From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- .../mediatek/vcodec/mtk_vcodec_dec_stateful.c | 610 +++++++++++++++++++++ 1 file changed, 610 insertions(+) create mode 100644 drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c (limited to 'drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c') diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c new file mode 100644 index 000000000..035c86e78 --- /dev/null +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c @@ -0,0 +1,610 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include + +#include "mtk_vcodec_drv.h" +#include "mtk_vcodec_dec.h" +#include "mtk_vcodec_intr.h" +#include "mtk_vcodec_util.h" +#include "mtk_vcodec_dec_pm.h" +#include "vdec_drv_if.h" + +static const struct mtk_video_fmt mtk_video_formats[] = { + { + .fourcc = V4L2_PIX_FMT_H264, + .type = MTK_FMT_DEC, + .num_planes = 1, + .flags = V4L2_FMT_FLAG_DYN_RESOLUTION, + .frmsize = { MTK_VDEC_MIN_W, MTK_VDEC_MAX_W, 16, + MTK_VDEC_MIN_H, MTK_VDEC_MAX_H, 16 }, + }, + { + .fourcc = V4L2_PIX_FMT_VP8, + .type = MTK_FMT_DEC, + .num_planes = 1, + .flags = V4L2_FMT_FLAG_DYN_RESOLUTION, + .frmsize = { MTK_VDEC_MIN_W, MTK_VDEC_MAX_W, 16, + MTK_VDEC_MIN_H, MTK_VDEC_MAX_H, 16 }, + }, + { + .fourcc = V4L2_PIX_FMT_VP9, + .type = MTK_FMT_DEC, + .num_planes = 1, + .flags = V4L2_FMT_FLAG_DYN_RESOLUTION, + .frmsize = { MTK_VDEC_MIN_W, MTK_VDEC_MAX_W, 16, + MTK_VDEC_MIN_H, MTK_VDEC_MAX_H, 16 }, + }, + { + .fourcc = V4L2_PIX_FMT_MT21C, + .type = MTK_FMT_FRAME, + .num_planes = 2, + }, +}; + +static const unsigned int num_supported_formats = + ARRAY_SIZE(mtk_video_formats); + +#define DEFAULT_OUT_FMT_IDX 0 +#define DEFAULT_CAP_FMT_IDX 3 + +/* + * This function tries to clean all display buffers, the buffers will return + * in display order. + * Note the buffers returned from codec driver may still be in driver's + * reference list. + */ +static struct vb2_buffer *get_display_buffer(struct mtk_vcodec_ctx *ctx) +{ + struct vdec_fb *disp_frame_buffer = NULL; + struct mtk_video_dec_buf *dstbuf; + struct vb2_v4l2_buffer *vb; + + mtk_v4l2_debug(3, "[%d]", ctx->id); + if (vdec_if_get_param(ctx, GET_PARAM_DISP_FRAME_BUFFER, + &disp_frame_buffer)) { + mtk_v4l2_err("[%d]Cannot get param : GET_PARAM_DISP_FRAME_BUFFER", ctx->id); + return NULL; + } + + if (!disp_frame_buffer) { + mtk_v4l2_debug(3, "No display frame buffer"); + return NULL; + } + + dstbuf = container_of(disp_frame_buffer, struct mtk_video_dec_buf, + frame_buffer); + vb = &dstbuf->m2m_buf.vb; + mutex_lock(&ctx->lock); + if (dstbuf->used) { + mtk_v4l2_debug(2, "[%d]status=%x queue id=%d to done_list %d", + ctx->id, disp_frame_buffer->status, + vb->vb2_buf.index, dstbuf->queued_in_vb2); + + v4l2_m2m_buf_done(vb, VB2_BUF_STATE_DONE); + ctx->decoded_frame_cnt++; + } + mutex_unlock(&ctx->lock); + return &vb->vb2_buf; +} + +/* + * This function tries to clean all capture buffers that are not used as + * reference buffers by codec driver any more + * In this case, we need re-queue buffer to vb2 buffer if user space + * already returns this buffer to v4l2 or this buffer is just the output of + * previous sps/pps/resolution change decode, or do nothing if user + * space still owns this buffer + */ +static struct vb2_buffer *get_free_buffer(struct mtk_vcodec_ctx *ctx) +{ + struct mtk_video_dec_buf *dstbuf; + struct vdec_fb *free_frame_buffer = NULL; + struct vb2_v4l2_buffer *vb; + + if (vdec_if_get_param(ctx, GET_PARAM_FREE_FRAME_BUFFER, + &free_frame_buffer)) { + mtk_v4l2_err("[%d] Error!! Cannot get param", ctx->id); + return NULL; + } + if (!free_frame_buffer) { + mtk_v4l2_debug(3, " No free frame buffer"); + return NULL; + } + + mtk_v4l2_debug(3, "[%d] tmp_frame_addr = 0x%p", ctx->id, + free_frame_buffer); + + dstbuf = container_of(free_frame_buffer, struct mtk_video_dec_buf, + frame_buffer); + vb = &dstbuf->m2m_buf.vb; + + mutex_lock(&ctx->lock); + if (dstbuf->used) { + if (dstbuf->queued_in_vb2 && dstbuf->queued_in_v4l2 && + free_frame_buffer->status == FB_ST_FREE) { + /* + * After decode sps/pps or non-display buffer, we don't + * need to return capture buffer to user space, but + * just re-queue this capture buffer to vb2 queue. + * This reduce overheads that dq/q unused capture + * buffer. In this case, queued_in_vb2 = true. + */ + mtk_v4l2_debug(2, "[%d]status=%x queue id=%d to rdy_queue %d", + ctx->id, free_frame_buffer->status, + vb->vb2_buf.index, dstbuf->queued_in_vb2); + v4l2_m2m_buf_queue(ctx->m2m_ctx, vb); + } else if (!dstbuf->queued_in_vb2 && dstbuf->queued_in_v4l2) { + /* + * If buffer in v4l2 driver but not in vb2 queue yet, + * and we get this buffer from free_list, it means + * that codec driver do not use this buffer as + * reference buffer anymore. We should q buffer to vb2 + * queue, so later work thread could get this buffer + * for decode. In this case, queued_in_vb2 = false + * means this buffer is not from previous decode + * output. + */ + mtk_v4l2_debug(2, + "[%d]status=%x queue id=%d to rdy_queue", + ctx->id, free_frame_buffer->status, + vb->vb2_buf.index); + v4l2_m2m_buf_queue(ctx->m2m_ctx, vb); + dstbuf->queued_in_vb2 = true; + } else { + /* + * Codec driver do not need to reference this capture + * buffer and this buffer is not in v4l2 driver. + * Then we don't need to do any thing, just add log when + * we need to debug buffer flow. + * When this buffer q from user space, it could + * directly q to vb2 buffer + */ + mtk_v4l2_debug(3, "[%d]status=%x err queue id=%d %d %d", + ctx->id, free_frame_buffer->status, + vb->vb2_buf.index, dstbuf->queued_in_vb2, + dstbuf->queued_in_v4l2); + } + dstbuf->used = false; + } + mutex_unlock(&ctx->lock); + return &vb->vb2_buf; +} + +static void clean_display_buffer(struct mtk_vcodec_ctx *ctx) +{ + while (get_display_buffer(ctx)) + ; +} + +static void clean_free_buffer(struct mtk_vcodec_ctx *ctx) +{ + while (get_free_buffer(ctx)) + ; +} + +static void mtk_vdec_queue_res_chg_event(struct mtk_vcodec_ctx *ctx) +{ + static const struct v4l2_event ev_src_ch = { + .type = V4L2_EVENT_SOURCE_CHANGE, + .u.src_change.changes = V4L2_EVENT_SRC_CH_RESOLUTION, + }; + + mtk_v4l2_debug(1, "[%d]", ctx->id); + v4l2_event_queue_fh(&ctx->fh, &ev_src_ch); +} + +static int mtk_vdec_flush_decoder(struct mtk_vcodec_ctx *ctx) +{ + bool res_chg; + int ret; + + ret = vdec_if_decode(ctx, NULL, NULL, &res_chg); + if (ret) + mtk_v4l2_err("DecodeFinal failed, ret=%d", ret); + + clean_display_buffer(ctx); + clean_free_buffer(ctx); + + return 0; +} + +static void mtk_vdec_update_fmt(struct mtk_vcodec_ctx *ctx, + unsigned int pixelformat) +{ + const struct mtk_video_fmt *fmt; + struct mtk_q_data *dst_q_data; + unsigned int k; + + dst_q_data = &ctx->q_data[MTK_Q_DATA_DST]; + for (k = 0; k < num_supported_formats; k++) { + fmt = &mtk_video_formats[k]; + if (fmt->fourcc == pixelformat) { + mtk_v4l2_debug(1, "Update cap fourcc(%d -> %d)", + dst_q_data->fmt->fourcc, pixelformat); + dst_q_data->fmt = fmt; + return; + } + } + + mtk_v4l2_err("Cannot get fourcc(%d), using init value", pixelformat); +} + +static int mtk_vdec_pic_info_update(struct mtk_vcodec_ctx *ctx) +{ + unsigned int dpbsize = 0; + int ret; + + if (vdec_if_get_param(ctx, GET_PARAM_PIC_INFO, + &ctx->last_decoded_picinfo)) { + mtk_v4l2_err("[%d]Error!! Cannot get param : GET_PARAM_PICTURE_INFO ERR", ctx->id); + return -EINVAL; + } + + if (ctx->last_decoded_picinfo.pic_w == 0 || + ctx->last_decoded_picinfo.pic_h == 0 || + ctx->last_decoded_picinfo.buf_w == 0 || + ctx->last_decoded_picinfo.buf_h == 0) { + mtk_v4l2_err("Cannot get correct pic info"); + return -EINVAL; + } + + if (ctx->last_decoded_picinfo.cap_fourcc != ctx->picinfo.cap_fourcc && + ctx->picinfo.cap_fourcc != 0) + mtk_vdec_update_fmt(ctx, ctx->picinfo.cap_fourcc); + + if (ctx->last_decoded_picinfo.pic_w == ctx->picinfo.pic_w || + ctx->last_decoded_picinfo.pic_h == ctx->picinfo.pic_h) + return 0; + + mtk_v4l2_debug(1, "[%d]-> new(%d,%d), old(%d,%d), real(%d,%d)", ctx->id, + ctx->last_decoded_picinfo.pic_w, + ctx->last_decoded_picinfo.pic_h, ctx->picinfo.pic_w, + ctx->picinfo.pic_h, ctx->last_decoded_picinfo.buf_w, + ctx->last_decoded_picinfo.buf_h); + + ret = vdec_if_get_param(ctx, GET_PARAM_DPB_SIZE, &dpbsize); + if (dpbsize == 0) + mtk_v4l2_err("Incorrect dpb size, ret=%d", ret); + + ctx->dpb_size = dpbsize; + + return ret; +} + +static void mtk_vdec_worker(struct work_struct *work) +{ + struct mtk_vcodec_ctx *ctx = + container_of(work, struct mtk_vcodec_ctx, decode_work); + struct mtk_vcodec_dev *dev = ctx->dev; + struct vb2_v4l2_buffer *src_buf, *dst_buf; + struct mtk_vcodec_mem buf; + struct vdec_fb *pfb; + bool res_chg = false; + int ret; + struct mtk_video_dec_buf *dst_buf_info, *src_buf_info; + + src_buf = v4l2_m2m_next_src_buf(ctx->m2m_ctx); + if (!src_buf) { + v4l2_m2m_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx); + mtk_v4l2_debug(1, "[%d] src_buf empty!!", ctx->id); + return; + } + + dst_buf = v4l2_m2m_next_dst_buf(ctx->m2m_ctx); + if (!dst_buf) { + v4l2_m2m_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx); + mtk_v4l2_debug(1, "[%d] dst_buf empty!!", ctx->id); + return; + } + + dst_buf_info = + container_of(dst_buf, struct mtk_video_dec_buf, m2m_buf.vb); + + pfb = &dst_buf_info->frame_buffer; + pfb->base_y.va = vb2_plane_vaddr(&dst_buf->vb2_buf, 0); + pfb->base_y.dma_addr = + vb2_dma_contig_plane_dma_addr(&dst_buf->vb2_buf, 0); + pfb->base_y.size = ctx->picinfo.fb_sz[0]; + + pfb->base_c.va = vb2_plane_vaddr(&dst_buf->vb2_buf, 1); + pfb->base_c.dma_addr = + vb2_dma_contig_plane_dma_addr(&dst_buf->vb2_buf, 1); + pfb->base_c.size = ctx->picinfo.fb_sz[1]; + pfb->status = 0; + mtk_v4l2_debug(3, "===>[%d] vdec_if_decode() ===>", ctx->id); + + mtk_v4l2_debug(3, + "id=%d Framebuf pfb=%p VA=%p Y_DMA=%pad C_DMA=%pad Size=%zx", + dst_buf->vb2_buf.index, pfb, pfb->base_y.va, + &pfb->base_y.dma_addr, &pfb->base_c.dma_addr, pfb->base_y.size); + + if (src_buf == &ctx->empty_flush_buf.vb) { + mtk_v4l2_debug(1, "Got empty flush input buffer."); + src_buf = v4l2_m2m_src_buf_remove(ctx->m2m_ctx); + + /* update dst buf status */ + dst_buf = v4l2_m2m_dst_buf_remove(ctx->m2m_ctx); + mutex_lock(&ctx->lock); + dst_buf_info->used = false; + mutex_unlock(&ctx->lock); + + vdec_if_decode(ctx, NULL, NULL, &res_chg); + clean_display_buffer(ctx); + vb2_set_plane_payload(&dst_buf->vb2_buf, 0, 0); + if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2) + vb2_set_plane_payload(&dst_buf->vb2_buf, 1, 0); + dst_buf->flags |= V4L2_BUF_FLAG_LAST; + v4l2_m2m_buf_done(dst_buf, VB2_BUF_STATE_DONE); + clean_free_buffer(ctx); + v4l2_m2m_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx); + return; + } + + src_buf_info = + container_of(src_buf, struct mtk_video_dec_buf, m2m_buf.vb); + + buf.va = vb2_plane_vaddr(&src_buf->vb2_buf, 0); + buf.dma_addr = vb2_dma_contig_plane_dma_addr(&src_buf->vb2_buf, 0); + buf.size = (size_t)src_buf->vb2_buf.planes[0].bytesused; + if (!buf.va) { + v4l2_m2m_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx); + mtk_v4l2_err("[%d] id=%d src_addr is NULL!!", ctx->id, + src_buf->vb2_buf.index); + return; + } + mtk_v4l2_debug(3, "[%d] Bitstream VA=%p DMA=%pad Size=%zx vb=%p", + ctx->id, buf.va, &buf.dma_addr, buf.size, src_buf); + dst_buf->vb2_buf.timestamp = src_buf->vb2_buf.timestamp; + dst_buf->timecode = src_buf->timecode; + mutex_lock(&ctx->lock); + dst_buf_info->used = true; + mutex_unlock(&ctx->lock); + src_buf_info->used = true; + + ret = vdec_if_decode(ctx, &buf, pfb, &res_chg); + + if (ret) { + mtk_v4l2_err(" <===[%d], src_buf[%d] sz=0x%zx pts=%llu dst_buf[%d] vdec_if_decode() ret=%d res_chg=%d===>", + ctx->id, src_buf->vb2_buf.index, buf.size, + src_buf->vb2_buf.timestamp, dst_buf->vb2_buf.index, ret, res_chg); + src_buf = v4l2_m2m_src_buf_remove(ctx->m2m_ctx); + if (ret == -EIO) { + mutex_lock(&ctx->lock); + src_buf_info->error = true; + mutex_unlock(&ctx->lock); + } + v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_ERROR); + } else if (!res_chg) { + /* + * we only return src buffer with VB2_BUF_STATE_DONE + * when decode success without resolution change + */ + src_buf = v4l2_m2m_src_buf_remove(ctx->m2m_ctx); + v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE); + } + + dst_buf = v4l2_m2m_dst_buf_remove(ctx->m2m_ctx); + clean_display_buffer(ctx); + clean_free_buffer(ctx); + + if (!ret && res_chg) { + mtk_vdec_pic_info_update(ctx); + /* + * On encountering a resolution change in the stream. + * The driver must first process and decode all + * remaining buffers from before the resolution change + * point, so call flush decode here + */ + mtk_vdec_flush_decoder(ctx); + /* + * After all buffers containing decoded frames from + * before the resolution change point ready to be + * dequeued on the CAPTURE queue, the driver sends a + * V4L2_EVENT_SOURCE_CHANGE event for source change + * type V4L2_EVENT_SRC_CH_RESOLUTION + */ + mtk_vdec_queue_res_chg_event(ctx); + } + v4l2_m2m_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx); +} + +static void vb2ops_vdec_stateful_buf_queue(struct vb2_buffer *vb) +{ + struct vb2_v4l2_buffer *src_buf; + struct mtk_vcodec_mem src_mem; + bool res_chg = false; + int ret; + unsigned int dpbsize = 1, i; + struct mtk_vcodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue); + struct vb2_v4l2_buffer *vb2_v4l2; + struct mtk_q_data *dst_q_data; + + mtk_v4l2_debug(3, "[%d] (%d) id=%d, vb=%p", ctx->id, + vb->vb2_queue->type, vb->index, vb); + /* + * check if this buffer is ready to be used after decode + */ + if (vb->vb2_queue->type != V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) { + struct mtk_video_dec_buf *buf; + + vb2_v4l2 = to_vb2_v4l2_buffer(vb); + buf = container_of(vb2_v4l2, struct mtk_video_dec_buf, + m2m_buf.vb); + mutex_lock(&ctx->lock); + if (!buf->used) { + v4l2_m2m_buf_queue(ctx->m2m_ctx, vb2_v4l2); + buf->queued_in_vb2 = true; + buf->queued_in_v4l2 = true; + } else { + buf->queued_in_vb2 = false; + buf->queued_in_v4l2 = true; + } + mutex_unlock(&ctx->lock); + return; + } + + v4l2_m2m_buf_queue(ctx->m2m_ctx, to_vb2_v4l2_buffer(vb)); + + if (ctx->state != MTK_STATE_INIT) { + mtk_v4l2_debug(3, "[%d] already init driver %d", ctx->id, + ctx->state); + return; + } + + src_buf = v4l2_m2m_next_src_buf(ctx->m2m_ctx); + if (!src_buf) { + mtk_v4l2_err("No src buffer"); + return; + } + + if (src_buf == &ctx->empty_flush_buf.vb) { + /* This shouldn't happen. Just in case. */ + mtk_v4l2_err("Invalid flush buffer."); + v4l2_m2m_src_buf_remove(ctx->m2m_ctx); + return; + } + + src_mem.va = vb2_plane_vaddr(&src_buf->vb2_buf, 0); + src_mem.dma_addr = vb2_dma_contig_plane_dma_addr(&src_buf->vb2_buf, 0); + src_mem.size = (size_t)src_buf->vb2_buf.planes[0].bytesused; + mtk_v4l2_debug(2, "[%d] buf id=%d va=%p dma=%pad size=%zx", ctx->id, + src_buf->vb2_buf.index, src_mem.va, &src_mem.dma_addr, + src_mem.size); + + ret = vdec_if_decode(ctx, &src_mem, NULL, &res_chg); + if (ret || !res_chg) { + /* + * fb == NULL means to parse SPS/PPS header or + * resolution info in src_mem. Decode can fail + * if there is no SPS header or picture info + * in bs + */ + + src_buf = v4l2_m2m_src_buf_remove(ctx->m2m_ctx); + if (ret == -EIO) { + mtk_v4l2_err("[%d] Unrecoverable error in vdec_if_decode.", ctx->id); + ctx->state = MTK_STATE_ABORT; + v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_ERROR); + } else { + v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE); + } + mtk_v4l2_debug(ret ? 0 : 1, + "[%d] vdec_if_decode() src_buf=%d, size=%zu, fail=%d, res_chg=%d", + ctx->id, src_buf->vb2_buf.index, src_mem.size, ret, res_chg); + return; + } + + if (vdec_if_get_param(ctx, GET_PARAM_PIC_INFO, &ctx->picinfo)) { + mtk_v4l2_err("[%d]Error!! Cannot get param : GET_PARAM_PICTURE_INFO ERR", ctx->id); + return; + } + + ctx->last_decoded_picinfo = ctx->picinfo; + dst_q_data = &ctx->q_data[MTK_Q_DATA_DST]; + for (i = 0; i < dst_q_data->fmt->num_planes; i++) { + dst_q_data->sizeimage[i] = ctx->picinfo.fb_sz[i]; + dst_q_data->bytesperline[i] = ctx->picinfo.buf_w; + } + + mtk_v4l2_debug(2, "[%d] vdec_if_init() OK wxh=%dx%d pic wxh=%dx%d sz[0]=0x%x sz[1]=0x%x", + ctx->id, ctx->picinfo.buf_w, ctx->picinfo.buf_h, ctx->picinfo.pic_w, + ctx->picinfo.pic_h, dst_q_data->sizeimage[0], dst_q_data->sizeimage[1]); + + ret = vdec_if_get_param(ctx, GET_PARAM_DPB_SIZE, &dpbsize); + if (dpbsize == 0) + mtk_v4l2_err("[%d] GET_PARAM_DPB_SIZE fail=%d", ctx->id, ret); + + ctx->dpb_size = dpbsize; + ctx->state = MTK_STATE_HEADER; + mtk_v4l2_debug(1, "[%d] dpbsize=%d", ctx->id, ctx->dpb_size); + + mtk_vdec_queue_res_chg_event(ctx); +} + +static int mtk_vdec_g_v_ctrl(struct v4l2_ctrl *ctrl) +{ + struct mtk_vcodec_ctx *ctx = ctrl_to_ctx(ctrl); + int ret = 0; + + switch (ctrl->id) { + case V4L2_CID_MIN_BUFFERS_FOR_CAPTURE: + if (ctx->state >= MTK_STATE_HEADER) { + ctrl->val = ctx->dpb_size; + } else { + mtk_v4l2_debug(0, "Seqinfo not ready"); + ctrl->val = 0; + } + break; + default: + ret = -EINVAL; + } + return ret; +} + +static const struct v4l2_ctrl_ops mtk_vcodec_dec_ctrl_ops = { + .g_volatile_ctrl = mtk_vdec_g_v_ctrl, +}; + +static int mtk_vcodec_dec_ctrls_setup(struct mtk_vcodec_ctx *ctx) +{ + struct v4l2_ctrl *ctrl; + + v4l2_ctrl_handler_init(&ctx->ctrl_hdl, 1); + + ctrl = v4l2_ctrl_new_std(&ctx->ctrl_hdl, &mtk_vcodec_dec_ctrl_ops, + V4L2_CID_MIN_BUFFERS_FOR_CAPTURE, 0, 32, 1, 1); + ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE; + v4l2_ctrl_new_std_menu(&ctx->ctrl_hdl, &mtk_vcodec_dec_ctrl_ops, + V4L2_CID_MPEG_VIDEO_VP9_PROFILE, + V4L2_MPEG_VIDEO_VP9_PROFILE_0, 0, + V4L2_MPEG_VIDEO_VP9_PROFILE_0); + /* + * H264. Baseline / Extended decoding is not supported. + */ + v4l2_ctrl_new_std_menu(&ctx->ctrl_hdl, &mtk_vcodec_dec_ctrl_ops, + V4L2_CID_MPEG_VIDEO_H264_PROFILE, V4L2_MPEG_VIDEO_H264_PROFILE_HIGH, + BIT(V4L2_MPEG_VIDEO_H264_PROFILE_BASELINE) | + BIT(V4L2_MPEG_VIDEO_H264_PROFILE_EXTENDED), + V4L2_MPEG_VIDEO_H264_PROFILE_MAIN); + + if (ctx->ctrl_hdl.error) { + mtk_v4l2_err("Adding control failed %d", ctx->ctrl_hdl.error); + return ctx->ctrl_hdl.error; + } + + v4l2_ctrl_handler_setup(&ctx->ctrl_hdl); + return 0; +} + +static void mtk_init_vdec_params(struct mtk_vcodec_ctx *ctx) +{ +} + +static struct vb2_ops mtk_vdec_frame_vb2_ops = { + .queue_setup = vb2ops_vdec_queue_setup, + .buf_prepare = vb2ops_vdec_buf_prepare, + .wait_prepare = vb2_ops_wait_prepare, + .wait_finish = vb2_ops_wait_finish, + .start_streaming = vb2ops_vdec_start_streaming, + + .buf_queue = vb2ops_vdec_stateful_buf_queue, + .buf_init = vb2ops_vdec_buf_init, + .buf_finish = vb2ops_vdec_buf_finish, + .stop_streaming = vb2ops_vdec_stop_streaming, +}; + +const struct mtk_vcodec_dec_pdata mtk_vdec_8173_pdata = { + .init_vdec_params = mtk_init_vdec_params, + .ctrls_setup = mtk_vcodec_dec_ctrls_setup, + .vdec_vb2_ops = &mtk_vdec_frame_vb2_ops, + .vdec_formats = mtk_video_formats, + .num_formats = &num_supported_formats, + .default_out_fmt = &mtk_video_formats[DEFAULT_OUT_FMT_IDX], + .default_cap_fmt = &mtk_video_formats[DEFAULT_CAP_FMT_IDX], + .worker = mtk_vdec_worker, + .flush_decoder = mtk_vdec_flush_decoder, + .is_subdev_supported = false, + .hw_arch = MTK_VDEC_PURE_SINGLE_CORE, +}; -- cgit v1.2.3