1 files changed, 440 insertions, 151 deletions

diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c
index 4e58069e24f..972f43f6920 100644
--- a/drivers/media/platform/ti-vpe/vpe.c
+++ b/drivers/media/platform/ti-vpe/vpe.c
@@ -30,6 +30,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/videodev2.h>
+#include <linux/log2.h>
 
 #include <media/v4l2-common.h>
 #include <media/v4l2-ctrls.h>
@@ -42,22 +43,20 @@
 
 #include "vpdma.h"
 #include "vpe_regs.h"
+#include "sc.h"
+#include "csc.h"
 
 #define VPE_MODULE_NAME "vpe"
 
 /* minimum and maximum frame sizes */
-#define MIN_W		128
-#define MIN_H		128
+#define MIN_W		32
+#define MIN_H		32
 #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)
@@ -268,6 +267,38 @@ static struct vpe_fmt vpe_formats[] = {
 		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_CY422],
 				  },
 	},
+	{
+		.name		= "RGB888 packed",
+		.fourcc		= V4L2_PIX_FMT_RGB24,
+		.types		= VPE_FMT_TYPE_CAPTURE,
+		.coplanar	= 0,
+		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_RGB24],
+				  },
+	},
+	{
+		.name		= "ARGB32",
+		.fourcc		= V4L2_PIX_FMT_RGB32,
+		.types		= VPE_FMT_TYPE_CAPTURE,
+		.coplanar	= 0,
+		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_ARGB32],
+				  },
+	},
+	{
+		.name		= "BGR888 packed",
+		.fourcc		= V4L2_PIX_FMT_BGR24,
+		.types		= VPE_FMT_TYPE_CAPTURE,
+		.coplanar	= 0,
+		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_BGR24],
+				  },
+	},
+	{
+		.name		= "ABGR32",
+		.fourcc		= V4L2_PIX_FMT_BGR32,
+		.types		= VPE_FMT_TYPE_CAPTURE,
+		.coplanar	= 0,
+		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_ABGR32],
+				  },
+	},
 };
 
 /*
@@ -327,9 +358,12 @@ struct vpe_dev {
 
 	int			irq;
 	void __iomem		*base;
+	struct resource		*res;
 
 	struct vb2_alloc_ctx	*alloc_ctx;
 	struct vpdma_data	*vpdma;		/* vpdma data handle */
+	struct sc_data		*sc;		/* scaler data handle */
+	struct csc_data		*csc;		/* csc data handle */
 };
 
 /*
@@ -356,6 +390,8 @@ struct vpe_ctx {
 	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_buf	sc_coeff_h;		/* h coeff buffer */
+	struct vpdma_buf	sc_coeff_v;		/* v coeff buffer */
 	struct vpdma_desc_list	desc_list;		/* DMA descriptor list */
 
 	bool			deinterlacing;		/* using de-interlacer */
@@ -374,8 +410,10 @@ static struct vpe_q_data *get_q_data(struct vpe_ctx *ctx,
 {
 	switch (type) {
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
 		return &ctx->q_data[Q_DATA_SRC];
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
 		return &ctx->q_data[Q_DATA_DST];
 	default:
 		BUG();
@@ -438,14 +476,23 @@ struct vpe_mmr_adb {
 	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	sc_hdr0;
+	u32			sc_regs0[7];
+	u32			sc_pad0[1];
+	struct vpdma_adb_hdr	sc_hdr8;
+	u32			sc_regs8[6];
+	u32			sc_pad8[2];
+	struct vpdma_adb_hdr	sc_hdr17;
+	u32			sc_regs17[9];
+	u32			sc_pad17[3];
 	struct vpdma_adb_hdr	csc_hdr;
 	u32			csc_regs[6];
 	u32			csc_pad[2];
 };
 
+#define GET_OFFSET_TOP(ctx, obj, reg)	\
+	((obj)->res->start - ctx->dev->res->start + reg)
+
 #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)
 /*
@@ -458,8 +505,14 @@ static void init_adb_hdrs(struct vpe_ctx *ctx)
 	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);
+	VPE_SET_MMR_ADB_HDR(ctx, sc_hdr0, sc_regs0,
+		GET_OFFSET_TOP(ctx, ctx->dev->sc, CFG_SC0));
+	VPE_SET_MMR_ADB_HDR(ctx, sc_hdr8, sc_regs8,
+		GET_OFFSET_TOP(ctx, ctx->dev->sc, CFG_SC8));
+	VPE_SET_MMR_ADB_HDR(ctx, sc_hdr17, sc_regs17,
+		GET_OFFSET_TOP(ctx, ctx->dev->sc, CFG_SC17));
+	VPE_SET_MMR_ADB_HDR(ctx, csc_hdr, csc_regs,
+		GET_OFFSET_TOP(ctx, ctx->dev->csc, CSC_CSC00));
 };
 
 /*
@@ -670,17 +723,20 @@ static void set_src_registers(struct vpe_ctx *ctx)
 static void set_dst_registers(struct vpe_ctx *ctx)
 {
 	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	enum v4l2_colorspace clrspc = ctx->q_data[Q_DATA_DST].colorspace;
 	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;
+	if (clrspc == V4L2_COLORSPACE_SRGB)
+		val |= VPE_RGB_OUT_SELECT;
 	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;
+	/*
+	 * the source of CHR_DS and CSC is always the scaler, irrespective of
+	 * whether it's used or not
+	 */
+	val |= VPE_DS_SRC_DEI_SCALER | VPE_CSC_SRC_DEI_SCALER;
 
 	if (fmt->fourcc != V4L2_PIX_FMT_NV12)
 		val |= VPE_DS_BYPASS;
@@ -742,28 +798,6 @@ static void set_dei_shadow_registers(struct vpe_ctx *ctx)
 	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.
@@ -772,6 +806,11 @@ 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];
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	unsigned int src_w = s_q_data->c_rect.width;
+	unsigned int src_h = s_q_data->c_rect.height;
+	unsigned int dst_w = d_q_data->c_rect.width;
+	unsigned int dst_h = d_q_data->c_rect.height;
 	size_t mv_buf_size;
 	int ret;
 
@@ -780,12 +819,23 @@ static int set_srcdst_params(struct vpe_ctx *ctx)
 
 	if ((s_q_data->flags & Q_DATA_INTERLACED) &&
 			!(d_q_data->flags & Q_DATA_INTERLACED)) {
+		int bytes_per_line;
 		const struct vpdma_data_format *mv =
 			&vpdma_misc_fmts[VPDMA_DATA_FMT_MV];
 
+		/*
+		 * we make sure that the source image has a 16 byte aligned
+		 * stride, we need to do the same for the motion vector buffer
+		 * by aligning it's stride to the next 16 byte boundry. this
+		 * extra space will not be used by the de-interlacer, but will
+		 * ensure that vpdma operates correctly
+		 */
+		bytes_per_line = ALIGN((s_q_data->width * mv->depth) >> 3,
+					VPDMA_STRIDE_ALIGN);
+		mv_buf_size = bytes_per_line * s_q_data->height;
+
 		ctx->deinterlacing = 1;
-		mv_buf_size =
-			(s_q_data->width * s_q_data->height * mv->depth) >> 3;
+		src_h <<= 1;
 	} else {
 		ctx->deinterlacing = 0;
 		mv_buf_size = 0;
@@ -799,8 +849,16 @@ static int set_srcdst_params(struct vpe_ctx *ctx)
 
 	set_cfg_and_line_modes(ctx);
 	set_dei_regs(ctx);
-	set_csc_coeff_bypass(ctx);
-	set_sc_regs_bypass(ctx);
+
+	csc_set_coeff(ctx->dev->csc, &mmr_adb->csc_regs[0],
+		s_q_data->colorspace, d_q_data->colorspace);
+
+	sc_set_hs_coeffs(ctx->dev->sc, ctx->sc_coeff_h.addr, src_w, dst_w);
+	sc_set_vs_coeffs(ctx->dev->sc, ctx->sc_coeff_v.addr, src_h, dst_h);
+
+	sc_config_scaler(ctx->dev->sc, &mmr_adb->sc_regs0[0],
+		&mmr_adb->sc_regs8[0], &mmr_adb->sc_regs17[0],
+		src_w, src_h, dst_w, dst_h);
 
 	return 0;
 }
@@ -831,6 +889,9 @@ static int job_ready(void *priv)
 	if (v4l2_m2m_num_src_bufs_ready(ctx->m2m_ctx) < needed)
 		return 0;
 
+	if (v4l2_m2m_num_dst_bufs_ready(ctx->m2m_ctx) < needed)
+		return 0;
+
 	return 1;
 }
 
@@ -916,35 +977,10 @@ static void vpe_dump_regs(struct vpe_dev *dev)
 	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
+
+	sc_dump_regs(dev->sc);
+	csc_dump_regs(dev->csc);
 }
 
 static void add_out_dtd(struct vpe_ctx *ctx, int port)
@@ -952,7 +988,6 @@ 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;
@@ -981,8 +1016,8 @@ static void add_out_dtd(struct vpe_ctx *ctx, int port)
 	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);
+	vpdma_add_out_dtd(&ctx->desc_list, q_data->width, &q_data->c_rect,
+		vpdma_fmt, dma_addr, p_data->channel, flags);
 }
 
 static void add_in_dtd(struct vpe_ctx *ctx, int port)
@@ -990,11 +1025,11 @@ 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;
+	int frame_width, frame_height;
 	dma_addr_t dma_addr;
 	u32 flags = 0;
 
@@ -1021,8 +1056,15 @@ static void add_in_dtd(struct vpe_ctx *ctx, int port)
 	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);
+	frame_width = q_data->c_rect.width;
+	frame_height = q_data->c_rect.height;
+
+	if (p_data->vb_part && fmt->fourcc == V4L2_PIX_FMT_NV12)
+		frame_height /= 2;
+
+	vpdma_add_in_dtd(&ctx->desc_list, q_data->width, &q_data->c_rect,
+		vpdma_fmt, dma_addr, p_data->channel, field, flags, frame_width,
+		frame_height, 0, 0);
 }
 
 /*
@@ -1053,6 +1095,7 @@ static void disable_irqs(struct vpe_ctx *ctx)
 static void device_run(void *priv)
 {
 	struct vpe_ctx *ctx = priv;
+	struct sc_data *sc = ctx->dev->sc;
 	struct vpe_q_data *d_q_data = &ctx->q_data[Q_DATA_DST];
 
 	if (ctx->deinterlacing && ctx->src_vbs[2] == NULL) {
@@ -1075,13 +1118,37 @@ static void device_run(void *priv)
 		ctx->load_mmrs = false;
 	}
 
+	if (sc->loaded_coeff_h != ctx->sc_coeff_h.dma_addr ||
+			sc->load_coeff_h) {
+		vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->sc_coeff_h);
+		vpdma_add_cfd_block(&ctx->desc_list, CFD_SC_CLIENT,
+			&ctx->sc_coeff_h, 0);
+
+		sc->loaded_coeff_h = ctx->sc_coeff_h.dma_addr;
+		sc->load_coeff_h = false;
+	}
+
+	if (sc->loaded_coeff_v != ctx->sc_coeff_v.dma_addr ||
+			sc->load_coeff_v) {
+		vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->sc_coeff_v);
+		vpdma_add_cfd_block(&ctx->desc_list, CFD_SC_CLIENT,
+			&ctx->sc_coeff_v, SC_COEF_SRAM_SIZE >> 4);
+
+		sc->loaded_coeff_v = ctx->sc_coeff_v.dma_addr;
+		sc->load_coeff_v = 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);
+	if (d_q_data->colorspace == V4L2_COLORSPACE_SRGB) {
+		add_out_dtd(ctx, VPE_PORT_RGB_OUT);
+	} else {
+		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) {
@@ -1117,9 +1184,16 @@ static void device_run(void *priv)
 	}
 
 	/* 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 (d_q_data->colorspace == V4L2_COLORSPACE_SRGB) {
+		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
+			VPE_CHAN_RGB_OUT);
+	} else {
+		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);
@@ -1198,6 +1272,8 @@ static irqreturn_t vpe_irq(int irq_vpe, void *data)
 
 	vpdma_unmap_desc_buf(dev->vpdma, &ctx->desc_list.buf);
 	vpdma_unmap_desc_buf(dev->vpdma, &ctx->mmr_adb);
+	vpdma_unmap_desc_buf(dev->vpdma, &ctx->sc_coeff_h);
+	vpdma_unmap_desc_buf(dev->vpdma, &ctx->sc_coeff_v);
 
 	vpdma_reset_desc_list(&ctx->desc_list);
 
@@ -1212,16 +1288,17 @@ static irqreturn_t vpe_irq(int irq_vpe, void *data)
 	s_buf = &s_vb->v4l2_buf;
 	d_buf = &d_vb->v4l2_buf;
 
+	d_buf->flags = s_buf->flags;
+
 	d_buf->timestamp = s_buf->timestamp;
-	if (s_buf->flags & V4L2_BUF_FLAG_TIMECODE) {
-		d_buf->flags |= V4L2_BUF_FLAG_TIMECODE;
+	if (s_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) {
+		d_buf->field = ctx->field;
 		if (ctx->field == V4L2_FIELD_BOTTOM) {
 			ctx->sequence++;
 			ctx->field = V4L2_FIELD_TOP;
@@ -1230,6 +1307,7 @@ static irqreturn_t vpe_irq(int irq_vpe, void *data)
 			ctx->field = V4L2_FIELD_BOTTOM;
 		}
 	} else {
+		d_buf->field = V4L2_FIELD_NONE;
 		ctx->sequence++;
 	}
 
@@ -1268,8 +1346,9 @@ static int vpe_querycap(struct file *file, void *priv,
 {
 	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;
+	snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s",
+		VPE_MODULE_NAME);
+	cap->device_caps  = V4L2_CAP_VIDEO_M2M_MPLANE | V4L2_CAP_STREAMING;
 	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
 	return 0;
 }
@@ -1352,7 +1431,8 @@ static int __vpe_try_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;
-	int i;
+	unsigned int w_align;
+	int i, depth, depth_bytes;
 
 	if (!fmt || !(fmt->types & type)) {
 		vpe_err(ctx->dev, "Fourcc format (0x%08x) invalid.\n",
@@ -1363,40 +1443,65 @@ static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f,
 	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,
+	depth = fmt->vpdma_fmt[VPE_LUMA]->depth;
+
+	/*
+	 * the line stride should 16 byte aligned for VPDMA to work, based on
+	 * the bytes per pixel, figure out how much the width should be aligned
+	 * to make sure line stride is 16 byte aligned
+	 */
+	depth_bytes = depth >> 3;
+
+	if (depth_bytes == 3)
+		/*
+		 * if bpp is 3(as in some RGB formats), the pixel width doesn't
+		 * really help in ensuring line stride is 16 byte aligned
+		 */
+		w_align = 4;
+	else
+		/*
+		 * for the remainder bpp(4, 2 and 1), the pixel width alignment
+		 * can ensure a line stride alignment of 16 bytes. For example,
+		 * if bpp is 2, then the line stride can be 16 byte aligned if
+		 * the width is 8 byte aligned
+		 */
+		w_align = order_base_2(VPDMA_DESC_ALIGN / depth_bytes);
+
+	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;
+	if (!pix->colorspace) {
+		if (fmt->fourcc == V4L2_PIX_FMT_RGB24 ||
+				fmt->fourcc == V4L2_PIX_FMT_BGR24 ||
+				fmt->fourcc == V4L2_PIX_FMT_RGB32 ||
+				fmt->fourcc == V4L2_PIX_FMT_BGR32) {
+			pix->colorspace = V4L2_COLORSPACE_SRGB;
+		} else {
+			if (pix->height > 1280)	/* HD */
+				pix->colorspace = V4L2_COLORSPACE_REC709;
+			else			/* SD */
+				pix->colorspace = V4L2_COLORSPACE_SMPTE170M;
+		}
 	}
 
+	memset(pix->reserved, 0, sizeof(pix->reserved));
 	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);
+			plane_fmt->bytesperline = (pix->width * depth) >> 3;
 		else
 			plane_fmt->bytesperline = pix->width;
 
 		plane_fmt->sizeimage =
 				(pix->height * pix->width * depth) >> 3;
+
+		memset(plane_fmt->reserved, 0, sizeof(plane_fmt->reserved));
 	}
 
 	return 0;
@@ -1488,6 +1593,151 @@ static int vpe_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
 	return set_srcdst_params(ctx);
 }
 
+static int __vpe_try_selection(struct vpe_ctx *ctx, struct v4l2_selection *s)
+{
+	struct vpe_q_data *q_data;
+
+	if ((s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) &&
+	    (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT))
+		return -EINVAL;
+
+	q_data = get_q_data(ctx, s->type);
+	if (!q_data)
+		return -EINVAL;
+
+	switch (s->target) {
+	case V4L2_SEL_TGT_COMPOSE:
+		/*
+		 * COMPOSE target is only valid for capture buffer type, return
+		 * error for output buffer type
+		 */
+		if (s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
+			return -EINVAL;
+		break;
+	case V4L2_SEL_TGT_CROP:
+		/*
+		 * CROP target is only valid for output buffer type, return
+		 * error for capture buffer type
+		 */
+		if (s->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
+			return -EINVAL;
+		break;
+	/*
+	 * bound and default crop/compose targets are invalid targets to
+	 * try/set
+	 */
+	default:
+		return -EINVAL;
+	}
+
+	if (s->r.top < 0 || s->r.left < 0) {
+		vpe_err(ctx->dev, "negative values for top and left\n");
+		s->r.top = s->r.left = 0;
+	}
+
+	v4l_bound_align_image(&s->r.width, MIN_W, q_data->width, 1,
+		&s->r.height, MIN_H, q_data->height, H_ALIGN, S_ALIGN);
+
+	/* adjust left/top if cropping rectangle is out of bounds */
+	if (s->r.left + s->r.width > q_data->width)
+		s->r.left = q_data->width - s->r.width;
+	if (s->r.top + s->r.height > q_data->height)
+		s->r.top = q_data->height - s->r.height;
+
+	return 0;
+}
+
+static int vpe_g_selection(struct file *file, void *fh,
+		struct v4l2_selection *s)
+{
+	struct vpe_ctx *ctx = file2ctx(file);
+	struct vpe_q_data *q_data;
+	bool use_c_rect = false;
+
+	if ((s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) &&
+	    (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT))
+		return -EINVAL;
+
+	q_data = get_q_data(ctx, s->type);
+	if (!q_data)
+		return -EINVAL;
+
+	switch (s->target) {
+	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
+	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
+		if (s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
+			return -EINVAL;
+		break;
+	case V4L2_SEL_TGT_CROP_BOUNDS:
+	case V4L2_SEL_TGT_CROP_DEFAULT:
+		if (s->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
+			return -EINVAL;
+		break;
+	case V4L2_SEL_TGT_COMPOSE:
+		if (s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
+			return -EINVAL;
+		use_c_rect = true;
+		break;
+	case V4L2_SEL_TGT_CROP:
+		if (s->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
+			return -EINVAL;
+		use_c_rect = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (use_c_rect) {
+		/*
+		 * for CROP/COMPOSE target type, return c_rect params from the
+		 * respective buffer type
+		 */
+		s->r = q_data->c_rect;
+	} else {
+		/*
+		 * for DEFAULT/BOUNDS target type, return width and height from
+		 * S_FMT of the respective buffer type
+		 */
+		s->r.left = 0;
+		s->r.top = 0;
+		s->r.width = q_data->width;
+		s->r.height = q_data->height;
+	}
+
+	return 0;
+}
+
+
+static int vpe_s_selection(struct file *file, void *fh,
+		struct v4l2_selection *s)
+{
+	struct vpe_ctx *ctx = file2ctx(file);
+	struct vpe_q_data *q_data;
+	struct v4l2_selection sel = *s;
+	int ret;
+
+	ret = __vpe_try_selection(ctx, &sel);
+	if (ret)
+		return ret;
+
+	q_data = get_q_data(ctx, sel.type);
+	if (!q_data)
+		return -EINVAL;
+
+	if ((q_data->c_rect.left == sel.r.left) &&
+			(q_data->c_rect.top == sel.r.top) &&
+			(q_data->c_rect.width == sel.r.width) &&
+			(q_data->c_rect.height == sel.r.height)) {
+		vpe_dbg(ctx->dev,
+			"requested crop/compose values are already set\n");
+		return 0;
+	}
+
+	q_data->c_rect = sel.r;
+
+	return set_srcdst_params(ctx);
+}
+
 static int vpe_reqbufs(struct file *file, void *priv,
 		       struct v4l2_requestbuffers *reqbufs)
 {
@@ -1575,6 +1825,9 @@ static const struct v4l2_ioctl_ops vpe_ioctl_ops = {
 	.vidioc_try_fmt_vid_out_mplane	= vpe_try_fmt,
 	.vidioc_s_fmt_vid_out_mplane	= vpe_s_fmt,
 
+	.vidioc_g_selection		= vpe_g_selection,
+	.vidioc_s_selection		= vpe_s_selection,
+
 	.vidioc_reqbufs		= vpe_reqbufs,
 	.vidioc_querybuf	= vpe_querybuf,
 
@@ -1627,6 +1880,16 @@ static int vpe_buf_prepare(struct vb2_buffer *vb)
 	q_data = get_q_data(ctx, vb->vb2_queue->type);
 	num_planes = q_data->fmt->coplanar ? 2 : 1;
 
+	if (vb->vb2_queue->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
+		if (!(q_data->flags & Q_DATA_INTERLACED)) {
+			vb->v4l2_buf.field = V4L2_FIELD_NONE;
+		} else {
+			if (vb->v4l2_buf.field != V4L2_FIELD_TOP &&
+					vb->v4l2_buf.field != V4L2_FIELD_BOTTOM)
+				return -EINVAL;
+		}
+	}
+
 	for (i = 0; i < num_planes; i++) {
 		if (vb2_plane_size(vb, i) < q_data->sizeimage[i]) {
 			vpe_err(ctx->dev,
@@ -1677,12 +1940,12 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 
 	memset(src_vq, 0, sizeof(*src_vq));
 	src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
-	src_vq->io_modes = VB2_MMAP;
+	src_vq->io_modes = VB2_MMAP | VB2_DMABUF;
 	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;
+	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -1690,12 +1953,12 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 
 	memset(dst_vq, 0, sizeof(*dst_vq));
 	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
-	dst_vq->io_modes = VB2_MMAP;
+	dst_vq->io_modes = VB2_MMAP | VB2_DMABUF;
 	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;
+	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 
 	return vb2_queue_init(dst_vq);
 }
@@ -1724,11 +1987,6 @@ static int vpe_open(struct file *file)
 
 	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;
@@ -1749,6 +2007,14 @@ static int vpe_open(struct file *file)
 	if (ret != 0)
 		goto free_desc_list;
 
+	ret = vpdma_alloc_desc_buf(&ctx->sc_coeff_h, SC_COEF_SRAM_SIZE);
+	if (ret != 0)
+		goto free_mmr_adb;
+
+	ret = vpdma_alloc_desc_buf(&ctx->sc_coeff_v, SC_COEF_SRAM_SIZE);
+	if (ret != 0)
+		goto free_sc_h;
+
 	init_adb_hdrs(ctx);
 
 	v4l2_fh_init(&ctx->fh, video_devdata(file));
@@ -1768,9 +2034,11 @@ static int vpe_open(struct file *file)
 	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->bytesperline[VPE_LUMA] = (s_q_data->width *
 			s_q_data->fmt->vpdma_fmt[VPE_LUMA]->depth) >> 3;
-	s_q_data->colorspace = V4L2_COLORSPACE_SMPTE240M;
+	s_q_data->sizeimage[VPE_LUMA] = (s_q_data->bytesperline[VPE_LUMA] *
+			s_q_data->height);
+	s_q_data->colorspace = V4L2_COLORSPACE_REC709;
 	s_q_data->field = V4L2_FIELD_NONE;
 	s_q_data->c_rect.left = 0;
 	s_q_data->c_rect.top = 0;
@@ -1817,6 +2085,10 @@ static int vpe_open(struct file *file)
 exit_fh:
 	v4l2_ctrl_handler_free(hdl);
 	v4l2_fh_exit(&ctx->fh);
+	vpdma_free_desc_buf(&ctx->sc_coeff_v);
+free_sc_h:
+	vpdma_free_desc_buf(&ctx->sc_coeff_h);
+free_mmr_adb:
 	vpdma_free_desc_buf(&ctx->mmr_adb);
 free_desc_list:
 	vpdma_free_desc_list(&ctx->desc_list);
@@ -1900,7 +2172,7 @@ static struct video_device vpe_videodev = {
 	.fops		= &vpe_fops,
 	.ioctl_ops	= &vpe_ioctl_ops,
 	.minor		= -1,
-	.release	= video_device_release,
+	.release	= video_device_release_empty,
 	.vfl_dir	= VFL_DIR_M2M,
 };
 
@@ -1934,16 +2206,45 @@ static void vpe_runtime_put(struct platform_device *pdev)
 	WARN_ON(r < 0 && r != -ENOSYS);
 }
 
+static void vpe_fw_cb(struct platform_device *pdev)
+{
+	struct vpe_dev *dev = platform_get_drvdata(pdev);
+	struct video_device *vfd;
+	int ret;
+
+	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");
+
+		vpe_set_clock_enable(dev, 0);
+		vpe_runtime_put(pdev);
+		pm_runtime_disable(&pdev->dev);
+		v4l2_m2m_release(dev->m2m_dev);
+		vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
+		v4l2_device_unregister(&dev->v4l2_dev);
+
+		return;
+	}
+
+	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);
+}
+
 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);
+	if (!dev)
+		return -ENOMEM;
 
 	spin_lock_init(&dev->lock);
 
@@ -1954,16 +2255,17 @@ static int vpe_probe(struct platform_device *pdev)
 	atomic_set(&dev->num_instances, 0);
 	mutex_init(&dev->dev_mutex);
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "vpe_top");
+	dev->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);
+	dev->base = devm_ioremap(&pdev->dev, dev->res->start, SZ_32K);
+	if (!dev->base) {
+		ret = -ENOMEM;
 		goto v4l2_dev_unreg;
 	}
 
@@ -2006,25 +2308,23 @@ static int vpe_probe(struct platform_device *pdev)
 
 	vpe_top_vpdma_reset(dev);
 
-	dev->vpdma = vpdma_create(pdev);
-	if (IS_ERR(dev->vpdma))
+	dev->sc = sc_create(pdev);
+	if (IS_ERR(dev->sc)) {
+		ret = PTR_ERR(dev->sc);
 		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");
+	dev->csc = csc_create(pdev);
+	if (IS_ERR(dev->csc)) {
+		ret = PTR_ERR(dev->csc);
 		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);
+	dev->vpdma = vpdma_create(pdev, vpe_fw_cb);
+	if (IS_ERR(dev->vpdma)) {
+		ret = PTR_ERR(dev->vpdma);
+		goto runtime_put;
+	}
 
 	return 0;
 
@@ -2081,18 +2381,7 @@ static struct platform_driver vpe_pdrv = {
 	},
 };
 
-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_platform_driver(vpe_pdrv);
 
 MODULE_DESCRIPTION("TI VPE driver");
 MODULE_AUTHOR("Dale Farnsworth, <dale@farnsworth.org>");