radeon/uvd: fix feedback buffer handling v2

Without the correct feedback buffer size UVD runs
into an error on each frame, reducing the maximum FPS.

v2: fixing Michels comments

Signed-off-by: Christian König <[email protected]>
Reviewed-by: Michel Dänzer <[email protected]>
Cc: "10.1" "10.0" "9.2" <[email protected]>
(cherry picked from commit c3c24c3accd1401cbe96098e44850bb1130d80b9)

1 files changed, 28 insertions, 12 deletions

diff --git a/src/gallium/drivers/radeon/radeon_uvd.c b/src/gallium/drivers/radeon/radeon_uvd.c
index 95757e30395..e88c45c5e5d 100644
--- a/src/gallium/drivers/radeon/radeon_uvd.c
+++ b/src/gallium/drivers/radeon/radeon_uvd.c
@@ -58,6 +58,9 @@
 #define NUM_H264_REFS 17
 #define NUM_VC1_REFS 5
 
+#define FB_BUFFER_OFFSET 0x1000
+#define FB_BUFFER_SIZE 2048
+
 /* UVD buffer representation */
 struct ruvd_buffer
 {
@@ -81,6 +84,7 @@ struct ruvd_decoder {
 
 	struct ruvd_buffer		msg_fb_buffers[NUM_BUFFERS];
 	struct ruvd_msg			*msg;
+	uint32_t			*fb;
 
 	struct ruvd_buffer		bs_buffers[NUM_BUFFERS];
 	void*				bs_ptr;
@@ -131,16 +135,21 @@ static void send_cmd(struct ruvd_decoder *dec, unsigned cmd,
 	set_reg(dec, RUVD_GPCOM_VCPU_CMD, cmd << 1);
 }
 
-/* map the next available message buffer */
-static void map_msg_buf(struct ruvd_decoder *dec)
+/* map the next available message/feedback buffer */
+static void map_msg_fb_buf(struct ruvd_decoder *dec)
 {
 	struct ruvd_buffer* buf;
+	uint8_t *ptr;
 
-	/* grap the current message buffer */
+	/* grab the current message/feedback buffer */
 	buf = &dec->msg_fb_buffers[dec->cur_buffer];
 
-	/* copy the message into it */
-	dec->msg = dec->ws->buffer_map(buf->cs_handle, dec->cs, PIPE_TRANSFER_WRITE);
+	/* and map it for CPU access */
+	ptr = dec->ws->buffer_map(buf->cs_handle, dec->cs, PIPE_TRANSFER_WRITE);
+
+	/* calc buffer offsets */
+	dec->msg = (struct ruvd_msg *)ptr;
+	dec->fb = (uint32_t *)(ptr + FB_BUFFER_OFFSET);
 }
 
 /* unmap and send a message command to the VCPU */
@@ -148,8 +157,8 @@ static void send_msg_buf(struct ruvd_decoder *dec)
 {
 	struct ruvd_buffer* buf;
 
-	/* ignore the request if message buffer isn't mapped */
-	if (!dec->msg)
+	/* ignore the request if message/feedback buffer isn't mapped */
+	if (!dec->msg || !dec->fb)
 		return;
 
 	/* grap the current message buffer */
@@ -157,6 +166,8 @@ static void send_msg_buf(struct ruvd_decoder *dec)
 
 	/* unmap the buffer */
 	dec->ws->buffer_unmap(buf->cs_handle);
+	dec->msg = NULL;
+	dec->fb = NULL;
 
 	/* and send it to the hardware */
 	send_cmd(dec, RUVD_CMD_MSG_BUFFER, buf->cs_handle, 0,
@@ -644,7 +655,7 @@ static void ruvd_destroy(struct pipe_video_codec *decoder)
 
 	assert(decoder);
 
-	map_msg_buf(dec);
+	map_msg_fb_buf(dec);
 	memset(dec->msg, 0, sizeof(*dec->msg));
 	dec->msg->size = sizeof(*dec->msg);
 	dec->msg->msg_type = RUVD_MSG_DESTROY;
@@ -773,7 +784,7 @@ static void ruvd_end_frame(struct pipe_video_codec *decoder,
 	memset(dec->bs_ptr, 0, bs_size - dec->bs_size);
 	dec->ws->buffer_unmap(bs_buf->cs_handle);
 
-	map_msg_buf(dec);
+	map_msg_fb_buf(dec);
 	dec->msg->size = sizeof(*dec->msg);
 	dec->msg->msg_type = RUVD_MSG_DECODE;
 	dec->msg->stream_handle = dec->stream_handle;
@@ -813,6 +824,10 @@ static void ruvd_end_frame(struct pipe_video_codec *decoder,
 
 	dec->msg->body.decode.db_surf_tile_config = dec->msg->body.decode.dt_surf_tile_config;
 	dec->msg->body.decode.extension_support = 0x1;
+
+	/* set at least the feedback buffer size */
+	dec->fb[0] = FB_BUFFER_SIZE;
+
 	send_msg_buf(dec);
 
 	send_cmd(dec, RUVD_CMD_DPB_BUFFER, dec->dpb.cs_handle, 0,
@@ -822,7 +837,7 @@ static void ruvd_end_frame(struct pipe_video_codec *decoder,
 	send_cmd(dec, RUVD_CMD_DECODING_TARGET_BUFFER, dt, 0,
 		 RADEON_USAGE_WRITE, RADEON_DOMAIN_VRAM);
 	send_cmd(dec, RUVD_CMD_FEEDBACK_BUFFER, msg_fb_buf->cs_handle,
-		 0x1000, RADEON_USAGE_WRITE, RADEON_DOMAIN_GTT);
+		 FB_BUFFER_OFFSET, RADEON_USAGE_WRITE, RADEON_DOMAIN_GTT);
 	set_reg(dec, RUVD_ENGINE_CNTL, 1);
 
 	flush(dec);
@@ -898,7 +913,8 @@ struct pipe_video_codec *ruvd_create_decoder(struct pipe_context *context,
 
 	bs_buf_size = width * height * 512 / (16 * 16);
 	for (i = 0; i < NUM_BUFFERS; ++i) {
-		unsigned msg_fb_size = align(sizeof(struct ruvd_msg), 0x1000) + 0x1000;
+		unsigned msg_fb_size = FB_BUFFER_OFFSET + FB_BUFFER_SIZE;
+		STATIC_ASSERT(sizeof(struct ruvd_msg) <= FB_BUFFER_OFFSET);
 		if (!create_buffer(dec, &dec->msg_fb_buffers[i], msg_fb_size)) {
 			RUVD_ERR("Can't allocated message buffers.\n");
 			goto error;
@@ -920,7 +936,7 @@ struct pipe_video_codec *ruvd_create_decoder(struct pipe_context *context,
 
 	clear_buffer(dec, &dec->dpb);
 
-	map_msg_buf(dec);
+	map_msg_fb_buf(dec);
 	dec->msg->size = sizeof(*dec->msg);
 	dec->msg->msg_type = RUVD_MSG_CREATE;
 	dec->msg->stream_handle = dec->stream_handle;