From: Eric Anholt Date: Thu, 14 Mar 2019 16:34:51 +0000 (-0700) Subject: drm/v3d: Use the new shmem helpers to reduce driver boilerplate. X-Git-Url: http://git.lede-project.org./?a=commitdiff_plain;h=40609d4820b21ff0bb0a58e196601a6747fd55b7;p=openwrt%2Fstaging%2Fblogic.git drm/v3d: Use the new shmem helpers to reduce driver boilerplate. The new shmem helpers from Noralf and Rob abstract out a bunch of our BO creation and mapping code. v2: Use the new sgt getter, and flag pages as dirty before freeing. v3: Remove the mismatched put_pages. Signed-off-by: Eric Anholt Link: https://patchwork.freedesktop.org/patch/msgid/20190314163451.13431-1-eric@anholt.net Reviewed-by: Rob Herring (v2) --- 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 dff38bf36c50..c0219ebb4284 100644 --- a/drivers/gpu/drm/v3d/v3d_bo.c +++ b/drivers/gpu/drm/v3d/v3d_bo.c @@ -25,158 +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->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; - - 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. */ @@ -185,83 +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); - 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); } -static void -v3d_set_mmap_vma_flags(struct vm_area_struct *vma) +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) { - vma->vm_flags &= ~VM_PFNMAP; - vma->vm_flags |= VM_MIXEDMAP; - vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); -} + struct v3d_bo *bo; + struct drm_gem_object *obj; -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; + if (size == 0) + return NULL; - /* 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); + bo = kzalloc(sizeof(*bo), GFP_KERNEL); + if (!bo) + return NULL; + obj = &bo->base.base; - return vmf_insert_mixed(vma, vmf->address, pfn); + obj->funcs = &v3d_gem_funcs; + + INIT_LIST_HEAD(&bo->unref_head); + + 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); + + v3d_mmu_insert_ptes(bo); - return ret; + 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 * @@ -269,27 +150,18 @@ v3d_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sgt) { - struct v3d_dev *v3d = to_v3d_dev(dev); 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; - - obj->resv = attach->dmabuf->resv; - - bo->sgt = sgt; - obj->import_attach = attach; - v3d_bo_get_pages(bo); + int ret; - mutex_lock(&v3d->bo_lock); - v3d->bo_stats.num_allocated++; - v3d->bo_stats.pages_allocated += obj->size >> PAGE_SHIFT; - mutex_unlock(&v3d->bo_lock); + 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; } @@ -312,8 +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; } @@ -323,7 +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); @@ -336,12 +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_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index 89b7567d550f..d600628bb5c1 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -161,17 +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 @@ -189,12 +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 | @@ -208,16 +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_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), diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index 65906c05dc9c..7b0fe6240f7d 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include "uapi/drm/v3d_drm.h" @@ -111,16 +112,10 @@ struct v3d_file_priv { }; 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; - /* List entry for the BO's position in * v3d_exec_info->unref_list */ @@ -258,6 +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); @@ -267,10 +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); -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); diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 945eaaaad016..b84d89c7b3fb 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -201,7 +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]->base.resv, fence); + reservation_object_add_excl_fence(bos[i]->base.base.resv, + fence); } } @@ -237,7 +238,8 @@ v3d_lock_bo_reservations(struct v3d_bo **bos, * before we commit the CL to the hardware. */ for (i = 0; i < bo_count; i++) { - ret = reservation_object_reserve_shared(bos[i]->base.resv, 1); + ret = reservation_object_reserve_shared(bos[i]->base.base.resv, + 1); if (ret) { v3d_unlock_bo_reservations(bos, bo_count, acquire_ctx); @@ -345,11 +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); @@ -376,7 +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); diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c index b8aea2dfbe82..b4d6ae81186d 100644 --- a/drivers/gpu/drm/v3d/v3d_irq.c +++ b/drivers/gpu/drm/v3d/v3d_irq.c @@ -37,12 +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 @@ -59,15 +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 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++)