| Message ID | 20250129195212.745731-12-matthew.brost@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Introduce GPU SVM and Xe SVM implementation | expand |
On 29/01/2025 19:51, Matthew Brost wrote: > Clear root PT entry and invalidate entire VM's address space when > closing the VM. Will prevent the GPU from accessing any of the VM's > memory after closing. > > v2: > - s/vma/vm in kernel doc (CI) > - Don't nuke migration VM as this occur at driver unload (CI) > v3: > - Rebase and pull into SVM series (Thomas) > - Wait for pending binds (Thomas) > > Signed-off-by: Matthew Brost <matthew.brost@intel.com> > --- > drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 24 +++++++++++++++++++++ > drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h | 2 ++ > drivers/gpu/drm/xe/xe_pt.c | 14 ++++++++++++ > drivers/gpu/drm/xe/xe_pt.h | 3 +++ > drivers/gpu/drm/xe/xe_vm.c | 22 +++++++++++++++++++ > 5 files changed, 65 insertions(+) > > diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > index 0a93831c0a02..1ef21ed01d1b 100644 > --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > @@ -410,6 +410,30 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt, > return send_tlb_invalidation(>->uc.guc, fence, action, len); > } > > +/** > + * xe_gt_tlb_invalidation_vm - Issue a TLB invalidation on this GT for a VM > + * @gt: graphics tile > + * @vm: VM to invalidate > + * > + * Invalidate entire VM's address space > + */ > +void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm) > +{ > + struct xe_gt_tlb_invalidation_fence fence; > + u64 range = 1ull << vm->xe->info.va_bits; > + int ret; > + > + xe_gt_tlb_invalidation_fence_init(gt, &fence, true); > + > + ret = xe_gt_tlb_invalidation_range(gt, &fence, 0, range, vm->usm.asid); > + if (ret < 0) { > + xe_gt_tlb_invalidation_fence_fini(&fence); IIRC we changed the tlb inval flow to do the fini() in the error case, so this will lead to double fini() I think? > + return; > + } > + > + xe_gt_tlb_invalidation_fence_wait(&fence); > +} > + > /** > * xe_gt_tlb_invalidation_vma - Issue a TLB invalidation on this GT for a VMA > * @gt: GT structure > diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > index 672acfcdf0d7..abe9b03d543e 100644 > --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > @@ -12,6 +12,7 @@ > > struct xe_gt; > struct xe_guc; > +struct xe_vm; > struct xe_vma; > > int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt); > @@ -21,6 +22,7 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt); > int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, > struct xe_gt_tlb_invalidation_fence *fence, > struct xe_vma *vma); > +void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm); > int xe_gt_tlb_invalidation_range(struct xe_gt *gt, > struct xe_gt_tlb_invalidation_fence *fence, > u64 start, u64 end, u32 asid); > diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c > index 99b97bf37c05..c5060011ad43 100644 > --- a/drivers/gpu/drm/xe/xe_pt.c > +++ b/drivers/gpu/drm/xe/xe_pt.c > @@ -214,6 +214,20 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred) > xe_pt_free(pt); > } > > +/** > + * xe_pt_clear() - Clear a page-table. > + * @xe: xe device. > + * @pt: The page-table. > + * > + * Clears page-table by setting to zero. > + */ > +void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt) > +{ > + struct iosys_map *map = &pt->bo->vmap; > + > + xe_map_memset(xe, map, 0, 0, SZ_4K); > +} > + > /** > * DOC: Pagetable building > * > diff --git a/drivers/gpu/drm/xe/xe_pt.h b/drivers/gpu/drm/xe/xe_pt.h > index 9ab386431cad..8e43912ae8e9 100644 > --- a/drivers/gpu/drm/xe/xe_pt.h > +++ b/drivers/gpu/drm/xe/xe_pt.h > @@ -13,6 +13,7 @@ struct dma_fence; > struct xe_bo; > struct xe_device; > struct xe_exec_queue; > +struct xe_svm_range; > struct xe_sync_entry; > struct xe_tile; > struct xe_vm; > @@ -35,6 +36,8 @@ void xe_pt_populate_empty(struct xe_tile *tile, struct xe_vm *vm, > > void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred); > > +void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt); > + > int xe_pt_update_ops_prepare(struct xe_tile *tile, struct xe_vma_ops *vops); > struct dma_fence *xe_pt_update_ops_run(struct xe_tile *tile, > struct xe_vma_ops *vops); > diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c > index bc34e6738c8c..82026c5a154d 100644 > --- a/drivers/gpu/drm/xe/xe_vm.c > +++ b/drivers/gpu/drm/xe/xe_vm.c > @@ -1537,8 +1537,30 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) > > static void xe_vm_close(struct xe_vm *vm) > { > + bool migration = (vm->flags & XE_VM_FLAG_MIGRATION); > + > down_write(&vm->lock); > + > vm->size = 0; > + > + if (!migration) { > + struct xe_tile *tile; > + struct xe_gt *gt; > + u8 id; > + > + /* Wait for pending binds */ > + dma_resv_wait_timeout(xe_vm_resv(vm), > + DMA_RESV_USAGE_BOOKKEEP, > + false, MAX_SCHEDULE_TIMEOUT); > + > + for_each_tile(tile, vm->xe, id) > + if (vm->pt_root[id]) > + xe_pt_clear(vm->xe, vm->pt_root[id]); > + > + for_each_gt(gt, vm->xe, id) > + xe_gt_tlb_invalidation_vm(gt, vm); > + } > + > up_write(&vm->lock); > } >
On Thu, Jan 30, 2025 at 10:50:49AM +0000, Matthew Auld wrote: > On 29/01/2025 19:51, Matthew Brost wrote: > > Clear root PT entry and invalidate entire VM's address space when > > closing the VM. Will prevent the GPU from accessing any of the VM's > > memory after closing. > > > > v2: > > - s/vma/vm in kernel doc (CI) > > - Don't nuke migration VM as this occur at driver unload (CI) > > v3: > > - Rebase and pull into SVM series (Thomas) > > - Wait for pending binds (Thomas) > > > > Signed-off-by: Matthew Brost <matthew.brost@intel.com> > > --- > > drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 24 +++++++++++++++++++++ > > drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h | 2 ++ > > drivers/gpu/drm/xe/xe_pt.c | 14 ++++++++++++ > > drivers/gpu/drm/xe/xe_pt.h | 3 +++ > > drivers/gpu/drm/xe/xe_vm.c | 22 +++++++++++++++++++ > > 5 files changed, 65 insertions(+) > > > > diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > > index 0a93831c0a02..1ef21ed01d1b 100644 > > --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > > +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > > @@ -410,6 +410,30 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt, > > return send_tlb_invalidation(>->uc.guc, fence, action, len); > > } > > +/** > > + * xe_gt_tlb_invalidation_vm - Issue a TLB invalidation on this GT for a VM > > + * @gt: graphics tile > > + * @vm: VM to invalidate > > + * > > + * Invalidate entire VM's address space > > + */ > > +void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm) > > +{ > > + struct xe_gt_tlb_invalidation_fence fence; > > + u64 range = 1ull << vm->xe->info.va_bits; > > + int ret; > > + > > + xe_gt_tlb_invalidation_fence_init(gt, &fence, true); > > + > > + ret = xe_gt_tlb_invalidation_range(gt, &fence, 0, range, vm->usm.asid); > > + if (ret < 0) { > > + xe_gt_tlb_invalidation_fence_fini(&fence); > > IIRC we changed the tlb inval flow to do the fini() in the error case, so > this will lead to double fini() I think? > Indeed, good catch. Will fixup. Thanks, Matt > > + return; > > + } > > + > > + xe_gt_tlb_invalidation_fence_wait(&fence); > > +} > > + > > /** > > * xe_gt_tlb_invalidation_vma - Issue a TLB invalidation on this GT for a VMA > > * @gt: GT structure > > diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > > index 672acfcdf0d7..abe9b03d543e 100644 > > --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > > +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > > @@ -12,6 +12,7 @@ > > struct xe_gt; > > struct xe_guc; > > +struct xe_vm; > > struct xe_vma; > > int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt); > > @@ -21,6 +22,7 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt); > > int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, > > struct xe_gt_tlb_invalidation_fence *fence, > > struct xe_vma *vma); > > +void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm); > > int xe_gt_tlb_invalidation_range(struct xe_gt *gt, > > struct xe_gt_tlb_invalidation_fence *fence, > > u64 start, u64 end, u32 asid); > > diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c > > index 99b97bf37c05..c5060011ad43 100644 > > --- a/drivers/gpu/drm/xe/xe_pt.c > > +++ b/drivers/gpu/drm/xe/xe_pt.c > > @@ -214,6 +214,20 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred) > > xe_pt_free(pt); > > } > > +/** > > + * xe_pt_clear() - Clear a page-table. > > + * @xe: xe device. > > + * @pt: The page-table. > > + * > > + * Clears page-table by setting to zero. > > + */ > > +void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt) > > +{ > > + struct iosys_map *map = &pt->bo->vmap; > > + > > + xe_map_memset(xe, map, 0, 0, SZ_4K); > > +} > > + > > /** > > * DOC: Pagetable building > > * > > diff --git a/drivers/gpu/drm/xe/xe_pt.h b/drivers/gpu/drm/xe/xe_pt.h > > index 9ab386431cad..8e43912ae8e9 100644 > > --- a/drivers/gpu/drm/xe/xe_pt.h > > +++ b/drivers/gpu/drm/xe/xe_pt.h > > @@ -13,6 +13,7 @@ struct dma_fence; > > struct xe_bo; > > struct xe_device; > > struct xe_exec_queue; > > +struct xe_svm_range; > > struct xe_sync_entry; > > struct xe_tile; > > struct xe_vm; > > @@ -35,6 +36,8 @@ void xe_pt_populate_empty(struct xe_tile *tile, struct xe_vm *vm, > > void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred); > > +void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt); > > + > > int xe_pt_update_ops_prepare(struct xe_tile *tile, struct xe_vma_ops *vops); > > struct dma_fence *xe_pt_update_ops_run(struct xe_tile *tile, > > struct xe_vma_ops *vops); > > diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c > > index bc34e6738c8c..82026c5a154d 100644 > > --- a/drivers/gpu/drm/xe/xe_vm.c > > +++ b/drivers/gpu/drm/xe/xe_vm.c > > @@ -1537,8 +1537,30 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) > > static void xe_vm_close(struct xe_vm *vm) > > { > > + bool migration = (vm->flags & XE_VM_FLAG_MIGRATION); > > + > > down_write(&vm->lock); > > + > > vm->size = 0; > > + > > + if (!migration) { > > + struct xe_tile *tile; > > + struct xe_gt *gt; > > + u8 id; > > + > > + /* Wait for pending binds */ > > + dma_resv_wait_timeout(xe_vm_resv(vm), > > + DMA_RESV_USAGE_BOOKKEEP, > > + false, MAX_SCHEDULE_TIMEOUT); > > + > > + for_each_tile(tile, vm->xe, id) > > + if (vm->pt_root[id]) > > + xe_pt_clear(vm->xe, vm->pt_root[id]); > > + > > + for_each_gt(gt, vm->xe, id) > > + xe_gt_tlb_invalidation_vm(gt, vm); > > + } > > + > > up_write(&vm->lock); > > } >
On Wed, 2025-01-29 at 11:51 -0800, Matthew Brost wrote: > Clear root PT entry and invalidate entire VM's address space when > closing the VM. Will prevent the GPU from accessing any of the VM's > memory after closing. > > v2: > - s/vma/vm in kernel doc (CI) > - Don't nuke migration VM as this occur at driver unload (CI) > v3: > - Rebase and pull into SVM series (Thomas) > - Wait for pending binds (Thomas) > > Signed-off-by: Matthew Brost <matthew.brost@intel.com> > --- > drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 24 > +++++++++++++++++++++ > drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h | 2 ++ > drivers/gpu/drm/xe/xe_pt.c | 14 ++++++++++++ > drivers/gpu/drm/xe/xe_pt.h | 3 +++ > drivers/gpu/drm/xe/xe_vm.c | 22 +++++++++++++++++++ > 5 files changed, 65 insertions(+) > > diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > index 0a93831c0a02..1ef21ed01d1b 100644 > --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > @@ -410,6 +410,30 @@ int xe_gt_tlb_invalidation_range(struct xe_gt > *gt, > return send_tlb_invalidation(>->uc.guc, fence, action, > len); > } > > +/** > + * xe_gt_tlb_invalidation_vm - Issue a TLB invalidation on this GT > for a VM > + * @gt: graphics tile > + * @vm: VM to invalidate > + * > + * Invalidate entire VM's address space > + */ > +void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm) > +{ > + struct xe_gt_tlb_invalidation_fence fence; > + u64 range = 1ull << vm->xe->info.va_bits; > + int ret; > + > + xe_gt_tlb_invalidation_fence_init(gt, &fence, true); > + > + ret = xe_gt_tlb_invalidation_range(gt, &fence, 0, range, vm- > >usm.asid); > + if (ret < 0) { > + xe_gt_tlb_invalidation_fence_fini(&fence); > + return; > + } > + > + xe_gt_tlb_invalidation_fence_wait(&fence); > +} > + > /** > * xe_gt_tlb_invalidation_vma - Issue a TLB invalidation on this GT > for a VMA > * @gt: GT structure > diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > index 672acfcdf0d7..abe9b03d543e 100644 > --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > @@ -12,6 +12,7 @@ > > struct xe_gt; > struct xe_guc; > +struct xe_vm; > struct xe_vma; > > int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt); > @@ -21,6 +22,7 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt); > int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, > struct xe_gt_tlb_invalidation_fence > *fence, > struct xe_vma *vma); > +void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm); > int xe_gt_tlb_invalidation_range(struct xe_gt *gt, > struct xe_gt_tlb_invalidation_fence > *fence, > u64 start, u64 end, u32 asid); > diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c > index 99b97bf37c05..c5060011ad43 100644 > --- a/drivers/gpu/drm/xe/xe_pt.c > +++ b/drivers/gpu/drm/xe/xe_pt.c > @@ -214,6 +214,20 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, > struct llist_head *deferred) > xe_pt_free(pt); > } > > +/** > + * xe_pt_clear() - Clear a page-table. > + * @xe: xe device. > + * @pt: The page-table. > + * > + * Clears page-table by setting to zero. > + */ > +void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt) > +{ > + struct iosys_map *map = &pt->bo->vmap; > + > + xe_map_memset(xe, map, 0, 0, SZ_4K); > +} > + > /** > * DOC: Pagetable building > * > diff --git a/drivers/gpu/drm/xe/xe_pt.h b/drivers/gpu/drm/xe/xe_pt.h > index 9ab386431cad..8e43912ae8e9 100644 > --- a/drivers/gpu/drm/xe/xe_pt.h > +++ b/drivers/gpu/drm/xe/xe_pt.h > @@ -13,6 +13,7 @@ struct dma_fence; > struct xe_bo; > struct xe_device; > struct xe_exec_queue; > +struct xe_svm_range; > struct xe_sync_entry; > struct xe_tile; > struct xe_vm; > @@ -35,6 +36,8 @@ void xe_pt_populate_empty(struct xe_tile *tile, > struct xe_vm *vm, > > void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head > *deferred); > > +void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt); > + > int xe_pt_update_ops_prepare(struct xe_tile *tile, struct xe_vma_ops > *vops); > struct dma_fence *xe_pt_update_ops_run(struct xe_tile *tile, > struct xe_vma_ops *vops); > diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c > index bc34e6738c8c..82026c5a154d 100644 > --- a/drivers/gpu/drm/xe/xe_vm.c > +++ b/drivers/gpu/drm/xe/xe_vm.c > @@ -1537,8 +1537,30 @@ struct xe_vm *xe_vm_create(struct xe_device > *xe, u32 flags) > > static void xe_vm_close(struct xe_vm *vm) > { > + bool migration = (vm->flags & XE_VM_FLAG_MIGRATION); Do we need a separate bool here? Only used in one place AFAICT. Otherwise, Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com> > + > down_write(&vm->lock); > + > vm->size = 0; > + > + if (!migration) { > + struct xe_tile *tile; > + struct xe_gt *gt; > + u8 id; > + > + /* Wait for pending binds */ > + dma_resv_wait_timeout(xe_vm_resv(vm), > + DMA_RESV_USAGE_BOOKKEEP, > + false, MAX_SCHEDULE_TIMEOUT); > + > + for_each_tile(tile, vm->xe, id) > + if (vm->pt_root[id]) > + xe_pt_clear(vm->xe, vm- > >pt_root[id]); > + > + for_each_gt(gt, vm->xe, id) > + xe_gt_tlb_invalidation_vm(gt, vm); > + } > + > up_write(&vm->lock); > } >
On Fri, Feb 07, 2025 at 11:15:38AM +0100, Thomas Hellström wrote: > On Wed, 2025-01-29 at 11:51 -0800, Matthew Brost wrote: > > Clear root PT entry and invalidate entire VM's address space when > > closing the VM. Will prevent the GPU from accessing any of the VM's > > memory after closing. > > > > v2: > > - s/vma/vm in kernel doc (CI) > > - Don't nuke migration VM as this occur at driver unload (CI) > > v3: > > - Rebase and pull into SVM series (Thomas) > > - Wait for pending binds (Thomas) > > > > Signed-off-by: Matthew Brost <matthew.brost@intel.com> > > --- > > drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 24 > > +++++++++++++++++++++ > > drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h | 2 ++ > > drivers/gpu/drm/xe/xe_pt.c | 14 ++++++++++++ > > drivers/gpu/drm/xe/xe_pt.h | 3 +++ > > drivers/gpu/drm/xe/xe_vm.c | 22 +++++++++++++++++++ > > 5 files changed, 65 insertions(+) > > > > diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > > b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > > index 0a93831c0a02..1ef21ed01d1b 100644 > > --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > > +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c > > @@ -410,6 +410,30 @@ int xe_gt_tlb_invalidation_range(struct xe_gt > > *gt, > > return send_tlb_invalidation(>->uc.guc, fence, action, > > len); > > } > > > > +/** > > + * xe_gt_tlb_invalidation_vm - Issue a TLB invalidation on this GT > > for a VM > > + * @gt: graphics tile > > + * @vm: VM to invalidate > > + * > > + * Invalidate entire VM's address space > > + */ > > +void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm) > > +{ > > + struct xe_gt_tlb_invalidation_fence fence; > > + u64 range = 1ull << vm->xe->info.va_bits; > > + int ret; > > + > > + xe_gt_tlb_invalidation_fence_init(gt, &fence, true); > > + > > + ret = xe_gt_tlb_invalidation_range(gt, &fence, 0, range, vm- > > >usm.asid); > > + if (ret < 0) { > > + xe_gt_tlb_invalidation_fence_fini(&fence); > > + return; > > + } > > + > > + xe_gt_tlb_invalidation_fence_wait(&fence); > > +} > > + > > /** > > * xe_gt_tlb_invalidation_vma - Issue a TLB invalidation on this GT > > for a VMA > > * @gt: GT structure > > diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > > b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > > index 672acfcdf0d7..abe9b03d543e 100644 > > --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > > +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h > > @@ -12,6 +12,7 @@ > > > > struct xe_gt; > > struct xe_guc; > > +struct xe_vm; > > struct xe_vma; > > > > int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt); > > @@ -21,6 +22,7 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt); > > int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, > > struct xe_gt_tlb_invalidation_fence > > *fence, > > struct xe_vma *vma); > > +void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm); > > int xe_gt_tlb_invalidation_range(struct xe_gt *gt, > > struct xe_gt_tlb_invalidation_fence > > *fence, > > u64 start, u64 end, u32 asid); > > diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c > > index 99b97bf37c05..c5060011ad43 100644 > > --- a/drivers/gpu/drm/xe/xe_pt.c > > +++ b/drivers/gpu/drm/xe/xe_pt.c > > @@ -214,6 +214,20 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, > > struct llist_head *deferred) > > xe_pt_free(pt); > > } > > > > +/** > > + * xe_pt_clear() - Clear a page-table. > > + * @xe: xe device. > > + * @pt: The page-table. > > + * > > + * Clears page-table by setting to zero. > > + */ > > +void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt) > > +{ > > + struct iosys_map *map = &pt->bo->vmap; > > + > > + xe_map_memset(xe, map, 0, 0, SZ_4K); > > +} > > + > > /** > > * DOC: Pagetable building > > * > > diff --git a/drivers/gpu/drm/xe/xe_pt.h b/drivers/gpu/drm/xe/xe_pt.h > > index 9ab386431cad..8e43912ae8e9 100644 > > --- a/drivers/gpu/drm/xe/xe_pt.h > > +++ b/drivers/gpu/drm/xe/xe_pt.h > > @@ -13,6 +13,7 @@ struct dma_fence; > > struct xe_bo; > > struct xe_device; > > struct xe_exec_queue; > > +struct xe_svm_range; > > struct xe_sync_entry; > > struct xe_tile; > > struct xe_vm; > > @@ -35,6 +36,8 @@ void xe_pt_populate_empty(struct xe_tile *tile, > > struct xe_vm *vm, > > > > void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head > > *deferred); > > > > +void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt); > > + > > int xe_pt_update_ops_prepare(struct xe_tile *tile, struct xe_vma_ops > > *vops); > > struct dma_fence *xe_pt_update_ops_run(struct xe_tile *tile, > > struct xe_vma_ops *vops); > > diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c > > index bc34e6738c8c..82026c5a154d 100644 > > --- a/drivers/gpu/drm/xe/xe_vm.c > > +++ b/drivers/gpu/drm/xe/xe_vm.c > > @@ -1537,8 +1537,30 @@ struct xe_vm *xe_vm_create(struct xe_device > > *xe, u32 flags) > > > > static void xe_vm_close(struct xe_vm *vm) > > { > > + bool migration = (vm->flags & XE_VM_FLAG_MIGRATION); > > Do we need a separate bool here? Only used in one place AFAICT. > Nope. Let me drop the bool. Matt > Otherwise, > Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com> > > > > + > > down_write(&vm->lock); > > + > > vm->size = 0; > > + > > + if (!migration) { > > + struct xe_tile *tile; > > + struct xe_gt *gt; > > + u8 id; > > + > > + /* Wait for pending binds */ > > + dma_resv_wait_timeout(xe_vm_resv(vm), > > + DMA_RESV_USAGE_BOOKKEEP, > > + false, MAX_SCHEDULE_TIMEOUT); > > + > > + for_each_tile(tile, vm->xe, id) > > + if (vm->pt_root[id]) > > + xe_pt_clear(vm->xe, vm- > > >pt_root[id]); > > + > > + for_each_gt(gt, vm->xe, id) > > + xe_gt_tlb_invalidation_vm(gt, vm); > > + } > > + > > up_write(&vm->lock); > > } > > >
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index 0a93831c0a02..1ef21ed01d1b 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -410,6 +410,30 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt, return send_tlb_invalidation(>->uc.guc, fence, action, len); } +/** + * xe_gt_tlb_invalidation_vm - Issue a TLB invalidation on this GT for a VM + * @gt: graphics tile + * @vm: VM to invalidate + * + * Invalidate entire VM's address space + */ +void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm) +{ + struct xe_gt_tlb_invalidation_fence fence; + u64 range = 1ull << vm->xe->info.va_bits; + int ret; + + xe_gt_tlb_invalidation_fence_init(gt, &fence, true); + + ret = xe_gt_tlb_invalidation_range(gt, &fence, 0, range, vm->usm.asid); + if (ret < 0) { + xe_gt_tlb_invalidation_fence_fini(&fence); + return; + } + + xe_gt_tlb_invalidation_fence_wait(&fence); +} + /** * xe_gt_tlb_invalidation_vma - Issue a TLB invalidation on this GT for a VMA * @gt: GT structure diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h index 672acfcdf0d7..abe9b03d543e 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h @@ -12,6 +12,7 @@ struct xe_gt; struct xe_guc; +struct xe_vm; struct xe_vma; int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt); @@ -21,6 +22,7 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt); int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence, struct xe_vma *vma); +void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm); int xe_gt_tlb_invalidation_range(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence, u64 start, u64 end, u32 asid); diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index 99b97bf37c05..c5060011ad43 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -214,6 +214,20 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred) xe_pt_free(pt); } +/** + * xe_pt_clear() - Clear a page-table. + * @xe: xe device. + * @pt: The page-table. + * + * Clears page-table by setting to zero. + */ +void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt) +{ + struct iosys_map *map = &pt->bo->vmap; + + xe_map_memset(xe, map, 0, 0, SZ_4K); +} + /** * DOC: Pagetable building * diff --git a/drivers/gpu/drm/xe/xe_pt.h b/drivers/gpu/drm/xe/xe_pt.h index 9ab386431cad..8e43912ae8e9 100644 --- a/drivers/gpu/drm/xe/xe_pt.h +++ b/drivers/gpu/drm/xe/xe_pt.h @@ -13,6 +13,7 @@ struct dma_fence; struct xe_bo; struct xe_device; struct xe_exec_queue; +struct xe_svm_range; struct xe_sync_entry; struct xe_tile; struct xe_vm; @@ -35,6 +36,8 @@ void xe_pt_populate_empty(struct xe_tile *tile, struct xe_vm *vm, void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred); +void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt); + int xe_pt_update_ops_prepare(struct xe_tile *tile, struct xe_vma_ops *vops); struct dma_fence *xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index bc34e6738c8c..82026c5a154d 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1537,8 +1537,30 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) static void xe_vm_close(struct xe_vm *vm) { + bool migration = (vm->flags & XE_VM_FLAG_MIGRATION); + down_write(&vm->lock); + vm->size = 0; + + if (!migration) { + struct xe_tile *tile; + struct xe_gt *gt; + u8 id; + + /* Wait for pending binds */ + dma_resv_wait_timeout(xe_vm_resv(vm), + DMA_RESV_USAGE_BOOKKEEP, + false, MAX_SCHEDULE_TIMEOUT); + + for_each_tile(tile, vm->xe, id) + if (vm->pt_root[id]) + xe_pt_clear(vm->xe, vm->pt_root[id]); + + for_each_gt(gt, vm->xe, id) + xe_gt_tlb_invalidation_vm(gt, vm); + } + up_write(&vm->lock); }
Clear root PT entry and invalidate entire VM's address space when closing the VM. Will prevent the GPU from accessing any of the VM's memory after closing. v2: - s/vma/vm in kernel doc (CI) - Don't nuke migration VM as this occur at driver unload (CI) v3: - Rebase and pull into SVM series (Thomas) - Wait for pending binds (Thomas) Signed-off-by: Matthew Brost <matthew.brost@intel.com> --- drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 24 +++++++++++++++++++++ drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h | 2 ++ drivers/gpu/drm/xe/xe_pt.c | 14 ++++++++++++ drivers/gpu/drm/xe/xe_pt.h | 3 +++ drivers/gpu/drm/xe/xe_vm.c | 22 +++++++++++++++++++ 5 files changed, 65 insertions(+)