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 <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20190314163451.13431-1-eric@anholt.net
Reviewed-by: Rob Herring <robh@kernel.org> (v2)
This commit is contained in:
Eric Anholt 2019-03-14 09:34:51 -07:00
parent 2194a63a81
commit 40609d4820
7 changed files with 119 additions and 273 deletions

View File

@ -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.

View File

@ -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;
if (size == 0)
return NULL;
bo = kzalloc(sizeof(*bo), GFP_KERNEL);
if (!bo)
return NULL;
obj = &bo->base.base;
obj->funcs = &v3d_gem_funcs;
INIT_LIST_HEAD(&bo->unref_head);
return &bo->base.base;
}
vm_fault_t v3d_gem_fault(struct vm_fault *vmf)
static int
v3d_bo_create_finish(struct drm_gem_object *obj)
{
struct vm_area_struct *vma = vmf->vma;
struct drm_gem_object *obj = vma->vm_private_data;
struct v3d_dev *v3d = to_v3d_dev(obj->dev);
struct v3d_bo *bo = to_v3d_bo(obj);
pfn_t pfn;
pgoff_t pgoff;
/* 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);
return vmf_insert_mixed(vma, vmf->address, pfn);
}
int v3d_mmap(struct file *filp, struct vm_area_struct *vma)
{
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;
}
int v3d_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
{
int ret;
ret = drm_gem_mmap_obj(obj, obj->size, vma);
if (ret < 0)
return ret;
v3d_set_mmap_vma_flags(vma);
v3d_mmu_insert_ptes(bo);
return 0;
}
struct sg_table *
v3d_prime_get_sg_table(struct drm_gem_object *obj)
struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv,
size_t unaligned_size)
{
struct v3d_bo *bo = to_v3d_bo(obj);
int npages = obj->size >> PAGE_SHIFT;
struct drm_gem_shmem_object *shmem_obj;
struct v3d_bo *bo;
int ret;
return drm_prime_pages_to_sg(bo->pages, npages);
shmem_obj = drm_gem_shmem_create(dev, unaligned_size);
if (!shmem_obj)
return NULL;
bo = to_v3d_bo(&shmem_obj->base);
ret = v3d_bo_create_finish(&shmem_obj->base);
if (ret)
goto free_obj;
return bo;
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;
int ret;
bo = v3d_bo_create_struct(dev, attach->dmabuf->size);
if (IS_ERR(bo))
return ERR_CAST(bo);
obj = &bo->base;
obj = drm_gem_shmem_prime_import_sg_table(dev, attach, sgt);
if (IS_ERR(obj))
return obj;
obj->resv = attach->dmabuf->resv;
bo->sgt = sgt;
obj->import_attach = attach;
v3d_bo_get_pages(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_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);
drm_gem_object_put_unlocked(gem_obj);
return ret;
return 0;
}
int v3d_get_bo_offset_ioctl(struct drm_device *dev, void *data,

View File

@ -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),

View File

@ -5,6 +5,7 @@
#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"
@ -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);

View File

@ -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);

View File

@ -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

View File

@ -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++)