drm/gpusvm, drm/xe: Fix userptr to not allow device private pages

When userptr is used on SVM-enabled VMs, a non-NULL
hmm_range::dev_private_owner value might mean that
hmm_range_fault() attempts to return device private pages.
Either that will fail, or the userptr code will not know
how to handle those.

Use NULL for hmm_range::dev_private_owner to migrate
such pages to system. In order to do that, move the
struct drm_gpusvm::device_private_page_owner field to
struct drm_gpusvm_ctx::device_private_page_owner so that
it doesn't remain immutable over the drm_gpusvm lifetime.

v2:
- Don't conditionally compile xe_svm_devm_owner().
- Kerneldoc xe_svm_devm_owner().

Fixes: 9e97874148 ("drm/xe/userptr: replace xe_hmm with gpusvm")
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://lore.kernel.org/r/20250930122752.96034-1-thomas.hellstrom@linux.intel.com
This commit is contained in:
Thomas Hellström
2025-09-30 14:27:52 +02:00
parent d9c401d8f3
commit ad298d9ec9
6 changed files with 36 additions and 22 deletions

View File

@@ -361,7 +361,6 @@ static const struct mmu_interval_notifier_ops drm_gpusvm_notifier_ops = {
* @name: Name of the GPU SVM.
* @drm: Pointer to the DRM device structure.
* @mm: Pointer to the mm_struct for the address space.
* @device_private_page_owner: Device private pages owner.
* @mm_start: Start address of GPU SVM.
* @mm_range: Range of the GPU SVM.
* @notifier_size: Size of individual notifiers.
@@ -383,7 +382,7 @@ static const struct mmu_interval_notifier_ops drm_gpusvm_notifier_ops = {
*/
int drm_gpusvm_init(struct drm_gpusvm *gpusvm,
const char *name, struct drm_device *drm,
struct mm_struct *mm, void *device_private_page_owner,
struct mm_struct *mm,
unsigned long mm_start, unsigned long mm_range,
unsigned long notifier_size,
const struct drm_gpusvm_ops *ops,
@@ -395,15 +394,13 @@ int drm_gpusvm_init(struct drm_gpusvm *gpusvm,
mmgrab(mm);
} else {
/* No full SVM mode, only core drm_gpusvm_pages API. */
if (ops || num_chunks || mm_range || notifier_size ||
device_private_page_owner)
if (ops || num_chunks || mm_range || notifier_size)
return -EINVAL;
}
gpusvm->name = name;
gpusvm->drm = drm;
gpusvm->mm = mm;
gpusvm->device_private_page_owner = device_private_page_owner;
gpusvm->mm_start = mm_start;
gpusvm->mm_range = mm_range;
gpusvm->notifier_size = notifier_size;
@@ -684,6 +681,7 @@ static unsigned int drm_gpusvm_hmm_pfn_to_order(unsigned long hmm_pfn,
* @notifier: Pointer to the GPU SVM notifier structure
* @start: Start address
* @end: End address
* @dev_private_owner: The device private page owner
*
* Check if pages between start and end have been faulted in on the CPU. Use to
* prevent migration of pages without CPU backing store.
@@ -692,14 +690,15 @@ static unsigned int drm_gpusvm_hmm_pfn_to_order(unsigned long hmm_pfn,
*/
static bool drm_gpusvm_check_pages(struct drm_gpusvm *gpusvm,
struct drm_gpusvm_notifier *notifier,
unsigned long start, unsigned long end)
unsigned long start, unsigned long end,
void *dev_private_owner)
{
struct hmm_range hmm_range = {
.default_flags = 0,
.notifier = &notifier->notifier,
.start = start,
.end = end,
.dev_private_owner = gpusvm->device_private_page_owner,
.dev_private_owner = dev_private_owner,
};
unsigned long timeout =
jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
@@ -753,6 +752,7 @@ err_free:
* @gpuva_start: Start address of GPUVA which mirrors CPU
* @gpuva_end: End address of GPUVA which mirrors CPU
* @check_pages_threshold: Check CPU pages for present threshold
* @dev_private_owner: The device private page owner
*
* This function determines the chunk size for the GPU SVM range based on the
* fault address, GPU SVM chunk sizes, existing GPU SVM ranges, and the virtual
@@ -767,7 +767,8 @@ drm_gpusvm_range_chunk_size(struct drm_gpusvm *gpusvm,
unsigned long fault_addr,
unsigned long gpuva_start,
unsigned long gpuva_end,
unsigned long check_pages_threshold)
unsigned long check_pages_threshold,
void *dev_private_owner)
{
unsigned long start, end;
int i = 0;
@@ -814,7 +815,7 @@ retry:
* process-many-malloc' mallocs at least 64k at a time.
*/
if (end - start <= check_pages_threshold &&
!drm_gpusvm_check_pages(gpusvm, notifier, start, end)) {
!drm_gpusvm_check_pages(gpusvm, notifier, start, end, dev_private_owner)) {
++i;
goto retry;
}
@@ -957,7 +958,8 @@ drm_gpusvm_range_find_or_insert(struct drm_gpusvm *gpusvm,
chunk_size = drm_gpusvm_range_chunk_size(gpusvm, notifier, vas,
fault_addr, gpuva_start,
gpuva_end,
ctx->check_pages_threshold);
ctx->check_pages_threshold,
ctx->device_private_page_owner);
if (chunk_size == LONG_MAX) {
err = -EINVAL;
goto err_notifier_remove;
@@ -1268,7 +1270,7 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm,
.notifier = notifier,
.start = pages_start,
.end = pages_end,
.dev_private_owner = gpusvm->device_private_page_owner,
.dev_private_owner = ctx->device_private_page_owner,
};
void *zdd;
unsigned long timeout =