Merge tag 'mediatek-drm-next-5.6' of https://github.com/ckhu-mediatek/linux.git-tags into drm-next

Mediatek DRM Next for Linux 5.6

This fix non-smooth cursor problem, add cmdq support, add ctm property
support and some refinement.
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: CK Hu <ck.hu@mediatek.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1578972526.14594.8.camel@mtksdaap41

drivers/gpu/drm/mediatek/Makefile

@@ -20,7 +20,7 @@ obj-$(CONFIG_DRM_MEDIATEK) += mediatek-drm.o
 mediatek-drm-hdmi-objs := mtk_cec.o \
 			  mtk_hdmi.o \
 			  mtk_hdmi_ddc.o \
-                          mtk_mt2701_hdmi_phy.o \
+			  mtk_mt2701_hdmi_phy.o \
 			  mtk_mt8173_hdmi_phy.o \
 			  mtk_hdmi_phy.o
 

drivers/gpu/drm/mediatek/mtk_disp_color.c

@@ -9,6 +9,7 @@
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
 
 #include "mtk_drm_crtc.h"
 #include "mtk_drm_ddp_comp.h"
@@ -45,12 +46,12 @@ static inline struct mtk_disp_color *comp_to_color(struct mtk_ddp_comp *comp)
 
 static void mtk_color_config(struct mtk_ddp_comp *comp, unsigned int w,
 			     unsigned int h, unsigned int vrefresh,
-			     unsigned int bpc)
+			     unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
 	struct mtk_disp_color *color = comp_to_color(comp);
 
-	writel(w, comp->regs + DISP_COLOR_WIDTH(color));
-	writel(h, comp->regs + DISP_COLOR_HEIGHT(color));
+	mtk_ddp_write(cmdq_pkt, w, comp, DISP_COLOR_WIDTH(color));
+	mtk_ddp_write(cmdq_pkt, h, comp, DISP_COLOR_HEIGHT(color));
 }
 
 static void mtk_color_start(struct mtk_ddp_comp *comp)

drivers/gpu/drm/mediatek/mtk_disp_ovl.c

@@ -11,6 +11,7 @@
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
 
 #include "mtk_drm_crtc.h"
 #include "mtk_drm_ddp_comp.h"
@@ -124,14 +125,15 @@ static void mtk_ovl_stop(struct mtk_ddp_comp *comp)
 
 static void mtk_ovl_config(struct mtk_ddp_comp *comp, unsigned int w,
 			   unsigned int h, unsigned int vrefresh,
-			   unsigned int bpc)
+			   unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
 	if (w != 0 && h != 0)
-		writel_relaxed(h << 16 | w, comp->regs + DISP_REG_OVL_ROI_SIZE);
-	writel_relaxed(0x0, comp->regs + DISP_REG_OVL_ROI_BGCLR);
+		mtk_ddp_write_relaxed(cmdq_pkt, h << 16 | w, comp,
+				      DISP_REG_OVL_ROI_SIZE);
+	mtk_ddp_write_relaxed(cmdq_pkt, 0x0, comp, DISP_REG_OVL_ROI_BGCLR);
 
-	writel(0x1, comp->regs + DISP_REG_OVL_RST);
-	writel(0x0, comp->regs + DISP_REG_OVL_RST);
+	mtk_ddp_write(cmdq_pkt, 0x1, comp, DISP_REG_OVL_RST);
+	mtk_ddp_write(cmdq_pkt, 0x0, comp, DISP_REG_OVL_RST);
 }
 
 static unsigned int mtk_ovl_layer_nr(struct mtk_ddp_comp *comp)
@@ -175,16 +177,16 @@ static int mtk_ovl_layer_check(struct mtk_ddp_comp *comp, unsigned int idx,
 	return 0;
 }
 
-static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx)
+static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx,
+			     struct cmdq_pkt *cmdq_pkt)
 {
-	unsigned int reg;
 	unsigned int gmc_thrshd_l;
 	unsigned int gmc_thrshd_h;
 	unsigned int gmc_value;
 	struct mtk_disp_ovl *ovl = comp_to_ovl(comp);
 
-	writel(0x1, comp->regs + DISP_REG_OVL_RDMA_CTRL(idx));
-
+	mtk_ddp_write(cmdq_pkt, 0x1, comp,
+		      DISP_REG_OVL_RDMA_CTRL(idx));
 	gmc_thrshd_l = GMC_THRESHOLD_LOW >>
 		      (GMC_THRESHOLD_BITS - ovl->data->gmc_bits);
 	gmc_thrshd_h = GMC_THRESHOLD_HIGH >>
@@ -194,22 +196,19 @@ static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx)
 	else
 		gmc_value = gmc_thrshd_l | gmc_thrshd_l << 8 |
 			    gmc_thrshd_h << 16 | gmc_thrshd_h << 24;
-	writel(gmc_value, comp->regs + DISP_REG_OVL_RDMA_GMC(idx));
-
-	reg = readl(comp->regs + DISP_REG_OVL_SRC_CON);
-	reg = reg | BIT(idx);
-	writel(reg, comp->regs + DISP_REG_OVL_SRC_CON);
+	mtk_ddp_write(cmdq_pkt, gmc_value,
+		      comp, DISP_REG_OVL_RDMA_GMC(idx));
+	mtk_ddp_write_mask(cmdq_pkt, BIT(idx), comp,
+			   DISP_REG_OVL_SRC_CON, BIT(idx));
 }
 
-static void mtk_ovl_layer_off(struct mtk_ddp_comp *comp, unsigned int idx)
+static void mtk_ovl_layer_off(struct mtk_ddp_comp *comp, unsigned int idx,
+			      struct cmdq_pkt *cmdq_pkt)
 {
-	unsigned int reg;
-
-	reg = readl(comp->regs + DISP_REG_OVL_SRC_CON);
-	reg = reg & ~BIT(idx);
-	writel(reg, comp->regs + DISP_REG_OVL_SRC_CON);
-
-	writel(0x0, comp->regs + DISP_REG_OVL_RDMA_CTRL(idx));
+	mtk_ddp_write_mask(cmdq_pkt, 0, comp,
+			   DISP_REG_OVL_SRC_CON, BIT(idx));
+	mtk_ddp_write(cmdq_pkt, 0, comp,
+		      DISP_REG_OVL_RDMA_CTRL(idx));
 }
 
 static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt)
@@ -249,7 +248,8 @@ static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt)
 }
 
 static void mtk_ovl_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
-				 struct mtk_plane_state *state)
+				 struct mtk_plane_state *state,
+				 struct cmdq_pkt *cmdq_pkt)
 {
 	struct mtk_disp_ovl *ovl = comp_to_ovl(comp);
 	struct mtk_plane_pending_state *pending = &state->pending;
@@ -260,11 +260,13 @@ static void mtk_ovl_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
 	unsigned int src_size = (pending->height << 16) | pending->width;
 	unsigned int con;
 
-	if (!pending->enable)
-		mtk_ovl_layer_off(comp, idx);
+	if (!pending->enable) {
+		mtk_ovl_layer_off(comp, idx, cmdq_pkt);
+		return;
+	}
 
 	con = ovl_fmt_convert(ovl, fmt);
-	if (idx != 0)
+	if (state->base.fb->format->has_alpha)
 		con |= OVL_CON_AEN | OVL_CON_ALPHA;
 
 	if (pending->rotation & DRM_MODE_REFLECT_Y) {
@@ -277,14 +279,18 @@ static void mtk_ovl_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
 		addr += pending->pitch - 1;
 	}
 
-	writel_relaxed(con, comp->regs + DISP_REG_OVL_CON(idx));
-	writel_relaxed(pitch, comp->regs + DISP_REG_OVL_PITCH(idx));
-	writel_relaxed(src_size, comp->regs + DISP_REG_OVL_SRC_SIZE(idx));
-	writel_relaxed(offset, comp->regs + DISP_REG_OVL_OFFSET(idx));
-	writel_relaxed(addr, comp->regs + DISP_REG_OVL_ADDR(ovl, idx));
-
-	if (pending->enable)
-		mtk_ovl_layer_on(comp, idx);
+	mtk_ddp_write_relaxed(cmdq_pkt, con, comp,
+			      DISP_REG_OVL_CON(idx));
+	mtk_ddp_write_relaxed(cmdq_pkt, pitch, comp,
+			      DISP_REG_OVL_PITCH(idx));
+	mtk_ddp_write_relaxed(cmdq_pkt, src_size, comp,
+			      DISP_REG_OVL_SRC_SIZE(idx));
+	mtk_ddp_write_relaxed(cmdq_pkt, offset, comp,
+			      DISP_REG_OVL_OFFSET(idx));
+	mtk_ddp_write_relaxed(cmdq_pkt, addr, comp,
+			      DISP_REG_OVL_ADDR(ovl, idx));
+
+	mtk_ovl_layer_on(comp, idx, cmdq_pkt);
 }
 
 static void mtk_ovl_bgclr_in_on(struct mtk_ddp_comp *comp)
@@ -313,8 +319,6 @@ static const struct mtk_ddp_comp_funcs mtk_disp_ovl_funcs = {
 	.disable_vblank = mtk_ovl_disable_vblank,
 	.supported_rotations = mtk_ovl_supported_rotations,
 	.layer_nr = mtk_ovl_layer_nr,
-	.layer_on = mtk_ovl_layer_on,
-	.layer_off = mtk_ovl_layer_off,
 	.layer_check = mtk_ovl_layer_check,
 	.layer_config = mtk_ovl_layer_config,
 	.bgclr_in_on = mtk_ovl_bgclr_in_on,

drivers/gpu/drm/mediatek/mtk_disp_rdma.c

@@ -9,6 +9,7 @@
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
 
 #include "mtk_drm_crtc.h"
 #include "mtk_drm_ddp_comp.h"
@@ -125,14 +126,16 @@ static void mtk_rdma_stop(struct mtk_ddp_comp *comp)
 
 static void mtk_rdma_config(struct mtk_ddp_comp *comp, unsigned int width,
 			    unsigned int height, unsigned int vrefresh,
-			    unsigned int bpc)
+			    unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
 	unsigned int threshold;
 	unsigned int reg;
 	struct mtk_disp_rdma *rdma = comp_to_rdma(comp);
 
-	rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0, 0xfff, width);
-	rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_1, 0xfffff, height);
+	mtk_ddp_write_mask(cmdq_pkt, width, comp,
+			   DISP_REG_RDMA_SIZE_CON_0, 0xfff);
+	mtk_ddp_write_mask(cmdq_pkt, height, comp,
+			   DISP_REG_RDMA_SIZE_CON_1, 0xfffff);
 
 	/*
 	 * Enable FIFO underflow since DSI and DPI can't be blocked.
@@ -144,7 +147,7 @@ static void mtk_rdma_config(struct mtk_ddp_comp *comp, unsigned int width,
 	reg = RDMA_FIFO_UNDERFLOW_EN |
 	      RDMA_FIFO_PSEUDO_SIZE(RDMA_FIFO_SIZE(rdma)) |
 	      RDMA_OUTPUT_VALID_FIFO_THRESHOLD(threshold);
-	writel(reg, comp->regs + DISP_REG_RDMA_FIFO_CON);
+	mtk_ddp_write(cmdq_pkt, reg, comp, DISP_REG_RDMA_FIFO_CON);
 }
 
 static unsigned int rdma_fmt_convert(struct mtk_disp_rdma *rdma,
@@ -190,7 +193,8 @@ static unsigned int mtk_rdma_layer_nr(struct mtk_ddp_comp *comp)
 }
 
 static void mtk_rdma_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
-				  struct mtk_plane_state *state)
+				  struct mtk_plane_state *state,
+				  struct cmdq_pkt *cmdq_pkt)
 {
 	struct mtk_disp_rdma *rdma = comp_to_rdma(comp);
 	struct mtk_plane_pending_state *pending = &state->pending;
@@ -200,24 +204,27 @@ static void mtk_rdma_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
 	unsigned int con;
 
 	con = rdma_fmt_convert(rdma, fmt);
-	writel_relaxed(con, comp->regs + DISP_RDMA_MEM_CON);
+	mtk_ddp_write_relaxed(cmdq_pkt, con, comp, DISP_RDMA_MEM_CON);
 
 	if (fmt == DRM_FORMAT_UYVY || fmt == DRM_FORMAT_YUYV) {
-		rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0,
-				 RDMA_MATRIX_ENABLE, RDMA_MATRIX_ENABLE);
-		rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0,
-				 RDMA_MATRIX_INT_MTX_SEL,
-				 RDMA_MATRIX_INT_MTX_BT601_to_RGB);
+		mtk_ddp_write_mask(cmdq_pkt, RDMA_MATRIX_ENABLE, comp,
+				   DISP_REG_RDMA_SIZE_CON_0,
+				   RDMA_MATRIX_ENABLE);
+		mtk_ddp_write_mask(cmdq_pkt, RDMA_MATRIX_INT_MTX_BT601_to_RGB,
+				   comp, DISP_REG_RDMA_SIZE_CON_0,
+				   RDMA_MATRIX_INT_MTX_SEL);
 	} else {
-		rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0,
-				 RDMA_MATRIX_ENABLE, 0);
+		mtk_ddp_write_mask(cmdq_pkt, 0, comp,
+				   DISP_REG_RDMA_SIZE_CON_0,
+				   RDMA_MATRIX_ENABLE);
 	}
+	mtk_ddp_write_relaxed(cmdq_pkt, addr, comp, DISP_RDMA_MEM_START_ADDR);
+	mtk_ddp_write_relaxed(cmdq_pkt, pitch, comp, DISP_RDMA_MEM_SRC_PITCH);
+	mtk_ddp_write(cmdq_pkt, RDMA_MEM_GMC, comp,
+		      DISP_RDMA_MEM_GMC_SETTING_0);
+	mtk_ddp_write_mask(cmdq_pkt, RDMA_MODE_MEMORY, comp,
+			   DISP_REG_RDMA_GLOBAL_CON, RDMA_MODE_MEMORY);
 
-	writel_relaxed(addr, comp->regs + DISP_RDMA_MEM_START_ADDR);
-	writel_relaxed(pitch, comp->regs + DISP_RDMA_MEM_SRC_PITCH);
-	writel(RDMA_MEM_GMC, comp->regs + DISP_RDMA_MEM_GMC_SETTING_0);
-	rdma_update_bits(comp, DISP_REG_RDMA_GLOBAL_CON,
-			 RDMA_MODE_MEMORY, RDMA_MODE_MEMORY);
 }
 
 static const struct mtk_ddp_comp_funcs mtk_disp_rdma_funcs = {

drivers/gpu/drm/mediatek/mtk_drm_crtc.c

@@ -5,6 +5,7 @@
 
 #include <linux/clk.h>
 #include <linux/pm_runtime.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
 
 #include <asm/barrier.h>
 #include <soc/mediatek/smi.h>
@@ -42,11 +43,20 @@ struct mtk_drm_crtc {
 	struct drm_plane		*planes;
 	unsigned int			layer_nr;
 	bool				pending_planes;
+	bool				pending_async_planes;
+
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	struct cmdq_client		*cmdq_client;
+	u32				cmdq_event;
+#endif
 
 	void __iomem			*config_regs;
 	struct mtk_disp_mutex		*mutex;
 	unsigned int			ddp_comp_nr;
 	struct mtk_ddp_comp		**ddp_comp;
+
+	/* lock for display hardware access */
+	struct mutex			hw_lock;
 };
 
 struct mtk_crtc_state {
@@ -215,11 +225,12 @@ struct mtk_ddp_comp *mtk_drm_ddp_comp_for_plane(struct drm_crtc *crtc,
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
 	struct mtk_ddp_comp *comp;
 	int i, count = 0;
+	unsigned int local_index = plane - mtk_crtc->planes;
 
 	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
 		comp = mtk_crtc->ddp_comp[i];
-		if (plane->index < (count + mtk_ddp_comp_layer_nr(comp))) {
-			*local_layer = plane->index - count;
+		if (local_index < (count + mtk_ddp_comp_layer_nr(comp))) {
+			*local_layer = local_index - count;
 			return comp;
 		}
 		count += mtk_ddp_comp_layer_nr(comp);
@@ -229,6 +240,13 @@ struct mtk_ddp_comp *mtk_drm_ddp_comp_for_plane(struct drm_crtc *crtc,
 	return NULL;
 }
 
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+static void ddp_cmdq_cb(struct cmdq_cb_data data)
+{
+	cmdq_pkt_destroy(data.data);
+}
+#endif
+
 static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 {
 	struct drm_crtc *crtc = &mtk_crtc->base;
@@ -297,7 +315,7 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 		if (i == 1)
 			mtk_ddp_comp_bgclr_in_on(comp);
 
-		mtk_ddp_comp_config(comp, width, height, vrefresh, bpc);
+		mtk_ddp_comp_config(comp, width, height, vrefresh, bpc, NULL);
 		mtk_ddp_comp_start(comp);
 	}
 
@@ -310,7 +328,9 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 
 		plane_state = to_mtk_plane_state(plane->state);
 		comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer);
-		mtk_ddp_comp_layer_config(comp, local_layer, plane_state);
+		if (comp)
+			mtk_ddp_comp_layer_config(comp, local_layer,
+						  plane_state, NULL);
 	}
 
 	return 0;
@@ -325,6 +345,7 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc)
 {
 	struct drm_device *drm = mtk_crtc->base.dev;
+	struct drm_crtc *crtc = &mtk_crtc->base;
 	int i;
 
 	DRM_DEBUG_DRIVER("%s\n", __func__);
@@ -350,9 +371,17 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc)
 	mtk_disp_mutex_unprepare(mtk_crtc->mutex);
 
 	pm_runtime_put(drm->dev);
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		crtc->state->event = NULL;
+		spin_unlock_irq(&crtc->dev->event_lock);
+	}
 }
 
-static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
+static void mtk_crtc_ddp_config(struct drm_crtc *crtc,
+				struct cmdq_pkt *cmdq_handle)
 {
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
 	struct mtk_crtc_state *state = to_mtk_crtc_state(mtk_crtc->base.state);
@@ -368,7 +397,8 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
 	if (state->pending_config) {
 		mtk_ddp_comp_config(comp, state->pending_width,
 				    state->pending_height,
-				    state->pending_vrefresh, 0);
+				    state->pending_vrefresh, 0,
+				    cmdq_handle);
 
 		state->pending_config = false;
 	}
@@ -386,12 +416,84 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
 			comp = mtk_drm_ddp_comp_for_plane(crtc, plane,
 							  &local_layer);
 
-			mtk_ddp_comp_layer_config(comp, local_layer,
-						  plane_state);
+			if (comp)
+				mtk_ddp_comp_layer_config(comp, local_layer,
+							  plane_state,
+							  cmdq_handle);
 			plane_state->pending.config = false;
 		}
 		mtk_crtc->pending_planes = false;
 	}
+
+	if (mtk_crtc->pending_async_planes) {
+		for (i = 0; i < mtk_crtc->layer_nr; i++) {
+			struct drm_plane *plane = &mtk_crtc->planes[i];
+			struct mtk_plane_state *plane_state;
+
+			plane_state = to_mtk_plane_state(plane->state);
+
+			if (!plane_state->pending.async_config)
+				continue;
+
+			comp = mtk_drm_ddp_comp_for_plane(crtc, plane,
+							  &local_layer);
+
+			if (comp)
+				mtk_ddp_comp_layer_config(comp, local_layer,
+							  plane_state,
+							  cmdq_handle);
+			plane_state->pending.async_config = false;
+		}
+		mtk_crtc->pending_async_planes = false;
+	}
+}
+
+static void mtk_drm_crtc_hw_config(struct mtk_drm_crtc *mtk_crtc)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	struct cmdq_pkt *cmdq_handle;
+#endif
+	struct drm_crtc *crtc = &mtk_crtc->base;
+	struct mtk_drm_private *priv = crtc->dev->dev_private;
+	unsigned int pending_planes = 0, pending_async_planes = 0;
+	int i;
+
+	mutex_lock(&mtk_crtc->hw_lock);
+	for (i = 0; i < mtk_crtc->layer_nr; i++) {
+		struct drm_plane *plane = &mtk_crtc->planes[i];
+		struct mtk_plane_state *plane_state;
+
+		plane_state = to_mtk_plane_state(plane->state);
+		if (plane_state->pending.dirty) {
+			plane_state->pending.config = true;
+			plane_state->pending.dirty = false;
+			pending_planes |= BIT(i);
+		} else if (plane_state->pending.async_dirty) {
+			plane_state->pending.async_config = true;
+			plane_state->pending.async_dirty = false;
+			pending_async_planes |= BIT(i);
+		}
+	}
+	if (pending_planes)
+		mtk_crtc->pending_planes = true;
+	if (pending_async_planes)
+		mtk_crtc->pending_async_planes = true;
+
+	if (priv->data->shadow_register) {
+		mtk_disp_mutex_acquire(mtk_crtc->mutex);
+		mtk_crtc_ddp_config(crtc, NULL);
+		mtk_disp_mutex_release(mtk_crtc->mutex);
+	}
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (mtk_crtc->cmdq_client) {
+		cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE);
+		cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event);
+		cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event);
+		mtk_crtc_ddp_config(crtc, cmdq_handle);
+		cmdq_pkt_flush_async(cmdq_handle, ddp_cmdq_cb, cmdq_handle);
+	}
+#endif
+	mutex_unlock(&mtk_crtc->hw_lock);
 }
 
 int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
@@ -401,7 +503,23 @@ int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
 	struct mtk_ddp_comp *comp;
 
 	comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer);
-	return mtk_ddp_comp_layer_check(comp, local_layer, state);
+	if (comp)
+		return mtk_ddp_comp_layer_check(comp, local_layer, state);
+	return 0;
+}
+
+void mtk_drm_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane,
+			       struct drm_plane_state *new_state)
+{
+	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
+	const struct drm_plane_helper_funcs *plane_helper_funcs =
+			plane->helper_private;
+
+	if (!mtk_crtc->enabled)
+		return;
+
+	plane_helper_funcs->atomic_update(plane, new_state);
+	mtk_drm_crtc_hw_config(mtk_crtc);
 }
 
 static void mtk_drm_crtc_atomic_enable(struct drm_crtc *crtc,
@@ -451,6 +569,7 @@ static void mtk_drm_crtc_atomic_disable(struct drm_crtc *crtc,
 	}
 	mtk_crtc->pending_planes = true;
 
+	mtk_drm_crtc_hw_config(mtk_crtc);
 	/* Wait for planes to be disabled */
 	drm_crtc_wait_one_vblank(crtc);
 
@@ -482,34 +601,16 @@ static void mtk_drm_crtc_atomic_flush(struct drm_crtc *crtc,
 				      struct drm_crtc_state *old_crtc_state)
 {
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
-	struct mtk_drm_private *priv = crtc->dev->dev_private;
-	unsigned int pending_planes = 0;
 	int i;
 
 	if (mtk_crtc->event)
 		mtk_crtc->pending_needs_vblank = true;
-	for (i = 0; i < mtk_crtc->layer_nr; i++) {
-		struct drm_plane *plane = &mtk_crtc->planes[i];
-		struct mtk_plane_state *plane_state;
-
-		plane_state = to_mtk_plane_state(plane->state);
-		if (plane_state->pending.dirty) {
-			plane_state->pending.config = true;
-			plane_state->pending.dirty = false;
-			pending_planes |= BIT(i);
-		}
-	}
-	if (pending_planes)
-		mtk_crtc->pending_planes = true;
 	if (crtc->state->color_mgmt_changed)
-		for (i = 0; i < mtk_crtc->ddp_comp_nr; i++)
+		for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
 			mtk_ddp_gamma_set(mtk_crtc->ddp_comp[i], crtc->state);
-
-	if (priv->data->shadow_register) {
-		mtk_disp_mutex_acquire(mtk_crtc->mutex);
-		mtk_crtc_ddp_config(crtc);
-		mtk_disp_mutex_release(mtk_crtc->mutex);
-	}
+			mtk_ddp_ctm_set(mtk_crtc->ddp_comp[i], crtc->state);
+		}
+	mtk_drm_crtc_hw_config(mtk_crtc);
 }
 
 static const struct drm_crtc_funcs mtk_crtc_funcs = {
@@ -559,8 +660,12 @@ void mtk_crtc_ddp_irq(struct drm_crtc *crtc, struct mtk_ddp_comp *comp)
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
 	struct mtk_drm_private *priv = crtc->dev->dev_private;
 
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (!priv->data->shadow_register && !mtk_crtc->cmdq_client)
+#else
 	if (!priv->data->shadow_register)
-		mtk_crtc_ddp_config(crtc);
+#endif
+		mtk_crtc_ddp_config(crtc, NULL);
 
 	mtk_drm_finish_page_flip(mtk_crtc);
 }
@@ -627,6 +732,8 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	int pipe = priv->num_pipes;
 	int ret;
 	int i;
+	bool has_ctm = false;
+	uint gamma_lut_size = 0;
 
 	if (!path)
 		return 0;
@@ -677,6 +784,14 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 		}
 
 		mtk_crtc->ddp_comp[i] = comp;
+
+		if (comp->funcs) {
+			if (comp->funcs->gamma_set)
+				gamma_lut_size = MTK_LUT_SIZE;
+
+			if (comp->funcs->ctm_set)
+				has_ctm = true;
+		}
 	}
 
 	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++)
@@ -697,9 +812,28 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 				NULL, pipe);
 	if (ret < 0)
 		return ret;
-	drm_mode_crtc_set_gamma_size(&mtk_crtc->base, MTK_LUT_SIZE);
-	drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, false, MTK_LUT_SIZE);
-	priv->num_pipes++;
 
+	if (gamma_lut_size)
+		drm_mode_crtc_set_gamma_size(&mtk_crtc->base, gamma_lut_size);
+	drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, has_ctm, gamma_lut_size);
+	priv->num_pipes++;
+	mutex_init(&mtk_crtc->hw_lock);
+
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	mtk_crtc->cmdq_client =
+			cmdq_mbox_create(dev, drm_crtc_index(&mtk_crtc->base),
+					 2000);
+	if (IS_ERR(mtk_crtc->cmdq_client)) {
+		dev_dbg(dev, "mtk_crtc %d failed to create mailbox client, writing register by CPU now\n",
+			drm_crtc_index(&mtk_crtc->base));
+		mtk_crtc->cmdq_client = NULL;
+	}
+	ret = of_property_read_u32_index(dev->of_node, "mediatek,gce-events",
+					 drm_crtc_index(&mtk_crtc->base),
+					 &mtk_crtc->cmdq_event);
+	if (ret)
+		dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n",
+			drm_crtc_index(&mtk_crtc->base));
+#endif
 	return 0;
 }

drivers/gpu/drm/mediatek/mtk_drm_crtc.h

@@ -21,5 +21,7 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 			unsigned int path_len);
 int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
 			     struct mtk_plane_state *state);
+void mtk_drm_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane,
+			       struct drm_plane_state *plane_state);
 
 #endif /* MTK_DRM_CRTC_H */

drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c

@@ -12,7 +12,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
-
+#include <linux/soc/mediatek/mtk-cmdq.h>
 #include "mtk_drm_drv.h"
 #include "mtk_drm_plane.h"
 #include "mtk_drm_ddp_comp.h"
@@ -37,7 +37,15 @@
 #define CCORR_EN				BIT(0)
 #define DISP_CCORR_CFG				0x0020
 #define CCORR_RELAY_MODE			BIT(0)
+#define CCORR_ENGINE_EN				BIT(1)
+#define CCORR_GAMMA_OFF				BIT(2)
+#define CCORR_WGAMUT_SRC_CLIP			BIT(3)
 #define DISP_CCORR_SIZE				0x0030
+#define DISP_CCORR_COEF_0			0x0080
+#define DISP_CCORR_COEF_1			0x0084
+#define DISP_CCORR_COEF_2			0x0088
+#define DISP_CCORR_COEF_3			0x008C
+#define DISP_CCORR_COEF_4			0x0090
 
 #define DISP_DITHER_EN				0x0000
 #define DITHER_EN				BIT(0)
@@ -76,36 +84,84 @@
 #define DITHER_ADD_LSHIFT_G(x)			(((x) & 0x7) << 4)
 #define DITHER_ADD_RSHIFT_G(x)			(((x) & 0x7) << 0)
 
+void mtk_ddp_write(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+		   struct mtk_ddp_comp *comp, unsigned int offset)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (cmdq_pkt)
+		cmdq_pkt_write(cmdq_pkt, comp->subsys,
+			       comp->regs_pa + offset, value);
+	else
+#endif
+		writel(value, comp->regs + offset);
+}
+
+void mtk_ddp_write_relaxed(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+			   struct mtk_ddp_comp *comp,
+			   unsigned int offset)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (cmdq_pkt)
+		cmdq_pkt_write(cmdq_pkt, comp->subsys,
+			       comp->regs_pa + offset, value);
+	else
+#endif
+		writel_relaxed(value, comp->regs + offset);
+}
+
+void mtk_ddp_write_mask(struct cmdq_pkt *cmdq_pkt,
+			unsigned int value,
+			struct mtk_ddp_comp *comp,
+			unsigned int offset,
+			unsigned int mask)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (cmdq_pkt) {
+		cmdq_pkt_write_mask(cmdq_pkt, comp->subsys,
+				    comp->regs_pa + offset, value, mask);
+	} else {
+#endif
+		u32 tmp = readl(comp->regs + offset);
+
+		tmp = (tmp & ~mask) | (value & mask);
+		writel(tmp, comp->regs + offset);
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	}
+#endif
+}
+
 void mtk_dither_set(struct mtk_ddp_comp *comp, unsigned int bpc,
-		    unsigned int CFG)
+		    unsigned int CFG, struct cmdq_pkt *cmdq_pkt)
 {
 	/* If bpc equal to 0, the dithering function didn't be enabled */
 	if (bpc == 0)
 		return;
 
 	if (bpc >= MTK_MIN_BPC) {
-		writel(0, comp->regs + DISP_DITHER_5);
-		writel(0, comp->regs + DISP_DITHER_7);
-		writel(DITHER_LSB_ERR_SHIFT_R(MTK_MAX_BPC - bpc) |
-		       DITHER_ADD_LSHIFT_R(MTK_MAX_BPC - bpc) |
-		       DITHER_NEW_BIT_MODE,
-		       comp->regs + DISP_DITHER_15);
-		writel(DITHER_LSB_ERR_SHIFT_B(MTK_MAX_BPC - bpc) |
-		       DITHER_ADD_LSHIFT_B(MTK_MAX_BPC - bpc) |
-		       DITHER_LSB_ERR_SHIFT_G(MTK_MAX_BPC - bpc) |
-		       DITHER_ADD_LSHIFT_G(MTK_MAX_BPC - bpc),
-		       comp->regs + DISP_DITHER_16);
-		writel(DISP_DITHERING, comp->regs + CFG);
+		mtk_ddp_write(cmdq_pkt, 0, comp, DISP_DITHER_5);
+		mtk_ddp_write(cmdq_pkt, 0, comp, DISP_DITHER_7);
+		mtk_ddp_write(cmdq_pkt,
+			      DITHER_LSB_ERR_SHIFT_R(MTK_MAX_BPC - bpc) |
+			      DITHER_ADD_LSHIFT_R(MTK_MAX_BPC - bpc) |
+			      DITHER_NEW_BIT_MODE,
+			      comp, DISP_DITHER_15);
+		mtk_ddp_write(cmdq_pkt,
+			      DITHER_LSB_ERR_SHIFT_B(MTK_MAX_BPC - bpc) |
+			      DITHER_ADD_LSHIFT_B(MTK_MAX_BPC - bpc) |
+			      DITHER_LSB_ERR_SHIFT_G(MTK_MAX_BPC - bpc) |
+			      DITHER_ADD_LSHIFT_G(MTK_MAX_BPC - bpc),
+			      comp, DISP_DITHER_16);
+		mtk_ddp_write(cmdq_pkt, DISP_DITHERING, comp, CFG);
 	}
 }
 
 static void mtk_od_config(struct mtk_ddp_comp *comp, unsigned int w,
 			  unsigned int h, unsigned int vrefresh,
-			  unsigned int bpc)
+			  unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(w << 16 | h, comp->regs + DISP_OD_SIZE);
-	writel(OD_RELAYMODE, comp->regs + DISP_OD_CFG);
-	mtk_dither_set(comp, bpc, DISP_OD_CFG);
+	mtk_ddp_write(cmdq_pkt, w << 16 | h, comp, DISP_OD_SIZE);
+	mtk_ddp_write(cmdq_pkt, OD_RELAYMODE, comp, DISP_OD_CFG);
+	mtk_dither_set(comp, bpc, DISP_OD_CFG, cmdq_pkt);
 }
 
 static void mtk_od_start(struct mtk_ddp_comp *comp)
@@ -120,9 +176,9 @@ static void mtk_ufoe_start(struct mtk_ddp_comp *comp)
 
 static void mtk_aal_config(struct mtk_ddp_comp *comp, unsigned int w,
 			   unsigned int h, unsigned int vrefresh,
-			   unsigned int bpc)
+			   unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(h << 16 | w, comp->regs + DISP_AAL_SIZE);
+	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_AAL_SIZE);
 }
 
 static void mtk_aal_start(struct mtk_ddp_comp *comp)
@@ -137,10 +193,10 @@ static void mtk_aal_stop(struct mtk_ddp_comp *comp)
 
 static void mtk_ccorr_config(struct mtk_ddp_comp *comp, unsigned int w,
 			     unsigned int h, unsigned int vrefresh,
-			     unsigned int bpc)
+			     unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(h << 16 | w, comp->regs + DISP_CCORR_SIZE);
-	writel(CCORR_RELAY_MODE, comp->regs + DISP_CCORR_CFG);
+	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_CCORR_SIZE);
+	mtk_ddp_write(cmdq_pkt, CCORR_ENGINE_EN, comp, DISP_CCORR_CFG);
 }
 
 static void mtk_ccorr_start(struct mtk_ddp_comp *comp)
@@ -153,12 +209,63 @@ static void mtk_ccorr_stop(struct mtk_ddp_comp *comp)
 	writel_relaxed(0x0, comp->regs + DISP_CCORR_EN);
 }
 
+/* Converts a DRM S31.32 value to the HW S1.10 format. */
+static u16 mtk_ctm_s31_32_to_s1_10(u64 in)
+{
+	u16 r;
+
+	/* Sign bit. */
+	r = in & BIT_ULL(63) ? BIT(11) : 0;
+
+	if ((in & GENMASK_ULL(62, 33)) > 0) {
+		/* identity value 0x100000000 -> 0x400, */
+		/* if bigger this, set it to max 0x7ff. */
+		r |= GENMASK(10, 0);
+	} else {
+		/* take the 11 most important bits. */
+		r |= (in >> 22) & GENMASK(10, 0);
+	}
+
+	return r;
+}
+
+static void mtk_ccorr_ctm_set(struct mtk_ddp_comp *comp,
+			      struct drm_crtc_state *state)
+{
+	struct drm_property_blob *blob = state->ctm;
+	struct drm_color_ctm *ctm;
+	const u64 *input;
+	uint16_t coeffs[9] = { 0 };
+	int i;
+	struct cmdq_pkt *cmdq_pkt = NULL;
+
+	if (!blob)
+		return;
+
+	ctm = (struct drm_color_ctm *)blob->data;
+	input = ctm->matrix;
+
+	for (i = 0; i < ARRAY_SIZE(coeffs); i++)
+		coeffs[i] = mtk_ctm_s31_32_to_s1_10(input[i]);
+
+	mtk_ddp_write(cmdq_pkt, coeffs[0] << 16 | coeffs[1],
+		      comp, DISP_CCORR_COEF_0);
+	mtk_ddp_write(cmdq_pkt, coeffs[2] << 16 | coeffs[3],
+		      comp, DISP_CCORR_COEF_1);
+	mtk_ddp_write(cmdq_pkt, coeffs[4] << 16 | coeffs[5],
+		      comp, DISP_CCORR_COEF_2);
+	mtk_ddp_write(cmdq_pkt, coeffs[6] << 16 | coeffs[7],
+		      comp, DISP_CCORR_COEF_3);
+	mtk_ddp_write(cmdq_pkt, coeffs[8] << 16,
+		      comp, DISP_CCORR_COEF_4);
+}
+
 static void mtk_dither_config(struct mtk_ddp_comp *comp, unsigned int w,
 			      unsigned int h, unsigned int vrefresh,
-			      unsigned int bpc)
+			      unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(h << 16 | w, comp->regs + DISP_DITHER_SIZE);
-	writel(DITHER_RELAY_MODE, comp->regs + DISP_DITHER_CFG);
+	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_DITHER_SIZE);
+	mtk_ddp_write(cmdq_pkt, DITHER_RELAY_MODE, comp, DISP_DITHER_CFG);
 }
 
 static void mtk_dither_start(struct mtk_ddp_comp *comp)
@@ -173,10 +280,10 @@ static void mtk_dither_stop(struct mtk_ddp_comp *comp)
 
 static void mtk_gamma_config(struct mtk_ddp_comp *comp, unsigned int w,
 			     unsigned int h, unsigned int vrefresh,
-			     unsigned int bpc)
+			     unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(h << 16 | w, comp->regs + DISP_GAMMA_SIZE);
-	mtk_dither_set(comp, bpc, DISP_GAMMA_CFG);
+	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_GAMMA_SIZE);
+	mtk_dither_set(comp, bpc, DISP_GAMMA_CFG, cmdq_pkt);
 }
 
 static void mtk_gamma_start(struct mtk_ddp_comp *comp)
@@ -223,6 +330,7 @@ static const struct mtk_ddp_comp_funcs ddp_ccorr = {
 	.config = mtk_ccorr_config,
 	.start = mtk_ccorr_start,
 	.stop = mtk_ccorr_stop,
+	.ctm_set = mtk_ccorr_ctm_set,
 };
 
 static const struct mtk_ddp_comp_funcs ddp_dither = {
@@ -326,6 +434,11 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 	enum mtk_ddp_comp_type type;
 	struct device_node *larb_node;
 	struct platform_device *larb_pdev;
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	struct resource res;
+	struct cmdq_client_reg cmdq_reg;
+	int ret;
+#endif
 
 	if (comp_id < 0 || comp_id >= DDP_COMPONENT_ID_MAX)
 		return -EINVAL;
@@ -379,6 +492,19 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 
 	comp->larb_dev = &larb_pdev->dev;
 
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (of_address_to_resource(node, 0, &res) != 0) {
+		dev_err(dev, "Missing reg in %s node\n", node->full_name);
+		return -EINVAL;
+	}
+	comp->regs_pa = res.start;
+
+	ret = cmdq_dev_get_client_reg(dev, &cmdq_reg, 0);
+	if (ret)
+		dev_dbg(dev, "get mediatek,gce-client-reg fail!\n");
+	else
+		comp->subsys = cmdq_reg.subsys;
+#endif
 	return 0;
 }
 

drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h

@@ -69,27 +69,29 @@ enum mtk_ddp_comp_id {
 };
 
 struct mtk_ddp_comp;
-
+struct cmdq_pkt;
 struct mtk_ddp_comp_funcs {
 	void (*config)(struct mtk_ddp_comp *comp, unsigned int w,
-		       unsigned int h, unsigned int vrefresh, unsigned int bpc);
+		       unsigned int h, unsigned int vrefresh,
+		       unsigned int bpc, struct cmdq_pkt *cmdq_pkt);
 	void (*start)(struct mtk_ddp_comp *comp);
 	void (*stop)(struct mtk_ddp_comp *comp);
 	void (*enable_vblank)(struct mtk_ddp_comp *comp, struct drm_crtc *crtc);
 	void (*disable_vblank)(struct mtk_ddp_comp *comp);
 	unsigned int (*supported_rotations)(struct mtk_ddp_comp *comp);
 	unsigned int (*layer_nr)(struct mtk_ddp_comp *comp);
-	void (*layer_on)(struct mtk_ddp_comp *comp, unsigned int idx);
-	void (*layer_off)(struct mtk_ddp_comp *comp, unsigned int idx);
 	int (*layer_check)(struct mtk_ddp_comp *comp,
 			   unsigned int idx,
 			   struct mtk_plane_state *state);
 	void (*layer_config)(struct mtk_ddp_comp *comp, unsigned int idx,
-			     struct mtk_plane_state *state);
+			     struct mtk_plane_state *state,
+			     struct cmdq_pkt *cmdq_pkt);
 	void (*gamma_set)(struct mtk_ddp_comp *comp,
 			  struct drm_crtc_state *state);
 	void (*bgclr_in_on)(struct mtk_ddp_comp *comp);
 	void (*bgclr_in_off)(struct mtk_ddp_comp *comp);
+	void (*ctm_set)(struct mtk_ddp_comp *comp,
+			struct drm_crtc_state *state);
 };
 
 struct mtk_ddp_comp {
@@ -99,14 +101,17 @@ struct mtk_ddp_comp {
 	struct device *larb_dev;
 	enum mtk_ddp_comp_id id;
 	const struct mtk_ddp_comp_funcs *funcs;
+	resource_size_t regs_pa;
+	u8 subsys;
 };
 
 static inline void mtk_ddp_comp_config(struct mtk_ddp_comp *comp,
 				       unsigned int w, unsigned int h,
-				       unsigned int vrefresh, unsigned int bpc)
+				       unsigned int vrefresh, unsigned int bpc,
+				       struct cmdq_pkt *cmdq_pkt)
 {
 	if (comp->funcs && comp->funcs->config)
-		comp->funcs->config(comp, w, h, vrefresh, bpc);
+		comp->funcs->config(comp, w, h, vrefresh, bpc, cmdq_pkt);
 }
 
 static inline void mtk_ddp_comp_start(struct mtk_ddp_comp *comp)
@@ -151,20 +156,6 @@ static inline unsigned int mtk_ddp_comp_layer_nr(struct mtk_ddp_comp *comp)
 	return 0;
 }
 
-static inline void mtk_ddp_comp_layer_on(struct mtk_ddp_comp *comp,
-					 unsigned int idx)
-{
-	if (comp->funcs && comp->funcs->layer_on)
-		comp->funcs->layer_on(comp, idx);
-}
-
-static inline void mtk_ddp_comp_layer_off(struct mtk_ddp_comp *comp,
-					  unsigned int idx)
-{
-	if (comp->funcs && comp->funcs->layer_off)
-		comp->funcs->layer_off(comp, idx);
-}
-
 static inline int mtk_ddp_comp_layer_check(struct mtk_ddp_comp *comp,
 					   unsigned int idx,
 					   struct mtk_plane_state *state)
@@ -176,10 +167,11 @@ static inline int mtk_ddp_comp_layer_check(struct mtk_ddp_comp *comp,
 
 static inline void mtk_ddp_comp_layer_config(struct mtk_ddp_comp *comp,
 					     unsigned int idx,
-					     struct mtk_plane_state *state)
+					     struct mtk_plane_state *state,
+					     struct cmdq_pkt *cmdq_pkt)
 {
 	if (comp->funcs && comp->funcs->layer_config)
-		comp->funcs->layer_config(comp, idx, state);
+		comp->funcs->layer_config(comp, idx, state, cmdq_pkt);
 }
 
 static inline void mtk_ddp_gamma_set(struct mtk_ddp_comp *comp,
@@ -201,6 +193,13 @@ static inline void mtk_ddp_comp_bgclr_in_off(struct mtk_ddp_comp *comp)
 		comp->funcs->bgclr_in_off(comp);
 }
 
+static inline void mtk_ddp_ctm_set(struct mtk_ddp_comp *comp,
+				   struct drm_crtc_state *state)
+{
+	if (comp->funcs && comp->funcs->ctm_set)
+		comp->funcs->ctm_set(comp, state);
+}
+
 int mtk_ddp_comp_get_id(struct device_node *node,
 			enum mtk_ddp_comp_type comp_type);
 int mtk_ddp_comp_init(struct device *dev, struct device_node *comp_node,
@@ -209,6 +208,13 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *comp_node,
 int mtk_ddp_comp_register(struct drm_device *drm, struct mtk_ddp_comp *comp);
 void mtk_ddp_comp_unregister(struct drm_device *drm, struct mtk_ddp_comp *comp);
 void mtk_dither_set(struct mtk_ddp_comp *comp, unsigned int bpc,
-		    unsigned int CFG);
-
+		    unsigned int CFG, struct cmdq_pkt *cmdq_pkt);
+enum mtk_ddp_comp_type mtk_ddp_comp_get_type(enum mtk_ddp_comp_id comp_id);
+void mtk_ddp_write(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+		   struct mtk_ddp_comp *comp, unsigned int offset);
+void mtk_ddp_write_relaxed(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+			   struct mtk_ddp_comp *comp, unsigned int offset);
+void mtk_ddp_write_mask(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+			struct mtk_ddp_comp *comp, unsigned int offset,
+			unsigned int mask);
 #endif /* MTK_DRM_DDP_COMP_H */

drivers/gpu/drm/mediatek/mtk_drm_drv.c

@@ -37,84 +37,9 @@
 #define DRIVER_MAJOR 1
 #define DRIVER_MINOR 0
 
-static void mtk_atomic_schedule(struct mtk_drm_private *private,
-				struct drm_atomic_state *state)
-{
-	private->commit.state = state;
-	schedule_work(&private->commit.work);
-}
-
-static void mtk_atomic_complete(struct mtk_drm_private *private,
-				struct drm_atomic_state *state)
-{
-	struct drm_device *drm = private->drm;
-
-	drm_atomic_helper_wait_for_fences(drm, state, false);
-
-	/*
-	 * Mediatek drm supports runtime PM, so plane registers cannot be
-	 * written when their crtc is disabled.
-	 *
-	 * The comment for drm_atomic_helper_commit states:
-	 *     For drivers supporting runtime PM the recommended sequence is
-	 *
-	 *     drm_atomic_helper_commit_modeset_disables(dev, state);
-	 *     drm_atomic_helper_commit_modeset_enables(dev, state);
-	 *     drm_atomic_helper_commit_planes(dev, state,
-	 *                                     DRM_PLANE_COMMIT_ACTIVE_ONLY);
-	 *
-	 * See the kerneldoc entries for these three functions for more details.
-	 */
-	drm_atomic_helper_commit_modeset_disables(drm, state);
-	drm_atomic_helper_commit_modeset_enables(drm, state);
-	drm_atomic_helper_commit_planes(drm, state,
-					DRM_PLANE_COMMIT_ACTIVE_ONLY);
-
-	drm_atomic_helper_wait_for_vblanks(drm, state);
-
-	drm_atomic_helper_cleanup_planes(drm, state);
-	drm_atomic_state_put(state);
-}
-
-static void mtk_atomic_work(struct work_struct *work)
-{
-	struct mtk_drm_private *private = container_of(work,
-			struct mtk_drm_private, commit.work);
-
-	mtk_atomic_complete(private, private->commit.state);
-}
-
-static int mtk_atomic_commit(struct drm_device *drm,
-			     struct drm_atomic_state *state,
-			     bool async)
-{
-	struct mtk_drm_private *private = drm->dev_private;
-	int ret;
-
-	ret = drm_atomic_helper_prepare_planes(drm, state);
-	if (ret)
-		return ret;
-
-	mutex_lock(&private->commit.lock);
-	flush_work(&private->commit.work);
-
-	ret = drm_atomic_helper_swap_state(state, true);
-	if (ret) {
-		mutex_unlock(&private->commit.lock);
-		drm_atomic_helper_cleanup_planes(drm, state);
-		return ret;
-	}
-
-	drm_atomic_state_get(state);
-	if (async)
-		mtk_atomic_schedule(private, state);
-	else
-		mtk_atomic_complete(private, state);
-
-	mutex_unlock(&private->commit.lock);
-
-	return 0;
-}
+static const struct drm_mode_config_helper_funcs mtk_drm_mode_config_helpers = {
+	.atomic_commit_tail = drm_atomic_helper_commit_tail_rpm,
+};
 
 static struct drm_framebuffer *
 mtk_drm_mode_fb_create(struct drm_device *dev,
@@ -132,7 +57,7 @@ mtk_drm_mode_fb_create(struct drm_device *dev,
 static const struct drm_mode_config_funcs mtk_drm_mode_config_funcs = {
 	.fb_create = mtk_drm_mode_fb_create,
 	.atomic_check = drm_atomic_helper_check,
-	.atomic_commit = mtk_atomic_commit,
+	.atomic_commit = drm_atomic_helper_commit,
 };
 
 static const enum mtk_ddp_comp_id mt2701_mtk_ddp_main[] = {
@@ -250,6 +175,7 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 	drm->mode_config.max_width = 4096;
 	drm->mode_config.max_height = 4096;
 	drm->mode_config.funcs = &mtk_drm_mode_config_funcs;
+	drm->mode_config.helper_private = &mtk_drm_mode_config_helpers;
 
 	ret = component_bind_all(drm->dev, drm);
 	if (ret)
@@ -509,8 +435,6 @@ static int mtk_drm_probe(struct platform_device *pdev)
 	if (!private)
 		return -ENOMEM;
 
-	mutex_init(&private->commit.lock);
-	INIT_WORK(&private->commit.work, mtk_atomic_work);
 	private->data = of_device_get_match_data(dev);
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);

drivers/gpu/drm/mediatek/mtk_drm_drv.h

@@ -43,13 +43,6 @@ struct mtk_drm_private {
 	struct device_node *comp_node[DDP_COMPONENT_ID_MAX];
 	struct mtk_ddp_comp *ddp_comp[DDP_COMPONENT_ID_MAX];
 	const struct mtk_mmsys_driver_data *data;
-
-	struct {
-		struct drm_atomic_state *state;
-		struct work_struct work;
-		struct mutex lock;
-	} commit;
-
 	struct drm_atomic_state *suspend_state;
 
 	bool dma_parms_allocated;

drivers/gpu/drm/mediatek/mtk_drm_plane.c

@@ -7,6 +7,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_fourcc.h>
+#include <drm/drm_atomic_uapi.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 
@@ -75,6 +76,50 @@ static void mtk_drm_plane_destroy_state(struct drm_plane *plane,
 	kfree(to_mtk_plane_state(state));
 }
 
+static int mtk_plane_atomic_async_check(struct drm_plane *plane,
+					struct drm_plane_state *state)
+{
+	struct drm_crtc_state *crtc_state;
+
+	if (plane != state->crtc->cursor)
+		return -EINVAL;
+
+	if (!plane->state)
+		return -EINVAL;
+
+	if (!plane->state->fb)
+		return -EINVAL;
+
+	if (state->state)
+		crtc_state = drm_atomic_get_existing_crtc_state(state->state,
+								state->crtc);
+	else /* Special case for asynchronous cursor updates. */
+		crtc_state = state->crtc->state;
+
+	return drm_atomic_helper_check_plane_state(plane->state, crtc_state,
+						   DRM_PLANE_HELPER_NO_SCALING,
+						   DRM_PLANE_HELPER_NO_SCALING,
+						   true, true);
+}
+
+static void mtk_plane_atomic_async_update(struct drm_plane *plane,
+					  struct drm_plane_state *new_state)
+{
+	struct mtk_plane_state *state = to_mtk_plane_state(plane->state);
+
+	plane->state->crtc_x = new_state->crtc_x;
+	plane->state->crtc_y = new_state->crtc_y;
+	plane->state->crtc_h = new_state->crtc_h;
+	plane->state->crtc_w = new_state->crtc_w;
+	plane->state->src_x = new_state->src_x;
+	plane->state->src_y = new_state->src_y;
+	plane->state->src_h = new_state->src_h;
+	plane->state->src_w = new_state->src_w;
+	state->pending.async_dirty = true;
+
+	mtk_drm_crtc_async_update(new_state->crtc, plane, new_state);
+}
+
 static const struct drm_plane_funcs mtk_plane_funcs = {
 	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
@@ -163,6 +208,8 @@ static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = {
 	.atomic_check = mtk_plane_atomic_check,
 	.atomic_update = mtk_plane_atomic_update,
 	.atomic_disable = mtk_plane_atomic_disable,
+	.atomic_async_update = mtk_plane_atomic_async_update,
+	.atomic_async_check = mtk_plane_atomic_async_check,
 };
 
 int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,

drivers/gpu/drm/mediatek/mtk_drm_plane.h

@@ -22,6 +22,8 @@ struct mtk_plane_pending_state {
 	unsigned int			height;
 	unsigned int			rotation;
 	bool				dirty;
+	bool				async_dirty;
+	bool				async_config;
 };
 
 struct mtk_plane_state {

drivers/soc/mediatek/mtk-cmdq-helper.c

@@ -9,12 +9,54 @@
 #include <linux/mailbox_controller.h>
 #include <linux/soc/mediatek/mtk-cmdq.h>
 
-#define CMDQ_ARG_A_WRITE_MASK	0xffff
 #define CMDQ_WRITE_ENABLE_MASK	BIT(0)
+#define CMDQ_POLL_ENABLE_MASK	BIT(0)
 #define CMDQ_EOC_IRQ_EN		BIT(0)
 #define CMDQ_EOC_CMD		((u64)((CMDQ_CODE_EOC << CMDQ_OP_CODE_SHIFT)) \
 				<< 32 | CMDQ_EOC_IRQ_EN)
 
+struct cmdq_instruction {
+	union {
+		u32 value;
+		u32 mask;
+	};
+	union {
+		u16 offset;
+		u16 event;
+	};
+	u8 subsys;
+	u8 op;
+};
+
+int cmdq_dev_get_client_reg(struct device *dev,
+			    struct cmdq_client_reg *client_reg, int idx)
+{
+	struct of_phandle_args spec;
+	int err;
+
+	if (!client_reg)
+		return -ENOENT;
+
+	err = of_parse_phandle_with_fixed_args(dev->of_node,
+					       "mediatek,gce-client-reg",
+					       3, idx, &spec);
+	if (err < 0) {
+		dev_err(dev,
+			"error %d can't parse gce-client-reg property (%d)",
+			err, idx);
+
+		return err;
+	}
+
+	client_reg->subsys = (u8)spec.args[0];
+	client_reg->offset = (u16)spec.args[1];
+	client_reg->size = (u16)spec.args[2];
+	of_node_put(spec.np);
+
+	return 0;
+}
+EXPORT_SYMBOL(cmdq_dev_get_client_reg);
+
 static void cmdq_client_timeout(struct timer_list *t)
 {
 	struct cmdq_client *client = from_timer(client, t, timer);
@@ -110,10 +152,10 @@ void cmdq_pkt_destroy(struct cmdq_pkt *pkt)
 }
 EXPORT_SYMBOL(cmdq_pkt_destroy);
 
-static int cmdq_pkt_append_command(struct cmdq_pkt *pkt, enum cmdq_code code,
-				   u32 arg_a, u32 arg_b)
+static int cmdq_pkt_append_command(struct cmdq_pkt *pkt,
+				   struct cmdq_instruction inst)
 {
-	u64 *cmd_ptr;
+	struct cmdq_instruction *cmd_ptr;
 
 	if (unlikely(pkt->cmd_buf_size + CMDQ_INST_SIZE > pkt->buf_size)) {
 		/*
@@ -129,8 +171,9 @@ static int cmdq_pkt_append_command(struct cmdq_pkt *pkt, enum cmdq_code code,
 			__func__, (u32)pkt->buf_size);
 		return -ENOMEM;
 	}
+
 	cmd_ptr = pkt->va_base + pkt->cmd_buf_size;
-	(*cmd_ptr) = (u64)((code << CMDQ_OP_CODE_SHIFT) | arg_a) << 32 | arg_b;
+	*cmd_ptr = inst;
 	pkt->cmd_buf_size += CMDQ_INST_SIZE;
 
 	return 0;
@@ -138,24 +181,34 @@ static int cmdq_pkt_append_command(struct cmdq_pkt *pkt, enum cmdq_code code,
 
 int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value)
 {
-	u32 arg_a = (offset & CMDQ_ARG_A_WRITE_MASK) |
-		    (subsys << CMDQ_SUBSYS_SHIFT);
+	struct cmdq_instruction inst;
 
-	return cmdq_pkt_append_command(pkt, CMDQ_CODE_WRITE, arg_a, value);
+	inst.op = CMDQ_CODE_WRITE;
+	inst.value = value;
+	inst.offset = offset;
+	inst.subsys = subsys;
+
+	return cmdq_pkt_append_command(pkt, inst);
 }
 EXPORT_SYMBOL(cmdq_pkt_write);
 
 int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys,
 			u16 offset, u32 value, u32 mask)
 {
-	u32 offset_mask = offset;
-	int err = 0;
+	struct cmdq_instruction inst = { {0} };
+	u16 offset_mask = offset;
+	int err;
 
 	if (mask != 0xffffffff) {
-		err = cmdq_pkt_append_command(pkt, CMDQ_CODE_MASK, 0, ~mask);
+		inst.op = CMDQ_CODE_MASK;
+		inst.mask = ~mask;
+		err = cmdq_pkt_append_command(pkt, inst);
+		if (err < 0)
+			return err;
+
 		offset_mask |= CMDQ_WRITE_ENABLE_MASK;
 	}
-	err |= cmdq_pkt_write(pkt, subsys, offset_mask, value);
+	err = cmdq_pkt_write(pkt, subsys, offset_mask, value);
 
 	return err;
 }
@@ -163,43 +216,85 @@ EXPORT_SYMBOL(cmdq_pkt_write_mask);
 
 int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event)
 {
-	u32 arg_b;
+	struct cmdq_instruction inst = { {0} };
 
 	if (event >= CMDQ_MAX_EVENT)
 		return -EINVAL;
 
-	/*
-	 * WFE arg_b
-	 * bit 0-11: wait value
-	 * bit 15: 1 - wait, 0 - no wait
-	 * bit 16-27: update value
-	 * bit 31: 1 - update, 0 - no update
-	 */
-	arg_b = CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | CMDQ_WFE_WAIT_VALUE;
+	inst.op = CMDQ_CODE_WFE;
+	inst.value = CMDQ_WFE_OPTION;
+	inst.event = event;
 
-	return cmdq_pkt_append_command(pkt, CMDQ_CODE_WFE, event, arg_b);
+	return cmdq_pkt_append_command(pkt, inst);
 }
 EXPORT_SYMBOL(cmdq_pkt_wfe);
 
 int cmdq_pkt_clear_event(struct cmdq_pkt *pkt, u16 event)
 {
+	struct cmdq_instruction inst = { {0} };
+
 	if (event >= CMDQ_MAX_EVENT)
 		return -EINVAL;
 
-	return cmdq_pkt_append_command(pkt, CMDQ_CODE_WFE, event,
-				       CMDQ_WFE_UPDATE);
+	inst.op = CMDQ_CODE_WFE;
+	inst.value = CMDQ_WFE_UPDATE;
+	inst.event = event;
+
+	return cmdq_pkt_append_command(pkt, inst);
 }
 EXPORT_SYMBOL(cmdq_pkt_clear_event);
 
+int cmdq_pkt_poll(struct cmdq_pkt *pkt, u8 subsys,
+		  u16 offset, u32 value)
+{
+	struct cmdq_instruction inst = { {0} };
+	int err;
+
+	inst.op = CMDQ_CODE_POLL;
+	inst.value = value;
+	inst.offset = offset;
+	inst.subsys = subsys;
+	err = cmdq_pkt_append_command(pkt, inst);
+
+	return err;
+}
+EXPORT_SYMBOL(cmdq_pkt_poll);
+
+int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys,
+		       u16 offset, u32 value, u32 mask)
+{
+	struct cmdq_instruction inst = { {0} };
+	int err;
+
+	inst.op = CMDQ_CODE_MASK;
+	inst.mask = ~mask;
+	err = cmdq_pkt_append_command(pkt, inst);
+	if (err < 0)
+		return err;
+
+	offset = offset | CMDQ_POLL_ENABLE_MASK;
+	err = cmdq_pkt_poll(pkt, subsys, offset, value);
+
+	return err;
+}
+EXPORT_SYMBOL(cmdq_pkt_poll_mask);
+
 static int cmdq_pkt_finalize(struct cmdq_pkt *pkt)
 {
+	struct cmdq_instruction inst = { {0} };
 	int err;
 
 	/* insert EOC and generate IRQ for each command iteration */
-	err = cmdq_pkt_append_command(pkt, CMDQ_CODE_EOC, 0, CMDQ_EOC_IRQ_EN);
+	inst.op = CMDQ_CODE_EOC;
+	inst.value = CMDQ_EOC_IRQ_EN;
+	err = cmdq_pkt_append_command(pkt, inst);
+	if (err < 0)
+		return err;
 
 	/* JUMP to end */
-	err |= cmdq_pkt_append_command(pkt, CMDQ_CODE_JUMP, 0, CMDQ_JUMP_PASS);
+	inst.op = CMDQ_CODE_JUMP;
+	inst.value = CMDQ_JUMP_PASS;
+	err = cmdq_pkt_append_command(pkt, inst);
 
 	return err;
 }

include/linux/mailbox/mtk-cmdq-mailbox.h

@@ -20,6 +20,16 @@
 #define CMDQ_WFE_WAIT			BIT(15)
 #define CMDQ_WFE_WAIT_VALUE		0x1
 
+/*
+ * WFE arg_b
+ * bit 0-11: wait value
+ * bit 15: 1 - wait, 0 - no wait
+ * bit 16-27: update value
+ * bit 31: 1 - update, 0 - no update
+ */
+#define CMDQ_WFE_OPTION			(CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | \
+					CMDQ_WFE_WAIT_VALUE)
+
 /** cmdq event maximum */
 #define CMDQ_MAX_EVENT			0x3ff
 
@@ -45,6 +55,7 @@
 enum cmdq_code {
 	CMDQ_CODE_MASK = 0x02,
 	CMDQ_CODE_WRITE = 0x04,
+	CMDQ_CODE_POLL = 0x08,
 	CMDQ_CODE_JUMP = 0x10,
 	CMDQ_CODE_WFE = 0x20,
 	CMDQ_CODE_EOC = 0x40,

include/linux/soc/mediatek/mtk-cmdq.h

@@ -15,6 +15,12 @@
 
 struct cmdq_pkt;
 
+struct cmdq_client_reg {
+	u8 subsys;
+	u16 offset;
+	u16 size;
+};
+
 struct cmdq_client {
 	spinlock_t lock;
 	u32 pkt_cnt;
@@ -24,6 +30,21 @@ struct cmdq_client {
 	u32 timeout_ms; /* in unit of microsecond */
 };
 
+/**
+ * cmdq_dev_get_client_reg() - parse cmdq client reg from the device
+ *			       node of CMDQ client
+ * @dev:	device of CMDQ mailbox client
+ * @client_reg: CMDQ client reg pointer
+ * @idx:	the index of desired reg
+ *
+ * Return: 0 for success; else the error code is returned
+ *
+ * Help CMDQ client parsing the cmdq client reg
+ * from the device node of CMDQ client.
+ */
+int cmdq_dev_get_client_reg(struct device *dev,
+			    struct cmdq_client_reg *client_reg, int idx);
+
 /**
  * cmdq_mbox_create() - create CMDQ mailbox client and channel
  * @dev:	device of CMDQ mailbox client
@@ -99,6 +120,38 @@ int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event);
  */
 int cmdq_pkt_clear_event(struct cmdq_pkt *pkt, u16 event);
 
+/**
+ * cmdq_pkt_poll() - Append polling command to the CMDQ packet, ask GCE to
+ *		     execute an instruction that wait for a specified
+ *		     hardware register to check for the value w/o mask.
+ *		     All GCE hardware threads will be blocked by this
+ *		     instruction.
+ * @pkt:	the CMDQ packet
+ * @subsys:	the CMDQ sub system code
+ * @offset:	register offset from CMDQ sub system
+ * @value:	the specified target register value
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_poll(struct cmdq_pkt *pkt, u8 subsys,
+		  u16 offset, u32 value);
+
+/**
+ * cmdq_pkt_poll_mask() - Append polling command to the CMDQ packet, ask GCE to
+ *		          execute an instruction that wait for a specified
+ *		          hardware register to check for the value w/ mask.
+ *		          All GCE hardware threads will be blocked by this
+ *		          instruction.
+ * @pkt:	the CMDQ packet
+ * @subsys:	the CMDQ sub system code
+ * @offset:	register offset from CMDQ sub system
+ * @value:	the specified target register value
+ * @mask:	the specified target register mask
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys,
+		       u16 offset, u32 value, u32 mask);
 /**
  * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ
  *                          packet and call back at the end of done packet