1 files changed, 287 insertions, 187 deletions

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 48e6e8d74c85..862e9e6bf0a5 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -2,7 +2,7 @@
 /*
  * Copyright (C) 2013 Red Hat
  * Copyright (c) 2014-2018, 2020-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved.
  *
  * Author: Rob Clark <robdclark@gmail.com>
  */
@@ -24,6 +24,7 @@
 #include "dpu_hw_catalog.h"
 #include "dpu_hw_intf.h"
 #include "dpu_hw_ctl.h"
+#include "dpu_hw_cwb.h"
 #include "dpu_hw_dspp.h"
 #include "dpu_hw_dsc.h"
 #include "dpu_hw_merge3d.h"
@@ -58,8 +59,6 @@
 
 #define IDLE_SHORT_TIMEOUT	1
 
-#define MAX_HDISPLAY_SPLIT 1080
-
 /* timeout in frames waiting for frame done */
 #define DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES 5
 
@@ -135,8 +134,12 @@ enum dpu_enc_rc_states {
  * @cur_slave:		As above but for the slave encoder.
  * @hw_pp:		Handle to the pingpong blocks used for the display. No.
  *			pingpong blocks can be different than num_phys_encs.
+ * @hw_cwb:		Handle to the CWB muxes used for concurrent writeback
+ *			display. Number of CWB muxes can be different than
+ *			num_phys_encs.
  * @hw_dsc:		Handle to the DSC blocks used for the display.
  * @dsc_mask:		Bitmask of used DSC blocks.
+ * @cwb_mask:		Bitmask of used CWB muxes
  * @intfs_swapped:	Whether or not the phys_enc interfaces have been swapped
  *			for partial update right-only cases, such as pingpong
  *			split where virtual pingpong does not generate IRQs
@@ -179,9 +182,11 @@ struct dpu_encoder_virt {
 	struct dpu_encoder_phys *cur_master;
 	struct dpu_encoder_phys *cur_slave;
 	struct dpu_hw_pingpong *hw_pp[MAX_CHANNELS_PER_ENC];
+	struct dpu_hw_cwb *hw_cwb[MAX_CHANNELS_PER_ENC];
 	struct dpu_hw_dsc *hw_dsc[MAX_CHANNELS_PER_ENC];
 
 	unsigned int dsc_mask;
+	unsigned int cwb_mask;
 
 	bool intfs_swapped;
 
@@ -622,9 +627,9 @@ bool dpu_encoder_use_dsc_merge(struct drm_encoder *drm_enc)
 		if (dpu_enc->phys_encs[i])
 			intf_count++;
 
-	/* See dpu_encoder_get_topology, we only support 2:2:1 topology */
-	if (dpu_enc->dsc)
-		num_dsc = 2;
+	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++)
+		if (dpu_enc->hw_dsc[i])
+			num_dsc++;
 
 	return (num_dsc > 0) && (num_dsc > intf_count);
 }
@@ -647,130 +652,51 @@ struct drm_dsc_config *dpu_encoder_get_dsc_config(struct drm_encoder *drm_enc)
 	return NULL;
 }
 
-static struct msm_display_topology dpu_encoder_get_topology(
-			struct dpu_encoder_virt *dpu_enc,
-			struct dpu_kms *dpu_kms,
-			struct drm_display_mode *mode,
-			struct drm_crtc_state *crtc_state,
-			struct drm_dsc_config *dsc)
+void dpu_encoder_update_topology(struct drm_encoder *drm_enc,
+				 struct msm_display_topology *topology,
+				 struct drm_atomic_state *state,
+				 const struct drm_display_mode *adj_mode)
 {
-	struct msm_display_topology topology = {0};
-	int i, intf_count = 0;
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	struct msm_drm_private *priv = dpu_enc->base.dev->dev_private;
+	struct msm_display_info *disp_info = &dpu_enc->disp_info;
+	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
+	struct drm_connector *connector;
+	struct drm_connector_state *conn_state;
+	struct drm_framebuffer *fb;
+	struct drm_dsc_config *dsc;
+
+	int i;
 
 	for (i = 0; i < MAX_PHYS_ENCODERS_PER_VIRTUAL; i++)
 		if (dpu_enc->phys_encs[i])
-			intf_count++;
+			topology->num_intf++;
 
-	/* Datapath topology selection
-	 *
-	 * Dual display
-	 * 2 LM, 2 INTF ( Split display using 2 interfaces)
-	 *
-	 * Single display
-	 * 1 LM, 1 INTF
-	 * 2 LM, 1 INTF (stream merge to support high resolution interfaces)
-	 *
-	 * Add dspps to the reservation requirements if ctm is requested
-	 */
-	if (intf_count == 2)
-		topology.num_lm = 2;
-	else if (!dpu_kms->catalog->caps->has_3d_merge)
-		topology.num_lm = 1;
-	else
-		topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1;
-
-	if (crtc_state->ctm)
-		topology.num_dspp = topology.num_lm;
-
-	topology.num_intf = intf_count;
+	dsc = dpu_encoder_get_dsc_config(drm_enc);
 
+	/* We only support 2 DSC mode (with 2 LM and 1 INTF) */
 	if (dsc) {
 		/*
-		 * In case of Display Stream Compression (DSC), we would use
-		 * 2 DSC encoders, 2 layer mixers and 1 interface
-		 * this is power optimal and can drive up to (including) 4k
-		 * screens
+		 * Use 2 DSC encoders, 2 layer mixers and 1 or 2 interfaces
+		 * when Display Stream Compression (DSC) is enabled,
+		 * and when enough DSC blocks are available.
+		 * This is power-optimal and can drive up to (including) 4k
+		 * screens.
 		 */
-		topology.num_dsc = 2;
-		topology.num_lm = 2;
-		topology.num_intf = 1;
-	}
-
-	return topology;
-}
-
-static void dpu_encoder_assign_crtc_resources(struct dpu_kms *dpu_kms,
-					      struct drm_encoder *drm_enc,
-					      struct dpu_global_state *global_state,
-					      struct drm_crtc_state *crtc_state)
-{
-	struct dpu_crtc_state *cstate;
-	struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC];
-	struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC];
-	struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_ENC];
-	int num_lm, num_ctl, num_dspp, i;
-
-	cstate = to_dpu_crtc_state(crtc_state);
-
-	memset(cstate->mixers, 0, sizeof(cstate->mixers));
-
-	num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
-		drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl));
-	num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
-		drm_enc->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm));
-	num_dspp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
-		drm_enc->base.id, DPU_HW_BLK_DSPP, hw_dspp,
-		ARRAY_SIZE(hw_dspp));
-
-	for (i = 0; i < num_lm; i++) {
-		int ctl_idx = (i < num_ctl) ? i : (num_ctl-1);
-
-		cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]);
-		cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]);
-		cstate->mixers[i].hw_dspp = i < num_dspp ? to_dpu_hw_dspp(hw_dspp[i]) : NULL;
-	}
-
-	cstate->num_mixers = num_lm;
-}
-
-static int dpu_encoder_virt_atomic_check(
-		struct drm_encoder *drm_enc,
-		struct drm_crtc_state *crtc_state,
-		struct drm_connector_state *conn_state)
-{
-	struct dpu_encoder_virt *dpu_enc;
-	struct msm_drm_private *priv;
-	struct dpu_kms *dpu_kms;
-	struct drm_display_mode *adj_mode;
-	struct msm_display_topology topology;
-	struct msm_display_info *disp_info;
-	struct dpu_global_state *global_state;
-	struct drm_framebuffer *fb;
-	struct drm_dsc_config *dsc;
-	int ret = 0;
-
-	if (!drm_enc || !crtc_state || !conn_state) {
-		DPU_ERROR("invalid arg(s), drm_enc %d, crtc/conn state %d/%d\n",
-				drm_enc != NULL, crtc_state != NULL, conn_state != NULL);
-		return -EINVAL;
+		WARN(topology->num_intf > 2,
+		     "DSC topology cannot support more than 2 interfaces\n");
+		if (topology->num_intf >= 2 || dpu_kms->catalog->dsc_count >= 2)
+			topology->num_dsc = 2;
+		else
+			topology->num_dsc = 1;
 	}
 
-	dpu_enc = to_dpu_encoder_virt(drm_enc);
-	DPU_DEBUG_ENC(dpu_enc, "\n");
-
-	priv = drm_enc->dev->dev_private;
-	disp_info = &dpu_enc->disp_info;
-	dpu_kms = to_dpu_kms(priv->kms);
-	adj_mode = &crtc_state->adjusted_mode;
-	global_state = dpu_kms_get_global_state(crtc_state->state);
-	if (IS_ERR(global_state))
-		return PTR_ERR(global_state);
-
-	trace_dpu_enc_atomic_check(DRMID(drm_enc));
-
-	dsc = dpu_encoder_get_dsc_config(drm_enc);
-
-	topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode, crtc_state, dsc);
+	connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc);
+	if (!connector)
+		return;
+	conn_state = drm_atomic_get_new_connector_state(state, connector);
+	if (!conn_state)
+		return;
 
 	/*
 	 * Use CDM only for writeback or DP at the moment as other interfaces cannot handle it.
@@ -781,34 +707,45 @@ static int dpu_encoder_virt_atomic_check(
 		fb = conn_state->writeback_job->fb;
 
 		if (fb && MSM_FORMAT_IS_YUV(msm_framebuffer_format(fb)))
-			topology.needs_cdm = true;
+			topology->num_cdm++;
 	} else if (disp_info->intf_type == INTF_DP) {
 		if (msm_dp_is_yuv_420_enabled(priv->dp[disp_info->h_tile_instance[0]], adj_mode))
-			topology.needs_cdm = true;
+			topology->num_cdm++;
 	}
+}
 
-	if (topology.needs_cdm && !dpu_enc->cur_master->hw_cdm)
-		crtc_state->mode_changed = true;
-	else if (!topology.needs_cdm && dpu_enc->cur_master->hw_cdm)
-		crtc_state->mode_changed = true;
-	/*
-	 * Release and Allocate resources on every modeset
-	 * Dont allocate when active is false.
-	 */
-	if (drm_atomic_crtc_needs_modeset(crtc_state)) {
-		dpu_rm_release(global_state, drm_enc);
+bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_state *state)
+{
+	struct drm_connector *connector;
+	struct drm_connector_state *conn_state;
+	struct drm_framebuffer *fb;
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
 
-		if (!crtc_state->active_changed || crtc_state->enable)
-			ret = dpu_rm_reserve(&dpu_kms->rm, global_state,
-					drm_enc, crtc_state, &topology);
-		if (!ret)
-			dpu_encoder_assign_crtc_resources(dpu_kms, drm_enc,
-							  global_state, crtc_state);
-	}
+	if (!drm_enc || !state)
+		return false;
 
-	trace_dpu_enc_atomic_check_flags(DRMID(drm_enc), adj_mode->flags);
+	connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc);
+	if (!connector)
+		return false;
 
-	return ret;
+	conn_state = drm_atomic_get_new_connector_state(state, connector);
+
+	/**
+	 * These checks are duplicated from dpu_encoder_update_topology() since
+	 * CRTC and encoder don't hold topology information
+	 */
+	if (dpu_enc->disp_info.intf_type == INTF_WB && conn_state->writeback_job) {
+		fb = conn_state->writeback_job->fb;
+		if (fb && MSM_FORMAT_IS_YUV(msm_framebuffer_format(fb))) {
+			if (!dpu_enc->cur_master->hw_cdm)
+				return true;
+		} else {
+			if (dpu_enc->cur_master->hw_cdm)
+				return true;
+		}
+	}
+
+	return false;
 }
 
 static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc,
@@ -1219,8 +1156,12 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
 	struct dpu_hw_blk *hw_pp[MAX_CHANNELS_PER_ENC];
 	struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC];
 	struct dpu_hw_blk *hw_dsc[MAX_CHANNELS_PER_ENC];
+	struct dpu_hw_blk *hw_cwb[MAX_CHANNELS_PER_ENC];
 	int num_ctl, num_pp, num_dsc;
+	int num_cwb = 0;
+	bool is_cwb_encoder;
 	unsigned int dsc_mask = 0;
+	unsigned int cwb_mask = 0;
 	int i;
 
 	if (!drm_enc) {
@@ -1233,6 +1174,8 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
 
 	priv = drm_enc->dev->dev_private;
 	dpu_kms = to_dpu_kms(priv->kms);
+	is_cwb_encoder = drm_crtc_in_clone_mode(crtc_state) &&
+			dpu_enc->disp_info.intf_type == INTF_WB;
 
 	global_state = dpu_kms_get_existing_global_state(dpu_kms);
 	if (IS_ERR_OR_NULL(global_state)) {
@@ -1243,18 +1186,38 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
 	trace_dpu_enc_mode_set(DRMID(drm_enc));
 
 	/* Query resource that have been reserved in atomic check step. */
-	num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
-		drm_enc->base.id, DPU_HW_BLK_PINGPONG, hw_pp,
-		ARRAY_SIZE(hw_pp));
+	if (is_cwb_encoder) {
+		num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+						       drm_enc->crtc,
+						       DPU_HW_BLK_DCWB_PINGPONG,
+						       hw_pp, ARRAY_SIZE(hw_pp));
+		num_cwb = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+						       drm_enc->crtc,
+						       DPU_HW_BLK_CWB,
+						       hw_cwb, ARRAY_SIZE(hw_cwb));
+	} else {
+		num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+						       drm_enc->crtc,
+						       DPU_HW_BLK_PINGPONG, hw_pp,
+						       ARRAY_SIZE(hw_pp));
+	}
+
+	for (i = 0; i < num_cwb; i++) {
+		dpu_enc->hw_cwb[i] = to_dpu_hw_cwb(hw_cwb[i]);
+		cwb_mask |= BIT(dpu_enc->hw_cwb[i]->idx - CWB_0);
+	}
+
+	dpu_enc->cwb_mask = cwb_mask;
+
 	num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
-		drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl));
+		drm_enc->crtc, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl));
 
 	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++)
 		dpu_enc->hw_pp[i] = i < num_pp ? to_dpu_hw_pingpong(hw_pp[i])
 						: NULL;
 
 	num_dsc = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
-						drm_enc->base.id, DPU_HW_BLK_DSC,
+						drm_enc->crtc, DPU_HW_BLK_DSC,
 						hw_dsc, ARRAY_SIZE(hw_dsc));
 	for (i = 0; i < num_dsc; i++) {
 		dpu_enc->hw_dsc[i] = to_dpu_hw_dsc(hw_dsc[i]);
@@ -1268,7 +1231,7 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
 		struct dpu_hw_blk *hw_cdm = NULL;
 
 		dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
-					      drm_enc->base.id, DPU_HW_BLK_CDM,
+					      drm_enc->crtc, DPU_HW_BLK_CDM,
 					      &hw_cdm, 1);
 		dpu_enc->cur_master->hw_cdm = hw_cdm ? to_dpu_hw_cdm(hw_cdm) : NULL;
 	}
@@ -1447,7 +1410,7 @@ static void dpu_encoder_virt_atomic_disable(struct drm_encoder *drm_enc,
 	/* after phys waits for frame-done, should be no more frames pending */
 	if (atomic_xchg(&dpu_enc->frame_done_timeout_ms, 0)) {
 		DPU_ERROR("enc%d timeout pending\n", drm_enc->base.id);
-		del_timer_sync(&dpu_enc->frame_done_timer);
+		timer_delete_sync(&dpu_enc->frame_done_timer);
 	}
 
 	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_STOP);
@@ -1619,7 +1582,7 @@ void dpu_encoder_frame_done_callback(
 
 		if (!dpu_enc->frame_busy_mask[0]) {
 			atomic_set(&dpu_enc->frame_done_timeout_ms, 0);
-			del_timer(&dpu_enc->frame_done_timer);
+			timer_delete(&dpu_enc->frame_done_timer);
 
 			dpu_encoder_resource_control(drm_enc,
 					DPU_ENC_RC_EVENT_FRAME_DONE);
@@ -1654,6 +1617,7 @@ static void dpu_encoder_off_work(struct work_struct *work)
 static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
 		struct dpu_encoder_phys *phys, uint32_t extra_flush_bits)
 {
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
 	struct dpu_hw_ctl *ctl;
 	int pending_kickoff_cnt;
 	u32 ret = UINT_MAX;
@@ -1671,6 +1635,15 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
 
 	pending_kickoff_cnt = dpu_encoder_phys_inc_pending(phys);
 
+	/* Return early if encoder is writeback and in clone mode */
+	if (drm_enc->encoder_type == DRM_MODE_ENCODER_VIRTUAL &&
+	    dpu_enc->cwb_mask) {
+		DPU_DEBUG("encoder %d skip flush for concurrent writeback encoder\n",
+				DRMID(drm_enc));
+		return;
+	}
+
+
 	if (extra_flush_bits && ctl->ops.update_pending_flush)
 		ctl->ops.update_pending_flush(ctl, extra_flush_bits);
 
@@ -1693,6 +1666,8 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
  */
 static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys)
 {
+	struct dpu_encoder_virt *dpu_enc;
+
 	if (!phys) {
 		DPU_ERROR("invalid argument(s)\n");
 		return;
@@ -1703,6 +1678,14 @@ static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys)
 		return;
 	}
 
+	dpu_enc = to_dpu_encoder_virt(phys->parent);
+
+	if (phys->parent->encoder_type == DRM_MODE_ENCODER_VIRTUAL &&
+	    dpu_enc->cwb_mask) {
+		DPU_DEBUG("encoder %d CWB enabled, skipping\n", DRMID(phys->parent));
+		return;
+	}
+
 	if (phys->ops.trigger_start && phys->enable_state != DPU_ENC_DISABLED)
 		phys->ops.trigger_start(phys);
 }
@@ -2020,7 +2003,6 @@ static void dpu_encoder_dsc_pipe_cfg(struct dpu_hw_ctl *ctl,
 static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc,
 				 struct drm_dsc_config *dsc)
 {
-	/* coding only for 2LM, 2enc, 1 dsc config */
 	struct dpu_encoder_phys *enc_master = dpu_enc->cur_master;
 	struct dpu_hw_ctl *ctl = enc_master->hw_ctl;
 	struct dpu_hw_dsc *hw_dsc[MAX_CHANNELS_PER_ENC];
@@ -2030,22 +2012,24 @@ static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc,
 	int dsc_common_mode;
 	int pic_width;
 	u32 initial_lines;
+	int num_dsc = 0;
 	int i;
 
 	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) {
 		hw_pp[i] = dpu_enc->hw_pp[i];
 		hw_dsc[i] = dpu_enc->hw_dsc[i];
 
-		if (!hw_pp[i] || !hw_dsc[i]) {
-			DPU_ERROR_ENC(dpu_enc, "invalid params for DSC\n");
-			return;
-		}
+		if (!hw_pp[i] || !hw_dsc[i])
+			break;
+
+		num_dsc++;
 	}
 
-	dsc_common_mode = 0;
 	pic_width = dsc->pic_width;
 
-	dsc_common_mode = DSC_MODE_SPLIT_PANEL;
+	dsc_common_mode = 0;
+	if (num_dsc > 1)
+		dsc_common_mode |= DSC_MODE_SPLIT_PANEL;
 	if (dpu_encoder_use_dsc_merge(enc_master->parent))
 		dsc_common_mode |= DSC_MODE_MULTIPLEX;
 	if (enc_master->intf_mode == INTF_MODE_VIDEO)
@@ -2054,14 +2038,10 @@ static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc,
 	this_frame_slices = pic_width / dsc->slice_width;
 	intf_ip_w = this_frame_slices * dsc->slice_width;
 
-	/*
-	 * dsc merge case: when using 2 encoders for the same stream,
-	 * no. of slices need to be same on both the encoders.
-	 */
-	enc_ip_w = intf_ip_w / 2;
+	enc_ip_w = intf_ip_w / num_dsc;
 	initial_lines = dpu_encoder_dsc_initial_line_calc(dsc, enc_ip_w);
 
-	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++)
+	for (i = 0; i < num_dsc; i++)
 		dpu_encoder_dsc_pipe_cfg(ctl, hw_dsc[i], hw_pp[i],
 					 dsc, dsc_common_mode, initial_lines);
 }
@@ -2135,6 +2115,25 @@ bool dpu_encoder_is_valid_for_commit(struct drm_encoder *drm_enc)
 }
 
 /**
+ * dpu_encoder_start_frame_done_timer - Start the encoder frame done timer
+ * @drm_enc: Pointer to drm encoder structure
+ */
+void dpu_encoder_start_frame_done_timer(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	unsigned long timeout_ms;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	timeout_ms = DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES * 1000 /
+			drm_mode_vrefresh(&drm_enc->crtc->state->adjusted_mode);
+
+	atomic_set(&dpu_enc->frame_done_timeout_ms, timeout_ms);
+	mod_timer(&dpu_enc->frame_done_timer,
+			jiffies + msecs_to_jiffies(timeout_ms));
+
+}
+
+/**
  * dpu_encoder_kickoff - trigger a double buffer flip of the ctl path
  *	(i.e. ctl flush and start) immediately.
  * @drm_enc:	encoder pointer
@@ -2143,7 +2142,6 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc)
 {
 	struct dpu_encoder_virt *dpu_enc;
 	struct dpu_encoder_phys *phys;
-	unsigned long timeout_ms;
 	unsigned int i;
 
 	DPU_ATRACE_BEGIN("encoder_kickoff");
@@ -2151,13 +2149,6 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc)
 
 	trace_dpu_enc_kickoff(DRMID(drm_enc));
 
-	timeout_ms = DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES * 1000 /
-			drm_mode_vrefresh(&drm_enc->crtc->state->adjusted_mode);
-
-	atomic_set(&dpu_enc->frame_done_timeout_ms, timeout_ms);
-	mod_timer(&dpu_enc->frame_done_timer,
-			jiffies + msecs_to_jiffies(timeout_ms));
-
 	/* All phys encs are ready to go, trigger the kickoff */
 	_dpu_encoder_kickoff_phys(dpu_enc);
 
@@ -2183,22 +2174,22 @@ static void dpu_encoder_helper_reset_mixers(struct dpu_encoder_phys *phys_enc)
 	memset(&mixer, 0, sizeof(mixer));
 
 	/* reset all mixers for this encoder */
-	if (phys_enc->hw_ctl->ops.clear_all_blendstages)
-		phys_enc->hw_ctl->ops.clear_all_blendstages(phys_enc->hw_ctl);
+	if (ctl->ops.clear_all_blendstages)
+		ctl->ops.clear_all_blendstages(ctl);
 
 	global_state = dpu_kms_get_existing_global_state(phys_enc->dpu_kms);
 
 	num_lm = dpu_rm_get_assigned_resources(&phys_enc->dpu_kms->rm, global_state,
-		phys_enc->parent->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm));
+		phys_enc->parent->crtc, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm));
 
 	for (i = 0; i < num_lm; i++) {
 		hw_mixer[i] = to_dpu_hw_mixer(hw_lm[i]);
-		if (phys_enc->hw_ctl->ops.update_pending_flush_mixer)
-			phys_enc->hw_ctl->ops.update_pending_flush_mixer(ctl, hw_mixer[i]->idx);
+		if (ctl->ops.update_pending_flush_mixer)
+			ctl->ops.update_pending_flush_mixer(ctl, hw_mixer[i]->idx);
 
 		/* clear all blendstages */
-		if (phys_enc->hw_ctl->ops.setup_blendstage)
-			phys_enc->hw_ctl->ops.setup_blendstage(ctl, hw_mixer[i]->idx, NULL);
+		if (ctl->ops.setup_blendstage)
+			ctl->ops.setup_blendstage(ctl, hw_mixer[i]->idx, NULL);
 	}
 }
 
@@ -2250,7 +2241,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 
 	dpu_enc = to_dpu_encoder_virt(phys_enc->parent);
 
-	phys_enc->hw_ctl->ops.reset(ctl);
+	ctl->ops.reset(ctl);
 
 	dpu_encoder_helper_reset_mixers(phys_enc);
 
@@ -2265,8 +2256,8 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 			phys_enc->hw_wb->ops.bind_pingpong_blk(phys_enc->hw_wb, PINGPONG_NONE);
 
 		/* mark WB flush as pending */
-		if (phys_enc->hw_ctl->ops.update_pending_flush_wb)
-			phys_enc->hw_ctl->ops.update_pending_flush_wb(ctl, phys_enc->hw_wb->idx);
+		if (ctl->ops.update_pending_flush_wb)
+			ctl->ops.update_pending_flush_wb(ctl, phys_enc->hw_wb->idx);
 	} else {
 		for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 			if (dpu_enc->phys_encs[i] && phys_enc->hw_intf->ops.bind_pingpong_blk)
@@ -2275,8 +2266,8 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 						PINGPONG_NONE);
 
 			/* mark INTF flush as pending */
-			if (phys_enc->hw_ctl->ops.update_pending_flush_intf)
-				phys_enc->hw_ctl->ops.update_pending_flush_intf(phys_enc->hw_ctl,
+			if (ctl->ops.update_pending_flush_intf)
+				ctl->ops.update_pending_flush_intf(ctl,
 						dpu_enc->phys_encs[i]->hw_intf->idx);
 		}
 	}
@@ -2284,12 +2275,15 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	if (phys_enc->hw_pp && phys_enc->hw_pp->ops.setup_dither)
 		phys_enc->hw_pp->ops.setup_dither(phys_enc->hw_pp, NULL);
 
+	if (dpu_enc->cwb_mask)
+		dpu_encoder_helper_phys_setup_cwb(phys_enc, false);
+
 	/* reset the merge 3D HW block */
 	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) {
 		phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
 				BLEND_3D_NONE);
-		if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d)
-			phys_enc->hw_ctl->ops.update_pending_flush_merge_3d(ctl,
+		if (ctl->ops.update_pending_flush_merge_3d)
+			ctl->ops.update_pending_flush_merge_3d(ctl,
 					phys_enc->hw_pp->merge_3d->idx);
 	}
 
@@ -2297,9 +2291,9 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 		if (phys_enc->hw_cdm->ops.bind_pingpong_blk && phys_enc->hw_pp)
 			phys_enc->hw_cdm->ops.bind_pingpong_blk(phys_enc->hw_cdm,
 								PINGPONG_NONE);
-		if (phys_enc->hw_ctl->ops.update_pending_flush_cdm)
-			phys_enc->hw_ctl->ops.update_pending_flush_cdm(phys_enc->hw_ctl,
-								       phys_enc->hw_cdm->idx);
+		if (ctl->ops.update_pending_flush_cdm)
+			ctl->ops.update_pending_flush_cdm(ctl,
+							  phys_enc->hw_cdm->idx);
 	}
 
 	if (dpu_enc->dsc) {
@@ -2310,6 +2304,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	intf_cfg.stream_sel = 0; /* Don't care value for video mode */
 	intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
 	intf_cfg.dsc = dpu_encoder_helper_get_dsc(phys_enc);
+	intf_cfg.cwb = dpu_enc->cwb_mask;
 
 	if (phys_enc->hw_intf)
 		intf_cfg.intf = phys_enc->hw_intf->idx;
@@ -2327,6 +2322,68 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	ctl->ops.clear_pending_flush(ctl);
 }
 
+void dpu_encoder_helper_phys_setup_cwb(struct dpu_encoder_phys *phys_enc,
+				       bool enable)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(phys_enc->parent);
+	struct dpu_hw_cwb *hw_cwb;
+	struct dpu_hw_ctl *hw_ctl;
+	struct dpu_hw_cwb_setup_cfg cwb_cfg;
+
+	struct dpu_kms *dpu_kms;
+	struct dpu_global_state *global_state;
+	struct dpu_hw_blk *rt_pp_list[MAX_CHANNELS_PER_ENC];
+	int num_pp;
+
+	if (!phys_enc->hw_wb)
+		return;
+
+	hw_ctl = phys_enc->hw_ctl;
+
+	if (!phys_enc->hw_ctl) {
+		DPU_DEBUG("[wb:%d] no ctl assigned\n",
+			  phys_enc->hw_wb->idx - WB_0);
+		return;
+	}
+
+	dpu_kms = phys_enc->dpu_kms;
+	global_state = dpu_kms_get_existing_global_state(dpu_kms);
+	num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+					       phys_enc->parent->crtc,
+					       DPU_HW_BLK_PINGPONG, rt_pp_list,
+					       ARRAY_SIZE(rt_pp_list));
+
+	if (num_pp == 0 || num_pp > MAX_CHANNELS_PER_ENC) {
+		DPU_DEBUG_ENC(dpu_enc, "invalid num_pp %d\n", num_pp);
+		return;
+	}
+
+	/*
+	 * The CWB mux supports using LM or DSPP as tap points. For now,
+	 * always use LM tap point
+	 */
+	cwb_cfg.input = INPUT_MODE_LM_OUT;
+
+	for (int i = 0; i < MAX_CHANNELS_PER_ENC; i++) {
+		hw_cwb = dpu_enc->hw_cwb[i];
+		if (!hw_cwb)
+			continue;
+
+		if (enable) {
+			struct dpu_hw_pingpong *hw_pp =
+					to_dpu_hw_pingpong(rt_pp_list[i]);
+			cwb_cfg.pp_idx = hw_pp->idx;
+		} else {
+			cwb_cfg.pp_idx = PINGPONG_NONE;
+		}
+
+		hw_cwb->ops.config_cwb(hw_cwb, &cwb_cfg);
+
+		if (hw_ctl->ops.update_pending_flush_cwb)
+			hw_ctl->ops.update_pending_flush_cwb(hw_ctl, hw_cwb->idx);
+	}
+}
+
 /**
  * dpu_encoder_helper_phys_setup_cdm - setup chroma down sampling block
  * @phys_enc: Pointer to physical encoder
@@ -2513,6 +2570,38 @@ static int dpu_encoder_virt_add_phys_encs(
 	return 0;
 }
 
+/**
+ * dpu_encoder_get_clones - Calculate the possible_clones for DPU encoder
+ * @drm_enc:        DRM encoder pointer
+ * Returns:         possible_clones mask
+ */
+uint32_t dpu_encoder_get_clones(struct drm_encoder *drm_enc)
+{
+	struct drm_encoder *curr;
+	int type = drm_enc->encoder_type;
+	uint32_t clone_mask = drm_encoder_mask(drm_enc);
+
+	/*
+	 * Set writeback as possible clones of real-time DSI encoders and vice
+	 * versa
+	 *
+	 * Writeback encoders can't be clones of each other and DSI
+	 * encoders can't be clones of each other.
+	 *
+	 * TODO: Add DP encoders as valid possible clones for writeback encoders
+	 * (and vice versa) once concurrent writeback has been validated for DP
+	 */
+	drm_for_each_encoder(curr, drm_enc->dev) {
+		if ((type == DRM_MODE_ENCODER_VIRTUAL &&
+		    curr->encoder_type == DRM_MODE_ENCODER_DSI) ||
+		    (type == DRM_MODE_ENCODER_DSI &&
+		    curr->encoder_type == DRM_MODE_ENCODER_VIRTUAL))
+			clone_mask |= drm_encoder_mask(curr);
+	}
+
+	return clone_mask;
+}
+
 static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc,
 				 struct dpu_kms *dpu_kms,
 				 struct msm_display_info *disp_info)
@@ -2630,7 +2719,6 @@ static const struct drm_encoder_helper_funcs dpu_encoder_helper_funcs = {
 	.atomic_mode_set = dpu_encoder_virt_atomic_mode_set,
 	.atomic_disable = dpu_encoder_virt_atomic_disable,
 	.atomic_enable = dpu_encoder_virt_atomic_enable,
-	.atomic_check = dpu_encoder_virt_atomic_check,
 };
 
 static const struct drm_encoder_funcs dpu_encoder_funcs = {
@@ -2789,6 +2877,18 @@ enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder)
 }
 
 /**
+ * dpu_encoder_helper_get_cwb_mask - get CWB blocks mask for the DPU encoder
+ * @phys_enc: Pointer to physical encoder structure
+ */
+unsigned int dpu_encoder_helper_get_cwb_mask(struct dpu_encoder_phys *phys_enc)
+{
+	struct drm_encoder *encoder = phys_enc->parent;
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(encoder);
+
+	return dpu_enc->cwb_mask;
+}
+
+/**
  * dpu_encoder_helper_get_dsc - get DSC blocks mask for the DPU encoder
  *   This helper function is used by physical encoder to get DSC blocks mask
  *   used for this encoder.