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. 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 | 40 +++++++++++++++++++++++++++++++-- 1 file changed, 38 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index 382a77a1097e..562b869dc750 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -598,6 +598,39 @@ __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; + + down_read(&mm->mmap_sem); + 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; + } + up_read(&mm->mmap_sem); + + 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 +665,12 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) return -EAGAIN; } - pvec = NULL; - pinned = 0; + /* Quickly exclude any invalid VMA */ + pinned = probe_range(mm, obj->userptr.ptr, obj->base.size); + if (pinned) + return pinned; + pvec = NULL; if (mm == current->mm) { pvec = kvmalloc_array(num_pages, sizeof(struct page *), GFP_KERNEL | -- 2.15.1 _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
