drm/gpusvm, drm/xe: Fix userptr to not allow device private pages
Subsystems (4)
Thomas Hellström
maintainerPATCH v2 1/1 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().
--- drivers/gpu/drm/drm_gpusvm.c | 24 +++++++++++++----------- drivers/gpu/drm/xe/xe_svm.c | 11 +++-------- drivers/gpu/drm/xe/xe_svm.h | 14 ++++++++++++++ drivers/gpu/drm/xe/xe_userptr.c | 1 + drivers/gpu/drm/xe/xe_vm.c | 1 + include/drm/drm_gpusvm.h | 7 ++++--- 6 files changed, 36 insertions(+), 22 deletions(-)
drivers/gpu/drm/drm_gpusvm.c +13 -11
@@ -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 = ¬ifier->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 @@ static bool drm_gpusvm_check_pages(struct drm_gpusvm *gpusvm,* @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 @@ drm_gpusvm_range_chunk_size(struct drm_gpusvm *gpusvm,* 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 =
drivers/gpu/drm/xe/xe_svm.c +3 -8
@@ -67,11 +67,6 @@ void xe_svm_range_debug(struct xe_svm_range *range, const char *operation)range_debug (range, operation); } -static void *xe_svm_devm_owner (struct xe_device *xe) -{ -return xe; -} -static struct drm_gpusvm_range *xe_svm_range_alloc (struct drm_gpusvm *gpusvm) {
@@ -744,15 +739,14 @@ int xe_svm_init(struct xe_vm *vm) xe_svm_garbage_collector_work_func); err =drm_gpusvm_init (&vm->svm.gpusvm,"Xe SVM" , &vm->xe->drm, - current->mm,xe_svm_devm_owner (vm->xe),0 , - vm->size, + current->mm,0 , vm->size, xe_modparam.svm_notifier_size *SZ_1M , &gpusvm_ops, fault_chunk_sizes,ARRAY_SIZE (fault_chunk_sizes));drm_gpusvm_driver_set_lock (&vm->svm.gpusvm, &vm->lock); }else { err =drm_gpusvm_init (&vm->svm.gpusvm,"Xe SVM (simple)" , - &vm->xe->drm,NULL ,NULL ,0 ,0 ,0 ,NULL , + &vm->xe->drm,NULL ,0 ,0 ,0 ,NULL ,NULL ,0 ); }
@@ -1017,6 +1011,7 @@ static int __xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma, .devmem_only = need_vram && devmem_possible, .timeslice_ms = need_vram && devmem_possible ? vm->xe->atomic_svm_timeslice_ms : 0, + .device_private_page_owner = xe_svm_devm_owner(vm->xe), };struct xe_validation_ctx vctx;struct drm_exec exec;
drivers/gpu/drm/xe/xe_svm.h +14 -0
@@ -6,6 +6,20 @@#ifndef _XE_SVM_H_#define _XE_SVM_H_ +struct xe_device ; + +/** +* xe_svm_devm_owner() - Return the owner of device private memory +* @xe: The xe device. +* +* Return: The owner of this device's device private memory to use in +* hmm_range_fault()- +*/ +static inline void *xe_svm_devm_owner (struct xe_device *xe) +{ +return xe; +} +#if IS_ENABLED (CONFIG_DRM_XE_GPUSVM )#include <drm/drm_pagemap.h>
drivers/gpu/drm/xe/xe_userptr.c +1 -0
@@ -54,6 +54,7 @@ int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma)struct xe_device *xe = vm->xe;struct drm_gpusvm_ctx ctx = { .read_only =xe_vma_read_only (vma), + .device_private_page_owner =NULL , };lockdep_assert_held (&vm->lock);
drivers/gpu/drm/xe/xe_vm.c +1 -0
@@ -2883,6 +2883,7 @@ static int prefetch_ranges(struct xe_vm *vm, struct xe_vma_op *op) ctx.read_only =xe_vma_read_only (vma); ctx.devmem_possible = devmem_possible; ctx.check_pages_threshold = devmem_possible ?SZ_64K :0 ; + ctx.device_private_page_owner =xe_svm_devm_owner (vm->xe);/* TODO: Threading the migration */ xa_for_each (&op->prefetch_range.range, i, svm_range) {
include/drm/drm_gpusvm.h +4 -3
@@ -179,7 +179,6 @@ struct drm_gpusvm_range {* @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
@@ -204,7 +203,6 @@ struct drm_gpusvm {const char *name;struct drm_device *drm;struct mm_struct *mm; -void *device_private_page_owner;unsigned long mm_start;unsigned long mm_range;unsigned long notifier_size;
@@ -226,6 +224,8 @@ struct drm_gpusvm {/** * struct drm_gpusvm_ctx - DRM GPU SVM context * +* @device_private_page_owner: The device-private page owner to use for +* this operation * @check_pages_threshold: Check CPU pages for present if chunk is less than or * equal to threshold. If not present, reduce chunk * size.
@@ -239,6 +239,7 @@ struct drm_gpusvm {* Context that is DRM GPUSVM is operating in (i.e. user arguments). */ struct drm_gpusvm_ctx { +void *device_private_page_owner;unsigned long check_pages_threshold;unsigned long timeslice_ms;unsigned int in_notifier :1 ;
@@ -249,7 +250,7 @@ struct drm_gpusvm_ctx { 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,
Signature · 1 line
2.51.0
kernel test robot
build botkernel test robot noticed the following build errors:
Hi Thomas,
kernel test robot noticed the following build errors:
[auto build test ERROR on drm-xe/drm-xe-next]
[also build test ERROR on linus/master]
[cannot apply to drm-tip/drm-tip v6.17 next-20251009]
[If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Thomas-Hellstr-m/drm-gpusvm-drm-xe-Fix-userptr-to-not-allow-device-private-pages/20250930-203135 base: https://gitlab.freedesktop.org/drm/xe/kernel.git drm-xe-next patch link: https://lore.kernel.org/r/20250930122752.96034-1-thomas.hellstrom%40linux.intel.com patch subject: [PATCH v2] drm/gpusvm, drm/xe: Fix userptr to not allow device private pages config: x86_64-randconfig-077-20251009 (https://download.01.org/0day-ci/archive/20251010/[email protected]/config) compiler: gcc-14 (Debian 14.2.0-19) 14.2.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251010/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All errors (new ones prefixed by >>):
In file included from include/uapi/linux/posix_types.h:5,
from include/uapi/linux/types.h:14,
from include/linux/types.h:6,
from include/linux/kasan-checks.h:5,
from include/asm-generic/rwonce.h:26,
from ./arch/x86/include/generated/asm/rwonce.h:1,
from include/linux/compiler.h:382,
from include/linux/build_bug.h:5,
from include/linux/bits.h:30,
from include/linux/gfp_types.h:5,
from include/linux/gfp.h:5,
from include/drm/drm_managed.h:6,
from drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c:7:
drivers/gpu/drm/xe/xe_svm.h: In function 'xe_svm_init':
>> include/linux/stddef.h:8:14: error: passing argument 5 of 'drm_gpusvm_init' makes integer from pointer without a cast [-Wint-conversion]
8 | #define NULL ((void *)0)
| ^~~~~~~~~~~
| |
| void *
drivers/gpu/drm/xe/xe_svm.h:217:38: note: in expansion of macro 'NULL'
217 | NULL, NULL, 0, 0, 0, NULL, NULL, 0);
| ^~~~
In file included from drivers/gpu/drm/xe/xe_bo_types.h:11,
from drivers/gpu/drm/xe/xe_bo.h:11,
from drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c:18:
include/drm/drm_gpusvm.h:254:35: note: expected 'long unsigned int' but argument is of type 'void *'
254 | unsigned long mm_start, unsigned long mm_range,
| ~~~~~~~~~~~~~~^~~~~~~~
include/linux/stddef.h:8:14: error: passing argument 10 of 'drm_gpusvm_init' makes integer from pointer without a cast [-Wint-conversion]
8 | #define NULL ((void *)0)
| ^~~~~~~~~~~
| |
| void *
drivers/gpu/drm/xe/xe_svm.h:217:59: note: in expansion of macro 'NULL'
217 | NULL, NULL, 0, 0, 0, NULL, NULL, 0);
| ^~~~
include/drm/drm_gpusvm.h:257:59: note: expected 'int' but argument is of type 'void *'
257 | const unsigned long *chunk_sizes, int num_chunks);
| ~~~~^~~~~~~~~~
In file included from drivers/gpu/drm/xe/xe_res_cursor.h:38,
from drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c:23:
>> drivers/gpu/drm/xe/xe_svm.h:216:16: error: too many arguments to function 'drm_gpusvm_init'
216 | return drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM (simple)", &vm->xe->drm,
| ^~~~~~~~~~~~~~~ include/drm/drm_gpusvm.h:251:5: note: declared here
251 | int drm_gpusvm_init(struct drm_gpusvm *gpusvm,
| ^~~~~~~~~~~~~~~
vim +/drm_gpusvm_init +8 include/linux/stddef.h
^1da177e4c3f415 Linus Torvalds 2005-04-16 6 ^1da177e4c3f415 Linus Torvalds 2005-04-16 7 #undef NULL ^1da177e4c3f415 Linus Torvalds 2005-04-16 @8 #define NULL ((void *)0)
6e2182874324727 Richard Knutsson 2006-09-30 9
Signature · 2 lines
0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki