From patchwork Mon May 18 17:40:09 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Ezequiel Garcia X-Patchwork-Id: 11555955 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 73F951391 for ; Mon, 18 May 2020 17:40:33 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 65DE7207FB for ; Mon, 18 May 2020 17:40:33 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729089AbgERRkc (ORCPT ); Mon, 18 May 2020 13:40:32 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:59586 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729083AbgERRkb (ORCPT ); Mon, 18 May 2020 13:40:31 -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 4CCDEC061A0C; Mon, 18 May 2020 10:40:31 -0700 (PDT) Received: from [127.0.0.1] (localhost [127.0.0.1]) (Authenticated sender: ezequiel) with ESMTPSA id BBB782A0C9C From: Ezequiel Garcia To: linux-media@vger.kernel.org, linux-rockchip@lists.infradead.org, linux-kernel@vger.kernel.org Cc: Tomasz Figa , kernel@collabora.com, Jonas Karlman , Heiko Stuebner , Hans Verkuil , Alexandre Courbot , Jeffrey Kardatzke , gustavo.padovan@collabora.com, Nicolas Dufresne , Ezequiel Garcia Subject: [PATCH v4 1/3] media: rkvdec: Fix .buf_prepare Date: Mon, 18 May 2020 14:40:09 -0300 Message-Id: <20200518174011.15543-2-ezequiel@collabora.com> X-Mailer: git-send-email 2.26.0.rc2 In-Reply-To: <20200518174011.15543-1-ezequiel@collabora.com> References: <20200518174011.15543-1-ezequiel@collabora.com> MIME-Version: 1.0 Sender: linux-media-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-media@vger.kernel.org The driver should only set the payload on .buf_prepare if the buffer is CAPTURE type, or if an OUTPUT buffer has a zeroed payload. Fix it. Fixes: cd33c830448ba ("media: rkvdec: Add the rkvdec driver") Signed-off-by: Ezequiel Garcia --- drivers/staging/media/rkvdec/rkvdec.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c index 225eeca73356..4df2a248ab96 100644 --- a/drivers/staging/media/rkvdec/rkvdec.c +++ b/drivers/staging/media/rkvdec/rkvdec.c @@ -456,7 +456,15 @@ static int rkvdec_buf_prepare(struct vb2_buffer *vb) if (vb2_plane_size(vb, i) < sizeimage) return -EINVAL; } - vb2_set_plane_payload(vb, 0, f->fmt.pix_mp.plane_fmt[0].sizeimage); + + /* + * Buffer's bytesused is written by the driver for CAPTURE buffers, + * or if the application passed zero bytesused on an OUTPUT buffer. + */ + if (!V4L2_TYPE_IS_OUTPUT(vq->type) || + (V4L2_TYPE_IS_OUTPUT(vq->type) && !vb2_get_plane_payload(vb, 0))) + vb2_set_plane_payload(vb, 0, + f->fmt.pix_mp.plane_fmt[0].sizeimage); return 0; } From patchwork Mon May 18 17:40:10 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Ezequiel Garcia X-Patchwork-Id: 11555959 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 827081391 for ; Mon, 18 May 2020 17:40:41 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 5E2B620853 for ; Mon, 18 May 2020 17:40:41 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729119AbgERRkk (ORCPT ); Mon, 18 May 2020 13:40:40 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:59612 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728489AbgERRkj (ORCPT ); Mon, 18 May 2020 13:40:39 -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 9EF38C061A0C; Mon, 18 May 2020 10:40:38 -0700 (PDT) Received: from [127.0.0.1] (localhost [127.0.0.1]) (Authenticated sender: ezequiel) with ESMTPSA id D5F9E2A10B8 From: Ezequiel Garcia To: linux-media@vger.kernel.org, linux-rockchip@lists.infradead.org, linux-kernel@vger.kernel.org Cc: Tomasz Figa , kernel@collabora.com, Jonas Karlman , Heiko Stuebner , Hans Verkuil , Alexandre Courbot , Jeffrey Kardatzke , gustavo.padovan@collabora.com, Nicolas Dufresne , Boris Brezillon , Ezequiel Garcia Subject: [PATCH v4 2/3] media: uapi: Add VP9 stateless decoder controls Date: Mon, 18 May 2020 14:40:10 -0300 Message-Id: <20200518174011.15543-3-ezequiel@collabora.com> X-Mailer: git-send-email 2.26.0.rc2 In-Reply-To: <20200518174011.15543-1-ezequiel@collabora.com> References: <20200518174011.15543-1-ezequiel@collabora.com> MIME-Version: 1.0 Sender: linux-media-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-media@vger.kernel.org From: Boris Brezillon Add the VP9 stateless decoder controls plus the documentation that goes with it. Signed-off-by: Boris Brezillon Signed-off-by: Ezequiel Garcia --- .../userspace-api/media/v4l/biblio.rst | 10 + .../media/v4l/ext-ctrls-codec.rst | 550 ++++++++++++++++++ drivers/media/v4l2-core/v4l2-ctrls.c | 239 ++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/media/v4l2-ctrls.h | 1 + include/media/vp9-ctrls.h | 485 +++++++++++++++ 6 files changed, 1286 insertions(+) create mode 100644 include/media/vp9-ctrls.h diff --git a/Documentation/userspace-api/media/v4l/biblio.rst b/Documentation/userspace-api/media/v4l/biblio.rst index 3c9634173e82..e09102e572fd 100644 --- a/Documentation/userspace-api/media/v4l/biblio.rst +++ b/Documentation/userspace-api/media/v4l/biblio.rst @@ -414,3 +414,13 @@ VP8 :title: RFC 6386: "VP8 Data Format and Decoding Guide" :author: J. Bankoski et al. + +.. _vp9: + +VP9 +=== + + +:title: VP9 Bitstream & Decoding Process Specification + +:author: Adrian Grange (Google), Peter de Rivaz (Argon Design), Jonathan Hunt (Argon Design) diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst index d0d506a444b1..5c5f7dd868da 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst @@ -2668,6 +2668,556 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type - - ``padding[3]`` - Applications and drivers must set this to zero. +.. _v4l2-mpeg-vp9: + +``V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(0..3) (struct)`` + Stores VP9 probabilities attached to a specific frame context. The VP9 + specification allows using a maximum of 4 contexts. Each frame being + decoded refers to one of those context. See section '7.1.2 Refresh + probs semantics' section of :ref:`vp9` for more details about these + contexts. + + This control is bi-directional: + + * all 4 contexts must be initialized by userspace just after the + stream is started and before the first decoding request is submitted. + * the referenced context might be read by the kernel when a decoding + request is submitted, and will be updated after the decoder is done + decoding the frame if the `V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX` flag + is set. + * contexts will be read back by user space before each decoding request + to retrieve the updated probabilities. + * userspace will re-initialize the context to their default values when + a reset context is required. + + .. note:: + + This compound control is not yet part of the public kernel API and + it is expected to change. + +.. c:type:: v4l2_ctrl_vp9_frame_ctx + +.. cssclass:: longtable + +.. tabularcolumns:: |p{5.8cm}|p{4.8cm}|p{6.6cm}| + +.. flat-table:: struct v4l2_ctrl_vp9_frame_ctx + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - struct :c:type:`v4l2_vp9_probabilities` + - ``probs`` + - Structure with VP9 probabilities attached to the context. + +.. c:type:: v4l2_vp9_probabilities + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: struct v4l2_vp9_probabilities + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u8 + - ``tx8[2][1]`` + - TX 8x8 probabilities. + * - __u8 + - ``tx16[2][2]`` + - TX 16x16 probabilities. + * - __u8 + - ``tx32[2][3]`` + - TX 32x32 probabilities. + * - __u8 + - ``coef[4][2][2][6][6][3]`` + - Coefficient probabilities. + * - __u8 + - ``skip[3]`` + - Skip probabilities. + * - __u8 + - ``inter_mode[7][3]`` + - Inter prediction mode probabilities. + * - __u8 + - ``interp_filter[4][2]`` + - Interpolation filter probabilities. + * - __u8 + - ``is_inter[4]`` + - Is inter-block probabilities. + * - __u8 + - ``comp_mode[5]`` + - Compound prediction mode probabilities. + * - __u8 + - ``single_ref[5][2]`` + - Single reference probabilities. + * - __u8 + - ``comp_mode[5]`` + - Compound reference probabilities. + * - __u8 + - ``y_mode[4][9]`` + - Y prediction mode probabilities. + * - __u8 + - ``uv_mode[10][9]`` + - UV prediction mode probabilities. + * - __u8 + - ``partition[16][3]`` + - Partition probabilities. + * - __u8 + - ``mv.joint[3]`` + - Motion vector joint probabilities. + * - __u8 + - ``mv.sign[2]`` + - Motion vector sign probabilities. + * - __u8 + - ``mv.class[2][10]`` + - Motion vector class probabilities. + * - __u8 + - ``mv.class0_bit[2]`` + - Motion vector class0 bit probabilities. + * - __u8 + - ``mv.bits[2][10]`` + - Motion vector bits probabilities. + * - __u8 + - ``mv.class0_fr[2][2][3]`` + - Motion vector class0 fractional bit probabilities. + * - __u8 + - ``mv.fr[2][3]`` + - Motion vector fractional bit probabilities. + * - __u8 + - ``mv.class0_hp[2]`` + - Motion vector class0 high precision fractional bit probabilities. + * - __u8 + - ``mv.hp[2]`` + - Motion vector high precision fractional bit probabilities. + +``V4L2_CID_MPEG_VIDEO_VP9_FRAME_DECODE_PARAMS (struct)`` + Specifies the frame parameters for the associated VP9 frame decode request. + This includes the necessary parameters for configuring a stateless hardware + decoding pipeline for VP9. The bitstream parameters are defined according + to :ref:`vp9`. + + .. note:: + + This compound control is not yet part of the public kernel API and + it is expected to change. + +.. c:type:: v4l2_ctrl_vp9_frame_decode_params + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: struct v4l2_ctrl_vp9_frame_decode_params + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u32 + - ``flags`` + - Combination of V4L2_VP9_FRAME_FLAG_* flags. See + :c:type:`v4l2_vp9_frame_flags`. + * - __u16 + - ``compressed_header_size`` + - Compressed header size in bytes. + * - __u16 + - ``uncompressed_header_size`` + - Uncompressed header size in bytes. + * - __u8 + - ``profile`` + - VP9 profile. Can be 0, 1, 2 or 3. + * - __u8 + - ``reset_frame_context`` + - Frame context that should be used/updated when decoding the frame. + * - __u8 + - ``bit_depth`` + - Component depth in bits. Must be 8 for profile 0 and 1. Must 10 or 12 + for profile 2 and 3. + * - __u8 + - ``interpolation_filter`` + - Specifies the filter selection used for performing inter prediction. See + :c:type:`v4l2_vp9_interpolation_filter`. + * - __u8 + - ``tile_cols_log2`` + - Specifies the base 2 logarithm of the width of each tile (where the + width is measured in units of 8x8 blocks). Shall be less than or equal + to 6. + * - __u8 + - ``tile_rows_log2`` + - Specifies the base 2 logarithm of the height of each tile (where the + height is measured in units of 8x8 blocks) + * - __u8 + - ``tx_mode`` + - Specifies the TX mode. See :c:type:`v4l2_vp9_tx_mode`. + * - __u8 + - ``reference_mode`` + - Specifies the type of inter prediction to be used. See + :c:type:`v4l2_vp9_reference_mode`. + * - __u8 + - ``padding`` + - Needed to make this struct 64 bit aligned. Shall be filled with zeroes. + * - __u16 + - ``frame_width_minus_1`` + - Add 1 to get the frame width expressed in pixels. + * - __u16 + - ``frame_height_minus_1`` + - Add 1 to to get the frame height expressed in pixels. + * - __u16 + - ``frame_width_minus_1`` + - Add 1 to to get the expected render width expressed in pixels. This is + not used during the decoding process but might be used by HW scalers to + prepare a frame that's ready for scanout. + * - __u16 + - frame_height_minus_1 + - Add 1 to get the expected render height expressed in pixels. This is + not used during the decoding process but might be used by HW scalers to + prepare a frame that's ready for scanout. + * - __u64 + - ``refs[3]`` + - Array of reference frame timestamps. + * - struct :c:type:`v4l2_vp9_loop_filter` + - ``lf`` + - Loop filter parameters. See struct :c:type:`v4l2_vp9_loop_filter`. + * - struct :c:type:`v4l2_vp9_quantization` + - ``quant`` + - Quantization parameters. See :c:type:`v4l2_vp9_quantization`. + * - struct :c:type:`v4l2_vp9_segmentation` + - ``seg`` + - Segmentation parameters. See :c:type:`v4l2_vp9_segmentation`. + * - struct :c:type:`v4l2_vp9_probabilities` + - ``probs`` + - Probabilities. See :c:type:`v4l2_vp9_probabilities`. + +.. c:type:: v4l2_vp9_frame_flags + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: enum v4l2_vp9_frame_flags + :header-rows: 0 + :stub-columns: 0 + :widths: 1 2 + + * - ``V4L2_VP9_FRAME_FLAG_KEY_FRAME`` + - The frame is a key frame. + * - ``V4L2_VP9_FRAME_FLAG_SHOW_FRAME`` + - The frame should be displayed. + * - ``V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT`` + - The decoding should be error resilient. + * - ``V4L2_VP9_FRAME_FLAG_INTRA_ONLY`` + - The frame does not reference other frames. + * - ``V4L2_VP9_FRAME_FLAG_ALLOW_HIGH_PREC_MV`` + - the frame might can high precision motion vectors. + * - ``V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX`` + - Frame context should be updated after decoding. + * - ``V4L2_VP9_FRAME_FLAG_PARALLEL_DEC_MODE`` + - Parallel decoding is used. + * - ``V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING`` + - Vertical subsampling is enabled. + * - ``V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING`` + - Horizontal subsampling is enabled. + * - ``V4L2_VP9_FRAME_FLAG_COLOR_RANGE_FULL_SWING`` + - The full UV range is used. + +.. c:type:: v4l2_vp9_ref_id + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: enum v4l2_vp9_ref_id + :header-rows: 0 + :stub-columns: 0 + :widths: 1 2 + + * - ``V4L2_REF_ID_LAST`` + - Last reference frame. + * - ``V4L2_REF_ID_GOLDEN`` + - Golden reference frame. + * - ``V4L2_REF_ID_ALTREF`` + - Alternative reference frame. + * - ``V4L2_REF_ID_CNT`` + - Number of reference frames. + +.. c:type:: v4l2_vp9_tx_mode + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: enum v4l2_vp9_tx_mode + :header-rows: 0 + :stub-columns: 0 + :widths: 1 2 + + * - ``V4L2_VP9_TX_MODE_ONLY_4X4`` + - Transform size is 4x4. + * - ``V4L2_VP9_TX_MODE_ALLOW_8X8`` + - Transform size can be up to 8x8. + * - ``V4L2_VP9_TX_MODE_ALLOW_16X16`` + - Transform size can be up to 16x16. + * - ``V4L2_VP9_TX_MODE_ALLOW_32X32`` + - transform size can be up to 32x32. + * - ``V4L2_VP9_TX_MODE_SELECT`` + - Bitstream contains transform size for each block. + +.. c:type:: v4l2_vp9_reference_mode + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: enum v4l2_vp9_reference_mode + :header-rows: 0 + :stub-columns: 0 + :widths: 1 2 + + * - ``V4L2_VP9_REF_MODE_SINGLE`` + - Indicates that all the inter blocks use only a single reference frame + to generate motion compensated prediction. + * - ``V4L2_VP9_REF_MODE_COMPOUND`` + - Requires all the inter blocks to use compound mode. Single reference + frame prediction is not allowed. + * - ``V4L2_VP9_REF_MODE_SELECT`` + - Allows each individual inter block to select between single and + compound prediction modes. + +.. c:type:: v4l2_vp9_interpolation_filter + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: enum v4l2_vp9_interpolation_filter + :header-rows: 0 + :stub-columns: 0 + :widths: 1 2 + + * - ``V4L2_VP9_INTERP_FILTER_8TAP`` + - Height tap filter. + * - ``V4L2_VP9_INTERP_FILTER_8TAP_SMOOTH`` + - Height tap smooth filter. + * - ``V4L2_VP9_INTERP_FILTER_8TAP_SHARP`` + - Height tap sharp filter. + * - ``V4L2_VP9_INTERP_FILTER_BILINEAR`` + - Bilinear filter. + * - ``V4L2_VP9_INTERP_FILTER_SWITCHABLE`` + - Filter selection is signaled at the block level. + +.. c:type:: v4l2_vp9_reset_frame_context + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: enum v4l2_vp9_reset_frame_context + :header-rows: 0 + :stub-columns: 0 + :widths: 1 2 + + * - ``V4L2_VP9_RESET_FRAME_CTX_NONE`` + - Do not reset any frame context. + * - ``V4L2_VP9_RESET_FRAME_CTX_SPEC`` + - Reset the frame context pointed by + :c:type:`v4l2_ctrl_vp9_frame_decode_params`.frame_context_idx. + * - ``V4L2_VP9_RESET_FRAME_CTX_ALL`` + - Reset all frame contexts. + +.. c:type:: v4l2_vp9_intra_prediction_mode + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: enum v4l2_vp9_intra_prediction_mode + :header-rows: 0 + :stub-columns: 0 + :widths: 1 2 + + * - ``V4L2_VP9_INTRA_PRED_DC`` + - DC intra prediction. + * - ``V4L2_VP9_INTRA_PRED_MODE_V`` + - Vertical intra prediction. + * - ``V4L2_VP9_INTRA_PRED_MODE_H`` + - Horizontal intra prediction. + * - ``V4L2_VP9_INTRA_PRED_MODE_D45`` + - D45 intra prediction. + * - ``V4L2_VP9_INTRA_PRED_MODE_D135`` + - D135 intra prediction. + * - ``V4L2_VP9_INTRA_PRED_MODE_D117`` + - D117 intra prediction. + * - ``V4L2_VP9_INTRA_PRED_MODE_D153`` + - D153 intra prediction. + * - ``V4L2_VP9_INTRA_PRED_MODE_D207`` + - D207 intra prediction. + * - ``V4L2_VP9_INTRA_PRED_MODE_D63`` + - D63 intra prediction. + * - ``V4L2_VP9_INTRA_PRED_MODE_TM`` + - True motion intra prediction. + +.. c:type:: v4l2_vp9_segmentation + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: struct v4l2_vp9_segmentation + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u8 + - ``flags`` + - Combination of V4L2_VP9_SEGMENTATION_FLAG_* flags. See + :c:type:`v4l2_vp9_segmentation_flags`. + * - __u8 + - ``tree_probs[7]`` + - Specifies the probability values to be used when decoding a Segment-ID. + See '5.15. Segmentation map' section of :ref:`vp9` for more details. + * - __u8 + - ``pred_prob[3]`` + - Specifies the probability values to be used when decoding a + Predicted-Segment-ID. See '6.4.14. Get segment id syntax' + section of :ref:`vp9` for more details. + * - __u8 + - ``padding[5]`` + - Used to align this struct on 64 bit. Shall be filled with zeroes. + * - __u8 + - ``feature_enabled[8]`` + - Bitmask defining which features are enabled in each segment. + * - __u8 + - ``feature_data[8][4]`` + - Data attached to each feature. Data entry is only valid if the feature + is enabled. + +.. c:type:: v4l2_vp9_segment_feature + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: enum v4l2_vp9_segment_feature + :header-rows: 0 + :stub-columns: 0 + :widths: 1 2 + + * - ``V4L2_VP9_SEGMENT_FEATURE_QP_DELTA`` + - QP delta segment feature. + * - ``V4L2_VP9_SEGMENT_FEATURE_LF`` + - Loop filter segment feature. + * - ``V4L2_VP9_SEGMENT_FEATURE_REF_FRAME`` + - Reference frame segment feature. + * - ``V4L2_VP9_SEGMENT_FEATURE_SKIP`` + - Skip segment feature. + * - ``V4L2_VP9_SEGMENT_FEATURE_CNT`` + - Number of segment features. + +.. c:type:: v4l2_vp9_segmentation_flags + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: enum v4l2_vp9_segmentation_flags + :header-rows: 0 + :stub-columns: 0 + :widths: 1 2 + + * - ``V4L2_VP9_SEGMENTATION_FLAG_ENABLED`` + - Indicates that this frame makes use of the segmentation tool. + * - ``V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP`` + - Indicates that the segmentation map should be updated during the + decoding of this frame. + * - ``V4L2_VP9_SEGMENTATION_FLAG_TEMPORAL_UPDATE`` + - Indicates that the updates to the segmentation map are coded + relative to the existing segmentation map. + * - ``V4L2_VP9_SEGMENTATION_FLAG_UPDATE_DATA`` + - Indicates that new parameters are about to be specified for each + segment. + * - ``V4L2_VP9_SEGMENTATION_FLAG_ABS_OR_DELTA_UPDATE`` + - Indicates that the segmentation parameters represent the actual values + to be used. + +.. c:type:: v4l2_vp9_quantization + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: struct v4l2_vp9_quantization + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u8 + - ``base_q_idx`` + - Indicates the base frame qindex. + * - __s8 + - ``delta_q_y_dc`` + - Indicates the Y DC quantizer relative to base_q_idx. + * - __s8 + - ``delta_q_uv_dc`` + - Indicates the UV DC quantizer relative to base_q_idx. + * - __s8 + - ``delta_q_uv_ac`` + - Indicates the UV AC quantizer relative to base_q_idx. + * - __u8 + - ``padding[4]`` + - Padding bytes used to align this struct on 64 bit. Must be set to 0. + +.. c:type:: v4l2_vp9_loop_filter + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: struct v4l2_vp9_loop_filter + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u8 + - ``flags`` + - Combination of V4L2_VP9_LOOP_FILTER_FLAG_* flags. + See :c:type:`v4l2_vp9_loop_filter_flags`. + * - __u8 + - ``level`` + - Indicates the loop filter strength. + * - __u8 + - ``sharpness`` + - Indicates the sharpness level. + * - __s8 + - ``ref_deltas[4]`` + - Contains the adjustment needed for the filter level based on the chosen + reference frame. + * - __s8 + - ``mode_deltas[2]`` + - Contains the adjustment needed for the filter level based on the chosen + mode + * - __u8 + - ``level_lookup[8][4][2]`` + - Level lookup table. + + +.. c:type:: v4l2_vp9_loop_filter_flags + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.5cm}|p{6.3cm}|p{9.4cm}| + +.. flat-table:: enum v4l2_vp9_loop_filter_flags + :header-rows: 0 + :stub-columns: 0 + :widths: 1 2 + + * - ``V4L2_VP9_LOOP_FILTER_FLAG_DELTA_ENABLED`` + - When set, the filter level depends on the mode and reference frame used + to predict a block. + * - ``V4L2_VP9_LOOP_FILTER_FLAG_DELTA_UPDATE`` + - When set, the bitstream contains additional syntax elements that + specify which mode and reference frame deltas are to be updated. + .. raw:: latex \normalsize diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 1c617b42a944..115beadaf02d 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -930,6 +930,11 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: return "VP8 Profile"; case V4L2_CID_MPEG_VIDEO_VP9_PROFILE: return "VP9 Profile"; case V4L2_CID_MPEG_VIDEO_VP8_FRAME_HEADER: return "VP8 Frame Header"; + case V4L2_CID_MPEG_VIDEO_VP9_FRAME_DECODE_PARAMS: return "VP9 Frame Decode Parameters"; + case V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(0): return "VP9 Frame Context 0"; + case V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(1): return "VP9 Frame Context 1"; + case V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(2): return "VP9 Frame Context 2"; + case V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(3): return "VP9 Frame Context 3"; /* HEVC controls */ case V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP: return "HEVC I-Frame QP Value"; @@ -1403,6 +1408,15 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_MPEG_VIDEO_VP8_FRAME_HEADER: *type = V4L2_CTRL_TYPE_VP8_FRAME_HEADER; break; + case V4L2_CID_MPEG_VIDEO_VP9_FRAME_DECODE_PARAMS: + *type = V4L2_CTRL_TYPE_VP9_FRAME_DECODE_PARAMS; + break; + case V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(0): + case V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(1): + case V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(2): + case V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(3): + *type = V4L2_CTRL_TYPE_VP9_FRAME_CONTEXT; + break; case V4L2_CID_MPEG_VIDEO_HEVC_SPS: *type = V4L2_CTRL_TYPE_HEVC_SPS; break; @@ -1703,6 +1717,219 @@ static void std_log(const struct v4l2_ctrl *ctrl) 0; \ }) +static int +validate_vp9_lf_params(struct v4l2_vp9_loop_filter *lf) +{ + unsigned int i, j, k; + + if (lf->flags & + ~(V4L2_VP9_LOOP_FILTER_FLAG_DELTA_ENABLED | + V4L2_VP9_LOOP_FILTER_FLAG_DELTA_UPDATE)) + return -EINVAL; + + /* + * V4L2_VP9_LOOP_FILTER_FLAG_DELTA_ENABLED implies + * V4L2_VP9_LOOP_FILTER_FLAG_DELTA_UPDATE. + */ + if (lf->flags & V4L2_VP9_LOOP_FILTER_FLAG_DELTA_UPDATE && + !(lf->flags & V4L2_VP9_LOOP_FILTER_FLAG_DELTA_ENABLED)) + return -EINVAL; + + /* That all values are in the accepted range. */ + if (lf->level > GENMASK(5, 0)) + return -EINVAL; + + if (lf->sharpness > GENMASK(2, 0)) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(lf->ref_deltas); i++) { + if (lf->ref_deltas[i] < -63 || lf->ref_deltas[i] > 63) + return -EINVAL; + } + + for (i = 0; i < ARRAY_SIZE(lf->mode_deltas); i++) { + if (lf->mode_deltas[i] < -63 || lf->mode_deltas[i] > 63) + return -EINVAL; + } + + for (i = 0; i < ARRAY_SIZE(lf->level_lookup); i++) { + for (j = 0; j < ARRAY_SIZE(lf->level_lookup[0]); j++) { + for (k = 0; k < ARRAY_SIZE(lf->level_lookup[0][0]); k++) { + if (lf->level_lookup[i][j][k] > 63) + return -EINVAL; + } + } + } + + return 0; +} + +static int +validate_vp9_quant_params(struct v4l2_vp9_quantization *quant) +{ + if (quant->delta_q_y_dc < -15 || quant->delta_q_y_dc > 15 || + quant->delta_q_uv_dc < -15 || quant->delta_q_uv_dc > 15 || + quant->delta_q_uv_ac < -15 || quant->delta_q_uv_ac > 15) + return -EINVAL; + + memset(quant->padding, 0, sizeof(quant->padding)); + return 0; +} + +static int +validate_vp9_seg_params(struct v4l2_vp9_segmentation *seg) +{ + unsigned int i, j; + + if (seg->flags & + ~(V4L2_VP9_SEGMENTATION_FLAG_ENABLED | + V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP | + V4L2_VP9_SEGMENTATION_FLAG_TEMPORAL_UPDATE | + V4L2_VP9_SEGMENTATION_FLAG_UPDATE_DATA | + V4L2_VP9_SEGMENTATION_FLAG_ABS_OR_DELTA_UPDATE)) + return -EINVAL; + + /* + * V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP and + * V4L2_VP9_SEGMENTATION_FLAG_UPDATE_DATA imply + * V4L2_VP9_SEGMENTATION_FLAG_ENABLED. + */ + if ((seg->flags & + (V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP | + V4L2_VP9_SEGMENTATION_FLAG_UPDATE_DATA)) && + !(seg->flags & V4L2_VP9_SEGMENTATION_FLAG_ENABLED)) + return -EINVAL; + + /* + * V4L2_VP9_SEGMENTATION_FLAG_TEMPORAL_UPDATE implies + * V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP. + */ + if (seg->flags & V4L2_VP9_SEGMENTATION_FLAG_TEMPORAL_UPDATE && + !(seg->flags & V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP)) + return -EINVAL; + + /* + * V4L2_VP9_SEGMENTATION_FLAG_ABS_OR_DELTA_UPDATE implies + * V4L2_VP9_SEGMENTATION_FLAG_UPDATE_DATA. + */ + if (seg->flags & V4L2_VP9_SEGMENTATION_FLAG_ABS_OR_DELTA_UPDATE && + !(seg->flags & V4L2_VP9_SEGMENTATION_FLAG_UPDATE_DATA)) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(seg->feature_enabled); i++) { + if (seg->feature_enabled[i] & + ~(V4L2_VP9_SEGMENT_FEATURE_QP_DELTA | + V4L2_VP9_SEGMENT_FEATURE_LF | + V4L2_VP9_SEGMENT_FEATURE_REF_FRAME | + V4L2_VP9_SEGMENT_FEATURE_SKIP)) + return -EINVAL; + } + + for (i = 0; i < ARRAY_SIZE(seg->feature_data); i++) { + const int range[] = {255, 63, 3, 0}; + + for (j = 0; j < ARRAY_SIZE(seg->feature_data[j]); j++) { + if (seg->feature_data[i][j] < -range[j] || + seg->feature_data[i][j] > range[j]) + return -EINVAL; + } + } + + memset(seg->padding, 0, sizeof(seg->padding)); + return 0; +} + +static int +validate_vp9_frame_decode_params(struct v4l2_ctrl_vp9_frame_decode_params *dec_params) +{ + int ret; + + /* Make sure we're not passed invalid flags. */ + if (dec_params->flags & + ~(V4L2_VP9_FRAME_FLAG_KEY_FRAME | + V4L2_VP9_FRAME_FLAG_SHOW_FRAME | + V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT | + V4L2_VP9_FRAME_FLAG_INTRA_ONLY | + V4L2_VP9_FRAME_FLAG_ALLOW_HIGH_PREC_MV | + V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX | + V4L2_VP9_FRAME_FLAG_PARALLEL_DEC_MODE | + V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING | + V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING | + V4L2_VP9_FRAME_FLAG_COLOR_RANGE_FULL_SWING)) + return -EINVAL; + + /* + * The refresh context and error resilient flags are mutually exclusive. + * Same goes for parallel decoding and error resilient modes. + */ + if (dec_params->flags & V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT && + dec_params->flags & + (V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX | + V4L2_VP9_FRAME_FLAG_PARALLEL_DEC_MODE)) + return -EINVAL; + + if (dec_params->profile > V4L2_VP9_PROFILE_MAX) + return -EINVAL; + + if (dec_params->reset_frame_context > V4L2_VP9_RESET_FRAME_CTX_ALL) + return -EINVAL; + + if (dec_params->frame_context_idx >= V4L2_VP9_NUM_FRAME_CTX) + return -EINVAL; + + /* + * Profiles 0 and 1 only support 8-bit depth, profiles 2 and 3 only 10 + * and 12 bit depths. + */ + if ((dec_params->profile < 2 && dec_params->bit_depth != 8) || + (dec_params->profile >= 2 && + (dec_params->bit_depth != 10 && dec_params->bit_depth != 12))) + return -EINVAL; + + /* Profile 0 and 2 only accept YUV 4:2:0. */ + if ((dec_params->profile == 0 || dec_params->profile == 2) && + (!(dec_params->flags & V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING) || + !(dec_params->flags & V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING))) + return -EINVAL; + + /* Profile 1 and 3 only accept YUV 4:2:2, 4:4:0 and 4:4:4. */ + if ((dec_params->profile == 1 || dec_params->profile == 3) && + ((dec_params->flags & V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING) && + (dec_params->flags & V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING))) + return -EINVAL; + + if (dec_params->interpolation_filter > V4L2_VP9_INTERP_FILTER_SWITCHABLE) + return -EINVAL; + + /* + * According to the spec, tile_cols_log2 shall be less than or equal + * to 6. + */ + if (dec_params->tile_cols_log2 > 6) + return -EINVAL; + + if (dec_params->tx_mode > V4L2_VP9_TX_MODE_SELECT) + return -EINVAL; + + if (dec_params->reference_mode > V4L2_VP9_REF_MODE_SELECT) + return -EINVAL; + + ret = validate_vp9_lf_params(&dec_params->lf); + if (ret) + return ret; + + ret = validate_vp9_quant_params(&dec_params->quant); + if (ret) + return ret; + + ret = validate_vp9_seg_params(&dec_params->seg); + if (ret) + return ret; + + memset(dec_params->padding, 0, sizeof(dec_params->padding)); + return 0; +} + /* Validate a new control */ #define zero_padding(s) \ @@ -1799,6 +2026,12 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx, zero_padding(p_vp8_frame_header->coder_state); break; + case V4L2_CTRL_TYPE_VP9_FRAME_DECODE_PARAMS: + return validate_vp9_frame_decode_params(p); + + case V4L2_CTRL_TYPE_VP9_FRAME_CONTEXT: + break; + case V4L2_CTRL_TYPE_HEVC_SPS: p_hevc_sps = p; @@ -2542,6 +2775,12 @@ static struct v4l2_ctrl *v4l2_ctrl_new(struct v4l2_ctrl_handler *hdl, case V4L2_CTRL_TYPE_VP8_FRAME_HEADER: elem_size = sizeof(struct v4l2_ctrl_vp8_frame_header); break; + case V4L2_CTRL_TYPE_VP9_FRAME_CONTEXT: + elem_size = sizeof(struct v4l2_ctrl_vp9_frame_ctx); + break; + case V4L2_CTRL_TYPE_VP9_FRAME_DECODE_PARAMS: + elem_size = sizeof(struct v4l2_ctrl_vp9_frame_decode_params); + break; case V4L2_CTRL_TYPE_HEVC_SPS: elem_size = sizeof(struct v4l2_ctrl_hevc_sps); break; diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 2322f08a98be..4fe77ad917c8 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1423,6 +1423,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_VP8: descr = "VP8"; break; case V4L2_PIX_FMT_VP8_FRAME: descr = "VP8 Frame"; break; case V4L2_PIX_FMT_VP9: descr = "VP9"; break; + case V4L2_PIX_FMT_VP9_FRAME: descr = "VP9 Frame"; break; case V4L2_PIX_FMT_HEVC: descr = "HEVC"; break; /* aka H.265 */ case V4L2_PIX_FMT_HEVC_SLICE: descr = "HEVC Parsed Slice Data"; break; case V4L2_PIX_FMT_FWHT: descr = "FWHT"; break; /* used in vicodec */ diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index 757a713bad41..2de8290f9f11 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -21,6 +21,7 @@ #include #include #include +#include #include /* forward references */ diff --git a/include/media/vp9-ctrls.h b/include/media/vp9-ctrls.h new file mode 100644 index 000000000000..0cdea8a18b72 --- /dev/null +++ b/include/media/vp9-ctrls.h @@ -0,0 +1,485 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * These are the VP9 state controls for use with stateless VP9 + * codec drivers. + * + * It turns out that these structs are not stable yet and will undergo + * more changes. So keep them private until they are stable and ready to + * become part of the official public API. + */ + +#ifndef _VP9_CTRLS_H_ +#define _VP9_CTRLS_H_ + +#include + +#define V4L2_PIX_FMT_VP9_FRAME v4l2_fourcc('V', 'P', '9', 'F') + +#define V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(i) (V4L2_CID_MPEG_BASE + 4000 + (i)) +#define V4L2_CID_MPEG_VIDEO_VP9_FRAME_DECODE_PARAMS (V4L2_CID_MPEG_BASE + 4004) +#define V4L2_CTRL_TYPE_VP9_FRAME_CONTEXT 0x400 +#define V4L2_CTRL_TYPE_VP9_FRAME_DECODE_PARAMS 0x404 + +/** + * enum v4l2_vp9_loop_filter_flags - VP9 loop filter flags + * + * @V4L2_VP9_LOOP_FILTER_FLAG_DELTA_ENABLED: the filter level depends on + * the mode and reference frame used + * to predict a block + * @V4L2_VP9_LOOP_FILTER_FLAG_DELTA_UPDATE: the bitstream contains additional + * syntax elements that specify which + * mode and reference frame deltas + * are to be updated + * + * Those are the flags you should pass to &v4l2_vp9_loop_filter.flags. See + * section '7.2.8 Loop filter semantics' of the VP9 specification for more + * details. + */ +enum v4l2_vp9_loop_filter_flags { + V4L2_VP9_LOOP_FILTER_FLAG_DELTA_ENABLED = 1 << 0, + V4L2_VP9_LOOP_FILTER_FLAG_DELTA_UPDATE = 1 << 1, +}; + +/** + * struct v4l2_vp9_loop_filter - VP9 loop filter parameters + * + * @flags: combination of V4L2_VP9_LOOP_FILTER_FLAG_* flags + * @level: indicates the loop filter strength + * @sharpness: indicates the sharpness level + * @ref_deltas: contains the adjustment needed for the filter level based on + * the chosen reference frame + * @mode_deltas: contains the adjustment needed for the filter level based on + * the chosen mode + * @level_lookup: level lookup table + * + * This structure contains all loop filter related parameters. See sections + * '7.2.8 Loop filter semantics' and '8.8.1 Loop filter frame init process' + * of the VP9 specification for more details. + */ +struct v4l2_vp9_loop_filter { + __u8 flags; + __u8 level; + __u8 sharpness; + __s8 ref_deltas[4]; + __s8 mode_deltas[2]; + __u8 level_lookup[8][4][2]; +}; + +/** + * struct v4l2_vp9_quantization - VP9 quantization parameters + * + * @base_q_idx: indicates the base frame qindex + * @delta_q_y_dc: indicates the Y DC quantizer relative to base_q_idx + * @delta_q_uv_dc: indicates the UV DC quantizer relative to base_q_idx + * @delta_q_uv_ac indicates the UV AC quantizer relative to base_q_idx + * @padding: padding bytes to align things on 64 bits. Must be set to 0 + * + * Encodes the quantization parameters. See section '7.2.9 Quantization params + * syntax' of the VP9 specification for more details. + */ +struct v4l2_vp9_quantization { + __u8 base_q_idx; + __s8 delta_q_y_dc; + __s8 delta_q_uv_dc; + __s8 delta_q_uv_ac; + __u8 padding[4]; +}; + +/** + * enum v4l2_vp9_segmentation_flags - VP9 segmentation flags + * + * @V4L2_VP9_SEGMENTATION_FLAG_ENABLED: indicates that this frame makes use of + * the segmentation tool + * @V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP: indicates that the segmentation map + * should be updated during the + * decoding of this frame + * @V4L2_VP9_SEGMENTATION_FLAG_TEMPORAL_UPDATE: indicates that the updates to + * the segmentation map are coded + * relative to the existing + * segmentation map + * @V4L2_VP9_SEGMENTATION_FLAG_UPDATE_DATA: indicates that new parameters are + * about to be specified for each + * segment + * @V4L2_VP9_SEGMENTATION_FLAG_ABS_OR_DELTA_UPDATE: indicates that the + * segmentation parameters + * represent the actual values + * to be used + * + * Those are the flags you should pass to &v4l2_vp9_segmentation.flags. See + * section '7.2.10 Segmentation params syntax' of the VP9 specification for + * more details. + */ +enum v4l2_vp9_segmentation_flags { + V4L2_VP9_SEGMENTATION_FLAG_ENABLED = 1 << 0, + V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP = 1 << 1, + V4L2_VP9_SEGMENTATION_FLAG_TEMPORAL_UPDATE = 1 << 2, + V4L2_VP9_SEGMENTATION_FLAG_UPDATE_DATA = 1 << 3, + V4L2_VP9_SEGMENTATION_FLAG_ABS_OR_DELTA_UPDATE = 1 << 4, +}; + +#define V4L2_VP9_SEGMENT_FEATURE_ENABLED(id) (1 << (id)) +#define V4L2_VP9_SEGMENT_FEATURE_ENABLED_MASK 0xf + +/** + * enum v4l2_vp9_segment_feature - VP9 segment feature IDs + * + * @V4L2_VP9_SEGMENT_FEATURE_QP_DELTA: QP delta segment feature + * @V4L2_VP9_SEGMENT_FEATURE_LF: loop filter segment feature + * @V4L2_VP9_SEGMENT_FEATURE_REF_FRAME: reference frame segment feature + * @V4L2_VP9_SEGMENT_FEATURE_SKIP: skip segment feature + * @V4L2_VP9_SEGMENT_FEATURE_CNT: number of segment features + * + * Segment feature IDs. See section '7.2.10 Segmentation params syntax' of the + * VP9 specification for more details. + */ +enum v4l2_vp9_segment_feature { + V4L2_VP9_SEGMENT_FEATURE_QP_DELTA, + V4L2_VP9_SEGMENT_FEATURE_LF, + V4L2_VP9_SEGMENT_FEATURE_REF_FRAME, + V4L2_VP9_SEGMENT_FEATURE_SKIP, + V4L2_VP9_SEGMENT_FEATURE_CNT, +}; + +/** + * struct v4l2_vp9_segmentation - VP9 segmentation parameters + * + * @flags: combination of V4L2_VP9_SEGMENTATION_FLAG_* flags + * @tree_probs: specifies the probability values to be used when + * decoding a Segment-ID. See '5.15. Segmentation map' + * section of the VP9 specification for more details. + * @pred_prob: specifies the probability values to be used when decoding a + * Predicted-Segment-ID. See '6.4.14. Get segment id syntax' + * section of :ref:`vp9` for more details.. + * @padding: padding used to make things aligned on 64 bits. Shall be zero + * filled + * @feature_enabled: bitmask defining which features are enabled in each + * segment + * @feature_data: data attached to each feature. Data entry is only valid if + * the feature is enabled + * + * Encodes the quantization parameters. See section '7.2.10 Segmentation + * params syntax' of the VP9 specification for more details. + */ +struct v4l2_vp9_segmentation { + __u8 flags; + __u8 tree_probs[7]; + __u8 pred_probs[3]; + __u8 padding[5]; + __u8 feature_enabled[8]; + __s16 feature_data[8][4]; +}; + +/** + * enum v4l2_vp9_intra_prediction_mode - VP9 Intra prediction modes + * + * @V4L2_VP9_INTRA_PRED_DC: DC intra prediction + * @V4L2_VP9_INTRA_PRED_MODE_V: vertical intra prediction + * @V4L2_VP9_INTRA_PRED_MODE_H: horizontal intra prediction + * @V4L2_VP9_INTRA_PRED_MODE_D45: D45 intra prediction + * @V4L2_VP9_INTRA_PRED_MODE_D135: D135 intra prediction + * @V4L2_VP9_INTRA_PRED_MODE_D117: D117 intra prediction + * @V4L2_VP9_INTRA_PRED_MODE_D153: D153 intra prediction + * @V4L2_VP9_INTRA_PRED_MODE_D207: D207 intra prediction + * @V4L2_VP9_INTRA_PRED_MODE_D63: D63 intra prediction + * @V4L2_VP9_INTRA_PRED_MODE_TM: True Motion intra prediction + * + * See section '7.4.5 Intra frame mode info semantics' for more details. + */ +enum v4l2_vp9_intra_prediction_mode { + V4L2_VP9_INTRA_PRED_MODE_DC, + V4L2_VP9_INTRA_PRED_MODE_V, + V4L2_VP9_INTRA_PRED_MODE_H, + V4L2_VP9_INTRA_PRED_MODE_D45, + V4L2_VP9_INTRA_PRED_MODE_D135, + V4L2_VP9_INTRA_PRED_MODE_D117, + V4L2_VP9_INTRA_PRED_MODE_D153, + V4L2_VP9_INTRA_PRED_MODE_D207, + V4L2_VP9_INTRA_PRED_MODE_D63, + V4L2_VP9_INTRA_PRED_MODE_TM, +}; + +/** + * struct v4l2_vp9_mv_probabilities - VP9 Motion vector probabilities + * @joint: motion vector joint probabilities + * @sign: motion vector sign probabilities + * @class: motion vector class probabilities + * @class0_bit: motion vector class0 bit probabilities + * @bits: motion vector bits probabilities + * @class0_fr: motion vector class0 fractional bit probabilities + * @fr: motion vector fractional bit probabilities + * @class0_hp: motion vector class0 high precision fractional bit probabilities + * @hp: motion vector high precision fractional bit probabilities + */ +struct v4l2_vp9_mv_probabilities { + __u8 joint[3]; + __u8 sign[2]; + __u8 class[2][10]; + __u8 class0_bit[2]; + __u8 bits[2][10]; + __u8 class0_fr[2][2][3]; + __u8 fr[2][3]; + __u8 class0_hp[2]; + __u8 hp[2]; +}; + +/** + * struct v4l2_vp9_probabilities - VP9 Probabilities + * + * @tx8: TX 8x8 probabilities + * @tx16: TX 16x16 probabilities + * @tx32: TX 32x32 probabilities + * @coef: coefficient probabilities + * @skip: skip probabilities + * @inter_mode: inter mode probabilities + * @interp_filter: interpolation filter probabilities + * @is_inter: is inter-block probabilities + * @comp_mode: compound prediction mode probabilities + * @single_ref: single ref probabilities + * @comp_ref: compound ref probabilities + * @y_mode: Y prediction mode probabilities + * @uv_mode: UV prediction mode probabilities + * @partition: partition probabilities + * @mv: motion vector probabilities + * + * Structure containing most VP9 probabilities. See the VP9 specification + * for more details. + */ +struct v4l2_vp9_probabilities { + __u8 tx8[2][1]; + __u8 tx16[2][2]; + __u8 tx32[2][3]; + __u8 coef[4][2][2][6][6][3]; + __u8 skip[3]; + __u8 inter_mode[7][3]; + __u8 interp_filter[4][2]; + __u8 is_inter[4]; + __u8 comp_mode[5]; + __u8 single_ref[5][2]; + __u8 comp_ref[5]; + __u8 y_mode[4][9]; + __u8 uv_mode[10][9]; + __u8 partition[16][3]; + + struct v4l2_vp9_mv_probabilities mv; +}; + +/** + * enum v4l2_vp9_reset_frame_context - Valid values for + * &v4l2_ctrl_vp9_frame_decode_params->reset_frame_context + * + * @V4L2_VP9_RESET_FRAME_CTX_NONE: don't reset any frame context + * @V4L2_VP9_RESET_FRAME_CTX_SPEC: reset the frame context pointed by + * &v4l2_ctrl_vp9_frame_decode_params.frame_context_idx + * @V4L2_VP9_RESET_FRAME_CTX_ALL: reset all frame contexts + * + * See section '7.2 Uncompressed header semantics' of the VP9 specification + * for more details. + */ +enum v4l2_vp9_reset_frame_context { + V4L2_VP9_RESET_FRAME_CTX_NONE, + V4L2_VP9_RESET_FRAME_CTX_SPEC, + V4L2_VP9_RESET_FRAME_CTX_ALL, +}; + +/** + * enum v4l2_vp9_interpolation_filter - VP9 interpolation filter types + * + * @V4L2_VP9_INTERP_FILTER_8TAP: height tap filter + * @V4L2_VP9_INTERP_FILTER_8TAP_SMOOTH: height tap smooth filter + * @V4L2_VP9_INTERP_FILTER_8TAP_SHARP: height tap sharp filter + * @V4L2_VP9_INTERP_FILTER_BILINEAR: bilinear filter + * @V4L2_VP9_INTERP_FILTER_SWITCHABLE: filter selection is signaled at the + * block level + * + * See section '7.2.7 Interpolation filter semantics' of the VP9 specification + * for more details. + */ +enum v4l2_vp9_interpolation_filter { + V4L2_VP9_INTERP_FILTER_8TAP, + V4L2_VP9_INTERP_FILTER_8TAP_SMOOTH, + V4L2_VP9_INTERP_FILTER_8TAP_SHARP, + V4L2_VP9_INTERP_FILTER_BILINEAR, + V4L2_VP9_INTERP_FILTER_SWITCHABLE, +}; + +/** + * enum v4l2_vp9_reference_mode - VP9 reference modes + * + * @V4L2_VP9_REF_MODE_SINGLE: indicates that all the inter blocks use only a + * single reference frame to generate motion + * compensated prediction + * @V4L2_VP9_REF_MODE_COMPOUND: requires all the inter blocks to use compound + * mode. Single reference frame prediction is not + * allowed + * @V4L2_VP9_REF_MODE_SELECT: allows each individual inter block to select + * between single and compound prediction modes + * + * See section '7.3.6 Frame reference mode semantics' of the VP9 specification + * for more details. + */ +enum v4l2_vp9_reference_mode { + V4L2_VP9_REF_MODE_SINGLE, + V4L2_VP9_REF_MODE_COMPOUND, + V4L2_VP9_REF_MODE_SELECT, +}; + +/** + * enum v4l2_vp9_tx_mode - VP9 TX modes + * + * @V4L2_VP9_TX_MODE_ONLY_4X4: transform size is 4x4 + * @V4L2_VP9_TX_MODE_ALLOW_8X8: transform size can be up to 8x8 + * @V4L2_VP9_TX_MODE_ALLOW_16X16: transform size can be up to 16x16 + * @V4L2_VP9_TX_MODE_ALLOW_32X32: transform size can be up to 32x32 + * @V4L2_VP9_TX_MODE_SELECT: bitstream contains transform size for each block + * + * See section '7.3.1 Tx mode semantics' of the VP9 specification for more + * details. + */ +enum v4l2_vp9_tx_mode { + V4L2_VP9_TX_MODE_ONLY_4X4, + V4L2_VP9_TX_MODE_ALLOW_8X8, + V4L2_VP9_TX_MODE_ALLOW_16X16, + V4L2_VP9_TX_MODE_ALLOW_32X32, + V4L2_VP9_TX_MODE_SELECT, +}; + +/** + * enum v4l2_vp9_ref_id - VP9 Reference frame IDs + * + * @V4L2_REF_ID_LAST: last reference frame + * @V4L2_REF_ID_GOLDEN: golden reference frame + * @V4L2_REF_ID_ALTREF: alternative reference frame + * @V4L2_REF_ID_CNT: number of reference frames + * + * See section '7.4.12 Ref frames semantics' of the VP9 specification for more + * details. + */ +enum v4l2_vp9_ref_id { + V4L2_REF_ID_LAST, + V4L2_REF_ID_GOLDEN, + V4L2_REF_ID_ALTREF, + V4L2_REF_ID_CNT, +}; + +/** + * enum v4l2_vp9_frame_flags - VP9 frame flags + * @V4L2_VP9_FRAME_FLAG_KEY_FRAME: the frame is a key frame + * @V4L2_VP9_FRAME_FLAG_SHOW_FRAME: the frame should be displayed + * @V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT: the decoding should be error resilient + * @V4L2_VP9_FRAME_FLAG_INTRA_ONLY: the frame does not reference other frames + * @V4L2_VP9_FRAME_FLAG_ALLOW_HIGH_PREC_MV: the frame might can high precision + * motion vectors + * @V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX: frame context should be updated + * after decoding + * @V4L2_VP9_FRAME_FLAG_PARALLEL_DEC_MODE: parallel decoding is used + * @V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING: vertical subsampling is enabled + * @V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING: horizontal subsampling is enabled + * @V4L2_VP9_FRAME_FLAG_COLOR_RANGE_FULL_SWING: full UV range is used + * + * Check the VP9 specification for more details. + */ +enum v4l2_vp9_frame_flags { + V4L2_VP9_FRAME_FLAG_KEY_FRAME = 1 << 0, + V4L2_VP9_FRAME_FLAG_SHOW_FRAME = 1 << 1, + V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT = 1 << 2, + V4L2_VP9_FRAME_FLAG_INTRA_ONLY = 1 << 3, + V4L2_VP9_FRAME_FLAG_ALLOW_HIGH_PREC_MV = 1 << 4, + V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX = 1 << 5, + V4L2_VP9_FRAME_FLAG_PARALLEL_DEC_MODE = 1 << 6, + V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING = 1 << 7, + V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING = 1 << 8, + V4L2_VP9_FRAME_FLAG_COLOR_RANGE_FULL_SWING = 1 << 9, +}; + +#define V4L2_VP9_PROFILE_MAX 3 + +/** + * struct v4l2_ctrl_vp9_frame_decode_params - VP9 frame decoding control + * + * @flags: combination of V4L2_VP9_FRAME_FLAG_* flags + * @compressed_header_size: compressed header size in bytes + * @uncompressed_header_size: uncompressed header size in bytes + * @profile: VP9 profile. Can be 0, 1, 2 or 3 + * @reset_frame_context: specifies whether the frame context should be reset + * to default values. See &v4l2_vp9_reset_frame_context + * for more details + * @frame_context_idx: frame context that should be used/updated + * @bit_depth: bits per components. Can be 8, 10 or 12. Note that not all + * profiles support 10 and/or 12 bits depths + * @interpolation_filter: specifies the filter selection used for performing + * inter prediction. See &v4l2_vp9_interpolation_filter + * for more details + * @tile_cols_log2: specifies the base 2 logarithm of the width of each tile + * (where the width is measured in units of 8x8 blocks). + * Shall be less than or equal to 6 + * @tile_rows_log2: specifies the base 2 logarithm of the height of each tile + * (where the height is measured in units of 8x8 blocks) + * @tx_mode: specifies the TX mode. See &v4l2_vp9_tx_mode for more details + * @reference_mode: specifies the type of inter prediction to be used. See + * &v4l2_vp9_reference_mode for more details + * @padding: needed to make this struct 64 bit aligned. Shall be filled with + * zeros + * @frame_width_minus_1: add 1 to it and you'll get the frame width expressed + * in pixels + * @frame_height_minus_1: add 1 to it and you'll get the frame height expressed + * in pixels + * @frame_width_minus_1: add 1 to it and you'll get the expected render width + * expressed in pixels. This is not used during the + * decoding process but might be used by HW scalers to + * prepare a frame that's ready for scanout + * @frame_height_minus_1: add 1 to it and you'll get the expected render height + * expressed in pixels. This is not used during the + * decoding process but might be used by HW scalers to + * prepare a frame that's ready for scanout + * @refs: array of reference frames. See &v4l2_vp9_ref_id for more details + * @lf: loop filter parameters. See &v4l2_vp9_loop_filter for more details + * @quant: quantization parameters. See &v4l2_vp9_quantization for more details + * @seg: segmentation parameters. See &v4l2_vp9_segmentation for more details + * @probs: probabilities. See &v4l2_vp9_probabilities for more details + */ +struct v4l2_ctrl_vp9_frame_decode_params { + __u32 flags; + __u16 compressed_header_size; + __u16 uncompressed_header_size; + __u8 profile; + __u8 reset_frame_context; + __u8 frame_context_idx; + __u8 bit_depth; + __u8 interpolation_filter; + __u8 tile_cols_log2; + __u8 tile_rows_log2; + __u8 tx_mode; + __u8 reference_mode; + __u8 padding[6]; + __u16 frame_width_minus_1; + __u16 frame_height_minus_1; + __u16 render_width_minus_1; + __u16 render_height_minus_1; + __u64 refs[V4L2_REF_ID_CNT]; + struct v4l2_vp9_loop_filter lf; + struct v4l2_vp9_quantization quant; + struct v4l2_vp9_segmentation seg; + struct v4l2_vp9_probabilities probs; +}; + +#define V4L2_VP9_NUM_FRAME_CTX 4 + +/** + * struct v4l2_ctrl_vp9_frame_ctx - VP9 frame context control + * + * @probs: VP9 probabilities + * + * This control is accessed in both direction. The user should initialize the + * 4 contexts with default values just after starting the stream. Then before + * decoding a frame it should query the current frame context (the one passed + * through &v4l2_ctrl_vp9_frame_decode_params.frame_context_idx) to initialize + * &v4l2_ctrl_vp9_frame_decode_params.probs. The probs are then adjusted based + * on the bitstream info and passed to the kernel. The codec should update + * the frame context after the frame has been decoded, so that next time + * userspace query this context it contains the updated probabilities. + */ +struct v4l2_ctrl_vp9_frame_ctx { + struct v4l2_vp9_probabilities probs; +}; + +#endif /* _VP9_CTRLS_H_ */ From patchwork Mon May 18 17:40:11 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Ezequiel Garcia X-Patchwork-Id: 11555965 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 87E3614B7 for ; Mon, 18 May 2020 17:40:48 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 60F3320829 for ; Mon, 18 May 2020 17:40:48 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729145AbgERRkq (ORCPT ); Mon, 18 May 2020 13:40:46 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:59630 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729142AbgERRkq (ORCPT ); Mon, 18 May 2020 13:40:46 -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 9464AC061A0C; Mon, 18 May 2020 10:40:45 -0700 (PDT) Received: from [127.0.0.1] (localhost [127.0.0.1]) (Authenticated sender: ezequiel) with ESMTPSA id 32E522A10C0 From: Ezequiel Garcia To: linux-media@vger.kernel.org, linux-rockchip@lists.infradead.org, linux-kernel@vger.kernel.org Cc: Tomasz Figa , kernel@collabora.com, Jonas Karlman , Heiko Stuebner , Hans Verkuil , Alexandre Courbot , Jeffrey Kardatzke , gustavo.padovan@collabora.com, Nicolas Dufresne , Boris Brezillon , Ezequiel Garcia Subject: [PATCH 3/3] media: rkvdec: Add the VP9 backend Date: Mon, 18 May 2020 14:40:11 -0300 Message-Id: <20200518174011.15543-4-ezequiel@collabora.com> X-Mailer: git-send-email 2.26.0.rc2 In-Reply-To: <20200518174011.15543-1-ezequiel@collabora.com> References: <20200518174011.15543-1-ezequiel@collabora.com> MIME-Version: 1.0 Sender: linux-media-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-media@vger.kernel.org From: Boris Brezillon The Rockchip VDEC supports VP9 profile 0 up to 4096x2304@30fps. Add a backend for this new format. Signed-off-by: Boris Brezillon Signed-off-by: Ezequiel Garcia --- drivers/staging/media/rkvdec/Makefile | 2 +- drivers/staging/media/rkvdec/rkvdec-vp9.c | 1577 +++++++++++++++++++++ drivers/staging/media/rkvdec/rkvdec.c | 56 +- drivers/staging/media/rkvdec/rkvdec.h | 6 + 4 files changed, 1637 insertions(+), 4 deletions(-) create mode 100644 drivers/staging/media/rkvdec/rkvdec-vp9.c diff --git a/drivers/staging/media/rkvdec/Makefile b/drivers/staging/media/rkvdec/Makefile index c08fed0a39f9..cb86b429cfaa 100644 --- a/drivers/staging/media/rkvdec/Makefile +++ b/drivers/staging/media/rkvdec/Makefile @@ -1,3 +1,3 @@ obj-$(CONFIG_VIDEO_ROCKCHIP_VDEC) += rockchip-vdec.o -rockchip-vdec-y += rkvdec.o rkvdec-h264.o +rockchip-vdec-y += rkvdec.o rkvdec-h264.o rkvdec-vp9.o diff --git a/drivers/staging/media/rkvdec/rkvdec-vp9.c b/drivers/staging/media/rkvdec/rkvdec-vp9.c new file mode 100644 index 000000000000..37d0ea4e3570 --- /dev/null +++ b/drivers/staging/media/rkvdec/rkvdec-vp9.c @@ -0,0 +1,1577 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Rockchip Video Decoder VP9 backend + * + * Copyright (C) 2019 Collabora, Ltd. + * Boris Brezillon + * + * Copyright (C) 2016 Rockchip Electronics Co., Ltd. + * Alpha Lin + */ + +#include +#include +#include + +#include "rkvdec.h" +#include "rkvdec-regs.h" + +#define RKVDEC_VP9_PROBE_SIZE 4864 +#define RKVDEC_VP9_COUNT_SIZE 13232 +#define RKVDEC_VP9_MAX_SEGMAP_SIZE 73728 + +struct rkvdec_vp9_intra_mode_probs { + u8 y_mode[105]; + u8 uv_mode[23]; +}; + +struct rkvdec_vp9_intra_only_frame_probs { + u8 coef_intra[4][2][128]; + struct rkvdec_vp9_intra_mode_probs intra_mode[10]; +}; + +struct rkvdec_vp9_inter_frame_probs { + u8 y_mode[4][9]; + u8 comp_mode[5]; + u8 comp_ref[5]; + u8 single_ref[5][2]; + u8 inter_mode[7][3]; + u8 interp_filter[4][2]; + u8 padding0[11]; + u8 coef[2][4][2][128]; + u8 uv_mode_0_2[3][9]; + u8 padding1[5]; + u8 uv_mode_3_5[3][9]; + u8 padding2[5]; + u8 uv_mode_6_8[3][9]; + u8 padding3[5]; + u8 uv_mode_9[9]; + u8 padding4[7]; + u8 padding5[16]; + struct { + u8 joint[3]; + u8 sign[2]; + u8 class[2][10]; + u8 class0_bit[2]; + u8 bits[2][10]; + u8 class0_fr[2][2][3]; + u8 fr[2][3]; + u8 class0_hp[2]; + u8 hp[2]; + } mv; +}; + +struct rkvdec_vp9_probs { + u8 partition[16][3]; + u8 pred[3]; + u8 tree[7]; + u8 skip[3]; + u8 tx32[2][3]; + u8 tx16[2][2]; + u8 tx8[2][1]; + u8 is_inter[4]; + /* 128 bit alignment */ + u8 padding0[3]; + union { + struct rkvdec_vp9_inter_frame_probs inter; + struct rkvdec_vp9_intra_only_frame_probs intra_only; + }; +}; + +/* Data structure describing auxiliary buffer format. */ +struct rkvdec_vp9_priv_tbl { + struct rkvdec_vp9_probs probs; + u8 segmap[2][RKVDEC_VP9_MAX_SEGMAP_SIZE]; +}; + +struct rkvdec_vp9_refs_counts { + u32 eob[2]; + u32 coeff[3]; +}; + +struct rkvdec_vp9_inter_frame_symbol_counts { + u32 partition[16][4]; + u32 skip[3][2]; + u32 inter[4][2]; + u32 tx32p[2][4]; + u32 tx16p[2][4]; + u32 tx8p[2][2]; + u32 y_mode[4][10]; + u32 uv_mode[10][10]; + u32 comp[5][2]; + u32 comp_ref[5][2]; + u32 single_ref[5][2][2]; + u32 mv_mode[7][4]; + u32 filter[4][3]; + u32 mv_joint[4]; + u32 sign[2][2]; + /* add 1 element for align */ + u32 classes[2][11 + 1]; + u32 class0[2][2]; + u32 bits[2][10][2]; + u32 class0_fp[2][2][4]; + u32 fp[2][4]; + u32 class0_hp[2][2]; + u32 hp[2][2]; + struct rkvdec_vp9_refs_counts ref_cnt[2][4][2][6][6]; +}; + +struct rkvdec_vp9_intra_frame_symbol_counts { + u32 partition[4][4][4]; + u32 skip[3][2]; + u32 intra[4][2]; + u32 tx32p[2][4]; + u32 tx16p[2][4]; + u32 tx8p[2][2]; + struct rkvdec_vp9_refs_counts ref_cnt[2][4][2][6][6]; +}; + +struct rkvdec_vp9_run { + struct rkvdec_run base; + const struct v4l2_ctrl_vp9_frame_decode_params *decode_params; +}; + +struct rkvdec_vp9_frame_info { + u32 valid : 1; + u32 segmapid : 1; + u32 frame_context_idx : 2; + u32 reference_mode : 2; + u32 tx_mode : 3; + u32 interpolation_filter : 3; + u32 flags; + u64 timestamp; + struct v4l2_vp9_segmentation seg; + struct v4l2_vp9_loop_filter lf; +}; + +struct rkvdec_vp9_ctx { + struct rkvdec_aux_buf priv_tbl; + struct rkvdec_aux_buf count_tbl; + struct v4l2_ctrl_vp9_frame_ctx frame_context; + struct rkvdec_vp9_frame_info cur; + struct rkvdec_vp9_frame_info last; +}; + +static u32 rkvdec_fastdiv(u32 dividend, u16 divisor) +{ +#define DIV_INV(d) (u32)(((1ULL << 32) + ((d) - 1)) / (d)) +#define DIVS_INV(d0, d1, d2, d3, d4, d5, d6, d7, d8, d9) \ + DIV_INV(d0), DIV_INV(d1), DIV_INV(d2), DIV_INV(d3), \ + DIV_INV(d4), DIV_INV(d5), DIV_INV(d6), DIV_INV(d7), \ + DIV_INV(d8), DIV_INV(d9) + + static const u32 inv[] = { + DIV_INV(2), DIV_INV(3), DIV_INV(4), DIV_INV(5), + DIV_INV(6), DIV_INV(7), DIV_INV(8), DIV_INV(9), + DIVS_INV(10, 11, 12, 13, 14, 15, 16, 17, 18, 19), + DIVS_INV(20, 21, 22, 23, 24, 25, 26, 27, 28, 29), + DIVS_INV(30, 31, 32, 33, 34, 35, 36, 37, 38, 39), + DIVS_INV(40, 41, 42, 43, 44, 45, 46, 47, 48, 49), + DIVS_INV(50, 51, 52, 53, 54, 55, 56, 57, 58, 59), + DIVS_INV(60, 61, 62, 63, 64, 65, 66, 67, 68, 69), + DIVS_INV(70, 71, 72, 73, 74, 75, 76, 77, 78, 79), + DIVS_INV(80, 81, 82, 83, 84, 85, 86, 87, 88, 89), + DIVS_INV(90, 91, 92, 93, 94, 95, 96, 97, 98, 99), + DIVS_INV(100, 101, 102, 103, 104, 105, 106, 107, 108, 109), + DIVS_INV(110, 111, 112, 113, 114, 115, 116, 117, 118, 119), + DIVS_INV(120, 121, 122, 123, 124, 125, 126, 127, 128, 129), + DIVS_INV(130, 131, 132, 133, 134, 135, 136, 137, 138, 139), + DIVS_INV(140, 141, 142, 143, 144, 145, 146, 147, 148, 149), + DIVS_INV(150, 151, 152, 153, 154, 155, 156, 157, 158, 159), + DIVS_INV(160, 161, 162, 163, 164, 165, 166, 167, 168, 169), + DIVS_INV(170, 171, 172, 173, 174, 175, 176, 177, 178, 179), + DIVS_INV(180, 181, 182, 183, 184, 185, 186, 187, 188, 189), + DIVS_INV(190, 191, 192, 193, 194, 195, 196, 197, 198, 199), + DIVS_INV(200, 201, 202, 203, 204, 205, 206, 207, 208, 209), + DIVS_INV(210, 211, 212, 213, 214, 215, 216, 217, 218, 219), + DIVS_INV(220, 221, 222, 223, 224, 225, 226, 227, 228, 229), + DIVS_INV(230, 231, 232, 233, 234, 235, 236, 237, 238, 239), + DIVS_INV(240, 241, 242, 243, 244, 245, 246, 247, 248, 249), + DIV_INV(250), DIV_INV(251), DIV_INV(252), DIV_INV(253), + DIV_INV(254), DIV_INV(255), DIV_INV(256), + }; + + if (divisor == 0) + return 0; + else if (divisor == 1) + return dividend; + + if (WARN_ON(divisor - 2 >= ARRAY_SIZE(inv))) + return dividend; + + return ((u64)dividend * inv[divisor - 2]) >> 32; +} + +static const u8 vp9_kf_y_mode_prob[10][10][9] = { + { + /* above = dc */ + { 137, 30, 42, 148, 151, 207, 70, 52, 91 },/*left = dc */ + { 92, 45, 102, 136, 116, 180, 74, 90, 100 },/*left = v */ + { 73, 32, 19, 187, 222, 215, 46, 34, 100 },/*left = h */ + { 91, 30, 32, 116, 121, 186, 93, 86, 94 },/*left = d45 */ + { 72, 35, 36, 149, 68, 206, 68, 63, 105 },/*left = d135*/ + { 73, 31, 28, 138, 57, 124, 55, 122, 151 },/*left = d117*/ + { 67, 23, 21, 140, 126, 197, 40, 37, 171 },/*left = d153*/ + { 86, 27, 28, 128, 154, 212, 45, 43, 53 },/*left = d207*/ + { 74, 32, 27, 107, 86, 160, 63, 134, 102 },/*left = d63 */ + { 59, 67, 44, 140, 161, 202, 78, 67, 119 } /*left = tm */ + }, { /* above = v */ + { 63, 36, 126, 146, 123, 158, 60, 90, 96 },/*left = dc */ + { 43, 46, 168, 134, 107, 128, 69, 142, 92 },/*left = v */ + { 44, 29, 68, 159, 201, 177, 50, 57, 77 },/*left = h */ + { 58, 38, 76, 114, 97, 172, 78, 133, 92 },/*left = d45 */ + { 46, 41, 76, 140, 63, 184, 69, 112, 57 },/*left = d135*/ + { 38, 32, 85, 140, 46, 112, 54, 151, 133 },/*left = d117*/ + { 39, 27, 61, 131, 110, 175, 44, 75, 136 },/*left = d153*/ + { 52, 30, 74, 113, 130, 175, 51, 64, 58 },/*left = d207*/ + { 47, 35, 80, 100, 74, 143, 64, 163, 74 },/*left = d63 */ + { 36, 61, 116, 114, 128, 162, 80, 125, 82 } /*left = tm */ + }, { /* above = h */ + { 82, 26, 26, 171, 208, 204, 44, 32, 105 },/*left = dc */ + { 55, 44, 68, 166, 179, 192, 57, 57, 108 },/*left = v */ + { 42, 26, 11, 199, 241, 228, 23, 15, 85 },/*left = h */ + { 68, 42, 19, 131, 160, 199, 55, 52, 83 },/*left = d45 */ + { 58, 50, 25, 139, 115, 232, 39, 52, 118 },/*left = d135*/ + { 50, 35, 33, 153, 104, 162, 64, 59, 131 },/*left = d117*/ + { 44, 24, 16, 150, 177, 202, 33, 19, 156 },/*left = d153*/ + { 55, 27, 12, 153, 203, 218, 26, 27, 49 },/*left = d207*/ + { 53, 49, 21, 110, 116, 168, 59, 80, 76 },/*left = d63 */ + { 38, 72, 19, 168, 203, 212, 50, 50, 107 } /*left = tm */ + }, { /* above = d45 */ + { 103, 26, 36, 129, 132, 201, 83, 80, 93 },/*left = dc */ + { 59, 38, 83, 112, 103, 162, 98, 136, 90 },/*left = v */ + { 62, 30, 23, 158, 200, 207, 59, 57, 50 },/*left = h */ + { 67, 30, 29, 84, 86, 191, 102, 91, 59 },/*left = d45 */ + { 60, 32, 33, 112, 71, 220, 64, 89, 104 },/*left = d135*/ + { 53, 26, 34, 130, 56, 149, 84, 120, 103 },/*left = d117*/ + { 53, 21, 23, 133, 109, 210, 56, 77, 172 },/*left = d153*/ + { 77, 19, 29, 112, 142, 228, 55, 66, 36 },/*left = d207*/ + { 61, 29, 29, 93, 97, 165, 83, 175, 162 },/*left = d63 */ + { 47, 47, 43, 114, 137, 181, 100, 99, 95 } /*left = tm */ + }, { /* above = d135 */ + { 69, 23, 29, 128, 83, 199, 46, 44, 101 },/*left = dc */ + { 53, 40, 55, 139, 69, 183, 61, 80, 110 },/*left = v */ + { 40, 29, 19, 161, 180, 207, 43, 24, 91 },/*left = h */ + { 60, 34, 19, 105, 61, 198, 53, 64, 89 },/*left = d45 */ + { 52, 31, 22, 158, 40, 209, 58, 62, 89 },/*left = d135*/ + { 44, 31, 29, 147, 46, 158, 56, 102, 198 },/*left = d117*/ + { 35, 19, 12, 135, 87, 209, 41, 45, 167 },/*left = d153*/ + { 55, 25, 21, 118, 95, 215, 38, 39, 66 },/*left = d207*/ + { 51, 38, 25, 113, 58, 164, 70, 93, 97 },/*left = d63 */ + { 47, 54, 34, 146, 108, 203, 72, 103, 151 } /*left = tm */ + }, { /* above = d117 */ + { 64, 19, 37, 156, 66, 138, 49, 95, 133 },/*left = dc */ + { 46, 27, 80, 150, 55, 124, 55, 121, 135 },/*left = v */ + { 36, 23, 27, 165, 149, 166, 54, 64, 118 },/*left = h */ + { 53, 21, 36, 131, 63, 163, 60, 109, 81 },/*left = d45 */ + { 40, 26, 35, 154, 40, 185, 51, 97, 123 },/*left = d135*/ + { 35, 19, 34, 179, 19, 97, 48, 129, 124 },/*left = d117*/ + { 36, 20, 26, 136, 62, 164, 33, 77, 154 },/*left = d153*/ + { 45, 18, 32, 130, 90, 157, 40, 79, 91 },/*left = d207*/ + { 45, 26, 28, 129, 45, 129, 49, 147, 123 },/*left = d63 */ + { 38, 44, 51, 136, 74, 162, 57, 97, 121 } /*left = tm */ + }, { /* above = d153 */ + { 75, 17, 22, 136, 138, 185, 32, 34, 166 },/*left = dc */ + { 56, 39, 58, 133, 117, 173, 48, 53, 187 },/*left = v */ + { 35, 21, 12, 161, 212, 207, 20, 23, 145 },/*left = h */ + { 56, 29, 19, 117, 109, 181, 55, 68, 112 },/*left = d45 */ + { 47, 29, 17, 153, 64, 220, 59, 51, 114 },/*left = d135*/ + { 46, 16, 24, 136, 76, 147, 41, 64, 172 },/*left = d117*/ + { 34, 17, 11, 108, 152, 187, 13, 15, 209 },/*left = d153*/ + { 51, 24, 14, 115, 133, 209, 32, 26, 104 },/*left = d207*/ + { 55, 30, 18, 122, 79, 179, 44, 88, 116 },/*left = d63 */ + { 37, 49, 25, 129, 168, 164, 41, 54, 148 } /*left = tm */ + }, { /* above = d207 */ + { 82, 22, 32, 127, 143, 213, 39, 41, 70 },/*left = dc */ + { 62, 44, 61, 123, 105, 189, 48, 57, 64 },/*left = v */ + { 47, 25, 17, 175, 222, 220, 24, 30, 86 },/*left = h */ + { 68, 36, 17, 106, 102, 206, 59, 74, 74 },/*left = d45 */ + { 57, 39, 23, 151, 68, 216, 55, 63, 58 },/*left = d135*/ + { 49, 30, 35, 141, 70, 168, 82, 40, 115 },/*left = d117*/ + { 51, 25, 15, 136, 129, 202, 38, 35, 139 },/*left = d153*/ + { 68, 26, 16, 111, 141, 215, 29, 28, 28 },/*left = d207*/ + { 59, 39, 19, 114, 75, 180, 77, 104, 42 },/*left = d63 */ + { 40, 61, 26, 126, 152, 206, 61, 59, 93 } /*left = tm */ + }, { /* above = d63 */ + { 78, 23, 39, 111, 117, 170, 74, 124, 94 },/*left = dc */ + { 48, 34, 86, 101, 92, 146, 78, 179, 134 },/*left = v */ + { 47, 22, 24, 138, 187, 178, 68, 69, 59 },/*left = h */ + { 56, 25, 33, 105, 112, 187, 95, 177, 129 },/*left = d45 */ + { 48, 31, 27, 114, 63, 183, 82, 116, 56 },/*left = d135*/ + { 43, 28, 37, 121, 63, 123, 61, 192, 169 },/*left = d117*/ + { 42, 17, 24, 109, 97, 177, 56, 76, 122 },/*left = d153*/ + { 58, 18, 28, 105, 139, 182, 70, 92, 63 },/*left = d207*/ + { 46, 23, 32, 74, 86, 150, 67, 183, 88 },/*left = d63 */ + { 36, 38, 48, 92, 122, 165, 88, 137, 91 } /*left = tm */ + }, { /* above = tm */ + { 65, 70, 60, 155, 159, 199, 61, 60, 81 },/*left = dc */ + { 44, 78, 115, 132, 119, 173, 71, 112, 93 },/*left = v */ + { 39, 38, 21, 184, 227, 206, 42, 32, 64 },/*left = h */ + { 58, 47, 36, 124, 137, 193, 80, 82, 78 },/*left = d45 */ + { 49, 50, 35, 144, 95, 205, 63, 78, 59 },/*left = d135*/ + { 41, 53, 52, 148, 71, 142, 65, 128, 51 },/*left = d117*/ + { 40, 36, 28, 143, 143, 202, 40, 55, 137 },/*left = d153*/ + { 52, 34, 29, 129, 183, 227, 42, 35, 43 },/*left = d207*/ + { 42, 44, 44, 104, 105, 164, 64, 130, 80 },/*left = d63 */ + { 43, 81, 53, 140, 169, 204, 68, 84, 72 } /*left = tm */ + } +}; + +static const u8 kf_partition_probs[16][3] = { + /* 8x8 -> 4x4 */ + { 158, 97, 94 }, /* a/l both not split */ + { 93, 24, 99 }, /* a split, l not split */ + { 85, 119, 44 }, /* l split, a not split */ + { 62, 59, 67 }, /* a/l both split */ + /* 16x16 -> 8x8 */ + { 149, 53, 53 }, /* a/l both not split */ + { 94, 20, 48 }, /* a split, l not split */ + { 83, 53, 24 }, /* l split, a not split */ + { 52, 18, 18 }, /* a/l both split */ + /* 32x32 -> 16x16 */ + { 150, 40, 39 }, /* a/l both not split */ + { 78, 12, 26 }, /* a split, l not split */ + { 67, 33, 11 }, /* l split, a not split */ + { 24, 7, 5 }, /* a/l both split */ + /* 64x64 -> 32x32 */ + { 174, 35, 49 }, /* a/l both not split */ + { 68, 11, 27 }, /* a split, l not split */ + { 57, 15, 9 }, /* l split, a not split */ + { 12, 3, 3 }, /* a/l both split */ +}; + +static const u8 kf_uv_mode_prob[10][9] = { + { 144, 11, 54, 157, 195, 130, 46, 58, 108 }, /* y = dc */ + { 118, 15, 123, 148, 131, 101, 44, 93, 131 }, /* y = v */ + { 113, 12, 23, 188, 226, 142, 26, 32, 125 }, /* y = h */ + { 120, 11, 50, 123, 163, 135, 64, 77, 103 }, /* y = d45 */ + { 113, 9, 36, 155, 111, 157, 32, 44, 161 }, /* y = d135 */ + { 116, 9, 55, 176, 76, 96, 37, 61, 149 }, /* y = d117 */ + { 115, 9, 28, 141, 161, 167, 21, 25, 193 }, /* y = d153 */ + { 120, 12, 32, 145, 195, 142, 32, 38, 86 }, /* y = d207 */ + { 116, 12, 64, 120, 140, 125, 49, 115, 121 }, /* y = d63 */ + { 102, 19, 66, 162, 182, 122, 35, 59, 128 } /* y = tm */ +}; + +static void write_coeff_plane(const u8 coef[6][6][3], u8 *coeff_plane) +{ + unsigned int idx = 0; + u8 byte_count = 0, p; + s32 k, m, n; + + for (k = 0; k < 6; k++) { + for (m = 0; m < 6; m++) { + for (n = 0; n < 3; n++) { + p = coef[k][m][n]; + coeff_plane[idx++] = p; + byte_count++; + if (byte_count == 27) { + idx += 5; + byte_count = 0; + } + } + } + } +} + +static void init_intra_only_probs(struct rkvdec_ctx *ctx, + const struct rkvdec_vp9_run *run) +{ + const struct v4l2_ctrl_vp9_frame_decode_params *dec_params; + struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv; + struct rkvdec_vp9_priv_tbl *tbl = vp9_ctx->priv_tbl.cpu; + struct rkvdec_vp9_intra_only_frame_probs *rkprobs; + const struct v4l2_vp9_probabilities *probs; + unsigned int i, j, k, m; + + rkprobs = &tbl->probs.intra_only; + dec_params = run->decode_params; + probs = &dec_params->probs; + + /* + * intra only 149 x 128 bits ,aligned to 152 x 128 bits coeff related + * prob 64 x 128 bits + */ + for (i = 0; i < ARRAY_SIZE(probs->coef); i++) { + for (j = 0; j < ARRAY_SIZE(probs->coef[0]); j++) + write_coeff_plane(probs->coef[i][j][0], + rkprobs->coef_intra[i][j]); + } + + /* intra mode prob 80 x 128 bits */ + for (i = 0; i < ARRAY_SIZE(vp9_kf_y_mode_prob); i++) { + u32 byte_count = 0; + int idx = 0; + + /* vp9_kf_y_mode_prob */ + for (j = 0; j < ARRAY_SIZE(vp9_kf_y_mode_prob[0]); j++) { + for (k = 0; k < ARRAY_SIZE(vp9_kf_y_mode_prob[0][0]); + k++) { + u8 val = vp9_kf_y_mode_prob[i][j][k]; + + rkprobs->intra_mode[i].y_mode[idx++] = val; + byte_count++; + if (byte_count == 27) { + byte_count = 0; + idx += 5; + } + } + } + + idx = 0; + if (i < 4) { + for (m = 0; m < (i < 3 ? 23 : 21); m++) { + const u8 *ptr = (const u8 *)kf_uv_mode_prob; + + rkprobs->intra_mode[i].uv_mode[idx++] = ptr[i * 23 + m]; + } + } + } +} + +static void init_inter_probs(struct rkvdec_ctx *ctx, + const struct rkvdec_vp9_run *run) +{ + const struct v4l2_ctrl_vp9_frame_decode_params *dec_params; + struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv; + struct rkvdec_vp9_priv_tbl *tbl = vp9_ctx->priv_tbl.cpu; + struct rkvdec_vp9_inter_frame_probs *rkprobs; + const struct v4l2_vp9_probabilities *probs; + unsigned int i, j, k; + + rkprobs = &tbl->probs.inter; + dec_params = run->decode_params; + probs = &dec_params->probs; + + /* + * inter probs + * 151 x 128 bits, aligned to 152 x 128 bits + * inter only + * intra_y_mode & inter_block info 6 x 128 bits + */ + + memcpy(rkprobs->y_mode, probs->y_mode, sizeof(rkprobs->y_mode)); + memcpy(rkprobs->comp_mode, probs->comp_mode, + sizeof(rkprobs->comp_mode)); + memcpy(rkprobs->comp_ref, probs->comp_ref, + sizeof(rkprobs->comp_ref)); + memcpy(rkprobs->single_ref, probs->single_ref, + sizeof(rkprobs->single_ref)); + memcpy(rkprobs->inter_mode, probs->inter_mode, + sizeof(rkprobs->inter_mode)); + memcpy(rkprobs->interp_filter, probs->interp_filter, + sizeof(rkprobs->interp_filter)); + + /* 128 x 128 bits coeff related */ + for (i = 0; i < ARRAY_SIZE(probs->coef); i++) { + for (j = 0; j < ARRAY_SIZE(probs->coef[0]); j++) { + for (k = 0; k < ARRAY_SIZE(probs->coef[0][0]); k++) + write_coeff_plane(probs->coef[i][j][k], + rkprobs->coef[k][i][j]); + } + } + + /* intra uv mode 6 x 128 */ + memcpy(rkprobs->uv_mode_0_2, &probs->uv_mode[0], + sizeof(rkprobs->uv_mode_0_2)); + memcpy(rkprobs->uv_mode_3_5, &probs->uv_mode[3], + sizeof(rkprobs->uv_mode_3_5)); + memcpy(rkprobs->uv_mode_6_8, &probs->uv_mode[6], + sizeof(rkprobs->uv_mode_6_8)); + memcpy(rkprobs->uv_mode_9, &probs->uv_mode[9], + sizeof(rkprobs->uv_mode_9)); + + /* mv related 6 x 128 */ + memcpy(rkprobs->mv.joint, probs->mv.joint, + sizeof(rkprobs->mv.joint)); + memcpy(rkprobs->mv.sign, probs->mv.sign, + sizeof(rkprobs->mv.sign)); + memcpy(rkprobs->mv.class, probs->mv.class, + sizeof(rkprobs->mv.class)); + memcpy(rkprobs->mv.class0_bit, probs->mv.class0_bit, + sizeof(rkprobs->mv.class0_bit)); + memcpy(rkprobs->mv.bits, probs->mv.bits, + sizeof(rkprobs->mv.bits)); + memcpy(rkprobs->mv.class0_fr, probs->mv.class0_fr, + sizeof(rkprobs->mv.class0_fr)); + memcpy(rkprobs->mv.fr, probs->mv.fr, + sizeof(rkprobs->mv.fr)); + memcpy(rkprobs->mv.class0_hp, probs->mv.class0_hp, + sizeof(rkprobs->mv.class0_hp)); + memcpy(rkprobs->mv.hp, probs->mv.hp, + sizeof(rkprobs->mv.hp)); +} + +static void init_probs(struct rkvdec_ctx *ctx, + const struct rkvdec_vp9_run *run) +{ + const struct v4l2_ctrl_vp9_frame_decode_params *dec_params; + struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv; + struct rkvdec_vp9_priv_tbl *tbl = vp9_ctx->priv_tbl.cpu; + struct rkvdec_vp9_probs *rkprobs = &tbl->probs; + const struct v4l2_vp9_segmentation *seg; + const struct v4l2_vp9_probabilities *probs; + bool intra_only; + + dec_params = run->decode_params; + probs = &dec_params->probs; + seg = &dec_params->seg; + + memset(rkprobs, 0, sizeof(*rkprobs)); + + intra_only = !!(dec_params->flags & + (V4L2_VP9_FRAME_FLAG_KEY_FRAME | + V4L2_VP9_FRAME_FLAG_INTRA_ONLY)); + + /* sb info 5 x 128 bit */ + memcpy(rkprobs->partition, + intra_only ? kf_partition_probs : probs->partition, + sizeof(rkprobs->partition)); + + memcpy(rkprobs->pred, seg->pred_probs, sizeof(rkprobs->pred)); + memcpy(rkprobs->tree, seg->tree_probs, sizeof(rkprobs->tree)); + memcpy(rkprobs->skip, probs->skip, sizeof(rkprobs->skip)); + memcpy(rkprobs->tx32, probs->tx32, sizeof(rkprobs->tx32)); + memcpy(rkprobs->tx16, probs->tx16, sizeof(rkprobs->tx16)); + memcpy(rkprobs->tx8, probs->tx8, sizeof(rkprobs->tx8)); + memcpy(rkprobs->is_inter, probs->is_inter, sizeof(rkprobs->is_inter)); + + if (intra_only) + init_intra_only_probs(ctx, run); + else + init_inter_probs(ctx, run); +} + +struct vp9d_ref_config { + u32 reg_frm_size; + u32 reg_hor_stride; + u32 reg_y_stride; + u32 reg_yuv_stride; + u32 reg_ref_base; +}; + +static struct vp9d_ref_config ref_config[3] = { + { + .reg_frm_size = RKVDEC_REG_VP9_FRAME_SIZE(0), + .reg_hor_stride = RKVDEC_VP9_HOR_VIRSTRIDE(0), + .reg_y_stride = RKVDEC_VP9_LAST_FRAME_YSTRIDE, + .reg_yuv_stride = RKVDEC_VP9_LAST_FRAME_YUVSTRIDE, + .reg_ref_base = RKVDEC_REG_VP9_LAST_FRAME_BASE, + }, + { + .reg_frm_size = RKVDEC_REG_VP9_FRAME_SIZE(1), + .reg_hor_stride = RKVDEC_VP9_HOR_VIRSTRIDE(1), + .reg_y_stride = RKVDEC_VP9_GOLDEN_FRAME_YSTRIDE, + .reg_yuv_stride = 0, + .reg_ref_base = RKVDEC_REG_VP9_GOLDEN_FRAME_BASE, + }, + { + .reg_frm_size = RKVDEC_REG_VP9_FRAME_SIZE(2), + .reg_hor_stride = RKVDEC_VP9_HOR_VIRSTRIDE(2), + .reg_y_stride = RKVDEC_VP9_ALTREF_FRAME_YSTRIDE, + .reg_yuv_stride = 0, + .reg_ref_base = RKVDEC_REG_VP9_ALTREF_FRAME_BASE, + } +}; + +static struct rkvdec_decoded_buffer * +get_ref_buf(struct rkvdec_ctx *ctx, struct vb2_v4l2_buffer *dst, u64 timestamp) +{ + struct v4l2_m2m_ctx *m2m_ctx = ctx->fh.m2m_ctx; + struct vb2_queue *cap_q = &m2m_ctx->cap_q_ctx.q; + int buf_idx; + + /* + * If a ref is unused or invalid, address of current destination + * buffer is returned. + */ + buf_idx = vb2_find_timestamp(cap_q, timestamp, 0); + if (buf_idx < 0) + return vb2_to_rkvdec_decoded_buf(&dst->vb2_buf); + + return vb2_to_rkvdec_decoded_buf(vb2_get_buffer(cap_q, buf_idx)); +} + +static dma_addr_t get_mv_base_addr(struct rkvdec_decoded_buffer *buf) +{ + u32 aligned_pitch, aligned_height, yuv_len; + + aligned_height = round_up(buf->vp9.height, 64); + aligned_pitch = round_up(buf->vp9.width * buf->vp9.bit_depth, 512) / 8; + yuv_len = (aligned_height * aligned_pitch * 3) / 2; + + return vb2_dma_contig_plane_dma_addr(&buf->base.vb.vb2_buf, 0) + + yuv_len; +} + +static void +config_ref_registers(struct rkvdec_ctx *ctx, + const struct rkvdec_vp9_run *run, + struct rkvdec_decoded_buffer **ref_bufs, + enum v4l2_vp9_ref_id id) +{ + u32 aligned_pitch, aligned_height, y_len, yuv_len; + struct rkvdec_decoded_buffer *buf = ref_bufs[id]; + struct rkvdec_dev *rkvdec = ctx->dev; + + aligned_height = round_up(buf->vp9.height, 64); + writel_relaxed(RKVDEC_VP9_FRAMEWIDTH(buf->vp9.width) | + RKVDEC_VP9_FRAMEHEIGHT(buf->vp9.height), + rkvdec->regs + ref_config[id].reg_frm_size); + + writel_relaxed(vb2_dma_contig_plane_dma_addr(&buf->base.vb.vb2_buf, 0), + rkvdec->regs + ref_config[id].reg_ref_base); + + if (&buf->base.vb == run->base.bufs.dst) + return; + + aligned_pitch = round_up(buf->vp9.width * buf->vp9.bit_depth, 512) / 8; + y_len = aligned_height * aligned_pitch; + yuv_len = (y_len * 3) / 2; + + writel_relaxed(RKVDEC_HOR_Y_VIRSTRIDE(aligned_pitch / 16) | + RKVDEC_HOR_UV_VIRSTRIDE(aligned_pitch / 16), + rkvdec->regs + ref_config[id].reg_hor_stride); + writel_relaxed(RKVDEC_VP9_REF_YSTRIDE(y_len / 16), + rkvdec->regs + ref_config[id].reg_y_stride); + + if (!ref_config[id].reg_yuv_stride) + return; + + writel_relaxed(RKVDEC_VP9_REF_YUVSTRIDE(yuv_len / 16), + rkvdec->regs + ref_config[id].reg_yuv_stride); +} + +static bool seg_featured_enabled(const struct v4l2_vp9_segmentation *seg, + enum v4l2_vp9_segment_feature feature, + unsigned int segid) +{ + u8 mask = V4L2_VP9_SEGMENT_FEATURE_ENABLED(feature); + + return !!(seg->feature_enabled[segid] & mask); +} + +static void +config_seg_registers(struct rkvdec_ctx *ctx, + unsigned int segid) +{ + struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv; + const struct v4l2_vp9_segmentation *seg; + struct rkvdec_dev *rkvdec = ctx->dev; + s16 feature_val; + u8 feature_id; + u32 val = 0; + + seg = vp9_ctx->last.valid ? &vp9_ctx->last.seg : &vp9_ctx->cur.seg; + feature_id = V4L2_VP9_SEGMENT_FEATURE_QP_DELTA; + if (seg_featured_enabled(seg, feature_id, segid)) { + feature_val = seg->feature_data[segid][feature_id]; + val |= RKVDEC_SEGID_FRAME_QP_DELTA_EN(1) | + RKVDEC_SEGID_FRAME_QP_DELTA(feature_val); + } + + feature_id = V4L2_VP9_SEGMENT_FEATURE_LF; + if (seg_featured_enabled(seg, feature_id, segid)) { + feature_val = seg->feature_data[segid][feature_id]; + val |= RKVDEC_SEGID_FRAME_LOOPFILTER_VALUE_EN(1) | + RKVDEC_SEGID_FRAME_LOOPFILTER_VALUE(feature_val); + } + + feature_id = V4L2_VP9_SEGMENT_FEATURE_REF_FRAME; + if (seg_featured_enabled(seg, feature_id, segid)) { + feature_val = seg->feature_data[segid][feature_id]; + val |= RKVDEC_SEGID_REFERINFO_EN(1) | + RKVDEC_SEGID_REFERINFO(feature_val); + } + + feature_id = V4L2_VP9_SEGMENT_FEATURE_SKIP; + if (seg_featured_enabled(seg, feature_id, segid)) + val |= RKVDEC_SEGID_FRAME_SKIP_EN(1); + + if (!segid && + (seg->flags & V4L2_VP9_SEGMENTATION_FLAG_ABS_OR_DELTA_UPDATE)) + val |= RKVDEC_SEGID_ABS_DELTA(1); + + writel_relaxed(val, rkvdec->regs + RKVDEC_VP9_SEGID_GRP(segid)); +} + +static void +update_dec_buf_info(struct rkvdec_decoded_buffer *buf, + const struct v4l2_ctrl_vp9_frame_decode_params *dec_params) +{ + buf->vp9.width = dec_params->frame_width_minus_1 + 1; + buf->vp9.height = dec_params->frame_height_minus_1 + 1; + buf->vp9.bit_depth = dec_params->bit_depth; +} + +static void +update_ctx_cur_info(struct rkvdec_vp9_ctx *vp9_ctx, + struct rkvdec_decoded_buffer *buf, + const struct v4l2_ctrl_vp9_frame_decode_params *dec_params) +{ + vp9_ctx->cur.valid = true; + vp9_ctx->cur.frame_context_idx = dec_params->frame_context_idx; + vp9_ctx->cur.reference_mode = dec_params->reference_mode; + vp9_ctx->cur.tx_mode = dec_params->tx_mode; + vp9_ctx->cur.interpolation_filter = dec_params->interpolation_filter; + vp9_ctx->cur.flags = dec_params->flags; + vp9_ctx->cur.timestamp = buf->base.vb.vb2_buf.timestamp; + vp9_ctx->cur.seg = dec_params->seg; + vp9_ctx->cur.lf = dec_params->lf; +} + +static void +update_ctx_last_info(struct rkvdec_vp9_ctx *vp9_ctx) +{ + vp9_ctx->last = vp9_ctx->cur; +} + +static void config_registers(struct rkvdec_ctx *ctx, + const struct rkvdec_vp9_run *run) +{ + u32 y_len, uv_len, yuv_len, bit_depth, aligned_height, aligned_pitch; + const struct v4l2_ctrl_vp9_frame_decode_params *dec_params; + struct rkvdec_decoded_buffer *ref_bufs[V4L2_REF_ID_CNT]; + struct rkvdec_decoded_buffer *dst, *last, *mv_ref; + struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv; + u32 val, stream_len, last_frame_info = 0; + const struct v4l2_vp9_segmentation *seg; + struct rkvdec_dev *rkvdec = ctx->dev; + dma_addr_t addr; + bool intra_only; + unsigned int i; + + dec_params = run->decode_params; + dst = vb2_to_rkvdec_decoded_buf(&run->base.bufs.dst->vb2_buf); + for (i = 0; i < ARRAY_SIZE(ref_bufs); i++) + ref_bufs[i] = get_ref_buf(ctx, &dst->base.vb, + dec_params->refs[i]); + + if (vp9_ctx->last.valid) + last = get_ref_buf(ctx, &dst->base.vb, vp9_ctx->last.timestamp); + else + last = dst; + + update_dec_buf_info(dst, dec_params); + update_ctx_cur_info(vp9_ctx, dst, dec_params); + seg = &dec_params->seg; + + intra_only = !!(dec_params->flags & + (V4L2_VP9_FRAME_FLAG_KEY_FRAME | + V4L2_VP9_FRAME_FLAG_INTRA_ONLY)); + + writel_relaxed(RKVDEC_MODE(RKVDEC_MODE_VP9), + rkvdec->regs + RKVDEC_REG_SYSCTRL); + + bit_depth = dec_params->bit_depth; + aligned_height = round_up(ctx->decoded_fmt.fmt.pix_mp.height, 64); + + aligned_pitch = round_up(ctx->decoded_fmt.fmt.pix_mp.width * + bit_depth, + 512) / 8; + y_len = aligned_height * aligned_pitch; + uv_len = y_len / 2; + yuv_len = y_len + uv_len; + + writel_relaxed(RKVDEC_Y_HOR_VIRSTRIDE(aligned_pitch / 16) | + RKVDEC_UV_HOR_VIRSTRIDE(aligned_pitch / 16), + rkvdec->regs + RKVDEC_REG_PICPAR); + writel_relaxed(RKVDEC_Y_VIRSTRIDE(y_len / 16), + rkvdec->regs + RKVDEC_REG_Y_VIRSTRIDE); + writel_relaxed(RKVDEC_YUV_VIRSTRIDE(yuv_len / 16), + rkvdec->regs + RKVDEC_REG_YUV_VIRSTRIDE); + + stream_len = vb2_get_plane_payload(&run->base.bufs.src->vb2_buf, 0); + writel_relaxed(RKVDEC_STRM_LEN(stream_len), + rkvdec->regs + RKVDEC_REG_STRM_LEN); + + /* + * Reset count buffer, because decoder only output intra related syntax + * counts when decoding intra frame, but update entropy need to update + * all the probabilities. + */ + if (intra_only) + memset(vp9_ctx->count_tbl.cpu, 0, vp9_ctx->count_tbl.size); + + vp9_ctx->cur.segmapid = vp9_ctx->last.segmapid; + if (!intra_only && + !(dec_params->flags & V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT) && + (!(seg->flags & V4L2_VP9_SEGMENTATION_FLAG_ENABLED) || + (seg->flags & V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP))) + vp9_ctx->cur.segmapid++; + + for (i = 0; i < ARRAY_SIZE(ref_bufs); i++) + config_ref_registers(ctx, run, ref_bufs, i); + + for (i = 0; i < 8; i++) + config_seg_registers(ctx, i); + + writel_relaxed(RKVDEC_VP9_TX_MODE(dec_params->tx_mode) | + RKVDEC_VP9_FRAME_REF_MODE(dec_params->reference_mode), + rkvdec->regs + RKVDEC_VP9_CPRHEADER_CONFIG); + + if (!intra_only) { + const struct v4l2_vp9_loop_filter *lf; + s8 delta; + + if (vp9_ctx->last.valid) + lf = &vp9_ctx->last.lf; + else + lf = &vp9_ctx->cur.lf; + + val = 0; + for (i = 0; i < ARRAY_SIZE(lf->ref_deltas); i++) { + delta = lf->ref_deltas[i]; + val |= RKVDEC_REF_DELTAS_LASTFRAME(i, delta); + } + + writel_relaxed(val, + rkvdec->regs + RKVDEC_VP9_REF_DELTAS_LASTFRAME); + + for (i = 0; i < ARRAY_SIZE(lf->mode_deltas); i++) { + delta = lf->mode_deltas[i]; + last_frame_info |= RKVDEC_MODE_DELTAS_LASTFRAME(i, + delta); + } + } + + if (vp9_ctx->last.valid && !intra_only && + vp9_ctx->last.seg.flags & V4L2_VP9_SEGMENTATION_FLAG_ENABLED) + last_frame_info |= RKVDEC_SEG_EN_LASTFRAME; + + if (vp9_ctx->last.valid && + vp9_ctx->last.flags & V4L2_VP9_FRAME_FLAG_SHOW_FRAME) + last_frame_info |= RKVDEC_LAST_SHOW_FRAME; + + if (vp9_ctx->last.valid && + vp9_ctx->last.flags & + (V4L2_VP9_FRAME_FLAG_KEY_FRAME | V4L2_VP9_FRAME_FLAG_INTRA_ONLY)) + last_frame_info |= RKVDEC_LAST_INTRA_ONLY; + + if (vp9_ctx->last.valid && + last->vp9.width == dst->vp9.width && + last->vp9.height == dst->vp9.height) + last_frame_info |= RKVDEC_LAST_WIDHHEIGHT_EQCUR; + + writel_relaxed(last_frame_info, + rkvdec->regs + RKVDEC_VP9_INFO_LASTFRAME); + + writel_relaxed(stream_len - dec_params->compressed_header_size - + dec_params->uncompressed_header_size, + rkvdec->regs + RKVDEC_VP9_LASTTILE_SIZE); + + for (i = 0; !intra_only && i < ARRAY_SIZE(ref_bufs); i++) { + u32 refw = ref_bufs[i]->vp9.width; + u32 refh = ref_bufs[i]->vp9.height; + u32 hscale, vscale; + + hscale = (refw << 14) / dst->vp9.width; + vscale = (refh << 14) / dst->vp9.height; + writel_relaxed(RKVDEC_VP9_REF_HOR_SCALE(hscale) | + RKVDEC_VP9_REF_VER_SCALE(vscale), + rkvdec->regs + RKVDEC_VP9_REF_SCALE(i)); + } + + addr = vb2_dma_contig_plane_dma_addr(&dst->base.vb.vb2_buf, 0); + writel_relaxed(addr, rkvdec->regs + RKVDEC_REG_DECOUT_BASE); + addr = vb2_dma_contig_plane_dma_addr(&run->base.bufs.src->vb2_buf, 0); + writel_relaxed(addr, rkvdec->regs + RKVDEC_REG_STRM_RLC_BASE); + writel_relaxed(vp9_ctx->priv_tbl.dma + + offsetof(struct rkvdec_vp9_priv_tbl, probs), + rkvdec->regs + RKVDEC_REG_CABACTBL_PROB_BASE); + writel_relaxed(vp9_ctx->count_tbl.dma, + rkvdec->regs + RKVDEC_REG_VP9COUNT_BASE); + + writel_relaxed(vp9_ctx->priv_tbl.dma + + offsetof(struct rkvdec_vp9_priv_tbl, segmap) + + (RKVDEC_VP9_MAX_SEGMAP_SIZE * vp9_ctx->cur.segmapid), + rkvdec->regs + RKVDEC_REG_VP9_SEGIDCUR_BASE); + writel_relaxed(vp9_ctx->priv_tbl.dma + + offsetof(struct rkvdec_vp9_priv_tbl, segmap) + + (RKVDEC_VP9_MAX_SEGMAP_SIZE * (!vp9_ctx->cur.segmapid)), + rkvdec->regs + RKVDEC_REG_VP9_SEGIDLAST_BASE); + + if (!intra_only && + !(dec_params->flags & V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT) && + vp9_ctx->last.valid) + mv_ref = last; + else + mv_ref = dst; + + writel_relaxed(get_mv_base_addr(mv_ref), + rkvdec->regs + RKVDEC_VP9_REF_COLMV_BASE); + + writel_relaxed(ctx->decoded_fmt.fmt.pix_mp.width | + (ctx->decoded_fmt.fmt.pix_mp.height << 16), + rkvdec->regs + RKVDEC_REG_PERFORMANCE_CYCLE); +} + +static int +validate_dec_params(struct rkvdec_ctx *ctx, + const struct v4l2_ctrl_vp9_frame_decode_params *dec_params) +{ + unsigned int aligned_width, aligned_height; + + /* We only support profile 0. */ + if (dec_params->profile != 0) { + dev_err(ctx->dev->dev, "unsupported profile %d\n", + dec_params->profile); + return -EINVAL; + } + + aligned_width = round_up(dec_params->frame_width_minus_1 + 1, 64); + aligned_height = round_up(dec_params->frame_height_minus_1 + 1, 64); + + /* + * Userspace should update the capture/decoded format when the + * resolution changes. + */ + if (aligned_width != ctx->decoded_fmt.fmt.pix_mp.width || + aligned_height != ctx->decoded_fmt.fmt.pix_mp.height) { + dev_err(ctx->dev->dev, + "unexpected bitstream resolution %dx%d\n", + dec_params->frame_width_minus_1 + 1, + dec_params->frame_height_minus_1 +1); + return -EINVAL; + } + + return 0; +} + +static int rkvdec_vp9_run_preamble(struct rkvdec_ctx *ctx, + struct rkvdec_vp9_run *run) +{ + const struct v4l2_ctrl_vp9_frame_decode_params *dec_params; + const struct v4l2_ctrl_vp9_frame_ctx *fctx = NULL; + struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv; + struct v4l2_ctrl *ctrl; + u8 frm_ctx; + int ret; + + rkvdec_run_preamble(ctx, &run->base); + + ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl, + V4L2_CID_MPEG_VIDEO_VP9_FRAME_DECODE_PARAMS); + WARN_ON(!ctrl); + + dec_params = ctrl ? ctrl->p_cur.p : NULL; + if (WARN_ON(!dec_params)) + return -EINVAL; + + ret = validate_dec_params(ctx, dec_params); + if (ret) + return ret; + + run->decode_params = dec_params; + + /* No need to load the frame context if we don't need to update it. */ + if (!(dec_params->flags & V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX)) + return 0; + + /* + * When a refresh context is requested in parallel mode, we should just + * update the context with the probs passed in the decode parameters. + */ + if (dec_params->flags & V4L2_VP9_FRAME_FLAG_PARALLEL_DEC_MODE) { + vp9_ctx->frame_context.probs = dec_params->probs; + return 0; + } + + frm_ctx = run->decode_params->frame_context_idx; + ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl, + V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(frm_ctx)); + if (WARN_ON(!ctrl)) + return 0; + + fctx = ctrl->p_cur.p; + vp9_ctx->frame_context = *fctx; + + /* + * For intra-only frames, we must update the context TX and skip probs + * with the value passed in the decode params. + */ + if (dec_params->flags & + (V4L2_VP9_FRAME_FLAG_KEY_FRAME | V4L2_VP9_FRAME_FLAG_INTRA_ONLY)) { + struct v4l2_vp9_probabilities *probs; + + probs = &vp9_ctx->frame_context.probs; + memcpy(probs->skip, dec_params->probs.skip, + sizeof(probs->skip)); + memcpy(probs->tx8, dec_params->probs.tx8, + sizeof(probs->tx8)); + memcpy(probs->tx16, dec_params->probs.tx16, + sizeof(probs->tx16)); + memcpy(probs->tx32, dec_params->probs.tx32, + sizeof(probs->tx32)); + } + + return 0; +} + +static int rkvdec_vp9_run(struct rkvdec_ctx *ctx) +{ + struct rkvdec_dev *rkvdec = ctx->dev; + struct rkvdec_vp9_run run = { }; + int ret; + + ret = rkvdec_vp9_run_preamble(ctx, &run); + if (ret) { + rkvdec_run_postamble(ctx, &run.base); + return ret; + } + + /* Prepare probs. */ + init_probs(ctx, &run); + + /* Configure hardware registers. */ + config_registers(ctx, &run); + + rkvdec_run_postamble(ctx, &run.base); + + schedule_delayed_work(&rkvdec->watchdog_work, msecs_to_jiffies(2000)); + + writel(1, rkvdec->regs + RKVDEC_REG_PREF_LUMA_CACHE_COMMAND); + writel(1, rkvdec->regs + RKVDEC_REG_PREF_CHR_CACHE_COMMAND); + + writel(0xe, rkvdec->regs + RKVDEC_REG_STRMD_ERR_EN); + /* Start decoding! */ + writel(RKVDEC_INTERRUPT_DEC_E | RKVDEC_CONFIG_DEC_CLK_GATE_E | + RKVDEC_TIMEOUT_E | RKVDEC_BUF_EMPTY_E, + rkvdec->regs + RKVDEC_REG_INTERRUPT); + + return 0; +} + +static u8 adapt_prob(u8 p1, u32 ct0, u32 ct1, u16 max_count, u32 update_factor) +{ + u32 ct = ct0 + ct1, p2; + u32 lo = 1; + u32 hi = 255; + + if (!ct) + return p1; + + p2 = ((ct0 << 8) + (ct >> 1)) / ct; + p2 = clamp(p2, lo, hi); + ct = min_t(u32, ct, max_count); + + if (WARN_ON(max_count >= 257)) + return p1; + + update_factor = rkvdec_fastdiv(update_factor * ct, max_count); + + return p1 + (((p2 - p1) * update_factor + 128) >> 8); +} + +#define BAND_6(band) ((band) == 0 ? 3 : 6) + +static void adapt_coeff(u8 coef[6][6][3], + const struct rkvdec_vp9_refs_counts ref_cnt[6][6], + u32 uf) +{ + s32 l, m, n; + + for (l = 0; l < 6; l++) { + for (m = 0; m < BAND_6(l); m++) { + u8 *p = coef[l][m]; + const u32 n0 = ref_cnt[l][m].coeff[0]; + const u32 n1 = ref_cnt[l][m].coeff[1]; + const u32 n2 = ref_cnt[l][m].coeff[2]; + const u32 neob = ref_cnt[l][m].eob[1]; + const u32 eob_count = ref_cnt[l][m].eob[0]; + const u32 branch_ct[3][2] = { + { neob, eob_count - neob }, + { n0, n1 + n2 }, + { n1, n2 } + }; + + for (n = 0; n < 3; n++) + p[n] = adapt_prob(p[n], branch_ct[n][0], + branch_ct[n][1], 24, uf); + } + } +} + +static void +adapt_coef_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_refs_counts ref_cnt[2][4][2][6][6], + unsigned int uf) +{ + unsigned int i, j, k; + + for (i = 0; i < ARRAY_SIZE(probs->coef); i++) { + for (j = 0; j < ARRAY_SIZE(probs->coef[0]); j++) { + for (k = 0; k < ARRAY_SIZE(probs->coef[0][0]); + k++) { + adapt_coeff(probs->coef[i][j][k], + ref_cnt[k][i][j], + uf); + } + } + } +} + +static void adapt_intra_frame_probs(struct rkvdec_ctx *ctx) +{ + struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv; + struct v4l2_vp9_probabilities *probs = &vp9_ctx->frame_context.probs; + const struct rkvdec_vp9_intra_frame_symbol_counts *sym_cnts; + + sym_cnts = vp9_ctx->count_tbl.cpu; + adapt_coef_probs(probs, sym_cnts->ref_cnt, 112); +} + +static void +adapt_skip_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(probs->skip); i++) + probs->skip[i] = adapt_prob(probs->skip[i], + sym_cnts->skip[i][0], + sym_cnts->skip[i][1], + 20, 128); +} + +static void +adapt_is_inter_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(probs->is_inter); i++) + probs->is_inter[i] = adapt_prob(probs->is_inter[i], + sym_cnts->inter[i][0], + sym_cnts->inter[i][1], + 20, 128); +} + +static void +adapt_comp_mode_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(probs->comp_mode); i++) + probs->comp_mode[i] = adapt_prob(probs->comp_mode[i], + sym_cnts->comp[i][0], + sym_cnts->comp[i][1], + 20, 128); +} + +static void +adapt_comp_ref_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(probs->comp_ref); i++) + probs->comp_ref[i] = adapt_prob(probs->comp_ref[i], + sym_cnts->comp_ref[i][0], + sym_cnts->comp_ref[i][1], + 20, 128); +} + +static void +adapt_single_ref_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(probs->single_ref); i++) { + u8 *p = probs->single_ref[i]; + + p[0] = adapt_prob(p[0], sym_cnts->single_ref[i][0][0], + sym_cnts->single_ref[i][0][1], 20, 128); + p[1] = adapt_prob(p[1], sym_cnts->single_ref[i][1][0], + sym_cnts->single_ref[i][1][1], 20, 128); + } +} + +static void +adapt_partition_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(probs->partition); i++) { + const u32 *c = sym_cnts->partition[i]; + u8 *p = probs->partition[i]; + + p[0] = adapt_prob(p[0], c[0], c[1] + c[2] + c[3], 20, 128); + p[1] = adapt_prob(p[1], c[1], c[2] + c[3], 20, 128); + p[2] = adapt_prob(p[2], c[2], c[3], 20, 128); + } +} + +static void +adapt_tx_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(probs->tx8); i++) { + u8 *p16x16 = probs->tx16[i]; + u8 *p32x32 = probs->tx32[i]; + const u32 *c16 = sym_cnts->tx16p[i]; + const u32 *c32 = sym_cnts->tx32p[i]; + const u32 *c8 = sym_cnts->tx8p[i]; + u8 *p8x8 = probs->tx8[i]; + + p8x8[0] = adapt_prob(p8x8[0], c8[0], c8[1], 20, 128); + p16x16[0] = adapt_prob(p16x16[0], c16[0], c16[1] + c16[2], + 20, 128); + p16x16[1] = adapt_prob(p16x16[1], c16[1], c16[2], 20, 128); + p32x32[0] = adapt_prob(p32x32[0], c32[0], + c32[1] + c32[2] + c32[3], 20, 128); + p32x32[1] = adapt_prob(p32x32[1], c32[1], c32[2] + c32[3], + 20, 128); + p32x32[2] = adapt_prob(p32x32[2], c32[2], c32[3], 20, 128); + } +} + +static void +adapt_interp_filter_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(probs->interp_filter); i++) { + u8 *p = probs->interp_filter[i]; + const u32 *c = sym_cnts->filter[i]; + + p[0] = adapt_prob(p[0], c[0], c[1] + c[2], 20, 128); + p[1] = adapt_prob(p[1], c[1], c[2], 20, 128); + } +} + +static void +adapt_inter_mode_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(probs->inter_mode); i++) { + const u32 *c = sym_cnts->mv_mode[i]; + u8 *p = probs->inter_mode[i]; + + p[0] = adapt_prob(p[0], c[2], c[1] + c[0] + c[3], 20, 128); + p[1] = adapt_prob(p[1], c[0], c[1] + c[3], 20, 128); + p[2] = adapt_prob(p[2], c[1], c[3], 20, 128); + } +} + +static void +adapt_mv_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts, + bool high_prec_mv) +{ + const u32 *c = sym_cnts->mv_joint; + u8 *p = probs->mv.joint; + unsigned int i, j; + u32 sum; + + p[0] = adapt_prob(p[0], c[0], c[1] + c[2] + c[3], 20, 128); + p[1] = adapt_prob(p[1], c[1], c[2] + c[3], 20, 128); + p[2] = adapt_prob(p[2], c[2], c[3], 20, 128); + + for (i = 0; i < ARRAY_SIZE(probs->mv.sign); i++) { + p = probs->mv.sign; + + p[i] = adapt_prob(p[i], sym_cnts->sign[i][0], + sym_cnts->sign[i][1], 20, 128); + + p = probs->mv.class[i]; + c = sym_cnts->classes[i]; + sum = c[1] + c[2] + c[3] + c[4] + c[5] + c[6] + c[7] + c[8] + + c[9] + c[10]; + p[0] = adapt_prob(p[0], c[0], sum, 20, 128); + sum -= c[1]; + p[1] = adapt_prob(p[1], c[1], sum, 20, 128); + sum -= c[2] + c[3]; + p[2] = adapt_prob(p[2], c[2] + c[3], sum, 20, 128); + p[3] = adapt_prob(p[3], c[2], c[3], 20, 128); + sum -= c[4] + c[5]; + p[4] = adapt_prob(p[4], c[4] + c[5], sum, 20, 128); + p[5] = adapt_prob(p[5], c[4], c[5], 20, 128); + sum -= c[6]; + p[6] = adapt_prob(p[6], c[6], sum, 20, 128); + p[7] = adapt_prob(p[7], c[7] + c[8], c[9] + c[10], 20, 128); + p[8] = adapt_prob(p[8], c[7], c[8], 20, 128); + p[9] = adapt_prob(p[9], c[9], c[10], 20, 128); + + p = probs->mv.class0_bit; + p[i] = adapt_prob(p[i], + sym_cnts->class0[i][0], + sym_cnts->class0[i][1], 20, 128); + + p = probs->mv.bits[i]; + for (j = 0; j < 10; j++) + p[j] = adapt_prob(p[j], sym_cnts->bits[i][j][0], + sym_cnts->bits[i][j][1], 20, 128); + + for (j = 0; j < 2; j++) { + p = probs->mv.class0_fr[i][j]; + c = sym_cnts->class0_fp[i][j]; + p[0] = adapt_prob(p[0], c[0], c[1] + c[2] + c[3], + 20, 128); + p[1] = adapt_prob(p[1], c[1], c[2] + c[3], 20, 128); + p[2] = adapt_prob(p[2], c[2], c[3], 20, 128); + } + + p = probs->mv.fr[i]; + c = sym_cnts->fp[i]; + p[0] = adapt_prob(p[0], c[0], c[1] + c[2] + c[3], 20, 128); + p[1] = adapt_prob(p[1], c[1], c[2] + c[3], 20, 128); + p[2] = adapt_prob(p[2], c[2], c[3], 20, 128); + + if (!high_prec_mv) + continue; + + p = probs->mv.class0_hp; + p[i] = adapt_prob(p[i], sym_cnts->class0_hp[i][0], + sym_cnts->class0_hp[i][1], 20, 128); + + p = probs->mv.hp; + p[i] = adapt_prob(p[i], sym_cnts->hp[i][0], + sym_cnts->hp[i][1], 20, 128); + } +} + +static void +adapt_intra_mode_probs(u8 *p, const u32 *c) +{ + u32 sum = 0, s2; + unsigned int i; + + for (i = V4L2_VP9_INTRA_PRED_MODE_V; i <= V4L2_VP9_INTRA_PRED_MODE_TM; + i++) + sum += c[i]; + + p[0] = adapt_prob(p[0], c[V4L2_VP9_INTRA_PRED_MODE_DC], sum, 20, 128); + sum -= c[V4L2_VP9_INTRA_PRED_MODE_TM]; + p[1] = adapt_prob(p[1], c[V4L2_VP9_INTRA_PRED_MODE_TM], sum, 20, 128); + sum -= c[V4L2_VP9_INTRA_PRED_MODE_V]; + p[2] = adapt_prob(p[2], c[V4L2_VP9_INTRA_PRED_MODE_V], sum, 20, 128); + s2 = c[V4L2_VP9_INTRA_PRED_MODE_H] + c[V4L2_VP9_INTRA_PRED_MODE_D135] + + c[V4L2_VP9_INTRA_PRED_MODE_D117]; + sum -= s2; + p[3] = adapt_prob(p[3], s2, sum, 20, 128); + s2 -= c[V4L2_VP9_INTRA_PRED_MODE_H]; + p[4] = adapt_prob(p[4], c[V4L2_VP9_INTRA_PRED_MODE_H], s2, 20, 128); + p[5] = adapt_prob(p[5], c[V4L2_VP9_INTRA_PRED_MODE_D135], + c[V4L2_VP9_INTRA_PRED_MODE_D117], 20, 128); + sum -= c[V4L2_VP9_INTRA_PRED_MODE_D45]; + p[6] = adapt_prob(p[6], c[V4L2_VP9_INTRA_PRED_MODE_D45], + sum, 20, 128); + sum -= c[V4L2_VP9_INTRA_PRED_MODE_D63]; + p[7] = adapt_prob(p[7], c[V4L2_VP9_INTRA_PRED_MODE_D63], sum, + 20, 128); + p[8] = adapt_prob(p[8], c[V4L2_VP9_INTRA_PRED_MODE_D153], + c[V4L2_VP9_INTRA_PRED_MODE_D207], 20, 128); +} + +static void +adapt_y_intra_mode_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(probs->y_mode); i++) + adapt_intra_mode_probs(probs->y_mode[i], sym_cnts->y_mode[i]); +} + +static void +adapt_uv_intra_mode_probs(struct v4l2_vp9_probabilities *probs, + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(probs->uv_mode); i++) + adapt_intra_mode_probs(probs->uv_mode[i], + sym_cnts->uv_mode[i]); +} + +static void +adapt_inter_frame_probs(struct rkvdec_ctx *ctx) +{ + struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv; + struct v4l2_vp9_probabilities *probs = &vp9_ctx->frame_context.probs; + const struct rkvdec_vp9_inter_frame_symbol_counts *sym_cnts; + + sym_cnts = vp9_ctx->count_tbl.cpu; + /* coefficients */ + if (vp9_ctx->last.valid && + !(vp9_ctx->last.flags & V4L2_VP9_FRAME_FLAG_KEY_FRAME)) + adapt_coef_probs(probs, sym_cnts->ref_cnt, 112); + else + adapt_coef_probs(probs, sym_cnts->ref_cnt, 128); + + /* skip flag */ + adapt_skip_probs(probs, sym_cnts); + + /* intra/inter flag */ + adapt_is_inter_probs(probs, sym_cnts); + + /* comppred flag */ + adapt_comp_mode_probs(probs, sym_cnts); + + /* reference frames */ + adapt_comp_ref_probs(probs, sym_cnts); + + if (vp9_ctx->cur.reference_mode != V4L2_VP9_REF_MODE_COMPOUND) + adapt_single_ref_probs(probs, sym_cnts); + + /* block partitioning */ + adapt_partition_probs(probs, sym_cnts); + + /* tx size */ + if (vp9_ctx->cur.tx_mode == V4L2_VP9_TX_MODE_SELECT) + adapt_tx_probs(probs, sym_cnts); + + /* interpolation filter */ + if (vp9_ctx->cur.interpolation_filter == V4L2_VP9_INTERP_FILTER_SWITCHABLE) + adapt_interp_filter_probs(probs, sym_cnts); + + /* inter modes */ + adapt_inter_mode_probs(probs, sym_cnts); + + /* mv probs */ + adapt_mv_probs(probs, sym_cnts, + !!(vp9_ctx->cur.flags & + V4L2_VP9_FRAME_FLAG_ALLOW_HIGH_PREC_MV)); + + /* y intra modes */ + adapt_y_intra_mode_probs(probs, sym_cnts); + + /* uv intra modes */ + adapt_uv_intra_mode_probs(probs, sym_cnts); +} + +static void adapt_probs(struct rkvdec_ctx *ctx) +{ + struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv; + bool intra_only; + + intra_only = !!(vp9_ctx->cur.flags & + (V4L2_VP9_FRAME_FLAG_KEY_FRAME | + V4L2_VP9_FRAME_FLAG_INTRA_ONLY)); + + if (intra_only) + adapt_intra_frame_probs(ctx); + else + adapt_inter_frame_probs(ctx); +} + +static void rkvdec_vp9_done(struct rkvdec_ctx *ctx, + struct vb2_v4l2_buffer *src_buf, + struct vb2_v4l2_buffer *dst_buf, + enum vb2_buffer_state result) +{ + struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv; + struct v4l2_ctrl *ctrl; + unsigned int fctx_idx; + + if (result == VB2_BUF_STATE_ERROR) + goto out_update_last; + + if (!(vp9_ctx->cur.flags & V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX)) + goto out_update_last; + + fctx_idx = vp9_ctx->cur.frame_context_idx; + + if (!(vp9_ctx->cur.flags & + (V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT | + V4L2_VP9_FRAME_FLAG_PARALLEL_DEC_MODE))) + adapt_probs(ctx); + + ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl, + V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(fctx_idx)); + if (WARN_ON(!ctrl)) + goto out_update_last; + + v4l2_ctrl_s_ctrl_compound(ctrl, V4L2_CTRL_TYPE_VP9_FRAME_CONTEXT, + &vp9_ctx->frame_context); + +out_update_last: + update_ctx_last_info(vp9_ctx); +} + +static int rkvdec_vp9_start(struct rkvdec_ctx *ctx) +{ + struct rkvdec_dev *rkvdec = ctx->dev; + struct rkvdec_vp9_priv_tbl *priv_tbl; + struct rkvdec_vp9_ctx *vp9_ctx; + u8 *count_tbl; + int ret; + + vp9_ctx = kzalloc(sizeof(*vp9_ctx), GFP_KERNEL); + if (!vp9_ctx) + return -ENOMEM; + + ctx->priv = vp9_ctx; + + priv_tbl = dma_alloc_coherent(rkvdec->dev, sizeof(*priv_tbl), + &vp9_ctx->priv_tbl.dma, GFP_KERNEL); + if (!priv_tbl) { + ret = -ENOMEM; + goto err_free_ctx; + } + + vp9_ctx->priv_tbl.size = sizeof(*priv_tbl); + vp9_ctx->priv_tbl.cpu = priv_tbl; + memset(priv_tbl, 0, sizeof(*priv_tbl)); + + count_tbl = dma_alloc_coherent(rkvdec->dev, RKVDEC_VP9_COUNT_SIZE, + &vp9_ctx->count_tbl.dma, GFP_KERNEL); + if (!count_tbl) { + ret = -ENOMEM; + goto err_free_priv_tbl; + } + + vp9_ctx->count_tbl.size = RKVDEC_VP9_COUNT_SIZE; + vp9_ctx->count_tbl.cpu = count_tbl; + memset(count_tbl, 0, sizeof(*count_tbl)); + + return 0; + +err_free_priv_tbl: + dma_free_coherent(rkvdec->dev, vp9_ctx->priv_tbl.size, + vp9_ctx->priv_tbl.cpu, vp9_ctx->priv_tbl.dma); + +err_free_ctx: + kfree(vp9_ctx); + return ret; +} + +static void rkvdec_vp9_stop(struct rkvdec_ctx *ctx) +{ + struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv; + struct rkvdec_dev *rkvdec = ctx->dev; + + dma_free_coherent(rkvdec->dev, vp9_ctx->count_tbl.size, + vp9_ctx->count_tbl.cpu, vp9_ctx->count_tbl.dma); + dma_free_coherent(rkvdec->dev, vp9_ctx->priv_tbl.size, + vp9_ctx->priv_tbl.cpu, vp9_ctx->priv_tbl.dma); + kfree(vp9_ctx); +} + +static int rkvdec_vp9_adjust_fmt(struct rkvdec_ctx *ctx, + struct v4l2_format *f) +{ + struct v4l2_pix_format_mplane *fmt = &f->fmt.pix_mp; + + fmt->num_planes = 1; + if (!fmt->plane_fmt[0].sizeimage) + fmt->plane_fmt[0].sizeimage = fmt->width * fmt->height * 2; + return 0; +} + +const struct rkvdec_coded_fmt_ops rkvdec_vp9_fmt_ops = { + .adjust_fmt = rkvdec_vp9_adjust_fmt, + .start = rkvdec_vp9_start, + .stop = rkvdec_vp9_stop, + .run = rkvdec_vp9_run, + .done = rkvdec_vp9_done, +}; diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c index 4df2a248ab96..393d649a1775 100644 --- a/drivers/staging/media/rkvdec/rkvdec.c +++ b/drivers/staging/media/rkvdec/rkvdec.c @@ -74,10 +74,45 @@ static const struct rkvdec_ctrls rkvdec_h264_ctrls = { .num_ctrls = ARRAY_SIZE(rkvdec_h264_ctrl_descs), }; -static const u32 rkvdec_h264_decoded_fmts[] = { +static const u32 rkvdec_h264_vp9_decoded_fmts[] = { V4L2_PIX_FMT_NV12, }; +static const struct rkvdec_ctrl_desc rkvdec_vp9_ctrl_descs[] = { + { + .per_request = true, + .mandatory = true, + .cfg.id = V4L2_CID_MPEG_VIDEO_VP9_FRAME_DECODE_PARAMS, + }, + { + .mandatory = true, + .cfg.id = V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(0), + }, + { + .mandatory = true, + .cfg.id = V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(1), + }, + { + .mandatory = true, + .cfg.id = V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(2), + }, + { + .mandatory = true, + .cfg.id = V4L2_CID_MPEG_VIDEO_VP9_FRAME_CONTEXT(3), + }, + { + .cfg.id = V4L2_CID_MPEG_VIDEO_VP9_PROFILE, + .cfg.min = V4L2_MPEG_VIDEO_VP9_PROFILE_0, + .cfg.max = V4L2_MPEG_VIDEO_VP9_PROFILE_0, + .cfg.def = V4L2_MPEG_VIDEO_VP9_PROFILE_0, + }, +}; + +static const struct rkvdec_ctrls rkvdec_vp9_ctrls = { + .ctrls = rkvdec_vp9_ctrl_descs, + .num_ctrls = ARRAY_SIZE(rkvdec_vp9_ctrl_descs), +}; + static const struct rkvdec_coded_fmt_desc rkvdec_coded_fmts[] = { { .fourcc = V4L2_PIX_FMT_H264_SLICE, @@ -91,8 +126,23 @@ static const struct rkvdec_coded_fmt_desc rkvdec_coded_fmts[] = { }, .ctrls = &rkvdec_h264_ctrls, .ops = &rkvdec_h264_fmt_ops, - .num_decoded_fmts = ARRAY_SIZE(rkvdec_h264_decoded_fmts), - .decoded_fmts = rkvdec_h264_decoded_fmts, + .num_decoded_fmts = ARRAY_SIZE(rkvdec_h264_vp9_decoded_fmts), + .decoded_fmts = rkvdec_h264_vp9_decoded_fmts, + }, + { + .fourcc = V4L2_PIX_FMT_VP9_FRAME, + .frmsize = { + .min_width = 64, + .max_width = 4096, + .step_width = 64, + .min_height = 64, + .max_height = 2304, + .step_height = 64, + }, + .ctrls = &rkvdec_vp9_ctrls, + .ops = &rkvdec_vp9_fmt_ops, + .num_decoded_fmts = ARRAY_SIZE(rkvdec_h264_vp9_decoded_fmts), + .decoded_fmts = rkvdec_h264_vp9_decoded_fmts, } }; diff --git a/drivers/staging/media/rkvdec/rkvdec.h b/drivers/staging/media/rkvdec/rkvdec.h index 2fc9f46b6910..2a795babfccd 100644 --- a/drivers/staging/media/rkvdec/rkvdec.h +++ b/drivers/staging/media/rkvdec/rkvdec.h @@ -52,6 +52,10 @@ struct rkvdec_vp9_decoded_buffer_info { struct rkvdec_decoded_buffer { /* Must be the first field in this struct. */ struct v4l2_m2m_buffer base; + + union { + struct rkvdec_vp9_decoded_buffer_info vp9; + }; }; static inline struct rkvdec_decoded_buffer * @@ -118,4 +122,6 @@ void rkvdec_run_preamble(struct rkvdec_ctx *ctx, struct rkvdec_run *run); void rkvdec_run_postamble(struct rkvdec_ctx *ctx, struct rkvdec_run *run); extern const struct rkvdec_coded_fmt_ops rkvdec_h264_fmt_ops; +extern const struct rkvdec_coded_fmt_ops rkvdec_vp9_fmt_ops; + #endif /* RKVDEC_H_ */