[PATCH] media: videobuf2: publish buffers in bufs_bitmap under mmap_lock

[Ricardo Ribalda <ribalda@chromium.org>]

vb2_mmap() only takes q->mmap_lock, not the main queue lock (q->lock).
To keep vb2_mmap() safe, newly allocated buffers must not become visible
in vb2_get_buffer() until they are fully initialized and q->mmap_lock is
held.

Commit a286b0837e13 ("media: core: Add bitmap manage bufs array entries")
started setting q->bufs_bitmap inside __vb2_queue_alloc() before buffer
memory is allocated and without holding q->mmap_lock. As a result:

- A concurrent mmap() can find a half-initialized buffer, and if buffer
  allocation or .buf_init() fails, __vb2_queue_alloc() frees that buffer
  without holding q->mmap_lock, causing a use-after-free in vb2_mmap().
- If fewer buffers are allocated than requested, they are already
  counted as active in q->bufs_bitmap before .queue_setup() checks
  whether the smaller count is acceptable.

Fix this by keeping new buffers only in q->bufs[] during allocation and
setting their bits in q->bufs_bitmap under q->mmap_lock once allocation
and .queue_setup() succeed. Add a memory barrier pair on q->bufs_bitmap
so lockless vb2_get_buffer() readers also see fully initialized buffers,
and let __vb2_queue_free() read q->bufs[] directly when cleaning up
unexposed buffers.

Fixes: a286b0837e13 ("media: core: Add bitmap manage bufs array entries")
Cc: stable@vger.kernel.org
Signed-off-by: Ricardo Ribalda <ribalda@chromium.org>
---
This patch was generated by an LLM, but supervised and reviewed by a
human (not the most handsome human, but a human).
---
 drivers/media/common/videobuf2/videobuf2-core.c | 97 +++++++++++++++++++------
 include/media/videobuf2-core.h                  | 13 +++-
 2 files changed, 85 insertions(+), 25 deletions(-)

diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c
index b0a6084f1757..185393078ce3 100644
--- a/drivers/media/common/videobuf2/videobuf2-core.c
+++ b/drivers/media/common/videobuf2/videobuf2-core.c
@@ -427,19 +427,36 @@ static void init_buffer_cache_hints(struct vb2_queue *q, struct vb2_buffer *vb)
 }
 
 /**
- * vb2_queue_add_buffer() - add a buffer to a queue
- * @q:	pointer to &struct vb2_queue with videobuf2 queue.
- * @vb:	pointer to &struct vb2_buffer to be added to the queue.
- * @index: index where add vb2_buffer in the queue
+ * vb2_queue_add_buffers() - publish buffers staged by __vb2_queue_alloc()
+ * @q:		pointer to &struct vb2_queue with videobuf2 queue.
+ * @start:	index of the first buffer to publish.
+ * @count:	number of buffers to publish.
+ *
+ * Set the @q->bufs_bitmap bits of the @count fully initialized buffers that
+ * __vb2_queue_alloc() stored in @q->bufs[] starting at @start, which makes
+ * them visible to vb2_get_buffer().
  */
-static void vb2_queue_add_buffer(struct vb2_queue *q, struct vb2_buffer *vb, unsigned int index)
+static void vb2_queue_add_buffers(struct vb2_queue *q, unsigned int start,
+				  unsigned int count)
 {
-	WARN_ON(index >= q->max_num_buffers || test_bit(index, q->bufs_bitmap) || vb->vb2_queue);
+	unsigned int i;
+
+	lockdep_assert_held(&q->mmap_lock);
 
-	q->bufs[index] = vb;
-	vb->index = index;
-	vb->vb2_queue = q;
-	set_bit(index, q->bufs_bitmap);
+	/*
+	 * Order the buffer initialization and the q->bufs[] stores done by
+	 * __vb2_queue_alloc() before the bits that publish them. Pairs with
+	 * test_bit_acquire() in vb2_get_buffer(), which is also called
+	 * without q->lock or q->mmap_lock held, e.g. by vb2_find_buffer()
+	 * from a mem2mem .device_run().
+	 */
+	smp_mb__before_atomic();
+	for (i = start; i < start + count; i++) {
+		if (WARN_ON(i >= q->max_num_buffers || !q->bufs[i] ||
+			    test_bit(i, q->bufs_bitmap)))
+			continue;
+		set_bit(i, q->bufs_bitmap);
+	}
 }
 
 /**
@@ -448,6 +465,8 @@ static void vb2_queue_add_buffer(struct vb2_queue *q, struct vb2_buffer *vb, uns
  */
 static void vb2_queue_remove_buffer(struct vb2_buffer *vb)
 {
+	lockdep_assert_held(&vb->vb2_queue->mmap_lock);
+
 	clear_bit(vb->index, vb->vb2_queue->bufs_bitmap);
 	vb->vb2_queue->bufs[vb->index] = NULL;
 	vb->vb2_queue = NULL;
@@ -460,6 +479,11 @@ static void vb2_queue_remove_buffer(struct vb2_buffer *vb)
  * @first_index: index of the first created buffer, all newly allocated buffers
  *		 have indices in the range [first_index..first_index+count-1]
  *
+ * The allocated buffers are stored in q->bufs[] but not published in
+ * q->bufs_bitmap: the caller must either publish them with
+ * vb2_queue_add_buffers() or free them with __vb2_queue_free(), both under
+ * q->mmap_lock.
+ *
  * Returns the number of buffers successfully allocated.
  */
 static int __vb2_queue_alloc(struct vb2_queue *q, enum vb2_memory memory,
@@ -506,7 +530,9 @@ static int __vb2_queue_alloc(struct vb2_queue *q, enum vb2_memory memory,
 		}
 
 		vb->state = VB2_BUF_STATE_DEQUEUED;
+		vb->vb2_queue = q;
 		vb->num_planes = num_planes;
+		vb->index = index + buffer;
 		vb->type = q->type;
 		vb->memory = memory;
 		init_buffer_cache_hints(q, vb);
@@ -515,7 +541,6 @@ static int __vb2_queue_alloc(struct vb2_queue *q, enum vb2_memory memory,
 			vb->planes[plane].min_length = plane_sizes[plane];
 		}
 
-		vb2_queue_add_buffer(q, vb, index++);
 		call_void_bufop(q, init_buffer, vb);
 
 		/* Allocate video buffer memory for the MMAP type */
@@ -524,7 +549,6 @@ static int __vb2_queue_alloc(struct vb2_queue *q, enum vb2_memory memory,
 			if (ret) {
 				dprintk(q, 1, "failed allocating memory for buffer %d\n",
 					buffer);
-				vb2_queue_remove_buffer(vb);
 				kfree(vb);
 				break;
 			}
@@ -539,11 +563,20 @@ static int __vb2_queue_alloc(struct vb2_queue *q, enum vb2_memory memory,
 				dprintk(q, 1, "buffer %d %p initialization failed\n",
 					buffer, vb);
 				__vb2_buf_mem_free(vb);
-				vb2_queue_remove_buffer(vb);
 				kfree(vb);
 				break;
 			}
 		}
+
+		/*
+		 * Stage the initialized buffer in q->bufs[]; it becomes visible
+		 * to vb2_get_buffer() only after vb2_queue_add_buffers() sets
+		 * its bit in q->bufs_bitmap under q->mmap_lock.
+		 */
+		WARN_ON(vb->index >= q->max_num_buffers ||
+			q->bufs[vb->index] ||
+			test_bit(vb->index, q->bufs_bitmap));
+		q->bufs[vb->index] = vb;
 	}
 
 	dprintk(q, 3, "allocated %d buffers, %d plane(s) each\n",
@@ -562,7 +595,8 @@ static void __vb2_free_mem(struct vb2_queue *q, unsigned int start, unsigned int
 	struct vb2_buffer *vb;
 
 	for (i = start; i < start + count; i++) {
-		vb = vb2_get_buffer(q, i);
+		/* See __vb2_queue_free() for why vb2_get_buffer() isn't used */
+		vb = q->bufs[i];
 		if (!vb)
 			continue;
 
@@ -580,6 +614,11 @@ static void __vb2_free_mem(struct vb2_queue *q, unsigned int start, unsigned int
  * __vb2_queue_free() - free @count buffers from @start index of the queue - video memory and
  * related information, if no buffers are left return the queue to an
  * uninitialized state. Might be called even if the queue has already been freed.
+ *
+ * Buffers are looked up directly in q->bufs[] instead of through
+ * vb2_get_buffer() so that buffers staged by __vb2_queue_alloc() that were
+ * never published in q->bufs_bitmap (because a later .queue_setup() call
+ * rejected the allocated number of buffers) are freed as well.
  */
 static void __vb2_queue_free(struct vb2_queue *q, unsigned int start, unsigned int count)
 {
@@ -587,9 +626,19 @@ static void __vb2_queue_free(struct vb2_queue *q, unsigned int start, unsigned i
 
 	lockdep_assert_held(&q->mmap_lock);
 
+	/*
+	 * No buffers were ever allocated (e.g. REQBUFS(0) on a fresh queue),
+	 * only the queue state needs to be reset.
+	 */
+	if (!q->bufs) {
+		q->memory = VB2_MEMORY_UNKNOWN;
+		INIT_LIST_HEAD(&q->queued_list);
+		return;
+	}
+
 	/* Call driver-provided cleanup function for each buffer, if provided */
 	for (i = start; i < start + count; i++) {
-		struct vb2_buffer *vb = vb2_get_buffer(q, i);
+		struct vb2_buffer *vb = q->bufs[i];
 
 		if (vb && vb->planes[0].mem_priv)
 			call_void_vb_qop(vb, buf_cleanup, vb);
@@ -624,7 +673,7 @@ static void __vb2_queue_free(struct vb2_queue *q, unsigned int start, unsigned i
 		q->cnt_unprepare_streaming = 0;
 	}
 	for (i = start; i < start + count; i++) {
-		struct vb2_buffer *vb = vb2_get_buffer(q, i);
+		struct vb2_buffer *vb = q->bufs[i];
 		bool unbalanced;
 
 		if (!vb)
@@ -676,7 +725,7 @@ static void __vb2_queue_free(struct vb2_queue *q, unsigned int start, unsigned i
 
 	/* Free vb2 buffers */
 	for (i = start; i < start + count; i++) {
-		struct vb2_buffer *vb = vb2_get_buffer(q, i);
+		struct vb2_buffer *vb = q->bufs[i];
 
 		if (!vb)
 			continue;
@@ -1000,14 +1049,16 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
 
 	if (ret < 0) {
 		/*
-		 * Note: __vb2_queue_free() will subtract 'allocated_buffers'
-		 * from already queued buffers and it will reset q->memory to
+		 * Note: the buffers allocated by __vb2_queue_alloc() were never
+		 * published in q->bufs_bitmap, __vb2_queue_free() frees them
+		 * straight from q->bufs[] and resets q->memory to
 		 * VB2_MEMORY_UNKNOWN.
 		 */
 		__vb2_queue_free(q, first_index, allocated_buffers);
 		mutex_unlock(&q->mmap_lock);
 		return ret;
 	}
+	vb2_queue_add_buffers(q, first_index, allocated_buffers);
 	mutex_unlock(&q->mmap_lock);
 
 	/*
@@ -1125,14 +1176,16 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
 
 	if (ret < 0) {
 		/*
-		 * Note: __vb2_queue_free() will subtract 'allocated_buffers'
-		 * from already queued buffers and it will reset q->memory to
-		 * VB2_MEMORY_UNKNOWN.
+		 * Note: the buffers allocated by __vb2_queue_alloc() were never
+		 * published in q->bufs_bitmap, __vb2_queue_free() frees them
+		 * straight from q->bufs[] and resets q->memory to
+		 * VB2_MEMORY_UNKNOWN if no buffers are left.
 		 */
 		__vb2_queue_free(q, *first_index, allocated_buffers);
 		mutex_unlock(&q->mmap_lock);
 		return -ENOMEM;
 	}
+	vb2_queue_add_buffers(q, *first_index, allocated_buffers);
 	mutex_unlock(&q->mmap_lock);
 
 	/*
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 4b4f4c15c53a..0b32ac7bc8fc 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -565,8 +565,11 @@ struct vb2_buf_ops {
  * @memory:	current memory type used
  * @dma_dir:	DMA mapping direction.
  * @bufs:	videobuf2 buffer structures. If it is non-NULL then
- *		bufs_bitmap is also non-NULL.
- * @bufs_bitmap: bitmap tracking whether each bufs[] entry is used
+ *		bufs_bitmap is also non-NULL. __vb2_queue_alloc() fills in
+ *		an entry before its bit is set in bufs_bitmap, so buffers
+ *		must be looked up with vb2_get_buffer().
+ * @bufs_bitmap: bitmap tracking which bufs[] entries hold a fully
+ *		initialized buffer. Bits are set and cleared under @mmap_lock.
  * @max_num_buffers: upper limit of number of allocated/used buffers.
  *		     If set to 0 v4l2 core will change it VB2_MAX_FRAME
  *		     for backward compatibility.
@@ -1286,7 +1289,11 @@ static inline struct vb2_buffer *vb2_get_buffer(struct vb2_queue *q,
 	if (index >= q->max_num_buffers)
 		return NULL;
 
-	if (test_bit(index, q->bufs_bitmap))
+	/*
+	 * A set bit guarantees that the buffer is fully initialized, pairs
+	 * with smp_mb__before_atomic() in vb2_queue_add_buffers().
+	 */
+	if (test_bit_acquire(index, q->bufs_bitmap))
 		return q->bufs[index];
 	return NULL;
 }

---
base-commit: 6628e7d4c6b25c8d18f1345e3a20d21829aae7e4
change-id: 20261102-vb2-mmap_lock-959e0cc4edb3

Best regards,
-- 
Ricardo Ribalda <ribalda@chromium.org>