Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

9 files changed, 115 insertions, 85 deletions

diff --git a/drivers/media/platform/verisilicon/Kconfig b/drivers/media/platform/verisilicon/Kconfig
index e65b836b9d..24b927d8f1 100644
--- a/drivers/media/platform/verisilicon/Kconfig
+++ b/drivers/media/platform/verisilicon/Kconfig
@@ -8,7 +8,6 @@ config VIDEO_HANTRO
 	depends on V4L_MEM2MEM_DRIVERS
 	depends on VIDEO_DEV
 	select MEDIA_CONTROLLER
-	select MEDIA_CONTROLLER_REQUEST_API
 	select VIDEOBUF2_DMA_CONTIG
 	select VIDEOBUF2_VMALLOC
 	select V4L2_MEM2MEM_DEV
diff --git a/drivers/media/platform/verisilicon/hantro.h b/drivers/media/platform/verisilicon/hantro.h
index 77aee94895..6f5eb975d0 100644
--- a/drivers/media/platform/verisilicon/hantro.h
+++ b/drivers/media/platform/verisilicon/hantro.h
@@ -328,6 +328,8 @@ struct hantro_vp9_decoded_buffer_info {
 	/* Info needed when the decoded frame serves as a reference frame. */
 	unsigned short width;
 	unsigned short height;
+	size_t chroma_offset;
+	size_t mv_offset;
 	u32 bit_depth : 4;
 };
 
@@ -469,11 +471,14 @@ hantro_get_dst_buf(struct hantro_ctx *ctx)
 bool hantro_needs_postproc(const struct hantro_ctx *ctx,
 			   const struct hantro_fmt *fmt);
 
+dma_addr_t
+hantro_postproc_get_dec_buf_addr(struct hantro_ctx *ctx, int index);
+
 static inline dma_addr_t
 hantro_get_dec_buf_addr(struct hantro_ctx *ctx, struct vb2_buffer *vb)
 {
 	if (hantro_needs_postproc(ctx, ctx->vpu_dst_fmt))
-		return ctx->postproc.dec_q[vb->index].dma;
+		return hantro_postproc_get_dec_buf_addr(ctx, vb->index);
 	return vb2_dma_contig_plane_dma_addr(vb, 0);
 }
 
@@ -485,8 +490,8 @@ vb2_to_hantro_decoded_buf(struct vb2_buffer *buf)
 
 void hantro_postproc_disable(struct hantro_ctx *ctx);
 void hantro_postproc_enable(struct hantro_ctx *ctx);
+int hantro_postproc_init(struct hantro_ctx *ctx);
 void hantro_postproc_free(struct hantro_ctx *ctx);
-int hantro_postproc_alloc(struct hantro_ctx *ctx);
 int hanto_postproc_enum_framesizes(struct hantro_ctx *ctx,
 				   struct v4l2_frmsizeenum *fsize);
 
diff --git a/drivers/media/platform/verisilicon/hantro_drv.c b/drivers/media/platform/verisilicon/hantro_drv.c
index 3a2a0f28cb..db3df6cc45 100644
--- a/drivers/media/platform/verisilicon/hantro_drv.c
+++ b/drivers/media/platform/verisilicon/hantro_drv.c
@@ -235,8 +235,10 @@ queue_init(void *priv, struct vb2_queue *src_vq, struct vb2_queue *dst_vq)
 	 * The Kernel needs access to the JPEG destination buffer for the
 	 * JPEG encoder to fill in the JPEG headers.
 	 */
-	if (!ctx->is_encoder)
+	if (!ctx->is_encoder) {
 		dst_vq->dma_attrs |= DMA_ATTR_NO_KERNEL_MAPPING;
+		dst_vq->max_num_buffers = MAX_POSTPROC_BUFFERS;
+	}
 
 	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
 	dst_vq->io_modes = VB2_MMAP | VB2_DMABUF;
diff --git a/drivers/media/platform/verisilicon/hantro_g2.c b/drivers/media/platform/verisilicon/hantro_g2.c
index ee5f14c5f8..b880a6849d 100644
--- a/drivers/media/platform/verisilicon/hantro_g2.c
+++ b/drivers/media/platform/verisilicon/hantro_g2.c
@@ -8,6 +8,8 @@
 #include "hantro_hw.h"
 #include "hantro_g2_regs.h"
 
+#define G2_ALIGN	16
+
 void hantro_g2_check_idle(struct hantro_dev *vpu)
 {
 	int i;
@@ -42,3 +44,15 @@ irqreturn_t hantro_g2_irq(int irq, void *dev_id)
 
 	return IRQ_HANDLED;
 }
+
+size_t hantro_g2_chroma_offset(struct hantro_ctx *ctx)
+{
+	return ctx->dst_fmt.width * ctx->dst_fmt.height * ctx->bit_depth / 8;
+}
+
+size_t hantro_g2_motion_vectors_offset(struct hantro_ctx *ctx)
+{
+	size_t cr_offset = hantro_g2_chroma_offset(ctx);
+
+	return ALIGN((cr_offset * 3) / 2, G2_ALIGN);
+}
diff --git a/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c b/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c
index a9d4ac84a8..d3f8c33eb1 100644
--- a/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c
+++ b/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c
@@ -8,20 +8,6 @@
 #include "hantro_hw.h"
 #include "hantro_g2_regs.h"
 
-#define G2_ALIGN	16
-
-static size_t hantro_hevc_chroma_offset(struct hantro_ctx *ctx)
-{
-	return ctx->dst_fmt.width * ctx->dst_fmt.height * ctx->bit_depth / 8;
-}
-
-static size_t hantro_hevc_motion_vectors_offset(struct hantro_ctx *ctx)
-{
-	size_t cr_offset = hantro_hevc_chroma_offset(ctx);
-
-	return ALIGN((cr_offset * 3) / 2, G2_ALIGN);
-}
-
 static void prepare_tile_info_buffer(struct hantro_ctx *ctx)
 {
 	struct hantro_dev *vpu = ctx->dev;
@@ -384,8 +370,8 @@ static int set_ref(struct hantro_ctx *ctx)
 	struct hantro_dev *vpu = ctx->dev;
 	struct vb2_v4l2_buffer *vb2_dst;
 	struct hantro_decoded_buffer *dst;
-	size_t cr_offset = hantro_hevc_chroma_offset(ctx);
-	size_t mv_offset = hantro_hevc_motion_vectors_offset(ctx);
+	size_t cr_offset = hantro_g2_chroma_offset(ctx);
+	size_t mv_offset = hantro_g2_motion_vectors_offset(ctx);
 	u32 max_ref_frames;
 	u16 dpb_longterm_e;
 	static const struct hantro_reg cur_poc[] = {
diff --git a/drivers/media/platform/verisilicon/hantro_g2_vp9_dec.c b/drivers/media/platform/verisilicon/hantro_g2_vp9_dec.c
index 6fc4b55551..342e543dee 100644
--- a/drivers/media/platform/verisilicon/hantro_g2_vp9_dec.c
+++ b/drivers/media/platform/verisilicon/hantro_g2_vp9_dec.c
@@ -16,8 +16,6 @@
 #include "hantro_vp9.h"
 #include "hantro_g2_regs.h"
 
-#define G2_ALIGN 16
-
 enum hantro_ref_frames {
 	INTRA_FRAME = 0,
 	LAST_FRAME = 1,
@@ -90,22 +88,6 @@ static int start_prepare_run(struct hantro_ctx *ctx, const struct v4l2_ctrl_vp9_
 	return 0;
 }
 
-static size_t chroma_offset(const struct hantro_ctx *ctx,
-			    const struct v4l2_ctrl_vp9_frame *dec_params)
-{
-	int bytes_per_pixel = dec_params->bit_depth == 8 ? 1 : 2;
-
-	return ctx->src_fmt.width * ctx->src_fmt.height * bytes_per_pixel;
-}
-
-static size_t mv_offset(const struct hantro_ctx *ctx,
-			const struct v4l2_ctrl_vp9_frame *dec_params)
-{
-	size_t cr_offset = chroma_offset(ctx, dec_params);
-
-	return ALIGN((cr_offset * 3) / 2, G2_ALIGN);
-}
-
 static struct hantro_decoded_buffer *
 get_ref_buf(struct hantro_ctx *ctx, struct vb2_v4l2_buffer *dst, u64 timestamp)
 {
@@ -156,11 +138,13 @@ static void config_output(struct hantro_ctx *ctx,
 	luma_addr = hantro_get_dec_buf_addr(ctx, &dst->base.vb.vb2_buf);
 	hantro_write_addr(ctx->dev, G2_OUT_LUMA_ADDR, luma_addr);
 
-	chroma_addr = luma_addr + chroma_offset(ctx, dec_params);
+	chroma_addr = luma_addr + hantro_g2_chroma_offset(ctx);
 	hantro_write_addr(ctx->dev, G2_OUT_CHROMA_ADDR, chroma_addr);
+	dst->vp9.chroma_offset = hantro_g2_chroma_offset(ctx);
 
-	mv_addr = luma_addr + mv_offset(ctx, dec_params);
+	mv_addr = luma_addr + hantro_g2_motion_vectors_offset(ctx);
 	hantro_write_addr(ctx->dev, G2_OUT_MV_ADDR, mv_addr);
+	dst->vp9.mv_offset = hantro_g2_motion_vectors_offset(ctx);
 }
 
 struct hantro_vp9_ref_reg {
@@ -195,7 +179,7 @@ static void config_ref(struct hantro_ctx *ctx,
 	luma_addr = hantro_get_dec_buf_addr(ctx, &buf->base.vb.vb2_buf);
 	hantro_write_addr(ctx->dev, ref_reg->y_base, luma_addr);
 
-	chroma_addr = luma_addr + chroma_offset(ctx, dec_params);
+	chroma_addr = luma_addr + buf->vp9.chroma_offset;
 	hantro_write_addr(ctx->dev, ref_reg->c_base, chroma_addr);
 }
 
@@ -238,7 +222,7 @@ static void config_ref_registers(struct hantro_ctx *ctx,
 	config_ref(ctx, dst, &ref_regs[2], dec_params, dec_params->alt_frame_ts);
 
 	mv_addr = hantro_get_dec_buf_addr(ctx, &mv_ref->base.vb.vb2_buf) +
-		  mv_offset(ctx, dec_params);
+		  mv_ref->vp9.mv_offset;
 	hantro_write_addr(ctx->dev, G2_REF_MV_ADDR(0), mv_addr);
 
 	hantro_reg_write(ctx->dev, &vp9_last_sign_bias,
diff --git a/drivers/media/platform/verisilicon/hantro_hw.h b/drivers/media/platform/verisilicon/hantro_hw.h
index 7f33f7b07c..9aec8a79ac 100644
--- a/drivers/media/platform/verisilicon/hantro_hw.h
+++ b/drivers/media/platform/verisilicon/hantro_hw.h
@@ -40,6 +40,8 @@
 
 #define AV1_MAX_FRAME_BUF_COUNT	(V4L2_AV1_TOTAL_REFS_PER_FRAME + 1)
 
+#define MAX_POSTPROC_BUFFERS	64
+
 struct hantro_dev;
 struct hantro_ctx;
 struct hantro_buf;
@@ -336,7 +338,7 @@ struct hantro_av1_dec_hw_ctx {
  * @dec_q:		References buffers, in decoder format.
  */
 struct hantro_postproc_ctx {
-	struct hantro_aux_buf dec_q[VB2_MAX_FRAME];
+	struct hantro_aux_buf dec_q[MAX_POSTPROC_BUFFERS];
 };
 
 /**
@@ -519,6 +521,9 @@ hantro_av1_mv_size(unsigned int width, unsigned int height)
 	return ALIGN(num_sbs * 384, 16) * 2 + 512;
 }
 
+size_t hantro_g2_chroma_offset(struct hantro_ctx *ctx);
+size_t hantro_g2_motion_vectors_offset(struct hantro_ctx *ctx);
+
 int hantro_g1_mpeg2_dec_run(struct hantro_ctx *ctx);
 int rockchip_vpu2_mpeg2_dec_run(struct hantro_ctx *ctx);
 void hantro_mpeg2_dec_copy_qtable(u8 *qtable,
diff --git a/drivers/media/platform/verisilicon/hantro_postproc.c b/drivers/media/platform/verisilicon/hantro_postproc.c
index 64d6fb852a..41e9317630 100644
--- a/drivers/media/platform/verisilicon/hantro_postproc.c
+++ b/drivers/media/platform/verisilicon/hantro_postproc.c
@@ -177,9 +177,11 @@ static int hantro_postproc_g2_enum_framesizes(struct hantro_ctx *ctx,
 void hantro_postproc_free(struct hantro_ctx *ctx)
 {
 	struct hantro_dev *vpu = ctx->dev;
+	struct v4l2_m2m_ctx *m2m_ctx = ctx->fh.m2m_ctx;
+	struct vb2_queue *queue = &m2m_ctx->cap_q_ctx.q;
 	unsigned int i;
 
-	for (i = 0; i < VB2_MAX_FRAME; ++i) {
+	for (i = 0; i < queue->max_num_buffers; ++i) {
 		struct hantro_aux_buf *priv = &ctx->postproc.dec_q[i];
 
 		if (priv->cpu) {
@@ -190,20 +192,17 @@ void hantro_postproc_free(struct hantro_ctx *ctx)
 	}
 }
 
-int hantro_postproc_alloc(struct hantro_ctx *ctx)
+static unsigned int hantro_postproc_buffer_size(struct hantro_ctx *ctx)
 {
-	struct hantro_dev *vpu = ctx->dev;
-	struct v4l2_m2m_ctx *m2m_ctx = ctx->fh.m2m_ctx;
-	struct vb2_queue *cap_queue = &m2m_ctx->cap_q_ctx.q;
-	unsigned int num_buffers = cap_queue->num_buffers;
 	struct v4l2_pix_format_mplane pix_mp;
 	const struct hantro_fmt *fmt;
-	unsigned int i, buf_size;
+	unsigned int buf_size;
 
 	/* this should always pick native format */
 	fmt = hantro_get_default_fmt(ctx, false, ctx->bit_depth, HANTRO_AUTO_POSTPROC);
 	if (!fmt)
-		return -EINVAL;
+		return 0;
+
 	v4l2_fill_pixfmt_mp(&pix_mp, fmt->fourcc, ctx->src_fmt.width,
 			    ctx->src_fmt.height);
 
@@ -221,23 +220,77 @@ int hantro_postproc_alloc(struct hantro_ctx *ctx)
 		buf_size += hantro_av1_mv_size(pix_mp.width,
 					       pix_mp.height);
 
-	for (i = 0; i < num_buffers; ++i) {
-		struct hantro_aux_buf *priv = &ctx->postproc.dec_q[i];
+	return buf_size;
+}
+
+static int hantro_postproc_alloc(struct hantro_ctx *ctx, int index)
+{
+	struct hantro_dev *vpu = ctx->dev;
+	struct hantro_aux_buf *priv = &ctx->postproc.dec_q[index];
+	unsigned int buf_size = hantro_postproc_buffer_size(ctx);
+
+	if (!buf_size)
+		return -EINVAL;
+
+	/*
+	 * The buffers on this queue are meant as intermediate
+	 * buffers for the decoder, so no mapping is needed.
+	 */
+	priv->attrs = DMA_ATTR_NO_KERNEL_MAPPING;
+	priv->cpu = dma_alloc_attrs(vpu->dev, buf_size, &priv->dma,
+				    GFP_KERNEL, priv->attrs);
+	if (!priv->cpu)
+		return -ENOMEM;
+	priv->size = buf_size;
+
+	return 0;
+}
 
-		/*
-		 * The buffers on this queue are meant as intermediate
-		 * buffers for the decoder, so no mapping is needed.
-		 */
-		priv->attrs = DMA_ATTR_NO_KERNEL_MAPPING;
-		priv->cpu = dma_alloc_attrs(vpu->dev, buf_size, &priv->dma,
-					    GFP_KERNEL, priv->attrs);
-		if (!priv->cpu)
-			return -ENOMEM;
-		priv->size = buf_size;
+int hantro_postproc_init(struct hantro_ctx *ctx)
+{
+	struct v4l2_m2m_ctx *m2m_ctx = ctx->fh.m2m_ctx;
+	struct vb2_queue *cap_queue = &m2m_ctx->cap_q_ctx.q;
+	unsigned int num_buffers = vb2_get_num_buffers(cap_queue);
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < num_buffers; i++) {
+		ret = hantro_postproc_alloc(ctx, i);
+		if (ret)
+			return ret;
 	}
+
 	return 0;
 }
 
+dma_addr_t
+hantro_postproc_get_dec_buf_addr(struct hantro_ctx *ctx, int index)
+{
+	struct hantro_aux_buf *priv = &ctx->postproc.dec_q[index];
+	unsigned int buf_size = hantro_postproc_buffer_size(ctx);
+	struct hantro_dev *vpu = ctx->dev;
+	int ret;
+
+	if (priv->size < buf_size && priv->cpu) {
+		/* buffer is too small, release it */
+		dma_free_attrs(vpu->dev, priv->size, priv->cpu,
+			       priv->dma, priv->attrs);
+		priv->cpu = NULL;
+	}
+
+	if (!priv->cpu) {
+		/* buffer not already allocated, try getting a new one */
+		ret = hantro_postproc_alloc(ctx, index);
+		if (ret)
+			return 0;
+	}
+
+	if (!priv->cpu)
+		return 0;
+
+	return priv->dma;
+}
+
 static void hantro_postproc_g1_disable(struct hantro_ctx *ctx)
 {
 	struct hantro_dev *vpu = ctx->dev;
diff --git a/drivers/media/platform/verisilicon/hantro_v4l2.c b/drivers/media/platform/verisilicon/hantro_v4l2.c
index db145519fc..941fa23c21 100644
--- a/drivers/media/platform/verisilicon/hantro_v4l2.c
+++ b/drivers/media/platform/verisilicon/hantro_v4l2.c
@@ -514,25 +514,14 @@ static int hantro_set_fmt_out(struct hantro_ctx *ctx,
 		return ret;
 
 	if (!ctx->is_encoder) {
-		struct vb2_queue *peer_vq;
-
 		/*
 		 * In order to support dynamic resolution change,
 		 * the decoder admits a resolution change, as long
-		 * as the pixelformat remains. Can't be done if streaming.
-		 */
-		if (vb2_is_streaming(vq) || (vb2_is_busy(vq) &&
-		    pix_mp->pixelformat != ctx->src_fmt.pixelformat))
-			return -EBUSY;
-		/*
-		 * Since format change on the OUTPUT queue will reset
-		 * the CAPTURE queue, we can't allow doing so
-		 * when the CAPTURE queue has buffers allocated.
+		 * as the pixelformat remains.
 		 */
-		peer_vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx,
-					  V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE);
-		if (vb2_is_busy(peer_vq))
+		if (vb2_is_streaming(vq) && pix_mp->pixelformat != ctx->src_fmt.pixelformat) {
 			return -EBUSY;
+		}
 	} else {
 		/*
 		 * The encoder doesn't admit a format change if
@@ -577,15 +566,8 @@ static int hantro_set_fmt_out(struct hantro_ctx *ctx,
 static int hantro_set_fmt_cap(struct hantro_ctx *ctx,
 			      struct v4l2_pix_format_mplane *pix_mp)
 {
-	struct vb2_queue *vq;
 	int ret;
 
-	/* Change not allowed if queue is busy. */
-	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx,
-			     V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE);
-	if (vb2_is_busy(vq))
-		return -EBUSY;
-
 	if (ctx->is_encoder) {
 		struct vb2_queue *peer_vq;
 
@@ -936,7 +918,7 @@ static int hantro_start_streaming(struct vb2_queue *q, unsigned int count)
 		}
 
 		if (hantro_needs_postproc(ctx, ctx->vpu_dst_fmt)) {
-			ret = hantro_postproc_alloc(ctx);
+			ret = hantro_postproc_init(ctx);
 			if (ret)
 				goto err_codec_exit;
 		}