Merge tag 'drm-msm-next-2019-11-05' of https://gitlab.freedesktop.org/drm/msm into drm-next

+ OCMEM support to enable the couple generations that had shared OCMEM
  rather than GMEM exclusively for the GPU (late a3xx and I think basically
  all of a4xx).  Bjorn and Brian decided to land this through the drm
  tree to avoid having to coordinate merge requests.
+ a510 support, and various associated display support
+ the usual misc cleanups and fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ <CAF6AEGv-JWswEJRxe5AmnGQO1SZnpxK05kO1E29K6UUzC9GMMw@mail.gmail.com

49 files changed, 1235 insertions, 307 deletions

diff --git a/Documentation/devicetree/bindings/display/msm/gmu.txt b/Documentation/devicetree/bindings/display/msm/gmu.txt
index 90af5b0a56a9..bf9c7a2a495c 100644
--- a/Documentation/devicetree/bindings/display/msm/gmu.txt
+++ b/Documentation/devicetree/bindings/display/msm/gmu.txt
@@ -31,6 +31,10 @@ Required properties:
 - iommus: phandle to the adreno iommu
 - operating-points-v2: phandle to the OPP operating points
 
+Optional properties:
+- sram: phandle to the On Chip Memory (OCMEM) that's present on some Snapdragon
+        SoCs. See Documentation/devicetree/bindings/sram/qcom,ocmem.yaml.
+
 Example:
 
 / {
@@ -63,3 +67,50 @@ Example:
 		operating-points-v2 = <&gmu_opp_table>;
 	};
 };
+
+a3xx example with OCMEM support:
+
+/ {
+	...
+
+	gpu: adreno@fdb00000 {
+		compatible = "qcom,adreno-330.2",
+		             "qcom,adreno";
+		reg = <0xfdb00000 0x10000>;
+		reg-names = "kgsl_3d0_reg_memory";
+		interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "kgsl_3d0_irq";
+		clock-names = "core",
+		              "iface",
+		              "mem_iface";
+		clocks = <&mmcc OXILI_GFX3D_CLK>,
+		         <&mmcc OXILICX_AHB_CLK>,
+		         <&mmcc OXILICX_AXI_CLK>;
+		sram = <&gmu_sram>;
+		power-domains = <&mmcc OXILICX_GDSC>;
+		operating-points-v2 = <&gpu_opp_table>;
+		iommus = <&gpu_iommu 0>;
+	};
+
+	ocmem@fdd00000 {
+		compatible = "qcom,msm8974-ocmem";
+
+		reg = <0xfdd00000 0x2000>,
+		      <0xfec00000 0x180000>;
+		reg-names = "ctrl",
+		             "mem";
+
+		clocks = <&rpmcc RPM_SMD_OCMEMGX_CLK>,
+		         <&mmcc OCMEMCX_OCMEMNOC_CLK>;
+		clock-names = "core",
+		              "iface";
+
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		gmu_sram: gmu-sram@0 {
+			reg = <0x0 0x100000>;
+			ranges = <0 0 0xfec00000 0x100000>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/display/msm/mdp5.txt b/Documentation/devicetree/bindings/display/msm/mdp5.txt
index 4e11338548aa..43d11279c925 100644
--- a/Documentation/devicetree/bindings/display/msm/mdp5.txt
+++ b/Documentation/devicetree/bindings/display/msm/mdp5.txt
@@ -76,6 +76,8 @@ Required properties:
 Optional properties:
 - clock-names: the following clocks are optional:
   * "lut"
+  * "tbu"
+  * "tbu_rt"
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/sram/qcom,ocmem.yaml b/Documentation/devicetree/bindings/sram/qcom,ocmem.yaml
new file mode 100644
index 000000000000..222990f9923c
--- /dev/null
+++ b/Documentation/devicetree/bindings/sram/qcom,ocmem.yaml
@@ -0,0 +1,96 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/sram/qcom,ocmem.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: On Chip Memory (OCMEM) that is present on some Qualcomm Snapdragon SoCs.
+
+maintainers:
+  - Brian Masney <masneyb@onstation.org>
+
+description: |
+  The On Chip Memory (OCMEM) is typically used by the GPU, camera/video, and
+  audio components on some Snapdragon SoCs.
+
+properties:
+  compatible:
+    const: qcom,msm8974-ocmem
+
+  reg:
+    items:
+      - description: Control registers
+      - description: OCMEM address range
+
+  reg-names:
+    items:
+      - const: ctrl
+      - const: mem
+
+  clocks:
+    items:
+      - description: Core clock
+      - description: Interface clock
+
+  clock-names:
+    items:
+      - const: core
+      - const: iface
+
+  '#address-cells':
+    const: 1
+
+  '#size-cells':
+    const: 1
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - clocks
+  - clock-names
+  - '#address-cells'
+  - '#size-cells'
+
+patternProperties:
+  "^.+-sram$":
+    type: object
+    description: A region of reserved memory.
+
+    properties:
+      reg:
+        maxItems: 1
+
+      ranges:
+        maxItems: 1
+
+    required:
+      - reg
+      - ranges
+
+examples:
+  - |
+      #include <dt-bindings/clock/qcom,rpmcc.h>
+      #include <dt-bindings/clock/qcom,mmcc-msm8974.h>
+
+      ocmem: ocmem@fdd00000 {
+        compatible = "qcom,msm8974-ocmem";
+
+        reg = <0xfdd00000 0x2000>,
+              <0xfec00000 0x180000>;
+        reg-names = "ctrl",
+                    "mem";
+
+        clocks = <&rpmcc RPM_SMD_OCMEMGX_CLK>,
+                 <&mmcc OCMEMCX_OCMEMNOC_CLK>;
+        clock-names = "core",
+                      "iface";
+
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        gmu-sram@0 {
+                reg = <0x0 0x100000>;
+                ranges = <0 0 0xfec00000 0x100000>;
+        };
+      };
diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c
index 215061c581e1..5d90b7f5ab5a 100644
--- a/drivers/firmware/qcom_scm-32.c
+++ b/drivers/firmware/qcom_scm-32.c
@@ -442,6 +442,41 @@ int __qcom_scm_hdcp_req(struct device *dev, struct qcom_scm_hdcp_req *req,
 		req, req_cnt * sizeof(*req), resp, sizeof(*resp));
 }
 
+int __qcom_scm_ocmem_lock(struct device *dev, u32 id, u32 offset, u32 size,
+			  u32 mode)
+{
+	struct ocmem_tz_lock {
+		__le32 id;
+		__le32 offset;
+		__le32 size;
+		__le32 mode;
+	} request;
+
+	request.id = cpu_to_le32(id);
+	request.offset = cpu_to_le32(offset);
+	request.size = cpu_to_le32(size);
+	request.mode = cpu_to_le32(mode);
+
+	return qcom_scm_call(dev, QCOM_SCM_OCMEM_SVC, QCOM_SCM_OCMEM_LOCK_CMD,
+			     &request, sizeof(request), NULL, 0);
+}
+
+int __qcom_scm_ocmem_unlock(struct device *dev, u32 id, u32 offset, u32 size)
+{
+	struct ocmem_tz_unlock {
+		__le32 id;
+		__le32 offset;
+		__le32 size;
+	} request;
+
+	request.id = cpu_to_le32(id);
+	request.offset = cpu_to_le32(offset);
+	request.size = cpu_to_le32(size);
+
+	return qcom_scm_call(dev, QCOM_SCM_OCMEM_SVC, QCOM_SCM_OCMEM_UNLOCK_CMD,
+			     &request, sizeof(request), NULL, 0);
+}
+
 void __qcom_scm_init(void)
 {
 }
@@ -582,7 +617,22 @@ int __qcom_scm_assign_mem(struct device *dev, phys_addr_t mem_region,
 int __qcom_scm_restore_sec_cfg(struct device *dev, u32 device_id,
 			       u32 spare)
 {
-	return -ENODEV;
+	struct msm_scm_sec_cfg {
+		__le32 id;
+		__le32 ctx_bank_num;
+	} cfg;
+	int ret, scm_ret = 0;
+
+	cfg.id = cpu_to_le32(device_id);
+	cfg.ctx_bank_num = cpu_to_le32(spare);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_MP, QCOM_SCM_RESTORE_SEC_CFG,
+			    &cfg, sizeof(cfg), &scm_ret, sizeof(scm_ret));
+
+	if (ret || scm_ret)
+		return ret ? ret : -EINVAL;
+
+	return 0;
 }
 
 int __qcom_scm_iommu_secure_ptbl_size(struct device *dev, u32 spare,
diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c
index 91d5ad7cf58b..c3a3d9874def 100644
--- a/drivers/firmware/qcom_scm-64.c
+++ b/drivers/firmware/qcom_scm-64.c
@@ -241,6 +241,18 @@ int __qcom_scm_hdcp_req(struct device *dev, struct qcom_scm_hdcp_req *req,
 	return ret;
 }
 
+int __qcom_scm_ocmem_lock(struct device *dev, uint32_t id, uint32_t offset,
+			  uint32_t size, uint32_t mode)
+{
+	return -ENOTSUPP;
+}
+
+int __qcom_scm_ocmem_unlock(struct device *dev, uint32_t id, uint32_t offset,
+			    uint32_t size)
+{
+	return -ENOTSUPP;
+}
+
 void __qcom_scm_init(void)
 {
 	u64 cmd;
diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c
index 4802ab170fe5..27c1d98a34e6 100644
--- a/drivers/firmware/qcom_scm.c
+++ b/drivers/firmware/qcom_scm.c
@@ -192,6 +192,46 @@ bool qcom_scm_pas_supported(u32 peripheral)
 EXPORT_SYMBOL(qcom_scm_pas_supported);
 
 /**
+ * qcom_scm_ocmem_lock_available() - is OCMEM lock/unlock interface available
+ */
+bool qcom_scm_ocmem_lock_available(void)
+{
+	return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_OCMEM_SVC,
+					    QCOM_SCM_OCMEM_LOCK_CMD);
+}
+EXPORT_SYMBOL(qcom_scm_ocmem_lock_available);
+
+/**
+ * qcom_scm_ocmem_lock() - call OCMEM lock interface to assign an OCMEM
+ * region to the specified initiator
+ *
+ * @id:     tz initiator id
+ * @offset: OCMEM offset
+ * @size:   OCMEM size
+ * @mode:   access mode (WIDE/NARROW)
+ */
+int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, u32 size,
+			u32 mode)
+{
+	return __qcom_scm_ocmem_lock(__scm->dev, id, offset, size, mode);
+}
+EXPORT_SYMBOL(qcom_scm_ocmem_lock);
+
+/**
+ * qcom_scm_ocmem_unlock() - call OCMEM unlock interface to release an OCMEM
+ * region from the specified initiator
+ *
+ * @id:     tz initiator id
+ * @offset: OCMEM offset
+ * @size:   OCMEM size
+ */
+int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, u32 size)
+{
+	return __qcom_scm_ocmem_unlock(__scm->dev, id, offset, size);
+}
+EXPORT_SYMBOL(qcom_scm_ocmem_unlock);
+
+/**
  * qcom_scm_pas_init_image() - Initialize peripheral authentication service
  *			       state machine for a given peripheral, using the
  *			       metadata
@@ -327,6 +367,19 @@ static const struct reset_control_ops qcom_scm_pas_reset_ops = {
 	.deassert = qcom_scm_pas_reset_deassert,
 };
 
+/**
+ * qcom_scm_restore_sec_cfg_available() - Check if secure environment
+ * supports restore security config interface.
+ *
+ * Return true if restore-cfg interface is supported, false if not.
+ */
+bool qcom_scm_restore_sec_cfg_available(void)
+{
+	return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_MP,
+					    QCOM_SCM_RESTORE_SEC_CFG);
+}
+EXPORT_SYMBOL(qcom_scm_restore_sec_cfg_available);
+
 int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare)
 {
 	return __qcom_scm_restore_sec_cfg(__scm->dev, device_id, spare);
diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h
index 99506bd873c0..ef293ee67ec1 100644
--- a/drivers/firmware/qcom_scm.h
+++ b/drivers/firmware/qcom_scm.h
@@ -42,6 +42,15 @@ extern int __qcom_scm_hdcp_req(struct device *dev,
 
 extern void __qcom_scm_init(void);
 
+#define QCOM_SCM_OCMEM_SVC			0xf
+#define QCOM_SCM_OCMEM_LOCK_CMD		0x1
+#define QCOM_SCM_OCMEM_UNLOCK_CMD		0x2
+
+extern int __qcom_scm_ocmem_lock(struct device *dev, u32 id, u32 offset,
+				 u32 size, u32 mode);
+extern int __qcom_scm_ocmem_unlock(struct device *dev, u32 id, u32 offset,
+				   u32 size);
+
 #define QCOM_SCM_SVC_PIL		0x2
 #define QCOM_SCM_PAS_INIT_IMAGE_CMD	0x1
 #define QCOM_SCM_PAS_MEM_SETUP_CMD	0x2
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index e9160ce39cbb..6deaa7d01654 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -7,6 +7,7 @@ config DRM_MSM
 	depends on OF && COMMON_CLK
 	depends on MMU
 	depends on INTERCONNECT || !INTERCONNECT
+	depends on QCOM_OCMEM || QCOM_OCMEM=n
 	select QCOM_MDT_LOADER if ARCH_QCOM
 	select REGULATOR
 	select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 5f7e98028eaf..7ad14937fcdf 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -6,10 +6,6 @@
  * Copyright (c) 2014 The Linux Foundation. All rights reserved.
  */
 
-#ifdef CONFIG_MSM_OCMEM
-#  include <mach/ocmem.h>
-#endif
-
 #include "a3xx_gpu.h"
 
 #define A3XX_INT0_MASK \
@@ -195,9 +191,9 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 		gpu_write(gpu, REG_A3XX_RBBM_GPR0_CTL, 0x00000000);
 
 	/* Set the OCMEM base address for A330, etc */
-	if (a3xx_gpu->ocmem_hdl) {
+	if (a3xx_gpu->ocmem.hdl) {
 		gpu_write(gpu, REG_A3XX_RB_GMEM_BASE_ADDR,
-			(unsigned int)(a3xx_gpu->ocmem_base >> 14));
+			(unsigned int)(a3xx_gpu->ocmem.base >> 14));
 	}
 
 	/* Turn on performance counters: */
@@ -318,10 +314,7 @@ static void a3xx_destroy(struct msm_gpu *gpu)
 
 	adreno_gpu_cleanup(adreno_gpu);
 
-#ifdef CONFIG_MSM_OCMEM
-	if (a3xx_gpu->ocmem_base)
-		ocmem_free(OCMEM_GRAPHICS, a3xx_gpu->ocmem_hdl);
-#endif
+	adreno_gpu_ocmem_cleanup(&a3xx_gpu->ocmem);
 
 	kfree(a3xx_gpu);
 }
@@ -494,17 +487,10 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 
 	/* if needed, allocate gmem: */
 	if (adreno_is_a330(adreno_gpu)) {
-#ifdef CONFIG_MSM_OCMEM
-		/* TODO this is different/missing upstream: */
-		struct ocmem_buf *ocmem_hdl =
-				ocmem_allocate(OCMEM_GRAPHICS, adreno_gpu->gmem);
-
-		a3xx_gpu->ocmem_hdl = ocmem_hdl;
-		a3xx_gpu->ocmem_base = ocmem_hdl->addr;
-		adreno_gpu->gmem = ocmem_hdl->len;
-		DBG("using %dK of OCMEM at 0x%08x", adreno_gpu->gmem / 1024,
-				a3xx_gpu->ocmem_base);
-#endif
+		ret = adreno_gpu_ocmem_init(&adreno_gpu->base.pdev->dev,
+					    adreno_gpu, &a3xx_gpu->ocmem);
+		if (ret)
+			goto fail;
 	}
 
 	if (!gpu->aspace) {
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h
index 5dc33e5ea53b..c555fb13e0d7 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h
@@ -19,8 +19,7 @@ struct a3xx_gpu {
 	struct adreno_gpu base;
 
 	/* if OCMEM is used for GMEM: */
-	uint32_t ocmem_base;
-	void *ocmem_hdl;
+	struct adreno_ocmem ocmem;
 };
 #define to_a3xx_gpu(x) container_of(x, struct a3xx_gpu, base)
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index ab2b752566d8..b01388a9e89e 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -2,9 +2,6 @@
 /* Copyright (c) 2014 The Linux Foundation. All rights reserved.
  */
 #include "a4xx_gpu.h"
-#ifdef CONFIG_MSM_OCMEM
-#  include <soc/qcom/ocmem.h>
-#endif
 
 #define A4XX_INT0_MASK \
 	(A4XX_INT0_RBBM_AHB_ERROR |        \
@@ -188,7 +185,7 @@ static int a4xx_hw_init(struct msm_gpu *gpu)
 			(1 << 30) | 0xFFFF);
 
 	gpu_write(gpu, REG_A4XX_RB_GMEM_BASE_ADDR,
-			(unsigned int)(a4xx_gpu->ocmem_base >> 14));
+			(unsigned int)(a4xx_gpu->ocmem.base >> 14));
 
 	/* Turn on performance counters: */
 	gpu_write(gpu, REG_A4XX_RBBM_PERFCTR_CTL, 0x01);
@@ -318,10 +315,7 @@ static void a4xx_destroy(struct msm_gpu *gpu)
 
 	adreno_gpu_cleanup(adreno_gpu);
 
-#ifdef CONFIG_MSM_OCMEM
-	if (a4xx_gpu->ocmem_base)
-		ocmem_free(OCMEM_GRAPHICS, a4xx_gpu->ocmem_hdl);
-#endif
+	adreno_gpu_ocmem_cleanup(&a4xx_gpu->ocmem);
 
 	kfree(a4xx_gpu);
 }
@@ -578,17 +572,10 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 
 	/* if needed, allocate gmem: */
 	if (adreno_is_a4xx(adreno_gpu)) {
-#ifdef CONFIG_MSM_OCMEM
-		/* TODO this is different/missing upstream: */
-		struct ocmem_buf *ocmem_hdl =
-				ocmem_allocate(OCMEM_GRAPHICS, adreno_gpu->gmem);
-
-		a4xx_gpu->ocmem_hdl = ocmem_hdl;
-		a4xx_gpu->ocmem_base = ocmem_hdl->addr;
-		adreno_gpu->gmem = ocmem_hdl->len;
-		DBG("using %dK of OCMEM at 0x%08x", adreno_gpu->gmem / 1024,
-				a4xx_gpu->ocmem_base);
-#endif
+		ret = adreno_gpu_ocmem_init(dev->dev, adreno_gpu,
+					    &a4xx_gpu->ocmem);
+		if (ret)
+			goto fail;
 	}
 
 	if (!gpu->aspace) {
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.h b/drivers/gpu/drm/msm/adreno/a4xx_gpu.h
index d506311ee240..a01448cba2ea 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.h
@@ -16,8 +16,7 @@ struct a4xx_gpu {
 	struct adreno_gpu base;
 
 	/* if OCMEM is used for GMEM: */
-	uint32_t ocmem_base;
-	void *ocmem_hdl;
+	struct adreno_ocmem ocmem;
 };
 #define to_a4xx_gpu(x) container_of(x, struct a4xx_gpu, base)
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index e9c55d1d6c04..b02e2042547f 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -353,6 +353,9 @@ static int a5xx_me_init(struct msm_gpu *gpu)
 		 * 2D mode 3 draw
 		 */
 		OUT_RING(ring, 0x0000000B);
+	} else if (adreno_is_a510(adreno_gpu)) {
+		/* Workaround for token and syncs */
+		OUT_RING(ring, 0x00000001);
 	} else {
 		/* No workarounds enabled */
 		OUT_RING(ring, 0x00000000);
@@ -568,15 +571,24 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 		0x00100000 + adreno_gpu->gmem - 1);
 	gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MAX_HI, 0x00000000);
 
-	gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x40);
-	if (adreno_is_a530(adreno_gpu))
-		gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40);
-	if (adreno_is_a540(adreno_gpu))
-		gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400);
-	gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x80000060);
-	gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x40201B16);
-
-	gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, (0x400 << 11 | 0x300 << 22));
+	if (adreno_is_a510(adreno_gpu)) {
+		gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x20);
+		gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x20);
+		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x40000030);
+		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x20100D0A);
+		gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL,
+			  (0x200 << 11 | 0x200 << 22));
+	} else {
+		gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x40);
+		if (adreno_is_a530(adreno_gpu))
+			gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40);
+		if (adreno_is_a540(adreno_gpu))
+			gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400);
+		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x80000060);
+		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x40201B16);
+		gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL,
+			  (0x400 << 11 | 0x300 << 22));
+	}
 
 	if (adreno_gpu->info->quirks & ADRENO_QUIRK_TWO_PASS_USE_WFI)
 		gpu_rmw(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0, (1 << 8));
@@ -589,6 +601,19 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	/* Enable ME/PFP split notification */
 	gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL1, 0xA6FFFFFF);
 
+	/*
+	 *  In A5x, CCU can send context_done event of a particular context to
+	 *  UCHE which ultimately reaches CP even when there is valid
+	 *  transaction of that context inside CCU. This can let CP to program
+	 *  config registers, which will make the "valid transaction" inside
+	 *  CCU to be interpreted differently. This can cause gpu fault. This
+	 *  bug is fixed in latest A510 revision. To enable this bug fix -
+	 *  bit[11] of RB_DBG_ECO_CNTL need to be set to 0, default is 1
+	 *  (disable). For older A510 version this bit is unused.
+	 */
+	if (adreno_is_a510(adreno_gpu))
+		gpu_rmw(gpu, REG_A5XX_RB_DBG_ECO_CNTL, (1 << 11), 0);
+
 	/* Enable HWCG */
 	a5xx_set_hwcg(gpu, true);
 
@@ -635,7 +660,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	/* UCHE */
 	gpu_write(gpu, REG_A5XX_CP_PROTECT(16), ADRENO_PROTECT_RW(0xE80, 16));
 
-	if (adreno_is_a530(adreno_gpu))
+	if (adreno_is_a530(adreno_gpu) || adreno_is_a510(adreno_gpu))
 		gpu_write(gpu, REG_A5XX_CP_PROTECT(17),
 			ADRENO_PROTECT_RW(0x10000, 0x8000));
 
@@ -679,7 +704,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 
 	a5xx_preempt_hw_init(gpu);
 
-	a5xx_gpmu_ucode_init(gpu);
+	if (!adreno_is_a510(adreno_gpu))
+		a5xx_gpmu_ucode_init(gpu);
 
 	ret = a5xx_ucode_init(gpu);
 	if (ret)
@@ -712,7 +738,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	}
 
 	/*
-	 * Try to load a zap shader into the secure world. If successful
+	 * If the chip that we are using does support loading one, then
+	 * try to load a zap shader into the secure world. If successful
 	 * we can use the CP to switch out of secure mode. If not then we
 	 * have no resource but to try to switch ourselves out manually. If we
 	 * guessed wrong then access to the RBBM_SECVID_TRUST_CNTL register will
@@ -1066,6 +1093,7 @@ static void a5xx_dump(struct msm_gpu *gpu)
 
 static int a5xx_pm_resume(struct msm_gpu *gpu)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int ret;
 
 	/* Turn on the core power */
@@ -1073,6 +1101,15 @@ static int a5xx_pm_resume(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	if (adreno_is_a510(adreno_gpu)) {
+		/* Halt the sp_input_clk at HM level */
+		gpu_write(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0x00000055);
+		a5xx_set_hwcg(gpu, true);
+		/* Turn on sp_input_clk at HM level */
+		gpu_rmw(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0xff, 0);
+		return 0;
+	}
+
 	/* Turn the RBCCU domain first to limit the chances of voltage droop */
 	gpu_write(gpu, REG_A5XX_GPMU_RBCCU_POWER_CNTL, 0x778000);
 
@@ -1101,9 +1138,17 @@ static int a5xx_pm_resume(struct msm_gpu *gpu)
 
 static int a5xx_pm_suspend(struct msm_gpu *gpu)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	u32 mask = 0xf;
+
+	/* A510 has 3 XIN ports in VBIF */
+	if (adreno_is_a510(adreno_gpu))
+		mask = 0x7;
+
 	/* Clear the VBIF pipe before shutting down */
-	gpu_write(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL0, 0xF);
-	spin_until((gpu_read(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL1) & 0xF) == 0xF);
+	gpu_write(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL0, mask);
+	spin_until((gpu_read(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL1) &
+				mask) == mask);
 
 	gpu_write(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL0, 0);
 
@@ -1289,7 +1334,7 @@ static void a5xx_gpu_state_destroy(struct kref *kref)
 	kfree(a5xx_state);
 }
 
-int a5xx_gpu_state_put(struct msm_gpu_state *state)
+static int a5xx_gpu_state_put(struct msm_gpu_state *state)
 {
 	if (IS_ERR_OR_NULL(state))
 		return 1;
@@ -1299,8 +1344,8 @@ int a5xx_gpu_state_put(struct msm_gpu_state *state)
 
 
 #if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
-void a5xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
-		struct drm_printer *p)
+static void a5xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		      struct drm_printer *p)
 {
 	int i, j;
 	u32 pos = 0;
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index a3a06db675ba..321a8061fd32 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -297,6 +297,10 @@ int a5xx_power_init(struct msm_gpu *gpu)
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int ret;
 
+	/* Not all A5xx chips have a GPMU */
+	if (adreno_is_a510(adreno_gpu))
+		return 0;
+
 	/* Set up the limits management */
 	if (adreno_is_a530(adreno_gpu))
 		a530_lm_setup(gpu);
@@ -326,6 +330,9 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu)
 	unsigned int *data, *ptr, *cmds;
 	unsigned int cmds_size;
 
+	if (adreno_is_a510(adreno_gpu))
+		return;
+
 	if (a5xx_gpu->gpmu_bo)
 		return;
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 0888e0df660d..fbbdf86504f5 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -115,6 +115,21 @@ static const struct adreno_info gpulist[] = {
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a4xx_gpu_init,
 	}, {
+		.rev   = ADRENO_REV(5, 1, 0, ANY_ID),
+		.revn = 510,
+		.name = "A510",
+		.fw = {
+			[ADRENO_FW_PM4] = "a530_pm4.fw",
+			[ADRENO_FW_PFP] = "a530_pfp.fw",
+		},
+		.gmem = SZ_256K,
+		/*
+		 * Increase inactive period to 250 to avoid bouncing
+		 * the GDSC which appears to make it grumpy
+		 */
+		.inactive_period = 250,
+		.init = a5xx_gpu_init,
+	}, {
 		.rev = ADRENO_REV(5, 3, 0, 2),
 		.revn = 530,
 		.name = "A530",
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 048c8be426f3..0783e4b5486a 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -14,6 +14,7 @@
 #include <linux/pm_opp.h>
 #include <linux/slab.h>
 #include <linux/soc/qcom/mdt_loader.h>
+#include <soc/qcom/ocmem.h>
 #include "adreno_gpu.h"
 #include "msm_gem.h"
 #include "msm_mmu.h"
@@ -893,6 +894,45 @@ static int adreno_get_pwrlevels(struct device *dev,
 	return 0;
 }
 
+int adreno_gpu_ocmem_init(struct device *dev, struct adreno_gpu *adreno_gpu,
+			  struct adreno_ocmem *adreno_ocmem)
+{
+	struct ocmem_buf *ocmem_hdl;
+	struct ocmem *ocmem;
+
+	ocmem = of_get_ocmem(dev);
+	if (IS_ERR(ocmem)) {
+		if (PTR_ERR(ocmem) == -ENODEV) {
+			/*
+			 * Return success since either the ocmem property was
+			 * not specified in device tree, or ocmem support is
+			 * not compiled into the kernel.
+			 */
+			return 0;
+		}
+
+		return PTR_ERR(ocmem);
+	}
+
+	ocmem_hdl = ocmem_allocate(ocmem, OCMEM_GRAPHICS, adreno_gpu->gmem);
+	if (IS_ERR(ocmem_hdl))
+		return PTR_ERR(ocmem_hdl);
+
+	adreno_ocmem->ocmem = ocmem;
+	adreno_ocmem->base = ocmem_hdl->addr;
+	adreno_ocmem->hdl = ocmem_hdl;
+	adreno_gpu->gmem = ocmem_hdl->len;
+
+	return 0;
+}
+
+void adreno_gpu_ocmem_cleanup(struct adreno_ocmem *adreno_ocmem)
+{
+	if (adreno_ocmem && adreno_ocmem->base)
+		ocmem_free(adreno_ocmem->ocmem, OCMEM_GRAPHICS,
+			   adreno_ocmem->hdl);
+}
+
 int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct adreno_gpu *adreno_gpu,
 		const struct adreno_gpu_funcs *funcs, int nr_rings)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index c7441fb8313e..e71a7570ef72 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -126,6 +126,12 @@ struct adreno_gpu {
 };
 #define to_adreno_gpu(x) container_of(x, struct adreno_gpu, base)
 
+struct adreno_ocmem {
+	struct ocmem *ocmem;
+	unsigned long base;
+	void *hdl;
+};
+
 /* platform config data (ie. from DT, or pdata) */
 struct adreno_platform_config {
 	struct adreno_rev rev;
@@ -206,6 +212,11 @@ static inline int adreno_is_a430(struct adreno_gpu *gpu)
        return gpu->revn == 430;
 }
 
+static inline int adreno_is_a510(struct adreno_gpu *gpu)
+{
+	return gpu->revn == 510;
+}
+
 static inline int adreno_is_a530(struct adreno_gpu *gpu)
 {
 	return gpu->revn == 530;
@@ -236,6 +247,10 @@ void adreno_dump(struct msm_gpu *gpu);
 void adreno_wait_ring(struct msm_ringbuffer *ring, uint32_t ndwords);
 struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu);
 
+int adreno_gpu_ocmem_init(struct device *dev, struct adreno_gpu *adreno_gpu,
+			  struct adreno_ocmem *ocmem);
+void adreno_gpu_ocmem_cleanup(struct adreno_ocmem *ocmem);
+
 int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct adreno_gpu *gpu, const struct adreno_gpu_funcs *funcs,
 		int nr_rings);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
index cdbea38b8697..f1bc6a1af7a7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
@@ -55,8 +55,7 @@ static void dpu_core_irq_callback_handler(void *arg, int irq_idx)
 int dpu_core_irq_idx_lookup(struct dpu_kms *dpu_kms,
 		enum dpu_intr_type intr_type, u32 instance_idx)
 {
-	if (!dpu_kms || !dpu_kms->hw_intr ||
-			!dpu_kms->hw_intr->ops.irq_idx_lookup)
+	if (!dpu_kms->hw_intr || !dpu_kms->hw_intr->ops.irq_idx_lookup)
 		return -EINVAL;
 
 	return dpu_kms->hw_intr->ops.irq_idx_lookup(intr_type,
@@ -73,7 +72,7 @@ static int _dpu_core_irq_enable(struct dpu_kms *dpu_kms, int irq_idx)
 	unsigned long irq_flags;
 	int ret = 0, enable_count;
 
-	if (!dpu_kms || !dpu_kms->hw_intr ||
+	if (!dpu_kms->hw_intr ||
 			!dpu_kms->irq_obj.enable_counts ||
 			!dpu_kms->irq_obj.irq_counts) {
 		DPU_ERROR("invalid params\n");
@@ -114,7 +113,7 @@ int dpu_core_irq_enable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
 {
 	int i, ret = 0, counts;
 
-	if (!dpu_kms || !irq_idxs || !irq_count) {
+	if (!irq_idxs || !irq_count) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -138,7 +137,7 @@ static int _dpu_core_irq_disable(struct dpu_kms *dpu_kms, int irq_idx)
 {
 	int ret = 0, enable_count;
 
-	if (!dpu_kms || !dpu_kms->hw_intr || !dpu_kms->irq_obj.enable_counts) {
+	if (!dpu_kms->hw_intr || !dpu_kms->irq_obj.enable_counts) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -169,7 +168,7 @@ int dpu_core_irq_disable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
 {
 	int i, ret = 0, counts;
 
-	if (!dpu_kms || !irq_idxs || !irq_count) {
+	if (!irq_idxs || !irq_count) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -186,7 +185,7 @@ int dpu_core_irq_disable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
 
 u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx, bool clear)
 {
-	if (!dpu_kms || !dpu_kms->hw_intr ||
+	if (!dpu_kms->hw_intr ||
 			!dpu_kms->hw_intr->ops.get_interrupt_status)
 		return 0;
 
@@ -205,7 +204,7 @@ int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int irq_idx,
 {
 	unsigned long irq_flags;
 
-	if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) {
+	if (!dpu_kms->irq_obj.irq_cb_tbl) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -240,7 +239,7 @@ int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx,
 {
 	unsigned long irq_flags;
 
-	if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) {
+	if (!dpu_kms->irq_obj.irq_cb_tbl) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -274,8 +273,7 @@ int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx,
 
 static void dpu_clear_all_irqs(struct dpu_kms *dpu_kms)
 {
-	if (!dpu_kms || !dpu_kms->hw_intr ||
-			!dpu_kms->hw_intr->ops.clear_all_irqs)
+	if (!dpu_kms->hw_intr || !dpu_kms->hw_intr->ops.clear_all_irqs)
 		return;
 
 	dpu_kms->hw_intr->ops.clear_all_irqs(dpu_kms->hw_intr);
@@ -283,8 +281,7 @@ static void dpu_clear_all_irqs(struct dpu_kms *dpu_kms)
 
 static void dpu_disable_all_irqs(struct dpu_kms *dpu_kms)
 {
-	if (!dpu_kms || !dpu_kms->hw_intr ||
-			!dpu_kms->hw_intr->ops.disable_all_irqs)
+	if (!dpu_kms->hw_intr || !dpu_kms->hw_intr->ops.disable_all_irqs)
 		return;
 
 	dpu_kms->hw_intr->ops.disable_all_irqs(dpu_kms->hw_intr);
@@ -343,18 +340,8 @@ void dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
 
 void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms)
 {
-	struct msm_drm_private *priv;
 	int i;
 
-	if (!dpu_kms->dev) {
-		DPU_ERROR("invalid drm device\n");
-		return;
-	} else if (!dpu_kms->dev->dev_private) {
-		DPU_ERROR("invalid device private\n");
-		return;
-	}
-	priv = dpu_kms->dev->dev_private;
-
 	pm_runtime_get_sync(&dpu_kms->pdev->dev);
 	dpu_clear_all_irqs(dpu_kms);
 	dpu_disable_all_irqs(dpu_kms);
@@ -379,18 +366,8 @@ void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms)
 
 void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms)
 {
-	struct msm_drm_private *priv;
 	int i;
 
-	if (!dpu_kms->dev) {
-		DPU_ERROR("invalid drm device\n");
-		return;
-	} else if (!dpu_kms->dev->dev_private) {
-		DPU_ERROR("invalid device private\n");
-		return;
-	}
-	priv = dpu_kms->dev->dev_private;
-
 	pm_runtime_get_sync(&dpu_kms->pdev->dev);
 	for (i = 0; i < dpu_kms->irq_obj.total_irqs; i++)
 		if (atomic_read(&dpu_kms->irq_obj.enable_counts[i]) ||
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 09a49b59bb5b..11f2bebe3869 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -32,18 +32,7 @@ enum dpu_perf_mode {
 static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
 {
 	struct msm_drm_private *priv;
-
-	if (!crtc->dev || !crtc->dev->dev_private) {
-		DPU_ERROR("invalid device\n");
-		return NULL;
-	}
-
 	priv = crtc->dev->dev_private;
-	if (!priv || !priv->kms) {
-		DPU_ERROR("invalid kms\n");
-		return NULL;
-	}
-
 	return to_dpu_kms(priv->kms);
 }
 
@@ -116,7 +105,7 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
 	}
 
 	kms = _dpu_crtc_get_kms(crtc);
-	if (!kms || !kms->catalog) {
+	if (!kms->catalog) {
 		DPU_ERROR("invalid parameters\n");
 		return 0;
 	}
@@ -215,7 +204,6 @@ static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
 void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
 {
 	struct dpu_crtc *dpu_crtc;
-	struct dpu_crtc_state *dpu_cstate;
 	struct dpu_kms *kms;
 
 	if (!crtc) {
@@ -224,13 +212,12 @@ void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
 	}
 
 	kms = _dpu_crtc_get_kms(crtc);
-	if (!kms || !kms->catalog) {
+	if (!kms->catalog) {
 		DPU_ERROR("invalid kms\n");
 		return;
 	}
 
 	dpu_crtc = to_dpu_crtc(crtc);
-	dpu_cstate = to_dpu_crtc_state(crtc->state);
 
 	if (atomic_dec_return(&kms->bandwidth_ref) > 0)
 		return;
@@ -287,7 +274,6 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 	u64 clk_rate = 0;
 	struct dpu_crtc *dpu_crtc;
 	struct dpu_crtc_state *dpu_cstate;
-	struct msm_drm_private *priv;
 	struct dpu_kms *kms;
 	int ret;
 
@@ -297,11 +283,10 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 	}
 
 	kms = _dpu_crtc_get_kms(crtc);
-	if (!kms || !kms->catalog) {
+	if (!kms->catalog) {
 		DPU_ERROR("invalid kms\n");
 		return -EINVAL;
 	}
-	priv = kms->dev->dev_private;
 
 	dpu_crtc = to_dpu_crtc(crtc);
 	dpu_cstate = to_dpu_crtc_state(crtc->state);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index ce59adff06aa..f197dce54576 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -266,11 +266,20 @@ enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc)
 {
 	struct drm_encoder *encoder;
 
-	if (!crtc || !crtc->dev) {
+	if (!crtc) {
 		DPU_ERROR("invalid crtc\n");
 		return INTF_MODE_NONE;
 	}
 
+	/*
+	 * TODO: This function is called from dpu debugfs and as part of atomic
+	 * check. When called from debugfs, the crtc->mutex must be held to
+	 * read crtc->state. However reading crtc->state from atomic check isn't
+	 * allowed (unless you have a good reason, a big comment, and a deep
+	 * understanding of how the atomic/modeset locks work (<- and this is
+	 * probably not possible)). So we'll keep the WARN_ON here for now, but
+	 * really we need to figure out a better way to track our operating mode
+	 */
 	WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
 
 	/* TODO: Returns the first INTF_MODE, could there be multiple values? */
@@ -694,7 +703,7 @@ static void dpu_crtc_disable(struct drm_crtc *crtc,
 	unsigned long flags;
 	bool release_bandwidth = false;
 
-	if (!crtc || !crtc->dev || !crtc->dev->dev_private || !crtc->state) {
+	if (!crtc || !crtc->state) {
 		DPU_ERROR("invalid crtc\n");
 		return;
 	}
@@ -766,7 +775,7 @@ static void dpu_crtc_enable(struct drm_crtc *crtc,
 	struct msm_drm_private *priv;
 	bool request_bandwidth;
 
-	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+	if (!crtc) {
 		DPU_ERROR("invalid crtc\n");
 		return;
 	}
@@ -1288,13 +1297,8 @@ struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane,
 {
 	struct drm_crtc *crtc = NULL;
 	struct dpu_crtc *dpu_crtc = NULL;
-	struct msm_drm_private *priv = NULL;
-	struct dpu_kms *kms = NULL;
 	int i;
 
-	priv = dev->dev_private;
-	kms = to_dpu_kms(priv->kms);
-
 	dpu_crtc = kzalloc(sizeof(*dpu_crtc), GFP_KERNEL);
 	if (!dpu_crtc)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index d82ea994063f..f96e142c4361 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -645,11 +645,6 @@ static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc,
 	priv = drm_enc->dev->dev_private;
 
 	dpu_kms = to_dpu_kms(priv->kms);
-	if (!dpu_kms) {
-		DPU_ERROR("invalid dpu_kms\n");
-		return;
-	}
-
 	hw_mdptop = dpu_kms->hw_mdp;
 	if (!hw_mdptop) {
 		DPU_ERROR("invalid mdptop\n");
@@ -735,8 +730,7 @@ static int dpu_encoder_resource_control(struct drm_encoder *drm_enc,
 	struct msm_drm_private *priv;
 	bool is_vid_mode = false;
 
-	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private ||
-			!drm_enc->crtc) {
+	if (!drm_enc || !drm_enc->dev || !drm_enc->crtc) {
 		DPU_ERROR("invalid parameters\n");
 		return -EINVAL;
 	}
@@ -1092,17 +1086,13 @@ static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc)
 	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
 
-	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private) {
+	if (!drm_enc || !drm_enc->dev) {
 		DPU_ERROR("invalid parameters\n");
 		return;
 	}
 
 	priv = drm_enc->dev->dev_private;
 	dpu_kms = to_dpu_kms(priv->kms);
-	if (!dpu_kms) {
-		DPU_ERROR("invalid dpu_kms\n");
-		return;
-	}
 
 	dpu_enc = to_dpu_encoder_virt(drm_enc);
 	if (!dpu_enc || !dpu_enc->cur_master) {
@@ -1184,7 +1174,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	struct dpu_encoder_virt *dpu_enc = NULL;
 	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
-	struct drm_display_mode *mode;
 	int i = 0;
 
 	if (!drm_enc) {
@@ -1193,9 +1182,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	} else if (!drm_enc->dev) {
 		DPU_ERROR("invalid dev\n");
 		return;
-	} else if (!drm_enc->dev->dev_private) {
-		DPU_ERROR("invalid dev_private\n");
-		return;
 	}
 
 	dpu_enc = to_dpu_encoder_virt(drm_enc);
@@ -1204,8 +1190,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	mutex_lock(&dpu_enc->enc_lock);
 	dpu_enc->enabled = false;
 
-	mode = &drm_enc->crtc->state->adjusted_mode;
-
 	priv = drm_enc->dev->dev_private;
 	dpu_kms = to_dpu_kms(priv->kms);
 
@@ -1734,8 +1718,7 @@ static void dpu_encoder_vsync_event_handler(struct timer_list *t)
 	struct msm_drm_private *priv;
 	struct msm_drm_thread *event_thread;
 
-	if (!drm_enc->dev || !drm_enc->dev->dev_private ||
-			!drm_enc->crtc) {
+	if (!drm_enc->dev || !drm_enc->crtc) {
 		DPU_ERROR("invalid parameters\n");
 		return;
 	}
@@ -1914,8 +1897,6 @@ static int _dpu_encoder_debugfs_status_open(struct inode *inode,
 static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
 {
 	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
-	struct msm_drm_private *priv;
-	struct dpu_kms *dpu_kms;
 	int i;
 
 	static const struct file_operations debugfs_status_fops = {
@@ -1927,14 +1908,11 @@ static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
 
 	char name[DPU_NAME_SIZE];
 
-	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
+	if (!drm_enc->dev) {
 		DPU_ERROR("invalid encoder or kms\n");
 		return -EINVAL;
 	}
 
-	priv = drm_enc->dev->dev_private;
-	dpu_kms = to_dpu_kms(priv->kms);
-
 	snprintf(name, DPU_NAME_SIZE, "encoder%u", drm_enc->base.id);
 
 	/* create overall sub-directory for the encoder */
@@ -2042,9 +2020,8 @@ static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc,
 	enum dpu_intf_type intf_type;
 	struct dpu_enc_phys_init_params phys_params;
 
-	if (!dpu_enc || !dpu_kms) {
-		DPU_ERROR("invalid arg(s), enc %d kms %d\n",
-				dpu_enc != 0, dpu_kms != 0);
+	if (!dpu_enc) {
+		DPU_ERROR("invalid arg(s), enc %d\n", dpu_enc != 0);
 		return -EINVAL;
 	}
 
@@ -2133,14 +2110,12 @@ static void dpu_encoder_frame_done_timeout(struct timer_list *t)
 	struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t,
 			frame_done_timer);
 	struct drm_encoder *drm_enc = &dpu_enc->base;
-	struct msm_drm_private *priv;
 	u32 event;
 
-	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
+	if (!drm_enc->dev) {
 		DPU_ERROR("invalid parameters\n");
 		return;
 	}
-	priv = drm_enc->dev->dev_private;
 
 	if (!dpu_enc->frame_busy_mask[0] || !dpu_enc->crtc_frame_event_cb) {
 		DRM_DEBUG_KMS("id:%u invalid timeout frame_busy_mask=%lu\n",
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 2923b63d95fe..047960949fbb 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
@@ -124,13 +124,11 @@ static void dpu_encoder_phys_cmd_pp_rd_ptr_irq(void *arg, int irq_idx)
 static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg, int irq_idx)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
-	struct dpu_encoder_phys_cmd *cmd_enc;
 
 	if (!phys_enc || !phys_enc->hw_ctl)
 		return;
 
 	DPU_ATRACE_BEGIN("ctl_start_irq");
-	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
 
 	atomic_add_unless(&phys_enc->pending_ctlstart_cnt, -1, 0);
 
@@ -316,13 +314,9 @@ end:
 static void dpu_encoder_phys_cmd_irq_control(struct dpu_encoder_phys *phys_enc,
 		bool enable)
 {
-	struct dpu_encoder_phys_cmd *cmd_enc;
-
 	if (!phys_enc)
 		return;
 
-	cmd_enc = to_dpu_encoder_phys_cmd(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));
@@ -355,7 +349,6 @@ static void dpu_encoder_phys_cmd_tearcheck_config(
 	struct drm_display_mode *mode;
 	bool tc_enable = true;
 	u32 vsync_hz;
-	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
 
 	if (!phys_enc || !phys_enc->hw_pp) {
@@ -373,11 +366,6 @@ static void dpu_encoder_phys_cmd_tearcheck_config(
 	}
 
 	dpu_kms = phys_enc->dpu_kms;
-	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev_private) {
-		DPU_ERROR("invalid device\n");
-		return;
-	}
-	priv = dpu_kms->dev->dev_private;
 
 	/*
 	 * TE default: dsi byte clock calculated base on 70 fps;
@@ -650,13 +638,10 @@ static int dpu_encoder_phys_cmd_wait_for_tx_complete(
 		struct dpu_encoder_phys *phys_enc)
 {
 	int rc;
-	struct dpu_encoder_phys_cmd *cmd_enc;
 
 	if (!phys_enc)
 		return -EINVAL;
 
-	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
-
 	rc = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc);
 	if (rc) {
 		DRM_ERROR("failed wait_for_idle: id:%u ret:%d intf:%d\n",
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 b9c84fb4d4a1..3123ef873cdf 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
@@ -374,7 +374,7 @@ static void dpu_encoder_phys_vid_mode_set(
 		struct drm_display_mode *mode,
 		struct drm_display_mode *adj_mode)
 {
-	if (!phys_enc || !phys_enc->dpu_kms) {
+	if (!phys_enc) {
 		DPU_ERROR("invalid encoder/kms\n");
 		return;
 	}
@@ -566,16 +566,13 @@ static void dpu_encoder_phys_vid_prepare_for_kickoff(
 
 static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc)
 {
-	struct msm_drm_private *priv;
 	unsigned long lock_flags;
 	int ret;
 
-	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev ||
-			!phys_enc->parent->dev->dev_private) {
+	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev) {
 		DPU_ERROR("invalid encoder/device\n");
 		return;
 	}
-	priv = phys_enc->parent->dev->dev_private;
 
 	if (!phys_enc->hw_intf || !phys_enc->hw_ctl) {
 		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 58b0485dc375..6c92f0fbeac9 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -30,10 +30,6 @@
 #define CREATE_TRACE_POINTS
 #include "dpu_trace.h"
 
-static const char * const iommu_ports[] = {
-		"mdp_0",
-};
-
 /*
  * To enable overall DRM driver logging
  * # echo 0x2 > /sys/module/drm/parameters/debug
@@ -68,16 +64,14 @@ static int _dpu_danger_signal_status(struct seq_file *s,
 		bool danger_status)
 {
 	struct dpu_kms *kms = (struct dpu_kms *)s->private;
-	struct msm_drm_private *priv;
 	struct dpu_danger_safe_status status;
 	int i;
 
-	if (!kms->dev || !kms->dev->dev_private || !kms->hw_mdp) {
+	if (!kms->hw_mdp) {
 		DPU_ERROR("invalid arg(s)\n");
 		return 0;
 	}
 
-	priv = kms->dev->dev_private;
 	memset(&status, 0, sizeof(struct dpu_danger_safe_status));
 
 	pm_runtime_get_sync(&kms->pdev->dev);
@@ -153,13 +147,7 @@ static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data)
 		return 0;
 
 	dev = dpu_kms->dev;
-	if (!dev)
-		return 0;
-
 	priv = dev->dev_private;
-	if (!priv)
-		return 0;
-
 	base = dpu_kms->mmio + regset->offset;
 
 	/* insert padding spaces, if needed */
@@ -280,7 +268,6 @@ static void dpu_kms_prepare_commit(struct msm_kms *kms,
 		struct drm_atomic_state *state)
 {
 	struct dpu_kms *dpu_kms;
-	struct msm_drm_private *priv;
 	struct drm_device *dev;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
@@ -292,10 +279,6 @@ static void dpu_kms_prepare_commit(struct msm_kms *kms,
 	dpu_kms = to_dpu_kms(kms);
 	dev = dpu_kms->dev;
 
-	if (!dev || !dev->dev_private)
-		return;
-	priv = dev->dev_private;
-
 	/* Call prepare_commit for all affected encoders */
 	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
 		drm_for_each_encoder_mask(encoder, crtc->dev,
@@ -333,7 +316,6 @@ void dpu_kms_encoder_enable(struct drm_encoder *encoder)
 	if (funcs && funcs->commit)
 		funcs->commit(encoder);
 
-	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
 	drm_for_each_crtc(crtc, dev) {
 		if (!(crtc->state->encoder_mask & drm_encoder_mask(encoder)))
 			continue;
@@ -464,16 +446,6 @@ static void _dpu_kms_drm_obj_destroy(struct dpu_kms *dpu_kms)
 	struct msm_drm_private *priv;
 	int i;
 
-	if (!dpu_kms) {
-		DPU_ERROR("invalid dpu_kms\n");
-		return;
-	} else if (!dpu_kms->dev) {
-		DPU_ERROR("invalid dev\n");
-		return;
-	} else if (!dpu_kms->dev->dev_private) {
-		DPU_ERROR("invalid dev_private\n");
-		return;
-	}
 	priv = dpu_kms->dev->dev_private;
 
 	for (i = 0; i < priv->num_crtcs; i++)
@@ -505,7 +477,6 @@ static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms)
 
 	int primary_planes_idx = 0, cursor_planes_idx = 0, i, ret;
 	int max_crtc_count;
-
 	dev = dpu_kms->dev;
 	priv = dev->dev_private;
 	catalog = dpu_kms->catalog;
@@ -585,8 +556,6 @@ static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms)
 	int i;
 
 	dev = dpu_kms->dev;
-	if (!dev)
-		return;
 
 	if (dpu_kms->hw_intr)
 		dpu_hw_intr_destroy(dpu_kms->hw_intr);
@@ -725,8 +694,7 @@ static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms)
 
 	mmu = dpu_kms->base.aspace->mmu;
 
-	mmu->funcs->detach(mmu, (const char **)iommu_ports,
-			ARRAY_SIZE(iommu_ports));
+	mmu->funcs->detach(mmu);
 	msm_gem_address_space_put(dpu_kms->base.aspace);
 
 	dpu_kms->base.aspace = NULL;
@@ -752,8 +720,7 @@ static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms)
 		return PTR_ERR(aspace);
 	}
 
-	ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
-			ARRAY_SIZE(iommu_ports));
+	ret = aspace->mmu->funcs->attach(aspace->mmu);
 	if (ret) {
 		DPU_ERROR("failed to attach iommu %d\n", ret);
 		msm_gem_address_space_put(aspace);
@@ -803,16 +770,7 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 
 	dpu_kms = to_dpu_kms(kms);
 	dev = dpu_kms->dev;
-	if (!dev) {
-		DPU_ERROR("invalid device\n");
-		return rc;
-	}
-
 	priv = dev->dev_private;
-	if (!priv) {
-		DPU_ERROR("invalid private data\n");
-		return rc;
-	}
 
 	atomic_set(&dpu_kms->bandwidth_ref, 0);
 
@@ -974,7 +932,7 @@ struct msm_kms *dpu_kms_init(struct drm_device *dev)
 	struct dpu_kms *dpu_kms;
 	int irq;
 
-	if (!dev || !dev->dev_private) {
+	if (!dev) {
 		DPU_ERROR("drm device node invalid\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -1064,11 +1022,6 @@ static int __maybe_unused dpu_runtime_suspend(struct device *dev)
 	struct dss_module_power *mp = &dpu_kms->mp;
 
 	ddev = dpu_kms->dev;
-	if (!ddev) {
-		DPU_ERROR("invalid drm_device\n");
-		return rc;
-	}
-
 	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false);
 	if (rc)
 		DPU_ERROR("clock disable failed rc:%d\n", rc);
@@ -1086,11 +1039,6 @@ static int __maybe_unused dpu_runtime_resume(struct device *dev)
 	struct dss_module_power *mp = &dpu_kms->mp;
 
 	ddev = dpu_kms->dev;
-	if (!ddev) {
-		DPU_ERROR("invalid drm_device\n");
-		return rc;
-	}
-
 	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
 	if (rc) {
 		DPU_ERROR("clock enable failed rc:%d\n", rc);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
index 959d03e007fa..c6169e7df19d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -139,10 +139,6 @@ struct vsync_info {
 
 #define to_dpu_kms(x) container_of(x, struct dpu_kms, base)
 
-/* get struct msm_kms * from drm_device * */
-#define ddev_to_msm_kms(D) ((D) && (D)->dev_private ? \
-		((struct msm_drm_private *)((D)->dev_private))->kms : NULL)
-
 /**
  * Debugfs functions - extra helper functions for debugfs support
  *
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
index 8d24b79fd400..991f4c8f8a12 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
@@ -154,10 +154,6 @@ void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
 	u32 ot_lim;
 	int ret, i;
 
-	if (!dpu_kms) {
-		DPU_ERROR("invalid arguments\n");
-		return;
-	}
 	mdp = dpu_kms->hw_mdp;
 
 	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
@@ -214,7 +210,7 @@ void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
 	const struct dpu_vbif_qos_tbl *qos_tbl;
 	int i;
 
-	if (!dpu_kms || !params || !dpu_kms->hw_mdp) {
+	if (!params || !dpu_kms->hw_mdp) {
 		DPU_ERROR("invalid arguments\n");
 		return;
 	}
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index 50711ccc8691..dda05436f716 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -157,10 +157,6 @@ static long mdp4_round_pixclk(struct msm_kms *kms, unsigned long rate,
 	}
 }
 
-static const char * const iommu_ports[] = {
-	"mdp_port0_cb0", "mdp_port1_cb0",
-};
-
 static void mdp4_destroy(struct msm_kms *kms)
 {
 	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
@@ -172,8 +168,7 @@ static void mdp4_destroy(struct msm_kms *kms)
 	drm_gem_object_put_unlocked(mdp4_kms->blank_cursor_bo);
 
 	if (aspace) {
-		aspace->mmu->funcs->detach(aspace->mmu,
-				iommu_ports, ARRAY_SIZE(iommu_ports));
+		aspace->mmu->funcs->detach(aspace->mmu);
 		msm_gem_address_space_put(aspace);
 	}
 
@@ -524,8 +519,7 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 
 		kms->aspace = aspace;
 
-		ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
-				ARRAY_SIZE(iommu_ports));
+		ret = aspace->mmu->funcs->attach(aspace->mmu);
 		if (ret)
 			goto fail;
 	} else {
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
index f6e71ff539ca..1f48f64539a2 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
@@ -14,7 +14,7 @@ struct mdp5_cfg_handler {
 /* mdp5_cfg must be exposed (used in mdp5.xml.h) */
 const struct mdp5_cfg_hw *mdp5_cfg = NULL;
 
-const struct mdp5_cfg_hw msm8x74v1_config = {
+static const struct mdp5_cfg_hw msm8x74v1_config = {
 	.name = "msm8x74v1",
 	.mdp = {
 		.count = 1,
@@ -98,7 +98,7 @@ const struct mdp5_cfg_hw msm8x74v1_config = {
 	.max_clk = 200000000,
 };
 
-const struct mdp5_cfg_hw msm8x74v2_config = {
+static const struct mdp5_cfg_hw msm8x74v2_config = {
 	.name = "msm8x74",
 	.mdp = {
 		.count = 1,
@@ -180,7 +180,7 @@ const struct mdp5_cfg_hw msm8x74v2_config = {
 	.max_clk = 200000000,
 };
 
-const struct mdp5_cfg_hw apq8084_config = {
+static const struct mdp5_cfg_hw apq8084_config = {
 	.name = "apq8084",
 	.mdp = {
 		.count = 1,
@@ -275,7 +275,7 @@ const struct mdp5_cfg_hw apq8084_config = {
 	.max_clk = 320000000,
 };
 
-const struct mdp5_cfg_hw msm8x16_config = {
+static const struct mdp5_cfg_hw msm8x16_config = {
 	.name = "msm8x16",
 	.mdp = {
 		.count = 1,
@@ -342,7 +342,7 @@ const struct mdp5_cfg_hw msm8x16_config = {
 	.max_clk = 320000000,
 };
 
-const struct mdp5_cfg_hw msm8x94_config = {
+static const struct mdp5_cfg_hw msm8x94_config = {
 	.name = "msm8x94",
 	.mdp = {
 		.count = 1,
@@ -437,7 +437,7 @@ const struct mdp5_cfg_hw msm8x94_config = {
 	.max_clk = 400000000,
 };
 
-const struct mdp5_cfg_hw msm8x96_config = {
+static const struct mdp5_cfg_hw msm8x96_config = {
 	.name = "msm8x96",
 	.mdp = {
 		.count = 1,
@@ -545,7 +545,104 @@ const struct mdp5_cfg_hw msm8x96_config = {
 	.max_clk = 412500000,
 };
 
-const struct mdp5_cfg_hw msm8917_config = {
+const struct mdp5_cfg_hw msm8x76_config = {
+	.name = "msm8x76",
+	.mdp = {
+		.count = 1,
+		.caps = MDP_CAP_SMP |
+			MDP_CAP_DSC |
+			MDP_CAP_SRC_SPLIT |
+			0,
+	},
+	.ctl = {
+		.count = 3,
+		.base = { 0x01000, 0x01200, 0x01400 },
+		.flush_hw_mask = 0xffffffff,
+	},
+	.smp = {
+		.mmb_count = 10,
+		.mmb_size = 10240,
+		.clients = {
+			[SSPP_VIG0] = 1, [SSPP_VIG1] = 9,
+			[SSPP_DMA0] = 4,
+			[SSPP_RGB0] = 7, [SSPP_RGB1] = 8,
+		},
+	},
+	.pipe_vig = {
+		.count = 2,
+		.base = { 0x04000, 0x06000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_SCALE	|
+			MDP_PIPE_CAP_CSC	|
+			MDP_PIPE_CAP_DECIMATION	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			0,
+	},
+	.pipe_rgb = {
+		.count = 2,
+		.base = { 0x14000, 0x16000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_DECIMATION	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			0,
+	},
+	.pipe_dma = {
+		.count = 1,
+		.base = { 0x24000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			0,
+	},
+	.pipe_cursor = {
+		.count = 1,
+		.base = { 0x440DC },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			MDP_PIPE_CAP_CURSOR	|
+			0,
+	},
+	.lm = {
+		.count = 2,
+		.base = { 0x44000, 0x45000 },
+		.instances = {
+				{ .id = 0, .pp = 0, .dspp = 0,
+				  .caps = MDP_LM_CAP_DISPLAY, },
+				{ .id = 1, .pp = -1, .dspp = -1,
+				  .caps = MDP_LM_CAP_WB },
+			     },
+		.nb_stages = 8,
+		.max_width = 2560,
+		.max_height = 0xFFFF,
+	},
+	.dspp = {
+		.count = 1,
+		.base = { 0x54000 },
+
+	},
+	.pp = {
+		.count = 3,
+		.base = { 0x70000, 0x70800, 0x72000 },
+	},
+	.dsc = {
+		.count = 2,
+		.base = { 0x80000, 0x80400 },
+	},
+	.intf = {
+		.base = { 0x6a000, 0x6a800, 0x6b000 },
+		.connect = {
+			[0] = INTF_DISABLED,
+			[1] = INTF_DSI,
+			[2] = INTF_DSI,
+		},
+	},
+	.max_clk = 360000000,
+};
+
+static const struct mdp5_cfg_hw msm8917_config = {
 	.name = "msm8917",
 	.mdp = {
 		.count = 1,
@@ -630,7 +727,7 @@ const struct mdp5_cfg_hw msm8917_config = {
 	.max_clk = 320000000,
 };
 
-const struct mdp5_cfg_hw msm8998_config = {
+static const struct mdp5_cfg_hw msm8998_config = {
 	.name = "msm8998",
 	.mdp = {
 		.count = 1,
@@ -745,6 +842,7 @@ static const struct mdp5_cfg_handler cfg_handlers_v1[] = {
 	{ .revision = 6, .config = { .hw = &msm8x16_config } },
 	{ .revision = 9, .config = { .hw = &msm8x94_config } },
 	{ .revision = 7, .config = { .hw = &msm8x96_config } },
+	{ .revision = 11, .config = { .hw = &msm8x76_config } },
 	{ .revision = 15, .config = { .hw = &msm8917_config } },
 };
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index eb0b4b7dc7cc..05cc04f729d6 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -214,7 +214,6 @@ static void blend_setup(struct drm_crtc *crtc)
 	struct mdp5_pipeline *pipeline = &mdp5_cstate->pipeline;
 	struct mdp5_kms *mdp5_kms = get_kms(crtc);
 	struct drm_plane *plane;
-	const struct mdp5_cfg_hw *hw_cfg;
 	struct mdp5_plane_state *pstate, *pstates[STAGE_MAX + 1] = {NULL};
 	const struct mdp_format *format;
 	struct mdp5_hw_mixer *mixer = pipeline->mixer;
@@ -232,8 +231,6 @@ static void blend_setup(struct drm_crtc *crtc)
 	u32 val;
 #define blender(stage)	((stage) - STAGE0)
 
-	hw_cfg = mdp5_cfg_get_hw_config(mdp5_kms->cfg);
-
 	spin_lock_irqsave(&mdp5_crtc->lm_lock, flags);
 
 	/* ctl could be released already when we are shutting down: */
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 91cd76a2bab1..e43ecd4be10a 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -19,10 +19,6 @@
 #include "msm_mmu.h"
 #include "mdp5_kms.h"
 
-static const char *iommu_ports[] = {
-		"mdp_0",
-};
-
 static int mdp5_hw_init(struct msm_kms *kms)
 {
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
@@ -233,8 +229,7 @@ static void mdp5_kms_destroy(struct msm_kms *kms)
 		mdp5_pipe_destroy(mdp5_kms->hwpipes[i]);
 
 	if (aspace) {
-		aspace->mmu->funcs->detach(aspace->mmu,
-				iommu_ports, ARRAY_SIZE(iommu_ports));
+		aspace->mmu->funcs->detach(aspace->mmu);
 		msm_gem_address_space_put(aspace);
 	}
 }
@@ -314,6 +309,10 @@ int mdp5_disable(struct mdp5_kms *mdp5_kms)
 	mdp5_kms->enable_count--;
 	WARN_ON(mdp5_kms->enable_count < 0);
 
+	if (mdp5_kms->tbu_rt_clk)
+		clk_disable_unprepare(mdp5_kms->tbu_rt_clk);
+	if (mdp5_kms->tbu_clk)
+		clk_disable_unprepare(mdp5_kms->tbu_clk);
 	clk_disable_unprepare(mdp5_kms->ahb_clk);
 	clk_disable_unprepare(mdp5_kms->axi_clk);
 	clk_disable_unprepare(mdp5_kms->core_clk);
@@ -334,6 +333,10 @@ int mdp5_enable(struct mdp5_kms *mdp5_kms)
 	clk_prepare_enable(mdp5_kms->core_clk);
 	if (mdp5_kms->lut_clk)
 		clk_prepare_enable(mdp5_kms->lut_clk);
+	if (mdp5_kms->tbu_clk)
+		clk_prepare_enable(mdp5_kms->tbu_clk);
+	if (mdp5_kms->tbu_rt_clk)
+		clk_prepare_enable(mdp5_kms->tbu_rt_clk);
 
 	return 0;
 }
@@ -466,14 +469,11 @@ static int modeset_init(struct mdp5_kms *mdp5_kms)
 {
 	struct drm_device *dev = mdp5_kms->dev;
 	struct msm_drm_private *priv = dev->dev_private;
-	const struct mdp5_cfg_hw *hw_cfg;
 	unsigned int num_crtcs;
 	int i, ret, pi = 0, ci = 0;
 	struct drm_plane *primary[MAX_BASES] = { NULL };
 	struct drm_plane *cursor[MAX_BASES] = { NULL };
 
-	hw_cfg = mdp5_cfg_get_hw_config(mdp5_kms->cfg);
-
 	/*
 	 * Construct encoders and modeset initialize connector devices
 	 * for each external display interface.
@@ -737,8 +737,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 
 		kms->aspace = aspace;
 
-		ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
-				ARRAY_SIZE(iommu_ports));
+		ret = aspace->mmu->funcs->attach(aspace->mmu);
 		if (ret) {
 			DRM_DEV_ERROR(&pdev->dev, "failed to attach iommu: %d\n",
 				ret);
@@ -974,6 +973,8 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev)
 
 	/* 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
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
index d1bf4fdfc815..128866742593 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
@@ -53,6 +53,8 @@ struct mdp5_kms {
 	struct clk *ahb_clk;
 	struct clk *core_clk;
 	struct clk *lut_clk;
+	struct clk *tbu_clk;
+	struct clk *tbu_rt_clk;
 	struct clk *vsync_clk;
 
 	/*
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
index b31cfb554fa2..d7fa2c49e741 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
@@ -121,7 +121,6 @@ uint32_t mdp5_smp_calculate(struct mdp5_smp *smp,
 	struct mdp5_kms *mdp5_kms = get_kms(smp);
 	int rev = mdp5_cfg_get_hw_rev(mdp5_kms->cfg);
 	int i, hsub, nplanes, nlines;
-	u32 fmt = format->base.pixel_format;
 	uint32_t blkcfg = 0;
 
 	nplanes = info->num_planes;
@@ -135,7 +134,6 @@ uint32_t mdp5_smp_calculate(struct mdp5_smp *smp,
 	 * them together, writes to SMP using a single client.
 	 */
 	if ((rev > 0) && (format->chroma_sample > CHROMA_FULL)) {
-		fmt = DRM_FORMAT_NV24;
 		nplanes = 2;
 
 		/* if decimation is enabled, HW decimates less on the
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index b7b7c1a9164a..86ad3fdf207d 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -66,6 +66,26 @@ static const struct msm_dsi_config msm8916_dsi_cfg = {
 	.num_dsi = 1,
 };
 
+static const char * const dsi_8976_bus_clk_names[] = {
+	"mdp_core", "iface", "bus",
+};
+
+static const struct msm_dsi_config msm8976_dsi_cfg = {
+	.io_offset = DSI_6G_REG_SHIFT,
+	.reg_cfg = {
+		.num = 3,
+		.regs = {
+			{"gdsc", -1, -1},
+			{"vdda", 100000, 100},	/* 1.2 V */
+			{"vddio", 100000, 100},	/* 1.8 V */
+		},
+	},
+	.bus_clk_names = dsi_8976_bus_clk_names,
+	.num_bus_clks = ARRAY_SIZE(dsi_8976_bus_clk_names),
+	.io_start = { 0x1a94000, 0x1a96000 },
+	.num_dsi = 2,
+};
+
 static const struct msm_dsi_config msm8994_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
@@ -147,7 +167,7 @@ static const struct msm_dsi_config sdm845_dsi_cfg = {
 	.num_dsi = 2,
 };
 
-const static struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
+static const struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
 	.link_clk_enable = dsi_link_clk_enable_v2,
 	.link_clk_disable = dsi_link_clk_disable_v2,
 	.clk_init_ver = dsi_clk_init_v2,
@@ -158,7 +178,7 @@ const static struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
 	.calc_clk_rate = dsi_calc_clk_rate_v2,
 };
 
-const static struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
+static const struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
 	.link_clk_enable = dsi_link_clk_enable_6g,
 	.link_clk_disable = dsi_link_clk_disable_6g,
 	.clk_init_ver = NULL,
@@ -169,7 +189,7 @@ const static struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
 	.calc_clk_rate = dsi_calc_clk_rate_6g,
 };
 
-const static struct msm_dsi_host_cfg_ops msm_dsi_6g_v2_host_ops = {
+static const struct msm_dsi_host_cfg_ops msm_dsi_6g_v2_host_ops = {
 	.link_clk_enable = dsi_link_clk_enable_6g,
 	.link_clk_disable = dsi_link_clk_disable_6g,
 	.clk_init_ver = dsi_clk_init_6g_v2,
@@ -197,6 +217,8 @@ static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = {
 		&msm8916_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_1,
 		&msm8996_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_2,
+		&msm8976_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_0,
 		&msm8998_dsi_cfg, &msm_dsi_6g_v2_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1,
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
index e2b7a7dfbe49..50a37ceb6a25 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
@@ -17,6 +17,7 @@
 #define MSM_DSI_6G_VER_MINOR_V1_3	0x10030000
 #define MSM_DSI_6G_VER_MINOR_V1_3_1	0x10030001
 #define MSM_DSI_6G_VER_MINOR_V1_4_1	0x10040001
+#define MSM_DSI_6G_VER_MINOR_V1_4_2	0x10040002
 #define MSM_DSI_6G_VER_MINOR_V2_2_0	0x20000000
 #define MSM_DSI_6G_VER_MINOR_V2_2_1	0x20020001
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 1e7b1be25bb0..458cec82ae13 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -1293,14 +1293,13 @@ static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len)
 static int dsi_cmd_dma_rx(struct msm_dsi_host *msm_host,
 			u8 *buf, int rx_byte, int pkt_size)
 {
-	u32 *lp, *temp, data;
+	u32 *temp, data;
 	int i, j = 0, cnt;
 	u32 read_cnt;
 	u8 reg[16];
 	int repeated_bytes = 0;
 	int buf_offset = buf - msm_host->rx_buf;
 
-	lp = (u32 *)buf;
 	temp = (u32 *)reg;
 	cnt = (rx_byte + 3) >> 2;
 	if (cnt > 4)
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index 3522863a4984..b0cfa67d2a57 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -145,7 +145,7 @@ int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing,
 {
 	const unsigned long bit_rate = clk_req->bitclk_rate;
 	const unsigned long esc_rate = clk_req->escclk_rate;
-	s32 ui, ui_x8, lpx;
+	s32 ui, ui_x8;
 	s32 tmax, tmin;
 	s32 pcnt0 = 50;
 	s32 pcnt1 = 50;
@@ -175,7 +175,6 @@ int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing,
 
 	ui = mult_frac(NSEC_PER_MSEC, coeff, bit_rate / 1000);
 	ui_x8 = ui << 3;
-	lpx = mult_frac(NSEC_PER_MSEC, coeff, esc_rate / 1000);
 
 	temp = S_DIV_ROUND_UP(38 * coeff - val_ckln * ui, ui_x8);
 	tmin = max_t(s32, temp, 0);
@@ -262,7 +261,7 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
 {
 	const unsigned long bit_rate = clk_req->bitclk_rate;
 	const unsigned long esc_rate = clk_req->escclk_rate;
-	s32 ui, ui_x8, lpx;
+	s32 ui, ui_x8;
 	s32 tmax, tmin;
 	s32 pcnt0 = 50;
 	s32 pcnt1 = 50;
@@ -284,7 +283,6 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
 
 	ui = mult_frac(NSEC_PER_MSEC, coeff, bit_rate / 1000);
 	ui_x8 = ui << 3;
-	lpx = mult_frac(NSEC_PER_MSEC, coeff, esc_rate / 1000);
 
 	temp = S_DIV_ROUND_UP(38 * coeff, ui_x8);
 	tmin = max_t(s32, temp, 0);
@@ -485,6 +483,8 @@ static const struct of_device_id dsi_phy_dt_match[] = {
 #ifdef CONFIG_DRM_MSM_DSI_28NM_PHY
 	{ .compatible = "qcom,dsi-phy-28nm-hpm",
 	  .data = &dsi_phy_28nm_hpm_cfgs },
+	{ .compatible = "qcom,dsi-phy-28nm-hpm-fam-b",
+	  .data = &dsi_phy_28nm_hpm_famb_cfgs },
 	{ .compatible = "qcom,dsi-phy-28nm-lp",
 	  .data = &dsi_phy_28nm_lp_cfgs },
 #endif
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
index c4069ce6afe6..24b294ed3059 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
@@ -40,6 +40,7 @@ struct msm_dsi_phy_cfg {
 };
 
 extern const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs;
+extern const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_famb_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_28nm_lp_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
index b3f678f6c2aa..c3c580cfd8b1 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
@@ -39,15 +39,10 @@ static void dsi_28nm_dphy_set_timing(struct msm_dsi_phy *phy,
 		DSI_28nm_PHY_TIMING_CTRL_11_TRIG3_CMD(0));
 }
 
-static void dsi_28nm_phy_regulator_ctrl(struct msm_dsi_phy *phy, bool enable)
+static void dsi_28nm_phy_regulator_enable_dcdc(struct msm_dsi_phy *phy)
 {
 	void __iomem *base = phy->reg_base;
 
-	if (!enable) {
-		dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CAL_PWR_CFG, 0);
-		return;
-	}
-
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_0, 0x0);
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CAL_PWR_CFG, 1);
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_5, 0);
@@ -56,6 +51,39 @@ static void dsi_28nm_phy_regulator_ctrl(struct msm_dsi_phy *phy, bool enable)
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_1, 0x9);
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_0, 0x7);
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_4, 0x20);
+	dsi_phy_write(phy->base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x00);
+}
+
+static void dsi_28nm_phy_regulator_enable_ldo(struct msm_dsi_phy *phy)
+{
+	void __iomem *base = phy->reg_base;
+
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_0, 0x0);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CAL_PWR_CFG, 0);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_5, 0x7);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_3, 0);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_2, 0x1);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_1, 0x1);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_4, 0x20);
+
+	if (phy->cfg->type == MSM_DSI_PHY_28NM_LP)
+		dsi_phy_write(phy->base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x05);
+	else
+		dsi_phy_write(phy->base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x0d);
+}
+
+static void dsi_28nm_phy_regulator_ctrl(struct msm_dsi_phy *phy, bool enable)
+{
+	if (!enable) {
+		dsi_phy_write(phy->reg_base +
+			      REG_DSI_28nm_PHY_REGULATOR_CAL_PWR_CFG, 0);
+		return;
+	}
+
+	if (phy->regulator_ldo_mode)
+		dsi_28nm_phy_regulator_enable_ldo(phy);
+	else
+		dsi_28nm_phy_regulator_enable_dcdc(phy);
 }
 
 static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
@@ -77,8 +105,6 @@ static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 
 	dsi_28nm_phy_regulator_ctrl(phy, true);
 
-	dsi_phy_write(base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x00);
-
 	dsi_28nm_dphy_set_timing(phy, timing);
 
 	dsi_phy_write(base + REG_DSI_28nm_PHY_CTRL_1, 0x00);
@@ -142,6 +168,24 @@ const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs = {
 	.num_dsi_phy = 2,
 };
 
+const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_famb_cfgs = {
+	.type = MSM_DSI_PHY_28NM_HPM,
+	.src_pll_truthtable = { {true, true}, {false, true} },
+	.reg_cfg = {
+		.num = 1,
+		.regs = {
+			{"vddio", 100000, 100},
+		},
+	},
+	.ops = {
+		.enable = dsi_28nm_phy_enable,
+		.disable = dsi_28nm_phy_disable,
+		.init = msm_dsi_phy_init_common,
+	},
+	.io_start = { 0x1a94400, 0x1a96400 },
+	.num_dsi_phy = 2,
+};
+
 const struct msm_dsi_phy_cfg dsi_phy_28nm_lp_cfgs = {
 	.type = MSM_DSI_PHY_28NM_LP,
 	.src_pll_truthtable = { {true, true}, {true, true} },
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
index 1697e61f9c2f..8a38d4b95102 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
@@ -29,8 +29,12 @@ static int msm_hdmi_phy_resource_init(struct hdmi_phy *phy)
 		reg = devm_regulator_get(dev, cfg->reg_names[i]);
 		if (IS_ERR(reg)) {
 			ret = PTR_ERR(reg);
-			DRM_DEV_ERROR(dev, "failed to get phy regulator: %s (%d)\n",
-				cfg->reg_names[i], ret);
+			if (ret != -EPROBE_DEFER) {
+				DRM_DEV_ERROR(dev,
+					      "failed to get phy regulator: %s (%d)\n",
+					      cfg->reg_names[i], ret);
+			}
+
 			return ret;
 		}
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index a052364a5d74..18f3a5c53ffb 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -16,6 +16,7 @@
 #include <linux/pm_opp.h>
 #include <linux/devfreq.h>
 #include <linux/devcoredump.h>
+#include <linux/sched/task.h>
 
 /*
  * Power Management:
@@ -838,7 +839,7 @@ msm_gpu_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev,
 		return ERR_CAST(aspace);
 	}
 
-	ret = aspace->mmu->funcs->attach(aspace->mmu, NULL, 0);
+	ret = aspace->mmu->funcs->attach(aspace->mmu);
 	if (ret) {
 		msm_gem_address_space_put(aspace);
 		return ERR_PTR(ret);
@@ -995,8 +996,7 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
 	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace, false);
 
 	if (!IS_ERR_OR_NULL(gpu->aspace)) {
-		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu,
-			NULL, 0);
+		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu);
 		msm_gem_address_space_put(gpu->aspace);
 	}
 }
diff --git a/drivers/gpu/drm/msm/msm_gpummu.c b/drivers/gpu/drm/msm/msm_gpummu.c
index 34f643a0c28a..34980d8eb7ad 100644
--- a/drivers/gpu/drm/msm/msm_gpummu.c
+++ b/drivers/gpu/drm/msm/msm_gpummu.c
@@ -21,14 +21,12 @@ struct msm_gpummu {
 #define GPUMMU_PAGE_SIZE SZ_4K
 #define TABLE_SIZE (sizeof(uint32_t) * GPUMMU_VA_RANGE / GPUMMU_PAGE_SIZE)
 
-static int msm_gpummu_attach(struct msm_mmu *mmu, const char * const *names,
-		int cnt)
+static int msm_gpummu_attach(struct msm_mmu *mmu)
 {
 	return 0;
 }
 
-static void msm_gpummu_detach(struct msm_mmu *mmu, const char * const *names,
-		int cnt)
+static void msm_gpummu_detach(struct msm_mmu *mmu)
 {
 }
 
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 8c95c31e2b12..ad58cfe5998e 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -23,16 +23,14 @@ static int msm_fault_handler(struct iommu_domain *domain, struct device *dev,
 	return 0;
 }
 
-static int msm_iommu_attach(struct msm_mmu *mmu, const char * const *names,
-			    int cnt)
+static int msm_iommu_attach(struct msm_mmu *mmu)
 {
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
 
 	return iommu_attach_device(iommu->domain, mmu->dev);
 }
 
-static void msm_iommu_detach(struct msm_mmu *mmu, const char * const *names,
-			     int cnt)
+static void msm_iommu_detach(struct msm_mmu *mmu)
 {
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
 
diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h
index 871d56303697..67a623f14319 100644
--- a/drivers/gpu/drm/msm/msm_mmu.h
+++ b/drivers/gpu/drm/msm/msm_mmu.h
@@ -10,8 +10,8 @@
 #include <linux/iommu.h>
 
 struct msm_mmu_funcs {
-	int (*attach)(struct msm_mmu *mmu, const char * const *names, int cnt);
-	void (*detach)(struct msm_mmu *mmu, const char * const *names, int cnt);
+	int (*attach)(struct msm_mmu *mmu);
+	void (*detach)(struct msm_mmu *mmu);
 	int (*map)(struct msm_mmu *mmu, uint64_t iova, struct sg_table *sgt,
 			unsigned len, int prot);
 	int (*unmap)(struct msm_mmu *mmu, uint64_t iova, unsigned len);
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index c7832a951039..af7ceb246c7c 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -298,7 +298,7 @@ void msm_rd_debugfs_cleanup(struct msm_drm_private *priv)
 
 static void snapshot_buf(struct msm_rd_state *rd,
 		struct msm_gem_submit *submit, int idx,
-		uint64_t iova, uint32_t size)
+		uint64_t iova, uint32_t size, bool full)
 {
 	struct msm_gem_object *obj = submit->bos[idx].obj;
 	unsigned offset = 0;
@@ -318,6 +318,9 @@ static void snapshot_buf(struct msm_rd_state *rd,
 	rd_write_section(rd, RD_GPUADDR,
 			(uint32_t[3]){ iova, size, iova >> 32 }, 12);
 
+	if (!full)
+		return;
+
 	/* But only dump the contents of buffers marked READ */
 	if (!(submit->bos[idx].flags & MSM_SUBMIT_BO_READ))
 		return;
@@ -381,18 +384,21 @@ void msm_rd_dump_submit(struct msm_rd_state *rd, struct msm_gem_submit *submit,
 	rd_write_section(rd, RD_CMD, msg, ALIGN(n, 4));
 
 	for (i = 0; i < submit->nr_bos; i++)
-		if (should_dump(submit, i))
-			snapshot_buf(rd, submit, i, 0, 0);
+		snapshot_buf(rd, submit, i, 0, 0, should_dump(submit, i));
 
 	for (i = 0; i < submit->nr_cmds; i++) {
-		uint64_t iova = submit->cmd[i].iova;
 		uint32_t szd  = submit->cmd[i].size; /* in dwords */
 
 		/* snapshot cmdstream bo's (if we haven't already): */
 		if (!should_dump(submit, i)) {
 			snapshot_buf(rd, submit, submit->cmd[i].idx,
-					submit->cmd[i].iova, szd * 4);
+					submit->cmd[i].iova, szd * 4, true);
 		}
+	}
+
+	for (i = 0; i < submit->nr_cmds; i++) {
+		uint64_t iova = submit->cmd[i].iova;
+		uint32_t szd  = submit->cmd[i].size; /* in dwords */
 
 		switch (submit->cmd[i].type) {
 		case MSM_SUBMIT_CMD_IB_TARGET_BUF:
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 661e47acc354..adbf3bfae805 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -74,6 +74,16 @@ config QCOM_MDT_LOADER
 	tristate
 	select QCOM_SCM
 
+config QCOM_OCMEM
+	tristate "Qualcomm On Chip Memory (OCMEM) driver"
+	depends on ARCH_QCOM
+	select QCOM_SCM
+	help
+          The On Chip Memory (OCMEM) allocator allows various clients to
+          allocate memory from OCMEM based on performance, latency and power
+          requirements. This is typically used by the GPU, camera/video, and
+          audio components on some Snapdragon SoCs.
+
 config QCOM_PM
 	bool "Qualcomm Power Management"
 	depends on ARCH_QCOM && !ARM64
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 162788701a77..aab333720bfd 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_QCOM_COMMAND_DB) += cmd-db.o
 obj-$(CONFIG_QCOM_GLINK_SSR) +=	glink_ssr.o
 obj-$(CONFIG_QCOM_GSBI)	+=	qcom_gsbi.o
 obj-$(CONFIG_QCOM_MDT_LOADER)	+= mdt_loader.o
+obj-$(CONFIG_QCOM_OCMEM)	+= ocmem.o
 obj-$(CONFIG_QCOM_PM)	+=	spm.o
 obj-$(CONFIG_QCOM_QMI_HELPERS)	+= qmi_helpers.o
 qmi_helpers-y	+= qmi_encdec.o qmi_interface.o
diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c
new file mode 100644
index 000000000000..7f9e9944d1ea
--- /dev/null
+++ b/drivers/soc/qcom/ocmem.c
@@ -0,0 +1,433 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * The On Chip Memory (OCMEM) allocator allows various clients to allocate
+ * memory from OCMEM based on performance, latency and power requirements.
+ * This is typically used by the GPU, camera/video, and audio components on
+ * some Snapdragon SoCs.
+ *
+ * Copyright (C) 2019 Brian Masney <masneyb@onstation.org>
+ * Copyright (C) 2015 Red Hat. Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/qcom_scm.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <soc/qcom/ocmem.h>
+
+enum region_mode {
+	WIDE_MODE = 0x0,
+	THIN_MODE,
+	MODE_DEFAULT = WIDE_MODE,
+};
+
+enum ocmem_macro_state {
+	PASSTHROUGH = 0,
+	PERI_ON = 1,
+	CORE_ON = 2,
+	CLK_OFF = 4,
+};
+
+struct ocmem_region {
+	bool interleaved;
+	enum region_mode mode;
+	unsigned int num_macros;
+	enum ocmem_macro_state macro_state[4];
+	unsigned long macro_size;
+	unsigned long region_size;
+};
+
+struct ocmem_config {
+	uint8_t num_regions;
+	unsigned long macro_size;
+};
+
+struct ocmem {
+	struct device *dev;
+	const struct ocmem_config *config;
+	struct resource *memory;
+	void __iomem *mmio;
+	unsigned int num_ports;
+	unsigned int num_macros;
+	bool interleaved;
+	struct ocmem_region *regions;
+	unsigned long active_allocations;
+};
+
+#define OCMEM_MIN_ALIGN				SZ_64K
+#define OCMEM_MIN_ALLOC				SZ_64K
+
+#define OCMEM_REG_HW_VERSION			0x00000000
+#define OCMEM_REG_HW_PROFILE			0x00000004
+
+#define OCMEM_REG_REGION_MODE_CTL		0x00001000
+#define OCMEM_REGION_MODE_CTL_REG0_THIN		0x00000001
+#define OCMEM_REGION_MODE_CTL_REG1_THIN		0x00000002
+#define OCMEM_REGION_MODE_CTL_REG2_THIN		0x00000004
+#define OCMEM_REGION_MODE_CTL_REG3_THIN		0x00000008
+
+#define OCMEM_REG_GFX_MPU_START			0x00001004
+#define OCMEM_REG_GFX_MPU_END			0x00001008
+
+#define OCMEM_HW_PROFILE_NUM_PORTS(val)		FIELD_PREP(0x0000000f, (val))
+#define OCMEM_HW_PROFILE_NUM_MACROS(val)	FIELD_PREP(0x00003f00, (val))
+
+#define OCMEM_HW_PROFILE_LAST_REGN_HALFSIZE	0x00010000
+#define OCMEM_HW_PROFILE_INTERLEAVING		0x00020000
+#define OCMEM_REG_GEN_STATUS			0x0000000c
+
+#define OCMEM_REG_PSGSC_STATUS			0x00000038
+#define OCMEM_REG_PSGSC_CTL(i0)			(0x0000003c + 0x1*(i0))
+
+#define OCMEM_PSGSC_CTL_MACRO0_MODE(val)	FIELD_PREP(0x00000007, (val))
+#define OCMEM_PSGSC_CTL_MACRO1_MODE(val)	FIELD_PREP(0x00000070, (val))
+#define OCMEM_PSGSC_CTL_MACRO2_MODE(val)	FIELD_PREP(0x00000700, (val))
+#define OCMEM_PSGSC_CTL_MACRO3_MODE(val)	FIELD_PREP(0x00007000, (val))
+
+#define OCMEM_CLK_CORE_IDX			0
+static struct clk_bulk_data ocmem_clks[] = {
+	{
+		.id = "core",
+	},
+	{
+		.id = "iface",
+	},
+};
+
+static inline void ocmem_write(struct ocmem *ocmem, u32 reg, u32 data)
+{
+	writel(data, ocmem->mmio + reg);
+}
+
+static inline u32 ocmem_read(struct ocmem *ocmem, u32 reg)
+{
+	return readl(ocmem->mmio + reg);
+}
+
+static void update_ocmem(struct ocmem *ocmem)
+{
+	uint32_t region_mode_ctrl = 0x0;
+	int i;
+
+	if (!qcom_scm_ocmem_lock_available()) {
+		for (i = 0; i < ocmem->config->num_regions; i++) {
+			struct ocmem_region *region = &ocmem->regions[i];
+
+			if (region->mode == THIN_MODE)
+				region_mode_ctrl |= BIT(i);
+		}
+
+		dev_dbg(ocmem->dev, "ocmem_region_mode_control %x\n",
+			region_mode_ctrl);
+		ocmem_write(ocmem, OCMEM_REG_REGION_MODE_CTL, region_mode_ctrl);
+	}
+
+	for (i = 0; i < ocmem->config->num_regions; i++) {
+		struct ocmem_region *region = &ocmem->regions[i];
+		u32 data;
+
+		data = OCMEM_PSGSC_CTL_MACRO0_MODE(region->macro_state[0]) |
+			OCMEM_PSGSC_CTL_MACRO1_MODE(region->macro_state[1]) |
+			OCMEM_PSGSC_CTL_MACRO2_MODE(region->macro_state[2]) |
+			OCMEM_PSGSC_CTL_MACRO3_MODE(region->macro_state[3]);
+
+		ocmem_write(ocmem, OCMEM_REG_PSGSC_CTL(i), data);
+	}
+}
+
+static unsigned long phys_to_offset(struct ocmem *ocmem,
+				    unsigned long addr)
+{
+	if (addr < ocmem->memory->start || addr >= ocmem->memory->end)
+		return 0;
+
+	return addr - ocmem->memory->start;
+}
+
+static unsigned long device_address(struct ocmem *ocmem,
+				    enum ocmem_client client,
+				    unsigned long addr)
+{
+	WARN_ON(client != OCMEM_GRAPHICS);
+
+	/* TODO: gpu uses phys_to_offset, but others do not.. */
+	return phys_to_offset(ocmem, addr);
+}
+
+static void update_range(struct ocmem *ocmem, struct ocmem_buf *buf,
+			 enum ocmem_macro_state mstate, enum region_mode rmode)
+{
+	unsigned long offset = 0;
+	int i, j;
+
+	for (i = 0; i < ocmem->config->num_regions; i++) {
+		struct ocmem_region *region = &ocmem->regions[i];
+
+		if (buf->offset <= offset && offset < buf->offset + buf->len)
+			region->mode = rmode;
+
+		for (j = 0; j < region->num_macros; j++) {
+			if (buf->offset <= offset &&
+			    offset < buf->offset + buf->len)
+				region->macro_state[j] = mstate;
+
+			offset += region->macro_size;
+		}
+	}
+
+	update_ocmem(ocmem);
+}
+
+struct ocmem *of_get_ocmem(struct device *dev)
+{
+	struct platform_device *pdev;
+	struct device_node *devnode;
+
+	devnode = of_parse_phandle(dev->of_node, "sram", 0);
+	if (!devnode || !devnode->parent) {
+		dev_err(dev, "Cannot look up sram phandle\n");
+		return ERR_PTR(-ENODEV);
+	}
+
+	pdev = of_find_device_by_node(devnode->parent);
+	if (!pdev) {
+		dev_err(dev, "Cannot find device node %s\n", devnode->name);
+		return ERR_PTR(-EPROBE_DEFER);
+	}
+
+	return platform_get_drvdata(pdev);
+}
+EXPORT_SYMBOL(of_get_ocmem);
+
+struct ocmem_buf *ocmem_allocate(struct ocmem *ocmem, enum ocmem_client client,
+				 unsigned long size)
+{
+	struct ocmem_buf *buf;
+	int ret;
+
+	/* TODO: add support for other clients... */
+	if (WARN_ON(client != OCMEM_GRAPHICS))
+		return ERR_PTR(-ENODEV);
+
+	if (size < OCMEM_MIN_ALLOC || !IS_ALIGNED(size, OCMEM_MIN_ALIGN))
+		return ERR_PTR(-EINVAL);
+
+	if (test_and_set_bit_lock(BIT(client), &ocmem->active_allocations))
+		return ERR_PTR(-EBUSY);
+
+	buf = kzalloc(sizeof(*buf), GFP_KERNEL);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto err_unlock;
+	}
+
+	buf->offset = 0;
+	buf->addr = device_address(ocmem, client, buf->offset);
+	buf->len = size;
+
+	update_range(ocmem, buf, CORE_ON, WIDE_MODE);
+
+	if (qcom_scm_ocmem_lock_available()) {
+		ret = qcom_scm_ocmem_lock(QCOM_SCM_OCMEM_GRAPHICS_ID,
+					  buf->offset, buf->len, WIDE_MODE);
+		if (ret) {
+			dev_err(ocmem->dev, "could not lock: %d\n", ret);
+			ret = -EINVAL;
+			goto err_kfree;
+		}
+	} else {
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_START, buf->offset);
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_END,
+			    buf->offset + buf->len);
+	}
+
+	dev_dbg(ocmem->dev, "using %ldK of OCMEM at 0x%08lx for client %d\n",
+		size / 1024, buf->addr, client);
+
+	return buf;
+
+err_kfree:
+	kfree(buf);
+err_unlock:
+	clear_bit_unlock(BIT(client), &ocmem->active_allocations);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL(ocmem_allocate);
+
+void ocmem_free(struct ocmem *ocmem, enum ocmem_client client,
+		struct ocmem_buf *buf)
+{
+	/* TODO: add support for other clients... */
+	if (WARN_ON(client != OCMEM_GRAPHICS))
+		return;
+
+	update_range(ocmem, buf, CLK_OFF, MODE_DEFAULT);
+
+	if (qcom_scm_ocmem_lock_available()) {
+		int ret;
+
+		ret = qcom_scm_ocmem_unlock(QCOM_SCM_OCMEM_GRAPHICS_ID,
+					    buf->offset, buf->len);
+		if (ret)
+			dev_err(ocmem->dev, "could not unlock: %d\n", ret);
+	} else {
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_START, 0x0);
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_END, 0x0);
+	}
+
+	kfree(buf);
+
+	clear_bit_unlock(BIT(client), &ocmem->active_allocations);
+}
+EXPORT_SYMBOL(ocmem_free);
+
+static int ocmem_dev_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	unsigned long reg, region_size;
+	int i, j, ret, num_banks;
+	struct resource *res;
+	struct ocmem *ocmem;
+
+	if (!qcom_scm_is_available())
+		return -EPROBE_DEFER;
+
+	ocmem = devm_kzalloc(dev, sizeof(*ocmem), GFP_KERNEL);
+	if (!ocmem)
+		return -ENOMEM;
+
+	ocmem->dev = dev;
+	ocmem->config = device_get_match_data(dev);
+
+	ret = devm_clk_bulk_get(dev, ARRAY_SIZE(ocmem_clks), ocmem_clks);
+	if (ret) {
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Unable to get clocks\n");
+
+		return ret;
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ctrl");
+	ocmem->mmio = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ocmem->mmio)) {
+		dev_err(&pdev->dev, "Failed to ioremap ocmem_ctrl resource\n");
+		return PTR_ERR(ocmem->mmio);
+	}
+
+	ocmem->memory = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						     "mem");
+	if (!ocmem->memory) {
+		dev_err(dev, "Could not get mem region\n");
+		return -ENXIO;
+	}
+
+	/* The core clock is synchronous with graphics */
+	WARN_ON(clk_set_rate(ocmem_clks[OCMEM_CLK_CORE_IDX].clk, 1000) < 0);
+
+	ret = clk_bulk_prepare_enable(ARRAY_SIZE(ocmem_clks), ocmem_clks);
+	if (ret) {
+		dev_info(ocmem->dev, "Failed to enable clocks\n");
+		return ret;
+	}
+
+	if (qcom_scm_restore_sec_cfg_available()) {
+		dev_dbg(dev, "configuring scm\n");
+		ret = qcom_scm_restore_sec_cfg(QCOM_SCM_OCMEM_DEV_ID, 0);
+		if (ret) {
+			dev_err(dev, "Could not enable secure configuration\n");
+			goto err_clk_disable;
+		}
+	}
+
+	reg = ocmem_read(ocmem, OCMEM_REG_HW_PROFILE);
+	ocmem->num_ports = OCMEM_HW_PROFILE_NUM_PORTS(reg);
+	ocmem->num_macros = OCMEM_HW_PROFILE_NUM_MACROS(reg);
+	ocmem->interleaved = !!(reg & OCMEM_HW_PROFILE_INTERLEAVING);
+
+	num_banks = ocmem->num_ports / 2;
+	region_size = ocmem->config->macro_size * num_banks;
+
+	dev_info(dev, "%u ports, %u regions, %u macros, %sinterleaved\n",
+		 ocmem->num_ports, ocmem->config->num_regions,
+		 ocmem->num_macros, ocmem->interleaved ? "" : "not ");
+
+	ocmem->regions = devm_kcalloc(dev, ocmem->config->num_regions,
+				      sizeof(struct ocmem_region), GFP_KERNEL);
+	if (!ocmem->regions) {
+		ret = -ENOMEM;
+		goto err_clk_disable;
+	}
+
+	for (i = 0; i < ocmem->config->num_regions; i++) {
+		struct ocmem_region *region = &ocmem->regions[i];
+
+		if (WARN_ON(num_banks > ARRAY_SIZE(region->macro_state))) {
+			ret = -EINVAL;
+			goto err_clk_disable;
+		}
+
+		region->mode = MODE_DEFAULT;
+		region->num_macros = num_banks;
+
+		if (i == (ocmem->config->num_regions - 1) &&
+		    reg & OCMEM_HW_PROFILE_LAST_REGN_HALFSIZE) {
+			region->macro_size = ocmem->config->macro_size / 2;
+			region->region_size = region_size / 2;
+		} else {
+			region->macro_size = ocmem->config->macro_size;
+			region->region_size = region_size;
+		}
+
+		for (j = 0; j < ARRAY_SIZE(region->macro_state); j++)
+			region->macro_state[j] = CLK_OFF;
+	}
+
+	platform_set_drvdata(pdev, ocmem);
+
+	return 0;
+
+err_clk_disable:
+	clk_bulk_disable_unprepare(ARRAY_SIZE(ocmem_clks), ocmem_clks);
+	return ret;
+}
+
+static int ocmem_dev_remove(struct platform_device *pdev)
+{
+	clk_bulk_disable_unprepare(ARRAY_SIZE(ocmem_clks), ocmem_clks);
+
+	return 0;
+}
+
+static const struct ocmem_config ocmem_8974_config = {
+	.num_regions = 3,
+	.macro_size = SZ_128K,
+};
+
+static const struct of_device_id ocmem_of_match[] = {
+	{ .compatible = "qcom,msm8974-ocmem", .data = &ocmem_8974_config },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, ocmem_of_match);
+
+static struct platform_driver ocmem_driver = {
+	.probe = ocmem_dev_probe,
+	.remove = ocmem_dev_remove,
+	.driver = {
+		.name = "ocmem",
+		.of_match_table = ocmem_of_match,
+	},
+};
+
+module_platform_driver(ocmem_driver);
+
+MODULE_DESCRIPTION("On Chip Memory (OCMEM) allocator for some Snapdragon SoCs");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h
index 2d5eff506e13..04382e1798e4 100644
--- a/include/linux/qcom_scm.h
+++ b/include/linux/qcom_scm.h
@@ -24,6 +24,26 @@ struct qcom_scm_vmperm {
 	int perm;
 };
 
+enum qcom_scm_ocmem_client {
+	QCOM_SCM_OCMEM_UNUSED_ID = 0x0,
+	QCOM_SCM_OCMEM_GRAPHICS_ID,
+	QCOM_SCM_OCMEM_VIDEO_ID,
+	QCOM_SCM_OCMEM_LP_AUDIO_ID,
+	QCOM_SCM_OCMEM_SENSORS_ID,
+	QCOM_SCM_OCMEM_OTHER_OS_ID,
+	QCOM_SCM_OCMEM_DEBUG_ID,
+};
+
+enum qcom_scm_sec_dev_id {
+	QCOM_SCM_MDSS_DEV_ID    = 1,
+	QCOM_SCM_OCMEM_DEV_ID   = 5,
+	QCOM_SCM_PCIE0_DEV_ID   = 11,
+	QCOM_SCM_PCIE1_DEV_ID   = 12,
+	QCOM_SCM_GFX_DEV_ID     = 18,
+	QCOM_SCM_UFS_DEV_ID     = 19,
+	QCOM_SCM_ICE_DEV_ID     = 20,
+};
+
 #define QCOM_SCM_VMID_HLOS       0x3
 #define QCOM_SCM_VMID_MSS_MSA    0xF
 #define QCOM_SCM_VMID_WLAN       0x18
@@ -41,6 +61,11 @@ extern bool qcom_scm_is_available(void);
 extern bool qcom_scm_hdcp_available(void);
 extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt,
 			     u32 *resp);
+extern bool qcom_scm_ocmem_lock_available(void);
+extern int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset,
+			       u32 size, u32 mode);
+extern int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset,
+				 u32 size);
 extern bool qcom_scm_pas_supported(u32 peripheral);
 extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata,
 				   size_t size);
@@ -55,6 +80,7 @@ extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
 extern void qcom_scm_cpu_power_down(u32 flags);
 extern u32 qcom_scm_get_version(void);
 extern int qcom_scm_set_remote_state(u32 state, u32 id);
+extern bool qcom_scm_restore_sec_cfg_available(void);
 extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare);
 extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size);
 extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare);
diff --git a/include/soc/qcom/ocmem.h b/include/soc/qcom/ocmem.h
new file mode 100644
index 000000000000..02a8bc2677b1
--- /dev/null
+++ b/include/soc/qcom/ocmem.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * The On Chip Memory (OCMEM) allocator allows various clients to allocate
+ * memory from OCMEM based on performance, latency and power requirements.
+ * This is typically used by the GPU, camera/video, and audio components on
+ * some Snapdragon SoCs.
+ *
+ * Copyright (C) 2019 Brian Masney <masneyb@onstation.org>
+ * Copyright (C) 2015 Red Hat. Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+
+#ifndef __OCMEM_H__
+#define __OCMEM_H__
+
+enum ocmem_client {
+	/* GMEM clients */
+	OCMEM_GRAPHICS = 0x0,
+	/*
+	 * TODO add more once ocmem_allocate() is clever enough to
+	 * deal with multiple clients.
+	 */
+	OCMEM_CLIENT_MAX,
+};
+
+struct ocmem;
+
+struct ocmem_buf {
+	unsigned long offset;
+	unsigned long addr;
+	unsigned long len;
+};
+
+#if IS_ENABLED(CONFIG_QCOM_OCMEM)
+
+struct ocmem *of_get_ocmem(struct device *dev);
+struct ocmem_buf *ocmem_allocate(struct ocmem *ocmem, enum ocmem_client client,
+				 unsigned long size);
+void ocmem_free(struct ocmem *ocmem, enum ocmem_client client,
+		struct ocmem_buf *buf);
+
+#else /* IS_ENABLED(CONFIG_QCOM_OCMEM) */
+
+static inline struct ocmem *of_get_ocmem(struct device *dev)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+static inline struct ocmem_buf *ocmem_allocate(struct ocmem *ocmem,
+					       enum ocmem_client client,
+					       unsigned long size)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+static inline void ocmem_free(struct ocmem *ocmem, enum ocmem_client client,
+			      struct ocmem_buf *buf)
+{
+}
+
+#endif /* IS_ENABLED(CONFIG_QCOM_OCMEM) */
+
+#endif /* __OCMEM_H__ */