[PATCH v4 04/21] rockchip/vpu: Cleanup JPEG bounce buffer management

From: Boris Brezillon <boris.brezillon@collabora.com>
To: Mauro Carvalho Chehab <mchehab@kernel.org>,
	Hans Verkuil <hans.verkuil@cisco.com>,
	Laurent Pinchart <laurent.pinchart@ideasonboard.com>,
	Sakari Ailus <sakari.ailus@iki.fi>,
	linux-media@vger.kernel.org
Cc: Tomasz Figa <tfiga@chromium.org>,
	Nicolas Dufresne <nicolas@ndufresne.ca>,
	kernel@collabora.com,
	Paul Kocialkowski <paul.kocialkowski@bootlin.com>,
	Ezequiel Garcia <ezequiel@collabora.com>,
	Jonas Karlman <jonas@kwiboo.se>,
	linux-rockchip@lists.infradead.org,
	Heiko Stuebner <heiko@sntech.de>,
	Boris Brezillon <boris.brezillon@collabora.com>
Subject: [PATCH v4 04/21] rockchip/vpu: Cleanup JPEG bounce buffer management
Date: Thu, 25 Apr 2019 09:12:25 +0200	[thread overview]
Message-ID: <20190425071242.18315-5-boris.brezillon@collabora.com> (raw)
In-Reply-To: <20190425071242.18315-1-boris.brezillon@collabora.com>

From: Ezequiel Garcia <ezequiel@collabora.com>

In order to make the code more generic, introduce a pair of start/stop
codec operations, and use them to allocate and release the JPEG bounce
buffer.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
---
Changes from v3:
* None

Changes from v2:

* Reword bounce buffer comment, so it's specific about JPEG.
* Rename helpers, start/stop to init/exit.
* Rename "jpeg_enc_ctx" to "jpeg_enc", since it's clear it's a member
  of a "_ctx" struct.
---
 .../media/rockchip/vpu/rk3288_vpu_hw.c        |  2 ++
 .../rockchip/vpu/rk3288_vpu_hw_jpeg_enc.c     |  4 +--
 .../media/rockchip/vpu/rk3399_vpu_hw.c        |  2 ++
 .../rockchip/vpu/rk3399_vpu_hw_jpeg_enc.c     |  4 +--
 .../staging/media/rockchip/vpu/rockchip_vpu.h | 12 ++++----
 .../media/rockchip/vpu/rockchip_vpu_drv.c     |  9 ++++--
 .../media/rockchip/vpu/rockchip_vpu_enc.c     | 23 +++++----------
 .../media/rockchip/vpu/rockchip_vpu_hw.h      | 28 ++++++++++++++++++
 .../media/rockchip/vpu/rockchip_vpu_jpeg.c    | 29 +++++++++++++++++++
 9 files changed, 84 insertions(+), 29 deletions(-)

diff --git a/drivers/staging/media/rockchip/vpu/rk3288_vpu_hw.c b/drivers/staging/media/rockchip/vpu/rk3288_vpu_hw.c
index a5e9d183fffd..a874a0d83c2d 100644
--- a/drivers/staging/media/rockchip/vpu/rk3288_vpu_hw.c
+++ b/drivers/staging/media/rockchip/vpu/rk3288_vpu_hw.c
@@ -98,6 +98,8 @@ static const struct rockchip_vpu_codec_ops rk3288_vpu_codec_ops[] = {
 	[RK_VPU_MODE_JPEG_ENC] = {
 		.run = rk3288_vpu_jpeg_enc_run,
 		.reset = rk3288_vpu_enc_reset,
+		.init = rockchip_vpu_jpeg_enc_init,
+		.exit = rockchip_vpu_jpeg_enc_exit,
 	},
 };
 
diff --git a/drivers/staging/media/rockchip/vpu/rk3288_vpu_hw_jpeg_enc.c b/drivers/staging/media/rockchip/vpu/rk3288_vpu_hw_jpeg_enc.c
index 06daea66fb49..791353ae01e7 100644
--- a/drivers/staging/media/rockchip/vpu/rk3288_vpu_hw_jpeg_enc.c
+++ b/drivers/staging/media/rockchip/vpu/rk3288_vpu_hw_jpeg_enc.c
@@ -37,9 +37,9 @@ static void rk3288_vpu_jpeg_enc_set_buffers(struct rockchip_vpu_dev *vpu,
 
 	WARN_ON(pix_fmt->num_planes > 3);
 
-	vepu_write_relaxed(vpu, ctx->bounce_dma_addr,
+	vepu_write_relaxed(vpu, ctx->jpeg_enc.bounce_buffer.dma,
 			   VEPU_REG_ADDR_OUTPUT_STREAM);
-	vepu_write_relaxed(vpu, ctx->bounce_size,
+	vepu_write_relaxed(vpu, ctx->jpeg_enc.bounce_buffer.size,
 			   VEPU_REG_STR_BUF_LIMIT);
 
 	if (pix_fmt->num_planes == 1) {
diff --git a/drivers/staging/media/rockchip/vpu/rk3399_vpu_hw.c b/drivers/staging/media/rockchip/vpu/rk3399_vpu_hw.c
index 6fdef61e2127..f4effad00605 100644
--- a/drivers/staging/media/rockchip/vpu/rk3399_vpu_hw.c
+++ b/drivers/staging/media/rockchip/vpu/rk3399_vpu_hw.c
@@ -98,6 +98,8 @@ static const struct rockchip_vpu_codec_ops rk3399_vpu_codec_ops[] = {
 	[RK_VPU_MODE_JPEG_ENC] = {
 		.run = rk3399_vpu_jpeg_enc_run,
 		.reset = rk3399_vpu_enc_reset,
+		.init = rockchip_vpu_jpeg_enc_init,
+		.exit = rockchip_vpu_jpeg_enc_exit,
 	},
 };
 
diff --git a/drivers/staging/media/rockchip/vpu/rk3399_vpu_hw_jpeg_enc.c b/drivers/staging/media/rockchip/vpu/rk3399_vpu_hw_jpeg_enc.c
index 3d438797692e..6f9f5158d193 100644
--- a/drivers/staging/media/rockchip/vpu/rk3399_vpu_hw_jpeg_enc.c
+++ b/drivers/staging/media/rockchip/vpu/rk3399_vpu_hw_jpeg_enc.c
@@ -69,9 +69,9 @@ static void rk3399_vpu_jpeg_enc_set_buffers(struct rockchip_vpu_dev *vpu,
 
 	WARN_ON(pix_fmt->num_planes > 3);
 
-	vepu_write_relaxed(vpu, ctx->bounce_dma_addr,
+	vepu_write_relaxed(vpu, ctx->jpeg_enc.bounce_buffer.dma,
 			   VEPU_REG_ADDR_OUTPUT_STREAM);
-	vepu_write_relaxed(vpu, ctx->bounce_size,
+	vepu_write_relaxed(vpu, ctx->jpeg_enc.bounce_buffer.size,
 			   VEPU_REG_STR_BUF_LIMIT);
 
 	if (pix_fmt->num_planes == 1) {
diff --git a/drivers/staging/media/rockchip/vpu/rockchip_vpu.h b/drivers/staging/media/rockchip/vpu/rockchip_vpu.h
index 1ec2be483e27..b15c02333a70 100644
--- a/drivers/staging/media/rockchip/vpu/rockchip_vpu.h
+++ b/drivers/staging/media/rockchip/vpu/rockchip_vpu.h
@@ -124,10 +124,7 @@ struct rockchip_vpu_dev {
  * @jpeg_quality:	User-specified JPEG compression quality.
  *
  * @codec_ops:		Set of operations related to codec mode.
- *
- * @bounce_dma_addr:	Bounce buffer bus address.
- * @bounce_buf:		Bounce buffer pointer.
- * @bounce_size:	Bounce buffer size.
+ * @jpeg_enc:		JPEG-encoding context.
  */
 struct rockchip_vpu_ctx {
 	struct rockchip_vpu_dev *dev;
@@ -146,9 +143,10 @@ struct rockchip_vpu_ctx {
 
 	const struct rockchip_vpu_codec_ops *codec_ops;
 
-	dma_addr_t bounce_dma_addr;
-	void *bounce_buf;
-	size_t bounce_size;
+	/* Specific for particular codec modes. */
+	union {
+		struct rockchip_vpu_jpeg_enc_hw_ctx jpeg_enc;
+	};
 };
 
 /**
diff --git a/drivers/staging/media/rockchip/vpu/rockchip_vpu_drv.c b/drivers/staging/media/rockchip/vpu/rockchip_vpu_drv.c
index 3638aa1fd25d..39e911797189 100644
--- a/drivers/staging/media/rockchip/vpu/rockchip_vpu_drv.c
+++ b/drivers/staging/media/rockchip/vpu/rockchip_vpu_drv.c
@@ -63,10 +63,15 @@ static void rockchip_vpu_job_finish(struct rockchip_vpu_dev *vpu,
 	avail_size = vb2_plane_size(&dst->vb2_buf, 0) -
 		     ctx->vpu_dst_fmt->header_size;
 	if (bytesused <= avail_size) {
-		if (ctx->bounce_buf) {
+		/*
+		 * The bounce buffer is only for the JPEG encoder.
+		 * TODO: Rework the JPEG encoder to eliminate the need
+		 * for a bounce buffer.
+		 */
+		if (ctx->jpeg_enc.bounce_buffer.cpu) {
 			memcpy(vb2_plane_vaddr(&dst->vb2_buf, 0) +
 			       ctx->vpu_dst_fmt->header_size,
-			       ctx->bounce_buf, bytesused);
+			       ctx->jpeg_enc.bounce_buffer.cpu, bytesused);
 		}
 		dst->vb2_buf.planes[0].bytesused =
 			ctx->vpu_dst_fmt->header_size + bytesused;
diff --git a/drivers/staging/media/rockchip/vpu/rockchip_vpu_enc.c b/drivers/staging/media/rockchip/vpu/rockchip_vpu_enc.c
index ae1ff3d9b9d2..0ace50746f2e 100644
--- a/drivers/staging/media/rockchip/vpu/rockchip_vpu_enc.c
+++ b/drivers/staging/media/rockchip/vpu/rockchip_vpu_enc.c
@@ -514,6 +514,7 @@ static int rockchip_vpu_start_streaming(struct vb2_queue *q, unsigned int count)
 {
 	struct rockchip_vpu_ctx *ctx = vb2_get_drv_priv(q);
 	enum rockchip_vpu_codec_mode codec_mode;
+	int ret = 0;
 
 	if (V4L2_TYPE_IS_OUTPUT(q->type))
 		ctx->sequence_out = 0;
@@ -526,17 +527,10 @@ static int rockchip_vpu_start_streaming(struct vb2_queue *q, unsigned int count)
 	vpu_debug(4, "Codec mode = %d\n", codec_mode);
 	ctx->codec_ops = &ctx->dev->variant->codec_ops[codec_mode];
 
-	/* A bounce buffer is needed for the JPEG payload */
-	if (!V4L2_TYPE_IS_OUTPUT(q->type)) {
-		ctx->bounce_size = ctx->dst_fmt.plane_fmt[0].sizeimage -
-				  ctx->vpu_dst_fmt->header_size;
-		ctx->bounce_buf = dma_alloc_attrs(ctx->dev->dev,
-						  ctx->bounce_size,
-						  &ctx->bounce_dma_addr,
-						  GFP_KERNEL,
-						  DMA_ATTR_ALLOC_SINGLE_PAGES);
-	}
-	return 0;
+	if (!V4L2_TYPE_IS_OUTPUT(q->type))
+		if (ctx->codec_ops && ctx->codec_ops->init)
+			ret = ctx->codec_ops->init(ctx);
+	return ret;
 }
 
 static void rockchip_vpu_stop_streaming(struct vb2_queue *q)
@@ -544,11 +538,8 @@ static void rockchip_vpu_stop_streaming(struct vb2_queue *q)
 	struct rockchip_vpu_ctx *ctx = vb2_get_drv_priv(q);
 
 	if (!V4L2_TYPE_IS_OUTPUT(q->type))
-		dma_free_attrs(ctx->dev->dev,
-			       ctx->bounce_size,
-			       ctx->bounce_buf,
-			       ctx->bounce_dma_addr,
-			       DMA_ATTR_ALLOC_SINGLE_PAGES);
+		if (ctx->codec_ops && ctx->codec_ops->exit)
+			ctx->codec_ops->exit(ctx);
 
 	/*
 	 * The mem2mem framework calls v4l2_m2m_cancel_job before
diff --git a/drivers/staging/media/rockchip/vpu/rockchip_vpu_hw.h b/drivers/staging/media/rockchip/vpu/rockchip_vpu_hw.h
index 2b955da1be1a..46716d121538 100644
--- a/drivers/staging/media/rockchip/vpu/rockchip_vpu_hw.h
+++ b/drivers/staging/media/rockchip/vpu/rockchip_vpu_hw.h
@@ -18,9 +18,33 @@ struct rockchip_vpu_ctx;
 struct rockchip_vpu_buf;
 struct rockchip_vpu_variant;
 
+/**
+ * struct rockchip_vpu_aux_buf - auxiliary DMA buffer for hardware data
+ * @cpu:	CPU pointer to the buffer.
+ * @dma:	DMA address of the buffer.
+ * @size:	Size of the buffer.
+ */
+struct rockchip_vpu_aux_buf {
+	void *cpu;
+	dma_addr_t dma;
+	size_t size;
+};
+
+/**
+ * struct rockchip_vpu_jpeg_enc_hw_ctx
+ * @bounce_buffer:	Bounce buffer
+ */
+struct rockchip_vpu_jpeg_enc_hw_ctx {
+	struct rockchip_vpu_aux_buf bounce_buffer;
+};
+
 /**
  * struct rockchip_vpu_codec_ops - codec mode specific operations
  *
+ * @init:	If needed, can be used for initialization.
+ *		Optional and called from process context.
+ * @exit:	If needed, can be used to undo the .init phase.
+ *		Optional and called from process context.
  * @run:	Start single {en,de)coding job. Called from atomic context
  *		to indicate that a pair of buffers is ready and the hardware
  *		should be programmed and started.
@@ -28,6 +52,8 @@ struct rockchip_vpu_variant;
  * @reset:	Reset the hardware in case of a timeout.
  */
 struct rockchip_vpu_codec_ops {
+	int (*init)(struct rockchip_vpu_ctx *ctx);
+	void (*exit)(struct rockchip_vpu_ctx *ctx);
 	void (*run)(struct rockchip_vpu_ctx *ctx);
 	void (*done)(struct rockchip_vpu_ctx *ctx, enum vb2_buffer_state);
 	void (*reset)(struct rockchip_vpu_ctx *ctx);
@@ -54,5 +80,7 @@ void rockchip_vpu_irq_done(struct rockchip_vpu_dev *vpu,
 
 void rk3288_vpu_jpeg_enc_run(struct rockchip_vpu_ctx *ctx);
 void rk3399_vpu_jpeg_enc_run(struct rockchip_vpu_ctx *ctx);
+int rockchip_vpu_jpeg_enc_init(struct rockchip_vpu_ctx *ctx);
+void rockchip_vpu_jpeg_enc_exit(struct rockchip_vpu_ctx *ctx);
 
 #endif /* ROCKCHIP_VPU_HW_H_ */
diff --git a/drivers/staging/media/rockchip/vpu/rockchip_vpu_jpeg.c b/drivers/staging/media/rockchip/vpu/rockchip_vpu_jpeg.c
index 0ff0badc1f7a..30b97d207dc5 100644
--- a/drivers/staging/media/rockchip/vpu/rockchip_vpu_jpeg.c
+++ b/drivers/staging/media/rockchip/vpu/rockchip_vpu_jpeg.c
@@ -6,9 +6,11 @@
  * Copyright (C) Jean-Francois Moine (http://moinejf.free.fr)
  * Copyright (C) 2014 Philipp Zabel, Pengutronix
  */
+#include <linux/dma-mapping.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include "rockchip_vpu_jpeg.h"
+#include "rockchip_vpu.h"
 
 #define LUMA_QUANT_OFF		7
 #define CHROMA_QUANT_OFF	72
@@ -288,3 +290,30 @@ void rockchip_vpu_jpeg_header_assemble(struct rockchip_vpu_jpeg_ctx *ctx)
 
 	jpeg_set_quality(buf, ctx->quality);
 }
+
+int rockchip_vpu_jpeg_enc_init(struct rockchip_vpu_ctx *ctx)
+{
+	ctx->jpeg_enc.bounce_buffer.size =
+		ctx->dst_fmt.plane_fmt[0].sizeimage -
+		ctx->vpu_dst_fmt->header_size;
+
+	ctx->jpeg_enc.bounce_buffer.cpu =
+		dma_alloc_attrs(ctx->dev->dev,
+				ctx->jpeg_enc.bounce_buffer.size,
+				&ctx->jpeg_enc.bounce_buffer.dma,
+				GFP_KERNEL,
+				DMA_ATTR_ALLOC_SINGLE_PAGES);
+	if (!ctx->jpeg_enc.bounce_buffer.cpu)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void rockchip_vpu_jpeg_enc_exit(struct rockchip_vpu_ctx *ctx)
+{
+	dma_free_attrs(ctx->dev->dev,
+		       ctx->jpeg_enc.bounce_buffer.size,
+		       ctx->jpeg_enc.bounce_buffer.cpu,
+		       ctx->jpeg_enc.bounce_buffer.dma,
+		       DMA_ATTR_ALLOC_SINGLE_PAGES);
+}
-- 
2.20.1

