mm/mmap: reposition vma iterator in mmap_region()

Instead of moving (or leaving) the vma iterator pointing at the previous
vma, leave it pointing at the insert location.  Pointing the vma iterator
at the insert location allows for a cleaner walk of the vma tree for
MAP_FIXED and the no expansion cases.

The vma_prev() call in the case of merging the previous vma is equivalent
to vma_iter_prev_range(), since the vma iterator will be pointing to the
location just before the previous vma.

This change needs to export abort_munmap_vmas() from mm/vma.

Link: https://lkml.kernel.org/r/20240830040101.822209-12-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Bert Karwatzki <spasswolf@web.de>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: Jiri Olsa <olsajiri@gmail.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 39 insertions, 33 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index ac348ae933ba..08cf9199f314 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1401,21 +1401,23 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		/* Prepare to unmap any existing mapping in the area */
 		error = vms_gather_munmap_vmas(&vms, &mas_detach);
 		if (error)
-			return error;
+			goto gather_failed;
 
 		/* Remove any existing mappings from the vma tree */
-		if (vma_iter_clear_gfp(&vmi, addr, end, GFP_KERNEL))
-			return -ENOMEM;
+		error = vma_iter_clear_gfp(&vmi, addr, end, GFP_KERNEL);
+		if (error)
+			goto clear_tree_failed;
 
 		/* Unmap any existing mapping in the area */
 		vms_complete_munmap_vmas(&vms, &mas_detach);
 		next = vms.next;
 		prev = vms.prev;
-		vma_prev(&vmi);
 		vma = NULL;
 	} else {
 		next = vma_next(&vmi);
 		prev = vma_prev(&vmi);
+		if (prev)
+			vma_iter_next_range(&vmi);
 	}
 
 	/*
@@ -1428,11 +1430,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		vm_flags |= VM_ACCOUNT;
 	}
 
-	if (vm_flags & VM_SPECIAL) {
-		if (prev)
-			vma_iter_next_range(&vmi);
+	if (vm_flags & VM_SPECIAL)
 		goto cannot_expand;
-	}
 
 	/* Attempt to expand an old mapping */
 	/* Check next */
@@ -1453,19 +1452,21 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		merge_start = prev->vm_start;
 		vma = prev;
 		vm_pgoff = prev->vm_pgoff;
-	} else if (prev) {
-		vma_iter_next_range(&vmi);
+		vma_prev(&vmi); /* Equivalent to going to the previous range */
 	}
 
-	/* Actually expand, if possible */
-	if (vma &&
-	    !vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) {
-		khugepaged_enter_vma(vma, vm_flags);
-		goto expanded;
+	if (vma) {
+		/* Actually expand, if possible */
+		if (!vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) {
+			khugepaged_enter_vma(vma, vm_flags);
+			goto expanded;
+		}
+
+		/* If the expand fails, then reposition the vma iterator */
+		if (unlikely(vma == prev))
+			vma_iter_set(&vmi, addr);
 	}
 
-	if (vma == prev)
-		vma_iter_set(&vmi, addr);
 cannot_expand:
 
 	/*
@@ -1624,6 +1625,11 @@ free_vma:
 unacct_error:
 	if (charged)
 		vm_unacct_memory(charged);
+
+clear_tree_failed:
+	if (vms.vma_count)
+		abort_munmap_vmas(&mas_detach);
+gather_failed:
 	validate_mm(mm);
 	return error;
 }
diff --git a/mm/vma.c b/mm/vma.c
index fc425eb34bf7..5e0ed5d63877 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -647,22 +647,6 @@ again:
 }
 
 /*
- * abort_munmap_vmas - Undo any munmap work and free resources
- *
- * Reattach any detached vmas and free up the maple tree used to track the vmas.
- */
-static inline void abort_munmap_vmas(struct ma_state *mas_detach)
-{
-	struct vm_area_struct *vma;
-
-	mas_set(mas_detach, 0);
-	mas_for_each(mas_detach, vma, ULONG_MAX)
-		vma_mark_detached(vma, false);
-
-	__mt_destroy(mas_detach->tree);
-}
-
-/*
  * vms_complete_munmap_vmas() - Finish the munmap() operation
  * @vms: The vma munmap struct
  * @mas_detach: The maple state of the detached vmas
diff --git a/mm/vma.h b/mm/vma.h
index 0e214bbf443e..c85fc7c888a8 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -116,6 +116,22 @@ int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
 void vms_complete_munmap_vmas(struct vma_munmap_struct *vms,
 		struct ma_state *mas_detach);
 
+/*
+ * abort_munmap_vmas - Undo any munmap work and free resources
+ *
+ * Reattach any detached vmas and free up the maple tree used to track the vmas.
+ */
+static inline void abort_munmap_vmas(struct ma_state *mas_detach)
+{
+	struct vm_area_struct *vma;
+
+	mas_set(mas_detach, 0);
+	mas_for_each(mas_detach, vma, ULONG_MAX)
+		vma_mark_detached(vma, false);
+
+	__mt_destroy(mas_detach->tree);
+}
+
 int
 do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		    struct mm_struct *mm, unsigned long start,