From 49b0638502da097c15d46cd4e871dbaa022caf7c Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Fri, 4 Aug 2023 08:27:19 -0700 Subject: mm: enable page walking API to lock vmas during the walk walk_page_range() and friends often operate under write-locked mmap_lock. With introduction of vma locks, the vmas have to be locked as well during such walks to prevent concurrent page faults in these areas. Add an additional member to mm_walk_ops to indicate locking requirements for the walk. The change ensures that page walks which prevent concurrent page faults by write-locking mmap_lock, operate correctly after introduction of per-vma locks. With per-vma locks page faults can be handled under vma lock without taking mmap_lock at all, so write locking mmap_lock would not stop them. The change ensures vmas are properly locked during such walks. A sample issue this solves is do_mbind() performing queue_pages_range() to queue pages for migration. Without this change a concurrent page can be faulted into the area and be left out of migration. Link: https://lkml.kernel.org/r/20230804152724.3090321-2-surenb@google.com Signed-off-by: Suren Baghdasaryan Suggested-by: Linus Torvalds Suggested-by: Jann Horn Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Johannes Weiner Cc: Laurent Dufour Cc: Liam Howlett Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Michel Lespinasse Cc: Peter Xu Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- include/linux/pagewalk.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 27a6df448ee5..27cd1e59ccf7 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -6,6 +6,16 @@ struct mm_walk; +/* Locking requirement during a page walk. */ +enum page_walk_lock { + /* mmap_lock should be locked for read to stabilize the vma tree */ + PGWALK_RDLOCK = 0, + /* vma will be write-locked during the walk */ + PGWALK_WRLOCK = 1, + /* vma is expected to be already write-locked during the walk */ + PGWALK_WRLOCK_VERIFY = 2, +}; + /** * struct mm_walk_ops - callbacks for walk_page_range * @pgd_entry: if set, called for each non-empty PGD (top-level) entry @@ -66,6 +76,7 @@ struct mm_walk_ops { int (*pre_vma)(unsigned long start, unsigned long end, struct mm_walk *walk); void (*post_vma)(struct mm_walk *walk); + enum page_walk_lock walk_lock; }; /* -- cgit v1.2.3