diff options
Diffstat (limited to 'drivers/gpu/drm/v3d')
| -rw-r--r-- | drivers/gpu/drm/v3d/Kconfig | 1 | ||||
| -rw-r--r-- | drivers/gpu/drm/v3d/v3d_bo.c | 314 | ||||
| -rw-r--r-- | drivers/gpu/drm/v3d/v3d_debugfs.c | 8 | ||||
| -rw-r--r-- | drivers/gpu/drm/v3d/v3d_drv.c | 63 | ||||
| -rw-r--r-- | drivers/gpu/drm/v3d/v3d_drv.h | 33 | ||||
| -rw-r--r-- | drivers/gpu/drm/v3d/v3d_gem.c | 104 | ||||
| -rw-r--r-- | drivers/gpu/drm/v3d/v3d_irq.c | 58 | ||||
| -rw-r--r-- | drivers/gpu/drm/v3d/v3d_mmu.c | 11 | ||||
| -rw-r--r-- | drivers/gpu/drm/v3d/v3d_regs.h | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/v3d/v3d_sched.c | 13 |
10 files changed, 218 insertions, 389 deletions
diff --git a/drivers/gpu/drm/v3d/Kconfig b/drivers/gpu/drm/v3d/Kconfig index 1552bf552c94..75a74c45f109 100644 --- a/drivers/gpu/drm/v3d/Kconfig +++ b/drivers/gpu/drm/v3d/Kconfig @@ -5,6 +5,7 @@ config DRM_V3D depends on COMMON_CLK depends on MMU select DRM_SCHED + select DRM_GEM_SHMEM_HELPER help Choose this option if you have a system that has a Broadcom V3D 3.x or newer GPU, such as BCM7268. diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c index a08766d39eab..c0219ebb4284 100644 --- a/drivers/gpu/drm/v3d/v3d_bo.c +++ b/drivers/gpu/drm/v3d/v3d_bo.c @@ -25,162 +25,6 @@ #include "v3d_drv.h" #include "uapi/drm/v3d_drm.h" -/* Pins the shmem pages, fills in the .pages and .sgt fields of the BO, and maps - * it for DMA. - */ -static int -v3d_bo_get_pages(struct v3d_bo *bo) -{ - struct drm_gem_object *obj = &bo->base; - struct drm_device *dev = obj->dev; - int npages = obj->size >> PAGE_SHIFT; - int ret = 0; - - mutex_lock(&bo->lock); - if (bo->pages_refcount++ != 0) - goto unlock; - - if (!obj->import_attach) { - bo->pages = drm_gem_get_pages(obj); - if (IS_ERR(bo->pages)) { - ret = PTR_ERR(bo->pages); - goto unlock; - } - - bo->sgt = drm_prime_pages_to_sg(bo->pages, npages); - if (IS_ERR(bo->sgt)) { - ret = PTR_ERR(bo->sgt); - goto put_pages; - } - - /* Map the pages for use by the GPU. */ - dma_map_sg(dev->dev, bo->sgt->sgl, - bo->sgt->nents, DMA_BIDIRECTIONAL); - } else { - bo->pages = kcalloc(npages, sizeof(*bo->pages), GFP_KERNEL); - if (!bo->pages) - goto put_pages; - - drm_prime_sg_to_page_addr_arrays(bo->sgt, bo->pages, - NULL, npages); - - /* Note that dma-bufs come in mapped. */ - } - - mutex_unlock(&bo->lock); - - return 0; - -put_pages: - drm_gem_put_pages(obj, bo->pages, true, true); - bo->pages = NULL; -unlock: - bo->pages_refcount--; - mutex_unlock(&bo->lock); - return ret; -} - -static void -v3d_bo_put_pages(struct v3d_bo *bo) -{ - struct drm_gem_object *obj = &bo->base; - - mutex_lock(&bo->lock); - if (--bo->pages_refcount == 0) { - if (!obj->import_attach) { - dma_unmap_sg(obj->dev->dev, bo->sgt->sgl, - bo->sgt->nents, DMA_BIDIRECTIONAL); - sg_free_table(bo->sgt); - kfree(bo->sgt); - drm_gem_put_pages(obj, bo->pages, true, true); - } else { - kfree(bo->pages); - } - } - mutex_unlock(&bo->lock); -} - -static struct v3d_bo *v3d_bo_create_struct(struct drm_device *dev, - size_t unaligned_size) -{ - struct v3d_dev *v3d = to_v3d_dev(dev); - struct drm_gem_object *obj; - struct v3d_bo *bo; - size_t size = roundup(unaligned_size, PAGE_SIZE); - int ret; - - if (size == 0) - return ERR_PTR(-EINVAL); - - bo = kzalloc(sizeof(*bo), GFP_KERNEL); - if (!bo) - return ERR_PTR(-ENOMEM); - obj = &bo->base; - - INIT_LIST_HEAD(&bo->vmas); - INIT_LIST_HEAD(&bo->unref_head); - mutex_init(&bo->lock); - - ret = drm_gem_object_init(dev, obj, size); - if (ret) - goto free_bo; - - spin_lock(&v3d->mm_lock); - ret = drm_mm_insert_node_generic(&v3d->mm, &bo->node, - obj->size >> PAGE_SHIFT, - GMP_GRANULARITY >> PAGE_SHIFT, 0, 0); - spin_unlock(&v3d->mm_lock); - if (ret) - goto free_obj; - - return bo; - -free_obj: - drm_gem_object_release(obj); -free_bo: - kfree(bo); - return ERR_PTR(ret); -} - -struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv, - size_t unaligned_size) -{ - struct v3d_dev *v3d = to_v3d_dev(dev); - struct drm_gem_object *obj; - struct v3d_bo *bo; - int ret; - - bo = v3d_bo_create_struct(dev, unaligned_size); - if (IS_ERR(bo)) - return bo; - obj = &bo->base; - - bo->resv = &bo->_resv; - reservation_object_init(bo->resv); - - ret = v3d_bo_get_pages(bo); - if (ret) - goto free_mm; - - v3d_mmu_insert_ptes(bo); - - mutex_lock(&v3d->bo_lock); - v3d->bo_stats.num_allocated++; - v3d->bo_stats.pages_allocated += obj->size >> PAGE_SHIFT; - mutex_unlock(&v3d->bo_lock); - - return bo; - -free_mm: - spin_lock(&v3d->mm_lock); - drm_mm_remove_node(&bo->node); - spin_unlock(&v3d->mm_lock); - - drm_gem_object_release(obj); - kfree(bo); - return ERR_PTR(ret); -} - /* Called DRM core on the last userspace/kernel unreference of the * BO. */ @@ -189,92 +33,116 @@ void v3d_free_object(struct drm_gem_object *obj) struct v3d_dev *v3d = to_v3d_dev(obj->dev); struct v3d_bo *bo = to_v3d_bo(obj); + v3d_mmu_remove_ptes(bo); + mutex_lock(&v3d->bo_lock); v3d->bo_stats.num_allocated--; v3d->bo_stats.pages_allocated -= obj->size >> PAGE_SHIFT; mutex_unlock(&v3d->bo_lock); - reservation_object_fini(&bo->_resv); - - v3d_bo_put_pages(bo); - - if (obj->import_attach) - drm_prime_gem_destroy(obj, bo->sgt); - - v3d_mmu_remove_ptes(bo); spin_lock(&v3d->mm_lock); drm_mm_remove_node(&bo->node); spin_unlock(&v3d->mm_lock); - mutex_destroy(&bo->lock); + /* GPU execution may have dirtied any pages in the BO. */ + bo->base.pages_mark_dirty_on_put = true; - drm_gem_object_release(obj); - kfree(bo); + drm_gem_shmem_free_object(obj); } -struct reservation_object *v3d_prime_res_obj(struct drm_gem_object *obj) +static const struct drm_gem_object_funcs v3d_gem_funcs = { + .free = v3d_free_object, + .print_info = drm_gem_shmem_print_info, + .pin = drm_gem_shmem_pin, + .unpin = drm_gem_shmem_unpin, + .get_sg_table = drm_gem_shmem_get_sg_table, + .vmap = drm_gem_shmem_vmap, + .vunmap = drm_gem_shmem_vunmap, + .vm_ops = &drm_gem_shmem_vm_ops, +}; + +/* gem_create_object function for allocating a BO struct and doing + * early setup. + */ +struct drm_gem_object *v3d_create_object(struct drm_device *dev, size_t size) { - struct v3d_bo *bo = to_v3d_bo(obj); + struct v3d_bo *bo; + struct drm_gem_object *obj; - return bo->resv; -} + if (size == 0) + return NULL; -static void -v3d_set_mmap_vma_flags(struct vm_area_struct *vma) -{ - vma->vm_flags &= ~VM_PFNMAP; - vma->vm_flags |= VM_MIXEDMAP; - vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); -} + bo = kzalloc(sizeof(*bo), GFP_KERNEL); + if (!bo) + return NULL; + obj = &bo->base.base; -vm_fault_t v3d_gem_fault(struct vm_fault *vmf) -{ - struct vm_area_struct *vma = vmf->vma; - struct drm_gem_object *obj = vma->vm_private_data; - struct v3d_bo *bo = to_v3d_bo(obj); - pfn_t pfn; - pgoff_t pgoff; + obj->funcs = &v3d_gem_funcs; - /* We don't use vmf->pgoff since that has the fake offset: */ - pgoff = (vmf->address - vma->vm_start) >> PAGE_SHIFT; - pfn = __pfn_to_pfn_t(page_to_pfn(bo->pages[pgoff]), PFN_DEV); + INIT_LIST_HEAD(&bo->unref_head); - return vmf_insert_mixed(vma, vmf->address, pfn); + return &bo->base.base; } -int v3d_mmap(struct file *filp, struct vm_area_struct *vma) +static int +v3d_bo_create_finish(struct drm_gem_object *obj) { + struct v3d_dev *v3d = to_v3d_dev(obj->dev); + struct v3d_bo *bo = to_v3d_bo(obj); + struct sg_table *sgt; int ret; - ret = drm_gem_mmap(filp, vma); + /* So far we pin the BO in the MMU for its lifetime, so use + * shmem's helper for getting a lifetime sgt. + */ + sgt = drm_gem_shmem_get_pages_sgt(&bo->base.base); + if (IS_ERR(sgt)) + return PTR_ERR(sgt); + + spin_lock(&v3d->mm_lock); + /* Allocate the object's space in the GPU's page tables. + * Inserting PTEs will happen later, but the offset is for the + * lifetime of the BO. + */ + ret = drm_mm_insert_node_generic(&v3d->mm, &bo->node, + obj->size >> PAGE_SHIFT, + GMP_GRANULARITY >> PAGE_SHIFT, 0, 0); + spin_unlock(&v3d->mm_lock); if (ret) return ret; - v3d_set_mmap_vma_flags(vma); + /* Track stats for /debug/dri/n/bo_stats. */ + mutex_lock(&v3d->bo_lock); + v3d->bo_stats.num_allocated++; + v3d->bo_stats.pages_allocated += obj->size >> PAGE_SHIFT; + mutex_unlock(&v3d->bo_lock); - return ret; + v3d_mmu_insert_ptes(bo); + + return 0; } -int v3d_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) +struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv, + size_t unaligned_size) { + struct drm_gem_shmem_object *shmem_obj; + struct v3d_bo *bo; int ret; - ret = drm_gem_mmap_obj(obj, obj->size, vma); - if (ret < 0) - return ret; - - v3d_set_mmap_vma_flags(vma); + shmem_obj = drm_gem_shmem_create(dev, unaligned_size); + if (!shmem_obj) + return NULL; + bo = to_v3d_bo(&shmem_obj->base); - return 0; -} + ret = v3d_bo_create_finish(&shmem_obj->base); + if (ret) + goto free_obj; -struct sg_table * -v3d_prime_get_sg_table(struct drm_gem_object *obj) -{ - struct v3d_bo *bo = to_v3d_bo(obj); - int npages = obj->size >> PAGE_SHIFT; + return bo; - return drm_prime_pages_to_sg(bo->pages, npages); +free_obj: + drm_gem_shmem_free_object(&shmem_obj->base); + return ERR_PTR(ret); } struct drm_gem_object * @@ -283,20 +151,17 @@ v3d_prime_import_sg_table(struct drm_device *dev, struct sg_table *sgt) { struct drm_gem_object *obj; - struct v3d_bo *bo; - - bo = v3d_bo_create_struct(dev, attach->dmabuf->size); - if (IS_ERR(bo)) - return ERR_CAST(bo); - obj = &bo->base; - - bo->resv = attach->dmabuf->resv; + int ret; - bo->sgt = sgt; - obj->import_attach = attach; - v3d_bo_get_pages(bo); + obj = drm_gem_shmem_prime_import_sg_table(dev, attach, sgt); + if (IS_ERR(obj)) + return obj; - v3d_mmu_insert_ptes(bo); + ret = v3d_bo_create_finish(obj); + if (ret) { + drm_gem_shmem_free_object(obj); + return ERR_PTR(ret); + } return obj; } @@ -319,8 +184,8 @@ int v3d_create_bo_ioctl(struct drm_device *dev, void *data, args->offset = bo->node.start << PAGE_SHIFT; - ret = drm_gem_handle_create(file_priv, &bo->base, &args->handle); - drm_gem_object_put_unlocked(&bo->base); + ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle); + drm_gem_object_put_unlocked(&bo->base.base); return ret; } @@ -330,7 +195,6 @@ int v3d_mmap_bo_ioctl(struct drm_device *dev, void *data, { struct drm_v3d_mmap_bo *args = data; struct drm_gem_object *gem_obj; - int ret; if (args->flags != 0) { DRM_INFO("unknown mmap_bo flags: %d\n", args->flags); @@ -343,12 +207,10 @@ int v3d_mmap_bo_ioctl(struct drm_device *dev, void *data, return -ENOENT; } - ret = drm_gem_create_mmap_offset(gem_obj); - if (ret == 0) - args->offset = drm_vma_node_offset_addr(&gem_obj->vma_node); + args->offset = drm_vma_node_offset_addr(&gem_obj->vma_node); drm_gem_object_put_unlocked(gem_obj); - return ret; + return 0; } int v3d_get_bo_offset_ioctl(struct drm_device *dev, void *data, diff --git a/drivers/gpu/drm/v3d/v3d_debugfs.c b/drivers/gpu/drm/v3d/v3d_debugfs.c index eb2b2d2f8553..a24af2d2f574 100644 --- a/drivers/gpu/drm/v3d/v3d_debugfs.c +++ b/drivers/gpu/drm/v3d/v3d_debugfs.c @@ -187,6 +187,11 @@ static int v3d_measure_clock(struct seq_file *m, void *unused) uint32_t cycles; int core = 0; int measure_ms = 1000; + int ret; + + ret = pm_runtime_get_sync(v3d->dev); + if (ret < 0) + return ret; if (v3d->ver >= 40) { V3D_CORE_WRITE(core, V3D_V4_PCTR_0_SRC_0_3, @@ -210,6 +215,9 @@ static int v3d_measure_clock(struct seq_file *m, void *unused) cycles / (measure_ms * 1000), (cycles / (measure_ms * 100)) % 10); + pm_runtime_mark_last_busy(v3d->dev); + pm_runtime_put_autosuspend(v3d->dev); + return 0; } diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index f0afcec72c34..d600628bb5c1 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -7,9 +7,9 @@ * This driver supports the Broadcom V3D 3.3 and 4.1 OpenGL ES GPUs. * For V3D 2.x support, see the VC4 driver. * - * Currently only single-core rendering using the binner and renderer - * is supported. The TFU (texture formatting unit) and V3D 4.x's CSD - * (compute shader dispatch) are not yet supported. + * Currently only single-core rendering using the binner and renderer, + * along with TFU (texture formatting unit) rendering is supported. + * V3D 4.x's CSD (compute shader dispatch) is not yet supported. */ #include <linux/clk.h> @@ -19,6 +19,7 @@ #include <linux/of_platform.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/reset.h> #include <drm/drm_fb_cma_helper.h> #include <drm/drm_fb_helper.h> @@ -160,17 +161,7 @@ v3d_postclose(struct drm_device *dev, struct drm_file *file) kfree(v3d_priv); } -static const struct file_operations v3d_drm_fops = { - .owner = THIS_MODULE, - .open = drm_open, - .release = drm_release, - .unlocked_ioctl = drm_ioctl, - .mmap = v3d_mmap, - .poll = drm_poll, - .read = drm_read, - .compat_ioctl = drm_compat_ioctl, - .llseek = noop_llseek, -}; +DEFINE_DRM_GEM_SHMEM_FOPS(v3d_drm_fops); /* DRM_AUTH is required on SUBMIT_CL for now, while we don't have GMP * protection between clients. Note that render nodes would be be @@ -188,12 +179,6 @@ static const struct drm_ioctl_desc v3d_drm_ioctls[] = { DRM_IOCTL_DEF_DRV(V3D_SUBMIT_TFU, v3d_submit_tfu_ioctl, DRM_RENDER_ALLOW | DRM_AUTH), }; -static const struct vm_operations_struct v3d_vm_ops = { - .fault = v3d_gem_fault, - .open = drm_gem_vm_open, - .close = drm_gem_vm_close, -}; - static struct drm_driver v3d_drm_driver = { .driver_features = (DRIVER_GEM | DRIVER_RENDER | @@ -207,17 +192,11 @@ static struct drm_driver v3d_drm_driver = { .debugfs_init = v3d_debugfs_init, #endif - .gem_free_object_unlocked = v3d_free_object, - .gem_vm_ops = &v3d_vm_ops, - + .gem_create_object = v3d_create_object, .prime_handle_to_fd = drm_gem_prime_handle_to_fd, .prime_fd_to_handle = drm_gem_prime_fd_to_handle, - .gem_prime_import = drm_gem_prime_import, - .gem_prime_export = drm_gem_prime_export, - .gem_prime_res_obj = v3d_prime_res_obj, - .gem_prime_get_sg_table = v3d_prime_get_sg_table, .gem_prime_import_sg_table = v3d_prime_import_sg_table, - .gem_prime_mmap = v3d_prime_mmap, + .gem_prime_mmap = drm_gem_prime_mmap, .ioctls = v3d_drm_ioctls, .num_ioctls = ARRAY_SIZE(v3d_drm_ioctls), @@ -265,10 +244,6 @@ static int v3d_platform_drm_probe(struct platform_device *pdev) v3d->pdev = pdev; drm = &v3d->drm; - ret = map_regs(v3d, &v3d->bridge_regs, "bridge"); - if (ret) - goto dev_free; - ret = map_regs(v3d, &v3d->hub_regs, "hub"); if (ret) goto dev_free; @@ -283,6 +258,22 @@ static int v3d_platform_drm_probe(struct platform_device *pdev) v3d->cores = V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_NCORES); WARN_ON(v3d->cores > 1); /* multicore not yet implemented */ + v3d->reset = devm_reset_control_get_exclusive(dev, NULL); + if (IS_ERR(v3d->reset)) { + ret = PTR_ERR(v3d->reset); + + if (ret == -EPROBE_DEFER) + goto dev_free; + + v3d->reset = NULL; + ret = map_regs(v3d, &v3d->bridge_regs, "bridge"); + if (ret) { + dev_err(dev, + "Failed to get reset control or bridge regs\n"); + goto dev_free; + } + } + if (v3d->ver < 41) { ret = map_regs(v3d, &v3d->gca_regs, "gca"); if (ret) @@ -312,14 +303,18 @@ static int v3d_platform_drm_probe(struct platform_device *pdev) if (ret) goto dev_destroy; - v3d_irq_init(v3d); + ret = v3d_irq_init(v3d); + if (ret) + goto gem_destroy; ret = drm_dev_register(drm, 0); if (ret) - goto gem_destroy; + goto irq_disable; return 0; +irq_disable: + v3d_irq_disable(v3d); gem_destroy: v3d_gem_destroy(drm); dev_destroy: diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index fdda3037f7af..7b0fe6240f7d 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0+ /* Copyright (C) 2015-2018 Broadcom */ -#include <linux/reservation.h> #include <linux/mm_types.h> #include <drm/drmP.h> #include <drm/drm_encoder.h> #include <drm/drm_gem.h> +#include <drm/drm_gem_shmem_helper.h> #include <drm/gpu_scheduler.h> #include "uapi/drm/v3d_drm.h" @@ -34,6 +34,7 @@ struct v3d_dev { * and revision. */ int ver; + bool single_irq_line; struct device *dev; struct platform_device *pdev; @@ -42,6 +43,7 @@ struct v3d_dev { void __iomem *bridge_regs; void __iomem *gca_regs; struct clk *clk; + struct reset_control *reset; /* Virtual and DMA addresses of the single shared page table. */ volatile u32 *pt; @@ -109,34 +111,15 @@ struct v3d_file_priv { struct drm_sched_entity sched_entity[V3D_MAX_QUEUES]; }; -/* Tracks a mapping of a BO into a per-fd address space */ -struct v3d_vma { - struct v3d_page_table *pt; - struct list_head list; /* entry in v3d_bo.vmas */ -}; - struct v3d_bo { - struct drm_gem_object base; - - struct mutex lock; + struct drm_gem_shmem_object base; struct drm_mm_node node; - u32 pages_refcount; - struct page **pages; - struct sg_table *sgt; - void *vaddr; - - struct list_head vmas; /* list of v3d_vma */ - /* List entry for the BO's position in * v3d_exec_info->unref_list */ struct list_head unref_head; - - /* normally (resv == &_resv) except for imported bo's */ - struct reservation_object *resv; - struct reservation_object _resv; }; static inline struct v3d_bo * @@ -270,6 +253,7 @@ static inline unsigned long nsecs_to_jiffies_timeout(const u64 n) } /* v3d_bo.c */ +struct drm_gem_object *v3d_create_object(struct drm_device *dev, size_t size); void v3d_free_object(struct drm_gem_object *gem_obj); struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv, size_t size); @@ -279,11 +263,6 @@ int v3d_mmap_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); int v3d_get_bo_offset_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); -vm_fault_t v3d_gem_fault(struct vm_fault *vmf); -int v3d_mmap(struct file *filp, struct vm_area_struct *vma); -struct reservation_object *v3d_prime_res_obj(struct drm_gem_object *obj); -int v3d_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma); -struct sg_table *v3d_prime_get_sg_table(struct drm_gem_object *obj); struct drm_gem_object *v3d_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sgt); @@ -310,7 +289,7 @@ void v3d_reset(struct v3d_dev *v3d); void v3d_invalidate_caches(struct v3d_dev *v3d); /* v3d_irq.c */ -void v3d_irq_init(struct v3d_dev *v3d); +int v3d_irq_init(struct v3d_dev *v3d); void v3d_irq_enable(struct v3d_dev *v3d); void v3d_irq_disable(struct v3d_dev *v3d); void v3d_irq_reset(struct v3d_dev *v3d); diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 803f31467ec1..b84d89c7b3fb 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -6,6 +6,7 @@ #include <linux/module.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/reset.h> #include <linux/device.h> #include <linux/io.h> #include <linux/sched/signal.h> @@ -24,7 +25,8 @@ v3d_init_core(struct v3d_dev *v3d, int core) * type. If you want the default behavior, you can still put * "2" in the indirect texture state's output_type field. */ - V3D_CORE_WRITE(core, V3D_CTL_MISCCFG, V3D_MISCCFG_OVRTMUOUT); + if (v3d->ver < 40) + V3D_CORE_WRITE(core, V3D_CTL_MISCCFG, V3D_MISCCFG_OVRTMUOUT); /* Whenever we flush the L2T cache, we always want to flush * the whole thing. @@ -69,7 +71,7 @@ v3d_idle_gca(struct v3d_dev *v3d) } static void -v3d_reset_v3d(struct v3d_dev *v3d) +v3d_reset_by_bridge(struct v3d_dev *v3d) { int version = V3D_BRIDGE_READ(V3D_TOP_GR_BRIDGE_REVISION); @@ -89,6 +91,15 @@ v3d_reset_v3d(struct v3d_dev *v3d) V3D_TOP_GR_BRIDGE_SW_INIT_1_V3D_CLK_108_SW_INIT); V3D_BRIDGE_WRITE(V3D_TOP_GR_BRIDGE_SW_INIT_1, 0); } +} + +static void +v3d_reset_v3d(struct v3d_dev *v3d) +{ + if (v3d->reset) + reset_control_reset(v3d->reset); + else + v3d_reset_by_bridge(v3d); v3d_init_hw_state(v3d); } @@ -190,7 +201,8 @@ v3d_attach_object_fences(struct v3d_bo **bos, int bo_count, for (i = 0; i < bo_count; i++) { /* XXX: Use shared fences for read-only objects. */ - reservation_object_add_excl_fence(bos[i]->resv, fence); + reservation_object_add_excl_fence(bos[i]->base.base.resv, + fence); } } @@ -199,12 +211,8 @@ v3d_unlock_bo_reservations(struct v3d_bo **bos, int bo_count, struct ww_acquire_ctx *acquire_ctx) { - int i; - - for (i = 0; i < bo_count; i++) - ww_mutex_unlock(&bos[i]->resv->lock); - - ww_acquire_fini(acquire_ctx); + drm_gem_unlock_reservations((struct drm_gem_object **)bos, bo_count, + acquire_ctx); } /* Takes the reservation lock on all the BOs being referenced, so that @@ -219,58 +227,19 @@ v3d_lock_bo_reservations(struct v3d_bo **bos, int bo_count, struct ww_acquire_ctx *acquire_ctx) { - int contended_lock = -1; int i, ret; - ww_acquire_init(acquire_ctx, &reservation_ww_class); - -retry: - if (contended_lock != -1) { - struct v3d_bo *bo = bos[contended_lock]; - - ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock, - acquire_ctx); - if (ret) { - ww_acquire_done(acquire_ctx); - return ret; - } - } - - for (i = 0; i < bo_count; i++) { - if (i == contended_lock) - continue; - - ret = ww_mutex_lock_interruptible(&bos[i]->resv->lock, - acquire_ctx); - if (ret) { - int j; - - for (j = 0; j < i; j++) - ww_mutex_unlock(&bos[j]->resv->lock); - - if (contended_lock != -1 && contended_lock >= i) { - struct v3d_bo *bo = bos[contended_lock]; - - ww_mutex_unlock(&bo->resv->lock); - } - - if (ret == -EDEADLK) { - contended_lock = i; - goto retry; - } - - ww_acquire_done(acquire_ctx); - return ret; - } - } - - ww_acquire_done(acquire_ctx); + ret = drm_gem_lock_reservations((struct drm_gem_object **)bos, + bo_count, acquire_ctx); + if (ret) + return ret; /* Reserve space for our shared (read-only) fence references, * before we commit the CL to the hardware. */ for (i = 0; i < bo_count; i++) { - ret = reservation_object_reserve_shared(bos[i]->resv, 1); + ret = reservation_object_reserve_shared(bos[i]->base.base.resv, + 1); if (ret) { v3d_unlock_bo_reservations(bos, bo_count, acquire_ctx); @@ -378,11 +347,11 @@ v3d_exec_cleanup(struct kref *ref) dma_fence_put(exec->render_done_fence); for (i = 0; i < exec->bo_count; i++) - drm_gem_object_put_unlocked(&exec->bo[i]->base); + drm_gem_object_put_unlocked(&exec->bo[i]->base.base); kvfree(exec->bo); list_for_each_entry_safe(bo, save, &exec->unref_list, unref_head) { - drm_gem_object_put_unlocked(&bo->base); + drm_gem_object_put_unlocked(&bo->base.base); } pm_runtime_mark_last_busy(v3d->dev); @@ -409,7 +378,7 @@ v3d_tfu_job_cleanup(struct kref *ref) for (i = 0; i < ARRAY_SIZE(job->bo); i++) { if (job->bo[i]) - drm_gem_object_put_unlocked(&job->bo[i]->base); + drm_gem_object_put_unlocked(&job->bo[i]->base.base); } pm_runtime_mark_last_busy(v3d->dev); @@ -429,8 +398,6 @@ v3d_wait_bo_ioctl(struct drm_device *dev, void *data, { int ret; struct drm_v3d_wait_bo *args = data; - struct drm_gem_object *gem_obj; - struct v3d_bo *bo; ktime_t start = ktime_get(); u64 delta_ns; unsigned long timeout_jiffies = @@ -439,21 +406,8 @@ v3d_wait_bo_ioctl(struct drm_device *dev, void *data, if (args->pad != 0) return -EINVAL; - gem_obj = drm_gem_object_lookup(file_priv, args->handle); - if (!gem_obj) { - DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle); - return -EINVAL; - } - bo = to_v3d_bo(gem_obj); - - ret = reservation_object_wait_timeout_rcu(bo->resv, - true, true, - timeout_jiffies); - - if (ret == 0) - ret = -ETIME; - else if (ret > 0) - ret = 0; + ret = drm_gem_reservation_object_wait(file_priv, args->handle, + true, timeout_jiffies); /* Decrement the user's timeout, in case we got interrupted * such that the ioctl will be restarted. @@ -468,8 +422,6 @@ v3d_wait_bo_ioctl(struct drm_device *dev, void *data, if (ret == -ETIME && args->timeout_ns) ret = -EAGAIN; - drm_gem_object_put_unlocked(gem_obj); - return ret; } diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c index 69338da70ddc..b4d6ae81186d 100644 --- a/drivers/gpu/drm/v3d/v3d_irq.c +++ b/drivers/gpu/drm/v3d/v3d_irq.c @@ -27,6 +27,9 @@ V3D_HUB_INT_MMU_CAP | \ V3D_HUB_INT_TFUC)) +static irqreturn_t +v3d_hub_irq(int irq, void *arg); + static void v3d_overflow_mem_work(struct work_struct *work) { @@ -34,12 +37,14 @@ v3d_overflow_mem_work(struct work_struct *work) container_of(work, struct v3d_dev, overflow_mem_work); struct drm_device *dev = &v3d->drm; struct v3d_bo *bo = v3d_bo_create(dev, NULL /* XXX: GMP */, 256 * 1024); + struct drm_gem_object *obj; unsigned long irqflags; if (IS_ERR(bo)) { DRM_ERROR("Couldn't allocate binner overflow mem\n"); return; } + obj = &bo->base.base; /* We lost a race, and our work task came in after the bin job * completed and exited. This can happen because the HW @@ -56,15 +61,15 @@ v3d_overflow_mem_work(struct work_struct *work) goto out; } - drm_gem_object_get(&bo->base); + drm_gem_object_get(obj); list_add_tail(&bo->unref_head, &v3d->bin_job->unref_list); spin_unlock_irqrestore(&v3d->job_lock, irqflags); V3D_CORE_WRITE(0, V3D_PTB_BPOA, bo->node.start << PAGE_SHIFT); - V3D_CORE_WRITE(0, V3D_PTB_BPOS, bo->base.size); + V3D_CORE_WRITE(0, V3D_PTB_BPOS, obj->size); out: - drm_gem_object_put_unlocked(&bo->base); + drm_gem_object_put_unlocked(obj); } static irqreturn_t @@ -112,6 +117,12 @@ v3d_irq(int irq, void *arg) if (intsts & V3D_INT_GMPV) dev_err(v3d->dev, "GMP violation\n"); + /* V3D 4.2 wires the hub and core IRQs together, so if we & + * didn't see the common one then check hub for MMU IRQs. + */ + if (v3d->single_irq_line && status == IRQ_NONE) + return v3d_hub_irq(irq, arg); + return status; } @@ -156,10 +167,10 @@ v3d_hub_irq(int irq, void *arg) return status; } -void +int v3d_irq_init(struct v3d_dev *v3d) { - int ret, core; + int irq1, ret, core; INIT_WORK(&v3d->overflow_mem_work, v3d_overflow_mem_work); @@ -170,16 +181,37 @@ v3d_irq_init(struct v3d_dev *v3d) V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS); V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS); - ret = devm_request_irq(v3d->dev, platform_get_irq(v3d->pdev, 0), - v3d_hub_irq, IRQF_SHARED, - "v3d_hub", v3d); - ret = devm_request_irq(v3d->dev, platform_get_irq(v3d->pdev, 1), - v3d_irq, IRQF_SHARED, - "v3d_core0", v3d); - if (ret) - dev_err(v3d->dev, "IRQ setup failed: %d\n", ret); + irq1 = platform_get_irq(v3d->pdev, 1); + if (irq1 == -EPROBE_DEFER) + return irq1; + if (irq1 > 0) { + ret = devm_request_irq(v3d->dev, irq1, + v3d_irq, IRQF_SHARED, + "v3d_core0", v3d); + if (ret) + goto fail; + ret = devm_request_irq(v3d->dev, platform_get_irq(v3d->pdev, 0), + v3d_hub_irq, IRQF_SHARED, + "v3d_hub", v3d); + if (ret) + goto fail; + } else { + v3d->single_irq_line = true; + + ret = devm_request_irq(v3d->dev, platform_get_irq(v3d->pdev, 0), + v3d_irq, IRQF_SHARED, + "v3d", v3d); + if (ret) + goto fail; + } v3d_irq_enable(v3d); + return 0; + +fail: + if (ret != -EPROBE_DEFER) + dev_err(v3d->dev, "IRQ setup failed: %d\n", ret); + return ret; } void diff --git a/drivers/gpu/drm/v3d/v3d_mmu.c b/drivers/gpu/drm/v3d/v3d_mmu.c index b00f97c31b70..7a21f1787ab1 100644 --- a/drivers/gpu/drm/v3d/v3d_mmu.c +++ b/drivers/gpu/drm/v3d/v3d_mmu.c @@ -83,13 +83,14 @@ int v3d_mmu_set_page_table(struct v3d_dev *v3d) void v3d_mmu_insert_ptes(struct v3d_bo *bo) { - struct v3d_dev *v3d = to_v3d_dev(bo->base.dev); + struct drm_gem_shmem_object *shmem_obj = &bo->base; + struct v3d_dev *v3d = to_v3d_dev(shmem_obj->base.dev); u32 page = bo->node.start; u32 page_prot = V3D_PTE_WRITEABLE | V3D_PTE_VALID; unsigned int count; struct scatterlist *sgl; - for_each_sg(bo->sgt->sgl, sgl, bo->sgt->nents, count) { + for_each_sg(shmem_obj->sgt->sgl, sgl, shmem_obj->sgt->nents, count) { u32 page_address = sg_dma_address(sgl) >> V3D_MMU_PAGE_SHIFT; u32 pte = page_prot | page_address; u32 i; @@ -102,7 +103,7 @@ void v3d_mmu_insert_ptes(struct v3d_bo *bo) } WARN_ON_ONCE(page - bo->node.start != - bo->base.size >> V3D_MMU_PAGE_SHIFT); + shmem_obj->base.size >> V3D_MMU_PAGE_SHIFT); if (v3d_mmu_flush_all(v3d)) dev_err(v3d->dev, "MMU flush timeout\n"); @@ -110,8 +111,8 @@ void v3d_mmu_insert_ptes(struct v3d_bo *bo) void v3d_mmu_remove_ptes(struct v3d_bo *bo) { - struct v3d_dev *v3d = to_v3d_dev(bo->base.dev); - u32 npages = bo->base.size >> V3D_MMU_PAGE_SHIFT; + struct v3d_dev *v3d = to_v3d_dev(bo->base.base.dev); + u32 npages = bo->base.base.size >> V3D_MMU_PAGE_SHIFT; u32 page; for (page = bo->node.start; page < bo->node.start + npages; page++) diff --git a/drivers/gpu/drm/v3d/v3d_regs.h b/drivers/gpu/drm/v3d/v3d_regs.h index 6ccdee9d47bd..8e88af237610 100644 --- a/drivers/gpu/drm/v3d/v3d_regs.h +++ b/drivers/gpu/drm/v3d/v3d_regs.h @@ -216,6 +216,8 @@ # define V3D_IDENT2_BCG_INT BIT(28) #define V3D_CTL_MISCCFG 0x00018 +# define V3D_CTL_MISCCFG_QRMAXCNT_MASK V3D_MASK(3, 1) +# define V3D_CTL_MISCCFG_QRMAXCNT_SHIFT 1 # define V3D_MISCCFG_OVRTMUOUT BIT(0) #define V3D_CTL_L2CACTL 0x00020 diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 4704b2df3688..d0c68b7c8b41 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -231,20 +231,17 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) mutex_lock(&v3d->reset_lock); /* block scheduler */ - for (q = 0; q < V3D_MAX_QUEUES; q++) { - struct drm_gpu_scheduler *sched = &v3d->queue[q].sched; - - drm_sched_stop(sched); + for (q = 0; q < V3D_MAX_QUEUES; q++) + drm_sched_stop(&v3d->queue[q].sched); - if(sched_job) - drm_sched_increase_karma(sched_job); - } + if (sched_job) + drm_sched_increase_karma(sched_job); /* get the GPU back into the init state */ v3d_reset(v3d); for (q = 0; q < V3D_MAX_QUEUES; q++) - drm_sched_resubmit_jobs(sched_job->sched); + drm_sched_resubmit_jobs(&v3d->queue[q].sched); /* Unblock schedulers and restart their jobs. */ for (q = 0; q < V3D_MAX_QUEUES; q++) { |