media: hantro: Introduce G2/HEVC decoder

Implement all the logic to get G2 hardware decoding HEVC frames.
It supports up level 5.1 HEVC stream.
It doesn't support yet 10 bits formats or the scaling feature.

Add HANTRO HEVC dedicated control to skip some bits at the beginning
of the slice header. That is very specific to this hardware so can't
go into uapi structures. Computing the needed value is complex and requires
information from the stream that only the userland knows so let it
provide the correct value to the driver.
Signed-off-by: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Co-developed-by: Adrian Ratiu <adrian.ratiu@collabora.com>
Signed-off-by: Adrian Ratiu <adrian.ratiu@collabora.com>
Co-developed-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>

drivers/staging/media/hantro/Makefile

@@ -10,12 +10,14 @@ hantro-vpu-y += \
 		hantro_g1.o \
 		hantro_g1_h264_dec.o \
 		hantro_g1_mpeg2_dec.o \
+		hantro_g2_hevc_dec.o \
 		hantro_g1_vp8_dec.o \
 		rk3399_vpu_hw_jpeg_enc.o \
 		rk3399_vpu_hw_mpeg2_dec.o \
 		rk3399_vpu_hw_vp8_dec.o \
 		hantro_jpeg.o \
 		hantro_h264.o \
+		hantro_hevc.o \
 		hantro_mpeg2.o \
 		hantro_vp8.o
 

drivers/staging/media/hantro/hantro.h

@@ -221,6 +221,7 @@ struct hantro_dev {
  * @jpeg_enc:		JPEG-encoding context.
  * @mpeg2_dec:		MPEG-2-decoding context.
  * @vp8_dec:		VP8-decoding context.
+ * @hevc_dec:		HEVC-decoding context.
  */
 struct hantro_ctx {
 	struct hantro_dev *dev;
@@ -247,6 +248,7 @@ struct hantro_ctx {
 		struct hantro_jpeg_enc_hw_ctx jpeg_enc;
 		struct hantro_mpeg2_dec_hw_ctx mpeg2_dec;
 		struct hantro_vp8_dec_hw_ctx vp8_dec;
+		struct hantro_hevc_dec_hw_ctx hevc_dec;
 	};
 };
 

drivers/staging/media/hantro/hantro_drv.c

@@ -290,6 +290,26 @@ static int hantro_jpeg_s_ctrl(struct v4l2_ctrl *ctrl)
 	return 0;
 }
 
+static int hantro_hevc_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct hantro_ctx *ctx;
+
+	ctx = container_of(ctrl->handler,
+			   struct hantro_ctx, ctrl_handler);
+
+	vpu_debug(1, "s_ctrl: id = %d, val = %d\n", ctrl->id, ctrl->val);
+
+	switch (ctrl->id) {
+	case V4L2_CID_HANTRO_HEVC_SLICE_HEADER_SKIP:
+		ctx->hevc_dec.ctrls.hevc_hdr_skip_length = ctrl->val;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct v4l2_ctrl_ops hantro_ctrl_ops = {
 	.try_ctrl = hantro_try_ctrl,
 };
@@ -298,6 +318,10 @@ static const struct v4l2_ctrl_ops hantro_jpeg_ctrl_ops = {
 	.s_ctrl = hantro_jpeg_s_ctrl,
 };
 
+static const struct v4l2_ctrl_ops hantro_hevc_ctrl_ops = {
+	.s_ctrl = hantro_hevc_s_ctrl,
+};
+
 static const struct hantro_ctrl controls[] = {
 	{
 		.codec = HANTRO_JPEG_ENCODER,
@@ -423,6 +447,18 @@ static const struct hantro_ctrl controls[] = {
 		.cfg = {
 			.id = V4L2_CID_MPEG_VIDEO_HEVC_DECODE_PARAMS,
 		},
+	}, {
+		.codec = HANTRO_HEVC_DECODER,
+		.cfg = {
+			.id = V4L2_CID_HANTRO_HEVC_SLICE_HEADER_SKIP,
+			.name = "Hantro HEVC slice header skip bytes",
+			.type = V4L2_CTRL_TYPE_INTEGER,
+			.min = 0,
+			.def = 0,
+			.max = 0x100,
+			.step = 1,
+			.ops = &hantro_hevc_ctrl_ops,
+		},
 	},
 };
 

drivers/staging/media/hantro/hantro_g2_regs.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021, Collabora
+ *
+ * Author: Benjamin Gaignard <benjamin.gaignard@collabora.com>
+ */
+
+#ifndef HANTRO_G2_REGS_H_
+#define HANTRO_G2_REGS_H_
+
+#include "hantro.h"
+
+#define G2_SWREG(nr)	((nr) * 4)
+
+#define G2_DEC_REG(b, s, m) \
+	((const struct hantro_reg) { \
+		.base = G2_SWREG(b), \
+		.shift = s, \
+		.mask = m, \
+	})
+
+#define G2_REG_VERSION			G2_SWREG(0)
+
+#define G2_REG_INTERRUPT		G2_SWREG(1)
+#define G2_REG_INTERRUPT_DEC_RDY_INT	BIT(12)
+#define G2_REG_INTERRUPT_DEC_ABORT_E	BIT(5)
+#define G2_REG_INTERRUPT_DEC_IRQ_DIS	BIT(4)
+#define G2_REG_INTERRUPT_DEC_E		BIT(0)
+
+#define g2_strm_swap		G2_DEC_REG(2, 28, 0xf)
+#define g2_dirmv_swap		G2_DEC_REG(2, 20, 0xf)
+
+#define g2_mode			G2_DEC_REG(3, 27, 0x1f)
+#define g2_compress_swap	G2_DEC_REG(3, 20, 0xf)
+#define g2_ref_compress_bypass	G2_DEC_REG(3, 17, 0x1)
+#define g2_out_rs_e		G2_DEC_REG(3, 16, 0x1)
+#define g2_out_dis		G2_DEC_REG(3, 15, 0x1)
+#define g2_out_filtering_dis	G2_DEC_REG(3, 14, 0x1)
+#define g2_write_mvs_e		G2_DEC_REG(3, 12, 0x1)
+
+#define g2_pic_width_in_cbs	G2_DEC_REG(4, 19, 0x1fff)
+#define g2_pic_height_in_cbs	G2_DEC_REG(4, 6,  0x1fff)
+#define g2_num_ref_frames	G2_DEC_REG(4, 0,  0x1f)
+
+#define g2_scaling_list_e	G2_DEC_REG(5, 24, 0x1)
+#define g2_cb_qp_offset		G2_DEC_REG(5, 19, 0x1f)
+#define g2_cr_qp_offset		G2_DEC_REG(5, 14, 0x1f)
+#define g2_sign_data_hide	G2_DEC_REG(5, 12, 0x1)
+#define g2_tempor_mvp_e		G2_DEC_REG(5, 11, 0x1)
+#define g2_max_cu_qpd_depth	G2_DEC_REG(5, 5,  0x3f)
+#define g2_cu_qpd_e		G2_DEC_REG(5, 4,  0x1)
+
+#define g2_stream_len		G2_DEC_REG(6, 0,  0xffffffff)
+
+#define g2_cabac_init_present	G2_DEC_REG(7, 31, 0x1)
+#define g2_weight_pred_e	G2_DEC_REG(7, 28, 0x1)
+#define g2_weight_bipr_idc	G2_DEC_REG(7, 26, 0x3)
+#define g2_filter_over_slices	G2_DEC_REG(7, 25, 0x1)
+#define g2_filter_over_tiles	G2_DEC_REG(7, 24, 0x1)
+#define g2_asym_pred_e		G2_DEC_REG(7, 23, 0x1)
+#define g2_sao_e		G2_DEC_REG(7, 22, 0x1)
+#define g2_pcm_filt_d		G2_DEC_REG(7, 21, 0x1)
+#define g2_slice_chqp_present	G2_DEC_REG(7, 20, 0x1)
+#define g2_dependent_slice	G2_DEC_REG(7, 19, 0x1)
+#define g2_filter_override	G2_DEC_REG(7, 18, 0x1)
+#define g2_strong_smooth_e	G2_DEC_REG(7, 17, 0x1)
+#define g2_filt_offset_beta	G2_DEC_REG(7, 12, 0x1f)
+#define g2_filt_offset_tc	G2_DEC_REG(7, 7,  0x1f)
+#define g2_slice_hdr_ext_e	G2_DEC_REG(7, 6,  0x1)
+#define g2_slice_hdr_ext_bits	G2_DEC_REG(7, 3,  0x7)
+
+#define g2_const_intra_e	G2_DEC_REG(8, 31, 0x1)
+#define g2_filt_ctrl_pres	G2_DEC_REG(8, 30, 0x1)
+#define g2_idr_pic_e		G2_DEC_REG(8, 16, 0x1)
+#define g2_bit_depth_pcm_y	G2_DEC_REG(8, 12, 0xf)
+#define g2_bit_depth_pcm_c	G2_DEC_REG(8, 8,  0xf)
+#define g2_bit_depth_y_minus8	G2_DEC_REG(8, 6,  0x3)
+#define g2_bit_depth_c_minus8	G2_DEC_REG(8, 4,  0x3)
+#define g2_output_8_bits	G2_DEC_REG(8, 3,  0x1)
+
+#define g2_refidx1_active	G2_DEC_REG(9, 19, 0x1f)
+#define g2_refidx0_active	G2_DEC_REG(9, 14, 0x1f)
+#define g2_hdr_skip_length	G2_DEC_REG(9, 0,  0x3fff)
+
+#define g2_start_code_e		G2_DEC_REG(10, 31, 0x1)
+#define g2_init_qp		G2_DEC_REG(10, 24, 0x3f)
+#define g2_num_tile_cols	G2_DEC_REG(10, 19, 0x1f)
+#define g2_num_tile_rows	G2_DEC_REG(10, 14, 0x1f)
+#define g2_tile_e		G2_DEC_REG(10, 1,  0x1)
+#define g2_entropy_sync_e	G2_DEC_REG(10, 0,  0x1)
+
+#define g2_refer_lterm_e	G2_DEC_REG(12, 16, 0xffff)
+#define g2_min_cb_size		G2_DEC_REG(12, 13, 0x7)
+#define g2_max_cb_size		G2_DEC_REG(12, 10, 0x7)
+#define g2_min_pcm_size		G2_DEC_REG(12, 7,  0x7)
+#define g2_max_pcm_size		G2_DEC_REG(12, 4,  0x7)
+#define g2_pcm_e		G2_DEC_REG(12, 3,  0x1)
+#define g2_transform_skip	G2_DEC_REG(12, 2,  0x1)
+#define g2_transq_bypass	G2_DEC_REG(12, 1,  0x1)
+#define g2_list_mod_e		G2_DEC_REG(12, 0,  0x1)
+
+#define hevc_min_trb_size		G2_DEC_REG(13, 13, 0x7)
+#define hevc_max_trb_size		G2_DEC_REG(13, 10, 0x7)
+#define hevc_max_intra_hierdepth	G2_DEC_REG(13, 7,  0x7)
+#define hevc_max_inter_hierdepth	G2_DEC_REG(13, 4,  0x7)
+#define hevc_parallel_merge		G2_DEC_REG(13, 0,  0xf)
+
+#define hevc_rlist_f0		G2_DEC_REG(14, 0,  0x1f)
+#define hevc_rlist_f1		G2_DEC_REG(14, 10, 0x1f)
+#define hevc_rlist_f2		G2_DEC_REG(14, 20, 0x1f)
+#define hevc_rlist_b0		G2_DEC_REG(14, 5,  0x1f)
+#define hevc_rlist_b1		G2_DEC_REG(14, 15, 0x1f)
+#define hevc_rlist_b2		G2_DEC_REG(14, 25, 0x1f)
+
+#define hevc_rlist_f3		G2_DEC_REG(15, 0,  0x1f)
+#define hevc_rlist_f4		G2_DEC_REG(15, 10, 0x1f)
+#define hevc_rlist_f5		G2_DEC_REG(15, 20, 0x1f)
+#define hevc_rlist_b3		G2_DEC_REG(15, 5,  0x1f)
+#define hevc_rlist_b4		G2_DEC_REG(15, 15, 0x1f)
+#define hevc_rlist_b5		G2_DEC_REG(15, 25, 0x1f)
+
+#define hevc_rlist_f6		G2_DEC_REG(16, 0,  0x1f)
+#define hevc_rlist_f7		G2_DEC_REG(16, 10, 0x1f)
+#define hevc_rlist_f8		G2_DEC_REG(16, 20, 0x1f)
+#define hevc_rlist_b6		G2_DEC_REG(16, 5,  0x1f)
+#define hevc_rlist_b7		G2_DEC_REG(16, 15, 0x1f)
+#define hevc_rlist_b8		G2_DEC_REG(16, 25, 0x1f)
+
+#define hevc_rlist_f9		G2_DEC_REG(17, 0,  0x1f)
+#define hevc_rlist_f10		G2_DEC_REG(17, 10, 0x1f)
+#define hevc_rlist_f11		G2_DEC_REG(17, 20, 0x1f)
+#define hevc_rlist_b9		G2_DEC_REG(17, 5,  0x1f)
+#define hevc_rlist_b10		G2_DEC_REG(17, 15, 0x1f)
+#define hevc_rlist_b11		G2_DEC_REG(17, 25, 0x1f)
+
+#define hevc_rlist_f12		G2_DEC_REG(18, 0,  0x1f)
+#define hevc_rlist_f13		G2_DEC_REG(18, 10, 0x1f)
+#define hevc_rlist_f14		G2_DEC_REG(18, 20, 0x1f)
+#define hevc_rlist_b12		G2_DEC_REG(18, 5,  0x1f)
+#define hevc_rlist_b13		G2_DEC_REG(18, 15, 0x1f)
+#define hevc_rlist_b14		G2_DEC_REG(18, 25, 0x1f)
+
+#define hevc_rlist_f15		G2_DEC_REG(19, 0,  0x1f)
+#define hevc_rlist_b15		G2_DEC_REG(19, 5,  0x1f)
+
+#define g2_partial_ctb_x	G2_DEC_REG(20, 31, 0x1)
+#define g2_partial_ctb_y	G2_DEC_REG(20, 30, 0x1)
+#define g2_pic_width_4x4	G2_DEC_REG(20, 16, 0xfff)
+#define g2_pic_height_4x4	G2_DEC_REG(20, 0,  0xfff)
+#define hevc_cur_poc_00		G2_DEC_REG(46, 24, 0xff)
+#define hevc_cur_poc_01		G2_DEC_REG(46, 16, 0xff)
+#define hevc_cur_poc_02		G2_DEC_REG(46, 8,  0xff)
+#define hevc_cur_poc_03		G2_DEC_REG(46, 0,  0xff)
+
+#define hevc_cur_poc_04		G2_DEC_REG(47, 24, 0xff)
+#define hevc_cur_poc_05		G2_DEC_REG(47, 16, 0xff)
+#define hevc_cur_poc_06		G2_DEC_REG(47, 8,  0xff)
+#define hevc_cur_poc_07		G2_DEC_REG(47, 0,  0xff)
+
+#define hevc_cur_poc_08		G2_DEC_REG(48, 24, 0xff)
+#define hevc_cur_poc_09		G2_DEC_REG(48, 16, 0xff)
+#define hevc_cur_poc_10		G2_DEC_REG(48, 8,  0xff)
+#define hevc_cur_poc_11		G2_DEC_REG(48, 0,  0xff)
+
+#define hevc_cur_poc_12		G2_DEC_REG(49, 24, 0xff)
+#define hevc_cur_poc_13		G2_DEC_REG(49, 16, 0xff)
+#define hevc_cur_poc_14		G2_DEC_REG(49, 8,  0xff)
+#define hevc_cur_poc_15		G2_DEC_REG(49, 0,  0xff)
+
+#define g2_apf_threshold	G2_DEC_REG(55, 0, 0xffff)
+
+#define g2_clk_gate_e		G2_DEC_REG(58, 16, 0x1)
+#define g2_buswidth		G2_DEC_REG(58, 8,  0x7)
+#define g2_max_burst		G2_DEC_REG(58, 0,  0xff)
+
+#define G2_REG_CONFIG				G2_SWREG(58)
+#define G2_REG_CONFIG_DEC_CLK_GATE_E		BIT(16)
+#define G2_REG_CONFIG_DEC_CLK_GATE_IDLE_E	BIT(17)
+
+#define G2_ADDR_DST		(G2_SWREG(65))
+#define G2_REG_ADDR_REF(i)	(G2_SWREG(67)  + ((i) * 0x8))
+#define G2_ADDR_DST_CHR		(G2_SWREG(99))
+#define G2_REG_CHR_REF(i)	(G2_SWREG(101) + ((i) * 0x8))
+#define G2_ADDR_DST_MV		(G2_SWREG(133))
+#define G2_REG_DMV_REF(i)	(G2_SWREG(135) + ((i) * 0x8))
+#define G2_ADDR_TILE_SIZE	(G2_SWREG(167))
+#define G2_ADDR_STR		(G2_SWREG(169))
+#define HEVC_SCALING_LIST	(G2_SWREG(171))
+#define G2_RASTER_SCAN		(G2_SWREG(175))
+#define G2_RASTER_SCAN_CHR	(G2_SWREG(177))
+#define G2_TILE_FILTER		(G2_SWREG(179))
+#define G2_TILE_SAO		(G2_SWREG(181))
+#define G2_TILE_BSD		(G2_SWREG(183))
+
+#define g2_strm_buffer_len	G2_DEC_REG(258, 0, 0xffffffff)
+#define g2_strm_start_offset	G2_DEC_REG(259, 0, 0xffffffff)
+
+#endif

drivers/staging/media/hantro/hantro_hevc.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hantro VPU HEVC codec driver
+ *
+ * Copyright (C) 2020 Safran Passenger Innovations LLC
+ */
+
+#include <linux/types.h>
+#include <media/v4l2-mem2mem.h>
+
+#include "hantro.h"
+#include "hantro_hw.h"
+
+#define VERT_FILTER_RAM_SIZE 8 /* bytes per pixel row */
+/*
+ * BSD control data of current picture at tile border
+ * 128 bits per 4x4 tile = 128/(8*4) bytes per row
+ */
+#define BSD_CTRL_RAM_SIZE 4 /* bytes per pixel row */
+/* tile border coefficients of filter */
+#define VERT_SAO_RAM_SIZE 48 /* bytes per pixel */
+
+#define MAX_TILE_COLS 20
+#define MAX_TILE_ROWS 22
+
+#define UNUSED_REF	-1
+
+#define G2_ALIGN		16
+
+size_t hantro_hevc_chroma_offset(const struct v4l2_ctrl_hevc_sps *sps)
+{
+	int bytes_per_pixel = sps->bit_depth_luma_minus8 == 0 ? 1 : 2;
+
+	return sps->pic_width_in_luma_samples *
+	       sps->pic_height_in_luma_samples * bytes_per_pixel;
+}
+
+size_t hantro_hevc_motion_vectors_offset(const struct v4l2_ctrl_hevc_sps *sps)
+{
+	size_t cr_offset = hantro_hevc_chroma_offset(sps);
+
+	return ALIGN((cr_offset * 3) / 2, G2_ALIGN);
+}
+
+static size_t hantro_hevc_mv_size(const struct v4l2_ctrl_hevc_sps *sps)
+{
+	u32 min_cb_log2_size_y = sps->log2_min_luma_coding_block_size_minus3 + 3;
+	u32 ctb_log2_size_y = min_cb_log2_size_y + sps->log2_diff_max_min_luma_coding_block_size;
+	u32 pic_width_in_ctbs_y = (sps->pic_width_in_luma_samples + (1 << ctb_log2_size_y) - 1)
+				  >> ctb_log2_size_y;
+	u32 pic_height_in_ctbs_y = (sps->pic_height_in_luma_samples + (1 << ctb_log2_size_y) - 1)
+				   >> ctb_log2_size_y;
+	size_t mv_size;
+
+	mv_size = pic_width_in_ctbs_y * pic_height_in_ctbs_y *
+		  (1 << (2 * (ctb_log2_size_y - 4))) * 16;
+
+	vpu_debug(4, "%dx%d (CTBs) %zu MV bytes\n",
+		  pic_width_in_ctbs_y, pic_height_in_ctbs_y, mv_size);
+
+	return mv_size;
+}
+
+static size_t hantro_hevc_ref_size(struct hantro_ctx *ctx)
+{
+	const struct hantro_hevc_dec_ctrls *ctrls = &ctx->hevc_dec.ctrls;
+	const struct v4l2_ctrl_hevc_sps *sps = ctrls->sps;
+
+	return hantro_hevc_motion_vectors_offset(sps) + hantro_hevc_mv_size(sps);
+}
+
+static void hantro_hevc_ref_free(struct hantro_ctx *ctx)
+{
+	struct hantro_hevc_dec_hw_ctx *hevc_dec = &ctx->hevc_dec;
+	struct hantro_dev *vpu = ctx->dev;
+	int i;
+
+	for (i = 0;  i < NUM_REF_PICTURES; i++) {
+		if (hevc_dec->ref_bufs[i].cpu)
+			dma_free_coherent(vpu->dev, hevc_dec->ref_bufs[i].size,
+					  hevc_dec->ref_bufs[i].cpu,
+					  hevc_dec->ref_bufs[i].dma);
+	}
+}
+
+static void hantro_hevc_ref_init(struct hantro_ctx *ctx)
+{
+	struct hantro_hevc_dec_hw_ctx *hevc_dec = &ctx->hevc_dec;
+	int i;
+
+	for (i = 0;  i < NUM_REF_PICTURES; i++)
+		hevc_dec->ref_bufs_poc[i] = UNUSED_REF;
+}
+
+dma_addr_t hantro_hevc_get_ref_buf(struct hantro_ctx *ctx,
+				   int poc)
+{
+	struct hantro_hevc_dec_hw_ctx *hevc_dec = &ctx->hevc_dec;
+	int i;
+
+	/* Find the reference buffer in already know ones */
+	for (i = 0;  i < NUM_REF_PICTURES; i++) {
+		if (hevc_dec->ref_bufs_poc[i] == poc) {
+			hevc_dec->ref_bufs_used |= 1 << i;
+			return hevc_dec->ref_bufs[i].dma;
+		}
+	}
+
+	/* Allocate a new reference buffer */
+	for (i = 0; i < NUM_REF_PICTURES; i++) {
+		if (hevc_dec->ref_bufs_poc[i] == UNUSED_REF) {
+			if (!hevc_dec->ref_bufs[i].cpu) {
+				struct hantro_dev *vpu = ctx->dev;
+
+				/*
+				 * Allocate the space needed for the raw data +
+				 * motion vector data. Optimizations could be to
+				 * allocate raw data in non coherent memory and only
+				 * clear the motion vector data.
+				 */
+				hevc_dec->ref_bufs[i].cpu =
+					dma_alloc_coherent(vpu->dev,
+							   hantro_hevc_ref_size(ctx),
+							   &hevc_dec->ref_bufs[i].dma,
+							   GFP_KERNEL);
+				if (!hevc_dec->ref_bufs[i].cpu)
+					return 0;
+
+				hevc_dec->ref_bufs[i].size = hantro_hevc_ref_size(ctx);
+			}
+			hevc_dec->ref_bufs_used |= 1 << i;
+			memset(hevc_dec->ref_bufs[i].cpu, 0, hantro_hevc_ref_size(ctx));
+			hevc_dec->ref_bufs_poc[i] = poc;
+
+			return hevc_dec->ref_bufs[i].dma;
+		}
+	}
+
+	return 0;
+}
+
+void hantro_hevc_ref_remove_unused(struct hantro_ctx *ctx)
+{
+	struct hantro_hevc_dec_hw_ctx *hevc_dec = &ctx->hevc_dec;
+	int i;
+
+	/* Just tag buffer as unused, do not free them */
+	for (i = 0;  i < NUM_REF_PICTURES; i++) {
+		if (hevc_dec->ref_bufs_poc[i] == UNUSED_REF)
+			continue;
+
+		if (hevc_dec->ref_bufs_used & (1 << i))
+			continue;
+
+		hevc_dec->ref_bufs_poc[i] = UNUSED_REF;
+	}
+}
+
+static int tile_buffer_reallocate(struct hantro_ctx *ctx)
+{
+	struct hantro_dev *vpu = ctx->dev;
+	struct hantro_hevc_dec_hw_ctx *hevc_dec = &ctx->hevc_dec;
+	const struct hantro_hevc_dec_ctrls *ctrls = &ctx->hevc_dec.ctrls;
+	const struct v4l2_ctrl_hevc_pps *pps = ctrls->pps;
+	const struct v4l2_ctrl_hevc_sps *sps = ctrls->sps;
+	unsigned int num_tile_cols = pps->num_tile_columns_minus1 + 1;
+	unsigned int height64 = (sps->pic_height_in_luma_samples + 63) & ~63;
+	unsigned int size;
+
+	if (num_tile_cols <= 1 ||
+	    num_tile_cols <= hevc_dec->num_tile_cols_allocated)
+		return 0;
+
+	/* Need to reallocate due to tiles passed via PPS */
+	if (hevc_dec->tile_filter.cpu) {
+		dma_free_coherent(vpu->dev, hevc_dec->tile_filter.size,
+				  hevc_dec->tile_filter.cpu,
+				  hevc_dec->tile_filter.dma);
+		hevc_dec->tile_filter.cpu = NULL;
+	}
+
+	if (hevc_dec->tile_sao.cpu) {
+		dma_free_coherent(vpu->dev, hevc_dec->tile_sao.size,
+				  hevc_dec->tile_sao.cpu,
+				  hevc_dec->tile_sao.dma);
+		hevc_dec->tile_sao.cpu = NULL;
+	}
+
+	if (hevc_dec->tile_bsd.cpu) {
+		dma_free_coherent(vpu->dev, hevc_dec->tile_bsd.size,
+				  hevc_dec->tile_bsd.cpu,
+				  hevc_dec->tile_bsd.dma);
+		hevc_dec->tile_bsd.cpu = NULL;
+	}
+
+	size = VERT_FILTER_RAM_SIZE * height64 * (num_tile_cols - 1);
+	hevc_dec->tile_filter.cpu = dma_alloc_coherent(vpu->dev, size,
+						       &hevc_dec->tile_filter.dma,
+						       GFP_KERNEL);
+	if (!hevc_dec->tile_filter.cpu)
+		goto err_free_tile_buffers;
+	hevc_dec->tile_filter.size = size;
+
+	size = VERT_SAO_RAM_SIZE * height64 * (num_tile_cols - 1);
+	hevc_dec->tile_sao.cpu = dma_alloc_coherent(vpu->dev, size,
+						    &hevc_dec->tile_sao.dma,
+						    GFP_KERNEL);
+	if (!hevc_dec->tile_sao.cpu)
+		goto err_free_tile_buffers;
+	hevc_dec->tile_sao.size = size;
+
+	size = BSD_CTRL_RAM_SIZE * height64 * (num_tile_cols - 1);
+	hevc_dec->tile_bsd.cpu = dma_alloc_coherent(vpu->dev, size,
+						    &hevc_dec->tile_bsd.dma,
+						    GFP_KERNEL);
+	if (!hevc_dec->tile_bsd.cpu)
+		goto err_free_tile_buffers;
+	hevc_dec->tile_bsd.size = size;
+
+	hevc_dec->num_tile_cols_allocated = num_tile_cols;
+
+	return 0;
+
+err_free_tile_buffers:
+	if (hevc_dec->tile_filter.cpu)
+		dma_free_coherent(vpu->dev, hevc_dec->tile_filter.size,
+				  hevc_dec->tile_filter.cpu,
+				  hevc_dec->tile_filter.dma);
+	hevc_dec->tile_filter.cpu = NULL;
+
+	if (hevc_dec->tile_sao.cpu)
+		dma_free_coherent(vpu->dev, hevc_dec->tile_sao.size,
+				  hevc_dec->tile_sao.cpu,
+				  hevc_dec->tile_sao.dma);
+	hevc_dec->tile_sao.cpu = NULL;
+
+	if (hevc_dec->tile_bsd.cpu)
+		dma_free_coherent(vpu->dev, hevc_dec->tile_bsd.size,
+				  hevc_dec->tile_bsd.cpu,
+				  hevc_dec->tile_bsd.dma);
+	hevc_dec->tile_bsd.cpu = NULL;
+
+	return -ENOMEM;
+}
+
+int hantro_hevc_dec_prepare_run(struct hantro_ctx *ctx)
+{
+	struct hantro_hevc_dec_hw_ctx *hevc_ctx = &ctx->hevc_dec;
+	struct hantro_hevc_dec_ctrls *ctrls = &hevc_ctx->ctrls;
+	int ret;
+
+	hantro_start_prepare_run(ctx);
+
+	ctrls->decode_params =
+		hantro_get_ctrl(ctx, V4L2_CID_MPEG_VIDEO_HEVC_DECODE_PARAMS);
+	if (WARN_ON(!ctrls->decode_params))
+		return -EINVAL;
+
+	ctrls->sps =
+		hantro_get_ctrl(ctx, V4L2_CID_MPEG_VIDEO_HEVC_SPS);
+	if (WARN_ON(!ctrls->sps))
+		return -EINVAL;
+
+	ctrls->pps =
+		hantro_get_ctrl(ctx, V4L2_CID_MPEG_VIDEO_HEVC_PPS);
+	if (WARN_ON(!ctrls->pps))
+		return -EINVAL;
+
+	ret = tile_buffer_reallocate(ctx);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+void hantro_hevc_dec_exit(struct hantro_ctx *ctx)
+{
+	struct hantro_dev *vpu = ctx->dev;
+	struct hantro_hevc_dec_hw_ctx *hevc_dec = &ctx->hevc_dec;
+
+	if (hevc_dec->tile_sizes.cpu)
+		dma_free_coherent(vpu->dev, hevc_dec->tile_sizes.size,
+				  hevc_dec->tile_sizes.cpu,
+				  hevc_dec->tile_sizes.dma);
+	hevc_dec->tile_sizes.cpu = NULL;
+
+	if (hevc_dec->tile_filter.cpu)
+		dma_free_coherent(vpu->dev, hevc_dec->tile_filter.size,
+				  hevc_dec->tile_filter.cpu,
+				  hevc_dec->tile_filter.dma);
+	hevc_dec->tile_filter.cpu = NULL;
+
+	if (hevc_dec->tile_sao.cpu)
+		dma_free_coherent(vpu->dev, hevc_dec->tile_sao.size,
+				  hevc_dec->tile_sao.cpu,
+				  hevc_dec->tile_sao.dma);
+	hevc_dec->tile_sao.cpu = NULL;
+
+	if (hevc_dec->tile_bsd.cpu)
+		dma_free_coherent(vpu->dev, hevc_dec->tile_bsd.size,
+				  hevc_dec->tile_bsd.cpu,
+				  hevc_dec->tile_bsd.dma);
+	hevc_dec->tile_bsd.cpu = NULL;
+
+	hantro_hevc_ref_free(ctx);
+}
+
+int hantro_hevc_dec_init(struct hantro_ctx *ctx)
+{
+	struct hantro_dev *vpu = ctx->dev;
+	struct hantro_hevc_dec_hw_ctx *hevc_dec = &ctx->hevc_dec;
+	unsigned int size;
+
+	memset(hevc_dec, 0, sizeof(*hevc_dec));
+
+	/*
+	 * Maximum number of tiles times width and height (2 bytes each),
+	 * rounding up to next 16 bytes boundary + one extra 16 byte
+	 * chunk (HW guys wanted to have this).
+	 */
+	size = round_up(MAX_TILE_COLS * MAX_TILE_ROWS * 4 * sizeof(u16) + 16, 16);
+	hevc_dec->tile_sizes.cpu = dma_alloc_coherent(vpu->dev, size,
+						      &hevc_dec->tile_sizes.dma,
+						      GFP_KERNEL);
+	if (!hevc_dec->tile_sizes.cpu)
+		return -ENOMEM;
+
+	hevc_dec->tile_sizes.size = size;
+
+	hantro_hevc_ref_init(ctx);
+
+	return 0;
+}

drivers/staging/media/hantro/hantro_hw.h

@@ -20,6 +20,8 @@
 #define MB_WIDTH(w)		DIV_ROUND_UP(w, MB_DIM)
 #define MB_HEIGHT(h)		DIV_ROUND_UP(h, MB_DIM)
 
+#define NUM_REF_PICTURES	(V4L2_HEVC_DPB_ENTRIES_NUM_MAX + 1)
+
 struct hantro_dev;
 struct hantro_ctx;
 struct hantro_buf;
@@ -95,6 +97,46 @@ struct hantro_h264_dec_hw_ctx {
 	struct hantro_h264_dec_ctrls ctrls;
 };
 
+/**
+ * struct hantro_hevc_dec_ctrls
+ * @decode_params: Decode params
+ * @sps:	SPS info
+ * @pps:	PPS info
+ * @hevc_hdr_skip_length: the number of data (in bits) to skip in the
+ *			  slice segment header syntax after 'slice type'
+ *			  token
+ */
+struct hantro_hevc_dec_ctrls {
+	const struct v4l2_ctrl_hevc_decode_params *decode_params;
+	const struct v4l2_ctrl_hevc_sps *sps;
+	const struct v4l2_ctrl_hevc_pps *pps;
+	u32 hevc_hdr_skip_length;
+};
+
+/**
+ * struct hantro_hevc_dec_hw_ctx
+ * @tile_sizes:		Tile sizes buffer
+ * @tile_filter:	Tile vertical filter buffer
+ * @tile_sao:		Tile SAO buffer
+ * @tile_bsd:		Tile BSD control buffer
+ * @ref_bufs:		Internal reference buffers
+ * @ref_bufs_poc:	Internal reference buffers picture order count
+ * @ref_bufs_used:	Bitfield of used reference buffers
+ * @ctrls:		V4L2 controls attached to a run
+ * @num_tile_cols_allocated: number of allocated tiles
+ */
+struct hantro_hevc_dec_hw_ctx {
+	struct hantro_aux_buf tile_sizes;
+	struct hantro_aux_buf tile_filter;
+	struct hantro_aux_buf tile_sao;
+	struct hantro_aux_buf tile_bsd;
+	struct hantro_aux_buf ref_bufs[NUM_REF_PICTURES];
+	int ref_bufs_poc[NUM_REF_PICTURES];
+	u32 ref_bufs_used;
+	struct hantro_hevc_dec_ctrls ctrls;
+	unsigned int num_tile_cols_allocated;
+};
+
 /**
  * struct hantro_mpeg2_dec_hw_ctx
  *
@@ -194,6 +236,15 @@ int hantro_g1_h264_dec_run(struct hantro_ctx *ctx);
 int hantro_h264_dec_init(struct hantro_ctx *ctx);
 void hantro_h264_dec_exit(struct hantro_ctx *ctx);
 
+int hantro_hevc_dec_init(struct hantro_ctx *ctx);
+void hantro_hevc_dec_exit(struct hantro_ctx *ctx);
+int hantro_g2_hevc_dec_run(struct hantro_ctx *ctx);
+int hantro_hevc_dec_prepare_run(struct hantro_ctx *ctx);
+dma_addr_t hantro_hevc_get_ref_buf(struct hantro_ctx *ctx, int poc);
+void hantro_hevc_ref_remove_unused(struct hantro_ctx *ctx);
+size_t hantro_hevc_chroma_offset(const struct v4l2_ctrl_hevc_sps *sps);
+size_t hantro_hevc_motion_vectors_offset(const struct v4l2_ctrl_hevc_sps *sps);
+
 static inline size_t
 hantro_h264_mv_size(unsigned int width, unsigned int height)
 {