diff options
27 files changed, 264 insertions, 157 deletions
diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index e9fbd8c14364..54486960cbf5 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -59,6 +59,18 @@ static bool aie2_tdr_detect(struct amdxdna_dev *xdna) return false; } +static void aie2_cmd_release(struct kref *ref) +{ + struct amdxdna_drv_cmd *drv_cmd = container_of(ref, struct amdxdna_drv_cmd, refcnt); + + kfree(drv_cmd); +} + +static void aie2_cmd_put(struct amdxdna_drv_cmd *drv_cmd) +{ + kref_put(&drv_cmd->refcnt, aie2_cmd_release); +} + static void aie2_job_release(struct kref *ref) { struct amdxdna_sched_job *job; @@ -70,6 +82,8 @@ static void aie2_job_release(struct kref *ref) wake_up(&job->hwctx->priv->job_free_wq); if (job->out_fence) dma_fence_put(job->out_fence); + if (job->drv_cmd) + aie2_cmd_put(job->drv_cmd); kfree(job->aie2_job_health); kfree(job); } @@ -901,7 +915,7 @@ static int aie2_hwctx_cfg_debug_bo(struct amdxdna_hwctx *hwctx, u32 bo_hdl, { struct amdxdna_client *client = hwctx->client; struct amdxdna_dev *xdna = client->xdna; - struct amdxdna_drv_cmd cmd = { 0 }; + struct amdxdna_drv_cmd *cmd; struct amdxdna_gem_obj *abo; u64 seq; int ret; @@ -912,32 +926,39 @@ static int aie2_hwctx_cfg_debug_bo(struct amdxdna_hwctx *hwctx, u32 bo_hdl, return -EINVAL; } + cmd = kzalloc_obj(*cmd); + if (!cmd) { + ret = -ENOMEM; + goto put_obj; + } + kref_init(&cmd->refcnt); + if (attach) { if (abo->assigned_hwctx != AMDXDNA_INVALID_CTX_HANDLE) { ret = -EBUSY; - goto put_obj; + goto put_cmd; } - cmd.opcode = ATTACH_DEBUG_BO; + cmd->opcode = ATTACH_DEBUG_BO; } else { if (abo->assigned_hwctx != hwctx->id) { ret = -EINVAL; - goto put_obj; + goto put_cmd; } - cmd.opcode = DETACH_DEBUG_BO; + cmd->opcode = DETACH_DEBUG_BO; } - ret = amdxdna_cmd_submit(client, &cmd, AMDXDNA_INVALID_BO_HANDLE, + ret = amdxdna_cmd_submit(client, cmd, AMDXDNA_INVALID_BO_HANDLE, &bo_hdl, 1, hwctx->id, &seq); if (ret) { XDNA_ERR(xdna, "Submit command failed"); - goto put_obj; + goto put_cmd; } aie2_cmd_wait(hwctx, seq); - if (cmd.result) { - XDNA_ERR(xdna, "Response failure 0x%x", cmd.result); + if (cmd->result) { + XDNA_ERR(xdna, "Response failure 0x%x", cmd->result); ret = -EINVAL; - goto put_obj; + goto put_cmd; } if (attach) @@ -947,6 +968,8 @@ static int aie2_hwctx_cfg_debug_bo(struct amdxdna_hwctx *hwctx, u32 bo_hdl, XDNA_DBG(xdna, "Config debug BO %d to %s", bo_hdl, hwctx->name); +put_cmd: + aie2_cmd_put(cmd); put_obj: amdxdna_gem_put_obj(abo); return ret; @@ -974,25 +997,32 @@ int aie2_hwctx_sync_debug_bo(struct amdxdna_hwctx *hwctx, u32 debug_bo_hdl) { struct amdxdna_client *client = hwctx->client; struct amdxdna_dev *xdna = client->xdna; - struct amdxdna_drv_cmd cmd = { 0 }; + struct amdxdna_drv_cmd *cmd; u64 seq; int ret; - cmd.opcode = SYNC_DEBUG_BO; - ret = amdxdna_cmd_submit(client, &cmd, AMDXDNA_INVALID_BO_HANDLE, + cmd = kzalloc_obj(*cmd); + if (!cmd) + return -ENOMEM; + kref_init(&cmd->refcnt); + + cmd->opcode = SYNC_DEBUG_BO; + ret = amdxdna_cmd_submit(client, cmd, AMDXDNA_INVALID_BO_HANDLE, &debug_bo_hdl, 1, hwctx->id, &seq); if (ret) { XDNA_ERR(xdna, "Submit command failed"); - return ret; + goto put_cmd; } aie2_cmd_wait(hwctx, seq); - if (cmd.result) { - XDNA_ERR(xdna, "Response failure 0x%x", cmd.result); - return -EINVAL; + if (cmd->result) { + XDNA_ERR(xdna, "Response failure 0x%x", cmd->result); + ret = -EINVAL; } - return 0; +put_cmd: + aie2_cmd_put(cmd); + return ret; } static int aie2_populate_range(struct amdxdna_gem_obj *abo) @@ -1142,6 +1172,8 @@ retry: dma_resv_add_fence(job->bos[i]->resv, job->out_fence, DMA_RESV_USAGE_WRITE); job->seq = hwctx->priv->seq++; kref_get(&job->refcnt); + if (job->drv_cmd) + kref_get(&job->drv_cmd->refcnt); drm_sched_entity_push_job(&job->base); *seq = job->seq; diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h index aaae16430466..b6bef3af7dab 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.h +++ b/drivers/accel/amdxdna/amdxdna_ctx.h @@ -132,6 +132,7 @@ enum amdxdna_job_opcode { struct amdxdna_drv_cmd { enum amdxdna_job_opcode opcode; u32 result; + struct kref refcnt; }; struct app_health_report; diff --git a/drivers/accel/amdxdna/amdxdna_iommu.c b/drivers/accel/amdxdna/amdxdna_iommu.c index eff00131d0f8..4f245b969eef 100644 --- a/drivers/accel/amdxdna/amdxdna_iommu.c +++ b/drivers/accel/amdxdna/amdxdna_iommu.c @@ -4,6 +4,7 @@ */ #include <drm/amdxdna_accel.h> +#include <drm/drm_managed.h> #include <linux/iommu.h> #include <linux/iova.h> @@ -153,10 +154,30 @@ void amdxdna_iommu_free(struct amdxdna_dev *xdna, size_t size, free_pages((unsigned long)cpu_addr, get_order(size)); } +static void amdxdna_cleanup_force_iova(struct drm_device *dev, void *res) +{ + struct amdxdna_dev *xdna = to_xdna_dev(dev); + + if (xdna->domain) { + iommu_detach_group(xdna->domain, xdna->group); + put_iova_domain(&xdna->iovad); + iova_cache_put(); + iommu_domain_free(xdna->domain); + } + + iommu_group_put(xdna->group); +} + +void amdxdna_iommu_fini(struct amdxdna_dev *xdna) +{ + if (xdna->group && !xdna->domain) + iommu_group_put(xdna->group); +} + int amdxdna_iommu_init(struct amdxdna_dev *xdna) { unsigned long order; - int ret; + int ret = 0; xdna->group = iommu_group_get(xdna->ddev.dev); if (!xdna->group || !force_iova) @@ -182,8 +203,14 @@ int amdxdna_iommu_init(struct amdxdna_dev *xdna) if (ret) goto put_iova; + ret = drmm_add_action(&xdna->ddev, amdxdna_cleanup_force_iova, NULL); + if (ret) + goto detach_group; + return 0; +detach_group: + iommu_detach_group(xdna->domain, xdna->group); put_iova: put_iova_domain(&xdna->iovad); iova_cache_put(); @@ -191,20 +218,8 @@ free_domain: iommu_domain_free(xdna->domain); put_group: iommu_group_put(xdna->group); + xdna->group = NULL; xdna->domain = NULL; return ret; } - -void amdxdna_iommu_fini(struct amdxdna_dev *xdna) -{ - if (xdna->domain) { - iommu_detach_group(xdna->domain, xdna->group); - put_iova_domain(&xdna->iovad); - iova_cache_put(); - iommu_domain_free(xdna->domain); - } - - if (xdna->group) - iommu_group_put(xdna->group); -} diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c index 65489bb3f2b0..e94d8290a807 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.c +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c @@ -138,9 +138,11 @@ static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp) xdna->dev_info->dev_heap_max_size); mutex_init(&client->mm_lock); + mutex_lock(&xdna->client_lock); mutex_lock(&xdna->dev_lock); list_add_tail(&client->node, &xdna->client_list); mutex_unlock(&xdna->dev_lock); + mutex_unlock(&xdna->client_lock); filp->driver_priv = client; client->filp = filp; @@ -174,18 +176,14 @@ static void amdxdna_drm_close(struct drm_device *ddev, struct drm_file *filp) { struct amdxdna_client *client = filp->driver_priv; struct amdxdna_dev *xdna = to_xdna_dev(ddev); - int idx; XDNA_DBG(xdna, "closing pid %d", client->pid); - if (!drm_dev_enter(&xdna->ddev, &idx)) - return; - + mutex_lock(&xdna->client_lock); mutex_lock(&xdna->dev_lock); amdxdna_client_cleanup(client); mutex_unlock(&xdna->dev_lock); - - drm_dev_exit(idx); + mutex_unlock(&xdna->client_lock); } static int amdxdna_drm_get_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) @@ -371,6 +369,10 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (!xdna->dev_info) return -ENODEV; + ret = drmm_mutex_init(ddev, &xdna->client_lock); + if (ret) + return ret; + drmm_mutex_init(ddev, &xdna->dev_lock); init_rwsem(&xdna->notifier_lock); INIT_LIST_HEAD(&xdna->client_list); @@ -390,9 +392,9 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) return ret; - xdna->notifier_wq = alloc_ordered_workqueue("notifier_wq", WQ_MEM_RECLAIM); - if (!xdna->notifier_wq) { - ret = -ENOMEM; + xdna->notifier_wq = drmm_alloc_ordered_workqueue(ddev, "notifier_wq", WQ_MEM_RECLAIM); + if (IS_ERR(xdna->notifier_wq)) { + ret = PTR_ERR(xdna->notifier_wq); goto iommu_fini; } @@ -401,7 +403,7 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id) mutex_unlock(&xdna->dev_lock); if (ret) { XDNA_ERR(xdna, "Hardware init failed, ret %d", ret); - goto destroy_notifier_wq; + goto iommu_fini; } ret = amdxdna_sysfs_init(xdna); @@ -425,8 +427,6 @@ failed_dev_fini: mutex_lock(&xdna->dev_lock); xdna->dev_info->ops->fini(xdna); mutex_unlock(&xdna->dev_lock); -destroy_notifier_wq: - destroy_workqueue(xdna->notifier_wq); iommu_fini: amdxdna_iommu_fini(xdna); return ret; @@ -437,23 +437,19 @@ static void amdxdna_remove(struct pci_dev *pdev) struct amdxdna_dev *xdna = pci_get_drvdata(pdev); struct amdxdna_client *client; - destroy_workqueue(xdna->notifier_wq); - drm_dev_unplug(&xdna->ddev); amdxdna_sysfs_fini(xdna); + mutex_lock(&xdna->client_lock); mutex_lock(&xdna->dev_lock); - client = list_first_entry_or_null(&xdna->client_list, - struct amdxdna_client, node); - while (client) { - amdxdna_client_cleanup(client); - - client = list_first_entry_or_null(&xdna->client_list, - struct amdxdna_client, node); + list_for_each_entry(client, &xdna->client_list, node) { + amdxdna_hwctx_remove_all(client); + amdxdna_sva_fini(client); } xdna->dev_info->ops->fini(xdna); mutex_unlock(&xdna->dev_lock); + mutex_unlock(&xdna->client_lock); amdxdna_iommu_fini(xdna); } diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h index 34271c14d359..a997d27a504d 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.h +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h @@ -120,6 +120,7 @@ struct amdxdna_dev { struct mutex dev_lock; /* per device lock */ struct list_head client_list; + struct mutex client_lock; /* client_list */ struct amdxdna_fw_ver fw_ver; struct rw_semaphore notifier_lock; /* for mmu notifier*/ struct workqueue_struct *notifier_wq; diff --git a/drivers/dma-buf/dma-fence-unwrap.c b/drivers/dma-buf/dma-fence-unwrap.c index 53bb40e70b27..364cbf79ad73 100644 --- a/drivers/dma-buf/dma-fence-unwrap.c +++ b/drivers/dma-buf/dma-fence-unwrap.c @@ -97,6 +97,9 @@ int dma_fence_dedup_array(struct dma_fence **fences, int num_fences) { int i, j; + if (!num_fences) + return 0; + sort(fences, num_fences, sizeof(*fences), fence_cmp, NULL); /* diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index b3bfa6943a8e..87797bea91cb 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -1168,7 +1168,7 @@ const char __rcu *dma_fence_driver_name(struct dma_fence *fence) /* RCU protection is required for safe access to returned string */ ops = rcu_dereference(fence->ops); - if (!dma_fence_test_signaled_flag(fence)) + if (ops) return (const char __rcu *)ops->get_driver_name(fence); else return (const char __rcu *)"detached-driver"; @@ -1201,8 +1201,8 @@ const char __rcu *dma_fence_timeline_name(struct dma_fence *fence) /* RCU protection is required for safe access to returned string */ ops = rcu_dereference(fence->ops); - if (!dma_fence_test_signaled_flag(fence)) - return (const char __rcu *)ops->get_driver_name(fence); + if (ops) + return (const char __rcu *)ops->get_timeline_name(fence); else return (const char __rcu *)"signaled-timeline"; } diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c index 5ba62e637a61..9aad1d1d28ec 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c @@ -313,7 +313,11 @@ void komeda_dev_destroy(struct komeda_dev *mdev) int komeda_dev_resume(struct komeda_dev *mdev) { - clk_prepare_enable(mdev->aclk); + int err; + + err = clk_prepare_enable(mdev->aclk); + if (err) + return err; mdev->funcs->enable_irq(mdev); diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c index 4bb5f250e95e..67fffab018ae 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c @@ -74,8 +74,11 @@ static int komeda_platform_probe(struct platform_device *pdev) } pm_runtime_enable(dev); - if (!pm_runtime_enabled(dev)) - komeda_dev_resume(mdrv->mdev); + if (!pm_runtime_enabled(dev)) { + err = komeda_dev_resume(mdrv->mdev); + if (err) + goto err_destroy_mdev; + } mdrv->kms = komeda_kms_attach(mdrv->mdev); if (IS_ERR(mdrv->kms)) { @@ -93,7 +96,7 @@ destroy_mdev: pm_runtime_disable(dev); else komeda_dev_suspend(mdrv->mdev); - +err_destroy_mdev: komeda_dev_destroy(mdrv->mdev); free_mdrv: @@ -140,11 +143,12 @@ static int __maybe_unused komeda_pm_suspend(struct device *dev) static int __maybe_unused komeda_pm_resume(struct device *dev) { struct komeda_drv *mdrv = dev_get_drvdata(dev); + int err = 0; if (!pm_runtime_status_suspended(dev)) - komeda_dev_resume(mdrv->mdev); + err = komeda_dev_resume(mdrv->mdev); - return drm_mode_config_helper_resume(&mdrv->kms->base); + return err ? err : drm_mode_config_helper_resume(&mdrv->kms->base); } static const struct dev_pm_ops komeda_pm_ops = { diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c index 9abe800f598a..23fa942ae4bb 100644 --- a/drivers/gpu/drm/arm/malidp_drv.c +++ b/drivers/gpu/drm/arm/malidp_drv.c @@ -670,6 +670,11 @@ static int malidp_runtime_pm_suspend(struct device *dev) struct drm_device *drm = dev_get_drvdata(dev); struct malidp_drm *malidp = drm_to_malidp(drm); struct malidp_hw_device *hwdev = malidp->dev; + struct clk_bulk_data clks[] = { + { .clk = hwdev->pclk }, + { .clk = hwdev->aclk }, + { .clk = hwdev->mclk }, + }; /* we can only suspend if the hardware is in config mode */ WARN_ON(!hwdev->hw->in_config_mode(hwdev)); @@ -677,9 +682,7 @@ static int malidp_runtime_pm_suspend(struct device *dev) malidp_se_irq_fini(hwdev); malidp_de_irq_fini(hwdev); hwdev->pm_suspended = true; - clk_disable_unprepare(hwdev->mclk); - clk_disable_unprepare(hwdev->aclk); - clk_disable_unprepare(hwdev->pclk); + clk_bulk_disable_unprepare(ARRAY_SIZE(clks), clks); return 0; } @@ -689,10 +692,17 @@ static int malidp_runtime_pm_resume(struct device *dev) struct drm_device *drm = dev_get_drvdata(dev); struct malidp_drm *malidp = drm_to_malidp(drm); struct malidp_hw_device *hwdev = malidp->dev; + struct clk_bulk_data clks[] = { + { .clk = hwdev->pclk }, + { .clk = hwdev->aclk }, + { .clk = hwdev->mclk }, + }; + int err; + + err = clk_bulk_prepare_enable(ARRAY_SIZE(clks), clks); + if (err) + return err; - clk_prepare_enable(hwdev->pclk); - clk_prepare_enable(hwdev->aclk); - clk_prepare_enable(hwdev->mclk); hwdev->pm_suspended = false; malidp_de_irq_hw_init(hwdev); malidp_se_irq_hw_init(hwdev); diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index 4de36fda0544..7ce9e212770a 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -3740,8 +3740,10 @@ void drm_dp_mst_topology_queue_probe(struct drm_dp_mst_topology_mgr *mgr) { mutex_lock(&mgr->lock); - if (drm_WARN_ON(mgr->dev, !mgr->mst_state || !mgr->mst_primary)) + if (!mgr->mst_state || !mgr->mst_primary) { + drm_dbg_kms(mgr->dev, "queue_probe skipped: topology torn down\n"); goto out_unlock; + } drm_dp_mst_topology_mgr_invalidate_mstb(mgr->mst_primary); drm_dp_mst_queue_probe_work(mgr); diff --git a/drivers/gpu/drm/imagination/pvr_context.c b/drivers/gpu/drm/imagination/pvr_context.c index eba4694400b5..52e16c1e7af0 100644 --- a/drivers/gpu/drm/imagination/pvr_context.c +++ b/drivers/gpu/drm/imagination/pvr_context.c @@ -161,22 +161,24 @@ ctx_fw_data_init(void *cpu_ptr, void *priv) /** * pvr_context_destroy_queues() - Destroy all queues attached to a context. * @ctx: Context to destroy queues on. + * @cleanup_queue_entity: Whether to cleanup the queue entity e.g. context + * creation failure path. * * Should be called when the last reference to a context object is dropped. * It releases all resources attached to the queues bound to this context. */ -static void pvr_context_destroy_queues(struct pvr_context *ctx) +static void pvr_context_destroy_queues(struct pvr_context *ctx, bool cleanup_queue_entity) { switch (ctx->type) { case DRM_PVR_CTX_TYPE_RENDER: - pvr_queue_destroy(ctx->queues.fragment); - pvr_queue_destroy(ctx->queues.geometry); + pvr_queue_destroy(ctx->queues.fragment, cleanup_queue_entity); + pvr_queue_destroy(ctx->queues.geometry, cleanup_queue_entity); break; case DRM_PVR_CTX_TYPE_COMPUTE: - pvr_queue_destroy(ctx->queues.compute); + pvr_queue_destroy(ctx->queues.compute, cleanup_queue_entity); break; case DRM_PVR_CTX_TYPE_TRANSFER_FRAG: - pvr_queue_destroy(ctx->queues.transfer); + pvr_queue_destroy(ctx->queues.transfer, cleanup_queue_entity); break; } } @@ -240,7 +242,7 @@ static int pvr_context_create_queues(struct pvr_context *ctx, return -EINVAL; err_destroy_queues: - pvr_context_destroy_queues(ctx); + pvr_context_destroy_queues(ctx, true); return err; } @@ -349,7 +351,7 @@ err_destroy_fw_obj: pvr_fw_object_destroy(ctx->fw_obj); err_destroy_queues: - pvr_context_destroy_queues(ctx); + pvr_context_destroy_queues(ctx, true); err_free_ctx_id: /* @@ -384,7 +386,7 @@ pvr_context_release(struct kref *ref_count) spin_unlock(&pvr_dev->ctx_list_lock); xa_erase(&pvr_dev->ctx_ids, ctx->ctx_id); - pvr_context_destroy_queues(ctx); + pvr_context_destroy_queues(ctx, false); pvr_fw_object_destroy(ctx->fw_obj); kfree(ctx->data); pvr_vm_context_put(ctx->vm_ctx); diff --git a/drivers/gpu/drm/imagination/pvr_drv.c b/drivers/gpu/drm/imagination/pvr_drv.c index b20c462bcba0..e8487fd22e15 100644 --- a/drivers/gpu/drm/imagination/pvr_drv.c +++ b/drivers/gpu/drm/imagination/pvr_drv.c @@ -515,7 +515,8 @@ copy_out: if (err < 0) return err; - args->size = sizeof(query); + if (args->size > sizeof(query)) + args->size = sizeof(query); return 0; } @@ -596,7 +597,8 @@ copy_out: if (err < 0) return err; - args->size = sizeof(query); + if (args->size > sizeof(query)) + args->size = sizeof(query); return 0; } @@ -1255,14 +1257,13 @@ pvr_set_uobj_array(const struct drm_pvr_obj_array *out, u32 min_stride, u32 obj_ if (copy_to_user(out_ptr, in_ptr, cpy_elem_size)) return -EFAULT; - out_ptr += obj_size; - in_ptr += out->stride; - } + if (out->stride > obj_size && + clear_user(out_ptr + cpy_elem_size, out->stride - obj_size)) { + return -EFAULT; + } - if (out->stride > obj_size && - clear_user(u64_to_user_ptr(out->array + obj_size), - out->stride - obj_size)) { - return -EFAULT; + out_ptr += out->stride; + in_ptr += obj_size; } } diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c index 7ed60e1c1a86..941c017399fc 100644 --- a/drivers/gpu/drm/imagination/pvr_queue.c +++ b/drivers/gpu/drm/imagination/pvr_queue.c @@ -1439,11 +1439,12 @@ void pvr_queue_kill(struct pvr_queue *queue) /** * pvr_queue_destroy() - Destroy a queue. * @queue: The queue to destroy. + * @cleanup_queue_entity: Whether to cleanup the queue entity. * * Cleanup the queue and free the resources attached to it. Should be * called from the context release function. */ -void pvr_queue_destroy(struct pvr_queue *queue) +void pvr_queue_destroy(struct pvr_queue *queue, bool cleanup_queue_entity) { if (!queue) return; @@ -1453,7 +1454,8 @@ void pvr_queue_destroy(struct pvr_queue *queue) mutex_unlock(&queue->ctx->pvr_dev->queues.lock); drm_sched_fini(&queue->scheduler); - drm_sched_entity_fini(&queue->entity); + if (cleanup_queue_entity) + drm_sched_entity_fini(&queue->entity); if (WARN_ON(queue->last_queued_job_scheduled_fence)) dma_fence_put(queue->last_queued_job_scheduled_fence); diff --git a/drivers/gpu/drm/imagination/pvr_queue.h b/drivers/gpu/drm/imagination/pvr_queue.h index 4aa72665ce25..149cc6d124bf 100644 --- a/drivers/gpu/drm/imagination/pvr_queue.h +++ b/drivers/gpu/drm/imagination/pvr_queue.h @@ -158,7 +158,7 @@ struct pvr_queue *pvr_queue_create(struct pvr_context *ctx, void pvr_queue_kill(struct pvr_queue *queue); -void pvr_queue_destroy(struct pvr_queue *queue); +void pvr_queue_destroy(struct pvr_queue *queue, bool cleanup_queue_entity); void pvr_queue_process(struct pvr_queue *queue); diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c index e1ec60f34b6e..396d349fb6ce 100644 --- a/drivers/gpu/drm/imagination/pvr_vm.c +++ b/drivers/gpu/drm/imagination/pvr_vm.c @@ -1019,7 +1019,8 @@ copy_out: if (err < 0) return err; - args->size = sizeof(query); + if (args->size > sizeof(query)) + args->size = sizeof(query); return 0; } @@ -1069,7 +1070,8 @@ copy_out: if (err < 0) return err; - args->size = sizeof(query); + if (args->size > sizeof(query)) + args->size = sizeof(query); return 0; } diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c index bd417d6ae8c0..0b25abebb803 100644 --- a/drivers/gpu/drm/panthor/panthor_device.c +++ b/drivers/gpu/drm/panthor/panthor_device.c @@ -207,6 +207,7 @@ int panthor_device_init(struct panthor_device *ptdev) *dummy_page_virt = 1; INIT_WORK(&ptdev->reset.work, panthor_device_reset_work); + disable_work(&ptdev->reset.work); ptdev->reset.wq = alloc_ordered_workqueue("panthor-reset-wq", 0); if (!ptdev->reset.wq) return -ENOMEM; @@ -285,6 +286,9 @@ int panthor_device_init(struct panthor_device *ptdev) panthor_gem_init(ptdev); + /* Now that everything is initialized, we can enable the reset work. */ + enable_work(&ptdev->reset.work); + /* ~3 frames */ pm_runtime_set_autosuspend_delay(ptdev->base.dev, 50); pm_runtime_use_autosuspend(ptdev->base.dev); diff --git a/drivers/gpu/drm/panthor/panthor_device.h b/drivers/gpu/drm/panthor/panthor_device.h index a412a50eec76..98828e81db0b 100644 --- a/drivers/gpu/drm/panthor/panthor_device.h +++ b/drivers/gpu/drm/panthor/panthor_device.h @@ -509,9 +509,6 @@ static irqreturn_t panthor_ ## __name ## _irq_raw_handler(int irq, void *data) struct panthor_irq *pirq = data; \ enum panthor_irq_state old_state; \ \ - if (!gpu_read(pirq->iomem, INT_STAT)) \ - return IRQ_NONE; \ - \ guard(spinlock_irqsave)(&pirq->mask_lock); \ old_state = atomic_cmpxchg(&pirq->state, \ PANTHOR_IRQ_STATE_ACTIVE, \ @@ -519,6 +516,13 @@ static irqreturn_t panthor_ ## __name ## _irq_raw_handler(int irq, void *data) if (old_state != PANTHOR_IRQ_STATE_ACTIVE) \ return IRQ_NONE; \ \ + if (!gpu_read(pirq->iomem, INT_STAT)) { \ + atomic_cmpxchg(&pirq->state, \ + PANTHOR_IRQ_STATE_PROCESSING, \ + PANTHOR_IRQ_STATE_ACTIVE); \ + return IRQ_NONE; \ + } \ + \ gpu_write(pirq->iomem, INT_MASK, 0); \ return IRQ_WAKE_THREAD; \ } \ @@ -581,14 +585,15 @@ static inline void panthor_ ## __name ## _irq_resume(struct panthor_irq *pirq) \ static int panthor_request_ ## __name ## _irq(struct panthor_device *ptdev, \ struct panthor_irq *pirq, \ - int irq, u32 mask, void __iomem *iomem) \ + int irq, void __iomem *iomem) \ { \ pirq->ptdev = ptdev; \ pirq->irq = irq; \ - pirq->mask = mask; \ + pirq->mask = 0; \ pirq->iomem = iomem; \ spin_lock_init(&pirq->mask_lock); \ - panthor_ ## __name ## _irq_resume(pirq); \ + atomic_set(&pirq->state, PANTHOR_IRQ_STATE_SUSPENDED); \ + gpu_write(pirq->iomem, INT_MASK, 0); \ \ return devm_request_threaded_irq(ptdev->base.dev, irq, \ panthor_ ## __name ## _irq_raw_handler, \ diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c index 986151681b24..de8e6689a869 100644 --- a/drivers/gpu/drm/panthor/panthor_fw.c +++ b/drivers/gpu/drm/panthor/panthor_fw.c @@ -1279,9 +1279,7 @@ void panthor_fw_unplug(struct panthor_device *ptdev) if (!IS_ENABLED(CONFIG_PM) || pm_runtime_active(ptdev->base.dev)) { /* Make sure the IRQ handler cannot be called after that point. */ - if (ptdev->fw->irq.irq) - panthor_job_irq_suspend(&ptdev->fw->irq); - + panthor_job_irq_suspend(&ptdev->fw->irq); panthor_fw_stop(ptdev); } @@ -1476,7 +1474,7 @@ int panthor_fw_init(struct panthor_device *ptdev) if (irq <= 0) return -ENODEV; - ret = panthor_request_job_irq(ptdev, &fw->irq, irq, 0, + ret = panthor_request_job_irq(ptdev, &fw->irq, irq, ptdev->iomem + JOB_INT_BASE); if (ret) { drm_err(&ptdev->base, "failed to request job irq"); diff --git a/drivers/gpu/drm/panthor/panthor_gpu.c b/drivers/gpu/drm/panthor/panthor_gpu.c index e52c5675981f..c013d6bf9a59 100644 --- a/drivers/gpu/drm/panthor/panthor_gpu.c +++ b/drivers/gpu/drm/panthor/panthor_gpu.c @@ -170,11 +170,12 @@ int panthor_gpu_init(struct panthor_device *ptdev) return irq; ret = panthor_request_gpu_irq(ptdev, &ptdev->gpu->irq, irq, - GPU_INTERRUPTS_MASK, ptdev->iomem + GPU_INT_BASE); if (ret) return ret; + panthor_gpu_irq_enable_events(&ptdev->gpu->irq, GPU_INTERRUPTS_MASK); + panthor_gpu_irq_resume(&ptdev->gpu->irq); return 0; } diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c index dab6840e8857..e592a8ebb478 100644 --- a/drivers/gpu/drm/panthor/panthor_mmu.c +++ b/drivers/gpu/drm/panthor/panthor_mmu.c @@ -3262,7 +3262,6 @@ int panthor_mmu_init(struct panthor_device *ptdev) return -ENODEV; ret = panthor_request_mmu_irq(ptdev, &mmu->irq, irq, - panthor_mmu_fault_mask(ptdev, ~0), ptdev->iomem + MMU_INT_BASE); if (ret) return ret; @@ -3280,7 +3279,13 @@ int panthor_mmu_init(struct panthor_device *ptdev) ptdev->gpu_info.mmu_features |= BITS_PER_LONG; } - return drmm_add_action_or_reset(&ptdev->base, panthor_mmu_release_wq, mmu->vm.wq); + ret = drmm_add_action_or_reset(&ptdev->base, panthor_mmu_release_wq, mmu->vm.wq); + if (ret) + return ret; + + panthor_mmu_irq_enable_events(&mmu->irq, panthor_mmu_fault_mask(ptdev, ~0)); + panthor_mmu_irq_resume(&mmu->irq); + return 0; } #ifdef CONFIG_DEBUG_FS diff --git a/drivers/gpu/drm/panthor/panthor_pwr.c b/drivers/gpu/drm/panthor/panthor_pwr.c index 7c7f424a1436..f2c2c3000590 100644 --- a/drivers/gpu/drm/panthor/panthor_pwr.c +++ b/drivers/gpu/drm/panthor/panthor_pwr.c @@ -453,7 +453,8 @@ void panthor_pwr_unplug(struct panthor_device *ptdev) return; /* Make sure the IRQ handler is not running after that point. */ - panthor_pwr_irq_suspend(&ptdev->pwr->irq); + if (!IS_ENABLED(CONFIG_PM) || pm_runtime_active(ptdev->base.dev)) + panthor_pwr_irq_suspend(&ptdev->pwr->irq); /* Wake-up all waiters. */ spin_lock_irqsave(&ptdev->pwr->reqs_lock, flags); @@ -483,12 +484,13 @@ int panthor_pwr_init(struct panthor_device *ptdev) if (irq < 0) return irq; - err = panthor_request_pwr_irq( - ptdev, &pwr->irq, irq, PWR_INTERRUPTS_MASK, - pwr->iomem + PWR_INT_BASE); + err = panthor_request_pwr_irq(ptdev, &pwr->irq, irq, + pwr->iomem + PWR_INT_BASE); if (err) return err; + panthor_pwr_irq_enable_events(&pwr->irq, PWR_INTERRUPTS_MASK); + panthor_pwr_irq_resume(&pwr->irq); return 0; } diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c index 5b34032deff8..298b046c95ed 100644 --- a/drivers/gpu/drm/panthor/panthor_sched.c +++ b/drivers/gpu/drm/panthor/panthor_sched.c @@ -1057,7 +1057,8 @@ group_unbind_locked(struct panthor_group *group) /* Tiler OOM events will be re-issued next time the group is scheduled. */ atomic_set(&group->tiler_oom, 0); - cancel_work(&group->tiler_oom_work); + if (cancel_work(&group->tiler_oom_work)) + group_put(group); for (u32 i = 0; i < group->queue_count; i++) group->queues[i]->doorbell_id = -1; @@ -1151,15 +1152,14 @@ queue_suspend_timeout_locked(struct panthor_queue *queue) static void queue_suspend_timeout(struct panthor_queue *queue) { - spin_lock(&queue->fence_ctx.lock); + guard(spinlock_irqsave)(&queue->fence_ctx.lock); queue_suspend_timeout_locked(queue); - spin_unlock(&queue->fence_ctx.lock); } static void queue_resume_timeout(struct panthor_queue *queue) { - spin_lock(&queue->fence_ctx.lock); + guard(spinlock_irqsave)(&queue->fence_ctx.lock); if (queue_timeout_is_suspended(queue)) { mod_delayed_work(queue->scheduler.timeout_wq, @@ -1168,8 +1168,6 @@ queue_resume_timeout(struct panthor_queue *queue) queue->timeout.remaining = MAX_SCHEDULE_TIMEOUT; } - - spin_unlock(&queue->fence_ctx.lock); } /** @@ -1542,7 +1540,7 @@ cs_slot_process_fault_event_locked(struct panthor_device *ptdev, u64 cs_extract = queue->iface.output->extract; struct panthor_job *job; - spin_lock(&queue->fence_ctx.lock); + guard(spinlock_irqsave)(&queue->fence_ctx.lock); list_for_each_entry(job, &queue->fence_ctx.in_flight_jobs, node) { if (cs_extract >= job->ringbuf.end) continue; @@ -1552,7 +1550,6 @@ cs_slot_process_fault_event_locked(struct panthor_device *ptdev, dma_fence_set_error(job->done_fence, -EINVAL); } - spin_unlock(&queue->fence_ctx.lock); } if (group) { @@ -1604,7 +1601,10 @@ static int group_process_tiler_oom(struct panthor_group *group, u32 cs_id) if (unlikely(csg_id < 0)) return 0; - if (IS_ERR(heaps) || frag_end > vt_end || vt_end >= vt_start) { + if (IS_ERR(heaps)) { + ret = -EINVAL; + heaps = NULL; + } else if (frag_end > vt_end || vt_end >= vt_start) { ret = -EINVAL; } else { /* We do the allocation without holding the scheduler lock to avoid @@ -2183,13 +2183,13 @@ group_term_post_processing(struct panthor_group *group) if (!queue) continue; - spin_lock(&queue->fence_ctx.lock); - list_for_each_entry_safe(job, tmp, &queue->fence_ctx.in_flight_jobs, node) { - list_move_tail(&job->node, &faulty_jobs); - dma_fence_set_error(job->done_fence, err); - dma_fence_signal_locked(job->done_fence); + scoped_guard(spinlock_irqsave, &queue->fence_ctx.lock) { + list_for_each_entry_safe(job, tmp, &queue->fence_ctx.in_flight_jobs, node) { + list_move_tail(&job->node, &faulty_jobs); + dma_fence_set_error(job->done_fence, err); + dma_fence_signal_locked(job->done_fence); + } } - spin_unlock(&queue->fence_ctx.lock); /* Manually update the syncobj seqno to unblock waiters. */ syncobj = group->syncobjs->kmap + (i * sizeof(*syncobj)); @@ -2368,7 +2368,13 @@ tick_ctx_apply(struct panthor_scheduler *sched, struct panthor_sched_tick_ctx *c csg_iface = panthor_fw_get_csg_iface(ptdev, csg_id); csg_slot = &sched->csg_slots[csg_id]; - group_bind_locked(group, csg_id); + ret = group_bind_locked(group, csg_id); + if (ret) { + panthor_device_schedule_reset(ptdev); + ctx->csg_upd_failed_mask |= BIT(csg_id); + return; + } + csg_slot_prog_locked(ptdev, csg_id, new_csg_prio--); csgs_upd_ctx_queue_reqs(ptdev, &upd_ctx, csg_id, group->state == PANTHOR_CS_GROUP_SUSPENDED ? @@ -2668,7 +2674,14 @@ static void sched_resume_tick(struct panthor_device *ptdev) else delay_jiffies = 0; - sched_queue_delayed_work(sched, tick, delay_jiffies); + /* We schedule immediate ticks when we need to process events on CSGs, + * but those don't change the resched_target because we want the other + * groups to stay scheduled for the remaining of the GPU timeslot they + * were given. Make sure those immediate ticks don't get overruled by + * a sched_queue_delayed_work() that would delay the tick execution. + */ + if (!delayed_work_pending(&sched->tick_work)) + sched_queue_delayed_work(sched, tick, delay_jiffies); } static void group_schedule_locked(struct panthor_group *group, u32 queue_mask) @@ -3049,39 +3062,39 @@ static bool queue_check_job_completion(struct panthor_queue *queue) LIST_HEAD(done_jobs); cookie = dma_fence_begin_signalling(); - spin_lock(&queue->fence_ctx.lock); - list_for_each_entry_safe(job, job_tmp, &queue->fence_ctx.in_flight_jobs, node) { - if (!syncobj) { - struct panthor_group *group = job->group; + scoped_guard(spinlock_irqsave, &queue->fence_ctx.lock) { + list_for_each_entry_safe(job, job_tmp, &queue->fence_ctx.in_flight_jobs, node) { + if (!syncobj) { + struct panthor_group *group = job->group; - syncobj = group->syncobjs->kmap + - (job->queue_idx * sizeof(*syncobj)); - } + syncobj = group->syncobjs->kmap + + (job->queue_idx * sizeof(*syncobj)); + } - if (syncobj->seqno < job->done_fence->seqno) - break; + if (syncobj->seqno < job->done_fence->seqno) + break; - list_move_tail(&job->node, &done_jobs); - dma_fence_signal_locked(job->done_fence); - } + list_move_tail(&job->node, &done_jobs); + dma_fence_signal_locked(job->done_fence); + } - if (list_empty(&queue->fence_ctx.in_flight_jobs)) { - /* If we have no job left, we cancel the timer, and reset remaining - * time to its default so it can be restarted next time - * queue_resume_timeout() is called. - */ - queue_suspend_timeout_locked(queue); + if (list_empty(&queue->fence_ctx.in_flight_jobs)) { + /* If we have no job left, we cancel the timer, and reset remaining + * time to its default so it can be restarted next time + * queue_resume_timeout() is called. + */ + queue_suspend_timeout_locked(queue); - /* If there's no job pending, we consider it progress to avoid a - * spurious timeout if the timeout handler and the sync update - * handler raced. - */ - progress = true; - } else if (!list_empty(&done_jobs)) { - queue_reset_timeout_locked(queue); - progress = true; + /* If there's no job pending, we consider it progress to avoid a + * spurious timeout if the timeout handler and the sync update + * handler raced. + */ + progress = true; + } else if (!list_empty(&done_jobs)) { + queue_reset_timeout_locked(queue); + progress = true; + } } - spin_unlock(&queue->fence_ctx.lock); dma_fence_end_signalling(cookie); list_for_each_entry_safe(job, job_tmp, &done_jobs, node) { @@ -3346,9 +3359,8 @@ queue_run_job(struct drm_sched_job *sched_job) job->ringbuf.end = job->ringbuf.start + (instrs.count * sizeof(u64)); panthor_job_get(&job->base); - spin_lock(&queue->fence_ctx.lock); - list_add_tail(&job->node, &queue->fence_ctx.in_flight_jobs); - spin_unlock(&queue->fence_ctx.lock); + scoped_guard(spinlock_irqsave, &queue->fence_ctx.lock) + list_add_tail(&job->node, &queue->fence_ctx.in_flight_jobs); /* Make sure the ring buffer is updated before the INSERT * register. diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index 67865810a2e7..c8b9475a7472 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -897,7 +897,8 @@ static int virtio_get_edid_block(void *data, u8 *buf, struct virtio_gpu_resp_edid *resp = data; size_t start = block * EDID_LENGTH; - if (start + len > le32_to_cpu(resp->size)) + if (start + len > le32_to_cpu(resp->size) || + start + len > sizeof(resp->edid)) return -EINVAL; memcpy(buf, resp->edid + start, len); return 0; diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h index 8c2d77a032f0..ab16c1be3900 100644 --- a/include/drm/display/drm_dp_helper.h +++ b/include/drm/display/drm_dp_helper.h @@ -115,6 +115,7 @@ struct drm_dp_vsc_sdp { * @duration_decr_ms: Successive frame duration decrease * @target_rr_divider: Target refresh rate divider * @mode: Adaptive Sync Operation Mode + * @coasting_vtotal: Coasting vtotal */ struct drm_dp_as_sdp { unsigned char sdp_type; diff --git a/include/drm/drm_fixed.h b/include/drm/drm_fixed.h index 33de514a5221..21d822aeed55 100644 --- a/include/drm/drm_fixed.h +++ b/include/drm/drm_fixed.h @@ -79,7 +79,8 @@ static inline u32 dfixed_div(fixed20_12 A, fixed20_12 B) #define DRM_FIXED_ALMOST_ONE (DRM_FIXED_ONE - DRM_FIXED_EPSILON) /** - * @drm_sm2fixp + * drm_sm2fixp() - convert signed-magnitude to fixed point + * @a: 1.31.32 signed-magnitude fixed point * * Convert a 1.31.32 signed-magnitude fixed point to 32.32 * 2s-complement fixed point diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h index f2a787bc4f64..0beede3ddc4e 100644 --- a/include/drm/drm_ras.h +++ b/include/drm/drm_ras.h @@ -6,6 +6,8 @@ #ifndef __DRM_RAS_H__ #define __DRM_RAS_H__ +#include <linux/types.h> + #include <uapi/drm/drm_ras.h> /** |