From patchwork Mon Dec 13 08:41:32 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yunfei Dong X-Patchwork-Id: 12673405 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 13A7DC4332F for ; Mon, 13 Dec 2021 08:57:26 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender: Content-Transfer-Encoding:Content-Type:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:MIME-Version:References:In-Reply-To: Message-ID:Date:Subject:CC:To:From:Reply-To:Content-ID:Content-Description: Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID: List-Owner; bh=GwZn7JyBUffPyIqn3kshDhkof+yxPxhgkU72hbRtQ/4=; b=Ebq6yhYWvpUJj3 RuGFAb3dFvCc+oF+6pXTneOWxWEtxBfB0DLqVkbCCI4rRWfSraNZnwQuD8xCoUx4BfxVhmUQgUdV5 H2tMwYK9Oibw1OvRf+MxAcwmWZCgxcehdTK5FXToJcRoSDcmNc8ucQYyGXQCju5mw1j/1DaBLvMMB zvT3xYblSszQ/xY052i9VOWo2z9sp2erqsRaER8lQNV+iHzt3aiZrzhGEtAjMbNyToSfF6kv0fKGC dXfiZvSVVD5HbNhEItxnZOiIGm09Z97tzT5NWJgSQWd2oGqzOH8ZGMO3YjitBz3OjT4oo6ez91s/9 Fy1IX10JbzBhlZyw/KrQ==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.94.2 #2 (Red Hat Linux)) id 1mwh8z-008Rd1-Qr; Mon, 13 Dec 2021 08:57:13 +0000 Received: from mailgw01.mediatek.com ([216.200.240.184]) by bombadil.infradead.org with esmtps (Exim 4.94.2 #2 (Red Hat Linux)) id 1mwh34-008OkA-Da; Mon, 13 Dec 2021 08:51:09 +0000 X-UUID: a6b0ad3289354be4a28b7776ab2e7fe1-20211213 X-UUID: a6b0ad3289354be4a28b7776ab2e7fe1-20211213 Received: from mtkcas66.mediatek.inc [(172.29.193.44)] by mailgw01.mediatek.com (envelope-from ) (musrelay.mediatek.com ESMTP with TLSv1.2 ECDHE-RSA-AES256-SHA384 256/256) with ESMTP id 448307772; Mon, 13 Dec 2021 01:50:57 -0700 Received: from mtkexhb02.mediatek.inc (172.21.101.103) by MTKMBS62DR.mediatek.inc (172.29.94.18) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Mon, 13 Dec 2021 00:41:59 -0800 Received: from mtkcas11.mediatek.inc (172.21.101.40) by mtkexhb02.mediatek.inc (172.21.101.103) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Mon, 13 Dec 2021 16:41:56 +0800 Received: from mhfsdcap04.gcn.mediatek.inc (10.17.3.154) by mtkcas11.mediatek.inc (172.21.101.73) with Microsoft SMTP Server id 15.0.1497.2 via Frontend Transport; Mon, 13 Dec 2021 16:41:55 +0800 From: Yunfei Dong To: Yunfei Dong , Alexandre Courbot , Hans Verkuil , "Tzung-Bi Shih" , Tiffany Lin , Andrew-CT Chen , Mauro Carvalho Chehab , Rob Herring , Matthias Brugger , Tomasz Figa CC: Hsin-Yi Wang , Fritz Koenig , Dafna Hirschfeld , Benjamin Gaignard , Daniel Vetter , dri-devel , Irui Wang , AngeloGioacchino Del Regno , "Steve Cho" , , , , , , , Subject: [PATCH v13, 10/19] media: mtk-vcodec: Add msg queue feature for lat and core architecture Date: Mon, 13 Dec 2021 16:41:32 +0800 Message-ID: <20211213084141.13363-11-yunfei.dong@mediatek.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20211213084141.13363-1-yunfei.dong@mediatek.com> References: <20211213084141.13363-1-yunfei.dong@mediatek.com> MIME-Version: 1.0 X-MTK: N X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20211213_005106_523102_4B2CC8F8 X-CRM114-Status: GOOD ( 27.49 ) X-BeenThere: linux-mediatek@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "Linux-mediatek" Errors-To: linux-mediatek-bounces+linux-mediatek=archiver.kernel.org@lists.infradead.org For lat and core architecture, lat thread will send message to core thread when lat decode done. Core hardware will use the message from lat to decode, then free message to lat thread when decode done. Signed-off-by: Yunfei Dong --- drivers/media/platform/mtk-vcodec/Makefile | 1 + .../platform/mtk-vcodec/mtk_vcodec_drv.h | 9 + .../platform/mtk-vcodec/vdec_msg_queue.c | 260 ++++++++++++++++++ .../platform/mtk-vcodec/vdec_msg_queue.h | 143 ++++++++++ 4 files changed, 413 insertions(+) create mode 100644 drivers/media/platform/mtk-vcodec/vdec_msg_queue.c create mode 100644 drivers/media/platform/mtk-vcodec/vdec_msg_queue.h diff --git a/drivers/media/platform/mtk-vcodec/Makefile b/drivers/media/platform/mtk-vcodec/Makefile index c61bfb179bcc..359619653a0e 100644 --- a/drivers/media/platform/mtk-vcodec/Makefile +++ b/drivers/media/platform/mtk-vcodec/Makefile @@ -12,6 +12,7 @@ mtk-vcodec-dec-y := vdec/vdec_h264_if.o \ mtk_vcodec_dec_drv.o \ vdec_drv_if.o \ vdec_vpu_if.o \ + vdec_msg_queue.o \ mtk_vcodec_dec.o \ mtk_vcodec_dec_stateful.o \ mtk_vcodec_dec_stateless.o \ diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h index 7fc106df039b..610b0af13879 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h @@ -15,7 +15,9 @@ #include #include #include + #include "mtk_vcodec_util.h" +#include "vdec_msg_queue.h" #define MTK_VCODEC_DRV_NAME "mtk_vcodec_drv" #define MTK_VCODEC_DEC_NAME "mtk-vcodec-dec" @@ -282,6 +284,8 @@ struct vdec_pic_info { * @decoded_frame_cnt: number of decoded frames * @lock: protect variables accessed by V4L2 threads and worker thread such as * mtk_video_dec_buf. + * + * @msg_queue: msg queue used to store lat buffer information. */ struct mtk_vcodec_ctx { enum mtk_instance_type type; @@ -325,6 +329,7 @@ struct mtk_vcodec_ctx { int decoded_frame_cnt; struct mutex lock; + struct vdec_msg_queue msg_queue; }; enum mtk_chip { @@ -457,6 +462,8 @@ struct mtk_vcodec_enc_pdata { * @dec_capability: used to identify decode capability, ex: 4k * @enc_capability: used to identify encode capability * + * @msg_queue_core_ctx: msg queue context used for core workqueue + * * @subdev_dev: subdev hardware device * @subdev_bitmap: used to record hardware is ready or not */ @@ -497,6 +504,8 @@ struct mtk_vcodec_dev { unsigned int dec_capability; unsigned int enc_capability; + struct vdec_msg_queue_ctx msg_queue_core_ctx; + void *subdev_dev[MTK_VDEC_HW_MAX]; DECLARE_BITMAP(subdev_bitmap, MTK_VDEC_HW_MAX); }; diff --git a/drivers/media/platform/mtk-vcodec/vdec_msg_queue.c b/drivers/media/platform/mtk-vcodec/vdec_msg_queue.c new file mode 100644 index 000000000000..913aefa67618 --- /dev/null +++ b/drivers/media/platform/mtk-vcodec/vdec_msg_queue.c @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 MediaTek Inc. + * Author: Yunfei Dong + */ + +#include +#include +#include + +#include "mtk_vcodec_dec_pm.h" +#include "mtk_vcodec_drv.h" +#include "vdec_msg_queue.h" + +#define VDEC_MSG_QUEUE_TIMEOUT_MS 1500 + +/* the size used to store lat slice header information */ +#define VDEC_LAT_SLICE_HEADER_SZ (640 * SZ_1K) + +/* the size used to store avc error information */ +#define VDEC_ERR_MAP_SZ_AVC (17 * SZ_1K) + +/* core will read the trans buffer which decoded by lat to decode again. + * The trans buffer size of FHD and 4K bitstreams are different. + */ +static int vde_msg_queue_get_trans_size(int width, int height) +{ + if (width > 1920 || height > 1088) + return 30 * SZ_1M; + else + return 6 * SZ_1M; +} + +void vdec_msg_queue_init_ctx(struct vdec_msg_queue_ctx *ctx, int hardware_index) +{ + init_waitqueue_head(&ctx->ready_to_use); + INIT_LIST_HEAD(&ctx->ready_queue); + spin_lock_init(&ctx->ready_lock); + ctx->ready_num = 0; + ctx->hardware_index = hardware_index; +} + +static struct list_head *vdec_get_buf_list(int hardware_index, struct vdec_lat_buf *buf) +{ + switch (hardware_index) { + case MTK_VDEC_CORE: + return &buf->core_list; + case MTK_VDEC_LAT0: + return &buf->lat_list; + default: + return NULL; + } +} + +int vdec_msg_queue_qbuf(struct vdec_msg_queue_ctx *msg_ctx, struct vdec_lat_buf *buf) +{ + struct list_head *head; + + head = vdec_get_buf_list(msg_ctx->hardware_index, buf); + if (!head) { + mtk_v4l2_err("fail to qbuf: %d",msg_ctx->hardware_index); + return -EINVAL; + } + + spin_lock(&msg_ctx->ready_lock); + list_add_tail(head, &msg_ctx->ready_queue); + msg_ctx->ready_num++; + + if (msg_ctx->hardware_index != MTK_VDEC_CORE) + wake_up_all(&msg_ctx->ready_to_use); + + mtk_v4l2_debug(3, "enqueue buf type: %d addr: 0x%p num: %d", + msg_ctx->hardware_index, buf, msg_ctx->ready_num); + spin_unlock(&msg_ctx->ready_lock); + + return 0; +} + +static bool vdec_msg_queue_wait_event(struct vdec_msg_queue_ctx *msg_ctx) +{ + int ret; + + ret = wait_event_timeout(msg_ctx->ready_to_use, + !list_empty(&msg_ctx->ready_queue), + msecs_to_jiffies(VDEC_MSG_QUEUE_TIMEOUT_MS)); + if (!ret) + return false; + + return true; +} + +struct vdec_lat_buf *vdec_msg_queue_dqbuf(struct vdec_msg_queue_ctx *msg_ctx) +{ + struct vdec_lat_buf *buf; + struct list_head *head; + int ret; + + spin_lock(&msg_ctx->ready_lock); + if (list_empty(&msg_ctx->ready_queue)) { + mtk_v4l2_debug(3, "queue is NULL, type:%d num: %d", + msg_ctx->hardware_index, msg_ctx->ready_num); + spin_unlock(&msg_ctx->ready_lock); + + if (msg_ctx->hardware_index == MTK_VDEC_CORE) + return NULL; + + ret = vdec_msg_queue_wait_event(msg_ctx); + if (!ret) + return NULL; + spin_lock(&msg_ctx->ready_lock); + } + + if (msg_ctx->hardware_index == MTK_VDEC_CORE) + buf = list_first_entry(&msg_ctx->ready_queue, + struct vdec_lat_buf, core_list); + else + buf = list_first_entry(&msg_ctx->ready_queue, + struct vdec_lat_buf, lat_list); + + head = vdec_get_buf_list(msg_ctx->hardware_index, buf); + if (!head) { + spin_unlock(&msg_ctx->ready_lock); + mtk_v4l2_err("fail to dqbuf: %d",msg_ctx->hardware_index); + return NULL; + } + list_del(head); + + msg_ctx->ready_num--; + mtk_v4l2_debug(3, "dqueue buf type:%d addr: 0x%p num: %d", + msg_ctx->hardware_index, buf, msg_ctx->ready_num); + spin_unlock(&msg_ctx->ready_lock); + + return buf; +} + +void vdec_msg_queue_update_ube_rptr(struct vdec_msg_queue *msg_queue, uint64_t ube_rptr) +{ + spin_lock(&msg_queue->lat_ctx.ready_lock); + msg_queue->wdma_rptr_addr = ube_rptr; + mtk_v4l2_debug(3, "update ube rprt (0x%llx)", ube_rptr); + spin_unlock(&msg_queue->lat_ctx.ready_lock); +} + +void vdec_msg_queue_update_ube_wptr(struct vdec_msg_queue *msg_queue, uint64_t ube_wptr) +{ + spin_lock(&msg_queue->lat_ctx.ready_lock); + msg_queue->wdma_wptr_addr = ube_wptr; + mtk_v4l2_debug(3, "update ube wprt: (0x%llx 0x%llx) offset: 0x%llx", + msg_queue->wdma_rptr_addr, msg_queue->wdma_wptr_addr, ube_wptr); + spin_unlock(&msg_queue->lat_ctx.ready_lock); +} + +bool vdec_msg_queue_wait_lat_buf_full(struct vdec_msg_queue *msg_queue) +{ + long timeout_jiff; + int ret; + + timeout_jiff = msecs_to_jiffies(1000 * (NUM_BUFFER_COUNT + 2)); + ret = wait_event_timeout(msg_queue->lat_ctx.ready_to_use, + msg_queue->lat_ctx.ready_num == NUM_BUFFER_COUNT, + timeout_jiff); + if (ret) { + mtk_v4l2_debug(3, "success to get lat buf: %d", + msg_queue->lat_ctx.ready_num); + return true; + } + mtk_v4l2_err("failed with lat buf isn't full: %d", + msg_queue->lat_ctx.ready_num); + return false; +} + +void vdec_msg_queue_deinit( + struct vdec_msg_queue *msg_queue, + struct mtk_vcodec_ctx *ctx) +{ + struct vdec_lat_buf *lat_buf; + struct mtk_vcodec_mem *mem; + int i; + + mem = &msg_queue->wdma_addr; + if (mem->va) + mtk_vcodec_mem_free(ctx, mem); + for (i = 0; i < NUM_BUFFER_COUNT; i++) { + lat_buf = &msg_queue->lat_buf[i]; + + mem = &lat_buf->wdma_err_addr; + if (mem->va) + mtk_vcodec_mem_free(ctx, mem); + + mem = &lat_buf->slice_bc_addr; + if (mem->va) + mtk_vcodec_mem_free(ctx, mem); + + if (lat_buf->private_data) + kfree(lat_buf->private_data); + } +} + +int vdec_msg_queue_init( + struct vdec_msg_queue *msg_queue, + struct mtk_vcodec_ctx *ctx, + core_decode_cb_t core_decode, + int private_size) +{ + struct vdec_lat_buf *lat_buf; + int i, err; + + /* already init msg queue */ + if (msg_queue->wdma_addr.size) + return 0; + + vdec_msg_queue_init_ctx(&msg_queue->lat_ctx, MTK_VDEC_LAT0); + msg_queue->wdma_addr.size = vde_msg_queue_get_trans_size( + ctx->picinfo.buf_w, ctx->picinfo.buf_h); + + err = mtk_vcodec_mem_alloc(ctx, &msg_queue->wdma_addr); + if (err) { + mtk_v4l2_err("failed to allocate wdma_addr buf"); + return -ENOMEM; + } + msg_queue->wdma_rptr_addr = msg_queue->wdma_addr.dma_addr; + msg_queue->wdma_wptr_addr = msg_queue->wdma_addr.dma_addr; + + for (i = 0; i < NUM_BUFFER_COUNT; i++) { + lat_buf = &msg_queue->lat_buf[i]; + + lat_buf->wdma_err_addr.size = VDEC_ERR_MAP_SZ_AVC; + err = mtk_vcodec_mem_alloc(ctx, &lat_buf->wdma_err_addr); + if (err) { + mtk_v4l2_err("failed to allocate wdma_err_addr buf[%d]", i); + goto mem_alloc_err; + } + + lat_buf->slice_bc_addr.size = VDEC_LAT_SLICE_HEADER_SZ; + err = mtk_vcodec_mem_alloc(ctx, &lat_buf->slice_bc_addr); + if (err) { + mtk_v4l2_err("failed to allocate wdma_addr buf[%d]", i); + goto mem_alloc_err; + } + + lat_buf->private_data = kzalloc(private_size, GFP_KERNEL); + if (!lat_buf->private_data) { + mtk_v4l2_err("failed to allocate private_data[%d]", i); + goto mem_alloc_err; + } + + lat_buf->ctx = ctx; + lat_buf->core_decode = core_decode; + err = vdec_msg_queue_qbuf(&msg_queue->lat_ctx, lat_buf); + if (err) { + mtk_v4l2_err("failed to qbuf buf[%d]", i); + goto mem_alloc_err; + } + } + return 0; + +mem_alloc_err: + vdec_msg_queue_deinit(msg_queue, ctx); + return err; +} diff --git a/drivers/media/platform/mtk-vcodec/vdec_msg_queue.h b/drivers/media/platform/mtk-vcodec/vdec_msg_queue.h new file mode 100644 index 000000000000..21a9c0aeb1b4 --- /dev/null +++ b/drivers/media/platform/mtk-vcodec/vdec_msg_queue.h @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 MediaTek Inc. + * Author: Yunfei Dong + */ + +#ifndef _VDEC_MSG_QUEUE_H_ +#define _VDEC_MSG_QUEUE_H_ + +#include +#include +#include +#include + +#include "mtk_vcodec_util.h" + +#define NUM_BUFFER_COUNT 3 + +struct vdec_lat_buf; +struct mtk_vcodec_ctx; +struct mtk_vcodec_dev; +typedef int (*core_decode_cb_t)(struct vdec_lat_buf *lat_buf); + +/** + * struct vdec_msg_queue_ctx - represents a queue for buffers ready to be processed + * @ready_used: ready used queue used to signalize when get a job queue + * @ready_queue: list of ready lat buffer queues + * @ready_lock: spin lock to protect the lat buffer usage + * @ready_num: number of buffers ready to be processed + * @hardware_index: hardware id that this queue is used for + */ +struct vdec_msg_queue_ctx { + wait_queue_head_t ready_to_use; + struct list_head ready_queue; + spinlock_t ready_lock; + int ready_num; + int hardware_index; +}; + +/** + * struct vdec_lat_buf - lat buffer message used to store lat info for core decode + * @wdma_err_addr: wdma error address used for lat hardware + * @slice_bc_addr: slice bc address used for lat hardware + * @ts_info: need to set timestamp from output to capture + * + * @private_data: shared information used to lat and core hardware + * @ctx: mtk vcodec context information + * @core_decode: different codec use different decode callback function + * @lat_list: add lat buffer to lat head list + * @core_list: add lat buffer to core head list + */ +struct vdec_lat_buf { + struct mtk_vcodec_mem wdma_err_addr; + struct mtk_vcodec_mem slice_bc_addr; + struct vb2_v4l2_buffer ts_info; + + void *private_data; + struct mtk_vcodec_ctx *ctx; + core_decode_cb_t core_decode; + struct list_head lat_list; + struct list_head core_list; +}; + +/** + * struct vdec_msg_queue - used to store lat buffer message + * @lat_buf: lat buffer used to store lat buffer information + * @wdma_addr: wdma address used for ube + * @wdma_rptr_addr: ube read point + * @wdma_wptr_addr: ube write point + * @lat_ctx: used to store lat buffer list + */ +struct vdec_msg_queue { + struct vdec_lat_buf lat_buf[NUM_BUFFER_COUNT]; + + struct mtk_vcodec_mem wdma_addr; + uint64_t wdma_rptr_addr; + uint64_t wdma_wptr_addr; + + struct vdec_msg_queue_ctx lat_ctx; +}; + +/** + * vdec_msg_queue_init - init lat buffer information. + * @msg_queue: used to store the lat buffer information + * @ctx: v4l2 ctx + * @core_decode: core decode callback for each codec + * @private_size: the private data size used to share with core + */ +int vdec_msg_queue_init( + struct vdec_msg_queue *msg_queue, + struct mtk_vcodec_ctx *ctx, + core_decode_cb_t core_decode, + int private_size); + +/** + * vdec_msg_queue_init_ctx - used to init msg queue context information. + * @ctx: message queue context + * @hardware_index: hardware index + */ +void vdec_msg_queue_init_ctx(struct vdec_msg_queue_ctx *ctx, int hardware_index); + +/** + * vdec_msg_queue_qbuf - enqueue lat buffer to queue list. + * @ctx: message queue context + * @buf: current lat buffer + */ +int vdec_msg_queue_qbuf(struct vdec_msg_queue_ctx *ctx, struct vdec_lat_buf *buf); + +/** + * vdec_msg_queue_dqbuf - dequeue lat buffer from queue list. + * @ctx: message queue context + */ +struct vdec_lat_buf *vdec_msg_queue_dqbuf(struct vdec_msg_queue_ctx *ctx); + +/** + * vdec_msg_queue_update_ube_rptr - used to updata the ube read point. + * @msg_queue: used to store the lat buffer information + * @ube_rptr: current ube read point + */ +void vdec_msg_queue_update_ube_rptr(struct vdec_msg_queue *msg_queue, uint64_t ube_rptr); + +/** + * vdec_msg_queue_update_ube_wptr - used to updata the ube write point. + * @msg_queue: used to store the lat buffer information + * @ube_wptr: current ube write point + */ +void vdec_msg_queue_update_ube_wptr(struct vdec_msg_queue *msg_queue, uint64_t ube_wptr); + +/** + * vdec_msg_queue_wait_lat_buf_full - used to check whether all lat buffer + * in lat list. + * @msg_queue: used to store the lat buffer information + */ +bool vdec_msg_queue_wait_lat_buf_full(struct vdec_msg_queue *msg_queue); + +/** + * vdec_msg_queue_deinit - deinit lat buffer information. + * @msg_queue: used to store the lat buffer information + * @ctx: v4l2 ctx + */ +void vdec_msg_queue_deinit(struct vdec_msg_queue *msg_queue, struct mtk_vcodec_ctx *ctx); + +#endif