diff --git a/drivers/media/platform/verisilicon/hantro_v4l2.c b/drivers/media/platform/verisilicon/hantro_v4l2.c
index 62d3962c18d9..32f69c6c703b 100644
--- a/drivers/media/platform/verisilicon/hantro_v4l2.c
+++ b/drivers/media/platform/verisilicon/hantro_v4l2.c
@@ -201,7 +201,15 @@ static int vidioc_enum_fmt(struct file *file, void *priv,
 	struct hantro_ctx *ctx = fh_to_ctx(priv);
 	const struct hantro_fmt *fmt, *formats;
 	unsigned int num_fmts, i, j = 0;
-	bool skip_mode_none;
+	bool skip_mode_none, enum_all_formats;
+	u32 index = f->index & ~V4L2_FMTDESC_FLAG_ENUM_ALL;
+
+	/*
+	 * If the V4L2_FMTDESC_FLAG_ENUM_ALL flag is set, we want to enumerate all
+	 * hardware supported pixel formats
+	 */
+	enum_all_formats = !!(f->index & V4L2_FMTDESC_FLAG_ENUM_ALL);
+	f->index = index;
 
 	/*
 	 * When dealing with an encoder:
@@ -222,9 +230,9 @@ static int vidioc_enum_fmt(struct file *file, void *priv,
 
 		if (skip_mode_none == mode_none)
 			continue;
-		if (!hantro_check_depth_match(fmt, ctx->bit_depth))
+		if (!hantro_check_depth_match(fmt, ctx->bit_depth) && !enum_all_formats)
 			continue;
-		if (j == f->index) {
+		if (j == index) {
 			f->pixelformat = fmt->fourcc;
 			return 0;
 		}
@@ -242,9 +250,9 @@ static int vidioc_enum_fmt(struct file *file, void *priv,
 	for (i = 0; i < num_fmts; i++) {
 		fmt = &formats[i];
 
-		if (!hantro_check_depth_match(fmt, ctx->bit_depth))
+		if (!hantro_check_depth_match(fmt, ctx->bit_depth) && !enum_all_formats)
 			continue;
-		if (j == f->index) {
+		if (j == index) {
 			f->pixelformat = fmt->fourcc;
 			return 0;
 		}