On Tue, Mar 03, 2026 at 02:34:09PM +0100, Thomas Hellström wrote: > Now that the two-pass notifier flow uses xe_vma_userptr_do_inval() for > the fence-wait + TLB-invalidate work, extend it to support a further > deferred TLB wait: > > - xe_vma_userptr_do_inval(): when the embedded finish handle is free, > submit the TLB invalidation asynchronously (xe_vm_invalidate_vma_submit) > and return &userptr->finish so the mmu_notifier core schedules a third > pass. When the handle is occupied by a concurrent invalidation, fall > back to the synchronous xe_vm_invalidate_vma() path. > > - xe_vma_userptr_complete_tlb_inval(): new helper called from > invalidate_finish when tlb_inval_submitted is set. Waits for the > previously submitted batch and unmaps the gpusvm pages. > > xe_vma_userptr_invalidate_finish() dispatches between the two helpers > via tlb_inval_submitted, making the three possible flows explicit: > > pass1 (fences pending) -> invalidate_finish -> do_inval (sync TLB) > pass1 (fences done) -> do_inval -> invalidate_finish > -> complete_tlb_inval (deferred TLB) > pass1 (finish occupied) -> do_inval (sync TLB, inline) > > In multi-GPU scenarios this allows TLB flushes to be submitted on all > GPUs in one pass before any of them are waited on. > > Also adds xe_vm_invalidate_vma_submit() which submits the TLB range > invalidation without blocking, populating a xe_tlb_inval_batch that > the caller waits on separately. > > v3: > - Add locking asserts and notifier state asserts (Matt Brost) > - Update the locking documentation of the notifier > state members (Matt Brost) > - Remove unrelated code formatting changes (Matt Brost) > > Assisted-by: GitHub Copilot:claude-sonnet-4.6 > Signed-off-by: Thomas Hellström <[email protected]>
Reviewed-by: Matthew Brost <[email protected]> > --- > drivers/gpu/drm/xe/xe_userptr.c | 63 ++++++++++++++++++++++++++++----- > drivers/gpu/drm/xe/xe_userptr.h | 17 +++++++++ > drivers/gpu/drm/xe/xe_vm.c | 38 +++++++++++++++----- > drivers/gpu/drm/xe/xe_vm.h | 2 ++ > 4 files changed, 104 insertions(+), 16 deletions(-) > > diff --git a/drivers/gpu/drm/xe/xe_userptr.c b/drivers/gpu/drm/xe/xe_userptr.c > index 37032b8125a6..6761005c0b90 100644 > --- a/drivers/gpu/drm/xe/xe_userptr.c > +++ b/drivers/gpu/drm/xe/xe_userptr.c > @@ -8,6 +8,7 @@ > > #include <linux/mm.h> > > +#include "xe_tlb_inval.h" > #include "xe_trace_bo.h" > > static void xe_userptr_assert_in_notifier(struct xe_vm *vm) > @@ -81,8 +82,8 @@ int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma) > &ctx); > } > > -static void xe_vma_userptr_do_inval(struct xe_vm *vm, struct xe_userptr_vma > *uvma, > - bool is_deferred) > +static struct mmu_interval_notifier_finish * > +xe_vma_userptr_do_inval(struct xe_vm *vm, struct xe_userptr_vma *uvma, bool > is_deferred) > { > struct xe_userptr *userptr = &uvma->userptr; > struct xe_vma *vma = &uvma->vma; > @@ -93,6 +94,8 @@ static void xe_vma_userptr_do_inval(struct xe_vm *vm, > struct xe_userptr_vma *uvm > long err; > > xe_userptr_assert_in_notifier(vm); > + if (is_deferred) > + xe_assert(vm->xe, userptr->finish_inuse && > !userptr->tlb_inval_submitted); > > err = dma_resv_wait_timeout(xe_vm_resv(vm), > DMA_RESV_USAGE_BOOKKEEP, > @@ -100,6 +103,19 @@ static void xe_vma_userptr_do_inval(struct xe_vm *vm, > struct xe_userptr_vma *uvm > XE_WARN_ON(err <= 0); > > if (xe_vm_in_fault_mode(vm) && userptr->initial_bind) { > + if (!userptr->finish_inuse) { > + /* > + * Defer the TLB wait to an extra pass so the caller > + * can pipeline TLB flushes across GPUs before waiting > + * on any of them. > + */ > + xe_assert(vm->xe, !userptr->tlb_inval_submitted); > + userptr->finish_inuse = true; > + userptr->tlb_inval_submitted = true; > + err = xe_vm_invalidate_vma_submit(vma, > &userptr->inval_batch); > + XE_WARN_ON(err); > + return &userptr->finish; > + } > err = xe_vm_invalidate_vma(vma); > XE_WARN_ON(err); > } > @@ -108,6 +124,28 @@ static void xe_vma_userptr_do_inval(struct xe_vm *vm, > struct xe_userptr_vma *uvm > userptr->finish_inuse = false; > drm_gpusvm_unmap_pages(&vm->svm.gpusvm, &uvma->userptr.pages, > xe_vma_size(vma) >> PAGE_SHIFT, &ctx); > + return NULL; > +} > + > +static void > +xe_vma_userptr_complete_tlb_inval(struct xe_vm *vm, struct xe_userptr_vma > *uvma) > +{ > + struct xe_userptr *userptr = &uvma->userptr; > + struct xe_vma *vma = &uvma->vma; > + struct drm_gpusvm_ctx ctx = { > + .in_notifier = true, > + .read_only = xe_vma_read_only(vma), > + }; > + > + xe_userptr_assert_in_notifier(vm); > + xe_assert(vm->xe, userptr->finish_inuse); > + xe_assert(vm->xe, userptr->tlb_inval_submitted); > + > + xe_tlb_inval_batch_wait(&userptr->inval_batch); > + userptr->tlb_inval_submitted = false; > + userptr->finish_inuse = false; > + drm_gpusvm_unmap_pages(&vm->svm.gpusvm, &uvma->userptr.pages, > + xe_vma_size(vma) >> PAGE_SHIFT, &ctx); > } > > static struct mmu_interval_notifier_finish * > @@ -153,11 +191,10 @@ xe_vma_userptr_invalidate_pass1(struct xe_vm *vm, > struct xe_userptr_vma *uvma) > * If it's already in use, or all fences are already signaled, > * proceed directly to invalidation without deferring. > */ > - if (signaled || userptr->finish_inuse) { > - xe_vma_userptr_do_inval(vm, uvma, false); > - return NULL; > - } > + if (signaled || userptr->finish_inuse) > + return xe_vma_userptr_do_inval(vm, uvma, false); > > + /* Defer: the notifier core will call invalidate_finish once done. */ > userptr->finish_inuse = true; > > return &userptr->finish; > @@ -205,7 +242,15 @@ static void xe_vma_userptr_invalidate_finish(struct > mmu_interval_notifier_finish > xe_vma_start(vma), xe_vma_size(vma)); > > down_write(&vm->svm.gpusvm.notifier_lock); > - xe_vma_userptr_do_inval(vm, uvma, true); > + /* > + * If a TLB invalidation was previously submitted (deferred from the > + * synchronous pass1 fallback), wait for it and unmap pages. > + * Otherwise, fences have now completed: invalidate the TLB and unmap. > + */ > + if (uvma->userptr.tlb_inval_submitted) > + xe_vma_userptr_complete_tlb_inval(vm, uvma); > + else > + xe_vma_userptr_do_inval(vm, uvma, true); > up_write(&vm->svm.gpusvm.notifier_lock); > trace_xe_vma_userptr_invalidate_complete(vma); > } > @@ -243,7 +288,9 @@ void xe_vma_userptr_force_invalidate(struct > xe_userptr_vma *uvma) > > finish = xe_vma_userptr_invalidate_pass1(vm, uvma); > if (finish) > - xe_vma_userptr_do_inval(vm, uvma, true); > + finish = xe_vma_userptr_do_inval(vm, uvma, true); > + if (finish) > + xe_vma_userptr_complete_tlb_inval(vm, uvma); > } > #endif > > diff --git a/drivers/gpu/drm/xe/xe_userptr.h b/drivers/gpu/drm/xe/xe_userptr.h > index e1830c2f5fd2..2a3cd1b5efbb 100644 > --- a/drivers/gpu/drm/xe/xe_userptr.h > +++ b/drivers/gpu/drm/xe/xe_userptr.h > @@ -14,6 +14,8 @@ > > #include <drm/drm_gpusvm.h> > > +#include "xe_tlb_inval_types.h" > + > struct xe_vm; > struct xe_vma; > struct xe_userptr_vma; > @@ -63,12 +65,27 @@ struct xe_userptr { > * alternatively by the same lock in read mode *and* the vm resv held. > */ > struct mmu_interval_notifier_finish finish; > + /** > + * @inval_batch: TLB invalidation batch for deferred completion. > + * Stores an in-flight TLB invalidation submitted during a two-pass > + * notifier so the wait can be deferred to a subsequent pass, allowing > + * multiple GPUs to be signalled before any of them are waited on. > + * Protected using the same locking as @finish. > + */ > + struct xe_tlb_inval_batch inval_batch; > /** > * @finish_inuse: Whether @finish is currently in use by an in-progress > * two-pass invalidation. > * Protected using the same locking as @finish. > */ > bool finish_inuse; > + /** > + * @tlb_inval_submitted: Whether a TLB invalidation has been submitted > + * via @inval_batch and is pending completion. When set, the next pass > + * must call xe_tlb_inval_batch_wait() before reusing @inval_batch. > + * Protected using the same locking as @finish. > + */ > + bool tlb_inval_submitted; > /** > * @initial_bind: user pointer has been bound at least once. > * write: vm->svm.gpusvm.notifier_lock in read mode and vm->resv held. > diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c > index a3c2e8cefec7..fdad9329dfb4 100644 > --- a/drivers/gpu/drm/xe/xe_vm.c > +++ b/drivers/gpu/drm/xe/xe_vm.c > @@ -3967,20 +3967,23 @@ void xe_vm_unlock(struct xe_vm *vm) > } > > /** > - * xe_vm_invalidate_vma - invalidate GPU mappings for VMA without a lock > + * xe_vm_invalidate_vma_submit - Submit a job to invalidate GPU mappings for > + * VMA. > * @vma: VMA to invalidate > + * @batch: TLB invalidation batch to populate; caller must later call > + * xe_tlb_inval_batch_wait() on it to wait for completion > * > * Walks a list of page tables leaves which it memset the entries owned by > this > - * VMA to zero, invalidates the TLBs, and block until TLBs invalidation is > - * complete. > + * VMA to zero, invalidates the TLBs, but doesn't block waiting for TLB flush > + * to complete, but instead populates @batch which can be waited on using > + * xe_tlb_inval_batch_wait(). > * > * Returns 0 for success, negative error code otherwise. > */ > -int xe_vm_invalidate_vma(struct xe_vma *vma) > +int xe_vm_invalidate_vma_submit(struct xe_vma *vma, struct > xe_tlb_inval_batch *batch) > { > struct xe_device *xe = xe_vma_vm(vma)->xe; > struct xe_vm *vm = xe_vma_vm(vma); > - struct xe_tlb_inval_batch batch; > struct xe_tile *tile; > u8 tile_mask = 0; > int ret = 0; > @@ -4023,14 +4026,33 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) > > ret = xe_tlb_inval_range_tilemask_submit(xe, xe_vma_vm(vma)->usm.asid, > xe_vma_start(vma), > xe_vma_end(vma), > - tile_mask, &batch); > + tile_mask, batch); > > /* WRITE_ONCE pairs with READ_ONCE in xe_vm_has_valid_gpu_mapping() */ > WRITE_ONCE(vma->tile_invalidated, vma->tile_mask); > + return ret; > +} > + > +/** > + * xe_vm_invalidate_vma - invalidate GPU mappings for VMA without a lock > + * @vma: VMA to invalidate > + * > + * Walks a list of page tables leaves which it memset the entries owned by > this > + * VMA to zero, invalidates the TLBs, and block until TLBs invalidation is > + * complete. > + * > + * Returns 0 for success, negative error code otherwise. > + */ > +int xe_vm_invalidate_vma(struct xe_vma *vma) > +{ > + struct xe_tlb_inval_batch batch; > + int ret; > > - if (!ret) > - xe_tlb_inval_batch_wait(&batch); > + ret = xe_vm_invalidate_vma_submit(vma, &batch); > + if (ret) > + return ret; > > + xe_tlb_inval_batch_wait(&batch); > return ret; > } > > diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h > index 62f4b6fec0bc..0bc7ed23eeae 100644 > --- a/drivers/gpu/drm/xe/xe_vm.h > +++ b/drivers/gpu/drm/xe/xe_vm.h > @@ -242,6 +242,8 @@ struct dma_fence *xe_vm_range_unbind(struct xe_vm *vm, > > int xe_vm_invalidate_vma(struct xe_vma *vma); > > +int xe_vm_invalidate_vma_submit(struct xe_vma *vma, struct > xe_tlb_inval_batch *batch); > + > int xe_vm_validate_protected(struct xe_vm *vm); > > static inline void xe_vm_queue_rebind_worker(struct xe_vm *vm) > -- > 2.53.0 >
