Adding upstream version 6.1.76.upstream/6.1.76

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

55 files changed, 26238 insertions, 0 deletions

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
new file mode 100644
index 000000000..b5b6e7031
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __DPU_CORE_IRQ_H__
+#define __DPU_CORE_IRQ_H__
+
+#include "dpu_kms.h"
+#include "dpu_hw_interrupts.h"
+
+/**
+ * dpu_core_irq_preinstall - perform pre-installation of core IRQ handler
+ * @kms:		MSM KMS handle
+ * @return:		none
+ */
+void dpu_core_irq_preinstall(struct msm_kms *kms);
+
+/**
+ * dpu_core_irq_uninstall - uninstall core IRQ handler
+ * @kms:		MSM KMS handle
+ * @return:		none
+ */
+void dpu_core_irq_uninstall(struct msm_kms *kms);
+
+/**
+ * dpu_core_irq - core IRQ handler
+ * @kms:		MSM KMS handle
+ * @return:		interrupt handling status
+ */
+irqreturn_t dpu_core_irq(struct msm_kms *kms);
+
+/**
+ * dpu_core_irq_read - IRQ helper function for reading IRQ status
+ * @dpu_kms:		DPU handle
+ * @irq_idx:		irq index
+ * @return:		non-zero if irq detected; otherwise no irq detected
+ */
+u32 dpu_core_irq_read(
+		struct dpu_kms *dpu_kms,
+		int irq_idx);
+
+/**
+ * dpu_core_irq_register_callback - For registering callback function on IRQ
+ *                             interrupt
+ * @dpu_kms:		DPU handle
+ * @irq_idx:		irq index
+ * @irq_cb:		IRQ callback funcion.
+ * @irq_arg:		IRQ callback argument.
+ * @return:		0 for success registering callback, otherwise failure
+ *
+ * This function supports registration of multiple callbacks for each interrupt.
+ */
+int dpu_core_irq_register_callback(
+		struct dpu_kms *dpu_kms,
+		int irq_idx,
+		void (*irq_cb)(void *arg, int irq_idx),
+		void *irq_arg);
+
+/**
+ * dpu_core_irq_unregister_callback - For unregistering callback function on IRQ
+ *                             interrupt
+ * @dpu_kms:		DPU handle
+ * @irq_idx:		irq index
+ * @return:		0 for success registering callback, otherwise failure
+ *
+ * This function supports registration of multiple callbacks for each interrupt.
+ */
+int dpu_core_irq_unregister_callback(
+		struct dpu_kms *dpu_kms,
+		int irq_idx);
+
+/**
+ * dpu_debugfs_core_irq_init - register core irq debugfs
+ * @dpu_kms: pointer to kms
+ * @parent: debugfs directory root
+ */
+void dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent);
+
+#endif /* __DPU_CORE_IRQ_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
new file mode 100644
index 000000000..1d9d83d7b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -0,0 +1,534 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/errno.h>
+#include <linux/mutex.h>
+#include <linux/pm_opp.h>
+#include <linux/sort.h>
+#include <linux/clk.h>
+#include <linux/bitmap.h>
+
+#include "dpu_kms.h"
+#include "dpu_trace.h"
+#include "dpu_crtc.h"
+#include "dpu_core_perf.h"
+
+/**
+ * enum dpu_perf_mode - performance tuning mode
+ * @DPU_PERF_MODE_NORMAL: performance controlled by user mode client
+ * @DPU_PERF_MODE_MINIMUM: performance bounded by minimum setting
+ * @DPU_PERF_MODE_FIXED: performance bounded by fixed setting
+ * @DPU_PERF_MODE_MAX: maximum value, used for error checking
+ */
+enum dpu_perf_mode {
+	DPU_PERF_MODE_NORMAL,
+	DPU_PERF_MODE_MINIMUM,
+	DPU_PERF_MODE_FIXED,
+	DPU_PERF_MODE_MAX
+};
+
+/**
+ * _dpu_core_perf_calc_bw() - to calculate BW per crtc
+ * @kms:  pointer to the dpu_kms
+ * @crtc: pointer to a crtc
+ * Return: returns aggregated BW for all planes in crtc.
+ */
+static u64 _dpu_core_perf_calc_bw(struct dpu_kms *kms,
+		struct drm_crtc *crtc)
+{
+	struct drm_plane *plane;
+	struct dpu_plane_state *pstate;
+	u64 crtc_plane_bw = 0;
+	u32 bw_factor;
+
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		pstate = to_dpu_plane_state(plane->state);
+		if (!pstate)
+			continue;
+
+		crtc_plane_bw += pstate->plane_fetch_bw;
+	}
+
+	bw_factor = kms->catalog->perf->bw_inefficiency_factor;
+	if (bw_factor) {
+		crtc_plane_bw *= bw_factor;
+		do_div(crtc_plane_bw, 100);
+	}
+
+	return crtc_plane_bw;
+}
+
+/**
+ * _dpu_core_perf_calc_clk() - to calculate clock per crtc
+ * @kms:  pointer to the dpu_kms
+ * @crtc: pointer to a crtc
+ * @state: pointer to a crtc state
+ * Return: returns max clk for all planes in crtc.
+ */
+static u64 _dpu_core_perf_calc_clk(struct dpu_kms *kms,
+		struct drm_crtc *crtc, struct drm_crtc_state *state)
+{
+	struct drm_plane *plane;
+	struct dpu_plane_state *pstate;
+	struct drm_display_mode *mode;
+	u64 crtc_clk;
+	u32 clk_factor;
+
+	mode = &state->adjusted_mode;
+
+	crtc_clk = mode->vtotal * mode->hdisplay * drm_mode_vrefresh(mode);
+
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		pstate = to_dpu_plane_state(plane->state);
+		if (!pstate)
+			continue;
+
+		crtc_clk = max(pstate->plane_clk, crtc_clk);
+	}
+
+	clk_factor = kms->catalog->perf->clk_inefficiency_factor;
+	if (clk_factor) {
+		crtc_clk *= clk_factor;
+		do_div(crtc_clk, 100);
+	}
+
+	return crtc_clk;
+}
+
+static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
+{
+	struct msm_drm_private *priv;
+	priv = crtc->dev->dev_private;
+	return to_dpu_kms(priv->kms);
+}
+
+static void _dpu_core_perf_calc_crtc(struct dpu_kms *kms,
+		struct drm_crtc *crtc,
+		struct drm_crtc_state *state,
+		struct dpu_core_perf_params *perf)
+{
+	if (!kms || !kms->catalog || !crtc || !state || !perf) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	memset(perf, 0, sizeof(struct dpu_core_perf_params));
+
+	if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM) {
+		perf->bw_ctl = 0;
+		perf->max_per_pipe_ib = 0;
+		perf->core_clk_rate = 0;
+	} else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED) {
+		perf->bw_ctl = kms->perf.fix_core_ab_vote;
+		perf->max_per_pipe_ib = kms->perf.fix_core_ib_vote;
+		perf->core_clk_rate = kms->perf.fix_core_clk_rate;
+	} else {
+		perf->bw_ctl = _dpu_core_perf_calc_bw(kms, crtc);
+		perf->max_per_pipe_ib = kms->catalog->perf->min_dram_ib;
+		perf->core_clk_rate = _dpu_core_perf_calc_clk(kms, crtc, state);
+	}
+
+	DRM_DEBUG_ATOMIC(
+		"crtc=%d clk_rate=%llu core_ib=%llu core_ab=%llu\n",
+			crtc->base.id, perf->core_clk_rate,
+			perf->max_per_pipe_ib, perf->bw_ctl);
+}
+
+int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	u32 bw, threshold;
+	u64 bw_sum_of_intfs = 0;
+	enum dpu_crtc_client_type curr_client_type;
+	struct dpu_crtc_state *dpu_cstate;
+	struct drm_crtc *tmp_crtc;
+	struct dpu_kms *kms;
+
+	if (!crtc || !state) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	kms = _dpu_crtc_get_kms(crtc);
+	if (!kms->catalog) {
+		DPU_ERROR("invalid parameters\n");
+		return 0;
+	}
+
+	/* we only need bandwidth check on real-time clients (interfaces) */
+	if (dpu_crtc_get_client_type(crtc) == NRT_CLIENT)
+		return 0;
+
+	dpu_cstate = to_dpu_crtc_state(state);
+
+	/* obtain new values */
+	_dpu_core_perf_calc_crtc(kms, crtc, state, &dpu_cstate->new_perf);
+
+	bw_sum_of_intfs = dpu_cstate->new_perf.bw_ctl;
+	curr_client_type = dpu_crtc_get_client_type(crtc);
+
+	drm_for_each_crtc(tmp_crtc, crtc->dev) {
+		if (tmp_crtc->enabled &&
+		    (dpu_crtc_get_client_type(tmp_crtc) ==
+				curr_client_type) && (tmp_crtc != crtc)) {
+			struct dpu_crtc_state *tmp_cstate =
+				to_dpu_crtc_state(tmp_crtc->state);
+
+			DRM_DEBUG_ATOMIC("crtc:%d bw:%llu ctrl:%d\n",
+				tmp_crtc->base.id, tmp_cstate->new_perf.bw_ctl,
+				tmp_cstate->bw_control);
+
+				bw_sum_of_intfs += tmp_cstate->new_perf.bw_ctl;
+		}
+
+		/* convert bandwidth to kb */
+		bw = DIV_ROUND_UP_ULL(bw_sum_of_intfs, 1000);
+		DRM_DEBUG_ATOMIC("calculated bandwidth=%uk\n", bw);
+
+		threshold = kms->catalog->perf->max_bw_high;
+
+		DRM_DEBUG_ATOMIC("final threshold bw limit = %d\n", threshold);
+
+		if (!threshold) {
+			DPU_ERROR("no bandwidth limits specified\n");
+			return -E2BIG;
+		} else if (bw > threshold) {
+			DPU_ERROR("exceeds bandwidth: %ukb > %ukb\n", bw,
+					threshold);
+			return -E2BIG;
+		}
+	}
+
+	return 0;
+}
+
+static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
+		struct drm_crtc *crtc)
+{
+	struct dpu_core_perf_params perf = { 0 };
+	enum dpu_crtc_client_type curr_client_type
+					= dpu_crtc_get_client_type(crtc);
+	struct drm_crtc *tmp_crtc;
+	struct dpu_crtc_state *dpu_cstate;
+	int i, ret = 0;
+	u64 avg_bw;
+
+	drm_for_each_crtc(tmp_crtc, crtc->dev) {
+		if (tmp_crtc->enabled &&
+			curr_client_type ==
+				dpu_crtc_get_client_type(tmp_crtc)) {
+			dpu_cstate = to_dpu_crtc_state(tmp_crtc->state);
+
+			perf.max_per_pipe_ib = max(perf.max_per_pipe_ib,
+					dpu_cstate->new_perf.max_per_pipe_ib);
+
+			perf.bw_ctl += dpu_cstate->new_perf.bw_ctl;
+
+			DRM_DEBUG_ATOMIC("crtc=%d bw=%llu paths:%d\n",
+				  tmp_crtc->base.id,
+				  dpu_cstate->new_perf.bw_ctl, kms->num_paths);
+		}
+	}
+
+	if (!kms->num_paths)
+		return 0;
+
+	avg_bw = perf.bw_ctl;
+	do_div(avg_bw, (kms->num_paths * 1000)); /*Bps_to_icc*/
+
+	for (i = 0; i < kms->num_paths; i++)
+		icc_set_bw(kms->path[i], avg_bw, perf.max_per_pipe_ib);
+
+	return ret;
+}
+
+/**
+ * dpu_core_perf_crtc_release_bw() - request zero bandwidth
+ * @crtc: pointer to a crtc
+ *
+ * Function checks a state variable for the crtc, if all pending commit
+ * requests are done, meaning no more bandwidth is needed, release
+ * bandwidth request.
+ */
+void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_kms *kms;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	kms = _dpu_crtc_get_kms(crtc);
+	if (!kms->catalog) {
+		DPU_ERROR("invalid kms\n");
+		return;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	if (atomic_dec_return(&kms->bandwidth_ref) > 0)
+		return;
+
+	/* Release the bandwidth */
+	if (kms->perf.enable_bw_release) {
+		trace_dpu_cmd_release_bw(crtc->base.id);
+		DRM_DEBUG_ATOMIC("Release BW crtc=%d\n", crtc->base.id);
+		dpu_crtc->cur_perf.bw_ctl = 0;
+		_dpu_core_perf_crtc_update_bus(kms, crtc);
+	}
+}
+
+static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms)
+{
+	u64 clk_rate = kms->perf.perf_tune.min_core_clk;
+	struct drm_crtc *crtc;
+	struct dpu_crtc_state *dpu_cstate;
+
+	drm_for_each_crtc(crtc, kms->dev) {
+		if (crtc->enabled) {
+			dpu_cstate = to_dpu_crtc_state(crtc->state);
+			clk_rate = max(dpu_cstate->new_perf.core_clk_rate,
+							clk_rate);
+			clk_rate = clk_round_rate(kms->perf.core_clk,
+					clk_rate);
+		}
+	}
+
+	if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED)
+		clk_rate = kms->perf.fix_core_clk_rate;
+
+	DRM_DEBUG_ATOMIC("clk:%llu\n", clk_rate);
+
+	return clk_rate;
+}
+
+int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
+		int params_changed, bool stop_req)
+{
+	struct dpu_core_perf_params *new, *old;
+	bool update_bus = false, update_clk = false;
+	u64 clk_rate = 0;
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *dpu_cstate;
+	struct dpu_kms *kms;
+	int ret;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	kms = _dpu_crtc_get_kms(crtc);
+	if (!kms->catalog) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_cstate = to_dpu_crtc_state(crtc->state);
+
+	DRM_DEBUG_ATOMIC("crtc:%d stop_req:%d core_clk:%llu\n",
+			crtc->base.id, stop_req, kms->perf.core_clk_rate);
+
+	old = &dpu_crtc->cur_perf;
+	new = &dpu_cstate->new_perf;
+
+	if (crtc->enabled && !stop_req) {
+		/*
+		 * cases for bus bandwidth update.
+		 * 1. new bandwidth vote - "ab or ib vote" is higher
+		 *    than current vote for update request.
+		 * 2. new bandwidth vote - "ab or ib vote" is lower
+		 *    than current vote at end of commit or stop.
+		 */
+		if ((params_changed && ((new->bw_ctl > old->bw_ctl) ||
+			(new->max_per_pipe_ib > old->max_per_pipe_ib)))	||
+			(!params_changed && ((new->bw_ctl < old->bw_ctl) ||
+			(new->max_per_pipe_ib < old->max_per_pipe_ib)))) {
+			DRM_DEBUG_ATOMIC("crtc=%d p=%d new_bw=%llu,old_bw=%llu\n",
+				crtc->base.id, params_changed,
+				new->bw_ctl, old->bw_ctl);
+			old->bw_ctl = new->bw_ctl;
+			old->max_per_pipe_ib = new->max_per_pipe_ib;
+			update_bus = true;
+		}
+
+		if ((params_changed &&
+			(new->core_clk_rate > old->core_clk_rate)) ||
+			(!params_changed &&
+			(new->core_clk_rate < old->core_clk_rate))) {
+			old->core_clk_rate = new->core_clk_rate;
+			update_clk = true;
+		}
+	} else {
+		DRM_DEBUG_ATOMIC("crtc=%d disable\n", crtc->base.id);
+		memset(old, 0, sizeof(*old));
+		update_bus = true;
+		update_clk = true;
+	}
+
+	trace_dpu_perf_crtc_update(crtc->base.id, new->bw_ctl,
+		new->core_clk_rate, stop_req, update_bus, update_clk);
+
+	if (update_bus) {
+		ret = _dpu_core_perf_crtc_update_bus(kms, crtc);
+		if (ret) {
+			DPU_ERROR("crtc-%d: failed to update bus bw vote\n",
+				  crtc->base.id);
+			return ret;
+		}
+	}
+
+	/*
+	 * Update the clock after bandwidth vote to ensure
+	 * bandwidth is available before clock rate is increased.
+	 */
+	if (update_clk) {
+		clk_rate = _dpu_core_perf_get_core_clk_rate(kms);
+
+		trace_dpu_core_perf_update_clk(kms->dev, stop_req, clk_rate);
+
+		clk_rate = min(clk_rate, kms->perf.max_core_clk_rate);
+		ret = dev_pm_opp_set_rate(&kms->pdev->dev, clk_rate);
+		if (ret) {
+			DPU_ERROR("failed to set core clock rate %llu\n", clk_rate);
+			return ret;
+		}
+
+		kms->perf.core_clk_rate = clk_rate;
+		DRM_DEBUG_ATOMIC("update clk rate = %lld HZ\n", clk_rate);
+	}
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+
+static ssize_t _dpu_core_perf_mode_write(struct file *file,
+		    const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_core_perf *perf = file->private_data;
+	const struct dpu_perf_cfg *cfg = perf->catalog->perf;
+	u32 perf_mode = 0;
+	int ret;
+
+	ret = kstrtouint_from_user(user_buf, count, 0, &perf_mode);
+	if (ret)
+		return ret;
+
+	if (perf_mode >= DPU_PERF_MODE_MAX)
+		return -EINVAL;
+
+	if (perf_mode == DPU_PERF_MODE_FIXED) {
+		DRM_INFO("fix performance mode\n");
+	} else if (perf_mode == DPU_PERF_MODE_MINIMUM) {
+		/* run the driver with max clk and BW vote */
+		perf->perf_tune.min_core_clk = perf->max_core_clk_rate;
+		perf->perf_tune.min_bus_vote =
+				(u64) cfg->max_bw_high * 1000;
+		DRM_INFO("minimum performance mode\n");
+	} else if (perf_mode == DPU_PERF_MODE_NORMAL) {
+		/* reset the perf tune params to 0 */
+		perf->perf_tune.min_core_clk = 0;
+		perf->perf_tune.min_bus_vote = 0;
+		DRM_INFO("normal performance mode\n");
+	}
+	perf->perf_tune.mode = perf_mode;
+
+	return count;
+}
+
+static ssize_t _dpu_core_perf_mode_read(struct file *file,
+			char __user *buff, size_t count, loff_t *ppos)
+{
+	struct dpu_core_perf *perf = file->private_data;
+	int len;
+	char buf[128];
+
+	len = scnprintf(buf, sizeof(buf),
+			"mode %d min_mdp_clk %llu min_bus_vote %llu\n",
+			perf->perf_tune.mode,
+			perf->perf_tune.min_core_clk,
+			perf->perf_tune.min_bus_vote);
+
+	return simple_read_from_buffer(buff, count, ppos, buf, len);
+}
+
+static const struct file_operations dpu_core_perf_mode_fops = {
+	.open = simple_open,
+	.read = _dpu_core_perf_mode_read,
+	.write = _dpu_core_perf_mode_write,
+};
+
+int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent)
+{
+	struct dpu_core_perf *perf = &dpu_kms->perf;
+	const struct dpu_mdss_cfg *catalog = perf->catalog;
+	struct dentry *entry;
+
+	entry = debugfs_create_dir("core_perf", parent);
+
+	debugfs_create_u64("max_core_clk_rate", 0600, entry,
+			&perf->max_core_clk_rate);
+	debugfs_create_u64("core_clk_rate", 0600, entry,
+			&perf->core_clk_rate);
+	debugfs_create_u32("enable_bw_release", 0600, entry,
+			(u32 *)&perf->enable_bw_release);
+	debugfs_create_u32("threshold_low", 0600, entry,
+			(u32 *)&catalog->perf->max_bw_low);
+	debugfs_create_u32("threshold_high", 0600, entry,
+			(u32 *)&catalog->perf->max_bw_high);
+	debugfs_create_u32("min_core_ib", 0600, entry,
+			(u32 *)&catalog->perf->min_core_ib);
+	debugfs_create_u32("min_llcc_ib", 0600, entry,
+			(u32 *)&catalog->perf->min_llcc_ib);
+	debugfs_create_u32("min_dram_ib", 0600, entry,
+			(u32 *)&catalog->perf->min_dram_ib);
+	debugfs_create_file("perf_mode", 0600, entry,
+			(u32 *)perf, &dpu_core_perf_mode_fops);
+	debugfs_create_u64("fix_core_clk_rate", 0600, entry,
+			&perf->fix_core_clk_rate);
+	debugfs_create_u64("fix_core_ib_vote", 0600, entry,
+			&perf->fix_core_ib_vote);
+	debugfs_create_u64("fix_core_ab_vote", 0600, entry,
+			&perf->fix_core_ab_vote);
+
+	return 0;
+}
+#endif
+
+void dpu_core_perf_destroy(struct dpu_core_perf *perf)
+{
+	if (!perf) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	perf->max_core_clk_rate = 0;
+	perf->core_clk = NULL;
+	perf->catalog = NULL;
+	perf->dev = NULL;
+}
+
+int dpu_core_perf_init(struct dpu_core_perf *perf,
+		struct drm_device *dev,
+		const struct dpu_mdss_cfg *catalog,
+		struct clk *core_clk)
+{
+	perf->dev = dev;
+	perf->catalog = catalog;
+	perf->core_clk = core_clk;
+
+	perf->max_core_clk_rate = clk_get_rate(core_clk);
+	if (!perf->max_core_clk_rate) {
+		DPU_DEBUG("optional max core clk rate, use default\n");
+		perf->max_core_clk_rate = DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
new file mode 100644
index 000000000..29bb8ee2b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -0,0 +1,121 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_CORE_PERF_H_
+#define _DPU_CORE_PERF_H_
+
+#include <linux/types.h>
+#include <linux/dcache.h>
+#include <linux/mutex.h>
+#include <drm/drm_crtc.h>
+
+#include "dpu_hw_catalog.h"
+
+#define	DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE	412500000
+
+/**
+ * struct dpu_core_perf_params - definition of performance parameters
+ * @max_per_pipe_ib: maximum instantaneous bandwidth request
+ * @bw_ctl: arbitrated bandwidth request
+ * @core_clk_rate: core clock rate request
+ */
+struct dpu_core_perf_params {
+	u64 max_per_pipe_ib;
+	u64 bw_ctl;
+	u64 core_clk_rate;
+};
+
+/**
+ * struct dpu_core_perf_tune - definition of performance tuning control
+ * @mode: performance mode
+ * @min_core_clk: minimum core clock
+ * @min_bus_vote: minimum bus vote
+ */
+struct dpu_core_perf_tune {
+	u32 mode;
+	u64 min_core_clk;
+	u64 min_bus_vote;
+};
+
+/**
+ * struct dpu_core_perf - definition of core performance context
+ * @dev: Pointer to drm device
+ * @debugfs_root: top level debug folder
+ * @catalog: Pointer to catalog configuration
+ * @core_clk: Pointer to the core clock
+ * @core_clk_rate: current core clock rate
+ * @max_core_clk_rate: maximum allowable core clock rate
+ * @perf_tune: debug control for performance tuning
+ * @enable_bw_release: debug control for bandwidth release
+ * @fix_core_clk_rate: fixed core clock request in Hz used in mode 2
+ * @fix_core_ib_vote: fixed core ib vote in bps used in mode 2
+ * @fix_core_ab_vote: fixed core ab vote in bps used in mode 2
+ */
+struct dpu_core_perf {
+	struct drm_device *dev;
+	struct dentry *debugfs_root;
+	const struct dpu_mdss_cfg *catalog;
+	struct clk *core_clk;
+	u64 core_clk_rate;
+	u64 max_core_clk_rate;
+	struct dpu_core_perf_tune perf_tune;
+	u32 enable_bw_release;
+	u64 fix_core_clk_rate;
+	u64 fix_core_ib_vote;
+	u64 fix_core_ab_vote;
+};
+
+/**
+ * dpu_core_perf_crtc_check - validate performance of the given crtc state
+ * @crtc: Pointer to crtc
+ * @state: Pointer to new crtc state
+ * return: zero if success, or error code otherwise
+ */
+int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
+		struct drm_crtc_state *state);
+
+/**
+ * dpu_core_perf_crtc_update - update performance of the given crtc
+ * @crtc: Pointer to crtc
+ * @params_changed: true if crtc parameters are modified
+ * @stop_req: true if this is a stop request
+ * return: zero if success, or error code otherwise
+ */
+int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
+		int params_changed, bool stop_req);
+
+/**
+ * dpu_core_perf_crtc_release_bw - release bandwidth of the given crtc
+ * @crtc: Pointer to crtc
+ */
+void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc);
+
+/**
+ * dpu_core_perf_destroy - destroy the given core performance context
+ * @perf: Pointer to core performance context
+ */
+void dpu_core_perf_destroy(struct dpu_core_perf *perf);
+
+/**
+ * dpu_core_perf_init - initialize the given core performance context
+ * @perf: Pointer to core performance context
+ * @dev: Pointer to drm device
+ * @catalog: Pointer to catalog
+ * @core_clk: pointer to core clock
+ */
+int dpu_core_perf_init(struct dpu_core_perf *perf,
+		struct drm_device *dev,
+		const struct dpu_mdss_cfg *catalog,
+		struct clk *core_clk);
+
+struct dpu_kms;
+
+/**
+ * dpu_core_perf_debugfs_init - initialize debugfs for core performance context
+ * @dpu_kms: Pointer to the dpu_kms struct
+ * @debugfs_parent: Pointer to parent debugfs
+ */
+int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent);
+
+#endif /* _DPU_CORE_PERF_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
new file mode 100644
index 000000000..5a5821e59
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -0,0 +1,1626 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2014-2021 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/sort.h>
+#include <linux/debugfs.h>
+#include <linux/ktime.h>
+#include <linux/bits.h>
+
+#include <drm/drm_atomic.h>
+#include <drm/drm_blend.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_flip_work.h>
+#include <drm/drm_framebuffer.h>
+#include <drm/drm_mode.h>
+#include <drm/drm_probe_helper.h>
+#include <drm/drm_rect.h>
+#include <drm/drm_vblank.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_dspp.h"
+#include "dpu_crtc.h"
+#include "dpu_plane.h"
+#include "dpu_encoder.h"
+#include "dpu_vbif.h"
+#include "dpu_core_perf.h"
+#include "dpu_trace.h"
+
+/* layer mixer index on dpu_crtc */
+#define LEFT_MIXER 0
+#define RIGHT_MIXER 1
+
+/* timeout in ms waiting for frame done */
+#define DPU_CRTC_FRAME_DONE_TIMEOUT_MS	60
+
+#define	CONVERT_S3_15(val) \
+	(((((u64)val) & ~BIT_ULL(63)) >> 17) & GENMASK_ULL(17, 0))
+
+static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
+{
+	struct msm_drm_private *priv = crtc->dev->dev_private;
+
+	return to_dpu_kms(priv->kms);
+}
+
+static void dpu_crtc_destroy(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+
+	if (!crtc)
+		return;
+
+	drm_crtc_cleanup(crtc);
+	kfree(dpu_crtc);
+}
+
+static struct drm_encoder *get_encoder_from_crtc(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_encoder *encoder;
+
+	drm_for_each_encoder(encoder, dev)
+		if (encoder->crtc == crtc)
+			return encoder;
+
+	return NULL;
+}
+
+static enum dpu_crtc_crc_source dpu_crtc_parse_crc_source(const char *src_name)
+{
+	if (!src_name ||
+	    !strcmp(src_name, "none"))
+		return DPU_CRTC_CRC_SOURCE_NONE;
+	if (!strcmp(src_name, "auto") ||
+	    !strcmp(src_name, "lm"))
+		return DPU_CRTC_CRC_SOURCE_LAYER_MIXER;
+	if (!strcmp(src_name, "encoder"))
+		return DPU_CRTC_CRC_SOURCE_ENCODER;
+
+	return DPU_CRTC_CRC_SOURCE_INVALID;
+}
+
+static int dpu_crtc_verify_crc_source(struct drm_crtc *crtc,
+		const char *src_name, size_t *values_cnt)
+{
+	enum dpu_crtc_crc_source source = dpu_crtc_parse_crc_source(src_name);
+	struct dpu_crtc_state *crtc_state = to_dpu_crtc_state(crtc->state);
+
+	if (source < 0) {
+		DRM_DEBUG_DRIVER("Invalid source %s for CRTC%d\n", src_name, crtc->index);
+		return -EINVAL;
+	}
+
+	if (source == DPU_CRTC_CRC_SOURCE_LAYER_MIXER) {
+		*values_cnt = crtc_state->num_mixers;
+	} else if (source == DPU_CRTC_CRC_SOURCE_ENCODER) {
+		struct drm_encoder *drm_enc;
+
+		*values_cnt = 0;
+
+		drm_for_each_encoder_mask(drm_enc, crtc->dev, crtc->state->encoder_mask)
+			*values_cnt += dpu_encoder_get_crc_values_cnt(drm_enc);
+	}
+
+	return 0;
+}
+
+static void dpu_crtc_setup_lm_misr(struct dpu_crtc_state *crtc_state)
+{
+	struct dpu_crtc_mixer *m;
+	int i;
+
+	for (i = 0; i < crtc_state->num_mixers; ++i) {
+		m = &crtc_state->mixers[i];
+
+		if (!m->hw_lm || !m->hw_lm->ops.setup_misr)
+			continue;
+
+		/* Calculate MISR over 1 frame */
+		m->hw_lm->ops.setup_misr(m->hw_lm);
+	}
+}
+
+static void dpu_crtc_setup_encoder_misr(struct drm_crtc *crtc)
+{
+	struct drm_encoder *drm_enc;
+
+	drm_for_each_encoder_mask(drm_enc, crtc->dev, crtc->state->encoder_mask)
+		dpu_encoder_setup_misr(drm_enc);
+}
+
+static int dpu_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name)
+{
+	enum dpu_crtc_crc_source source = dpu_crtc_parse_crc_source(src_name);
+	enum dpu_crtc_crc_source current_source;
+	struct dpu_crtc_state *crtc_state;
+	struct drm_device *drm_dev = crtc->dev;
+
+	bool was_enabled;
+	bool enable = false;
+	int ret = 0;
+
+	if (source < 0) {
+		DRM_DEBUG_DRIVER("Invalid CRC source %s for CRTC%d\n", src_name, crtc->index);
+		return -EINVAL;
+	}
+
+	ret = drm_modeset_lock(&crtc->mutex, NULL);
+
+	if (ret)
+		return ret;
+
+	enable = (source != DPU_CRTC_CRC_SOURCE_NONE);
+	crtc_state = to_dpu_crtc_state(crtc->state);
+
+	spin_lock_irq(&drm_dev->event_lock);
+	current_source = crtc_state->crc_source;
+	spin_unlock_irq(&drm_dev->event_lock);
+
+	was_enabled = (current_source != DPU_CRTC_CRC_SOURCE_NONE);
+
+	if (!was_enabled && enable) {
+		ret = drm_crtc_vblank_get(crtc);
+
+		if (ret)
+			goto cleanup;
+
+	} else if (was_enabled && !enable) {
+		drm_crtc_vblank_put(crtc);
+	}
+
+	spin_lock_irq(&drm_dev->event_lock);
+	crtc_state->crc_source = source;
+	spin_unlock_irq(&drm_dev->event_lock);
+
+	crtc_state->crc_frame_skip_count = 0;
+
+	if (source == DPU_CRTC_CRC_SOURCE_LAYER_MIXER)
+		dpu_crtc_setup_lm_misr(crtc_state);
+	else if (source == DPU_CRTC_CRC_SOURCE_ENCODER)
+		dpu_crtc_setup_encoder_misr(crtc);
+	else
+		ret = -EINVAL;
+
+cleanup:
+	drm_modeset_unlock(&crtc->mutex);
+
+	return ret;
+}
+
+static u32 dpu_crtc_get_vblank_counter(struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder = get_encoder_from_crtc(crtc);
+	if (!encoder) {
+		DRM_ERROR("no encoder found for crtc %d\n", crtc->index);
+		return 0;
+	}
+
+	return dpu_encoder_get_vsync_count(encoder);
+}
+
+static int dpu_crtc_get_lm_crc(struct drm_crtc *crtc,
+		struct dpu_crtc_state *crtc_state)
+{
+	struct dpu_crtc_mixer *m;
+	u32 crcs[CRTC_DUAL_MIXERS];
+
+	int rc = 0;
+	int i;
+
+	BUILD_BUG_ON(ARRAY_SIZE(crcs) != ARRAY_SIZE(crtc_state->mixers));
+
+	for (i = 0; i < crtc_state->num_mixers; ++i) {
+
+		m = &crtc_state->mixers[i];
+
+		if (!m->hw_lm || !m->hw_lm->ops.collect_misr)
+			continue;
+
+		rc = m->hw_lm->ops.collect_misr(m->hw_lm, &crcs[i]);
+
+		if (rc) {
+			if (rc != -ENODATA)
+				DRM_DEBUG_DRIVER("MISR read failed\n");
+			return rc;
+		}
+	}
+
+	return drm_crtc_add_crc_entry(crtc, true,
+			drm_crtc_accurate_vblank_count(crtc), crcs);
+}
+
+static int dpu_crtc_get_encoder_crc(struct drm_crtc *crtc)
+{
+	struct drm_encoder *drm_enc;
+	int rc, pos = 0;
+	u32 crcs[INTF_MAX];
+
+	drm_for_each_encoder_mask(drm_enc, crtc->dev, crtc->state->encoder_mask) {
+		rc = dpu_encoder_get_crc(drm_enc, crcs, pos);
+		if (rc < 0) {
+			if (rc != -ENODATA)
+				DRM_DEBUG_DRIVER("MISR read failed\n");
+
+			return rc;
+		}
+
+		pos += rc;
+	}
+
+	return drm_crtc_add_crc_entry(crtc, true,
+			drm_crtc_accurate_vblank_count(crtc), crcs);
+}
+
+static int dpu_crtc_get_crc(struct drm_crtc *crtc)
+{
+	struct dpu_crtc_state *crtc_state = to_dpu_crtc_state(crtc->state);
+
+	/* Skip first 2 frames in case of "uncooked" CRCs */
+	if (crtc_state->crc_frame_skip_count < 2) {
+		crtc_state->crc_frame_skip_count++;
+		return 0;
+	}
+
+	if (crtc_state->crc_source == DPU_CRTC_CRC_SOURCE_LAYER_MIXER)
+		return dpu_crtc_get_lm_crc(crtc, crtc_state);
+	else if (crtc_state->crc_source == DPU_CRTC_CRC_SOURCE_ENCODER)
+		return dpu_crtc_get_encoder_crc(crtc);
+
+	return -EINVAL;
+}
+
+static bool dpu_crtc_get_scanout_position(struct drm_crtc *crtc,
+					   bool in_vblank_irq,
+					   int *vpos, int *hpos,
+					   ktime_t *stime, ktime_t *etime,
+					   const struct drm_display_mode *mode)
+{
+	unsigned int pipe = crtc->index;
+	struct drm_encoder *encoder;
+	int line, vsw, vbp, vactive_start, vactive_end, vfp_end;
+
+	encoder = get_encoder_from_crtc(crtc);
+	if (!encoder) {
+		DRM_ERROR("no encoder found for crtc %d\n", pipe);
+		return false;
+	}
+
+	vsw = mode->crtc_vsync_end - mode->crtc_vsync_start;
+	vbp = mode->crtc_vtotal - mode->crtc_vsync_end;
+
+	/*
+	 * the line counter is 1 at the start of the VSYNC pulse and VTOTAL at
+	 * the end of VFP. Translate the porch values relative to the line
+	 * counter positions.
+	 */
+
+	vactive_start = vsw + vbp + 1;
+	vactive_end = vactive_start + mode->crtc_vdisplay;
+
+	/* last scan line before VSYNC */
+	vfp_end = mode->crtc_vtotal;
+
+	if (stime)
+		*stime = ktime_get();
+
+	line = dpu_encoder_get_linecount(encoder);
+
+	if (line < vactive_start)
+		line -= vactive_start;
+	else if (line > vactive_end)
+		line = line - vfp_end - vactive_start;
+	else
+		line -= vactive_start;
+
+	*vpos = line;
+	*hpos = 0;
+
+	if (etime)
+		*etime = ktime_get();
+
+	return true;
+}
+
+static void _dpu_crtc_setup_blend_cfg(struct dpu_crtc_mixer *mixer,
+		struct dpu_plane_state *pstate, struct dpu_format *format)
+{
+	struct dpu_hw_mixer *lm = mixer->hw_lm;
+	uint32_t blend_op;
+	uint32_t fg_alpha, bg_alpha;
+
+	fg_alpha = pstate->base.alpha >> 8;
+	bg_alpha = 0xff - fg_alpha;
+
+	/* default to opaque blending */
+	if (pstate->base.pixel_blend_mode == DRM_MODE_BLEND_PIXEL_NONE ||
+	    !format->alpha_enable) {
+		blend_op = DPU_BLEND_FG_ALPHA_FG_CONST |
+			DPU_BLEND_BG_ALPHA_BG_CONST;
+	} else if (pstate->base.pixel_blend_mode == DRM_MODE_BLEND_PREMULTI) {
+		blend_op = DPU_BLEND_FG_ALPHA_FG_CONST |
+			DPU_BLEND_BG_ALPHA_FG_PIXEL;
+		if (fg_alpha != 0xff) {
+			bg_alpha = fg_alpha;
+			blend_op |= DPU_BLEND_BG_MOD_ALPHA |
+				    DPU_BLEND_BG_INV_MOD_ALPHA;
+		} else {
+			blend_op |= DPU_BLEND_BG_INV_ALPHA;
+		}
+	} else {
+		/* coverage blending */
+		blend_op = DPU_BLEND_FG_ALPHA_FG_PIXEL |
+			DPU_BLEND_BG_ALPHA_FG_PIXEL;
+		if (fg_alpha != 0xff) {
+			bg_alpha = fg_alpha;
+			blend_op |= DPU_BLEND_FG_MOD_ALPHA |
+				    DPU_BLEND_FG_INV_MOD_ALPHA |
+				    DPU_BLEND_BG_MOD_ALPHA |
+				    DPU_BLEND_BG_INV_MOD_ALPHA;
+		} else {
+			blend_op |= DPU_BLEND_BG_INV_ALPHA;
+		}
+	}
+
+	lm->ops.setup_blend_config(lm, pstate->stage,
+				fg_alpha, bg_alpha, blend_op);
+
+	DRM_DEBUG_ATOMIC("format:%p4cc, alpha_en:%u blend_op:0x%x\n",
+		  &format->base.pixel_format, format->alpha_enable, blend_op);
+}
+
+static void _dpu_crtc_program_lm_output_roi(struct drm_crtc *crtc)
+{
+	struct dpu_crtc_state *crtc_state;
+	int lm_idx, lm_horiz_position;
+
+	crtc_state = to_dpu_crtc_state(crtc->state);
+
+	lm_horiz_position = 0;
+	for (lm_idx = 0; lm_idx < crtc_state->num_mixers; lm_idx++) {
+		const struct drm_rect *lm_roi = &crtc_state->lm_bounds[lm_idx];
+		struct dpu_hw_mixer *hw_lm = crtc_state->mixers[lm_idx].hw_lm;
+		struct dpu_hw_mixer_cfg cfg;
+
+		if (!lm_roi || !drm_rect_visible(lm_roi))
+			continue;
+
+		cfg.out_width = drm_rect_width(lm_roi);
+		cfg.out_height = drm_rect_height(lm_roi);
+		cfg.right_mixer = lm_horiz_position++;
+		cfg.flags = 0;
+		hw_lm->ops.setup_mixer_out(hw_lm, &cfg);
+	}
+}
+
+static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc,
+	struct dpu_crtc *dpu_crtc, struct dpu_crtc_mixer *mixer,
+	struct dpu_hw_stage_cfg *stage_cfg)
+{
+	struct drm_plane *plane;
+	struct drm_framebuffer *fb;
+	struct drm_plane_state *state;
+	struct dpu_crtc_state *cstate = to_dpu_crtc_state(crtc->state);
+	struct dpu_plane_state *pstate = NULL;
+	struct dpu_format *format;
+	struct dpu_hw_ctl *ctl = mixer->lm_ctl;
+
+	uint32_t stage_idx, lm_idx;
+	int zpos_cnt[DPU_STAGE_MAX + 1] = { 0 };
+	bool bg_alpha_enable = false;
+	DECLARE_BITMAP(fetch_active, SSPP_MAX);
+
+	memset(fetch_active, 0, sizeof(fetch_active));
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		enum dpu_sspp sspp_idx;
+
+		state = plane->state;
+		if (!state)
+			continue;
+
+		if (!state->visible)
+			continue;
+
+		pstate = to_dpu_plane_state(state);
+		fb = state->fb;
+
+		sspp_idx = dpu_plane_pipe(plane);
+		set_bit(sspp_idx, fetch_active);
+
+		DRM_DEBUG_ATOMIC("crtc %d stage:%d - plane %d sspp %d fb %d\n",
+				crtc->base.id,
+				pstate->stage,
+				plane->base.id,
+				sspp_idx - SSPP_VIG0,
+				state->fb ? state->fb->base.id : -1);
+
+		format = to_dpu_format(msm_framebuffer_format(pstate->base.fb));
+
+		if (pstate->stage == DPU_STAGE_BASE && format->alpha_enable)
+			bg_alpha_enable = true;
+
+		stage_idx = zpos_cnt[pstate->stage]++;
+		stage_cfg->stage[pstate->stage][stage_idx] =
+					sspp_idx;
+		stage_cfg->multirect_index[pstate->stage][stage_idx] =
+					pstate->multirect_index;
+
+		trace_dpu_crtc_setup_mixer(DRMID(crtc), DRMID(plane),
+					   state, pstate, stage_idx,
+					   sspp_idx - SSPP_VIG0,
+					   format->base.pixel_format,
+					   fb ? fb->modifier : 0);
+
+		/* blend config update */
+		for (lm_idx = 0; lm_idx < cstate->num_mixers; lm_idx++) {
+			_dpu_crtc_setup_blend_cfg(mixer + lm_idx,
+						pstate, format);
+
+			mixer[lm_idx].lm_ctl->ops.update_pending_flush_sspp(mixer[lm_idx].lm_ctl,
+									    sspp_idx);
+
+			if (bg_alpha_enable && !format->alpha_enable)
+				mixer[lm_idx].mixer_op_mode = 0;
+			else
+				mixer[lm_idx].mixer_op_mode |=
+						1 << pstate->stage;
+		}
+	}
+
+	if (ctl->ops.set_active_pipes)
+		ctl->ops.set_active_pipes(ctl, fetch_active);
+
+	_dpu_crtc_program_lm_output_roi(crtc);
+}
+
+/**
+ * _dpu_crtc_blend_setup - configure crtc mixers
+ * @crtc: Pointer to drm crtc structure
+ */
+static void _dpu_crtc_blend_setup(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct dpu_crtc_state *cstate = to_dpu_crtc_state(crtc->state);
+	struct dpu_crtc_mixer *mixer = cstate->mixers;
+	struct dpu_hw_ctl *ctl;
+	struct dpu_hw_mixer *lm;
+	struct dpu_hw_stage_cfg stage_cfg;
+	int i;
+
+	DRM_DEBUG_ATOMIC("%s\n", dpu_crtc->name);
+
+	for (i = 0; i < cstate->num_mixers; i++) {
+		mixer[i].mixer_op_mode = 0;
+		if (mixer[i].lm_ctl->ops.clear_all_blendstages)
+			mixer[i].lm_ctl->ops.clear_all_blendstages(
+					mixer[i].lm_ctl);
+	}
+
+	/* initialize stage cfg */
+	memset(&stage_cfg, 0, sizeof(struct dpu_hw_stage_cfg));
+
+	_dpu_crtc_blend_setup_mixer(crtc, dpu_crtc, mixer, &stage_cfg);
+
+	for (i = 0; i < cstate->num_mixers; i++) {
+		ctl = mixer[i].lm_ctl;
+		lm = mixer[i].hw_lm;
+
+		lm->ops.setup_alpha_out(lm, mixer[i].mixer_op_mode);
+
+		/* stage config flush mask */
+		ctl->ops.update_pending_flush_mixer(ctl,
+			mixer[i].hw_lm->idx);
+
+		DRM_DEBUG_ATOMIC("lm %d, op_mode 0x%X, ctl %d\n",
+			mixer[i].hw_lm->idx - LM_0,
+			mixer[i].mixer_op_mode,
+			ctl->idx - CTL_0);
+
+		ctl->ops.setup_blendstage(ctl, mixer[i].hw_lm->idx,
+			&stage_cfg);
+	}
+}
+
+/**
+ *  _dpu_crtc_complete_flip - signal pending page_flip events
+ * Any pending vblank events are added to the vblank_event_list
+ * so that the next vblank interrupt shall signal them.
+ * However PAGE_FLIP events are not handled through the vblank_event_list.
+ * This API signals any pending PAGE_FLIP events requested through
+ * DRM_IOCTL_MODE_PAGE_FLIP and are cached in the dpu_crtc->event.
+ * @crtc: Pointer to drm crtc structure
+ */
+static void _dpu_crtc_complete_flip(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+	if (dpu_crtc->event) {
+		DRM_DEBUG_VBL("%s: send event: %pK\n", dpu_crtc->name,
+			      dpu_crtc->event);
+		trace_dpu_crtc_complete_flip(DRMID(crtc));
+		drm_crtc_send_vblank_event(crtc, dpu_crtc->event);
+		dpu_crtc->event = NULL;
+	}
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
+enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+
+	/*
+	 * TODO: This function is called from dpu debugfs and as part of atomic
+	 * check. When called from debugfs, the crtc->mutex must be held to
+	 * read crtc->state. However reading crtc->state from atomic check isn't
+	 * allowed (unless you have a good reason, a big comment, and a deep
+	 * understanding of how the atomic/modeset locks work (<- and this is
+	 * probably not possible)). So we'll keep the WARN_ON here for now, but
+	 * really we need to figure out a better way to track our operating mode
+	 */
+	WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
+
+	/* TODO: Returns the first INTF_MODE, could there be multiple values? */
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
+		return dpu_encoder_get_intf_mode(encoder);
+
+	return INTF_MODE_NONE;
+}
+
+void dpu_crtc_vblank_callback(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+
+	/* keep statistics on vblank callback - with auto reset via debugfs */
+	if (ktime_compare(dpu_crtc->vblank_cb_time, ktime_set(0, 0)) == 0)
+		dpu_crtc->vblank_cb_time = ktime_get();
+	else
+		dpu_crtc->vblank_cb_count++;
+
+	dpu_crtc_get_crc(crtc);
+
+	drm_crtc_handle_vblank(crtc);
+	trace_dpu_crtc_vblank_cb(DRMID(crtc));
+}
+
+static void dpu_crtc_frame_event_work(struct kthread_work *work)
+{
+	struct dpu_crtc_frame_event *fevent = container_of(work,
+			struct dpu_crtc_frame_event, work);
+	struct drm_crtc *crtc = fevent->crtc;
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	unsigned long flags;
+	bool frame_done = false;
+
+	DPU_ATRACE_BEGIN("crtc_frame_event");
+
+	DRM_DEBUG_ATOMIC("crtc%d event:%u ts:%lld\n", crtc->base.id, fevent->event,
+			ktime_to_ns(fevent->ts));
+
+	if (fevent->event & (DPU_ENCODER_FRAME_EVENT_DONE
+				| DPU_ENCODER_FRAME_EVENT_ERROR
+				| DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)) {
+
+		if (atomic_read(&dpu_crtc->frame_pending) < 1) {
+			/* ignore vblank when not pending */
+		} else if (atomic_dec_return(&dpu_crtc->frame_pending) == 0) {
+			/* release bandwidth and other resources */
+			trace_dpu_crtc_frame_event_done(DRMID(crtc),
+							fevent->event);
+			dpu_core_perf_crtc_release_bw(crtc);
+		} else {
+			trace_dpu_crtc_frame_event_more_pending(DRMID(crtc),
+								fevent->event);
+		}
+
+		if (fevent->event & (DPU_ENCODER_FRAME_EVENT_DONE
+					| DPU_ENCODER_FRAME_EVENT_ERROR))
+			frame_done = true;
+	}
+
+	if (fevent->event & DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)
+		DPU_ERROR("crtc%d ts:%lld received panel dead event\n",
+				crtc->base.id, ktime_to_ns(fevent->ts));
+
+	if (frame_done)
+		complete_all(&dpu_crtc->frame_done_comp);
+
+	spin_lock_irqsave(&dpu_crtc->spin_lock, flags);
+	list_add_tail(&fevent->list, &dpu_crtc->frame_event_list);
+	spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags);
+	DPU_ATRACE_END("crtc_frame_event");
+}
+
+/*
+ * dpu_crtc_frame_event_cb - crtc frame event callback API. CRTC module
+ * registers this API to encoder for all frame event callbacks like
+ * frame_error, frame_done, idle_timeout, etc. Encoder may call different events
+ * from different context - IRQ, user thread, commit_thread, etc. Each event
+ * should be carefully reviewed and should be processed in proper task context
+ * to avoid schedulin delay or properly manage the irq context's bottom half
+ * processing.
+ */
+static void dpu_crtc_frame_event_cb(void *data, u32 event)
+{
+	struct drm_crtc *crtc = (struct drm_crtc *)data;
+	struct dpu_crtc *dpu_crtc;
+	struct msm_drm_private *priv;
+	struct dpu_crtc_frame_event *fevent;
+	unsigned long flags;
+	u32 crtc_id;
+
+	/* Nothing to do on idle event */
+	if (event & DPU_ENCODER_FRAME_EVENT_IDLE)
+		return;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	priv = crtc->dev->dev_private;
+	crtc_id = drm_crtc_index(crtc);
+
+	trace_dpu_crtc_frame_event_cb(DRMID(crtc), event);
+
+	spin_lock_irqsave(&dpu_crtc->spin_lock, flags);
+	fevent = list_first_entry_or_null(&dpu_crtc->frame_event_list,
+			struct dpu_crtc_frame_event, list);
+	if (fevent)
+		list_del_init(&fevent->list);
+	spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags);
+
+	if (!fevent) {
+		DRM_ERROR_RATELIMITED("crtc%d event %d overflow\n", crtc->base.id, event);
+		return;
+	}
+
+	fevent->event = event;
+	fevent->crtc = crtc;
+	fevent->ts = ktime_get();
+	kthread_queue_work(priv->event_thread[crtc_id].worker, &fevent->work);
+}
+
+void dpu_crtc_complete_commit(struct drm_crtc *crtc)
+{
+	trace_dpu_crtc_complete_commit(DRMID(crtc));
+	dpu_core_perf_crtc_update(crtc, 0, false);
+	_dpu_crtc_complete_flip(crtc);
+}
+
+static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	struct dpu_crtc_state *cstate = to_dpu_crtc_state(state);
+	struct drm_display_mode *adj_mode = &state->adjusted_mode;
+	u32 crtc_split_width = adj_mode->hdisplay / cstate->num_mixers;
+	int i;
+
+	for (i = 0; i < cstate->num_mixers; i++) {
+		struct drm_rect *r = &cstate->lm_bounds[i];
+		r->x1 = crtc_split_width * i;
+		r->y1 = 0;
+		r->x2 = r->x1 + crtc_split_width;
+		r->y2 = adj_mode->vdisplay;
+
+		trace_dpu_crtc_setup_lm_bounds(DRMID(crtc), i, r);
+	}
+}
+
+static void _dpu_crtc_get_pcc_coeff(struct drm_crtc_state *state,
+		struct dpu_hw_pcc_cfg *cfg)
+{
+	struct drm_color_ctm *ctm;
+
+	memset(cfg, 0, sizeof(struct dpu_hw_pcc_cfg));
+
+	ctm = (struct drm_color_ctm *)state->ctm->data;
+
+	if (!ctm)
+		return;
+
+	cfg->r.r = CONVERT_S3_15(ctm->matrix[0]);
+	cfg->g.r = CONVERT_S3_15(ctm->matrix[1]);
+	cfg->b.r = CONVERT_S3_15(ctm->matrix[2]);
+
+	cfg->r.g = CONVERT_S3_15(ctm->matrix[3]);
+	cfg->g.g = CONVERT_S3_15(ctm->matrix[4]);
+	cfg->b.g = CONVERT_S3_15(ctm->matrix[5]);
+
+	cfg->r.b = CONVERT_S3_15(ctm->matrix[6]);
+	cfg->g.b = CONVERT_S3_15(ctm->matrix[7]);
+	cfg->b.b = CONVERT_S3_15(ctm->matrix[8]);
+}
+
+static void _dpu_crtc_setup_cp_blocks(struct drm_crtc *crtc)
+{
+	struct drm_crtc_state *state = crtc->state;
+	struct dpu_crtc_state *cstate = to_dpu_crtc_state(crtc->state);
+	struct dpu_crtc_mixer *mixer = cstate->mixers;
+	struct dpu_hw_pcc_cfg cfg;
+	struct dpu_hw_ctl *ctl;
+	struct dpu_hw_dspp *dspp;
+	int i;
+
+
+	if (!state->color_mgmt_changed)
+		return;
+
+	for (i = 0; i < cstate->num_mixers; i++) {
+		ctl = mixer[i].lm_ctl;
+		dspp = mixer[i].hw_dspp;
+
+		if (!dspp || !dspp->ops.setup_pcc)
+			continue;
+
+		if (!state->ctm) {
+			dspp->ops.setup_pcc(dspp, NULL);
+		} else {
+			_dpu_crtc_get_pcc_coeff(state, &cfg);
+			dspp->ops.setup_pcc(dspp, &cfg);
+		}
+
+		/* stage config flush mask */
+		ctl->ops.update_pending_flush_dspp(ctl,
+			mixer[i].hw_dspp->idx);
+	}
+}
+
+static void dpu_crtc_atomic_begin(struct drm_crtc *crtc,
+		struct drm_atomic_state *state)
+{
+	struct dpu_crtc_state *cstate = to_dpu_crtc_state(crtc->state);
+	struct drm_encoder *encoder;
+
+	if (!crtc->state->enable) {
+		DRM_DEBUG_ATOMIC("crtc%d -> enable %d, skip atomic_begin\n",
+				crtc->base.id, crtc->state->enable);
+		return;
+	}
+
+	DRM_DEBUG_ATOMIC("crtc%d\n", crtc->base.id);
+
+	_dpu_crtc_setup_lm_bounds(crtc, crtc->state);
+
+	/* encoder will trigger pending mask now */
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
+		dpu_encoder_trigger_kickoff_pending(encoder);
+
+	/*
+	 * If no mixers have been allocated in dpu_crtc_atomic_check(),
+	 * it means we are trying to flush a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!cstate->num_mixers))
+		return;
+
+	_dpu_crtc_blend_setup(crtc);
+
+	_dpu_crtc_setup_cp_blocks(crtc);
+
+	/*
+	 * PP_DONE irq is only used by command mode for now.
+	 * It is better to request pending before FLUSH and START trigger
+	 * to make sure no pp_done irq missed.
+	 * This is safe because no pp_done will happen before SW trigger
+	 * in command mode.
+	 */
+}
+
+static void dpu_crtc_atomic_flush(struct drm_crtc *crtc,
+		struct drm_atomic_state *state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct drm_device *dev;
+	struct drm_plane *plane;
+	struct msm_drm_private *priv;
+	unsigned long flags;
+	struct dpu_crtc_state *cstate;
+
+	if (!crtc->state->enable) {
+		DRM_DEBUG_ATOMIC("crtc%d -> enable %d, skip atomic_flush\n",
+				crtc->base.id, crtc->state->enable);
+		return;
+	}
+
+	DRM_DEBUG_ATOMIC("crtc%d\n", crtc->base.id);
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(crtc->state);
+	dev = crtc->dev;
+	priv = dev->dev_private;
+
+	if (crtc->index >= ARRAY_SIZE(priv->event_thread)) {
+		DPU_ERROR("invalid crtc index[%d]\n", crtc->index);
+		return;
+	}
+
+	WARN_ON(dpu_crtc->event);
+	spin_lock_irqsave(&dev->event_lock, flags);
+	dpu_crtc->event = crtc->state->event;
+	crtc->state->event = NULL;
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+
+	/*
+	 * If no mixers has been allocated in dpu_crtc_atomic_check(),
+	 * it means we are trying to flush a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!cstate->num_mixers))
+		return;
+
+	/* update performance setting before crtc kickoff */
+	dpu_core_perf_crtc_update(crtc, 1, false);
+
+	/*
+	 * Final plane updates: Give each plane a chance to complete all
+	 *                      required writes/flushing before crtc's "flush
+	 *                      everything" call below.
+	 */
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		if (dpu_crtc->smmu_state.transition_error)
+			dpu_plane_set_error(plane, true);
+		dpu_plane_flush(plane);
+	}
+
+	/* Kickoff will be scheduled by outer layer */
+}
+
+/**
+ * dpu_crtc_destroy_state - state destroy hook
+ * @crtc: drm CRTC
+ * @state: CRTC state object to release
+ */
+static void dpu_crtc_destroy_state(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	struct dpu_crtc_state *cstate = to_dpu_crtc_state(state);
+
+	DRM_DEBUG_ATOMIC("crtc%d\n", crtc->base.id);
+
+	__drm_atomic_helper_crtc_destroy_state(state);
+
+	kfree(cstate);
+}
+
+static int _dpu_crtc_wait_for_frame_done(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	int ret, rc = 0;
+
+	if (!atomic_read(&dpu_crtc->frame_pending)) {
+		DRM_DEBUG_ATOMIC("no frames pending\n");
+		return 0;
+	}
+
+	DPU_ATRACE_BEGIN("frame done completion wait");
+	ret = wait_for_completion_timeout(&dpu_crtc->frame_done_comp,
+			msecs_to_jiffies(DPU_CRTC_FRAME_DONE_TIMEOUT_MS));
+	if (!ret) {
+		DRM_ERROR("frame done wait timed out, ret:%d\n", ret);
+		rc = -ETIMEDOUT;
+	}
+	DPU_ATRACE_END("frame done completion wait");
+
+	return rc;
+}
+
+void dpu_crtc_commit_kickoff(struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc);
+	struct dpu_crtc_state *cstate = to_dpu_crtc_state(crtc->state);
+
+	/*
+	 * If no mixers has been allocated in dpu_crtc_atomic_check(),
+	 * it means we are trying to start a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!cstate->num_mixers))
+		return;
+
+	DPU_ATRACE_BEGIN("crtc_commit");
+
+	drm_for_each_encoder_mask(encoder, crtc->dev,
+			crtc->state->encoder_mask) {
+		if (!dpu_encoder_is_valid_for_commit(encoder)) {
+			DRM_DEBUG_ATOMIC("invalid FB not kicking off crtc\n");
+			goto end;
+		}
+	}
+	/*
+	 * Encoder will flush/start now, unless it has a tx pending. If so, it
+	 * may delay and flush at an irq event (e.g. ppdone)
+	 */
+	drm_for_each_encoder_mask(encoder, crtc->dev,
+				  crtc->state->encoder_mask)
+		dpu_encoder_prepare_for_kickoff(encoder);
+
+	if (atomic_inc_return(&dpu_crtc->frame_pending) == 1) {
+		/* acquire bandwidth and other resources */
+		DRM_DEBUG_ATOMIC("crtc%d first commit\n", crtc->base.id);
+	} else
+		DRM_DEBUG_ATOMIC("crtc%d commit\n", crtc->base.id);
+
+	dpu_crtc->play_count++;
+
+	dpu_vbif_clear_errors(dpu_kms);
+
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
+		dpu_encoder_kickoff(encoder);
+
+	reinit_completion(&dpu_crtc->frame_done_comp);
+
+end:
+	DPU_ATRACE_END("crtc_commit");
+}
+
+static void dpu_crtc_reset(struct drm_crtc *crtc)
+{
+	struct dpu_crtc_state *cstate = kzalloc(sizeof(*cstate), GFP_KERNEL);
+
+	if (crtc->state)
+		dpu_crtc_destroy_state(crtc, crtc->state);
+
+	if (cstate)
+		__drm_atomic_helper_crtc_reset(crtc, &cstate->base);
+	else
+		__drm_atomic_helper_crtc_reset(crtc, NULL);
+}
+
+/**
+ * dpu_crtc_duplicate_state - state duplicate hook
+ * @crtc: Pointer to drm crtc structure
+ */
+static struct drm_crtc_state *dpu_crtc_duplicate_state(struct drm_crtc *crtc)
+{
+	struct dpu_crtc_state *cstate, *old_cstate = to_dpu_crtc_state(crtc->state);
+
+	cstate = kmemdup(old_cstate, sizeof(*old_cstate), GFP_KERNEL);
+	if (!cstate) {
+		DPU_ERROR("failed to allocate state\n");
+		return NULL;
+	}
+
+	/* duplicate base helper */
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &cstate->base);
+
+	return &cstate->base;
+}
+
+static void dpu_crtc_atomic_print_state(struct drm_printer *p,
+					const struct drm_crtc_state *state)
+{
+	const struct dpu_crtc_state *cstate = to_dpu_crtc_state(state);
+	int i;
+
+	for (i = 0; i < cstate->num_mixers; i++) {
+		drm_printf(p, "\tlm[%d]=%d\n", i, cstate->mixers[i].hw_lm->idx - LM_0);
+		drm_printf(p, "\tctl[%d]=%d\n", i, cstate->mixers[i].lm_ctl->idx - CTL_0);
+		if (cstate->mixers[i].hw_dspp)
+			drm_printf(p, "\tdspp[%d]=%d\n", i, cstate->mixers[i].hw_dspp->idx - DSPP_0);
+	}
+}
+
+static void dpu_crtc_disable(struct drm_crtc *crtc,
+			     struct drm_atomic_state *state)
+{
+	struct drm_crtc_state *old_crtc_state = drm_atomic_get_old_crtc_state(state,
+									      crtc);
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct dpu_crtc_state *cstate = to_dpu_crtc_state(crtc->state);
+	struct drm_encoder *encoder;
+	unsigned long flags;
+	bool release_bandwidth = false;
+
+	DRM_DEBUG_KMS("crtc%d\n", crtc->base.id);
+
+	/* Disable/save vblank irq handling */
+	drm_crtc_vblank_off(crtc);
+
+	drm_for_each_encoder_mask(encoder, crtc->dev,
+				  old_crtc_state->encoder_mask) {
+		/* in video mode, we hold an extra bandwidth reference
+		 * as we cannot drop bandwidth at frame-done if any
+		 * crtc is being used in video mode.
+		 */
+		if (dpu_encoder_get_intf_mode(encoder) == INTF_MODE_VIDEO)
+			release_bandwidth = true;
+		dpu_encoder_assign_crtc(encoder, NULL);
+	}
+
+	/* wait for frame_event_done completion */
+	if (_dpu_crtc_wait_for_frame_done(crtc))
+		DPU_ERROR("crtc%d wait for frame done failed;frame_pending%d\n",
+				crtc->base.id,
+				atomic_read(&dpu_crtc->frame_pending));
+
+	trace_dpu_crtc_disable(DRMID(crtc), false, dpu_crtc);
+	dpu_crtc->enabled = false;
+
+	if (atomic_read(&dpu_crtc->frame_pending)) {
+		trace_dpu_crtc_disable_frame_pending(DRMID(crtc),
+				     atomic_read(&dpu_crtc->frame_pending));
+		if (release_bandwidth)
+			dpu_core_perf_crtc_release_bw(crtc);
+		atomic_set(&dpu_crtc->frame_pending, 0);
+	}
+
+	dpu_core_perf_crtc_update(crtc, 0, true);
+
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
+		dpu_encoder_register_frame_event_callback(encoder, NULL, NULL);
+
+	memset(cstate->mixers, 0, sizeof(cstate->mixers));
+	cstate->num_mixers = 0;
+
+	/* disable clk & bw control until clk & bw properties are set */
+	cstate->bw_control = false;
+	cstate->bw_split_vote = false;
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		crtc->state->event = NULL;
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+	}
+
+	pm_runtime_put_sync(crtc->dev->dev);
+}
+
+static void dpu_crtc_enable(struct drm_crtc *crtc,
+		struct drm_atomic_state *state)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct drm_encoder *encoder;
+	bool request_bandwidth = false;
+
+	pm_runtime_get_sync(crtc->dev->dev);
+
+	DRM_DEBUG_KMS("crtc%d\n", crtc->base.id);
+
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask) {
+		/* in video mode, we hold an extra bandwidth reference
+		 * as we cannot drop bandwidth at frame-done if any
+		 * crtc is being used in video mode.
+		 */
+		if (dpu_encoder_get_intf_mode(encoder) == INTF_MODE_VIDEO)
+			request_bandwidth = true;
+		dpu_encoder_register_frame_event_callback(encoder,
+				dpu_crtc_frame_event_cb, (void *)crtc);
+	}
+
+	if (request_bandwidth)
+		atomic_inc(&_dpu_crtc_get_kms(crtc)->bandwidth_ref);
+
+	trace_dpu_crtc_enable(DRMID(crtc), true, dpu_crtc);
+	dpu_crtc->enabled = true;
+
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
+		dpu_encoder_assign_crtc(encoder, crtc);
+
+	/* Enable/restore vblank irq handling */
+	drm_crtc_vblank_on(crtc);
+}
+
+struct plane_state {
+	struct dpu_plane_state *dpu_pstate;
+	const struct drm_plane_state *drm_pstate;
+	int stage;
+	u32 pipe_id;
+};
+
+static bool dpu_crtc_needs_dirtyfb(struct drm_crtc_state *cstate)
+{
+	struct drm_crtc *crtc = cstate->crtc;
+	struct drm_encoder *encoder;
+
+	drm_for_each_encoder_mask (encoder, crtc->dev, cstate->encoder_mask) {
+		if (dpu_encoder_get_intf_mode(encoder) == INTF_MODE_CMD) {
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
+		struct drm_atomic_state *state)
+{
+	struct drm_crtc_state *crtc_state = drm_atomic_get_new_crtc_state(state,
+									  crtc);
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct dpu_crtc_state *cstate = to_dpu_crtc_state(crtc_state);
+	struct plane_state *pstates;
+
+	const struct drm_plane_state *pstate;
+	struct drm_plane *plane;
+	struct drm_display_mode *mode;
+
+	int cnt = 0, rc = 0, mixer_width = 0, i, z_pos;
+
+	struct dpu_multirect_plane_states multirect_plane[DPU_STAGE_MAX * 2];
+	int multirect_count = 0;
+	const struct drm_plane_state *pipe_staged[SSPP_MAX];
+	int left_zpos_cnt = 0, right_zpos_cnt = 0;
+	struct drm_rect crtc_rect = { 0 };
+	bool needs_dirtyfb = dpu_crtc_needs_dirtyfb(crtc_state);
+
+	pstates = kzalloc(sizeof(*pstates) * DPU_STAGE_MAX * 4, GFP_KERNEL);
+	if (!pstates)
+		return -ENOMEM;
+
+	if (!crtc_state->enable || !crtc_state->active) {
+		DRM_DEBUG_ATOMIC("crtc%d -> enable %d, active %d, skip atomic_check\n",
+				crtc->base.id, crtc_state->enable,
+				crtc_state->active);
+		memset(&cstate->new_perf, 0, sizeof(cstate->new_perf));
+		goto end;
+	}
+
+	mode = &crtc_state->adjusted_mode;
+	DRM_DEBUG_ATOMIC("%s: check\n", dpu_crtc->name);
+
+	/* force a full mode set if active state changed */
+	if (crtc_state->active_changed)
+		crtc_state->mode_changed = true;
+
+	memset(pipe_staged, 0, sizeof(pipe_staged));
+
+	if (cstate->num_mixers) {
+		mixer_width = mode->hdisplay / cstate->num_mixers;
+
+		_dpu_crtc_setup_lm_bounds(crtc, crtc_state);
+	}
+
+	crtc_rect.x2 = mode->hdisplay;
+	crtc_rect.y2 = mode->vdisplay;
+
+	 /* get plane state for all drm planes associated with crtc state */
+	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) {
+		struct dpu_plane_state *dpu_pstate = to_dpu_plane_state(pstate);
+		struct drm_rect dst, clip = crtc_rect;
+
+		if (IS_ERR_OR_NULL(pstate)) {
+			rc = PTR_ERR(pstate);
+			DPU_ERROR("%s: failed to get plane%d state, %d\n",
+					dpu_crtc->name, plane->base.id, rc);
+			goto end;
+		}
+		if (cnt >= DPU_STAGE_MAX * 4)
+			continue;
+
+		if (!pstate->visible)
+			continue;
+
+		pstates[cnt].dpu_pstate = dpu_pstate;
+		pstates[cnt].drm_pstate = pstate;
+		pstates[cnt].stage = pstate->normalized_zpos;
+		pstates[cnt].pipe_id = dpu_plane_pipe(plane);
+
+		dpu_pstate->needs_dirtyfb = needs_dirtyfb;
+
+		if (pipe_staged[pstates[cnt].pipe_id]) {
+			multirect_plane[multirect_count].r0 =
+				pipe_staged[pstates[cnt].pipe_id];
+			multirect_plane[multirect_count].r1 = pstate;
+			multirect_count++;
+
+			pipe_staged[pstates[cnt].pipe_id] = NULL;
+		} else {
+			pipe_staged[pstates[cnt].pipe_id] = pstate;
+		}
+
+		cnt++;
+
+		dst = drm_plane_state_dest(pstate);
+		if (!drm_rect_intersect(&clip, &dst)) {
+			DPU_ERROR("invalid vertical/horizontal destination\n");
+			DPU_ERROR("display: " DRM_RECT_FMT " plane: "
+				  DRM_RECT_FMT "\n", DRM_RECT_ARG(&crtc_rect),
+				  DRM_RECT_ARG(&dst));
+			rc = -E2BIG;
+			goto end;
+		}
+	}
+
+	for (i = 1; i < SSPP_MAX; i++) {
+		if (pipe_staged[i])
+			dpu_plane_clear_multirect(pipe_staged[i]);
+	}
+
+	z_pos = -1;
+	for (i = 0; i < cnt; i++) {
+		/* reset counts at every new blend stage */
+		if (pstates[i].stage != z_pos) {
+			left_zpos_cnt = 0;
+			right_zpos_cnt = 0;
+			z_pos = pstates[i].stage;
+		}
+
+		/* verify z_pos setting before using it */
+		if (z_pos >= DPU_STAGE_MAX - DPU_STAGE_0) {
+			DPU_ERROR("> %d plane stages assigned\n",
+					DPU_STAGE_MAX - DPU_STAGE_0);
+			rc = -EINVAL;
+			goto end;
+		} else if (pstates[i].drm_pstate->crtc_x < mixer_width) {
+			if (left_zpos_cnt == 2) {
+				DPU_ERROR("> 2 planes @ stage %d on left\n",
+					z_pos);
+				rc = -EINVAL;
+				goto end;
+			}
+			left_zpos_cnt++;
+
+		} else {
+			if (right_zpos_cnt == 2) {
+				DPU_ERROR("> 2 planes @ stage %d on right\n",
+					z_pos);
+				rc = -EINVAL;
+				goto end;
+			}
+			right_zpos_cnt++;
+		}
+
+		pstates[i].dpu_pstate->stage = z_pos + DPU_STAGE_0;
+		DRM_DEBUG_ATOMIC("%s: zpos %d\n", dpu_crtc->name, z_pos);
+	}
+
+	for (i = 0; i < multirect_count; i++) {
+		if (dpu_plane_validate_multirect_v2(&multirect_plane[i])) {
+			DPU_ERROR(
+			"multirect validation failed for planes (%d - %d)\n",
+					multirect_plane[i].r0->plane->base.id,
+					multirect_plane[i].r1->plane->base.id);
+			rc = -EINVAL;
+			goto end;
+		}
+	}
+
+	atomic_inc(&_dpu_crtc_get_kms(crtc)->bandwidth_ref);
+
+	rc = dpu_core_perf_crtc_check(crtc, crtc_state);
+	if (rc) {
+		DPU_ERROR("crtc%d failed performance check %d\n",
+				crtc->base.id, rc);
+		goto end;
+	}
+
+	/* validate source split:
+	 * use pstates sorted by stage to check planes on same stage
+	 * we assume that all pipes are in source split so its valid to compare
+	 * without taking into account left/right mixer placement
+	 */
+	for (i = 1; i < cnt; i++) {
+		struct plane_state *prv_pstate, *cur_pstate;
+		struct drm_rect left_rect, right_rect;
+		int32_t left_pid, right_pid;
+		int32_t stage;
+
+		prv_pstate = &pstates[i - 1];
+		cur_pstate = &pstates[i];
+		if (prv_pstate->stage != cur_pstate->stage)
+			continue;
+
+		stage = cur_pstate->stage;
+
+		left_pid = prv_pstate->dpu_pstate->base.plane->base.id;
+		left_rect = drm_plane_state_dest(prv_pstate->drm_pstate);
+
+		right_pid = cur_pstate->dpu_pstate->base.plane->base.id;
+		right_rect = drm_plane_state_dest(cur_pstate->drm_pstate);
+
+		if (right_rect.x1 < left_rect.x1) {
+			swap(left_pid, right_pid);
+			swap(left_rect, right_rect);
+		}
+
+		/**
+		 * - planes are enumerated in pipe-priority order such that
+		 *   planes with lower drm_id must be left-most in a shared
+		 *   blend-stage when using source split.
+		 * - planes in source split must be contiguous in width
+		 * - planes in source split must have same dest yoff and height
+		 */
+		if (right_pid < left_pid) {
+			DPU_ERROR(
+				"invalid src split cfg. priority mismatch. stage: %d left: %d right: %d\n",
+				stage, left_pid, right_pid);
+			rc = -EINVAL;
+			goto end;
+		} else if (right_rect.x1 != drm_rect_width(&left_rect)) {
+			DPU_ERROR("non-contiguous coordinates for src split. "
+				  "stage: %d left: " DRM_RECT_FMT " right: "
+				  DRM_RECT_FMT "\n", stage,
+				  DRM_RECT_ARG(&left_rect),
+				  DRM_RECT_ARG(&right_rect));
+			rc = -EINVAL;
+			goto end;
+		} else if (left_rect.y1 != right_rect.y1 ||
+			   drm_rect_height(&left_rect) != drm_rect_height(&right_rect)) {
+			DPU_ERROR("source split at stage: %d. invalid "
+				  "yoff/height: left: " DRM_RECT_FMT " right: "
+				  DRM_RECT_FMT "\n", stage,
+				  DRM_RECT_ARG(&left_rect),
+				  DRM_RECT_ARG(&right_rect));
+			rc = -EINVAL;
+			goto end;
+		}
+	}
+
+end:
+	kfree(pstates);
+	return rc;
+}
+
+int dpu_crtc_vblank(struct drm_crtc *crtc, bool en)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct drm_encoder *enc;
+
+	trace_dpu_crtc_vblank(DRMID(&dpu_crtc->base), en, dpu_crtc);
+
+	/*
+	 * Normally we would iterate through encoder_mask in crtc state to find
+	 * attached encoders. In this case, we might be disabling vblank _after_
+	 * encoder_mask has been cleared.
+	 *
+	 * Instead, we "assign" a crtc to the encoder in enable and clear it in
+	 * disable (which is also after encoder_mask is cleared). So instead of
+	 * using encoder mask, we'll ask the encoder to toggle itself iff it's
+	 * currently assigned to our crtc.
+	 *
+	 * Note also that this function cannot be called while crtc is disabled
+	 * since we use drm_crtc_vblank_on/off. So we don't need to worry
+	 * about the assigned crtcs being inconsistent with the current state
+	 * (which means no need to worry about modeset locks).
+	 */
+	list_for_each_entry(enc, &crtc->dev->mode_config.encoder_list, head) {
+		trace_dpu_crtc_vblank_enable(DRMID(crtc), DRMID(enc), en,
+					     dpu_crtc);
+
+		dpu_encoder_toggle_vblank_for_crtc(enc, crtc, en);
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int _dpu_debugfs_status_show(struct seq_file *s, void *data)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_plane_state *pstate = NULL;
+	struct dpu_crtc_mixer *m;
+
+	struct drm_crtc *crtc;
+	struct drm_plane *plane;
+	struct drm_display_mode *mode;
+	struct drm_framebuffer *fb;
+	struct drm_plane_state *state;
+	struct dpu_crtc_state *cstate;
+
+	int i, out_width;
+
+	dpu_crtc = s->private;
+	crtc = &dpu_crtc->base;
+
+	drm_modeset_lock_all(crtc->dev);
+	cstate = to_dpu_crtc_state(crtc->state);
+
+	mode = &crtc->state->adjusted_mode;
+	out_width = mode->hdisplay / cstate->num_mixers;
+
+	seq_printf(s, "crtc:%d width:%d height:%d\n", crtc->base.id,
+				mode->hdisplay, mode->vdisplay);
+
+	seq_puts(s, "\n");
+
+	for (i = 0; i < cstate->num_mixers; ++i) {
+		m = &cstate->mixers[i];
+		seq_printf(s, "\tmixer:%d ctl:%d width:%d height:%d\n",
+			m->hw_lm->idx - LM_0, m->lm_ctl->idx - CTL_0,
+			out_width, mode->vdisplay);
+	}
+
+	seq_puts(s, "\n");
+
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		pstate = to_dpu_plane_state(plane->state);
+		state = plane->state;
+
+		if (!pstate || !state)
+			continue;
+
+		seq_printf(s, "\tplane:%u stage:%d\n", plane->base.id,
+			pstate->stage);
+
+		if (plane->state->fb) {
+			fb = plane->state->fb;
+
+			seq_printf(s, "\tfb:%d image format:%4.4s wxh:%ux%u ",
+				fb->base.id, (char *) &fb->format->format,
+				fb->width, fb->height);
+			for (i = 0; i < ARRAY_SIZE(fb->format->cpp); ++i)
+				seq_printf(s, "cpp[%d]:%u ",
+						i, fb->format->cpp[i]);
+			seq_puts(s, "\n\t");
+
+			seq_printf(s, "modifier:%8llu ", fb->modifier);
+			seq_puts(s, "\n");
+
+			seq_puts(s, "\t");
+			for (i = 0; i < ARRAY_SIZE(fb->pitches); i++)
+				seq_printf(s, "pitches[%d]:%8u ", i,
+							fb->pitches[i]);
+			seq_puts(s, "\n");
+
+			seq_puts(s, "\t");
+			for (i = 0; i < ARRAY_SIZE(fb->offsets); i++)
+				seq_printf(s, "offsets[%d]:%8u ", i,
+							fb->offsets[i]);
+			seq_puts(s, "\n");
+		}
+
+		seq_printf(s, "\tsrc_x:%4d src_y:%4d src_w:%4d src_h:%4d\n",
+			state->src_x, state->src_y, state->src_w, state->src_h);
+
+		seq_printf(s, "\tdst x:%4d dst_y:%4d dst_w:%4d dst_h:%4d\n",
+			state->crtc_x, state->crtc_y, state->crtc_w,
+			state->crtc_h);
+		seq_printf(s, "\tmultirect: mode: %d index: %d\n",
+			pstate->multirect_mode, pstate->multirect_index);
+
+		seq_puts(s, "\n");
+	}
+	if (dpu_crtc->vblank_cb_count) {
+		ktime_t diff = ktime_sub(ktime_get(), dpu_crtc->vblank_cb_time);
+		s64 diff_ms = ktime_to_ms(diff);
+		s64 fps = diff_ms ? div_s64(
+				dpu_crtc->vblank_cb_count * 1000, diff_ms) : 0;
+
+		seq_printf(s,
+			"vblank fps:%lld count:%u total:%llums total_framecount:%llu\n",
+				fps, dpu_crtc->vblank_cb_count,
+				ktime_to_ms(diff), dpu_crtc->play_count);
+
+		/* reset time & count for next measurement */
+		dpu_crtc->vblank_cb_count = 0;
+		dpu_crtc->vblank_cb_time = ktime_set(0, 0);
+	}
+
+	drm_modeset_unlock_all(crtc->dev);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(_dpu_debugfs_status);
+
+static int dpu_crtc_debugfs_state_show(struct seq_file *s, void *v)
+{
+	struct drm_crtc *crtc = (struct drm_crtc *) s->private;
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+
+	seq_printf(s, "client type: %d\n", dpu_crtc_get_client_type(crtc));
+	seq_printf(s, "intf_mode: %d\n", dpu_crtc_get_intf_mode(crtc));
+	seq_printf(s, "core_clk_rate: %llu\n",
+			dpu_crtc->cur_perf.core_clk_rate);
+	seq_printf(s, "bw_ctl: %llu\n", dpu_crtc->cur_perf.bw_ctl);
+	seq_printf(s, "max_per_pipe_ib: %llu\n",
+				dpu_crtc->cur_perf.max_per_pipe_ib);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(dpu_crtc_debugfs_state);
+
+static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct dentry *debugfs_root;
+
+	debugfs_root = debugfs_create_dir(dpu_crtc->name,
+			crtc->dev->primary->debugfs_root);
+
+	debugfs_create_file("status", 0400,
+			debugfs_root,
+			dpu_crtc, &_dpu_debugfs_status_fops);
+	debugfs_create_file("state", 0600,
+			debugfs_root,
+			&dpu_crtc->base,
+			&dpu_crtc_debugfs_state_fops);
+
+	return 0;
+}
+#else
+static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc)
+{
+	return 0;
+}
+#endif /* CONFIG_DEBUG_FS */
+
+static int dpu_crtc_late_register(struct drm_crtc *crtc)
+{
+	return _dpu_crtc_init_debugfs(crtc);
+}
+
+static const struct drm_crtc_funcs dpu_crtc_funcs = {
+	.set_config = drm_atomic_helper_set_config,
+	.destroy = dpu_crtc_destroy,
+	.page_flip = drm_atomic_helper_page_flip,
+	.reset = dpu_crtc_reset,
+	.atomic_duplicate_state = dpu_crtc_duplicate_state,
+	.atomic_destroy_state = dpu_crtc_destroy_state,
+	.atomic_print_state = dpu_crtc_atomic_print_state,
+	.late_register = dpu_crtc_late_register,
+	.verify_crc_source = dpu_crtc_verify_crc_source,
+	.set_crc_source = dpu_crtc_set_crc_source,
+	.enable_vblank  = msm_crtc_enable_vblank,
+	.disable_vblank = msm_crtc_disable_vblank,
+	.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
+	.get_vblank_counter = dpu_crtc_get_vblank_counter,
+};
+
+static const struct drm_crtc_helper_funcs dpu_crtc_helper_funcs = {
+	.atomic_disable = dpu_crtc_disable,
+	.atomic_enable = dpu_crtc_enable,
+	.atomic_check = dpu_crtc_atomic_check,
+	.atomic_begin = dpu_crtc_atomic_begin,
+	.atomic_flush = dpu_crtc_atomic_flush,
+	.get_scanout_position = dpu_crtc_get_scanout_position,
+};
+
+/* initialize crtc */
+struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane,
+				struct drm_plane *cursor)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
+	struct drm_crtc *crtc = NULL;
+	struct dpu_crtc *dpu_crtc = NULL;
+	int i;
+
+	dpu_crtc = kzalloc(sizeof(*dpu_crtc), GFP_KERNEL);
+	if (!dpu_crtc)
+		return ERR_PTR(-ENOMEM);
+
+	crtc = &dpu_crtc->base;
+	crtc->dev = dev;
+
+	spin_lock_init(&dpu_crtc->spin_lock);
+	atomic_set(&dpu_crtc->frame_pending, 0);
+
+	init_completion(&dpu_crtc->frame_done_comp);
+
+	INIT_LIST_HEAD(&dpu_crtc->frame_event_list);
+
+	for (i = 0; i < ARRAY_SIZE(dpu_crtc->frame_events); i++) {
+		INIT_LIST_HEAD(&dpu_crtc->frame_events[i].list);
+		list_add(&dpu_crtc->frame_events[i].list,
+				&dpu_crtc->frame_event_list);
+		kthread_init_work(&dpu_crtc->frame_events[i].work,
+				dpu_crtc_frame_event_work);
+	}
+
+	drm_crtc_init_with_planes(dev, crtc, plane, cursor, &dpu_crtc_funcs,
+				NULL);
+
+	drm_crtc_helper_add(crtc, &dpu_crtc_helper_funcs);
+
+	if (dpu_kms->catalog->dspp_count)
+		drm_crtc_enable_color_mgmt(crtc, 0, true, 0);
+
+	/* save user friendly CRTC name for later */
+	snprintf(dpu_crtc->name, DPU_CRTC_NAME_SIZE, "crtc%u", crtc->base.id);
+
+	/* initialize event handling */
+	spin_lock_init(&dpu_crtc->event_lock);
+
+	DRM_DEBUG_KMS("%s: successfully initialized crtc\n", dpu_crtc->name);
+	return crtc;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
new file mode 100644
index 000000000..539b68b16
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
@@ -0,0 +1,303 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2015-2021 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#ifndef _DPU_CRTC_H_
+#define _DPU_CRTC_H_
+
+#include <linux/kthread.h>
+#include <drm/drm_crtc.h>
+#include "dpu_kms.h"
+#include "dpu_core_perf.h"
+
+#define DPU_CRTC_NAME_SIZE	12
+
+/* define the maximum number of in-flight frame events */
+#define DPU_CRTC_FRAME_EVENT_SIZE	4
+
+/**
+ * enum dpu_crtc_client_type: crtc client type
+ * @RT_CLIENT:	RealTime client like video/cmd mode display
+ *              voting through apps rsc
+ * @NRT_CLIENT:	Non-RealTime client like WB display
+ *              voting through apps rsc
+ */
+enum dpu_crtc_client_type {
+	RT_CLIENT,
+	NRT_CLIENT,
+};
+
+/**
+ * enum dpu_crtc_smmu_state:	smmu state
+ * @ATTACHED:	 all the context banks are attached.
+ * @DETACHED:	 all the context banks are detached.
+ * @ATTACH_ALL_REQ:	 transient state of attaching context banks.
+ * @DETACH_ALL_REQ:	 transient state of detaching context banks.
+ */
+enum dpu_crtc_smmu_state {
+	ATTACHED = 0,
+	DETACHED,
+	ATTACH_ALL_REQ,
+	DETACH_ALL_REQ,
+};
+
+/**
+ * enum dpu_crtc_smmu_state_transition_type: state transition type
+ * @NONE: no pending state transitions
+ * @PRE_COMMIT: state transitions should be done before processing the commit
+ * @POST_COMMIT: state transitions to be done after processing the commit.
+ */
+enum dpu_crtc_smmu_state_transition_type {
+	NONE,
+	PRE_COMMIT,
+	POST_COMMIT
+};
+
+/**
+ * struct dpu_crtc_smmu_state_data: stores the smmu state and transition type
+ * @state: current state of smmu context banks
+ * @transition_type: transition request type
+ * @transition_error: whether there is error while transitioning the state
+ */
+struct dpu_crtc_smmu_state_data {
+	uint32_t state;
+	uint32_t transition_type;
+	uint32_t transition_error;
+};
+
+/**
+ * enum dpu_crtc_crc_source: CRC source
+ * @DPU_CRTC_CRC_SOURCE_NONE: no source set
+ * @DPU_CRTC_CRC_SOURCE_LAYER_MIXER: CRC in layer mixer
+ * @DPU_CRTC_CRC_SOURCE_ENCODER: CRC in encoder
+ * @DPU_CRTC_CRC_SOURCE_INVALID: Invalid source
+ */
+enum dpu_crtc_crc_source {
+	DPU_CRTC_CRC_SOURCE_NONE = 0,
+	DPU_CRTC_CRC_SOURCE_LAYER_MIXER,
+	DPU_CRTC_CRC_SOURCE_ENCODER,
+	DPU_CRTC_CRC_SOURCE_MAX,
+	DPU_CRTC_CRC_SOURCE_INVALID = -1
+};
+
+/**
+ * struct dpu_crtc_mixer: stores the map for each virtual pipeline in the CRTC
+ * @hw_lm:	LM HW Driver context
+ * @lm_ctl:	CTL Path HW driver context
+ * @lm_dspp:	DSPP HW driver context
+ * @mixer_op_mode:	mixer blending operation mode
+ * @flush_mask:	mixer flush mask for ctl, mixer and pipe
+ */
+struct dpu_crtc_mixer {
+	struct dpu_hw_mixer *hw_lm;
+	struct dpu_hw_ctl *lm_ctl;
+	struct dpu_hw_dspp *hw_dspp;
+	u32 mixer_op_mode;
+};
+
+/**
+ * struct dpu_crtc_frame_event: stores crtc frame event for crtc processing
+ * @work:	base work structure
+ * @crtc:	Pointer to crtc handling this event
+ * @list:	event list
+ * @ts:		timestamp at queue entry
+ * @event:	event identifier
+ */
+struct dpu_crtc_frame_event {
+	struct kthread_work work;
+	struct drm_crtc *crtc;
+	struct list_head list;
+	ktime_t ts;
+	u32 event;
+};
+
+/*
+ * Maximum number of free event structures to cache
+ */
+#define DPU_CRTC_MAX_EVENT_COUNT	16
+
+/**
+ * struct dpu_crtc - virtualized CRTC data structure
+ * @base          : Base drm crtc structure
+ * @name          : ASCII description of this crtc
+ * @event         : Pointer to last received drm vblank event. If there is a
+ *                  pending vblank event, this will be non-null.
+ * @vsync_count   : Running count of received vsync events
+ * @drm_requested_vblank : Whether vblanks have been enabled in the encoder
+ * @property_info : Opaque structure for generic property support
+ * @property_defaults : Array of default values for generic property support
+ * @vblank_cb_count : count of vblank callback since last reset
+ * @play_count    : frame count between crtc enable and disable
+ * @vblank_cb_time  : ktime at vblank count reset
+ * @enabled       : whether the DPU CRTC is currently enabled. updated in the
+ *                  commit-thread, not state-swap time which is earlier, so
+ *                  safe to make decisions on during VBLANK on/off work
+ * @feature_list  : list of color processing features supported on a crtc
+ * @active_list   : list of color processing features are active
+ * @dirty_list    : list of color processing features are dirty
+ * @ad_dirty: list containing ad properties that are dirty
+ * @ad_active: list containing ad properties that are active
+ * @frame_pending : Whether or not an update is pending
+ * @frame_events  : static allocation of in-flight frame events
+ * @frame_event_list : available frame event list
+ * @spin_lock     : spin lock for frame event, transaction status, etc...
+ * @frame_done_comp    : for frame_event_done synchronization
+ * @event_thread  : Pointer to event handler thread
+ * @event_worker  : Event worker queue
+ * @event_lock    : Spinlock around event handling code
+ * @phandle: Pointer to power handler
+ * @cur_perf      : current performance committed to clock/bandwidth driver
+ * @crc_source    : CRC source
+ */
+struct dpu_crtc {
+	struct drm_crtc base;
+	char name[DPU_CRTC_NAME_SIZE];
+
+	struct drm_pending_vblank_event *event;
+	u32 vsync_count;
+
+	u32 vblank_cb_count;
+	u64 play_count;
+	ktime_t vblank_cb_time;
+	bool enabled;
+
+	struct list_head feature_list;
+	struct list_head active_list;
+	struct list_head dirty_list;
+	struct list_head ad_dirty;
+	struct list_head ad_active;
+
+	atomic_t frame_pending;
+	struct dpu_crtc_frame_event frame_events[DPU_CRTC_FRAME_EVENT_SIZE];
+	struct list_head frame_event_list;
+	spinlock_t spin_lock;
+	struct completion frame_done_comp;
+
+	/* for handling internal event thread */
+	spinlock_t event_lock;
+
+	struct dpu_core_perf_params cur_perf;
+
+	struct dpu_crtc_smmu_state_data smmu_state;
+};
+
+#define to_dpu_crtc(x) container_of(x, struct dpu_crtc, base)
+
+/**
+ * struct dpu_crtc_state - dpu container for atomic crtc state
+ * @base: Base drm crtc state structure
+ * @bw_control    : true if bw/clk controlled by core bw/clk properties
+ * @bw_split_vote : true if bw controlled by llcc/dram bw properties
+ * @lm_bounds     : LM boundaries based on current mode full resolution, no ROI.
+ *                  Origin top left of CRTC.
+ * @property_state: Local storage for msm_prop properties
+ * @property_values: Current crtc property values
+ * @input_fence_timeout_ns : Cached input fence timeout, in ns
+ * @new_perf: new performance state being requested
+ * @num_mixers    : Number of mixers in use
+ * @mixers        : List of active mixers
+ * @num_ctls      : Number of ctl paths in use
+ * @hw_ctls       : List of active ctl paths
+ * @crc_source    : CRC source
+ * @crc_frame_skip_count: Number of frames skipped before getting CRC
+ */
+struct dpu_crtc_state {
+	struct drm_crtc_state base;
+
+	bool bw_control;
+	bool bw_split_vote;
+	struct drm_rect lm_bounds[CRTC_DUAL_MIXERS];
+
+	uint64_t input_fence_timeout_ns;
+
+	struct dpu_core_perf_params new_perf;
+
+	/* HW Resources reserved for the crtc */
+	u32 num_mixers;
+	struct dpu_crtc_mixer mixers[CRTC_DUAL_MIXERS];
+
+	u32 num_ctls;
+	struct dpu_hw_ctl *hw_ctls[CRTC_DUAL_MIXERS];
+
+	enum dpu_crtc_crc_source crc_source;
+	int crc_frame_skip_count;
+};
+
+#define to_dpu_crtc_state(x) \
+	container_of(x, struct dpu_crtc_state, base)
+
+/**
+ * dpu_crtc_frame_pending - retun the number of pending frames
+ * @crtc: Pointer to drm crtc object
+ */
+static inline int dpu_crtc_frame_pending(struct drm_crtc *crtc)
+{
+	return crtc ? atomic_read(&to_dpu_crtc(crtc)->frame_pending) : -EINVAL;
+}
+
+/**
+ * dpu_crtc_vblank - enable or disable vblanks for this crtc
+ * @crtc: Pointer to drm crtc object
+ * @en: true to enable vblanks, false to disable
+ */
+int dpu_crtc_vblank(struct drm_crtc *crtc, bool en);
+
+/**
+ * dpu_crtc_vblank_callback - called on vblank irq, issues completion events
+ * @crtc: Pointer to drm crtc object
+ */
+void dpu_crtc_vblank_callback(struct drm_crtc *crtc);
+
+/**
+ * dpu_crtc_commit_kickoff - trigger kickoff of the commit for this crtc
+ * @crtc: Pointer to drm crtc object
+ */
+void dpu_crtc_commit_kickoff(struct drm_crtc *crtc);
+
+/**
+ * dpu_crtc_complete_commit - callback signalling completion of current commit
+ * @crtc: Pointer to drm crtc object
+ */
+void dpu_crtc_complete_commit(struct drm_crtc *crtc);
+
+/**
+ * dpu_crtc_init - create a new crtc object
+ * @dev: dpu device
+ * @plane: base plane
+ * @cursor: cursor plane
+ * @Return: new crtc object or error
+ */
+struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane,
+			       struct drm_plane *cursor);
+
+/**
+ * dpu_crtc_register_custom_event - api for enabling/disabling crtc event
+ * @kms: Pointer to dpu_kms
+ * @crtc_drm: Pointer to crtc object
+ * @event: Event that client is interested
+ * @en: Flag to enable/disable the event
+ */
+int dpu_crtc_register_custom_event(struct dpu_kms *kms,
+		struct drm_crtc *crtc_drm, u32 event, bool en);
+
+/**
+ * dpu_crtc_get_intf_mode - get interface mode of the given crtc
+ * @crtc: Pointert to crtc
+ */
+enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc);
+
+/**
+ * dpu_crtc_get_client_type - check the crtc type- rt, nrt etc.
+ * @crtc: Pointer to crtc
+ */
+static inline enum dpu_crtc_client_type dpu_crtc_get_client_type(
+						struct drm_crtc *crtc)
+{
+	return crtc && crtc->state ? RT_CLIENT : NRT_CLIENT;
+}
+
+#endif /* _DPU_CRTC_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
new file mode 100644
index 000000000..b0eb881f8
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -0,0 +1,2556 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * 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.
+ *
+ * Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/debugfs.h>
+#include <linux/kthread.h>
+#include <linux/seq_file.h>
+
+#include <drm/drm_crtc.h>
+#include <drm/drm_file.h>
+#include <drm/drm_probe_helper.h>
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_intf.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_dspp.h"
+#include "dpu_hw_dsc.h"
+#include "dpu_hw_merge3d.h"
+#include "dpu_formats.h"
+#include "dpu_encoder_phys.h"
+#include "dpu_crtc.h"
+#include "dpu_trace.h"
+#include "dpu_core_irq.h"
+#include "disp/msm_disp_snapshot.h"
+
+#define DPU_DEBUG_ENC(e, fmt, ...) DRM_DEBUG_ATOMIC("enc%d " fmt,\
+		(e) ? (e)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_ENC(e, fmt, ...) DPU_ERROR("enc%d " fmt,\
+		(e) ? (e)->base.base.id : -1, ##__VA_ARGS__)
+
+/*
+ * Two to anticipate panels that can do cmd/vid dynamic switching
+ * plan is to create all possible physical encoder types, and switch between
+ * them at runtime
+ */
+#define NUM_PHYS_ENCODER_TYPES 2
+
+#define MAX_PHYS_ENCODERS_PER_VIRTUAL \
+	(MAX_H_TILES_PER_DISPLAY * NUM_PHYS_ENCODER_TYPES)
+
+#define MAX_CHANNELS_PER_ENC 2
+
+#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
+
+/**
+ * enum dpu_enc_rc_events - events for resource control state machine
+ * @DPU_ENC_RC_EVENT_KICKOFF:
+ *	This event happens at NORMAL priority.
+ *	Event that signals the start of the transfer. When this event is
+ *	received, enable MDP/DSI core clocks. Regardless of the previous
+ *	state, the resource should be in ON state at the end of this event.
+ * @DPU_ENC_RC_EVENT_FRAME_DONE:
+ *	This event happens at INTERRUPT level.
+ *	Event signals the end of the data transfer after the PP FRAME_DONE
+ *	event. At the end of this event, a delayed work is scheduled to go to
+ *	IDLE_PC state after IDLE_TIMEOUT time.
+ * @DPU_ENC_RC_EVENT_PRE_STOP:
+ *	This event happens at NORMAL priority.
+ *	This event, when received during the ON state, leave the RC STATE
+ *	in the PRE_OFF state. It should be followed by the STOP event as
+ *	part of encoder disable.
+ *	If received during IDLE or OFF states, it will do nothing.
+ * @DPU_ENC_RC_EVENT_STOP:
+ *	This event happens at NORMAL priority.
+ *	When this event is received, disable all the MDP/DSI core clocks, and
+ *	disable IRQs. It should be called from the PRE_OFF or IDLE states.
+ *	IDLE is expected when IDLE_PC has run, and PRE_OFF did nothing.
+ *	PRE_OFF is expected when PRE_STOP was executed during the ON state.
+ *	Resource state should be in OFF at the end of the event.
+ * @DPU_ENC_RC_EVENT_ENTER_IDLE:
+ *	This event happens at NORMAL priority from a work item.
+ *	Event signals that there were no frame updates for IDLE_TIMEOUT time.
+ *	This would disable MDP/DSI core clocks and change the resource state
+ *	to IDLE.
+ */
+enum dpu_enc_rc_events {
+	DPU_ENC_RC_EVENT_KICKOFF = 1,
+	DPU_ENC_RC_EVENT_FRAME_DONE,
+	DPU_ENC_RC_EVENT_PRE_STOP,
+	DPU_ENC_RC_EVENT_STOP,
+	DPU_ENC_RC_EVENT_ENTER_IDLE
+};
+
+/*
+ * enum dpu_enc_rc_states - states that the resource control maintains
+ * @DPU_ENC_RC_STATE_OFF: Resource is in OFF state
+ * @DPU_ENC_RC_STATE_PRE_OFF: Resource is transitioning to OFF state
+ * @DPU_ENC_RC_STATE_ON: Resource is in ON state
+ * @DPU_ENC_RC_STATE_MODESET: Resource is in modeset state
+ * @DPU_ENC_RC_STATE_IDLE: Resource is in IDLE state
+ */
+enum dpu_enc_rc_states {
+	DPU_ENC_RC_STATE_OFF,
+	DPU_ENC_RC_STATE_PRE_OFF,
+	DPU_ENC_RC_STATE_ON,
+	DPU_ENC_RC_STATE_IDLE
+};
+
+/**
+ * struct dpu_encoder_virt - virtual encoder. Container of one or more physical
+ *	encoders. Virtual encoder manages one "logical" display. Physical
+ *	encoders manage one intf block, tied to a specific panel/sub-panel.
+ *	Virtual encoder defers as much as possible to the physical encoders.
+ *	Virtual encoder registers itself with the DRM Framework as the encoder.
+ * @base:		drm_encoder base class for registration with DRM
+ * @enc_spinlock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ * @enabled:		True if the encoder is active, protected by enc_lock
+ * @num_phys_encs:	Actual number of physical encoders contained.
+ * @phys_encs:		Container of physical encoders managed.
+ * @cur_master:		Pointer to the current master in this mode. Optimization
+ *			Only valid after enable. Cleared as disable.
+ * @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_dsc:		Handle to the DSC blocks used for the display.
+ * @dsc_mask:		Bitmask of used DSC blocks.
+ * @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
+ * @crtc:		Pointer to the currently assigned crtc. Normally you
+ *			would use crtc->state->encoder_mask to determine the
+ *			link between encoder/crtc. However in this case we need
+ *			to track crtc in the disable() hook which is called
+ *			_after_ encoder_mask is cleared.
+ * @connector:		If a mode is set, cached pointer to the active connector
+ * @crtc_kickoff_cb:		Callback into CRTC that will flush & start
+ *				all CTL paths
+ * @crtc_kickoff_cb_data:	Opaque user data given to crtc_kickoff_cb
+ * @debugfs_root:		Debug file system root file node
+ * @enc_lock:			Lock around physical encoder
+ *				create/destroy/enable/disable
+ * @frame_busy_mask:		Bitmask tracking which phys_enc we are still
+ *				busy processing current command.
+ *				Bit0 = phys_encs[0] etc.
+ * @crtc_frame_event_cb:	callback handler for frame event
+ * @crtc_frame_event_cb_data:	callback handler private data
+ * @frame_done_timeout_ms:	frame done timeout in ms
+ * @frame_done_timer:		watchdog timer for frame done event
+ * @vsync_event_timer:		vsync timer
+ * @disp_info:			local copy of msm_display_info struct
+ * @idle_pc_supported:		indicate if idle power collaps is supported
+ * @rc_lock:			resource control mutex lock to protect
+ *				virt encoder over various state changes
+ * @rc_state:			resource controller state
+ * @delayed_off_work:		delayed worker to schedule disabling of
+ *				clks and resources after IDLE_TIMEOUT time.
+ * @vsync_event_work:		worker to handle vsync event for autorefresh
+ * @topology:                   topology of the display
+ * @idle_timeout:		idle timeout duration in milliseconds
+ * @dsc:			drm_dsc_config pointer, for DSC-enabled encoders
+ */
+struct dpu_encoder_virt {
+	struct drm_encoder base;
+	spinlock_t enc_spinlock;
+
+	bool enabled;
+
+	unsigned int num_phys_encs;
+	struct dpu_encoder_phys *phys_encs[MAX_PHYS_ENCODERS_PER_VIRTUAL];
+	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_dsc *hw_dsc[MAX_CHANNELS_PER_ENC];
+
+	unsigned int dsc_mask;
+
+	bool intfs_swapped;
+
+	struct drm_crtc *crtc;
+	struct drm_connector *connector;
+
+	struct dentry *debugfs_root;
+	struct mutex enc_lock;
+	DECLARE_BITMAP(frame_busy_mask, MAX_PHYS_ENCODERS_PER_VIRTUAL);
+	void (*crtc_frame_event_cb)(void *, u32 event);
+	void *crtc_frame_event_cb_data;
+
+	atomic_t frame_done_timeout_ms;
+	struct timer_list frame_done_timer;
+	struct timer_list vsync_event_timer;
+
+	struct msm_display_info disp_info;
+
+	bool idle_pc_supported;
+	struct mutex rc_lock;
+	enum dpu_enc_rc_states rc_state;
+	struct delayed_work delayed_off_work;
+	struct kthread_work vsync_event_work;
+	struct msm_display_topology topology;
+
+	u32 idle_timeout;
+
+	bool wide_bus_en;
+
+	/* DSC configuration */
+	struct drm_dsc_config *dsc;
+};
+
+#define to_dpu_encoder_virt(x) container_of(x, struct dpu_encoder_virt, base)
+
+static u32 dither_matrix[DITHER_MATRIX_SZ] = {
+	15, 7, 13, 5, 3, 11, 1, 9, 12, 4, 14, 6, 0, 8, 2, 10
+};
+
+
+bool dpu_encoder_is_widebus_enabled(const struct drm_encoder *drm_enc)
+{
+	const struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	return dpu_enc->wide_bus_en;
+}
+
+int dpu_encoder_get_crc_values_cnt(const struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i, num_intf = 0;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys->hw_intf && phys->hw_intf->ops.setup_misr
+				&& phys->hw_intf->ops.collect_misr)
+			num_intf++;
+	}
+
+	return num_intf;
+}
+
+void dpu_encoder_setup_misr(const struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+
+	int i;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys->hw_intf || !phys->hw_intf->ops.setup_misr)
+			continue;
+
+		phys->hw_intf->ops.setup_misr(phys->hw_intf);
+	}
+}
+
+int dpu_encoder_get_crc(const struct drm_encoder *drm_enc, u32 *crcs, int pos)
+{
+	struct dpu_encoder_virt *dpu_enc;
+
+	int i, rc = 0, entries_added = 0;
+
+	if (!drm_enc->crtc) {
+		DRM_ERROR("no crtc found for encoder %d\n", drm_enc->index);
+		return -EINVAL;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys->hw_intf || !phys->hw_intf->ops.collect_misr)
+			continue;
+
+		rc = phys->hw_intf->ops.collect_misr(phys->hw_intf, &crcs[pos + entries_added]);
+		if (rc)
+			return rc;
+		entries_added++;
+	}
+
+	return entries_added;
+}
+
+static void _dpu_encoder_setup_dither(struct dpu_hw_pingpong *hw_pp, unsigned bpc)
+{
+	struct dpu_hw_dither_cfg dither_cfg = { 0 };
+
+	if (!hw_pp->ops.setup_dither)
+		return;
+
+	switch (bpc) {
+	case 6:
+		dither_cfg.c0_bitdepth = 6;
+		dither_cfg.c1_bitdepth = 6;
+		dither_cfg.c2_bitdepth = 6;
+		dither_cfg.c3_bitdepth = 6;
+		dither_cfg.temporal_en = 0;
+		break;
+	default:
+		hw_pp->ops.setup_dither(hw_pp, NULL);
+		return;
+	}
+
+	memcpy(&dither_cfg.matrix, dither_matrix,
+			sizeof(u32) * DITHER_MATRIX_SZ);
+
+	hw_pp->ops.setup_dither(hw_pp, &dither_cfg);
+}
+
+static char *dpu_encoder_helper_get_intf_type(enum dpu_intf_mode intf_mode)
+{
+	switch (intf_mode) {
+	case INTF_MODE_VIDEO:
+		return "INTF_MODE_VIDEO";
+	case INTF_MODE_CMD:
+		return "INTF_MODE_CMD";
+	case INTF_MODE_WB_BLOCK:
+		return "INTF_MODE_WB_BLOCK";
+	case INTF_MODE_WB_LINE:
+		return "INTF_MODE_WB_LINE";
+	default:
+		return "INTF_MODE_UNKNOWN";
+	}
+}
+
+void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx)
+{
+	DRM_ERROR("irq timeout id=%u, intf_mode=%s intf=%d wb=%d, pp=%d, intr=%d\n",
+			DRMID(phys_enc->parent),
+			dpu_encoder_helper_get_intf_type(phys_enc->intf_mode),
+			phys_enc->intf_idx - INTF_0, phys_enc->wb_idx - WB_0,
+			phys_enc->hw_pp->idx - PINGPONG_0, intr_idx);
+
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(
+				phys_enc->parent, phys_enc,
+				DPU_ENCODER_FRAME_EVENT_ERROR);
+}
+
+static int dpu_encoder_helper_wait_event_timeout(int32_t drm_id,
+		u32 irq_idx, struct dpu_encoder_wait_info *info);
+
+int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
+		int irq,
+		void (*func)(void *arg, int irq_idx),
+		struct dpu_encoder_wait_info *wait_info)
+{
+	u32 irq_status;
+	int ret;
+
+	if (!wait_info) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+	/* note: do master / slave checking outside */
+
+	/* return EWOULDBLOCK since we know the wait isn't necessary */
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DRM_ERROR("encoder is disabled id=%u, callback=%ps, irq=%d\n",
+			  DRMID(phys_enc->parent), func,
+			  irq);
+		return -EWOULDBLOCK;
+	}
+
+	if (irq < 0) {
+		DRM_DEBUG_KMS("skip irq wait id=%u, callback=%ps\n",
+			      DRMID(phys_enc->parent), func);
+		return 0;
+	}
+
+	DRM_DEBUG_KMS("id=%u, callback=%ps, irq=%d, pp=%d, pending_cnt=%d\n",
+		      DRMID(phys_enc->parent), func,
+		      irq, phys_enc->hw_pp->idx - PINGPONG_0,
+		      atomic_read(wait_info->atomic_cnt));
+
+	ret = dpu_encoder_helper_wait_event_timeout(
+			DRMID(phys_enc->parent),
+			irq,
+			wait_info);
+
+	if (ret <= 0) {
+		irq_status = dpu_core_irq_read(phys_enc->dpu_kms, irq);
+		if (irq_status) {
+			unsigned long flags;
+
+			DRM_DEBUG_KMS("irq not triggered id=%u, callback=%ps, irq=%d, pp=%d, atomic_cnt=%d\n",
+				      DRMID(phys_enc->parent), func,
+				      irq,
+				      phys_enc->hw_pp->idx - PINGPONG_0,
+				      atomic_read(wait_info->atomic_cnt));
+			local_irq_save(flags);
+			func(phys_enc, irq);
+			local_irq_restore(flags);
+			ret = 0;
+		} else {
+			ret = -ETIMEDOUT;
+			DRM_DEBUG_KMS("irq timeout id=%u, callback=%ps, irq=%d, pp=%d, atomic_cnt=%d\n",
+				      DRMID(phys_enc->parent), func,
+				      irq,
+				      phys_enc->hw_pp->idx - PINGPONG_0,
+				      atomic_read(wait_info->atomic_cnt));
+		}
+	} else {
+		ret = 0;
+		trace_dpu_enc_irq_wait_success(DRMID(phys_enc->parent),
+			func, irq,
+			phys_enc->hw_pp->idx - PINGPONG_0,
+			atomic_read(wait_info->atomic_cnt));
+	}
+
+	return ret;
+}
+
+int dpu_encoder_get_vsync_count(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	struct dpu_encoder_phys *phys = dpu_enc ? dpu_enc->cur_master : NULL;
+	return phys ? atomic_read(&phys->vsync_cnt) : 0;
+}
+
+int dpu_encoder_get_linecount(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	int linecount = 0;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	phys = dpu_enc ? dpu_enc->cur_master : NULL;
+
+	if (phys && phys->ops.get_line_count)
+		linecount = phys->ops.get_line_count(phys);
+
+	return linecount;
+}
+
+static void dpu_encoder_destroy(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i = 0;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	mutex_lock(&dpu_enc->enc_lock);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys->ops.destroy) {
+			phys->ops.destroy(phys);
+			--dpu_enc->num_phys_encs;
+			dpu_enc->phys_encs[i] = NULL;
+		}
+	}
+
+	if (dpu_enc->num_phys_encs)
+		DPU_ERROR_ENC(dpu_enc, "expected 0 num_phys_encs not %d\n",
+				dpu_enc->num_phys_encs);
+	dpu_enc->num_phys_encs = 0;
+	mutex_unlock(&dpu_enc->enc_lock);
+
+	drm_encoder_cleanup(drm_enc);
+	mutex_destroy(&dpu_enc->enc_lock);
+}
+
+void dpu_encoder_helper_split_config(
+		struct dpu_encoder_phys *phys_enc,
+		enum dpu_intf interface)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct split_pipe_cfg cfg = { 0 };
+	struct dpu_hw_mdp *hw_mdptop;
+	struct msm_display_info *disp_info;
+
+	if (!phys_enc->hw_mdptop || !phys_enc->parent) {
+		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != NULL);
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(phys_enc->parent);
+	hw_mdptop = phys_enc->hw_mdptop;
+	disp_info = &dpu_enc->disp_info;
+
+	if (disp_info->intf_type != DRM_MODE_ENCODER_DSI)
+		return;
+
+	/**
+	 * disable split modes since encoder will be operating in as the only
+	 * encoder, either for the entire use case in the case of, for example,
+	 * single DSI, or for this frame in the case of left/right only partial
+	 * update.
+	 */
+	if (phys_enc->split_role == ENC_ROLE_SOLO) {
+		if (hw_mdptop->ops.setup_split_pipe)
+			hw_mdptop->ops.setup_split_pipe(hw_mdptop, &cfg);
+		return;
+	}
+
+	cfg.en = true;
+	cfg.mode = phys_enc->intf_mode;
+	cfg.intf = interface;
+
+	if (cfg.en && phys_enc->ops.needs_single_flush &&
+			phys_enc->ops.needs_single_flush(phys_enc))
+		cfg.split_flush_en = true;
+
+	if (phys_enc->split_role == ENC_ROLE_MASTER) {
+		DPU_DEBUG_ENC(dpu_enc, "enable %d\n", cfg.en);
+
+		if (hw_mdptop->ops.setup_split_pipe)
+			hw_mdptop->ops.setup_split_pipe(hw_mdptop, &cfg);
+	}
+}
+
+bool dpu_encoder_use_dsc_merge(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	int i, intf_count = 0, num_dsc = 0;
+
+	for (i = 0; i < MAX_PHYS_ENCODERS_PER_VIRTUAL; i++)
+		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;
+
+	return (num_dsc > 0) && (num_dsc > intf_count);
+}
+
+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 msm_display_topology topology = {0};
+	int i, intf_count = 0;
+
+	for (i = 0; i < MAX_PHYS_ENCODERS_PER_VIRTUAL; i++)
+		if (dpu_enc->phys_encs[i])
+			intf_count++;
+
+	/* 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)
+	 *
+	 * Adding color blocks only to primary interface if available in
+	 * sufficient number
+	 */
+	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 (dpu_enc->disp_info.intf_type == DRM_MODE_ENCODER_DSI) {
+		if (dpu_kms->catalog->dspp &&
+			(dpu_kms->catalog->dspp_count >= topology.num_lm))
+			topology.num_dspp = topology.num_lm;
+	}
+
+	topology.num_enc = 0;
+	topology.num_intf = intf_count;
+
+	if (dpu_enc->dsc) {
+		/* In case of Display Stream Compression (DSC), we would use
+		 * 2 encoders, 2 layer mixers and 1 interface
+		 * this is power optimal and can drive up to (including) 4k
+		 * screens
+		 */
+		topology.num_enc = 2;
+		topology.num_dsc = 2;
+		topology.num_intf = 1;
+		topology.num_lm = 2;
+	}
+
+	return topology;
+}
+
+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 dpu_global_state *global_state;
+	int i = 0;
+	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;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	priv = drm_enc->dev->dev_private;
+	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));
+
+	/* perform atomic check on the first physical encoder (master) */
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys->ops.atomic_check)
+			ret = phys->ops.atomic_check(phys, crtc_state,
+					conn_state);
+		if (ret) {
+			DPU_ERROR_ENC(dpu_enc,
+					"mode unsupported, phys idx %d\n", i);
+			break;
+		}
+	}
+
+	topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode);
+
+	/* Reserve dynamic resources now. */
+	if (!ret) {
+		/*
+		 * 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);
+
+			if (!crtc_state->active_changed || crtc_state->enable)
+				ret = dpu_rm_reserve(&dpu_kms->rm, global_state,
+						drm_enc, crtc_state, topology);
+		}
+	}
+
+	trace_dpu_enc_atomic_check_flags(DRMID(drm_enc), adj_mode->flags);
+
+	return ret;
+}
+
+static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc,
+			struct msm_display_info *disp_info)
+{
+	struct dpu_vsync_source_cfg vsync_cfg = { 0 };
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct dpu_hw_mdp *hw_mdptop;
+	struct drm_encoder *drm_enc;
+	int i;
+
+	if (!dpu_enc || !disp_info) {
+		DPU_ERROR("invalid param dpu_enc:%d or disp_info:%d\n",
+					dpu_enc != NULL, disp_info != NULL);
+		return;
+	} else if (dpu_enc->num_phys_encs > ARRAY_SIZE(dpu_enc->hw_pp)) {
+		DPU_ERROR("invalid num phys enc %d/%d\n",
+				dpu_enc->num_phys_encs,
+				(int) ARRAY_SIZE(dpu_enc->hw_pp));
+		return;
+	}
+
+	drm_enc = &dpu_enc->base;
+	/* this pointers are checked in virt_enable_helper */
+	priv = drm_enc->dev->dev_private;
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	hw_mdptop = dpu_kms->hw_mdp;
+	if (!hw_mdptop) {
+		DPU_ERROR("invalid mdptop\n");
+		return;
+	}
+
+	if (hw_mdptop->ops.setup_vsync_source &&
+			disp_info->is_cmd_mode) {
+		for (i = 0; i < dpu_enc->num_phys_encs; i++)
+			vsync_cfg.ppnumber[i] = dpu_enc->hw_pp[i]->idx;
+
+		vsync_cfg.pp_count = dpu_enc->num_phys_encs;
+		if (disp_info->is_te_using_watchdog_timer)
+			vsync_cfg.vsync_source = DPU_VSYNC_SOURCE_WD_TIMER_0;
+		else
+			vsync_cfg.vsync_source = DPU_VSYNC0_SOURCE_GPIO;
+
+		hw_mdptop->ops.setup_vsync_source(hw_mdptop, &vsync_cfg);
+	}
+}
+
+static void _dpu_encoder_irq_control(struct drm_encoder *drm_enc, bool enable)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	DPU_DEBUG_ENC(dpu_enc, "enable:%d\n", enable);
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys->ops.irq_control)
+			phys->ops.irq_control(phys, enable);
+	}
+
+}
+
+static void _dpu_encoder_resource_control_helper(struct drm_encoder *drm_enc,
+		bool enable)
+{
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct dpu_encoder_virt *dpu_enc;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	trace_dpu_enc_rc_helper(DRMID(drm_enc), enable);
+
+	if (!dpu_enc->cur_master) {
+		DPU_ERROR("encoder master not set\n");
+		return;
+	}
+
+	if (enable) {
+		/* enable DPU core clks */
+		pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+		/* enable all the irq */
+		_dpu_encoder_irq_control(drm_enc, true);
+
+	} else {
+		/* disable all the irq */
+		_dpu_encoder_irq_control(drm_enc, false);
+
+		/* disable DPU core clks */
+		pm_runtime_put_sync(&dpu_kms->pdev->dev);
+	}
+
+}
+
+static int dpu_encoder_resource_control(struct drm_encoder *drm_enc,
+		u32 sw_event)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	bool is_vid_mode = false;
+
+	if (!drm_enc || !drm_enc->dev || !drm_enc->crtc) {
+		DPU_ERROR("invalid parameters\n");
+		return -EINVAL;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	priv = drm_enc->dev->dev_private;
+	is_vid_mode = !dpu_enc->disp_info.is_cmd_mode;
+
+	/*
+	 * when idle_pc is not supported, process only KICKOFF, STOP and MODESET
+	 * events and return early for other events (ie wb display).
+	 */
+	if (!dpu_enc->idle_pc_supported &&
+			(sw_event != DPU_ENC_RC_EVENT_KICKOFF &&
+			sw_event != DPU_ENC_RC_EVENT_STOP &&
+			sw_event != DPU_ENC_RC_EVENT_PRE_STOP))
+		return 0;
+
+	trace_dpu_enc_rc(DRMID(drm_enc), sw_event, dpu_enc->idle_pc_supported,
+			 dpu_enc->rc_state, "begin");
+
+	switch (sw_event) {
+	case DPU_ENC_RC_EVENT_KICKOFF:
+		/* cancel delayed off work, if any */
+		if (cancel_delayed_work_sync(&dpu_enc->delayed_off_work))
+			DPU_DEBUG_ENC(dpu_enc, "sw_event:%d, work cancelled\n",
+					sw_event);
+
+		mutex_lock(&dpu_enc->rc_lock);
+
+		/* return if the resource control is already in ON state */
+		if (dpu_enc->rc_state == DPU_ENC_RC_STATE_ON) {
+			DRM_DEBUG_ATOMIC("id;%u, sw_event:%d, rc in ON state\n",
+				      DRMID(drm_enc), sw_event);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		} else if (dpu_enc->rc_state != DPU_ENC_RC_STATE_OFF &&
+				dpu_enc->rc_state != DPU_ENC_RC_STATE_IDLE) {
+			DRM_DEBUG_ATOMIC("id;%u, sw_event:%d, rc in state %d\n",
+				      DRMID(drm_enc), sw_event,
+				      dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return -EINVAL;
+		}
+
+		if (is_vid_mode && dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE)
+			_dpu_encoder_irq_control(drm_enc, true);
+		else
+			_dpu_encoder_resource_control_helper(drm_enc, true);
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_ON;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "kickoff");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	case DPU_ENC_RC_EVENT_FRAME_DONE:
+		/*
+		 * mutex lock is not used as this event happens at interrupt
+		 * context. And locking is not required as, the other events
+		 * like KICKOFF and STOP does a wait-for-idle before executing
+		 * the resource_control
+		 */
+		if (dpu_enc->rc_state != DPU_ENC_RC_STATE_ON) {
+			DRM_DEBUG_KMS("id:%d, sw_event:%d,rc:%d-unexpected\n",
+				      DRMID(drm_enc), sw_event,
+				      dpu_enc->rc_state);
+			return -EINVAL;
+		}
+
+		/*
+		 * schedule off work item only when there are no
+		 * frames pending
+		 */
+		if (dpu_crtc_frame_pending(drm_enc->crtc) > 1) {
+			DRM_DEBUG_KMS("id:%d skip schedule work\n",
+				      DRMID(drm_enc));
+			return 0;
+		}
+
+		queue_delayed_work(priv->wq, &dpu_enc->delayed_off_work,
+				   msecs_to_jiffies(dpu_enc->idle_timeout));
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "frame done");
+		break;
+
+	case DPU_ENC_RC_EVENT_PRE_STOP:
+		/* cancel delayed off work, if any */
+		if (cancel_delayed_work_sync(&dpu_enc->delayed_off_work))
+			DPU_DEBUG_ENC(dpu_enc, "sw_event:%d, work cancelled\n",
+					sw_event);
+
+		mutex_lock(&dpu_enc->rc_lock);
+
+		if (is_vid_mode &&
+			  dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE) {
+			_dpu_encoder_irq_control(drm_enc, true);
+		}
+		/* skip if is already OFF or IDLE, resources are off already */
+		else if (dpu_enc->rc_state == DPU_ENC_RC_STATE_OFF ||
+				dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE) {
+			DRM_DEBUG_KMS("id:%u, sw_event:%d, rc in %d state\n",
+				      DRMID(drm_enc), sw_event,
+				      dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		}
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_PRE_OFF;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "pre stop");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	case DPU_ENC_RC_EVENT_STOP:
+		mutex_lock(&dpu_enc->rc_lock);
+
+		/* return if the resource control is already in OFF state */
+		if (dpu_enc->rc_state == DPU_ENC_RC_STATE_OFF) {
+			DRM_DEBUG_KMS("id: %u, sw_event:%d, rc in OFF state\n",
+				      DRMID(drm_enc), sw_event);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		} else if (dpu_enc->rc_state == DPU_ENC_RC_STATE_ON) {
+			DRM_ERROR("id: %u, sw_event:%d, rc in state %d\n",
+				  DRMID(drm_enc), sw_event, dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return -EINVAL;
+		}
+
+		/**
+		 * expect to arrive here only if in either idle state or pre-off
+		 * and in IDLE state the resources are already disabled
+		 */
+		if (dpu_enc->rc_state == DPU_ENC_RC_STATE_PRE_OFF)
+			_dpu_encoder_resource_control_helper(drm_enc, false);
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_OFF;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "stop");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	case DPU_ENC_RC_EVENT_ENTER_IDLE:
+		mutex_lock(&dpu_enc->rc_lock);
+
+		if (dpu_enc->rc_state != DPU_ENC_RC_STATE_ON) {
+			DRM_ERROR("id: %u, sw_event:%d, rc:%d !ON state\n",
+				  DRMID(drm_enc), sw_event, dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		}
+
+		/*
+		 * if we are in ON but a frame was just kicked off,
+		 * ignore the IDLE event, it's probably a stale timer event
+		 */
+		if (dpu_enc->frame_busy_mask[0]) {
+			DRM_ERROR("id:%u, sw_event:%d, rc:%d frame pending\n",
+				  DRMID(drm_enc), sw_event, dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		}
+
+		if (is_vid_mode)
+			_dpu_encoder_irq_control(drm_enc, false);
+		else
+			_dpu_encoder_resource_control_helper(drm_enc, false);
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_IDLE;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "idle");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	default:
+		DRM_ERROR("id:%u, unexpected sw_event: %d\n", DRMID(drm_enc),
+			  sw_event);
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "error");
+		break;
+	}
+
+	trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+			 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+			 "end");
+	return 0;
+}
+
+void dpu_encoder_prepare_wb_job(struct drm_encoder *drm_enc,
+		struct drm_writeback_job *job)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys->ops.prepare_wb_job)
+			phys->ops.prepare_wb_job(phys, job);
+
+	}
+}
+
+void dpu_encoder_cleanup_wb_job(struct drm_encoder *drm_enc,
+		struct drm_writeback_job *job)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys->ops.cleanup_wb_job)
+			phys->ops.cleanup_wb_job(phys, job);
+
+	}
+}
+
+static void dpu_encoder_virt_atomic_mode_set(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 dpu_crtc_state *cstate;
+	struct dpu_global_state *global_state;
+	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_lm[MAX_CHANNELS_PER_ENC];
+	struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_ENC] = { NULL };
+	struct dpu_hw_blk *hw_dsc[MAX_CHANNELS_PER_ENC];
+	int num_lm, num_ctl, num_pp, num_dsc;
+	unsigned int dsc_mask = 0;
+	int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	global_state = dpu_kms_get_existing_global_state(dpu_kms);
+	if (IS_ERR_OR_NULL(global_state)) {
+		DPU_ERROR("Failed to get global state");
+		return;
+	}
+
+	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));
+	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));
+	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 < MAX_CHANNELS_PER_ENC; i++)
+		dpu_enc->hw_pp[i] = i < num_pp ? to_dpu_hw_pingpong(hw_pp[i])
+						: NULL;
+
+	if (dpu_enc->dsc) {
+		num_dsc = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+							drm_enc->base.id, 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]);
+			dsc_mask |= BIT(dpu_enc->hw_dsc[i]->idx - DSC_0);
+		}
+	}
+
+	dpu_enc->dsc_mask = dsc_mask;
+
+	cstate = to_dpu_crtc_state(crtc_state);
+
+	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 = to_dpu_hw_dspp(hw_dspp[i]);
+	}
+
+	cstate->num_mixers = num_lm;
+
+	dpu_enc->connector = conn_state->connector;
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!dpu_enc->hw_pp[i]) {
+			DPU_ERROR_ENC(dpu_enc,
+				"no pp block assigned at idx: %d\n", i);
+			return;
+		}
+
+		if (!hw_ctl[i]) {
+			DPU_ERROR_ENC(dpu_enc,
+				"no ctl block assigned at idx: %d\n", i);
+			return;
+		}
+
+		phys->hw_pp = dpu_enc->hw_pp[i];
+		phys->hw_ctl = to_dpu_hw_ctl(hw_ctl[i]);
+
+		phys->cached_mode = crtc_state->adjusted_mode;
+		if (phys->ops.atomic_mode_set)
+			phys->ops.atomic_mode_set(phys, crtc_state, conn_state);
+	}
+}
+
+static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i;
+
+	if (!drm_enc || !drm_enc->dev) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	if (!dpu_enc || !dpu_enc->cur_master) {
+		DPU_ERROR("invalid dpu encoder/master\n");
+		return;
+	}
+
+
+	if (dpu_enc->disp_info.intf_type == DRM_MODE_ENCODER_TMDS &&
+		dpu_enc->cur_master->hw_mdptop &&
+		dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select)
+		dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select(
+			dpu_enc->cur_master->hw_mdptop);
+
+	_dpu_encoder_update_vsync_source(dpu_enc, &dpu_enc->disp_info);
+
+	if (dpu_enc->disp_info.intf_type == DRM_MODE_ENCODER_DSI &&
+			!WARN_ON(dpu_enc->num_phys_encs == 0)) {
+		unsigned bpc = dpu_enc->connector->display_info.bpc;
+		for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) {
+			if (!dpu_enc->hw_pp[i])
+				continue;
+			_dpu_encoder_setup_dither(dpu_enc->hw_pp[i], bpc);
+		}
+	}
+}
+
+void dpu_encoder_virt_runtime_resume(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	mutex_lock(&dpu_enc->enc_lock);
+
+	if (!dpu_enc->enabled)
+		goto out;
+
+	if (dpu_enc->cur_slave && dpu_enc->cur_slave->ops.restore)
+		dpu_enc->cur_slave->ops.restore(dpu_enc->cur_slave);
+	if (dpu_enc->cur_master && dpu_enc->cur_master->ops.restore)
+		dpu_enc->cur_master->ops.restore(dpu_enc->cur_master);
+
+	_dpu_encoder_virt_enable_helper(drm_enc);
+
+out:
+	mutex_unlock(&dpu_enc->enc_lock);
+}
+
+static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int ret = 0;
+	struct drm_display_mode *cur_mode = NULL;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	mutex_lock(&dpu_enc->enc_lock);
+	cur_mode = &dpu_enc->base.crtc->state->adjusted_mode;
+
+	trace_dpu_enc_enable(DRMID(drm_enc), cur_mode->hdisplay,
+			     cur_mode->vdisplay);
+
+	/* always enable slave encoder before master */
+	if (dpu_enc->cur_slave && dpu_enc->cur_slave->ops.enable)
+		dpu_enc->cur_slave->ops.enable(dpu_enc->cur_slave);
+
+	if (dpu_enc->cur_master && dpu_enc->cur_master->ops.enable)
+		dpu_enc->cur_master->ops.enable(dpu_enc->cur_master);
+
+	ret = dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_KICKOFF);
+	if (ret) {
+		DPU_ERROR_ENC(dpu_enc, "dpu resource control failed: %d\n",
+				ret);
+		goto out;
+	}
+
+	_dpu_encoder_virt_enable_helper(drm_enc);
+
+	dpu_enc->enabled = true;
+
+out:
+	mutex_unlock(&dpu_enc->enc_lock);
+}
+
+static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i = 0;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	mutex_lock(&dpu_enc->enc_lock);
+	dpu_enc->enabled = false;
+
+	trace_dpu_enc_disable(DRMID(drm_enc));
+
+	/* wait for idle */
+	dpu_encoder_wait_for_event(drm_enc, MSM_ENC_TX_COMPLETE);
+
+	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_PRE_STOP);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys->ops.disable)
+			phys->ops.disable(phys);
+	}
+
+
+	/* 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);
+	}
+
+	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_STOP);
+
+	dpu_enc->connector = NULL;
+
+	DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n");
+
+	mutex_unlock(&dpu_enc->enc_lock);
+}
+
+static enum dpu_intf dpu_encoder_get_intf(const struct dpu_mdss_cfg *catalog,
+		enum dpu_intf_type type, u32 controller_id)
+{
+	int i = 0;
+
+	if (type == INTF_WB)
+		return INTF_MAX;
+
+	for (i = 0; i < catalog->intf_count; i++) {
+		if (catalog->intf[i].type == type
+		    && catalog->intf[i].controller_id == controller_id) {
+			return catalog->intf[i].id;
+		}
+	}
+
+	return INTF_MAX;
+}
+
+static enum dpu_wb dpu_encoder_get_wb(const struct dpu_mdss_cfg *catalog,
+		enum dpu_intf_type type, u32 controller_id)
+{
+	int i = 0;
+
+	if (type != INTF_WB)
+		return WB_MAX;
+
+	for (i = 0; i < catalog->wb_count; i++) {
+		if (catalog->wb[i].id == controller_id)
+			return catalog->wb[i].id;
+	}
+
+	return WB_MAX;
+}
+
+static void dpu_encoder_vblank_callback(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phy_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	unsigned long lock_flags;
+
+	if (!drm_enc || !phy_enc)
+		return;
+
+	DPU_ATRACE_BEGIN("encoder_vblank_callback");
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	atomic_inc(&phy_enc->vsync_cnt);
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	if (dpu_enc->crtc)
+		dpu_crtc_vblank_callback(dpu_enc->crtc);
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+
+	DPU_ATRACE_END("encoder_vblank_callback");
+}
+
+static void dpu_encoder_underrun_callback(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phy_enc)
+{
+	if (!phy_enc)
+		return;
+
+	DPU_ATRACE_BEGIN("encoder_underrun_callback");
+	atomic_inc(&phy_enc->underrun_cnt);
+
+	/* trigger dump only on the first underrun */
+	if (atomic_read(&phy_enc->underrun_cnt) == 1)
+		msm_disp_snapshot_state(drm_enc->dev);
+
+	trace_dpu_enc_underrun_cb(DRMID(drm_enc),
+				  atomic_read(&phy_enc->underrun_cnt));
+	DPU_ATRACE_END("encoder_underrun_callback");
+}
+
+void dpu_encoder_assign_crtc(struct drm_encoder *drm_enc, struct drm_crtc *crtc)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned long lock_flags;
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	/* crtc should always be cleared before re-assigning */
+	WARN_ON(crtc && dpu_enc->crtc);
+	dpu_enc->crtc = crtc;
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+}
+
+void dpu_encoder_toggle_vblank_for_crtc(struct drm_encoder *drm_enc,
+					struct drm_crtc *crtc, bool enable)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned long lock_flags;
+	int i;
+
+	trace_dpu_enc_vblank_cb(DRMID(drm_enc), enable);
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	if (dpu_enc->crtc != crtc) {
+		spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+		return;
+	}
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys->ops.control_vblank_irq)
+			phys->ops.control_vblank_irq(phys, enable);
+	}
+}
+
+void dpu_encoder_register_frame_event_callback(struct drm_encoder *drm_enc,
+		void (*frame_event_cb)(void *, u32 event),
+		void *frame_event_cb_data)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned long lock_flags;
+	bool enable;
+
+	enable = frame_event_cb ? true : false;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	trace_dpu_enc_frame_event_cb(DRMID(drm_enc), enable);
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	dpu_enc->crtc_frame_event_cb = frame_event_cb;
+	dpu_enc->crtc_frame_event_cb_data = frame_event_cb_data;
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+}
+
+static void dpu_encoder_frame_done_callback(
+		struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *ready_phys, u32 event)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned int i;
+
+	if (event & (DPU_ENCODER_FRAME_EVENT_DONE
+			| DPU_ENCODER_FRAME_EVENT_ERROR
+			| DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)) {
+
+		if (!dpu_enc->frame_busy_mask[0]) {
+			/**
+			 * suppress frame_done without waiter,
+			 * likely autorefresh
+			 */
+			trace_dpu_enc_frame_done_cb_not_busy(DRMID(drm_enc), event,
+					dpu_encoder_helper_get_intf_type(ready_phys->intf_mode),
+					ready_phys->intf_idx, ready_phys->wb_idx);
+			return;
+		}
+
+		/* One of the physical encoders has become idle */
+		for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+			if (dpu_enc->phys_encs[i] == ready_phys) {
+				trace_dpu_enc_frame_done_cb(DRMID(drm_enc), i,
+						dpu_enc->frame_busy_mask[0]);
+				clear_bit(i, dpu_enc->frame_busy_mask);
+			}
+		}
+
+		if (!dpu_enc->frame_busy_mask[0]) {
+			atomic_set(&dpu_enc->frame_done_timeout_ms, 0);
+			del_timer(&dpu_enc->frame_done_timer);
+
+			dpu_encoder_resource_control(drm_enc,
+					DPU_ENC_RC_EVENT_FRAME_DONE);
+
+			if (dpu_enc->crtc_frame_event_cb)
+				dpu_enc->crtc_frame_event_cb(
+					dpu_enc->crtc_frame_event_cb_data,
+					event);
+		}
+	} else {
+		if (dpu_enc->crtc_frame_event_cb)
+			dpu_enc->crtc_frame_event_cb(
+				dpu_enc->crtc_frame_event_cb_data, event);
+	}
+}
+
+static void dpu_encoder_off_work(struct work_struct *work)
+{
+	struct dpu_encoder_virt *dpu_enc = container_of(work,
+			struct dpu_encoder_virt, delayed_off_work.work);
+
+	dpu_encoder_resource_control(&dpu_enc->base,
+						DPU_ENC_RC_EVENT_ENTER_IDLE);
+
+	dpu_encoder_frame_done_callback(&dpu_enc->base, NULL,
+				DPU_ENCODER_FRAME_EVENT_IDLE);
+}
+
+/**
+ * _dpu_encoder_trigger_flush - trigger flush for a physical encoder
+ * @drm_enc: Pointer to drm encoder structure
+ * @phys: Pointer to physical encoder structure
+ * @extra_flush_bits: Additional bit mask to include in flush trigger
+ */
+static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phys, uint32_t extra_flush_bits)
+{
+	struct dpu_hw_ctl *ctl;
+	int pending_kickoff_cnt;
+	u32 ret = UINT_MAX;
+
+	if (!phys->hw_pp) {
+		DPU_ERROR("invalid pingpong hw\n");
+		return;
+	}
+
+	ctl = phys->hw_ctl;
+	if (!ctl->ops.trigger_flush) {
+		DPU_ERROR("missing trigger cb\n");
+		return;
+	}
+
+	pending_kickoff_cnt = dpu_encoder_phys_inc_pending(phys);
+
+	if (extra_flush_bits && ctl->ops.update_pending_flush)
+		ctl->ops.update_pending_flush(ctl, extra_flush_bits);
+
+	ctl->ops.trigger_flush(ctl);
+
+	if (ctl->ops.get_pending_flush)
+		ret = ctl->ops.get_pending_flush(ctl);
+
+	trace_dpu_enc_trigger_flush(DRMID(drm_enc),
+			dpu_encoder_helper_get_intf_type(phys->intf_mode),
+			phys->intf_idx, phys->wb_idx,
+			pending_kickoff_cnt, ctl->idx,
+			extra_flush_bits, ret);
+}
+
+/**
+ * _dpu_encoder_trigger_start - trigger start for a physical encoder
+ * @phys: Pointer to physical encoder structure
+ */
+static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys)
+{
+	if (!phys) {
+		DPU_ERROR("invalid argument(s)\n");
+		return;
+	}
+
+	if (!phys->hw_pp) {
+		DPU_ERROR("invalid pingpong hw\n");
+		return;
+	}
+
+	if (phys->ops.trigger_start && phys->enable_state != DPU_ENC_DISABLED)
+		phys->ops.trigger_start(phys);
+}
+
+void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_ctl *ctl;
+
+	ctl = phys_enc->hw_ctl;
+	if (ctl->ops.trigger_start) {
+		ctl->ops.trigger_start(ctl);
+		trace_dpu_enc_trigger_start(DRMID(phys_enc->parent), ctl->idx);
+	}
+}
+
+static int dpu_encoder_helper_wait_event_timeout(
+		int32_t drm_id,
+		u32 irq_idx,
+		struct dpu_encoder_wait_info *info)
+{
+	int rc = 0;
+	s64 expected_time = ktime_to_ms(ktime_get()) + info->timeout_ms;
+	s64 jiffies = msecs_to_jiffies(info->timeout_ms);
+	s64 time;
+
+	do {
+		rc = wait_event_timeout(*(info->wq),
+				atomic_read(info->atomic_cnt) == 0, jiffies);
+		time = ktime_to_ms(ktime_get());
+
+		trace_dpu_enc_wait_event_timeout(drm_id, irq_idx, rc, time,
+						 expected_time,
+						 atomic_read(info->atomic_cnt));
+	/* If we timed out, counter is valid and time is less, wait again */
+	} while (atomic_read(info->atomic_cnt) && (rc == 0) &&
+			(time < expected_time));
+
+	return rc;
+}
+
+static void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_hw_ctl *ctl;
+	int rc;
+	struct drm_encoder *drm_enc;
+
+	dpu_enc = to_dpu_encoder_virt(phys_enc->parent);
+	ctl = phys_enc->hw_ctl;
+	drm_enc = phys_enc->parent;
+
+	if (!ctl->ops.reset)
+		return;
+
+	DRM_DEBUG_KMS("id:%u ctl %d reset\n", DRMID(drm_enc),
+		      ctl->idx);
+
+	rc = ctl->ops.reset(ctl);
+	if (rc) {
+		DPU_ERROR_ENC(dpu_enc, "ctl %d reset failure\n",  ctl->idx);
+		msm_disp_snapshot_state(drm_enc->dev);
+	}
+
+	phys_enc->enable_state = DPU_ENC_ENABLED;
+}
+
+/**
+ * _dpu_encoder_kickoff_phys - handle physical encoder kickoff
+ *	Iterate through the physical encoders and perform consolidated flush
+ *	and/or control start triggering as needed. This is done in the virtual
+ *	encoder rather than the individual physical ones in order to handle
+ *	use cases that require visibility into multiple physical encoders at
+ *	a time.
+ * @dpu_enc: Pointer to virtual encoder structure
+ */
+static void _dpu_encoder_kickoff_phys(struct dpu_encoder_virt *dpu_enc)
+{
+	struct dpu_hw_ctl *ctl;
+	uint32_t i, pending_flush;
+	unsigned long lock_flags;
+
+	pending_flush = 0x0;
+
+	/* update pending counts and trigger kickoff ctl flush atomically */
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+
+	/* don't perform flush/start operations for slave encoders */
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys->enable_state == DPU_ENC_DISABLED)
+			continue;
+
+		ctl = phys->hw_ctl;
+
+		/*
+		 * This is cleared in frame_done worker, which isn't invoked
+		 * for async commits. So don't set this for async, since it'll
+		 * roll over to the next commit.
+		 */
+		if (phys->split_role != ENC_ROLE_SLAVE)
+			set_bit(i, dpu_enc->frame_busy_mask);
+
+		if (!phys->ops.needs_single_flush ||
+				!phys->ops.needs_single_flush(phys))
+			_dpu_encoder_trigger_flush(&dpu_enc->base, phys, 0x0);
+		else if (ctl->ops.get_pending_flush)
+			pending_flush |= ctl->ops.get_pending_flush(ctl);
+	}
+
+	/* for split flush, combine pending flush masks and send to master */
+	if (pending_flush && dpu_enc->cur_master) {
+		_dpu_encoder_trigger_flush(
+				&dpu_enc->base,
+				dpu_enc->cur_master,
+				pending_flush);
+	}
+
+	_dpu_encoder_trigger_start(dpu_enc->cur_master);
+
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+}
+
+void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	unsigned int i;
+	struct dpu_hw_ctl *ctl;
+	struct msm_display_info *disp_info;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	disp_info = &dpu_enc->disp_info;
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+
+		ctl = phys->hw_ctl;
+		if (ctl->ops.clear_pending_flush)
+			ctl->ops.clear_pending_flush(ctl);
+
+		/* update only for command mode primary ctl */
+		if ((phys == dpu_enc->cur_master) &&
+		    disp_info->is_cmd_mode
+		    && ctl->ops.trigger_pending)
+			ctl->ops.trigger_pending(ctl);
+	}
+}
+
+static u32 _dpu_encoder_calculate_linetime(struct dpu_encoder_virt *dpu_enc,
+		struct drm_display_mode *mode)
+{
+	u64 pclk_rate;
+	u32 pclk_period;
+	u32 line_time;
+
+	/*
+	 * For linetime calculation, only operate on master encoder.
+	 */
+	if (!dpu_enc->cur_master)
+		return 0;
+
+	if (!dpu_enc->cur_master->ops.get_line_count) {
+		DPU_ERROR("get_line_count function not defined\n");
+		return 0;
+	}
+
+	pclk_rate = mode->clock; /* pixel clock in kHz */
+	if (pclk_rate == 0) {
+		DPU_ERROR("pclk is 0, cannot calculate line time\n");
+		return 0;
+	}
+
+	pclk_period = DIV_ROUND_UP_ULL(1000000000ull, pclk_rate);
+	if (pclk_period == 0) {
+		DPU_ERROR("pclk period is 0\n");
+		return 0;
+	}
+
+	/*
+	 * Line time calculation based on Pixel clock and HTOTAL.
+	 * Final unit is in ns.
+	 */
+	line_time = (pclk_period * mode->htotal) / 1000;
+	if (line_time == 0) {
+		DPU_ERROR("line time calculation is 0\n");
+		return 0;
+	}
+
+	DPU_DEBUG_ENC(dpu_enc,
+			"clk_rate=%lldkHz, clk_period=%d, linetime=%dns\n",
+			pclk_rate, pclk_period, line_time);
+
+	return line_time;
+}
+
+int dpu_encoder_vsync_time(struct drm_encoder *drm_enc, ktime_t *wakeup_time)
+{
+	struct drm_display_mode *mode;
+	struct dpu_encoder_virt *dpu_enc;
+	u32 cur_line;
+	u32 line_time;
+	u32 vtotal, time_to_vsync;
+	ktime_t cur_time;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	if (!drm_enc->crtc || !drm_enc->crtc->state) {
+		DPU_ERROR("crtc/crtc state object is NULL\n");
+		return -EINVAL;
+	}
+	mode = &drm_enc->crtc->state->adjusted_mode;
+
+	line_time = _dpu_encoder_calculate_linetime(dpu_enc, mode);
+	if (!line_time)
+		return -EINVAL;
+
+	cur_line = dpu_enc->cur_master->ops.get_line_count(dpu_enc->cur_master);
+
+	vtotal = mode->vtotal;
+	if (cur_line >= vtotal)
+		time_to_vsync = line_time * vtotal;
+	else
+		time_to_vsync = line_time * (vtotal - cur_line);
+
+	if (time_to_vsync == 0) {
+		DPU_ERROR("time to vsync should not be zero, vtotal=%d\n",
+				vtotal);
+		return -EINVAL;
+	}
+
+	cur_time = ktime_get();
+	*wakeup_time = ktime_add_ns(cur_time, time_to_vsync);
+
+	DPU_DEBUG_ENC(dpu_enc,
+			"cur_line=%u vtotal=%u time_to_vsync=%u, cur_time=%lld, wakeup_time=%lld\n",
+			cur_line, vtotal, time_to_vsync,
+			ktime_to_ms(cur_time),
+			ktime_to_ms(*wakeup_time));
+	return 0;
+}
+
+static void dpu_encoder_vsync_event_handler(struct timer_list *t)
+{
+	struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t,
+			vsync_event_timer);
+	struct drm_encoder *drm_enc = &dpu_enc->base;
+	struct msm_drm_private *priv;
+	struct msm_drm_thread *event_thread;
+
+	if (!drm_enc->dev || !drm_enc->crtc) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	priv = drm_enc->dev->dev_private;
+
+	if (drm_enc->crtc->index >= ARRAY_SIZE(priv->event_thread)) {
+		DPU_ERROR("invalid crtc index\n");
+		return;
+	}
+	event_thread = &priv->event_thread[drm_enc->crtc->index];
+	if (!event_thread) {
+		DPU_ERROR("event_thread not found for crtc:%d\n",
+				drm_enc->crtc->index);
+		return;
+	}
+
+	del_timer(&dpu_enc->vsync_event_timer);
+}
+
+static void dpu_encoder_vsync_event_work_handler(struct kthread_work *work)
+{
+	struct dpu_encoder_virt *dpu_enc = container_of(work,
+			struct dpu_encoder_virt, vsync_event_work);
+	ktime_t wakeup_time;
+
+	if (dpu_encoder_vsync_time(&dpu_enc->base, &wakeup_time))
+		return;
+
+	trace_dpu_enc_vsync_event_work(DRMID(&dpu_enc->base), wakeup_time);
+	mod_timer(&dpu_enc->vsync_event_timer,
+			nsecs_to_jiffies(ktime_to_ns(wakeup_time)));
+}
+
+static u32
+dpu_encoder_dsc_initial_line_calc(struct drm_dsc_config *dsc,
+				  u32 enc_ip_width)
+{
+	int ssm_delay, total_pixels, soft_slice_per_enc;
+
+	soft_slice_per_enc = enc_ip_width / dsc->slice_width;
+
+	/*
+	 * minimum number of initial line pixels is a sum of:
+	 * 1. sub-stream multiplexer delay (83 groups for 8bpc,
+	 *    91 for 10 bpc) * 3
+	 * 2. for two soft slice cases, add extra sub-stream multiplexer * 3
+	 * 3. the initial xmit delay
+	 * 4. total pipeline delay through the "lock step" of encoder (47)
+	 * 5. 6 additional pixels as the output of the rate buffer is
+	 *    48 bits wide
+	 */
+	ssm_delay = ((dsc->bits_per_component < 10) ? 84 : 92);
+	total_pixels = ssm_delay * 3 + dsc->initial_xmit_delay + 47;
+	if (soft_slice_per_enc > 1)
+		total_pixels += (ssm_delay * 3);
+	return DIV_ROUND_UP(total_pixels, dsc->slice_width);
+}
+
+static void dpu_encoder_dsc_pipe_cfg(struct dpu_hw_dsc *hw_dsc,
+				     struct dpu_hw_pingpong *hw_pp,
+				     struct drm_dsc_config *dsc,
+				     u32 common_mode,
+				     u32 initial_lines)
+{
+	if (hw_dsc->ops.dsc_config)
+		hw_dsc->ops.dsc_config(hw_dsc, dsc, common_mode, initial_lines);
+
+	if (hw_dsc->ops.dsc_config_thresh)
+		hw_dsc->ops.dsc_config_thresh(hw_dsc, dsc);
+
+	if (hw_pp->ops.setup_dsc)
+		hw_pp->ops.setup_dsc(hw_pp);
+
+	if (hw_pp->ops.enable_dsc)
+		hw_pp->ops.enable_dsc(hw_pp);
+}
+
+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_dsc *hw_dsc[MAX_CHANNELS_PER_ENC];
+	struct dpu_hw_pingpong *hw_pp[MAX_CHANNELS_PER_ENC];
+	int this_frame_slices;
+	int intf_ip_w, enc_ip_w;
+	int dsc_common_mode;
+	int pic_width;
+	u32 initial_lines;
+	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;
+		}
+	}
+
+	dsc_common_mode = 0;
+	pic_width = dsc->pic_width;
+
+	dsc_common_mode = DSC_MODE_MULTIPLEX | DSC_MODE_SPLIT_PANEL;
+	if (enc_master->intf_mode == INTF_MODE_VIDEO)
+		dsc_common_mode |= DSC_MODE_VIDEO;
+
+	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;
+	initial_lines = dpu_encoder_dsc_initial_line_calc(dsc, enc_ip_w);
+
+	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++)
+		dpu_encoder_dsc_pipe_cfg(hw_dsc[i], hw_pp[i], dsc, dsc_common_mode, initial_lines);
+}
+
+void dpu_encoder_prepare_for_kickoff(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	bool needs_hw_reset = false;
+	unsigned int i;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	trace_dpu_enc_prepare_kickoff(DRMID(drm_enc));
+
+	/* prepare for next kickoff, may include waiting on previous kickoff */
+	DPU_ATRACE_BEGIN("enc_prepare_for_kickoff");
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+		if (phys->ops.prepare_for_kickoff)
+			phys->ops.prepare_for_kickoff(phys);
+		if (phys->enable_state == DPU_ENC_ERR_NEEDS_HW_RESET)
+			needs_hw_reset = true;
+	}
+	DPU_ATRACE_END("enc_prepare_for_kickoff");
+
+	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_KICKOFF);
+
+	/* if any phys needs reset, reset all phys, in-order */
+	if (needs_hw_reset) {
+		trace_dpu_enc_prepare_kickoff_reset(DRMID(drm_enc));
+		for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+			dpu_encoder_helper_hw_reset(dpu_enc->phys_encs[i]);
+		}
+	}
+
+	if (dpu_enc->dsc)
+		dpu_encoder_prep_dsc(dpu_enc, dpu_enc->dsc);
+}
+
+bool dpu_encoder_is_valid_for_commit(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	unsigned int i;
+	struct dpu_encoder_phys *phys;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	if (drm_enc->encoder_type == DRM_MODE_ENCODER_VIRTUAL) {
+		for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+			phys = dpu_enc->phys_encs[i];
+			if (phys->ops.is_valid_for_commit && !phys->ops.is_valid_for_commit(phys)) {
+				DPU_DEBUG("invalid FB not kicking off\n");
+				return false;
+			}
+		}
+	}
+
+	return true;
+}
+
+void dpu_encoder_kickoff(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	ktime_t wakeup_time;
+	unsigned long timeout_ms;
+	unsigned int i;
+
+	DPU_ATRACE_BEGIN("encoder_kickoff");
+	dpu_enc = to_dpu_encoder_virt(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);
+
+	/* allow phys encs to handle any post-kickoff business */
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+		if (phys->ops.handle_post_kickoff)
+			phys->ops.handle_post_kickoff(phys);
+	}
+
+	if (dpu_enc->disp_info.intf_type == DRM_MODE_ENCODER_DSI &&
+			!dpu_encoder_vsync_time(drm_enc, &wakeup_time)) {
+		trace_dpu_enc_early_kickoff(DRMID(drm_enc),
+					    ktime_to_ms(wakeup_time));
+		mod_timer(&dpu_enc->vsync_event_timer,
+				nsecs_to_jiffies(ktime_to_ns(wakeup_time)));
+	}
+
+	DPU_ATRACE_END("encoder_kickoff");
+}
+
+static void dpu_encoder_helper_reset_mixers(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_mixer_cfg mixer;
+	int i, num_lm;
+	struct dpu_global_state *global_state;
+	struct dpu_hw_blk *hw_lm[2];
+	struct dpu_hw_mixer *hw_mixer[2];
+	struct dpu_hw_ctl *ctl = phys_enc->hw_ctl;
+
+	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);
+
+	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));
+
+	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);
+
+		/* clear all blendstages */
+		if (phys_enc->hw_ctl->ops.setup_blendstage)
+			phys_enc->hw_ctl->ops.setup_blendstage(ctl, hw_mixer[i]->idx, NULL);
+	}
+}
+
+void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_ctl *ctl = phys_enc->hw_ctl;
+	struct dpu_hw_intf_cfg intf_cfg = { 0 };
+	int i;
+	struct dpu_encoder_virt *dpu_enc;
+
+	dpu_enc = to_dpu_encoder_virt(phys_enc->parent);
+
+	phys_enc->hw_ctl->ops.reset(ctl);
+
+	dpu_encoder_helper_reset_mixers(phys_enc);
+
+	/*
+	 * TODO: move the once-only operation like CTL flush/trigger
+	 * into dpu_encoder_virt_disable() and all operations which need
+	 * to be done per phys encoder into the phys_disable() op.
+	 */
+	if (phys_enc->hw_wb) {
+		/* disable the PP block */
+		if (phys_enc->hw_wb->ops.bind_pingpong_blk)
+			phys_enc->hw_wb->ops.bind_pingpong_blk(phys_enc->hw_wb, false,
+					phys_enc->hw_pp->idx);
+
+		/* 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);
+	} 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)
+				phys_enc->hw_intf->ops.bind_pingpong_blk(
+						dpu_enc->phys_encs[i]->hw_intf, false,
+						dpu_enc->phys_encs[i]->hw_pp->idx);
+
+			/* 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,
+						dpu_enc->phys_encs[i]->hw_intf->idx);
+		}
+	}
+
+	/* reset the merge 3D HW block */
+	if (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,
+					phys_enc->hw_pp->merge_3d->idx);
+	}
+
+	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);
+
+	if (phys_enc->hw_intf)
+		intf_cfg.intf = phys_enc->hw_intf->idx;
+	if (phys_enc->hw_wb)
+		intf_cfg.wb = phys_enc->hw_wb->idx;
+
+	if (phys_enc->hw_pp->merge_3d)
+		intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
+
+	if (ctl->ops.reset_intf_cfg)
+		ctl->ops.reset_intf_cfg(ctl, &intf_cfg);
+
+	ctl->ops.trigger_flush(ctl);
+	ctl->ops.trigger_start(ctl);
+	ctl->ops.clear_pending_flush(ctl);
+}
+
+void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+		if (phys->ops.prepare_commit)
+			phys->ops.prepare_commit(phys);
+	}
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int _dpu_encoder_status_show(struct seq_file *s, void *data)
+{
+	struct dpu_encoder_virt *dpu_enc = s->private;
+	int i;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		seq_printf(s, "intf:%d  wb:%d  vsync:%8d     underrun:%8d    ",
+				phys->intf_idx - INTF_0, phys->wb_idx - WB_0,
+				atomic_read(&phys->vsync_cnt),
+				atomic_read(&phys->underrun_cnt));
+
+		seq_printf(s, "mode: %s\n", dpu_encoder_helper_get_intf_type(phys->intf_mode));
+	}
+	mutex_unlock(&dpu_enc->enc_lock);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(_dpu_encoder_status);
+
+static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	int i;
+
+	char name[DPU_NAME_SIZE];
+
+	if (!drm_enc->dev) {
+		DPU_ERROR("invalid encoder or kms\n");
+		return -EINVAL;
+	}
+
+	snprintf(name, DPU_NAME_SIZE, "encoder%u", drm_enc->base.id);
+
+	/* create overall sub-directory for the encoder */
+	dpu_enc->debugfs_root = debugfs_create_dir(name,
+			drm_enc->dev->primary->debugfs_root);
+
+	/* don't error check these */
+	debugfs_create_file("status", 0600,
+		dpu_enc->debugfs_root, dpu_enc, &_dpu_encoder_status_fops);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++)
+		if (dpu_enc->phys_encs[i]->ops.late_register)
+			dpu_enc->phys_encs[i]->ops.late_register(
+					dpu_enc->phys_encs[i],
+					dpu_enc->debugfs_root);
+
+	return 0;
+}
+#else
+static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
+{
+	return 0;
+}
+#endif
+
+static int dpu_encoder_late_register(struct drm_encoder *encoder)
+{
+	return _dpu_encoder_init_debugfs(encoder);
+}
+
+static void dpu_encoder_early_unregister(struct drm_encoder *encoder)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(encoder);
+
+	debugfs_remove_recursive(dpu_enc->debugfs_root);
+}
+
+static int dpu_encoder_virt_add_phys_encs(
+		struct msm_display_info *disp_info,
+		struct dpu_encoder_virt *dpu_enc,
+		struct dpu_enc_phys_init_params *params)
+{
+	struct dpu_encoder_phys *enc = NULL;
+
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	/*
+	 * We may create up to NUM_PHYS_ENCODER_TYPES physical encoder types
+	 * in this function, check up-front.
+	 */
+	if (dpu_enc->num_phys_encs + NUM_PHYS_ENCODER_TYPES >=
+			ARRAY_SIZE(dpu_enc->phys_encs)) {
+		DPU_ERROR_ENC(dpu_enc, "too many physical encoders %d\n",
+			  dpu_enc->num_phys_encs);
+		return -EINVAL;
+	}
+
+
+	if (disp_info->intf_type == DRM_MODE_ENCODER_VIRTUAL) {
+		enc = dpu_encoder_phys_wb_init(params);
+
+		if (IS_ERR(enc)) {
+			DPU_ERROR_ENC(dpu_enc, "failed to init wb enc: %ld\n",
+				PTR_ERR(enc));
+			return PTR_ERR(enc);
+		}
+
+		dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc;
+		++dpu_enc->num_phys_encs;
+	} else if (disp_info->is_cmd_mode) {
+		enc = dpu_encoder_phys_cmd_init(params);
+
+		if (IS_ERR(enc)) {
+			DPU_ERROR_ENC(dpu_enc, "failed to init cmd enc: %ld\n",
+				PTR_ERR(enc));
+			return PTR_ERR(enc);
+		}
+
+		dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc;
+		++dpu_enc->num_phys_encs;
+	} else {
+		enc = dpu_encoder_phys_vid_init(params);
+
+		if (IS_ERR(enc)) {
+			DPU_ERROR_ENC(dpu_enc, "failed to init vid enc: %ld\n",
+				PTR_ERR(enc));
+			return PTR_ERR(enc);
+		}
+
+		dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc;
+		++dpu_enc->num_phys_encs;
+	}
+
+	if (params->split_role == ENC_ROLE_SLAVE)
+		dpu_enc->cur_slave = enc;
+	else
+		dpu_enc->cur_master = enc;
+
+	return 0;
+}
+
+static const struct dpu_encoder_virt_ops dpu_encoder_parent_ops = {
+	.handle_vblank_virt = dpu_encoder_vblank_callback,
+	.handle_underrun_virt = dpu_encoder_underrun_callback,
+	.handle_frame_done = dpu_encoder_frame_done_callback,
+};
+
+static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc,
+				 struct dpu_kms *dpu_kms,
+				 struct msm_display_info *disp_info)
+{
+	int ret = 0;
+	int i = 0;
+	enum dpu_intf_type intf_type = INTF_NONE;
+	struct dpu_enc_phys_init_params phys_params;
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid arg(s), enc %d\n", dpu_enc != NULL);
+		return -EINVAL;
+	}
+
+	dpu_enc->cur_master = NULL;
+
+	memset(&phys_params, 0, sizeof(phys_params));
+	phys_params.dpu_kms = dpu_kms;
+	phys_params.parent = &dpu_enc->base;
+	phys_params.parent_ops = &dpu_encoder_parent_ops;
+	phys_params.enc_spinlock = &dpu_enc->enc_spinlock;
+
+	switch (disp_info->intf_type) {
+	case DRM_MODE_ENCODER_DSI:
+		intf_type = INTF_DSI;
+		break;
+	case DRM_MODE_ENCODER_TMDS:
+		intf_type = INTF_DP;
+		break;
+	case DRM_MODE_ENCODER_VIRTUAL:
+		intf_type = INTF_WB;
+		break;
+	}
+
+	WARN_ON(disp_info->num_of_h_tiles < 1);
+
+	DPU_DEBUG("dsi_info->num_of_h_tiles %d\n", disp_info->num_of_h_tiles);
+
+	if (disp_info->intf_type != DRM_MODE_ENCODER_VIRTUAL)
+		dpu_enc->idle_pc_supported =
+				dpu_kms->catalog->caps->has_idle_pc;
+
+	dpu_enc->dsc = disp_info->dsc;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	for (i = 0; i < disp_info->num_of_h_tiles && !ret; i++) {
+		/*
+		 * Left-most tile is at index 0, content is controller id
+		 * h_tile_instance_ids[2] = {0, 1}; DSI0 = left, DSI1 = right
+		 * h_tile_instance_ids[2] = {1, 0}; DSI1 = left, DSI0 = right
+		 */
+		u32 controller_id = disp_info->h_tile_instance[i];
+
+		if (disp_info->num_of_h_tiles > 1) {
+			if (i == 0)
+				phys_params.split_role = ENC_ROLE_MASTER;
+			else
+				phys_params.split_role = ENC_ROLE_SLAVE;
+		} else {
+			phys_params.split_role = ENC_ROLE_SOLO;
+		}
+
+		DPU_DEBUG("h_tile_instance %d = %d, split_role %d\n",
+				i, controller_id, phys_params.split_role);
+
+		phys_params.intf_idx = dpu_encoder_get_intf(dpu_kms->catalog,
+													intf_type,
+													controller_id);
+
+		phys_params.wb_idx = dpu_encoder_get_wb(dpu_kms->catalog,
+				intf_type, controller_id);
+		/*
+		 * The phys_params might represent either an INTF or a WB unit, but not
+		 * both of them at the same time.
+		 */
+		if ((phys_params.intf_idx == INTF_MAX) &&
+				(phys_params.wb_idx == WB_MAX)) {
+			DPU_ERROR_ENC(dpu_enc, "could not get intf or wb: type %d, id %d\n",
+						  intf_type, controller_id);
+			ret = -EINVAL;
+		}
+
+		if ((phys_params.intf_idx != INTF_MAX) &&
+				(phys_params.wb_idx != WB_MAX)) {
+			DPU_ERROR_ENC(dpu_enc, "both intf and wb present: type %d, id %d\n",
+						  intf_type, controller_id);
+			ret = -EINVAL;
+		}
+
+		if (!ret) {
+			ret = dpu_encoder_virt_add_phys_encs(disp_info,
+					dpu_enc, &phys_params);
+			if (ret)
+				DPU_ERROR_ENC(dpu_enc, "failed to add phys encs\n");
+		}
+	}
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+		atomic_set(&phys->vsync_cnt, 0);
+		atomic_set(&phys->underrun_cnt, 0);
+
+		if (phys->intf_idx >= INTF_0 && phys->intf_idx < INTF_MAX)
+			phys->hw_intf = dpu_rm_get_intf(&dpu_kms->rm, phys->intf_idx);
+
+		if (phys->wb_idx >= WB_0 && phys->wb_idx < WB_MAX)
+			phys->hw_wb = dpu_rm_get_wb(&dpu_kms->rm, phys->wb_idx);
+
+		if (!phys->hw_intf && !phys->hw_wb) {
+			DPU_ERROR_ENC(dpu_enc, "no intf or wb block assigned at idx: %d\n", i);
+			ret = -EINVAL;
+		}
+
+		if (phys->hw_intf && phys->hw_wb) {
+			DPU_ERROR_ENC(dpu_enc,
+					"invalid phys both intf and wb block at idx: %d\n", i);
+			ret = -EINVAL;
+		}
+	}
+
+	mutex_unlock(&dpu_enc->enc_lock);
+
+	return ret;
+}
+
+static void dpu_encoder_frame_done_timeout(struct timer_list *t)
+{
+	struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t,
+			frame_done_timer);
+	struct drm_encoder *drm_enc = &dpu_enc->base;
+	u32 event;
+
+	if (!drm_enc->dev) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	if (!dpu_enc->frame_busy_mask[0] || !dpu_enc->crtc_frame_event_cb) {
+		DRM_DEBUG_KMS("id:%u invalid timeout frame_busy_mask=%lu\n",
+			      DRMID(drm_enc), dpu_enc->frame_busy_mask[0]);
+		return;
+	} else if (!atomic_xchg(&dpu_enc->frame_done_timeout_ms, 0)) {
+		DRM_DEBUG_KMS("id:%u invalid timeout\n", DRMID(drm_enc));
+		return;
+	}
+
+	DPU_ERROR_ENC(dpu_enc, "frame done timeout\n");
+
+	event = DPU_ENCODER_FRAME_EVENT_ERROR;
+	trace_dpu_enc_frame_done_timeout(DRMID(drm_enc), event);
+	dpu_enc->crtc_frame_event_cb(dpu_enc->crtc_frame_event_cb_data, event);
+}
+
+static const struct drm_encoder_helper_funcs dpu_encoder_helper_funcs = {
+	.atomic_mode_set = dpu_encoder_virt_atomic_mode_set,
+	.disable = dpu_encoder_virt_disable,
+	.enable = dpu_encoder_virt_enable,
+	.atomic_check = dpu_encoder_virt_atomic_check,
+};
+
+static const struct drm_encoder_funcs dpu_encoder_funcs = {
+		.destroy = dpu_encoder_destroy,
+		.late_register = dpu_encoder_late_register,
+		.early_unregister = dpu_encoder_early_unregister,
+};
+
+int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
+		struct msm_display_info *disp_info)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
+	struct drm_encoder *drm_enc = NULL;
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int ret = 0;
+
+	dpu_enc = to_dpu_encoder_virt(enc);
+
+	ret = dpu_encoder_setup_display(dpu_enc, dpu_kms, disp_info);
+	if (ret)
+		goto fail;
+
+	atomic_set(&dpu_enc->frame_done_timeout_ms, 0);
+	timer_setup(&dpu_enc->frame_done_timer,
+			dpu_encoder_frame_done_timeout, 0);
+
+	if (disp_info->intf_type == DRM_MODE_ENCODER_DSI)
+		timer_setup(&dpu_enc->vsync_event_timer,
+				dpu_encoder_vsync_event_handler,
+				0);
+	else if (disp_info->intf_type == DRM_MODE_ENCODER_TMDS)
+		dpu_enc->wide_bus_en = msm_dp_wide_bus_available(
+				priv->dp[disp_info->h_tile_instance[0]]);
+
+	INIT_DELAYED_WORK(&dpu_enc->delayed_off_work,
+			dpu_encoder_off_work);
+	dpu_enc->idle_timeout = IDLE_TIMEOUT;
+
+	kthread_init_work(&dpu_enc->vsync_event_work,
+			dpu_encoder_vsync_event_work_handler);
+
+	memcpy(&dpu_enc->disp_info, disp_info, sizeof(*disp_info));
+
+	DPU_DEBUG_ENC(dpu_enc, "created\n");
+
+	return ret;
+
+fail:
+	DPU_ERROR("failed to create encoder\n");
+	if (drm_enc)
+		dpu_encoder_destroy(drm_enc);
+
+	return ret;
+
+
+}
+
+struct drm_encoder *dpu_encoder_init(struct drm_device *dev,
+		int drm_enc_mode)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int rc = 0;
+
+	dpu_enc = devm_kzalloc(dev->dev, sizeof(*dpu_enc), GFP_KERNEL);
+	if (!dpu_enc)
+		return ERR_PTR(-ENOMEM);
+
+
+	rc = drm_encoder_init(dev, &dpu_enc->base, &dpu_encoder_funcs,
+							  drm_enc_mode, NULL);
+	if (rc) {
+		devm_kfree(dev->dev, dpu_enc);
+		return ERR_PTR(rc);
+	}
+
+	drm_encoder_helper_add(&dpu_enc->base, &dpu_encoder_helper_funcs);
+
+	spin_lock_init(&dpu_enc->enc_spinlock);
+	dpu_enc->enabled = false;
+	mutex_init(&dpu_enc->enc_lock);
+	mutex_init(&dpu_enc->rc_lock);
+
+	return &dpu_enc->base;
+}
+
+int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc,
+	enum msm_event_wait event)
+{
+	int (*fn_wait)(struct dpu_encoder_phys *phys_enc) = NULL;
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i, ret = 0;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		switch (event) {
+		case MSM_ENC_COMMIT_DONE:
+			fn_wait = phys->ops.wait_for_commit_done;
+			break;
+		case MSM_ENC_TX_COMPLETE:
+			fn_wait = phys->ops.wait_for_tx_complete;
+			break;
+		case MSM_ENC_VBLANK:
+			fn_wait = phys->ops.wait_for_vblank;
+			break;
+		default:
+			DPU_ERROR_ENC(dpu_enc, "unknown wait event %d\n",
+					event);
+			return -EINVAL;
+		}
+
+		if (fn_wait) {
+			DPU_ATRACE_BEGIN("wait_for_completion_event");
+			ret = fn_wait(phys);
+			DPU_ATRACE_END("wait_for_completion_event");
+			if (ret)
+				return ret;
+		}
+	}
+
+	return ret;
+}
+
+enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+
+	if (!encoder) {
+		DPU_ERROR("invalid encoder\n");
+		return INTF_MODE_NONE;
+	}
+	dpu_enc = to_dpu_encoder_virt(encoder);
+
+	if (dpu_enc->cur_master)
+		return dpu_enc->cur_master->intf_mode;
+
+	if (dpu_enc->num_phys_encs)
+		return dpu_enc->phys_encs[0]->intf_mode;
+
+	return INTF_MODE_NONE;
+}
+
+unsigned int dpu_encoder_helper_get_dsc(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->dsc_mask;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
new file mode 100644
index 000000000..9e7236ef3
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
@@ -0,0 +1,227 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#ifndef __DPU_ENCODER_H__
+#define __DPU_ENCODER_H__
+
+#include <drm/drm_crtc.h>
+#include "dpu_hw_mdss.h"
+
+#define DPU_ENCODER_FRAME_EVENT_DONE			BIT(0)
+#define DPU_ENCODER_FRAME_EVENT_ERROR			BIT(1)
+#define DPU_ENCODER_FRAME_EVENT_PANEL_DEAD		BIT(2)
+#define DPU_ENCODER_FRAME_EVENT_IDLE			BIT(3)
+
+#define IDLE_TIMEOUT	(66 - 16/2)
+
+/**
+ * struct msm_display_info - defines display properties
+ * @intf_type:          DRM_MODE_ENCODER_ type
+ * @num_of_h_tiles:     Number of horizontal tiles in case of split interface
+ * @h_tile_instance:    Controller instance used per tile. Number of elements is
+ *                      based on num_of_h_tiles
+ * @is_cmd_mode		Boolean to indicate if the CMD mode is requested
+ * @is_te_using_watchdog_timer:  Boolean to indicate watchdog TE is
+ *				 used instead of panel TE in cmd mode panels
+ * @dsc:		DSC configuration data for DSC-enabled displays
+ */
+struct msm_display_info {
+	int intf_type;
+	uint32_t num_of_h_tiles;
+	uint32_t h_tile_instance[MAX_H_TILES_PER_DISPLAY];
+	bool is_cmd_mode;
+	bool is_te_using_watchdog_timer;
+	struct drm_dsc_config *dsc;
+};
+
+/**
+ * dpu_encoder_assign_crtc - Link the encoder to the crtc it's assigned to
+ * @encoder:	encoder pointer
+ * @crtc:	crtc pointer
+ */
+void dpu_encoder_assign_crtc(struct drm_encoder *encoder,
+			     struct drm_crtc *crtc);
+
+/**
+ * dpu_encoder_toggle_vblank_for_crtc - Toggles vblank interrupts on or off if
+ *	the encoder is assigned to the given crtc
+ * @encoder:	encoder pointer
+ * @crtc:	crtc pointer
+ * @enable:	true if vblank should be enabled
+ */
+void dpu_encoder_toggle_vblank_for_crtc(struct drm_encoder *encoder,
+					struct drm_crtc *crtc, bool enable);
+
+/**
+ * dpu_encoder_register_frame_event_callback - provide callback to encoder that
+ *	will be called after the request is complete, or other events.
+ * @encoder:	encoder pointer
+ * @cb:		callback pointer, provide NULL to deregister
+ * @data:	user data provided to callback
+ */
+void dpu_encoder_register_frame_event_callback(struct drm_encoder *encoder,
+		void (*cb)(void *, u32), void *data);
+
+/**
+ * dpu_encoder_prepare_for_kickoff - schedule double buffer flip of the ctl
+ *	path (i.e. ctl flush and start) at next appropriate time.
+ *	Immediately: if no previous commit is outstanding.
+ *	Delayed: Block until next trigger can be issued.
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_prepare_for_kickoff(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_trigger_kickoff_pending - Clear the flush bits from previous
+ *        kickoff and trigger the ctl prepare progress for command mode display.
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_kickoff - trigger a double buffer flip of the ctl path
+ *	(i.e. ctl flush and start) immediately.
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_kickoff(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_wakeup_time - get the time of the next vsync
+ */
+int dpu_encoder_vsync_time(struct drm_encoder *drm_enc, ktime_t *wakeup_time);
+
+/**
+ * dpu_encoder_wait_for_event - Waits for encoder events
+ * @encoder:	encoder pointer
+ * @event:      event to wait for
+ * MSM_ENC_COMMIT_DONE -  Wait for hardware to have flushed the current pending
+ *                        frames to hardware at a vblank or ctl_start
+ *                        Encoders will map this differently depending on the
+ *                        panel type.
+ *	                  vid mode -> vsync_irq
+ *                        cmd mode -> ctl_start
+ * MSM_ENC_TX_COMPLETE -  Wait for the hardware to transfer all the pixels to
+ *                        the panel. Encoders will map this differently
+ *                        depending on the panel type.
+ *                        vid mode -> vsync_irq
+ *                        cmd mode -> pp_done
+ * Returns: 0 on success, -EWOULDBLOCK if already signaled, error otherwise
+ */
+int dpu_encoder_wait_for_event(struct drm_encoder *drm_encoder,
+						enum msm_event_wait event);
+
+/*
+ * dpu_encoder_get_intf_mode - get interface mode of the given encoder
+ * @encoder: Pointer to drm encoder object
+ */
+enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_virt_runtime_resume - pm runtime resume the encoder configs
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_virt_runtime_resume(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_init - initialize virtual encoder object
+ * @dev:        Pointer to drm device structure
+ * @disp_info:  Pointer to display information structure
+ * Returns:     Pointer to newly created drm encoder
+ */
+struct drm_encoder *dpu_encoder_init(
+		struct drm_device *dev,
+		int drm_enc_mode);
+
+/**
+ * dpu_encoder_setup - setup dpu_encoder for the display probed
+ * @dev:		Pointer to drm device structure
+ * @enc:		Pointer to the drm_encoder
+ * @disp_info:	Pointer to the display info
+ */
+int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
+		struct msm_display_info *disp_info);
+
+/**
+ * dpu_encoder_prepare_commit - prepare encoder at the very beginning of an
+ *	atomic commit, before any registers are written
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ */
+void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc);
+
+/**
+ * dpu_encoder_set_idle_timeout - set the idle timeout for video
+ *                    and command mode encoders.
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ * @idle_timeout:    idle timeout duration in milliseconds
+ */
+void dpu_encoder_set_idle_timeout(struct drm_encoder *drm_enc,
+							u32 idle_timeout);
+/**
+ * dpu_encoder_get_linecount - get interface line count for the encoder.
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ */
+int dpu_encoder_get_linecount(struct drm_encoder *drm_enc);
+
+/**
+ * dpu_encoder_get_vsync_count - get vsync count for the encoder.
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ */
+int dpu_encoder_get_vsync_count(struct drm_encoder *drm_enc);
+
+bool dpu_encoder_is_widebus_enabled(const struct drm_encoder *drm_enc);
+
+/**
+ * dpu_encoder_get_crc_values_cnt - get number of physical encoders contained
+ *	in virtual encoder that can collect CRC values
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ * Returns:     Number of physical encoders for given drm encoder
+ */
+int dpu_encoder_get_crc_values_cnt(const struct drm_encoder *drm_enc);
+
+/**
+ * dpu_encoder_setup_misr - enable misr calculations
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ */
+void dpu_encoder_setup_misr(const struct drm_encoder *drm_encoder);
+
+/**
+ * dpu_encoder_get_crc - get the crc value from interface blocks
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ * Returns:     0 on success, error otherwise
+ */
+int dpu_encoder_get_crc(const struct drm_encoder *drm_enc, u32 *crcs, int pos);
+
+/**
+ * dpu_encoder_use_dsc_merge - returns true if the encoder uses DSC merge topology.
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ */
+bool dpu_encoder_use_dsc_merge(struct drm_encoder *drm_enc);
+
+/**
+ * dpu_encoder_prepare_wb_job - prepare writeback job for the encoder.
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ * @job:        Pointer to the current drm writeback job
+ */
+void dpu_encoder_prepare_wb_job(struct drm_encoder *drm_enc,
+		struct drm_writeback_job *job);
+
+/**
+ * dpu_encoder_cleanup_wb_job - cleanup writeback job for the encoder.
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ * @job:        Pointer to the current drm writeback job
+ */
+void dpu_encoder_cleanup_wb_job(struct drm_encoder *drm_enc,
+		struct drm_writeback_job *job);
+
+/**
+ * dpu_encoder_is_valid_for_commit - check if encode has valid parameters for commit.
+ * @drm_enc:    Pointer to drm encoder structure
+ */
+bool dpu_encoder_is_valid_for_commit(struct drm_encoder *drm_enc);
+
+#endif /* __DPU_ENCODER_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
new file mode 100644
index 000000000..f2af07d87
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
@@ -0,0 +1,403 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __DPU_ENCODER_PHYS_H__
+#define __DPU_ENCODER_PHYS_H__
+
+#include <drm/drm_writeback.h>
+#include <linux/jiffies.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_intf.h"
+#include "dpu_hw_wb.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_top.h"
+#include "dpu_encoder.h"
+#include "dpu_crtc.h"
+
+#define DPU_ENCODER_NAME_MAX	16
+
+/* wait for at most 2 vsync for lowest refresh rate (24hz) */
+#define KICKOFF_TIMEOUT_MS		84
+#define KICKOFF_TIMEOUT_JIFFIES		msecs_to_jiffies(KICKOFF_TIMEOUT_MS)
+
+/**
+ * enum dpu_enc_split_role - Role this physical encoder will play in a
+ *	split-panel configuration, where one panel is master, and others slaves.
+ *	Masters have extra responsibilities, like managing the VBLANK IRQ.
+ * @ENC_ROLE_SOLO:	This is the one and only panel. This encoder is master.
+ * @ENC_ROLE_MASTER:	This encoder is the master of a split panel config.
+ * @ENC_ROLE_SLAVE:	This encoder is not the master of a split panel config.
+ */
+enum dpu_enc_split_role {
+	ENC_ROLE_SOLO,
+	ENC_ROLE_MASTER,
+	ENC_ROLE_SLAVE,
+};
+
+/**
+ * enum dpu_enc_enable_state - current enabled state of the physical encoder
+ * @DPU_ENC_DISABLING:	Encoder transitioning to disable state
+ *			Events bounding transition are encoder type specific
+ * @DPU_ENC_DISABLED:	Encoder is disabled
+ * @DPU_ENC_ENABLING:	Encoder transitioning to enabled
+ *			Events bounding transition are encoder type specific
+ * @DPU_ENC_ENABLED:	Encoder is enabled
+ * @DPU_ENC_ERR_NEEDS_HW_RESET:	Encoder is enabled, but requires a hw_reset
+ *				to recover from a previous error
+ */
+enum dpu_enc_enable_state {
+	DPU_ENC_DISABLING,
+	DPU_ENC_DISABLED,
+	DPU_ENC_ENABLING,
+	DPU_ENC_ENABLED,
+	DPU_ENC_ERR_NEEDS_HW_RESET
+};
+
+struct dpu_encoder_phys;
+
+/**
+ * struct dpu_encoder_virt_ops - Interface the containing virtual encoder
+ *	provides for the physical encoders to use to callback.
+ * @handle_vblank_virt:	Notify virtual encoder of vblank IRQ reception
+ *			Note: This is called from IRQ handler context.
+ * @handle_underrun_virt: Notify virtual encoder of underrun IRQ reception
+ *			Note: This is called from IRQ handler context.
+ * @handle_frame_done:	Notify virtual encoder that this phys encoder
+ *			completes last request frame.
+ */
+struct dpu_encoder_virt_ops {
+	void (*handle_vblank_virt)(struct drm_encoder *,
+			struct dpu_encoder_phys *phys);
+	void (*handle_underrun_virt)(struct drm_encoder *,
+			struct dpu_encoder_phys *phys);
+	void (*handle_frame_done)(struct drm_encoder *,
+			struct dpu_encoder_phys *phys, u32 event);
+};
+
+/**
+ * struct dpu_encoder_phys_ops - Interface the physical encoders provide to
+ *	the containing virtual encoder.
+ * @late_register:		DRM Call. Add Userspace interfaces, debugfs.
+ * @prepare_commit:		MSM Atomic Call, start of atomic commit sequence
+ * @is_master:			Whether this phys_enc is the current master
+ *				encoder. Can be switched at enable time. Based
+ *				on split_role and current mode (CMD/VID).
+ * @atomic_mode_set:		DRM Call. Set a DRM mode.
+ *				This likely caches the mode, for use at enable.
+ * @enable:			DRM Call. Enable a DRM mode.
+ * @disable:			DRM Call. Disable mode.
+ * @atomic_check:		DRM Call. Atomic check new DRM state.
+ * @destroy:			DRM Call. Destroy and release resources.
+ * @control_vblank_irq		Register/Deregister for VBLANK IRQ
+ * @wait_for_commit_done:	Wait for hardware to have flushed the
+ *				current pending frames to hardware
+ * @wait_for_tx_complete:	Wait for hardware to transfer the pixels
+ *				to the panel
+ * @wait_for_vblank:		Wait for VBLANK, for sub-driver internal use
+ * @prepare_for_kickoff:	Do any work necessary prior to a kickoff
+ *				For CMD encoder, may wait for previous tx done
+ * @handle_post_kickoff:	Do any work necessary post-kickoff work
+ * @trigger_start:		Process start event on physical encoder
+ * @needs_single_flush:		Whether encoder slaves need to be flushed
+ * @irq_control:		Handler to enable/disable all the encoder IRQs
+ * @prepare_idle_pc:		phys encoder can update the vsync_enable status
+ *                              on idle power collapse prepare
+ * @restore:			Restore all the encoder configs.
+ * @get_line_count:		Obtain current vertical line count
+ */
+
+struct dpu_encoder_phys_ops {
+	int (*late_register)(struct dpu_encoder_phys *encoder,
+			struct dentry *debugfs_root);
+	void (*prepare_commit)(struct dpu_encoder_phys *encoder);
+	bool (*is_master)(struct dpu_encoder_phys *encoder);
+	void (*atomic_mode_set)(struct dpu_encoder_phys *encoder,
+			struct drm_crtc_state *crtc_state,
+			struct drm_connector_state *conn_state);
+	void (*enable)(struct dpu_encoder_phys *encoder);
+	void (*disable)(struct dpu_encoder_phys *encoder);
+	int (*atomic_check)(struct dpu_encoder_phys *encoder,
+			    struct drm_crtc_state *crtc_state,
+			    struct drm_connector_state *conn_state);
+	void (*destroy)(struct dpu_encoder_phys *encoder);
+	int (*control_vblank_irq)(struct dpu_encoder_phys *enc, bool enable);
+	int (*wait_for_commit_done)(struct dpu_encoder_phys *phys_enc);
+	int (*wait_for_tx_complete)(struct dpu_encoder_phys *phys_enc);
+	int (*wait_for_vblank)(struct dpu_encoder_phys *phys_enc);
+	void (*prepare_for_kickoff)(struct dpu_encoder_phys *phys_enc);
+	void (*handle_post_kickoff)(struct dpu_encoder_phys *phys_enc);
+	void (*trigger_start)(struct dpu_encoder_phys *phys_enc);
+	bool (*needs_single_flush)(struct dpu_encoder_phys *phys_enc);
+	void (*irq_control)(struct dpu_encoder_phys *phys, bool enable);
+	void (*prepare_idle_pc)(struct dpu_encoder_phys *phys_enc);
+	void (*restore)(struct dpu_encoder_phys *phys);
+	int (*get_line_count)(struct dpu_encoder_phys *phys);
+	int (*get_frame_count)(struct dpu_encoder_phys *phys);
+	void (*prepare_wb_job)(struct dpu_encoder_phys *phys_enc,
+			struct drm_writeback_job *job);
+	void (*cleanup_wb_job)(struct dpu_encoder_phys *phys_enc,
+			struct drm_writeback_job *job);
+	bool (*is_valid_for_commit)(struct dpu_encoder_phys *phys_enc);
+};
+
+/**
+ * enum dpu_intr_idx - dpu encoder interrupt index
+ * @INTR_IDX_VSYNC:    Vsync interrupt for video mode panel
+ * @INTR_IDX_PINGPONG: Pingpong done unterrupt for cmd mode panel
+ * @INTR_IDX_UNDERRUN: Underrun unterrupt for video and cmd mode panel
+ * @INTR_IDX_RDPTR:    Readpointer done unterrupt for cmd mode panel
+ * @INTR_IDX_WB_DONE:  Writeback fone interrupt for virtual connector
+ */
+enum dpu_intr_idx {
+	INTR_IDX_VSYNC,
+	INTR_IDX_PINGPONG,
+	INTR_IDX_UNDERRUN,
+	INTR_IDX_CTL_START,
+	INTR_IDX_RDPTR,
+	INTR_IDX_WB_DONE,
+	INTR_IDX_MAX,
+};
+
+/**
+ * struct dpu_encoder_phys - physical encoder that drives a single INTF block
+ *	tied to a specific panel / sub-panel. Abstract type, sub-classed by
+ *	phys_vid or phys_cmd for video mode or command mode encs respectively.
+ * @parent:		Pointer to the containing virtual encoder
+ * @ops:		Operations exposed to the virtual encoder
+ * @parent_ops:		Callbacks exposed by the parent to the phys_enc
+ * @hw_mdptop:		Hardware interface to the top registers
+ * @hw_ctl:		Hardware interface to the ctl registers
+ * @hw_pp:		Hardware interface to the ping pong registers
+ * @hw_intf:		Hardware interface to the intf registers
+ * @hw_wb:		Hardware interface to the wb registers
+ * @dpu_kms:		Pointer to the dpu_kms top level
+ * @cached_mode:	DRM mode cached at mode_set time, acted on in enable
+ * @enabled:		Whether the encoder has enabled and running a mode
+ * @split_role:		Role to play in a split-panel configuration
+ * @intf_mode:		Interface mode
+ * @intf_idx:		Interface index on dpu hardware
+ * @wb_idx:			Writeback index on dpu hardware
+ * @enc_spinlock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ * @enable_state:	Enable state tracking
+ * @vblank_refcount:	Reference count of vblank request
+ * @vsync_cnt:		Vsync count for the physical encoder
+ * @underrun_cnt:	Underrun count for the physical encoder
+ * @pending_kickoff_cnt:	Atomic counter tracking the number of kickoffs
+ *				vs. the number of done/vblank irqs. Should hover
+ *				between 0-2 Incremented when a new kickoff is
+ *				scheduled. Decremented in irq handler
+ * @pending_ctlstart_cnt:	Atomic counter tracking the number of ctl start
+ *                              pending.
+ * @pending_kickoff_wq:		Wait queue for blocking until kickoff completes
+ * @irq:			IRQ indices
+ */
+struct dpu_encoder_phys {
+	struct drm_encoder *parent;
+	struct dpu_encoder_phys_ops ops;
+	const struct dpu_encoder_virt_ops *parent_ops;
+	struct dpu_hw_mdp *hw_mdptop;
+	struct dpu_hw_ctl *hw_ctl;
+	struct dpu_hw_pingpong *hw_pp;
+	struct dpu_hw_intf *hw_intf;
+	struct dpu_hw_wb *hw_wb;
+	struct dpu_kms *dpu_kms;
+	struct drm_display_mode cached_mode;
+	enum dpu_enc_split_role split_role;
+	enum dpu_intf_mode intf_mode;
+	enum dpu_intf intf_idx;
+	enum dpu_wb wb_idx;
+	spinlock_t *enc_spinlock;
+	enum dpu_enc_enable_state enable_state;
+	atomic_t vblank_refcount;
+	atomic_t vsync_cnt;
+	atomic_t underrun_cnt;
+	atomic_t pending_ctlstart_cnt;
+	atomic_t pending_kickoff_cnt;
+	wait_queue_head_t pending_kickoff_wq;
+	int irq[INTR_IDX_MAX];
+};
+
+static inline int dpu_encoder_phys_inc_pending(struct dpu_encoder_phys *phys)
+{
+	atomic_inc_return(&phys->pending_ctlstart_cnt);
+	return atomic_inc_return(&phys->pending_kickoff_cnt);
+}
+
+/**
+ * struct dpu_encoder_phys_wb - sub-class of dpu_encoder_phys to handle command
+ *	mode specific operations
+ * @base:	Baseclass physical encoder structure
+ * @wbirq_refcount:     Reference count of writeback interrupt
+ * @wb_done_timeout_cnt: number of wb done irq timeout errors
+ * @wb_cfg:  writeback block config to store fb related details
+ * @wb_conn: backpointer to writeback connector
+ * @wb_job: backpointer to current writeback job
+ * @dest:   dpu buffer layout for current writeback output buffer
+ */
+struct dpu_encoder_phys_wb {
+	struct dpu_encoder_phys base;
+	atomic_t wbirq_refcount;
+	int wb_done_timeout_cnt;
+	struct dpu_hw_wb_cfg wb_cfg;
+	struct drm_writeback_connector *wb_conn;
+	struct drm_writeback_job *wb_job;
+	struct dpu_hw_fmt_layout dest;
+};
+
+/**
+ * struct dpu_encoder_phys_cmd - sub-class of dpu_encoder_phys to handle command
+ *	mode specific operations
+ * @base:	Baseclass physical encoder structure
+ * @intf_idx:	Intf Block index used by this phys encoder
+ * @stream_sel:	Stream selection for multi-stream interfaces
+ * @serialize_wait4pp:	serialize wait4pp feature waits for pp_done interrupt
+ *			after ctl_start instead of before next frame kickoff
+ * @pp_timeout_report_cnt: number of pingpong done irq timeout errors
+ * @pending_vblank_cnt: Atomic counter tracking pending wait for VBLANK
+ * @pending_vblank_wq: Wait queue for blocking until VBLANK received
+ */
+struct dpu_encoder_phys_cmd {
+	struct dpu_encoder_phys base;
+	int stream_sel;
+	bool serialize_wait4pp;
+	int pp_timeout_report_cnt;
+	atomic_t pending_vblank_cnt;
+	wait_queue_head_t pending_vblank_wq;
+};
+
+/**
+ * struct dpu_enc_phys_init_params - initialization parameters for phys encs
+ * @dpu_kms:		Pointer to the dpu_kms top level
+ * @parent:		Pointer to the containing virtual encoder
+ * @parent_ops:		Callbacks exposed by the parent to the phys_enc
+ * @split_role:		Role to play in a split-panel configuration
+ * @intf_idx:		Interface index this phys_enc will control
+ * @wb_idx:			Writeback index this phys_enc will control
+ * @enc_spinlock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ */
+struct dpu_enc_phys_init_params {
+	struct dpu_kms *dpu_kms;
+	struct drm_encoder *parent;
+	const struct dpu_encoder_virt_ops *parent_ops;
+	enum dpu_enc_split_role split_role;
+	enum dpu_intf intf_idx;
+	enum dpu_wb wb_idx;
+	spinlock_t *enc_spinlock;
+};
+
+/**
+ * dpu_encoder_wait_info - container for passing arguments to irq wait functions
+ * @wq: wait queue structure
+ * @atomic_cnt: wait until atomic_cnt equals zero
+ * @timeout_ms: timeout value in milliseconds
+ */
+struct dpu_encoder_wait_info {
+	wait_queue_head_t *wq;
+	atomic_t *atomic_cnt;
+	s64 timeout_ms;
+};
+
+/**
+ * dpu_encoder_phys_vid_init - Construct a new video mode physical encoder
+ * @p:	Pointer to init params structure
+ * Return: Error code or newly allocated encoder
+ */
+struct dpu_encoder_phys *dpu_encoder_phys_vid_init(
+		struct dpu_enc_phys_init_params *p);
+
+/**
+ * dpu_encoder_phys_cmd_init - Construct a new command mode physical encoder
+ * @p:	Pointer to init params structure
+ * Return: Error code or newly allocated encoder
+ */
+struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
+		struct dpu_enc_phys_init_params *p);
+
+/**
+ * dpu_encoder_phys_wb_init - initialize writeback encoder
+ * @init:	Pointer to init info structure with initialization params
+ */
+struct dpu_encoder_phys *dpu_encoder_phys_wb_init(
+		struct dpu_enc_phys_init_params *p);
+
+/**
+ * dpu_encoder_helper_trigger_start - control start helper function
+ *	This helper function may be optionally specified by physical
+ *	encoders if they require ctl_start triggering.
+ * @phys_enc: Pointer to physical encoder structure
+ */
+void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc);
+
+static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_crtc_state *dpu_cstate;
+
+	if (!phys_enc || phys_enc->enable_state == DPU_ENC_DISABLING)
+		return BLEND_3D_NONE;
+
+	dpu_cstate = to_dpu_crtc_state(phys_enc->parent->crtc->state);
+
+	/* Use merge_3d unless DSC MERGE topology is used */
+	if (phys_enc->split_role == ENC_ROLE_SOLO &&
+	    dpu_cstate->num_mixers == CRTC_DUAL_MIXERS &&
+	    !dpu_encoder_use_dsc_merge(phys_enc->parent))
+		return BLEND_3D_H_ROW_INT;
+
+	return BLEND_3D_NONE;
+}
+
+/**
+ * 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.
+ * @phys_enc: Pointer to physical encoder structure
+ */
+unsigned int dpu_encoder_helper_get_dsc(struct dpu_encoder_phys *phys_enc);
+
+/**
+ * dpu_encoder_helper_split_config - split display configuration helper function
+ *	This helper function may be used by physical encoders to configure
+ *	the split display related registers.
+ * @phys_enc: Pointer to physical encoder structure
+ * @interface: enum dpu_intf setting
+ */
+void dpu_encoder_helper_split_config(
+		struct dpu_encoder_phys *phys_enc,
+		enum dpu_intf interface);
+
+/**
+ * dpu_encoder_helper_report_irq_timeout - utility to report error that irq has
+ *	timed out, including reporting frame error event to crtc and debug dump
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: Failing interrupt index
+ */
+void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx);
+
+/**
+ * dpu_encoder_helper_wait_for_irq - utility to wait on an irq.
+ *	note: will call dpu_encoder_helper_wait_for_irq on timeout
+ * @phys_enc: Pointer to physical encoder structure
+ * @irq: IRQ index
+ * @func: IRQ callback to be called in case of timeout
+ * @wait_info: wait info struct
+ * @Return: 0 or -ERROR
+ */
+int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
+		int irq,
+		void (*func)(void *arg, int irq_idx),
+		struct dpu_encoder_wait_info *wait_info);
+
+/**
+ * dpu_encoder_helper_phys_cleanup - helper to cleanup dpu pipeline
+ * @phys_enc: Pointer to physical encoder structure
+ */
+void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc);
+
+#endif /* __dpu_encoder_phys_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
new file mode 100644
index 000000000..ae28b2b93
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -0,0 +1,803 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2015-2018, 2020-2021 The Linux Foundation. All rights reserved.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/delay.h>
+#include "dpu_encoder_phys.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_core_irq.h"
+#include "dpu_formats.h"
+#include "dpu_trace.h"
+#include "disp/msm_disp_snapshot.h"
+
+#define DPU_DEBUG_CMDENC(e, fmt, ...) DPU_DEBUG("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) ? (e)->base.intf_idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_CMDENC(e, fmt, ...) DPU_ERROR("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) ? (e)->base.intf_idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define to_dpu_encoder_phys_cmd(x) \
+	container_of(x, struct dpu_encoder_phys_cmd, base)
+
+#define PP_TIMEOUT_MAX_TRIALS	10
+
+/*
+ * Tearcheck sync start and continue thresholds are empirically found
+ * based on common panels In the future, may want to allow panels to override
+ * these default values
+ */
+#define DEFAULT_TEARCHECK_SYNC_THRESH_START	4
+#define DEFAULT_TEARCHECK_SYNC_THRESH_CONTINUE	4
+
+#define DPU_ENC_WR_PTR_START_TIMEOUT_US 20000
+
+#define DPU_ENC_MAX_POLL_TIMEOUT_US	2000
+
+static bool dpu_encoder_phys_cmd_is_master(struct dpu_encoder_phys *phys_enc)
+{
+	return (phys_enc->split_role != ENC_ROLE_SLAVE);
+}
+
+static void _dpu_encoder_phys_cmd_update_intf_cfg(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_hw_ctl *ctl;
+	struct dpu_hw_intf_cfg intf_cfg = { 0 };
+
+	ctl = phys_enc->hw_ctl;
+	if (!ctl->ops.setup_intf_cfg)
+		return;
+
+	intf_cfg.intf = phys_enc->intf_idx;
+	intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_CMD;
+	intf_cfg.stream_sel = cmd_enc->stream_sel;
+	intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
+	ctl->ops.setup_intf_cfg(ctl, &intf_cfg);
+
+	/* setup which pp blk will connect to this intf */
+	if (test_bit(DPU_CTL_ACTIVE_CFG, &ctl->caps->features) && phys_enc->hw_intf->ops.bind_pingpong_blk)
+		phys_enc->hw_intf->ops.bind_pingpong_blk(
+				phys_enc->hw_intf,
+				true,
+				phys_enc->hw_pp->idx);
+}
+
+static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	unsigned long lock_flags;
+	int new_cnt;
+	u32 event = DPU_ENCODER_FRAME_EVENT_DONE;
+
+	if (!phys_enc->hw_pp)
+		return;
+
+	DPU_ATRACE_BEGIN("pp_done_irq");
+	/* notify all synchronous clients first, then asynchronous clients */
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(phys_enc->parent,
+				phys_enc, event);
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	new_cnt = atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	trace_dpu_enc_phys_cmd_pp_tx_done(DRMID(phys_enc->parent),
+					  phys_enc->hw_pp->idx - PINGPONG_0,
+					  new_cnt, event);
+
+	/* Signal any waiting atomic commit thread */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+	DPU_ATRACE_END("pp_done_irq");
+}
+
+static void dpu_encoder_phys_cmd_pp_rd_ptr_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc->hw_pp)
+		return;
+
+	DPU_ATRACE_BEGIN("rd_ptr_irq");
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (phys_enc->parent_ops->handle_vblank_virt)
+		phys_enc->parent_ops->handle_vblank_virt(phys_enc->parent,
+			phys_enc);
+
+	atomic_add_unless(&cmd_enc->pending_vblank_cnt, -1, 0);
+	wake_up_all(&cmd_enc->pending_vblank_wq);
+	DPU_ATRACE_END("rd_ptr_irq");
+}
+
+static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+
+	DPU_ATRACE_BEGIN("ctl_start_irq");
+
+	atomic_add_unless(&phys_enc->pending_ctlstart_cnt, -1, 0);
+
+	/* Signal any waiting ctl start interrupt */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+	DPU_ATRACE_END("ctl_start_irq");
+}
+
+static void dpu_encoder_phys_cmd_underrun_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+
+	if (phys_enc->parent_ops->handle_underrun_virt)
+		phys_enc->parent_ops->handle_underrun_virt(phys_enc->parent,
+			phys_enc);
+}
+
+static void dpu_encoder_phys_cmd_atomic_mode_set(
+		struct dpu_encoder_phys *phys_enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state)
+{
+	phys_enc->irq[INTR_IDX_CTL_START] = phys_enc->hw_ctl->caps->intr_start;
+
+	phys_enc->irq[INTR_IDX_PINGPONG] = phys_enc->hw_pp->caps->intr_done;
+
+	phys_enc->irq[INTR_IDX_RDPTR] = phys_enc->hw_pp->caps->intr_rdptr;
+
+	phys_enc->irq[INTR_IDX_UNDERRUN] = phys_enc->hw_intf->cap->intr_underrun;
+}
+
+static int _dpu_encoder_phys_cmd_handle_ppdone_timeout(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	u32 frame_event = DPU_ENCODER_FRAME_EVENT_ERROR;
+	bool do_log = false;
+	struct drm_encoder *drm_enc;
+
+	if (!phys_enc->hw_pp)
+		return -EINVAL;
+
+	drm_enc = phys_enc->parent;
+
+	cmd_enc->pp_timeout_report_cnt++;
+	if (cmd_enc->pp_timeout_report_cnt == PP_TIMEOUT_MAX_TRIALS) {
+		frame_event |= DPU_ENCODER_FRAME_EVENT_PANEL_DEAD;
+		do_log = true;
+	} else if (cmd_enc->pp_timeout_report_cnt == 1) {
+		do_log = true;
+	}
+
+	trace_dpu_enc_phys_cmd_pdone_timeout(DRMID(drm_enc),
+		     phys_enc->hw_pp->idx - PINGPONG_0,
+		     cmd_enc->pp_timeout_report_cnt,
+		     atomic_read(&phys_enc->pending_kickoff_cnt),
+		     frame_event);
+
+	/* to avoid flooding, only log first time, and "dead" time */
+	if (do_log) {
+		DRM_ERROR("id:%d pp:%d kickoff timeout %d cnt %d koff_cnt %d\n",
+			  DRMID(drm_enc),
+			  phys_enc->hw_pp->idx - PINGPONG_0,
+			  phys_enc->hw_ctl->idx - CTL_0,
+			  cmd_enc->pp_timeout_report_cnt,
+			  atomic_read(&phys_enc->pending_kickoff_cnt));
+		msm_disp_snapshot_state(drm_enc->dev);
+		dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+				phys_enc->irq[INTR_IDX_RDPTR]);
+	}
+
+	atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0);
+
+	/* request a ctl reset before the next kickoff */
+	phys_enc->enable_state = DPU_ENC_ERR_NEEDS_HW_RESET;
+
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(
+				drm_enc, phys_enc, frame_event);
+
+	return -ETIMEDOUT;
+}
+
+static int _dpu_encoder_phys_cmd_wait_for_idle(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_encoder_wait_info wait_info;
+	int ret;
+
+	wait_info.wq = &phys_enc->pending_kickoff_wq;
+	wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt;
+	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
+
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc,
+			phys_enc->irq[INTR_IDX_PINGPONG],
+			dpu_encoder_phys_cmd_pp_tx_done_irq,
+			&wait_info);
+	if (ret == -ETIMEDOUT)
+		_dpu_encoder_phys_cmd_handle_ppdone_timeout(phys_enc);
+	else if (!ret)
+		cmd_enc->pp_timeout_report_cnt = 0;
+
+	return ret;
+}
+
+static int dpu_encoder_phys_cmd_control_vblank_irq(
+		struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	int ret = 0;
+	int refcount;
+
+	if (!phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+
+	refcount = atomic_read(&phys_enc->vblank_refcount);
+
+	/* Slave encoders don't report vblank */
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		goto end;
+
+	/* protect against negative */
+	if (!enable && refcount == 0) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	DRM_DEBUG_KMS("id:%u pp:%d enable=%s/%d\n", DRMID(phys_enc->parent),
+		      phys_enc->hw_pp->idx - PINGPONG_0,
+		      enable ? "true" : "false", refcount);
+
+	if (enable && atomic_inc_return(&phys_enc->vblank_refcount) == 1)
+		ret = dpu_core_irq_register_callback(phys_enc->dpu_kms,
+				phys_enc->irq[INTR_IDX_RDPTR],
+				dpu_encoder_phys_cmd_pp_rd_ptr_irq,
+				phys_enc);
+	else if (!enable && atomic_dec_return(&phys_enc->vblank_refcount) == 0)
+		ret = dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+				phys_enc->irq[INTR_IDX_RDPTR]);
+
+end:
+	if (ret) {
+		DRM_ERROR("vblank irq err id:%u pp:%d ret:%d, enable %s/%d\n",
+			  DRMID(phys_enc->parent),
+			  phys_enc->hw_pp->idx - PINGPONG_0, ret,
+			  enable ? "true" : "false", refcount);
+	}
+
+	return ret;
+}
+
+static void dpu_encoder_phys_cmd_irq_control(struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	trace_dpu_enc_phys_cmd_irq_ctrl(DRMID(phys_enc->parent),
+			phys_enc->hw_pp->idx - PINGPONG_0,
+			enable, atomic_read(&phys_enc->vblank_refcount));
+
+	if (enable) {
+		dpu_core_irq_register_callback(phys_enc->dpu_kms,
+				phys_enc->irq[INTR_IDX_PINGPONG],
+				dpu_encoder_phys_cmd_pp_tx_done_irq,
+				phys_enc);
+		dpu_core_irq_register_callback(phys_enc->dpu_kms,
+				phys_enc->irq[INTR_IDX_UNDERRUN],
+				dpu_encoder_phys_cmd_underrun_irq,
+				phys_enc);
+		dpu_encoder_phys_cmd_control_vblank_irq(phys_enc, true);
+
+		if (dpu_encoder_phys_cmd_is_master(phys_enc))
+			dpu_core_irq_register_callback(phys_enc->dpu_kms,
+					phys_enc->irq[INTR_IDX_CTL_START],
+					dpu_encoder_phys_cmd_ctl_start_irq,
+					phys_enc);
+	} else {
+		if (dpu_encoder_phys_cmd_is_master(phys_enc))
+			dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+					phys_enc->irq[INTR_IDX_CTL_START]);
+
+		dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+				phys_enc->irq[INTR_IDX_UNDERRUN]);
+		dpu_encoder_phys_cmd_control_vblank_irq(phys_enc, false);
+		dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+				phys_enc->irq[INTR_IDX_PINGPONG]);
+	}
+}
+
+static void dpu_encoder_phys_cmd_tearcheck_config(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_hw_tear_check tc_cfg = { 0 };
+	struct drm_display_mode *mode;
+	bool tc_enable = true;
+	u32 vsync_hz;
+	struct dpu_kms *dpu_kms;
+
+	if (!phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	mode = &phys_enc->cached_mode;
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp %d\n", phys_enc->hw_pp->idx - PINGPONG_0);
+
+	if (!phys_enc->hw_pp->ops.setup_tearcheck ||
+		!phys_enc->hw_pp->ops.enable_tearcheck) {
+		DPU_DEBUG_CMDENC(cmd_enc, "tearcheck not supported\n");
+		return;
+	}
+
+	dpu_kms = phys_enc->dpu_kms;
+
+	/*
+	 * TE default: dsi byte clock calculated base on 70 fps;
+	 * around 14 ms to complete a kickoff cycle if te disabled;
+	 * vclk_line base on 60 fps; write is faster than read;
+	 * init == start == rdptr;
+	 *
+	 * vsync_count is ratio of MDP VSYNC clock frequency to LCD panel
+	 * frequency divided by the no. of rows (lines) in the LCDpanel.
+	 */
+	vsync_hz = dpu_kms_get_clk_rate(dpu_kms, "vsync");
+	if (vsync_hz <= 0) {
+		DPU_DEBUG_CMDENC(cmd_enc, "invalid - vsync_hz %u\n",
+				 vsync_hz);
+		return;
+	}
+
+	tc_cfg.vsync_count = vsync_hz /
+				(mode->vtotal * drm_mode_vrefresh(mode));
+
+	/*
+	 * Set the sync_cfg_height to twice vtotal so that if we lose a
+	 * TE event coming from the display TE pin we won't stall immediately
+	 */
+	tc_cfg.hw_vsync_mode = 1;
+	tc_cfg.sync_cfg_height = mode->vtotal * 2;
+	tc_cfg.vsync_init_val = mode->vdisplay;
+	tc_cfg.sync_threshold_start = DEFAULT_TEARCHECK_SYNC_THRESH_START;
+	tc_cfg.sync_threshold_continue = DEFAULT_TEARCHECK_SYNC_THRESH_CONTINUE;
+	tc_cfg.start_pos = mode->vdisplay;
+	tc_cfg.rd_ptr_irq = mode->vdisplay + 1;
+
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d vsync_clk_speed_hz %u vtotal %u vrefresh %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, vsync_hz,
+		mode->vtotal, drm_mode_vrefresh(mode));
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d enable %u start_pos %u rd_ptr_irq %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, tc_enable, tc_cfg.start_pos,
+		tc_cfg.rd_ptr_irq);
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d hw_vsync_mode %u vsync_count %u vsync_init_val %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, tc_cfg.hw_vsync_mode,
+		tc_cfg.vsync_count, tc_cfg.vsync_init_val);
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d cfgheight %u thresh_start %u thresh_cont %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, tc_cfg.sync_cfg_height,
+		tc_cfg.sync_threshold_start, tc_cfg.sync_threshold_continue);
+
+	phys_enc->hw_pp->ops.setup_tearcheck(phys_enc->hw_pp, &tc_cfg);
+	phys_enc->hw_pp->ops.enable_tearcheck(phys_enc->hw_pp, tc_enable);
+}
+
+static void _dpu_encoder_phys_cmd_pingpong_config(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc->hw_pp || !phys_enc->hw_ctl->ops.setup_intf_cfg) {
+		DPU_ERROR("invalid arg(s), enc %d\n", phys_enc != NULL);
+		return;
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp %d, enabling mode:\n",
+			phys_enc->hw_pp->idx - PINGPONG_0);
+	drm_mode_debug_printmodeline(&phys_enc->cached_mode);
+
+	_dpu_encoder_phys_cmd_update_intf_cfg(phys_enc);
+	dpu_encoder_phys_cmd_tearcheck_config(phys_enc);
+}
+
+static bool dpu_encoder_phys_cmd_needs_single_flush(
+		struct dpu_encoder_phys *phys_enc)
+{
+	/**
+	 * we do separate flush for each CTL and let
+	 * CTL_START synchronize them
+	 */
+	return false;
+}
+
+static void dpu_encoder_phys_cmd_enable_helper(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_ctl *ctl;
+
+	if (!phys_enc->hw_pp) {
+		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != NULL);
+		return;
+	}
+
+	dpu_encoder_helper_split_config(phys_enc, phys_enc->intf_idx);
+
+	_dpu_encoder_phys_cmd_pingpong_config(phys_enc);
+
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return;
+
+	ctl = phys_enc->hw_ctl;
+	ctl->ops.update_pending_flush_intf(ctl, phys_enc->intf_idx);
+}
+
+static void dpu_encoder_phys_cmd_enable(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc->hw_pp) {
+		DPU_ERROR("invalid phys encoder\n");
+		return;
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp %d\n", phys_enc->hw_pp->idx - PINGPONG_0);
+
+	if (phys_enc->enable_state == DPU_ENC_ENABLED) {
+		DPU_ERROR("already enabled\n");
+		return;
+	}
+
+	dpu_encoder_phys_cmd_enable_helper(phys_enc);
+	phys_enc->enable_state = DPU_ENC_ENABLED;
+}
+
+static void _dpu_encoder_phys_cmd_connect_te(
+		struct dpu_encoder_phys *phys_enc, bool enable)
+{
+	if (!phys_enc->hw_pp || !phys_enc->hw_pp->ops.connect_external_te)
+		return;
+
+	trace_dpu_enc_phys_cmd_connect_te(DRMID(phys_enc->parent), enable);
+	phys_enc->hw_pp->ops.connect_external_te(phys_enc->hw_pp, enable);
+}
+
+static void dpu_encoder_phys_cmd_prepare_idle_pc(
+		struct dpu_encoder_phys *phys_enc)
+{
+	_dpu_encoder_phys_cmd_connect_te(phys_enc, false);
+}
+
+static int dpu_encoder_phys_cmd_get_line_count(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_pingpong *hw_pp;
+
+	if (!phys_enc->hw_pp)
+		return -EINVAL;
+
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return -EINVAL;
+
+	hw_pp = phys_enc->hw_pp;
+	if (!hw_pp->ops.get_line_count)
+		return -EINVAL;
+
+	return hw_pp->ops.get_line_count(hw_pp);
+}
+
+static void dpu_encoder_phys_cmd_disable(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_hw_ctl *ctl;
+
+	if (!phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	DRM_DEBUG_KMS("id:%u pp:%d state:%d\n", DRMID(phys_enc->parent),
+		      phys_enc->hw_pp->idx - PINGPONG_0,
+		      phys_enc->enable_state);
+
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DPU_ERROR_CMDENC(cmd_enc, "already disabled\n");
+		return;
+	}
+
+	if (phys_enc->hw_pp->ops.enable_tearcheck)
+		phys_enc->hw_pp->ops.enable_tearcheck(phys_enc->hw_pp, false);
+
+	if (phys_enc->hw_intf->ops.bind_pingpong_blk) {
+		phys_enc->hw_intf->ops.bind_pingpong_blk(
+				phys_enc->hw_intf,
+				false,
+				phys_enc->hw_pp->idx);
+
+		ctl = phys_enc->hw_ctl;
+		ctl->ops.update_pending_flush_intf(ctl, phys_enc->intf_idx);
+	}
+
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+}
+
+static void dpu_encoder_phys_cmd_destroy(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	kfree(cmd_enc);
+}
+
+static void dpu_encoder_phys_cmd_prepare_for_kickoff(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	int ret;
+
+	if (!phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	DRM_DEBUG_KMS("id:%u pp:%d pending_cnt:%d\n", DRMID(phys_enc->parent),
+		      phys_enc->hw_pp->idx - PINGPONG_0,
+		      atomic_read(&phys_enc->pending_kickoff_cnt));
+
+	/*
+	 * Mark kickoff request as outstanding. If there are more than one,
+	 * outstanding, then we have to wait for the previous one to complete
+	 */
+	ret = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc);
+	if (ret) {
+		/* force pending_kickoff_cnt 0 to discard failed kickoff */
+		atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+		DRM_ERROR("failed wait_for_idle: id:%u ret:%d pp:%d\n",
+			  DRMID(phys_enc->parent), ret,
+			  phys_enc->hw_pp->idx - PINGPONG_0);
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp:%d pending_cnt %d\n",
+			phys_enc->hw_pp->idx - PINGPONG_0,
+			atomic_read(&phys_enc->pending_kickoff_cnt));
+}
+
+static bool dpu_encoder_phys_cmd_is_ongoing_pptx(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_pp_vsync_info info;
+
+	if (!phys_enc)
+		return false;
+
+	phys_enc->hw_pp->ops.get_vsync_info(phys_enc->hw_pp, &info);
+	if (info.wr_ptr_line_count > 0 &&
+	    info.wr_ptr_line_count < phys_enc->cached_mode.vdisplay)
+		return true;
+
+	return false;
+}
+
+static void dpu_encoder_phys_cmd_prepare_commit(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+	int trial = 0;
+
+	if (!phys_enc)
+		return;
+	if (!phys_enc->hw_pp)
+		return;
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return;
+
+	/* If autorefresh is already disabled, we have nothing to do */
+	if (!phys_enc->hw_pp->ops.get_autorefresh(phys_enc->hw_pp, NULL))
+		return;
+
+	/*
+	 * If autorefresh is enabled, disable it and make sure it is safe to
+	 * proceed with current frame commit/push. Sequence fallowed is,
+	 * 1. Disable TE
+	 * 2. Disable autorefresh config
+	 * 4. Poll for frame transfer ongoing to be false
+	 * 5. Enable TE back
+	 */
+	_dpu_encoder_phys_cmd_connect_te(phys_enc, false);
+	phys_enc->hw_pp->ops.setup_autorefresh(phys_enc->hw_pp, 0, false);
+
+	do {
+		udelay(DPU_ENC_MAX_POLL_TIMEOUT_US);
+		if ((trial * DPU_ENC_MAX_POLL_TIMEOUT_US)
+				> (KICKOFF_TIMEOUT_MS * USEC_PER_MSEC)) {
+			DPU_ERROR_CMDENC(cmd_enc,
+					"disable autorefresh failed\n");
+			break;
+		}
+
+		trial++;
+	} while (dpu_encoder_phys_cmd_is_ongoing_pptx(phys_enc));
+
+	_dpu_encoder_phys_cmd_connect_te(phys_enc, true);
+
+	DPU_DEBUG_CMDENC(to_dpu_encoder_phys_cmd(phys_enc),
+			 "disabled autorefresh\n");
+}
+
+static int _dpu_encoder_phys_cmd_wait_for_ctl_start(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_encoder_wait_info wait_info;
+	int ret;
+
+	wait_info.wq = &phys_enc->pending_kickoff_wq;
+	wait_info.atomic_cnt = &phys_enc->pending_ctlstart_cnt;
+	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
+
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc,
+			phys_enc->irq[INTR_IDX_CTL_START],
+			dpu_encoder_phys_cmd_ctl_start_irq,
+			&wait_info);
+	if (ret == -ETIMEDOUT) {
+		DPU_ERROR_CMDENC(cmd_enc, "ctl start interrupt wait failed\n");
+		ret = -EINVAL;
+	} else if (!ret)
+		ret = 0;
+
+	return ret;
+}
+
+static int dpu_encoder_phys_cmd_wait_for_tx_complete(
+		struct dpu_encoder_phys *phys_enc)
+{
+	int rc;
+
+	rc = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc);
+	if (rc) {
+		DRM_ERROR("failed wait_for_idle: id:%u ret:%d intf:%d\n",
+			  DRMID(phys_enc->parent), rc,
+			  phys_enc->intf_idx - INTF_0);
+	}
+
+	return rc;
+}
+
+static int dpu_encoder_phys_cmd_wait_for_commit_done(
+		struct dpu_encoder_phys *phys_enc)
+{
+	/* only required for master controller */
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return 0;
+
+	if (phys_enc->hw_ctl->ops.is_started(phys_enc->hw_ctl))
+		return dpu_encoder_phys_cmd_wait_for_tx_complete(phys_enc);
+
+	return _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc);
+}
+
+static int dpu_encoder_phys_cmd_wait_for_vblank(
+		struct dpu_encoder_phys *phys_enc)
+{
+	int rc = 0;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+	struct dpu_encoder_wait_info wait_info;
+
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	/* only required for master controller */
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return rc;
+
+	wait_info.wq = &cmd_enc->pending_vblank_wq;
+	wait_info.atomic_cnt = &cmd_enc->pending_vblank_cnt;
+	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
+
+	atomic_inc(&cmd_enc->pending_vblank_cnt);
+
+	rc = dpu_encoder_helper_wait_for_irq(phys_enc,
+			phys_enc->irq[INTR_IDX_RDPTR],
+			dpu_encoder_phys_cmd_pp_rd_ptr_irq,
+			&wait_info);
+
+	return rc;
+}
+
+static void dpu_encoder_phys_cmd_handle_post_kickoff(
+		struct dpu_encoder_phys *phys_enc)
+{
+	/**
+	 * re-enable external TE, either for the first time after enabling
+	 * or if disabled for Autorefresh
+	 */
+	_dpu_encoder_phys_cmd_connect_te(phys_enc, true);
+}
+
+static void dpu_encoder_phys_cmd_trigger_start(
+		struct dpu_encoder_phys *phys_enc)
+{
+	dpu_encoder_helper_trigger_start(phys_enc);
+}
+
+static void dpu_encoder_phys_cmd_init_ops(
+		struct dpu_encoder_phys_ops *ops)
+{
+	ops->prepare_commit = dpu_encoder_phys_cmd_prepare_commit;
+	ops->is_master = dpu_encoder_phys_cmd_is_master;
+	ops->atomic_mode_set = dpu_encoder_phys_cmd_atomic_mode_set;
+	ops->enable = dpu_encoder_phys_cmd_enable;
+	ops->disable = dpu_encoder_phys_cmd_disable;
+	ops->destroy = dpu_encoder_phys_cmd_destroy;
+	ops->control_vblank_irq = dpu_encoder_phys_cmd_control_vblank_irq;
+	ops->wait_for_commit_done = dpu_encoder_phys_cmd_wait_for_commit_done;
+	ops->prepare_for_kickoff = dpu_encoder_phys_cmd_prepare_for_kickoff;
+	ops->wait_for_tx_complete = dpu_encoder_phys_cmd_wait_for_tx_complete;
+	ops->wait_for_vblank = dpu_encoder_phys_cmd_wait_for_vblank;
+	ops->trigger_start = dpu_encoder_phys_cmd_trigger_start;
+	ops->needs_single_flush = dpu_encoder_phys_cmd_needs_single_flush;
+	ops->irq_control = dpu_encoder_phys_cmd_irq_control;
+	ops->restore = dpu_encoder_phys_cmd_enable_helper;
+	ops->prepare_idle_pc = dpu_encoder_phys_cmd_prepare_idle_pc;
+	ops->handle_post_kickoff = dpu_encoder_phys_cmd_handle_post_kickoff;
+	ops->get_line_count = dpu_encoder_phys_cmd_get_line_count;
+}
+
+struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
+		struct dpu_enc_phys_init_params *p)
+{
+	struct dpu_encoder_phys *phys_enc = NULL;
+	struct dpu_encoder_phys_cmd *cmd_enc = NULL;
+	int i, ret = 0;
+
+	DPU_DEBUG("intf %d\n", p->intf_idx - INTF_0);
+
+	cmd_enc = kzalloc(sizeof(*cmd_enc), GFP_KERNEL);
+	if (!cmd_enc) {
+		ret = -ENOMEM;
+		DPU_ERROR("failed to allocate\n");
+		return ERR_PTR(ret);
+	}
+	phys_enc = &cmd_enc->base;
+	phys_enc->hw_mdptop = p->dpu_kms->hw_mdp;
+	phys_enc->intf_idx = p->intf_idx;
+
+	dpu_encoder_phys_cmd_init_ops(&phys_enc->ops);
+	phys_enc->parent = p->parent;
+	phys_enc->parent_ops = p->parent_ops;
+	phys_enc->dpu_kms = p->dpu_kms;
+	phys_enc->split_role = p->split_role;
+	phys_enc->intf_mode = INTF_MODE_CMD;
+	phys_enc->enc_spinlock = p->enc_spinlock;
+	cmd_enc->stream_sel = 0;
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+	for (i = 0; i < ARRAY_SIZE(phys_enc->irq); i++)
+		phys_enc->irq[i] = -EINVAL;
+
+	atomic_set(&phys_enc->vblank_refcount, 0);
+	atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+	atomic_set(&phys_enc->pending_ctlstart_cnt, 0);
+	atomic_set(&cmd_enc->pending_vblank_cnt, 0);
+	init_waitqueue_head(&phys_enc->pending_kickoff_wq);
+	init_waitqueue_head(&cmd_enc->pending_vblank_wq);
+
+	DPU_DEBUG_CMDENC(cmd_enc, "created\n");
+
+	return phys_enc;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
new file mode 100644
index 000000000..2c1464666
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -0,0 +1,716 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015-2018, 2020-2021 The Linux Foundation. All rights reserved.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include "dpu_encoder_phys.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_hw_merge3d.h"
+#include "dpu_core_irq.h"
+#include "dpu_formats.h"
+#include "dpu_trace.h"
+#include "disp/msm_disp_snapshot.h"
+
+#define DPU_DEBUG_VIDENC(e, fmt, ...) DPU_DEBUG("enc%d intf%d " fmt, \
+		(e) && (e)->parent ? \
+		(e)->parent->base.id : -1, \
+		(e) && (e)->hw_intf ? \
+		(e)->hw_intf->idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_VIDENC(e, fmt, ...) DPU_ERROR("enc%d intf%d " fmt, \
+		(e) && (e)->parent ? \
+		(e)->parent->base.id : -1, \
+		(e) && (e)->hw_intf ? \
+		(e)->hw_intf->idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define to_dpu_encoder_phys_vid(x) \
+	container_of(x, struct dpu_encoder_phys_vid, base)
+
+static bool dpu_encoder_phys_vid_is_master(
+		struct dpu_encoder_phys *phys_enc)
+{
+	bool ret = false;
+
+	if (phys_enc->split_role != ENC_ROLE_SLAVE)
+		ret = true;
+
+	return ret;
+}
+
+static void drm_mode_to_intf_timing_params(
+		const struct dpu_encoder_phys *phys_enc,
+		const struct drm_display_mode *mode,
+		struct intf_timing_params *timing)
+{
+	memset(timing, 0, sizeof(*timing));
+
+	if ((mode->htotal < mode->hsync_end)
+			|| (mode->hsync_start < mode->hdisplay)
+			|| (mode->vtotal < mode->vsync_end)
+			|| (mode->vsync_start < mode->vdisplay)
+			|| (mode->hsync_end < mode->hsync_start)
+			|| (mode->vsync_end < mode->vsync_start)) {
+		DPU_ERROR(
+		    "invalid params - hstart:%d,hend:%d,htot:%d,hdisplay:%d\n",
+				mode->hsync_start, mode->hsync_end,
+				mode->htotal, mode->hdisplay);
+		DPU_ERROR("vstart:%d,vend:%d,vtot:%d,vdisplay:%d\n",
+				mode->vsync_start, mode->vsync_end,
+				mode->vtotal, mode->vdisplay);
+		return;
+	}
+
+	/*
+	 * https://www.kernel.org/doc/htmldocs/drm/ch02s05.html
+	 *  Active Region      Front Porch   Sync   Back Porch
+	 * <-----------------><------------><-----><----------->
+	 * <- [hv]display --->
+	 * <--------- [hv]sync_start ------>
+	 * <----------------- [hv]sync_end ------->
+	 * <---------------------------- [hv]total ------------->
+	 */
+	timing->width = mode->hdisplay;	/* active width */
+	timing->height = mode->vdisplay;	/* active height */
+	timing->xres = timing->width;
+	timing->yres = timing->height;
+	timing->h_back_porch = mode->htotal - mode->hsync_end;
+	timing->h_front_porch = mode->hsync_start - mode->hdisplay;
+	timing->v_back_porch = mode->vtotal - mode->vsync_end;
+	timing->v_front_porch = mode->vsync_start - mode->vdisplay;
+	timing->hsync_pulse_width = mode->hsync_end - mode->hsync_start;
+	timing->vsync_pulse_width = mode->vsync_end - mode->vsync_start;
+	timing->hsync_polarity = (mode->flags & DRM_MODE_FLAG_NHSYNC) ? 1 : 0;
+	timing->vsync_polarity = (mode->flags & DRM_MODE_FLAG_NVSYNC) ? 1 : 0;
+	timing->border_clr = 0;
+	timing->underflow_clr = 0xff;
+	timing->hsync_skew = mode->hskew;
+
+	/* DSI controller cannot handle active-low sync signals. */
+	if (phys_enc->hw_intf->cap->type == INTF_DSI) {
+		timing->hsync_polarity = 0;
+		timing->vsync_polarity = 0;
+	}
+
+	/* for DP/EDP, Shift timings to align it to bottom right */
+	if (phys_enc->hw_intf->cap->type == INTF_DP) {
+		timing->h_back_porch += timing->h_front_porch;
+		timing->h_front_porch = 0;
+		timing->v_back_porch += timing->v_front_porch;
+		timing->v_front_porch = 0;
+	}
+
+	timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent);
+
+	/*
+	 * for DP, divide the horizonal parameters by 2 when
+	 * widebus is enabled
+	 */
+	if (phys_enc->hw_intf->cap->type == INTF_DP && timing->wide_bus_en) {
+		timing->width = timing->width >> 1;
+		timing->xres = timing->xres >> 1;
+		timing->h_back_porch = timing->h_back_porch >> 1;
+		timing->h_front_porch = timing->h_front_porch >> 1;
+		timing->hsync_pulse_width = timing->hsync_pulse_width >> 1;
+	}
+}
+
+static u32 get_horizontal_total(const struct intf_timing_params *timing)
+{
+	u32 active = timing->xres;
+	u32 inactive =
+	    timing->h_back_porch + timing->h_front_porch +
+	    timing->hsync_pulse_width;
+	return active + inactive;
+}
+
+static u32 get_vertical_total(const struct intf_timing_params *timing)
+{
+	u32 active = timing->yres;
+	u32 inactive =
+	    timing->v_back_porch + timing->v_front_porch +
+	    timing->vsync_pulse_width;
+	return active + inactive;
+}
+
+/*
+ * programmable_fetch_get_num_lines:
+ *	Number of fetch lines in vertical front porch
+ * @timing: Pointer to the intf timing information for the requested mode
+ *
+ * Returns the number of fetch lines in vertical front porch at which mdp
+ * can start fetching the next frame.
+ *
+ * Number of needed prefetch lines is anything that cannot be absorbed in the
+ * start of frame time (back porch + vsync pulse width).
+ *
+ * Some panels have very large VFP, however we only need a total number of
+ * lines based on the chip worst case latencies.
+ */
+static u32 programmable_fetch_get_num_lines(
+		struct dpu_encoder_phys *phys_enc,
+		const struct intf_timing_params *timing)
+{
+	u32 worst_case_needed_lines =
+	    phys_enc->hw_intf->cap->prog_fetch_lines_worst_case;
+	u32 start_of_frame_lines =
+	    timing->v_back_porch + timing->vsync_pulse_width;
+	u32 needed_vfp_lines = worst_case_needed_lines - start_of_frame_lines;
+	u32 actual_vfp_lines = 0;
+
+	/* Fetch must be outside active lines, otherwise undefined. */
+	if (start_of_frame_lines >= worst_case_needed_lines) {
+		DPU_DEBUG_VIDENC(phys_enc,
+				"prog fetch is not needed, large vbp+vsw\n");
+		actual_vfp_lines = 0;
+	} else if (timing->v_front_porch < needed_vfp_lines) {
+		/* Warn fetch needed, but not enough porch in panel config */
+		pr_warn_once
+			("low vbp+vfp may lead to perf issues in some cases\n");
+		DPU_DEBUG_VIDENC(phys_enc,
+				"less vfp than fetch req, using entire vfp\n");
+		actual_vfp_lines = timing->v_front_porch;
+	} else {
+		DPU_DEBUG_VIDENC(phys_enc, "room in vfp for needed prefetch\n");
+		actual_vfp_lines = needed_vfp_lines;
+	}
+
+	DPU_DEBUG_VIDENC(phys_enc,
+		"v_front_porch %u v_back_porch %u vsync_pulse_width %u\n",
+		timing->v_front_porch, timing->v_back_porch,
+		timing->vsync_pulse_width);
+	DPU_DEBUG_VIDENC(phys_enc,
+		"wc_lines %u needed_vfp_lines %u actual_vfp_lines %u\n",
+		worst_case_needed_lines, needed_vfp_lines, actual_vfp_lines);
+
+	return actual_vfp_lines;
+}
+
+/*
+ * programmable_fetch_config: Programs HW to prefetch lines by offsetting
+ *	the start of fetch into the vertical front porch for cases where the
+ *	vsync pulse width and vertical back porch time is insufficient
+ *
+ *	Gets # of lines to pre-fetch, then calculate VSYNC counter value.
+ *	HW layer requires VSYNC counter of first pixel of tgt VFP line.
+ *
+ * @timing: Pointer to the intf timing information for the requested mode
+ */
+static void programmable_fetch_config(struct dpu_encoder_phys *phys_enc,
+				      const struct intf_timing_params *timing)
+{
+	struct intf_prog_fetch f = { 0 };
+	u32 vfp_fetch_lines = 0;
+	u32 horiz_total = 0;
+	u32 vert_total = 0;
+	u32 vfp_fetch_start_vsync_counter = 0;
+	unsigned long lock_flags;
+
+	if (WARN_ON_ONCE(!phys_enc->hw_intf->ops.setup_prg_fetch))
+		return;
+
+	vfp_fetch_lines = programmable_fetch_get_num_lines(phys_enc, timing);
+	if (vfp_fetch_lines) {
+		vert_total = get_vertical_total(timing);
+		horiz_total = get_horizontal_total(timing);
+		vfp_fetch_start_vsync_counter =
+		    (vert_total - vfp_fetch_lines) * horiz_total + 1;
+		f.enable = 1;
+		f.fetch_start = vfp_fetch_start_vsync_counter;
+	}
+
+	DPU_DEBUG_VIDENC(phys_enc,
+		"vfp_fetch_lines %u vfp_fetch_start_vsync_counter %u\n",
+		vfp_fetch_lines, vfp_fetch_start_vsync_counter);
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	phys_enc->hw_intf->ops.setup_prg_fetch(phys_enc->hw_intf, &f);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+}
+
+static void dpu_encoder_phys_vid_setup_timing_engine(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct drm_display_mode mode;
+	struct intf_timing_params timing_params = { 0 };
+	const struct dpu_format *fmt = NULL;
+	u32 fmt_fourcc = DRM_FORMAT_RGB888;
+	unsigned long lock_flags;
+	struct dpu_hw_intf_cfg intf_cfg = { 0 };
+
+	if (!phys_enc->hw_ctl->ops.setup_intf_cfg) {
+		DPU_ERROR("invalid encoder %d\n", phys_enc != NULL);
+		return;
+	}
+
+	mode = phys_enc->cached_mode;
+	if (!phys_enc->hw_intf->ops.setup_timing_gen) {
+		DPU_ERROR("timing engine setup is not supported\n");
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(phys_enc, "enabling mode:\n");
+	drm_mode_debug_printmodeline(&mode);
+
+	if (phys_enc->split_role != ENC_ROLE_SOLO) {
+		mode.hdisplay >>= 1;
+		mode.htotal >>= 1;
+		mode.hsync_start >>= 1;
+		mode.hsync_end >>= 1;
+
+		DPU_DEBUG_VIDENC(phys_enc,
+			"split_role %d, halve horizontal %d %d %d %d\n",
+			phys_enc->split_role,
+			mode.hdisplay, mode.htotal,
+			mode.hsync_start, mode.hsync_end);
+	}
+
+	drm_mode_to_intf_timing_params(phys_enc, &mode, &timing_params);
+
+	fmt = dpu_get_dpu_format(fmt_fourcc);
+	DPU_DEBUG_VIDENC(phys_enc, "fmt_fourcc 0x%X\n", fmt_fourcc);
+
+	intf_cfg.intf = phys_enc->hw_intf->idx;
+	intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_VID;
+	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);
+	if (phys_enc->hw_pp->merge_3d)
+		intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	phys_enc->hw_intf->ops.setup_timing_gen(phys_enc->hw_intf,
+			&timing_params, fmt);
+	phys_enc->hw_ctl->ops.setup_intf_cfg(phys_enc->hw_ctl, &intf_cfg);
+
+	/* setup which pp blk will connect to this intf */
+	if (phys_enc->hw_intf->ops.bind_pingpong_blk)
+		phys_enc->hw_intf->ops.bind_pingpong_blk(
+				phys_enc->hw_intf,
+				true,
+				phys_enc->hw_pp->idx);
+
+	if (phys_enc->hw_pp->merge_3d)
+		phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d, intf_cfg.mode_3d);
+
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	programmable_fetch_config(phys_enc, &timing_params);
+}
+
+static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	struct dpu_hw_ctl *hw_ctl;
+	unsigned long lock_flags;
+	u32 flush_register = 0;
+
+	hw_ctl = phys_enc->hw_ctl;
+
+	DPU_ATRACE_BEGIN("vblank_irq");
+
+	if (phys_enc->parent_ops->handle_vblank_virt)
+		phys_enc->parent_ops->handle_vblank_virt(phys_enc->parent,
+				phys_enc);
+
+	atomic_read(&phys_enc->pending_kickoff_cnt);
+
+	/*
+	 * only decrement the pending flush count if we've actually flushed
+	 * hardware. due to sw irq latency, vblank may have already happened
+	 * so we need to double-check with hw that it accepted the flush bits
+	 */
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	if (hw_ctl->ops.get_flush_register)
+		flush_register = hw_ctl->ops.get_flush_register(hw_ctl);
+
+	if (!(flush_register & hw_ctl->ops.get_pending_flush(hw_ctl)))
+		atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	/* Signal any waiting atomic commit thread */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+
+	phys_enc->parent_ops->handle_frame_done(phys_enc->parent, phys_enc,
+			DPU_ENCODER_FRAME_EVENT_DONE);
+
+	DPU_ATRACE_END("vblank_irq");
+}
+
+static void dpu_encoder_phys_vid_underrun_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+
+	if (phys_enc->parent_ops->handle_underrun_virt)
+		phys_enc->parent_ops->handle_underrun_virt(phys_enc->parent,
+			phys_enc);
+}
+
+static bool dpu_encoder_phys_vid_needs_single_flush(
+		struct dpu_encoder_phys *phys_enc)
+{
+	return phys_enc->split_role != ENC_ROLE_SOLO;
+}
+
+static void dpu_encoder_phys_vid_atomic_mode_set(
+		struct dpu_encoder_phys *phys_enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state)
+{
+	phys_enc->irq[INTR_IDX_VSYNC] = phys_enc->hw_intf->cap->intr_vsync;
+
+	phys_enc->irq[INTR_IDX_UNDERRUN] = phys_enc->hw_intf->cap->intr_underrun;
+}
+
+static int dpu_encoder_phys_vid_control_vblank_irq(
+		struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	int ret = 0;
+	int refcount;
+
+	refcount = atomic_read(&phys_enc->vblank_refcount);
+
+	/* Slave encoders don't report vblank */
+	if (!dpu_encoder_phys_vid_is_master(phys_enc))
+		goto end;
+
+	/* protect against negative */
+	if (!enable && refcount == 0) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	DRM_DEBUG_VBL("id:%u enable=%d/%d\n", DRMID(phys_enc->parent), enable,
+		      atomic_read(&phys_enc->vblank_refcount));
+
+	if (enable && atomic_inc_return(&phys_enc->vblank_refcount) == 1)
+		ret = dpu_core_irq_register_callback(phys_enc->dpu_kms,
+				phys_enc->irq[INTR_IDX_VSYNC],
+				dpu_encoder_phys_vid_vblank_irq,
+				phys_enc);
+	else if (!enable && atomic_dec_return(&phys_enc->vblank_refcount) == 0)
+		ret = dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+				phys_enc->irq[INTR_IDX_VSYNC]);
+
+end:
+	if (ret) {
+		DRM_ERROR("failed: id:%u intf:%d ret:%d enable:%d refcnt:%d\n",
+			  DRMID(phys_enc->parent),
+			  phys_enc->hw_intf->idx - INTF_0, ret, enable,
+			  refcount);
+	}
+	return ret;
+}
+
+static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_ctl *ctl;
+
+	ctl = phys_enc->hw_ctl;
+
+	DPU_DEBUG_VIDENC(phys_enc, "\n");
+
+	if (WARN_ON(!phys_enc->hw_intf->ops.enable_timing))
+		return;
+
+	dpu_encoder_helper_split_config(phys_enc, phys_enc->hw_intf->idx);
+
+	dpu_encoder_phys_vid_setup_timing_engine(phys_enc);
+
+	/*
+	 * For single flush cases (dual-ctl or pp-split), skip setting the
+	 * flush bit for the slave intf, since both intfs use same ctl
+	 * and HW will only flush the master.
+	 */
+	if (dpu_encoder_phys_vid_needs_single_flush(phys_enc) &&
+		!dpu_encoder_phys_vid_is_master(phys_enc))
+		goto skip_flush;
+
+	ctl->ops.update_pending_flush_intf(ctl, phys_enc->hw_intf->idx);
+	if (ctl->ops.update_pending_flush_merge_3d && phys_enc->hw_pp->merge_3d)
+		ctl->ops.update_pending_flush_merge_3d(ctl, phys_enc->hw_pp->merge_3d->idx);
+
+skip_flush:
+	DPU_DEBUG_VIDENC(phys_enc,
+		"update pending flush ctl %d intf %d\n",
+		ctl->idx - CTL_0, phys_enc->hw_intf->idx);
+
+	atomic_set(&phys_enc->underrun_cnt, 0);
+
+	/* ctl_flush & timing engine enable will be triggered by framework */
+	if (phys_enc->enable_state == DPU_ENC_DISABLED)
+		phys_enc->enable_state = DPU_ENC_ENABLING;
+}
+
+static void dpu_encoder_phys_vid_destroy(struct dpu_encoder_phys *phys_enc)
+{
+	DPU_DEBUG_VIDENC(phys_enc, "\n");
+	kfree(phys_enc);
+}
+
+static int dpu_encoder_phys_vid_wait_for_vblank(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_wait_info wait_info;
+	int ret;
+
+	wait_info.wq = &phys_enc->pending_kickoff_wq;
+	wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt;
+	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
+
+	if (!dpu_encoder_phys_vid_is_master(phys_enc)) {
+		return 0;
+	}
+
+	/* Wait for kickoff to complete */
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc,
+			phys_enc->irq[INTR_IDX_VSYNC],
+			dpu_encoder_phys_vid_vblank_irq,
+			&wait_info);
+
+	if (ret == -ETIMEDOUT) {
+		dpu_encoder_helper_report_irq_timeout(phys_enc, INTR_IDX_VSYNC);
+	}
+
+	return ret;
+}
+
+static int dpu_encoder_phys_vid_wait_for_commit_done(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_ctl *hw_ctl = phys_enc->hw_ctl;
+	int ret;
+
+	if (!hw_ctl)
+		return 0;
+
+	ret = wait_event_timeout(phys_enc->pending_kickoff_wq,
+		(hw_ctl->ops.get_flush_register(hw_ctl) == 0),
+		msecs_to_jiffies(50));
+	if (ret <= 0) {
+		DPU_ERROR("vblank timeout\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static void dpu_encoder_phys_vid_prepare_for_kickoff(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_ctl *ctl;
+	int rc;
+	struct drm_encoder *drm_enc;
+
+	drm_enc = phys_enc->parent;
+
+	ctl = phys_enc->hw_ctl;
+	if (!ctl->ops.wait_reset_status)
+		return;
+
+	/*
+	 * hw supports hardware initiated ctl reset, so before we kickoff a new
+	 * frame, need to check and wait for hw initiated ctl reset completion
+	 */
+	rc = ctl->ops.wait_reset_status(ctl);
+	if (rc) {
+		DPU_ERROR_VIDENC(phys_enc, "ctl %d reset failure: %d\n",
+				ctl->idx, rc);
+		msm_disp_snapshot_state(drm_enc->dev);
+		dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+				phys_enc->irq[INTR_IDX_VSYNC]);
+	}
+}
+
+static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc)
+{
+	unsigned long lock_flags;
+	int ret;
+
+	if (!phys_enc->parent || !phys_enc->parent->dev) {
+		DPU_ERROR("invalid encoder/device\n");
+		return;
+	}
+
+	if (!phys_enc->hw_intf) {
+		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
+				phys_enc->hw_intf != NULL, phys_enc->hw_ctl != NULL);
+		return;
+	}
+
+	if (WARN_ON(!phys_enc->hw_intf->ops.enable_timing))
+		return;
+
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DPU_ERROR("already disabled\n");
+		return;
+	}
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	phys_enc->hw_intf->ops.enable_timing(phys_enc->hw_intf, 0);
+	if (dpu_encoder_phys_vid_is_master(phys_enc))
+		dpu_encoder_phys_inc_pending(phys_enc);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	/*
+	 * Wait for a vsync so we know the ENABLE=0 latched before
+	 * the (connector) source of the vsync's gets disabled,
+	 * otherwise we end up in a funny state if we re-enable
+	 * before the disable latches, which results that some of
+	 * the settings changes for the new modeset (like new
+	 * scanout buffer) don't latch properly..
+	 */
+	if (dpu_encoder_phys_vid_is_master(phys_enc)) {
+		ret = dpu_encoder_phys_vid_wait_for_vblank(phys_enc);
+		if (ret) {
+			atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+			DRM_ERROR("wait disable failed: id:%u intf:%d ret:%d\n",
+				  DRMID(phys_enc->parent),
+				  phys_enc->hw_intf->idx - INTF_0, ret);
+		}
+	}
+
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+}
+
+static void dpu_encoder_phys_vid_handle_post_kickoff(
+		struct dpu_encoder_phys *phys_enc)
+{
+	unsigned long lock_flags;
+
+	/*
+	 * Video mode must flush CTL before enabling timing engine
+	 * Video encoders need to turn on their interfaces now
+	 */
+	if (phys_enc->enable_state == DPU_ENC_ENABLING) {
+		trace_dpu_enc_phys_vid_post_kickoff(DRMID(phys_enc->parent),
+				    phys_enc->hw_intf->idx - INTF_0);
+		spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+		phys_enc->hw_intf->ops.enable_timing(phys_enc->hw_intf, 1);
+		spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+		phys_enc->enable_state = DPU_ENC_ENABLED;
+	}
+}
+
+static void dpu_encoder_phys_vid_irq_control(struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	int ret;
+
+	trace_dpu_enc_phys_vid_irq_ctrl(DRMID(phys_enc->parent),
+			    phys_enc->hw_intf->idx - INTF_0,
+			    enable,
+			    atomic_read(&phys_enc->vblank_refcount));
+
+	if (enable) {
+		ret = dpu_encoder_phys_vid_control_vblank_irq(phys_enc, true);
+		if (WARN_ON(ret))
+			return;
+
+		dpu_core_irq_register_callback(phys_enc->dpu_kms,
+				phys_enc->irq[INTR_IDX_UNDERRUN],
+				dpu_encoder_phys_vid_underrun_irq,
+				phys_enc);
+	} else {
+		dpu_encoder_phys_vid_control_vblank_irq(phys_enc, false);
+		dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+				phys_enc->irq[INTR_IDX_UNDERRUN]);
+	}
+}
+
+static int dpu_encoder_phys_vid_get_line_count(
+		struct dpu_encoder_phys *phys_enc)
+{
+	if (!dpu_encoder_phys_vid_is_master(phys_enc))
+		return -EINVAL;
+
+	if (!phys_enc->hw_intf || !phys_enc->hw_intf->ops.get_line_count)
+		return -EINVAL;
+
+	return phys_enc->hw_intf->ops.get_line_count(phys_enc->hw_intf);
+}
+
+static int dpu_encoder_phys_vid_get_frame_count(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct intf_status s = {0};
+	u32 fetch_start = 0;
+	struct drm_display_mode mode = phys_enc->cached_mode;
+
+	if (!dpu_encoder_phys_vid_is_master(phys_enc))
+		return -EINVAL;
+
+	if (!phys_enc->hw_intf || !phys_enc->hw_intf->ops.get_status)
+		return -EINVAL;
+
+	phys_enc->hw_intf->ops.get_status(phys_enc->hw_intf, &s);
+
+	if (s.is_prog_fetch_en && s.is_en) {
+		fetch_start = mode.vtotal - (mode.vsync_start - mode.vdisplay);
+		if ((s.line_count > fetch_start) &&
+			(s.line_count <= mode.vtotal))
+			return s.frame_count + 1;
+	}
+
+	return s.frame_count;
+}
+
+static void dpu_encoder_phys_vid_init_ops(struct dpu_encoder_phys_ops *ops)
+{
+	ops->is_master = dpu_encoder_phys_vid_is_master;
+	ops->atomic_mode_set = dpu_encoder_phys_vid_atomic_mode_set;
+	ops->enable = dpu_encoder_phys_vid_enable;
+	ops->disable = dpu_encoder_phys_vid_disable;
+	ops->destroy = dpu_encoder_phys_vid_destroy;
+	ops->control_vblank_irq = dpu_encoder_phys_vid_control_vblank_irq;
+	ops->wait_for_commit_done = dpu_encoder_phys_vid_wait_for_commit_done;
+	ops->wait_for_vblank = dpu_encoder_phys_vid_wait_for_vblank;
+	ops->wait_for_tx_complete = dpu_encoder_phys_vid_wait_for_vblank;
+	ops->irq_control = dpu_encoder_phys_vid_irq_control;
+	ops->prepare_for_kickoff = dpu_encoder_phys_vid_prepare_for_kickoff;
+	ops->handle_post_kickoff = dpu_encoder_phys_vid_handle_post_kickoff;
+	ops->needs_single_flush = dpu_encoder_phys_vid_needs_single_flush;
+	ops->get_line_count = dpu_encoder_phys_vid_get_line_count;
+	ops->get_frame_count = dpu_encoder_phys_vid_get_frame_count;
+}
+
+struct dpu_encoder_phys *dpu_encoder_phys_vid_init(
+		struct dpu_enc_phys_init_params *p)
+{
+	struct dpu_encoder_phys *phys_enc = NULL;
+	int i;
+
+	if (!p) {
+		DPU_ERROR("failed to create encoder due to invalid parameter\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	phys_enc = kzalloc(sizeof(*phys_enc), GFP_KERNEL);
+	if (!phys_enc) {
+		DPU_ERROR("failed to create encoder due to memory allocation error\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	phys_enc->hw_mdptop = p->dpu_kms->hw_mdp;
+	phys_enc->intf_idx = p->intf_idx;
+
+	DPU_DEBUG_VIDENC(phys_enc, "\n");
+
+	dpu_encoder_phys_vid_init_ops(&phys_enc->ops);
+	phys_enc->parent = p->parent;
+	phys_enc->parent_ops = p->parent_ops;
+	phys_enc->dpu_kms = p->dpu_kms;
+	phys_enc->split_role = p->split_role;
+	phys_enc->intf_mode = INTF_MODE_VIDEO;
+	phys_enc->enc_spinlock = p->enc_spinlock;
+	for (i = 0; i < ARRAY_SIZE(phys_enc->irq); i++)
+		phys_enc->irq[i] = -EINVAL;
+
+	atomic_set(&phys_enc->vblank_refcount, 0);
+	atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+	init_waitqueue_head(&phys_enc->pending_kickoff_wq);
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+
+	DPU_DEBUG_VIDENC(phys_enc, "created intf idx:%d\n", p->intf_idx);
+
+	return phys_enc;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
new file mode 100644
index 000000000..42c7e378d
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
@@ -0,0 +1,752 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+
+#include <drm/drm_framebuffer.h>
+
+#include "dpu_encoder_phys.h"
+#include "dpu_formats.h"
+#include "dpu_hw_top.h"
+#include "dpu_hw_wb.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_merge3d.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_core_irq.h"
+#include "dpu_vbif.h"
+#include "dpu_crtc.h"
+#include "disp/msm_disp_snapshot.h"
+
+#define to_dpu_encoder_phys_wb(x) \
+	container_of(x, struct dpu_encoder_phys_wb, base)
+
+/**
+ * dpu_encoder_phys_wb_is_master - report wb always as master encoder
+ */
+static bool dpu_encoder_phys_wb_is_master(struct dpu_encoder_phys *phys_enc)
+{
+	/* there is only one physical enc for dpu_writeback */
+	return true;
+}
+
+/**
+ * dpu_encoder_phys_wb_set_ot_limit - set OT limit for writeback interface
+ * @phys_enc:	Pointer to physical encoder
+ */
+static void dpu_encoder_phys_wb_set_ot_limit(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_wb *hw_wb = phys_enc->hw_wb;
+	struct dpu_vbif_set_ot_params ot_params;
+
+	memset(&ot_params, 0, sizeof(ot_params));
+	ot_params.xin_id = hw_wb->caps->xin_id;
+	ot_params.num = hw_wb->idx - WB_0;
+	ot_params.width = phys_enc->cached_mode.hdisplay;
+	ot_params.height = phys_enc->cached_mode.vdisplay;
+	ot_params.is_wfd = true;
+	ot_params.frame_rate = drm_mode_vrefresh(&phys_enc->cached_mode);
+	ot_params.vbif_idx = hw_wb->caps->vbif_idx;
+	ot_params.clk_ctrl = hw_wb->caps->clk_ctrl;
+	ot_params.rd = false;
+
+	dpu_vbif_set_ot_limit(phys_enc->dpu_kms, &ot_params);
+}
+
+/**
+ * dpu_encoder_phys_wb_set_qos_remap - set QoS remapper for writeback
+ * @phys_enc:	Pointer to physical encoder
+ */
+static void dpu_encoder_phys_wb_set_qos_remap(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_wb *hw_wb;
+	struct dpu_vbif_set_qos_params qos_params;
+
+	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->crtc) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+
+	if (!phys_enc->hw_wb || !phys_enc->hw_wb->caps) {
+		DPU_ERROR("invalid writeback hardware\n");
+		return;
+	}
+
+	hw_wb = phys_enc->hw_wb;
+
+	memset(&qos_params, 0, sizeof(qos_params));
+	qos_params.vbif_idx = hw_wb->caps->vbif_idx;
+	qos_params.xin_id = hw_wb->caps->xin_id;
+	qos_params.clk_ctrl = hw_wb->caps->clk_ctrl;
+	qos_params.num = hw_wb->idx - WB_0;
+	qos_params.is_rt = false;
+
+	DPU_DEBUG("[qos_remap] wb:%d vbif:%d xin:%d is_rt:%d\n",
+			qos_params.num,
+			qos_params.vbif_idx,
+			qos_params.xin_id, qos_params.is_rt);
+
+	dpu_vbif_set_qos_remap(phys_enc->dpu_kms, &qos_params);
+}
+
+/**
+ * dpu_encoder_phys_wb_set_qos - set QoS/danger/safe LUTs for writeback
+ * @phys_enc:	Pointer to physical encoder
+ */
+static void dpu_encoder_phys_wb_set_qos(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_wb *hw_wb;
+	struct dpu_hw_wb_qos_cfg qos_cfg;
+	const struct dpu_mdss_cfg *catalog;
+	const struct dpu_qos_lut_tbl *qos_lut_tb;
+
+	if (!phys_enc || !phys_enc->dpu_kms || !phys_enc->dpu_kms->catalog) {
+		DPU_ERROR("invalid parameter(s)\n");
+		return;
+	}
+
+	catalog = phys_enc->dpu_kms->catalog;
+
+	hw_wb = phys_enc->hw_wb;
+
+	memset(&qos_cfg, 0, sizeof(struct dpu_hw_wb_qos_cfg));
+	qos_cfg.danger_safe_en = true;
+	qos_cfg.danger_lut =
+		catalog->perf->danger_lut_tbl[DPU_QOS_LUT_USAGE_NRT];
+
+	qos_cfg.safe_lut = catalog->perf->safe_lut_tbl[DPU_QOS_LUT_USAGE_NRT];
+
+	qos_lut_tb = &catalog->perf->qos_lut_tbl[DPU_QOS_LUT_USAGE_NRT];
+	qos_cfg.creq_lut = _dpu_hw_get_qos_lut(qos_lut_tb, 0);
+
+	if (hw_wb->ops.setup_qos_lut)
+		hw_wb->ops.setup_qos_lut(hw_wb, &qos_cfg);
+}
+
+/**
+ * dpu_encoder_phys_wb_setup_fb - setup output framebuffer
+ * @phys_enc:	Pointer to physical encoder
+ * @fb:		Pointer to output framebuffer
+ */
+static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc,
+		struct drm_framebuffer *fb)
+{
+	struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc);
+	struct dpu_hw_wb *hw_wb;
+	struct dpu_hw_wb_cfg *wb_cfg;
+	struct dpu_hw_cdp_cfg cdp_cfg;
+
+	if (!phys_enc || !phys_enc->dpu_kms || !phys_enc->dpu_kms->catalog) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	hw_wb = phys_enc->hw_wb;
+	wb_cfg = &wb_enc->wb_cfg;
+
+	wb_cfg->intf_mode = phys_enc->intf_mode;
+	wb_cfg->roi.x1 = 0;
+	wb_cfg->roi.x2 = phys_enc->cached_mode.hdisplay;
+	wb_cfg->roi.y1 = 0;
+	wb_cfg->roi.y2 = phys_enc->cached_mode.vdisplay;
+
+	if (hw_wb->ops.setup_roi)
+		hw_wb->ops.setup_roi(hw_wb, wb_cfg);
+
+	if (hw_wb->ops.setup_outformat)
+		hw_wb->ops.setup_outformat(hw_wb, wb_cfg);
+
+	if (hw_wb->ops.setup_cdp) {
+		memset(&cdp_cfg, 0, sizeof(struct dpu_hw_cdp_cfg));
+
+		cdp_cfg.enable = phys_enc->dpu_kms->catalog->perf->cdp_cfg
+				[DPU_PERF_CDP_USAGE_NRT].wr_enable;
+		cdp_cfg.ubwc_meta_enable =
+				DPU_FORMAT_IS_UBWC(wb_cfg->dest.format);
+		cdp_cfg.tile_amortize_enable =
+				DPU_FORMAT_IS_UBWC(wb_cfg->dest.format) ||
+				DPU_FORMAT_IS_TILE(wb_cfg->dest.format);
+		cdp_cfg.preload_ahead = DPU_WB_CDP_PRELOAD_AHEAD_64;
+
+		hw_wb->ops.setup_cdp(hw_wb, &cdp_cfg);
+	}
+
+	if (hw_wb->ops.setup_outaddress)
+		hw_wb->ops.setup_outaddress(hw_wb, wb_cfg);
+}
+
+/**
+ * dpu_encoder_phys_wb_setup_cdp - setup chroma down prefetch block
+ * @phys_enc:Pointer to physical encoder
+ */
+static void dpu_encoder_phys_wb_setup_cdp(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_wb *hw_wb;
+	struct dpu_hw_ctl *ctl;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	hw_wb = phys_enc->hw_wb;
+	ctl = phys_enc->hw_ctl;
+
+	if (test_bit(DPU_CTL_ACTIVE_CFG, &ctl->caps->features) &&
+		(phys_enc->hw_ctl &&
+		 phys_enc->hw_ctl->ops.setup_intf_cfg)) {
+		struct dpu_hw_intf_cfg intf_cfg = {0};
+		struct dpu_hw_pingpong *hw_pp = phys_enc->hw_pp;
+		enum dpu_3d_blend_mode mode_3d;
+
+		mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
+
+		intf_cfg.intf = DPU_NONE;
+		intf_cfg.wb = hw_wb->idx;
+
+		if (mode_3d && hw_pp && hw_pp->merge_3d)
+			intf_cfg.merge_3d = hw_pp->merge_3d->idx;
+
+		if (phys_enc->hw_pp->merge_3d && phys_enc->hw_pp->merge_3d->ops.setup_3d_mode)
+			phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
+					mode_3d);
+
+		/* setup which pp blk will connect to this wb */
+		if (hw_pp && phys_enc->hw_wb->ops.bind_pingpong_blk)
+			phys_enc->hw_wb->ops.bind_pingpong_blk(phys_enc->hw_wb, true,
+					phys_enc->hw_pp->idx);
+
+		phys_enc->hw_ctl->ops.setup_intf_cfg(phys_enc->hw_ctl, &intf_cfg);
+	} else if (phys_enc->hw_ctl && phys_enc->hw_ctl->ops.setup_intf_cfg) {
+		struct dpu_hw_intf_cfg intf_cfg = {0};
+
+		intf_cfg.intf = DPU_NONE;
+		intf_cfg.wb = hw_wb->idx;
+		intf_cfg.mode_3d =
+			dpu_encoder_helper_get_3d_blend_mode(phys_enc);
+		phys_enc->hw_ctl->ops.setup_intf_cfg(phys_enc->hw_ctl, &intf_cfg);
+	}
+}
+
+/**
+ * dpu_encoder_phys_wb_atomic_check - verify and fixup given atomic states
+ * @phys_enc:	Pointer to physical encoder
+ * @crtc_state:	Pointer to CRTC atomic state
+ * @conn_state:	Pointer to connector atomic state
+ */
+static int dpu_encoder_phys_wb_atomic_check(
+		struct dpu_encoder_phys *phys_enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state)
+{
+	struct drm_framebuffer *fb;
+	const struct drm_display_mode *mode = &crtc_state->mode;
+
+	DPU_DEBUG("[atomic_check:%d, \"%s\",%d,%d]\n",
+			phys_enc->wb_idx, mode->name, mode->hdisplay, mode->vdisplay);
+
+	if (!conn_state || !conn_state->connector) {
+		DPU_ERROR("invalid connector state\n");
+		return -EINVAL;
+	} else if (conn_state->connector->status !=
+			connector_status_connected) {
+		DPU_ERROR("connector not connected %d\n",
+				conn_state->connector->status);
+		return -EINVAL;
+	}
+
+	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+		return 0;
+
+	fb = conn_state->writeback_job->fb;
+
+	DPU_DEBUG("[fb_id:%u][fb:%u,%u]\n", fb->base.id,
+			fb->width, fb->height);
+
+	if (fb->width != mode->hdisplay) {
+		DPU_ERROR("invalid fb w=%d, mode w=%d\n", fb->width,
+				mode->hdisplay);
+		return -EINVAL;
+	} else if (fb->height != mode->vdisplay) {
+		DPU_ERROR("invalid fb h=%d, mode h=%d\n", fb->height,
+				  mode->vdisplay);
+		return -EINVAL;
+	} else if (fb->width > phys_enc->hw_wb->caps->maxlinewidth) {
+		DPU_ERROR("invalid fb w=%d, maxlinewidth=%u\n",
+				  fb->width, phys_enc->hw_wb->caps->maxlinewidth);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+
+/**
+ * _dpu_encoder_phys_wb_update_flush - flush hardware update
+ * @phys_enc:	Pointer to physical encoder
+ */
+static void _dpu_encoder_phys_wb_update_flush(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_wb *hw_wb;
+	struct dpu_hw_ctl *hw_ctl;
+	struct dpu_hw_pingpong *hw_pp;
+	u32 pending_flush = 0;
+
+	if (!phys_enc)
+		return;
+
+	hw_wb = phys_enc->hw_wb;
+	hw_pp = phys_enc->hw_pp;
+	hw_ctl = phys_enc->hw_ctl;
+
+	DPU_DEBUG("[wb:%d]\n", hw_wb->idx - WB_0);
+
+	if (!hw_ctl) {
+		DPU_DEBUG("[wb:%d] no ctl assigned\n", hw_wb->idx - WB_0);
+		return;
+	}
+
+	if (hw_ctl->ops.update_pending_flush_wb)
+		hw_ctl->ops.update_pending_flush_wb(hw_ctl, hw_wb->idx);
+
+	if (hw_ctl->ops.update_pending_flush_merge_3d && hw_pp && hw_pp->merge_3d)
+		hw_ctl->ops.update_pending_flush_merge_3d(hw_ctl,
+				hw_pp->merge_3d->idx);
+
+	if (hw_ctl->ops.get_pending_flush)
+		pending_flush = hw_ctl->ops.get_pending_flush(hw_ctl);
+
+	DPU_DEBUG("Pending flush mask for CTL_%d is 0x%x, WB %d\n",
+			hw_ctl->idx - CTL_0, pending_flush,
+			hw_wb->idx - WB_0);
+}
+
+/**
+ * dpu_encoder_phys_wb_setup - setup writeback encoder
+ * @phys_enc:	Pointer to physical encoder
+ */
+static void dpu_encoder_phys_wb_setup(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_wb *hw_wb = phys_enc->hw_wb;
+	struct drm_display_mode mode = phys_enc->cached_mode;
+	struct drm_framebuffer *fb = NULL;
+
+	DPU_DEBUG("[mode_set:%d, \"%s\",%d,%d]\n",
+			hw_wb->idx - WB_0, mode.name,
+			mode.hdisplay, mode.vdisplay);
+
+	dpu_encoder_phys_wb_set_ot_limit(phys_enc);
+
+	dpu_encoder_phys_wb_set_qos_remap(phys_enc);
+
+	dpu_encoder_phys_wb_set_qos(phys_enc);
+
+	dpu_encoder_phys_wb_setup_fb(phys_enc, fb);
+
+	dpu_encoder_phys_wb_setup_cdp(phys_enc);
+
+}
+
+static void _dpu_encoder_phys_wb_frame_done_helper(void *arg)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc);
+
+	struct dpu_hw_wb *hw_wb = phys_enc->hw_wb;
+	unsigned long lock_flags;
+	u32 event = DPU_ENCODER_FRAME_EVENT_DONE;
+
+	DPU_DEBUG("[wb:%d]\n", hw_wb->idx - WB_0);
+
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(phys_enc->parent,
+				phys_enc, event);
+
+	if (phys_enc->parent_ops->handle_vblank_virt)
+		phys_enc->parent_ops->handle_vblank_virt(phys_enc->parent,
+				phys_enc);
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	if (wb_enc->wb_conn)
+		drm_writeback_signal_completion(wb_enc->wb_conn, 0);
+
+	/* Signal any waiting atomic commit thread */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+}
+
+/**
+ * dpu_encoder_phys_wb_done_irq - writeback interrupt handler
+ * @arg:	Pointer to writeback encoder
+ * @irq_idx:	interrupt index
+ */
+static void dpu_encoder_phys_wb_done_irq(void *arg, int irq_idx)
+{
+	_dpu_encoder_phys_wb_frame_done_helper(arg);
+}
+
+/**
+ * dpu_encoder_phys_wb_irq_ctrl - irq control of WB
+ * @phys:	Pointer to physical encoder
+ * @enable:	indicates enable or disable interrupts
+ */
+static void dpu_encoder_phys_wb_irq_ctrl(
+		struct dpu_encoder_phys *phys, bool enable)
+{
+
+	struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys);
+
+	if (enable && atomic_inc_return(&wb_enc->wbirq_refcount) == 1)
+		dpu_core_irq_register_callback(phys->dpu_kms,
+				phys->irq[INTR_IDX_WB_DONE], dpu_encoder_phys_wb_done_irq, phys);
+	else if (!enable &&
+			atomic_dec_return(&wb_enc->wbirq_refcount) == 0)
+		dpu_core_irq_unregister_callback(phys->dpu_kms, phys->irq[INTR_IDX_WB_DONE]);
+}
+
+static void dpu_encoder_phys_wb_atomic_mode_set(
+		struct dpu_encoder_phys *phys_enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state)
+{
+
+	phys_enc->irq[INTR_IDX_WB_DONE] = phys_enc->hw_wb->caps->intr_wb_done;
+}
+
+static void _dpu_encoder_phys_wb_handle_wbdone_timeout(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc);
+	u32 frame_event = DPU_ENCODER_FRAME_EVENT_ERROR;
+
+	wb_enc->wb_done_timeout_cnt++;
+
+	if (wb_enc->wb_done_timeout_cnt == 1)
+		msm_disp_snapshot_state(phys_enc->parent->dev);
+
+	atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0);
+
+	/* request a ctl reset before the next kickoff */
+	phys_enc->enable_state = DPU_ENC_ERR_NEEDS_HW_RESET;
+
+	if (wb_enc->wb_conn)
+		drm_writeback_signal_completion(wb_enc->wb_conn, 0);
+
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(
+				phys_enc->parent, phys_enc, frame_event);
+}
+
+/**
+ * dpu_encoder_phys_wb_wait_for_commit_done - wait until request is committed
+ * @phys_enc:	Pointer to physical encoder
+ */
+static int dpu_encoder_phys_wb_wait_for_commit_done(
+		struct dpu_encoder_phys *phys_enc)
+{
+	unsigned long ret;
+	struct dpu_encoder_wait_info wait_info;
+	struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc);
+
+	wait_info.wq = &phys_enc->pending_kickoff_wq;
+	wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt;
+	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
+
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc,
+			phys_enc->irq[INTR_IDX_WB_DONE],
+			dpu_encoder_phys_wb_done_irq, &wait_info);
+	if (ret == -ETIMEDOUT)
+		_dpu_encoder_phys_wb_handle_wbdone_timeout(phys_enc);
+	else if (!ret)
+		wb_enc->wb_done_timeout_cnt = 0;
+
+	return ret;
+}
+
+/**
+ * dpu_encoder_phys_wb_prepare_for_kickoff - pre-kickoff processing
+ * @phys_enc:	Pointer to physical encoder
+ * Returns:	Zero on success
+ */
+static void dpu_encoder_phys_wb_prepare_for_kickoff(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc);
+	struct drm_connector *drm_conn;
+	struct drm_connector_state *state;
+
+	DPU_DEBUG("[wb:%d]\n", phys_enc->hw_wb->idx - WB_0);
+
+	if (!wb_enc->wb_conn || !wb_enc->wb_job) {
+		DPU_ERROR("invalid wb_conn or wb_job\n");
+		return;
+	}
+
+	drm_conn = &wb_enc->wb_conn->base;
+	state = drm_conn->state;
+
+	if (wb_enc->wb_conn && wb_enc->wb_job)
+		drm_writeback_queue_job(wb_enc->wb_conn, state);
+
+	dpu_encoder_phys_wb_setup(phys_enc);
+
+	_dpu_encoder_phys_wb_update_flush(phys_enc);
+}
+
+/**
+ * dpu_encoder_phys_wb_needs_single_flush - trigger flush processing
+ * @phys_enc:	Pointer to physical encoder
+ */
+static bool dpu_encoder_phys_wb_needs_single_flush(struct dpu_encoder_phys *phys_enc)
+{
+	DPU_DEBUG("[wb:%d]\n", phys_enc->hw_wb->idx - WB_0);
+	return false;
+}
+
+/**
+ * dpu_encoder_phys_wb_handle_post_kickoff - post-kickoff processing
+ * @phys_enc:	Pointer to physical encoder
+ */
+static void dpu_encoder_phys_wb_handle_post_kickoff(
+		struct dpu_encoder_phys *phys_enc)
+{
+	DPU_DEBUG("[wb:%d]\n", phys_enc->hw_wb->idx - WB_0);
+
+}
+
+/**
+ * dpu_encoder_phys_wb_enable - enable writeback encoder
+ * @phys_enc:	Pointer to physical encoder
+ */
+static void dpu_encoder_phys_wb_enable(struct dpu_encoder_phys *phys_enc)
+{
+	DPU_DEBUG("[wb:%d]\n", phys_enc->hw_wb->idx - WB_0);
+	phys_enc->enable_state = DPU_ENC_ENABLED;
+}
+/**
+ * dpu_encoder_phys_wb_disable - disable writeback encoder
+ * @phys_enc:	Pointer to physical encoder
+ */
+static void dpu_encoder_phys_wb_disable(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_wb *hw_wb = phys_enc->hw_wb;
+	struct dpu_hw_ctl *hw_ctl = phys_enc->hw_ctl;
+
+	DPU_DEBUG("[wb:%d]\n", hw_wb->idx - WB_0);
+
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DPU_ERROR("encoder is already disabled\n");
+		return;
+	}
+
+	/* reset h/w before final flush */
+	if (phys_enc->hw_ctl->ops.clear_pending_flush)
+		phys_enc->hw_ctl->ops.clear_pending_flush(phys_enc->hw_ctl);
+
+	/*
+	 * New CTL reset sequence from 5.0 MDP onwards.
+	 * If has_3d_merge_reset is not set, legacy reset
+	 * sequence is executed.
+	 *
+	 * Legacy reset sequence has not been implemented yet.
+	 * Any target earlier than SM8150 will need it and when
+	 * WB support is added to those targets will need to add
+	 * the legacy teardown sequence as well.
+	 */
+	if (hw_ctl->caps->features & BIT(DPU_CTL_ACTIVE_CFG))
+		dpu_encoder_helper_phys_cleanup(phys_enc);
+
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+}
+
+/**
+ * dpu_encoder_phys_wb_destroy - destroy writeback encoder
+ * @phys_enc:	Pointer to physical encoder
+ */
+static void dpu_encoder_phys_wb_destroy(struct dpu_encoder_phys *phys_enc)
+{
+	if (!phys_enc)
+		return;
+
+	DPU_DEBUG("[wb:%d]\n", phys_enc->wb_idx - WB_0);
+
+	kfree(phys_enc);
+}
+
+static void dpu_encoder_phys_wb_prepare_wb_job(struct dpu_encoder_phys *phys_enc,
+		struct drm_writeback_job *job)
+{
+	const struct msm_format *format;
+	struct msm_gem_address_space *aspace;
+	struct dpu_hw_wb_cfg *wb_cfg;
+	int ret;
+	struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc);
+
+	if (!job->fb)
+		return;
+
+	wb_enc->wb_job = job;
+	wb_enc->wb_conn = job->connector;
+	aspace = phys_enc->dpu_kms->base.aspace;
+
+	wb_cfg = &wb_enc->wb_cfg;
+
+	memset(wb_cfg, 0, sizeof(struct dpu_hw_wb_cfg));
+
+	ret = msm_framebuffer_prepare(job->fb, aspace, false);
+	if (ret) {
+		DPU_ERROR("prep fb failed, %d\n", ret);
+		return;
+	}
+
+	format = msm_framebuffer_format(job->fb);
+
+	wb_cfg->dest.format = dpu_get_dpu_format_ext(
+			format->pixel_format, job->fb->modifier);
+	if (!wb_cfg->dest.format) {
+		/* this error should be detected during atomic_check */
+		DPU_ERROR("failed to get format %x\n", format->pixel_format);
+		return;
+	}
+
+	ret = dpu_format_populate_layout(aspace, job->fb, &wb_cfg->dest);
+	if (ret) {
+		DPU_DEBUG("failed to populate layout %d\n", ret);
+		return;
+	}
+
+	wb_cfg->dest.width = job->fb->width;
+	wb_cfg->dest.height = job->fb->height;
+	wb_cfg->dest.num_planes = wb_cfg->dest.format->num_planes;
+
+	if ((wb_cfg->dest.format->fetch_planes == DPU_PLANE_PLANAR) &&
+			(wb_cfg->dest.format->element[0] == C1_B_Cb))
+		swap(wb_cfg->dest.plane_addr[1], wb_cfg->dest.plane_addr[2]);
+
+	DPU_DEBUG("[fb_offset:%8.8x,%8.8x,%8.8x,%8.8x]\n",
+			wb_cfg->dest.plane_addr[0], wb_cfg->dest.plane_addr[1],
+			wb_cfg->dest.plane_addr[2], wb_cfg->dest.plane_addr[3]);
+
+	DPU_DEBUG("[fb_stride:%8.8x,%8.8x,%8.8x,%8.8x]\n",
+			wb_cfg->dest.plane_pitch[0], wb_cfg->dest.plane_pitch[1],
+			wb_cfg->dest.plane_pitch[2], wb_cfg->dest.plane_pitch[3]);
+}
+
+static void dpu_encoder_phys_wb_cleanup_wb_job(struct dpu_encoder_phys *phys_enc,
+		struct drm_writeback_job *job)
+{
+	struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc);
+	struct msm_gem_address_space *aspace;
+
+	if (!job->fb)
+		return;
+
+	aspace = phys_enc->dpu_kms->base.aspace;
+
+	msm_framebuffer_cleanup(job->fb, aspace, false);
+	wb_enc->wb_job = NULL;
+	wb_enc->wb_conn = NULL;
+}
+
+static bool dpu_encoder_phys_wb_is_valid_for_commit(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc);
+
+	if (wb_enc->wb_job)
+		return true;
+	else
+		return false;
+}
+
+/**
+ * dpu_encoder_phys_wb_init_ops - initialize writeback operations
+ * @ops:	Pointer to encoder operation table
+ */
+static void dpu_encoder_phys_wb_init_ops(struct dpu_encoder_phys_ops *ops)
+{
+	ops->is_master = dpu_encoder_phys_wb_is_master;
+	ops->atomic_mode_set = dpu_encoder_phys_wb_atomic_mode_set;
+	ops->enable = dpu_encoder_phys_wb_enable;
+	ops->disable = dpu_encoder_phys_wb_disable;
+	ops->destroy = dpu_encoder_phys_wb_destroy;
+	ops->atomic_check = dpu_encoder_phys_wb_atomic_check;
+	ops->wait_for_commit_done = dpu_encoder_phys_wb_wait_for_commit_done;
+	ops->prepare_for_kickoff = dpu_encoder_phys_wb_prepare_for_kickoff;
+	ops->handle_post_kickoff = dpu_encoder_phys_wb_handle_post_kickoff;
+	ops->needs_single_flush = dpu_encoder_phys_wb_needs_single_flush;
+	ops->trigger_start = dpu_encoder_helper_trigger_start;
+	ops->prepare_wb_job = dpu_encoder_phys_wb_prepare_wb_job;
+	ops->cleanup_wb_job = dpu_encoder_phys_wb_cleanup_wb_job;
+	ops->irq_control = dpu_encoder_phys_wb_irq_ctrl;
+	ops->is_valid_for_commit = dpu_encoder_phys_wb_is_valid_for_commit;
+
+}
+
+/**
+ * dpu_encoder_phys_wb_init - initialize writeback encoder
+ * @p:	Pointer to init info structure with initialization params
+ */
+struct dpu_encoder_phys *dpu_encoder_phys_wb_init(
+		struct dpu_enc_phys_init_params *p)
+{
+	struct dpu_encoder_phys *phys_enc = NULL;
+	struct dpu_encoder_phys_wb *wb_enc = NULL;
+	int ret = 0;
+	int i;
+
+	DPU_DEBUG("\n");
+
+	if (!p || !p->parent) {
+		DPU_ERROR("invalid params\n");
+		ret = -EINVAL;
+		goto fail_alloc;
+	}
+
+	wb_enc = kzalloc(sizeof(*wb_enc), GFP_KERNEL);
+	if (!wb_enc) {
+		DPU_ERROR("failed to allocate wb phys_enc enc\n");
+		ret = -ENOMEM;
+		goto fail_alloc;
+	}
+
+	phys_enc = &wb_enc->base;
+	phys_enc->hw_mdptop = p->dpu_kms->hw_mdp;
+	phys_enc->wb_idx = p->wb_idx;
+
+	dpu_encoder_phys_wb_init_ops(&phys_enc->ops);
+	phys_enc->parent = p->parent;
+	phys_enc->parent_ops = p->parent_ops;
+	phys_enc->dpu_kms = p->dpu_kms;
+	phys_enc->split_role = p->split_role;
+	phys_enc->intf_mode = INTF_MODE_WB_LINE;
+	phys_enc->wb_idx = p->wb_idx;
+	phys_enc->enc_spinlock = p->enc_spinlock;
+
+	atomic_set(&wb_enc->wbirq_refcount, 0);
+
+	for (i = 0; i < ARRAY_SIZE(phys_enc->irq); i++)
+		phys_enc->irq[i] = -EINVAL;
+
+	atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+	atomic_set(&phys_enc->vblank_refcount, 0);
+	wb_enc->wb_done_timeout_cnt = 0;
+
+	init_waitqueue_head(&phys_enc->pending_kickoff_wq);
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+
+	DPU_DEBUG("Created dpu_encoder_phys for wb %d\n",
+			phys_enc->wb_idx);
+
+	return phys_enc;
+
+fail_alloc:
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
new file mode 100644
index 000000000..f436a1f34
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -0,0 +1,1043 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <uapi/drm/drm_fourcc.h>
+#include <drm/drm_framebuffer.h>
+
+#include "msm_media_info.h"
+#include "dpu_kms.h"
+#include "dpu_formats.h"
+
+#define DPU_UBWC_META_MACRO_W_H		16
+#define DPU_UBWC_META_BLOCK_SIZE	256
+#define DPU_UBWC_PLANE_SIZE_ALIGNMENT	4096
+
+#define DPU_TILE_HEIGHT_DEFAULT	1
+#define DPU_TILE_HEIGHT_TILED	4
+#define DPU_TILE_HEIGHT_UBWC	4
+#define DPU_TILE_HEIGHT_NV12	8
+
+#define DPU_MAX_IMG_WIDTH		0x3FFF
+#define DPU_MAX_IMG_HEIGHT		0x3FFF
+
+/*
+ * DPU supported format packing, bpp, and other format
+ * information.
+ * DPU currently only supports interleaved RGB formats
+ * UBWC support for a pixel format is indicated by the flag,
+ * there is additional meta data plane for such formats
+ */
+
+#define INTERLEAVED_RGB_FMT(fmt, a, r, g, b, e0, e1, e2, e3, uc, alpha,   \
+bp, flg, fm, np)                                                          \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_INTERLEAVED,                            \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), (e3) },                            \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = DPU_CHROMA_RGB,                                  \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = uc,                                               \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define INTERLEAVED_RGB_FMT_TILED(fmt, a, r, g, b, e0, e1, e2, e3, uc,    \
+alpha, bp, flg, fm, np, th)                                               \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_INTERLEAVED,                            \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), (e3) },                            \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = DPU_CHROMA_RGB,                                  \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = uc,                                               \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = th                                                 \
+}
+
+
+#define INTERLEAVED_YUV_FMT(fmt, a, r, g, b, e0, e1, e2, e3,              \
+alpha, chroma, count, bp, flg, fm, np)                                    \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_INTERLEAVED,                            \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), (e3)},                             \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = count,                                            \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define PSEUDO_YUV_FMT(fmt, a, r, g, b, e0, e1, chroma, flg, fm, np)      \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define PSEUDO_YUV_FMT_TILED(fmt, a, r, g, b, e0, e1, chroma,             \
+flg, fm, np, th)                                                          \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = th                                                 \
+}
+
+#define PSEUDO_YUV_FMT_LOOSE(fmt, a, r, g, b, e0, e1, chroma, flg, fm, np)\
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 1,                                            \
+	.unpack_tight = 0,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define PSEUDO_YUV_FMT_LOOSE_TILED(fmt, a, r, g, b, e0, e1, chroma,       \
+flg, fm, np, th)                                                          \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 1,                                            \
+	.unpack_tight = 0,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = th                                                 \
+}
+
+
+#define PLANAR_YUV_FMT(fmt, a, r, g, b, e0, e1, e2, alpha, chroma, bp,    \
+flg, fm, np)                                                      \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PLANAR,                                 \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), 0 },                               \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = 1,                                                \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+/*
+ * struct dpu_media_color_map - maps drm format to media format
+ * @format: DRM base pixel format
+ * @color: Media API color related to DRM format
+ */
+struct dpu_media_color_map {
+	uint32_t format;
+	uint32_t color;
+};
+
+static const struct dpu_format dpu_format_map[] = {
+	INTERLEAVED_RGB_FMT(ARGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGB888,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		false, 3, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGR888,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 3, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGB565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGR565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ARGB1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ARGB4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ARGB2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	PSEUDO_YUV_FMT(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PSEUDO_YUV_FMT(NV21,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PSEUDO_YUV_FMT(NV16,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_H2V1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PSEUDO_YUV_FMT(NV61,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb,
+		DPU_CHROMA_H2V1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(VYUY,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C0_G_Y,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(UYVY,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C0_G_Y,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(YUYV,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C0_G_Y, C1_B_Cb, C0_G_Y, C2_R_Cr,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(YVYU,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C0_G_Y, C2_R_Cr, C0_G_Y, C1_B_Cb,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PLANAR_YUV_FMT(YUV420,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb, C0_G_Y,
+		false, DPU_CHROMA_420, 1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 3),
+
+	PLANAR_YUV_FMT(YVU420,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr, C0_G_Y,
+		false, DPU_CHROMA_420, 1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 3),
+};
+
+/*
+ * UBWC formats table:
+ * This table holds the UBWC formats supported.
+ * If a compression ratio needs to be used for this or any other format,
+ * the data will be passed by user-space.
+ */
+static const struct dpu_format dpu_format_map_ubwc[] = {
+	INTERLEAVED_RGB_FMT_TILED(BGR565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 2, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(ABGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	/* ARGB8888 and ABGR8888 purposely have the same color
+	 * ordering.  The hardware only supports ABGR8888 UBWC
+	 * natively.
+	 */
+	INTERLEAVED_RGB_FMT_TILED(ARGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(XBGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(XRGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(ABGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX | DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(XBGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX | DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	PSEUDO_YUV_FMT_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV |
+				DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12),
+};
+
+/* _dpu_get_v_h_subsample_rate - Get subsample rates for all formats we support
+ *   Note: Not using the drm_format_*_subsampling since we have formats
+ */
+static void _dpu_get_v_h_subsample_rate(
+	enum dpu_chroma_samp_type chroma_sample,
+	uint32_t *v_sample,
+	uint32_t *h_sample)
+{
+	if (!v_sample || !h_sample)
+		return;
+
+	switch (chroma_sample) {
+	case DPU_CHROMA_H2V1:
+		*v_sample = 1;
+		*h_sample = 2;
+		break;
+	case DPU_CHROMA_H1V2:
+		*v_sample = 2;
+		*h_sample = 1;
+		break;
+	case DPU_CHROMA_420:
+		*v_sample = 2;
+		*h_sample = 2;
+		break;
+	default:
+		*v_sample = 1;
+		*h_sample = 1;
+		break;
+	}
+}
+
+static int _dpu_format_get_media_color_ubwc(const struct dpu_format *fmt)
+{
+	static const struct dpu_media_color_map dpu_media_ubwc_map[] = {
+		{DRM_FORMAT_ABGR8888, COLOR_FMT_RGBA8888_UBWC},
+		{DRM_FORMAT_ARGB8888, COLOR_FMT_RGBA8888_UBWC},
+		{DRM_FORMAT_XBGR8888, COLOR_FMT_RGBA8888_UBWC},
+		{DRM_FORMAT_XRGB8888, COLOR_FMT_RGBA8888_UBWC},
+		{DRM_FORMAT_ABGR2101010, COLOR_FMT_RGBA1010102_UBWC},
+		{DRM_FORMAT_XBGR2101010, COLOR_FMT_RGBA1010102_UBWC},
+		{DRM_FORMAT_BGR565, COLOR_FMT_RGB565_UBWC},
+	};
+	int color_fmt = -1;
+	int i;
+
+	if (fmt->base.pixel_format == DRM_FORMAT_NV12) {
+		if (DPU_FORMAT_IS_DX(fmt)) {
+			if (fmt->unpack_tight)
+				color_fmt = COLOR_FMT_NV12_BPP10_UBWC;
+			else
+				color_fmt = COLOR_FMT_P010_UBWC;
+		} else
+			color_fmt = COLOR_FMT_NV12_UBWC;
+		return color_fmt;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dpu_media_ubwc_map); ++i)
+		if (fmt->base.pixel_format == dpu_media_ubwc_map[i].format) {
+			color_fmt = dpu_media_ubwc_map[i].color;
+			break;
+		}
+	return color_fmt;
+}
+
+static int _dpu_format_get_plane_sizes_ubwc(
+		const struct dpu_format *fmt,
+		const uint32_t width,
+		const uint32_t height,
+		struct dpu_hw_fmt_layout *layout)
+{
+	int i;
+	int color;
+	bool meta = DPU_FORMAT_IS_UBWC(fmt);
+
+	memset(layout, 0, sizeof(struct dpu_hw_fmt_layout));
+	layout->format = fmt;
+	layout->width = width;
+	layout->height = height;
+	layout->num_planes = fmt->num_planes;
+
+	color = _dpu_format_get_media_color_ubwc(fmt);
+	if (color < 0) {
+		DRM_ERROR("UBWC format not supported for fmt: %4.4s\n",
+			(char *)&fmt->base.pixel_format);
+		return -EINVAL;
+	}
+
+	if (DPU_FORMAT_IS_YUV(layout->format)) {
+		uint32_t y_sclines, uv_sclines;
+		uint32_t y_meta_scanlines = 0;
+		uint32_t uv_meta_scanlines = 0;
+
+		layout->num_planes = 2;
+		layout->plane_pitch[0] = VENUS_Y_STRIDE(color, width);
+		y_sclines = VENUS_Y_SCANLINES(color, height);
+		layout->plane_size[0] = MSM_MEDIA_ALIGN(layout->plane_pitch[0] *
+			y_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		layout->plane_pitch[1] = VENUS_UV_STRIDE(color, width);
+		uv_sclines = VENUS_UV_SCANLINES(color, height);
+		layout->plane_size[1] = MSM_MEDIA_ALIGN(layout->plane_pitch[1] *
+			uv_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		if (!meta)
+			goto done;
+
+		layout->num_planes += 2;
+		layout->plane_pitch[2] = VENUS_Y_META_STRIDE(color, width);
+		y_meta_scanlines = VENUS_Y_META_SCANLINES(color, height);
+		layout->plane_size[2] = MSM_MEDIA_ALIGN(layout->plane_pitch[2] *
+			y_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		layout->plane_pitch[3] = VENUS_UV_META_STRIDE(color, width);
+		uv_meta_scanlines = VENUS_UV_META_SCANLINES(color, height);
+		layout->plane_size[3] = MSM_MEDIA_ALIGN(layout->plane_pitch[3] *
+			uv_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+	} else {
+		uint32_t rgb_scanlines, rgb_meta_scanlines;
+
+		layout->num_planes = 1;
+
+		layout->plane_pitch[0] = VENUS_RGB_STRIDE(color, width);
+		rgb_scanlines = VENUS_RGB_SCANLINES(color, height);
+		layout->plane_size[0] = MSM_MEDIA_ALIGN(layout->plane_pitch[0] *
+			rgb_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		if (!meta)
+			goto done;
+		layout->num_planes += 2;
+		layout->plane_pitch[2] = VENUS_RGB_META_STRIDE(color, width);
+		rgb_meta_scanlines = VENUS_RGB_META_SCANLINES(color, height);
+		layout->plane_size[2] = MSM_MEDIA_ALIGN(layout->plane_pitch[2] *
+			rgb_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+	}
+
+done:
+	for (i = 0; i < DPU_MAX_PLANES; i++)
+		layout->total_size += layout->plane_size[i];
+
+	return 0;
+}
+
+static int _dpu_format_get_plane_sizes_linear(
+		const struct dpu_format *fmt,
+		const uint32_t width,
+		const uint32_t height,
+		struct dpu_hw_fmt_layout *layout,
+		const uint32_t *pitches)
+{
+	int i;
+
+	memset(layout, 0, sizeof(struct dpu_hw_fmt_layout));
+	layout->format = fmt;
+	layout->width = width;
+	layout->height = height;
+	layout->num_planes = fmt->num_planes;
+
+	/* Due to memset above, only need to set planes of interest */
+	if (fmt->fetch_planes == DPU_PLANE_INTERLEAVED) {
+		layout->num_planes = 1;
+		layout->plane_size[0] = width * height * layout->format->bpp;
+		layout->plane_pitch[0] = width * layout->format->bpp;
+	} else {
+		uint32_t v_subsample, h_subsample;
+		uint32_t chroma_samp;
+		uint32_t bpp = 1;
+
+		chroma_samp = fmt->chroma_sample;
+		_dpu_get_v_h_subsample_rate(chroma_samp, &v_subsample,
+				&h_subsample);
+
+		if (width % h_subsample || height % v_subsample) {
+			DRM_ERROR("mismatch in subsample vs dimensions\n");
+			return -EINVAL;
+		}
+
+		if ((fmt->base.pixel_format == DRM_FORMAT_NV12) &&
+			(DPU_FORMAT_IS_DX(fmt)))
+			bpp = 2;
+		layout->plane_pitch[0] = width * bpp;
+		layout->plane_pitch[1] = layout->plane_pitch[0] / h_subsample;
+		layout->plane_size[0] = layout->plane_pitch[0] * height;
+		layout->plane_size[1] = layout->plane_pitch[1] *
+				(height / v_subsample);
+
+		if (fmt->fetch_planes == DPU_PLANE_PSEUDO_PLANAR) {
+			layout->num_planes = 2;
+			layout->plane_size[1] *= 2;
+			layout->plane_pitch[1] *= 2;
+		} else {
+			/* planar */
+			layout->num_planes = 3;
+			layout->plane_size[2] = layout->plane_size[1];
+			layout->plane_pitch[2] = layout->plane_pitch[1];
+		}
+	}
+
+	/*
+	 * linear format: allow user allocated pitches if they are greater than
+	 * the requirement.
+	 * ubwc format: pitch values are computed uniformly across
+	 * all the components based on ubwc specifications.
+	 */
+	for (i = 0; i < layout->num_planes && i < DPU_MAX_PLANES; ++i) {
+		if (pitches && layout->plane_pitch[i] < pitches[i])
+			layout->plane_pitch[i] = pitches[i];
+	}
+
+	for (i = 0; i < DPU_MAX_PLANES; i++)
+		layout->total_size += layout->plane_size[i];
+
+	return 0;
+}
+
+static int dpu_format_get_plane_sizes(
+		const struct dpu_format *fmt,
+		const uint32_t w,
+		const uint32_t h,
+		struct dpu_hw_fmt_layout *layout,
+		const uint32_t *pitches)
+{
+	if (!layout || !fmt) {
+		DRM_ERROR("invalid pointer\n");
+		return -EINVAL;
+	}
+
+	if ((w > DPU_MAX_IMG_WIDTH) || (h > DPU_MAX_IMG_HEIGHT)) {
+		DRM_ERROR("image dimensions outside max range\n");
+		return -ERANGE;
+	}
+
+	if (DPU_FORMAT_IS_UBWC(fmt) || DPU_FORMAT_IS_TILE(fmt))
+		return _dpu_format_get_plane_sizes_ubwc(fmt, w, h, layout);
+
+	return _dpu_format_get_plane_sizes_linear(fmt, w, h, layout, pitches);
+}
+
+static int _dpu_format_populate_addrs_ubwc(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *layout)
+{
+	uint32_t base_addr = 0;
+	bool meta;
+
+	if (!fb || !layout) {
+		DRM_ERROR("invalid pointers\n");
+		return -EINVAL;
+	}
+
+	if (aspace)
+		base_addr = msm_framebuffer_iova(fb, aspace, 0);
+	if (!base_addr) {
+		DRM_ERROR("failed to retrieve base addr\n");
+		return -EFAULT;
+	}
+
+	meta = DPU_FORMAT_IS_UBWC(layout->format);
+
+	/* Per-format logic for verifying active planes */
+	if (DPU_FORMAT_IS_YUV(layout->format)) {
+		/************************************************/
+		/*      UBWC            **                      */
+		/*      buffer          **      DPU PLANE       */
+		/*      format          **                      */
+		/************************************************/
+		/* -------------------  ** -------------------- */
+		/* |      Y meta     |  ** |    Y bitstream   | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |    Y bitstream  |  ** |  CbCr bitstream  | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |   Cbcr metadata |  ** |       Y meta     | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |  CbCr bitstream |  ** |     CbCr meta    | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/************************************************/
+
+		/* configure Y bitstream plane */
+		layout->plane_addr[0] = base_addr + layout->plane_size[2];
+
+		/* configure CbCr bitstream plane */
+		layout->plane_addr[1] = base_addr + layout->plane_size[0]
+			+ layout->plane_size[2] + layout->plane_size[3];
+
+		if (!meta)
+			return 0;
+
+		/* configure Y metadata plane */
+		layout->plane_addr[2] = base_addr;
+
+		/* configure CbCr metadata plane */
+		layout->plane_addr[3] = base_addr + layout->plane_size[0]
+			+ layout->plane_size[2];
+
+	} else {
+		/************************************************/
+		/*      UBWC            **                      */
+		/*      buffer          **      DPU PLANE       */
+		/*      format          **                      */
+		/************************************************/
+		/* -------------------  ** -------------------- */
+		/* |      RGB meta   |  ** |   RGB bitstream  | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |  RGB bitstream  |  ** |       NONE       | */
+		/* |       data      |  ** |                  | */
+		/* -------------------  ** -------------------- */
+		/*                      ** |     RGB meta     | */
+		/*                      ** |       plane      | */
+		/*                      ** -------------------- */
+		/************************************************/
+
+		layout->plane_addr[0] = base_addr + layout->plane_size[2];
+		layout->plane_addr[1] = 0;
+
+		if (!meta)
+			return 0;
+
+		layout->plane_addr[2] = base_addr;
+		layout->plane_addr[3] = 0;
+	}
+	return 0;
+}
+
+static int _dpu_format_populate_addrs_linear(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *layout)
+{
+	unsigned int i;
+
+	/* Can now check the pitches given vs pitches expected */
+	for (i = 0; i < layout->num_planes; ++i) {
+		if (layout->plane_pitch[i] > fb->pitches[i]) {
+			DRM_ERROR("plane %u expected pitch %u, fb %u\n",
+				i, layout->plane_pitch[i], fb->pitches[i]);
+			return -EINVAL;
+		}
+	}
+
+	/* Populate addresses for simple formats here */
+	for (i = 0; i < layout->num_planes; ++i) {
+		if (aspace)
+			layout->plane_addr[i] =
+				msm_framebuffer_iova(fb, aspace, i);
+		if (!layout->plane_addr[i]) {
+			DRM_ERROR("failed to retrieve base addr\n");
+			return -EFAULT;
+		}
+	}
+
+	return 0;
+}
+
+int dpu_format_populate_layout(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *layout)
+{
+	uint32_t plane_addr[DPU_MAX_PLANES];
+	int i, ret;
+
+	if (!fb || !layout) {
+		DRM_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	if ((fb->width > DPU_MAX_IMG_WIDTH) ||
+			(fb->height > DPU_MAX_IMG_HEIGHT)) {
+		DRM_ERROR("image dimensions outside max range\n");
+		return -ERANGE;
+	}
+
+	layout->format = to_dpu_format(msm_framebuffer_format(fb));
+
+	/* Populate the plane sizes etc via get_format */
+	ret = dpu_format_get_plane_sizes(layout->format, fb->width, fb->height,
+			layout, fb->pitches);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < DPU_MAX_PLANES; ++i)
+		plane_addr[i] = layout->plane_addr[i];
+
+	/* Populate the addresses given the fb */
+	if (DPU_FORMAT_IS_UBWC(layout->format) ||
+			DPU_FORMAT_IS_TILE(layout->format))
+		ret = _dpu_format_populate_addrs_ubwc(aspace, fb, layout);
+	else
+		ret = _dpu_format_populate_addrs_linear(aspace, fb, layout);
+
+	/* check if anything changed */
+	if (!ret && !memcmp(plane_addr, layout->plane_addr, sizeof(plane_addr)))
+		ret = -EAGAIN;
+
+	return ret;
+}
+
+int dpu_format_check_modified_format(
+		const struct msm_kms *kms,
+		const struct msm_format *msm_fmt,
+		const struct drm_mode_fb_cmd2 *cmd,
+		struct drm_gem_object **bos)
+{
+	const struct drm_format_info *info;
+	const struct dpu_format *fmt;
+	struct dpu_hw_fmt_layout layout;
+	uint32_t bos_total_size = 0;
+	int ret, i;
+
+	if (!msm_fmt || !cmd || !bos) {
+		DRM_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	fmt = to_dpu_format(msm_fmt);
+	info = drm_format_info(fmt->base.pixel_format);
+	if (!info)
+		return -EINVAL;
+
+	ret = dpu_format_get_plane_sizes(fmt, cmd->width, cmd->height,
+			&layout, cmd->pitches);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < info->num_planes; i++) {
+		if (!bos[i]) {
+			DRM_ERROR("invalid handle for plane %d\n", i);
+			return -EINVAL;
+		}
+		if ((i == 0) || (bos[i] != bos[0]))
+			bos_total_size += bos[i]->size;
+	}
+
+	if (bos_total_size < layout.total_size) {
+		DRM_ERROR("buffers total size too small %u expected %u\n",
+				bos_total_size, layout.total_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+const struct dpu_format *dpu_get_dpu_format_ext(
+		const uint32_t format,
+		const uint64_t modifier)
+{
+	uint32_t i = 0;
+	const struct dpu_format *fmt = NULL;
+	const struct dpu_format *map = NULL;
+	ssize_t map_size = 0;
+
+	/*
+	 * Currently only support exactly zero or one modifier.
+	 * All planes use the same modifier.
+	 */
+	DRM_DEBUG_ATOMIC("plane format modifier 0x%llX\n", modifier);
+
+	switch (modifier) {
+	case 0:
+		map = dpu_format_map;
+		map_size = ARRAY_SIZE(dpu_format_map);
+		break;
+	case DRM_FORMAT_MOD_QCOM_COMPRESSED:
+		map = dpu_format_map_ubwc;
+		map_size = ARRAY_SIZE(dpu_format_map_ubwc);
+		DRM_DEBUG_ATOMIC("found fmt: %4.4s  DRM_FORMAT_MOD_QCOM_COMPRESSED\n",
+				(char *)&format);
+		break;
+	default:
+		DPU_ERROR("unsupported format modifier %llX\n", modifier);
+		return NULL;
+	}
+
+	for (i = 0; i < map_size; i++) {
+		if (format == map[i].base.pixel_format) {
+			fmt = &map[i];
+			break;
+		}
+	}
+
+	if (fmt == NULL)
+		DPU_ERROR("unsupported fmt: %4.4s modifier 0x%llX\n",
+			(char *)&format, modifier);
+	else
+		DRM_DEBUG_ATOMIC("fmt %4.4s mod 0x%llX ubwc %d yuv %d\n",
+				(char *)&format, modifier,
+				DPU_FORMAT_IS_UBWC(fmt),
+				DPU_FORMAT_IS_YUV(fmt));
+
+	return fmt;
+}
+
+const struct msm_format *dpu_get_msm_format(
+		struct msm_kms *kms,
+		const uint32_t format,
+		const uint64_t modifiers)
+{
+	const struct dpu_format *fmt = dpu_get_dpu_format_ext(format,
+			modifiers);
+	if (fmt)
+		return &fmt->base;
+	return NULL;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
new file mode 100644
index 000000000..84b8b3289
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_FORMATS_H
+#define _DPU_FORMATS_H
+
+#include <drm/drm_fourcc.h>
+#include "msm_gem.h"
+#include "dpu_hw_mdss.h"
+
+/**
+ * dpu_get_dpu_format_ext() - Returns dpu format structure pointer.
+ * @format:          DRM FourCC Code
+ * @modifiers:       format modifier array from client, one per plane
+ */
+const struct dpu_format *dpu_get_dpu_format_ext(
+		const uint32_t format,
+		const uint64_t modifier);
+
+#define dpu_get_dpu_format(f) dpu_get_dpu_format_ext(f, 0)
+
+/**
+ * dpu_find_format - validate if the pixel format is supported
+ * @format:		dpu format
+ * @supported_formats:	supported formats by dpu HW
+ * @num_formatss:	total number of formats
+ *
+ * Return: false if not valid format, true on success
+ */
+static inline bool dpu_find_format(u32 format, const u32 *supported_formats,
+					size_t num_formats)
+{
+	int i;
+
+	for (i = 0; i < num_formats; i++) {
+		/* check for valid formats supported */
+		if (format == supported_formats[i])
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * dpu_get_msm_format - get an dpu_format by its msm_format base
+ *                     callback function registers with the msm_kms layer
+ * @kms:             kms driver
+ * @format:          DRM FourCC Code
+ * @modifiers:       data layout modifier
+ */
+const struct msm_format *dpu_get_msm_format(
+		struct msm_kms *kms,
+		const uint32_t format,
+		const uint64_t modifiers);
+
+/**
+ * dpu_format_check_modified_format - validate format and buffers for
+ *                   dpu non-standard, i.e. modified format
+ * @kms:             kms driver
+ * @msm_fmt:         pointer to the msm_fmt base pointer of an dpu_format
+ * @cmd:             fb_cmd2 structure user request
+ * @bos:             gem buffer object list
+ *
+ * Return: error code on failure, 0 on success
+ */
+int dpu_format_check_modified_format(
+		const struct msm_kms *kms,
+		const struct msm_format *msm_fmt,
+		const struct drm_mode_fb_cmd2 *cmd,
+		struct drm_gem_object **bos);
+
+/**
+ * dpu_format_populate_layout - populate the given format layout based on
+ *                     mmu, fb, and format found in the fb
+ * @aspace:            address space pointer
+ * @fb:                framebuffer pointer
+ * @fmtl:              format layout structure to populate
+ *
+ * Return: error code on failure, -EAGAIN if success but the addresses
+ *         are the same as before or 0 if new addresses were populated
+ */
+int dpu_format_populate_layout(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *fmtl);
+
+#endif /*_DPU_FORMATS_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
new file mode 100644
index 000000000..b2f330e99
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -0,0 +1,1959 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022. Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/slab.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_kms.h"
+
+#define VIG_BASE_MASK \
+	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) |\
+	BIT(DPU_SSPP_CDP) |\
+	BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_EXCL_RECT))
+
+#define VIG_MASK \
+	(VIG_BASE_MASK | \
+	BIT(DPU_SSPP_CSC_10BIT))
+
+#define VIG_MSM8998_MASK \
+	(VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED3))
+
+#define VIG_SDM845_MASK \
+	(VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED3))
+
+#define VIG_SC7180_MASK \
+	(VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED4))
+
+#define VIG_SM8250_MASK \
+	(VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED3LITE))
+
+#define VIG_QCM2290_MASK (VIG_BASE_MASK | BIT(DPU_SSPP_QOS_8LVL))
+
+#define DMA_MSM8998_MASK \
+	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) |\
+	BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_TS_PREFILL_REC1) |\
+	BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_EXCL_RECT))
+
+#define VIG_SC7280_MASK \
+	(VIG_SC7180_MASK | BIT(DPU_SSPP_INLINE_ROTATION))
+
+#define DMA_SDM845_MASK \
+	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) | BIT(DPU_SSPP_QOS_8LVL) |\
+	BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_TS_PREFILL_REC1) |\
+	BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_EXCL_RECT))
+
+#define DMA_CURSOR_SDM845_MASK \
+	(DMA_SDM845_MASK | BIT(DPU_SSPP_CURSOR))
+
+#define DMA_CURSOR_MSM8998_MASK \
+	(DMA_MSM8998_MASK | BIT(DPU_SSPP_CURSOR))
+
+#define MIXER_MSM8998_MASK \
+	(BIT(DPU_MIXER_SOURCESPLIT))
+
+#define MIXER_SDM845_MASK \
+	(BIT(DPU_MIXER_SOURCESPLIT) | BIT(DPU_DIM_LAYER) | BIT(DPU_MIXER_COMBINED_ALPHA))
+
+#define MIXER_SC7180_MASK \
+	(BIT(DPU_DIM_LAYER) | BIT(DPU_MIXER_COMBINED_ALPHA))
+
+#define PINGPONG_SDM845_MASK BIT(DPU_PINGPONG_DITHER)
+
+#define PINGPONG_SDM845_SPLIT_MASK \
+	(PINGPONG_SDM845_MASK | BIT(DPU_PINGPONG_TE2))
+
+#define CTL_SC7280_MASK \
+	(BIT(DPU_CTL_ACTIVE_CFG) | BIT(DPU_CTL_FETCH_ACTIVE) | BIT(DPU_CTL_VM_CFG))
+
+#define MERGE_3D_SM8150_MASK (0)
+
+#define DSPP_MSM8998_MASK BIT(DPU_DSPP_PCC) | BIT(DPU_DSPP_GC)
+
+#define DSPP_SC7180_MASK BIT(DPU_DSPP_PCC)
+
+#define INTF_SDM845_MASK (0)
+
+#define INTF_SC7180_MASK \
+	(BIT(DPU_INTF_INPUT_CTRL) | \
+	 BIT(DPU_INTF_TE) | \
+	 BIT(DPU_INTF_STATUS_SUPPORTED) | \
+	 BIT(DPU_DATA_HCTL_EN))
+
+#define INTF_SC7280_MASK (INTF_SC7180_MASK)
+
+#define IRQ_SDM845_MASK (BIT(MDP_SSPP_TOP0_INTR) | \
+			 BIT(MDP_SSPP_TOP0_INTR2) | \
+			 BIT(MDP_SSPP_TOP0_HIST_INTR) | \
+			 BIT(MDP_INTF0_INTR) | \
+			 BIT(MDP_INTF1_INTR) | \
+			 BIT(MDP_INTF2_INTR) | \
+			 BIT(MDP_INTF3_INTR) | \
+			 BIT(MDP_INTF4_INTR) | \
+			 BIT(MDP_AD4_0_INTR) | \
+			 BIT(MDP_AD4_1_INTR))
+
+#define IRQ_SC7180_MASK (BIT(MDP_SSPP_TOP0_INTR) | \
+			 BIT(MDP_SSPP_TOP0_INTR2) | \
+			 BIT(MDP_SSPP_TOP0_HIST_INTR) | \
+			 BIT(MDP_INTF0_INTR) | \
+			 BIT(MDP_INTF1_INTR))
+
+#define IRQ_SC7280_MASK (BIT(MDP_SSPP_TOP0_INTR) | \
+			 BIT(MDP_SSPP_TOP0_INTR2) | \
+			 BIT(MDP_SSPP_TOP0_HIST_INTR) | \
+			 BIT(MDP_INTF0_7xxx_INTR) | \
+			 BIT(MDP_INTF1_7xxx_INTR) | \
+			 BIT(MDP_INTF5_7xxx_INTR))
+
+#define IRQ_SM8250_MASK (BIT(MDP_SSPP_TOP0_INTR) | \
+			 BIT(MDP_SSPP_TOP0_INTR2) | \
+			 BIT(MDP_SSPP_TOP0_HIST_INTR) | \
+			 BIT(MDP_INTF0_INTR) | \
+			 BIT(MDP_INTF1_INTR) | \
+			 BIT(MDP_INTF2_INTR) | \
+			 BIT(MDP_INTF3_INTR) | \
+			 BIT(MDP_INTF4_INTR))
+
+#define IRQ_SC8180X_MASK (BIT(MDP_SSPP_TOP0_INTR) | \
+			  BIT(MDP_SSPP_TOP0_INTR2) | \
+			  BIT(MDP_SSPP_TOP0_HIST_INTR) | \
+			  BIT(MDP_INTF0_INTR) | \
+			  BIT(MDP_INTF1_INTR) | \
+			  BIT(MDP_INTF2_INTR) | \
+			  BIT(MDP_INTF3_INTR) | \
+			  BIT(MDP_INTF4_INTR) | \
+			  BIT(MDP_INTF5_INTR) | \
+			  BIT(MDP_AD4_0_INTR) | \
+			  BIT(MDP_AD4_1_INTR))
+
+#define WB_SM8250_MASK (BIT(DPU_WB_LINE_MODE) | \
+			 BIT(DPU_WB_UBWC) | \
+			 BIT(DPU_WB_YUV_CONFIG) | \
+			 BIT(DPU_WB_PIPE_ALPHA) | \
+			 BIT(DPU_WB_XY_ROI_OFFSET) | \
+			 BIT(DPU_WB_QOS) | \
+			 BIT(DPU_WB_QOS_8LVL) | \
+			 BIT(DPU_WB_CDP) | \
+			 BIT(DPU_WB_INPUT_CTRL))
+
+#define DEFAULT_PIXEL_RAM_SIZE		(50 * 1024)
+#define DEFAULT_DPU_LINE_WIDTH		2048
+#define DEFAULT_DPU_OUTPUT_LINE_WIDTH	2560
+
+#define MAX_HORZ_DECIMATION	4
+#define MAX_VERT_DECIMATION	4
+
+#define MAX_UPSCALE_RATIO	20
+#define MAX_DOWNSCALE_RATIO	4
+#define SSPP_UNITY_SCALE	1
+
+#define STRCAT(X, Y) (X Y)
+
+static const uint32_t plane_formats[] = {
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_RGBA8888,
+	DRM_FORMAT_BGRA8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_RGBX8888,
+	DRM_FORMAT_BGRX8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR565,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_RGBA5551,
+	DRM_FORMAT_BGRA5551,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_XBGR1555,
+	DRM_FORMAT_RGBX5551,
+	DRM_FORMAT_BGRX5551,
+	DRM_FORMAT_ARGB4444,
+	DRM_FORMAT_ABGR4444,
+	DRM_FORMAT_RGBA4444,
+	DRM_FORMAT_BGRA4444,
+	DRM_FORMAT_XRGB4444,
+	DRM_FORMAT_XBGR4444,
+	DRM_FORMAT_RGBX4444,
+	DRM_FORMAT_BGRX4444,
+};
+
+static const uint32_t plane_formats_yuv[] = {
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_RGBA8888,
+	DRM_FORMAT_BGRX8888,
+	DRM_FORMAT_BGRA8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_RGBX8888,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR565,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_RGBA5551,
+	DRM_FORMAT_BGRA5551,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_XBGR1555,
+	DRM_FORMAT_RGBX5551,
+	DRM_FORMAT_BGRX5551,
+	DRM_FORMAT_ARGB4444,
+	DRM_FORMAT_ABGR4444,
+	DRM_FORMAT_RGBA4444,
+	DRM_FORMAT_BGRA4444,
+	DRM_FORMAT_XRGB4444,
+	DRM_FORMAT_XBGR4444,
+	DRM_FORMAT_RGBX4444,
+	DRM_FORMAT_BGRX4444,
+
+	DRM_FORMAT_NV12,
+	DRM_FORMAT_NV21,
+	DRM_FORMAT_NV16,
+	DRM_FORMAT_NV61,
+	DRM_FORMAT_VYUY,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_YVYU,
+	DRM_FORMAT_YUV420,
+	DRM_FORMAT_YVU420,
+};
+
+static const u32 rotation_v2_formats[] = {
+	DRM_FORMAT_NV12,
+	/* TODO add formats after validation */
+};
+
+static const uint32_t wb2_formats[] = {
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR565,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_RGBA8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_RGBX8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_RGBA5551,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_RGBX5551,
+	DRM_FORMAT_ARGB4444,
+	DRM_FORMAT_RGBA4444,
+	DRM_FORMAT_RGBX4444,
+	DRM_FORMAT_XRGB4444,
+	DRM_FORMAT_BGR565,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_BGRA8888,
+	DRM_FORMAT_BGRX8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_BGRA5551,
+	DRM_FORMAT_XBGR1555,
+	DRM_FORMAT_BGRX5551,
+	DRM_FORMAT_ABGR4444,
+	DRM_FORMAT_BGRA4444,
+	DRM_FORMAT_BGRX4444,
+	DRM_FORMAT_XBGR4444,
+};
+
+/*************************************************************
+ * DPU sub blocks config
+ *************************************************************/
+/* DPU top level caps */
+static const struct dpu_caps msm8998_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0x7,
+	.qseed_type = DPU_SSPP_SCALER_QSEED3,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V1,
+	.ubwc_version = DPU_HW_UBWC_VER_10,
+	.has_src_split = true,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
+	.has_3d_merge = true,
+	.max_linewidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE,
+	.max_hdeci_exp = MAX_HORZ_DECIMATION,
+	.max_vdeci_exp = MAX_VERT_DECIMATION,
+};
+
+static const struct dpu_caps qcm2290_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0x4,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
+	.max_linewidth = 2160,
+	.pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE,
+};
+
+static const struct dpu_caps sdm845_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0xb,
+	.qseed_type = DPU_SSPP_SCALER_QSEED3,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2,
+	.ubwc_version = DPU_HW_UBWC_VER_20,
+	.has_src_split = true,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
+	.has_3d_merge = true,
+	.max_linewidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE,
+	.max_hdeci_exp = MAX_HORZ_DECIMATION,
+	.max_vdeci_exp = MAX_VERT_DECIMATION,
+};
+
+static const struct dpu_caps sc7180_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0x9,
+	.qseed_type = DPU_SSPP_SCALER_QSEED4,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2,
+	.ubwc_version = DPU_HW_UBWC_VER_20,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
+	.max_linewidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE,
+};
+
+static const struct dpu_caps sm8150_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0xb,
+	.qseed_type = DPU_SSPP_SCALER_QSEED3,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2, /* TODO: v2.5 */
+	.ubwc_version = DPU_HW_UBWC_VER_30,
+	.has_src_split = true,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
+	.has_3d_merge = true,
+	.max_linewidth = 4096,
+	.pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE,
+	.max_hdeci_exp = MAX_HORZ_DECIMATION,
+	.max_vdeci_exp = MAX_VERT_DECIMATION,
+};
+
+static const struct dpu_caps sc8180x_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0xb,
+	.qseed_type = DPU_SSPP_SCALER_QSEED3,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2, /* TODO: v2.5 */
+	.ubwc_version = DPU_HW_UBWC_VER_30,
+	.has_src_split = true,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
+	.has_3d_merge = true,
+	.max_linewidth = 4096,
+	.pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE,
+	.max_hdeci_exp = MAX_HORZ_DECIMATION,
+	.max_vdeci_exp = MAX_VERT_DECIMATION,
+};
+
+static const struct dpu_caps sm8250_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0xb,
+	.qseed_type = DPU_SSPP_SCALER_QSEED4,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2, /* TODO: v2.5 */
+	.ubwc_version = DPU_HW_UBWC_VER_40,
+	.has_src_split = true,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
+	.has_3d_merge = true,
+	.max_linewidth = 4096,
+	.pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE,
+};
+
+static const struct dpu_caps sc7280_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0x7,
+	.qseed_type = DPU_SSPP_SCALER_QSEED4,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2,
+	.ubwc_version = DPU_HW_UBWC_VER_30,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
+	.max_linewidth = 2400,
+	.pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE,
+};
+
+static const struct dpu_mdp_cfg msm8998_mdp[] = {
+	{
+	.name = "top_0", .id = MDP_TOP,
+	.base = 0x0, .len = 0x458,
+	.features = 0,
+	.highest_bank_bit = 0x2,
+	.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
+			.reg_off = 0x2AC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG1] = {
+			.reg_off = 0x2B4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG2] = {
+			.reg_off = 0x2BC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG3] = {
+			.reg_off = 0x2C4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_DMA0] = {
+			.reg_off = 0x2AC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_DMA1] = {
+			.reg_off = 0x2B4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_DMA2] = {
+			.reg_off = 0x2C4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_DMA3] = {
+			.reg_off = 0x2C4, .bit_off = 12},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR0] = {
+			.reg_off = 0x3A8, .bit_off = 15},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR1] = {
+			.reg_off = 0x3B0, .bit_off = 15},
+	},
+};
+
+static const struct dpu_mdp_cfg sdm845_mdp[] = {
+	{
+	.name = "top_0", .id = MDP_TOP,
+	.base = 0x0, .len = 0x45C,
+	.features = BIT(DPU_MDP_AUDIO_SELECT),
+	.highest_bank_bit = 0x2,
+	.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
+			.reg_off = 0x2AC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG1] = {
+			.reg_off = 0x2B4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG2] = {
+			.reg_off = 0x2BC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG3] = {
+			.reg_off = 0x2C4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_DMA0] = {
+			.reg_off = 0x2AC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_DMA1] = {
+			.reg_off = 0x2B4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR0] = {
+			.reg_off = 0x2BC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR1] = {
+			.reg_off = 0x2C4, .bit_off = 8},
+	},
+};
+
+static const struct dpu_mdp_cfg sc7180_mdp[] = {
+	{
+	.name = "top_0", .id = MDP_TOP,
+	.base = 0x0, .len = 0x494,
+	.features = 0,
+	.highest_bank_bit = 0x3,
+	.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
+		.reg_off = 0x2AC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_DMA0] = {
+		.reg_off = 0x2AC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR0] = {
+		.reg_off = 0x2B4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR1] = {
+		.reg_off = 0x2C4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_WB2] = {
+		.reg_off = 0x3B8, .bit_off = 24},
+	},
+};
+
+static const struct dpu_mdp_cfg sc8180x_mdp[] = {
+	{
+	.name = "top_0", .id = MDP_TOP,
+	.base = 0x0, .len = 0x45C,
+	.features = 0,
+	.highest_bank_bit = 0x3,
+	.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
+			.reg_off = 0x2AC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG1] = {
+			.reg_off = 0x2B4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG2] = {
+			.reg_off = 0x2BC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG3] = {
+			.reg_off = 0x2C4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_DMA0] = {
+			.reg_off = 0x2AC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_DMA1] = {
+			.reg_off = 0x2B4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR0] = {
+			.reg_off = 0x2BC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR1] = {
+			.reg_off = 0x2C4, .bit_off = 8},
+	},
+};
+
+static const struct dpu_mdp_cfg sm8250_mdp[] = {
+	{
+	.name = "top_0", .id = MDP_TOP,
+	.base = 0x0, .len = 0x494,
+	.features = 0,
+	.highest_bank_bit = 0x3, /* TODO: 2 for LP_DDR4 */
+	.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
+			.reg_off = 0x2AC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG1] = {
+			.reg_off = 0x2B4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG2] = {
+			.reg_off = 0x2BC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG3] = {
+			.reg_off = 0x2C4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_DMA0] = {
+			.reg_off = 0x2AC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_DMA1] = {
+			.reg_off = 0x2B4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR0] = {
+			.reg_off = 0x2BC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR1] = {
+			.reg_off = 0x2C4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_REG_DMA] = {
+			.reg_off = 0x2BC, .bit_off = 20},
+	.clk_ctrls[DPU_CLK_CTRL_WB2] = {
+			.reg_off = 0x3B8, .bit_off = 24},
+	},
+};
+
+static const struct dpu_mdp_cfg sc7280_mdp[] = {
+	{
+	.name = "top_0", .id = MDP_TOP,
+	.base = 0x0, .len = 0x2014,
+	.highest_bank_bit = 0x1,
+	.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
+		.reg_off = 0x2AC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_DMA0] = {
+		.reg_off = 0x2AC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR0] = {
+		.reg_off = 0x2B4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR1] = {
+		.reg_off = 0x2C4, .bit_off = 8},
+	},
+};
+
+static const struct dpu_mdp_cfg qcm2290_mdp[] = {
+	{
+	.name = "top_0", .id = MDP_TOP,
+	.base = 0x0, .len = 0x494,
+	.features = 0,
+	.highest_bank_bit = 0x2,
+	.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
+		.reg_off = 0x2AC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_DMA0] = {
+		.reg_off = 0x2AC, .bit_off = 8},
+	},
+};
+
+/*************************************************************
+ * CTL sub blocks config
+ *************************************************************/
+static const struct dpu_ctl_cfg msm8998_ctl[] = {
+	{
+	.name = "ctl_0", .id = CTL_0,
+	.base = 0x1000, .len = 0x94,
+	.features = BIT(DPU_CTL_SPLIT_DISPLAY),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9),
+	},
+	{
+	.name = "ctl_1", .id = CTL_1,
+	.base = 0x1200, .len = 0x94,
+	.features = 0,
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10),
+	},
+	{
+	.name = "ctl_2", .id = CTL_2,
+	.base = 0x1400, .len = 0x94,
+	.features = BIT(DPU_CTL_SPLIT_DISPLAY),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 11),
+	},
+	{
+	.name = "ctl_3", .id = CTL_3,
+	.base = 0x1600, .len = 0x94,
+	.features = 0,
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 12),
+	},
+	{
+	.name = "ctl_4", .id = CTL_4,
+	.base = 0x1800, .len = 0x94,
+	.features = 0,
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 13),
+	},
+};
+
+static const struct dpu_ctl_cfg sdm845_ctl[] = {
+	{
+	.name = "ctl_0", .id = CTL_0,
+	.base = 0x1000, .len = 0xE4,
+	.features = BIT(DPU_CTL_SPLIT_DISPLAY),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9),
+	},
+	{
+	.name = "ctl_1", .id = CTL_1,
+	.base = 0x1200, .len = 0xE4,
+	.features = BIT(DPU_CTL_SPLIT_DISPLAY),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10),
+	},
+	{
+	.name = "ctl_2", .id = CTL_2,
+	.base = 0x1400, .len = 0xE4,
+	.features = 0,
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 11),
+	},
+	{
+	.name = "ctl_3", .id = CTL_3,
+	.base = 0x1600, .len = 0xE4,
+	.features = 0,
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 12),
+	},
+	{
+	.name = "ctl_4", .id = CTL_4,
+	.base = 0x1800, .len = 0xE4,
+	.features = 0,
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 13),
+	},
+};
+
+static const struct dpu_ctl_cfg sc7180_ctl[] = {
+	{
+	.name = "ctl_0", .id = CTL_0,
+	.base = 0x1000, .len = 0x1dc,
+	.features = BIT(DPU_CTL_ACTIVE_CFG),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9),
+	},
+	{
+	.name = "ctl_1", .id = CTL_1,
+	.base = 0x1200, .len = 0x1dc,
+	.features = BIT(DPU_CTL_ACTIVE_CFG),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10),
+	},
+	{
+	.name = "ctl_2", .id = CTL_2,
+	.base = 0x1400, .len = 0x1dc,
+	.features = BIT(DPU_CTL_ACTIVE_CFG),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 11),
+	},
+};
+
+static const struct dpu_ctl_cfg sm8150_ctl[] = {
+	{
+	.name = "ctl_0", .id = CTL_0,
+	.base = 0x1000, .len = 0x1e0,
+	.features = BIT(DPU_CTL_ACTIVE_CFG) | BIT(DPU_CTL_SPLIT_DISPLAY),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9),
+	},
+	{
+	.name = "ctl_1", .id = CTL_1,
+	.base = 0x1200, .len = 0x1e0,
+	.features = BIT(DPU_CTL_ACTIVE_CFG) | BIT(DPU_CTL_SPLIT_DISPLAY),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10),
+	},
+	{
+	.name = "ctl_2", .id = CTL_2,
+	.base = 0x1400, .len = 0x1e0,
+	.features = BIT(DPU_CTL_ACTIVE_CFG),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 11),
+	},
+	{
+	.name = "ctl_3", .id = CTL_3,
+	.base = 0x1600, .len = 0x1e0,
+	.features = BIT(DPU_CTL_ACTIVE_CFG),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 12),
+	},
+	{
+	.name = "ctl_4", .id = CTL_4,
+	.base = 0x1800, .len = 0x1e0,
+	.features = BIT(DPU_CTL_ACTIVE_CFG),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 13),
+	},
+	{
+	.name = "ctl_5", .id = CTL_5,
+	.base = 0x1a00, .len = 0x1e0,
+	.features = BIT(DPU_CTL_ACTIVE_CFG),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 23),
+	},
+};
+
+static const struct dpu_ctl_cfg sc7280_ctl[] = {
+	{
+	.name = "ctl_0", .id = CTL_0,
+	.base = 0x15000, .len = 0x1E8,
+	.features = CTL_SC7280_MASK,
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9),
+	},
+	{
+	.name = "ctl_1", .id = CTL_1,
+	.base = 0x16000, .len = 0x1E8,
+	.features = CTL_SC7280_MASK,
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10),
+	},
+	{
+	.name = "ctl_2", .id = CTL_2,
+	.base = 0x17000, .len = 0x1E8,
+	.features = CTL_SC7280_MASK,
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 11),
+	},
+	{
+	.name = "ctl_3", .id = CTL_3,
+	.base = 0x18000, .len = 0x1E8,
+	.features = CTL_SC7280_MASK,
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 12),
+	},
+};
+
+static const struct dpu_ctl_cfg qcm2290_ctl[] = {
+	{
+	.name = "ctl_0", .id = CTL_0,
+	.base = 0x1000, .len = 0x1dc,
+	.features = BIT(DPU_CTL_ACTIVE_CFG),
+	.intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9),
+	},
+};
+
+/*************************************************************
+ * SSPP sub blocks config
+ *************************************************************/
+
+/* SSPP common configuration */
+#define _VIG_SBLK(num, sdma_pri, qseed_ver) \
+	{ \
+	.maxdwnscale = MAX_DOWNSCALE_RATIO, \
+	.maxupscale = MAX_UPSCALE_RATIO, \
+	.smart_dma_priority = sdma_pri, \
+	.src_blk = {.name = STRCAT("sspp_src_", num), \
+		.id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \
+	.scaler_blk = {.name = STRCAT("sspp_scaler", num), \
+		.id = qseed_ver, \
+		.base = 0xa00, .len = 0xa0,}, \
+	.csc_blk = {.name = STRCAT("sspp_csc", num), \
+		.id = DPU_SSPP_CSC_10BIT, \
+		.base = 0x1a00, .len = 0x100,}, \
+	.format_list = plane_formats_yuv, \
+	.num_formats = ARRAY_SIZE(plane_formats_yuv), \
+	.virt_format_list = plane_formats, \
+	.virt_num_formats = ARRAY_SIZE(plane_formats), \
+	.rotation_cfg = NULL, \
+	}
+
+#define _VIG_SBLK_ROT(num, sdma_pri, qseed_ver, rot_cfg) \
+	{ \
+	.maxdwnscale = MAX_DOWNSCALE_RATIO, \
+	.maxupscale = MAX_UPSCALE_RATIO, \
+	.smart_dma_priority = sdma_pri, \
+	.src_blk = {.name = STRCAT("sspp_src_", num), \
+		.id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \
+	.scaler_blk = {.name = STRCAT("sspp_scaler", num), \
+		.id = qseed_ver, \
+		.base = 0xa00, .len = 0xa0,}, \
+	.csc_blk = {.name = STRCAT("sspp_csc", num), \
+		.id = DPU_SSPP_CSC_10BIT, \
+		.base = 0x1a00, .len = 0x100,}, \
+	.format_list = plane_formats_yuv, \
+	.num_formats = ARRAY_SIZE(plane_formats_yuv), \
+	.virt_format_list = plane_formats, \
+	.virt_num_formats = ARRAY_SIZE(plane_formats), \
+	.rotation_cfg = rot_cfg, \
+	}
+
+#define _DMA_SBLK(num, sdma_pri) \
+	{ \
+	.maxdwnscale = SSPP_UNITY_SCALE, \
+	.maxupscale = SSPP_UNITY_SCALE, \
+	.smart_dma_priority = sdma_pri, \
+	.src_blk = {.name = STRCAT("sspp_src_", num), \
+		.id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \
+	.format_list = plane_formats, \
+	.num_formats = ARRAY_SIZE(plane_formats), \
+	.virt_format_list = plane_formats, \
+	.virt_num_formats = ARRAY_SIZE(plane_formats), \
+	}
+
+static const struct dpu_sspp_sub_blks msm8998_vig_sblk_0 =
+				_VIG_SBLK("0", 0, DPU_SSPP_SCALER_QSEED3);
+static const struct dpu_sspp_sub_blks msm8998_vig_sblk_1 =
+				_VIG_SBLK("1", 0, DPU_SSPP_SCALER_QSEED3);
+static const struct dpu_sspp_sub_blks msm8998_vig_sblk_2 =
+				_VIG_SBLK("2", 0, DPU_SSPP_SCALER_QSEED3);
+static const struct dpu_sspp_sub_blks msm8998_vig_sblk_3 =
+				_VIG_SBLK("3", 0, DPU_SSPP_SCALER_QSEED3);
+
+static const struct dpu_rotation_cfg dpu_rot_sc7280_cfg_v2 = {
+	.rot_maxheight = 1088,
+	.rot_num_formats = ARRAY_SIZE(rotation_v2_formats),
+	.rot_format_list = rotation_v2_formats,
+};
+
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_0 =
+				_VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED3);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_1 =
+				_VIG_SBLK("1", 6, DPU_SSPP_SCALER_QSEED3);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_2 =
+				_VIG_SBLK("2", 7, DPU_SSPP_SCALER_QSEED3);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_3 =
+				_VIG_SBLK("3", 8, DPU_SSPP_SCALER_QSEED3);
+
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_0 = _DMA_SBLK("8", 1);
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_1 = _DMA_SBLK("9", 2);
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_2 = _DMA_SBLK("10", 3);
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_3 = _DMA_SBLK("11", 4);
+
+#define SSPP_BLK(_name, _id, _base, _features, \
+		_sblk, _xinid, _type, _clkctrl) \
+	{ \
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x1c8, \
+	.features = _features, \
+	.sblk = &_sblk, \
+	.xin_id = _xinid, \
+	.type = _type, \
+	.clk_ctrl = _clkctrl \
+	}
+
+static const struct dpu_sspp_cfg msm8998_sspp[] = {
+	SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_MSM8998_MASK,
+		msm8998_vig_sblk_0, 0,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0),
+	SSPP_BLK("sspp_1", SSPP_VIG1, 0x6000, VIG_MSM8998_MASK,
+		msm8998_vig_sblk_1, 4,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG1),
+	SSPP_BLK("sspp_2", SSPP_VIG2, 0x8000, VIG_MSM8998_MASK,
+		msm8998_vig_sblk_2, 8, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG2),
+	SSPP_BLK("sspp_3", SSPP_VIG3, 0xa000, VIG_MSM8998_MASK,
+		msm8998_vig_sblk_3, 12,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG3),
+	SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000,  DMA_MSM8998_MASK,
+		sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0),
+	SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000,  DMA_MSM8998_MASK,
+		sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1),
+	SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000,  DMA_CURSOR_MSM8998_MASK,
+		sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA2),
+	SSPP_BLK("sspp_11", SSPP_DMA3, 0x2a000,  DMA_CURSOR_MSM8998_MASK,
+		sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA3),
+};
+
+static const struct dpu_sspp_cfg sdm845_sspp[] = {
+	SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SDM845_MASK,
+		sdm845_vig_sblk_0, 0,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0),
+	SSPP_BLK("sspp_1", SSPP_VIG1, 0x6000, VIG_SDM845_MASK,
+		sdm845_vig_sblk_1, 4,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG1),
+	SSPP_BLK("sspp_2", SSPP_VIG2, 0x8000, VIG_SDM845_MASK,
+		sdm845_vig_sblk_2, 8, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG2),
+	SSPP_BLK("sspp_3", SSPP_VIG3, 0xa000, VIG_SDM845_MASK,
+		sdm845_vig_sblk_3, 12,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG3),
+	SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000,  DMA_SDM845_MASK,
+		sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0),
+	SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000,  DMA_SDM845_MASK,
+		sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1),
+	SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000,  DMA_CURSOR_SDM845_MASK,
+		sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0),
+	SSPP_BLK("sspp_11", SSPP_DMA3, 0x2a000,  DMA_CURSOR_SDM845_MASK,
+		sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1),
+};
+
+static const struct dpu_sspp_sub_blks sc7180_vig_sblk_0 =
+				_VIG_SBLK("0", 4, DPU_SSPP_SCALER_QSEED4);
+
+static const struct dpu_sspp_sub_blks sc7280_vig_sblk_0 =
+			_VIG_SBLK_ROT("0", 4, DPU_SSPP_SCALER_QSEED4, &dpu_rot_sc7280_cfg_v2);
+
+static const struct dpu_sspp_cfg sc7180_sspp[] = {
+	SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SC7180_MASK,
+		sc7180_vig_sblk_0, 0,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0),
+	SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000,  DMA_SDM845_MASK,
+		sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0),
+	SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000,  DMA_CURSOR_SDM845_MASK,
+		sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0),
+	SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000,  DMA_CURSOR_SDM845_MASK,
+		sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1),
+};
+
+static const struct dpu_sspp_sub_blks sm8250_vig_sblk_0 =
+				_VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED4);
+static const struct dpu_sspp_sub_blks sm8250_vig_sblk_1 =
+				_VIG_SBLK("1", 6, DPU_SSPP_SCALER_QSEED4);
+static const struct dpu_sspp_sub_blks sm8250_vig_sblk_2 =
+				_VIG_SBLK("2", 7, DPU_SSPP_SCALER_QSEED4);
+static const struct dpu_sspp_sub_blks sm8250_vig_sblk_3 =
+				_VIG_SBLK("3", 8, DPU_SSPP_SCALER_QSEED4);
+
+static const struct dpu_sspp_cfg sm8250_sspp[] = {
+	SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SC7180_MASK,
+		sm8250_vig_sblk_0, 0,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0),
+	SSPP_BLK("sspp_1", SSPP_VIG1, 0x6000, VIG_SC7180_MASK,
+		sm8250_vig_sblk_1, 4,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG1),
+	SSPP_BLK("sspp_2", SSPP_VIG2, 0x8000, VIG_SC7180_MASK,
+		sm8250_vig_sblk_2, 8, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG2),
+	SSPP_BLK("sspp_3", SSPP_VIG3, 0xa000, VIG_SC7180_MASK,
+		sm8250_vig_sblk_3, 12,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG3),
+	SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000,  DMA_SDM845_MASK,
+		sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0),
+	SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000,  DMA_SDM845_MASK,
+		sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1),
+	SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000,  DMA_CURSOR_SDM845_MASK,
+		sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0),
+	SSPP_BLK("sspp_11", SSPP_DMA3, 0x2a000,  DMA_CURSOR_SDM845_MASK,
+		sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1),
+};
+
+static const struct dpu_sspp_cfg sc7280_sspp[] = {
+	SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SC7280_MASK,
+		sc7280_vig_sblk_0, 0,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0),
+	SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000,  DMA_SDM845_MASK,
+		sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0),
+	SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000,  DMA_CURSOR_SDM845_MASK,
+		sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0),
+	SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000,  DMA_CURSOR_SDM845_MASK,
+		sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1),
+};
+
+
+#define _VIG_SBLK_NOSCALE(num, sdma_pri) \
+	{ \
+	.maxdwnscale = SSPP_UNITY_SCALE, \
+	.maxupscale = SSPP_UNITY_SCALE, \
+	.smart_dma_priority = sdma_pri, \
+	.src_blk = {.name = STRCAT("sspp_src_", num), \
+		.id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \
+	.format_list = plane_formats_yuv, \
+	.num_formats = ARRAY_SIZE(plane_formats_yuv), \
+	.virt_format_list = plane_formats, \
+	.virt_num_formats = ARRAY_SIZE(plane_formats), \
+	}
+
+static const struct dpu_sspp_sub_blks qcm2290_vig_sblk_0 = _VIG_SBLK_NOSCALE("0", 2);
+static const struct dpu_sspp_sub_blks qcm2290_dma_sblk_0 = _DMA_SBLK("8", 1);
+
+static const struct dpu_sspp_cfg qcm2290_sspp[] = {
+	SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_QCM2290_MASK,
+		 qcm2290_vig_sblk_0, 0, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0),
+	SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000,  DMA_SDM845_MASK,
+		 qcm2290_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0),
+};
+
+/*************************************************************
+ * MIXER sub blocks config
+ *************************************************************/
+
+#define LM_BLK(_name, _id, _base, _fmask, _sblk, _pp, _lmpair, _dspp) \
+	{ \
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x320, \
+	.features = _fmask, \
+	.sblk = _sblk, \
+	.pingpong = _pp, \
+	.lm_pair_mask = (1 << _lmpair), \
+	.dspp = _dspp \
+	}
+
+/* MSM8998 */
+
+static const struct dpu_lm_sub_blks msm8998_lm_sblk = {
+	.maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.maxblendstages = 7, /* excluding base layer */
+	.blendstage_base = { /* offsets relative to mixer base */
+		0x20, 0x50, 0x80, 0xb0, 0x230,
+		0x260, 0x290
+	},
+};
+
+static const struct dpu_lm_cfg msm8998_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, MIXER_MSM8998_MASK,
+		&msm8998_lm_sblk, PINGPONG_0, LM_2, DSPP_0),
+	LM_BLK("lm_1", LM_1, 0x45000, MIXER_MSM8998_MASK,
+		&msm8998_lm_sblk, PINGPONG_1, LM_5, DSPP_1),
+	LM_BLK("lm_2", LM_2, 0x46000, MIXER_MSM8998_MASK,
+		&msm8998_lm_sblk, PINGPONG_2, LM_0, 0),
+	LM_BLK("lm_3", LM_3, 0x47000, MIXER_MSM8998_MASK,
+		&msm8998_lm_sblk, PINGPONG_MAX, 0, 0),
+	LM_BLK("lm_4", LM_4, 0x48000, MIXER_MSM8998_MASK,
+		&msm8998_lm_sblk, PINGPONG_MAX, 0, 0),
+	LM_BLK("lm_5", LM_5, 0x49000, MIXER_MSM8998_MASK,
+		&msm8998_lm_sblk, PINGPONG_3, LM_1, 0),
+};
+
+/* SDM845 */
+
+static const struct dpu_lm_sub_blks sdm845_lm_sblk = {
+	.maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.maxblendstages = 11, /* excluding base layer */
+	.blendstage_base = { /* offsets relative to mixer base */
+		0x20, 0x38, 0x50, 0x68, 0x80, 0x98,
+		0xb0, 0xc8, 0xe0, 0xf8, 0x110
+	},
+};
+
+static const struct dpu_lm_cfg sdm845_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_0, LM_1, 0),
+	LM_BLK("lm_1", LM_1, 0x45000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_1, LM_0, 0),
+	LM_BLK("lm_2", LM_2, 0x46000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_2, LM_5, 0),
+	LM_BLK("lm_3", LM_3, 0x0, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_MAX, 0, 0),
+	LM_BLK("lm_4", LM_4, 0x0, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_MAX, 0, 0),
+	LM_BLK("lm_5", LM_5, 0x49000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_3, LM_2, 0),
+};
+
+/* SC7180 */
+
+static const struct dpu_lm_sub_blks sc7180_lm_sblk = {
+	.maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.maxblendstages = 7, /* excluding base layer */
+	.blendstage_base = { /* offsets relative to mixer base */
+		0x20, 0x38, 0x50, 0x68, 0x80, 0x98, 0xb0
+	},
+};
+
+static const struct dpu_lm_cfg sc7180_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, MIXER_SC7180_MASK,
+		&sc7180_lm_sblk, PINGPONG_0, LM_1, DSPP_0),
+	LM_BLK("lm_1", LM_1, 0x45000, MIXER_SC7180_MASK,
+		&sc7180_lm_sblk, PINGPONG_1, LM_0, 0),
+};
+
+/* SM8150 */
+
+static const struct dpu_lm_cfg sm8150_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_0, LM_1, DSPP_0),
+	LM_BLK("lm_1", LM_1, 0x45000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_1, LM_0, DSPP_1),
+	LM_BLK("lm_2", LM_2, 0x46000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_2, LM_3, 0),
+	LM_BLK("lm_3", LM_3, 0x47000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_3, LM_2, 0),
+	LM_BLK("lm_4", LM_4, 0x48000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_4, LM_5, 0),
+	LM_BLK("lm_5", LM_5, 0x49000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_5, LM_4, 0),
+};
+
+static const struct dpu_lm_cfg sc7280_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, MIXER_SC7180_MASK,
+		&sc7180_lm_sblk, PINGPONG_0, 0, DSPP_0),
+	LM_BLK("lm_2", LM_2, 0x46000, MIXER_SC7180_MASK,
+		&sc7180_lm_sblk, PINGPONG_2, LM_3, 0),
+	LM_BLK("lm_3", LM_3, 0x47000, MIXER_SC7180_MASK,
+		&sc7180_lm_sblk, PINGPONG_3, LM_2, 0),
+};
+
+/* QCM2290 */
+
+static const struct dpu_lm_sub_blks qcm2290_lm_sblk = {
+	.maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.maxblendstages = 4, /* excluding base layer */
+	.blendstage_base = { /* offsets relative to mixer base */
+		0x20, 0x38, 0x50, 0x68
+	},
+};
+
+static const struct dpu_lm_cfg qcm2290_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, MIXER_SC7180_MASK,
+		&qcm2290_lm_sblk, PINGPONG_0, 0, DSPP_0),
+};
+
+/*************************************************************
+ * DSPP sub blocks config
+ *************************************************************/
+static const struct dpu_dspp_sub_blks msm8998_dspp_sblk = {
+	.pcc = {.id = DPU_DSPP_PCC, .base = 0x1700,
+		.len = 0x90, .version = 0x10007},
+	.gc = { .id = DPU_DSPP_GC, .base = 0x17c0,
+		.len = 0x90, .version = 0x10007},
+};
+
+static const struct dpu_dspp_sub_blks sc7180_dspp_sblk = {
+	.pcc = {.id = DPU_DSPP_PCC, .base = 0x1700,
+		.len = 0x90, .version = 0x10000},
+};
+
+static const struct dpu_dspp_sub_blks sm8150_dspp_sblk = {
+	.pcc = {.id = DPU_DSPP_PCC, .base = 0x1700,
+		.len = 0x90, .version = 0x40000},
+};
+
+#define DSPP_BLK(_name, _id, _base, _mask, _sblk) \
+		{\
+		.name = _name, .id = _id, \
+		.base = _base, .len = 0x1800, \
+		.features = _mask, \
+		.sblk = _sblk \
+		}
+
+static const struct dpu_dspp_cfg msm8998_dspp[] = {
+	DSPP_BLK("dspp_0", DSPP_0, 0x54000, DSPP_MSM8998_MASK,
+		 &msm8998_dspp_sblk),
+	DSPP_BLK("dspp_1", DSPP_1, 0x56000, DSPP_MSM8998_MASK,
+		 &msm8998_dspp_sblk),
+};
+
+static const struct dpu_dspp_cfg sc7180_dspp[] = {
+	DSPP_BLK("dspp_0", DSPP_0, 0x54000, DSPP_SC7180_MASK,
+		 &sc7180_dspp_sblk),
+};
+
+static const struct dpu_dspp_cfg sm8150_dspp[] = {
+	DSPP_BLK("dspp_0", DSPP_0, 0x54000, DSPP_SC7180_MASK,
+		 &sm8150_dspp_sblk),
+	DSPP_BLK("dspp_1", DSPP_1, 0x56000, DSPP_SC7180_MASK,
+		 &sm8150_dspp_sblk),
+	DSPP_BLK("dspp_2", DSPP_2, 0x58000, DSPP_SC7180_MASK,
+		 &sm8150_dspp_sblk),
+	DSPP_BLK("dspp_3", DSPP_3, 0x5a000, DSPP_SC7180_MASK,
+		 &sm8150_dspp_sblk),
+};
+
+static const struct dpu_dspp_cfg qcm2290_dspp[] = {
+	DSPP_BLK("dspp_0", DSPP_0, 0x54000, DSPP_SC7180_MASK,
+		 &sm8150_dspp_sblk),
+};
+
+/*************************************************************
+ * PINGPONG sub blocks config
+ *************************************************************/
+static const struct dpu_pingpong_sub_blks sdm845_pp_sblk_te = {
+	.te2 = {.id = DPU_PINGPONG_TE2, .base = 0x2000, .len = 0x0,
+		.version = 0x1},
+	.dither = {.id = DPU_PINGPONG_DITHER, .base = 0x30e0,
+		.len = 0x20, .version = 0x10000},
+};
+
+static const struct dpu_pingpong_sub_blks sdm845_pp_sblk = {
+	.dither = {.id = DPU_PINGPONG_DITHER, .base = 0x30e0,
+		.len = 0x20, .version = 0x10000},
+};
+
+static const struct dpu_pingpong_sub_blks sc7280_pp_sblk = {
+	.dither = {.id = DPU_PINGPONG_DITHER, .base = 0xe0,
+	.len = 0x20, .version = 0x20000},
+};
+
+#define PP_BLK_TE(_name, _id, _base, _merge_3d, _sblk, _done, _rdptr) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0xd4, \
+	.features = PINGPONG_SDM845_SPLIT_MASK, \
+	.merge_3d = _merge_3d, \
+	.sblk = &_sblk, \
+	.intr_done = _done, \
+	.intr_rdptr = _rdptr, \
+	}
+#define PP_BLK(_name, _id, _base, _merge_3d, _sblk, _done, _rdptr) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0xd4, \
+	.features = PINGPONG_SDM845_MASK, \
+	.merge_3d = _merge_3d, \
+	.sblk = &_sblk, \
+	.intr_done = _done, \
+	.intr_rdptr = _rdptr, \
+	}
+
+static const struct dpu_pingpong_cfg sdm845_pp[] = {
+	PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk_te,
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)),
+	PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, 0, sdm845_pp_sblk_te,
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)),
+	PP_BLK("pingpong_2", PINGPONG_2, 0x71000, 0, sdm845_pp_sblk,
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10),
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)),
+	PP_BLK("pingpong_3", PINGPONG_3, 0x71800, 0, sdm845_pp_sblk,
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11),
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)),
+};
+
+static struct dpu_pingpong_cfg sc7180_pp[] = {
+	PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk_te, -1, -1),
+	PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, 0, sdm845_pp_sblk_te, -1, -1),
+};
+
+static const struct dpu_pingpong_cfg sm8150_pp[] = {
+	PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te,
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)),
+	PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te,
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)),
+	PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk,
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10),
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)),
+	PP_BLK("pingpong_3", PINGPONG_3, 0x71800, MERGE_3D_1, sdm845_pp_sblk,
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11),
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)),
+	PP_BLK("pingpong_4", PINGPONG_4, 0x72000, MERGE_3D_2, sdm845_pp_sblk,
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30),
+			-1),
+	PP_BLK("pingpong_5", PINGPONG_5, 0x72800, MERGE_3D_2, sdm845_pp_sblk,
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31),
+			-1),
+};
+
+static const struct dpu_pingpong_cfg sc7280_pp[] = {
+	PP_BLK("pingpong_0", PINGPONG_0, 0x69000, 0, sc7280_pp_sblk, -1, -1),
+	PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk, -1, -1),
+	PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk, -1, -1),
+	PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk, -1, -1),
+};
+
+static struct dpu_pingpong_cfg qcm2290_pp[] = {
+	PP_BLK("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk,
+		DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
+		DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)),
+};
+
+/*************************************************************
+ * MERGE_3D sub blocks config
+ *************************************************************/
+#define MERGE_3D_BLK(_name, _id, _base) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x8, \
+	.features = MERGE_3D_SM8150_MASK, \
+	.sblk = NULL \
+	}
+
+static const struct dpu_merge_3d_cfg sm8150_merge_3d[] = {
+	MERGE_3D_BLK("merge_3d_0", MERGE_3D_0, 0x83000),
+	MERGE_3D_BLK("merge_3d_1", MERGE_3D_1, 0x83100),
+	MERGE_3D_BLK("merge_3d_2", MERGE_3D_2, 0x83200),
+};
+
+/*************************************************************
+ * DSC sub blocks config
+ *************************************************************/
+#define DSC_BLK(_name, _id, _base) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x140, \
+	.features = 0, \
+	}
+
+static struct dpu_dsc_cfg sdm845_dsc[] = {
+	DSC_BLK("dsc_0", DSC_0, 0x80000),
+	DSC_BLK("dsc_1", DSC_1, 0x80400),
+	DSC_BLK("dsc_2", DSC_2, 0x80800),
+	DSC_BLK("dsc_3", DSC_3, 0x80c00),
+};
+
+/*************************************************************
+ * INTF sub blocks config
+ *************************************************************/
+#define INTF_BLK(_name, _id, _base, _type, _ctrl_id, _progfetch, _features, _reg, _underrun_bit, _vsync_bit) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x280, \
+	.features = _features, \
+	.type = _type, \
+	.controller_id = _ctrl_id, \
+	.prog_fetch_lines_worst_case = _progfetch, \
+	.intr_underrun = DPU_IRQ_IDX(_reg, _underrun_bit), \
+	.intr_vsync = DPU_IRQ_IDX(_reg, _vsync_bit), \
+	}
+
+static const struct dpu_intf_cfg msm8998_intf[] = {
+	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 24, 25),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 26, 27),
+	INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 28, 29),
+	INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_HDMI, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 30, 31),
+};
+
+static const struct dpu_intf_cfg sdm845_intf[] = {
+	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, 24, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 24, 25),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 26, 27),
+	INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, 24, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 28, 29),
+	INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1, 24, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 30, 31),
+};
+
+static const struct dpu_intf_cfg sc7180_intf[] = {
+	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, MSM_DP_CONTROLLER_0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 24, 25),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 26, 27),
+};
+
+static const struct dpu_intf_cfg sm8150_intf[] = {
+	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 24, 25),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 26, 27),
+	INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 28, 29),
+	INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 30, 31),
+};
+
+static const struct dpu_intf_cfg sc7280_intf[] = {
+	INTF_BLK("intf_0", INTF_0, 0x34000, INTF_DP, MSM_DP_CONTROLLER_0, 24, INTF_SC7280_MASK, MDP_SSPP_TOP0_INTR, 24, 25),
+	INTF_BLK("intf_1", INTF_1, 0x35000, INTF_DSI, 0, 24, INTF_SC7280_MASK, MDP_SSPP_TOP0_INTR, 26, 27),
+	INTF_BLK("intf_5", INTF_5, 0x39000, INTF_DP, MSM_DP_CONTROLLER_1, 24, INTF_SC7280_MASK, MDP_SSPP_TOP0_INTR, 22, 23),
+};
+
+static const struct dpu_intf_cfg sc8180x_intf[] = {
+	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, MSM_DP_CONTROLLER_0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 24, 25),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 26, 27),
+	INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 28, 29),
+	/* INTF_3 is for MST, wired to INTF_DP 0 and 1, use dummy index until this is supported */
+	INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 999, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 30, 31),
+	INTF_BLK("intf_4", INTF_4, 0x6C000, INTF_DP, MSM_DP_CONTROLLER_1, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 20, 21),
+	INTF_BLK("intf_5", INTF_5, 0x6C800, INTF_DP, MSM_DP_CONTROLLER_2, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 22, 23),
+};
+
+static const struct dpu_intf_cfg qcm2290_intf[] = {
+	INTF_BLK("intf_0", INTF_0, 0x00000, INTF_NONE, 0, 0, 0, 0, 0, 0),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 26, 27),
+};
+
+/*************************************************************
+ * Writeback blocks config
+ *************************************************************/
+#define WB_BLK(_name, _id, _base, _features, _clk_ctrl, \
+		__xin_id, vbif_id, _reg, _max_linewidth, _wb_done_bit) \
+	{ \
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x2c8, \
+	.features = _features, \
+	.format_list = wb2_formats, \
+	.num_formats = ARRAY_SIZE(wb2_formats), \
+	.clk_ctrl = _clk_ctrl, \
+	.xin_id = __xin_id, \
+	.vbif_idx = vbif_id, \
+	.maxlinewidth = _max_linewidth, \
+	.intr_wb_done = DPU_IRQ_IDX(_reg, _wb_done_bit) \
+	}
+
+static const struct dpu_wb_cfg sm8250_wb[] = {
+	WB_BLK("wb_2", WB_2, 0x65000, WB_SM8250_MASK, DPU_CLK_CTRL_WB2, 6,
+			VBIF_RT, MDP_SSPP_TOP0_INTR, 4096, 4),
+};
+
+/*************************************************************
+ * VBIF sub blocks config
+ *************************************************************/
+/* VBIF QOS remap */
+static const u32 msm8998_rt_pri_lvl[] = {1, 2, 2, 2};
+static const u32 msm8998_nrt_pri_lvl[] = {1, 1, 1, 1};
+static const u32 sdm845_rt_pri_lvl[] = {3, 3, 4, 4, 5, 5, 6, 6};
+static const u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3};
+
+static const struct dpu_vbif_dynamic_ot_cfg msm8998_ot_rdwr_cfg[] = {
+	{
+		.pps = 1088 * 1920 * 30,
+		.ot_limit = 2,
+	},
+	{
+		.pps = 1088 * 1920 * 60,
+		.ot_limit = 6,
+	},
+	{
+		.pps = 3840 * 2160 * 30,
+		.ot_limit = 16,
+	},
+};
+
+static const struct dpu_vbif_cfg msm8998_vbif[] = {
+	{
+	.name = "vbif_rt", .id = VBIF_RT,
+	.base = 0, .len = 0x1040,
+	.default_ot_rd_limit = 32,
+	.default_ot_wr_limit = 32,
+	.features = BIT(DPU_VBIF_QOS_REMAP) | BIT(DPU_VBIF_QOS_OTLIM),
+	.xin_halt_timeout = 0x4000,
+	.qos_rp_remap_size = 0x20,
+	.dynamic_ot_rd_tbl = {
+		.count = ARRAY_SIZE(msm8998_ot_rdwr_cfg),
+		.cfg = msm8998_ot_rdwr_cfg,
+		},
+	.dynamic_ot_wr_tbl = {
+		.count = ARRAY_SIZE(msm8998_ot_rdwr_cfg),
+		.cfg = msm8998_ot_rdwr_cfg,
+		},
+	.qos_rt_tbl = {
+		.npriority_lvl = ARRAY_SIZE(msm8998_rt_pri_lvl),
+		.priority_lvl = msm8998_rt_pri_lvl,
+		},
+	.qos_nrt_tbl = {
+		.npriority_lvl = ARRAY_SIZE(msm8998_nrt_pri_lvl),
+		.priority_lvl = msm8998_nrt_pri_lvl,
+		},
+	.memtype_count = 14,
+	.memtype = {2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2},
+	},
+};
+
+static const struct dpu_vbif_cfg sdm845_vbif[] = {
+	{
+	.name = "vbif_rt", .id = VBIF_RT,
+	.base = 0, .len = 0x1040,
+	.features = BIT(DPU_VBIF_QOS_REMAP),
+	.xin_halt_timeout = 0x4000,
+	.qos_rp_remap_size = 0x40,
+	.qos_rt_tbl = {
+		.npriority_lvl = ARRAY_SIZE(sdm845_rt_pri_lvl),
+		.priority_lvl = sdm845_rt_pri_lvl,
+		},
+	.qos_nrt_tbl = {
+		.npriority_lvl = ARRAY_SIZE(sdm845_nrt_pri_lvl),
+		.priority_lvl = sdm845_nrt_pri_lvl,
+		},
+	.memtype_count = 14,
+	.memtype = {3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3},
+	},
+};
+
+static const struct dpu_reg_dma_cfg sdm845_regdma = {
+	.base = 0x0, .version = 0x1, .trigger_sel_off = 0x119c
+};
+
+static const struct dpu_reg_dma_cfg sm8150_regdma = {
+	.base = 0x0, .version = 0x00010001, .trigger_sel_off = 0x119c
+};
+
+static const struct dpu_reg_dma_cfg sm8250_regdma = {
+	.base = 0x0,
+	.version = 0x00010002,
+	.trigger_sel_off = 0x119c,
+	.xin_id = 7,
+	.clk_ctrl = DPU_CLK_CTRL_REG_DMA,
+};
+
+/*************************************************************
+ * PERF data config
+ *************************************************************/
+
+/* SSPP QOS LUTs */
+static const struct dpu_qos_lut_entry msm8998_qos_linear[] = {
+	{.fl = 4,  .lut = 0x1b},
+	{.fl = 5,  .lut = 0x5b},
+	{.fl = 6,  .lut = 0x15b},
+	{.fl = 7,  .lut = 0x55b},
+	{.fl = 8,  .lut = 0x155b},
+	{.fl = 9,  .lut = 0x555b},
+	{.fl = 10, .lut = 0x1555b},
+	{.fl = 11, .lut = 0x5555b},
+	{.fl = 12, .lut = 0x15555b},
+	{.fl = 13, .lut = 0x55555b},
+	{.fl = 14, .lut = 0},
+	{.fl = 1,  .lut = 0x1b},
+	{.fl = 0,  .lut = 0}
+};
+
+static const struct dpu_qos_lut_entry sdm845_qos_linear[] = {
+	{.fl = 4, .lut = 0x357},
+	{.fl = 5, .lut = 0x3357},
+	{.fl = 6, .lut = 0x23357},
+	{.fl = 7, .lut = 0x223357},
+	{.fl = 8, .lut = 0x2223357},
+	{.fl = 9, .lut = 0x22223357},
+	{.fl = 10, .lut = 0x222223357},
+	{.fl = 11, .lut = 0x2222223357},
+	{.fl = 12, .lut = 0x22222223357},
+	{.fl = 13, .lut = 0x222222223357},
+	{.fl = 14, .lut = 0x1222222223357},
+	{.fl = 0, .lut = 0x11222222223357}
+};
+
+static const struct dpu_qos_lut_entry msm8998_qos_macrotile[] = {
+	{.fl = 10, .lut = 0x1aaff},
+	{.fl = 11, .lut = 0x5aaff},
+	{.fl = 12, .lut = 0x15aaff},
+	{.fl = 13, .lut = 0x55aaff},
+	{.fl = 1,  .lut = 0x1aaff},
+	{.fl = 0,  .lut = 0},
+};
+
+static const struct dpu_qos_lut_entry sc7180_qos_linear[] = {
+	{.fl = 0, .lut = 0x0011222222335777},
+};
+
+static const struct dpu_qos_lut_entry sm8150_qos_linear[] = {
+	{.fl = 0, .lut = 0x0011222222223357 },
+};
+
+static const struct dpu_qos_lut_entry sc8180x_qos_linear[] = {
+	{.fl = 4, .lut = 0x0000000000000357 },
+};
+
+static const struct dpu_qos_lut_entry qcm2290_qos_linear[] = {
+	{.fl = 0, .lut = 0x0011222222335777},
+};
+
+static const struct dpu_qos_lut_entry sdm845_qos_macrotile[] = {
+	{.fl = 10, .lut = 0x344556677},
+	{.fl = 11, .lut = 0x3344556677},
+	{.fl = 12, .lut = 0x23344556677},
+	{.fl = 13, .lut = 0x223344556677},
+	{.fl = 14, .lut = 0x1223344556677},
+	{.fl = 0, .lut = 0x112233344556677},
+};
+
+static const struct dpu_qos_lut_entry sc7180_qos_macrotile[] = {
+	{.fl = 0, .lut = 0x0011223344556677},
+};
+
+static const struct dpu_qos_lut_entry sc8180x_qos_macrotile[] = {
+	{.fl = 10, .lut = 0x0000000344556677},
+};
+
+static const struct dpu_qos_lut_entry msm8998_qos_nrt[] = {
+	{.fl = 0, .lut = 0x0},
+};
+
+static const struct dpu_qos_lut_entry sdm845_qos_nrt[] = {
+	{.fl = 0, .lut = 0x0},
+};
+
+static const struct dpu_qos_lut_entry sc7180_qos_nrt[] = {
+	{.fl = 0, .lut = 0x0},
+};
+
+static const struct dpu_perf_cfg msm8998_perf_data = {
+	.max_bw_low = 6700000,
+	.max_bw_high = 6700000,
+	.min_core_ib = 2400000,
+	.min_llcc_ib = 800000,
+	.min_dram_ib = 800000,
+	.undersized_prefill_lines = 2,
+	.xtra_prefill_lines = 2,
+	.dest_scale_prefill_lines = 3,
+	.macrotile_prefill_lines = 4,
+	.yuv_nv12_prefill_lines = 8,
+	.linear_prefill_lines = 1,
+	.downscaling_prefill_lines = 1,
+	.amortizable_threshold = 25,
+	.min_prefill_lines = 25,
+	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.safe_lut_tbl = {0xfffc, 0xff00, 0xffff},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(msm8998_qos_linear),
+		.entries = msm8998_qos_linear
+		},
+		{.nentry = ARRAY_SIZE(msm8998_qos_macrotile),
+		.entries = msm8998_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(msm8998_qos_nrt),
+		.entries = msm8998_qos_nrt
+		},
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+	.clk_inefficiency_factor = 200,
+	.bw_inefficiency_factor = 120,
+};
+
+static const struct dpu_perf_cfg sdm845_perf_data = {
+	.max_bw_low = 6800000,
+	.max_bw_high = 6800000,
+	.min_core_ib = 2400000,
+	.min_llcc_ib = 800000,
+	.min_dram_ib = 800000,
+	.undersized_prefill_lines = 2,
+	.xtra_prefill_lines = 2,
+	.dest_scale_prefill_lines = 3,
+	.macrotile_prefill_lines = 4,
+	.yuv_nv12_prefill_lines = 8,
+	.linear_prefill_lines = 1,
+	.downscaling_prefill_lines = 1,
+	.amortizable_threshold = 25,
+	.min_prefill_lines = 24,
+	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.safe_lut_tbl = {0xfff0, 0xf000, 0xffff},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(sdm845_qos_linear),
+		.entries = sdm845_qos_linear
+		},
+		{.nentry = ARRAY_SIZE(sdm845_qos_macrotile),
+		.entries = sdm845_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(sdm845_qos_nrt),
+		.entries = sdm845_qos_nrt
+		},
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+	.clk_inefficiency_factor = 105,
+	.bw_inefficiency_factor = 120,
+};
+
+static const struct dpu_perf_cfg sc7180_perf_data = {
+	.max_bw_low = 6800000,
+	.max_bw_high = 6800000,
+	.min_core_ib = 2400000,
+	.min_llcc_ib = 800000,
+	.min_dram_ib = 1600000,
+	.min_prefill_lines = 24,
+	.danger_lut_tbl = {0xff, 0xffff, 0x0},
+	.safe_lut_tbl = {0xfff0, 0xff00, 0xffff},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(sc7180_qos_linear),
+		.entries = sc7180_qos_linear
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_macrotile),
+		.entries = sc7180_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_nrt),
+		.entries = sc7180_qos_nrt
+		},
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+	.clk_inefficiency_factor = 105,
+	.bw_inefficiency_factor = 120,
+};
+
+static const struct dpu_perf_cfg sm8150_perf_data = {
+	.max_bw_low = 12800000,
+	.max_bw_high = 12800000,
+	.min_core_ib = 2400000,
+	.min_llcc_ib = 800000,
+	.min_dram_ib = 800000,
+	.min_prefill_lines = 24,
+	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.safe_lut_tbl = {0xfff8, 0xf000, 0xffff},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(sm8150_qos_linear),
+		.entries = sm8150_qos_linear
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_macrotile),
+		.entries = sc7180_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_nrt),
+		.entries = sc7180_qos_nrt
+		},
+		/* TODO: macrotile-qseed is different from macrotile */
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+	.clk_inefficiency_factor = 105,
+	.bw_inefficiency_factor = 120,
+};
+
+static const struct dpu_perf_cfg sc8180x_perf_data = {
+	.max_bw_low = 9600000,
+	.max_bw_high = 9600000,
+	.min_core_ib = 2400000,
+	.min_llcc_ib = 800000,
+	.min_dram_ib = 800000,
+	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(sc8180x_qos_linear),
+		.entries = sc8180x_qos_linear
+		},
+		{.nentry = ARRAY_SIZE(sc8180x_qos_macrotile),
+		.entries = sc8180x_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_nrt),
+		.entries = sc7180_qos_nrt
+		},
+		/* TODO: macrotile-qseed is different from macrotile */
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+	.clk_inefficiency_factor = 105,
+	.bw_inefficiency_factor = 120,
+};
+
+static const struct dpu_perf_cfg sm8250_perf_data = {
+	.max_bw_low = 13700000,
+	.max_bw_high = 16600000,
+	.min_core_ib = 4800000,
+	.min_llcc_ib = 0,
+	.min_dram_ib = 800000,
+	.min_prefill_lines = 35,
+	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.safe_lut_tbl = {0xfff0, 0xff00, 0xffff},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(sc7180_qos_linear),
+		.entries = sc7180_qos_linear
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_macrotile),
+		.entries = sc7180_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_nrt),
+		.entries = sc7180_qos_nrt
+		},
+		/* TODO: macrotile-qseed is different from macrotile */
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+	.clk_inefficiency_factor = 105,
+	.bw_inefficiency_factor = 120,
+};
+
+static const struct dpu_perf_cfg sc7280_perf_data = {
+	.max_bw_low = 4700000,
+	.max_bw_high = 8800000,
+	.min_core_ib = 2500000,
+	.min_llcc_ib = 0,
+	.min_dram_ib = 1600000,
+	.min_prefill_lines = 24,
+	.danger_lut_tbl = {0xffff, 0xffff, 0x0},
+	.safe_lut_tbl = {0xff00, 0xff00, 0xffff},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(sc7180_qos_macrotile),
+		.entries = sc7180_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_macrotile),
+		.entries = sc7180_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_nrt),
+		.entries = sc7180_qos_nrt
+		},
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+	.clk_inefficiency_factor = 105,
+	.bw_inefficiency_factor = 120,
+};
+
+static const struct dpu_perf_cfg qcm2290_perf_data = {
+	.max_bw_low = 2700000,
+	.max_bw_high = 2700000,
+	.min_core_ib = 1300000,
+	.min_llcc_ib = 0,
+	.min_dram_ib = 1600000,
+	.min_prefill_lines = 24,
+	.danger_lut_tbl = {0xff, 0x0, 0x0},
+	.safe_lut_tbl = {0xfff0, 0x0, 0x0},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(qcm2290_qos_linear),
+		.entries = qcm2290_qos_linear
+		},
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+	.clk_inefficiency_factor = 105,
+	.bw_inefficiency_factor = 120,
+};
+/*************************************************************
+ * Hardware catalog
+ *************************************************************/
+
+static const struct dpu_mdss_cfg msm8998_dpu_cfg = {
+	.caps = &msm8998_dpu_caps,
+	.mdp_count = ARRAY_SIZE(msm8998_mdp),
+	.mdp = msm8998_mdp,
+	.ctl_count = ARRAY_SIZE(msm8998_ctl),
+	.ctl = msm8998_ctl,
+	.sspp_count = ARRAY_SIZE(msm8998_sspp),
+	.sspp = msm8998_sspp,
+	.mixer_count = ARRAY_SIZE(msm8998_lm),
+	.mixer = msm8998_lm,
+	.dspp_count = ARRAY_SIZE(msm8998_dspp),
+	.dspp = msm8998_dspp,
+	.pingpong_count = ARRAY_SIZE(sdm845_pp),
+	.pingpong = sdm845_pp,
+	.intf_count = ARRAY_SIZE(msm8998_intf),
+	.intf = msm8998_intf,
+	.vbif_count = ARRAY_SIZE(msm8998_vbif),
+	.vbif = msm8998_vbif,
+	.reg_dma_count = 0,
+	.perf = &msm8998_perf_data,
+	.mdss_irqs = IRQ_SM8250_MASK,
+};
+
+static const struct dpu_mdss_cfg sdm845_dpu_cfg = {
+	.caps = &sdm845_dpu_caps,
+	.mdp_count = ARRAY_SIZE(sdm845_mdp),
+	.mdp = sdm845_mdp,
+	.ctl_count = ARRAY_SIZE(sdm845_ctl),
+	.ctl = sdm845_ctl,
+	.sspp_count = ARRAY_SIZE(sdm845_sspp),
+	.sspp = sdm845_sspp,
+	.mixer_count = ARRAY_SIZE(sdm845_lm),
+	.mixer = sdm845_lm,
+	.pingpong_count = ARRAY_SIZE(sdm845_pp),
+	.pingpong = sdm845_pp,
+	.dsc_count = ARRAY_SIZE(sdm845_dsc),
+	.dsc = sdm845_dsc,
+	.intf_count = ARRAY_SIZE(sdm845_intf),
+	.intf = sdm845_intf,
+	.vbif_count = ARRAY_SIZE(sdm845_vbif),
+	.vbif = sdm845_vbif,
+	.reg_dma_count = 1,
+	.dma_cfg = &sdm845_regdma,
+	.perf = &sdm845_perf_data,
+	.mdss_irqs = IRQ_SDM845_MASK,
+};
+
+static const struct dpu_mdss_cfg sc7180_dpu_cfg = {
+	.caps = &sc7180_dpu_caps,
+	.mdp_count = ARRAY_SIZE(sc7180_mdp),
+	.mdp = sc7180_mdp,
+	.ctl_count = ARRAY_SIZE(sc7180_ctl),
+	.ctl = sc7180_ctl,
+	.sspp_count = ARRAY_SIZE(sc7180_sspp),
+	.sspp = sc7180_sspp,
+	.mixer_count = ARRAY_SIZE(sc7180_lm),
+	.mixer = sc7180_lm,
+	.dspp_count = ARRAY_SIZE(sc7180_dspp),
+	.dspp = sc7180_dspp,
+	.pingpong_count = ARRAY_SIZE(sc7180_pp),
+	.pingpong = sc7180_pp,
+	.intf_count = ARRAY_SIZE(sc7180_intf),
+	.intf = sc7180_intf,
+	.wb_count = ARRAY_SIZE(sm8250_wb),
+	.wb = sm8250_wb,
+	.vbif_count = ARRAY_SIZE(sdm845_vbif),
+	.vbif = sdm845_vbif,
+	.reg_dma_count = 1,
+	.dma_cfg = &sdm845_regdma,
+	.perf = &sc7180_perf_data,
+	.mdss_irqs = IRQ_SC7180_MASK,
+};
+
+static const struct dpu_mdss_cfg sm8150_dpu_cfg = {
+	.caps = &sm8150_dpu_caps,
+	.mdp_count = ARRAY_SIZE(sdm845_mdp),
+	.mdp = sdm845_mdp,
+	.ctl_count = ARRAY_SIZE(sm8150_ctl),
+	.ctl = sm8150_ctl,
+	.sspp_count = ARRAY_SIZE(sdm845_sspp),
+	.sspp = sdm845_sspp,
+	.mixer_count = ARRAY_SIZE(sm8150_lm),
+	.mixer = sm8150_lm,
+	.dspp_count = ARRAY_SIZE(sm8150_dspp),
+	.dspp = sm8150_dspp,
+	.pingpong_count = ARRAY_SIZE(sm8150_pp),
+	.pingpong = sm8150_pp,
+	.merge_3d_count = ARRAY_SIZE(sm8150_merge_3d),
+	.merge_3d = sm8150_merge_3d,
+	.intf_count = ARRAY_SIZE(sm8150_intf),
+	.intf = sm8150_intf,
+	.vbif_count = ARRAY_SIZE(sdm845_vbif),
+	.vbif = sdm845_vbif,
+	.reg_dma_count = 1,
+	.dma_cfg = &sm8150_regdma,
+	.perf = &sm8150_perf_data,
+	.mdss_irqs = IRQ_SDM845_MASK,
+};
+
+static const struct dpu_mdss_cfg sc8180x_dpu_cfg = {
+	.caps = &sc8180x_dpu_caps,
+	.mdp_count = ARRAY_SIZE(sc8180x_mdp),
+	.mdp = sc8180x_mdp,
+	.ctl_count = ARRAY_SIZE(sm8150_ctl),
+	.ctl = sm8150_ctl,
+	.sspp_count = ARRAY_SIZE(sdm845_sspp),
+	.sspp = sdm845_sspp,
+	.mixer_count = ARRAY_SIZE(sm8150_lm),
+	.mixer = sm8150_lm,
+	.pingpong_count = ARRAY_SIZE(sm8150_pp),
+	.pingpong = sm8150_pp,
+	.merge_3d_count = ARRAY_SIZE(sm8150_merge_3d),
+	.merge_3d = sm8150_merge_3d,
+	.intf_count = ARRAY_SIZE(sc8180x_intf),
+	.intf = sc8180x_intf,
+	.vbif_count = ARRAY_SIZE(sdm845_vbif),
+	.vbif = sdm845_vbif,
+	.reg_dma_count = 1,
+	.dma_cfg = &sm8150_regdma,
+	.perf = &sc8180x_perf_data,
+	.mdss_irqs = IRQ_SC8180X_MASK,
+};
+
+static const struct dpu_mdss_cfg sm8250_dpu_cfg = {
+	.caps = &sm8250_dpu_caps,
+	.mdp_count = ARRAY_SIZE(sm8250_mdp),
+	.mdp = sm8250_mdp,
+	.ctl_count = ARRAY_SIZE(sm8150_ctl),
+	.ctl = sm8150_ctl,
+	.sspp_count = ARRAY_SIZE(sm8250_sspp),
+	.sspp = sm8250_sspp,
+	.mixer_count = ARRAY_SIZE(sm8150_lm),
+	.mixer = sm8150_lm,
+	.dspp_count = ARRAY_SIZE(sm8150_dspp),
+	.dspp = sm8150_dspp,
+	.pingpong_count = ARRAY_SIZE(sm8150_pp),
+	.pingpong = sm8150_pp,
+	.merge_3d_count = ARRAY_SIZE(sm8150_merge_3d),
+	.merge_3d = sm8150_merge_3d,
+	.intf_count = ARRAY_SIZE(sm8150_intf),
+	.intf = sm8150_intf,
+	.vbif_count = ARRAY_SIZE(sdm845_vbif),
+	.vbif = sdm845_vbif,
+	.wb_count = ARRAY_SIZE(sm8250_wb),
+	.wb = sm8250_wb,
+	.reg_dma_count = 1,
+	.dma_cfg = &sm8250_regdma,
+	.perf = &sm8250_perf_data,
+	.mdss_irqs = IRQ_SM8250_MASK,
+};
+
+static const struct dpu_mdss_cfg sc7280_dpu_cfg = {
+	.caps = &sc7280_dpu_caps,
+	.mdp_count = ARRAY_SIZE(sc7280_mdp),
+	.mdp = sc7280_mdp,
+	.ctl_count = ARRAY_SIZE(sc7280_ctl),
+	.ctl = sc7280_ctl,
+	.sspp_count = ARRAY_SIZE(sc7280_sspp),
+	.sspp = sc7280_sspp,
+	.dspp_count = ARRAY_SIZE(sc7180_dspp),
+	.dspp = sc7180_dspp,
+	.mixer_count = ARRAY_SIZE(sc7280_lm),
+	.mixer = sc7280_lm,
+	.pingpong_count = ARRAY_SIZE(sc7280_pp),
+	.pingpong = sc7280_pp,
+	.intf_count = ARRAY_SIZE(sc7280_intf),
+	.intf = sc7280_intf,
+	.vbif_count = ARRAY_SIZE(sdm845_vbif),
+	.vbif = sdm845_vbif,
+	.perf = &sc7280_perf_data,
+	.mdss_irqs = IRQ_SC7280_MASK,
+};
+
+static const struct dpu_mdss_cfg qcm2290_dpu_cfg = {
+	.caps = &qcm2290_dpu_caps,
+	.mdp_count = ARRAY_SIZE(qcm2290_mdp),
+	.mdp = qcm2290_mdp,
+	.ctl_count = ARRAY_SIZE(qcm2290_ctl),
+	.ctl = qcm2290_ctl,
+	.sspp_count = ARRAY_SIZE(qcm2290_sspp),
+	.sspp = qcm2290_sspp,
+	.mixer_count = ARRAY_SIZE(qcm2290_lm),
+	.mixer = qcm2290_lm,
+	.dspp_count = ARRAY_SIZE(qcm2290_dspp),
+	.dspp = qcm2290_dspp,
+	.pingpong_count = ARRAY_SIZE(qcm2290_pp),
+	.pingpong = qcm2290_pp,
+	.intf_count = ARRAY_SIZE(qcm2290_intf),
+	.intf = qcm2290_intf,
+	.vbif_count = ARRAY_SIZE(sdm845_vbif),
+	.vbif = sdm845_vbif,
+	.perf = &qcm2290_perf_data,
+	.mdss_irqs = IRQ_SC7180_MASK,
+};
+
+static const struct dpu_mdss_hw_cfg_handler cfg_handler[] = {
+	{ .hw_rev = DPU_HW_VER_300, .dpu_cfg = &msm8998_dpu_cfg},
+	{ .hw_rev = DPU_HW_VER_301, .dpu_cfg = &msm8998_dpu_cfg},
+	{ .hw_rev = DPU_HW_VER_400, .dpu_cfg = &sdm845_dpu_cfg},
+	{ .hw_rev = DPU_HW_VER_401, .dpu_cfg = &sdm845_dpu_cfg},
+	{ .hw_rev = DPU_HW_VER_500, .dpu_cfg = &sm8150_dpu_cfg},
+	{ .hw_rev = DPU_HW_VER_501, .dpu_cfg = &sm8150_dpu_cfg},
+	{ .hw_rev = DPU_HW_VER_510, .dpu_cfg = &sc8180x_dpu_cfg},
+	{ .hw_rev = DPU_HW_VER_600, .dpu_cfg = &sm8250_dpu_cfg},
+	{ .hw_rev = DPU_HW_VER_620, .dpu_cfg = &sc7180_dpu_cfg},
+	{ .hw_rev = DPU_HW_VER_650, .dpu_cfg = &qcm2290_dpu_cfg},
+	{ .hw_rev = DPU_HW_VER_720, .dpu_cfg = &sc7280_dpu_cfg},
+};
+
+const struct dpu_mdss_cfg *dpu_hw_catalog_init(u32 hw_rev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cfg_handler); i++) {
+		if (cfg_handler[i].hw_rev == hw_rev)
+			return cfg_handler[i].dpu_cfg;
+	}
+
+	DPU_ERROR("unsupported chipset id:%X\n", hw_rev);
+
+	return ERR_PTR(-ENODEV);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
new file mode 100644
index 000000000..77c46ce5a
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
@@ -0,0 +1,895 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022. Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2015-2018, 2020 The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HW_CATALOG_H
+#define _DPU_HW_CATALOG_H
+
+#include <linux/kernel.h>
+#include <linux/bug.h>
+#include <linux/bitmap.h>
+#include <linux/err.h>
+
+/**
+ * Max hardware block count: For ex: max 12 SSPP pipes or
+ * 5 ctl paths. In all cases, it can have max 12 hardware blocks
+ * based on current design
+ */
+#define MAX_BLOCKS    12
+
+#define DPU_HW_VER(MAJOR, MINOR, STEP) (((MAJOR & 0xF) << 28)    |\
+		((MINOR & 0xFFF) << 16)  |\
+		(STEP & 0xFFFF))
+
+#define DPU_HW_MAJOR(rev)		((rev) >> 28)
+#define DPU_HW_MINOR(rev)		(((rev) >> 16) & 0xFFF)
+#define DPU_HW_STEP(rev)		((rev) & 0xFFFF)
+#define DPU_HW_MAJOR_MINOR(rev)		((rev) >> 16)
+
+#define IS_DPU_MAJOR_MINOR_SAME(rev1, rev2)   \
+	(DPU_HW_MAJOR_MINOR((rev1)) == DPU_HW_MAJOR_MINOR((rev2)))
+
+#define DPU_HW_VER_170	DPU_HW_VER(1, 7, 0) /* 8996 v1.0 */
+#define DPU_HW_VER_171	DPU_HW_VER(1, 7, 1) /* 8996 v2.0 */
+#define DPU_HW_VER_172	DPU_HW_VER(1, 7, 2) /* 8996 v3.0 */
+#define DPU_HW_VER_300	DPU_HW_VER(3, 0, 0) /* 8998 v1.0 */
+#define DPU_HW_VER_301	DPU_HW_VER(3, 0, 1) /* 8998 v1.1 */
+#define DPU_HW_VER_400	DPU_HW_VER(4, 0, 0) /* sdm845 v1.0 */
+#define DPU_HW_VER_401	DPU_HW_VER(4, 0, 1) /* sdm845 v2.0 */
+#define DPU_HW_VER_410	DPU_HW_VER(4, 1, 0) /* sdm670 v1.0 */
+#define DPU_HW_VER_500	DPU_HW_VER(5, 0, 0) /* sm8150 v1.0 */
+#define DPU_HW_VER_501	DPU_HW_VER(5, 0, 1) /* sm8150 v2.0 */
+#define DPU_HW_VER_510	DPU_HW_VER(5, 1, 1) /* sc8180 */
+#define DPU_HW_VER_600	DPU_HW_VER(6, 0, 0) /* sm8250 */
+#define DPU_HW_VER_620	DPU_HW_VER(6, 2, 0) /* sc7180 v1.0 */
+#define DPU_HW_VER_650	DPU_HW_VER(6, 5, 0) /* qcm2290|sm4125 */
+#define DPU_HW_VER_720	DPU_HW_VER(7, 2, 0) /* sc7280 */
+
+#define IS_MSM8996_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_170)
+#define IS_MSM8998_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_300)
+#define IS_SDM845_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_400)
+#define IS_SDM670_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_410)
+#define IS_SDM855_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_500)
+#define IS_SC7180_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_620)
+#define IS_SC7280_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_720)
+
+#define DPU_HW_BLK_NAME_LEN	16
+
+#define MAX_IMG_WIDTH 0x3fff
+#define MAX_IMG_HEIGHT 0x3fff
+
+#define CRTC_DUAL_MIXERS	2
+
+#define MAX_XIN_COUNT 16
+
+/**
+ * Supported UBWC feature versions
+ */
+enum {
+	DPU_HW_UBWC_VER_10 = 0x100,
+	DPU_HW_UBWC_VER_20 = 0x200,
+	DPU_HW_UBWC_VER_30 = 0x300,
+	DPU_HW_UBWC_VER_40 = 0x400,
+};
+
+/**
+ * MDP TOP BLOCK features
+ * @DPU_MDP_PANIC_PER_PIPE Panic configuration needs to be done per pipe
+ * @DPU_MDP_10BIT_SUPPORT, Chipset supports 10 bit pixel formats
+ * @DPU_MDP_BWC,           MDSS HW supports Bandwidth compression.
+ * @DPU_MDP_UBWC_1_0,      This chipsets supports Universal Bandwidth
+ *                         compression initial revision
+ * @DPU_MDP_UBWC_1_5,      Universal Bandwidth compression version 1.5
+ * @DPU_MDP_MAX            Maximum value
+
+ */
+enum {
+	DPU_MDP_PANIC_PER_PIPE = 0x1,
+	DPU_MDP_10BIT_SUPPORT,
+	DPU_MDP_BWC,
+	DPU_MDP_UBWC_1_0,
+	DPU_MDP_UBWC_1_5,
+	DPU_MDP_AUDIO_SELECT,
+	DPU_MDP_MAX
+};
+
+/**
+ * SSPP sub-blocks/features
+ * @DPU_SSPP_SRC             Src and fetch part of the pipes,
+ * @DPU_SSPP_SCALER_QSEED2,  QSEED2 algorithm support
+ * @DPU_SSPP_SCALER_QSEED3,  QSEED3 alogorithm support
+ * @DPU_SSPP_SCALER_QSEED3LITE,  QSEED3 Lite alogorithm support
+ * @DPU_SSPP_SCALER_QSEED4,  QSEED4 algorithm support
+ * @DPU_SSPP_SCALER_RGB,     RGB Scaler, supported by RGB pipes
+ * @DPU_SSPP_CSC,            Support of Color space converion
+ * @DPU_SSPP_CSC_10BIT,      Support of 10-bit Color space conversion
+ * @DPU_SSPP_CURSOR,         SSPP can be used as a cursor layer
+ * @DPU_SSPP_QOS,            SSPP support QoS control, danger/safe/creq
+ * @DPU_SSPP_QOS_8LVL,       SSPP support 8-level QoS control
+ * @DPU_SSPP_EXCL_RECT,      SSPP supports exclusion rect
+ * @DPU_SSPP_SMART_DMA_V1,   SmartDMA 1.0 support
+ * @DPU_SSPP_SMART_DMA_V2,   SmartDMA 2.0 support
+ * @DPU_SSPP_TS_PREFILL      Supports prefill with traffic shaper
+ * @DPU_SSPP_TS_PREFILL_REC1 Supports prefill with traffic shaper multirec
+ * @DPU_SSPP_CDP             Supports client driven prefetch
+ * @DPU_SSPP_INLINE_ROTATION Support inline rotation
+ * @DPU_SSPP_MAX             maximum value
+ */
+enum {
+	DPU_SSPP_SRC = 0x1,
+	DPU_SSPP_SCALER_QSEED2,
+	DPU_SSPP_SCALER_QSEED3,
+	DPU_SSPP_SCALER_QSEED3LITE,
+	DPU_SSPP_SCALER_QSEED4,
+	DPU_SSPP_SCALER_RGB,
+	DPU_SSPP_CSC,
+	DPU_SSPP_CSC_10BIT,
+	DPU_SSPP_CURSOR,
+	DPU_SSPP_QOS,
+	DPU_SSPP_QOS_8LVL,
+	DPU_SSPP_EXCL_RECT,
+	DPU_SSPP_SMART_DMA_V1,
+	DPU_SSPP_SMART_DMA_V2,
+	DPU_SSPP_TS_PREFILL,
+	DPU_SSPP_TS_PREFILL_REC1,
+	DPU_SSPP_CDP,
+	DPU_SSPP_INLINE_ROTATION,
+	DPU_SSPP_MAX
+};
+
+/*
+ * MIXER sub-blocks/features
+ * @DPU_MIXER_LAYER           Layer mixer layer blend configuration,
+ * @DPU_MIXER_SOURCESPLIT     Layer mixer supports source-split configuration
+ * @DPU_MIXER_GC              Gamma correction block
+ * @DPU_DIM_LAYER             Layer mixer supports dim layer
+ * @DPU_MIXER_COMBINED_ALPHA  Layer mixer has combined alpha register
+ * @DPU_MIXER_MAX             maximum value
+ */
+enum {
+	DPU_MIXER_LAYER = 0x1,
+	DPU_MIXER_SOURCESPLIT,
+	DPU_MIXER_GC,
+	DPU_DIM_LAYER,
+	DPU_MIXER_COMBINED_ALPHA,
+	DPU_MIXER_MAX
+};
+
+/**
+ * DSPP sub-blocks
+ * @DPU_DSPP_PCC             Panel color correction block
+ * @DPU_DSPP_GC              Gamma correction block
+ */
+enum {
+	DPU_DSPP_PCC = 0x1,
+	DPU_DSPP_GC,
+	DPU_DSPP_MAX
+};
+
+/**
+ * PINGPONG sub-blocks
+ * @DPU_PINGPONG_TE         Tear check block
+ * @DPU_PINGPONG_TE2        Additional tear check block for split pipes
+ * @DPU_PINGPONG_SPLIT      PP block supports split fifo
+ * @DPU_PINGPONG_SLAVE      PP block is a suitable slave for split fifo
+ * @DPU_PINGPONG_DITHER,    Dither blocks
+ * @DPU_PINGPONG_MAX
+ */
+enum {
+	DPU_PINGPONG_TE = 0x1,
+	DPU_PINGPONG_TE2,
+	DPU_PINGPONG_SPLIT,
+	DPU_PINGPONG_SLAVE,
+	DPU_PINGPONG_DITHER,
+	DPU_PINGPONG_MAX
+};
+
+/**
+ * CTL sub-blocks
+ * @DPU_CTL_SPLIT_DISPLAY:	CTL supports video mode split display
+ * @DPU_CTL_FETCH_ACTIVE:	Active CTL for fetch HW (SSPPs)
+ * @DPU_CTL_VM_CFG:		CTL config to support multiple VMs
+ * @DPU_CTL_MAX
+ */
+enum {
+	DPU_CTL_SPLIT_DISPLAY = 0x1,
+	DPU_CTL_ACTIVE_CFG,
+	DPU_CTL_FETCH_ACTIVE,
+	DPU_CTL_VM_CFG,
+	DPU_CTL_MAX
+};
+
+/**
+ * INTF sub-blocks
+ * @DPU_INTF_INPUT_CTRL             Supports the setting of pp block from which
+ *                                  pixel data arrives to this INTF
+ * @DPU_INTF_TE                     INTF block has TE configuration support
+ * @DPU_DATA_HCTL_EN                Allows data to be transferred at different rate
+ *                                  than video timing
+ * @DPU_INTF_STATUS_SUPPORTED       INTF block has INTF_STATUS register
+ * @DPU_INTF_MAX
+ */
+enum {
+	DPU_INTF_INPUT_CTRL = 0x1,
+	DPU_INTF_TE,
+	DPU_DATA_HCTL_EN,
+	DPU_INTF_STATUS_SUPPORTED,
+	DPU_INTF_MAX
+};
+
+/**
+  * WB sub-blocks and features
+  * @DPU_WB_LINE_MODE        Writeback module supports line/linear mode
+  * @DPU_WB_BLOCK_MODE       Writeback module supports block mode read
+  * @DPU_WB_CHROMA_DOWN,     Writeback chroma down block,
+  * @DPU_WB_DOWNSCALE,       Writeback integer downscaler,
+  * @DPU_WB_DITHER,          Dither block
+  * @DPU_WB_TRAFFIC_SHAPER,  Writeback traffic shaper bloc
+  * @DPU_WB_UBWC,            Writeback Universal bandwidth compression
+  * @DPU_WB_YUV_CONFIG       Writeback supports output of YUV colorspace
+  * @DPU_WB_PIPE_ALPHA       Writeback supports pipe alpha
+  * @DPU_WB_XY_ROI_OFFSET    Writeback supports x/y-offset of out ROI in
+  *                          the destination image
+  * @DPU_WB_QOS,             Writeback supports QoS control, danger/safe/creq
+  * @DPU_WB_QOS_8LVL,        Writeback supports 8-level QoS control
+  * @DPU_WB_CDP              Writeback supports client driven prefetch
+  * @DPU_WB_INPUT_CTRL       Writeback supports from which pp block input pixel
+  *                          data arrives.
+  * @DPU_WB_CROP             CWB supports cropping
+  * @DPU_WB_MAX              maximum value
+  */
+enum {
+	DPU_WB_LINE_MODE = 0x1,
+	DPU_WB_BLOCK_MODE,
+	DPU_WB_UBWC,
+	DPU_WB_YUV_CONFIG,
+	DPU_WB_PIPE_ALPHA,
+	DPU_WB_XY_ROI_OFFSET,
+	DPU_WB_QOS,
+	DPU_WB_QOS_8LVL,
+	DPU_WB_CDP,
+	DPU_WB_INPUT_CTRL,
+	DPU_WB_CROP,
+	DPU_WB_MAX
+};
+
+/**
+ * VBIF sub-blocks and features
+ * @DPU_VBIF_QOS_OTLIM        VBIF supports OT Limit
+ * @DPU_VBIF_QOS_REMAP        VBIF supports QoS priority remap
+ * @DPU_VBIF_MAX              maximum value
+ */
+enum {
+	DPU_VBIF_QOS_OTLIM = 0x1,
+	DPU_VBIF_QOS_REMAP,
+	DPU_VBIF_MAX
+};
+
+/**
+ * MACRO DPU_HW_BLK_INFO - information of HW blocks inside DPU
+ * @name:              string name for debug purposes
+ * @id:                enum identifying this block
+ * @base:              register base offset to mdss
+ * @len:               length of hardware block
+ * @features           bit mask identifying sub-blocks/features
+ */
+#define DPU_HW_BLK_INFO \
+	char name[DPU_HW_BLK_NAME_LEN]; \
+	u32 id; \
+	u32 base; \
+	u32 len; \
+	unsigned long features
+
+/**
+ * MACRO DPU_HW_SUBBLK_INFO - information of HW sub-block inside DPU
+ * @name:              string name for debug purposes
+ * @id:                enum identifying this sub-block
+ * @base:              offset of this sub-block relative to the block
+ *                     offset
+ * @len                register block length of this sub-block
+ */
+#define DPU_HW_SUBBLK_INFO \
+	char name[DPU_HW_BLK_NAME_LEN]; \
+	u32 id; \
+	u32 base; \
+	u32 len
+
+/**
+ * struct dpu_src_blk: SSPP part of the source pipes
+ * @info:   HW register and features supported by this sub-blk
+ */
+struct dpu_src_blk {
+	DPU_HW_SUBBLK_INFO;
+};
+
+/**
+ * struct dpu_scaler_blk: Scaler information
+ * @info:   HW register and features supported by this sub-blk
+ * @version: qseed block revision
+ */
+struct dpu_scaler_blk {
+	DPU_HW_SUBBLK_INFO;
+	u32 version;
+};
+
+struct dpu_csc_blk {
+	DPU_HW_SUBBLK_INFO;
+};
+
+/**
+ * struct dpu_pp_blk : Pixel processing sub-blk information
+ * @info:   HW register and features supported by this sub-blk
+ * @version: HW Algorithm version
+ */
+struct dpu_pp_blk {
+	DPU_HW_SUBBLK_INFO;
+	u32 version;
+};
+
+/**
+ * enum dpu_qos_lut_usage - define QoS LUT use cases
+ */
+enum dpu_qos_lut_usage {
+	DPU_QOS_LUT_USAGE_LINEAR,
+	DPU_QOS_LUT_USAGE_MACROTILE,
+	DPU_QOS_LUT_USAGE_NRT,
+	DPU_QOS_LUT_USAGE_MAX,
+};
+
+/**
+ * struct dpu_qos_lut_entry - define QoS LUT table entry
+ * @fl: fill level, or zero on last entry to indicate default lut
+ * @lut: lut to use if equal to or less than fill level
+ */
+struct dpu_qos_lut_entry {
+	u32 fl;
+	u64 lut;
+};
+
+/**
+ * struct dpu_qos_lut_tbl - define QoS LUT table
+ * @nentry: number of entry in this table
+ * @entries: Pointer to table entries
+ */
+struct dpu_qos_lut_tbl {
+	u32 nentry;
+	const struct dpu_qos_lut_entry *entries;
+};
+
+/**
+ * struct dpu_rotation_cfg - define inline rotation config
+ * @rot_maxheight: max pre rotated height allowed for rotation
+ * @rot_num_formats: number of elements in @rot_format_list
+ * @rot_format_list: list of supported rotator formats
+ */
+struct dpu_rotation_cfg {
+	u32 rot_maxheight;
+	size_t rot_num_formats;
+	const u32 *rot_format_list;
+};
+
+/**
+ * struct dpu_caps - define DPU capabilities
+ * @max_mixer_width    max layer mixer line width support.
+ * @max_mixer_blendstages max layer mixer blend stages or
+ *                       supported z order
+ * @qseed_type         qseed2 or qseed3 support.
+ * @smart_dma_rev      Supported version of SmartDMA feature.
+ * @ubwc_version       UBWC feature version (0x0 for not supported)
+ * @has_src_split      source split feature status
+ * @has_dim_layer      dim layer feature status
+ * @has_idle_pc        indicate if idle power collapse feature is supported
+ * @has_3d_merge       indicate if 3D merge is supported
+ * @max_linewidth      max linewidth for sspp
+ * @pixel_ram_size     size of latency hiding and de-tiling buffer in bytes
+ * @max_hdeci_exp      max horizontal decimation supported (max is 2^value)
+ * @max_vdeci_exp      max vertical decimation supported (max is 2^value)
+ */
+struct dpu_caps {
+	u32 max_mixer_width;
+	u32 max_mixer_blendstages;
+	u32 qseed_type;
+	u32 smart_dma_rev;
+	u32 ubwc_version;
+	bool has_src_split;
+	bool has_dim_layer;
+	bool has_idle_pc;
+	bool has_3d_merge;
+	/* SSPP limits */
+	u32 max_linewidth;
+	u32 pixel_ram_size;
+	u32 max_hdeci_exp;
+	u32 max_vdeci_exp;
+};
+
+/**
+ * struct dpu_sspp_sub_blks : SSPP sub-blocks
+ * common: Pointer to common configurations shared by sub blocks
+ * @creq_vblank: creq priority during vertical blanking
+ * @danger_vblank: danger priority during vertical blanking
+ * @maxdwnscale: max downscale ratio supported(without DECIMATION)
+ * @maxupscale:  maxupscale ratio supported
+ * @smart_dma_priority: hw priority of rect1 of multirect pipe
+ * @max_per_pipe_bw: maximum allowable bandwidth of this pipe in kBps
+ * @qseed_ver: qseed version
+ * @src_blk:
+ * @scaler_blk:
+ * @csc_blk:
+ * @hsic:
+ * @memcolor:
+ * @pcc_blk:
+ * @igc_blk:
+ * @format_list: Pointer to list of supported formats
+ * @num_formats: Number of supported formats
+ * @virt_format_list: Pointer to list of supported formats for virtual planes
+ * @virt_num_formats: Number of supported formats for virtual planes
+ * @dpu_rotation_cfg: inline rotation configuration
+ */
+struct dpu_sspp_sub_blks {
+	u32 creq_vblank;
+	u32 danger_vblank;
+	u32 maxdwnscale;
+	u32 maxupscale;
+	u32 smart_dma_priority;
+	u32 max_per_pipe_bw;
+	u32 qseed_ver;
+	struct dpu_src_blk src_blk;
+	struct dpu_scaler_blk scaler_blk;
+	struct dpu_pp_blk csc_blk;
+	struct dpu_pp_blk hsic_blk;
+	struct dpu_pp_blk memcolor_blk;
+	struct dpu_pp_blk pcc_blk;
+	struct dpu_pp_blk igc_blk;
+
+	const u32 *format_list;
+	u32 num_formats;
+	const u32 *virt_format_list;
+	u32 virt_num_formats;
+	const struct dpu_rotation_cfg *rotation_cfg;
+};
+
+/**
+ * struct dpu_lm_sub_blks:      information of mixer block
+ * @maxwidth:               Max pixel width supported by this mixer
+ * @maxblendstages:         Max number of blend-stages supported
+ * @blendstage_base:        Blend-stage register base offset
+ * @gc: gamma correction block
+ */
+struct dpu_lm_sub_blks {
+	u32 maxwidth;
+	u32 maxblendstages;
+	u32 blendstage_base[MAX_BLOCKS];
+	struct dpu_pp_blk gc;
+};
+
+/**
+ * struct dpu_dspp_sub_blks: Information of DSPP block
+ * @gc : gamma correction block
+ * @pcc: pixel color correction block
+ */
+struct dpu_dspp_sub_blks {
+	struct dpu_pp_blk gc;
+	struct dpu_pp_blk pcc;
+};
+
+struct dpu_pingpong_sub_blks {
+	struct dpu_pp_blk te;
+	struct dpu_pp_blk te2;
+	struct dpu_pp_blk dither;
+};
+
+/**
+ * dpu_clk_ctrl_type - Defines top level clock control signals
+ */
+enum dpu_clk_ctrl_type {
+	DPU_CLK_CTRL_NONE,
+	DPU_CLK_CTRL_VIG0,
+	DPU_CLK_CTRL_VIG1,
+	DPU_CLK_CTRL_VIG2,
+	DPU_CLK_CTRL_VIG3,
+	DPU_CLK_CTRL_VIG4,
+	DPU_CLK_CTRL_RGB0,
+	DPU_CLK_CTRL_RGB1,
+	DPU_CLK_CTRL_RGB2,
+	DPU_CLK_CTRL_RGB3,
+	DPU_CLK_CTRL_DMA0,
+	DPU_CLK_CTRL_DMA1,
+	DPU_CLK_CTRL_DMA2,
+	DPU_CLK_CTRL_DMA3,
+	DPU_CLK_CTRL_CURSOR0,
+	DPU_CLK_CTRL_CURSOR1,
+	DPU_CLK_CTRL_INLINE_ROT0_SSPP,
+	DPU_CLK_CTRL_REG_DMA,
+	DPU_CLK_CTRL_WB2,
+	DPU_CLK_CTRL_MAX,
+};
+
+/* struct dpu_clk_ctrl_reg : Clock control register
+ * @reg_off:           register offset
+ * @bit_off:           bit offset
+ */
+struct dpu_clk_ctrl_reg {
+	u32 reg_off;
+	u32 bit_off;
+};
+
+/* struct dpu_mdp_cfg : MDP TOP-BLK instance info
+ * @id:                index identifying this block
+ * @base:              register base offset to mdss
+ * @features           bit mask identifying sub-blocks/features
+ * @highest_bank_bit:  UBWC parameter
+ * @ubwc_static:       ubwc static configuration
+ * @ubwc_swizzle:      ubwc default swizzle setting
+ * @clk_ctrls          clock control register definition
+ */
+struct dpu_mdp_cfg {
+	DPU_HW_BLK_INFO;
+	u32 highest_bank_bit;
+	u32 ubwc_swizzle;
+	struct dpu_clk_ctrl_reg clk_ctrls[DPU_CLK_CTRL_MAX];
+};
+
+/* struct dpu_ctl_cfg : MDP CTL instance info
+ * @id:                index identifying this block
+ * @base:              register base offset to mdss
+ * @features           bit mask identifying sub-blocks/features
+ * @intr_start:        interrupt index for CTL_START
+ */
+struct dpu_ctl_cfg {
+	DPU_HW_BLK_INFO;
+	s32 intr_start;
+};
+
+/**
+ * struct dpu_sspp_cfg - information of source pipes
+ * @id:                index identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @sblk:              SSPP sub-blocks information
+ * @xin_id:            bus client identifier
+ * @clk_ctrl           clock control identifier
+ * @type               sspp type identifier
+ */
+struct dpu_sspp_cfg {
+	DPU_HW_BLK_INFO;
+	const struct dpu_sspp_sub_blks *sblk;
+	u32 xin_id;
+	enum dpu_clk_ctrl_type clk_ctrl;
+	u32 type;
+};
+
+/**
+ * struct dpu_lm_cfg - information of layer mixer blocks
+ * @id:                index identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @sblk:              LM Sub-blocks information
+ * @pingpong:          ID of connected PingPong, PINGPONG_MAX if unsupported
+ * @lm_pair_mask:      Bitmask of LMs that can be controlled by same CTL
+ */
+struct dpu_lm_cfg {
+	DPU_HW_BLK_INFO;
+	const struct dpu_lm_sub_blks *sblk;
+	u32 pingpong;
+	u32 dspp;
+	unsigned long lm_pair_mask;
+};
+
+/**
+ * struct dpu_dspp_cfg - information of DSPP blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ *                     supported by this block
+ * @sblk               sub-blocks information
+ */
+struct dpu_dspp_cfg  {
+	DPU_HW_BLK_INFO;
+	const struct dpu_dspp_sub_blks *sblk;
+};
+
+/**
+ * struct dpu_pingpong_cfg - information of PING-PONG blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @intr_done:         index for PINGPONG done interrupt
+ * @intr_rdptr:        index for PINGPONG readpointer done interrupt
+ * @sblk               sub-blocks information
+ */
+struct dpu_pingpong_cfg  {
+	DPU_HW_BLK_INFO;
+	u32 merge_3d;
+	s32 intr_done;
+	s32 intr_rdptr;
+	const struct dpu_pingpong_sub_blks *sblk;
+};
+
+/**
+ * struct dpu_merge_3d_cfg - information of DSPP blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ *                     supported by this block
+ * @sblk               sub-blocks information
+ */
+struct dpu_merge_3d_cfg  {
+	DPU_HW_BLK_INFO;
+	const struct dpu_merge_3d_sub_blks *sblk;
+};
+
+/**
+ * struct dpu_dsc_cfg - information of DSC blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ */
+struct dpu_dsc_cfg {
+	DPU_HW_BLK_INFO;
+};
+
+/**
+ * struct dpu_intf_cfg - information of timing engine blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @type:              Interface type(DSI, DP, HDMI)
+ * @controller_id:     Controller Instance ID in case of multiple of intf type
+ * @prog_fetch_lines_worst_case	Worst case latency num lines needed to prefetch
+ * @intr_underrun:	index for INTF underrun interrupt
+ * @intr_vsync:	        index for INTF VSYNC interrupt
+ */
+struct dpu_intf_cfg  {
+	DPU_HW_BLK_INFO;
+	u32 type;   /* interface type*/
+	u32 controller_id;
+	u32 prog_fetch_lines_worst_case;
+	s32 intr_underrun;
+	s32 intr_vsync;
+};
+
+/**
+ * struct dpu_wb_cfg - information of writeback blocks
+ * @DPU_HW_BLK_INFO:    refer to the description above for DPU_HW_BLK_INFO
+ * @vbif_idx:           vbif client index
+ * @maxlinewidth:       max line width supported by writeback block
+ * @xin_id:             bus client identifier
+ * @intr_wb_done:       interrupt index for WB_DONE
+ * @format_list:	    list of formats supported by this writeback block
+ * @num_formats:	    number of formats supported by this writeback block
+ * @clk_ctrl:	        clock control identifier
+ */
+struct dpu_wb_cfg {
+	DPU_HW_BLK_INFO;
+	u8 vbif_idx;
+	u32 maxlinewidth;
+	u32 xin_id;
+	s32 intr_wb_done;
+	const u32 *format_list;
+	u32 num_formats;
+	enum dpu_clk_ctrl_type clk_ctrl;
+};
+
+/**
+ * struct dpu_vbif_dynamic_ot_cfg - dynamic OT setting
+ * @pps                pixel per seconds
+ * @ot_limit           OT limit to use up to specified pixel per second
+ */
+struct dpu_vbif_dynamic_ot_cfg {
+	u64 pps;
+	u32 ot_limit;
+};
+
+/**
+ * struct dpu_vbif_dynamic_ot_tbl - dynamic OT setting table
+ * @count              length of cfg
+ * @cfg                pointer to array of configuration settings with
+ *                     ascending requirements
+ */
+struct dpu_vbif_dynamic_ot_tbl {
+	u32 count;
+	const struct dpu_vbif_dynamic_ot_cfg *cfg;
+};
+
+/**
+ * struct dpu_vbif_qos_tbl - QoS priority table
+ * @npriority_lvl      num of priority level
+ * @priority_lvl       pointer to array of priority level in ascending order
+ */
+struct dpu_vbif_qos_tbl {
+	u32 npriority_lvl;
+	const u32 *priority_lvl;
+};
+
+/**
+ * struct dpu_vbif_cfg - information of VBIF blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @ot_rd_limit        default OT read limit
+ * @ot_wr_limit        default OT write limit
+ * @xin_halt_timeout   maximum time (in usec) for xin to halt
+ * @qos_rp_remap_size  size of VBIF_XINL_QOS_RP_REMAP register space
+ * @dynamic_ot_rd_tbl  dynamic OT read configuration table
+ * @dynamic_ot_wr_tbl  dynamic OT write configuration table
+ * @qos_rt_tbl         real-time QoS priority table
+ * @qos_nrt_tbl        non-real-time QoS priority table
+ * @memtype_count      number of defined memtypes
+ * @memtype            array of xin memtype definitions
+ */
+struct dpu_vbif_cfg {
+	DPU_HW_BLK_INFO;
+	u32 default_ot_rd_limit;
+	u32 default_ot_wr_limit;
+	u32 xin_halt_timeout;
+	u32 qos_rp_remap_size;
+	struct dpu_vbif_dynamic_ot_tbl dynamic_ot_rd_tbl;
+	struct dpu_vbif_dynamic_ot_tbl dynamic_ot_wr_tbl;
+	struct dpu_vbif_qos_tbl qos_rt_tbl;
+	struct dpu_vbif_qos_tbl qos_nrt_tbl;
+	u32 memtype_count;
+	u32 memtype[MAX_XIN_COUNT];
+};
+/**
+ * struct dpu_reg_dma_cfg - information of lut dma blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @version            version of lutdma hw block
+ * @trigger_sel_off    offset to trigger select registers of lutdma
+ */
+struct dpu_reg_dma_cfg {
+	DPU_HW_BLK_INFO;
+	u32 version;
+	u32 trigger_sel_off;
+	u32 xin_id;
+	enum dpu_clk_ctrl_type clk_ctrl;
+};
+
+/**
+ * Define CDP use cases
+ * @DPU_PERF_CDP_UDAGE_RT: real-time use cases
+ * @DPU_PERF_CDP_USAGE_NRT: non real-time use cases such as WFD
+ */
+enum {
+	DPU_PERF_CDP_USAGE_RT,
+	DPU_PERF_CDP_USAGE_NRT,
+	DPU_PERF_CDP_USAGE_MAX
+};
+
+/**
+ * struct dpu_perf_cdp_cfg - define CDP use case configuration
+ * @rd_enable: true if read pipe CDP is enabled
+ * @wr_enable: true if write pipe CDP is enabled
+ */
+struct dpu_perf_cdp_cfg {
+	bool rd_enable;
+	bool wr_enable;
+};
+
+/**
+ * struct dpu_perf_cfg - performance control settings
+ * @max_bw_low         low threshold of maximum bandwidth (kbps)
+ * @max_bw_high        high threshold of maximum bandwidth (kbps)
+ * @min_core_ib        minimum bandwidth for core (kbps)
+ * @min_core_ib        minimum mnoc ib vote in kbps
+ * @min_llcc_ib        minimum llcc ib vote in kbps
+ * @min_dram_ib        minimum dram ib vote in kbps
+ * @undersized_prefill_lines   undersized prefill in lines
+ * @xtra_prefill_lines         extra prefill latency in lines
+ * @dest_scale_prefill_lines   destination scaler latency in lines
+ * @macrotile_perfill_lines    macrotile latency in lines
+ * @yuv_nv12_prefill_lines     yuv_nv12 latency in lines
+ * @linear_prefill_lines       linear latency in lines
+ * @downscaling_prefill_lines  downscaling latency in lines
+ * @amortizable_theshold minimum y position for traffic shaping prefill
+ * @min_prefill_lines  minimum pipeline latency in lines
+ * @clk_inefficiency_factor DPU src clock inefficiency factor
+ * @bw_inefficiency_factor DPU axi bus bw inefficiency factor
+ * @safe_lut_tbl: LUT tables for safe signals
+ * @danger_lut_tbl: LUT tables for danger signals
+ * @qos_lut_tbl: LUT tables for QoS signals
+ * @cdp_cfg            cdp use case configurations
+ */
+struct dpu_perf_cfg {
+	u32 max_bw_low;
+	u32 max_bw_high;
+	u32 min_core_ib;
+	u32 min_llcc_ib;
+	u32 min_dram_ib;
+	u32 undersized_prefill_lines;
+	u32 xtra_prefill_lines;
+	u32 dest_scale_prefill_lines;
+	u32 macrotile_prefill_lines;
+	u32 yuv_nv12_prefill_lines;
+	u32 linear_prefill_lines;
+	u32 downscaling_prefill_lines;
+	u32 amortizable_threshold;
+	u32 min_prefill_lines;
+	u32 clk_inefficiency_factor;
+	u32 bw_inefficiency_factor;
+	u32 safe_lut_tbl[DPU_QOS_LUT_USAGE_MAX];
+	u32 danger_lut_tbl[DPU_QOS_LUT_USAGE_MAX];
+	struct dpu_qos_lut_tbl qos_lut_tbl[DPU_QOS_LUT_USAGE_MAX];
+	struct dpu_perf_cdp_cfg cdp_cfg[DPU_PERF_CDP_USAGE_MAX];
+};
+
+/**
+ * struct dpu_mdss_cfg - information of MDSS HW
+ * This is the main catalog data structure representing
+ * this HW version. Contains number of instances,
+ * register offsets, capabilities of the all MDSS HW sub-blocks.
+ *
+ * @dma_formats        Supported formats for dma pipe
+ * @cursor_formats     Supported formats for cursor pipe
+ * @vig_formats        Supported formats for vig pipe
+ * @mdss_irqs:         Bitmap with the irqs supported by the target
+ */
+struct dpu_mdss_cfg {
+	const struct dpu_caps *caps;
+
+	u32 mdp_count;
+	const struct dpu_mdp_cfg *mdp;
+
+	u32 ctl_count;
+	const struct dpu_ctl_cfg *ctl;
+
+	u32 sspp_count;
+	const struct dpu_sspp_cfg *sspp;
+
+	u32 mixer_count;
+	const struct dpu_lm_cfg *mixer;
+
+	u32 pingpong_count;
+	const struct dpu_pingpong_cfg *pingpong;
+
+	u32 merge_3d_count;
+	const struct dpu_merge_3d_cfg *merge_3d;
+
+	u32 dsc_count;
+	struct dpu_dsc_cfg *dsc;
+
+	u32 intf_count;
+	const struct dpu_intf_cfg *intf;
+
+	u32 vbif_count;
+	const struct dpu_vbif_cfg *vbif;
+
+	u32 wb_count;
+	const struct dpu_wb_cfg *wb;
+
+	u32 reg_dma_count;
+	const struct dpu_reg_dma_cfg *dma_cfg;
+
+	u32 ad_count;
+
+	u32 dspp_count;
+	const struct dpu_dspp_cfg *dspp;
+
+	/* Add additional block data structures here */
+
+	const struct dpu_perf_cfg *perf;
+	const struct dpu_format_extended *dma_formats;
+	const struct dpu_format_extended *cursor_formats;
+	const struct dpu_format_extended *vig_formats;
+
+	unsigned long mdss_irqs;
+};
+
+struct dpu_mdss_hw_cfg_handler {
+	u32 hw_rev;
+	const struct dpu_mdss_cfg *dpu_cfg;
+};
+
+/**
+ * dpu_hw_catalog_init - dpu hardware catalog init API retrieves
+ * hardcoded target specific catalog information in config structure
+ * @hw_rev:       caller needs provide the hardware revision.
+ *
+ * Return: dpu config structure
+ */
+const struct dpu_mdss_cfg *dpu_hw_catalog_init(u32 hw_rev);
+
+#endif /* _DPU_HW_CATALOG_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
new file mode 100644
index 000000000..696c32d30
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
@@ -0,0 +1,713 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/delay.h>
+#include "dpu_hwio.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_kms.h"
+#include "dpu_trace.h"
+
+#define   CTL_LAYER(lm)                 \
+	(((lm) == LM_5) ? (0x024) : (((lm) - LM_0) * 0x004))
+#define   CTL_LAYER_EXT(lm)             \
+	(0x40 + (((lm) - LM_0) * 0x004))
+#define   CTL_LAYER_EXT2(lm)             \
+	(0x70 + (((lm) - LM_0) * 0x004))
+#define   CTL_LAYER_EXT3(lm)             \
+	(0xA0 + (((lm) - LM_0) * 0x004))
+#define   CTL_TOP                       0x014
+#define   CTL_FLUSH                     0x018
+#define   CTL_START                     0x01C
+#define   CTL_PREPARE                   0x0d0
+#define   CTL_SW_RESET                  0x030
+#define   CTL_LAYER_EXTN_OFFSET         0x40
+#define   CTL_MERGE_3D_ACTIVE           0x0E4
+#define   CTL_WB_ACTIVE                 0x0EC
+#define   CTL_INTF_ACTIVE               0x0F4
+#define   CTL_MERGE_3D_FLUSH            0x100
+#define   CTL_DSC_ACTIVE                0x0E8
+#define   CTL_DSC_FLUSH                0x104
+#define   CTL_WB_FLUSH                  0x108
+#define   CTL_INTF_FLUSH                0x110
+#define   CTL_INTF_MASTER               0x134
+#define   CTL_FETCH_PIPE_ACTIVE         0x0FC
+
+#define CTL_MIXER_BORDER_OUT            BIT(24)
+#define CTL_FLUSH_MASK_CTL              BIT(17)
+
+#define DPU_REG_RESET_TIMEOUT_US        2000
+#define  MERGE_3D_IDX   23
+#define  DSC_IDX        22
+#define  INTF_IDX       31
+#define WB_IDX          16
+#define CTL_INVALID_BIT                 0xffff
+#define CTL_DEFAULT_GROUP_ID		0xf
+
+static const u32 fetch_tbl[SSPP_MAX] = {CTL_INVALID_BIT, 16, 17, 18, 19,
+	CTL_INVALID_BIT, CTL_INVALID_BIT, CTL_INVALID_BIT, CTL_INVALID_BIT, 0,
+	1, 2, 3, CTL_INVALID_BIT, CTL_INVALID_BIT};
+
+static const struct dpu_ctl_cfg *_ctl_offset(enum dpu_ctl ctl,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->ctl_count; i++) {
+		if (ctl == m->ctl[i].id) {
+			b->blk_addr = addr + m->ctl[i].base;
+			b->log_mask = DPU_DBG_MASK_CTL;
+			return &m->ctl[i];
+		}
+	}
+	return ERR_PTR(-ENOMEM);
+}
+
+static int _mixer_stages(const struct dpu_lm_cfg *mixer, int count,
+		enum dpu_lm lm)
+{
+	int i;
+	int stages = -EINVAL;
+
+	for (i = 0; i < count; i++) {
+		if (lm == mixer[i].id) {
+			stages = mixer[i].sblk->maxblendstages;
+			break;
+		}
+	}
+
+	return stages;
+}
+
+static inline u32 dpu_hw_ctl_get_flush_register(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	return DPU_REG_READ(c, CTL_FLUSH);
+}
+
+static inline void dpu_hw_ctl_trigger_start(struct dpu_hw_ctl *ctx)
+{
+	trace_dpu_hw_ctl_trigger_start(ctx->pending_flush_mask,
+				       dpu_hw_ctl_get_flush_register(ctx));
+	DPU_REG_WRITE(&ctx->hw, CTL_START, 0x1);
+}
+
+static inline bool dpu_hw_ctl_is_started(struct dpu_hw_ctl *ctx)
+{
+	return !!(DPU_REG_READ(&ctx->hw, CTL_START) & BIT(0));
+}
+
+static inline void dpu_hw_ctl_trigger_pending(struct dpu_hw_ctl *ctx)
+{
+	trace_dpu_hw_ctl_trigger_prepare(ctx->pending_flush_mask,
+					 dpu_hw_ctl_get_flush_register(ctx));
+	DPU_REG_WRITE(&ctx->hw, CTL_PREPARE, 0x1);
+}
+
+static inline void dpu_hw_ctl_clear_pending_flush(struct dpu_hw_ctl *ctx)
+{
+	trace_dpu_hw_ctl_clear_pending_flush(ctx->pending_flush_mask,
+				     dpu_hw_ctl_get_flush_register(ctx));
+	ctx->pending_flush_mask = 0x0;
+}
+
+static inline void dpu_hw_ctl_update_pending_flush(struct dpu_hw_ctl *ctx,
+		u32 flushbits)
+{
+	trace_dpu_hw_ctl_update_pending_flush(flushbits,
+					      ctx->pending_flush_mask);
+	ctx->pending_flush_mask |= flushbits;
+}
+
+static u32 dpu_hw_ctl_get_pending_flush(struct dpu_hw_ctl *ctx)
+{
+	return ctx->pending_flush_mask;
+}
+
+static inline void dpu_hw_ctl_trigger_flush_v1(struct dpu_hw_ctl *ctx)
+{
+	if (ctx->pending_flush_mask & BIT(MERGE_3D_IDX))
+		DPU_REG_WRITE(&ctx->hw, CTL_MERGE_3D_FLUSH,
+				ctx->pending_merge_3d_flush_mask);
+	if (ctx->pending_flush_mask & BIT(INTF_IDX))
+		DPU_REG_WRITE(&ctx->hw, CTL_INTF_FLUSH,
+				ctx->pending_intf_flush_mask);
+	if (ctx->pending_flush_mask & BIT(WB_IDX))
+		DPU_REG_WRITE(&ctx->hw, CTL_WB_FLUSH,
+				ctx->pending_wb_flush_mask);
+
+	DPU_REG_WRITE(&ctx->hw, CTL_FLUSH, ctx->pending_flush_mask);
+}
+
+static inline void dpu_hw_ctl_trigger_flush(struct dpu_hw_ctl *ctx)
+{
+	trace_dpu_hw_ctl_trigger_pending_flush(ctx->pending_flush_mask,
+				     dpu_hw_ctl_get_flush_register(ctx));
+	DPU_REG_WRITE(&ctx->hw, CTL_FLUSH, ctx->pending_flush_mask);
+}
+
+static void dpu_hw_ctl_update_pending_flush_sspp(struct dpu_hw_ctl *ctx,
+	enum dpu_sspp sspp)
+{
+	switch (sspp) {
+	case SSPP_VIG0:
+		ctx->pending_flush_mask |=  BIT(0);
+		break;
+	case SSPP_VIG1:
+		ctx->pending_flush_mask |= BIT(1);
+		break;
+	case SSPP_VIG2:
+		ctx->pending_flush_mask |= BIT(2);
+		break;
+	case SSPP_VIG3:
+		ctx->pending_flush_mask |= BIT(18);
+		break;
+	case SSPP_RGB0:
+		ctx->pending_flush_mask |= BIT(3);
+		break;
+	case SSPP_RGB1:
+		ctx->pending_flush_mask |= BIT(4);
+		break;
+	case SSPP_RGB2:
+		ctx->pending_flush_mask |= BIT(5);
+		break;
+	case SSPP_RGB3:
+		ctx->pending_flush_mask |= BIT(19);
+		break;
+	case SSPP_DMA0:
+		ctx->pending_flush_mask |= BIT(11);
+		break;
+	case SSPP_DMA1:
+		ctx->pending_flush_mask |= BIT(12);
+		break;
+	case SSPP_DMA2:
+		ctx->pending_flush_mask |= BIT(24);
+		break;
+	case SSPP_DMA3:
+		ctx->pending_flush_mask |= BIT(25);
+		break;
+	case SSPP_CURSOR0:
+		ctx->pending_flush_mask |= BIT(22);
+		break;
+	case SSPP_CURSOR1:
+		ctx->pending_flush_mask |= BIT(23);
+		break;
+	default:
+		break;
+	}
+}
+
+static void dpu_hw_ctl_update_pending_flush_mixer(struct dpu_hw_ctl *ctx,
+	enum dpu_lm lm)
+{
+	switch (lm) {
+	case LM_0:
+		ctx->pending_flush_mask |= BIT(6);
+		break;
+	case LM_1:
+		ctx->pending_flush_mask |= BIT(7);
+		break;
+	case LM_2:
+		ctx->pending_flush_mask |= BIT(8);
+		break;
+	case LM_3:
+		ctx->pending_flush_mask |= BIT(9);
+		break;
+	case LM_4:
+		ctx->pending_flush_mask |= BIT(10);
+		break;
+	case LM_5:
+		ctx->pending_flush_mask |= BIT(20);
+		break;
+	default:
+		break;
+	}
+
+	ctx->pending_flush_mask |= CTL_FLUSH_MASK_CTL;
+}
+
+static void dpu_hw_ctl_update_pending_flush_intf(struct dpu_hw_ctl *ctx,
+		enum dpu_intf intf)
+{
+	switch (intf) {
+	case INTF_0:
+		ctx->pending_flush_mask |= BIT(31);
+		break;
+	case INTF_1:
+		ctx->pending_flush_mask |= BIT(30);
+		break;
+	case INTF_2:
+		ctx->pending_flush_mask |= BIT(29);
+		break;
+	case INTF_3:
+		ctx->pending_flush_mask |= BIT(28);
+		break;
+	default:
+		break;
+	}
+}
+
+static void dpu_hw_ctl_update_pending_flush_wb(struct dpu_hw_ctl *ctx,
+		enum dpu_wb wb)
+{
+	switch (wb) {
+	case WB_0:
+	case WB_1:
+	case WB_2:
+		ctx->pending_flush_mask |= BIT(WB_IDX);
+		break;
+	default:
+		break;
+	}
+}
+
+static void dpu_hw_ctl_update_pending_flush_wb_v1(struct dpu_hw_ctl *ctx,
+		enum dpu_wb wb)
+{
+	ctx->pending_wb_flush_mask |= BIT(wb - WB_0);
+	ctx->pending_flush_mask |= BIT(WB_IDX);
+}
+
+static void dpu_hw_ctl_update_pending_flush_intf_v1(struct dpu_hw_ctl *ctx,
+		enum dpu_intf intf)
+{
+	ctx->pending_intf_flush_mask |= BIT(intf - INTF_0);
+	ctx->pending_flush_mask |= BIT(INTF_IDX);
+}
+
+static void dpu_hw_ctl_update_pending_flush_merge_3d_v1(struct dpu_hw_ctl *ctx,
+		enum dpu_merge_3d merge_3d)
+{
+	ctx->pending_merge_3d_flush_mask |= BIT(merge_3d - MERGE_3D_0);
+	ctx->pending_flush_mask |= BIT(MERGE_3D_IDX);
+}
+
+static void dpu_hw_ctl_update_pending_flush_dspp(struct dpu_hw_ctl *ctx,
+	enum dpu_dspp dspp)
+{
+	switch (dspp) {
+	case DSPP_0:
+		ctx->pending_flush_mask |= BIT(13);
+		break;
+	case DSPP_1:
+		ctx->pending_flush_mask |= BIT(14);
+		break;
+	case DSPP_2:
+		ctx->pending_flush_mask |= BIT(15);
+		break;
+	case DSPP_3:
+		ctx->pending_flush_mask |= BIT(21);
+		break;
+	default:
+		break;
+	}
+}
+
+static u32 dpu_hw_ctl_poll_reset_status(struct dpu_hw_ctl *ctx, u32 timeout_us)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	ktime_t timeout;
+	u32 status;
+
+	timeout = ktime_add_us(ktime_get(), timeout_us);
+
+	/*
+	 * it takes around 30us to have mdp finish resetting its ctl path
+	 * poll every 50us so that reset should be completed at 1st poll
+	 */
+	do {
+		status = DPU_REG_READ(c, CTL_SW_RESET);
+		status &= 0x1;
+		if (status)
+			usleep_range(20, 50);
+	} while (status && ktime_compare_safe(ktime_get(), timeout) < 0);
+
+	return status;
+}
+
+static int dpu_hw_ctl_reset_control(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	pr_debug("issuing hw ctl reset for ctl:%d\n", ctx->idx);
+	DPU_REG_WRITE(c, CTL_SW_RESET, 0x1);
+	if (dpu_hw_ctl_poll_reset_status(ctx, DPU_REG_RESET_TIMEOUT_US))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int dpu_hw_ctl_wait_reset_status(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 status;
+
+	status = DPU_REG_READ(c, CTL_SW_RESET);
+	status &= 0x01;
+	if (!status)
+		return 0;
+
+	pr_debug("hw ctl reset is set for ctl:%d\n", ctx->idx);
+	if (dpu_hw_ctl_poll_reset_status(ctx, DPU_REG_RESET_TIMEOUT_US)) {
+		pr_err("hw recovery is not complete for ctl:%d\n", ctx->idx);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void dpu_hw_ctl_clear_all_blendstages(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int i;
+
+	for (i = 0; i < ctx->mixer_count; i++) {
+		enum dpu_lm mixer_id = ctx->mixer_hw_caps[i].id;
+
+		DPU_REG_WRITE(c, CTL_LAYER(mixer_id), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT(mixer_id), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT2(mixer_id), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT3(mixer_id), 0);
+	}
+
+	DPU_REG_WRITE(c, CTL_FETCH_PIPE_ACTIVE, 0);
+}
+
+static void dpu_hw_ctl_setup_blendstage(struct dpu_hw_ctl *ctx,
+	enum dpu_lm lm, struct dpu_hw_stage_cfg *stage_cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 mixercfg = 0, mixercfg_ext = 0, mix, ext;
+	u32 mixercfg_ext2 = 0, mixercfg_ext3 = 0;
+	int i, j;
+	int stages;
+	int pipes_per_stage;
+
+	stages = _mixer_stages(ctx->mixer_hw_caps, ctx->mixer_count, lm);
+	if (stages < 0)
+		return;
+
+	if (test_bit(DPU_MIXER_SOURCESPLIT,
+		&ctx->mixer_hw_caps->features))
+		pipes_per_stage = PIPES_PER_STAGE;
+	else
+		pipes_per_stage = 1;
+
+	mixercfg = CTL_MIXER_BORDER_OUT; /* always set BORDER_OUT */
+
+	if (!stage_cfg)
+		goto exit;
+
+	for (i = 0; i <= stages; i++) {
+		/* overflow to ext register if 'i + 1 > 7' */
+		mix = (i + 1) & 0x7;
+		ext = i >= 7;
+
+		for (j = 0 ; j < pipes_per_stage; j++) {
+			enum dpu_sspp_multirect_index rect_index =
+				stage_cfg->multirect_index[i][j];
+
+			switch (stage_cfg->stage[i][j]) {
+			case SSPP_VIG0:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 0;
+				} else {
+					mixercfg |= mix << 0;
+					mixercfg_ext |= ext << 0;
+				}
+				break;
+			case SSPP_VIG1:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 4;
+				} else {
+					mixercfg |= mix << 3;
+					mixercfg_ext |= ext << 2;
+				}
+				break;
+			case SSPP_VIG2:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 8;
+				} else {
+					mixercfg |= mix << 6;
+					mixercfg_ext |= ext << 4;
+				}
+				break;
+			case SSPP_VIG3:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 12;
+				} else {
+					mixercfg |= mix << 26;
+					mixercfg_ext |= ext << 6;
+				}
+				break;
+			case SSPP_RGB0:
+				mixercfg |= mix << 9;
+				mixercfg_ext |= ext << 8;
+				break;
+			case SSPP_RGB1:
+				mixercfg |= mix << 12;
+				mixercfg_ext |= ext << 10;
+				break;
+			case SSPP_RGB2:
+				mixercfg |= mix << 15;
+				mixercfg_ext |= ext << 12;
+				break;
+			case SSPP_RGB3:
+				mixercfg |= mix << 29;
+				mixercfg_ext |= ext << 14;
+				break;
+			case SSPP_DMA0:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 8;
+				} else {
+					mixercfg |= mix << 18;
+					mixercfg_ext |= ext << 16;
+				}
+				break;
+			case SSPP_DMA1:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 12;
+				} else {
+					mixercfg |= mix << 21;
+					mixercfg_ext |= ext << 18;
+				}
+				break;
+			case SSPP_DMA2:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 16;
+				} else {
+					mix |= (i + 1) & 0xF;
+					mixercfg_ext2 |= mix << 0;
+				}
+				break;
+			case SSPP_DMA3:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 20;
+				} else {
+					mix |= (i + 1) & 0xF;
+					mixercfg_ext2 |= mix << 4;
+				}
+				break;
+			case SSPP_CURSOR0:
+				mixercfg_ext |= ((i + 1) & 0xF) << 20;
+				break;
+			case SSPP_CURSOR1:
+				mixercfg_ext |= ((i + 1) & 0xF) << 26;
+				break;
+			default:
+				break;
+			}
+		}
+	}
+
+exit:
+	DPU_REG_WRITE(c, CTL_LAYER(lm), mixercfg);
+	DPU_REG_WRITE(c, CTL_LAYER_EXT(lm), mixercfg_ext);
+	DPU_REG_WRITE(c, CTL_LAYER_EXT2(lm), mixercfg_ext2);
+	DPU_REG_WRITE(c, CTL_LAYER_EXT3(lm), mixercfg_ext3);
+}
+
+
+static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx,
+		struct dpu_hw_intf_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 intf_active = 0;
+	u32 wb_active = 0;
+	u32 mode_sel = 0;
+
+	/* CTL_TOP[31:28] carries group_id to collate CTL paths
+	 * per VM. Explicitly disable it until VM support is
+	 * added in SW. Power on reset value is not disable.
+	 */
+	if ((test_bit(DPU_CTL_VM_CFG, &ctx->caps->features)))
+		mode_sel = CTL_DEFAULT_GROUP_ID  << 28;
+
+	if (cfg->dsc)
+		DPU_REG_WRITE(&ctx->hw, CTL_DSC_FLUSH, cfg->dsc);
+
+	if (cfg->intf_mode_sel == DPU_CTL_MODE_SEL_CMD)
+		mode_sel |= BIT(17);
+
+	intf_active = DPU_REG_READ(c, CTL_INTF_ACTIVE);
+	wb_active = DPU_REG_READ(c, CTL_WB_ACTIVE);
+
+	if (cfg->intf)
+		intf_active |= BIT(cfg->intf - INTF_0);
+
+	if (cfg->wb)
+		wb_active |= BIT(cfg->wb - WB_0);
+
+	DPU_REG_WRITE(c, CTL_TOP, mode_sel);
+	DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active);
+	DPU_REG_WRITE(c, CTL_WB_ACTIVE, wb_active);
+
+	if (cfg->merge_3d)
+		DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE,
+			      BIT(cfg->merge_3d - MERGE_3D_0));
+	if (cfg->dsc) {
+		DPU_REG_WRITE(&ctx->hw, CTL_FLUSH, BIT(DSC_IDX));
+		DPU_REG_WRITE(c, CTL_DSC_ACTIVE, cfg->dsc);
+	}
+}
+
+static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx,
+		struct dpu_hw_intf_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 intf_cfg = 0;
+
+	intf_cfg |= (cfg->intf & 0xF) << 4;
+
+	if (cfg->mode_3d) {
+		intf_cfg |= BIT(19);
+		intf_cfg |= (cfg->mode_3d - 0x1) << 20;
+	}
+
+	if (cfg->wb)
+		intf_cfg |= (cfg->wb & 0x3) + 2;
+
+	switch (cfg->intf_mode_sel) {
+	case DPU_CTL_MODE_SEL_VID:
+		intf_cfg &= ~BIT(17);
+		intf_cfg &= ~(0x3 << 15);
+		break;
+	case DPU_CTL_MODE_SEL_CMD:
+		intf_cfg |= BIT(17);
+		intf_cfg |= ((cfg->stream_sel & 0x3) << 15);
+		break;
+	default:
+		pr_err("unknown interface type %d\n", cfg->intf_mode_sel);
+		return;
+	}
+
+	DPU_REG_WRITE(c, CTL_TOP, intf_cfg);
+}
+
+static void dpu_hw_ctl_reset_intf_cfg_v1(struct dpu_hw_ctl *ctx,
+		struct dpu_hw_intf_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 intf_active = 0;
+	u32 wb_active = 0;
+	u32 merge3d_active = 0;
+
+	/*
+	 * This API resets each portion of the CTL path namely,
+	 * clearing the sspps staged on the lm, merge_3d block,
+	 * interfaces , writeback etc to ensure clean teardown of the pipeline.
+	 * This will be used for writeback to begin with to have a
+	 * proper teardown of the writeback session but upon further
+	 * validation, this can be extended to all interfaces.
+	 */
+	if (cfg->merge_3d) {
+		merge3d_active = DPU_REG_READ(c, CTL_MERGE_3D_ACTIVE);
+		merge3d_active &= ~BIT(cfg->merge_3d - MERGE_3D_0);
+		DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE,
+				merge3d_active);
+	}
+
+	dpu_hw_ctl_clear_all_blendstages(ctx);
+
+	if (cfg->intf) {
+		intf_active = DPU_REG_READ(c, CTL_INTF_ACTIVE);
+		intf_active &= ~BIT(cfg->intf - INTF_0);
+		DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active);
+	}
+
+	if (cfg->wb) {
+		wb_active = DPU_REG_READ(c, CTL_WB_ACTIVE);
+		wb_active &= ~BIT(cfg->wb - WB_0);
+		DPU_REG_WRITE(c, CTL_WB_ACTIVE, wb_active);
+	}
+}
+
+static void dpu_hw_ctl_set_fetch_pipe_active(struct dpu_hw_ctl *ctx,
+	unsigned long *fetch_active)
+{
+	int i;
+	u32 val = 0;
+
+	if (fetch_active) {
+		for (i = 0; i < SSPP_MAX; i++) {
+			if (test_bit(i, fetch_active) &&
+				fetch_tbl[i] != CTL_INVALID_BIT)
+				val |= BIT(fetch_tbl[i]);
+		}
+	}
+
+	DPU_REG_WRITE(&ctx->hw, CTL_FETCH_PIPE_ACTIVE, val);
+}
+
+static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops,
+		unsigned long cap)
+{
+	if (cap & BIT(DPU_CTL_ACTIVE_CFG)) {
+		ops->trigger_flush = dpu_hw_ctl_trigger_flush_v1;
+		ops->setup_intf_cfg = dpu_hw_ctl_intf_cfg_v1;
+		ops->reset_intf_cfg = dpu_hw_ctl_reset_intf_cfg_v1;
+		ops->update_pending_flush_intf =
+			dpu_hw_ctl_update_pending_flush_intf_v1;
+		ops->update_pending_flush_merge_3d =
+			dpu_hw_ctl_update_pending_flush_merge_3d_v1;
+		ops->update_pending_flush_wb = dpu_hw_ctl_update_pending_flush_wb_v1;
+	} else {
+		ops->trigger_flush = dpu_hw_ctl_trigger_flush;
+		ops->setup_intf_cfg = dpu_hw_ctl_intf_cfg;
+		ops->update_pending_flush_intf =
+			dpu_hw_ctl_update_pending_flush_intf;
+		ops->update_pending_flush_wb = dpu_hw_ctl_update_pending_flush_wb;
+	}
+	ops->clear_pending_flush = dpu_hw_ctl_clear_pending_flush;
+	ops->update_pending_flush = dpu_hw_ctl_update_pending_flush;
+	ops->get_pending_flush = dpu_hw_ctl_get_pending_flush;
+	ops->get_flush_register = dpu_hw_ctl_get_flush_register;
+	ops->trigger_start = dpu_hw_ctl_trigger_start;
+	ops->is_started = dpu_hw_ctl_is_started;
+	ops->trigger_pending = dpu_hw_ctl_trigger_pending;
+	ops->reset = dpu_hw_ctl_reset_control;
+	ops->wait_reset_status = dpu_hw_ctl_wait_reset_status;
+	ops->clear_all_blendstages = dpu_hw_ctl_clear_all_blendstages;
+	ops->setup_blendstage = dpu_hw_ctl_setup_blendstage;
+	ops->update_pending_flush_sspp = dpu_hw_ctl_update_pending_flush_sspp;
+	ops->update_pending_flush_mixer = dpu_hw_ctl_update_pending_flush_mixer;
+	ops->update_pending_flush_dspp = dpu_hw_ctl_update_pending_flush_dspp;
+	if (cap & BIT(DPU_CTL_FETCH_ACTIVE))
+		ops->set_active_pipes = dpu_hw_ctl_set_fetch_pipe_active;
+};
+
+struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_ctl *c;
+	const struct dpu_ctl_cfg *cfg;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _ctl_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		pr_err("failed to create dpu_hw_ctl %d\n", idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->caps = cfg;
+	_setup_ctl_ops(&c->ops, c->caps->features);
+	c->idx = idx;
+	c->mixer_count = m->mixer_count;
+	c->mixer_hw_caps = m->mixer;
+
+	return c;
+}
+
+void dpu_hw_ctl_destroy(struct dpu_hw_ctl *ctx)
+{
+	kfree(ctx);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
new file mode 100644
index 000000000..96c012ec8
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
@@ -0,0 +1,277 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _DPU_HW_CTL_H
+#define _DPU_HW_CTL_H
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_sspp.h"
+
+/**
+ * dpu_ctl_mode_sel: Interface mode selection
+ * DPU_CTL_MODE_SEL_VID:    Video mode interface
+ * DPU_CTL_MODE_SEL_CMD:    Command mode interface
+ */
+enum dpu_ctl_mode_sel {
+	DPU_CTL_MODE_SEL_VID = 0,
+	DPU_CTL_MODE_SEL_CMD
+};
+
+struct dpu_hw_ctl;
+/**
+ * struct dpu_hw_stage_cfg - blending stage cfg
+ * @stage : SSPP_ID at each stage
+ * @multirect_index: index of the rectangle of SSPP.
+ */
+struct dpu_hw_stage_cfg {
+	enum dpu_sspp stage[DPU_STAGE_MAX][PIPES_PER_STAGE];
+	enum dpu_sspp_multirect_index multirect_index
+					[DPU_STAGE_MAX][PIPES_PER_STAGE];
+};
+
+/**
+ * struct dpu_hw_intf_cfg :Describes how the DPU writes data to output interface
+ * @intf :                 Interface id
+ * @mode_3d:               3d mux configuration
+ * @merge_3d:              3d merge block used
+ * @intf_mode_sel:         Interface mode, cmd / vid
+ * @stream_sel:            Stream selection for multi-stream interfaces
+ * @dsc:                   DSC BIT masks used
+ */
+struct dpu_hw_intf_cfg {
+	enum dpu_intf intf;
+	enum dpu_wb wb;
+	enum dpu_3d_blend_mode mode_3d;
+	enum dpu_merge_3d merge_3d;
+	enum dpu_ctl_mode_sel intf_mode_sel;
+	int stream_sel;
+	unsigned int dsc;
+};
+
+/**
+ * struct dpu_hw_ctl_ops - Interface to the wb Hw driver functions
+ * Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_ctl_ops {
+	/**
+	 * kickoff hw operation for Sw controlled interfaces
+	 * DSI cmd mode and WB interface are SW controlled
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*trigger_start)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * check if the ctl is started
+	 * @ctx       : ctl path ctx pointer
+	 * @Return: true if started, false if stopped
+	 */
+	bool (*is_started)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * kickoff prepare is in progress hw operation for sw
+	 * controlled interfaces: DSI cmd mode and WB interface
+	 * are SW controlled
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*trigger_pending)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Clear the value of the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*clear_pending_flush)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Query the value of the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	u32 (*get_pending_flush)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * OR in the given flushbits to the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 * @flushbits : module flushmask
+	 */
+	void (*update_pending_flush)(struct dpu_hw_ctl *ctx,
+		u32 flushbits);
+
+	/**
+	 * OR in the given flushbits to the cached pending_(wb_)flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 * @blk       : writeback block index
+	 */
+	void (*update_pending_flush_wb)(struct dpu_hw_ctl *ctx,
+		enum dpu_wb blk);
+
+	/**
+	 * OR in the given flushbits to the cached pending_(intf_)flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 * @blk       : interface block index
+	 */
+	void (*update_pending_flush_intf)(struct dpu_hw_ctl *ctx,
+		enum dpu_intf blk);
+
+	/**
+	 * OR in the given flushbits to the cached pending_(merge_3d_)flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 * @blk       : interface block index
+	 */
+	void (*update_pending_flush_merge_3d)(struct dpu_hw_ctl *ctx,
+		enum dpu_merge_3d blk);
+
+	/**
+	 * OR in the given flushbits to the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 * @blk       : SSPP block index
+	 */
+	void (*update_pending_flush_sspp)(struct dpu_hw_ctl *ctx,
+		enum dpu_sspp blk);
+
+	/**
+	 * OR in the given flushbits to the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 * @blk       : LM block index
+	 */
+	void (*update_pending_flush_mixer)(struct dpu_hw_ctl *ctx,
+		enum dpu_lm blk);
+
+	/**
+	 * OR in the given flushbits to the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 * @blk       : DSPP block index
+	 */
+	void (*update_pending_flush_dspp)(struct dpu_hw_ctl *ctx,
+		enum dpu_dspp blk);
+	/**
+	 * Write the value of the pending_flush_mask to hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*trigger_flush)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Read the value of the flush register
+	 * @ctx       : ctl path ctx pointer
+	 * @Return: value of the ctl flush register.
+	 */
+	u32 (*get_flush_register)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Setup ctl_path interface config
+	 * @ctx
+	 * @cfg    : interface config structure pointer
+	 */
+	void (*setup_intf_cfg)(struct dpu_hw_ctl *ctx,
+		struct dpu_hw_intf_cfg *cfg);
+
+	/**
+	 * reset ctl_path interface config
+	 * @ctx    : ctl path ctx pointer
+	 * @cfg    : interface config structure pointer
+	 */
+	void (*reset_intf_cfg)(struct dpu_hw_ctl *ctx,
+			struct dpu_hw_intf_cfg *cfg);
+
+	int (*reset)(struct dpu_hw_ctl *c);
+
+	/*
+	 * wait_reset_status - checks ctl reset status
+	 * @ctx       : ctl path ctx pointer
+	 *
+	 * This function checks the ctl reset status bit.
+	 * If the reset bit is set, it keeps polling the status till the hw
+	 * reset is complete.
+	 * Returns: 0 on success or -error if reset incomplete within interval
+	 */
+	int (*wait_reset_status)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Set all blend stages to disabled
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*clear_all_blendstages)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Configure layer mixer to pipe configuration
+	 * @ctx       : ctl path ctx pointer
+	 * @lm        : layer mixer enumeration
+	 * @cfg       : blend stage configuration
+	 */
+	void (*setup_blendstage)(struct dpu_hw_ctl *ctx,
+		enum dpu_lm lm, struct dpu_hw_stage_cfg *cfg);
+
+	void (*set_active_pipes)(struct dpu_hw_ctl *ctx,
+		unsigned long *fetch_active);
+};
+
+/**
+ * struct dpu_hw_ctl : CTL PATH driver object
+ * @base: hardware block base structure
+ * @hw: block register map object
+ * @idx: control path index
+ * @caps: control path capabilities
+ * @mixer_count: number of mixers
+ * @mixer_hw_caps: mixer hardware capabilities
+ * @pending_flush_mask: storage for pending ctl_flush managed via ops
+ * @pending_intf_flush_mask: pending INTF flush
+ * @pending_wb_flush_mask: pending WB flush
+ * @ops: operation list
+ */
+struct dpu_hw_ctl {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* ctl path */
+	int idx;
+	const struct dpu_ctl_cfg *caps;
+	int mixer_count;
+	const struct dpu_lm_cfg *mixer_hw_caps;
+	u32 pending_flush_mask;
+	u32 pending_intf_flush_mask;
+	u32 pending_wb_flush_mask;
+	u32 pending_merge_3d_flush_mask;
+
+	/* ops */
+	struct dpu_hw_ctl_ops ops;
+};
+
+/**
+ * dpu_hw_ctl - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_ctl *to_dpu_hw_ctl(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_ctl, base);
+}
+
+/**
+ * dpu_hw_ctl_init(): Initializes the ctl_path hw driver object.
+ * should be called before accessing every ctl path registers.
+ * @idx:  ctl_path index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_ctl_destroy(): Destroys ctl driver context
+ * should be called to free the context
+ */
+void dpu_hw_ctl_destroy(struct dpu_hw_ctl *ctx);
+
+#endif /*_DPU_HW_CTL_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c
new file mode 100644
index 000000000..c8f145558
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020-2022, Linaro Limited
+ */
+
+#include "dpu_kms.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_dsc.h"
+
+#define DSC_COMMON_MODE                 0x000
+#define DSC_ENC                         0x004
+#define DSC_PICTURE                     0x008
+#define DSC_SLICE                       0x00C
+#define DSC_CHUNK_SIZE                  0x010
+#define DSC_DELAY                       0x014
+#define DSC_SCALE_INITIAL               0x018
+#define DSC_SCALE_DEC_INTERVAL          0x01C
+#define DSC_SCALE_INC_INTERVAL          0x020
+#define DSC_FIRST_LINE_BPG_OFFSET       0x024
+#define DSC_BPG_OFFSET                  0x028
+#define DSC_DSC_OFFSET                  0x02C
+#define DSC_FLATNESS                    0x030
+#define DSC_RC_MODEL_SIZE               0x034
+#define DSC_RC                          0x038
+#define DSC_RC_BUF_THRESH               0x03C
+#define DSC_RANGE_MIN_QP                0x074
+#define DSC_RANGE_MAX_QP                0x0B0
+#define DSC_RANGE_BPG_OFFSET            0x0EC
+
+static void dpu_hw_dsc_disable(struct dpu_hw_dsc *dsc)
+{
+	struct dpu_hw_blk_reg_map *c = &dsc->hw;
+
+	DPU_REG_WRITE(c, DSC_COMMON_MODE, 0);
+}
+
+static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc,
+			      struct drm_dsc_config *dsc,
+			      u32 mode,
+			      u32 initial_lines)
+{
+	struct dpu_hw_blk_reg_map *c = &hw_dsc->hw;
+	u32 data;
+	u32 slice_last_group_size;
+	u32 det_thresh_flatness;
+	bool is_cmd_mode = !(mode & DSC_MODE_VIDEO);
+
+	DPU_REG_WRITE(c, DSC_COMMON_MODE, mode);
+
+	if (is_cmd_mode)
+		initial_lines += 1;
+
+	slice_last_group_size = (dsc->slice_width + 2) % 3;
+
+	data = (initial_lines << 20);
+	data |= (slice_last_group_size << 18);
+	/* bpp is 6.4 format, 4 LSBs bits are for fractional part */
+	data |= (dsc->bits_per_pixel << 8);
+	data |= (dsc->block_pred_enable << 7);
+	data |= (dsc->line_buf_depth << 3);
+	data |= (dsc->simple_422 << 2);
+	data |= (dsc->convert_rgb << 1);
+	data |= dsc->bits_per_component;
+
+	DPU_REG_WRITE(c, DSC_ENC, data);
+
+	data = dsc->pic_width << 16;
+	data |= dsc->pic_height;
+	DPU_REG_WRITE(c, DSC_PICTURE, data);
+
+	data = dsc->slice_width << 16;
+	data |= dsc->slice_height;
+	DPU_REG_WRITE(c, DSC_SLICE, data);
+
+	data = dsc->slice_chunk_size << 16;
+	DPU_REG_WRITE(c, DSC_CHUNK_SIZE, data);
+
+	data = dsc->initial_dec_delay << 16;
+	data |= dsc->initial_xmit_delay;
+	DPU_REG_WRITE(c, DSC_DELAY, data);
+
+	data = dsc->initial_scale_value;
+	DPU_REG_WRITE(c, DSC_SCALE_INITIAL, data);
+
+	data = dsc->scale_decrement_interval;
+	DPU_REG_WRITE(c, DSC_SCALE_DEC_INTERVAL, data);
+
+	data = dsc->scale_increment_interval;
+	DPU_REG_WRITE(c, DSC_SCALE_INC_INTERVAL, data);
+
+	data = dsc->first_line_bpg_offset;
+	DPU_REG_WRITE(c, DSC_FIRST_LINE_BPG_OFFSET, data);
+
+	data = dsc->nfl_bpg_offset << 16;
+	data |= dsc->slice_bpg_offset;
+	DPU_REG_WRITE(c, DSC_BPG_OFFSET, data);
+
+	data = dsc->initial_offset << 16;
+	data |= dsc->final_offset;
+	DPU_REG_WRITE(c, DSC_DSC_OFFSET, data);
+
+	det_thresh_flatness = 7 + 2 * (dsc->bits_per_component - 8);
+	data = det_thresh_flatness << 10;
+	data |= dsc->flatness_max_qp << 5;
+	data |= dsc->flatness_min_qp;
+	DPU_REG_WRITE(c, DSC_FLATNESS, data);
+
+	data = dsc->rc_model_size;
+	DPU_REG_WRITE(c, DSC_RC_MODEL_SIZE, data);
+
+	data = dsc->rc_tgt_offset_low << 18;
+	data |= dsc->rc_tgt_offset_high << 14;
+	data |= dsc->rc_quant_incr_limit1 << 9;
+	data |= dsc->rc_quant_incr_limit0 << 4;
+	data |= dsc->rc_edge_factor;
+	DPU_REG_WRITE(c, DSC_RC, data);
+}
+
+static void dpu_hw_dsc_config_thresh(struct dpu_hw_dsc *hw_dsc,
+				     struct drm_dsc_config *dsc)
+{
+	struct drm_dsc_rc_range_parameters *rc = dsc->rc_range_params;
+	struct dpu_hw_blk_reg_map *c = &hw_dsc->hw;
+	u32 off;
+	int i;
+
+	off = DSC_RC_BUF_THRESH;
+	for (i = 0; i < DSC_NUM_BUF_RANGES - 1 ; i++) {
+		DPU_REG_WRITE(c, off, dsc->rc_buf_thresh[i]);
+		off += 4;
+	}
+
+	off = DSC_RANGE_MIN_QP;
+	for (i = 0; i < DSC_NUM_BUF_RANGES; i++) {
+		DPU_REG_WRITE(c, off, rc[i].range_min_qp);
+		off += 4;
+	}
+
+	off = DSC_RANGE_MAX_QP;
+	for (i = 0; i < 15; i++) {
+		DPU_REG_WRITE(c, off, rc[i].range_max_qp);
+		off += 4;
+	}
+
+	off = DSC_RANGE_BPG_OFFSET;
+	for (i = 0; i < 15; i++) {
+		DPU_REG_WRITE(c, off, rc[i].range_bpg_offset);
+		off += 4;
+	}
+}
+
+static struct dpu_dsc_cfg *_dsc_offset(enum dpu_dsc dsc,
+				       const struct dpu_mdss_cfg *m,
+				       void __iomem *addr,
+				       struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->dsc_count; i++) {
+		if (dsc == m->dsc[i].id) {
+			b->blk_addr = addr + m->dsc[i].base;
+			b->log_mask = DPU_DBG_MASK_DSC;
+			return &m->dsc[i];
+		}
+	}
+
+	return NULL;
+}
+
+static void _setup_dsc_ops(struct dpu_hw_dsc_ops *ops,
+			   unsigned long cap)
+{
+	ops->dsc_disable = dpu_hw_dsc_disable;
+	ops->dsc_config = dpu_hw_dsc_config;
+	ops->dsc_config_thresh = dpu_hw_dsc_config_thresh;
+};
+
+struct dpu_hw_dsc *dpu_hw_dsc_init(enum dpu_dsc idx, void __iomem *addr,
+				   const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_dsc *c;
+	struct dpu_dsc_cfg *cfg;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _dsc_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->idx = idx;
+	c->caps = cfg;
+	_setup_dsc_ops(&c->ops, c->caps->features);
+
+	return c;
+}
+
+void dpu_hw_dsc_destroy(struct dpu_hw_dsc *dsc)
+{
+	kfree(dsc);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h
new file mode 100644
index 000000000..c0b77fe1a
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2020-2022, Linaro Limited */
+
+#ifndef _DPU_HW_DSC_H
+#define _DPU_HW_DSC_H
+
+#include <drm/display/drm_dsc.h>
+
+#define DSC_MODE_SPLIT_PANEL            BIT(0)
+#define DSC_MODE_MULTIPLEX              BIT(1)
+#define DSC_MODE_VIDEO                  BIT(2)
+
+struct dpu_hw_dsc;
+
+/**
+ * struct dpu_hw_dsc_ops - interface to the dsc hardware driver functions
+ * Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_dsc_ops {
+	/**
+	 * dsc_disable - disable dsc
+	 * @hw_dsc: Pointer to dsc context
+	 */
+	void (*dsc_disable)(struct dpu_hw_dsc *hw_dsc);
+
+	/**
+	 * dsc_config - configures dsc encoder
+	 * @hw_dsc: Pointer to dsc context
+	 * @dsc: panel dsc parameters
+	 * @mode: dsc topology mode to be set
+	 * @initial_lines: amount of initial lines to be used
+	 */
+	void (*dsc_config)(struct dpu_hw_dsc *hw_dsc,
+			   struct drm_dsc_config *dsc,
+			   u32 mode,
+			   u32 initial_lines);
+
+	/**
+	 * dsc_config_thresh - programs panel thresholds
+	 * @hw_dsc: Pointer to dsc context
+	 * @dsc: panel dsc parameters
+	 */
+	void (*dsc_config_thresh)(struct dpu_hw_dsc *hw_dsc,
+				  struct drm_dsc_config *dsc);
+};
+
+struct dpu_hw_dsc {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* dsc */
+	enum dpu_dsc idx;
+	const struct dpu_dsc_cfg *caps;
+
+	/* ops */
+	struct dpu_hw_dsc_ops ops;
+};
+
+/**
+ * dpu_hw_dsc_init - initializes the dsc block for the passed dsc idx.
+ * @idx:  DSC index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @m:    Pointer to mdss catalog data
+ * Returns: Error code or allocated dpu_hw_dsc context
+ */
+struct dpu_hw_dsc *dpu_hw_dsc_init(enum dpu_dsc idx, void __iomem *addr,
+				   const struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_dsc_destroy - destroys dsc driver context
+ * @dsc:   Pointer to dsc driver context returned by dpu_hw_dsc_init
+ */
+void dpu_hw_dsc_destroy(struct dpu_hw_dsc *dsc);
+
+static inline struct dpu_hw_dsc *to_dpu_hw_dsc(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_dsc, base);
+}
+
+#endif /* _DPU_HW_DSC_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
new file mode 100644
index 000000000..8ab5ace34
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_dspp.h"
+#include "dpu_kms.h"
+
+
+/* DSPP_PCC */
+#define PCC_EN BIT(0)
+#define PCC_DIS 0
+#define PCC_RED_R_OFF 0x10
+#define PCC_RED_G_OFF 0x1C
+#define PCC_RED_B_OFF 0x28
+#define PCC_GREEN_R_OFF 0x14
+#define PCC_GREEN_G_OFF 0x20
+#define PCC_GREEN_B_OFF 0x2C
+#define PCC_BLUE_R_OFF 0x18
+#define PCC_BLUE_G_OFF 0x24
+#define PCC_BLUE_B_OFF 0x30
+
+static void dpu_setup_dspp_pcc(struct dpu_hw_dspp *ctx,
+		struct dpu_hw_pcc_cfg *cfg)
+{
+
+	u32 base;
+
+	if (!ctx) {
+		DRM_ERROR("invalid ctx %pK\n", ctx);
+		return;
+	}
+
+	base = ctx->cap->sblk->pcc.base;
+
+	if (!base) {
+		DRM_ERROR("invalid ctx %pK pcc base 0x%x\n", ctx, base);
+		return;
+	}
+
+	if (!cfg) {
+		DRM_DEBUG_DRIVER("disable pcc feature\n");
+		DPU_REG_WRITE(&ctx->hw, base, PCC_DIS);
+		return;
+	}
+
+	DPU_REG_WRITE(&ctx->hw, base + PCC_RED_R_OFF, cfg->r.r);
+	DPU_REG_WRITE(&ctx->hw, base + PCC_RED_G_OFF, cfg->r.g);
+	DPU_REG_WRITE(&ctx->hw, base + PCC_RED_B_OFF, cfg->r.b);
+
+	DPU_REG_WRITE(&ctx->hw, base + PCC_GREEN_R_OFF, cfg->g.r);
+	DPU_REG_WRITE(&ctx->hw, base + PCC_GREEN_G_OFF, cfg->g.g);
+	DPU_REG_WRITE(&ctx->hw, base + PCC_GREEN_B_OFF, cfg->g.b);
+
+	DPU_REG_WRITE(&ctx->hw, base + PCC_BLUE_R_OFF, cfg->b.r);
+	DPU_REG_WRITE(&ctx->hw, base + PCC_BLUE_G_OFF, cfg->b.g);
+	DPU_REG_WRITE(&ctx->hw, base + PCC_BLUE_B_OFF, cfg->b.b);
+
+	DPU_REG_WRITE(&ctx->hw, base, PCC_EN);
+}
+
+static void _setup_dspp_ops(struct dpu_hw_dspp *c,
+		unsigned long features)
+{
+	if (test_bit(DPU_DSPP_PCC, &features))
+		c->ops.setup_pcc = dpu_setup_dspp_pcc;
+}
+
+static const struct dpu_dspp_cfg *_dspp_offset(enum dpu_dspp dspp,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	if (!m || !addr || !b)
+		return ERR_PTR(-EINVAL);
+
+	for (i = 0; i < m->dspp_count; i++) {
+		if (dspp == m->dspp[i].id) {
+			b->blk_addr = addr + m->dspp[i].base;
+			b->log_mask = DPU_DBG_MASK_DSPP;
+			return &m->dspp[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+struct dpu_hw_dspp *dpu_hw_dspp_init(enum dpu_dspp idx,
+			void __iomem *addr,
+			const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_dspp *c;
+	const struct dpu_dspp_cfg *cfg;
+
+	if (!addr || !m)
+		return ERR_PTR(-EINVAL);
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _dspp_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Assign ops */
+	c->idx = idx;
+	c->cap = cfg;
+	_setup_dspp_ops(c, c->cap->features);
+
+	return c;
+}
+
+void dpu_hw_dspp_destroy(struct dpu_hw_dspp *dspp)
+{
+	kfree(dspp);
+}
+
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.h
new file mode 100644
index 000000000..05ecfdfac
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.h
@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HW_DSPP_H
+#define _DPU_HW_DSPP_H
+
+struct dpu_hw_dspp;
+
+/**
+ * struct dpu_hw_pcc_coeff - PCC coefficient structure for each color
+ *                            component.
+ * @r: red coefficient.
+ * @g: green coefficient.
+ * @b: blue coefficient.
+ */
+
+struct dpu_hw_pcc_coeff {
+	__u32 r;
+	__u32 g;
+	__u32 b;
+};
+
+/**
+ * struct dpu_hw_pcc - pcc feature structure
+ * @r: red coefficients.
+ * @g: green coefficients.
+ * @b: blue coefficients.
+ */
+struct dpu_hw_pcc_cfg {
+	struct dpu_hw_pcc_coeff r;
+	struct dpu_hw_pcc_coeff g;
+	struct dpu_hw_pcc_coeff b;
+};
+
+/**
+ * struct dpu_hw_dspp_ops - interface to the dspp hardware driver functions
+ * Caller must call the init function to get the dspp context for each dspp
+ * Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_dspp_ops {
+	/**
+	 * setup_pcc - setup dspp pcc
+	 * @ctx: Pointer to dspp context
+	 * @cfg: Pointer to configuration
+	 */
+	void (*setup_pcc)(struct dpu_hw_dspp *ctx, struct dpu_hw_pcc_cfg *cfg);
+
+};
+
+/**
+ * struct dpu_hw_dspp - dspp description
+ * @base: Hardware block base structure
+ * @hw: Block hardware details
+ * @idx: DSPP index
+ * @cap: Pointer to layer_cfg
+ * @ops: Pointer to operations possible for this DSPP
+ */
+struct dpu_hw_dspp {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* dspp */
+	int idx;
+	const struct dpu_dspp_cfg *cap;
+
+	/* Ops */
+	struct dpu_hw_dspp_ops ops;
+};
+
+/**
+ * dpu_hw_dspp - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_dspp *to_dpu_hw_dspp(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_dspp, base);
+}
+
+/**
+ * dpu_hw_dspp_init - initializes the dspp hw driver object.
+ * should be called once before accessing every dspp.
+ * @idx:  DSPP index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @Return: pointer to structure or ERR_PTR
+ */
+struct dpu_hw_dspp *dpu_hw_dspp_init(enum dpu_dspp idx,
+	void __iomem *addr, const struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_dspp_destroy(): Destroys DSPP driver context
+ * @dspp: Pointer to DSPP driver context
+ */
+void dpu_hw_dspp_destroy(struct dpu_hw_dspp *dspp);
+
+#endif /*_DPU_HW_DSPP_H */
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
new file mode 100644
index 000000000..75e1b89c9
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
@@ -0,0 +1,574 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/bitops.h>
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+
+#include "dpu_core_irq.h"
+#include "dpu_kms.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_trace.h"
+
+/*
+ * Register offsets in MDSS register file for the interrupt registers
+ * w.r.t. the MDP base
+ */
+#define MDP_SSPP_TOP0_OFF		0x0
+#define MDP_INTF_0_OFF			0x6A000
+#define MDP_INTF_1_OFF			0x6A800
+#define MDP_INTF_2_OFF			0x6B000
+#define MDP_INTF_3_OFF			0x6B800
+#define MDP_INTF_4_OFF			0x6C000
+#define MDP_INTF_5_OFF			0x6C800
+#define INTF_INTR_EN			0x1c0
+#define INTF_INTR_STATUS		0x1c4
+#define INTF_INTR_CLEAR			0x1c8
+#define MDP_AD4_0_OFF			0x7C000
+#define MDP_AD4_1_OFF			0x7D000
+#define MDP_AD4_INTR_EN_OFF		0x41c
+#define MDP_AD4_INTR_CLEAR_OFF		0x424
+#define MDP_AD4_INTR_STATUS_OFF		0x420
+#define MDP_INTF_0_OFF_REV_7xxx             0x34000
+#define MDP_INTF_1_OFF_REV_7xxx             0x35000
+#define MDP_INTF_2_OFF_REV_7xxx             0x36000
+#define MDP_INTF_3_OFF_REV_7xxx             0x37000
+#define MDP_INTF_4_OFF_REV_7xxx             0x38000
+#define MDP_INTF_5_OFF_REV_7xxx             0x39000
+
+/**
+ * struct dpu_intr_reg - array of DPU register sets
+ * @clr_off:	offset to CLEAR reg
+ * @en_off:	offset to ENABLE reg
+ * @status_off:	offset to STATUS reg
+ */
+struct dpu_intr_reg {
+	u32 clr_off;
+	u32 en_off;
+	u32 status_off;
+};
+
+/*
+ * struct dpu_intr_reg -  List of DPU interrupt registers
+ *
+ * When making changes be sure to sync with dpu_hw_intr_reg
+ */
+static const struct dpu_intr_reg dpu_intr_set[] = {
+	[MDP_SSPP_TOP0_INTR] = {
+		MDP_SSPP_TOP0_OFF+INTR_CLEAR,
+		MDP_SSPP_TOP0_OFF+INTR_EN,
+		MDP_SSPP_TOP0_OFF+INTR_STATUS
+	},
+	[MDP_SSPP_TOP0_INTR2] = {
+		MDP_SSPP_TOP0_OFF+INTR2_CLEAR,
+		MDP_SSPP_TOP0_OFF+INTR2_EN,
+		MDP_SSPP_TOP0_OFF+INTR2_STATUS
+	},
+	[MDP_SSPP_TOP0_HIST_INTR] = {
+		MDP_SSPP_TOP0_OFF+HIST_INTR_CLEAR,
+		MDP_SSPP_TOP0_OFF+HIST_INTR_EN,
+		MDP_SSPP_TOP0_OFF+HIST_INTR_STATUS
+	},
+	[MDP_INTF0_INTR] = {
+		MDP_INTF_0_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_0_OFF+INTF_INTR_EN,
+		MDP_INTF_0_OFF+INTF_INTR_STATUS
+	},
+	[MDP_INTF1_INTR] = {
+		MDP_INTF_1_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_1_OFF+INTF_INTR_EN,
+		MDP_INTF_1_OFF+INTF_INTR_STATUS
+	},
+	[MDP_INTF2_INTR] = {
+		MDP_INTF_2_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_2_OFF+INTF_INTR_EN,
+		MDP_INTF_2_OFF+INTF_INTR_STATUS
+	},
+	[MDP_INTF3_INTR] = {
+		MDP_INTF_3_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_3_OFF+INTF_INTR_EN,
+		MDP_INTF_3_OFF+INTF_INTR_STATUS
+	},
+	[MDP_INTF4_INTR] = {
+		MDP_INTF_4_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_4_OFF+INTF_INTR_EN,
+		MDP_INTF_4_OFF+INTF_INTR_STATUS
+	},
+	[MDP_INTF5_INTR] = {
+		MDP_INTF_5_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_5_OFF+INTF_INTR_EN,
+		MDP_INTF_5_OFF+INTF_INTR_STATUS
+	},
+	[MDP_AD4_0_INTR] = {
+		MDP_AD4_0_OFF + MDP_AD4_INTR_CLEAR_OFF,
+		MDP_AD4_0_OFF + MDP_AD4_INTR_EN_OFF,
+		MDP_AD4_0_OFF + MDP_AD4_INTR_STATUS_OFF,
+	},
+	[MDP_AD4_1_INTR] = {
+		MDP_AD4_1_OFF + MDP_AD4_INTR_CLEAR_OFF,
+		MDP_AD4_1_OFF + MDP_AD4_INTR_EN_OFF,
+		MDP_AD4_1_OFF + MDP_AD4_INTR_STATUS_OFF,
+	},
+	[MDP_INTF0_7xxx_INTR] = {
+		MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_CLEAR,
+		MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_EN,
+		MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_STATUS
+	},
+	[MDP_INTF1_7xxx_INTR] = {
+		MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_CLEAR,
+		MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_EN,
+		MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_STATUS
+	},
+	[MDP_INTF2_7xxx_INTR] = {
+		MDP_INTF_2_OFF_REV_7xxx+INTF_INTR_CLEAR,
+		MDP_INTF_2_OFF_REV_7xxx+INTF_INTR_EN,
+		MDP_INTF_2_OFF_REV_7xxx+INTF_INTR_STATUS
+	},
+	[MDP_INTF3_7xxx_INTR] = {
+		MDP_INTF_3_OFF_REV_7xxx+INTF_INTR_CLEAR,
+		MDP_INTF_3_OFF_REV_7xxx+INTF_INTR_EN,
+		MDP_INTF_3_OFF_REV_7xxx+INTF_INTR_STATUS
+	},
+	[MDP_INTF4_7xxx_INTR] = {
+		MDP_INTF_4_OFF_REV_7xxx+INTF_INTR_CLEAR,
+		MDP_INTF_4_OFF_REV_7xxx+INTF_INTR_EN,
+		MDP_INTF_4_OFF_REV_7xxx+INTF_INTR_STATUS
+	},
+	[MDP_INTF5_7xxx_INTR] = {
+		MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_CLEAR,
+		MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_EN,
+		MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_STATUS
+	},
+};
+
+#define DPU_IRQ_REG(irq_idx)	(irq_idx / 32)
+#define DPU_IRQ_MASK(irq_idx)	(BIT(irq_idx % 32))
+
+/**
+ * dpu_core_irq_callback_handler - dispatch core interrupts
+ * @dpu_kms:		Pointer to DPU's KMS structure
+ * @irq_idx:		interrupt index
+ */
+static void dpu_core_irq_callback_handler(struct dpu_kms *dpu_kms, int irq_idx)
+{
+	VERB("irq_idx=%d\n", irq_idx);
+
+	if (!dpu_kms->hw_intr->irq_tbl[irq_idx].cb)
+		DRM_ERROR("no registered cb, idx:%d\n", irq_idx);
+
+	atomic_inc(&dpu_kms->hw_intr->irq_tbl[irq_idx].count);
+
+	/*
+	 * Perform registered function callback
+	 */
+	dpu_kms->hw_intr->irq_tbl[irq_idx].cb(dpu_kms->hw_intr->irq_tbl[irq_idx].arg, irq_idx);
+}
+
+irqreturn_t dpu_core_irq(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	struct dpu_hw_intr *intr = dpu_kms->hw_intr;
+	int reg_idx;
+	int irq_idx;
+	u32 irq_status;
+	u32 enable_mask;
+	int bit;
+	unsigned long irq_flags;
+
+	if (!intr)
+		return IRQ_NONE;
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	for (reg_idx = 0; reg_idx < ARRAY_SIZE(dpu_intr_set); reg_idx++) {
+		if (!test_bit(reg_idx, &intr->irq_mask))
+			continue;
+
+		/* Read interrupt status */
+		irq_status = DPU_REG_READ(&intr->hw, dpu_intr_set[reg_idx].status_off);
+
+		/* Read enable mask */
+		enable_mask = DPU_REG_READ(&intr->hw, dpu_intr_set[reg_idx].en_off);
+
+		/* and clear the interrupt */
+		if (irq_status)
+			DPU_REG_WRITE(&intr->hw, dpu_intr_set[reg_idx].clr_off,
+				     irq_status);
+
+		/* Finally update IRQ status based on enable mask */
+		irq_status &= enable_mask;
+
+		if (!irq_status)
+			continue;
+
+		/*
+		 * Search through matching intr status.
+		 */
+		while ((bit = ffs(irq_status)) != 0) {
+			irq_idx = DPU_IRQ_IDX(reg_idx, bit - 1);
+
+			dpu_core_irq_callback_handler(dpu_kms, irq_idx);
+
+			/*
+			 * When callback finish, clear the irq_status
+			 * with the matching mask. Once irq_status
+			 * is all cleared, the search can be stopped.
+			 */
+			irq_status &= ~BIT(bit - 1);
+		}
+	}
+
+	/* ensure register writes go through */
+	wmb();
+
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+
+	return IRQ_HANDLED;
+}
+
+static int dpu_hw_intr_enable_irq_locked(struct dpu_hw_intr *intr, int irq_idx)
+{
+	int reg_idx;
+	const struct dpu_intr_reg *reg;
+	const char *dbgstr = NULL;
+	uint32_t cache_irq_mask;
+
+	if (!intr)
+		return -EINVAL;
+
+	if (irq_idx < 0 || irq_idx >= intr->total_irqs) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	/*
+	 * The cache_irq_mask and hardware RMW operations needs to be done
+	 * under irq_lock and it's the caller's responsibility to ensure that's
+	 * held.
+	 */
+	assert_spin_locked(&intr->irq_lock);
+
+	reg_idx = DPU_IRQ_REG(irq_idx);
+	reg = &dpu_intr_set[reg_idx];
+
+	cache_irq_mask = intr->cache_irq_mask[reg_idx];
+	if (cache_irq_mask & DPU_IRQ_MASK(irq_idx)) {
+		dbgstr = "DPU IRQ already set:";
+	} else {
+		dbgstr = "DPU IRQ enabled:";
+
+		cache_irq_mask |= DPU_IRQ_MASK(irq_idx);
+		/* Cleaning any pending interrupt */
+		DPU_REG_WRITE(&intr->hw, reg->clr_off, DPU_IRQ_MASK(irq_idx));
+		/* Enabling interrupts with the new mask */
+		DPU_REG_WRITE(&intr->hw, reg->en_off, cache_irq_mask);
+
+		/* ensure register write goes through */
+		wmb();
+
+		intr->cache_irq_mask[reg_idx] = cache_irq_mask;
+	}
+
+	pr_debug("%s MASK:0x%.8lx, CACHE-MASK:0x%.8x\n", dbgstr,
+			DPU_IRQ_MASK(irq_idx), cache_irq_mask);
+
+	return 0;
+}
+
+static int dpu_hw_intr_disable_irq_locked(struct dpu_hw_intr *intr, int irq_idx)
+{
+	int reg_idx;
+	const struct dpu_intr_reg *reg;
+	const char *dbgstr = NULL;
+	uint32_t cache_irq_mask;
+
+	if (!intr)
+		return -EINVAL;
+
+	if (irq_idx < 0 || irq_idx >= intr->total_irqs) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	/*
+	 * The cache_irq_mask and hardware RMW operations needs to be done
+	 * under irq_lock and it's the caller's responsibility to ensure that's
+	 * held.
+	 */
+	assert_spin_locked(&intr->irq_lock);
+
+	reg_idx = DPU_IRQ_REG(irq_idx);
+	reg = &dpu_intr_set[reg_idx];
+
+	cache_irq_mask = intr->cache_irq_mask[reg_idx];
+	if ((cache_irq_mask & DPU_IRQ_MASK(irq_idx)) == 0) {
+		dbgstr = "DPU IRQ is already cleared:";
+	} else {
+		dbgstr = "DPU IRQ mask disable:";
+
+		cache_irq_mask &= ~DPU_IRQ_MASK(irq_idx);
+		/* Disable interrupts based on the new mask */
+		DPU_REG_WRITE(&intr->hw, reg->en_off, cache_irq_mask);
+		/* Cleaning any pending interrupt */
+		DPU_REG_WRITE(&intr->hw, reg->clr_off, DPU_IRQ_MASK(irq_idx));
+
+		/* ensure register write goes through */
+		wmb();
+
+		intr->cache_irq_mask[reg_idx] = cache_irq_mask;
+	}
+
+	pr_debug("%s MASK:0x%.8lx, CACHE-MASK:0x%.8x\n", dbgstr,
+			DPU_IRQ_MASK(irq_idx), cache_irq_mask);
+
+	return 0;
+}
+
+static void dpu_clear_irqs(struct dpu_kms *dpu_kms)
+{
+	struct dpu_hw_intr *intr = dpu_kms->hw_intr;
+	int i;
+
+	if (!intr)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) {
+		if (test_bit(i, &intr->irq_mask))
+			DPU_REG_WRITE(&intr->hw,
+					dpu_intr_set[i].clr_off, 0xffffffff);
+	}
+
+	/* ensure register writes go through */
+	wmb();
+}
+
+static void dpu_disable_all_irqs(struct dpu_kms *dpu_kms)
+{
+	struct dpu_hw_intr *intr = dpu_kms->hw_intr;
+	int i;
+
+	if (!intr)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) {
+		if (test_bit(i, &intr->irq_mask))
+			DPU_REG_WRITE(&intr->hw,
+					dpu_intr_set[i].en_off, 0x00000000);
+	}
+
+	/* ensure register writes go through */
+	wmb();
+}
+
+u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx)
+{
+	struct dpu_hw_intr *intr = dpu_kms->hw_intr;
+	int reg_idx;
+	unsigned long irq_flags;
+	u32 intr_status;
+
+	if (!intr)
+		return 0;
+
+	if (irq_idx < 0) {
+		DPU_ERROR("[%pS] invalid irq_idx=%d\n",
+				__builtin_return_address(0), irq_idx);
+		return 0;
+	}
+
+	if (irq_idx < 0 || irq_idx >= intr->total_irqs) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return 0;
+	}
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+
+	reg_idx = DPU_IRQ_REG(irq_idx);
+	intr_status = DPU_REG_READ(&intr->hw,
+			dpu_intr_set[reg_idx].status_off) &
+		DPU_IRQ_MASK(irq_idx);
+	if (intr_status)
+		DPU_REG_WRITE(&intr->hw, dpu_intr_set[reg_idx].clr_off,
+				intr_status);
+
+	/* ensure register writes go through */
+	wmb();
+
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+
+	return intr_status;
+}
+
+static void __intr_offset(const struct dpu_mdss_cfg *m,
+		void __iomem *addr, struct dpu_hw_blk_reg_map *hw)
+{
+	hw->blk_addr = addr + m->mdp[0].base;
+}
+
+struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_intr *intr;
+	int nirq = MDP_INTR_MAX * 32;
+
+	if (!addr || !m)
+		return ERR_PTR(-EINVAL);
+
+	intr = kzalloc(struct_size(intr, irq_tbl, nirq), GFP_KERNEL);
+	if (!intr)
+		return ERR_PTR(-ENOMEM);
+
+	__intr_offset(m, addr, &intr->hw);
+
+	intr->total_irqs = nirq;
+
+	intr->irq_mask = m->mdss_irqs;
+
+	spin_lock_init(&intr->irq_lock);
+
+	return intr;
+}
+
+void dpu_hw_intr_destroy(struct dpu_hw_intr *intr)
+{
+	kfree(intr);
+}
+
+int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int irq_idx,
+		void (*irq_cb)(void *arg, int irq_idx),
+		void *irq_arg)
+{
+	unsigned long irq_flags;
+	int ret;
+
+	if (!irq_cb) {
+		DPU_ERROR("invalid ird_idx:%d irq_cb:%ps\n", irq_idx, irq_cb);
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->total_irqs) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	VERB("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx);
+
+	spin_lock_irqsave(&dpu_kms->hw_intr->irq_lock, irq_flags);
+
+	if (unlikely(WARN_ON(dpu_kms->hw_intr->irq_tbl[irq_idx].cb))) {
+		spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags);
+
+		return -EBUSY;
+	}
+
+	trace_dpu_core_irq_register_callback(irq_idx, irq_cb);
+	dpu_kms->hw_intr->irq_tbl[irq_idx].arg = irq_arg;
+	dpu_kms->hw_intr->irq_tbl[irq_idx].cb = irq_cb;
+
+	ret = dpu_hw_intr_enable_irq_locked(
+				dpu_kms->hw_intr,
+				irq_idx);
+	if (ret)
+		DPU_ERROR("Fail to enable IRQ for irq_idx:%d\n",
+					irq_idx);
+	spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags);
+
+	trace_dpu_irq_register_success(irq_idx);
+
+	return 0;
+}
+
+int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx)
+{
+	unsigned long irq_flags;
+	int ret;
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->total_irqs) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	VERB("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx);
+
+	spin_lock_irqsave(&dpu_kms->hw_intr->irq_lock, irq_flags);
+	trace_dpu_core_irq_unregister_callback(irq_idx);
+
+	ret = dpu_hw_intr_disable_irq_locked(dpu_kms->hw_intr, irq_idx);
+	if (ret)
+		DPU_ERROR("Fail to disable IRQ for irq_idx:%d: %d\n",
+					irq_idx, ret);
+
+	dpu_kms->hw_intr->irq_tbl[irq_idx].cb = NULL;
+	dpu_kms->hw_intr->irq_tbl[irq_idx].arg = NULL;
+
+	spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags);
+
+	trace_dpu_irq_unregister_success(irq_idx);
+
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v)
+{
+	struct dpu_kms *dpu_kms = s->private;
+	unsigned long irq_flags;
+	int i, irq_count;
+	void *cb;
+
+	for (i = 0; i < dpu_kms->hw_intr->total_irqs; i++) {
+		spin_lock_irqsave(&dpu_kms->hw_intr->irq_lock, irq_flags);
+		irq_count = atomic_read(&dpu_kms->hw_intr->irq_tbl[i].count);
+		cb = dpu_kms->hw_intr->irq_tbl[i].cb;
+		spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags);
+
+		if (irq_count || cb)
+			seq_printf(s, "idx:%d irq:%d cb:%ps\n", i, irq_count, cb);
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(dpu_debugfs_core_irq);
+
+void dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent)
+{
+	debugfs_create_file("core_irq", 0600, parent, dpu_kms,
+		&dpu_debugfs_core_irq_fops);
+}
+#endif
+
+void dpu_core_irq_preinstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	int i;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	dpu_clear_irqs(dpu_kms);
+	dpu_disable_all_irqs(dpu_kms);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	for (i = 0; i < dpu_kms->hw_intr->total_irqs; i++)
+		atomic_set(&dpu_kms->hw_intr->irq_tbl[i].count, 0);
+}
+
+void dpu_core_irq_uninstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	int i;
+
+	if (!dpu_kms->hw_intr)
+		return;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	for (i = 0; i < dpu_kms->hw_intr->total_irqs; i++)
+		if (dpu_kms->hw_intr->irq_tbl[i].cb)
+			DPU_ERROR("irq_idx=%d still enabled/registered\n", i);
+
+	dpu_clear_irqs(dpu_kms);
+	dpu_disable_all_irqs(dpu_kms);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
new file mode 100644
index 000000000..464439554
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HW_INTERRUPTS_H
+#define _DPU_HW_INTERRUPTS_H
+
+#include <linux/types.h>
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_mdss.h"
+
+/* When making changes be sure to sync with dpu_intr_set */
+enum dpu_hw_intr_reg {
+	MDP_SSPP_TOP0_INTR,
+	MDP_SSPP_TOP0_INTR2,
+	MDP_SSPP_TOP0_HIST_INTR,
+	MDP_INTF0_INTR,
+	MDP_INTF1_INTR,
+	MDP_INTF2_INTR,
+	MDP_INTF3_INTR,
+	MDP_INTF4_INTR,
+	MDP_INTF5_INTR,
+	MDP_AD4_0_INTR,
+	MDP_AD4_1_INTR,
+	MDP_INTF0_7xxx_INTR,
+	MDP_INTF1_7xxx_INTR,
+	MDP_INTF2_7xxx_INTR,
+	MDP_INTF3_7xxx_INTR,
+	MDP_INTF4_7xxx_INTR,
+	MDP_INTF5_7xxx_INTR,
+	MDP_INTR_MAX,
+};
+
+#define DPU_IRQ_IDX(reg_idx, offset)	(reg_idx * 32 + offset)
+
+/**
+ * struct dpu_hw_intr: hw interrupts handling data structure
+ * @hw:               virtual address mapping
+ * @ops:              function pointer mapping for IRQ handling
+ * @cache_irq_mask:   array of IRQ enable masks reg storage created during init
+ * @save_irq_status:  array of IRQ status reg storage created during init
+ * @total_irqs: total number of irq_idx mapped in the hw_interrupts
+ * @irq_lock:         spinlock for accessing IRQ resources
+ * @irq_cb_tbl:       array of IRQ callbacks
+ */
+struct dpu_hw_intr {
+	struct dpu_hw_blk_reg_map hw;
+	u32 cache_irq_mask[MDP_INTR_MAX];
+	u32 *save_irq_status;
+	u32 total_irqs;
+	spinlock_t irq_lock;
+	unsigned long irq_mask;
+
+	struct {
+		void (*cb)(void *arg, int irq_idx);
+		void *arg;
+		atomic_t count;
+	} irq_tbl[];
+};
+
+/**
+ * dpu_hw_intr_init(): Initializes the interrupts hw object
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_intr_destroy(): Cleanup interrutps hw object
+ * @intr: pointer to interrupts hw object
+ */
+void dpu_hw_intr_destroy(struct dpu_hw_intr *intr);
+#endif
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
new file mode 100644
index 000000000..384558d2f
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_intf.h"
+#include "dpu_kms.h"
+
+#define INTF_TIMING_ENGINE_EN           0x000
+#define INTF_CONFIG                     0x004
+#define INTF_HSYNC_CTL                  0x008
+#define INTF_VSYNC_PERIOD_F0            0x00C
+#define INTF_VSYNC_PERIOD_F1            0x010
+#define INTF_VSYNC_PULSE_WIDTH_F0       0x014
+#define INTF_VSYNC_PULSE_WIDTH_F1       0x018
+#define INTF_DISPLAY_V_START_F0         0x01C
+#define INTF_DISPLAY_V_START_F1         0x020
+#define INTF_DISPLAY_V_END_F0           0x024
+#define INTF_DISPLAY_V_END_F1           0x028
+#define INTF_ACTIVE_V_START_F0          0x02C
+#define INTF_ACTIVE_V_START_F1          0x030
+#define INTF_ACTIVE_V_END_F0            0x034
+#define INTF_ACTIVE_V_END_F1            0x038
+#define INTF_DISPLAY_HCTL               0x03C
+#define INTF_ACTIVE_HCTL                0x040
+#define INTF_BORDER_COLOR               0x044
+#define INTF_UNDERFLOW_COLOR            0x048
+#define INTF_HSYNC_SKEW                 0x04C
+#define INTF_POLARITY_CTL               0x050
+#define INTF_TEST_CTL                   0x054
+#define INTF_TP_COLOR0                  0x058
+#define INTF_TP_COLOR1                  0x05C
+#define INTF_CONFIG2                    0x060
+#define INTF_DISPLAY_DATA_HCTL          0x064
+#define INTF_ACTIVE_DATA_HCTL           0x068
+#define INTF_FRAME_LINE_COUNT_EN        0x0A8
+#define INTF_FRAME_COUNT                0x0AC
+#define   INTF_LINE_COUNT               0x0B0
+
+#define   INTF_DEFLICKER_CONFIG         0x0F0
+#define   INTF_DEFLICKER_STRNG_COEFF    0x0F4
+#define   INTF_DEFLICKER_WEAK_COEFF     0x0F8
+
+#define   INTF_DSI_CMD_MODE_TRIGGER_EN  0x084
+#define   INTF_PANEL_FORMAT             0x090
+#define   INTF_TPG_ENABLE               0x100
+#define   INTF_TPG_MAIN_CONTROL         0x104
+#define   INTF_TPG_VIDEO_CONFIG         0x108
+#define   INTF_TPG_COMPONENT_LIMITS     0x10C
+#define   INTF_TPG_RECTANGLE            0x110
+#define   INTF_TPG_INITIAL_VALUE        0x114
+#define   INTF_TPG_BLK_WHITE_PATTERN_FRAMES   0x118
+#define   INTF_TPG_RGB_MAPPING          0x11C
+#define   INTF_PROG_FETCH_START         0x170
+#define   INTF_PROG_ROT_START           0x174
+#define   INTF_MUX                      0x25C
+#define   INTF_STATUS                   0x26C
+
+#define INTF_CFG_ACTIVE_H_EN	BIT(29)
+#define INTF_CFG_ACTIVE_V_EN	BIT(30)
+
+#define INTF_CFG2_DATABUS_WIDEN	BIT(0)
+#define INTF_CFG2_DATA_HCTL_EN	BIT(4)
+
+#define INTF_MISR_CTRL			0x180
+#define INTF_MISR_SIGNATURE		0x184
+
+static const struct dpu_intf_cfg *_intf_offset(enum dpu_intf intf,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->intf_count; i++) {
+		if ((intf == m->intf[i].id) &&
+		(m->intf[i].type != INTF_NONE)) {
+			b->blk_addr = addr + m->intf[i].base;
+			b->log_mask = DPU_DBG_MASK_INTF;
+			return &m->intf[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx,
+		const struct intf_timing_params *p,
+		const struct dpu_format *fmt)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 hsync_period, vsync_period;
+	u32 display_v_start, display_v_end;
+	u32 hsync_start_x, hsync_end_x;
+	u32 hsync_data_start_x, hsync_data_end_x;
+	u32 active_h_start, active_h_end;
+	u32 active_v_start, active_v_end;
+	u32 active_hctl, display_hctl, hsync_ctl;
+	u32 polarity_ctl, den_polarity, hsync_polarity, vsync_polarity;
+	u32 panel_format;
+	u32 intf_cfg, intf_cfg2 = 0;
+	u32 display_data_hctl = 0, active_data_hctl = 0;
+	u32 data_width;
+	bool dp_intf = false;
+
+	/* read interface_cfg */
+	intf_cfg = DPU_REG_READ(c, INTF_CONFIG);
+
+	if (ctx->cap->type == INTF_DP)
+		dp_intf = true;
+
+	hsync_period = p->hsync_pulse_width + p->h_back_porch + p->width +
+	p->h_front_porch;
+	vsync_period = p->vsync_pulse_width + p->v_back_porch + p->height +
+	p->v_front_porch;
+
+	display_v_start = ((p->vsync_pulse_width + p->v_back_porch) *
+	hsync_period) + p->hsync_skew;
+	display_v_end = ((vsync_period - p->v_front_porch) * hsync_period) +
+	p->hsync_skew - 1;
+
+	hsync_start_x = p->h_back_porch + p->hsync_pulse_width;
+	hsync_end_x = hsync_period - p->h_front_porch - 1;
+
+	if (p->width != p->xres) { /* border fill added */
+		active_h_start = hsync_start_x;
+		active_h_end = active_h_start + p->xres - 1;
+	} else {
+		active_h_start = 0;
+		active_h_end = 0;
+	}
+
+	if (p->height != p->yres) { /* border fill added */
+		active_v_start = display_v_start;
+		active_v_end = active_v_start + (p->yres * hsync_period) - 1;
+	} else {
+		active_v_start = 0;
+		active_v_end = 0;
+	}
+
+	if (active_h_end) {
+		active_hctl = (active_h_end << 16) | active_h_start;
+		intf_cfg |= INTF_CFG_ACTIVE_H_EN;
+	} else {
+		active_hctl = 0;
+	}
+
+	if (active_v_end)
+		intf_cfg |= INTF_CFG_ACTIVE_V_EN;
+
+	hsync_ctl = (hsync_period << 16) | p->hsync_pulse_width;
+	display_hctl = (hsync_end_x << 16) | hsync_start_x;
+
+	/*
+	 * DATA_HCTL_EN controls data timing which can be different from
+	 * video timing. It is recommended to enable it for all cases, except
+	 * if compression is enabled in 1 pixel per clock mode
+	 */
+	if (p->wide_bus_en)
+		intf_cfg2 |= INTF_CFG2_DATABUS_WIDEN | INTF_CFG2_DATA_HCTL_EN;
+
+	data_width = p->width;
+
+	hsync_data_start_x = hsync_start_x;
+	hsync_data_end_x =  hsync_start_x + data_width - 1;
+
+	display_data_hctl = (hsync_data_end_x << 16) | hsync_data_start_x;
+
+	if (dp_intf) {
+		/* DP timing adjustment */
+		display_v_start += p->hsync_pulse_width + p->h_back_porch;
+		display_v_end   -= p->h_front_porch;
+
+		active_h_start = hsync_start_x;
+		active_h_end = active_h_start + p->xres - 1;
+		active_v_start = display_v_start;
+		active_v_end = active_v_start + (p->yres * hsync_period) - 1;
+
+		active_hctl = (active_h_end << 16) | active_h_start;
+		display_hctl = active_hctl;
+
+		intf_cfg |= INTF_CFG_ACTIVE_H_EN | INTF_CFG_ACTIVE_V_EN;
+	}
+
+	den_polarity = 0;
+	if (ctx->cap->type == INTF_HDMI) {
+		hsync_polarity = p->yres >= 720 ? 0 : 1;
+		vsync_polarity = p->yres >= 720 ? 0 : 1;
+	} else if (ctx->cap->type == INTF_DP) {
+		hsync_polarity = p->hsync_polarity;
+		vsync_polarity = p->vsync_polarity;
+	} else {
+		hsync_polarity = 0;
+		vsync_polarity = 0;
+	}
+	polarity_ctl = (den_polarity << 2) | /*  DEN Polarity  */
+		(vsync_polarity << 1) | /* VSYNC Polarity */
+		(hsync_polarity << 0);  /* HSYNC Polarity */
+
+	if (!DPU_FORMAT_IS_YUV(fmt))
+		panel_format = (fmt->bits[C0_G_Y] |
+				(fmt->bits[C1_B_Cb] << 2) |
+				(fmt->bits[C2_R_Cr] << 4) |
+				(0x21 << 8));
+	else
+		/* Interface treats all the pixel data in RGB888 format */
+		panel_format = (COLOR_8BIT |
+				(COLOR_8BIT << 2) |
+				(COLOR_8BIT << 4) |
+				(0x21 << 8));
+
+	DPU_REG_WRITE(c, INTF_HSYNC_CTL, hsync_ctl);
+	DPU_REG_WRITE(c, INTF_VSYNC_PERIOD_F0, vsync_period * hsync_period);
+	DPU_REG_WRITE(c, INTF_VSYNC_PULSE_WIDTH_F0,
+			p->vsync_pulse_width * hsync_period);
+	DPU_REG_WRITE(c, INTF_DISPLAY_HCTL, display_hctl);
+	DPU_REG_WRITE(c, INTF_DISPLAY_V_START_F0, display_v_start);
+	DPU_REG_WRITE(c, INTF_DISPLAY_V_END_F0, display_v_end);
+	DPU_REG_WRITE(c, INTF_ACTIVE_HCTL,  active_hctl);
+	DPU_REG_WRITE(c, INTF_ACTIVE_V_START_F0, active_v_start);
+	DPU_REG_WRITE(c, INTF_ACTIVE_V_END_F0, active_v_end);
+	DPU_REG_WRITE(c, INTF_BORDER_COLOR, p->border_clr);
+	DPU_REG_WRITE(c, INTF_UNDERFLOW_COLOR, p->underflow_clr);
+	DPU_REG_WRITE(c, INTF_HSYNC_SKEW, p->hsync_skew);
+	DPU_REG_WRITE(c, INTF_POLARITY_CTL, polarity_ctl);
+	DPU_REG_WRITE(c, INTF_FRAME_LINE_COUNT_EN, 0x3);
+	DPU_REG_WRITE(c, INTF_CONFIG, intf_cfg);
+	DPU_REG_WRITE(c, INTF_PANEL_FORMAT, panel_format);
+	if (ctx->cap->features & BIT(DPU_DATA_HCTL_EN)) {
+		DPU_REG_WRITE(c, INTF_CONFIG2, intf_cfg2);
+		DPU_REG_WRITE(c, INTF_DISPLAY_DATA_HCTL, display_data_hctl);
+		DPU_REG_WRITE(c, INTF_ACTIVE_DATA_HCTL, active_data_hctl);
+	}
+}
+
+static void dpu_hw_intf_enable_timing_engine(
+		struct dpu_hw_intf *intf,
+		u8 enable)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	/* Note: Display interface select is handled in top block hw layer */
+	DPU_REG_WRITE(c, INTF_TIMING_ENGINE_EN, enable != 0);
+}
+
+static void dpu_hw_intf_setup_prg_fetch(
+		struct dpu_hw_intf *intf,
+		const struct intf_prog_fetch *fetch)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	int fetch_enable;
+
+	/*
+	 * Fetch should always be outside the active lines. If the fetching
+	 * is programmed within active region, hardware behavior is unknown.
+	 */
+
+	fetch_enable = DPU_REG_READ(c, INTF_CONFIG);
+	if (fetch->enable) {
+		fetch_enable |= BIT(31);
+		DPU_REG_WRITE(c, INTF_PROG_FETCH_START,
+				fetch->fetch_start);
+	} else {
+		fetch_enable &= ~BIT(31);
+	}
+
+	DPU_REG_WRITE(c, INTF_CONFIG, fetch_enable);
+}
+
+static void dpu_hw_intf_bind_pingpong_blk(
+		struct dpu_hw_intf *intf,
+		bool enable,
+		const enum dpu_pingpong pp)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	u32 mux_cfg;
+
+	mux_cfg = DPU_REG_READ(c, INTF_MUX);
+	mux_cfg &= ~0xf;
+
+	if (enable)
+		mux_cfg |= (pp - PINGPONG_0) & 0x7;
+	else
+		mux_cfg |= 0xf;
+
+	DPU_REG_WRITE(c, INTF_MUX, mux_cfg);
+}
+
+static void dpu_hw_intf_get_status(
+		struct dpu_hw_intf *intf,
+		struct intf_status *s)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	unsigned long cap = intf->cap->features;
+
+	if (cap & BIT(DPU_INTF_STATUS_SUPPORTED))
+		s->is_en = DPU_REG_READ(c, INTF_STATUS) & BIT(0);
+	else
+		s->is_en = DPU_REG_READ(c, INTF_TIMING_ENGINE_EN);
+
+	s->is_prog_fetch_en = !!(DPU_REG_READ(c, INTF_CONFIG) & BIT(31));
+	if (s->is_en) {
+		s->frame_count = DPU_REG_READ(c, INTF_FRAME_COUNT);
+		s->line_count = DPU_REG_READ(c, INTF_LINE_COUNT);
+	} else {
+		s->line_count = 0;
+		s->frame_count = 0;
+	}
+}
+
+static u32 dpu_hw_intf_get_line_count(struct dpu_hw_intf *intf)
+{
+	struct dpu_hw_blk_reg_map *c;
+
+	if (!intf)
+		return 0;
+
+	c = &intf->hw;
+
+	return DPU_REG_READ(c, INTF_LINE_COUNT);
+}
+
+static void dpu_hw_intf_setup_misr(struct dpu_hw_intf *intf)
+{
+	dpu_hw_setup_misr(&intf->hw, INTF_MISR_CTRL, 0x1);
+}
+
+static int dpu_hw_intf_collect_misr(struct dpu_hw_intf *intf, u32 *misr_value)
+{
+	return dpu_hw_collect_misr(&intf->hw, INTF_MISR_CTRL, INTF_MISR_SIGNATURE, misr_value);
+}
+
+static void _setup_intf_ops(struct dpu_hw_intf_ops *ops,
+		unsigned long cap)
+{
+	ops->setup_timing_gen = dpu_hw_intf_setup_timing_engine;
+	ops->setup_prg_fetch  = dpu_hw_intf_setup_prg_fetch;
+	ops->get_status = dpu_hw_intf_get_status;
+	ops->enable_timing = dpu_hw_intf_enable_timing_engine;
+	ops->get_line_count = dpu_hw_intf_get_line_count;
+	if (cap & BIT(DPU_INTF_INPUT_CTRL))
+		ops->bind_pingpong_blk = dpu_hw_intf_bind_pingpong_blk;
+	ops->setup_misr = dpu_hw_intf_setup_misr;
+	ops->collect_misr = dpu_hw_intf_collect_misr;
+}
+
+struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_intf *c;
+	const struct dpu_intf_cfg *cfg;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _intf_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		pr_err("failed to create dpu_hw_intf %d\n", idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Assign ops
+	 */
+	c->idx = idx;
+	c->cap = cfg;
+	c->mdss = m;
+	_setup_intf_ops(&c->ops, c->cap->features);
+
+	return c;
+}
+
+void dpu_hw_intf_destroy(struct dpu_hw_intf *intf)
+{
+	kfree(intf);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
new file mode 100644
index 000000000..e75339b96
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
@@ -0,0 +1,116 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HW_INTF_H
+#define _DPU_HW_INTF_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+struct dpu_hw_intf;
+
+/* intf timing settings */
+struct intf_timing_params {
+	u32 width;		/* active width */
+	u32 height;		/* active height */
+	u32 xres;		/* Display panel width */
+	u32 yres;		/* Display panel height */
+
+	u32 h_back_porch;
+	u32 h_front_porch;
+	u32 v_back_porch;
+	u32 v_front_porch;
+	u32 hsync_pulse_width;
+	u32 vsync_pulse_width;
+	u32 hsync_polarity;
+	u32 vsync_polarity;
+	u32 border_clr;
+	u32 underflow_clr;
+	u32 hsync_skew;
+
+	bool wide_bus_en;
+};
+
+struct intf_prog_fetch {
+	u8 enable;
+	/* vsync counter for the front porch pixel line */
+	u32 fetch_start;
+};
+
+struct intf_status {
+	u8 is_en;		/* interface timing engine is enabled or not */
+	u8 is_prog_fetch_en;	/* interface prog fetch counter is enabled or not */
+	u32 frame_count;	/* frame count since timing engine enabled */
+	u32 line_count;		/* current line count including blanking */
+};
+
+/**
+ * struct dpu_hw_intf_ops : Interface to the interface Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ * @ setup_timing_gen : programs the timing engine
+ * @ setup_prog_fetch : enables/disables the programmable fetch logic
+ * @ enable_timing: enable/disable timing engine
+ * @ get_status: returns if timing engine is enabled or not
+ * @ get_line_count: reads current vertical line counter
+ * @bind_pingpong_blk: enable/disable the connection with pingpong which will
+ *                     feed pixels to this interface
+ * @setup_misr: enable/disable MISR
+ * @collect_misr: read MISR signature
+ */
+struct dpu_hw_intf_ops {
+	void (*setup_timing_gen)(struct dpu_hw_intf *intf,
+			const struct intf_timing_params *p,
+			const struct dpu_format *fmt);
+
+	void (*setup_prg_fetch)(struct dpu_hw_intf *intf,
+			const struct intf_prog_fetch *fetch);
+
+	void (*enable_timing)(struct dpu_hw_intf *intf,
+			u8 enable);
+
+	void (*get_status)(struct dpu_hw_intf *intf,
+			struct intf_status *status);
+
+	u32 (*get_line_count)(struct dpu_hw_intf *intf);
+
+	void (*bind_pingpong_blk)(struct dpu_hw_intf *intf,
+			bool enable,
+			const enum dpu_pingpong pp);
+	void (*setup_misr)(struct dpu_hw_intf *intf);
+	int (*collect_misr)(struct dpu_hw_intf *intf, u32 *misr_value);
+};
+
+struct dpu_hw_intf {
+	struct dpu_hw_blk_reg_map hw;
+
+	/* intf */
+	enum dpu_intf idx;
+	const struct dpu_intf_cfg *cap;
+	const struct dpu_mdss_cfg *mdss;
+
+	/* ops */
+	struct dpu_hw_intf_ops ops;
+};
+
+/**
+ * dpu_hw_intf_init(): Initializes the intf driver for the passed
+ * interface idx.
+ * @idx:  interface index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_intf_destroy(): Destroys INTF driver context
+ * @intf:   Pointer to INTF driver context
+ */
+void dpu_hw_intf_destroy(struct dpu_hw_intf *intf);
+
+#endif /*_DPU_HW_INTF_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
new file mode 100644
index 000000000..cc04fb979
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2015-2021, The Linux Foundation. All rights reserved.
+ */
+
+#include "dpu_kms.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_mdss.h"
+
+#define LM_OP_MODE                        0x00
+#define LM_OUT_SIZE                       0x04
+#define LM_BORDER_COLOR_0                 0x08
+#define LM_BORDER_COLOR_1                 0x010
+
+/* These register are offset to mixer base + stage base */
+#define LM_BLEND0_OP                     0x00
+#define LM_BLEND0_CONST_ALPHA            0x04
+#define LM_FG_COLOR_FILL_COLOR_0         0x08
+#define LM_FG_COLOR_FILL_COLOR_1         0x0C
+#define LM_FG_COLOR_FILL_SIZE            0x10
+#define LM_FG_COLOR_FILL_XY              0x14
+
+#define LM_BLEND0_FG_ALPHA               0x04
+#define LM_BLEND0_BG_ALPHA               0x08
+
+#define LM_MISR_CTRL                     0x310
+#define LM_MISR_SIGNATURE                0x314
+
+
+static const struct dpu_lm_cfg *_lm_offset(enum dpu_lm mixer,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->mixer_count; i++) {
+		if (mixer == m->mixer[i].id) {
+			b->blk_addr = addr + m->mixer[i].base;
+			b->log_mask = DPU_DBG_MASK_LM;
+			return &m->mixer[i];
+		}
+	}
+
+	return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * _stage_offset(): returns the relative offset of the blend registers
+ * for the stage to be setup
+ * @ctx:     mixer ctx contains the mixer to be programmed
+ * @stage: stage index to setup
+ */
+static inline int _stage_offset(struct dpu_hw_mixer *ctx, enum dpu_stage stage)
+{
+	const struct dpu_lm_sub_blks *sblk = ctx->cap->sblk;
+	if (stage != DPU_STAGE_BASE && stage <= sblk->maxblendstages)
+		return sblk->blendstage_base[stage - DPU_STAGE_0];
+
+	return -EINVAL;
+}
+
+static void dpu_hw_lm_setup_out(struct dpu_hw_mixer *ctx,
+		struct dpu_hw_mixer_cfg *mixer)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 outsize;
+	u32 op_mode;
+
+	op_mode = DPU_REG_READ(c, LM_OP_MODE);
+
+	outsize = mixer->out_height << 16 | mixer->out_width;
+	DPU_REG_WRITE(c, LM_OUT_SIZE, outsize);
+
+	/* SPLIT_LEFT_RIGHT */
+	if (mixer->right_mixer)
+		op_mode |= BIT(31);
+	else
+		op_mode &= ~BIT(31);
+	DPU_REG_WRITE(c, LM_OP_MODE, op_mode);
+}
+
+static void dpu_hw_lm_setup_border_color(struct dpu_hw_mixer *ctx,
+		struct dpu_mdss_color *color,
+		u8 border_en)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	if (border_en) {
+		DPU_REG_WRITE(c, LM_BORDER_COLOR_0,
+			(color->color_0 & 0xFFF) |
+			((color->color_1 & 0xFFF) << 0x10));
+		DPU_REG_WRITE(c, LM_BORDER_COLOR_1,
+			(color->color_2 & 0xFFF) |
+			((color->color_3 & 0xFFF) << 0x10));
+	}
+}
+
+static void dpu_hw_lm_setup_misr(struct dpu_hw_mixer *ctx)
+{
+	dpu_hw_setup_misr(&ctx->hw, LM_MISR_CTRL, 0x0);
+}
+
+static int dpu_hw_lm_collect_misr(struct dpu_hw_mixer *ctx, u32 *misr_value)
+{
+	return dpu_hw_collect_misr(&ctx->hw, LM_MISR_CTRL, LM_MISR_SIGNATURE, misr_value);
+}
+
+static void dpu_hw_lm_setup_blend_config_combined_alpha(struct dpu_hw_mixer *ctx,
+	u32 stage, u32 fg_alpha, u32 bg_alpha, u32 blend_op)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int stage_off;
+	u32 const_alpha;
+
+	if (stage == DPU_STAGE_BASE)
+		return;
+
+	stage_off = _stage_offset(ctx, stage);
+	if (WARN_ON(stage_off < 0))
+		return;
+
+	const_alpha = (bg_alpha & 0xFF) | ((fg_alpha & 0xFF) << 16);
+	DPU_REG_WRITE(c, LM_BLEND0_CONST_ALPHA + stage_off, const_alpha);
+	DPU_REG_WRITE(c, LM_BLEND0_OP + stage_off, blend_op);
+}
+
+static void dpu_hw_lm_setup_blend_config(struct dpu_hw_mixer *ctx,
+	u32 stage, u32 fg_alpha, u32 bg_alpha, u32 blend_op)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int stage_off;
+
+	if (stage == DPU_STAGE_BASE)
+		return;
+
+	stage_off = _stage_offset(ctx, stage);
+	if (WARN_ON(stage_off < 0))
+		return;
+
+	DPU_REG_WRITE(c, LM_BLEND0_FG_ALPHA + stage_off, fg_alpha);
+	DPU_REG_WRITE(c, LM_BLEND0_BG_ALPHA + stage_off, bg_alpha);
+	DPU_REG_WRITE(c, LM_BLEND0_OP + stage_off, blend_op);
+}
+
+static void dpu_hw_lm_setup_color3(struct dpu_hw_mixer *ctx,
+	uint32_t mixer_op_mode)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int op_mode;
+
+	/* read the existing op_mode configuration */
+	op_mode = DPU_REG_READ(c, LM_OP_MODE);
+
+	op_mode = (op_mode & (BIT(31) | BIT(30))) | mixer_op_mode;
+
+	DPU_REG_WRITE(c, LM_OP_MODE, op_mode);
+}
+
+static void _setup_mixer_ops(const struct dpu_mdss_cfg *m,
+		struct dpu_hw_lm_ops *ops,
+		unsigned long features)
+{
+	ops->setup_mixer_out = dpu_hw_lm_setup_out;
+	if (test_bit(DPU_MIXER_COMBINED_ALPHA, &features))
+		ops->setup_blend_config = dpu_hw_lm_setup_blend_config_combined_alpha;
+	else
+		ops->setup_blend_config = dpu_hw_lm_setup_blend_config;
+	ops->setup_alpha_out = dpu_hw_lm_setup_color3;
+	ops->setup_border_color = dpu_hw_lm_setup_border_color;
+	ops->setup_misr = dpu_hw_lm_setup_misr;
+	ops->collect_misr = dpu_hw_lm_collect_misr;
+}
+
+struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_mixer *c;
+	const struct dpu_lm_cfg *cfg;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _lm_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Assign ops */
+	c->idx = idx;
+	c->cap = cfg;
+	_setup_mixer_ops(m, &c->ops, c->cap->features);
+
+	return c;
+}
+
+void dpu_hw_lm_destroy(struct dpu_hw_mixer *lm)
+{
+	kfree(lm);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
new file mode 100644
index 000000000..0a050eb24
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2015-2021, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HW_LM_H
+#define _DPU_HW_LM_H
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+struct dpu_hw_mixer;
+
+struct dpu_hw_mixer_cfg {
+	u32 out_width;
+	u32 out_height;
+	bool right_mixer;
+	int flags;
+};
+
+struct dpu_hw_color3_cfg {
+	u8 keep_fg[DPU_STAGE_MAX];
+};
+
+/**
+ *
+ * struct dpu_hw_lm_ops : Interface to the mixer Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_lm_ops {
+	/*
+	 * Sets up mixer output width and height
+	 * and border color if enabled
+	 */
+	void (*setup_mixer_out)(struct dpu_hw_mixer *ctx,
+		struct dpu_hw_mixer_cfg *cfg);
+
+	/*
+	 * Alpha blending configuration
+	 * for the specified stage
+	 */
+	void (*setup_blend_config)(struct dpu_hw_mixer *ctx, uint32_t stage,
+		uint32_t fg_alpha, uint32_t bg_alpha, uint32_t blend_op);
+
+	/*
+	 * Alpha color component selection from either fg or bg
+	 */
+	void (*setup_alpha_out)(struct dpu_hw_mixer *ctx, uint32_t mixer_op);
+
+	/**
+	 * setup_border_color : enable/disable border color
+	 */
+	void (*setup_border_color)(struct dpu_hw_mixer *ctx,
+		struct dpu_mdss_color *color,
+		u8 border_en);
+
+	/**
+	 * setup_misr: Enable/disable MISR
+	 */
+	void (*setup_misr)(struct dpu_hw_mixer *ctx);
+
+	/**
+	 * collect_misr: Read MISR signature
+	 */
+	int (*collect_misr)(struct dpu_hw_mixer *ctx, u32 *misr_value);
+};
+
+struct dpu_hw_mixer {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* lm */
+	enum dpu_lm  idx;
+	const struct dpu_lm_cfg   *cap;
+	const struct dpu_mdp_cfg  *mdp;
+	const struct dpu_ctl_cfg  *ctl;
+
+	/* ops */
+	struct dpu_hw_lm_ops ops;
+
+	/* store mixer info specific to display */
+	struct dpu_hw_mixer_cfg cfg;
+};
+
+/**
+ * to_dpu_hw_mixer - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_mixer *to_dpu_hw_mixer(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_mixer, base);
+}
+
+/**
+ * dpu_hw_lm_init(): Initializes the mixer hw driver object.
+ * should be called once before accessing every mixer.
+ * @idx:  mixer index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_lm_destroy(): Destroys layer mixer driver context
+ * @lm:   Pointer to LM driver context
+ */
+void dpu_hw_lm_destroy(struct dpu_hw_mixer *lm);
+
+#endif /*_DPU_HW_LM_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h
new file mode 100644
index 000000000..d3b0ed0a9
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h
@@ -0,0 +1,459 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HW_MDSS_H
+#define _DPU_HW_MDSS_H
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+
+#include "msm_drv.h"
+
+#define DPU_DBG_NAME			"dpu"
+
+#define DPU_NONE                        0
+
+#ifndef DPU_CSC_MATRIX_COEFF_SIZE
+#define DPU_CSC_MATRIX_COEFF_SIZE	9
+#endif
+
+#ifndef DPU_CSC_CLAMP_SIZE
+#define DPU_CSC_CLAMP_SIZE		6
+#endif
+
+#ifndef DPU_CSC_BIAS_SIZE
+#define DPU_CSC_BIAS_SIZE		3
+#endif
+
+#ifndef DPU_MAX_PLANES
+#define DPU_MAX_PLANES			4
+#endif
+
+#define PIPES_PER_STAGE			2
+#ifndef DPU_MAX_DE_CURVES
+#define DPU_MAX_DE_CURVES		3
+#endif
+
+enum dpu_format_flags {
+	DPU_FORMAT_FLAG_YUV_BIT,
+	DPU_FORMAT_FLAG_DX_BIT,
+	DPU_FORMAT_FLAG_COMPRESSED_BIT,
+	DPU_FORMAT_FLAG_BIT_MAX,
+};
+
+#define DPU_FORMAT_FLAG_YUV		BIT(DPU_FORMAT_FLAG_YUV_BIT)
+#define DPU_FORMAT_FLAG_DX		BIT(DPU_FORMAT_FLAG_DX_BIT)
+#define DPU_FORMAT_FLAG_COMPRESSED	BIT(DPU_FORMAT_FLAG_COMPRESSED_BIT)
+#define DPU_FORMAT_IS_YUV(X)		\
+	(test_bit(DPU_FORMAT_FLAG_YUV_BIT, (X)->flag))
+#define DPU_FORMAT_IS_DX(X)		\
+	(test_bit(DPU_FORMAT_FLAG_DX_BIT, (X)->flag))
+#define DPU_FORMAT_IS_LINEAR(X)		((X)->fetch_mode == DPU_FETCH_LINEAR)
+#define DPU_FORMAT_IS_TILE(X) \
+	(((X)->fetch_mode == DPU_FETCH_UBWC) && \
+			!test_bit(DPU_FORMAT_FLAG_COMPRESSED_BIT, (X)->flag))
+#define DPU_FORMAT_IS_UBWC(X) \
+	(((X)->fetch_mode == DPU_FETCH_UBWC) && \
+			test_bit(DPU_FORMAT_FLAG_COMPRESSED_BIT, (X)->flag))
+
+#define DPU_BLEND_FG_ALPHA_FG_CONST	(0 << 0)
+#define DPU_BLEND_FG_ALPHA_BG_CONST	(1 << 0)
+#define DPU_BLEND_FG_ALPHA_FG_PIXEL	(2 << 0)
+#define DPU_BLEND_FG_ALPHA_BG_PIXEL	(3 << 0)
+#define DPU_BLEND_FG_INV_ALPHA		(1 << 2)
+#define DPU_BLEND_FG_MOD_ALPHA		(1 << 3)
+#define DPU_BLEND_FG_INV_MOD_ALPHA	(1 << 4)
+#define DPU_BLEND_FG_TRANSP_EN		(1 << 5)
+#define DPU_BLEND_BG_ALPHA_FG_CONST	(0 << 8)
+#define DPU_BLEND_BG_ALPHA_BG_CONST	(1 << 8)
+#define DPU_BLEND_BG_ALPHA_FG_PIXEL	(2 << 8)
+#define DPU_BLEND_BG_ALPHA_BG_PIXEL	(3 << 8)
+#define DPU_BLEND_BG_INV_ALPHA		(1 << 10)
+#define DPU_BLEND_BG_MOD_ALPHA		(1 << 11)
+#define DPU_BLEND_BG_INV_MOD_ALPHA	(1 << 12)
+#define DPU_BLEND_BG_TRANSP_EN		(1 << 13)
+
+#define DPU_VSYNC0_SOURCE_GPIO		0
+#define DPU_VSYNC1_SOURCE_GPIO		1
+#define DPU_VSYNC2_SOURCE_GPIO		2
+#define DPU_VSYNC_SOURCE_INTF_0		3
+#define DPU_VSYNC_SOURCE_INTF_1		4
+#define DPU_VSYNC_SOURCE_INTF_2		5
+#define DPU_VSYNC_SOURCE_INTF_3		6
+#define DPU_VSYNC_SOURCE_WD_TIMER_4	11
+#define DPU_VSYNC_SOURCE_WD_TIMER_3	12
+#define DPU_VSYNC_SOURCE_WD_TIMER_2	13
+#define DPU_VSYNC_SOURCE_WD_TIMER_1	14
+#define DPU_VSYNC_SOURCE_WD_TIMER_0	15
+
+enum dpu_hw_blk_type {
+	DPU_HW_BLK_TOP = 0,
+	DPU_HW_BLK_SSPP,
+	DPU_HW_BLK_LM,
+	DPU_HW_BLK_CTL,
+	DPU_HW_BLK_PINGPONG,
+	DPU_HW_BLK_INTF,
+	DPU_HW_BLK_WB,
+	DPU_HW_BLK_DSPP,
+	DPU_HW_BLK_MERGE_3D,
+	DPU_HW_BLK_DSC,
+	DPU_HW_BLK_MAX,
+};
+
+enum dpu_mdp {
+	MDP_TOP = 0x1,
+	MDP_MAX,
+};
+
+enum dpu_sspp {
+	SSPP_NONE,
+	SSPP_VIG0,
+	SSPP_VIG1,
+	SSPP_VIG2,
+	SSPP_VIG3,
+	SSPP_RGB0,
+	SSPP_RGB1,
+	SSPP_RGB2,
+	SSPP_RGB3,
+	SSPP_DMA0,
+	SSPP_DMA1,
+	SSPP_DMA2,
+	SSPP_DMA3,
+	SSPP_CURSOR0,
+	SSPP_CURSOR1,
+	SSPP_MAX
+};
+
+enum dpu_sspp_type {
+	SSPP_TYPE_VIG,
+	SSPP_TYPE_RGB,
+	SSPP_TYPE_DMA,
+	SSPP_TYPE_CURSOR,
+	SSPP_TYPE_MAX
+};
+
+enum dpu_lm {
+	LM_0 = 1,
+	LM_1,
+	LM_2,
+	LM_3,
+	LM_4,
+	LM_5,
+	LM_6,
+	LM_MAX
+};
+
+enum dpu_stage {
+	DPU_STAGE_BASE = 0,
+	DPU_STAGE_0,
+	DPU_STAGE_1,
+	DPU_STAGE_2,
+	DPU_STAGE_3,
+	DPU_STAGE_4,
+	DPU_STAGE_5,
+	DPU_STAGE_6,
+	DPU_STAGE_7,
+	DPU_STAGE_8,
+	DPU_STAGE_9,
+	DPU_STAGE_10,
+	DPU_STAGE_MAX
+};
+enum dpu_dspp {
+	DSPP_0 = 1,
+	DSPP_1,
+	DSPP_2,
+	DSPP_3,
+	DSPP_MAX
+};
+
+enum dpu_ctl {
+	CTL_0 = 1,
+	CTL_1,
+	CTL_2,
+	CTL_3,
+	CTL_4,
+	CTL_5,
+	CTL_MAX
+};
+
+enum dpu_dsc {
+	DSC_NONE = 0,
+	DSC_0,
+	DSC_1,
+	DSC_2,
+	DSC_3,
+	DSC_4,
+	DSC_5,
+	DSC_MAX
+};
+
+enum dpu_pingpong {
+	PINGPONG_0 = 1,
+	PINGPONG_1,
+	PINGPONG_2,
+	PINGPONG_3,
+	PINGPONG_4,
+	PINGPONG_5,
+	PINGPONG_S0,
+	PINGPONG_MAX
+};
+
+enum dpu_merge_3d {
+	MERGE_3D_0 = 1,
+	MERGE_3D_1,
+	MERGE_3D_2,
+	MERGE_3D_MAX
+};
+
+enum dpu_intf {
+	INTF_0 = 1,
+	INTF_1,
+	INTF_2,
+	INTF_3,
+	INTF_4,
+	INTF_5,
+	INTF_6,
+	INTF_MAX
+};
+
+/*
+ * Historically these values correspond to the values written to the
+ * DISP_INTF_SEL register, which had to programmed manually. On newer MDP
+ * generations this register is NOP, but we keep the values for historical
+ * reasons.
+ */
+enum dpu_intf_type {
+	INTF_NONE = 0x0,
+	INTF_DSI = 0x1,
+	INTF_HDMI = 0x3,
+	INTF_LCDC = 0x5,
+	/* old eDP found on 8x74 and 8x84 */
+	INTF_EDP = 0x9,
+	/* both DP and eDP,  handled by the new DP driver */
+	INTF_DP = 0xa,
+
+	/* virtual interfaces */
+	INTF_WB = 0x100,
+};
+
+enum dpu_intf_mode {
+	INTF_MODE_NONE = 0,
+	INTF_MODE_CMD,
+	INTF_MODE_VIDEO,
+	INTF_MODE_WB_BLOCK,
+	INTF_MODE_WB_LINE,
+	INTF_MODE_MAX
+};
+
+enum dpu_wb {
+	WB_0 = 1,
+	WB_1,
+	WB_2,
+	WB_3,
+	WB_MAX
+};
+
+enum dpu_cwb {
+	CWB_0 = 0x1,
+	CWB_1,
+	CWB_2,
+	CWB_3,
+	CWB_MAX
+};
+
+enum dpu_wd_timer {
+	WD_TIMER_0 = 0x1,
+	WD_TIMER_1,
+	WD_TIMER_2,
+	WD_TIMER_3,
+	WD_TIMER_4,
+	WD_TIMER_5,
+	WD_TIMER_MAX
+};
+
+enum dpu_vbif {
+	VBIF_RT,
+	VBIF_NRT,
+	VBIF_MAX,
+};
+
+/**
+ * DPU HW,Component order color map
+ */
+enum {
+	C0_G_Y = 0,
+	C1_B_Cb = 1,
+	C2_R_Cr = 2,
+	C3_ALPHA = 3
+};
+
+/**
+ * enum dpu_plane_type - defines how the color component pixel packing
+ * @DPU_PLANE_INTERLEAVED   : Color components in single plane
+ * @DPU_PLANE_PLANAR        : Color component in separate planes
+ * @DPU_PLANE_PSEUDO_PLANAR : Chroma components interleaved in separate plane
+ */
+enum dpu_plane_type {
+	DPU_PLANE_INTERLEAVED,
+	DPU_PLANE_PLANAR,
+	DPU_PLANE_PSEUDO_PLANAR,
+};
+
+/**
+ * enum dpu_chroma_samp_type - chroma sub-samplng type
+ * @DPU_CHROMA_RGB   : No chroma subsampling
+ * @DPU_CHROMA_H2V1  : Chroma pixels are horizontally subsampled
+ * @DPU_CHROMA_H1V2  : Chroma pixels are vertically subsampled
+ * @DPU_CHROMA_420   : 420 subsampling
+ */
+enum dpu_chroma_samp_type {
+	DPU_CHROMA_RGB,
+	DPU_CHROMA_H2V1,
+	DPU_CHROMA_H1V2,
+	DPU_CHROMA_420
+};
+
+/**
+ * dpu_fetch_type - Defines How DPU HW fetches data
+ * @DPU_FETCH_LINEAR   : fetch is line by line
+ * @DPU_FETCH_TILE     : fetches data in Z order from a tile
+ * @DPU_FETCH_UBWC     : fetch and decompress data
+ */
+enum dpu_fetch_type {
+	DPU_FETCH_LINEAR,
+	DPU_FETCH_TILE,
+	DPU_FETCH_UBWC
+};
+
+/**
+ * Value of enum chosen to fit the number of bits
+ * expected by the HW programming.
+ */
+enum {
+	COLOR_ALPHA_1BIT = 0,
+	COLOR_ALPHA_4BIT = 1,
+	COLOR_4BIT = 0,
+	COLOR_5BIT = 1, /* No 5-bit Alpha */
+	COLOR_6BIT = 2, /* 6-Bit Alpha also = 2 */
+	COLOR_8BIT = 3, /* 8-Bit Alpha also = 3 */
+};
+
+/**
+ * enum dpu_3d_blend_mode
+ * Desribes how the 3d data is blended
+ * @BLEND_3D_NONE      : 3d blending not enabled
+ * @BLEND_3D_FRAME_INT : Frame interleaving
+ * @BLEND_3D_H_ROW_INT : Horizontal row interleaving
+ * @BLEND_3D_V_ROW_INT : vertical row interleaving
+ * @BLEND_3D_COL_INT   : column interleaving
+ * @BLEND_3D_MAX       :
+ */
+enum dpu_3d_blend_mode {
+	BLEND_3D_NONE = 0,
+	BLEND_3D_FRAME_INT,
+	BLEND_3D_H_ROW_INT,
+	BLEND_3D_V_ROW_INT,
+	BLEND_3D_COL_INT,
+	BLEND_3D_MAX
+};
+
+/** struct dpu_format - defines the format configuration which
+ * allows DPU HW to correctly fetch and decode the format
+ * @base: base msm_format structure containing fourcc code
+ * @fetch_planes: how the color components are packed in pixel format
+ * @element: element color ordering
+ * @bits: element bit widths
+ * @chroma_sample: chroma sub-samplng type
+ * @unpack_align_msb: unpack aligned, 0 to LSB, 1 to MSB
+ * @unpack_tight: 0 for loose, 1 for tight
+ * @unpack_count: 0 = 1 component, 1 = 2 component
+ * @bpp: bytes per pixel
+ * @alpha_enable: whether the format has an alpha channel
+ * @num_planes: number of planes (including meta data planes)
+ * @fetch_mode: linear, tiled, or ubwc hw fetch behavior
+ * @flag: usage bit flags
+ * @tile_width: format tile width
+ * @tile_height: format tile height
+ */
+struct dpu_format {
+	struct msm_format base;
+	enum dpu_plane_type fetch_planes;
+	u8 element[DPU_MAX_PLANES];
+	u8 bits[DPU_MAX_PLANES];
+	enum dpu_chroma_samp_type chroma_sample;
+	u8 unpack_align_msb;
+	u8 unpack_tight;
+	u8 unpack_count;
+	u8 bpp;
+	u8 alpha_enable;
+	u8 num_planes;
+	enum dpu_fetch_type fetch_mode;
+	DECLARE_BITMAP(flag, DPU_FORMAT_FLAG_BIT_MAX);
+	u16 tile_width;
+	u16 tile_height;
+};
+#define to_dpu_format(x) container_of(x, struct dpu_format, base)
+
+/**
+ * struct dpu_hw_fmt_layout - format information of the source pixel data
+ * @format: pixel format parameters
+ * @num_planes: number of planes (including meta data planes)
+ * @width: image width
+ * @height: image height
+ * @total_size: total size in bytes
+ * @plane_addr: address of each plane
+ * @plane_size: length of each plane
+ * @plane_pitch: pitch of each plane
+ */
+struct dpu_hw_fmt_layout {
+	const struct dpu_format *format;
+	uint32_t num_planes;
+	uint32_t width;
+	uint32_t height;
+	uint32_t total_size;
+	uint32_t plane_addr[DPU_MAX_PLANES];
+	uint32_t plane_size[DPU_MAX_PLANES];
+	uint32_t plane_pitch[DPU_MAX_PLANES];
+};
+
+struct dpu_csc_cfg {
+	/* matrix coefficients in S15.16 format */
+	uint32_t csc_mv[DPU_CSC_MATRIX_COEFF_SIZE];
+	uint32_t csc_pre_bv[DPU_CSC_BIAS_SIZE];
+	uint32_t csc_post_bv[DPU_CSC_BIAS_SIZE];
+	uint32_t csc_pre_lv[DPU_CSC_CLAMP_SIZE];
+	uint32_t csc_post_lv[DPU_CSC_CLAMP_SIZE];
+};
+
+/**
+ * struct dpu_mdss_color - mdss color description
+ * color 0 : green
+ * color 1 : blue
+ * color 2 : red
+ * color 3 : alpha
+ */
+struct dpu_mdss_color {
+	u32 color_0;
+	u32 color_1;
+	u32 color_2;
+	u32 color_3;
+};
+
+/*
+ * Define bit masks for h/w logging.
+ */
+#define DPU_DBG_MASK_NONE     (1 << 0)
+#define DPU_DBG_MASK_INTF     (1 << 1)
+#define DPU_DBG_MASK_LM       (1 << 2)
+#define DPU_DBG_MASK_CTL      (1 << 3)
+#define DPU_DBG_MASK_PINGPONG (1 << 4)
+#define DPU_DBG_MASK_SSPP     (1 << 5)
+#define DPU_DBG_MASK_WB       (1 << 6)
+#define DPU_DBG_MASK_TOP      (1 << 7)
+#define DPU_DBG_MASK_VBIF     (1 << 8)
+#define DPU_DBG_MASK_ROT      (1 << 9)
+#define DPU_DBG_MASK_DSPP     (1 << 10)
+#define DPU_DBG_MASK_DSC      (1 << 11)
+
+#endif  /* _DPU_HW_MDSS_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_merge3d.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_merge3d.c
new file mode 100644
index 000000000..def0a87fd
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_merge3d.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/iopoll.h>
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_merge3d.h"
+#include "dpu_kms.h"
+#include "dpu_trace.h"
+
+#define MERGE_3D_MUX  0x000
+#define MERGE_3D_MODE 0x004
+
+static const struct dpu_merge_3d_cfg *_merge_3d_offset(enum dpu_merge_3d idx,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->merge_3d_count; i++) {
+		if (idx == m->merge_3d[i].id) {
+			b->blk_addr = addr + m->merge_3d[i].base;
+			b->log_mask = DPU_DBG_MASK_PINGPONG;
+			return &m->merge_3d[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static void dpu_hw_merge_3d_setup_3d_mode(struct dpu_hw_merge_3d *merge_3d,
+			enum dpu_3d_blend_mode mode_3d)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 data;
+
+
+	c = &merge_3d->hw;
+	if (mode_3d == BLEND_3D_NONE) {
+		DPU_REG_WRITE(c, MERGE_3D_MODE, 0);
+		DPU_REG_WRITE(c, MERGE_3D_MUX, 0);
+	} else {
+		data = BIT(0) | ((mode_3d - 1) << 1);
+		DPU_REG_WRITE(c, MERGE_3D_MODE, data);
+	}
+}
+
+static void _setup_merge_3d_ops(struct dpu_hw_merge_3d *c,
+				unsigned long features)
+{
+	c->ops.setup_3d_mode = dpu_hw_merge_3d_setup_3d_mode;
+};
+
+struct dpu_hw_merge_3d *dpu_hw_merge_3d_init(enum dpu_merge_3d idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_merge_3d *c;
+	const struct dpu_merge_3d_cfg *cfg;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _merge_3d_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->idx = idx;
+	c->caps = cfg;
+	_setup_merge_3d_ops(c, c->caps->features);
+
+	return c;
+}
+
+void dpu_hw_merge_3d_destroy(struct dpu_hw_merge_3d *hw)
+{
+	kfree(hw);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_merge3d.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_merge3d.h
new file mode 100644
index 000000000..81fd1d5f7
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_merge3d.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HW_MERGE3D_H
+#define _DPU_HW_MERGE3D_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+struct dpu_hw_merge_3d;
+
+/**
+ *
+ * struct dpu_hw_merge_3d_ops : Interface to the merge_3d Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ *  @setup_3d_mode : enable 3D merge
+ */
+struct dpu_hw_merge_3d_ops {
+	void (*setup_3d_mode)(struct dpu_hw_merge_3d *merge_3d,
+			enum dpu_3d_blend_mode mode_3d);
+
+};
+
+struct dpu_hw_merge_3d {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* merge_3d */
+	enum dpu_merge_3d idx;
+	const struct dpu_merge_3d_cfg *caps;
+
+	/* ops */
+	struct dpu_hw_merge_3d_ops ops;
+};
+
+/**
+ * to_dpu_hw_merge_3d - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_merge_3d *to_dpu_hw_merge_3d(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_merge_3d, base);
+}
+
+/**
+ * dpu_hw_merge_3d_init - initializes the merge_3d driver for the passed
+ *	merge_3d idx.
+ * @idx:  Pingpong index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @m:    Pointer to mdss catalog data
+ * Returns: Error code or allocated dpu_hw_merge_3d context
+ */
+struct dpu_hw_merge_3d *dpu_hw_merge_3d_init(enum dpu_merge_3d idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_merge_3d_destroy - destroys merge_3d driver context
+ *	should be called to free the context
+ * @pp:   Pointer to PP driver context returned by dpu_hw_merge_3d_init
+ */
+void dpu_hw_merge_3d_destroy(struct dpu_hw_merge_3d *pp);
+
+#endif /*_DPU_HW_MERGE3D_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
new file mode 100644
index 000000000..0fcad9760
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
@@ -0,0 +1,320 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/iopoll.h>
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_kms.h"
+#include "dpu_trace.h"
+
+#define PP_TEAR_CHECK_EN                0x000
+#define PP_SYNC_CONFIG_VSYNC            0x004
+#define PP_SYNC_CONFIG_HEIGHT           0x008
+#define PP_SYNC_WRCOUNT                 0x00C
+#define PP_VSYNC_INIT_VAL               0x010
+#define PP_INT_COUNT_VAL                0x014
+#define PP_SYNC_THRESH                  0x018
+#define PP_START_POS                    0x01C
+#define PP_RD_PTR_IRQ                   0x020
+#define PP_WR_PTR_IRQ                   0x024
+#define PP_OUT_LINE_COUNT               0x028
+#define PP_LINE_COUNT                   0x02C
+#define PP_AUTOREFRESH_CONFIG           0x030
+
+#define PP_FBC_MODE                     0x034
+#define PP_FBC_BUDGET_CTL               0x038
+#define PP_FBC_LOSSY_MODE               0x03C
+#define PP_DSC_MODE                     0x0a0
+#define PP_DCE_DATA_IN_SWAP             0x0ac
+#define PP_DCE_DATA_OUT_SWAP            0x0c8
+
+#define PP_DITHER_EN			0x000
+#define PP_DITHER_BITDEPTH		0x004
+#define PP_DITHER_MATRIX		0x008
+
+#define DITHER_DEPTH_MAP_INDEX 9
+
+static u32 dither_depth_map[DITHER_DEPTH_MAP_INDEX] = {
+	0, 0, 0, 0, 0, 0, 0, 1, 2
+};
+
+static const struct dpu_pingpong_cfg *_pingpong_offset(enum dpu_pingpong pp,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->pingpong_count; i++) {
+		if (pp == m->pingpong[i].id) {
+			b->blk_addr = addr + m->pingpong[i].base;
+			b->log_mask = DPU_DBG_MASK_PINGPONG;
+			return &m->pingpong[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static void dpu_hw_pp_setup_dither(struct dpu_hw_pingpong *pp,
+				    struct dpu_hw_dither_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 i, base, data = 0;
+
+	c = &pp->hw;
+	base = pp->caps->sblk->dither.base;
+	if (!cfg) {
+		DPU_REG_WRITE(c, base + PP_DITHER_EN, 0);
+		return;
+	}
+
+	data = dither_depth_map[cfg->c0_bitdepth] & REG_MASK(2);
+	data |= (dither_depth_map[cfg->c1_bitdepth] & REG_MASK(2)) << 2;
+	data |= (dither_depth_map[cfg->c2_bitdepth] & REG_MASK(2)) << 4;
+	data |= (dither_depth_map[cfg->c3_bitdepth] & REG_MASK(2)) << 6;
+	data |= (cfg->temporal_en) ? (1 << 8) : 0;
+
+	DPU_REG_WRITE(c, base + PP_DITHER_BITDEPTH, data);
+
+	for (i = 0; i < DITHER_MATRIX_SZ - 3; i += 4) {
+		data = (cfg->matrix[i] & REG_MASK(4)) |
+			((cfg->matrix[i + 1] & REG_MASK(4)) << 4) |
+			((cfg->matrix[i + 2] & REG_MASK(4)) << 8) |
+			((cfg->matrix[i + 3] & REG_MASK(4)) << 12);
+		DPU_REG_WRITE(c, base + PP_DITHER_MATRIX + i, data);
+	}
+	DPU_REG_WRITE(c, base + PP_DITHER_EN, 1);
+}
+
+static int dpu_hw_pp_setup_te_config(struct dpu_hw_pingpong *pp,
+		struct dpu_hw_tear_check *te)
+{
+	struct dpu_hw_blk_reg_map *c;
+	int cfg;
+
+	if (!pp || !te)
+		return -EINVAL;
+	c = &pp->hw;
+
+	cfg = BIT(19); /*VSYNC_COUNTER_EN */
+	if (te->hw_vsync_mode)
+		cfg |= BIT(20);
+
+	cfg |= te->vsync_count;
+
+	DPU_REG_WRITE(c, PP_SYNC_CONFIG_VSYNC, cfg);
+	DPU_REG_WRITE(c, PP_SYNC_CONFIG_HEIGHT, te->sync_cfg_height);
+	DPU_REG_WRITE(c, PP_VSYNC_INIT_VAL, te->vsync_init_val);
+	DPU_REG_WRITE(c, PP_RD_PTR_IRQ, te->rd_ptr_irq);
+	DPU_REG_WRITE(c, PP_START_POS, te->start_pos);
+	DPU_REG_WRITE(c, PP_SYNC_THRESH,
+			((te->sync_threshold_continue << 16) |
+			 te->sync_threshold_start));
+	DPU_REG_WRITE(c, PP_SYNC_WRCOUNT,
+			(te->start_pos + te->sync_threshold_start + 1));
+
+	return 0;
+}
+
+static void dpu_hw_pp_setup_autorefresh_config(struct dpu_hw_pingpong *pp,
+					       u32 frame_count, bool enable)
+{
+	DPU_REG_WRITE(&pp->hw, PP_AUTOREFRESH_CONFIG,
+		      enable ? (BIT(31) | frame_count) : 0);
+}
+
+/*
+ * dpu_hw_pp_get_autorefresh_config - Get autorefresh config from HW
+ * @pp:          DPU pingpong structure
+ * @frame_count: Used to return the current frame count from hw
+ *
+ * Returns: True if autorefresh enabled, false if disabled.
+ */
+static bool dpu_hw_pp_get_autorefresh_config(struct dpu_hw_pingpong *pp,
+					     u32 *frame_count)
+{
+	u32 val = DPU_REG_READ(&pp->hw, PP_AUTOREFRESH_CONFIG);
+	if (frame_count != NULL)
+		*frame_count = val & 0xffff;
+	return !!((val & BIT(31)) >> 31);
+}
+
+static int dpu_hw_pp_poll_timeout_wr_ptr(struct dpu_hw_pingpong *pp,
+		u32 timeout_us)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 val;
+	int rc;
+
+	if (!pp)
+		return -EINVAL;
+
+	c = &pp->hw;
+	rc = readl_poll_timeout(c->blk_addr + PP_LINE_COUNT,
+			val, (val & 0xffff) >= 1, 10, timeout_us);
+
+	return rc;
+}
+
+static int dpu_hw_pp_enable_te(struct dpu_hw_pingpong *pp, bool enable)
+{
+	struct dpu_hw_blk_reg_map *c;
+
+	if (!pp)
+		return -EINVAL;
+	c = &pp->hw;
+
+	DPU_REG_WRITE(c, PP_TEAR_CHECK_EN, enable);
+	return 0;
+}
+
+static int dpu_hw_pp_connect_external_te(struct dpu_hw_pingpong *pp,
+		bool enable_external_te)
+{
+	struct dpu_hw_blk_reg_map *c = &pp->hw;
+	u32 cfg;
+	int orig;
+
+	if (!pp)
+		return -EINVAL;
+
+	c = &pp->hw;
+	cfg = DPU_REG_READ(c, PP_SYNC_CONFIG_VSYNC);
+	orig = (bool)(cfg & BIT(20));
+	if (enable_external_te)
+		cfg |= BIT(20);
+	else
+		cfg &= ~BIT(20);
+	DPU_REG_WRITE(c, PP_SYNC_CONFIG_VSYNC, cfg);
+	trace_dpu_pp_connect_ext_te(pp->idx - PINGPONG_0, cfg);
+
+	return orig;
+}
+
+static int dpu_hw_pp_get_vsync_info(struct dpu_hw_pingpong *pp,
+		struct dpu_hw_pp_vsync_info *info)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 val;
+
+	if (!pp || !info)
+		return -EINVAL;
+	c = &pp->hw;
+
+	val = DPU_REG_READ(c, PP_VSYNC_INIT_VAL);
+	info->rd_ptr_init_val = val & 0xffff;
+
+	val = DPU_REG_READ(c, PP_INT_COUNT_VAL);
+	info->rd_ptr_frame_count = (val & 0xffff0000) >> 16;
+	info->rd_ptr_line_count = val & 0xffff;
+
+	val = DPU_REG_READ(c, PP_LINE_COUNT);
+	info->wr_ptr_line_count = val & 0xffff;
+
+	return 0;
+}
+
+static u32 dpu_hw_pp_get_line_count(struct dpu_hw_pingpong *pp)
+{
+	struct dpu_hw_blk_reg_map *c = &pp->hw;
+	u32 height, init;
+	u32 line = 0xFFFF;
+
+	if (!pp)
+		return 0;
+	c = &pp->hw;
+
+	init = DPU_REG_READ(c, PP_VSYNC_INIT_VAL) & 0xFFFF;
+	height = DPU_REG_READ(c, PP_SYNC_CONFIG_HEIGHT) & 0xFFFF;
+
+	if (height < init)
+		return line;
+
+	line = DPU_REG_READ(c, PP_INT_COUNT_VAL) & 0xFFFF;
+
+	if (line < init)
+		line += (0xFFFF - init);
+	else
+		line -= init;
+
+	return line;
+}
+
+static int dpu_hw_pp_dsc_enable(struct dpu_hw_pingpong *pp)
+{
+	struct dpu_hw_blk_reg_map *c = &pp->hw;
+
+	DPU_REG_WRITE(c, PP_DSC_MODE, 1);
+	return 0;
+}
+
+static void dpu_hw_pp_dsc_disable(struct dpu_hw_pingpong *pp)
+{
+	struct dpu_hw_blk_reg_map *c = &pp->hw;
+
+	DPU_REG_WRITE(c, PP_DSC_MODE, 0);
+}
+
+static int dpu_hw_pp_setup_dsc(struct dpu_hw_pingpong *pp)
+{
+	struct dpu_hw_blk_reg_map *pp_c = &pp->hw;
+	int data;
+
+	data = DPU_REG_READ(pp_c, PP_DCE_DATA_OUT_SWAP);
+	data |= BIT(18); /* endian flip */
+	DPU_REG_WRITE(pp_c, PP_DCE_DATA_OUT_SWAP, data);
+	return 0;
+}
+
+static void _setup_pingpong_ops(struct dpu_hw_pingpong *c,
+				unsigned long features)
+{
+	c->ops.setup_tearcheck = dpu_hw_pp_setup_te_config;
+	c->ops.enable_tearcheck = dpu_hw_pp_enable_te;
+	c->ops.connect_external_te = dpu_hw_pp_connect_external_te;
+	c->ops.get_vsync_info = dpu_hw_pp_get_vsync_info;
+	c->ops.setup_autorefresh = dpu_hw_pp_setup_autorefresh_config;
+	c->ops.get_autorefresh = dpu_hw_pp_get_autorefresh_config;
+	c->ops.poll_timeout_wr_ptr = dpu_hw_pp_poll_timeout_wr_ptr;
+	c->ops.get_line_count = dpu_hw_pp_get_line_count;
+	c->ops.setup_dsc = dpu_hw_pp_setup_dsc;
+	c->ops.enable_dsc = dpu_hw_pp_dsc_enable;
+	c->ops.disable_dsc = dpu_hw_pp_dsc_disable;
+
+	if (test_bit(DPU_PINGPONG_DITHER, &features))
+		c->ops.setup_dither = dpu_hw_pp_setup_dither;
+};
+
+struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_pingpong *c;
+	const struct dpu_pingpong_cfg *cfg;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _pingpong_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->idx = idx;
+	c->caps = cfg;
+	_setup_pingpong_ops(c, c->caps->features);
+
+	return c;
+}
+
+void dpu_hw_pingpong_destroy(struct dpu_hw_pingpong *pp)
+{
+	kfree(pp);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
new file mode 100644
index 000000000..c00223441
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HW_PINGPONG_H
+#define _DPU_HW_PINGPONG_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+#define DITHER_MATRIX_SZ 16
+
+struct dpu_hw_pingpong;
+
+struct dpu_hw_tear_check {
+	/*
+	 * This is ratio of MDP VSYNC clk freq(Hz) to
+	 * refresh rate divided by no of lines
+	 */
+	u32 vsync_count;
+	u32 sync_cfg_height;
+	u32 vsync_init_val;
+	u32 sync_threshold_start;
+	u32 sync_threshold_continue;
+	u32 start_pos;
+	u32 rd_ptr_irq;
+	u8 hw_vsync_mode;
+};
+
+struct dpu_hw_pp_vsync_info {
+	u32 rd_ptr_init_val;	/* value of rd pointer at vsync edge */
+	u32 rd_ptr_frame_count;	/* num frames sent since enabling interface */
+	u32 rd_ptr_line_count;	/* current line on panel (rd ptr) */
+	u32 wr_ptr_line_count;	/* current line within pp fifo (wr ptr) */
+};
+
+/**
+ * struct dpu_hw_dither_cfg - dither feature structure
+ * @flags: for customizing operations
+ * @temporal_en: temperal dither enable
+ * @c0_bitdepth: c0 component bit depth
+ * @c1_bitdepth: c1 component bit depth
+ * @c2_bitdepth: c2 component bit depth
+ * @c3_bitdepth: c2 component bit depth
+ * @matrix: dither strength matrix
+ */
+struct dpu_hw_dither_cfg {
+	u64 flags;
+	u32 temporal_en;
+	u32 c0_bitdepth;
+	u32 c1_bitdepth;
+	u32 c2_bitdepth;
+	u32 c3_bitdepth;
+	u32 matrix[DITHER_MATRIX_SZ];
+};
+
+/**
+ *
+ * struct dpu_hw_pingpong_ops : Interface to the pingpong Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ *  @setup_tearcheck : program tear check values
+ *  @enable_tearcheck : enables tear check
+ *  @get_vsync_info : retries timing info of the panel
+ *  @setup_autorefresh : configure and enable the autorefresh config
+ *  @get_autorefresh : retrieve autorefresh config from hardware
+ *  @setup_dither : function to program the dither hw block
+ *  @get_line_count: obtain current vertical line counter
+ */
+struct dpu_hw_pingpong_ops {
+	/**
+	 * enables vysnc generation and sets up init value of
+	 * read pointer and programs the tear check cofiguration
+	 */
+	int (*setup_tearcheck)(struct dpu_hw_pingpong *pp,
+			struct dpu_hw_tear_check *cfg);
+
+	/**
+	 * enables tear check block
+	 */
+	int (*enable_tearcheck)(struct dpu_hw_pingpong *pp,
+			bool enable);
+
+	/**
+	 * read, modify, write to either set or clear listening to external TE
+	 * @Return: 1 if TE was originally connected, 0 if not, or -ERROR
+	 */
+	int (*connect_external_te)(struct dpu_hw_pingpong *pp,
+			bool enable_external_te);
+
+	/**
+	 * provides the programmed and current
+	 * line_count
+	 */
+	int (*get_vsync_info)(struct dpu_hw_pingpong *pp,
+			struct dpu_hw_pp_vsync_info  *info);
+
+	/**
+	 * configure and enable the autorefresh config
+	 */
+	void (*setup_autorefresh)(struct dpu_hw_pingpong *pp,
+				  u32 frame_count, bool enable);
+
+	/**
+	 * retrieve autorefresh config from hardware
+	 */
+	bool (*get_autorefresh)(struct dpu_hw_pingpong *pp,
+				u32 *frame_count);
+
+	/**
+	 * poll until write pointer transmission starts
+	 * @Return: 0 on success, -ETIMEDOUT on timeout
+	 */
+	int (*poll_timeout_wr_ptr)(struct dpu_hw_pingpong *pp, u32 timeout_us);
+
+	/**
+	 * Obtain current vertical line counter
+	 */
+	u32 (*get_line_count)(struct dpu_hw_pingpong *pp);
+
+	/**
+	 * Setup dither matix for pingpong block
+	 */
+	void (*setup_dither)(struct dpu_hw_pingpong *pp,
+			struct dpu_hw_dither_cfg *cfg);
+	/**
+	 * Enable DSC
+	 */
+	int (*enable_dsc)(struct dpu_hw_pingpong *pp);
+
+	/**
+	 * Disable DSC
+	 */
+	void (*disable_dsc)(struct dpu_hw_pingpong *pp);
+
+	/**
+	 * Setup DSC
+	 */
+	int (*setup_dsc)(struct dpu_hw_pingpong *pp);
+};
+
+struct dpu_hw_merge_3d;
+
+struct dpu_hw_pingpong {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* pingpong */
+	enum dpu_pingpong idx;
+	const struct dpu_pingpong_cfg *caps;
+	struct dpu_hw_merge_3d *merge_3d;
+
+	/* ops */
+	struct dpu_hw_pingpong_ops ops;
+};
+
+/**
+ * to_dpu_hw_pingpong - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_pingpong *to_dpu_hw_pingpong(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_pingpong, base);
+}
+
+/**
+ * dpu_hw_pingpong_init - initializes the pingpong driver for the passed
+ *	pingpong idx.
+ * @idx:  Pingpong index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @m:    Pointer to mdss catalog data
+ * Returns: Error code or allocated dpu_hw_pingpong context
+ */
+struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_pingpong_destroy - destroys pingpong driver context
+ *	should be called to free the context
+ * @pp:   Pointer to PP driver context returned by dpu_hw_pingpong_init
+ */
+void dpu_hw_pingpong_destroy(struct dpu_hw_pingpong *pp);
+
+#endif /*_DPU_HW_PINGPONG_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
new file mode 100644
index 000000000..691c471b0
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
@@ -0,0 +1,815 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_sspp.h"
+#include "dpu_kms.h"
+
+#include <drm/drm_file.h>
+
+#define DPU_FETCH_CONFIG_RESET_VALUE   0x00000087
+
+/* DPU_SSPP_SRC */
+#define SSPP_SRC_SIZE                      0x00
+#define SSPP_SRC_XY                        0x08
+#define SSPP_OUT_SIZE                      0x0c
+#define SSPP_OUT_XY                        0x10
+#define SSPP_SRC0_ADDR                     0x14
+#define SSPP_SRC1_ADDR                     0x18
+#define SSPP_SRC2_ADDR                     0x1C
+#define SSPP_SRC3_ADDR                     0x20
+#define SSPP_SRC_YSTRIDE0                  0x24
+#define SSPP_SRC_YSTRIDE1                  0x28
+#define SSPP_SRC_FORMAT                    0x30
+#define SSPP_SRC_UNPACK_PATTERN            0x34
+#define SSPP_SRC_OP_MODE                   0x38
+
+/* SSPP_MULTIRECT*/
+#define SSPP_SRC_SIZE_REC1                 0x16C
+#define SSPP_SRC_XY_REC1                   0x168
+#define SSPP_OUT_SIZE_REC1                 0x160
+#define SSPP_OUT_XY_REC1                   0x164
+#define SSPP_SRC_FORMAT_REC1               0x174
+#define SSPP_SRC_UNPACK_PATTERN_REC1       0x178
+#define SSPP_SRC_OP_MODE_REC1              0x17C
+#define SSPP_MULTIRECT_OPMODE              0x170
+#define SSPP_SRC_CONSTANT_COLOR_REC1       0x180
+#define SSPP_EXCL_REC_SIZE_REC1            0x184
+#define SSPP_EXCL_REC_XY_REC1              0x188
+
+#define MDSS_MDP_OP_DEINTERLACE            BIT(22)
+#define MDSS_MDP_OP_DEINTERLACE_ODD        BIT(23)
+#define MDSS_MDP_OP_IGC_ROM_1              BIT(18)
+#define MDSS_MDP_OP_IGC_ROM_0              BIT(17)
+#define MDSS_MDP_OP_IGC_EN                 BIT(16)
+#define MDSS_MDP_OP_FLIP_UD                BIT(14)
+#define MDSS_MDP_OP_FLIP_LR                BIT(13)
+#define MDSS_MDP_OP_BWC_EN                 BIT(0)
+#define MDSS_MDP_OP_PE_OVERRIDE            BIT(31)
+#define MDSS_MDP_OP_BWC_LOSSLESS           (0 << 1)
+#define MDSS_MDP_OP_BWC_Q_HIGH             (1 << 1)
+#define MDSS_MDP_OP_BWC_Q_MED              (2 << 1)
+
+#define SSPP_SRC_CONSTANT_COLOR            0x3c
+#define SSPP_EXCL_REC_CTL                  0x40
+#define SSPP_UBWC_STATIC_CTRL              0x44
+#define SSPP_FETCH_CONFIG                  0x048
+#define SSPP_DANGER_LUT                    0x60
+#define SSPP_SAFE_LUT                      0x64
+#define SSPP_CREQ_LUT                      0x68
+#define SSPP_QOS_CTRL                      0x6C
+#define SSPP_DECIMATION_CONFIG             0xB4
+#define SSPP_SRC_ADDR_SW_STATUS            0x70
+#define SSPP_CREQ_LUT_0                    0x74
+#define SSPP_CREQ_LUT_1                    0x78
+#define SSPP_SW_PIX_EXT_C0_LR              0x100
+#define SSPP_SW_PIX_EXT_C0_TB              0x104
+#define SSPP_SW_PIX_EXT_C0_REQ_PIXELS      0x108
+#define SSPP_SW_PIX_EXT_C1C2_LR            0x110
+#define SSPP_SW_PIX_EXT_C1C2_TB            0x114
+#define SSPP_SW_PIX_EXT_C1C2_REQ_PIXELS    0x118
+#define SSPP_SW_PIX_EXT_C3_LR              0x120
+#define SSPP_SW_PIX_EXT_C3_TB              0x124
+#define SSPP_SW_PIX_EXT_C3_REQ_PIXELS      0x128
+#define SSPP_TRAFFIC_SHAPER                0x130
+#define SSPP_CDP_CNTL                      0x134
+#define SSPP_UBWC_ERROR_STATUS             0x138
+#define SSPP_CDP_CNTL_REC1                 0x13c
+#define SSPP_TRAFFIC_SHAPER_PREFILL        0x150
+#define SSPP_TRAFFIC_SHAPER_REC1_PREFILL   0x154
+#define SSPP_TRAFFIC_SHAPER_REC1           0x158
+#define SSPP_EXCL_REC_SIZE                 0x1B4
+#define SSPP_EXCL_REC_XY                   0x1B8
+#define SSPP_VIG_OP_MODE                   0x0
+#define SSPP_VIG_CSC_10_OP_MODE            0x0
+#define SSPP_TRAFFIC_SHAPER_BPC_MAX        0xFF
+
+/* SSPP_QOS_CTRL */
+#define SSPP_QOS_CTRL_VBLANK_EN            BIT(16)
+#define SSPP_QOS_CTRL_DANGER_SAFE_EN       BIT(0)
+#define SSPP_QOS_CTRL_DANGER_VBLANK_MASK   0x3
+#define SSPP_QOS_CTRL_DANGER_VBLANK_OFF    4
+#define SSPP_QOS_CTRL_CREQ_VBLANK_MASK     0x3
+#define SSPP_QOS_CTRL_CREQ_VBLANK_OFF      20
+
+/* DPU_SSPP_SCALER_QSEED2 */
+#define SCALE_CONFIG                       0x04
+#define COMP0_3_PHASE_STEP_X               0x10
+#define COMP0_3_PHASE_STEP_Y               0x14
+#define COMP1_2_PHASE_STEP_X               0x18
+#define COMP1_2_PHASE_STEP_Y               0x1c
+#define COMP0_3_INIT_PHASE_X               0x20
+#define COMP0_3_INIT_PHASE_Y               0x24
+#define COMP1_2_INIT_PHASE_X               0x28
+#define COMP1_2_INIT_PHASE_Y               0x2C
+#define VIG_0_QSEED2_SHARP                 0x30
+
+/*
+ * Definitions for ViG op modes
+ */
+#define VIG_OP_CSC_DST_DATAFMT BIT(19)
+#define VIG_OP_CSC_SRC_DATAFMT BIT(18)
+#define VIG_OP_CSC_EN          BIT(17)
+#define VIG_OP_MEM_PROT_CONT   BIT(15)
+#define VIG_OP_MEM_PROT_VAL    BIT(14)
+#define VIG_OP_MEM_PROT_SAT    BIT(13)
+#define VIG_OP_MEM_PROT_HUE    BIT(12)
+#define VIG_OP_HIST            BIT(8)
+#define VIG_OP_SKY_COL         BIT(7)
+#define VIG_OP_FOIL            BIT(6)
+#define VIG_OP_SKIN_COL        BIT(5)
+#define VIG_OP_PA_EN           BIT(4)
+#define VIG_OP_PA_SAT_ZERO_EXP BIT(2)
+#define VIG_OP_MEM_PROT_BLEND  BIT(1)
+
+/*
+ * Definitions for CSC 10 op modes
+ */
+#define VIG_CSC_10_SRC_DATAFMT BIT(1)
+#define VIG_CSC_10_EN          BIT(0)
+#define CSC_10BIT_OFFSET       4
+
+/* traffic shaper clock in Hz */
+#define TS_CLK			19200000
+
+
+static int _sspp_subblk_offset(struct dpu_hw_pipe *ctx,
+		int s_id,
+		u32 *idx)
+{
+	int rc = 0;
+	const struct dpu_sspp_sub_blks *sblk;
+
+	if (!ctx || !ctx->cap || !ctx->cap->sblk)
+		return -EINVAL;
+
+	sblk = ctx->cap->sblk;
+
+	switch (s_id) {
+	case DPU_SSPP_SRC:
+		*idx = sblk->src_blk.base;
+		break;
+	case DPU_SSPP_SCALER_QSEED2:
+	case DPU_SSPP_SCALER_QSEED3:
+	case DPU_SSPP_SCALER_RGB:
+		*idx = sblk->scaler_blk.base;
+		break;
+	case DPU_SSPP_CSC:
+	case DPU_SSPP_CSC_10BIT:
+		*idx = sblk->csc_blk.base;
+		break;
+	default:
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+static void dpu_hw_sspp_setup_multirect(struct dpu_hw_pipe *ctx,
+		enum dpu_sspp_multirect_index index,
+		enum dpu_sspp_multirect_mode mode)
+{
+	u32 mode_mask;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (index == DPU_SSPP_RECT_SOLO) {
+		/**
+		 * if rect index is RECT_SOLO, we cannot expect a
+		 * virtual plane sharing the same SSPP id. So we go
+		 * and disable multirect
+		 */
+		mode_mask = 0;
+	} else {
+		mode_mask = DPU_REG_READ(&ctx->hw, SSPP_MULTIRECT_OPMODE + idx);
+		mode_mask |= index;
+		if (mode == DPU_SSPP_MULTIRECT_TIME_MX)
+			mode_mask |= BIT(2);
+		else
+			mode_mask &= ~BIT(2);
+	}
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_MULTIRECT_OPMODE + idx, mode_mask);
+}
+
+static void _sspp_setup_opmode(struct dpu_hw_pipe *ctx,
+		u32 mask, u8 en)
+{
+	u32 idx;
+	u32 opmode;
+
+	if (!test_bit(DPU_SSPP_SCALER_QSEED2, &ctx->cap->features) ||
+		_sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED2, &idx) ||
+		!test_bit(DPU_SSPP_CSC, &ctx->cap->features))
+		return;
+
+	opmode = DPU_REG_READ(&ctx->hw, SSPP_VIG_OP_MODE + idx);
+
+	if (en)
+		opmode |= mask;
+	else
+		opmode &= ~mask;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_VIG_OP_MODE + idx, opmode);
+}
+
+static void _sspp_setup_csc10_opmode(struct dpu_hw_pipe *ctx,
+		u32 mask, u8 en)
+{
+	u32 idx;
+	u32 opmode;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_CSC_10BIT, &idx))
+		return;
+
+	opmode = DPU_REG_READ(&ctx->hw, SSPP_VIG_CSC_10_OP_MODE + idx);
+	if (en)
+		opmode |= mask;
+	else
+		opmode &= ~mask;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_VIG_CSC_10_OP_MODE + idx, opmode);
+}
+
+/*
+ * Setup source pixel format, flip,
+ */
+static void dpu_hw_sspp_setup_format(struct dpu_hw_pipe *ctx,
+		const struct dpu_format *fmt, u32 flags,
+		enum dpu_sspp_multirect_index rect_mode)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 chroma_samp, unpack, src_format;
+	u32 opmode = 0;
+	u32 fast_clear = 0;
+	u32 op_mode_off, unpack_pat_off, format_off;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !fmt)
+		return;
+
+	if (rect_mode == DPU_SSPP_RECT_SOLO || rect_mode == DPU_SSPP_RECT_0) {
+		op_mode_off = SSPP_SRC_OP_MODE;
+		unpack_pat_off = SSPP_SRC_UNPACK_PATTERN;
+		format_off = SSPP_SRC_FORMAT;
+	} else {
+		op_mode_off = SSPP_SRC_OP_MODE_REC1;
+		unpack_pat_off = SSPP_SRC_UNPACK_PATTERN_REC1;
+		format_off = SSPP_SRC_FORMAT_REC1;
+	}
+
+	c = &ctx->hw;
+	opmode = DPU_REG_READ(c, op_mode_off + idx);
+	opmode &= ~(MDSS_MDP_OP_FLIP_LR | MDSS_MDP_OP_FLIP_UD |
+			MDSS_MDP_OP_BWC_EN | MDSS_MDP_OP_PE_OVERRIDE);
+
+	if (flags & DPU_SSPP_FLIP_LR)
+		opmode |= MDSS_MDP_OP_FLIP_LR;
+	if (flags & DPU_SSPP_FLIP_UD)
+		opmode |= MDSS_MDP_OP_FLIP_UD;
+
+	chroma_samp = fmt->chroma_sample;
+	if (flags & DPU_SSPP_SOURCE_ROTATED_90) {
+		if (chroma_samp == DPU_CHROMA_H2V1)
+			chroma_samp = DPU_CHROMA_H1V2;
+		else if (chroma_samp == DPU_CHROMA_H1V2)
+			chroma_samp = DPU_CHROMA_H2V1;
+	}
+
+	src_format = (chroma_samp << 23) | (fmt->fetch_planes << 19) |
+		(fmt->bits[C3_ALPHA] << 6) | (fmt->bits[C2_R_Cr] << 4) |
+		(fmt->bits[C1_B_Cb] << 2) | (fmt->bits[C0_G_Y] << 0);
+
+	if (flags & DPU_SSPP_ROT_90)
+		src_format |= BIT(11); /* ROT90 */
+
+	if (fmt->alpha_enable && fmt->fetch_planes == DPU_PLANE_INTERLEAVED)
+		src_format |= BIT(8); /* SRCC3_EN */
+
+	if (flags & DPU_SSPP_SOLID_FILL)
+		src_format |= BIT(22);
+
+	unpack = (fmt->element[3] << 24) | (fmt->element[2] << 16) |
+		(fmt->element[1] << 8) | (fmt->element[0] << 0);
+	src_format |= ((fmt->unpack_count - 1) << 12) |
+		(fmt->unpack_tight << 17) |
+		(fmt->unpack_align_msb << 18) |
+		((fmt->bpp - 1) << 9);
+
+	if (fmt->fetch_mode != DPU_FETCH_LINEAR) {
+		if (DPU_FORMAT_IS_UBWC(fmt))
+			opmode |= MDSS_MDP_OP_BWC_EN;
+		src_format |= (fmt->fetch_mode & 3) << 30; /*FRAME_FORMAT */
+		DPU_REG_WRITE(c, SSPP_FETCH_CONFIG,
+			DPU_FETCH_CONFIG_RESET_VALUE |
+			ctx->mdp->highest_bank_bit << 18);
+		switch (ctx->catalog->caps->ubwc_version) {
+		case DPU_HW_UBWC_VER_10:
+			/* TODO: UBWC v1 case */
+			break;
+		case DPU_HW_UBWC_VER_20:
+			fast_clear = fmt->alpha_enable ? BIT(31) : 0;
+			DPU_REG_WRITE(c, SSPP_UBWC_STATIC_CTRL,
+					fast_clear | (ctx->mdp->ubwc_swizzle) |
+					(ctx->mdp->highest_bank_bit << 4));
+			break;
+		case DPU_HW_UBWC_VER_30:
+			DPU_REG_WRITE(c, SSPP_UBWC_STATIC_CTRL,
+					BIT(30) | (ctx->mdp->ubwc_swizzle) |
+					(ctx->mdp->highest_bank_bit << 4));
+			break;
+		case DPU_HW_UBWC_VER_40:
+			DPU_REG_WRITE(c, SSPP_UBWC_STATIC_CTRL,
+					DPU_FORMAT_IS_YUV(fmt) ? 0 : BIT(30));
+			break;
+		}
+	}
+
+	opmode |= MDSS_MDP_OP_PE_OVERRIDE;
+
+	/* if this is YUV pixel format, enable CSC */
+	if (DPU_FORMAT_IS_YUV(fmt))
+		src_format |= BIT(15);
+
+	if (DPU_FORMAT_IS_DX(fmt))
+		src_format |= BIT(14);
+
+	/* update scaler opmode, if appropriate */
+	if (test_bit(DPU_SSPP_CSC, &ctx->cap->features))
+		_sspp_setup_opmode(ctx, VIG_OP_CSC_EN | VIG_OP_CSC_SRC_DATAFMT,
+			DPU_FORMAT_IS_YUV(fmt));
+	else if (test_bit(DPU_SSPP_CSC_10BIT, &ctx->cap->features))
+		_sspp_setup_csc10_opmode(ctx,
+			VIG_CSC_10_EN | VIG_CSC_10_SRC_DATAFMT,
+			DPU_FORMAT_IS_YUV(fmt));
+
+	DPU_REG_WRITE(c, format_off + idx, src_format);
+	DPU_REG_WRITE(c, unpack_pat_off + idx, unpack);
+	DPU_REG_WRITE(c, op_mode_off + idx, opmode);
+
+	/* clear previous UBWC error */
+	DPU_REG_WRITE(c, SSPP_UBWC_ERROR_STATUS + idx, BIT(31));
+}
+
+static void dpu_hw_sspp_setup_pe_config(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pixel_ext *pe_ext)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u8 color;
+	u32 lr_pe[4], tb_pe[4], tot_req_pixels[4];
+	const u32 bytemask = 0xff;
+	const u32 shortmask = 0xffff;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !pe_ext)
+		return;
+
+	c = &ctx->hw;
+
+	/* program SW pixel extension override for all pipes*/
+	for (color = 0; color < DPU_MAX_PLANES; color++) {
+		/* color 2 has the same set of registers as color 1 */
+		if (color == 2)
+			continue;
+
+		lr_pe[color] = ((pe_ext->right_ftch[color] & bytemask) << 24)|
+			((pe_ext->right_rpt[color] & bytemask) << 16)|
+			((pe_ext->left_ftch[color] & bytemask) << 8)|
+			(pe_ext->left_rpt[color] & bytemask);
+
+		tb_pe[color] = ((pe_ext->btm_ftch[color] & bytemask) << 24)|
+			((pe_ext->btm_rpt[color] & bytemask) << 16)|
+			((pe_ext->top_ftch[color] & bytemask) << 8)|
+			(pe_ext->top_rpt[color] & bytemask);
+
+		tot_req_pixels[color] = (((pe_ext->roi_h[color] +
+			pe_ext->num_ext_pxls_top[color] +
+			pe_ext->num_ext_pxls_btm[color]) & shortmask) << 16) |
+			((pe_ext->roi_w[color] +
+			pe_ext->num_ext_pxls_left[color] +
+			pe_ext->num_ext_pxls_right[color]) & shortmask);
+	}
+
+	/* color 0 */
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_LR + idx, lr_pe[0]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_TB + idx, tb_pe[0]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_REQ_PIXELS + idx,
+			tot_req_pixels[0]);
+
+	/* color 1 and color 2 */
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_LR + idx, lr_pe[1]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_TB + idx, tb_pe[1]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_REQ_PIXELS + idx,
+			tot_req_pixels[1]);
+
+	/* color 3 */
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_LR + idx, lr_pe[3]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_TB + idx, lr_pe[3]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_REQ_PIXELS + idx,
+			tot_req_pixels[3]);
+}
+
+static void _dpu_hw_sspp_setup_scaler3(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *sspp,
+		void *scaler_cfg)
+{
+	u32 idx;
+	struct dpu_hw_scaler3_cfg *scaler3_cfg = scaler_cfg;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED3, &idx) || !sspp
+		|| !scaler3_cfg)
+		return;
+
+	dpu_hw_setup_scaler3(&ctx->hw, scaler3_cfg, idx,
+			ctx->cap->sblk->scaler_blk.version,
+			sspp->layout.format);
+}
+
+static u32 _dpu_hw_sspp_get_scaler3_ver(struct dpu_hw_pipe *ctx)
+{
+	u32 idx;
+
+	if (!ctx || _sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED3, &idx))
+		return 0;
+
+	return dpu_hw_get_scaler3_ver(&ctx->hw, idx);
+}
+
+/*
+ * dpu_hw_sspp_setup_rects()
+ */
+static void dpu_hw_sspp_setup_rects(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *cfg,
+		enum dpu_sspp_multirect_index rect_index)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 src_size, src_xy, dst_size, dst_xy, ystride0, ystride1;
+	u32 src_size_off, src_xy_off, out_size_off, out_xy_off;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !cfg)
+		return;
+
+	c = &ctx->hw;
+
+	if (rect_index == DPU_SSPP_RECT_SOLO || rect_index == DPU_SSPP_RECT_0) {
+		src_size_off = SSPP_SRC_SIZE;
+		src_xy_off = SSPP_SRC_XY;
+		out_size_off = SSPP_OUT_SIZE;
+		out_xy_off = SSPP_OUT_XY;
+	} else {
+		src_size_off = SSPP_SRC_SIZE_REC1;
+		src_xy_off = SSPP_SRC_XY_REC1;
+		out_size_off = SSPP_OUT_SIZE_REC1;
+		out_xy_off = SSPP_OUT_XY_REC1;
+	}
+
+
+	/* src and dest rect programming */
+	src_xy = (cfg->src_rect.y1 << 16) | cfg->src_rect.x1;
+	src_size = (drm_rect_height(&cfg->src_rect) << 16) |
+		   drm_rect_width(&cfg->src_rect);
+	dst_xy = (cfg->dst_rect.y1 << 16) | cfg->dst_rect.x1;
+	dst_size = (drm_rect_height(&cfg->dst_rect) << 16) |
+		drm_rect_width(&cfg->dst_rect);
+
+	if (rect_index == DPU_SSPP_RECT_SOLO) {
+		ystride0 = (cfg->layout.plane_pitch[0]) |
+			(cfg->layout.plane_pitch[1] << 16);
+		ystride1 = (cfg->layout.plane_pitch[2]) |
+			(cfg->layout.plane_pitch[3] << 16);
+	} else {
+		ystride0 = DPU_REG_READ(c, SSPP_SRC_YSTRIDE0 + idx);
+		ystride1 = DPU_REG_READ(c, SSPP_SRC_YSTRIDE1 + idx);
+
+		if (rect_index == DPU_SSPP_RECT_0) {
+			ystride0 = (ystride0 & 0xFFFF0000) |
+				(cfg->layout.plane_pitch[0] & 0x0000FFFF);
+			ystride1 = (ystride1 & 0xFFFF0000)|
+				(cfg->layout.plane_pitch[2] & 0x0000FFFF);
+		} else {
+			ystride0 = (ystride0 & 0x0000FFFF) |
+				((cfg->layout.plane_pitch[0] << 16) &
+				 0xFFFF0000);
+			ystride1 = (ystride1 & 0x0000FFFF) |
+				((cfg->layout.plane_pitch[2] << 16) &
+				 0xFFFF0000);
+		}
+	}
+
+	/* rectangle register programming */
+	DPU_REG_WRITE(c, src_size_off + idx, src_size);
+	DPU_REG_WRITE(c, src_xy_off + idx, src_xy);
+	DPU_REG_WRITE(c, out_size_off + idx, dst_size);
+	DPU_REG_WRITE(c, out_xy_off + idx, dst_xy);
+
+	DPU_REG_WRITE(c, SSPP_SRC_YSTRIDE0 + idx, ystride0);
+	DPU_REG_WRITE(c, SSPP_SRC_YSTRIDE1 + idx, ystride1);
+}
+
+static void dpu_hw_sspp_setup_sourceaddress(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *cfg,
+		enum dpu_sspp_multirect_index rect_mode)
+{
+	int i;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (rect_mode == DPU_SSPP_RECT_SOLO) {
+		for (i = 0; i < ARRAY_SIZE(cfg->layout.plane_addr); i++)
+			DPU_REG_WRITE(&ctx->hw, SSPP_SRC0_ADDR + idx + i * 0x4,
+					cfg->layout.plane_addr[i]);
+	} else if (rect_mode == DPU_SSPP_RECT_0) {
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC0_ADDR + idx,
+				cfg->layout.plane_addr[0]);
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC2_ADDR + idx,
+				cfg->layout.plane_addr[2]);
+	} else {
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC1_ADDR + idx,
+				cfg->layout.plane_addr[0]);
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC3_ADDR + idx,
+				cfg->layout.plane_addr[2]);
+	}
+}
+
+static void dpu_hw_sspp_setup_csc(struct dpu_hw_pipe *ctx,
+		const struct dpu_csc_cfg *data)
+{
+	u32 idx;
+	bool csc10 = false;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_CSC, &idx) || !data)
+		return;
+
+	if (test_bit(DPU_SSPP_CSC_10BIT, &ctx->cap->features)) {
+		idx += CSC_10BIT_OFFSET;
+		csc10 = true;
+	}
+
+	dpu_hw_csc_setup(&ctx->hw, idx, data, csc10);
+}
+
+static void dpu_hw_sspp_setup_solidfill(struct dpu_hw_pipe *ctx, u32 color, enum
+		dpu_sspp_multirect_index rect_index)
+{
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (rect_index == DPU_SSPP_RECT_SOLO || rect_index == DPU_SSPP_RECT_0)
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC_CONSTANT_COLOR + idx, color);
+	else
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC_CONSTANT_COLOR_REC1 + idx,
+				color);
+}
+
+static void dpu_hw_sspp_setup_danger_safe_lut(struct dpu_hw_pipe *ctx,
+			u32 danger_lut,
+			u32 safe_lut)
+{
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_DANGER_LUT + idx, danger_lut);
+	DPU_REG_WRITE(&ctx->hw, SSPP_SAFE_LUT + idx, safe_lut);
+}
+
+static void dpu_hw_sspp_setup_creq_lut(struct dpu_hw_pipe *ctx,
+			u64 creq_lut)
+{
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (ctx->cap && test_bit(DPU_SSPP_QOS_8LVL, &ctx->cap->features)) {
+		DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT_0 + idx, creq_lut);
+		DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT_1 + idx,
+				creq_lut >> 32);
+	} else {
+		DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT + idx, creq_lut);
+	}
+}
+
+static void dpu_hw_sspp_setup_qos_ctrl(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_qos_cfg *cfg)
+{
+	u32 idx;
+	u32 qos_ctrl = 0;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (cfg->vblank_en) {
+		qos_ctrl |= ((cfg->creq_vblank &
+				SSPP_QOS_CTRL_CREQ_VBLANK_MASK) <<
+				SSPP_QOS_CTRL_CREQ_VBLANK_OFF);
+		qos_ctrl |= ((cfg->danger_vblank &
+				SSPP_QOS_CTRL_DANGER_VBLANK_MASK) <<
+				SSPP_QOS_CTRL_DANGER_VBLANK_OFF);
+		qos_ctrl |= SSPP_QOS_CTRL_VBLANK_EN;
+	}
+
+	if (cfg->danger_safe_en)
+		qos_ctrl |= SSPP_QOS_CTRL_DANGER_SAFE_EN;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_QOS_CTRL + idx, qos_ctrl);
+}
+
+static void dpu_hw_sspp_setup_cdp(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_cdp_cfg *cfg,
+		enum dpu_sspp_multirect_index index)
+{
+	u32 idx;
+	u32 cdp_cntl = 0;
+	u32 cdp_cntl_offset = 0;
+
+	if (!ctx || !cfg)
+		return;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (index == DPU_SSPP_RECT_SOLO || index == DPU_SSPP_RECT_0)
+		cdp_cntl_offset = SSPP_CDP_CNTL;
+	else
+		cdp_cntl_offset = SSPP_CDP_CNTL_REC1;
+
+	if (cfg->enable)
+		cdp_cntl |= BIT(0);
+	if (cfg->ubwc_meta_enable)
+		cdp_cntl |= BIT(1);
+	if (cfg->tile_amortize_enable)
+		cdp_cntl |= BIT(2);
+	if (cfg->preload_ahead == DPU_SSPP_CDP_PRELOAD_AHEAD_64)
+		cdp_cntl |= BIT(3);
+
+	DPU_REG_WRITE(&ctx->hw, cdp_cntl_offset, cdp_cntl);
+}
+
+static void _setup_layer_ops(struct dpu_hw_pipe *c,
+		unsigned long features)
+{
+	if (test_bit(DPU_SSPP_SRC, &features)) {
+		c->ops.setup_format = dpu_hw_sspp_setup_format;
+		c->ops.setup_rects = dpu_hw_sspp_setup_rects;
+		c->ops.setup_sourceaddress = dpu_hw_sspp_setup_sourceaddress;
+		c->ops.setup_solidfill = dpu_hw_sspp_setup_solidfill;
+		c->ops.setup_pe = dpu_hw_sspp_setup_pe_config;
+	}
+
+	if (test_bit(DPU_SSPP_QOS, &features)) {
+		c->ops.setup_danger_safe_lut =
+			dpu_hw_sspp_setup_danger_safe_lut;
+		c->ops.setup_creq_lut = dpu_hw_sspp_setup_creq_lut;
+		c->ops.setup_qos_ctrl = dpu_hw_sspp_setup_qos_ctrl;
+	}
+
+	if (test_bit(DPU_SSPP_CSC, &features) ||
+		test_bit(DPU_SSPP_CSC_10BIT, &features))
+		c->ops.setup_csc = dpu_hw_sspp_setup_csc;
+
+	if (test_bit(DPU_SSPP_SMART_DMA_V1, &c->cap->features) ||
+		test_bit(DPU_SSPP_SMART_DMA_V2, &c->cap->features))
+		c->ops.setup_multirect = dpu_hw_sspp_setup_multirect;
+
+	if (test_bit(DPU_SSPP_SCALER_QSEED3, &features) ||
+			test_bit(DPU_SSPP_SCALER_QSEED3LITE, &features) ||
+			test_bit(DPU_SSPP_SCALER_QSEED4, &features)) {
+		c->ops.setup_scaler = _dpu_hw_sspp_setup_scaler3;
+		c->ops.get_scaler_ver = _dpu_hw_sspp_get_scaler3_ver;
+	}
+
+	if (test_bit(DPU_SSPP_CDP, &features))
+		c->ops.setup_cdp = dpu_hw_sspp_setup_cdp;
+}
+
+#ifdef CONFIG_DEBUG_FS
+int _dpu_hw_sspp_init_debugfs(struct dpu_hw_pipe *hw_pipe, struct dpu_kms *kms, struct dentry *entry)
+{
+	const struct dpu_sspp_cfg *cfg = hw_pipe->cap;
+	const struct dpu_sspp_sub_blks *sblk = cfg->sblk;
+	struct dentry *debugfs_root;
+	char sspp_name[32];
+
+	snprintf(sspp_name, sizeof(sspp_name), "%d", hw_pipe->idx);
+
+	/* create overall sub-directory for the pipe */
+	debugfs_root =
+		debugfs_create_dir(sspp_name, entry);
+
+	/* don't error check these */
+	debugfs_create_xul("features", 0600,
+			debugfs_root, (unsigned long *)&hw_pipe->cap->features);
+
+	/* add register dump support */
+	dpu_debugfs_create_regset32("src_blk", 0400,
+			debugfs_root,
+			sblk->src_blk.base + cfg->base,
+			sblk->src_blk.len,
+			kms);
+
+	if (cfg->features & BIT(DPU_SSPP_SCALER_QSEED3) ||
+			cfg->features & BIT(DPU_SSPP_SCALER_QSEED3LITE) ||
+			cfg->features & BIT(DPU_SSPP_SCALER_QSEED2) ||
+			cfg->features & BIT(DPU_SSPP_SCALER_QSEED4))
+		dpu_debugfs_create_regset32("scaler_blk", 0400,
+				debugfs_root,
+				sblk->scaler_blk.base + cfg->base,
+				sblk->scaler_blk.len,
+				kms);
+
+	if (cfg->features & BIT(DPU_SSPP_CSC) ||
+			cfg->features & BIT(DPU_SSPP_CSC_10BIT))
+		dpu_debugfs_create_regset32("csc_blk", 0400,
+				debugfs_root,
+				sblk->csc_blk.base + cfg->base,
+				sblk->csc_blk.len,
+				kms);
+
+	debugfs_create_u32("xin_id",
+			0400,
+			debugfs_root,
+			(u32 *) &cfg->xin_id);
+	debugfs_create_u32("clk_ctrl",
+			0400,
+			debugfs_root,
+			(u32 *) &cfg->clk_ctrl);
+	debugfs_create_x32("creq_vblank",
+			0600,
+			debugfs_root,
+			(u32 *) &sblk->creq_vblank);
+	debugfs_create_x32("danger_vblank",
+			0600,
+			debugfs_root,
+			(u32 *) &sblk->danger_vblank);
+
+	return 0;
+}
+#endif
+
+
+static const struct dpu_sspp_cfg *_sspp_offset(enum dpu_sspp sspp,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *catalog,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	if ((sspp < SSPP_MAX) && catalog && addr && b) {
+		for (i = 0; i < catalog->sspp_count; i++) {
+			if (sspp == catalog->sspp[i].id) {
+				b->blk_addr = addr + catalog->sspp[i].base;
+				b->log_mask = DPU_DBG_MASK_SSPP;
+				return &catalog->sspp[i];
+			}
+		}
+	}
+
+	return ERR_PTR(-ENOMEM);
+}
+
+struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
+		void __iomem *addr, const struct dpu_mdss_cfg *catalog)
+{
+	struct dpu_hw_pipe *hw_pipe;
+	const struct dpu_sspp_cfg *cfg;
+
+	if (!addr || !catalog)
+		return ERR_PTR(-EINVAL);
+
+	hw_pipe = kzalloc(sizeof(*hw_pipe), GFP_KERNEL);
+	if (!hw_pipe)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _sspp_offset(idx, addr, catalog, &hw_pipe->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(hw_pipe);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Assign ops */
+	hw_pipe->catalog = catalog;
+	hw_pipe->mdp = &catalog->mdp[0];
+	hw_pipe->idx = idx;
+	hw_pipe->cap = cfg;
+	_setup_layer_ops(hw_pipe, hw_pipe->cap->features);
+
+	return hw_pipe;
+}
+
+void dpu_hw_sspp_destroy(struct dpu_hw_pipe *ctx)
+{
+	kfree(ctx);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
new file mode 100644
index 000000000..0c95b7e64
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
@@ -0,0 +1,395 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HW_SSPP_H
+#define _DPU_HW_SSPP_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_formats.h"
+
+struct dpu_hw_pipe;
+
+/**
+ * Flags
+ */
+#define DPU_SSPP_FLIP_LR		BIT(0)
+#define DPU_SSPP_FLIP_UD		BIT(1)
+#define DPU_SSPP_SOURCE_ROTATED_90	BIT(2)
+#define DPU_SSPP_ROT_90			BIT(3)
+#define DPU_SSPP_SOLID_FILL		BIT(4)
+
+/**
+ * Define all scaler feature bits in catalog
+ */
+#define DPU_SSPP_SCALER (BIT(DPU_SSPP_SCALER_RGB) | \
+			 BIT(DPU_SSPP_SCALER_QSEED2) | \
+			 BIT(DPU_SSPP_SCALER_QSEED3) | \
+			 BIT(DPU_SSPP_SCALER_QSEED3LITE) | \
+			 BIT(DPU_SSPP_SCALER_QSEED4))
+
+/*
+ * Define all CSC feature bits in catalog
+ */
+#define DPU_SSPP_CSC_ANY (BIT(DPU_SSPP_CSC) | \
+			  BIT(DPU_SSPP_CSC_10BIT))
+
+/**
+ * Component indices
+ */
+enum {
+	DPU_SSPP_COMP_0,
+	DPU_SSPP_COMP_1_2,
+	DPU_SSPP_COMP_2,
+	DPU_SSPP_COMP_3,
+
+	DPU_SSPP_COMP_MAX
+};
+
+/**
+ * DPU_SSPP_RECT_SOLO - multirect disabled
+ * DPU_SSPP_RECT_0 - rect0 of a multirect pipe
+ * DPU_SSPP_RECT_1 - rect1 of a multirect pipe
+ *
+ * Note: HW supports multirect with either RECT0 or
+ * RECT1. Considering no benefit of such configs over
+ * SOLO mode and to keep the plane management simple,
+ * we dont support single rect multirect configs.
+ */
+enum dpu_sspp_multirect_index {
+	DPU_SSPP_RECT_SOLO = 0,
+	DPU_SSPP_RECT_0,
+	DPU_SSPP_RECT_1,
+};
+
+enum dpu_sspp_multirect_mode {
+	DPU_SSPP_MULTIRECT_NONE = 0,
+	DPU_SSPP_MULTIRECT_PARALLEL,
+	DPU_SSPP_MULTIRECT_TIME_MX,
+};
+
+enum {
+	DPU_FRAME_LINEAR,
+	DPU_FRAME_TILE_A4X,
+	DPU_FRAME_TILE_A5X,
+};
+
+enum dpu_hw_filter {
+	DPU_SCALE_FILTER_NEAREST = 0,
+	DPU_SCALE_FILTER_BIL,
+	DPU_SCALE_FILTER_PCMN,
+	DPU_SCALE_FILTER_CA,
+	DPU_SCALE_FILTER_MAX
+};
+
+enum dpu_hw_filter_alpa {
+	DPU_SCALE_ALPHA_PIXEL_REP,
+	DPU_SCALE_ALPHA_BIL
+};
+
+enum dpu_hw_filter_yuv {
+	DPU_SCALE_2D_4X4,
+	DPU_SCALE_2D_CIR,
+	DPU_SCALE_1D_SEP,
+	DPU_SCALE_BIL
+};
+
+struct dpu_hw_sharp_cfg {
+	u32 strength;
+	u32 edge_thr;
+	u32 smooth_thr;
+	u32 noise_thr;
+};
+
+struct dpu_hw_pixel_ext {
+	/* scaling factors are enabled for this input layer */
+	uint8_t enable_pxl_ext;
+
+	int init_phase_x[DPU_MAX_PLANES];
+	int phase_step_x[DPU_MAX_PLANES];
+	int init_phase_y[DPU_MAX_PLANES];
+	int phase_step_y[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels extension in left, right, top and bottom direction
+	 * for all color components. This pixel value for each color component
+	 * should be sum of fetch + repeat pixels.
+	 */
+	int num_ext_pxls_left[DPU_MAX_PLANES];
+	int num_ext_pxls_right[DPU_MAX_PLANES];
+	int num_ext_pxls_top[DPU_MAX_PLANES];
+	int num_ext_pxls_btm[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels needs to be overfetched in left, right, top and
+	 * bottom directions from source image for scaling.
+	 */
+	int left_ftch[DPU_MAX_PLANES];
+	int right_ftch[DPU_MAX_PLANES];
+	int top_ftch[DPU_MAX_PLANES];
+	int btm_ftch[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels needs to be repeated in left, right, top and
+	 * bottom directions for scaling.
+	 */
+	int left_rpt[DPU_MAX_PLANES];
+	int right_rpt[DPU_MAX_PLANES];
+	int top_rpt[DPU_MAX_PLANES];
+	int btm_rpt[DPU_MAX_PLANES];
+
+	uint32_t roi_w[DPU_MAX_PLANES];
+	uint32_t roi_h[DPU_MAX_PLANES];
+
+	/*
+	 * Filter type to be used for scaling in horizontal and vertical
+	 * directions
+	 */
+	enum dpu_hw_filter horz_filter[DPU_MAX_PLANES];
+	enum dpu_hw_filter vert_filter[DPU_MAX_PLANES];
+
+};
+
+/**
+ * struct dpu_hw_pipe_cfg : Pipe description
+ * @layout:    format layout information for programming buffer to hardware
+ * @src_rect:  src ROI, caller takes into account the different operations
+ *             such as decimation, flip etc to program this field
+ * @dest_rect: destination ROI.
+ * @index:     index of the rectangle of SSPP
+ * @mode:      parallel or time multiplex multirect mode
+ */
+struct dpu_hw_pipe_cfg {
+	struct dpu_hw_fmt_layout layout;
+	struct drm_rect src_rect;
+	struct drm_rect dst_rect;
+	enum dpu_sspp_multirect_index index;
+	enum dpu_sspp_multirect_mode mode;
+};
+
+/**
+ * struct dpu_hw_pipe_qos_cfg : Source pipe QoS configuration
+ * @creq_vblank: creq value generated to vbif during vertical blanking
+ * @danger_vblank: danger value generated during vertical blanking
+ * @vblank_en: enable creq_vblank and danger_vblank during vblank
+ * @danger_safe_en: enable danger safe generation
+ */
+struct dpu_hw_pipe_qos_cfg {
+	u32 creq_vblank;
+	u32 danger_vblank;
+	bool vblank_en;
+	bool danger_safe_en;
+};
+
+/**
+ * enum CDP preload ahead address size
+ */
+enum {
+	DPU_SSPP_CDP_PRELOAD_AHEAD_32,
+	DPU_SSPP_CDP_PRELOAD_AHEAD_64
+};
+
+/**
+ * struct dpu_hw_pipe_ts_cfg - traffic shaper configuration
+ * @size: size to prefill in bytes, or zero to disable
+ * @time: time to prefill in usec, or zero to disable
+ */
+struct dpu_hw_pipe_ts_cfg {
+	u64 size;
+	u64 time;
+};
+
+/**
+ * struct dpu_hw_sspp_ops - interface to the SSPP Hw driver functions
+ * Caller must call the init function to get the pipe context for each pipe
+ * Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_sspp_ops {
+	/**
+	 * setup_format - setup pixel format cropping rectangle, flip
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe config structure
+	 * @flags: Extra flags for format config
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_format)(struct dpu_hw_pipe *ctx,
+			const struct dpu_format *fmt, u32 flags,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_rects - setup pipe ROI rectangles
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe config structure
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_rects)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_cfg *cfg,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_pe - setup pipe pixel extension
+	 * @ctx: Pointer to pipe context
+	 * @pe_ext: Pointer to pixel ext settings
+	 */
+	void (*setup_pe)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pixel_ext *pe_ext);
+
+	/**
+	 * setup_sourceaddress - setup pipe source addresses
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe config structure
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_sourceaddress)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_cfg *cfg,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_csc - setup color space coversion
+	 * @ctx: Pointer to pipe context
+	 * @data: Pointer to config structure
+	 */
+	void (*setup_csc)(struct dpu_hw_pipe *ctx, const struct dpu_csc_cfg *data);
+
+	/**
+	 * setup_solidfill - enable/disable colorfill
+	 * @ctx: Pointer to pipe context
+	 * @const_color: Fill color value
+	 * @flags: Pipe flags
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_solidfill)(struct dpu_hw_pipe *ctx, u32 color,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_multirect - setup multirect configuration
+	 * @ctx: Pointer to pipe context
+	 * @index: rectangle index in multirect
+	 * @mode: parallel fetch / time multiplex multirect mode
+	 */
+
+	void (*setup_multirect)(struct dpu_hw_pipe *ctx,
+			enum dpu_sspp_multirect_index index,
+			enum dpu_sspp_multirect_mode mode);
+
+	/**
+	 * setup_sharpening - setup sharpening
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to config structure
+	 */
+	void (*setup_sharpening)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_sharp_cfg *cfg);
+
+	/**
+	 * setup_danger_safe_lut - setup danger safe LUTs
+	 * @ctx: Pointer to pipe context
+	 * @danger_lut: LUT for generate danger level based on fill level
+	 * @safe_lut: LUT for generate safe level based on fill level
+	 *
+	 */
+	void (*setup_danger_safe_lut)(struct dpu_hw_pipe *ctx,
+			u32 danger_lut,
+			u32 safe_lut);
+
+	/**
+	 * setup_creq_lut - setup CREQ LUT
+	 * @ctx: Pointer to pipe context
+	 * @creq_lut: LUT for generate creq level based on fill level
+	 *
+	 */
+	void (*setup_creq_lut)(struct dpu_hw_pipe *ctx,
+			u64 creq_lut);
+
+	/**
+	 * setup_qos_ctrl - setup QoS control
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe QoS configuration
+	 *
+	 */
+	void (*setup_qos_ctrl)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_qos_cfg *cfg);
+
+	/**
+	 * setup_histogram - setup histograms
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to histogram configuration
+	 */
+	void (*setup_histogram)(struct dpu_hw_pipe *ctx,
+			void *cfg);
+
+	/**
+	 * setup_scaler - setup scaler
+	 * @ctx: Pointer to pipe context
+	 * @pipe_cfg: Pointer to pipe configuration
+	 * @scaler_cfg: Pointer to scaler configuration
+	 */
+	void (*setup_scaler)(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *pipe_cfg,
+		void *scaler_cfg);
+
+	/**
+	 * get_scaler_ver - get scaler h/w version
+	 * @ctx: Pointer to pipe context
+	 */
+	u32 (*get_scaler_ver)(struct dpu_hw_pipe *ctx);
+
+	/**
+	 * setup_cdp - setup client driven prefetch
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to cdp configuration
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_cdp)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_cdp_cfg *cfg,
+			enum dpu_sspp_multirect_index index);
+};
+
+/**
+ * struct dpu_hw_pipe - pipe description
+ * @base: hardware block base structure
+ * @hw: block hardware details
+ * @catalog: back pointer to catalog
+ * @mdp: pointer to associated mdp portion of the catalog
+ * @idx: pipe index
+ * @cap: pointer to layer_cfg
+ * @ops: pointer to operations possible for this pipe
+ */
+struct dpu_hw_pipe {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+	const struct dpu_mdss_cfg *catalog;
+	const struct dpu_mdp_cfg *mdp;
+
+	/* Pipe */
+	enum dpu_sspp idx;
+	const struct dpu_sspp_cfg *cap;
+
+	/* Ops */
+	struct dpu_hw_sspp_ops ops;
+};
+
+struct dpu_kms;
+/**
+ * dpu_hw_sspp_init - initializes the sspp hw driver object.
+ * Should be called once before accessing every pipe.
+ * @idx:  Pipe index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @catalog : Pointer to mdss catalog data
+ */
+struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
+		void __iomem *addr, const struct dpu_mdss_cfg *catalog);
+
+/**
+ * dpu_hw_sspp_destroy(): Destroys SSPP driver context
+ * should be called during Hw pipe cleanup.
+ * @ctx:  Pointer to SSPP driver context returned by dpu_hw_sspp_init
+ */
+void dpu_hw_sspp_destroy(struct dpu_hw_pipe *ctx);
+
+void dpu_debugfs_sspp_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root);
+int _dpu_hw_sspp_init_debugfs(struct dpu_hw_pipe *hw_pipe, struct dpu_kms *kms, struct dentry *entry);
+
+#endif /*_DPU_HW_SSPP_H */
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
new file mode 100644
index 000000000..c3110a25a
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_top.h"
+#include "dpu_kms.h"
+
+#define SSPP_SPARE                        0x28
+
+#define FLD_SPLIT_DISPLAY_CMD             BIT(1)
+#define FLD_SMART_PANEL_FREE_RUN          BIT(2)
+#define FLD_INTF_1_SW_TRG_MUX             BIT(4)
+#define FLD_INTF_2_SW_TRG_MUX             BIT(8)
+#define FLD_TE_LINE_INTER_WATERLEVEL_MASK 0xFFFF
+
+#define DANGER_STATUS                     0x360
+#define SAFE_STATUS                       0x364
+
+#define TE_LINE_INTERVAL                  0x3F4
+
+#define TRAFFIC_SHAPER_EN                 BIT(31)
+#define TRAFFIC_SHAPER_RD_CLIENT(num)     (0x030 + (num * 4))
+#define TRAFFIC_SHAPER_WR_CLIENT(num)     (0x060 + (num * 4))
+#define TRAFFIC_SHAPER_FIXPOINT_FACTOR    4
+
+#define MDP_WD_TIMER_0_CTL                0x380
+#define MDP_WD_TIMER_0_CTL2               0x384
+#define MDP_WD_TIMER_0_LOAD_VALUE         0x388
+#define MDP_WD_TIMER_1_CTL                0x390
+#define MDP_WD_TIMER_1_CTL2               0x394
+#define MDP_WD_TIMER_1_LOAD_VALUE         0x398
+#define MDP_WD_TIMER_2_CTL                0x420
+#define MDP_WD_TIMER_2_CTL2               0x424
+#define MDP_WD_TIMER_2_LOAD_VALUE         0x428
+#define MDP_WD_TIMER_3_CTL                0x430
+#define MDP_WD_TIMER_3_CTL2               0x434
+#define MDP_WD_TIMER_3_LOAD_VALUE         0x438
+#define MDP_WD_TIMER_4_CTL                0x440
+#define MDP_WD_TIMER_4_CTL2               0x444
+#define MDP_WD_TIMER_4_LOAD_VALUE         0x448
+
+#define MDP_TICK_COUNT                    16
+#define XO_CLK_RATE                       19200
+#define MS_TICKS_IN_SEC                   1000
+
+#define CALCULATE_WD_LOAD_VALUE(fps) \
+	((uint32_t)((MS_TICKS_IN_SEC * XO_CLK_RATE)/(MDP_TICK_COUNT * fps)))
+
+#define DCE_SEL                           0x450
+
+static void dpu_hw_setup_split_pipe(struct dpu_hw_mdp *mdp,
+		struct split_pipe_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 upper_pipe = 0;
+	u32 lower_pipe = 0;
+
+	if (!mdp || !cfg)
+		return;
+
+	c = &mdp->hw;
+
+	if (cfg->en) {
+		if (cfg->mode == INTF_MODE_CMD) {
+			lower_pipe = FLD_SPLIT_DISPLAY_CMD;
+			/* interface controlling sw trigger */
+			if (cfg->intf == INTF_2)
+				lower_pipe |= FLD_INTF_1_SW_TRG_MUX;
+			else
+				lower_pipe |= FLD_INTF_2_SW_TRG_MUX;
+			upper_pipe = lower_pipe;
+		} else {
+			if (cfg->intf == INTF_2) {
+				lower_pipe = FLD_INTF_1_SW_TRG_MUX;
+				upper_pipe = FLD_INTF_2_SW_TRG_MUX;
+			} else {
+				lower_pipe = FLD_INTF_2_SW_TRG_MUX;
+				upper_pipe = FLD_INTF_1_SW_TRG_MUX;
+			}
+		}
+	}
+
+	DPU_REG_WRITE(c, SSPP_SPARE, cfg->split_flush_en ? 0x1 : 0x0);
+	DPU_REG_WRITE(c, SPLIT_DISPLAY_LOWER_PIPE_CTRL, lower_pipe);
+	DPU_REG_WRITE(c, SPLIT_DISPLAY_UPPER_PIPE_CTRL, upper_pipe);
+	DPU_REG_WRITE(c, SPLIT_DISPLAY_EN, cfg->en & 0x1);
+}
+
+static bool dpu_hw_setup_clk_force_ctrl(struct dpu_hw_mdp *mdp,
+		enum dpu_clk_ctrl_type clk_ctrl, bool enable)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_off, bit_off;
+	u32 reg_val, new_val;
+	bool clk_forced_on;
+
+	if (!mdp)
+		return false;
+
+	c = &mdp->hw;
+
+	if (clk_ctrl <= DPU_CLK_CTRL_NONE || clk_ctrl >= DPU_CLK_CTRL_MAX)
+		return false;
+
+	reg_off = mdp->caps->clk_ctrls[clk_ctrl].reg_off;
+	bit_off = mdp->caps->clk_ctrls[clk_ctrl].bit_off;
+
+	reg_val = DPU_REG_READ(c, reg_off);
+
+	if (enable)
+		new_val = reg_val | BIT(bit_off);
+	else
+		new_val = reg_val & ~BIT(bit_off);
+
+	DPU_REG_WRITE(c, reg_off, new_val);
+
+	clk_forced_on = !(reg_val & BIT(bit_off));
+
+	return clk_forced_on;
+}
+
+
+static void dpu_hw_get_danger_status(struct dpu_hw_mdp *mdp,
+		struct dpu_danger_safe_status *status)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 value;
+
+	if (!mdp || !status)
+		return;
+
+	c = &mdp->hw;
+
+	value = DPU_REG_READ(c, DANGER_STATUS);
+	status->mdp = (value >> 0) & 0x3;
+	status->sspp[SSPP_VIG0] = (value >> 4) & 0x3;
+	status->sspp[SSPP_VIG1] = (value >> 6) & 0x3;
+	status->sspp[SSPP_VIG2] = (value >> 8) & 0x3;
+	status->sspp[SSPP_VIG3] = (value >> 10) & 0x3;
+	status->sspp[SSPP_RGB0] = (value >> 12) & 0x3;
+	status->sspp[SSPP_RGB1] = (value >> 14) & 0x3;
+	status->sspp[SSPP_RGB2] = (value >> 16) & 0x3;
+	status->sspp[SSPP_RGB3] = (value >> 18) & 0x3;
+	status->sspp[SSPP_DMA0] = (value >> 20) & 0x3;
+	status->sspp[SSPP_DMA1] = (value >> 22) & 0x3;
+	status->sspp[SSPP_DMA2] = (value >> 28) & 0x3;
+	status->sspp[SSPP_DMA3] = (value >> 30) & 0x3;
+	status->sspp[SSPP_CURSOR0] = (value >> 24) & 0x3;
+	status->sspp[SSPP_CURSOR1] = (value >> 26) & 0x3;
+}
+
+static void dpu_hw_setup_vsync_source(struct dpu_hw_mdp *mdp,
+		struct dpu_vsync_source_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg, wd_load_value, wd_ctl, wd_ctl2, i;
+	static const u32 pp_offset[PINGPONG_MAX] = {0xC, 0x8, 0x4, 0x13, 0x18};
+
+	if (!mdp || !cfg || (cfg->pp_count > ARRAY_SIZE(cfg->ppnumber)))
+		return;
+
+	c = &mdp->hw;
+	reg = DPU_REG_READ(c, MDP_VSYNC_SEL);
+	for (i = 0; i < cfg->pp_count; i++) {
+		int pp_idx = cfg->ppnumber[i] - PINGPONG_0;
+
+		if (pp_idx >= ARRAY_SIZE(pp_offset))
+			continue;
+
+		reg &= ~(0xf << pp_offset[pp_idx]);
+		reg |= (cfg->vsync_source & 0xf) << pp_offset[pp_idx];
+	}
+	DPU_REG_WRITE(c, MDP_VSYNC_SEL, reg);
+
+	if (cfg->vsync_source >= DPU_VSYNC_SOURCE_WD_TIMER_4 &&
+			cfg->vsync_source <= DPU_VSYNC_SOURCE_WD_TIMER_0) {
+		switch (cfg->vsync_source) {
+		case DPU_VSYNC_SOURCE_WD_TIMER_4:
+			wd_load_value = MDP_WD_TIMER_4_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_4_CTL;
+			wd_ctl2 = MDP_WD_TIMER_4_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_3:
+			wd_load_value = MDP_WD_TIMER_3_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_3_CTL;
+			wd_ctl2 = MDP_WD_TIMER_3_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_2:
+			wd_load_value = MDP_WD_TIMER_2_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_2_CTL;
+			wd_ctl2 = MDP_WD_TIMER_2_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_1:
+			wd_load_value = MDP_WD_TIMER_1_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_1_CTL;
+			wd_ctl2 = MDP_WD_TIMER_1_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_0:
+		default:
+			wd_load_value = MDP_WD_TIMER_0_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_0_CTL;
+			wd_ctl2 = MDP_WD_TIMER_0_CTL2;
+			break;
+		}
+
+		DPU_REG_WRITE(c, wd_load_value,
+			CALCULATE_WD_LOAD_VALUE(cfg->frame_rate));
+
+		DPU_REG_WRITE(c, wd_ctl, BIT(0)); /* clear timer */
+		reg = DPU_REG_READ(c, wd_ctl2);
+		reg |= BIT(8);		/* enable heartbeat timer */
+		reg |= BIT(0);		/* enable WD timer */
+		DPU_REG_WRITE(c, wd_ctl2, reg);
+
+		/* make sure that timers are enabled/disabled for vsync state */
+		wmb();
+	}
+}
+
+static void dpu_hw_get_safe_status(struct dpu_hw_mdp *mdp,
+		struct dpu_danger_safe_status *status)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 value;
+
+	if (!mdp || !status)
+		return;
+
+	c = &mdp->hw;
+
+	value = DPU_REG_READ(c, SAFE_STATUS);
+	status->mdp = (value >> 0) & 0x1;
+	status->sspp[SSPP_VIG0] = (value >> 4) & 0x1;
+	status->sspp[SSPP_VIG1] = (value >> 6) & 0x1;
+	status->sspp[SSPP_VIG2] = (value >> 8) & 0x1;
+	status->sspp[SSPP_VIG3] = (value >> 10) & 0x1;
+	status->sspp[SSPP_RGB0] = (value >> 12) & 0x1;
+	status->sspp[SSPP_RGB1] = (value >> 14) & 0x1;
+	status->sspp[SSPP_RGB2] = (value >> 16) & 0x1;
+	status->sspp[SSPP_RGB3] = (value >> 18) & 0x1;
+	status->sspp[SSPP_DMA0] = (value >> 20) & 0x1;
+	status->sspp[SSPP_DMA1] = (value >> 22) & 0x1;
+	status->sspp[SSPP_DMA2] = (value >> 28) & 0x1;
+	status->sspp[SSPP_DMA3] = (value >> 30) & 0x1;
+	status->sspp[SSPP_CURSOR0] = (value >> 24) & 0x1;
+	status->sspp[SSPP_CURSOR1] = (value >> 26) & 0x1;
+}
+
+static void dpu_hw_intf_audio_select(struct dpu_hw_mdp *mdp)
+{
+	struct dpu_hw_blk_reg_map *c;
+
+	if (!mdp)
+		return;
+
+	c = &mdp->hw;
+
+	DPU_REG_WRITE(c, HDMI_DP_CORE_SELECT, 0x1);
+}
+
+static void _setup_mdp_ops(struct dpu_hw_mdp_ops *ops,
+		unsigned long cap)
+{
+	ops->setup_split_pipe = dpu_hw_setup_split_pipe;
+	ops->setup_clk_force_ctrl = dpu_hw_setup_clk_force_ctrl;
+	ops->get_danger_status = dpu_hw_get_danger_status;
+	ops->setup_vsync_source = dpu_hw_setup_vsync_source;
+	ops->get_safe_status = dpu_hw_get_safe_status;
+
+	if (cap & BIT(DPU_MDP_AUDIO_SELECT))
+		ops->intf_audio_select = dpu_hw_intf_audio_select;
+}
+
+static const struct dpu_mdp_cfg *_top_offset(enum dpu_mdp mdp,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	if (!m || !addr || !b)
+		return ERR_PTR(-EINVAL);
+
+	for (i = 0; i < m->mdp_count; i++) {
+		if (mdp == m->mdp[i].id) {
+			b->blk_addr = addr + m->mdp[i].base;
+			b->log_mask = DPU_DBG_MASK_TOP;
+			return &m->mdp[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_mdp *mdp;
+	const struct dpu_mdp_cfg *cfg;
+
+	if (!addr || !m)
+		return ERR_PTR(-EINVAL);
+
+	mdp = kzalloc(sizeof(*mdp), GFP_KERNEL);
+	if (!mdp)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _top_offset(idx, m, addr, &mdp->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(mdp);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Assign ops
+	 */
+	mdp->idx = idx;
+	mdp->caps = cfg;
+	_setup_mdp_ops(&mdp->ops, mdp->caps->features);
+
+	return mdp;
+}
+
+void dpu_hw_mdp_destroy(struct dpu_hw_mdp *mdp)
+{
+	kfree(mdp);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h
new file mode 100644
index 000000000..a1a9e44be
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HW_TOP_H
+#define _DPU_HW_TOP_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+struct dpu_hw_mdp;
+
+/**
+ * struct traffic_shaper_cfg: traffic shaper configuration
+ * @en        : enable/disable traffic shaper
+ * @rd_client : true if read client; false if write client
+ * @client_id : client identifier
+ * @bpc_denom : denominator of byte per clk
+ * @bpc_numer : numerator of byte per clk
+ */
+struct traffic_shaper_cfg {
+	bool en;
+	bool rd_client;
+	u32 client_id;
+	u32 bpc_denom;
+	u64 bpc_numer;
+};
+
+/**
+ * struct split_pipe_cfg - pipe configuration for dual display panels
+ * @en        : Enable/disable dual pipe configuration
+ * @mode      : Panel interface mode
+ * @intf      : Interface id for main control path
+ * @split_flush_en: Allows both the paths to be flushed when master path is
+ *              flushed
+ */
+struct split_pipe_cfg {
+	bool en;
+	enum dpu_intf_mode mode;
+	enum dpu_intf intf;
+	bool split_flush_en;
+};
+
+/**
+ * struct dpu_danger_safe_status: danger and safe status signals
+ * @mdp: top level status
+ * @sspp: source pipe status
+ */
+struct dpu_danger_safe_status {
+	u8 mdp;
+	u8 sspp[SSPP_MAX];
+};
+
+/**
+ * struct dpu_vsync_source_cfg - configure vsync source and configure the
+ *                                    watchdog timers if required.
+ * @pp_count: number of ping pongs active
+ * @frame_rate: Display frame rate
+ * @ppnumber: ping pong index array
+ * @vsync_source: vsync source selection
+ */
+struct dpu_vsync_source_cfg {
+	u32 pp_count;
+	u32 frame_rate;
+	u32 ppnumber[PINGPONG_MAX];
+	u32 vsync_source;
+};
+
+/**
+ * struct dpu_hw_mdp_ops - interface to the MDP TOP Hw driver functions
+ * Assumption is these functions will be called after clocks are enabled.
+ * @setup_split_pipe : Programs the pipe control registers
+ * @setup_pp_split : Programs the pp split control registers
+ * @setup_traffic_shaper : programs traffic shaper control
+ */
+struct dpu_hw_mdp_ops {
+	/** setup_split_pipe() : Registers are not double buffered, thisk
+	 * function should be called before timing control enable
+	 * @mdp  : mdp top context driver
+	 * @cfg  : upper and lower part of pipe configuration
+	 */
+	void (*setup_split_pipe)(struct dpu_hw_mdp *mdp,
+			struct split_pipe_cfg *p);
+
+	/**
+	 * setup_traffic_shaper() : Setup traffic shaper control
+	 * @mdp  : mdp top context driver
+	 * @cfg  : traffic shaper configuration
+	 */
+	void (*setup_traffic_shaper)(struct dpu_hw_mdp *mdp,
+			struct traffic_shaper_cfg *cfg);
+
+	/**
+	 * setup_clk_force_ctrl - set clock force control
+	 * @mdp: mdp top context driver
+	 * @clk_ctrl: clock to be controlled
+	 * @enable: force on enable
+	 * @return: if the clock is forced-on by this function
+	 */
+	bool (*setup_clk_force_ctrl)(struct dpu_hw_mdp *mdp,
+			enum dpu_clk_ctrl_type clk_ctrl, bool enable);
+
+	/**
+	 * get_danger_status - get danger status
+	 * @mdp: mdp top context driver
+	 * @status: Pointer to danger safe status
+	 */
+	void (*get_danger_status)(struct dpu_hw_mdp *mdp,
+			struct dpu_danger_safe_status *status);
+
+	/**
+	 * setup_vsync_source - setup vsync source configuration details
+	 * @mdp: mdp top context driver
+	 * @cfg: vsync source selection configuration
+	 */
+	void (*setup_vsync_source)(struct dpu_hw_mdp *mdp,
+				struct dpu_vsync_source_cfg *cfg);
+
+	/**
+	 * get_safe_status - get safe status
+	 * @mdp: mdp top context driver
+	 * @status: Pointer to danger safe status
+	 */
+	void (*get_safe_status)(struct dpu_hw_mdp *mdp,
+			struct dpu_danger_safe_status *status);
+
+	/**
+	 * intf_audio_select - select the external interface for audio
+	 * @mdp: mdp top context driver
+	 */
+	void (*intf_audio_select)(struct dpu_hw_mdp *mdp);
+};
+
+struct dpu_hw_mdp {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* top */
+	enum dpu_mdp idx;
+	const struct dpu_mdp_cfg *caps;
+
+	/* ops */
+	struct dpu_hw_mdp_ops ops;
+};
+
+/**
+ * dpu_hw_mdptop_init - initializes the top driver for the passed idx
+ * @idx:  Interface index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @m:    Pointer to mdss catalog data
+ */
+struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+void dpu_hw_mdp_destroy(struct dpu_hw_mdp *mdp);
+
+#endif /*_DPU_HW_TOP_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
new file mode 100644
index 000000000..1b7439ae6
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
@@ -0,0 +1,492 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+/* using a file static variables for debugfs access */
+static u32 dpu_hw_util_log_mask = DPU_DBG_MASK_NONE;
+
+/* DPU_SCALER_QSEED3 */
+#define QSEED3_HW_VERSION                  0x00
+#define QSEED3_OP_MODE                     0x04
+#define QSEED3_RGB2Y_COEFF                 0x08
+#define QSEED3_PHASE_INIT                  0x0C
+#define QSEED3_PHASE_STEP_Y_H              0x10
+#define QSEED3_PHASE_STEP_Y_V              0x14
+#define QSEED3_PHASE_STEP_UV_H             0x18
+#define QSEED3_PHASE_STEP_UV_V             0x1C
+#define QSEED3_PRELOAD                     0x20
+#define QSEED3_DE_SHARPEN                  0x24
+#define QSEED3_DE_SHARPEN_CTL              0x28
+#define QSEED3_DE_SHAPE_CTL                0x2C
+#define QSEED3_DE_THRESHOLD                0x30
+#define QSEED3_DE_ADJUST_DATA_0            0x34
+#define QSEED3_DE_ADJUST_DATA_1            0x38
+#define QSEED3_DE_ADJUST_DATA_2            0x3C
+#define QSEED3_SRC_SIZE_Y_RGB_A            0x40
+#define QSEED3_SRC_SIZE_UV                 0x44
+#define QSEED3_DST_SIZE                    0x48
+#define QSEED3_COEF_LUT_CTRL               0x4C
+#define QSEED3_COEF_LUT_SWAP_BIT           0
+#define QSEED3_COEF_LUT_DIR_BIT            1
+#define QSEED3_COEF_LUT_Y_CIR_BIT          2
+#define QSEED3_COEF_LUT_UV_CIR_BIT         3
+#define QSEED3_COEF_LUT_Y_SEP_BIT          4
+#define QSEED3_COEF_LUT_UV_SEP_BIT         5
+#define QSEED3_BUFFER_CTRL                 0x50
+#define QSEED3_CLK_CTRL0                   0x54
+#define QSEED3_CLK_CTRL1                   0x58
+#define QSEED3_CLK_STATUS                  0x5C
+#define QSEED3_PHASE_INIT_Y_H              0x90
+#define QSEED3_PHASE_INIT_Y_V              0x94
+#define QSEED3_PHASE_INIT_UV_H             0x98
+#define QSEED3_PHASE_INIT_UV_V             0x9C
+#define QSEED3_COEF_LUT                    0x100
+#define QSEED3_FILTERS                     5
+#define QSEED3_LUT_REGIONS                 4
+#define QSEED3_CIRCULAR_LUTS               9
+#define QSEED3_SEPARABLE_LUTS              10
+#define QSEED3_LUT_SIZE                    60
+#define QSEED3_ENABLE                      2
+#define QSEED3_DIR_LUT_SIZE                (200 * sizeof(u32))
+#define QSEED3_CIR_LUT_SIZE \
+	(QSEED3_LUT_SIZE * QSEED3_CIRCULAR_LUTS * sizeof(u32))
+#define QSEED3_SEP_LUT_SIZE \
+	(QSEED3_LUT_SIZE * QSEED3_SEPARABLE_LUTS * sizeof(u32))
+
+/* DPU_SCALER_QSEED3LITE */
+#define QSEED3LITE_COEF_LUT_Y_SEP_BIT         4
+#define QSEED3LITE_COEF_LUT_UV_SEP_BIT        5
+#define QSEED3LITE_COEF_LUT_CTRL              0x4C
+#define QSEED3LITE_COEF_LUT_SWAP_BIT          0
+#define QSEED3LITE_DIR_FILTER_WEIGHT          0x60
+#define QSEED3LITE_FILTERS                 2
+#define QSEED3LITE_SEPARABLE_LUTS             10
+#define QSEED3LITE_LUT_SIZE                   33
+#define QSEED3LITE_SEP_LUT_SIZE \
+	        (QSEED3LITE_LUT_SIZE * QSEED3LITE_SEPARABLE_LUTS * sizeof(u32))
+
+
+void dpu_reg_write(struct dpu_hw_blk_reg_map *c,
+		u32 reg_off,
+		u32 val,
+		const char *name)
+{
+	/* don't need to mutex protect this */
+	if (c->log_mask & dpu_hw_util_log_mask)
+		DPU_DEBUG_DRIVER("[%s:0x%X] <= 0x%X\n",
+				name, reg_off, val);
+	writel_relaxed(val, c->blk_addr + reg_off);
+}
+
+int dpu_reg_read(struct dpu_hw_blk_reg_map *c, u32 reg_off)
+{
+	return readl_relaxed(c->blk_addr + reg_off);
+}
+
+u32 *dpu_hw_util_get_log_mask_ptr(void)
+{
+	return &dpu_hw_util_log_mask;
+}
+
+static void _dpu_hw_setup_scaler3_lut(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg, u32 offset)
+{
+	int i, j, filter;
+	int config_lut = 0x0;
+	unsigned long lut_flags;
+	u32 lut_addr, lut_offset, lut_len;
+	u32 *lut[QSEED3_FILTERS] = {NULL, NULL, NULL, NULL, NULL};
+	static const uint32_t off_tbl[QSEED3_FILTERS][QSEED3_LUT_REGIONS][2] = {
+		{{18, 0x000}, {12, 0x120}, {12, 0x1E0}, {8, 0x2A0} },
+		{{6, 0x320}, {3, 0x3E0}, {3, 0x440}, {3, 0x4A0} },
+		{{6, 0x500}, {3, 0x5c0}, {3, 0x620}, {3, 0x680} },
+		{{6, 0x380}, {3, 0x410}, {3, 0x470}, {3, 0x4d0} },
+		{{6, 0x560}, {3, 0x5f0}, {3, 0x650}, {3, 0x6b0} },
+	};
+
+	lut_flags = (unsigned long) scaler3_cfg->lut_flag;
+	if (test_bit(QSEED3_COEF_LUT_DIR_BIT, &lut_flags) &&
+		(scaler3_cfg->dir_len == QSEED3_DIR_LUT_SIZE)) {
+		lut[0] = scaler3_cfg->dir_lut;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_Y_CIR_BIT, &lut_flags) &&
+		(scaler3_cfg->y_rgb_cir_lut_idx < QSEED3_CIRCULAR_LUTS) &&
+		(scaler3_cfg->cir_len == QSEED3_CIR_LUT_SIZE)) {
+		lut[1] = scaler3_cfg->cir_lut +
+			scaler3_cfg->y_rgb_cir_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_UV_CIR_BIT, &lut_flags) &&
+		(scaler3_cfg->uv_cir_lut_idx < QSEED3_CIRCULAR_LUTS) &&
+		(scaler3_cfg->cir_len == QSEED3_CIR_LUT_SIZE)) {
+		lut[2] = scaler3_cfg->cir_lut +
+			scaler3_cfg->uv_cir_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_Y_SEP_BIT, &lut_flags) &&
+		(scaler3_cfg->y_rgb_sep_lut_idx < QSEED3_SEPARABLE_LUTS) &&
+		(scaler3_cfg->sep_len == QSEED3_SEP_LUT_SIZE)) {
+		lut[3] = scaler3_cfg->sep_lut +
+			scaler3_cfg->y_rgb_sep_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_UV_SEP_BIT, &lut_flags) &&
+		(scaler3_cfg->uv_sep_lut_idx < QSEED3_SEPARABLE_LUTS) &&
+		(scaler3_cfg->sep_len == QSEED3_SEP_LUT_SIZE)) {
+		lut[4] = scaler3_cfg->sep_lut +
+			scaler3_cfg->uv_sep_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+
+	if (config_lut) {
+		for (filter = 0; filter < QSEED3_FILTERS; filter++) {
+			if (!lut[filter])
+				continue;
+			lut_offset = 0;
+			for (i = 0; i < QSEED3_LUT_REGIONS; i++) {
+				lut_addr = QSEED3_COEF_LUT + offset
+					+ off_tbl[filter][i][1];
+				lut_len = off_tbl[filter][i][0] << 2;
+				for (j = 0; j < lut_len; j++) {
+					DPU_REG_WRITE(c,
+						lut_addr,
+						(lut[filter])[lut_offset++]);
+					lut_addr += 4;
+				}
+			}
+		}
+	}
+
+	if (test_bit(QSEED3_COEF_LUT_SWAP_BIT, &lut_flags))
+		DPU_REG_WRITE(c, QSEED3_COEF_LUT_CTRL + offset, BIT(0));
+
+}
+
+static void _dpu_hw_setup_scaler3lite_lut(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg, u32 offset)
+{
+	int j, filter;
+	int config_lut = 0x0;
+	unsigned long lut_flags;
+	u32 lut_addr, lut_offset;
+	u32 *lut[QSEED3LITE_FILTERS] = {NULL, NULL};
+	static const uint32_t off_tbl[QSEED3_FILTERS] = { 0x000, 0x200 };
+
+	DPU_REG_WRITE(c, QSEED3LITE_DIR_FILTER_WEIGHT + offset, scaler3_cfg->dir_weight);
+
+	if (!scaler3_cfg->sep_lut)
+		return;
+
+	lut_flags = (unsigned long) scaler3_cfg->lut_flag;
+	if (test_bit(QSEED3_COEF_LUT_Y_SEP_BIT, &lut_flags) &&
+		(scaler3_cfg->y_rgb_sep_lut_idx < QSEED3LITE_SEPARABLE_LUTS) &&
+		(scaler3_cfg->sep_len == QSEED3LITE_SEP_LUT_SIZE)) {
+		lut[0] = scaler3_cfg->sep_lut +
+			scaler3_cfg->y_rgb_sep_lut_idx * QSEED3LITE_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_UV_SEP_BIT, &lut_flags) &&
+		(scaler3_cfg->uv_sep_lut_idx < QSEED3LITE_SEPARABLE_LUTS) &&
+		(scaler3_cfg->sep_len == QSEED3LITE_SEP_LUT_SIZE)) {
+		lut[1] = scaler3_cfg->sep_lut +
+			scaler3_cfg->uv_sep_lut_idx * QSEED3LITE_LUT_SIZE;
+		config_lut = 1;
+	}
+
+	if (config_lut) {
+		for (filter = 0; filter < QSEED3LITE_FILTERS; filter++) {
+			if (!lut[filter])
+				continue;
+			lut_offset = 0;
+			lut_addr = QSEED3_COEF_LUT + offset + off_tbl[filter];
+			for (j = 0; j < QSEED3LITE_LUT_SIZE; j++) {
+				DPU_REG_WRITE(c,
+					lut_addr,
+					(lut[filter])[lut_offset++]);
+				lut_addr += 4;
+			}
+		}
+	}
+
+	if (test_bit(QSEED3_COEF_LUT_SWAP_BIT, &lut_flags))
+		DPU_REG_WRITE(c, QSEED3_COEF_LUT_CTRL + offset, BIT(0));
+
+}
+
+static void _dpu_hw_setup_scaler3_de(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_de_cfg *de_cfg, u32 offset)
+{
+	u32 sharp_lvl, sharp_ctl, shape_ctl, de_thr;
+	u32 adjust_a, adjust_b, adjust_c;
+
+	if (!de_cfg->enable)
+		return;
+
+	sharp_lvl = (de_cfg->sharpen_level1 & 0x1FF) |
+		((de_cfg->sharpen_level2 & 0x1FF) << 16);
+
+	sharp_ctl = ((de_cfg->limit & 0xF) << 9) |
+		((de_cfg->prec_shift & 0x7) << 13) |
+		((de_cfg->clip & 0x7) << 16);
+
+	shape_ctl = (de_cfg->thr_quiet & 0xFF) |
+		((de_cfg->thr_dieout & 0x3FF) << 16);
+
+	de_thr = (de_cfg->thr_low & 0x3FF) |
+		((de_cfg->thr_high & 0x3FF) << 16);
+
+	adjust_a = (de_cfg->adjust_a[0] & 0x3FF) |
+		((de_cfg->adjust_a[1] & 0x3FF) << 10) |
+		((de_cfg->adjust_a[2] & 0x3FF) << 20);
+
+	adjust_b = (de_cfg->adjust_b[0] & 0x3FF) |
+		((de_cfg->adjust_b[1] & 0x3FF) << 10) |
+		((de_cfg->adjust_b[2] & 0x3FF) << 20);
+
+	adjust_c = (de_cfg->adjust_c[0] & 0x3FF) |
+		((de_cfg->adjust_c[1] & 0x3FF) << 10) |
+		((de_cfg->adjust_c[2] & 0x3FF) << 20);
+
+	DPU_REG_WRITE(c, QSEED3_DE_SHARPEN + offset, sharp_lvl);
+	DPU_REG_WRITE(c, QSEED3_DE_SHARPEN_CTL + offset, sharp_ctl);
+	DPU_REG_WRITE(c, QSEED3_DE_SHAPE_CTL + offset, shape_ctl);
+	DPU_REG_WRITE(c, QSEED3_DE_THRESHOLD + offset, de_thr);
+	DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_0 + offset, adjust_a);
+	DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_1 + offset, adjust_b);
+	DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_2 + offset, adjust_c);
+
+}
+
+void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg,
+		u32 scaler_offset, u32 scaler_version,
+		const struct dpu_format *format)
+{
+	u32 op_mode = 0;
+	u32 phase_init, preload, src_y_rgb, src_uv, dst;
+
+	if (!scaler3_cfg->enable)
+		goto end;
+
+	op_mode |= BIT(0);
+	op_mode |= (scaler3_cfg->y_rgb_filter_cfg & 0x3) << 16;
+
+	if (format && DPU_FORMAT_IS_YUV(format)) {
+		op_mode |= BIT(12);
+		op_mode |= (scaler3_cfg->uv_filter_cfg & 0x3) << 24;
+	}
+
+	op_mode |= (scaler3_cfg->blend_cfg & 1) << 31;
+	op_mode |= (scaler3_cfg->dir_en) ? BIT(4) : 0;
+
+	preload =
+		((scaler3_cfg->preload_x[0] & 0x7F) << 0) |
+		((scaler3_cfg->preload_y[0] & 0x7F) << 8) |
+		((scaler3_cfg->preload_x[1] & 0x7F) << 16) |
+		((scaler3_cfg->preload_y[1] & 0x7F) << 24);
+
+	src_y_rgb = (scaler3_cfg->src_width[0] & 0x1FFFF) |
+		((scaler3_cfg->src_height[0] & 0x1FFFF) << 16);
+
+	src_uv = (scaler3_cfg->src_width[1] & 0x1FFFF) |
+		((scaler3_cfg->src_height[1] & 0x1FFFF) << 16);
+
+	dst = (scaler3_cfg->dst_width & 0x1FFFF) |
+		((scaler3_cfg->dst_height & 0x1FFFF) << 16);
+
+	if (scaler3_cfg->de.enable) {
+		_dpu_hw_setup_scaler3_de(c, &scaler3_cfg->de, scaler_offset);
+		op_mode |= BIT(8);
+	}
+
+	if (scaler3_cfg->lut_flag) {
+		if (scaler_version < 0x2004)
+			_dpu_hw_setup_scaler3_lut(c, scaler3_cfg, scaler_offset);
+		else
+			_dpu_hw_setup_scaler3lite_lut(c, scaler3_cfg, scaler_offset);
+	}
+
+	if (scaler_version == 0x1002) {
+		phase_init =
+			((scaler3_cfg->init_phase_x[0] & 0x3F) << 0) |
+			((scaler3_cfg->init_phase_y[0] & 0x3F) << 8) |
+			((scaler3_cfg->init_phase_x[1] & 0x3F) << 16) |
+			((scaler3_cfg->init_phase_y[1] & 0x3F) << 24);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT + scaler_offset, phase_init);
+	} else {
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_Y_H + scaler_offset,
+			scaler3_cfg->init_phase_x[0] & 0x1FFFFF);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_Y_V + scaler_offset,
+			scaler3_cfg->init_phase_y[0] & 0x1FFFFF);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_UV_H + scaler_offset,
+			scaler3_cfg->init_phase_x[1] & 0x1FFFFF);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_UV_V + scaler_offset,
+			scaler3_cfg->init_phase_y[1] & 0x1FFFFF);
+	}
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_Y_H + scaler_offset,
+		scaler3_cfg->phase_step_x[0] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_Y_V + scaler_offset,
+		scaler3_cfg->phase_step_y[0] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_UV_H + scaler_offset,
+		scaler3_cfg->phase_step_x[1] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_UV_V + scaler_offset,
+		scaler3_cfg->phase_step_y[1] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PRELOAD + scaler_offset, preload);
+
+	DPU_REG_WRITE(c, QSEED3_SRC_SIZE_Y_RGB_A + scaler_offset, src_y_rgb);
+
+	DPU_REG_WRITE(c, QSEED3_SRC_SIZE_UV + scaler_offset, src_uv);
+
+	DPU_REG_WRITE(c, QSEED3_DST_SIZE + scaler_offset, dst);
+
+end:
+	if (format && !DPU_FORMAT_IS_DX(format))
+		op_mode |= BIT(14);
+
+	if (format && format->alpha_enable) {
+		op_mode |= BIT(10);
+		if (scaler_version == 0x1002)
+			op_mode |= (scaler3_cfg->alpha_filter_cfg & 0x1) << 30;
+		else
+			op_mode |= (scaler3_cfg->alpha_filter_cfg & 0x3) << 29;
+	}
+
+	DPU_REG_WRITE(c, QSEED3_OP_MODE + scaler_offset, op_mode);
+}
+
+u32 dpu_hw_get_scaler3_ver(struct dpu_hw_blk_reg_map *c,
+			u32 scaler_offset)
+{
+	return DPU_REG_READ(c, QSEED3_HW_VERSION + scaler_offset);
+}
+
+void dpu_hw_csc_setup(struct dpu_hw_blk_reg_map *c,
+		u32 csc_reg_off,
+		const struct dpu_csc_cfg *data, bool csc10)
+{
+	static const u32 matrix_shift = 7;
+	u32 clamp_shift = csc10 ? 16 : 8;
+	u32 val;
+
+	/* matrix coeff - convert S15.16 to S4.9 */
+	val = ((data->csc_mv[0] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[1] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off, val);
+	val = ((data->csc_mv[2] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[3] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off + 0x4, val);
+	val = ((data->csc_mv[4] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[5] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off + 0x8, val);
+	val = ((data->csc_mv[6] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[7] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off + 0xc, val);
+	val = (data->csc_mv[8] >> matrix_shift) & 0x1FFF;
+	DPU_REG_WRITE(c, csc_reg_off + 0x10, val);
+
+	/* Pre clamp */
+	val = (data->csc_pre_lv[0] << clamp_shift) | data->csc_pre_lv[1];
+	DPU_REG_WRITE(c, csc_reg_off + 0x14, val);
+	val = (data->csc_pre_lv[2] << clamp_shift) | data->csc_pre_lv[3];
+	DPU_REG_WRITE(c, csc_reg_off + 0x18, val);
+	val = (data->csc_pre_lv[4] << clamp_shift) | data->csc_pre_lv[5];
+	DPU_REG_WRITE(c, csc_reg_off + 0x1c, val);
+
+	/* Post clamp */
+	val = (data->csc_post_lv[0] << clamp_shift) | data->csc_post_lv[1];
+	DPU_REG_WRITE(c, csc_reg_off + 0x20, val);
+	val = (data->csc_post_lv[2] << clamp_shift) | data->csc_post_lv[3];
+	DPU_REG_WRITE(c, csc_reg_off + 0x24, val);
+	val = (data->csc_post_lv[4] << clamp_shift) | data->csc_post_lv[5];
+	DPU_REG_WRITE(c, csc_reg_off + 0x28, val);
+
+	/* Pre-Bias */
+	DPU_REG_WRITE(c, csc_reg_off + 0x2c, data->csc_pre_bv[0]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x30, data->csc_pre_bv[1]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x34, data->csc_pre_bv[2]);
+
+	/* Post-Bias */
+	DPU_REG_WRITE(c, csc_reg_off + 0x38, data->csc_post_bv[0]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x3c, data->csc_post_bv[1]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x40, data->csc_post_bv[2]);
+}
+
+/**
+ * _dpu_hw_get_qos_lut - get LUT mapping based on fill level
+ * @tbl:		Pointer to LUT table
+ * @total_fl:		fill level
+ * Return: LUT setting corresponding to the fill level
+ */
+u64 _dpu_hw_get_qos_lut(const struct dpu_qos_lut_tbl *tbl,
+		u32 total_fl)
+{
+	int i;
+
+	if (!tbl || !tbl->nentry || !tbl->entries)
+		return 0;
+
+	for (i = 0; i < tbl->nentry; i++)
+		if (total_fl <= tbl->entries[i].fl)
+			return tbl->entries[i].lut;
+
+	/* if last fl is zero, use as default */
+	if (!tbl->entries[i-1].fl)
+		return tbl->entries[i-1].lut;
+
+	return 0;
+}
+
+/*
+ * note: Aside from encoders, input_sel should be set to 0x0 by default
+ */
+void dpu_hw_setup_misr(struct dpu_hw_blk_reg_map *c,
+		u32 misr_ctrl_offset, u8 input_sel)
+{
+	u32 config = 0;
+
+	DPU_REG_WRITE(c, misr_ctrl_offset, MISR_CTRL_STATUS_CLEAR);
+
+	/* Clear old MISR value (in case it's read before a new value is calculated)*/
+	wmb();
+
+	config = MISR_FRAME_COUNT | MISR_CTRL_ENABLE | MISR_CTRL_FREE_RUN_MASK |
+		((input_sel & 0xF) << 24);
+	DPU_REG_WRITE(c, misr_ctrl_offset, config);
+}
+
+int dpu_hw_collect_misr(struct dpu_hw_blk_reg_map *c,
+		u32 misr_ctrl_offset,
+		u32 misr_signature_offset,
+		u32 *misr_value)
+{
+	u32 ctrl = 0;
+
+	if (!misr_value)
+		return -EINVAL;
+
+	ctrl = DPU_REG_READ(c, misr_ctrl_offset);
+
+	if (!(ctrl & MISR_CTRL_ENABLE))
+		return -ENODATA;
+
+	if (!(ctrl & MISR_CTRL_STATUS))
+		return -EINVAL;
+
+	*misr_value = DPU_REG_READ(c, misr_signature_offset);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
new file mode 100644
index 000000000..4ae2a4343
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
@@ -0,0 +1,360 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2015-2021, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HW_UTIL_H
+#define _DPU_HW_UTIL_H
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_catalog.h"
+
+#define REG_MASK(n)                     ((BIT(n)) - 1)
+#define MISR_FRAME_COUNT                0x1
+#define MISR_CTRL_ENABLE                BIT(8)
+#define MISR_CTRL_STATUS                BIT(9)
+#define MISR_CTRL_STATUS_CLEAR          BIT(10)
+#define MISR_CTRL_FREE_RUN_MASK         BIT(31)
+
+/*
+ * This is the common struct maintained by each sub block
+ * for mapping the register offsets in this block to the
+ * absoulute IO address
+ * @blk_addr:     hw block register mapped address
+ * @log_mask:     log mask for this block
+ */
+struct dpu_hw_blk_reg_map {
+	void __iomem *blk_addr;
+	u32 log_mask;
+};
+
+/**
+ * struct dpu_hw_blk - opaque hardware block object
+ */
+struct dpu_hw_blk {
+	/* opaque */
+};
+
+/**
+ * struct dpu_hw_scaler3_de_cfg : QSEEDv3 detail enhancer configuration
+ * @enable:         detail enhancer enable/disable
+ * @sharpen_level1: sharpening strength for noise
+ * @sharpen_level2: sharpening strength for signal
+ * @ clip:          clip shift
+ * @ limit:         limit value
+ * @ thr_quiet:     quiet threshold
+ * @ thr_dieout:    dieout threshold
+ * @ thr_high:      low threshold
+ * @ thr_high:      high threshold
+ * @ prec_shift:    precision shift
+ * @ adjust_a:      A-coefficients for mapping curve
+ * @ adjust_b:      B-coefficients for mapping curve
+ * @ adjust_c:      C-coefficients for mapping curve
+ */
+struct dpu_hw_scaler3_de_cfg {
+	u32 enable;
+	int16_t sharpen_level1;
+	int16_t sharpen_level2;
+	uint16_t clip;
+	uint16_t limit;
+	uint16_t thr_quiet;
+	uint16_t thr_dieout;
+	uint16_t thr_low;
+	uint16_t thr_high;
+	uint16_t prec_shift;
+	int16_t adjust_a[DPU_MAX_DE_CURVES];
+	int16_t adjust_b[DPU_MAX_DE_CURVES];
+	int16_t adjust_c[DPU_MAX_DE_CURVES];
+};
+
+
+/**
+ * struct dpu_hw_scaler3_cfg : QSEEDv3 configuration
+ * @enable:        scaler enable
+ * @dir_en:        direction detection block enable
+ * @ init_phase_x: horizontal initial phase
+ * @ phase_step_x: horizontal phase step
+ * @ init_phase_y: vertical initial phase
+ * @ phase_step_y: vertical phase step
+ * @ preload_x:    horizontal preload value
+ * @ preload_y:    vertical preload value
+ * @ src_width:    source width
+ * @ src_height:   source height
+ * @ dst_width:    destination width
+ * @ dst_height:   destination height
+ * @ y_rgb_filter_cfg: y/rgb plane filter configuration
+ * @ uv_filter_cfg: uv plane filter configuration
+ * @ alpha_filter_cfg: alpha filter configuration
+ * @ blend_cfg:    blend coefficients configuration
+ * @ lut_flag:     scaler LUT update flags
+ *                 0x1 swap LUT bank
+ *                 0x2 update 2D filter LUT
+ *                 0x4 update y circular filter LUT
+ *                 0x8 update uv circular filter LUT
+ *                 0x10 update y separable filter LUT
+ *                 0x20 update uv separable filter LUT
+ * @ dir_lut_idx:  2D filter LUT index
+ * @ y_rgb_cir_lut_idx: y circular filter LUT index
+ * @ uv_cir_lut_idx: uv circular filter LUT index
+ * @ y_rgb_sep_lut_idx: y circular filter LUT index
+ * @ uv_sep_lut_idx: uv separable filter LUT index
+ * @ dir_lut:      pointer to 2D LUT
+ * @ cir_lut:      pointer to circular filter LUT
+ * @ sep_lut:      pointer to separable filter LUT
+ * @ de: detail enhancer configuration
+ * @ dir_weight:   Directional weight
+ */
+struct dpu_hw_scaler3_cfg {
+	u32 enable;
+	u32 dir_en;
+	int32_t init_phase_x[DPU_MAX_PLANES];
+	int32_t phase_step_x[DPU_MAX_PLANES];
+	int32_t init_phase_y[DPU_MAX_PLANES];
+	int32_t phase_step_y[DPU_MAX_PLANES];
+
+	u32 preload_x[DPU_MAX_PLANES];
+	u32 preload_y[DPU_MAX_PLANES];
+	u32 src_width[DPU_MAX_PLANES];
+	u32 src_height[DPU_MAX_PLANES];
+
+	u32 dst_width;
+	u32 dst_height;
+
+	u32 y_rgb_filter_cfg;
+	u32 uv_filter_cfg;
+	u32 alpha_filter_cfg;
+	u32 blend_cfg;
+
+	u32 lut_flag;
+	u32 dir_lut_idx;
+
+	u32 y_rgb_cir_lut_idx;
+	u32 uv_cir_lut_idx;
+	u32 y_rgb_sep_lut_idx;
+	u32 uv_sep_lut_idx;
+	u32 *dir_lut;
+	size_t dir_len;
+	u32 *cir_lut;
+	size_t cir_len;
+	u32 *sep_lut;
+	size_t sep_len;
+
+	/*
+	 * Detail enhancer settings
+	 */
+	struct dpu_hw_scaler3_de_cfg de;
+
+	u32 dir_weight;
+};
+
+/**
+ * struct dpu_drm_pix_ext_v1 - version 1 of pixel ext structure
+ * @num_ext_pxls_lr: Number of total horizontal pixels
+ * @num_ext_pxls_tb: Number of total vertical lines
+ * @left_ftch:       Number of extra pixels to overfetch from left
+ * @right_ftch:      Number of extra pixels to overfetch from right
+ * @top_ftch:        Number of extra lines to overfetch from top
+ * @btm_ftch:        Number of extra lines to overfetch from bottom
+ * @left_rpt:        Number of extra pixels to repeat from left
+ * @right_rpt:       Number of extra pixels to repeat from right
+ * @top_rpt:         Number of extra lines to repeat from top
+ * @btm_rpt:         Number of extra lines to repeat from bottom
+ */
+struct dpu_drm_pix_ext_v1 {
+	/*
+	 * Number of pixels ext in left, right, top and bottom direction
+	 * for all color components.
+	 */
+	int32_t num_ext_pxls_lr[DPU_MAX_PLANES];
+	int32_t num_ext_pxls_tb[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels needs to be overfetched in left, right, top
+	 * and bottom directions from source image for scaling.
+	 */
+	int32_t left_ftch[DPU_MAX_PLANES];
+	int32_t right_ftch[DPU_MAX_PLANES];
+	int32_t top_ftch[DPU_MAX_PLANES];
+	int32_t btm_ftch[DPU_MAX_PLANES];
+	/*
+	 * Number of pixels needs to be repeated in left, right, top and
+	 * bottom directions for scaling.
+	 */
+	int32_t left_rpt[DPU_MAX_PLANES];
+	int32_t right_rpt[DPU_MAX_PLANES];
+	int32_t top_rpt[DPU_MAX_PLANES];
+	int32_t btm_rpt[DPU_MAX_PLANES];
+
+};
+
+/**
+ * struct dpu_drm_de_v1 - version 1 of detail enhancer structure
+ * @enable:         Enables/disables detail enhancer
+ * @sharpen_level1: Sharpening strength for noise
+ * @sharpen_level2: Sharpening strength for context
+ * @clip:           Clip coefficient
+ * @limit:          Detail enhancer limit factor
+ * @thr_quiet:      Quite zone threshold
+ * @thr_dieout:     Die-out zone threshold
+ * @thr_low:        Linear zone left threshold
+ * @thr_high:       Linear zone right threshold
+ * @prec_shift:     Detail enhancer precision
+ * @adjust_a:       Mapping curves A coefficients
+ * @adjust_b:       Mapping curves B coefficients
+ * @adjust_c:       Mapping curves C coefficients
+ */
+struct dpu_drm_de_v1 {
+	uint32_t enable;
+	int16_t sharpen_level1;
+	int16_t sharpen_level2;
+	uint16_t clip;
+	uint16_t limit;
+	uint16_t thr_quiet;
+	uint16_t thr_dieout;
+	uint16_t thr_low;
+	uint16_t thr_high;
+	uint16_t prec_shift;
+	int16_t adjust_a[DPU_MAX_DE_CURVES];
+	int16_t adjust_b[DPU_MAX_DE_CURVES];
+	int16_t adjust_c[DPU_MAX_DE_CURVES];
+};
+
+/**
+ * struct dpu_drm_scaler_v2 - version 2 of struct dpu_drm_scaler
+ * @enable:            Scaler enable
+ * @dir_en:            Detail enhancer enable
+ * @pe:                Pixel extension settings
+ * @horz_decimate:     Horizontal decimation factor
+ * @vert_decimate:     Vertical decimation factor
+ * @init_phase_x:      Initial scaler phase values for x
+ * @phase_step_x:      Phase step values for x
+ * @init_phase_y:      Initial scaler phase values for y
+ * @phase_step_y:      Phase step values for y
+ * @preload_x:         Horizontal preload value
+ * @preload_y:         Vertical preload value
+ * @src_width:         Source width
+ * @src_height:        Source height
+ * @dst_width:         Destination width
+ * @dst_height:        Destination height
+ * @y_rgb_filter_cfg:  Y/RGB plane filter configuration
+ * @uv_filter_cfg:     UV plane filter configuration
+ * @alpha_filter_cfg:  Alpha filter configuration
+ * @blend_cfg:         Selection of blend coefficients
+ * @lut_flag:          LUT configuration flags
+ * @dir_lut_idx:       2d 4x4 LUT index
+ * @y_rgb_cir_lut_idx: Y/RGB circular LUT index
+ * @uv_cir_lut_idx:    UV circular LUT index
+ * @y_rgb_sep_lut_idx: Y/RGB separable LUT index
+ * @uv_sep_lut_idx:    UV separable LUT index
+ * @de:                Detail enhancer settings
+ */
+struct dpu_drm_scaler_v2 {
+	/*
+	 * General definitions
+	 */
+	uint32_t enable;
+	uint32_t dir_en;
+
+	/*
+	 * Pix ext settings
+	 */
+	struct dpu_drm_pix_ext_v1 pe;
+
+	/*
+	 * Decimation settings
+	 */
+	uint32_t horz_decimate;
+	uint32_t vert_decimate;
+
+	/*
+	 * Phase settings
+	 */
+	int32_t init_phase_x[DPU_MAX_PLANES];
+	int32_t phase_step_x[DPU_MAX_PLANES];
+	int32_t init_phase_y[DPU_MAX_PLANES];
+	int32_t phase_step_y[DPU_MAX_PLANES];
+
+	uint32_t preload_x[DPU_MAX_PLANES];
+	uint32_t preload_y[DPU_MAX_PLANES];
+	uint32_t src_width[DPU_MAX_PLANES];
+	uint32_t src_height[DPU_MAX_PLANES];
+
+	uint32_t dst_width;
+	uint32_t dst_height;
+
+	uint32_t y_rgb_filter_cfg;
+	uint32_t uv_filter_cfg;
+	uint32_t alpha_filter_cfg;
+	uint32_t blend_cfg;
+
+	uint32_t lut_flag;
+	uint32_t dir_lut_idx;
+
+	/* for Y(RGB) and UV planes*/
+	uint32_t y_rgb_cir_lut_idx;
+	uint32_t uv_cir_lut_idx;
+	uint32_t y_rgb_sep_lut_idx;
+	uint32_t uv_sep_lut_idx;
+
+	/*
+	 * Detail enhancer settings
+	 */
+	struct dpu_drm_de_v1 de;
+};
+
+/**
+ * struct dpu_hw_cdp_cfg : CDP configuration
+ * @enable: true to enable CDP
+ * @ubwc_meta_enable: true to enable ubwc metadata preload
+ * @tile_amortize_enable: true to enable amortization control for tile format
+ * @preload_ahead: number of request to preload ahead
+ *	DPU_*_CDP_PRELOAD_AHEAD_32,
+ *	DPU_*_CDP_PRELOAD_AHEAD_64
+ */
+struct dpu_hw_cdp_cfg {
+	bool enable;
+	bool ubwc_meta_enable;
+	bool tile_amortize_enable;
+	u32 preload_ahead;
+};
+
+u32 *dpu_hw_util_get_log_mask_ptr(void);
+
+void dpu_reg_write(struct dpu_hw_blk_reg_map *c,
+		u32 reg_off,
+		u32 val,
+		const char *name);
+int dpu_reg_read(struct dpu_hw_blk_reg_map *c, u32 reg_off);
+
+#define DPU_REG_WRITE(c, off, val) dpu_reg_write(c, off, val, #off)
+#define DPU_REG_READ(c, off) dpu_reg_read(c, off)
+
+void *dpu_hw_util_get_dir(void);
+
+void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg,
+		u32 scaler_offset, u32 scaler_version,
+		const struct dpu_format *format);
+
+u32 dpu_hw_get_scaler3_ver(struct dpu_hw_blk_reg_map *c,
+		u32 scaler_offset);
+
+void dpu_hw_csc_setup(struct dpu_hw_blk_reg_map  *c,
+		u32 csc_reg_off,
+		const struct dpu_csc_cfg *data, bool csc10);
+
+u64 _dpu_hw_get_qos_lut(const struct dpu_qos_lut_tbl *tbl,
+		u32 total_fl);
+
+void dpu_hw_setup_misr(struct dpu_hw_blk_reg_map *c,
+		u32 misr_ctrl_offset, u8 input_sel);
+
+int dpu_hw_collect_misr(struct dpu_hw_blk_reg_map *c,
+		u32 misr_ctrl_offset,
+		u32 misr_signature_offset,
+		u32 *misr_value);
+
+#endif /* _DPU_HW_UTIL_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
new file mode 100644
index 000000000..16c56e240
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
@@ -0,0 +1,264 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_vbif.h"
+
+#define VBIF_VERSION			0x0000
+#define VBIF_CLK_FORCE_CTRL0		0x0008
+#define VBIF_CLK_FORCE_CTRL1		0x000C
+#define VBIF_QOS_REMAP_00		0x0020
+#define VBIF_QOS_REMAP_01		0x0024
+#define VBIF_QOS_REMAP_10		0x0028
+#define VBIF_QOS_REMAP_11		0x002C
+#define VBIF_WRITE_GATHER_EN		0x00AC
+#define VBIF_IN_RD_LIM_CONF0		0x00B0
+#define VBIF_IN_RD_LIM_CONF1		0x00B4
+#define VBIF_IN_RD_LIM_CONF2		0x00B8
+#define VBIF_IN_WR_LIM_CONF0		0x00C0
+#define VBIF_IN_WR_LIM_CONF1		0x00C4
+#define VBIF_IN_WR_LIM_CONF2		0x00C8
+#define VBIF_OUT_RD_LIM_CONF0		0x00D0
+#define VBIF_OUT_WR_LIM_CONF0		0x00D4
+#define VBIF_OUT_AXI_AMEMTYPE_CONF0	0x0160
+#define VBIF_OUT_AXI_AMEMTYPE_CONF1	0x0164
+#define VBIF_XIN_PND_ERR		0x0190
+#define VBIF_XIN_SRC_ERR		0x0194
+#define VBIF_XIN_CLR_ERR		0x019C
+#define VBIF_XIN_HALT_CTRL0		0x0200
+#define VBIF_XIN_HALT_CTRL1		0x0204
+#define VBIF_XINL_QOS_RP_REMAP_000	0x0550
+#define VBIF_XINL_QOS_LVL_REMAP_000(vbif)	(VBIF_XINL_QOS_RP_REMAP_000 + (vbif)->cap->qos_rp_remap_size)
+
+static void dpu_hw_clear_errors(struct dpu_hw_vbif *vbif,
+		u32 *pnd_errors, u32 *src_errors)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 pnd, src;
+
+	if (!vbif)
+		return;
+	c = &vbif->hw;
+	pnd = DPU_REG_READ(c, VBIF_XIN_PND_ERR);
+	src = DPU_REG_READ(c, VBIF_XIN_SRC_ERR);
+
+	if (pnd_errors)
+		*pnd_errors = pnd;
+	if (src_errors)
+		*src_errors = src;
+
+	DPU_REG_WRITE(c, VBIF_XIN_CLR_ERR, pnd | src);
+}
+
+static void dpu_hw_set_mem_type(struct dpu_hw_vbif *vbif,
+		u32 xin_id, u32 value)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_off;
+	u32 bit_off;
+	u32 reg_val;
+
+	/*
+	 * Assume 4 bits per bit field, 8 fields per 32-bit register so
+	 * 16 bit fields maximum across two registers
+	 */
+	if (!vbif || xin_id >= MAX_XIN_COUNT || xin_id >= 16)
+		return;
+
+	c = &vbif->hw;
+
+	if (xin_id >= 8) {
+		xin_id -= 8;
+		reg_off = VBIF_OUT_AXI_AMEMTYPE_CONF1;
+	} else {
+		reg_off = VBIF_OUT_AXI_AMEMTYPE_CONF0;
+	}
+	bit_off = (xin_id & 0x7) * 4;
+	reg_val = DPU_REG_READ(c, reg_off);
+	reg_val &= ~(0x7 << bit_off);
+	reg_val |= (value & 0x7) << bit_off;
+	DPU_REG_WRITE(c, reg_off, reg_val);
+}
+
+static void dpu_hw_set_limit_conf(struct dpu_hw_vbif *vbif,
+		u32 xin_id, bool rd, u32 limit)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+	u32 reg_off;
+	u32 bit_off;
+
+	if (rd)
+		reg_off = VBIF_IN_RD_LIM_CONF0;
+	else
+		reg_off = VBIF_IN_WR_LIM_CONF0;
+
+	reg_off += (xin_id / 4) * 4;
+	bit_off = (xin_id % 4) * 8;
+	reg_val = DPU_REG_READ(c, reg_off);
+	reg_val &= ~(0xFF << bit_off);
+	reg_val |= (limit) << bit_off;
+	DPU_REG_WRITE(c, reg_off, reg_val);
+}
+
+static u32 dpu_hw_get_limit_conf(struct dpu_hw_vbif *vbif,
+		u32 xin_id, bool rd)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+	u32 reg_off;
+	u32 bit_off;
+	u32 limit;
+
+	if (rd)
+		reg_off = VBIF_IN_RD_LIM_CONF0;
+	else
+		reg_off = VBIF_IN_WR_LIM_CONF0;
+
+	reg_off += (xin_id / 4) * 4;
+	bit_off = (xin_id % 4) * 8;
+	reg_val = DPU_REG_READ(c, reg_off);
+	limit = (reg_val >> bit_off) & 0xFF;
+
+	return limit;
+}
+
+static void dpu_hw_set_halt_ctrl(struct dpu_hw_vbif *vbif,
+		u32 xin_id, bool enable)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+
+	reg_val = DPU_REG_READ(c, VBIF_XIN_HALT_CTRL0);
+
+	if (enable)
+		reg_val |= BIT(xin_id);
+	else
+		reg_val &= ~BIT(xin_id);
+
+	DPU_REG_WRITE(c, VBIF_XIN_HALT_CTRL0, reg_val);
+}
+
+static bool dpu_hw_get_halt_ctrl(struct dpu_hw_vbif *vbif,
+		u32 xin_id)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+
+	reg_val = DPU_REG_READ(c, VBIF_XIN_HALT_CTRL1);
+
+	return (reg_val & BIT(xin_id)) ? true : false;
+}
+
+static void dpu_hw_set_qos_remap(struct dpu_hw_vbif *vbif,
+		u32 xin_id, u32 level, u32 remap_level)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_lvl, reg_val, reg_val_lvl, mask, reg_high, reg_shift;
+
+	if (!vbif)
+		return;
+
+	c = &vbif->hw;
+
+	reg_lvl = VBIF_XINL_QOS_LVL_REMAP_000(vbif);
+	reg_high = ((xin_id & 0x8) >> 3) * 4 + (level * 8);
+	reg_shift = (xin_id & 0x7) * 4;
+
+	reg_val = DPU_REG_READ(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high);
+	reg_val_lvl = DPU_REG_READ(c, reg_lvl + reg_high);
+
+	mask = 0x7 << reg_shift;
+
+	reg_val &= ~mask;
+	reg_val |= (remap_level << reg_shift) & mask;
+
+	reg_val_lvl &= ~mask;
+	reg_val_lvl |= (remap_level << reg_shift) & mask;
+
+	DPU_REG_WRITE(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high, reg_val);
+	DPU_REG_WRITE(c, reg_lvl + reg_high, reg_val_lvl);
+}
+
+static void dpu_hw_set_write_gather_en(struct dpu_hw_vbif *vbif, u32 xin_id)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_val;
+
+	if (!vbif || xin_id >= MAX_XIN_COUNT)
+		return;
+
+	c = &vbif->hw;
+
+	reg_val = DPU_REG_READ(c, VBIF_WRITE_GATHER_EN);
+	reg_val |= BIT(xin_id);
+	DPU_REG_WRITE(c, VBIF_WRITE_GATHER_EN, reg_val);
+}
+
+static void _setup_vbif_ops(struct dpu_hw_vbif_ops *ops,
+		unsigned long cap)
+{
+	ops->set_limit_conf = dpu_hw_set_limit_conf;
+	ops->get_limit_conf = dpu_hw_get_limit_conf;
+	ops->set_halt_ctrl = dpu_hw_set_halt_ctrl;
+	ops->get_halt_ctrl = dpu_hw_get_halt_ctrl;
+	if (test_bit(DPU_VBIF_QOS_REMAP, &cap))
+		ops->set_qos_remap = dpu_hw_set_qos_remap;
+	ops->set_mem_type = dpu_hw_set_mem_type;
+	ops->clear_errors = dpu_hw_clear_errors;
+	ops->set_write_gather_en = dpu_hw_set_write_gather_en;
+}
+
+static const struct dpu_vbif_cfg *_top_offset(enum dpu_vbif vbif,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->vbif_count; i++) {
+		if (vbif == m->vbif[i].id) {
+			b->blk_addr = addr + m->vbif[i].base;
+			b->log_mask = DPU_DBG_MASK_VBIF;
+			return &m->vbif[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+struct dpu_hw_vbif *dpu_hw_vbif_init(enum dpu_vbif idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_vbif *c;
+	const struct dpu_vbif_cfg *cfg;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _top_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Assign ops
+	 */
+	c->idx = idx;
+	c->cap = cfg;
+	_setup_vbif_ops(&c->ops, c->cap->features);
+
+	/* no need to register sub-range in dpu dbg, dump entire vbif io base */
+
+	return c;
+}
+
+void dpu_hw_vbif_destroy(struct dpu_hw_vbif *vbif)
+{
+	kfree(vbif);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h
new file mode 100644
index 000000000..6417aa28d
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HW_VBIF_H
+#define _DPU_HW_VBIF_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+struct dpu_hw_vbif;
+
+/**
+ * struct dpu_hw_vbif_ops : Interface to the VBIF hardware driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_vbif_ops {
+	/**
+	 * set_limit_conf - set transaction limit config
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @rd: true for read limit; false for write limit
+	 * @limit: outstanding transaction limit
+	 */
+	void (*set_limit_conf)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, bool rd, u32 limit);
+
+	/**
+	 * get_limit_conf - get transaction limit config
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @rd: true for read limit; false for write limit
+	 * @return: outstanding transaction limit
+	 */
+	u32 (*get_limit_conf)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, bool rd);
+
+	/**
+	 * set_halt_ctrl - set halt control
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @enable: halt control enable
+	 */
+	void (*set_halt_ctrl)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, bool enable);
+
+	/**
+	 * get_halt_ctrl - get halt control
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @return: halt control enable
+	 */
+	bool (*get_halt_ctrl)(struct dpu_hw_vbif *vbif,
+			u32 xin_id);
+
+	/**
+	 * set_qos_remap - set QoS priority remap
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @level: priority level
+	 * @remap_level: remapped level
+	 */
+	void (*set_qos_remap)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, u32 level, u32 remap_level);
+
+	/**
+	 * set_mem_type - set memory type
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @value: memory type value
+	 */
+	void (*set_mem_type)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, u32 value);
+
+	/**
+	 * clear_errors - clear any vbif errors
+	 *	This function clears any detected pending/source errors
+	 *	on the VBIF interface, and optionally returns the detected
+	 *	error mask(s).
+	 * @vbif: vbif context driver
+	 * @pnd_errors: pointer to pending error reporting variable
+	 * @src_errors: pointer to source error reporting variable
+	 */
+	void (*clear_errors)(struct dpu_hw_vbif *vbif,
+		u32 *pnd_errors, u32 *src_errors);
+
+	/**
+	 * set_write_gather_en - set write_gather enable
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 */
+	void (*set_write_gather_en)(struct dpu_hw_vbif *vbif, u32 xin_id);
+};
+
+struct dpu_hw_vbif {
+	/* base */
+	struct dpu_hw_blk_reg_map hw;
+
+	/* vbif */
+	enum dpu_vbif idx;
+	const struct dpu_vbif_cfg *cap;
+
+	/* ops */
+	struct dpu_hw_vbif_ops ops;
+};
+
+/**
+ * dpu_hw_vbif_init - initializes the vbif driver for the passed interface idx
+ * @idx:  Interface index for which driver object is required
+ * @addr: Mapped register io address of MDSS
+ * @m:    Pointer to mdss catalog data
+ */
+struct dpu_hw_vbif *dpu_hw_vbif_init(enum dpu_vbif idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+void dpu_hw_vbif_destroy(struct dpu_hw_vbif *vbif);
+
+#endif /*_DPU_HW_VBIF_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c
new file mode 100644
index 000000000..a3e413d27
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c
@@ -0,0 +1,277 @@
+// SPDX-License-Identifier: GPL-2.0-only
+ /*
+  * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved
+  */
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_wb.h"
+#include "dpu_formats.h"
+#include "dpu_kms.h"
+
+#define WB_DST_FORMAT                         0x000
+#define WB_DST_OP_MODE                        0x004
+#define WB_DST_PACK_PATTERN                   0x008
+#define WB_DST0_ADDR                          0x00C
+#define WB_DST1_ADDR                          0x010
+#define WB_DST2_ADDR                          0x014
+#define WB_DST3_ADDR                          0x018
+#define WB_DST_YSTRIDE0                       0x01C
+#define WB_DST_YSTRIDE1                       0x020
+#define WB_DST_YSTRIDE1                       0x020
+#define WB_DST_DITHER_BITDEPTH                0x024
+#define WB_DST_MATRIX_ROW0                    0x030
+#define WB_DST_MATRIX_ROW1                    0x034
+#define WB_DST_MATRIX_ROW2                    0x038
+#define WB_DST_MATRIX_ROW3                    0x03C
+#define WB_DST_WRITE_CONFIG                   0x048
+#define WB_ROTATION_DNSCALER                  0x050
+#define WB_ROTATOR_PIPE_DOWNSCALER            0x054
+#define WB_N16_INIT_PHASE_X_C03               0x060
+#define WB_N16_INIT_PHASE_X_C12               0x064
+#define WB_N16_INIT_PHASE_Y_C03               0x068
+#define WB_N16_INIT_PHASE_Y_C12               0x06C
+#define WB_OUT_SIZE                           0x074
+#define WB_ALPHA_X_VALUE                      0x078
+#define WB_DANGER_LUT                         0x084
+#define WB_SAFE_LUT                           0x088
+#define WB_QOS_CTRL                           0x090
+#define WB_CREQ_LUT_0                         0x098
+#define WB_CREQ_LUT_1                         0x09C
+#define WB_UBWC_STATIC_CTRL                   0x144
+#define WB_MUX                                0x150
+#define WB_CROP_CTRL                          0x154
+#define WB_CROP_OFFSET                        0x158
+#define WB_CSC_BASE                           0x260
+#define WB_DST_ADDR_SW_STATUS                 0x2B0
+#define WB_CDP_CNTL                           0x2B4
+#define WB_OUT_IMAGE_SIZE                     0x2C0
+#define WB_OUT_XY                             0x2C4
+
+/* WB_QOS_CTRL */
+#define WB_QOS_CTRL_DANGER_SAFE_EN            BIT(0)
+
+static const struct dpu_wb_cfg *_wb_offset(enum dpu_wb wb,
+		const struct dpu_mdss_cfg *m, void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->wb_count; i++) {
+		if (wb == m->wb[i].id) {
+			b->blk_addr = addr + m->wb[i].base;
+			b->log_mask = DPU_DBG_MASK_WB;
+			return &m->wb[i];
+		}
+	}
+	return ERR_PTR(-EINVAL);
+}
+
+static void dpu_hw_wb_setup_outaddress(struct dpu_hw_wb *ctx,
+		struct dpu_hw_wb_cfg *data)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	DPU_REG_WRITE(c, WB_DST0_ADDR, data->dest.plane_addr[0]);
+	DPU_REG_WRITE(c, WB_DST1_ADDR, data->dest.plane_addr[1]);
+	DPU_REG_WRITE(c, WB_DST2_ADDR, data->dest.plane_addr[2]);
+	DPU_REG_WRITE(c, WB_DST3_ADDR, data->dest.plane_addr[3]);
+}
+
+static void dpu_hw_wb_setup_format(struct dpu_hw_wb *ctx,
+		struct dpu_hw_wb_cfg *data)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	const struct dpu_format *fmt = data->dest.format;
+	u32 dst_format, pattern, ystride0, ystride1, outsize, chroma_samp;
+	u32 write_config = 0;
+	u32 opmode = 0;
+	u32 dst_addr_sw = 0;
+
+	chroma_samp = fmt->chroma_sample;
+
+	dst_format = (chroma_samp << 23) |
+		(fmt->fetch_planes << 19) |
+		(fmt->bits[C3_ALPHA] << 6) |
+		(fmt->bits[C2_R_Cr] << 4) |
+		(fmt->bits[C1_B_Cb] << 2) |
+		(fmt->bits[C0_G_Y] << 0);
+
+	if (fmt->bits[C3_ALPHA] || fmt->alpha_enable) {
+		dst_format |= BIT(8); /* DSTC3_EN */
+		if (!fmt->alpha_enable ||
+			!(ctx->caps->features & BIT(DPU_WB_PIPE_ALPHA)))
+			dst_format |= BIT(14); /* DST_ALPHA_X */
+	}
+
+	pattern = (fmt->element[3] << 24) |
+		(fmt->element[2] << 16) |
+		(fmt->element[1] << 8)  |
+		(fmt->element[0] << 0);
+
+	dst_format |= (fmt->unpack_align_msb << 18) |
+		(fmt->unpack_tight << 17) |
+		((fmt->unpack_count - 1) << 12) |
+		((fmt->bpp - 1) << 9);
+
+	ystride0 = data->dest.plane_pitch[0] |
+		(data->dest.plane_pitch[1] << 16);
+	ystride1 = data->dest.plane_pitch[2] |
+	(data->dest.plane_pitch[3] << 16);
+
+	if (drm_rect_height(&data->roi) && drm_rect_width(&data->roi))
+		outsize = (drm_rect_height(&data->roi) << 16) | drm_rect_width(&data->roi);
+	else
+		outsize = (data->dest.height << 16) | data->dest.width;
+
+	DPU_REG_WRITE(c, WB_ALPHA_X_VALUE, 0xFF);
+	DPU_REG_WRITE(c, WB_DST_FORMAT, dst_format);
+	DPU_REG_WRITE(c, WB_DST_OP_MODE, opmode);
+	DPU_REG_WRITE(c, WB_DST_PACK_PATTERN, pattern);
+	DPU_REG_WRITE(c, WB_DST_YSTRIDE0, ystride0);
+	DPU_REG_WRITE(c, WB_DST_YSTRIDE1, ystride1);
+	DPU_REG_WRITE(c, WB_OUT_SIZE, outsize);
+	DPU_REG_WRITE(c, WB_DST_WRITE_CONFIG, write_config);
+	DPU_REG_WRITE(c, WB_DST_ADDR_SW_STATUS, dst_addr_sw);
+}
+
+static void dpu_hw_wb_roi(struct dpu_hw_wb *ctx, struct dpu_hw_wb_cfg *wb)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 image_size, out_size, out_xy;
+
+	image_size = (wb->dest.height << 16) | wb->dest.width;
+	out_xy = 0;
+	out_size = (drm_rect_height(&wb->roi) << 16) | drm_rect_width(&wb->roi);
+
+	DPU_REG_WRITE(c, WB_OUT_IMAGE_SIZE, image_size);
+	DPU_REG_WRITE(c, WB_OUT_XY, out_xy);
+	DPU_REG_WRITE(c, WB_OUT_SIZE, out_size);
+}
+
+static void dpu_hw_wb_setup_qos_lut(struct dpu_hw_wb *ctx,
+		struct dpu_hw_wb_qos_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 qos_ctrl = 0;
+
+	if (!ctx || !cfg)
+		return;
+
+	DPU_REG_WRITE(c, WB_DANGER_LUT, cfg->danger_lut);
+	DPU_REG_WRITE(c, WB_SAFE_LUT, cfg->safe_lut);
+
+	/*
+	 * for chipsets not using DPU_WB_QOS_8LVL but still using DPU
+	 * driver such as msm8998, the reset value of WB_CREQ_LUT is
+	 * sufficient for writeback to work. SW doesn't need to explicitly
+	 * program a value.
+	 */
+	if (ctx->caps && test_bit(DPU_WB_QOS_8LVL, &ctx->caps->features)) {
+		DPU_REG_WRITE(c, WB_CREQ_LUT_0, cfg->creq_lut);
+		DPU_REG_WRITE(c, WB_CREQ_LUT_1, cfg->creq_lut >> 32);
+	}
+
+	if (cfg->danger_safe_en)
+		qos_ctrl |= WB_QOS_CTRL_DANGER_SAFE_EN;
+
+	DPU_REG_WRITE(c, WB_QOS_CTRL, qos_ctrl);
+}
+
+static void dpu_hw_wb_setup_cdp(struct dpu_hw_wb *ctx,
+		struct dpu_hw_cdp_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 cdp_cntl = 0;
+
+	if (!ctx || !cfg)
+		return;
+
+	c = &ctx->hw;
+
+	if (cfg->enable)
+		cdp_cntl |= BIT(0);
+	if (cfg->ubwc_meta_enable)
+		cdp_cntl |= BIT(1);
+	if (cfg->preload_ahead == DPU_WB_CDP_PRELOAD_AHEAD_64)
+		cdp_cntl |= BIT(3);
+
+	DPU_REG_WRITE(c, WB_CDP_CNTL, cdp_cntl);
+}
+
+static void dpu_hw_wb_bind_pingpong_blk(
+		struct dpu_hw_wb *ctx,
+		bool enable, const enum dpu_pingpong pp)
+{
+	struct dpu_hw_blk_reg_map *c;
+	int mux_cfg;
+
+	if (!ctx)
+		return;
+
+	c = &ctx->hw;
+
+	mux_cfg = DPU_REG_READ(c, WB_MUX);
+	mux_cfg &= ~0xf;
+
+	if (enable)
+		mux_cfg |= (pp - PINGPONG_0) & 0x7;
+	else
+		mux_cfg |= 0xf;
+
+	DPU_REG_WRITE(c, WB_MUX, mux_cfg);
+}
+
+static void _setup_wb_ops(struct dpu_hw_wb_ops *ops,
+		unsigned long features)
+{
+	ops->setup_outaddress = dpu_hw_wb_setup_outaddress;
+	ops->setup_outformat = dpu_hw_wb_setup_format;
+
+	if (test_bit(DPU_WB_XY_ROI_OFFSET, &features))
+		ops->setup_roi = dpu_hw_wb_roi;
+
+	if (test_bit(DPU_WB_QOS, &features))
+		ops->setup_qos_lut = dpu_hw_wb_setup_qos_lut;
+
+	if (test_bit(DPU_WB_CDP, &features))
+		ops->setup_cdp = dpu_hw_wb_setup_cdp;
+
+	if (test_bit(DPU_WB_INPUT_CTRL, &features))
+		ops->bind_pingpong_blk = dpu_hw_wb_bind_pingpong_blk;
+}
+
+struct dpu_hw_wb *dpu_hw_wb_init(enum dpu_wb idx,
+		void __iomem *addr, const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_wb *c;
+	const struct dpu_wb_cfg *cfg;
+
+	if (!addr || !m)
+		return ERR_PTR(-EINVAL);
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _wb_offset(idx, m, addr, &c->hw);
+	if (IS_ERR(cfg)) {
+		WARN(1, "Unable to find wb idx=%d\n", idx);
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Assign ops */
+	c->mdp = &m->mdp[0];
+	c->idx = idx;
+	c->caps = cfg;
+	_setup_wb_ops(&c->ops, c->caps->features);
+
+	return c;
+}
+
+void dpu_hw_wb_destroy(struct dpu_hw_wb *hw_wb)
+{
+	kfree(hw_wb);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.h
new file mode 100644
index 000000000..3ff5a4854
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved
+ */
+
+#ifndef _DPU_HW_WB_H
+#define _DPU_HW_WB_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_top.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_pingpong.h"
+
+struct dpu_hw_wb;
+
+struct dpu_hw_wb_cfg {
+	struct dpu_hw_fmt_layout dest;
+	enum dpu_intf_mode intf_mode;
+	struct drm_rect roi;
+	struct drm_rect crop;
+};
+
+/**
+ * enum CDP preload ahead address size
+ */
+enum {
+	DPU_WB_CDP_PRELOAD_AHEAD_32,
+	DPU_WB_CDP_PRELOAD_AHEAD_64
+};
+
+/**
+ * struct dpu_hw_wb_qos_cfg : Writeback pipe QoS configuration
+ * @danger_lut: LUT for generate danger level based on fill level
+ * @safe_lut: LUT for generate safe level based on fill level
+ * @creq_lut: LUT for generate creq level based on fill level
+ * @danger_safe_en: enable danger safe generation
+ */
+struct dpu_hw_wb_qos_cfg {
+	u32 danger_lut;
+	u32 safe_lut;
+	u64 creq_lut;
+	bool danger_safe_en;
+};
+
+/**
+ *
+ * struct dpu_hw_wb_ops : Interface to the wb hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ *  @setup_outaddress: setup output address from the writeback job
+ *  @setup_outformat: setup output format of writeback block from writeback job
+ *  @setup_qos_lut:   setup qos LUT for writeback block based on input
+ *  @setup_cdp:       setup chroma down prefetch block for writeback block
+ *  @bind_pingpong_blk: enable/disable the connection with ping-pong block
+ */
+struct dpu_hw_wb_ops {
+	void (*setup_outaddress)(struct dpu_hw_wb *ctx,
+			struct dpu_hw_wb_cfg *wb);
+
+	void (*setup_outformat)(struct dpu_hw_wb *ctx,
+			struct dpu_hw_wb_cfg *wb);
+
+	void (*setup_roi)(struct dpu_hw_wb *ctx,
+			struct dpu_hw_wb_cfg *wb);
+
+	void (*setup_qos_lut)(struct dpu_hw_wb *ctx,
+			struct dpu_hw_wb_qos_cfg *cfg);
+
+	void (*setup_cdp)(struct dpu_hw_wb *ctx,
+			struct dpu_hw_cdp_cfg *cfg);
+
+	void (*bind_pingpong_blk)(struct dpu_hw_wb *ctx,
+			bool enable, const enum dpu_pingpong pp);
+};
+
+/**
+ * struct dpu_hw_wb : WB driver object
+ * @hw: block hardware details
+ * @mdp: pointer to associated mdp portion of the catalog
+ * @idx: hardware index number within type
+ * @wb_hw_caps: hardware capabilities
+ * @ops: function pointers
+ * @hw_mdp: MDP top level hardware block
+ */
+struct dpu_hw_wb {
+	struct dpu_hw_blk_reg_map hw;
+	const struct dpu_mdp_cfg *mdp;
+
+	/* wb path */
+	int idx;
+	const struct dpu_wb_cfg *caps;
+
+	/* ops */
+	struct dpu_hw_wb_ops ops;
+
+	struct dpu_hw_mdp *hw_mdp;
+};
+
+/**
+ * dpu_hw_wb_init(): Initializes and return writeback hw driver object.
+ * @idx:  wb_path index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_wb *dpu_hw_wb_init(enum dpu_wb idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_wb_destroy(): Destroy writeback hw driver object.
+ * @hw_wb:  Pointer to writeback hw driver object
+ */
+void dpu_hw_wb_destroy(struct dpu_hw_wb *hw_wb);
+
+#endif /*_DPU_HW_WB_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h
new file mode 100644
index 000000000..93081e82c
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DPU_HWIO_H
+#define _DPU_HWIO_H
+
+#include "dpu_hw_util.h"
+
+/**
+ * MDP TOP block Register and bit fields and defines
+ */
+#define DISP_INTF_SEL                   0x004
+#define INTR_EN                         0x010
+#define INTR_STATUS                     0x014
+#define INTR_CLEAR                      0x018
+#define INTR2_EN                        0x008
+#define INTR2_STATUS                    0x00c
+#define INTR2_CLEAR                     0x02c
+#define HIST_INTR_EN                    0x01c
+#define HIST_INTR_STATUS                0x020
+#define HIST_INTR_CLEAR                 0x024
+#define SPLIT_DISPLAY_EN                0x2F4
+#define SPLIT_DISPLAY_UPPER_PIPE_CTRL   0x2F8
+#define DSPP_IGC_COLOR0_RAM_LUTN        0x300
+#define DSPP_IGC_COLOR1_RAM_LUTN        0x304
+#define DSPP_IGC_COLOR2_RAM_LUTN        0x308
+#define HW_EVENTS_CTL                   0x37C
+#define CLK_CTRL3                       0x3A8
+#define CLK_STATUS3                     0x3AC
+#define CLK_CTRL4                       0x3B0
+#define CLK_STATUS4                     0x3B4
+#define CLK_CTRL5                       0x3B8
+#define CLK_STATUS5                     0x3BC
+#define CLK_CTRL7                       0x3D0
+#define CLK_STATUS7                     0x3D4
+#define SPLIT_DISPLAY_LOWER_PIPE_CTRL   0x3F0
+#define SPLIT_DISPLAY_TE_LINE_INTERVAL  0x3F4
+#define INTF_SW_RESET_MASK              0x3FC
+#define HDMI_DP_CORE_SELECT             0x408
+#define MDP_OUT_CTL_0                   0x410
+#define MDP_VSYNC_SEL                   0x414
+#define DCE_SEL                         0x450
+
+#endif /*_DPU_HWIO_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
new file mode 100644
index 000000000..b7901b666
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -0,0 +1,1337 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 Red Hat
+ * Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ *
+ * Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/dma-buf.h>
+#include <linux/of_irq.h>
+#include <linux/pm_opp.h>
+
+#include <drm/drm_crtc.h>
+#include <drm/drm_file.h>
+#include <drm/drm_framebuffer.h>
+#include <drm/drm_vblank.h>
+#include <drm/drm_writeback.h>
+
+#include "msm_drv.h"
+#include "msm_mmu.h"
+#include "msm_gem.h"
+#include "disp/msm_disp_snapshot.h"
+
+#include "dpu_core_irq.h"
+#include "dpu_crtc.h"
+#include "dpu_encoder.h"
+#include "dpu_formats.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_kms.h"
+#include "dpu_plane.h"
+#include "dpu_vbif.h"
+#include "dpu_writeback.h"
+
+#define CREATE_TRACE_POINTS
+#include "dpu_trace.h"
+
+/*
+ * To enable overall DRM driver logging
+ * # echo 0x2 > /sys/module/drm/parameters/debug
+ *
+ * To enable DRM driver h/w logging
+ * # echo <mask> > /sys/kernel/debug/dri/0/debug/hw_log_mask
+ *
+ * See dpu_hw_mdss.h for h/w logging mask definitions (search for DPU_DBG_MASK_)
+ */
+#define DPU_DEBUGFS_DIR "msm_dpu"
+#define DPU_DEBUGFS_HWMASKNAME "hw_log_mask"
+
+static int dpu_kms_hw_init(struct msm_kms *kms);
+static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms);
+
+#ifdef CONFIG_DEBUG_FS
+static int _dpu_danger_signal_status(struct seq_file *s,
+		bool danger_status)
+{
+	struct dpu_kms *kms = (struct dpu_kms *)s->private;
+	struct dpu_danger_safe_status status;
+	int i;
+
+	if (!kms->hw_mdp) {
+		DPU_ERROR("invalid arg(s)\n");
+		return 0;
+	}
+
+	memset(&status, 0, sizeof(struct dpu_danger_safe_status));
+
+	pm_runtime_get_sync(&kms->pdev->dev);
+	if (danger_status) {
+		seq_puts(s, "\nDanger signal status:\n");
+		if (kms->hw_mdp->ops.get_danger_status)
+			kms->hw_mdp->ops.get_danger_status(kms->hw_mdp,
+					&status);
+	} else {
+		seq_puts(s, "\nSafe signal status:\n");
+		if (kms->hw_mdp->ops.get_safe_status)
+			kms->hw_mdp->ops.get_safe_status(kms->hw_mdp,
+					&status);
+	}
+	pm_runtime_put_sync(&kms->pdev->dev);
+
+	seq_printf(s, "MDP     :  0x%x\n", status.mdp);
+
+	for (i = SSPP_VIG0; i < SSPP_MAX; i++)
+		seq_printf(s, "SSPP%d   :  0x%x  \n", i - SSPP_VIG0,
+				status.sspp[i]);
+	seq_puts(s, "\n");
+
+	return 0;
+}
+
+static int dpu_debugfs_danger_stats_show(struct seq_file *s, void *v)
+{
+	return _dpu_danger_signal_status(s, true);
+}
+DEFINE_SHOW_ATTRIBUTE(dpu_debugfs_danger_stats);
+
+static int dpu_debugfs_safe_stats_show(struct seq_file *s, void *v)
+{
+	return _dpu_danger_signal_status(s, false);
+}
+DEFINE_SHOW_ATTRIBUTE(dpu_debugfs_safe_stats);
+
+static ssize_t _dpu_plane_danger_read(struct file *file,
+			char __user *buff, size_t count, loff_t *ppos)
+{
+	struct dpu_kms *kms = file->private_data;
+	int len;
+	char buf[40];
+
+	len = scnprintf(buf, sizeof(buf), "%d\n", !kms->has_danger_ctrl);
+
+	return simple_read_from_buffer(buff, count, ppos, buf, len);
+}
+
+static void _dpu_plane_set_danger_state(struct dpu_kms *kms, bool enable)
+{
+	struct drm_plane *plane;
+
+	drm_for_each_plane(plane, kms->dev) {
+		if (plane->fb && plane->state) {
+			dpu_plane_danger_signal_ctrl(plane, enable);
+			DPU_DEBUG("plane:%d img:%dx%d ",
+				plane->base.id, plane->fb->width,
+				plane->fb->height);
+			DPU_DEBUG("src[%d,%d,%d,%d] dst[%d,%d,%d,%d]\n",
+				plane->state->src_x >> 16,
+				plane->state->src_y >> 16,
+				plane->state->src_w >> 16,
+				plane->state->src_h >> 16,
+				plane->state->crtc_x, plane->state->crtc_y,
+				plane->state->crtc_w, plane->state->crtc_h);
+		} else {
+			DPU_DEBUG("Inactive plane:%d\n", plane->base.id);
+		}
+	}
+}
+
+static ssize_t _dpu_plane_danger_write(struct file *file,
+		    const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_kms *kms = file->private_data;
+	int disable_panic;
+	int ret;
+
+	ret = kstrtouint_from_user(user_buf, count, 0, &disable_panic);
+	if (ret)
+		return ret;
+
+	if (disable_panic) {
+		/* Disable panic signal for all active pipes */
+		DPU_DEBUG("Disabling danger:\n");
+		_dpu_plane_set_danger_state(kms, false);
+		kms->has_danger_ctrl = false;
+	} else {
+		/* Enable panic signal for all active pipes */
+		DPU_DEBUG("Enabling danger:\n");
+		kms->has_danger_ctrl = true;
+		_dpu_plane_set_danger_state(kms, true);
+	}
+
+	return count;
+}
+
+static const struct file_operations dpu_plane_danger_enable = {
+	.open = simple_open,
+	.read = _dpu_plane_danger_read,
+	.write = _dpu_plane_danger_write,
+};
+
+static void dpu_debugfs_danger_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent)
+{
+	struct dentry *entry = debugfs_create_dir("danger", parent);
+
+	debugfs_create_file("danger_status", 0600, entry,
+			dpu_kms, &dpu_debugfs_danger_stats_fops);
+	debugfs_create_file("safe_status", 0600, entry,
+			dpu_kms, &dpu_debugfs_safe_stats_fops);
+	debugfs_create_file("disable_danger", 0600, entry,
+			dpu_kms, &dpu_plane_danger_enable);
+
+}
+
+/*
+ * Companion structure for dpu_debugfs_create_regset32.
+ */
+struct dpu_debugfs_regset32 {
+	uint32_t offset;
+	uint32_t blk_len;
+	struct dpu_kms *dpu_kms;
+};
+
+static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data)
+{
+	struct dpu_debugfs_regset32 *regset = s->private;
+	struct dpu_kms *dpu_kms = regset->dpu_kms;
+	void __iomem *base;
+	uint32_t i, addr;
+
+	if (!dpu_kms->mmio)
+		return 0;
+
+	base = dpu_kms->mmio + regset->offset;
+
+	/* insert padding spaces, if needed */
+	if (regset->offset & 0xF) {
+		seq_printf(s, "[%x]", regset->offset & ~0xF);
+		for (i = 0; i < (regset->offset & 0xF); i += 4)
+			seq_puts(s, "         ");
+	}
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+	/* main register output */
+	for (i = 0; i < regset->blk_len; i += 4) {
+		addr = regset->offset + i;
+		if ((addr & 0xF) == 0x0)
+			seq_printf(s, i ? "\n[%x]" : "[%x]", addr);
+		seq_printf(s, " %08x", readl_relaxed(base + i));
+	}
+	seq_puts(s, "\n");
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+}
+
+static int dpu_debugfs_open_regset32(struct inode *inode,
+		struct file *file)
+{
+	return single_open(file, _dpu_debugfs_show_regset32, inode->i_private);
+}
+
+static const struct file_operations dpu_fops_regset32 = {
+	.open =		dpu_debugfs_open_regset32,
+	.read =		seq_read,
+	.llseek =	seq_lseek,
+	.release =	single_release,
+};
+
+void dpu_debugfs_create_regset32(const char *name, umode_t mode,
+		void *parent,
+		uint32_t offset, uint32_t length, struct dpu_kms *dpu_kms)
+{
+	struct dpu_debugfs_regset32 *regset;
+
+	if (WARN_ON(!name || !dpu_kms || !length))
+		return;
+
+	regset = devm_kzalloc(&dpu_kms->pdev->dev, sizeof(*regset), GFP_KERNEL);
+	if (!regset)
+		return;
+
+	/* make sure offset is a multiple of 4 */
+	regset->offset = round_down(offset, 4);
+	regset->blk_len = length;
+	regset->dpu_kms = dpu_kms;
+
+	debugfs_create_file(name, mode, parent, regset, &dpu_fops_regset32);
+}
+
+static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	void *p = dpu_hw_util_get_log_mask_ptr();
+	struct dentry *entry;
+	struct drm_device *dev;
+	struct msm_drm_private *priv;
+	int i;
+
+	if (!p)
+		return -EINVAL;
+
+	/* Only create a set of debugfs for the primary node, ignore render nodes */
+	if (minor->type != DRM_MINOR_PRIMARY)
+		return 0;
+
+	dev = dpu_kms->dev;
+	priv = dev->dev_private;
+
+	entry = debugfs_create_dir("debug", minor->debugfs_root);
+
+	debugfs_create_x32(DPU_DEBUGFS_HWMASKNAME, 0600, entry, p);
+
+	dpu_debugfs_danger_init(dpu_kms, entry);
+	dpu_debugfs_vbif_init(dpu_kms, entry);
+	dpu_debugfs_core_irq_init(dpu_kms, entry);
+	dpu_debugfs_sspp_init(dpu_kms, entry);
+
+	for (i = 0; i < ARRAY_SIZE(priv->dp); i++) {
+		if (priv->dp[i])
+			msm_dp_debugfs_init(priv->dp[i], minor);
+	}
+
+	return dpu_core_perf_debugfs_init(dpu_kms, entry);
+}
+#endif
+
+/* Global/shared object state funcs */
+
+/*
+ * This is a helper that returns the private state currently in operation.
+ * Note that this would return the "old_state" if called in the atomic check
+ * path, and the "new_state" after the atomic swap has been done.
+ */
+struct dpu_global_state *
+dpu_kms_get_existing_global_state(struct dpu_kms *dpu_kms)
+{
+	return to_dpu_global_state(dpu_kms->global_state.state);
+}
+
+/*
+ * This acquires the modeset lock set aside for global state, creates
+ * a new duplicated private object state.
+ */
+struct dpu_global_state *dpu_kms_get_global_state(struct drm_atomic_state *s)
+{
+	struct msm_drm_private *priv = s->dev->dev_private;
+	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
+	struct drm_private_state *priv_state;
+	int ret;
+
+	ret = drm_modeset_lock(&dpu_kms->global_state_lock, s->acquire_ctx);
+	if (ret)
+		return ERR_PTR(ret);
+
+	priv_state = drm_atomic_get_private_obj_state(s,
+						&dpu_kms->global_state);
+	if (IS_ERR(priv_state))
+		return ERR_CAST(priv_state);
+
+	return to_dpu_global_state(priv_state);
+}
+
+static struct drm_private_state *
+dpu_kms_global_duplicate_state(struct drm_private_obj *obj)
+{
+	struct dpu_global_state *state;
+
+	state = kmemdup(obj->state, sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return NULL;
+
+	__drm_atomic_helper_private_obj_duplicate_state(obj, &state->base);
+
+	return &state->base;
+}
+
+static void dpu_kms_global_destroy_state(struct drm_private_obj *obj,
+				      struct drm_private_state *state)
+{
+	struct dpu_global_state *dpu_state = to_dpu_global_state(state);
+
+	kfree(dpu_state);
+}
+
+static const struct drm_private_state_funcs dpu_kms_global_state_funcs = {
+	.atomic_duplicate_state = dpu_kms_global_duplicate_state,
+	.atomic_destroy_state = dpu_kms_global_destroy_state,
+};
+
+static int dpu_kms_global_obj_init(struct dpu_kms *dpu_kms)
+{
+	struct dpu_global_state *state;
+
+	drm_modeset_lock_init(&dpu_kms->global_state_lock);
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+
+	drm_atomic_private_obj_init(dpu_kms->dev, &dpu_kms->global_state,
+				    &state->base,
+				    &dpu_kms_global_state_funcs);
+	return 0;
+}
+
+static int dpu_kms_parse_data_bus_icc_path(struct dpu_kms *dpu_kms)
+{
+	struct icc_path *path0;
+	struct icc_path *path1;
+	struct drm_device *dev = dpu_kms->dev;
+	struct device *dpu_dev = dev->dev;
+
+	path0 = msm_icc_get(dpu_dev, "mdp0-mem");
+	path1 = msm_icc_get(dpu_dev, "mdp1-mem");
+
+	if (IS_ERR_OR_NULL(path0))
+		return PTR_ERR_OR_ZERO(path0);
+
+	dpu_kms->path[0] = path0;
+	dpu_kms->num_paths = 1;
+
+	if (!IS_ERR_OR_NULL(path1)) {
+		dpu_kms->path[1] = path1;
+		dpu_kms->num_paths++;
+	}
+	return 0;
+}
+
+static int dpu_kms_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc)
+{
+	return dpu_crtc_vblank(crtc, true);
+}
+
+static void dpu_kms_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc)
+{
+	dpu_crtc_vblank(crtc, false);
+}
+
+static void dpu_kms_enable_commit(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+}
+
+static void dpu_kms_disable_commit(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+}
+
+static ktime_t dpu_kms_vsync_time(struct msm_kms *kms, struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask) {
+		ktime_t vsync_time;
+
+		if (dpu_encoder_vsync_time(encoder, &vsync_time) == 0)
+			return vsync_time;
+	}
+
+	return ktime_get();
+}
+
+static void dpu_kms_prepare_commit(struct msm_kms *kms,
+		struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	struct drm_encoder *encoder;
+	int i;
+
+	if (!kms)
+		return;
+
+	/* Call prepare_commit for all affected encoders */
+	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
+		drm_for_each_encoder_mask(encoder, crtc->dev,
+					  crtc_state->encoder_mask) {
+			dpu_encoder_prepare_commit(encoder);
+		}
+	}
+}
+
+static void dpu_kms_flush_commit(struct msm_kms *kms, unsigned crtc_mask)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	struct drm_crtc *crtc;
+
+	for_each_crtc_mask(dpu_kms->dev, crtc, crtc_mask) {
+		if (!crtc->state->active)
+			continue;
+
+		trace_dpu_kms_commit(DRMID(crtc));
+		dpu_crtc_commit_kickoff(crtc);
+	}
+}
+
+static void dpu_kms_complete_commit(struct msm_kms *kms, unsigned crtc_mask)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	struct drm_crtc *crtc;
+
+	DPU_ATRACE_BEGIN("kms_complete_commit");
+
+	for_each_crtc_mask(dpu_kms->dev, crtc, crtc_mask)
+		dpu_crtc_complete_commit(crtc);
+
+	DPU_ATRACE_END("kms_complete_commit");
+}
+
+static void dpu_kms_wait_for_commit_done(struct msm_kms *kms,
+		struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+	struct drm_device *dev;
+	int ret;
+
+	if (!kms || !crtc || !crtc->state) {
+		DPU_ERROR("invalid params\n");
+		return;
+	}
+
+	dev = crtc->dev;
+
+	if (!crtc->state->enable) {
+		DPU_DEBUG("[crtc:%d] not enable\n", crtc->base.id);
+		return;
+	}
+
+	if (!crtc->state->active) {
+		DPU_DEBUG("[crtc:%d] not active\n", crtc->base.id);
+		return;
+	}
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->crtc != crtc)
+			continue;
+		/*
+		 * Wait for post-flush if necessary to delay before
+		 * plane_cleanup. For example, wait for vsync in case of video
+		 * mode panels. This may be a no-op for command mode panels.
+		 */
+		trace_dpu_kms_wait_for_commit_done(DRMID(crtc));
+		ret = dpu_encoder_wait_for_event(encoder, MSM_ENC_COMMIT_DONE);
+		if (ret && ret != -EWOULDBLOCK) {
+			DPU_ERROR("wait for commit done returned %d\n", ret);
+			break;
+		}
+	}
+}
+
+static void dpu_kms_wait_flush(struct msm_kms *kms, unsigned crtc_mask)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	struct drm_crtc *crtc;
+
+	for_each_crtc_mask(dpu_kms->dev, crtc, crtc_mask)
+		dpu_kms_wait_for_commit_done(kms, crtc);
+}
+
+static int _dpu_kms_initialize_dsi(struct drm_device *dev,
+				    struct msm_drm_private *priv,
+				    struct dpu_kms *dpu_kms)
+{
+	struct drm_encoder *encoder = NULL;
+	struct msm_display_info info;
+	int i, rc = 0;
+
+	if (!(priv->dsi[0] || priv->dsi[1]))
+		return rc;
+
+	/*
+	 * We support following confiurations:
+	 * - Single DSI host (dsi0 or dsi1)
+	 * - Two independent DSI hosts
+	 * - Bonded DSI0 and DSI1 hosts
+	 *
+	 * TODO: Support swapping DSI0 and DSI1 in the bonded setup.
+	 */
+	for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) {
+		int other = (i + 1) % 2;
+
+		if (!priv->dsi[i])
+			continue;
+
+		if (msm_dsi_is_bonded_dsi(priv->dsi[i]) &&
+		    !msm_dsi_is_master_dsi(priv->dsi[i]))
+			continue;
+
+		encoder = dpu_encoder_init(dev, DRM_MODE_ENCODER_DSI);
+		if (IS_ERR(encoder)) {
+			DPU_ERROR("encoder init failed for dsi display\n");
+			return PTR_ERR(encoder);
+		}
+
+		memset(&info, 0, sizeof(info));
+		info.intf_type = encoder->encoder_type;
+
+		rc = msm_dsi_modeset_init(priv->dsi[i], dev, encoder);
+		if (rc) {
+			DPU_ERROR("modeset_init failed for dsi[%d], rc = %d\n",
+				i, rc);
+			break;
+		}
+
+		info.h_tile_instance[info.num_of_h_tiles++] = i;
+		info.is_cmd_mode = msm_dsi_is_cmd_mode(priv->dsi[i]);
+
+		info.dsc = msm_dsi_get_dsc_config(priv->dsi[i]);
+
+		if (msm_dsi_is_bonded_dsi(priv->dsi[i]) && priv->dsi[other]) {
+			rc = msm_dsi_modeset_init(priv->dsi[other], dev, encoder);
+			if (rc) {
+				DPU_ERROR("modeset_init failed for dsi[%d], rc = %d\n",
+					other, rc);
+				break;
+			}
+
+			info.h_tile_instance[info.num_of_h_tiles++] = other;
+		}
+
+		rc = dpu_encoder_setup(dev, encoder, &info);
+		if (rc)
+			DPU_ERROR("failed to setup DPU encoder %d: rc:%d\n",
+				  encoder->base.id, rc);
+	}
+
+	return rc;
+}
+
+static int _dpu_kms_initialize_displayport(struct drm_device *dev,
+					    struct msm_drm_private *priv,
+					    struct dpu_kms *dpu_kms)
+{
+	struct drm_encoder *encoder = NULL;
+	struct msm_display_info info;
+	int rc;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(priv->dp); i++) {
+		if (!priv->dp[i])
+			continue;
+
+		encoder = dpu_encoder_init(dev, DRM_MODE_ENCODER_TMDS);
+		if (IS_ERR(encoder)) {
+			DPU_ERROR("encoder init failed for dsi display\n");
+			return PTR_ERR(encoder);
+		}
+
+		memset(&info, 0, sizeof(info));
+		rc = msm_dp_modeset_init(priv->dp[i], dev, encoder);
+		if (rc) {
+			DPU_ERROR("modeset_init failed for DP, rc = %d\n", rc);
+			drm_encoder_cleanup(encoder);
+			return rc;
+		}
+
+		info.num_of_h_tiles = 1;
+		info.h_tile_instance[0] = i;
+		info.intf_type = encoder->encoder_type;
+		rc = dpu_encoder_setup(dev, encoder, &info);
+		if (rc) {
+			DPU_ERROR("failed to setup DPU encoder %d: rc:%d\n",
+				  encoder->base.id, rc);
+			return rc;
+		}
+	}
+
+	return 0;
+}
+
+static int _dpu_kms_initialize_writeback(struct drm_device *dev,
+		struct msm_drm_private *priv, struct dpu_kms *dpu_kms,
+		const u32 *wb_formats, int n_formats)
+{
+	struct drm_encoder *encoder = NULL;
+	struct msm_display_info info;
+	int rc;
+
+	encoder = dpu_encoder_init(dev, DRM_MODE_ENCODER_VIRTUAL);
+	if (IS_ERR(encoder)) {
+		DPU_ERROR("encoder init failed for dsi display\n");
+		return PTR_ERR(encoder);
+	}
+
+	memset(&info, 0, sizeof(info));
+
+	rc = dpu_writeback_init(dev, encoder, wb_formats,
+			n_formats);
+	if (rc) {
+		DPU_ERROR("dpu_writeback_init, rc = %d\n", rc);
+		drm_encoder_cleanup(encoder);
+		return rc;
+	}
+
+	info.num_of_h_tiles = 1;
+	/* use only WB idx 2 instance for DPU */
+	info.h_tile_instance[0] = WB_2;
+	info.intf_type = encoder->encoder_type;
+
+	rc = dpu_encoder_setup(dev, encoder, &info);
+	if (rc) {
+		DPU_ERROR("failed to setup DPU encoder %d: rc:%d\n",
+				  encoder->base.id, rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+/**
+ * _dpu_kms_setup_displays - create encoders, bridges and connectors
+ *                           for underlying displays
+ * @dev:        Pointer to drm device structure
+ * @priv:       Pointer to private drm device data
+ * @dpu_kms:    Pointer to dpu kms structure
+ * Returns:     Zero on success
+ */
+static int _dpu_kms_setup_displays(struct drm_device *dev,
+				    struct msm_drm_private *priv,
+				    struct dpu_kms *dpu_kms)
+{
+	int rc = 0;
+	int i;
+
+	rc = _dpu_kms_initialize_dsi(dev, priv, dpu_kms);
+	if (rc) {
+		DPU_ERROR("initialize_dsi failed, rc = %d\n", rc);
+		return rc;
+	}
+
+	rc = _dpu_kms_initialize_displayport(dev, priv, dpu_kms);
+	if (rc) {
+		DPU_ERROR("initialize_DP failed, rc = %d\n", rc);
+		return rc;
+	}
+
+	/* Since WB isn't a driver check the catalog before initializing */
+	if (dpu_kms->catalog->wb_count) {
+		for (i = 0; i < dpu_kms->catalog->wb_count; i++) {
+			if (dpu_kms->catalog->wb[i].id == WB_2) {
+				rc = _dpu_kms_initialize_writeback(dev, priv, dpu_kms,
+						dpu_kms->catalog->wb[i].format_list,
+						dpu_kms->catalog->wb[i].num_formats);
+				if (rc) {
+					DPU_ERROR("initialize_WB failed, rc = %d\n", rc);
+					return rc;
+				}
+			}
+		}
+	}
+
+	return rc;
+}
+
+#define MAX_PLANES 20
+static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms)
+{
+	struct drm_device *dev;
+	struct drm_plane *primary_planes[MAX_PLANES], *plane;
+	struct drm_plane *cursor_planes[MAX_PLANES] = { NULL };
+	struct drm_crtc *crtc;
+	struct drm_encoder *encoder;
+	unsigned int num_encoders;
+
+	struct msm_drm_private *priv;
+	const struct dpu_mdss_cfg *catalog;
+
+	int primary_planes_idx = 0, cursor_planes_idx = 0, i, ret;
+	int max_crtc_count;
+	dev = dpu_kms->dev;
+	priv = dev->dev_private;
+	catalog = dpu_kms->catalog;
+
+	/*
+	 * Create encoder and query display drivers to create
+	 * bridges and connectors
+	 */
+	ret = _dpu_kms_setup_displays(dev, priv, dpu_kms);
+	if (ret)
+		return ret;
+
+	num_encoders = 0;
+	drm_for_each_encoder(encoder, dev)
+		num_encoders++;
+
+	max_crtc_count = min(catalog->mixer_count, num_encoders);
+
+	/* Create the planes, keeping track of one primary/cursor per crtc */
+	for (i = 0; i < catalog->sspp_count; i++) {
+		enum drm_plane_type type;
+
+		if ((catalog->sspp[i].features & BIT(DPU_SSPP_CURSOR))
+			&& cursor_planes_idx < max_crtc_count)
+			type = DRM_PLANE_TYPE_CURSOR;
+		else if (primary_planes_idx < max_crtc_count)
+			type = DRM_PLANE_TYPE_PRIMARY;
+		else
+			type = DRM_PLANE_TYPE_OVERLAY;
+
+		DPU_DEBUG("Create plane type %d with features %lx (cur %lx)\n",
+			  type, catalog->sspp[i].features,
+			  catalog->sspp[i].features & BIT(DPU_SSPP_CURSOR));
+
+		plane = dpu_plane_init(dev, catalog->sspp[i].id, type,
+				       (1UL << max_crtc_count) - 1);
+		if (IS_ERR(plane)) {
+			DPU_ERROR("dpu_plane_init failed\n");
+			ret = PTR_ERR(plane);
+			return ret;
+		}
+
+		if (type == DRM_PLANE_TYPE_CURSOR)
+			cursor_planes[cursor_planes_idx++] = plane;
+		else if (type == DRM_PLANE_TYPE_PRIMARY)
+			primary_planes[primary_planes_idx++] = plane;
+	}
+
+	max_crtc_count = min(max_crtc_count, primary_planes_idx);
+
+	/* Create one CRTC per encoder */
+	for (i = 0; i < max_crtc_count; i++) {
+		crtc = dpu_crtc_init(dev, primary_planes[i], cursor_planes[i]);
+		if (IS_ERR(crtc)) {
+			ret = PTR_ERR(crtc);
+			return ret;
+		}
+		priv->crtcs[priv->num_crtcs++] = crtc;
+	}
+
+	/* All CRTCs are compatible with all encoders */
+	drm_for_each_encoder(encoder, dev)
+		encoder->possible_crtcs = (1 << priv->num_crtcs) - 1;
+
+	return 0;
+}
+
+static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms)
+{
+	int i;
+
+	if (dpu_kms->hw_intr)
+		dpu_hw_intr_destroy(dpu_kms->hw_intr);
+	dpu_kms->hw_intr = NULL;
+
+	/* safe to call these more than once during shutdown */
+	_dpu_kms_mmu_destroy(dpu_kms);
+
+	if (dpu_kms->catalog) {
+		for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+			if (dpu_kms->hw_vbif[i]) {
+				dpu_hw_vbif_destroy(dpu_kms->hw_vbif[i]);
+				dpu_kms->hw_vbif[i] = NULL;
+			}
+		}
+	}
+
+	if (dpu_kms->rm_init)
+		dpu_rm_destroy(&dpu_kms->rm);
+	dpu_kms->rm_init = false;
+
+	dpu_kms->catalog = NULL;
+
+	if (dpu_kms->vbif[VBIF_NRT])
+		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->vbif[VBIF_NRT]);
+	dpu_kms->vbif[VBIF_NRT] = NULL;
+
+	if (dpu_kms->vbif[VBIF_RT])
+		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->vbif[VBIF_RT]);
+	dpu_kms->vbif[VBIF_RT] = NULL;
+
+	if (dpu_kms->hw_mdp)
+		dpu_hw_mdp_destroy(dpu_kms->hw_mdp);
+	dpu_kms->hw_mdp = NULL;
+
+	if (dpu_kms->mmio)
+		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->mmio);
+	dpu_kms->mmio = NULL;
+}
+
+static void dpu_kms_destroy(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms;
+
+	if (!kms) {
+		DPU_ERROR("invalid kms\n");
+		return;
+	}
+
+	dpu_kms = to_dpu_kms(kms);
+
+	_dpu_kms_hw_destroy(dpu_kms);
+
+	msm_kms_destroy(&dpu_kms->base);
+
+	if (dpu_kms->rpm_enabled)
+		pm_runtime_disable(&dpu_kms->pdev->dev);
+}
+
+static int dpu_irq_postinstall(struct msm_kms *kms)
+{
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	int i;
+
+	if (!dpu_kms || !dpu_kms->dev)
+		return -EINVAL;
+
+	priv = dpu_kms->dev->dev_private;
+	if (!priv)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(priv->dp); i++)
+		msm_dp_irq_postinstall(priv->dp[i]);
+
+	return 0;
+}
+
+static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_kms *kms)
+{
+	int i;
+	struct dpu_kms *dpu_kms;
+	const struct dpu_mdss_cfg *cat;
+
+	dpu_kms = to_dpu_kms(kms);
+
+	cat = dpu_kms->catalog;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+	/* dump CTL sub-blocks HW regs info */
+	for (i = 0; i < cat->ctl_count; i++)
+		msm_disp_snapshot_add_block(disp_state, cat->ctl[i].len,
+				dpu_kms->mmio + cat->ctl[i].base, "ctl_%d", i);
+
+	/* dump DSPP sub-blocks HW regs info */
+	for (i = 0; i < cat->dspp_count; i++)
+		msm_disp_snapshot_add_block(disp_state, cat->dspp[i].len,
+				dpu_kms->mmio + cat->dspp[i].base, "dspp_%d", i);
+
+	/* dump INTF sub-blocks HW regs info */
+	for (i = 0; i < cat->intf_count; i++)
+		msm_disp_snapshot_add_block(disp_state, cat->intf[i].len,
+				dpu_kms->mmio + cat->intf[i].base, "intf_%d", i);
+
+	/* dump PP sub-blocks HW regs info */
+	for (i = 0; i < cat->pingpong_count; i++)
+		msm_disp_snapshot_add_block(disp_state, cat->pingpong[i].len,
+				dpu_kms->mmio + cat->pingpong[i].base, "pingpong_%d", i);
+
+	/* dump SSPP sub-blocks HW regs info */
+	for (i = 0; i < cat->sspp_count; i++)
+		msm_disp_snapshot_add_block(disp_state, cat->sspp[i].len,
+				dpu_kms->mmio + cat->sspp[i].base, "sspp_%d", i);
+
+	/* dump LM sub-blocks HW regs info */
+	for (i = 0; i < cat->mixer_count; i++)
+		msm_disp_snapshot_add_block(disp_state, cat->mixer[i].len,
+				dpu_kms->mmio + cat->mixer[i].base, "lm_%d", i);
+
+	/* dump WB sub-blocks HW regs info */
+	for (i = 0; i < cat->wb_count; i++)
+		msm_disp_snapshot_add_block(disp_state, cat->wb[i].len,
+				dpu_kms->mmio + cat->wb[i].base, "wb_%d", i);
+
+	msm_disp_snapshot_add_block(disp_state, cat->mdp[0].len,
+			dpu_kms->mmio + cat->mdp[0].base, "top");
+
+	/* dump DSC sub-blocks HW regs info */
+	for (i = 0; i < cat->dsc_count; i++)
+		msm_disp_snapshot_add_block(disp_state, cat->dsc[i].len,
+				dpu_kms->mmio + cat->dsc[i].base, "dsc_%d", i);
+
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+}
+
+static const struct msm_kms_funcs kms_funcs = {
+	.hw_init         = dpu_kms_hw_init,
+	.irq_preinstall  = dpu_core_irq_preinstall,
+	.irq_postinstall = dpu_irq_postinstall,
+	.irq_uninstall   = dpu_core_irq_uninstall,
+	.irq             = dpu_core_irq,
+	.enable_commit   = dpu_kms_enable_commit,
+	.disable_commit  = dpu_kms_disable_commit,
+	.vsync_time      = dpu_kms_vsync_time,
+	.prepare_commit  = dpu_kms_prepare_commit,
+	.flush_commit    = dpu_kms_flush_commit,
+	.wait_flush      = dpu_kms_wait_flush,
+	.complete_commit = dpu_kms_complete_commit,
+	.enable_vblank   = dpu_kms_enable_vblank,
+	.disable_vblank  = dpu_kms_disable_vblank,
+	.check_modified_format = dpu_format_check_modified_format,
+	.get_format      = dpu_get_msm_format,
+	.destroy         = dpu_kms_destroy,
+	.snapshot        = dpu_kms_mdp_snapshot,
+#ifdef CONFIG_DEBUG_FS
+	.debugfs_init    = dpu_kms_debugfs_init,
+#endif
+};
+
+static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms)
+{
+	struct msm_mmu *mmu;
+
+	if (!dpu_kms->base.aspace)
+		return;
+
+	mmu = dpu_kms->base.aspace->mmu;
+
+	mmu->funcs->detach(mmu);
+	msm_gem_address_space_put(dpu_kms->base.aspace);
+
+	dpu_kms->base.aspace = NULL;
+}
+
+static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms)
+{
+	struct msm_gem_address_space *aspace;
+
+	aspace = msm_kms_init_aspace(dpu_kms->dev);
+	if (IS_ERR(aspace))
+		return PTR_ERR(aspace);
+
+	dpu_kms->base.aspace = aspace;
+
+	return 0;
+}
+
+u64 dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name)
+{
+	struct clk *clk;
+
+	clk = msm_clk_bulk_get_clock(dpu_kms->clocks, dpu_kms->num_clocks, clock_name);
+	if (!clk)
+		return -EINVAL;
+
+	return clk_get_rate(clk);
+}
+
+static int dpu_kms_hw_init(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms;
+	struct drm_device *dev;
+	int i, rc = -EINVAL;
+
+	if (!kms) {
+		DPU_ERROR("invalid kms\n");
+		return rc;
+	}
+
+	dpu_kms = to_dpu_kms(kms);
+	dev = dpu_kms->dev;
+
+	rc = dpu_kms_global_obj_init(dpu_kms);
+	if (rc)
+		return rc;
+
+	atomic_set(&dpu_kms->bandwidth_ref, 0);
+
+	dpu_kms->mmio = msm_ioremap(dpu_kms->pdev, "mdp");
+	if (IS_ERR(dpu_kms->mmio)) {
+		rc = PTR_ERR(dpu_kms->mmio);
+		DPU_ERROR("mdp register memory map failed: %d\n", rc);
+		dpu_kms->mmio = NULL;
+		goto error;
+	}
+	DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio);
+
+	dpu_kms->vbif[VBIF_RT] = msm_ioremap(dpu_kms->pdev, "vbif");
+	if (IS_ERR(dpu_kms->vbif[VBIF_RT])) {
+		rc = PTR_ERR(dpu_kms->vbif[VBIF_RT]);
+		DPU_ERROR("vbif register memory map failed: %d\n", rc);
+		dpu_kms->vbif[VBIF_RT] = NULL;
+		goto error;
+	}
+	dpu_kms->vbif[VBIF_NRT] = msm_ioremap_quiet(dpu_kms->pdev, "vbif_nrt");
+	if (IS_ERR(dpu_kms->vbif[VBIF_NRT])) {
+		dpu_kms->vbif[VBIF_NRT] = NULL;
+		DPU_DEBUG("VBIF NRT is not defined");
+	}
+
+	dpu_kms->reg_dma = msm_ioremap_quiet(dpu_kms->pdev, "regdma");
+	if (IS_ERR(dpu_kms->reg_dma)) {
+		dpu_kms->reg_dma = NULL;
+		DPU_DEBUG("REG_DMA is not defined");
+	}
+
+	dpu_kms_parse_data_bus_icc_path(dpu_kms);
+
+	rc = pm_runtime_resume_and_get(&dpu_kms->pdev->dev);
+	if (rc < 0)
+		goto error;
+
+	dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0);
+
+	pr_info("dpu hardware revision:0x%x\n", dpu_kms->core_rev);
+
+	dpu_kms->catalog = dpu_hw_catalog_init(dpu_kms->core_rev);
+	if (IS_ERR_OR_NULL(dpu_kms->catalog)) {
+		rc = PTR_ERR(dpu_kms->catalog);
+		if (!dpu_kms->catalog)
+			rc = -EINVAL;
+		DPU_ERROR("catalog init failed: %d\n", rc);
+		dpu_kms->catalog = NULL;
+		goto power_error;
+	}
+
+	/*
+	 * Now we need to read the HW catalog and initialize resources such as
+	 * clocks, regulators, GDSC/MMAGIC, ioremap the register ranges etc
+	 */
+	rc = _dpu_kms_mmu_init(dpu_kms);
+	if (rc) {
+		DPU_ERROR("dpu_kms_mmu_init failed: %d\n", rc);
+		goto power_error;
+	}
+
+	rc = dpu_rm_init(&dpu_kms->rm, dpu_kms->catalog, dpu_kms->mmio);
+	if (rc) {
+		DPU_ERROR("rm init failed: %d\n", rc);
+		goto power_error;
+	}
+
+	dpu_kms->rm_init = true;
+
+	dpu_kms->hw_mdp = dpu_hw_mdptop_init(MDP_TOP, dpu_kms->mmio,
+					     dpu_kms->catalog);
+	if (IS_ERR(dpu_kms->hw_mdp)) {
+		rc = PTR_ERR(dpu_kms->hw_mdp);
+		DPU_ERROR("failed to get hw_mdp: %d\n", rc);
+		dpu_kms->hw_mdp = NULL;
+		goto power_error;
+	}
+
+	for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
+		u32 vbif_idx = dpu_kms->catalog->vbif[i].id;
+
+		dpu_kms->hw_vbif[vbif_idx] = dpu_hw_vbif_init(vbif_idx,
+				dpu_kms->vbif[vbif_idx], dpu_kms->catalog);
+		if (IS_ERR(dpu_kms->hw_vbif[vbif_idx])) {
+			rc = PTR_ERR(dpu_kms->hw_vbif[vbif_idx]);
+			DPU_ERROR("failed to init vbif %d: %d\n", vbif_idx, rc);
+			dpu_kms->hw_vbif[vbif_idx] = NULL;
+			goto power_error;
+		}
+	}
+
+	rc = dpu_core_perf_init(&dpu_kms->perf, dev, dpu_kms->catalog,
+			msm_clk_bulk_get_clock(dpu_kms->clocks, dpu_kms->num_clocks, "core"));
+	if (rc) {
+		DPU_ERROR("failed to init perf %d\n", rc);
+		goto perf_err;
+	}
+
+	dpu_kms->hw_intr = dpu_hw_intr_init(dpu_kms->mmio, dpu_kms->catalog);
+	if (IS_ERR_OR_NULL(dpu_kms->hw_intr)) {
+		rc = PTR_ERR(dpu_kms->hw_intr);
+		DPU_ERROR("hw_intr init failed: %d\n", rc);
+		dpu_kms->hw_intr = NULL;
+		goto hw_intr_init_err;
+	}
+
+	dev->mode_config.min_width = 0;
+	dev->mode_config.min_height = 0;
+
+	/*
+	 * max crtc width is equal to the max mixer width * 2 and max height is
+	 * is 4K
+	 */
+	dev->mode_config.max_width =
+			dpu_kms->catalog->caps->max_mixer_width * 2;
+	dev->mode_config.max_height = 4096;
+
+	dev->max_vblank_count = 0xffffffff;
+	/* Disable vblank irqs aggressively for power-saving */
+	dev->vblank_disable_immediate = true;
+
+	/*
+	 * _dpu_kms_drm_obj_init should create the DRM related objects
+	 * i.e. CRTCs, planes, encoders, connectors and so forth
+	 */
+	rc = _dpu_kms_drm_obj_init(dpu_kms);
+	if (rc) {
+		DPU_ERROR("modeset init failed: %d\n", rc);
+		goto drm_obj_init_err;
+	}
+
+	dpu_vbif_init_memtypes(dpu_kms);
+
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+
+drm_obj_init_err:
+	dpu_core_perf_destroy(&dpu_kms->perf);
+hw_intr_init_err:
+perf_err:
+power_error:
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+error:
+	_dpu_kms_hw_destroy(dpu_kms);
+
+	return rc;
+}
+
+static int dpu_kms_init(struct drm_device *ddev)
+{
+	struct msm_drm_private *priv = ddev->dev_private;
+	struct device *dev = ddev->dev;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dpu_kms *dpu_kms;
+	int irq;
+	struct dev_pm_opp *opp;
+	int ret = 0;
+	unsigned long max_freq = ULONG_MAX;
+
+	dpu_kms = devm_kzalloc(&pdev->dev, sizeof(*dpu_kms), GFP_KERNEL);
+	if (!dpu_kms)
+		return -ENOMEM;
+
+	ret = devm_pm_opp_set_clkname(dev, "core");
+	if (ret)
+		return ret;
+	/* OPP table is optional */
+	ret = devm_pm_opp_of_add_table(dev);
+	if (ret && ret != -ENODEV) {
+		dev_err(dev, "invalid OPP table in device tree\n");
+		return ret;
+	}
+
+	ret = devm_clk_bulk_get_all(&pdev->dev, &dpu_kms->clocks);
+	if (ret < 0) {
+		DPU_ERROR("failed to parse clocks, ret=%d\n", ret);
+		return ret;
+	}
+	dpu_kms->num_clocks = ret;
+
+	opp = dev_pm_opp_find_freq_floor(dev, &max_freq);
+	if (!IS_ERR(opp))
+		dev_pm_opp_put(opp);
+
+	dev_pm_opp_set_rate(dev, max_freq);
+
+	ret = msm_kms_init(&dpu_kms->base, &kms_funcs);
+	if (ret) {
+		DPU_ERROR("failed to init kms, ret=%d\n", ret);
+		return ret;
+	}
+	dpu_kms->dev = ddev;
+	dpu_kms->pdev = pdev;
+
+	pm_runtime_enable(&pdev->dev);
+	dpu_kms->rpm_enabled = true;
+
+	priv->kms = &dpu_kms->base;
+
+	irq = irq_of_parse_and_map(dpu_kms->pdev->dev.of_node, 0);
+	if (!irq) {
+		DPU_ERROR("failed to get irq\n");
+		return -EINVAL;
+	}
+	dpu_kms->base.irq = irq;
+
+	return 0;
+}
+
+static int dpu_dev_probe(struct platform_device *pdev)
+{
+	return msm_drv_probe(&pdev->dev, dpu_kms_init);
+}
+
+static int dpu_dev_remove(struct platform_device *pdev)
+{
+	component_master_del(&pdev->dev, &msm_drm_ops);
+
+	return 0;
+}
+
+static int __maybe_unused dpu_runtime_suspend(struct device *dev)
+{
+	int i;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct msm_drm_private *priv = platform_get_drvdata(pdev);
+	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
+
+	/* Drop the performance state vote */
+	dev_pm_opp_set_rate(dev, 0);
+	clk_bulk_disable_unprepare(dpu_kms->num_clocks, dpu_kms->clocks);
+
+	for (i = 0; i < dpu_kms->num_paths; i++)
+		icc_set_bw(dpu_kms->path[i], 0, 0);
+
+	return 0;
+}
+
+static int __maybe_unused dpu_runtime_resume(struct device *dev)
+{
+	int rc = -1;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct msm_drm_private *priv = platform_get_drvdata(pdev);
+	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
+	struct drm_encoder *encoder;
+	struct drm_device *ddev;
+
+	ddev = dpu_kms->dev;
+
+	rc = clk_bulk_prepare_enable(dpu_kms->num_clocks, dpu_kms->clocks);
+	if (rc) {
+		DPU_ERROR("clock enable failed rc:%d\n", rc);
+		return rc;
+	}
+
+	dpu_vbif_init_memtypes(dpu_kms);
+
+	drm_for_each_encoder(encoder, ddev)
+		dpu_encoder_virt_runtime_resume(encoder);
+
+	return rc;
+}
+
+static const struct dev_pm_ops dpu_pm_ops = {
+	SET_RUNTIME_PM_OPS(dpu_runtime_suspend, dpu_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	.prepare = msm_pm_prepare,
+	.complete = msm_pm_complete,
+};
+
+static const struct of_device_id dpu_dt_match[] = {
+	{ .compatible = "qcom,msm8998-dpu", },
+	{ .compatible = "qcom,qcm2290-dpu", },
+	{ .compatible = "qcom,sdm845-dpu", },
+	{ .compatible = "qcom,sc7180-dpu", },
+	{ .compatible = "qcom,sc7280-dpu", },
+	{ .compatible = "qcom,sc8180x-dpu", },
+	{ .compatible = "qcom,sm8150-dpu", },
+	{ .compatible = "qcom,sm8250-dpu", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, dpu_dt_match);
+
+static struct platform_driver dpu_driver = {
+	.probe = dpu_dev_probe,
+	.remove = dpu_dev_remove,
+	.shutdown = msm_drv_shutdown,
+	.driver = {
+		.name = "msm_dpu",
+		.of_match_table = dpu_dt_match,
+		.pm = &dpu_pm_ops,
+	},
+};
+
+void __init msm_dpu_register(void)
+{
+	platform_driver_register(&dpu_driver);
+}
+
+void __exit msm_dpu_unregister(void)
+{
+	platform_driver_unregister(&dpu_driver);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
new file mode 100644
index 000000000..ed80ed678
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -0,0 +1,207 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#ifndef __DPU_KMS_H__
+#define __DPU_KMS_H__
+
+#include <linux/interconnect.h>
+
+#include <drm/drm_drv.h>
+
+#include "msm_drv.h"
+#include "msm_kms.h"
+#include "msm_mmu.h"
+#include "msm_gem.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_hw_top.h"
+#include "dpu_rm.h"
+#include "dpu_core_perf.h"
+
+#define DRMID(x) ((x) ? (x)->base.id : -1)
+
+/**
+ * DPU_DEBUG - macro for kms/plane/crtc/encoder/connector logs
+ * @fmt: Pointer to format string
+ */
+#define DPU_DEBUG(fmt, ...)                                                \
+	do {                                                               \
+		if (drm_debug_enabled(DRM_UT_KMS))                         \
+			DRM_DEBUG(fmt, ##__VA_ARGS__); \
+		else                                                       \
+			pr_debug(fmt, ##__VA_ARGS__);                      \
+	} while (0)
+
+/**
+ * DPU_DEBUG_DRIVER - macro for hardware driver logging
+ * @fmt: Pointer to format string
+ */
+#define DPU_DEBUG_DRIVER(fmt, ...)                                         \
+	do {                                                               \
+		if (drm_debug_enabled(DRM_UT_DRIVER))                      \
+			DRM_ERROR(fmt, ##__VA_ARGS__); \
+		else                                                       \
+			pr_debug(fmt, ##__VA_ARGS__);                      \
+	} while (0)
+
+#define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__)
+
+/**
+ * ktime_compare_safe - compare two ktime structures
+ *	This macro is similar to the standard ktime_compare() function, but
+ *	attempts to also handle ktime overflows.
+ * @A: First ktime value
+ * @B: Second ktime value
+ * Returns: -1 if A < B, 0 if A == B, 1 if A > B
+ */
+#define ktime_compare_safe(A, B) \
+	ktime_compare(ktime_sub((A), (B)), ktime_set(0, 0))
+
+#define DPU_NAME_SIZE  12
+
+struct dpu_kms {
+	struct msm_kms base;
+	struct drm_device *dev;
+	int core_rev;
+	const struct dpu_mdss_cfg *catalog;
+
+	/* io/register spaces: */
+	void __iomem *mmio, *vbif[VBIF_MAX], *reg_dma;
+
+	struct regulator *vdd;
+	struct regulator *mmagic;
+	struct regulator *venus;
+
+	struct dpu_hw_intr *hw_intr;
+
+	struct dpu_core_perf perf;
+
+	/*
+	 * Global private object state, Do not access directly, use
+	 * dpu_kms_global_get_state()
+	 */
+	struct drm_modeset_lock global_state_lock;
+	struct drm_private_obj global_state;
+
+	struct dpu_rm rm;
+	bool rm_init;
+
+	struct dpu_hw_vbif *hw_vbif[VBIF_MAX];
+	struct dpu_hw_mdp *hw_mdp;
+
+	bool has_danger_ctrl;
+
+	struct platform_device *pdev;
+	bool rpm_enabled;
+
+	struct clk_bulk_data *clocks;
+	size_t num_clocks;
+
+	/* reference count bandwidth requests, so we know when we can
+	 * release bandwidth.  Each atomic update increments, and frame-
+	 * done event decrements.  Additionally, for video mode, the
+	 * reference is incremented when crtc is enabled, and decremented
+	 * when disabled.
+	 */
+	atomic_t bandwidth_ref;
+	struct icc_path *path[2];
+	u32 num_paths;
+};
+
+struct vsync_info {
+	u32 frame_count;
+	u32 line_count;
+};
+
+#define to_dpu_kms(x) container_of(x, struct dpu_kms, base)
+
+#define to_dpu_global_state(x) container_of(x, struct dpu_global_state, base)
+
+/* Global private object state for tracking resources that are shared across
+ * multiple kms objects (planes/crtcs/etc).
+ */
+struct dpu_global_state {
+	struct drm_private_state base;
+
+	uint32_t pingpong_to_enc_id[PINGPONG_MAX - PINGPONG_0];
+	uint32_t mixer_to_enc_id[LM_MAX - LM_0];
+	uint32_t ctl_to_enc_id[CTL_MAX - CTL_0];
+	uint32_t dspp_to_enc_id[DSPP_MAX - DSPP_0];
+	uint32_t dsc_to_enc_id[DSC_MAX - DSC_0];
+};
+
+struct dpu_global_state
+	*dpu_kms_get_existing_global_state(struct dpu_kms *dpu_kms);
+struct dpu_global_state
+	*__must_check dpu_kms_get_global_state(struct drm_atomic_state *s);
+
+/**
+ * Debugfs functions - extra helper functions for debugfs support
+ *
+ * Main debugfs documentation is located at,
+ *
+ * Documentation/filesystems/debugfs.rst
+ *
+ * @dpu_debugfs_create_regset32: Create 32-bit register dump file
+ */
+
+/**
+ * dpu_debugfs_create_regset32 - Create register read back file for debugfs
+ *
+ * This function is almost identical to the standard debugfs_create_regset32()
+ * function, with the main difference being that a list of register
+ * names/offsets do not need to be provided. The 'read' function simply outputs
+ * sequential register values over a specified range.
+ *
+ * @name:   File name within debugfs
+ * @mode:   File mode within debugfs
+ * @parent: Parent directory entry within debugfs, can be NULL
+ * @offset: sub-block offset
+ * @length: sub-block length, in bytes
+ * @dpu_kms: pointer to dpu kms structure
+ */
+void dpu_debugfs_create_regset32(const char *name, umode_t mode,
+		void *parent,
+		uint32_t offset, uint32_t length, struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_debugfs_get_root - Return root directory entry for KMS's debugfs
+ *
+ * The return value should be passed as the 'parent' argument to subsequent
+ * debugfs create calls.
+ *
+ * @dpu_kms: Pointer to DPU's KMS structure
+ *
+ * Return: dentry pointer for DPU's debugfs location
+ */
+void *dpu_debugfs_get_root(struct dpu_kms *dpu_kms);
+
+/**
+ * DPU info management functions
+ * These functions/definitions allow for building up a 'dpu_info' structure
+ * containing one or more "key=value\n" entries.
+ */
+#define DPU_KMS_INFO_MAX_SIZE	4096
+
+/**
+ * Vblank enable/disable functions
+ */
+int dpu_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc);
+void dpu_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc);
+
+/**
+ * dpu_kms_get_clk_rate() - get the clock rate
+ * @dpu_kms:  pointer to dpu_kms structure
+ * @clock_name: clock name to get the rate
+ *
+ * Return: current clock rate
+ */
+u64 dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name);
+
+#endif /* __dpu_kms_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
new file mode 100644
index 000000000..62d48c0f9
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -0,0 +1,1539 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014-2018 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/dma-buf.h>
+
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_uapi.h>
+#include <drm/drm_blend.h>
+#include <drm/drm_damage_helper.h>
+#include <drm/drm_framebuffer.h>
+#include <drm/drm_gem_atomic_helper.h>
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include "dpu_formats.h"
+#include "dpu_hw_sspp.h"
+#include "dpu_trace.h"
+#include "dpu_crtc.h"
+#include "dpu_vbif.h"
+#include "dpu_plane.h"
+
+#define DPU_DEBUG_PLANE(pl, fmt, ...) DRM_DEBUG_ATOMIC("plane%d " fmt,\
+		(pl) ? (pl)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_PLANE(pl, fmt, ...) DPU_ERROR("plane%d " fmt,\
+		(pl) ? (pl)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DECIMATED_DIMENSION(dim, deci) (((dim) + ((1 << (deci)) - 1)) >> (deci))
+#define PHASE_STEP_SHIFT	21
+#define PHASE_STEP_UNIT_SCALE   ((int) (1 << PHASE_STEP_SHIFT))
+#define PHASE_RESIDUAL		15
+
+#define SHARP_STRENGTH_DEFAULT	32
+#define SHARP_EDGE_THR_DEFAULT	112
+#define SHARP_SMOOTH_THR_DEFAULT	8
+#define SHARP_NOISE_THR_DEFAULT	2
+
+#define DPU_NAME_SIZE  12
+
+#define DPU_PLANE_COLOR_FILL_FLAG	BIT(31)
+#define DPU_ZPOS_MAX 255
+
+/* multirect rect index */
+enum {
+	R0,
+	R1,
+	R_MAX
+};
+
+/*
+ * Default Preload Values
+ */
+#define DPU_QSEED3_DEFAULT_PRELOAD_H 0x4
+#define DPU_QSEED3_DEFAULT_PRELOAD_V 0x3
+#define DPU_QSEED4_DEFAULT_PRELOAD_V 0x2
+#define DPU_QSEED4_DEFAULT_PRELOAD_H 0x4
+
+#define DEFAULT_REFRESH_RATE	60
+
+static const uint32_t qcom_compressed_supported_formats[] = {
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_BGR565,
+
+	DRM_FORMAT_NV12,
+};
+
+/**
+ * enum dpu_plane_qos - Different qos configurations for each pipe
+ *
+ * @DPU_PLANE_QOS_VBLANK_CTRL: Setup VBLANK qos for the pipe.
+ * @DPU_PLANE_QOS_VBLANK_AMORTIZE: Enables Amortization within pipe.
+ *	this configuration is mutually exclusive from VBLANK_CTRL.
+ * @DPU_PLANE_QOS_PANIC_CTRL: Setup panic for the pipe.
+ */
+enum dpu_plane_qos {
+	DPU_PLANE_QOS_VBLANK_CTRL = BIT(0),
+	DPU_PLANE_QOS_VBLANK_AMORTIZE = BIT(1),
+	DPU_PLANE_QOS_PANIC_CTRL = BIT(2),
+};
+
+/*
+ * struct dpu_plane - local dpu plane structure
+ * @aspace: address space pointer
+ * @csc_ptr: Points to dpu_csc_cfg structure to use for current
+ * @catalog: Points to dpu catalog structure
+ * @revalidate: force revalidation of all the plane properties
+ */
+struct dpu_plane {
+	struct drm_plane base;
+
+	struct mutex lock;
+
+	enum dpu_sspp pipe;
+
+	struct dpu_hw_pipe *pipe_hw;
+	uint32_t color_fill;
+	bool is_error;
+	bool is_rt_pipe;
+	const struct dpu_mdss_cfg *catalog;
+};
+
+static const uint64_t supported_format_modifiers[] = {
+	DRM_FORMAT_MOD_QCOM_COMPRESSED,
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID
+};
+
+#define to_dpu_plane(x) container_of(x, struct dpu_plane, base)
+
+static struct dpu_kms *_dpu_plane_get_kms(struct drm_plane *plane)
+{
+	struct msm_drm_private *priv = plane->dev->dev_private;
+
+	return to_dpu_kms(priv->kms);
+}
+
+/**
+ * _dpu_plane_calc_bw - calculate bandwidth required for a plane
+ * @plane: Pointer to drm plane.
+ * @fb:   Pointer to framebuffer associated with the given plane
+ * @pipe_cfg: Pointer to pipe configuration
+ * Result: Updates calculated bandwidth in the plane state.
+ * BW Equation: src_w * src_h * bpp * fps * (v_total / v_dest)
+ * Prefill BW Equation: line src bytes * line_time
+ */
+static void _dpu_plane_calc_bw(struct drm_plane *plane,
+	struct drm_framebuffer *fb,
+	struct dpu_hw_pipe_cfg *pipe_cfg)
+{
+	struct dpu_plane_state *pstate;
+	struct drm_display_mode *mode;
+	const struct dpu_format *fmt = NULL;
+	struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane);
+	int src_width, src_height, dst_height, fps;
+	u64 plane_pixel_rate, plane_bit_rate;
+	u64 plane_prefill_bw;
+	u64 plane_bw;
+	u32 hw_latency_lines;
+	u64 scale_factor;
+	int vbp, vpw, vfp;
+
+	pstate = to_dpu_plane_state(plane->state);
+	mode = &plane->state->crtc->mode;
+
+	fmt = dpu_get_dpu_format_ext(fb->format->format, fb->modifier);
+
+	src_width = drm_rect_width(&pipe_cfg->src_rect);
+	src_height = drm_rect_height(&pipe_cfg->src_rect);
+	dst_height = drm_rect_height(&pipe_cfg->dst_rect);
+	fps = drm_mode_vrefresh(mode);
+	vbp = mode->vtotal - mode->vsync_end;
+	vpw = mode->vsync_end - mode->vsync_start;
+	vfp = mode->vsync_start - mode->vdisplay;
+	hw_latency_lines =  dpu_kms->catalog->perf->min_prefill_lines;
+	scale_factor = src_height > dst_height ?
+		mult_frac(src_height, 1, dst_height) : 1;
+
+	plane_pixel_rate = src_width * mode->vtotal * fps;
+	plane_bit_rate = plane_pixel_rate * fmt->bpp;
+
+	plane_bw = plane_bit_rate * scale_factor;
+
+	plane_prefill_bw = plane_bw * hw_latency_lines;
+
+	if ((vbp+vpw) > hw_latency_lines)
+		do_div(plane_prefill_bw, (vbp+vpw));
+	else if ((vbp+vpw+vfp) < hw_latency_lines)
+		do_div(plane_prefill_bw, (vbp+vpw+vfp));
+	else
+		do_div(plane_prefill_bw, hw_latency_lines);
+
+
+	pstate->plane_fetch_bw = max(plane_bw, plane_prefill_bw);
+}
+
+/**
+ * _dpu_plane_calc_clk - calculate clock required for a plane
+ * @plane: Pointer to drm plane.
+ * @pipe_cfg: Pointer to pipe configuration
+ * Result: Updates calculated clock in the plane state.
+ * Clock equation: dst_w * v_total * fps * (src_h / dst_h)
+ */
+static void _dpu_plane_calc_clk(struct drm_plane *plane, struct dpu_hw_pipe_cfg *pipe_cfg)
+{
+	struct dpu_plane_state *pstate;
+	struct drm_display_mode *mode;
+	int dst_width, src_height, dst_height, fps;
+
+	pstate = to_dpu_plane_state(plane->state);
+	mode = &plane->state->crtc->mode;
+
+	src_height = drm_rect_height(&pipe_cfg->src_rect);
+	dst_width = drm_rect_width(&pipe_cfg->dst_rect);
+	dst_height = drm_rect_height(&pipe_cfg->dst_rect);
+	fps = drm_mode_vrefresh(mode);
+
+	pstate->plane_clk =
+		dst_width * mode->vtotal * fps;
+
+	if (src_height > dst_height) {
+		pstate->plane_clk *= src_height;
+		do_div(pstate->plane_clk, dst_height);
+	}
+}
+
+/**
+ * _dpu_plane_calc_fill_level - calculate fill level of the given source format
+ * @plane:		Pointer to drm plane
+ * @fmt:		Pointer to source buffer format
+ * @src_width:		width of source buffer
+ * Return: fill level corresponding to the source buffer/format or 0 if error
+ */
+static int _dpu_plane_calc_fill_level(struct drm_plane *plane,
+		const struct dpu_format *fmt, u32 src_width)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+	u32 fixed_buff_size;
+	u32 total_fl;
+
+	if (!fmt || !plane->state || !src_width || !fmt->bpp) {
+		DPU_ERROR("invalid arguments\n");
+		return 0;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pstate = to_dpu_plane_state(plane->state);
+	fixed_buff_size = pdpu->catalog->caps->pixel_ram_size;
+
+	/* FIXME: in multirect case account for the src_width of all the planes */
+
+	if (fmt->fetch_planes == DPU_PLANE_PSEUDO_PLANAR) {
+		if (fmt->chroma_sample == DPU_CHROMA_420) {
+			/* NV12 */
+			total_fl = (fixed_buff_size / 2) /
+				((src_width + 32) * fmt->bpp);
+		} else {
+			/* non NV12 */
+			total_fl = (fixed_buff_size / 2) * 2 /
+				((src_width + 32) * fmt->bpp);
+		}
+	} else {
+		if (pstate->multirect_mode == DPU_SSPP_MULTIRECT_PARALLEL) {
+			total_fl = (fixed_buff_size / 2) * 2 /
+				((src_width + 32) * fmt->bpp);
+		} else {
+			total_fl = (fixed_buff_size) * 2 /
+				((src_width + 32) * fmt->bpp);
+		}
+	}
+
+	DPU_DEBUG_PLANE(pdpu, "pnum:%d fmt: %4.4s w:%u fl:%u\n",
+			pdpu->pipe - SSPP_VIG0,
+			(char *)&fmt->base.pixel_format,
+			src_width, total_fl);
+
+	return total_fl;
+}
+
+/**
+ * _dpu_plane_set_qos_lut - set QoS LUT of the given plane
+ * @plane:		Pointer to drm plane
+ * @fb:			Pointer to framebuffer associated with the given plane
+ * @pipe_cfg:		Pointer to pipe configuration
+ */
+static void _dpu_plane_set_qos_lut(struct drm_plane *plane,
+		struct drm_framebuffer *fb, struct dpu_hw_pipe_cfg *pipe_cfg)
+{
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	const struct dpu_format *fmt = NULL;
+	u64 qos_lut;
+	u32 total_fl = 0, lut_usage;
+
+	if (!pdpu->is_rt_pipe) {
+		lut_usage = DPU_QOS_LUT_USAGE_NRT;
+	} else {
+		fmt = dpu_get_dpu_format_ext(
+				fb->format->format,
+				fb->modifier);
+		total_fl = _dpu_plane_calc_fill_level(plane, fmt,
+				drm_rect_width(&pipe_cfg->src_rect));
+
+		if (fmt && DPU_FORMAT_IS_LINEAR(fmt))
+			lut_usage = DPU_QOS_LUT_USAGE_LINEAR;
+		else
+			lut_usage = DPU_QOS_LUT_USAGE_MACROTILE;
+	}
+
+	qos_lut = _dpu_hw_get_qos_lut(
+			&pdpu->catalog->perf->qos_lut_tbl[lut_usage], total_fl);
+
+	trace_dpu_perf_set_qos_luts(pdpu->pipe - SSPP_VIG0,
+			(fmt) ? fmt->base.pixel_format : 0,
+			pdpu->is_rt_pipe, total_fl, qos_lut, lut_usage);
+
+	DPU_DEBUG_PLANE(pdpu, "pnum:%d fmt: %4.4s rt:%d fl:%u lut:0x%llx\n",
+			pdpu->pipe - SSPP_VIG0,
+			fmt ? (char *)&fmt->base.pixel_format : NULL,
+			pdpu->is_rt_pipe, total_fl, qos_lut);
+
+	pdpu->pipe_hw->ops.setup_creq_lut(pdpu->pipe_hw, qos_lut);
+}
+
+/**
+ * _dpu_plane_set_danger_lut - set danger/safe LUT of the given plane
+ * @plane:		Pointer to drm plane
+ * @fb:			Pointer to framebuffer associated with the given plane
+ */
+static void _dpu_plane_set_danger_lut(struct drm_plane *plane,
+		struct drm_framebuffer *fb)
+{
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	const struct dpu_format *fmt = NULL;
+	u32 danger_lut, safe_lut;
+
+	if (!pdpu->is_rt_pipe) {
+		danger_lut = pdpu->catalog->perf->danger_lut_tbl
+				[DPU_QOS_LUT_USAGE_NRT];
+		safe_lut = pdpu->catalog->perf->safe_lut_tbl
+				[DPU_QOS_LUT_USAGE_NRT];
+	} else {
+		fmt = dpu_get_dpu_format_ext(
+				fb->format->format,
+				fb->modifier);
+
+		if (fmt && DPU_FORMAT_IS_LINEAR(fmt)) {
+			danger_lut = pdpu->catalog->perf->danger_lut_tbl
+					[DPU_QOS_LUT_USAGE_LINEAR];
+			safe_lut = pdpu->catalog->perf->safe_lut_tbl
+					[DPU_QOS_LUT_USAGE_LINEAR];
+		} else {
+			danger_lut = pdpu->catalog->perf->danger_lut_tbl
+					[DPU_QOS_LUT_USAGE_MACROTILE];
+			safe_lut = pdpu->catalog->perf->safe_lut_tbl
+					[DPU_QOS_LUT_USAGE_MACROTILE];
+		}
+	}
+
+	trace_dpu_perf_set_danger_luts(pdpu->pipe - SSPP_VIG0,
+			(fmt) ? fmt->base.pixel_format : 0,
+			(fmt) ? fmt->fetch_mode : 0,
+			danger_lut,
+			safe_lut);
+
+	DPU_DEBUG_PLANE(pdpu, "pnum:%d fmt: %4.4s mode:%d luts[0x%x, 0x%x]\n",
+		pdpu->pipe - SSPP_VIG0,
+		fmt ? (char *)&fmt->base.pixel_format : NULL,
+		fmt ? fmt->fetch_mode : -1,
+		danger_lut,
+		safe_lut);
+
+	pdpu->pipe_hw->ops.setup_danger_safe_lut(pdpu->pipe_hw,
+			danger_lut, safe_lut);
+}
+
+/**
+ * _dpu_plane_set_qos_ctrl - set QoS control of the given plane
+ * @plane:		Pointer to drm plane
+ * @enable:		true to enable QoS control
+ * @flags:		QoS control mode (enum dpu_plane_qos)
+ */
+static void _dpu_plane_set_qos_ctrl(struct drm_plane *plane,
+	bool enable, u32 flags)
+{
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_hw_pipe_qos_cfg pipe_qos_cfg;
+
+	memset(&pipe_qos_cfg, 0, sizeof(pipe_qos_cfg));
+
+	if (flags & DPU_PLANE_QOS_VBLANK_CTRL) {
+		pipe_qos_cfg.creq_vblank = pdpu->pipe_hw->cap->sblk->creq_vblank;
+		pipe_qos_cfg.danger_vblank =
+				pdpu->pipe_hw->cap->sblk->danger_vblank;
+		pipe_qos_cfg.vblank_en = enable;
+	}
+
+	if (flags & DPU_PLANE_QOS_VBLANK_AMORTIZE) {
+		/* this feature overrules previous VBLANK_CTRL */
+		pipe_qos_cfg.vblank_en = false;
+		pipe_qos_cfg.creq_vblank = 0; /* clear vblank bits */
+	}
+
+	if (flags & DPU_PLANE_QOS_PANIC_CTRL)
+		pipe_qos_cfg.danger_safe_en = enable;
+
+	if (!pdpu->is_rt_pipe) {
+		pipe_qos_cfg.vblank_en = false;
+		pipe_qos_cfg.danger_safe_en = false;
+	}
+
+	DPU_DEBUG_PLANE(pdpu, "pnum:%d ds:%d vb:%d pri[0x%x, 0x%x] is_rt:%d\n",
+		pdpu->pipe - SSPP_VIG0,
+		pipe_qos_cfg.danger_safe_en,
+		pipe_qos_cfg.vblank_en,
+		pipe_qos_cfg.creq_vblank,
+		pipe_qos_cfg.danger_vblank,
+		pdpu->is_rt_pipe);
+
+	pdpu->pipe_hw->ops.setup_qos_ctrl(pdpu->pipe_hw,
+			&pipe_qos_cfg);
+}
+
+/**
+ * _dpu_plane_set_ot_limit - set OT limit for the given plane
+ * @plane:		Pointer to drm plane
+ * @crtc:		Pointer to drm crtc
+ * @pipe_cfg:		Pointer to pipe configuration
+ */
+static void _dpu_plane_set_ot_limit(struct drm_plane *plane,
+		struct drm_crtc *crtc, struct dpu_hw_pipe_cfg *pipe_cfg)
+{
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_vbif_set_ot_params ot_params;
+	struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane);
+
+	memset(&ot_params, 0, sizeof(ot_params));
+	ot_params.xin_id = pdpu->pipe_hw->cap->xin_id;
+	ot_params.num = pdpu->pipe_hw->idx - SSPP_NONE;
+	ot_params.width = drm_rect_width(&pipe_cfg->src_rect);
+	ot_params.height = drm_rect_height(&pipe_cfg->src_rect);
+	ot_params.is_wfd = !pdpu->is_rt_pipe;
+	ot_params.frame_rate = drm_mode_vrefresh(&crtc->mode);
+	ot_params.vbif_idx = VBIF_RT;
+	ot_params.clk_ctrl = pdpu->pipe_hw->cap->clk_ctrl;
+	ot_params.rd = true;
+
+	dpu_vbif_set_ot_limit(dpu_kms, &ot_params);
+}
+
+/**
+ * _dpu_plane_set_qos_remap - set vbif QoS for the given plane
+ * @plane:		Pointer to drm plane
+ */
+static void _dpu_plane_set_qos_remap(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_vbif_set_qos_params qos_params;
+	struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane);
+
+	memset(&qos_params, 0, sizeof(qos_params));
+	qos_params.vbif_idx = VBIF_RT;
+	qos_params.clk_ctrl = pdpu->pipe_hw->cap->clk_ctrl;
+	qos_params.xin_id = pdpu->pipe_hw->cap->xin_id;
+	qos_params.num = pdpu->pipe_hw->idx - SSPP_VIG0;
+	qos_params.is_rt = pdpu->is_rt_pipe;
+
+	DPU_DEBUG_PLANE(pdpu, "pipe:%d vbif:%d xin:%d rt:%d, clk_ctrl:%d\n",
+			qos_params.num,
+			qos_params.vbif_idx,
+			qos_params.xin_id, qos_params.is_rt,
+			qos_params.clk_ctrl);
+
+	dpu_vbif_set_qos_remap(dpu_kms, &qos_params);
+}
+
+static void _dpu_plane_set_scanout(struct drm_plane *plane,
+		struct dpu_plane_state *pstate,
+		struct dpu_hw_pipe_cfg *pipe_cfg,
+		struct drm_framebuffer *fb)
+{
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base);
+	struct msm_gem_address_space *aspace = kms->base.aspace;
+	int ret;
+
+	ret = dpu_format_populate_layout(aspace, fb, &pipe_cfg->layout);
+	if (ret == -EAGAIN)
+		DPU_DEBUG_PLANE(pdpu, "not updating same src addrs\n");
+	else if (ret)
+		DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret);
+	else if (pdpu->pipe_hw->ops.setup_sourceaddress) {
+		trace_dpu_plane_set_scanout(pdpu->pipe_hw->idx,
+					    &pipe_cfg->layout,
+					    pstate->multirect_index);
+		pdpu->pipe_hw->ops.setup_sourceaddress(pdpu->pipe_hw, pipe_cfg,
+						pstate->multirect_index);
+	}
+}
+
+static void _dpu_plane_setup_scaler3(struct dpu_plane *pdpu,
+		struct dpu_plane_state *pstate,
+		uint32_t src_w, uint32_t src_h, uint32_t dst_w, uint32_t dst_h,
+		struct dpu_hw_scaler3_cfg *scale_cfg,
+		const struct dpu_format *fmt,
+		uint32_t chroma_subsmpl_h, uint32_t chroma_subsmpl_v)
+{
+	uint32_t i;
+	bool inline_rotation = pstate->rotation & DRM_MODE_ROTATE_90;
+
+	/*
+	 * For inline rotation cases, scaler config is post-rotation,
+	 * so swap the dimensions here. However, pixel extension will
+	 * need pre-rotation settings.
+	 */
+	if (inline_rotation)
+		swap(src_w, src_h);
+
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_0] =
+		mult_frac((1 << PHASE_STEP_SHIFT), src_w, dst_w);
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_0] =
+		mult_frac((1 << PHASE_STEP_SHIFT), src_h, dst_h);
+
+
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_1_2] =
+		scale_cfg->phase_step_y[DPU_SSPP_COMP_0] / chroma_subsmpl_v;
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_1_2] =
+		scale_cfg->phase_step_x[DPU_SSPP_COMP_0] / chroma_subsmpl_h;
+
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_2] =
+		scale_cfg->phase_step_x[DPU_SSPP_COMP_1_2];
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_2] =
+		scale_cfg->phase_step_y[DPU_SSPP_COMP_1_2];
+
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_3] =
+		scale_cfg->phase_step_x[DPU_SSPP_COMP_0];
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_3] =
+		scale_cfg->phase_step_y[DPU_SSPP_COMP_0];
+
+	for (i = 0; i < DPU_MAX_PLANES; i++) {
+		scale_cfg->src_width[i] = src_w;
+		scale_cfg->src_height[i] = src_h;
+		if (i == DPU_SSPP_COMP_1_2 || i == DPU_SSPP_COMP_2) {
+			scale_cfg->src_width[i] /= chroma_subsmpl_h;
+			scale_cfg->src_height[i] /= chroma_subsmpl_v;
+		}
+
+		if (pdpu->pipe_hw->cap->features &
+			BIT(DPU_SSPP_SCALER_QSEED4)) {
+			scale_cfg->preload_x[i] = DPU_QSEED4_DEFAULT_PRELOAD_H;
+			scale_cfg->preload_y[i] = DPU_QSEED4_DEFAULT_PRELOAD_V;
+		} else {
+			scale_cfg->preload_x[i] = DPU_QSEED3_DEFAULT_PRELOAD_H;
+			scale_cfg->preload_y[i] = DPU_QSEED3_DEFAULT_PRELOAD_V;
+		}
+	}
+	if (!(DPU_FORMAT_IS_YUV(fmt)) && (src_h == dst_h)
+		&& (src_w == dst_w))
+		return;
+
+	scale_cfg->dst_width = dst_w;
+	scale_cfg->dst_height = dst_h;
+	scale_cfg->y_rgb_filter_cfg = DPU_SCALE_BIL;
+	scale_cfg->uv_filter_cfg = DPU_SCALE_BIL;
+	scale_cfg->alpha_filter_cfg = DPU_SCALE_ALPHA_BIL;
+	scale_cfg->lut_flag = 0;
+	scale_cfg->blend_cfg = 1;
+	scale_cfg->enable = 1;
+}
+
+static void _dpu_plane_setup_pixel_ext(struct dpu_hw_scaler3_cfg *scale_cfg,
+				struct dpu_hw_pixel_ext *pixel_ext,
+				uint32_t src_w, uint32_t src_h,
+				uint32_t chroma_subsmpl_h, uint32_t chroma_subsmpl_v)
+{
+	int i;
+
+	for (i = 0; i < DPU_MAX_PLANES; i++) {
+		if (i == DPU_SSPP_COMP_1_2 || i == DPU_SSPP_COMP_2) {
+			src_w /= chroma_subsmpl_h;
+			src_h /= chroma_subsmpl_v;
+		}
+
+		pixel_ext->num_ext_pxls_top[i] = src_h;
+		pixel_ext->num_ext_pxls_left[i] = src_w;
+	}
+}
+
+static const struct dpu_csc_cfg dpu_csc_YUV2RGB_601L = {
+	{
+		/* S15.16 format */
+		0x00012A00, 0x00000000, 0x00019880,
+		0x00012A00, 0xFFFF9B80, 0xFFFF3000,
+		0x00012A00, 0x00020480, 0x00000000,
+	},
+	/* signed bias */
+	{ 0xfff0, 0xff80, 0xff80,},
+	{ 0x0, 0x0, 0x0,},
+	/* unsigned clamp */
+	{ 0x10, 0xeb, 0x10, 0xf0, 0x10, 0xf0,},
+	{ 0x00, 0xff, 0x00, 0xff, 0x00, 0xff,},
+};
+
+static const struct dpu_csc_cfg dpu_csc10_YUV2RGB_601L = {
+	{
+		/* S15.16 format */
+		0x00012A00, 0x00000000, 0x00019880,
+		0x00012A00, 0xFFFF9B80, 0xFFFF3000,
+		0x00012A00, 0x00020480, 0x00000000,
+		},
+	/* signed bias */
+	{ 0xffc0, 0xfe00, 0xfe00,},
+	{ 0x0, 0x0, 0x0,},
+	/* unsigned clamp */
+	{ 0x40, 0x3ac, 0x40, 0x3c0, 0x40, 0x3c0,},
+	{ 0x00, 0x3ff, 0x00, 0x3ff, 0x00, 0x3ff,},
+};
+
+static const struct dpu_csc_cfg *_dpu_plane_get_csc(struct dpu_plane *pdpu, const struct dpu_format *fmt)
+{
+	const struct dpu_csc_cfg *csc_ptr;
+
+	if (!pdpu) {
+		DPU_ERROR("invalid plane\n");
+		return NULL;
+	}
+
+	if (!DPU_FORMAT_IS_YUV(fmt))
+		return NULL;
+
+	if (BIT(DPU_SSPP_CSC_10BIT) & pdpu->pipe_hw->cap->features)
+		csc_ptr = &dpu_csc10_YUV2RGB_601L;
+	else
+		csc_ptr = &dpu_csc_YUV2RGB_601L;
+
+	DPU_DEBUG_PLANE(pdpu, "using 0x%X 0x%X 0x%X...\n",
+			csc_ptr->csc_mv[0],
+			csc_ptr->csc_mv[1],
+			csc_ptr->csc_mv[2]);
+
+	return csc_ptr;
+}
+
+static void _dpu_plane_setup_scaler(struct dpu_plane *pdpu,
+		struct dpu_plane_state *pstate,
+		const struct dpu_format *fmt, bool color_fill,
+		struct dpu_hw_pipe_cfg *pipe_cfg)
+{
+	const struct drm_format_info *info = drm_format_info(fmt->base.pixel_format);
+	struct dpu_hw_scaler3_cfg scaler3_cfg;
+	struct dpu_hw_pixel_ext pixel_ext;
+	u32 src_width = drm_rect_width(&pipe_cfg->src_rect);
+	u32 src_height = drm_rect_height(&pipe_cfg->src_rect);
+	u32 dst_width = drm_rect_width(&pipe_cfg->dst_rect);
+	u32 dst_height = drm_rect_height(&pipe_cfg->dst_rect);
+
+	memset(&scaler3_cfg, 0, sizeof(scaler3_cfg));
+	memset(&pixel_ext, 0, sizeof(pixel_ext));
+
+	/* don't chroma subsample if decimating */
+	/* update scaler. calculate default config for QSEED3 */
+	_dpu_plane_setup_scaler3(pdpu, pstate,
+			src_width,
+			src_height,
+			dst_width,
+			dst_height,
+			&scaler3_cfg, fmt,
+			info->hsub, info->vsub);
+
+	/* configure pixel extension based on scalar config */
+	_dpu_plane_setup_pixel_ext(&scaler3_cfg, &pixel_ext,
+			src_width, src_height, info->hsub, info->vsub);
+
+	if (pdpu->pipe_hw->ops.setup_pe)
+		pdpu->pipe_hw->ops.setup_pe(pdpu->pipe_hw,
+				&pixel_ext);
+
+	/**
+	 * when programmed in multirect mode, scalar block will be
+	 * bypassed. Still we need to update alpha and bitwidth
+	 * ONLY for RECT0
+	 */
+	if (pdpu->pipe_hw->ops.setup_scaler &&
+			pstate->multirect_index != DPU_SSPP_RECT_1)
+		pdpu->pipe_hw->ops.setup_scaler(pdpu->pipe_hw,
+				pipe_cfg,
+				&scaler3_cfg);
+}
+
+/**
+ * _dpu_plane_color_fill - enables color fill on plane
+ * @pdpu:   Pointer to DPU plane object
+ * @color:  RGB fill color value, [23..16] Blue, [15..8] Green, [7..0] Red
+ * @alpha:  8-bit fill alpha value, 255 selects 100% alpha
+ * Returns: 0 on success
+ */
+static int _dpu_plane_color_fill(struct dpu_plane *pdpu,
+		uint32_t color, uint32_t alpha)
+{
+	const struct dpu_format *fmt;
+	const struct drm_plane *plane = &pdpu->base;
+	struct dpu_plane_state *pstate = to_dpu_plane_state(plane->state);
+	struct dpu_hw_pipe_cfg pipe_cfg;
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	/*
+	 * select fill format to match user property expectation,
+	 * h/w only supports RGB variants
+	 */
+	fmt = dpu_get_dpu_format(DRM_FORMAT_ABGR8888);
+
+	/* update sspp */
+	if (fmt && pdpu->pipe_hw->ops.setup_solidfill) {
+		pdpu->pipe_hw->ops.setup_solidfill(pdpu->pipe_hw,
+				(color & 0xFFFFFF) | ((alpha & 0xFF) << 24),
+				pstate->multirect_index);
+
+		/* override scaler/decimation if solid fill */
+		pipe_cfg.dst_rect = pstate->base.dst;
+
+		pipe_cfg.src_rect.x1 = 0;
+		pipe_cfg.src_rect.y1 = 0;
+		pipe_cfg.src_rect.x2 =
+			drm_rect_width(&pipe_cfg.dst_rect);
+		pipe_cfg.src_rect.y2 =
+			drm_rect_height(&pipe_cfg.dst_rect);
+
+		if (pdpu->pipe_hw->ops.setup_format)
+			pdpu->pipe_hw->ops.setup_format(pdpu->pipe_hw,
+					fmt, DPU_SSPP_SOLID_FILL,
+					pstate->multirect_index);
+
+		if (pdpu->pipe_hw->ops.setup_rects)
+			pdpu->pipe_hw->ops.setup_rects(pdpu->pipe_hw,
+					&pipe_cfg,
+					pstate->multirect_index);
+
+		_dpu_plane_setup_scaler(pdpu, pstate, fmt, true, &pipe_cfg);
+	}
+
+	return 0;
+}
+
+void dpu_plane_clear_multirect(const struct drm_plane_state *drm_state)
+{
+	struct dpu_plane_state *pstate = to_dpu_plane_state(drm_state);
+
+	pstate->multirect_index = DPU_SSPP_RECT_SOLO;
+	pstate->multirect_mode = DPU_SSPP_MULTIRECT_NONE;
+}
+
+int dpu_plane_validate_multirect_v2(struct dpu_multirect_plane_states *plane)
+{
+	struct dpu_plane_state *pstate[R_MAX];
+	const struct drm_plane_state *drm_state[R_MAX];
+	struct drm_rect src[R_MAX], dst[R_MAX];
+	struct dpu_plane *dpu_plane[R_MAX];
+	const struct dpu_format *fmt[R_MAX];
+	int i, buffer_lines;
+	unsigned int max_tile_height = 1;
+	bool parallel_fetch_qualified = true;
+	bool has_tiled_rect = false;
+
+	for (i = 0; i < R_MAX; i++) {
+		const struct msm_format *msm_fmt;
+
+		drm_state[i] = i ? plane->r1 : plane->r0;
+		msm_fmt = msm_framebuffer_format(drm_state[i]->fb);
+		fmt[i] = to_dpu_format(msm_fmt);
+
+		if (DPU_FORMAT_IS_UBWC(fmt[i])) {
+			has_tiled_rect = true;
+			if (fmt[i]->tile_height > max_tile_height)
+				max_tile_height = fmt[i]->tile_height;
+		}
+	}
+
+	for (i = 0; i < R_MAX; i++) {
+		int width_threshold;
+
+		pstate[i] = to_dpu_plane_state(drm_state[i]);
+		dpu_plane[i] = to_dpu_plane(drm_state[i]->plane);
+
+		if (pstate[i] == NULL) {
+			DPU_ERROR("DPU plane state of plane id %d is NULL\n",
+				drm_state[i]->plane->base.id);
+			return -EINVAL;
+		}
+
+		src[i].x1 = drm_state[i]->src_x >> 16;
+		src[i].y1 = drm_state[i]->src_y >> 16;
+		src[i].x2 = src[i].x1 + (drm_state[i]->src_w >> 16);
+		src[i].y2 = src[i].y1 + (drm_state[i]->src_h >> 16);
+
+		dst[i] = drm_plane_state_dest(drm_state[i]);
+
+		if (drm_rect_calc_hscale(&src[i], &dst[i], 1, 1) != 1 ||
+		    drm_rect_calc_vscale(&src[i], &dst[i], 1, 1) != 1) {
+			DPU_ERROR_PLANE(dpu_plane[i],
+				"scaling is not supported in multirect mode\n");
+			return -EINVAL;
+		}
+
+		if (DPU_FORMAT_IS_YUV(fmt[i])) {
+			DPU_ERROR_PLANE(dpu_plane[i],
+				"Unsupported format for multirect mode\n");
+			return -EINVAL;
+		}
+
+		/**
+		 * SSPP PD_MEM is split half - one for each RECT.
+		 * Tiled formats need 5 lines of buffering while fetching
+		 * whereas linear formats need only 2 lines.
+		 * So we cannot support more than half of the supported SSPP
+		 * width for tiled formats.
+		 */
+		width_threshold = dpu_plane[i]->catalog->caps->max_linewidth;
+		if (has_tiled_rect)
+			width_threshold /= 2;
+
+		if (parallel_fetch_qualified &&
+		    drm_rect_width(&src[i]) > width_threshold)
+			parallel_fetch_qualified = false;
+
+	}
+
+	/* Validate RECT's and set the mode */
+
+	/* Prefer PARALLEL FETCH Mode over TIME_MX Mode */
+	if (parallel_fetch_qualified) {
+		pstate[R0]->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL;
+		pstate[R1]->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL;
+
+		goto done;
+	}
+
+	/* TIME_MX Mode */
+	buffer_lines = 2 * max_tile_height;
+
+	if (dst[R1].y1 >= dst[R0].y2 + buffer_lines ||
+	    dst[R0].y1 >= dst[R1].y2 + buffer_lines) {
+		pstate[R0]->multirect_mode = DPU_SSPP_MULTIRECT_TIME_MX;
+		pstate[R1]->multirect_mode = DPU_SSPP_MULTIRECT_TIME_MX;
+	} else {
+		DPU_ERROR(
+			"No multirect mode possible for the planes (%d - %d)\n",
+			drm_state[R0]->plane->base.id,
+			drm_state[R1]->plane->base.id);
+		return -EINVAL;
+	}
+
+done:
+	pstate[R0]->multirect_index = DPU_SSPP_RECT_0;
+	pstate[R1]->multirect_index = DPU_SSPP_RECT_1;
+
+	DPU_DEBUG_PLANE(dpu_plane[R0], "R0: %d - %d\n",
+		pstate[R0]->multirect_mode, pstate[R0]->multirect_index);
+	DPU_DEBUG_PLANE(dpu_plane[R1], "R1: %d - %d\n",
+		pstate[R1]->multirect_mode, pstate[R1]->multirect_index);
+	return 0;
+}
+
+static int dpu_plane_prepare_fb(struct drm_plane *plane,
+		struct drm_plane_state *new_state)
+{
+	struct drm_framebuffer *fb = new_state->fb;
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_plane_state *pstate = to_dpu_plane_state(new_state);
+	struct dpu_hw_fmt_layout layout;
+	struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base);
+	int ret;
+
+	if (!new_state->fb)
+		return 0;
+
+	DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", fb->base.id);
+
+	/* cache aspace */
+	pstate->aspace = kms->base.aspace;
+
+	/*
+	 * TODO: Need to sort out the msm_framebuffer_prepare() call below so
+	 *       we can use msm_atomic_prepare_fb() instead of doing the
+	 *       implicit fence and fb prepare by hand here.
+	 */
+	drm_gem_plane_helper_prepare_fb(plane, new_state);
+
+	if (pstate->aspace) {
+		ret = msm_framebuffer_prepare(new_state->fb,
+				pstate->aspace, pstate->needs_dirtyfb);
+		if (ret) {
+			DPU_ERROR("failed to prepare framebuffer\n");
+			return ret;
+		}
+	}
+
+	/* validate framebuffer layout before commit */
+	ret = dpu_format_populate_layout(pstate->aspace,
+			new_state->fb, &layout);
+	if (ret) {
+		DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void dpu_plane_cleanup_fb(struct drm_plane *plane,
+		struct drm_plane_state *old_state)
+{
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_plane_state *old_pstate;
+
+	if (!old_state || !old_state->fb)
+		return;
+
+	old_pstate = to_dpu_plane_state(old_state);
+
+	DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", old_state->fb->base.id);
+
+	msm_framebuffer_cleanup(old_state->fb, old_pstate->aspace,
+				old_pstate->needs_dirtyfb);
+}
+
+static bool dpu_plane_validate_src(struct drm_rect *src,
+				   struct drm_rect *fb_rect,
+				   uint32_t min_src_size)
+{
+	/* Ensure fb size is supported */
+	if (drm_rect_width(fb_rect) > MAX_IMG_WIDTH ||
+	    drm_rect_height(fb_rect) > MAX_IMG_HEIGHT)
+		return false;
+
+	/* Ensure src rect is above the minimum size */
+	if (drm_rect_width(src) < min_src_size ||
+	    drm_rect_height(src) < min_src_size)
+		return false;
+
+	/* Ensure src is fully encapsulated in fb */
+	return drm_rect_intersect(fb_rect, src) &&
+		drm_rect_equals(fb_rect, src);
+}
+
+static int dpu_plane_check_inline_rotation(struct dpu_plane *pdpu,
+						const struct dpu_sspp_sub_blks *sblk,
+						struct drm_rect src, const struct dpu_format *fmt)
+{
+	size_t num_formats;
+	const u32 *supported_formats;
+
+	if (!sblk->rotation_cfg) {
+		DPU_ERROR("invalid rotation cfg\n");
+		return -EINVAL;
+	}
+
+	if (drm_rect_width(&src) > sblk->rotation_cfg->rot_maxheight) {
+		DPU_DEBUG_PLANE(pdpu, "invalid height for inline rot:%d max:%d\n",
+				src.y2, sblk->rotation_cfg->rot_maxheight);
+		return -EINVAL;
+	}
+
+	supported_formats = sblk->rotation_cfg->rot_format_list;
+	num_formats = sblk->rotation_cfg->rot_num_formats;
+
+	if (!DPU_FORMAT_IS_UBWC(fmt) ||
+		!dpu_find_format(fmt->base.pixel_format, supported_formats, num_formats))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int dpu_plane_atomic_check(struct drm_plane *plane,
+				  struct drm_atomic_state *state)
+{
+	struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state,
+										 plane);
+	int ret = 0, min_scale;
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_plane_state *pstate = to_dpu_plane_state(new_plane_state);
+	const struct drm_crtc_state *crtc_state = NULL;
+	const struct dpu_format *fmt;
+	struct drm_rect src, dst, fb_rect = { 0 };
+	uint32_t min_src_size, max_linewidth;
+	unsigned int rotation;
+	uint32_t supported_rotations;
+	const struct dpu_sspp_cfg *pipe_hw_caps = pdpu->pipe_hw->cap;
+	const struct dpu_sspp_sub_blks *sblk = pdpu->pipe_hw->cap->sblk;
+
+	if (new_plane_state->crtc)
+		crtc_state = drm_atomic_get_new_crtc_state(state,
+							   new_plane_state->crtc);
+
+	min_scale = FRAC_16_16(1, sblk->maxupscale);
+	ret = drm_atomic_helper_check_plane_state(new_plane_state, crtc_state,
+						  min_scale,
+						  sblk->maxdwnscale << 16,
+						  true, true);
+	if (ret) {
+		DPU_DEBUG_PLANE(pdpu, "Check plane state failed (%d)\n", ret);
+		return ret;
+	}
+	if (!new_plane_state->visible)
+		return 0;
+
+	src.x1 = new_plane_state->src_x >> 16;
+	src.y1 = new_plane_state->src_y >> 16;
+	src.x2 = src.x1 + (new_plane_state->src_w >> 16);
+	src.y2 = src.y1 + (new_plane_state->src_h >> 16);
+
+	dst = drm_plane_state_dest(new_plane_state);
+
+	fb_rect.x2 = new_plane_state->fb->width;
+	fb_rect.y2 = new_plane_state->fb->height;
+
+	max_linewidth = pdpu->catalog->caps->max_linewidth;
+
+	fmt = to_dpu_format(msm_framebuffer_format(new_plane_state->fb));
+
+	min_src_size = DPU_FORMAT_IS_YUV(fmt) ? 2 : 1;
+
+	if (DPU_FORMAT_IS_YUV(fmt) &&
+		(!(pipe_hw_caps->features & DPU_SSPP_SCALER) ||
+		 !(pipe_hw_caps->features & DPU_SSPP_CSC_ANY))) {
+		DPU_DEBUG_PLANE(pdpu,
+				"plane doesn't have scaler/csc for yuv\n");
+		return -EINVAL;
+
+	/* check src bounds */
+	} else if (!dpu_plane_validate_src(&src, &fb_rect, min_src_size)) {
+		DPU_DEBUG_PLANE(pdpu, "invalid source " DRM_RECT_FMT "\n",
+				DRM_RECT_ARG(&src));
+		return -E2BIG;
+
+	/* valid yuv image */
+	} else if (DPU_FORMAT_IS_YUV(fmt) &&
+		   (src.x1 & 0x1 || src.y1 & 0x1 ||
+		    drm_rect_width(&src) & 0x1 ||
+		    drm_rect_height(&src) & 0x1)) {
+		DPU_DEBUG_PLANE(pdpu, "invalid yuv source " DRM_RECT_FMT "\n",
+				DRM_RECT_ARG(&src));
+		return -EINVAL;
+
+	/* min dst support */
+	} else if (drm_rect_width(&dst) < 0x1 || drm_rect_height(&dst) < 0x1) {
+		DPU_DEBUG_PLANE(pdpu, "invalid dest rect " DRM_RECT_FMT "\n",
+				DRM_RECT_ARG(&dst));
+		return -EINVAL;
+
+	/* check decimated source width */
+	} else if (drm_rect_width(&src) > max_linewidth) {
+		DPU_DEBUG_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u\n",
+				DRM_RECT_ARG(&src), max_linewidth);
+		return -E2BIG;
+	}
+
+	supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0;
+
+	if (pipe_hw_caps->features & BIT(DPU_SSPP_INLINE_ROTATION))
+		supported_rotations |= DRM_MODE_ROTATE_90;
+
+	rotation = drm_rotation_simplify(new_plane_state->rotation,
+					supported_rotations);
+
+	if ((pipe_hw_caps->features & BIT(DPU_SSPP_INLINE_ROTATION)) &&
+		(rotation & DRM_MODE_ROTATE_90)) {
+		ret = dpu_plane_check_inline_rotation(pdpu, sblk, src, fmt);
+		if (ret)
+			return ret;
+	}
+
+	pstate->rotation = rotation;
+	pstate->needs_qos_remap = drm_atomic_crtc_needs_modeset(crtc_state);
+
+	return 0;
+}
+
+void dpu_plane_flush(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+
+	if (!plane || !plane->state) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pstate = to_dpu_plane_state(plane->state);
+
+	/*
+	 * These updates have to be done immediately before the plane flush
+	 * timing, and may not be moved to the atomic_update/mode_set functions.
+	 */
+	if (pdpu->is_error)
+		/* force white frame with 100% alpha pipe output on error */
+		_dpu_plane_color_fill(pdpu, 0xFFFFFF, 0xFF);
+	else if (pdpu->color_fill & DPU_PLANE_COLOR_FILL_FLAG)
+		/* force 100% alpha */
+		_dpu_plane_color_fill(pdpu, pdpu->color_fill, 0xFF);
+	else if (pdpu->pipe_hw && pdpu->pipe_hw->ops.setup_csc) {
+		const struct dpu_format *fmt = to_dpu_format(msm_framebuffer_format(plane->state->fb));
+		const struct dpu_csc_cfg *csc_ptr = _dpu_plane_get_csc(pdpu, fmt);
+
+		if (csc_ptr)
+			pdpu->pipe_hw->ops.setup_csc(pdpu->pipe_hw, csc_ptr);
+	}
+
+	/* flag h/w flush complete */
+	if (plane->state)
+		pstate->pending = false;
+}
+
+/**
+ * dpu_plane_set_error: enable/disable error condition
+ * @plane: pointer to drm_plane structure
+ * @error: error value to set
+ */
+void dpu_plane_set_error(struct drm_plane *plane, bool error)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane)
+		return;
+
+	pdpu = to_dpu_plane(plane);
+	pdpu->is_error = error;
+}
+
+static void dpu_plane_sspp_atomic_update(struct drm_plane *plane)
+{
+	uint32_t src_flags;
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct drm_plane_state *state = plane->state;
+	struct dpu_plane_state *pstate = to_dpu_plane_state(state);
+	struct drm_crtc *crtc = state->crtc;
+	struct drm_framebuffer *fb = state->fb;
+	bool is_rt_pipe;
+	const struct dpu_format *fmt =
+		to_dpu_format(msm_framebuffer_format(fb));
+	struct dpu_hw_pipe_cfg pipe_cfg;
+
+	memset(&pipe_cfg, 0, sizeof(struct dpu_hw_pipe_cfg));
+
+	_dpu_plane_set_scanout(plane, pstate, &pipe_cfg, fb);
+
+	pstate->pending = true;
+
+	is_rt_pipe = (dpu_crtc_get_client_type(crtc) != NRT_CLIENT);
+	pstate->needs_qos_remap |= (is_rt_pipe != pdpu->is_rt_pipe);
+	pdpu->is_rt_pipe = is_rt_pipe;
+
+	_dpu_plane_set_qos_ctrl(plane, false, DPU_PLANE_QOS_PANIC_CTRL);
+
+	DPU_DEBUG_PLANE(pdpu, "FB[%u] " DRM_RECT_FP_FMT "->crtc%u " DRM_RECT_FMT
+			", %4.4s ubwc %d\n", fb->base.id, DRM_RECT_FP_ARG(&state->src),
+			crtc->base.id, DRM_RECT_ARG(&state->dst),
+			(char *)&fmt->base.pixel_format, DPU_FORMAT_IS_UBWC(fmt));
+
+	pipe_cfg.src_rect = state->src;
+
+	/* state->src is 16.16, src_rect is not */
+	pipe_cfg.src_rect.x1 >>= 16;
+	pipe_cfg.src_rect.x2 >>= 16;
+	pipe_cfg.src_rect.y1 >>= 16;
+	pipe_cfg.src_rect.y2 >>= 16;
+
+	pipe_cfg.dst_rect = state->dst;
+
+	/* override for color fill */
+	if (pdpu->color_fill & DPU_PLANE_COLOR_FILL_FLAG) {
+		/* skip remaining processing on color fill */
+		return;
+	}
+
+	if (pdpu->pipe_hw->ops.setup_rects) {
+		pdpu->pipe_hw->ops.setup_rects(pdpu->pipe_hw,
+				&pipe_cfg,
+				pstate->multirect_index);
+	}
+
+	_dpu_plane_setup_scaler(pdpu, pstate, fmt, false, &pipe_cfg);
+
+	if (pdpu->pipe_hw->ops.setup_multirect)
+		pdpu->pipe_hw->ops.setup_multirect(
+				pdpu->pipe_hw,
+				pstate->multirect_index,
+				pstate->multirect_mode);
+
+	if (pdpu->pipe_hw->ops.setup_format) {
+		unsigned int rotation = pstate->rotation;
+
+		src_flags = 0x0;
+
+		if (rotation & DRM_MODE_REFLECT_X)
+			src_flags |= DPU_SSPP_FLIP_LR;
+
+		if (rotation & DRM_MODE_REFLECT_Y)
+			src_flags |= DPU_SSPP_FLIP_UD;
+
+		if (rotation & DRM_MODE_ROTATE_90)
+			src_flags |= DPU_SSPP_ROT_90;
+
+		/* update format */
+		pdpu->pipe_hw->ops.setup_format(pdpu->pipe_hw, fmt, src_flags,
+				pstate->multirect_index);
+
+		if (pdpu->pipe_hw->ops.setup_cdp) {
+			struct dpu_hw_cdp_cfg cdp_cfg;
+
+			memset(&cdp_cfg, 0, sizeof(struct dpu_hw_cdp_cfg));
+
+			cdp_cfg.enable = pdpu->catalog->perf->cdp_cfg
+					[DPU_PERF_CDP_USAGE_RT].rd_enable;
+			cdp_cfg.ubwc_meta_enable =
+					DPU_FORMAT_IS_UBWC(fmt);
+			cdp_cfg.tile_amortize_enable =
+					DPU_FORMAT_IS_UBWC(fmt) ||
+					DPU_FORMAT_IS_TILE(fmt);
+			cdp_cfg.preload_ahead = DPU_SSPP_CDP_PRELOAD_AHEAD_64;
+
+			pdpu->pipe_hw->ops.setup_cdp(pdpu->pipe_hw, &cdp_cfg, pstate->multirect_index);
+		}
+	}
+
+	_dpu_plane_set_qos_lut(plane, fb, &pipe_cfg);
+	_dpu_plane_set_danger_lut(plane, fb);
+
+	if (plane->type != DRM_PLANE_TYPE_CURSOR) {
+		_dpu_plane_set_qos_ctrl(plane, true, DPU_PLANE_QOS_PANIC_CTRL);
+		_dpu_plane_set_ot_limit(plane, crtc, &pipe_cfg);
+	}
+
+	if (pstate->needs_qos_remap) {
+		pstate->needs_qos_remap = false;
+		_dpu_plane_set_qos_remap(plane);
+	}
+
+	_dpu_plane_calc_bw(plane, fb, &pipe_cfg);
+
+	_dpu_plane_calc_clk(plane, &pipe_cfg);
+}
+
+static void _dpu_plane_atomic_disable(struct drm_plane *plane)
+{
+	struct drm_plane_state *state = plane->state;
+	struct dpu_plane_state *pstate = to_dpu_plane_state(state);
+
+	trace_dpu_plane_disable(DRMID(plane), false,
+				pstate->multirect_mode);
+
+	pstate->pending = true;
+}
+
+static void dpu_plane_atomic_update(struct drm_plane *plane,
+				struct drm_atomic_state *state)
+{
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state,
+									   plane);
+
+	pdpu->is_error = false;
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	if (!new_state->visible) {
+		_dpu_plane_atomic_disable(plane);
+	} else {
+		dpu_plane_sspp_atomic_update(plane);
+	}
+}
+
+static void dpu_plane_destroy(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu = plane ? to_dpu_plane(plane) : NULL;
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	if (pdpu) {
+		_dpu_plane_set_qos_ctrl(plane, false, DPU_PLANE_QOS_PANIC_CTRL);
+
+		mutex_destroy(&pdpu->lock);
+
+		/* this will destroy the states as well */
+		drm_plane_cleanup(plane);
+
+		dpu_hw_sspp_destroy(pdpu->pipe_hw);
+
+		kfree(pdpu);
+	}
+}
+
+static void dpu_plane_destroy_state(struct drm_plane *plane,
+		struct drm_plane_state *state)
+{
+	__drm_atomic_helper_plane_destroy_state(state);
+	kfree(to_dpu_plane_state(state));
+}
+
+static struct drm_plane_state *
+dpu_plane_duplicate_state(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+	struct dpu_plane_state *old_state;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return NULL;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return NULL;
+	}
+
+	old_state = to_dpu_plane_state(plane->state);
+	pdpu = to_dpu_plane(plane);
+	pstate = kmemdup(old_state, sizeof(*old_state), GFP_KERNEL);
+	if (!pstate) {
+		DPU_ERROR_PLANE(pdpu, "failed to allocate state\n");
+		return NULL;
+	}
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	pstate->pending = false;
+
+	__drm_atomic_helper_plane_duplicate_state(plane, &pstate->base);
+
+	return &pstate->base;
+}
+
+static const char * const multirect_mode_name[] = {
+	[DPU_SSPP_MULTIRECT_NONE] = "none",
+	[DPU_SSPP_MULTIRECT_PARALLEL] = "parallel",
+	[DPU_SSPP_MULTIRECT_TIME_MX] = "time_mx",
+};
+
+static const char * const multirect_index_name[] = {
+	[DPU_SSPP_RECT_SOLO] = "solo",
+	[DPU_SSPP_RECT_0] = "rect_0",
+	[DPU_SSPP_RECT_1] = "rect_1",
+};
+
+static const char *dpu_get_multirect_mode(enum dpu_sspp_multirect_mode mode)
+{
+	if (WARN_ON(mode >= ARRAY_SIZE(multirect_mode_name)))
+		return "unknown";
+
+	return multirect_mode_name[mode];
+}
+
+static const char *dpu_get_multirect_index(enum dpu_sspp_multirect_index index)
+{
+	if (WARN_ON(index >= ARRAY_SIZE(multirect_index_name)))
+		return "unknown";
+
+	return multirect_index_name[index];
+}
+
+static void dpu_plane_atomic_print_state(struct drm_printer *p,
+		const struct drm_plane_state *state)
+{
+	const struct dpu_plane_state *pstate = to_dpu_plane_state(state);
+	const struct dpu_plane *pdpu = to_dpu_plane(state->plane);
+
+	drm_printf(p, "\tstage=%d\n", pstate->stage);
+	drm_printf(p, "\tsspp=%s\n", pdpu->pipe_hw->cap->name);
+	drm_printf(p, "\tmultirect_mode=%s\n", dpu_get_multirect_mode(pstate->multirect_mode));
+	drm_printf(p, "\tmultirect_index=%s\n", dpu_get_multirect_index(pstate->multirect_index));
+}
+
+static void dpu_plane_reset(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	/* remove previous state, if present */
+	if (plane->state) {
+		dpu_plane_destroy_state(plane, plane->state);
+		plane->state = NULL;
+	}
+
+	pstate = kzalloc(sizeof(*pstate), GFP_KERNEL);
+	if (!pstate) {
+		DPU_ERROR_PLANE(pdpu, "failed to allocate state\n");
+		return;
+	}
+
+	__drm_atomic_helper_plane_reset(plane, &pstate->base);
+}
+
+#ifdef CONFIG_DEBUG_FS
+void dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable)
+{
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane);
+
+	if (!pdpu->is_rt_pipe)
+		return;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	_dpu_plane_set_qos_ctrl(plane, enable, DPU_PLANE_QOS_PANIC_CTRL);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+}
+
+/* SSPP live inside dpu_plane private data only. Enumerate them here. */
+void dpu_debugfs_sspp_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
+{
+	struct drm_plane *plane;
+	struct dentry *entry = debugfs_create_dir("sspp", debugfs_root);
+
+	if (IS_ERR(entry))
+		return;
+
+	drm_for_each_plane(plane, dpu_kms->dev) {
+		struct dpu_plane *pdpu = to_dpu_plane(plane);
+
+		_dpu_hw_sspp_init_debugfs(pdpu->pipe_hw, dpu_kms, entry);
+	}
+}
+#endif
+
+static bool dpu_plane_format_mod_supported(struct drm_plane *plane,
+		uint32_t format, uint64_t modifier)
+{
+	if (modifier == DRM_FORMAT_MOD_LINEAR)
+		return true;
+
+	if (modifier == DRM_FORMAT_MOD_QCOM_COMPRESSED)
+		return dpu_find_format(format, qcom_compressed_supported_formats,
+				ARRAY_SIZE(qcom_compressed_supported_formats));
+
+	return false;
+}
+
+static const struct drm_plane_funcs dpu_plane_funcs = {
+		.update_plane = drm_atomic_helper_update_plane,
+		.disable_plane = drm_atomic_helper_disable_plane,
+		.destroy = dpu_plane_destroy,
+		.reset = dpu_plane_reset,
+		.atomic_duplicate_state = dpu_plane_duplicate_state,
+		.atomic_destroy_state = dpu_plane_destroy_state,
+		.atomic_print_state = dpu_plane_atomic_print_state,
+		.format_mod_supported = dpu_plane_format_mod_supported,
+};
+
+static const struct drm_plane_helper_funcs dpu_plane_helper_funcs = {
+		.prepare_fb = dpu_plane_prepare_fb,
+		.cleanup_fb = dpu_plane_cleanup_fb,
+		.atomic_check = dpu_plane_atomic_check,
+		.atomic_update = dpu_plane_atomic_update,
+};
+
+enum dpu_sspp dpu_plane_pipe(struct drm_plane *plane)
+{
+	return plane ? to_dpu_plane(plane)->pipe : SSPP_NONE;
+}
+
+/* initialize plane */
+struct drm_plane *dpu_plane_init(struct drm_device *dev,
+		uint32_t pipe, enum drm_plane_type type,
+		unsigned long possible_crtcs)
+{
+	struct drm_plane *plane = NULL;
+	const uint32_t *format_list;
+	struct dpu_plane *pdpu;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct dpu_kms *kms = to_dpu_kms(priv->kms);
+	uint32_t num_formats;
+	uint32_t supported_rotations;
+	int ret = -EINVAL;
+
+	/* create and zero local structure */
+	pdpu = kzalloc(sizeof(*pdpu), GFP_KERNEL);
+	if (!pdpu) {
+		DPU_ERROR("[%u]failed to allocate local plane struct\n", pipe);
+		ret = -ENOMEM;
+		return ERR_PTR(ret);
+	}
+
+	/* cache local stuff for later */
+	plane = &pdpu->base;
+	pdpu->pipe = pipe;
+
+	/* initialize underlying h/w driver */
+	pdpu->pipe_hw = dpu_hw_sspp_init(pipe, kms->mmio, kms->catalog);
+	if (IS_ERR(pdpu->pipe_hw)) {
+		DPU_ERROR("[%u]SSPP init failed\n", pipe);
+		ret = PTR_ERR(pdpu->pipe_hw);
+		goto clean_plane;
+	} else if (!pdpu->pipe_hw->cap || !pdpu->pipe_hw->cap->sblk) {
+		DPU_ERROR("[%u]SSPP init returned invalid cfg\n", pipe);
+		goto clean_sspp;
+	}
+
+	format_list = pdpu->pipe_hw->cap->sblk->format_list;
+	num_formats = pdpu->pipe_hw->cap->sblk->num_formats;
+
+	ret = drm_universal_plane_init(dev, plane, 0xff, &dpu_plane_funcs,
+				format_list, num_formats,
+				supported_format_modifiers, type, NULL);
+	if (ret)
+		goto clean_sspp;
+
+	pdpu->catalog = kms->catalog;
+
+	ret = drm_plane_create_zpos_property(plane, 0, 0, DPU_ZPOS_MAX);
+	if (ret)
+		DPU_ERROR("failed to install zpos property, rc = %d\n", ret);
+
+	drm_plane_create_alpha_property(plane);
+	drm_plane_create_blend_mode_property(plane,
+			BIT(DRM_MODE_BLEND_PIXEL_NONE) |
+			BIT(DRM_MODE_BLEND_PREMULTI) |
+			BIT(DRM_MODE_BLEND_COVERAGE));
+
+	supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180;
+
+	if (pdpu->pipe_hw->cap->features & BIT(DPU_SSPP_INLINE_ROTATION))
+		supported_rotations |= DRM_MODE_ROTATE_MASK;
+
+	drm_plane_create_rotation_property(plane,
+		    DRM_MODE_ROTATE_0, supported_rotations);
+
+	drm_plane_enable_fb_damage_clips(plane);
+
+	/* success! finalize initialization */
+	drm_plane_helper_add(plane, &dpu_plane_helper_funcs);
+
+	mutex_init(&pdpu->lock);
+
+	DPU_DEBUG("%s created for pipe:%u id:%u\n", plane->name,
+					pipe, plane->base.id);
+	return plane;
+
+clean_sspp:
+	if (pdpu && pdpu->pipe_hw)
+		dpu_hw_sspp_destroy(pdpu->pipe_hw);
+clean_plane:
+	kfree(pdpu);
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h
new file mode 100644
index 000000000..b7b1b0519
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#ifndef _DPU_PLANE_H_
+#define _DPU_PLANE_H_
+
+#include <drm/drm_crtc.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_sspp.h"
+
+/**
+ * struct dpu_plane_state: Define dpu extension of drm plane state object
+ * @base:	base drm plane state object
+ * @aspace:	pointer to address space for input/output buffers
+ * @stage:	assigned by crtc blender
+ * @needs_qos_remap: qos remap settings need to be updated
+ * @multirect_index: index of the rectangle of SSPP
+ * @multirect_mode: parallel or time multiplex multirect mode
+ * @pending:	whether the current update is still pending
+ * @plane_fetch_bw: calculated BW per plane
+ * @plane_clk: calculated clk per plane
+ * @needs_dirtyfb: whether attached CRTC needs pixel data explicitly flushed
+ * @rotation: simplified drm rotation hint
+ */
+struct dpu_plane_state {
+	struct drm_plane_state base;
+	struct msm_gem_address_space *aspace;
+	enum dpu_stage stage;
+	bool needs_qos_remap;
+	uint32_t multirect_index;
+	uint32_t multirect_mode;
+	bool pending;
+
+	u64 plane_fetch_bw;
+	u64 plane_clk;
+
+	bool needs_dirtyfb;
+	unsigned int rotation;
+};
+
+/**
+ * struct dpu_multirect_plane_states: Defines multirect pair of drm plane states
+ * @r0: drm plane configured on rect 0
+ * @r1: drm plane configured on rect 1
+ */
+struct dpu_multirect_plane_states {
+	const struct drm_plane_state *r0;
+	const struct drm_plane_state *r1;
+};
+
+#define to_dpu_plane_state(x) \
+	container_of(x, struct dpu_plane_state, base)
+
+/**
+ * dpu_plane_pipe - return sspp identifier for the given plane
+ * @plane:   Pointer to DRM plane object
+ * Returns: sspp identifier of the given plane
+ */
+enum dpu_sspp dpu_plane_pipe(struct drm_plane *plane);
+
+/**
+ * dpu_plane_flush - final plane operations before commit flush
+ * @plane: Pointer to drm plane structure
+ */
+void dpu_plane_flush(struct drm_plane *plane);
+
+/**
+ * dpu_plane_set_error: enable/disable error condition
+ * @plane: pointer to drm_plane structure
+ */
+void dpu_plane_set_error(struct drm_plane *plane, bool error);
+
+/**
+ * dpu_plane_init - create new dpu plane for the given pipe
+ * @dev:   Pointer to DRM device
+ * @pipe:  dpu hardware pipe identifier
+ * @type:  Plane type - PRIMARY/OVERLAY/CURSOR
+ * @possible_crtcs: bitmask of crtc that can be attached to the given pipe
+ *
+ */
+struct drm_plane *dpu_plane_init(struct drm_device *dev,
+		uint32_t pipe, enum drm_plane_type type,
+		unsigned long possible_crtcs);
+
+/**
+ * dpu_plane_validate_multirecti_v2 - validate the multirect planes
+ *				      against hw limitations
+ * @plane: drm plate states of the multirect pair
+ */
+int dpu_plane_validate_multirect_v2(struct dpu_multirect_plane_states *plane);
+
+/**
+ * dpu_plane_clear_multirect - clear multirect bits for the given pipe
+ * @drm_state: Pointer to DRM plane state
+ */
+void dpu_plane_clear_multirect(const struct drm_plane_state *drm_state);
+
+/**
+ * dpu_plane_color_fill - enables color fill on plane
+ * @plane:  Pointer to DRM plane object
+ * @color:  RGB fill color value, [23..16] Blue, [15..8] Green, [7..0] Red
+ * @alpha:  8-bit fill alpha value, 255 selects 100% alpha
+ * Returns: 0 on success
+ */
+int dpu_plane_color_fill(struct drm_plane *plane,
+		uint32_t color, uint32_t alpha);
+
+#ifdef CONFIG_DEBUG_FS
+void dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable);
+#else
+static inline void dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable) {}
+#endif
+
+#endif /* _DPU_PLANE_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
new file mode 100644
index 000000000..58abf5fe9
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -0,0 +1,674 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s] " fmt, __func__
+#include "dpu_kms.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_hw_intf.h"
+#include "dpu_hw_wb.h"
+#include "dpu_hw_dspp.h"
+#include "dpu_hw_merge3d.h"
+#include "dpu_hw_dsc.h"
+#include "dpu_encoder.h"
+#include "dpu_trace.h"
+
+
+static inline bool reserved_by_other(uint32_t *res_map, int idx,
+				     uint32_t enc_id)
+{
+	return res_map[idx] && res_map[idx] != enc_id;
+}
+
+/**
+ * struct dpu_rm_requirements - Reservation requirements parameter bundle
+ * @topology:  selected topology for the display
+ * @hw_res:	   Hardware resources required as reported by the encoders
+ */
+struct dpu_rm_requirements {
+	struct msm_display_topology topology;
+};
+
+int dpu_rm_destroy(struct dpu_rm *rm)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(rm->dspp_blks); i++) {
+		struct dpu_hw_dspp *hw;
+
+		if (rm->dspp_blks[i]) {
+			hw = to_dpu_hw_dspp(rm->dspp_blks[i]);
+			dpu_hw_dspp_destroy(hw);
+		}
+	}
+	for (i = 0; i < ARRAY_SIZE(rm->pingpong_blks); i++) {
+		struct dpu_hw_pingpong *hw;
+
+		if (rm->pingpong_blks[i]) {
+			hw = to_dpu_hw_pingpong(rm->pingpong_blks[i]);
+			dpu_hw_pingpong_destroy(hw);
+		}
+	}
+	for (i = 0; i < ARRAY_SIZE(rm->merge_3d_blks); i++) {
+		struct dpu_hw_merge_3d *hw;
+
+		if (rm->merge_3d_blks[i]) {
+			hw = to_dpu_hw_merge_3d(rm->merge_3d_blks[i]);
+			dpu_hw_merge_3d_destroy(hw);
+		}
+	}
+	for (i = 0; i < ARRAY_SIZE(rm->mixer_blks); i++) {
+		struct dpu_hw_mixer *hw;
+
+		if (rm->mixer_blks[i]) {
+			hw = to_dpu_hw_mixer(rm->mixer_blks[i]);
+			dpu_hw_lm_destroy(hw);
+		}
+	}
+	for (i = 0; i < ARRAY_SIZE(rm->ctl_blks); i++) {
+		struct dpu_hw_ctl *hw;
+
+		if (rm->ctl_blks[i]) {
+			hw = to_dpu_hw_ctl(rm->ctl_blks[i]);
+			dpu_hw_ctl_destroy(hw);
+		}
+	}
+	for (i = 0; i < ARRAY_SIZE(rm->hw_intf); i++)
+		dpu_hw_intf_destroy(rm->hw_intf[i]);
+
+	for (i = 0; i < ARRAY_SIZE(rm->dsc_blks); i++) {
+		struct dpu_hw_dsc *hw;
+
+		if (rm->dsc_blks[i]) {
+			hw = to_dpu_hw_dsc(rm->dsc_blks[i]);
+			dpu_hw_dsc_destroy(hw);
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(rm->hw_wb); i++)
+		dpu_hw_wb_destroy(rm->hw_wb[i]);
+
+	return 0;
+}
+
+int dpu_rm_init(struct dpu_rm *rm,
+		const struct dpu_mdss_cfg *cat,
+		void __iomem *mmio)
+{
+	int rc, i;
+
+	if (!rm || !cat || !mmio) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	/* Clear, setup lists */
+	memset(rm, 0, sizeof(*rm));
+
+	/* Interrogate HW catalog and create tracking items for hw blocks */
+	for (i = 0; i < cat->mixer_count; i++) {
+		struct dpu_hw_mixer *hw;
+		const struct dpu_lm_cfg *lm = &cat->mixer[i];
+
+		if (lm->pingpong == PINGPONG_MAX) {
+			DPU_DEBUG("skip mixer %d without pingpong\n", lm->id);
+			continue;
+		}
+
+		if (lm->id < LM_0 || lm->id >= LM_MAX) {
+			DPU_ERROR("skip mixer %d with invalid id\n", lm->id);
+			continue;
+		}
+		hw = dpu_hw_lm_init(lm->id, mmio, cat);
+		if (IS_ERR(hw)) {
+			rc = PTR_ERR(hw);
+			DPU_ERROR("failed lm object creation: err %d\n", rc);
+			goto fail;
+		}
+		rm->mixer_blks[lm->id - LM_0] = &hw->base;
+	}
+
+	for (i = 0; i < cat->merge_3d_count; i++) {
+		struct dpu_hw_merge_3d *hw;
+		const struct dpu_merge_3d_cfg *merge_3d = &cat->merge_3d[i];
+
+		if (merge_3d->id < MERGE_3D_0 || merge_3d->id >= MERGE_3D_MAX) {
+			DPU_ERROR("skip merge_3d %d with invalid id\n", merge_3d->id);
+			continue;
+		}
+		hw = dpu_hw_merge_3d_init(merge_3d->id, mmio, cat);
+		if (IS_ERR(hw)) {
+			rc = PTR_ERR(hw);
+			DPU_ERROR("failed merge_3d object creation: err %d\n",
+				rc);
+			goto fail;
+		}
+		rm->merge_3d_blks[merge_3d->id - MERGE_3D_0] = &hw->base;
+	}
+
+	for (i = 0; i < cat->pingpong_count; i++) {
+		struct dpu_hw_pingpong *hw;
+		const struct dpu_pingpong_cfg *pp = &cat->pingpong[i];
+
+		if (pp->id < PINGPONG_0 || pp->id >= PINGPONG_MAX) {
+			DPU_ERROR("skip pingpong %d with invalid id\n", pp->id);
+			continue;
+		}
+		hw = dpu_hw_pingpong_init(pp->id, mmio, cat);
+		if (IS_ERR(hw)) {
+			rc = PTR_ERR(hw);
+			DPU_ERROR("failed pingpong object creation: err %d\n",
+				rc);
+			goto fail;
+		}
+		if (pp->merge_3d && pp->merge_3d < MERGE_3D_MAX)
+			hw->merge_3d = to_dpu_hw_merge_3d(rm->merge_3d_blks[pp->merge_3d - MERGE_3D_0]);
+		rm->pingpong_blks[pp->id - PINGPONG_0] = &hw->base;
+	}
+
+	for (i = 0; i < cat->intf_count; i++) {
+		struct dpu_hw_intf *hw;
+		const struct dpu_intf_cfg *intf = &cat->intf[i];
+
+		if (intf->type == INTF_NONE) {
+			DPU_DEBUG("skip intf %d with type none\n", i);
+			continue;
+		}
+		if (intf->id < INTF_0 || intf->id >= INTF_MAX) {
+			DPU_ERROR("skip intf %d with invalid id\n", intf->id);
+			continue;
+		}
+		hw = dpu_hw_intf_init(intf->id, mmio, cat);
+		if (IS_ERR(hw)) {
+			rc = PTR_ERR(hw);
+			DPU_ERROR("failed intf object creation: err %d\n", rc);
+			goto fail;
+		}
+		rm->hw_intf[intf->id - INTF_0] = hw;
+	}
+
+	for (i = 0; i < cat->wb_count; i++) {
+		struct dpu_hw_wb *hw;
+		const struct dpu_wb_cfg *wb = &cat->wb[i];
+
+		if (wb->id < WB_0 || wb->id >= WB_MAX) {
+			DPU_ERROR("skip intf %d with invalid id\n", wb->id);
+			continue;
+		}
+
+		hw = dpu_hw_wb_init(wb->id, mmio, cat);
+		if (IS_ERR(hw)) {
+			rc = PTR_ERR(hw);
+			DPU_ERROR("failed wb object creation: err %d\n", rc);
+			goto fail;
+		}
+		rm->hw_wb[wb->id - WB_0] = hw;
+	}
+
+	for (i = 0; i < cat->ctl_count; i++) {
+		struct dpu_hw_ctl *hw;
+		const struct dpu_ctl_cfg *ctl = &cat->ctl[i];
+
+		if (ctl->id < CTL_0 || ctl->id >= CTL_MAX) {
+			DPU_ERROR("skip ctl %d with invalid id\n", ctl->id);
+			continue;
+		}
+		hw = dpu_hw_ctl_init(ctl->id, mmio, cat);
+		if (IS_ERR(hw)) {
+			rc = PTR_ERR(hw);
+			DPU_ERROR("failed ctl object creation: err %d\n", rc);
+			goto fail;
+		}
+		rm->ctl_blks[ctl->id - CTL_0] = &hw->base;
+	}
+
+	for (i = 0; i < cat->dspp_count; i++) {
+		struct dpu_hw_dspp *hw;
+		const struct dpu_dspp_cfg *dspp = &cat->dspp[i];
+
+		if (dspp->id < DSPP_0 || dspp->id >= DSPP_MAX) {
+			DPU_ERROR("skip dspp %d with invalid id\n", dspp->id);
+			continue;
+		}
+		hw = dpu_hw_dspp_init(dspp->id, mmio, cat);
+		if (IS_ERR(hw)) {
+			rc = PTR_ERR(hw);
+			DPU_ERROR("failed dspp object creation: err %d\n", rc);
+			goto fail;
+		}
+		rm->dspp_blks[dspp->id - DSPP_0] = &hw->base;
+	}
+
+	for (i = 0; i < cat->dsc_count; i++) {
+		struct dpu_hw_dsc *hw;
+		const struct dpu_dsc_cfg *dsc = &cat->dsc[i];
+
+		hw = dpu_hw_dsc_init(dsc->id, mmio, cat);
+		if (IS_ERR_OR_NULL(hw)) {
+			rc = PTR_ERR(hw);
+			DPU_ERROR("failed dsc object creation: err %d\n", rc);
+			goto fail;
+		}
+		rm->dsc_blks[dsc->id - DSC_0] = &hw->base;
+	}
+
+	return 0;
+
+fail:
+	dpu_rm_destroy(rm);
+
+	return rc ? rc : -EFAULT;
+}
+
+static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top)
+{
+	return top->num_intf > 1;
+}
+
+/**
+ * _dpu_rm_check_lm_peer - check if a mixer is a peer of the primary
+ * @rm: dpu resource manager handle
+ * @primary_idx: index of primary mixer in rm->mixer_blks[]
+ * @peer_idx: index of other mixer in rm->mixer_blks[]
+ * Return: true if rm->mixer_blks[peer_idx] is a peer of
+ *          rm->mixer_blks[primary_idx]
+ */
+static bool _dpu_rm_check_lm_peer(struct dpu_rm *rm, int primary_idx,
+		int peer_idx)
+{
+	const struct dpu_lm_cfg *prim_lm_cfg;
+	const struct dpu_lm_cfg *peer_cfg;
+
+	prim_lm_cfg = to_dpu_hw_mixer(rm->mixer_blks[primary_idx])->cap;
+	peer_cfg = to_dpu_hw_mixer(rm->mixer_blks[peer_idx])->cap;
+
+	if (!test_bit(peer_cfg->id, &prim_lm_cfg->lm_pair_mask)) {
+		DPU_DEBUG("lm %d not peer of lm %d\n", peer_cfg->id,
+				peer_cfg->id);
+		return false;
+	}
+	return true;
+}
+
+/**
+ * _dpu_rm_check_lm_and_get_connected_blks - check if proposed layer mixer meets
+ *	proposed use case requirements, incl. hardwired dependent blocks like
+ *	pingpong
+ * @rm: dpu resource manager handle
+ * @global_state: resources shared across multiple kms objects
+ * @enc_id: encoder id requesting for allocation
+ * @lm_idx: index of proposed layer mixer in rm->mixer_blks[], function checks
+ *      if lm, and all other hardwired blocks connected to the lm (pp) is
+ *      available and appropriate
+ * @pp_idx: output parameter, index of pingpong block attached to the layer
+ *      mixer in rm->pingpong_blks[].
+ * @dspp_idx: output parameter, index of dspp block attached to the layer
+ *      mixer in rm->dspp_blks[].
+ * @reqs: input parameter, rm requirements for HW blocks needed in the
+ *      datapath.
+ * Return: true if lm matches all requirements, false otherwise
+ */
+static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm,
+		struct dpu_global_state *global_state,
+		uint32_t enc_id, int lm_idx, int *pp_idx, int *dspp_idx,
+		struct dpu_rm_requirements *reqs)
+{
+	const struct dpu_lm_cfg *lm_cfg;
+	int idx;
+
+	/* Already reserved? */
+	if (reserved_by_other(global_state->mixer_to_enc_id, lm_idx, enc_id)) {
+		DPU_DEBUG("lm %d already reserved\n", lm_idx + LM_0);
+		return false;
+	}
+
+	lm_cfg = to_dpu_hw_mixer(rm->mixer_blks[lm_idx])->cap;
+	idx = lm_cfg->pingpong - PINGPONG_0;
+	if (idx < 0 || idx >= ARRAY_SIZE(rm->pingpong_blks)) {
+		DPU_ERROR("failed to get pp on lm %d\n", lm_cfg->pingpong);
+		return false;
+	}
+
+	if (reserved_by_other(global_state->pingpong_to_enc_id, idx, enc_id)) {
+		DPU_DEBUG("lm %d pp %d already reserved\n", lm_cfg->id,
+				lm_cfg->pingpong);
+		return false;
+	}
+	*pp_idx = idx;
+
+	if (!reqs->topology.num_dspp)
+		return true;
+
+	idx = lm_cfg->dspp - DSPP_0;
+	if (idx < 0 || idx >= ARRAY_SIZE(rm->dspp_blks)) {
+		DPU_ERROR("failed to get dspp on lm %d\n", lm_cfg->dspp);
+		return false;
+	}
+
+	if (reserved_by_other(global_state->dspp_to_enc_id, idx, enc_id)) {
+		DPU_DEBUG("lm %d dspp %d already reserved\n", lm_cfg->id,
+				lm_cfg->dspp);
+		return false;
+	}
+	*dspp_idx = idx;
+
+	return true;
+}
+
+static int _dpu_rm_reserve_lms(struct dpu_rm *rm,
+			       struct dpu_global_state *global_state,
+			       uint32_t enc_id,
+			       struct dpu_rm_requirements *reqs)
+
+{
+	int lm_idx[MAX_BLOCKS];
+	int pp_idx[MAX_BLOCKS];
+	int dspp_idx[MAX_BLOCKS] = {0};
+	int i, j, lm_count = 0;
+
+	if (!reqs->topology.num_lm) {
+		DPU_ERROR("invalid number of lm: %d\n", reqs->topology.num_lm);
+		return -EINVAL;
+	}
+
+	/* Find a primary mixer */
+	for (i = 0; i < ARRAY_SIZE(rm->mixer_blks) &&
+			lm_count < reqs->topology.num_lm; i++) {
+		if (!rm->mixer_blks[i])
+			continue;
+
+		lm_count = 0;
+		lm_idx[lm_count] = i;
+
+		if (!_dpu_rm_check_lm_and_get_connected_blks(rm, global_state,
+				enc_id, i, &pp_idx[lm_count],
+				&dspp_idx[lm_count], reqs)) {
+			continue;
+		}
+
+		++lm_count;
+
+		/* Valid primary mixer found, find matching peers */
+		for (j = i + 1; j < ARRAY_SIZE(rm->mixer_blks) &&
+				lm_count < reqs->topology.num_lm; j++) {
+			if (!rm->mixer_blks[j])
+				continue;
+
+			if (!_dpu_rm_check_lm_peer(rm, i, j)) {
+				DPU_DEBUG("lm %d not peer of lm %d\n", LM_0 + j,
+						LM_0 + i);
+				continue;
+			}
+
+			if (!_dpu_rm_check_lm_and_get_connected_blks(rm,
+					global_state, enc_id, j,
+					&pp_idx[lm_count], &dspp_idx[lm_count],
+					reqs)) {
+				continue;
+			}
+
+			lm_idx[lm_count] = j;
+			++lm_count;
+		}
+	}
+
+	if (lm_count != reqs->topology.num_lm) {
+		DPU_DEBUG("unable to find appropriate mixers\n");
+		return -ENAVAIL;
+	}
+
+	for (i = 0; i < lm_count; i++) {
+		global_state->mixer_to_enc_id[lm_idx[i]] = enc_id;
+		global_state->pingpong_to_enc_id[pp_idx[i]] = enc_id;
+		global_state->dspp_to_enc_id[dspp_idx[i]] =
+			reqs->topology.num_dspp ? enc_id : 0;
+
+		trace_dpu_rm_reserve_lms(lm_idx[i] + LM_0, enc_id,
+					 pp_idx[i] + PINGPONG_0);
+	}
+
+	return 0;
+}
+
+static int _dpu_rm_reserve_ctls(
+		struct dpu_rm *rm,
+		struct dpu_global_state *global_state,
+		uint32_t enc_id,
+		const struct msm_display_topology *top)
+{
+	int ctl_idx[MAX_BLOCKS];
+	int i = 0, j, num_ctls;
+	bool needs_split_display;
+
+	/* each hw_intf needs its own hw_ctrl to program its control path */
+	num_ctls = top->num_intf;
+
+	needs_split_display = _dpu_rm_needs_split_display(top);
+
+	for (j = 0; j < ARRAY_SIZE(rm->ctl_blks); j++) {
+		const struct dpu_hw_ctl *ctl;
+		unsigned long features;
+		bool has_split_display;
+
+		if (!rm->ctl_blks[j])
+			continue;
+		if (reserved_by_other(global_state->ctl_to_enc_id, j, enc_id))
+			continue;
+
+		ctl = to_dpu_hw_ctl(rm->ctl_blks[j]);
+		features = ctl->caps->features;
+		has_split_display = BIT(DPU_CTL_SPLIT_DISPLAY) & features;
+
+		DPU_DEBUG("ctl %d caps 0x%lX\n", j + CTL_0, features);
+
+		if (needs_split_display != has_split_display)
+			continue;
+
+		ctl_idx[i] = j;
+		DPU_DEBUG("ctl %d match\n", j + CTL_0);
+
+		if (++i == num_ctls)
+			break;
+
+	}
+
+	if (i != num_ctls)
+		return -ENAVAIL;
+
+	for (i = 0; i < ARRAY_SIZE(ctl_idx) && i < num_ctls; i++) {
+		global_state->ctl_to_enc_id[ctl_idx[i]] = enc_id;
+		trace_dpu_rm_reserve_ctls(i + CTL_0, enc_id);
+	}
+
+	return 0;
+}
+
+static int _dpu_rm_reserve_dsc(struct dpu_rm *rm,
+			       struct dpu_global_state *global_state,
+			       struct drm_encoder *enc,
+			       const struct msm_display_topology *top)
+{
+	int num_dsc = top->num_dsc;
+	int i;
+
+	/* check if DSC required are allocated or not */
+	for (i = 0; i < num_dsc; i++) {
+		if (global_state->dsc_to_enc_id[i]) {
+			DPU_ERROR("DSC %d is already allocated\n", i);
+			return -EIO;
+		}
+	}
+
+	for (i = 0; i < num_dsc; i++)
+		global_state->dsc_to_enc_id[i] = enc->base.id;
+
+	return 0;
+}
+
+static int _dpu_rm_make_reservation(
+		struct dpu_rm *rm,
+		struct dpu_global_state *global_state,
+		struct drm_encoder *enc,
+		struct dpu_rm_requirements *reqs)
+{
+	int ret;
+
+	ret = _dpu_rm_reserve_lms(rm, global_state, enc->base.id, reqs);
+	if (ret) {
+		DPU_ERROR("unable to find appropriate mixers\n");
+		return ret;
+	}
+
+	ret = _dpu_rm_reserve_ctls(rm, global_state, enc->base.id,
+				&reqs->topology);
+	if (ret) {
+		DPU_ERROR("unable to find appropriate CTL\n");
+		return ret;
+	}
+
+	ret  = _dpu_rm_reserve_dsc(rm, global_state, enc, &reqs->topology);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+static int _dpu_rm_populate_requirements(
+		struct drm_encoder *enc,
+		struct dpu_rm_requirements *reqs,
+		struct msm_display_topology req_topology)
+{
+	reqs->topology = req_topology;
+
+	DRM_DEBUG_KMS("num_lm: %d num_enc: %d num_intf: %d\n",
+		      reqs->topology.num_lm, reqs->topology.num_enc,
+		      reqs->topology.num_intf);
+
+	return 0;
+}
+
+static void _dpu_rm_clear_mapping(uint32_t *res_mapping, int cnt,
+				  uint32_t enc_id)
+{
+	int i;
+
+	for (i = 0; i < cnt; i++) {
+		if (res_mapping[i] == enc_id)
+			res_mapping[i] = 0;
+	}
+}
+
+void dpu_rm_release(struct dpu_global_state *global_state,
+		    struct drm_encoder *enc)
+{
+	_dpu_rm_clear_mapping(global_state->pingpong_to_enc_id,
+		ARRAY_SIZE(global_state->pingpong_to_enc_id), enc->base.id);
+	_dpu_rm_clear_mapping(global_state->mixer_to_enc_id,
+		ARRAY_SIZE(global_state->mixer_to_enc_id), enc->base.id);
+	_dpu_rm_clear_mapping(global_state->ctl_to_enc_id,
+		ARRAY_SIZE(global_state->ctl_to_enc_id), enc->base.id);
+	_dpu_rm_clear_mapping(global_state->dsc_to_enc_id,
+		ARRAY_SIZE(global_state->dsc_to_enc_id), enc->base.id);
+	_dpu_rm_clear_mapping(global_state->dspp_to_enc_id,
+		ARRAY_SIZE(global_state->dspp_to_enc_id), enc->base.id);
+}
+
+int dpu_rm_reserve(
+		struct dpu_rm *rm,
+		struct dpu_global_state *global_state,
+		struct drm_encoder *enc,
+		struct drm_crtc_state *crtc_state,
+		struct msm_display_topology topology)
+{
+	struct dpu_rm_requirements reqs;
+	int ret;
+
+	/* Check if this is just a page-flip */
+	if (!drm_atomic_crtc_needs_modeset(crtc_state))
+		return 0;
+
+	if (IS_ERR(global_state)) {
+		DPU_ERROR("failed to global state\n");
+		return PTR_ERR(global_state);
+	}
+
+	DRM_DEBUG_KMS("reserving hw for enc %d crtc %d\n",
+		      enc->base.id, crtc_state->crtc->base.id);
+
+	ret = _dpu_rm_populate_requirements(enc, &reqs, topology);
+	if (ret) {
+		DPU_ERROR("failed to populate hw requirements\n");
+		return ret;
+	}
+
+	ret = _dpu_rm_make_reservation(rm, global_state, enc, &reqs);
+	if (ret)
+		DPU_ERROR("failed to reserve hw resources: %d\n", ret);
+
+
+
+	return ret;
+}
+
+int dpu_rm_get_assigned_resources(struct dpu_rm *rm,
+	struct dpu_global_state *global_state, uint32_t enc_id,
+	enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size)
+{
+	struct dpu_hw_blk **hw_blks;
+	uint32_t *hw_to_enc_id;
+	int i, num_blks, max_blks;
+
+	switch (type) {
+	case DPU_HW_BLK_PINGPONG:
+		hw_blks = rm->pingpong_blks;
+		hw_to_enc_id = global_state->pingpong_to_enc_id;
+		max_blks = ARRAY_SIZE(rm->pingpong_blks);
+		break;
+	case DPU_HW_BLK_LM:
+		hw_blks = rm->mixer_blks;
+		hw_to_enc_id = global_state->mixer_to_enc_id;
+		max_blks = ARRAY_SIZE(rm->mixer_blks);
+		break;
+	case DPU_HW_BLK_CTL:
+		hw_blks = rm->ctl_blks;
+		hw_to_enc_id = global_state->ctl_to_enc_id;
+		max_blks = ARRAY_SIZE(rm->ctl_blks);
+		break;
+	case DPU_HW_BLK_DSPP:
+		hw_blks = rm->dspp_blks;
+		hw_to_enc_id = global_state->dspp_to_enc_id;
+		max_blks = ARRAY_SIZE(rm->dspp_blks);
+		break;
+	case DPU_HW_BLK_DSC:
+		hw_blks = rm->dsc_blks;
+		hw_to_enc_id = global_state->dsc_to_enc_id;
+		max_blks = ARRAY_SIZE(rm->dsc_blks);
+		break;
+	default:
+		DPU_ERROR("blk type %d not managed by rm\n", type);
+		return 0;
+	}
+
+	num_blks = 0;
+	for (i = 0; i < max_blks; i++) {
+		if (hw_to_enc_id[i] != enc_id)
+			continue;
+
+		if (num_blks == blks_size) {
+			DPU_ERROR("More than %d resources assigned to enc %d\n",
+				  blks_size, enc_id);
+			break;
+		}
+		if (!hw_blks[i]) {
+			DPU_ERROR("Allocated resource %d unavailable to assign to enc %d\n",
+				  type, enc_id);
+			break;
+		}
+		blks[num_blks++] = hw_blks[i];
+	}
+
+	return num_blks;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
new file mode 100644
index 000000000..59de72b38
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __DPU_RM_H__
+#define __DPU_RM_H__
+
+#include <linux/list.h>
+
+#include "msm_kms.h"
+#include "dpu_hw_top.h"
+
+struct dpu_global_state;
+
+/**
+ * struct dpu_rm - DPU dynamic hardware resource manager
+ * @pingpong_blks: array of pingpong hardware resources
+ * @mixer_blks: array of layer mixer hardware resources
+ * @ctl_blks: array of ctl hardware resources
+ * @hw_intf: array of intf hardware resources
+ * @hw_wb: array of wb hardware resources
+ * @dspp_blks: array of dspp hardware resources
+ */
+struct dpu_rm {
+	struct dpu_hw_blk *pingpong_blks[PINGPONG_MAX - PINGPONG_0];
+	struct dpu_hw_blk *mixer_blks[LM_MAX - LM_0];
+	struct dpu_hw_blk *ctl_blks[CTL_MAX - CTL_0];
+	struct dpu_hw_intf *hw_intf[INTF_MAX - INTF_0];
+	struct dpu_hw_wb *hw_wb[WB_MAX - WB_0];
+	struct dpu_hw_blk *dspp_blks[DSPP_MAX - DSPP_0];
+	struct dpu_hw_blk *merge_3d_blks[MERGE_3D_MAX - MERGE_3D_0];
+	struct dpu_hw_blk *dsc_blks[DSC_MAX - DSC_0];
+};
+
+/**
+ * dpu_rm_init - Read hardware catalog and create reservation tracking objects
+ *	for all HW blocks.
+ * @rm: DPU Resource Manager handle
+ * @cat: Pointer to hardware catalog
+ * @mmio: mapped register io address of MDP
+ * @Return: 0 on Success otherwise -ERROR
+ */
+int dpu_rm_init(struct dpu_rm *rm,
+		const struct dpu_mdss_cfg *cat,
+		void __iomem *mmio);
+
+/**
+ * dpu_rm_destroy - Free all memory allocated by dpu_rm_init
+ * @rm: DPU Resource Manager handle
+ * @Return: 0 on Success otherwise -ERROR
+ */
+int dpu_rm_destroy(struct dpu_rm *rm);
+
+/**
+ * dpu_rm_reserve - Given a CRTC->Encoder->Connector display chain, analyze
+ *	the use connections and user requirements, specified through related
+ *	topology control properties, and reserve hardware blocks to that
+ *	display chain.
+ *	HW blocks can then be accessed through dpu_rm_get_* functions.
+ *	HW Reservations should be released via dpu_rm_release_hw.
+ * @rm: DPU Resource Manager handle
+ * @drm_enc: DRM Encoder handle
+ * @crtc_state: Proposed Atomic DRM CRTC State handle
+ * @topology: Pointer to topology info for the display
+ * @Return: 0 on Success otherwise -ERROR
+ */
+int dpu_rm_reserve(struct dpu_rm *rm,
+		struct dpu_global_state *global_state,
+		struct drm_encoder *drm_enc,
+		struct drm_crtc_state *crtc_state,
+		struct msm_display_topology topology);
+
+/**
+ * dpu_rm_reserve - Given the encoder for the display chain, release any
+ *	HW blocks previously reserved for that use case.
+ * @rm: DPU Resource Manager handle
+ * @enc: DRM Encoder handle
+ * @Return: 0 on Success otherwise -ERROR
+ */
+void dpu_rm_release(struct dpu_global_state *global_state,
+		struct drm_encoder *enc);
+
+/**
+ * Get hw resources of the given type that are assigned to this encoder.
+ */
+int dpu_rm_get_assigned_resources(struct dpu_rm *rm,
+	struct dpu_global_state *global_state, uint32_t enc_id,
+	enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size);
+
+/**
+ * dpu_rm_get_intf - Return a struct dpu_hw_intf instance given it's index.
+ * @rm: DPU Resource Manager handle
+ * @intf_idx: INTF's index
+ */
+static inline struct dpu_hw_intf *dpu_rm_get_intf(struct dpu_rm *rm, enum dpu_intf intf_idx)
+{
+	return rm->hw_intf[intf_idx - INTF_0];
+}
+
+/**
+ * dpu_rm_get_wb - Return a struct dpu_hw_wb instance given it's index.
+ * @rm: DPU Resource Manager handle
+ * @wb_idx: WB index
+ */
+static inline struct dpu_hw_wb *dpu_rm_get_wb(struct dpu_rm *rm, enum dpu_wb wb_idx)
+{
+	return rm->hw_wb[wb_idx - WB_0];
+}
+
+#endif /* __DPU_RM_H__ */
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
new file mode 100644
index 000000000..76169f406
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
@@ -0,0 +1,978 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ */
+
+#if !defined(_DPU_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _DPU_TRACE_H_
+
+#include <linux/stringify.h>
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#include <drm/drm_rect.h>
+#include "dpu_crtc.h"
+#include "dpu_encoder_phys.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_plane.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM dpu
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE dpu_trace
+
+TRACE_EVENT(dpu_perf_set_qos_luts,
+	TP_PROTO(u32 pnum, u32 fmt, bool rt, u32 fl,
+		u32 lut, u32 lut_usage),
+	TP_ARGS(pnum, fmt, rt, fl, lut, lut_usage),
+	TP_STRUCT__entry(
+			__field(u32, pnum)
+			__field(u32, fmt)
+			__field(bool, rt)
+			__field(u32, fl)
+			__field(u64, lut)
+			__field(u32, lut_usage)
+	),
+	TP_fast_assign(
+			__entry->pnum = pnum;
+			__entry->fmt = fmt;
+			__entry->rt = rt;
+			__entry->fl = fl;
+			__entry->lut = lut;
+			__entry->lut_usage = lut_usage;
+	),
+	TP_printk("pnum=%d fmt=%x rt=%d fl=%d lut=0x%llx lut_usage=%d",
+			__entry->pnum, __entry->fmt,
+			__entry->rt, __entry->fl,
+			__entry->lut, __entry->lut_usage)
+);
+
+TRACE_EVENT(dpu_perf_set_danger_luts,
+	TP_PROTO(u32 pnum, u32 fmt, u32 mode, u32 danger_lut,
+		u32 safe_lut),
+	TP_ARGS(pnum, fmt, mode, danger_lut, safe_lut),
+	TP_STRUCT__entry(
+			__field(u32, pnum)
+			__field(u32, fmt)
+			__field(u32, mode)
+			__field(u32, danger_lut)
+			__field(u32, safe_lut)
+	),
+	TP_fast_assign(
+			__entry->pnum = pnum;
+			__entry->fmt = fmt;
+			__entry->mode = mode;
+			__entry->danger_lut = danger_lut;
+			__entry->safe_lut = safe_lut;
+	),
+	TP_printk("pnum=%d fmt=%x mode=%d luts[0x%x, 0x%x]",
+			__entry->pnum, __entry->fmt,
+			__entry->mode, __entry->danger_lut,
+			__entry->safe_lut)
+);
+
+TRACE_EVENT(dpu_perf_set_ot,
+	TP_PROTO(u32 pnum, u32 xin_id, u32 rd_lim, u32 vbif_idx),
+	TP_ARGS(pnum, xin_id, rd_lim, vbif_idx),
+	TP_STRUCT__entry(
+			__field(u32, pnum)
+			__field(u32, xin_id)
+			__field(u32, rd_lim)
+			__field(u32, vbif_idx)
+	),
+	TP_fast_assign(
+			__entry->pnum = pnum;
+			__entry->xin_id = xin_id;
+			__entry->rd_lim = rd_lim;
+			__entry->vbif_idx = vbif_idx;
+	),
+	TP_printk("pnum:%d xin_id:%d ot:%d vbif:%d",
+			__entry->pnum, __entry->xin_id, __entry->rd_lim,
+			__entry->vbif_idx)
+)
+
+TRACE_EVENT(dpu_cmd_release_bw,
+	TP_PROTO(u32 crtc_id),
+	TP_ARGS(crtc_id),
+	TP_STRUCT__entry(
+			__field(u32, crtc_id)
+	),
+	TP_fast_assign(
+			__entry->crtc_id = crtc_id;
+	),
+	TP_printk("crtc:%d", __entry->crtc_id)
+);
+
+TRACE_EVENT(tracing_mark_write,
+	TP_PROTO(int pid, const char *name, bool trace_begin),
+	TP_ARGS(pid, name, trace_begin),
+	TP_STRUCT__entry(
+			__field(int, pid)
+			__string(trace_name, name)
+			__field(bool, trace_begin)
+	),
+	TP_fast_assign(
+			__entry->pid = pid;
+			__assign_str(trace_name, name);
+			__entry->trace_begin = trace_begin;
+	),
+	TP_printk("%s|%d|%s", __entry->trace_begin ? "B" : "E",
+		__entry->pid, __get_str(trace_name))
+)
+
+TRACE_EVENT(dpu_trace_counter,
+	TP_PROTO(int pid, char *name, int value),
+	TP_ARGS(pid, name, value),
+	TP_STRUCT__entry(
+			__field(int, pid)
+			__string(counter_name, name)
+			__field(int, value)
+	),
+	TP_fast_assign(
+			__entry->pid = current->tgid;
+			__assign_str(counter_name, name);
+			__entry->value = value;
+	),
+	TP_printk("%d|%s|%d", __entry->pid,
+			__get_str(counter_name), __entry->value)
+)
+
+TRACE_EVENT(dpu_perf_crtc_update,
+	TP_PROTO(u32 crtc, u64 bw_ctl, u32 core_clk_rate,
+			bool stop_req, bool update_bus, bool update_clk),
+	TP_ARGS(crtc, bw_ctl, core_clk_rate, stop_req, update_bus, update_clk),
+	TP_STRUCT__entry(
+			__field(u32, crtc)
+			__field(u64, bw_ctl)
+			__field(u32, core_clk_rate)
+			__field(bool, stop_req)
+			__field(u32, update_bus)
+			__field(u32, update_clk)
+	),
+	TP_fast_assign(
+			__entry->crtc = crtc;
+			__entry->bw_ctl = bw_ctl;
+			__entry->core_clk_rate = core_clk_rate;
+			__entry->stop_req = stop_req;
+			__entry->update_bus = update_bus;
+			__entry->update_clk = update_clk;
+	),
+	 TP_printk(
+		"crtc=%d bw_ctl=%llu clk_rate=%u stop_req=%d u_bus=%d u_clk=%d",
+			__entry->crtc,
+			__entry->bw_ctl,
+			__entry->core_clk_rate,
+			__entry->stop_req,
+			__entry->update_bus,
+			__entry->update_clk)
+);
+
+DECLARE_EVENT_CLASS(dpu_irq_template,
+	TP_PROTO(int irq_idx),
+	TP_ARGS(irq_idx),
+	TP_STRUCT__entry(
+		__field(	int,			irq_idx		)
+	),
+	TP_fast_assign(
+		__entry->irq_idx = irq_idx;
+	),
+	TP_printk("irq=%d", __entry->irq_idx)
+);
+DEFINE_EVENT(dpu_irq_template, dpu_irq_register_success,
+	TP_PROTO(int irq_idx),
+	TP_ARGS(irq_idx)
+);
+DEFINE_EVENT(dpu_irq_template, dpu_irq_unregister_success,
+	TP_PROTO(int irq_idx),
+	TP_ARGS(irq_idx)
+);
+
+TRACE_EVENT(dpu_enc_irq_wait_success,
+	TP_PROTO(uint32_t drm_id, void *func,
+		 int irq_idx, enum dpu_pingpong pp_idx, int atomic_cnt),
+	TP_ARGS(drm_id, func, irq_idx, pp_idx, atomic_cnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	void *,			func		)
+		__field(	int,			irq_idx		)
+		__field(	enum dpu_pingpong,	pp_idx		)
+		__field(	int,			atomic_cnt	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->func = func;
+		__entry->irq_idx = irq_idx;
+		__entry->pp_idx = pp_idx;
+		__entry->atomic_cnt = atomic_cnt;
+	),
+	TP_printk("id=%u, callback=%ps, irq=%d, pp=%d, atomic_cnt=%d",
+		  __entry->drm_id, __entry->func,
+		  __entry->irq_idx, __entry->pp_idx, __entry->atomic_cnt)
+);
+
+DECLARE_EVENT_CLASS(dpu_drm_obj_template,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+	),
+	TP_printk("id=%u", __entry->drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_atomic_check,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_mode_set,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_disable,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_kickoff,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_prepare_kickoff,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_prepare_kickoff_reset,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_complete_flip,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_vblank_cb,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_complete_commit,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_commit,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_wait_for_commit_done,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_runtime_resume,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+
+TRACE_EVENT(dpu_enc_enable,
+	TP_PROTO(uint32_t drm_id, int hdisplay, int vdisplay),
+	TP_ARGS(drm_id, hdisplay, vdisplay),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	int,			hdisplay	)
+		__field(	int,			vdisplay	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->hdisplay = hdisplay;
+		__entry->vdisplay = vdisplay;
+	),
+	TP_printk("id=%u, mode=%dx%d",
+		  __entry->drm_id, __entry->hdisplay, __entry->vdisplay)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_keyval_template,
+	TP_PROTO(uint32_t drm_id, int val),
+	TP_ARGS(drm_id, val),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id	)
+		__field(	int,		val	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->val = val;
+	),
+	TP_printk("id=%u, val=%d", __entry->drm_id, __entry->val)
+);
+DEFINE_EVENT(dpu_enc_keyval_template, dpu_enc_underrun_cb,
+	TP_PROTO(uint32_t drm_id, int count),
+	TP_ARGS(drm_id, count)
+);
+DEFINE_EVENT(dpu_enc_keyval_template, dpu_enc_trigger_start,
+	TP_PROTO(uint32_t drm_id, int ctl_idx),
+	TP_ARGS(drm_id, ctl_idx)
+);
+
+TRACE_EVENT(dpu_enc_atomic_check_flags,
+	TP_PROTO(uint32_t drm_id, unsigned int flags),
+	TP_ARGS(drm_id, flags),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	unsigned int,		flags		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->flags = flags;
+	),
+	TP_printk("id=%u, flags=%u",
+		  __entry->drm_id, __entry->flags)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_id_enable_template,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	bool,			enable		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->enable = enable;
+	),
+	TP_printk("id=%u, enable=%s",
+		  __entry->drm_id, __entry->enable ? "true" : "false")
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_rc_helper,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_vblank_cb,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_frame_event_cb,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_phys_cmd_connect_te,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+
+TRACE_EVENT(dpu_enc_rc,
+	TP_PROTO(uint32_t drm_id, u32 sw_event, bool idle_pc_supported,
+		 int rc_state, const char *stage),
+	TP_ARGS(drm_id, sw_event, idle_pc_supported, rc_state, stage),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id			)
+		__field(	u32,		sw_event		)
+		__field(	bool,		idle_pc_supported	)
+		__field(	int,		rc_state		)
+		__string(	stage_str,	stage			)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->sw_event = sw_event;
+		__entry->idle_pc_supported = idle_pc_supported;
+		__entry->rc_state = rc_state;
+		__assign_str(stage_str, stage);
+	),
+	TP_printk("%s: id:%u, sw_event:%d, idle_pc_supported:%s, rc_state:%d",
+		  __get_str(stage_str), __entry->drm_id, __entry->sw_event,
+		  __entry->idle_pc_supported ? "true" : "false",
+		  __entry->rc_state)
+);
+
+TRACE_EVENT(dpu_enc_frame_done_cb_not_busy,
+	TP_PROTO(uint32_t drm_id, u32 event, char *intf_mode, enum dpu_intf intf_idx,
+			enum dpu_wb wb_idx),
+	TP_ARGS(drm_id, event, intf_mode, intf_idx, wb_idx),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id		)
+		__field(	u32,		event		)
+		__string(	intf_mode_str,	intf_mode	)
+		__field(	enum dpu_intf,	intf_idx	)
+		__field(	enum dpu_wb,	wb_idx		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->event = event;
+		__assign_str(intf_mode_str, intf_mode);
+		__entry->intf_idx = intf_idx;
+		__entry->wb_idx = wb_idx;
+	),
+	TP_printk("id=%u, event=%u, intf_mode=%s intf=%d wb=%d", __entry->drm_id,
+			__entry->event, __get_str(intf_mode_str),
+			__entry->intf_idx, __entry->wb_idx)
+);
+
+TRACE_EVENT(dpu_enc_frame_done_cb,
+	TP_PROTO(uint32_t drm_id, unsigned int idx,
+		 unsigned long frame_busy_mask),
+	TP_ARGS(drm_id, idx, frame_busy_mask),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	unsigned int,		idx		)
+		__field(	unsigned long,		frame_busy_mask	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->idx = idx;
+		__entry->frame_busy_mask = frame_busy_mask;
+	),
+	TP_printk("id=%u, idx=%u, frame_busy_mask=%lx", __entry->drm_id,
+		  __entry->idx, __entry->frame_busy_mask)
+);
+
+TRACE_EVENT(dpu_enc_trigger_flush,
+	TP_PROTO(uint32_t drm_id, char *intf_mode, enum dpu_intf intf_idx, enum dpu_wb wb_idx,
+		 int pending_kickoff_cnt, int ctl_idx, u32 extra_flush_bits,
+		 u32 pending_flush_ret),
+	TP_ARGS(drm_id, intf_mode, intf_idx, wb_idx, pending_kickoff_cnt, ctl_idx,
+		extra_flush_bits, pending_flush_ret),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id			)
+		__string(	intf_mode_str,	intf_mode		)
+		__field(	enum dpu_intf,	intf_idx		)
+		__field(	enum dpu_wb,	wb_idx			)
+		__field(	int,		pending_kickoff_cnt	)
+		__field(	int,		ctl_idx			)
+		__field(	u32,		extra_flush_bits	)
+		__field(	u32,		pending_flush_ret	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__assign_str(intf_mode_str, intf_mode);
+		__entry->intf_idx = intf_idx;
+		__entry->wb_idx = wb_idx;
+		__entry->pending_kickoff_cnt = pending_kickoff_cnt;
+		__entry->ctl_idx = ctl_idx;
+		__entry->extra_flush_bits = extra_flush_bits;
+		__entry->pending_flush_ret = pending_flush_ret;
+	),
+	TP_printk("id=%u, intf_mode=%s, intf_idx=%d, wb_idx=%d, pending_kickoff_cnt=%d ctl_idx=%d "
+		  "extra_flush_bits=0x%x pending_flush_ret=0x%x",
+		  __entry->drm_id, __get_str(intf_mode_str), __entry->intf_idx, __entry->wb_idx,
+		  __entry->pending_kickoff_cnt, __entry->ctl_idx,
+		  __entry->extra_flush_bits, __entry->pending_flush_ret)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_ktime_template,
+	TP_PROTO(uint32_t drm_id, ktime_t time),
+	TP_ARGS(drm_id, time),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id	)
+		__field(	ktime_t,	time	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->time = time;
+	),
+	TP_printk("id=%u, time=%lld", __entry->drm_id,
+		  ktime_to_ms(__entry->time))
+);
+DEFINE_EVENT(dpu_enc_ktime_template, dpu_enc_vsync_event_work,
+	TP_PROTO(uint32_t drm_id, ktime_t time),
+	TP_ARGS(drm_id, time)
+);
+DEFINE_EVENT(dpu_enc_ktime_template, dpu_enc_early_kickoff,
+	TP_PROTO(uint32_t drm_id, ktime_t time),
+	TP_ARGS(drm_id, time)
+);
+
+DECLARE_EVENT_CLASS(dpu_id_event_template,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id	)
+		__field(	u32,		event	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->event = event;
+	),
+	TP_printk("id=%u, event=%u", __entry->drm_id, __entry->event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_enc_frame_done_timeout,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_cb,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_done,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_more_pending,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+
+TRACE_EVENT(dpu_enc_wait_event_timeout,
+	TP_PROTO(uint32_t drm_id, int irq_idx, int rc, s64 time,
+		 s64 expected_time, int atomic_cnt),
+	TP_ARGS(drm_id, irq_idx, rc, time, expected_time, atomic_cnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id		)
+		__field(	int,		irq_idx		)
+		__field(	int,		rc		)
+		__field(	s64,		time		)
+		__field(	s64,		expected_time	)
+		__field(	int,		atomic_cnt	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->irq_idx = irq_idx;
+		__entry->rc = rc;
+		__entry->time = time;
+		__entry->expected_time = expected_time;
+		__entry->atomic_cnt = atomic_cnt;
+	),
+	TP_printk("id=%u, irq_idx=%d, rc=%d, time=%lld, expected=%lld cnt=%d",
+		  __entry->drm_id, __entry->irq_idx, __entry->rc, __entry->time,
+		  __entry->expected_time, __entry->atomic_cnt)
+);
+
+TRACE_EVENT(dpu_enc_phys_cmd_irq_ctrl,
+	TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, bool enable,
+		 int refcnt),
+	TP_ARGS(drm_id, pp, enable, refcnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	enum dpu_pingpong,	pp	)
+		__field(	bool,			enable	)
+		__field(	int,			refcnt	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->pp = pp;
+		__entry->enable = enable;
+		__entry->refcnt = refcnt;
+	),
+	TP_printk("id=%u, pp=%d, enable=%s, refcnt=%d", __entry->drm_id,
+		  __entry->pp, __entry->enable ? "true" : "false",
+		  __entry->refcnt)
+);
+
+TRACE_EVENT(dpu_enc_phys_cmd_pp_tx_done,
+	TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, int new_count,
+		 u32 event),
+	TP_ARGS(drm_id, pp, new_count, event),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_pingpong,	pp		)
+		__field(	int,			new_count	)
+		__field(	u32,			event		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->pp = pp;
+		__entry->new_count = new_count;
+		__entry->event = event;
+	),
+	TP_printk("id=%u, pp=%d, new_count=%d, event=%u", __entry->drm_id,
+		  __entry->pp, __entry->new_count, __entry->event)
+);
+
+TRACE_EVENT(dpu_enc_phys_cmd_pdone_timeout,
+	TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, int timeout_count,
+		 int kickoff_count, u32 event),
+	TP_ARGS(drm_id, pp, timeout_count, kickoff_count, event),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_pingpong,	pp		)
+		__field(	int,			timeout_count	)
+		__field(	int,			kickoff_count	)
+		__field(	u32,			event		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->pp = pp;
+		__entry->timeout_count = timeout_count;
+		__entry->kickoff_count = kickoff_count;
+		__entry->event = event;
+	),
+	TP_printk("id=%u, pp=%d, timeout_count=%d, kickoff_count=%d, event=%u",
+		  __entry->drm_id, __entry->pp, __entry->timeout_count,
+		  __entry->kickoff_count, __entry->event)
+);
+
+TRACE_EVENT(dpu_enc_phys_vid_post_kickoff,
+	TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx),
+	TP_ARGS(drm_id, intf_idx),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id			)
+		__field(	enum dpu_intf,	intf_idx		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intf_idx = intf_idx;
+	),
+	TP_printk("id=%u, intf_idx=%d", __entry->drm_id, __entry->intf_idx)
+);
+
+TRACE_EVENT(dpu_enc_phys_vid_irq_ctrl,
+	TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx, bool enable,
+		 int refcnt),
+	TP_ARGS(drm_id, intf_idx, enable, refcnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id		)
+		__field(	enum dpu_intf,	intf_idx	)
+		__field(	bool,		enable		)
+		__field(	int,		refcnt		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intf_idx = intf_idx;
+		__entry->enable = enable;
+		__entry->refcnt = refcnt;
+	),
+	TP_printk("id=%u, intf_idx=%d enable=%s refcnt=%d", __entry->drm_id,
+		  __entry->intf_idx, __entry->enable ? "true" : "false",
+		  __entry->drm_id)
+);
+
+TRACE_EVENT(dpu_crtc_setup_mixer,
+	TP_PROTO(uint32_t crtc_id, uint32_t plane_id,
+		 struct drm_plane_state *state, struct dpu_plane_state *pstate,
+		 uint32_t stage_idx, enum dpu_sspp sspp, uint32_t pixel_format,
+		 uint64_t modifier),
+	TP_ARGS(crtc_id, plane_id, state, pstate, stage_idx, sspp,
+		pixel_format, modifier),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		crtc_id		)
+		__field(	uint32_t,		plane_id	)
+		__field(	uint32_t,		fb_id		)
+		__field_struct(	struct drm_rect,	src_rect	)
+		__field_struct(	struct drm_rect,	dst_rect	)
+		__field(	uint32_t,		stage_idx	)
+		__field(	enum dpu_stage,		stage		)
+		__field(	enum dpu_sspp,		sspp		)
+		__field(	uint32_t,		multirect_idx	)
+		__field(	uint32_t,		multirect_mode	)
+		__field(	uint32_t,		pixel_format	)
+		__field(	uint64_t,		modifier	)
+	),
+	TP_fast_assign(
+		__entry->crtc_id = crtc_id;
+		__entry->plane_id = plane_id;
+		__entry->fb_id = state ? state->fb->base.id : 0;
+		__entry->src_rect = drm_plane_state_src(state);
+		__entry->dst_rect = drm_plane_state_dest(state);
+		__entry->stage_idx = stage_idx;
+		__entry->stage = pstate->stage;
+		__entry->sspp = sspp;
+		__entry->multirect_idx = pstate->multirect_index;
+		__entry->multirect_mode = pstate->multirect_mode;
+		__entry->pixel_format = pixel_format;
+		__entry->modifier = modifier;
+	),
+	TP_printk("crtc_id:%u plane_id:%u fb_id:%u src:" DRM_RECT_FP_FMT
+		  " dst:" DRM_RECT_FMT " stage_idx:%u stage:%d, sspp:%d "
+		  "multirect_index:%d multirect_mode:%u pix_format:%u "
+		  "modifier:%llu",
+		  __entry->crtc_id, __entry->plane_id, __entry->fb_id,
+		  DRM_RECT_FP_ARG(&__entry->src_rect),
+		  DRM_RECT_ARG(&__entry->dst_rect),
+		  __entry->stage_idx, __entry->stage, __entry->sspp,
+		  __entry->multirect_idx, __entry->multirect_mode,
+		  __entry->pixel_format, __entry->modifier)
+);
+
+TRACE_EVENT(dpu_crtc_setup_lm_bounds,
+	TP_PROTO(uint32_t drm_id, int mixer, struct drm_rect *bounds),
+	TP_ARGS(drm_id, mixer, bounds),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	int,			mixer	)
+		__field_struct(	struct drm_rect,	bounds	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->mixer = mixer;
+		__entry->bounds = *bounds;
+	),
+	TP_printk("id:%u mixer:%d bounds:" DRM_RECT_FMT, __entry->drm_id,
+		  __entry->mixer, DRM_RECT_ARG(&__entry->bounds))
+);
+
+TRACE_EVENT(dpu_crtc_vblank_enable,
+	TP_PROTO(uint32_t drm_id, uint32_t enc_id, bool enable,
+		 struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enc_id, enable, crtc),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	uint32_t,		enc_id	)
+		__field(	bool,			enable	)
+		__field(	bool,			enabled )
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->enc_id = enc_id;
+		__entry->enable = enable;
+		__entry->enabled = crtc->enabled;
+	),
+	TP_printk("id:%u encoder:%u enable:%s state{enabled:%s}",
+		  __entry->drm_id, __entry->enc_id,
+		  __entry->enable ? "true" : "false",
+		  __entry->enabled ? "true" : "false")
+);
+
+DECLARE_EVENT_CLASS(dpu_crtc_enable_template,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	bool,			enable	)
+		__field(	bool,			enabled )
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->enable = enable;
+		__entry->enabled = crtc->enabled;
+	),
+	TP_printk("id:%u enable:%s state{enabled:%s}",
+		  __entry->drm_id, __entry->enable ? "true" : "false",
+		  __entry->enabled ? "true" : "false")
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_enable,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_disable,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_vblank,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+
+TRACE_EVENT(dpu_crtc_disable_frame_pending,
+	TP_PROTO(uint32_t drm_id, int frame_pending),
+	TP_ARGS(drm_id, frame_pending),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	int,			frame_pending	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->frame_pending = frame_pending;
+	),
+	TP_printk("id:%u frame_pending:%d", __entry->drm_id,
+		  __entry->frame_pending)
+);
+
+TRACE_EVENT(dpu_plane_set_scanout,
+	TP_PROTO(enum dpu_sspp index, struct dpu_hw_fmt_layout *layout,
+		 enum dpu_sspp_multirect_index multirect_index),
+	TP_ARGS(index, layout, multirect_index),
+	TP_STRUCT__entry(
+		__field(	enum dpu_sspp,			index	)
+		__field_struct(	struct dpu_hw_fmt_layout,	layout	)
+		__field(	enum dpu_sspp_multirect_index,	multirect_index)
+	),
+	TP_fast_assign(
+		__entry->index = index;
+		__entry->layout = *layout;
+		__entry->multirect_index = multirect_index;
+	),
+	TP_printk("index:%d layout:{%ux%u @ [%u/%u, %u/%u, %u/%u, %u/%u]} "
+		  "multirect_index:%d", __entry->index, __entry->layout.width,
+		  __entry->layout.height, __entry->layout.plane_addr[0],
+		  __entry->layout.plane_size[0],
+		  __entry->layout.plane_addr[1],
+		  __entry->layout.plane_size[1],
+		  __entry->layout.plane_addr[2],
+		  __entry->layout.plane_size[2],
+		  __entry->layout.plane_addr[3],
+		  __entry->layout.plane_size[3], __entry->multirect_index)
+);
+
+TRACE_EVENT(dpu_plane_disable,
+	TP_PROTO(uint32_t drm_id, bool is_virtual, uint32_t multirect_mode),
+	TP_ARGS(drm_id, is_virtual, multirect_mode),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	bool,			is_virtual	)
+		__field(	uint32_t,		multirect_mode	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->is_virtual = is_virtual;
+		__entry->multirect_mode = multirect_mode;
+	),
+	TP_printk("id:%u is_virtual:%s multirect_mode:%u", __entry->drm_id,
+		  __entry->is_virtual ? "true" : "false",
+		  __entry->multirect_mode)
+);
+
+DECLARE_EVENT_CLASS(dpu_rm_iter_template,
+	TP_PROTO(uint32_t id, uint32_t enc_id),
+	TP_ARGS(id, enc_id),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		id	)
+		__field(	uint32_t,		enc_id	)
+	),
+	TP_fast_assign(
+		__entry->id = id;
+		__entry->enc_id = enc_id;
+	),
+	TP_printk("id:%d enc_id:%u", __entry->id, __entry->enc_id)
+);
+DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_intf,
+	TP_PROTO(uint32_t id, uint32_t enc_id),
+	TP_ARGS(id, enc_id)
+);
+DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_ctls,
+	TP_PROTO(uint32_t id, uint32_t enc_id),
+	TP_ARGS(id, enc_id)
+);
+
+TRACE_EVENT(dpu_rm_reserve_lms,
+	TP_PROTO(uint32_t id, uint32_t enc_id, uint32_t pp_id),
+	TP_ARGS(id, enc_id, pp_id),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		id	)
+		__field(	uint32_t,		enc_id	)
+		__field(	uint32_t,		pp_id	)
+	),
+	TP_fast_assign(
+		__entry->id = id;
+		__entry->enc_id = enc_id;
+		__entry->pp_id = pp_id;
+	),
+	TP_printk("id:%d enc_id:%u pp_id:%u", __entry->id,
+		  __entry->enc_id, __entry->pp_id)
+);
+
+TRACE_EVENT(dpu_vbif_wait_xin_halt_fail,
+	TP_PROTO(enum dpu_vbif index, u32 xin_id),
+	TP_ARGS(index, xin_id),
+	TP_STRUCT__entry(
+		__field(	enum dpu_vbif,	index	)
+		__field(	u32,		xin_id	)
+	),
+	TP_fast_assign(
+		__entry->index = index;
+		__entry->xin_id = xin_id;
+	),
+	TP_printk("index:%d xin_id:%u", __entry->index, __entry->xin_id)
+);
+
+TRACE_EVENT(dpu_pp_connect_ext_te,
+	TP_PROTO(enum dpu_pingpong pp, u32 cfg),
+	TP_ARGS(pp, cfg),
+	TP_STRUCT__entry(
+		__field(	enum dpu_pingpong,	pp	)
+		__field(	u32,			cfg	)
+	),
+	TP_fast_assign(
+		__entry->pp = pp;
+		__entry->cfg = cfg;
+	),
+	TP_printk("pp:%d cfg:%u", __entry->pp, __entry->cfg)
+);
+
+TRACE_EVENT(dpu_core_irq_register_callback,
+	TP_PROTO(int irq_idx, void *callback),
+	TP_ARGS(irq_idx, callback),
+	TP_STRUCT__entry(
+		__field(	int,				irq_idx	)
+		__field(	void *,				callback)
+	),
+	TP_fast_assign(
+		__entry->irq_idx = irq_idx;
+		__entry->callback = callback;
+	),
+	TP_printk("irq_idx:%d callback:%ps", __entry->irq_idx,
+		  __entry->callback)
+);
+
+TRACE_EVENT(dpu_core_irq_unregister_callback,
+	TP_PROTO(int irq_idx),
+	TP_ARGS(irq_idx),
+	TP_STRUCT__entry(
+		__field(	int,				irq_idx	)
+	),
+	TP_fast_assign(
+		__entry->irq_idx = irq_idx;
+	),
+	TP_printk("irq_idx:%d", __entry->irq_idx)
+);
+
+TRACE_EVENT(dpu_core_perf_update_clk,
+	TP_PROTO(struct drm_device *dev, bool stop_req, u64 clk_rate),
+	TP_ARGS(dev, stop_req, clk_rate),
+	TP_STRUCT__entry(
+		__string(	dev_name,		dev->unique	)
+		__field(	bool,			stop_req	)
+		__field(	u64,			clk_rate	)
+	),
+	TP_fast_assign(
+		__assign_str(dev_name, dev->unique);
+		__entry->stop_req = stop_req;
+		__entry->clk_rate = clk_rate;
+	),
+	TP_printk("dev:%s stop_req:%s clk_rate:%llu", __get_str(dev_name),
+		  __entry->stop_req ? "true" : "false", __entry->clk_rate)
+);
+
+TRACE_EVENT(dpu_hw_ctl_update_pending_flush,
+	TP_PROTO(u32 new_bits, u32 pending_mask),
+	TP_ARGS(new_bits, pending_mask),
+	TP_STRUCT__entry(
+		__field(	u32,			new_bits	)
+		__field(	u32,			pending_mask	)
+	),
+	TP_fast_assign(
+		__entry->new_bits = new_bits;
+		__entry->pending_mask = pending_mask;
+	),
+	TP_printk("new=%x existing=%x", __entry->new_bits,
+		  __entry->pending_mask)
+);
+
+DECLARE_EVENT_CLASS(dpu_hw_ctl_pending_flush_template,
+	TP_PROTO(u32 pending_mask, u32 ctl_flush),
+	TP_ARGS(pending_mask, ctl_flush),
+	TP_STRUCT__entry(
+		__field(	u32,			pending_mask	)
+		__field(	u32,			ctl_flush	)
+	),
+	TP_fast_assign(
+		__entry->pending_mask = pending_mask;
+		__entry->ctl_flush = ctl_flush;
+	),
+	TP_printk("pending_mask=%x CTL_FLUSH=%x", __entry->pending_mask,
+		  __entry->ctl_flush)
+);
+DEFINE_EVENT(dpu_hw_ctl_pending_flush_template, dpu_hw_ctl_clear_pending_flush,
+	TP_PROTO(u32 pending_mask, u32 ctl_flush),
+	TP_ARGS(pending_mask, ctl_flush)
+);
+DEFINE_EVENT(dpu_hw_ctl_pending_flush_template,
+	     dpu_hw_ctl_trigger_pending_flush,
+	TP_PROTO(u32 pending_mask, u32 ctl_flush),
+	TP_ARGS(pending_mask, ctl_flush)
+);
+DEFINE_EVENT(dpu_hw_ctl_pending_flush_template, dpu_hw_ctl_trigger_prepare,
+	TP_PROTO(u32 pending_mask, u32 ctl_flush),
+	TP_ARGS(pending_mask, ctl_flush)
+);
+DEFINE_EVENT(dpu_hw_ctl_pending_flush_template, dpu_hw_ctl_trigger_start,
+	TP_PROTO(u32 pending_mask, u32 ctl_flush),
+	TP_ARGS(pending_mask, ctl_flush)
+);
+
+#define DPU_ATRACE_END(name) trace_tracing_mark_write(current->tgid, name, 0)
+#define DPU_ATRACE_BEGIN(name) trace_tracing_mark_write(current->tgid, name, 1)
+#define DPU_ATRACE_FUNC() DPU_ATRACE_BEGIN(__func__)
+
+#define DPU_ATRACE_INT(name, value) \
+	trace_dpu_trace_counter(current->tgid, name, value)
+
+#endif /* _DPU_TRACE_H_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#include <trace/define_trace.h>
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
new file mode 100644
index 000000000..1305e250b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+
+#include "dpu_vbif.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_trace.h"
+
+static struct dpu_hw_vbif *dpu_get_vbif(struct dpu_kms *dpu_kms, enum dpu_vbif vbif_idx)
+{
+	if (vbif_idx < ARRAY_SIZE(dpu_kms->hw_vbif))
+		return dpu_kms->hw_vbif[vbif_idx];
+
+	return NULL;
+}
+
+static const char *dpu_vbif_name(enum dpu_vbif idx)
+{
+	switch (idx) {
+	case VBIF_RT:
+		return "VBIF_RT";
+	case VBIF_NRT:
+		return "VBIF_NRT";
+	default:
+		return "??";
+	}
+}
+
+/**
+ * _dpu_vbif_wait_for_xin_halt - wait for the xin to halt
+ * @vbif:	Pointer to hardware vbif driver
+ * @xin_id:	Client interface identifier
+ * @return:	0 if success; error code otherwise
+ */
+static int _dpu_vbif_wait_for_xin_halt(struct dpu_hw_vbif *vbif, u32 xin_id)
+{
+	ktime_t timeout;
+	bool status;
+	int rc;
+
+	if (!vbif || !vbif->cap || !vbif->ops.get_halt_ctrl) {
+		DPU_ERROR("invalid arguments vbif %d\n", vbif != NULL);
+		return -EINVAL;
+	}
+
+	timeout = ktime_add_us(ktime_get(), vbif->cap->xin_halt_timeout);
+	for (;;) {
+		status = vbif->ops.get_halt_ctrl(vbif, xin_id);
+		if (status)
+			break;
+		if (ktime_compare_safe(ktime_get(), timeout) > 0) {
+			status = vbif->ops.get_halt_ctrl(vbif, xin_id);
+			break;
+		}
+		usleep_range(501, 1000);
+	}
+
+	if (!status) {
+		rc = -ETIMEDOUT;
+		DPU_ERROR("%s client %d not halting. TIMEDOUT.\n",
+				dpu_vbif_name(vbif->idx), xin_id);
+	} else {
+		rc = 0;
+		DRM_DEBUG_ATOMIC("%s client %d is halted\n",
+				dpu_vbif_name(vbif->idx), xin_id);
+	}
+
+	return rc;
+}
+
+/**
+ * _dpu_vbif_apply_dynamic_ot_limit - determine OT based on usecase parameters
+ * @vbif:	Pointer to hardware vbif driver
+ * @ot_lim:	Pointer to OT limit to be modified
+ * @params:	Pointer to usecase parameters
+ */
+static void _dpu_vbif_apply_dynamic_ot_limit(struct dpu_hw_vbif *vbif,
+		u32 *ot_lim, struct dpu_vbif_set_ot_params *params)
+{
+	u64 pps;
+	const struct dpu_vbif_dynamic_ot_tbl *tbl;
+	u32 i;
+
+	if (!vbif || !(vbif->cap->features & BIT(DPU_VBIF_QOS_OTLIM)))
+		return;
+
+	/* Dynamic OT setting done only for WFD */
+	if (!params->is_wfd)
+		return;
+
+	pps = params->frame_rate;
+	pps *= params->width;
+	pps *= params->height;
+
+	tbl = params->rd ? &vbif->cap->dynamic_ot_rd_tbl :
+			&vbif->cap->dynamic_ot_wr_tbl;
+
+	for (i = 0; i < tbl->count; i++) {
+		if (pps <= tbl->cfg[i].pps) {
+			*ot_lim = tbl->cfg[i].ot_limit;
+			break;
+		}
+	}
+
+	DRM_DEBUG_ATOMIC("%s xin:%d w:%d h:%d fps:%d pps:%llu ot:%u\n",
+			dpu_vbif_name(vbif->idx), params->xin_id,
+			params->width, params->height, params->frame_rate,
+			pps, *ot_lim);
+}
+
+/**
+ * _dpu_vbif_get_ot_limit - get OT based on usecase & configuration parameters
+ * @vbif:	Pointer to hardware vbif driver
+ * @params:	Pointer to usecase parameters
+ * @return:	OT limit
+ */
+static u32 _dpu_vbif_get_ot_limit(struct dpu_hw_vbif *vbif,
+	struct dpu_vbif_set_ot_params *params)
+{
+	u32 ot_lim = 0;
+	u32 val;
+
+	if (!vbif || !vbif->cap) {
+		DPU_ERROR("invalid arguments vbif %d\n", vbif != NULL);
+		return -EINVAL;
+	}
+
+	if (vbif->cap->default_ot_wr_limit && !params->rd)
+		ot_lim = vbif->cap->default_ot_wr_limit;
+	else if (vbif->cap->default_ot_rd_limit && params->rd)
+		ot_lim = vbif->cap->default_ot_rd_limit;
+
+	/*
+	 * If default ot is not set from dt/catalog,
+	 * then do not configure it.
+	 */
+	if (ot_lim == 0)
+		goto exit;
+
+	/* Modify the limits if the target and the use case requires it */
+	_dpu_vbif_apply_dynamic_ot_limit(vbif, &ot_lim, params);
+
+	if (vbif && vbif->ops.get_limit_conf) {
+		val = vbif->ops.get_limit_conf(vbif,
+				params->xin_id, params->rd);
+		if (val == ot_lim)
+			ot_lim = 0;
+	}
+
+exit:
+	DRM_DEBUG_ATOMIC("%s xin:%d ot_lim:%d\n",
+			dpu_vbif_name(vbif->idx), params->xin_id, ot_lim);
+	return ot_lim;
+}
+
+/**
+ * dpu_vbif_set_ot_limit - set OT based on usecase & configuration parameters
+ * @dpu_kms:	DPU handler
+ * @params:	Pointer to usecase parameters
+ *
+ * Note this function would block waiting for bus halt.
+ */
+void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_ot_params *params)
+{
+	struct dpu_hw_vbif *vbif;
+	struct dpu_hw_mdp *mdp;
+	bool forced_on = false;
+	u32 ot_lim;
+	int ret;
+
+	mdp = dpu_kms->hw_mdp;
+
+	vbif = dpu_get_vbif(dpu_kms, params->vbif_idx);
+	if (!vbif || !mdp) {
+		DRM_DEBUG_ATOMIC("invalid arguments vbif %d mdp %d\n",
+				vbif != NULL, mdp != NULL);
+		return;
+	}
+
+	if (!mdp->ops.setup_clk_force_ctrl ||
+			!vbif->ops.set_limit_conf ||
+			!vbif->ops.set_halt_ctrl)
+		return;
+
+	/* set write_gather_en for all write clients */
+	if (vbif->ops.set_write_gather_en && !params->rd)
+		vbif->ops.set_write_gather_en(vbif, params->xin_id);
+
+	ot_lim = _dpu_vbif_get_ot_limit(vbif, params) & 0xFF;
+
+	if (ot_lim == 0)
+		return;
+
+	trace_dpu_perf_set_ot(params->num, params->xin_id, ot_lim,
+		params->vbif_idx);
+
+	forced_on = mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, true);
+
+	vbif->ops.set_limit_conf(vbif, params->xin_id, params->rd, ot_lim);
+
+	vbif->ops.set_halt_ctrl(vbif, params->xin_id, true);
+
+	ret = _dpu_vbif_wait_for_xin_halt(vbif, params->xin_id);
+	if (ret)
+		trace_dpu_vbif_wait_xin_halt_fail(vbif->idx, params->xin_id);
+
+	vbif->ops.set_halt_ctrl(vbif, params->xin_id, false);
+
+	if (forced_on)
+		mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, false);
+}
+
+void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_qos_params *params)
+{
+	struct dpu_hw_vbif *vbif;
+	struct dpu_hw_mdp *mdp;
+	bool forced_on = false;
+	const struct dpu_vbif_qos_tbl *qos_tbl;
+	int i;
+
+	if (!params || !dpu_kms->hw_mdp) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+	mdp = dpu_kms->hw_mdp;
+
+	vbif = dpu_get_vbif(dpu_kms, params->vbif_idx);
+
+	if (!vbif || !vbif->cap) {
+		DPU_ERROR("invalid vbif %d\n", params->vbif_idx);
+		return;
+	}
+
+	if (!vbif->ops.set_qos_remap || !mdp->ops.setup_clk_force_ctrl) {
+		DRM_DEBUG_ATOMIC("qos remap not supported\n");
+		return;
+	}
+
+	qos_tbl = params->is_rt ? &vbif->cap->qos_rt_tbl :
+			&vbif->cap->qos_nrt_tbl;
+
+	if (!qos_tbl->npriority_lvl || !qos_tbl->priority_lvl) {
+		DRM_DEBUG_ATOMIC("qos tbl not defined\n");
+		return;
+	}
+
+	forced_on = mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, true);
+
+	for (i = 0; i < qos_tbl->npriority_lvl; i++) {
+		DRM_DEBUG_ATOMIC("%s xin:%d lvl:%d/%d\n",
+				dpu_vbif_name(params->vbif_idx), params->xin_id, i,
+				qos_tbl->priority_lvl[i]);
+		vbif->ops.set_qos_remap(vbif, params->xin_id, i,
+				qos_tbl->priority_lvl[i]);
+	}
+
+	if (forced_on)
+		mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, false);
+}
+
+void dpu_vbif_clear_errors(struct dpu_kms *dpu_kms)
+{
+	struct dpu_hw_vbif *vbif;
+	u32 i, pnd, src;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		vbif = dpu_kms->hw_vbif[i];
+		if (vbif && vbif->ops.clear_errors) {
+			vbif->ops.clear_errors(vbif, &pnd, &src);
+			if (pnd || src) {
+				DRM_DEBUG_KMS("%s: pnd 0x%X, src 0x%X\n",
+					      dpu_vbif_name(vbif->idx), pnd, src);
+			}
+		}
+	}
+}
+
+void dpu_vbif_init_memtypes(struct dpu_kms *dpu_kms)
+{
+	struct dpu_hw_vbif *vbif;
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		vbif = dpu_kms->hw_vbif[i];
+		if (vbif && vbif->cap && vbif->ops.set_mem_type) {
+			for (j = 0; j < vbif->cap->memtype_count; j++)
+				vbif->ops.set_mem_type(
+						vbif, j, vbif->cap->memtype[j]);
+		}
+	}
+}
+
+#ifdef CONFIG_DEBUG_FS
+
+void dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
+{
+	char vbif_name[32];
+	struct dentry *entry, *debugfs_vbif;
+	int i, j;
+
+	entry = debugfs_create_dir("vbif", debugfs_root);
+
+	for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
+		const struct dpu_vbif_cfg *vbif = &dpu_kms->catalog->vbif[i];
+
+		snprintf(vbif_name, sizeof(vbif_name), "%d", vbif->id);
+
+		debugfs_vbif = debugfs_create_dir(vbif_name, entry);
+
+		debugfs_create_u32("features", 0600, debugfs_vbif,
+			(u32 *)&vbif->features);
+
+		debugfs_create_u32("xin_halt_timeout", 0400, debugfs_vbif,
+			(u32 *)&vbif->xin_halt_timeout);
+
+		debugfs_create_u32("default_rd_ot_limit", 0400, debugfs_vbif,
+			(u32 *)&vbif->default_ot_rd_limit);
+
+		debugfs_create_u32("default_wr_ot_limit", 0400, debugfs_vbif,
+			(u32 *)&vbif->default_ot_wr_limit);
+
+		for (j = 0; j < vbif->dynamic_ot_rd_tbl.count; j++) {
+			const struct dpu_vbif_dynamic_ot_cfg *cfg =
+					&vbif->dynamic_ot_rd_tbl.cfg[j];
+
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_rd_%d_pps", j);
+			debugfs_create_u64(vbif_name, 0400, debugfs_vbif,
+					(u64 *)&cfg->pps);
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_rd_%d_ot_limit", j);
+			debugfs_create_u32(vbif_name, 0400, debugfs_vbif,
+					(u32 *)&cfg->ot_limit);
+		}
+
+		for (j = 0; j < vbif->dynamic_ot_wr_tbl.count; j++) {
+			const struct dpu_vbif_dynamic_ot_cfg *cfg =
+					&vbif->dynamic_ot_wr_tbl.cfg[j];
+
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_wr_%d_pps", j);
+			debugfs_create_u64(vbif_name, 0400, debugfs_vbif,
+					(u64 *)&cfg->pps);
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_wr_%d_ot_limit", j);
+			debugfs_create_u32(vbif_name, 0400, debugfs_vbif,
+					(u32 *)&cfg->ot_limit);
+		}
+	}
+}
+#endif
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
new file mode 100644
index 000000000..ab490177d
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __DPU_VBIF_H__
+#define __DPU_VBIF_H__
+
+#include "dpu_kms.h"
+
+struct dpu_vbif_set_ot_params {
+	u32 xin_id;
+	u32 num;
+	u32 width;
+	u32 height;
+	u32 frame_rate;
+	bool rd;
+	bool is_wfd;
+	u32 vbif_idx;
+	u32 clk_ctrl;
+};
+
+struct dpu_vbif_set_memtype_params {
+	u32 xin_id;
+	u32 vbif_idx;
+	u32 clk_ctrl;
+	bool is_cacheable;
+};
+
+/**
+ * struct dpu_vbif_set_qos_params - QoS remapper parameter
+ * @vbif_idx: vbif identifier
+ * @xin_id: client interface identifier
+ * @clk_ctrl: clock control identifier of the xin
+ * @num: pipe identifier (debug only)
+ * @is_rt: true if pipe is used in real-time use case
+ */
+struct dpu_vbif_set_qos_params {
+	u32 vbif_idx;
+	u32 xin_id;
+	u32 clk_ctrl;
+	u32 num;
+	bool is_rt;
+};
+
+/**
+ * dpu_vbif_set_ot_limit - set OT limit for vbif client
+ * @dpu_kms:	DPU handler
+ * @params:	Pointer to OT configuration parameters
+ */
+void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_ot_params *params);
+
+/**
+ * dpu_vbif_set_qos_remap - set QoS priority level remap
+ * @dpu_kms:	DPU handler
+ * @params:	Pointer to QoS configuration parameters
+ */
+void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_qos_params *params);
+
+/**
+ * dpu_vbif_clear_errors - clear any vbif errors
+ * @dpu_kms:	DPU handler
+ */
+void dpu_vbif_clear_errors(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_vbif_init_memtypes - initialize xin memory types for vbif
+ * @dpu_kms:	DPU handler
+ */
+void dpu_vbif_init_memtypes(struct dpu_kms *dpu_kms);
+
+void dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root);
+
+#endif /* __DPU_VBIF_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
new file mode 100644
index 000000000..2a5a68366
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <drm/drm_edid.h>
+
+#include "dpu_writeback.h"
+
+static int dpu_wb_conn_get_modes(struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
+
+	/*
+	 * We should ideally be limiting the modes only to the maxlinewidth but
+	 * on some chipsets this will allow even 4k modes to be added which will
+	 * fail the per SSPP bandwidth checks. So, till we have dual-SSPP support
+	 * and source split support added lets limit the modes based on max_mixer_width
+	 * as 4K modes can then be supported.
+	 */
+	return drm_add_modes_noedid(connector, dpu_kms->catalog->caps->max_mixer_width,
+			dev->mode_config.max_height);
+}
+
+static const struct drm_connector_funcs dpu_wb_conn_funcs = {
+	.reset = drm_atomic_helper_connector_reset,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = drm_connector_cleanup,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static int dpu_wb_conn_prepare_job(struct drm_writeback_connector *connector,
+		struct drm_writeback_job *job)
+{
+
+	struct dpu_wb_connector *dpu_wb_conn = to_dpu_wb_conn(connector);
+
+	if (!job->fb)
+		return 0;
+
+	dpu_encoder_prepare_wb_job(dpu_wb_conn->wb_enc, job);
+
+	return 0;
+}
+
+static void dpu_wb_conn_cleanup_job(struct drm_writeback_connector *connector,
+		struct drm_writeback_job *job)
+{
+	struct dpu_wb_connector *dpu_wb_conn = to_dpu_wb_conn(connector);
+
+	if (!job->fb)
+		return;
+
+	dpu_encoder_cleanup_wb_job(dpu_wb_conn->wb_enc, job);
+}
+
+static const struct drm_connector_helper_funcs dpu_wb_conn_helper_funcs = {
+	.get_modes = dpu_wb_conn_get_modes,
+	.prepare_writeback_job = dpu_wb_conn_prepare_job,
+	.cleanup_writeback_job = dpu_wb_conn_cleanup_job,
+};
+
+int dpu_writeback_init(struct drm_device *dev, struct drm_encoder *enc,
+		const u32 *format_list, u32 num_formats)
+{
+	struct dpu_wb_connector *dpu_wb_conn;
+	int rc = 0;
+
+	dpu_wb_conn = devm_kzalloc(dev->dev, sizeof(*dpu_wb_conn), GFP_KERNEL);
+	if (!dpu_wb_conn)
+		return -ENOMEM;
+
+	drm_connector_helper_add(&dpu_wb_conn->base.base, &dpu_wb_conn_helper_funcs);
+
+	/* DPU initializes the encoder and sets it up completely for writeback
+	 * cases and hence should use the new API drm_writeback_connector_init_with_encoder
+	 * to initialize the writeback connector
+	 */
+	rc = drm_writeback_connector_init_with_encoder(dev, &dpu_wb_conn->base, enc,
+			&dpu_wb_conn_funcs, format_list, num_formats);
+
+	if (!rc)
+		dpu_wb_conn->wb_enc = enc;
+
+	return rc;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.h
new file mode 100644
index 000000000..5a75ea916
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _DPU_WRITEBACK_H
+#define _DPU_WRITEBACK_H
+
+#include <drm/drm_crtc.h>
+#include <drm/drm_file.h>
+#include <drm/drm_probe_helper.h>
+#include <drm/drm_writeback.h>
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include "dpu_encoder_phys.h"
+
+struct dpu_wb_connector {
+	struct drm_writeback_connector base;
+	struct drm_encoder *wb_enc;
+};
+
+static inline struct dpu_wb_connector *to_dpu_wb_conn(struct drm_writeback_connector *conn)
+{
+	return container_of(conn, struct dpu_wb_connector, base);
+}
+
+int dpu_writeback_init(struct drm_device *dev, struct drm_encoder *enc,
+		const u32 *format_list, u32 num_formats);
+
+#endif /*_DPU_WRITEBACK_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h b/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h
new file mode 100644
index 000000000..9fc9dbde8
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h
@@ -0,0 +1,1155 @@
+#ifndef __MEDIA_INFO_H__
+#define __MEDIA_INFO_H__
+
+#ifndef MSM_MEDIA_ALIGN
+#define MSM_MEDIA_ALIGN(__sz, __align) (((__align) & ((__align) - 1)) ?\
+	((((__sz) + (__align) - 1) / (__align)) * (__align)) :\
+	(((__sz) + (__align) - 1) & (~((__align) - 1))))
+#endif
+
+#ifndef MSM_MEDIA_ROUNDUP
+#define MSM_MEDIA_ROUNDUP(__sz, __r) (((__sz) + ((__r) - 1)) / (__r))
+#endif
+
+#ifndef MSM_MEDIA_MAX
+#define MSM_MEDIA_MAX(__a, __b) ((__a) > (__b)?(__a):(__b))
+#endif
+
+enum color_fmts {
+	/* Venus NV12:
+	 * YUV 4:2:0 image with a plane of 8 bit Y samples followed
+	 * by an interleaved U/V plane containing 8 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 * U V U V U V U V U V U V . . . .  ^
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  --> Buffer size alignment
+	 *
+	 * Y_Stride : Width aligned to 128
+	 * UV_Stride : Width aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((Y_Stride * Y_Scanlines
+	 *          + UV_Stride * UV_Scanlines
+	 *          + max(Extradata, Y_Stride * 8), 4096)
+	 */
+	COLOR_FMT_NV12,
+
+	/* Venus NV21:
+	 * YUV 4:2:0 image with a plane of 8 bit Y samples followed
+	 * by an interleaved V/U plane containing 8 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 * V U V U V U V U V U V U . . . .  ^
+	 * V U V U V U V U V U V U . . . .  |
+	 * V U V U V U V U V U V U . . . .  |
+	 * V U V U V U V U V U V U . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  --> Padding & Buffer size alignment
+	 *
+	 * Y_Stride : Width aligned to 128
+	 * UV_Stride : Width aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((Y_Stride * Y_Scanlines
+	 *          + UV_Stride * UV_Scanlines
+	 *          + max(Extradata, Y_Stride * 8), 4096)
+	 */
+	COLOR_FMT_NV21,
+	/* Venus NV12_MVTB:
+	 * Two YUV 4:2:0 images/views one after the other
+	 * in a top-bottom layout, same as NV12
+	 * with a plane of 8 bit Y samples followed
+	 * by an interleaved U/V plane containing 8 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^               ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |               |
+	 * . . . . . . . . . . . . . . . .              |             View_1
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              V               |
+	 * U V U V U V U V U V U V . . . .  ^                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines                |
+	 * . . . . . . . . . . . . . . . .  |                           |
+	 * . . . . . . . . . . . . . . . .  V                           V
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^               ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |               |
+	 * . . . . . . . . . . . . . . . .              |             View_2
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              V               |
+	 * U V U V U V U V U V U V . . . .  ^                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines                |
+	 * . . . . . . . . . . . . . . . .  |                           |
+	 * . . . . . . . . . . . . . . . .  V                           V
+	 * . . . . . . . . . . . . . . . .  --> Buffer size alignment
+	 *
+	 * Y_Stride : Width aligned to 128
+	 * UV_Stride : Width aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * View_1 begin at: 0 (zero)
+	 * View_2 begin at: Y_Stride * Y_Scanlines + UV_Stride * UV_Scanlines
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((2*(Y_Stride * Y_Scanlines)
+	 *          + 2*(UV_Stride * UV_Scanlines) + Extradata), 4096)
+	 */
+	COLOR_FMT_NV12_MVTB,
+	/*
+	 * The buffer can be of 2 types:
+	 * (1) Venus NV12 UBWC Progressive
+	 * (2) Venus NV12 UBWC Interlaced
+	 *
+	 * (1) Venus NV12 UBWC Progressive Buffer Format:
+	 * Compressed Macro-tile format for NV12.
+	 * Contains 4 planes in the following order -
+	 * (A) Y_Meta_Plane
+	 * (B) Y_UBWC_Plane
+	 * (C) UV_Meta_Plane
+	 * (D) UV_UBWC_Plane
+	 *
+	 * Y_Meta_Plane consists of meta information to decode compressed
+	 * tile data in Y_UBWC_Plane.
+	 * Y_UBWC_Plane consists of Y data in compressed macro-tile format.
+	 * UBWC decoder block will use the Y_Meta_Plane data together with
+	 * Y_UBWC_Plane data to produce loss-less uncompressed 8 bit Y samples.
+	 *
+	 * UV_Meta_Plane consists of meta information to decode compressed
+	 * tile data in UV_UBWC_Plane.
+	 * UV_UBWC_Plane consists of UV data in compressed macro-tile format.
+	 * UBWC decoder block will use UV_Meta_Plane data together with
+	 * UV_UBWC_Plane data to produce loss-less uncompressed 8 bit 2x2
+	 * subsampled color difference samples.
+	 *
+	 * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
+	 * and randomly accessible. There is no dependency between tiles.
+	 *
+	 * <----- Y_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <--Compressed tile Y Stride--->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  Height      |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----- UV_Meta_Stride ---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <--Compressed tile UV Stride--->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 * Y_Stride = align(Width, 128)
+	 * UV_Stride = align(Width, 128)
+	 * Y_Scanlines = align(Height, 32)
+	 * UV_Scanlines = align(Height/2, 16)
+	 * Y_UBWC_Plane_size = align(Y_Stride * Y_Scanlines, 4096)
+	 * UV_UBWC_Plane_size = align(UV_Stride * UV_Scanlines, 4096)
+	 * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16)
+	 * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096)
+	 * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16)
+	 * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align( Y_UBWC_Plane_size + UV_UBWC_Plane_size +
+	 *           Y_Meta_Plane_size + UV_Meta_Plane_size
+	 *           + max(Extradata, Y_Stride * 48), 4096)
+	 *
+	 *
+	 * (2) Venus NV12 UBWC Interlaced Buffer Format:
+	 * Compressed Macro-tile format for NV12 interlaced.
+	 * Contains 8 planes in the following order -
+	 * (A) Y_Meta_Top_Field_Plane
+	 * (B) Y_UBWC_Top_Field_Plane
+	 * (C) UV_Meta_Top_Field_Plane
+	 * (D) UV_UBWC_Top_Field_Plane
+	 * (E) Y_Meta_Bottom_Field_Plane
+	 * (F) Y_UBWC_Bottom_Field_Plane
+	 * (G) UV_Meta_Bottom_Field_Plane
+	 * (H) UV_UBWC_Bottom_Field_Plane
+	 * Y_Meta_Top_Field_Plane consists of meta information to decode
+	 * compressed tile data for Y_UBWC_Top_Field_Plane.
+	 * Y_UBWC_Top_Field_Plane consists of Y data in compressed macro-tile
+	 * format for top field of an interlaced frame.
+	 * UBWC decoder block will use the Y_Meta_Top_Field_Plane data together
+	 * with Y_UBWC_Top_Field_Plane data to produce loss-less uncompressed
+	 * 8 bit Y samples for top field of an interlaced frame.
+	 *
+	 * UV_Meta_Top_Field_Plane consists of meta information to decode
+	 * compressed tile data in UV_UBWC_Top_Field_Plane.
+	 * UV_UBWC_Top_Field_Plane consists of UV data in compressed macro-tile
+	 * format for top field of an interlaced frame.
+	 * UBWC decoder block will use UV_Meta_Top_Field_Plane data together
+	 * with UV_UBWC_Top_Field_Plane data to produce loss-less uncompressed
+	 * 8 bit subsampled color difference samples for top field of an
+	 * interlaced frame.
+	 *
+	 * Each tile in Y_UBWC_Top_Field_Plane/UV_UBWC_Top_Field_Plane is
+	 * independently decodable and randomly accessible. There is no
+	 * dependency between tiles.
+	 *
+	 * Y_Meta_Bottom_Field_Plane consists of meta information to decode
+	 * compressed tile data for Y_UBWC_Bottom_Field_Plane.
+	 * Y_UBWC_Bottom_Field_Plane consists of Y data in compressed macro-tile
+	 * format for bottom field of an interlaced frame.
+	 * UBWC decoder block will use the Y_Meta_Bottom_Field_Plane data
+	 * together with Y_UBWC_Bottom_Field_Plane data to produce loss-less
+	 * uncompressed 8 bit Y samples for bottom field of an interlaced frame.
+	 *
+	 * UV_Meta_Bottom_Field_Plane consists of meta information to decode
+	 * compressed tile data in UV_UBWC_Bottom_Field_Plane.
+	 * UV_UBWC_Bottom_Field_Plane consists of UV data in compressed
+	 * macro-tile format for bottom field of an interlaced frame.
+	 * UBWC decoder block will use UV_Meta_Bottom_Field_Plane data together
+	 * with UV_UBWC_Bottom_Field_Plane data to produce loss-less
+	 * uncompressed 8 bit subsampled color difference samples for bottom
+	 * field of an interlaced frame.
+	 *
+	 * Each tile in Y_UBWC_Bottom_Field_Plane/UV_UBWC_Bottom_Field_Plane is
+	 * independently decodable and randomly accessible. There is no
+	 * dependency between tiles.
+	 *
+	 * <-----Y_TF_Meta_Stride---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . . Half_height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_TF_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-Compressed tile Y_TF Stride->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Half_height  |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_TF_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----UV_TF_Meta_Stride---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_TF_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <-Compressed tile UV_TF Stride->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_TF_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * <-----Y_BF_Meta_Stride---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . . Half_height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_BF_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-Compressed tile Y_BF Stride->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Half_height  |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_BF_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----UV_BF_Meta_Stride---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_BF_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <-Compressed tile UV_BF Stride->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_BF_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 * Half_height = (Height+1)>>1
+	 * Y_TF_Stride = align(Width, 128)
+	 * UV_TF_Stride = align(Width, 128)
+	 * Y_TF_Scanlines = align(Half_height, 32)
+	 * UV_TF_Scanlines = align((Half_height+1)/2, 32)
+	 * Y_UBWC_TF_Plane_size = align(Y_TF_Stride * Y_TF_Scanlines, 4096)
+	 * UV_UBWC_TF_Plane_size = align(UV_TF_Stride * UV_TF_Scanlines, 4096)
+	 * Y_TF_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_TF_Meta_Scanlines = align(roundup(Half_height, Y_TileHeight), 16)
+	 * Y_TF_Meta_Plane_size =
+	 *     align(Y_TF_Meta_Stride * Y_TF_Meta_Scanlines, 4096)
+	 * UV_TF_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_TF_Meta_Scanlines = align(roundup(Half_height, UV_TileHeight), 16)
+	 * UV_TF_Meta_Plane_size =
+	 *     align(UV_TF_Meta_Stride * UV_TF_Meta_Scanlines, 4096)
+	 * Y_BF_Stride = align(Width, 128)
+	 * UV_BF_Stride = align(Width, 128)
+	 * Y_BF_Scanlines = align(Half_height, 32)
+	 * UV_BF_Scanlines = align((Half_height+1)/2, 32)
+	 * Y_UBWC_BF_Plane_size = align(Y_BF_Stride * Y_BF_Scanlines, 4096)
+	 * UV_UBWC_BF_Plane_size = align(UV_BF_Stride * UV_BF_Scanlines, 4096)
+	 * Y_BF_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_BF_Meta_Scanlines = align(roundup(Half_height, Y_TileHeight), 16)
+	 * Y_BF_Meta_Plane_size =
+	 *     align(Y_BF_Meta_Stride * Y_BF_Meta_Scanlines, 4096)
+	 * UV_BF_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_BF_Meta_Scanlines = align(roundup(Half_height, UV_TileHeight), 16)
+	 * UV_BF_Meta_Plane_size =
+	 *     align(UV_BF_Meta_Stride * UV_BF_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align( Y_UBWC_TF_Plane_size + UV_UBWC_TF_Plane_size +
+	 *           Y_TF_Meta_Plane_size + UV_TF_Meta_Plane_size +
+	 *			 Y_UBWC_BF_Plane_size + UV_UBWC_BF_Plane_size +
+	 *           Y_BF_Meta_Plane_size + UV_BF_Meta_Plane_size +
+	 *           + max(Extradata, Y_TF_Stride * 48), 4096)
+	 */
+	COLOR_FMT_NV12_UBWC,
+	/* Venus NV12 10-bit UBWC:
+	 * Compressed Macro-tile format for NV12.
+	 * Contains 4 planes in the following order -
+	 * (A) Y_Meta_Plane
+	 * (B) Y_UBWC_Plane
+	 * (C) UV_Meta_Plane
+	 * (D) UV_UBWC_Plane
+	 *
+	 * Y_Meta_Plane consists of meta information to decode compressed
+	 * tile data in Y_UBWC_Plane.
+	 * Y_UBWC_Plane consists of Y data in compressed macro-tile format.
+	 * UBWC decoder block will use the Y_Meta_Plane data together with
+	 * Y_UBWC_Plane data to produce loss-less uncompressed 10 bit Y samples.
+	 *
+	 * UV_Meta_Plane consists of meta information to decode compressed
+	 * tile data in UV_UBWC_Plane.
+	 * UV_UBWC_Plane consists of UV data in compressed macro-tile format.
+	 * UBWC decoder block will use UV_Meta_Plane data together with
+	 * UV_UBWC_Plane data to produce loss-less uncompressed 10 bit 2x2
+	 * subsampled color difference samples.
+	 *
+	 * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
+	 * and randomly accessible. There is no dependency between tiles.
+	 *
+	 * <----- Y_Meta_Stride ----->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <--Compressed tile Y Stride--->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  Height      |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----- UV_Meta_Stride ---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <--Compressed tile UV Stride--->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 *
+	 * Y_Stride = align(Width * 4/3, 128)
+	 * UV_Stride = align(Width * 4/3, 128)
+	 * Y_Scanlines = align(Height, 32)
+	 * UV_Scanlines = align(Height/2, 16)
+	 * Y_UBWC_Plane_Size = align(Y_Stride * Y_Scanlines, 4096)
+	 * UV_UBWC_Plane_Size = align(UV_Stride * UV_Scanlines, 4096)
+	 * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16)
+	 * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096)
+	 * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16)
+	 * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(Y_UBWC_Plane_size + UV_UBWC_Plane_size +
+	 *           Y_Meta_Plane_size + UV_Meta_Plane_size
+	 *           + max(Extradata, Y_Stride * 48), 4096)
+	 */
+	COLOR_FMT_NV12_BPP10_UBWC,
+	/* Venus RGBA8888 format:
+	 * Contains 1 plane in the following order -
+	 * (A) RGBA plane
+	 *
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 4, 128)
+	 * RGB_Scanlines = align(Height, 32)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Plane_size + Extradata, 4096)
+	 */
+	COLOR_FMT_RGBA8888,
+	/* Venus RGBA8888 UBWC format:
+	 * Contains 2 planes in the following order -
+	 * (A) Meta plane
+	 * (B) RGBA plane
+	 *
+	 * <--- RGB_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |       Meta_RGB_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .    -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 4, 128)
+	 * RGB_Scanlines = align(Height, 32)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64)
+	 * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16)
+	 * RGB_Meta_Plane_size = align(RGB_Meta_Stride *
+	 *		RGB_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size +
+	 *		Extradata, 4096)
+	 */
+	COLOR_FMT_RGBA8888_UBWC,
+	/* Venus RGBA1010102 UBWC format:
+	 * Contains 2 planes in the following order -
+	 * (A) Meta plane
+	 * (B) RGBA plane
+	 *
+	 * <--- RGB_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |       Meta_RGB_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .    -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 4, 256)
+	 * RGB_Scanlines = align(Height, 16)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64)
+	 * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16)
+	 * RGB_Meta_Plane_size = align(RGB_Meta_Stride *
+	 *		RGB_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size +
+	 *		Extradata, 4096)
+	 */
+	COLOR_FMT_RGBA1010102_UBWC,
+	/* Venus RGB565 UBWC format:
+	 * Contains 2 planes in the following order -
+	 * (A) Meta plane
+	 * (B) RGB plane
+	 *
+	 * <--- RGB_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |       Meta_RGB_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .    -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 2, 128)
+	 * RGB_Scanlines = align(Height, 16)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64)
+	 * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16)
+	 * RGB_Meta_Plane_size = align(RGB_Meta_Stride *
+	 *		RGB_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size +
+	 *		Extradata, 4096)
+	 */
+	COLOR_FMT_RGB565_UBWC,
+	/* P010 UBWC:
+	 * Compressed Macro-tile format for NV12.
+	 * Contains 4 planes in the following order -
+	 * (A) Y_Meta_Plane
+	 * (B) Y_UBWC_Plane
+	 * (C) UV_Meta_Plane
+	 * (D) UV_UBWC_Plane
+	 *
+	 * Y_Meta_Plane consists of meta information to decode compressed
+	 * tile data in Y_UBWC_Plane.
+	 * Y_UBWC_Plane consists of Y data in compressed macro-tile format.
+	 * UBWC decoder block will use the Y_Meta_Plane data together with
+	 * Y_UBWC_Plane data to produce loss-less uncompressed 10 bit Y samples.
+	 *
+	 * UV_Meta_Plane consists of meta information to decode compressed
+	 * tile data in UV_UBWC_Plane.
+	 * UV_UBWC_Plane consists of UV data in compressed macro-tile format.
+	 * UBWC decoder block will use UV_Meta_Plane data together with
+	 * UV_UBWC_Plane data to produce loss-less uncompressed 10 bit 2x2
+	 * subsampled color difference samples.
+	 *
+	 * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
+	 * and randomly accessible. There is no dependency between tiles.
+	 *
+	 * <----- Y_Meta_Stride ----->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <--Compressed tile Y Stride--->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  Height      |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----- UV_Meta_Stride ---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <--Compressed tile UV Stride--->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 *
+	 * Y_Stride = align(Width * 2, 256)
+	 * UV_Stride = align(Width * 2, 256)
+	 * Y_Scanlines = align(Height, 16)
+	 * UV_Scanlines = align(Height/2, 16)
+	 * Y_UBWC_Plane_Size = align(Y_Stride * Y_Scanlines, 4096)
+	 * UV_UBWC_Plane_Size = align(UV_Stride * UV_Scanlines, 4096)
+	 * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16)
+	 * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096)
+	 * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16)
+	 * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(Y_UBWC_Plane_size + UV_UBWC_Plane_size +
+	 *           Y_Meta_Plane_size + UV_Meta_Plane_size
+	 *           + max(Extradata, Y_Stride * 48), 4096)
+	 */
+	COLOR_FMT_P010_UBWC,
+	/* Venus P010:
+	 * YUV 4:2:0 image with a plane of 10 bit Y samples followed
+	 * by an interleaved U/V plane containing 10 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 * U V U V U V U V U V U V . . . .  ^
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  --> Buffer size alignment
+	 *
+	 * Y_Stride : Width * 2 aligned to 128
+	 * UV_Stride : Width * 2 aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((Y_Stride * Y_Scanlines
+	 *          + UV_Stride * UV_Scanlines
+	 *          + max(Extradata, Y_Stride * 8), 4096)
+	 */
+	COLOR_FMT_P010,
+};
+
+#define COLOR_FMT_RGBA1010102_UBWC	COLOR_FMT_RGBA1010102_UBWC
+#define COLOR_FMT_RGB565_UBWC		COLOR_FMT_RGB565_UBWC
+#define COLOR_FMT_P010_UBWC		COLOR_FMT_P010_UBWC
+#define COLOR_FMT_P010		COLOR_FMT_P010
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static unsigned int VENUS_Y_STRIDE(int color_fmt, int width)
+{
+	unsigned int stride = 0;
+
+	if (!width)
+		return 0;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_UBWC:
+		stride = MSM_MEDIA_ALIGN(width, 128);
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		stride = MSM_MEDIA_ALIGN(width, 192);
+		stride = MSM_MEDIA_ALIGN(stride * 4 / 3, 256);
+		break;
+	case COLOR_FMT_P010_UBWC:
+		stride = MSM_MEDIA_ALIGN(width * 2, 256);
+		break;
+	case COLOR_FMT_P010:
+		stride = MSM_MEDIA_ALIGN(width * 2, 128);
+		break;
+	}
+
+	return stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static unsigned int VENUS_UV_STRIDE(int color_fmt, int width)
+{
+	unsigned int stride = 0;
+
+	if (!width)
+		return 0;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_UBWC:
+		stride = MSM_MEDIA_ALIGN(width, 128);
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		stride = MSM_MEDIA_ALIGN(width, 192);
+		stride = MSM_MEDIA_ALIGN(stride * 4 / 3, 256);
+		break;
+	case COLOR_FMT_P010_UBWC:
+		stride = MSM_MEDIA_ALIGN(width * 2, 256);
+		break;
+	case COLOR_FMT_P010:
+		stride = MSM_MEDIA_ALIGN(width * 2, 128);
+		break;
+	}
+
+	return stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static unsigned int VENUS_Y_SCANLINES(int color_fmt, int height)
+{
+	unsigned int sclines = 0;
+
+	if (!height)
+		return 0;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_UBWC:
+	case COLOR_FMT_P010:
+		sclines = MSM_MEDIA_ALIGN(height, 32);
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		sclines = MSM_MEDIA_ALIGN(height, 16);
+		break;
+	}
+
+	return sclines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static unsigned int VENUS_UV_SCANLINES(int color_fmt, int height)
+{
+	unsigned int sclines = 0;
+
+	if (!height)
+		return 0;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+	case COLOR_FMT_P010:
+		sclines = MSM_MEDIA_ALIGN((height + 1) >> 1, 16);
+		break;
+	case COLOR_FMT_NV12_UBWC:
+		sclines = MSM_MEDIA_ALIGN((height + 1) >> 1, 32);
+		break;
+	}
+
+	return sclines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static unsigned int VENUS_Y_META_STRIDE(int color_fmt, int width)
+{
+	int y_tile_width = 0, y_meta_stride;
+
+	if (!width)
+		return 0;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		y_tile_width = 32;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		y_tile_width = 48;
+		break;
+	default:
+		return 0;
+	}
+
+	y_meta_stride = MSM_MEDIA_ROUNDUP(width, y_tile_width);
+	return MSM_MEDIA_ALIGN(y_meta_stride, 64);
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static unsigned int VENUS_Y_META_SCANLINES(int color_fmt, int height)
+{
+	int y_tile_height = 0, y_meta_scanlines;
+
+	if (!height)
+		return 0;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+		y_tile_height = 8;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		y_tile_height = 4;
+		break;
+	default:
+		return 0;
+	}
+
+	y_meta_scanlines = MSM_MEDIA_ROUNDUP(height, y_tile_height);
+	return MSM_MEDIA_ALIGN(y_meta_scanlines, 16);
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static unsigned int VENUS_UV_META_STRIDE(int color_fmt, int width)
+{
+	int uv_tile_width = 0, uv_meta_stride;
+
+	if (!width)
+		return 0;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		uv_tile_width = 16;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		uv_tile_width = 24;
+		break;
+	default:
+		return 0;
+	}
+
+	uv_meta_stride = MSM_MEDIA_ROUNDUP((width+1)>>1, uv_tile_width);
+	return MSM_MEDIA_ALIGN(uv_meta_stride, 64);
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static unsigned int VENUS_UV_META_SCANLINES(int color_fmt, int height)
+{
+	int uv_tile_height = 0, uv_meta_scanlines;
+
+	if (!height)
+		return 0;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+		uv_tile_height = 8;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		uv_tile_height = 4;
+		break;
+	default:
+		return 0;
+	}
+
+	uv_meta_scanlines = MSM_MEDIA_ROUNDUP((height+1)>>1, uv_tile_height);
+	return MSM_MEDIA_ALIGN(uv_meta_scanlines, 16);
+}
+
+static unsigned int VENUS_RGB_STRIDE(int color_fmt, int width)
+{
+	unsigned int alignment = 0, bpp = 4;
+
+	if (!width)
+		return 0;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888:
+		alignment = 128;
+		break;
+	case COLOR_FMT_RGB565_UBWC:
+		alignment = 256;
+		bpp = 2;
+		break;
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+		alignment = 256;
+		break;
+	default:
+		return 0;
+	}
+
+	return MSM_MEDIA_ALIGN(width * bpp, alignment);
+}
+
+static unsigned int VENUS_RGB_SCANLINES(int color_fmt, int height)
+{
+	unsigned int alignment = 0;
+
+	if (!height)
+		return 0;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888:
+		alignment = 32;
+		break;
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		alignment = 16;
+		break;
+	default:
+		return 0;
+	}
+
+	return MSM_MEDIA_ALIGN(height, alignment);
+}
+
+static unsigned int VENUS_RGB_META_STRIDE(int color_fmt, int width)
+{
+	int rgb_meta_stride;
+
+	if (!width)
+		return 0;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		rgb_meta_stride = MSM_MEDIA_ROUNDUP(width, 16);
+		return MSM_MEDIA_ALIGN(rgb_meta_stride, 64);
+	}
+
+	return 0;
+}
+
+static unsigned int VENUS_RGB_META_SCANLINES(int color_fmt, int height)
+{
+	int rgb_meta_scanlines;
+
+	if (!height)
+		return 0;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		rgb_meta_scanlines = MSM_MEDIA_ROUNDUP(height, 4);
+		return MSM_MEDIA_ALIGN(rgb_meta_scanlines, 16);
+	}
+
+	return 0;
+}
+
+#endif