diff options
Diffstat (limited to 'drivers/gpu')
131 files changed, 1458 insertions, 590 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c index ca4a6b82817f..df77558e03ef 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c @@ -561,6 +561,13 @@ static uint32_t read_vmid_from_vmfault_reg(struct amdgpu_device *adev) return REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, VMID); } +static uint32_t kgd_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue) + +{ + return 0; +} + const struct kfd2kgd_calls gfx_v7_kfd2kgd = { .program_sh_mem_settings = kgd_program_sh_mem_settings, .set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping, @@ -578,4 +585,5 @@ const struct kfd2kgd_calls gfx_v7_kfd2kgd = { .set_scratch_backing_va = set_scratch_backing_va, .set_vm_context_page_table_base = set_vm_context_page_table_base, .read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg, + .hqd_sdma_get_doorbell = kgd_hqd_sdma_get_doorbell, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c index 0f3e2944edd7..e68c0fa8d751 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c @@ -582,6 +582,13 @@ static void set_vm_context_page_table_base(struct amdgpu_device *adev, lower_32_bits(page_table_base)); } +static uint32_t kgd_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue) + +{ + return 0; +} + const struct kfd2kgd_calls gfx_v8_kfd2kgd = { .program_sh_mem_settings = kgd_program_sh_mem_settings, .set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping, @@ -599,4 +606,5 @@ const struct kfd2kgd_calls gfx_v8_kfd2kgd = { get_atc_vmid_pasid_mapping_info, .set_scratch_backing_va = set_scratch_backing_va, .set_vm_context_page_table_base = set_vm_context_page_table_base, + .hqd_sdma_get_doorbell = kgd_hqd_sdma_get_doorbell, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 85567d0d9545..f5d5c45ddc0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -944,6 +944,7 @@ static void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr) drm_sched_entity_fini(entity); } } + kref_put(&ctx->refcount, amdgpu_ctx_fini); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 8e626f50b362..f81608330a3d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -1902,7 +1902,7 @@ no_preempt: continue; } job = to_amdgpu_job(s_job); - if (preempted && (&job->hw_fence) == fence) + if (preempted && (&job->hw_fence.base) == fence) /* mark the job as preempted */ job->preemption_status |= AMDGPU_IB_PREEMPTED; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index e1bab6a96cb6..78f8755996f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -6019,16 +6019,12 @@ static int amdgpu_device_health_check(struct list_head *device_list_handle) return ret; } -static int amdgpu_device_halt_activities(struct amdgpu_device *adev, - struct amdgpu_job *job, - struct amdgpu_reset_context *reset_context, - struct list_head *device_list, - struct amdgpu_hive_info *hive, - bool need_emergency_restart) +static int amdgpu_device_recovery_prepare(struct amdgpu_device *adev, + struct list_head *device_list, + struct amdgpu_hive_info *hive) { - struct list_head *device_list_handle = NULL; struct amdgpu_device *tmp_adev = NULL; - int i, r = 0; + int r; /* * Build list of devices to reset. @@ -6045,26 +6041,54 @@ static int amdgpu_device_halt_activities(struct amdgpu_device *adev, } if (!list_is_first(&adev->reset_list, device_list)) list_rotate_to_front(&adev->reset_list, device_list); - device_list_handle = device_list; } else { list_add_tail(&adev->reset_list, device_list); - device_list_handle = device_list; } if (!amdgpu_sriov_vf(adev) && (!adev->pcie_reset_ctx.occurs_dpc)) { - r = amdgpu_device_health_check(device_list_handle); + r = amdgpu_device_health_check(device_list); if (r) return r; } - /* We need to lock reset domain only once both for XGMI and single device */ - tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device, - reset_list); + return 0; +} + +static void amdgpu_device_recovery_get_reset_lock(struct amdgpu_device *adev, + struct list_head *device_list) +{ + struct amdgpu_device *tmp_adev = NULL; + + if (list_empty(device_list)) + return; + tmp_adev = + list_first_entry(device_list, struct amdgpu_device, reset_list); amdgpu_device_lock_reset_domain(tmp_adev->reset_domain); +} - /* block all schedulers and reset given job's ring */ - list_for_each_entry(tmp_adev, device_list_handle, reset_list) { +static void amdgpu_device_recovery_put_reset_lock(struct amdgpu_device *adev, + struct list_head *device_list) +{ + struct amdgpu_device *tmp_adev = NULL; + if (list_empty(device_list)) + return; + tmp_adev = + list_first_entry(device_list, struct amdgpu_device, reset_list); + amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain); +} + +static int amdgpu_device_halt_activities( + struct amdgpu_device *adev, struct amdgpu_job *job, + struct amdgpu_reset_context *reset_context, + struct list_head *device_list, struct amdgpu_hive_info *hive, + bool need_emergency_restart) +{ + struct amdgpu_device *tmp_adev = NULL; + int i, r = 0; + + /* block all schedulers and reset given job's ring */ + list_for_each_entry(tmp_adev, device_list, reset_list) { amdgpu_device_set_mp1_state(tmp_adev); /* @@ -6252,11 +6276,6 @@ static void amdgpu_device_gpu_resume(struct amdgpu_device *adev, amdgpu_ras_set_error_query_ready(tmp_adev, true); } - - tmp_adev = list_first_entry(device_list, struct amdgpu_device, - reset_list); - amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain); - } @@ -6324,10 +6343,16 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, reset_context->hive = hive; INIT_LIST_HEAD(&device_list); + if (amdgpu_device_recovery_prepare(adev, &device_list, hive)) + goto end_reset; + + /* We need to lock reset domain only once both for XGMI and single device */ + amdgpu_device_recovery_get_reset_lock(adev, &device_list); + r = amdgpu_device_halt_activities(adev, job, reset_context, &device_list, hive, need_emergency_restart); if (r) - goto end_reset; + goto reset_unlock; if (need_emergency_restart) goto skip_sched_resume; @@ -6337,7 +6362,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, * * job->base holds a reference to parent fence */ - if (job && dma_fence_is_signaled(&job->hw_fence)) { + if (job && dma_fence_is_signaled(&job->hw_fence.base)) { job_signaled = true; dev_info(adev->dev, "Guilty job already signaled, skipping HW reset"); goto skip_hw_reset; @@ -6345,13 +6370,15 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, r = amdgpu_device_asic_reset(adev, &device_list, reset_context); if (r) - goto end_reset; + goto reset_unlock; skip_hw_reset: r = amdgpu_device_sched_resume(&device_list, reset_context, job_signaled); if (r) - goto end_reset; + goto reset_unlock; skip_sched_resume: amdgpu_device_gpu_resume(adev, &device_list, need_emergency_restart); +reset_unlock: + amdgpu_device_recovery_put_reset_lock(adev, &device_list); end_reset: if (hive) { mutex_unlock(&hive->hive_lock); @@ -6763,6 +6790,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta memset(&reset_context, 0, sizeof(reset_context)); INIT_LIST_HEAD(&device_list); + amdgpu_device_recovery_prepare(adev, &device_list, hive); + amdgpu_device_recovery_get_reset_lock(adev, &device_list); r = amdgpu_device_halt_activities(adev, NULL, &reset_context, &device_list, hive, false); if (hive) { @@ -6880,8 +6909,8 @@ out: if (hive) { list_for_each_entry(tmp_adev, &device_list, reset_list) amdgpu_device_unset_mp1_state(tmp_adev); - amdgpu_device_unlock_reset_domain(adev->reset_domain); } + amdgpu_device_recovery_put_reset_lock(adev, &device_list); } if (hive) { @@ -6927,6 +6956,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev) amdgpu_device_sched_resume(&device_list, NULL, NULL); amdgpu_device_gpu_resume(adev, &device_list, false); + amdgpu_device_recovery_put_reset_lock(adev, &device_list); adev->pcie_reset_ctx.occurs_dpc = false; if (hive) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index a0e9bf9b2710..81b3443c8d7f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -321,10 +321,12 @@ static int amdgpu_discovery_read_binary_from_file(struct amdgpu_device *adev, const struct firmware *fw; int r; - r = request_firmware(&fw, fw_name, adev->dev); + r = firmware_request_nowarn(&fw, fw_name, adev->dev); if (r) { - dev_err(adev->dev, "can't load firmware \"%s\"\n", - fw_name); + if (amdgpu_discovery == 2) + dev_err(adev->dev, "can't load firmware \"%s\"\n", fw_name); + else + drm_info(&adev->ddev, "Optional firmware \"%s\" was not found\n", fw_name); return r; } @@ -459,16 +461,12 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) /* Read from file if it is the preferred option */ fw_name = amdgpu_discovery_get_fw_name(adev); if (fw_name != NULL) { - dev_info(adev->dev, "use ip discovery information from file"); + drm_dbg(&adev->ddev, "use ip discovery information from file"); r = amdgpu_discovery_read_binary_from_file(adev, adev->mman.discovery_bin, fw_name); - - if (r) { - dev_err(adev->dev, "failed to read ip discovery binary from file\n"); - r = -EINVAL; + if (r) goto out; - } - } else { + drm_dbg(&adev->ddev, "use ip discovery information from memory"); r = amdgpu_discovery_read_binary_from_mem( adev, adev->mman.discovery_bin); if (r) @@ -1338,10 +1336,8 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev) int r; r = amdgpu_discovery_init(adev); - if (r) { - DRM_ERROR("amdgpu_discovery_init failed\n"); + if (r) return r; - } wafl_ver = 0; adev->gfx.xcc_mask = 0; @@ -2579,8 +2575,10 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) break; default: r = amdgpu_discovery_reg_base_init(adev); - if (r) - return -EINVAL; + if (r) { + drm_err(&adev->ddev, "discovery failed: %d\n", r); + return r; + } amdgpu_discovery_harvest_ip(adev); amdgpu_discovery_get_gfx_info(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 8cecf25996ed..5fec808d7f54 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -41,22 +41,6 @@ #include "amdgpu_trace.h" #include "amdgpu_reset.h" -/* - * Fences mark an event in the GPUs pipeline and are used - * for GPU/CPU synchronization. When the fence is written, - * it is expected that all buffers associated with that fence - * are no longer in use by the associated ring on the GPU and - * that the relevant GPU caches have been flushed. - */ - -struct amdgpu_fence { - struct dma_fence base; - - /* RB, DMA, etc. */ - struct amdgpu_ring *ring; - ktime_t start_timestamp; -}; - static struct kmem_cache *amdgpu_fence_slab; int amdgpu_fence_slab_init(void) @@ -151,12 +135,12 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd am_fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_ATOMIC); if (am_fence == NULL) return -ENOMEM; - fence = &am_fence->base; - am_fence->ring = ring; } else { /* take use of job-embedded fence */ - fence = &job->hw_fence; + am_fence = &job->hw_fence; } + fence = &am_fence->base; + am_fence->ring = ring; seq = ++ring->fence_drv.sync_seq; if (job && job->job_run_counter) { @@ -718,7 +702,7 @@ void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring) * it right here or we won't be able to track them in fence_drv * and they will remain unsignaled during sa_bo free. */ - job = container_of(old, struct amdgpu_job, hw_fence); + job = container_of(old, struct amdgpu_job, hw_fence.base); if (!job->base.s_fence && !dma_fence_is_signaled(old)) dma_fence_signal(old); RCU_INIT_POINTER(*ptr, NULL); @@ -780,7 +764,7 @@ static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f) static const char *amdgpu_job_fence_get_timeline_name(struct dma_fence *f) { - struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence); + struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence.base); return (const char *)to_amdgpu_ring(job->base.sched)->name; } @@ -810,7 +794,7 @@ static bool amdgpu_fence_enable_signaling(struct dma_fence *f) */ static bool amdgpu_job_fence_enable_signaling(struct dma_fence *f) { - struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence); + struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence.base); if (!timer_pending(&to_amdgpu_ring(job->base.sched)->fence_drv.fallback_timer)) amdgpu_fence_schedule_fallback(to_amdgpu_ring(job->base.sched)); @@ -845,7 +829,7 @@ static void amdgpu_job_fence_free(struct rcu_head *rcu) struct dma_fence *f = container_of(rcu, struct dma_fence, rcu); /* free job if fence has a parent job */ - kfree(container_of(f, struct amdgpu_job, hw_fence)); + kfree(container_of(f, struct amdgpu_job, hw_fence.base)); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index acb21fc8b3ce..ddb9d3269357 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -272,8 +272,8 @@ void amdgpu_job_free_resources(struct amdgpu_job *job) /* Check if any fences where initialized */ if (job->base.s_fence && job->base.s_fence->finished.ops) f = &job->base.s_fence->finished; - else if (job->hw_fence.ops) - f = &job->hw_fence; + else if (job->hw_fence.base.ops) + f = &job->hw_fence.base; else f = NULL; @@ -290,10 +290,10 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job) amdgpu_sync_free(&job->explicit_sync); /* only put the hw fence if has embedded fence */ - if (!job->hw_fence.ops) + if (!job->hw_fence.base.ops) kfree(job); else - dma_fence_put(&job->hw_fence); + dma_fence_put(&job->hw_fence.base); } void amdgpu_job_set_gang_leader(struct amdgpu_job *job, @@ -322,10 +322,10 @@ void amdgpu_job_free(struct amdgpu_job *job) if (job->gang_submit != &job->base.s_fence->scheduled) dma_fence_put(job->gang_submit); - if (!job->hw_fence.ops) + if (!job->hw_fence.base.ops) kfree(job); else - dma_fence_put(&job->hw_fence); + dma_fence_put(&job->hw_fence.base); } struct dma_fence *amdgpu_job_submit(struct amdgpu_job *job) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h index f2c049129661..931fed8892cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h @@ -48,7 +48,7 @@ struct amdgpu_job { struct drm_sched_job base; struct amdgpu_vm *vm; struct amdgpu_sync explicit_sync; - struct dma_fence hw_fence; + struct amdgpu_fence hw_fence; struct dma_fence *gang_submit; uint32_t preamble_status; uint32_t preemption_status; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index e6f0b035e20b..c14f63cefe67 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -3522,8 +3522,12 @@ int psp_init_sos_microcode(struct psp_context *psp, const char *chip_name) uint8_t *ucode_array_start_addr; int err = 0; - err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, AMDGPU_UCODE_REQUIRED, - "amdgpu/%s_sos.bin", chip_name); + if (amdgpu_is_kicker_fw(adev)) + err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, AMDGPU_UCODE_REQUIRED, + "amdgpu/%s_sos_kicker.bin", chip_name); + else + err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, AMDGPU_UCODE_REQUIRED, + "amdgpu/%s_sos.bin", chip_name); if (err) goto out; @@ -3799,8 +3803,12 @@ int psp_init_ta_microcode(struct psp_context *psp, const char *chip_name) struct amdgpu_device *adev = psp->adev; int err; - err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, AMDGPU_UCODE_REQUIRED, - "amdgpu/%s_ta.bin", chip_name); + if (amdgpu_is_kicker_fw(adev)) + err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, AMDGPU_UCODE_REQUIRED, + "amdgpu/%s_ta_kicker.bin", chip_name); + else + err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, AMDGPU_UCODE_REQUIRED, + "amdgpu/%s_ta.bin", chip_name); if (err) return err; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index b95b47110769..e1f25218943a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -127,6 +127,22 @@ struct amdgpu_fence_driver { struct dma_fence **fences; }; +/* + * Fences mark an event in the GPUs pipeline and are used + * for GPU/CPU synchronization. When the fence is written, + * it is expected that all buffers associated with that fence + * are no longer in use by the associated ring on the GPU and + * that the relevant GPU caches have been flushed. + */ + +struct amdgpu_fence { + struct dma_fence base; + + /* RB, DMA, etc. */ + struct amdgpu_ring *ring; + ktime_t start_timestamp; +}; + extern const struct drm_sched_backend_ops amdgpu_sched_ops; void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c index 6716ac281c49..9b54a1ece447 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c @@ -540,8 +540,10 @@ static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id) case IP_VERSION(4, 4, 2): case IP_VERSION(4, 4, 4): case IP_VERSION(4, 4, 5): - /* For SDMA 4.x, use the existing DPM interface for backward compatibility */ - r = amdgpu_dpm_reset_sdma(adev, 1 << instance_id); + /* For SDMA 4.x, use the existing DPM interface for backward compatibility, + * we need to convert the logical instance ID to physical instance ID before reset. + */ + r = amdgpu_dpm_reset_sdma(adev, 1 << GET_INST(SDMA0, instance_id)); break; case IP_VERSION(5, 0, 0): case IP_VERSION(5, 0, 1): @@ -568,7 +570,7 @@ static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id) /** * amdgpu_sdma_reset_engine - Reset a specific SDMA engine * @adev: Pointer to the AMDGPU device - * @instance_id: ID of the SDMA engine instance to reset + * @instance_id: Logical ID of the SDMA engine instance to reset * * Returns: 0 on success, or a negative error code on failure. */ @@ -601,7 +603,7 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id) /* Perform the SDMA reset for the specified instance */ ret = amdgpu_sdma_soft_reset(adev, instance_id); if (ret) { - dev_err(adev->dev, "Failed to reset SDMA instance %u\n", instance_id); + dev_err(adev->dev, "Failed to reset SDMA logical instance %u\n", instance_id); goto exit; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index 2505c46a9c3d..eaddc441c51a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -30,6 +30,10 @@ #define AMDGPU_UCODE_NAME_MAX (128) +static const struct kicker_device kicker_device_list[] = { + {0x744B, 0x00}, +}; + static void amdgpu_ucode_print_common_hdr(const struct common_firmware_header *hdr) { DRM_DEBUG("size_bytes: %u\n", le32_to_cpu(hdr->size_bytes)); @@ -1387,6 +1391,19 @@ static const char *amdgpu_ucode_legacy_naming(struct amdgpu_device *adev, int bl return NULL; } +bool amdgpu_is_kicker_fw(struct amdgpu_device *adev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(kicker_device_list); i++) { + if (adev->pdev->device == kicker_device_list[i].device && + adev->pdev->revision == kicker_device_list[i].revision) + return true; + } + + return false; +} + void amdgpu_ucode_ip_version_decode(struct amdgpu_device *adev, int block_type, char *ucode_prefix, int len) { int maj, min, rev; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 9e89c3487be5..6349aad6da35 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -605,6 +605,11 @@ struct amdgpu_firmware { uint32_t pldm_version; }; +struct kicker_device{ + unsigned short device; + u8 revision; +}; + void amdgpu_ucode_print_mc_hdr(const struct common_firmware_header *hdr); void amdgpu_ucode_print_smc_hdr(const struct common_firmware_header *hdr); void amdgpu_ucode_print_imu_hdr(const struct common_firmware_header *hdr); @@ -632,5 +637,6 @@ amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type); const char *amdgpu_ucode_name(enum AMDGPU_UCODE_ID ucode_id); void amdgpu_ucode_ip_version_decode(struct amdgpu_device *adev, int block_type, char *ucode_prefix, int len); +bool amdgpu_is_kicker_fw(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index afd6d59164bf..ec9b84f92d46 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -85,6 +85,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_0_pfp.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_0_me.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_0_mec.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc_kicker.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc_1.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_0_toc.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_1_pfp.bin"); @@ -759,6 +760,10 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, AMDGPU_UCODE_REQUIRED, "amdgpu/gc_11_0_0_rlc_1.bin"); + else if (amdgpu_is_kicker_fw(adev)) + err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, + AMDGPU_UCODE_REQUIRED, + "amdgpu/%s_rlc_kicker.bin", ucode_prefix); else err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, AMDGPU_UCODE_REQUIRED, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index d377a7c57d5e..ad9be3656653 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2235,6 +2235,25 @@ static int gfx_v9_0_sw_init(struct amdgpu_ip_block *ip_block) } switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { + case IP_VERSION(9, 0, 1): + case IP_VERSION(9, 2, 1): + case IP_VERSION(9, 4, 0): + case IP_VERSION(9, 2, 2): + case IP_VERSION(9, 1, 0): + case IP_VERSION(9, 3, 0): + adev->gfx.cleaner_shader_ptr = gfx_9_4_2_cleaner_shader_hex; + adev->gfx.cleaner_shader_size = sizeof(gfx_9_4_2_cleaner_shader_hex); + if (adev->gfx.me_fw_version >= 167 && + adev->gfx.pfp_fw_version >= 196 && + adev->gfx.mec_fw_version >= 474) { + 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(9, 4, 2): adev->gfx.cleaner_shader_ptr = gfx_9_4_2_cleaner_shader_hex; adev->gfx.cleaner_shader_size = sizeof(gfx_9_4_2_cleaner_shader_hex); diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c index cfa91d709d49..cc626036ed9c 100644 --- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c @@ -32,6 +32,7 @@ #include "gc/gc_11_0_0_sh_mask.h" MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu_kicker.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_1_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_2_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_imu.bin"); @@ -51,8 +52,12 @@ static int imu_v11_0_init_microcode(struct amdgpu_device *adev) DRM_DEBUG("\n"); amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); - err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, AMDGPU_UCODE_REQUIRED, - "amdgpu/%s_imu.bin", ucode_prefix); + if (amdgpu_is_kicker_fw(adev)) + err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, AMDGPU_UCODE_REQUIRED, + "amdgpu/%s_imu_kicker.bin", ucode_prefix); + else + err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, AMDGPU_UCODE_REQUIRED, + "amdgpu/%s_imu.bin", ucode_prefix); if (err) goto out; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index c9eba537de09..28eb846280dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -1630,10 +1630,12 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) goto failure; - r = mes_v11_0_set_hw_resources_1(&adev->mes); - if (r) { - DRM_ERROR("failed mes_v11_0_set_hw_resources_1, r=%d\n", r); - goto failure; + if ((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x50) { + r = mes_v11_0_set_hw_resources_1(&adev->mes); + if (r) { + DRM_ERROR("failed mes_v11_0_set_hw_resources_1, r=%d\n", r); + goto failure; + } } r = mes_v11_0_query_sched_status(&adev->mes); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index b4f17332d466..6b222630f3fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -1742,7 +1742,8 @@ static int mes_v12_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) goto failure; - mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_SCHED_PIPE); + if ((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x4b) + mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_SCHED_PIPE); mes_v12_0_init_aggregated_doorbell(&adev->mes); diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index df612fd9cc50..ead616c11705 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -42,7 +42,9 @@ MODULE_FIRMWARE("amdgpu/psp_13_0_5_ta.bin"); MODULE_FIRMWARE("amdgpu/psp_13_0_8_toc.bin"); MODULE_FIRMWARE("amdgpu/psp_13_0_8_ta.bin"); MODULE_FIRMWARE("amdgpu/psp_13_0_0_sos.bin"); +MODULE_FIRMWARE("amdgpu/psp_13_0_0_sos_kicker.bin"); MODULE_FIRMWARE("amdgpu/psp_13_0_0_ta.bin"); +MODULE_FIRMWARE("amdgpu/psp_13_0_0_ta_kicker.bin"); MODULE_FIRMWARE("amdgpu/psp_13_0_7_sos.bin"); MODULE_FIRMWARE("amdgpu/psp_13_0_7_ta.bin"); MODULE_FIRMWARE("amdgpu/psp_13_0_10_sos.bin"); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c index 9c169112a5e7..bb82c652e4c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c @@ -45,6 +45,7 @@ #include "amdgpu_ras.h" MODULE_FIRMWARE("amdgpu/sdma_4_4_2.bin"); +MODULE_FIRMWARE("amdgpu/sdma_4_4_4.bin"); MODULE_FIRMWARE("amdgpu/sdma_4_4_5.bin"); static const struct amdgpu_hwip_reg_entry sdma_reg_list_4_4_2[] = { @@ -490,7 +491,7 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev, { struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES]; u32 doorbell_offset, doorbell; - u32 rb_cntl, ib_cntl; + u32 rb_cntl, ib_cntl, sdma_cntl; int i; for_each_inst(i, inst_mask) { @@ -502,6 +503,9 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev, ib_cntl = RREG32_SDMA(i, regSDMA_GFX_IB_CNTL); ib_cntl = REG_SET_FIELD(ib_cntl, SDMA_GFX_IB_CNTL, IB_ENABLE, 0); WREG32_SDMA(i, regSDMA_GFX_IB_CNTL, ib_cntl); + sdma_cntl = RREG32_SDMA(i, regSDMA_CNTL); + sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, UTC_L1_ENABLE, 0); + WREG32_SDMA(i, regSDMA_CNTL, sdma_cntl); if (sdma[i]->use_doorbell) { doorbell = RREG32_SDMA(i, regSDMA_GFX_DOORBELL); @@ -995,6 +999,7 @@ static int sdma_v4_4_2_inst_start(struct amdgpu_device *adev, /* set utc l1 enable flag always to 1 */ temp = RREG32_SDMA(i, regSDMA_CNTL); temp = REG_SET_FIELD(temp, SDMA_CNTL, UTC_L1_ENABLE, 1); + WREG32_SDMA(i, regSDMA_CNTL, temp); if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) < IP_VERSION(4, 4, 5)) { /* enable context empty interrupt during initialization */ @@ -1670,7 +1675,7 @@ static bool sdma_v4_4_2_page_ring_is_guilty(struct amdgpu_ring *ring) static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid) { struct amdgpu_device *adev = ring->adev; - u32 id = GET_INST(SDMA0, ring->me); + u32 id = ring->me; int r; if (!(adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)) @@ -1686,7 +1691,7 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid) static int sdma_v4_4_2_stop_queue(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - u32 instance_id = GET_INST(SDMA0, ring->me); + u32 instance_id = ring->me; u32 inst_mask; uint64_t rptr; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index 9505ae96fbec..37f4b5b4a098 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -1399,6 +1399,7 @@ static int sdma_v5_0_sw_init(struct amdgpu_ip_block *ip_block) return r; for (i = 0; i < adev->sdma.num_instances; i++) { + mutex_init(&adev->sdma.instance[i].engine_reset_mutex); adev->sdma.instance[i].funcs = &sdma_v5_0_sdma_funcs; ring = &adev->sdma.instance[i].ring; ring->ring_obj = NULL; @@ -1542,8 +1543,13 @@ static int sdma_v5_0_reset_queue(struct amdgpu_ring *ring, unsigned int vmid) { struct amdgpu_device *adev = ring->adev; u32 inst_id = ring->me; + int r; + + amdgpu_amdkfd_suspend(adev, true); + r = amdgpu_sdma_reset_engine(adev, inst_id); + amdgpu_amdkfd_resume(adev, true); - return amdgpu_sdma_reset_engine(adev, inst_id); + return r; } static int sdma_v5_0_stop_queue(struct amdgpu_ring *ring) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index a6e612b4a892..0b40411b92a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -1318,6 +1318,7 @@ static int sdma_v5_2_sw_init(struct amdgpu_ip_block *ip_block) } for (i = 0; i < adev->sdma.num_instances; i++) { + mutex_init(&adev->sdma.instance[i].engine_reset_mutex); adev->sdma.instance[i].funcs = &sdma_v5_2_sdma_funcs; ring = &adev->sdma.instance[i].ring; ring->ring_obj = NULL; @@ -1455,8 +1456,13 @@ static int sdma_v5_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid) { struct amdgpu_device *adev = ring->adev; u32 inst_id = ring->me; + int r; + + amdgpu_amdkfd_suspend(adev, true); + r = amdgpu_sdma_reset_engine(adev, inst_id); + amdgpu_amdkfd_resume(adev, true); - return amdgpu_sdma_reset_engine(adev, inst_id); + return r; } static int sdma_v5_2_stop_queue(struct amdgpu_ring *ring) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index 5a70ae17be04..a9bdf8d61d6c 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1374,9 +1374,22 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block) else DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n"); - /* add firmware version checks here */ - if (0 && !adev->sdma.disable_uq) - adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + 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) + 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) + 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) + adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + break; + default: + break; + } r = amdgpu_sdma_sysfs_reset_mask_init(adev); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index ad47d0bdf777..86903eccbd4e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -1349,9 +1349,15 @@ static int sdma_v7_0_sw_init(struct amdgpu_ip_block *ip_block) else DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n"); - /* add firmware version checks here */ - if (0 && !adev->sdma.disable_uq) - adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) { + case IP_VERSION(7, 0, 0): + case IP_VERSION(7, 0, 1): + if ((adev->sdma.instance[0].fw_version >= 7836028) && !adev->sdma.disable_uq) + adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + break; + default: + break; + } return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c index 338cf43c45fe..cdefd7fcb0da 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c @@ -669,6 +669,9 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst, if (indirect) amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM); + /* resetting ring, fw should not check RB ring */ + fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; + /* Pause dpg */ vcn_v5_0_1_pause_dpg_mode(vinst, &state); @@ -681,7 +684,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst, tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0); WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0); @@ -692,6 +695,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst, tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); tmp |= VCN_RB_ENABLE__RB1_EN_MASK; WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); + /* resetting done, fw can check RB ring */ fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); WREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c index 8fa6489b6f5d..505036968a77 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c @@ -240,7 +240,7 @@ static int pm_map_queues_v9(struct packet_manager *pm, uint32_t *buffer, packet->bitfields2.engine_sel = engine_sel__mes_map_queues__compute_vi; - packet->bitfields2.gws_control_queue = q->gws ? 1 : 0; + packet->bitfields2.gws_control_queue = q->properties.is_gws ? 1 : 0; packet->bitfields2.extended_engine_sel = extended_engine_sel__mes_map_queues__legacy_engine_sel; packet->bitfields2.queue_type = diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 865dca2547de..a0f22ea6d15a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1171,13 +1171,12 @@ svm_range_split_head(struct svm_range *prange, uint64_t new_start, } static void -svm_range_add_child(struct svm_range *prange, struct mm_struct *mm, - struct svm_range *pchild, enum svm_work_list_ops op) +svm_range_add_child(struct svm_range *prange, struct svm_range *pchild, enum svm_work_list_ops op) { pr_debug("add child 0x%p [0x%lx 0x%lx] to prange 0x%p child list %d\n", pchild, pchild->start, pchild->last, prange, op); - pchild->work_item.mm = mm; + pchild->work_item.mm = NULL; pchild->work_item.op = op; list_add_tail(&pchild->child_list, &prange->child_list); } @@ -1278,7 +1277,7 @@ svm_range_get_pte_flags(struct kfd_node *node, mapping_flags |= ext_coherent ? AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; /* system memory accessed by the dGPU */ } else { - if (gc_ip_version < IP_VERSION(9, 5, 0)) + if (gc_ip_version < IP_VERSION(9, 5, 0) || ext_coherent) mapping_flags |= AMDGPU_VM_MTYPE_UC; else mapping_flags |= AMDGPU_VM_MTYPE_NC; @@ -2394,15 +2393,17 @@ svm_range_add_list_work(struct svm_range_list *svms, struct svm_range *prange, prange->work_item.op != SVM_OP_UNMAP_RANGE) prange->work_item.op = op; } else { - prange->work_item.op = op; - - /* Pairs with mmput in deferred_list_work */ - mmget(mm); - prange->work_item.mm = mm; - list_add_tail(&prange->deferred_list, - &prange->svms->deferred_range_list); - pr_debug("add prange 0x%p [0x%lx 0x%lx] to work list op %d\n", - prange, prange->start, prange->last, op); + /* Pairs with mmput in deferred_list_work. + * If process is exiting and mm is gone, don't update mmu notifier. + */ + if (mmget_not_zero(mm)) { + prange->work_item.mm = mm; + prange->work_item.op = op; + list_add_tail(&prange->deferred_list, + &prange->svms->deferred_range_list); + pr_debug("add prange 0x%p [0x%lx 0x%lx] to work list op %d\n", + prange, prange->start, prange->last, op); + } } spin_unlock(&svms->deferred_list_lock); } @@ -2416,8 +2417,7 @@ void schedule_deferred_list_work(struct svm_range_list *svms) } static void -svm_range_unmap_split(struct mm_struct *mm, struct svm_range *parent, - struct svm_range *prange, unsigned long start, +svm_range_unmap_split(struct svm_range *parent, struct svm_range *prange, unsigned long start, unsigned long last) { struct svm_range *head; @@ -2438,12 +2438,12 @@ svm_range_unmap_split(struct mm_struct *mm, struct svm_range *parent, svm_range_split(tail, last + 1, tail->last, &head); if (head != prange && tail != prange) { - svm_range_add_child(parent, mm, head, SVM_OP_UNMAP_RANGE); - svm_range_add_child(parent, mm, tail, SVM_OP_ADD_RANGE); + svm_range_add_child(parent, head, SVM_OP_UNMAP_RANGE); + svm_range_add_child(parent, tail, SVM_OP_ADD_RANGE); } else if (tail != prange) { - svm_range_add_child(parent, mm, tail, SVM_OP_UNMAP_RANGE); + svm_range_add_child(parent, tail, SVM_OP_UNMAP_RANGE); } else if (head != prange) { - svm_range_add_child(parent, mm, head, SVM_OP_UNMAP_RANGE); + svm_range_add_child(parent, head, SVM_OP_UNMAP_RANGE); } else if (parent != prange) { prange->work_item.op = SVM_OP_UNMAP_RANGE; } @@ -2520,14 +2520,14 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange, l = min(last, pchild->last); if (l >= s) svm_range_unmap_from_gpus(pchild, s, l, trigger); - svm_range_unmap_split(mm, prange, pchild, start, last); + svm_range_unmap_split(prange, pchild, start, last); mutex_unlock(&pchild->lock); } s = max(start, prange->start); l = min(last, prange->last); if (l >= s) svm_range_unmap_from_gpus(prange, s, l, trigger); - svm_range_unmap_split(mm, prange, prange, start, last); + svm_range_unmap_split(prange, prange, start, last); if (unmap_parent) svm_range_add_list_work(svms, prange, mm, SVM_OP_UNMAP_RANGE); @@ -2570,8 +2570,6 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni, if (range->event == MMU_NOTIFY_RELEASE) return true; - if (!mmget_not_zero(mni->mm)) - return true; start = mni->interval_tree.start; last = mni->interval_tree.last; @@ -2598,7 +2596,6 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni, } svm_range_unlock(prange); - mmput(mni->mm); return true; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index baa2374acdeb..4ec73f33535e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -510,6 +510,10 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr, dev->node_props.capability |= HSA_CAP_AQL_QUEUE_DOUBLE_MAP; + if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(10, 0, 0) && + (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)) + dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED; + sysfs_show_32bit_prop(buffer, offs, "max_engine_clk_fcompute", dev->node_props.max_engine_clk_fcompute); @@ -2008,8 +2012,6 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev) if (!amdgpu_sriov_vf(dev->gpu->adev)) dev->node_props.capability |= HSA_CAP_PER_QUEUE_RESET_SUPPORTED; - if (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE) - dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED; } else { dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX10 | HSA_DBG_WATCH_ADDR_MASK_HI_BIT; 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 d3100f641ac6..f58fa5da7fe5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3610,13 +3610,15 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) luminance_range = &conn_base->display_info.luminance_range; - if (luminance_range->max_luminance) { - caps->aux_min_input_signal = luminance_range->min_luminance; + if (luminance_range->max_luminance) caps->aux_max_input_signal = luminance_range->max_luminance; - } else { - caps->aux_min_input_signal = 0; + else caps->aux_max_input_signal = 512; - } + + if (luminance_range->min_luminance) + caps->aux_min_input_signal = luminance_range->min_luminance; + else + caps->aux_min_input_signal = 1; min_input_signal_override = drm_get_panel_min_brightness_quirk(aconnector->drm_edid); if (min_input_signal_override >= 0) @@ -4718,9 +4720,23 @@ static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps, return 1; } +/* Rescale from [min..max] to [0..MAX_BACKLIGHT_LEVEL] */ +static inline u32 scale_input_to_fw(int min, int max, u64 input) +{ + return DIV_ROUND_CLOSEST_ULL(input * MAX_BACKLIGHT_LEVEL, max - min); +} + +/* Rescale from [0..MAX_BACKLIGHT_LEVEL] to [min..max] */ +static inline u32 scale_fw_to_input(int min, int max, u64 input) +{ + return min + DIV_ROUND_CLOSEST_ULL(input * (max - min), MAX_BACKLIGHT_LEVEL); +} + static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *caps, - uint32_t *brightness) + unsigned int min, unsigned int max, + uint32_t *user_brightness) { + u32 brightness = scale_input_to_fw(min, max, *user_brightness); u8 prev_signal = 0, prev_lum = 0; int i = 0; @@ -4731,7 +4747,7 @@ static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *cap return; /* choose start to run less interpolation steps */ - if (caps->luminance_data[caps->data_points/2].input_signal > *brightness) + if (caps->luminance_data[caps->data_points/2].input_signal > brightness) i = caps->data_points/2; do { u8 signal = caps->luminance_data[i].input_signal; @@ -4742,17 +4758,18 @@ static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *cap * brightness < signal: interpolate between previous and current luminance numerator * brightness > signal: find next data point */ - if (*brightness > signal) { + if (brightness > signal) { prev_signal = signal; prev_lum = lum; i++; continue; } - if (*brightness < signal) + if (brightness < signal) lum = prev_lum + DIV_ROUND_CLOSEST((lum - prev_lum) * - (*brightness - prev_signal), + (brightness - prev_signal), signal - prev_signal); - *brightness = DIV_ROUND_CLOSEST(lum * *brightness, 101); + *user_brightness = scale_fw_to_input(min, max, + DIV_ROUND_CLOSEST(lum * brightness, 101)); return; } while (i < caps->data_points); } @@ -4765,11 +4782,10 @@ static u32 convert_brightness_from_user(const struct amdgpu_dm_backlight_caps *c if (!get_brightness_range(caps, &min, &max)) return brightness; - convert_custom_brightness(caps, &brightness); + convert_custom_brightness(caps, min, max, &brightness); - // Rescale 0..255 to min..max - return min + DIV_ROUND_CLOSEST((max - min) * brightness, - AMDGPU_MAX_BL_LEVEL); + // Rescale 0..max to min..max + return min + DIV_ROUND_CLOSEST_ULL((u64)(max - min) * brightness, max); } static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *caps, @@ -4782,8 +4798,8 @@ static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *cap if (brightness < min) return 0; - // Rescale min..max to 0..255 - return DIV_ROUND_CLOSEST(AMDGPU_MAX_BL_LEVEL * (brightness - min), + // Rescale min..max to 0..max + return DIV_ROUND_CLOSEST_ULL((u64)max * (brightness - min), max - min); } @@ -4908,7 +4924,7 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) struct drm_device *drm = aconnector->base.dev; struct amdgpu_display_manager *dm = &drm_to_adev(drm)->dm; struct backlight_properties props = { 0 }; - struct amdgpu_dm_backlight_caps caps = { 0 }; + struct amdgpu_dm_backlight_caps *caps; char bl_name[16]; int min, max; @@ -4922,22 +4938,21 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) return; } - amdgpu_acpi_get_backlight_caps(&caps); - if (caps.caps_valid && get_brightness_range(&caps, &min, &max)) { + caps = &dm->backlight_caps[aconnector->bl_idx]; + if (get_brightness_range(caps, &min, &max)) { if (power_supply_is_system_supplied() > 0) - props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps.ac_level, 100); + props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps->ac_level, 100); else - props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps.dc_level, 100); + props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps->dc_level, 100); /* min is zero, so max needs to be adjusted */ props.max_brightness = max - min; drm_dbg(drm, "Backlight caps: min: %d, max: %d, ac %d, dc %d\n", min, max, - caps.ac_level, caps.dc_level); + caps->ac_level, caps->dc_level); } else - props.brightness = AMDGPU_MAX_BL_LEVEL; + props.brightness = props.max_brightness = MAX_BACKLIGHT_LEVEL; - if (caps.data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) + if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) drm_info(drm, "Using custom brightness curve\n"); - props.max_brightness = AMDGPU_MAX_BL_LEVEL; props.type = BACKLIGHT_RAW; snprintf(bl_name, sizeof(bl_name), "amdgpu_bl%d", diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index d4395b92fb85..9e3e51a2dc49 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -1029,6 +1029,10 @@ enum dc_edid_status dm_helpers_read_local_edid( return EDID_NO_RESPONSE; edid = drm_edid_raw(drm_edid); // FIXME: Get rid of drm_edid_raw() + if (!edid || + edid->extensions >= sizeof(sink->dc_edid.raw_edid) / EDID_LENGTH) + return EDID_BAD_INPUT; + sink->dc_edid.length = EDID_LENGTH * (edid->extensions + 1); memmove(sink->dc_edid.raw_edid, (uint8_t *)edid, sink->dc_edid.length); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 56d011a1323c..b34b5b52236d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -241,6 +241,7 @@ static bool create_links( DC_LOG_DC("BIOS object table - end"); /* Create a link for each usb4 dpia port */ + dc->lowest_dpia_link_index = MAX_LINKS; for (i = 0; i < dc->res_pool->usb4_dpia_count; i++) { struct link_init_data link_init_params = {0}; struct dc_link *link; @@ -253,6 +254,9 @@ static bool create_links( link = dc->link_srv->create_link(&link_init_params); if (link) { + if (dc->lowest_dpia_link_index > dc->link_count) + dc->lowest_dpia_link_index = dc->link_count; + dc->links[dc->link_count] = link; link->dc = dc; ++dc->link_count; @@ -6376,6 +6380,35 @@ unsigned int dc_get_det_buffer_size_from_state(const struct dc_state *context) else return 0; } +/** + *********************************************************************************************** + * dc_get_host_router_index: Get index of host router from a dpia link + * + * This function return a host router index of the target link. If the target link is dpia link. + * + * @param [in] link: target link + * @param [out] host_router_index: host router index of the target link + * + * @return: true if the host router index is found and valid. + * + *********************************************************************************************** + */ +bool dc_get_host_router_index(const struct dc_link *link, unsigned int *host_router_index) +{ + struct dc *dc = link->ctx->dc; + + if (link->ep_type != DISPLAY_ENDPOINT_USB4_DPIA) + return false; + + if (link->link_index < dc->lowest_dpia_link_index) + return false; + + *host_router_index = (link->link_index - dc->lowest_dpia_link_index) / dc->caps.num_of_dpias_per_host_router; + if (*host_router_index < dc->caps.num_of_host_routers) + return true; + else + return false; +} bool dc_is_cursor_limit_pending(struct dc *dc) { diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 1d917be36fc4..f41073c0147e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -66,7 +66,8 @@ struct dmub_notification; #define MAX_STREAMS 6 #define MIN_VIEWPORT_SIZE 12 #define MAX_NUM_EDP 2 -#define MAX_HOST_ROUTERS_NUM 2 +#define MAX_HOST_ROUTERS_NUM 3 +#define MAX_DPIA_PER_HOST_ROUTER 2 /* Display Core Interfaces */ struct dc_versions { @@ -305,6 +306,8 @@ struct dc_caps { /* Conservative limit for DCC cases which require ODM4:1 to support*/ uint32_t dcc_plane_width_limit; struct dc_scl_caps scl_caps; + uint8_t num_of_host_routers; + uint8_t num_of_dpias_per_host_router; }; struct dc_bug_wa { @@ -1603,6 +1606,7 @@ struct dc { uint8_t link_count; struct dc_link *links[MAX_LINKS]; + uint8_t lowest_dpia_link_index; struct link_service *link_srv; struct dc_state *current_state; @@ -2595,6 +2599,8 @@ struct dc_power_profile dc_get_power_profile_for_dc_state(const struct dc_state unsigned int dc_get_det_buffer_size_from_state(const struct dc_state *context); +bool dc_get_host_router_index(const struct dc_link *link, unsigned int *host_router_index); + /* DSC Interfaces */ #include "dc_dsc.h" diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h index 0bad8304ccf6..d346f8ae1634 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h @@ -1172,8 +1172,8 @@ struct dc_lttpr_caps { union dp_128b_132b_supported_lttpr_link_rates supported_128b_132b_rates; union dp_alpm_lttpr_cap alpm; uint8_t aux_rd_interval[MAX_REPEATER_CNT - 1]; - uint8_t lttpr_ieee_oui[3]; - uint8_t lttpr_device_id[6]; + uint8_t lttpr_ieee_oui[3]; // Always read from closest LTTPR to host + uint8_t lttpr_device_id[6]; // Always read from closest LTTPR to host }; struct dc_dongle_dfp_cap_ext { diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h index d562ddeca512..c9f6c6275ca1 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h @@ -974,6 +974,7 @@ struct dc_crtc_timing { uint32_t pix_clk_100hz; uint32_t min_refresh_in_uhz; + uint32_t max_refresh_in_uhz; uint32_t vic; uint32_t hdmi_vic; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c index d47cacfdb695..2aa6d44bb359 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c @@ -788,6 +788,7 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm plane->pixel_format = dml2_420_10; break; case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616: + case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616: case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F: case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F: plane->pixel_format = dml2_444_64; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c index c4dad7164d31..5b62cd19d979 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c @@ -4685,7 +4685,10 @@ static void calculate_tdlut_setting( //the tdlut is fetched during the 2 row times of prefetch. if (p->setup_for_tdlut) { *p->tdlut_groups_per_2row_ub = (unsigned int)math_ceil2((double) *p->tdlut_bytes_per_frame / *p->tdlut_bytes_per_group, 1); - *p->tdlut_opt_time = (*p->tdlut_bytes_per_frame - p->cursor_buffer_size * 1024) / tdlut_drain_rate; + if (*p->tdlut_bytes_per_frame > p->cursor_buffer_size * 1024) + *p->tdlut_opt_time = (*p->tdlut_bytes_per_frame - p->cursor_buffer_size * 1024) / tdlut_drain_rate; + else + *p->tdlut_opt_time = 0; *p->tdlut_drain_time = p->cursor_buffer_size * 1024 / tdlut_drain_rate; *p->tdlut_bytes_to_deliver = (unsigned int) (p->cursor_buffer_size * 1024.0); } diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c index 5de775fd8fce..208630754c8a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c @@ -953,6 +953,7 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p out->SourcePixelFormat[location] = dml_420_10; break; case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616: + case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616: case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F: case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F: out->SourcePixelFormat[location] = dml_444_64; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index e8730cc40edb..38e17b1796e1 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1225,7 +1225,7 @@ void dce110_blank_stream(struct pipe_ctx *pipe_ctx) return; if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) { - if (!link->skip_implict_edp_power_control) + if (!link->skip_implict_edp_power_control && hws) hws->funcs.edp_backlight_control(link, false); link->dc->hwss.set_abm_immediate_disable(pipe_ctx); } 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 c814d957305a..a267f574b619 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 @@ -1047,6 +1047,15 @@ void dcn35_calc_blocks_to_gate(struct dc *dc, struct dc_state *context, if (dc->caps.sequential_ono) { update_state->pg_pipe_res_update[PG_HUBP][pipe_ctx->stream_res.dsc->inst] = false; update_state->pg_pipe_res_update[PG_DPP][pipe_ctx->stream_res.dsc->inst] = false; + + /* All HUBP/DPP instances must be powered if the DSC inst != HUBP inst */ + if (!pipe_ctx->top_pipe && pipe_ctx->plane_res.hubp && + pipe_ctx->plane_res.hubp->inst != pipe_ctx->stream_res.dsc->inst) { + for (j = 0; j < dc->res_pool->pipe_count; ++j) { + update_state->pg_pipe_res_update[PG_HUBP][j] = false; + update_state->pg_pipe_res_update[PG_DPP][j] = false; + } + } } } @@ -1193,6 +1202,25 @@ void dcn35_calc_blocks_to_ungate(struct dc *dc, struct dc_state *context, update_state->pg_pipe_res_update[PG_HDMISTREAM][0] = true; if (dc->caps.sequential_ono) { + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i]; + + if (new_pipe->stream_res.dsc && !new_pipe->top_pipe && + update_state->pg_pipe_res_update[PG_DSC][new_pipe->stream_res.dsc->inst]) { + update_state->pg_pipe_res_update[PG_HUBP][new_pipe->stream_res.dsc->inst] = true; + update_state->pg_pipe_res_update[PG_DPP][new_pipe->stream_res.dsc->inst] = true; + + /* All HUBP/DPP instances must be powered if the DSC inst != HUBP inst */ + if (new_pipe->plane_res.hubp && + new_pipe->plane_res.hubp->inst != new_pipe->stream_res.dsc->inst) { + for (j = 0; j < dc->res_pool->pipe_count; ++j) { + update_state->pg_pipe_res_update[PG_HUBP][j] = true; + update_state->pg_pipe_res_update[PG_DPP][j] = true; + } + } + } + } + for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) { if (update_state->pg_pipe_res_update[PG_HUBP][i] && update_state->pg_pipe_res_update[PG_DPP][i]) { diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index a5127c2d47ef..0f965380a9b4 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -385,9 +385,15 @@ bool dp_is_128b_132b_signal(struct pipe_ctx *pipe_ctx) bool dp_is_lttpr_present(struct dc_link *link) { /* Some sink devices report invalid LTTPR revision, so don't validate against that cap */ - return (dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) != 0 && + uint32_t lttpr_count = dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt); + bool is_lttpr_present = (lttpr_count > 0 && link->dpcd_caps.lttpr_caps.max_lane_count > 0 && link->dpcd_caps.lttpr_caps.max_lane_count <= 4); + + if (lttpr_count > 0 && !is_lttpr_present) + DC_LOG_ERROR("LTTPR count is nonzero but invalid lane count reported. Assuming no LTTPR present.\n"); + + return is_lttpr_present; } /* in DP compliance test, DPR-120 may have @@ -1551,6 +1557,8 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link) uint8_t lttpr_dpcd_data[10] = {0}; enum dc_status status; bool is_lttpr_present; + uint32_t lttpr_count; + uint32_t closest_lttpr_offset; /* Logic to determine LTTPR support*/ bool vbios_lttpr_interop = link->dc->caps.vbios_lttpr_aware; @@ -1602,20 +1610,22 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link) lttpr_dpcd_data[DP_LTTPR_ALPM_CAPABILITIES - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; + lttpr_count = dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt); + /* If this chip cap is set, at least one retimer must exist in the chain * Override count to 1 if we receive a known bad count (0 or an invalid value) */ if (((link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && - (dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) == 0)) { + lttpr_count == 0) { /* If you see this message consistently, either the host platform has FIXED_VS flag * incorrectly configured or the sink device is returning an invalid count. */ DC_LOG_ERROR("lttpr_caps phy_repeater_cnt is 0x%x, forcing it to 0x80.", link->dpcd_caps.lttpr_caps.phy_repeater_cnt); link->dpcd_caps.lttpr_caps.phy_repeater_cnt = 0x80; + lttpr_count = 1; DC_LOG_DC("lttpr_caps forced phy_repeater_cnt = %d\n", link->dpcd_caps.lttpr_caps.phy_repeater_cnt); } - /* Attempt to train in LTTPR transparent mode if repeater count exceeds 8. */ is_lttpr_present = dp_is_lttpr_present(link); DC_LOG_DC("is_lttpr_present = %d\n", is_lttpr_present); @@ -1623,11 +1633,25 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link) if (is_lttpr_present) { CONN_DATA_DETECT(link, lttpr_dpcd_data, sizeof(lttpr_dpcd_data), "LTTPR Caps: "); - core_link_read_dpcd(link, DP_LTTPR_IEEE_OUI, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui)); - CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui), "LTTPR IEEE OUI: "); + // Identify closest LTTPR to determine if workarounds required for known embedded LTTPR + closest_lttpr_offset = dp_get_closest_lttpr_offset(lttpr_count); - core_link_read_dpcd(link, DP_LTTPR_DEVICE_ID, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id)); - CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id), "LTTPR Device ID: "); + core_link_read_dpcd(link, (DP_LTTPR_IEEE_OUI + closest_lttpr_offset), + link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui)); + core_link_read_dpcd(link, (DP_LTTPR_DEVICE_ID + closest_lttpr_offset), + link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id)); + + if (lttpr_count > 1) { + CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui), + "Closest LTTPR To Host's IEEE OUI: "); + CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id), + "Closest LTTPR To Host's LTTPR Device ID: "); + } else { + CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui), + "LTTPR IEEE OUI: "); + CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id), + "LTTPR Device ID: "); + } } return status; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c index 7e0af5297dc4..51ca0b2959fc 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c @@ -1954,6 +1954,9 @@ static bool dcn31_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1; + dc->caps.num_of_host_routers = 2; + dc->caps.num_of_dpias_per_host_router = 2; + /* Use pipe context based otg sync logic */ dc->config.use_pipe_ctx_sync_logic = true; dc->config.disable_hbr_audio_dp2 = true; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c index d96bc6cb73ad..8383e2e59be5 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c @@ -1885,6 +1885,9 @@ static bool dcn314_resource_construct( dc->caps.max_disp_clock_khz_at_vmin = 650000; + dc->caps.num_of_host_routers = 2; + dc->caps.num_of_dpias_per_host_router = 2; + /* Use pipe context based otg sync logic */ dc->config.use_pipe_ctx_sync_logic = true; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index 72c6cf047db0..e01aa2f2e13e 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -1894,6 +1894,9 @@ static bool dcn35_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1; + dc->caps.num_of_host_routers = 2; + dc->caps.num_of_dpias_per_host_router = 2; + /* max_disp_clock_khz_at_vmin is slightly lower than the STA value in order * to provide some margin. * It's expected for furture ASIC to have equal or higher value, in order to diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c index 989a270f7dea..4ebe4e00a4f8 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c @@ -1866,6 +1866,9 @@ static bool dcn351_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1; + dc->caps.num_of_host_routers = 2; + dc->caps.num_of_dpias_per_host_router = 2; + /* max_disp_clock_khz_at_vmin is slightly lower than the STA value in order * to provide some margin. * It's expected for furture ASIC to have equal or higher value, in order to diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c index 48e1f234185f..db36b8f9ce65 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c @@ -1867,6 +1867,9 @@ static bool dcn36_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1; + dc->caps.num_of_host_routers = 2; + dc->caps.num_of_dpias_per_host_router = 2; + /* max_disp_clock_khz_at_vmin is slightly lower than the STA value in order * to provide some margin. * It's expected for furture ASIC to have equal or higher value, in order to diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index 3ba9b62ba70b..250f09922d2f 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -155,6 +155,14 @@ unsigned int mod_freesync_calc_v_total_from_refresh( v_total = div64_u64(div64_u64(((unsigned long long)( frame_duration_in_ns) * (stream->timing.pix_clk_100hz / 10)), stream->timing.h_total), 1000000); + } else if (refresh_in_uhz >= stream->timing.max_refresh_in_uhz) { + /* When the target refresh rate is the maximum panel refresh rate + * round up the vtotal value to prevent off-by-one error causing + * v_total_min to be below the panel's lower bound + */ + v_total = div64_u64(div64_u64(((unsigned long long)( + frame_duration_in_ns) * (stream->timing.pix_clk_100hz / 10)), + stream->timing.h_total) + (1000000 - 1), 1000000); } else { v_total = div64_u64(div64_u64(((unsigned long long)( frame_duration_in_ns) * (stream->timing.pix_clk_100hz / 10)), diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index a7167668d189..1c7235935d14 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -58,6 +58,7 @@ MODULE_FIRMWARE("amdgpu/aldebaran_smc.bin"); MODULE_FIRMWARE("amdgpu/smu_13_0_0.bin"); +MODULE_FIRMWARE("amdgpu/smu_13_0_0_kicker.bin"); MODULE_FIRMWARE("amdgpu/smu_13_0_7.bin"); MODULE_FIRMWARE("amdgpu/smu_13_0_10.bin"); @@ -92,7 +93,7 @@ const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16}; int smu_v13_0_init_microcode(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - char ucode_prefix[15]; + char ucode_prefix[30]; int err = 0; const struct smc_firmware_header_v1_0 *hdr; const struct common_firmware_header *header; @@ -103,8 +104,13 @@ int smu_v13_0_init_microcode(struct smu_context *smu) return 0; amdgpu_ucode_ip_version_decode(adev, MP1_HWIP, ucode_prefix, sizeof(ucode_prefix)); - err = amdgpu_ucode_request(adev, &adev->pm.fw, AMDGPU_UCODE_REQUIRED, - "amdgpu/%s.bin", ucode_prefix); + + if (amdgpu_is_kicker_fw(adev)) + err = amdgpu_ucode_request(adev, &adev->pm.fw, AMDGPU_UCODE_REQUIRED, + "amdgpu/%s_kicker.bin", ucode_prefix); + else + err = amdgpu_ucode_request(adev, &adev->pm.fw, AMDGPU_UCODE_REQUIRED, + "amdgpu/%s.bin", ucode_prefix); if (err) goto out; diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c index 34547edf1ee3..87f2e5ee8790 100644 --- a/drivers/gpu/drm/arm/malidp_planes.c +++ b/drivers/gpu/drm/arm/malidp_planes.c @@ -159,7 +159,7 @@ bool malidp_format_mod_supported(struct drm_device *drm, } if (!fourcc_mod_is_vendor(modifier, ARM)) { - DRM_ERROR("Unknown modifier (not Arm)\n"); + DRM_DEBUG_KMS("Unknown modifier (not Arm)\n"); return false; } diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 1de832964e92..031980d8f3ab 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -29,7 +29,6 @@ */ #include <linux/delay.h> -#include <linux/export.h> #include <linux/pci.h> #include <drm/drm_atomic.h> diff --git a/drivers/gpu/drm/bridge/aux-hpd-bridge.c b/drivers/gpu/drm/bridge/aux-hpd-bridge.c index b3f588b71a7d..af6f79793407 100644 --- a/drivers/gpu/drm/bridge/aux-hpd-bridge.c +++ b/drivers/gpu/drm/bridge/aux-hpd-bridge.c @@ -64,10 +64,11 @@ struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, str adev->id = ret; adev->name = "dp_hpd_bridge"; adev->dev.parent = parent; - adev->dev.of_node = of_node_get(parent->of_node); adev->dev.release = drm_aux_hpd_bridge_release; adev->dev.platform_data = of_node_get(np); + device_set_of_node_from_dev(&adev->dev, parent); + ret = auxiliary_device_init(adev); if (ret) { of_node_put(adev->dev.platform_data); diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c index 79b009ab9396..29b0358a7b6d 100644 --- a/drivers/gpu/drm/bridge/panel.c +++ b/drivers/gpu/drm/bridge/panel.c @@ -299,6 +299,7 @@ struct drm_bridge *drm_panel_bridge_add_typed(struct drm_panel *panel, panel_bridge->bridge.of_node = panel->dev->of_node; panel_bridge->bridge.ops = DRM_BRIDGE_OP_MODES; panel_bridge->bridge.type = connector_type; + panel_bridge->bridge.pre_enable_prev_first = panel->prepare_prev_first; drm_bridge_add(&panel_bridge->bridge); @@ -413,8 +414,6 @@ struct drm_bridge *devm_drm_panel_bridge_add_typed(struct device *dev, return bridge; } - bridge->pre_enable_prev_first = panel->prepare_prev_first; - *ptr = bridge; devres_add(dev, ptr); @@ -456,8 +455,6 @@ struct drm_bridge *drmm_panel_bridge_add(struct drm_device *drm, if (ret) return ERR_PTR(ret); - bridge->pre_enable_prev_first = panel->prepare_prev_first; - return bridge; } EXPORT_SYMBOL(drmm_panel_bridge_add); diff --git a/drivers/gpu/drm/bridge/samsung-dsim.c b/drivers/gpu/drm/bridge/samsung-dsim.c index 0014c497e3fe..bccc88d25948 100644 --- a/drivers/gpu/drm/bridge/samsung-dsim.c +++ b/drivers/gpu/drm/bridge/samsung-dsim.c @@ -1095,7 +1095,7 @@ static void samsung_dsim_send_to_fifo(struct samsung_dsim *dsi, bool first = !xfer->tx_done; u32 reg; - dev_dbg(dev, "< xfer %pK: tx len %u, done %u, rx len %u, done %u\n", + dev_dbg(dev, "< xfer %p: tx len %u, done %u, rx len %u, done %u\n", xfer, length, xfer->tx_done, xfer->rx_len, xfer->rx_done); if (length > DSI_TX_FIFO_SIZE) @@ -1293,7 +1293,7 @@ static bool samsung_dsim_transfer_finish(struct samsung_dsim *dsi) spin_unlock_irqrestore(&dsi->transfer_lock, flags); dev_dbg(dsi->dev, - "> xfer %pK, tx_len %zu, tx_done %u, rx_len %u, rx_done %u\n", + "> xfer %p, tx_len %zu, tx_done %u, rx_len %u, rx_done %u\n", xfer, xfer->packet.payload_length, xfer->tx_done, xfer->rx_len, xfer->rx_done); diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 60224f476e1d..de9c23537465 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -348,12 +348,18 @@ static void ti_sn65dsi86_enable_comms(struct ti_sn65dsi86 *pdata, * 200 ms. We'll assume that the panel driver will have the hardcoded * delay in its prepare and always disable HPD. * - * If HPD somehow makes sense on some future panel we'll have to - * change this to be conditional on someone specifying that HPD should - * be used. + * For DisplayPort bridge type, we need HPD. So we use the bridge type + * to conditionally disable HPD. + * NOTE: The bridge type is set in ti_sn_bridge_probe() but enable_comms() + * can be called before. So for DisplayPort, HPD will be enabled once + * bridge type is set. We are using bridge type instead of "no-hpd" + * property because it is not used properly in devicetree description + * and hence is unreliable. */ - regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE, - HPD_DISABLE); + + if (pdata->bridge.type != DRM_MODE_CONNECTOR_DisplayPort) + regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE, + HPD_DISABLE); pdata->comms_enabled = true; @@ -1195,9 +1201,14 @@ static enum drm_connector_status ti_sn_bridge_detect(struct drm_bridge *bridge) struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); int val = 0; - pm_runtime_get_sync(pdata->dev); + /* + * Runtime reference is grabbed in ti_sn_bridge_hpd_enable() + * as the chip won't report HPD just after being powered on. + * HPD_DEBOUNCED_STATE reflects correct state only after the + * debounce time (~100-400 ms). + */ + regmap_read(pdata->regmap, SN_HPD_DISABLE_REG, &val); - pm_runtime_put_autosuspend(pdata->dev); return val & HPD_DEBOUNCED_STATE ? connector_status_connected : connector_status_disconnected; @@ -1220,6 +1231,26 @@ static void ti_sn65dsi86_debugfs_init(struct drm_bridge *bridge, struct dentry * debugfs_create_file("status", 0600, debugfs, pdata, &status_fops); } +static void ti_sn_bridge_hpd_enable(struct drm_bridge *bridge) +{ + struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); + + /* + * Device needs to be powered on before reading the HPD state + * for reliable hpd detection in ti_sn_bridge_detect() due to + * the high debounce time. + */ + + pm_runtime_get_sync(pdata->dev); +} + +static void ti_sn_bridge_hpd_disable(struct drm_bridge *bridge) +{ + struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); + + pm_runtime_put_autosuspend(pdata->dev); +} + static const struct drm_bridge_funcs ti_sn_bridge_funcs = { .attach = ti_sn_bridge_attach, .detach = ti_sn_bridge_detach, @@ -1234,6 +1265,8 @@ static const struct drm_bridge_funcs ti_sn_bridge_funcs = { .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, .debugfs_init = ti_sn65dsi86_debugfs_init, + .hpd_enable = ti_sn_bridge_hpd_enable, + .hpd_disable = ti_sn_bridge_hpd_disable, }; static void ti_sn_bridge_parse_lanes(struct ti_sn65dsi86 *pdata, @@ -1321,8 +1354,26 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev, pdata->bridge.type = pdata->next_bridge->type == DRM_MODE_CONNECTOR_DisplayPort ? DRM_MODE_CONNECTOR_DisplayPort : DRM_MODE_CONNECTOR_eDP; - if (pdata->bridge.type == DRM_MODE_CONNECTOR_DisplayPort) - pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT; + if (pdata->bridge.type == DRM_MODE_CONNECTOR_DisplayPort) { + pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT | + DRM_BRIDGE_OP_HPD; + /* + * If comms were already enabled they would have been enabled + * with the wrong value of HPD_DISABLE. Update it now. Comms + * could be enabled if anyone is holding a pm_runtime reference + * (like if a GPIO is in use). Note that in most cases nobody + * is doing AUX channel xfers before the bridge is added so + * HPD doesn't _really_ matter then. The only exception is in + * the eDP case where the panel wants to read the EDID before + * the bridge is added. We always consistently have HPD disabled + * for eDP. + */ + mutex_lock(&pdata->comms_mutex); + if (pdata->comms_enabled) + regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, + HPD_DISABLE, 0); + mutex_unlock(&pdata->comms_mutex); + }; drm_bridge_add(&pdata->bridge); diff --git a/drivers/gpu/drm/display/drm_bridge_connector.c b/drivers/gpu/drm/display/drm_bridge_connector.c index 7d2e499ea5de..262e93e07a28 100644 --- a/drivers/gpu/drm/display/drm_bridge_connector.c +++ b/drivers/gpu/drm/display/drm_bridge_connector.c @@ -708,11 +708,14 @@ struct drm_connector *drm_bridge_connector_init(struct drm_device *drm, if (bridge_connector->bridge_hdmi_audio || bridge_connector->bridge_dp_audio) { struct device *dev; + struct drm_bridge *bridge; if (bridge_connector->bridge_hdmi_audio) - dev = bridge_connector->bridge_hdmi_audio->hdmi_audio_dev; + bridge = bridge_connector->bridge_hdmi_audio; else - dev = bridge_connector->bridge_dp_audio->hdmi_audio_dev; + bridge = bridge_connector->bridge_dp_audio; + + dev = bridge->hdmi_audio_dev; ret = drm_connector_hdmi_audio_init(connector, dev, &drm_bridge_connector_hdmi_audio_funcs, diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index f2a6559a2710..dc622c78db9d 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -725,7 +725,7 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, * monitor doesn't power down exactly after the throw away read. */ if (!aux->is_remote) { - ret = drm_dp_dpcd_probe(aux, DP_DPCD_REV); + ret = drm_dp_dpcd_probe(aux, DP_LANE0_1_STATUS); if (ret < 0) return ret; } diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 1e659d2660f7..4bf0a76bb35e 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -212,6 +212,35 @@ void drm_gem_private_object_fini(struct drm_gem_object *obj) } EXPORT_SYMBOL(drm_gem_private_object_fini); +static void drm_gem_object_handle_get(struct drm_gem_object *obj) +{ + struct drm_device *dev = obj->dev; + + drm_WARN_ON(dev, !mutex_is_locked(&dev->object_name_lock)); + + if (obj->handle_count++ == 0) + drm_gem_object_get(obj); +} + +/** + * drm_gem_object_handle_get_unlocked - acquire reference on user-space handles + * @obj: GEM object + * + * Acquires a reference on the GEM buffer object's handle. Required + * to keep the GEM object alive. Call drm_gem_object_handle_put_unlocked() + * to release the reference. + */ +void drm_gem_object_handle_get_unlocked(struct drm_gem_object *obj) +{ + struct drm_device *dev = obj->dev; + + guard(mutex)(&dev->object_name_lock); + + drm_WARN_ON(dev, !obj->handle_count); /* first ref taken in create-tail helper */ + drm_gem_object_handle_get(obj); +} +EXPORT_SYMBOL(drm_gem_object_handle_get_unlocked); + /** * drm_gem_object_handle_free - release resources bound to userspace handles * @obj: GEM object to clean up. @@ -242,8 +271,14 @@ static void drm_gem_object_exported_dma_buf_free(struct drm_gem_object *obj) } } -static void -drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj) +/** + * drm_gem_object_handle_put_unlocked - releases reference on user-space handles + * @obj: GEM object + * + * Releases a reference on the GEM buffer object's handle. Possibly releases + * the GEM buffer object and associated dma-buf objects. + */ +void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj) { struct drm_device *dev = obj->dev; bool final = false; @@ -268,6 +303,7 @@ drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj) if (final) drm_gem_object_put(obj); } +EXPORT_SYMBOL(drm_gem_object_handle_put_unlocked); /* * Called at device or object close to release the file's @@ -389,8 +425,8 @@ drm_gem_handle_create_tail(struct drm_file *file_priv, int ret; WARN_ON(!mutex_is_locked(&dev->object_name_lock)); - if (obj->handle_count++ == 0) - drm_gem_object_get(obj); + + drm_gem_object_handle_get(obj); /* * Get the user-visible handle using idr. Preload and perform diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c index 6f72e7a0f427..14a87788695d 100644 --- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c +++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c @@ -99,7 +99,7 @@ void drm_gem_fb_destroy(struct drm_framebuffer *fb) unsigned int i; for (i = 0; i < fb->format->num_planes; i++) - drm_gem_object_put(fb->obj[i]); + drm_gem_object_handle_put_unlocked(fb->obj[i]); drm_framebuffer_cleanup(fb); kfree(fb); @@ -182,8 +182,10 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev, if (!objs[i]) { drm_dbg_kms(dev, "Failed to lookup GEM object\n"); ret = -ENOENT; - goto err_gem_object_put; + goto err_gem_object_handle_put_unlocked; } + drm_gem_object_handle_get_unlocked(objs[i]); + drm_gem_object_put(objs[i]); min_size = (height - 1) * mode_cmd->pitches[i] + drm_format_info_min_pitch(info, i, width) @@ -193,22 +195,22 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev, drm_dbg_kms(dev, "GEM object size (%zu) smaller than minimum size (%u) for plane %d\n", objs[i]->size, min_size, i); - drm_gem_object_put(objs[i]); + drm_gem_object_handle_put_unlocked(objs[i]); ret = -EINVAL; - goto err_gem_object_put; + goto err_gem_object_handle_put_unlocked; } } ret = drm_gem_fb_init(dev, fb, mode_cmd, objs, i, funcs); if (ret) - goto err_gem_object_put; + goto err_gem_object_handle_put_unlocked; return 0; -err_gem_object_put: +err_gem_object_handle_put_unlocked: while (i > 0) { --i; - drm_gem_object_put(objs[i]); + drm_gem_object_handle_put_unlocked(objs[i]); } return ret; } diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index e44f28fd81d3..be77d61a16ce 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -161,6 +161,8 @@ void drm_sysfs_lease_event(struct drm_device *dev); /* drm_gem.c */ int drm_gem_init(struct drm_device *dev); +void drm_gem_object_handle_get_unlocked(struct drm_gem_object *obj); +void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj); int drm_gem_handle_create_tail(struct drm_file *file_priv, struct drm_gem_object *obj, u32 *handlep); diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index e5184a0c2465..21fd647f8ce1 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -91,12 +91,13 @@ static const struct dev_pm_ops mipi_dsi_device_pm_ops = { .restore = pm_generic_restore, }; -static const struct bus_type mipi_dsi_bus_type = { +const struct bus_type mipi_dsi_bus_type = { .name = "mipi-dsi", .match = mipi_dsi_device_match, .uevent = mipi_dsi_uevent, .pm = &mipi_dsi_device_pm_ops, }; +EXPORT_SYMBOL_GPL(mipi_dsi_bus_type); /** * of_find_mipi_dsi_device_by_node() - find the MIPI DSI device matching a diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c index edbeab88ff2b..d983ee85cf13 100644 --- a/drivers/gpu/drm/drm_writeback.c +++ b/drivers/gpu/drm/drm_writeback.c @@ -343,17 +343,18 @@ EXPORT_SYMBOL(drm_writeback_connector_init_with_encoder); /** * drm_writeback_connector_cleanup - Cleanup the writeback connector * @dev: DRM device - * @wb_connector: Pointer to the writeback connector to clean up + * @data: Pointer to the writeback connector to clean up * * This will decrement the reference counter of blobs and destroy properties. It * will also clean the remaining jobs in this writeback connector. Caution: This helper will not * clean up the attached encoder and the drm_connector. */ static void drm_writeback_connector_cleanup(struct drm_device *dev, - struct drm_writeback_connector *wb_connector) + void *data) { unsigned long flags; struct drm_writeback_job *pos, *n; + struct drm_writeback_connector *wb_connector = data; delete_writeback_properties(dev); drm_property_blob_put(wb_connector->pixel_formats_blob_ptr); @@ -405,7 +406,7 @@ int drmm_writeback_connector_init(struct drm_device *dev, if (ret) return ret; - ret = drmm_add_action_or_reset(dev, (void *)drm_writeback_connector_cleanup, + ret = drmm_add_action_or_reset(dev, drm_writeback_connector_cleanup, wb_connector); if (ret) return ret; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 76a3a3e517d8..71e2e6b9d713 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -35,6 +35,7 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) { struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job); + struct drm_gpu_scheduler *sched = sched_job->sched; struct etnaviv_gpu *gpu = submit->gpu; u32 dma_addr, primid = 0; int change; @@ -89,7 +90,9 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job return DRM_GPU_SCHED_STAT_NOMINAL; out_no_timeout: - list_add(&sched_job->list, &sched_job->sched->pending_list); + spin_lock(&sched->job_list_lock); + list_add(&sched_job->list, &sched->pending_list); + spin_unlock(&sched->job_list_lock); return DRM_GPU_SCHED_STAT_NOMINAL; } diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index f91daefa9d2b..805aa28c1723 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -636,6 +636,10 @@ static irqreturn_t decon_irq_handler(int irq, void *dev_id) if (!ctx->drm_dev) goto out; + /* check if crtc and vblank have been initialized properly */ + if (!drm_dev_has_vblank(ctx->drm_dev)) + goto out; + if (!ctx->i80_if) { drm_crtc_handle_vblank(&ctx->crtc->base); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index c394cc702d7d..205c238cc73a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -187,6 +187,7 @@ struct fimd_context { u32 i80ifcon; bool i80_if; bool suspended; + bool dp_clk_enabled; wait_queue_head_t wait_vsync_queue; atomic_t wait_vsync_event; atomic_t win_updated; @@ -1047,7 +1048,18 @@ static void fimd_dp_clock_enable(struct exynos_drm_clk *clk, bool enable) struct fimd_context *ctx = container_of(clk, struct fimd_context, dp_clk); u32 val = enable ? DP_MIE_CLK_DP_ENABLE : DP_MIE_CLK_DISABLE; + + if (enable == ctx->dp_clk_enabled) + return; + + if (enable) + pm_runtime_resume_and_get(ctx->dev); + + ctx->dp_clk_enabled = enable; writel(val, ctx->regs + DP_MIE_CLKCON); + + if (!enable) + pm_runtime_put(ctx->dev); } static const struct exynos_drm_crtc_ops fimd_crtc_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c index 4787fee4696f..d44401a695e2 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c @@ -174,7 +174,7 @@ static struct exynos_drm_gem *exynos_drm_gem_init(struct drm_device *dev, return ERR_PTR(ret); } - DRM_DEV_DEBUG_KMS(dev->dev, "created file object = %pK\n", obj->filp); + DRM_DEV_DEBUG_KMS(dev->dev, "created file object = %p\n", obj->filp); return exynos_gem; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c index ea9f66037600..03c8490af4f4 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c +++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c @@ -271,7 +271,7 @@ static inline struct exynos_drm_ipp_task * task->src.rect.h = task->dst.rect.h = UINT_MAX; task->transform.rotation = DRM_MODE_ROTATE_0; - DRM_DEV_DEBUG_DRIVER(task->dev, "Allocated task %pK\n", task); + DRM_DEV_DEBUG_DRIVER(task->dev, "Allocated task %p\n", task); return task; } @@ -339,7 +339,7 @@ static int exynos_drm_ipp_task_set(struct exynos_drm_ipp_task *task, } DRM_DEV_DEBUG_DRIVER(task->dev, - "Got task %pK configuration from userspace\n", + "Got task %p configuration from userspace\n", task); return 0; } @@ -394,7 +394,7 @@ static void exynos_drm_ipp_task_release_buf(struct exynos_drm_ipp_buffer *buf) static void exynos_drm_ipp_task_free(struct exynos_drm_ipp *ipp, struct exynos_drm_ipp_task *task) { - DRM_DEV_DEBUG_DRIVER(task->dev, "Freeing task %pK\n", task); + DRM_DEV_DEBUG_DRIVER(task->dev, "Freeing task %p\n", task); exynos_drm_ipp_task_release_buf(&task->src); exynos_drm_ipp_task_release_buf(&task->dst); @@ -559,7 +559,7 @@ static int exynos_drm_ipp_check_format(struct exynos_drm_ipp_task *task, DRM_EXYNOS_IPP_FORMAT_DESTINATION); if (!fmt) { DRM_DEV_DEBUG_DRIVER(task->dev, - "Task %pK: %s format not supported\n", + "Task %p: %s format not supported\n", task, buf == src ? "src" : "dst"); return -EINVAL; } @@ -609,7 +609,7 @@ static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task) bool rotate = (rotation != DRM_MODE_ROTATE_0); bool scale = false; - DRM_DEV_DEBUG_DRIVER(task->dev, "Checking task %pK\n", task); + DRM_DEV_DEBUG_DRIVER(task->dev, "Checking task %p\n", task); if (src->rect.w == UINT_MAX) src->rect.w = src->buf.width; @@ -625,7 +625,7 @@ static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task) dst->rect.x + dst->rect.w > (dst->buf.width) || dst->rect.y + dst->rect.h > (dst->buf.height)) { DRM_DEV_DEBUG_DRIVER(task->dev, - "Task %pK: defined area is outside provided buffers\n", + "Task %p: defined area is outside provided buffers\n", task); return -EINVAL; } @@ -642,7 +642,7 @@ static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task) (!(ipp->capabilities & DRM_EXYNOS_IPP_CAP_SCALE) && scale) || (!(ipp->capabilities & DRM_EXYNOS_IPP_CAP_CONVERT) && src->buf.fourcc != dst->buf.fourcc)) { - DRM_DEV_DEBUG_DRIVER(task->dev, "Task %pK: hw capabilities exceeded\n", + DRM_DEV_DEBUG_DRIVER(task->dev, "Task %p: hw capabilities exceeded\n", task); return -EINVAL; } @@ -655,7 +655,7 @@ static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task) if (ret) return ret; - DRM_DEV_DEBUG_DRIVER(ipp->dev, "Task %pK: all checks done.\n", + DRM_DEV_DEBUG_DRIVER(ipp->dev, "Task %p: all checks done.\n", task); return ret; @@ -667,25 +667,25 @@ static int exynos_drm_ipp_task_setup_buffers(struct exynos_drm_ipp_task *task, struct exynos_drm_ipp_buffer *src = &task->src, *dst = &task->dst; int ret = 0; - DRM_DEV_DEBUG_DRIVER(task->dev, "Setting buffer for task %pK\n", + DRM_DEV_DEBUG_DRIVER(task->dev, "Setting buffer for task %p\n", task); ret = exynos_drm_ipp_task_setup_buffer(src, filp); if (ret) { DRM_DEV_DEBUG_DRIVER(task->dev, - "Task %pK: src buffer setup failed\n", + "Task %p: src buffer setup failed\n", task); return ret; } ret = exynos_drm_ipp_task_setup_buffer(dst, filp); if (ret) { DRM_DEV_DEBUG_DRIVER(task->dev, - "Task %pK: dst buffer setup failed\n", + "Task %p: dst buffer setup failed\n", task); return ret; } - DRM_DEV_DEBUG_DRIVER(task->dev, "Task %pK: buffers prepared.\n", + DRM_DEV_DEBUG_DRIVER(task->dev, "Task %p: buffers prepared.\n", task); return ret; @@ -764,7 +764,7 @@ void exynos_drm_ipp_task_done(struct exynos_drm_ipp_task *task, int ret) struct exynos_drm_ipp *ipp = task->ipp; unsigned long flags; - DRM_DEV_DEBUG_DRIVER(task->dev, "ipp: %d, task %pK done: %d\n", + DRM_DEV_DEBUG_DRIVER(task->dev, "ipp: %d, task %p done: %d\n", ipp->id, task, ret); spin_lock_irqsave(&ipp->lock, flags); @@ -807,7 +807,7 @@ static void exynos_drm_ipp_next_task(struct exynos_drm_ipp *ipp) spin_unlock_irqrestore(&ipp->lock, flags); DRM_DEV_DEBUG_DRIVER(ipp->dev, - "ipp: %d, selected task %pK to run\n", ipp->id, + "ipp: %d, selected task %p to run\n", ipp->id, task); ret = ipp->funcs->commit(ipp, task); @@ -917,14 +917,14 @@ int exynos_drm_ipp_commit_ioctl(struct drm_device *dev, void *data, */ if (arg->flags & DRM_EXYNOS_IPP_FLAG_NONBLOCK) { DRM_DEV_DEBUG_DRIVER(ipp->dev, - "ipp: %d, nonblocking processing task %pK\n", + "ipp: %d, nonblocking processing task %p\n", ipp->id, task); task->flags |= DRM_EXYNOS_IPP_TASK_ASYNC; exynos_drm_ipp_schedule_task(task->ipp, task); ret = 0; } else { - DRM_DEV_DEBUG_DRIVER(ipp->dev, "ipp: %d, processing task %pK\n", + DRM_DEV_DEBUG_DRIVER(ipp->dev, "ipp: %d, processing task %p\n", ipp->id, task); exynos_drm_ipp_schedule_task(ipp, task); ret = wait_event_interruptible(ipp->done_wq, diff --git a/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c b/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c index 74bb3bedf30f..5111bdc3075b 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c +++ b/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c @@ -103,8 +103,8 @@ static void get_ana_cp_int_prop(u64 vco_clk, DIV_ROUND_DOWN_ULL(curve_1_interpolated, CURVE0_MULTIPLIER))); ana_cp_int_temp = - DIV_ROUND_CLOSEST_ULL(DIV_ROUND_DOWN_ULL(adjusted_vco_clk1, curve_2_scaled1), - CURVE2_MULTIPLIER); + DIV64_U64_ROUND_CLOSEST(DIV_ROUND_DOWN_ULL(adjusted_vco_clk1, curve_2_scaled1), + CURVE2_MULTIPLIER); *ana_cp_int = max(1, min(ana_cp_int_temp, 127)); diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index 346737f15fa9..2007bb9d974d 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -1056,7 +1056,7 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder, BXT_MIPI_TRANS_VACTIVE(port)); adjusted_mode->crtc_vtotal = intel_de_read(display, - BXT_MIPI_TRANS_VTOTAL(port)); + BXT_MIPI_TRANS_VTOTAL(port)) + 1; hactive = adjusted_mode->crtc_hdisplay; hfp = intel_de_read(display, MIPI_HFP_COUNT(display, port)); @@ -1260,7 +1260,7 @@ static void set_dsi_timings(struct intel_encoder *encoder, intel_de_write(display, BXT_MIPI_TRANS_VACTIVE(port), adjusted_mode->crtc_vdisplay); intel_de_write(display, BXT_MIPI_TRANS_VTOTAL(port), - adjusted_mode->crtc_vtotal); + adjusted_mode->crtc_vtotal - 1); } intel_de_write(display, MIPI_HACTIVE_AREA_COUNT(display, port), @@ -1589,8 +1589,8 @@ static void vlv_dsi_add_properties(struct intel_connector *connector) static void vlv_dphy_param_init(struct intel_dsi *intel_dsi) { + struct intel_display *display = to_intel_display(&intel_dsi->base); struct intel_connector *connector = intel_dsi->attached_connector; - struct intel_display *display = to_intel_display(connector); struct mipi_config *mipi_config = connector->panel.vbt.dsi.config; u32 tlpx_ns, extra_byte_count, tlpx_ui; u32 ui_num, ui_den; diff --git a/drivers/gpu/drm/i915/gt/intel_gsc.c b/drivers/gpu/drm/i915/gt/intel_gsc.c index 1e925c75fb08..c43febc862dc 100644 --- a/drivers/gpu/drm/i915/gt/intel_gsc.c +++ b/drivers/gpu/drm/i915/gt/intel_gsc.c @@ -284,7 +284,7 @@ static void gsc_irq_handler(struct intel_gt *gt, unsigned int intf_id) if (gt->gsc.intf[intf_id].irq < 0) return; - ret = generic_handle_irq(gt->gsc.intf[intf_id].irq); + ret = generic_handle_irq_safe(gt->gsc.intf[intf_id].irq); if (ret) gt_err_ratelimited(gt, "error handling GSC irq: %d\n", ret); } diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index a876a34455f1..2a6d79abf25b 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -610,7 +610,6 @@ static int ring_context_alloc(struct intel_context *ce) /* One ringbuffer to rule them all */ GEM_BUG_ON(!engine->legacy.ring); ce->ring = engine->legacy.ring; - ce->timeline = intel_timeline_get(engine->legacy.timeline); GEM_BUG_ON(ce->state); if (engine->context_size) { @@ -623,6 +622,8 @@ static int ring_context_alloc(struct intel_context *ce) ce->state = vma; } + ce->timeline = intel_timeline_get(engine->legacy.timeline); + return 0; } diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index e5a188ce3185..5bc696bfbb0f 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -108,11 +108,11 @@ static unsigned int config_bit(const u64 config) return other_bit(config); } -static u32 config_mask(const u64 config) +static __always_inline u32 config_mask(const u64 config) { unsigned int bit = config_bit(config); - if (__builtin_constant_p(config)) + if (__builtin_constant_p(bit)) BUILD_BUG_ON(bit > BITS_PER_TYPE(typeof_member(struct i915_pmu, enable)) - 1); @@ -121,7 +121,7 @@ static u32 config_mask(const u64 config) BITS_PER_TYPE(typeof_member(struct i915_pmu, enable)) - 1); - return BIT(config_bit(config)); + return BIT(bit); } static bool is_engine_event(struct perf_event *event) diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index 88870844b5bd..2fb7a9e7efec 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -73,8 +73,8 @@ static int igt_add_request(void *arg) /* Basic preliminary test to create a request and let it loose! */ request = mock_request(rcs0(i915)->kernel_context, HZ / 10); - if (!request) - return -ENOMEM; + if (IS_ERR(request)) + return PTR_ERR(request); i915_request_add(request); @@ -91,8 +91,8 @@ static int igt_wait_request(void *arg) /* Submit a request, then wait upon it */ request = mock_request(rcs0(i915)->kernel_context, T); - if (!request) - return -ENOMEM; + if (IS_ERR(request)) + return PTR_ERR(request); i915_request_get(request); @@ -160,8 +160,8 @@ static int igt_fence_wait(void *arg) /* Submit a request, treat it as a fence and wait upon it */ request = mock_request(rcs0(i915)->kernel_context, T); - if (!request) - return -ENOMEM; + if (IS_ERR(request)) + return PTR_ERR(request); if (dma_fence_wait_timeout(&request->fence, false, T) != -ETIME) { pr_err("fence wait success before submit (expected timeout)!\n"); @@ -219,8 +219,8 @@ static int igt_request_rewind(void *arg) GEM_BUG_ON(IS_ERR(ce)); request = mock_request(ce, 2 * HZ); intel_context_put(ce); - if (!request) { - err = -ENOMEM; + if (IS_ERR(request)) { + err = PTR_ERR(request); goto err_context_0; } @@ -237,8 +237,8 @@ static int igt_request_rewind(void *arg) GEM_BUG_ON(IS_ERR(ce)); vip = mock_request(ce, 0); intel_context_put(ce); - if (!vip) { - err = -ENOMEM; + if (IS_ERR(vip)) { + err = PTR_ERR(vip); goto err_context_1; } diff --git a/drivers/gpu/drm/i915/selftests/mock_request.c b/drivers/gpu/drm/i915/selftests/mock_request.c index 09f747228dff..1b0cf073e964 100644 --- a/drivers/gpu/drm/i915/selftests/mock_request.c +++ b/drivers/gpu/drm/i915/selftests/mock_request.c @@ -35,7 +35,7 @@ mock_request(struct intel_context *ce, unsigned long delay) /* NB the i915->requests slab cache is enlarged to fit mock_request */ request = intel_context_create_request(ce); if (IS_ERR(request)) - return NULL; + return request; request->mock.delay = delay; return request; diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c index 47136bbbe8c6..ab08d690d882 100644 --- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c +++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c @@ -109,7 +109,7 @@ static void meson_encoder_hdmi_set_vclk(struct meson_encoder_hdmi *encoder_hdmi, venc_freq /= 2; dev_dbg(priv->dev, - "vclk:%lluHz phy=%lluHz venc=%lluHz hdmi=%lluHz enci=%d\n", + "phy:%lluHz vclk=%lluHz venc=%lluHz hdmi=%lluHz enci=%d\n", phy_freq, vclk_freq, venc_freq, hdmi_freq, priv->venc.hdmi_use_enci); diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c index 3325580d885d..dfe0c28a0f05 100644 --- a/drivers/gpu/drm/meson/meson_vclk.c +++ b/drivers/gpu/drm/meson/meson_vclk.c @@ -110,10 +110,7 @@ #define HDMI_PLL_LOCK BIT(31) #define HDMI_PLL_LOCK_G12A (3 << 30) -#define PIXEL_FREQ_1000_1001(_freq) \ - DIV_ROUND_CLOSEST_ULL((_freq) * 1000ULL, 1001ULL) -#define PHY_FREQ_1000_1001(_freq) \ - (PIXEL_FREQ_1000_1001(DIV_ROUND_DOWN_ULL(_freq, 10ULL)) * 10) +#define FREQ_1000_1001(_freq) DIV_ROUND_CLOSEST_ULL((_freq) * 1000ULL, 1001ULL) /* VID PLL Dividers */ enum { @@ -772,6 +769,36 @@ static void meson_hdmi_pll_generic_set(struct meson_drm *priv, pll_freq); } +static bool meson_vclk_freqs_are_matching_param(unsigned int idx, + unsigned long long phy_freq, + unsigned long long vclk_freq) +{ + DRM_DEBUG_DRIVER("i = %d vclk_freq = %lluHz alt = %lluHz\n", + idx, params[idx].vclk_freq, + FREQ_1000_1001(params[idx].vclk_freq)); + DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n", + idx, params[idx].phy_freq, + FREQ_1000_1001(params[idx].phy_freq)); + + /* Match strict frequency */ + if (phy_freq == params[idx].phy_freq && + vclk_freq == params[idx].vclk_freq) + return true; + + /* Match 1000/1001 variant: vclk deviation has to be less than 1kHz + * (drm EDID is defined in 1kHz steps, so everything smaller must be + * rounding error) and the PHY freq deviation has to be less than + * 10kHz (as the TMDS clock is 10 times the pixel clock, so anything + * smaller must be rounding error as well). + */ + if (abs(vclk_freq - FREQ_1000_1001(params[idx].vclk_freq)) < 1000 && + abs(phy_freq - FREQ_1000_1001(params[idx].phy_freq)) < 10000) + return true; + + /* no match */ + return false; +} + enum drm_mode_status meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned long long phy_freq, @@ -790,19 +817,7 @@ meson_vclk_vic_supported_freq(struct meson_drm *priv, } for (i = 0 ; params[i].pixel_freq ; ++i) { - DRM_DEBUG_DRIVER("i = %d pixel_freq = %lluHz alt = %lluHz\n", - i, params[i].pixel_freq, - PIXEL_FREQ_1000_1001(params[i].pixel_freq)); - DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n", - i, params[i].phy_freq, - PHY_FREQ_1000_1001(params[i].phy_freq)); - /* Match strict frequency */ - if (phy_freq == params[i].phy_freq && - vclk_freq == params[i].vclk_freq) - return MODE_OK; - /* Match 1000/1001 variant */ - if (phy_freq == PHY_FREQ_1000_1001(params[i].phy_freq) && - vclk_freq == PIXEL_FREQ_1000_1001(params[i].vclk_freq)) + if (meson_vclk_freqs_are_matching_param(i, phy_freq, vclk_freq)) return MODE_OK; } @@ -1075,10 +1090,8 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target, } for (freq = 0 ; params[freq].pixel_freq ; ++freq) { - if ((phy_freq == params[freq].phy_freq || - phy_freq == PHY_FREQ_1000_1001(params[freq].phy_freq)) && - (vclk_freq == params[freq].vclk_freq || - vclk_freq == PIXEL_FREQ_1000_1001(params[freq].vclk_freq))) { + if (meson_vclk_freqs_are_matching_param(freq, phy_freq, + vclk_freq)) { if (vclk_freq != params[freq].vclk_freq) vic_alternate_clock = true; else diff --git a/drivers/gpu/drm/mgag200/mgag200_ddc.c b/drivers/gpu/drm/mgag200/mgag200_ddc.c index 6d81ea8931e8..c31673eaa554 100644 --- a/drivers/gpu/drm/mgag200/mgag200_ddc.c +++ b/drivers/gpu/drm/mgag200/mgag200_ddc.c @@ -26,7 +26,6 @@ * Authors: Dave Airlie <airlied@redhat.com> */ -#include <linux/export.h> #include <linux/i2c-algo-bit.h> #include <linux/i2c.h> #include <linux/pci.h> diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c index 39641551eeb6..4280f71e472a 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c @@ -71,10 +71,6 @@ static int a2xx_gpummu_unmap(struct msm_mmu *mmu, uint64_t iova, size_t len) return 0; } -static void a2xx_gpummu_resume_translation(struct msm_mmu *mmu) -{ -} - static void a2xx_gpummu_destroy(struct msm_mmu *mmu) { struct a2xx_gpummu *gpummu = to_a2xx_gpummu(mmu); @@ -90,7 +86,6 @@ static const struct msm_mmu_funcs funcs = { .map = a2xx_gpummu_map, .unmap = a2xx_gpummu_unmap, .destroy = a2xx_gpummu_destroy, - .resume_translation = a2xx_gpummu_resume_translation, }; struct msm_mmu *a2xx_gpummu_new(struct device *dev, struct msm_gpu *gpu) diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 650e5bac225f..60aef0796236 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -131,6 +131,8 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) struct msm_ringbuffer *ring = submit->ring; unsigned int i, ibs = 0; + adreno_check_and_reenable_stall(adreno_gpu); + if (IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) && submit->in_rb) { ring->cur_ctx_seqno = 0; a5xx_submit_in_rb(gpu, submit); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index bf3758f010f4..491fde0083a2 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -130,6 +130,20 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence))); OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence))); OUT_RING(ring, submit->seqno - 1); + + OUT_PKT7(ring, CP_THREAD_CONTROL, 1); + OUT_RING(ring, CP_SET_THREAD_BOTH); + + /* Reset state used to synchronize BR and BV */ + OUT_PKT7(ring, CP_RESET_CONTEXT_STATE, 1); + OUT_RING(ring, + CP_RESET_CONTEXT_STATE_0_CLEAR_ON_CHIP_TS | + CP_RESET_CONTEXT_STATE_0_CLEAR_RESOURCE_TABLE | + CP_RESET_CONTEXT_STATE_0_CLEAR_BV_BR_COUNTER | + CP_RESET_CONTEXT_STATE_0_RESET_GLOBAL_LOCAL_TS); + + OUT_PKT7(ring, CP_THREAD_CONTROL, 1); + OUT_RING(ring, CP_SET_THREAD_BR); } if (!sysprof) { @@ -212,6 +226,8 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) struct msm_ringbuffer *ring = submit->ring; unsigned int i, ibs = 0; + adreno_check_and_reenable_stall(adreno_gpu); + a6xx_set_pagetable(a6xx_gpu, ring, submit); get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0), @@ -335,6 +351,8 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) struct msm_ringbuffer *ring = submit->ring; unsigned int i, ibs = 0; + adreno_check_and_reenable_stall(adreno_gpu); + /* * Toggle concurrent binning for pagetable switch and set the thread to * BR since only it can execute the pagetable switch packets. diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index f5e1490d07c1..16e7ac444efd 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -137,9 +137,8 @@ err_disable_rpm: return NULL; } -static int find_chipid(struct device *dev, uint32_t *chipid) +static int find_chipid(struct device_node *node, uint32_t *chipid) { - struct device_node *node = dev->of_node; const char *compat; int ret; @@ -173,15 +172,36 @@ static int find_chipid(struct device *dev, uint32_t *chipid) /* and if that fails, fall back to legacy "qcom,chipid" property: */ ret = of_property_read_u32(node, "qcom,chipid", chipid); if (ret) { - DRM_DEV_ERROR(dev, "could not parse qcom,chipid: %d\n", ret); + DRM_ERROR("%pOF: could not parse qcom,chipid: %d\n", + node, ret); return ret; } - dev_warn(dev, "Using legacy qcom,chipid binding!\n"); + pr_warn("%pOF: Using legacy qcom,chipid binding!\n", node); return 0; } +bool adreno_has_gpu(struct device_node *node) +{ + const struct adreno_info *info; + uint32_t chip_id; + int ret; + + ret = find_chipid(node, &chip_id); + if (ret) + return false; + + info = adreno_info(chip_id); + if (!info) { + pr_warn("%pOF: Unknown GPU revision: %"ADRENO_CHIPID_FMT"\n", + node, ADRENO_CHIPID_ARGS(chip_id)); + return false; + } + + return true; +} + static int adreno_bind(struct device *dev, struct device *master, void *data) { static struct adreno_platform_config config = {}; @@ -191,19 +211,18 @@ static int adreno_bind(struct device *dev, struct device *master, void *data) struct msm_gpu *gpu; int ret; - ret = find_chipid(dev, &config.chip_id); - if (ret) + ret = find_chipid(dev->of_node, &config.chip_id); + /* We shouldn't have gotten this far if we can't parse the chip_id */ + if (WARN_ON(ret)) return ret; dev->platform_data = &config; priv->gpu_pdev = to_platform_device(dev); info = adreno_info(config.chip_id); - if (!info) { - dev_warn(drm->dev, "Unknown GPU revision: %"ADRENO_CHIPID_FMT"\n", - ADRENO_CHIPID_ARGS(config.chip_id)); + /* We shouldn't have gotten this far if we don't recognize the GPU: */ + if (WARN_ON(!info)) return -ENXIO; - } config.info = info; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 2348ffb35f7e..86bff915c3e7 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -259,24 +259,54 @@ u64 adreno_private_address_space_size(struct msm_gpu *gpu) return BIT(ttbr1_cfg->ias) - ADRENO_VM_START; } +void adreno_check_and_reenable_stall(struct adreno_gpu *adreno_gpu) +{ + struct msm_gpu *gpu = &adreno_gpu->base; + struct msm_drm_private *priv = gpu->dev->dev_private; + unsigned long flags; + + /* + * Wait until the cooldown period has passed and we would actually + * collect a crashdump to re-enable stall-on-fault. + */ + spin_lock_irqsave(&priv->fault_stall_lock, flags); + if (!priv->stall_enabled && + ktime_after(ktime_get(), priv->stall_reenable_time) && + !READ_ONCE(gpu->crashstate)) { + priv->stall_enabled = true; + + gpu->aspace->mmu->funcs->set_stall(gpu->aspace->mmu, true); + } + spin_unlock_irqrestore(&priv->fault_stall_lock, flags); +} + #define ARM_SMMU_FSR_TF BIT(1) #define ARM_SMMU_FSR_PF BIT(3) #define ARM_SMMU_FSR_EF BIT(4) +#define ARM_SMMU_FSR_SS BIT(30) int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags, struct adreno_smmu_fault_info *info, const char *block, u32 scratch[4]) { + struct msm_drm_private *priv = gpu->dev->dev_private; const char *type = "UNKNOWN"; - bool do_devcoredump = info && !READ_ONCE(gpu->crashstate); + bool do_devcoredump = info && (info->fsr & ARM_SMMU_FSR_SS) && + !READ_ONCE(gpu->crashstate); + unsigned long irq_flags; /* - * If we aren't going to be resuming later from fault_worker, then do - * it now. + * In case there is a subsequent storm of pagefaults, disable + * stall-on-fault for at least half a second. */ - if (!do_devcoredump) { - gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu); + spin_lock_irqsave(&priv->fault_stall_lock, irq_flags); + if (priv->stall_enabled) { + priv->stall_enabled = false; + + gpu->aspace->mmu->funcs->set_stall(gpu->aspace->mmu, false); } + priv->stall_reenable_time = ktime_add_ms(ktime_get(), 500); + spin_unlock_irqrestore(&priv->fault_stall_lock, irq_flags); /* * Print a default message if we couldn't get the data from the @@ -304,16 +334,18 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags, scratch[0], scratch[1], scratch[2], scratch[3]); if (do_devcoredump) { + struct msm_gpu_fault_info fault_info = {}; + /* Turn off the hangcheck timer to keep it from bothering us */ timer_delete(&gpu->hangcheck_timer); - gpu->fault_info.ttbr0 = info->ttbr0; - gpu->fault_info.iova = iova; - gpu->fault_info.flags = flags; - gpu->fault_info.type = type; - gpu->fault_info.block = block; + fault_info.ttbr0 = info->ttbr0; + fault_info.iova = iova; + fault_info.flags = flags; + fault_info.type = type; + fault_info.block = block; - kthread_queue_work(gpu->worker, &gpu->fault_work); + msm_gpu_fault_crashstate_capture(gpu, &fault_info); } return 0; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index a8f4bf416e64..bc063594a359 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -636,6 +636,8 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags, struct adreno_smmu_fault_info *info, const char *block, u32 scratch[4]); +void adreno_check_and_reenable_stall(struct adreno_gpu *gpu); + int adreno_read_speedbin(struct device *dev, u32 *speedbin); /* diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index 8a618841e3ea..1c468ca5d692 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -94,17 +94,21 @@ static void drm_mode_to_intf_timing_params( timing->vsync_polarity = 0; } - /* for DP/EDP, Shift timings to align it to bottom right */ - if (phys_enc->hw_intf->cap->type == INTF_DP) { + timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent); + timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent); + + /* + * For DP/EDP, Shift timings to align it to bottom right. + * wide_bus_en is set for everything excluding SDM845 & + * porch changes cause DisplayPort failure and HDMI tearing. + */ + if (phys_enc->hw_intf->cap->type == INTF_DP && timing->wide_bus_en) { timing->h_back_porch += timing->h_front_porch; timing->h_front_porch = 0; timing->v_back_porch += timing->v_front_porch; timing->v_front_porch = 0; } - timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent); - timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent); - /* * for DP, divide the horizonal parameters by 2 when * widebus is enabled diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 386c4669c831..a48e6db4f156 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -128,6 +128,11 @@ static const struct msm_dp_desc msm_dp_desc_sa8775p[] = { {} }; +static const struct msm_dp_desc msm_dp_desc_sdm845[] = { + { .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0 }, + {} +}; + static const struct msm_dp_desc msm_dp_desc_sc7180[] = { { .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true }, {} @@ -180,7 +185,7 @@ static const struct of_device_id msm_dp_dt_match[] = { { .compatible = "qcom,sc8180x-edp", .data = &msm_dp_desc_sc8180x }, { .compatible = "qcom,sc8280xp-dp", .data = &msm_dp_desc_sc8280xp }, { .compatible = "qcom,sc8280xp-edp", .data = &msm_dp_desc_sc8280xp }, - { .compatible = "qcom,sdm845-dp", .data = &msm_dp_desc_sc7180 }, + { .compatible = "qcom,sdm845-dp", .data = &msm_dp_desc_sdm845 }, { .compatible = "qcom,sm8350-dp", .data = &msm_dp_desc_sc7180 }, { .compatible = "qcom,sm8650-dp", .data = &msm_dp_desc_sm8650 }, { .compatible = "qcom,x1e80100-dp", .data = &msm_dp_desc_x1e80100 }, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c index 9812b4d69197..af2e30f3f842 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c @@ -704,6 +704,13 @@ static int dsi_pll_10nm_init(struct msm_dsi_phy *phy) /* TODO: Remove this when we have proper display handover support */ msm_dsi_phy_pll_save_state(phy); + /* + * Store also proper vco_current_rate, because its value will be used in + * dsi_10nm_pll_restore_state(). + */ + if (!dsi_pll_10nm_vco_recalc_rate(&pll_10nm->clk_hw, VCO_REF_CLK_RATE)) + pll_10nm->vco_current_rate = pll_10nm->phy->cfg->min_pll_rate; + return 0; } diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index 7ab607252d18..6af72162cda4 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -208,6 +208,35 @@ DEFINE_DEBUGFS_ATTRIBUTE(shrink_fops, shrink_get, shrink_set, "0x%08llx\n"); +/* + * Return the number of microseconds to wait until stall-on-fault is + * re-enabled. If 0 then it is already enabled or will be re-enabled on the + * next submit (unless there's a leftover devcoredump). This is useful for + * kernel tests that intentionally produce a fault and check the devcoredump to + * wait until the cooldown period is over. + */ + +static int +stall_reenable_time_get(void *data, u64 *val) +{ + struct msm_drm_private *priv = data; + unsigned long irq_flags; + + spin_lock_irqsave(&priv->fault_stall_lock, irq_flags); + + if (priv->stall_enabled) + *val = 0; + else + *val = max(ktime_us_delta(priv->stall_reenable_time, ktime_get()), 0); + + spin_unlock_irqrestore(&priv->fault_stall_lock, irq_flags); + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(stall_reenable_time_fops, + stall_reenable_time_get, NULL, + "%lld\n"); static int msm_gem_show(struct seq_file *m, void *arg) { @@ -319,6 +348,9 @@ static void msm_debugfs_gpu_init(struct drm_minor *minor) debugfs_create_bool("disable_err_irq", 0600, minor->debugfs_root, &priv->disable_err_irq); + debugfs_create_file("stall_reenable_time_us", 0400, minor->debugfs_root, + priv, &stall_reenable_time_fops); + gpu_devfreq = debugfs_create_dir("devfreq", minor->debugfs_root); debugfs_create_bool("idle_clamp",0600, gpu_devfreq, diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index f316e6776f67..d007687c2446 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -245,6 +245,10 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) drm_gem_lru_init(&priv->lru.willneed, &priv->lru.lock); drm_gem_lru_init(&priv->lru.dontneed, &priv->lru.lock); + /* Initialize stall-on-fault */ + spin_lock_init(&priv->fault_stall_lock); + priv->stall_enabled = true; + /* Teach lockdep about lock ordering wrt. shrinker: */ fs_reclaim_acquire(GFP_KERNEL); might_lock(&priv->lru.lock); @@ -926,7 +930,7 @@ static const struct drm_driver msm_driver = { * is no external component that we need to add since LVDS is within MDP4 * itself. */ -static int add_components_mdp(struct device *master_dev, +static int add_mdp_components(struct device *master_dev, struct component_match **matchptr) { struct device_node *np = master_dev->of_node; @@ -1030,7 +1034,7 @@ static int add_gpu_components(struct device *dev, if (!np) return 0; - if (of_device_is_available(np)) + if (of_device_is_available(np) && adreno_has_gpu(np)) drm_of_component_match_add(dev, matchptr, component_compare_of, np); of_node_put(np); @@ -1071,7 +1075,7 @@ int msm_drv_probe(struct device *master_dev, /* Add mdp components if we have KMS. */ if (kms_init) { - ret = add_components_mdp(master_dev, &match); + ret = add_mdp_components(master_dev, &match); if (ret) return ret; } diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index a65077855201..c8afb1ea6040 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -222,6 +222,29 @@ struct msm_drm_private { * the sw hangcheck mechanism. */ bool disable_err_irq; + + /** + * @fault_stall_lock: + * + * Serialize changes to stall-on-fault state. + */ + spinlock_t fault_stall_lock; + + /** + * @fault_stall_reenable_time: + * + * If stall_enabled is false, when to reenable stall-on-fault. + * Protected by @fault_stall_lock. + */ + ktime_t stall_reenable_time; + + /** + * @stall_enabled: + * + * Whether stall-on-fault is currently enabled. Protected by + * @fault_stall_lock. + */ + bool stall_enabled; }; const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format, uint64_t modifier); diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 3e9aa2cc38ef..d4f71bb54e84 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -85,6 +85,15 @@ void __msm_gem_submit_destroy(struct kref *kref) container_of(kref, struct msm_gem_submit, ref); unsigned i; + /* + * In error paths, we could unref the submit without calling + * drm_sched_entity_push_job(), so msm_job_free() will never + * get called. Since drm_sched_job_cleanup() will NULL out + * s_fence, we can use that to detect this case. + */ + if (submit->base.s_fence) + drm_sched_job_cleanup(&submit->base); + if (submit->fence_id) { spin_lock(&submit->queue->idr_lock); idr_remove(&submit->queue->fence_idr, submit->fence_id); @@ -649,6 +658,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct msm_ringbuffer *ring; struct msm_submit_post_dep *post_deps = NULL; struct drm_syncobj **syncobjs_to_reset = NULL; + struct sync_file *sync_file = NULL; int out_fence_fd = -1; unsigned i; int ret; @@ -858,7 +868,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, } if (ret == 0 && args->flags & MSM_SUBMIT_FENCE_FD_OUT) { - struct sync_file *sync_file = sync_file_create(submit->user_fence); + sync_file = sync_file_create(submit->user_fence); if (!sync_file) { ret = -ENOMEM; } else { @@ -892,8 +902,11 @@ out: out_unlock: mutex_unlock(&queue->lock); out_post_unlock: - if (ret && (out_fence_fd >= 0)) + if (ret && (out_fence_fd >= 0)) { put_unused_fd(out_fence_fd); + if (sync_file) + fput(sync_file->file); + } if (!IS_ERR_OR_NULL(submit)) { msm_gem_submit_put(submit); diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 197871fdf508..3947f7ba1421 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -257,7 +257,8 @@ out: } static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, - struct msm_gem_submit *submit, char *comm, char *cmd) + struct msm_gem_submit *submit, struct msm_gpu_fault_info *fault_info, + char *comm, char *cmd) { struct msm_gpu_state *state; @@ -276,7 +277,8 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, /* Fill in the additional crash state information */ state->comm = kstrdup(comm, GFP_KERNEL); state->cmd = kstrdup(cmd, GFP_KERNEL); - state->fault_info = gpu->fault_info; + if (fault_info) + state->fault_info = *fault_info; if (submit) { int i; @@ -308,7 +310,8 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, } #else static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, - struct msm_gem_submit *submit, char *comm, char *cmd) + struct msm_gem_submit *submit, struct msm_gpu_fault_info *fault_info, + char *comm, char *cmd) { } #endif @@ -405,7 +408,7 @@ static void recover_worker(struct kthread_work *work) /* Record the crash state */ pm_runtime_get_sync(&gpu->pdev->dev); - msm_gpu_crashstate_capture(gpu, submit, comm, cmd); + msm_gpu_crashstate_capture(gpu, submit, NULL, comm, cmd); kfree(cmd); kfree(comm); @@ -459,9 +462,8 @@ out_unlock: msm_gpu_retire(gpu); } -static void fault_worker(struct kthread_work *work) +void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info) { - struct msm_gpu *gpu = container_of(work, struct msm_gpu, fault_work); struct msm_gem_submit *submit; struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu); char *comm = NULL, *cmd = NULL; @@ -484,16 +486,13 @@ static void fault_worker(struct kthread_work *work) /* Record the crash state */ pm_runtime_get_sync(&gpu->pdev->dev); - msm_gpu_crashstate_capture(gpu, submit, comm, cmd); + msm_gpu_crashstate_capture(gpu, submit, fault_info, comm, cmd); pm_runtime_put_sync(&gpu->pdev->dev); kfree(cmd); kfree(comm); resume_smmu: - memset(&gpu->fault_info, 0, sizeof(gpu->fault_info)); - gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu); - mutex_unlock(&gpu->lock); } @@ -882,7 +881,6 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, init_waitqueue_head(&gpu->retire_event); kthread_init_work(&gpu->retire_work, retire_worker); kthread_init_work(&gpu->recover_work, recover_worker); - kthread_init_work(&gpu->fault_work, fault_worker); priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD; diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index e25009150579..5bf7cd985b9c 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -253,12 +253,6 @@ struct msm_gpu { #define DRM_MSM_HANGCHECK_PROGRESS_RETRIES 3 struct timer_list hangcheck_timer; - /* Fault info for most recent iova fault: */ - struct msm_gpu_fault_info fault_info; - - /* work for handling GPU ioval faults: */ - struct kthread_work fault_work; - /* work for handling GPU recovery: */ struct kthread_work recover_work; @@ -668,6 +662,7 @@ msm_gpu_create_private_address_space(struct msm_gpu *gpu, struct task_struct *ta void msm_gpu_cleanup(struct msm_gpu *gpu); struct msm_gpu *adreno_load_gpu(struct drm_device *dev); +bool adreno_has_gpu(struct device_node *node); void __init adreno_register(void); void __exit adreno_unregister(void); @@ -705,6 +700,8 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu) mutex_unlock(&gpu->lock); } +void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info); + /* * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can * support expanded privileges diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index fd73dcd3f30e..739ce2c283a4 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -345,7 +345,6 @@ static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev unsigned long iova, int flags, void *arg) { struct msm_iommu *iommu = arg; - struct msm_mmu *mmu = &iommu->base; struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(iommu->base.dev); struct adreno_smmu_fault_info info, *ptr = NULL; @@ -359,9 +358,6 @@ static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev pr_warn_ratelimited("*** fault: iova=%16lx, flags=%d\n", iova, flags); - if (mmu->funcs->resume_translation) - mmu->funcs->resume_translation(mmu); - return 0; } @@ -376,12 +372,12 @@ static int msm_disp_fault_handler(struct iommu_domain *domain, struct device *de return -ENOSYS; } -static void msm_iommu_resume_translation(struct msm_mmu *mmu) +static void msm_iommu_set_stall(struct msm_mmu *mmu, bool enable) { struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(mmu->dev); - if (adreno_smmu->resume_translation) - adreno_smmu->resume_translation(adreno_smmu->cookie, true); + if (adreno_smmu->set_stall) + adreno_smmu->set_stall(adreno_smmu->cookie, enable); } static void msm_iommu_detach(struct msm_mmu *mmu) @@ -431,7 +427,7 @@ static const struct msm_mmu_funcs funcs = { .map = msm_iommu_map, .unmap = msm_iommu_unmap, .destroy = msm_iommu_destroy, - .resume_translation = msm_iommu_resume_translation, + .set_stall = msm_iommu_set_stall, }; struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h index daf91529e02b..0c694907140d 100644 --- a/drivers/gpu/drm/msm/msm_mmu.h +++ b/drivers/gpu/drm/msm/msm_mmu.h @@ -15,7 +15,7 @@ struct msm_mmu_funcs { size_t len, int prot); int (*unmap)(struct msm_mmu *mmu, uint64_t iova, size_t len); void (*destroy)(struct msm_mmu *mmu); - void (*resume_translation)(struct msm_mmu *mmu); + void (*set_stall)(struct msm_mmu *mmu, bool enable); }; enum msm_mmu_type { diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml index 5a6ae9fc3194..462713401622 100644 --- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml +++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml @@ -2255,7 +2255,8 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <reg32 offset="0" name="0"> <bitfield name="CLEAR_ON_CHIP_TS" pos="0" type="boolean"/> <bitfield name="CLEAR_RESOURCE_TABLE" pos="1" type="boolean"/> - <bitfield name="CLEAR_GLOBAL_LOCAL_TS" pos="2" type="boolean"/> + <bitfield name="CLEAR_BV_BR_COUNTER" pos="2" type="boolean"/> + <bitfield name="RESET_GLOBAL_LOCAL_TS" pos="3" type="boolean"/> </reg32> </domain> diff --git a/drivers/gpu/drm/msm/registers/gen_header.py b/drivers/gpu/drm/msm/registers/gen_header.py index 3926485bb197..a409404627c7 100644 --- a/drivers/gpu/drm/msm/registers/gen_header.py +++ b/drivers/gpu/drm/msm/registers/gen_header.py @@ -11,6 +11,7 @@ import collections import argparse import time import datetime +import re class Error(Exception): def __init__(self, message): @@ -877,13 +878,14 @@ The rules-ng-ng source files this header was generated from are: """) maxlen = 0 for filepath in p.xml_files: - maxlen = max(maxlen, len(filepath)) + new_filepath = re.sub("^.+drivers","drivers",filepath) + maxlen = max(maxlen, len(new_filepath)) for filepath in p.xml_files: - pad = " " * (maxlen - len(filepath)) + pad = " " * (maxlen - len(new_filepath)) filesize = str(os.path.getsize(filepath)) filesize = " " * (7 - len(filesize)) + filesize filetime = time.ctime(os.path.getmtime(filepath)) - print("- " + filepath + pad + " (" + filesize + " bytes, from " + filetime + ")") + print("- " + new_filepath + pad + " (" + filesize + " bytes, from <stripped>)") if p.copyright_year: current_year = str(datetime.date.today().year) print() diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c index d47442125fa1..9aae26eb7d8f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_backlight.c +++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c @@ -42,7 +42,7 @@ #include "nouveau_acpi.h" static struct ida bl_ida; -#define BL_NAME_SIZE 15 // 12 for name + 2 for digits + 1 for '\0' +#define BL_NAME_SIZE 24 // 12 for name + 11 for digits + 1 for '\0' static bool nouveau_get_backlight_name(char backlight_name[BL_NAME_SIZE], diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c index 5acb98d137bd..9d06ff722fea 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c @@ -637,12 +637,18 @@ r535_gsp_rpc_push(struct nvkm_gsp *gsp, void *payload, if (payload_size > max_payload_size) { const u32 fn = rpc->function; u32 remain_payload_size = payload_size; + void *next; - /* Adjust length, and send initial RPC. */ - rpc->length = sizeof(*rpc) + max_payload_size; - msg->checksum = rpc->length; + /* Send initial RPC. */ + next = r535_gsp_rpc_get(gsp, fn, max_payload_size); + if (IS_ERR(next)) { + repv = next; + goto done; + } - repv = r535_gsp_rpc_send(gsp, payload, NVKM_GSP_RPC_REPLY_NOWAIT, 0); + memcpy(next, payload, max_payload_size); + + repv = r535_gsp_rpc_send(gsp, next, NVKM_GSP_RPC_REPLY_NOWAIT, 0); if (IS_ERR(repv)) goto done; @@ -653,7 +659,6 @@ r535_gsp_rpc_push(struct nvkm_gsp *gsp, void *payload, while (remain_payload_size) { u32 size = min(remain_payload_size, max_payload_size); - void *next; next = r535_gsp_rpc_get(gsp, NV_VGPU_MSG_FUNCTION_CONTINUATION_RECORD, size); if (IS_ERR(next)) { @@ -674,6 +679,8 @@ r535_gsp_rpc_push(struct nvkm_gsp *gsp, void *payload, /* Wait for reply. */ repv = r535_gsp_rpc_handle_reply(gsp, fn, policy, payload_size + sizeof(*rpc)); + if (!IS_ERR(repv)) + kvfree(msg); } else { repv = r535_gsp_rpc_send(gsp, payload, policy, gsp_rpc_len); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c index 52f2e5f14517..f25ea610cd99 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c @@ -121,7 +121,7 @@ r535_mmu_vaspace_new(struct nvkm_vmm *vmm, u32 handle, bool external) page_shift -= desc->bits; ctrl->levels[i].physAddress = pd->pt[0]->addr; - ctrl->levels[i].size = (1 << desc->bits) * desc->size; + ctrl->levels[i].size = BIT_ULL(desc->bits) * desc->size; ctrl->levels[i].aperture = 1; ctrl->levels[i].pageShift = page_shift; diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 0a3b26bb4d73..9f81fa960b46 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -26,6 +26,7 @@ #include <linux/i2c.h> #include <linux/media-bus-format.h> #include <linux/module.h> +#include <linux/of_device.h> #include <linux/of_platform.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> @@ -136,6 +137,14 @@ struct panel_desc { int connector_type; }; +struct panel_desc_dsi { + struct panel_desc desc; + + unsigned long flags; + enum mipi_dsi_pixel_format format; + unsigned int lanes; +}; + struct panel_simple { struct drm_panel base; @@ -430,10 +439,7 @@ static const struct drm_panel_funcs panel_simple_funcs = { .get_timings = panel_simple_get_timings, }; -static struct panel_desc panel_dpi; - -static int panel_dpi_probe(struct device *dev, - struct panel_simple *panel) +static struct panel_desc *panel_dpi_probe(struct device *dev) { struct display_timing *timing; const struct device_node *np; @@ -445,17 +451,17 @@ static int panel_dpi_probe(struct device *dev, np = dev->of_node; desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL); if (!desc) - return -ENOMEM; + return ERR_PTR(-ENOMEM); timing = devm_kzalloc(dev, sizeof(*timing), GFP_KERNEL); if (!timing) - return -ENOMEM; + return ERR_PTR(-ENOMEM); ret = of_get_display_timing(np, "panel-timing", timing); if (ret < 0) { dev_err(dev, "%pOF: no panel-timing node found for \"panel-dpi\" binding\n", np); - return ret; + return ERR_PTR(ret); } desc->timings = timing; @@ -473,9 +479,7 @@ static int panel_dpi_probe(struct device *dev, /* We do not know the connector for the DT node, so guess it */ desc->connector_type = DRM_MODE_CONNECTOR_DPI; - panel->desc = desc; - - return 0; + return desc; } #define PANEL_SIMPLE_BOUNDS_CHECK(to_check, bounds, field) \ @@ -570,8 +574,44 @@ static int panel_simple_override_nondefault_lvds_datamapping(struct device *dev, return 0; } -static int panel_simple_probe(struct device *dev, const struct panel_desc *desc) +static const struct panel_desc *panel_simple_get_desc(struct device *dev) { + if (IS_ENABLED(CONFIG_DRM_MIPI_DSI) && + dev_is_mipi_dsi(dev)) { + const struct panel_desc_dsi *dsi_desc; + + dsi_desc = of_device_get_match_data(dev); + if (!dsi_desc) + return ERR_PTR(-ENODEV); + + return &dsi_desc->desc; + } + + if (dev_is_platform(dev)) { + const struct panel_desc *desc; + + desc = of_device_get_match_data(dev); + if (!desc) { + /* + * panel-dpi probes without a descriptor and + * panel_dpi_probe() will initialize one for us + * based on the device tree. + */ + if (of_device_is_compatible(dev->of_node, "panel-dpi")) + return panel_dpi_probe(dev); + else + return ERR_PTR(-ENODEV); + } + + return desc; + } + + return ERR_PTR(-ENODEV); +} + +static struct panel_simple *panel_simple_probe(struct device *dev) +{ + const struct panel_desc *desc; struct panel_simple *panel; struct display_timing dt; struct device_node *ddc; @@ -579,27 +619,31 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc) u32 bus_flags; int err; + desc = panel_simple_get_desc(dev); + if (IS_ERR(desc)) + return ERR_CAST(desc); + panel = devm_drm_panel_alloc(dev, struct panel_simple, base, &panel_simple_funcs, desc->connector_type); if (IS_ERR(panel)) - return PTR_ERR(panel); + return ERR_CAST(panel); panel->desc = desc; panel->supply = devm_regulator_get(dev, "power"); if (IS_ERR(panel->supply)) - return PTR_ERR(panel->supply); + return ERR_CAST(panel->supply); panel->enable_gpio = devm_gpiod_get_optional(dev, "enable", GPIOD_OUT_LOW); if (IS_ERR(panel->enable_gpio)) - return dev_err_probe(dev, PTR_ERR(panel->enable_gpio), - "failed to request GPIO\n"); + return dev_err_cast_probe(dev, panel->enable_gpio, + "failed to request GPIO\n"); err = of_drm_get_panel_orientation(dev->of_node, &panel->orientation); if (err) { dev_err(dev, "%pOF: failed to get orientation %d\n", dev->of_node, err); - return err; + return ERR_PTR(err); } ddc = of_parse_phandle(dev->of_node, "ddc-i2c-bus", 0); @@ -608,19 +652,12 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc) of_node_put(ddc); if (!panel->ddc) - return -EPROBE_DEFER; + return ERR_PTR(-EPROBE_DEFER); } - if (desc == &panel_dpi) { - /* Handle the generic panel-dpi binding */ - err = panel_dpi_probe(dev, panel); - if (err) - goto free_ddc; - desc = panel->desc; - } else { - if (!of_get_display_timing(dev->of_node, "panel-timing", &dt)) - panel_simple_parse_panel_timing_node(dev, panel, &dt); - } + if (!of_device_is_compatible(dev->of_node, "panel-dpi") && + !of_get_display_timing(dev->of_node, "panel-timing", &dt)) + panel_simple_parse_panel_timing_node(dev, panel, &dt); if (desc->connector_type == DRM_MODE_CONNECTOR_LVDS) { /* Optional data-mapping property for overriding bus format */ @@ -703,7 +740,7 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc) drm_panel_add(&panel->base); - return 0; + return panel; disable_pm_runtime: pm_runtime_dont_use_autosuspend(dev); @@ -712,7 +749,7 @@ free_ddc: if (panel->ddc) put_device(&panel->ddc->dev); - return err; + return ERR_PTR(err); } static void panel_simple_shutdown(struct device *dev) @@ -5367,7 +5404,12 @@ static const struct of_device_id platform_of_match[] = { }, { /* Must be the last entry */ .compatible = "panel-dpi", - .data = &panel_dpi, + + /* + * Explicitly NULL, the panel_desc structure will be + * allocated by panel_dpi_probe(). + */ + .data = NULL, }, { /* sentinel */ } @@ -5376,13 +5418,13 @@ MODULE_DEVICE_TABLE(of, platform_of_match); static int panel_simple_platform_probe(struct platform_device *pdev) { - const struct panel_desc *desc; + struct panel_simple *panel; - desc = of_device_get_match_data(&pdev->dev); - if (!desc) - return -ENODEV; + panel = panel_simple_probe(&pdev->dev); + if (IS_ERR(panel)) + return PTR_ERR(panel); - return panel_simple_probe(&pdev->dev, desc); + return 0; } static void panel_simple_platform_remove(struct platform_device *pdev) @@ -5412,14 +5454,6 @@ static struct platform_driver panel_simple_platform_driver = { .shutdown = panel_simple_platform_shutdown, }; -struct panel_desc_dsi { - struct panel_desc desc; - - unsigned long flags; - enum mipi_dsi_pixel_format format; - unsigned int lanes; -}; - static const struct drm_display_mode auo_b080uan01_mode = { .clock = 154500, .hdisplay = 1200, @@ -5653,16 +5687,14 @@ MODULE_DEVICE_TABLE(of, dsi_of_match); static int panel_simple_dsi_probe(struct mipi_dsi_device *dsi) { const struct panel_desc_dsi *desc; + struct panel_simple *panel; int err; - desc = of_device_get_match_data(&dsi->dev); - if (!desc) - return -ENODEV; - - err = panel_simple_probe(&dsi->dev, &desc->desc); - if (err < 0) - return err; + panel = panel_simple_probe(&dsi->dev); + if (IS_ERR(panel)) + return PTR_ERR(panel); + desc = container_of(panel->desc, struct panel_desc_dsi, desc); dsi->mode_flags = desc->flags; dsi->format = desc->format; dsi->lanes = desc->lanes; diff --git a/drivers/gpu/drm/sitronix/Kconfig b/drivers/gpu/drm/sitronix/Kconfig index c069d0d41775..741d1bb4b83f 100644 --- a/drivers/gpu/drm/sitronix/Kconfig +++ b/drivers/gpu/drm/sitronix/Kconfig @@ -5,6 +5,7 @@ config DRM_ST7571_I2C select DRM_GEM_SHMEM_HELPER select DRM_KMS_HELPER select REGMAP_I2C + select VIDEOMODE_HELPERS help DRM driver for Sitronix ST7571 panels controlled over I2C. diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c index dd2006d51c7a..eec43d1a5595 100644 --- a/drivers/gpu/drm/solomon/ssd130x.c +++ b/drivers/gpu/drm/solomon/ssd130x.c @@ -974,7 +974,7 @@ static void ssd130x_clear_screen(struct ssd130x_device *ssd130x, u8 *data_array) static void ssd132x_clear_screen(struct ssd130x_device *ssd130x, u8 *data_array) { - unsigned int columns = DIV_ROUND_UP(ssd130x->height, SSD132X_SEGMENT_WIDTH); + unsigned int columns = DIV_ROUND_UP(ssd130x->width, SSD132X_SEGMENT_WIDTH); unsigned int height = ssd130x->height; memset(data_array, 0, columns * height); diff --git a/drivers/gpu/drm/sysfb/vesadrm.c b/drivers/gpu/drm/sysfb/vesadrm.c index 4d62c78e7d1e..f7532db3831f 100644 --- a/drivers/gpu/drm/sysfb/vesadrm.c +++ b/drivers/gpu/drm/sysfb/vesadrm.c @@ -362,14 +362,19 @@ static struct vesadrm_device *vesadrm_device_create(struct drm_driver *drv, if (!__screen_info_vbe_mode_nonvga(si)) { vesa->cmap_write = vesadrm_vga_cmap_write; -#if defined(CONFIG_X86_32) } else { +#if defined(CONFIG_X86_32) phys_addr_t pmi_base = __screen_info_vesapm_info_base(si); - const u16 *pmi_addr = phys_to_virt(pmi_base); - vesa->pmi.PrimaryPalette = (u8 *)pmi_addr + pmi_addr[2]; - vesa->cmap_write = vesadrm_pmi_cmap_write; + if (pmi_base) { + const u16 *pmi_addr = phys_to_virt(pmi_base); + + vesa->pmi.PrimaryPalette = (u8 *)pmi_addr + pmi_addr[2]; + vesa->cmap_write = vesadrm_pmi_cmap_write; + } else #endif + if (format->is_color_indexed) + drm_warn(dev, "hardware palette is unchangeable, colors may be incorrect\n"); } #ifdef CONFIG_X86 diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 15cab9bda17f..bd90404ea609 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -254,6 +254,13 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, ret = dma_resv_trylock(&fbo->base.base._resv); WARN_ON(!ret); + ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1); + if (ret) { + dma_resv_unlock(&fbo->base.base._resv); + kfree(fbo); + return ret; + } + if (fbo->base.resource) { ttm_resource_set_bo(fbo->base.resource, &fbo->base); bo->resource = NULL; @@ -262,12 +269,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, fbo->base.bulk_move = NULL; } - ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1); - if (ret) { - kfree(fbo); - return ret; - } - ttm_bo_get(bo); fbo->bo = bo; diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index b51f0b648a08..411e47702f8a 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -101,6 +101,12 @@ enum v3d_gen { V3D_GEN_71 = 71, }; +enum v3d_irq { + V3D_CORE_IRQ, + V3D_HUB_IRQ, + V3D_MAX_IRQS, +}; + struct v3d_dev { struct drm_device drm; @@ -112,6 +118,8 @@ struct v3d_dev { bool single_irq_line; + int irq[V3D_MAX_IRQS]; + struct v3d_perfmon_info perfmon_info; void __iomem *hub_regs; diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index d7d16da78db3..37bf5eecdd2c 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -134,6 +134,8 @@ v3d_reset(struct v3d_dev *v3d) if (false) v3d_idle_axi(v3d, 0); + v3d_irq_disable(v3d); + v3d_idle_gca(v3d); v3d_reset_sms(v3d); v3d_reset_v3d(v3d); diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c index 2cca5d3a26a2..a515a301e480 100644 --- a/drivers/gpu/drm/v3d/v3d_irq.c +++ b/drivers/gpu/drm/v3d/v3d_irq.c @@ -260,7 +260,7 @@ v3d_hub_irq(int irq, void *arg) int v3d_irq_init(struct v3d_dev *v3d) { - int irq1, ret, core; + int irq, ret, core; INIT_WORK(&v3d->overflow_mem_work, v3d_overflow_mem_work); @@ -271,17 +271,24 @@ v3d_irq_init(struct v3d_dev *v3d) V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS(v3d->ver)); V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS(v3d->ver)); - irq1 = platform_get_irq_optional(v3d_to_pdev(v3d), 1); - if (irq1 == -EPROBE_DEFER) - return irq1; - if (irq1 > 0) { - ret = devm_request_irq(v3d->drm.dev, irq1, + irq = platform_get_irq_optional(v3d_to_pdev(v3d), 1); + if (irq == -EPROBE_DEFER) + return irq; + if (irq > 0) { + v3d->irq[V3D_CORE_IRQ] = irq; + + ret = devm_request_irq(v3d->drm.dev, v3d->irq[V3D_CORE_IRQ], v3d_irq, IRQF_SHARED, "v3d_core0", v3d); if (ret) goto fail; - ret = devm_request_irq(v3d->drm.dev, - platform_get_irq(v3d_to_pdev(v3d), 0), + + irq = platform_get_irq(v3d_to_pdev(v3d), 0); + if (irq < 0) + return irq; + v3d->irq[V3D_HUB_IRQ] = irq; + + ret = devm_request_irq(v3d->drm.dev, v3d->irq[V3D_HUB_IRQ], v3d_hub_irq, IRQF_SHARED, "v3d_hub", v3d); if (ret) @@ -289,8 +296,12 @@ v3d_irq_init(struct v3d_dev *v3d) } else { v3d->single_irq_line = true; - ret = devm_request_irq(v3d->drm.dev, - platform_get_irq(v3d_to_pdev(v3d), 0), + irq = platform_get_irq(v3d_to_pdev(v3d), 0); + if (irq < 0) + return irq; + v3d->irq[V3D_CORE_IRQ] = irq; + + ret = devm_request_irq(v3d->drm.dev, v3d->irq[V3D_CORE_IRQ], v3d_irq, IRQF_SHARED, "v3d", v3d); if (ret) @@ -331,6 +342,12 @@ v3d_irq_disable(struct v3d_dev *v3d) V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_SET, ~0); V3D_WRITE(V3D_HUB_INT_MSK_SET, ~0); + /* Finish any interrupt handler still in flight. */ + for (int i = 0; i < V3D_MAX_IRQS; i++) { + if (v3d->irq[i]) + synchronize_irq(v3d->irq[i]); + } + /* Clear any pending interrupts we might have left. */ for (core = 0; core < v3d->cores; core++) V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS(v3d->ver)); diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 35f131a46d07..42df9d3567e7 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -199,7 +199,6 @@ v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue) struct v3d_dev *v3d = job->v3d; struct v3d_file_priv *file = job->file->driver_priv; struct v3d_stats *global_stats = &v3d->queue[queue].stats; - struct v3d_stats *local_stats = &file->stats[queue]; u64 now = local_clock(); unsigned long flags; @@ -209,7 +208,12 @@ v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue) else preempt_disable(); - v3d_stats_update(local_stats, now); + /* Don't update the local stats if the file context has already closed */ + if (file) + v3d_stats_update(&file->stats[queue], now); + else + drm_dbg(&v3d->drm, "The file descriptor was closed before job completion\n"); + v3d_stats_update(global_stats, now); if (IS_ENABLED(CONFIG_LOCKDEP)) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index a29a6ef266f9..163d092bd973 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -560,12 +560,6 @@ static int vc4_hdmi_connector_init(struct drm_device *dev, if (ret) return ret; - ret = drm_connector_hdmi_audio_init(connector, dev->dev, - &vc4_hdmi_audio_funcs, - 8, false, -1); - if (ret) - return ret; - drm_connector_helper_add(connector, &vc4_hdmi_connector_helper_funcs); /* @@ -2291,6 +2285,12 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) return ret; } + ret = drm_connector_hdmi_audio_init(&vc4_hdmi->connector, dev, + &vc4_hdmi_audio_funcs, 8, false, + -1); + if (ret) + return ret; + dai_link->cpus = &vc4_hdmi->audio.cpu; dai_link->codecs = &vc4_hdmi->audio.codec; dai_link->platforms = &vc4_hdmi->audio.platform; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 0695a342b1ef..5205552b1970 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -749,7 +749,7 @@ static int vmw_setup_pci_resources(struct vmw_private *dev, dev->fifo_mem = devm_memremap(dev->drm.dev, fifo_start, fifo_size, - MEMREMAP_WB); + MEMREMAP_WB | MEMREMAP_DEC); if (IS_ERR(dev->fifo_mem)) { drm_err(&dev->drm, diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig index fcc2677a4229..99a91355842e 100644 --- a/drivers/gpu/drm/xe/Kconfig +++ b/drivers/gpu/drm/xe/Kconfig @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only config DRM_XE - tristate "Intel Xe Graphics" - depends on DRM && PCI && (m || (y && KUNIT=y)) + tristate "Intel Xe2 Graphics" + depends on DRM && PCI + depends on KUNIT || !KUNIT depends on INTEL_VSEC || !INTEL_VSEC depends on X86_PLATFORM_DEVICES || !(X86 && ACPI) select INTERVAL_TREE @@ -46,7 +47,8 @@ config DRM_XE select AUXILIARY_BUS select HMM_MIRROR help - Experimental driver for Intel Xe series GPUs + Driver for Intel Xe2 series GPUs and later. Experimental support + for Xe series is also available. If "M" is selected, the module will be called xe. diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c index 68f064f33d4b..9f4ade25787a 100644 --- a/drivers/gpu/drm/xe/display/xe_display.c +++ b/drivers/gpu/drm/xe/display/xe_display.c @@ -104,6 +104,8 @@ int xe_display_create(struct xe_device *xe) spin_lock_init(&xe->display.fb_tracking.lock); xe->display.hotplug.dp_wq = alloc_ordered_workqueue("xe-dp", 0); + if (!xe->display.hotplug.dp_wq) + return -ENOMEM; return drmm_add_action_or_reset(&xe->drm, display_destroy, NULL); } diff --git a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c index f95375451e2f..9f941fc2e36b 100644 --- a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c +++ b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c @@ -17,10 +17,7 @@ u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf) void intel_dsb_buffer_write(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val) { - struct xe_device *xe = dsb_buf->vma->bo->tile->xe; - iosys_map_wr(&dsb_buf->vma->bo->vmap, idx * 4, u32, val); - xe_device_l2_flush(xe); } u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx) @@ -30,12 +27,9 @@ u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx) void intel_dsb_buffer_memset(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val, size_t size) { - struct xe_device *xe = dsb_buf->vma->bo->tile->xe; - WARN_ON(idx > (dsb_buf->buf_size - size) / sizeof(*dsb_buf->cmd_buf)); iosys_map_memset(&dsb_buf->vma->bo->vmap, idx * 4, val, size); - xe_device_l2_flush(xe); } bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *dsb_buf, size_t size) @@ -74,9 +68,12 @@ void intel_dsb_buffer_cleanup(struct intel_dsb_buffer *dsb_buf) void intel_dsb_buffer_flush_map(struct intel_dsb_buffer *dsb_buf) { + struct xe_device *xe = dsb_buf->vma->bo->tile->xe; + /* * The memory barrier here is to ensure coherency of DSB vs MMIO, * both for weak ordering archs and discrete cards. */ - xe_device_wmb(dsb_buf->vma->bo->tile->xe); + xe_device_wmb(xe); + xe_device_l2_flush(xe); } diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c index d918ae1c8061..55259969480b 100644 --- a/drivers/gpu/drm/xe/display/xe_fb_pin.c +++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c @@ -164,6 +164,9 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb, vma->dpt = dpt; vma->node = dpt->ggtt_node[tile0->id]; + + /* Ensure DPT writes are flushed */ + xe_device_l2_flush(xe); return 0; } @@ -333,8 +336,6 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb, if (ret) goto err_unpin; - /* Ensure DPT writes are flushed */ - xe_device_l2_flush(xe); return vma; err_unpin: diff --git a/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h b/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h index 5394a1373a6b..ef2bf984723f 100644 --- a/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h @@ -40,6 +40,7 @@ #define PCU_CR_PACKAGE_RAPL_LIMIT XE_REG(MCHBAR_MIRROR_BASE_SNB + 0x59a0) #define PWR_LIM_VAL REG_GENMASK(14, 0) #define PWR_LIM_EN REG_BIT(15) +#define PWR_LIM REG_GENMASK(15, 0) #define PWR_LIM_TIME REG_GENMASK(23, 17) #define PWR_LIM_TIME_X REG_GENMASK(23, 22) #define PWR_LIM_TIME_Y REG_GENMASK(21, 17) diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index c02c4c4e9412..e9f3c1a53db2 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -40,6 +40,7 @@ #include "xe_gt_printk.h" #include "xe_gt_sriov_vf.h" #include "xe_guc.h" +#include "xe_guc_pc.h" #include "xe_hw_engine_group.h" #include "xe_hwmon.h" #include "xe_irq.h" @@ -986,38 +987,15 @@ void xe_device_wmb(struct xe_device *xe) xe_mmio_write32(xe_root_tile_mmio(xe), VF_CAP_REG, 0); } -/** - * xe_device_td_flush() - Flush transient L3 cache entries - * @xe: The device - * - * Display engine has direct access to memory and is never coherent with L3/L4 - * caches (or CPU caches), however KMD is responsible for specifically flushing - * transient L3 GPU cache entries prior to the flip sequence to ensure scanout - * can happen from such a surface without seeing corruption. - * - * Display surfaces can be tagged as transient by mapping it using one of the - * various L3:XD PAT index modes on Xe2. - * - * Note: On non-discrete xe2 platforms, like LNL, the entire L3 cache is flushed - * at the end of each submission via PIPE_CONTROL for compute/render, since SA - * Media is not coherent with L3 and we want to support render-vs-media - * usescases. For other engines like copy/blt the HW internally forces uncached - * behaviour, hence why we can skip the TDF on such platforms. +/* + * Issue a TRANSIENT_FLUSH_REQUEST and wait for completion on each gt. */ -void xe_device_td_flush(struct xe_device *xe) +static void tdf_request_sync(struct xe_device *xe) { - struct xe_gt *gt; unsigned int fw_ref; + struct xe_gt *gt; u8 id; - if (!IS_DGFX(xe) || GRAPHICS_VER(xe) < 20) - return; - - if (XE_WA(xe_root_mmio_gt(xe), 16023588340)) { - xe_device_l2_flush(xe); - return; - } - for_each_gt(gt, xe, id) { if (xe_gt_is_media_type(gt)) continue; @@ -1027,6 +1005,7 @@ void xe_device_td_flush(struct xe_device *xe) return; xe_mmio_write32(>->mmio, XE2_TDF_CTRL, TRANSIENT_FLUSH_REQUEST); + /* * FIXME: We can likely do better here with our choice of * timeout. Currently we just assume the worst case, i.e. 150us, @@ -1057,15 +1036,52 @@ void xe_device_l2_flush(struct xe_device *xe) return; spin_lock(>->global_invl_lock); - xe_mmio_write32(>->mmio, XE2_GLOBAL_INVAL, 0x1); + xe_mmio_write32(>->mmio, XE2_GLOBAL_INVAL, 0x1); if (xe_mmio_wait32(>->mmio, XE2_GLOBAL_INVAL, 0x1, 0x0, 500, NULL, true)) xe_gt_err_once(gt, "Global invalidation timeout\n"); + spin_unlock(>->global_invl_lock); xe_force_wake_put(gt_to_fw(gt), fw_ref); } +/** + * xe_device_td_flush() - Flush transient L3 cache entries + * @xe: The device + * + * Display engine has direct access to memory and is never coherent with L3/L4 + * caches (or CPU caches), however KMD is responsible for specifically flushing + * transient L3 GPU cache entries prior to the flip sequence to ensure scanout + * can happen from such a surface without seeing corruption. + * + * Display surfaces can be tagged as transient by mapping it using one of the + * various L3:XD PAT index modes on Xe2. + * + * Note: On non-discrete xe2 platforms, like LNL, the entire L3 cache is flushed + * at the end of each submission via PIPE_CONTROL for compute/render, since SA + * Media is not coherent with L3 and we want to support render-vs-media + * usescases. For other engines like copy/blt the HW internally forces uncached + * behaviour, hence why we can skip the TDF on such platforms. + */ +void xe_device_td_flush(struct xe_device *xe) +{ + struct xe_gt *root_gt; + + if (!IS_DGFX(xe) || GRAPHICS_VER(xe) < 20) + return; + + root_gt = xe_root_mmio_gt(xe); + if (XE_WA(root_gt, 16023588340)) { + /* A transient flush is not sufficient: flush the L2 */ + xe_device_l2_flush(xe); + } else { + xe_guc_pc_apply_flush_freq_limit(&root_gt->uc.guc.pc); + tdf_request_sync(xe); + xe_guc_pc_remove_flush_freq_limit(&root_gt->uc.guc.pc); + } +} + u32 xe_device_ccs_bytes(struct xe_device *xe, u64 size) { return xe_device_has_flat_ccs(xe) ? diff --git a/drivers/gpu/drm/xe/xe_drv.h b/drivers/gpu/drm/xe/xe_drv.h index d61650d4aa0b..95242a375e54 100644 --- a/drivers/gpu/drm/xe/xe_drv.h +++ b/drivers/gpu/drm/xe/xe_drv.h @@ -9,7 +9,7 @@ #include <drm/drm_drv.h> #define DRIVER_NAME "xe" -#define DRIVER_DESC "Intel Xe Graphics" +#define DRIVER_DESC "Intel Xe2 Graphics" /* Interface history: * diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c index 7062115909f2..2c799958c1e4 100644 --- a/drivers/gpu/drm/xe/xe_ggtt.c +++ b/drivers/gpu/drm/xe/xe_ggtt.c @@ -201,6 +201,13 @@ static const struct xe_ggtt_pt_ops xelpg_pt_wa_ops = { .ggtt_set_pte = xe_ggtt_set_pte_and_flush, }; +static void dev_fini_ggtt(void *arg) +{ + struct xe_ggtt *ggtt = arg; + + drain_workqueue(ggtt->wq); +} + /** * xe_ggtt_init_early - Early GGTT initialization * @ggtt: the &xe_ggtt to be initialized @@ -257,6 +264,10 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt) if (err) return err; + err = devm_add_action_or_reset(xe->drm.dev, dev_fini_ggtt, ggtt); + if (err) + return err; + if (IS_SRIOV_VF(xe)) { err = xe_gt_sriov_vf_prepare_ggtt(xe_tile_get_gt(ggtt->tile, 0)); if (err) diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 0e5d243c9451..6c4cb9576fb6 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -118,7 +118,7 @@ static void xe_gt_enable_host_l2_vram(struct xe_gt *gt) xe_gt_mcr_multicast_write(gt, XE2_GAMREQSTRM_CTRL, reg); } - xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0x3); + xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0xF); xe_force_wake_put(gt_to_fw(gt), fw_ref); } diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index 084cbdeba8ea..e1362e608146 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -138,6 +138,14 @@ void xe_gt_tlb_invalidation_reset(struct xe_gt *gt) int pending_seqno; /* + * we can get here before the CTs are even initialized if we're wedging + * very early, in which case there are not going to be any pending + * fences so we can bail immediately. + */ + if (!xe_guc_ct_initialized(>->uc.guc.ct)) + return; + + /* * CT channel is already disabled at this point. No new TLB requests can * appear. */ diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index 2447de0ebedf..bbcbb348256f 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -34,6 +34,11 @@ #include "xe_pm.h" #include "xe_trace_guc.h" +static void receive_g2h(struct xe_guc_ct *ct); +static void g2h_worker_func(struct work_struct *w); +static void safe_mode_worker_func(struct work_struct *w); +static void ct_exit_safe_mode(struct xe_guc_ct *ct); + #if IS_ENABLED(CONFIG_DRM_XE_DEBUG) enum { /* Internal states, not error conditions */ @@ -186,14 +191,11 @@ static void guc_ct_fini(struct drm_device *drm, void *arg) { struct xe_guc_ct *ct = arg; + ct_exit_safe_mode(ct); destroy_workqueue(ct->g2h_wq); xa_destroy(&ct->fence_lookup); } -static void receive_g2h(struct xe_guc_ct *ct); -static void g2h_worker_func(struct work_struct *w); -static void safe_mode_worker_func(struct work_struct *w); - static void primelockdep(struct xe_guc_ct *ct) { if (!IS_ENABLED(CONFIG_LOCKDEP)) @@ -514,6 +516,9 @@ void xe_guc_ct_disable(struct xe_guc_ct *ct) */ void xe_guc_ct_stop(struct xe_guc_ct *ct) { + if (!xe_guc_ct_initialized(ct)) + return; + xe_guc_ct_set_state(ct, XE_GUC_CT_STATE_STOPPED); stop_g2h_handler(ct); } @@ -760,7 +765,7 @@ static int __guc_ct_send_locked(struct xe_guc_ct *ct, const u32 *action, u16 seqno; int ret; - xe_gt_assert(gt, ct->state != XE_GUC_CT_STATE_NOT_INITIALIZED); + xe_gt_assert(gt, xe_guc_ct_initialized(ct)); xe_gt_assert(gt, !g2h_len || !g2h_fence); xe_gt_assert(gt, !num_g2h || !g2h_fence); xe_gt_assert(gt, !g2h_len || num_g2h); @@ -1344,7 +1349,7 @@ static int g2h_read(struct xe_guc_ct *ct, u32 *msg, bool fast_path) u32 action; u32 *hxg; - xe_gt_assert(gt, ct->state != XE_GUC_CT_STATE_NOT_INITIALIZED); + xe_gt_assert(gt, xe_guc_ct_initialized(ct)); lockdep_assert_held(&ct->fast_lock); if (ct->state == XE_GUC_CT_STATE_DISABLED) diff --git a/drivers/gpu/drm/xe/xe_guc_ct.h b/drivers/gpu/drm/xe/xe_guc_ct.h index 82c4ae458dda..582aac106469 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.h +++ b/drivers/gpu/drm/xe/xe_guc_ct.h @@ -22,6 +22,11 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot, struct drm_pr void xe_guc_ct_snapshot_free(struct xe_guc_ct_snapshot *snapshot); void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p, bool want_ctb); +static inline bool xe_guc_ct_initialized(struct xe_guc_ct *ct) +{ + return ct->state != XE_GUC_CT_STATE_NOT_INITIALIZED; +} + static inline bool xe_guc_ct_enabled(struct xe_guc_ct *ct) { return ct->state == XE_GUC_CT_STATE_ENABLED; diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c index 18c623992035..c0ca61695d76 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc.c +++ b/drivers/gpu/drm/xe/xe_guc_pc.c @@ -5,8 +5,11 @@ #include "xe_guc_pc.h" +#include <linux/cleanup.h> #include <linux/delay.h> +#include <linux/jiffies.h> #include <linux/ktime.h> +#include <linux/wait_bit.h> #include <drm/drm_managed.h> #include <drm/drm_print.h> @@ -51,9 +54,12 @@ #define LNL_MERT_FREQ_CAP 800 #define BMG_MERT_FREQ_CAP 2133 +#define BMG_MIN_FREQ 1200 +#define BMG_MERT_FLUSH_FREQ_CAP 2600 #define SLPC_RESET_TIMEOUT_MS 5 /* roughly 5ms, but no need for precision */ #define SLPC_RESET_EXTENDED_TIMEOUT_MS 1000 /* To be used only at pc_start */ +#define SLPC_ACT_FREQ_TIMEOUT_MS 100 /** * DOC: GuC Power Conservation (PC) @@ -141,6 +147,36 @@ static int wait_for_pc_state(struct xe_guc_pc *pc, return -ETIMEDOUT; } +static int wait_for_flush_complete(struct xe_guc_pc *pc) +{ + const unsigned long timeout = msecs_to_jiffies(30); + + if (!wait_var_event_timeout(&pc->flush_freq_limit, + !atomic_read(&pc->flush_freq_limit), + timeout)) + return -ETIMEDOUT; + + return 0; +} + +static int wait_for_act_freq_limit(struct xe_guc_pc *pc, u32 freq) +{ + int timeout_us = SLPC_ACT_FREQ_TIMEOUT_MS * USEC_PER_MSEC; + int slept, wait = 10; + + for (slept = 0; slept < timeout_us;) { + if (xe_guc_pc_get_act_freq(pc) <= freq) + return 0; + + usleep_range(wait, wait << 1); + slept += wait; + wait <<= 1; + if (slept + wait > timeout_us) + wait = timeout_us - slept; + } + + return -ETIMEDOUT; +} static int pc_action_reset(struct xe_guc_pc *pc) { struct xe_guc_ct *ct = pc_to_ct(pc); @@ -553,6 +589,25 @@ u32 xe_guc_pc_get_rpn_freq(struct xe_guc_pc *pc) return pc->rpn_freq; } +static int xe_guc_pc_get_min_freq_locked(struct xe_guc_pc *pc, u32 *freq) +{ + int ret; + + lockdep_assert_held(&pc->freq_lock); + + /* Might be in the middle of a gt reset */ + if (!pc->freq_ready) + return -EAGAIN; + + ret = pc_action_query_task_state(pc); + if (ret) + return ret; + + *freq = pc_get_min_freq(pc); + + return 0; +} + /** * xe_guc_pc_get_min_freq - Get the min operational frequency * @pc: The GuC PC @@ -563,26 +618,28 @@ u32 xe_guc_pc_get_rpn_freq(struct xe_guc_pc *pc) */ int xe_guc_pc_get_min_freq(struct xe_guc_pc *pc, u32 *freq) { + guard(mutex)(&pc->freq_lock); + + return xe_guc_pc_get_min_freq_locked(pc, freq); +} + +static int xe_guc_pc_set_min_freq_locked(struct xe_guc_pc *pc, u32 freq) +{ int ret; - xe_device_assert_mem_access(pc_to_xe(pc)); + lockdep_assert_held(&pc->freq_lock); - mutex_lock(&pc->freq_lock); - if (!pc->freq_ready) { - /* Might be in the middle of a gt reset */ - ret = -EAGAIN; - goto out; - } + /* Might be in the middle of a gt reset */ + if (!pc->freq_ready) + return -EAGAIN; - ret = pc_action_query_task_state(pc); + ret = pc_set_min_freq(pc, freq); if (ret) - goto out; + return ret; - *freq = pc_get_min_freq(pc); + pc->user_requested_min = freq; -out: - mutex_unlock(&pc->freq_lock); - return ret; + return 0; } /** @@ -596,24 +653,28 @@ out: */ int xe_guc_pc_set_min_freq(struct xe_guc_pc *pc, u32 freq) { + guard(mutex)(&pc->freq_lock); + + return xe_guc_pc_set_min_freq_locked(pc, freq); +} + +static int xe_guc_pc_get_max_freq_locked(struct xe_guc_pc *pc, u32 *freq) +{ int ret; - mutex_lock(&pc->freq_lock); - if (!pc->freq_ready) { - /* Might be in the middle of a gt reset */ - ret = -EAGAIN; - goto out; - } + lockdep_assert_held(&pc->freq_lock); - ret = pc_set_min_freq(pc, freq); + /* Might be in the middle of a gt reset */ + if (!pc->freq_ready) + return -EAGAIN; + + ret = pc_action_query_task_state(pc); if (ret) - goto out; + return ret; - pc->user_requested_min = freq; + *freq = pc_get_max_freq(pc); -out: - mutex_unlock(&pc->freq_lock); - return ret; + return 0; } /** @@ -626,24 +687,28 @@ out: */ int xe_guc_pc_get_max_freq(struct xe_guc_pc *pc, u32 *freq) { + guard(mutex)(&pc->freq_lock); + + return xe_guc_pc_get_max_freq_locked(pc, freq); +} + +static int xe_guc_pc_set_max_freq_locked(struct xe_guc_pc *pc, u32 freq) +{ int ret; - mutex_lock(&pc->freq_lock); - if (!pc->freq_ready) { - /* Might be in the middle of a gt reset */ - ret = -EAGAIN; - goto out; - } + lockdep_assert_held(&pc->freq_lock); - ret = pc_action_query_task_state(pc); + /* Might be in the middle of a gt reset */ + if (!pc->freq_ready) + return -EAGAIN; + + ret = pc_set_max_freq(pc, freq); if (ret) - goto out; + return ret; - *freq = pc_get_max_freq(pc); + pc->user_requested_max = freq; -out: - mutex_unlock(&pc->freq_lock); - return ret; + return 0; } /** @@ -657,24 +722,14 @@ out: */ int xe_guc_pc_set_max_freq(struct xe_guc_pc *pc, u32 freq) { - int ret; - - mutex_lock(&pc->freq_lock); - if (!pc->freq_ready) { - /* Might be in the middle of a gt reset */ - ret = -EAGAIN; - goto out; + if (XE_WA(pc_to_gt(pc), 22019338487)) { + if (wait_for_flush_complete(pc) != 0) + return -EAGAIN; } - ret = pc_set_max_freq(pc, freq); - if (ret) - goto out; - - pc->user_requested_max = freq; + guard(mutex)(&pc->freq_lock); -out: - mutex_unlock(&pc->freq_lock); - return ret; + return xe_guc_pc_set_max_freq_locked(pc, freq); } /** @@ -817,6 +872,7 @@ void xe_guc_pc_init_early(struct xe_guc_pc *pc) static int pc_adjust_freq_bounds(struct xe_guc_pc *pc) { + struct xe_tile *tile = gt_to_tile(pc_to_gt(pc)); int ret; lockdep_assert_held(&pc->freq_lock); @@ -843,6 +899,9 @@ static int pc_adjust_freq_bounds(struct xe_guc_pc *pc) if (pc_get_min_freq(pc) > pc->rp0_freq) ret = pc_set_min_freq(pc, pc->rp0_freq); + if (XE_WA(tile->primary_gt, 14022085890)) + ret = pc_set_min_freq(pc, max(BMG_MIN_FREQ, pc_get_min_freq(pc))); + out: return ret; } @@ -868,30 +927,117 @@ static int pc_adjust_requested_freq(struct xe_guc_pc *pc) return ret; } -static int pc_set_mert_freq_cap(struct xe_guc_pc *pc) +static bool needs_flush_freq_limit(struct xe_guc_pc *pc) { - int ret = 0; + struct xe_gt *gt = pc_to_gt(pc); - if (XE_WA(pc_to_gt(pc), 22019338487)) { - /* - * Get updated min/max and stash them. - */ - ret = xe_guc_pc_get_min_freq(pc, &pc->stashed_min_freq); - if (!ret) - ret = xe_guc_pc_get_max_freq(pc, &pc->stashed_max_freq); - if (ret) - return ret; + return XE_WA(gt, 22019338487) && + pc->rp0_freq > BMG_MERT_FLUSH_FREQ_CAP; +} + +/** + * xe_guc_pc_apply_flush_freq_limit() - Limit max GT freq during L2 flush + * @pc: the xe_guc_pc object + * + * As per the WA, reduce max GT frequency during L2 cache flush + */ +void xe_guc_pc_apply_flush_freq_limit(struct xe_guc_pc *pc) +{ + struct xe_gt *gt = pc_to_gt(pc); + u32 max_freq; + int ret; + + if (!needs_flush_freq_limit(pc)) + return; + + guard(mutex)(&pc->freq_lock); + + ret = xe_guc_pc_get_max_freq_locked(pc, &max_freq); + if (!ret && max_freq > BMG_MERT_FLUSH_FREQ_CAP) { + ret = pc_set_max_freq(pc, BMG_MERT_FLUSH_FREQ_CAP); + if (ret) { + xe_gt_err_once(gt, "Failed to cap max freq on flush to %u, %pe\n", + BMG_MERT_FLUSH_FREQ_CAP, ERR_PTR(ret)); + return; + } + + atomic_set(&pc->flush_freq_limit, 1); /* - * Ensure min and max are bound by MERT_FREQ_CAP until driver loads. + * If user has previously changed max freq, stash that value to + * restore later, otherwise use the current max. New user + * requests wait on flush. */ - mutex_lock(&pc->freq_lock); - ret = pc_set_min_freq(pc, min(pc->rpe_freq, pc_max_freq_cap(pc))); - if (!ret) - ret = pc_set_max_freq(pc, min(pc->rp0_freq, pc_max_freq_cap(pc))); - mutex_unlock(&pc->freq_lock); + if (pc->user_requested_max != 0) + pc->stashed_max_freq = pc->user_requested_max; + else + pc->stashed_max_freq = max_freq; } + /* + * Wait for actual freq to go below the flush cap: even if the previous + * max was below cap, the current one might still be above it + */ + ret = wait_for_act_freq_limit(pc, BMG_MERT_FLUSH_FREQ_CAP); + if (ret) + xe_gt_err_once(gt, "Actual freq did not reduce to %u, %pe\n", + BMG_MERT_FLUSH_FREQ_CAP, ERR_PTR(ret)); +} + +/** + * xe_guc_pc_remove_flush_freq_limit() - Remove max GT freq limit after L2 flush completes. + * @pc: the xe_guc_pc object + * + * Retrieve the previous GT max frequency value. + */ +void xe_guc_pc_remove_flush_freq_limit(struct xe_guc_pc *pc) +{ + struct xe_gt *gt = pc_to_gt(pc); + int ret = 0; + + if (!needs_flush_freq_limit(pc)) + return; + + if (!atomic_read(&pc->flush_freq_limit)) + return; + + mutex_lock(&pc->freq_lock); + + ret = pc_set_max_freq(>->uc.guc.pc, pc->stashed_max_freq); + if (ret) + xe_gt_err_once(gt, "Failed to restore max freq %u:%d", + pc->stashed_max_freq, ret); + + atomic_set(&pc->flush_freq_limit, 0); + mutex_unlock(&pc->freq_lock); + wake_up_var(&pc->flush_freq_limit); +} + +static int pc_set_mert_freq_cap(struct xe_guc_pc *pc) +{ + int ret; + + if (!XE_WA(pc_to_gt(pc), 22019338487)) + return 0; + + guard(mutex)(&pc->freq_lock); + + /* + * Get updated min/max and stash them. + */ + ret = xe_guc_pc_get_min_freq_locked(pc, &pc->stashed_min_freq); + if (!ret) + ret = xe_guc_pc_get_max_freq_locked(pc, &pc->stashed_max_freq); + if (ret) + return ret; + + /* + * Ensure min and max are bound by MERT_FREQ_CAP until driver loads. + */ + ret = pc_set_min_freq(pc, min(pc->rpe_freq, pc_max_freq_cap(pc))); + if (!ret) + ret = pc_set_max_freq(pc, min(pc->rp0_freq, pc_max_freq_cap(pc))); + return ret; } @@ -1068,7 +1214,7 @@ int xe_guc_pc_start(struct xe_guc_pc *pc) goto out; } - memset(pc->bo->vmap.vaddr, 0, size); + xe_map_memset(xe, &pc->bo->vmap, 0, 0, size); slpc_shared_data_write(pc, header.size, size); earlier = ktime_get(); diff --git a/drivers/gpu/drm/xe/xe_guc_pc.h b/drivers/gpu/drm/xe/xe_guc_pc.h index 0a2664d5c811..52ecdd5ddbff 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc.h +++ b/drivers/gpu/drm/xe/xe_guc_pc.h @@ -38,5 +38,7 @@ u64 xe_guc_pc_mc6_residency(struct xe_guc_pc *pc); void xe_guc_pc_init_early(struct xe_guc_pc *pc); int xe_guc_pc_restore_stashed_freq(struct xe_guc_pc *pc); void xe_guc_pc_raise_unslice(struct xe_guc_pc *pc); +void xe_guc_pc_apply_flush_freq_limit(struct xe_guc_pc *pc); +void xe_guc_pc_remove_flush_freq_limit(struct xe_guc_pc *pc); #endif /* _XE_GUC_PC_H_ */ diff --git a/drivers/gpu/drm/xe/xe_guc_pc_types.h b/drivers/gpu/drm/xe/xe_guc_pc_types.h index 2978ac9a249b..c02053948a57 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc_types.h +++ b/drivers/gpu/drm/xe/xe_guc_pc_types.h @@ -15,6 +15,8 @@ struct xe_guc_pc { /** @bo: GGTT buffer object that is shared with GuC PC */ struct xe_bo *bo; + /** @flush_freq_limit: 1 when max freq changes are limited by driver */ + atomic_t flush_freq_limit; /** @rp0_freq: HW RP0 frequency - The Maximum one */ u32 rp0_freq; /** @rpa_freq: HW RPa frequency - The Achievable one */ diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 6d84a52b660a..2ac87ff4a057 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -891,12 +891,13 @@ static void xe_guc_exec_queue_lr_cleanup(struct work_struct *w) struct xe_exec_queue *q = ge->q; struct xe_guc *guc = exec_queue_to_guc(q); struct xe_gpu_scheduler *sched = &ge->sched; - bool wedged; + bool wedged = false; xe_gt_assert(guc_to_gt(guc), xe_exec_queue_is_lr(q)); trace_xe_exec_queue_lr_cleanup(q); - wedged = guc_submit_hint_wedged(exec_queue_to_guc(q)); + if (!exec_queue_killed(q)) + wedged = guc_submit_hint_wedged(exec_queue_to_guc(q)); /* Kill the run_job / process_msg entry points */ xe_sched_submission_stop(sched); @@ -1070,7 +1071,7 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job) int err = -ETIME; pid_t pid = -1; int i = 0; - bool wedged, skip_timeout_check; + bool wedged = false, skip_timeout_check; /* * TDR has fired before free job worker. Common if exec queue @@ -1116,7 +1117,8 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job) * doesn't work for SRIOV. For now assuming timeouts in wedged mode are * genuine timeouts. */ - wedged = guc_submit_hint_wedged(exec_queue_to_guc(q)); + if (!exec_queue_killed(q)) + wedged = guc_submit_hint_wedged(exec_queue_to_guc(q)); /* Engine state now stable, disable scheduling to check timestamp */ if (!wedged && exec_queue_registered(q)) { @@ -1762,6 +1764,9 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc) { int ret; + if (!guc->submission_state.initialized) + return 0; + /* * Using an atomic here rather than submission_state.lock as this * function can be called while holding the CT lock (engine reset diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c index 74f31639b37f..f008e8049700 100644 --- a/drivers/gpu/drm/xe/xe_hwmon.c +++ b/drivers/gpu/drm/xe/xe_hwmon.c @@ -159,8 +159,8 @@ static int xe_hwmon_pcode_read_power_limit(const struct xe_hwmon *hwmon, u32 att return ret; } -static int xe_hwmon_pcode_write_power_limit(const struct xe_hwmon *hwmon, u32 attr, u8 channel, - u32 uval) +static int xe_hwmon_pcode_rmw_power_limit(const struct xe_hwmon *hwmon, u32 attr, u8 channel, + u32 clr, u32 set) { struct xe_tile *root_tile = xe_device_get_root_tile(hwmon->xe); u32 val0, val1; @@ -179,7 +179,7 @@ static int xe_hwmon_pcode_write_power_limit(const struct xe_hwmon *hwmon, u32 at channel, val0, val1, ret); if (attr == PL1_HWMON_ATTR) - val0 = uval; + val0 = (val0 & ~clr) | set; else return -EIO; @@ -339,7 +339,7 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe if (hwmon->xe->info.has_mbx_power_limits) { drm_dbg(&hwmon->xe->drm, "disabling %s on channel %d\n", PWR_ATTR_TO_STR(attr), channel); - xe_hwmon_pcode_write_power_limit(hwmon, attr, channel, 0); + xe_hwmon_pcode_rmw_power_limit(hwmon, attr, channel, PWR_LIM_EN, 0); xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, ®_val); } else { reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM_EN, 0); @@ -370,10 +370,9 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe } if (hwmon->xe->info.has_mbx_power_limits) - ret = xe_hwmon_pcode_write_power_limit(hwmon, attr, channel, reg_val); + ret = xe_hwmon_pcode_rmw_power_limit(hwmon, attr, channel, PWR_LIM, reg_val); else - reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM_EN | PWR_LIM_VAL, - reg_val); + reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM, reg_val); unlock: mutex_unlock(&hwmon->hwmon_lock); return ret; @@ -563,14 +562,11 @@ xe_hwmon_power_max_interval_store(struct device *dev, struct device_attribute *a 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); - r = (r & ~PWR_LIM_TIME) | rxy; - xe_hwmon_pcode_write_power_limit(hwmon, power_attr, channel, r); - } else { + if (hwmon->xe->info.has_mbx_power_limits) + xe_hwmon_pcode_rmw_power_limit(hwmon, power_attr, channel, PWR_LIM_TIME, rxy); + else r = xe_mmio_rmw32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel), PWR_LIM_TIME, rxy); - } mutex_unlock(&hwmon->hwmon_lock); @@ -1138,12 +1134,12 @@ xe_hwmon_get_preregistration_info(struct xe_hwmon *hwmon) } else { drm_info(&hwmon->xe->drm, "Using mailbox commands for power limits\n"); /* Write default limits to read from pcode from now on. */ - xe_hwmon_pcode_write_power_limit(hwmon, PL1_HWMON_ATTR, - CHANNEL_CARD, - hwmon->pl1_on_boot[CHANNEL_CARD]); - xe_hwmon_pcode_write_power_limit(hwmon, PL1_HWMON_ATTR, - CHANNEL_PKG, - hwmon->pl1_on_boot[CHANNEL_PKG]); + xe_hwmon_pcode_rmw_power_limit(hwmon, PL1_HWMON_ATTR, + CHANNEL_CARD, PWR_LIM | PWR_LIM_TIME, + hwmon->pl1_on_boot[CHANNEL_CARD]); + xe_hwmon_pcode_rmw_power_limit(hwmon, PL1_HWMON_ATTR, + CHANNEL_PKG, PWR_LIM | PWR_LIM_TIME, + hwmon->pl1_on_boot[CHANNEL_PKG]); hwmon->scl_shift_power = PWR_UNIT; hwmon->scl_shift_energy = ENERGY_UNIT; hwmon->scl_shift_time = TIME_UNIT; diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 63d74e27f54c..6e7b70532d11 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -40,6 +40,7 @@ #define LRC_PPHWSP_SIZE SZ_4K #define LRC_INDIRECT_RING_STATE_SIZE SZ_4K +#define LRC_WA_BB_SIZE SZ_4K static struct xe_device * lrc_to_xe(struct xe_lrc *lrc) @@ -910,7 +911,11 @@ static void xe_lrc_finish(struct xe_lrc *lrc) { xe_hw_fence_ctx_finish(&lrc->fence_ctx); xe_bo_unpin_map_no_vm(lrc->bo); - xe_bo_unpin_map_no_vm(lrc->bb_per_ctx_bo); +} + +static size_t wa_bb_offset(struct xe_lrc *lrc) +{ + return lrc->bo->size - LRC_WA_BB_SIZE; } /* @@ -941,11 +946,19 @@ static void xe_lrc_finish(struct xe_lrc *lrc) * store it in the PPHSWP. */ #define CONTEXT_ACTIVE 1ULL -static void xe_lrc_setup_utilization(struct xe_lrc *lrc) +static int xe_lrc_setup_utilization(struct xe_lrc *lrc) { - u32 *cmd; + const size_t max_size = LRC_WA_BB_SIZE; + u32 *cmd, *buf = NULL; - cmd = lrc->bb_per_ctx_bo->vmap.vaddr; + if (lrc->bo->vmap.is_iomem) { + buf = kmalloc(max_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + cmd = buf; + } else { + cmd = lrc->bo->vmap.vaddr + wa_bb_offset(lrc); + } *cmd++ = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET; *cmd++ = ENGINE_ID(0).addr; @@ -966,9 +979,17 @@ static void xe_lrc_setup_utilization(struct xe_lrc *lrc) *cmd++ = MI_BATCH_BUFFER_END; - xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR, - xe_bo_ggtt_addr(lrc->bb_per_ctx_bo) | 1); + if (buf) { + xe_map_memcpy_to(gt_to_xe(lrc->gt), &lrc->bo->vmap, + wa_bb_offset(lrc), buf, + (cmd - buf) * sizeof(*cmd)); + kfree(buf); + } + + xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR, xe_bo_ggtt_addr(lrc->bo) + + wa_bb_offset(lrc) + 1); + return 0; } #define PVC_CTX_ASID (0x2e + 1) @@ -1004,20 +1025,13 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, * FIXME: Perma-pinning LRC as we don't yet support moving GGTT address * via VM bind calls. */ - lrc->bo = xe_bo_create_pin_map(xe, tile, NULL, lrc_size, + lrc->bo = xe_bo_create_pin_map(xe, tile, NULL, + lrc_size + LRC_WA_BB_SIZE, ttm_bo_type_kernel, bo_flags); if (IS_ERR(lrc->bo)) return PTR_ERR(lrc->bo); - lrc->bb_per_ctx_bo = xe_bo_create_pin_map(xe, tile, NULL, SZ_4K, - ttm_bo_type_kernel, - bo_flags); - if (IS_ERR(lrc->bb_per_ctx_bo)) { - err = PTR_ERR(lrc->bb_per_ctx_bo); - goto err_lrc_finish; - } - lrc->size = lrc_size; lrc->ring.size = ring_size; lrc->ring.tail = 0; @@ -1125,7 +1139,9 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, map = __xe_lrc_start_seqno_map(lrc); xe_map_write32(lrc_to_xe(lrc), &map, lrc->fence_ctx.next_seqno - 1); - xe_lrc_setup_utilization(lrc); + err = xe_lrc_setup_utilization(lrc); + if (err) + goto err_lrc_finish; return 0; @@ -1803,7 +1819,8 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc) snapshot->seqno = xe_lrc_seqno(lrc); snapshot->lrc_bo = xe_bo_get(lrc->bo); snapshot->lrc_offset = xe_lrc_pphwsp_offset(lrc); - snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset; + snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset - + LRC_WA_BB_SIZE; snapshot->lrc_snapshot = NULL; snapshot->ctx_timestamp = lower_32_bits(xe_lrc_ctx_timestamp(lrc)); snapshot->ctx_job_timestamp = xe_lrc_ctx_job_timestamp(lrc); diff --git a/drivers/gpu/drm/xe/xe_lrc_types.h b/drivers/gpu/drm/xe/xe_lrc_types.h index ae24cf6f8dd9..883e550a9423 100644 --- a/drivers/gpu/drm/xe/xe_lrc_types.h +++ b/drivers/gpu/drm/xe/xe_lrc_types.h @@ -53,9 +53,6 @@ struct xe_lrc { /** @ctx_timestamp: readout value of CTX_TIMESTAMP on last update */ u64 ctx_timestamp; - - /** @bb_per_ctx_bo: buffer object for per context batch wa buffer */ - struct xe_bo *bb_per_ctx_bo; }; struct xe_lrc_snapshot; diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 8f8e9fdfb2a8..7acdc4c78866 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -82,7 +82,7 @@ struct xe_migrate { * of the instruction. Subtracting the instruction header (1 dword) and * address (2 dwords), that leaves 0x3FD dwords (0x1FE qwords) for PTE values. */ -#define MAX_PTE_PER_SDI 0x1FE +#define MAX_PTE_PER_SDI 0x1FEU /** * xe_tile_migrate_exec_queue() - Get this tile's migrate exec queue. @@ -1553,15 +1553,17 @@ static u32 pte_update_cmd_size(u64 size) u64 entries = DIV_U64_ROUND_UP(size, XE_PAGE_SIZE); XE_WARN_ON(size > MAX_PREEMPTDISABLE_TRANSFER); + /* * MI_STORE_DATA_IMM command is used to update page table. Each - * instruction can update maximumly 0x1ff pte entries. To update - * n (n <= 0x1ff) pte entries, we need: - * 1 dword for the MI_STORE_DATA_IMM command header (opcode etc) - * 2 dword for the page table's physical location - * 2*n dword for value of pte to fill (each pte entry is 2 dwords) + * instruction can update maximumly MAX_PTE_PER_SDI pte entries. To + * update n (n <= MAX_PTE_PER_SDI) pte entries, we need: + * + * - 1 dword for the MI_STORE_DATA_IMM command header (opcode etc) + * - 2 dword for the page table's physical location + * - 2*n dword for value of pte to fill (each pte entry is 2 dwords) */ - num_dword = (1 + 2) * DIV_U64_ROUND_UP(entries, 0x1ff); + num_dword = (1 + 2) * DIV_U64_ROUND_UP(entries, MAX_PTE_PER_SDI); num_dword += entries * 2; return num_dword; @@ -1577,7 +1579,7 @@ static void build_pt_update_batch_sram(struct xe_migrate *m, ptes = DIV_ROUND_UP(size, XE_PAGE_SIZE); while (ptes) { - u32 chunk = min(0x1ffU, ptes); + u32 chunk = min(MAX_PTE_PER_SDI, ptes); bb->cs[bb->len++] = MI_STORE_DATA_IMM | MI_SDI_NUM_QW(chunk); bb->cs[bb->len++] = pt_offset; diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c index 6345896585de..f0b167b3fb6a 100644 --- a/drivers/gpu/drm/xe/xe_svm.c +++ b/drivers/gpu/drm/xe/xe_svm.c @@ -764,7 +764,7 @@ static bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range, return false; } - if (range_size <= SZ_64K && !supports_4K_migration(vm->xe)) { + if (range_size < SZ_64K && !supports_4K_migration(vm->xe)) { drm_dbg(&vm->xe->drm, "Platform doesn't support SZ_4K range migration\n"); return false; } diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index 9efc5accd43d..69c1d7fc695e 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -21,7 +21,8 @@ GRAPHICS_VERSION_RANGE(1270, 1274) MEDIA_VERSION(1300) PLATFORM(DG2) -14018094691 GRAPHICS_VERSION(2004) +14018094691 GRAPHICS_VERSION_RANGE(2001, 2002) + GRAPHICS_VERSION(2004) 14019882105 GRAPHICS_VERSION(2004), GRAPHICS_STEP(A0, B0) 18024947630 GRAPHICS_VERSION(2001) GRAPHICS_VERSION(2004) @@ -59,3 +60,7 @@ no_media_l3 MEDIA_VERSION(3000) MEDIA_VERSION_RANGE(1301, 3000) 16026508708 GRAPHICS_VERSION_RANGE(1200, 3001) MEDIA_VERSION_RANGE(1300, 3000) + +# SoC workaround - currently applies to all platforms with the following +# primary GT GMDID +14022085890 GRAPHICS_VERSION(2001) |