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 <surenb@google.com>
Suggested-by: Linus Torvalds <torvalds@linuxfoundation.org>
Suggested-by: Jann Horn <jannh@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Laurent Dufour <ldufour@linux.ibm.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Michel Lespinasse <michel@lespinasse.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 16 insertions, 9 deletions

diff --git a/mm/ksm.c b/mm/ksm.c
index d20d7662419b..d7b5b95e936e 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -455,6 +455,12 @@ static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long nex
 
 static const struct mm_walk_ops break_ksm_ops = {
 	.pmd_entry = break_ksm_pmd_entry,
+	.walk_lock = PGWALK_RDLOCK,
+};
+
+static const struct mm_walk_ops break_ksm_lock_vma_ops = {
+	.pmd_entry = break_ksm_pmd_entry,
+	.walk_lock = PGWALK_WRLOCK,
 };
 
 /*
@@ -470,16 +476,17 @@ static const struct mm_walk_ops break_ksm_ops = {
  * of the process that owns 'vma'.  We also do not want to enforce
  * protection keys here anyway.
  */
-static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
+static int break_ksm(struct vm_area_struct *vma, unsigned long addr, bool lock_vma)
 {
 	vm_fault_t ret = 0;
+	const struct mm_walk_ops *ops = lock_vma ?
+				&break_ksm_lock_vma_ops : &break_ksm_ops;
 
 	do {
 		int ksm_page;
 
 		cond_resched();
-		ksm_page = walk_page_range_vma(vma, addr, addr + 1,
-					       &break_ksm_ops, NULL);
+		ksm_page = walk_page_range_vma(vma, addr, addr + 1, ops, NULL);
 		if (WARN_ON_ONCE(ksm_page < 0))
 			return ksm_page;
 		if (!ksm_page)
@@ -565,7 +572,7 @@ static void break_cow(struct ksm_rmap_item *rmap_item)
 	mmap_read_lock(mm);
 	vma = find_mergeable_vma(mm, addr);
 	if (vma)
-		break_ksm(vma, addr);
+		break_ksm(vma, addr, false);
 	mmap_read_unlock(mm);
 }
 
@@ -871,7 +878,7 @@ static void remove_trailing_rmap_items(struct ksm_rmap_item **rmap_list)
  * in cmp_and_merge_page on one of the rmap_items we would be removing.
  */
 static int unmerge_ksm_pages(struct vm_area_struct *vma,
-			     unsigned long start, unsigned long end)
+			     unsigned long start, unsigned long end, bool lock_vma)
 {
 	unsigned long addr;
 	int err = 0;
@@ -882,7 +889,7 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma,
 		if (signal_pending(current))
 			err = -ERESTARTSYS;
 		else
-			err = break_ksm(vma, addr);
+			err = break_ksm(vma, addr, lock_vma);
 	}
 	return err;
 }
@@ -1029,7 +1036,7 @@ static int unmerge_and_remove_all_rmap_items(void)
 			if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
 				continue;
 			err = unmerge_ksm_pages(vma,
-						vma->vm_start, vma->vm_end);
+						vma->vm_start, vma->vm_end, false);
 			if (err)
 				goto error;
 		}
@@ -2530,7 +2537,7 @@ static int __ksm_del_vma(struct vm_area_struct *vma)
 		return 0;
 
 	if (vma->anon_vma) {
-		err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end);
+		err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end, true);
 		if (err)
 			return err;
 	}
@@ -2668,7 +2675,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 			return 0;		/* just ignore the advice */
 
 		if (vma->anon_vma) {
-			err = unmerge_ksm_pages(vma, start, end);
+			err = unmerge_ksm_pages(vma, start, end, true);
 			if (err)
 				return err;
 		}