diff options
Diffstat (limited to 'drivers/gpu')
125 files changed, 1342 insertions, 765 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index fbe7616555c8..a2879d2b7c8e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -250,16 +250,24 @@ void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev, void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool suspend_proc) { - if (adev->kfd.dev) - kgd2kfd_suspend(adev->kfd.dev, suspend_proc); + if (adev->kfd.dev) { + if (adev->in_s0ix) + kgd2kfd_stop_sched_all_nodes(adev->kfd.dev); + else + kgd2kfd_suspend(adev->kfd.dev, suspend_proc); + } } int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool resume_proc) { int r = 0; - if (adev->kfd.dev) - r = kgd2kfd_resume(adev->kfd.dev, resume_proc); + if (adev->kfd.dev) { + if (adev->in_s0ix) + r = kgd2kfd_start_sched_all_nodes(adev->kfd.dev); + else + r = kgd2kfd_resume(adev->kfd.dev, resume_proc); + } return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 33eb4826b58b..aa88bad7416b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -426,7 +426,9 @@ void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint64_t throttle_bitmask); int kgd2kfd_check_and_lock_kfd(struct kfd_dev *kfd); void kgd2kfd_unlock_kfd(struct kfd_dev *kfd); int kgd2kfd_start_sched(struct kfd_dev *kfd, uint32_t node_id); +int kgd2kfd_start_sched_all_nodes(struct kfd_dev *kfd); int kgd2kfd_stop_sched(struct kfd_dev *kfd, uint32_t node_id); +int kgd2kfd_stop_sched_all_nodes(struct kfd_dev *kfd); bool kgd2kfd_compute_active(struct kfd_dev *kfd, uint32_t node_id); bool kgd2kfd_vmfault_fast_path(struct amdgpu_device *adev, struct amdgpu_iv_entry *entry, bool retry_fault); @@ -516,11 +518,21 @@ static inline int kgd2kfd_start_sched(struct kfd_dev *kfd, uint32_t node_id) return 0; } +static inline int kgd2kfd_start_sched_all_nodes(struct kfd_dev *kfd) +{ + return 0; +} + static inline int kgd2kfd_stop_sched(struct kfd_dev *kfd, uint32_t node_id) { return 0; } +static inline int kgd2kfd_stop_sched_all_nodes(struct kfd_dev *kfd) +{ + return 0; +} + static inline bool kgd2kfd_compute_active(struct kfd_dev *kfd, uint32_t node_id) { return false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 260165bbe373..b16cce7c22c3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -213,19 +213,35 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, spin_lock(&kfd_mem_limit.mem_limit_lock); if (kfd_mem_limit.system_mem_used + system_mem_needed > - kfd_mem_limit.max_system_mem_limit) + kfd_mem_limit.max_system_mem_limit) { pr_debug("Set no_system_mem_limit=1 if using shared memory\n"); + if (!no_system_mem_limit) { + ret = -ENOMEM; + goto release; + } + } - if ((kfd_mem_limit.system_mem_used + system_mem_needed > - kfd_mem_limit.max_system_mem_limit && !no_system_mem_limit) || - (kfd_mem_limit.ttm_mem_used + ttm_mem_needed > - kfd_mem_limit.max_ttm_mem_limit) || - (adev && xcp_id >= 0 && adev->kfd.vram_used[xcp_id] + vram_needed > - vram_size - reserved_for_pt - reserved_for_ras - atomic64_read(&adev->vram_pin_size))) { + if (kfd_mem_limit.ttm_mem_used + ttm_mem_needed > + kfd_mem_limit.max_ttm_mem_limit) { ret = -ENOMEM; goto release; } + /*if is_app_apu is false and apu_prefer_gtt is true, it is an APU with + * carve out < gtt. In that case, VRAM allocation will go to gtt domain, skip + * VRAM check since ttm_mem_limit check already cover this allocation + */ + + if (adev && xcp_id >= 0 && (!adev->apu_prefer_gtt || adev->gmc.is_app_apu)) { + uint64_t vram_available = + vram_size - reserved_for_pt - reserved_for_ras - + atomic64_read(&adev->vram_pin_size); + if (adev->kfd.vram_used[xcp_id] + vram_needed > vram_available) { + ret = -ENOMEM; + goto release; + } + } + /* Update memory accounting by decreasing available system * memory, TTM memory and GPU memory as computed above */ @@ -1626,11 +1642,15 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev, uint64_t vram_available, system_mem_available, ttm_mem_available; spin_lock(&kfd_mem_limit.mem_limit_lock); - vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id) - - adev->kfd.vram_used_aligned[xcp_id] - - atomic64_read(&adev->vram_pin_size) - - reserved_for_pt - - reserved_for_ras; + if (adev->apu_prefer_gtt && !adev->gmc.is_app_apu) + vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id) + - adev->kfd.vram_used_aligned[xcp_id]; + else + vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id) + - adev->kfd.vram_used_aligned[xcp_id] + - atomic64_read(&adev->vram_pin_size) + - reserved_for_pt + - reserved_for_ras; if (adev->apu_prefer_gtt) { system_mem_available = no_system_mem_limit ? diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c index dfb6cfd83760..02138aa55793 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c @@ -88,8 +88,8 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm, } r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, size, - AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE | - AMDGPU_VM_PAGE_EXECUTABLE); + AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE | + AMDGPU_PTE_EXECUTABLE); if (r) { DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 01d234cf8156..c8459337fcb8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5136,7 +5136,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients) adev->in_suspend = true; if (amdgpu_sriov_vf(adev)) { - if (!adev->in_s0ix && !adev->in_runpm) + if (!adev->in_runpm) amdgpu_amdkfd_suspend_process(adev); amdgpu_virt_fini_data_exchange(adev); r = amdgpu_virt_request_full_gpu(adev, false); @@ -5156,10 +5156,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients) amdgpu_device_ip_suspend_phase1(adev); - if (!adev->in_s0ix) { - amdgpu_amdkfd_suspend(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm); - amdgpu_userq_suspend(adev); - } + amdgpu_amdkfd_suspend(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm); + amdgpu_userq_suspend(adev); r = amdgpu_device_evict_resources(adev); if (r) @@ -5254,15 +5252,13 @@ int amdgpu_device_resume(struct drm_device *dev, bool notify_clients) goto exit; } - if (!adev->in_s0ix) { - r = amdgpu_amdkfd_resume(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm); - if (r) - goto exit; + r = amdgpu_amdkfd_resume(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm); + if (r) + goto exit; - r = amdgpu_userq_resume(adev); - if (r) - goto exit; - } + r = amdgpu_userq_resume(adev); + if (r) + goto exit; r = amdgpu_device_ip_late_init(adev); if (r) @@ -5275,7 +5271,7 @@ exit: amdgpu_virt_init_data_exchange(adev); amdgpu_virt_release_full_gpu(adev, true); - if (!adev->in_s0ix && !r && !adev->in_runpm) + if (!r && !adev->in_runpm) r = amdgpu_amdkfd_resume_process(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 5743ebb2f1b7..ce27cb5bb05e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -285,6 +285,36 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf, return ret; } +static int amdgpu_dma_buf_vmap(struct dma_buf *dma_buf, struct iosys_map *map) +{ + struct drm_gem_object *obj = dma_buf->priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + int ret; + + /* + * Pin to keep buffer in place while it's vmap'ed. The actual + * domain is not that important as long as it's mapable. Using + * GTT and VRAM should be compatible with most use cases. + */ + ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT | AMDGPU_GEM_DOMAIN_VRAM); + if (ret) + return ret; + ret = drm_gem_dmabuf_vmap(dma_buf, map); + if (ret) + amdgpu_bo_unpin(bo); + + return ret; +} + +static void amdgpu_dma_buf_vunmap(struct dma_buf *dma_buf, struct iosys_map *map) +{ + struct drm_gem_object *obj = dma_buf->priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + + drm_gem_dmabuf_vunmap(dma_buf, map); + amdgpu_bo_unpin(bo); +} + const struct dma_buf_ops amdgpu_dmabuf_ops = { .attach = amdgpu_dma_buf_attach, .pin = amdgpu_dma_buf_pin, @@ -294,8 +324,8 @@ const struct dma_buf_ops amdgpu_dmabuf_ops = { .release = drm_gem_dmabuf_release, .begin_cpu_access = amdgpu_dma_buf_begin_cpu_access, .mmap = drm_gem_dmabuf_mmap, - .vmap = drm_gem_dmabuf_vmap, - .vunmap = drm_gem_dmabuf_vunmap, + .vmap = amdgpu_dma_buf_vmap, + .vunmap = amdgpu_dma_buf_vunmap, }; /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 23484317a5fa..693357caa9a8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -448,7 +448,7 @@ static int psp_sw_init(struct amdgpu_ip_block *ip_block) psp->cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL); if (!psp->cmd) { dev_err(adev->dev, "Failed to allocate memory to command buffer!\n"); - ret = -ENOMEM; + return -ENOMEM; } adev->psp.xgmi_context.supports_extended_data = diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 6379bb25bf5c..486c3646710c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -421,8 +421,6 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring) dma_fence_put(ring->vmid_wait); ring->vmid_wait = NULL; ring->me = 0; - - ring->adev->rings[ring->idx] = NULL; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index c3ace8030530..8190c24a649a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -471,6 +471,7 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args) if (index == (uint64_t)-EINVAL) { drm_file_err(uq_mgr->file, "Failed to get doorbell for queue\n"); kfree(queue); + r = -EINVAL; goto unlock; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index bf7c22f81cda..ba73518f5cdf 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -1462,17 +1462,12 @@ static int dce_v10_0_audio_init(struct amdgpu_device *adev) static void dce_v10_0_audio_fini(struct amdgpu_device *adev) { - int i; - if (!amdgpu_audio) return; if (!adev->mode_info.audio.enabled) return; - for (i = 0; i < adev->mode_info.audio.num_pins; i++) - dce_v10_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); - adev->mode_info.audio.enabled = false; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 47e05783c4a0..b01d88d078fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -1511,17 +1511,12 @@ static int dce_v11_0_audio_init(struct amdgpu_device *adev) static void dce_v11_0_audio_fini(struct amdgpu_device *adev) { - int i; - if (!amdgpu_audio) return; if (!adev->mode_info.audio.enabled) return; - for (i = 0; i < adev->mode_info.audio.num_pins; i++) - dce_v11_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); - adev->mode_info.audio.enabled = false; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index 276c025c4c03..81760a26f2ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -1451,17 +1451,12 @@ static int dce_v6_0_audio_init(struct amdgpu_device *adev) static void dce_v6_0_audio_fini(struct amdgpu_device *adev) { - int i; - if (!amdgpu_audio) return; if (!adev->mode_info.audio.enabled) return; - for (i = 0; i < adev->mode_info.audio.num_pins; i++) - dce_v6_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); - adev->mode_info.audio.enabled = false; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index e62ccf9eb73d..19a265bd4d19 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -1443,17 +1443,12 @@ static int dce_v8_0_audio_init(struct amdgpu_device *adev) static void dce_v8_0_audio_fini(struct amdgpu_device *adev) { - int i; - if (!amdgpu_audio) return; if (!adev->mode_info.audio.enabled) return; - for (i = 0; i < adev->mode_info.audio.num_pins; i++) - dce_v8_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); - adev->mode_info.audio.enabled = false; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index c01c241a1b06..c37527704d43 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1612,9 +1612,9 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block) case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): if (!adev->gfx.disable_uq && - adev->gfx.me_fw_version >= 2390 && - adev->gfx.pfp_fw_version >= 2530 && - adev->gfx.mec_fw_version >= 2600 && + adev->gfx.me_fw_version >= 2420 && + adev->gfx.pfp_fw_version >= 2580 && + adev->gfx.mec_fw_version >= 2650 && adev->mes.fw_version[0] >= 120) { adev->userq_funcs[AMDGPU_HW_IP_GFX] = &userq_mes_funcs; adev->userq_funcs[AMDGPU_HW_IP_COMPUTE] = &userq_mes_funcs; @@ -1654,6 +1654,21 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block) } } break; + case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 4): + adev->gfx.cleaner_shader_ptr = gfx_11_0_3_cleaner_shader_hex; + adev->gfx.cleaner_shader_size = sizeof(gfx_11_0_3_cleaner_shader_hex); + if (adev->gfx.pfp_fw_version >= 102 && + adev->gfx.mec_fw_version >= 66 && + adev->mes.fw_version[0] >= 128) { + adev->gfx.enable_cleaner_shader = true; + r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size); + if (r) { + adev->gfx.enable_cleaner_shader = false; + dev_err(adev->dev, "Failed to initialize cleaner shader\n"); + } + } + break; case IP_VERSION(11, 5, 0): case IP_VERSION(11, 5, 1): adev->gfx.cleaner_shader_ptr = gfx_11_0_3_cleaner_shader_hex; @@ -4129,6 +4144,8 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m, #endif if (prop->tmz_queue) tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, TMZ_MATCH, 1); + if (!prop->kernel_queue) + tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_NON_PRIV, 1); mqd->cp_gfx_hqd_cntl = tmp; /* set up cp_doorbell_control */ @@ -4281,8 +4298,10 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m, tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH, prop->allow_tunneling); - tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1); - tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1); + if (prop->kernel_queue) { + tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1); + tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1); + } if (prop->tmz_queue) tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TMZ, 1); mqd->cp_hqd_pq_control = tmp; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 3e138527d534..fd44d5503e28 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -3026,6 +3026,8 @@ static int gfx_v12_0_gfx_mqd_init(struct amdgpu_device *adev, void *m, #endif if (prop->tmz_queue) tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, TMZ_MATCH, 1); + if (!prop->kernel_queue) + tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_NON_PRIV, 1); mqd->cp_gfx_hqd_cntl = tmp; /* set up cp_doorbell_control */ @@ -3175,8 +3177,10 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m, (order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1)); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH, 0); - tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1); - tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1); + if (prop->kernel_queue) { + tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1); + tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1); + } if (prop->tmz_queue) tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TMZ, 1); mqd->cp_hqd_pq_control = tmp; diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c index a887df520414..4258d3e0b706 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c @@ -29,6 +29,8 @@ #include "amdgpu.h" #include "isp_v4_1_1.h" +MODULE_FIRMWARE("amdgpu/isp_4_1_1.bin"); + #define ISP_PERFORMANCE_STATE_LOW 0 #define ISP_PERFORMANCE_STATE_HIGH 1 diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 28eb846280dd..3f6a828cad8a 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -641,8 +641,9 @@ static int mes_v11_0_misc_op(struct amdgpu_mes *mes, break; case MES_MISC_OP_CHANGE_CONFIG: if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) < 0x63) { - dev_err(mes->adev->dev, "MES FW version must be larger than 0x63 to support limit single process feature.\n"); - return -EINVAL; + dev_warn_once(mes->adev->dev, + "MES FW version must be larger than 0x63 to support limit single process feature.\n"); + return 0; } misc_pkt.opcode = MESAPI_MISC__CHANGE_CONFIG; misc_pkt.change_config.opcode = diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index 6cc05d36e359..64b240b51f1a 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -149,12 +149,12 @@ static int psp_v11_0_wait_for_bootloader(struct psp_context *psp) int ret; int retry_loop; - for (retry_loop = 0; retry_loop < 10; retry_loop++) { + for (retry_loop = 0; retry_loop < 20; retry_loop++) { /* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */ ret = psp_wait_for( psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35), - 0x80000000, 0x80000000, PSP_WAITREG_NOVERBOSE); + 0x80000000, 0x8000FFFF, PSP_WAITREG_NOVERBOSE); if (ret == 0) return 0; @@ -397,18 +397,6 @@ static int psp_v11_0_mode1_reset(struct psp_context *psp) msleep(500); - offset = SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_33); - - ret = psp_wait_for(psp, offset, MBOX_TOS_RESP_FLAG, MBOX_TOS_RESP_MASK, - 0); - - if (ret) { - DRM_INFO("psp mode 1 reset failed!\n"); - return -EINVAL; - } - - DRM_INFO("psp mode1 reset succeed \n"); - return 0; } @@ -665,7 +653,8 @@ static const struct psp_funcs psp_v11_0_funcs = { .ring_get_wptr = psp_v11_0_ring_get_wptr, .ring_set_wptr = psp_v11_0_ring_set_wptr, .load_usbc_pd_fw = psp_v11_0_load_usbc_pd_fw, - .read_usbc_pd_fw = psp_v11_0_read_usbc_pd_fw + .read_usbc_pd_fw = psp_v11_0_read_usbc_pd_fw, + .wait_for_bootloader = psp_v11_0_wait_for_bootloader }; void psp_v11_0_set_psp_funcs(struct psp_context *psp) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index e6d8eddda2bf..db6e41967f12 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1377,7 +1377,7 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block) switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) { case IP_VERSION(6, 0, 0): - if ((adev->sdma.instance[0].fw_version >= 24) && !adev->sdma.disable_uq) + if ((adev->sdma.instance[0].fw_version >= 27) && !adev->sdma.disable_uq) adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; break; case IP_VERSION(6, 0, 1): @@ -1385,11 +1385,11 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block) adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; break; case IP_VERSION(6, 0, 2): - if ((adev->sdma.instance[0].fw_version >= 21) && !adev->sdma.disable_uq) + if ((adev->sdma.instance[0].fw_version >= 23) && !adev->sdma.disable_uq) adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; break; case IP_VERSION(6, 0, 3): - if ((adev->sdma.instance[0].fw_version >= 25) && !adev->sdma.disable_uq) + if ((adev->sdma.instance[0].fw_version >= 27) && !adev->sdma.disable_uq) adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; break; case IP_VERSION(6, 1, 0): diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 4b8f4407047f..2811226b0ea5 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1888,15 +1888,19 @@ 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(&job->base.entity->fence_seq)) - return -EINVAL; + struct dma_fence *fence; /* if VCN0 is harvested, we can't support AV1 */ if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) return -EINVAL; + /* wait for all jobs to finish before switching to instance 0 */ + fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull); + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC] [AMDGPU_RING_PRIO_DEFAULT].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 1924e075b66f..706f3b2f484f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -1808,15 +1808,19 @@ static int vcn_v4_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(&job->base.entity->fence_seq)) - return -EINVAL; + struct dma_fence *fence; /* if VCN0 is harvested, we can't support AV1 */ if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) return -EINVAL; + /* wait for all jobs to finish before switching to instance 0 */ + fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull); + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC] [AMDGPU_RING_PRIO_0].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); @@ -1907,22 +1911,16 @@ out: #define RADEON_VCN_ENGINE_TYPE_ENCODE (0x00000002) #define RADEON_VCN_ENGINE_TYPE_DECODE (0x00000003) - #define RADEON_VCN_ENGINE_INFO (0x30000001) -#define RADEON_VCN_ENGINE_INFO_MAX_OFFSET 16 - #define RENCODE_ENCODE_STANDARD_AV1 2 #define RENCODE_IB_PARAM_SESSION_INIT 0x00000003 -#define RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET 64 -/* return the offset in ib if id is found, -1 otherwise - * to speed up the searching we only search upto max_offset - */ -static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int max_offset) +/* return the offset in ib if id is found, -1 otherwise */ +static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int start) { int i; - for (i = 0; i < ib->length_dw && i < max_offset && ib->ptr[i] >= 8; i += ib->ptr[i]/4) { + for (i = start; i < ib->length_dw && ib->ptr[i] >= 8; i += ib->ptr[i] / 4) { if (ib->ptr[i + 1] == id) return i; } @@ -1937,33 +1935,29 @@ static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_vcn_decode_buffer *decode_buffer; uint64_t addr; uint32_t val; - int idx; + int idx = 0, sidx; /* The first instance can decode anything */ if (!ring->me) return 0; - /* RADEON_VCN_ENGINE_INFO is at the top of ib block */ - idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, - RADEON_VCN_ENGINE_INFO_MAX_OFFSET); - if (idx < 0) /* engine info is missing */ - return 0; + while ((idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, idx)) >= 0) { + val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ + if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { + decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; - val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ - if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { - decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; + if (!(decode_buffer->valid_buf_flag & 0x1)) + return 0; - if (!(decode_buffer->valid_buf_flag & 0x1)) - return 0; - - addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | - decode_buffer->msg_buffer_address_lo; - return vcn_v4_0_dec_msg(p, job, addr); - } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { - idx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, - RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET); - if (idx >= 0 && ib->ptr[idx + 2] == RENCODE_ENCODE_STANDARD_AV1) - return vcn_v4_0_limit_sched(p, job); + addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | + decode_buffer->msg_buffer_address_lo; + return vcn_v4_0_dec_msg(p, job, addr); + } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { + sidx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, idx); + if (sidx >= 0 && ib->ptr[sidx + 2] == RENCODE_ENCODE_STANDARD_AV1) + return vcn_v4_0_limit_sched(p, job); + } + idx += ib->ptr[idx] / 4; } return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 7e749f9b6d69..349c351e242b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -1550,6 +1550,25 @@ int kgd2kfd_start_sched(struct kfd_dev *kfd, uint32_t node_id) return ret; } +int kgd2kfd_start_sched_all_nodes(struct kfd_dev *kfd) +{ + struct kfd_node *node; + int i, r; + + if (!kfd->init_complete) + return 0; + + for (i = 0; i < kfd->num_nodes; i++) { + node = kfd->nodes[i]; + r = node->dqm->ops.unhalt(node->dqm); + if (r) { + dev_err(kfd_device, "Error in starting scheduler\n"); + return r; + } + } + return 0; +} + int kgd2kfd_stop_sched(struct kfd_dev *kfd, uint32_t node_id) { struct kfd_node *node; @@ -1567,6 +1586,23 @@ int kgd2kfd_stop_sched(struct kfd_dev *kfd, uint32_t node_id) return node->dqm->ops.halt(node->dqm); } +int kgd2kfd_stop_sched_all_nodes(struct kfd_dev *kfd) +{ + struct kfd_node *node; + int i, r; + + if (!kfd->init_complete) + return 0; + + for (i = 0; i < kfd->num_nodes; i++) { + node = kfd->nodes[i]; + r = node->dqm->ops.halt(node->dqm); + if (r) + return r; + } + return 0; +} + bool kgd2kfd_compute_active(struct kfd_dev *kfd, uint32_t node_id) { struct kfd_node *node; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 4ec73f33535e..720b20e842ba 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -1587,7 +1587,8 @@ static int kfd_dev_create_p2p_links(void) break; if (!dev->gpu || !dev->gpu->adev || (dev->gpu->kfd->hive_id && - dev->gpu->kfd->hive_id == new_dev->gpu->kfd->hive_id)) + dev->gpu->kfd->hive_id == new_dev->gpu->kfd->hive_id && + amdgpu_xgmi_get_is_sharing_enabled(dev->gpu->adev, new_dev->gpu->adev))) goto next; /* check if node(s) is/are peer accessible in one direction or bi-direction */ 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 a0ca3b2c6bd8..97d9eba17963 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2913,6 +2913,17 @@ static int dm_oem_i2c_hw_init(struct amdgpu_device *adev) return 0; } +static void dm_oem_i2c_hw_fini(struct amdgpu_device *adev) +{ + struct amdgpu_display_manager *dm = &adev->dm; + + if (dm->oem_i2c) { + i2c_del_adapter(&dm->oem_i2c->base); + kfree(dm->oem_i2c); + dm->oem_i2c = NULL; + } +} + /** * dm_hw_init() - Initialize DC device * @ip_block: Pointer to the amdgpu_ip_block for this hw instance. @@ -2963,7 +2974,7 @@ static int dm_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; - kfree(adev->dm.oem_i2c); + dm_oem_i2c_hw_fini(adev); amdgpu_dm_hpd_fini(adev); @@ -3127,25 +3138,6 @@ static void dm_destroy_cached_state(struct amdgpu_device *adev) dm->cached_state = NULL; } -static void dm_complete(struct amdgpu_ip_block *ip_block) -{ - struct amdgpu_device *adev = ip_block->adev; - - dm_destroy_cached_state(adev); -} - -static int dm_prepare_suspend(struct amdgpu_ip_block *ip_block) -{ - struct amdgpu_device *adev = ip_block->adev; - - if (amdgpu_in_reset(adev)) - return 0; - - WARN_ON(adev->dm.cached_state); - - return dm_cache_state(adev); -} - static int dm_suspend(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; @@ -3571,10 +3563,8 @@ static const struct amd_ip_funcs amdgpu_dm_funcs = { .early_fini = amdgpu_dm_early_fini, .hw_init = dm_hw_init, .hw_fini = dm_hw_fini, - .prepare_suspend = dm_prepare_suspend, .suspend = dm_suspend, .resume = dm_resume, - .complete = dm_complete, .is_idle = dm_is_idle, .wait_for_idle = dm_wait_for_idle, .check_soft_reset = dm_check_soft_reset, @@ -8381,8 +8371,7 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector) drm_add_modes_noedid(connector, 1920, 1080); } else { amdgpu_dm_connector_ddc_get_modes(connector, drm_edid); - if (encoder && (connector->connector_type != DRM_MODE_CONNECTOR_eDP) && - (connector->connector_type != DRM_MODE_CONNECTOR_LVDS)) + if (encoder) amdgpu_dm_connector_add_common_modes(encoder, connector); amdgpu_dm_connector_add_freesync_modes(connector, drm_edid); } @@ -8728,7 +8717,16 @@ static int amdgpu_dm_encoder_init(struct drm_device *dev, static void manage_dm_interrupts(struct amdgpu_device *adev, struct amdgpu_crtc *acrtc, struct dm_crtc_state *acrtc_state) -{ +{ /* + * We cannot be sure that the frontend index maps to the same + * backend index - some even map to more than one. + * So we have to go through the CRTC to find the right IRQ. + */ + int irq_type = amdgpu_display_crtc_idx_to_irq_type( + adev, + acrtc->crtc_id); + struct drm_device *dev = adev_to_drm(adev); + struct drm_vblank_crtc_config config = {0}; struct dc_crtc_timing *timing; int offdelay; @@ -8781,7 +8779,35 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, drm_crtc_vblank_on_config(&acrtc->base, &config); + /* Allow RX6xxx, RX7700, RX7800 GPUs to call amdgpu_irq_get.*/ + switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) { + case IP_VERSION(3, 0, 0): + case IP_VERSION(3, 0, 2): + case IP_VERSION(3, 0, 3): + case IP_VERSION(3, 2, 0): + if (amdgpu_irq_get(adev, &adev->pageflip_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot get pageflip irq!\n"); +#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) + if (amdgpu_irq_get(adev, &adev->vline0_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot get vline0 irq!\n"); +#endif + } + } else { + /* Allow RX6xxx, RX7700, RX7800 GPUs to call amdgpu_irq_put.*/ + switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) { + case IP_VERSION(3, 0, 0): + case IP_VERSION(3, 0, 2): + case IP_VERSION(3, 0, 3): + case IP_VERSION(3, 2, 0): +#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) + if (amdgpu_irq_put(adev, &adev->vline0_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot put vline0 irq!\n"); +#endif + if (amdgpu_irq_put(adev, &adev->pageflip_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot put pageflip irq!\n"); + } + drm_crtc_vblank_off(&acrtc->base); } } 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 7187d5aedf0a..77a9d2c7d318 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 @@ -809,6 +809,7 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, drm_dp_aux_init(&aconnector->dm_dp_aux.aux); drm_dp_cec_register_connector(&aconnector->dm_dp_aux.aux, &aconnector->base); + drm_dp_dpcd_set_probe(&aconnector->dm_dp_aux.aux, false); if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_eDP) return; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 59c07756130d..f24e1da68269 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -1145,6 +1145,7 @@ struct dc_debug_options { bool enable_hblank_borrow; bool force_subvp_df_throttle; uint32_t acpi_transition_bitmasks[MAX_PIPES]; + bool enable_pg_cntl_debug_logs; }; diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c index 58c84f555c0f..0ce9489ac6b7 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c @@ -133,30 +133,34 @@ enum dsc_clk_source { }; -static void dccg35_set_dsc_clk_rcg(struct dccg *dccg, int inst, bool enable) +static void dccg35_set_dsc_clk_rcg(struct dccg *dccg, int inst, bool allow_rcg) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc && enable) + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc && allow_rcg) return; switch (inst) { case 0: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 1: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 2: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 3: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; default: BREAK_TO_DEBUGGER(); return; } + + /* Wait for clock to ramp */ + if (!allow_rcg) + udelay(10); } static void dccg35_set_symclk32_se_rcg( @@ -385,35 +389,34 @@ static void dccg35_set_dtbclk_p_rcg(struct dccg *dccg, int inst, bool enable) } } -static void dccg35_set_dppclk_rcg(struct dccg *dccg, - int inst, bool enable) +static void dccg35_set_dppclk_rcg(struct dccg *dccg, int inst, bool allow_rcg) { - struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - - if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && enable) + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && allow_rcg) return; switch (inst) { case 0: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 1: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 2: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 3: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; default: BREAK_TO_DEBUGGER(); break; } - //DC_LOG_DEBUG("%s: inst(%d) DPPCLK rcg_disable: %d\n", __func__, inst, enable ? 0 : 1); + /* Wait for clock to ramp */ + if (!allow_rcg) + udelay(10); } static void dccg35_set_dpstreamclk_rcg( @@ -1177,32 +1180,34 @@ static void dccg35_update_dpp_dto(struct dccg *dccg, int dpp_inst, } static void dccg35_set_dppclk_root_clock_gating(struct dccg *dccg, - uint32_t dpp_inst, uint32_t enable) + uint32_t dpp_inst, uint32_t disallow_rcg) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && !disallow_rcg) return; switch (dpp_inst) { case 0: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, disallow_rcg); break; case 1: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, disallow_rcg); break; case 2: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, disallow_rcg); break; case 3: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, disallow_rcg); break; default: break; } - //DC_LOG_DEBUG("%s: dpp_inst(%d) rcg: %d\n", __func__, dpp_inst, enable); + /* Wait for clock to ramp */ + if (disallow_rcg) + udelay(10); } static void dccg35_get_pixel_rate_div( @@ -1782,8 +1787,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) //Disable DTO switch (inst) { case 0: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK0_DTO_PARAM, DSCCLK0_DTO_PHASE, 0, @@ -1791,8 +1795,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK0_EN, 1); break; case 1: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK1_DTO_PARAM, DSCCLK1_DTO_PHASE, 0, @@ -1800,8 +1803,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK1_EN, 1); break; case 2: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK2_DTO_PARAM, DSCCLK2_DTO_PHASE, 0, @@ -1809,8 +1811,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK2_EN, 1); break; case 3: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK3_DTO_PARAM, DSCCLK3_DTO_PHASE, 0, @@ -1821,6 +1822,9 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) BREAK_TO_DEBUGGER(); return; } + + /* Wait for clock to ramp */ + udelay(10); } static void dccg35_disable_dscclk(struct dccg *dccg, @@ -1864,6 +1868,9 @@ static void dccg35_disable_dscclk(struct dccg *dccg, default: return; } + + /* Wait for clock ramp */ + udelay(10); } static void dccg35_enable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst, uint32_t link_enc_inst) @@ -2349,10 +2356,7 @@ static void dccg35_disable_symclk_se_cb( void dccg35_root_gate_disable_control(struct dccg *dccg, uint32_t pipe_idx, uint32_t disable_clock_gating) { - - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) { - dccg35_set_dppclk_root_clock_gating(dccg, pipe_idx, disable_clock_gating); - } + dccg35_set_dppclk_root_clock_gating(dccg, pipe_idx, disable_clock_gating); } static const struct dccg_funcs dccg35_funcs_new = { diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c index 75fb77bca83b..01480a04f85e 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c @@ -520,6 +520,15 @@ void dpp1_dppclk_control( REG_UPDATE(DPP_CONTROL, DPP_CLOCK_ENABLE, 0); } +void dpp_force_disable_cursor(struct dpp *dpp_base) +{ + struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base); + + /* Force disable cursor */ + REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, 0); + dpp_base->pos.cur0_ctl.bits.cur0_enable = 0; +} + static const struct dpp_funcs dcn10_dpp_funcs = { .dpp_read_state = dpp_read_state, .dpp_reset = dpp_reset, diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h index c48139bed11f..f466182963f7 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h @@ -1525,4 +1525,6 @@ void dpp1_construct(struct dcn10_dpp *dpp1, void dpp1_cm_get_gamut_remap(struct dpp *dpp_base, struct dpp_grph_csc_adjustment *adjust); +void dpp_force_disable_cursor(struct dpp *dpp_base); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c index 2d70586cef40..09be2a90cc79 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c @@ -1494,6 +1494,7 @@ static struct dpp_funcs dcn30_dpp_funcs = { .dpp_dppclk_control = dpp1_dppclk_control, .dpp_set_hdr_multiplier = dpp3_set_hdr_multiplier, .dpp_get_gamut_remap = dpp3_cm_get_gamut_remap, + .dpp_force_disable_cursor = dpp_force_disable_cursor, }; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index 3207addbd4eb..b7c2d3095b25 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -955,7 +955,7 @@ enum dc_status dcn20_enable_stream_timing( return DC_ERROR_UNEXPECTED; } - fsleep(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz)); + udelay(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz)); params.vertical_total_min = stream->adjust.v_total_min; params.vertical_total_max = stream->adjust.v_total_max; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c index e68f21fd5f0f..560984533950 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c @@ -528,3 +528,75 @@ void dcn314_disable_link_output(struct dc_link *link, apply_symclk_on_tx_off_wa(link); } + +/** + * dcn314_dpp_pg_control - DPP power gate control. + * + * @hws: dce_hwseq reference. + * @dpp_inst: DPP instance reference. + * @power_on: true if we want to enable power gate, false otherwise. + * + * Enable or disable power gate in the specific DPP instance. + * If power gating is disabled, will force disable cursor in the DPP instance. + */ +void dcn314_dpp_pg_control( + struct dce_hwseq *hws, + unsigned int dpp_inst, + bool power_on) +{ + uint32_t power_gate = power_on ? 0 : 1; + uint32_t pwr_status = power_on ? 0 : 2; + + + if (hws->ctx->dc->debug.disable_dpp_power_gate) { + /* Workaround for DCN314 with disabled power gating */ + if (!power_on) { + + /* Force disable cursor if power gating is disabled */ + struct dpp *dpp = hws->ctx->dc->res_pool->dpps[dpp_inst]; + if (dpp && dpp->funcs->dpp_force_disable_cursor) + dpp->funcs->dpp_force_disable_cursor(dpp); + } + return; + } + if (REG(DOMAIN1_PG_CONFIG) == 0) + return; + + switch (dpp_inst) { + case 0: /* DPP0 */ + REG_UPDATE(DOMAIN1_PG_CONFIG, + DOMAIN1_POWER_GATE, power_gate); + + REG_WAIT(DOMAIN1_PG_STATUS, + DOMAIN1_PGFSM_PWR_STATUS, pwr_status, + 1, 1000); + break; + case 1: /* DPP1 */ + REG_UPDATE(DOMAIN3_PG_CONFIG, + DOMAIN3_POWER_GATE, power_gate); + + REG_WAIT(DOMAIN3_PG_STATUS, + DOMAIN3_PGFSM_PWR_STATUS, pwr_status, + 1, 1000); + break; + case 2: /* DPP2 */ + REG_UPDATE(DOMAIN5_PG_CONFIG, + DOMAIN5_POWER_GATE, power_gate); + + REG_WAIT(DOMAIN5_PG_STATUS, + DOMAIN5_PGFSM_PWR_STATUS, pwr_status, + 1, 1000); + break; + case 3: /* DPP3 */ + REG_UPDATE(DOMAIN7_PG_CONFIG, + DOMAIN7_POWER_GATE, power_gate); + + REG_WAIT(DOMAIN7_PG_STATUS, + DOMAIN7_PGFSM_PWR_STATUS, pwr_status, + 1, 1000); + break; + default: + BREAK_TO_DEBUGGER(); + break; + } +} diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h index 2305ad282f21..6c072d0274ea 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h @@ -47,4 +47,6 @@ void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst, void dcn314_disable_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal); +void dcn314_dpp_pg_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool power_on); + #endif /* __DC_HWSS_DCN314_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c index f5112742edf9..9f454fa90e65 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c @@ -141,6 +141,7 @@ static const struct hwseq_private_funcs dcn314_private_funcs = { .enable_power_gating_plane = dcn314_enable_power_gating_plane, .dpp_root_clock_control = dcn314_dpp_root_clock_control, .hubp_pg_control = dcn31_hubp_pg_control, + .dpp_pg_control = dcn314_dpp_pg_control, .program_all_writeback_pipes_in_tree = dcn30_program_all_writeback_pipes_in_tree, .update_odm = dcn314_update_odm, .dsc_pg_control = dcn314_dsc_pg_control, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c index a267f574b619..764eff6a4ec6 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c @@ -113,6 +113,14 @@ static void enable_memory_low_power(struct dc *dc) } #endif +static void print_pg_status(struct dc *dc, const char *debug_func, const char *debug_log) +{ + if (dc->debug.enable_pg_cntl_debug_logs && dc->res_pool->pg_cntl) { + if (dc->res_pool->pg_cntl->funcs->print_pg_status) + dc->res_pool->pg_cntl->funcs->print_pg_status(dc->res_pool->pg_cntl, debug_func, debug_log); + } +} + void dcn35_set_dmu_fgcg(struct dce_hwseq *hws, bool enable) { REG_UPDATE_3(DMU_CLK_CNTL, @@ -137,6 +145,8 @@ void dcn35_init_hw(struct dc *dc) uint32_t user_level = MAX_BACKLIGHT_LEVEL; int i; + print_pg_status(dc, __func__, ": start"); + if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks) dc->clk_mgr->funcs->init_clocks(dc->clk_mgr); @@ -200,10 +210,7 @@ void dcn35_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc->link_srv->blank_all_dp_displays(dc); -/* - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); -*/ + if (res_pool->hubbub && res_pool->hubbub->funcs->dchubbub_init) res_pool->hubbub->funcs->dchubbub_init(dc->res_pool->hubbub); /* If taking control over from VBIOS, we may want to optimize our first @@ -236,6 +243,8 @@ void dcn35_init_hw(struct dc *dc) } hws->funcs.init_pipes(dc, dc->current_state); + print_pg_status(dc, __func__, ": after init_pipes"); + if (dc->res_pool->hubbub->funcs->allow_self_refresh_control && !dc->res_pool->hubbub->ctx->dc->debug.disable_stutter) dc->res_pool->hubbub->funcs->allow_self_refresh_control(dc->res_pool->hubbub, @@ -312,6 +321,7 @@ void dcn35_init_hw(struct dc *dc) if (dc->res_pool->pg_cntl->funcs->init_pg_status) dc->res_pool->pg_cntl->funcs->init_pg_status(dc->res_pool->pg_cntl); } + print_pg_status(dc, __func__, ": after init_pg_status"); } static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) @@ -500,97 +510,6 @@ void dcn35_physymclk_root_clock_control(struct dce_hwseq *hws, unsigned int phy_ } } -void dcn35_dsc_pg_control( - struct dce_hwseq *hws, - unsigned int dsc_inst, - bool power_on) -{ - uint32_t power_gate = power_on ? 0 : 1; - uint32_t pwr_status = power_on ? 0 : 2; - uint32_t org_ip_request_cntl = 0; - - if (hws->ctx->dc->debug.disable_dsc_power_gate) - return; - if (hws->ctx->dc->debug.ignore_pg) - return; - REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); - if (org_ip_request_cntl == 0) - REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - - switch (dsc_inst) { - case 0: /* DSC0 */ - REG_UPDATE(DOMAIN16_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN16_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - case 1: /* DSC1 */ - REG_UPDATE(DOMAIN17_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN17_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - case 2: /* DSC2 */ - REG_UPDATE(DOMAIN18_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN18_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - case 3: /* DSC3 */ - REG_UPDATE(DOMAIN19_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN19_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - default: - BREAK_TO_DEBUGGER(); - break; - } - - if (org_ip_request_cntl == 0) - REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); -} - -void dcn35_enable_power_gating_plane(struct dce_hwseq *hws, bool enable) -{ - bool force_on = true; /* disable power gating */ - uint32_t org_ip_request_cntl = 0; - - if (hws->ctx->dc->debug.disable_hubp_power_gate) - return; - if (hws->ctx->dc->debug.ignore_pg) - return; - REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); - if (org_ip_request_cntl == 0) - REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - /* DCHUBP0/1/2/3/4/5 */ - REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - /* DPP0/1/2/3/4/5 */ - REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - - force_on = true; /* disable power gating */ - if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate) - force_on = false; - - /* DCS0/1/2/3/4 */ - REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN19_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - - -} - /* In headless boot cases, DIG may be turned * on which causes HW/SW discrepancies. * To avoid this, power down hardware on boot @@ -1453,6 +1372,8 @@ void dcn35_prepare_bandwidth( } dcn20_prepare_bandwidth(dc, context); + + print_pg_status(dc, __func__, ": after rcg and power up"); } void dcn35_optimize_bandwidth( @@ -1461,6 +1382,8 @@ void dcn35_optimize_bandwidth( { struct pg_block_update pg_update_state; + print_pg_status(dc, __func__, ": before rcg and power up"); + dcn20_optimize_bandwidth(dc, context); if (dc->hwss.calc_blocks_to_gate) { @@ -1472,6 +1395,8 @@ void dcn35_optimize_bandwidth( if (dc->hwss.root_clock_control) dc->hwss.root_clock_control(dc, &pg_update_state, false); } + + print_pg_status(dc, __func__, ": after rcg and power up"); } void dcn35_set_drr(struct pipe_ctx **pipe_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c index a3ccf805bd16..aefb7c473741 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c @@ -115,7 +115,6 @@ static const struct hw_sequencer_funcs dcn35_funcs = { .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state, .update_visual_confirm_color = dcn10_update_visual_confirm_color, .apply_idle_power_optimizations = dcn35_apply_idle_power_optimizations, - .update_dsc_pg = dcn32_update_dsc_pg, .calc_blocks_to_gate = dcn35_calc_blocks_to_gate, .calc_blocks_to_ungate = dcn35_calc_blocks_to_ungate, .hw_block_power_up = dcn35_hw_block_power_up, @@ -150,7 +149,6 @@ static const struct hwseq_private_funcs dcn35_private_funcs = { .plane_atomic_disable = dcn35_plane_atomic_disable, //.plane_atomic_disable = dcn20_plane_atomic_disable,/*todo*/ //.hubp_pg_control = dcn35_hubp_pg_control, - .enable_power_gating_plane = dcn35_enable_power_gating_plane, .dpp_root_clock_control = dcn35_dpp_root_clock_control, .dpstream_root_clock_control = dcn35_dpstream_root_clock_control, .physymclk_root_clock_control = dcn35_physymclk_root_clock_control, @@ -165,7 +163,6 @@ static const struct hwseq_private_funcs dcn35_private_funcs = { .calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values, .resync_fifo_dccg_dio = dcn314_resync_fifo_dccg_dio, .is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy, - .dsc_pg_control = dcn35_dsc_pg_control, .dsc_pg_status = dcn32_dsc_pg_status, .enable_plane = dcn35_enable_plane, .wait_for_pipe_update_if_needed = dcn10_wait_for_pipe_update_if_needed, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c index 58f2be2a326b..a580a55695c3 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c @@ -114,7 +114,6 @@ static const struct hw_sequencer_funcs dcn351_funcs = { .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state, .update_visual_confirm_color = dcn10_update_visual_confirm_color, .apply_idle_power_optimizations = dcn35_apply_idle_power_optimizations, - .update_dsc_pg = dcn32_update_dsc_pg, .calc_blocks_to_gate = dcn351_calc_blocks_to_gate, .calc_blocks_to_ungate = dcn351_calc_blocks_to_ungate, .hw_block_power_up = dcn351_hw_block_power_up, @@ -145,7 +144,6 @@ static const struct hwseq_private_funcs dcn351_private_funcs = { .plane_atomic_disable = dcn35_plane_atomic_disable, //.plane_atomic_disable = dcn20_plane_atomic_disable,/*todo*/ //.hubp_pg_control = dcn35_hubp_pg_control, - .enable_power_gating_plane = dcn35_enable_power_gating_plane, .dpp_root_clock_control = dcn35_dpp_root_clock_control, .dpstream_root_clock_control = dcn35_dpstream_root_clock_control, .physymclk_root_clock_control = dcn35_physymclk_root_clock_control, @@ -159,7 +157,6 @@ static const struct hwseq_private_funcs dcn351_private_funcs = { .setup_hpo_hw_control = dcn35_setup_hpo_hw_control, .calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values, .is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy, - .dsc_pg_control = dcn35_dsc_pg_control, .dsc_pg_status = dcn32_dsc_pg_status, .enable_plane = dcn35_enable_plane, .wait_for_pipe_update_if_needed = dcn10_wait_for_pipe_update_if_needed, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h index 0c5675d1c593..1b7c085dc2cc 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h @@ -349,6 +349,9 @@ struct dpp_funcs { struct dpp *dpp_base, enum dc_color_space color_space, struct dc_csc_transform cursor_csc_color_matrix); + + void (*dpp_force_disable_cursor)(struct dpp *dpp_base); + }; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h index 44f86cc2d1d6..227e3f8d7e5f 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h @@ -49,6 +49,7 @@ struct pg_cntl_funcs { void (*mem_pg_control)(struct pg_cntl *pg_cntl, bool power_on); void (*dio_pg_control)(struct pg_cntl *pg_cntl, bool power_on); void (*init_pg_status)(struct pg_cntl *pg_cntl); + void (*print_pg_status)(struct pg_cntl *pg_cntl, const char *debug_func, const char *debug_log); }; #endif //__DC_PG_CNTL_H__ diff --git a/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c b/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c index af21c0a27f86..72bd43f9bbe2 100644 --- a/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c @@ -79,16 +79,12 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo uint32_t power_gate = power_on ? 0 : 1; uint32_t pwr_status = power_on ? 0 : 2; uint32_t org_ip_request_cntl = 0; - bool block_enabled; - - /*need to enable dscclk regardless DSC_PG*/ - if (pg_cntl->ctx->dc->res_pool->dccg->funcs->enable_dsc && power_on) - pg_cntl->ctx->dc->res_pool->dccg->funcs->enable_dsc( - pg_cntl->ctx->dc->res_pool->dccg, dsc_inst); + bool block_enabled = false; + bool skip_pg = pg_cntl->ctx->dc->debug.ignore_pg || + pg_cntl->ctx->dc->debug.disable_dsc_power_gate || + pg_cntl->ctx->dc->idle_optimizations_allowed; - if (pg_cntl->ctx->dc->debug.ignore_pg || - pg_cntl->ctx->dc->debug.disable_dsc_power_gate || - pg_cntl->ctx->dc->idle_optimizations_allowed) + if (skip_pg && !power_on) return; block_enabled = pg_cntl35_dsc_pg_status(pg_cntl, dsc_inst); @@ -111,7 +107,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN16_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; case 1: /* DSC1 */ REG_UPDATE(DOMAIN17_PG_CONFIG, @@ -119,7 +115,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN17_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; case 2: /* DSC2 */ REG_UPDATE(DOMAIN18_PG_CONFIG, @@ -127,7 +123,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN18_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; case 3: /* DSC3 */ REG_UPDATE(DOMAIN19_PG_CONFIG, @@ -135,7 +131,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN19_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; default: BREAK_TO_DEBUGGER(); @@ -144,12 +140,6 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo if (dsc_inst < MAX_PIPES) pg_cntl->pg_pipe_res_enable[PG_DSC][dsc_inst] = power_on; - - if (pg_cntl->ctx->dc->res_pool->dccg->funcs->disable_dsc && !power_on) { - /*this is to disable dscclk*/ - pg_cntl->ctx->dc->res_pool->dccg->funcs->disable_dsc( - pg_cntl->ctx->dc->res_pool->dccg, dsc_inst); - } } static bool pg_cntl35_hubp_dpp_pg_status(struct pg_cntl *pg_cntl, unsigned int hubp_dpp_inst) @@ -189,11 +179,12 @@ void pg_cntl35_hubp_dpp_pg_control(struct pg_cntl *pg_cntl, unsigned int hubp_dp uint32_t pwr_status = power_on ? 0 : 2; uint32_t org_ip_request_cntl; bool block_enabled; + bool skip_pg = pg_cntl->ctx->dc->debug.ignore_pg || + pg_cntl->ctx->dc->debug.disable_hubp_power_gate || + pg_cntl->ctx->dc->debug.disable_dpp_power_gate || + pg_cntl->ctx->dc->idle_optimizations_allowed; - if (pg_cntl->ctx->dc->debug.ignore_pg || - pg_cntl->ctx->dc->debug.disable_hubp_power_gate || - pg_cntl->ctx->dc->debug.disable_dpp_power_gate || - pg_cntl->ctx->dc->idle_optimizations_allowed) + if (skip_pg && !power_on) return; block_enabled = pg_cntl35_hubp_dpp_pg_status(pg_cntl, hubp_dpp_inst); @@ -213,22 +204,22 @@ void pg_cntl35_hubp_dpp_pg_control(struct pg_cntl *pg_cntl, unsigned int hubp_dp case 0: /* DPP0 & HUBP0 */ REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; case 1: /* DPP1 & HUBP1 */ REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; case 2: /* DPP2 & HUBP2 */ REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; case 3: /* DPP3 & HUBP3 */ REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; default: BREAK_TO_DEBUGGER(); @@ -501,6 +492,36 @@ void pg_cntl35_init_pg_status(struct pg_cntl *pg_cntl) pg_cntl->pg_res_enable[PG_DWB] = block_enabled; } +static void pg_cntl35_print_pg_status(struct pg_cntl *pg_cntl, const char *debug_func, const char *debug_log) +{ + int i = 0; + bool block_enabled = false; + + DC_LOG_DEBUG("%s: %s", debug_func, debug_log); + + DC_LOG_DEBUG("PG_CNTL status:\n"); + + block_enabled = pg_cntl35_io_clk_status(pg_cntl); + DC_LOG_DEBUG("ONO0=%d (DCCG, DIO, DCIO)\n", block_enabled ? 1 : 0); + + block_enabled = pg_cntl35_mem_status(pg_cntl); + DC_LOG_DEBUG("ONO1=%d (DCHUBBUB, DCHVM, DCHUBBUBMEM)\n", block_enabled ? 1 : 0); + + block_enabled = pg_cntl35_plane_otg_status(pg_cntl); + DC_LOG_DEBUG("ONO2=%d (MPC, OPP, OPTC, DWB)\n", block_enabled ? 1 : 0); + + block_enabled = pg_cntl35_hpo_pg_status(pg_cntl); + DC_LOG_DEBUG("ONO3=%d (HPO)\n", block_enabled ? 1 : 0); + + for (i = 0; i < pg_cntl->ctx->dc->res_pool->pipe_count; i++) { + block_enabled = pg_cntl35_hubp_dpp_pg_status(pg_cntl, i); + DC_LOG_DEBUG("ONO%d=%d (DCHUBP%d, DPP%d)\n", 4 + i * 2, block_enabled ? 1 : 0, i, i); + + block_enabled = pg_cntl35_dsc_pg_status(pg_cntl, i); + DC_LOG_DEBUG("ONO%d=%d (DSC%d)\n", 5 + i * 2, block_enabled ? 1 : 0, i); + } +} + static const struct pg_cntl_funcs pg_cntl35_funcs = { .init_pg_status = pg_cntl35_init_pg_status, .dsc_pg_control = pg_cntl35_dsc_pg_control, @@ -511,7 +532,8 @@ static const struct pg_cntl_funcs pg_cntl35_funcs = { .mpcc_pg_control = pg_cntl35_mpcc_pg_control, .opp_pg_control = pg_cntl35_opp_pg_control, .optc_pg_control = pg_cntl35_optc_pg_control, - .dwb_pg_control = pg_cntl35_dwb_pg_control + .dwb_pg_control = pg_cntl35_dwb_pg_control, + .print_pg_status = pg_cntl35_print_pg_status }; struct pg_cntl *pg_cntl35_create( diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 4b64851fdb42..5fbfe7333b54 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -3458,14 +3458,16 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, effective_mode &= ~S_IWUSR; /* not implemented yet for APUs other than GC 10.3.1 (vangogh) and 9.4.3 */ - if (((adev->family == AMDGPU_FAMILY_SI) || - ((adev->flags & AMD_IS_APU) && (gc_ver != IP_VERSION(10, 3, 1)) && - (gc_ver != IP_VERSION(9, 4, 3) && gc_ver != IP_VERSION(9, 4, 4)))) && - (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr || - attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr || - attr == &sensor_dev_attr_power1_cap.dev_attr.attr || - attr == &sensor_dev_attr_power1_cap_default.dev_attr.attr)) - return 0; + if (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr || + attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr || + attr == &sensor_dev_attr_power1_cap.dev_attr.attr || + attr == &sensor_dev_attr_power1_cap_default.dev_attr.attr) { + if (adev->family == AMDGPU_FAMILY_SI || + ((adev->flags & AMD_IS_APU) && gc_ver != IP_VERSION(10, 3, 1) && + (gc_ver != IP_VERSION(9, 4, 3) && gc_ver != IP_VERSION(9, 4, 4))) || + (amdgpu_sriov_vf(adev) && gc_ver == IP_VERSION(11, 0, 3))) + return 0; + } /* not implemented yet for APUs having < GC 9.3.0 (Renoir) */ if (((adev->family == AMDGPU_FAMILY_SI) || diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index b47cb4a5f488..408f05dfab90 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -2236,7 +2236,7 @@ static int smu_resume(struct amdgpu_ip_block *ip_block) return ret; } - if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { + if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL && smu->od_enabled) { ret = smu_od_edit_dpm_table(smu, PP_OD_COMMIT_DPM_TABLE, NULL, 0); if (ret) return ret; diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index c0ad8f59e483..8b3304dedcd9 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -2677,7 +2677,7 @@ static int anx7625_i2c_probe(struct i2c_client *client) ret = devm_request_threaded_irq(dev, platform->pdata.intp_irq, NULL, anx7625_intr_hpd_isr, IRQF_TRIGGER_FALLING | - IRQF_ONESHOT, + IRQF_ONESHOT | IRQF_NO_AUTOEN, "anx7625-intp", platform); if (ret) { DRM_DEV_ERROR(dev, "fail to request irq\n"); @@ -2746,8 +2746,10 @@ static int anx7625_i2c_probe(struct i2c_client *client) } /* Add work function */ - if (platform->pdata.intp_irq) + if (platform->pdata.intp_irq) { + enable_irq(platform->pdata.intp_irq); queue_work(platform->workqueue, &platform->work); + } if (platform->pdata.audio_en) anx7625_register_audio(dev, platform); diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c index a614d1384f71..38726ae1bf15 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c @@ -1984,8 +1984,10 @@ static void cdns_mhdp_atomic_enable(struct drm_bridge *bridge, mhdp_state = to_cdns_mhdp_bridge_state(new_state); mhdp_state->current_mode = drm_mode_duplicate(bridge->dev, mode); - if (!mhdp_state->current_mode) - return; + if (!mhdp_state->current_mode) { + ret = -EINVAL; + goto out; + } drm_mode_set_name(mhdp_state->current_mode); diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 464390372b34..ae0d08e5e960 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -393,6 +393,17 @@ static int __maybe_unused ti_sn65dsi86_resume(struct device *dev) gpiod_set_value_cansleep(pdata->enable_gpio, 1); /* + * After EN is deasserted and an external clock is detected, the bridge + * will sample GPIO3:1 to determine its frequency. The driver will + * overwrite this setting in ti_sn_bridge_set_refclk_freq(). But this is + * racy. Thus we have to wait a couple of us. According to the datasheet + * the GPIO lines has to be stable at least 5 us (td5) but it seems that + * is not enough and the refclk frequency value is still lost or + * overwritten by the bridge itself. Waiting for 20us seems to work. + */ + usleep_range(20, 30); + + /* * If we have a reference clock we can enable communication w/ the * panel (including the aux channel) w/out any need for an input clock * so we can do it in resume which lets us read the EDID before diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c index 74d949995a72..86853535fb7b 100644 --- a/drivers/gpu/drm/drm_gpuvm.c +++ b/drivers/gpu/drm/drm_gpuvm.c @@ -40,7 +40,7 @@ * mapping's backing &drm_gem_object buffers. * * &drm_gem_object buffers maintain a list of &drm_gpuva objects representing - * all existent GPU VA mappings using this &drm_gem_object as backing buffer. + * all existing GPU VA mappings using this &drm_gem_object as backing buffer. * * GPU VAs can be flagged as sparse, such that drivers may use GPU VAs to also * keep track of sparse PTEs in order to support Vulkan 'Sparse Resources'. @@ -72,7 +72,7 @@ * but it can also be a 'dummy' object, which can be allocated with * drm_gpuvm_resv_object_alloc(). * - * In order to connect a struct drm_gpuva its backing &drm_gem_object each + * In order to connect a struct drm_gpuva to its backing &drm_gem_object each * &drm_gem_object maintains a list of &drm_gpuvm_bo structures, and each * &drm_gpuvm_bo contains a list of &drm_gpuva structures. * @@ -81,7 +81,7 @@ * This is ensured by the API through drm_gpuvm_bo_obtain() and * drm_gpuvm_bo_obtain_prealloc() which first look into the corresponding * &drm_gem_object list of &drm_gpuvm_bos for an existing instance of this - * particular combination. If not existent a new instance is created and linked + * particular combination. If not present, a new instance is created and linked * to the &drm_gem_object. * * &drm_gpuvm_bo structures, since unique for a given &drm_gpuvm, are also used @@ -108,7 +108,7 @@ * sequence of operations to satisfy a given map or unmap request. * * Therefore the DRM GPU VA manager provides an algorithm implementing splitting - * and merging of existent GPU VA mappings with the ones that are requested to + * and merging of existing GPU VA mappings with the ones that are requested to * be mapped or unmapped. This feature is required by the Vulkan API to * implement Vulkan 'Sparse Memory Bindings' - drivers UAPIs often refer to this * as VM BIND. @@ -119,7 +119,7 @@ * execute in order to integrate the new mapping cleanly into the current state * of the GPU VA space. * - * Depending on how the new GPU VA mapping intersects with the existent mappings + * Depending on how the new GPU VA mapping intersects with the existing mappings * of the GPU VA space the &drm_gpuvm_ops callbacks contain an arbitrary amount * of unmap operations, a maximum of two remap operations and a single map * operation. The caller might receive no callback at all if no operation is @@ -139,16 +139,16 @@ * one unmap operation and one or two map operations, such that drivers can * derive the page table update delta accordingly. * - * Note that there can't be more than two existent mappings to split up, one at + * Note that there can't be more than two existing mappings to split up, one at * the beginning and one at the end of the new mapping, hence there is a * maximum of two remap operations. * * Analogous to drm_gpuvm_sm_map() drm_gpuvm_sm_unmap() uses &drm_gpuvm_ops to * call back into the driver in order to unmap a range of GPU VA space. The - * logic behind this function is way simpler though: For all existent mappings + * logic behind this function is way simpler though: For all existing mappings * enclosed by the given range unmap operations are created. For mappings which - * are only partically located within the given range, remap operations are - * created such that those mappings are split up and re-mapped partically. + * are only partially located within the given range, remap operations are + * created such that those mappings are split up and re-mapped partially. * * As an alternative to drm_gpuvm_sm_map() and drm_gpuvm_sm_unmap(), * drm_gpuvm_sm_map_ops_create() and drm_gpuvm_sm_unmap_ops_create() can be used @@ -168,7 +168,7 @@ * provided helper functions drm_gpuva_map(), drm_gpuva_remap() and * drm_gpuva_unmap() instead. * - * The following diagram depicts the basic relationships of existent GPU VA + * The following diagram depicts the basic relationships of existing GPU VA * mappings, a newly requested mapping and the resulting mappings as implemented * by drm_gpuvm_sm_map() - it doesn't cover any arbitrary combinations of these. * @@ -218,7 +218,7 @@ * * * 4) Existent mapping is a left aligned subset of the requested one, hence - * replace the existent one. + * replace the existing one. * * :: * @@ -236,9 +236,9 @@ * and/or non-contiguous BO offset. * * - * 5) Requested mapping's range is a left aligned subset of the existent one, + * 5) Requested mapping's range is a left aligned subset of the existing one, * but backed by a different BO. Hence, map the requested mapping and split - * the existent one adjusting its BO offset. + * the existing one adjusting its BO offset. * * :: * @@ -271,9 +271,9 @@ * new: |-----|-----| (a.bo_offset=n, a'.bo_offset=n+1) * * - * 7) Requested mapping's range is a right aligned subset of the existent one, + * 7) Requested mapping's range is a right aligned subset of the existing one, * but backed by a different BO. Hence, map the requested mapping and split - * the existent one, without adjusting the BO offset. + * the existing one, without adjusting the BO offset. * * :: * @@ -304,7 +304,7 @@ * * 9) Existent mapping is overlapped at the end by the requested mapping backed * by a different BO. Hence, map the requested mapping and split up the - * existent one, without adjusting the BO offset. + * existing one, without adjusting the BO offset. * * :: * @@ -334,9 +334,9 @@ * new: |-----|-----------| (a'.bo_offset=n, a.bo_offset=n+1) * * - * 11) Requested mapping's range is a centered subset of the existent one + * 11) Requested mapping's range is a centered subset of the existing one * having a different backing BO. Hence, map the requested mapping and split - * up the existent one in two mappings, adjusting the BO offset of the right + * up the existing one in two mappings, adjusting the BO offset of the right * one accordingly. * * :: @@ -351,7 +351,7 @@ * new: |-----|-----|-----| (a.bo_offset=n,b.bo_offset=m,a'.bo_offset=n+2) * * - * 12) Requested mapping is a contiguous subset of the existent one. Split it + * 12) Requested mapping is a contiguous subset of the existing one. Split it * up, but indicate that the backing PTEs could be kept. * * :: @@ -367,7 +367,7 @@ * * * 13) Existent mapping is a right aligned subset of the requested one, hence - * replace the existent one. + * replace the existing one. * * :: * @@ -386,7 +386,7 @@ * * * 14) Existent mapping is a centered subset of the requested one, hence - * replace the existent one. + * replace the existing one. * * :: * @@ -406,7 +406,7 @@ * * 15) Existent mappings is overlapped at the beginning by the requested mapping * backed by a different BO. Hence, map the requested mapping and split up - * the existent one, adjusting its BO offset accordingly. + * the existing one, adjusting its BO offset accordingly. * * :: * @@ -469,8 +469,8 @@ * make use of them. * * The below code is strictly limited to illustrate the generic usage pattern. - * To maintain simplicitly, it doesn't make use of any abstractions for common - * code, different (asyncronous) stages with fence signalling critical paths, + * To maintain simplicity, it doesn't make use of any abstractions for common + * code, different (asynchronous) stages with fence signalling critical paths, * any other helpers or error handling in terms of freeing memory and dropping * previously taken locks. * @@ -479,7 +479,7 @@ * // Allocates a new &drm_gpuva. * struct drm_gpuva * driver_gpuva_alloc(void); * - * // Typically drivers would embedd the &drm_gpuvm and &drm_gpuva + * // Typically drivers would embed the &drm_gpuvm and &drm_gpuva * // structure in individual driver structures and lock the dma-resv with * // drm_exec or similar helpers. * int driver_mapping_create(struct drm_gpuvm *gpuvm, @@ -582,7 +582,7 @@ * .sm_step_unmap = driver_gpuva_unmap, * }; * - * // Typically drivers would embedd the &drm_gpuvm and &drm_gpuva + * // Typically drivers would embed the &drm_gpuvm and &drm_gpuva * // structure in individual driver structures and lock the dma-resv with * // drm_exec or similar helpers. * int driver_mapping_create(struct drm_gpuvm *gpuvm, @@ -680,7 +680,7 @@ * * This helper is here to provide lockless list iteration. Lockless as in, the * iterator releases the lock immediately after picking the first element from - * the list, so list insertion deletion can happen concurrently. + * the list, so list insertion and deletion can happen concurrently. * * Elements popped from the original list are kept in a local list, so removal * and is_empty checks can still happen while we're iterating the list. @@ -1160,7 +1160,7 @@ drm_gpuvm_prepare_objects_locked(struct drm_gpuvm *gpuvm, } /** - * drm_gpuvm_prepare_objects() - prepare all assoiciated BOs + * drm_gpuvm_prepare_objects() - prepare all associated BOs * @gpuvm: the &drm_gpuvm * @exec: the &drm_exec locking context * @num_fences: the amount of &dma_fences to reserve @@ -1230,13 +1230,13 @@ drm_gpuvm_prepare_range(struct drm_gpuvm *gpuvm, struct drm_exec *exec, EXPORT_SYMBOL_GPL(drm_gpuvm_prepare_range); /** - * drm_gpuvm_exec_lock() - lock all dma-resv of all assoiciated BOs + * drm_gpuvm_exec_lock() - lock all dma-resv of all associated BOs * @vm_exec: the &drm_gpuvm_exec wrapper * * Acquires all dma-resv locks of all &drm_gem_objects the given * &drm_gpuvm contains mappings of. * - * Addionally, when calling this function with struct drm_gpuvm_exec::extra + * Additionally, when calling this function with struct drm_gpuvm_exec::extra * being set the driver receives the given @fn callback to lock additional * dma-resv in the context of the &drm_gpuvm_exec instance. Typically, drivers * would call drm_exec_prepare_obj() from within this callback. @@ -1293,7 +1293,7 @@ fn_lock_array(struct drm_gpuvm_exec *vm_exec) } /** - * drm_gpuvm_exec_lock_array() - lock all dma-resv of all assoiciated BOs + * drm_gpuvm_exec_lock_array() - lock all dma-resv of all associated BOs * @vm_exec: the &drm_gpuvm_exec wrapper * @objs: additional &drm_gem_objects to lock * @num_objs: the number of additional &drm_gem_objects to lock @@ -1588,7 +1588,7 @@ drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm, EXPORT_SYMBOL_GPL(drm_gpuvm_bo_find); /** - * drm_gpuvm_bo_obtain() - obtains and instance of the &drm_gpuvm_bo for the + * drm_gpuvm_bo_obtain() - obtains an instance of the &drm_gpuvm_bo for the * given &drm_gpuvm and &drm_gem_object * @gpuvm: The &drm_gpuvm the @obj is mapped in. * @obj: The &drm_gem_object being mapped in the @gpuvm. @@ -1624,7 +1624,7 @@ drm_gpuvm_bo_obtain(struct drm_gpuvm *gpuvm, EXPORT_SYMBOL_GPL(drm_gpuvm_bo_obtain); /** - * drm_gpuvm_bo_obtain_prealloc() - obtains and instance of the &drm_gpuvm_bo + * drm_gpuvm_bo_obtain_prealloc() - obtains an instance of the &drm_gpuvm_bo * for the given &drm_gpuvm and &drm_gem_object * @__vm_bo: A pre-allocated struct drm_gpuvm_bo. * @@ -1688,7 +1688,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_bo_extobj_add); * @vm_bo: the &drm_gpuvm_bo to add or remove * @evict: indicates whether the object is evicted * - * Adds a &drm_gpuvm_bo to or removes it from the &drm_gpuvms evicted list. + * Adds a &drm_gpuvm_bo to or removes it from the &drm_gpuvm's evicted list. */ void drm_gpuvm_bo_evict(struct drm_gpuvm_bo *vm_bo, bool evict) @@ -1790,7 +1790,7 @@ __drm_gpuva_remove(struct drm_gpuva *va) * drm_gpuva_remove() - remove a &drm_gpuva * @va: the &drm_gpuva to remove * - * This removes the given &va from the underlaying tree. + * This removes the given &va from the underlying tree. * * It is safe to use this function using the safe versions of iterating the GPU * VA space, such as drm_gpuvm_for_each_va_safe() and @@ -2358,7 +2358,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_sm_map); * * This function iterates the given range of the GPU VA space. It utilizes the * &drm_gpuvm_ops to call back into the driver providing the operations to - * unmap and, if required, split existent mappings. + * unmap and, if required, split existing mappings. * * Drivers may use these callbacks to update the GPU VA space right away within * the callback. In case the driver decides to copy and store the operations for @@ -2430,9 +2430,7 @@ static const struct drm_gpuvm_ops lock_ops = { * remapped, and locks+prepares (drm_exec_prepare_object()) objects that * will be newly mapped. * - * The expected usage is: - * - * .. code-block:: c + * The expected usage is:: * * vm_bind { * struct drm_exec exec; @@ -2475,7 +2473,7 @@ static const struct drm_gpuvm_ops lock_ops = { * required without the earlier DRIVER_OP_MAP. This is safe because we've * already locked the GEM object in the earlier DRIVER_OP_MAP step. * - * Returns: 0 on success or a negative error codec + * Returns: 0 on success or a negative error code */ int drm_gpuvm_sm_map_exec_lock(struct drm_gpuvm *gpuvm, @@ -2619,12 +2617,12 @@ static const struct drm_gpuvm_ops gpuvm_list_ops = { * @req_offset: the offset within the &drm_gem_object * * This function creates a list of operations to perform splitting and merging - * of existent mapping(s) with the newly requested one. + * of existing mapping(s) with the newly requested one. * * The list can be iterated with &drm_gpuva_for_each_op and must be processed * in the given order. It can contain map, unmap and remap operations, but it * also can be empty if no operation is required, e.g. if the requested mapping - * already exists is the exact same way. + * already exists in the exact same way. * * There can be an arbitrary amount of unmap operations, a maximum of two remap * operations and a single map operation. The latter one represents the original diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 273054c22325..c92f3e736228 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -1172,7 +1172,7 @@ static void icl_mbus_init(struct intel_display *display) if (DISPLAY_VER(display) == 12) abox_regs |= BIT(0); - for_each_set_bit(i, &abox_regs, sizeof(abox_regs)) + for_each_set_bit(i, &abox_regs, BITS_PER_TYPE(abox_regs)) intel_de_rmw(display, MBUS_ABOX_CTL(i), mask, val); } @@ -1629,11 +1629,11 @@ static void tgl_bw_buddy_init(struct intel_display *display) if (table[config].page_mask == 0) { drm_dbg_kms(display->drm, "Unknown memory configuration; disabling address buddy logic.\n"); - for_each_set_bit(i, &abox_mask, sizeof(abox_mask)) + for_each_set_bit(i, &abox_mask, BITS_PER_TYPE(abox_mask)) intel_de_write(display, BW_BUDDY_CTL(i), BW_BUDDY_DISABLE); } else { - for_each_set_bit(i, &abox_mask, sizeof(abox_mask)) { + for_each_set_bit(i, &abox_mask, BITS_PER_TYPE(abox_mask)) { intel_de_write(display, BW_BUDDY_PAGE_MASK(i), table[config].page_mask); diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 41228478b21c..0a3a3f6a5f9d 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -546,7 +546,7 @@ static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector, luminance_range->max_luminance, panel->vbt.backlight.pwm_freq_hz, intel_dp->edp_dpcd, ¤t_level, ¤t_mode, - false); + panel->backlight.edp.vesa.luminance_control_support); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index d5e6bab36414..eb5537f0ac90 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -394,10 +394,12 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) continue; drm_dev = device_find_child(&pdev->dev, NULL, mtk_drm_match); + put_device(&pdev->dev); if (!drm_dev) continue; temp_drm_priv = dev_get_drvdata(drm_dev); + put_device(drm_dev); if (!temp_drm_priv) continue; diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index d7726091819c..0e2bcd5f67b7 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -1002,6 +1002,12 @@ static int mtk_dsi_host_attach(struct mipi_dsi_host *host, return PTR_ERR(dsi->next_bridge); } + /* + * set flag to request the DSI host bridge be pre-enabled before device bridge + * in the chain, so the DSI host is ready when the device bridge is pre-enabled + */ + dsi->next_bridge->pre_enable_prev_first = true; + drm_bridge_add(&dsi->bridge); ret = component_add(host->dev, &mtk_dsi_component_ops); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 845fd8aa43c3..b766dd5e6c8d 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -182,8 +182,8 @@ static inline struct mtk_hdmi *hdmi_ctx_from_bridge(struct drm_bridge *b) static void mtk_hdmi_hw_vid_black(struct mtk_hdmi *hdmi, bool black) { - regmap_update_bits(hdmi->regs, VIDEO_SOURCE_SEL, - VIDEO_CFG_4, black ? GEN_RGB : NORMAL_PATH); + regmap_update_bits(hdmi->regs, VIDEO_CFG_4, + VIDEO_SOURCE_SEL, black ? GEN_RGB : NORMAL_PATH); } static void mtk_hdmi_hw_make_reg_writable(struct mtk_hdmi *hdmi, bool enable) @@ -310,8 +310,8 @@ static void mtk_hdmi_hw_send_info_frame(struct mtk_hdmi *hdmi, u8 *buffer, static void mtk_hdmi_hw_send_aud_packet(struct mtk_hdmi *hdmi, bool enable) { - regmap_update_bits(hdmi->regs, AUDIO_PACKET_OFF, - GRL_SHIFT_R2, enable ? 0 : AUDIO_PACKET_OFF); + regmap_update_bits(hdmi->regs, GRL_SHIFT_R2, + AUDIO_PACKET_OFF, enable ? 0 : AUDIO_PACKET_OFF); } static void mtk_hdmi_hw_config_sys(struct mtk_hdmi *hdmi) diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c index cbc4f37da8ba..02349bd44001 100644 --- a/drivers/gpu/drm/mediatek/mtk_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_plane.c @@ -292,7 +292,8 @@ static void mtk_plane_atomic_disable(struct drm_plane *plane, wmb(); /* Make sure the above parameter is set before update */ mtk_plane_state->pending.dirty = true; - mtk_crtc_plane_disable(old_state->crtc, plane); + if (old_state && old_state->crtc) + mtk_crtc_plane_disable(old_state->crtc, plane); } static void mtk_plane_atomic_update(struct drm_plane *plane, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index faca2a0243ab..d5d1271fce61 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -11,7 +11,7 @@ static const unsigned int *gen7_0_0_external_core_regs[] __always_unused; static const unsigned int *gen7_2_0_external_core_regs[] __always_unused; static const unsigned int *gen7_9_0_external_core_regs[] __always_unused; -static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused; +static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused; static const u32 gen7_9_0_cx_debugbus_blocks[] __always_unused; #include "adreno_gen7_0_0_snapshot.h" @@ -174,8 +174,15 @@ static int a6xx_crashdumper_run(struct msm_gpu *gpu, static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset, u32 *data) { - u32 reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | - A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + u32 reg; + + if (to_adreno_gpu(gpu)->info->family >= ADRENO_7XX_GEN1) { + reg = A7XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | + A7XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + } else { + reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | + A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + } gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_A, reg); gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_B, reg); @@ -198,11 +205,18 @@ static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset, readl((ptr) + ((offset) << 2)) /* read a value from the CX debug bus */ -static int cx_debugbus_read(void __iomem *cxdbg, u32 block, u32 offset, +static int cx_debugbus_read(struct msm_gpu *gpu, void __iomem *cxdbg, u32 block, u32 offset, u32 *data) { - u32 reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | - A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + u32 reg; + + if (to_adreno_gpu(gpu)->info->family >= ADRENO_7XX_GEN1) { + reg = A7XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | + A7XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + } else { + reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | + A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + } cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_A, reg); cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_B, reg); @@ -315,7 +329,8 @@ static void a6xx_get_debugbus_block(struct msm_gpu *gpu, ptr += debugbus_read(gpu, block->id, i, ptr); } -static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg, +static void a6xx_get_cx_debugbus_block(struct msm_gpu *gpu, + void __iomem *cxdbg, struct a6xx_gpu_state *a6xx_state, const struct a6xx_debugbus_block *block, struct a6xx_gpu_state_obj *obj) @@ -330,7 +345,7 @@ static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg, obj->handle = block; for (ptr = obj->data, i = 0; i < block->count; i++) - ptr += cx_debugbus_read(cxdbg, block->id, i, ptr); + ptr += cx_debugbus_read(gpu, cxdbg, block->id, i, ptr); } static void a6xx_get_debugbus_blocks(struct msm_gpu *gpu, @@ -423,8 +438,9 @@ static void a7xx_get_debugbus_blocks(struct msm_gpu *gpu, a6xx_state, &a7xx_debugbus_blocks[gbif_debugbus_blocks[i]], &a6xx_state->debugbus[i + debugbus_blocks_count]); } - } + a6xx_state->nr_debugbus = total_debugbus_blocks; + } } static void a6xx_get_debugbus(struct msm_gpu *gpu, @@ -526,7 +542,8 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu, int i; for (i = 0; i < nr_cx_debugbus_blocks; i++) - a6xx_get_cx_debugbus_block(cxdbg, + a6xx_get_cx_debugbus_block(gpu, + cxdbg, a6xx_state, &cx_debugbus_blocks[i], &a6xx_state->cx_debugbus[i]); @@ -759,15 +776,15 @@ static void a7xx_get_cluster(struct msm_gpu *gpu, size_t datasize; int i, regcount = 0; - /* Some clusters need a selector register to be programmed too */ - if (cluster->sel) - in += CRASHDUMP_WRITE(in, cluster->sel->cd_reg, cluster->sel->val); - in += CRASHDUMP_WRITE(in, REG_A7XX_CP_APERTURE_CNTL_CD, A7XX_CP_APERTURE_CNTL_CD_PIPE(cluster->pipe_id) | A7XX_CP_APERTURE_CNTL_CD_CLUSTER(cluster->cluster_id) | A7XX_CP_APERTURE_CNTL_CD_CONTEXT(cluster->context_id)); + /* Some clusters need a selector register to be programmed too */ + if (cluster->sel) + in += CRASHDUMP_WRITE(in, cluster->sel->cd_reg, cluster->sel->val); + for (i = 0; cluster->regs[i] != UINT_MAX; i += 2) { int count = RANGE(cluster->regs, i); @@ -1796,6 +1813,7 @@ static void a7xx_show_shader(struct a6xx_gpu_state_obj *obj, print_name(p, " - type: ", a7xx_statetype_names[block->statetype]); print_name(p, " - pipe: ", a7xx_pipe_names[block->pipeid]); + drm_printf(p, " - location: %d\n", block->location); for (i = 0; i < block->num_sps; i++) { drm_printf(p, " - sp: %d\n", i); @@ -1873,6 +1891,7 @@ static void a7xx_show_dbgahb_cluster(struct a6xx_gpu_state_obj *obj, print_name(p, " - pipe: ", a7xx_pipe_names[dbgahb->pipe_id]); print_name(p, " - cluster-name: ", a7xx_cluster_names[dbgahb->cluster_id]); drm_printf(p, " - context: %d\n", dbgahb->context_id); + drm_printf(p, " - location: %d\n", dbgahb->location_id); a7xx_show_registers_indented(dbgahb->regs, obj->data, p, 4); } } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index 95d93ac6812a..1c18499b60bb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -419,47 +419,47 @@ static const struct a6xx_indexed_registers a6xx_indexed_reglist[] = { REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL }, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, REG_A6XX_CP_ROQ_DBG_DATA, 0, a6xx_get_cp_roq_size}, }; static const struct a6xx_indexed_registers a7xx_indexed_reglist[] = { { "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR, - REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL }, + REG_A6XX_CP_SQE_STAT_DATA, 0x40, NULL }, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR, - REG_A7XX_CP_BV_SQE_STAT_DATA, 0x33, NULL }, - { "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR, + { "CP_BV_SQE_STAT", REG_A7XX_CP_BV_SQE_STAT_ADDR, + REG_A7XX_CP_BV_SQE_STAT_DATA, 0x40, NULL }, + { "CP_BV_DRAW_STATE", REG_A7XX_CP_BV_DRAW_STATE_ADDR, REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, + { "CP_BV_SQE_UCODE_DBG", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR, - REG_A7XX_CP_SQE_AC_STAT_DATA, 0x33, NULL }, - { "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, + { "CP_SQE_AC_STAT", REG_A7XX_CP_SQE_AC_STAT_ADDR, + REG_A7XX_CP_SQE_AC_STAT_DATA, 0x40, NULL }, + { "CP_LPAC_DRAW_STATE", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, + { "CP_SQE_AC_UCODE_DBG", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, + { "CP_LPAC_FIFO_DBG", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x40, NULL }, - { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, REG_A6XX_CP_ROQ_DBG_DATA, 0, a7xx_get_cp_roq_size }, }; static const struct a6xx_indexed_registers a6xx_cp_mempool_indexed = { - "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR, + "CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR, REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2060, NULL, }; static const struct a6xx_indexed_registers a7xx_cp_bv_mempool_indexed[] = { - { "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR, - REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2100, NULL }, - { "CP_BV_MEMPOOL", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR, - REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2100, NULL }, + { "CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR, + REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2200, NULL }, + { "CP_BV_MEM_POOL_DBG", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR, + REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2200, NULL }, }; #define DEBUGBUS(_id, _count) { .id = _id, .name = #_id, .count = _count } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h index cb66ece6606b..04b49d385f9d 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h @@ -81,7 +81,7 @@ static const u32 gen7_0_0_debugbus_blocks[] = { A7XX_DBGBUS_USPTP_7, }; -static struct gen7_shader_block gen7_0_0_shader_blocks[] = { +static const struct gen7_shader_block gen7_0_0_shader_blocks[] = { {A7XX_TP0_TMO_DATA, 0x200, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, {A7XX_TP0_SMO_DATA, 0x80, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, @@ -668,12 +668,19 @@ static const u32 gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers), 8)); -/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */ -static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = { +/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_NONE */ +static const u32 gen7_0_0_tpl1_noncontext_pipe_none_registers[] = { 0x0b600, 0x0b600, 0x0b602, 0x0b602, 0x0b604, 0x0b604, 0x0b608, 0x0b60c, 0x0b60f, 0x0b621, 0x0b630, 0x0b633, UINT_MAX, UINT_MAX, }; +static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_none_registers), 8)); + +/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */ +static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = { + 0x0b600, 0x0b600, + UINT_MAX, UINT_MAX, +}; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_br_registers), 8)); /* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_LPAC */ @@ -695,7 +702,7 @@ static const struct gen7_sel_reg gen7_0_0_rb_rbp_sel = { .val = 0x9, }; -static struct gen7_cluster_registers gen7_0_0_clusters[] = { +static const struct gen7_cluster_registers gen7_0_0_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, gen7_0_0_noncontext_pipe_br_registers, }, { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, @@ -764,7 +771,7 @@ static struct gen7_cluster_registers gen7_0_0_clusters[] = { gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, }; -static struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = { +static const struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 }, { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, @@ -914,7 +921,7 @@ static const u32 gen7_0_0_dpm_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_dpm_registers), 8)); -static struct gen7_reg_list gen7_0_0_reg_list[] = { +static const struct gen7_reg_list gen7_0_0_reg_list[] = { { gen7_0_0_gpu_registers, NULL }, { gen7_0_0_cx_misc_registers, NULL }, { gen7_0_0_dpm_registers, NULL }, diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h index 6f8ad50f32ce..772652eb61f3 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h @@ -95,7 +95,7 @@ static const u32 gen7_2_0_debugbus_blocks[] = { A7XX_DBGBUS_CCHE_2, }; -static struct gen7_shader_block gen7_2_0_shader_blocks[] = { +static const struct gen7_shader_block gen7_2_0_shader_blocks[] = { {A7XX_TP0_TMO_DATA, 0x200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, {A7XX_TP0_SMO_DATA, 0x80, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, @@ -489,7 +489,7 @@ static const struct gen7_sel_reg gen7_2_0_rb_rbp_sel = { .val = 0x9, }; -static struct gen7_cluster_registers gen7_2_0_clusters[] = { +static const struct gen7_cluster_registers gen7_2_0_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, gen7_2_0_noncontext_pipe_br_registers, }, { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, @@ -558,7 +558,7 @@ static struct gen7_cluster_registers gen7_2_0_clusters[] = { gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, }; -static struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { +static const struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 }, { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, @@ -573,6 +573,8 @@ static struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers, 0xaf80 }, { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_br_registers, 0xb600 }, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_NONE, 0, A7XX_USPTP, + gen7_0_0_tpl1_noncontext_pipe_none_registers, 0xb600 }, { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_lpac_registers, 0xb780 }, { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, @@ -737,7 +739,7 @@ static const u32 gen7_2_0_dpm_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_2_0_dpm_registers), 8)); -static struct gen7_reg_list gen7_2_0_reg_list[] = { +static const struct gen7_reg_list gen7_2_0_reg_list[] = { { gen7_2_0_gpu_registers, NULL }, { gen7_2_0_cx_misc_registers, NULL }, { gen7_2_0_dpm_registers, NULL }, diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h index e02cabb39f19..0956dfca1f05 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h @@ -117,7 +117,7 @@ static const u32 gen7_9_0_cx_debugbus_blocks[] = { A7XX_DBGBUS_GBIF_CX, }; -static struct gen7_shader_block gen7_9_0_shader_blocks[] = { +static const struct gen7_shader_block gen7_9_0_shader_blocks[] = { { A7XX_TP0_TMO_DATA, 0x0200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, { A7XX_TP0_SMO_DATA, 0x0080, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, { A7XX_TP0_MIPMAP_BASE_DATA, 0x03C0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, @@ -1116,7 +1116,7 @@ static const struct gen7_sel_reg gen7_9_0_rb_rbp_sel = { .val = 0x9, }; -static struct gen7_cluster_registers gen7_9_0_clusters[] = { +static const struct gen7_cluster_registers gen7_9_0_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, gen7_9_0_non_context_pipe_br_registers, }, { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, @@ -1185,7 +1185,7 @@ static struct gen7_cluster_registers gen7_9_0_clusters[] = { gen7_9_0_vpc_pipe_bv_cluster_vpc_ps_registers, }, }; -static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { +static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_9_0_non_context_sp_pipe_br_hlsq_state_registers, 0xae00}, { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, @@ -1294,34 +1294,34 @@ static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000}, }; -static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { +static const struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { { "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR, REG_A6XX_CP_SQE_STAT_DATA, 0x00040}, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x00200}, - { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, REG_A6XX_CP_ROQ_DBG_DATA, 0x00800}, - { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x08000}, - { "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR, + { "CP_BV_DRAW_STATE", REG_A7XX_CP_BV_DRAW_STATE_ADDR, REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x00200}, - { "CP_BV_ROQ_DBG_ADDR", REG_A7XX_CP_BV_ROQ_DBG_ADDR, + { "CP_BV_ROQ_DBG", REG_A7XX_CP_BV_ROQ_DBG_ADDR, REG_A7XX_CP_BV_ROQ_DBG_DATA, 0x00800}, - { "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, + { "CP_BV_SQE_UCODE_DBG", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x08000}, - { "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR, + { "CP_BV_SQE_STAT", REG_A7XX_CP_BV_SQE_STAT_ADDR, REG_A7XX_CP_BV_SQE_STAT_DATA, 0x00040}, - { "CP_RESOURCE_TBL", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR, + { "CP_RESOURCE_TABLE_DBG", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR, REG_A7XX_CP_RESOURCE_TABLE_DBG_DATA, 0x04100}, - { "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, + { "CP_LPAC_DRAW_STATE", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x00200}, - { "CP_LPAC_ROQ", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR, + { "CP_LPAC_ROQ_DBG", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR, REG_A7XX_CP_LPAC_ROQ_DBG_DATA, 0x00200}, - { "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, + { "CP_SQE_AC_UCODE_DBG", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x08000}, - { "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR, + { "CP_SQE_AC_STAT", REG_A7XX_CP_SQE_AC_STAT_ADDR, REG_A7XX_CP_SQE_AC_STAT_DATA, 0x00040}, - { "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, + { "CP_LPAC_FIFO_DBG", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x00040}, { "CP_AQE_ROQ_0", REG_A7XX_CP_AQE_ROQ_DBG_ADDR_0, REG_A7XX_CP_AQE_ROQ_DBG_DATA_0, 0x00100}, @@ -1337,7 +1337,7 @@ static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { REG_A7XX_CP_AQE_STAT_DATA_1, 0x00040}, }; -static struct gen7_reg_list gen7_9_0_reg_list[] = { +static const struct gen7_reg_list gen7_9_0_reg_list[] = { { gen7_9_0_gpu_registers, NULL}, { gen7_9_0_cx_misc_registers, NULL}, { gen7_9_0_cx_dbgc_registers, NULL}, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index d4b545448d74..94912b4708fb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -596,7 +596,7 @@ static void _dpu_crtc_complete_flip(struct drm_crtc *crtc) spin_lock_irqsave(&dev->event_lock, flags); if (dpu_crtc->event) { - DRM_DEBUG_VBL("%s: send event: %pK\n", dpu_crtc->name, + DRM_DEBUG_VBL("%s: send event: %p\n", dpu_crtc->name, dpu_crtc->event); trace_dpu_crtc_complete_flip(DRMID(crtc)); drm_crtc_send_vblank_event(crtc, dpu_crtc->event); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 05e5f3463e30..258edaa18fc0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -730,6 +730,8 @@ bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_st return false; conn_state = drm_atomic_get_new_connector_state(state, connector); + if (!conn_state) + return false; /** * These checks are duplicated from dpu_encoder_update_topology() since diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c index 11fb1bc54fa9..54b20faa0b69 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c @@ -31,14 +31,14 @@ static void dpu_setup_dspp_pcc(struct dpu_hw_dspp *ctx, u32 base; if (!ctx) { - DRM_ERROR("invalid ctx %pK\n", ctx); + DRM_ERROR("invalid ctx %p\n", ctx); return; } base = ctx->cap->sblk->pcc.base; if (!base) { - DRM_ERROR("invalid ctx %pK pcc base 0x%x\n", ctx, base); + DRM_ERROR("invalid ctx %p pcc base 0x%x\n", ctx, base); return; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 12dcb32b4724..a306077647c3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -1345,7 +1345,7 @@ static int dpu_kms_mmap_mdp5(struct dpu_kms *dpu_kms) dpu_kms->mmio = NULL; return ret; } - DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio); + DRM_DEBUG("mapped dpu address space @%p\n", dpu_kms->mmio); dpu_kms->vbif[VBIF_RT] = msm_ioremap_mdss(mdss_dev, dpu_kms->pdev, @@ -1380,7 +1380,7 @@ static int dpu_kms_mmap_dpu(struct dpu_kms *dpu_kms) dpu_kms->mmio = NULL; return ret; } - DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio); + DRM_DEBUG("mapped dpu address space @%p\n", dpu_kms->mmio); dpu_kms->vbif[VBIF_RT] = msm_ioremap(pdev, "vbif"); if (IS_ERR(dpu_kms->vbif[VBIF_RT])) { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 01171c535a27..6859e8ef6b05 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -1129,7 +1129,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, struct drm_plane_state *old_plane_state = drm_atomic_get_old_plane_state(state, plane); struct dpu_plane_state *pstate = to_dpu_plane_state(plane_state); - struct drm_crtc_state *crtc_state; + struct drm_crtc_state *crtc_state = NULL; int ret; if (IS_ERR(plane_state)) @@ -1162,7 +1162,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, if (!old_plane_state || !old_plane_state->fb || old_plane_state->src_w != plane_state->src_w || old_plane_state->src_h != plane_state->src_h || - old_plane_state->src_w != plane_state->src_w || + old_plane_state->crtc_w != plane_state->crtc_w || old_plane_state->crtc_h != plane_state->crtc_h || msm_framebuffer_format(old_plane_state->fb) != msm_framebuffer_format(plane_state->fb)) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 221f12db5f8b..4ea681130dba 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -5,6 +5,8 @@ #include <linux/clk-provider.h> #include <linux/platform_device.h> +#include <linux/pm_clock.h> +#include <linux/pm_runtime.h> #include <dt-bindings/phy/phy.h> #include "dsi_phy.h" @@ -511,30 +513,6 @@ int msm_dsi_cphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing, return 0; } -static int dsi_phy_enable_resource(struct msm_dsi_phy *phy) -{ - struct device *dev = &phy->pdev->dev; - int ret; - - ret = pm_runtime_resume_and_get(dev); - if (ret) - return ret; - - ret = clk_prepare_enable(phy->ahb_clk); - if (ret) { - DRM_DEV_ERROR(dev, "%s: can't enable ahb clk, %d\n", __func__, ret); - pm_runtime_put_sync(dev); - } - - return ret; -} - -static void dsi_phy_disable_resource(struct msm_dsi_phy *phy) -{ - clk_disable_unprepare(phy->ahb_clk); - pm_runtime_put(&phy->pdev->dev); -} - static const struct of_device_id dsi_phy_dt_match[] = { #ifdef CONFIG_DRM_MSM_DSI_28NM_PHY { .compatible = "qcom,dsi-phy-28nm-hpm", @@ -698,22 +676,20 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) if (ret) return ret; - phy->ahb_clk = msm_clk_get(pdev, "iface"); - if (IS_ERR(phy->ahb_clk)) - return dev_err_probe(dev, PTR_ERR(phy->ahb_clk), - "Unable to get ahb clk\n"); + platform_set_drvdata(pdev, phy); - ret = devm_pm_runtime_enable(&pdev->dev); + ret = devm_pm_runtime_enable(dev); if (ret) return ret; - /* PLL init will call into clk_register which requires - * register access, so we need to enable power and ahb clock. - */ - ret = dsi_phy_enable_resource(phy); + ret = devm_pm_clk_create(dev); if (ret) return ret; + ret = pm_clk_add(dev, "iface"); + if (ret < 0) + return dev_err_probe(dev, ret, "Unable to get iface clk\n"); + if (phy->cfg->ops.pll_init) { ret = phy->cfg->ops.pll_init(phy); if (ret) @@ -727,18 +703,19 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) return dev_err_probe(dev, ret, "Failed to register clk provider\n"); - dsi_phy_disable_resource(phy); - - platform_set_drvdata(pdev, phy); - return 0; } +static const struct dev_pm_ops dsi_phy_pm_ops = { + SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL) +}; + static struct platform_driver dsi_phy_platform_driver = { .probe = dsi_phy_driver_probe, .driver = { .name = "msm_dsi_phy", .of_match_table = dsi_phy_dt_match, + .pm = &dsi_phy_pm_ops, }, }; @@ -764,9 +741,9 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy, dev = &phy->pdev->dev; - ret = dsi_phy_enable_resource(phy); + ret = pm_runtime_resume_and_get(dev); if (ret) { - DRM_DEV_ERROR(dev, "%s: resource enable failed, %d\n", + DRM_DEV_ERROR(dev, "%s: resume failed, %d\n", __func__, ret); goto res_en_fail; } @@ -810,7 +787,7 @@ pll_restor_fail: phy_en_fail: regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies); reg_en_fail: - dsi_phy_disable_resource(phy); + pm_runtime_put(dev); res_en_fail: return ret; } @@ -823,7 +800,7 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy) phy->cfg->ops.disable(phy); regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies); - dsi_phy_disable_resource(phy); + pm_runtime_put(&phy->pdev->dev); } void msm_dsi_phy_set_usecase(struct msm_dsi_phy *phy, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index c558f8df1684..3cbf08231492 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -104,7 +104,6 @@ struct msm_dsi_phy { phys_addr_t lane_size; int id; - struct clk *ahb_clk; struct regulator_bulk_data *supplies; struct msm_dsi_dphy_timing timing; diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index bbda865addae..97dc70876442 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -325,25 +325,28 @@ static struct drm_info_list msm_debugfs_list[] = { static int late_init_minor(struct drm_minor *minor) { - struct drm_device *dev = minor->dev; - struct msm_drm_private *priv = dev->dev_private; + struct drm_device *dev; + struct msm_drm_private *priv; int ret; if (!minor) return 0; + dev = minor->dev; + priv = dev->dev_private; + if (!priv->gpu_pdev) return 0; ret = msm_rd_debugfs_init(minor); if (ret) { - DRM_DEV_ERROR(minor->dev->dev, "could not install rd debugfs\n"); + DRM_DEV_ERROR(dev->dev, "could not install rd debugfs\n"); return ret; } ret = msm_perf_debugfs_init(minor); if (ret) { - DRM_DEV_ERROR(minor->dev->dev, "could not install perf debugfs\n"); + DRM_DEV_ERROR(dev->dev, "could not install perf debugfs\n"); return ret; } diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 7ff994d4f91a..e7631f4ef530 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -95,7 +95,6 @@ void msm_gem_vma_get(struct drm_gem_object *obj) void msm_gem_vma_put(struct drm_gem_object *obj) { struct msm_drm_private *priv = obj->dev->dev_private; - struct drm_exec exec; if (atomic_dec_return(&to_msm_bo(obj)->vma_ref)) return; @@ -103,9 +102,13 @@ void msm_gem_vma_put(struct drm_gem_object *obj) if (!priv->kms) return; +#ifdef CONFIG_DRM_MSM_KMS + struct drm_exec exec; + msm_gem_lock_vm_and_obj(&exec, obj, priv->kms->vm); put_iova_spaces(obj, priv->kms->vm, true, "vma_put"); drm_exec_fini(&exec); /* drop locks */ +#endif } /* @@ -663,9 +666,13 @@ int msm_gem_set_iova(struct drm_gem_object *obj, static bool is_kms_vm(struct drm_gpuvm *vm) { +#ifdef CONFIG_DRM_MSM_KMS struct msm_drm_private *priv = vm->drm->dev_private; return priv->kms && (priv->kms->vm == vm); +#else + return false; +#endif } /* @@ -1113,10 +1120,12 @@ static void msm_gem_free_object(struct drm_gem_object *obj) put_pages(obj); } - if (msm_obj->flags & MSM_BO_NO_SHARE) { + if (obj->resv != &obj->_resv) { struct drm_gem_object *r_obj = container_of(obj->resv, struct drm_gem_object, _resv); + WARN_ON(!(msm_obj->flags & MSM_BO_NO_SHARE)); + /* Drop reference we hold to shared resv obj: */ drm_gem_object_put(r_obj); } diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index 88239da1cd72..751c3b4965bc 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -100,7 +100,7 @@ struct msm_gem_vm { * * Only used for kernel managed VMs, unused for user managed VMs. * - * Protected by @mm_lock. + * Protected by vm lock. See msm_gem_lock_vm_and_obj(), for ex. */ struct drm_mm mm; diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 5f8e939a5906..3ab3b27134f9 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -271,32 +271,37 @@ out: return ret; } -/* This is where we make sure all the bo's are reserved and pin'd: */ -static int submit_lock_objects(struct msm_gem_submit *submit) +static int submit_lock_objects_vmbind(struct msm_gem_submit *submit) { - unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT; + unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT | DRM_EXEC_IGNORE_DUPLICATES; struct drm_exec *exec = &submit->exec; - int ret; + int ret = 0; - if (msm_context_is_vmbind(submit->queue->ctx)) { - flags |= DRM_EXEC_IGNORE_DUPLICATES; + drm_exec_init(&submit->exec, flags, submit->nr_bos); - drm_exec_init(&submit->exec, flags, submit->nr_bos); + drm_exec_until_all_locked (&submit->exec) { + ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1); + drm_exec_retry_on_contention(exec); + if (ret) + break; - drm_exec_until_all_locked (&submit->exec) { - ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1); - drm_exec_retry_on_contention(exec); - if (ret) - return ret; + ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1); + drm_exec_retry_on_contention(exec); + if (ret) + break; + } - ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1); - drm_exec_retry_on_contention(exec); - if (ret) - return ret; - } + return ret; +} - return 0; - } +/* This is where we make sure all the bo's are reserved and pin'd: */ +static int submit_lock_objects(struct msm_gem_submit *submit) +{ + unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT; + int ret = 0; + + if (msm_context_is_vmbind(submit->queue->ctx)) + return submit_lock_objects_vmbind(submit); drm_exec_init(&submit->exec, flags, submit->nr_bos); @@ -305,17 +310,17 @@ static int submit_lock_objects(struct msm_gem_submit *submit) drm_gpuvm_resv_obj(submit->vm)); drm_exec_retry_on_contention(&submit->exec); if (ret) - return ret; + break; for (unsigned i = 0; i < submit->nr_bos; i++) { struct drm_gem_object *obj = submit->bos[i].obj; ret = drm_exec_prepare_obj(&submit->exec, obj, 1); drm_exec_retry_on_contention(&submit->exec); if (ret) - return ret; + break; } } - return 0; + return ret; } static int submit_fence_sync(struct msm_gem_submit *submit) @@ -514,14 +519,15 @@ out: */ static void submit_cleanup(struct msm_gem_submit *submit, bool error) { + if (error) + submit_unpin_objects(submit); + if (submit->exec.objects) drm_exec_fini(&submit->exec); - if (error) { - submit_unpin_objects(submit); - /* job wasn't enqueued to scheduler, so early retirement: */ + /* if job wasn't enqueued to scheduler, early retirement: */ + if (error) msm_submit_retire(submit); - } } void msm_submit_retire(struct msm_gem_submit *submit) @@ -769,12 +775,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (ret == 0 && args->flags & MSM_SUBMIT_FENCE_FD_OUT) { sync_file = sync_file_create(submit->user_fence); - if (!sync_file) { + if (!sync_file) ret = -ENOMEM; - } else { - fd_install(out_fence_fd, sync_file->file); - args->fence_fd = out_fence_fd; - } } if (ret) @@ -812,10 +814,14 @@ out: out_unlock: mutex_unlock(&queue->lock); out_post_unlock: - if (ret && (out_fence_fd >= 0)) { - put_unused_fd(out_fence_fd); + if (ret) { + if (out_fence_fd >= 0) + put_unused_fd(out_fence_fd); if (sync_file) fput(sync_file->file); + } else if (sync_file) { + fd_install(out_fence_fd, sync_file->file); + args->fence_fd = out_fence_fd; } if (!IS_ERR_OR_NULL(submit)) { diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index 3cd8562a5109..00d0f3b7ba32 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -319,13 +319,10 @@ msm_gem_vma_map(struct drm_gpuva *vma, int prot, struct sg_table *sgt) mutex_lock(&vm->mmu_lock); /* - * NOTE: iommu/io-pgtable can allocate pages, so we cannot hold + * NOTE: if not using pgtable preallocation, we cannot hold * a lock across map/unmap which is also used in the job_run() * path, as this can cause deadlock in job_run() vs shrinker/ * reclaim. - * - * Revisit this if we can come up with a scheme to pre-alloc pages - * for the pgtable in map/unmap ops. */ ret = vm_map_op(vm, &(struct msm_vm_map_op){ .iova = vma->va.addr, @@ -454,6 +451,8 @@ msm_gem_vm_bo_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) struct op_arg { unsigned flags; struct msm_vm_bind_job *job; + const struct msm_vm_bind_op *op; + bool kept; }; static void @@ -475,14 +474,18 @@ vma_from_op(struct op_arg *arg, struct drm_gpuva_op_map *op) } static int -msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *arg) +msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg) { - struct msm_vm_bind_job *job = ((struct op_arg *)arg)->job; + struct op_arg *arg = _arg; + struct msm_vm_bind_job *job = arg->job; struct drm_gem_object *obj = op->map.gem.obj; struct drm_gpuva *vma; struct sg_table *sgt; unsigned prot; + if (arg->kept) + return 0; + vma = vma_from_op(arg, &op->map); if (WARN_ON(IS_ERR(vma))) return PTR_ERR(vma); @@ -602,15 +605,41 @@ msm_gem_vm_sm_step_remap(struct drm_gpuva_op *op, void *arg) } static int -msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *arg) +msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *_arg) { - struct msm_vm_bind_job *job = ((struct op_arg *)arg)->job; + struct op_arg *arg = _arg; + struct msm_vm_bind_job *job = arg->job; struct drm_gpuva *vma = op->unmap.va; struct msm_gem_vma *msm_vma = to_msm_vma(vma); vm_dbg("%p:%p:%p: %016llx %016llx", vma->vm, vma, vma->gem.obj, vma->va.addr, vma->va.range); + /* + * Detect in-place remap. Turnip does this to change the vma flags, + * in particular MSM_VMA_DUMP. In this case we want to avoid actually + * touching the page tables, as that would require synchronization + * against SUBMIT jobs running on the GPU. + */ + if (op->unmap.keep && + (arg->op->op == MSM_VM_BIND_OP_MAP) && + (vma->gem.obj == arg->op->obj) && + (vma->gem.offset == arg->op->obj_offset) && + (vma->va.addr == arg->op->iova) && + (vma->va.range == arg->op->range)) { + /* We are only expecting a single in-place unmap+map cb pair: */ + WARN_ON(arg->kept); + + /* Leave the existing VMA in place, but signal that to the map cb: */ + arg->kept = true; + + /* Only flags are changing, so update that in-place: */ + unsigned orig_flags = vma->flags & (DRM_GPUVA_USERBITS - 1); + vma->flags = orig_flags | arg->flags; + + return 0; + } + if (!msm_vma->mapped) goto out_close; @@ -1271,6 +1300,7 @@ vm_bind_job_prepare(struct msm_vm_bind_job *job) const struct msm_vm_bind_op *op = &job->ops[i]; struct op_arg arg = { .job = job, + .op = op, }; switch (op->op) { @@ -1460,12 +1490,8 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file) if (args->flags & MSM_VM_BIND_FENCE_FD_OUT) { sync_file = sync_file_create(job->fence); - if (!sync_file) { + if (!sync_file) ret = -ENOMEM; - } else { - fd_install(out_fence_fd, sync_file->file); - args->fence_fd = out_fence_fd; - } } if (ret) @@ -1494,10 +1520,14 @@ out: out_unlock: mutex_unlock(&queue->lock); out_post_unlock: - if (ret && (out_fence_fd >= 0)) { - put_unused_fd(out_fence_fd); + if (ret) { + if (out_fence_fd >= 0) + put_unused_fd(out_fence_fd); if (sync_file) fput(sync_file->file); + } else if (sync_file) { + fd_install(out_fence_fd, sync_file->file); + args->fence_fd = out_fence_fd; } if (!IS_ERR_OR_NULL(job)) { diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index c317b25a8162..26c5ce897cbb 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -465,6 +465,7 @@ static void recover_worker(struct kthread_work *work) struct msm_gem_submit *submit; struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu); char *comm = NULL, *cmd = NULL; + struct task_struct *task; int i; mutex_lock(&gpu->lock); @@ -482,16 +483,20 @@ static void recover_worker(struct kthread_work *work) /* Increment the fault counts */ submit->queue->faults++; - if (submit->vm) { + + task = get_pid_task(submit->pid, PIDTYPE_PID); + if (!task) + gpu->global_faults++; + else { struct msm_gem_vm *vm = to_msm_vm(submit->vm); vm->faults++; /* * If userspace has opted-in to VM_BIND (and therefore userspace - * management of the VM), faults mark the VM as unusuable. This + * management of the VM), faults mark the VM as unusable. This * matches vulkan expectations (vulkan is the main target for - * VM_BIND) + * VM_BIND). */ if (!vm->managed) msm_gem_vm_unusable(submit->vm); @@ -553,8 +558,15 @@ static void recover_worker(struct kthread_work *work) unsigned long flags; spin_lock_irqsave(&ring->submit_lock, flags); - list_for_each_entry(submit, &ring->submits, node) + list_for_each_entry(submit, &ring->submits, node) { + /* + * If the submit uses an unusable vm make sure + * we don't actually run it + */ + if (to_msm_vm(submit->vm)->unusable) + submit->nr_cmds = 0; gpu->funcs->submit(gpu, submit); + } spin_unlock_irqrestore(&ring->submit_lock, flags); } } diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 55c29f49b788..76cdd5ea06a0 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -14,7 +14,9 @@ struct msm_iommu { struct msm_mmu base; struct iommu_domain *domain; - atomic_t pagetables; + + struct mutex init_lock; /* protects pagetables counter and prr_page */ + int pagetables; struct page *prr_page; struct kmem_cache *pt_cache; @@ -227,7 +229,8 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu) * If this is the last attached pagetable for the parent, * disable TTBR0 in the arm-smmu driver */ - if (atomic_dec_return(&iommu->pagetables) == 0) { + mutex_lock(&iommu->init_lock); + if (--iommu->pagetables == 0) { adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, NULL); if (adreno_smmu->set_prr_bit) { @@ -236,6 +239,7 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu) iommu->prr_page = NULL; } } + mutex_unlock(&iommu->init_lock); free_io_pgtable_ops(pagetable->pgtbl_ops); kfree(pagetable); @@ -568,9 +572,12 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool kernel_m * If this is the first pagetable that we've allocated, send it back to * the arm-smmu driver as a trigger to set up TTBR0 */ - if (atomic_inc_return(&iommu->pagetables) == 1) { + mutex_lock(&iommu->init_lock); + if (iommu->pagetables++ == 0) { ret = adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, &ttbr0_cfg); if (ret) { + iommu->pagetables--; + mutex_unlock(&iommu->init_lock); free_io_pgtable_ops(pagetable->pgtbl_ops); kfree(pagetable); return ERR_PTR(ret); @@ -595,6 +602,7 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool kernel_m adreno_smmu->set_prr_bit(adreno_smmu->cookie, true); } } + mutex_unlock(&iommu->init_lock); /* Needed later for TLB flush */ pagetable->parent = parent; @@ -730,7 +738,7 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) iommu->domain = domain; msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU); - atomic_set(&iommu->pagetables, 0); + mutex_init(&iommu->init_lock); ret = iommu_attach_device(iommu->domain, dev); if (ret) { diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c index 6889f1c1e721..56828d218e88 100644 --- a/drivers/gpu/drm/msm/msm_kms.c +++ b/drivers/gpu/drm/msm/msm_kms.c @@ -275,6 +275,12 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv) if (ret) return ret; + ret = msm_disp_snapshot_init(ddev); + if (ret) { + DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret); + return ret; + } + ret = priv->kms_init(ddev); if (ret) { DRM_DEV_ERROR(dev, "failed to load kms\n"); @@ -327,10 +333,6 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv) goto err_msm_uninit; } - ret = msm_disp_snapshot_init(ddev); - if (ret) - DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret); - drm_mode_config_reset(ddev); return 0; diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 1f5fe7811e01..39885b333910 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -423,7 +423,7 @@ static struct msm_mdss *msm_mdss_init(struct platform_device *pdev, bool is_mdp5 if (IS_ERR(msm_mdss->mmio)) return ERR_CAST(msm_mdss->mmio); - dev_dbg(&pdev->dev, "mapped mdss address space @%pK\n", msm_mdss->mmio); + dev_dbg(&pdev->dev, "mapped mdss address space @%p\n", msm_mdss->mmio); ret = msm_mdss_parse_data_bus_icc_path(&pdev->dev, msm_mdss); if (ret) diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml index d860fd94feae..86fab2750ba7 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml @@ -594,10 +594,14 @@ by a particular renderpass/blit. <reg32 offset="0x0600" name="DBGC_CFG_DBGBUS_SEL_A"/> <reg32 offset="0x0601" name="DBGC_CFG_DBGBUS_SEL_B"/> <reg32 offset="0x0602" name="DBGC_CFG_DBGBUS_SEL_C"/> - <reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D"> + <reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D" variants="A6XX"> <bitfield high="7" low="0" name="PING_INDEX"/> <bitfield high="15" low="8" name="PING_BLK_SEL"/> </reg32> + <reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D" variants="A7XX-"> + <bitfield high="7" low="0" name="PING_INDEX"/> + <bitfield high="24" low="16" name="PING_BLK_SEL"/> + </reg32> <reg32 offset="0x0604" name="DBGC_CFG_DBGBUS_CNTLT"> <bitfield high="5" low="0" name="TRACEEN"/> <bitfield high="14" low="12" name="GRANU"/> @@ -3796,6 +3800,14 @@ by a particular renderpass/blit. <reg32 offset="0x0030" name="CFG_DBGBUS_TRACE_BUF2"/> </domain> +<domain name="A7XX_CX_DBGC" width="32"> + <!-- Bitfields shifted, but otherwise the same: --> + <reg32 offset="0x0000" name="CFG_DBGBUS_SEL_A" variants="A7XX-"> + <bitfield high="7" low="0" name="PING_INDEX"/> + <bitfield high="24" low="16" name="PING_BLK_SEL"/> + </reg32> +</domain> + <domain name="A6XX_CX_MISC" width="32" prefix="variant" varset="chip"> <reg32 offset="0x0001" name="SYSTEM_CACHE_CNTL_0"/> <reg32 offset="0x0002" name="SYSTEM_CACHE_CNTL_1"/> diff --git a/drivers/gpu/drm/msm/registers/display/dsi.xml b/drivers/gpu/drm/msm/registers/display/dsi.xml index 501ffc585a9f..c7a7b633d747 100644 --- a/drivers/gpu/drm/msm/registers/display/dsi.xml +++ b/drivers/gpu/drm/msm/registers/display/dsi.xml @@ -159,28 +159,28 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="RGB_SWAP" low="12" high="14" type="dsi_rgb_swap"/> </reg32> <reg32 offset="0x00020" name="ACTIVE_H"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00024" name="ACTIVE_V"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00028" name="TOTAL"> - <bitfield name="H_TOTAL" low="0" high="11" type="uint"/> - <bitfield name="V_TOTAL" low="16" high="27" type="uint"/> + <bitfield name="H_TOTAL" low="0" high="15" type="uint"/> + <bitfield name="V_TOTAL" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x0002c" name="ACTIVE_HSYNC"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00030" name="ACTIVE_VSYNC_HPOS"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00034" name="ACTIVE_VSYNC_VPOS"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00038" name="CMD_DMA_CTRL"> @@ -209,8 +209,8 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="WORD_COUNT" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00058" name="CMD_MDP_STREAM0_TOTAL"> - <bitfield name="H_TOTAL" low="0" high="11" type="uint"/> - <bitfield name="V_TOTAL" low="16" high="27" type="uint"/> + <bitfield name="H_TOTAL" low="0" high="15" type="uint"/> + <bitfield name="V_TOTAL" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x0005c" name="CMD_MDP_STREAM1_CTRL"> <bitfield name="DATA_TYPE" low="0" high="5" type="uint"/> diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 11d5b923d6e7..e2c55f4b9c5a 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -795,6 +795,10 @@ static bool nv50_plane_format_mod_supported(struct drm_plane *plane, struct nouveau_drm *drm = nouveau_drm(plane->dev); uint8_t i; + /* All chipsets can display all formats in linear layout */ + if (modifier == DRM_FORMAT_MOD_LINEAR) + return true; + if (drm->client.device.info.chipset < 0xc0) { const struct drm_format_info *info = drm_format_info(format); const uint8_t kind = (modifier >> 12) & 0xff; diff --git a/drivers/gpu/drm/nouveau/gv100_fence.c b/drivers/gpu/drm/nouveau/gv100_fence.c index cccdeca72002..317e516c4ec7 100644 --- a/drivers/gpu/drm/nouveau/gv100_fence.c +++ b/drivers/gpu/drm/nouveau/gv100_fence.c @@ -18,7 +18,7 @@ gv100_fence_emit32(struct nouveau_channel *chan, u64 virtual, u32 sequence) struct nvif_push *push = &chan->chan.push; int ret; - ret = PUSH_WAIT(push, 8); + ret = PUSH_WAIT(push, 13); if (ret) return ret; @@ -32,6 +32,11 @@ gv100_fence_emit32(struct nouveau_channel *chan, u64 virtual, u32 sequence) NVDEF(NVC36F, SEM_EXECUTE, PAYLOAD_SIZE, 32BIT) | NVDEF(NVC36F, SEM_EXECUTE, RELEASE_TIMESTAMP, DIS)); + PUSH_MTHD(push, NVC36F, MEM_OP_A, 0, + MEM_OP_B, 0, + MEM_OP_C, NVDEF(NVC36F, MEM_OP_C, MEMBAR_TYPE, SYS_MEMBAR), + MEM_OP_D, NVDEF(NVC36F, MEM_OP_D, OPERATION, MEMBAR)); + PUSH_MTHD(push, NVC36F, NON_STALL_INTERRUPT, 0); PUSH_KICK(push); diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h b/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h index 8735dda4c8a7..338f74b9f501 100644 --- a/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h +++ b/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h @@ -7,6 +7,91 @@ #define NVC36F_NON_STALL_INTERRUPT (0x00000020) #define NVC36F_NON_STALL_INTERRUPT_HANDLE 31:0 +// NOTE - MEM_OP_A and MEM_OP_B have been replaced in gp100 with methods for +// specifying the page address for a targeted TLB invalidate and the uTLB for +// a targeted REPLAY_CANCEL for UVM. +// The previous MEM_OP_A/B functionality is in MEM_OP_C/D, with slightly +// rearranged fields. +#define NVC36F_MEM_OP_A (0x00000028) +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_TARGET_CLIENT_UNIT_ID 5:0 // only relevant for REPLAY_CANCEL_TARGETED +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_INVALIDATION_SIZE 5:0 // Used to specify size of invalidate, used for invalidates which are not of the REPLAY_CANCEL_TARGETED type +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_TARGET_GPC_ID 10:6 // only relevant for REPLAY_CANCEL_TARGETED +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_MMU_ENGINE_ID 6:0 // only relevant for REPLAY_CANCEL_VA_GLOBAL +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR 11:11 +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR_EN 0x00000001 +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR_DIS 0x00000000 +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_TARGET_ADDR_LO 31:12 +#define NVC36F_MEM_OP_B (0x0000002c) +#define NVC36F_MEM_OP_B_TLB_INVALIDATE_TARGET_ADDR_HI 31:0 +#define NVC36F_MEM_OP_C (0x00000030) +#define NVC36F_MEM_OP_C_MEMBAR_TYPE 2:0 +#define NVC36F_MEM_OP_C_MEMBAR_TYPE_SYS_MEMBAR 0x00000000 +#define NVC36F_MEM_OP_C_MEMBAR_TYPE_MEMBAR 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB 0:0 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ONE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ALL 0x00000001 // Probably nonsensical for MMU_TLB_INVALIDATE_TARGETED +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC 1:1 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC_ENABLE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC_DISABLE 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY 4:2 // only relevant if GPC ENABLE +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_NONE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_START 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_START_ACK_ALL 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_TARGETED 0x00000003 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_GLOBAL 0x00000004 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_VA_GLOBAL 0x00000005 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE 6:5 // only relevant if GPC ENABLE +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_NONE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_GLOBALLY 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_INTRANODE 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE 9:7 //only relevant for REPLAY_CANCEL_VA_GLOBAL +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_READ 0 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_WRITE 1 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_STRONG 2 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_RSVRVD 3 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_WEAK 4 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_ALL 5 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_WRITE_AND_ATOMIC 6 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ALL 7 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL 9:7 // Invalidate affects this level and all below +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_ALL 0x00000000 // Invalidate tlb caches at all levels of the page table +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_PTE_ONLY 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE0 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE1 0x00000003 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE2 0x00000004 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE3 0x00000005 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE4 0x00000006 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE5 0x00000007 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE 11:10 // only relevant if PDB_ONE +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_VID_MEM 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_SYS_MEM_COHERENT 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_SYS_MEM_NONCOHERENT 0x00000003 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ADDR_LO 31:12 // only relevant if PDB_ONE +#define NVC36F_MEM_OP_C_ACCESS_COUNTER_CLR_TARGETED_NOTIFY_TAG 19:0 +// MEM_OP_D MUST be preceded by MEM_OPs A-C. +#define NVC36F_MEM_OP_D (0x00000034) +#define NVC36F_MEM_OP_D_TLB_INVALIDATE_PDB_ADDR_HI 26:0 // only relevant if PDB_ONE +#define NVC36F_MEM_OP_D_OPERATION 31:27 +#define NVC36F_MEM_OP_D_OPERATION_MEMBAR 0x00000005 +#define NVC36F_MEM_OP_D_OPERATION_MMU_TLB_INVALIDATE 0x00000009 +#define NVC36F_MEM_OP_D_OPERATION_MMU_TLB_INVALIDATE_TARGETED 0x0000000a +#define NVC36F_MEM_OP_D_OPERATION_L2_PEERMEM_INVALIDATE 0x0000000d +#define NVC36F_MEM_OP_D_OPERATION_L2_SYSMEM_INVALIDATE 0x0000000e +// CLEAN_LINES is an alias for Tegra/GPU IP usage +#define NVC36F_MEM_OP_B_OPERATION_L2_INVALIDATE_CLEAN_LINES 0x0000000e +#define NVC36F_MEM_OP_D_OPERATION_L2_CLEAN_COMPTAGS 0x0000000f +#define NVC36F_MEM_OP_D_OPERATION_L2_FLUSH_DIRTY 0x00000010 +#define NVC36F_MEM_OP_D_OPERATION_L2_WAIT_FOR_SYS_PENDING_READS 0x00000015 +#define NVC36F_MEM_OP_D_OPERATION_ACCESS_COUNTER_CLR 0x00000016 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE 1:0 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_MIMC 0x00000000 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_MOMC 0x00000001 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_ALL 0x00000002 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_TARGETED 0x00000003 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE 2:2 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE_MIMC 0x00000000 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE_MOMC 0x00000001 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_BANK 6:3 #define NVC36F_SEM_ADDR_LO (0x0000005c) #define NVC36F_SEM_ADDR_LO_OFFSET 31:2 #define NVC36F_SEM_ADDR_HI (0x00000060) diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 9f345a008717..869d4335c0f4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -240,21 +240,6 @@ nouveau_fence_emit(struct nouveau_fence *fence) return ret; } -void -nouveau_fence_cancel(struct nouveau_fence *fence) -{ - struct nouveau_fence_chan *fctx = nouveau_fctx(fence); - unsigned long flags; - - spin_lock_irqsave(&fctx->lock, flags); - if (!dma_fence_is_signaled_locked(&fence->base)) { - dma_fence_set_error(&fence->base, -ECANCELED); - if (nouveau_fence_signal(fence)) - nvif_event_block(&fctx->event); - } - spin_unlock_irqrestore(&fctx->lock, flags); -} - bool nouveau_fence_done(struct nouveau_fence *fence) { diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 9957a919bd38..183dd43ecfff 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -29,7 +29,6 @@ void nouveau_fence_unref(struct nouveau_fence **); int nouveau_fence_emit(struct nouveau_fence *); bool nouveau_fence_done(struct nouveau_fence *); -void nouveau_fence_cancel(struct nouveau_fence *fence); int nouveau_fence_wait(struct nouveau_fence *, bool lazy, bool intr); int nouveau_fence_sync(struct nouveau_bo *, struct nouveau_channel *, bool exclusive, bool intr); diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c index 0cc0bc9f9952..e60f7892f5ce 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.c +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c @@ -11,7 +11,6 @@ #include "nouveau_exec.h" #include "nouveau_abi16.h" #include "nouveau_sched.h" -#include "nouveau_chan.h" #define NOUVEAU_SCHED_JOB_TIMEOUT_MS 10000 @@ -122,9 +121,11 @@ nouveau_job_done(struct nouveau_job *job) { struct nouveau_sched *sched = job->sched; - spin_lock(&sched->job_list.lock); + spin_lock(&sched->job.list.lock); list_del(&job->entry); - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); + + wake_up(&sched->job.wq); } void @@ -305,9 +306,9 @@ nouveau_job_submit(struct nouveau_job *job) } /* Submit was successful; add the job to the schedulers job list. */ - spin_lock(&sched->job_list.lock); - list_add(&job->entry, &sched->job_list.head); - spin_unlock(&sched->job_list.lock); + spin_lock(&sched->job.list.lock); + list_add(&job->entry, &sched->job.list.head); + spin_unlock(&sched->job.list.lock); drm_sched_job_arm(&job->base); job->done_fence = dma_fence_get(&job->base.s_fence->finished); @@ -392,23 +393,10 @@ nouveau_sched_free_job(struct drm_sched_job *sched_job) nouveau_job_fini(job); } -static void -nouveau_sched_cancel_job(struct drm_sched_job *sched_job) -{ - struct nouveau_fence *fence; - struct nouveau_job *job; - - job = to_nouveau_job(sched_job); - fence = to_nouveau_fence(job->done_fence); - - nouveau_fence_cancel(fence); -} - static const struct drm_sched_backend_ops nouveau_sched_ops = { .run_job = nouveau_sched_run_job, .timedout_job = nouveau_sched_timedout_job, .free_job = nouveau_sched_free_job, - .cancel_job = nouveau_sched_cancel_job, }; static int @@ -458,8 +446,9 @@ nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm, goto fail_sched; mutex_init(&sched->mutex); - spin_lock_init(&sched->job_list.lock); - INIT_LIST_HEAD(&sched->job_list.head); + spin_lock_init(&sched->job.list.lock); + INIT_LIST_HEAD(&sched->job.list.head); + init_waitqueue_head(&sched->job.wq); return 0; @@ -493,12 +482,16 @@ nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, return 0; } + static void nouveau_sched_fini(struct nouveau_sched *sched) { struct drm_gpu_scheduler *drm_sched = &sched->base; struct drm_sched_entity *entity = &sched->entity; + rmb(); /* for list_empty to work without lock */ + wait_event(sched->job.wq, list_empty(&sched->job.list.head)); + drm_sched_entity_fini(entity); drm_sched_fini(drm_sched); diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h index b98c3f0bef30..20cd1da8db73 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.h +++ b/drivers/gpu/drm/nouveau/nouveau_sched.h @@ -103,9 +103,12 @@ struct nouveau_sched { struct mutex mutex; struct { - struct list_head head; - spinlock_t lock; - } job_list; + struct { + struct list_head head; + spinlock_t lock; + } list; + struct wait_queue_head wq; + } job; }; int nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index ddfc46bc1b3e..48f105239f42 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1019,8 +1019,8 @@ bind_validate_map_sparse(struct nouveau_job *job, u64 addr, u64 range) u64 end = addr + range; again: - spin_lock(&sched->job_list.lock); - list_for_each_entry(__job, &sched->job_list.head, entry) { + spin_lock(&sched->job.list.lock); + list_for_each_entry(__job, &sched->job.list.head, entry) { struct nouveau_uvmm_bind_job *bind_job = to_uvmm_bind_job(__job); list_for_each_op(op, &bind_job->ops) { @@ -1030,7 +1030,7 @@ again: if (!(end <= op_addr || addr >= op_end)) { nouveau_uvmm_bind_job_get(bind_job); - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); wait_for_completion(&bind_job->complete); nouveau_uvmm_bind_job_put(bind_job); goto again; @@ -1038,7 +1038,7 @@ again: } } } - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); } static int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c index fdffa0391b31..6fd4e60634fb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c @@ -350,6 +350,8 @@ nvkm_fifo_dtor(struct nvkm_engine *engine) nvkm_chid_unref(&fifo->chid); nvkm_event_fini(&fifo->nonstall.event); + if (fifo->func->nonstall_dtor) + fifo->func->nonstall_dtor(fifo); mutex_destroy(&fifo->mutex); if (fifo->func->dtor) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c index e74493a4569e..6848a56f20c0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c @@ -517,19 +517,11 @@ ga100_fifo_nonstall_intr(struct nvkm_inth *inth) static void ga100_fifo_nonstall_block(struct nvkm_event *event, int type, int index) { - struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event); - struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0); - - nvkm_inth_block(&runl->nonstall.inth); } static void ga100_fifo_nonstall_allow(struct nvkm_event *event, int type, int index) { - struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event); - struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0); - - nvkm_inth_allow(&runl->nonstall.inth); } const struct nvkm_event_func @@ -564,12 +556,26 @@ ga100_fifo_nonstall_ctor(struct nvkm_fifo *fifo) if (ret) return ret; + nvkm_inth_allow(&runl->nonstall.inth); + nr = max(nr, runl->id + 1); } return nr; } +void +ga100_fifo_nonstall_dtor(struct nvkm_fifo *fifo) +{ + struct nvkm_runl *runl; + + nvkm_runl_foreach(runl, fifo) { + if (runl->nonstall.vector < 0) + continue; + nvkm_inth_block(&runl->nonstall.inth); + } +} + int ga100_fifo_runl_ctor(struct nvkm_fifo *fifo) { @@ -599,6 +605,7 @@ ga100_fifo = { .runl_ctor = ga100_fifo_runl_ctor, .mmu_fault = &tu102_fifo_mmu_fault, .nonstall_ctor = ga100_fifo_nonstall_ctor, + .nonstall_dtor = ga100_fifo_nonstall_dtor, .nonstall = &ga100_fifo_nonstall, .runl = &ga100_runl, .runq = &ga100_runq, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c index 755235f55b3a..18a0b1f4eab7 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c @@ -30,6 +30,7 @@ ga102_fifo = { .runl_ctor = ga100_fifo_runl_ctor, .mmu_fault = &tu102_fifo_mmu_fault, .nonstall_ctor = ga100_fifo_nonstall_ctor, + .nonstall_dtor = ga100_fifo_nonstall_dtor, .nonstall = &ga100_fifo_nonstall, .runl = &ga100_runl, .runq = &ga100_runq, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h index 5e81ae195329..fff1428ef267 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h @@ -41,6 +41,7 @@ struct nvkm_fifo_func { void (*start)(struct nvkm_fifo *, unsigned long *); int (*nonstall_ctor)(struct nvkm_fifo *); + void (*nonstall_dtor)(struct nvkm_fifo *); const struct nvkm_event_func *nonstall; const struct nvkm_runl_func *runl; @@ -200,6 +201,7 @@ u32 tu102_chan_doorbell_handle(struct nvkm_chan *); int ga100_fifo_runl_ctor(struct nvkm_fifo *); int ga100_fifo_nonstall_ctor(struct nvkm_fifo *); +void ga100_fifo_nonstall_dtor(struct nvkm_fifo *); extern const struct nvkm_event_func ga100_fifo_nonstall; extern const struct nvkm_runl_func ga100_runl; extern const struct nvkm_runq_func ga100_runq; diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c index b7da3ab44c27..7c43397c19e6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c @@ -103,7 +103,7 @@ gm200_flcn_pio_imem_wr_init(struct nvkm_falcon *falcon, u8 port, bool sec, u32 i static void gm200_flcn_pio_imem_wr(struct nvkm_falcon *falcon, u8 port, const u8 *img, int len, u16 tag) { - nvkm_falcon_wr32(falcon, 0x188 + (port * 0x10), tag++); + nvkm_falcon_wr32(falcon, 0x188 + (port * 0x10), tag); while (len >= 4) { nvkm_falcon_wr32(falcon, 0x184 + (port * 0x10), *(u32 *)img); img += 4; @@ -249,9 +249,11 @@ int gm200_flcn_fw_load(struct nvkm_falcon_fw *fw) { struct nvkm_falcon *falcon = fw->falcon; - int target, ret; + int ret; if (fw->inst) { + int target; + nvkm_falcon_mask(falcon, 0x048, 0x00000001, 0x00000001); switch (nvkm_memory_target(fw->inst)) { @@ -285,15 +287,6 @@ gm200_flcn_fw_load(struct nvkm_falcon_fw *fw) } if (fw->boot) { - switch (nvkm_memory_target(&fw->fw.mem.memory)) { - case NVKM_MEM_TARGET_VRAM: target = 4; break; - case NVKM_MEM_TARGET_HOST: target = 5; break; - case NVKM_MEM_TARGET_NCOH: target = 6; break; - default: - WARN_ON(1); - return -EINVAL; - } - ret = nvkm_falcon_pio_wr(falcon, fw->boot, 0, 0, IMEM, falcon->code.limit - fw->boot_size, fw->boot_size, fw->boot_addr >> 8, false); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c index 52412965fac1..5b721bd9d799 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c @@ -209,11 +209,12 @@ nvkm_gsp_fwsec_v2(struct nvkm_gsp *gsp, const char *name, fw->boot_addr = bld->start_tag << 8; fw->boot_size = bld->code_size; fw->boot = kmemdup(bl->data + hdr->data_offset + bld->code_off, fw->boot_size, GFP_KERNEL); - if (!fw->boot) - ret = -ENOMEM; nvkm_firmware_put(bl); + if (!fw->boot) + return -ENOMEM; + /* Patch in interface data. */ return nvkm_gsp_fwsec_patch(gsp, fw, desc->InterfaceOffset, init_cmd); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c index 1ac5628c5140..4ed54b386a60 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c @@ -601,6 +601,7 @@ r535_fifo_new(const struct nvkm_fifo_func *hw, struct nvkm_device *device, rm->chan.func = &r535_chan; rm->nonstall = &ga100_fifo_nonstall; rm->nonstall_ctor = ga100_fifo_nonstall_ctor; + rm->nonstall_dtor = ga100_fifo_nonstall_dtor; return nvkm_fifo_new_(rm, device, type, inst, pfifo); } diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c index 1116f2d2826e..4d8e9b34702a 100644 --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@ -1094,7 +1094,7 @@ static int panthor_ioctl_group_create(struct drm_device *ddev, void *data, struct drm_panthor_queue_create *queue_args; int ret; - if (!args->queues.count) + if (!args->queues.count || args->queues.count > MAX_CS_PER_CSG) return -EINVAL; ret = PANTHOR_UOBJ_GET_ARRAY(queue_args, &args->queues); diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 8867b95ab089..3d06f72531ba 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -391,7 +391,8 @@ EXPORT_SYMBOL(drm_sched_entity_set_priority); * Add a callback to the current dependency of the entity to wake up the * scheduler when the entity becomes available. */ -static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) +static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity, + struct drm_sched_job *sched_job) { struct drm_gpu_scheduler *sched = entity->rq->sched; struct dma_fence *fence = entity->dependency; @@ -421,6 +422,10 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) entity->dependency = fence; } + if (trace_drm_sched_job_unschedulable_enabled() && + !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &entity->dependency->flags)) + trace_drm_sched_job_unschedulable(sched_job, entity->dependency); + if (!dma_fence_add_callback(entity->dependency, &entity->cb, drm_sched_entity_wakeup)) return true; @@ -461,10 +466,8 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) while ((entity->dependency = drm_sched_job_dependency(sched_job, entity))) { - if (drm_sched_entity_add_dependency_cb(entity)) { - trace_drm_sched_job_unschedulable(sched_job, entity->dependency); + if (drm_sched_entity_add_dependency_cb(entity, sched_job)) return NULL; - } } /* skip jobs from entity that marked guilty */ diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index 41a285ec889f..8ede07fb7a21 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -526,7 +526,7 @@ void tegra_bo_free_object(struct drm_gem_object *gem) if (drm_gem_is_imported(gem)) { dma_buf_unmap_attachment_unlocked(gem->import_attach, bo->sgt, DMA_TO_DEVICE); - dma_buf_detach(gem->dma_buf, gem->import_attach); + dma_buf_detach(gem->import_attach->dmabuf, gem->import_attach); } } diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h index 81eb046aeebf..b9f67d7a00d8 100644 --- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h +++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h @@ -117,6 +117,7 @@ enum xe_guc_action { XE_GUC_ACTION_ENTER_S_STATE = 0x501, XE_GUC_ACTION_EXIT_S_STATE = 0x502, XE_GUC_ACTION_GLOBAL_SCHED_POLICY_CHANGE = 0x506, + XE_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV = 0x509, XE_GUC_ACTION_SCHED_CONTEXT = 0x1000, XE_GUC_ACTION_SCHED_CONTEXT_MODE_SET = 0x1001, XE_GUC_ACTION_SCHED_CONTEXT_MODE_DONE = 0x1002, diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h index 0366a9da5977..d7719d0e36ca 100644 --- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h +++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h @@ -17,6 +17,7 @@ * | 0 | 31:16 | **KEY** - KLV key identifier | * | | | - `GuC Self Config KLVs`_ | * | | | - `GuC Opt In Feature KLVs`_ | + * | | | - `GuC Scheduling Policies KLVs`_ | * | | | - `GuC VGT Policy KLVs`_ | * | | | - `GuC VF Configuration KLVs`_ | * | | | | @@ -153,6 +154,30 @@ enum { #define GUC_KLV_OPT_IN_FEATURE_DYNAMIC_INHIBIT_CONTEXT_SWITCH_LEN 0u /** + * DOC: GuC Scheduling Policies KLVs + * + * `GuC KLV`_ keys available for use with UPDATE_SCHEDULING_POLICIES_KLV. + * + * _`GUC_KLV_SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD` : 0x1001 + * Some platforms do not allow concurrent execution of RCS and CCS + * workloads from different address spaces. By default, the GuC prioritizes + * RCS submissions over CCS ones, which can lead to CCS workloads being + * significantly (or completely) starved of execution time. This KLV allows + * the driver to specify a quantum (in ms) and a ratio (percentage value + * between 0 and 100), and the GuC will prioritize the CCS for that + * percentage of each quantum. For example, specifying 100ms and 30% will + * make the GuC prioritize the CCS for 30ms of every 100ms. + * Note that this does not necessarly mean that RCS and CCS engines will + * only be active for their percentage of the quantum, as the restriction + * only kicks in if both classes are fully busy with non-compatible address + * spaces; i.e., if one engine is idle or running the same address space, + * a pending job on the other engine will still be submitted to the HW no + * matter what the ratio is + */ +#define GUC_KLV_SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD_KEY 0x1001 +#define GUC_KLV_SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD_LEN 2u + +/** * DOC: GuC VGT Policy KLVs * * `GuC KLV`_ keys available for use with PF2GUC_UPDATE_VGT_POLICY. diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c index bb469096d072..7b40cc8be1c9 100644 --- a/drivers/gpu/drm/xe/tests/xe_bo.c +++ b/drivers/gpu/drm/xe/tests/xe_bo.c @@ -236,7 +236,7 @@ static int evict_test_run_tile(struct xe_device *xe, struct xe_tile *tile, struc } xe_bo_lock(external, false); - err = xe_bo_pin_external(external); + err = xe_bo_pin_external(external, false); xe_bo_unlock(external); if (err) { KUNIT_FAIL(test, "external bo pin err=%pe\n", diff --git a/drivers/gpu/drm/xe/tests/xe_dma_buf.c b/drivers/gpu/drm/xe/tests/xe_dma_buf.c index c53f67ce4b0a..121f17c112ec 100644 --- a/drivers/gpu/drm/xe/tests/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/tests/xe_dma_buf.c @@ -89,15 +89,7 @@ static void check_residency(struct kunit *test, struct xe_bo *exported, return; } - /* - * If on different devices, the exporter is kept in system if - * possible, saving a migration step as the transfer is just - * likely as fast from system memory. - */ - if (params->mem_mask & XE_BO_FLAG_SYSTEM) - KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, XE_PL_TT)); - else - KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, mem_type)); + KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, mem_type)); if (params->force_different_devices) KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(imported, XE_PL_TT)); diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 18f27da47a36..bae7ff2e5927 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -186,6 +186,8 @@ static void try_add_system(struct xe_device *xe, struct xe_bo *bo, bo->placements[*c] = (struct ttm_place) { .mem_type = XE_PL_TT, + .flags = (bo_flags & XE_BO_FLAG_VRAM_MASK) ? + TTM_PL_FLAG_FALLBACK : 0, }; *c += 1; } @@ -812,14 +814,14 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, } if (ttm_bo->type == ttm_bo_type_sg) { - ret = xe_bo_move_notify(bo, ctx); + if (new_mem->mem_type == XE_PL_SYSTEM) + ret = xe_bo_move_notify(bo, ctx); if (!ret) ret = xe_bo_move_dmabuf(ttm_bo, new_mem); return ret; } - tt_has_data = ttm && (ttm_tt_is_populated(ttm) || - (ttm->page_flags & TTM_TT_FLAG_SWAPPED)); + tt_has_data = ttm && (ttm_tt_is_populated(ttm) || ttm_tt_is_swapped(ttm)); move_lacks_source = !old_mem || (handle_system_ccs ? (!bo->ccs_cleared) : (!mem_type_is_vram(old_mem_type) && !tt_has_data)); @@ -2269,6 +2271,7 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res) /** * xe_bo_pin_external - pin an external BO * @bo: buffer object to be pinned + * @in_place: Pin in current placement, don't attempt to migrate. * * Pin an external (not tied to a VM, can be exported via dma-buf / prime FD) * BO. Unique call compared to xe_bo_pin as this function has it own set of @@ -2276,7 +2279,7 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res) * * Returns 0 for success, negative error code otherwise. */ -int xe_bo_pin_external(struct xe_bo *bo) +int xe_bo_pin_external(struct xe_bo *bo, bool in_place) { struct xe_device *xe = xe_bo_device(bo); int err; @@ -2285,9 +2288,11 @@ int xe_bo_pin_external(struct xe_bo *bo) xe_assert(xe, xe_bo_is_user(bo)); if (!xe_bo_is_pinned(bo)) { - err = xe_bo_validate(bo, NULL, false); - if (err) - return err; + if (!in_place) { + err = xe_bo_validate(bo, NULL, false); + if (err) + return err; + } spin_lock(&xe->pinned.lock); list_add_tail(&bo->pinned_link, &xe->pinned.late.external); @@ -2438,9 +2443,11 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict) .no_wait_gpu = false, .gfp_retry_mayfail = true, }; - struct pin_cookie cookie; int ret; + if (xe_bo_is_pinned(bo)) + return 0; + if (vm) { lockdep_assert_held(&vm->lock); xe_vm_assert_held(vm); @@ -2449,10 +2456,10 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict) ctx.resv = xe_vm_resv(vm); } - cookie = xe_vm_set_validating(vm, allow_res_evict); + xe_vm_set_validating(vm, allow_res_evict); trace_xe_bo_validate(bo); ret = ttm_bo_validate(&bo->ttm, &bo->placement, &ctx); - xe_vm_clear_validating(vm, allow_res_evict, cookie); + xe_vm_clear_validating(vm, allow_res_evict); return ret; } diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 02e8cde4c6b2..9ce94d252015 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -198,7 +198,7 @@ static inline void xe_bo_unlock_vm_held(struct xe_bo *bo) } } -int xe_bo_pin_external(struct xe_bo *bo); +int xe_bo_pin_external(struct xe_bo *bo, bool in_place); int xe_bo_pin(struct xe_bo *bo); void xe_bo_unpin_external(struct xe_bo *bo); void xe_bo_unpin(struct xe_bo *bo); diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.c b/drivers/gpu/drm/xe/xe_device_sysfs.c index bd9015761aa0..3e3b2d9033a7 100644 --- a/drivers/gpu/drm/xe/xe_device_sysfs.c +++ b/drivers/gpu/drm/xe/xe_device_sysfs.c @@ -311,12 +311,16 @@ int xe_device_sysfs_init(struct xe_device *xe) if (xe->info.platform == XE_BATTLEMAGE) { ret = sysfs_create_files(&dev->kobj, auto_link_downgrade_attrs); if (ret) - return ret; + goto cleanup; ret = late_bind_create_files(dev); if (ret) - return ret; + goto cleanup; } return devm_add_action_or_reset(dev, xe_device_sysfs_fini, xe); + +cleanup: + xe_device_sysfs_fini(xe); + return ret; } diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index d4d2c6854790..7ceb0c90f391 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -553,6 +553,12 @@ struct xe_device { /** @pm_notifier: Our PM notifier to perform actions in response to various PM events. */ struct notifier_block pm_notifier; + /** @pm_block: Completion to block validating tasks on suspend / hibernate prepare */ + struct completion pm_block; + /** @rebind_resume_list: List of wq items to kick on resume. */ + struct list_head rebind_resume_list; + /** @rebind_resume_lock: Lock to protect the rebind_resume_list */ + struct mutex rebind_resume_lock; /** @pmt: Support the PMT driver callback interface */ struct { diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index 346f857f3837..af64baf872ef 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -72,7 +72,7 @@ static int xe_dma_buf_pin(struct dma_buf_attachment *attach) return ret; } - ret = xe_bo_pin_external(bo); + ret = xe_bo_pin_external(bo, true); xe_assert(xe, !ret); return 0; diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 44364c042ad7..374c831e691b 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -237,6 +237,15 @@ retry: goto err_unlock_list; } + /* + * It's OK to block interruptible here with the vm lock held, since + * on task freezing during suspend / hibernate, the call will + * return -ERESTARTSYS and the IOCTL will be rerun. + */ + err = wait_for_completion_interruptible(&xe->pm_block); + if (err) + goto err_unlock_list; + vm_exec.vm = &vm->gpuvm; vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT; if (xe_vm_in_lr_mode(vm)) { diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 8991b4aed440..c07edcda99c5 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -151,6 +151,16 @@ err_lrc: return err; } +static void __xe_exec_queue_fini(struct xe_exec_queue *q) +{ + int i; + + q->ops->fini(q); + + for (i = 0; i < q->width; ++i) + xe_lrc_put(q->lrc[i]); +} + struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *vm, u32 logical_mask, u16 width, struct xe_hw_engine *hwe, u32 flags, @@ -181,11 +191,13 @@ struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *v if (xe_exec_queue_uses_pxp(q)) { err = xe_pxp_exec_queue_add(xe->pxp, q); if (err) - goto err_post_alloc; + goto err_post_init; } return q; +err_post_init: + __xe_exec_queue_fini(q); err_post_alloc: __xe_exec_queue_free(q); return ERR_PTR(err); @@ -283,13 +295,11 @@ void xe_exec_queue_destroy(struct kref *ref) xe_exec_queue_put(eq); } - q->ops->fini(q); + q->ops->destroy(q); } void xe_exec_queue_fini(struct xe_exec_queue *q) { - int i; - /* * Before releasing our ref to lrc and xef, accumulate our run ticks * and wakeup any waiters. @@ -298,9 +308,7 @@ void xe_exec_queue_fini(struct xe_exec_queue *q) if (q->xef && atomic_dec_and_test(&q->xef->exec_queue.pending_removal)) wake_up_var(&q->xef->exec_queue.pending_removal); - for (i = 0; i < q->width; ++i) - xe_lrc_put(q->lrc[i]); - + __xe_exec_queue_fini(q); __xe_exec_queue_free(q); } diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index cc1cffb5c87f..1c9d03f2a3e5 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -166,8 +166,14 @@ struct xe_exec_queue_ops { int (*init)(struct xe_exec_queue *q); /** @kill: Kill inflight submissions for backend */ void (*kill)(struct xe_exec_queue *q); - /** @fini: Fini exec queue for submission backend */ + /** @fini: Undoes the init() for submission backend */ void (*fini)(struct xe_exec_queue *q); + /** + * @destroy: Destroy exec queue for submission backend. The backend + * function must call xe_exec_queue_fini() (which will in turn call the + * fini() backend function) to ensure the queue is properly cleaned up. + */ + void (*destroy)(struct xe_exec_queue *q); /** @set_priority: Set priority for exec queue */ int (*set_priority)(struct xe_exec_queue *q, enum xe_exec_queue_priority priority); diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c index 788f56b066b6..f83d421ac9d3 100644 --- a/drivers/gpu/drm/xe/xe_execlist.c +++ b/drivers/gpu/drm/xe/xe_execlist.c @@ -385,10 +385,20 @@ err_free: return err; } -static void execlist_exec_queue_fini_async(struct work_struct *w) +static void execlist_exec_queue_fini(struct xe_exec_queue *q) +{ + struct xe_execlist_exec_queue *exl = q->execlist; + + drm_sched_entity_fini(&exl->entity); + drm_sched_fini(&exl->sched); + + kfree(exl); +} + +static void execlist_exec_queue_destroy_async(struct work_struct *w) { struct xe_execlist_exec_queue *ee = - container_of(w, struct xe_execlist_exec_queue, fini_async); + container_of(w, struct xe_execlist_exec_queue, destroy_async); struct xe_exec_queue *q = ee->q; struct xe_execlist_exec_queue *exl = q->execlist; struct xe_device *xe = gt_to_xe(q->gt); @@ -401,10 +411,6 @@ static void execlist_exec_queue_fini_async(struct work_struct *w) list_del(&exl->active_link); spin_unlock_irqrestore(&exl->port->lock, flags); - drm_sched_entity_fini(&exl->entity); - drm_sched_fini(&exl->sched); - kfree(exl); - xe_exec_queue_fini(q); } @@ -413,10 +419,10 @@ static void execlist_exec_queue_kill(struct xe_exec_queue *q) /* NIY */ } -static void execlist_exec_queue_fini(struct xe_exec_queue *q) +static void execlist_exec_queue_destroy(struct xe_exec_queue *q) { - INIT_WORK(&q->execlist->fini_async, execlist_exec_queue_fini_async); - queue_work(system_unbound_wq, &q->execlist->fini_async); + INIT_WORK(&q->execlist->destroy_async, execlist_exec_queue_destroy_async); + queue_work(system_unbound_wq, &q->execlist->destroy_async); } static int execlist_exec_queue_set_priority(struct xe_exec_queue *q, @@ -467,6 +473,7 @@ static const struct xe_exec_queue_ops execlist_exec_queue_ops = { .init = execlist_exec_queue_init, .kill = execlist_exec_queue_kill, .fini = execlist_exec_queue_fini, + .destroy = execlist_exec_queue_destroy, .set_priority = execlist_exec_queue_set_priority, .set_timeslice = execlist_exec_queue_set_timeslice, .set_preempt_timeout = execlist_exec_queue_set_preempt_timeout, diff --git a/drivers/gpu/drm/xe/xe_execlist_types.h b/drivers/gpu/drm/xe/xe_execlist_types.h index 415140936f11..92c4ba52db0c 100644 --- a/drivers/gpu/drm/xe/xe_execlist_types.h +++ b/drivers/gpu/drm/xe/xe_execlist_types.h @@ -42,7 +42,7 @@ struct xe_execlist_exec_queue { bool has_run; - struct work_struct fini_async; + struct work_struct destroy_async; enum xe_exec_queue_priority active_priority; struct list_head active_link; diff --git a/drivers/gpu/drm/xe/xe_gen_wa_oob.c b/drivers/gpu/drm/xe/xe_gen_wa_oob.c index 6581cb0f0e59..247e41c1c48d 100644 --- a/drivers/gpu/drm/xe/xe_gen_wa_oob.c +++ b/drivers/gpu/drm/xe/xe_gen_wa_oob.c @@ -123,11 +123,19 @@ static int parse(FILE *input, FILE *csource, FILE *cheader, char *prefix) return 0; } +/* Avoid GNU vs POSIX basename() discrepancy, just use our own */ +static const char *xbasename(const char *s) +{ + const char *p = strrchr(s, '/'); + + return p ? p + 1 : s; +} + static int fn_to_prefix(const char *fn, char *prefix, size_t size) { size_t len; - fn = basename(fn); + fn = xbasename(fn); len = strlen(fn); if (len > size - 1) diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index c8eda36546d3..17634195cdc2 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -41,6 +41,7 @@ #include "xe_gt_topology.h" #include "xe_guc_exec_queue_types.h" #include "xe_guc_pc.h" +#include "xe_guc_submit.h" #include "xe_hw_fence.h" #include "xe_hw_engine_class_sysfs.h" #include "xe_irq.h" @@ -97,7 +98,7 @@ void xe_gt_sanitize(struct xe_gt *gt) * FIXME: if xe_uc_sanitize is called here, on TGL driver will not * reload */ - gt->uc.guc.submission_state.enabled = false; + xe_guc_submit_disable(>->uc.guc); } static void xe_gt_enable_host_l2_vram(struct xe_gt *gt) diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c index 494909f74eb2..d84831a03610 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c @@ -1632,7 +1632,6 @@ static u64 pf_estimate_fair_lmem(struct xe_gt *gt, unsigned int num_vfs) u64 fair; fair = div_u64(available, num_vfs); - fair = rounddown_pow_of_two(fair); /* XXX: ttm_vram_mgr & drm_buddy limitation */ fair = ALIGN_DOWN(fair, alignment); #ifdef MAX_FAIR_LMEM fair = min_t(u64, MAX_FAIR_LMEM, fair); diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c index b1d1d6da3758..270fc3792493 100644 --- a/drivers/gpu/drm/xe/xe_guc.c +++ b/drivers/gpu/drm/xe/xe_guc.c @@ -880,9 +880,7 @@ int xe_guc_post_load_init(struct xe_guc *guc) return ret; } - guc->submission_state.enabled = true; - - return 0; + return xe_guc_submit_enable(guc); } int xe_guc_reset(struct xe_guc *guc) @@ -1579,7 +1577,7 @@ void xe_guc_sanitize(struct xe_guc *guc) { xe_uc_fw_sanitize(&guc->fw); xe_guc_ct_disable(&guc->ct); - guc->submission_state.enabled = false; + xe_guc_submit_disable(guc); } int xe_guc_reset_prepare(struct xe_guc *guc) diff --git a/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h b/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h index a3f421e2adc0..c30c0e3ccbbb 100644 --- a/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h @@ -35,8 +35,8 @@ struct xe_guc_exec_queue { struct xe_sched_msg static_msgs[MAX_STATIC_MSG_TYPE]; /** @lr_tdr: long running TDR worker */ struct work_struct lr_tdr; - /** @fini_async: do final fini async from this worker */ - struct work_struct fini_async; + /** @destroy_async: do final destroy async from this worker */ + struct work_struct destroy_async; /** @resume_time: time of last resume */ u64 resume_time; /** @state: GuC specific state for this xe_exec_queue */ diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index cafb47711e9b..0104afbc941c 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -32,6 +32,7 @@ #include "xe_guc_ct.h" #include "xe_guc_exec_queue_types.h" #include "xe_guc_id_mgr.h" +#include "xe_guc_klv_helpers.h" #include "xe_guc_submit_types.h" #include "xe_hw_engine.h" #include "xe_hw_fence.h" @@ -316,6 +317,71 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids) return drmm_add_action_or_reset(&xe->drm, guc_submit_fini, guc); } +/* + * Given that we want to guarantee enough RCS throughput to avoid missing + * frames, we set the yield policy to 20% of each 80ms interval. + */ +#define RC_YIELD_DURATION 80 /* in ms */ +#define RC_YIELD_RATIO 20 /* in percent */ +static u32 *emit_render_compute_yield_klv(u32 *emit) +{ + *emit++ = PREP_GUC_KLV_TAG(SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD); + *emit++ = RC_YIELD_DURATION; + *emit++ = RC_YIELD_RATIO; + + return emit; +} + +#define SCHEDULING_POLICY_MAX_DWORDS 16 +static int guc_init_global_schedule_policy(struct xe_guc *guc) +{ + u32 data[SCHEDULING_POLICY_MAX_DWORDS]; + u32 *emit = data; + u32 count = 0; + int ret; + + if (GUC_SUBMIT_VER(guc) < MAKE_GUC_VER(1, 1, 0)) + return 0; + + *emit++ = XE_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV; + + if (CCS_MASK(guc_to_gt(guc))) + emit = emit_render_compute_yield_klv(emit); + + count = emit - data; + if (count > 1) { + xe_assert(guc_to_xe(guc), count <= SCHEDULING_POLICY_MAX_DWORDS); + + ret = xe_guc_ct_send_block(&guc->ct, data, count); + if (ret < 0) { + xe_gt_err(guc_to_gt(guc), + "failed to enable GuC sheduling policies: %pe\n", + ERR_PTR(ret)); + return ret; + } + } + + return 0; +} + +int xe_guc_submit_enable(struct xe_guc *guc) +{ + int ret; + + ret = guc_init_global_schedule_policy(guc); + if (ret) + return ret; + + guc->submission_state.enabled = true; + + return 0; +} + +void xe_guc_submit_disable(struct xe_guc *guc) +{ + guc->submission_state.enabled = false; +} + static void __release_guc_id(struct xe_guc *guc, struct xe_exec_queue *q, u32 xa_count) { int i; @@ -1277,48 +1343,57 @@ rearm: return DRM_GPU_SCHED_STAT_NO_HANG; } -static void __guc_exec_queue_fini_async(struct work_struct *w) +static void guc_exec_queue_fini(struct xe_exec_queue *q) +{ + struct xe_guc_exec_queue *ge = q->guc; + struct xe_guc *guc = exec_queue_to_guc(q); + + release_guc_id(guc, q); + xe_sched_entity_fini(&ge->entity); + xe_sched_fini(&ge->sched); + + /* + * RCU free due sched being exported via DRM scheduler fences + * (timeline name). + */ + kfree_rcu(ge, rcu); +} + +static void __guc_exec_queue_destroy_async(struct work_struct *w) { struct xe_guc_exec_queue *ge = - container_of(w, struct xe_guc_exec_queue, fini_async); + container_of(w, struct xe_guc_exec_queue, destroy_async); struct xe_exec_queue *q = ge->q; struct xe_guc *guc = exec_queue_to_guc(q); xe_pm_runtime_get(guc_to_xe(guc)); trace_xe_exec_queue_destroy(q); - release_guc_id(guc, q); if (xe_exec_queue_is_lr(q)) cancel_work_sync(&ge->lr_tdr); /* Confirm no work left behind accessing device structures */ cancel_delayed_work_sync(&ge->sched.base.work_tdr); - xe_sched_entity_fini(&ge->entity); - xe_sched_fini(&ge->sched); - /* - * RCU free due sched being exported via DRM scheduler fences - * (timeline name). - */ - kfree_rcu(ge, rcu); xe_exec_queue_fini(q); + xe_pm_runtime_put(guc_to_xe(guc)); } -static void guc_exec_queue_fini_async(struct xe_exec_queue *q) +static void guc_exec_queue_destroy_async(struct xe_exec_queue *q) { struct xe_guc *guc = exec_queue_to_guc(q); struct xe_device *xe = guc_to_xe(guc); - INIT_WORK(&q->guc->fini_async, __guc_exec_queue_fini_async); + INIT_WORK(&q->guc->destroy_async, __guc_exec_queue_destroy_async); /* We must block on kernel engines so slabs are empty on driver unload */ if (q->flags & EXEC_QUEUE_FLAG_PERMANENT || exec_queue_wedged(q)) - __guc_exec_queue_fini_async(&q->guc->fini_async); + __guc_exec_queue_destroy_async(&q->guc->destroy_async); else - queue_work(xe->destroy_wq, &q->guc->fini_async); + queue_work(xe->destroy_wq, &q->guc->destroy_async); } -static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q) +static void __guc_exec_queue_destroy(struct xe_guc *guc, struct xe_exec_queue *q) { /* * Might be done from within the GPU scheduler, need to do async as we @@ -1327,7 +1402,7 @@ static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q) * this we and don't really care when everything is fini'd, just that it * is. */ - guc_exec_queue_fini_async(q); + guc_exec_queue_destroy_async(q); } static void __guc_exec_queue_process_msg_cleanup(struct xe_sched_msg *msg) @@ -1341,7 +1416,7 @@ static void __guc_exec_queue_process_msg_cleanup(struct xe_sched_msg *msg) if (exec_queue_registered(q)) disable_scheduling_deregister(guc, q); else - __guc_exec_queue_fini(guc, q); + __guc_exec_queue_destroy(guc, q); } static bool guc_exec_queue_allowed_to_change_state(struct xe_exec_queue *q) @@ -1574,14 +1649,14 @@ static bool guc_exec_queue_try_add_msg(struct xe_exec_queue *q, #define STATIC_MSG_CLEANUP 0 #define STATIC_MSG_SUSPEND 1 #define STATIC_MSG_RESUME 2 -static void guc_exec_queue_fini(struct xe_exec_queue *q) +static void guc_exec_queue_destroy(struct xe_exec_queue *q) { struct xe_sched_msg *msg = q->guc->static_msgs + STATIC_MSG_CLEANUP; if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && !exec_queue_wedged(q)) guc_exec_queue_add_msg(q, msg, CLEANUP); else - __guc_exec_queue_fini(exec_queue_to_guc(q), q); + __guc_exec_queue_destroy(exec_queue_to_guc(q), q); } static int guc_exec_queue_set_priority(struct xe_exec_queue *q, @@ -1711,6 +1786,7 @@ static const struct xe_exec_queue_ops guc_exec_queue_ops = { .init = guc_exec_queue_init, .kill = guc_exec_queue_kill, .fini = guc_exec_queue_fini, + .destroy = guc_exec_queue_destroy, .set_priority = guc_exec_queue_set_priority, .set_timeslice = guc_exec_queue_set_timeslice, .set_preempt_timeout = guc_exec_queue_set_preempt_timeout, @@ -1732,7 +1808,7 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q) if (exec_queue_extra_ref(q) || xe_exec_queue_is_lr(q)) xe_exec_queue_put(q); else if (exec_queue_destroyed(q)) - __guc_exec_queue_fini(guc, q); + __guc_exec_queue_destroy(guc, q); } if (q->guc->suspend_pending) { set_exec_queue_suspended(q); @@ -1989,7 +2065,7 @@ static void handle_deregister_done(struct xe_guc *guc, struct xe_exec_queue *q) if (exec_queue_extra_ref(q) || xe_exec_queue_is_lr(q)) xe_exec_queue_put(q); else - __guc_exec_queue_fini(guc, q); + __guc_exec_queue_destroy(guc, q); } int xe_guc_deregister_done_handler(struct xe_guc *guc, u32 *msg, u32 len) diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h index 9b71a986c6ca..0d126b807c10 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.h +++ b/drivers/gpu/drm/xe/xe_guc_submit.h @@ -13,6 +13,8 @@ struct xe_exec_queue; struct xe_guc; int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids); +int xe_guc_submit_enable(struct xe_guc *guc); +void xe_guc_submit_disable(struct xe_guc *guc); int xe_guc_submit_reset_prepare(struct xe_guc *guc); void xe_guc_submit_reset_wait(struct xe_guc *guc); diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c index c17ed1ae8649..c5b63e10bb91 100644 --- a/drivers/gpu/drm/xe/xe_hwmon.c +++ b/drivers/gpu/drm/xe/xe_hwmon.c @@ -286,7 +286,7 @@ static struct xe_reg xe_hwmon_get_reg(struct xe_hwmon *hwmon, enum xe_hwmon_reg */ static void xe_hwmon_power_max_read(struct xe_hwmon *hwmon, u32 attr, int channel, long *value) { - u64 reg_val = 0, min, max; + u32 reg_val = 0; struct xe_device *xe = hwmon->xe; struct xe_reg rapl_limit, pkg_power_sku; struct xe_mmio *mmio = xe_root_tile_mmio(xe); @@ -294,7 +294,7 @@ static void xe_hwmon_power_max_read(struct xe_hwmon *hwmon, u32 attr, int channe mutex_lock(&hwmon->hwmon_lock); if (hwmon->xe->info.has_mbx_power_limits) { - xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, (u32 *)®_val); + xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, ®_val); } else { rapl_limit = xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel); pkg_power_sku = xe_hwmon_get_reg(hwmon, REG_PKG_POWER_SKU, channel); @@ -304,19 +304,21 @@ static void xe_hwmon_power_max_read(struct xe_hwmon *hwmon, u32 attr, int channe /* Check if PL limits are disabled. */ if (!(reg_val & PWR_LIM_EN)) { *value = PL_DISABLE; - drm_info(&hwmon->xe->drm, "%s disabled for channel %d, val 0x%016llx\n", + drm_info(&hwmon->xe->drm, "%s disabled for channel %d, val 0x%08x\n", PWR_ATTR_TO_STR(attr), channel, reg_val); goto unlock; } reg_val = REG_FIELD_GET(PWR_LIM_VAL, reg_val); - *value = mul_u64_u32_shr(reg_val, SF_POWER, hwmon->scl_shift_power); + *value = mul_u32_u32(reg_val, SF_POWER) >> hwmon->scl_shift_power; /* For platforms with mailbox power limit support clamping would be done by pcode. */ if (!hwmon->xe->info.has_mbx_power_limits) { - reg_val = xe_mmio_read64_2x32(mmio, pkg_power_sku); - min = REG_FIELD_GET(PKG_MIN_PWR, reg_val); - max = REG_FIELD_GET(PKG_MAX_PWR, reg_val); + u64 pkg_pwr, min, max; + + pkg_pwr = xe_mmio_read64_2x32(mmio, pkg_power_sku); + min = REG_FIELD_GET(PKG_MIN_PWR, pkg_pwr); + max = REG_FIELD_GET(PKG_MAX_PWR, pkg_pwr); min = mul_u64_u32_shr(min, SF_POWER, hwmon->scl_shift_power); max = mul_u64_u32_shr(max, SF_POWER, hwmon->scl_shift_power); if (min && max) @@ -493,8 +495,8 @@ xe_hwmon_power_max_interval_show(struct device *dev, struct device_attribute *at { struct xe_hwmon *hwmon = dev_get_drvdata(dev); struct xe_mmio *mmio = xe_root_tile_mmio(hwmon->xe); - u32 x, y, x_w = 2; /* 2 bits */ - u64 r, tau4, out; + u32 reg_val, x, y, x_w = 2; /* 2 bits */ + u64 tau4, out; int channel = (to_sensor_dev_attr(attr)->index % 2) ? CHANNEL_PKG : CHANNEL_CARD; u32 power_attr = (to_sensor_dev_attr(attr)->index > 1) ? PL2_HWMON_ATTR : PL1_HWMON_ATTR; @@ -505,23 +507,24 @@ xe_hwmon_power_max_interval_show(struct device *dev, struct device_attribute *at mutex_lock(&hwmon->hwmon_lock); if (hwmon->xe->info.has_mbx_power_limits) { - ret = xe_hwmon_pcode_read_power_limit(hwmon, power_attr, channel, (u32 *)&r); + ret = xe_hwmon_pcode_read_power_limit(hwmon, power_attr, channel, ®_val); if (ret) { drm_err(&hwmon->xe->drm, - "power interval read fail, ch %d, attr %d, r 0%llx, ret %d\n", - channel, power_attr, r, ret); - r = 0; + "power interval read fail, ch %d, attr %d, val 0x%08x, ret %d\n", + channel, power_attr, reg_val, ret); + reg_val = 0; } } else { - r = xe_mmio_read32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel)); + reg_val = xe_mmio_read32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, + channel)); } mutex_unlock(&hwmon->hwmon_lock); xe_pm_runtime_put(hwmon->xe); - x = REG_FIELD_GET(PWR_LIM_TIME_X, r); - y = REG_FIELD_GET(PWR_LIM_TIME_Y, r); + x = REG_FIELD_GET(PWR_LIM_TIME_X, reg_val); + y = REG_FIELD_GET(PWR_LIM_TIME_Y, reg_val); /* * tau = (1 + (x / 4)) * power(2,y), x = bits(23:22), y = bits(21:17) diff --git a/drivers/gpu/drm/xe/xe_nvm.c b/drivers/gpu/drm/xe/xe_nvm.c index 61b0a1531a53..2cfe9eb67391 100644 --- a/drivers/gpu/drm/xe/xe_nvm.c +++ b/drivers/gpu/drm/xe/xe_nvm.c @@ -35,6 +35,10 @@ static const struct intel_dg_nvm_region regions[INTEL_DG_NVM_REGIONS] = { static void xe_nvm_release_dev(struct device *dev) { + struct auxiliary_device *aux = container_of(dev, struct auxiliary_device, dev); + struct intel_dg_nvm_dev *nvm = container_of(aux, struct intel_dg_nvm_dev, aux_dev); + + kfree(nvm); } static bool xe_nvm_non_posted_erase(struct xe_device *xe) @@ -162,6 +166,5 @@ void xe_nvm_fini(struct xe_device *xe) auxiliary_device_delete(&nvm->aux_dev); auxiliary_device_uninit(&nvm->aux_dev); - kfree(nvm); xe->nvm = NULL; } diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index e279b47ba03b..bb9b6ecad2af 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -24,6 +24,7 @@ #include "xe_pcode.h" #include "xe_pxp.h" #include "xe_trace.h" +#include "xe_vm.h" #include "xe_wa.h" /** @@ -290,6 +291,19 @@ static u32 vram_threshold_value(struct xe_device *xe) return DEFAULT_VRAM_THRESHOLD; } +static void xe_pm_wake_rebind_workers(struct xe_device *xe) +{ + struct xe_vm *vm, *next; + + mutex_lock(&xe->rebind_resume_lock); + list_for_each_entry_safe(vm, next, &xe->rebind_resume_list, + preempt.pm_activate_link) { + list_del_init(&vm->preempt.pm_activate_link); + xe_vm_resume_rebind_worker(vm); + } + mutex_unlock(&xe->rebind_resume_lock); +} + static int xe_pm_notifier_callback(struct notifier_block *nb, unsigned long action, void *data) { @@ -299,30 +313,30 @@ static int xe_pm_notifier_callback(struct notifier_block *nb, switch (action) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: + reinit_completion(&xe->pm_block); xe_pm_runtime_get(xe); err = xe_bo_evict_all_user(xe); - if (err) { + if (err) drm_dbg(&xe->drm, "Notifier evict user failed (%d)\n", err); - xe_pm_runtime_put(xe); - break; - } err = xe_bo_notifier_prepare_all_pinned(xe); - if (err) { + if (err) drm_dbg(&xe->drm, "Notifier prepare pin failed (%d)\n", err); - xe_pm_runtime_put(xe); - } + /* + * Keep the runtime pm reference until post hibernation / post suspend to + * avoid a runtime suspend interfering with evicted objects or backup + * allocations. + */ break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: + complete_all(&xe->pm_block); + xe_pm_wake_rebind_workers(xe); xe_bo_notifier_unprepare_all_pinned(xe); xe_pm_runtime_put(xe); break; } - if (err) - return NOTIFY_BAD; - return NOTIFY_DONE; } @@ -344,6 +358,14 @@ int xe_pm_init(struct xe_device *xe) if (err) return err; + err = drmm_mutex_init(&xe->drm, &xe->rebind_resume_lock); + if (err) + goto err_unregister; + + init_completion(&xe->pm_block); + complete_all(&xe->pm_block); + INIT_LIST_HEAD(&xe->rebind_resume_list); + /* For now suspend/resume is only allowed with GuC */ if (!xe_device_uc_enabled(xe)) return 0; diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c index 41705f5d52e3..8f7b0add2364 100644 --- a/drivers/gpu/drm/xe/xe_survivability_mode.c +++ b/drivers/gpu/drm/xe/xe_survivability_mode.c @@ -41,6 +41,8 @@ * * # echo 1 > /sys/kernel/config/xe/0000:03:00.0/survivability_mode * + * It is the responsibility of the user to clear the mode once firmware flash is complete. + * * Refer :ref:`xe_configfs` for more details on how to use configfs * * Survivability mode is indicated by the below admin-only readable sysfs which provides additional @@ -147,7 +149,6 @@ static void xe_survivability_mode_fini(void *arg) struct pci_dev *pdev = to_pci_dev(xe->drm.dev); struct device *dev = &pdev->dev; - xe_configfs_clear_survivability_mode(pdev); sysfs_remove_file(&dev->kobj, &dev_attr_survivability_mode.attr); } diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c index f87276df18f2..82872a51f098 100644 --- a/drivers/gpu/drm/xe/xe_sync.c +++ b/drivers/gpu/drm/xe/xe_sync.c @@ -77,6 +77,7 @@ static void user_fence_worker(struct work_struct *w) { struct xe_user_fence *ufence = container_of(w, struct xe_user_fence, worker); + WRITE_ONCE(ufence->signalled, 1); if (mmget_not_zero(ufence->mm)) { kthread_use_mm(ufence->mm); if (copy_to_user(ufence->addr, &ufence->value, sizeof(ufence->value))) @@ -91,7 +92,6 @@ static void user_fence_worker(struct work_struct *w) * Wake up waiters only after updating the ufence state, allowing the UMD * to safely reuse the same ufence without encountering -EBUSY errors. */ - WRITE_ONCE(ufence->signalled, 1); wake_up_all(&ufence->xe->ufence_wq); user_fence_put(ufence); } diff --git a/drivers/gpu/drm/xe/xe_tile_sysfs.c b/drivers/gpu/drm/xe/xe_tile_sysfs.c index b804234a6551..9e1236a9ec67 100644 --- a/drivers/gpu/drm/xe/xe_tile_sysfs.c +++ b/drivers/gpu/drm/xe/xe_tile_sysfs.c @@ -44,16 +44,18 @@ int xe_tile_sysfs_init(struct xe_tile *tile) kt->tile = tile; err = kobject_add(&kt->base, &dev->kobj, "tile%d", tile->id); - if (err) { - kobject_put(&kt->base); - return err; - } + if (err) + goto err_object; tile->sysfs = &kt->base; err = xe_vram_freq_sysfs_init(tile); if (err) - return err; + goto err_object; return devm_add_action_or_reset(xe->drm.dev, tile_sysfs_fini, tile); + +err_object: + kobject_put(&kt->base); + return err; } diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index ec04bef8ae40..5146999d27fa 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -240,8 +240,8 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) pfence = xe_preempt_fence_create(q, q->lr.context, ++q->lr.seqno); - if (!pfence) { - err = -ENOMEM; + if (IS_ERR(pfence)) { + err = PTR_ERR(pfence); goto out_fini; } @@ -393,6 +393,9 @@ static int xe_gpuvm_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) list_move_tail(&gpuva_to_vma(gpuva)->combined_links.rebind, &vm->rebind_list); + if (!try_wait_for_completion(&vm->xe->pm_block)) + return -EAGAIN; + ret = xe_bo_validate(gem_to_xe_bo(vm_bo->obj), vm, false); if (ret) return ret; @@ -479,6 +482,33 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm, return xe_vm_validate_rebind(vm, exec, vm->preempt.num_exec_queues); } +static bool vm_suspend_rebind_worker(struct xe_vm *vm) +{ + struct xe_device *xe = vm->xe; + bool ret = false; + + mutex_lock(&xe->rebind_resume_lock); + if (!try_wait_for_completion(&vm->xe->pm_block)) { + ret = true; + list_move_tail(&vm->preempt.pm_activate_link, &xe->rebind_resume_list); + } + mutex_unlock(&xe->rebind_resume_lock); + + return ret; +} + +/** + * xe_vm_resume_rebind_worker() - Resume the rebind worker. + * @vm: The vm whose preempt worker to resume. + * + * Resume a preempt worker that was previously suspended by + * vm_suspend_rebind_worker(). + */ +void xe_vm_resume_rebind_worker(struct xe_vm *vm) +{ + queue_work(vm->xe->ordered_wq, &vm->preempt.rebind_work); +} + static void preempt_rebind_work_func(struct work_struct *w) { struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work); @@ -502,6 +532,11 @@ static void preempt_rebind_work_func(struct work_struct *w) } retry: + if (!try_wait_for_completion(&vm->xe->pm_block) && vm_suspend_rebind_worker(vm)) { + up_write(&vm->lock); + return; + } + if (xe_vm_userptr_check_repin(vm)) { err = xe_vm_userptr_pin(vm); if (err) @@ -1610,8 +1645,12 @@ static int xe_vm_create_scratch(struct xe_device *xe, struct xe_tile *tile, for (i = MAX_HUGEPTE_LEVEL; i < vm->pt_root[id]->level; i++) { vm->scratch_pt[id][i] = xe_pt_create(vm, tile, i); - if (IS_ERR(vm->scratch_pt[id][i])) - return PTR_ERR(vm->scratch_pt[id][i]); + if (IS_ERR(vm->scratch_pt[id][i])) { + int err = PTR_ERR(vm->scratch_pt[id][i]); + + vm->scratch_pt[id][i] = NULL; + return err; + } xe_pt_populate_empty(tile, vm, vm->scratch_pt[id][i]); } @@ -1710,6 +1749,7 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) if (flags & XE_VM_FLAG_LR_MODE) { INIT_WORK(&vm->preempt.rebind_work, preempt_rebind_work_func); xe_pm_runtime_get_noresume(xe); + INIT_LIST_HEAD(&vm->preempt.pm_activate_link); } if (flags & XE_VM_FLAG_FAULT_MODE) { @@ -1891,8 +1931,12 @@ void xe_vm_close_and_put(struct xe_vm *vm) xe_assert(xe, !vm->preempt.num_exec_queues); xe_vm_close(vm); - if (xe_vm_in_preempt_fence_mode(vm)) + if (xe_vm_in_preempt_fence_mode(vm)) { + mutex_lock(&xe->rebind_resume_lock); + list_del_init(&vm->preempt.pm_activate_link); + mutex_unlock(&xe->rebind_resume_lock); flush_work(&vm->preempt.rebind_work); + } if (xe_vm_in_fault_mode(vm)) xe_svm_close(vm); diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index 2f213737c7e5..82b112795807 100644 --- a/drivers/gpu/drm/xe/xe_vm.h +++ b/drivers/gpu/drm/xe/xe_vm.h @@ -273,6 +273,8 @@ struct dma_fence *xe_vm_bind_kernel_bo(struct xe_vm *vm, struct xe_bo *bo, struct xe_exec_queue *q, u64 addr, enum xe_cache_level cache_lvl); +void xe_vm_resume_rebind_worker(struct xe_vm *vm); + /** * xe_vm_resv() - Return's the vm's reservation object * @vm: The vm @@ -315,22 +317,14 @@ void xe_vm_snapshot_free(struct xe_vm_snapshot *snap); * Register this task as currently making bos resident for the vm. Intended * to avoid eviction by the same task of shared bos bound to the vm. * Call with the vm's resv lock held. - * - * Return: A pin cookie that should be used for xe_vm_clear_validating(). */ -static inline struct pin_cookie xe_vm_set_validating(struct xe_vm *vm, - bool allow_res_evict) +static inline void xe_vm_set_validating(struct xe_vm *vm, bool allow_res_evict) { - struct pin_cookie cookie = {}; - if (vm && !allow_res_evict) { xe_vm_assert_held(vm); - cookie = lockdep_pin_lock(&xe_vm_resv(vm)->lock.base); /* Pairs with READ_ONCE in xe_vm_is_validating() */ WRITE_ONCE(vm->validating, current); } - - return cookie; } /** @@ -338,17 +332,14 @@ static inline struct pin_cookie xe_vm_set_validating(struct xe_vm *vm, * @vm: Pointer to the vm or NULL * @allow_res_evict: Eviction from @vm was allowed. Must be set to the same * value as for xe_vm_set_validation(). - * @cookie: Cookie obtained from xe_vm_set_validating(). * * Register this task as currently making bos resident for the vm. Intended * to avoid eviction by the same task of shared bos bound to the vm. * Call with the vm's resv lock held. */ -static inline void xe_vm_clear_validating(struct xe_vm *vm, bool allow_res_evict, - struct pin_cookie cookie) +static inline void xe_vm_clear_validating(struct xe_vm *vm, bool allow_res_evict) { if (vm && !allow_res_evict) { - lockdep_unpin_lock(&xe_vm_resv(vm)->lock.base, cookie); /* Pairs with READ_ONCE in xe_vm_is_validating() */ WRITE_ONCE(vm->validating, NULL); } diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index 8a07feef503b..6058cf739388 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -293,6 +293,11 @@ struct xe_vm { * BOs */ struct work_struct rebind_work; + /** + * @preempt.pm_activate_link: Link to list of rebind workers to be + * kicked on resume. + */ + struct list_head pm_activate_link; } preempt; /** @um: unified memory state */ diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index e990f20eccfe..710f4423726c 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -30,7 +30,8 @@ 16022287689 GRAPHICS_VERSION(2001) GRAPHICS_VERSION(2004) 13011645652 GRAPHICS_VERSION(2004) - GRAPHICS_VERSION(3001) + GRAPHICS_VERSION_RANGE(3000, 3001) + GRAPHICS_VERSION(3003) 14022293748 GRAPHICS_VERSION_RANGE(2001, 2002) GRAPHICS_VERSION(2004) GRAPHICS_VERSION_RANGE(3000, 3001) diff --git a/drivers/gpu/nova-core/Kconfig b/drivers/gpu/nova-core/Kconfig index 8726d80d6ba4..20d3e6d0d796 100644 --- a/drivers/gpu/nova-core/Kconfig +++ b/drivers/gpu/nova-core/Kconfig @@ -1,5 +1,6 @@ config NOVA_CORE tristate "Nova Core GPU driver" + depends on 64BIT depends on PCI depends on RUST depends on RUST_FW_LOADER_ABSTRACTIONS |