radeon/vce: add proper CPB backtrack

Remember what frames we encoded at which position.

Signed-off-by: Christian König <[email protected]>

3 files changed, 123 insertions, 23 deletions

diff --git a/src/gallium/drivers/radeon/radeon_vce.c b/src/gallium/drivers/radeon/radeon_vce.c
index 012b4f8e13e..a7dfcda4816 100644
--- a/src/gallium/drivers/radeon/radeon_vce.c
+++ b/src/gallium/drivers/radeon/radeon_vce.c
@@ -80,6 +80,57 @@ static void dump_feedback(struct rvce_encoder *enc, struct rvid_buffer *fb)
 #endif
 
 /**
+ * reset the CPB handling
+ */
+static void reset_cpb(struct rvce_encoder *enc)
+{
+	unsigned i;
+
+	LIST_INITHEAD(&enc->cpb_slots);
+	for (i = 0; i < RVCE_NUM_CPB_FRAMES; ++i) {
+		struct rvce_cpb_slot *slot = &enc->cpb_array[i];
+		slot->index = i;
+		slot->picture_type = PIPE_H264_ENC_PICTURE_TYPE_SKIP;
+		slot->frame_num = 0;
+		slot->pic_order_cnt = 0;
+		LIST_ADDTAIL(&slot->list, &enc->cpb_slots);
+	}
+}
+
+/**
+ * sort l0 and l1 to the top of the list
+ */
+static void sort_cpb(struct rvce_encoder *enc)
+{
+	struct rvce_cpb_slot *i, *l0 = NULL, *l1 = NULL;
+
+	LIST_FOR_EACH_ENTRY(i, &enc->cpb_slots, list) {
+		if (i->frame_num == enc->pic.ref_idx_l0)
+			l0 = i;
+
+		if (i->frame_num == enc->pic.ref_idx_l1)
+			l1 = i;
+
+		if (enc->pic.picture_type == PIPE_H264_ENC_PICTURE_TYPE_P && l0)
+			break;
+
+		if (enc->pic.picture_type == PIPE_H264_ENC_PICTURE_TYPE_B &&
+		    l0 && l1)
+			break;
+	}
+
+	if (l1) {
+		LIST_DEL(&l1->list);
+		LIST_ADD(&l1->list, &enc->cpb_slots);
+	}
+
+	if (l0) {
+		LIST_DEL(&l0->list);
+		LIST_ADD(&l0->list, &enc->cpb_slots);
+	}
+}
+
+/**
  * destroy this video encoder
  */
 static void rvce_destroy(struct pipe_video_codec *encoder)
@@ -97,6 +148,7 @@ static void rvce_destroy(struct pipe_video_codec *encoder)
 	}
 	rvid_destroy_buffer(&enc->cpb);
 	enc->ws->cs_destroy(enc->cs);
+	FREE(enc->cpb_array);
 	FREE(enc);
 }
 
@@ -118,6 +170,12 @@ static void rvce_begin_frame(struct pipe_video_codec *encoder,
 
 	enc->get_buffer(vid_buf->resources[0], &enc->handle, &enc->luma);
 	enc->get_buffer(vid_buf->resources[1], NULL, &enc->chroma);
+
+	if (pic->picture_type == PIPE_H264_ENC_PICTURE_TYPE_IDR)
+		reset_cpb(enc);
+	else if (pic->picture_type == PIPE_H264_ENC_PICTURE_TYPE_P ||
+	         pic->picture_type == PIPE_H264_ENC_PICTURE_TYPE_B)
+		sort_cpb(enc);
 	
 	if (!enc->stream_handle) {
 		struct rvid_buffer fb;
@@ -167,7 +225,17 @@ static void rvce_end_frame(struct pipe_video_codec *encoder,
 			   struct pipe_picture_desc *picture)
 {
 	struct rvce_encoder *enc = (struct rvce_encoder*)encoder;
+	struct rvce_cpb_slot *slot = LIST_ENTRY(
+		struct rvce_cpb_slot, enc->cpb_slots.prev, list);
+
 	flush(enc);
+
+	/* update the CPB backtrack with the just encoded frame */
+	LIST_DEL(&slot->list);
+	slot->picture_type = enc->pic.picture_type;
+	slot->frame_num = enc->pic.frame_num;
+	slot->pic_order_cnt = enc->pic.pic_order_cnt;
+	LIST_ADD(&slot->list, &enc->cpb_slots);
 }
 
 static void rvce_get_feedback(struct pipe_video_codec *encoder,
@@ -213,7 +281,7 @@ struct pipe_video_codec *rvce_create_encoder(struct pipe_context *context,
 	struct rvce_encoder *enc;
 	struct pipe_video_buffer *tmp_buf, templat = {};
 	struct radeon_surface *tmp_surf;
-	unsigned pitch, vpitch;
+	unsigned cpb_size;
 
 	if (!rscreen->info.vce_fw_version) {
 		RVID_ERR("Kernel doesn't supports VCE!\n");
@@ -258,16 +326,22 @@ struct pipe_video_codec *rvce_create_encoder(struct pipe_context *context,
 	}
 
 	get_buffer(((struct vl_video_buffer *)tmp_buf)->resources[0], NULL, &tmp_surf);
-	pitch = align(tmp_surf->level[0].pitch_bytes, 128);
-	vpitch = align(tmp_surf->npix_y, 16);
+	cpb_size = align(tmp_surf->level[0].pitch_bytes, 128);
+	cpb_size = cpb_size * align(tmp_surf->npix_y, 16);
+	cpb_size = cpb_size * 3 / 2;
+	cpb_size = cpb_size * RVCE_NUM_CPB_FRAMES;
 	tmp_buf->destroy(tmp_buf);
-	if (!rvid_create_buffer(enc->ws, &enc->cpb,
-			pitch * vpitch * 1.5 * RVCE_NUM_CPB_FRAMES,
-			RADEON_DOMAIN_VRAM)) {
+	if (!rvid_create_buffer(enc->ws, &enc->cpb, cpb_size, RADEON_DOMAIN_VRAM)) {
 		RVID_ERR("Can't create CPB buffer.\n");
 		goto error;
 	}
 
+	enc->cpb_array = CALLOC(RVCE_NUM_CPB_FRAMES, sizeof(struct rvce_cpb_slot));
+	if (!enc->cpb_array)
+		goto error;
+
+	reset_cpb(enc);
+
 	radeon_vce_40_2_2_init(enc);
 
 	return &enc->base;
@@ -278,6 +352,7 @@ error:
 
 	rvid_destroy_buffer(&enc->cpb);
 
+	FREE(enc->cpb_array);
 	FREE(enc);
 	return NULL;
 }
diff --git a/src/gallium/drivers/radeon/radeon_vce.h b/src/gallium/drivers/radeon/radeon_vce.h
index 3ea738b9452..f815cad38aa 100644
--- a/src/gallium/drivers/radeon/radeon_vce.h
+++ b/src/gallium/drivers/radeon/radeon_vce.h
@@ -34,6 +34,8 @@
 #ifndef RADEON_VCE_H
 #define RADEON_VCE_H
 
+#include "util/u_double_list.h"
+
 #define RVCE_RELOC(buf, usage, domain) (enc->ws->cs_add_reloc(enc->cs, (buf), (usage), domain, RADEON_PRIO_MIN))
 
 #define RVCE_CS(value) (enc->cs->buf[enc->cs->cdw++] = (value))
@@ -52,6 +54,16 @@ typedef void (*rvce_get_buffer)(struct pipe_resource *resource,
 				struct radeon_winsys_cs_handle **handle,
 				struct radeon_surface **surface);
 
+/* Coded picture buffer slot */
+struct rvce_cpb_slot {
+	struct list_head		list;
+
+	unsigned			index;
+	enum pipe_h264_enc_picture_type	picture_type;
+	unsigned			frame_num;
+	unsigned			pic_order_cnt;
+};
+
 /* VCE encoder representation */
 struct rvce_encoder {
 	struct pipe_video_codec		base;
@@ -82,6 +94,9 @@ struct rvce_encoder {
 	struct radeon_winsys_cs_handle*	bs_handle;
 	unsigned			bs_size;
 
+	struct rvce_cpb_slot		*cpb_array;
+	struct list_head		cpb_slots;
+
 	struct rvid_buffer		*fb;
 	struct rvid_buffer		cpb;
 	struct pipe_h264_enc_picture_desc pic;
diff --git a/src/gallium/drivers/radeon/radeon_vce_40_2_2.c b/src/gallium/drivers/radeon/radeon_vce_40_2_2.c
index 33a58f3e8e9..1327d64f983 100644
--- a/src/gallium/drivers/radeon/radeon_vce_40_2_2.c
+++ b/src/gallium/drivers/radeon/radeon_vce_40_2_2.c
@@ -44,6 +44,27 @@
 #include "radeon_video.h"
 #include "radeon_vce.h"
 
+static struct rvce_cpb_slot *current_slot(struct rvce_encoder *enc)
+{
+	return LIST_ENTRY(struct rvce_cpb_slot, enc->cpb_slots.prev, list);
+}
+
+static struct rvce_cpb_slot *l0_slot(struct rvce_encoder *enc)
+{
+	return LIST_ENTRY(struct rvce_cpb_slot, enc->cpb_slots.next, list);
+}
+
+static void frame_offset(struct rvce_encoder *enc, struct rvce_cpb_slot *slot,
+			 unsigned *luma_offset, unsigned *chroma_offset)
+{
+	unsigned pitch = align(enc->luma->level[0].pitch_bytes, 128);
+	unsigned vpitch = align(enc->luma->npix_y, 16);
+	unsigned fsize = pitch * (vpitch + vpitch / 2);
+
+	*luma_offset = slot->index * fsize;
+	*chroma_offset = *luma_offset + pitch * vpitch;
+}
+
 static void session(struct rvce_encoder *enc)
 {
 	RVCE_BEGIN(0x00000001); // session cmd
@@ -218,17 +239,6 @@ static void rdo(struct rvce_encoder *enc)
 	RVCE_END();
 }
 
-static void frame_offset(struct rvce_encoder *enc, unsigned frame_num,
-			 unsigned *luma_offset, unsigned *chroma_offset)
-{
-	unsigned pitch = align(enc->luma->level[0].pitch_bytes, 128);
-	unsigned vpitch = align(enc->luma->npix_y, 16);
-	unsigned fsize = pitch * (vpitch + vpitch / 2);
-
-	*luma_offset = (frame_num % RVCE_NUM_CPB_FRAMES) * fsize;
-	*chroma_offset = *luma_offset + pitch * vpitch;
-}
-
 static void encode(struct rvce_encoder *enc)
 {
 	int i;
@@ -297,11 +307,11 @@ static void encode(struct rvce_encoder *enc)
 		RVCE_CS(0xffffffff); // chromaOffset
 	}
 	else if(enc->pic.picture_type == PIPE_H264_ENC_PICTURE_TYPE_P) {
-		frame_offset(enc, enc->pic.ref_idx_l0, &luma_offset, &chroma_offset);
-		RVCE_CS(0x00000000); // encPicType
-		// TODO: Stores these in the CPB backtrack
-		RVCE_CS(enc->pic.frame_num - 1); // frameNumber
-		RVCE_CS(enc->pic.frame_num - 1); // pictureOrderCount
+		struct rvce_cpb_slot *l0 = l0_slot(enc);
+		frame_offset(enc, l0, &luma_offset, &chroma_offset);
+		RVCE_CS(l0->picture_type); // encPicType
+		RVCE_CS(l0->frame_num); // frameNumber
+		RVCE_CS(l0->pic_order_cnt); // pictureOrderCount
 		RVCE_CS(luma_offset); // lumaOffset
 		RVCE_CS(chroma_offset); // chromaOffset
 	}
@@ -314,7 +324,7 @@ static void encode(struct rvce_encoder *enc)
 		RVCE_CS(0xffffffff); // chromaOffset
 	}
 	
-	frame_offset(enc, enc->pic.frame_num, &luma_offset, &chroma_offset);
+	frame_offset(enc, current_slot(enc), &luma_offset, &chroma_offset);
 	RVCE_CS(luma_offset); // encReconstructedLumaOffset
 	RVCE_CS(chroma_offset); // encReconstructedChromaOffset
 	RVCE_CS(0x00000000); // encColocBufferOffset