From 2577b202458cddff85cc154b1fe7f313e0d1f418 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Mon, 14 Apr 2025 14:25:40 +0100 Subject: [PATCH] drm/xe/userptr: fix notifier vs folio deadlock MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit User is reporting what smells like notifier vs folio deadlock, where migrate_pages_batch() on core kernel side is holding folio lock(s) and then interacting with the mappings of it, however those mappings are tied to some userptr, which means calling into the notifier callback and grabbing the notifier lock. With perfect timing it looks possible that the pages we pulled from the hmm fault can get sniped by migrate_pages_batch() at the same time that we are holding the notifier lock to mark the pages as accessed/dirty, but at this point we also want to grab the folio locks(s) to mark them as dirty, but if they are contended from notifier/migrate_pages_batch side then we deadlock since folio lock won't be dropped until we drop the notifier lock. Fortunately the mark_page_accessed/dirty is not really needed in the first place it seems and should have already been done by hmm fault, so just remove it. Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4765 Fixes: 0a98219bcc96 ("drm/xe/hmm: Don't dereference struct page pointers without notifier lock") Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Matthew Brost Cc: # v6.10+ Reviewed-by: Thomas Hellström Reviewed-by: Matthew Brost Link: https://lore.kernel.org/r/20250414132539.26654-2-matthew.auld@intel.com (cherry picked from commit bd7c0cb695e87c0e43247be8196b4919edbe0e85) Signed-off-by: Lucas De Marchi --- drivers/gpu/drm/xe/xe_hmm.c | 24 ------------------------ 1 file changed, 24 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c index c3cc0fa105e8..57b71956ddf4 100644 --- a/drivers/gpu/drm/xe/xe_hmm.c +++ b/drivers/gpu/drm/xe/xe_hmm.c @@ -19,29 +19,6 @@ static u64 xe_npages_in_range(unsigned long start, unsigned long end) return (end - start) >> PAGE_SHIFT; } -/** - * xe_mark_range_accessed() - mark a range is accessed, so core mm - * have such information for memory eviction or write back to - * hard disk - * @range: the range to mark - * @write: if write to this range, we mark pages in this range - * as dirty - */ -static void xe_mark_range_accessed(struct hmm_range *range, bool write) -{ - struct page *page; - u64 i, npages; - - npages = xe_npages_in_range(range->start, range->end); - for (i = 0; i < npages; i++) { - page = hmm_pfn_to_page(range->hmm_pfns[i]); - if (write) - set_page_dirty_lock(page); - - mark_page_accessed(page); - } -} - static int xe_alloc_sg(struct xe_device *xe, struct sg_table *st, struct hmm_range *range, struct rw_semaphore *notifier_sem) { @@ -331,7 +308,6 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, if (ret) goto out_unlock; - xe_mark_range_accessed(&hmm_range, write); userptr->sg = &userptr->sgt; xe_hmm_userptr_set_mapped(uvma); userptr->notifier_seq = hmm_range.notifier_seq; -- 2.49.0