Merge tag 'rproc-v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc

Pull remoteproc updates from Bjorn Andersson:
 "This introduces support for the Mediatek MT9182 SCP and controlling
  the Cortex R5F processors found in TI K3 platforms. It clones the
  longstanding debugfs interface for controlling crash handling to
  sysfs. Lastly it solves a bug where after a warm reset of Qualcomm
  platforms the modem would crash upon first boot"

* tag 'rproc-v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc:
  remoteproc/mediatek: Remove non-standard dsb()
  remoteproc: Add recovery configuration to the sysfs interface
  remoteproc: Add coredump as part of sysfs interface
  remoteproc: Change default dump configuration to "disabled"
  remoteproc: k3-r5: Add loading support for on-chip SRAM regions
  remoteproc: k3-r5: Initialize TCM memories for ECC
  remoteproc: k3-r5: Add a remoteproc driver for R5F subsystem
  dt-bindings: remoteproc: Add bindings for R5F subsystem on TI K3 SoCs
  remoteproc/mediatek: Add support for mt8192 SCP
  remoteproc: Fixup coredump debugfs disable request
  remoteproc: qcom_q6v5: Assign mpss region to Q6 before MBA boot
  remoteproc/mediatek: fix null pointer dereference on null scp pointer
  remoteproc: stm32: Fix pointer assignement
  remoteproc: scp: add COMPILE_TEST dependency

14 files changed, 2086 insertions, 62 deletions

diff --git a/Documentation/ABI/testing/sysfs-class-remoteproc b/Documentation/ABI/testing/sysfs-class-remoteproc
index 36094fbeb974..066b9b6f4924 100644
--- a/Documentation/ABI/testing/sysfs-class-remoteproc
+++ b/Documentation/ABI/testing/sysfs-class-remoteproc
@@ -58,3 +58,47 @@ Description:	Remote processor name
 		Reports the name of the remote processor. This can be used by
 		userspace in exactly identifying a remote processor and ease
 		up the usage in modifying the 'firmware' or 'state' files.
+
+What:		/sys/class/remoteproc/.../coredump
+Date:		July 2020
+Contact:	Bjorn Andersson <bjorn.andersson@linaro.org>, Ohad Ben-Cohen <ohad@wizery.com>
+Description:	Remote processor coredump configuration
+
+		Reports the coredump configuration of the remote processor,
+		which will be one of:
+
+		"disabled"
+		"enabled"
+		"inline"
+
+		"disabled" means no dump will be collected.
+
+		"enabled" means when the remote processor's coredump is
+		collected it will be copied to a separate buffer and that
+		buffer is exposed to userspace.
+
+		"inline" means when the remote processor's coredump is
+		collected userspace will directly read from the remote
+		processor's device memory. Extra buffer will not be used to
+		copy the dump. Also recovery process will not proceed until
+		all data is read by usersapce.
+
+What:		/sys/class/remoteproc/.../recovery
+Date:		July 2020
+Contact:	Bjorn Andersson <bjorn.andersson@linaro.org>, Ohad Ben-Cohen <ohad@wizery.com>
+Description:	Remote processor recovery mechanism
+
+		Reports the recovery mechanism of the remote processor,
+		which will be one of:
+
+		"enabled"
+		"disabled"
+
+		"enabled" means, the remote processor will be automatically
+		recovered whenever it crashes. Moreover, if the remote
+		processor crashes while recovery is disabled, it will
+		be automatically recovered too as soon as recovery is enabled.
+
+		"disabled" means, a remote processor will remain in a crashed
+		state if it crashes. This is useful for debugging purposes;
+		without it, debugging a crash is substantially harder.
diff --git a/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml
new file mode 100644
index 000000000000..4069f0f5e8fa
--- /dev/null
+++ b/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml
@@ -0,0 +1,281 @@
+# SPDX-License-Identifier: (GPL-2.0-only or BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/remoteproc/ti,k3-r5f-rproc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: TI K3 R5F processor subsystems
+
+maintainers:
+  - Suman Anna <s-anna@ti.com>
+
+description: |
+  The TI K3 family of SoCs usually have one or more dual-core Arm Cortex R5F
+  processor subsystems/clusters (R5FSS). The dual core cluster can be used
+  either in a LockStep mode providing safety/fault tolerance features or in a
+  Split mode providing two individual compute cores for doubling the compute
+  capacity. These are used together with other processors present on the SoC
+  to achieve various system level goals.
+
+  Each Dual-Core R5F sub-system is represented as a single DTS node
+  representing the cluster, with a pair of child DT nodes representing
+  the individual R5F cores. Each node has a number of required or optional
+  properties that enable the OS running on the host processor to perform
+  the device management of the remote processor and to communicate with the
+  remote processor.
+
+properties:
+  $nodename:
+    pattern: "^r5fss(@.*)?"
+
+  compatible:
+    enum:
+      - ti,am654-r5fss
+      - ti,j721e-r5fss
+
+  power-domains:
+    description: |
+      Should contain a phandle to a PM domain provider node and an args
+      specifier containing the R5FSS device id value.
+    maxItems: 1
+
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 1
+
+  ranges:
+    description: |
+      Standard ranges definition providing address translations for
+      local R5F TCM address spaces to bus addresses.
+
+# Optional properties:
+# --------------------
+
+  ti,cluster-mode:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [0, 1]
+    description: |
+      Configuration Mode for the Dual R5F cores within the R5F cluster.
+      Should be either a value of 1 (LockStep mode) or 0 (Split mode),
+      default is LockStep mode if omitted.
+
+# R5F Processor Child Nodes:
+# ==========================
+
+patternProperties:
+  "^r5f@[a-f0-9]+$":
+    type: object
+    description: |
+      The R5F Sub-System device node should define two R5F child nodes, each
+      node representing a TI instantiation of the Arm Cortex R5F core. There
+      are some specific integration differences for the IP like the usage of
+      a Region Address Translator (RAT) for translating the larger SoC bus
+      addresses into a 32-bit address space for the processor.
+
+      Each R5F core has an associated 64 KB of Tightly-Coupled Memory (TCM)
+      internal memories split between two banks - TCMA and TCMB (further
+      interleaved into two banks TCMB0 and TCMB1). These memories (also called
+      ATCM and BTCM) provide read/write performance on par with the core's L1
+      caches. Each of the TCMs can be enabled or disabled independently and
+      either of them can be configured to appear at that R5F's address 0x0.
+
+      The cores do not use an MMU, but has a Region Address Translater
+      (RAT) module that is accessible only from the R5Fs for providing
+      translations between 32-bit CPU addresses into larger system bus
+      addresses. Cache and memory access settings are provided through a
+      Memory Protection Unit (MPU), programmable only from the R5Fs.
+
+    allOf:
+      - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml#
+
+    properties:
+      compatible:
+        enum:
+          - ti,am654-r5f
+          - ti,j721e-r5f
+
+      reg:
+        items:
+          - description: Address and Size of the ATCM internal memory region
+          - description: Address and Size of the BTCM internal memory region
+
+      reg-names:
+        items:
+          - const: atcm
+          - const: btcm
+
+      resets:
+        description: |
+          Should contain the phandle to the reset controller node managing the
+          local resets for this device, and a reset specifier.
+        maxItems: 1
+
+      firmware-name:
+        description: |
+          Should contain the name of the default firmware image
+          file located on the firmware search path
+
+# The following properties are mandatory for R5F Core0 in both LockStep and Split
+# modes, and are mandatory for R5F Core1 _only_ in Split mode. They are unused for
+# R5F Core1 in LockStep mode:
+
+      mboxes:
+        description: |
+          OMAP Mailbox specifier denoting the sub-mailbox, to be used for
+          communication with the remote processor. This property should match
+          with the sub-mailbox node used in the firmware image.
+        maxItems: 1
+
+      memory-region:
+        description: |
+          phandle to the reserved memory nodes to be associated with the
+          remoteproc device. There should be at least two reserved memory nodes
+          defined. The reserved memory nodes should be carveout nodes, and
+          should be defined with a "no-map" property as per the bindings in
+          Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
+        minItems: 2
+        maxItems: 8
+        items:
+          - description: region used for dynamic DMA allocations like vrings and
+                         vring buffers
+          - description: region reserved for firmware image sections
+        additionalItems: true
+
+
+# Optional properties:
+# --------------------
+# The following properties are optional properties for each of the R5F cores:
+
+      ti,atcm-enable:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        enum: [0, 1]
+        description: |
+          R5F core configuration mode dictating if ATCM should be enabled. The
+          R5F address of ATCM is dictated by ti,loczrama property. Should be
+          either a value of 1 (enabled) or 0 (disabled), default is disabled
+          if omitted. Recommended to enable it for maximizing TCMs.
+
+      ti,btcm-enable:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        enum: [0, 1]
+        description: |
+          R5F core configuration mode dictating if BTCM should be enabled. The
+          R5F address of BTCM is dictated by ti,loczrama property. Should be
+          either a value of 1 (enabled) or 0 (disabled), default is enabled if
+          omitted.
+
+      ti,loczrama:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        enum: [0, 1]
+        description: |
+          R5F core configuration mode dictating which TCM should appear at
+          address 0 (from core's view). Should be either a value of 1 (ATCM
+          at 0x0) or 0 (BTCM at 0x0), default value is 1 if omitted.
+
+      sram:
+        $ref: /schemas/types.yaml#/definitions/phandle-array
+        minItems: 1
+        maxItems: 4
+        description: |
+          phandles to one or more reserved on-chip SRAM regions. 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
+
+    required:
+      - compatible
+      - reg
+      - reg-names
+      - ti,sci
+      - ti,sci-dev-id
+      - ti,sci-proc-ids
+      - resets
+      - firmware-name
+
+    unevaluatedProperties: false
+
+required:
+  - compatible
+  - power-domains
+  - "#address-cells"
+  - "#size-cells"
+  - ranges
+
+additionalProperties: false
+
+examples:
+  - |
+    / {
+        model = "Texas Instruments K3 AM654 SoC";
+        compatible = "ti,am654-evm", "ti,am654";
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        bus@100000 {
+            compatible = "simple-bus";
+            #address-cells = <2>;
+            #size-cells = <2>;
+            ranges = <0x00 0x00100000 0x00 0x00100000 0x00 0x00020000>, /* ctrl mmr */
+                     <0x00 0x41000000 0x00 0x41000000 0x00 0x00020000>,
+                     <0x00 0x41400000 0x00 0x41400000 0x00 0x00020000>,
+                     <0x00 0x41c00000 0x00 0x41c00000 0x00 0x00080000>;
+
+            bus@28380000 {
+                compatible = "simple-bus";
+                #address-cells = <2>;
+                #size-cells = <2>;
+                ranges = <0x00 0x28380000 0x00 0x28380000 0x00 0x03880000>, /* MCU NAVSS */
+                         <0x00 0x41000000 0x00 0x41000000 0x00 0x00020000>, /* MCU R5F Core0 */
+                         <0x00 0x41400000 0x00 0x41400000 0x00 0x00020000>, /* MCU R5F Core1 */
+                         <0x00 0x41c00000 0x00 0x41c00000 0x00 0x00080000>; /* MCU SRAM */
+
+                /* AM65x MCU R5FSS node */
+                mcu_r5fss0: r5fss@41000000 {
+                    compatible = "ti,am654-r5fss";
+                    power-domains = <&k3_pds 129>;
+                    ti,cluster-mode = <1>;
+                    #address-cells = <1>;
+                    #size-cells = <1>;
+                    ranges = <0x41000000 0x00 0x41000000 0x20000>,
+                             <0x41400000 0x00 0x41400000 0x20000>;
+
+                    mcu_r5f0: r5f@41000000 {
+                        compatible = "ti,am654-r5f";
+                        reg = <0x41000000 0x00008000>,
+                              <0x41010000 0x00008000>;
+                        reg-names = "atcm", "btcm";
+                        ti,sci = <&dmsc>;
+                        ti,sci-dev-id = <159>;
+                        ti,sci-proc-ids = <0x01 0xFF>;
+                        resets = <&k3_reset 159 1>;
+                        firmware-name = "am65x-mcu-r5f0_0-fw";
+                        ti,atcm-enable = <1>;
+                        ti,btcm-enable = <1>;
+                        ti,loczrama = <1>;
+                        mboxes = <&mailbox0 &mbox_mcu_r5fss0_core0>;
+                        memory-region = <&mcu_r5fss0_core0_dma_memory_region>,
+                                        <&mcu_r5fss0_core0_memory_region>;
+                        sram = <&mcu_r5fss0_core0_sram>;
+                    };
+
+                    mcu_r5f1: r5f@41400000 {
+                        compatible = "ti,am654-r5f";
+                        reg = <0x41400000 0x00008000>,
+                              <0x41410000 0x00008000>;
+                        reg-names = "atcm", "btcm";
+                        ti,sci = <&dmsc>;
+                        ti,sci-dev-id = <245>;
+                        ti,sci-proc-ids = <0x02 0xFF>;
+                        resets = <&k3_reset 245 1>;
+                        firmware-name = "am65x-mcu-r5f0_1-fw";
+                        ti,atcm-enable = <1>;
+                        ti,btcm-enable = <1>;
+                        ti,loczrama = <1>;
+                        mboxes = <&mailbox1 &mbox_mcu_r5fss0_core1>;
+                    };
+                };
+            };
+        };
+    };
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index d1fcada71017..d99548fb5dde 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -275,6 +275,19 @@ config TI_K3_DSP_REMOTEPROC
 	  It's safe to say N here if you're not interested in utilizing
 	  the DSP slave processors.
 
+config TI_K3_R5_REMOTEPROC
+	tristate "TI K3 R5 remoteproc support"
+	depends on ARCH_K3
+	select MAILBOX
+	select OMAP2PLUS_MBOX
+	help
+	  Say m here to support TI's R5F remote processor subsystems
+	  on various TI K3 family of SoCs through the remote processor
+	  framework.
+
+	  It's safe to say N here if you're not interested in utilizing
+	  a slave processor.
+
 endif # REMOTEPROC
 
 endmenu
diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile
index 3dfa28e6c701..da2ace4ec86c 100644
--- a/drivers/remoteproc/Makefile
+++ b/drivers/remoteproc/Makefile
@@ -33,3 +33,4 @@ obj-$(CONFIG_ST_REMOTEPROC)		+= st_remoteproc.o
 obj-$(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
diff --git a/drivers/remoteproc/mtk_common.h b/drivers/remoteproc/mtk_common.h
index 0066c83636d0..47b4561443a9 100644
--- a/drivers/remoteproc/mtk_common.h
+++ b/drivers/remoteproc/mtk_common.h
@@ -32,6 +32,23 @@
 #define MT8183_SCP_CACHESIZE_8KB	BIT(8)
 #define MT8183_SCP_CACHE_CON_WAYEN	BIT(10)
 
+#define MT8192_L2TCM_SRAM_PD_0		0x210C0
+#define MT8192_L2TCM_SRAM_PD_1		0x210C4
+#define MT8192_L2TCM_SRAM_PD_2		0x210C8
+#define MT8192_L1TCM_SRAM_PDN		0x2102C
+#define MT8192_CPU0_SRAM_PD		0x21080
+
+#define MT8192_SCP2APMCU_IPC_SET	0x24080
+#define MT8192_SCP2APMCU_IPC_CLR	0x24084
+#define MT8192_SCP_IPC_INT_BIT		BIT(0)
+#define MT8192_SCP2SPM_IPC_CLR		0x24094
+#define MT8192_GIPC_IN_SET		0x24098
+#define MT8192_HOST_IPC_INT_BIT		BIT(0)
+
+#define MT8192_CORE0_SW_RSTN_CLR	0x30000
+#define MT8192_CORE0_SW_RSTN_SET	0x30004
+#define MT8192_CORE0_WDT_CFG		0x30034
+
 #define SCP_FW_VER_LEN			32
 #define SCP_SHARE_BUFFER_SIZE		288
 
@@ -50,6 +67,19 @@ struct scp_ipi_desc {
 	void *priv;
 };
 
+struct mtk_scp;
+
+struct mtk_scp_of_data {
+	int (*scp_before_load)(struct mtk_scp *scp);
+	void (*scp_irq_handler)(struct mtk_scp *scp);
+	void (*scp_reset_assert)(struct mtk_scp *scp);
+	void (*scp_reset_deassert)(struct mtk_scp *scp);
+	void (*scp_stop)(struct mtk_scp *scp);
+
+	u32 host_to_scp_reg;
+	u32 host_to_scp_int_bit;
+};
+
 struct mtk_scp {
 	struct device *dev;
 	struct rproc *rproc;
@@ -58,6 +88,8 @@ struct mtk_scp {
 	void __iomem *sram_base;
 	size_t sram_size;
 
+	const struct mtk_scp_of_data *data;
+
 	struct mtk_share_obj __iomem *recv_buf;
 	struct mtk_share_obj __iomem *send_buf;
 	struct scp_run run;
diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c
index ac13e7b046a6..577cbd5d421e 100644
--- a/drivers/remoteproc/mtk_scp.c
+++ b/drivers/remoteproc/mtk_scp.c
@@ -124,9 +124,6 @@ static int scp_ipi_init(struct mtk_scp *scp)
 	size_t send_offset = SCP_FW_END - sizeof(struct mtk_share_obj);
 	size_t recv_offset = send_offset - sizeof(struct mtk_share_obj);
 
-	/* Disable SCP to host interrupt */
-	writel(MT8183_SCP_IPC_INT_BIT, scp->reg_base + MT8183_SCP_TO_HOST);
-
 	/* shared buffer initialization */
 	scp->recv_buf =
 		(struct mtk_share_obj __iomem *)(scp->sram_base + recv_offset);
@@ -138,7 +135,7 @@ static int scp_ipi_init(struct mtk_scp *scp)
 	return 0;
 }
 
-static void scp_reset_assert(const struct mtk_scp *scp)
+static void mt8183_scp_reset_assert(struct mtk_scp *scp)
 {
 	u32 val;
 
@@ -147,7 +144,7 @@ static void scp_reset_assert(const struct mtk_scp *scp)
 	writel(val, scp->reg_base + MT8183_SW_RSTN);
 }
 
-static void scp_reset_deassert(const struct mtk_scp *scp)
+static void mt8183_scp_reset_deassert(struct mtk_scp *scp)
 {
 	u32 val;
 
@@ -156,17 +153,19 @@ static void scp_reset_deassert(const struct mtk_scp *scp)
 	writel(val, scp->reg_base + MT8183_SW_RSTN);
 }
 
-static irqreturn_t scp_irq_handler(int irq, void *priv)
+static void mt8192_scp_reset_assert(struct mtk_scp *scp)
 {
-	struct mtk_scp *scp = priv;
-	u32 scp_to_host;
-	int ret;
+	writel(1, scp->reg_base + MT8192_CORE0_SW_RSTN_SET);
+}
 
-	ret = clk_prepare_enable(scp->clk);
-	if (ret) {
-		dev_err(scp->dev, "failed to enable clocks\n");
-		return IRQ_NONE;
-	}
+static void mt8192_scp_reset_deassert(struct mtk_scp *scp)
+{
+	writel(1, scp->reg_base + MT8192_CORE0_SW_RSTN_CLR);
+}
+
+static void mt8183_scp_irq_handler(struct mtk_scp *scp)
+{
+	u32 scp_to_host;
 
 	scp_to_host = readl(scp->reg_base + MT8183_SCP_TO_HOST);
 	if (scp_to_host & MT8183_SCP_IPC_INT_BIT)
@@ -177,6 +176,40 @@ static irqreturn_t scp_irq_handler(int irq, void *priv)
 	/* SCP won't send another interrupt until we set SCP_TO_HOST to 0. */
 	writel(MT8183_SCP_IPC_INT_BIT | MT8183_SCP_WDT_INT_BIT,
 	       scp->reg_base + MT8183_SCP_TO_HOST);
+}
+
+static void mt8192_scp_irq_handler(struct mtk_scp *scp)
+{
+	u32 scp_to_host;
+
+	scp_to_host = readl(scp->reg_base + MT8192_SCP2APMCU_IPC_SET);
+
+	if (scp_to_host & MT8192_SCP_IPC_INT_BIT)
+		scp_ipi_handler(scp);
+	else
+		scp_wdt_handler(scp, scp_to_host);
+
+	/*
+	 * SCP won't send another interrupt until we clear
+	 * MT8192_SCP2APMCU_IPC.
+	 */
+	writel(MT8192_SCP_IPC_INT_BIT,
+	       scp->reg_base + MT8192_SCP2APMCU_IPC_CLR);
+}
+
+static irqreturn_t scp_irq_handler(int irq, void *priv)
+{
+	struct mtk_scp *scp = priv;
+	int ret;
+
+	ret = clk_prepare_enable(scp->clk);
+	if (ret) {
+		dev_err(scp->dev, "failed to enable clocks\n");
+		return IRQ_NONE;
+	}
+
+	scp->data->scp_irq_handler(scp);
+
 	clk_disable_unprepare(scp->clk);
 
 	return IRQ_HANDLED;
@@ -238,20 +271,10 @@ static int scp_elf_load_segments(struct rproc *rproc, const struct firmware *fw)
 	return ret;
 }
 
-static int scp_load(struct rproc *rproc, const struct firmware *fw)
+static int mt8183_scp_before_load(struct mtk_scp *scp)
 {
-	const struct mtk_scp *scp = rproc->priv;
-	struct device *dev = scp->dev;
-	int ret;
-
-	ret = clk_prepare_enable(scp->clk);
-	if (ret) {
-		dev_err(dev, "failed to enable clocks\n");
-		return ret;
-	}
-
-	/* Hold SCP in reset while loading FW. */
-	scp_reset_assert(scp);
+	/* Clear SCP to host interrupt */
+	writel(MT8183_SCP_IPC_INT_BIT, scp->reg_base + MT8183_SCP_TO_HOST);
 
 	/* Reset clocks before loading FW */
 	writel(0x0, scp->reg_base + MT8183_SCP_CLK_SW_SEL);
@@ -272,6 +295,63 @@ static int scp_load(struct rproc *rproc, const struct firmware *fw)
 	       scp->reg_base + MT8183_SCP_CACHE_CON);
 	writel(MT8183_SCP_CACHESIZE_8KB, scp->reg_base + MT8183_SCP_DCACHE_CON);
 
+	return 0;
+}
+
+static void mt8192_power_on_sram(void *addr)
+{
+	int i;
+
+	for (i = 31; i >= 0; i--)
+		writel(GENMASK(i, 0), addr);
+	writel(0, addr);
+}
+
+static void mt8192_power_off_sram(void *addr)
+{
+	int i;
+
+	writel(0, addr);
+	for (i = 0; i < 32; i++)
+		writel(GENMASK(i, 0), addr);
+}
+
+static int mt8192_scp_before_load(struct mtk_scp *scp)
+{
+	/* clear SPM interrupt, SCP2SPM_IPC_CLR */
+	writel(0xff, scp->reg_base + MT8192_SCP2SPM_IPC_CLR);
+
+	writel(1, scp->reg_base + MT8192_CORE0_SW_RSTN_SET);
+
+	/* enable SRAM clock */
+	mt8192_power_on_sram(scp->reg_base + MT8192_L2TCM_SRAM_PD_0);
+	mt8192_power_on_sram(scp->reg_base + MT8192_L2TCM_SRAM_PD_1);
+	mt8192_power_on_sram(scp->reg_base + MT8192_L2TCM_SRAM_PD_2);
+	mt8192_power_on_sram(scp->reg_base + MT8192_L1TCM_SRAM_PDN);
+	mt8192_power_on_sram(scp->reg_base + MT8192_CPU0_SRAM_PD);
+
+	return 0;
+}
+
+static int scp_load(struct rproc *rproc, const struct firmware *fw)
+{
+	struct mtk_scp *scp = rproc->priv;
+	struct device *dev = scp->dev;
+	int ret;
+
+	ret = clk_prepare_enable(scp->clk);
+	if (ret) {
+		dev_err(dev, "failed to enable clocks\n");
+		return ret;
+	}
+
+	/* Hold SCP in reset while loading FW. */
+	scp->data->scp_reset_assert(scp);
+
+	ret = scp->data->scp_before_load(scp);
+	if (ret < 0)
+		return ret;
+
 	ret = scp_elf_load_segments(rproc, fw);
 	clk_disable_unprepare(scp->clk);
 
@@ -293,7 +373,7 @@ static int scp_start(struct rproc *rproc)
 
 	run->signaled = false;
 
-	scp_reset_deassert(scp);
+	scp->data->scp_reset_deassert(scp);
 
 	ret = wait_event_interruptible_timeout(
 					run->wq,
@@ -309,13 +389,14 @@ static int scp_start(struct rproc *rproc)
 		dev_err(dev, "wait SCP interrupted by a signal!\n");
 		goto stop;
 	}
+
 	clk_disable_unprepare(scp->clk);
 	dev_info(dev, "SCP is ready. FW version %s\n", run->fw_ver);
 
 	return 0;
 
 stop:
-	scp_reset_assert(scp);
+	scp->data->scp_reset_assert(scp);
 	clk_disable_unprepare(scp->clk);
 	return ret;
 }
@@ -329,7 +410,7 @@ static void *scp_da_to_va(struct rproc *rproc, u64 da, size_t len)
 		offset = da;
 		if (offset >= 0 && (offset + len) < scp->sram_size)
 			return (void __force *)scp->sram_base + offset;
-	} else {
+	} else if (scp->dram_size) {
 		offset = da - scp->dma_addr;
 		if (offset >= 0 && (offset + len) < scp->dram_size)
 			return (void __force *)scp->cpu_addr + offset;
@@ -338,6 +419,25 @@ static void *scp_da_to_va(struct rproc *rproc, u64 da, size_t len)
 	return NULL;
 }
 
+static void mt8183_scp_stop(struct mtk_scp *scp)
+{
+	/* Disable SCP watchdog */
+	writel(0, scp->reg_base + MT8183_WDT_CFG);
+}
+
+static void mt8192_scp_stop(struct mtk_scp *scp)
+{
+	/* Disable SRAM clock */
+	mt8192_power_off_sram(scp->reg_base + MT8192_L2TCM_SRAM_PD_0);
+	mt8192_power_off_sram(scp->reg_base + MT8192_L2TCM_SRAM_PD_1);
+	mt8192_power_off_sram(scp->reg_base + MT8192_L2TCM_SRAM_PD_2);
+	mt8192_power_off_sram(scp->reg_base + MT8192_L1TCM_SRAM_PDN);
+	mt8192_power_off_sram(scp->reg_base + MT8192_CPU0_SRAM_PD);
+
+	/* Disable SCP watchdog */
+	writel(0, scp->reg_base + MT8192_CORE0_WDT_CFG);
+}
+
 static int scp_stop(struct rproc *rproc)
 {
 	struct mtk_scp *scp = (struct mtk_scp *)rproc->priv;
@@ -349,9 +449,8 @@ static int scp_stop(struct rproc *rproc)
 		return ret;
 	}
 
-	scp_reset_assert(scp);
-	/* Disable SCP watchdog */
-	writel(0, scp->reg_base + MT8183_WDT_CFG);
+	scp->data->scp_reset_assert(scp);
+	scp->data->scp_stop(scp);
 	clk_disable_unprepare(scp->clk);
 
 	return 0;
@@ -443,6 +542,13 @@ static int scp_map_memory_region(struct mtk_scp *scp)
 	int ret;
 
 	ret = of_reserved_mem_device_init(scp->dev);
+
+	/* reserved memory is optional. */
+	if (ret == -ENODEV) {
+		dev_info(scp->dev, "skipping reserved memory initialization.");
+		return 0;
+	}
+
 	if (ret) {
 		dev_err(scp->dev, "failed to assign memory-region: %d\n", ret);
 		return -ENOMEM;
@@ -460,6 +566,9 @@ static int scp_map_memory_region(struct mtk_scp *scp)
 
 static void scp_unmap_memory_region(struct mtk_scp *scp)
 {
+	if (scp->dram_size == 0)
+		return;
+
 	dma_free_coherent(scp->dev, scp->dram_size, scp->cpu_addr,
 			  scp->dma_addr);
 	of_reserved_mem_device_release(scp->dev);
@@ -536,6 +645,7 @@ static int scp_probe(struct platform_device *pdev)
 	scp = (struct mtk_scp *)rproc->priv;
 	scp->rproc = rproc;
 	scp->dev = dev;
+	scp->data = of_device_get_match_data(dev);
 	platform_set_drvdata(pdev, scp);
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sram");
@@ -642,8 +752,29 @@ static int scp_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct mtk_scp_of_data mt8183_of_data = {
+	.scp_before_load = mt8183_scp_before_load,
+	.scp_irq_handler = mt8183_scp_irq_handler,
+	.scp_reset_assert = mt8183_scp_reset_assert,
+	.scp_reset_deassert = mt8183_scp_reset_deassert,
+	.scp_stop = mt8183_scp_stop,
+	.host_to_scp_reg = MT8183_HOST_TO_SCP,
+	.host_to_scp_int_bit = MT8183_HOST_IPC_INT_BIT,
+};
+
+static const struct mtk_scp_of_data mt8192_of_data = {
+	.scp_before_load = mt8192_scp_before_load,
+	.scp_irq_handler = mt8192_scp_irq_handler,
+	.scp_reset_assert = mt8192_scp_reset_assert,
+	.scp_reset_deassert = mt8192_scp_reset_deassert,
+	.scp_stop = mt8192_scp_stop,
+	.host_to_scp_reg = MT8192_GIPC_IN_SET,
+	.host_to_scp_int_bit = MT8192_HOST_IPC_INT_BIT,
+};
+
 static const struct of_device_id mtk_scp_of_match[] = {
-	{ .compatible = "mediatek,mt8183-scp"},
+	{ .compatible = "mediatek,mt8183-scp", .data = &mt8183_of_data },
+	{ .compatible = "mediatek,mt8192-scp", .data = &mt8192_of_data },
 	{},
 };
 MODULE_DEVICE_TABLE(of, mtk_scp_of_match);
diff --git a/drivers/remoteproc/mtk_scp_ipi.c b/drivers/remoteproc/mtk_scp_ipi.c
index 3d3d87210ef2..6dc955ecab80 100644
--- a/drivers/remoteproc/mtk_scp_ipi.c
+++ b/drivers/remoteproc/mtk_scp_ipi.c
@@ -30,10 +30,8 @@ int scp_ipi_register(struct mtk_scp *scp,
 		     scp_ipi_handler_t handler,
 		     void *priv)
 {
-	if (!scp) {
-		dev_err(scp->dev, "scp device is not ready\n");
+	if (!scp)
 		return -EPROBE_DEFER;
-	}
 
 	if (WARN_ON(id >= SCP_IPI_MAX) || WARN_ON(handler == NULL))
 		return -EINVAL;
@@ -182,7 +180,7 @@ int scp_ipi_send(struct mtk_scp *scp, u32 id, void *buf, unsigned int len,
 			ret = -ETIMEDOUT;
 			goto clock_disable;
 		}
-	} while (readl(scp->reg_base + MT8183_HOST_TO_SCP));
+	} while (readl(scp->reg_base + scp->data->host_to_scp_reg));
 
 	scp_memcpy_aligned(send_obj->share_buf, buf, len);
 
@@ -191,7 +189,8 @@ int scp_ipi_send(struct mtk_scp *scp, u32 id, void *buf, unsigned int len,
 
 	scp->ipi_id_ack[id] = false;
 	/* send the command to SCP */
-	writel(MT8183_HOST_IPC_INT_BIT, scp->reg_base + MT8183_HOST_TO_SCP);
+	writel(scp->data->host_to_scp_int_bit,
+	       scp->reg_base + scp->data->host_to_scp_reg);
 
 	if (wait) {
 		/* wait for SCP's ACK */
diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index c401bcc263fa..eb3457a6c3b7 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -931,6 +931,17 @@ static int q6v5_mba_load(struct q6v5 *qproc)
 		goto assert_reset;
 	}
 
+	/*
+	 * Some versions of the MBA firmware will upon boot wipe the MPSS region as well, so provide
+	 * the Q6 access to this region.
+	 */
+	ret = q6v5_xfer_mem_ownership(qproc, &qproc->mpss_perm, false, true,
+				      qproc->mpss_phys, qproc->mpss_size);
+	if (ret) {
+		dev_err(qproc->dev, "assigning Q6 access to mpss memory failed: %d\n", ret);
+		goto disable_active_clks;
+	}
+
 	/* Assign MBA image access in DDR to q6 */
 	ret = q6v5_xfer_mem_ownership(qproc, &qproc->mba_perm, false, true,
 				      qproc->mba_phys, qproc->mba_size);
@@ -1135,10 +1146,9 @@ static int q6v5_mpss_load(struct q6v5 *qproc)
 			max_addr = ALIGN(phdr->p_paddr + phdr->p_memsz, SZ_4K);
 	}
 
-	/**
+	/*
 	 * In case of a modem subsystem restart on secure devices, the modem
-	 * memory can be reclaimed only after MBA is loaded. For modem cold
-	 * boot this will be a nop
+	 * memory can be reclaimed only after MBA is loaded.
 	 */
 	q6v5_xfer_mem_ownership(qproc, &qproc->mpss_perm, true, false,
 				qproc->mpss_phys, qproc->mpss_size);
diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c
index bb15a29038e8..34530dc20cb4 100644
--- a/drivers/remoteproc/remoteproc_coredump.c
+++ b/drivers/remoteproc/remoteproc_coredump.c
@@ -257,7 +257,7 @@ void rproc_coredump(struct rproc *rproc)
 		 * directly read from device memory.
 		 */
 		data_size += elf_size_of_phdr(class);
-		if (dump_conf == RPROC_COREDUMP_DEFAULT)
+		if (dump_conf == RPROC_COREDUMP_ENABLED)
 			data_size += segment->size;
 
 		phnum++;
@@ -297,14 +297,14 @@ void rproc_coredump(struct rproc *rproc)
 		elf_phdr_set_p_flags(class, phdr, PF_R | PF_W | PF_X);
 		elf_phdr_set_p_align(class, phdr, 0);
 
-		if (dump_conf == RPROC_COREDUMP_DEFAULT)
+		if (dump_conf == RPROC_COREDUMP_ENABLED)
 			rproc_copy_segment(rproc, data + offset, segment, 0,
 					   segment->size);
 
 		offset += elf_phdr_get_p_filesz(class, phdr);
 		phdr += elf_size_of_phdr(class);
 	}
-	if (dump_conf == RPROC_COREDUMP_DEFAULT) {
+	if (dump_conf == RPROC_COREDUMP_ENABLED) {
 		dev_coredumpv(&rproc->dev, data, data_size, GFP_KERNEL);
 		return;
 	}
diff --git a/drivers/remoteproc/remoteproc_debugfs.c b/drivers/remoteproc/remoteproc_debugfs.c
index 2e3b3e22e1d0..7e5845376e9f 100644
--- a/drivers/remoteproc/remoteproc_debugfs.c
+++ b/drivers/remoteproc/remoteproc_debugfs.c
@@ -33,9 +33,9 @@ static struct dentry *rproc_dbg;
  * enum rproc_coredump_mechanism
  */
 static const char * const rproc_coredump_str[] = {
-	[RPROC_COREDUMP_DEFAULT]	= "default",
-	[RPROC_COREDUMP_INLINE]		= "inline",
 	[RPROC_COREDUMP_DISABLED]	= "disabled",
+	[RPROC_COREDUMP_ENABLED]	= "enabled",
+	[RPROC_COREDUMP_INLINE]		= "inline",
 };
 
 /* Expose the current coredump configuration via debugfs */
@@ -54,20 +54,19 @@ static ssize_t rproc_coredump_read(struct file *filp, char __user *userbuf,
 
 /*
  * By writing to the 'coredump' debugfs entry, we control the behavior of the
- * coredump mechanism dynamically. The default value of this entry is "default".
+ * coredump mechanism dynamically. The default value of this entry is "disabled".
  *
  * The 'coredump' debugfs entry supports these commands:
  *
- * default:	This is the default coredump mechanism. When the remoteproc
- *		crashes the entire coredump will be copied to a separate buffer
- *		and exposed to userspace.
+ * disabled:	By default coredump collection is disabled. Recovery will
+ *		proceed without collecting any dump.
+ *
+ * enabled:	When the remoteproc crashes the entire coredump will be copied
+ *		to a separate buffer and exposed to userspace.
  *
  * inline:	The coredump will not be copied to a separate buffer and the
  *		recovery process will have to wait until data is read by
  *		userspace. But this avoid usage of extra memory.
- *
- * disabled:	This will disable coredump. Recovery will proceed without
- *		collecting any dump.
  */
 static ssize_t rproc_coredump_write(struct file *filp,
 				    const char __user *user_buf, size_t count,
@@ -94,12 +93,12 @@ static ssize_t rproc_coredump_write(struct file *filp,
 		goto out;
 	}
 
-	if (!strncmp(buf, "disable", count)) {
+	if (!strncmp(buf, "disabled", count)) {
 		rproc->dump_conf = RPROC_COREDUMP_DISABLED;
+	} else if (!strncmp(buf, "enabled", count)) {
+		rproc->dump_conf = RPROC_COREDUMP_ENABLED;
 	} else if (!strncmp(buf, "inline", count)) {
 		rproc->dump_conf = RPROC_COREDUMP_INLINE;
-	} else if (!strncmp(buf, "default", count)) {
-		rproc->dump_conf = RPROC_COREDUMP_DEFAULT;
 	} else {
 		dev_err(&rproc->dev, "Invalid coredump configuration\n");
 		err = -EINVAL;
diff --git a/drivers/remoteproc/remoteproc_sysfs.c b/drivers/remoteproc/remoteproc_sysfs.c
index eea514cec50e..d1cf7bf277c4 100644
--- a/drivers/remoteproc/remoteproc_sysfs.c
+++ b/drivers/remoteproc/remoteproc_sysfs.c
@@ -10,6 +10,123 @@
 
 #define to_rproc(d) container_of(d, struct rproc, dev)
 
+static ssize_t recovery_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct rproc *rproc = to_rproc(dev);
+
+	return sprintf(buf, "%s", rproc->recovery_disabled ? "disabled\n" : "enabled\n");
+}
+
+/*
+ * By writing to the 'recovery' sysfs entry, we control the behavior of the
+ * recovery mechanism dynamically. The default value of this entry is "enabled".
+ *
+ * The 'recovery' sysfs entry supports these commands:
+ *
+ * enabled:	When enabled, the remote processor will be automatically
+ *		recovered whenever it crashes. Moreover, if the remote
+ *		processor crashes while recovery is disabled, it will
+ *		be automatically recovered too as soon as recovery is enabled.
+ *
+ * disabled:	When disabled, a remote processor will remain in a crashed
+ *		state if it crashes. This is useful for debugging purposes;
+ *		without it, debugging a crash is substantially harder.
+ *
+ * recover:	This function will trigger an immediate recovery if the
+ *		remote processor is in a crashed state, without changing
+ *		or checking the recovery state (enabled/disabled).
+ *		This is useful during debugging sessions, when one expects
+ *		additional crashes to happen after enabling recovery. In this
+ *		case, enabling recovery will make it hard to debug subsequent
+ *		crashes, so it's recommended to keep recovery disabled, and
+ *		instead use the "recover" command as needed.
+ */
+static ssize_t recovery_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct rproc *rproc = to_rproc(dev);
+
+	if (sysfs_streq(buf, "enabled")) {
+		/* change the flag and begin the recovery process if needed */
+		rproc->recovery_disabled = false;
+		rproc_trigger_recovery(rproc);
+	} else if (sysfs_streq(buf, "disabled")) {
+		rproc->recovery_disabled = true;
+	} else if (sysfs_streq(buf, "recover")) {
+		/* begin the recovery process without changing the flag */
+		rproc_trigger_recovery(rproc);
+	} else {
+		return -EINVAL;
+	}
+
+	return count;
+}
+static DEVICE_ATTR_RW(recovery);
+
+/*
+ * A coredump-configuration-to-string lookup table, for exposing a
+ * human readable configuration via sysfs. Always keep in sync with
+ * enum rproc_coredump_mechanism
+ */
+static const char * const rproc_coredump_str[] = {
+	[RPROC_COREDUMP_DISABLED]	= "disabled",
+	[RPROC_COREDUMP_ENABLED]	= "enabled",
+	[RPROC_COREDUMP_INLINE]		= "inline",
+};
+
+/* Expose the current coredump configuration via debugfs */
+static ssize_t coredump_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct rproc *rproc = to_rproc(dev);
+
+	return sprintf(buf, "%s\n", rproc_coredump_str[rproc->dump_conf]);
+}
+
+/*
+ * By writing to the 'coredump' sysfs entry, we control the behavior of the
+ * coredump mechanism dynamically. The default value of this entry is "default".
+ *
+ * The 'coredump' sysfs entry supports these commands:
+ *
+ * disabled:	This is the default coredump mechanism. Recovery will proceed
+ *		without collecting any dump.
+ *
+ * default:	When the remoteproc crashes the entire coredump will be
+ *		copied to a separate buffer and exposed to userspace.
+ *
+ * inline:	The coredump will not be copied to a separate buffer and the
+ *		recovery process will have to wait until data is read by
+ *		userspace. But this avoid usage of extra memory.
+ */
+static ssize_t coredump_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct rproc *rproc = to_rproc(dev);
+
+	if (rproc->state == RPROC_CRASHED) {
+		dev_err(&rproc->dev, "can't change coredump configuration\n");
+		return -EBUSY;
+	}
+
+	if (sysfs_streq(buf, "disabled")) {
+		rproc->dump_conf = RPROC_COREDUMP_DISABLED;
+	} else if (sysfs_streq(buf, "enabled")) {
+		rproc->dump_conf = RPROC_COREDUMP_ENABLED;
+	} else if (sysfs_streq(buf, "inline")) {
+		rproc->dump_conf = RPROC_COREDUMP_INLINE;
+	} else {
+		dev_err(&rproc->dev, "Invalid coredump configuration\n");
+		return -EINVAL;
+	}
+
+	return count;
+}
+static DEVICE_ATTR_RW(coredump);
+
 /* Expose the loaded / running firmware name via sysfs */
 static ssize_t firmware_show(struct device *dev, struct device_attribute *attr,
 			  char *buf)
@@ -138,6 +255,8 @@ static ssize_t name_show(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR_RO(name);
 
 static struct attribute *rproc_attrs[] = {
+	&dev_attr_coredump.attr,
+	&dev_attr_recovery.attr,
 	&dev_attr_firmware.attr,
 	&dev_attr_state.attr,
 	&dev_attr_name.attr,
diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c
index f4da42fc0eeb..d2414cc1d90d 100644
--- a/drivers/remoteproc/stm32_rproc.c
+++ b/drivers/remoteproc/stm32_rproc.c
@@ -685,7 +685,7 @@ static int stm32_rproc_get_m4_status(struct stm32_rproc *ddata,
 		 * We couldn't get the coprocessor's state, assume
 		 * it is not running.
 		 */
-		state = M4_STATE_OFF;
+		*state = M4_STATE_OFF;
 		return 0;
 	}
 
diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c
new file mode 100644
index 000000000000..d9307935441d
--- /dev/null
+++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
@@ -0,0 +1,1395 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * TI K3 R5F (MCU) Remote Processor driver
+ *
+ * Copyright (C) 2017-2020 Texas Instruments Incorporated - https://www.ti.com/
+ *	Suman Anna <s-anna@ti.com>
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mailbox_client.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/omap-mailbox.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/remoteproc.h>
+#include <linux/reset.h>
+#include <linux/slab.h>
+
+#include "omap_remoteproc.h"
+#include "remoteproc_internal.h"
+#include "ti_sci_proc.h"
+
+/* This address can either be for ATCM or BTCM with the other at address 0x0 */
+#define K3_R5_TCM_DEV_ADDR	0x41010000
+
+/* R5 TI-SCI Processor Configuration Flags */
+#define PROC_BOOT_CFG_FLAG_R5_DBG_EN			0x00000001
+#define PROC_BOOT_CFG_FLAG_R5_DBG_NIDEN			0x00000002
+#define PROC_BOOT_CFG_FLAG_R5_LOCKSTEP			0x00000100
+#define PROC_BOOT_CFG_FLAG_R5_TEINIT			0x00000200
+#define PROC_BOOT_CFG_FLAG_R5_NMFI_EN			0x00000400
+#define PROC_BOOT_CFG_FLAG_R5_TCM_RSTBASE		0x00000800
+#define PROC_BOOT_CFG_FLAG_R5_BTCM_EN			0x00001000
+#define PROC_BOOT_CFG_FLAG_R5_ATCM_EN			0x00002000
+
+/* R5 TI-SCI Processor Control Flags */
+#define PROC_BOOT_CTRL_FLAG_R5_CORE_HALT		0x00000001
+
+/* R5 TI-SCI Processor Status Flags */
+#define PROC_BOOT_STATUS_FLAG_R5_WFE			0x00000001
+#define PROC_BOOT_STATUS_FLAG_R5_WFI			0x00000002
+#define PROC_BOOT_STATUS_FLAG_R5_CLK_GATED		0x00000004
+#define PROC_BOOT_STATUS_FLAG_R5_LOCKSTEP_PERMITTED	0x00000100
+
+/**
+ * struct k3_r5_mem - internal memory structure
+ * @cpu_addr: MPU virtual address of the memory region
+ * @bus_addr: Bus address used to access the memory region
+ * @dev_addr: Device address from remoteproc view
+ * @size: Size of the memory region
+ */
+struct k3_r5_mem {
+	void __iomem *cpu_addr;
+	phys_addr_t bus_addr;
+	u32 dev_addr;
+	size_t size;
+};
+
+enum cluster_mode {
+	CLUSTER_MODE_SPLIT = 0,
+	CLUSTER_MODE_LOCKSTEP,
+};
+
+/**
+ * struct k3_r5_cluster - K3 R5F Cluster structure
+ * @dev: cached device pointer
+ * @mode: Mode to configure the Cluster - Split or LockStep
+ * @cores: list of R5 cores within the cluster
+ */
+struct k3_r5_cluster {
+	struct device *dev;
+	enum cluster_mode mode;
+	struct list_head cores;
+};
+
+/**
+ * struct k3_r5_core - K3 R5 core structure
+ * @elem: linked list item
+ * @dev: cached device pointer
+ * @rproc: rproc handle representing this core
+ * @mem: internal memory regions data
+ * @sram: on-chip SRAM memory regions data
+ * @num_mems: number of internal memory regions
+ * @num_sram: number of on-chip SRAM memory regions
+ * @reset: reset control handle
+ * @tsp: TI-SCI processor control handle
+ * @ti_sci: TI-SCI handle
+ * @ti_sci_id: TI-SCI device identifier
+ * @atcm_enable: flag to control ATCM enablement
+ * @btcm_enable: flag to control BTCM enablement
+ * @loczrama: flag to dictate which TCM is at device address 0x0
+ */
+struct k3_r5_core {
+	struct list_head elem;
+	struct device *dev;
+	struct rproc *rproc;
+	struct k3_r5_mem *mem;
+	struct k3_r5_mem *sram;
+	int num_mems;
+	int num_sram;
+	struct reset_control *reset;
+	struct ti_sci_proc *tsp;
+	const struct ti_sci_handle *ti_sci;
+	u32 ti_sci_id;
+	u32 atcm_enable;
+	u32 btcm_enable;
+	u32 loczrama;
+};
+
+/**
+ * struct k3_r5_rproc - K3 remote processor state
+ * @dev: cached device pointer
+ * @cluster: cached pointer to parent cluster structure
+ * @mbox: mailbox channel handle
+ * @client: mailbox client to request the mailbox channel
+ * @rproc: rproc handle
+ * @core: cached pointer to r5 core structure being used
+ * @rmem: reserved memory regions data
+ * @num_rmems: number of reserved memory regions
+ */
+struct k3_r5_rproc {
+	struct device *dev;
+	struct k3_r5_cluster *cluster;
+	struct mbox_chan *mbox;
+	struct mbox_client client;
+	struct rproc *rproc;
+	struct k3_r5_core *core;
+	struct k3_r5_mem *rmem;
+	int num_rmems;
+};
+
+/**
+ * k3_r5_rproc_mbox_callback() - inbound mailbox message handler
+ * @client: mailbox client pointer used for requesting the mailbox channel
+ * @data: mailbox payload
+ *
+ * This handler is invoked by the OMAP mailbox driver whenever a mailbox
+ * message is received. Usually, the mailbox payload simply contains
+ * the index of the virtqueue that is kicked by the remote processor,
+ * and we let remoteproc core handle it.
+ *
+ * In addition to virtqueue indices, we also have some out-of-band values
+ * that indicate different events. Those values are deliberately very
+ * large so they don't coincide with virtqueue indices.
+ */
+static void k3_r5_rproc_mbox_callback(struct mbox_client *client, void *data)
+{
+	struct k3_r5_rproc *kproc = container_of(client, struct k3_r5_rproc,
+						client);
+	struct device *dev = kproc->rproc->dev.parent;
+	const char *name = kproc->rproc->name;
+	u32 msg = omap_mbox_message(data);
+
+	dev_dbg(dev, "mbox msg: 0x%x\n", msg);
+
+	switch (msg) {
+	case RP_MBOX_CRASH:
+		/*
+		 * remoteproc detected an exception, but error recovery is not
+		 * supported. So, just log this for now
+		 */
+		dev_err(dev, "K3 R5F rproc %s crashed\n", name);
+		break;
+	case RP_MBOX_ECHO_REPLY:
+		dev_info(dev, "received echo reply from %s\n", name);
+		break;
+	default:
+		/* silently handle all other valid messages */
+		if (msg >= RP_MBOX_READY && msg < RP_MBOX_END_MSG)
+			return;
+		if (msg > kproc->rproc->max_notifyid) {
+			dev_dbg(dev, "dropping unknown message 0x%x", msg);
+			return;
+		}
+		/* msg contains the index of the triggered vring */
+		if (rproc_vq_interrupt(kproc->rproc, msg) == IRQ_NONE)
+			dev_dbg(dev, "no message was found in vqid %d\n", msg);
+	}
+}
+
+/* kick a virtqueue */
+static void k3_r5_rproc_kick(struct rproc *rproc, int vqid)
+{
+	struct k3_r5_rproc *kproc = rproc->priv;
+	struct device *dev = rproc->dev.parent;
+	mbox_msg_t msg = (mbox_msg_t)vqid;
+	int ret;
+
+	/* send the index of the triggered virtqueue in the mailbox payload */
+	ret = mbox_send_message(kproc->mbox, (void *)msg);
+	if (ret < 0)
+		dev_err(dev, "failed to send mailbox message, status = %d\n",
+			ret);
+}
+
+static int k3_r5_split_reset(struct k3_r5_core *core)
+{
+	int ret;
+
+	ret = reset_control_assert(core->reset);
+	if (ret) {
+		dev_err(core->dev, "local-reset assert failed, ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	ret = core->ti_sci->ops.dev_ops.put_device(core->ti_sci,
+						   core->ti_sci_id);
+	if (ret) {
+		dev_err(core->dev, "module-reset assert failed, ret = %d\n",
+			ret);
+		if (reset_control_deassert(core->reset))
+			dev_warn(core->dev, "local-reset deassert back failed\n");
+	}
+
+	return ret;
+}
+
+static int k3_r5_split_release(struct k3_r5_core *core)
+{
+	int ret;
+
+	ret = core->ti_sci->ops.dev_ops.get_device(core->ti_sci,
+						   core->ti_sci_id);
+	if (ret) {
+		dev_err(core->dev, "module-reset deassert failed, ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	ret = reset_control_deassert(core->reset);
+	if (ret) {
+		dev_err(core->dev, "local-reset deassert failed, ret = %d\n",
+			ret);
+		if (core->ti_sci->ops.dev_ops.put_device(core->ti_sci,
+							 core->ti_sci_id))
+			dev_warn(core->dev, "module-reset assert back failed\n");
+	}
+
+	return ret;
+}
+
+static int k3_r5_lockstep_reset(struct k3_r5_cluster *cluster)
+{
+	struct k3_r5_core *core;
+	int ret;
+
+	/* assert local reset on all applicable cores */
+	list_for_each_entry(core, &cluster->cores, elem) {
+		ret = reset_control_assert(core->reset);
+		if (ret) {
+			dev_err(core->dev, "local-reset assert failed, ret = %d\n",
+				ret);
+			core = list_prev_entry(core, elem);
+			goto unroll_local_reset;
+		}
+	}
+
+	/* disable PSC modules on all applicable cores */
+	list_for_each_entry(core, &cluster->cores, elem) {
+		ret = core->ti_sci->ops.dev_ops.put_device(core->ti_sci,
+							   core->ti_sci_id);
+		if (ret) {
+			dev_err(core->dev, "module-reset assert failed, ret = %d\n",
+				ret);
+			goto unroll_module_reset;
+		}
+	}
+
+	return 0;
+
+unroll_module_reset:
+	list_for_each_entry_continue_reverse(core, &cluster->cores, elem) {
+		if (core->ti_sci->ops.dev_ops.put_device(core->ti_sci,
+							 core->ti_sci_id))
+			dev_warn(core->dev, "module-reset assert back failed\n");
+	}
+	core = list_last_entry(&cluster->cores, struct k3_r5_core, elem);
+unroll_local_reset:
+	list_for_each_entry_from_reverse(core, &cluster->cores, elem) {
+		if (reset_control_deassert(core->reset))
+			dev_warn(core->dev, "local-reset deassert back failed\n");
+	}
+
+	return ret;
+}
+
+static int k3_r5_lockstep_release(struct k3_r5_cluster *cluster)
+{
+	struct k3_r5_core *core;
+	int ret;
+
+	/* enable PSC modules on all applicable cores */
+	list_for_each_entry_reverse(core, &cluster->cores, elem) {
+		ret = core->ti_sci->ops.dev_ops.get_device(core->ti_sci,
+							   core->ti_sci_id);
+		if (ret) {
+			dev_err(core->dev, "module-reset deassert failed, ret = %d\n",
+				ret);
+			core = list_next_entry(core, elem);
+			goto unroll_module_reset;
+		}
+	}
+
+	/* deassert local reset on all applicable cores */
+	list_for_each_entry_reverse(core, &cluster->cores, elem) {
+		ret = reset_control_deassert(core->reset);
+		if (ret) {
+			dev_err(core->dev, "module-reset deassert failed, ret = %d\n",
+				ret);
+			goto unroll_local_reset;
+		}
+	}
+
+	return 0;
+
+unroll_local_reset:
+	list_for_each_entry_continue(core, &cluster->cores, elem) {
+		if (reset_control_assert(core->reset))
+			dev_warn(core->dev, "local-reset assert back failed\n");
+	}
+	core = list_first_entry(&cluster->cores, struct k3_r5_core, elem);
+unroll_module_reset:
+	list_for_each_entry_from(core, &cluster->cores, elem) {
+		if (core->ti_sci->ops.dev_ops.put_device(core->ti_sci,
+							 core->ti_sci_id))
+			dev_warn(core->dev, "module-reset assert back failed\n");
+	}
+
+	return ret;
+}
+
+static inline int k3_r5_core_halt(struct k3_r5_core *core)
+{
+	return ti_sci_proc_set_control(core->tsp,
+				       PROC_BOOT_CTRL_FLAG_R5_CORE_HALT, 0);
+}
+
+static inline int k3_r5_core_run(struct k3_r5_core *core)
+{
+	return ti_sci_proc_set_control(core->tsp,
+				       0, PROC_BOOT_CTRL_FLAG_R5_CORE_HALT);
+}
+
+/*
+ * The R5F cores have controls for both a reset and a halt/run. The code
+ * execution from DDR requires the initial boot-strapping code to be run
+ * from the internal TCMs. This function is used to release the resets on
+ * applicable cores to allow loading into the TCMs. The .prepare() ops is
+ * invoked by remoteproc core before any firmware loading, and is followed
+ * by the .start() ops after loading to actually let the R5 cores run.
+ */
+static int k3_r5_rproc_prepare(struct rproc *rproc)
+{
+	struct k3_r5_rproc *kproc = rproc->priv;
+	struct k3_r5_cluster *cluster = kproc->cluster;
+	struct k3_r5_core *core = kproc->core;
+	struct device *dev = kproc->dev;
+	int ret;
+
+	ret = (cluster->mode == CLUSTER_MODE_LOCKSTEP) ?
+		k3_r5_lockstep_release(cluster) : k3_r5_split_release(core);
+	if (ret) {
+		dev_err(dev, "unable to enable cores for TCM loading, ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	/*
+	 * Zero out both TCMs unconditionally (access from v8 Arm core is not
+	 * affected by ATCM & BTCM enable configuration values) so that ECC
+	 * can be effective on all TCM addresses.
+	 */
+	dev_dbg(dev, "zeroing out ATCM memory\n");
+	memset(core->mem[0].cpu_addr, 0x00, core->mem[0].size);
+
+	dev_dbg(dev, "zeroing out BTCM memory\n");
+	memset(core->mem[1].cpu_addr, 0x00, core->mem[1].size);
+
+	return 0;
+}
+
+/*
+ * This function implements the .unprepare() ops and performs the complimentary
+ * operations to that of the .prepare() ops. The function is used to assert the
+ * resets on all applicable cores for the rproc device (depending on LockStep
+ * or Split mode). This completes the second portion of powering down the R5F
+ * cores. The cores themselves are only halted in the .stop() ops, and the
+ * .unprepare() ops is invoked by the remoteproc core after the remoteproc is
+ * stopped.
+ */
+static int k3_r5_rproc_unprepare(struct rproc *rproc)
+{
+	struct k3_r5_rproc *kproc = rproc->priv;
+	struct k3_r5_cluster *cluster = kproc->cluster;
+	struct k3_r5_core *core = kproc->core;
+	struct device *dev = kproc->dev;
+	int ret;
+
+	ret = (cluster->mode == CLUSTER_MODE_LOCKSTEP) ?
+		k3_r5_lockstep_reset(cluster) : k3_r5_split_reset(core);
+	if (ret)
+		dev_err(dev, "unable to disable cores, ret = %d\n", ret);
+
+	return ret;
+}
+
+/*
+ * The R5F start sequence includes two different operations
+ * 1. Configure the boot vector for R5F core(s)
+ * 2. Unhalt/Run the R5F core(s)
+ *
+ * The sequence is different between LockStep and Split modes. The LockStep
+ * mode requires the boot vector to be configured only for Core0, and then
+ * unhalt both the cores to start the execution - Core1 needs to be unhalted
+ * first followed by Core0. The Split-mode requires that Core0 to be maintained
+ * always in a higher power state that Core1 (implying Core1 needs to be started
+ * always only after Core0 is started).
+ */
+static int k3_r5_rproc_start(struct rproc *rproc)
+{
+	struct k3_r5_rproc *kproc = rproc->priv;
+	struct k3_r5_cluster *cluster = kproc->cluster;
+	struct mbox_client *client = &kproc->client;
+	struct device *dev = kproc->dev;
+	struct k3_r5_core *core;
+	u32 boot_addr;
+	int ret;
+
+	client->dev = dev;
+	client->tx_done = NULL;
+	client->rx_callback = k3_r5_rproc_mbox_callback;
+	client->tx_block = false;
+	client->knows_txdone = false;
+
+	kproc->mbox = mbox_request_channel(client, 0);
+	if (IS_ERR(kproc->mbox)) {
+		ret = -EBUSY;
+		dev_err(dev, "mbox_request_channel failed: %ld\n",
+			PTR_ERR(kproc->mbox));
+		return ret;
+	}
+
+	/*
+	 * Ping the remote processor, this is only for sanity-sake for now;
+	 * there is no functional effect whatsoever.
+	 *
+	 * Note that the reply will _not_ arrive immediately: this message
+	 * will wait in the mailbox fifo until the remote processor is booted.
+	 */
+	ret = mbox_send_message(kproc->mbox, (void *)RP_MBOX_ECHO_REQUEST);
+	if (ret < 0) {
+		dev_err(dev, "mbox_send_message failed: %d\n", ret);
+		goto put_mbox;
+	}
+
+	boot_addr = rproc->bootaddr;
+	/* TODO: add boot_addr sanity checking */
+	dev_dbg(dev, "booting R5F core using boot addr = 0x%x\n", boot_addr);
+
+	/* boot vector need not be programmed for Core1 in LockStep mode */
+	core = kproc->core;
+	ret = ti_sci_proc_set_config(core->tsp, boot_addr, 0, 0);
+	if (ret)
+		goto put_mbox;
+
+	/* unhalt/run all applicable cores */
+	if (cluster->mode == CLUSTER_MODE_LOCKSTEP) {
+		list_for_each_entry_reverse(core, &cluster->cores, elem) {
+			ret = k3_r5_core_run(core);
+			if (ret)
+				goto unroll_core_run;
+		}
+	} else {
+		ret = k3_r5_core_run(core);
+		if (ret)
+			goto put_mbox;
+	}
+
+	return 0;
+
+unroll_core_run:
+	list_for_each_entry_continue(core, &cluster->cores, elem) {
+		if (k3_r5_core_halt(core))
+			dev_warn(core->dev, "core halt back failed\n");
+	}
+put_mbox:
+	mbox_free_channel(kproc->mbox);
+	return ret;
+}
+
+/*
+ * The R5F stop function includes the following operations
+ * 1. Halt R5F core(s)
+ *
+ * The sequence is different between LockStep and Split modes, and the order
+ * of cores the operations are performed are also in general reverse to that
+ * of the start function. The LockStep mode requires each operation to be
+ * performed first on Core0 followed by Core1. The Split-mode requires that
+ * Core0 to be maintained always in a higher power state that Core1 (implying
+ * Core1 needs to be stopped first before Core0).
+ *
+ * Note that the R5F halt operation in general is not effective when the R5F
+ * core is running, but is needed to make sure the core won't run after
+ * deasserting the reset the subsequent time. The asserting of reset can
+ * be done here, but is preferred to be done in the .unprepare() ops - this
+ * maintains the symmetric behavior between the .start(), .stop(), .prepare()
+ * and .unprepare() ops, and also balances them well between sysfs 'state'
+ * flow and device bind/unbind or module removal.
+ */
+static int k3_r5_rproc_stop(struct rproc *rproc)
+{
+	struct k3_r5_rproc *kproc = rproc->priv;
+	struct k3_r5_cluster *cluster = kproc->cluster;
+	struct k3_r5_core *core = kproc->core;
+	int ret;
+
+	/* halt all applicable cores */
+	if (cluster->mode == CLUSTER_MODE_LOCKSTEP) {
+		list_for_each_entry(core, &cluster->cores, elem) {
+			ret = k3_r5_core_halt(core);
+			if (ret) {
+				core = list_prev_entry(core, elem);
+				goto unroll_core_halt;
+			}
+		}
+	} else {
+		ret = k3_r5_core_halt(core);
+		if (ret)
+			goto out;
+	}
+
+	mbox_free_channel(kproc->mbox);
+
+	return 0;
+
+unroll_core_halt:
+	list_for_each_entry_from_reverse(core, &cluster->cores, elem) {
+		if (k3_r5_core_run(core))
+			dev_warn(core->dev, "core run back failed\n");
+	}
+out:
+	return ret;
+}
+
+/*
+ * Internal Memory translation helper
+ *
+ * Custom function implementing the rproc .da_to_va ops to provide address
+ * translation (device address to kernel virtual address) for internal RAMs
+ * present in a DSP or IPU device). The translated addresses can be used
+ * either by the remoteproc core for loading, or by any rpmsg bus drivers.
+ */
+static void *k3_r5_rproc_da_to_va(struct rproc *rproc, u64 da, size_t len)
+{
+	struct k3_r5_rproc *kproc = rproc->priv;
+	struct k3_r5_core *core = kproc->core;
+	void __iomem *va = NULL;
+	phys_addr_t bus_addr;
+	u32 dev_addr, offset;
+	size_t size;
+	int i;
+
+	if (len == 0)
+		return NULL;
+
+	/* handle both R5 and SoC views of ATCM and BTCM */
+	for (i = 0; i < core->num_mems; i++) {
+		bus_addr = core->mem[i].bus_addr;
+		dev_addr = core->mem[i].dev_addr;
+		size = core->mem[i].size;
+
+		/* handle R5-view addresses of TCMs */
+		if (da >= dev_addr && ((da + len) <= (dev_addr + size))) {
+			offset = da - dev_addr;
+			va = core->mem[i].cpu_addr + offset;
+			return (__force void *)va;
+		}
+
+		/* handle SoC-view addresses of TCMs */
+		if (da >= bus_addr && ((da + len) <= (bus_addr + size))) {
+			offset = da - bus_addr;
+			va = core->mem[i].cpu_addr + offset;
+			return (__force void *)va;
+		}
+	}
+
+	/* handle any SRAM regions using SoC-view addresses */
+	for (i = 0; i < core->num_sram; i++) {
+		dev_addr = core->sram[i].dev_addr;
+		size = core->sram[i].size;
+
+		if (da >= dev_addr && ((da + len) <= (dev_addr + size))) {
+			offset = da - dev_addr;
+			va = core->sram[i].cpu_addr + offset;
+			return (__force void *)va;
+		}
+	}
+
+	/* handle static DDR reserved memory regions */
+	for (i = 0; i < kproc->num_rmems; i++) {
+		dev_addr = kproc->rmem[i].dev_addr;
+		size = kproc->rmem[i].size;
+
+		if (da >= dev_addr && ((da + len) <= (dev_addr + size))) {
+			offset = da - dev_addr;
+			va = kproc->rmem[i].cpu_addr + offset;
+			return (__force void *)va;
+		}
+	}
+
+	return NULL;
+}
+
+static const struct rproc_ops k3_r5_rproc_ops = {
+	.prepare	= k3_r5_rproc_prepare,
+	.unprepare	= k3_r5_rproc_unprepare,
+	.start		= k3_r5_rproc_start,
+	.stop		= k3_r5_rproc_stop,
+	.kick		= k3_r5_rproc_kick,
+	.da_to_va	= k3_r5_rproc_da_to_va,
+};
+
+/*
+ * Internal R5F Core configuration
+ *
+ * Each R5FSS has a cluster-level setting for configuring the processor
+ * subsystem either in a safety/fault-tolerant LockStep mode or a performance
+ * oriented Split mode. Each R5F core has a number of settings to either
+ * enable/disable each of the TCMs, control which TCM appears at the R5F core's
+ * address 0x0. These settings need to be configured before the resets for the
+ * corresponding core are released. These settings are all protected and managed
+ * by the System Processor.
+ *
+ * This function is used to pre-configure these settings for each R5F core, and
+ * the configuration is all done through various ti_sci_proc functions that
+ * communicate with the System Processor. The function also ensures that both
+ * the cores are halted before the .prepare() step.
+ *
+ * The function is called from k3_r5_cluster_rproc_init() and is invoked either
+ * once (in LockStep mode) or twice (in Split mode). Support for LockStep-mode
+ * is dictated by an eFUSE register bit, and the config settings retrieved from
+ * DT are adjusted accordingly as per the permitted cluster mode. All cluster
+ * level settings like Cluster mode and TEINIT (exception handling state
+ * dictating ARM or Thumb mode) can only be set and retrieved using Core0.
+ *
+ * The function behavior is different based on the cluster mode. The R5F cores
+ * are configured independently as per their individual settings in Split mode.
+ * They are identically configured in LockStep mode using the primary Core0
+ * settings. However, some individual settings cannot be set in LockStep mode.
+ * This is overcome by switching to Split-mode initially and then programming
+ * both the cores with the same settings, before reconfiguing again for
+ * LockStep mode.
+ */
+static int k3_r5_rproc_configure(struct k3_r5_rproc *kproc)
+{
+	struct k3_r5_cluster *cluster = kproc->cluster;
+	struct device *dev = kproc->dev;
+	struct k3_r5_core *core0, *core, *temp;
+	u32 ctrl = 0, cfg = 0, stat = 0;
+	u32 set_cfg = 0, clr_cfg = 0;
+	u64 boot_vec = 0;
+	bool lockstep_en;
+	int ret;
+
+	core0 = list_first_entry(&cluster->cores, struct k3_r5_core, elem);
+	core = (cluster->mode == CLUSTER_MODE_LOCKSTEP) ? core0 : kproc->core;
+
+	ret = ti_sci_proc_get_status(core->tsp, &boot_vec, &cfg, &ctrl,
+				     &stat);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(dev, "boot_vector = 0x%llx, cfg = 0x%x ctrl = 0x%x stat = 0x%x\n",
+		boot_vec, cfg, ctrl, stat);
+
+	lockstep_en = !!(stat & PROC_BOOT_STATUS_FLAG_R5_LOCKSTEP_PERMITTED);
+	if (!lockstep_en && cluster->mode == CLUSTER_MODE_LOCKSTEP) {
+		dev_err(cluster->dev, "lockstep mode not permitted, force configuring for split-mode\n");
+		cluster->mode = CLUSTER_MODE_SPLIT;
+	}
+
+	/* always enable ARM mode and set boot vector to 0 */
+	boot_vec = 0x0;
+	if (core == core0) {
+		clr_cfg = PROC_BOOT_CFG_FLAG_R5_TEINIT;
+		/*
+		 * LockStep configuration bit is Read-only on Split-mode _only_
+		 * devices and system firmware will NACK any requests with the
+		 * bit configured, so program it only on permitted devices
+		 */
+		if (lockstep_en)
+			clr_cfg |= PROC_BOOT_CFG_FLAG_R5_LOCKSTEP;
+	}
+
+	if (core->atcm_enable)
+		set_cfg |= PROC_BOOT_CFG_FLAG_R5_ATCM_EN;
+	else
+		clr_cfg |= PROC_BOOT_CFG_FLAG_R5_ATCM_EN;
+
+	if (core->btcm_enable)
+		set_cfg |= PROC_BOOT_CFG_FLAG_R5_BTCM_EN;
+	else
+		clr_cfg |= PROC_BOOT_CFG_FLAG_R5_BTCM_EN;
+
+	if (core->loczrama)
+		set_cfg |= PROC_BOOT_CFG_FLAG_R5_TCM_RSTBASE;
+	else
+		clr_cfg |= PROC_BOOT_CFG_FLAG_R5_TCM_RSTBASE;
+
+	if (cluster->mode == CLUSTER_MODE_LOCKSTEP) {
+		/*
+		 * work around system firmware limitations to make sure both
+		 * cores are programmed symmetrically in LockStep. LockStep
+		 * and TEINIT config is only allowed with Core0.
+		 */
+		list_for_each_entry(temp, &cluster->cores, elem) {
+			ret = k3_r5_core_halt(temp);
+			if (ret)
+				goto out;
+
+			if (temp != core) {
+				clr_cfg &= ~PROC_BOOT_CFG_FLAG_R5_LOCKSTEP;
+				clr_cfg &= ~PROC_BOOT_CFG_FLAG_R5_TEINIT;
+			}
+			ret = ti_sci_proc_set_config(temp->tsp, boot_vec,
+						     set_cfg, clr_cfg);
+			if (ret)
+				goto out;
+		}
+
+		set_cfg = PROC_BOOT_CFG_FLAG_R5_LOCKSTEP;
+		clr_cfg = 0;
+		ret = ti_sci_proc_set_config(core->tsp, boot_vec,
+					     set_cfg, clr_cfg);
+	} else {
+		ret = k3_r5_core_halt(core);
+		if (ret)
+			goto out;
+
+		ret = ti_sci_proc_set_config(core->tsp, boot_vec,
+					     set_cfg, clr_cfg);
+	}
+
+out:
+	return ret;
+}
+
+static int k3_r5_reserved_mem_init(struct k3_r5_rproc *kproc)
+{
+	struct device *dev = kproc->dev;
+	struct device_node *np = dev_of_node(dev);
+	struct device_node *rmem_np;
+	struct reserved_mem *rmem;
+	int num_rmems;
+	int ret, i;
+
+	num_rmems = of_property_count_elems_of_size(np, "memory-region",
+						    sizeof(phandle));
+	if (num_rmems <= 0) {
+		dev_err(dev, "device does not have reserved memory regions, ret = %d\n",
+			num_rmems);
+		return -EINVAL;
+	}
+	if (num_rmems < 2) {
+		dev_err(dev, "device needs atleast two memory regions to be defined, num = %d\n",
+			num_rmems);
+		return -EINVAL;
+	}
+
+	/* use reserved memory region 0 for vring DMA allocations */
+	ret = of_reserved_mem_device_init_by_idx(dev, np, 0);
+	if (ret) {
+		dev_err(dev, "device cannot initialize DMA pool, ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	num_rmems--;
+	kproc->rmem = kcalloc(num_rmems, sizeof(*kproc->rmem), GFP_KERNEL);
+	if (!kproc->rmem) {
+		ret = -ENOMEM;
+		goto release_rmem;
+	}
+
+	/* use remaining reserved memory regions for static carveouts */
+	for (i = 0; i < num_rmems; i++) {
+		rmem_np = of_parse_phandle(np, "memory-region", i + 1);
+		if (!rmem_np) {
+			ret = -EINVAL;
+			goto unmap_rmem;
+		}
+
+		rmem = of_reserved_mem_lookup(rmem_np);
+		if (!rmem) {
+			of_node_put(rmem_np);
+			ret = -EINVAL;
+			goto unmap_rmem;
+		}
+		of_node_put(rmem_np);
+
+		kproc->rmem[i].bus_addr = rmem->base;
+		/*
+		 * R5Fs do not have an MMU, but have a Region Address Translator
+		 * (RAT) module that provides a fixed entry translation between
+		 * the 32-bit processor addresses to 64-bit bus addresses. The
+		 * RAT is programmable only by the R5F cores. Support for RAT
+		 * is currently not supported, so 64-bit address regions are not
+		 * supported. The absence of MMUs implies that the R5F device
+		 * addresses/supported memory regions are restricted to 32-bit
+		 * bus addresses, and are identical
+		 */
+		kproc->rmem[i].dev_addr = (u32)rmem->base;
+		kproc->rmem[i].size = rmem->size;
+		kproc->rmem[i].cpu_addr = ioremap_wc(rmem->base, rmem->size);
+		if (!kproc->rmem[i].cpu_addr) {
+			dev_err(dev, "failed to map reserved memory#%d at %pa of size %pa\n",
+				i + 1, &rmem->base, &rmem->size);
+			ret = -ENOMEM;
+			goto unmap_rmem;
+		}
+
+		dev_dbg(dev, "reserved memory%d: bus addr %pa size 0x%zx va %pK da 0x%x\n",
+			i + 1, &kproc->rmem[i].bus_addr,
+			kproc->rmem[i].size, kproc->rmem[i].cpu_addr,
+			kproc->rmem[i].dev_addr);
+	}
+	kproc->num_rmems = num_rmems;
+
+	return 0;
+
+unmap_rmem:
+	for (i--; i >= 0; i--)
+		iounmap(kproc->rmem[i].cpu_addr);
+	kfree(kproc->rmem);
+release_rmem:
+	of_reserved_mem_device_release(dev);
+	return ret;
+}
+
+static void k3_r5_reserved_mem_exit(struct k3_r5_rproc *kproc)
+{
+	int i;
+
+	for (i = 0; i < kproc->num_rmems; i++)
+		iounmap(kproc->rmem[i].cpu_addr);
+	kfree(kproc->rmem);
+
+	of_reserved_mem_device_release(kproc->dev);
+}
+
+static int k3_r5_cluster_rproc_init(struct platform_device *pdev)
+{
+	struct k3_r5_cluster *cluster = platform_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
+	struct k3_r5_rproc *kproc;
+	struct k3_r5_core *core, *core1;
+	struct device *cdev;
+	const char *fw_name;
+	struct rproc *rproc;
+	int ret;
+
+	core1 = list_last_entry(&cluster->cores, struct k3_r5_core, elem);
+	list_for_each_entry(core, &cluster->cores, elem) {
+		cdev = core->dev;
+		ret = rproc_of_parse_firmware(cdev, 0, &fw_name);
+		if (ret) {
+			dev_err(dev, "failed to parse firmware-name property, ret = %d\n",
+				ret);
+			goto out;
+		}
+
+		rproc = rproc_alloc(cdev, dev_name(cdev), &k3_r5_rproc_ops,
+				    fw_name, sizeof(*kproc));
+		if (!rproc) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		/* K3 R5s have a Region Address Translator (RAT) but no MMU */
+		rproc->has_iommu = false;
+		/* error recovery is not supported at present */
+		rproc->recovery_disabled = true;
+
+		kproc = rproc->priv;
+		kproc->cluster = cluster;
+		kproc->core = core;
+		kproc->dev = cdev;
+		kproc->rproc = rproc;
+		core->rproc = rproc;
+
+		ret = k3_r5_rproc_configure(kproc);
+		if (ret) {
+			dev_err(dev, "initial configure failed, ret = %d\n",
+				ret);
+			goto err_config;
+		}
+
+		ret = k3_r5_reserved_mem_init(kproc);
+		if (ret) {
+			dev_err(dev, "reserved memory init failed, ret = %d\n",
+				ret);
+			goto err_config;
+		}
+
+		ret = rproc_add(rproc);
+		if (ret) {
+			dev_err(dev, "rproc_add failed, ret = %d\n", ret);
+			goto err_add;
+		}
+
+		/* create only one rproc in lockstep mode */
+		if (cluster->mode == CLUSTER_MODE_LOCKSTEP)
+			break;
+	}
+
+	return 0;
+
+err_split:
+	rproc_del(rproc);
+err_add:
+	k3_r5_reserved_mem_exit(kproc);
+err_config:
+	rproc_free(rproc);
+	core->rproc = NULL;
+out:
+	/* undo core0 upon any failures on core1 in split-mode */
+	if (cluster->mode == CLUSTER_MODE_SPLIT && core == core1) {
+		core = list_prev_entry(core, elem);
+		rproc = core->rproc;
+		kproc = rproc->priv;
+		goto err_split;
+	}
+	return ret;
+}
+
+static int k3_r5_cluster_rproc_exit(struct platform_device *pdev)
+{
+	struct k3_r5_cluster *cluster = platform_get_drvdata(pdev);
+	struct k3_r5_rproc *kproc;
+	struct k3_r5_core *core;
+	struct rproc *rproc;
+
+	/*
+	 * lockstep mode has only one rproc associated with first core, whereas
+	 * split-mode has two rprocs associated with each core, and requires
+	 * that core1 be powered down first
+	 */
+	core = (cluster->mode == CLUSTER_MODE_LOCKSTEP) ?
+		list_first_entry(&cluster->cores, struct k3_r5_core, elem) :
+		list_last_entry(&cluster->cores, struct k3_r5_core, elem);
+
+	list_for_each_entry_from_reverse(core, &cluster->cores, elem) {
+		rproc = core->rproc;
+		kproc = rproc->priv;
+
+		rproc_del(rproc);
+
+		k3_r5_reserved_mem_exit(kproc);
+
+		rproc_free(rproc);
+		core->rproc = NULL;
+	}
+
+	return 0;
+}
+
+static int k3_r5_core_of_get_internal_memories(struct platform_device *pdev,
+					       struct k3_r5_core *core)
+{
+	static const char * const mem_names[] = {"atcm", "btcm"};
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	int num_mems;
+	int i;
+
+	num_mems = ARRAY_SIZE(mem_names);
+	core->mem = devm_kcalloc(dev, num_mems, sizeof(*core->mem), GFP_KERNEL);
+	if (!core->mem)
+		return -ENOMEM;
+
+	for (i = 0; i < num_mems; i++) {
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						   mem_names[i]);
+		if (!res) {
+			dev_err(dev, "found no memory resource for %s\n",
+				mem_names[i]);
+			return -EINVAL;
+		}
+		if (!devm_request_mem_region(dev, res->start,
+					     resource_size(res),
+					     dev_name(dev))) {
+			dev_err(dev, "could not request %s region for resource\n",
+				mem_names[i]);
+			return -EBUSY;
+		}
+
+		/*
+		 * TCMs are designed in general to support RAM-like backing
+		 * memories. So, map these as Normal Non-Cached memories. This
+		 * also avoids/fixes any potential alignment faults due to
+		 * unaligned data accesses when using memcpy() or memset()
+		 * functions (normally seen with device type memory).
+		 */
+		core->mem[i].cpu_addr = devm_ioremap_wc(dev, res->start,
+							resource_size(res));
+		if (!core->mem[i].cpu_addr) {
+			dev_err(dev, "failed to map %s memory\n", mem_names[i]);
+			return -ENOMEM;
+		}
+		core->mem[i].bus_addr = res->start;
+
+		/*
+		 * TODO:
+		 * The R5F cores can place ATCM & BTCM anywhere in its address
+		 * based on the corresponding Region Registers in the System
+		 * Control coprocessor. For now, place ATCM and BTCM at
+		 * addresses 0 and 0x41010000 (same as the bus address on AM65x
+		 * SoCs) based on loczrama setting
+		 */
+		if (!strcmp(mem_names[i], "atcm")) {
+			core->mem[i].dev_addr = core->loczrama ?
+							0 : K3_R5_TCM_DEV_ADDR;
+		} else {
+			core->mem[i].dev_addr = core->loczrama ?
+							K3_R5_TCM_DEV_ADDR : 0;
+		}
+		core->mem[i].size = resource_size(res);
+
+		dev_dbg(dev, "memory %5s: bus addr %pa size 0x%zx va %pK da 0x%x\n",
+			mem_names[i], &core->mem[i].bus_addr,
+			core->mem[i].size, core->mem[i].cpu_addr,
+			core->mem[i].dev_addr);
+	}
+	core->num_mems = num_mems;
+
+	return 0;
+}
+
+static int k3_r5_core_of_get_sram_memories(struct platform_device *pdev,
+					   struct k3_r5_core *core)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct device *dev = &pdev->dev;
+	struct device_node *sram_np;
+	struct resource res;
+	int num_sram;
+	int i, ret;
+
+	num_sram = of_property_count_elems_of_size(np, "sram", sizeof(phandle));
+	if (num_sram <= 0) {
+		dev_dbg(dev, "device does not use reserved on-chip memories, num_sram = %d\n",
+			num_sram);
+		return 0;
+	}
+
+	core->sram = devm_kcalloc(dev, num_sram, sizeof(*core->sram), GFP_KERNEL);
+	if (!core->sram)
+		return -ENOMEM;
+
+	for (i = 0; i < num_sram; i++) {
+		sram_np = of_parse_phandle(np, "sram", i);
+		if (!sram_np)
+			return -EINVAL;
+
+		if (!of_device_is_available(sram_np)) {
+			of_node_put(sram_np);
+			return -EINVAL;
+		}
+
+		ret = of_address_to_resource(sram_np, 0, &res);
+		of_node_put(sram_np);
+		if (ret)
+			return -EINVAL;
+
+		core->sram[i].bus_addr = res.start;
+		core->sram[i].dev_addr = res.start;
+		core->sram[i].size = resource_size(&res);
+		core->sram[i].cpu_addr = devm_ioremap_wc(dev, res.start,
+							 resource_size(&res));
+		if (!core->sram[i].cpu_addr) {
+			dev_err(dev, "failed to parse and map sram%d memory at %pad\n",
+				i, &res.start);
+			return -ENOMEM;
+		}
+
+		dev_dbg(dev, "memory sram%d: bus addr %pa size 0x%zx va %pK da 0x%x\n",
+			i, &core->sram[i].bus_addr,
+			core->sram[i].size, core->sram[i].cpu_addr,
+			core->sram[i].dev_addr);
+	}
+	core->num_sram = num_sram;
+
+	return 0;
+}
+
+static
+struct ti_sci_proc *k3_r5_core_of_get_tsp(struct device *dev,
+					  const struct ti_sci_handle *sci)
+{
+	struct ti_sci_proc *tsp;
+	u32 temp[2];
+	int ret;
+
+	ret = of_property_read_u32_array(dev_of_node(dev), "ti,sci-proc-ids",
+					 temp, 2);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	tsp = devm_kzalloc(dev, sizeof(*tsp), GFP_KERNEL);
+	if (!tsp)
+		return ERR_PTR(-ENOMEM);
+
+	tsp->dev = dev;
+	tsp->sci = sci;
+	tsp->ops = &sci->ops.proc_ops;
+	tsp->proc_id = temp[0];
+	tsp->host_id = temp[1];
+
+	return tsp;
+}
+
+static int k3_r5_core_of_init(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev_of_node(dev);
+	struct k3_r5_core *core;
+	int ret;
+
+	if (!devres_open_group(dev, k3_r5_core_of_init, GFP_KERNEL))
+		return -ENOMEM;
+
+	core = devm_kzalloc(dev, sizeof(*core), GFP_KERNEL);
+	if (!core) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	core->dev = dev;
+	/*
+	 * Use SoC Power-on-Reset values as default if no DT properties are
+	 * used to dictate the TCM configurations
+	 */
+	core->atcm_enable = 0;
+	core->btcm_enable = 1;
+	core->loczrama = 1;
+
+	ret = of_property_read_u32(np, "ti,atcm-enable", &core->atcm_enable);
+	if (ret < 0 && ret != -EINVAL) {
+		dev_err(dev, "invalid format for ti,atcm-enable, ret = %d\n",
+			ret);
+		goto err;
+	}
+
+	ret = of_property_read_u32(np, "ti,btcm-enable", &core->btcm_enable);
+	if (ret < 0 && ret != -EINVAL) {
+		dev_err(dev, "invalid format for ti,btcm-enable, ret = %d\n",
+			ret);
+		goto err;
+	}
+
+	ret = of_property_read_u32(np, "ti,loczrama", &core->loczrama);
+	if (ret < 0 && ret != -EINVAL) {
+		dev_err(dev, "invalid format for ti,loczrama, ret = %d\n", ret);
+		goto err;
+	}
+
+	core->ti_sci = devm_ti_sci_get_by_phandle(dev, "ti,sci");
+	if (IS_ERR(core->ti_sci)) {
+		ret = PTR_ERR(core->ti_sci);
+		if (ret != -EPROBE_DEFER) {
+			dev_err(dev, "failed to get ti-sci handle, ret = %d\n",
+				ret);
+		}
+		core->ti_sci = NULL;
+		goto err;
+	}
+
+	ret = of_property_read_u32(np, "ti,sci-dev-id", &core->ti_sci_id);
+	if (ret) {
+		dev_err(dev, "missing 'ti,sci-dev-id' property\n");
+		goto err;
+	}
+
+	core->reset = devm_reset_control_get_exclusive(dev, NULL);
+	if (IS_ERR_OR_NULL(core->reset)) {
+		ret = PTR_ERR_OR_ZERO(core->reset);
+		if (!ret)
+			ret = -ENODEV;
+		if (ret != -EPROBE_DEFER) {
+			dev_err(dev, "failed to get reset handle, ret = %d\n",
+				ret);
+		}
+		goto err;
+	}
+
+	core->tsp = k3_r5_core_of_get_tsp(dev, core->ti_sci);
+	if (IS_ERR(core->tsp)) {
+		dev_err(dev, "failed to construct ti-sci proc control, ret = %d\n",
+			ret);
+		ret = PTR_ERR(core->tsp);
+		goto err;
+	}
+
+	ret = k3_r5_core_of_get_internal_memories(pdev, core);
+	if (ret) {
+		dev_err(dev, "failed to get internal memories, ret = %d\n",
+			ret);
+		goto err;
+	}
+
+	ret = k3_r5_core_of_get_sram_memories(pdev, core);
+	if (ret) {
+		dev_err(dev, "failed to get sram memories, ret = %d\n", ret);
+		goto err;
+	}
+
+	ret = ti_sci_proc_request(core->tsp);
+	if (ret < 0) {
+		dev_err(dev, "ti_sci_proc_request failed, ret = %d\n", ret);
+		goto err;
+	}
+
+	platform_set_drvdata(pdev, core);
+	devres_close_group(dev, k3_r5_core_of_init);
+
+	return 0;
+
+err:
+	devres_release_group(dev, k3_r5_core_of_init);
+	return ret;
+}
+
+/*
+ * free the resources explicitly since driver model is not being used
+ * for the child R5F devices
+ */
+static void k3_r5_core_of_exit(struct platform_device *pdev)
+{
+	struct k3_r5_core *core = platform_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	ret = ti_sci_proc_release(core->tsp);
+	if (ret)
+		dev_err(dev, "failed to release proc, ret = %d\n", ret);
+
+	platform_set_drvdata(pdev, NULL);
+	devres_release_group(dev, k3_r5_core_of_init);
+}
+
+static void k3_r5_cluster_of_exit(struct platform_device *pdev)
+{
+	struct k3_r5_cluster *cluster = platform_get_drvdata(pdev);
+	struct platform_device *cpdev;
+	struct k3_r5_core *core, *temp;
+
+	list_for_each_entry_safe_reverse(core, temp, &cluster->cores, elem) {
+		list_del(&core->elem);
+		cpdev = to_platform_device(core->dev);
+		k3_r5_core_of_exit(cpdev);
+	}
+}
+
+static int k3_r5_cluster_of_init(struct platform_device *pdev)
+{
+	struct k3_r5_cluster *cluster = platform_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev_of_node(dev);
+	struct platform_device *cpdev;
+	struct device_node *child;
+	struct k3_r5_core *core;
+	int ret;
+
+	for_each_available_child_of_node(np, child) {
+		cpdev = of_find_device_by_node(child);
+		if (!cpdev) {
+			ret = -ENODEV;
+			dev_err(dev, "could not get R5 core platform device\n");
+			goto fail;
+		}
+
+		ret = k3_r5_core_of_init(cpdev);
+		if (ret) {
+			dev_err(dev, "k3_r5_core_of_init failed, ret = %d\n",
+				ret);
+			put_device(&cpdev->dev);
+			goto fail;
+		}
+
+		core = platform_get_drvdata(cpdev);
+		put_device(&cpdev->dev);
+		list_add_tail(&core->elem, &cluster->cores);
+	}
+
+	return 0;
+
+fail:
+	k3_r5_cluster_of_exit(pdev);
+	return ret;
+}
+
+static int k3_r5_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev_of_node(dev);
+	struct k3_r5_cluster *cluster;
+	int ret;
+	int num_cores;
+
+	cluster = devm_kzalloc(dev, sizeof(*cluster), GFP_KERNEL);
+	if (!cluster)
+		return -ENOMEM;
+
+	cluster->dev = dev;
+	cluster->mode = CLUSTER_MODE_LOCKSTEP;
+	INIT_LIST_HEAD(&cluster->cores);
+
+	ret = of_property_read_u32(np, "ti,cluster-mode", &cluster->mode);
+	if (ret < 0 && ret != -EINVAL) {
+		dev_err(dev, "invalid format for ti,cluster-mode, ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	num_cores = of_get_available_child_count(np);
+	if (num_cores != 2) {
+		dev_err(dev, "MCU cluster requires both R5F cores to be enabled, num_cores = %d\n",
+			num_cores);
+		return -ENODEV;
+	}
+
+	platform_set_drvdata(pdev, cluster);
+
+	ret = devm_of_platform_populate(dev);
+	if (ret) {
+		dev_err(dev, "devm_of_platform_populate failed, ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	ret = k3_r5_cluster_of_init(pdev);
+	if (ret) {
+		dev_err(dev, "k3_r5_cluster_of_init failed, ret = %d\n", ret);
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(dev,
+				       (void(*)(void *))k3_r5_cluster_of_exit,
+				       pdev);
+	if (ret)
+		return ret;
+
+	ret = k3_r5_cluster_rproc_init(pdev);
+	if (ret) {
+		dev_err(dev, "k3_r5_cluster_rproc_init failed, ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(dev,
+				       (void(*)(void *))k3_r5_cluster_rproc_exit,
+				       pdev);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct of_device_id k3_r5_of_match[] = {
+	{ .compatible = "ti,am654-r5fss", },
+	{ .compatible = "ti,j721e-r5fss", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, k3_r5_of_match);
+
+static struct platform_driver k3_r5_rproc_driver = {
+	.probe = k3_r5_probe,
+	.driver = {
+		.name = "k3_r5_rproc",
+		.of_match_table = k3_r5_of_match,
+	},
+};
+
+module_platform_driver(k3_r5_rproc_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("TI K3 R5F remote processor driver");
+MODULE_AUTHOR("Suman Anna <s-anna@ti.com>");
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index 2fa68bf5aa4f..3fa3ba6498e8 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -442,16 +442,16 @@ enum rproc_crash_type {
 
 /**
  * enum rproc_dump_mechanism - Coredump options for core
- * @RPROC_COREDUMP_DEFAULT:	Copy dump to separate buffer and carry on with
+ * @RPROC_COREDUMP_DISABLED:	Don't perform any dump
+ * @RPROC_COREDUMP_ENABLED:	Copy dump to separate buffer and carry on with
 				recovery
  * @RPROC_COREDUMP_INLINE:	Read segments directly from device memory. Stall
 				recovery until all segments are read
- * @RPROC_COREDUMP_DISABLED:	Don't perform any dump
  */
 enum rproc_dump_mechanism {
-	RPROC_COREDUMP_DEFAULT,
-	RPROC_COREDUMP_INLINE,
 	RPROC_COREDUMP_DISABLED,
+	RPROC_COREDUMP_ENABLED,
+	RPROC_COREDUMP_INLINE,
 };
 
 /**