diff --git a/drivers/staging/media/hantro/hantro_v4l2.c b/drivers/staging/media/hantro/hantro_v4l2.c
index 67148ba346f5292dc362c0580a8beda7b5f339b5..50d636678ff39280d28ecd854b4701410b6c2c40 100644
--- a/drivers/staging/media/hantro/hantro_v4l2.c
+++ b/drivers/staging/media/hantro/hantro_v4l2.c
@@ -409,6 +409,30 @@ hantro_update_requires_request(struct hantro_ctx *ctx, u32 fourcc)
 	}
 }
 
+static void
+hantro_update_requires_hold_capture_buf(struct hantro_ctx *ctx, u32 fourcc)
+{
+	struct vb2_queue *vq;
+
+	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx,
+			     V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE);
+
+	switch (fourcc) {
+	case V4L2_PIX_FMT_JPEG:
+	case V4L2_PIX_FMT_MPEG2_SLICE:
+	case V4L2_PIX_FMT_VP8_FRAME:
+	case V4L2_PIX_FMT_HEVC_SLICE:
+	case V4L2_PIX_FMT_VP9_FRAME:
+		vq->subsystem_flags &= ~(VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF);
+		break;
+	case V4L2_PIX_FMT_H264_SLICE:
+		vq->subsystem_flags |= VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF;
+		break;
+	default:
+		break;
+	}
+}
+
 static int hantro_set_fmt_out(struct hantro_ctx *ctx,
 			      struct v4l2_pix_format_mplane *pix_mp)
 {
@@ -472,6 +496,7 @@ static int hantro_set_fmt_out(struct hantro_ctx *ctx,
 	ctx->dst_fmt.quantization = pix_mp->quantization;
 
 	hantro_update_requires_request(ctx, pix_mp->pixelformat);
+	hantro_update_requires_hold_capture_buf(ctx, pix_mp->pixelformat);
 
 	vpu_debug(0, "OUTPUT codec mode: %d\n", ctx->vpu_src_fmt->codec_mode);
 	vpu_debug(0, "fmt - w: %d, h: %d\n",