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

1 files changed, 214 insertions, 2 deletions

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);