drm/amdgpu: Implement mmap as GEM object function

Moving the driver-specific mmap code into a GEM object function allows
for using DRM helpers for various mmap callbacks.

This change resolves several inconsistencies between regular mmap and
prime-based mmap. The vm_ops field in vma is now set for all mmap'ed
areas. Previously it way only set for regular mmap calls, prime-based
mmap used TTM's default vm_ops. The function amdgpu_verify_access() is
no longer being called and therefore removed by this patch.

As a side effect, amdgpu_ttm_vm_ops and amdgpu_ttm_fault() are now
implemented in amdgpu's GEM code.

v4:
	* rebased
v3:
	* rename mmap function to amdgpu_gem_object_mmap() (Christian)
	* remove unnecessary checks from mmap (Christian)
v2:
	* rename amdgpu_ttm_vm_ops and amdgpu_ttm_fault() to
	  amdgpu_gem_vm_ops and amdgpu_gem_fault() (Christian)
	* the check for kfd_bo has meanwhile been removed

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210525151055.8174-3-tzimmermann@suse.de
This commit is contained in:
Thomas Zimmermann 2021-05-25 17:10:50 +02:00
parent ccd9fe972c
commit 71df0368e9
6 changed files with 57 additions and 126 deletions

View File

@ -42,52 +42,6 @@
#include <linux/pci-p2pdma.h>
#include <linux/pm_runtime.h>
/**
* amdgpu_gem_prime_mmap - &drm_driver.gem_prime_mmap implementation
* @obj: GEM BO
* @vma: Virtual memory area
*
* Sets up a userspace mapping of the BO's memory in the given
* virtual memory area.
*
* Returns:
* 0 on success or a negative error code on failure.
*/
int amdgpu_gem_prime_mmap(struct drm_gem_object *obj,
struct vm_area_struct *vma)
{
struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
unsigned asize = amdgpu_bo_size(bo);
int ret;
if (!vma->vm_file)
return -ENODEV;
if (adev == NULL)
return -ENODEV;
/* Check for valid size. */
if (asize < vma->vm_end - vma->vm_start)
return -EINVAL;
if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm) ||
(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)) {
return -EPERM;
}
vma->vm_pgoff += amdgpu_bo_mmap_offset(bo) >> PAGE_SHIFT;
/* prime mmap does not need to check access, so allow here */
ret = drm_vma_node_allow(&obj->vma_node, vma->vm_file->private_data);
if (ret)
return ret;
ret = ttm_bo_mmap(vma->vm_file, vma, &adev->mman.bdev);
drm_vma_node_revoke(&obj->vma_node, vma->vm_file->private_data);
return ret;
}
static int
__dma_resv_make_exclusive(struct dma_resv *obj)
{

View File

@ -31,8 +31,6 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
struct dma_buf *dma_buf);
bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev,
struct amdgpu_bo *bo);
int amdgpu_gem_prime_mmap(struct drm_gem_object *obj,
struct vm_area_struct *vma);
extern const struct dma_buf_ops amdgpu_dmabuf_ops;

View File

@ -1695,7 +1695,7 @@ static const struct file_operations amdgpu_driver_kms_fops = {
.flush = amdgpu_flush,
.release = drm_release,
.unlocked_ioctl = amdgpu_drm_ioctl,
.mmap = amdgpu_mmap,
.mmap = drm_gem_mmap,
.poll = drm_poll,
.read = drm_read,
#ifdef CONFIG_COMPAT
@ -1762,7 +1762,7 @@ static const struct drm_driver amdgpu_kms_driver = {
.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
.gem_prime_import = amdgpu_gem_prime_import,
.gem_prime_mmap = amdgpu_gem_prime_mmap,
.gem_prime_mmap = drm_gem_prime_mmap,
.name = DRIVER_NAME,
.desc = DRIVER_DESC,

View File

@ -32,6 +32,7 @@
#include <linux/dma-buf.h>
#include <drm/amdgpu_drm.h>
#include <drm/drm_drv.h>
#include <drm/drm_gem_ttm_helper.h>
#include "amdgpu.h"
@ -41,6 +42,46 @@
static const struct drm_gem_object_funcs amdgpu_gem_object_funcs;
static vm_fault_t amdgpu_gem_fault(struct vm_fault *vmf)
{
struct ttm_buffer_object *bo = vmf->vma->vm_private_data;
struct drm_device *ddev = bo->base.dev;
vm_fault_t ret;
int idx;
ret = ttm_bo_vm_reserve(bo, vmf);
if (ret)
return ret;
if (drm_dev_enter(ddev, &idx)) {
ret = amdgpu_bo_fault_reserve_notify(bo);
if (ret) {
drm_dev_exit(idx);
goto unlock;
}
ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
TTM_BO_VM_NUM_PREFAULT, 1);
drm_dev_exit(idx);
} else {
ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);
}
if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
return ret;
unlock:
dma_resv_unlock(bo->base.resv);
return ret;
}
static const struct vm_operations_struct amdgpu_gem_vm_ops = {
.fault = amdgpu_gem_fault,
.open = ttm_bo_vm_open,
.close = ttm_bo_vm_close,
.access = ttm_bo_vm_access
};
static void amdgpu_gem_object_free(struct drm_gem_object *gobj)
{
struct amdgpu_bo *robj = gem_to_amdgpu_bo(gobj);
@ -205,6 +246,18 @@ out_unlock:
ttm_eu_backoff_reservation(&ticket, &list);
}
static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
{
struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm))
return -EPERM;
if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
return -EPERM;
return drm_gem_ttm_mmap(obj, vma);
}
static const struct drm_gem_object_funcs amdgpu_gem_object_funcs = {
.free = amdgpu_gem_object_free,
.open = amdgpu_gem_object_open,
@ -212,6 +265,8 @@ static const struct drm_gem_object_funcs amdgpu_gem_object_funcs = {
.export = amdgpu_gem_prime_export,
.vmap = drm_gem_ttm_vmap,
.vunmap = drm_gem_ttm_vunmap,
.mmap = amdgpu_gem_object_mmap,
.vm_ops = &amdgpu_gem_vm_ops,
};
/*

View File

@ -47,7 +47,6 @@
#include <drm/ttm/ttm_placement.h>
#include <drm/amdgpu_drm.h>
#include <drm/drm_drv.h>
#include "amdgpu.h"
#include "amdgpu_object.h"
@ -166,25 +165,6 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
*placement = abo->placement;
}
/**
* amdgpu_verify_access - Verify access for a mmap call
*
* @bo: The buffer object to map
* @filp: The file pointer from the process performing the mmap
*
* This is called by ttm_bo_mmap() to verify whether a process
* has the right to mmap a BO to their process space.
*/
static int amdgpu_verify_access(struct ttm_buffer_object *bo, struct file *filp)
{
struct amdgpu_bo *abo = ttm_to_amdgpu_bo(bo);
if (amdgpu_ttm_tt_get_usermm(bo->ttm))
return -EPERM;
return drm_vma_node_verify_access(&abo->tbo.base.vma_node,
filp->private_data);
}
/**
* amdgpu_ttm_map_buffer - Map memory into the GART windows
* @bo: buffer object to map
@ -1476,7 +1456,6 @@ static struct ttm_device_funcs amdgpu_bo_driver = {
.eviction_valuable = amdgpu_ttm_bo_eviction_valuable,
.evict_flags = &amdgpu_evict_flags,
.move = &amdgpu_bo_move,
.verify_access = &amdgpu_verify_access,
.delete_mem_notify = &amdgpu_bo_delete_mem_notify,
.release_notify = &amdgpu_bo_release_notify,
.io_mem_reserve = &amdgpu_ttm_io_mem_reserve,
@ -1844,60 +1823,6 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
adev->mman.buffer_funcs_enabled = enable;
}
static vm_fault_t amdgpu_ttm_fault(struct vm_fault *vmf)
{
struct ttm_buffer_object *bo = vmf->vma->vm_private_data;
struct drm_device *ddev = bo->base.dev;
vm_fault_t ret;
int idx;
ret = ttm_bo_vm_reserve(bo, vmf);
if (ret)
return ret;
if (drm_dev_enter(ddev, &idx)) {
ret = amdgpu_bo_fault_reserve_notify(bo);
if (ret) {
drm_dev_exit(idx);
goto unlock;
}
ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
TTM_BO_VM_NUM_PREFAULT, 1);
drm_dev_exit(idx);
} else {
ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);
}
if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
return ret;
unlock:
dma_resv_unlock(bo->base.resv);
return ret;
}
static const struct vm_operations_struct amdgpu_ttm_vm_ops = {
.fault = amdgpu_ttm_fault,
.open = ttm_bo_vm_open,
.close = ttm_bo_vm_close,
.access = ttm_bo_vm_access
};
int amdgpu_mmap(struct file *filp, struct vm_area_struct *vma)
{
struct drm_file *file_priv = filp->private_data;
struct amdgpu_device *adev = drm_to_adev(file_priv->minor->dev);
int r;
r = ttm_bo_mmap(filp, vma, &adev->mman.bdev);
if (unlikely(r != 0))
return r;
vma->vm_ops = &amdgpu_ttm_vm_ops;
return 0;
}
int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
uint64_t dst_offset, uint32_t byte_count,
struct dma_resv *resv,

View File

@ -142,7 +142,6 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo,
struct dma_resv *resv,
struct dma_fence **fence);
int amdgpu_mmap(struct file *filp, struct vm_area_struct *vma);
int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo);
int amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo);
uint64_t amdgpu_ttm_domain_start(struct amdgpu_device *adev, uint32_t type);