[PATCH v3] drm/xe: Invalidate userptr VMA on page pin fault
Matthew Brost
matthew.brost at intel.com
Mon Mar 11 20:11:46 UTC 2024
On Mon, Mar 11, 2024 at 08:47:50PM +0100, Thomas Hellström wrote:
> On Mon, 2024-03-11 at 12:20 -0700, Matthew Brost wrote:
> > Rather than return an error to the user or ban the VM when userptr
> > VMA
> > page pin fails with -EFAULT, invalidate VMA mappings. This supports
> > the
> > UMD use case of freeing userptr while still having bindings.
> >
> > Now that non-faulting VMs can invalidate VMAs, drop the usm prefix
> > for
> > the tile_invalidated member.
> >
> > v2:
> > - Fix build error (CI)
> > v3:
> > - Don't invalidate VMA if in fault mode, rather kill VM (Thomas)
> > - Update commit message with tile_invalidated name chagne (Thomas)
> > - Wait VM bookkeep slots with VM resv lock (Thomas)
> >
> > Signed-off-by: Matthew Brost <matthew.brost at intel.com>
> > ---
> > drivers/gpu/drm/xe/xe_gt_pagefault.c | 4 ++--
> > drivers/gpu/drm/xe/xe_trace.h | 2 +-
> > drivers/gpu/drm/xe/xe_vm.c | 29 ++++++++++++++++++++------
> > --
> > drivers/gpu/drm/xe/xe_vm_types.h | 7 ++-----
> > 4 files changed, 26 insertions(+), 16 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c
> > b/drivers/gpu/drm/xe/xe_gt_pagefault.c
> > index 73c535193a98..241c294270d9 100644
> > --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
> > +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
> > @@ -69,7 +69,7 @@ static bool access_is_atomic(enum access_type
> > access_type)
> > static bool vma_is_valid(struct xe_tile *tile, struct xe_vma *vma)
> > {
> > return BIT(tile->id) & vma->tile_present &&
> > - !(BIT(tile->id) & vma->usm.tile_invalidated);
> > + !(BIT(tile->id) & vma->tile_invalidated);
> > }
> >
> > static bool vma_matches(struct xe_vma *vma, u64 page_addr)
> > @@ -226,7 +226,7 @@ static int handle_pagefault(struct xe_gt *gt,
> > struct pagefault *pf)
> >
> > if (xe_vma_is_userptr(vma))
> > ret =
> > xe_vma_userptr_check_repin(to_userptr_vma(vma));
> > - vma->usm.tile_invalidated &= ~BIT(tile->id);
> > + vma->tile_invalidated &= ~BIT(tile->id);
> >
> > unlock_dma_resv:
> > drm_exec_fini(&exec);
> > diff --git a/drivers/gpu/drm/xe/xe_trace.h
> > b/drivers/gpu/drm/xe/xe_trace.h
> > index 4ddc55527f9a..846f14507d5f 100644
> > --- a/drivers/gpu/drm/xe/xe_trace.h
> > +++ b/drivers/gpu/drm/xe/xe_trace.h
> > @@ -468,7 +468,7 @@ DEFINE_EVENT(xe_vma, xe_vma_userptr_invalidate,
> > TP_ARGS(vma)
> > );
> >
> > -DEFINE_EVENT(xe_vma, xe_vma_usm_invalidate,
> > +DEFINE_EVENT(xe_vma, xe_vma_invalidate,
> > TP_PROTO(struct xe_vma *vma),
> > TP_ARGS(vma)
> > );
> > diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> > index 643b3701a738..19323b411cb2 100644
> > --- a/drivers/gpu/drm/xe/xe_vm.c
> > +++ b/drivers/gpu/drm/xe/xe_vm.c
> > @@ -724,11 +724,25 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
> > list_for_each_entry_safe(uvma, next, &vm-
> > >userptr.repin_list,
> > userptr.repin_link) {
> > err = xe_vma_userptr_pin_pages(uvma);
> > - if (err < 0)
> > - return err;
> > -
> > list_del_init(&uvma->userptr.repin_link);
> > - list_move_tail(&uvma->vma.combined_links.rebind,
> > &vm->rebind_list);
> > + if (err == -EFAULT && !xe_vm_in_fault_mode(vm)) {
Just remembered this now. This function is not called in fault mode
either. It is called by the exec IOCTL (dma-fence mode) or preempt
rebind worker.
I'll delete this part and add an assert at the top of the function.
> > + /* Wait for pending binds */
> > + xe_vm_lock(vm, false);
> > + dma_resv_wait_timeout(xe_vm_resv(vm),
> > +
> > DMA_RESV_USAGE_BOOKKEEP,
> > + false,
> > MAX_SCHEDULE_TIMEOUT);
> > +
> > + err = xe_vm_invalidate_vma(&uvma->vma);
>
> This can still race with yet another notifier, I think.
>
Wouldn't another invalidate just add it back to the
&vm->userptr.invalidated list and trigger xe_vm_userptr_pin again? That
seems to be fine to me.
The lockdep in xe_vm_invalidate_vma would be unhappy though (I think)?
Maybe we call a version of xe_vm_invalidate_vma here where the lockdep
checks are skipped?
> > + xe_vm_unlock(vm);
> > + if (err)
> > + return err;
> > + } else {
> > + if (err < 0)
>
> And here we should've kept the userptr on the repin list.
>
Yes this is a change in behavior but this change is fine as I think we
try to kill the VM at this point, right? I can change it back if you
feel strongly.
Matt
>
> /Thomas
>
>
> > + return err;
> > +
>
>
> > + list_move_tail(&uvma-
> > >vma.combined_links.rebind,
> > + &vm->rebind_list);
> > + }
> > }
> >
> > return 0;
> > @@ -2024,7 +2038,7 @@ static int xe_vm_prefetch(struct xe_vm *vm,
> > struct xe_vma *vma,
> > return err;
> > }
> >
> > - if (vma->tile_mask != (vma->tile_present & ~vma-
> > >usm.tile_invalidated)) {
> > + if (vma->tile_mask != (vma->tile_present & ~vma-
> > >tile_invalidated)) {
> > return xe_vm_bind(vm, vma, q, xe_vma_bo(vma), syncs,
> > num_syncs,
> > true, first_op, last_op);
> > } else {
> > @@ -3214,9 +3228,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
> > u8 id;
> > int ret;
> >
> > - xe_assert(xe, xe_vm_in_fault_mode(xe_vma_vm(vma)));
> > xe_assert(xe, !xe_vma_is_null(vma));
> > - trace_xe_vma_usm_invalidate(vma);
> > + trace_xe_vma_invalidate(vma);
> >
> > /* Check that we don't race with page-table updates */
> > if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
> > @@ -3254,7 +3267,7 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
> > }
> > }
> >
> > - vma->usm.tile_invalidated = vma->tile_mask;
> > + vma->tile_invalidated = vma->tile_mask;
> >
> > return 0;
> > }
> > diff --git a/drivers/gpu/drm/xe/xe_vm_types.h
> > b/drivers/gpu/drm/xe/xe_vm_types.h
> > index 79b5cab57711..ae5fb565f6bf 100644
> > --- a/drivers/gpu/drm/xe/xe_vm_types.h
> > +++ b/drivers/gpu/drm/xe/xe_vm_types.h
> > @@ -84,11 +84,8 @@ struct xe_vma {
> > struct work_struct destroy_work;
> > };
> >
> > - /** @usm: unified shared memory state */
> > - struct {
> > - /** @tile_invalidated: VMA has been invalidated */
> > - u8 tile_invalidated;
> > - } usm;
> > + /** @tile_invalidated: VMA has been invalidated */
> > + u8 tile_invalidated;
> >
> > /** @tile_mask: Tile mask of where to create binding for
> > this VMA */
> > u8 tile_mask;
>
More information about the Intel-xe
mailing list