mm: fix (harmless) type confusion in lock_vma_under_rcu()

There is a (harmless) type confusion in lock_vma_under_rcu(): After
vma_start_read(), we have taken the VMA lock but don't know yet whether
the VMA has already been detached and scheduled for RCU freeing.  At this
point, ->vm_start and ->vm_end are accessed.

vm_area_struct contains a union such that ->vm_rcu uses the same memory as
->vm_start and ->vm_end; so accessing ->vm_start and ->vm_end of a
detached VMA is illegal and leads to type confusion between union members.

Fix it by reordering the vma->detached check above the address checks, and
document the rules for RCU readers accessing VMAs.

This will probably change the number of observed VMA_LOCK_MISS events
(since previously, trying to access a detached VMA whose ->vm_rcu has been
scheduled would bail out when checking the fault address against the
rcu_head members reinterpreted as VMA bounds).

Link: https://lkml.kernel.org/r/20240805-fix-vma-lock-type-confusion-v1-1-9f25443a9a71@google.com
Fixes: 50ee32537206 ("mm: introduce lock_vma_under_rcu to be used from arch-specific code")
Signed-off-by: Jann Horn <[email protected]>
Acked-by: Suren Baghdasaryan <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

2 files changed, 23 insertions, 6 deletions

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 165c58b12ccc..003619fab20e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -660,6 +660,9 @@ struct vma_numab_state {
  * per VM-area/task. A VM area is any part of the process virtual memory
  * space that has a special rule for the page-fault handlers (ie a shared
  * library, the executable area etc).
+ *
+ * Only explicitly marked struct members may be accessed by RCU readers before
+ * getting a stable reference.
  */
 struct vm_area_struct {
 	/* The first cache line has the info for VMA tree walking. */
@@ -675,7 +678,11 @@ struct vm_area_struct {
 #endif
 	};
 
-	struct mm_struct *vm_mm;	/* The address space we belong to. */
+	/*
+	 * The address space we belong to.
+	 * Unstable RCU readers are allowed to read this.
+	 */
+	struct mm_struct *vm_mm;
 	pgprot_t vm_page_prot;          /* Access permissions of this VMA. */
 
 	/*
@@ -688,7 +695,10 @@ struct vm_area_struct {
 	};
 
 #ifdef CONFIG_PER_VMA_LOCK
-	/* Flag to indicate areas detached from the mm->mm_mt tree */
+	/*
+	 * Flag to indicate areas detached from the mm->mm_mt tree.
+	 * Unstable RCU readers are allowed to read this.
+	 */
 	bool detached;
 
 	/*
@@ -706,6 +716,7 @@ struct vm_area_struct {
 	 * slowpath.
 	 */
 	int vm_lock_seq;
+	/* Unstable RCU readers are allowed to read this. */
 	struct vma_lock *vm_lock;
 #endif
 
diff --git a/mm/memory.c b/mm/memory.c
index 661168a46b43..46a44dc702fa 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5997,10 +5997,6 @@ retry:
 	if (!vma_start_read(vma))
 		goto inval;
 
-	/* Check since vm_start/vm_end might change before we lock the VMA */
-	if (unlikely(address < vma->vm_start || address >= vma->vm_end))
-		goto inval_end_read;
-
 	/* Check if the VMA got isolated after we found it */
 	if (vma->detached) {
 		vma_end_read(vma);
@@ -6008,6 +6004,16 @@ retry:
 		/* The area was replaced with another one */
 		goto retry;
 	}
+	/*
+	 * At this point, we have a stable reference to a VMA: The VMA is
+	 * locked and we know it hasn't already been isolated.
+	 * From here on, we can access the VMA without worrying about which
+	 * fields are accessible for RCU readers.
+	 */
+
+	/* Check since vm_start/vm_end might change before we lock the VMA */
+	if (unlikely(address < vma->vm_start || address >= vma->vm_end))
+		goto inval_end_read;
 
 	rcu_read_unlock();
 	return vma;