Merge branch 'rpmsg-ti-linux-4.19.y-intg' of git://git.ti.com/rpmsg/rpmsg into ti-linux-4.19.y

TI-Feature: rpmsg
TI-Tree: git://git.ti.com/rpmsg/rpmsg.git
TI-Branch: rpmsg-ti-linux-4.19.y-intg

* 'rpmsg-ti-linux-4.19.y-intg' of git://git.ti.com/rpmsg/rpmsg: (27 commits)
  remoteproc/k3-dsp: add support for IPC-only mode for all K3 DSPs
  ti_config_fragments: v8_rpmsg: Enable K3 DSP remoteproc support
  arm64: dts: ti: k3-j721e: Add an alias for C71x rproc node
  arm64: dts: ti: k3-j721e-som-p0: Add DDR carveout memory nodes for C71x DSP
  arm64: dts: ti: k3-j721e-main: Add C71x DSP node
  remoteproc/k3-dsp: add support for C71x DSPs
  remoteproc: add support for a new 64-bit trace version
  remoteproc: introduce version element into resource type field
  remoteproc: add 64-bit ELF loader support code
  dt-bindings: remoteproc: k3-dsp: Update bindings for C71x DSPs
  arm64: dts: ti: k3-j721e: Add aliases for C66x rproc nodes
  arm64: dts: ti: k3-j721e-som-p0: Add DDR carveout memory nodes for C66 DSPs
  arm64: dts: ti: k3-j721e-main: Add C66x DSP nodes
  remoteproc/k3-dsp: add a remoteproc driver of K3 C66x DSPs
  dt-bindings: remoteproc: Add bindings for DSP C66x clusters on TI K3 SoCs
  remoteproc/k3-r5: add support for IPC-only mode for all R5Fs on J721E SoCs
  ti_config_fragments: v8_rpmsg: Enable rpmsg client sample
  TEMP: samples/rpmsg: add compatible to support J7ES PDK firmware images
  arm64: dts: ti: k3-j721e-som-p0: Reserve memory for IPC between RTOS cores
  arm64: dts: ti: k3-j721e-som-p0: Add DDR carveout memory nodes for MAIN R5Fs
  ...

Signed-off-by: LCPD Auto Merger <lcpd_integration@list.ti.com>

Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.txt

@@ -0,0 +1,179 @@
+TI K3 DSP devices
+=================
+
+The TI K3 family of SoCs usually have one or more TI DSP Core sub-systems that
+are used to offload some of the processor-intensive tasks or algorithms, for
+achieving various system level goals.
+
+These processor sub-systems usually contain additional sub-modules like L1
+and/or L2 caches/SRAMs, an Interrupt Controller, an external memory controller,
+a dedicated local power/sleep controller etc. The DSP processor cores in the
+K3 SoCs is usually either a TMS320C66x CorePac processor or a TMS320C71x CorePac
+processor.
+
+DSP Device Node:
+================
+Each DSP Core sub-system is represented as a single DT node. Each node has a
+number of required or optional properties that enable the OS running on the
+host processor (Arm CorePac) to perform the device management of the remote
+processor and to communicate with the remote processor.
+
+Required properties:
+--------------------
+The following are the mandatory properties:
+
+- compatible:		Should be one of the following,
+			    "ti,j721e-c66-dsp" for C66x DSPs on K3 J721E SoCs
+			    "ti,j721e-c71-dsp" for C71x DSPs on K3 J721E SoCs
+
+- reg:			Should contain an entry for each value in 'reg-names'.
+			Each entry should have the memory region's start address
+			and the size of the region, the representation matching
+			the parent node's '#address-cells' and '#size-cells' values.
+
+- reg-names:		Should contain strings with the following names, each
+			representing a specific internal memory region (if
+			present), and should be defined in this order,
+			     "l2sram", "l1pram", "l1dram"
+			NOTE: C71x DSPs do not have a "l1pram" memory.
+
+- ti,sci:		Should be a phandle to the TI-SCI System Controller node
+
+- ti,sci-dev-id:	Should contain the TI-SCI device id corresponding to the
+			DSP Core. Please refer to the corresponding System
+			Controller documentation for valid values for the DSP
+			cores.
+
+- ti,sci-proc-ids:	Should contain 2 integer values. The first cell should
+			contain the TI-SCI processor id for the DSP core device
+			and the second cell should contain the TI-SCI host id to
+			which the processor control ownership should be
+			transferred to.
+
+- resets:		Should contain the phandle to the reset controller node
+			managing the resets for this device, and a reset
+			specifier. Please refer to the following reset bindings
+			for the reset argument specifier,
+			Documentation/devicetree/bindings/reset/ti,sci-reset.txt
+
+- power-domains:	Should contain a phandle to a PM domain provider node
+			and an args specifier containing the DSP device id
+			value. This property is as per the binding,
+			Documentation/devicetree/bindings/soc/ti/sci-pm-domain.txt
+
+- mboxes:		OMAP Mailbox specifier denoting the sub-mailbox, to be
+			used for communication with the remote processor. The
+			specifier format is as per the bindings,
+			Documentation/devicetree/bindings/mailbox/omap-mailbox.txt
+			This property should match with the sub-mailbox node
+			used in the firmware image.
+
+- memory-region:	phandle to the reserved memory nodes to be associated
+			with the remoteproc device. There should be atleast two
+			reserved memory nodes defined - the first one would be
+			used for dynamic DMA allocations like vrings and vring
+			buffers, and the remaining ones used for the firmware
+			image sections. The reserved memory nodes should be
+			carveout nodes, and should be defined as per the
+			bindings in
+			Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
+
+Optional properties:
+--------------------
+
+- sram:			pHandle to a reserved on-chip SRAM region. The region
+			should be defined as a child node of the respective
+			SRAM node, and should be defined as per the generic
+			bindings in,
+			Documentation/devicetree/bindings/misc/sram.txt
+
+
+Example:
+---------
+
+1. J721E SoC
+	/* J721E remoteproc alias */
+	aliases {
+		rproc0 = &mcu_r5fss0_core0;
+		rproc1 = &mcu_r5fss0_core1;
+		rproc2 = &main_r5fss0_core0;
+		rproc3 = &main_r5fss0_core1;
+		rproc4 = &main_r5fss1_core0;
+		rproc5 = &main_r5fss1_core1;
+		rproc6 = &c66_0;
+		rproc7 = &c66_1;
+		rproc8 = &c71_0;
+	};
+
+	/* DSP Carveout reserved memory nodes */
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		c66_0_dma_memory_region: c66-dma-memory@a6000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa6000000 0x00 0x100000>;
+			no-map;
+		};
+
+		c66_0_memory_region: c66-memory@a6100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa6100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		c71_0_dma_memory_region: c71-dma-memory@a8000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa8000000 0x00 0x100000>;
+			no-map;
+		};
+
+		c71_0_memory_region: c71-memory@a8100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa8100000 0x00 0xf00000>;
+			no-map;
+		};
+	};
+
+	cbass_main: interconnect@100000 {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges = <0x00 0x64800000 0x00 0x64800000 0x00 0x00800000>, /* C71_0 */
+			 <0x4d 0x80800000 0x4d 0x80800000 0x00 0x00800000>, /* C66_0 */
+			 <0x4d 0x81800000 0x4d 0x81800000 0x00 0x00800000>; /* C66_1 */
+
+		/* J721E C66_0 DSP node */
+		c66_0: dsp@4d80800000 {
+			compatible = "ti,j721e-c66-dsp";
+			reg = <0x4d 0x80800000 0x00 0x00048000>,
+			      <0x4d 0x80e00000 0x00 0x00008000>,
+			      <0x4d 0x80f00000 0x00 0x00008000>;
+			reg-names = "l2sram", "l1pram", "l1dram";
+			ti,sci = <&dmsc>;
+			ti,sci-dev-id = <142>;
+			ti,sci-proc-ids = <0x03 0xFF>;
+			resets = <&k3_reset 142 1>;
+			power-domains = <&k3_pds 142 TI_SCI_PD_EXCLUSIVE>;
+			memory-region = <&c66_0_dma_memory_region>,
+					<&c66_0_memory_region>;
+			mboxes = <&mailbox0_cluster3 &mbox_c66_0>;
+		};
+
+		/* J721E C71_0 DSP node */
+		c71_0: dsp@64800000 {
+			compatible = "ti,j721e-c71-dsp";
+			reg = <0x00 0x64800000 0x00 0x00080000>,
+			      <0x00 0x64e00000 0x00 0x0000c000>;
+			reg-names = "l2sram", "l1dram";
+			ti,sci = <&dmsc>;
+			ti,sci-dev-id = <15>;
+			ti,sci-proc-ids = <0x30 0xFF>;
+			resets = <&k3_reset 15 1>;
+			power-domains = <&k3_pds 15 TI_SCI_PD_EXCLUSIVE>;
+			memory-region = <&c71_0_dma_memory_region>,
+					<&c71_0_memory_region>;
+			mboxes = <&mailbox0_cluster4 &mbox_c71_0>;
+		};
+	};

Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.txt

@@ -23,6 +23,8 @@ The following are the mandatory properties:
 - compatible:		Should be one of the following,
 			    "ti,am654-r5fss" for R5F clusters/subsystems on
 			                       K3 AM65x SoCs
+			    "ti,j721e-r5fss" for R5F clusters/subsystems on
+			                       K3 J721E SoCs
 - power-domains:	Should contain a phandle to a PM domain provider node
 			and an args specifier containing the R5FSS device id
 			value. This property is as per the binding,
@@ -53,6 +55,7 @@ The following are the mandatory properties:
 
 - compatible:		Should be one of the following,
 			    "ti,am654-r5f" for the R5F cores in K3 AM65x SoCs
+			    "ti,j721e-r5f" for the R5F cores in K3 J721E SOCs
 - reg:			Should contain an entry for each value in 'reg-names'.
 			Each entry should have the memory region's start address
 			and the size of the region, the representation matching
@@ -76,7 +79,7 @@ The following are the mandatory properties:
 			specifier. Please refer to the following reset bindings
 			for the reset argument specifier,
 			Documentation/devicetree/bindings/reset/ti,sci-reset.txt
-			    for AM65x SoCs
+			    for AM65x and J721E SoCs
 
 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

arch/arm64/boot/dts/ti/k3-j721e-main.dtsi

@@ -1316,4 +1316,125 @@
 		dma-coherent;
 		no-1-8-v;
 	};
+
+	main_r5fss0: r5fss@5c00000 {
+		compatible = "ti,j721e-r5fss";
+		lockstep-mode = <0>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x5c00000 0x00 0x5c00000 0x20000>,
+			 <0x5d00000 0x00 0x5d00000 0x20000>;
+		power-domains = <&k3_pds 243 TI_SCI_PD_EXCLUSIVE>;
+
+		main_r5fss0_core0: r5f@5c00000 {
+			compatible = "ti,j721e-r5f";
+			reg = <0x5c00000 0x00008000>,
+			      <0x5c10000 0x00008000>;
+			reg-names = "atcm", "btcm";
+			ti,sci = <&dmsc>;
+			ti,sci-dev-id = <245>;
+			ti,sci-proc-ids = <0x06 0xFF>;
+			resets = <&k3_reset 245 1>;
+			atcm-enable = <1>;
+			btcm-enable = <1>;
+			loczrama = <1>;
+			mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core0>;
+		};
+
+		main_r5fss0_core1: r5f@5d00000 {
+			compatible = "ti,j721e-r5f";
+			reg = <0x5d00000 0x00008000>,
+			      <0x5d10000 0x00008000>;
+			reg-names = "atcm", "btcm";
+			ti,sci = <&dmsc>;
+			ti,sci-dev-id = <246>;
+			ti,sci-proc-ids = <0x07 0xFF>;
+			resets = <&k3_reset 246 1>;
+			atcm-enable = <1>;
+			btcm-enable = <1>;
+			loczrama = <1>;
+			mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core1>;
+		};
+	};
+
+	main_r5fss1: r5fss@5e00000 {
+		compatible = "ti,j721e-r5fss";
+		lockstep-mode = <1>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x5e00000 0x00 0x5e00000 0x20000>,
+			 <0x5f00000 0x00 0x5f00000 0x20000>;
+		power-domains = <&k3_pds 244 TI_SCI_PD_EXCLUSIVE>;
+
+		main_r5fss1_core0: r5f@5e00000 {
+			compatible = "ti,j721e-r5f";
+			reg = <0x5e00000 0x00008000>,
+			      <0x5e10000 0x00008000>;
+			reg-names = "atcm", "btcm";
+			ti,sci = <&dmsc>;
+			ti,sci-dev-id = <247>;
+			ti,sci-proc-ids = <0x08 0xFF>;
+			resets = <&k3_reset 247 1>;
+			atcm-enable = <1>;
+			btcm-enable = <1>;
+			loczrama = <1>;
+			mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core0>;
+		};
+
+		main_r5fss1_core1: r5f@5f00000 {
+			compatible = "ti,j721e-r5f";
+			reg = <0x5f00000 0x00008000>,
+			      <0x5f10000 0x00008000>;
+			reg-names = "atcm", "btcm";
+			ti,sci = <&dmsc>;
+			ti,sci-dev-id = <248>;
+			ti,sci-proc-ids = <0x09 0xFF>;
+			resets = <&k3_reset 248 1>;
+			atcm-enable = <1>;
+			btcm-enable = <1>;
+			loczrama = <1>;
+			mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core1>;
+		};
+	};
+
+	c66_0: dsp@4d80800000 {
+		compatible = "ti,j721e-c66-dsp";
+		reg = <0x4d 0x80800000 0x00 0x00048000>,
+		      <0x4d 0x80e00000 0x00 0x00008000>,
+		      <0x4d 0x80f00000 0x00 0x00008000>;
+		reg-names = "l2sram", "l1pram", "l1dram";
+		ti,sci = <&dmsc>;
+		ti,sci-dev-id = <142>;
+		ti,sci-proc-ids = <0x03 0xFF>;
+		resets = <&k3_reset 142 1>;
+		/*power-domains = <&k3_pds 142 TI_SCI_PD_EXCLUSIVE>;*/
+		mboxes = <&mailbox0_cluster3 &mbox_c66_0>;
+	};
+
+	c66_1: dsp@4d81800000 {
+		compatible = "ti,j721e-c66-dsp";
+		reg = <0x4d 0x81800000 0x00 0x00048000>,
+		      <0x4d 0x81e00000 0x00 0x00008000>,
+		      <0x4d 0x81f00000 0x00 0x00008000>;
+		reg-names = "l2sram", "l1pram", "l1dram";
+		ti,sci = <&dmsc>;
+		ti,sci-dev-id = <143>;
+		ti,sci-proc-ids = <0x04 0xFF>;
+		resets = <&k3_reset 143 1>;
+		/*power-domains = <&k3_pds 143 TI_SCI_PD_EXCLUSIVE>;*/
+		mboxes = <&mailbox0_cluster3 &mbox_c66_1>;
+	};
+
+	c71_0: dsp@64800000 {
+		compatible = "ti,j721e-c71-dsp";
+		reg = <0x00 0x64800000 0x00 0x00080000>,
+		      <0x00 0x64e00000 0x00 0x0000c000>;
+		reg-names = "l2sram", "l1dram";
+		ti,sci = <&dmsc>;
+		ti,sci-dev-id = <15>;
+		ti,sci-proc-ids = <0x30 0xFF>;
+		resets = <&k3_reset 15 1>;
+		/*power-domains = <&k3_pds 15 TI_SCI_PD_EXCLUSIVE>;*/
+		mboxes = <&mailbox0_cluster4 &mbox_c71_0>;
+	};
 };

arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi

@@ -415,4 +415,44 @@
 			#size-cells = <0>;
 		};
 	};
+
+	mcu_r5fss0: r5fss@41000000 {
+		compatible = "ti,j721e-r5fss";
+		lockstep-mode = <1>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x41000000 0x00 0x41000000 0x20000>,
+			 <0x41400000 0x00 0x41400000 0x20000>;
+		power-domains = <&k3_pds 249 TI_SCI_PD_EXCLUSIVE>;
+
+		mcu_r5fss0_core0: r5f@41000000 {
+			compatible = "ti,j721e-r5f";
+			reg = <0x41000000 0x00008000>,
+			      <0x41010000 0x00008000>;
+			reg-names = "atcm", "btcm";
+			ti,sci = <&dmsc>;
+			ti,sci-dev-id = <250>;
+			ti,sci-proc-ids = <0x01 0xFF>;
+			resets = <&k3_reset 250 1>;
+			atcm-enable = <1>;
+			btcm-enable = <1>;
+			loczrama = <1>;
+			mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core0>;
+		};
+
+		mcu_r5fss0_core1: r5f@41400000 {
+			compatible = "ti,j721e-r5f";
+			reg = <0x41400000 0x00008000>,
+			      <0x41410000 0x00008000>;
+			reg-names = "atcm", "btcm";
+			ti,sci = <&dmsc>;
+			ti,sci-dev-id = <251>;
+			ti,sci-proc-ids = <0x02 0xFF>;
+			resets = <&k3_reset 251 1>;
+			atcm-enable = <1>;
+			btcm-enable = <1>;
+			loczrama = <1>;
+			mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core1>;
+		};
+	};
 };

arch/arm64/boot/dts/ti/k3-j721e-som-p0.dtsi

@@ -25,6 +25,120 @@
 			alignment = <0x1000>;
 			no-map;
 		};
+
+		mcu_r5fss0_core0_dma_memory_region: r5f-dma-memory@a0000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa0000000 0x00 0x100000>;
+			no-map;
+		};
+
+		mcu_r5fss0_core0_memory_region: r5f-memory@a0100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa0100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		mcu_r5fss0_core1_dma_memory_region: r5f-dma-memory@a1000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa1000000 0x00 0x100000>;
+			no-map;
+		};
+
+		mcu_r5fss0_core1_memory_region: r5f-memory@a1100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa1100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		main_r5fss0_core0_dma_memory_region: r5f-dma-memory@a2000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa2000000 0x00 0x100000>;
+			no-map;
+		};
+
+		main_r5fss0_core0_memory_region: r5f-memory@a2100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa2100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		main_r5fss0_core1_dma_memory_region: r5f-dma-memory@a3000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa3000000 0x00 0x100000>;
+			no-map;
+		};
+
+		main_r5fss0_core1_memory_region: r5f-memory@a3100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa3100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		main_r5fss1_core0_dma_memory_region: r5f-dma-memory@a4000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa4000000 0x00 0x100000>;
+			no-map;
+		};
+
+		main_r5fss1_core0_memory_region: r5f-memory@a4100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa4100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		main_r5fss1_core1_dma_memory_region: r5f-dma-memory@a5000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa5000000 0x00 0x100000>;
+			no-map;
+		};
+
+		main_r5fss1_core1_memory_region: r5f-memory@a5100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa5100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		c66_1_dma_memory_region: c66-dma-memory@a6000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa6000000 0x00 0x100000>;
+			no-map;
+		};
+
+		c66_0_memory_region: c66-memory@a6100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa6100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		c66_0_dma_memory_region: c66-dma-memory@a7000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa7000000 0x00 0x100000>;
+			no-map;
+		};
+
+		c66_1_memory_region: c66-memory@a7100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa7100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		c71_0_dma_memory_region: c71-dma-memory@a8000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa8000000 0x00 0x100000>;
+			no-map;
+		};
+
+		c71_0_memory_region: c71-memory@a8100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa8100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		rtos_ipc_memory_region: ipc-memories@aa000000 {
+			reg = <0x00 0xaa000000 0x00 0x01c00000>;
+			alignment = <0x1000>;
+			no-map;
+		};
 	};
 };
 
@@ -111,3 +225,48 @@
 		#size-cells = <1>;
 	};
 };
+
+&mcu_r5fss0_core0 {
+	memory-region = <&mcu_r5fss0_core0_dma_memory_region>,
+			<&mcu_r5fss0_core0_memory_region>;
+};
+
+&mcu_r5fss0_core1 {
+	memory-region = <&mcu_r5fss0_core1_dma_memory_region>,
+			<&mcu_r5fss0_core1_memory_region>;
+};
+
+&main_r5fss0_core0 {
+	memory-region = <&main_r5fss0_core0_dma_memory_region>,
+			<&main_r5fss0_core0_memory_region>;
+};
+
+&main_r5fss0_core1 {
+	memory-region = <&main_r5fss0_core1_dma_memory_region>,
+			<&main_r5fss0_core1_memory_region>;
+};
+
+&main_r5fss1_core0 {
+	memory-region = <&main_r5fss1_core0_dma_memory_region>,
+			<&main_r5fss1_core0_memory_region>;
+};
+
+&main_r5fss1_core1 {
+	memory-region = <&main_r5fss1_core1_dma_memory_region>,
+			<&main_r5fss1_core1_memory_region>;
+};
+
+&c66_0 {
+	memory-region = <&c66_0_dma_memory_region>,
+			<&c66_0_memory_region>;
+};
+
+&c66_1 {
+	memory-region = <&c66_1_dma_memory_region>,
+			<&c66_1_memory_region>;
+};
+
+&c71_0 {
+	memory-region = <&c71_0_dma_memory_region>,
+			<&c71_0_memory_region>;
+};

arch/arm64/boot/dts/ti/k3-j721e.dtsi

@@ -33,6 +33,15 @@
 		serial11 = &main_uart9;
 		spi0 = &ospi0;
 		spi1 = &ospi1;
+		rproc0 = &mcu_r5fss0_core0;
+		rproc1 = &mcu_r5fss0_core1;
+		rproc2 = &main_r5fss0_core0;
+		rproc3 = &main_r5fss0_core1;
+		rproc4 = &main_r5fss1_core0;
+		rproc5 = &main_r5fss1_core1;
+		rproc6 = &c66_0;
+		rproc7 = &c66_1;
+		rproc8 = &c71_0;
 	};
 
 	chosen { };

drivers/remoteproc/Kconfig

@@ -223,6 +223,22 @@ config TI_K3_R5_REMOTEPROC
 	  It's safe to say N here if you're not interested in utilizing
 	  a slave processor
 
+config TI_K3_DSP_REMOTEPROC
+	tristate "TI K3 DSP remoteproc support"
+	depends on ARCH_K3
+	select MAILBOX
+	select OMAP2PLUS_MBOX
+	help
+	  Say y here to support TI's C66x and C71x DSP remote processor
+	  subsystems on various TI K3 family of SoCs through the remote
+	  processor framework.
+
+	  You want to say m here in order to offload some processing
+	  tasks to these processors.
+
+	  It's safe to say N here if you're not interested in utilizing
+	  the DSP slave processors.
+
 endif # REMOTEPROC
 
 endmenu

drivers/remoteproc/Makefile

@@ -9,6 +9,7 @@ remoteproc-y				+= remoteproc_debugfs.o
 remoteproc-y				+= remoteproc_sysfs.o
 remoteproc-y				+= remoteproc_virtio.o
 remoteproc-y				+= remoteproc_elf_loader.o
+remoteproc-y				+= remoteproc_elf64_loader.o
 obj-$(CONFIG_IMX_REMOTEPROC)		+= imx_rproc.o
 obj-$(CONFIG_OMAP_REMOTEPROC)		+= omap_remoteproc.o
 obj-$(CONFIG_WKUP_M3_RPROC)		+= wkup_m3_rproc.o
@@ -27,3 +28,4 @@ qcom_wcnss_pil-y			+= qcom_wcnss_iris.o
 obj-$(CONFIG_ST_REMOTEPROC)		+= st_remoteproc.o
 obj-$(CONFIG_ST_SLIM_REMOTEPROC)	+= st_slim_rproc.o
 obj-$(CONFIG_TI_K3_R5_REMOTEPROC)	+= ti_k3_r5_remoteproc.o
+obj-$(CONFIG_TI_K3_DSP_REMOTEPROC)	+= ti_k3_dsp_remoteproc.o

drivers/remoteproc/remoteproc_core.c

@@ -54,7 +54,7 @@ static LIST_HEAD(rproc_list);
 typedef int (*rproc_handle_resources_t)(struct rproc *rproc,
 				struct resource_table *table, int len);
 typedef int (*rproc_handle_resource_t)(struct rproc *rproc,
-				 void *, int offset, int avail);
+				 void *, int offset, int avail, u16 ver);
 
 /* Unique indices for remoteproc devices */
 static DEFINE_IDA(rproc_dev_index);
@@ -382,6 +382,7 @@ static void rproc_vdev_do_stop(struct rproc_subdev *subdev, bool crashed)
  * @rproc: the remote processor
  * @rsc: the vring resource descriptor
  * @avail: size of available data (for sanity checking the image)
+ * @ver: version number of the resource type
  *
  * This resource entry requests the host to statically register a virtio
  * device (vdev), and setup everything needed to support it. It contains
@@ -405,7 +406,7 @@ static void rproc_vdev_do_stop(struct rproc_subdev *subdev, bool crashed)
  * Returns 0 on success, or an appropriate error code otherwise
  */
 static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc,
-			     int offset, int avail)
+			     int offset, int avail, u16 ver)
 {
 	struct device *dev = &rproc->dev;
 	struct rproc_vdev *rvdev;
@@ -598,6 +599,7 @@ copy_and_exit:
  * @rproc: the remote processor
  * @rsc: the trace resource descriptor
  * @avail: size of available data (for sanity checking the image)
+ * @ver: version number of the resource type
  *
  * In case the remote processor dumps trace logs into memory,
  * export it via debugfs.
@@ -609,27 +611,51 @@ copy_and_exit:
  *
  * Returns 0 on success, or an appropriate error code otherwise
  */
-static int rproc_handle_trace(struct rproc *rproc, struct fw_rsc_trace *rsc,
-			      int offset, int avail)
+static int rproc_handle_trace(struct rproc *rproc, void *rsc,
+			      int offset, int avail, u16 ver)
 {
 	struct rproc_mem_entry *trace;
 	struct device *dev = &rproc->dev;
+	struct fw_rsc_trace *rsc1;
+	struct fw_rsc_trace2 *rsc2;
 	void *ptr;
 	char name[15];
+	size_t rsc_size;
+	u32 reserved;
+	u64 da;
+	u32 len;
+
+	if (!ver) {
+		rsc1 = (struct fw_rsc_trace *)rsc;
+		rsc_size = sizeof(*rsc1);
+		reserved = rsc1->reserved;
+		da = rsc1->da;
+		len = rsc1->len;
+	} else if (ver == 1) {
+		rsc2 = (struct fw_rsc_trace2 *)rsc;
+		rsc_size = sizeof(*rsc2);
+		reserved = rsc2->reserved;
+		da = rsc2->da;
+		len = rsc2->len;
+	} else {
+		dev_err(dev, "unsupported trace rsc version %d\n", ver);
+		return -EINVAL;
+	}
 
-	if (sizeof(*rsc) > avail) {
+	if (rsc_size > avail) {
 		dev_err(dev, "trace rsc is truncated\n");
 		return -EINVAL;
 	}
 
 	/* make sure reserved bytes are zeroes */
-	if (rsc->reserved) {
-		dev_err(dev, "trace rsc has non zero reserved bytes\n");
+	if (reserved) {
+		dev_err(dev, "trace rsc has non zero reserved bytes, value = 0x%x\n",
+			reserved);
 		return -EINVAL;
 	}
 
 	/* what's the kernel address of this resource ? */
-	ptr = rproc_da_to_va(rproc, rsc->da, rsc->len, RPROC_FLAGS_NONE);
+	ptr = rproc_da_to_va(rproc, da, len, RPROC_FLAGS_NONE);
 	if (!ptr) {
 		dev_err(dev, "erroneous trace resource entry\n");
 		return -EINVAL;
@@ -640,7 +666,7 @@ static int rproc_handle_trace(struct rproc *rproc, struct fw_rsc_trace *rsc,
 		return -ENOMEM;
 
 	/* set the trace buffer dma properties */
-	trace->len = rsc->len;
+	trace->len = len;
 	trace->va = ptr;
 
 	/* make sure snprintf always null terminates, even if truncating */
@@ -658,8 +684,8 @@ static int rproc_handle_trace(struct rproc *rproc, struct fw_rsc_trace *rsc,
 
 	rproc->num_traces++;
 
-	dev_dbg(dev, "%s added: va %pK, da 0x%x, len 0x%x\n",
-		name, ptr, rsc->da, rsc->len);
+	dev_dbg(dev, "%s added: va %pK, da 0x%llx, len 0x%x\n",
+		name, ptr, da, len);
 
 	return 0;
 }
@@ -669,6 +695,7 @@ static int rproc_handle_trace(struct rproc *rproc, struct fw_rsc_trace *rsc,
  * @rproc: remote processor handle
  * @rsc: the devmem resource entry
  * @avail: size of available data (for sanity checking the image)
+ * @ver: version number of the resource type
  *
  * Remote processors commonly need to access certain on-chip peripherals.
  *
@@ -690,7 +717,7 @@ static int rproc_handle_trace(struct rproc *rproc, struct fw_rsc_trace *rsc,
  * are outside those ranges.
  */
 static int rproc_handle_devmem(struct rproc *rproc, struct fw_rsc_devmem *rsc,
-			       int offset, int avail)
+			       int offset, int avail, u16 ver)
 {
 	struct rproc_mem_entry *mapping;
 	struct device *dev = &rproc->dev;
@@ -748,6 +775,7 @@ out:
  * @rproc: rproc handle
  * @rsc: the resource entry
  * @avail: size of available data (for image validation)
+ * @ver: version number of the resource type
  *
  * This function will handle firmware requests for allocation of physically
  * contiguous memory regions.
@@ -763,7 +791,7 @@ out:
  */
 static int rproc_handle_carveout(struct rproc *rproc,
 				 struct fw_rsc_carveout *rsc,
-				 int offset, int avail)
+				 int offset, int avail, u16 ver)
 {
 	struct rproc_mem_entry *carveout, *mapping;
 	struct device *dev = &rproc->dev;
@@ -960,18 +988,19 @@ static int rproc_handle_resources(struct rproc *rproc,
 			return -EINVAL;
 		}
 
-		dev_dbg(dev, "rsc: type %d\n", hdr->type);
+		dev_dbg(dev, "rsc: type %d vers %d\n", hdr->st.t, hdr->st.v);
 
-		if (hdr->type >= RSC_LAST) {
-			dev_warn(dev, "unsupported resource %d\n", hdr->type);
+		if (hdr->st.t >= RSC_LAST) {
+			dev_warn(dev, "unsupported resource %d\n", hdr->st.t);
 			continue;
 		}
 
-		handler = handlers[hdr->type];
+		handler = handlers[hdr->st.t];
 		if (!handler)
 			continue;
 
-		ret = handler(rproc, rsc, offset + sizeof(*hdr), avail);
+		ret = handler(rproc, rsc, offset + sizeof(*hdr), avail,
+			      hdr->st.v);
 		if (ret)
 			break;
 	}

drivers/remoteproc/remoteproc_debugfs.c

@@ -164,7 +164,8 @@ static int rproc_rsc_table_show(struct seq_file *seq, void *p)
 	struct resource_table *table = rproc->table_ptr;
 	struct fw_rsc_carveout *c;
 	struct fw_rsc_devmem *d;
-	struct fw_rsc_trace *t;
+	struct fw_rsc_trace *t1;
+	struct fw_rsc_trace2 *t2;
 	struct fw_rsc_vdev *v;
 	struct fw_rsc_vendor *vr;
 	int i, j;
@@ -178,11 +179,13 @@ static int rproc_rsc_table_show(struct seq_file *seq, void *p)
 		int offset = table->offset[i];
 		struct fw_rsc_hdr *hdr = (void *)table + offset;
 		void *rsc = (void *)hdr + sizeof(*hdr);
+		u16 ver = hdr->st.v;
 
-		switch (hdr->type) {
+		switch (hdr->st.t) {
 		case RSC_CARVEOUT:
 			c = rsc;
-			seq_printf(seq, "Entry %d is of type %s\n", i, types[hdr->type]);
+			seq_printf(seq, "Entry %d is of type %s\n",
+				   i, types[hdr->st.t]);
 			seq_printf(seq, "  Device Address 0x%x\n", c->da);
 			seq_printf(seq, "  Physical Address 0x%x\n", c->pa);
 			seq_printf(seq, "  Length 0x%x Bytes\n", c->len);
@@ -192,7 +195,8 @@ static int rproc_rsc_table_show(struct seq_file *seq, void *p)
 			break;
 		case RSC_DEVMEM:
 			d = rsc;
-			seq_printf(seq, "Entry %d is of type %s\n", i, types[hdr->type]);
+			seq_printf(seq, "Entry %d is of type %s\n",
+				   i, types[hdr->st.t]);
 			seq_printf(seq, "  Device Address 0x%x\n", d->da);
 			seq_printf(seq, "  Physical Address 0x%x\n", d->pa);
 			seq_printf(seq, "  Length 0x%x Bytes\n", d->len);
@@ -201,17 +205,37 @@ static int rproc_rsc_table_show(struct seq_file *seq, void *p)
 			seq_printf(seq, "  Name %s\n\n", d->name);
 			break;
 		case RSC_TRACE:
-			t = rsc;
-			seq_printf(seq, "Entry %d is of type %s\n", i, types[hdr->type]);
-			seq_printf(seq, "  Device Address 0x%x\n", t->da);
-			seq_printf(seq, "  Length 0x%x Bytes\n", t->len);
-			seq_printf(seq, "  Reserved (should be zero) [%d]\n", t->reserved);
-			seq_printf(seq, "  Name %s\n\n", t->name);
+			if (ver == 0) {
+				t1 = rsc;
+				seq_printf(seq, "Entry %d is version %d of type %s\n",
+					   i, ver, types[hdr->st.t]);
+				seq_printf(seq, "  Device Address 0x%x\n",
+					   t1->da);
+				seq_printf(seq, "  Length 0x%x Bytes\n",
+					   t1->len);
+				seq_printf(seq, "  Reserved (should be zero) [%d]\n",
+					   t1->reserved);
+				seq_printf(seq, "  Name %s\n\n", t1->name);
+			} else if (ver == 1) {
+				t2 = rsc;
+				seq_printf(seq, "Entry %d is version %d of type %s\n",
+					   i, ver, types[hdr->st.t]);
+				seq_printf(seq, "  Device Address 0x%llx\n",
+					   t2->da);
+				seq_printf(seq, "  Length 0x%x Bytes\n",
+					   t2->len);
+				seq_printf(seq, "  Reserved (should be zero) [%d]\n",
+					   t2->reserved);
+				seq_printf(seq, "  Name %s\n\n", t2->name);
+			} else {
+				seq_printf(seq, "Entry %d is an unsupported version %d of type %s\n",
+					   i, ver, types[hdr->st.t]);
+			}
 			break;
 		case RSC_VDEV:
 			v = rsc;
-			seq_printf(seq, "Entry %d is of type %s\n", i, types[hdr->type]);
-
+			seq_printf(seq, "Entry %d is of type %s\n",
+				   i, types[hdr->st.t]);
 			seq_printf(seq, "  ID %d\n", v->id);
 			seq_printf(seq, "  Notify ID %d\n", v->notifyid);
 			seq_printf(seq, "  Device features 0x%x\n", v->dfeatures);
@@ -244,7 +268,7 @@ static int rproc_rsc_table_show(struct seq_file *seq, void *p)
 			break;
 		default:
 			seq_printf(seq, "Unknown resource type found: %d [hdr: %pK]\n",
-				   hdr->type, hdr);
+				   hdr->st.t, hdr);
 			break;
 		}
 	}

drivers/remoteproc/remoteproc_elf64_loader.c

@@ -0,0 +1,335 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Remote Processor Framework 64-bit Elf loader
+ * Code based on current remoteproc_elf_loader.c
+ *
+ * Copyright (C) 2018-2019 Texas Instruments, Inc.
+ *
+ * Suman Anna <s-anna@ti.com>
+ */
+
+#define pr_fmt(fmt)    "%s: " fmt, __func__
+
+#include <linux/elf.h>
+#include <linux/kernel.h>
+#include <linux/remoteproc.h>
+
+#include "remoteproc_internal.h"
+
+/**
+ * rproc_elf64_sanity_check() - Sanity Check ELF firmware image
+ * @rproc: the remote processor handle
+ * @fw: the ELF firmware image
+ *
+ * Make sure this fw image is sane.
+ */
+int rproc_elf64_sanity_check(struct rproc *rproc, const struct firmware *fw)
+{
+	const char *name = rproc->firmware;
+	struct device *dev = &rproc->dev;
+	struct elf64_hdr *ehdr;
+	char class;
+
+	if (!fw) {
+		dev_err(dev, "failed to load %s\n", name);
+		return -EINVAL;
+	}
+
+	if (fw->size < sizeof(struct elf64_hdr)) {
+		dev_err(dev, "Image is too small\n");
+		return -EINVAL;
+	}
+
+	ehdr = (struct elf64_hdr *)fw->data;
+
+	/* We only support ELF64 at this point */
+	class = ehdr->e_ident[EI_CLASS];
+	if (class != ELFCLASS64) {
+		dev_err(dev, "Unsupported class: %d\n", class);
+		return -EINVAL;
+	}
+
+	/* We assume the firmware has the same endianness as the host */
+# ifdef __LITTLE_ENDIAN
+	if (ehdr->e_ident[EI_DATA] != ELFDATA2LSB) {
+# else /* BIG ENDIAN */
+	if (ehdr->e_ident[EI_DATA] != ELFDATA2MSB) {
+# endif
+		dev_err(dev, "Unsupported firmware endianness\n");
+		return -EINVAL;
+	}
+
+	if (fw->size < ehdr->e_shoff + sizeof(struct elf64_shdr)) {
+		dev_err(dev, "Image is too small\n");
+		return -EINVAL;
+	}
+
+	if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG)) {
+		dev_err(dev, "Image is corrupted (bad magic)\n");
+		return -EINVAL;
+	}
+
+	if (ehdr->e_phnum == 0) {
+		dev_err(dev, "No loadable segments\n");
+		return -EINVAL;
+	}
+
+	if (ehdr->e_phoff > fw->size) {
+		dev_err(dev, "Firmware size is too small\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(rproc_elf64_sanity_check);
+
+/**
+ * rproc_elf64_get_boot_addr() - Get rproc's boot address.
+ * @rproc: the remote processor handle
+ * @fw: the ELF firmware image
+ *
+ * This function returns the entry point address of the ELF
+ * image.
+ *
+ * Note that the boot address is not a configurable property of all remote
+ * processors. Some will always boot at a specific hard-coded address.
+ *
+ * FIXME: The entry-point with 64-bit processors will be a 64-bit address,
+ * but return a 32-bit address for now to overload and reuse the current
+ * rproc_ops. This will scale as long as the higher 32-bit addresses are
+ * zero.
+ */
+u32 rproc_elf64_get_boot_addr(struct rproc *rproc, const struct firmware *fw)
+{
+	struct elf64_hdr *ehdr = (struct elf64_hdr *)fw->data;
+
+	WARN_ON(upper_32_bits(ehdr->e_entry) != 0);
+
+	return lower_32_bits(ehdr->e_entry);
+}
+EXPORT_SYMBOL(rproc_elf64_get_boot_addr);
+
+/**
+ * rproc_elf64_load_segments() - load firmware segments to memory
+ * @rproc: remote processor which will be booted using these fw segments
+ * @fw: the ELF firmware image
+ *
+ * This function loads the firmware segments to memory, where the remote
+ * processor expects them.
+ *
+ * Some remote processors will expect their code and data to be placed
+ * in specific device addresses, and can't have them dynamically assigned.
+ *
+ * We currently support only those kind of remote processors, and expect
+ * the program header's paddr member to contain those addresses. We then
+ * request the remoteproc core to perform a lookup either in its list of
+ * allocated (and mapped) physically contiguous "carveout" memory regions
+ * and/or registered pre-fixed physically contiguous reserved memory
+ * regions, and "translate" device address to kernel addresses, so we can
+ * copy the segments where they are expected.
+ */
+int rproc_elf64_load_segments(struct rproc *rproc, const struct firmware *fw)
+{
+	struct device *dev = &rproc->dev;
+	struct elf64_hdr *ehdr;
+	struct elf64_phdr *phdr;
+	int i, ret = 0;
+	const u8 *elf_data = fw->data;
+
+	ehdr = (struct elf64_hdr *)elf_data;
+	phdr = (struct elf64_phdr *)(elf_data + ehdr->e_phoff);
+
+	/* go through the available ELF segments */
+	for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
+		u32 da = phdr->p_paddr;
+		u32 memsz = phdr->p_memsz;
+		u32 filesz = phdr->p_filesz;
+		u32 offset = phdr->p_offset;
+		void *ptr;
+
+		if (phdr->p_type != PT_LOAD)
+			continue;
+
+		dev_dbg(dev, "phdr: type %d da 0x%x memsz 0x%x filesz 0x%x\n",
+			phdr->p_type, da, memsz, filesz);
+
+		if (filesz > memsz) {
+			dev_err(dev, "bad phdr filesz 0x%x memsz 0x%x\n",
+				filesz, memsz);
+			ret = -EINVAL;
+			break;
+		}
+
+		if (offset + filesz > fw->size) {
+			dev_err(dev, "truncated fw: need 0x%x avail 0x%zx\n",
+				offset + filesz, fw->size);
+			ret = -EINVAL;
+			break;
+		}
+
+		/*
+		 * grab the kernel address for this device address. Use
+		 * RPROC_FLAGS_NONE as current rproc_da_to_va() does not
+		 * scale for 64-bit flags, and there are no existing use-cases
+		 * requiring this
+		 */
+		ptr = rproc_da_to_va(rproc, da, memsz, RPROC_FLAGS_NONE);
+		if (!ptr) {
+			dev_err(dev, "bad phdr da 0x%x mem 0x%x\n", da, memsz);
+			ret = -EINVAL;
+			break;
+		}
+
+		/* put the segment where the remote processor expects it */
+		if (phdr->p_filesz)
+			memcpy(ptr, elf_data + phdr->p_offset, filesz);
+
+		/*
+		 * Zero out remaining memory for this segment.
+		 *
+		 * This isn't strictly required since dma_alloc_coherent already
+		 * did this for us. albeit harmless, we may consider removing
+		 * this.
+		 */
+		if (memsz > filesz)
+			memset(ptr + filesz, 0, memsz - filesz);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(rproc_elf64_load_segments);
+
+static struct elf64_shdr *
+find_table(struct device *dev, struct elf64_hdr *ehdr, size_t fw_size)
+{
+	struct elf64_shdr *shdr;
+	int i;
+	const char *name_table;
+	struct resource_table *table = NULL;
+	const u8 *elf_data = (void *)ehdr;
+
+	/* look for the resource table and handle it */
+	shdr = (struct elf64_shdr *)(elf_data + ehdr->e_shoff);
+	name_table = elf_data + shdr[ehdr->e_shstrndx].sh_offset;
+
+	for (i = 0; i < ehdr->e_shnum; i++, shdr++) {
+		u32 size = shdr->sh_size;
+		u32 offset = shdr->sh_offset;
+
+		if (strcmp(name_table + shdr->sh_name, ".resource_table"))
+			continue;
+
+		table = (struct resource_table *)(elf_data + offset);
+
+		/* make sure we have the entire table */
+		if (offset + size > fw_size || offset + size < size) {
+			dev_err(dev, "resource table truncated\n");
+			return NULL;
+		}
+
+		/* make sure table has at least the header */
+		if (sizeof(struct resource_table) > size) {
+			dev_err(dev, "header-less resource table\n");
+			return NULL;
+		}
+
+		/* we don't support any version beyond the first */
+		if (table->ver != 1) {
+			dev_err(dev, "unsupported fw ver: %d\n", table->ver);
+			return NULL;
+		}
+
+		/* make sure reserved bytes are zeroes */
+		if (table->reserved[0] || table->reserved[1]) {
+			dev_err(dev, "non zero reserved bytes\n");
+			return NULL;
+		}
+
+		/* make sure the offsets array isn't truncated */
+		if (table->num * sizeof(table->offset[0]) +
+				sizeof(struct resource_table) > size) {
+			dev_err(dev, "resource table incomplete\n");
+			return NULL;
+		}
+
+		return shdr;
+	}
+
+	return NULL;
+}
+
+/**
+ * rproc_elf64_load_rsc_table() - load the resource table
+ * @rproc: the rproc handle
+ * @fw: the ELF firmware image
+ *
+ * This function finds the resource table inside the remote processor's
+ * firmware, load it into the @cached_table and update @table_ptr.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int rproc_elf64_load_rsc_table(struct rproc *rproc, const struct firmware *fw)
+{
+	struct elf64_hdr *ehdr;
+	struct elf64_shdr *shdr;
+	struct device *dev = &rproc->dev;
+	struct resource_table *table = NULL;
+	const u8 *elf_data = fw->data;
+	size_t tablesz;
+
+	ehdr = (struct elf64_hdr *)elf_data;
+
+	shdr = find_table(dev, ehdr, fw->size);
+	if (!shdr)
+		return -EINVAL;
+
+	table = (struct resource_table *)(elf_data + shdr->sh_offset);
+	tablesz = shdr->sh_size;
+
+	/*
+	 * Create a copy of the resource table. When a virtio device starts
+	 * and calls vring_new_virtqueue() the address of the allocated vring
+	 * will be stored in the cached_table. Before the device is started,
+	 * cached_table will be copied into device memory.
+	 */
+	rproc->cached_table = kmemdup(table, tablesz, GFP_KERNEL);
+	if (!rproc->cached_table)
+		return -ENOMEM;
+
+	rproc->table_ptr = rproc->cached_table;
+	rproc->table_sz = tablesz;
+
+	return 0;
+}
+EXPORT_SYMBOL(rproc_elf64_load_rsc_table);
+
+/**
+ * rproc_elf64_find_loaded_rsc_table() - find the loaded resource table
+ * @rproc: the rproc handle
+ * @fw: the ELF firmware image
+ *
+ * This function finds the location of the loaded resource table. Don't
+ * call this function if the table wasn't loaded yet - it's a bug if you do.
+ *
+ * Returns the pointer to the resource table if it is found or NULL otherwise.
+ * If the table wasn't loaded yet the result is unspecified.
+ */
+struct resource_table *
+rproc_elf64_find_loaded_rsc_table(struct rproc *rproc,
+				  const struct firmware *fw)
+{
+	struct elf64_hdr *ehdr = (struct elf64_hdr *)fw->data;
+	struct elf64_shdr *shdr;
+
+	shdr = find_table(&rproc->dev, ehdr, fw->size);
+	if (!shdr)
+		return NULL;
+
+	/*
+	 * Use RPROC_FLAGS_NONE as current rproc_da_to_va() does not
+	 * scale for 64-bit flags, and no current use-cases require this
+	 */
+	return rproc_da_to_va(rproc, shdr->sh_addr, shdr->sh_size,
+			      RPROC_FLAGS_NONE);
+}
+EXPORT_SYMBOL(rproc_elf64_find_loaded_rsc_table);

drivers/remoteproc/remoteproc_internal.h

@@ -60,6 +60,14 @@ int rproc_elf_load_rsc_table(struct rproc *rproc, const struct firmware *fw);
 struct resource_table *rproc_elf_find_loaded_rsc_table(struct rproc *rproc,
 						       const struct firmware *fw);
 
+int rproc_elf64_sanity_check(struct rproc *rproc, const struct firmware *fw);
+u32 rproc_elf64_get_boot_addr(struct rproc *rproc, const struct firmware *fw);
+int rproc_elf64_load_segments(struct rproc *rproc, const struct firmware *fw);
+int rproc_elf64_load_rsc_table(struct rproc *rproc, const struct firmware *fw);
+struct resource_table *
+rproc_elf64_find_loaded_rsc_table(struct rproc *rproc,
+				  const struct firmware *fw);
+
 static inline
 int rproc_fw_sanity_check(struct rproc *rproc, const struct firmware *fw)
 {

drivers/remoteproc/ti_k3_dsp_remoteproc.c

@@ -0,0 +1,785 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * TI K3 DSP Remote Processor(s) driver
+ *
+ * Copyright (C) 2018-2019 Texas Instruments Incorporated - http://www.ti.com/
+ *	Suman Anna <s-anna@ti.com>
+ */
+
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/remoteproc.h>
+#include <linux/mailbox_client.h>
+#include <linux/omap-mailbox.h>
+#include <linux/reset.h>
+#include <linux/soc/ti/ti_sci_protocol.h>
+
+#include "omap_remoteproc.h"
+#include "remoteproc_internal.h"
+#include "ti_sci_proc.h"
+
+#define KEYSTONE_RPROC_LOCAL_ADDRESS_MASK	(SZ_16M - 1)
+
+/**
+ * struct k3_dsp_rproc_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 of the memory region from DSP view
+ * @size: Size of the memory region
+ */
+struct k3_dsp_rproc_mem {
+	void __iomem *cpu_addr;
+	phys_addr_t bus_addr;
+	u32 dev_addr;
+	size_t size;
+};
+
+/**
+ * struct k3_dsp_rproc - k3 DSP remote processor driver structure
+ * @dev: cached device pointer
+ * @rproc: remoteproc device handle
+ * @mem: internal memory regions data
+ * @num_mems: number of internal memory regions
+ * @rmem: reserved memory regions data
+ * @num_rmems: number of reserved memory regions
+ * @reset: reset control handle
+ * @tsp: TI-SCI processor control handle
+ * @ti_sci: TI-SCI handle
+ * @ti_sci_id: TI-SCI device identifier
+ * @mbox: mailbox channel handle
+ * @client: mailbox client to request the mailbox channel
+ * @ipc_only: flag to indicate IPC-only mode
+ */
+struct k3_dsp_rproc {
+	struct device *dev;
+	struct rproc *rproc;
+	struct k3_dsp_rproc_mem *mem;
+	int num_mems;
+	struct k3_dsp_rproc_mem *rmem;
+	int num_rmems;
+	struct reset_control *reset;
+	struct ti_sci_proc *tsp;
+	const struct ti_sci_handle *ti_sci;
+	u32 ti_sci_id;
+	struct mbox_chan *mbox;
+	struct mbox_client client;
+	unsigned int ipc_only : 1;
+};
+
+/**
+ * struct k3_dsp_rproc_dev_data - device data for the remote processor
+ * @device_name: device name of the remote processor
+ * @fw_name: firmware name to use
+ */
+struct k3_dsp_rproc_dev_data {
+	const char *device_name;
+	const char *fw_name;
+};
+
+/**
+ * k3_dsp_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_dsp_rproc_mbox_callback(struct mbox_client *client, void *data)
+{
+	struct k3_dsp_rproc *kproc = container_of(client, struct k3_dsp_rproc,
+						client);
+	struct device *dev = kproc->rproc->dev.parent;
+	const char *name = kproc->rproc->name;
+	u32 msg = to_omap_mbox_msg(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 DSP 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 the remote processor to notify about pending unprocessed messages.
+ * The vqid usage is not used and is inconsequential, as the kick is performed
+ * through a simulated GPIO (a bit in an IPC interrupt-triggering register),
+ * the remote processor is expected to process both its Tx and Rx virtqueues.
+ */
+static void k3_dsp_rproc_kick(struct rproc *rproc, int vqid)
+{
+	struct k3_dsp_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);
+}
+
+/* Put the DSP processor into reset */
+static int k3_dsp_rproc_reset(struct k3_dsp_rproc *kproc)
+{
+	struct device *dev = kproc->dev;
+	int ret;
+
+#ifdef LOCAL_RESET
+	ret = reset_control_assert(kproc->reset);
+	if (ret) {
+		dev_err(dev, "local-reset assert failed, ret = %d\n", ret);
+		return ret;
+	}
+#endif
+
+	ret = kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci,
+						    kproc->ti_sci_id);
+	if (ret) {
+		dev_err(dev, "module-reset assert failed, ret = %d\n", ret);
+#ifdef LOCAL_RESET
+		if (reset_control_deassert(kproc->reset))
+			dev_warn(dev, "local-reset deassert back failed\n");
+#endif
+	}
+
+	return ret;
+}
+
+/* Release the DSP processor from reset */
+static int k3_dsp_rproc_release(struct k3_dsp_rproc *kproc)
+{
+	struct device *dev = kproc->dev;
+	int ret;
+
+	ret = kproc->ti_sci->ops.dev_ops.get_device(kproc->ti_sci,
+						   kproc->ti_sci_id);
+	if (ret) {
+		dev_err(dev, "module-reset deassert failed, ret = %d\n", ret);
+		return ret;
+	}
+
+#ifdef LOCAL_RESET
+	ret = reset_control_deassert(kproc->reset);
+	if (ret) {
+		dev_err(dev, "local-reset deassert failed, ret = %d\n", ret);
+		if (kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci,
+							  kproc->ti_sci_id))
+			dev_warn(dev, "module-reset assert back failed\n");
+	}
+#endif
+
+	return ret;
+}
+
+/*
+ * Power up the DSP remote processor.
+ *
+ * This function will be invoked only after the firmware for this rproc
+ * was loaded, parsed successfully, and all of its resource requirements
+ * were met.
+ */
+static int k3_dsp_rproc_start(struct rproc *rproc)
+{
+	struct k3_dsp_rproc *kproc = rproc->priv;
+	struct mbox_client *client = &kproc->client;
+	struct device *dev = kproc->dev;
+	u32 boot_addr;
+	int ret;
+
+	client->dev = dev;
+	client->tx_done = NULL;
+	client->rx_callback = k3_dsp_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;
+	}
+
+	/*
+	 * no need to issue TI-SCI commands to configure and boot the DSP cores
+	 * in IPC-only mode.
+	 */
+	if (kproc->ipc_only) {
+		dev_err(dev, "DSP initialized in IPC-only mode\n");
+		return 0;
+	}
+
+	boot_addr = rproc->bootaddr;
+	if (boot_addr & (SZ_1K - 1)) {
+		dev_err(dev, "invalid boot address 0x%x, must be aligned on a 1KB boundary\n",
+			boot_addr);
+		ret = -EINVAL;
+		goto put_mbox;
+	}
+
+	dev_err(dev, "booting DSP core using boot addr = 0x%x\n", boot_addr);
+	ret = ti_sci_proc_set_config(kproc->tsp, boot_addr, 0, 0);
+	if (ret)
+		goto put_mbox;
+
+	ret = k3_dsp_rproc_release(kproc);
+	if (ret)
+		goto put_mbox;
+
+	return 0;
+
+put_mbox:
+	mbox_free_channel(kproc->mbox);
+	return ret;
+}
+
+/*
+ * Stop the DSP remote processor.
+ *
+ * This function puts the DSP processor into reset, and finishes processing
+ * of any pending messages.
+ */
+static int k3_dsp_rproc_stop(struct rproc *rproc)
+{
+	struct k3_dsp_rproc *kproc = rproc->priv;
+
+	mbox_free_channel(kproc->mbox);
+
+	/*
+	 * no need to issue TI-SCI commands to stop the DSP core
+	 * in IPC-only mode.
+	 */
+	if (kproc->ipc_only) {
+		dev_err(kproc->dev, "DSP deinitialized in IPC-only mode\n");
+		return 0;
+	}
+
+	k3_dsp_rproc_reset(kproc);
+
+	return 0;
+}
+
+/*
+ * Custom function to translate a DSP device address (internal RAMs only) to a
+ * kernel virtual address.  The DSPs can access their RAMs at either an internal
+ * address visible only from a DSP, or at the SoC-level bus address. Both these
+ * addresses need to be looked through for translation. The translated addresses
+ * can be used either by the remoteproc core for loading (when using kernel
+ * remoteproc loader), or by any rpmsg bus drivers.
+ */
+static void *k3_dsp_rproc_da_to_va(struct rproc *rproc, u64 da, int len,
+				   u32 flags)
+{
+	struct k3_dsp_rproc *kproc = rproc->priv;
+	void __iomem *va = NULL;
+	phys_addr_t bus_addr;
+	u32 dev_addr, offset;
+	size_t size;
+	int i;
+
+	if (len <= 0)
+		return NULL;
+
+	for (i = 0; i < kproc->num_mems; i++) {
+		bus_addr = kproc->mem[i].bus_addr;
+		dev_addr = kproc->mem[i].dev_addr;
+		size = kproc->mem[i].size;
+
+		if (da < KEYSTONE_RPROC_LOCAL_ADDRESS_MASK) {
+			/* handle DSP-view addresses */
+			if (da >= dev_addr &&
+			    ((da + len) <= (dev_addr + size))) {
+				offset = da - dev_addr;
+				va = kproc->mem[i].cpu_addr + offset;
+				return (__force void *)va;
+			}
+		} else {
+			/* handle SoC-view addresses */
+			if (da >= bus_addr &&
+			    (da + len) <= (bus_addr + size)) {
+				offset = da - bus_addr;
+				va = kproc->mem[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_dsp_rproc_ops = {
+	.start		= k3_dsp_rproc_start,
+	.stop		= k3_dsp_rproc_stop,
+	.kick		= k3_dsp_rproc_kick,
+	.da_to_va	= k3_dsp_rproc_da_to_va,
+};
+
+static const char *k3_dsp_rproc_get_firmware(struct device *dev)
+{
+	const struct k3_dsp_rproc_dev_data *data =
+						of_device_get_match_data(dev);
+
+	if (!data) {
+		dev_err(dev, "data is NULL, %s\n", dev_name(dev));
+		return ERR_PTR(-ENODEV);
+	}
+
+	for (; data && data->device_name; data++) {
+		if (!strcmp(dev_name(dev), data->device_name))
+			return data->fw_name;
+	}
+
+	dev_err(dev, "No matching DSP device found, %s\n", dev_name(dev));
+	return ERR_PTR(-ENODEV);
+}
+
+static int k3_dsp_rproc_of_get_memories(struct platform_device *pdev,
+					struct k3_dsp_rproc *kproc)
+{
+	static const char * const mem_names[] = {"l2sram", "l1pram", "l1dram"};
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct resource *res;
+	int num_mems = 0;
+	int i;
+
+	num_mems = ARRAY_SIZE(mem_names);
+	kproc->mem = devm_kcalloc(kproc->dev, num_mems,
+				  sizeof(*kproc->mem), GFP_KERNEL);
+	if (!kproc->mem)
+		return -ENOMEM;
+
+	for (i = 0; i < num_mems; i++) {
+		/* C71x cores only have a L1P Cache, there are no L1P SRAMs */
+		if (of_device_is_compatible(np, "ti,j721e-c71-dsp") &&
+		    !strcmp(mem_names[i], "l1pram"))
+			continue;
+
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						   mem_names[i]);
+		kproc->mem[i].cpu_addr = devm_ioremap_resource(dev, res);
+		if (IS_ERR(kproc->mem[i].cpu_addr)) {
+			dev_err(dev, "failed to parse and map %s memory\n",
+				mem_names[i]);
+			return PTR_ERR(kproc->mem[i].cpu_addr);
+		}
+		kproc->mem[i].bus_addr = res->start;
+		kproc->mem[i].dev_addr =
+				res->start & KEYSTONE_RPROC_LOCAL_ADDRESS_MASK;
+		kproc->mem[i].size = resource_size(res);
+
+		dev_dbg(dev, "memory %8s: bus addr %pa size 0x%zx va %pK da 0x%x\n",
+			mem_names[i], &kproc->mem[i].bus_addr,
+			kproc->mem[i].size, kproc->mem[i].cpu_addr,
+			kproc->mem[i].dev_addr);
+
+		/* zero out memories to start in a pristine state */
+		/*
+		 * FIXME: comment out until kernel crash is fixed, possible
+		 * issue with local resets.
+		 * memset((__force void *)kproc->mem[i].cpu_addr, 0,
+		 *      kproc->mem[i].size);
+		 */
+	}
+	kproc->num_mems = num_mems;
+
+	return 0;
+}
+
+static int k3_dsp_reserved_mem_init(struct k3_dsp_rproc *kproc)
+{
+	struct device *dev = kproc->dev;
+	struct device_node *np = dev->of_node;
+	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 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;
+		/* 64-bit address regions currently not supported */
+		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--) {
+		if (kproc->rmem[i].cpu_addr)
+			iounmap(kproc->rmem[i].cpu_addr);
+	}
+	kfree(kproc->rmem);
+release_rmem:
+	of_reserved_mem_device_release(kproc->dev);
+	return ret;
+}
+
+static void k3_dsp_reserved_mem_exit(struct k3_dsp_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
+struct ti_sci_proc *k3_dsp_rproc_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, "ti,sci-proc-ids",
+					 temp, 2);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	tsp = kzalloc(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_dsp_rproc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct k3_dsp_rproc *kproc;
+	struct rproc *rproc;
+	const char *fw_name;
+	bool r_state = false;
+	bool p_state = false;
+	int ret = 0;
+	int ret1;
+
+	fw_name = k3_dsp_rproc_get_firmware(dev);
+	if (IS_ERR(fw_name))
+		return PTR_ERR(fw_name);
+
+	rproc = rproc_alloc(dev, dev_name(dev), &k3_dsp_rproc_ops, fw_name,
+			    sizeof(*kproc));
+	if (!rproc)
+		return -ENOMEM;
+
+	rproc->has_iommu = false;
+	rproc->recovery_disabled = true;
+	kproc = rproc->priv;
+	kproc->rproc = rproc;
+	kproc->dev = dev;
+
+	/* C71x is a 64-bit processor, so customize rproc elf loader ops */
+	if (of_device_is_compatible(np, "ti,j721e-c71-dsp")) {
+		rproc->ops->load = rproc_elf64_load_segments;
+		rproc->ops->sanity_check = rproc_elf64_sanity_check;
+		rproc->ops->parse_fw = rproc_elf64_load_rsc_table;
+		rproc->ops->find_loaded_rsc_table =
+				rproc_elf64_find_loaded_rsc_table;
+		rproc->ops->get_boot_addr = rproc_elf64_get_boot_addr;
+		rproc->ops->load = rproc_elf64_load_segments;
+	}
+
+	kproc->ti_sci = ti_sci_get_by_phandle(np, "ti,sci");
+	if (IS_ERR(kproc->ti_sci)) {
+		ret = PTR_ERR(kproc->ti_sci);
+		if (ret != -EPROBE_DEFER) {
+			dev_err(dev, "failed to get ti-sci handle, ret = %d\n",
+				ret);
+		}
+		kproc->ti_sci = NULL;
+		goto free_rproc;
+	}
+
+	ret = of_property_read_u32(np, "ti,sci-dev-id", &kproc->ti_sci_id);
+	if (ret) {
+		dev_err(dev, "missing 'ti,sci-dev-id' property\n");
+		goto put_sci;
+	}
+
+	kproc->reset = devm_reset_control_get_exclusive(dev, NULL);
+	if (IS_ERR(kproc->reset)) {
+		ret = PTR_ERR(kproc->reset);
+		dev_err(dev, "failed to get reset, status = %d\n", ret);
+		goto put_sci;
+	}
+
+	kproc->tsp = k3_dsp_rproc_of_get_tsp(dev, kproc->ti_sci);
+	if (IS_ERR(kproc->tsp)) {
+		dev_err(dev, "failed to construct ti-sci proc control, ret = %d\n",
+			ret);
+		ret = PTR_ERR(kproc->tsp);
+		goto put_sci;
+	}
+
+	ret = ti_sci_proc_request(kproc->tsp);
+	if (ret < 0) {
+		dev_err(dev, "ti_sci_proc_request failed, ret = %d\n", ret);
+		goto free_tsp;
+	}
+
+	/* enable clock for accessing DSP internal memories */
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "failed to enable clock, status = %d\n", ret);
+		pm_runtime_put_noidle(dev);
+		goto disable_rpm;
+	}
+
+	ret = k3_dsp_rproc_of_get_memories(pdev, kproc);
+	if (ret)
+		goto disable_clk;
+
+	ret = k3_dsp_reserved_mem_init(kproc);
+	if (ret) {
+		dev_err(dev, "reserved memory init failed, ret = %d\n", ret);
+		goto disable_clk;
+	}
+
+	ret = kproc->ti_sci->ops.dev_ops.is_on(kproc->ti_sci, kproc->ti_sci_id,
+					       &r_state, &p_state);
+	if (ret) {
+		dev_err(dev, "failed to get initial state, mode cannot be determined, ret = %d\n",
+			ret);
+		goto release_mem;
+	}
+
+	/* configure J721E devices for either remoteproc or IPC-only mode */
+	if (p_state) {
+		dev_err(dev, "configured DSP for IPC-only mode\n");
+		rproc->skip_load = 1;
+		kproc->ipc_only = 1;
+	} else {
+		dev_err(dev, "configured DSP for remoteproc mode\n");
+	}
+
+	ret = rproc_add(rproc);
+	if (ret) {
+		dev_err(dev, "failed to add register device with remoteproc core, status = %d\n",
+			ret);
+		goto release_mem;
+	}
+
+	platform_set_drvdata(pdev, kproc);
+
+	return 0;
+
+release_mem:
+	k3_dsp_reserved_mem_exit(kproc);
+disable_clk:
+	pm_runtime_put_sync(dev);
+disable_rpm:
+	pm_runtime_disable(dev);
+	ret1 = ti_sci_proc_release(kproc->tsp);
+	if (ret1)
+		dev_err(dev, "failed to release proc, ret = %d\n", ret1);
+free_tsp:
+	kfree(kproc->tsp);
+put_sci:
+	ret1 = ti_sci_put_handle(kproc->ti_sci);
+	if (ret1)
+		dev_err(dev, "failed to put ti_sci handle, ret = %d\n", ret1);
+free_rproc:
+	rproc_free(rproc);
+	return ret;
+}
+
+static int k3_dsp_rproc_remove(struct platform_device *pdev)
+{
+	struct k3_dsp_rproc *kproc = platform_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	rproc_del(kproc->rproc);
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	ret = ti_sci_proc_release(kproc->tsp);
+	if (ret)
+		dev_err(dev, "failed to release proc, ret = %d\n", ret);
+
+	kfree(kproc->tsp);
+
+	ret = ti_sci_put_handle(kproc->ti_sci);
+	if (ret)
+		dev_err(dev, "failed to put ti_sci handle, ret = %d\n", ret);
+
+	k3_dsp_reserved_mem_exit(kproc);
+	rproc_free(kproc->rproc);
+
+	return 0;
+}
+
+static const struct k3_dsp_rproc_dev_data j721e_c66_dsp_dev_data[] = {
+	{
+		.device_name	= "4d80800000.dsp",
+		.fw_name	= "j7-c66_0-fw",
+	},
+	{
+		.device_name	= "4d81800000.dsp",
+		.fw_name	= "j7-c66_1-fw",
+	},
+	{
+		/* sentinel */
+	},
+};
+
+static const struct k3_dsp_rproc_dev_data j721e_c71_dsp_dev_data[] = {
+	{
+		.device_name	= "64800000.dsp",
+		.fw_name	= "j7-c71_0-fw",
+	},
+	{
+		/* sentinel */
+	},
+};
+
+static const struct of_device_id k3_dsp_of_match[] = {
+	{
+		.compatible = "ti,j721e-c66-dsp",
+		.data = j721e_c66_dsp_dev_data,
+	},
+	{
+		.compatible = "ti,j721e-c71-dsp",
+		.data = j721e_c71_dsp_dev_data,
+	},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, k3_dsp_of_match);
+
+static struct platform_driver k3_dsp_rproc_driver = {
+	.probe	= k3_dsp_rproc_probe,
+	.remove	= k3_dsp_rproc_remove,
+	.driver	= {
+		.name = "k3-dsp-rproc",
+		.of_match_table = k3_dsp_of_match,
+	},
+};
+
+module_platform_driver(k3_dsp_rproc_driver);
+
+MODULE_AUTHOR("Suman Anna <s-anna@ti.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("TI K3 DSP Remoteproc driver");

drivers/remoteproc/ti_k3_r5_remoteproc.c

@@ -122,6 +122,7 @@ struct k3_r5_core {
  * @core: cached pointer to r5 core structure being used
  * @rmem: reserved memory regions data
  * @num_rmems: number of reserved memory regions
+ * @ipc_only: flag to indicate IPC-only mode
  */
 struct k3_r5_rproc {
 	struct device *dev;
@@ -132,6 +133,7 @@ struct k3_r5_rproc {
 	struct k3_r5_core *core;
 	struct k3_r5_mem *rmem;
 	int num_rmems;
+	unsigned int ipc_only : 1;
 };
 
 /**
@@ -373,6 +375,10 @@ static int k3_r5_rproc_prepare(struct rproc *rproc)
 	struct device *dev = kproc->dev;
 	int ret;
 
+	/* IPC-only mode does not require the cores to be released from reset */
+	if (kproc->ipc_only)
+		return 0;
+
 	ret = cluster->mode ? k3_r5_lockstep_release(cluster) :
 			      k3_r5_split_release(core);
 	if (ret)
@@ -399,6 +405,10 @@ static int k3_r5_rproc_unprepare(struct rproc *rproc)
 	struct device *dev = kproc->dev;
 	int ret;
 
+	/* do not put back the cores into reset in IPC-only mode */
+	if (kproc->ipc_only)
+		return 0;
+
 	ret = cluster->mode ? k3_r5_lockstep_reset(cluster) :
 			      k3_r5_split_reset(core);
 	if (ret)
@@ -456,6 +466,15 @@ static int k3_r5_rproc_start(struct rproc *rproc)
 		goto put_mbox;
 	}
 
+	/*
+	 * no need to issue TI-SCI commands to configure and boot the R5F cores
+	 * in IPC-only mode.
+	 */
+	if (kproc->ipc_only) {
+		dev_err(dev, "R5F core initialized in IPC-only mode\n");
+		return 0;
+	}
+
 	boot_addr = rproc->bootaddr;
 	/* TODO: add boot_addr sanity checking */
 	dev_err(dev, "booting R5F core using boot addr = 0x%x\n", boot_addr);
@@ -517,6 +536,16 @@ static int k3_r5_rproc_stop(struct rproc *rproc)
 	struct k3_r5_core *core = kproc->core;
 	int ret;
 
+	/*
+	 * no need to issue TI-SCI commands to stop the R5F cores
+	 * in IPC-only mode.
+	 */
+	if (kproc->ipc_only) {
+		mbox_free_channel(kproc->mbox);
+		dev_err(kproc->dev, "R5F core deinitialized in IPC-only mode\n");
+		return 0;
+	}
+
 	/* halt all applicable cores */
 	if (cluster->mode) {
 		list_for_each_entry(core, &cluster->cores, elem) {
@@ -826,6 +855,108 @@ static void k3_r5_reserved_mem_exit(struct k3_r5_rproc *kproc)
 	of_reserved_mem_device_release(kproc->dev);
 }
 
+/*
+ * This function checks and configures a R5F core for IPC-only or remoteproc
+ * mode. The driver is configured to be in IPC-only mode for a R5F core when
+ * the core has been loaded and started by a bootloader. The IPC-only mode is
+ * detected by querying the System Firmware for reset, power on and halt status
+ * and ensuring that the core is running. Any incomplete steps at bootloader
+ * are validated and errored out.
+ *
+ * In IPC-only mode, the driver state flags for ATCM, BTCM and LOCZRAMA settings
+ * and cluster mode parsed originally from kernel DT are updated to reflect the
+ * actual values configured by bootloader. The driver internal device memory
+ * addresses for TCMs are also updated.
+ *
+ * The R5F cores on AM65x SoCs are currently limited to remoteproc mode only
+ * until the early-boot support is added for the AM65x SoC family.
+ */
+static int k3_r5_rproc_configure_mode(struct k3_r5_rproc *kproc)
+{
+	struct k3_r5_cluster *cluster = kproc->cluster;
+	struct k3_r5_core *core = kproc->core;
+	struct device *cdev = core->dev;
+	bool r_state = false, c_state = false;
+	u32 ctrl = 0, cfg = 0, stat = 0, halted = 0;
+	u64 boot_vec = 0;
+	u32 atcm_enable, btcm_enable, loczrama;
+	struct k3_r5_core *core0;
+	enum cluster_mode mode;
+	int ret;
+
+	if (!of_device_is_compatible(cdev->of_node, "ti,j721e-r5f"))
+		return 0;
+
+	core0 = list_first_entry(&cluster->cores, struct k3_r5_core, elem);
+
+	ret = core->ti_sci->ops.dev_ops.is_on(core->ti_sci, core->ti_sci_id,
+					      &r_state, &c_state);
+	if (ret) {
+		dev_err(cdev, "failed to get initial state, mode cannot be determined, ret = %d\n",
+			ret);
+		return ret;
+	}
+	if (r_state != c_state) {
+		dev_warn(cdev, "R5F core may have been powered on by a different host, programmed state (%d) != actual state (%d)\n",
+			 r_state, c_state);
+	}
+
+	ret = reset_control_status(core->reset);
+	if (ret < 0) {
+		dev_err(cdev, "failed to get initial local reset status, ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	ret = ti_sci_proc_get_status(core->tsp, &boot_vec, &cfg, &ctrl,
+				     &stat);
+	if (ret < 0) {
+		dev_err(cdev, "failed to get initial processor status, ret = %d\n",
+			ret);
+		return ret;
+	}
+	atcm_enable = cfg & PROC_BOOT_CFG_FLAG_R5_ATCM_EN ?  1 : 0;
+	btcm_enable = cfg & PROC_BOOT_CFG_FLAG_R5_BTCM_EN ?  1 : 0;
+	loczrama = cfg & PROC_BOOT_CFG_FLAG_R5_TCM_RSTBASE ?  1 : 0;
+	mode = cfg & PROC_BOOT_CFG_FLAG_R5_LOCKSTEP ?  1 : 0;
+	halted = ctrl & PROC_BOOT_CTRL_FLAG_R5_CORE_HALT;
+
+	/*
+	 * IPC-only mode detection requires both local and module resets to
+	 * be deasserted and R5F core to be unhalted. Local reset status is
+	 * irrelevant if module reset is asserted (POR value has local reset
+	 * deasserted), and is deemed as remoteproc mode
+	 */
+	if (c_state && !ret && !halted) {
+		dev_err(cdev, "configured R5F for IPC-only mode\n");
+		kproc->rproc->skip_load = 1;
+		kproc->ipc_only = 1;
+		ret = 1;
+	} else if (!c_state) {
+		dev_err(cdev, "configured R5F for remoteproc mode\n");
+		ret = 0;
+	} else {
+		dev_err(cdev, "mismatched mode: local_reset = %s, module_reset = %s, core_state = %s\n",
+			!ret ? "deasserted" : "asserted",
+			c_state ? "deasserted" : "asserted",
+			halted ? "halted" : "unhalted");
+		ret = -EINVAL;
+	}
+
+	/* fixup TCMs, cluster & core flags to actual values in IPC-only mode */
+	if (ret > 0) {
+		if (core == core0)
+			cluster->mode = mode;
+		core->atcm_enable = atcm_enable;
+		core->btcm_enable = btcm_enable;
+		core->loczrama = loczrama;
+		core->mem[0].dev_addr = loczrama ? 0 : K3_R5_TCM_DEV_ADDR;
+		core->mem[1].dev_addr = loczrama ? K3_R5_TCM_DEV_ADDR : 0;
+	}
+
+	return ret;
+}
+
 static int k3_r5_cluster_rproc_init(struct platform_device *pdev)
 {
 	struct k3_r5_cluster *cluster = platform_get_drvdata(pdev);
@@ -865,6 +996,12 @@ static int k3_r5_cluster_rproc_init(struct platform_device *pdev)
 		kproc->rproc = rproc;
 		core->rproc = rproc;
 
+		ret = k3_r5_rproc_configure_mode(kproc);
+		if (ret < 0)
+			goto err_config;
+		if (ret)
+			goto init_rmem;
+
 		ret = k3_r5_rproc_configure(kproc);
 		if (ret) {
 			dev_err(dev, "initial configure failed, ret = %d\n",
@@ -872,6 +1009,7 @@ static int k3_r5_cluster_rproc_init(struct platform_device *pdev)
 			goto err_config;
 		}
 
+init_rmem:
 		ret = k3_r5_reserved_mem_init(kproc);
 		if (ret) {
 			dev_err(dev, "reserved memory init failed, ret = %d\n",
@@ -1423,11 +1561,45 @@ static const struct k3_r5_rproc_dev_data am65x_r5f_dev_data[] = {
 	},
 };
 
+static const struct k3_r5_rproc_dev_data j721e_r5f_dev_data[] = {
+	{
+		.device_name	= "41000000.r5f",
+		.fw_name	= "j7-mcu-r5f0_0-fw",
+	},
+	{
+		.device_name	= "41400000.r5f",
+		.fw_name	= "j7-mcu-r5f0_1-fw",
+	},
+	{
+		.device_name	= "5c00000.r5f",
+		.fw_name	= "j7-main-r5f0_0-fw",
+	},
+	{
+		.device_name	= "5d00000.r5f",
+		.fw_name	= "j7-main-r5f0_1-fw",
+	},
+	{
+		.device_name	= "5e00000.r5f",
+		.fw_name	= "j7-main-r5f1_0-fw",
+	},
+	{
+		.device_name	= "5f00000.r5f",
+		.fw_name	= "j7-main-r5f1_1-fw",
+	},
+	{
+		/* sentinel */
+	},
+};
+
 static const struct of_device_id k3_r5_of_match[] = {
 	{
 		.compatible     = "ti,am654-r5fss",
 		.data           = am65x_r5f_dev_data,
 	},
+	{
+		.compatible     = "ti,j721e-r5fss",
+		.data           = j721e_r5f_dev_data,
+	},
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, k3_r5_of_match);

include/linux/remoteproc.h

@@ -87,7 +87,13 @@ struct resource_table {
  * this header, and it should be parsed according to the resource type.
  */
 struct fw_rsc_hdr {
-	u32 type;
+	union {
+		u32 type;
+		struct {
+			u16 t;
+			u16 v;
+		} st;
+	};
 	u8 data[0];
 } __packed;
 
@@ -240,6 +246,32 @@ struct fw_rsc_trace {
 	u8 name[32];
 } __packed;
 
+/**
+ * struct fw_rsc_trace2 - trace buffer declaration supporting 64-bits
+ * @padding: initial padding after type field for aligned 64-bit access
+ * @da: device address (64-bit)
+ * @len: length (in bytes)
+ * @reserved: reserved (must be zero)
+ * @name: human-readable name of the trace buffer
+ *
+ * This resource entry is an enhanced version of the fw_rsc_trace resourec entry
+ * and the provides equivalent functionality but designed for 64-bit remote
+ * processors.
+ *
+ * @da specifies the device address of the buffer, @len specifies
+ * its size, and @name may contain a human readable name of the trace buffer.
+ *
+ * After booting the remote processor, the trace buffers are exposed to the
+ * user via debugfs entries (called trace0, trace1, etc..).
+ */
+struct fw_rsc_trace2 {
+	u32 padding;
+	u64 da;
+	u32 len;
+	u32 reserved;
+	u8 name[32];
+} __packed;
+
 /**
  * struct fw_rsc_vdev_vring - vring descriptor entry
  * @da: device address

samples/rpmsg/rpmsg_client_sample.c

@@ -87,6 +87,7 @@ static void rpmsg_sample_remove(struct rpmsg_device *rpdev)
 
 static struct rpmsg_device_id rpmsg_driver_sample_id_table[] = {
 	{ .name	= "rpmsg-client-sample" },
+	{ .name	= "ti.ipc4.ping-pong" },
 	{ },
 };
 MODULE_DEVICE_TABLE(rpmsg, rpmsg_driver_sample_id_table);

ti_config_fragments/v8_ipc.cfg

@@ -16,8 +16,13 @@ CONFIG_TI_PRUSS=m
 CONFIG_REMOTEPROC=m
 CONFIG_PRU_REMOTEPROC=m
 CONFIG_TI_K3_R5_REMOTEPROC=m
+CONFIG_TI_K3_DSP_REMOTEPROC=m
 
 # RPMsg
 CONFIG_RPMSG_VIRTIO=m
 CONFIG_RPMSG_PROTO=m
 CONFIG_RPMSG_PRU=m
+
+# RPMsg Samples
+CONFIG_SAMPLES=y
+CONFIG_SAMPLE_RPMSG_CLIENT=m