Merge tag 'rproc-v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/remoteproc/linux

Pull remoteproc updates from Bjorn Andersson:
 "rproc-virtio device names are now auto generated, to avoid conflicts
  between remoteproc instances.

  The imx_rproc driver is extended with support for communicating with
  and attaching to a running M4 on i.MX8QXP, as well as support for
  attaching to the M4 after self-recovering from a crash. Support is
  added for i.MX8QM and mailbox channels are reconnected during the
  recovery process, in order to avoid data corruption.

  The Xilinx Zynqmp firmware interface is extended and support for the
  Xilinx R5 RPU is introduced.

  Various resources leaks, primarily in error paths, throughout the
  Qualcomm drivers are corrected.

  Lastly a fix to ensure that pm_relax is invoked even if the remoteproc
  instance is stopped between a crash is being reported and the recovery
  handler is scheduled"

* tag 'rproc-v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/remoteproc/linux: (25 commits)
  remoteproc: core: Do pm_relax when in RPROC_OFFLINE state
  remoteproc: qcom: q6v5: Fix missing clk_disable_unprepare() in q6v5_wcss_qcs404_power_on()
  remoteproc: qcom_q6v5_pas: Fix missing of_node_put() in adsp_alloc_memory_region()
  remoteproc: qcom_q6v5_pas: detach power domains on remove
  remoteproc: qcom_q6v5_pas: disable wakeup on probe fail or remove
  remoteproc: qcom: q6v5: Fix potential null-ptr-deref in q6v5_wcss_init_mmio()
  remoteproc: sysmon: fix memory leak in qcom_add_sysmon_subdev()
  remoteproc: sysmon: Make QMI message rules const
  drivers: remoteproc: Add Xilinx r5 remoteproc driver
  firmware: xilinx: Add RPU configuration APIs
  firmware: xilinx: Add shutdown/wakeup APIs
  firmware: xilinx: Add ZynqMP firmware ioctl enums for RPU configuration.
  arm64: dts: xilinx: zynqmp: Add RPU subsystem device node
  dt-bindings: remoteproc: Add Xilinx RPU subsystem bindings
  remoteproc: core: Use device_match_of_node()
  remoteproc: imx_rproc: Correct i.MX93 DRAM mapping
  remoteproc: imx_rproc: Enable attach recovery for i.MX8QM/QXP
  remoteproc: imx_rproc: Request mbox channel later
  remoteproc: imx_rproc: Support i.MX8QM
  remoteproc: imx_rproc: Support kicking Mcore from Linux for i.MX8QXP
  ...

15 files changed, 1760 insertions, 20 deletions

diff --git a/Documentation/devicetree/bindings/remoteproc/fsl,imx-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/fsl,imx-rproc.yaml
index e732255b901965..ae2eab4452ddc1 100644
--- a/Documentation/devicetree/bindings/remoteproc/fsl,imx-rproc.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/fsl,imx-rproc.yaml
@@ -22,6 +22,8 @@ properties:
       - fsl,imx8mn-cm7
       - fsl,imx8mp-cm7
       - fsl,imx8mq-cm4
+      - fsl,imx8qm-cm4
+      - fsl,imx8qxp-cm4
       - fsl,imx8ulp-cm33
       - fsl,imx93-cm33
 
@@ -54,12 +56,26 @@ properties:
     minItems: 1
     maxItems: 32
 
+  power-domains:
+    maxItems: 8
+
   fsl,auto-boot:
     $ref: /schemas/types.yaml#/definitions/flag
     description:
       Indicate whether need to load the default firmware and start the remote
       processor automatically.
 
+  fsl,entry-address:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      Specify CPU entry address for SCU enabled processor.
+
+  fsl,resource-id:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      This property is to specify the resource id of the remote processor in SoC
+      which supports SCFW
+
 required:
   - compatible
 
diff --git a/Documentation/devicetree/bindings/remoteproc/xlnx,zynqmp-r5fss.yaml b/Documentation/devicetree/bindings/remoteproc/xlnx,zynqmp-r5fss.yaml
new file mode 100644
index 00000000000000..9f677367dd9f7e
--- /dev/null
+++ b/Documentation/devicetree/bindings/remoteproc/xlnx,zynqmp-r5fss.yaml
@@ -0,0 +1,135 @@
+# SPDX-License-Identifier: (GPL-2.0-only or BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/remoteproc/xlnx,zynqmp-r5fss.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Xilinx R5F processor subsystem
+
+maintainers:
+  - Ben Levinsky <ben.levinsky@amd.com>
+  - Tanmay Shah <tanmay.shah@amd.com>
+
+description: |
+  The Xilinx platforms include a pair of Cortex-R5F processors (RPU) for
+  real-time processing based on the Cortex-R5F processor core from ARM.
+  The Cortex-R5F processor implements the Arm v7-R architecture and includes a
+  floating-point unit that implements the Arm VFPv3 instruction set.
+
+properties:
+  compatible:
+    const: xlnx,zynqmp-r5fss
+
+  xlnx,cluster-mode:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [0, 1, 2]
+    description: |
+      The RPU MPCore can operate in split mode (Dual-processor performance), Safety
+      lock-step mode(Both RPU cores execute the same code in lock-step,
+      clock-for-clock) or Single CPU mode (RPU core 0 is held in reset while
+      core 1 runs normally). The processor does not support dynamic configuration.
+      Switching between modes is only permitted immediately after a processor reset.
+      If set to  1 then lockstep mode and if 0 then split mode.
+      If set to  2 then single CPU mode. When not defined, default will be lockstep mode.
+      In summary,
+      0: split mode
+      1: lockstep mode (default)
+      2: single cpu mode
+
+patternProperties:
+  "^r5f-[a-f0-9]+$":
+    type: object
+    description: |
+      The RPU is located in the Low Power Domain of the Processor Subsystem.
+      Each processor includes separate L1 instruction and data caches and
+      tightly coupled memories (TCM). System memory is cacheable, but the TCM
+      memory space is non-cacheable.
+
+      Each RPU contains one 64KB memory and two 32KB memories that
+      are accessed via the TCM A and B port interfaces, for a total of 128KB
+      per processor. In lock-step mode, the processor has access to 256KB of
+      TCM memory.
+
+    properties:
+      compatible:
+        const: xlnx,zynqmp-r5f
+
+      power-domains:
+        maxItems: 1
+
+      mboxes:
+        minItems: 1
+        items:
+          - description: mailbox channel to send data to RPU
+          - description: mailbox channel to receive data from RPU
+
+      mbox-names:
+        minItems: 1
+        items:
+          - const: tx
+          - const: rx
+
+      sram:
+        $ref: /schemas/types.yaml#/definitions/phandle-array
+        minItems: 1
+        maxItems: 8
+        items:
+          maxItems: 1
+        description: |
+          phandles to one or more reserved on-chip SRAM regions. Other than TCM,
+          the RPU can execute instructions and access data from the OCM memory,
+          the main DDR memory, and other system memories.
+
+          The regions should be defined as child nodes of the respective SRAM
+          node, and should be defined as per the generic bindings in
+          Documentation/devicetree/bindings/sram/sram.yaml
+
+      memory-region:
+        description: |
+          List of phandles to the reserved memory regions associated with the
+          remoteproc device. This is variable and describes the memories shared with
+          the remote processor (e.g. remoteproc firmware and carveouts, rpmsg
+          vrings, ...). This reserved memory region will be allocated in DDR memory.
+        minItems: 1
+        maxItems: 8
+        items:
+          - description: region used for RPU firmware image section
+          - description: vdev buffer
+          - description: vring0
+          - description: vring1
+        additionalItems: true
+
+    required:
+      - compatible
+      - power-domains
+
+    unevaluatedProperties: false
+
+required:
+  - compatible
+
+additionalProperties: false
+
+examples:
+  - |
+    remoteproc {
+        compatible = "xlnx,zynqmp-r5fss";
+        xlnx,cluster-mode = <1>;
+
+        r5f-0 {
+            compatible = "xlnx,zynqmp-r5f";
+            power-domains = <&zynqmp_firmware 0x7>;
+            memory-region = <&rproc_0_fw_image>, <&rpu0vdev0buffer>, <&rpu0vdev0vring0>, <&rpu0vdev0vring1>;
+            mboxes = <&ipi_mailbox_rpu0 0>, <&ipi_mailbox_rpu0 1>;
+            mbox-names = "tx", "rx";
+        };
+
+        r5f-1 {
+            compatible = "xlnx,zynqmp-r5f";
+            power-domains = <&zynqmp_firmware 0x8>;
+            memory-region = <&rproc_1_fw_image>, <&rpu1vdev0buffer>, <&rpu1vdev0vring0>, <&rpu1vdev0vring1>;
+            mboxes = <&ipi_mailbox_rpu1 0>, <&ipi_mailbox_rpu1 1>;
+            mbox-names = "tx", "rx";
+        };
+    };
+...
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
index 307c76cd8544c7..4325cb8526edce 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
@@ -100,6 +100,22 @@
 		};
 	};
 
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		rproc_0_fw_image: memory@3ed00000 {
+			no-map;
+			reg = <0x0 0x3ed00000 0x0 0x40000>;
+		};
+
+		rproc_1_fw_image: memory@3ef00000 {
+			no-map;
+			reg = <0x0 0x3ef00000 0x0 0x40000>;
+		};
+	};
+
 	zynqmp_ipi: zynqmp_ipi {
 		compatible = "xlnx,zynqmp-ipi-mailbox";
 		interrupt-parent = <&gic>;
@@ -203,6 +219,23 @@
 		ranges;
 	};
 
+	remoteproc {
+		compatible = "xlnx,zynqmp-r5fss";
+		xlnx,cluster-mode = <1>;
+
+		r5f-0 {
+			compatible = "xlnx,zynqmp-r5f";
+			power-domains = <&zynqmp_firmware PD_RPU_0>;
+			memory-region = <&rproc_0_fw_image>;
+		};
+
+		r5f-1 {
+			compatible = "xlnx,zynqmp-r5f";
+			power-domains = <&zynqmp_firmware PD_RPU_1>;
+			memory-region = <&rproc_1_fw_image>;
+		};
+	};
+
 	amba: axi {
 		compatible = "simple-bus";
 		#address-cells = <2>;
diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 6bc6b6c84241ca..129f68d7a6f530 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -1167,6 +1167,103 @@ int zynqmp_pm_release_node(const u32 node)
 EXPORT_SYMBOL_GPL(zynqmp_pm_release_node);
 
 /**
+ * zynqmp_pm_get_rpu_mode() - Get RPU mode
+ * @node_id:	Node ID of the device
+ * @rpu_mode:	return by reference value
+ *		either split or lockstep
+ *
+ * Return:	return 0 on success or error+reason.
+ *		if success, then  rpu_mode will be set
+ *		to current rpu mode.
+ */
+int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mode)
+{
+	u32 ret_payload[PAYLOAD_ARG_CNT];
+	int ret;
+
+	ret = zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
+				  IOCTL_GET_RPU_OPER_MODE, 0, 0, ret_payload);
+
+	/* only set rpu_mode if no error */
+	if (ret == XST_PM_SUCCESS)
+		*rpu_mode = ret_payload[0];
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(zynqmp_pm_get_rpu_mode);
+
+/**
+ * zynqmp_pm_set_rpu_mode() - Set RPU mode
+ * @node_id:	Node ID of the device
+ * @rpu_mode:	Argument 1 to requested IOCTL call. either split or lockstep
+ *
+ *		This function is used to set RPU mode to split or
+ *		lockstep
+ *
+ * Return:	Returns status, either success or error+reason
+ */
+int zynqmp_pm_set_rpu_mode(u32 node_id, enum rpu_oper_mode rpu_mode)
+{
+	return zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
+				   IOCTL_SET_RPU_OPER_MODE, (u32)rpu_mode,
+				   0, NULL);
+}
+EXPORT_SYMBOL_GPL(zynqmp_pm_set_rpu_mode);
+
+/**
+ * zynqmp_pm_set_tcm_config - configure TCM
+ * @node_id:	Firmware specific TCM subsystem ID
+ * @tcm_mode:	Argument 1 to requested IOCTL call
+ *              either PM_RPU_TCM_COMB or PM_RPU_TCM_SPLIT
+ *
+ * This function is used to set RPU mode to split or combined
+ *
+ * Return: status: 0 for success, else failure
+ */
+int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mode)
+{
+	return zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
+				   IOCTL_TCM_COMB_CONFIG, (u32)tcm_mode, 0,
+				   NULL);
+}
+EXPORT_SYMBOL_GPL(zynqmp_pm_set_tcm_config);
+
+/**
+ * zynqmp_pm_force_pwrdwn - PM call to request for another PU or subsystem to
+ *             be powered down forcefully
+ * @node:  Node ID of the targeted PU or subsystem
+ * @ack:   Flag to specify whether acknowledge is requested
+ *
+ * Return: status, either success or error+reason
+ */
+int zynqmp_pm_force_pwrdwn(const u32 node,
+			   const enum zynqmp_pm_request_ack ack)
+{
+	return zynqmp_pm_invoke_fn(PM_FORCE_POWERDOWN, node, ack, 0, 0, NULL);
+}
+EXPORT_SYMBOL_GPL(zynqmp_pm_force_pwrdwn);
+
+/**
+ * zynqmp_pm_request_wake - PM call to wake up selected master or subsystem
+ * @node:  Node ID of the master or subsystem
+ * @set_addr:  Specifies whether the address argument is relevant
+ * @address:   Address from which to resume when woken up
+ * @ack:   Flag to specify whether acknowledge requested
+ *
+ * Return: status, either success or error+reason
+ */
+int zynqmp_pm_request_wake(const u32 node,
+			   const bool set_addr,
+			   const u64 address,
+			   const enum zynqmp_pm_request_ack ack)
+{
+	/* set_addr flag is encoded into 1st bit of address */
+	return zynqmp_pm_invoke_fn(PM_REQUEST_WAKEUP, node, address | set_addr,
+				   address >> 32, ack, NULL);
+}
+EXPORT_SYMBOL_GPL(zynqmp_pm_request_wake);
+
+/**
  * zynqmp_pm_set_requirement() - PM call to set requirement for PM slaves
  * @node:		Node ID of the slave
  * @capabilities:	Requested capabilities of the slave
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index 1660197866531d..a850e9f486dd63 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -352,6 +352,19 @@ config TI_K3_R5_REMOTEPROC
 	  It's safe to say N here if you're not interested in utilizing
 	  a slave processor.
 
+config XLNX_R5_REMOTEPROC
+	tristate "Xilinx R5 remoteproc support"
+	depends on PM && ARCH_ZYNQMP
+	select ZYNQMP_FIRMWARE
+	select RPMSG_VIRTIO
+	select MAILBOX
+	select ZYNQMP_IPI_MBOX
+	help
+	  Say y or m here to support Xilinx R5 remote processors via the remote
+	  processor framework.
+
+	  It's safe to say N if not interested in using RPU r5f cores.
+
 endif # REMOTEPROC
 
 endmenu
diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile
index 5478c7cb9e07b8..91314a9b43cefc 100644
--- a/drivers/remoteproc/Makefile
+++ b/drivers/remoteproc/Makefile
@@ -38,3 +38,4 @@ obj-$(CONFIG_ST_SLIM_REMOTEPROC)	+= st_slim_rproc.o
 obj-$(CONFIG_STM32_RPROC)		+= stm32_rproc.o
 obj-$(CONFIG_TI_K3_DSP_REMOTEPROC)	+= ti_k3_dsp_remoteproc.o
 obj-$(CONFIG_TI_K3_R5_REMOTEPROC)	+= ti_k3_r5_remoteproc.o
+obj-$(CONFIG_XLNX_R5_REMOTEPROC)	+= xlnx_r5_remoteproc.o
diff --git a/drivers/remoteproc/imx_dsp_rproc.c b/drivers/remoteproc/imx_dsp_rproc.c
index 899aa8dd12f075..95da1cbefacf0b 100644
--- a/drivers/remoteproc/imx_dsp_rproc.c
+++ b/drivers/remoteproc/imx_dsp_rproc.c
@@ -347,9 +347,6 @@ static int imx_dsp_rproc_stop(struct rproc *rproc)
 	struct device *dev = rproc->dev.parent;
 	int ret = 0;
 
-	/* Make sure work is finished */
-	flush_work(&priv->rproc_work);
-
 	if (rproc->state == RPROC_CRASHED) {
 		priv->flags &= ~REMOTE_IS_READY;
 		return 0;
@@ -432,9 +429,18 @@ static void imx_dsp_rproc_vq_work(struct work_struct *work)
 {
 	struct imx_dsp_rproc *priv = container_of(work, struct imx_dsp_rproc,
 						  rproc_work);
+	struct rproc *rproc = priv->rproc;
+
+	mutex_lock(&rproc->lock);
+
+	if (rproc->state != RPROC_RUNNING)
+		goto unlock_mutex;
 
 	rproc_vq_interrupt(priv->rproc, 0);
 	rproc_vq_interrupt(priv->rproc, 1);
+
+unlock_mutex:
+	mutex_unlock(&rproc->lock);
 }
 
 /**
diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c
index 7cc4fd207e2d81..9fc978e0393cee 100644
--- a/drivers/remoteproc/imx_rproc.c
+++ b/drivers/remoteproc/imx_rproc.c
@@ -3,9 +3,11 @@
  * Copyright (c) 2017 Pengutronix, Oleksij Rempel <kernel@pengutronix.de>
  */
 
+#include <dt-bindings/firmware/imx/rsrc.h>
 #include <linux/arm-smccc.h>
 #include <linux/clk.h>
 #include <linux/err.h>
+#include <linux/firmware/imx/sci.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/mailbox_client.h>
@@ -15,6 +17,7 @@
 #include <linux/of_reserved_mem.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm_domain.h>
 #include <linux/regmap.h>
 #include <linux/remoteproc.h>
 #include <linux/workqueue.h>
@@ -59,6 +62,8 @@
 #define IMX_SIP_RPROC_STARTED		0x01
 #define IMX_SIP_RPROC_STOP		0x02
 
+#define IMX_SC_IRQ_GROUP_REBOOTED	5
+
 /**
  * struct imx_rproc_mem - slim internal memory structure
  * @cpu_addr: MPU virtual address of the memory region
@@ -71,10 +76,17 @@ struct imx_rproc_mem {
 	size_t size;
 };
 
-/* att flags */
+/* att flags: lower 16 bits specifying core, higher 16 bits for flags  */
 /* M4 own area. Can be mapped at probe */
-#define ATT_OWN		BIT(1)
-#define ATT_IOMEM	BIT(2)
+#define ATT_OWN         BIT(31)
+#define ATT_IOMEM       BIT(30)
+
+#define ATT_CORE_MASK   0xffff
+#define ATT_CORE(I)     BIT((I))
+
+static int imx_rproc_xtr_mbox_init(struct rproc *rproc);
+static void imx_rproc_free_mbox(struct rproc *rproc);
+static int imx_rproc_detach_pd(struct rproc *rproc);
 
 struct imx_rproc {
 	struct device			*dev;
@@ -89,6 +101,15 @@ struct imx_rproc {
 	struct work_struct		rproc_work;
 	struct workqueue_struct		*workqueue;
 	void __iomem			*rsc_table;
+	struct imx_sc_ipc		*ipc_handle;
+	struct notifier_block		rproc_nb;
+	u32				rproc_pt;	/* partition id */
+	u32				rsrc_id;	/* resource id */
+	u32				entry;		/* cpu start address */
+	int                             num_pd;
+	u32				core_index;
+	struct device                   **pd_dev;
+	struct device_link              **pd_dev_link;
 };
 
 static const struct imx_rproc_att imx_rproc_att_imx93[] = {
@@ -113,8 +134,33 @@ static const struct imx_rproc_att imx_rproc_att_imx93[] = {
 	{ 0x80000000, 0x80000000, 0x10000000, 0 },
 	{ 0x90000000, 0x80000000, 0x10000000, 0 },
 
-	{ 0xC0000000, 0xa0000000, 0x10000000, 0 },
-	{ 0xD0000000, 0xa0000000, 0x10000000, 0 },
+	{ 0xC0000000, 0xC0000000, 0x10000000, 0 },
+	{ 0xD0000000, 0xC0000000, 0x10000000, 0 },
+};
+
+static const struct imx_rproc_att imx_rproc_att_imx8qm[] = {
+	/* dev addr , sys addr  , size      , flags */
+	{ 0x08000000, 0x08000000, 0x10000000, 0},
+	/* TCML */
+	{ 0x1FFE0000, 0x34FE0000, 0x00020000, ATT_OWN | ATT_IOMEM | ATT_CORE(0)},
+	{ 0x1FFE0000, 0x38FE0000, 0x00020000, ATT_OWN | ATT_IOMEM | ATT_CORE(1)},
+	/* TCMU */
+	{ 0x20000000, 0x35000000, 0x00020000, ATT_OWN | ATT_IOMEM | ATT_CORE(0)},
+	{ 0x20000000, 0x39000000, 0x00020000, ATT_OWN | ATT_IOMEM | ATT_CORE(1)},
+	/* DDR (Data) */
+	{ 0x80000000, 0x80000000, 0x60000000, 0 },
+};
+
+static const struct imx_rproc_att imx_rproc_att_imx8qxp[] = {
+	{ 0x08000000, 0x08000000, 0x10000000, 0 },
+	/* TCML/U */
+	{ 0x1FFE0000, 0x34FE0000, 0x00040000, ATT_OWN | ATT_IOMEM },
+	/* OCRAM(Low 96KB) */
+	{ 0x21000000, 0x00100000, 0x00018000, 0 },
+	/* OCRAM */
+	{ 0x21100000, 0x00100000, 0x00040000, 0 },
+	/* DDR (Data) */
+	{ 0x80000000, 0x80000000, 0x60000000, 0 },
 };
 
 static const struct imx_rproc_att imx_rproc_att_imx8mn[] = {
@@ -255,6 +301,18 @@ static const struct imx_rproc_dcfg imx_rproc_cfg_imx8mq = {
 	.method		= IMX_RPROC_MMIO,
 };
 
+static const struct imx_rproc_dcfg imx_rproc_cfg_imx8qm = {
+	.att            = imx_rproc_att_imx8qm,
+	.att_size       = ARRAY_SIZE(imx_rproc_att_imx8qm),
+	.method         = IMX_RPROC_SCU_API,
+};
+
+static const struct imx_rproc_dcfg imx_rproc_cfg_imx8qxp = {
+	.att		= imx_rproc_att_imx8qxp,
+	.att_size	= ARRAY_SIZE(imx_rproc_att_imx8qxp),
+	.method		= IMX_RPROC_SCU_API,
+};
+
 static const struct imx_rproc_dcfg imx_rproc_cfg_imx8ulp = {
 	.att		= imx_rproc_att_imx8ulp,
 	.att_size	= ARRAY_SIZE(imx_rproc_att_imx8ulp),
@@ -301,6 +359,10 @@ static int imx_rproc_start(struct rproc *rproc)
 	struct arm_smccc_res res;
 	int ret;
 
+	ret = imx_rproc_xtr_mbox_init(rproc);
+	if (ret)
+		return ret;
+
 	switch (dcfg->method) {
 	case IMX_RPROC_MMIO:
 		ret = regmap_update_bits(priv->regmap, dcfg->src_reg, dcfg->src_mask,
@@ -310,6 +372,9 @@ static int imx_rproc_start(struct rproc *rproc)
 		arm_smccc_smc(IMX_SIP_RPROC, IMX_SIP_RPROC_START, 0, 0, 0, 0, 0, 0, &res);
 		ret = res.a0;
 		break;
+	case IMX_RPROC_SCU_API:
+		ret = imx_sc_pm_cpu_start(priv->ipc_handle, priv->rsrc_id, true, priv->entry);
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -339,12 +404,17 @@ static int imx_rproc_stop(struct rproc *rproc)
 		if (res.a1)
 			dev_info(dev, "Not in wfi, force stopped\n");
 		break;
+	case IMX_RPROC_SCU_API:
+		ret = imx_sc_pm_cpu_start(priv->ipc_handle, priv->rsrc_id, false, priv->entry);
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
 	if (ret)
 		dev_err(dev, "Failed to stop remote core\n");
+	else
+		imx_rproc_free_mbox(rproc);
 
 	return ret;
 }
@@ -359,6 +429,17 @@ static int imx_rproc_da_to_sys(struct imx_rproc *priv, u64 da,
 	for (i = 0; i < dcfg->att_size; i++) {
 		const struct imx_rproc_att *att = &dcfg->att[i];
 
+		/*
+		 * Ignore entries not belong to current core:
+		 * i.MX8QM has dual general M4_[0,1] cores, M4_0's own entries
+		 * has "ATT_CORE(0) & BIT(0)" true, M4_1's own entries has
+		 * "ATT_CORE(1) & BIT(1)" true.
+		 */
+		if (att->flags & ATT_CORE_MASK) {
+			if (!((BIT(priv->core_index)) & (att->flags & ATT_CORE_MASK)))
+				continue;
+		}
+
 		if (da >= att->da && da + len < att->da + att->size) {
 			unsigned int offset = da - att->da;
 
@@ -519,6 +600,22 @@ static void imx_rproc_kick(struct rproc *rproc, int vqid)
 
 static int imx_rproc_attach(struct rproc *rproc)
 {
+	return imx_rproc_xtr_mbox_init(rproc);
+}
+
+static int imx_rproc_detach(struct rproc *rproc)
+{
+	struct imx_rproc *priv = rproc->priv;
+	const struct imx_rproc_dcfg *dcfg = priv->dcfg;
+
+	if (dcfg->method != IMX_RPROC_SCU_API)
+		return -EOPNOTSUPP;
+
+	if (imx_sc_rm_is_resource_owned(priv->ipc_handle, priv->rsrc_id))
+		return -EOPNOTSUPP;
+
+	imx_rproc_free_mbox(rproc);
+
 	return 0;
 }
 
@@ -537,6 +634,7 @@ static struct resource_table *imx_rproc_get_loaded_rsc_table(struct rproc *rproc
 static const struct rproc_ops imx_rproc_ops = {
 	.prepare	= imx_rproc_prepare,
 	.attach		= imx_rproc_attach,
+	.detach		= imx_rproc_detach,
 	.start		= imx_rproc_start,
 	.stop		= imx_rproc_stop,
 	.kick		= imx_rproc_kick,
@@ -647,6 +745,18 @@ static int imx_rproc_xtr_mbox_init(struct rproc *rproc)
 	struct device *dev = priv->dev;
 	struct mbox_client *cl;
 
+	/*
+	 * stop() and detach() will free the mbox channels, so need
+	 * to request mbox channels in start() and attach().
+	 *
+	 * Because start() and attach() not able to handle mbox defer
+	 * probe, imx_rproc_xtr_mbox_init is also called in probe().
+	 * The check is to avoid request mbox again when start() or
+	 * attach() after probe() returns success.
+	 */
+	if (priv->tx_ch && priv->rx_ch)
+		return 0;
+
 	if (!of_get_property(dev->of_node, "mbox-names", NULL))
 		return 0;
 
@@ -676,8 +786,119 @@ static void imx_rproc_free_mbox(struct rproc *rproc)
 {
 	struct imx_rproc *priv = rproc->priv;
 
-	mbox_free_channel(priv->tx_ch);
-	mbox_free_channel(priv->rx_ch);
+	if (priv->tx_ch) {
+		mbox_free_channel(priv->tx_ch);
+		priv->tx_ch = NULL;
+	}
+
+	if (priv->rx_ch) {
+		mbox_free_channel(priv->rx_ch);
+		priv->rx_ch = NULL;
+	}
+}
+
+static void imx_rproc_put_scu(struct rproc *rproc)
+{
+	struct imx_rproc *priv = rproc->priv;
+	const struct imx_rproc_dcfg *dcfg = priv->dcfg;
+
+	if (dcfg->method != IMX_RPROC_SCU_API)
+		return;
+
+	if (imx_sc_rm_is_resource_owned(priv->ipc_handle, priv->rsrc_id)) {
+		imx_rproc_detach_pd(rproc);
+		return;
+	}
+
+	imx_scu_irq_group_enable(IMX_SC_IRQ_GROUP_REBOOTED, BIT(priv->rproc_pt), false);
+	imx_scu_irq_unregister_notifier(&priv->rproc_nb);
+}
+
+static int imx_rproc_partition_notify(struct notifier_block *nb,
+				      unsigned long event, void *group)
+{
+	struct imx_rproc *priv = container_of(nb, struct imx_rproc, rproc_nb);
+
+	/* Ignore other irqs */
+	if (!((event & BIT(priv->rproc_pt)) && (*(u8 *)group == IMX_SC_IRQ_GROUP_REBOOTED)))
+		return 0;
+
+	rproc_report_crash(priv->rproc, RPROC_WATCHDOG);
+
+	pr_info("Partition%d reset!\n", priv->rproc_pt);
+
+	return 0;
+}
+
+static int imx_rproc_attach_pd(struct imx_rproc *priv)
+{
+	struct device *dev = priv->dev;
+	int ret, i;
+
+	/*
+	 * If there is only one power-domain entry, the platform driver framework
+	 * will handle it, no need handle it in this driver.
+	 */
+	priv->num_pd = of_count_phandle_with_args(dev->of_node, "power-domains",
+						  "#power-domain-cells");
+	if (priv->num_pd <= 1)
+		return 0;
+
+	priv->pd_dev = devm_kmalloc_array(dev, priv->num_pd, sizeof(*priv->pd_dev), GFP_KERNEL);
+	if (!priv->pd_dev)
+		return -ENOMEM;
+
+	priv->pd_dev_link = devm_kmalloc_array(dev, priv->num_pd, sizeof(*priv->pd_dev_link),
+					       GFP_KERNEL);
+
+	if (!priv->pd_dev_link)
+		return -ENOMEM;
+
+	for (i = 0; i < priv->num_pd; i++) {
+		priv->pd_dev[i] = dev_pm_domain_attach_by_id(dev, i);
+		if (IS_ERR(priv->pd_dev[i])) {
+			ret = PTR_ERR(priv->pd_dev[i]);
+			goto detach_pd;
+		}
+
+		priv->pd_dev_link[i] = device_link_add(dev, priv->pd_dev[i], DL_FLAG_STATELESS |
+						       DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE);
+		if (!priv->pd_dev_link[i]) {
+			dev_pm_domain_detach(priv->pd_dev[i], false);
+			ret = -EINVAL;
+			goto detach_pd;
+		}
+	}
+
+	return 0;
+
+detach_pd:
+	while (--i >= 0) {
+		device_link_del(priv->pd_dev_link[i]);
+		dev_pm_domain_detach(priv->pd_dev[i], false);
+	}
+
+	return ret;
+}
+
+static int imx_rproc_detach_pd(struct rproc *rproc)
+{
+	struct imx_rproc *priv = rproc->priv;
+	int i;
+
+	/*
+	 * If there is only one power-domain entry, the platform driver framework
+	 * will handle it, no need handle it in this driver.
+	 */
+	if (priv->num_pd <= 1)
+		return 0;
+
+	for (i = 0; i < priv->num_pd; i++) {
+		device_link_del(priv->pd_dev_link[i]);
+		dev_pm_domain_detach(priv->pd_dev[i], false);
+	}
+
+	return 0;
 }
 
 static int imx_rproc_detect_mode(struct imx_rproc *priv)
@@ -689,6 +910,7 @@ static int imx_rproc_detect_mode(struct imx_rproc *priv)
 	struct arm_smccc_res res;
 	int ret;
 	u32 val;
+	u8 pt;
 
 	switch (dcfg->method) {
 	case IMX_RPROC_NONE:
@@ -699,6 +921,61 @@ static int imx_rproc_detect_mode(struct imx_rproc *priv)
 		if (res.a0)
 			priv->rproc->state = RPROC_DETACHED;
 		return 0;
+	case IMX_RPROC_SCU_API:
+		ret = imx_scu_get_handle(&priv->ipc_handle);
+		if (ret)
+			return ret;
+		ret = of_property_read_u32(dev->of_node, "fsl,resource-id", &priv->rsrc_id);
+		if (ret) {
+			dev_err(dev, "No fsl,resource-id property\n");
+			return ret;
+		}
+
+		if (priv->rsrc_id == IMX_SC_R_M4_1_PID0)
+			priv->core_index = 1;
+		else
+			priv->core_index = 0;
+
+		/*
+		 * If Mcore resource is not owned by Acore partition, It is kicked by ROM,
+		 * and Linux could only do IPC with Mcore and nothing else.
+		 */
+		if (imx_sc_rm_is_resource_owned(priv->ipc_handle, priv->rsrc_id)) {
+			if (of_property_read_u32(dev->of_node, "fsl,entry-address", &priv->entry))
+				return -EINVAL;
+
+			return imx_rproc_attach_pd(priv);
+		}
+
+		priv->rproc->state = RPROC_DETACHED;
+		priv->rproc->recovery_disabled = false;
+		rproc_set_feature(priv->rproc, RPROC_FEAT_ATTACH_ON_RECOVERY);
+
+		/* Get partition id and enable irq in SCFW */
+		ret = imx_sc_rm_get_resource_owner(priv->ipc_handle, priv->rsrc_id, &pt);
+		if (ret) {
+			dev_err(dev, "not able to get resource owner\n");
+			return ret;
+		}
+
+		priv->rproc_pt = pt;
+		priv->rproc_nb.notifier_call = imx_rproc_partition_notify;
+
+		ret = imx_scu_irq_register_notifier(&priv->rproc_nb);
+		if (ret) {
+			dev_err(dev, "register scu notifier failed, %d\n", ret);
+			return ret;
+		}
+
+		ret = imx_scu_irq_group_enable(IMX_SC_IRQ_GROUP_REBOOTED, BIT(priv->rproc_pt),
+					       true);
+		if (ret) {
+			imx_scu_irq_unregister_notifier(&priv->rproc_nb);
+			dev_err(dev, "Enable irq failed, %d\n", ret);
+			return ret;
+		}
+
+		return 0;
 	default:
 		break;
 	}
@@ -803,7 +1080,7 @@ static int imx_rproc_probe(struct platform_device *pdev)
 
 	ret = imx_rproc_clk_enable(priv);
 	if (ret)
-		goto err_put_mbox;
+		goto err_put_scu;
 
 	INIT_WORK(&priv->rproc_work, imx_rproc_vq_work);
 
@@ -820,6 +1097,8 @@ static int imx_rproc_probe(struct platform_device *pdev)
 
 err_put_clk:
 	clk_disable_unprepare(priv->clk);
+err_put_scu:
+	imx_rproc_put_scu(rproc);
 err_put_mbox:
 	imx_rproc_free_mbox(rproc);
 err_put_wkq:
@@ -837,6 +1116,7 @@ static int imx_rproc_remove(struct platform_device *pdev)
 
 	clk_disable_unprepare(priv->clk);
 	rproc_del(rproc);
+	imx_rproc_put_scu(rproc);
 	imx_rproc_free_mbox(rproc);
 	destroy_workqueue(priv->workqueue);
 	rproc_free(rproc);
@@ -852,6 +1132,8 @@ static const struct of_device_id imx_rproc_of_match[] = {
 	{ .compatible = "fsl,imx8mm-cm4", .data = &imx_rproc_cfg_imx8mq },
 	{ .compatible = "fsl,imx8mn-cm7", .data = &imx_rproc_cfg_imx8mn },
 	{ .compatible = "fsl,imx8mp-cm7", .data = &imx_rproc_cfg_imx8mn },
+	{ .compatible = "fsl,imx8qxp-cm4", .data = &imx_rproc_cfg_imx8qxp },
+	{ .compatible = "fsl,imx8qm-cm4", .data = &imx_rproc_cfg_imx8qm },
 	{ .compatible = "fsl,imx8ulp-cm33", .data = &imx_rproc_cfg_imx8ulp },
 	{ .compatible = "fsl,imx93-cm33", .data = &imx_rproc_cfg_imx93 },
 	{},
diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index 6afd0941e55245..dc6f07ca83410f 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -449,6 +449,7 @@ static int adsp_alloc_memory_region(struct qcom_adsp *adsp)
 	}
 
 	ret = of_address_to_resource(node, 0, &r);
+	of_node_put(node);
 	if (ret)
 		return ret;
 
@@ -556,6 +557,7 @@ static int adsp_probe(struct platform_device *pdev)
 detach_proxy_pds:
 	adsp_pds_detach(adsp, adsp->proxy_pds, adsp->proxy_pd_count);
 free_rproc:
+	device_init_wakeup(adsp->dev, false);
 	rproc_free(rproc);
 
 	return ret;
@@ -572,6 +574,8 @@ static int adsp_remove(struct platform_device *pdev)
 	qcom_remove_sysmon_subdev(adsp->sysmon);
 	qcom_remove_smd_subdev(adsp->rproc, &adsp->smd_subdev);
 	qcom_remove_ssr_subdev(adsp->rproc, &adsp->ssr_subdev);
+	adsp_pds_detach(adsp, adsp->proxy_pds, adsp->proxy_pd_count);
+	device_init_wakeup(adsp->dev, false);
 	rproc_free(adsp->rproc);
 
 	return 0;
diff --git a/drivers/remoteproc/qcom_q6v5_wcss.c b/drivers/remoteproc/qcom_q6v5_wcss.c
index bb0947f7770ea0..ba24d745b2d65c 100644
--- a/drivers/remoteproc/qcom_q6v5_wcss.c
+++ b/drivers/remoteproc/qcom_q6v5_wcss.c
@@ -351,7 +351,7 @@ static int q6v5_wcss_qcs404_power_on(struct q6v5_wcss *wcss)
 	if (ret) {
 		dev_err(wcss->dev,
 			"xo cbcr enabling timed out (rc:%d)\n", ret);
-		return ret;
+		goto disable_xo_cbcr_clk;
 	}
 
 	writel(0, wcss->reg_base + Q6SS_CGC_OVERRIDE);
@@ -417,6 +417,7 @@ disable_sleep_cbcr_clk:
 	val = readl(wcss->reg_base + Q6SS_SLEEP_CBCR);
 	val &= ~Q6SS_CLK_ENABLE;
 	writel(val, wcss->reg_base + Q6SS_SLEEP_CBCR);
+disable_xo_cbcr_clk:
 	val = readl(wcss->reg_base + Q6SS_XO_CBCR);
 	val &= ~Q6SS_CLK_ENABLE;
 	writel(val, wcss->reg_base + Q6SS_XO_CBCR);
@@ -827,6 +828,9 @@ static int q6v5_wcss_init_mmio(struct q6v5_wcss *wcss,
 	int ret;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "qdsp6");
+	if (!res)
+		return -EINVAL;
+
 	wcss->reg_base = devm_ioremap(&pdev->dev, res->start,
 				      resource_size(res));
 	if (!wcss->reg_base)
diff --git a/drivers/remoteproc/qcom_sysmon.c b/drivers/remoteproc/qcom_sysmon.c
index 57dde2a69b9ddf..85393d5eb0058f 100644
--- a/drivers/remoteproc/qcom_sysmon.c
+++ b/drivers/remoteproc/qcom_sysmon.c
@@ -190,7 +190,7 @@ struct ssctl_shutdown_resp {
 	struct qmi_response_type_v01 resp;
 };
 
-static struct qmi_elem_info ssctl_shutdown_resp_ei[] = {
+static const struct qmi_elem_info ssctl_shutdown_resp_ei[] = {
 	{
 		.data_type	= QMI_STRUCT,
 		.elem_len	= 1,
@@ -211,7 +211,7 @@ struct ssctl_subsys_event_req {
 	u32 evt_driven;
 };
 
-static struct qmi_elem_info ssctl_subsys_event_req_ei[] = {
+static const struct qmi_elem_info ssctl_subsys_event_req_ei[] = {
 	{
 		.data_type	= QMI_DATA_LEN,
 		.elem_len	= 1,
@@ -269,7 +269,7 @@ struct ssctl_subsys_event_resp {
 	struct qmi_response_type_v01 resp;
 };
 
-static struct qmi_elem_info ssctl_subsys_event_resp_ei[] = {
+static const struct qmi_elem_info ssctl_subsys_event_resp_ei[] = {
 	{
 		.data_type	= QMI_STRUCT,
 		.elem_len	= 1,
@@ -283,7 +283,7 @@ static struct qmi_elem_info ssctl_subsys_event_resp_ei[] = {
 	{}
 };
 
-static struct qmi_elem_info ssctl_shutdown_ind_ei[] = {
+static const struct qmi_elem_info ssctl_shutdown_ind_ei[] = {
 	{}
 };
 
@@ -652,7 +652,9 @@ struct qcom_sysmon *qcom_add_sysmon_subdev(struct rproc *rproc,
 		if (sysmon->shutdown_irq != -ENODATA) {
 			dev_err(sysmon->dev,
 				"failed to retrieve shutdown-ack IRQ\n");
-			return ERR_PTR(sysmon->shutdown_irq);
+			ret = sysmon->shutdown_irq;
+			kfree(sysmon);
+			return ERR_PTR(ret);
 		}
 	} else {
 		ret = devm_request_threaded_irq(sysmon->dev,
@@ -663,6 +665,7 @@ struct qcom_sysmon *qcom_add_sysmon_subdev(struct rproc *rproc,
 		if (ret) {
 			dev_err(sysmon->dev,
 				"failed to acquire shutdown-ack IRQ\n");
+			kfree(sysmon);
 			return ERR_PTR(ret);
 		}
 	}
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 8768cb64f560ce..1cd4815a6dd197 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -509,7 +509,13 @@ static int rproc_handle_vdev(struct rproc *rproc, void *ptr,
 	rvdev_data.rsc_offset = offset;
 	rvdev_data.rsc = rsc;
 
-	pdev = platform_device_register_data(dev, "rproc-virtio", rvdev_data.index, &rvdev_data,
+	/*
+	 * When there is more than one remote processor, rproc->nb_vdev number is
+	 * same for each separate instances of "rproc". If rvdev_data.index is used
+	 * as device id, then we get duplication in sysfs, so need to use
+	 * PLATFORM_DEVID_AUTO to auto select device id.
+	 */
+	pdev = platform_device_register_data(dev, "rproc-virtio", PLATFORM_DEVID_AUTO, &rvdev_data,
 					     sizeof(rvdev_data));
 	if (IS_ERR(pdev)) {
 		dev_err(dev, "failed to create rproc-virtio device\n");
@@ -1862,12 +1868,18 @@ static void rproc_crash_handler_work(struct work_struct *work)
 
 	mutex_lock(&rproc->lock);
 
-	if (rproc->state == RPROC_CRASHED || rproc->state == RPROC_OFFLINE) {
+	if (rproc->state == RPROC_CRASHED) {
 		/* handle only the first crash detected */
 		mutex_unlock(&rproc->lock);
 		return;
 	}
 
+	if (rproc->state == RPROC_OFFLINE) {
+		/* Don't recover if the remote processor was stopped */
+		mutex_unlock(&rproc->lock);
+		goto out;
+	}
+
 	rproc->state = RPROC_CRASHED;
 	dev_err(dev, "handling crash #%u in %s\n", ++rproc->crash_cnt,
 		rproc->name);
@@ -1877,6 +1889,7 @@ static void rproc_crash_handler_work(struct work_struct *work)
 	if (!rproc->recovery_disabled)
 		rproc_trigger_recovery(rproc);
 
+out:
 	pm_relax(rproc->dev.parent);
 }
 
@@ -2106,7 +2119,7 @@ struct rproc *rproc_get_by_phandle(phandle phandle)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(r, &rproc_list, node) {
-		if (r->dev.parent && r->dev.parent->of_node == np) {
+		if (r->dev.parent && device_match_of_node(r->dev.parent, np)) {
 			/* prevent underlying implementation from being removed */
 			if (!try_module_get(r->dev.parent->driver->owner)) {
 				dev_err(&r->dev, "can't get owner\n");
diff --git a/drivers/remoteproc/xlnx_r5_remoteproc.c b/drivers/remoteproc/xlnx_r5_remoteproc.c
new file mode 100644
index 00000000000000..2db57d3941555f
--- /dev/null
+++ b/drivers/remoteproc/xlnx_r5_remoteproc.c
@@ -0,0 +1,1067 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ZynqMP R5 Remote Processor driver
+ *
+ */
+
+#include <dt-bindings/power/xlnx-zynqmp-power.h>
+#include <linux/dma-mapping.h>
+#include <linux/firmware/xlnx-zynqmp.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/platform_device.h>
+#include <linux/remoteproc.h>
+#include <linux/slab.h>
+
+#include "remoteproc_internal.h"
+
+/*
+ * settings for RPU cluster mode which
+ * reflects possible values of xlnx,cluster-mode dt-property
+ */
+enum zynqmp_r5_cluster_mode {
+	SPLIT_MODE = 0, /* When cores run as separate processor */
+	LOCKSTEP_MODE = 1, /* cores execute same code in lockstep,clk-for-clk */
+	SINGLE_CPU_MODE = 2, /* core0 is held in reset and only core1 runs */
+};
+
+/**
+ * struct mem_bank_data - Memory Bank description
+ *
+ * @addr: Start address of memory bank
+ * @size: Size of Memory bank
+ * @pm_domain_id: Power-domains id of memory bank for firmware to turn on/off
+ * @bank_name: name of the bank for remoteproc framework
+ */
+struct mem_bank_data {
+	phys_addr_t addr;
+	size_t size;
+	u32 pm_domain_id;
+	char *bank_name;
+};
+
+/*
+ * Hardcoded TCM bank values. This will be removed once TCM bindings are
+ * accepted for system-dt specifications and upstreamed in linux kernel
+ */
+static const struct mem_bank_data zynqmp_tcm_banks[] = {
+	{0xffe00000UL, 0x10000UL, PD_R5_0_ATCM, "atcm0"}, /* TCM 64KB each */
+	{0xffe20000UL, 0x10000UL, PD_R5_0_BTCM, "btcm0"},
+	{0xffe90000UL, 0x10000UL, PD_R5_1_ATCM, "atcm1"},
+	{0xffeb0000UL, 0x10000UL, PD_R5_1_BTCM, "btcm1"},
+};
+
+/**
+ * struct zynqmp_r5_core
+ *
+ * @dev: device of RPU instance
+ * @np: device node of RPU instance
+ * @tcm_bank_count: number TCM banks accessible to this RPU
+ * @tcm_banks: array of each TCM bank data
+ * @rmem_count: Number of reserved mem regions
+ * @rmem: reserved memory region nodes from device tree
+ * @rproc: rproc handle
+ * @pm_domain_id: RPU CPU power domain id
+ */
+struct zynqmp_r5_core {
+	struct device *dev;
+	struct device_node *np;
+	int tcm_bank_count;
+	struct mem_bank_data **tcm_banks;
+	int rmem_count;
+	struct reserved_mem **rmem;
+	struct rproc *rproc;
+	u32 pm_domain_id;
+};
+
+/**
+ * struct zynqmp_r5_cluster
+ *
+ * @dev: r5f subsystem cluster device node
+ * @mode: cluster mode of type zynqmp_r5_cluster_mode
+ * @core_count: number of r5 cores used for this cluster mode
+ * @r5_cores: Array of pointers pointing to r5 core
+ */
+struct zynqmp_r5_cluster {
+	struct device *dev;
+	enum  zynqmp_r5_cluster_mode mode;
+	int core_count;
+	struct zynqmp_r5_core **r5_cores;
+};
+
+/*
+ * zynqmp_r5_set_mode()
+ *
+ * set RPU cluster and TCM operation mode
+ *
+ * @r5_core: pointer to zynqmp_r5_core type object
+ * @fw_reg_val: value expected by firmware to configure RPU cluster mode
+ * @tcm_mode: value expected by fw to configure TCM mode (lockstep or split)
+ *
+ * Return: 0 for success and < 0 for failure
+ */
+static int zynqmp_r5_set_mode(struct zynqmp_r5_core *r5_core,
+			      enum rpu_oper_mode fw_reg_val,
+			      enum rpu_tcm_comb tcm_mode)
+{
+	int ret;
+
+	ret = zynqmp_pm_set_rpu_mode(r5_core->pm_domain_id, fw_reg_val);
+	if (ret < 0) {
+		dev_err(r5_core->dev, "failed to set RPU mode\n");
+		return ret;
+	}
+
+	ret = zynqmp_pm_set_tcm_config(r5_core->pm_domain_id, tcm_mode);
+	if (ret < 0)
+		dev_err(r5_core->dev, "failed to configure TCM\n");
+
+	return ret;
+}
+
+/*
+ * zynqmp_r5_rproc_start()
+ * @rproc: single R5 core's corresponding rproc instance
+ *
+ * Start R5 Core from designated boot address.
+ *
+ * return 0 on success, otherwise non-zero value on failure
+ */
+static int zynqmp_r5_rproc_start(struct rproc *rproc)
+{
+	struct zynqmp_r5_core *r5_core = rproc->priv;
+	enum rpu_boot_mem bootmem;
+	int ret;
+
+	/*
+	 * The exception vector pointers (EVP) refer to the base-address of
+	 * exception vectors (for reset, IRQ, FIQ, etc). The reset-vector
+	 * starts at the base-address and subsequent vectors are on 4-byte
+	 * boundaries.
+	 *
+	 * Exception vectors can start either from 0x0000_0000 (LOVEC) or
+	 * from 0xFFFF_0000 (HIVEC) which is mapped in the OCM (On-Chip Memory)
+	 *
+	 * Usually firmware will put Exception vectors at LOVEC.
+	 *
+	 * It is not recommend that you change the exception vector.
+	 * Changing the EVP to HIVEC will result in increased interrupt latency
+	 * and jitter. Also, if the OCM is secured and the Cortex-R5F processor
+	 * is non-secured, then the Cortex-R5F processor cannot access the
+	 * HIVEC exception vectors in the OCM.
+	 */
+	bootmem = (rproc->bootaddr >= 0xFFFC0000) ?
+		   PM_RPU_BOOTMEM_HIVEC : PM_RPU_BOOTMEM_LOVEC;
+
+	dev_dbg(r5_core->dev, "RPU boot addr 0x%llx from %s.", rproc->bootaddr,
+		bootmem == PM_RPU_BOOTMEM_HIVEC ? "OCM" : "TCM");
+
+	ret = zynqmp_pm_request_wake(r5_core->pm_domain_id, 1,
+				     bootmem, ZYNQMP_PM_REQUEST_ACK_NO);
+	if (ret)
+		dev_err(r5_core->dev,
+			"failed to start RPU = 0x%x\n", r5_core->pm_domain_id);
+	return ret;
+}
+
+/*
+ * zynqmp_r5_rproc_stop()
+ * @rproc: single R5 core's corresponding rproc instance
+ *
+ * Power down  R5 Core.
+ *
+ * return 0 on success, otherwise non-zero value on failure
+ */
+static int zynqmp_r5_rproc_stop(struct rproc *rproc)
+{
+	struct zynqmp_r5_core *r5_core = rproc->priv;
+	int ret;
+
+	ret = zynqmp_pm_force_pwrdwn(r5_core->pm_domain_id,
+				     ZYNQMP_PM_REQUEST_ACK_BLOCKING);
+	if (ret)
+		dev_err(r5_core->dev, "failed to stop remoteproc RPU %d\n", ret);
+
+	return ret;
+}
+
+/*
+ * zynqmp_r5_mem_region_map()
+ * @rproc: single R5 core's corresponding rproc instance
+ * @mem: mem descriptor to map reserved memory-regions
+ *
+ * Callback to map va for memory-region's carveout.
+ *
+ * return 0 on success, otherwise non-zero value on failure
+ */
+static int zynqmp_r5_mem_region_map(struct rproc *rproc,
+				    struct rproc_mem_entry *mem)
+{
+	void __iomem *va;
+
+	va = ioremap_wc(mem->dma, mem->len);
+	if (IS_ERR_OR_NULL(va))
+		return -ENOMEM;
+
+	mem->va = (void *)va;
+
+	return 0;
+}
+
+/*
+ * zynqmp_r5_rproc_mem_unmap
+ * @rproc: single R5 core's corresponding rproc instance
+ * @mem: mem entry to unmap
+ *
+ * Unmap memory-region carveout
+ *
+ * return: always returns 0
+ */
+static int zynqmp_r5_mem_region_unmap(struct rproc *rproc,
+				      struct rproc_mem_entry *mem)
+{
+	iounmap((void __iomem *)mem->va);
+	return 0;
+}
+
+/*
+ * add_mem_regions_carveout()
+ * @rproc: single R5 core's corresponding rproc instance
+ *
+ * Construct rproc mem carveouts from memory-region property nodes
+ *
+ * return 0 on success, otherwise non-zero value on failure
+ */
+static int add_mem_regions_carveout(struct rproc *rproc)
+{
+	struct rproc_mem_entry *rproc_mem;
+	struct zynqmp_r5_core *r5_core;
+	struct reserved_mem *rmem;
+	int i, num_mem_regions;
+
+	r5_core = (struct zynqmp_r5_core *)rproc->priv;
+	num_mem_regions = r5_core->rmem_count;
+
+	for (i = 0; i < num_mem_regions; i++) {
+		rmem = r5_core->rmem[i];
+
+		if (!strncmp(rmem->name, "vdev0buffer", strlen("vdev0buffer"))) {
+			/* Init reserved memory for vdev buffer */
+			rproc_mem = rproc_of_resm_mem_entry_init(&rproc->dev, i,
+								 rmem->size,
+								 rmem->base,
+								 rmem->name);
+		} else {
+			/* Register associated reserved memory regions */
+			rproc_mem = rproc_mem_entry_init(&rproc->dev, NULL,
+							 (dma_addr_t)rmem->base,
+							 rmem->size, rmem->base,
+							 zynqmp_r5_mem_region_map,
+							 zynqmp_r5_mem_region_unmap,
+							 rmem->name);
+		}
+
+		if (!rproc_mem)
+			return -ENOMEM;
+
+		rproc_add_carveout(rproc, rproc_mem);
+
+		dev_dbg(&rproc->dev, "reserved mem carveout %s addr=%llx, size=0x%llx",
+			rmem->name, rmem->base, rmem->size);
+	}
+
+	return 0;
+}
+
+/*
+ * tcm_mem_unmap()
+ * @rproc: single R5 core's corresponding rproc instance
+ * @mem: tcm mem entry to unmap
+ *
+ * Unmap TCM banks when powering down R5 core.
+ *
+ * return always 0
+ */
+static int tcm_mem_unmap(struct rproc *rproc, struct rproc_mem_entry *mem)
+{
+	iounmap((void __iomem *)mem->va);
+
+	return 0;
+}
+
+/*
+ * tcm_mem_map()
+ * @rproc: single R5 core's corresponding rproc instance
+ * @mem: tcm memory entry descriptor
+ *
+ * Given TCM bank entry, this func setup virtual address for TCM bank
+ * remoteproc carveout. It also takes care of va to da address translation
+ *
+ * return 0 on success, otherwise non-zero value on failure
+ */
+static int tcm_mem_map(struct rproc *rproc,
+		       struct rproc_mem_entry *mem)
+{
+	void __iomem *va;
+
+	va = ioremap_wc(mem->dma, mem->len);
+	if (IS_ERR_OR_NULL(va))
+		return -ENOMEM;
+
+	/* Update memory entry va */
+	mem->va = (void *)va;
+
+	/* clear TCMs */
+	memset_io(va, 0, mem->len);
+
+	/*
+	 * The R5s expect their TCM banks to be at address 0x0 and 0x2000,
+	 * while on the Linux side they are at 0xffexxxxx.
+	 *
+	 * Zero out the high 12 bits of the address. This will give
+	 * expected values for TCM Banks 0A and 0B (0x0 and 0x20000).
+	 */
+	mem->da &= 0x000fffff;
+
+	/*
+	 * TCM Banks 1A and 1B still have to be translated.
+	 *
+	 * Below handle these two banks' absolute addresses (0xffe90000 and
+	 * 0xffeb0000) and convert to the expected relative addresses
+	 * (0x0 and 0x20000).
+	 */
+	if (mem->da == 0x90000 || mem->da == 0xB0000)
+		mem->da -= 0x90000;
+
+	/* if translated TCM bank address is not valid report error */
+	if (mem->da != 0x0 && mem->da != 0x20000) {
+		dev_err(&rproc->dev, "invalid TCM address: %x\n", mem->da);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
+ * add_tcm_carveout_split_mode()
+ * @rproc: single R5 core's corresponding rproc instance
+ *
+ * allocate and add remoteproc carveout for TCM memory in split mode
+ *
+ * return 0 on success, otherwise non-zero value on failure
+ */
+static int add_tcm_carveout_split_mode(struct rproc *rproc)
+{
+	struct rproc_mem_entry *rproc_mem;
+	struct zynqmp_r5_core *r5_core;
+	int i, num_banks, ret;
+	phys_addr_t bank_addr;
+	struct device *dev;
+	u32 pm_domain_id;
+	size_t bank_size;
+	char *bank_name;
+
+	r5_core = (struct zynqmp_r5_core *)rproc->priv;
+	dev = r5_core->dev;
+	num_banks = r5_core->tcm_bank_count;
+
+	/*
+	 * Power-on Each 64KB TCM,
+	 * register its address space, map and unmap functions
+	 * and add carveouts accordingly
+	 */
+	for (i = 0; i < num_banks; i++) {
+		bank_addr = r5_core->tcm_banks[i]->addr;
+		bank_name = r5_core->tcm_banks[i]->bank_name;
+		bank_size = r5_core->tcm_banks[i]->size;
+		pm_domain_id = r5_core->tcm_banks[i]->pm_domain_id;
+
+		ret = zynqmp_pm_request_node(pm_domain_id,
+					     ZYNQMP_PM_CAPABILITY_ACCESS, 0,
+					     ZYNQMP_PM_REQUEST_ACK_BLOCKING);
+		if (ret < 0) {
+			dev_err(dev, "failed to turn on TCM 0x%x", pm_domain_id);
+			goto release_tcm_split;
+		}
+
+		dev_dbg(dev, "TCM carveout split mode %s addr=%llx, size=0x%lx",
+			bank_name, bank_addr, bank_size);
+
+		rproc_mem = rproc_mem_entry_init(dev, NULL, bank_addr,
+						 bank_size, bank_addr,
+						 tcm_mem_map, tcm_mem_unmap,
+						 bank_name);
+		if (!rproc_mem) {
+			ret = -ENOMEM;
+			zynqmp_pm_release_node(pm_domain_id);
+			goto release_tcm_split;
+		}
+
+		rproc_add_carveout(rproc, rproc_mem);
+	}
+
+	return 0;
+
+release_tcm_split:
+	/* If failed, Turn off all TCM banks turned on before */
+	for (i--; i >= 0; i--) {
+		pm_domain_id = r5_core->tcm_banks[i]->pm_domain_id;
+		zynqmp_pm_release_node(pm_domain_id);
+	}
+	return ret;
+}
+
+/*
+ * add_tcm_carveout_lockstep_mode()
+ * @rproc: single R5 core's corresponding rproc instance
+ *
+ * allocate and add remoteproc carveout for TCM memory in lockstep mode
+ *
+ * return 0 on success, otherwise non-zero value on failure
+ */
+static int add_tcm_carveout_lockstep_mode(struct rproc *rproc)
+{
+	struct rproc_mem_entry *rproc_mem;
+	struct zynqmp_r5_core *r5_core;
+	int i, num_banks, ret;
+	phys_addr_t bank_addr;
+	size_t bank_size = 0;
+	struct device *dev;
+	u32 pm_domain_id;
+	char *bank_name;
+
+	r5_core = (struct zynqmp_r5_core *)rproc->priv;
+	dev = r5_core->dev;
+
+	/* Go through zynqmp banks for r5 node */
+	num_banks = r5_core->tcm_bank_count;
+
+	/*
+	 * In lockstep mode, TCM is contiguous memory block
+	 * However, each TCM block still needs to be enabled individually.
+	 * So, Enable each TCM block individually, but add their size
+	 * to create contiguous memory region.
+	 */
+	bank_addr = r5_core->tcm_banks[0]->addr;
+	bank_name = r5_core->tcm_banks[0]->bank_name;
+
+	for (i = 0; i < num_banks; i++) {
+		bank_size += r5_core->tcm_banks[i]->size;
+		pm_domain_id = r5_core->tcm_banks[i]->pm_domain_id;
+
+		/* Turn on each TCM bank individually */
+		ret = zynqmp_pm_request_node(pm_domain_id,
+					     ZYNQMP_PM_CAPABILITY_ACCESS, 0,
+					     ZYNQMP_PM_REQUEST_ACK_BLOCKING);
+		if (ret < 0) {
+			dev_err(dev, "failed to turn on TCM 0x%x", pm_domain_id);
+			goto release_tcm_lockstep;
+		}
+	}
+
+	dev_dbg(dev, "TCM add carveout lockstep mode %s addr=0x%llx, size=0x%lx",
+		bank_name, bank_addr, bank_size);
+
+	/* Register TCM address range, TCM map and unmap functions */
+	rproc_mem = rproc_mem_entry_init(dev, NULL, bank_addr,
+					 bank_size, bank_addr,
+					 tcm_mem_map, tcm_mem_unmap,
+					 bank_name);
+	if (!rproc_mem) {
+		ret = -ENOMEM;
+		goto release_tcm_lockstep;
+	}
+
+	/* If registration is success, add carveouts */
+	rproc_add_carveout(rproc, rproc_mem);
+
+	return 0;
+
+release_tcm_lockstep:
+	/* If failed, Turn off all TCM banks turned on before */
+	for (i--; i >= 0; i--) {
+		pm_domain_id = r5_core->tcm_banks[i]->pm_domain_id;
+		zynqmp_pm_release_node(pm_domain_id);
+	}
+	return ret;
+}
+
+/*
+ * add_tcm_banks()
+ * @rproc: single R5 core's corresponding rproc instance
+ *
+ * allocate and add remoteproc carveouts for TCM memory based on cluster mode
+ *
+ * return 0 on success, otherwise non-zero value on failure
+ */
+static int add_tcm_banks(struct rproc *rproc)
+{
+	struct zynqmp_r5_cluster *cluster;
+	struct zynqmp_r5_core *r5_core;
+	struct device *dev;
+
+	r5_core = (struct zynqmp_r5_core *)rproc->priv;
+	if (!r5_core)
+		return -EINVAL;
+
+	dev = r5_core->dev;
+
+	cluster = dev_get_drvdata(dev->parent);
+	if (!cluster) {
+		dev_err(dev->parent, "Invalid driver data\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * In lockstep mode TCM banks are one contiguous memory region of 256Kb
+	 * In split mode, each TCM bank is 64Kb and not contiguous.
+	 * We add memory carveouts accordingly.
+	 */
+	if (cluster->mode == SPLIT_MODE)
+		return add_tcm_carveout_split_mode(rproc);
+	else if (cluster->mode == LOCKSTEP_MODE)
+		return add_tcm_carveout_lockstep_mode(rproc);
+
+	return -EINVAL;
+}
+
+/*
+ * zynqmp_r5_parse_fw()
+ * @rproc: single R5 core's corresponding rproc instance
+ * @fw: ptr to firmware to be loaded onto r5 core
+ *
+ * get resource table if available
+ *
+ * return 0 on success, otherwise non-zero value on failure
+ */
+static int zynqmp_r5_parse_fw(struct rproc *rproc, const struct firmware *fw)
+{
+	int ret;
+
+	ret = rproc_elf_load_rsc_table(rproc, fw);
+	if (ret == -EINVAL) {
+		/*
+		 * resource table only required for IPC.
+		 * if not present, this is not necessarily an error;
+		 * for example, loading r5 hello world application
+		 * so simply inform user and keep going.
+		 */
+		dev_info(&rproc->dev, "no resource table found.\n");
+		ret = 0;
+	}
+	return ret;
+}
+
+/**
+ * zynqmp_r5_rproc_prepare()
+ * adds carveouts for TCM bank and reserved memory regions
+ *
+ * @rproc: Device node of each rproc
+ *
+ * Return: 0 for success else < 0 error code
+ */
+static int zynqmp_r5_rproc_prepare(struct rproc *rproc)
+{
+	int ret;
+
+	ret = add_tcm_banks(rproc);
+	if (ret) {
+		dev_err(&rproc->dev, "failed to get TCM banks, err %d\n", ret);
+		return ret;
+	}
+
+	ret = add_mem_regions_carveout(rproc);
+	if (ret) {
+		dev_err(&rproc->dev, "failed to get reserve mem regions %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * zynqmp_r5_rproc_unprepare()
+ * Turns off TCM banks using power-domain id
+ *
+ * @rproc: Device node of each rproc
+ *
+ * Return: always 0
+ */
+static int zynqmp_r5_rproc_unprepare(struct rproc *rproc)
+{
+	struct zynqmp_r5_core *r5_core;
+	u32 pm_domain_id;
+	int i;
+
+	r5_core = (struct zynqmp_r5_core *)rproc->priv;
+
+	for (i = 0; i < r5_core->tcm_bank_count; i++) {
+		pm_domain_id = r5_core->tcm_banks[i]->pm_domain_id;
+		if (zynqmp_pm_release_node(pm_domain_id))
+			dev_warn(r5_core->dev,
+				 "can't turn off TCM bank 0x%x", pm_domain_id);
+	}
+
+	return 0;
+}
+
+static const struct rproc_ops zynqmp_r5_rproc_ops = {
+	.prepare	= zynqmp_r5_rproc_prepare,
+	.unprepare	= zynqmp_r5_rproc_unprepare,
+	.start		= zynqmp_r5_rproc_start,
+	.stop		= zynqmp_r5_rproc_stop,
+	.load		= rproc_elf_load_segments,
+	.parse_fw	= zynqmp_r5_parse_fw,
+	.find_loaded_rsc_table = rproc_elf_find_loaded_rsc_table,
+	.sanity_check	= rproc_elf_sanity_check,
+	.get_boot_addr	= rproc_elf_get_boot_addr,
+};
+
+/**
+ * zynqmp_r5_add_rproc_core()
+ * Allocate and add struct rproc object for each r5f core
+ * This is called for each individual r5f core
+ *
+ * @cdev: Device node of each r5 core
+ *
+ * Return: zynqmp_r5_core object for success else error code pointer
+ */
+static struct zynqmp_r5_core *zynqmp_r5_add_rproc_core(struct device *cdev)
+{
+	struct zynqmp_r5_core *r5_core;
+	struct rproc *r5_rproc;
+	int ret;
+
+	/* Set up DMA mask */
+	ret = dma_set_coherent_mask(cdev, DMA_BIT_MASK(32));
+	if (ret)
+		return ERR_PTR(ret);
+
+	/* Allocate remoteproc instance */
+	r5_rproc = rproc_alloc(cdev, dev_name(cdev),
+			       &zynqmp_r5_rproc_ops,
+			       NULL, sizeof(struct zynqmp_r5_core));
+	if (!r5_rproc) {
+		dev_err(cdev, "failed to allocate memory for rproc instance\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	r5_rproc->auto_boot = false;
+	r5_core = (struct zynqmp_r5_core *)r5_rproc->priv;
+	r5_core->dev = cdev;
+	r5_core->np = dev_of_node(cdev);
+	if (!r5_core->np) {
+		dev_err(cdev, "can't get device node for r5 core\n");
+		ret = -EINVAL;
+		goto free_rproc;
+	}
+
+	/* Add R5 remoteproc core */
+	ret = rproc_add(r5_rproc);
+	if (ret) {
+		dev_err(cdev, "failed to add r5 remoteproc\n");
+		goto free_rproc;
+	}
+
+	r5_core->rproc = r5_rproc;
+	return r5_core;
+
+free_rproc:
+	rproc_free(r5_rproc);
+	return ERR_PTR(ret);
+}
+
+/**
+ * zynqmp_r5_get_tcm_node()
+ * Ideally this function should parse tcm node and store information
+ * in r5_core instance. For now, Hardcoded TCM information is used.
+ * This approach is used as TCM bindings for system-dt is being developed
+ *
+ * @cluster: pointer to zynqmp_r5_cluster type object
+ *
+ * Return: 0 for success and < 0 error code for failure.
+ */
+static int zynqmp_r5_get_tcm_node(struct zynqmp_r5_cluster *cluster)
+{
+	struct device *dev = cluster->dev;
+	struct zynqmp_r5_core *r5_core;
+	int tcm_bank_count, tcm_node;
+	int i, j;
+
+	tcm_bank_count = ARRAY_SIZE(zynqmp_tcm_banks);
+
+	/* count per core tcm banks */
+	tcm_bank_count = tcm_bank_count / cluster->core_count;
+
+	/*
+	 * r5 core 0 will use all of TCM banks in lockstep mode.
+	 * In split mode, r5 core0 will use 128k and r5 core1 will use another
+	 * 128k. Assign TCM banks to each core accordingly
+	 */
+	tcm_node = 0;
+	for (i = 0; i < cluster->core_count; i++) {
+		r5_core = cluster->r5_cores[i];
+		r5_core->tcm_banks = devm_kcalloc(dev, tcm_bank_count,
+						  sizeof(struct mem_bank_data *),
+						  GFP_KERNEL);
+		if (!r5_core->tcm_banks)
+			return -ENOMEM;
+
+		for (j = 0; j < tcm_bank_count; j++) {
+			/*
+			 * Use pre-defined TCM reg values.
+			 * Eventually this should be replaced by values
+			 * parsed from dts.
+			 */
+			r5_core->tcm_banks[j] =
+				(struct mem_bank_data *)&zynqmp_tcm_banks[tcm_node];
+			tcm_node++;
+		}
+
+		r5_core->tcm_bank_count = tcm_bank_count;
+	}
+
+	return 0;
+}
+
+/**
+ * zynqmp_r5_get_mem_region_node()
+ * parse memory-region property and get reserved mem regions
+ *
+ * @r5_core: pointer to zynqmp_r5_core type object
+ *
+ * Return: 0 for success and error code for failure.
+ */
+static int zynqmp_r5_get_mem_region_node(struct zynqmp_r5_core *r5_core)
+{
+	struct device_node *np, *rmem_np;
+	struct reserved_mem **rmem;
+	int res_mem_count, i;
+	struct device *dev;
+
+	dev = r5_core->dev;
+	np = r5_core->np;
+
+	res_mem_count = of_property_count_elems_of_size(np, "memory-region",
+							sizeof(phandle));
+	if (res_mem_count <= 0) {
+		dev_warn(dev, "failed to get memory-region property %d\n",
+			 res_mem_count);
+		return 0;
+	}
+
+	rmem = devm_kcalloc(dev, res_mem_count,
+			    sizeof(struct reserved_mem *), GFP_KERNEL);
+	if (!rmem)
+		return -ENOMEM;
+
+	for (i = 0; i < res_mem_count; i++) {
+		rmem_np = of_parse_phandle(np, "memory-region", i);
+		if (!rmem_np)
+			goto release_rmem;
+
+		rmem[i] = of_reserved_mem_lookup(rmem_np);
+		if (!rmem[i]) {
+			of_node_put(rmem_np);
+			goto release_rmem;
+		}
+
+		of_node_put(rmem_np);
+	}
+
+	r5_core->rmem_count = res_mem_count;
+	r5_core->rmem = rmem;
+	return 0;
+
+release_rmem:
+	return -EINVAL;
+}
+
+/*
+ * zynqmp_r5_core_init()
+ * Create and initialize zynqmp_r5_core type object
+ *
+ * @cluster: pointer to zynqmp_r5_cluster type object
+ * @fw_reg_val: value expected by firmware to configure RPU cluster mode
+ * @tcm_mode: value expected by fw to configure TCM mode (lockstep or split)
+ *
+ * Return: 0 for success and error code for failure.
+ */
+static int zynqmp_r5_core_init(struct zynqmp_r5_cluster *cluster,
+			       enum rpu_oper_mode fw_reg_val,
+			       enum rpu_tcm_comb tcm_mode)
+{
+	struct device *dev = cluster->dev;
+	struct zynqmp_r5_core *r5_core;
+	int ret, i;
+
+	ret = zynqmp_r5_get_tcm_node(cluster);
+	if (ret < 0) {
+		dev_err(dev, "can't get tcm node, err %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < cluster->core_count; i++) {
+		r5_core = cluster->r5_cores[i];
+
+		ret = zynqmp_r5_get_mem_region_node(r5_core);
+		if (ret)
+			dev_warn(dev, "memory-region prop failed %d\n", ret);
+
+		/* Initialize r5 cores with power-domains parsed from dts */
+		ret = of_property_read_u32_index(r5_core->np, "power-domains",
+						 1, &r5_core->pm_domain_id);
+		if (ret) {
+			dev_err(dev, "failed to get power-domains property\n");
+			return ret;
+		}
+
+		ret = zynqmp_r5_set_mode(r5_core, fw_reg_val, tcm_mode);
+		if (ret) {
+			dev_err(dev, "failed to set r5 cluster mode %d, err %d\n",
+				cluster->mode, ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * zynqmp_r5_cluster_init()
+ * Create and initialize zynqmp_r5_cluster type object
+ *
+ * @cluster: pointer to zynqmp_r5_cluster type object
+ *
+ * Return: 0 for success and error code for failure.
+ */
+static int zynqmp_r5_cluster_init(struct zynqmp_r5_cluster *cluster)
+{
+	enum zynqmp_r5_cluster_mode cluster_mode = LOCKSTEP_MODE;
+	struct device *dev = cluster->dev;
+	struct device_node *dev_node = dev_of_node(dev);
+	struct platform_device *child_pdev;
+	struct zynqmp_r5_core **r5_cores;
+	enum rpu_oper_mode fw_reg_val;
+	struct device **child_devs;
+	struct device_node *child;
+	enum rpu_tcm_comb tcm_mode;
+	int core_count, ret, i;
+
+	ret = of_property_read_u32(dev_node, "xlnx,cluster-mode", &cluster_mode);
+
+	/*
+	 * on success returns 0, if not defined then returns -EINVAL,
+	 * In that case, default is LOCKSTEP mode. Other than that
+	 * returns relative error code < 0.
+	 */
+	if (ret != -EINVAL && ret != 0) {
+		dev_err(dev, "Invalid xlnx,cluster-mode property\n");
+		return ret;
+	}
+
+	/*
+	 * For now driver only supports split mode and lockstep mode.
+	 * fail driver probe if either of that is not set in dts.
+	 */
+	if (cluster_mode == LOCKSTEP_MODE) {
+		tcm_mode = PM_RPU_TCM_COMB;
+		fw_reg_val = PM_RPU_MODE_LOCKSTEP;
+	} else if (cluster_mode == SPLIT_MODE) {
+		tcm_mode = PM_RPU_TCM_SPLIT;
+		fw_reg_val = PM_RPU_MODE_SPLIT;
+	} else {
+		dev_err(dev, "driver does not support cluster mode %d\n", cluster_mode);
+		return -EINVAL;
+	}
+
+	/*
+	 * Number of cores is decided by number of child nodes of
+	 * r5f subsystem node in dts. If Split mode is used in dts
+	 * 2 child nodes are expected.
+	 * In lockstep mode if two child nodes are available,
+	 * only use first child node and consider it as core0
+	 * and ignore core1 dt node.
+	 */
+	core_count = of_get_available_child_count(dev_node);
+	if (core_count == 0) {
+		dev_err(dev, "Invalid number of r5 cores %d", core_count);
+		return -EINVAL;
+	} else if (cluster_mode == SPLIT_MODE && core_count != 2) {
+		dev_err(dev, "Invalid number of r5 cores for split mode\n");
+		return -EINVAL;
+	} else if (cluster_mode == LOCKSTEP_MODE && core_count == 2) {
+		dev_warn(dev, "Only r5 core0 will be used\n");
+		core_count = 1;
+	}
+
+	child_devs = kcalloc(core_count, sizeof(struct device *), GFP_KERNEL);
+	if (!child_devs)
+		return -ENOMEM;
+
+	r5_cores = kcalloc(core_count,
+			   sizeof(struct zynqmp_r5_core *), GFP_KERNEL);
+	if (!r5_cores) {
+		kfree(child_devs);
+		return -ENOMEM;
+	}
+
+	i = 0;
+	for_each_available_child_of_node(dev_node, child) {
+		child_pdev = of_find_device_by_node(child);
+		if (!child_pdev) {
+			of_node_put(child);
+			ret = -ENODEV;
+			goto release_r5_cores;
+		}
+
+		child_devs[i] = &child_pdev->dev;
+
+		/* create and add remoteproc instance of type struct rproc */
+		r5_cores[i] = zynqmp_r5_add_rproc_core(&child_pdev->dev);
+		if (IS_ERR(r5_cores[i])) {
+			of_node_put(child);
+			ret = PTR_ERR(r5_cores[i]);
+			r5_cores[i] = NULL;
+			goto release_r5_cores;
+		}
+
+		/*
+		 * If two child nodes are available in dts in lockstep mode,
+		 * then ignore second child node.
+		 */
+		if (cluster_mode == LOCKSTEP_MODE) {
+			of_node_put(child);
+			break;
+		}
+
+		i++;
+	}
+
+	cluster->mode = cluster_mode;
+	cluster->core_count = core_count;
+	cluster->r5_cores = r5_cores;
+
+	ret = zynqmp_r5_core_init(cluster, fw_reg_val, tcm_mode);
+	if (ret < 0) {
+		dev_err(dev, "failed to init r5 core err %d\n", ret);
+		cluster->core_count = 0;
+		cluster->r5_cores = NULL;
+
+		/*
+		 * at this point rproc resources for each core are allocated.
+		 * adjust index to free resources in reverse order
+		 */
+		i = core_count - 1;
+		goto release_r5_cores;
+	}
+
+	kfree(child_devs);
+	return 0;
+
+release_r5_cores:
+	while (i >= 0) {
+		put_device(child_devs[i]);
+		if (r5_cores[i]) {
+			of_reserved_mem_device_release(r5_cores[i]->dev);
+			rproc_del(r5_cores[i]->rproc);
+			rproc_free(r5_cores[i]->rproc);
+		}
+		i--;
+	}
+	kfree(r5_cores);
+	kfree(child_devs);
+	return ret;
+}
+
+static void zynqmp_r5_cluster_exit(void *data)
+{
+	struct platform_device *pdev = (struct platform_device *)data;
+	struct zynqmp_r5_cluster *cluster;
+	struct zynqmp_r5_core *r5_core;
+	int i;
+
+	cluster = (struct zynqmp_r5_cluster *)platform_get_drvdata(pdev);
+	if (!cluster)
+		return;
+
+	for (i = 0; i < cluster->core_count; i++) {
+		r5_core = cluster->r5_cores[i];
+		of_reserved_mem_device_release(r5_core->dev);
+		put_device(r5_core->dev);
+		rproc_del(r5_core->rproc);
+		rproc_free(r5_core->rproc);
+	}
+
+	kfree(cluster->r5_cores);
+	kfree(cluster);
+	platform_set_drvdata(pdev, NULL);
+}
+
+/*
+ * zynqmp_r5_remoteproc_probe()
+ * parse device-tree, initialize hardware and allocate required resources
+ * and remoteproc ops
+ *
+ * @pdev: domain platform device for R5 cluster
+ *
+ * Return: 0 for success and < 0 for failure.
+ */
+static int zynqmp_r5_remoteproc_probe(struct platform_device *pdev)
+{
+	struct zynqmp_r5_cluster *cluster;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	cluster = kzalloc(sizeof(*cluster), GFP_KERNEL);
+	if (!cluster)
+		return -ENOMEM;
+
+	cluster->dev = dev;
+
+	ret = devm_of_platform_populate(dev);
+	if (ret) {
+		dev_err_probe(dev, ret, "failed to populate platform dev\n");
+		kfree(cluster);
+		return ret;
+	}
+
+	/* wire in so each core can be cleaned up at driver remove */
+	platform_set_drvdata(pdev, cluster);
+
+	ret = zynqmp_r5_cluster_init(cluster);
+	if (ret) {
+		kfree(cluster);
+		platform_set_drvdata(pdev, NULL);
+		dev_err_probe(dev, ret, "Invalid r5f subsystem device tree\n");
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(dev, zynqmp_r5_cluster_exit, pdev);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/* Match table for OF platform binding */
+static const struct of_device_id zynqmp_r5_remoteproc_match[] = {
+	{ .compatible = "xlnx,zynqmp-r5fss", },
+	{ /* end of list */ },
+};
+MODULE_DEVICE_TABLE(of, zynqmp_r5_remoteproc_match);
+
+static struct platform_driver zynqmp_r5_remoteproc_driver = {
+	.probe = zynqmp_r5_remoteproc_probe,
+	.driver = {
+		.name = "zynqmp_r5_remoteproc",
+		.of_match_table = zynqmp_r5_remoteproc_match,
+	},
+};
+module_platform_driver(zynqmp_r5_remoteproc_driver);
+
+MODULE_DESCRIPTION("Xilinx R5F remote processor driver");
+MODULE_AUTHOR("Xilinx Inc.");
+MODULE_LICENSE("GPL");
diff --git a/include/dt-bindings/power/xlnx-zynqmp-power.h b/include/dt-bindings/power/xlnx-zynqmp-power.h
index 0d9a412fd5e04c..618024cbb20dc6 100644
--- a/include/dt-bindings/power/xlnx-zynqmp-power.h
+++ b/include/dt-bindings/power/xlnx-zynqmp-power.h
@@ -6,6 +6,12 @@
 #ifndef _DT_BINDINGS_ZYNQMP_POWER_H
 #define _DT_BINDINGS_ZYNQMP_POWER_H
 
+#define		PD_RPU_0	7
+#define		PD_RPU_1	8
+#define		PD_R5_0_ATCM	15
+#define		PD_R5_0_BTCM	16
+#define		PD_R5_1_ATCM	17
+#define		PD_R5_1_BTCM	18
 #define		PD_USB_0	22
 #define		PD_USB_1	23
 #define		PD_TTC_0	24
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index fac37680ffe7b2..b986e267d149be 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -12,6 +12,7 @@
 
 #ifndef __FIRMWARE_ZYNQMP_H__
 #define __FIRMWARE_ZYNQMP_H__
+#include <linux/types.h>
 
 #include <linux/err.h>
 
@@ -87,6 +88,8 @@ enum pm_api_cb_id {
 enum pm_api_id {
 	PM_GET_API_VERSION = 1,
 	PM_REGISTER_NOTIFIER = 5,
+	PM_FORCE_POWERDOWN = 8,
+	PM_REQUEST_WAKEUP = 10,
 	PM_SYSTEM_SHUTDOWN = 12,
 	PM_REQUEST_NODE = 13,
 	PM_RELEASE_NODE = 14,
@@ -135,6 +138,10 @@ enum pm_ret_status {
 };
 
 enum pm_ioctl_id {
+	IOCTL_GET_RPU_OPER_MODE = 0,
+	IOCTL_SET_RPU_OPER_MODE = 1,
+	IOCTL_RPU_BOOT_ADDR_CONFIG = 2,
+	IOCTL_TCM_COMB_CONFIG = 3,
 	IOCTL_SET_TAPDELAY_BYPASS = 4,
 	IOCTL_SD_DLL_RESET = 6,
 	IOCTL_SET_SD_TAPDELAY = 7,
@@ -176,6 +183,21 @@ enum pm_query_id {
 	PM_QID_CLOCK_GET_MAX_DIVISOR = 13,
 };
 
+enum rpu_oper_mode {
+	PM_RPU_MODE_LOCKSTEP = 0,
+	PM_RPU_MODE_SPLIT = 1,
+};
+
+enum rpu_boot_mem {
+	PM_RPU_BOOTMEM_LOVEC = 0,
+	PM_RPU_BOOTMEM_HIVEC = 1,
+};
+
+enum rpu_tcm_comb {
+	PM_RPU_TCM_SPLIT = 0,
+	PM_RPU_TCM_COMB = 1,
+};
+
 enum zynqmp_pm_reset_action {
 	PM_RESET_ACTION_RELEASE = 0,
 	PM_RESET_ACTION_ASSERT = 1,
@@ -516,6 +538,15 @@ int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id);
 int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value);
 int zynqmp_pm_get_feature_config(enum pm_feature_config_id id, u32 *payload);
 int zynqmp_pm_register_sgi(u32 sgi_num, u32 reset);
+int zynqmp_pm_force_pwrdwn(const u32 target,
+			   const enum zynqmp_pm_request_ack ack);
+int zynqmp_pm_request_wake(const u32 node,
+			   const bool set_addr,
+			   const u64 address,
+			   const enum zynqmp_pm_request_ack ack);
+int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mode);
+int zynqmp_pm_set_rpu_mode(u32 node_id, u32 arg1);
+int zynqmp_pm_set_tcm_config(u32 node_id, u32 arg1);
 int zynqmp_pm_set_sd_config(u32 node, enum pm_sd_config_type config, u32 value);
 int zynqmp_pm_set_gem_config(u32 node, enum pm_gem_config_type config,
 			     u32 value);
@@ -795,6 +826,35 @@ static inline int zynqmp_pm_register_sgi(u32 sgi_num, u32 reset)
 	return -ENODEV;
 }
 
+static inline int zynqmp_pm_force_pwrdwn(const u32 target,
+					 const enum zynqmp_pm_request_ack ack)
+{
+	return -ENODEV;
+}
+
+static inline int zynqmp_pm_request_wake(const u32 node,
+					 const bool set_addr,
+					 const u64 address,
+					 const enum zynqmp_pm_request_ack ack)
+{
+	return -ENODEV;
+}
+
+static inline int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mode)
+{
+	return -ENODEV;
+}
+
+static inline int zynqmp_pm_set_rpu_mode(u32 node_id, u32 arg1)
+{
+	return -ENODEV;
+}
+
+static inline int zynqmp_pm_set_tcm_config(u32 node_id, u32 arg1)
+{
+	return -ENODEV;
+}
+
 static inline int zynqmp_pm_set_sd_config(u32 node,
 					  enum pm_sd_config_type config,
 					  u32 value)