drm/meson: Support Overlay plane for video rendering

The Amlogic Meson GX SoCs support an Overlay plane behind the primary
plane for video rendering.

This Overlay plane support various YUV layouts :
- YUYV
- NV12 / NV21
- YUV444 / 422 / 420 / 411 / 410

The scaler supports a wide range of scaling ratios, but for simplicity,
plane atomic check limits the scaling from x5 to /5 in vertical and
horizontal scaling.

The z-order is fixed and always behind the primary plane and cannot be changed.

The scaling parameter algorithm was taken from the Amlogic vendor kernel
code and rewritten to match the atomic universal plane requirements.

The video rendering using this overlay plane support has been tested using
the new Kodi DRM-KMS Prime rendering path along the in-review V4L2 Mem2Mem
Hardware Video Decoder up to 3840x2160 NV12 frames on various display modes.

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Tested-by: Maxime Jourdan <mjourdan@baylibre.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1541497202-20570-2-git-send-email-narmstrong@baylibre.com

11 files changed, 971 insertions, 8 deletions

diff --git a/drivers/gpu/drm/meson/Makefile b/drivers/gpu/drm/meson/Makefile
index c5c4cc362f02..7709f2fbb9f7 100644
--- a/drivers/gpu/drm/meson/Makefile
+++ b/drivers/gpu/drm/meson/Makefile
@@ -1,5 +1,5 @@
 meson-drm-y := meson_drv.o meson_plane.o meson_crtc.o meson_venc_cvbs.o
-meson-drm-y += meson_viu.o meson_vpp.o meson_venc.o meson_vclk.o meson_canvas.o
+meson-drm-y += meson_viu.o meson_vpp.o meson_venc.o meson_vclk.o meson_canvas.o meson_overlay.o
 
 obj-$(CONFIG_DRM_MESON) += meson-drm.o
 obj-$(CONFIG_DRM_MESON_DW_HDMI) += meson_dw_hdmi.o
diff --git a/drivers/gpu/drm/meson/meson_canvas.c b/drivers/gpu/drm/meson/meson_canvas.c
index 08f6073d967e..5de11aa7c775 100644
--- a/drivers/gpu/drm/meson/meson_canvas.c
+++ b/drivers/gpu/drm/meson/meson_canvas.c
@@ -39,6 +39,7 @@
 #define CANVAS_WIDTH_HBIT       0
 #define CANVAS_HEIGHT_BIT       9
 #define CANVAS_BLKMODE_BIT      24
+#define CANVAS_ENDIAN_BIT	26
 #define DMC_CAV_LUT_ADDR	0x50 /* 0x14 offset in data sheet */
 #define CANVAS_LUT_WR_EN        (0x2 << 8)
 #define CANVAS_LUT_RD_EN        (0x1 << 8)
@@ -47,7 +48,8 @@ void meson_canvas_setup(struct meson_drm *priv,
 			uint32_t canvas_index, uint32_t addr,
 			uint32_t stride, uint32_t height,
 			unsigned int wrap,
-			unsigned int blkmode)
+			unsigned int blkmode,
+			unsigned int endian)
 {
 	unsigned int val;
 
@@ -60,7 +62,8 @@ void meson_canvas_setup(struct meson_drm *priv,
 						CANVAS_WIDTH_HBIT) |
 		(height << CANVAS_HEIGHT_BIT) |
 		(wrap << 22) |
-		(blkmode << CANVAS_BLKMODE_BIT));
+		(blkmode << CANVAS_BLKMODE_BIT) |
+		(endian << CANVAS_ENDIAN_BIT));
 
 	regmap_write(priv->dmc, DMC_CAV_LUT_ADDR,
 			CANVAS_LUT_WR_EN | canvas_index);
diff --git a/drivers/gpu/drm/meson/meson_canvas.h b/drivers/gpu/drm/meson/meson_canvas.h
index af1759da4b27..85dbf26e2826 100644
--- a/drivers/gpu/drm/meson/meson_canvas.h
+++ b/drivers/gpu/drm/meson/meson_canvas.h
@@ -23,6 +23,9 @@
 #define __MESON_CANVAS_H
 
 #define MESON_CANVAS_ID_OSD1	0x4e
+#define MESON_CANVAS_ID_VD1_0	0x60
+#define MESON_CANVAS_ID_VD1_1	0x61
+#define MESON_CANVAS_ID_VD1_2	0x62
 
 /* Canvas configuration. */
 #define MESON_CANVAS_WRAP_NONE	0x00
@@ -33,10 +36,16 @@
 #define	MESON_CANVAS_BLKMODE_32x32	0x01
 #define	MESON_CANVAS_BLKMODE_64x64	0x02
 
+#define MESON_CANVAS_ENDIAN_SWAP16	0x1
+#define MESON_CANVAS_ENDIAN_SWAP32	0x3
+#define MESON_CANVAS_ENDIAN_SWAP64	0x7
+#define MESON_CANVAS_ENDIAN_SWAP128	0xf
+
 void meson_canvas_setup(struct meson_drm *priv,
 			uint32_t canvas_index, uint32_t addr,
 			uint32_t stride, uint32_t height,
 			unsigned int wrap,
-			unsigned int blkmode);
+			unsigned int blkmode,
+			unsigned int endian);
 
 #endif /* __MESON_CANVAS_H */
diff --git a/drivers/gpu/drm/meson/meson_crtc.c b/drivers/gpu/drm/meson/meson_crtc.c
index b3bc0b0ee07f..38686c9945e0 100644
--- a/drivers/gpu/drm/meson/meson_crtc.c
+++ b/drivers/gpu/drm/meson/meson_crtc.c
@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
+#include <linux/bitfield.h>
 #include <drm/drmP.h>
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
@@ -98,6 +99,10 @@ static void meson_crtc_atomic_enable(struct drm_crtc *crtc,
 	writel(crtc_state->mode.hdisplay,
 	       priv->io_base + _REG(VPP_POSTBLEND_H_SIZE));
 
+	/* VD1 Preblend vertical start/end */
+	writel(FIELD_PREP(GENMASK(11, 0), 2303),
+			priv->io_base + _REG(VPP_PREBLEND_VD1_V_START_END));
+
 	writel_bits_relaxed(VPP_POSTBLEND_ENABLE, VPP_POSTBLEND_ENABLE,
 			    priv->io_base + _REG(VPP_MISC));
 
@@ -110,11 +115,17 @@ static void meson_crtc_atomic_disable(struct drm_crtc *crtc,
 	struct meson_crtc *meson_crtc = to_meson_crtc(crtc);
 	struct meson_drm *priv = meson_crtc->priv;
 
+	DRM_DEBUG_DRIVER("\n");
+
 	priv->viu.osd1_enabled = false;
 	priv->viu.osd1_commit = false;
 
+	priv->viu.vd1_enabled = false;
+	priv->viu.vd1_commit = false;
+
 	/* Disable VPP Postblend */
-	writel_bits_relaxed(VPP_POSTBLEND_ENABLE, 0,
+	writel_bits_relaxed(VPP_OSD1_POSTBLEND | VPP_VD1_POSTBLEND |
+			    VPP_VD1_PREBLEND | VPP_POSTBLEND_ENABLE, 0,
 			    priv->io_base + _REG(VPP_MISC));
 
 	if (crtc->state->event && !crtc->state->active) {
@@ -149,6 +160,7 @@ static void meson_crtc_atomic_flush(struct drm_crtc *crtc,
 	struct meson_drm *priv = meson_crtc->priv;
 
 	priv->viu.osd1_commit = true;
+	priv->viu.vd1_commit = true;
 }
 
 static const struct drm_crtc_helper_funcs meson_crtc_helper_funcs = {
@@ -202,7 +214,7 @@ void meson_crtc_irq(struct meson_drm *priv)
 			meson_canvas_setup(priv, MESON_CANVAS_ID_OSD1,
 				priv->viu.osd1_addr, priv->viu.osd1_stride,
 				priv->viu.osd1_height, MESON_CANVAS_WRAP_NONE,
-				MESON_CANVAS_BLKMODE_LINEAR);
+				MESON_CANVAS_BLKMODE_LINEAR, 0);
 
 		/* Enable OSD1 */
 		writel_bits_relaxed(VPP_OSD1_POSTBLEND, VPP_OSD1_POSTBLEND,
@@ -211,6 +223,206 @@ void meson_crtc_irq(struct meson_drm *priv)
 		priv->viu.osd1_commit = false;
 	}
 
+	/* Update the VD1 registers */
+	if (priv->viu.vd1_enabled && priv->viu.vd1_commit) {
+
+		switch (priv->viu.vd1_planes) {
+		case 3:
+			if (priv->canvas)
+				meson_canvas_config(priv->canvas,
+						    priv->canvas_id_vd1_2,
+						    priv->viu.vd1_addr2,
+						    priv->viu.vd1_stride2,
+						    priv->viu.vd1_height2,
+						    MESON_CANVAS_WRAP_NONE,
+						    MESON_CANVAS_BLKMODE_LINEAR,
+						    MESON_CANVAS_ENDIAN_SWAP64);
+			else
+				meson_canvas_setup(priv, MESON_CANVAS_ID_VD1_2,
+						   priv->viu.vd1_addr2,
+						   priv->viu.vd1_stride2,
+						   priv->viu.vd1_height2,
+						   MESON_CANVAS_WRAP_NONE,
+						   MESON_CANVAS_BLKMODE_LINEAR,
+						   MESON_CANVAS_ENDIAN_SWAP64);
+		/* fallthrough */
+		case 2:
+			if (priv->canvas)
+				meson_canvas_config(priv->canvas,
+						    priv->canvas_id_vd1_1,
+						    priv->viu.vd1_addr1,
+						    priv->viu.vd1_stride1,
+						    priv->viu.vd1_height1,
+						    MESON_CANVAS_WRAP_NONE,
+						    MESON_CANVAS_BLKMODE_LINEAR,
+						    MESON_CANVAS_ENDIAN_SWAP64);
+			else
+				meson_canvas_setup(priv, MESON_CANVAS_ID_VD1_1,
+						   priv->viu.vd1_addr2,
+						   priv->viu.vd1_stride2,
+						   priv->viu.vd1_height2,
+						   MESON_CANVAS_WRAP_NONE,
+						   MESON_CANVAS_BLKMODE_LINEAR,
+						   MESON_CANVAS_ENDIAN_SWAP64);
+		/* fallthrough */
+		case 1:
+			if (priv->canvas)
+				meson_canvas_config(priv->canvas,
+						    priv->canvas_id_vd1_0,
+						    priv->viu.vd1_addr0,
+						    priv->viu.vd1_stride0,
+						    priv->viu.vd1_height0,
+						    MESON_CANVAS_WRAP_NONE,
+						    MESON_CANVAS_BLKMODE_LINEAR,
+						    MESON_CANVAS_ENDIAN_SWAP64);
+			else
+				meson_canvas_setup(priv, MESON_CANVAS_ID_VD1_0,
+						   priv->viu.vd1_addr2,
+						   priv->viu.vd1_stride2,
+						   priv->viu.vd1_height2,
+						   MESON_CANVAS_WRAP_NONE,
+						   MESON_CANVAS_BLKMODE_LINEAR,
+						   MESON_CANVAS_ENDIAN_SWAP64);
+		};
+
+		writel_relaxed(priv->viu.vd1_if0_gen_reg,
+				priv->io_base + _REG(VD1_IF0_GEN_REG));
+		writel_relaxed(priv->viu.vd1_if0_gen_reg,
+				priv->io_base + _REG(VD2_IF0_GEN_REG));
+		writel_relaxed(priv->viu.vd1_if0_gen_reg2,
+				priv->io_base + _REG(VD1_IF0_GEN_REG2));
+		writel_relaxed(priv->viu.viu_vd1_fmt_ctrl,
+				priv->io_base + _REG(VIU_VD1_FMT_CTRL));
+		writel_relaxed(priv->viu.viu_vd1_fmt_ctrl,
+				priv->io_base + _REG(VIU_VD2_FMT_CTRL));
+		writel_relaxed(priv->viu.viu_vd1_fmt_w,
+				priv->io_base + _REG(VIU_VD1_FMT_W));
+		writel_relaxed(priv->viu.viu_vd1_fmt_w,
+				priv->io_base + _REG(VIU_VD2_FMT_W));
+		writel_relaxed(priv->viu.vd1_if0_canvas0,
+				priv->io_base + _REG(VD1_IF0_CANVAS0));
+		writel_relaxed(priv->viu.vd1_if0_canvas0,
+				priv->io_base + _REG(VD1_IF0_CANVAS1));
+		writel_relaxed(priv->viu.vd1_if0_canvas0,
+				priv->io_base + _REG(VD2_IF0_CANVAS0));
+		writel_relaxed(priv->viu.vd1_if0_canvas0,
+				priv->io_base + _REG(VD2_IF0_CANVAS1));
+		writel_relaxed(priv->viu.vd1_if0_luma_x0,
+				priv->io_base + _REG(VD1_IF0_LUMA_X0));
+		writel_relaxed(priv->viu.vd1_if0_luma_x0,
+				priv->io_base + _REG(VD1_IF0_LUMA_X1));
+		writel_relaxed(priv->viu.vd1_if0_luma_x0,
+				priv->io_base + _REG(VD2_IF0_LUMA_X0));
+		writel_relaxed(priv->viu.vd1_if0_luma_x0,
+				priv->io_base + _REG(VD2_IF0_LUMA_X1));
+		writel_relaxed(priv->viu.vd1_if0_luma_y0,
+				priv->io_base + _REG(VD1_IF0_LUMA_Y0));
+		writel_relaxed(priv->viu.vd1_if0_luma_y0,
+				priv->io_base + _REG(VD1_IF0_LUMA_Y1));
+		writel_relaxed(priv->viu.vd1_if0_luma_y0,
+				priv->io_base + _REG(VD2_IF0_LUMA_Y0));
+		writel_relaxed(priv->viu.vd1_if0_luma_y0,
+				priv->io_base + _REG(VD2_IF0_LUMA_Y1));
+		writel_relaxed(priv->viu.vd1_if0_chroma_x0,
+				priv->io_base + _REG(VD1_IF0_CHROMA_X0));
+		writel_relaxed(priv->viu.vd1_if0_chroma_x0,
+				priv->io_base + _REG(VD1_IF0_CHROMA_X1));
+		writel_relaxed(priv->viu.vd1_if0_chroma_x0,
+				priv->io_base + _REG(VD2_IF0_CHROMA_X0));
+		writel_relaxed(priv->viu.vd1_if0_chroma_x0,
+				priv->io_base + _REG(VD2_IF0_CHROMA_X1));
+		writel_relaxed(priv->viu.vd1_if0_chroma_y0,
+				priv->io_base + _REG(VD1_IF0_CHROMA_Y0));
+		writel_relaxed(priv->viu.vd1_if0_chroma_y0,
+				priv->io_base + _REG(VD1_IF0_CHROMA_Y1));
+		writel_relaxed(priv->viu.vd1_if0_chroma_y0,
+				priv->io_base + _REG(VD2_IF0_CHROMA_Y0));
+		writel_relaxed(priv->viu.vd1_if0_chroma_y0,
+				priv->io_base + _REG(VD2_IF0_CHROMA_Y1));
+		writel_relaxed(priv->viu.vd1_if0_repeat_loop,
+				priv->io_base + _REG(VD1_IF0_RPT_LOOP));
+		writel_relaxed(priv->viu.vd1_if0_repeat_loop,
+				priv->io_base + _REG(VD2_IF0_RPT_LOOP));
+		writel_relaxed(priv->viu.vd1_if0_luma0_rpt_pat,
+				priv->io_base + _REG(VD1_IF0_LUMA0_RPT_PAT));
+		writel_relaxed(priv->viu.vd1_if0_luma0_rpt_pat,
+				priv->io_base + _REG(VD2_IF0_LUMA0_RPT_PAT));
+		writel_relaxed(priv->viu.vd1_if0_luma0_rpt_pat,
+				priv->io_base + _REG(VD1_IF0_LUMA1_RPT_PAT));
+		writel_relaxed(priv->viu.vd1_if0_luma0_rpt_pat,
+				priv->io_base + _REG(VD2_IF0_LUMA1_RPT_PAT));
+		writel_relaxed(priv->viu.vd1_if0_chroma0_rpt_pat,
+				priv->io_base + _REG(VD1_IF0_CHROMA0_RPT_PAT));
+		writel_relaxed(priv->viu.vd1_if0_chroma0_rpt_pat,
+				priv->io_base + _REG(VD2_IF0_CHROMA0_RPT_PAT));
+		writel_relaxed(priv->viu.vd1_if0_chroma0_rpt_pat,
+				priv->io_base + _REG(VD1_IF0_CHROMA1_RPT_PAT));
+		writel_relaxed(priv->viu.vd1_if0_chroma0_rpt_pat,
+				priv->io_base + _REG(VD2_IF0_CHROMA1_RPT_PAT));
+		writel_relaxed(0, priv->io_base + _REG(VD1_IF0_LUMA_PSEL));
+		writel_relaxed(0, priv->io_base + _REG(VD1_IF0_CHROMA_PSEL));
+		writel_relaxed(0, priv->io_base + _REG(VD2_IF0_LUMA_PSEL));
+		writel_relaxed(0, priv->io_base + _REG(VD2_IF0_CHROMA_PSEL));
+		writel_relaxed(priv->viu.vd1_range_map_y,
+				priv->io_base + _REG(VD1_IF0_RANGE_MAP_Y));
+		writel_relaxed(priv->viu.vd1_range_map_cb,
+				priv->io_base + _REG(VD1_IF0_RANGE_MAP_CB));
+		writel_relaxed(priv->viu.vd1_range_map_cr,
+				priv->io_base + _REG(VD1_IF0_RANGE_MAP_CR));
+		writel_relaxed(0x78404,
+				priv->io_base + _REG(VPP_SC_MISC));
+		writel_relaxed(priv->viu.vpp_pic_in_height,
+				priv->io_base + _REG(VPP_PIC_IN_HEIGHT));
+		writel_relaxed(priv->viu.vpp_postblend_vd1_h_start_end,
+			priv->io_base + _REG(VPP_POSTBLEND_VD1_H_START_END));
+		writel_relaxed(priv->viu.vpp_blend_vd2_h_start_end,
+			priv->io_base + _REG(VPP_BLEND_VD2_H_START_END));
+		writel_relaxed(priv->viu.vpp_postblend_vd1_v_start_end,
+			priv->io_base + _REG(VPP_POSTBLEND_VD1_V_START_END));
+		writel_relaxed(priv->viu.vpp_blend_vd2_v_start_end,
+			priv->io_base + _REG(VPP_BLEND_VD2_V_START_END));
+		writel_relaxed(priv->viu.vpp_hsc_region12_startp,
+				priv->io_base + _REG(VPP_HSC_REGION12_STARTP));
+		writel_relaxed(priv->viu.vpp_hsc_region34_startp,
+				priv->io_base + _REG(VPP_HSC_REGION34_STARTP));
+		writel_relaxed(priv->viu.vpp_hsc_region4_endp,
+				priv->io_base + _REG(VPP_HSC_REGION4_ENDP));
+		writel_relaxed(priv->viu.vpp_hsc_start_phase_step,
+				priv->io_base + _REG(VPP_HSC_START_PHASE_STEP));
+		writel_relaxed(priv->viu.vpp_hsc_region1_phase_slope,
+			priv->io_base + _REG(VPP_HSC_REGION1_PHASE_SLOPE));
+		writel_relaxed(priv->viu.vpp_hsc_region3_phase_slope,
+			priv->io_base + _REG(VPP_HSC_REGION3_PHASE_SLOPE));
+		writel_relaxed(priv->viu.vpp_line_in_length,
+				priv->io_base + _REG(VPP_LINE_IN_LENGTH));
+		writel_relaxed(priv->viu.vpp_preblend_h_size,
+				priv->io_base + _REG(VPP_PREBLEND_H_SIZE));
+		writel_relaxed(priv->viu.vpp_vsc_region12_startp,
+				priv->io_base + _REG(VPP_VSC_REGION12_STARTP));
+		writel_relaxed(priv->viu.vpp_vsc_region34_startp,
+				priv->io_base + _REG(VPP_VSC_REGION34_STARTP));
+		writel_relaxed(priv->viu.vpp_vsc_region4_endp,
+				priv->io_base + _REG(VPP_VSC_REGION4_ENDP));
+		writel_relaxed(priv->viu.vpp_vsc_start_phase_step,
+				priv->io_base + _REG(VPP_VSC_START_PHASE_STEP));
+		writel_relaxed(priv->viu.vpp_vsc_ini_phase,
+				priv->io_base + _REG(VPP_VSC_INI_PHASE));
+		writel_relaxed(priv->viu.vpp_vsc_phase_ctrl,
+				priv->io_base + _REG(VPP_VSC_PHASE_CTRL));
+		writel_relaxed(priv->viu.vpp_hsc_phase_ctrl,
+				priv->io_base + _REG(VPP_HSC_PHASE_CTRL));
+		writel_relaxed(0x42, priv->io_base + _REG(VPP_SCALE_COEF_IDX));
+
+		/* Enable VD1 */
+		writel_bits_relaxed(VPP_VD1_PREBLEND | VPP_VD1_POSTBLEND |
+				    VPP_COLOR_MNG_ENABLE,
+				    VPP_VD1_PREBLEND | VPP_VD1_POSTBLEND |
+				    VPP_COLOR_MNG_ENABLE,
+				    priv->io_base + _REG(VPP_MISC));
+
+		priv->viu.vd1_commit = false;
+	}
+
 	drm_crtc_handle_vblank(priv->crtc);
 
 	spin_lock_irqsave(&priv->drm->event_lock, flags);
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 3fe6edf79b5c..3ee4d4a4ecba 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -41,6 +41,7 @@
 
 #include "meson_drv.h"
 #include "meson_plane.h"
+#include "meson_overlay.h"
 #include "meson_crtc.h"
 #include "meson_venc_cvbs.h"
 
@@ -213,6 +214,24 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 		ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_osd1);
 		if (ret)
 			goto free_drm;
+		ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_vd1_0);
+		if (ret) {
+			meson_canvas_free(priv->canvas, priv->canvas_id_osd1);
+			goto free_drm;
+		}
+		ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_vd1_1);
+		if (ret) {
+			meson_canvas_free(priv->canvas, priv->canvas_id_osd1);
+			meson_canvas_free(priv->canvas, priv->canvas_id_vd1_0);
+			goto free_drm;
+		}
+		ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_vd1_2);
+		if (ret) {
+			meson_canvas_free(priv->canvas, priv->canvas_id_osd1);
+			meson_canvas_free(priv->canvas, priv->canvas_id_vd1_0);
+			meson_canvas_free(priv->canvas, priv->canvas_id_vd1_1);
+			goto free_drm;
+		}
 	} else {
 		priv->canvas = NULL;
 
@@ -273,6 +292,10 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 	if (ret)
 		goto free_drm;
 
+	ret = meson_overlay_create(priv);
+	if (ret)
+		goto free_drm;
+
 	ret = meson_crtc_create(priv);
 	if (ret)
 		goto free_drm;
@@ -311,8 +334,12 @@ static void meson_drv_unbind(struct device *dev)
 	struct drm_device *drm = dev_get_drvdata(dev);
 	struct meson_drm *priv = drm->dev_private;
 
-	if (priv->canvas)
+	if (priv->canvas) {
 		meson_canvas_free(priv->canvas, priv->canvas_id_osd1);
+		meson_canvas_free(priv->canvas, priv->canvas_id_vd1_0);
+		meson_canvas_free(priv->canvas, priv->canvas_id_vd1_1);
+		meson_canvas_free(priv->canvas, priv->canvas_id_vd1_2);
+	}
 
 	drm_dev_unregister(drm);
 	drm_kms_helper_poll_fini(drm);
diff --git a/drivers/gpu/drm/meson/meson_drv.h b/drivers/gpu/drm/meson/meson_drv.h
index 747a996dcbdd..83e73491039a 100644
--- a/drivers/gpu/drm/meson/meson_drv.h
+++ b/drivers/gpu/drm/meson/meson_drv.h
@@ -34,10 +34,14 @@ struct meson_drm {
 
 	struct meson_canvas *canvas;
 	u8 canvas_id_osd1;
+	u8 canvas_id_vd1_0;
+	u8 canvas_id_vd1_1;
+	u8 canvas_id_vd1_2;
 
 	struct drm_device *drm;
 	struct drm_crtc *crtc;
 	struct drm_plane *primary_plane;
+	struct drm_plane *overlay_plane;
 
 	/* Components Data */
 	struct {
@@ -49,6 +53,54 @@ struct meson_drm {
 		uint32_t osd1_addr;
 		uint32_t osd1_stride;
 		uint32_t osd1_height;
+
+		bool vd1_enabled;
+		bool vd1_commit;
+		unsigned int vd1_planes;
+		uint32_t vd1_if0_gen_reg;
+		uint32_t vd1_if0_luma_x0;
+		uint32_t vd1_if0_luma_y0;
+		uint32_t vd1_if0_chroma_x0;
+		uint32_t vd1_if0_chroma_y0;
+		uint32_t vd1_if0_repeat_loop;
+		uint32_t vd1_if0_luma0_rpt_pat;
+		uint32_t vd1_if0_chroma0_rpt_pat;
+		uint32_t vd1_range_map_y;
+		uint32_t vd1_range_map_cb;
+		uint32_t vd1_range_map_cr;
+		uint32_t viu_vd1_fmt_w;
+		uint32_t vd1_if0_canvas0;
+		uint32_t vd1_if0_gen_reg2;
+		uint32_t viu_vd1_fmt_ctrl;
+		uint32_t vd1_addr0;
+		uint32_t vd1_addr1;
+		uint32_t vd1_addr2;
+		uint32_t vd1_stride0;
+		uint32_t vd1_stride1;
+		uint32_t vd1_stride2;
+		uint32_t vd1_height0;
+		uint32_t vd1_height1;
+		uint32_t vd1_height2;
+		uint32_t vpp_pic_in_height;
+		uint32_t vpp_postblend_vd1_h_start_end;
+		uint32_t vpp_postblend_vd1_v_start_end;
+		uint32_t vpp_hsc_region12_startp;
+		uint32_t vpp_hsc_region34_startp;
+		uint32_t vpp_hsc_region4_endp;
+		uint32_t vpp_hsc_start_phase_step;
+		uint32_t vpp_hsc_region1_phase_slope;
+		uint32_t vpp_hsc_region3_phase_slope;
+		uint32_t vpp_line_in_length;
+		uint32_t vpp_preblend_h_size;
+		uint32_t vpp_vsc_region12_startp;
+		uint32_t vpp_vsc_region34_startp;
+		uint32_t vpp_vsc_region4_endp;
+		uint32_t vpp_vsc_start_phase_step;
+		uint32_t vpp_vsc_ini_phase;
+		uint32_t vpp_vsc_phase_ctrl;
+		uint32_t vpp_hsc_phase_ctrl;
+		uint32_t vpp_blend_vd2_h_start_end;
+		uint32_t vpp_blend_vd2_v_start_end;
 	} viu;
 
 	struct {
diff --git a/drivers/gpu/drm/meson/meson_overlay.c b/drivers/gpu/drm/meson/meson_overlay.c
new file mode 100644
index 000000000000..9aebc5e4b418
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_overlay.c
@@ -0,0 +1,586 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2018 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ * Copyright (C) 2015 Amlogic, Inc. All rights reserved.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/bitfield.h>
+#include <linux/platform_device.h>
+#include <drm/drmP.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_plane_helper.h>
+#include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_rect.h>
+
+#include "meson_overlay.h"
+#include "meson_vpp.h"
+#include "meson_viu.h"
+#include "meson_canvas.h"
+#include "meson_registers.h"
+
+/* VD1_IF0_GEN_REG */
+#define VD_URGENT_CHROMA		BIT(28)
+#define VD_URGENT_LUMA			BIT(27)
+#define VD_HOLD_LINES(lines)		FIELD_PREP(GENMASK(24, 19), lines)
+#define VD_DEMUX_MODE_RGB		BIT(16)
+#define VD_BYTES_PER_PIXEL(val)		FIELD_PREP(GENMASK(15, 14), val)
+#define VD_CHRO_RPT_LASTL_CTRL		BIT(6)
+#define VD_LITTLE_ENDIAN		BIT(4)
+#define VD_SEPARATE_EN			BIT(1)
+#define VD_ENABLE			BIT(0)
+
+/* VD1_IF0_CANVAS0 */
+#define CANVAS_ADDR2(addr)		FIELD_PREP(GENMASK(23, 16), addr)
+#define CANVAS_ADDR1(addr)		FIELD_PREP(GENMASK(15, 8), addr)
+#define CANVAS_ADDR0(addr)		FIELD_PREP(GENMASK(7, 0), addr)
+
+/* VD1_IF0_LUMA_X0 VD1_IF0_CHROMA_X0 */
+#define VD_X_START(value)		FIELD_PREP(GENMASK(14, 0), value)
+#define VD_X_END(value)			FIELD_PREP(GENMASK(30, 16), value)
+
+/* VD1_IF0_LUMA_Y0 VD1_IF0_CHROMA_Y0 */
+#define VD_Y_START(value)		FIELD_PREP(GENMASK(12, 0), value)
+#define VD_Y_END(value)			FIELD_PREP(GENMASK(28, 16), value)
+
+/* VD1_IF0_GEN_REG2 */
+#define VD_COLOR_MAP(value)		FIELD_PREP(GENMASK(1, 0), value)
+
+/* VIU_VD1_FMT_CTRL */
+#define VD_HORZ_Y_C_RATIO(value)	FIELD_PREP(GENMASK(22, 21), value)
+#define VD_HORZ_FMT_EN			BIT(20)
+#define VD_VERT_RPT_LINE0		BIT(16)
+#define VD_VERT_INITIAL_PHASE(value)	FIELD_PREP(GENMASK(11, 8), value)
+#define VD_VERT_PHASE_STEP(value)	FIELD_PREP(GENMASK(7, 1), value)
+#define VD_VERT_FMT_EN			BIT(0)
+
+/* VPP_POSTBLEND_VD1_H_START_END */
+#define VD_H_END(value)			FIELD_PREP(GENMASK(11, 0), value)
+#define VD_H_START(value)		FIELD_PREP(GENMASK(27, 16), value)
+
+/* VPP_POSTBLEND_VD1_V_START_END */
+#define VD_V_END(value)			FIELD_PREP(GENMASK(11, 0), value)
+#define VD_V_START(value)		FIELD_PREP(GENMASK(27, 16), value)
+
+/* VPP_BLEND_VD2_V_START_END */
+#define VD2_V_END(value)		FIELD_PREP(GENMASK(11, 0), value)
+#define VD2_V_START(value)		FIELD_PREP(GENMASK(27, 16), value)
+
+/* VIU_VD1_FMT_W */
+#define VD_V_WIDTH(value)		FIELD_PREP(GENMASK(11, 0), value)
+#define VD_H_WIDTH(value)		FIELD_PREP(GENMASK(27, 16), value)
+
+/* VPP_HSC_REGION12_STARTP VPP_HSC_REGION34_STARTP */
+#define VD_REGION24_START(value)	FIELD_PREP(GENMASK(11, 0), value)
+#define VD_REGION13_END(value)		FIELD_PREP(GENMASK(27, 16), value)
+
+struct meson_overlay {
+	struct drm_plane base;
+	struct meson_drm *priv;
+};
+#define to_meson_overlay(x) container_of(x, struct meson_overlay, base)
+
+#define FRAC_16_16(mult, div)    (((mult) << 16) / (div))
+
+static int meson_overlay_atomic_check(struct drm_plane *plane,
+				      struct drm_plane_state *state)
+{
+	struct drm_crtc_state *crtc_state;
+
+	if (!state->crtc)
+		return 0;
+
+	crtc_state = drm_atomic_get_crtc_state(state->state, state->crtc);
+	if (IS_ERR(crtc_state))
+		return PTR_ERR(crtc_state);
+
+	return drm_atomic_helper_check_plane_state(state, crtc_state,
+						   FRAC_16_16(1, 5),
+						   FRAC_16_16(5, 1),
+						   true, true);
+}
+
+/* Takes a fixed 16.16 number and converts it to integer. */
+static inline int64_t fixed16_to_int(int64_t value)
+{
+	return value >> 16;
+}
+
+static const uint8_t skip_tab[6] = {
+	0x24, 0x04, 0x68, 0x48, 0x28, 0x08,
+};
+
+static void meson_overlay_get_vertical_phase(unsigned int ratio_y, int *phase,
+					     int *repeat, bool interlace)
+{
+	int offset_in = 0;
+	int offset_out = 0;
+	int repeat_skip = 0;
+
+	if (!interlace && ratio_y > (1 << 18))
+		offset_out = (1 * ratio_y) >> 10;
+
+	while ((offset_in + (4 << 8)) <= offset_out) {
+		repeat_skip++;
+		offset_in += 4 << 8;
+	}
+
+	*phase = (offset_out - offset_in) >> 2;
+
+	if (*phase > 0x100)
+		repeat_skip++;
+
+	*phase = *phase & 0xff;
+
+	if (repeat_skip > 5)
+		repeat_skip = 5;
+
+	*repeat = skip_tab[repeat_skip];
+}
+
+static void meson_overlay_setup_scaler_params(struct meson_drm *priv,
+					      struct drm_plane *plane,
+					      bool interlace_mode)
+{
+	struct drm_crtc_state *crtc_state = priv->crtc->state;
+	int video_top, video_left, video_width, video_height;
+	struct drm_plane_state *state = plane->state;
+	unsigned int vd_start_lines, vd_end_lines;
+	unsigned int hd_start_lines, hd_end_lines;
+	unsigned int crtc_height, crtc_width;
+	unsigned int vsc_startp, vsc_endp;
+	unsigned int hsc_startp, hsc_endp;
+	unsigned int crop_top, crop_left;
+	int vphase, vphase_repeat_skip;
+	unsigned int ratio_x, ratio_y;
+	int temp_height, temp_width;
+	unsigned int w_in, h_in;
+	int temp, start, end;
+
+	if (!crtc_state) {
+		DRM_ERROR("Invalid crtc_state\n");
+		return;
+	}
+
+	crtc_height = crtc_state->mode.vdisplay;
+	crtc_width = crtc_state->mode.hdisplay;
+
+	w_in = fixed16_to_int(state->src_w);
+	h_in = fixed16_to_int(state->src_h);
+	crop_top = fixed16_to_int(state->src_x);
+	crop_left = fixed16_to_int(state->src_x);
+
+	video_top = state->crtc_y;
+	video_left = state->crtc_x;
+	video_width = state->crtc_w;
+	video_height = state->crtc_h;
+
+	DRM_DEBUG("crtc_width %d crtc_height %d interlace %d\n",
+		  crtc_width, crtc_height, interlace_mode);
+	DRM_DEBUG("w_in %d h_in %d crop_top %d crop_left %d\n",
+		  w_in, h_in, crop_top, crop_left);
+	DRM_DEBUG("video top %d left %d width %d height %d\n",
+		  video_top, video_left, video_width, video_height);
+
+	ratio_x = (w_in << 18) / video_width;
+	ratio_y = (h_in << 18) / video_height;
+
+	if (ratio_x * video_width < (w_in << 18))
+		ratio_x++;
+
+	DRM_DEBUG("ratio x 0x%x y 0x%x\n", ratio_x, ratio_y);
+
+	meson_overlay_get_vertical_phase(ratio_y, &vphase, &vphase_repeat_skip,
+					 interlace_mode);
+
+	DRM_DEBUG("vphase 0x%x skip %d\n", vphase, vphase_repeat_skip);
+
+	/* Vertical */
+
+	start = video_top + video_height / 2 - ((h_in << 17) / ratio_y);
+	end = (h_in << 18) / ratio_y + start - 1;
+
+	if (video_top < 0 && start < 0)
+		vd_start_lines = (-(start) * ratio_y) >> 18;
+	else if (start < video_top)
+		vd_start_lines = ((video_top - start) * ratio_y) >> 18;
+	else
+		vd_start_lines = 0;
+
+	if (video_top < 0)
+		temp_height = min_t(unsigned int,
+				    video_top + video_height - 1,
+				    crtc_height - 1);
+	else
+		temp_height = min_t(unsigned int,
+				    video_top + video_height - 1,
+				    crtc_height - 1) - video_top + 1;
+
+	temp = vd_start_lines + (temp_height * ratio_y >> 18);
+	vd_end_lines = (temp <= (h_in - 1)) ? temp : (h_in - 1);
+
+	vd_start_lines += crop_left;
+	vd_end_lines += crop_left;
+
+	/*
+	 * TOFIX: Input frames are handled and scaled like progressive frames,
+	 * proper handling of interlaced field input frames need to be figured
+	 * out using the proper framebuffer flags set by userspace.
+	 */
+	if (interlace_mode) {
+		start >>= 1;
+		end >>= 1;
+	}
+
+	vsc_startp = max_t(int, start,
+			   max_t(int, 0, video_top));
+	vsc_endp = min_t(int, end,
+			 min_t(int, crtc_height - 1,
+			       video_top + video_height - 1));
+
+	DRM_DEBUG("vsc startp %d endp %d start_lines %d end_lines %d\n",
+		 vsc_startp, vsc_endp, vd_start_lines, vd_end_lines);
+
+	/* Horizontal */
+
+	start = video_left + video_width / 2 - ((w_in << 17) / ratio_x);
+	end = (w_in << 18) / ratio_x + start - 1;
+
+	if (video_left < 0 && start < 0)
+		hd_start_lines = (-(start) * ratio_x) >> 18;
+	else if (start < video_left)
+		hd_start_lines = ((video_left - start) * ratio_x) >> 18;
+	else
+		hd_start_lines = 0;
+
+	if (video_left < 0)
+		temp_width = min_t(unsigned int,
+				   video_left + video_width - 1,
+				   crtc_width - 1);
+	else
+		temp_width = min_t(unsigned int,
+				   video_left + video_width - 1,
+				   crtc_width - 1) - video_left + 1;
+
+	temp = hd_start_lines + (temp_width * ratio_x >> 18);
+	hd_end_lines = (temp <= (w_in - 1)) ? temp : (w_in - 1);
+
+	priv->viu.vpp_line_in_length = hd_end_lines - hd_start_lines + 1;
+	hsc_startp = max_t(int, start, max_t(int, 0, video_left));
+	hsc_endp = min_t(int, end, min_t(int, crtc_width - 1,
+					 video_left + video_width - 1));
+
+	hd_start_lines += crop_top;
+	hd_end_lines += crop_top;
+
+	DRM_DEBUG("hsc startp %d endp %d start_lines %d end_lines %d\n",
+		 hsc_startp, hsc_endp, hd_start_lines, hd_end_lines);
+
+	priv->viu.vpp_vsc_start_phase_step = ratio_y << 6;
+
+	priv->viu.vpp_vsc_ini_phase = vphase << 8;
+	priv->viu.vpp_vsc_phase_ctrl = (1 << 13) | (4 << 8) |
+				       vphase_repeat_skip;
+
+	priv->viu.vd1_if0_luma_x0 = VD_X_START(hd_start_lines) |
+				    VD_X_END(hd_end_lines);
+	priv->viu.vd1_if0_chroma_x0 = VD_X_START(hd_start_lines >> 1) |
+				      VD_X_END(hd_end_lines >> 1);
+
+	priv->viu.viu_vd1_fmt_w =
+			VD_H_WIDTH(hd_end_lines - hd_start_lines + 1) |
+			VD_V_WIDTH(hd_end_lines/2 - hd_start_lines/2 + 1);
+
+	priv->viu.vd1_if0_luma_y0 = VD_Y_START(vd_start_lines) |
+				    VD_Y_END(vd_end_lines);
+
+	priv->viu.vd1_if0_chroma_y0 = VD_Y_START(vd_start_lines >> 1) |
+				      VD_Y_END(vd_end_lines >> 1);
+
+	priv->viu.vpp_pic_in_height = h_in;
+
+	priv->viu.vpp_postblend_vd1_h_start_end = VD_H_START(hsc_startp) |
+						  VD_H_END(hsc_endp);
+	priv->viu.vpp_blend_vd2_h_start_end = VD_H_START(hd_start_lines) |
+					      VD_H_END(hd_end_lines);
+	priv->viu.vpp_hsc_region12_startp = VD_REGION13_END(0) |
+					    VD_REGION24_START(hsc_startp);
+	priv->viu.vpp_hsc_region34_startp =
+				VD_REGION13_END(hsc_startp) |
+				VD_REGION24_START(hsc_endp - hsc_startp);
+	priv->viu.vpp_hsc_region4_endp = hsc_endp - hsc_startp;
+	priv->viu.vpp_hsc_start_phase_step = ratio_x << 6;
+	priv->viu.vpp_hsc_region1_phase_slope = 0;
+	priv->viu.vpp_hsc_region3_phase_slope = 0;
+	priv->viu.vpp_hsc_phase_ctrl = (1 << 21) | (4 << 16);
+
+	priv->viu.vpp_line_in_length = hd_end_lines - hd_start_lines + 1;
+	priv->viu.vpp_preblend_h_size = hd_end_lines - hd_start_lines + 1;
+
+	priv->viu.vpp_postblend_vd1_v_start_end = VD_V_START(vsc_startp) |
+						  VD_V_END(vsc_endp);
+	priv->viu.vpp_blend_vd2_v_start_end =
+				VD2_V_START((vd_end_lines + 1) >> 1) |
+				VD2_V_END(vd_end_lines);
+
+	priv->viu.vpp_vsc_region12_startp = 0;
+	priv->viu.vpp_vsc_region34_startp =
+				VD_REGION13_END(vsc_endp - vsc_startp) |
+				VD_REGION24_START(vsc_endp - vsc_startp);
+	priv->viu.vpp_vsc_region4_endp = vsc_endp - vsc_startp;
+	priv->viu.vpp_vsc_start_phase_step = ratio_y << 6;
+}
+
+static void meson_overlay_atomic_update(struct drm_plane *plane,
+					struct drm_plane_state *old_state)
+{
+	struct meson_overlay *meson_overlay = to_meson_overlay(plane);
+	struct drm_plane_state *state = plane->state;
+	struct drm_framebuffer *fb = state->fb;
+	struct meson_drm *priv = meson_overlay->priv;
+	struct drm_gem_cma_object *gem;
+	unsigned long flags;
+	bool interlace_mode;
+
+	DRM_DEBUG_DRIVER("\n");
+
+	/* Fallback is canvas provider is not available */
+	if (!priv->canvas) {
+		priv->canvas_id_vd1_0 = MESON_CANVAS_ID_VD1_0;
+		priv->canvas_id_vd1_1 = MESON_CANVAS_ID_VD1_1;
+		priv->canvas_id_vd1_2 = MESON_CANVAS_ID_VD1_2;
+	}
+
+	interlace_mode = state->crtc->mode.flags & DRM_MODE_FLAG_INTERLACE;
+
+	spin_lock_irqsave(&priv->drm->event_lock, flags);
+
+	priv->viu.vd1_if0_gen_reg = VD_URGENT_CHROMA |
+				    VD_URGENT_LUMA |
+				    VD_HOLD_LINES(9) |
+				    VD_CHRO_RPT_LASTL_CTRL |
+				    VD_ENABLE;
+
+	/* Setup scaler params */
+	meson_overlay_setup_scaler_params(priv, plane, interlace_mode);
+
+	priv->viu.vd1_if0_repeat_loop = 0;
+	priv->viu.vd1_if0_luma0_rpt_pat = interlace_mode ? 8 : 0;
+	priv->viu.vd1_if0_chroma0_rpt_pat = interlace_mode ? 8 : 0;
+	priv->viu.vd1_range_map_y = 0;
+	priv->viu.vd1_range_map_cb = 0;
+	priv->viu.vd1_range_map_cr = 0;
+
+	/* Default values for RGB888/YUV444 */
+	priv->viu.vd1_if0_gen_reg2 = 0;
+	priv->viu.viu_vd1_fmt_ctrl = 0;
+
+	switch (fb->format->format) {
+	/* TOFIX DRM_FORMAT_RGB888 should be supported */
+	case DRM_FORMAT_YUYV:
+		priv->viu.vd1_if0_gen_reg |= VD_BYTES_PER_PIXEL(1);
+		priv->viu.vd1_if0_canvas0 =
+					CANVAS_ADDR2(priv->canvas_id_vd1_0) |
+					CANVAS_ADDR1(priv->canvas_id_vd1_0) |
+					CANVAS_ADDR0(priv->canvas_id_vd1_0);
+		priv->viu.viu_vd1_fmt_ctrl = VD_HORZ_Y_C_RATIO(1) | /* /2 */
+					     VD_HORZ_FMT_EN |
+					     VD_VERT_RPT_LINE0 |
+					     VD_VERT_INITIAL_PHASE(12) |
+					     VD_VERT_PHASE_STEP(16) | /* /2 */
+					     VD_VERT_FMT_EN;
+		break;
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+		priv->viu.vd1_if0_gen_reg |= VD_SEPARATE_EN;
+		priv->viu.vd1_if0_canvas0 =
+					CANVAS_ADDR2(priv->canvas_id_vd1_1) |
+					CANVAS_ADDR1(priv->canvas_id_vd1_1) |
+					CANVAS_ADDR0(priv->canvas_id_vd1_0);
+		if (fb->format->format == DRM_FORMAT_NV12)
+			priv->viu.vd1_if0_gen_reg2 = VD_COLOR_MAP(1);
+		else
+			priv->viu.vd1_if0_gen_reg2 = VD_COLOR_MAP(2);
+		priv->viu.viu_vd1_fmt_ctrl = VD_HORZ_Y_C_RATIO(1) | /* /2 */
+					     VD_HORZ_FMT_EN |
+					     VD_VERT_RPT_LINE0 |
+					     VD_VERT_INITIAL_PHASE(12) |
+					     VD_VERT_PHASE_STEP(8) | /* /4 */
+					     VD_VERT_FMT_EN;
+		break;
+	case DRM_FORMAT_YUV444:
+	case DRM_FORMAT_YUV422:
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YUV411:
+	case DRM_FORMAT_YUV410:
+		priv->viu.vd1_if0_gen_reg |= VD_SEPARATE_EN;
+		priv->viu.vd1_if0_canvas0 =
+					CANVAS_ADDR2(priv->canvas_id_vd1_2) |
+					CANVAS_ADDR1(priv->canvas_id_vd1_1) |
+					CANVAS_ADDR0(priv->canvas_id_vd1_0);
+		switch (fb->format->format) {
+		case DRM_FORMAT_YUV422:
+			priv->viu.viu_vd1_fmt_ctrl =
+					VD_HORZ_Y_C_RATIO(1) | /* /2 */
+					VD_HORZ_FMT_EN |
+					VD_VERT_RPT_LINE0 |
+					VD_VERT_INITIAL_PHASE(12) |
+					VD_VERT_PHASE_STEP(16) | /* /2 */
+					VD_VERT_FMT_EN;
+			break;
+		case DRM_FORMAT_YUV420:
+			priv->viu.viu_vd1_fmt_ctrl =
+					VD_HORZ_Y_C_RATIO(1) | /* /2 */
+					VD_HORZ_FMT_EN |
+					VD_VERT_RPT_LINE0 |
+					VD_VERT_INITIAL_PHASE(12) |
+					VD_VERT_PHASE_STEP(8) | /* /4 */
+					VD_VERT_FMT_EN;
+			break;
+		case DRM_FORMAT_YUV411:
+			priv->viu.viu_vd1_fmt_ctrl =
+					VD_HORZ_Y_C_RATIO(2) | /* /4 */
+					VD_HORZ_FMT_EN |
+					VD_VERT_RPT_LINE0 |
+					VD_VERT_INITIAL_PHASE(12) |
+					VD_VERT_PHASE_STEP(16) | /* /2 */
+					VD_VERT_FMT_EN;
+			break;
+		case DRM_FORMAT_YUV410:
+			priv->viu.viu_vd1_fmt_ctrl =
+					VD_HORZ_Y_C_RATIO(2) | /* /4 */
+					VD_HORZ_FMT_EN |
+					VD_VERT_RPT_LINE0 |
+					VD_VERT_INITIAL_PHASE(12) |
+					VD_VERT_PHASE_STEP(8) | /* /4 */
+					VD_VERT_FMT_EN;
+			break;
+		}
+		break;
+	}
+
+	/* Update Canvas with buffer address */
+	priv->viu.vd1_planes = drm_format_num_planes(fb->format->format);
+
+	switch (priv->viu.vd1_planes) {
+	case 3:
+		gem = drm_fb_cma_get_gem_obj(fb, 2);
+		priv->viu.vd1_addr2 = gem->paddr + fb->offsets[2];
+		priv->viu.vd1_stride2 = fb->pitches[2];
+		priv->viu.vd1_height2 =
+			drm_format_plane_height(fb->height,
+						fb->format->format, 2);
+		DRM_DEBUG("plane 2 addr 0x%x stride %d height %d\n",
+			 priv->viu.vd1_addr2,
+			 priv->viu.vd1_stride2,
+			 priv->viu.vd1_height2);
+	/* fallthrough */
+	case 2:
+		gem = drm_fb_cma_get_gem_obj(fb, 1);
+		priv->viu.vd1_addr1 = gem->paddr + fb->offsets[1];
+		priv->viu.vd1_stride1 = fb->pitches[1];
+		priv->viu.vd1_height1 =
+			drm_format_plane_height(fb->height,
+						fb->format->format, 1);
+		DRM_DEBUG("plane 1 addr 0x%x stride %d height %d\n",
+			 priv->viu.vd1_addr1,
+			 priv->viu.vd1_stride1,
+			 priv->viu.vd1_height1);
+	/* fallthrough */
+	case 1:
+		gem = drm_fb_cma_get_gem_obj(fb, 0);
+		priv->viu.vd1_addr0 = gem->paddr + fb->offsets[0];
+		priv->viu.vd1_stride0 = fb->pitches[0];
+		priv->viu.vd1_height0 =
+			drm_format_plane_height(fb->height,
+						fb->format->format, 0);
+		DRM_DEBUG("plane 0 addr 0x%x stride %d height %d\n",
+			 priv->viu.vd1_addr0,
+			 priv->viu.vd1_stride0,
+			 priv->viu.vd1_height0);
+	}
+
+	priv->viu.vd1_enabled = true;
+
+	spin_unlock_irqrestore(&priv->drm->event_lock, flags);
+
+	DRM_DEBUG_DRIVER("\n");
+}
+
+static void meson_overlay_atomic_disable(struct drm_plane *plane,
+				       struct drm_plane_state *old_state)
+{
+	struct meson_overlay *meson_overlay = to_meson_overlay(plane);
+	struct meson_drm *priv = meson_overlay->priv;
+
+	DRM_DEBUG_DRIVER("\n");
+
+	priv->viu.vd1_enabled = false;
+
+	/* Disable VD1 */
+	writel_bits_relaxed(VPP_VD1_POSTBLEND | VPP_VD1_PREBLEND, 0,
+			    priv->io_base + _REG(VPP_MISC));
+
+}
+
+static const struct drm_plane_helper_funcs meson_overlay_helper_funcs = {
+	.atomic_check	= meson_overlay_atomic_check,
+	.atomic_disable	= meson_overlay_atomic_disable,
+	.atomic_update	= meson_overlay_atomic_update,
+};
+
+static const struct drm_plane_funcs meson_overlay_funcs = {
+	.update_plane		= drm_atomic_helper_update_plane,
+	.disable_plane		= drm_atomic_helper_disable_plane,
+	.destroy		= drm_plane_cleanup,
+	.reset			= drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
+};
+
+static const uint32_t supported_drm_formats[] = {
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_NV12,
+	DRM_FORMAT_NV21,
+	DRM_FORMAT_YUV444,
+	DRM_FORMAT_YUV422,
+	DRM_FORMAT_YUV420,
+	DRM_FORMAT_YUV411,
+	DRM_FORMAT_YUV410,
+};
+
+int meson_overlay_create(struct meson_drm *priv)
+{
+	struct meson_overlay *meson_overlay;
+	struct drm_plane *plane;
+
+	DRM_DEBUG_DRIVER("\n");
+
+	meson_overlay = devm_kzalloc(priv->drm->dev, sizeof(*meson_overlay),
+				   GFP_KERNEL);
+	if (!meson_overlay)
+		return -ENOMEM;
+
+	meson_overlay->priv = priv;
+	plane = &meson_overlay->base;
+
+	drm_universal_plane_init(priv->drm, plane, 0xFF,
+				 &meson_overlay_funcs,
+				 supported_drm_formats,
+				 ARRAY_SIZE(supported_drm_formats),
+				 NULL,
+				 DRM_PLANE_TYPE_OVERLAY, "meson_overlay_plane");
+
+	drm_plane_helper_add(plane, &meson_overlay_helper_funcs);
+
+	priv->overlay_plane = plane;
+
+	DRM_DEBUG_DRIVER("\n");
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/meson/meson_overlay.h b/drivers/gpu/drm/meson/meson_overlay.h
new file mode 100644
index 000000000000..dae24f5ac63d
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_overlay.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2018 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#ifndef __MESON_OVERLAY_H
+#define __MESON_OVERLAY_H
+
+#include "meson_drv.h"
+
+int meson_overlay_create(struct meson_drm *priv);
+
+#endif /* __MESON_OVERLAY_H */
diff --git a/drivers/gpu/drm/meson/meson_registers.h b/drivers/gpu/drm/meson/meson_registers.h
index bca87143e548..5c7e02c703bc 100644
--- a/drivers/gpu/drm/meson/meson_registers.h
+++ b/drivers/gpu/drm/meson/meson_registers.h
@@ -286,6 +286,7 @@
 #define VIU_OSD1_MATRIX_COEF22_30 0x1a9d
 #define VIU_OSD1_MATRIX_COEF31_32 0x1a9e
 #define VIU_OSD1_MATRIX_COEF40_41 0x1a9f
+#define VD1_IF0_GEN_REG3 0x1aa7
 #define VIU_OSD1_EOTF_CTL 0x1ad4
 #define VIU_OSD1_EOTF_COEF00_01 0x1ad5
 #define VIU_OSD1_EOTF_COEF02_10 0x1ad6
@@ -297,6 +298,7 @@
 #define VIU_OSD1_OETF_CTL 0x1adc
 #define VIU_OSD1_OETF_LUT_ADDR_PORT 0x1add
 #define VIU_OSD1_OETF_LUT_DATA_PORT 0x1ade
+#define AFBC_ENABLE 0x1ae0
 
 /* vpp */
 #define VPP_DUMMY_DATA 0x1d00
@@ -349,6 +351,7 @@
 #define		VPP_VD2_PREBLEND	BIT(15)
 #define		VPP_OSD1_PREBLEND	BIT(16)
 #define		VPP_OSD2_PREBLEND	BIT(17)
+#define		VPP_COLOR_MNG_ENABLE	BIT(28)
 #define VPP_OFIFO_SIZE 0x1d27
 #define VPP_FIFO_STATUS 0x1d28
 #define VPP_SMOKE_CTRL 0x1d29
diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c
index 6bcfa527c180..2dffb987ec65 100644
--- a/drivers/gpu/drm/meson/meson_viu.c
+++ b/drivers/gpu/drm/meson/meson_viu.c
@@ -329,6 +329,21 @@ void meson_viu_init(struct meson_drm *priv)
 			    0xff << OSD_REPLACE_SHIFT,
 			    priv->io_base + _REG(VIU_OSD2_CTRL_STAT2));
 
+	/* Disable VD1 AFBC */
+	/* di_mif0_en=0 mif0_to_vpp_en=0 di_mad_en=0 */
+	writel_bits_relaxed(0x7 << 16, 0,
+			priv->io_base + _REG(VIU_MISC_CTRL0));
+	/* afbc vd1 set=0 */
+	writel_bits_relaxed(BIT(20), 0,
+			priv->io_base + _REG(VIU_MISC_CTRL0));
+	writel_relaxed(0, priv->io_base + _REG(AFBC_ENABLE));
+
+	writel_relaxed(0x00FF00C0,
+			priv->io_base + _REG(VD1_IF0_LUMA_FIFO_SIZE));
+	writel_relaxed(0x00FF00C0,
+			priv->io_base + _REG(VD2_IF0_LUMA_FIFO_SIZE));
+
+
 	priv->viu.osd1_enabled = false;
 	priv->viu.osd1_commit = false;
 	priv->viu.osd1_interlace = false;
diff --git a/drivers/gpu/drm/meson/meson_vpp.c b/drivers/gpu/drm/meson/meson_vpp.c
index 27356f81a0ab..5dc24a99e978 100644
--- a/drivers/gpu/drm/meson/meson_vpp.c
+++ b/drivers/gpu/drm/meson/meson_vpp.c
@@ -122,6 +122,31 @@ static void meson_vpp_write_scaling_filter_coefs(struct meson_drm *priv,
 				priv->io_base + _REG(VPP_OSD_SCALE_COEF));
 }
 
+static const uint32_t vpp_filter_coefs_bicubic[] = {
+	0x00800000, 0x007f0100, 0xff7f0200, 0xfe7f0300,
+	0xfd7e0500, 0xfc7e0600, 0xfb7d0800, 0xfb7c0900,
+	0xfa7b0b00, 0xfa7a0dff, 0xf9790fff, 0xf97711ff,
+	0xf87613ff, 0xf87416fe, 0xf87218fe, 0xf8701afe,
+	0xf76f1dfd, 0xf76d1ffd, 0xf76b21fd, 0xf76824fd,
+	0xf76627fc, 0xf76429fc, 0xf7612cfc, 0xf75f2ffb,
+	0xf75d31fb, 0xf75a34fb, 0xf75837fa, 0xf7553afa,
+	0xf8523cfa, 0xf8503ff9, 0xf84d42f9, 0xf84a45f9,
+	0xf84848f8
+};
+
+static void meson_vpp_write_vd_scaling_filter_coefs(struct meson_drm *priv,
+						    const unsigned int *coefs,
+						    bool is_horizontal)
+{
+	int i;
+
+	writel_relaxed(is_horizontal ? BIT(8) : 0,
+			priv->io_base + _REG(VPP_SCALE_COEF_IDX));
+	for (i = 0; i < 33; i++)
+		writel_relaxed(coefs[i],
+				priv->io_base + _REG(VPP_SCALE_COEF));
+}
+
 void meson_vpp_init(struct meson_drm *priv)
 {
 	/* set dummy data default YUV black */
@@ -150,17 +175,34 @@ void meson_vpp_init(struct meson_drm *priv)
 
 	/* Force all planes off */
 	writel_bits_relaxed(VPP_OSD1_POSTBLEND | VPP_OSD2_POSTBLEND |
-			    VPP_VD1_POSTBLEND | VPP_VD2_POSTBLEND, 0,
+			    VPP_VD1_POSTBLEND | VPP_VD2_POSTBLEND |
+			    VPP_VD1_PREBLEND | VPP_VD2_PREBLEND, 0,
 			    priv->io_base + _REG(VPP_MISC));
 
+	/* Setup default VD settings */
+	writel_relaxed(4096,
+			priv->io_base + _REG(VPP_PREBLEND_VD1_H_START_END));
+	writel_relaxed(4096,
+			priv->io_base + _REG(VPP_BLEND_VD2_H_START_END));
+
 	/* Disable Scalers */
 	writel_relaxed(0, priv->io_base + _REG(VPP_OSD_SC_CTRL0));
 	writel_relaxed(0, priv->io_base + _REG(VPP_OSD_VSC_CTRL0));
 	writel_relaxed(0, priv->io_base + _REG(VPP_OSD_HSC_CTRL0));
+	writel_relaxed(4 | (4 << 8) | BIT(15),
+		       priv->io_base + _REG(VPP_SC_MISC));
+
+	writel_relaxed(1, priv->io_base + _REG(VPP_VADJ_CTRL));
 
 	/* Write in the proper filter coefficients. */
 	meson_vpp_write_scaling_filter_coefs(priv,
 				vpp_filter_coefs_4point_bspline, false);
 	meson_vpp_write_scaling_filter_coefs(priv,
 				vpp_filter_coefs_4point_bspline, true);
+
+	/* Write the VD proper filter coefficients. */
+	meson_vpp_write_vd_scaling_filter_coefs(priv, vpp_filter_coefs_bicubic,
+						false);
+	meson_vpp_write_vd_scaling_filter_coefs(priv, vpp_filter_coefs_bicubic,
+						true);
 }