binder: add lockless binder_alloc_(set|get)_vma()

Bring back the original lockless design in binder_alloc to determine
whether the buffer setup has been completed by the ->mmap() handler.
However, this time use smp_load_acquire() and smp_store_release() to
wrap all the ordering in a single macro call.

Also, add comments to make it evident that binder uses alloc->vma to
determine when the binder_alloc has been fully initialized. In these
scenarios acquiring the mmap_lock is not required.

Fixes: a43cfc87 ("android: binder: stop saving a pointer to the VMA")
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20230502201220.1756319-3-cmllamas@google.comSigned-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/android/binder_alloc.c

@@ -309,17 +309,18 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 	return vma ? -ENOMEM : -ESRCH;
 }
 
+static inline void binder_alloc_set_vma(struct binder_alloc *alloc,
+		struct vm_area_struct *vma)
+{
+	/* pairs with smp_load_acquire in binder_alloc_get_vma() */
+	smp_store_release(&alloc->vma, vma);
+}
+
 static inline struct vm_area_struct *binder_alloc_get_vma(
 		struct binder_alloc *alloc)
 {
-	struct vm_area_struct *vma = NULL;
-
-	if (alloc->vma) {
-		/* Look at description in binder_alloc_set_vma */
-		smp_rmb();
-		vma = alloc->vma;
-	}
-	return vma;
+	/* pairs with smp_store_release in binder_alloc_set_vma() */
+	return smp_load_acquire(&alloc->vma);
 }
 
 static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid)
@@ -382,6 +383,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	size_t size, data_offsets_size;
 	int ret;
 
+	/* Check binder_alloc is fully initialized */
 	if (!binder_alloc_get_vma(alloc)) {
 		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
 				   "%d: binder_alloc_buf, no vma\n",
@@ -777,7 +779,9 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 	buffer->free = 1;
 	binder_insert_free_buffer(alloc, buffer);
 	alloc->free_async_space = alloc->buffer_size / 2;
-	alloc->vma = vma;
+
+	/* Signal binder_alloc is fully initialized */
+	binder_alloc_set_vma(alloc, vma);
 
 	return 0;
 
@@ -959,7 +963,7 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
  */
 void binder_alloc_vma_close(struct binder_alloc *alloc)
 {
-	alloc->vma = 0;
+	binder_alloc_set_vma(alloc, NULL);
 }
 
 /**