaded\n"); - return rc; -} -subsys_initcall(vga_arb_device_init); |