diff options
Diffstat (limited to 'drivers/media/platform/qcom')
-rw-r--r-- | drivers/media/platform/qcom/venus/core.c | 56 | ||||
-rw-r--r-- | drivers/media/platform/qcom/venus/core.h | 30 | ||||
-rw-r--r-- | drivers/media/platform/qcom/venus/helpers.c | 247 | ||||
-rw-r--r-- | drivers/media/platform/qcom/venus/helpers.h | 3 | ||||
-rw-r--r-- | drivers/media/platform/qcom/venus/hfi_venus.c | 6 | ||||
-rw-r--r-- | drivers/media/platform/qcom/venus/vdec.c | 11 | ||||
-rw-r--r-- | drivers/media/platform/qcom/venus/venc.c | 7 |
7 files changed, 330 insertions, 30 deletions
diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c index e6eff512a8a1..07312a2fab24 100644 --- a/drivers/media/platform/qcom/venus/core.c +++ b/drivers/media/platform/qcom/venus/core.c @@ -5,6 +5,7 @@ */ #include <linux/clk.h> #include <linux/init.h> +#include <linux/interconnect.h> #include <linux/ioctl.h> #include <linux/list.h> #include <linux/module.h> @@ -239,6 +240,14 @@ static int venus_probe(struct platform_device *pdev) if (IS_ERR(core->base)) return PTR_ERR(core->base); + core->video_path = of_icc_get(dev, "video-mem"); + if (IS_ERR(core->video_path)) + return PTR_ERR(core->video_path); + + core->cpucfg_path = of_icc_get(dev, "cpu-cfg"); + if (IS_ERR(core->cpucfg_path)) + return PTR_ERR(core->cpucfg_path); + core->irq = platform_get_irq(pdev, 0); if (core->irq < 0) return core->irq; @@ -273,6 +282,10 @@ static int venus_probe(struct platform_device *pdev) if (ret) return ret; + ret = icc_set_bw(core->cpucfg_path, 0, kbps_to_icc(1000)); + if (ret) + return ret; + ret = hfi_create(core, &venus_core_ops); if (ret) return ret; @@ -355,6 +368,9 @@ static int venus_remove(struct platform_device *pdev) pm_runtime_put_sync(dev); pm_runtime_disable(dev); + icc_put(core->video_path); + icc_put(core->cpucfg_path); + v4l2_device_unregister(&core->v4l2_dev); return ret; @@ -427,10 +443,11 @@ static const struct venus_resources msm8916_res = { }; static const struct freq_tbl msm8996_freq_table[] = { - { 1944000, 490000000 }, /* 4k UHD @ 60 */ - { 972000, 320000000 }, /* 4k UHD @ 30 */ - { 489600, 150000000 }, /* 1080p @ 60 */ - { 244800, 75000000 }, /* 1080p @ 30 */ + { 1944000, 520000000 }, /* 4k UHD @ 60 (decode only) */ + { 972000, 520000000 }, /* 4k UHD @ 30 */ + { 489600, 346666667 }, /* 1080p @ 60 */ + { 244800, 150000000 }, /* 1080p @ 30 */ + { 108000, 75000000 }, /* 720p @ 30 */ }; static const struct reg_val msm8996_reg_preset[] = { @@ -464,9 +481,40 @@ static const struct freq_tbl sdm845_freq_table[] = { { 244800, 100000000 }, /* 1920x1080@30 */ }; +static struct codec_freq_data sdm845_codec_freq_data[] = { + { V4L2_PIX_FMT_H264, VIDC_SESSION_TYPE_ENC, 675, 10 }, + { V4L2_PIX_FMT_HEVC, VIDC_SESSION_TYPE_ENC, 675, 10 }, + { V4L2_PIX_FMT_VP8, VIDC_SESSION_TYPE_ENC, 675, 10 }, + { V4L2_PIX_FMT_MPEG2, VIDC_SESSION_TYPE_DEC, 200, 10 }, + { V4L2_PIX_FMT_H264, VIDC_SESSION_TYPE_DEC, 200, 10 }, + { V4L2_PIX_FMT_HEVC, VIDC_SESSION_TYPE_DEC, 200, 10 }, + { V4L2_PIX_FMT_VP8, VIDC_SESSION_TYPE_DEC, 200, 10 }, + { V4L2_PIX_FMT_VP9, VIDC_SESSION_TYPE_DEC, 200, 10 }, +}; + +static const struct bw_tbl sdm845_bw_table_enc[] = { + { 1944000, 1612000, 0, 2416000, 0 }, /* 3840x2160@60 */ + { 972000, 951000, 0, 1434000, 0 }, /* 3840x2160@30 */ + { 489600, 723000, 0, 973000, 0 }, /* 1920x1080@60 */ + { 244800, 370000, 0, 495000, 0 }, /* 1920x1080@30 */ +}; + +static const struct bw_tbl sdm845_bw_table_dec[] = { + { 2073600, 3929000, 0, 5551000, 0 }, /* 4096x2160@60 */ + { 1036800, 1987000, 0, 2797000, 0 }, /* 4096x2160@30 */ + { 489600, 1040000, 0, 1298000, 0 }, /* 1920x1080@60 */ + { 244800, 530000, 0, 659000, 0 }, /* 1920x1080@30 */ +}; + static const struct venus_resources sdm845_res = { .freq_tbl = sdm845_freq_table, .freq_tbl_size = ARRAY_SIZE(sdm845_freq_table), + .bw_tbl_enc = sdm845_bw_table_enc, + .bw_tbl_enc_size = ARRAY_SIZE(sdm845_bw_table_enc), + .bw_tbl_dec = sdm845_bw_table_dec, + .bw_tbl_dec_size = ARRAY_SIZE(sdm845_bw_table_dec), + .codec_freq_data = sdm845_codec_freq_data, + .codec_freq_data_size = ARRAY_SIZE(sdm845_codec_freq_data), .clks = {"core", "iface", "bus" }, .clks_num = 3, .max_load = 3110400, /* 4096x2160@90 */ diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h index 922cb7e64bfa..11585fb3cae3 100644 --- a/drivers/media/platform/qcom/venus/core.h +++ b/drivers/media/platform/qcom/venus/core.h @@ -26,12 +26,33 @@ struct reg_val { u32 value; }; +struct codec_freq_data { + u32 pixfmt; + u32 session_type; + unsigned long vpp_freq; + unsigned long vsp_freq; +}; + +struct bw_tbl { + u32 mbs_per_sec; + u32 avg; + u32 peak; + u32 avg_10bit; + u32 peak_10bit; +}; + struct venus_resources { u64 dma_mask; const struct freq_tbl *freq_tbl; unsigned int freq_tbl_size; + const struct bw_tbl *bw_tbl_enc; + unsigned int bw_tbl_enc_size; + const struct bw_tbl *bw_tbl_dec; + unsigned int bw_tbl_dec_size; const struct reg_val *reg_tbl; unsigned int reg_tbl_size; + const struct codec_freq_data *codec_freq_data; + unsigned int codec_freq_data_size; const char * const clks[VIDC_CLKS_NUM_MAX]; unsigned int clks_num; enum hfi_version hfi_version; @@ -115,6 +136,8 @@ struct venus_core { struct clk *core1_clk; struct clk *core0_bus_clk; struct clk *core1_bus_clk; + struct icc_path *video_path; + struct icc_path *cpucfg_path; struct video_device *vdev_dec; struct video_device *vdev_enc; struct v4l2_device v4l2_dev; @@ -208,6 +231,12 @@ struct venus_buffer { struct list_head ref_list; }; +struct clock_data { + u32 core_id; + unsigned long freq; + const struct codec_freq_data *codec_freq_data; +}; + #define to_venus_buffer(ptr) container_of(ptr, struct venus_buffer, vb) enum venus_dec_state { @@ -288,6 +317,7 @@ struct venus_inst { struct list_head list; struct mutex lock; struct venus_core *core; + struct clock_data clk_data; struct list_head dpbbufs; struct list_head internalbufs; struct list_head registeredbufs; diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c index 1ad96c25ab09..a172f1ac0b35 100644 --- a/drivers/media/platform/qcom/venus/helpers.c +++ b/drivers/media/platform/qcom/venus/helpers.c @@ -5,6 +5,7 @@ */ #include <linux/clk.h> #include <linux/iopoll.h> +#include <linux/interconnect.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/pm_runtime.h> @@ -388,12 +389,91 @@ static u32 load_per_type(struct venus_core *core, u32 session_type) return mbs_per_sec; } -int venus_helper_load_scale_clocks(struct venus_core *core) +static void mbs_to_bw(struct venus_inst *inst, u32 mbs, u32 *avg, u32 *peak) { + const struct venus_resources *res = inst->core->res; + const struct bw_tbl *bw_tbl; + unsigned int num_rows, i; + + *avg = 0; + *peak = 0; + + if (mbs == 0) + return; + + if (inst->session_type == VIDC_SESSION_TYPE_ENC) { + num_rows = res->bw_tbl_enc_size; + bw_tbl = res->bw_tbl_enc; + } else if (inst->session_type == VIDC_SESSION_TYPE_DEC) { + num_rows = res->bw_tbl_dec_size; + bw_tbl = res->bw_tbl_dec; + } else { + return; + } + + if (!bw_tbl || num_rows == 0) + return; + + for (i = 0; i < num_rows; i++) { + if (mbs > bw_tbl[i].mbs_per_sec) + break; + + if (inst->dpb_fmt & HFI_COLOR_FORMAT_10_BIT_BASE) { + *avg = bw_tbl[i].avg_10bit; + *peak = bw_tbl[i].peak_10bit; + } else { + *avg = bw_tbl[i].avg; + *peak = bw_tbl[i].peak; + } + } +} + +static int load_scale_bw(struct venus_core *core) +{ + struct venus_inst *inst = NULL; + u32 mbs_per_sec, avg, peak, total_avg = 0, total_peak = 0; + + mutex_lock(&core->lock); + list_for_each_entry(inst, &core->instances, list) { + mbs_per_sec = load_per_instance(inst); + mbs_to_bw(inst, mbs_per_sec, &avg, &peak); + total_avg += avg; + total_peak += peak; + } + mutex_unlock(&core->lock); + + dev_dbg(core->dev, "total: avg_bw: %u, peak_bw: %u\n", + total_avg, total_peak); + + return icc_set_bw(core->video_path, total_avg, total_peak); +} + +static int set_clk_freq(struct venus_core *core, unsigned long freq) +{ + struct clk *clk = core->clks[0]; + int ret; + + ret = clk_set_rate(clk, freq); + if (ret) + return ret; + + ret = clk_set_rate(core->core0_clk, freq); + if (ret) + return ret; + + ret = clk_set_rate(core->core1_clk, freq); + if (ret) + return ret; + + return 0; +} + +static int scale_clocks(struct venus_inst *inst) +{ + struct venus_core *core = inst->core; const struct freq_tbl *table = core->res->freq_tbl; unsigned int num_rows = core->res->freq_tbl_size; unsigned long freq = table[0].freq; - struct clk *clk = core->clks[0]; struct device *dev = core->dev; u32 mbs_per_sec; unsigned int i; @@ -419,23 +499,124 @@ int venus_helper_load_scale_clocks(struct venus_core *core) set_freq: - ret = clk_set_rate(clk, freq); - if (ret) - goto err; + ret = set_clk_freq(core, freq); + if (ret) { + dev_err(dev, "failed to set clock rate %lu (%d)\n", + freq, ret); + return ret; + } - ret = clk_set_rate(core->core0_clk, freq); - if (ret) - goto err; + ret = load_scale_bw(core); + if (ret) { + dev_err(dev, "failed to set bandwidth (%d)\n", + ret); + return ret; + } - ret = clk_set_rate(core->core1_clk, freq); - if (ret) - goto err; + return 0; +} + +static unsigned long calculate_inst_freq(struct venus_inst *inst, + unsigned long filled_len) +{ + unsigned long vpp_freq = 0, vsp_freq = 0; + u32 fps = (u32)inst->fps; + u32 mbs_per_sec; + + mbs_per_sec = load_per_instance(inst) / fps; + + vpp_freq = mbs_per_sec * inst->clk_data.codec_freq_data->vpp_freq; + /* 21 / 20 is overhead factor */ + vpp_freq += vpp_freq / 20; + vsp_freq = mbs_per_sec * inst->clk_data.codec_freq_data->vsp_freq; + + /* 10 / 7 is overhead factor */ + if (inst->session_type == VIDC_SESSION_TYPE_ENC) + vsp_freq += (inst->controls.enc.bitrate * 10) / 7; + else + vsp_freq += ((fps * filled_len * 8) * 10) / 7; + + return max(vpp_freq, vsp_freq); +} + +static int scale_clocks_v4(struct venus_inst *inst) +{ + struct venus_core *core = inst->core; + const struct freq_tbl *table = core->res->freq_tbl; + unsigned int num_rows = core->res->freq_tbl_size; + struct v4l2_m2m_ctx *m2m_ctx = inst->m2m_ctx; + struct device *dev = core->dev; + unsigned long freq = 0, freq_core1 = 0, freq_core2 = 0; + unsigned long filled_len = 0; + struct venus_buffer *buf, *n; + struct vb2_buffer *vb; + int i, ret; + + v4l2_m2m_for_each_src_buf_safe(m2m_ctx, buf, n) { + vb = &buf->vb.vb2_buf; + filled_len = max(filled_len, vb2_get_plane_payload(vb, 0)); + } + + if (inst->session_type == VIDC_SESSION_TYPE_DEC && !filled_len) + return 0; + + freq = calculate_inst_freq(inst, filled_len); + inst->clk_data.freq = freq; + + mutex_lock(&core->lock); + list_for_each_entry(inst, &core->instances, list) { + if (inst->clk_data.core_id == VIDC_CORE_ID_1) { + freq_core1 += inst->clk_data.freq; + } else if (inst->clk_data.core_id == VIDC_CORE_ID_2) { + freq_core2 += inst->clk_data.freq; + } else if (inst->clk_data.core_id == VIDC_CORE_ID_3) { + freq_core1 += inst->clk_data.freq; + freq_core2 += inst->clk_data.freq; + } + } + mutex_unlock(&core->lock); + + freq = max(freq_core1, freq_core2); + + if (freq >= table[0].freq) { + freq = table[0].freq; + dev_warn(dev, "HW is overloaded, needed: %lu max: %lu\n", + freq, table[0].freq); + goto set_freq; + } + + for (i = num_rows - 1 ; i >= 0; i--) { + if (freq <= table[i].freq) { + freq = table[i].freq; + break; + } + } + +set_freq: + + ret = set_clk_freq(core, freq); + if (ret) { + dev_err(dev, "failed to set clock rate %lu (%d)\n", + freq, ret); + return ret; + } + + ret = load_scale_bw(core); + if (ret) { + dev_err(dev, "failed to set bandwidth (%d)\n", + ret); + return ret; + } return 0; +} -err: - dev_err(dev, "failed to set clock rate %lu (%d)\n", freq, ret); - return ret; +int venus_helper_load_scale_clocks(struct venus_inst *inst) +{ + if (IS_V4(inst->core)) + return scale_clocks_v4(inst); + + return scale_clocks(inst); } EXPORT_SYMBOL_GPL(venus_helper_load_scale_clocks); @@ -541,6 +722,8 @@ session_process_buf(struct venus_inst *inst, struct vb2_v4l2_buffer *vbuf) if (inst->session_type == VIDC_SESSION_TYPE_DEC) put_ts_metadata(inst, vbuf); + + venus_helper_load_scale_clocks(inst); } else if (type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) { if (inst->session_type == VIDC_SESSION_TYPE_ENC) fdata.buffer_type = HFI_BUFFER_OUTPUT; @@ -809,6 +992,7 @@ int venus_helper_set_core_usage(struct venus_inst *inst, u32 usage) const u32 ptype = HFI_PROPERTY_CONFIG_VIDEOCORES_USAGE; struct hfi_videocores_usage_type cu; + inst->clk_data.core_id = usage; if (!IS_V4(inst->core)) return 0; @@ -818,6 +1002,36 @@ int venus_helper_set_core_usage(struct venus_inst *inst, u32 usage) } EXPORT_SYMBOL_GPL(venus_helper_set_core_usage); +int venus_helper_init_codec_freq_data(struct venus_inst *inst) +{ + const struct codec_freq_data *data; + unsigned int i, data_size; + u32 pixfmt; + int ret = 0; + + if (!IS_V4(inst->core)) + return 0; + + data = inst->core->res->codec_freq_data; + data_size = inst->core->res->codec_freq_data_size; + pixfmt = inst->session_type == VIDC_SESSION_TYPE_DEC ? + inst->fmt_out->pixfmt : inst->fmt_cap->pixfmt; + + for (i = 0; i < data_size; i++) { + if (data[i].pixfmt == pixfmt && + data[i].session_type == inst->session_type) { + inst->clk_data.codec_freq_data = &data[i]; + break; + } + } + + if (!inst->clk_data.codec_freq_data) + ret = -EINVAL; + + return ret; +} +EXPORT_SYMBOL_GPL(venus_helper_init_codec_freq_data); + int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs, unsigned int output_bufs, unsigned int output2_bufs) @@ -1140,7 +1354,7 @@ void venus_helper_vb2_stop_streaming(struct vb2_queue *q) venus_helper_free_dpb_bufs(inst); - venus_helper_load_scale_clocks(core); + venus_helper_load_scale_clocks(inst); INIT_LIST_HEAD(&inst->registeredbufs); } @@ -1193,7 +1407,6 @@ EXPORT_SYMBOL_GPL(venus_helper_process_initial_out_bufs); int venus_helper_vb2_start_streaming(struct venus_inst *inst) { - struct venus_core *core = inst->core; int ret; ret = venus_helper_intbufs_alloc(inst); @@ -1204,7 +1417,7 @@ int venus_helper_vb2_start_streaming(struct venus_inst *inst) if (ret) goto err_bufs_free; - venus_helper_load_scale_clocks(core); + venus_helper_load_scale_clocks(inst); ret = hfi_session_load_res(inst); if (ret) diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h index 01f411b12f81..34dcd0c13f06 100644 --- a/drivers/media/platform/qcom/venus/helpers.h +++ b/drivers/media/platform/qcom/venus/helpers.h @@ -33,6 +33,7 @@ int venus_helper_set_output_resolution(struct venus_inst *inst, unsigned int width, unsigned int height, u32 buftype); int venus_helper_set_work_mode(struct venus_inst *inst, u32 mode); +int venus_helper_init_codec_freq_data(struct venus_inst *inst); int venus_helper_set_core_usage(struct venus_inst *inst, u32 usage); int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs, unsigned int output_bufs, @@ -59,7 +60,7 @@ int venus_helper_intbufs_free(struct venus_inst *inst); int venus_helper_intbufs_realloc(struct venus_inst *inst); int venus_helper_queue_dpb_bufs(struct venus_inst *inst); int venus_helper_unregister_bufs(struct venus_inst *inst); -int venus_helper_load_scale_clocks(struct venus_core *core); +int venus_helper_load_scale_clocks(struct venus_inst *inst); int venus_helper_process_initial_cap_bufs(struct venus_inst *inst); int venus_helper_process_initial_out_bufs(struct venus_inst *inst); void venus_helper_get_ts_metadata(struct venus_inst *inst, u64 timestamp_us, diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c index 7129a2aea09a..0d8855014ab3 100644 --- a/drivers/media/platform/qcom/venus/hfi_venus.c +++ b/drivers/media/platform/qcom/venus/hfi_venus.c @@ -1472,6 +1472,7 @@ static int venus_suspend_3xx(struct venus_core *core) { struct venus_hfi_device *hdev = to_hfi_priv(core); struct device *dev = core->dev; + u32 ctrl_status; bool val; int ret; @@ -1487,6 +1488,10 @@ static int venus_suspend_3xx(struct venus_core *core) return -EINVAL; } + ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0); + if (ctrl_status & CPU_CS_SCIACMDARG0_PC_READY) + goto power_off; + /* * Power collapse sequence for Venus 3xx and 4xx versions: * 1. Check for ARM9 and video core to be idle by checking WFI bit @@ -1511,6 +1516,7 @@ static int venus_suspend_3xx(struct venus_core *core) if (ret) return ret; +power_off: mutex_lock(&hdev->lock); ret = venus_power_off(hdev); diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index 7f4660555ddb..8feaf5daece9 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -685,6 +685,10 @@ static int vdec_session_init(struct venus_inst *inst) if (ret) goto deinit; + ret = venus_helper_init_codec_freq_data(inst); + if (ret) + goto deinit; + return 0; deinit: hfi_session_deinit(inst); @@ -864,7 +868,7 @@ reconfigure: if (ret) goto free_dpb_bufs; - venus_helper_load_scale_clocks(inst->core); + venus_helper_load_scale_clocks(inst); ret = hfi_session_continue(inst); if (ret) @@ -1072,7 +1076,7 @@ static void vdec_session_release(struct venus_inst *inst) hfi_session_abort(inst); venus_helper_free_dpb_bufs(inst); - venus_helper_load_scale_clocks(core); + venus_helper_load_scale_clocks(inst); INIT_LIST_HEAD(&inst->registeredbufs); mutex_unlock(&inst->lock); @@ -1412,9 +1416,6 @@ static const struct v4l2_file_operations vdec_fops = { .unlocked_ioctl = video_ioctl2, .poll = v4l2_m2m_fop_poll, .mmap = v4l2_m2m_fop_mmap, -#ifdef CONFIG_COMPAT - .compat_ioctl32 = v4l2_compat_ioctl32, -#endif }; static int vdec_probe(struct platform_device *pdev) diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c index 1b7fb2d5887c..453edf966d4f 100644 --- a/drivers/media/platform/qcom/venus/venc.c +++ b/drivers/media/platform/qcom/venus/venc.c @@ -842,6 +842,10 @@ static int venc_init_session(struct venus_inst *inst) if (ret) goto deinit; + ret = venus_helper_init_codec_freq_data(inst); + if (ret) + goto deinit; + ret = venc_set_properties(inst); if (ret) goto deinit; @@ -1235,9 +1239,6 @@ static const struct v4l2_file_operations venc_fops = { .unlocked_ioctl = video_ioctl2, .poll = v4l2_m2m_fop_poll, .mmap = v4l2_m2m_fop_mmap, -#ifdef CONFIG_COMPAT - .compat_ioctl32 = v4l2_compat_ioctl32, -#endif }; static int venc_probe(struct platform_device *pdev) |