Adding upstream version 6.7.7.upstream/6.7.7

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

93 files changed, 2525 insertions, 1536 deletions

diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 6309a857ca..ad70b611b4 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -6,6 +6,7 @@ config DRM_MSM
 	depends on ARCH_QCOM || SOC_IMX5 || COMPILE_TEST
 	depends on COMMON_CLK
 	depends on IOMMU_SUPPORT
+	depends on QCOM_AOSS_QMP || QCOM_AOSS_QMP=n
 	depends on QCOM_OCMEM || QCOM_OCMEM=n
 	depends on QCOM_LLCC || QCOM_LLCC=n
 	depends on QCOM_COMMAND_DB || QCOM_COMMAND_DB=n
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index 8d02d8c330..49671364fd 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -106,6 +106,7 @@ msm-y += \
 	msm_gpu_devfreq.o \
 	msm_io_utils.o \
 	msm_iommu.o \
+	msm_kms.o \
 	msm_perf.o \
 	msm_rd.o \
 	msm_ringbuffer.o \
diff --git a/drivers/gpu/drm/msm/adreno/a6xx.xml.h b/drivers/gpu/drm/msm/adreno/a6xx.xml.h
index 1c051535fd..863b5e3b0e 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx.xml.h
@@ -1114,6 +1114,12 @@ enum a6xx_tex_type {
 #define REG_A6XX_CP_MISC_CNTL					0x00000840
 
 #define REG_A6XX_CP_APRIV_CNTL					0x00000844
+#define A6XX_CP_APRIV_CNTL_CDWRITE				0x00000040
+#define A6XX_CP_APRIV_CNTL_CDREAD				0x00000020
+#define A6XX_CP_APRIV_CNTL_RBRPWB				0x00000008
+#define A6XX_CP_APRIV_CNTL_RBPRIVLEVEL				0x00000004
+#define A6XX_CP_APRIV_CNTL_RBFETCH				0x00000002
+#define A6XX_CP_APRIV_CNTL_ICACHE				0x00000001
 
 #define REG_A6XX_CP_PREEMPT_THRESHOLD				0x000008c0
 
@@ -1939,6 +1945,8 @@ static inline uint32_t REG_A6XX_RBBM_PERFCTR_RBBM_SEL(uint32_t i0) { return 0x00
 
 #define REG_A6XX_RBBM_CLOCK_HYST_TEX_FCHE			0x00000122
 
+#define REG_A7XX_RBBM_CLOCK_HYST2_VFD				0x0000012f
+
 #define REG_A6XX_RBBM_LPAC_GBIF_CLIENT_QOS_CNTL			0x000005ff
 
 #define REG_A6XX_DBGC_CFG_DBGBUS_SEL_A				0x00000600
@@ -8252,5 +8260,6 @@ static inline uint32_t A6XX_CX_DBGC_CFG_DBGBUS_BYTEL_1_BYTEL15(uint32_t val)
 
 #define REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1			0x00000002
 
+#define REG_A7XX_CX_MISC_TCM_RET_CNTL				0x00000039
 
 #endif /* A6XX_XML */
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 7923129363..8c4900444b 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/interconnect.h>
 #include <linux/of_platform.h>
@@ -202,9 +203,10 @@ int a6xx_gmu_wait_for_idle(struct a6xx_gmu *gmu)
 
 static int a6xx_gmu_start(struct a6xx_gmu *gmu)
 {
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	u32 mask, reset_val, val;
 	int ret;
-	u32 val;
-	u32 mask, reset_val;
 
 	val = gmu_read(gmu, REG_A6XX_GMU_CM3_DTCM_START + 0xff8);
 	if (val <= 0x20010004) {
@@ -220,7 +222,11 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu)
 	/* Set the log wptr index
 	 * note: downstream saves the value in poweroff and restores it here
 	 */
-	gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_PWR_COL_CP_RESP, 0);
+	if (adreno_is_a7xx(adreno_gpu))
+		gmu_write(gmu, REG_A6XX_GMU_GENERAL_9, 0);
+	else
+		gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_PWR_COL_CP_RESP, 0);
+
 
 	gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 0);
 
@@ -513,6 +519,7 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct platform_device *pdev = to_platform_device(gmu->dev);
 	void __iomem *pdcptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc");
+	u32 seqmem0_drv0_reg = REG_A6XX_RSCC_SEQ_MEM_0_DRV0;
 	void __iomem *seqptr = NULL;
 	uint32_t pdc_address_offset;
 	bool pdc_in_aop = false;
@@ -520,7 +527,9 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 	if (IS_ERR(pdcptr))
 		goto err;
 
-	if (adreno_is_a650(adreno_gpu) || adreno_is_a660_family(adreno_gpu))
+	if (adreno_is_a650(adreno_gpu) ||
+	    adreno_is_a660_family(adreno_gpu) ||
+	    adreno_is_a7xx(adreno_gpu))
 		pdc_in_aop = true;
 	else if (adreno_is_a618(adreno_gpu) || adreno_is_a640_family(adreno_gpu))
 		pdc_address_offset = 0x30090;
@@ -544,20 +553,26 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 	gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_ADDR, 0);
 	gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_DATA + 2, 0);
 	gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_ADDR + 2, 0);
-	gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_DATA + 4, 0x80000000);
+	gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_DATA + 4,
+		       adreno_is_a740_family(adreno_gpu) ? 0x80000021 : 0x80000000);
 	gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_ADDR + 4, 0);
 	gmu_write_rscc(gmu, REG_A6XX_RSCC_OVERRIDE_START_ADDR, 0);
 	gmu_write_rscc(gmu, REG_A6XX_RSCC_PDC_SEQ_START_ADDR, 0x4520);
 	gmu_write_rscc(gmu, REG_A6XX_RSCC_PDC_MATCH_VALUE_LO, 0x4510);
 	gmu_write_rscc(gmu, REG_A6XX_RSCC_PDC_MATCH_VALUE_HI, 0x4514);
 
+	/* The second spin of A7xx GPUs messed with some register offsets.. */
+	if (adreno_is_a740_family(adreno_gpu))
+		seqmem0_drv0_reg = REG_A7XX_RSCC_SEQ_MEM_0_DRV0_A740;
+
 	/* Load RSC sequencer uCode for sleep and wakeup */
-	if (adreno_is_a650_family(adreno_gpu)) {
-		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0, 0xeaaae5a0);
-		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 1, 0xe1a1ebab);
-		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 2, 0xa2e0a581);
-		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 3, 0xecac82e2);
-		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 4, 0x0020edad);
+	if (adreno_is_a650_family(adreno_gpu) ||
+	    adreno_is_a7xx(adreno_gpu)) {
+		gmu_write_rscc(gmu, seqmem0_drv0_reg, 0xeaaae5a0);
+		gmu_write_rscc(gmu, seqmem0_drv0_reg + 1, 0xe1a1ebab);
+		gmu_write_rscc(gmu, seqmem0_drv0_reg + 2, 0xa2e0a581);
+		gmu_write_rscc(gmu, seqmem0_drv0_reg + 3, 0xecac82e2);
+		gmu_write_rscc(gmu, seqmem0_drv0_reg + 4, 0x0020edad);
 	} else {
 		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0, 0xa7a506a0);
 		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 1, 0xa1e6a6e7);
@@ -637,11 +652,18 @@ err:
 /* Set up the idle state for the GMU */
 static void a6xx_gmu_power_config(struct a6xx_gmu *gmu)
 {
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+
 	/* Disable GMU WB/RB buffer */
 	gmu_write(gmu, REG_A6XX_GMU_SYS_BUS_CONFIG, 0x1);
 	gmu_write(gmu, REG_A6XX_GMU_ICACHE_CONFIG, 0x1);
 	gmu_write(gmu, REG_A6XX_GMU_DCACHE_CONFIG, 0x1);
 
+	/* A7xx knows better by default! */
+	if (adreno_is_a7xx(adreno_gpu))
+		return;
+
 	gmu_write(gmu, REG_A6XX_GMU_PWR_COL_INTER_FRAME_CTRL, 0x9c40400);
 
 	switch (gmu->idle_level) {
@@ -698,7 +720,7 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu)
 	u32 itcm_base = 0x00000000;
 	u32 dtcm_base = 0x00040000;
 
-	if (adreno_is_a650_family(adreno_gpu))
+	if (adreno_is_a650_family(adreno_gpu) || adreno_is_a7xx(adreno_gpu))
 		dtcm_base = 0x10004000;
 
 	if (gmu->legacy) {
@@ -747,14 +769,22 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state)
 {
 	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	u32 fence_range_lower, fence_range_upper;
+	u32 chipid, chipid_min = 0;
 	int ret;
-	u32 chipid;
 
-	if (adreno_is_a650_family(adreno_gpu)) {
+	/* Vote veto for FAL10 */
+	if (adreno_is_a650_family(adreno_gpu) || adreno_is_a7xx(adreno_gpu)) {
 		gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_CX_FALNEXT_INTF, 1);
 		gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_CX_FAL_INTF, 1);
 	}
 
+	/* Turn on TCM (Tightly Coupled Memory) retention */
+	if (adreno_is_a7xx(adreno_gpu))
+		a6xx_llc_write(a6xx_gpu, REG_A7XX_CX_MISC_TCM_RET_CNTL, 1);
+	else
+		gmu_write(gmu, REG_A6XX_GMU_GENERAL_7, 1);
+
 	if (state == GMU_WARM_BOOT) {
 		ret = a6xx_rpmh_start(gmu);
 		if (ret)
@@ -764,9 +794,6 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state)
 			"GMU firmware is not loaded\n"))
 			return -ENOENT;
 
-		/* Turn on register retention */
-		gmu_write(gmu, REG_A6XX_GMU_GENERAL_7, 1);
-
 		ret = a6xx_rpmh_start(gmu);
 		if (ret)
 			return ret;
@@ -776,6 +803,7 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state)
 			return ret;
 	}
 
+	/* Clear init result to make sure we are getting a fresh value */
 	gmu_write(gmu, REG_A6XX_GMU_CM3_FW_INIT_RESULT, 0);
 	gmu_write(gmu, REG_A6XX_GMU_CM3_BOOT_CONFIG, 0x02);
 
@@ -783,8 +811,18 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state)
 	gmu_write(gmu, REG_A6XX_GMU_HFI_QTBL_ADDR, gmu->hfi.iova);
 	gmu_write(gmu, REG_A6XX_GMU_HFI_QTBL_INFO, 1);
 
+	if (adreno_is_a7xx(adreno_gpu)) {
+		fence_range_upper = 0x32;
+		fence_range_lower = 0x8a0;
+	} else {
+		fence_range_upper = 0xa;
+		fence_range_lower = 0xa0;
+	}
+
 	gmu_write(gmu, REG_A6XX_GMU_AHB_FENCE_RANGE_0,
-		(1 << 31) | (0xa << 18) | (0xa0));
+		  BIT(31) |
+		  FIELD_PREP(GENMASK(30, 18), fence_range_upper) |
+		  FIELD_PREP(GENMASK(17, 0), fence_range_lower));
 
 	/*
 	 * Snapshots toggle the NMI bit which will result in a jump to the NMI
@@ -792,21 +830,49 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state)
 	 */
 	gmu_write(gmu, REG_A6XX_GMU_CM3_CFG, 0x4052);
 
-	/*
-	 * Note that the GMU has a slightly different layout for
-	 * chip_id, for whatever reason, so a bit of massaging
-	 * is needed.  The upper 16b are the same, but minor and
-	 * patchid are packed in four bits each with the lower
-	 * 8b unused:
-	 */
-	chipid  = adreno_gpu->chip_id & 0xffff0000;
-	chipid |= (adreno_gpu->chip_id << 4) & 0xf000; /* minor */
-	chipid |= (adreno_gpu->chip_id << 8) & 0x0f00; /* patchid */
+	/* NOTE: A730 may also fall in this if-condition with a future GMU fw update. */
+	if (adreno_is_a7xx(adreno_gpu) && !adreno_is_a730(adreno_gpu)) {
+		/* A7xx GPUs have obfuscated chip IDs. Use constant maj = 7 */
+		chipid = FIELD_PREP(GENMASK(31, 24), 0x7);
+
+		/*
+		 * The min part has a 1-1 mapping for each GPU SKU.
+		 * This chipid that the GMU expects corresponds to the "GENX_Y_Z" naming,
+		 * where X = major, Y = minor, Z = patchlevel, e.g. GEN7_2_1 for prod A740.
+		 */
+		if (adreno_is_a740(adreno_gpu))
+			chipid_min = 2;
+		else
+			return -EINVAL;
+
+		chipid |= FIELD_PREP(GENMASK(23, 16), chipid_min);
 
-	gmu_write(gmu, REG_A6XX_GMU_HFI_SFR_ADDR, chipid);
+		/* Get the patchid (which may vary) from the device tree */
+		chipid |= FIELD_PREP(GENMASK(15, 8), adreno_patchid(adreno_gpu));
+	} else {
+		/*
+		 * Note that the GMU has a slightly different layout for
+		 * chip_id, for whatever reason, so a bit of massaging
+		 * is needed.  The upper 16b are the same, but minor and
+		 * patchid are packed in four bits each with the lower
+		 * 8b unused:
+		 */
+		chipid  = adreno_gpu->chip_id & 0xffff0000;
+		chipid |= (adreno_gpu->chip_id << 4) & 0xf000; /* minor */
+		chipid |= (adreno_gpu->chip_id << 8) & 0x0f00; /* patchid */
+	}
 
-	gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_PWR_COL_CP_MSG,
-		  gmu->log.iova | (gmu->log.size / SZ_4K - 1));
+	if (adreno_is_a7xx(adreno_gpu)) {
+		gmu_write(gmu, REG_A6XX_GMU_GENERAL_10, chipid);
+		gmu_write(gmu, REG_A6XX_GMU_GENERAL_8,
+			  (gmu->log.iova & GENMASK(31, 12)) |
+			  ((gmu->log.size / SZ_4K - 1) & GENMASK(7, 0)));
+	} else {
+		gmu_write(gmu, REG_A6XX_GMU_HFI_SFR_ADDR, chipid);
+
+		gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_PWR_COL_CP_MSG,
+			  gmu->log.iova | (gmu->log.size / SZ_4K - 1));
+	}
 
 	/* Set up the lowest idle level on the GMU */
 	a6xx_gmu_power_config(gmu);
@@ -857,17 +923,23 @@ static void a6xx_gmu_irq_disable(struct a6xx_gmu *gmu)
 
 static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu)
 {
-	u32 val;
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	u32 val, seqmem_off = 0;
+
+	/* The second spin of A7xx GPUs messed with some register offsets.. */
+	if (adreno_is_a740_family(adreno_gpu))
+		seqmem_off = 4;
 
 	/* Make sure there are no outstanding RPMh votes */
-	gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS0_DRV0_STATUS, val,
-		(val & 1), 100, 10000);
-	gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS1_DRV0_STATUS, val,
-		(val & 1), 100, 10000);
-	gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS2_DRV0_STATUS, val,
-		(val & 1), 100, 10000);
-	gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS3_DRV0_STATUS, val,
-		(val & 1), 100, 1000);
+	gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS0_DRV0_STATUS + seqmem_off,
+		val, (val & 1), 100, 10000);
+	gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS1_DRV0_STATUS + seqmem_off,
+		val, (val & 1), 100, 10000);
+	gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS2_DRV0_STATUS + seqmem_off,
+		val, (val & 1), 100, 10000);
+	gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS3_DRV0_STATUS + seqmem_off,
+		val, (val & 1), 100, 1000);
 }
 
 /* Force the GMU off in case it isn't responsive */
@@ -950,6 +1022,14 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 
 	gmu->hung = false;
 
+	/* Notify AOSS about the ACD state (unimplemented for now => disable it) */
+	if (!IS_ERR(gmu->qmp)) {
+		ret = qmp_send(gmu->qmp, "{class: gpu, res: acd, val: %d}",
+			       0 /* Hardcode ACD to be disabled for now */);
+		if (ret)
+			dev_err(gmu->dev, "failed to send GPU ACD state\n");
+	}
+
 	/* Turn on the resources */
 	pm_runtime_get_sync(gmu->dev);
 
@@ -963,7 +1043,8 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 
 	/* Use a known rate to bring up the GMU */
 	clk_set_rate(gmu->core_clk, 200000000);
-	clk_set_rate(gmu->hub_clk, 150000000);
+	clk_set_rate(gmu->hub_clk, adreno_is_a740_family(adreno_gpu) ?
+		     200000000 : 150000000);
 	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
 	if (ret) {
 		pm_runtime_put(gmu->gxpd);
@@ -980,15 +1061,19 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	enable_irq(gmu->gmu_irq);
 
 	/* Check to see if we are doing a cold or warm boot */
-	status = gmu_read(gmu, REG_A6XX_GMU_GENERAL_7) == 1 ?
-		GMU_WARM_BOOT : GMU_COLD_BOOT;
-
-	/*
-	 * Warm boot path does not work on newer GPUs
-	 * Presumably this is because icache/dcache regions must be restored
-	 */
-	if (!gmu->legacy)
+	if (adreno_is_a7xx(adreno_gpu)) {
+		status = a6xx_llc_read(a6xx_gpu, REG_A7XX_CX_MISC_TCM_RET_CNTL) == 1 ?
+			GMU_WARM_BOOT : GMU_COLD_BOOT;
+	} else if (gmu->legacy) {
+		status = gmu_read(gmu, REG_A6XX_GMU_GENERAL_7) == 1 ?
+			GMU_WARM_BOOT : GMU_COLD_BOOT;
+	} else {
+		/*
+		 * Warm boot path does not work on newer A6xx GPUs
+		 * Presumably this is because icache/dcache regions must be restored
+		 */
 		status = GMU_COLD_BOOT;
+	}
 
 	ret = a6xx_gmu_fw_start(gmu, status);
 	if (ret)
@@ -1473,6 +1558,9 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu)
 		dev_pm_domain_detach(gmu->gxpd, false);
 	}
 
+	if (!IS_ERR_OR_NULL(gmu->qmp))
+		qmp_put(gmu->qmp);
+
 	iounmap(gmu->mmio);
 	if (platform_get_resource_byname(pdev, IORESOURCE_MEM, "rscc"))
 		iounmap(gmu->rscc);
@@ -1569,6 +1657,7 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
 	struct platform_device *pdev = of_find_device_by_node(node);
+	struct device_link *link;
 	int ret;
 
 	if (!pdev)
@@ -1600,7 +1689,8 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	 * are otherwise unused by a660.
 	 */
 	gmu->dummy.size = SZ_4K;
-	if (adreno_is_a660_family(adreno_gpu)) {
+	if (adreno_is_a660_family(adreno_gpu) ||
+	    adreno_is_a7xx(adreno_gpu)) {
 		ret = a6xx_gmu_memory_alloc(gmu, &gmu->debug, SZ_4K * 7,
 					    0x60400000, "debug");
 		if (ret)
@@ -1616,7 +1706,8 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 		goto err_memory;
 
 	/* Note that a650 family also includes a660 family: */
-	if (adreno_is_a650_family(adreno_gpu)) {
+	if (adreno_is_a650_family(adreno_gpu) ||
+	    adreno_is_a7xx(adreno_gpu)) {
 		ret = a6xx_gmu_memory_alloc(gmu, &gmu->icache,
 			SZ_16M - SZ_16K, 0x04000, "icache");
 		if (ret)
@@ -1664,7 +1755,8 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 		goto err_memory;
 	}
 
-	if (adreno_is_a650_family(adreno_gpu)) {
+	if (adreno_is_a650_family(adreno_gpu) ||
+	    adreno_is_a7xx(adreno_gpu)) {
 		gmu->rscc = a6xx_gmu_get_mmio(pdev, "rscc");
 		if (IS_ERR(gmu->rscc)) {
 			ret = -ENODEV;
@@ -1689,12 +1781,18 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 		goto err_mmio;
 	}
 
-	if (!device_link_add(gmu->dev, gmu->cxpd,
-					DL_FLAG_PM_RUNTIME)) {
+	link = device_link_add(gmu->dev, gmu->cxpd, DL_FLAG_PM_RUNTIME);
+	if (!link) {
 		ret = -ENODEV;
 		goto detach_cxpd;
 	}
 
+	gmu->qmp = qmp_get(gmu->dev);
+	if (IS_ERR(gmu->qmp) && adreno_is_a7xx(adreno_gpu)) {
+		ret = PTR_ERR(gmu->qmp);
+		goto remove_device_link;
+	}
+
 	init_completion(&gmu->pd_gate);
 	complete_all(&gmu->pd_gate);
 	gmu->pd_nb.notifier_call = cxpd_notifier_cb;
@@ -1718,6 +1816,9 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 
 	return 0;
 
+remove_device_link:
+	device_link_del(link);
+
 detach_cxpd:
 	dev_pm_domain_detach(gmu->cxpd, false);
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index 236f81a43c..592b296aab 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -8,6 +8,7 @@
 #include <linux/iopoll.h>
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
+#include <linux/soc/qcom/qcom_aoss.h>
 #include "msm_drv.h"
 #include "a6xx_hfi.h"
 
@@ -96,6 +97,8 @@ struct a6xx_gmu {
 	/* For power domain callback */
 	struct notifier_block pd_nb;
 	struct completion pd_gate;
+
+	struct qmp *qmp;
 };
 
 static inline u32 gmu_read(struct a6xx_gmu *gmu, u32 offset)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h
index fcd9eb53ba..5b66efafc9 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h
@@ -360,6 +360,12 @@ static inline uint32_t A6XX_GMU_GPU_NAP_CTRL_SID(uint32_t val)
 
 #define REG_A6XX_GMU_GENERAL_7					0x000051cc
 
+#define REG_A6XX_GMU_GENERAL_8					0x000051cd
+
+#define REG_A6XX_GMU_GENERAL_9					0x000051ce
+
+#define REG_A6XX_GMU_GENERAL_10					0x000051cf
+
 #define REG_A6XX_GMU_ISENSE_CTRL				0x0000515d
 
 #define REG_A6XX_GPU_CS_ENABLE_REG				0x00008920
@@ -471,6 +477,8 @@ static inline uint32_t A6XX_GMU_GPU_NAP_CTRL_SID(uint32_t val)
 
 #define REG_A6XX_RSCC_SEQ_BUSY_DRV0				0x00000101
 
+#define REG_A7XX_RSCC_SEQ_MEM_0_DRV0_A740			0x00000154
+
 #define REG_A6XX_RSCC_SEQ_MEM_0_DRV0				0x00000180
 
 #define REG_A6XX_RSCC_TCS0_DRV0_STATUS				0x00000346
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 522ca7fe67..500ed2d183 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -103,6 +103,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 		struct msm_ringbuffer *ring, struct msm_file_private *ctx)
 {
 	bool sysprof = refcount_read(&a6xx_gpu->base.base.sysprof_active) > 1;
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	phys_addr_t ttbr;
 	u32 asid;
 	u64 memptr = rbmemptr(ring, ttbr0);
@@ -114,9 +115,11 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 		return;
 
 	if (!sysprof) {
-		/* Turn off protected mode to write to special registers */
-		OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1);
-		OUT_RING(ring, 0);
+		if (!adreno_is_a7xx(adreno_gpu)) {
+			/* Turn off protected mode to write to special registers */
+			OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1);
+			OUT_RING(ring, 0);
+		}
 
 		OUT_PKT4(ring, REG_A6XX_RBBM_PERFCTR_SRAM_INIT_CMD, 1);
 		OUT_RING(ring, 1);
@@ -142,6 +145,16 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 	OUT_RING(ring, (asid << 16) | upper_32_bits(ttbr));
 
 	/*
+	 * Sync both threads after switching pagetables and enable BR only
+	 * to make sure BV doesn't race ahead while BR is still switching
+	 * pagetables.
+	 */
+	if (adreno_is_a7xx(&a6xx_gpu->base)) {
+		OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+		OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BR);
+	}
+
+	/*
 	 * And finally, trigger a uche flush to be sure there isn't anything
 	 * lingering in that part of the GPU
 	 */
@@ -163,9 +176,11 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 		OUT_RING(ring, CP_WAIT_REG_MEM_4_MASK(0x1));
 		OUT_RING(ring, CP_WAIT_REG_MEM_5_DELAY_LOOP_CYCLES(0));
 
-		/* Re-enable protected mode: */
-		OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1);
-		OUT_RING(ring, 1);
+		if (!adreno_is_a7xx(adreno_gpu)) {
+			/* Re-enable protected mode: */
+			OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1);
+			OUT_RING(ring, 1);
+		}
 	}
 }
 
@@ -252,6 +267,133 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	a6xx_flush(gpu, ring);
 }
 
+static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
+{
+	unsigned int index = submit->seqno % MSM_GPU_SUBMIT_STATS_COUNT;
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+	struct msm_ringbuffer *ring = submit->ring;
+	unsigned int i, ibs = 0;
+
+	/*
+	 * Toggle concurrent binning for pagetable switch and set the thread to
+	 * BR since only it can execute the pagetable switch packets.
+	 */
+	OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+	OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BR);
+
+	a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx);
+
+	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0),
+		rbmemptr_stats(ring, index, cpcycles_start));
+	get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER,
+		rbmemptr_stats(ring, index, alwayson_start));
+
+	OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+	OUT_RING(ring, CP_SET_THREAD_BOTH);
+
+	OUT_PKT7(ring, CP_SET_MARKER, 1);
+	OUT_RING(ring, 0x101); /* IFPC disable */
+
+	OUT_PKT7(ring, CP_SET_MARKER, 1);
+	OUT_RING(ring, 0x00d); /* IB1LIST start */
+
+	/* Submit the commands */
+	for (i = 0; i < submit->nr_cmds; i++) {
+		switch (submit->cmd[i].type) {
+		case MSM_SUBMIT_CMD_IB_TARGET_BUF:
+			break;
+		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
+			if (gpu->cur_ctx_seqno == submit->queue->ctx->seqno)
+				break;
+			fallthrough;
+		case MSM_SUBMIT_CMD_BUF:
+			OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
+			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
+			OUT_RING(ring, upper_32_bits(submit->cmd[i].iova));
+			OUT_RING(ring, submit->cmd[i].size);
+			ibs++;
+			break;
+		}
+
+		/*
+		 * Periodically update shadow-wptr if needed, so that we
+		 * can see partial progress of submits with large # of
+		 * cmds.. otherwise we could needlessly stall waiting for
+		 * ringbuffer state, simply due to looking at a shadow
+		 * rptr value that has not been updated
+		 */
+		if ((ibs % 32) == 0)
+			update_shadow_rptr(gpu, ring);
+	}
+
+	OUT_PKT7(ring, CP_SET_MARKER, 1);
+	OUT_RING(ring, 0x00e); /* IB1LIST end */
+
+	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0),
+		rbmemptr_stats(ring, index, cpcycles_end));
+	get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER,
+		rbmemptr_stats(ring, index, alwayson_end));
+
+	/* Write the fence to the scratch register */
+	OUT_PKT4(ring, REG_A6XX_CP_SCRATCH_REG(2), 1);
+	OUT_RING(ring, submit->seqno);
+
+	OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+	OUT_RING(ring, CP_SET_THREAD_BR);
+
+	OUT_PKT7(ring, CP_EVENT_WRITE, 1);
+	OUT_RING(ring, CCU_INVALIDATE_DEPTH);
+
+	OUT_PKT7(ring, CP_EVENT_WRITE, 1);
+	OUT_RING(ring, CCU_INVALIDATE_COLOR);
+
+	OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+	OUT_RING(ring, CP_SET_THREAD_BV);
+
+	/*
+	 * Make sure the timestamp is committed once BV pipe is
+	 * completely done with this submission.
+	 */
+	OUT_PKT7(ring, CP_EVENT_WRITE, 4);
+	OUT_RING(ring, CACHE_CLEAN | BIT(27));
+	OUT_RING(ring, lower_32_bits(rbmemptr(ring, bv_fence)));
+	OUT_RING(ring, upper_32_bits(rbmemptr(ring, bv_fence)));
+	OUT_RING(ring, submit->seqno);
+
+	OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+	OUT_RING(ring, CP_SET_THREAD_BR);
+
+	/*
+	 * This makes sure that BR doesn't race ahead and commit
+	 * timestamp to memstore while BV is still processing
+	 * this submission.
+	 */
+	OUT_PKT7(ring, CP_WAIT_TIMESTAMP, 4);
+	OUT_RING(ring, 0);
+	OUT_RING(ring, lower_32_bits(rbmemptr(ring, bv_fence)));
+	OUT_RING(ring, upper_32_bits(rbmemptr(ring, bv_fence)));
+	OUT_RING(ring, submit->seqno);
+
+	/* write the ringbuffer timestamp */
+	OUT_PKT7(ring, CP_EVENT_WRITE, 4);
+	OUT_RING(ring, CACHE_CLEAN | CP_EVENT_WRITE_0_IRQ | BIT(27));
+	OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence)));
+	OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence)));
+	OUT_RING(ring, submit->seqno);
+
+	OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+	OUT_RING(ring, CP_SET_THREAD_BOTH);
+
+	OUT_PKT7(ring, CP_SET_MARKER, 1);
+	OUT_RING(ring, 0x100); /* IFPC enable */
+
+	trace_msm_gpu_submit_flush(submit,
+		gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER));
+
+	a6xx_flush(gpu, ring);
+}
+
 const struct adreno_reglist a612_hwcg[] = {
 	{REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x22222222},
 	{REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220},
@@ -695,6 +837,121 @@ const struct adreno_reglist a690_hwcg[] = {
 	{}
 };
 
+const struct adreno_reglist a730_hwcg[] = {
+	{ REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x02222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x02022222 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_SP0, 0x0000f3cf },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_SP0, 0x00000080 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_TP0, 0x22222220 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL3_TP0, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL4_TP0, 0x00222222 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_TP0, 0x77777777 },
+	{ REG_A6XX_RBBM_CLOCK_HYST2_TP0, 0x77777777 },
+	{ REG_A6XX_RBBM_CLOCK_HYST3_TP0, 0x77777777 },
+	{ REG_A6XX_RBBM_CLOCK_HYST4_TP0, 0x00077777 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_TP0, 0x11111111 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY3_TP0, 0x11111111 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY4_TP0, 0x00011111 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_UCHE, 0x00000004 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_RB0, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_RB0, 0x01002222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_CCU0, 0x00002220 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_RB_CCU0, 0x44000f00 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_RAC, 0x25222022 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_RAC, 0x00555555 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_RAC, 0x00000011 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_RAC, 0x00440044 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222 },
+	{ REG_A7XX_RBBM_CLOCK_MODE2_GRAS, 0x00000222 },
+	{ REG_A7XX_RBBM_CLOCK_MODE_BV_GRAS, 0x00222222 },
+	{ REG_A6XX_RBBM_CLOCK_MODE_GPC, 0x02222223 },
+	{ REG_A6XX_RBBM_CLOCK_MODE_VFD, 0x00002222 },
+	{ REG_A7XX_RBBM_CLOCK_MODE_BV_GPC, 0x00222222 },
+	{ REG_A7XX_RBBM_CLOCK_MODE_BV_VFD, 0x00002222 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_GPC, 0x04104004 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_VFD, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_GPC, 0x00000200 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_VFD, 0x00002222 },
+	{ REG_A6XX_RBBM_CLOCK_MODE_HLSQ, 0x00002222 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_HLSQ, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_HLSQ_2, 0x00000002 },
+	{ REG_A7XX_RBBM_CLOCK_MODE_BV_LRZ, 0x55555552 },
+	{ REG_A7XX_RBBM_CLOCK_MODE_CP, 0x00000223 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL, 0x8aa8aa82 },
+	{ REG_A6XX_RBBM_ISDB_CNT, 0x00000182 },
+	{ REG_A6XX_RBBM_RAC_THRESHOLD_CNT, 0x00000000 },
+	{ REG_A6XX_RBBM_SP_HYST_CNT, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555 },
+	{},
+};
+
+const struct adreno_reglist a740_hwcg[] = {
+	{ REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x02222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x22022222 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_SP0, 0x003cf3cf },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_SP0, 0x00000080 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_TP0, 0x22222220 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL3_TP0, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL4_TP0, 0x00222222 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_TP0, 0x77777777 },
+	{ REG_A6XX_RBBM_CLOCK_HYST2_TP0, 0x77777777 },
+	{ REG_A6XX_RBBM_CLOCK_HYST3_TP0, 0x77777777 },
+	{ REG_A6XX_RBBM_CLOCK_HYST4_TP0, 0x00077777 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_TP0, 0x11111111 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY3_TP0, 0x11111111 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY4_TP0, 0x00011111 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_UCHE, 0x00222222 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_UCHE, 0x00000444 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_UCHE, 0x00000222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_RB0, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_RB0, 0x01002222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_CCU0, 0x00002220 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_RB_CCU0, 0x44000f00 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_RAC, 0x25222022 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_RAC, 0x00555555 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_RAC, 0x00000011 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_RAC, 0x00440044 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222 },
+	{ REG_A7XX_RBBM_CLOCK_MODE2_GRAS, 0x00000222 },
+	{ REG_A7XX_RBBM_CLOCK_MODE_BV_GRAS, 0x00222222 },
+	{ REG_A6XX_RBBM_CLOCK_MODE_GPC, 0x02222223 },
+	{ REG_A6XX_RBBM_CLOCK_MODE_VFD, 0x00222222 },
+	{ REG_A7XX_RBBM_CLOCK_MODE_BV_GPC, 0x00222222 },
+	{ REG_A7XX_RBBM_CLOCK_MODE_BV_VFD, 0x00002222 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_GPC, 0x04104004 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_VFD, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_GPC, 0x00000200 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_VFD, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_MODE_HLSQ, 0x00002222 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_HLSQ, 0x00000000 },
+	{ REG_A7XX_RBBM_CLOCK_MODE_BV_LRZ, 0x55555552 },
+	{ REG_A7XX_RBBM_CLOCK_HYST2_VFD, 0x00000000 },
+	{ REG_A7XX_RBBM_CLOCK_MODE_CP, 0x00000222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL, 0x8aa8aa82 },
+	{ REG_A6XX_RBBM_ISDB_CNT, 0x00000182 },
+	{ REG_A6XX_RBBM_RAC_THRESHOLD_CNT, 0x00000000 },
+	{ REG_A6XX_RBBM_SP_HYST_CNT, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555 },
+	{},
+};
+
 static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -702,7 +959,7 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
 	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
 	const struct adreno_reglist *reg;
 	unsigned int i;
-	u32 val, clock_cntl_on;
+	u32 val, clock_cntl_on, cgc_mode;
 
 	if (!adreno_gpu->info->hwcg)
 		return;
@@ -714,6 +971,17 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
 	else
 		clock_cntl_on = 0x8aa8aa82;
 
+	if (adreno_is_a7xx(adreno_gpu)) {
+		cgc_mode = adreno_is_a740_family(adreno_gpu) ? 0x20222 : 0x20000;
+
+		gmu_write(&a6xx_gpu->gmu, REG_A6XX_GPU_GMU_AO_GMU_CGC_MODE_CNTL,
+			  state ? cgc_mode : 0);
+		gmu_write(&a6xx_gpu->gmu, REG_A6XX_GPU_GMU_AO_GMU_CGC_DELAY_CNTL,
+			  state ? 0x10111 : 0);
+		gmu_write(&a6xx_gpu->gmu, REG_A6XX_GPU_GMU_AO_GMU_CGC_HYST_CNTL,
+			  state ? 0x5555 : 0);
+	}
+
 	val = gpu_read(gpu, REG_A6XX_RBBM_CLOCK_CNTL);
 
 	/* Don't re-program the registers if they are already correct */
@@ -721,14 +989,14 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
 		return;
 
 	/* Disable SP clock before programming HWCG registers */
-	if (!adreno_is_a610(adreno_gpu))
+	if (!adreno_is_a610(adreno_gpu) && !adreno_is_a7xx(adreno_gpu))
 		gmu_rmw(gmu, REG_A6XX_GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL, 1, 0);
 
 	for (i = 0; (reg = &adreno_gpu->info->hwcg[i], reg->offset); i++)
 		gpu_write(gpu, reg->offset, state ? reg->value : 0);
 
 	/* Enable SP clock */
-	if (!adreno_is_a610(adreno_gpu))
+	if (!adreno_is_a610(adreno_gpu) && !adreno_is_a7xx(adreno_gpu))
 		gmu_rmw(gmu, REG_A6XX_GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL, 0, 1);
 
 	gpu_write(gpu, REG_A6XX_RBBM_CLOCK_CNTL, state ? clock_cntl_on : 0);
@@ -897,6 +1165,59 @@ static const u32 a690_protect[] = {
 	A6XX_PROTECT_NORDWR(0x11c00, 0x00000), /*note: infiite range */
 };
 
+static const u32 a730_protect[] = {
+	A6XX_PROTECT_RDONLY(0x00000, 0x04ff),
+	A6XX_PROTECT_RDONLY(0x0050b, 0x0058),
+	A6XX_PROTECT_NORDWR(0x0050e, 0x0000),
+	A6XX_PROTECT_NORDWR(0x00510, 0x0000),
+	A6XX_PROTECT_NORDWR(0x00534, 0x0000),
+	A6XX_PROTECT_RDONLY(0x005fb, 0x009d),
+	A6XX_PROTECT_NORDWR(0x00699, 0x01e9),
+	A6XX_PROTECT_NORDWR(0x008a0, 0x0008),
+	A6XX_PROTECT_NORDWR(0x008ab, 0x0024),
+	/* 0x008d0-0x008dd are unprotected on purpose for tools like perfetto */
+	A6XX_PROTECT_RDONLY(0x008de, 0x0154),
+	A6XX_PROTECT_NORDWR(0x00900, 0x004d),
+	A6XX_PROTECT_NORDWR(0x0098d, 0x00b2),
+	A6XX_PROTECT_NORDWR(0x00a41, 0x01be),
+	A6XX_PROTECT_NORDWR(0x00df0, 0x0001),
+	A6XX_PROTECT_NORDWR(0x00e01, 0x0000),
+	A6XX_PROTECT_NORDWR(0x00e07, 0x0008),
+	A6XX_PROTECT_NORDWR(0x03c00, 0x00c3),
+	A6XX_PROTECT_RDONLY(0x03cc4, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x08630, 0x01cf),
+	A6XX_PROTECT_NORDWR(0x08e00, 0x0000),
+	A6XX_PROTECT_NORDWR(0x08e08, 0x0000),
+	A6XX_PROTECT_NORDWR(0x08e50, 0x001f),
+	A6XX_PROTECT_NORDWR(0x08e80, 0x0280),
+	A6XX_PROTECT_NORDWR(0x09624, 0x01db),
+	A6XX_PROTECT_NORDWR(0x09e40, 0x0000),
+	A6XX_PROTECT_NORDWR(0x09e64, 0x000d),
+	A6XX_PROTECT_NORDWR(0x09e78, 0x0187),
+	A6XX_PROTECT_NORDWR(0x0a630, 0x01cf),
+	A6XX_PROTECT_NORDWR(0x0ae02, 0x0000),
+	A6XX_PROTECT_NORDWR(0x0ae50, 0x000f),
+	A6XX_PROTECT_NORDWR(0x0ae66, 0x0003),
+	A6XX_PROTECT_NORDWR(0x0ae6f, 0x0003),
+	A6XX_PROTECT_NORDWR(0x0b604, 0x0003),
+	A6XX_PROTECT_NORDWR(0x0ec00, 0x0fff),
+	A6XX_PROTECT_RDONLY(0x0fc00, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x18400, 0x0053),
+	A6XX_PROTECT_RDONLY(0x18454, 0x0004),
+	A6XX_PROTECT_NORDWR(0x18459, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x1a459, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x1c459, 0x1fff),
+	A6XX_PROTECT_NORDWR(0x1f400, 0x0443),
+	A6XX_PROTECT_RDONLY(0x1f844, 0x007b),
+	A6XX_PROTECT_NORDWR(0x1f860, 0x0000),
+	A6XX_PROTECT_NORDWR(0x1f878, 0x002a),
+	/* CP_PROTECT_REG[44, 46] are left untouched! */
+	0,
+	0,
+	0,
+	A6XX_PROTECT_NORDWR(0x1f8c0, 0x00000),
+};
+
 static void a6xx_set_cp_protect(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -918,6 +1239,11 @@ static void a6xx_set_cp_protect(struct msm_gpu *gpu)
 		count = ARRAY_SIZE(a660_protect);
 		count_max = 48;
 		BUILD_BUG_ON(ARRAY_SIZE(a660_protect) > 48);
+	} else if (adreno_is_a730(adreno_gpu) || adreno_is_a740(adreno_gpu)) {
+		regs = a730_protect;
+		count = ARRAY_SIZE(a730_protect);
+		count_max = 48;
+		BUILD_BUG_ON(ARRAY_SIZE(a730_protect) > 48);
 	} else {
 		regs = a6xx_protect;
 		count = ARRAY_SIZE(a6xx_protect);
@@ -984,7 +1310,11 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 	if (adreno_is_a640_family(adreno_gpu))
 		amsbc = 1;
 
-	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu)) {
+	if (adreno_is_a650(adreno_gpu) ||
+	    adreno_is_a660(adreno_gpu) ||
+	    adreno_is_a690(adreno_gpu) ||
+	    adreno_is_a730(adreno_gpu) ||
+	    adreno_is_a740_family(adreno_gpu)) {
 		/* TODO: get ddr type from bootloader and use 2 for LPDDR4 */
 		hbb_lo = 3;
 		amsbc = 1;
@@ -992,13 +1322,6 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 		uavflagprd_inv = 2;
 	}
 
-	if (adreno_is_a690(adreno_gpu)) {
-		hbb_lo = 2;
-		amsbc = 1;
-		rgb565_predicator = 1;
-		uavflagprd_inv = 2;
-	}
-
 	if (adreno_is_7c3(adreno_gpu)) {
 		hbb_lo = 1;
 		amsbc = 1;
@@ -1017,6 +1340,10 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 		  uavflagprd_inv << 4 | min_acc_len << 3 |
 		  hbb_lo << 1 | ubwc_mode);
 
+	if (adreno_is_a7xx(adreno_gpu))
+		gpu_write(gpu, REG_A7XX_GRAS_NC_MODE_CNTL,
+			  FIELD_PREP(GENMASK(8, 5), hbb_lo));
+
 	gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, min_acc_len << 23 | hbb_lo << 21);
 }
 
@@ -1049,6 +1376,55 @@ static int a6xx_cp_init(struct msm_gpu *gpu)
 	return a6xx_idle(gpu, ring) ? 0 : -EINVAL;
 }
 
+static int a7xx_cp_init(struct msm_gpu *gpu)
+{
+	struct msm_ringbuffer *ring = gpu->rb[0];
+	u32 mask;
+
+	/* Disable concurrent binning before sending CP init */
+	OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+	OUT_RING(ring, BIT(27));
+
+	OUT_PKT7(ring, CP_ME_INIT, 7);
+
+	/* Use multiple HW contexts */
+	mask = BIT(0);
+
+	/* Enable error detection */
+	mask |= BIT(1);
+
+	/* Set default reset state */
+	mask |= BIT(3);
+
+	/* Disable save/restore of performance counters across preemption */
+	mask |= BIT(6);
+
+	/* Enable the register init list with the spinlock */
+	mask |= BIT(8);
+
+	OUT_RING(ring, mask);
+
+	/* Enable multiple hardware contexts */
+	OUT_RING(ring, 0x00000003);
+
+	/* Enable error detection */
+	OUT_RING(ring, 0x20000000);
+
+	/* Operation mode mask */
+	OUT_RING(ring, 0x00000002);
+
+	/* *Don't* send a power up reg list for concurrent binning (TODO) */
+	/* Lo address */
+	OUT_RING(ring, 0x00000000);
+	/* Hi address */
+	OUT_RING(ring, 0x00000000);
+	/* BIT(31) set => read the regs from the list */
+	OUT_RING(ring, 0x00000000);
+
+	a6xx_flush(gpu, ring);
+	return a6xx_idle(gpu, ring) ? 0 : -EINVAL;
+}
+
 /*
  * Check that the microcode version is new enough to include several key
  * security fixes. Return true if the ucode is safe.
@@ -1065,6 +1441,10 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 	if (IS_ERR(buf))
 		return false;
 
+	/* A7xx is safe! */
+	if (adreno_is_a7xx(adreno_gpu))
+		return true;
+
 	/*
 	 * Targets up to a640 (a618, a630 and a640) need to check for a
 	 * microcode version that is patched to support the whereami opcode or
@@ -1181,22 +1561,46 @@ static int a6xx_zap_shader_init(struct msm_gpu *gpu)
 }
 
 #define A6XX_INT_MASK (A6XX_RBBM_INT_0_MASK_CP_AHB_ERROR | \
-	  A6XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNCFIFO_OVERFLOW | \
-	  A6XX_RBBM_INT_0_MASK_CP_HW_ERROR | \
-	  A6XX_RBBM_INT_0_MASK_CP_IB2 | \
-	  A6XX_RBBM_INT_0_MASK_CP_IB1 | \
-	  A6XX_RBBM_INT_0_MASK_CP_RB | \
-	  A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS | \
-	  A6XX_RBBM_INT_0_MASK_RBBM_ATB_BUS_OVERFLOW | \
-	  A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT | \
-	  A6XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS | \
-	  A6XX_RBBM_INT_0_MASK_UCHE_TRAP_INTR)
+		       A6XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNCFIFO_OVERFLOW | \
+		       A6XX_RBBM_INT_0_MASK_CP_HW_ERROR | \
+		       A6XX_RBBM_INT_0_MASK_CP_IB2 | \
+		       A6XX_RBBM_INT_0_MASK_CP_IB1 | \
+		       A6XX_RBBM_INT_0_MASK_CP_RB | \
+		       A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS | \
+		       A6XX_RBBM_INT_0_MASK_RBBM_ATB_BUS_OVERFLOW | \
+		       A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT | \
+		       A6XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS | \
+		       A6XX_RBBM_INT_0_MASK_UCHE_TRAP_INTR)
+
+#define A7XX_INT_MASK (A6XX_RBBM_INT_0_MASK_CP_AHB_ERROR | \
+		       A6XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNCFIFO_OVERFLOW | \
+		       A6XX_RBBM_INT_0_MASK_RBBM_GPC_ERROR | \
+		       A6XX_RBBM_INT_0_MASK_CP_SW | \
+		       A6XX_RBBM_INT_0_MASK_CP_HW_ERROR | \
+		       A6XX_RBBM_INT_0_MASK_PM4CPINTERRUPT | \
+		       A6XX_RBBM_INT_0_MASK_CP_RB_DONE_TS | \
+		       A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS | \
+		       A6XX_RBBM_INT_0_MASK_RBBM_ATB_BUS_OVERFLOW | \
+		       A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT | \
+		       A6XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS | \
+		       A6XX_RBBM_INT_0_MASK_UCHE_TRAP_INTR | \
+		       A6XX_RBBM_INT_0_MASK_TSBWRITEERROR)
+
+#define A7XX_APRIV_MASK (A6XX_CP_APRIV_CNTL_ICACHE | \
+			 A6XX_CP_APRIV_CNTL_RBFETCH | \
+			 A6XX_CP_APRIV_CNTL_RBPRIVLEVEL | \
+			 A6XX_CP_APRIV_CNTL_RBRPWB)
+
+#define A7XX_BR_APRIVMASK (A7XX_APRIV_MASK | \
+			   A6XX_CP_APRIV_CNTL_CDREAD | \
+			   A6XX_CP_APRIV_CNTL_CDWRITE)
 
 static int hw_init(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
+	u64 gmem_range_min;
 	int ret;
 
 	if (!adreno_has_gmu_wrapper(adreno_gpu)) {
@@ -1219,6 +1623,10 @@ static int hw_init(struct msm_gpu *gpu)
 		mb();
 	}
 
+	/* Some GPUs are stubborn and take their sweet time to unhalt GBIF! */
+	if (adreno_is_a7xx(adreno_gpu) && a6xx_has_gbif(adreno_gpu))
+		spin_until(!gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK));
+
 	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_CNTL, 0);
 
 	if (adreno_is_a619_holi(adreno_gpu))
@@ -1232,19 +1640,21 @@ static int hw_init(struct msm_gpu *gpu)
 	gpu_write64(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE, 0x00000000);
 	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000);
 
-	/* Turn on 64 bit addressing for all blocks */
-	gpu_write(gpu, REG_A6XX_CP_ADDR_MODE_CNTL, 0x1);
-	gpu_write(gpu, REG_A6XX_VSC_ADDR_MODE_CNTL, 0x1);
-	gpu_write(gpu, REG_A6XX_GRAS_ADDR_MODE_CNTL, 0x1);
-	gpu_write(gpu, REG_A6XX_RB_ADDR_MODE_CNTL, 0x1);
-	gpu_write(gpu, REG_A6XX_PC_ADDR_MODE_CNTL, 0x1);
-	gpu_write(gpu, REG_A6XX_HLSQ_ADDR_MODE_CNTL, 0x1);
-	gpu_write(gpu, REG_A6XX_VFD_ADDR_MODE_CNTL, 0x1);
-	gpu_write(gpu, REG_A6XX_VPC_ADDR_MODE_CNTL, 0x1);
-	gpu_write(gpu, REG_A6XX_UCHE_ADDR_MODE_CNTL, 0x1);
-	gpu_write(gpu, REG_A6XX_SP_ADDR_MODE_CNTL, 0x1);
-	gpu_write(gpu, REG_A6XX_TPL1_ADDR_MODE_CNTL, 0x1);
-	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL, 0x1);
+	if (!adreno_is_a7xx(adreno_gpu)) {
+		/* Turn on 64 bit addressing for all blocks */
+		gpu_write(gpu, REG_A6XX_CP_ADDR_MODE_CNTL, 0x1);
+		gpu_write(gpu, REG_A6XX_VSC_ADDR_MODE_CNTL, 0x1);
+		gpu_write(gpu, REG_A6XX_GRAS_ADDR_MODE_CNTL, 0x1);
+		gpu_write(gpu, REG_A6XX_RB_ADDR_MODE_CNTL, 0x1);
+		gpu_write(gpu, REG_A6XX_PC_ADDR_MODE_CNTL, 0x1);
+		gpu_write(gpu, REG_A6XX_HLSQ_ADDR_MODE_CNTL, 0x1);
+		gpu_write(gpu, REG_A6XX_VFD_ADDR_MODE_CNTL, 0x1);
+		gpu_write(gpu, REG_A6XX_VPC_ADDR_MODE_CNTL, 0x1);
+		gpu_write(gpu, REG_A6XX_UCHE_ADDR_MODE_CNTL, 0x1);
+		gpu_write(gpu, REG_A6XX_SP_ADDR_MODE_CNTL, 0x1);
+		gpu_write(gpu, REG_A6XX_TPL1_ADDR_MODE_CNTL, 0x1);
+		gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL, 0x1);
+	}
 
 	/* enable hardware clockgating */
 	a6xx_set_hwcg(gpu, true);
@@ -1252,12 +1662,14 @@ static int hw_init(struct msm_gpu *gpu)
 	/* VBIF/GBIF start*/
 	if (adreno_is_a610(adreno_gpu) ||
 	    adreno_is_a640_family(adreno_gpu) ||
-	    adreno_is_a650_family(adreno_gpu)) {
+	    adreno_is_a650_family(adreno_gpu) ||
+	    adreno_is_a7xx(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE0, 0x00071620);
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE1, 0x00071620);
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE2, 0x00071620);
 		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE3, 0x00071620);
-		gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x3);
+		gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL,
+			  adreno_is_a7xx(adreno_gpu) ? 0x2120212 : 0x3);
 	} else {
 		gpu_write(gpu, REG_A6XX_RBBM_VBIF_CLIENT_QOS_CNTL, 0x3);
 	}
@@ -1265,24 +1677,39 @@ static int hw_init(struct msm_gpu *gpu)
 	if (adreno_is_a630(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009);
 
+	if (adreno_is_a7xx(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_UCHE_GBIF_GX_CONFIG, 0x10240e0);
+
 	/* Make all blocks contribute to the GPU BUSY perf counter */
 	gpu_write(gpu, REG_A6XX_RBBM_PERFCTR_GPU_BUSY_MASKED, 0xffffffff);
 
 	/* Disable L2 bypass in the UCHE */
-	gpu_write64(gpu, REG_A6XX_UCHE_WRITE_RANGE_MAX, 0x0001ffffffffffc0llu);
-	gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, 0x0001fffffffff000llu);
-	gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, 0x0001fffffffff000llu);
+	if (adreno_is_a7xx(adreno_gpu)) {
+		gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, 0x0001fffffffff000llu);
+		gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, 0x0001fffffffff000llu);
+	} else {
+		gpu_write64(gpu, REG_A6XX_UCHE_WRITE_RANGE_MAX, 0x0001ffffffffffc0llu);
+		gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, 0x0001fffffffff000llu);
+		gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, 0x0001fffffffff000llu);
+	}
+
+	if (!(adreno_is_a650_family(adreno_gpu) ||
+	      adreno_is_a730(adreno_gpu))) {
+		gmem_range_min = adreno_is_a740_family(adreno_gpu) ? SZ_16M : SZ_1M;
 
-	if (!adreno_is_a650_family(adreno_gpu)) {
 		/* Set the GMEM VA range [0x100000:0x100000 + gpu->gmem - 1] */
-		gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN, 0x00100000);
+		gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN, gmem_range_min);
 
 		gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MAX,
-			0x00100000 + adreno_gpu->info->gmem - 1);
+			gmem_range_min + adreno_gpu->info->gmem - 1);
 	}
 
-	gpu_write(gpu, REG_A6XX_UCHE_FILTER_CNTL, 0x804);
-	gpu_write(gpu, REG_A6XX_UCHE_CACHE_WAYS, 0x4);
+	if (adreno_is_a7xx(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_UCHE_CACHE_WAYS, BIT(23));
+	else {
+		gpu_write(gpu, REG_A6XX_UCHE_FILTER_CNTL, 0x804);
+		gpu_write(gpu, REG_A6XX_UCHE_CACHE_WAYS, 0x4);
+	}
 
 	if (adreno_is_a640_family(adreno_gpu) || adreno_is_a650_family(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x02000140);
@@ -1290,7 +1717,7 @@ static int hw_init(struct msm_gpu *gpu)
 	} else if (adreno_is_a610(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x00800060);
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_1, 0x40201b16);
-	} else {
+	} else if (!adreno_is_a7xx(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x010000c0);
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_1, 0x8040362c);
 	}
@@ -1302,13 +1729,15 @@ static int hw_init(struct msm_gpu *gpu)
 	if (adreno_is_a610(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 48);
 		gpu_write(gpu, REG_A6XX_CP_MEM_POOL_DBG_ADDR, 47);
-	} else
+	} else if (!adreno_is_a7xx(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 128);
 
 	/* Setting the primFifo thresholds default values,
 	 * and vccCacheSkipDis=1 bit (0x200) for A640 and newer
 	*/
-	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu) || adreno_is_a690(adreno_gpu))
+	if (adreno_is_a690(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00800200);
+	else if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
 	else if (adreno_is_a640_family(adreno_gpu) || adreno_is_7c3(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00200200);
@@ -1318,7 +1747,7 @@ static int hw_init(struct msm_gpu *gpu)
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00018000);
 	else if (adreno_is_a610(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00080000);
-	else
+	else if (!adreno_is_a7xx(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00180000);
 
 	/* Set the AHB default slave response to "ERROR" */
@@ -1327,13 +1756,24 @@ static int hw_init(struct msm_gpu *gpu)
 	/* Turn on performance counters */
 	gpu_write(gpu, REG_A6XX_RBBM_PERFCTR_CNTL, 0x1);
 
+	if (adreno_is_a7xx(adreno_gpu)) {
+		/* Turn on the IFPC counter (countable 4 on XOCLK4) */
+		gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_SELECT_1,
+			  FIELD_PREP(GENMASK(7, 0), 0x4));
+	}
+
 	/* Select CP0 to always count cycles */
 	gpu_write(gpu, REG_A6XX_CP_PERFCTR_CP_SEL(0), PERF_CP_ALWAYS_COUNT);
 
 	a6xx_set_ubwc_config(gpu);
 
 	/* Enable fault detection */
-	if (adreno_is_a619(adreno_gpu))
+	if (adreno_is_a730(adreno_gpu) ||
+	    adreno_is_a740_family(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0xcfffff);
+	else if (adreno_is_a690(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0x4fffff);
+	else if (adreno_is_a619(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0x3fffff);
 	else if (adreno_is_a610(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0x3ffff);
@@ -1366,22 +1806,43 @@ static int hw_init(struct msm_gpu *gpu)
 	a6xx_set_cp_protect(gpu);
 
 	if (adreno_is_a660_family(adreno_gpu)) {
-		gpu_write(gpu, REG_A6XX_CP_CHICKEN_DBG, 0x1);
+		if (adreno_is_a690(adreno_gpu))
+			gpu_write(gpu, REG_A6XX_CP_CHICKEN_DBG, 0x00028801);
+		else
+			gpu_write(gpu, REG_A6XX_CP_CHICKEN_DBG, 0x1);
 		gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x0);
 	}
 
+	if (adreno_is_a690(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x90);
 	/* Set dualQ + disable afull for A660 GPU */
-	if (adreno_is_a660(adreno_gpu))
+	else if (adreno_is_a660(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
+	else if (adreno_is_a7xx(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG,
+			  FIELD_PREP(GENMASK(19, 16), 6) |
+			  FIELD_PREP(GENMASK(15, 12), 6) |
+			  FIELD_PREP(GENMASK(11, 8), 9) |
+			  BIT(3) | BIT(2) |
+			  FIELD_PREP(GENMASK(1, 0), 2));
 
 	/* Enable expanded apriv for targets that support it */
 	if (gpu->hw_apriv) {
-		gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL,
-			(1 << 6) | (1 << 5) | (1 << 3) | (1 << 2) | (1 << 1));
+		if (adreno_is_a7xx(adreno_gpu)) {
+			gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL,
+				  A7XX_BR_APRIVMASK);
+			gpu_write(gpu, REG_A7XX_CP_BV_APRIV_CNTL,
+				  A7XX_APRIV_MASK);
+			gpu_write(gpu, REG_A7XX_CP_LPAC_APRIV_CNTL,
+				  A7XX_APRIV_MASK);
+		} else
+			gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL,
+				  BIT(6) | BIT(5) | BIT(3) | BIT(2) | BIT(1));
 	}
 
 	/* Enable interrupts */
-	gpu_write(gpu, REG_A6XX_RBBM_INT_0_MASK, A6XX_INT_MASK);
+	gpu_write(gpu, REG_A6XX_RBBM_INT_0_MASK,
+		  adreno_is_a7xx(adreno_gpu) ? A7XX_INT_MASK : A6XX_INT_MASK);
 
 	ret = adreno_hw_init(gpu);
 	if (ret)
@@ -1408,6 +1869,12 @@ static int hw_init(struct msm_gpu *gpu)
 			shadowptr(a6xx_gpu, gpu->rb[0]));
 	}
 
+	/* ..which means "always" on A7xx, also for BV shadow */
+	if (adreno_is_a7xx(adreno_gpu)) {
+		gpu_write64(gpu, REG_A7XX_CP_BV_RB_RPTR_ADDR,
+			    rbmemptr(gpu->rb[0], bv_fence));
+	}
+
 	/* Always come up on rb 0 */
 	a6xx_gpu->cur_ring = gpu->rb[0];
 
@@ -1416,7 +1883,7 @@ static int hw_init(struct msm_gpu *gpu)
 	/* Enable the SQE_to start the CP engine */
 	gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 1);
 
-	ret = a6xx_cp_init(gpu);
+	ret = adreno_is_a7xx(adreno_gpu) ? a7xx_cp_init(gpu) : a6xx_cp_init(gpu);
 	if (ret)
 		goto out;
 
@@ -1653,7 +2120,7 @@ static void a6xx_cp_hw_err_irq(struct msm_gpu *gpu)
 			(val & 0x3ffff), val);
 	}
 
-	if (status & A6XX_CP_INT_CP_AHB_ERROR)
+	if (status & A6XX_CP_INT_CP_AHB_ERROR && !adreno_is_a7xx(to_adreno_gpu(gpu)))
 		dev_err_ratelimited(&gpu->pdev->dev, "CP AHB error interrupt\n");
 
 	if (status & A6XX_CP_INT_CP_VSD_PARITY_ERROR)
@@ -1803,6 +2270,35 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 	gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0), cntl1_regval);
 }
 
+static void a7xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
+{
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	struct msm_gpu *gpu = &adreno_gpu->base;
+
+	if (IS_ERR(a6xx_gpu->llc_mmio))
+		return;
+
+	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
+		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
+
+		gpu_scid &= GENMASK(4, 0);
+
+		gpu_write(gpu, REG_A6XX_GBIF_SCACHE_CNTL1,
+			  FIELD_PREP(GENMASK(29, 25), gpu_scid) |
+			  FIELD_PREP(GENMASK(24, 20), gpu_scid) |
+			  FIELD_PREP(GENMASK(19, 15), gpu_scid) |
+			  FIELD_PREP(GENMASK(14, 10), gpu_scid) |
+			  FIELD_PREP(GENMASK(9, 5), gpu_scid) |
+			  FIELD_PREP(GENMASK(4, 0), gpu_scid));
+
+		gpu_write(gpu, REG_A6XX_GBIF_SCACHE_CNTL0,
+			  FIELD_PREP(GENMASK(14, 10), gpu_scid) |
+			  BIT(8));
+	}
+
+	llcc_slice_activate(a6xx_gpu->htw_llc_slice);
+}
+
 static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu)
 {
 	/* No LLCC on non-RPMh (and by extension, non-GMU) SoCs */
@@ -1814,7 +2310,7 @@ static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu)
 }
 
 static void a6xx_llc_slices_init(struct platform_device *pdev,
-		struct a6xx_gpu *a6xx_gpu)
+		struct a6xx_gpu *a6xx_gpu, bool is_a7xx)
 {
 	struct device_node *phandle;
 
@@ -1823,18 +2319,18 @@ static void a6xx_llc_slices_init(struct platform_device *pdev,
 		return;
 
 	/*
-	 * There is a different programming path for targets with an mmu500
-	 * attached, so detect if that is the case
+	 * There is a different programming path for A6xx targets with an
+	 * mmu500 attached, so detect if that is the case
 	 */
 	phandle = of_parse_phandle(pdev->dev.of_node, "iommus", 0);
 	a6xx_gpu->have_mmu500 = (phandle &&
 		of_device_is_compatible(phandle, "arm,mmu-500"));
 	of_node_put(phandle);
 
-	if (a6xx_gpu->have_mmu500)
-		a6xx_gpu->llc_mmio = NULL;
-	else
+	if (is_a7xx || !a6xx_gpu->have_mmu500)
 		a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem");
+	else
+		a6xx_gpu->llc_mmio = NULL;
 
 	a6xx_gpu->llc_slice = llcc_slice_getd(LLCC_GPU);
 	a6xx_gpu->htw_llc_slice = llcc_slice_getd(LLCC_GPUHTW);
@@ -1920,7 +2416,7 @@ static int a6xx_gmu_pm_resume(struct msm_gpu *gpu)
 
 	msm_devfreq_resume(gpu);
 
-	a6xx_llc_activate(a6xx_gpu);
+	adreno_is_a7xx(adreno_gpu) ? a7xx_llc_activate : a6xx_llc_activate(a6xx_gpu);
 
 	return ret;
 }
@@ -2307,6 +2803,37 @@ static const struct adreno_gpu_funcs funcs_gmuwrapper = {
 	.get_timestamp = a6xx_get_timestamp,
 };
 
+static const struct adreno_gpu_funcs funcs_a7xx = {
+	.base = {
+		.get_param = adreno_get_param,
+		.set_param = adreno_set_param,
+		.hw_init = a6xx_hw_init,
+		.ucode_load = a6xx_ucode_load,
+		.pm_suspend = a6xx_gmu_pm_suspend,
+		.pm_resume = a6xx_gmu_pm_resume,
+		.recover = a6xx_recover,
+		.submit = a7xx_submit,
+		.active_ring = a6xx_active_ring,
+		.irq = a6xx_irq,
+		.destroy = a6xx_destroy,
+#if defined(CONFIG_DRM_MSM_GPU_STATE)
+		.show = a6xx_show,
+#endif
+		.gpu_busy = a6xx_gpu_busy,
+		.gpu_get_freq = a6xx_gmu_get_freq,
+		.gpu_set_freq = a6xx_gpu_set_freq,
+#if defined(CONFIG_DRM_MSM_GPU_STATE)
+		.gpu_state_get = a6xx_gpu_state_get,
+		.gpu_state_put = a6xx_gpu_state_put,
+#endif
+		.create_address_space = a6xx_create_address_space,
+		.create_private_address_space = a6xx_create_private_address_space,
+		.get_rptr = a6xx_get_rptr,
+		.progress = a6xx_progress,
+	},
+	.get_timestamp = a6xx_gmu_get_timestamp,
+};
+
 struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
@@ -2316,6 +2843,7 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	struct a6xx_gpu *a6xx_gpu;
 	struct adreno_gpu *adreno_gpu;
 	struct msm_gpu *gpu;
+	bool is_a7xx;
 	int ret;
 
 	a6xx_gpu = kzalloc(sizeof(*a6xx_gpu), GFP_KERNEL);
@@ -2339,7 +2867,11 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	adreno_gpu->base.hw_apriv =
 		!!(config->info->quirks & ADRENO_QUIRK_HAS_HW_APRIV);
 
-	a6xx_llc_slices_init(pdev, a6xx_gpu);
+	/* gpu->info only gets assigned in adreno_gpu_init() */
+	is_a7xx = config->info->family == ADRENO_7XX_GEN1 ||
+		  config->info->family == ADRENO_7XX_GEN2;
+
+	a6xx_llc_slices_init(pdev, a6xx_gpu, is_a7xx);
 
 	ret = a6xx_set_supported_hw(&pdev->dev, config->info);
 	if (ret) {
@@ -2347,7 +2879,9 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 		return ERR_PTR(ret);
 	}
 
-	if (adreno_has_gmu_wrapper(adreno_gpu))
+	if (is_a7xx)
+		ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_a7xx, 1);
+	else if (adreno_has_gmu_wrapper(adreno_gpu))
 		ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_gmuwrapper, 1);
 	else
 		ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 4e5d650578..91a564a24d 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -882,12 +882,13 @@ static void a6xx_snapshot_gmu_hfi_history(struct msm_gpu *gpu,
 	}
 }
 
+#define A6XX_REGLIST_SIZE        1
 #define A6XX_GBIF_REGLIST_SIZE   1
 static void a6xx_get_registers(struct msm_gpu *gpu,
 		struct a6xx_gpu_state *a6xx_state,
 		struct a6xx_crashdumper *dumper)
 {
-	int i, count = ARRAY_SIZE(a6xx_ahb_reglist) +
+	int i, count = A6XX_REGLIST_SIZE +
 		ARRAY_SIZE(a6xx_reglist) +
 		ARRAY_SIZE(a6xx_hlsq_reglist) + A6XX_GBIF_REGLIST_SIZE;
 	int index = 0;
@@ -901,12 +902,20 @@ static void a6xx_get_registers(struct msm_gpu *gpu,
 
 	a6xx_state->nr_registers = count;
 
-	for (i = 0; i < ARRAY_SIZE(a6xx_ahb_reglist); i++)
+	if (adreno_is_a7xx(adreno_gpu))
 		a6xx_get_ahb_gpu_registers(gpu,
-			a6xx_state, &a6xx_ahb_reglist[i],
+			a6xx_state, &a7xx_ahb_reglist,
+			&a6xx_state->registers[index++]);
+	else
+		a6xx_get_ahb_gpu_registers(gpu,
+			a6xx_state, &a6xx_ahb_reglist,
 			&a6xx_state->registers[index++]);
 
-	if (a6xx_has_gbif(adreno_gpu))
+	if (adreno_is_a7xx(adreno_gpu))
+		a6xx_get_ahb_gpu_registers(gpu,
+				a6xx_state, &a7xx_gbif_reglist,
+				&a6xx_state->registers[index++]);
+	else if (a6xx_has_gbif(adreno_gpu))
 		a6xx_get_ahb_gpu_registers(gpu,
 				a6xx_state, &a6xx_gbif_reglist,
 				&a6xx_state->registers[index++]);
@@ -948,6 +957,18 @@ static u32 a6xx_get_cp_roq_size(struct msm_gpu *gpu)
 	return gpu_read(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2) >> 14;
 }
 
+static u32 a7xx_get_cp_roq_size(struct msm_gpu *gpu)
+{
+	/*
+	 * The value at CP_ROQ_THRESHOLDS_2[20:31] is in 4dword units.
+	 * That register however is not directly accessible from APSS on A7xx.
+	 * Program the SQE_UCODE_DBG_ADDR with offset=0x70d3 and read the value.
+	 */
+	gpu_write(gpu, REG_A6XX_CP_SQE_UCODE_DBG_ADDR, 0x70d3);
+
+	return 4 * (gpu_read(gpu, REG_A6XX_CP_SQE_UCODE_DBG_DATA) >> 20);
+}
+
 /* Read a block of data from an indexed register pair */
 static void a6xx_get_indexed_regs(struct msm_gpu *gpu,
 		struct a6xx_gpu_state *a6xx_state,
@@ -1019,8 +1040,40 @@ static void a6xx_get_indexed_registers(struct msm_gpu *gpu,
 
 	/* Restore the size in the hardware */
 	gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, mempool_size);
+}
 
-	a6xx_state->nr_indexed_regs = count;
+static void a7xx_get_indexed_registers(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state)
+{
+	int i, indexed_count, mempool_count;
+
+	indexed_count = ARRAY_SIZE(a7xx_indexed_reglist);
+	mempool_count = ARRAY_SIZE(a7xx_cp_bv_mempool_indexed);
+
+	a6xx_state->indexed_regs = state_kcalloc(a6xx_state,
+					indexed_count + mempool_count,
+					sizeof(*a6xx_state->indexed_regs));
+	if (!a6xx_state->indexed_regs)
+		return;
+
+	a6xx_state->nr_indexed_regs = indexed_count + mempool_count;
+
+	/* First read the common regs */
+	for (i = 0; i < indexed_count; i++)
+		a6xx_get_indexed_regs(gpu, a6xx_state, &a7xx_indexed_reglist[i],
+			&a6xx_state->indexed_regs[i]);
+
+	gpu_rmw(gpu, REG_A6XX_CP_CHICKEN_DBG, 0, BIT(2));
+	gpu_rmw(gpu, REG_A7XX_CP_BV_CHICKEN_DBG, 0, BIT(2));
+
+	/* Get the contents of the CP_BV mempool */
+	for (i = 0; i < mempool_count; i++)
+		a6xx_get_indexed_regs(gpu, a6xx_state, a7xx_cp_bv_mempool_indexed,
+			&a6xx_state->indexed_regs[indexed_count - 1 + i]);
+
+	gpu_rmw(gpu, REG_A6XX_CP_CHICKEN_DBG, BIT(2), 0);
+	gpu_rmw(gpu, REG_A7XX_CP_BV_CHICKEN_DBG, BIT(2), 0);
+	return;
 }
 
 struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
@@ -1056,6 +1109,12 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
 		return &a6xx_state->base;
 
 	/* Get the banks of indexed registers */
+	if (adreno_is_a7xx(adreno_gpu)) {
+		a7xx_get_indexed_registers(gpu, a6xx_state);
+		/* Further codeflow is untested on A7xx. */
+		return &a6xx_state->base;
+	}
+
 	a6xx_get_indexed_registers(gpu, a6xx_state);
 
 	/*
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
index e788ed72eb..9560fc1b85 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
@@ -328,9 +328,8 @@ static const u32 a6xx_gbif_registers[] = {
 	0x3C00, 0X3C0B, 0X3C40, 0X3C47, 0X3CC0, 0X3CD1, 0xE3A, 0xE3A,
 };
 
-static const struct a6xx_registers a6xx_ahb_reglist[] = {
-	REGS(a6xx_ahb_registers, 0, 0),
-};
+static const struct a6xx_registers a6xx_ahb_reglist =
+	REGS(a6xx_ahb_registers, 0, 0);
 
 static const struct a6xx_registers a6xx_vbif_reglist =
 			REGS(a6xx_vbif_registers, 0, 0);
@@ -338,6 +337,27 @@ static const struct a6xx_registers a6xx_vbif_reglist =
 static const struct a6xx_registers a6xx_gbif_reglist =
 			REGS(a6xx_gbif_registers, 0, 0);
 
+static const u32 a7xx_ahb_registers[] = {
+	/* RBBM_STATUS */
+	0x210, 0x210,
+	/* RBBM_STATUS2-3 */
+	0x212, 0x213,
+};
+
+static const u32 a7xx_gbif_registers[] = {
+	0x3c00, 0x3c0b,
+	0x3c40, 0x3c42,
+	0x3c45, 0x3c47,
+	0x3c49, 0x3c4a,
+	0x3cc0, 0x3cd1,
+};
+
+static const struct a6xx_registers a7xx_ahb_reglist=
+	REGS(a7xx_ahb_registers, 0, 0);
+
+static const struct a6xx_registers a7xx_gbif_reglist =
+	REGS(a7xx_gbif_registers, 0, 0);
+
 static const u32 a6xx_gmu_gx_registers[] = {
 	/* GMU GX */
 	0x0000, 0x0000, 0x0010, 0x0013, 0x0016, 0x0016, 0x0018, 0x001b,
@@ -384,14 +404,17 @@ static const struct a6xx_registers a6xx_gmu_reglist[] = {
 };
 
 static u32 a6xx_get_cp_roq_size(struct msm_gpu *gpu);
+static u32 a7xx_get_cp_roq_size(struct msm_gpu *gpu);
 
-static struct a6xx_indexed_registers {
+struct a6xx_indexed_registers {
 	const char *name;
 	u32 addr;
 	u32 data;
 	u32 count;
 	u32 (*count_fn)(struct msm_gpu *gpu);
-} a6xx_indexed_reglist[] = {
+};
+
+static struct a6xx_indexed_registers a6xx_indexed_reglist[] = {
 	{ "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
 		REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL },
 	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
@@ -402,11 +425,43 @@ static struct a6xx_indexed_registers {
 		REG_A6XX_CP_ROQ_DBG_DATA, 0, a6xx_get_cp_roq_size},
 };
 
+static struct a6xx_indexed_registers a7xx_indexed_reglist[] = {
+	{ "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
+		REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL },
+	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
+		REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL },
+	{ "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
+		REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL },
+	{ "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR,
+		REG_A7XX_CP_BV_SQE_STAT_DATA, 0x33, NULL },
+	{ "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR,
+		REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x100, NULL },
+	{ "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR,
+		REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x8000, NULL },
+	{ "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR,
+		REG_A7XX_CP_SQE_AC_STAT_DATA, 0x33, NULL },
+	{ "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR,
+		REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x100, NULL },
+	{ "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR,
+		REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x8000, NULL },
+	{ "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR,
+		REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x40, NULL },
+	{ "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR,
+		REG_A6XX_CP_ROQ_DBG_DATA, 0, a7xx_get_cp_roq_size },
+};
+
 static struct a6xx_indexed_registers a6xx_cp_mempool_indexed = {
 	"CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
 		REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2060, NULL,
 };
 
+static struct a6xx_indexed_registers a7xx_cp_bv_mempool_indexed[] = {
+	{ "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
+		REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2100, NULL },
+	{ "CP_BV_MEMPOOL", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR,
+		REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2100, NULL },
+};
+
 #define DEBUGBUS(_id, _count) { .id = _id, .name = #_id, .count = _count }
 
 static const struct a6xx_debugbus_block {
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
index 25b235b49e..cdb3f6e74d 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
@@ -5,6 +5,8 @@
 #include <linux/circ_buf.h>
 #include <linux/list.h>
 
+#include <soc/qcom/cmd-db.h>
+
 #include "a6xx_gmu.h"
 #include "a6xx_gmu.xml.h"
 #include "a6xx_gpu.h"
@@ -506,6 +508,88 @@ static void adreno_7c3_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 	msg->cnoc_cmds_data[0][0] =  0x40000000;
 	msg->cnoc_cmds_data[1][0] =  0x60000001;
 }
+
+static void a730_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+	msg->bw_level_num = 12;
+
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x7;
+
+	msg->ddr_cmds_addrs[0] = cmd_db_read_addr("SH0");
+	msg->ddr_cmds_addrs[1] = cmd_db_read_addr("MC0");
+	msg->ddr_cmds_addrs[2] = cmd_db_read_addr("ACV");
+
+	msg->ddr_cmds_data[0][0] = 0x40000000;
+	msg->ddr_cmds_data[0][1] = 0x40000000;
+	msg->ddr_cmds_data[0][2] = 0x40000000;
+	msg->ddr_cmds_data[1][0] = 0x600002e8;
+	msg->ddr_cmds_data[1][1] = 0x600003d0;
+	msg->ddr_cmds_data[1][2] = 0x60000008;
+	msg->ddr_cmds_data[2][0] = 0x6000068d;
+	msg->ddr_cmds_data[2][1] = 0x6000089a;
+	msg->ddr_cmds_data[2][2] = 0x60000008;
+	msg->ddr_cmds_data[3][0] = 0x600007f2;
+	msg->ddr_cmds_data[3][1] = 0x60000a6e;
+	msg->ddr_cmds_data[3][2] = 0x60000008;
+	msg->ddr_cmds_data[4][0] = 0x600009e5;
+	msg->ddr_cmds_data[4][1] = 0x60000cfd;
+	msg->ddr_cmds_data[4][2] = 0x60000008;
+	msg->ddr_cmds_data[5][0] = 0x60000b29;
+	msg->ddr_cmds_data[5][1] = 0x60000ea6;
+	msg->ddr_cmds_data[5][2] = 0x60000008;
+	msg->ddr_cmds_data[6][0] = 0x60001698;
+	msg->ddr_cmds_data[6][1] = 0x60001da8;
+	msg->ddr_cmds_data[6][2] = 0x60000008;
+	msg->ddr_cmds_data[7][0] = 0x600018d2;
+	msg->ddr_cmds_data[7][1] = 0x60002093;
+	msg->ddr_cmds_data[7][2] = 0x60000008;
+	msg->ddr_cmds_data[8][0] = 0x60001e66;
+	msg->ddr_cmds_data[8][1] = 0x600027e6;
+	msg->ddr_cmds_data[8][2] = 0x60000008;
+	msg->ddr_cmds_data[9][0] = 0x600027c2;
+	msg->ddr_cmds_data[9][1] = 0x6000342f;
+	msg->ddr_cmds_data[9][2] = 0x60000008;
+	msg->ddr_cmds_data[10][0] = 0x60002e71;
+	msg->ddr_cmds_data[10][1] = 0x60003cf5;
+	msg->ddr_cmds_data[10][2] = 0x60000008;
+	msg->ddr_cmds_data[11][0] = 0x600030ae;
+	msg->ddr_cmds_data[11][1] = 0x60003fe5;
+	msg->ddr_cmds_data[11][2] = 0x60000008;
+
+	msg->cnoc_cmds_num = 1;
+	msg->cnoc_wait_bitmask = 0x1;
+
+	msg->cnoc_cmds_addrs[0] = cmd_db_read_addr("CN0");
+	msg->cnoc_cmds_data[0][0] = 0x40000000;
+	msg->cnoc_cmds_data[1][0] = 0x60000001;
+}
+
+static void a740_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+	msg->bw_level_num = 1;
+
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x7;
+
+	msg->ddr_cmds_addrs[0] = cmd_db_read_addr("SH0");
+	msg->ddr_cmds_addrs[1] = cmd_db_read_addr("MC0");
+	msg->ddr_cmds_addrs[2] = cmd_db_read_addr("ACV");
+
+	msg->ddr_cmds_data[0][0] = 0x40000000;
+	msg->ddr_cmds_data[0][1] = 0x40000000;
+	msg->ddr_cmds_data[0][2] = 0x40000000;
+
+	/* TODO: add a proper dvfs table */
+
+	msg->cnoc_cmds_num = 1;
+	msg->cnoc_wait_bitmask = 0x1;
+
+	msg->cnoc_cmds_addrs[0] = cmd_db_read_addr("CN0");
+	msg->cnoc_cmds_data[0][0] = 0x40000000;
+	msg->cnoc_cmds_data[1][0] = 0x60000001;
+}
+
 static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 {
 	/* Send a single "off" entry since the 630 GMU doesn't do bus scaling */
@@ -564,6 +648,10 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
 		a660_build_bw_table(&msg);
 	else if (adreno_is_a690(adreno_gpu))
 		a690_build_bw_table(&msg);
+	else if (adreno_is_a730(adreno_gpu))
+		a730_build_bw_table(&msg);
+	else if (adreno_is_a740_family(adreno_gpu))
+		a740_build_bw_table(&msg);
 	else
 		a6xx_build_bw_table(&msg);
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index b7b527e21d..3ee14646ab 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -454,11 +454,13 @@ static const struct adreno_info gpulist[] = {
 		.quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT |
 			ADRENO_QUIRK_HAS_HW_APRIV,
 		.init = a6xx_gpu_init,
+		.zapfw = "a660_zap.mbn",
 		.hwcg = a660_hwcg,
 		.address_space_size = SZ_16G,
 		.speedbins = ADRENO_SPEEDBINS(
 			{ 0,   0 },
 			{ 117, 0 },
+			{ 172, 2 }, /* Called speedbin 1 downstream, but let's not break things! */
 			{ 190, 1 },
 		),
 	}, {
@@ -490,6 +492,36 @@ static const struct adreno_info gpulist[] = {
 		.zapfw = "a690_zap.mdt",
 		.hwcg = a690_hwcg,
 		.address_space_size = SZ_16G,
+	}, {
+		.chip_ids = ADRENO_CHIP_IDS(0x07030001),
+		.family = ADRENO_7XX_GEN1,
+		.fw = {
+			[ADRENO_FW_SQE] = "a730_sqe.fw",
+			[ADRENO_FW_GMU] = "gmu_gen70000.bin",
+		},
+		.gmem = SZ_2M,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT |
+			  ADRENO_QUIRK_HAS_HW_APRIV,
+		.init = a6xx_gpu_init,
+		.zapfw = "a730_zap.mdt",
+		.hwcg = a730_hwcg,
+		.address_space_size = SZ_16G,
+	}, {
+		.chip_ids = ADRENO_CHIP_IDS(0x43050a01), /* "C510v2" */
+		.family = ADRENO_7XX_GEN2,
+		.fw = {
+			[ADRENO_FW_SQE] = "a740_sqe.fw",
+			[ADRENO_FW_GMU] = "gmu_gen70200.bin",
+		},
+		.gmem = 3 * SZ_1M,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT |
+			  ADRENO_QUIRK_HAS_HW_APRIV,
+		.init = a6xx_gpu_init,
+		.zapfw = "a740_zap.mdt",
+		.hwcg = a740_hwcg,
+		.address_space_size = SZ_16G,
 	},
 };
 
@@ -751,10 +783,9 @@ static int adreno_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int adreno_remove(struct platform_device *pdev)
+static void adreno_remove(struct platform_device *pdev)
 {
 	component_del(&pdev->dev, &a3xx_ops);
-	return 0;
 }
 
 static void adreno_shutdown(struct platform_device *pdev)
@@ -869,7 +900,7 @@ static const struct dev_pm_ops adreno_pm_ops = {
 
 static struct platform_driver adreno_driver = {
 	.probe = adreno_probe,
-	.remove = adreno_remove,
+	.remove_new = adreno_remove,
 	.shutdown = adreno_shutdown,
 	.driver = {
 		.name = "adreno",
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 8090dde032..3fe9fd240c 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -323,7 +323,11 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx,
 		*value = adreno_gpu->info->gmem;
 		return 0;
 	case MSM_PARAM_GMEM_BASE:
-		*value = !adreno_is_a650_family(adreno_gpu) ? 0x100000 : 0;
+		if (adreno_is_a650_family(adreno_gpu) ||
+		    adreno_is_a740_family(adreno_gpu))
+			*value = 0;
+		else
+			*value = 0x100000;
 		return 0;
 	case MSM_PARAM_CHIP_ID:
 		*value = adreno_gpu->chip_id;
@@ -567,6 +571,7 @@ int adreno_hw_init(struct msm_gpu *gpu)
 		ring->cur = ring->start;
 		ring->next = ring->start;
 		ring->memptrs->rptr = 0;
+		ring->memptrs->bv_fence = ring->fctx->completed_fence;
 
 		/* Detect and clean up an impossible fence, ie. if GPU managed
 		 * to scribble something invalid, we don't want that to confuse
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 49f38edf98..80b3f63121 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -46,6 +46,8 @@ enum adreno_family {
 	ADRENO_6XX_GEN2,  /* a640 family */
 	ADRENO_6XX_GEN3,  /* a650 family */
 	ADRENO_6XX_GEN4,  /* a660 family */
+	ADRENO_7XX_GEN1,  /* a730 family */
+	ADRENO_7XX_GEN2,  /* a740 family */
 };
 
 #define ADRENO_QUIRK_TWO_PASS_USE_WFI		BIT(0)
@@ -75,7 +77,7 @@ struct adreno_reglist {
 };
 
 extern const struct adreno_reglist a612_hwcg[], a615_hwcg[], a630_hwcg[], a640_hwcg[], a650_hwcg[];
-extern const struct adreno_reglist a660_hwcg[], a690_hwcg[];
+extern const struct adreno_reglist a660_hwcg[], a690_hwcg[], a730_hwcg[], a740_hwcg[];
 
 struct adreno_speedbin {
 	uint16_t fuse;
@@ -391,7 +393,8 @@ static inline int adreno_is_a650_family(const struct adreno_gpu *gpu)
 {
 	if (WARN_ON_ONCE(!gpu->info))
 		return false;
-	return gpu->info->family >= ADRENO_6XX_GEN3;
+	return gpu->info->family == ADRENO_6XX_GEN3 ||
+	       gpu->info->family == ADRENO_6XX_GEN4;
 }
 
 static inline int adreno_is_a640_family(const struct adreno_gpu *gpu)
@@ -401,6 +404,31 @@ static inline int adreno_is_a640_family(const struct adreno_gpu *gpu)
 	return gpu->info->family == ADRENO_6XX_GEN2;
 }
 
+static inline int adreno_is_a730(struct adreno_gpu *gpu)
+{
+	return gpu->info->chip_ids[0] == 0x07030001;
+}
+
+static inline int adreno_is_a740(struct adreno_gpu *gpu)
+{
+	return gpu->info->chip_ids[0] == 0x43050a01;
+}
+
+/* Placeholder to make future diffs smaller */
+static inline int adreno_is_a740_family(struct adreno_gpu *gpu)
+{
+	if (WARN_ON_ONCE(!gpu->info))
+		return false;
+	return gpu->info->family == ADRENO_7XX_GEN2;
+}
+
+static inline int adreno_is_a7xx(struct adreno_gpu *gpu)
+{
+	/* Update with non-fake (i.e. non-A702) Gen 7 GPUs */
+	return gpu->info->family == ADRENO_7XX_GEN1 ||
+	       adreno_is_a740_family(gpu);
+}
+
 u64 adreno_private_address_space_size(struct msm_gpu *gpu);
 int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx,
 		     uint32_t param, uint64_t *value, uint32_t *len);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h
index 43c47a19cd..aa1867943c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h
@@ -244,7 +244,6 @@ static const struct dpu_intf_cfg msm8998_intf[] = {
 		.prog_fetch_lines_worst_case = 21,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x6a800, .len = 0x280,
@@ -253,7 +252,6 @@ static const struct dpu_intf_cfg msm8998_intf[] = {
 		.prog_fetch_lines_worst_case = 21,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_2", .id = INTF_2,
 		.base = 0x6b000, .len = 0x280,
@@ -262,7 +260,6 @@ static const struct dpu_intf_cfg msm8998_intf[] = {
 		.prog_fetch_lines_worst_case = 21,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_3", .id = INTF_3,
 		.base = 0x6b800, .len = 0x280,
@@ -270,7 +267,6 @@ static const struct dpu_intf_cfg msm8998_intf[] = {
 		.prog_fetch_lines_worst_case = 21,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h
index 88a5177dfd..38ac0c1a13 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h
@@ -260,7 +260,6 @@ static const struct dpu_intf_cfg sdm845_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x6a800, .len = 0x280,
@@ -269,7 +268,6 @@ static const struct dpu_intf_cfg sdm845_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_2", .id = INTF_2,
 		.base = 0x6b000, .len = 0x280,
@@ -278,7 +276,6 @@ static const struct dpu_intf_cfg sdm845_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_3", .id = INTF_3,
 		.base = 0x6b800, .len = 0x280,
@@ -287,7 +284,6 @@ static const struct dpu_intf_cfg sdm845_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h
index 99acaf917e..c022e57864 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h
@@ -77,7 +77,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = {
 		.name = "sspp_0", .id = SSPP_VIG0,
 		.base = 0x4000, .len = 0x1f0,
 		.features = VIG_SDM845_MASK,
-		.sblk = &sdm845_vig_sblk_0,
+		.sblk = &sm8150_vig_sblk_0,
 		.xin_id = 0,
 		.type = SSPP_TYPE_VIG,
 		.clk_ctrl = DPU_CLK_CTRL_VIG0,
@@ -85,7 +85,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = {
 		.name = "sspp_1", .id = SSPP_VIG1,
 		.base = 0x6000, .len = 0x1f0,
 		.features = VIG_SDM845_MASK,
-		.sblk = &sdm845_vig_sblk_1,
+		.sblk = &sm8150_vig_sblk_1,
 		.xin_id = 4,
 		.type = SSPP_TYPE_VIG,
 		.clk_ctrl = DPU_CLK_CTRL_VIG1,
@@ -93,7 +93,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = {
 		.name = "sspp_2", .id = SSPP_VIG2,
 		.base = 0x8000, .len = 0x1f0,
 		.features = VIG_SDM845_MASK,
-		.sblk = &sdm845_vig_sblk_2,
+		.sblk = &sm8150_vig_sblk_2,
 		.xin_id = 8,
 		.type = SSPP_TYPE_VIG,
 		.clk_ctrl = DPU_CLK_CTRL_VIG2,
@@ -101,7 +101,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = {
 		.name = "sspp_3", .id = SSPP_VIG3,
 		.base = 0xa000, .len = 0x1f0,
 		.features = VIG_SDM845_MASK,
-		.sblk = &sdm845_vig_sblk_3,
+		.sblk = &sm8150_vig_sblk_3,
 		.xin_id = 12,
 		.type = SSPP_TYPE_VIG,
 		.clk_ctrl = DPU_CLK_CTRL_VIG3,
@@ -220,7 +220,6 @@ static const struct dpu_pingpong_cfg sm8150_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_1", .id = PINGPONG_1,
 		.base = 0x70800, .len = 0xd4,
@@ -228,7 +227,6 @@ static const struct dpu_pingpong_cfg sm8150_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_2", .id = PINGPONG_2,
 		.base = 0x71000, .len = 0xd4,
@@ -236,7 +234,6 @@ static const struct dpu_pingpong_cfg sm8150_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_3", .id = PINGPONG_3,
 		.base = 0x71800, .len = 0xd4,
@@ -244,7 +241,6 @@ static const struct dpu_pingpong_cfg sm8150_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_4", .id = PINGPONG_4,
 		.base = 0x72000, .len = 0xd4,
@@ -252,7 +248,6 @@ static const struct dpu_pingpong_cfg sm8150_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_5", .id = PINGPONG_5,
 		.base = 0x72800, .len = 0xd4,
@@ -260,7 +255,6 @@ static const struct dpu_pingpong_cfg sm8150_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31),
-		.intr_rdptr = -1,
 	},
 };
 
@@ -307,7 +301,6 @@ static const struct dpu_intf_cfg sm8150_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x6a800, .len = 0x2bc,
@@ -337,7 +330,6 @@ static const struct dpu_intf_cfg sm8150_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h
index c92fbf24fb..cb0758f082 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h
@@ -76,7 +76,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = {
 		.name = "sspp_0", .id = SSPP_VIG0,
 		.base = 0x4000, .len = 0x1f0,
 		.features = VIG_SDM845_MASK,
-		.sblk = &sdm845_vig_sblk_0,
+		.sblk = &sm8150_vig_sblk_0,
 		.xin_id = 0,
 		.type = SSPP_TYPE_VIG,
 		.clk_ctrl = DPU_CLK_CTRL_VIG0,
@@ -84,7 +84,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = {
 		.name = "sspp_1", .id = SSPP_VIG1,
 		.base = 0x6000, .len = 0x1f0,
 		.features = VIG_SDM845_MASK,
-		.sblk = &sdm845_vig_sblk_1,
+		.sblk = &sm8150_vig_sblk_1,
 		.xin_id = 4,
 		.type = SSPP_TYPE_VIG,
 		.clk_ctrl = DPU_CLK_CTRL_VIG1,
@@ -92,7 +92,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = {
 		.name = "sspp_2", .id = SSPP_VIG2,
 		.base = 0x8000, .len = 0x1f0,
 		.features = VIG_SDM845_MASK,
-		.sblk = &sdm845_vig_sblk_2,
+		.sblk = &sm8150_vig_sblk_2,
 		.xin_id = 8,
 		.type = SSPP_TYPE_VIG,
 		.clk_ctrl = DPU_CLK_CTRL_VIG2,
@@ -100,7 +100,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = {
 		.name = "sspp_3", .id = SSPP_VIG3,
 		.base = 0xa000, .len = 0x1f0,
 		.features = VIG_SDM845_MASK,
-		.sblk = &sdm845_vig_sblk_3,
+		.sblk = &sm8150_vig_sblk_3,
 		.xin_id = 12,
 		.type = SSPP_TYPE_VIG,
 		.clk_ctrl = DPU_CLK_CTRL_VIG3,
@@ -219,7 +219,6 @@ static const struct dpu_pingpong_cfg sc8180x_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_1", .id = PINGPONG_1,
 		.base = 0x70800, .len = 0xd4,
@@ -227,7 +226,6 @@ static const struct dpu_pingpong_cfg sc8180x_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_2", .id = PINGPONG_2,
 		.base = 0x71000, .len = 0xd4,
@@ -235,7 +233,6 @@ static const struct dpu_pingpong_cfg sc8180x_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_3", .id = PINGPONG_3,
 		.base = 0x71800, .len = 0xd4,
@@ -243,7 +240,6 @@ static const struct dpu_pingpong_cfg sc8180x_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_4", .id = PINGPONG_4,
 		.base = 0x72000, .len = 0xd4,
@@ -251,7 +247,6 @@ static const struct dpu_pingpong_cfg sc8180x_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_5", .id = PINGPONG_5,
 		.base = 0x72800, .len = 0xd4,
@@ -259,7 +254,6 @@ static const struct dpu_pingpong_cfg sc8180x_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31),
-		.intr_rdptr = -1,
 	},
 };
 
@@ -314,7 +308,6 @@ static const struct dpu_intf_cfg sc8180x_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x6a800, .len = 0x2bc,
@@ -346,7 +339,6 @@ static const struct dpu_intf_cfg sc8180x_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_4", .id = INTF_4,
 		.base = 0x6c000, .len = 0x280,
@@ -356,7 +348,6 @@ static const struct dpu_intf_cfg sc8180x_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 20),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 21),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_5", .id = INTF_5,
 		.base = 0x6c800, .len = 0x280,
@@ -366,7 +357,6 @@ static const struct dpu_intf_cfg sc8180x_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 22),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 23),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h
index 2491eed100..cec7af6667 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h
@@ -129,7 +129,6 @@ static const struct dpu_pingpong_cfg sm6125_pp[] = {
 		.merge_3d = 0,
 		.sblk = &sdm845_pp_sblk,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_1", .id = PINGPONG_1,
 		.base = 0x70800, .len = 0xd4,
@@ -137,7 +136,6 @@ static const struct dpu_pingpong_cfg sm6125_pp[] = {
 		.merge_3d = 0,
 		.sblk = &sdm845_pp_sblk,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
-		.intr_rdptr = -1,
 	},
 };
 
@@ -151,7 +149,6 @@ static const struct dpu_intf_cfg sm6125_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x6a800, .len = 0x2c0,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h
index ee781037ad..9f8068fa01 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h
@@ -219,7 +219,6 @@ static const struct dpu_pingpong_cfg sm8250_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_1", .id = PINGPONG_1,
 		.base = 0x70800, .len = 0xd4,
@@ -227,7 +226,6 @@ static const struct dpu_pingpong_cfg sm8250_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_2", .id = PINGPONG_2,
 		.base = 0x71000, .len = 0xd4,
@@ -235,7 +233,6 @@ static const struct dpu_pingpong_cfg sm8250_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_3", .id = PINGPONG_3,
 		.base = 0x71800, .len = 0xd4,
@@ -243,7 +240,6 @@ static const struct dpu_pingpong_cfg sm8250_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_4", .id = PINGPONG_4,
 		.base = 0x72000, .len = 0xd4,
@@ -251,7 +247,6 @@ static const struct dpu_pingpong_cfg sm8250_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_5", .id = PINGPONG_5,
 		.base = 0x72800, .len = 0xd4,
@@ -259,7 +254,6 @@ static const struct dpu_pingpong_cfg sm8250_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31),
-		.intr_rdptr = -1,
 	},
 };
 
@@ -306,7 +300,6 @@ static const struct dpu_intf_cfg sm8250_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x6a800, .len = 0x2c0,
@@ -336,7 +329,6 @@ static const struct dpu_intf_cfg sm8250_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h
index 69d3f7e5e0..9bfa15e4e6 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h
@@ -120,7 +120,6 @@ static const struct dpu_pingpong_cfg sc7180_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = 0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_1", .id = PINGPONG_1,
 		.base = 0x70800, .len = 0xd4,
@@ -128,7 +127,6 @@ static const struct dpu_pingpong_cfg sc7180_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = 0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
-		.intr_rdptr = -1,
 	},
 };
 
@@ -142,7 +140,6 @@ static const struct dpu_intf_cfg sc7180_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x6a800, .len = 0x2c0,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h
index 7e6000167e..57ce14c18d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h
@@ -83,7 +83,6 @@ static const struct dpu_pingpong_cfg sm6115_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = 0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h
index cf5db6f296..62db84bd15 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h
@@ -128,7 +128,6 @@ static struct dpu_pingpong_cfg sm6350_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = 0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_1", .id = PINGPONG_1,
 		.base = 0x70800, .len = 0xd4,
@@ -136,7 +135,6 @@ static struct dpu_pingpong_cfg sm6350_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = 0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
-		.intr_rdptr = -1,
 	},
 };
 
@@ -158,7 +156,6 @@ static const struct dpu_intf_cfg sm6350_intf[] = {
 		.prog_fetch_lines_worst_case = 35,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x6a800, .len = 0x2c0,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h
index 87a03aa165..fb36fba517 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h
@@ -82,7 +82,6 @@ static const struct dpu_pingpong_cfg qcm2290_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = 0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_9_sm6375.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_9_sm6375.h
index a327e21c90..5a3aad364c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_9_sm6375.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_9_sm6375.h
@@ -85,7 +85,6 @@ static const struct dpu_pingpong_cfg sm6375_pp[] = {
 		.sblk = &sdm845_pp_sblk,
 		.merge_3d = 0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h
index f8d16f9bf5..022b0408c2 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h
@@ -31,6 +31,7 @@ static const struct dpu_mdp_cfg sm8350_mdp = {
 		[DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2b4, .bit_off = 8 },
 		[DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2bc, .bit_off = 8 },
 		[DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2c4, .bit_off = 8 },
+		[DPU_CLK_CTRL_WB2] = { .reg_off = 0x2bc, .bit_off = 16 },
 		[DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2bc, .bit_off = 20 },
 	},
 };
@@ -218,7 +219,6 @@ static const struct dpu_pingpong_cfg sm8350_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_1", .id = PINGPONG_1,
 		.base = 0x6a000, .len = 0,
@@ -226,7 +226,6 @@ static const struct dpu_pingpong_cfg sm8350_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_2", .id = PINGPONG_2,
 		.base = 0x6b000, .len = 0,
@@ -234,7 +233,6 @@ static const struct dpu_pingpong_cfg sm8350_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_3", .id = PINGPONG_3,
 		.base = 0x6c000, .len = 0,
@@ -242,7 +240,6 @@ static const struct dpu_pingpong_cfg sm8350_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_4", .id = PINGPONG_4,
 		.base = 0x6d000, .len = 0,
@@ -250,7 +247,6 @@ static const struct dpu_pingpong_cfg sm8350_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_5", .id = PINGPONG_5,
 		.base = 0x6e000, .len = 0,
@@ -258,7 +254,6 @@ static const struct dpu_pingpong_cfg sm8350_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31),
-		.intr_rdptr = -1,
 	},
 };
 
@@ -304,6 +299,21 @@ static const struct dpu_dsc_cfg sm8350_dsc[] = {
 	},
 };
 
+static const struct dpu_wb_cfg sm8350_wb[] = {
+	{
+		.name = "wb_2", .id = WB_2,
+		.base = 0x65000, .len = 0x2c8,
+		.features = WB_SM8250_MASK,
+		.format_list = wb2_formats,
+		.num_formats = ARRAY_SIZE(wb2_formats),
+		.clk_ctrl = DPU_CLK_CTRL_WB2,
+		.xin_id = 6,
+		.vbif_idx = VBIF_RT,
+		.maxlinewidth = 4096,
+		.intr_wb_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 4),
+	},
+};
+
 static const struct dpu_intf_cfg sm8350_intf[] = {
 	{
 		.name = "intf_0", .id = INTF_0,
@@ -314,7 +324,6 @@ static const struct dpu_intf_cfg sm8350_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x35000, .len = 0x2c4,
@@ -344,7 +353,6 @@ static const struct dpu_intf_cfg sm8350_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
@@ -401,6 +409,8 @@ const struct dpu_mdss_cfg dpu_sm8350_cfg = {
 	.dsc = sm8350_dsc,
 	.merge_3d_count = ARRAY_SIZE(sm8350_merge_3d),
 	.merge_3d = sm8350_merge_3d,
+	.wb_count = ARRAY_SIZE(sm8350_wb),
+	.wb = sm8350_wb,
 	.intf_count = ARRAY_SIZE(sm8350_intf),
 	.intf = sm8350_intf,
 	.vbif_count = ARRAY_SIZE(sdm845_vbif),
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h
index 9195cb996f..b9c296e51e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h
@@ -131,7 +131,6 @@ static const struct dpu_pingpong_cfg sc7280_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = 0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_1", .id = PINGPONG_1,
 		.base = 0x6a000, .len = 0,
@@ -139,7 +138,6 @@ static const struct dpu_pingpong_cfg sc7280_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = 0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_2", .id = PINGPONG_2,
 		.base = 0x6b000, .len = 0,
@@ -147,7 +145,6 @@ static const struct dpu_pingpong_cfg sc7280_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = 0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_3", .id = PINGPONG_3,
 		.base = 0x6c000, .len = 0,
@@ -155,7 +152,6 @@ static const struct dpu_pingpong_cfg sc7280_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = 0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11),
-		.intr_rdptr = -1,
 	},
 };
 
@@ -194,7 +190,6 @@ static const struct dpu_intf_cfg sc7280_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x35000, .len = 0x2c4,
@@ -214,7 +209,6 @@ static const struct dpu_intf_cfg sc7280_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 22),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 23),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
index ff9adb8000..4c0528794e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
@@ -221,7 +221,6 @@ static const struct dpu_pingpong_cfg sc8280xp_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_1", .id = PINGPONG_1,
 		.base = 0x6a000, .len = 0,
@@ -229,7 +228,6 @@ static const struct dpu_pingpong_cfg sc8280xp_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_2", .id = PINGPONG_2,
 		.base = 0x6b000, .len = 0,
@@ -237,7 +235,6 @@ static const struct dpu_pingpong_cfg sc8280xp_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_3", .id = PINGPONG_3,
 		.base = 0x6c000, .len = 0,
@@ -245,7 +242,6 @@ static const struct dpu_pingpong_cfg sc8280xp_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_4", .id = PINGPONG_4,
 		.base = 0x6d000, .len = 0,
@@ -253,7 +249,6 @@ static const struct dpu_pingpong_cfg sc8280xp_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_5", .id = PINGPONG_5,
 		.base = 0x6e000, .len = 0,
@@ -261,7 +256,6 @@ static const struct dpu_pingpong_cfg sc8280xp_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31),
-		.intr_rdptr = -1,
 	},
 };
 
@@ -328,7 +322,6 @@ static const struct dpu_intf_cfg sc8280xp_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x35000, .len = 0x300,
@@ -358,7 +351,6 @@ static const struct dpu_intf_cfg sc8280xp_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_4", .id = INTF_4,
 		.base = 0x38000, .len = 0x280,
@@ -368,7 +360,6 @@ static const struct dpu_intf_cfg sc8280xp_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 20),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 21),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_5", .id = INTF_5,
 		.base = 0x39000, .len = 0x280,
@@ -378,7 +369,6 @@ static const struct dpu_intf_cfg sc8280xp_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 22),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 23),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_6", .id = INTF_6,
 		.base = 0x3a000, .len = 0x280,
@@ -388,7 +378,6 @@ static const struct dpu_intf_cfg sc8280xp_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_7", .id = INTF_7,
 		.base = 0x3b000, .len = 0x280,
@@ -398,7 +387,6 @@ static const struct dpu_intf_cfg sc8280xp_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 18),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 19),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_8", .id = INTF_8,
 		.base = 0x3c000, .len = 0x280,
@@ -408,7 +396,6 @@ static const struct dpu_intf_cfg sc8280xp_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h
index 1b12178dfb..7adc42257e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h
@@ -32,6 +32,7 @@ static const struct dpu_mdp_cfg sm8450_mdp = {
 		[DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2b4, .bit_off = 8 },
 		[DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2bc, .bit_off = 8 },
 		[DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2c4, .bit_off = 8 },
+		[DPU_CLK_CTRL_WB2] = { .reg_off = 0x2bc, .bit_off = 16 },
 		[DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2bc, .bit_off = 20 },
 	},
 };
@@ -75,39 +76,39 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = {
 	{
 		.name = "sspp_0", .id = SSPP_VIG0,
 		.base = 0x4000, .len = 0x32c,
-		.features = VIG_SC7180_MASK,
-		.sblk = &sm8250_vig_sblk_0,
+		.features = VIG_SC7180_MASK_SDMA,
+		.sblk = &sm8450_vig_sblk_0,
 		.xin_id = 0,
 		.type = SSPP_TYPE_VIG,
 		.clk_ctrl = DPU_CLK_CTRL_VIG0,
 	}, {
 		.name = "sspp_1", .id = SSPP_VIG1,
 		.base = 0x6000, .len = 0x32c,
-		.features = VIG_SC7180_MASK,
-		.sblk = &sm8250_vig_sblk_1,
+		.features = VIG_SC7180_MASK_SDMA,
+		.sblk = &sm8450_vig_sblk_1,
 		.xin_id = 4,
 		.type = SSPP_TYPE_VIG,
 		.clk_ctrl = DPU_CLK_CTRL_VIG1,
 	}, {
 		.name = "sspp_2", .id = SSPP_VIG2,
 		.base = 0x8000, .len = 0x32c,
-		.features = VIG_SC7180_MASK,
-		.sblk = &sm8250_vig_sblk_2,
+		.features = VIG_SC7180_MASK_SDMA,
+		.sblk = &sm8450_vig_sblk_2,
 		.xin_id = 8,
 		.type = SSPP_TYPE_VIG,
 		.clk_ctrl = DPU_CLK_CTRL_VIG2,
 	}, {
 		.name = "sspp_3", .id = SSPP_VIG3,
 		.base = 0xa000, .len = 0x32c,
-		.features = VIG_SC7180_MASK,
-		.sblk = &sm8250_vig_sblk_3,
+		.features = VIG_SC7180_MASK_SDMA,
+		.sblk = &sm8450_vig_sblk_3,
 		.xin_id = 12,
 		.type = SSPP_TYPE_VIG,
 		.clk_ctrl = DPU_CLK_CTRL_VIG3,
 	}, {
 		.name = "sspp_8", .id = SSPP_DMA0,
 		.base = 0x24000, .len = 0x32c,
-		.features = DMA_SDM845_MASK,
+		.features = DMA_SDM845_MASK_SDMA,
 		.sblk = &sdm845_dma_sblk_0,
 		.xin_id = 1,
 		.type = SSPP_TYPE_DMA,
@@ -115,7 +116,7 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = {
 	}, {
 		.name = "sspp_9", .id = SSPP_DMA1,
 		.base = 0x26000, .len = 0x32c,
-		.features = DMA_SDM845_MASK,
+		.features = DMA_SDM845_MASK_SDMA,
 		.sblk = &sdm845_dma_sblk_1,
 		.xin_id = 5,
 		.type = SSPP_TYPE_DMA,
@@ -123,7 +124,7 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = {
 	}, {
 		.name = "sspp_10", .id = SSPP_DMA2,
 		.base = 0x28000, .len = 0x32c,
-		.features = DMA_CURSOR_SDM845_MASK,
+		.features = DMA_CURSOR_SDM845_MASK_SDMA,
 		.sblk = &sdm845_dma_sblk_2,
 		.xin_id = 9,
 		.type = SSPP_TYPE_DMA,
@@ -131,7 +132,7 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = {
 	}, {
 		.name = "sspp_11", .id = SSPP_DMA3,
 		.base = 0x2a000, .len = 0x32c,
-		.features = DMA_CURSOR_SDM845_MASK,
+		.features = DMA_CURSOR_SDM845_MASK_SDMA,
 		.sblk = &sdm845_dma_sblk_3,
 		.xin_id = 13,
 		.type = SSPP_TYPE_DMA,
@@ -221,7 +222,6 @@ static const struct dpu_pingpong_cfg sm8450_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_1", .id = PINGPONG_1,
 		.base = 0x6a000, .len = 0,
@@ -229,7 +229,6 @@ static const struct dpu_pingpong_cfg sm8450_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_2", .id = PINGPONG_2,
 		.base = 0x6b000, .len = 0,
@@ -237,7 +236,6 @@ static const struct dpu_pingpong_cfg sm8450_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_3", .id = PINGPONG_3,
 		.base = 0x6c000, .len = 0,
@@ -245,7 +243,6 @@ static const struct dpu_pingpong_cfg sm8450_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_4", .id = PINGPONG_4,
 		.base = 0x6d000, .len = 0,
@@ -253,7 +250,6 @@ static const struct dpu_pingpong_cfg sm8450_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_5", .id = PINGPONG_5,
 		.base = 0x6e000, .len = 0,
@@ -261,23 +257,18 @@ static const struct dpu_pingpong_cfg sm8450_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_6", .id = PINGPONG_6,
 		.base = 0x65800, .len = 0,
 		.features = BIT(DPU_PINGPONG_DITHER),
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_3,
-		.intr_done = -1,
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_7", .id = PINGPONG_7,
 		.base = 0x65c00, .len = 0,
 		.features = BIT(DPU_PINGPONG_DITHER),
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_3,
-		.intr_done = -1,
-		.intr_rdptr = -1,
 	},
 };
 
@@ -326,6 +317,21 @@ static const struct dpu_dsc_cfg sm8450_dsc[] = {
 	},
 };
 
+static const struct dpu_wb_cfg sm8450_wb[] = {
+	{
+		.name = "wb_2", .id = WB_2,
+		.base = 0x65000, .len = 0x2c8,
+		.features = WB_SM8250_MASK,
+		.format_list = wb2_formats,
+		.num_formats = ARRAY_SIZE(wb2_formats),
+		.clk_ctrl = DPU_CLK_CTRL_WB2,
+		.xin_id = 6,
+		.vbif_idx = VBIF_RT,
+		.maxlinewidth = 4096,
+		.intr_wb_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 4),
+	},
+};
+
 static const struct dpu_intf_cfg sm8450_intf[] = {
 	{
 		.name = "intf_0", .id = INTF_0,
@@ -336,7 +342,6 @@ static const struct dpu_intf_cfg sm8450_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x35000, .len = 0x300,
@@ -366,7 +371,6 @@ static const struct dpu_intf_cfg sm8450_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
@@ -423,6 +427,8 @@ const struct dpu_mdss_cfg dpu_sm8450_cfg = {
 	.dsc = sm8450_dsc,
 	.merge_3d_count = ARRAY_SIZE(sm8450_merge_3d),
 	.merge_3d = sm8450_merge_3d,
+	.wb_count = ARRAY_SIZE(sm8450_wb),
+	.wb = sm8450_wb,
 	.intf_count = ARRAY_SIZE(sm8450_intf),
 	.intf = sm8450_intf,
 	.vbif_count = ARRAY_SIZE(sdm845_vbif),
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h
index 7bed819dfc..69b80af656 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h
@@ -24,16 +24,6 @@ static const struct dpu_mdp_cfg sm8550_mdp = {
 	.base = 0, .len = 0x494,
 	.features = BIT(DPU_MDP_PERIPH_0_REMOVED),
 	.clk_ctrls = {
-		[DPU_CLK_CTRL_VIG0] = { .reg_off = 0x4330, .bit_off = 0 },
-		[DPU_CLK_CTRL_VIG1] = { .reg_off = 0x6330, .bit_off = 0 },
-		[DPU_CLK_CTRL_VIG2] = { .reg_off = 0x8330, .bit_off = 0 },
-		[DPU_CLK_CTRL_VIG3] = { .reg_off = 0xa330, .bit_off = 0 },
-		[DPU_CLK_CTRL_DMA0] = { .reg_off = 0x24330, .bit_off = 0 },
-		[DPU_CLK_CTRL_DMA1] = { .reg_off = 0x26330, .bit_off = 0 },
-		[DPU_CLK_CTRL_DMA2] = { .reg_off = 0x28330, .bit_off = 0 },
-		[DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2a330, .bit_off = 0 },
-		[DPU_CLK_CTRL_DMA4] = { .reg_off = 0x2c330, .bit_off = 0 },
-		[DPU_CLK_CTRL_DMA5] = { .reg_off = 0x2e330, .bit_off = 0 },
 		[DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2bc, .bit_off = 20 },
 	},
 };
@@ -81,7 +71,6 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = {
 		.sblk = &sm8550_vig_sblk_0,
 		.xin_id = 0,
 		.type = SSPP_TYPE_VIG,
-		.clk_ctrl = DPU_CLK_CTRL_VIG0,
 	}, {
 		.name = "sspp_1", .id = SSPP_VIG1,
 		.base = 0x6000, .len = 0x344,
@@ -89,7 +78,6 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = {
 		.sblk = &sm8550_vig_sblk_1,
 		.xin_id = 4,
 		.type = SSPP_TYPE_VIG,
-		.clk_ctrl = DPU_CLK_CTRL_VIG1,
 	}, {
 		.name = "sspp_2", .id = SSPP_VIG2,
 		.base = 0x8000, .len = 0x344,
@@ -97,7 +85,6 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = {
 		.sblk = &sm8550_vig_sblk_2,
 		.xin_id = 8,
 		.type = SSPP_TYPE_VIG,
-		.clk_ctrl = DPU_CLK_CTRL_VIG2,
 	}, {
 		.name = "sspp_3", .id = SSPP_VIG3,
 		.base = 0xa000, .len = 0x344,
@@ -105,7 +92,6 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = {
 		.sblk = &sm8550_vig_sblk_3,
 		.xin_id = 12,
 		.type = SSPP_TYPE_VIG,
-		.clk_ctrl = DPU_CLK_CTRL_VIG3,
 	}, {
 		.name = "sspp_8", .id = SSPP_DMA0,
 		.base = 0x24000, .len = 0x344,
@@ -113,7 +99,6 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = {
 		.sblk = &sdm845_dma_sblk_0,
 		.xin_id = 1,
 		.type = SSPP_TYPE_DMA,
-		.clk_ctrl = DPU_CLK_CTRL_DMA0,
 	}, {
 		.name = "sspp_9", .id = SSPP_DMA1,
 		.base = 0x26000, .len = 0x344,
@@ -121,7 +106,6 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = {
 		.sblk = &sdm845_dma_sblk_1,
 		.xin_id = 5,
 		.type = SSPP_TYPE_DMA,
-		.clk_ctrl = DPU_CLK_CTRL_DMA1,
 	}, {
 		.name = "sspp_10", .id = SSPP_DMA2,
 		.base = 0x28000, .len = 0x344,
@@ -129,7 +113,6 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = {
 		.sblk = &sdm845_dma_sblk_2,
 		.xin_id = 9,
 		.type = SSPP_TYPE_DMA,
-		.clk_ctrl = DPU_CLK_CTRL_DMA2,
 	}, {
 		.name = "sspp_11", .id = SSPP_DMA3,
 		.base = 0x2a000, .len = 0x344,
@@ -137,7 +120,6 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = {
 		.sblk = &sdm845_dma_sblk_3,
 		.xin_id = 13,
 		.type = SSPP_TYPE_DMA,
-		.clk_ctrl = DPU_CLK_CTRL_DMA3,
 	}, {
 		.name = "sspp_12", .id = SSPP_DMA4,
 		.base = 0x2c000, .len = 0x344,
@@ -145,7 +127,6 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = {
 		.sblk = &sm8550_dma_sblk_4,
 		.xin_id = 14,
 		.type = SSPP_TYPE_DMA,
-		.clk_ctrl = DPU_CLK_CTRL_DMA4,
 	}, {
 		.name = "sspp_13", .id = SSPP_DMA5,
 		.base = 0x2e000, .len = 0x344,
@@ -153,7 +134,6 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = {
 		.sblk = &sm8550_dma_sblk_5,
 		.xin_id = 15,
 		.type = SSPP_TYPE_DMA,
-		.clk_ctrl = DPU_CLK_CTRL_DMA5,
 	},
 };
 
@@ -236,7 +216,6 @@ static const struct dpu_pingpong_cfg sm8550_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_1", .id = PINGPONG_1,
 		.base = 0x6a000, .len = 0,
@@ -244,7 +223,6 @@ static const struct dpu_pingpong_cfg sm8550_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_0,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_2", .id = PINGPONG_2,
 		.base = 0x6b000, .len = 0,
@@ -252,7 +230,6 @@ static const struct dpu_pingpong_cfg sm8550_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_3", .id = PINGPONG_3,
 		.base = 0x6c000, .len = 0,
@@ -260,7 +237,6 @@ static const struct dpu_pingpong_cfg sm8550_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_1,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_4", .id = PINGPONG_4,
 		.base = 0x6d000, .len = 0,
@@ -268,7 +244,6 @@ static const struct dpu_pingpong_cfg sm8550_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_5", .id = PINGPONG_5,
 		.base = 0x6e000, .len = 0,
@@ -276,23 +251,18 @@ static const struct dpu_pingpong_cfg sm8550_pp[] = {
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_2,
 		.intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31),
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_6", .id = PINGPONG_6,
 		.base = 0x66000, .len = 0,
 		.features = BIT(DPU_PINGPONG_DITHER),
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_3,
-		.intr_done = -1,
-		.intr_rdptr = -1,
 	}, {
 		.name = "pingpong_7", .id = PINGPONG_7,
 		.base = 0x66400, .len = 0,
 		.features = BIT(DPU_PINGPONG_DITHER),
 		.sblk = &sc7280_pp_sblk,
 		.merge_3d = MERGE_3D_3,
-		.intr_done = -1,
-		.intr_rdptr = -1,
 	},
 };
 
@@ -341,6 +311,20 @@ static const struct dpu_dsc_cfg sm8550_dsc[] = {
 	},
 };
 
+static const struct dpu_wb_cfg sm8550_wb[] = {
+	{
+		.name = "wb_2", .id = WB_2,
+		.base = 0x65000, .len = 0x2c8,
+		.features = WB_SM8250_MASK,
+		.format_list = wb2_formats,
+		.num_formats = ARRAY_SIZE(wb2_formats),
+		.xin_id = 6,
+		.vbif_idx = VBIF_RT,
+		.maxlinewidth = 4096,
+		.intr_wb_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 4),
+	},
+};
+
 static const struct dpu_intf_cfg sm8550_intf[] = {
 	{
 		.name = "intf_0", .id = INTF_0,
@@ -351,7 +335,6 @@ static const struct dpu_intf_cfg sm8550_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x35000, .len = 0x300,
@@ -381,7 +364,6 @@ static const struct dpu_intf_cfg sm8550_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
@@ -438,6 +420,8 @@ const struct dpu_mdss_cfg dpu_sm8550_cfg = {
 	.dsc = sm8550_dsc,
 	.merge_3d_count = ARRAY_SIZE(sm8550_merge_3d),
 	.merge_3d = sm8550_merge_3d,
+	.wb_count = ARRAY_SIZE(sm8550_wb),
+	.wb = sm8550_wb,
 	.intf_count = ARRAY_SIZE(sm8550_intf),
 	.intf = sm8550_intf,
 	.vbif_count = ARRAY_SIZE(sm8550_vbif),
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
index b5b6e7031f..7c286bafb9 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
@@ -37,7 +37,7 @@ irqreturn_t dpu_core_irq(struct msm_kms *kms);
  */
 u32 dpu_core_irq_read(
 		struct dpu_kms *dpu_kms,
-		int irq_idx);
+		unsigned int irq_idx);
 
 /**
  * dpu_core_irq_register_callback - For registering callback function on IRQ
@@ -52,8 +52,8 @@ u32 dpu_core_irq_read(
  */
 int dpu_core_irq_register_callback(
 		struct dpu_kms *dpu_kms,
-		int irq_idx,
-		void (*irq_cb)(void *arg, int irq_idx),
+		unsigned int irq_idx,
+		void (*irq_cb)(void *arg),
 		void *irq_arg);
 
 /**
@@ -67,7 +67,7 @@ int dpu_core_irq_register_callback(
  */
 int dpu_core_irq_unregister_callback(
 		struct dpu_kms *dpu_kms,
-		int irq_idx);
+		unsigned int irq_idx);
 
 /**
  * dpu_debugfs_core_irq_init - register core irq debugfs
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index e238e4e811..db501ce1d8 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -1466,7 +1466,7 @@ struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane,
 	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;
+	struct dpu_crtc *dpu_crtc;
 	int i, ret;
 
 	dpu_crtc = kzalloc(sizeof(*dpu_crtc), GFP_KERNEL);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index b02aa2eb6c..cf0d44b6e7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -39,6 +39,9 @@
 #define DPU_ERROR_ENC(e, fmt, ...) DPU_ERROR("enc%d " fmt,\
 		(e) ? (e)->base.base.id : -1, ##__VA_ARGS__)
 
+#define DPU_ERROR_ENC_RATELIMITED(e, fmt, ...) DPU_ERROR_RATELIMITED("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
@@ -347,8 +350,8 @@ 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),
+		unsigned int irq_idx,
+		void (*func)(void *arg),
 		struct dpu_encoder_wait_info *wait_info)
 {
 	u32 irq_status;
@@ -362,54 +365,54 @@ int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
 
 	/* 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",
+		DRM_ERROR("encoder is disabled id=%u, callback=%ps, IRQ=[%d, %d]\n",
 			  DRMID(phys_enc->parent), func,
-			  irq);
+			  DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 		return -EWOULDBLOCK;
 	}
 
-	if (irq < 0) {
+	if (irq_idx < 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",
+	DRM_DEBUG_KMS("id=%u, callback=%ps, IRQ=[%d, %d], pp=%d, pending_cnt=%d\n",
 		      DRMID(phys_enc->parent), func,
-		      irq, phys_enc->hw_pp->idx - PINGPONG_0,
+		      DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), 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,
+			irq_idx,
 			wait_info);
 
 	if (ret <= 0) {
-		irq_status = dpu_core_irq_read(phys_enc->dpu_kms, irq);
+		irq_status = dpu_core_irq_read(phys_enc->dpu_kms, irq_idx);
 		if (irq_status) {
 			unsigned long flags;
 
-			DRM_DEBUG_KMS("irq not triggered id=%u, callback=%ps, irq=%d, pp=%d, atomic_cnt=%d\n",
+			DRM_DEBUG_KMS("IRQ=[%d, %d] not triggered id=%u, callback=%ps, pp=%d, atomic_cnt=%d\n",
+				      DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx),
 				      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);
+			func(phys_enc);
 			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",
+			DRM_DEBUG_KMS("IRQ=[%d, %d] timeout id=%u, callback=%ps, pp=%d, atomic_cnt=%d\n",
+				      DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx),
 				      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,
+			func, DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx),
 			phys_enc->hw_pp->idx - PINGPONG_0,
 			atomic_read(wait_info->atomic_cnt));
 	}
@@ -1194,11 +1197,21 @@ static void dpu_encoder_virt_atomic_enable(struct drm_encoder *drm_enc,
 	struct dpu_encoder_virt *dpu_enc = NULL;
 	int ret = 0;
 	struct drm_display_mode *cur_mode = NULL;
+	struct msm_drm_private *priv = drm_enc->dev->dev_private;
+	struct msm_display_info *disp_info;
+	int index;
 
 	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	disp_info = &dpu_enc->disp_info;
+	index = disp_info->h_tile_instance[0];
 
 	dpu_enc->dsc = dpu_encoder_get_dsc_config(drm_enc);
 
+	if (disp_info->intf_type == INTF_DP)
+		dpu_enc->wide_bus_en = msm_dp_wide_bus_available(priv->dp[index]);
+	else if (disp_info->intf_type == INTF_DSI)
+		dpu_enc->wide_bus_en = msm_dsi_wide_bus_enabled(priv->dsi[index]);
+
 	mutex_lock(&dpu_enc->enc_lock);
 	cur_mode = &dpu_enc->base.crtc->state->adjusted_mode;
 
@@ -1537,7 +1550,7 @@ void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc)
 
 static int dpu_encoder_helper_wait_event_timeout(
 		int32_t drm_id,
-		u32 irq_idx,
+		unsigned int irq_idx,
 		struct dpu_encoder_wait_info *info)
 {
 	int rc = 0;
@@ -1550,7 +1563,9 @@ static int dpu_encoder_helper_wait_event_timeout(
 				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,
+		trace_dpu_enc_wait_event_timeout(drm_id,
+						 DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx),
+						 rc, time,
 						 expected_time,
 						 atomic_read(info->atomic_cnt));
 	/* If we timed out, counter is valid and time is less, wait again */
@@ -2060,7 +2075,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	}
 
 	/* reset the merge 3D HW block */
-	if (phys_enc->hw_pp->merge_3d) {
+	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) {
 		phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
 				BLEND_3D_NONE);
 		if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d)
@@ -2082,7 +2097,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	if (phys_enc->hw_wb)
 		intf_cfg.wb = phys_enc->hw_wb->idx;
 
-	if (phys_enc->hw_pp->merge_3d)
+	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d)
 		intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
 
 	if (ctl->ops.reset_intf_cfg)
@@ -2327,7 +2342,7 @@ static void dpu_encoder_frame_done_timeout(struct timer_list *t)
 		return;
 	}
 
-	DPU_ERROR_ENC(dpu_enc, "frame done timeout\n");
+	DPU_ERROR_ENC_RATELIMITED(dpu_enc, "frame done timeout\n");
 
 	event = DPU_ENCODER_FRAME_EVENT_ERROR;
 	trace_dpu_enc_frame_done_timeout(DRMID(drm_enc), event);
@@ -2383,10 +2398,6 @@ struct drm_encoder *dpu_encoder_init(struct drm_device *dev,
 	timer_setup(&dpu_enc->frame_done_timer,
 			dpu_encoder_frame_done_timeout, 0);
 
-	if (disp_info->intf_type == INTF_DP)
-		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;
@@ -2480,8 +2491,6 @@ unsigned int dpu_encoder_helper_get_dsc(struct dpu_encoder_phys *phys_enc)
 void dpu_encoder_phys_init(struct dpu_encoder_phys *phys_enc,
 			  struct dpu_enc_phys_init_params *p)
 {
-	int i;
-
 	phys_enc->hw_mdptop = p->dpu_kms->hw_mdp;
 	phys_enc->hw_intf = p->hw_intf;
 	phys_enc->hw_wb = p->hw_wb;
@@ -2491,10 +2500,6 @@ void dpu_encoder_phys_init(struct dpu_encoder_phys *phys_enc,
 	phys_enc->enc_spinlock = p->enc_spinlock;
 	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);
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
index d48558ede4..96bda57b69 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
@@ -155,6 +155,7 @@ enum dpu_intr_idx {
  * @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
+ * @vblank_ctl_lock:	Vblank ctl mutex lock to protect vblank_refcount
  * @enabled:		Whether the encoder has enabled and running a mode
  * @split_role:		Role to play in a split-panel configuration
  * @intf_mode:		Interface mode
@@ -183,17 +184,18 @@ struct dpu_encoder_phys {
 	struct dpu_hw_wb *hw_wb;
 	struct dpu_kms *dpu_kms;
 	struct drm_display_mode cached_mode;
+	struct mutex vblank_ctl_lock;
 	enum dpu_enc_split_role split_role;
 	enum dpu_intf_mode intf_mode;
 	spinlock_t *enc_spinlock;
 	enum dpu_enc_enable_state enable_state;
-	atomic_t vblank_refcount;
+	int 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];
+	unsigned int irq[INTR_IDX_MAX];
 	bool has_intf_te;
 };
 
@@ -364,8 +366,8 @@ void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc,
  * @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),
+		unsigned int irq,
+		void (*func)(void *arg),
 		struct dpu_encoder_wait_info *wait_info);
 
 /**
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
index df88358e70..2d788c5e26 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -72,11 +72,13 @@ static void _dpu_encoder_phys_cmd_update_intf_cfg(
 	if (intf_cfg.dsc != 0)
 		cmd_mode_cfg.data_compress = true;
 
+	cmd_mode_cfg.wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent);
+
 	if (phys_enc->hw_intf->ops.program_intf_cmd_cfg)
 		phys_enc->hw_intf->ops.program_intf_cmd_cfg(phys_enc->hw_intf, &cmd_mode_cfg);
 }
 
-static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg, int irq_idx)
+static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 	unsigned long lock_flags;
@@ -103,19 +105,11 @@ static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg, int irq_idx)
 	DPU_ATRACE_END("pp_done_irq");
 }
 
-static void dpu_encoder_phys_cmd_te_rd_ptr_irq(void *arg, int irq_idx)
+static void dpu_encoder_phys_cmd_te_rd_ptr_irq(void *arg)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 	struct dpu_encoder_phys_cmd *cmd_enc;
 
-	if (phys_enc->has_intf_te) {
-		if (!phys_enc->hw_intf)
-			return;
-	} else {
-		if (!phys_enc->hw_pp)
-			return;
-	}
-
 	DPU_ATRACE_BEGIN("rd_ptr_irq");
 	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
 
@@ -126,7 +120,7 @@ static void dpu_encoder_phys_cmd_te_rd_ptr_irq(void *arg, int irq_idx)
 	DPU_ATRACE_END("rd_ptr_irq");
 }
 
-static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg, int irq_idx)
+static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 
@@ -139,7 +133,7 @@ static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg, int irq_idx)
 	DPU_ATRACE_END("ctl_start_irq");
 }
 
-static void dpu_encoder_phys_cmd_underrun_irq(void *arg, int irq_idx)
+static void dpu_encoder_phys_cmd_underrun_irq(void *arg)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 
@@ -250,7 +244,8 @@ static int dpu_encoder_phys_cmd_control_vblank_irq(
 		return -EINVAL;
 	}
 
-	refcount = atomic_read(&phys_enc->vblank_refcount);
+	mutex_lock(&phys_enc->vblank_ctl_lock);
+	refcount = phys_enc->vblank_refcount;
 
 	/* Slave encoders don't report vblank */
 	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
@@ -266,16 +261,24 @@ static int dpu_encoder_phys_cmd_control_vblank_irq(
 		      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_te_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]);
+	if (enable) {
+		if (phys_enc->vblank_refcount == 0)
+			ret = dpu_core_irq_register_callback(phys_enc->dpu_kms,
+					phys_enc->irq[INTR_IDX_RDPTR],
+					dpu_encoder_phys_cmd_te_rd_ptr_irq,
+					phys_enc);
+		if (!ret)
+			phys_enc->vblank_refcount++;
+	} else if (!enable) {
+		if (phys_enc->vblank_refcount == 1)
+			ret = dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+					phys_enc->irq[INTR_IDX_RDPTR]);
+		if (!ret)
+			phys_enc->vblank_refcount--;
+	}
 
 end:
+	mutex_unlock(&phys_enc->vblank_ctl_lock);
 	if (ret) {
 		DRM_ERROR("vblank irq err id:%u pp:%d ret:%d, enable %s/%d\n",
 			  DRMID(phys_enc->parent),
@@ -291,7 +294,7 @@ static void dpu_encoder_phys_cmd_irq_control(struct dpu_encoder_phys *phys_enc,
 {
 	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));
+			enable, phys_enc->vblank_refcount);
 
 	if (enable) {
 		dpu_core_irq_register_callback(phys_enc->dpu_kms,
@@ -333,24 +336,21 @@ static void dpu_encoder_phys_cmd_tearcheck_config(
 	unsigned long vsync_hz;
 	struct dpu_kms *dpu_kms;
 
-	if (phys_enc->has_intf_te) {
-		if (!phys_enc->hw_intf ||
-		    !phys_enc->hw_intf->ops.enable_tearcheck) {
-			DPU_DEBUG_CMDENC(cmd_enc, "tearcheck not supported\n");
-			return;
-		}
-
-		DPU_DEBUG_CMDENC(cmd_enc, "");
-	} else {
-		if (!phys_enc->hw_pp ||
-		    !phys_enc->hw_pp->ops.enable_tearcheck) {
-			DPU_DEBUG_CMDENC(cmd_enc, "tearcheck not supported\n");
-			return;
-		}
-
-		DPU_DEBUG_CMDENC(cmd_enc, "pp %d\n", phys_enc->hw_pp->idx - PINGPONG_0);
+	/*
+	 * TODO: if/when resource allocation is refactored, move this to a
+	 * place where the driver can actually return an error.
+	 */
+	if (!phys_enc->has_intf_te &&
+	    (!phys_enc->hw_pp ||
+	     !phys_enc->hw_pp->ops.enable_tearcheck)) {
+		DPU_DEBUG_CMDENC(cmd_enc, "tearcheck not supported\n");
+		return;
 	}
 
+	DPU_DEBUG_CMDENC(cmd_enc, "intf %d pp %d\n",
+			 phys_enc->hw_intf ? phys_enc->hw_intf->idx - INTF_0 : -1,
+			 phys_enc->hw_pp ? phys_enc->hw_pp->idx - PINGPONG_0 : -1);
+
 	mode = &phys_enc->cached_mode;
 
 	dpu_kms = phys_enc->dpu_kms;
@@ -772,12 +772,26 @@ struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
 
 	dpu_encoder_phys_init(phys_enc, p);
 
+	mutex_init(&phys_enc->vblank_ctl_lock);
+	phys_enc->vblank_refcount = 0;
+
 	dpu_encoder_phys_cmd_init_ops(&phys_enc->ops);
 	phys_enc->intf_mode = INTF_MODE_CMD;
 	cmd_enc->stream_sel = 0;
 
-	phys_enc->has_intf_te = test_bit(DPU_INTF_TE,
-					 &phys_enc->hw_intf->cap->features);
+	if (!phys_enc->hw_intf) {
+		DPU_ERROR_CMDENC(cmd_enc, "no INTF provided\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* DPU before 5.0 use PINGPONG for TE handling */
+	if (phys_enc->dpu_kms->catalog->mdss_ver->core_major_ver >= 5)
+		phys_enc->has_intf_te = true;
+
+	if (phys_enc->has_intf_te && !phys_enc->hw_intf->ops.enable_tearcheck) {
+		DPU_ERROR_CMDENC(cmd_enc, "tearcheck not supported\n");
+		return ERR_PTR(-EINVAL);
+	}
 
 	atomic_set(&cmd_enc->pending_vblank_cnt, 0);
 	init_waitqueue_head(&cmd_enc->pending_vblank_wq);
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
index c2189e58de..eeb0acf966 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -297,7 +297,7 @@ static void dpu_encoder_phys_vid_setup_timing_engine(
 	programmable_fetch_config(phys_enc, &timing_params);
 }
 
-static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx)
+static void dpu_encoder_phys_vid_vblank_irq(void *arg)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 	struct dpu_hw_ctl *hw_ctl;
@@ -334,7 +334,7 @@ static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx)
 	DPU_ATRACE_END("vblank_irq");
 }
 
-static void dpu_encoder_phys_vid_underrun_irq(void *arg, int irq_idx)
+static void dpu_encoder_phys_vid_underrun_irq(void *arg)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 
@@ -364,7 +364,8 @@ static int dpu_encoder_phys_vid_control_vblank_irq(
 	int ret = 0;
 	int refcount;
 
-	refcount = atomic_read(&phys_enc->vblank_refcount);
+	mutex_lock(&phys_enc->vblank_ctl_lock);
+	refcount = phys_enc->vblank_refcount;
 
 	/* Slave encoders don't report vblank */
 	if (!dpu_encoder_phys_vid_is_master(phys_enc))
@@ -377,18 +378,26 @@ static int dpu_encoder_phys_vid_control_vblank_irq(
 	}
 
 	DRM_DEBUG_VBL("id:%u enable=%d/%d\n", DRMID(phys_enc->parent), enable,
-		      atomic_read(&phys_enc->vblank_refcount));
+		      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]);
+	if (enable) {
+		if (phys_enc->vblank_refcount == 0)
+			ret = dpu_core_irq_register_callback(phys_enc->dpu_kms,
+					phys_enc->irq[INTR_IDX_VSYNC],
+					dpu_encoder_phys_vid_vblank_irq,
+					phys_enc);
+		if (!ret)
+			phys_enc->vblank_refcount++;
+	} else if (!enable) {
+		if (phys_enc->vblank_refcount == 1)
+			ret = dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+					phys_enc->irq[INTR_IDX_VSYNC]);
+		if (!ret)
+			phys_enc->vblank_refcount--;
+	}
 
 end:
+	mutex_unlock(&phys_enc->vblank_ctl_lock);
 	if (ret) {
 		DRM_ERROR("failed: id:%u intf:%d ret:%d enable:%d refcnt:%d\n",
 			  DRMID(phys_enc->parent),
@@ -618,7 +627,7 @@ static void dpu_encoder_phys_vid_irq_control(struct dpu_encoder_phys *phys_enc,
 	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));
+			   phys_enc->vblank_refcount);
 
 	if (enable) {
 		ret = dpu_encoder_phys_vid_control_vblank_irq(phys_enc, true);
@@ -713,6 +722,8 @@ struct dpu_encoder_phys *dpu_encoder_phys_vid_init(
 	DPU_DEBUG_VIDENC(phys_enc, "\n");
 
 	dpu_encoder_phys_init(phys_enc, p);
+	mutex_init(&phys_enc->vblank_ctl_lock);
+	phys_enc->vblank_refcount = 0;
 
 	dpu_encoder_phys_vid_init_ops(&phys_enc->ops);
 	phys_enc->intf_mode = INTF_MODE_VIDEO;
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
index 78037a6976..0b6a761d68 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
@@ -34,6 +34,23 @@ static bool dpu_encoder_phys_wb_is_master(struct dpu_encoder_phys *phys_enc)
 	return true;
 }
 
+static bool _dpu_encoder_phys_wb_clk_force_ctrl(struct dpu_hw_wb *wb,
+						struct dpu_hw_mdp *mdp,
+						bool enable, bool *forced_on)
+{
+	if (wb->ops.setup_clk_force_ctrl) {
+		*forced_on = wb->ops.setup_clk_force_ctrl(wb, enable);
+		return true;
+	}
+
+	if (mdp->ops.setup_clk_force_ctrl) {
+		*forced_on = mdp->ops.setup_clk_force_ctrl(mdp, wb->caps->clk_ctrl, enable);
+		return true;
+	}
+
+	return false;
+}
+
 /**
  * dpu_encoder_phys_wb_set_ot_limit - set OT limit for writeback interface
  * @phys_enc:	Pointer to physical encoder
@@ -43,6 +60,7 @@ static void dpu_encoder_phys_wb_set_ot_limit(
 {
 	struct dpu_hw_wb *hw_wb = phys_enc->hw_wb;
 	struct dpu_vbif_set_ot_params ot_params;
+	bool forced_on = false;
 
 	memset(&ot_params, 0, sizeof(ot_params));
 	ot_params.xin_id = hw_wb->caps->xin_id;
@@ -52,10 +70,17 @@ static void dpu_encoder_phys_wb_set_ot_limit(
 	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;
 
+	if (!_dpu_encoder_phys_wb_clk_force_ctrl(hw_wb, phys_enc->dpu_kms->hw_mdp,
+						 true, &forced_on))
+		return;
+
 	dpu_vbif_set_ot_limit(phys_enc->dpu_kms, &ot_params);
+
+	if (forced_on)
+		_dpu_encoder_phys_wb_clk_force_ctrl(hw_wb, phys_enc->dpu_kms->hw_mdp,
+						    false, &forced_on);
 }
 
 /**
@@ -67,6 +92,7 @@ static void dpu_encoder_phys_wb_set_qos_remap(
 {
 	struct dpu_hw_wb *hw_wb;
 	struct dpu_vbif_set_qos_params qos_params;
+	bool forced_on = false;
 
 	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->crtc) {
 		DPU_ERROR("invalid arguments\n");
@@ -83,7 +109,6 @@ static void dpu_encoder_phys_wb_set_qos_remap(
 	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;
 
@@ -92,7 +117,15 @@ static void dpu_encoder_phys_wb_set_qos_remap(
 			qos_params.vbif_idx,
 			qos_params.xin_id, qos_params.is_rt);
 
+	if (!_dpu_encoder_phys_wb_clk_force_ctrl(hw_wb, phys_enc->dpu_kms->hw_mdp,
+						 true, &forced_on))
+		return;
+
 	dpu_vbif_set_qos_remap(phys_enc->dpu_kms, &qos_params);
+
+	if (forced_on)
+		_dpu_encoder_phys_wb_clk_force_ctrl(hw_wb, phys_enc->dpu_kms->hw_mdp,
+						    false, &forced_on);
 }
 
 /**
@@ -345,7 +378,11 @@ static void dpu_encoder_phys_wb_setup(
 
 }
 
-static void _dpu_encoder_phys_wb_frame_done_helper(void *arg)
+/**
+ * dpu_encoder_phys_wb_done_irq - writeback interrupt handler
+ * @arg:	Pointer to writeback encoder
+ */
+static void dpu_encoder_phys_wb_done_irq(void *arg)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 	struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc);
@@ -372,16 +409,6 @@ static void _dpu_encoder_phys_wb_frame_done_helper(void *arg)
 }
 
 /**
- * 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
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
index 713dfc0797..7056c08b99 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -79,7 +79,7 @@
 	(BIT(DPU_DIM_LAYER) | BIT(DPU_MIXER_COMBINED_ALPHA))
 
 #define PINGPONG_SDM845_MASK \
-	(BIT(DPU_PINGPONG_DITHER) | BIT(DPU_PINGPONG_TE) | BIT(DPU_PINGPONG_DSC))
+	(BIT(DPU_PINGPONG_DITHER) | BIT(DPU_PINGPONG_DSC))
 
 #define PINGPONG_SDM845_TE2_MASK \
 	(PINGPONG_SDM845_MASK | BIT(DPU_PINGPONG_TE2))
@@ -100,7 +100,6 @@
 
 #define INTF_SC7180_MASK \
 	(BIT(DPU_INTF_INPUT_CTRL) | \
-	 BIT(DPU_INTF_TE) | \
 	 BIT(DPU_INTF_STATUS_SUPPORTED) | \
 	 BIT(DPU_DATA_HCTL_EN))
 
@@ -250,14 +249,17 @@ static const uint32_t wb2_formats[] = {
  * SSPP sub blocks config
  *************************************************************/
 
+#define SSPP_SCALER_VER(maj, min) (((maj) << 16) | (min))
+
 /* SSPP common configuration */
-#define _VIG_SBLK(sdma_pri, qseed_ver) \
+#define _VIG_SBLK(sdma_pri, qseed_ver, scaler_ver) \
 	{ \
 	.maxdwnscale = MAX_DOWNSCALE_RATIO, \
 	.maxupscale = MAX_UPSCALE_RATIO, \
 	.smart_dma_priority = sdma_pri, \
 	.scaler_blk = {.name = "scaler", \
 		.id = qseed_ver, \
+		.version = scaler_ver, \
 		.base = 0xa00, .len = 0xa0,}, \
 	.csc_blk = {.name = "csc", \
 		.id = DPU_SSPP_CSC_10BIT, \
@@ -269,13 +271,14 @@ static const uint32_t wb2_formats[] = {
 	.rotation_cfg = NULL, \
 	}
 
-#define _VIG_SBLK_ROT(sdma_pri, qseed_ver, rot_cfg) \
+#define _VIG_SBLK_ROT(sdma_pri, qseed_ver, scaler_ver, rot_cfg) \
 	{ \
 	.maxdwnscale = MAX_DOWNSCALE_RATIO, \
 	.maxupscale = MAX_UPSCALE_RATIO, \
 	.smart_dma_priority = sdma_pri, \
 	.scaler_blk = {.name = "scaler", \
 		.id = qseed_ver, \
+		.version = scaler_ver, \
 		.base = 0xa00, .len = 0xa0,}, \
 	.csc_blk = {.name = "csc", \
 		.id = DPU_SSPP_CSC_10BIT, \
@@ -299,13 +302,17 @@ static const uint32_t wb2_formats[] = {
 	}
 
 static const struct dpu_sspp_sub_blks msm8998_vig_sblk_0 =
-				_VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3);
+				_VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3,
+					  SSPP_SCALER_VER(1, 2));
 static const struct dpu_sspp_sub_blks msm8998_vig_sblk_1 =
-				_VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3);
+				_VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3,
+					  SSPP_SCALER_VER(1, 2));
 static const struct dpu_sspp_sub_blks msm8998_vig_sblk_2 =
-				_VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3);
+				_VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3,
+					  SSPP_SCALER_VER(1, 2));
 static const struct dpu_sspp_sub_blks msm8998_vig_sblk_3 =
-				_VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3);
+				_VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3,
+					  SSPP_SCALER_VER(1, 2));
 
 static const struct dpu_rotation_cfg dpu_rot_sc7280_cfg_v2 = {
 	.rot_maxheight = 1088,
@@ -314,13 +321,30 @@ static const struct dpu_rotation_cfg dpu_rot_sc7280_cfg_v2 = {
 };
 
 static const struct dpu_sspp_sub_blks sdm845_vig_sblk_0 =
-				_VIG_SBLK(5, DPU_SSPP_SCALER_QSEED3);
+				_VIG_SBLK(5, DPU_SSPP_SCALER_QSEED3,
+					  SSPP_SCALER_VER(1, 3));
 static const struct dpu_sspp_sub_blks sdm845_vig_sblk_1 =
-				_VIG_SBLK(6, DPU_SSPP_SCALER_QSEED3);
+				_VIG_SBLK(6, DPU_SSPP_SCALER_QSEED3,
+					  SSPP_SCALER_VER(1, 3));
 static const struct dpu_sspp_sub_blks sdm845_vig_sblk_2 =
-				_VIG_SBLK(7, DPU_SSPP_SCALER_QSEED3);
+				_VIG_SBLK(7, DPU_SSPP_SCALER_QSEED3,
+					  SSPP_SCALER_VER(1, 3));
 static const struct dpu_sspp_sub_blks sdm845_vig_sblk_3 =
-				_VIG_SBLK(8, DPU_SSPP_SCALER_QSEED3);
+				_VIG_SBLK(8, DPU_SSPP_SCALER_QSEED3,
+					  SSPP_SCALER_VER(1, 3));
+
+static const struct dpu_sspp_sub_blks sm8150_vig_sblk_0 =
+				_VIG_SBLK(5, DPU_SSPP_SCALER_QSEED3,
+					  SSPP_SCALER_VER(1, 4));
+static const struct dpu_sspp_sub_blks sm8150_vig_sblk_1 =
+				_VIG_SBLK(6, DPU_SSPP_SCALER_QSEED3,
+					  SSPP_SCALER_VER(1, 4));
+static const struct dpu_sspp_sub_blks sm8150_vig_sblk_2 =
+				_VIG_SBLK(7, DPU_SSPP_SCALER_QSEED3,
+					  SSPP_SCALER_VER(1, 4));
+static const struct dpu_sspp_sub_blks sm8150_vig_sblk_3 =
+				_VIG_SBLK(8, DPU_SSPP_SCALER_QSEED3,
+					  SSPP_SCALER_VER(1, 4));
 
 static const struct dpu_sspp_sub_blks sdm845_dma_sblk_0 = _DMA_SBLK(1);
 static const struct dpu_sspp_sub_blks sdm845_dma_sblk_1 = _DMA_SBLK(2);
@@ -328,34 +352,60 @@ static const struct dpu_sspp_sub_blks sdm845_dma_sblk_2 = _DMA_SBLK(3);
 static const struct dpu_sspp_sub_blks sdm845_dma_sblk_3 = _DMA_SBLK(4);
 
 static const struct dpu_sspp_sub_blks sc7180_vig_sblk_0 =
-				_VIG_SBLK(4, DPU_SSPP_SCALER_QSEED4);
+				_VIG_SBLK(4, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 0));
 
 static const struct dpu_sspp_sub_blks sc7280_vig_sblk_0 =
-			_VIG_SBLK_ROT(4, DPU_SSPP_SCALER_QSEED4, &dpu_rot_sc7280_cfg_v2);
+			_VIG_SBLK_ROT(4, DPU_SSPP_SCALER_QSEED4,
+				      SSPP_SCALER_VER(3, 0),
+				      &dpu_rot_sc7280_cfg_v2);
 
 static const struct dpu_sspp_sub_blks sm6115_vig_sblk_0 =
-				_VIG_SBLK(2, DPU_SSPP_SCALER_QSEED4);
+				_VIG_SBLK(2, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 0));
 
 static const struct dpu_sspp_sub_blks sm6125_vig_sblk_0 =
-				_VIG_SBLK(3, DPU_SSPP_SCALER_QSEED3LITE);
+				_VIG_SBLK(3, DPU_SSPP_SCALER_QSEED3LITE,
+					  SSPP_SCALER_VER(2, 4));
 
 static const struct dpu_sspp_sub_blks sm8250_vig_sblk_0 =
-				_VIG_SBLK(5, DPU_SSPP_SCALER_QSEED4);
+				_VIG_SBLK(5, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 0));
 static const struct dpu_sspp_sub_blks sm8250_vig_sblk_1 =
-				_VIG_SBLK(6, DPU_SSPP_SCALER_QSEED4);
+				_VIG_SBLK(6, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 0));
 static const struct dpu_sspp_sub_blks sm8250_vig_sblk_2 =
-				_VIG_SBLK(7, DPU_SSPP_SCALER_QSEED4);
+				_VIG_SBLK(7, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 0));
 static const struct dpu_sspp_sub_blks sm8250_vig_sblk_3 =
-				_VIG_SBLK(8, DPU_SSPP_SCALER_QSEED4);
+				_VIG_SBLK(8, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 0));
+
+static const struct dpu_sspp_sub_blks sm8450_vig_sblk_0 =
+				_VIG_SBLK(5, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 1));
+static const struct dpu_sspp_sub_blks sm8450_vig_sblk_1 =
+				_VIG_SBLK(6, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 1));
+static const struct dpu_sspp_sub_blks sm8450_vig_sblk_2 =
+				_VIG_SBLK(7, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 1));
+static const struct dpu_sspp_sub_blks sm8450_vig_sblk_3 =
+				_VIG_SBLK(8, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 1));
 
 static const struct dpu_sspp_sub_blks sm8550_vig_sblk_0 =
-				_VIG_SBLK(7, DPU_SSPP_SCALER_QSEED4);
+				_VIG_SBLK(7, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 2));
 static const struct dpu_sspp_sub_blks sm8550_vig_sblk_1 =
-				_VIG_SBLK(8, DPU_SSPP_SCALER_QSEED4);
+				_VIG_SBLK(8, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 2));
 static const struct dpu_sspp_sub_blks sm8550_vig_sblk_2 =
-				_VIG_SBLK(9, DPU_SSPP_SCALER_QSEED4);
+				_VIG_SBLK(9, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 2));
 static const struct dpu_sspp_sub_blks sm8550_vig_sblk_3 =
-				_VIG_SBLK(10, DPU_SSPP_SCALER_QSEED4);
+				_VIG_SBLK(10, DPU_SSPP_SCALER_QSEED4,
+					  SSPP_SCALER_VER(3, 2));
 static const struct dpu_sspp_sub_blks sm8550_dma_sblk_4 = _DMA_SBLK(5);
 static const struct dpu_sspp_sub_blks sm8550_dma_sblk_5 = _DMA_SBLK(6);
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
index 6c9634209e..6244507530 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
@@ -119,7 +119,6 @@ enum {
 
 /**
  * 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
@@ -128,8 +127,7 @@ enum {
  * @DPU_PINGPONG_MAX
  */
 enum {
-	DPU_PINGPONG_TE = 0x1,
-	DPU_PINGPONG_TE2,
+	DPU_PINGPONG_TE2 = 0x1,
 	DPU_PINGPONG_SPLIT,
 	DPU_PINGPONG_SLAVE,
 	DPU_PINGPONG_DITHER,
@@ -160,7 +158,6 @@ enum {
  * 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
@@ -168,7 +165,6 @@ enum {
  */
 enum {
 	DPU_INTF_INPUT_CTRL = 0x1,
-	DPU_INTF_TE,
 	DPU_DATA_HCTL_EN,
 	DPU_INTF_STATUS_SUPPORTED,
 	DPU_INTF_MAX
@@ -269,7 +265,8 @@ enum {
 /**
  * struct dpu_scaler_blk: Scaler information
  * @info:   HW register and features supported by this sub-blk
- * @version: qseed block revision
+ * @version: qseed block revision, on QSEED3+ platforms this is the value of
+ *           scaler_blk.base + QSEED3_HW_VERSION registers.
  */
 struct dpu_scaler_blk {
 	DPU_HW_SUBBLK_INFO;
@@ -494,7 +491,7 @@ struct dpu_mdp_cfg {
  */
 struct dpu_ctl_cfg {
 	DPU_HW_BLK_INFO;
-	s32 intr_start;
+	unsigned int intr_start;
 };
 
 /**
@@ -557,8 +554,8 @@ struct dpu_dspp_cfg  {
 struct dpu_pingpong_cfg  {
 	DPU_HW_BLK_INFO;
 	u32 merge_3d;
-	s32 intr_done;
-	s32 intr_rdptr;
+	unsigned int intr_done;
+	unsigned int intr_rdptr;
 	const struct dpu_pingpong_sub_blks *sblk;
 };
 
@@ -605,9 +602,9 @@ struct dpu_intf_cfg  {
 	u32 type;   /* interface type*/
 	u32 controller_id;
 	u32 prog_fetch_lines_worst_case;
-	s32 intr_underrun;
-	s32 intr_vsync;
-	s32 intr_tear_rd_ptr;
+	unsigned int intr_underrun;
+	unsigned int intr_vsync;
+	unsigned int intr_tear_rd_ptr;
 };
 
 /**
@@ -626,7 +623,7 @@ struct dpu_wb_cfg {
 	u8 vbif_idx;
 	u32 maxlinewidth;
 	u32 xin_id;
-	s32 intr_wb_done;
+	unsigned int intr_wb_done;
 	const u32 *format_list;
 	u32 num_formats;
 	enum dpu_clk_ctrl_type clk_ctrl;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
index e3c50439f8..088807db2c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
@@ -197,27 +197,40 @@ static const struct dpu_intr_reg dpu_intr_set_7xxx[] = {
 	},
 };
 
-#define DPU_IRQ_REG(irq_idx)	(irq_idx / 32)
-#define DPU_IRQ_MASK(irq_idx)	(BIT(irq_idx % 32))
+#define DPU_IRQ_MASK(irq_idx)	(BIT(DPU_IRQ_BIT(irq_idx)))
+
+static inline bool dpu_core_irq_is_valid(unsigned int irq_idx)
+{
+	return irq_idx && irq_idx <= DPU_NUM_IRQS;
+}
+
+static inline struct dpu_hw_intr_entry *dpu_core_irq_get_entry(struct dpu_hw_intr *intr,
+							       unsigned int irq_idx)
+{
+	return &intr->irq_tbl[irq_idx - 1];
+}
 
 /**
  * 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)
+static void dpu_core_irq_callback_handler(struct dpu_kms *dpu_kms, unsigned int irq_idx)
 {
-	VERB("irq_idx=%d\n", irq_idx);
+	struct dpu_hw_intr_entry *irq_entry = dpu_core_irq_get_entry(dpu_kms->hw_intr, irq_idx);
+
+	VERB("IRQ=[%d, %d]\n", DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 
-	if (!dpu_kms->hw_intr->irq_tbl[irq_idx].cb)
-		DRM_ERROR("no registered cb, idx:%d\n", irq_idx);
+	if (!irq_entry->cb)
+		DRM_ERROR("no registered cb, IRQ=[%d, %d]\n",
+			  DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 
-	atomic_inc(&dpu_kms->hw_intr->irq_tbl[irq_idx].count);
+	atomic_inc(&irq_entry->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);
+	irq_entry->cb(irq_entry->arg);
 }
 
 irqreturn_t dpu_core_irq(struct msm_kms *kms)
@@ -225,7 +238,7 @@ 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;
+	unsigned int irq_idx;
 	u32 irq_status;
 	u32 enable_mask;
 	int bit;
@@ -281,7 +294,8 @@ irqreturn_t dpu_core_irq(struct msm_kms *kms)
 	return IRQ_HANDLED;
 }
 
-static int dpu_hw_intr_enable_irq_locked(struct dpu_hw_intr *intr, int irq_idx)
+static int dpu_hw_intr_enable_irq_locked(struct dpu_hw_intr *intr,
+					 unsigned int irq_idx)
 {
 	int reg_idx;
 	const struct dpu_intr_reg *reg;
@@ -291,8 +305,9 @@ static int dpu_hw_intr_enable_irq_locked(struct dpu_hw_intr *intr, int irq_idx)
 	if (!intr)
 		return -EINVAL;
 
-	if (irq_idx < 0 || irq_idx >= intr->total_irqs) {
-		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+	if (!dpu_core_irq_is_valid(irq_idx)) {
+		pr_err("invalid IRQ=[%d, %d]\n",
+		       DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 		return -EINVAL;
 	}
 
@@ -328,13 +343,15 @@ static int dpu_hw_intr_enable_irq_locked(struct dpu_hw_intr *intr, int irq_idx)
 		intr->cache_irq_mask[reg_idx] = cache_irq_mask;
 	}
 
-	pr_debug("DPU IRQ %d %senabled: MASK:0x%.8lx, CACHE-MASK:0x%.8x\n", irq_idx, dbgstr,
+	pr_debug("DPU IRQ=[%d, %d] %senabled: MASK:0x%.8lx, CACHE-MASK:0x%.8x\n",
+		 DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), 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)
+static int dpu_hw_intr_disable_irq_locked(struct dpu_hw_intr *intr,
+					  unsigned int irq_idx)
 {
 	int reg_idx;
 	const struct dpu_intr_reg *reg;
@@ -344,8 +361,9 @@ static int dpu_hw_intr_disable_irq_locked(struct dpu_hw_intr *intr, int irq_idx)
 	if (!intr)
 		return -EINVAL;
 
-	if (irq_idx < 0 || irq_idx >= intr->total_irqs) {
-		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+	if (!dpu_core_irq_is_valid(irq_idx)) {
+		pr_err("invalid IRQ=[%d, %d]\n",
+		       DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 		return -EINVAL;
 	}
 
@@ -377,7 +395,8 @@ static int dpu_hw_intr_disable_irq_locked(struct dpu_hw_intr *intr, int irq_idx)
 		intr->cache_irq_mask[reg_idx] = cache_irq_mask;
 	}
 
-	pr_debug("DPU IRQ %d %sdisabled: MASK:0x%.8lx, CACHE-MASK:0x%.8x\n", irq_idx, dbgstr,
+	pr_debug("DPU IRQ=[%d, %d] %sdisabled: MASK:0x%.8lx, CACHE-MASK:0x%.8x\n",
+		 DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), dbgstr,
 			DPU_IRQ_MASK(irq_idx), cache_irq_mask);
 
 	return 0;
@@ -419,7 +438,8 @@ static void dpu_disable_all_irqs(struct dpu_kms *dpu_kms)
 	wmb();
 }
 
-u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx)
+u32 dpu_core_irq_read(struct dpu_kms *dpu_kms,
+		      unsigned int irq_idx)
 {
 	struct dpu_hw_intr *intr = dpu_kms->hw_intr;
 	int reg_idx;
@@ -429,14 +449,8 @@ u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx)
 	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);
+	if (!dpu_core_irq_is_valid(irq_idx)) {
+		pr_err("invalid IRQ=[%d, %d]\n", DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 		return 0;
 	}
 
@@ -462,13 +476,12 @@ 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;
 	unsigned int i;
 
 	if (!addr || !m)
 		return ERR_PTR(-EINVAL);
 
-	intr = kzalloc(struct_size(intr, irq_tbl, nirq), GFP_KERNEL);
+	intr = kzalloc(sizeof(*intr), GFP_KERNEL);
 	if (!intr)
 		return ERR_PTR(-ENOMEM);
 
@@ -479,8 +492,6 @@ struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr,
 
 	intr->hw.blk_addr = addr + m->mdp[0].base;
 
-	intr->total_irqs = nirq;
-
 	intr->irq_mask = BIT(MDP_SSPP_TOP0_INTR) |
 			 BIT(MDP_SSPP_TOP0_INTR2) |
 			 BIT(MDP_SSPP_TOP0_HIST_INTR);
@@ -492,7 +503,7 @@ struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr,
 
 		intr->irq_mask |= BIT(MDP_INTFn_INTR(intf->id));
 
-		if (intf->intr_tear_rd_ptr != -1)
+		if (intf->intr_tear_rd_ptr)
 			intr->irq_mask |= BIT(DPU_IRQ_REG(intf->intr_tear_rd_ptr));
 	}
 
@@ -506,76 +517,87 @@ 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)
+int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms,
+				   unsigned int irq_idx,
+				   void (*irq_cb)(void *arg),
+				   void *irq_arg)
 {
+	struct dpu_hw_intr_entry *irq_entry;
 	unsigned long irq_flags;
 	int ret;
 
 	if (!irq_cb) {
-		DPU_ERROR("invalid ird_idx:%d irq_cb:%ps\n", irq_idx, irq_cb);
+		DPU_ERROR("invalid IRQ=[%d, %d] irq_cb:%ps\n",
+			  DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(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);
+	if (!dpu_core_irq_is_valid(irq_idx)) {
+		DPU_ERROR("invalid IRQ=[%d, %d]\n",
+			  DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 		return -EINVAL;
 	}
 
-	VERB("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx);
+	VERB("[%pS] IRQ=[%d, %d]\n", __builtin_return_address(0),
+	     DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(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))) {
+	irq_entry = dpu_core_irq_get_entry(dpu_kms->hw_intr, irq_idx);
+	if (unlikely(WARN_ON(irq_entry->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;
+	trace_dpu_core_irq_register_callback(DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), irq_cb);
+	irq_entry->arg = irq_arg;
+	irq_entry->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);
+		DPU_ERROR("Failed/ to enable IRQ=[%d, %d]\n",
+			  DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 	spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags);
 
-	trace_dpu_irq_register_success(irq_idx);
+	trace_dpu_irq_register_success(DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 
 	return 0;
 }
 
-int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx)
+int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms,
+				     unsigned int irq_idx)
 {
+	struct dpu_hw_intr_entry *irq_entry;
 	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);
+	if (!dpu_core_irq_is_valid(irq_idx)) {
+		DPU_ERROR("invalid IRQ=[%d, %d]\n",
+			  DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 		return -EINVAL;
 	}
 
-	VERB("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx);
+	VERB("[%pS] IRQ=[%d, %d]\n", __builtin_return_address(0),
+	     DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 
 	spin_lock_irqsave(&dpu_kms->hw_intr->irq_lock, irq_flags);
-	trace_dpu_core_irq_unregister_callback(irq_idx);
+	trace_dpu_core_irq_unregister_callback(DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(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_ERROR("Failed to disable IRQ=[%d, %d]: %d\n",
+			  DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), ret);
 
-	dpu_kms->hw_intr->irq_tbl[irq_idx].cb = NULL;
-	dpu_kms->hw_intr->irq_tbl[irq_idx].arg = NULL;
+	irq_entry = dpu_core_irq_get_entry(dpu_kms->hw_intr, irq_idx);
+	irq_entry->cb = NULL;
+	irq_entry->arg = NULL;
 
 	spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags);
 
-	trace_dpu_irq_unregister_success(irq_idx);
+	trace_dpu_irq_unregister_success(DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 
 	return 0;
 }
@@ -584,18 +606,21 @@ int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx)
 static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v)
 {
 	struct dpu_kms *dpu_kms = s->private;
+	struct dpu_hw_intr_entry *irq_entry;
 	unsigned long irq_flags;
 	int i, irq_count;
 	void *cb;
 
-	for (i = 0; i < dpu_kms->hw_intr->total_irqs; i++) {
+	for (i = 1; i <= DPU_NUM_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;
+		irq_entry = dpu_core_irq_get_entry(dpu_kms->hw_intr, i);
+		irq_count = atomic_read(&irq_entry->count);
+		cb = irq_entry->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);
+			seq_printf(s, "IRQ=[%d, %d] count:%d cb:%ps\n",
+				   DPU_IRQ_REG(i), DPU_IRQ_BIT(i), irq_count, cb);
 	}
 
 	return 0;
@@ -614,6 +639,7 @@ void dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
 void dpu_core_irq_preinstall(struct msm_kms *kms)
 {
 	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	struct dpu_hw_intr_entry *irq_entry;
 	int i;
 
 	pm_runtime_get_sync(&dpu_kms->pdev->dev);
@@ -621,22 +647,28 @@ void dpu_core_irq_preinstall(struct msm_kms *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);
+	for (i = 1; i <= DPU_NUM_IRQS; i++) {
+		irq_entry = dpu_core_irq_get_entry(dpu_kms->hw_intr, i);
+		atomic_set(&irq_entry->count, 0);
+	}
 }
 
 void dpu_core_irq_uninstall(struct msm_kms *kms)
 {
 	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	struct dpu_hw_intr_entry *irq_entry;
 	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);
+	for (i = 1; i <= DPU_NUM_IRQS; i++) {
+		irq_entry = dpu_core_irq_get_entry(dpu_kms->hw_intr, i);
+		if (irq_entry->cb)
+			DPU_ERROR("IRQ=[%d, %d] still enabled/registered\n",
+				  DPU_IRQ_REG(i), DPU_IRQ_BIT(i));
+	}
 
 	dpu_clear_irqs(dpu_kms);
 	dpu_disable_all_irqs(dpu_kms);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
index dab761e548..53a21ebc57 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
@@ -36,7 +36,17 @@ enum dpu_hw_intr_reg {
 
 #define MDP_INTFn_INTR(intf)	(MDP_INTF0_INTR + (intf - INTF_0))
 
-#define DPU_IRQ_IDX(reg_idx, offset)	(reg_idx * 32 + offset)
+#define DPU_IRQ_IDX(reg_idx, offset)	(1 + reg_idx * 32 + offset)
+#define DPU_IRQ_REG(irq_idx)	((irq_idx - 1) / 32)
+#define DPU_IRQ_BIT(irq_idx)	((irq_idx - 1) % 32)
+
+#define DPU_NUM_IRQS		(MDP_INTR_MAX * 32)
+
+struct dpu_hw_intr_entry {
+	void (*cb)(void *arg);
+	void *arg;
+	atomic_t count;
+};
 
 /**
  * struct dpu_hw_intr: hw interrupts handling data structure
@@ -44,7 +54,6 @@ enum dpu_hw_intr_reg {
  * @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
  */
@@ -52,16 +61,11 @@ 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;
 	const struct dpu_intr_reg *intr_set;
 
-	struct {
-		void (*cb)(void *arg, int irq_idx);
-		void *arg;
-		atomic_t count;
-	} irq_tbl[];
+	struct dpu_hw_intr_entry irq_tbl[DPU_NUM_IRQS];
 };
 
 /**
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
index da071b1c02..27b9373cd7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
@@ -521,32 +521,10 @@ static void dpu_hw_intf_program_intf_cmd_cfg(struct dpu_hw_intf *ctx,
 	if (cmd_mode_cfg->data_compress)
 		intf_cfg2 |= INTF_CFG2_DCE_DATA_COMPRESS;
 
-	DPU_REG_WRITE(&ctx->hw, INTF_CONFIG2, intf_cfg2);
-}
-
-static void _setup_intf_ops(struct dpu_hw_intf_ops *ops,
-		unsigned long cap, const struct dpu_mdss_version *mdss_rev)
-{
-	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;
-
-	if (cap & BIT(DPU_INTF_TE)) {
-		ops->enable_tearcheck = dpu_hw_intf_enable_te;
-		ops->disable_tearcheck = dpu_hw_intf_disable_te;
-		ops->connect_external_te = dpu_hw_intf_connect_external_te;
-		ops->vsync_sel = dpu_hw_intf_vsync_sel;
-		ops->disable_autorefresh = dpu_hw_intf_disable_autorefresh;
-	}
+	if (cmd_mode_cfg->wide_bus_en)
+		intf_cfg2 |= INTF_CFG2_DATABUS_WIDEN;
 
-	if (mdss_rev->core_major_ver >= 7)
-		ops->program_intf_cmd_cfg = dpu_hw_intf_program_intf_cmd_cfg;
+	DPU_REG_WRITE(&ctx->hw, INTF_CONFIG2, intf_cfg2);
 }
 
 struct dpu_hw_intf *dpu_hw_intf_init(const struct dpu_intf_cfg *cfg,
@@ -571,7 +549,35 @@ struct dpu_hw_intf *dpu_hw_intf_init(const struct dpu_intf_cfg *cfg,
 	 */
 	c->idx = cfg->id;
 	c->cap = cfg;
-	_setup_intf_ops(&c->ops, c->cap->features, mdss_rev);
+
+	c->ops.setup_timing_gen = dpu_hw_intf_setup_timing_engine;
+	c->ops.setup_prg_fetch  = dpu_hw_intf_setup_prg_fetch;
+	c->ops.get_status = dpu_hw_intf_get_status;
+	c->ops.enable_timing = dpu_hw_intf_enable_timing_engine;
+	c->ops.get_line_count = dpu_hw_intf_get_line_count;
+	c->ops.setup_misr = dpu_hw_intf_setup_misr;
+	c->ops.collect_misr = dpu_hw_intf_collect_misr;
+
+	if (cfg->features & BIT(DPU_INTF_INPUT_CTRL))
+		c->ops.bind_pingpong_blk = dpu_hw_intf_bind_pingpong_blk;
+
+	/* INTF TE is only for DSI interfaces */
+	if (mdss_rev->core_major_ver >= 5 && cfg->type == INTF_DSI) {
+		WARN_ON(!cfg->intr_tear_rd_ptr);
+
+		c->ops.enable_tearcheck = dpu_hw_intf_enable_te;
+		c->ops.disable_tearcheck = dpu_hw_intf_disable_te;
+		c->ops.connect_external_te = dpu_hw_intf_connect_external_te;
+		c->ops.vsync_sel = dpu_hw_intf_vsync_sel;
+		c->ops.disable_autorefresh = dpu_hw_intf_disable_autorefresh;
+	}
+
+	/* Technically, INTF_CONFIG2 is present for DPU 5.0+, but
+	 * we can configure it for DPU 7.0+ since the wide bus and DSC flags
+	 * would not be set for DPU < 7.0 anyways
+	 */
+	if (mdss_rev->core_major_ver >= 7)
+		c->ops.program_intf_cmd_cfg = dpu_hw_intf_program_intf_cmd_cfg;
 
 	return c;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
index 4e86108bee..66a5603dc7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
@@ -50,6 +50,7 @@ struct dpu_hw_intf_status {
 
 struct dpu_hw_intf_cmd_mode_cfg {
 	u8 data_compress;	/* enable data compress between dpu and dsi */
+	u8 wide_bus_en;		/* enable databus widen mode */
 };
 
 /**
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
index 437d9e62a8..057cac7f5d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
@@ -281,10 +281,24 @@ static int dpu_hw_pp_setup_dsc(struct dpu_hw_pingpong *pp)
 	return 0;
 }
 
-static void _setup_pingpong_ops(struct dpu_hw_pingpong *c,
-				unsigned long features)
+struct dpu_hw_pingpong *dpu_hw_pingpong_init(const struct dpu_pingpong_cfg *cfg,
+		void __iomem *addr, const struct dpu_mdss_version *mdss_rev)
 {
-	if (test_bit(DPU_PINGPONG_TE, &features)) {
+	struct dpu_hw_pingpong *c;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	c->hw.blk_addr = addr + cfg->base;
+	c->hw.log_mask = DPU_DBG_MASK_PINGPONG;
+
+	c->idx = cfg->id;
+	c->caps = cfg;
+
+	if (mdss_rev->core_major_ver < 5) {
+		WARN_ON(!cfg->intr_rdptr);
+
 		c->ops.enable_tearcheck = dpu_hw_pp_enable_te;
 		c->ops.disable_tearcheck = dpu_hw_pp_disable_te;
 		c->ops.connect_external_te = dpu_hw_pp_connect_external_te;
@@ -292,31 +306,14 @@ static void _setup_pingpong_ops(struct dpu_hw_pingpong *c,
 		c->ops.disable_autorefresh = dpu_hw_pp_disable_autorefresh;
 	}
 
-	if (test_bit(DPU_PINGPONG_DSC, &features)) {
+	if (test_bit(DPU_PINGPONG_DSC, &cfg->features)) {
 		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))
+	if (test_bit(DPU_PINGPONG_DITHER, &cfg->features))
 		c->ops.setup_dither = dpu_hw_pp_setup_dither;
-};
-
-struct dpu_hw_pingpong *dpu_hw_pingpong_init(const struct dpu_pingpong_cfg *cfg,
-		void __iomem *addr)
-{
-	struct dpu_hw_pingpong *c;
-
-	c = kzalloc(sizeof(*c), GFP_KERNEL);
-	if (!c)
-		return ERR_PTR(-ENOMEM);
-
-	c->hw.blk_addr = addr + cfg->base;
-	c->hw.log_mask = DPU_DBG_MASK_PINGPONG;
-
-	c->idx = cfg->id;
-	c->caps = cfg;
-	_setup_pingpong_ops(c, c->caps->features);
 
 	return c;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
index d3246a9a58..0d541ca5b0 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
@@ -123,10 +123,11 @@ static inline struct dpu_hw_pingpong *to_dpu_hw_pingpong(struct dpu_hw_blk *hw)
  * pingpong catalog entry.
  * @cfg:  Pingpong catalog entry for which driver object is required
  * @addr: Mapped register io address of MDP
+ * @mdss_rev: dpu core's major and minor versions
  * Return: Error code or allocated dpu_hw_pingpong context
  */
 struct dpu_hw_pingpong *dpu_hw_pingpong_init(const struct dpu_pingpong_cfg *cfg,
-		void __iomem *addr);
+		void __iomem *addr, const struct dpu_mdss_version *mdss_rev);
 
 /**
  * dpu_hw_pingpong_destroy - destroys pingpong driver context
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
index f2192de937..8e3c65989c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
@@ -69,6 +69,7 @@
 #define SSPP_EXCL_REC_XY_REC1              0x188
 #define SSPP_EXCL_REC_SIZE                 0x1B4
 #define SSPP_EXCL_REC_XY                   0x1B8
+#define SSPP_CLK_CTRL                      0x330
 
 /* SSPP_SRC_OP_MODE & OP_MODE_REC1 */
 #define MDSS_MDP_OP_DEINTERLACE            BIT(22)
@@ -581,8 +582,18 @@ static void dpu_hw_sspp_setup_cdp(struct dpu_sw_pipe *pipe,
 	dpu_setup_cdp(&ctx->hw, cdp_cntl_offset, fmt, enable);
 }
 
+static bool dpu_hw_sspp_setup_clk_force_ctrl(struct dpu_hw_sspp *ctx, bool enable)
+{
+	static const struct dpu_clk_ctrl_reg sspp_clk_ctrl = {
+		.reg_off = SSPP_CLK_CTRL,
+		.bit_off = 0
+	};
+
+	return dpu_hw_clk_force_ctrl(&ctx->hw, &sspp_clk_ctrl, enable);
+}
+
 static void _setup_layer_ops(struct dpu_hw_sspp *c,
-		unsigned long features)
+		unsigned long features, const struct dpu_mdss_version *mdss_rev)
 {
 	c->ops.setup_format = dpu_hw_sspp_setup_format;
 	c->ops.setup_rects = dpu_hw_sspp_setup_rects;
@@ -612,6 +623,9 @@ static void _setup_layer_ops(struct dpu_hw_sspp *c,
 
 	if (test_bit(DPU_SSPP_CDP, &features))
 		c->ops.setup_cdp = dpu_hw_sspp_setup_cdp;
+
+	if (mdss_rev->core_major_ver >= 9)
+		c->ops.setup_clk_force_ctrl = dpu_hw_sspp_setup_clk_force_ctrl;
 }
 
 #ifdef CONFIG_DEBUG_FS
@@ -672,7 +686,8 @@ int _dpu_hw_sspp_init_debugfs(struct dpu_hw_sspp *hw_pipe, struct dpu_kms *kms,
 #endif
 
 struct dpu_hw_sspp *dpu_hw_sspp_init(const struct dpu_sspp_cfg *cfg,
-		void __iomem *addr, const struct msm_mdss_data *mdss_data)
+		void __iomem *addr, const struct msm_mdss_data *mdss_data,
+		const struct dpu_mdss_version *mdss_rev)
 {
 	struct dpu_hw_sspp *hw_pipe;
 
@@ -690,7 +705,7 @@ struct dpu_hw_sspp *dpu_hw_sspp_init(const struct dpu_sspp_cfg *cfg,
 	hw_pipe->ubwc = mdss_data;
 	hw_pipe->idx = cfg->id;
 	hw_pipe->cap = cfg;
-	_setup_layer_ops(hw_pipe, hw_pipe->cap->features);
+	_setup_layer_ops(hw_pipe, hw_pipe->cap->features, mdss_rev);
 
 	return hw_pipe;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
index cbf4f95ff0..f93969fddb 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
@@ -272,6 +272,14 @@ struct dpu_hw_sspp_ops {
 			       bool danger_safe_en);
 
 	/**
+	 * setup_clk_force_ctrl - setup clock force control
+	 * @ctx: Pointer to pipe context
+	 * @enable: enable clock force if true
+	 */
+	bool (*setup_clk_force_ctrl)(struct dpu_hw_sspp *ctx,
+				     bool enable);
+
+	/**
 	 * setup_histogram - setup histograms
 	 * @ctx: Pointer to pipe context
 	 * @cfg: Pointer to histogram configuration
@@ -334,9 +342,11 @@ struct dpu_kms;
  * @cfg:  Pipe catalog entry for which driver object is required
  * @addr: Mapped register io address of MDP
  * @mdss_data: UBWC / MDSS configuration data
+ * @mdss_rev: dpu core's major and minor versions
  */
 struct dpu_hw_sspp *dpu_hw_sspp_init(const struct dpu_sspp_cfg *cfg,
-		void __iomem *addr, const struct msm_mdss_data *mdss_data);
+		void __iomem *addr, const struct msm_mdss_data *mdss_data,
+		const struct dpu_mdss_version *mdss_rev);
 
 /**
  * dpu_hw_sspp_destroy(): Destroys SSPP driver context
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
index cff48763ce..24e734768a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
@@ -66,34 +66,13 @@ static void dpu_hw_setup_split_pipe(struct dpu_hw_mdp *mdp,
 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;
+	return dpu_hw_clk_force_ctrl(&mdp->hw, &mdp->caps->clk_ctrls[clk_ctrl], enable);
 }
 
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
index 6eee9f68ab..1d4f0b97c3 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
@@ -542,3 +542,24 @@ void dpu_setup_cdp(struct dpu_hw_blk_reg_map *c, u32 offset,
 
 	DPU_REG_WRITE(c, offset, cdp_cntl);
 }
+
+bool dpu_hw_clk_force_ctrl(struct dpu_hw_blk_reg_map *c,
+			   const struct dpu_clk_ctrl_reg *clk_ctrl_reg,
+			   bool enable)
+{
+	u32 reg_val, new_val;
+	bool clk_forced_on;
+
+	reg_val = DPU_REG_READ(c, clk_ctrl_reg->reg_off);
+
+	if (enable)
+		new_val = reg_val | BIT(clk_ctrl_reg->bit_off);
+	else
+		new_val = reg_val & ~BIT(clk_ctrl_reg->bit_off);
+
+	DPU_REG_WRITE(c, clk_ctrl_reg->reg_off, new_val);
+
+	clk_forced_on = !(reg_val & BIT(clk_ctrl_reg->bit_off));
+
+	return clk_forced_on;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
index 0aed54d7f6..ec09fc3865 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
@@ -365,4 +365,8 @@ int dpu_hw_collect_misr(struct dpu_hw_blk_reg_map *c,
 		u32 misr_signature_offset,
 		u32 *misr_value);
 
+bool dpu_hw_clk_force_ctrl(struct dpu_hw_blk_reg_map *c,
+			   const struct dpu_clk_ctrl_reg *clk_ctrl_reg,
+			   bool enable);
+
 #endif /* _DPU_HW_UTIL_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
index ebc4164003..d49b3ef768 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c
@@ -43,6 +43,7 @@
 #define WB_MUX                                0x150
 #define WB_CROP_CTRL                          0x154
 #define WB_CROP_OFFSET                        0x158
+#define WB_CLK_CTRL                           0x178
 #define WB_CSC_BASE                           0x260
 #define WB_DST_ADDR_SW_STATUS                 0x2B0
 #define WB_CDP_CNTL                           0x2B4
@@ -86,6 +87,9 @@ static void dpu_hw_wb_setup_format(struct dpu_hw_wb *ctx,
 			dst_format |= BIT(14); /* DST_ALPHA_X */
 	}
 
+	if (DPU_FORMAT_IS_YUV(fmt))
+		dst_format |= BIT(15);
+
 	pattern = (fmt->element[3] << 24) |
 		(fmt->element[2] << 16) |
 		(fmt->element[1] << 8)  |
@@ -175,8 +179,18 @@ static void dpu_hw_wb_bind_pingpong_blk(
 	DPU_REG_WRITE(c, WB_MUX, mux_cfg);
 }
 
+static bool dpu_hw_wb_setup_clk_force_ctrl(struct dpu_hw_wb *ctx, bool enable)
+{
+	static const struct dpu_clk_ctrl_reg wb_clk_ctrl = {
+		.reg_off = WB_CLK_CTRL,
+		.bit_off = 0
+	};
+
+	return dpu_hw_clk_force_ctrl(&ctx->hw, &wb_clk_ctrl, enable);
+}
+
 static void _setup_wb_ops(struct dpu_hw_wb_ops *ops,
-		unsigned long features)
+		unsigned long features, const struct dpu_mdss_version *mdss_rev)
 {
 	ops->setup_outaddress = dpu_hw_wb_setup_outaddress;
 	ops->setup_outformat = dpu_hw_wb_setup_format;
@@ -192,10 +206,13 @@ static void _setup_wb_ops(struct dpu_hw_wb_ops *ops,
 
 	if (test_bit(DPU_WB_INPUT_CTRL, &features))
 		ops->bind_pingpong_blk = dpu_hw_wb_bind_pingpong_blk;
+
+	if (mdss_rev->core_major_ver >= 9)
+		ops->setup_clk_force_ctrl = dpu_hw_wb_setup_clk_force_ctrl;
 }
 
 struct dpu_hw_wb *dpu_hw_wb_init(const struct dpu_wb_cfg *cfg,
-		void __iomem *addr)
+		void __iomem *addr, const struct dpu_mdss_version *mdss_rev)
 {
 	struct dpu_hw_wb *c;
 
@@ -212,7 +229,7 @@ struct dpu_hw_wb *dpu_hw_wb_init(const struct dpu_wb_cfg *cfg,
 	/* Assign ops */
 	c->idx = cfg->id;
 	c->caps = cfg;
-	_setup_wb_ops(&c->ops, c->caps->features);
+	_setup_wb_ops(&c->ops, c->caps->features, mdss_rev);
 
 	return c;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.h
index 2d7db2efa3..88792f450a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.h
@@ -29,6 +29,7 @@ struct dpu_hw_wb_cfg {
  *  @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
+ *  @setup_clk_force_ctrl: setup clock force control
  *  @bind_pingpong_blk: enable/disable the connection with ping-pong block
  */
 struct dpu_hw_wb_ops {
@@ -48,6 +49,9 @@ struct dpu_hw_wb_ops {
 			  const struct dpu_format *fmt,
 			  bool enable);
 
+	bool (*setup_clk_force_ctrl)(struct dpu_hw_wb *ctx,
+				     bool enable);
+
 	void (*bind_pingpong_blk)(struct dpu_hw_wb *ctx,
 				  const enum dpu_pingpong pp);
 };
@@ -74,10 +78,11 @@ struct dpu_hw_wb {
  * dpu_hw_wb_init() - Initializes the writeback hw driver object.
  * @cfg:  wb_path catalog entry for which driver object is required
  * @addr: mapped register io address of MDP
+ * @mdss_rev: dpu core's major and minor versions
  * Return: Error code or allocated dpu_hw_wb context
  */
 struct dpu_hw_wb *dpu_hw_wb_init(const struct dpu_wb_cfg *cfg,
-		void __iomem *addr);
+		void __iomem *addr, const struct dpu_mdss_version *mdss_rev);
 
 /**
  * dpu_hw_wb_destroy(): Destroy writeback hw driver object.
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index aa6ba2cf4b..fe7267b3bf 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -389,8 +389,7 @@ 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;
+	struct device *dpu_dev = &dpu_kms->pdev->dev;
 
 	path0 = msm_icc_get(dpu_dev, "mdp0-mem");
 	path1 = msm_icc_get(dpu_dev, "mdp1-mem");
@@ -829,21 +828,9 @@ static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms)
 
 	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)
@@ -1079,30 +1066,6 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 
 	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_parse_data_bus_icc_path(dpu_kms);
-
 	rc = pm_runtime_resume_and_get(&dpu_kms->pdev->dev);
 	if (rc < 0)
 		goto error;
@@ -1241,33 +1204,11 @@ 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 dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
 	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);
@@ -1280,33 +1221,79 @@ static int dpu_kms_init(struct drm_device *ddev)
 		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);
+	struct device *dev = &pdev->dev;
+	struct dpu_kms *dpu_kms;
+	int irq;
+	int ret = 0;
+
+	dpu_kms = devm_kzalloc(dev, sizeof(*dpu_kms), GFP_KERNEL);
+	if (!dpu_kms)
+		return -ENOMEM;
+
+	dpu_kms->pdev = pdev;
+
+	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)
+		return dev_err_probe(dev, ret, "invalid OPP table in device tree\n");
+
+	ret = devm_clk_bulk_get_all(&pdev->dev, &dpu_kms->clocks);
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "failed to parse clocks\n");
+
+	dpu_kms->num_clocks = ret;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return dev_err_probe(dev, irq, "failed to get irq\n");
+
+	dpu_kms->base.irq = irq;
+
+	dpu_kms->mmio = msm_ioremap(pdev, "mdp");
+	if (IS_ERR(dpu_kms->mmio)) {
+		ret = PTR_ERR(dpu_kms->mmio);
+		DPU_ERROR("mdp register memory map failed: %d\n", ret);
+		dpu_kms->mmio = NULL;
+		return ret;
+	}
+	DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio);
+
+	dpu_kms->vbif[VBIF_RT] = msm_ioremap(pdev, "vbif");
+	if (IS_ERR(dpu_kms->vbif[VBIF_RT])) {
+		ret = PTR_ERR(dpu_kms->vbif[VBIF_RT]);
+		DPU_ERROR("vbif register memory map failed: %d\n", ret);
+		dpu_kms->vbif[VBIF_RT] = NULL;
+		return ret;
+	}
+
+	dpu_kms->vbif[VBIF_NRT] = msm_ioremap_quiet(pdev, "vbif_nrt");
+	if (IS_ERR(dpu_kms->vbif[VBIF_NRT])) {
+		dpu_kms->vbif[VBIF_NRT] = NULL;
+		DPU_DEBUG("VBIF NRT is not defined");
+	}
+
+	ret = dpu_kms_parse_data_bus_icc_path(dpu_kms);
+	if (ret)
+		return ret;
+
+	return msm_drv_probe(&pdev->dev, dpu_kms_init, &dpu_kms->base);
 }
 
-static int dpu_dev_remove(struct platform_device *pdev)
+static void 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)
@@ -1355,8 +1342,8 @@ 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,
+	.prepare = msm_kms_pm_prepare,
+	.complete = msm_kms_pm_complete,
 };
 
 static const struct of_device_id dpu_dt_match[] = {
@@ -1382,8 +1369,8 @@ 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,
+	.remove_new = dpu_dev_remove,
+	.shutdown = msm_kms_shutdown,
 	.driver = {
 		.name = "msm_dpu",
 		.of_match_table = dpu_dt_match,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
index b6f53ca6e9..f5473d4dea 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -51,6 +51,7 @@
 	} while (0)
 
 #define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__)
+#define DPU_ERROR_RATELIMITED(fmt, ...) pr_err_ratelimited("[dpu error]" fmt, ##__VA_ARGS__)
 
 /**
  * ktime_compare_safe - compare two ktime structures
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 0be195f914..3eef5e025e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -333,6 +333,23 @@ static void _dpu_plane_set_qos_ctrl(struct drm_plane *plane,
 				       enable);
 }
 
+static bool _dpu_plane_sspp_clk_force_ctrl(struct dpu_hw_sspp *sspp,
+					   struct dpu_hw_mdp *mdp,
+					   bool enable, bool *forced_on)
+{
+	if (sspp->ops.setup_clk_force_ctrl) {
+		*forced_on = sspp->ops.setup_clk_force_ctrl(sspp, enable);
+		return true;
+	}
+
+	if (mdp->ops.setup_clk_force_ctrl) {
+		*forced_on = mdp->ops.setup_clk_force_ctrl(mdp, sspp->cap->clk_ctrl, enable);
+		return true;
+	}
+
+	return false;
+}
+
 /**
  * _dpu_plane_set_ot_limit - set OT limit for the given plane
  * @plane:		Pointer to drm plane
@@ -348,6 +365,7 @@ static void _dpu_plane_set_ot_limit(struct drm_plane *plane,
 	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);
+	bool forced_on = false;
 
 	memset(&ot_params, 0, sizeof(ot_params));
 	ot_params.xin_id = pipe->sspp->cap->xin_id;
@@ -357,10 +375,17 @@ static void _dpu_plane_set_ot_limit(struct drm_plane *plane,
 	ot_params.is_wfd = !pdpu->is_rt_pipe;
 	ot_params.frame_rate = frame_rate;
 	ot_params.vbif_idx = VBIF_RT;
-	ot_params.clk_ctrl = pipe->sspp->cap->clk_ctrl;
 	ot_params.rd = true;
 
+	if (!_dpu_plane_sspp_clk_force_ctrl(pipe->sspp, dpu_kms->hw_mdp,
+					    true, &forced_on))
+		return;
+
 	dpu_vbif_set_ot_limit(dpu_kms, &ot_params);
+
+	if (forced_on)
+		_dpu_plane_sspp_clk_force_ctrl(pipe->sspp, dpu_kms->hw_mdp,
+					       false, &forced_on);
 }
 
 /**
@@ -374,21 +399,28 @@ 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);
+	bool forced_on = false;
 
 	memset(&qos_params, 0, sizeof(qos_params));
 	qos_params.vbif_idx = VBIF_RT;
-	qos_params.clk_ctrl = pipe->sspp->cap->clk_ctrl;
 	qos_params.xin_id = pipe->sspp->cap->xin_id;
 	qos_params.num = pipe->sspp->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",
+	DPU_DEBUG_PLANE(pdpu, "pipe:%d vbif:%d xin:%d rt:%d\n",
 			qos_params.num,
 			qos_params.vbif_idx,
-			qos_params.xin_id, qos_params.is_rt,
-			qos_params.clk_ctrl);
+			qos_params.xin_id, qos_params.is_rt);
+
+	if (!_dpu_plane_sspp_clk_force_ctrl(pipe->sspp, dpu_kms->hw_mdp,
+					    true, &forced_on))
+		return;
 
 	dpu_vbif_set_qos_remap(dpu_kms, &qos_params);
+
+	if (forced_on)
+		_dpu_plane_sspp_clk_force_ctrl(pipe->sspp, dpu_kms->hw_mdp,
+					       false, &forced_on);
 }
 
 static void _dpu_plane_setup_scaler3(struct dpu_hw_sspp *pipe_hw,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index f9215643c7..8759466e2f 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -146,7 +146,7 @@ int dpu_rm_init(struct dpu_rm *rm,
 		struct dpu_hw_pingpong *hw;
 		const struct dpu_pingpong_cfg *pp = &cat->pingpong[i];
 
-		hw = dpu_hw_pingpong_init(pp, mmio);
+		hw = dpu_hw_pingpong_init(pp, mmio, cat->mdss_ver);
 		if (IS_ERR(hw)) {
 			rc = PTR_ERR(hw);
 			DPU_ERROR("failed pingpong object creation: err %d\n",
@@ -175,7 +175,7 @@ int dpu_rm_init(struct dpu_rm *rm,
 		struct dpu_hw_wb *hw;
 		const struct dpu_wb_cfg *wb = &cat->wb[i];
 
-		hw = dpu_hw_wb_init(wb, mmio);
+		hw = dpu_hw_wb_init(wb, mmio, cat->mdss_ver);
 		if (IS_ERR(hw)) {
 			rc = PTR_ERR(hw);
 			DPU_ERROR("failed wb object creation: err %d\n", rc);
@@ -231,7 +231,7 @@ int dpu_rm_init(struct dpu_rm *rm,
 		struct dpu_hw_sspp *hw;
 		const struct dpu_sspp_cfg *sspp = &cat->sspp[i];
 
-		hw = dpu_hw_sspp_init(sspp, mmio, mdss_data);
+		hw = dpu_hw_sspp_init(sspp, mmio, mdss_data, cat->mdss_ver);
 		if (IS_ERR(hw)) {
 			rc = PTR_ERR(hw);
 			DPU_ERROR("failed sspp object creation: err %d\n", rc);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
index c74b9be25e..35d03b121a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
@@ -168,46 +168,50 @@ TRACE_EVENT(dpu_perf_crtc_update,
 );
 
 DECLARE_EVENT_CLASS(dpu_irq_template,
-	TP_PROTO(int irq_idx),
-	TP_ARGS(irq_idx),
+	TP_PROTO(unsigned int irq_reg, unsigned int irq_bit),
+	TP_ARGS(irq_reg, irq_bit),
 	TP_STRUCT__entry(
-		__field(	int,			irq_idx		)
+		__field(	unsigned int,		irq_reg		)
+		__field(	unsigned int,		irq_bit		)
 	),
 	TP_fast_assign(
-		__entry->irq_idx = irq_idx;
+		__entry->irq_reg = irq_reg;
+		__entry->irq_bit = irq_bit;
 	),
-	TP_printk("irq=%d", __entry->irq_idx)
+	TP_printk("IRQ=[%d, %d]", __entry->irq_reg, __entry->irq_bit)
 );
 DEFINE_EVENT(dpu_irq_template, dpu_irq_register_success,
-	TP_PROTO(int irq_idx),
-	TP_ARGS(irq_idx)
+	TP_PROTO(unsigned int irq_reg, unsigned int irq_bit),
+	TP_ARGS(irq_reg, irq_bit)
 );
 DEFINE_EVENT(dpu_irq_template, dpu_irq_unregister_success,
-	TP_PROTO(int irq_idx),
-	TP_ARGS(irq_idx)
+	TP_PROTO(unsigned int irq_reg, unsigned int irq_bit),
+	TP_ARGS(irq_reg, irq_bit)
 );
 
 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),
+		 unsigned int irq_reg, unsigned int irq_bit, enum dpu_pingpong pp_idx, int atomic_cnt),
+	TP_ARGS(drm_id, func, irq_reg, irq_bit, pp_idx, atomic_cnt),
 	TP_STRUCT__entry(
 		__field(	uint32_t,		drm_id		)
 		__field(	void *,			func		)
-		__field(	int,			irq_idx		)
+		__field(	unsigned int,		irq_reg		)
+		__field(	unsigned int,		irq_bit		)
 		__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->irq_reg = irq_reg;
+		__entry->irq_bit = irq_bit;
 		__entry->pp_idx = pp_idx;
 		__entry->atomic_cnt = atomic_cnt;
 	),
-	TP_printk("id=%u, callback=%ps, irq=%d, pp=%d, atomic_cnt=%d",
+	TP_printk("id=%u, callback=%ps, IRQ=[%d, %d], pp=%d, atomic_cnt=%d",
 		  __entry->drm_id, __entry->func,
-		  __entry->irq_idx, __entry->pp_idx, __entry->atomic_cnt)
+		  __entry->irq_reg, __entry->irq_bit, __entry->pp_idx, __entry->atomic_cnt)
 );
 
 DECLARE_EVENT_CLASS(dpu_drm_obj_template,
@@ -484,12 +488,13 @@ DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_more_pending,
 );
 
 TRACE_EVENT(dpu_enc_wait_event_timeout,
-	TP_PROTO(uint32_t drm_id, int irq_idx, int rc, s64 time,
+	TP_PROTO(uint32_t drm_id, unsigned int irq_reg, unsigned int irq_bit, int rc, s64 time,
 		 s64 expected_time, int atomic_cnt),
-	TP_ARGS(drm_id, irq_idx, rc, time, expected_time, atomic_cnt),
+	TP_ARGS(drm_id, irq_reg, irq_bit, rc, time, expected_time, atomic_cnt),
 	TP_STRUCT__entry(
 		__field(	uint32_t,	drm_id		)
-		__field(	int,		irq_idx		)
+		__field(	unsigned int,	irq_reg		)
+		__field(	unsigned int,	irq_bit		)
 		__field(	int,		rc		)
 		__field(	s64,		time		)
 		__field(	s64,		expected_time	)
@@ -497,14 +502,15 @@ TRACE_EVENT(dpu_enc_wait_event_timeout,
 	),
 	TP_fast_assign(
 		__entry->drm_id = drm_id;
-		__entry->irq_idx = irq_idx;
+		__entry->irq_reg = irq_reg;
+		__entry->irq_bit = irq_bit;
 		__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,
+	TP_printk("id=%u, IRQ=[%d, %d], rc=%d, time=%lld, expected=%lld cnt=%d",
+		  __entry->drm_id, __entry->irq_reg, __entry->irq_bit, __entry->rc, __entry->time,
 		  __entry->expected_time, __entry->atomic_cnt)
 );
 
@@ -863,30 +869,34 @@ TRACE_EVENT(dpu_intf_connect_ext_te,
 );
 
 TRACE_EVENT(dpu_core_irq_register_callback,
-	TP_PROTO(int irq_idx, void *callback),
-	TP_ARGS(irq_idx, callback),
+	TP_PROTO(unsigned int irq_reg, unsigned int irq_bit, void *callback),
+	TP_ARGS(irq_reg, irq_bit, callback),
 	TP_STRUCT__entry(
-		__field(	int,				irq_idx	)
+		__field(	unsigned int,			irq_reg	)
+		__field(	unsigned int,			irq_bit	)
 		__field(	void *,				callback)
 	),
 	TP_fast_assign(
-		__entry->irq_idx = irq_idx;
+		__entry->irq_reg = irq_reg;
+		__entry->irq_bit = irq_bit;
 		__entry->callback = callback;
 	),
-	TP_printk("irq_idx:%d callback:%ps", __entry->irq_idx,
+	TP_printk("IRQ=[%d, %d] callback:%ps", __entry->irq_reg, __entry->irq_bit,
 		  __entry->callback)
 );
 
 TRACE_EVENT(dpu_core_irq_unregister_callback,
-	TP_PROTO(int irq_idx),
-	TP_ARGS(irq_idx),
+	TP_PROTO(unsigned int irq_reg, unsigned int irq_bit),
+	TP_ARGS(irq_reg, irq_bit),
 	TP_STRUCT__entry(
-		__field(	int,				irq_idx	)
+		__field(	unsigned int,			irq_reg	)
+		__field(	unsigned int,			irq_bit	)
 	),
 	TP_fast_assign(
-		__entry->irq_idx = irq_idx;
+		__entry->irq_reg = irq_reg;
+		__entry->irq_bit = irq_bit;
 	),
-	TP_printk("irq_idx:%d", __entry->irq_idx)
+	TP_printk("IRQ=[%d, %d]", __entry->irq_reg, __entry->irq_bit)
 );
 
 TRACE_EVENT(dpu_core_perf_update_clk,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
index 1305e250b7..47c02b98ea 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
@@ -169,23 +169,16 @@ 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);
+	if (!vbif) {
+		DRM_DEBUG_ATOMIC("invalid arguments vbif %d\n", vbif != NULL);
 		return;
 	}
 
-	if (!mdp->ops.setup_clk_force_ctrl ||
-			!vbif->ops.set_limit_conf ||
-			!vbif->ops.set_halt_ctrl)
+	if (!vbif->ops.set_limit_conf || !vbif->ops.set_halt_ctrl)
 		return;
 
 	/* set write_gather_en for all write clients */
@@ -200,8 +193,6 @@ void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
 	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);
@@ -211,25 +202,19 @@ void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
 		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) {
+	if (!params) {
 		DPU_ERROR("invalid arguments\n");
 		return;
 	}
-	mdp = dpu_kms->hw_mdp;
 
 	vbif = dpu_get_vbif(dpu_kms, params->vbif_idx);
 
@@ -238,7 +223,7 @@ void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
 		return;
 	}
 
-	if (!vbif->ops.set_qos_remap || !mdp->ops.setup_clk_force_ctrl) {
+	if (!vbif->ops.set_qos_remap) {
 		DRM_DEBUG_ATOMIC("qos remap not supported\n");
 		return;
 	}
@@ -251,8 +236,6 @@ void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
 		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,
@@ -260,9 +243,6 @@ void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
 		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)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
index ab490177d8..e1b1f7f4e4 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
@@ -16,13 +16,11 @@ struct dpu_vbif_set_ot_params {
 	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;
 };
 
@@ -30,14 +28,12 @@ struct dpu_vbif_set_memtype_params {
  * 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;
 };
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index 700df4040e..4ba1cb74ad 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -135,8 +135,6 @@ static void mdp4_destroy(struct msm_kms *kms)
 		pm_runtime_disable(dev);
 
 	mdp_kms_destroy(&mdp4_kms->base);
-
-	kfree(mdp4_kms);
 }
 
 static const struct mdp_kms_funcs kms_funcs = {
@@ -380,56 +378,27 @@ static int mdp4_kms_init(struct drm_device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev->dev);
 	struct msm_drm_private *priv = dev->dev_private;
-	struct mdp4_kms *mdp4_kms;
+	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(priv->kms));
 	struct msm_kms *kms = NULL;
 	struct msm_mmu *mmu;
 	struct msm_gem_address_space *aspace;
-	int irq, ret;
+	int ret;
 	u32 major, minor;
 	unsigned long max_clk;
 
 	/* TODO: Chips that aren't apq8064 have a 200 Mhz max_clk */
 	max_clk = 266667000;
 
-	mdp4_kms = kzalloc(sizeof(*mdp4_kms), GFP_KERNEL);
-	if (!mdp4_kms) {
-		DRM_DEV_ERROR(dev->dev, "failed to allocate kms\n");
-		return -ENOMEM;
-	}
-
 	ret = mdp_kms_init(&mdp4_kms->base, &kms_funcs);
 	if (ret) {
 		DRM_DEV_ERROR(dev->dev, "failed to init kms\n");
 		goto fail;
 	}
 
-	priv->kms = &mdp4_kms->base.base;
 	kms = priv->kms;
 
 	mdp4_kms->dev = dev;
 
-	mdp4_kms->mmio = msm_ioremap(pdev, NULL);
-	if (IS_ERR(mdp4_kms->mmio)) {
-		ret = PTR_ERR(mdp4_kms->mmio);
-		goto fail;
-	}
-
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		ret = irq;
-		goto fail;
-	}
-
-	kms->irq = irq;
-
-	/* NOTE: driver for this regulator still missing upstream.. use
-	 * _get_exclusive() and ignore the error if it does not exist
-	 * (and hope that the bootloader left it on for us)
-	 */
-	mdp4_kms->vdd = devm_regulator_get_exclusive(&pdev->dev, "vdd");
-	if (IS_ERR(mdp4_kms->vdd))
-		mdp4_kms->vdd = NULL;
-
 	if (mdp4_kms->vdd) {
 		ret = regulator_enable(mdp4_kms->vdd);
 		if (ret) {
@@ -438,24 +407,6 @@ static int mdp4_kms_init(struct drm_device *dev)
 		}
 	}
 
-	mdp4_kms->clk = devm_clk_get(&pdev->dev, "core_clk");
-	if (IS_ERR(mdp4_kms->clk)) {
-		DRM_DEV_ERROR(dev->dev, "failed to get core_clk\n");
-		ret = PTR_ERR(mdp4_kms->clk);
-		goto fail;
-	}
-
-	mdp4_kms->pclk = devm_clk_get(&pdev->dev, "iface_clk");
-	if (IS_ERR(mdp4_kms->pclk))
-		mdp4_kms->pclk = NULL;
-
-	mdp4_kms->axi_clk = devm_clk_get(&pdev->dev, "bus_clk");
-	if (IS_ERR(mdp4_kms->axi_clk)) {
-		DRM_DEV_ERROR(dev->dev, "failed to get axi_clk\n");
-		ret = PTR_ERR(mdp4_kms->axi_clk);
-		goto fail;
-	}
-
 	clk_set_rate(mdp4_kms->clk, max_clk);
 
 	read_mdp_hw_revision(mdp4_kms, &major, &minor);
@@ -470,10 +421,9 @@ static int mdp4_kms_init(struct drm_device *dev)
 	mdp4_kms->rev = minor;
 
 	if (mdp4_kms->rev >= 2) {
-		mdp4_kms->lut_clk = devm_clk_get(&pdev->dev, "lut_clk");
-		if (IS_ERR(mdp4_kms->lut_clk)) {
+		if (!mdp4_kms->lut_clk) {
 			DRM_DEV_ERROR(dev->dev, "failed to get lut_clk\n");
-			ret = PTR_ERR(mdp4_kms->lut_clk);
+			ret = -ENODEV;
 			goto fail;
 		}
 		clk_set_rate(mdp4_kms->lut_clk, max_clk);
@@ -551,20 +501,64 @@ fail:
 }
 
 static const struct dev_pm_ops mdp4_pm_ops = {
-	.prepare = msm_pm_prepare,
-	.complete = msm_pm_complete,
+	.prepare = msm_kms_pm_prepare,
+	.complete = msm_kms_pm_complete,
 };
 
 static int mdp4_probe(struct platform_device *pdev)
 {
-	return msm_drv_probe(&pdev->dev, mdp4_kms_init);
+	struct device *dev = &pdev->dev;
+	struct mdp4_kms *mdp4_kms;
+	int irq;
+
+	mdp4_kms = devm_kzalloc(dev, sizeof(*mdp4_kms), GFP_KERNEL);
+	if (!mdp4_kms)
+		return dev_err_probe(dev, -ENOMEM, "failed to allocate kms\n");
+
+	mdp4_kms->mmio = msm_ioremap(pdev, NULL);
+	if (IS_ERR(mdp4_kms->mmio))
+		return PTR_ERR(mdp4_kms->mmio);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return dev_err_probe(dev, irq, "failed to get irq\n");
+
+	mdp4_kms->base.base.irq = irq;
+
+	/* NOTE: driver for this regulator still missing upstream.. use
+	 * _get_exclusive() and ignore the error if it does not exist
+	 * (and hope that the bootloader left it on for us)
+	 */
+	mdp4_kms->vdd = devm_regulator_get_exclusive(&pdev->dev, "vdd");
+	if (IS_ERR(mdp4_kms->vdd))
+		mdp4_kms->vdd = NULL;
+
+	mdp4_kms->clk = devm_clk_get(&pdev->dev, "core_clk");
+	if (IS_ERR(mdp4_kms->clk))
+		return dev_err_probe(dev, PTR_ERR(mdp4_kms->clk), "failed to get core_clk\n");
+
+	mdp4_kms->pclk = devm_clk_get(&pdev->dev, "iface_clk");
+	if (IS_ERR(mdp4_kms->pclk))
+		mdp4_kms->pclk = NULL;
+
+	mdp4_kms->axi_clk = devm_clk_get(&pdev->dev, "bus_clk");
+	if (IS_ERR(mdp4_kms->axi_clk))
+		return dev_err_probe(dev, PTR_ERR(mdp4_kms->axi_clk), "failed to get axi_clk\n");
+
+	/*
+	 * This is required for revn >= 2. Handle errors here and let the kms
+	 * init bail out if the clock is not provided.
+	 */
+	mdp4_kms->lut_clk = devm_clk_get_optional(&pdev->dev, "lut_clk");
+	if (IS_ERR(mdp4_kms->lut_clk))
+		return dev_err_probe(dev, PTR_ERR(mdp4_kms->lut_clk), "failed to get lut_clk\n");
+
+	return msm_drv_probe(&pdev->dev, mdp4_kms_init, &mdp4_kms->base.base);
 }
 
-static int mdp4_remove(struct platform_device *pdev)
+static void mdp4_remove(struct platform_device *pdev)
 {
 	component_master_del(&pdev->dev, &msm_drm_ops);
-
-	return 0;
 }
 
 static const struct of_device_id mdp4_dt_match[] = {
@@ -575,8 +569,8 @@ MODULE_DEVICE_TABLE(of, mdp4_dt_match);
 
 static struct platform_driver mdp4_platform_driver = {
 	.probe      = mdp4_probe,
-	.remove     = mdp4_remove,
-	.shutdown   = msm_drv_shutdown,
+	.remove_new = mdp4_remove,
+	.shutdown   = msm_kms_shutdown,
 	.driver     = {
 		.name   = "mdp4",
 		.of_match_table = mdp4_dt_match,
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 92bf9d949d..ec933d597e 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -554,20 +554,16 @@ static int mdp5_kms_init(struct drm_device *dev)
 	struct platform_device *pdev;
 	struct mdp5_kms *mdp5_kms;
 	struct mdp5_cfg *config;
-	struct msm_kms *kms;
+	struct msm_kms *kms = priv->kms;
 	struct msm_gem_address_space *aspace;
-	int irq, i, ret;
+	int i, ret;
 
 	ret = mdp5_init(to_platform_device(dev->dev), dev);
 	if (ret)
 		return ret;
 
-	/* priv->kms would have been populated by the MDP5 driver */
-	kms = priv->kms;
-	if (!kms)
-		return -ENOMEM;
-
 	mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
+
 	pdev = mdp5_kms->pdev;
 
 	ret = mdp_kms_init(&mdp5_kms->base, &kms_funcs);
@@ -576,15 +572,6 @@ static int mdp5_kms_init(struct drm_device *dev)
 		goto fail;
 	}
 
-	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
-	if (!irq) {
-		ret = -EINVAL;
-		DRM_DEV_ERROR(&pdev->dev, "failed to get irq\n");
-		goto fail;
-	}
-
-	kms->irq = irq;
-
 	config = mdp5_cfg_get_config(mdp5_kms->cfg);
 
 	/* make sure things are off before attaching iommu (bootloader could
@@ -787,60 +774,23 @@ static int interface_init(struct mdp5_kms *mdp5_kms)
 static int mdp5_init(struct platform_device *pdev, struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
-	struct mdp5_kms *mdp5_kms;
+	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(priv->kms));
 	struct mdp5_cfg *config;
 	u32 major, minor;
 	int ret;
 
-	mdp5_kms = devm_kzalloc(&pdev->dev, sizeof(*mdp5_kms), GFP_KERNEL);
-	if (!mdp5_kms) {
-		ret = -ENOMEM;
-		goto fail;
-	}
-
-	spin_lock_init(&mdp5_kms->resource_lock);
-
 	mdp5_kms->dev = dev;
-	mdp5_kms->pdev = pdev;
 
 	ret = mdp5_global_obj_init(mdp5_kms);
 	if (ret)
 		goto fail;
 
-	mdp5_kms->mmio = msm_ioremap(pdev, "mdp_phys");
-	if (IS_ERR(mdp5_kms->mmio)) {
-		ret = PTR_ERR(mdp5_kms->mmio);
-		goto fail;
-	}
-
-	/* mandatory clocks: */
-	ret = get_clk(pdev, &mdp5_kms->axi_clk, "bus", true);
-	if (ret)
-		goto fail;
-	ret = get_clk(pdev, &mdp5_kms->ahb_clk, "iface", true);
-	if (ret)
-		goto fail;
-	ret = get_clk(pdev, &mdp5_kms->core_clk, "core", true);
-	if (ret)
-		goto fail;
-	ret = get_clk(pdev, &mdp5_kms->vsync_clk, "vsync", true);
-	if (ret)
-		goto fail;
-
-	/* optional clocks: */
-	get_clk(pdev, &mdp5_kms->lut_clk, "lut", false);
-	get_clk(pdev, &mdp5_kms->tbu_clk, "tbu", false);
-	get_clk(pdev, &mdp5_kms->tbu_rt_clk, "tbu_rt", false);
-
 	/* we need to set a default rate before enabling.  Set a safe
 	 * rate first, then figure out hw revision, and then set a
 	 * more optimal rate:
 	 */
 	clk_set_rate(mdp5_kms->core_clk, 200000000);
 
-	/* set uninit-ed kms */
-	priv->kms = &mdp5_kms->base.base;
-
 	pm_runtime_enable(&pdev->dev);
 	mdp5_kms->rpm_enabled = true;
 
@@ -894,8 +844,7 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev)
 
 	return 0;
 fail:
-	if (mdp5_kms)
-		mdp5_destroy(mdp5_kms);
+	mdp5_destroy(mdp5_kms);
 	return ret;
 }
 
@@ -931,22 +880,59 @@ static int mdp5_setup_interconnect(struct platform_device *pdev)
 
 static int mdp5_dev_probe(struct platform_device *pdev)
 {
-	int ret;
+	struct mdp5_kms *mdp5_kms;
+	int ret, irq;
 
 	DBG("");
 
+	mdp5_kms = devm_kzalloc(&pdev->dev, sizeof(*mdp5_kms), GFP_KERNEL);
+	if (!mdp5_kms)
+		return -ENOMEM;
+
 	ret = mdp5_setup_interconnect(pdev);
 	if (ret)
 		return ret;
 
-	return msm_drv_probe(&pdev->dev, mdp5_kms_init);
+	mdp5_kms->pdev = pdev;
+
+	spin_lock_init(&mdp5_kms->resource_lock);
+
+	mdp5_kms->mmio = msm_ioremap(pdev, "mdp_phys");
+	if (IS_ERR(mdp5_kms->mmio))
+		return PTR_ERR(mdp5_kms->mmio);
+
+	/* mandatory clocks: */
+	ret = get_clk(pdev, &mdp5_kms->axi_clk, "bus", true);
+	if (ret)
+		return ret;
+	ret = get_clk(pdev, &mdp5_kms->ahb_clk, "iface", true);
+	if (ret)
+		return ret;
+	ret = get_clk(pdev, &mdp5_kms->core_clk, "core", true);
+	if (ret)
+		return ret;
+	ret = get_clk(pdev, &mdp5_kms->vsync_clk, "vsync", true);
+	if (ret)
+		return ret;
+
+	/* optional clocks: */
+	get_clk(pdev, &mdp5_kms->lut_clk, "lut", false);
+	get_clk(pdev, &mdp5_kms->tbu_clk, "tbu", false);
+	get_clk(pdev, &mdp5_kms->tbu_rt_clk, "tbu_rt", false);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return dev_err_probe(&pdev->dev, irq, "failed to get irq\n");
+
+	mdp5_kms->base.base.irq = irq;
+
+	return msm_drv_probe(&pdev->dev, mdp5_kms_init, &mdp5_kms->base.base);
 }
 
-static int mdp5_dev_remove(struct platform_device *pdev)
+static void mdp5_dev_remove(struct platform_device *pdev)
 {
 	DBG("");
 	component_master_del(&pdev->dev, &msm_drm_ops);
-	return 0;
 }
 
 static __maybe_unused int mdp5_runtime_suspend(struct device *dev)
@@ -973,8 +959,8 @@ static __maybe_unused int mdp5_runtime_resume(struct device *dev)
 
 static const struct dev_pm_ops mdp5_pm_ops = {
 	SET_RUNTIME_PM_OPS(mdp5_runtime_suspend, mdp5_runtime_resume, NULL)
-	.prepare = msm_pm_prepare,
-	.complete = msm_pm_complete,
+	.prepare = msm_kms_pm_prepare,
+	.complete = msm_kms_pm_complete,
 };
 
 static const struct of_device_id mdp5_dt_match[] = {
@@ -987,8 +973,8 @@ MODULE_DEVICE_TABLE(of, mdp5_dt_match);
 
 static struct platform_driver mdp5_driver = {
 	.probe = mdp5_dev_probe,
-	.remove = mdp5_dev_remove,
-	.shutdown = msm_drv_shutdown,
+	.remove_new = mdp5_dev_remove,
+	.shutdown = msm_kms_shutdown,
 	.driver = {
 		.name = "msm_mdp",
 		.of_match_table = mdp5_dt_match,
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
index 56a3063545..b68682c1b5 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
@@ -379,7 +379,7 @@ struct mdp5_smp *mdp5_smp_init(struct mdp5_kms *mdp5_kms, const struct mdp5_smp_
 {
 	struct mdp5_smp_state *state;
 	struct mdp5_global_state *global_state;
-	struct mdp5_smp *smp = NULL;
+	struct mdp5_smp *smp;
 	int ret;
 
 	smp = kzalloc(sizeof(*smp), GFP_KERNEL);
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index 77a8d9366e..fb588fde29 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -135,11 +135,6 @@ static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl)
 	tbd = dp_link_get_test_bits_depth(ctrl->link,
 			ctrl->panel->dp_mode.bpp);
 
-	if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) {
-		pr_debug("BIT_DEPTH not set. Configure default\n");
-		tbd = DP_TEST_BIT_DEPTH_8;
-	}
-
 	config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT;
 
 	/* Num of Lanes */
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index 76f1395401..4f89c99395 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -88,7 +88,6 @@ struct dp_display_private {
 	bool audio_supported;
 
 	struct drm_device *drm_dev;
-	struct platform_device *pdev;
 	struct dentry *root;
 
 	struct dp_parser  *parser;
@@ -171,6 +170,11 @@ static const struct msm_dp_desc sm8350_dp_descs[] = {
 	{}
 };
 
+static const struct msm_dp_desc sm8650_dp_descs[] = {
+	{ .io_start = 0x0af54000, .id = MSM_DP_CONTROLLER_0, .connector_type = DRM_MODE_CONNECTOR_DisplayPort },
+	{}
+};
+
 static const struct of_device_id dp_dt_match[] = {
 	{ .compatible = "qcom,sc7180-dp", .data = &sc7180_dp_descs },
 	{ .compatible = "qcom,sc7280-dp", .data = &sc7280_dp_descs },
@@ -181,6 +185,7 @@ static const struct of_device_id dp_dt_match[] = {
 	{ .compatible = "qcom,sc8280xp-edp", .data = &sc8280xp_edp_descs },
 	{ .compatible = "qcom,sdm845-dp", .data = &sc7180_dp_descs },
 	{ .compatible = "qcom,sm8350-dp", .data = &sm8350_dp_descs },
+	{ .compatible = "qcom,sm8650-dp", .data = &sm8650_dp_descs },
 	{}
 };
 
@@ -341,21 +346,6 @@ static const struct component_ops dp_display_comp_ops = {
 	.unbind = dp_display_unbind,
 };
 
-static bool dp_display_is_ds_bridge(struct dp_panel *panel)
-{
-	return (panel->dpcd[DP_DOWNSTREAMPORT_PRESENT] &
-		DP_DWN_STRM_PORT_PRESENT);
-}
-
-static bool dp_display_is_sink_count_zero(struct dp_display_private *dp)
-{
-	drm_dbg_dp(dp->drm_dev, "present=%#x sink_count=%d\n",
-			dp->panel->dpcd[DP_DOWNSTREAMPORT_PRESENT],
-		dp->link->sink_count);
-	return dp_display_is_ds_bridge(dp->panel) &&
-		(dp->link->sink_count == 0);
-}
-
 static void dp_display_send_hpd_event(struct msm_dp *dp_display)
 {
 	struct dp_display_private *dp;
@@ -379,8 +369,14 @@ static int dp_display_send_hpd_notification(struct dp_display_private *dp,
 	}
 
 	/* reset video pattern flag on disconnect */
-	if (!hpd)
+	if (!hpd) {
 		dp->panel->video_test = false;
+		if (!dp->dp_display.is_edp)
+			drm_dp_set_subconnector_property(dp->dp_display.connector,
+							 connector_status_disconnected,
+							 dp->panel->dpcd,
+							 dp->panel->downstream_ports);
+	}
 
 	dp->dp_display.is_connected = hpd;
 
@@ -408,6 +404,12 @@ static int dp_display_process_hpd_high(struct dp_display_private *dp)
 
 	dp_link_process_request(dp->link);
 
+	if (!dp->dp_display.is_edp)
+		drm_dp_set_subconnector_property(dp->dp_display.connector,
+						 connector_status_connected,
+						 dp->panel->dpcd,
+						 dp->panel->downstream_ports);
+
 	edid = dp->panel->edid;
 
 	dp->dp_display.psr_supported = dp->panel->psr_cap.version && psr_enabled;
@@ -514,7 +516,7 @@ static int dp_display_handle_port_ststus_changed(struct dp_display_private *dp)
 {
 	int rc = 0;
 
-	if (dp_display_is_sink_count_zero(dp)) {
+	if (drm_dp_is_branch(dp->panel->dpcd) && dp->link->sink_count == 0) {
 		drm_dbg_dp(dp->drm_dev, "sink count is zero, nothing to do\n");
 		if (dp->hpd_state != ST_DISCONNECTED) {
 			dp->hpd_state = ST_DISCONNECT_PENDING;
@@ -603,7 +605,7 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data)
 		return 0;
 	}
 
-	ret = dp_display_usbpd_configure_cb(&dp->pdev->dev);
+	ret = dp_display_usbpd_configure_cb(&dp->dp_display.pdev->dev);
 	if (ret) {	/* link train failed */
 		dp->hpd_state = ST_DISCONNECTED;
 	} else {
@@ -651,7 +653,7 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data)
 		if (dp->link->sink_count == 0) {
 			dp_display_host_phy_exit(dp);
 		}
-		dp_display_notify_disconnect(&dp->pdev->dev);
+		dp_display_notify_disconnect(&dp->dp_display.pdev->dev);
 		mutex_unlock(&dp->event_mutex);
 		return 0;
 	} else if (state == ST_DISCONNECT_PENDING) {
@@ -661,7 +663,7 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data)
 		dp_ctrl_off_link(dp->ctrl);
 		dp_display_host_phy_exit(dp);
 		dp->hpd_state = ST_DISCONNECTED;
-		dp_display_notify_disconnect(&dp->pdev->dev);
+		dp_display_notify_disconnect(&dp->dp_display.pdev->dev);
 		mutex_unlock(&dp->event_mutex);
 		return 0;
 	}
@@ -670,7 +672,7 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data)
 	 * We don't need separate work for disconnect as
 	 * connect/attention interrupts are disabled
 	 */
-	dp_display_notify_disconnect(&dp->pdev->dev);
+	dp_display_notify_disconnect(&dp->dp_display.pdev->dev);
 
 	if (state == ST_DISPLAY_OFF) {
 		dp->hpd_state = ST_DISCONNECTED;
@@ -712,7 +714,7 @@ static int dp_irq_hpd_handle(struct dp_display_private *dp, u32 data)
 		return 0;
 	}
 
-	dp_display_usbpd_attention_cb(&dp->pdev->dev);
+	dp_display_usbpd_attention_cb(&dp->dp_display.pdev->dev);
 
 	drm_dbg_dp(dp->drm_dev, "After, type=%d hpd_state=%d\n",
 			dp->dp_display.connector_type, state);
@@ -733,12 +735,12 @@ static void dp_display_deinit_sub_modules(struct dp_display_private *dp)
 static int dp_init_sub_modules(struct dp_display_private *dp)
 {
 	int rc = 0;
-	struct device *dev = &dp->pdev->dev;
+	struct device *dev = &dp->dp_display.pdev->dev;
 	struct dp_panel_in panel_in = {
 		.dev = dev,
 	};
 
-	dp->parser = dp_parser_get(dp->pdev);
+	dp->parser = dp_parser_get(dp->dp_display.pdev);
 	if (IS_ERR(dp->parser)) {
 		rc = PTR_ERR(dp->parser);
 		DRM_ERROR("failed to initialize parser, rc = %d\n", rc);
@@ -799,7 +801,7 @@ static int dp_init_sub_modules(struct dp_display_private *dp)
 		goto error_ctrl;
 	}
 
-	dp->audio = dp_audio_get(dp->pdev, dp->panel, dp->catalog);
+	dp->audio = dp_audio_get(dp->dp_display.pdev, dp->panel, dp->catalog);
 	if (IS_ERR(dp->audio)) {
 		rc = PTR_ERR(dp->audio);
 		pr_err("failed to initialize audio, rc = %d\n", rc);
@@ -1205,7 +1207,7 @@ int dp_display_request_irq(struct msm_dp *dp_display)
 
 	dp = container_of(dp_display, struct dp_display_private, dp_display);
 
-	dp->irq = irq_of_parse_and_map(dp->pdev->dev.of_node, 0);
+	dp->irq = irq_of_parse_and_map(dp->dp_display.pdev->dev.of_node, 0);
 	if (!dp->irq) {
 		DRM_ERROR("failed to get irq\n");
 		return -EINVAL;
@@ -1261,7 +1263,7 @@ static int dp_display_probe(struct platform_device *pdev)
 	if (!desc)
 		return -EINVAL;
 
-	dp->pdev = pdev;
+	dp->dp_display.pdev = pdev;
 	dp->name = "drm_dp";
 	dp->id = desc->id;
 	dp->dp_display.connector_type = desc->connector_type;
@@ -1296,7 +1298,7 @@ static int dp_display_probe(struct platform_device *pdev)
 	return rc;
 }
 
-static int dp_display_remove(struct platform_device *pdev)
+static void dp_display_remove(struct platform_device *pdev)
 {
 	struct dp_display_private *dp = dev_get_dp_display_private(&pdev->dev);
 
@@ -1304,8 +1306,6 @@ static int dp_display_remove(struct platform_device *pdev)
 	dp_display_deinit_sub_modules(dp);
 
 	platform_set_drvdata(pdev, NULL);
-
-	return 0;
 }
 
 static int dp_pm_resume(struct device *dev)
@@ -1415,7 +1415,7 @@ static const struct dev_pm_ops dp_pm_ops = {
 
 static struct platform_driver dp_display_driver = {
 	.probe  = dp_display_probe,
-	.remove = dp_display_remove,
+	.remove_new = dp_display_remove,
 	.driver = {
 		.name = "msm-dp-display",
 		.of_match_table = dp_dt_match,
@@ -1469,7 +1469,7 @@ void msm_dp_debugfs_init(struct msm_dp *dp_display, struct drm_minor *minor)
 	int rc;
 
 	dp = container_of(dp_display, struct dp_display_private, dp_display);
-	dev = &dp->pdev->dev;
+	dev = &dp->dp_display.pdev->dev;
 
 	dp->debug = dp_debug_get(dev, dp->panel,
 					dp->link, dp->dp_display.connector,
@@ -1489,7 +1489,7 @@ static int dp_display_get_next_bridge(struct msm_dp *dp)
 	struct device *dev;
 
 	dp_priv = container_of(dp, struct dp_display_private, dp_display);
-	dev = &dp_priv->pdev->dev;
+	dev = &dp_priv->dp_display.pdev->dev;
 	aux_bus = of_get_child_by_name(dev->of_node, "aux-bus");
 
 	if (aux_bus && dp->is_edp) {
@@ -1541,7 +1541,6 @@ error:
 int msm_dp_modeset_init(struct msm_dp *dp_display, struct drm_device *dev,
 			struct drm_encoder *encoder)
 {
-	struct msm_drm_private *priv = dev->dev_private;
 	struct dp_display_private *dp_priv;
 	int ret;
 
@@ -1559,17 +1558,13 @@ int msm_dp_modeset_init(struct msm_dp *dp_display, struct drm_device *dev,
 	if (ret)
 		return ret;
 
-	dp_display->bridge = dp_bridge_init(dp_display, dev, encoder);
-	if (IS_ERR(dp_display->bridge)) {
-		ret = PTR_ERR(dp_display->bridge);
+	ret = dp_bridge_init(dp_display, dev, encoder);
+	if (ret) {
 		DRM_DEV_ERROR(dev->dev,
 			"failed to create dp bridge: %d\n", ret);
-		dp_display->bridge = NULL;
 		return ret;
 	}
 
-	priv->bridges[priv->num_bridges++] = dp_display->bridge;
-
 	dp_display->connector = dp_drm_connector_init(dp_display, encoder);
 	if (IS_ERR(dp_display->connector)) {
 		ret = PTR_ERR(dp_display->connector);
diff --git a/drivers/gpu/drm/msm/dp/dp_display.h b/drivers/gpu/drm/msm/dp/dp_display.h
index 1e9415ab15..f66cdbc357 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.h
+++ b/drivers/gpu/drm/msm/dp/dp_display.h
@@ -12,6 +12,7 @@
 
 struct msm_dp {
 	struct drm_device *drm_dev;
+	struct platform_device *pdev;
 	struct device *codec_dev;
 	struct drm_bridge *bridge;
 	struct drm_connector *connector;
diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c
index 785d766394..e3bdd7dd4c 100644
--- a/drivers/gpu/drm/msm/dp/dp_drm.c
+++ b/drivers/gpu/drm/msm/dp/dp_drm.c
@@ -272,7 +272,7 @@ static const struct drm_bridge_funcs edp_bridge_ops = {
 	.atomic_check = edp_bridge_atomic_check,
 };
 
-struct drm_bridge *dp_bridge_init(struct msm_dp *dp_display, struct drm_device *dev,
+int dp_bridge_init(struct msm_dp *dp_display, struct drm_device *dev,
 			struct drm_encoder *encoder)
 {
 	int rc;
@@ -281,7 +281,7 @@ struct drm_bridge *dp_bridge_init(struct msm_dp *dp_display, struct drm_device *
 
 	dp_bridge = devm_kzalloc(dev->dev, sizeof(*dp_bridge), GFP_KERNEL);
 	if (!dp_bridge)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	dp_bridge->dp_display = dp_display;
 
@@ -307,14 +307,18 @@ struct drm_bridge *dp_bridge_init(struct msm_dp *dp_display, struct drm_device *
 			DRM_BRIDGE_OP_MODES;
 	}
 
-	drm_bridge_add(bridge);
+	rc = devm_drm_bridge_add(dev->dev, bridge);
+	if (rc) {
+		DRM_ERROR("failed to add bridge, rc=%d\n", rc);
+
+		return rc;
+	}
 
 	rc = drm_bridge_attach(encoder, bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR);
 	if (rc) {
 		DRM_ERROR("failed to attach bridge, rc=%d\n", rc);
-		drm_bridge_remove(bridge);
 
-		return ERR_PTR(rc);
+		return rc;
 	}
 
 	if (dp_display->next_bridge) {
@@ -323,12 +327,13 @@ struct drm_bridge *dp_bridge_init(struct msm_dp *dp_display, struct drm_device *
 					DRM_BRIDGE_ATTACH_NO_CONNECTOR);
 		if (rc < 0) {
 			DRM_ERROR("failed to attach panel bridge: %d\n", rc);
-			drm_bridge_remove(bridge);
-			return ERR_PTR(rc);
+			return rc;
 		}
 	}
 
-	return bridge;
+	dp_display->bridge = bridge;
+
+	return 0;
 }
 
 /* connector initialization */
@@ -340,6 +345,9 @@ struct drm_connector *dp_drm_connector_init(struct msm_dp *dp_display, struct dr
 	if (IS_ERR(connector))
 		return connector;
 
+	if (!dp_display->is_edp)
+		drm_connector_attach_dp_subconnector_property(connector);
+
 	drm_connector_attach_encoder(connector, encoder);
 
 	return connector;
diff --git a/drivers/gpu/drm/msm/dp/dp_drm.h b/drivers/gpu/drm/msm/dp/dp_drm.h
index afe79b85e1..b3d684db23 100644
--- a/drivers/gpu/drm/msm/dp/dp_drm.h
+++ b/drivers/gpu/drm/msm/dp/dp_drm.h
@@ -20,7 +20,7 @@ struct msm_dp_bridge {
 #define to_dp_bridge(x)     container_of((x), struct msm_dp_bridge, bridge)
 
 struct drm_connector *dp_drm_connector_init(struct msm_dp *dp_display, struct drm_encoder *encoder);
-struct drm_bridge *dp_bridge_init(struct msm_dp *dp_display, struct drm_device *dev,
+int dp_bridge_init(struct msm_dp *dp_display, struct drm_device *dev,
 			struct drm_encoder *encoder);
 
 void dp_bridge_atomic_enable(struct drm_bridge *drm_bridge,
diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c
index 6375daaeb9..49dfac1fd1 100644
--- a/drivers/gpu/drm/msm/dp/dp_link.c
+++ b/drivers/gpu/drm/msm/dp/dp_link.c
@@ -7,6 +7,7 @@
 
 #include <drm/drm_print.h>
 
+#include "dp_reg.h"
 #include "dp_link.h"
 #include "dp_panel.h"
 
@@ -712,49 +713,17 @@ end:
 	return ret;
 }
 
-/**
- * dp_link_parse_sink_count() - parses the sink count
- * @dp_link: pointer to link module data
- *
- * Parses the DPCD to check if there is an update to the sink count
- * (Byte 0x200), and whether all the sink devices connected have Content
- * Protection enabled.
- */
-static int dp_link_parse_sink_count(struct dp_link *dp_link)
-{
-	ssize_t rlen;
-	bool cp_ready;
-
-	struct dp_link_private *link = container_of(dp_link,
-			struct dp_link_private, dp_link);
-
-	rlen = drm_dp_dpcd_readb(link->aux, DP_SINK_COUNT,
-				 &link->dp_link.sink_count);
-	if (rlen < 0) {
-		DRM_ERROR("sink count read failed. rlen=%zd\n", rlen);
-		return rlen;
-	}
-
-	cp_ready = link->dp_link.sink_count & DP_SINK_CP_READY;
-
-	link->dp_link.sink_count =
-		DP_GET_SINK_COUNT(link->dp_link.sink_count);
-
-	drm_dbg_dp(link->drm_dev, "sink_count = 0x%x, cp_ready = 0x%x\n",
-				link->dp_link.sink_count, cp_ready);
-	return 0;
-}
-
 static int dp_link_parse_sink_status_field(struct dp_link_private *link)
 {
-	int len = 0;
+	int len;
 
 	link->prev_sink_count = link->dp_link.sink_count;
-	len = dp_link_parse_sink_count(&link->dp_link);
+	len = drm_dp_read_sink_count(link->aux);
 	if (len < 0) {
 		DRM_ERROR("DP parse sink count failed\n");
 		return len;
 	}
+	link->dp_link.sink_count = len;
 
 	len = drm_dp_dpcd_read_link_status(link->aux,
 		link->link_status);
@@ -1114,7 +1083,7 @@ int dp_link_process_request(struct dp_link *dp_link)
 
 int dp_link_get_colorimetry_config(struct dp_link *dp_link)
 {
-	u32 cc;
+	u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB;
 	struct dp_link_private *link;
 
 	if (!dp_link) {
@@ -1128,10 +1097,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link)
 	 * Unless a video pattern CTS test is ongoing, use RGB_VESA
 	 * Only RGB_VESA and RGB_CEA supported for now
 	 */
-	if (dp_link_is_video_pattern_requested(link))
-		cc = link->dp_link.test_video.test_dyn_range;
-	else
-		cc = DP_TEST_DYNAMIC_RANGE_VESA;
+	if (dp_link_is_video_pattern_requested(link)) {
+		if (link->dp_link.test_video.test_dyn_range &
+					DP_TEST_DYNAMIC_RANGE_CEA)
+			cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB;
+	}
 
 	return cc;
 }
@@ -1211,6 +1181,9 @@ void dp_link_reset_phy_params_vx_px(struct dp_link *dp_link)
 u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
 {
 	u32 tbd;
+	struct dp_link_private *link;
+
+	link = container_of(dp_link, struct dp_link_private, dp_link);
 
 	/*
 	 * Few simplistic rules and assumptions made here:
@@ -1228,12 +1201,13 @@ u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
 		tbd = DP_TEST_BIT_DEPTH_10;
 		break;
 	default:
-		tbd = DP_TEST_BIT_DEPTH_UNKNOWN;
+		drm_dbg_dp(link->drm_dev, "bpp=%d not supported, use bpc=8\n",
+			   bpp);
+		tbd = DP_TEST_BIT_DEPTH_8;
 		break;
 	}
 
-	if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN)
-		tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
+	tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
 
 	return tbd;
 }
diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c
index 86a8e06c7a..127f6af995 100644
--- a/drivers/gpu/drm/msm/dp/dp_panel.c
+++ b/drivers/gpu/drm/msm/dp/dp_panel.c
@@ -17,7 +17,6 @@ struct dp_panel_private {
 	struct dp_link *link;
 	struct dp_catalog *catalog;
 	bool panel_on;
-	bool aux_cfg_update_done;
 };
 
 static void dp_panel_read_psr_cap(struct dp_panel_private *panel)
@@ -43,58 +42,24 @@ static void dp_panel_read_psr_cap(struct dp_panel_private *panel)
 
 static int dp_panel_read_dpcd(struct dp_panel *dp_panel)
 {
-	int rc = 0;
-	size_t len;
-	ssize_t rlen;
+	int rc;
 	struct dp_panel_private *panel;
 	struct dp_link_info *link_info;
-	u8 *dpcd, major = 0, minor = 0, temp;
-	u32 offset = DP_DPCD_REV;
+	u8 *dpcd, major, minor;
 
+	panel = container_of(dp_panel, struct dp_panel_private, dp_panel);
 	dpcd = dp_panel->dpcd;
+	rc = drm_dp_read_dpcd_caps(panel->aux, dpcd);
+	if (rc)
+		return rc;
 
-	panel = container_of(dp_panel, struct dp_panel_private, dp_panel);
 	link_info = &dp_panel->link_info;
-
-	rlen = drm_dp_dpcd_read(panel->aux, offset,
-			dpcd, (DP_RECEIVER_CAP_SIZE + 1));
-	if (rlen < (DP_RECEIVER_CAP_SIZE + 1)) {
-		DRM_ERROR("dpcd read failed, rlen=%zd\n", rlen);
-		if (rlen == -ETIMEDOUT)
-			rc = rlen;
-		else
-			rc = -EINVAL;
-
-		goto end;
-	}
-
-	temp = dpcd[DP_TRAINING_AUX_RD_INTERVAL];
-
-	/* check for EXTENDED_RECEIVER_CAPABILITY_FIELD_PRESENT */
-	if (temp & BIT(7)) {
-		drm_dbg_dp(panel->drm_dev,
-				"using EXTENDED_RECEIVER_CAPABILITY_FIELD\n");
-		offset = DPRX_EXTENDED_DPCD_FIELD;
-	}
-
-	rlen = drm_dp_dpcd_read(panel->aux, offset,
-		dpcd, (DP_RECEIVER_CAP_SIZE + 1));
-	if (rlen < (DP_RECEIVER_CAP_SIZE + 1)) {
-		DRM_ERROR("dpcd read failed, rlen=%zd\n", rlen);
-		if (rlen == -ETIMEDOUT)
-			rc = rlen;
-		else
-			rc = -EINVAL;
-
-		goto end;
-	}
-
 	link_info->revision = dpcd[DP_DPCD_REV];
 	major = (link_info->revision >> 4) & 0x0f;
 	minor = link_info->revision & 0x0f;
 
-	link_info->rate = drm_dp_bw_code_to_link_rate(dpcd[DP_MAX_LINK_RATE]);
-	link_info->num_lanes = dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK;
+	link_info->rate = drm_dp_max_link_rate(dpcd);
+	link_info->num_lanes = drm_dp_max_lane_count(dpcd);
 
 	/* Limit data lanes from data-lanes of endpoint property of dtsi */
 	if (link_info->num_lanes > dp_panel->max_dp_lanes)
@@ -111,25 +76,8 @@ static int dp_panel_read_dpcd(struct dp_panel *dp_panel)
 	if (drm_dp_enhanced_frame_cap(dpcd))
 		link_info->capabilities |= DP_LINK_CAP_ENHANCED_FRAMING;
 
-	dp_panel->dfp_present = dpcd[DP_DOWNSTREAMPORT_PRESENT];
-	dp_panel->dfp_present &= DP_DWN_STRM_PORT_PRESENT;
-
-	if (dp_panel->dfp_present && (dpcd[DP_DPCD_REV] > 0x10)) {
-		dp_panel->ds_port_cnt = dpcd[DP_DOWN_STREAM_PORT_COUNT];
-		dp_panel->ds_port_cnt &= DP_PORT_COUNT_MASK;
-		len = DP_DOWNSTREAM_PORTS * DP_DOWNSTREAM_CAP_SIZE;
-
-		rlen = drm_dp_dpcd_read(panel->aux,
-			DP_DOWNSTREAM_PORT_0, dp_panel->ds_cap_info, len);
-		if (rlen < len) {
-			DRM_ERROR("ds port status failed, rlen=%zd\n", rlen);
-			rc = -EINVAL;
-			goto end;
-		}
-	}
-
 	dp_panel_read_psr_cap(panel);
-end:
+
 	return rc;
 }
 
@@ -179,8 +127,8 @@ static int dp_panel_update_modes(struct drm_connector *connector,
 int dp_panel_read_sink_caps(struct dp_panel *dp_panel,
 	struct drm_connector *connector)
 {
-	int rc = 0, bw_code;
-	int rlen, count;
+	int rc, bw_code;
+	int count;
 	struct dp_panel_private *panel;
 
 	if (!dp_panel || !connector) {
@@ -205,20 +153,19 @@ int dp_panel_read_sink_caps(struct dp_panel *dp_panel,
 		return -EINVAL;
 	}
 
-	if (dp_panel->dfp_present) {
-		rlen = drm_dp_dpcd_read(panel->aux, DP_SINK_COUNT,
-				&count, 1);
-		if (rlen == 1) {
-			count = DP_GET_SINK_COUNT(count);
-			if (!count) {
-				DRM_ERROR("no downstream ports connected\n");
-				panel->link->sink_count = 0;
-				rc = -ENOTCONN;
-				goto end;
-			}
+	if (drm_dp_is_branch(dp_panel->dpcd)) {
+		count = drm_dp_read_sink_count(panel->aux);
+		if (!count) {
+			panel->link->sink_count = 0;
+			return -ENOTCONN;
 		}
 	}
 
+	rc = drm_dp_read_downstream_info(panel->aux, dp_panel->dpcd,
+					 dp_panel->downstream_ports);
+	if (rc)
+		return rc;
+
 	kfree(dp_panel->edid);
 	dp_panel->edid = NULL;
 
@@ -233,19 +180,6 @@ int dp_panel_read_sink_caps(struct dp_panel *dp_panel,
 		}
 	}
 
-	if (panel->aux_cfg_update_done) {
-		drm_dbg_dp(panel->drm_dev,
-				"read DPCD with updated AUX config\n");
-		rc = dp_panel_read_dpcd(dp_panel);
-		bw_code = drm_dp_link_rate_to_bw_code(dp_panel->link_info.rate);
-		if (rc || !is_link_rate_valid(bw_code) ||
-			!is_lane_count_valid(dp_panel->link_info.num_lanes)
-			|| (bw_code > dp_panel->max_bw_code)) {
-			DRM_ERROR("read dpcd failed %d\n", rc);
-			return rc;
-		}
-		panel->aux_cfg_update_done = false;
-	}
 end:
 	return rc;
 }
@@ -473,7 +407,6 @@ struct dp_panel *dp_panel_get(struct dp_panel_in *in)
 
 	dp_panel = &panel->dp_panel;
 	dp_panel->max_bw_code = DP_LINK_BW_8_1;
-	panel->aux_cfg_update_done = false;
 
 	return dp_panel;
 }
diff --git a/drivers/gpu/drm/msm/dp/dp_panel.h b/drivers/gpu/drm/msm/dp/dp_panel.h
index ed1030e17e..a0dfc579c5 100644
--- a/drivers/gpu/drm/msm/dp/dp_panel.h
+++ b/drivers/gpu/drm/msm/dp/dp_panel.h
@@ -13,11 +13,6 @@
 
 struct edid;
 
-#define DPRX_EXTENDED_DPCD_FIELD	0x2200
-
-#define DP_DOWNSTREAM_PORTS		4
-#define DP_DOWNSTREAM_CAP_SIZE		4
-
 struct dp_display_mode {
 	struct drm_display_mode drm_mode;
 	u32 capabilities;
@@ -40,10 +35,8 @@ struct dp_panel_psr {
 
 struct dp_panel {
 	/* dpcd raw data */
-	u8 dpcd[DP_RECEIVER_CAP_SIZE + 1];
-	u8 ds_cap_info[DP_DOWNSTREAM_PORTS * DP_DOWNSTREAM_CAP_SIZE];
-	u32 ds_port_cnt;
-	u32 dfp_present;
+	u8 dpcd[DP_RECEIVER_CAP_SIZE];
+	u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS];
 
 	struct dp_link_info link_info;
 	struct drm_dp_desc desc;
diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h
index ea85a691e7..78785ed4b4 100644
--- a/drivers/gpu/drm/msm/dp/dp_reg.h
+++ b/drivers/gpu/drm/msm/dp/dp_reg.h
@@ -143,6 +143,9 @@
 #define DP_MISC0_COLORIMETRY_CFG_SHIFT		(0x00000001)
 #define DP_MISC0_TEST_BITS_DEPTH_SHIFT		(0x00000005)
 
+#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB	(0)
+#define DP_MISC0_COLORIMERY_CFG_CEA_RGB		(0x04)
+
 #define REG_DP_VALID_BOUNDARY			(0x00000030)
 #define REG_DP_VALID_BOUNDARY_2			(0x00000034)
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c
index 32f965bacd..c6bd7bf156 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -17,6 +17,11 @@ struct drm_dsc_config *msm_dsi_get_dsc_config(struct msm_dsi *msm_dsi)
 	return msm_dsi_host_get_dsc_config(msm_dsi->host);
 }
 
+bool msm_dsi_wide_bus_enabled(struct msm_dsi *msm_dsi)
+{
+	return msm_dsi_host_is_wide_bus_enabled(msm_dsi->host);
+}
+
 static int dsi_get_phy(struct msm_dsi *msm_dsi)
 {
 	struct platform_device *pdev = msm_dsi->pdev;
@@ -162,14 +167,12 @@ static int dsi_dev_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int dsi_dev_remove(struct platform_device *pdev)
+static void dsi_dev_remove(struct platform_device *pdev)
 {
 	struct msm_dsi *msm_dsi = platform_get_drvdata(pdev);
 
 	DBG("");
 	dsi_destroy(msm_dsi);
-
-	return 0;
 }
 
 static const struct of_device_id dt_match[] = {
@@ -188,7 +191,7 @@ static const struct dev_pm_ops dsi_pm_ops = {
 
 static struct platform_driver dsi_driver = {
 	.probe = dsi_dev_probe,
-	.remove = dsi_dev_remove,
+	.remove_new = dsi_dev_remove,
 	.driver = {
 		.name = "msm_dsi",
 		.of_match_table = dt_match,
@@ -213,20 +216,14 @@ void __exit msm_dsi_unregister(void)
 int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 			 struct drm_encoder *encoder)
 {
-	struct msm_drm_private *priv = dev->dev_private;
 	int ret;
 
-	if (priv->num_bridges == ARRAY_SIZE(priv->bridges)) {
-		DRM_DEV_ERROR(dev->dev, "too many bridges\n");
-		return -ENOSPC;
-	}
-
 	msm_dsi->dev = dev;
 
 	ret = msm_dsi_host_modeset_init(msm_dsi->host, dev);
 	if (ret) {
 		DRM_DEV_ERROR(dev->dev, "failed to modeset init host: %d\n", ret);
-		goto fail;
+		return ret;
 	}
 
 	if (msm_dsi_is_bonded_dsi(msm_dsi) &&
@@ -240,32 +237,20 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 
 	msm_dsi->encoder = encoder;
 
-	msm_dsi->bridge = msm_dsi_manager_bridge_init(msm_dsi->id);
-	if (IS_ERR(msm_dsi->bridge)) {
-		ret = PTR_ERR(msm_dsi->bridge);
+	ret = msm_dsi_manager_bridge_init(msm_dsi);
+	if (ret) {
 		DRM_DEV_ERROR(dev->dev, "failed to create dsi bridge: %d\n", ret);
-		msm_dsi->bridge = NULL;
-		goto fail;
+		return ret;
 	}
 
 	ret = msm_dsi_manager_ext_bridge_init(msm_dsi->id);
 	if (ret) {
 		DRM_DEV_ERROR(dev->dev,
 			"failed to create dsi connector: %d\n", ret);
-		goto fail;
+		return ret;
 	}
 
-	priv->bridges[priv->num_bridges++]       = msm_dsi->bridge;
-
 	return 0;
-fail:
-	/* bridge/connector are normally destroyed by drm: */
-	if (msm_dsi->bridge) {
-		msm_dsi_manager_bridge_destroy(msm_dsi->bridge);
-		msm_dsi->bridge = NULL;
-	}
-
-	return ret;
 }
 
 void msm_dsi_snapshot(struct msm_disp_state *disp_state, struct msm_dsi *msm_dsi)
diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h
index 3b46617a59..28379b1af6 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.h
@@ -56,8 +56,7 @@ struct msm_dsi {
 };
 
 /* dsi manager */
-struct drm_bridge *msm_dsi_manager_bridge_init(u8 id);
-void msm_dsi_manager_bridge_destroy(struct drm_bridge *bridge);
+int msm_dsi_manager_bridge_init(struct msm_dsi *msm_dsi);
 int msm_dsi_manager_ext_bridge_init(u8 id);
 int msm_dsi_manager_cmd_xfer(int id, const struct mipi_dsi_msg *msg);
 bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 dma_base, u32 len);
@@ -135,6 +134,7 @@ int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_bonded_dsi);
 void msm_dsi_host_snapshot(struct msm_disp_state *disp_state, struct mipi_dsi_host *host);
 void msm_dsi_host_test_pattern_en(struct mipi_dsi_host *host);
 struct drm_dsc_config *msm_dsi_host_get_dsc_config(struct mipi_dsi_host *host);
+bool msm_dsi_host_is_wide_bus_enabled(struct mipi_dsi_host *host);
 
 /* dsi phy */
 struct msm_dsi_phy;
diff --git a/drivers/gpu/drm/msm/dsi/dsi.xml.h b/drivers/gpu/drm/msm/dsi/dsi.xml.h
index a4a1546011..2a7d980e12 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.xml.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.xml.h
@@ -664,6 +664,7 @@ static inline uint32_t DSI_CMD_MODE_MDP_CTRL2_INPUT_RGB_SWAP(enum dsi_rgb_swap v
 	return ((val) << DSI_CMD_MODE_MDP_CTRL2_INPUT_RGB_SWAP__SHIFT) & DSI_CMD_MODE_MDP_CTRL2_INPUT_RGB_SWAP__MASK;
 }
 #define DSI_CMD_MODE_MDP_CTRL2_BURST_MODE			0x00010000
+#define DSI_CMD_MODE_MDP_CTRL2_DATABUS_WIDEN			0x00100000
 
 #define REG_DSI_CMD_MODE_MDP_STREAM2_CTRL			0x000001b8
 #define DSI_CMD_MODE_MDP_STREAM2_CTRL_DATA_TYPE__MASK		0x0000003f
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 470866896b..deeecdfd6c 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -711,6 +711,15 @@ static void dsi_ctrl_disable(struct msm_dsi_host *msm_host)
 	dsi_write(msm_host, REG_DSI_CTRL, 0);
 }
 
+bool msm_dsi_host_is_wide_bus_enabled(struct mipi_dsi_host *host)
+{
+	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+
+	return msm_host->dsc &&
+		(msm_host->cfg_hnd->major == MSM_DSI_VER_MAJOR_6G &&
+		 msm_host->cfg_hnd->minor >= MSM_DSI_6G_VER_MINOR_V2_5_0);
+}
+
 static void dsi_ctrl_enable(struct msm_dsi_host *msm_host,
 			struct msm_dsi_phy_shared_timings *phy_shared_timings, struct msm_dsi_phy *phy)
 {
@@ -754,10 +763,16 @@ static void dsi_ctrl_enable(struct msm_dsi_host *msm_host,
 		data |= DSI_CMD_CFG1_INSERT_DCS_COMMAND;
 		dsi_write(msm_host, REG_DSI_CMD_CFG1, data);
 
-		if (msm_host->cfg_hnd->major == MSM_DSI_VER_MAJOR_6G &&
-		    msm_host->cfg_hnd->minor >= MSM_DSI_6G_VER_MINOR_V1_3) {
+		if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
 			data = dsi_read(msm_host, REG_DSI_CMD_MODE_MDP_CTRL2);
-			data |= DSI_CMD_MODE_MDP_CTRL2_BURST_MODE;
+
+			if (cfg_hnd->minor >= MSM_DSI_6G_VER_MINOR_V1_3)
+				data |= DSI_CMD_MODE_MDP_CTRL2_BURST_MODE;
+
+			/* TODO: Allow for video-mode support once tested/fixed */
+			if (msm_dsi_host_is_wide_bus_enabled(&msm_host->base))
+				data |= DSI_CMD_MODE_MDP_CTRL2_DATABUS_WIDEN;
+
 			dsi_write(msm_host, REG_DSI_CMD_MODE_MDP_CTRL2, data);
 		}
 	}
@@ -895,6 +910,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 	u32 hdisplay = mode->hdisplay;
 	u32 wc;
 	int ret;
+	bool wide_bus_enabled = msm_dsi_host_is_wide_bus_enabled(&msm_host->base);
 
 	DBG("");
 
@@ -915,6 +931,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 
 	if (msm_host->dsc) {
 		struct drm_dsc_config *dsc = msm_host->dsc;
+		u32 bytes_per_pclk;
 
 		/* update dsc params with timing params */
 		if (!dsc || !mode->hdisplay || !mode->vdisplay) {
@@ -938,7 +955,13 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 		 * pulse width same
 		 */
 		h_total -= hdisplay;
-		hdisplay = DIV_ROUND_UP(msm_dsc_get_bytes_per_line(msm_host->dsc), 3);
+		if (wide_bus_enabled && !(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO))
+			bytes_per_pclk = 6;
+		else
+			bytes_per_pclk = 3;
+
+		hdisplay = DIV_ROUND_UP(msm_dsc_get_bytes_per_line(msm_host->dsc), bytes_per_pclk);
+
 		h_total += hdisplay;
 		ha_end = ha_start + hdisplay;
 	}
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 28b8012a21..896f369fdd 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -466,9 +466,8 @@ static const struct drm_bridge_funcs dsi_mgr_bridge_funcs = {
 };
 
 /* initialize bridge */
-struct drm_bridge *msm_dsi_manager_bridge_init(u8 id)
+int msm_dsi_manager_bridge_init(struct msm_dsi *msm_dsi)
 {
-	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
 	struct drm_bridge *bridge = NULL;
 	struct dsi_bridge *dsi_bridge;
 	struct drm_encoder *encoder;
@@ -476,31 +475,27 @@ struct drm_bridge *msm_dsi_manager_bridge_init(u8 id)
 
 	dsi_bridge = devm_kzalloc(msm_dsi->dev->dev,
 				sizeof(*dsi_bridge), GFP_KERNEL);
-	if (!dsi_bridge) {
-		ret = -ENOMEM;
-		goto fail;
-	}
+	if (!dsi_bridge)
+		return -ENOMEM;
 
-	dsi_bridge->id = id;
+	dsi_bridge->id = msm_dsi->id;
 
 	encoder = msm_dsi->encoder;
 
 	bridge = &dsi_bridge->base;
 	bridge->funcs = &dsi_mgr_bridge_funcs;
 
-	drm_bridge_add(bridge);
+	ret = devm_drm_bridge_add(msm_dsi->dev->dev, bridge);
+	if (ret)
+		return ret;
 
 	ret = drm_bridge_attach(encoder, bridge, NULL, 0);
 	if (ret)
-		goto fail;
+		return ret;
 
-	return bridge;
+	msm_dsi->bridge = bridge;
 
-fail:
-	if (bridge)
-		msm_dsi_manager_bridge_destroy(bridge);
-
-	return ERR_PTR(ret);
+	return 0;
 }
 
 int msm_dsi_manager_ext_bridge_init(u8 id)
@@ -557,11 +552,6 @@ int msm_dsi_manager_ext_bridge_init(u8 id)
 	return 0;
 }
 
-void msm_dsi_manager_bridge_destroy(struct drm_bridge *bridge)
-{
-	drm_bridge_remove(bridge);
-}
-
 int msm_dsi_manager_cmd_xfer(int id, const struct mipi_dsi_msg *msg)
 {
 	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index b6314bb66d..e49ebd9f63 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -691,6 +691,10 @@ static int dsi_phy_driver_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, PTR_ERR(phy->ahb_clk),
 				     "Unable to get ahb clk\n");
 
+	ret = devm_pm_runtime_enable(&pdev->dev);
+	if (ret)
+		return ret;
+
 	/* PLL init will call into clk_register which requires
 	 * register access, so we need to enable power and ahb clock.
 	 */
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c
index 60509fb397..c8ebd75176 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.c
@@ -160,24 +160,16 @@ fail:
 int msm_hdmi_modeset_init(struct hdmi *hdmi,
 		struct drm_device *dev, struct drm_encoder *encoder)
 {
-	struct msm_drm_private *priv = dev->dev_private;
 	int ret;
 
-	if (priv->num_bridges == ARRAY_SIZE(priv->bridges)) {
-		DRM_DEV_ERROR(dev->dev, "too many bridges\n");
-		return -ENOSPC;
-	}
-
 	hdmi->dev = dev;
 	hdmi->encoder = encoder;
 
 	hdmi_audio_infoframe_init(&hdmi->audio.infoframe);
 
-	hdmi->bridge = msm_hdmi_bridge_init(hdmi);
-	if (IS_ERR(hdmi->bridge)) {
-		ret = PTR_ERR(hdmi->bridge);
+	ret = msm_hdmi_bridge_init(hdmi);
+	if (ret) {
 		DRM_DEV_ERROR(dev->dev, "failed to create HDMI bridge: %d\n", ret);
-		hdmi->bridge = NULL;
 		goto fail;
 	}
 
@@ -215,16 +207,9 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi,
 		goto fail;
 	}
 
-	priv->bridges[priv->num_bridges++]       = hdmi->bridge;
-
 	return 0;
 
 fail:
-	/* bridge is normally destroyed by drm: */
-	if (hdmi->bridge) {
-		msm_hdmi_bridge_destroy(hdmi->bridge);
-		hdmi->bridge = NULL;
-	}
 	if (hdmi->connector) {
 		hdmi->connector->funcs->destroy(hdmi->connector);
 		hdmi->connector = NULL;
@@ -395,6 +380,9 @@ static void msm_hdmi_unbind(struct device *dev, struct device *master,
 		if (priv->hdmi->audio_pdev)
 			platform_device_unregister(priv->hdmi->audio_pdev);
 
+		if (priv->hdmi->bridge)
+			msm_hdmi_hpd_disable(priv->hdmi);
+
 		msm_hdmi_destroy(priv->hdmi);
 		priv->hdmi = NULL;
 	}
@@ -551,15 +539,13 @@ err_put_phy:
 	return ret;
 }
 
-static int msm_hdmi_dev_remove(struct platform_device *pdev)
+static void msm_hdmi_dev_remove(struct platform_device *pdev)
 {
 	struct hdmi *hdmi = dev_get_drvdata(&pdev->dev);
 
 	component_del(&pdev->dev, &msm_hdmi_ops);
 
 	msm_hdmi_put_phy(hdmi);
-
-	return 0;
 }
 
 static const struct of_device_id msm_hdmi_dt_match[] = {
@@ -574,7 +560,7 @@ static const struct of_device_id msm_hdmi_dt_match[] = {
 
 static struct platform_driver msm_hdmi_driver = {
 	.probe = msm_hdmi_dev_probe,
-	.remove = msm_hdmi_dev_remove,
+	.remove_new = msm_hdmi_dev_remove,
 	.driver = {
 		.name = "hdmi_msm",
 		.of_match_table = msm_hdmi_dt_match,
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h
index e8dbee5063..ec57864403 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.h
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.h
@@ -224,14 +224,13 @@ void msm_hdmi_audio_set_sample_rate(struct hdmi *hdmi, int rate);
  * hdmi bridge:
  */
 
-struct drm_bridge *msm_hdmi_bridge_init(struct hdmi *hdmi);
-void msm_hdmi_bridge_destroy(struct drm_bridge *bridge);
+int msm_hdmi_bridge_init(struct hdmi *hdmi);
 
 void msm_hdmi_hpd_irq(struct drm_bridge *bridge);
 enum drm_connector_status msm_hdmi_bridge_detect(
 		struct drm_bridge *bridge);
 int msm_hdmi_hpd_enable(struct drm_bridge *bridge);
-void msm_hdmi_hpd_disable(struct hdmi_bridge *hdmi_bridge);
+void msm_hdmi_hpd_disable(struct hdmi *hdmi);
 
 /*
  * i2c adapter for ddc:
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c
index 9b1391d27e..f5e01471b0 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c
@@ -11,14 +11,6 @@
 #include "msm_kms.h"
 #include "hdmi.h"
 
-void msm_hdmi_bridge_destroy(struct drm_bridge *bridge)
-{
-	struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge);
-
-	msm_hdmi_hpd_disable(hdmi_bridge);
-	drm_bridge_remove(bridge);
-}
-
 static void msm_hdmi_power_on(struct drm_bridge *bridge)
 {
 	struct drm_device *dev = bridge->dev;
@@ -317,7 +309,7 @@ msm_hdmi_hotplug_work(struct work_struct *work)
 }
 
 /* initialize bridge */
-struct drm_bridge *msm_hdmi_bridge_init(struct hdmi *hdmi)
+int msm_hdmi_bridge_init(struct hdmi *hdmi)
 {
 	struct drm_bridge *bridge = NULL;
 	struct hdmi_bridge *hdmi_bridge;
@@ -325,10 +317,8 @@ struct drm_bridge *msm_hdmi_bridge_init(struct hdmi *hdmi)
 
 	hdmi_bridge = devm_kzalloc(hdmi->dev->dev,
 			sizeof(*hdmi_bridge), GFP_KERNEL);
-	if (!hdmi_bridge) {
-		ret = -ENOMEM;
-		goto fail;
-	}
+	if (!hdmi_bridge)
+		return -ENOMEM;
 
 	hdmi_bridge->hdmi = hdmi;
 	INIT_WORK(&hdmi_bridge->hpd_work, msm_hdmi_hotplug_work);
@@ -341,17 +331,15 @@ struct drm_bridge *msm_hdmi_bridge_init(struct hdmi *hdmi)
 		DRM_BRIDGE_OP_DETECT |
 		DRM_BRIDGE_OP_EDID;
 
-	drm_bridge_add(bridge);
+	ret = devm_drm_bridge_add(hdmi->dev->dev, bridge);
+	if (ret)
+		return ret;
 
 	ret = drm_bridge_attach(hdmi->encoder, bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR);
 	if (ret)
-		goto fail;
+		return ret;
 
-	return bridge;
+	hdmi->bridge = bridge;
 
-fail:
-	if (bridge)
-		msm_hdmi_bridge_destroy(bridge);
-
-	return ERR_PTR(ret);
+	return 0;
 }
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c b/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c
index bfa827b479..9ce0ffa354 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c
@@ -147,9 +147,8 @@ fail:
 	return ret;
 }
 
-void msm_hdmi_hpd_disable(struct hdmi_bridge *hdmi_bridge)
+void msm_hdmi_hpd_disable(struct hdmi *hdmi)
 {
-	struct hdmi *hdmi = hdmi_bridge->hdmi;
 	const struct hdmi_platform_config *config = hdmi->config;
 	struct device *dev = &hdmi->pdev->dev;
 	int ret;
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
index 3e00fb8190..88a3423b7f 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
@@ -177,11 +177,9 @@ static int msm_hdmi_phy_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int msm_hdmi_phy_remove(struct platform_device *pdev)
+static void msm_hdmi_phy_remove(struct platform_device *pdev)
 {
 	pm_runtime_disable(&pdev->dev);
-
-	return 0;
 }
 
 static const struct of_device_id msm_hdmi_phy_dt_match[] = {
@@ -200,7 +198,7 @@ static const struct of_device_id msm_hdmi_phy_dt_match[] = {
 
 static struct platform_driver msm_hdmi_phy_platform_driver = {
 	.probe      = msm_hdmi_phy_probe,
-	.remove     = msm_hdmi_phy_remove,
+	.remove_new = msm_hdmi_phy_remove,
 	.driver     = {
 		.name   = "msm_hdmi_phy",
 		.of_match_table = msm_hdmi_phy_dt_match,
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index a0a936f80a..04d304eed2 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -266,6 +266,9 @@ static int msm_fb_show(struct seq_file *m, void *arg)
 static struct drm_info_list msm_debugfs_list[] = {
 		{"gem", msm_gem_show},
 		{ "mm", msm_mm_show },
+};
+
+static struct drm_info_list msm_kms_debugfs_list[] = {
 		{ "fb", msm_fb_show },
 };
 
@@ -314,8 +317,13 @@ void msm_debugfs_init(struct drm_minor *minor)
 	debugfs_create_file("gpu", S_IRUSR, minor->debugfs_root,
 		dev, &msm_gpu_fops);
 
-	debugfs_create_file("kms", S_IRUSR, minor->debugfs_root,
-		dev, &msm_kms_fops);
+	if (priv->kms) {
+		drm_debugfs_create_files(msm_kms_debugfs_list,
+					 ARRAY_SIZE(msm_kms_debugfs_list),
+					 minor->debugfs_root, minor);
+		debugfs_create_file("kms", S_IRUSR, minor->debugfs_root,
+				    dev, &msm_kms_fops);
+	}
 
 	debugfs_create_u32("hangcheck_period_ms", 0600, minor->debugfs_root,
 		&priv->hangcheck_period);
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 4bd028fa75..3f217b5782 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -7,29 +7,17 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/fault-inject.h>
-#include <linux/kthread.h>
 #include <linux/of_address.h>
-#include <linux/sched/mm.h>
 #include <linux/uaccess.h>
-#include <uapi/linux/sched/types.h>
 
-#include <drm/drm_aperture.h>
-#include <drm/drm_bridge.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
-#include <drm/drm_prime.h>
 #include <drm/drm_of.h>
-#include <drm/drm_vblank.h>
 
-#include "disp/msm_disp_snapshot.h"
 #include "msm_drv.h"
 #include "msm_debugfs.h"
-#include "msm_fence.h"
-#include "msm_gem.h"
-#include "msm_gpu.h"
 #include "msm_kms.h"
-#include "msm_mmu.h"
 #include "adreno/adreno_gpu.h"
 
 /*
@@ -56,16 +44,6 @@
 
 static void msm_deinit_vram(struct drm_device *ddev);
 
-static const struct drm_mode_config_funcs mode_config_funcs = {
-	.fb_create = msm_framebuffer_create,
-	.atomic_check = msm_atomic_check,
-	.atomic_commit = drm_atomic_helper_commit,
-};
-
-static const struct drm_mode_config_helper_funcs mode_config_helper_funcs = {
-	.atomic_commit_tail = msm_atomic_commit_tail,
-};
-
 static char *vram = "16m";
 MODULE_PARM_DESC(vram, "Configure VRAM size (for devices without IOMMU/GPUMMU)");
 module_param(vram, charp, 0);
@@ -83,125 +61,11 @@ DECLARE_FAULT_ATTR(fail_gem_alloc);
 DECLARE_FAULT_ATTR(fail_gem_iova);
 #endif
 
-static irqreturn_t msm_irq(int irq, void *arg)
-{
-	struct drm_device *dev = arg;
-	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-
-	BUG_ON(!kms);
-
-	return kms->funcs->irq(kms);
-}
-
-static void msm_irq_preinstall(struct drm_device *dev)
-{
-	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-
-	BUG_ON(!kms);
-
-	kms->funcs->irq_preinstall(kms);
-}
-
-static int msm_irq_postinstall(struct drm_device *dev)
-{
-	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-
-	BUG_ON(!kms);
-
-	if (kms->funcs->irq_postinstall)
-		return kms->funcs->irq_postinstall(kms);
-
-	return 0;
-}
-
-static int msm_irq_install(struct drm_device *dev, unsigned int irq)
-{
-	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-	int ret;
-
-	if (irq == IRQ_NOTCONNECTED)
-		return -ENOTCONN;
-
-	msm_irq_preinstall(dev);
-
-	ret = request_irq(irq, msm_irq, 0, dev->driver->name, dev);
-	if (ret)
-		return ret;
-
-	kms->irq_requested = true;
-
-	ret = msm_irq_postinstall(dev);
-	if (ret) {
-		free_irq(irq, dev);
-		return ret;
-	}
-
-	return 0;
-}
-
-static void msm_irq_uninstall(struct drm_device *dev)
-{
-	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-
-	kms->funcs->irq_uninstall(kms);
-	if (kms->irq_requested)
-		free_irq(kms->irq, dev);
-}
-
-struct msm_vblank_work {
-	struct work_struct work;
-	struct drm_crtc *crtc;
-	bool enable;
-	struct msm_drm_private *priv;
-};
-
-static void vblank_ctrl_worker(struct work_struct *work)
-{
-	struct msm_vblank_work *vbl_work = container_of(work,
-						struct msm_vblank_work, work);
-	struct msm_drm_private *priv = vbl_work->priv;
-	struct msm_kms *kms = priv->kms;
-
-	if (vbl_work->enable)
-		kms->funcs->enable_vblank(kms, vbl_work->crtc);
-	else
-		kms->funcs->disable_vblank(kms,	vbl_work->crtc);
-
-	kfree(vbl_work);
-}
-
-static int vblank_ctrl_queue_work(struct msm_drm_private *priv,
-					struct drm_crtc *crtc, bool enable)
-{
-	struct msm_vblank_work *vbl_work;
-
-	vbl_work = kzalloc(sizeof(*vbl_work), GFP_ATOMIC);
-	if (!vbl_work)
-		return -ENOMEM;
-
-	INIT_WORK(&vbl_work->work, vblank_ctrl_worker);
-
-	vbl_work->crtc = crtc;
-	vbl_work->enable = enable;
-	vbl_work->priv = priv;
-
-	queue_work(priv->wq, &vbl_work->work);
-
-	return 0;
-}
-
 static int msm_drm_uninit(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct msm_drm_private *priv = platform_get_drvdata(pdev);
 	struct drm_device *ddev = priv->dev;
-	struct msm_kms *kms = priv->kms;
-	int i;
 
 	/*
 	 * Shutdown the hw if we're far enough along where things might be on.
@@ -212,7 +76,8 @@ static int msm_drm_uninit(struct device *dev)
 	 */
 	if (ddev->registered) {
 		drm_dev_unregister(ddev);
-		drm_atomic_helper_shutdown(ddev);
+		if (priv->kms)
+			drm_atomic_helper_shutdown(ddev);
 	}
 
 	/* We must cancel and cleanup any pending vblank enable/disable
@@ -222,36 +87,13 @@ static int msm_drm_uninit(struct device *dev)
 
 	flush_workqueue(priv->wq);
 
-	/* clean up event worker threads */
-	for (i = 0; i < priv->num_crtcs; i++) {
-		if (priv->event_thread[i].worker)
-			kthread_destroy_worker(priv->event_thread[i].worker);
-	}
-
 	msm_gem_shrinker_cleanup(ddev);
 
-	drm_kms_helper_poll_fini(ddev);
-
 	msm_perf_debugfs_cleanup(priv);
 	msm_rd_debugfs_cleanup(priv);
 
-	if (kms)
-		msm_disp_snapshot_destroy(ddev);
-
-	drm_mode_config_cleanup(ddev);
-
-	for (i = 0; i < priv->num_bridges; i++)
-		drm_bridge_remove(priv->bridges[i]);
-	priv->num_bridges = 0;
-
-	if (kms) {
-		pm_runtime_get_sync(dev);
-		msm_irq_uninstall(ddev);
-		pm_runtime_put_sync(dev);
-	}
-
-	if (kms && kms->funcs)
-		kms->funcs->destroy(kms);
+	if (priv->kms)
+		msm_drm_kms_uninit(dev);
 
 	msm_deinit_vram(ddev);
 
@@ -265,42 +107,6 @@ static int msm_drm_uninit(struct device *dev)
 	return 0;
 }
 
-struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev)
-{
-	struct msm_gem_address_space *aspace;
-	struct msm_mmu *mmu;
-	struct device *mdp_dev = dev->dev;
-	struct device *mdss_dev = mdp_dev->parent;
-	struct device *iommu_dev;
-
-	/*
-	 * IOMMUs can be a part of MDSS device tree binding, or the
-	 * MDP/DPU device.
-	 */
-	if (device_iommu_mapped(mdp_dev))
-		iommu_dev = mdp_dev;
-	else
-		iommu_dev = mdss_dev;
-
-	mmu = msm_iommu_new(iommu_dev, 0);
-	if (IS_ERR(mmu))
-		return ERR_CAST(mmu);
-
-	if (!mmu) {
-		drm_info(dev, "no IOMMU, fallback to phys contig buffers for scanout\n");
-		return NULL;
-	}
-
-	aspace = msm_gem_address_space_create(mmu, "mdp_kms",
-		0x1000, 0x100000000 - 0x1000);
-	if (IS_ERR(aspace)) {
-		dev_err(mdp_dev, "aspace create, error %pe\n", aspace);
-		mmu->funcs->destroy(mmu);
-	}
-
-	return aspace;
-}
-
 bool msm_use_mmu(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
@@ -406,8 +212,6 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 {
 	struct msm_drm_private *priv = dev_get_drvdata(dev);
 	struct drm_device *ddev;
-	struct msm_kms *kms;
-	struct drm_crtc *crtc;
 	int ret;
 
 	if (drm_firmware_drivers_only())
@@ -444,11 +248,15 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 	might_lock(&priv->lru.lock);
 	fs_reclaim_release(GFP_KERNEL);
 
-	drm_mode_config_init(ddev);
+	if (priv->kms_init) {
+		ret = drmm_mode_config_init(ddev);
+		if (ret)
+			goto err_destroy_wq;
+	}
 
 	ret = msm_init_vram(ddev);
 	if (ret)
-		goto err_cleanup_mode_config;
+		goto err_destroy_wq;
 
 	dma_set_max_seg_size(dev, UINT_MAX);
 
@@ -457,96 +265,33 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 	if (ret)
 		goto err_deinit_vram;
 
-	/* the fw fb could be anywhere in memory */
-	ret = drm_aperture_remove_framebuffers(drv);
+	ret = msm_gem_shrinker_init(ddev);
 	if (ret)
 		goto err_msm_uninit;
 
-	msm_gem_shrinker_init(ddev);
-
 	if (priv->kms_init) {
-		ret = priv->kms_init(ddev);
-		if (ret) {
-			DRM_DEV_ERROR(dev, "failed to load kms\n");
-			priv->kms = NULL;
+		ret = msm_drm_kms_init(dev, drv);
+		if (ret)
 			goto err_msm_uninit;
-		}
-		kms = priv->kms;
 	} else {
 		/* valid only for the dummy headless case, where of_node=NULL */
 		WARN_ON(dev->of_node);
-		kms = NULL;
-	}
-
-	/* Enable normalization of plane zpos */
-	ddev->mode_config.normalize_zpos = true;
-
-	if (kms) {
-		kms->dev = ddev;
-		ret = kms->funcs->hw_init(kms);
-		if (ret) {
-			DRM_DEV_ERROR(dev, "kms hw init failed: %d\n", ret);
-			goto err_msm_uninit;
-		}
-	}
-
-	drm_helper_move_panel_connectors_to_head(ddev);
-
-	ddev->mode_config.funcs = &mode_config_funcs;
-	ddev->mode_config.helper_private = &mode_config_helper_funcs;
-
-	drm_for_each_crtc(crtc, ddev) {
-		struct msm_drm_thread *ev_thread;
-
-		/* initialize event thread */
-		ev_thread = &priv->event_thread[drm_crtc_index(crtc)];
-		ev_thread->dev = ddev;
-		ev_thread->worker = kthread_create_worker(0, "crtc_event:%d", crtc->base.id);
-		if (IS_ERR(ev_thread->worker)) {
-			ret = PTR_ERR(ev_thread->worker);
-			DRM_DEV_ERROR(dev, "failed to create crtc_event kthread\n");
-			ev_thread->worker = NULL;
-			goto err_msm_uninit;
-		}
-
-		sched_set_fifo(ev_thread->worker->task);
-	}
-
-	ret = drm_vblank_init(ddev, priv->num_crtcs);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev, "failed to initialize vblank\n");
-		goto err_msm_uninit;
-	}
-
-	if (kms) {
-		pm_runtime_get_sync(dev);
-		ret = msm_irq_install(ddev, kms->irq);
-		pm_runtime_put_sync(dev);
-		if (ret < 0) {
-			DRM_DEV_ERROR(dev, "failed to install IRQ handler\n");
-			goto err_msm_uninit;
-		}
+		ddev->driver_features &= ~DRIVER_MODESET;
+		ddev->driver_features &= ~DRIVER_ATOMIC;
 	}
 
 	ret = drm_dev_register(ddev, 0);
 	if (ret)
 		goto err_msm_uninit;
 
-	if (kms) {
-		ret = msm_disp_snapshot_init(ddev);
-		if (ret)
-			DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret);
-	}
-	drm_mode_config_reset(ddev);
-
 	ret = msm_debugfs_late_init(ddev);
 	if (ret)
 		goto err_msm_uninit;
 
-	drm_kms_helper_poll_init(ddev);
-
-	if (kms)
+	if (priv->kms_init) {
+		drm_kms_helper_poll_init(ddev);
 		msm_fbdev_setup(ddev);
+	}
 
 	return 0;
 
@@ -557,8 +302,7 @@ err_msm_uninit:
 
 err_deinit_vram:
 	msm_deinit_vram(ddev);
-err_cleanup_mode_config:
-	drm_mode_config_cleanup(ddev);
+err_destroy_wq:
 	destroy_workqueue(priv->wq);
 err_put_dev:
 	drm_dev_put(ddev);
@@ -638,28 +382,6 @@ static void msm_postclose(struct drm_device *dev, struct drm_file *file)
 	context_close(ctx);
 }
 
-int msm_crtc_enable_vblank(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-	if (!kms)
-		return -ENXIO;
-	drm_dbg_vbl(dev, "crtc=%u", crtc->base.id);
-	return vblank_ctrl_queue_work(priv, crtc, true);
-}
-
-void msm_crtc_disable_vblank(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_kms *kms = priv->kms;
-	if (!kms)
-		return;
-	drm_dbg_vbl(dev, "crtc=%u", crtc->base.id);
-	vblank_ctrl_queue_work(priv, crtc, false);
-}
-
 /*
  * DRM ioctls:
  */
@@ -1102,33 +824,6 @@ static const struct drm_driver msm_driver = {
 	.patchlevel         = MSM_VERSION_PATCHLEVEL,
 };
 
-int msm_pm_prepare(struct device *dev)
-{
-	struct msm_drm_private *priv = dev_get_drvdata(dev);
-	struct drm_device *ddev = priv ? priv->dev : NULL;
-
-	if (!priv || !priv->kms)
-		return 0;
-
-	return drm_mode_config_helper_suspend(ddev);
-}
-
-void msm_pm_complete(struct device *dev)
-{
-	struct msm_drm_private *priv = dev_get_drvdata(dev);
-	struct drm_device *ddev = priv ? priv->dev : NULL;
-
-	if (!priv || !priv->kms)
-		return;
-
-	drm_mode_config_helper_resume(ddev);
-}
-
-static const struct dev_pm_ops msm_pm_ops = {
-	.prepare = msm_pm_prepare,
-	.complete = msm_pm_complete,
-};
-
 /*
  * Componentized driver support:
  */
@@ -1230,7 +925,8 @@ const struct component_master_ops msm_drm_ops = {
 };
 
 int msm_drv_probe(struct device *master_dev,
-	int (*kms_init)(struct drm_device *dev))
+	int (*kms_init)(struct drm_device *dev),
+	struct msm_kms *kms)
 {
 	struct msm_drm_private *priv;
 	struct component_match *match = NULL;
@@ -1240,6 +936,7 @@ int msm_drv_probe(struct device *master_dev,
 	if (!priv)
 		return -ENOMEM;
 
+	priv->kms = kms;
 	priv->kms_init = kms_init;
 	dev_set_drvdata(master_dev, priv);
 
@@ -1275,39 +972,19 @@ int msm_drv_probe(struct device *master_dev,
 
 static int msm_pdev_probe(struct platform_device *pdev)
 {
-	return msm_drv_probe(&pdev->dev, NULL);
+	return msm_drv_probe(&pdev->dev, NULL, NULL);
 }
 
-static int msm_pdev_remove(struct platform_device *pdev)
+static void msm_pdev_remove(struct platform_device *pdev)
 {
 	component_master_del(&pdev->dev, &msm_drm_ops);
-
-	return 0;
-}
-
-void msm_drv_shutdown(struct platform_device *pdev)
-{
-	struct msm_drm_private *priv = platform_get_drvdata(pdev);
-	struct drm_device *drm = priv ? priv->dev : NULL;
-
-	/*
-	 * Shutdown the hw if we're far enough along where things might be on.
-	 * If we run this too early, we'll end up panicking in any variety of
-	 * places. Since we don't register the drm device until late in
-	 * msm_drm_init, drm_dev->registered is used as an indicator that the
-	 * shutdown will be successful.
-	 */
-	if (drm && drm->registered && priv->kms)
-		drm_atomic_helper_shutdown(drm);
 }
 
 static struct platform_driver msm_platform_driver = {
 	.probe      = msm_pdev_probe,
-	.remove     = msm_pdev_remove,
-	.shutdown   = msm_drv_shutdown,
+	.remove_new = msm_pdev_remove,
 	.driver     = {
 		.name   = "msm",
-		.pm     = &msm_pm_ops,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 02fd6c7d0b..cd5bf658df 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -206,9 +206,6 @@ struct msm_drm_private {
 
 	struct msm_drm_thread event_thread[MAX_CRTCS];
 
-	unsigned int num_bridges;
-	struct drm_bridge *bridges[MAX_BRIDGES];
-
 	/* VRAM carveout, used when no IOMMU: */
 	struct {
 		unsigned long size;
@@ -221,7 +218,7 @@ struct msm_drm_private {
 	} vram;
 
 	struct notifier_block vmap_notifier;
-	struct shrinker shrinker;
+	struct shrinker *shrinker;
 
 	struct drm_atomic_state *pm_state;
 
@@ -283,7 +280,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 unsigned long msm_gem_shrinker_shrink(struct drm_device *dev, unsigned long nr_to_scan);
 #endif
 
-void msm_gem_shrinker_init(struct drm_device *dev);
+int msm_gem_shrinker_init(struct drm_device *dev);
 void msm_gem_shrinker_cleanup(struct drm_device *dev);
 
 struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj);
@@ -343,6 +340,7 @@ void msm_dsi_snapshot(struct msm_disp_state *disp_state, struct msm_dsi *msm_dsi
 bool msm_dsi_is_cmd_mode(struct msm_dsi *msm_dsi);
 bool msm_dsi_is_bonded_dsi(struct msm_dsi *msm_dsi);
 bool msm_dsi_is_master_dsi(struct msm_dsi *msm_dsi);
+bool msm_dsi_wide_bus_enabled(struct msm_dsi *msm_dsi);
 struct drm_dsc_config *msm_dsi_get_dsc_config(struct msm_dsi *msm_dsi);
 #else
 static inline void __init msm_dsi_register(void)
@@ -372,6 +370,10 @@ static inline bool msm_dsi_is_master_dsi(struct msm_dsi *msm_dsi)
 {
 	return false;
 }
+static inline bool msm_dsi_wide_bus_enabled(struct msm_dsi *msm_dsi)
+{
+	return false;
+}
 
 static inline struct drm_dsc_config *msm_dsi_get_dsc_config(struct msm_dsi *msm_dsi)
 {
@@ -561,12 +563,13 @@ static inline unsigned long timeout_to_jiffies(const ktime_t *timeout)
 
 extern const struct component_master_ops msm_drm_ops;
 
-int msm_pm_prepare(struct device *dev);
-void msm_pm_complete(struct device *dev);
+int msm_kms_pm_prepare(struct device *dev);
+void msm_kms_pm_complete(struct device *dev);
 
 int msm_drv_probe(struct device *dev,
-	int (*kms_init)(struct drm_device *dev));
-void msm_drv_shutdown(struct platform_device *pdev);
+	int (*kms_init)(struct drm_device *dev),
+	struct msm_kms *kms);
+void msm_kms_shutdown(struct platform_device *pdev);
 
 
 #endif /* __MSM_DRV_H__ */
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index 5f68e31a3e..0915f3b687 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -26,7 +26,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
 {
 	void *vaddr;
 
-	vaddr = msm_gem_get_vaddr(obj);
+	vaddr = msm_gem_get_vaddr_locked(obj);
 	if (IS_ERR(vaddr))
 		return PTR_ERR(vaddr);
 	iosys_map_set_vaddr(map, vaddr);
@@ -36,7 +36,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
 
 void msm_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map)
 {
-	msm_gem_put_vaddr(obj);
+	msm_gem_put_vaddr_locked(obj);
 }
 
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c
index f38296ad87..5a7d48c02c 100644
--- a/drivers/gpu/drm/msm/msm_gem_shrinker.c
+++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c
@@ -34,8 +34,7 @@ static bool can_block(struct shrink_control *sc)
 static unsigned long
 msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 {
-	struct msm_drm_private *priv =
-		container_of(shrinker, struct msm_drm_private, shrinker);
+	struct msm_drm_private *priv = shrinker->private_data;
 	unsigned count = priv->lru.dontneed.count;
 
 	if (can_swap())
@@ -100,8 +99,7 @@ active_evict(struct drm_gem_object *obj)
 static unsigned long
 msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 {
-	struct msm_drm_private *priv =
-		container_of(shrinker, struct msm_drm_private, shrinker);
+	struct msm_drm_private *priv = shrinker->private_data;
 	struct {
 		struct drm_gem_lru *lru;
 		bool (*shrink)(struct drm_gem_object *obj);
@@ -148,10 +146,11 @@ msm_gem_shrinker_shrink(struct drm_device *dev, unsigned long nr_to_scan)
 	struct shrink_control sc = {
 		.nr_to_scan = nr_to_scan,
 	};
-	int ret;
+	unsigned long ret = SHRINK_STOP;
 
 	fs_reclaim_acquire(GFP_KERNEL);
-	ret = msm_gem_shrinker_scan(&priv->shrinker, &sc);
+	if (priv->shrinker)
+		ret = msm_gem_shrinker_scan(priv->shrinker, &sc);
 	fs_reclaim_release(GFP_KERNEL);
 
 	return ret;
@@ -210,16 +209,24 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr)
  *
  * This function registers and sets up the msm shrinker.
  */
-void msm_gem_shrinker_init(struct drm_device *dev)
+int msm_gem_shrinker_init(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
-	priv->shrinker.count_objects = msm_gem_shrinker_count;
-	priv->shrinker.scan_objects = msm_gem_shrinker_scan;
-	priv->shrinker.seeks = DEFAULT_SEEKS;
-	WARN_ON(register_shrinker(&priv->shrinker, "drm-msm_gem"));
+
+	priv->shrinker = shrinker_alloc(0, "drm-msm_gem");
+	if (!priv->shrinker)
+		return -ENOMEM;
+
+	priv->shrinker->count_objects = msm_gem_shrinker_count;
+	priv->shrinker->scan_objects = msm_gem_shrinker_scan;
+	priv->shrinker->private_data = priv;
+
+	shrinker_register(priv->shrinker);
 
 	priv->vmap_notifier.notifier_call = msm_gem_shrinker_vmap;
 	WARN_ON(register_vmap_purge_notifier(&priv->vmap_notifier));
+
+	return 0;
 }
 
 /**
@@ -232,8 +239,8 @@ void msm_gem_shrinker_cleanup(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
 
-	if (priv->shrinker.nr_deferred) {
+	if (priv->shrinker) {
 		WARN_ON(unregister_vmap_purge_notifier(&priv->vmap_notifier));
-		unregister_shrinker(&priv->shrinker);
+		shrinker_free(priv->shrinker);
 	}
 }
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 7f64c66673..5c10b559a5 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -749,12 +749,14 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned long flags;
 
-	pm_runtime_get_sync(&gpu->pdev->dev);
+	WARN_ON(!mutex_is_locked(&gpu->lock));
 
-	mutex_lock(&gpu->lock);
+	pm_runtime_get_sync(&gpu->pdev->dev);
 
 	msm_gpu_hw_init(gpu);
 
+	submit->seqno = submit->hw_fence->seqno;
+
 	update_sw_cntrs(gpu);
 
 	/*
@@ -779,11 +781,8 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	gpu->funcs->submit(gpu, submit);
 	gpu->cur_ctx_seqno = submit->queue->ctx->seqno;
 
-	hangcheck_timer_reset(gpu);
-
-	mutex_unlock(&gpu->lock);
-
 	pm_runtime_put(&gpu->pdev->dev);
+	hangcheck_timer_reset(gpu);
 }
 
 /*
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 5cc8d358cc..d5512037c3 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -21,6 +21,8 @@ struct msm_iommu_pagetable {
 	struct msm_mmu base;
 	struct msm_mmu *parent;
 	struct io_pgtable_ops *pgtbl_ops;
+	const struct iommu_flush_ops *tlb;
+	struct device *iommu_dev;
 	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
 	phys_addr_t ttbr;
 	u32 asid;
@@ -201,11 +203,33 @@ static const struct msm_mmu_funcs pagetable_funcs = {
 
 static void msm_iommu_tlb_flush_all(void *cookie)
 {
+	struct msm_iommu_pagetable *pagetable = cookie;
+	struct adreno_smmu_priv *adreno_smmu;
+
+	if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
+		return;
+
+	adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
+
+	pagetable->tlb->tlb_flush_all((void *)adreno_smmu->cookie);
+
+	pm_runtime_put_autosuspend(pagetable->iommu_dev);
 }
 
 static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size,
 		size_t granule, void *cookie)
 {
+	struct msm_iommu_pagetable *pagetable = cookie;
+	struct adreno_smmu_priv *adreno_smmu;
+
+	if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
+		return;
+
+	adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
+
+	pagetable->tlb->tlb_flush_walk(iova, size, granule, (void *)adreno_smmu->cookie);
+
+	pm_runtime_put_autosuspend(pagetable->iommu_dev);
 }
 
 static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
@@ -213,7 +237,7 @@ static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
 {
 }
 
-static const struct iommu_flush_ops null_tlb_ops = {
+static const struct iommu_flush_ops tlb_ops = {
 	.tlb_flush_all = msm_iommu_tlb_flush_all,
 	.tlb_flush_walk = msm_iommu_tlb_flush_walk,
 	.tlb_add_page = msm_iommu_tlb_add_page,
@@ -254,10 +278,10 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
 
 	/* The incoming cfg will have the TTBR1 quirk enabled */
 	ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1;
-	ttbr0_cfg.tlb = &null_tlb_ops;
+	ttbr0_cfg.tlb = &tlb_ops;
 
 	pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1,
-		&ttbr0_cfg, iommu->domain);
+		&ttbr0_cfg, pagetable);
 
 	if (!pagetable->pgtbl_ops) {
 		kfree(pagetable);
@@ -279,6 +303,8 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
 
 	/* Needed later for TLB flush */
 	pagetable->parent = parent;
+	pagetable->tlb = ttbr1_cfg->tlb;
+	pagetable->iommu_dev = ttbr1_cfg->iommu_dev;
 	pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap;
 	pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr;
 
diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c
new file mode 100644
index 0000000000..84c21ec2ce
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_kms.c
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2016-2018, 2020-2021 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#include <linux/kthread.h>
+#include <linux/sched/mm.h>
+#include <uapi/linux/sched/types.h>
+
+#include <drm/drm_aperture.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_mode_config.h>
+#include <drm/drm_vblank.h>
+
+#include "disp/msm_disp_snapshot.h"
+#include "msm_drv.h"
+#include "msm_gem.h"
+#include "msm_kms.h"
+#include "msm_mmu.h"
+
+static const struct drm_mode_config_funcs mode_config_funcs = {
+	.fb_create = msm_framebuffer_create,
+	.atomic_check = msm_atomic_check,
+	.atomic_commit = drm_atomic_helper_commit,
+};
+
+static const struct drm_mode_config_helper_funcs mode_config_helper_funcs = {
+	.atomic_commit_tail = msm_atomic_commit_tail,
+};
+
+static irqreturn_t msm_irq(int irq, void *arg)
+{
+	struct drm_device *dev = arg;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	BUG_ON(!kms);
+
+	return kms->funcs->irq(kms);
+}
+
+static void msm_irq_preinstall(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	BUG_ON(!kms);
+
+	kms->funcs->irq_preinstall(kms);
+}
+
+static int msm_irq_postinstall(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	BUG_ON(!kms);
+
+	if (kms->funcs->irq_postinstall)
+		return kms->funcs->irq_postinstall(kms);
+
+	return 0;
+}
+
+static int msm_irq_install(struct drm_device *dev, unsigned int irq)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	int ret;
+
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
+	msm_irq_preinstall(dev);
+
+	ret = request_irq(irq, msm_irq, 0, dev->driver->name, dev);
+	if (ret)
+		return ret;
+
+	kms->irq_requested = true;
+
+	ret = msm_irq_postinstall(dev);
+	if (ret) {
+		free_irq(irq, dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void msm_irq_uninstall(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	kms->funcs->irq_uninstall(kms);
+	if (kms->irq_requested)
+		free_irq(kms->irq, dev);
+}
+
+struct msm_vblank_work {
+	struct work_struct work;
+	struct drm_crtc *crtc;
+	bool enable;
+	struct msm_drm_private *priv;
+};
+
+static void vblank_ctrl_worker(struct work_struct *work)
+{
+	struct msm_vblank_work *vbl_work = container_of(work,
+						struct msm_vblank_work, work);
+	struct msm_drm_private *priv = vbl_work->priv;
+	struct msm_kms *kms = priv->kms;
+
+	if (vbl_work->enable)
+		kms->funcs->enable_vblank(kms, vbl_work->crtc);
+	else
+		kms->funcs->disable_vblank(kms,	vbl_work->crtc);
+
+	kfree(vbl_work);
+}
+
+static int vblank_ctrl_queue_work(struct msm_drm_private *priv,
+				  struct drm_crtc *crtc, bool enable)
+{
+	struct msm_vblank_work *vbl_work;
+
+	vbl_work = kzalloc(sizeof(*vbl_work), GFP_ATOMIC);
+	if (!vbl_work)
+		return -ENOMEM;
+
+	INIT_WORK(&vbl_work->work, vblank_ctrl_worker);
+
+	vbl_work->crtc = crtc;
+	vbl_work->enable = enable;
+	vbl_work->priv = priv;
+
+	queue_work(priv->wq, &vbl_work->work);
+
+	return 0;
+}
+
+int msm_crtc_enable_vblank(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	if (!kms)
+		return -ENXIO;
+	drm_dbg_vbl(dev, "crtc=%u", crtc->base.id);
+	return vblank_ctrl_queue_work(priv, crtc, true);
+}
+
+void msm_crtc_disable_vblank(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	if (!kms)
+		return;
+	drm_dbg_vbl(dev, "crtc=%u", crtc->base.id);
+	vblank_ctrl_queue_work(priv, crtc, false);
+}
+
+struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev)
+{
+	struct msm_gem_address_space *aspace;
+	struct msm_mmu *mmu;
+	struct device *mdp_dev = dev->dev;
+	struct device *mdss_dev = mdp_dev->parent;
+	struct device *iommu_dev;
+
+	/*
+	 * IOMMUs can be a part of MDSS device tree binding, or the
+	 * MDP/DPU device.
+	 */
+	if (device_iommu_mapped(mdp_dev))
+		iommu_dev = mdp_dev;
+	else
+		iommu_dev = mdss_dev;
+
+	mmu = msm_iommu_new(iommu_dev, 0);
+	if (IS_ERR(mmu))
+		return ERR_CAST(mmu);
+
+	if (!mmu) {
+		drm_info(dev, "no IOMMU, fallback to phys contig buffers for scanout\n");
+		return NULL;
+	}
+
+	aspace = msm_gem_address_space_create(mmu, "mdp_kms",
+		0x1000, 0x100000000 - 0x1000);
+	if (IS_ERR(aspace)) {
+		dev_err(mdp_dev, "aspace create, error %pe\n", aspace);
+		mmu->funcs->destroy(mmu);
+	}
+
+	return aspace;
+}
+
+void msm_drm_kms_uninit(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct msm_drm_private *priv = platform_get_drvdata(pdev);
+	struct drm_device *ddev = priv->dev;
+	struct msm_kms *kms = priv->kms;
+	int i;
+
+	BUG_ON(!kms);
+
+	/* clean up event worker threads */
+	for (i = 0; i < priv->num_crtcs; i++) {
+		if (priv->event_thread[i].worker)
+			kthread_destroy_worker(priv->event_thread[i].worker);
+	}
+
+	drm_kms_helper_poll_fini(ddev);
+
+	msm_disp_snapshot_destroy(ddev);
+
+	pm_runtime_get_sync(dev);
+	msm_irq_uninstall(ddev);
+	pm_runtime_put_sync(dev);
+
+	if (kms && kms->funcs)
+		kms->funcs->destroy(kms);
+}
+
+int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv)
+{
+	struct msm_drm_private *priv = dev_get_drvdata(dev);
+	struct drm_device *ddev = priv->dev;
+	struct msm_kms *kms = priv->kms;
+	struct drm_crtc *crtc;
+	int ret;
+
+	/* the fw fb could be anywhere in memory */
+	ret = drm_aperture_remove_framebuffers(drv);
+	if (ret)
+		return ret;
+
+	ret = priv->kms_init(ddev);
+	if (ret) {
+		DRM_DEV_ERROR(dev, "failed to load kms\n");
+		priv->kms = NULL;
+		return ret;
+	}
+
+	/* Enable normalization of plane zpos */
+	ddev->mode_config.normalize_zpos = true;
+
+	ddev->mode_config.funcs = &mode_config_funcs;
+	ddev->mode_config.helper_private = &mode_config_helper_funcs;
+
+	kms->dev = ddev;
+	ret = kms->funcs->hw_init(kms);
+	if (ret) {
+		DRM_DEV_ERROR(dev, "kms hw init failed: %d\n", ret);
+		goto err_msm_uninit;
+	}
+
+	drm_helper_move_panel_connectors_to_head(ddev);
+
+	drm_for_each_crtc(crtc, ddev) {
+		struct msm_drm_thread *ev_thread;
+
+		/* initialize event thread */
+		ev_thread = &priv->event_thread[drm_crtc_index(crtc)];
+		ev_thread->dev = ddev;
+		ev_thread->worker = kthread_create_worker(0, "crtc_event:%d", crtc->base.id);
+		if (IS_ERR(ev_thread->worker)) {
+			ret = PTR_ERR(ev_thread->worker);
+			DRM_DEV_ERROR(dev, "failed to create crtc_event kthread\n");
+			ev_thread->worker = NULL;
+			goto err_msm_uninit;
+		}
+
+		sched_set_fifo(ev_thread->worker->task);
+	}
+
+	ret = drm_vblank_init(ddev, priv->num_crtcs);
+	if (ret < 0) {
+		DRM_DEV_ERROR(dev, "failed to initialize vblank\n");
+		goto err_msm_uninit;
+	}
+
+	pm_runtime_get_sync(dev);
+	ret = msm_irq_install(ddev, kms->irq);
+	pm_runtime_put_sync(dev);
+	if (ret < 0) {
+		DRM_DEV_ERROR(dev, "failed to install IRQ handler\n");
+		goto err_msm_uninit;
+	}
+
+	ret = msm_disp_snapshot_init(ddev);
+	if (ret)
+		DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret);
+
+	drm_mode_config_reset(ddev);
+
+	return 0;
+
+err_msm_uninit:
+	return ret;
+}
+
+int msm_kms_pm_prepare(struct device *dev)
+{
+	struct msm_drm_private *priv = dev_get_drvdata(dev);
+	struct drm_device *ddev = priv ? priv->dev : NULL;
+
+	if (!priv || !priv->kms)
+		return 0;
+
+	return drm_mode_config_helper_suspend(ddev);
+}
+
+void msm_kms_pm_complete(struct device *dev)
+{
+	struct msm_drm_private *priv = dev_get_drvdata(dev);
+	struct drm_device *ddev = priv ? priv->dev : NULL;
+
+	if (!priv || !priv->kms)
+		return;
+
+	drm_mode_config_helper_resume(ddev);
+}
+
+void msm_kms_shutdown(struct platform_device *pdev)
+{
+	struct msm_drm_private *priv = platform_get_drvdata(pdev);
+	struct drm_device *drm = priv ? priv->dev : NULL;
+
+	/*
+	 * Shutdown the hw if we're far enough along where things might be on.
+	 * If we run this too early, we'll end up panicking in any variety of
+	 * places. Since we don't register the drm device until late in
+	 * msm_drm_init, drm_dev->registered is used as an indicator that the
+	 * shutdown will be successful.
+	 */
+	if (drm && drm->registered && priv->kms)
+		drm_atomic_helper_shutdown(drm);
+}
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index 086a3f1ff9..44aa435d68 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -195,4 +195,7 @@ static inline void msm_kms_destroy(struct msm_kms *kms)
 	drm_for_each_crtc_reverse(crtc, dev) \
 		for_each_if (drm_crtc_mask(crtc) & (crtc_mask))
 
+int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv);
+void msm_drm_kms_uninit(struct device *dev);
+
 #endif /* __MSM_KMS_H__ */
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 348c66b146..29bb38f0bb 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -497,15 +497,13 @@ static int mdss_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int mdss_remove(struct platform_device *pdev)
+static void mdss_remove(struct platform_device *pdev)
 {
 	struct msm_mdss *mdss = platform_get_drvdata(pdev);
 
 	of_platform_depopulate(&pdev->dev);
 
 	msm_mdss_destroy(mdss);
-
-	return 0;
 }
 
 static const struct msm_mdss_data msm8998_data = {
@@ -547,7 +545,7 @@ static const struct msm_mdss_data sc8280xp_data = {
 	.ubwc_dec_version = UBWC_4_0,
 	.ubwc_swizzle = 6,
 	.ubwc_static = 1,
-	.highest_bank_bit = 2,
+	.highest_bank_bit = 3,
 	.macrotile_mode = 1,
 };
 
@@ -629,7 +627,7 @@ MODULE_DEVICE_TABLE(of, mdss_dt_match);
 
 static struct platform_driver mdss_platform_driver = {
 	.probe      = mdss_probe,
-	.remove     = mdss_remove,
+	.remove_new = mdss_remove,
 	.driver     = {
 		.name   = "msm-mdss",
 		.of_match_table = mdss_dt_match,
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 40c0bc35a4..a7e152f659 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -21,8 +21,6 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 
 	msm_fence_init(submit->hw_fence, fctx);
 
-	submit->seqno = submit->hw_fence->seqno;
-
 	mutex_lock(&priv->lru.lock);
 
 	for (i = 0; i < submit->nr_bos; i++) {
@@ -34,8 +32,13 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 
 	mutex_unlock(&priv->lru.lock);
 
+	/* TODO move submit path over to using a per-ring lock.. */
+	mutex_lock(&gpu->lock);
+
 	msm_gpu_submit(gpu, submit);
 
+	mutex_unlock(&gpu->lock);
+
 	return dma_fence_get(submit->hw_fence);
 }
 
@@ -95,8 +98,9 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 	sched_timeout = MAX_SCHEDULE_TIMEOUT;
 
 	ret = drm_sched_init(&ring->sched, &msm_sched_ops,
-			num_hw_submissions, 0, sched_timeout,
-			NULL, NULL, to_msm_bo(ring->bo)->name, gpu->dev->dev);
+			     DRM_SCHED_PRIORITY_COUNT,
+			     num_hw_submissions, 0, sched_timeout,
+			     NULL, NULL, to_msm_bo(ring->bo)->name, gpu->dev->dev);
 	if (ret) {
 		goto fail;
 	}
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h
index 698b333abc..0d6beb8cd3 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.h
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.h
@@ -30,6 +30,8 @@ struct msm_gpu_submit_stats {
 struct msm_rbmemptrs {
 	volatile uint32_t rptr;
 	volatile uint32_t fence;
+	/* Introduced on A7xx */
+	volatile uint32_t bv_fence;
 
 	volatile struct msm_gpu_submit_stats stats[MSM_GPU_SUBMIT_STATS_COUNT];
 	volatile u64 ttbr0;