From 7440adb405dfc4abe21bc95abf3481e6a6649c05 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 13 Feb 2025 14:46:44 -0800 Subject: [PATCH] mm: allow vma_start_read_locked/vma_start_read_locked_nested to fail With upcoming replacement of vm_lock with vm_refcnt, we need to handle a possibility of vma_start_read_locked/vma_start_read_locked_nested failing due to refcount overflow. Prepare for such possibility by changing these APIs and adjusting their users. Link: https://lkml.kernel.org/r/20250213224655.1680278-8-surenb@google.com Signed-off-by: Suren Baghdasaryan Cc: Lokesh Gidra Tested-by: Shivank Garg Link: https://lkml.kernel.org/r/5e19ec93-8307-47c2-bb13-3ddf7150624e@amd.com Reviewed-by: Vlastimil Babka Cc: Christian Brauner Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Jann Horn Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Klara Modin Cc: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Mateusz Guzik Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pasha Tatashin Cc: "Paul E . McKenney" Cc: Peter Xu Cc: Peter Zijlstra (Intel) Cc: Shakeel Butt Cc: Sourav Panda Cc: Wei Yang Cc: Will Deacon Cc: Heiko Carstens Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- include/linux/mm.h | 6 ++++-- mm/userfaultfd.c | 30 +++++++++++++++++++++++------- 2 files changed, 27 insertions(+), 9 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 003c3e5c0a96..09b48af68699 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -747,10 +747,11 @@ static inline bool vma_start_read(struct vm_area_struct *vma) * not be used in such cases because it might fail due to mm_lock_seq overflow. * This functionality is used to obtain vma read lock and drop the mmap read lock. */ -static inline void vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass) +static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass) { mmap_assert_locked(vma->vm_mm); down_read_nested(&vma->vm_lock.lock, subclass); + return true; } /* @@ -759,10 +760,11 @@ static inline void vma_start_read_locked_nested(struct vm_area_struct *vma, int * not be used in such cases because it might fail due to mm_lock_seq overflow. * This functionality is used to obtain vma read lock and drop the mmap read lock. */ -static inline void vma_start_read_locked(struct vm_area_struct *vma) +static inline bool vma_start_read_locked(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); down_read(&vma->vm_lock.lock); + return true; } static inline void vma_end_read(struct vm_area_struct *vma) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 48ac81bbfee6..fbf2cf62ab9f 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -85,8 +85,12 @@ static struct vm_area_struct *uffd_lock_vma(struct mm_struct *mm, mmap_read_lock(mm); vma = find_vma_and_prepare_anon(mm, address); - if (!IS_ERR(vma)) - vma_start_read_locked(vma); + if (!IS_ERR(vma)) { + bool locked = vma_start_read_locked(vma); + + if (!locked) + vma = ERR_PTR(-EAGAIN); + } mmap_read_unlock(mm); return vma; @@ -1555,12 +1559,24 @@ static int uffd_move_lock(struct mm_struct *mm, mmap_read_lock(mm); err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap); - if (!err) { - vma_start_read_locked(*dst_vmap); - if (*dst_vmap != *src_vmap) - vma_start_read_locked_nested(*src_vmap, - SINGLE_DEPTH_NESTING); + if (err) + goto out; + + if (!vma_start_read_locked(*dst_vmap)) { + err = -EAGAIN; + goto out; } + + /* Nothing further to do if both vmas are locked. */ + if (*dst_vmap == *src_vmap) + goto out; + + if (!vma_start_read_locked_nested(*src_vmap, SINGLE_DEPTH_NESTING)) { + /* Undo dst_vmap locking if src_vmap failed to lock */ + vma_end_read(*dst_vmap); + err = -EAGAIN; + } +out: mmap_read_unlock(mm); return err; } -- 2.50.1