mm: handle userfaults under VMA lock

Enable handle_userfault to operate under VMA lock by releasing VMA lock
instead of mmap_lock and retrying.  Note that FAULT_FLAG_RETRY_NOWAIT
should never be used when handling faults under per-VMA lock protection
because that would break the assumption that lock is dropped on retry.

[[email protected]: fix a lockdep issue in vma_assert_write_locked]
  Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Suren Baghdasaryan <[email protected]>
Acked-by: Peter Xu <[email protected]>
Cc: Alistair Popple <[email protected]>
Cc: Al Viro <[email protected]>
Cc: Christian Brauner <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: David Howells <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: Hillf Danton <[email protected]>
Cc: "Huang, Ying" <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Jan Kara <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Josef Bacik <[email protected]>
Cc: Laurent Dufour <[email protected]>
Cc: Liam R. Howlett <[email protected]>
Cc: Lorenzo Stoakes <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Michel Lespinasse <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Pavel Tatashin <[email protected]>
Cc: Punit Agrawal <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Yu Zhao <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

1 files changed, 20 insertions, 0 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0d16208178c7..c1db400e83cb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -679,6 +679,7 @@ static inline void vma_end_read(struct vm_area_struct *vma)
 	rcu_read_unlock();
 }
 
+/* WARNING! Can only be used if mmap_lock is expected to be write-locked */
 static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
 {
 	mmap_assert_write_locked(vma->vm_mm);
@@ -721,6 +722,12 @@ static inline void vma_assert_write_locked(struct vm_area_struct *vma)
 	VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma);
 }
 
+static inline void vma_assert_locked(struct vm_area_struct *vma)
+{
+	if (!rwsem_is_locked(&vma->vm_lock->lock))
+		vma_assert_write_locked(vma);
+}
+
 static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached)
 {
 	/* When detaching vma should be write-locked */
@@ -737,6 +744,14 @@ static inline void release_fault_lock(struct vm_fault *vmf)
 		mmap_read_unlock(vmf->vma->vm_mm);
 }
 
+static inline void assert_fault_locked(struct vm_fault *vmf)
+{
+	if (vmf->flags & FAULT_FLAG_VMA_LOCK)
+		vma_assert_locked(vmf->vma);
+	else
+		mmap_assert_locked(vmf->vma->vm_mm);
+}
+
 struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
 					  unsigned long address);
 
@@ -762,6 +777,11 @@ static inline void release_fault_lock(struct vm_fault *vmf)
 	mmap_read_unlock(vmf->vma->vm_mm);
 }
 
+static inline void assert_fault_locked(struct vm_fault *vmf)
+{
+	mmap_assert_locked(vmf->vma->vm_mm);
+}
+
 #endif /* CONFIG_PER_VMA_LOCK */
 
 extern const struct vm_operations_struct vma_dummy_vm_ops;