Quoting Chris Wilson (2017-12-15 09:53:45) > We want to exclude any GGTT objects from being present on our internal > lists to avoid the deadlock we may run into with our requirement for > struct_mutex during invalidate. However, if the gup_fast fails, we put > the userptr onto the workqueue and mark it as active, so that we > remember to serialise the worker upon mmu_invalidate. > > v2: Hold mmap_sem to prevent modifications to the mm while we probe and > add ourselves to the interval-tree for notificiation. > > Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104209 > Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> > Cc: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx> > Cc: Michał Winiarski <michal.winiarski@xxxxxxxxx> > --- > drivers/gpu/drm/i915/i915_gem_userptr.c | 52 ++++++++++++++++++++++++++++++--- > 1 file changed, 48 insertions(+), 4 deletions(-) > > diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c > index 382a77a1097e..71971020562a 100644 > --- a/drivers/gpu/drm/i915/i915_gem_userptr.c > +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c > @@ -598,6 +598,37 @@ __i915_gem_userptr_get_pages_schedule(struct drm_i915_gem_object *obj) > return ERR_PTR(-EAGAIN); > } > > +static int > +probe_range(struct mm_struct *mm, unsigned long addr, unsigned long len) > +{ > + const unsigned long end = addr + len; > + struct vm_area_struct *vma; > + int ret = -EFAULT; > + > + for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) { > + if (vma->vm_start > addr) > + break; > + > + /* > + * Exclude any VMA that is backed only by struct_page, i.e. > + * IO regions that include our own GGTT mmaps. We cannot handle > + * such ranges, as we may encounter deadlocks around our > + * struct_mutex on mmu_invalidate_range. > + */ > + if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) > + break; > + > + if (vma->vm_end >= end) { > + ret = 0; > + break; > + } > + > + addr = vma->vm_end; > + } > + > + return ret; > +} > + > static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) > { > const int num_pages = obj->base.size >> PAGE_SHIFT; > @@ -632,9 +663,17 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) > return -EAGAIN; > } > > - pvec = NULL; > - pinned = 0; > + /* Quickly exclude any invalid VMA */ > + down_read(&mm->mmap_sem); > + pinned = probe_range(mm, obj->userptr.ptr, obj->base.size); > + if (pinned) > + goto err_mmap_sem; > + > + pinned = __i915_gem_userptr_set_active(obj, true); > + if (pinned) > + goto err_mmap_sem; > > + pvec = NULL; > if (mm == current->mm) { > pvec = kvmalloc_array(num_pages, sizeof(struct page *), > GFP_KERNEL | > @@ -658,14 +697,19 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) > pages = __i915_gem_userptr_alloc_pages(obj, pvec, num_pages); > active = !IS_ERR(pages); > } > - if (active) > - __i915_gem_userptr_set_active(obj, true); > + if (!active) > + __i915_gem_userptr_set_active(obj, false); > + up_read(&mm->mmap_sem); Otoh, if we are holding mmap_sem all this time, we don't need to call set_active twice as we should be serialized with mmu-invalidate. -Chris _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
