diff options
Diffstat (limited to 'drivers/media/platform/ti-vpe')
-rw-r--r-- | drivers/media/platform/ti-vpe/Makefile | 5 | ||||
-rw-r--r-- | drivers/media/platform/ti-vpe/vpdma.c | 846 | ||||
-rw-r--r-- | drivers/media/platform/ti-vpe/vpdma.h | 203 | ||||
-rw-r--r-- | drivers/media/platform/ti-vpe/vpdma_priv.h | 641 | ||||
-rw-r--r-- | drivers/media/platform/ti-vpe/vpe.c | 2099 | ||||
-rw-r--r-- | drivers/media/platform/ti-vpe/vpe_regs.h | 496 |
6 files changed, 4290 insertions, 0 deletions
diff --git a/drivers/media/platform/ti-vpe/Makefile b/drivers/media/platform/ti-vpe/Makefile new file mode 100644 index 000000000000..cbf0a806ba1d --- /dev/null +++ b/drivers/media/platform/ti-vpe/Makefile @@ -0,0 +1,5 @@ +obj-$(CONFIG_VIDEO_TI_VPE) += ti-vpe.o + +ti-vpe-y := vpe.o vpdma.o + +ccflags-$(CONFIG_VIDEO_TI_VPE_DEBUG) += -DDEBUG diff --git a/drivers/media/platform/ti-vpe/vpdma.c b/drivers/media/platform/ti-vpe/vpdma.c new file mode 100644 index 000000000000..af0a5ffcaa98 --- /dev/null +++ b/drivers/media/platform/ti-vpe/vpdma.c @@ -0,0 +1,846 @@ +/* + * VPDMA helper library + * + * Copyright (c) 2013 Texas Instruments Inc. + * + * David Griego, <dagriego@biglakesoftware.com> + * Dale Farnsworth, <dale@farnsworth.org> + * Archit Taneja, <archit@ti.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/delay.h> +#include <linux/dma-mapping.h> +#include <linux/err.h> +#include <linux/firmware.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/videodev2.h> + +#include "vpdma.h" +#include "vpdma_priv.h" + +#define VPDMA_FIRMWARE "vpdma-1b8.bin" + +const struct vpdma_data_format vpdma_yuv_fmts[] = { + [VPDMA_DATA_FMT_Y444] = { + .data_type = DATA_TYPE_Y444, + .depth = 8, + }, + [VPDMA_DATA_FMT_Y422] = { + .data_type = DATA_TYPE_Y422, + .depth = 8, + }, + [VPDMA_DATA_FMT_Y420] = { + .data_type = DATA_TYPE_Y420, + .depth = 8, + }, + [VPDMA_DATA_FMT_C444] = { + .data_type = DATA_TYPE_C444, + .depth = 8, + }, + [VPDMA_DATA_FMT_C422] = { + .data_type = DATA_TYPE_C422, + .depth = 8, + }, + [VPDMA_DATA_FMT_C420] = { + .data_type = DATA_TYPE_C420, + .depth = 4, + }, + [VPDMA_DATA_FMT_YC422] = { + .data_type = DATA_TYPE_YC422, + .depth = 16, + }, + [VPDMA_DATA_FMT_YC444] = { + .data_type = DATA_TYPE_YC444, + .depth = 24, + }, + [VPDMA_DATA_FMT_CY422] = { + .data_type = DATA_TYPE_CY422, + .depth = 16, + }, +}; + +const struct vpdma_data_format vpdma_rgb_fmts[] = { + [VPDMA_DATA_FMT_RGB565] = { + .data_type = DATA_TYPE_RGB16_565, + .depth = 16, + }, + [VPDMA_DATA_FMT_ARGB16_1555] = { + .data_type = DATA_TYPE_ARGB_1555, + .depth = 16, + }, + [VPDMA_DATA_FMT_ARGB16] = { + .data_type = DATA_TYPE_ARGB_4444, + .depth = 16, + }, + [VPDMA_DATA_FMT_RGBA16_5551] = { + .data_type = DATA_TYPE_RGBA_5551, + .depth = 16, + }, + [VPDMA_DATA_FMT_RGBA16] = { + .data_type = DATA_TYPE_RGBA_4444, + .depth = 16, + }, + [VPDMA_DATA_FMT_ARGB24] = { + .data_type = DATA_TYPE_ARGB24_6666, + .depth = 24, + }, + [VPDMA_DATA_FMT_RGB24] = { + .data_type = DATA_TYPE_RGB24_888, + .depth = 24, + }, + [VPDMA_DATA_FMT_ARGB32] = { + .data_type = DATA_TYPE_ARGB32_8888, + .depth = 32, + }, + [VPDMA_DATA_FMT_RGBA24] = { + .data_type = DATA_TYPE_RGBA24_6666, + .depth = 24, + }, + [VPDMA_DATA_FMT_RGBA32] = { + .data_type = DATA_TYPE_RGBA32_8888, + .depth = 32, + }, + [VPDMA_DATA_FMT_BGR565] = { + .data_type = DATA_TYPE_BGR16_565, + .depth = 16, + }, + [VPDMA_DATA_FMT_ABGR16_1555] = { + .data_type = DATA_TYPE_ABGR_1555, + .depth = 16, + }, + [VPDMA_DATA_FMT_ABGR16] = { + .data_type = DATA_TYPE_ABGR_4444, + .depth = 16, + }, + [VPDMA_DATA_FMT_BGRA16_5551] = { + .data_type = DATA_TYPE_BGRA_5551, + .depth = 16, + }, + [VPDMA_DATA_FMT_BGRA16] = { + .data_type = DATA_TYPE_BGRA_4444, + .depth = 16, + }, + [VPDMA_DATA_FMT_ABGR24] = { + .data_type = DATA_TYPE_ABGR24_6666, + .depth = 24, + }, + [VPDMA_DATA_FMT_BGR24] = { + .data_type = DATA_TYPE_BGR24_888, + .depth = 24, + }, + [VPDMA_DATA_FMT_ABGR32] = { + .data_type = DATA_TYPE_ABGR32_8888, + .depth = 32, + }, + [VPDMA_DATA_FMT_BGRA24] = { + .data_type = DATA_TYPE_BGRA24_6666, + .depth = 24, + }, + [VPDMA_DATA_FMT_BGRA32] = { + .data_type = DATA_TYPE_BGRA32_8888, + .depth = 32, + }, +}; + +const struct vpdma_data_format vpdma_misc_fmts[] = { + [VPDMA_DATA_FMT_MV] = { + .data_type = DATA_TYPE_MV, + .depth = 4, + }, +}; + +struct vpdma_channel_info { + int num; /* VPDMA channel number */ + int cstat_offset; /* client CSTAT register offset */ +}; + +static const struct vpdma_channel_info chan_info[] = { + [VPE_CHAN_LUMA1_IN] = { + .num = VPE_CHAN_NUM_LUMA1_IN, + .cstat_offset = VPDMA_DEI_LUMA1_CSTAT, + }, + [VPE_CHAN_CHROMA1_IN] = { + .num = VPE_CHAN_NUM_CHROMA1_IN, + .cstat_offset = VPDMA_DEI_CHROMA1_CSTAT, + }, + [VPE_CHAN_LUMA2_IN] = { + .num = VPE_CHAN_NUM_LUMA2_IN, + .cstat_offset = VPDMA_DEI_LUMA2_CSTAT, + }, + [VPE_CHAN_CHROMA2_IN] = { + .num = VPE_CHAN_NUM_CHROMA2_IN, + .cstat_offset = VPDMA_DEI_CHROMA2_CSTAT, + }, + [VPE_CHAN_LUMA3_IN] = { + .num = VPE_CHAN_NUM_LUMA3_IN, + .cstat_offset = VPDMA_DEI_LUMA3_CSTAT, + }, + [VPE_CHAN_CHROMA3_IN] = { + .num = VPE_CHAN_NUM_CHROMA3_IN, + .cstat_offset = VPDMA_DEI_CHROMA3_CSTAT, + }, + [VPE_CHAN_MV_IN] = { + .num = VPE_CHAN_NUM_MV_IN, + .cstat_offset = VPDMA_DEI_MV_IN_CSTAT, + }, + [VPE_CHAN_MV_OUT] = { + .num = VPE_CHAN_NUM_MV_OUT, + .cstat_offset = VPDMA_DEI_MV_OUT_CSTAT, + }, + [VPE_CHAN_LUMA_OUT] = { + .num = VPE_CHAN_NUM_LUMA_OUT, + .cstat_offset = VPDMA_VIP_UP_Y_CSTAT, + }, + [VPE_CHAN_CHROMA_OUT] = { + .num = VPE_CHAN_NUM_CHROMA_OUT, + .cstat_offset = VPDMA_VIP_UP_UV_CSTAT, + }, + [VPE_CHAN_RGB_OUT] = { + .num = VPE_CHAN_NUM_RGB_OUT, + .cstat_offset = VPDMA_VIP_UP_Y_CSTAT, + }, +}; + +static u32 read_reg(struct vpdma_data *vpdma, int offset) +{ + return ioread32(vpdma->base + offset); +} + +static void write_reg(struct vpdma_data *vpdma, int offset, u32 value) +{ + iowrite32(value, vpdma->base + offset); +} + +static int read_field_reg(struct vpdma_data *vpdma, int offset, + u32 mask, int shift) +{ + return (read_reg(vpdma, offset) & (mask << shift)) >> shift; +} + +static void write_field_reg(struct vpdma_data *vpdma, int offset, u32 field, + u32 mask, int shift) +{ + u32 val = read_reg(vpdma, offset); + + val &= ~(mask << shift); + val |= (field & mask) << shift; + + write_reg(vpdma, offset, val); +} + +void vpdma_dump_regs(struct vpdma_data *vpdma) +{ + struct device *dev = &vpdma->pdev->dev; + +#define DUMPREG(r) dev_dbg(dev, "%-35s %08x\n", #r, read_reg(vpdma, VPDMA_##r)) + + dev_dbg(dev, "VPDMA Registers:\n"); + + DUMPREG(PID); + DUMPREG(LIST_ADDR); + DUMPREG(LIST_ATTR); + DUMPREG(LIST_STAT_SYNC); + DUMPREG(BG_RGB); + DUMPREG(BG_YUV); + DUMPREG(SETUP); + DUMPREG(MAX_SIZE1); + DUMPREG(MAX_SIZE2); + DUMPREG(MAX_SIZE3); + + /* + * dumping registers of only group0 and group3, because VPE channels + * lie within group0 and group3 registers + */ + DUMPREG(INT_CHAN_STAT(0)); + DUMPREG(INT_CHAN_MASK(0)); + DUMPREG(INT_CHAN_STAT(3)); + DUMPREG(INT_CHAN_MASK(3)); + DUMPREG(INT_CLIENT0_STAT); + DUMPREG(INT_CLIENT0_MASK); + DUMPREG(INT_CLIENT1_STAT); + DUMPREG(INT_CLIENT1_MASK); + DUMPREG(INT_LIST0_STAT); + DUMPREG(INT_LIST0_MASK); + + /* + * these are registers specific to VPE clients, we can make this + * function dump client registers specific to VPE or VIP based on + * who is using it + */ + DUMPREG(DEI_CHROMA1_CSTAT); + DUMPREG(DEI_LUMA1_CSTAT); + DUMPREG(DEI_CHROMA2_CSTAT); + DUMPREG(DEI_LUMA2_CSTAT); + DUMPREG(DEI_CHROMA3_CSTAT); + DUMPREG(DEI_LUMA3_CSTAT); + DUMPREG(DEI_MV_IN_CSTAT); + DUMPREG(DEI_MV_OUT_CSTAT); + DUMPREG(VIP_UP_Y_CSTAT); + DUMPREG(VIP_UP_UV_CSTAT); + DUMPREG(VPI_CTL_CSTAT); +} + +/* + * Allocate a DMA buffer + */ +int vpdma_alloc_desc_buf(struct vpdma_buf *buf, size_t size) +{ + buf->size = size; + buf->mapped = false; + buf->addr = kzalloc(size, GFP_KERNEL); + if (!buf->addr) + return -ENOMEM; + + WARN_ON((u32) buf->addr & VPDMA_DESC_ALIGN); + + return 0; +} + +void vpdma_free_desc_buf(struct vpdma_buf *buf) +{ + WARN_ON(buf->mapped); + kfree(buf->addr); + buf->addr = NULL; + buf->size = 0; +} + +/* + * map descriptor/payload DMA buffer, enabling DMA access + */ +int vpdma_map_desc_buf(struct vpdma_data *vpdma, struct vpdma_buf *buf) +{ + struct device *dev = &vpdma->pdev->dev; + + WARN_ON(buf->mapped); + buf->dma_addr = dma_map_single(dev, buf->addr, buf->size, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, buf->dma_addr)) { + dev_err(dev, "failed to map buffer\n"); + return -EINVAL; + } + + buf->mapped = true; + + return 0; +} + +/* + * unmap descriptor/payload DMA buffer, disabling DMA access and + * allowing the main processor to acces the data + */ +void vpdma_unmap_desc_buf(struct vpdma_data *vpdma, struct vpdma_buf *buf) +{ + struct device *dev = &vpdma->pdev->dev; + + if (buf->mapped) + dma_unmap_single(dev, buf->dma_addr, buf->size, DMA_TO_DEVICE); + + buf->mapped = false; +} + +/* + * create a descriptor list, the user of this list will append configuration, + * control and data descriptors to this list, this list will be submitted to + * VPDMA. VPDMA's list parser will go through each descriptor and perform the + * required DMA operations + */ +int vpdma_create_desc_list(struct vpdma_desc_list *list, size_t size, int type) +{ + int r; + + r = vpdma_alloc_desc_buf(&list->buf, size); + if (r) + return r; + + list->next = list->buf.addr; + + list->type = type; + + return 0; +} + +/* + * once a descriptor list is parsed by VPDMA, we reset the list by emptying it, + * to allow new descriptors to be added to the list. + */ +void vpdma_reset_desc_list(struct vpdma_desc_list *list) +{ + list->next = list->buf.addr; +} + +/* + * free the buffer allocated fot the VPDMA descriptor list, this should be + * called when the user doesn't want to use VPDMA any more. + */ +void vpdma_free_desc_list(struct vpdma_desc_list *list) +{ + vpdma_free_desc_buf(&list->buf); + + list->next = NULL; +} + +static bool vpdma_list_busy(struct vpdma_data *vpdma, int list_num) +{ + return read_reg(vpdma, VPDMA_LIST_STAT_SYNC) & BIT(list_num + 16); +} + +/* + * submit a list of DMA descriptors to the VPE VPDMA, do not wait for completion + */ +int vpdma_submit_descs(struct vpdma_data *vpdma, struct vpdma_desc_list *list) +{ + /* we always use the first list */ + int list_num = 0; + int list_size; + + if (vpdma_list_busy(vpdma, list_num)) + return -EBUSY; + + /* 16-byte granularity */ + list_size = (list->next - list->buf.addr) >> 4; + + write_reg(vpdma, VPDMA_LIST_ADDR, (u32) list->buf.dma_addr); + + write_reg(vpdma, VPDMA_LIST_ATTR, + (list_num << VPDMA_LIST_NUM_SHFT) | + (list->type << VPDMA_LIST_TYPE_SHFT) | + list_size); + + return 0; +} + +static void dump_cfd(struct vpdma_cfd *cfd) +{ + int class; + + class = cfd_get_class(cfd); + + pr_debug("config descriptor of payload class: %s\n", + class == CFD_CLS_BLOCK ? "simple block" : + "address data block"); + + if (class == CFD_CLS_BLOCK) + pr_debug("word0: dst_addr_offset = 0x%08x\n", + cfd->dest_addr_offset); + + if (class == CFD_CLS_BLOCK) + pr_debug("word1: num_data_wrds = %d\n", cfd->block_len); + + pr_debug("word2: payload_addr = 0x%08x\n", cfd->payload_addr); + + pr_debug("word3: pkt_type = %d, direct = %d, class = %d, dest = %d, " + "payload_len = %d\n", cfd_get_pkt_type(cfd), + cfd_get_direct(cfd), class, cfd_get_dest(cfd), + cfd_get_payload_len(cfd)); +} + +/* + * append a configuration descriptor to the given descriptor list, where the + * payload is in the form of a simple data block specified in the descriptor + * header, this is used to upload scaler coefficients to the scaler module + */ +void vpdma_add_cfd_block(struct vpdma_desc_list *list, int client, + struct vpdma_buf *blk, u32 dest_offset) +{ + struct vpdma_cfd *cfd; + int len = blk->size; + + WARN_ON(blk->dma_addr & VPDMA_DESC_ALIGN); + + cfd = list->next; + WARN_ON((void *)(cfd + 1) > (list->buf.addr + list->buf.size)); + + cfd->dest_addr_offset = dest_offset; + cfd->block_len = len; + cfd->payload_addr = (u32) blk->dma_addr; + cfd->ctl_payload_len = cfd_pkt_payload_len(CFD_INDIRECT, CFD_CLS_BLOCK, + client, len >> 4); + + list->next = cfd + 1; + + dump_cfd(cfd); +} + +/* + * append a configuration descriptor to the given descriptor list, where the + * payload is in the address data block format, this is used to a configure a + * discontiguous set of MMRs + */ +void vpdma_add_cfd_adb(struct vpdma_desc_list *list, int client, + struct vpdma_buf *adb) +{ + struct vpdma_cfd *cfd; + unsigned int len = adb->size; + + WARN_ON(len & VPDMA_ADB_SIZE_ALIGN); + WARN_ON(adb->dma_addr & VPDMA_DESC_ALIGN); + + cfd = list->next; + BUG_ON((void *)(cfd + 1) > (list->buf.addr + list->buf.size)); + + cfd->w0 = 0; + cfd->w1 = 0; + cfd->payload_addr = (u32) adb->dma_addr; + cfd->ctl_payload_len = cfd_pkt_payload_len(CFD_INDIRECT, CFD_CLS_ADB, + client, len >> 4); + + list->next = cfd + 1; + + dump_cfd(cfd); +}; + +/* + * control descriptor format change based on what type of control descriptor it + * is, we only use 'sync on channel' control descriptors for now, so assume it's + * that + */ +static void dump_ctd(struct vpdma_ctd *ctd) +{ + pr_debug("control descriptor\n"); + + pr_debug("word3: pkt_type = %d, source = %d, ctl_type = %d\n", + ctd_get_pkt_type(ctd), ctd_get_source(ctd), ctd_get_ctl(ctd)); +} + +/* + * append a 'sync on channel' type control descriptor to the given descriptor + * list, this descriptor stalls the VPDMA list till the time DMA is completed + * on the specified channel + */ +void vpdma_add_sync_on_channel_ctd(struct vpdma_desc_list *list, + enum vpdma_channel chan) +{ + struct vpdma_ctd *ctd; + + ctd = list->next; + WARN_ON((void *)(ctd + 1) > (list->buf.addr + list->buf.size)); + + ctd->w0 = 0; + ctd->w1 = 0; + ctd->w2 = 0; + ctd->type_source_ctl = ctd_type_source_ctl(chan_info[chan].num, + CTD_TYPE_SYNC_ON_CHANNEL); + + list->next = ctd + 1; + + dump_ctd(ctd); +} + +static void dump_dtd(struct vpdma_dtd *dtd) +{ + int dir, chan; + + dir = dtd_get_dir(dtd); + chan = dtd_get_chan(dtd); + + pr_debug("%s data transfer descriptor for channel %d\n", + dir == DTD_DIR_OUT ? "outbound" : "inbound", chan); + + pr_debug("word0: data_type = %d, notify = %d, field = %d, 1D = %d, " + "even_ln_skp = %d, odd_ln_skp = %d, line_stride = %d\n", + dtd_get_data_type(dtd), dtd_get_notify(dtd), dtd_get_field(dtd), + dtd_get_1d(dtd), dtd_get_even_line_skip(dtd), + dtd_get_odd_line_skip(dtd), dtd_get_line_stride(dtd)); + + if (dir == DTD_DIR_IN) + pr_debug("word1: line_length = %d, xfer_height = %d\n", + dtd_get_line_length(dtd), dtd_get_xfer_height(dtd)); + + pr_debug("word2: start_addr = 0x%08x\n", dtd->start_addr); + + pr_debug("word3: pkt_type = %d, mode = %d, dir = %d, chan = %d, " + "pri = %d, next_chan = %d\n", dtd_get_pkt_type(dtd), + dtd_get_mode(dtd), dir, chan, dtd_get_priority(dtd), + dtd_get_next_chan(dtd)); + + if (dir == DTD_DIR_IN) + pr_debug("word4: frame_width = %d, frame_height = %d\n", + dtd_get_frame_width(dtd), dtd_get_frame_height(dtd)); + else + pr_debug("word4: desc_write_addr = 0x%08x, write_desc = %d, " + "drp_data = %d, use_desc_reg = %d\n", + dtd_get_desc_write_addr(dtd), dtd_get_write_desc(dtd), + dtd_get_drop_data(dtd), dtd_get_use_desc(dtd)); + + if (dir == DTD_DIR_IN) + pr_debug("word5: hor_start = %d, ver_start = %d\n", + dtd_get_h_start(dtd), dtd_get_v_start(dtd)); + else + pr_debug("word5: max_width %d, max_height %d\n", + dtd_get_max_width(dtd), dtd_get_max_height(dtd)); + + pr_debug("word6: client specfic attr0 = 0x%08x\n", dtd->client_attr0); + pr_debug("word7: client specfic attr1 = 0x%08x\n", dtd->client_attr1); +} + +/* + * append an outbound data transfer descriptor to the given descriptor list, + * this sets up a 'client to memory' VPDMA transfer for the given VPDMA channel + */ +void vpdma_add_out_dtd(struct vpdma_desc_list *list, struct v4l2_rect *c_rect, + const struct vpdma_data_format *fmt, dma_addr_t dma_addr, + enum vpdma_channel chan, u32 flags) +{ + int priority = 0; + int field = 0; + int notify = 1; + int channel, next_chan; + int depth = fmt->depth; + int stride; + struct vpdma_dtd *dtd; + + channel = next_chan = chan_info[chan].num; + + if (fmt->data_type == DATA_TYPE_C420) + depth = 8; + + stride = (depth * c_rect->width) >> 3; + dma_addr += (c_rect->left * depth) >> 3; + + dtd = list->next; + WARN_ON((void *)(dtd + 1) > (list->buf.addr + list->buf.size)); + + dtd->type_ctl_stride = dtd_type_ctl_stride(fmt->data_type, + notify, + field, + !!(flags & VPDMA_DATA_FRAME_1D), + !!(flags & VPDMA_DATA_EVEN_LINE_SKIP), + !!(flags & VPDMA_DATA_ODD_LINE_SKIP), + stride); + dtd->w1 = 0; + dtd->start_addr = (u32) dma_addr; + dtd->pkt_ctl = dtd_pkt_ctl(!!(flags & VPDMA_DATA_MODE_TILED), + DTD_DIR_OUT, channel, priority, next_chan); + dtd->desc_write_addr = dtd_desc_write_addr(0, 0, 0, 0); + dtd->max_width_height = dtd_max_width_height(MAX_OUT_WIDTH_1920, + MAX_OUT_HEIGHT_1080); + dtd->client_attr0 = 0; + dtd->client_attr1 = 0; + + list->next = dtd + 1; + + dump_dtd(dtd); +} + +/* + * append an inbound data transfer descriptor to the given descriptor list, + * this sets up a 'memory to client' VPDMA transfer for the given VPDMA channel + */ +void vpdma_add_in_dtd(struct vpdma_desc_list *list, int frame_width, + int frame_height, struct v4l2_rect *c_rect, + const struct vpdma_data_format *fmt, dma_addr_t dma_addr, + enum vpdma_channel chan, int field, u32 flags) +{ + int priority = 0; + int notify = 1; + int depth = fmt->depth; + int channel, next_chan; + int stride; + int height = c_rect->height; + struct vpdma_dtd *dtd; + + channel = next_chan = chan_info[chan].num; + + if (fmt->data_type == DATA_TYPE_C420) { + height >>= 1; + frame_height >>= 1; + depth = 8; + } + + stride = (depth * c_rect->width) >> 3; + dma_addr += (c_rect->left * depth) >> 3; + + dtd = list->next; + WARN_ON((void *)(dtd + 1) > (list->buf.addr + list->buf.size)); + + dtd->type_ctl_stride = dtd_type_ctl_stride(fmt->data_type, + notify, + field, + !!(flags & VPDMA_DATA_FRAME_1D), + !!(flags & VPDMA_DATA_EVEN_LINE_SKIP), + !!(flags & VPDMA_DATA_ODD_LINE_SKIP), + stride); + + dtd->xfer_length_height = dtd_xfer_length_height(c_rect->width, height); + dtd->start_addr = (u32) dma_addr; + dtd->pkt_ctl = dtd_pkt_ctl(!!(flags & VPDMA_DATA_MODE_TILED), + DTD_DIR_IN, channel, priority, next_chan); + dtd->frame_width_height = dtd_frame_width_height(frame_width, + frame_height); + dtd->start_h_v = dtd_start_h_v(c_rect->left, c_rect->top); + dtd->client_attr0 = 0; + dtd->client_attr1 = 0; + + list->next = dtd + 1; + + dump_dtd(dtd); +} + +/* set or clear the mask for list complete interrupt */ +void vpdma_enable_list_complete_irq(struct vpdma_data *vpdma, int list_num, + bool enable) +{ + u32 val; + + val = read_reg(vpdma, VPDMA_INT_LIST0_MASK); + if (enable) + val |= (1 << (list_num * 2)); + else + val &= ~(1 << (list_num * 2)); + write_reg(vpdma, VPDMA_INT_LIST0_MASK, val); +} + +/* clear previosuly occured list intterupts in the LIST_STAT register */ +void vpdma_clear_list_stat(struct vpdma_data *vpdma) +{ + write_reg(vpdma, VPDMA_INT_LIST0_STAT, + read_reg(vpdma, VPDMA_INT_LIST0_STAT)); +} + +/* + * configures the output mode of the line buffer for the given client, the + * line buffer content can either be mirrored(each line repeated twice) or + * passed to the client as is + */ +void vpdma_set_line_mode(struct vpdma_data *vpdma, int line_mode, + enum vpdma_channel chan) +{ + int client_cstat = chan_info[chan].cstat_offset; + + write_field_reg(vpdma, client_cstat, line_mode, + VPDMA_CSTAT_LINE_MODE_MASK, VPDMA_CSTAT_LINE_MODE_SHIFT); +} + +/* + * configures the event which should trigger VPDMA transfer for the given + * client + */ +void vpdma_set_frame_start_event(struct vpdma_data *vpdma, + enum vpdma_frame_start_event fs_event, + enum vpdma_channel chan) +{ + int client_cstat = chan_info[chan].cstat_offset; + + write_field_reg(vpdma, client_cstat, fs_event, + VPDMA_CSTAT_FRAME_START_MASK, VPDMA_CSTAT_FRAME_START_SHIFT); +} + +static void vpdma_firmware_cb(const struct firmware *f, void *context) +{ + struct vpdma_data *vpdma = context; + struct vpdma_buf fw_dma_buf; + int i, r; + + dev_dbg(&vpdma->pdev->dev, "firmware callback\n"); + + if (!f || !f->data) { + dev_err(&vpdma->pdev->dev, "couldn't get firmware\n"); + return; + } + + /* already initialized */ + if (read_field_reg(vpdma, VPDMA_LIST_ATTR, VPDMA_LIST_RDY_MASK, + VPDMA_LIST_RDY_SHFT)) { + vpdma->ready = true; + return; + } + + r = vpdma_alloc_desc_buf(&fw_dma_buf, f->size); + if (r) { + dev_err(&vpdma->pdev->dev, + "failed to allocate dma buffer for firmware\n"); + goto rel_fw; + } + + memcpy(fw_dma_buf.addr, f->data, f->size); + + vpdma_map_desc_buf(vpdma, &fw_dma_buf); + + write_reg(vpdma, VPDMA_LIST_ADDR, (u32) fw_dma_buf.dma_addr); + + for (i = 0; i < 100; i++) { /* max 1 second */ + msleep_interruptible(10); + + if (read_field_reg(vpdma, VPDMA_LIST_ATTR, VPDMA_LIST_RDY_MASK, + VPDMA_LIST_RDY_SHFT)) + break; + } + + if (i == 100) { + dev_err(&vpdma->pdev->dev, "firmware upload failed\n"); + goto free_buf; + } + + vpdma->ready = true; + +free_buf: + vpdma_unmap_desc_buf(vpdma, &fw_dma_buf); + + vpdma_free_desc_buf(&fw_dma_buf); +rel_fw: + release_firmware(f); +} + +static int vpdma_load_firmware(struct vpdma_data *vpdma) +{ + int r; + struct device *dev = &vpdma->pdev->dev; + + r = request_firmware_nowait(THIS_MODULE, 1, + (const char *) VPDMA_FIRMWARE, dev, GFP_KERNEL, vpdma, + vpdma_firmware_cb); + if (r) { + dev_err(dev, "firmware not available %s\n", VPDMA_FIRMWARE); + return r; + } else { + dev_info(dev, "loading firmware %s\n", VPDMA_FIRMWARE); + } + + return 0; +} + +struct vpdma_data *vpdma_create(struct platform_device *pdev) +{ + struct resource *res; + struct vpdma_data *vpdma; + int r; + + dev_dbg(&pdev->dev, "vpdma_create\n"); + + vpdma = devm_kzalloc(&pdev->dev, sizeof(*vpdma), GFP_KERNEL); + if (!vpdma) { + dev_err(&pdev->dev, "couldn't alloc vpdma_dev\n"); + return ERR_PTR(-ENOMEM); + } + + vpdma->pdev = pdev; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "vpdma"); + if (res == NULL) { + dev_err(&pdev->dev, "missing platform resources data\n"); + return ERR_PTR(-ENODEV); + } + + vpdma->base = devm_ioremap(&pdev->dev, res->start, resource_size(res)); + if (!vpdma->base) { + dev_err(&pdev->dev, "failed to ioremap\n"); + return ERR_PTR(-ENOMEM); + } + + r = vpdma_load_firmware(vpdma); + if (r) { + pr_err("failed to load firmware %s\n", VPDMA_FIRMWARE); + return ERR_PTR(r); + } + + return vpdma; +} +MODULE_FIRMWARE(VPDMA_FIRMWARE); diff --git a/drivers/media/platform/ti-vpe/vpdma.h b/drivers/media/platform/ti-vpe/vpdma.h new file mode 100644 index 000000000000..eaa2a71a5db9 --- /dev/null +++ b/drivers/media/platform/ti-vpe/vpdma.h @@ -0,0 +1,203 @@ +/* + * Copyright (c) 2013 Texas Instruments Inc. + * + * David Griego, <dagriego@biglakesoftware.com> + * Dale Farnsworth, <dale@farnsworth.org> + * Archit Taneja, <archit@ti.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#ifndef __TI_VPDMA_H_ +#define __TI_VPDMA_H_ + +/* + * A vpdma_buf tracks the size, DMA address and mapping status of each + * driver DMA area. + */ +struct vpdma_buf { + void *addr; + dma_addr_t dma_addr; + size_t size; + bool mapped; +}; + +struct vpdma_desc_list { + struct vpdma_buf buf; + void *next; + int type; +}; + +struct vpdma_data { + void __iomem *base; + + struct platform_device *pdev; + + /* tells whether vpdma firmware is loaded or not */ + bool ready; +}; + +struct vpdma_data_format { + int data_type; + u8 depth; +}; + +#define VPDMA_DESC_ALIGN 16 /* 16-byte descriptor alignment */ + +#define VPDMA_DTD_DESC_SIZE 32 /* 8 words */ +#define VPDMA_CFD_CTD_DESC_SIZE 16 /* 4 words */ + +#define VPDMA_LIST_TYPE_NORMAL 0 +#define VPDMA_LIST_TYPE_SELF_MODIFYING 1 +#define VPDMA_LIST_TYPE_DOORBELL 2 + +enum vpdma_yuv_formats { + VPDMA_DATA_FMT_Y444 = 0, + VPDMA_DATA_FMT_Y422, + VPDMA_DATA_FMT_Y420, + VPDMA_DATA_FMT_C444, + VPDMA_DATA_FMT_C422, + VPDMA_DATA_FMT_C420, + VPDMA_DATA_FMT_YC422, + VPDMA_DATA_FMT_YC444, + VPDMA_DATA_FMT_CY422, +}; + +enum vpdma_rgb_formats { + VPDMA_DATA_FMT_RGB565 = 0, + VPDMA_DATA_FMT_ARGB16_1555, + VPDMA_DATA_FMT_ARGB16, + VPDMA_DATA_FMT_RGBA16_5551, + VPDMA_DATA_FMT_RGBA16, + VPDMA_DATA_FMT_ARGB24, + VPDMA_DATA_FMT_RGB24, + VPDMA_DATA_FMT_ARGB32, + VPDMA_DATA_FMT_RGBA24, + VPDMA_DATA_FMT_RGBA32, + VPDMA_DATA_FMT_BGR565, + VPDMA_DATA_FMT_ABGR16_1555, + VPDMA_DATA_FMT_ABGR16, + VPDMA_DATA_FMT_BGRA16_5551, + VPDMA_DATA_FMT_BGRA16, + VPDMA_DATA_FMT_ABGR24, + VPDMA_DATA_FMT_BGR24, + VPDMA_DATA_FMT_ABGR32, + VPDMA_DATA_FMT_BGRA24, + VPDMA_DATA_FMT_BGRA32, +}; + +enum vpdma_misc_formats { + VPDMA_DATA_FMT_MV = 0, +}; + +extern const struct vpdma_data_format vpdma_yuv_fmts[]; +extern const struct vpdma_data_format vpdma_rgb_fmts[]; +extern const struct vpdma_data_format vpdma_misc_fmts[]; + +enum vpdma_frame_start_event { + VPDMA_FSEVENT_HDMI_FID = 0, + VPDMA_FSEVENT_DVO2_FID, + VPDMA_FSEVENT_HDCOMP_FID, + VPDMA_FSEVENT_SD_FID, + VPDMA_FSEVENT_LM_FID0, + VPDMA_FSEVENT_LM_FID1, + VPDMA_FSEVENT_LM_FID2, + VPDMA_FSEVENT_CHANNEL_ACTIVE, +}; + +/* + * VPDMA channel numbers + */ +enum vpdma_channel { + VPE_CHAN_LUMA1_IN, + VPE_CHAN_CHROMA1_IN, + VPE_CHAN_LUMA2_IN, + VPE_CHAN_CHROMA2_IN, + VPE_CHAN_LUMA3_IN, + VPE_CHAN_CHROMA3_IN, + VPE_CHAN_MV_IN, + VPE_CHAN_MV_OUT, + VPE_CHAN_LUMA_OUT, + VPE_CHAN_CHROMA_OUT, + VPE_CHAN_RGB_OUT, +}; + +/* flags for VPDMA data descriptors */ +#define VPDMA_DATA_ODD_LINE_SKIP (1 << 0) +#define VPDMA_DATA_EVEN_LINE_SKIP (1 << 1) +#define VPDMA_DATA_FRAME_1D (1 << 2) +#define VPDMA_DATA_MODE_TILED (1 << 3) + +/* + * client identifiers used for configuration descriptors + */ +#define CFD_MMR_CLIENT 0 +#define CFD_SC_CLIENT 4 + +/* Address data block header format */ +struct vpdma_adb_hdr { + u32 offset; + u32 nwords; + u32 reserved0; + u32 reserved1; +}; + +/* helpers for creating ADB headers for config descriptors MMRs as client */ +#define ADB_ADDR(dma_buf, str, fld) ((dma_buf)->addr + offsetof(str, fld)) +#define MMR_ADB_ADDR(buf, str, fld) ADB_ADDR(&(buf), struct str, fld) + +#define VPDMA_SET_MMR_ADB_HDR(buf, str, hdr, regs, offset_a) \ + do { \ + struct vpdma_adb_hdr *h; \ + struct str *adb = NULL; \ + h = MMR_ADB_ADDR(buf, str, hdr); \ + h->offset = (offset_a); \ + h->nwords = sizeof(adb->regs) >> 2; \ + } while (0) + +/* vpdma descriptor buffer allocation and management */ +int vpdma_alloc_desc_buf(struct vpdma_buf *buf, size_t size); +void vpdma_free_desc_buf(struct vpdma_buf *buf); +int vpdma_map_desc_buf(struct vpdma_data *vpdma, struct vpdma_buf *buf); +void vpdma_unmap_desc_buf(struct vpdma_data *vpdma, struct vpdma_buf *buf); + +/* vpdma descriptor list funcs */ +int vpdma_create_desc_list(struct vpdma_desc_list *list, size_t size, int type); +void vpdma_reset_desc_list(struct vpdma_desc_list *list); +void vpdma_free_desc_list(struct vpdma_desc_list *list); +int vpdma_submit_descs(struct vpdma_data *vpdma, struct vpdma_desc_list *list); + +/* helpers for creating vpdma descriptors */ +void vpdma_add_cfd_block(struct vpdma_desc_list *list, int client, + struct vpdma_buf *blk, u32 dest_offset); +void vpdma_add_cfd_adb(struct vpdma_desc_list *list, int client, + struct vpdma_buf *adb); +void vpdma_add_sync_on_channel_ctd(struct vpdma_desc_list *list, + enum vpdma_channel chan); +void vpdma_add_out_dtd(struct vpdma_desc_list *list, struct v4l2_rect *c_rect, + const struct vpdma_data_format *fmt, dma_addr_t dma_addr, + enum vpdma_channel chan, u32 flags); +void vpdma_add_in_dtd(struct vpdma_desc_list *list, int frame_width, + int frame_height, struct v4l2_rect *c_rect, + const struct vpdma_data_format *fmt, dma_addr_t dma_addr, + enum vpdma_channel chan, int field, u32 flags); + +/* vpdma list interrupt management */ +void vpdma_enable_list_complete_irq(struct vpdma_data *vpdma, int list_num, + bool enable); +void vpdma_clear_list_stat(struct vpdma_data *vpdma); + +/* vpdma client configuration */ +void vpdma_set_line_mode(struct vpdma_data *vpdma, int line_mode, + enum vpdma_channel chan); +void vpdma_set_frame_start_event(struct vpdma_data *vpdma, + enum vpdma_frame_start_event fs_event, enum vpdma_channel chan); + +void vpdma_dump_regs(struct vpdma_data *vpdma); + +/* initialize vpdma, passed with VPE's platform device pointer */ +struct vpdma_data *vpdma_create(struct platform_device *pdev); + +#endif diff --git a/drivers/media/platform/ti-vpe/vpdma_priv.h b/drivers/media/platform/ti-vpe/vpdma_priv.h new file mode 100644 index 000000000000..f0e9a8038c1b --- /dev/null +++ b/drivers/media/platform/ti-vpe/vpdma_priv.h @@ -0,0 +1,641 @@ +/* + * Copyright (c) 2013 Texas Instruments Inc. + * + * David Griego, <dagriego@biglakesoftware.com> + * Dale Farnsworth, <dale@farnsworth.org> + * Archit Taneja, <archit@ti.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#ifndef _TI_VPDMA_PRIV_H_ +#define _TI_VPDMA_PRIV_H_ + +/* + * VPDMA Register offsets + */ + +/* Top level */ +#define VPDMA_PID 0x00 +#define VPDMA_LIST_ADDR 0x04 +#define VPDMA_LIST_ATTR 0x08 +#define VPDMA_LIST_STAT_SYNC 0x0c +#define VPDMA_BG_RGB 0x18 +#define VPDMA_BG_YUV 0x1c +#define VPDMA_SETUP 0x30 +#define VPDMA_MAX_SIZE1 0x34 +#define VPDMA_MAX_SIZE2 0x38 +#define VPDMA_MAX_SIZE3 0x3c + +/* Interrupts */ +#define VPDMA_INT_CHAN_STAT(grp) (0x40 + grp * 8) +#define VPDMA_INT_CHAN_MASK(grp) (VPDMA_INT_CHAN_STAT(grp) + 4) +#define VPDMA_INT_CLIENT0_STAT 0x78 +#define VPDMA_INT_CLIENT0_MASK 0x7c +#define VPDMA_INT_CLIENT1_STAT 0x80 +#define VPDMA_INT_CLIENT1_MASK 0x84 +#define VPDMA_INT_LIST0_STAT 0x88 +#define VPDMA_INT_LIST0_MASK 0x8c + +#define VPDMA_PERFMON(i) (0x200 + i * 4) + +/* VPE specific client registers */ +#define VPDMA_DEI_CHROMA1_CSTAT 0x0300 +#define VPDMA_DEI_LUMA1_CSTAT 0x0304 +#define VPDMA_DEI_LUMA2_CSTAT 0x0308 +#define VPDMA_DEI_CHROMA2_CSTAT 0x030c +#define VPDMA_DEI_LUMA3_CSTAT 0x0310 +#define VPDMA_DEI_CHROMA3_CSTAT 0x0314 +#define VPDMA_DEI_MV_IN_CSTAT 0x0330 +#define VPDMA_DEI_MV_OUT_CSTAT 0x033c +#define VPDMA_VIP_UP_Y_CSTAT 0x0390 +#define VPDMA_VIP_UP_UV_CSTAT 0x0394 +#define VPDMA_VPI_CTL_CSTAT 0x03d0 + +/* Reg field info for VPDMA_CLIENT_CSTAT registers */ +#define VPDMA_CSTAT_LINE_MODE_MASK 0x03 +#define VPDMA_CSTAT_LINE_MODE_SHIFT 8 +#define VPDMA_CSTAT_FRAME_START_MASK 0xf +#define VPDMA_CSTAT_FRAME_START_SHIFT 10 + +#define VPDMA_LIST_NUM_MASK 0x07 +#define VPDMA_LIST_NUM_SHFT 24 +#define VPDMA_LIST_STOP_SHFT 20 +#define VPDMA_LIST_RDY_MASK 0x01 +#define VPDMA_LIST_RDY_SHFT 19 +#define VPDMA_LIST_TYPE_MASK 0x03 +#define VPDMA_LIST_TYPE_SHFT 16 +#define VPDMA_LIST_SIZE_MASK 0xffff + +/* VPDMA data type values for data formats */ +#define DATA_TYPE_Y444 0x0 +#define DATA_TYPE_Y422 0x1 +#define DATA_TYPE_Y420 0x2 +#define DATA_TYPE_C444 0x4 +#define DATA_TYPE_C422 0x5 +#define DATA_TYPE_C420 0x6 +#define DATA_TYPE_YC422 0x7 +#define DATA_TYPE_YC444 0x8 +#define DATA_TYPE_CY422 0x23 + +#define DATA_TYPE_RGB16_565 0x0 +#define DATA_TYPE_ARGB_1555 0x1 +#define DATA_TYPE_ARGB_4444 0x2 +#define DATA_TYPE_RGBA_5551 0x3 +#define DATA_TYPE_RGBA_4444 0x4 +#define DATA_TYPE_ARGB24_6666 0x5 +#define DATA_TYPE_RGB24_888 0x6 +#define DATA_TYPE_ARGB32_8888 0x7 +#define DATA_TYPE_RGBA24_6666 0x8 +#define DATA_TYPE_RGBA32_8888 0x9 +#define DATA_TYPE_BGR16_565 0x10 +#define DATA_TYPE_ABGR_1555 0x11 +#define DATA_TYPE_ABGR_4444 0x12 +#define DATA_TYPE_BGRA_5551 0x13 +#define DATA_TYPE_BGRA_4444 0x14 +#define DATA_TYPE_ABGR24_6666 0x15 +#define DATA_TYPE_BGR24_888 0x16 +#define DATA_TYPE_ABGR32_8888 0x17 +#define DATA_TYPE_BGRA24_6666 0x18 +#define DATA_TYPE_BGRA32_8888 0x19 + +#define DATA_TYPE_MV 0x3 + +/* VPDMA channel numbers(only VPE channels for now) */ +#define VPE_CHAN_NUM_LUMA1_IN 0 +#define VPE_CHAN_NUM_CHROMA1_IN 1 +#define VPE_CHAN_NUM_LUMA2_IN 2 +#define VPE_CHAN_NUM_CHROMA2_IN 3 +#define VPE_CHAN_NUM_LUMA3_IN 4 +#define VPE_CHAN_NUM_CHROMA3_IN 5 +#define VPE_CHAN_NUM_MV_IN 12 +#define VPE_CHAN_NUM_MV_OUT 15 +#define VPE_CHAN_NUM_LUMA_OUT 102 +#define VPE_CHAN_NUM_CHROMA_OUT 103 +#define VPE_CHAN_NUM_RGB_OUT 106 + +/* + * a VPDMA address data block payload for a configuration descriptor needs to + * have each sub block length as a multiple of 16 bytes. Therefore, the overall + * size of the payload also needs to be a multiple of 16 bytes. The sub block + * lengths should be ensured to be aligned by the VPDMA user. + */ +#define VPDMA_ADB_SIZE_ALIGN 0x0f + +/* + * data transfer descriptor + */ +struct vpdma_dtd { + u32 type_ctl_stride; + union { + u32 xfer_length_height; + u32 w1; + }; + dma_addr_t start_addr; + u32 pkt_ctl; + union { + u32 frame_width_height; /* inbound */ + dma_addr_t desc_write_addr; /* outbound */ + }; + union { + u32 start_h_v; /* inbound */ + u32 max_width_height; /* outbound */ + }; + u32 client_attr0; + u32 client_attr1; +}; + +/* Data Transfer Descriptor specifics */ +#define DTD_NO_NOTIFY 0 +#define DTD_NOTIFY 1 + +#define DTD_PKT_TYPE 0xa +#define DTD_DIR_IN 0 +#define DTD_DIR_OUT 1 + +/* type_ctl_stride */ +#define DTD_DATA_TYPE_MASK 0x3f +#define DTD_DATA_TYPE_SHFT 26 +#define DTD_NOTIFY_MASK 0x01 +#define DTD_NOTIFY_SHFT 25 +#define DTD_FIELD_MASK 0x01 +#define DTD_FIELD_SHFT 24 +#define DTD_1D_MASK 0x01 +#define DTD_1D_SHFT 23 +#define DTD_EVEN_LINE_SKIP_MASK 0x01 +#define DTD_EVEN_LINE_SKIP_SHFT 20 +#define DTD_ODD_LINE_SKIP_MASK 0x01 +#define DTD_ODD_LINE_SKIP_SHFT 16 +#define DTD_LINE_STRIDE_MASK 0xffff +#define DTD_LINE_STRIDE_SHFT 0 + +/* xfer_length_height */ +#define DTD_LINE_LENGTH_MASK 0xffff +#define DTD_LINE_LENGTH_SHFT 16 +#define DTD_XFER_HEIGHT_MASK 0xffff +#define DTD_XFER_HEIGHT_SHFT 0 + +/* pkt_ctl */ +#define DTD_PKT_TYPE_MASK 0x1f +#define DTD_PKT_TYPE_SHFT 27 +#define DTD_MODE_MASK 0x01 +#define DTD_MODE_SHFT 26 +#define DTD_DIR_MASK 0x01 +#define DTD_DIR_SHFT 25 +#define DTD_CHAN_MASK 0x01ff +#define DTD_CHAN_SHFT 16 +#define DTD_PRI_MASK 0x0f +#define DTD_PRI_SHFT 9 +#define DTD_NEXT_CHAN_MASK 0x01ff +#define DTD_NEXT_CHAN_SHFT 0 + +/* frame_width_height */ +#define DTD_FRAME_WIDTH_MASK 0xffff +#define DTD_FRAME_WIDTH_SHFT 16 +#define DTD_FRAME_HEIGHT_MASK 0xffff +#define DTD_FRAME_HEIGHT_SHFT 0 + +/* start_h_v */ +#define DTD_H_START_MASK 0xffff +#define DTD_H_START_SHFT 16 +#define DTD_V_START_MASK 0xffff +#define DTD_V_START_SHFT 0 + +#define DTD_DESC_START_SHIFT 5 +#define DTD_WRITE_DESC_MASK 0x01 +#define DTD_WRITE_DESC_SHIFT 2 +#define DTD_DROP_DATA_MASK 0x01 +#define DTD_DROP_DATA_SHIFT 1 +#define DTD_USE_DESC_MASK 0x01 +#define DTD_USE_DESC_SHIFT 0 + +/* max_width_height */ +#define DTD_MAX_WIDTH_MASK 0x07 +#define DTD_MAX_WIDTH_SHFT 4 +#define DTD_MAX_HEIGHT_MASK 0x07 +#define DTD_MAX_HEIGHT_SHFT 0 + +/* max width configurations */ + /* unlimited width */ +#define MAX_OUT_WIDTH_UNLIMITED 0 +/* as specified in max_size1 reg */ +#define MAX_OUT_WIDTH_REG1 1 +/* as specified in max_size2 reg */ +#define MAX_OUT_WIDTH_REG2 2 +/* as specified in max_size3 reg */ +#define MAX_OUT_WIDTH_REG3 3 +/* maximum of 352 pixels as width */ +#define MAX_OUT_WIDTH_352 4 +/* maximum of 768 pixels as width */ +#define MAX_OUT_WIDTH_768 5 +/* maximum of 1280 pixels width */ +#define MAX_OUT_WIDTH_1280 6 +/* maximum of 1920 pixels as width */ +#define MAX_OUT_WIDTH_1920 7 + +/* max height configurations */ + /* unlimited height */ +#define MAX_OUT_HEIGHT_UNLIMITED 0 +/* as specified in max_size1 reg */ +#define MAX_OUT_HEIGHT_REG1 1 +/* as specified in max_size2 reg */ +#define MAX_OUT_HEIGHT_REG2 2 +/* as specified in max_size3 reg */ +#define MAX_OUT_HEIGHT_REG3 3 +/* maximum of 288 lines as height */ +#define MAX_OUT_HEIGHT_288 4 +/* maximum of 576 lines as height */ +#define MAX_OUT_HEIGHT_576 5 +/* maximum of 720 lines as height */ +#define MAX_OUT_HEIGHT_720 6 +/* maximum of 1080 lines as height */ +#define MAX_OUT_HEIGHT_1080 7 + +static inline u32 dtd_type_ctl_stride(int type, bool notify, int field, + bool one_d, bool even_line_skip, bool odd_line_skip, + int line_stride) +{ + return (type << DTD_DATA_TYPE_SHFT) | (notify << DTD_NOTIFY_SHFT) | + (field << DTD_FIELD_SHFT) | (one_d << DTD_1D_SHFT) | + (even_line_skip << DTD_EVEN_LINE_SKIP_SHFT) | + (odd_line_skip << DTD_ODD_LINE_SKIP_SHFT) | + line_stride; +} + +static inline u32 dtd_xfer_length_height(int line_length, int xfer_height) +{ + return (line_length << DTD_LINE_LENGTH_SHFT) | xfer_height; +} + +static inline u32 dtd_pkt_ctl(bool mode, bool dir, int chan, int pri, + int next_chan) +{ + return (DTD_PKT_TYPE << DTD_PKT_TYPE_SHFT) | (mode << DTD_MODE_SHFT) | + (dir << DTD_DIR_SHFT) | (chan << DTD_CHAN_SHFT) | + (pri << DTD_PRI_SHFT) | next_chan; +} + +static inline u32 dtd_frame_width_height(int width, int height) +{ + return (width << DTD_FRAME_WIDTH_SHFT) | height; +} + +static inline u32 dtd_desc_write_addr(unsigned int addr, bool write_desc, + bool drop_data, bool use_desc) +{ + return (addr << DTD_DESC_START_SHIFT) | + (write_desc << DTD_WRITE_DESC_SHIFT) | + (drop_data << DTD_DROP_DATA_SHIFT) | + use_desc; +} + +static inline u32 dtd_start_h_v(int h_start, int v_start) +{ + return (h_start << DTD_H_START_SHFT) | v_start; +} + +static inline u32 dtd_max_width_height(int max_width, int max_height) +{ + return (max_width << DTD_MAX_WIDTH_SHFT) | max_height; +} + +static inline int dtd_get_data_type(struct vpdma_dtd *dtd) +{ + return dtd->type_ctl_stride >> DTD_DATA_TYPE_SHFT; +} + +static inline bool dtd_get_notify(struct vpdma_dtd *dtd) +{ + return (dtd->type_ctl_stride >> DTD_NOTIFY_SHFT) & DTD_NOTIFY_MASK; +} + +static inline int dtd_get_field(struct vpdma_dtd *dtd) +{ + return (dtd->type_ctl_stride >> DTD_FIELD_SHFT) & DTD_FIELD_MASK; +} + +static inline bool dtd_get_1d(struct vpdma_dtd *dtd) +{ + return (dtd->type_ctl_stride >> DTD_1D_SHFT) & DTD_1D_MASK; +} + +static inline bool dtd_get_even_line_skip(struct vpdma_dtd *dtd) +{ + return (dtd->type_ctl_stride >> DTD_EVEN_LINE_SKIP_SHFT) + & DTD_EVEN_LINE_SKIP_MASK; +} + +static inline bool dtd_get_odd_line_skip(struct vpdma_dtd *dtd) +{ + return (dtd->type_ctl_stride >> DTD_ODD_LINE_SKIP_SHFT) + & DTD_ODD_LINE_SKIP_MASK; +} + +static inline int dtd_get_line_stride(struct vpdma_dtd *dtd) +{ + return dtd->type_ctl_stride & DTD_LINE_STRIDE_MASK; +} + +static inline int dtd_get_line_length(struct vpdma_dtd *dtd) +{ + return dtd->xfer_length_height >> DTD_LINE_LENGTH_SHFT; +} + +static inline int dtd_get_xfer_height(struct vpdma_dtd *dtd) +{ + return dtd->xfer_length_height & DTD_XFER_HEIGHT_MASK; +} + +static inline int dtd_get_pkt_type(struct vpdma_dtd *dtd) +{ + return dtd->pkt_ctl >> DTD_PKT_TYPE_SHFT; +} + +static inline bool dtd_get_mode(struct vpdma_dtd *dtd) +{ + return (dtd->pkt_ctl >> DTD_MODE_SHFT) & DTD_MODE_MASK; +} + +static inline bool dtd_get_dir(struct vpdma_dtd *dtd) +{ + return (dtd->pkt_ctl >> DTD_DIR_SHFT) & DTD_DIR_MASK; +} + +static inline int dtd_get_chan(struct vpdma_dtd *dtd) +{ + return (dtd->pkt_ctl >> DTD_CHAN_SHFT) & DTD_CHAN_MASK; +} + +static inline int dtd_get_priority(struct vpdma_dtd *dtd) +{ + return (dtd->pkt_ctl >> DTD_PRI_SHFT) & DTD_PRI_MASK; +} + +static inline int dtd_get_next_chan(struct vpdma_dtd *dtd) +{ + return (dtd->pkt_ctl >> DTD_NEXT_CHAN_SHFT) & DTD_NEXT_CHAN_MASK; +} + +static inline int dtd_get_frame_width(struct vpdma_dtd *dtd) +{ + return dtd->frame_width_height >> DTD_FRAME_WIDTH_SHFT; +} + +static inline int dtd_get_frame_height(struct vpdma_dtd *dtd) +{ + return dtd->frame_width_height & DTD_FRAME_HEIGHT_MASK; +} + +static inline int dtd_get_desc_write_addr(struct vpdma_dtd *dtd) +{ + return dtd->desc_write_addr >> DTD_DESC_START_SHIFT; +} + +static inline bool dtd_get_write_desc(struct vpdma_dtd *dtd) +{ + return (dtd->desc_write_addr >> DTD_WRITE_DESC_SHIFT) & + DTD_WRITE_DESC_MASK; +} + +static inline bool dtd_get_drop_data(struct vpdma_dtd *dtd) +{ + return (dtd->desc_write_addr >> DTD_DROP_DATA_SHIFT) & + DTD_DROP_DATA_MASK; +} + +static inline bool dtd_get_use_desc(struct vpdma_dtd *dtd) +{ + return dtd->desc_write_addr & DTD_USE_DESC_MASK; +} + +static inline int dtd_get_h_start(struct vpdma_dtd *dtd) +{ + return dtd->start_h_v >> DTD_H_START_SHFT; +} + +static inline int dtd_get_v_start(struct vpdma_dtd *dtd) +{ + return dtd->start_h_v & DTD_V_START_MASK; +} + +static inline int dtd_get_max_width(struct vpdma_dtd *dtd) +{ + return (dtd->max_width_height >> DTD_MAX_WIDTH_SHFT) & + DTD_MAX_WIDTH_MASK; +} + +static inline int dtd_get_max_height(struct vpdma_dtd *dtd) +{ + return (dtd->max_width_height >> DTD_MAX_HEIGHT_SHFT) & + DTD_MAX_HEIGHT_MASK; +} + +/* + * configuration descriptor + */ +struct vpdma_cfd { + union { + u32 dest_addr_offset; + u32 w0; + }; + union { + u32 block_len; /* in words */ + u32 w1; + }; + u32 payload_addr; + u32 ctl_payload_len; /* in words */ +}; + +/* Configuration descriptor specifics */ + +#define CFD_PKT_TYPE 0xb + +#define CFD_DIRECT 1 +#define CFD_INDIRECT 0 +#define CFD_CLS_ADB 0 +#define CFD_CLS_BLOCK 1 + +/* block_len */ +#define CFD__BLOCK_LEN_MASK 0xffff +#define CFD__BLOCK_LEN_SHFT 0 + +/* ctl_payload_len */ +#define CFD_PKT_TYPE_MASK 0x1f +#define CFD_PKT_TYPE_SHFT 27 +#define CFD_DIRECT_MASK 0x01 +#define CFD_DIRECT_SHFT 26 +#define CFD_CLASS_MASK 0x03 +#define CFD_CLASS_SHFT 24 +#define CFD_DEST_MASK 0xff +#define CFD_DEST_SHFT 16 +#define CFD_PAYLOAD_LEN_MASK 0xffff +#define CFD_PAYLOAD_LEN_SHFT 0 + +static inline u32 cfd_pkt_payload_len(bool direct, int cls, int dest, + int payload_len) +{ + return (CFD_PKT_TYPE << CFD_PKT_TYPE_SHFT) | + (direct << CFD_DIRECT_SHFT) | + (cls << CFD_CLASS_SHFT) | + (dest << CFD_DEST_SHFT) | + payload_len; +} + +static inline int cfd_get_pkt_type(struct vpdma_cfd *cfd) +{ + return cfd->ctl_payload_len >> CFD_PKT_TYPE_SHFT; +} + +static inline bool cfd_get_direct(struct vpdma_cfd *cfd) +{ + return (cfd->ctl_payload_len >> CFD_DIRECT_SHFT) & CFD_DIRECT_MASK; +} + +static inline bool cfd_get_class(struct vpdma_cfd *cfd) +{ + return (cfd->ctl_payload_len >> CFD_CLASS_SHFT) & CFD_CLASS_MASK; +} + +static inline int cfd_get_dest(struct vpdma_cfd *cfd) +{ + return (cfd->ctl_payload_len >> CFD_DEST_SHFT) & CFD_DEST_MASK; +} + +static inline int cfd_get_payload_len(struct vpdma_cfd *cfd) +{ + return cfd->ctl_payload_len & CFD_PAYLOAD_LEN_MASK; +} + +/* + * control descriptor + */ +struct vpdma_ctd { + union { + u32 timer_value; + u32 list_addr; + u32 w0; + }; + union { + u32 pixel_line_count; + u32 list_size; + u32 w1; + }; + union { + u32 event; + u32 fid_ctl; + u32 w2; + }; + u32 type_source_ctl; +}; + +/* control descriptor types */ +#define CTD_TYPE_SYNC_ON_CLIENT 0 +#define CTD_TYPE_SYNC_ON_LIST 1 +#define CTD_TYPE_SYNC_ON_EXT 2 +#define CTD_TYPE_SYNC_ON_LM_TIMER 3 +#define CTD_TYPE_SYNC_ON_CHANNEL 4 +#define CTD_TYPE_CHNG_CLIENT_IRQ 5 +#define CTD_TYPE_SEND_IRQ 6 +#define CTD_TYPE_RELOAD_LIST 7 +#define CTD_TYPE_ABORT_CHANNEL 8 + +#define CTD_PKT_TYPE 0xc + +/* timer_value */ +#define CTD_TIMER_VALUE_MASK 0xffff +#define CTD_TIMER_VALUE_SHFT 0 + +/* pixel_line_count */ +#define CTD_PIXEL_COUNT_MASK 0xffff +#define CTD_PIXEL_COUNT_SHFT 16 +#define CTD_LINE_COUNT_MASK 0xffff +#define CTD_LINE_COUNT_SHFT 0 + +/* list_size */ +#define CTD_LIST_SIZE_MASK 0xffff +#define CTD_LIST_SIZE_SHFT 0 + +/* event */ +#define CTD_EVENT_MASK 0x0f +#define CTD_EVENT_SHFT 0 + +/* fid_ctl */ +#define CTD_FID2_MASK 0x03 +#define CTD_FID2_SHFT 4 +#define CTD_FID1_MASK 0x03 +#define CTD_FID1_SHFT 2 +#define CTD_FID0_MASK 0x03 +#define CTD_FID0_SHFT 0 + +/* type_source_ctl */ +#define CTD_PKT_TYPE_MASK 0x1f +#define CTD_PKT_TYPE_SHFT 27 +#define CTD_SOURCE_MASK 0xff +#define CTD_SOURCE_SHFT 16 +#define CTD_CONTROL_MASK 0x0f +#define CTD_CONTROL_SHFT 0 + +static inline u32 ctd_pixel_line_count(int pixel_count, int line_count) +{ + return (pixel_count << CTD_PIXEL_COUNT_SHFT) | line_count; +} + +static inline u32 ctd_set_fid_ctl(int fid0, int fid1, int fid2) +{ + return (fid2 << CTD_FID2_SHFT) | (fid1 << CTD_FID1_SHFT) | fid0; +} + +static inline u32 ctd_type_source_ctl(int source, int control) +{ + return (CTD_PKT_TYPE << CTD_PKT_TYPE_SHFT) | + (source << CTD_SOURCE_SHFT) | control; +} + +static inline u32 ctd_get_pixel_count(struct vpdma_ctd *ctd) +{ + return ctd->pixel_line_count >> CTD_PIXEL_COUNT_SHFT; +} + +static inline int ctd_get_line_count(struct vpdma_ctd *ctd) +{ + return ctd->pixel_line_count & CTD_LINE_COUNT_MASK; +} + +static inline int ctd_get_event(struct vpdma_ctd *ctd) +{ + return ctd->event & CTD_EVENT_MASK; +} + +static inline int ctd_get_fid2_ctl(struct vpdma_ctd *ctd) +{ + return (ctd->fid_ctl >> CTD_FID2_SHFT) & CTD_FID2_MASK; +} + +static inline int ctd_get_fid1_ctl(struct vpdma_ctd *ctd) +{ + return (ctd->fid_ctl >> CTD_FID1_SHFT) & CTD_FID1_MASK; +} + +static inline int ctd_get_fid0_ctl(struct vpdma_ctd *ctd) +{ + return ctd->fid_ctl & CTD_FID2_MASK; +} + +static inline int ctd_get_pkt_type(struct vpdma_ctd *ctd) +{ + return ctd->type_source_ctl >> CTD_PKT_TYPE_SHFT; +} + +static inline int ctd_get_source(struct vpdma_ctd *ctd) +{ + return (ctd->type_source_ctl >> CTD_SOURCE_SHFT) & CTD_SOURCE_MASK; +} + +static inline int ctd_get_ctl(struct vpdma_ctd *ctd) +{ + return ctd->type_source_ctl & CTD_CONTROL_MASK; +} + +#endif diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c new file mode 100644 index 000000000000..4e58069e24ff --- /dev/null +++ b/drivers/media/platform/ti-vpe/vpe.c @@ -0,0 +1,2099 @@ +/* + * TI VPE mem2mem driver, based on the virtual v4l2-mem2mem example driver + * + * Copyright (c) 2013 Texas Instruments Inc. + * David Griego, <dagriego@biglakesoftware.com> + * Dale Farnsworth, <dale@farnsworth.org> + * Archit Taneja, <archit@ti.com> + * + * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd. + * Pawel Osciak, <pawel@osciak.com> + * Marek Szyprowski, <m.szyprowski@samsung.com> + * + * Based on the virtual v4l2-mem2mem example device + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation + */ + +#include <linux/delay.h> +#include <linux/dma-mapping.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/ioctl.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/videodev2.h> + +#include <media/v4l2-common.h> +#include <media/v4l2-ctrls.h> +#include <media/v4l2-device.h> +#include <media/v4l2-event.h> +#include <media/v4l2-ioctl.h> +#include <media/v4l2-mem2mem.h> +#include <media/videobuf2-core.h> +#include <media/videobuf2-dma-contig.h> + +#include "vpdma.h" +#include "vpe_regs.h" + +#define VPE_MODULE_NAME "vpe" + +/* minimum and maximum frame sizes */ +#define MIN_W 128 +#define MIN_H 128 +#define MAX_W 1920 +#define MAX_H 1080 + +/* required alignments */ +#define S_ALIGN 0 /* multiple of 1 */ +#define H_ALIGN 1 /* multiple of 2 */ +#define W_ALIGN 1 /* multiple of 2 */ + +/* multiple of 128 bits, line stride, 16 bytes */ +#define L_ALIGN 4 + +/* flags that indicate a format can be used for capture/output */ +#define VPE_FMT_TYPE_CAPTURE (1 << 0) +#define VPE_FMT_TYPE_OUTPUT (1 << 1) + +/* used as plane indices */ +#define VPE_MAX_PLANES 2 +#define VPE_LUMA 0 +#define VPE_CHROMA 1 + +/* per m2m context info */ +#define VPE_MAX_SRC_BUFS 3 /* need 3 src fields to de-interlace */ + +#define VPE_DEF_BUFS_PER_JOB 1 /* default one buffer per batch job */ + +/* + * each VPE context can need up to 3 config desciptors, 7 input descriptors, + * 3 output descriptors, and 10 control descriptors + */ +#define VPE_DESC_LIST_SIZE (10 * VPDMA_DTD_DESC_SIZE + \ + 13 * VPDMA_CFD_CTD_DESC_SIZE) + +#define vpe_dbg(vpedev, fmt, arg...) \ + dev_dbg((vpedev)->v4l2_dev.dev, fmt, ##arg) +#define vpe_err(vpedev, fmt, arg...) \ + dev_err((vpedev)->v4l2_dev.dev, fmt, ##arg) + +struct vpe_us_coeffs { + unsigned short anchor_fid0_c0; + unsigned short anchor_fid0_c1; + unsigned short anchor_fid0_c2; + unsigned short anchor_fid0_c3; + unsigned short interp_fid0_c0; + unsigned short interp_fid0_c1; + unsigned short interp_fid0_c2; + unsigned short interp_fid0_c3; + unsigned short anchor_fid1_c0; + unsigned short anchor_fid1_c1; + unsigned short anchor_fid1_c2; + unsigned short anchor_fid1_c3; + unsigned short interp_fid1_c0; + unsigned short interp_fid1_c1; + unsigned short interp_fid1_c2; + unsigned short interp_fid1_c3; +}; + +/* + * Default upsampler coefficients + */ +static const struct vpe_us_coeffs us_coeffs[] = { + { + /* Coefficients for progressive input */ + 0x00C8, 0x0348, 0x0018, 0x3FD8, 0x3FB8, 0x0378, 0x00E8, 0x3FE8, + 0x00C8, 0x0348, 0x0018, 0x3FD8, 0x3FB8, 0x0378, 0x00E8, 0x3FE8, + }, + { + /* Coefficients for Top Field Interlaced input */ + 0x0051, 0x03D5, 0x3FE3, 0x3FF7, 0x3FB5, 0x02E9, 0x018F, 0x3FD3, + /* Coefficients for Bottom Field Interlaced input */ + 0x016B, 0x0247, 0x00B1, 0x3F9D, 0x3FCF, 0x03DB, 0x005D, 0x3FF9, + }, +}; + +/* + * the following registers are for configuring some of the parameters of the + * motion and edge detection blocks inside DEI, these generally remain the same, + * these could be passed later via userspace if some one needs to tweak these. + */ +struct vpe_dei_regs { + unsigned long mdt_spacial_freq_thr_reg; /* VPE_DEI_REG2 */ + unsigned long edi_config_reg; /* VPE_DEI_REG3 */ + unsigned long edi_lut_reg0; /* VPE_DEI_REG4 */ + unsigned long edi_lut_reg1; /* VPE_DEI_REG5 */ + unsigned long edi_lut_reg2; /* VPE_DEI_REG6 */ + unsigned long edi_lut_reg3; /* VPE_DEI_REG7 */ +}; + +/* + * default expert DEI register values, unlikely to be modified. + */ +static const struct vpe_dei_regs dei_regs = { + 0x020C0804u, + 0x0118100Fu, + 0x08040200u, + 0x1010100Cu, + 0x10101010u, + 0x10101010u, +}; + +/* + * The port_data structure contains per-port data. + */ +struct vpe_port_data { + enum vpdma_channel channel; /* VPDMA channel */ + u8 vb_index; /* input frame f, f-1, f-2 index */ + u8 vb_part; /* plane index for co-panar formats */ +}; + +/* + * Define indices into the port_data tables + */ +#define VPE_PORT_LUMA1_IN 0 +#define VPE_PORT_CHROMA1_IN 1 +#define VPE_PORT_LUMA2_IN 2 +#define VPE_PORT_CHROMA2_IN 3 +#define VPE_PORT_LUMA3_IN 4 +#define VPE_PORT_CHROMA3_IN 5 +#define VPE_PORT_MV_IN 6 +#define VPE_PORT_MV_OUT 7 +#define VPE_PORT_LUMA_OUT 8 +#define VPE_PORT_CHROMA_OUT 9 +#define VPE_PORT_RGB_OUT 10 + +static const struct vpe_port_data port_data[11] = { + [VPE_PORT_LUMA1_IN] = { + .channel = VPE_CHAN_LUMA1_IN, + .vb_index = 0, + .vb_part = VPE_LUMA, + }, + [VPE_PORT_CHROMA1_IN] = { + .channel = VPE_CHAN_CHROMA1_IN, + .vb_index = 0, + .vb_part = VPE_CHROMA, + }, + [VPE_PORT_LUMA2_IN] = { + .channel = VPE_CHAN_LUMA2_IN, + .vb_index = 1, + .vb_part = VPE_LUMA, + }, + [VPE_PORT_CHROMA2_IN] = { + .channel = VPE_CHAN_CHROMA2_IN, + .vb_index = 1, + .vb_part = VPE_CHROMA, + }, + [VPE_PORT_LUMA3_IN] = { + .channel = VPE_CHAN_LUMA3_IN, + .vb_index = 2, + .vb_part = VPE_LUMA, + }, + [VPE_PORT_CHROMA3_IN] = { + .channel = VPE_CHAN_CHROMA3_IN, + .vb_index = 2, + .vb_part = VPE_CHROMA, + }, + [VPE_PORT_MV_IN] = { + .channel = VPE_CHAN_MV_IN, + }, + [VPE_PORT_MV_OUT] = { + .channel = VPE_CHAN_MV_OUT, + }, + [VPE_PORT_LUMA_OUT] = { + .channel = VPE_CHAN_LUMA_OUT, + .vb_part = VPE_LUMA, + }, + [VPE_PORT_CHROMA_OUT] = { + .channel = VPE_CHAN_CHROMA_OUT, + .vb_part = VPE_CHROMA, + }, + [VPE_PORT_RGB_OUT] = { + .channel = VPE_CHAN_RGB_OUT, + .vb_part = VPE_LUMA, + }, +}; + + +/* driver info for each of the supported video formats */ +struct vpe_fmt { + char *name; /* human-readable name */ + u32 fourcc; /* standard format identifier */ + u8 types; /* CAPTURE and/or OUTPUT */ + u8 coplanar; /* set for unpacked Luma and Chroma */ + /* vpdma format info for each plane */ + struct vpdma_data_format const *vpdma_fmt[VPE_MAX_PLANES]; +}; + +static struct vpe_fmt vpe_formats[] = { + { + .name = "YUV 422 co-planar", + .fourcc = V4L2_PIX_FMT_NV16, + .types = VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT, + .coplanar = 1, + .vpdma_fmt = { &vpdma_yuv_fmts[VPDMA_DATA_FMT_Y444], + &vpdma_yuv_fmts[VPDMA_DATA_FMT_C444], + }, + }, + { + .name = "YUV 420 co-planar", + .fourcc = V4L2_PIX_FMT_NV12, + .types = VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT, + .coplanar = 1, + .vpdma_fmt = { &vpdma_yuv_fmts[VPDMA_DATA_FMT_Y420], + &vpdma_yuv_fmts[VPDMA_DATA_FMT_C420], + }, + }, + { + .name = "YUYV 422 packed", + .fourcc = V4L2_PIX_FMT_YUYV, + .types = VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT, + .coplanar = 0, + .vpdma_fmt = { &vpdma_yuv_fmts[VPDMA_DATA_FMT_YC422], + }, + }, + { + .name = "UYVY 422 packed", + .fourcc = V4L2_PIX_FMT_UYVY, + .types = VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT, + .coplanar = 0, + .vpdma_fmt = { &vpdma_yuv_fmts[VPDMA_DATA_FMT_CY422], + }, + }, +}; + +/* + * per-queue, driver-specific private data. + * there is one source queue and one destination queue for each m2m context. + */ +struct vpe_q_data { + unsigned int width; /* frame width */ + unsigned int height; /* frame height */ + unsigned int bytesperline[VPE_MAX_PLANES]; /* bytes per line in memory */ + enum v4l2_colorspace colorspace; + enum v4l2_field field; /* supported field value */ + unsigned int flags; + unsigned int sizeimage[VPE_MAX_PLANES]; /* image size in memory */ + struct v4l2_rect c_rect; /* crop/compose rectangle */ + struct vpe_fmt *fmt; /* format info */ +}; + +/* vpe_q_data flag bits */ +#define Q_DATA_FRAME_1D (1 << 0) +#define Q_DATA_MODE_TILED (1 << 1) +#define Q_DATA_INTERLACED (1 << 2) + +enum { + Q_DATA_SRC = 0, + Q_DATA_DST = 1, +}; + +/* find our format description corresponding to the passed v4l2_format */ +static struct vpe_fmt *find_format(struct v4l2_format *f) +{ + struct vpe_fmt *fmt; + unsigned int k; + + for (k = 0; k < ARRAY_SIZE(vpe_formats); k++) { + fmt = &vpe_formats[k]; + if (fmt->fourcc == f->fmt.pix.pixelformat) + return fmt; + } + + return NULL; +} + +/* + * there is one vpe_dev structure in the driver, it is shared by + * all instances. + */ +struct vpe_dev { + struct v4l2_device v4l2_dev; + struct video_device vfd; + struct v4l2_m2m_dev *m2m_dev; + + atomic_t num_instances; /* count of driver instances */ + dma_addr_t loaded_mmrs; /* shadow mmrs in device */ + struct mutex dev_mutex; + spinlock_t lock; + + int irq; + void __iomem *base; + + struct vb2_alloc_ctx *alloc_ctx; + struct vpdma_data *vpdma; /* vpdma data handle */ +}; + +/* + * There is one vpe_ctx structure for each m2m context. + */ +struct vpe_ctx { + struct v4l2_fh fh; + struct vpe_dev *dev; + struct v4l2_m2m_ctx *m2m_ctx; + struct v4l2_ctrl_handler hdl; + + unsigned int field; /* current field */ + unsigned int sequence; /* current frame/field seq */ + unsigned int aborting; /* abort after next irq */ + + unsigned int bufs_per_job; /* input buffers per batch */ + unsigned int bufs_completed; /* bufs done in this batch */ + + struct vpe_q_data q_data[2]; /* src & dst queue data */ + struct vb2_buffer *src_vbs[VPE_MAX_SRC_BUFS]; + struct vb2_buffer *dst_vb; + + dma_addr_t mv_buf_dma[2]; /* dma addrs of motion vector in/out bufs */ + void *mv_buf[2]; /* virtual addrs of motion vector bufs */ + size_t mv_buf_size; /* current motion vector buffer size */ + struct vpdma_buf mmr_adb; /* shadow reg addr/data block */ + struct vpdma_desc_list desc_list; /* DMA descriptor list */ + + bool deinterlacing; /* using de-interlacer */ + bool load_mmrs; /* have new shadow reg values */ + + unsigned int src_mv_buf_selector; +}; + + +/* + * M2M devices get 2 queues. + * Return the queue given the type. + */ +static struct vpe_q_data *get_q_data(struct vpe_ctx *ctx, + enum v4l2_buf_type type) +{ + switch (type) { + case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: + return &ctx->q_data[Q_DATA_SRC]; + case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: + return &ctx->q_data[Q_DATA_DST]; + default: + BUG(); + } + return NULL; +} + +static u32 read_reg(struct vpe_dev *dev, int offset) +{ + return ioread32(dev->base + offset); +} + +static void write_reg(struct vpe_dev *dev, int offset, u32 value) +{ + iowrite32(value, dev->base + offset); +} + +/* register field read/write helpers */ +static int get_field(u32 value, u32 mask, int shift) +{ + return (value & (mask << shift)) >> shift; +} + +static int read_field_reg(struct vpe_dev *dev, int offset, u32 mask, int shift) +{ + return get_field(read_reg(dev, offset), mask, shift); +} + +static void write_field(u32 *valp, u32 field, u32 mask, int shift) +{ + u32 val = *valp; + + val &= ~(mask << shift); + val |= (field & mask) << shift; + *valp = val; +} + +static void write_field_reg(struct vpe_dev *dev, int offset, u32 field, + u32 mask, int shift) +{ + u32 val = read_reg(dev, offset); + + write_field(&val, field, mask, shift); + + write_reg(dev, offset, val); +} + +/* + * DMA address/data block for the shadow registers + */ +struct vpe_mmr_adb { + struct vpdma_adb_hdr out_fmt_hdr; + u32 out_fmt_reg[1]; + u32 out_fmt_pad[3]; + struct vpdma_adb_hdr us1_hdr; + u32 us1_regs[8]; + struct vpdma_adb_hdr us2_hdr; + u32 us2_regs[8]; + struct vpdma_adb_hdr us3_hdr; + u32 us3_regs[8]; + struct vpdma_adb_hdr dei_hdr; + u32 dei_regs[8]; + struct vpdma_adb_hdr sc_hdr; + u32 sc_regs[1]; + u32 sc_pad[3]; + struct vpdma_adb_hdr csc_hdr; + u32 csc_regs[6]; + u32 csc_pad[2]; +}; + +#define VPE_SET_MMR_ADB_HDR(ctx, hdr, regs, offset_a) \ + VPDMA_SET_MMR_ADB_HDR(ctx->mmr_adb, vpe_mmr_adb, hdr, regs, offset_a) +/* + * Set the headers for all of the address/data block structures. + */ +static void init_adb_hdrs(struct vpe_ctx *ctx) +{ + VPE_SET_MMR_ADB_HDR(ctx, out_fmt_hdr, out_fmt_reg, VPE_CLK_FORMAT_SELECT); + VPE_SET_MMR_ADB_HDR(ctx, us1_hdr, us1_regs, VPE_US1_R0); + VPE_SET_MMR_ADB_HDR(ctx, us2_hdr, us2_regs, VPE_US2_R0); + VPE_SET_MMR_ADB_HDR(ctx, us3_hdr, us3_regs, VPE_US3_R0); + VPE_SET_MMR_ADB_HDR(ctx, dei_hdr, dei_regs, VPE_DEI_FRAME_SIZE); + VPE_SET_MMR_ADB_HDR(ctx, sc_hdr, sc_regs, VPE_SC_MP_SC0); + VPE_SET_MMR_ADB_HDR(ctx, csc_hdr, csc_regs, VPE_CSC_CSC00); +}; + +/* + * Allocate or re-allocate the motion vector DMA buffers + * There are two buffers, one for input and one for output. + * However, the roles are reversed after each field is processed. + * In other words, after each field is processed, the previous + * output (dst) MV buffer becomes the new input (src) MV buffer. + */ +static int realloc_mv_buffers(struct vpe_ctx *ctx, size_t size) +{ + struct device *dev = ctx->dev->v4l2_dev.dev; + + if (ctx->mv_buf_size == size) + return 0; + + if (ctx->mv_buf[0]) + dma_free_coherent(dev, ctx->mv_buf_size, ctx->mv_buf[0], + ctx->mv_buf_dma[0]); + + if (ctx->mv_buf[1]) + dma_free_coherent(dev, ctx->mv_buf_size, ctx->mv_buf[1], + ctx->mv_buf_dma[1]); + + if (size == 0) + return 0; + + ctx->mv_buf[0] = dma_alloc_coherent(dev, size, &ctx->mv_buf_dma[0], + GFP_KERNEL); + if (!ctx->mv_buf[0]) { + vpe_err(ctx->dev, "failed to allocate motion vector buffer\n"); + return -ENOMEM; + } + + ctx->mv_buf[1] = dma_alloc_coherent(dev, size, &ctx->mv_buf_dma[1], + GFP_KERNEL); + if (!ctx->mv_buf[1]) { + vpe_err(ctx->dev, "failed to allocate motion vector buffer\n"); + dma_free_coherent(dev, size, ctx->mv_buf[0], + ctx->mv_buf_dma[0]); + + return -ENOMEM; + } + + ctx->mv_buf_size = size; + ctx->src_mv_buf_selector = 0; + + return 0; +} + +static void free_mv_buffers(struct vpe_ctx *ctx) +{ + realloc_mv_buffers(ctx, 0); +} + +/* + * While de-interlacing, we keep the two most recent input buffers + * around. This function frees those two buffers when we have + * finished processing the current stream. + */ +static void free_vbs(struct vpe_ctx *ctx) +{ + struct vpe_dev *dev = ctx->dev; + unsigned long flags; + + if (ctx->src_vbs[2] == NULL) + return; + + spin_lock_irqsave(&dev->lock, flags); + if (ctx->src_vbs[2]) { + v4l2_m2m_buf_done(ctx->src_vbs[2], VB2_BUF_STATE_DONE); + v4l2_m2m_buf_done(ctx->src_vbs[1], VB2_BUF_STATE_DONE); + } + spin_unlock_irqrestore(&dev->lock, flags); +} + +/* + * Enable or disable the VPE clocks + */ +static void vpe_set_clock_enable(struct vpe_dev *dev, bool on) +{ + u32 val = 0; + + if (on) + val = VPE_DATA_PATH_CLK_ENABLE | VPE_VPEDMA_CLK_ENABLE; + write_reg(dev, VPE_CLK_ENABLE, val); +} + +static void vpe_top_reset(struct vpe_dev *dev) +{ + + write_field_reg(dev, VPE_CLK_RESET, 1, VPE_DATA_PATH_CLK_RESET_MASK, + VPE_DATA_PATH_CLK_RESET_SHIFT); + + usleep_range(100, 150); + + write_field_reg(dev, VPE_CLK_RESET, 0, VPE_DATA_PATH_CLK_RESET_MASK, + VPE_DATA_PATH_CLK_RESET_SHIFT); +} + +static void vpe_top_vpdma_reset(struct vpe_dev *dev) +{ + write_field_reg(dev, VPE_CLK_RESET, 1, VPE_VPDMA_CLK_RESET_MASK, + VPE_VPDMA_CLK_RESET_SHIFT); + + usleep_range(100, 150); + + write_field_reg(dev, VPE_CLK_RESET, 0, VPE_VPDMA_CLK_RESET_MASK, + VPE_VPDMA_CLK_RESET_SHIFT); +} + +/* + * Load the correct of upsampler coefficients into the shadow MMRs + */ +static void set_us_coefficients(struct vpe_ctx *ctx) +{ + struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr; + struct vpe_q_data *s_q_data = &ctx->q_data[Q_DATA_SRC]; + u32 *us1_reg = &mmr_adb->us1_regs[0]; + u32 *us2_reg = &mmr_adb->us2_regs[0]; + u32 *us3_reg = &mmr_adb->us3_regs[0]; + const unsigned short *cp, *end_cp; + + cp = &us_coeffs[0].anchor_fid0_c0; + + if (s_q_data->flags & Q_DATA_INTERLACED) /* interlaced */ + cp += sizeof(us_coeffs[0]) / sizeof(*cp); + + end_cp = cp + sizeof(us_coeffs[0]) / sizeof(*cp); + + while (cp < end_cp) { + write_field(us1_reg, *cp++, VPE_US_C0_MASK, VPE_US_C0_SHIFT); + write_field(us1_reg, *cp++, VPE_US_C1_MASK, VPE_US_C1_SHIFT); + *us2_reg++ = *us1_reg; + *us3_reg++ = *us1_reg++; + } + ctx->load_mmrs = true; +} + +/* + * Set the upsampler config mode and the VPDMA line mode in the shadow MMRs. + */ +static void set_cfg_and_line_modes(struct vpe_ctx *ctx) +{ + struct vpe_fmt *fmt = ctx->q_data[Q_DATA_SRC].fmt; + struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr; + u32 *us1_reg0 = &mmr_adb->us1_regs[0]; + u32 *us2_reg0 = &mmr_adb->us2_regs[0]; + u32 *us3_reg0 = &mmr_adb->us3_regs[0]; + int line_mode = 1; + int cfg_mode = 1; + + /* + * Cfg Mode 0: YUV420 source, enable upsampler, DEI is de-interlacing. + * Cfg Mode 1: YUV422 source, disable upsampler, DEI is de-interlacing. + */ + + if (fmt->fourcc == V4L2_PIX_FMT_NV12) { + cfg_mode = 0; + line_mode = 0; /* double lines to line buffer */ + } + + write_field(us1_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT); + write_field(us2_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT); + write_field(us3_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT); + + /* regs for now */ + vpdma_set_line_mode(ctx->dev->vpdma, line_mode, VPE_CHAN_CHROMA1_IN); + vpdma_set_line_mode(ctx->dev->vpdma, line_mode, VPE_CHAN_CHROMA2_IN); + vpdma_set_line_mode(ctx->dev->vpdma, line_mode, VPE_CHAN_CHROMA3_IN); + + /* frame start for input luma */ + vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE, + VPE_CHAN_LUMA1_IN); + vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE, + VPE_CHAN_LUMA2_IN); + vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE, + VPE_CHAN_LUMA3_IN); + + /* frame start for input chroma */ + vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE, + VPE_CHAN_CHROMA1_IN); + vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE, + VPE_CHAN_CHROMA2_IN); + vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE, + VPE_CHAN_CHROMA3_IN); + + /* frame start for MV in client */ + vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE, + VPE_CHAN_MV_IN); + + ctx->load_mmrs = true; +} + +/* + * Set the shadow registers that are modified when the source + * format changes. + */ +static void set_src_registers(struct vpe_ctx *ctx) +{ + set_us_coefficients(ctx); +} + +/* + * Set the shadow registers that are modified when the destination + * format changes. + */ +static void set_dst_registers(struct vpe_ctx *ctx) +{ + struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr; + struct vpe_fmt *fmt = ctx->q_data[Q_DATA_DST].fmt; + u32 val = 0; + + /* select RGB path when color space conversion is supported in future */ + if (fmt->fourcc == V4L2_PIX_FMT_RGB24) + val |= VPE_RGB_OUT_SELECT | VPE_CSC_SRC_DEI_SCALER; + else if (fmt->fourcc == V4L2_PIX_FMT_NV16) + val |= VPE_COLOR_SEPARATE_422; + + /* The source of CHR_DS is always the scaler, whether it's used or not */ + val |= VPE_DS_SRC_DEI_SCALER; + + if (fmt->fourcc != V4L2_PIX_FMT_NV12) + val |= VPE_DS_BYPASS; + + mmr_adb->out_fmt_reg[0] = val; + + ctx->load_mmrs = true; +} + +/* + * Set the de-interlacer shadow register values + */ +static void set_dei_regs(struct vpe_ctx *ctx) +{ + struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr; + struct vpe_q_data *s_q_data = &ctx->q_data[Q_DATA_SRC]; + unsigned int src_h = s_q_data->c_rect.height; + unsigned int src_w = s_q_data->c_rect.width; + u32 *dei_mmr0 = &mmr_adb->dei_regs[0]; + bool deinterlace = true; + u32 val = 0; + + /* + * according to TRM, we should set DEI in progressive bypass mode when + * the input content is progressive, however, DEI is bypassed correctly + * for both progressive and interlace content in interlace bypass mode. + * It has been recommended not to use progressive bypass mode. + */ + if ((!ctx->deinterlacing && (s_q_data->flags & Q_DATA_INTERLACED)) || + !(s_q_data->flags & Q_DATA_INTERLACED)) { + deinterlace = false; + val = VPE_DEI_INTERLACE_BYPASS; + } + + src_h = deinterlace ? src_h * 2 : src_h; + + val |= (src_h << VPE_DEI_HEIGHT_SHIFT) | + (src_w << VPE_DEI_WIDTH_SHIFT) | + VPE_DEI_FIELD_FLUSH; + + *dei_mmr0 = val; + + ctx->load_mmrs = true; +} + +static void set_dei_shadow_registers(struct vpe_ctx *ctx) +{ + struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr; + u32 *dei_mmr = &mmr_adb->dei_regs[0]; + const struct vpe_dei_regs *cur = &dei_regs; + + dei_mmr[2] = cur->mdt_spacial_freq_thr_reg; + dei_mmr[3] = cur->edi_config_reg; + dei_mmr[4] = cur->edi_lut_reg0; + dei_mmr[5] = cur->edi_lut_reg1; + dei_mmr[6] = cur->edi_lut_reg2; + dei_mmr[7] = cur->edi_lut_reg3; + + ctx->load_mmrs = true; +} + +static void set_csc_coeff_bypass(struct vpe_ctx *ctx) +{ + struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr; + u32 *shadow_csc_reg5 = &mmr_adb->csc_regs[5]; + + *shadow_csc_reg5 |= VPE_CSC_BYPASS; + + ctx->load_mmrs = true; +} + +static void set_sc_regs_bypass(struct vpe_ctx *ctx) +{ + struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr; + u32 *sc_reg0 = &mmr_adb->sc_regs[0]; + u32 val = 0; + + val |= VPE_SC_BYPASS; + *sc_reg0 = val; + + ctx->load_mmrs = true; +} + +/* + * Set the shadow registers whose values are modified when either the + * source or destination format is changed. + */ +static int set_srcdst_params(struct vpe_ctx *ctx) +{ + struct vpe_q_data *s_q_data = &ctx->q_data[Q_DATA_SRC]; + struct vpe_q_data *d_q_data = &ctx->q_data[Q_DATA_DST]; + size_t mv_buf_size; + int ret; + + ctx->sequence = 0; + ctx->field = V4L2_FIELD_TOP; + + if ((s_q_data->flags & Q_DATA_INTERLACED) && + !(d_q_data->flags & Q_DATA_INTERLACED)) { + const struct vpdma_data_format *mv = + &vpdma_misc_fmts[VPDMA_DATA_FMT_MV]; + + ctx->deinterlacing = 1; + mv_buf_size = + (s_q_data->width * s_q_data->height * mv->depth) >> 3; + } else { + ctx->deinterlacing = 0; + mv_buf_size = 0; + } + + free_vbs(ctx); + + ret = realloc_mv_buffers(ctx, mv_buf_size); + if (ret) + return ret; + + set_cfg_and_line_modes(ctx); + set_dei_regs(ctx); + set_csc_coeff_bypass(ctx); + set_sc_regs_bypass(ctx); + + return 0; +} + +/* + * Return the vpe_ctx structure for a given struct file + */ +static struct vpe_ctx *file2ctx(struct file *file) +{ + return container_of(file->private_data, struct vpe_ctx, fh); +} + +/* + * mem2mem callbacks + */ + +/** + * job_ready() - check whether an instance is ready to be scheduled to run + */ +static int job_ready(void *priv) +{ + struct vpe_ctx *ctx = priv; + int needed = ctx->bufs_per_job; + + if (ctx->deinterlacing && ctx->src_vbs[2] == NULL) + needed += 2; /* need additional two most recent fields */ + + if (v4l2_m2m_num_src_bufs_ready(ctx->m2m_ctx) < needed) + return 0; + + return 1; +} + +static void job_abort(void *priv) +{ + struct vpe_ctx *ctx = priv; + + /* Will cancel the transaction in the next interrupt handler */ + ctx->aborting = 1; +} + +/* + * Lock access to the device + */ +static void vpe_lock(void *priv) +{ + struct vpe_ctx *ctx = priv; + struct vpe_dev *dev = ctx->dev; + mutex_lock(&dev->dev_mutex); +} + +static void vpe_unlock(void *priv) +{ + struct vpe_ctx *ctx = priv; + struct vpe_dev *dev = ctx->dev; + mutex_unlock(&dev->dev_mutex); +} + +static void vpe_dump_regs(struct vpe_dev *dev) +{ +#define DUMPREG(r) vpe_dbg(dev, "%-35s %08x\n", #r, read_reg(dev, VPE_##r)) + + vpe_dbg(dev, "VPE Registers:\n"); + + DUMPREG(PID); + DUMPREG(SYSCONFIG); + DUMPREG(INT0_STATUS0_RAW); + DUMPREG(INT0_STATUS0); + DUMPREG(INT0_ENABLE0); + DUMPREG(INT0_STATUS1_RAW); + DUMPREG(INT0_STATUS1); + DUMPREG(INT0_ENABLE1); + DUMPREG(CLK_ENABLE); + DUMPREG(CLK_RESET); + DUMPREG(CLK_FORMAT_SELECT); + DUMPREG(CLK_RANGE_MAP); + DUMPREG(US1_R0); + DUMPREG(US1_R1); + DUMPREG(US1_R2); + DUMPREG(US1_R3); + DUMPREG(US1_R4); + DUMPREG(US1_R5); + DUMPREG(US1_R6); + DUMPREG(US1_R7); + DUMPREG(US2_R0); + DUMPREG(US2_R1); + DUMPREG(US2_R2); + DUMPREG(US2_R3); + DUMPREG(US2_R4); + DUMPREG(US2_R5); + DUMPREG(US2_R6); + DUMPREG(US2_R7); + DUMPREG(US3_R0); + DUMPREG(US3_R1); + DUMPREG(US3_R2); + DUMPREG(US3_R3); + DUMPREG(US3_R4); + DUMPREG(US3_R5); + DUMPREG(US3_R6); + DUMPREG(US3_R7); + DUMPREG(DEI_FRAME_SIZE); + DUMPREG(MDT_BYPASS); + DUMPREG(MDT_SF_THRESHOLD); + DUMPREG(EDI_CONFIG); + DUMPREG(DEI_EDI_LUT_R0); + DUMPREG(DEI_EDI_LUT_R1); + DUMPREG(DEI_EDI_LUT_R2); + DUMPREG(DEI_EDI_LUT_R3); + DUMPREG(DEI_FMD_WINDOW_R0); + DUMPREG(DEI_FMD_WINDOW_R1); + DUMPREG(DEI_FMD_CONTROL_R0); + DUMPREG(DEI_FMD_CONTROL_R1); + DUMPREG(DEI_FMD_STATUS_R0); + DUMPREG(DEI_FMD_STATUS_R1); + DUMPREG(DEI_FMD_STATUS_R2); + DUMPREG(SC_MP_SC0); + DUMPREG(SC_MP_SC1); + DUMPREG(SC_MP_SC2); + DUMPREG(SC_MP_SC3); + DUMPREG(SC_MP_SC4); + DUMPREG(SC_MP_SC5); + DUMPREG(SC_MP_SC6); + DUMPREG(SC_MP_SC8); + DUMPREG(SC_MP_SC9); + DUMPREG(SC_MP_SC10); + DUMPREG(SC_MP_SC11); + DUMPREG(SC_MP_SC12); + DUMPREG(SC_MP_SC13); + DUMPREG(SC_MP_SC17); + DUMPREG(SC_MP_SC18); + DUMPREG(SC_MP_SC19); + DUMPREG(SC_MP_SC20); + DUMPREG(SC_MP_SC21); + DUMPREG(SC_MP_SC22); + DUMPREG(SC_MP_SC23); + DUMPREG(SC_MP_SC24); + DUMPREG(SC_MP_SC25); + DUMPREG(CSC_CSC00); + DUMPREG(CSC_CSC01); + DUMPREG(CSC_CSC02); + DUMPREG(CSC_CSC03); + DUMPREG(CSC_CSC04); + DUMPREG(CSC_CSC05); +#undef DUMPREG +} + +static void add_out_dtd(struct vpe_ctx *ctx, int port) +{ + struct vpe_q_data *q_data = &ctx->q_data[Q_DATA_DST]; + const struct vpe_port_data *p_data = &port_data[port]; + struct vb2_buffer *vb = ctx->dst_vb; + struct v4l2_rect *c_rect = &q_data->c_rect; + struct vpe_fmt *fmt = q_data->fmt; + const struct vpdma_data_format *vpdma_fmt; + int mv_buf_selector = !ctx->src_mv_buf_selector; + dma_addr_t dma_addr; + u32 flags = 0; + + if (port == VPE_PORT_MV_OUT) { + vpdma_fmt = &vpdma_misc_fmts[VPDMA_DATA_FMT_MV]; + dma_addr = ctx->mv_buf_dma[mv_buf_selector]; + } else { + /* to incorporate interleaved formats */ + int plane = fmt->coplanar ? p_data->vb_part : 0; + + vpdma_fmt = fmt->vpdma_fmt[plane]; + dma_addr = vb2_dma_contig_plane_dma_addr(vb, plane); + if (!dma_addr) { + vpe_err(ctx->dev, + "acquiring output buffer(%d) dma_addr failed\n", + port); + return; + } + } + + if (q_data->flags & Q_DATA_FRAME_1D) + flags |= VPDMA_DATA_FRAME_1D; + if (q_data->flags & Q_DATA_MODE_TILED) + flags |= VPDMA_DATA_MODE_TILED; + + vpdma_add_out_dtd(&ctx->desc_list, c_rect, vpdma_fmt, dma_addr, + p_data->channel, flags); +} + +static void add_in_dtd(struct vpe_ctx *ctx, int port) +{ + struct vpe_q_data *q_data = &ctx->q_data[Q_DATA_SRC]; + const struct vpe_port_data *p_data = &port_data[port]; + struct vb2_buffer *vb = ctx->src_vbs[p_data->vb_index]; + struct v4l2_rect *c_rect = &q_data->c_rect; + struct vpe_fmt *fmt = q_data->fmt; + const struct vpdma_data_format *vpdma_fmt; + int mv_buf_selector = ctx->src_mv_buf_selector; + int field = vb->v4l2_buf.field == V4L2_FIELD_BOTTOM; + dma_addr_t dma_addr; + u32 flags = 0; + + if (port == VPE_PORT_MV_IN) { + vpdma_fmt = &vpdma_misc_fmts[VPDMA_DATA_FMT_MV]; + dma_addr = ctx->mv_buf_dma[mv_buf_selector]; + } else { + /* to incorporate interleaved formats */ + int plane = fmt->coplanar ? p_data->vb_part : 0; + + vpdma_fmt = fmt->vpdma_fmt[plane]; + + dma_addr = vb2_dma_contig_plane_dma_addr(vb, plane); + if (!dma_addr) { + vpe_err(ctx->dev, + "acquiring input buffer(%d) dma_addr failed\n", + port); + return; + } + } + + if (q_data->flags & Q_DATA_FRAME_1D) + flags |= VPDMA_DATA_FRAME_1D; + if (q_data->flags & Q_DATA_MODE_TILED) + flags |= VPDMA_DATA_MODE_TILED; + + vpdma_add_in_dtd(&ctx->desc_list, q_data->width, q_data->height, + c_rect, vpdma_fmt, dma_addr, p_data->channel, field, flags); +} + +/* + * Enable the expected IRQ sources + */ +static void enable_irqs(struct vpe_ctx *ctx) +{ + write_reg(ctx->dev, VPE_INT0_ENABLE0_SET, VPE_INT0_LIST0_COMPLETE); + write_reg(ctx->dev, VPE_INT0_ENABLE1_SET, VPE_DEI_ERROR_INT | + VPE_DS1_UV_ERROR_INT); + + vpdma_enable_list_complete_irq(ctx->dev->vpdma, 0, true); +} + +static void disable_irqs(struct vpe_ctx *ctx) +{ + write_reg(ctx->dev, VPE_INT0_ENABLE0_CLR, 0xffffffff); + write_reg(ctx->dev, VPE_INT0_ENABLE1_CLR, 0xffffffff); + + vpdma_enable_list_complete_irq(ctx->dev->vpdma, 0, false); +} + +/* device_run() - prepares and starts the device + * + * This function is only called when both the source and destination + * buffers are in place. + */ +static void device_run(void *priv) +{ + struct vpe_ctx *ctx = priv; + struct vpe_q_data *d_q_data = &ctx->q_data[Q_DATA_DST]; + + if (ctx->deinterlacing && ctx->src_vbs[2] == NULL) { + ctx->src_vbs[2] = v4l2_m2m_src_buf_remove(ctx->m2m_ctx); + WARN_ON(ctx->src_vbs[2] == NULL); + ctx->src_vbs[1] = v4l2_m2m_src_buf_remove(ctx->m2m_ctx); + WARN_ON(ctx->src_vbs[1] == NULL); + } + + ctx->src_vbs[0] = v4l2_m2m_src_buf_remove(ctx->m2m_ctx); + WARN_ON(ctx->src_vbs[0] == NULL); + ctx->dst_vb = v4l2_m2m_dst_buf_remove(ctx->m2m_ctx); + WARN_ON(ctx->dst_vb == NULL); + + /* config descriptors */ + if (ctx->dev->loaded_mmrs != ctx->mmr_adb.dma_addr || ctx->load_mmrs) { + vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->mmr_adb); + vpdma_add_cfd_adb(&ctx->desc_list, CFD_MMR_CLIENT, &ctx->mmr_adb); + ctx->dev->loaded_mmrs = ctx->mmr_adb.dma_addr; + ctx->load_mmrs = false; + } + + /* output data descriptors */ + if (ctx->deinterlacing) + add_out_dtd(ctx, VPE_PORT_MV_OUT); + + add_out_dtd(ctx, VPE_PORT_LUMA_OUT); + if (d_q_data->fmt->coplanar) + add_out_dtd(ctx, VPE_PORT_CHROMA_OUT); + + /* input data descriptors */ + if (ctx->deinterlacing) { + add_in_dtd(ctx, VPE_PORT_LUMA3_IN); + add_in_dtd(ctx, VPE_PORT_CHROMA3_IN); + + add_in_dtd(ctx, VPE_PORT_LUMA2_IN); + add_in_dtd(ctx, VPE_PORT_CHROMA2_IN); + } + + add_in_dtd(ctx, VPE_PORT_LUMA1_IN); + add_in_dtd(ctx, VPE_PORT_CHROMA1_IN); + + if (ctx->deinterlacing) + add_in_dtd(ctx, VPE_PORT_MV_IN); + + /* sync on channel control descriptors for input ports */ + vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_LUMA1_IN); + vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_CHROMA1_IN); + + if (ctx->deinterlacing) { + vpdma_add_sync_on_channel_ctd(&ctx->desc_list, + VPE_CHAN_LUMA2_IN); + vpdma_add_sync_on_channel_ctd(&ctx->desc_list, + VPE_CHAN_CHROMA2_IN); + + vpdma_add_sync_on_channel_ctd(&ctx->desc_list, + VPE_CHAN_LUMA3_IN); + vpdma_add_sync_on_channel_ctd(&ctx->desc_list, + VPE_CHAN_CHROMA3_IN); + + vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_MV_IN); + } + + /* sync on channel control descriptors for output ports */ + vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_LUMA_OUT); + if (d_q_data->fmt->coplanar) + vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_CHROMA_OUT); + + if (ctx->deinterlacing) + vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_MV_OUT); + + enable_irqs(ctx); + + vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->desc_list.buf); + vpdma_submit_descs(ctx->dev->vpdma, &ctx->desc_list); +} + +static void dei_error(struct vpe_ctx *ctx) +{ + dev_warn(ctx->dev->v4l2_dev.dev, + "received DEI error interrupt\n"); +} + +static void ds1_uv_error(struct vpe_ctx *ctx) +{ + dev_warn(ctx->dev->v4l2_dev.dev, + "received downsampler error interrupt\n"); +} + +static irqreturn_t vpe_irq(int irq_vpe, void *data) +{ + struct vpe_dev *dev = (struct vpe_dev *)data; + struct vpe_ctx *ctx; + struct vpe_q_data *d_q_data; + struct vb2_buffer *s_vb, *d_vb; + struct v4l2_buffer *s_buf, *d_buf; + unsigned long flags; + u32 irqst0, irqst1; + + irqst0 = read_reg(dev, VPE_INT0_STATUS0); + if (irqst0) { + write_reg(dev, VPE_INT0_STATUS0_CLR, irqst0); + vpe_dbg(dev, "INT0_STATUS0 = 0x%08x\n", irqst0); + } + + irqst1 = read_reg(dev, VPE_INT0_STATUS1); + if (irqst1) { + write_reg(dev, VPE_INT0_STATUS1_CLR, irqst1); + vpe_dbg(dev, "INT0_STATUS1 = 0x%08x\n", irqst1); + } + + ctx = v4l2_m2m_get_curr_priv(dev->m2m_dev); + if (!ctx) { + vpe_err(dev, "instance released before end of transaction\n"); + goto handled; + } + + if (irqst1) { + if (irqst1 & VPE_DEI_ERROR_INT) { + irqst1 &= ~VPE_DEI_ERROR_INT; + dei_error(ctx); + } + if (irqst1 & VPE_DS1_UV_ERROR_INT) { + irqst1 &= ~VPE_DS1_UV_ERROR_INT; + ds1_uv_error(ctx); + } + } + + if (irqst0) { + if (irqst0 & VPE_INT0_LIST0_COMPLETE) + vpdma_clear_list_stat(ctx->dev->vpdma); + + irqst0 &= ~(VPE_INT0_LIST0_COMPLETE); + } + + if (irqst0 | irqst1) { + dev_warn(dev->v4l2_dev.dev, "Unexpected interrupt: " + "INT0_STATUS0 = 0x%08x, INT0_STATUS1 = 0x%08x\n", + irqst0, irqst1); + } + + disable_irqs(ctx); + + vpdma_unmap_desc_buf(dev->vpdma, &ctx->desc_list.buf); + vpdma_unmap_desc_buf(dev->vpdma, &ctx->mmr_adb); + + vpdma_reset_desc_list(&ctx->desc_list); + + /* the previous dst mv buffer becomes the next src mv buffer */ + ctx->src_mv_buf_selector = !ctx->src_mv_buf_selector; + + if (ctx->aborting) + goto finished; + + s_vb = ctx->src_vbs[0]; + d_vb = ctx->dst_vb; + s_buf = &s_vb->v4l2_buf; + d_buf = &d_vb->v4l2_buf; + + d_buf->timestamp = s_buf->timestamp; + if (s_buf->flags & V4L2_BUF_FLAG_TIMECODE) { + d_buf->flags |= V4L2_BUF_FLAG_TIMECODE; + d_buf->timecode = s_buf->timecode; + } + d_buf->sequence = ctx->sequence; + d_buf->field = ctx->field; + + d_q_data = &ctx->q_data[Q_DATA_DST]; + if (d_q_data->flags & Q_DATA_INTERLACED) { + if (ctx->field == V4L2_FIELD_BOTTOM) { + ctx->sequence++; + ctx->field = V4L2_FIELD_TOP; + } else { + WARN_ON(ctx->field != V4L2_FIELD_TOP); + ctx->field = V4L2_FIELD_BOTTOM; + } + } else { + ctx->sequence++; + } + + if (ctx->deinterlacing) + s_vb = ctx->src_vbs[2]; + + spin_lock_irqsave(&dev->lock, flags); + v4l2_m2m_buf_done(s_vb, VB2_BUF_STATE_DONE); + v4l2_m2m_buf_done(d_vb, VB2_BUF_STATE_DONE); + spin_unlock_irqrestore(&dev->lock, flags); + + if (ctx->deinterlacing) { + ctx->src_vbs[2] = ctx->src_vbs[1]; + ctx->src_vbs[1] = ctx->src_vbs[0]; + } + + ctx->bufs_completed++; + if (ctx->bufs_completed < ctx->bufs_per_job) { + device_run(ctx); + goto handled; + } + +finished: + vpe_dbg(ctx->dev, "finishing transaction\n"); + ctx->bufs_completed = 0; + v4l2_m2m_job_finish(dev->m2m_dev, ctx->m2m_ctx); +handled: + return IRQ_HANDLED; +} + +/* + * video ioctls + */ +static int vpe_querycap(struct file *file, void *priv, + struct v4l2_capability *cap) +{ + strncpy(cap->driver, VPE_MODULE_NAME, sizeof(cap->driver) - 1); + strncpy(cap->card, VPE_MODULE_NAME, sizeof(cap->card) - 1); + strlcpy(cap->bus_info, VPE_MODULE_NAME, sizeof(cap->bus_info)); + cap->device_caps = V4L2_CAP_VIDEO_M2M | V4L2_CAP_STREAMING; + cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS; + return 0; +} + +static int __enum_fmt(struct v4l2_fmtdesc *f, u32 type) +{ + int i, index; + struct vpe_fmt *fmt = NULL; + + index = 0; + for (i = 0; i < ARRAY_SIZE(vpe_formats); ++i) { + if (vpe_formats[i].types & type) { + if (index == f->index) { + fmt = &vpe_formats[i]; + break; + } + index++; + } + } + + if (!fmt) + return -EINVAL; + + strncpy(f->description, fmt->name, sizeof(f->description) - 1); + f->pixelformat = fmt->fourcc; + return 0; +} + +static int vpe_enum_fmt(struct file *file, void *priv, + struct v4l2_fmtdesc *f) +{ + if (V4L2_TYPE_IS_OUTPUT(f->type)) + return __enum_fmt(f, VPE_FMT_TYPE_OUTPUT); + + return __enum_fmt(f, VPE_FMT_TYPE_CAPTURE); +} + +static int vpe_g_fmt(struct file *file, void *priv, struct v4l2_format *f) +{ + struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp; + struct vpe_ctx *ctx = file2ctx(file); + struct vb2_queue *vq; + struct vpe_q_data *q_data; + int i; + + vq = v4l2_m2m_get_vq(ctx->m2m_ctx, f->type); + if (!vq) + return -EINVAL; + + q_data = get_q_data(ctx, f->type); + + pix->width = q_data->width; + pix->height = q_data->height; + pix->pixelformat = q_data->fmt->fourcc; + pix->field = q_data->field; + + if (V4L2_TYPE_IS_OUTPUT(f->type)) { + pix->colorspace = q_data->colorspace; + } else { + struct vpe_q_data *s_q_data; + + /* get colorspace from the source queue */ + s_q_data = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE); + + pix->colorspace = s_q_data->colorspace; + } + + pix->num_planes = q_data->fmt->coplanar ? 2 : 1; + + for (i = 0; i < pix->num_planes; i++) { + pix->plane_fmt[i].bytesperline = q_data->bytesperline[i]; + pix->plane_fmt[i].sizeimage = q_data->sizeimage[i]; + } + + return 0; +} + +static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f, + struct vpe_fmt *fmt, int type) +{ + struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp; + struct v4l2_plane_pix_format *plane_fmt; + int i; + + if (!fmt || !(fmt->types & type)) { + vpe_err(ctx->dev, "Fourcc format (0x%08x) invalid.\n", + pix->pixelformat); + return -EINVAL; + } + + if (pix->field != V4L2_FIELD_NONE && pix->field != V4L2_FIELD_ALTERNATE) + pix->field = V4L2_FIELD_NONE; + + v4l_bound_align_image(&pix->width, MIN_W, MAX_W, W_ALIGN, + &pix->height, MIN_H, MAX_H, H_ALIGN, + S_ALIGN); + + pix->num_planes = fmt->coplanar ? 2 : 1; + pix->pixelformat = fmt->fourcc; + + if (type == VPE_FMT_TYPE_CAPTURE) { + struct vpe_q_data *s_q_data; + + /* get colorspace from the source queue */ + s_q_data = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE); + + pix->colorspace = s_q_data->colorspace; + } else { + if (!pix->colorspace) + pix->colorspace = V4L2_COLORSPACE_SMPTE240M; + } + + for (i = 0; i < pix->num_planes; i++) { + int depth; + + plane_fmt = &pix->plane_fmt[i]; + depth = fmt->vpdma_fmt[i]->depth; + + if (i == VPE_LUMA) + plane_fmt->bytesperline = + round_up((pix->width * depth) >> 3, + 1 << L_ALIGN); + else + plane_fmt->bytesperline = pix->width; + + plane_fmt->sizeimage = + (pix->height * pix->width * depth) >> 3; + } + + return 0; +} + +static int vpe_try_fmt(struct file *file, void *priv, struct v4l2_format *f) +{ + struct vpe_ctx *ctx = file2ctx(file); + struct vpe_fmt *fmt = find_format(f); + + if (V4L2_TYPE_IS_OUTPUT(f->type)) + return __vpe_try_fmt(ctx, f, fmt, VPE_FMT_TYPE_OUTPUT); + else + return __vpe_try_fmt(ctx, f, fmt, VPE_FMT_TYPE_CAPTURE); +} + +static int __vpe_s_fmt(struct vpe_ctx *ctx, struct v4l2_format *f) +{ + struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp; + struct v4l2_plane_pix_format *plane_fmt; + struct vpe_q_data *q_data; + struct vb2_queue *vq; + int i; + + vq = v4l2_m2m_get_vq(ctx->m2m_ctx, f->type); + if (!vq) + return -EINVAL; + + if (vb2_is_busy(vq)) { + vpe_err(ctx->dev, "queue busy\n"); + return -EBUSY; + } + + q_data = get_q_data(ctx, f->type); + if (!q_data) + return -EINVAL; + + q_data->fmt = find_format(f); + q_data->width = pix->width; + q_data->height = pix->height; + q_data->colorspace = pix->colorspace; + q_data->field = pix->field; + + for (i = 0; i < pix->num_planes; i++) { + plane_fmt = &pix->plane_fmt[i]; + + q_data->bytesperline[i] = plane_fmt->bytesperline; + q_data->sizeimage[i] = plane_fmt->sizeimage; + } + + q_data->c_rect.left = 0; + q_data->c_rect.top = 0; + q_data->c_rect.width = q_data->width; + q_data->c_rect.height = q_data->height; + + if (q_data->field == V4L2_FIELD_ALTERNATE) + q_data->flags |= Q_DATA_INTERLACED; + else + q_data->flags &= ~Q_DATA_INTERLACED; + + vpe_dbg(ctx->dev, "Setting format for type %d, wxh: %dx%d, fmt: %d bpl_y %d", + f->type, q_data->width, q_data->height, q_data->fmt->fourcc, + q_data->bytesperline[VPE_LUMA]); + if (q_data->fmt->coplanar) + vpe_dbg(ctx->dev, " bpl_uv %d\n", + q_data->bytesperline[VPE_CHROMA]); + + return 0; +} + +static int vpe_s_fmt(struct file *file, void *priv, struct v4l2_format *f) +{ + int ret; + struct vpe_ctx *ctx = file2ctx(file); + + ret = vpe_try_fmt(file, priv, f); + if (ret) + return ret; + + ret = __vpe_s_fmt(ctx, f); + if (ret) + return ret; + + if (V4L2_TYPE_IS_OUTPUT(f->type)) + set_src_registers(ctx); + else + set_dst_registers(ctx); + + return set_srcdst_params(ctx); +} + +static int vpe_reqbufs(struct file *file, void *priv, + struct v4l2_requestbuffers *reqbufs) +{ + struct vpe_ctx *ctx = file2ctx(file); + + return v4l2_m2m_reqbufs(file, ctx->m2m_ctx, reqbufs); +} + +static int vpe_querybuf(struct file *file, void *priv, struct v4l2_buffer *buf) +{ + struct vpe_ctx *ctx = file2ctx(file); + + return v4l2_m2m_querybuf(file, ctx->m2m_ctx, buf); +} + +static int vpe_qbuf(struct file *file, void *priv, struct v4l2_buffer *buf) +{ + struct vpe_ctx *ctx = file2ctx(file); + + return v4l2_m2m_qbuf(file, ctx->m2m_ctx, buf); +} + +static int vpe_dqbuf(struct file *file, void *priv, struct v4l2_buffer *buf) +{ + struct vpe_ctx *ctx = file2ctx(file); + + return v4l2_m2m_dqbuf(file, ctx->m2m_ctx, buf); +} + +static int vpe_streamon(struct file *file, void *priv, enum v4l2_buf_type type) +{ + struct vpe_ctx *ctx = file2ctx(file); + + return v4l2_m2m_streamon(file, ctx->m2m_ctx, type); +} + +static int vpe_streamoff(struct file *file, void *priv, enum v4l2_buf_type type) +{ + struct vpe_ctx *ctx = file2ctx(file); + + vpe_dump_regs(ctx->dev); + vpdma_dump_regs(ctx->dev->vpdma); + + return v4l2_m2m_streamoff(file, ctx->m2m_ctx, type); +} + +/* + * defines number of buffers/frames a context can process with VPE before + * switching to a different context. default value is 1 buffer per context + */ +#define V4L2_CID_VPE_BUFS_PER_JOB (V4L2_CID_USER_TI_VPE_BASE + 0) + +static int vpe_s_ctrl(struct v4l2_ctrl *ctrl) +{ + struct vpe_ctx *ctx = + container_of(ctrl->handler, struct vpe_ctx, hdl); + + switch (ctrl->id) { + case V4L2_CID_VPE_BUFS_PER_JOB: + ctx->bufs_per_job = ctrl->val; + break; + + default: + vpe_err(ctx->dev, "Invalid control\n"); + return -EINVAL; + } + + return 0; +} + +static const struct v4l2_ctrl_ops vpe_ctrl_ops = { + .s_ctrl = vpe_s_ctrl, +}; + +static const struct v4l2_ioctl_ops vpe_ioctl_ops = { + .vidioc_querycap = vpe_querycap, + + .vidioc_enum_fmt_vid_cap_mplane = vpe_enum_fmt, + .vidioc_g_fmt_vid_cap_mplane = vpe_g_fmt, + .vidioc_try_fmt_vid_cap_mplane = vpe_try_fmt, + .vidioc_s_fmt_vid_cap_mplane = vpe_s_fmt, + + .vidioc_enum_fmt_vid_out_mplane = vpe_enum_fmt, + .vidioc_g_fmt_vid_out_mplane = vpe_g_fmt, + .vidioc_try_fmt_vid_out_mplane = vpe_try_fmt, + .vidioc_s_fmt_vid_out_mplane = vpe_s_fmt, + + .vidioc_reqbufs = vpe_reqbufs, + .vidioc_querybuf = vpe_querybuf, + + .vidioc_qbuf = vpe_qbuf, + .vidioc_dqbuf = vpe_dqbuf, + + .vidioc_streamon = vpe_streamon, + .vidioc_streamoff = vpe_streamoff, + .vidioc_subscribe_event = v4l2_ctrl_subscribe_event, + .vidioc_unsubscribe_event = v4l2_event_unsubscribe, +}; + +/* + * Queue operations + */ +static int vpe_queue_setup(struct vb2_queue *vq, + const struct v4l2_format *fmt, + unsigned int *nbuffers, unsigned int *nplanes, + unsigned int sizes[], void *alloc_ctxs[]) +{ + int i; + struct vpe_ctx *ctx = vb2_get_drv_priv(vq); + struct vpe_q_data *q_data; + + q_data = get_q_data(ctx, vq->type); + + *nplanes = q_data->fmt->coplanar ? 2 : 1; + + for (i = 0; i < *nplanes; i++) { + sizes[i] = q_data->sizeimage[i]; + alloc_ctxs[i] = ctx->dev->alloc_ctx; + } + + vpe_dbg(ctx->dev, "get %d buffer(s) of size %d", *nbuffers, + sizes[VPE_LUMA]); + if (q_data->fmt->coplanar) + vpe_dbg(ctx->dev, " and %d\n", sizes[VPE_CHROMA]); + + return 0; +} + +static int vpe_buf_prepare(struct vb2_buffer *vb) +{ + struct vpe_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue); + struct vpe_q_data *q_data; + int i, num_planes; + + vpe_dbg(ctx->dev, "type: %d\n", vb->vb2_queue->type); + + q_data = get_q_data(ctx, vb->vb2_queue->type); + num_planes = q_data->fmt->coplanar ? 2 : 1; + + for (i = 0; i < num_planes; i++) { + if (vb2_plane_size(vb, i) < q_data->sizeimage[i]) { + vpe_err(ctx->dev, + "data will not fit into plane (%lu < %lu)\n", + vb2_plane_size(vb, i), + (long) q_data->sizeimage[i]); + return -EINVAL; + } + } + + for (i = 0; i < num_planes; i++) + vb2_set_plane_payload(vb, i, q_data->sizeimage[i]); + + return 0; +} + +static void vpe_buf_queue(struct vb2_buffer *vb) +{ + struct vpe_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue); + v4l2_m2m_buf_queue(ctx->m2m_ctx, vb); +} + +static void vpe_wait_prepare(struct vb2_queue *q) +{ + struct vpe_ctx *ctx = vb2_get_drv_priv(q); + vpe_unlock(ctx); +} + +static void vpe_wait_finish(struct vb2_queue *q) +{ + struct vpe_ctx *ctx = vb2_get_drv_priv(q); + vpe_lock(ctx); +} + +static struct vb2_ops vpe_qops = { + .queue_setup = vpe_queue_setup, + .buf_prepare = vpe_buf_prepare, + .buf_queue = vpe_buf_queue, + .wait_prepare = vpe_wait_prepare, + .wait_finish = vpe_wait_finish, +}; + +static int queue_init(void *priv, struct vb2_queue *src_vq, + struct vb2_queue *dst_vq) +{ + struct vpe_ctx *ctx = priv; + int ret; + + memset(src_vq, 0, sizeof(*src_vq)); + src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE; + src_vq->io_modes = VB2_MMAP; + src_vq->drv_priv = ctx; + src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer); + src_vq->ops = &vpe_qops; + src_vq->mem_ops = &vb2_dma_contig_memops; + src_vq->timestamp_type = V4L2_BUF_FLAG_TIMESTAMP_COPY; + + ret = vb2_queue_init(src_vq); + if (ret) + return ret; + + memset(dst_vq, 0, sizeof(*dst_vq)); + dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE; + dst_vq->io_modes = VB2_MMAP; + dst_vq->drv_priv = ctx; + dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer); + dst_vq->ops = &vpe_qops; + dst_vq->mem_ops = &vb2_dma_contig_memops; + dst_vq->timestamp_type = V4L2_BUF_FLAG_TIMESTAMP_COPY; + + return vb2_queue_init(dst_vq); +} + +static const struct v4l2_ctrl_config vpe_bufs_per_job = { + .ops = &vpe_ctrl_ops, + .id = V4L2_CID_VPE_BUFS_PER_JOB, + .name = "Buffers Per Transaction", + .type = V4L2_CTRL_TYPE_INTEGER, + .def = VPE_DEF_BUFS_PER_JOB, + .min = 1, + .max = VIDEO_MAX_FRAME, + .step = 1, +}; + +/* + * File operations + */ +static int vpe_open(struct file *file) +{ + struct vpe_dev *dev = video_drvdata(file); + struct vpe_ctx *ctx = NULL; + struct vpe_q_data *s_q_data; + struct v4l2_ctrl_handler *hdl; + int ret; + + vpe_dbg(dev, "vpe_open\n"); + + if (!dev->vpdma->ready) { + vpe_err(dev, "vpdma firmware not loaded\n"); + return -ENODEV; + } + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->dev = dev; + + if (mutex_lock_interruptible(&dev->dev_mutex)) { + ret = -ERESTARTSYS; + goto free_ctx; + } + + ret = vpdma_create_desc_list(&ctx->desc_list, VPE_DESC_LIST_SIZE, + VPDMA_LIST_TYPE_NORMAL); + if (ret != 0) + goto unlock; + + ret = vpdma_alloc_desc_buf(&ctx->mmr_adb, sizeof(struct vpe_mmr_adb)); + if (ret != 0) + goto free_desc_list; + + init_adb_hdrs(ctx); + + v4l2_fh_init(&ctx->fh, video_devdata(file)); + file->private_data = &ctx->fh; + + hdl = &ctx->hdl; + v4l2_ctrl_handler_init(hdl, 1); + v4l2_ctrl_new_custom(hdl, &vpe_bufs_per_job, NULL); + if (hdl->error) { + ret = hdl->error; + goto exit_fh; + } + ctx->fh.ctrl_handler = hdl; + v4l2_ctrl_handler_setup(hdl); + + s_q_data = &ctx->q_data[Q_DATA_SRC]; + s_q_data->fmt = &vpe_formats[2]; + s_q_data->width = 1920; + s_q_data->height = 1080; + s_q_data->sizeimage[VPE_LUMA] = (s_q_data->width * s_q_data->height * + s_q_data->fmt->vpdma_fmt[VPE_LUMA]->depth) >> 3; + s_q_data->colorspace = V4L2_COLORSPACE_SMPTE240M; + s_q_data->field = V4L2_FIELD_NONE; + s_q_data->c_rect.left = 0; + s_q_data->c_rect.top = 0; + s_q_data->c_rect.width = s_q_data->width; + s_q_data->c_rect.height = s_q_data->height; + s_q_data->flags = 0; + + ctx->q_data[Q_DATA_DST] = *s_q_data; + + set_dei_shadow_registers(ctx); + set_src_registers(ctx); + set_dst_registers(ctx); + ret = set_srcdst_params(ctx); + if (ret) + goto exit_fh; + + ctx->m2m_ctx = v4l2_m2m_ctx_init(dev->m2m_dev, ctx, &queue_init); + + if (IS_ERR(ctx->m2m_ctx)) { + ret = PTR_ERR(ctx->m2m_ctx); + goto exit_fh; + } + + v4l2_fh_add(&ctx->fh); + + /* + * for now, just report the creation of the first instance, we can later + * optimize the driver to enable or disable clocks when the first + * instance is created or the last instance released + */ + if (atomic_inc_return(&dev->num_instances) == 1) + vpe_dbg(dev, "first instance created\n"); + + ctx->bufs_per_job = VPE_DEF_BUFS_PER_JOB; + + ctx->load_mmrs = true; + + vpe_dbg(dev, "created instance %p, m2m_ctx: %p\n", + ctx, ctx->m2m_ctx); + + mutex_unlock(&dev->dev_mutex); + + return 0; +exit_fh: + v4l2_ctrl_handler_free(hdl); + v4l2_fh_exit(&ctx->fh); + vpdma_free_desc_buf(&ctx->mmr_adb); +free_desc_list: + vpdma_free_desc_list(&ctx->desc_list); +unlock: + mutex_unlock(&dev->dev_mutex); +free_ctx: + kfree(ctx); + return ret; +} + +static int vpe_release(struct file *file) +{ + struct vpe_dev *dev = video_drvdata(file); + struct vpe_ctx *ctx = file2ctx(file); + + vpe_dbg(dev, "releasing instance %p\n", ctx); + + mutex_lock(&dev->dev_mutex); + free_vbs(ctx); + free_mv_buffers(ctx); + vpdma_free_desc_list(&ctx->desc_list); + vpdma_free_desc_buf(&ctx->mmr_adb); + + v4l2_fh_del(&ctx->fh); + v4l2_fh_exit(&ctx->fh); + v4l2_ctrl_handler_free(&ctx->hdl); + v4l2_m2m_ctx_release(ctx->m2m_ctx); + + kfree(ctx); + + /* + * for now, just report the release of the last instance, we can later + * optimize the driver to enable or disable clocks when the first + * instance is created or the last instance released + */ + if (atomic_dec_return(&dev->num_instances) == 0) + vpe_dbg(dev, "last instance released\n"); + + mutex_unlock(&dev->dev_mutex); + + return 0; +} + +static unsigned int vpe_poll(struct file *file, + struct poll_table_struct *wait) +{ + struct vpe_ctx *ctx = file2ctx(file); + struct vpe_dev *dev = ctx->dev; + int ret; + + mutex_lock(&dev->dev_mutex); + ret = v4l2_m2m_poll(file, ctx->m2m_ctx, wait); + mutex_unlock(&dev->dev_mutex); + return ret; +} + +static int vpe_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct vpe_ctx *ctx = file2ctx(file); + struct vpe_dev *dev = ctx->dev; + int ret; + + if (mutex_lock_interruptible(&dev->dev_mutex)) + return -ERESTARTSYS; + ret = v4l2_m2m_mmap(file, ctx->m2m_ctx, vma); + mutex_unlock(&dev->dev_mutex); + return ret; +} + +static const struct v4l2_file_operations vpe_fops = { + .owner = THIS_MODULE, + .open = vpe_open, + .release = vpe_release, + .poll = vpe_poll, + .unlocked_ioctl = video_ioctl2, + .mmap = vpe_mmap, +}; + +static struct video_device vpe_videodev = { + .name = VPE_MODULE_NAME, + .fops = &vpe_fops, + .ioctl_ops = &vpe_ioctl_ops, + .minor = -1, + .release = video_device_release, + .vfl_dir = VFL_DIR_M2M, +}; + +static struct v4l2_m2m_ops m2m_ops = { + .device_run = device_run, + .job_ready = job_ready, + .job_abort = job_abort, + .lock = vpe_lock, + .unlock = vpe_unlock, +}; + +static int vpe_runtime_get(struct platform_device *pdev) +{ + int r; + + dev_dbg(&pdev->dev, "vpe_runtime_get\n"); + + r = pm_runtime_get_sync(&pdev->dev); + WARN_ON(r < 0); + return r < 0 ? r : 0; +} + +static void vpe_runtime_put(struct platform_device *pdev) +{ + + int r; + + dev_dbg(&pdev->dev, "vpe_runtime_put\n"); + + r = pm_runtime_put_sync(&pdev->dev); + WARN_ON(r < 0 && r != -ENOSYS); +} + +static int vpe_probe(struct platform_device *pdev) +{ + struct vpe_dev *dev; + struct video_device *vfd; + struct resource *res; + int ret, irq, func; + + dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + spin_lock_init(&dev->lock); + + ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev); + if (ret) + return ret; + + atomic_set(&dev->num_instances, 0); + mutex_init(&dev->dev_mutex); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "vpe_top"); + /* + * HACK: we get resource info from device tree in the form of a list of + * VPE sub blocks, the driver currently uses only the base of vpe_top + * for register access, the driver should be changed later to access + * registers based on the sub block base addresses + */ + dev->base = devm_ioremap(&pdev->dev, res->start, SZ_32K); + if (IS_ERR(dev->base)) { + ret = PTR_ERR(dev->base); + goto v4l2_dev_unreg; + } + + irq = platform_get_irq(pdev, 0); + ret = devm_request_irq(&pdev->dev, irq, vpe_irq, 0, VPE_MODULE_NAME, + dev); + if (ret) + goto v4l2_dev_unreg; + + platform_set_drvdata(pdev, dev); + + dev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev); + if (IS_ERR(dev->alloc_ctx)) { + vpe_err(dev, "Failed to alloc vb2 context\n"); + ret = PTR_ERR(dev->alloc_ctx); + goto v4l2_dev_unreg; + } + + dev->m2m_dev = v4l2_m2m_init(&m2m_ops); + if (IS_ERR(dev->m2m_dev)) { + vpe_err(dev, "Failed to init mem2mem device\n"); + ret = PTR_ERR(dev->m2m_dev); + goto rel_ctx; + } + + pm_runtime_enable(&pdev->dev); + + ret = vpe_runtime_get(pdev); + if (ret) + goto rel_m2m; + + /* Perform clk enable followed by reset */ + vpe_set_clock_enable(dev, 1); + + vpe_top_reset(dev); + + func = read_field_reg(dev, VPE_PID, VPE_PID_FUNC_MASK, + VPE_PID_FUNC_SHIFT); + vpe_dbg(dev, "VPE PID function %x\n", func); + + vpe_top_vpdma_reset(dev); + + dev->vpdma = vpdma_create(pdev); + if (IS_ERR(dev->vpdma)) + goto runtime_put; + + vfd = &dev->vfd; + *vfd = vpe_videodev; + vfd->lock = &dev->dev_mutex; + vfd->v4l2_dev = &dev->v4l2_dev; + + ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0); + if (ret) { + vpe_err(dev, "Failed to register video device\n"); + goto runtime_put; + } + + video_set_drvdata(vfd, dev); + snprintf(vfd->name, sizeof(vfd->name), "%s", vpe_videodev.name); + dev_info(dev->v4l2_dev.dev, "Device registered as /dev/video%d\n", + vfd->num); + + return 0; + +runtime_put: + vpe_runtime_put(pdev); +rel_m2m: + pm_runtime_disable(&pdev->dev); + v4l2_m2m_release(dev->m2m_dev); +rel_ctx: + vb2_dma_contig_cleanup_ctx(dev->alloc_ctx); +v4l2_dev_unreg: + v4l2_device_unregister(&dev->v4l2_dev); + + return ret; +} + +static int vpe_remove(struct platform_device *pdev) +{ + struct vpe_dev *dev = + (struct vpe_dev *) platform_get_drvdata(pdev); + + v4l2_info(&dev->v4l2_dev, "Removing " VPE_MODULE_NAME); + + v4l2_m2m_release(dev->m2m_dev); + video_unregister_device(&dev->vfd); + v4l2_device_unregister(&dev->v4l2_dev); + vb2_dma_contig_cleanup_ctx(dev->alloc_ctx); + + vpe_set_clock_enable(dev, 0); + vpe_runtime_put(pdev); + pm_runtime_disable(&pdev->dev); + + return 0; +} + +#if defined(CONFIG_OF) +static const struct of_device_id vpe_of_match[] = { + { + .compatible = "ti,vpe", + }, + {}, +}; +#else +#define vpe_of_match NULL +#endif + +static struct platform_driver vpe_pdrv = { + .probe = vpe_probe, + .remove = vpe_remove, + .driver = { + .name = VPE_MODULE_NAME, + .owner = THIS_MODULE, + .of_match_table = vpe_of_match, + }, +}; + +static void __exit vpe_exit(void) +{ + platform_driver_unregister(&vpe_pdrv); +} + +static int __init vpe_init(void) +{ + return platform_driver_register(&vpe_pdrv); +} + +module_init(vpe_init); +module_exit(vpe_exit); + +MODULE_DESCRIPTION("TI VPE driver"); +MODULE_AUTHOR("Dale Farnsworth, <dale@farnsworth.org>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/media/platform/ti-vpe/vpe_regs.h b/drivers/media/platform/ti-vpe/vpe_regs.h new file mode 100644 index 000000000000..ed214e828398 --- /dev/null +++ b/drivers/media/platform/ti-vpe/vpe_regs.h @@ -0,0 +1,496 @@ +/* + * Copyright (c) 2013 Texas Instruments Inc. + * + * David Griego, <dagriego@biglakesoftware.com> + * Dale Farnsworth, <dale@farnsworth.org> + * Archit Taneja, <archit@ti.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#ifndef __TI_VPE_REGS_H +#define __TI_VPE_REGS_H + +/* VPE register offsets and field selectors */ + +/* VPE top level regs */ +#define VPE_PID 0x0000 +#define VPE_PID_MINOR_MASK 0x3f +#define VPE_PID_MINOR_SHIFT 0 +#define VPE_PID_CUSTOM_MASK 0x03 +#define VPE_PID_CUSTOM_SHIFT 6 +#define VPE_PID_MAJOR_MASK 0x07 +#define VPE_PID_MAJOR_SHIFT 8 +#define VPE_PID_RTL_MASK 0x1f +#define VPE_PID_RTL_SHIFT 11 +#define VPE_PID_FUNC_MASK 0xfff +#define VPE_PID_FUNC_SHIFT 16 +#define VPE_PID_SCHEME_MASK 0x03 +#define VPE_PID_SCHEME_SHIFT 30 + +#define VPE_SYSCONFIG 0x0010 +#define VPE_SYSCONFIG_IDLE_MASK 0x03 +#define VPE_SYSCONFIG_IDLE_SHIFT 2 +#define VPE_SYSCONFIG_STANDBY_MASK 0x03 +#define VPE_SYSCONFIG_STANDBY_SHIFT 4 +#define VPE_FORCE_IDLE_MODE 0 +#define VPE_NO_IDLE_MODE 1 +#define VPE_SMART_IDLE_MODE 2 +#define VPE_SMART_IDLE_WAKEUP_MODE 3 +#define VPE_FORCE_STANDBY_MODE 0 +#define VPE_NO_STANDBY_MODE 1 +#define VPE_SMART_STANDBY_MODE 2 +#define VPE_SMART_STANDBY_WAKEUP_MODE 3 + +#define VPE_INT0_STATUS0_RAW_SET 0x0020 +#define VPE_INT0_STATUS0_RAW VPE_INT0_STATUS0_RAW_SET +#define VPE_INT0_STATUS0_CLR 0x0028 +#define VPE_INT0_STATUS0 VPE_INT0_STATUS0_CLR +#define VPE_INT0_ENABLE0_SET 0x0030 +#define VPE_INT0_ENABLE0 VPE_INT0_ENABLE0_SET +#define VPE_INT0_ENABLE0_CLR 0x0038 +#define VPE_INT0_LIST0_COMPLETE (1 << 0) +#define VPE_INT0_LIST0_NOTIFY (1 << 1) +#define VPE_INT0_LIST1_COMPLETE (1 << 2) +#define VPE_INT0_LIST1_NOTIFY (1 << 3) +#define VPE_INT0_LIST2_COMPLETE (1 << 4) +#define VPE_INT0_LIST2_NOTIFY (1 << 5) +#define VPE_INT0_LIST3_COMPLETE (1 << 6) +#define VPE_INT0_LIST3_NOTIFY (1 << 7) +#define VPE_INT0_LIST4_COMPLETE (1 << 8) +#define VPE_INT0_LIST4_NOTIFY (1 << 9) +#define VPE_INT0_LIST5_COMPLETE (1 << 10) +#define VPE_INT0_LIST5_NOTIFY (1 << 11) +#define VPE_INT0_LIST6_COMPLETE (1 << 12) +#define VPE_INT0_LIST6_NOTIFY (1 << 13) +#define VPE_INT0_LIST7_COMPLETE (1 << 14) +#define VPE_INT0_LIST7_NOTIFY (1 << 15) +#define VPE_INT0_DESCRIPTOR (1 << 16) +#define VPE_DEI_FMD_INT (1 << 18) + +#define VPE_INT0_STATUS1_RAW_SET 0x0024 +#define VPE_INT0_STATUS1_RAW VPE_INT0_STATUS1_RAW_SET +#define VPE_INT0_STATUS1_CLR 0x002c +#define VPE_INT0_STATUS1 VPE_INT0_STATUS1_CLR +#define VPE_INT0_ENABLE1_SET 0x0034 +#define VPE_INT0_ENABLE1 VPE_INT0_ENABLE1_SET +#define VPE_INT0_ENABLE1_CLR 0x003c +#define VPE_INT0_CHANNEL_GROUP0 (1 << 0) +#define VPE_INT0_CHANNEL_GROUP1 (1 << 1) +#define VPE_INT0_CHANNEL_GROUP2 (1 << 2) +#define VPE_INT0_CHANNEL_GROUP3 (1 << 3) +#define VPE_INT0_CHANNEL_GROUP4 (1 << 4) +#define VPE_INT0_CHANNEL_GROUP5 (1 << 5) +#define VPE_INT0_CLIENT (1 << 7) +#define VPE_DEI_ERROR_INT (1 << 16) +#define VPE_DS1_UV_ERROR_INT (1 << 22) + +#define VPE_INTC_EOI 0x00a0 + +#define VPE_CLK_ENABLE 0x0100 +#define VPE_VPEDMA_CLK_ENABLE (1 << 0) +#define VPE_DATA_PATH_CLK_ENABLE (1 << 1) + +#define VPE_CLK_RESET 0x0104 +#define VPE_VPDMA_CLK_RESET_MASK 0x1 +#define VPE_VPDMA_CLK_RESET_SHIFT 0 +#define VPE_DATA_PATH_CLK_RESET_MASK 0x1 +#define VPE_DATA_PATH_CLK_RESET_SHIFT 1 +#define VPE_MAIN_RESET_MASK 0x1 +#define VPE_MAIN_RESET_SHIFT 31 + +#define VPE_CLK_FORMAT_SELECT 0x010c +#define VPE_CSC_SRC_SELECT_MASK 0x03 +#define VPE_CSC_SRC_SELECT_SHIFT 0 +#define VPE_RGB_OUT_SELECT (1 << 8) +#define VPE_DS_SRC_SELECT_MASK 0x07 +#define VPE_DS_SRC_SELECT_SHIFT 9 +#define VPE_DS_BYPASS (1 << 16) +#define VPE_COLOR_SEPARATE_422 (1 << 18) + +#define VPE_DS_SRC_DEI_SCALER (5 << VPE_DS_SRC_SELECT_SHIFT) +#define VPE_CSC_SRC_DEI_SCALER (3 << VPE_CSC_SRC_SELECT_SHIFT) + +#define VPE_CLK_RANGE_MAP 0x011c +#define VPE_RANGE_RANGE_MAP_Y_MASK 0x07 +#define VPE_RANGE_RANGE_MAP_Y_SHIFT 0 +#define VPE_RANGE_RANGE_MAP_UV_MASK 0x07 +#define VPE_RANGE_RANGE_MAP_UV_SHIFT 3 +#define VPE_RANGE_MAP_ON (1 << 6) +#define VPE_RANGE_REDUCTION_ON (1 << 28) + +/* VPE chrominance upsampler regs */ +#define VPE_US1_R0 0x0304 +#define VPE_US2_R0 0x0404 +#define VPE_US3_R0 0x0504 +#define VPE_US_C1_MASK 0x3fff +#define VPE_US_C1_SHIFT 2 +#define VPE_US_C0_MASK 0x3fff +#define VPE_US_C0_SHIFT 18 +#define VPE_US_MODE_MASK 0x03 +#define VPE_US_MODE_SHIFT 16 +#define VPE_ANCHOR_FID0_C1_MASK 0x3fff +#define VPE_ANCHOR_FID0_C1_SHIFT 2 +#define VPE_ANCHOR_FID0_C0_MASK 0x3fff +#define VPE_ANCHOR_FID0_C0_SHIFT 18 + +#define VPE_US1_R1 0x0308 +#define VPE_US2_R1 0x0408 +#define VPE_US3_R1 0x0508 +#define VPE_ANCHOR_FID0_C3_MASK 0x3fff +#define VPE_ANCHOR_FID0_C3_SHIFT 2 +#define VPE_ANCHOR_FID0_C2_MASK 0x3fff +#define VPE_ANCHOR_FID0_C2_SHIFT 18 + +#define VPE_US1_R2 0x030c +#define VPE_US2_R2 0x040c +#define VPE_US3_R2 0x050c +#define VPE_INTERP_FID0_C1_MASK 0x3fff +#define VPE_INTERP_FID0_C1_SHIFT 2 +#define VPE_INTERP_FID0_C0_MASK 0x3fff +#define VPE_INTERP_FID0_C0_SHIFT 18 + +#define VPE_US1_R3 0x0310 +#define VPE_US2_R3 0x0410 +#define VPE_US3_R3 0x0510 +#define VPE_INTERP_FID0_C3_MASK 0x3fff +#define VPE_INTERP_FID0_C3_SHIFT 2 +#define VPE_INTERP_FID0_C2_MASK 0x3fff +#define VPE_INTERP_FID0_C2_SHIFT 18 + +#define VPE_US1_R4 0x0314 +#define VPE_US2_R4 0x0414 +#define VPE_US3_R4 0x0514 +#define VPE_ANCHOR_FID1_C1_MASK 0x3fff +#define VPE_ANCHOR_FID1_C1_SHIFT 2 +#define VPE_ANCHOR_FID1_C0_MASK 0x3fff +#define VPE_ANCHOR_FID1_C0_SHIFT 18 + +#define VPE_US1_R5 0x0318 +#define VPE_US2_R5 0x0418 +#define VPE_US3_R5 0x0518 +#define VPE_ANCHOR_FID1_C3_MASK 0x3fff +#define VPE_ANCHOR_FID1_C3_SHIFT 2 +#define VPE_ANCHOR_FID1_C2_MASK 0x3fff +#define VPE_ANCHOR_FID1_C2_SHIFT 18 + +#define VPE_US1_R6 0x031c +#define VPE_US2_R6 0x041c +#define VPE_US3_R6 0x051c +#define VPE_INTERP_FID1_C1_MASK 0x3fff +#define VPE_INTERP_FID1_C1_SHIFT 2 +#define VPE_INTERP_FID1_C0_MASK 0x3fff +#define VPE_INTERP_FID1_C0_SHIFT 18 + +#define VPE_US1_R7 0x0320 +#define VPE_US2_R7 0x0420 +#define VPE_US3_R7 0x0520 +#define VPE_INTERP_FID0_C3_MASK 0x3fff +#define VPE_INTERP_FID0_C3_SHIFT 2 +#define VPE_INTERP_FID0_C2_MASK 0x3fff +#define VPE_INTERP_FID0_C2_SHIFT 18 + +/* VPE de-interlacer regs */ +#define VPE_DEI_FRAME_SIZE 0x0600 +#define VPE_DEI_WIDTH_MASK 0x07ff +#define VPE_DEI_WIDTH_SHIFT 0 +#define VPE_DEI_HEIGHT_MASK 0x07ff +#define VPE_DEI_HEIGHT_SHIFT 16 +#define VPE_DEI_INTERLACE_BYPASS (1 << 29) +#define VPE_DEI_FIELD_FLUSH (1 << 30) +#define VPE_DEI_PROGRESSIVE (1 << 31) + +#define VPE_MDT_BYPASS 0x0604 +#define VPE_MDT_TEMPMAX_BYPASS (1 << 0) +#define VPE_MDT_SPATMAX_BYPASS (1 << 1) + +#define VPE_MDT_SF_THRESHOLD 0x0608 +#define VPE_MDT_SF_SC_THR1_MASK 0xff +#define VPE_MDT_SF_SC_THR1_SHIFT 0 +#define VPE_MDT_SF_SC_THR2_MASK 0xff +#define VPE_MDT_SF_SC_THR2_SHIFT 0 +#define VPE_MDT_SF_SC_THR3_MASK 0xff +#define VPE_MDT_SF_SC_THR3_SHIFT 0 + +#define VPE_EDI_CONFIG 0x060c +#define VPE_EDI_INP_MODE_MASK 0x03 +#define VPE_EDI_INP_MODE_SHIFT 0 +#define VPE_EDI_ENABLE_3D (1 << 2) +#define VPE_EDI_ENABLE_CHROMA_3D (1 << 3) +#define VPE_EDI_CHROMA3D_COR_THR_MASK 0xff +#define VPE_EDI_CHROMA3D_COR_THR_SHIFT 8 +#define VPE_EDI_DIR_COR_LOWER_THR_MASK 0xff +#define VPE_EDI_DIR_COR_LOWER_THR_SHIFT 16 +#define VPE_EDI_COR_SCALE_FACTOR_MASK 0xff +#define VPE_EDI_COR_SCALE_FACTOR_SHIFT 23 + +#define VPE_DEI_EDI_LUT_R0 0x0610 +#define VPE_EDI_LUT0_MASK 0x1f +#define VPE_EDI_LUT0_SHIFT 0 +#define VPE_EDI_LUT1_MASK 0x1f +#define VPE_EDI_LUT1_SHIFT 8 +#define VPE_EDI_LUT2_MASK 0x1f +#define VPE_EDI_LUT2_SHIFT 16 +#define VPE_EDI_LUT3_MASK 0x1f +#define VPE_EDI_LUT3_SHIFT 24 + +#define VPE_DEI_EDI_LUT_R1 0x0614 +#define VPE_EDI_LUT0_MASK 0x1f +#define VPE_EDI_LUT0_SHIFT 0 +#define VPE_EDI_LUT1_MASK 0x1f +#define VPE_EDI_LUT1_SHIFT 8 +#define VPE_EDI_LUT2_MASK 0x1f +#define VPE_EDI_LUT2_SHIFT 16 +#define VPE_EDI_LUT3_MASK 0x1f +#define VPE_EDI_LUT3_SHIFT 24 + +#define VPE_DEI_EDI_LUT_R2 0x0618 +#define VPE_EDI_LUT4_MASK 0x1f +#define VPE_EDI_LUT4_SHIFT 0 +#define VPE_EDI_LUT5_MASK 0x1f +#define VPE_EDI_LUT5_SHIFT 8 +#define VPE_EDI_LUT6_MASK 0x1f +#define VPE_EDI_LUT6_SHIFT 16 +#define VPE_EDI_LUT7_MASK 0x1f +#define VPE_EDI_LUT7_SHIFT 24 + +#define VPE_DEI_EDI_LUT_R3 0x061c +#define VPE_EDI_LUT8_MASK 0x1f +#define VPE_EDI_LUT8_SHIFT 0 +#define VPE_EDI_LUT9_MASK 0x1f +#define VPE_EDI_LUT9_SHIFT 8 +#define VPE_EDI_LUT10_MASK 0x1f +#define VPE_EDI_LUT10_SHIFT 16 +#define VPE_EDI_LUT11_MASK 0x1f +#define VPE_EDI_LUT11_SHIFT 24 + +#define VPE_DEI_FMD_WINDOW_R0 0x0620 +#define VPE_FMD_WINDOW_MINX_MASK 0x07ff +#define VPE_FMD_WINDOW_MINX_SHIFT 0 +#define VPE_FMD_WINDOW_MAXX_MASK 0x07ff +#define VPE_FMD_WINDOW_MAXX_SHIFT 16 +#define VPE_FMD_WINDOW_ENABLE (1 << 31) + +#define VPE_DEI_FMD_WINDOW_R1 0x0624 +#define VPE_FMD_WINDOW_MINY_MASK 0x07ff +#define VPE_FMD_WINDOW_MINY_SHIFT 0 +#define VPE_FMD_WINDOW_MAXY_MASK 0x07ff +#define VPE_FMD_WINDOW_MAXY_SHIFT 16 + +#define VPE_DEI_FMD_CONTROL_R0 0x0628 +#define VPE_FMD_ENABLE (1 << 0) +#define VPE_FMD_LOCK (1 << 1) +#define VPE_FMD_JAM_DIR (1 << 2) +#define VPE_FMD_BED_ENABLE (1 << 3) +#define VPE_FMD_CAF_FIELD_THR_MASK 0xff +#define VPE_FMD_CAF_FIELD_THR_SHIFT 16 +#define VPE_FMD_CAF_LINE_THR_MASK 0xff +#define VPE_FMD_CAF_LINE_THR_SHIFT 24 + +#define VPE_DEI_FMD_CONTROL_R1 0x062c +#define VPE_FMD_CAF_THR_MASK 0x000fffff +#define VPE_FMD_CAF_THR_SHIFT 0 + +#define VPE_DEI_FMD_STATUS_R0 0x0630 +#define VPE_FMD_CAF_MASK 0x000fffff +#define VPE_FMD_CAF_SHIFT 0 +#define VPE_FMD_RESET (1 << 24) + +#define VPE_DEI_FMD_STATUS_R1 0x0634 +#define VPE_FMD_FIELD_DIFF_MASK 0x0fffffff +#define VPE_FMD_FIELD_DIFF_SHIFT 0 + +#define VPE_DEI_FMD_STATUS_R2 0x0638 +#define VPE_FMD_FRAME_DIFF_MASK 0x000fffff +#define VPE_FMD_FRAME_DIFF_SHIFT 0 + +/* VPE scaler regs */ +#define VPE_SC_MP_SC0 0x0700 +#define VPE_INTERLACE_O (1 << 0) +#define VPE_LINEAR (1 << 1) +#define VPE_SC_BYPASS (1 << 2) +#define VPE_INVT_FID (1 << 3) +#define VPE_USE_RAV (1 << 4) +#define VPE_ENABLE_EV (1 << 5) +#define VPE_AUTO_HS (1 << 6) +#define VPE_DCM_2X (1 << 7) +#define VPE_DCM_4X (1 << 8) +#define VPE_HP_BYPASS (1 << 9) +#define VPE_INTERLACE_I (1 << 10) +#define VPE_ENABLE_SIN2_VER_INTP (1 << 11) +#define VPE_Y_PK_EN (1 << 14) +#define VPE_TRIM (1 << 15) +#define VPE_SELFGEN_FID (1 << 16) + +#define VPE_SC_MP_SC1 0x0704 +#define VPE_ROW_ACC_INC_MASK 0x07ffffff +#define VPE_ROW_ACC_INC_SHIFT 0 + +#define VPE_SC_MP_SC2 0x0708 +#define VPE_ROW_ACC_OFFSET_MASK 0x0fffffff +#define VPE_ROW_ACC_OFFSET_SHIFT 0 + +#define VPE_SC_MP_SC3 0x070c +#define VPE_ROW_ACC_OFFSET_B_MASK 0x0fffffff +#define VPE_ROW_ACC_OFFSET_B_SHIFT 0 + +#define VPE_SC_MP_SC4 0x0710 +#define VPE_TAR_H_MASK 0x07ff +#define VPE_TAR_H_SHIFT 0 +#define VPE_TAR_W_MASK 0x07ff +#define VPE_TAR_W_SHIFT 12 +#define VPE_LIN_ACC_INC_U_MASK 0x07 +#define VPE_LIN_ACC_INC_U_SHIFT 24 +#define VPE_NLIN_ACC_INIT_U_MASK 0x07 +#define VPE_NLIN_ACC_INIT_U_SHIFT 28 + +#define VPE_SC_MP_SC5 0x0714 +#define VPE_SRC_H_MASK 0x07ff +#define VPE_SRC_H_SHIFT 0 +#define VPE_SRC_W_MASK 0x07ff +#define VPE_SRC_W_SHIFT 12 +#define VPE_NLIN_ACC_INC_U_MASK 0x07 +#define VPE_NLIN_ACC_INC_U_SHIFT 24 + +#define VPE_SC_MP_SC6 0x0718 +#define VPE_ROW_ACC_INIT_RAV_MASK 0x03ff +#define VPE_ROW_ACC_INIT_RAV_SHIFT 0 +#define VPE_ROW_ACC_INIT_RAV_B_MASK 0x03ff +#define VPE_ROW_ACC_INIT_RAV_B_SHIFT 10 + +#define VPE_SC_MP_SC8 0x0720 +#define VPE_NLIN_LEFT_MASK 0x07ff +#define VPE_NLIN_LEFT_SHIFT 0 +#define VPE_NLIN_RIGHT_MASK 0x07ff +#define VPE_NLIN_RIGHT_SHIFT 12 + +#define VPE_SC_MP_SC9 0x0724 +#define VPE_LIN_ACC_INC VPE_SC_MP_SC9 + +#define VPE_SC_MP_SC10 0x0728 +#define VPE_NLIN_ACC_INIT VPE_SC_MP_SC10 + +#define VPE_SC_MP_SC11 0x072c +#define VPE_NLIN_ACC_INC VPE_SC_MP_SC11 + +#define VPE_SC_MP_SC12 0x0730 +#define VPE_COL_ACC_OFFSET_MASK 0x01ffffff +#define VPE_COL_ACC_OFFSET_SHIFT 0 + +#define VPE_SC_MP_SC13 0x0734 +#define VPE_SC_FACTOR_RAV_MASK 0x03ff +#define VPE_SC_FACTOR_RAV_SHIFT 0 +#define VPE_CHROMA_INTP_THR_MASK 0x03ff +#define VPE_CHROMA_INTP_THR_SHIFT 12 +#define VPE_DELTA_CHROMA_THR_MASK 0x0f +#define VPE_DELTA_CHROMA_THR_SHIFT 24 + +#define VPE_SC_MP_SC17 0x0744 +#define VPE_EV_THR_MASK 0x03ff +#define VPE_EV_THR_SHIFT 12 +#define VPE_DELTA_LUMA_THR_MASK 0x0f +#define VPE_DELTA_LUMA_THR_SHIFT 24 +#define VPE_DELTA_EV_THR_MASK 0x0f +#define VPE_DELTA_EV_THR_SHIFT 28 + +#define VPE_SC_MP_SC18 0x0748 +#define VPE_HS_FACTOR_MASK 0x03ff +#define VPE_HS_FACTOR_SHIFT 0 +#define VPE_CONF_DEFAULT_MASK 0x01ff +#define VPE_CONF_DEFAULT_SHIFT 16 + +#define VPE_SC_MP_SC19 0x074c +#define VPE_HPF_COEFF0_MASK 0xff +#define VPE_HPF_COEFF0_SHIFT 0 +#define VPE_HPF_COEFF1_MASK 0xff +#define VPE_HPF_COEFF1_SHIFT 8 +#define VPE_HPF_COEFF2_MASK 0xff +#define VPE_HPF_COEFF2_SHIFT 16 +#define VPE_HPF_COEFF3_MASK 0xff +#define VPE_HPF_COEFF3_SHIFT 23 + +#define VPE_SC_MP_SC20 0x0750 +#define VPE_HPF_COEFF4_MASK 0xff +#define VPE_HPF_COEFF4_SHIFT 0 +#define VPE_HPF_COEFF5_MASK 0xff +#define VPE_HPF_COEFF5_SHIFT 8 +#define VPE_HPF_NORM_SHIFT_MASK 0x07 +#define VPE_HPF_NORM_SHIFT_SHIFT 16 +#define VPE_NL_LIMIT_MASK 0x1ff +#define VPE_NL_LIMIT_SHIFT 20 + +#define VPE_SC_MP_SC21 0x0754 +#define VPE_NL_LO_THR_MASK 0x01ff +#define VPE_NL_LO_THR_SHIFT 0 +#define VPE_NL_LO_SLOPE_MASK 0xff +#define VPE_NL_LO_SLOPE_SHIFT 16 + +#define VPE_SC_MP_SC22 0x0758 +#define VPE_NL_HI_THR_MASK 0x01ff +#define VPE_NL_HI_THR_SHIFT 0 +#define VPE_NL_HI_SLOPE_SH_MASK 0x07 +#define VPE_NL_HI_SLOPE_SH_SHIFT 16 + +#define VPE_SC_MP_SC23 0x075c +#define VPE_GRADIENT_THR_MASK 0x07ff +#define VPE_GRADIENT_THR_SHIFT 0 +#define VPE_GRADIENT_THR_RANGE_MASK 0x0f +#define VPE_GRADIENT_THR_RANGE_SHIFT 12 +#define VPE_MIN_GY_THR_MASK 0xff +#define VPE_MIN_GY_THR_SHIFT 16 +#define VPE_MIN_GY_THR_RANGE_MASK 0x0f +#define VPE_MIN_GY_THR_RANGE_SHIFT 28 + +#define VPE_SC_MP_SC24 0x0760 +#define VPE_ORG_H_MASK 0x07ff +#define VPE_ORG_H_SHIFT 0 +#define VPE_ORG_W_MASK 0x07ff +#define VPE_ORG_W_SHIFT 16 + +#define VPE_SC_MP_SC25 0x0764 +#define VPE_OFF_H_MASK 0x07ff +#define VPE_OFF_H_SHIFT 0 +#define VPE_OFF_W_MASK 0x07ff +#define VPE_OFF_W_SHIFT 16 + +/* VPE color space converter regs */ +#define VPE_CSC_CSC00 0x5700 +#define VPE_CSC_A0_MASK 0x1fff +#define VPE_CSC_A0_SHIFT 0 +#define VPE_CSC_B0_MASK 0x1fff +#define VPE_CSC_B0_SHIFT 16 + +#define VPE_CSC_CSC01 0x5704 +#define VPE_CSC_C0_MASK 0x1fff +#define VPE_CSC_C0_SHIFT 0 +#define VPE_CSC_A1_MASK 0x1fff +#define VPE_CSC_A1_SHIFT 16 + +#define VPE_CSC_CSC02 0x5708 +#define VPE_CSC_B1_MASK 0x1fff +#define VPE_CSC_B1_SHIFT 0 +#define VPE_CSC_C1_MASK 0x1fff +#define VPE_CSC_C1_SHIFT 16 + +#define VPE_CSC_CSC03 0x570c +#define VPE_CSC_A2_MASK 0x1fff +#define VPE_CSC_A2_SHIFT 0 +#define VPE_CSC_B2_MASK 0x1fff +#define VPE_CSC_B2_SHIFT 16 + +#define VPE_CSC_CSC04 0x5710 +#define VPE_CSC_C2_MASK 0x1fff +#define VPE_CSC_C2_SHIFT 0 +#define VPE_CSC_D0_MASK 0x0fff +#define VPE_CSC_D0_SHIFT 16 + +#define VPE_CSC_CSC05 0x5714 +#define VPE_CSC_D1_MASK 0x0fff +#define VPE_CSC_D1_SHIFT 0 +#define VPE_CSC_D2_MASK 0x0fff +#define VPE_CSC_D2_SHIFT 16 +#define VPE_CSC_BYPASS (1 << 28) + +#endif |