From patchwork Tue May 25 16:12:31 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Benjamin Gaignard X-Patchwork-Id: 447616 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.7 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, UNPARSEABLE_RELAY, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 92643C47085 for ; Tue, 25 May 2021 16:12:54 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 6E7AE61413 for ; Tue, 25 May 2021 16:12:54 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232913AbhEYQOX (ORCPT ); Tue, 25 May 2021 12:14:23 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:42734 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232408AbhEYQOW (ORCPT ); Tue, 25 May 2021 12:14:22 -0400 Received: from bhuna.collabora.co.uk (bhuna.collabora.co.uk [IPv6:2a00:1098:0:82:1000:25:2eeb:e3e3]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 4D582C061574; Tue, 25 May 2021 09:12:52 -0700 (PDT) Received: from [127.0.0.1] (localhost [127.0.0.1]) (Authenticated sender: benjamin.gaignard) with ESMTPSA id 78A321F4282B From: Benjamin Gaignard To: ezequiel@collabora.com, p.zabel@pengutronix.de, mchehab@kernel.org, shawnguo@kernel.org, s.hauer@pengutronix.de, festevam@gmail.com, gregkh@linuxfoundation.org, mripard@kernel.org, paul.kocialkowski@bootlin.com, wens@csie.org, jernej.skrabec@siol.net, emil.l.velikov@gmail.com Cc: kernel@pengutronix.de, linux-imx@nxp.com, linux-media@vger.kernel.org, linux-rockchip@lists.infradead.org, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, Benjamin Gaignard Subject: [PATCH v11 2/9] media: hevc: Add decode params control Date: Tue, 25 May 2021 18:12:31 +0200 Message-Id: <20210525161238.1191168-3-benjamin.gaignard@collabora.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20210525161238.1191168-1-benjamin.gaignard@collabora.com> References: <20210525161238.1191168-1-benjamin.gaignard@collabora.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-media@vger.kernel.org Add decode params control and the associated structure to group all the information that are needed to decode a reference frame as is described in ITU-T Rec. H.265 section "8.3.2 Decoding process for reference picture set". Adapt Cedrus driver to these changes. Signed-off-by: Benjamin Gaignard Reviewed-by: Ezequiel Garcia --- version 11: - Split what was done in v4l2-ctrls.c in v4l2-ctrls-core.c and v4l2-ctrls-defs.c .../media/v4l/ext-ctrls-codec.rst | 94 +++++++++++++++---- .../media/v4l/vidioc-queryctrl.rst | 6 ++ drivers/media/v4l2-core/v4l2-ctrls-core.c | 21 +++-- drivers/media/v4l2-core/v4l2-ctrls-defs.c | 4 + drivers/staging/media/sunxi/cedrus/cedrus.c | 6 ++ drivers/staging/media/sunxi/cedrus/cedrus.h | 1 + .../staging/media/sunxi/cedrus/cedrus_dec.c | 2 + .../staging/media/sunxi/cedrus/cedrus_h265.c | 12 ++- include/media/hevc-ctrls.h | 29 ++++-- 9 files changed, 136 insertions(+), 39 deletions(-) diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst index 9cfb471fc6be..9120c5bcaf90 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst @@ -2997,9 +2997,6 @@ enum v4l2_mpeg_video_hevc_size_of_length_field - * - __u8 - ``pic_struct`` - - * - __u8 - - ``num_active_dpb_entries`` - - The number of entries in ``dpb``. * - __u8 - ``ref_idx_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - The list of L0 reference elements as indices in the DPB. @@ -3007,22 +3004,8 @@ enum v4l2_mpeg_video_hevc_size_of_length_field - - ``ref_idx_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - The list of L1 reference elements as indices in the DPB. * - __u8 - - ``num_rps_poc_st_curr_before`` - - The number of reference pictures in the short-term set that come before - the current frame. - * - __u8 - - ``num_rps_poc_st_curr_after`` - - The number of reference pictures in the short-term set that come after - the current frame. - * - __u8 - - ``num_rps_poc_lt_curr`` - - The number of reference pictures in the long-term set. - * - __u8 - - ``padding[7]`` + - ``padding`` - Applications and drivers must set this to zero. - * - struct :c:type:`v4l2_hevc_dpb_entry` - - ``dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - - The decoded picture buffer, for meta-data about reference frames. * - struct :c:type:`v4l2_hevc_pred_weight_table` - ``pred_weight_table`` - The prediction weight coefficients for inter-picture prediction. @@ -3278,3 +3261,78 @@ enum v4l2_mpeg_video_hevc_size_of_length_field - encoding the next frame queued after setting this control. This provides a bitmask which consists of bits [0, LTR_COUNT-1]. This is applicable to the H264 and HEVC encoders. + +``V4L2_CID_MPEG_VIDEO_HEVC_DECODE_PARAMS (struct)`` + Specifies various decode parameters, especially the references picture order + count (POC) for all the lists (short, long, before, current, after) and the + number of entries for each of them. + These parameters are defined according to :ref:`hevc`. + They are described in section 8.3 "Slice decoding process" of the + specification. + +.. c:type:: v4l2_ctrl_hevc_decode_params + +.. cssclass:: longtable + +.. flat-table:: struct v4l2_ctrl_hevc_decode_params + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __s32 + - ``pic_order_cnt_val`` + - PicOrderCntVal as described in section 8.3.1 "Decoding process + for picture order count" of the specification. + * - __u8 + - ``num_active_dpb_entries`` + - The number of entries in ``dpb``. + * - struct :c:type:`v4l2_hevc_dpb_entry` + - ``dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - The decoded picture buffer, for meta-data about reference frames. + * - __u8 + - ``num_poc_st_curr_before`` + - The number of reference pictures in the short-term set that come before + the current frame. + * - __u8 + - ``num_poc_st_curr_after`` + - The number of reference pictures in the short-term set that come after + the current frame. + * - __u8 + - ``num_poc_lt_curr`` + - The number of reference pictures in the long-term set. + * - __u8 + - ``poc_st_curr_before[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - PocStCurrBefore as described in section 8.3.2 "Decoding process for reference + picture set. + * - __u8 + - ``poc_st_curr_after[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - PocStCurrAfter as described in section 8.3.2 "Decoding process for reference + picture set. + * - __u8 + - ``poc_lt_curr[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - PocLtCurr as described in section 8.3.2 "Decoding process for reference + picture set. + * - __u64 + - ``flags`` + - See :ref:`Decode Parameters Flags ` + +.. _hevc_decode_params_flags: + +``Decode Parameters Flags`` + +.. cssclass:: longtable + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_HEVC_DECODE_PARAM_FLAG_IRAP_PIC`` + - 0x00000001 + - + * - ``V4L2_HEVC_DECODE_PARAM_FLAG_IDR_PIC`` + - 0x00000002 + - + * - ``V4L2_HEVC_DECODE_PARAM_FLAG_NO_OUTPUT_OF_PRIOR`` + - 0x00000004 + - diff --git a/Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst b/Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst index 07e54029e1e9..f9ecf6276129 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst @@ -501,6 +501,12 @@ See also the examples in :ref:`control`. - n/a - A struct :c:type:`v4l2_ctrl_vp8_frame`, containing VP8 frame parameters for stateless video decoders. + * - ``V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS`` + - n/a + - n/a + - n/a + - A struct :c:type:`v4l2_ctrl_hevc_decode_params`, containing HEVC + decoding parameters for stateless video decoders. .. raw:: latex diff --git a/drivers/media/v4l2-core/v4l2-ctrls-core.c b/drivers/media/v4l2-core/v4l2-ctrls-core.c index 081439224357..c4b5082849b6 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-core.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-core.c @@ -337,6 +337,7 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx, struct v4l2_ctrl_hevc_pps *p_hevc_pps; struct v4l2_ctrl_hevc_slice_params *p_hevc_slice_params; struct v4l2_ctrl_hdr10_mastering_display *p_hdr10_mastering; + struct v4l2_ctrl_hevc_decode_params *p_hevc_decode_params; struct v4l2_area *area; void *p = ptr.p + idx * ctrl->elem_size; unsigned int i; @@ -616,23 +617,26 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx, zero_padding(*p_hevc_pps); break; - case V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS: - p_hevc_slice_params = p; + case V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS: + p_hevc_decode_params = p; - if (p_hevc_slice_params->num_active_dpb_entries > + if (p_hevc_decode_params->num_active_dpb_entries > V4L2_HEVC_DPB_ENTRIES_NUM_MAX) return -EINVAL; - zero_padding(p_hevc_slice_params->pred_weight_table); - - for (i = 0; i < p_hevc_slice_params->num_active_dpb_entries; + for (i = 0; i < p_hevc_decode_params->num_active_dpb_entries; i++) { struct v4l2_hevc_dpb_entry *dpb_entry = - &p_hevc_slice_params->dpb[i]; + &p_hevc_decode_params->dpb[i]; zero_padding(*dpb_entry); } + break; + case V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS: + p_hevc_slice_params = p; + + zero_padding(p_hevc_slice_params->pred_weight_table); zero_padding(*p_hevc_slice_params); break; @@ -1236,6 +1240,9 @@ static struct v4l2_ctrl *v4l2_ctrl_new(struct v4l2_ctrl_handler *hdl, case V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS: elem_size = sizeof(struct v4l2_ctrl_hevc_slice_params); break; + case V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS: + elem_size = sizeof(struct v4l2_ctrl_hevc_decode_params); + break; case V4L2_CTRL_TYPE_HDR10_CLL_INFO: elem_size = sizeof(struct v4l2_ctrl_hdr10_cll_info); break; diff --git a/drivers/media/v4l2-core/v4l2-ctrls-defs.c b/drivers/media/v4l2-core/v4l2-ctrls-defs.c index 7963c7b43450..b6344bbf1e00 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-defs.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-defs.c @@ -996,6 +996,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_HEVC_SPS: return "HEVC Sequence Parameter Set"; case V4L2_CID_MPEG_VIDEO_HEVC_PPS: return "HEVC Picture Parameter Set"; case V4L2_CID_MPEG_VIDEO_HEVC_SLICE_PARAMS: return "HEVC Slice Parameters"; + case V4L2_CID_MPEG_VIDEO_HEVC_DECODE_PARAMS: return "HEVC Decode Parameters"; case V4L2_CID_MPEG_VIDEO_HEVC_DECODE_MODE: return "HEVC Decode Mode"; case V4L2_CID_MPEG_VIDEO_HEVC_START_CODE: return "HEVC Start Code"; @@ -1487,6 +1488,9 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_MPEG_VIDEO_HEVC_SLICE_PARAMS: *type = V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS; break; + case V4L2_CID_MPEG_VIDEO_HEVC_DECODE_PARAMS: + *type = V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS; + break; case V4L2_CID_UNIT_CELL_SIZE: *type = V4L2_CTRL_TYPE_AREA; *flags |= V4L2_CTRL_FLAG_READ_ONLY; diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.c b/drivers/staging/media/sunxi/cedrus/cedrus.c index fa348c09f844..c0d005dafc6c 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus.c @@ -157,6 +157,12 @@ static const struct cedrus_control cedrus_controls[] = { }, .codec = CEDRUS_CODEC_VP8, }, + { + .cfg = { + .id = V4L2_CID_MPEG_VIDEO_HEVC_DECODE_PARAMS, + }, + .codec = CEDRUS_CODEC_H265, + }, }; #define CEDRUS_CONTROLS_COUNT ARRAY_SIZE(cedrus_controls) diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.h b/drivers/staging/media/sunxi/cedrus/cedrus.h index bbcdcd0787cf..88afba17b78b 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.h +++ b/drivers/staging/media/sunxi/cedrus/cedrus.h @@ -77,6 +77,7 @@ struct cedrus_h265_run { const struct v4l2_ctrl_hevc_sps *sps; const struct v4l2_ctrl_hevc_pps *pps; const struct v4l2_ctrl_hevc_slice_params *slice_params; + const struct v4l2_ctrl_hevc_decode_params *decode_params; }; struct cedrus_vp8_run { diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c index 97e410d92506..40e8c4123f76 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c @@ -70,6 +70,8 @@ void cedrus_device_run(void *priv) V4L2_CID_MPEG_VIDEO_HEVC_PPS); run.h265.slice_params = cedrus_find_control_data(ctx, V4L2_CID_MPEG_VIDEO_HEVC_SLICE_PARAMS); + run.h265.decode_params = cedrus_find_control_data(ctx, + V4L2_CID_MPEG_VIDEO_HEVC_DECODE_PARAMS); break; case V4L2_PIX_FMT_VP8_FRAME: diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c index 10744fab7cea..6821e3d05d34 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c @@ -245,6 +245,7 @@ static void cedrus_h265_setup(struct cedrus_ctx *ctx, const struct v4l2_ctrl_hevc_sps *sps; const struct v4l2_ctrl_hevc_pps *pps; const struct v4l2_ctrl_hevc_slice_params *slice_params; + const struct v4l2_ctrl_hevc_decode_params *decode_params; const struct v4l2_hevc_pred_weight_table *pred_weight_table; dma_addr_t src_buf_addr; dma_addr_t src_buf_end_addr; @@ -256,6 +257,7 @@ static void cedrus_h265_setup(struct cedrus_ctx *ctx, sps = run->h265.sps; pps = run->h265.pps; slice_params = run->h265.slice_params; + decode_params = run->h265.decode_params; pred_weight_table = &slice_params->pred_weight_table; /* MV column buffer size and allocation. */ @@ -487,7 +489,7 @@ static void cedrus_h265_setup(struct cedrus_ctx *ctx, reg = VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_TC_OFFSET_DIV2(slice_params->slice_tc_offset_div2) | VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_BETA_OFFSET_DIV2(slice_params->slice_beta_offset_div2) | - VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_POC_BIGEST_IN_RPS_ST(slice_params->num_rps_poc_st_curr_after == 0) | + VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_POC_BIGEST_IN_RPS_ST(decode_params->num_poc_st_curr_after == 0) | VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_CR_QP_OFFSET(slice_params->slice_cr_qp_offset) | VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_CB_QP_OFFSET(slice_params->slice_cb_qp_offset) | VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_QP_DELTA(slice_params->slice_qp_delta); @@ -527,8 +529,8 @@ static void cedrus_h265_setup(struct cedrus_ctx *ctx, cedrus_write(dev, VE_DEC_H265_NEIGHBOR_INFO_ADDR, reg); /* Write decoded picture buffer in pic list. */ - cedrus_h265_frame_info_write_dpb(ctx, slice_params->dpb, - slice_params->num_active_dpb_entries); + cedrus_h265_frame_info_write_dpb(ctx, decode_params->dpb, + decode_params->num_active_dpb_entries); /* Output frame. */ @@ -545,7 +547,7 @@ static void cedrus_h265_setup(struct cedrus_ctx *ctx, /* Reference picture list 0 (for P/B frames). */ if (slice_params->slice_type != V4L2_HEVC_SLICE_TYPE_I) { - cedrus_h265_ref_pic_list_write(dev, slice_params->dpb, + cedrus_h265_ref_pic_list_write(dev, decode_params->dpb, slice_params->ref_idx_l0, slice_params->num_ref_idx_l0_active_minus1 + 1, VE_DEC_H265_SRAM_OFFSET_REF_PIC_LIST0); @@ -564,7 +566,7 @@ static void cedrus_h265_setup(struct cedrus_ctx *ctx, /* Reference picture list 1 (for B frames). */ if (slice_params->slice_type == V4L2_HEVC_SLICE_TYPE_B) { - cedrus_h265_ref_pic_list_write(dev, slice_params->dpb, + cedrus_h265_ref_pic_list_write(dev, decode_params->dpb, slice_params->ref_idx_l1, slice_params->num_ref_idx_l1_active_minus1 + 1, VE_DEC_H265_SRAM_OFFSET_REF_PIC_LIST1); diff --git a/include/media/hevc-ctrls.h b/include/media/hevc-ctrls.h index 245052c15864..e53666a1127f 100644 --- a/include/media/hevc-ctrls.h +++ b/include/media/hevc-ctrls.h @@ -19,6 +19,7 @@ #define V4L2_CID_MPEG_VIDEO_HEVC_SPS (V4L2_CID_CODEC_BASE + 1008) #define V4L2_CID_MPEG_VIDEO_HEVC_PPS (V4L2_CID_CODEC_BASE + 1009) #define V4L2_CID_MPEG_VIDEO_HEVC_SLICE_PARAMS (V4L2_CID_CODEC_BASE + 1010) +#define V4L2_CID_MPEG_VIDEO_HEVC_DECODE_PARAMS (V4L2_CID_CODEC_BASE + 1012) #define V4L2_CID_MPEG_VIDEO_HEVC_DECODE_MODE (V4L2_CID_CODEC_BASE + 1015) #define V4L2_CID_MPEG_VIDEO_HEVC_START_CODE (V4L2_CID_CODEC_BASE + 1016) @@ -26,6 +27,7 @@ #define V4L2_CTRL_TYPE_HEVC_SPS 0x0120 #define V4L2_CTRL_TYPE_HEVC_PPS 0x0121 #define V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS 0x0122 +#define V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS 0x0124 enum v4l2_mpeg_video_hevc_decode_mode { V4L2_MPEG_VIDEO_HEVC_DECODE_MODE_SLICE_BASED, @@ -195,18 +197,10 @@ struct v4l2_ctrl_hevc_slice_params { __u8 pic_struct; /* ISO/IEC 23008-2, ITU-T Rec. H.265: General slice segment header */ - __u8 num_active_dpb_entries; __u8 ref_idx_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; __u8 ref_idx_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __u8 num_rps_poc_st_curr_before; - __u8 num_rps_poc_st_curr_after; - __u8 num_rps_poc_lt_curr; - - __u8 padding; - - /* ISO/IEC 23008-2, ITU-T Rec. H.265: General slice segment header */ - struct v4l2_hevc_dpb_entry dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __u8 padding[5]; /* ISO/IEC 23008-2, ITU-T Rec. H.265: Weighted prediction parameter */ struct v4l2_hevc_pred_weight_table pred_weight_table; @@ -214,4 +208,21 @@ struct v4l2_ctrl_hevc_slice_params { __u64 flags; }; +#define V4L2_HEVC_DECODE_PARAM_FLAG_IRAP_PIC 0x1 +#define V4L2_HEVC_DECODE_PARAM_FLAG_IDR_PIC 0x2 +#define V4L2_HEVC_DECODE_PARAM_FLAG_NO_OUTPUT_OF_PRIOR 0x4 + +struct v4l2_ctrl_hevc_decode_params { + __s32 pic_order_cnt_val; + __u8 num_active_dpb_entries; + struct v4l2_hevc_dpb_entry dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __u8 num_poc_st_curr_before; + __u8 num_poc_st_curr_after; + __u8 num_poc_lt_curr; + __u8 poc_st_curr_before[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __u8 poc_st_curr_after[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __u8 poc_lt_curr[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __u64 flags; +}; + #endif From patchwork Tue May 25 16:12:32 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Benjamin Gaignard X-Patchwork-Id: 447615 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.7 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, UNPARSEABLE_RELAY, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id BEB51C47086 for ; Tue, 25 May 2021 16:12:55 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 98F066141C for ; Tue, 25 May 2021 16:12:55 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233040AbhEYQOY (ORCPT ); Tue, 25 May 2021 12:14:24 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:42740 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232946AbhEYQOX (ORCPT ); Tue, 25 May 2021 12:14:23 -0400 Received: from bhuna.collabora.co.uk (bhuna.collabora.co.uk [IPv6:2a00:1098:0:82:1000:25:2eeb:e3e3]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id EDD2FC061756; Tue, 25 May 2021 09:12:52 -0700 (PDT) Received: from [127.0.0.1] (localhost [127.0.0.1]) (Authenticated sender: benjamin.gaignard) with ESMTPSA id C1E231F4282E From: Benjamin Gaignard To: ezequiel@collabora.com, p.zabel@pengutronix.de, mchehab@kernel.org, shawnguo@kernel.org, s.hauer@pengutronix.de, festevam@gmail.com, gregkh@linuxfoundation.org, mripard@kernel.org, paul.kocialkowski@bootlin.com, wens@csie.org, jernej.skrabec@siol.net, emil.l.velikov@gmail.com Cc: kernel@pengutronix.de, linux-imx@nxp.com, linux-media@vger.kernel.org, linux-rockchip@lists.infradead.org, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, Benjamin Gaignard Subject: [PATCH v11 3/9] media: hantro: change hantro_codec_ops run prototype to return errors Date: Tue, 25 May 2021 18:12:32 +0200 Message-Id: <20210525161238.1191168-4-benjamin.gaignard@collabora.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20210525161238.1191168-1-benjamin.gaignard@collabora.com> References: <20210525161238.1191168-1-benjamin.gaignard@collabora.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-media@vger.kernel.org Change hantro_codec_ops run prototype from 'void' to 'int'. This allows the driver to cancel the job if an error occurs while configuring the hardware. Signed-off-by: Benjamin Gaignard Reviewed-by: Ezequiel Garcia --- drivers/staging/media/hantro/hantro_drv.c | 4 +++- .../staging/media/hantro/hantro_g1_h264_dec.c | 10 +++++++--- .../media/hantro/hantro_g1_mpeg2_dec.c | 4 +++- .../staging/media/hantro/hantro_g1_vp8_dec.c | 6 ++++-- .../staging/media/hantro/hantro_h1_jpeg_enc.c | 4 +++- drivers/staging/media/hantro/hantro_hw.h | 19 ++++++++++--------- .../media/hantro/rk3399_vpu_hw_jpeg_enc.c | 4 +++- .../media/hantro/rk3399_vpu_hw_mpeg2_dec.c | 4 +++- .../media/hantro/rk3399_vpu_hw_vp8_dec.c | 6 ++++-- 9 files changed, 40 insertions(+), 21 deletions(-) diff --git a/drivers/staging/media/hantro/hantro_drv.c b/drivers/staging/media/hantro/hantro_drv.c index 2f6b01c7a6a0..1f28cd2607d2 100644 --- a/drivers/staging/media/hantro/hantro_drv.c +++ b/drivers/staging/media/hantro/hantro_drv.c @@ -170,7 +170,9 @@ static void device_run(void *priv) v4l2_m2m_buf_copy_metadata(src, dst, true); - ctx->codec_ops->run(ctx); + if (ctx->codec_ops->run(ctx)) + goto err_cancel_job; + return; err_cancel_job: diff --git a/drivers/staging/media/hantro/hantro_g1_h264_dec.c b/drivers/staging/media/hantro/hantro_g1_h264_dec.c index 845bef73d218..5c792b7bcb79 100644 --- a/drivers/staging/media/hantro/hantro_g1_h264_dec.c +++ b/drivers/staging/media/hantro/hantro_g1_h264_dec.c @@ -273,13 +273,15 @@ static void set_buffers(struct hantro_ctx *ctx) vdpu_write_relaxed(vpu, ctx->h264_dec.priv.dma, G1_REG_ADDR_QTABLE); } -void hantro_g1_h264_dec_run(struct hantro_ctx *ctx) +int hantro_g1_h264_dec_run(struct hantro_ctx *ctx) { struct hantro_dev *vpu = ctx->dev; + int ret; /* Prepare the H264 decoder context. */ - if (hantro_h264_dec_prepare_run(ctx)) - return; + ret = hantro_h264_dec_prepare_run(ctx); + if (ret) + return ret; /* Configure hardware registers. */ set_params(ctx); @@ -301,4 +303,6 @@ void hantro_g1_h264_dec_run(struct hantro_ctx *ctx) G1_REG_CONFIG_DEC_CLK_GATE_E, G1_REG_CONFIG); vdpu_write(vpu, G1_REG_INTERRUPT_DEC_E, G1_REG_INTERRUPT); + + return 0; } diff --git a/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c b/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c index 6ee1a19d189b..9aea331e1a3c 100644 --- a/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c +++ b/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c @@ -145,7 +145,7 @@ hantro_g1_mpeg2_dec_set_buffers(struct hantro_dev *vpu, struct hantro_ctx *ctx, vdpu_write_relaxed(vpu, backward_addr, G1_REG_REFER3_BASE); } -void hantro_g1_mpeg2_dec_run(struct hantro_ctx *ctx) +int hantro_g1_mpeg2_dec_run(struct hantro_ctx *ctx) { struct hantro_dev *vpu = ctx->dev; struct vb2_v4l2_buffer *src_buf, *dst_buf; @@ -235,4 +235,6 @@ void hantro_g1_mpeg2_dec_run(struct hantro_ctx *ctx) hantro_end_prepare_run(ctx); vdpu_write(vpu, G1_REG_INTERRUPT_DEC_E, G1_REG_INTERRUPT); + + return 0; } diff --git a/drivers/staging/media/hantro/hantro_g1_vp8_dec.c b/drivers/staging/media/hantro/hantro_g1_vp8_dec.c index 57002ba70176..96622a7f8279 100644 --- a/drivers/staging/media/hantro/hantro_g1_vp8_dec.c +++ b/drivers/staging/media/hantro/hantro_g1_vp8_dec.c @@ -425,7 +425,7 @@ static void cfg_buffers(struct hantro_ctx *ctx, vdpu_write_relaxed(vpu, dst_dma, G1_REG_ADDR_DST); } -void hantro_g1_vp8_dec_run(struct hantro_ctx *ctx) +int hantro_g1_vp8_dec_run(struct hantro_ctx *ctx) { const struct v4l2_ctrl_vp8_frame *hdr; struct hantro_dev *vpu = ctx->dev; @@ -438,7 +438,7 @@ void hantro_g1_vp8_dec_run(struct hantro_ctx *ctx) hdr = hantro_get_ctrl(ctx, V4L2_CID_STATELESS_VP8_FRAME); if (WARN_ON(!hdr)) - return; + return -EINVAL; /* Reset segment_map buffer in keyframe */ if (V4L2_VP8_FRAME_IS_KEY_FRAME(hdr) && ctx->vp8_dec.segment_map.cpu) @@ -498,4 +498,6 @@ void hantro_g1_vp8_dec_run(struct hantro_ctx *ctx) hantro_end_prepare_run(ctx); vdpu_write(vpu, G1_REG_INTERRUPT_DEC_E, G1_REG_INTERRUPT); + + return 0; } diff --git a/drivers/staging/media/hantro/hantro_h1_jpeg_enc.c b/drivers/staging/media/hantro/hantro_h1_jpeg_enc.c index b88dc4ed06db..56cf261a8e95 100644 --- a/drivers/staging/media/hantro/hantro_h1_jpeg_enc.c +++ b/drivers/staging/media/hantro/hantro_h1_jpeg_enc.c @@ -88,7 +88,7 @@ hantro_h1_jpeg_enc_set_qtable(struct hantro_dev *vpu, } } -void hantro_h1_jpeg_enc_run(struct hantro_ctx *ctx) +int hantro_h1_jpeg_enc_run(struct hantro_ctx *ctx) { struct hantro_dev *vpu = ctx->dev; struct vb2_v4l2_buffer *src_buf, *dst_buf; @@ -136,6 +136,8 @@ void hantro_h1_jpeg_enc_run(struct hantro_ctx *ctx) hantro_end_prepare_run(ctx); vepu_write(vpu, reg, H1_REG_ENC_CTRL); + + return 0; } void hantro_jpeg_enc_done(struct hantro_ctx *ctx) diff --git a/drivers/staging/media/hantro/hantro_hw.h b/drivers/staging/media/hantro/hantro_hw.h index 3d8b53567f16..4b73c8011b25 100644 --- a/drivers/staging/media/hantro/hantro_hw.h +++ b/drivers/staging/media/hantro/hantro_hw.h @@ -133,14 +133,15 @@ struct hantro_postproc_ctx { * 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. + * should be programmed and started. Returns zero if OK, a + * negative value in error cases. * @done: Read back processing results and additional data from hardware. * @reset: Reset the hardware in case of a timeout. */ struct hantro_codec_ops { int (*init)(struct hantro_ctx *ctx); void (*exit)(struct hantro_ctx *ctx); - void (*run)(struct hantro_ctx *ctx); + int (*run)(struct hantro_ctx *ctx); void (*done)(struct hantro_ctx *ctx); void (*reset)(struct hantro_ctx *ctx); }; @@ -180,8 +181,8 @@ void hantro_end_prepare_run(struct hantro_ctx *ctx); irqreturn_t hantro_g1_irq(int irq, void *dev_id); void hantro_g1_reset(struct hantro_ctx *ctx); -void hantro_h1_jpeg_enc_run(struct hantro_ctx *ctx); -void rk3399_vpu_jpeg_enc_run(struct hantro_ctx *ctx); +int hantro_h1_jpeg_enc_run(struct hantro_ctx *ctx); +int rk3399_vpu_jpeg_enc_run(struct hantro_ctx *ctx); int hantro_jpeg_enc_init(struct hantro_ctx *ctx); void hantro_jpeg_enc_exit(struct hantro_ctx *ctx); void hantro_jpeg_enc_done(struct hantro_ctx *ctx); @@ -189,7 +190,7 @@ void hantro_jpeg_enc_done(struct hantro_ctx *ctx); dma_addr_t hantro_h264_get_ref_buf(struct hantro_ctx *ctx, unsigned int dpb_idx); int hantro_h264_dec_prepare_run(struct hantro_ctx *ctx); -void hantro_g1_h264_dec_run(struct hantro_ctx *ctx); +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); @@ -220,15 +221,15 @@ hantro_h264_mv_size(unsigned int width, unsigned int height) return 64 * MB_WIDTH(width) * MB_WIDTH(height) + 32; } -void hantro_g1_mpeg2_dec_run(struct hantro_ctx *ctx); -void rk3399_vpu_mpeg2_dec_run(struct hantro_ctx *ctx); +int hantro_g1_mpeg2_dec_run(struct hantro_ctx *ctx); +int rk3399_vpu_mpeg2_dec_run(struct hantro_ctx *ctx); void hantro_mpeg2_dec_copy_qtable(u8 *qtable, const struct v4l2_ctrl_mpeg2_quantisation *ctrl); int hantro_mpeg2_dec_init(struct hantro_ctx *ctx); void hantro_mpeg2_dec_exit(struct hantro_ctx *ctx); -void hantro_g1_vp8_dec_run(struct hantro_ctx *ctx); -void rk3399_vpu_vp8_dec_run(struct hantro_ctx *ctx); +int hantro_g1_vp8_dec_run(struct hantro_ctx *ctx); +int rk3399_vpu_vp8_dec_run(struct hantro_ctx *ctx); int hantro_vp8_dec_init(struct hantro_ctx *ctx); void hantro_vp8_dec_exit(struct hantro_ctx *ctx); void hantro_vp8_prob_update(struct hantro_ctx *ctx, diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw_jpeg_enc.c b/drivers/staging/media/hantro/rk3399_vpu_hw_jpeg_enc.c index 3498e6124acd..3a27ebef4f38 100644 --- a/drivers/staging/media/hantro/rk3399_vpu_hw_jpeg_enc.c +++ b/drivers/staging/media/hantro/rk3399_vpu_hw_jpeg_enc.c @@ -118,7 +118,7 @@ rk3399_vpu_jpeg_enc_set_qtable(struct hantro_dev *vpu, } } -void rk3399_vpu_jpeg_enc_run(struct hantro_ctx *ctx) +int rk3399_vpu_jpeg_enc_run(struct hantro_ctx *ctx) { struct hantro_dev *vpu = ctx->dev; struct vb2_v4l2_buffer *src_buf, *dst_buf; @@ -168,4 +168,6 @@ void rk3399_vpu_jpeg_enc_run(struct hantro_ctx *ctx) /* Kick the watchdog and start encoding */ hantro_end_prepare_run(ctx); vepu_write(vpu, reg, VEPU_REG_ENCODE_START); + + return 0; } diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c b/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c index 2527dce7eb18..683982c24c2d 100644 --- a/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c +++ b/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c @@ -148,7 +148,7 @@ rk3399_vpu_mpeg2_dec_set_buffers(struct hantro_dev *vpu, vdpu_write_relaxed(vpu, backward_addr, VDPU_REG_REFER3_BASE); } -void rk3399_vpu_mpeg2_dec_run(struct hantro_ctx *ctx) +int rk3399_vpu_mpeg2_dec_run(struct hantro_ctx *ctx) { struct hantro_dev *vpu = ctx->dev; struct vb2_v4l2_buffer *src_buf, *dst_buf; @@ -244,4 +244,6 @@ void rk3399_vpu_mpeg2_dec_run(struct hantro_ctx *ctx) reg = vdpu_read(vpu, VDPU_SWREG(57)) | VDPU_REG_DEC_E(1); vdpu_write(vpu, reg, VDPU_SWREG(57)); + + return 0; } diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw_vp8_dec.c b/drivers/staging/media/hantro/rk3399_vpu_hw_vp8_dec.c index 8661a3cc1e6b..e5d20fe5b007 100644 --- a/drivers/staging/media/hantro/rk3399_vpu_hw_vp8_dec.c +++ b/drivers/staging/media/hantro/rk3399_vpu_hw_vp8_dec.c @@ -503,7 +503,7 @@ static void cfg_buffers(struct hantro_ctx *ctx, vdpu_write_relaxed(vpu, dst_dma, VDPU_REG_ADDR_DST); } -void rk3399_vpu_vp8_dec_run(struct hantro_ctx *ctx) +int rk3399_vpu_vp8_dec_run(struct hantro_ctx *ctx) { const struct v4l2_ctrl_vp8_frame *hdr; struct hantro_dev *vpu = ctx->dev; @@ -516,7 +516,7 @@ void rk3399_vpu_vp8_dec_run(struct hantro_ctx *ctx) hdr = hantro_get_ctrl(ctx, V4L2_CID_STATELESS_VP8_FRAME); if (WARN_ON(!hdr)) - return; + return -EINVAL; /* Reset segment_map buffer in keyframe */ if (V4L2_VP8_FRAME_IS_KEY_FRAME(hdr) && ctx->vp8_dec.segment_map.cpu) @@ -589,4 +589,6 @@ void rk3399_vpu_vp8_dec_run(struct hantro_ctx *ctx) hantro_end_prepare_run(ctx); hantro_reg_write(vpu, &vp8_dec_start_dec, 1); + + return 0; } From patchwork Tue May 25 16:12:35 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Benjamin Gaignard X-Patchwork-Id: 447614 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.7 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, UNPARSEABLE_RELAY, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 92D84C2B9F8 for ; Tue, 25 May 2021 16:13:01 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 6F487611C2 for ; Tue, 25 May 2021 16:13:01 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233243AbhEYQO2 (ORCPT ); Tue, 25 May 2021 12:14:28 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:42764 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233166AbhEYQO0 (ORCPT ); Tue, 25 May 2021 12:14:26 -0400 Received: from bhuna.collabora.co.uk (bhuna.collabora.co.uk [IPv6:2a00:1098:0:82:1000:25:2eeb:e3e3]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 34E0BC06138A; Tue, 25 May 2021 09:12:56 -0700 (PDT) Received: from [127.0.0.1] (localhost [127.0.0.1]) (Authenticated sender: benjamin.gaignard) with ESMTPSA id 2C18E1F4282D From: Benjamin Gaignard To: ezequiel@collabora.com, p.zabel@pengutronix.de, mchehab@kernel.org, shawnguo@kernel.org, s.hauer@pengutronix.de, festevam@gmail.com, gregkh@linuxfoundation.org, mripard@kernel.org, paul.kocialkowski@bootlin.com, wens@csie.org, jernej.skrabec@siol.net, emil.l.velikov@gmail.com Cc: kernel@pengutronix.de, linux-imx@nxp.com, linux-media@vger.kernel.org, linux-rockchip@lists.infradead.org, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, Benjamin Gaignard Subject: [PATCH v11 6/9] media: uapi: Add a control for HANTRO driver Date: Tue, 25 May 2021 18:12:35 +0200 Message-Id: <20210525161238.1191168-7-benjamin.gaignard@collabora.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20210525161238.1191168-1-benjamin.gaignard@collabora.com> References: <20210525161238.1191168-1-benjamin.gaignard@collabora.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-media@vger.kernel.org The HEVC HANTRO driver needs to know the number of bits to skip at the beginning of the slice header. That is a hardware specific requirement so create a dedicated control for this purpose. Signed-off-by: Benjamin Gaignard --- .../userspace-api/media/drivers/hantro.rst | 19 +++++++++++++++++++ .../userspace-api/media/drivers/index.rst | 1 + include/media/hevc-ctrls.h | 13 +++++++++++++ 3 files changed, 33 insertions(+) create mode 100644 Documentation/userspace-api/media/drivers/hantro.rst diff --git a/Documentation/userspace-api/media/drivers/hantro.rst b/Documentation/userspace-api/media/drivers/hantro.rst new file mode 100644 index 000000000000..cd9754b4e005 --- /dev/null +++ b/Documentation/userspace-api/media/drivers/hantro.rst @@ -0,0 +1,19 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Hantro video decoder driver +=========================== + +The Hantro video decoder driver implements the following driver-specific controls: + +``V4L2_CID_HANTRO_HEVC_SLICE_HEADER_SKIP (integer)`` + Specifies to Hantro HEVC video decoder driver the number of data (in bits) to + skip in the slice segment header. + If non-IDR, the bits to be skipped go from syntax element "pic_output_flag" + to before syntax element "slice_temporal_mvp_enabled_flag". + If IDR, the skipped bits are just "pic_output_flag" + (separate_colour_plane_flag is not supported). + +.. note:: + + This control is not yet part of the public kernel API and + it is expected to change. diff --git a/Documentation/userspace-api/media/drivers/index.rst b/Documentation/userspace-api/media/drivers/index.rst index 1a9038f5f9fa..12e3c512d718 100644 --- a/Documentation/userspace-api/media/drivers/index.rst +++ b/Documentation/userspace-api/media/drivers/index.rst @@ -33,6 +33,7 @@ For more details see the file COPYING in the source distribution of Linux. ccs cx2341x-uapi + hantro imx-uapi max2175 meye-uapi diff --git a/include/media/hevc-ctrls.h b/include/media/hevc-ctrls.h index e53666a1127f..dc964ff7cd29 100644 --- a/include/media/hevc-ctrls.h +++ b/include/media/hevc-ctrls.h @@ -225,4 +225,17 @@ struct v4l2_ctrl_hevc_decode_params { __u64 flags; }; +/* MPEG-class control IDs specific to the Hantro driver as defined by V4L2 */ +#define V4L2_CID_CODEC_HANTRO_BASE (V4L2_CTRL_CLASS_CODEC | 0x1200) +/* + * V4L2_CID_HANTRO_HEVC_SLICE_HEADER_SKIP - + * the number of data (in bits) to skip in the + * slice segment header. + * If non-IDR, the bits to be skipped go from syntax element "pic_output_flag" + * to before syntax element "slice_temporal_mvp_enabled_flag". + * If IDR, the skipped bits are just "pic_output_flag" + * (separate_colour_plane_flag is not supported). + */ +#define V4L2_CID_HANTRO_HEVC_SLICE_HEADER_SKIP (V4L2_CID_CODEC_HANTRO_BASE + 0) + #endif From patchwork Tue May 25 16:12:37 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Benjamin Gaignard X-Patchwork-Id: 447613 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.7 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, UNPARSEABLE_RELAY, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 73F8BC2B9F8 for ; Tue, 25 May 2021 16:13:04 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 541C661413 for ; Tue, 25 May 2021 16:13:04 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233329AbhEYQOc (ORCPT ); Tue, 25 May 2021 12:14:32 -0400 Received: from bhuna.collabora.co.uk ([46.235.227.227]:49074 "EHLO bhuna.collabora.co.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233215AbhEYQO3 (ORCPT ); Tue, 25 May 2021 12:14:29 -0400 Received: from [127.0.0.1] (localhost [127.0.0.1]) (Authenticated sender: benjamin.gaignard) with ESMTPSA id 5FB681F42836 From: Benjamin Gaignard To: ezequiel@collabora.com, p.zabel@pengutronix.de, mchehab@kernel.org, shawnguo@kernel.org, s.hauer@pengutronix.de, festevam@gmail.com, gregkh@linuxfoundation.org, mripard@kernel.org, paul.kocialkowski@bootlin.com, wens@csie.org, jernej.skrabec@siol.net, emil.l.velikov@gmail.com Cc: kernel@pengutronix.de, linux-imx@nxp.com, linux-media@vger.kernel.org, linux-rockchip@lists.infradead.org, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, Benjamin Gaignard , Adrian Ratiu Subject: [PATCH v11 8/9] media: hantro: Introduce G2/HEVC decoder Date: Tue, 25 May 2021 18:12:37 +0200 Message-Id: <20210525161238.1191168-9-benjamin.gaignard@collabora.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20210525161238.1191168-1-benjamin.gaignard@collabora.com> References: <20210525161238.1191168-1-benjamin.gaignard@collabora.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-media@vger.kernel.org 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 Co-developed-by: Adrian Ratiu Signed-off-by: Adrian Ratiu Co-developed-by: Ezequiel Garcia Signed-off-by: Ezequiel Garcia --- version 11: - Fix some of Hans's remarks - Do not change array to static since they are already const - Fix pic_width_in_cbs and pic_height_in_cbs masks fields drivers/staging/media/hantro/Makefile | 2 + drivers/staging/media/hantro/hantro.h | 2 + drivers/staging/media/hantro/hantro_drv.c | 36 ++ .../staging/media/hantro/hantro_g2_hevc_dec.c | 588 ++++++++++++++++++ drivers/staging/media/hantro/hantro_g2_regs.h | 198 ++++++ drivers/staging/media/hantro/hantro_hevc.c | 327 ++++++++++ drivers/staging/media/hantro/hantro_hw.h | 49 ++ 7 files changed, 1202 insertions(+) create mode 100644 drivers/staging/media/hantro/hantro_g2_hevc_dec.c create mode 100644 drivers/staging/media/hantro/hantro_g2_regs.h create mode 100644 drivers/staging/media/hantro/hantro_hevc.c diff --git a/drivers/staging/media/hantro/Makefile b/drivers/staging/media/hantro/Makefile index f4b99901eeee..23bfc423b23c 100644 --- a/drivers/staging/media/hantro/Makefile +++ b/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 diff --git a/drivers/staging/media/hantro/hantro.h b/drivers/staging/media/hantro/hantro.h index e50d39b51902..a70c386de6f1 100644 --- a/drivers/staging/media/hantro/hantro.h +++ b/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; }; }; diff --git a/drivers/staging/media/hantro/hantro_drv.c b/drivers/staging/media/hantro/hantro_drv.c index 8bb0ca21150e..ae8a0037706f 100644 --- a/drivers/staging/media/hantro/hantro_drv.c +++ b/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, + }, }, }; diff --git a/drivers/staging/media/hantro/hantro_g2_hevc_dec.c b/drivers/staging/media/hantro/hantro_g2_hevc_dec.c new file mode 100644 index 000000000000..dffd70adbc5a --- /dev/null +++ b/drivers/staging/media/hantro/hantro_g2_hevc_dec.c @@ -0,0 +1,588 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hantro VPU HEVC codec driver + * + * Copyright (C) 2020 Safran Passenger Innovations LLC + */ + +#include "hantro_hw.h" +#include "hantro_g2_regs.h" + +#define HEVC_DEC_MODE 0xC + +#define BUS_WIDTH_32 0 +#define BUS_WIDTH_64 1 +#define BUS_WIDTH_128 2 +#define BUS_WIDTH_256 3 + +static inline void hantro_write_addr(struct hantro_dev *vpu, + unsigned long offset, + dma_addr_t addr) +{ + vdpu_write(vpu, addr & 0xffffffff, offset); + vdpu_write(vpu, (addr >> 32) & 0xffffffff, offset + 4); +} + +static void prepare_tile_info_buffer(struct hantro_ctx *ctx) +{ + struct hantro_dev *vpu = ctx->dev; + 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; + u16 *p = (u16 *)((u8 *)ctx->hevc_dec.tile_sizes.cpu); + unsigned int num_tile_rows = pps->num_tile_rows_minus1 + 1; + unsigned int num_tile_cols = pps->num_tile_columns_minus1 + 1; + unsigned int pic_width_in_ctbs, pic_height_in_ctbs; + unsigned int max_log2_ctb_size, ctb_size; + bool tiles_enabled, uniform_spacing; + u32 no_chroma = 0; + + tiles_enabled = !!(pps->flags & V4L2_HEVC_PPS_FLAG_TILES_ENABLED); + uniform_spacing = !!(pps->flags & V4L2_HEVC_PPS_FLAG_UNIFORM_SPACING); + + hantro_reg_write(vpu, hevc_tile_e, tiles_enabled); + + max_log2_ctb_size = sps->log2_min_luma_coding_block_size_minus3 + 3 + + sps->log2_diff_max_min_luma_coding_block_size; + pic_width_in_ctbs = (sps->pic_width_in_luma_samples + + (1 << max_log2_ctb_size) - 1) >> max_log2_ctb_size; + pic_height_in_ctbs = (sps->pic_height_in_luma_samples + (1 << max_log2_ctb_size) - 1) + >> max_log2_ctb_size; + ctb_size = 1 << max_log2_ctb_size; + + vpu_debug(1, "Preparing tile sizes buffer for %dx%d CTBs (CTB size %d)\n", + pic_width_in_ctbs, pic_height_in_ctbs, ctb_size); + + if (tiles_enabled) { + unsigned int i, j, h; + + vpu_debug(1, "Tiles enabled! %dx%d\n", num_tile_cols, num_tile_rows); + + hantro_reg_write(vpu, hevc_num_tile_rows, num_tile_rows); + hantro_reg_write(vpu, hevc_num_tile_cols, num_tile_cols); + + /* write width + height for each tile in pic */ + if (!uniform_spacing) { + u32 tmp_w = 0, tmp_h = 0; + + for (i = 0; i < num_tile_rows; i++) { + if (i == num_tile_rows - 1) + h = pic_height_in_ctbs - tmp_h; + else + h = pps->row_height_minus1[i] + 1; + tmp_h += h; + if (i == 0 && h == 1 && ctb_size == 16) + no_chroma = 1; + for (j = 0, tmp_w = 0; j < num_tile_cols - 1; j++) { + tmp_w += pps->column_width_minus1[j] + 1; + *p++ = pps->column_width_minus1[j + 1]; + *p++ = h; + if (i == 0 && h == 1 && ctb_size == 16) + no_chroma = 1; + } + /* last column */ + *p++ = pic_width_in_ctbs - tmp_w; + *p++ = h; + } + } else { /* uniform spacing */ + u32 tmp, prev_h, prev_w; + + for (i = 0, prev_h = 0; i < num_tile_rows; i++) { + tmp = (i + 1) * pic_height_in_ctbs / num_tile_rows; + h = tmp - prev_h; + prev_h = tmp; + if (i == 0 && h == 1 && ctb_size == 16) + no_chroma = 1; + for (j = 0, prev_w = 0; j < num_tile_cols; j++) { + tmp = (j + 1) * pic_width_in_ctbs / num_tile_cols; + *p++ = tmp - prev_w; + *p++ = h; + if (j == 0 && + (pps->column_width_minus1[0] + 1) == 1 && + ctb_size == 16) + no_chroma = 1; + prev_w = tmp; + } + } + } + } else { + hantro_reg_write(vpu, hevc_num_tile_rows, 1); + hantro_reg_write(vpu, hevc_num_tile_cols, 1); + + /* There's one tile, with dimensions equal to pic size. */ + p[0] = pic_width_in_ctbs; + p[1] = pic_height_in_ctbs; + } + + if (no_chroma) + vpu_debug(1, "%s: no chroma!\n", __func__); +} + +static void set_params(struct hantro_ctx *ctx) +{ + const struct hantro_hevc_dec_ctrls *ctrls = &ctx->hevc_dec.ctrls; + const struct v4l2_ctrl_hevc_sps *sps = ctrls->sps; + const struct v4l2_ctrl_hevc_pps *pps = ctrls->pps; + const struct v4l2_ctrl_hevc_decode_params *decode_params = ctrls->decode_params; + struct hantro_dev *vpu = ctx->dev; + u32 min_log2_cb_size, max_log2_ctb_size, min_cb_size, max_ctb_size; + u32 pic_width_in_min_cbs, pic_height_in_min_cbs; + u32 pic_width_aligned, pic_height_aligned; + u32 partial_ctb_x, partial_ctb_y; + + hantro_reg_write(vpu, hevc_bit_depth_y_minus8, sps->bit_depth_luma_minus8); + hantro_reg_write(vpu, hevc_bit_depth_c_minus8, sps->bit_depth_chroma_minus8); + + hantro_reg_write(vpu, hevc_output_8_bits, 0); + + hantro_reg_write(vpu, hevc_hdr_skip_length, ctrls->hevc_hdr_skip_length); + + min_log2_cb_size = sps->log2_min_luma_coding_block_size_minus3 + 3; + max_log2_ctb_size = min_log2_cb_size + sps->log2_diff_max_min_luma_coding_block_size; + + hantro_reg_write(vpu, hevc_min_cb_size, min_log2_cb_size); + hantro_reg_write(vpu, hevc_max_cb_size, max_log2_ctb_size); + + min_cb_size = 1 << min_log2_cb_size; + max_ctb_size = 1 << max_log2_ctb_size; + + pic_width_in_min_cbs = sps->pic_width_in_luma_samples / min_cb_size; + pic_height_in_min_cbs = sps->pic_height_in_luma_samples / min_cb_size; + pic_width_aligned = ALIGN(sps->pic_width_in_luma_samples, max_ctb_size); + pic_height_aligned = ALIGN(sps->pic_height_in_luma_samples, max_ctb_size); + + partial_ctb_x = !!(sps->pic_width_in_luma_samples != pic_width_aligned); + partial_ctb_y = !!(sps->pic_height_in_luma_samples != pic_height_aligned); + + hantro_reg_write(vpu, hevc_partial_ctb_x, partial_ctb_x); + hantro_reg_write(vpu, hevc_partial_ctb_y, partial_ctb_y); + + hantro_reg_write(vpu, hevc_pic_width_in_cbs, pic_width_in_min_cbs); + hantro_reg_write(vpu, hevc_pic_height_in_cbs, pic_height_in_min_cbs); + + hantro_reg_write(vpu, hevc_pic_width_4x4, + (pic_width_in_min_cbs * min_cb_size) / 4); + hantro_reg_write(vpu, hevc_pic_height_4x4, + (pic_height_in_min_cbs * min_cb_size) / 4); + + hantro_reg_write(vpu, hevc_max_inter_hierdepth, + sps->max_transform_hierarchy_depth_inter); + hantro_reg_write(vpu, hevc_max_intra_hierdepth, + sps->max_transform_hierarchy_depth_intra); + hantro_reg_write(vpu, hevc_min_trb_size, + sps->log2_min_luma_transform_block_size_minus2 + 2); + hantro_reg_write(vpu, hevc_max_trb_size, + sps->log2_min_luma_transform_block_size_minus2 + 2 + + sps->log2_diff_max_min_luma_transform_block_size); + + hantro_reg_write(vpu, hevc_tempor_mvp_e, + !!(sps->flags & V4L2_HEVC_SPS_FLAG_SPS_TEMPORAL_MVP_ENABLED) && + !(decode_params->flags & V4L2_HEVC_DECODE_PARAM_FLAG_IDR_PIC)); + hantro_reg_write(vpu, hevc_strong_smooth_e, + !!(sps->flags & V4L2_HEVC_SPS_FLAG_STRONG_INTRA_SMOOTHING_ENABLED)); + hantro_reg_write(vpu, hevc_asym_pred_e, + !!(sps->flags & V4L2_HEVC_SPS_FLAG_AMP_ENABLED)); + hantro_reg_write(vpu, hevc_sao_e, + !!(sps->flags & V4L2_HEVC_SPS_FLAG_SAMPLE_ADAPTIVE_OFFSET)); + hantro_reg_write(vpu, hevc_sign_data_hide, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_SIGN_DATA_HIDING_ENABLED)); + + if (pps->flags & V4L2_HEVC_PPS_FLAG_CU_QP_DELTA_ENABLED) { + hantro_reg_write(vpu, hevc_cu_qpd_e, 1); + hantro_reg_write(vpu, hevc_max_cu_qpd_depth, pps->diff_cu_qp_delta_depth); + } else { + hantro_reg_write(vpu, hevc_cu_qpd_e, 0); + hantro_reg_write(vpu, hevc_max_cu_qpd_depth, 0); + } + + if (pps->flags & V4L2_HEVC_PPS_FLAG_PPS_SLICE_CHROMA_QP_OFFSETS_PRESENT) { + hantro_reg_write(vpu, hevc_cb_qp_offset, pps->pps_cb_qp_offset); + hantro_reg_write(vpu, hevc_cr_qp_offset, pps->pps_cr_qp_offset); + } else { + hantro_reg_write(vpu, hevc_cb_qp_offset, 0); + hantro_reg_write(vpu, hevc_cr_qp_offset, 0); + } + + hantro_reg_write(vpu, hevc_filt_offset_beta, pps->pps_beta_offset_div2); + hantro_reg_write(vpu, hevc_filt_offset_tc, pps->pps_tc_offset_div2); + hantro_reg_write(vpu, hevc_slice_hdr_ext_e, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_SLICE_SEGMENT_HEADER_EXTENSION_PRESENT)); + hantro_reg_write(vpu, hevc_slice_hdr_ext_bits, pps->num_extra_slice_header_bits); + hantro_reg_write(vpu, hevc_slice_chqp_present, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_PPS_SLICE_CHROMA_QP_OFFSETS_PRESENT)); + hantro_reg_write(vpu, hevc_weight_bipr_idc, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_WEIGHTED_BIPRED)); + hantro_reg_write(vpu, hevc_transq_bypass, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_TRANSQUANT_BYPASS_ENABLED)); + hantro_reg_write(vpu, hevc_list_mod_e, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_LISTS_MODIFICATION_PRESENT)); + hantro_reg_write(vpu, hevc_entropy_sync_e, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_ENTROPY_CODING_SYNC_ENABLED)); + hantro_reg_write(vpu, hevc_cabac_init_present, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_CABAC_INIT_PRESENT)); + hantro_reg_write(vpu, hevc_idr_pic_e, + !!(decode_params->flags & V4L2_HEVC_DECODE_PARAM_FLAG_IRAP_PIC)); + hantro_reg_write(vpu, hevc_parallel_merge, + pps->log2_parallel_merge_level_minus2 + 2); + hantro_reg_write(vpu, hevc_pcm_filt_d, + !!(sps->flags & V4L2_HEVC_SPS_FLAG_PCM_LOOP_FILTER_DISABLED)); + hantro_reg_write(vpu, hevc_pcm_e, + !!(sps->flags & V4L2_HEVC_SPS_FLAG_PCM_ENABLED)); + if (sps->flags & V4L2_HEVC_SPS_FLAG_PCM_ENABLED) { + hantro_reg_write(vpu, hevc_max_pcm_size, + sps->log2_diff_max_min_pcm_luma_coding_block_size + + sps->log2_min_pcm_luma_coding_block_size_minus3 + 3); + hantro_reg_write(vpu, hevc_min_pcm_size, + sps->log2_min_pcm_luma_coding_block_size_minus3 + 3); + hantro_reg_write(vpu, hevc_bit_depth_pcm_y, + sps->pcm_sample_bit_depth_luma_minus1 + 1); + hantro_reg_write(vpu, hevc_bit_depth_pcm_c, + sps->pcm_sample_bit_depth_chroma_minus1 + 1); + } else { + hantro_reg_write(vpu, hevc_max_pcm_size, 0); + hantro_reg_write(vpu, hevc_min_pcm_size, 0); + hantro_reg_write(vpu, hevc_bit_depth_pcm_y, 0); + hantro_reg_write(vpu, hevc_bit_depth_pcm_c, 0); + } + + hantro_reg_write(vpu, hevc_start_code_e, 1); + hantro_reg_write(vpu, hevc_init_qp, pps->init_qp_minus26 + 26); + hantro_reg_write(vpu, hevc_weight_pred_e, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_WEIGHTED_PRED)); + hantro_reg_write(vpu, hevc_cabac_init_present, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_CABAC_INIT_PRESENT)); + hantro_reg_write(vpu, hevc_const_intra_e, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_CONSTRAINED_INTRA_PRED)); + hantro_reg_write(vpu, hevc_transform_skip, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_TRANSFORM_SKIP_ENABLED)); + hantro_reg_write(vpu, hevc_out_filtering_dis, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_PPS_DISABLE_DEBLOCKING_FILTER)); + hantro_reg_write(vpu, hevc_filt_ctrl_pres, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_CONTROL_PRESENT)); + hantro_reg_write(vpu, hevc_dependent_slice, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_DEPENDENT_SLICE_SEGMENT_ENABLED)); + hantro_reg_write(vpu, hevc_filter_override, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_OVERRIDE_ENABLED)); + hantro_reg_write(vpu, hevc_refidx0_active, + pps->num_ref_idx_l0_default_active_minus1 + 1); + hantro_reg_write(vpu, hevc_refidx1_active, + pps->num_ref_idx_l1_default_active_minus1 + 1); + hantro_reg_write(vpu, hevc_apf_threshold, 8); +} + +static int find_ref_pic_index(const struct v4l2_hevc_dpb_entry *dpb, int pic_order_cnt) +{ + int i; + + for (i = 0; i < V4L2_HEVC_DPB_ENTRIES_NUM_MAX; i++) { + if (dpb[i].pic_order_cnt[0] == pic_order_cnt) + return i; + } + + return 0x0; +} + +static void set_ref_pic_list(struct hantro_ctx *ctx) +{ + const struct hantro_hevc_dec_ctrls *ctrls = &ctx->hevc_dec.ctrls; + struct hantro_dev *vpu = ctx->dev; + const struct v4l2_ctrl_hevc_decode_params *decode_params = ctrls->decode_params; + const struct v4l2_hevc_dpb_entry *dpb = decode_params->dpb; + u32 list0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX] = {}; + u32 list1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX] = {}; + const struct hantro_reg *ref_pic_regs0[] = { + hevc_rlist_f0, + hevc_rlist_f1, + hevc_rlist_f2, + hevc_rlist_f3, + hevc_rlist_f4, + hevc_rlist_f5, + hevc_rlist_f6, + hevc_rlist_f7, + hevc_rlist_f8, + hevc_rlist_f9, + hevc_rlist_f10, + hevc_rlist_f11, + hevc_rlist_f12, + hevc_rlist_f13, + hevc_rlist_f14, + hevc_rlist_f15, + }; + const struct hantro_reg *ref_pic_regs1[] = { + hevc_rlist_b0, + hevc_rlist_b1, + hevc_rlist_b2, + hevc_rlist_b3, + hevc_rlist_b4, + hevc_rlist_b5, + hevc_rlist_b6, + hevc_rlist_b7, + hevc_rlist_b8, + hevc_rlist_b9, + hevc_rlist_b10, + hevc_rlist_b11, + hevc_rlist_b12, + hevc_rlist_b13, + hevc_rlist_b14, + hevc_rlist_b15, + }; + unsigned int i, j; + + /* List 0 contains: short term before, short term after and long term */ + j = 0; + for (i = 0; i < decode_params->num_poc_st_curr_before && j < ARRAY_SIZE(list0); i++) + list0[j++] = find_ref_pic_index(dpb, decode_params->poc_st_curr_before[i]); + for (i = 0; i < decode_params->num_poc_st_curr_after && j < ARRAY_SIZE(list0); i++) + list0[j++] = find_ref_pic_index(dpb, decode_params->poc_st_curr_after[i]); + for (i = 0; i < decode_params->num_poc_lt_curr && j < ARRAY_SIZE(list0); i++) + list0[j++] = find_ref_pic_index(dpb, decode_params->poc_lt_curr[i]); + + /* Fill the list, copying over and over */ + i = 0; + while (j < ARRAY_SIZE(list0)) + list0[j++] = list0[i++]; + + j = 0; + for (i = 0; i < decode_params->num_poc_st_curr_after && j < ARRAY_SIZE(list1); i++) + list1[j++] = find_ref_pic_index(dpb, decode_params->poc_st_curr_after[i]); + for (i = 0; i < decode_params->num_poc_st_curr_before && j < ARRAY_SIZE(list1); i++) + list1[j++] = find_ref_pic_index(dpb, decode_params->poc_st_curr_before[i]); + for (i = 0; i < decode_params->num_poc_lt_curr && j < ARRAY_SIZE(list1); i++) + list1[j++] = find_ref_pic_index(dpb, decode_params->poc_lt_curr[i]); + + i = 0; + while (j < ARRAY_SIZE(list1)) + list1[j++] = list1[i++]; + + for (i = 0; i < V4L2_HEVC_DPB_ENTRIES_NUM_MAX; i++) { + hantro_reg_write(vpu, ref_pic_regs0[i], list0[i]); + hantro_reg_write(vpu, ref_pic_regs1[i], list1[i]); + } +} + +static int set_ref(struct hantro_ctx *ctx) +{ + const struct hantro_hevc_dec_ctrls *ctrls = &ctx->hevc_dec.ctrls; + const struct v4l2_ctrl_hevc_sps *sps = ctrls->sps; + const struct v4l2_ctrl_hevc_pps *pps = ctrls->pps; + const struct v4l2_ctrl_hevc_decode_params *decode_params = ctrls->decode_params; + const struct v4l2_hevc_dpb_entry *dpb = decode_params->dpb; + dma_addr_t luma_addr, chroma_addr, mv_addr = 0; + struct hantro_dev *vpu = ctx->dev; + size_t cr_offset = hantro_hevc_chroma_offset(sps); + size_t mv_offset = hantro_hevc_motion_vectors_offset(sps); + u32 max_ref_frames; + u16 dpb_longterm_e; + + const struct hantro_reg *cur_poc[] = { + hevc_cur_poc_00, + hevc_cur_poc_01, + hevc_cur_poc_02, + hevc_cur_poc_03, + hevc_cur_poc_04, + hevc_cur_poc_05, + hevc_cur_poc_06, + hevc_cur_poc_07, + hevc_cur_poc_08, + hevc_cur_poc_09, + hevc_cur_poc_10, + hevc_cur_poc_11, + hevc_cur_poc_12, + hevc_cur_poc_13, + hevc_cur_poc_14, + hevc_cur_poc_15, + }; + unsigned int i; + + max_ref_frames = decode_params->num_poc_lt_curr + + decode_params->num_poc_st_curr_before + + decode_params->num_poc_st_curr_after; + /* + * Set max_ref_frames to non-zero to avoid HW hang when decoding + * badly marked I-frames. + */ + max_ref_frames = max_ref_frames ? max_ref_frames : 1; + hantro_reg_write(vpu, hevc_num_ref_frames, max_ref_frames); + hantro_reg_write(vpu, hevc_filter_over_slices, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_PPS_LOOP_FILTER_ACROSS_SLICES_ENABLED)); + hantro_reg_write(vpu, hevc_filter_over_tiles, + !!(pps->flags & V4L2_HEVC_PPS_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED)); + + /* + * Write POC count diff from current pic. For frame decoding only compute + * pic_order_cnt[0] and ignore pic_order_cnt[1] used in field-coding. + */ + for (i = 0; i < decode_params->num_active_dpb_entries && i < ARRAY_SIZE(cur_poc); i++) { + char poc_diff = decode_params->pic_order_cnt_val - dpb[i].pic_order_cnt[0]; + + hantro_reg_write(vpu, cur_poc[i], poc_diff); + } + + if (i < ARRAY_SIZE(cur_poc)) { + /* + * After the references, fill one entry pointing to itself, + * i.e. difference is zero. + */ + hantro_reg_write(vpu, cur_poc[i], 0); + i++; + } + + /* Fill the rest with the current picture */ + for (; i < ARRAY_SIZE(cur_poc); i++) + hantro_reg_write(vpu, cur_poc[i], decode_params->pic_order_cnt_val); + + set_ref_pic_list(ctx); + + /* We will only keep the references picture that are still used */ + ctx->hevc_dec.ref_bufs_used = 0; + + /* Set up addresses of DPB buffers */ + dpb_longterm_e = 0; + for (i = 0; i < decode_params->num_active_dpb_entries && + i < (V4L2_HEVC_DPB_ENTRIES_NUM_MAX - 1); i++) { + luma_addr = hantro_hevc_get_ref_buf(ctx, dpb[i].pic_order_cnt[0]); + if (!luma_addr) + return -ENOMEM; + + chroma_addr = luma_addr + cr_offset; + mv_addr = luma_addr + mv_offset; + + if (dpb[i].rps == V4L2_HEVC_DPB_ENTRY_RPS_LT_CURR) + dpb_longterm_e |= BIT(V4L2_HEVC_DPB_ENTRIES_NUM_MAX - 1 - i); + + hantro_write_addr(vpu, HEVC_REG_ADDR_REF(i), luma_addr); + hantro_write_addr(vpu, HEVC_REG_CHR_REF(i), chroma_addr); + hantro_write_addr(vpu, HEVC_REG_DMV_REF(i), mv_addr); + } + + luma_addr = hantro_hevc_get_ref_buf(ctx, decode_params->pic_order_cnt_val); + if (!luma_addr) + return -ENOMEM; + + chroma_addr = luma_addr + cr_offset; + mv_addr = luma_addr + mv_offset; + + hantro_write_addr(vpu, HEVC_REG_ADDR_REF(i), luma_addr); + hantro_write_addr(vpu, HEVC_REG_CHR_REF(i), chroma_addr); + hantro_write_addr(vpu, HEVC_REG_DMV_REF(i++), mv_addr); + + hantro_write_addr(vpu, HEVC_ADDR_DST, luma_addr); + hantro_write_addr(vpu, HEVC_ADDR_DST_CHR, chroma_addr); + hantro_write_addr(vpu, HEVC_ADDR_DST_MV, mv_addr); + + hantro_hevc_ref_remove_unused(ctx); + + for (; i < V4L2_HEVC_DPB_ENTRIES_NUM_MAX; i++) { + hantro_write_addr(vpu, HEVC_REG_ADDR_REF(i), 0); + hantro_write_addr(vpu, HEVC_REG_CHR_REF(i), 0); + hantro_write_addr(vpu, HEVC_REG_DMV_REF(i), 0); + } + + hantro_reg_write(vpu, hevc_refer_lterm_e, dpb_longterm_e); + + return 0; +} + +static void set_buffers(struct hantro_ctx *ctx) +{ + struct vb2_v4l2_buffer *src_buf, *dst_buf; + struct hantro_dev *vpu = ctx->dev; + const struct hantro_hevc_dec_ctrls *ctrls = &ctx->hevc_dec.ctrls; + const struct v4l2_ctrl_hevc_sps *sps = ctrls->sps; + size_t cr_offset = hantro_hevc_chroma_offset(sps); + dma_addr_t src_dma, dst_dma; + u32 src_len, src_buf_len; + + src_buf = hantro_get_src_buf(ctx); + dst_buf = hantro_get_dst_buf(ctx); + + /* Source (stream) buffer. */ + src_dma = vb2_dma_contig_plane_dma_addr(&src_buf->vb2_buf, 0); + src_len = vb2_get_plane_payload(&src_buf->vb2_buf, 0); + src_buf_len = vb2_plane_size(&src_buf->vb2_buf, 0); + + hantro_write_addr(vpu, HEVC_ADDR_STR, src_dma); + hantro_reg_write(vpu, hevc_stream_len, src_len); + hantro_reg_write(vpu, hevc_strm_buffer_len, src_buf_len); + hantro_reg_write(vpu, hevc_strm_start_offset, 0); + hantro_reg_write(vpu, hevc_write_mvs_e, 1); + + /* Destination (decoded frame) buffer. */ + dst_dma = hantro_get_dec_buf_addr(ctx, &dst_buf->vb2_buf); + + hantro_write_addr(vpu, HEVC_RASTER_SCAN, dst_dma); + hantro_write_addr(vpu, HEVC_RASTER_SCAN_CHR, dst_dma + cr_offset); + hantro_write_addr(vpu, HEVC_ADDR_TILE_SIZE, ctx->hevc_dec.tile_sizes.dma); + hantro_write_addr(vpu, HEVC_TILE_FILTER, ctx->hevc_dec.tile_filter.dma); + hantro_write_addr(vpu, HEVC_TILE_SAO, ctx->hevc_dec.tile_sao.dma); + hantro_write_addr(vpu, HEVC_TILE_BSD, ctx->hevc_dec.tile_bsd.dma); +} + +static void hantro_g2_check_idle(struct hantro_dev *vpu) +{ + int i; + + for (i = 0; i < 3; i++) { + u32 status; + + /* Make sure the VPU is idle */ + status = vdpu_read(vpu, HEVC_REG_INTERRUPT); + if (status & HEVC_REG_INTERRUPT_DEC_E) { + dev_warn(vpu->dev, "device still running, aborting"); + status |= HEVC_REG_INTERRUPT_DEC_ABORT_E | HEVC_REG_INTERRUPT_DEC_IRQ_DIS; + vdpu_write(vpu, status, HEVC_REG_INTERRUPT); + } + } +} + +int hantro_g2_hevc_dec_run(struct hantro_ctx *ctx) +{ + struct hantro_dev *vpu = ctx->dev; + int ret; + + hantro_g2_check_idle(vpu); + + /* Prepare HEVC decoder context. */ + ret = hantro_hevc_dec_prepare_run(ctx); + if (ret) + return ret; + + /* Configure hardware registers. */ + set_params(ctx); + + /* set reference pictures */ + ret = set_ref(ctx); + if (ret) + return ret; + + set_buffers(ctx); + prepare_tile_info_buffer(ctx); + + hantro_end_prepare_run(ctx); + + hantro_reg_write(vpu, hevc_mode, HEVC_DEC_MODE); + hantro_reg_write(vpu, hevc_clk_gate_e, 1); + + /* Don't disable output */ + hantro_reg_write(vpu, hevc_out_dis, 0); + + /* Don't compress buffers */ + hantro_reg_write(vpu, hevc_ref_compress_bypass, 1); + + /* use NV12 as output format */ + hantro_reg_write(vpu, hevc_out_rs_e, 1); + + /* Bus width and max burst */ + hantro_reg_write(vpu, hevc_buswidth, BUS_WIDTH_128); + hantro_reg_write(vpu, hevc_max_burst, 16); + + /* Swap */ + hantro_reg_write(vpu, hevc_strm_swap, 0xf); + hantro_reg_write(vpu, hevc_dirmv_swap, 0xf); + hantro_reg_write(vpu, hevc_compress_swap, 0xf); + + /* Start decoding! */ + vdpu_write(vpu, HEVC_REG_INTERRUPT_DEC_E, HEVC_REG_INTERRUPT); + + return 0; +} diff --git a/drivers/staging/media/hantro/hantro_g2_regs.h b/drivers/staging/media/hantro/hantro_g2_regs.h new file mode 100644 index 000000000000..2477573f7163 --- /dev/null +++ b/drivers/staging/media/hantro/hantro_g2_regs.h @@ -0,0 +1,198 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2021, Collabora + * + * Author: Benjamin Gaignard + */ + +#ifndef HANTRO_G2_REGS_H_ +#define HANTRO_G2_REGS_H_ + +#include "hantro.h" + +#define G2_SWREG(nr) ((nr) * 4) + +#define HEVC_DEC_REG(name, base, shift, mask) \ + static const struct hantro_reg _hevc_##name[] = { \ + { G2_SWREG(base), (shift), (mask) } \ + }; \ + static const struct hantro_reg __maybe_unused *hevc_##name = &_hevc_##name[0]; + +#define HEVC_REG_VERSION G2_SWREG(0) + +#define HEVC_REG_INTERRUPT G2_SWREG(1) +#define HEVC_REG_INTERRUPT_DEC_RDY_INT BIT(12) +#define HEVC_REG_INTERRUPT_DEC_ABORT_E BIT(5) +#define HEVC_REG_INTERRUPT_DEC_IRQ_DIS BIT(4) +#define HEVC_REG_INTERRUPT_DEC_E BIT(0) + +HEVC_DEC_REG(strm_swap, 2, 28, 0xf) +HEVC_DEC_REG(dirmv_swap, 2, 20, 0xf) + +HEVC_DEC_REG(mode, 3, 27, 0x1f) +HEVC_DEC_REG(compress_swap, 3, 20, 0xf) +HEVC_DEC_REG(ref_compress_bypass, 3, 17, 0x1) +HEVC_DEC_REG(out_rs_e, 3, 16, 0x1) +HEVC_DEC_REG(out_dis, 3, 15, 0x1) +HEVC_DEC_REG(out_filtering_dis, 3, 14, 0x1) +HEVC_DEC_REG(write_mvs_e, 3, 12, 0x1) + +HEVC_DEC_REG(pic_width_in_cbs, 4, 19, 0x1fff) +HEVC_DEC_REG(pic_height_in_cbs, 4, 6, 0x1fff) +HEVC_DEC_REG(num_ref_frames, 4, 0, 0x1f) + +HEVC_DEC_REG(scaling_list_e, 5, 24, 0x1) +HEVC_DEC_REG(cb_qp_offset, 5, 19, 0x1f) +HEVC_DEC_REG(cr_qp_offset, 5, 14, 0x1f) +HEVC_DEC_REG(sign_data_hide, 5, 12, 0x1) +HEVC_DEC_REG(tempor_mvp_e, 5, 11, 0x1) +HEVC_DEC_REG(max_cu_qpd_depth, 5, 5, 0x3f) +HEVC_DEC_REG(cu_qpd_e, 5, 4, 0x1) + +HEVC_DEC_REG(stream_len, 6, 0, 0xffffffff) + +HEVC_DEC_REG(cabac_init_present, 7, 31, 0x1) +HEVC_DEC_REG(weight_pred_e, 7, 28, 0x1) +HEVC_DEC_REG(weight_bipr_idc, 7, 26, 0x3) +HEVC_DEC_REG(filter_over_slices, 7, 25, 0x1) +HEVC_DEC_REG(filter_over_tiles, 7, 24, 0x1) +HEVC_DEC_REG(asym_pred_e, 7, 23, 0x1) +HEVC_DEC_REG(sao_e, 7, 22, 0x1) +HEVC_DEC_REG(pcm_filt_d, 7, 21, 0x1) +HEVC_DEC_REG(slice_chqp_present, 7, 20, 0x1) +HEVC_DEC_REG(dependent_slice, 7, 19, 0x1) +HEVC_DEC_REG(filter_override, 7, 18, 0x1) +HEVC_DEC_REG(strong_smooth_e, 7, 17, 0x1) +HEVC_DEC_REG(filt_offset_beta, 7, 12, 0x1f) +HEVC_DEC_REG(filt_offset_tc, 7, 7, 0x1f) +HEVC_DEC_REG(slice_hdr_ext_e, 7, 6, 0x1) +HEVC_DEC_REG(slice_hdr_ext_bits, 7, 3, 0x7) + +HEVC_DEC_REG(const_intra_e, 8, 31, 0x1) +HEVC_DEC_REG(filt_ctrl_pres, 8, 30, 0x1) +HEVC_DEC_REG(idr_pic_e, 8, 16, 0x1) +HEVC_DEC_REG(bit_depth_pcm_y, 8, 12, 0xf) +HEVC_DEC_REG(bit_depth_pcm_c, 8, 8, 0xf) +HEVC_DEC_REG(bit_depth_y_minus8, 8, 6, 0x3) +HEVC_DEC_REG(bit_depth_c_minus8, 8, 4, 0x3) +HEVC_DEC_REG(output_8_bits, 8, 3, 0x1) + +HEVC_DEC_REG(refidx1_active, 9, 19, 0x1f) +HEVC_DEC_REG(refidx0_active, 9, 14, 0x1f) +HEVC_DEC_REG(hdr_skip_length, 9, 0, 0x3fff) + +HEVC_DEC_REG(start_code_e, 10, 31, 0x1) +HEVC_DEC_REG(init_qp, 10, 24, 0x3f) +HEVC_DEC_REG(num_tile_cols, 10, 19, 0x1f) +HEVC_DEC_REG(num_tile_rows, 10, 14, 0x1f) +HEVC_DEC_REG(tile_e, 10, 1, 0x1) +HEVC_DEC_REG(entropy_sync_e, 10, 0, 0x1) + +HEVC_DEC_REG(refer_lterm_e, 12, 16, 0xffff) +HEVC_DEC_REG(min_cb_size, 12, 13, 0x7) +HEVC_DEC_REG(max_cb_size, 12, 10, 0x7) +HEVC_DEC_REG(min_pcm_size, 12, 7, 0x7) +HEVC_DEC_REG(max_pcm_size, 12, 4, 0x7) +HEVC_DEC_REG(pcm_e, 12, 3, 0x1) +HEVC_DEC_REG(transform_skip, 12, 2, 0x1) +HEVC_DEC_REG(transq_bypass, 12, 1, 0x1) +HEVC_DEC_REG(list_mod_e, 12, 0, 0x1) + +HEVC_DEC_REG(min_trb_size, 13, 13, 0x7) +HEVC_DEC_REG(max_trb_size, 13, 10, 0x7) +HEVC_DEC_REG(max_intra_hierdepth, 13, 7, 0x7) +HEVC_DEC_REG(max_inter_hierdepth, 13, 4, 0x7) +HEVC_DEC_REG(parallel_merge, 13, 0, 0xf) + +HEVC_DEC_REG(rlist_f0, 14, 0, 0x1f) +HEVC_DEC_REG(rlist_f1, 14, 10, 0x1f) +HEVC_DEC_REG(rlist_f2, 14, 20, 0x1f) +HEVC_DEC_REG(rlist_b0, 14, 5, 0x1f) +HEVC_DEC_REG(rlist_b1, 14, 15, 0x1f) +HEVC_DEC_REG(rlist_b2, 14, 25, 0x1f) + +HEVC_DEC_REG(rlist_f3, 15, 0, 0x1f) +HEVC_DEC_REG(rlist_f4, 15, 10, 0x1f) +HEVC_DEC_REG(rlist_f5, 15, 20, 0x1f) +HEVC_DEC_REG(rlist_b3, 15, 5, 0x1f) +HEVC_DEC_REG(rlist_b4, 15, 15, 0x1f) +HEVC_DEC_REG(rlist_b5, 15, 25, 0x1f) + +HEVC_DEC_REG(rlist_f6, 16, 0, 0x1f) +HEVC_DEC_REG(rlist_f7, 16, 10, 0x1f) +HEVC_DEC_REG(rlist_f8, 16, 20, 0x1f) +HEVC_DEC_REG(rlist_b6, 16, 5, 0x1f) +HEVC_DEC_REG(rlist_b7, 16, 15, 0x1f) +HEVC_DEC_REG(rlist_b8, 16, 25, 0x1f) + +HEVC_DEC_REG(rlist_f9, 17, 0, 0x1f) +HEVC_DEC_REG(rlist_f10, 17, 10, 0x1f) +HEVC_DEC_REG(rlist_f11, 17, 20, 0x1f) +HEVC_DEC_REG(rlist_b9, 17, 5, 0x1f) +HEVC_DEC_REG(rlist_b10, 17, 15, 0x1f) +HEVC_DEC_REG(rlist_b11, 17, 25, 0x1f) + +HEVC_DEC_REG(rlist_f12, 18, 0, 0x1f) +HEVC_DEC_REG(rlist_f13, 18, 10, 0x1f) +HEVC_DEC_REG(rlist_f14, 18, 20, 0x1f) +HEVC_DEC_REG(rlist_b12, 18, 5, 0x1f) +HEVC_DEC_REG(rlist_b13, 18, 15, 0x1f) +HEVC_DEC_REG(rlist_b14, 18, 25, 0x1f) + +HEVC_DEC_REG(rlist_f15, 19, 0, 0x1f) +HEVC_DEC_REG(rlist_b15, 19, 5, 0x1f) + +HEVC_DEC_REG(partial_ctb_x, 20, 31, 0x1) +HEVC_DEC_REG(partial_ctb_y, 20, 30, 0x1) +HEVC_DEC_REG(pic_width_4x4, 20, 16, 0xfff) +HEVC_DEC_REG(pic_height_4x4, 20, 0, 0xfff) + +HEVC_DEC_REG(cur_poc_00, 46, 24, 0xff) +HEVC_DEC_REG(cur_poc_01, 46, 16, 0xff) +HEVC_DEC_REG(cur_poc_02, 46, 8, 0xff) +HEVC_DEC_REG(cur_poc_03, 46, 0, 0xff) + +HEVC_DEC_REG(cur_poc_04, 47, 24, 0xff) +HEVC_DEC_REG(cur_poc_05, 47, 16, 0xff) +HEVC_DEC_REG(cur_poc_06, 47, 8, 0xff) +HEVC_DEC_REG(cur_poc_07, 47, 0, 0xff) + +HEVC_DEC_REG(cur_poc_08, 48, 24, 0xff) +HEVC_DEC_REG(cur_poc_09, 48, 16, 0xff) +HEVC_DEC_REG(cur_poc_10, 48, 8, 0xff) +HEVC_DEC_REG(cur_poc_11, 48, 0, 0xff) + +HEVC_DEC_REG(cur_poc_12, 49, 24, 0xff) +HEVC_DEC_REG(cur_poc_13, 49, 16, 0xff) +HEVC_DEC_REG(cur_poc_14, 49, 8, 0xff) +HEVC_DEC_REG(cur_poc_15, 49, 0, 0xff) + +HEVC_DEC_REG(apf_threshold, 55, 0, 0xffff) + +HEVC_DEC_REG(clk_gate_e, 58, 16, 0x1) +HEVC_DEC_REG(buswidth, 58, 8, 0x7) +HEVC_DEC_REG(max_burst, 58, 0, 0xff) + +#define HEVC_REG_CONFIG G2_SWREG(58) +#define HEVC_REG_CONFIG_DEC_CLK_GATE_E BIT(16) +#define HEVC_REG_CONFIG_DEC_CLK_GATE_IDLE_E BIT(17) + +#define HEVC_ADDR_DST (G2_SWREG(65)) +#define HEVC_REG_ADDR_REF(i) (G2_SWREG(67) + ((i) * 0x8)) +#define HEVC_ADDR_DST_CHR (G2_SWREG(99)) +#define HEVC_REG_CHR_REF(i) (G2_SWREG(101) + ((i) * 0x8)) +#define HEVC_ADDR_DST_MV (G2_SWREG(133)) +#define HEVC_REG_DMV_REF(i) (G2_SWREG(135) + ((i) * 0x8)) +#define HEVC_ADDR_TILE_SIZE (G2_SWREG(167)) +#define HEVC_ADDR_STR (G2_SWREG(169)) +#define HEVC_SCALING_LIST (G2_SWREG(171)) +#define HEVC_RASTER_SCAN (G2_SWREG(175)) +#define HEVC_RASTER_SCAN_CHR (G2_SWREG(177)) +#define HEVC_TILE_FILTER (G2_SWREG(179)) +#define HEVC_TILE_SAO (G2_SWREG(181)) +#define HEVC_TILE_BSD (G2_SWREG(183)) + +HEVC_DEC_REG(strm_buffer_len, 258, 0, 0xffffffff) +HEVC_DEC_REG(strm_start_offset, 259, 0, 0xffffffff) + +#endif diff --git a/drivers/staging/media/hantro/hantro_hevc.c b/drivers/staging/media/hantro/hantro_hevc.c new file mode 100644 index 000000000000..015197797591 --- /dev/null +++ b/drivers/staging/media/hantro/hantro_hevc.c @@ -0,0 +1,327 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hantro VPU HEVC codec driver + * + * Copyright (C) 2020 Safran Passenger Innovations LLC + */ + +#include +#include + +#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.size) + dma_free_coherent(vpu->dev, hevc_dec->tile_filter.size, + hevc_dec->tile_filter.cpu, + hevc_dec->tile_filter.dma); + + 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); + + 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); + + 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.size) + 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; +} diff --git a/drivers/staging/media/hantro/hantro_hw.h b/drivers/staging/media/hantro/hantro_hw.h index 4b73c8011b25..b743b255bf32 100644 --- a/drivers/staging/media/hantro/hantro_hw.h +++ b/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 +97,44 @@ 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 + * @dpb: DPB + * @reflists: P/B0/B1 reflists + * @ctrls: V4L2 controls attached to a run + */ +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 +234,15 @@ 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) {