Merge tag 'rproc-v6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/remoteproc/linux

Pull remoteproc updates from Bjorn Andersson:
 "This makes the remoteproc core rproc_class const.

  DeviceTree bindings for a few different Qualcomm remoteprocs are
  updated to remove a range of validation warnings/errors. The Qualcomm
  SMD binding marks qcom,ipc deprecated, in favor or the mailbox
  interface.

  The TI K3 R5 remoteproc driver is updated to ensure that cores are
  powered up in the appropriate order. The driver also see a couple of
  fixes related to cleanups in error paths during probe.

  The Mediatek remoteproc driver is extended to support the MT8188 SCP
  core 1. Support for varying DRAM and IPI shared buffer sizes are
  introduced. This together with a couple of bug fixes and improvements
  to the driver.

  Support for the AMD-Xilinx Versal and Versal-NET platforms are added.
  Coredump support and support for parsing TCM information from
  DeviceTree is added to the Xilinx R5F remoteproc driver"

* tag 'rproc-v6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/remoteproc/linux: (22 commits)
  dt-bindings: remoteproc: qcom,sdm845-adsp-pil: Fix qcom,halt-regs definition
  dt-bindings: remoteproc: qcom,sc7280-wpss-pil: Fix qcom,halt-regs definition
  dt-bindings: remoteproc: qcom,qcs404-cdsp-pil: Fix qcom,halt-regs definition
  dt-bindings: remoteproc: qcom,msm8996-mss-pil: allow glink-edge on msm8996
  dt-bindings: remoteproc: qcom,smd-edge: Mark qcom,ipc as deprecated
  remoteproc: k3-r5: Jump to error handling labels in start/stop errors
  remoteproc: mediatek: Fix error code in scp_rproc_init()
  remoteproc: k3-r5: Do not allow core1 to power up before core0 via sysfs
  remoteproc: k3-r5: Wait for core0 power-up before powering up core1
  remoteproc: mediatek: Add IMGSYS IPI command
  remoteproc: mediatek: Support setting DRAM and IPI shared buffer sizes
  remoteproc: mediatek: Support MT8188 SCP core 1
  dt-bindings: remoteproc: mediatek: Support MT8188 dual-core SCP
  drivers: remoteproc: xlnx: Fix uninitialized tcm mode
  drivers: remoteproc: xlnx: Fix uninitialized variable use
  drivers: remoteproc: xlnx: Add Versal and Versal-NET support
  remoteproc: zynqmp: parse TCM from device tree
  dt-bindings: remoteproc: Add Tightly Coupled Memory (TCM) bindings
  remoteproc: zynqmp: fix lockstep mode memory region
  remoteproc: zynqmp: Add coredump support
  ...

7 files changed, 444 insertions, 206 deletions

diff --git a/drivers/remoteproc/mtk_common.h b/drivers/remoteproc/mtk_common.h
index 6d7736a031f7..fd5c539ab2ac 100644
--- a/drivers/remoteproc/mtk_common.h
+++ b/drivers/remoteproc/mtk_common.h
@@ -78,7 +78,6 @@
 #define MT8195_L2TCM_OFFSET			0x850d0
 
 #define SCP_FW_VER_LEN			32
-#define SCP_SHARE_BUFFER_SIZE		288
 
 struct scp_run {
 	u32 signaled;
@@ -97,6 +96,11 @@ struct scp_ipi_desc {
 
 struct mtk_scp;
 
+struct mtk_scp_sizes_data {
+	size_t max_dram_size;
+	size_t ipi_share_buffer_size;
+};
+
 struct mtk_scp_of_data {
 	int (*scp_clk_get)(struct mtk_scp *scp);
 	int (*scp_before_load)(struct mtk_scp *scp);
@@ -110,6 +114,7 @@ struct mtk_scp_of_data {
 	u32 host_to_scp_int_bit;
 
 	size_t ipi_buf_offset;
+	const struct mtk_scp_sizes_data *scp_sizes;
 };
 
 struct mtk_scp_of_cluster {
@@ -141,10 +146,10 @@ struct mtk_scp {
 	struct scp_ipi_desc ipi_desc[SCP_IPI_MAX];
 	bool ipi_id_ack[SCP_IPI_MAX];
 	wait_queue_head_t ack_wq;
+	u8 *share_buf;
 
 	void *cpu_addr;
 	dma_addr_t dma_addr;
-	size_t dram_size;
 
 	struct rproc_subdev *rpmsg_subdev;
 
@@ -162,7 +167,7 @@ struct mtk_scp {
 struct mtk_share_obj {
 	u32 id;
 	u32 len;
-	u8 share_buf[SCP_SHARE_BUFFER_SIZE];
+	u8 *share_buf;
 };
 
 void scp_memcpy_aligned(void __iomem *dst, const void *src, unsigned int len);
diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c
index a35409eda0cf..b8498772dba1 100644
--- a/drivers/remoteproc/mtk_scp.c
+++ b/drivers/remoteproc/mtk_scp.c
@@ -20,7 +20,6 @@
 #include "mtk_common.h"
 #include "remoteproc_internal.h"
 
-#define MAX_CODE_SIZE 0x500000
 #define SECTION_NAME_IPI_BUFFER ".ipi_buffer"
 
 /**
@@ -94,14 +93,15 @@ static void scp_ipi_handler(struct mtk_scp *scp)
 {
 	struct mtk_share_obj __iomem *rcv_obj = scp->recv_buf;
 	struct scp_ipi_desc *ipi_desc = scp->ipi_desc;
-	u8 tmp_data[SCP_SHARE_BUFFER_SIZE];
 	scp_ipi_handler_t handler;
 	u32 id = readl(&rcv_obj->id);
 	u32 len = readl(&rcv_obj->len);
+	const struct mtk_scp_sizes_data *scp_sizes;
 
-	if (len > SCP_SHARE_BUFFER_SIZE) {
-		dev_err(scp->dev, "ipi message too long (len %d, max %d)", len,
-			SCP_SHARE_BUFFER_SIZE);
+	scp_sizes = scp->data->scp_sizes;
+	if (len > scp_sizes->ipi_share_buffer_size) {
+		dev_err(scp->dev, "ipi message too long (len %d, max %zd)", len,
+			scp_sizes->ipi_share_buffer_size);
 		return;
 	}
 	if (id >= SCP_IPI_MAX) {
@@ -117,8 +117,9 @@ static void scp_ipi_handler(struct mtk_scp *scp)
 		return;
 	}
 
-	memcpy_fromio(tmp_data, &rcv_obj->share_buf, len);
-	handler(tmp_data, len, ipi_desc[id].priv);
+	memset(scp->share_buf, 0, scp_sizes->ipi_share_buffer_size);
+	memcpy_fromio(scp->share_buf, &rcv_obj->share_buf, len);
+	handler(scp->share_buf, len, ipi_desc[id].priv);
 	scp_ipi_unlock(scp, id);
 
 	scp->ipi_id_ack[id] = true;
@@ -132,7 +133,9 @@ static int scp_elf_read_ipi_buf_addr(struct mtk_scp *scp,
 static int scp_ipi_init(struct mtk_scp *scp, const struct firmware *fw)
 {
 	int ret;
-	size_t offset;
+	size_t buf_sz, offset;
+	size_t share_buf_offset;
+	const struct mtk_scp_sizes_data *scp_sizes;
 
 	/* read the ipi buf addr from FW itself first */
 	ret = scp_elf_read_ipi_buf_addr(scp, fw, &offset);
@@ -144,12 +147,23 @@ static int scp_ipi_init(struct mtk_scp *scp, const struct firmware *fw)
 	}
 	dev_info(scp->dev, "IPI buf addr %#010zx\n", offset);
 
+	/* Make sure IPI buffer fits in the L2TCM range assigned to this core */
+	buf_sz = sizeof(*scp->recv_buf) + sizeof(*scp->send_buf);
+
+	if (scp->sram_size < buf_sz + offset) {
+		dev_err(scp->dev, "IPI buffer does not fit in SRAM.\n");
+		return -EOVERFLOW;
+	}
+
+	scp_sizes = scp->data->scp_sizes;
 	scp->recv_buf = (struct mtk_share_obj __iomem *)
 			(scp->sram_base + offset);
+	share_buf_offset = sizeof(scp->recv_buf->id)
+		+ sizeof(scp->recv_buf->len) + scp_sizes->ipi_share_buffer_size;
 	scp->send_buf = (struct mtk_share_obj __iomem *)
-			(scp->sram_base + offset + sizeof(*scp->recv_buf));
-	memset_io(scp->recv_buf, 0, sizeof(*scp->recv_buf));
-	memset_io(scp->send_buf, 0, sizeof(*scp->send_buf));
+			(scp->sram_base + offset + share_buf_offset);
+	memset_io(scp->recv_buf, 0, share_buf_offset);
+	memset_io(scp->send_buf, 0, share_buf_offset);
 
 	return 0;
 }
@@ -463,6 +477,86 @@ static int mt8186_scp_before_load(struct mtk_scp *scp)
 	return 0;
 }
 
+static int mt8188_scp_l2tcm_on(struct mtk_scp *scp)
+{
+	struct mtk_scp_of_cluster *scp_cluster = scp->cluster;
+
+	mutex_lock(&scp_cluster->cluster_lock);
+
+	if (scp_cluster->l2tcm_refcnt == 0) {
+		/* clear SPM interrupt, SCP2SPM_IPC_CLR */
+		writel(0xff, scp->cluster->reg_base + MT8192_SCP2SPM_IPC_CLR);
+
+		/* Power on L2TCM */
+		scp_sram_power_on(scp->cluster->reg_base + MT8192_L2TCM_SRAM_PD_0, 0);
+		scp_sram_power_on(scp->cluster->reg_base + MT8192_L2TCM_SRAM_PD_1, 0);
+		scp_sram_power_on(scp->cluster->reg_base + MT8192_L2TCM_SRAM_PD_2, 0);
+		scp_sram_power_on(scp->cluster->reg_base + MT8192_L1TCM_SRAM_PDN, 0);
+	}
+
+	scp_cluster->l2tcm_refcnt += 1;
+
+	mutex_unlock(&scp_cluster->cluster_lock);
+
+	return 0;
+}
+
+static int mt8188_scp_before_load(struct mtk_scp *scp)
+{
+	writel(1, scp->cluster->reg_base + MT8192_CORE0_SW_RSTN_SET);
+
+	mt8188_scp_l2tcm_on(scp);
+
+	scp_sram_power_on(scp->cluster->reg_base + MT8192_CPU0_SRAM_PD, 0);
+
+	/* enable MPU for all memory regions */
+	writel(0xff, scp->cluster->reg_base + MT8192_CORE0_MEM_ATT_PREDEF);
+
+	return 0;
+}
+
+static int mt8188_scp_c1_before_load(struct mtk_scp *scp)
+{
+	u32 sec_ctrl;
+	struct mtk_scp *scp_c0;
+	struct mtk_scp_of_cluster *scp_cluster = scp->cluster;
+
+	scp->data->scp_reset_assert(scp);
+
+	mt8188_scp_l2tcm_on(scp);
+
+	scp_sram_power_on(scp->cluster->reg_base + MT8195_CPU1_SRAM_PD, 0);
+
+	/* enable MPU for all memory regions */
+	writel(0xff, scp->cluster->reg_base + MT8195_CORE1_MEM_ATT_PREDEF);
+
+	/*
+	 * The L2TCM_OFFSET_RANGE and L2TCM_OFFSET shift the destination address
+	 * on SRAM when SCP core 1 accesses SRAM.
+	 *
+	 * This configuration solves booting the SCP core 0 and core 1 from
+	 * different SRAM address because core 0 and core 1 both boot from
+	 * the head of SRAM by default. this must be configured before boot SCP core 1.
+	 *
+	 * The value of L2TCM_OFFSET_RANGE is from the viewpoint of SCP core 1.
+	 * When SCP core 1 issues address within the range (L2TCM_OFFSET_RANGE),
+	 * the address will be added with a fixed offset (L2TCM_OFFSET) on the bus.
+	 * The shift action is tranparent to software.
+	 */
+	writel(0, scp->cluster->reg_base + MT8195_L2TCM_OFFSET_RANGE_0_LOW);
+	writel(scp->sram_size, scp->cluster->reg_base + MT8195_L2TCM_OFFSET_RANGE_0_HIGH);
+
+	scp_c0 = list_first_entry(&scp_cluster->mtk_scp_list, struct mtk_scp, elem);
+	writel(scp->sram_phys - scp_c0->sram_phys, scp->cluster->reg_base + MT8195_L2TCM_OFFSET);
+
+	/* enable SRAM offset when fetching instruction and data */
+	sec_ctrl = readl(scp->cluster->reg_base + MT8195_SEC_CTRL);
+	sec_ctrl |= MT8195_CORE_OFFSET_ENABLE_I | MT8195_CORE_OFFSET_ENABLE_D;
+	writel(sec_ctrl, scp->cluster->reg_base + MT8195_SEC_CTRL);
+
+	return 0;
+}
+
 static int mt8192_scp_before_load(struct mtk_scp *scp)
 {
 	/* clear SPM interrupt, SCP2SPM_IPC_CLR */
@@ -653,14 +747,16 @@ stop:
 static void *mt8183_scp_da_to_va(struct mtk_scp *scp, u64 da, size_t len)
 {
 	int offset;
+	const struct mtk_scp_sizes_data *scp_sizes;
 
+	scp_sizes = scp->data->scp_sizes;
 	if (da < scp->sram_size) {
 		offset = da;
 		if (offset >= 0 && (offset + len) <= scp->sram_size)
 			return (void __force *)scp->sram_base + offset;
-	} else if (scp->dram_size) {
+	} else if (scp_sizes->max_dram_size) {
 		offset = da - scp->dma_addr;
-		if (offset >= 0 && (offset + len) <= scp->dram_size)
+		if (offset >= 0 && (offset + len) <= scp_sizes->max_dram_size)
 			return scp->cpu_addr + offset;
 	}
 
@@ -670,7 +766,9 @@ static void *mt8183_scp_da_to_va(struct mtk_scp *scp, u64 da, size_t len)
 static void *mt8192_scp_da_to_va(struct mtk_scp *scp, u64 da, size_t len)
 {
 	int offset;
+	const struct mtk_scp_sizes_data *scp_sizes;
 
+	scp_sizes = scp->data->scp_sizes;
 	if (da >= scp->sram_phys &&
 	    (da + len) <= scp->sram_phys + scp->sram_size) {
 		offset = da - scp->sram_phys;
@@ -686,9 +784,9 @@ static void *mt8192_scp_da_to_va(struct mtk_scp *scp, u64 da, size_t len)
 	}
 
 	/* optional memory region */
-	if (scp->dram_size &&
+	if (scp_sizes->max_dram_size &&
 	    da >= scp->dma_addr &&
-	    (da + len) <= scp->dma_addr + scp->dram_size) {
+	    (da + len) <= scp->dma_addr + scp_sizes->max_dram_size) {
 		offset = da - scp->dma_addr;
 		return scp->cpu_addr + offset;
 	}
@@ -709,6 +807,47 @@ static void mt8183_scp_stop(struct mtk_scp *scp)
 	writel(0, scp->cluster->reg_base + MT8183_WDT_CFG);
 }
 
+static void mt8188_scp_l2tcm_off(struct mtk_scp *scp)
+{
+	struct mtk_scp_of_cluster *scp_cluster = scp->cluster;
+
+	mutex_lock(&scp_cluster->cluster_lock);
+
+	if (scp_cluster->l2tcm_refcnt > 0)
+		scp_cluster->l2tcm_refcnt -= 1;
+
+	if (scp_cluster->l2tcm_refcnt == 0) {
+		/* Power off L2TCM */
+		scp_sram_power_off(scp->cluster->reg_base + MT8192_L2TCM_SRAM_PD_0, 0);
+		scp_sram_power_off(scp->cluster->reg_base + MT8192_L2TCM_SRAM_PD_1, 0);
+		scp_sram_power_off(scp->cluster->reg_base + MT8192_L2TCM_SRAM_PD_2, 0);
+		scp_sram_power_off(scp->cluster->reg_base + MT8192_L1TCM_SRAM_PDN, 0);
+	}
+
+	mutex_unlock(&scp_cluster->cluster_lock);
+}
+
+static void mt8188_scp_stop(struct mtk_scp *scp)
+{
+	mt8188_scp_l2tcm_off(scp);
+
+	scp_sram_power_off(scp->cluster->reg_base + MT8192_CPU0_SRAM_PD, 0);
+
+	/* Disable SCP watchdog */
+	writel(0, scp->cluster->reg_base + MT8192_CORE0_WDT_CFG);
+}
+
+static void mt8188_scp_c1_stop(struct mtk_scp *scp)
+{
+	mt8188_scp_l2tcm_off(scp);
+
+	/* Power off CPU SRAM */
+	scp_sram_power_off(scp->cluster->reg_base + MT8195_CPU1_SRAM_PD, 0);
+
+	/* Disable SCP watchdog */
+	writel(0, scp->cluster->reg_base + MT8195_CORE1_WDT_CFG);
+}
+
 static void mt8192_scp_stop(struct mtk_scp *scp)
 {
 	/* Disable SRAM clock */
@@ -868,6 +1007,7 @@ EXPORT_SYMBOL_GPL(scp_mapping_dm_addr);
 static int scp_map_memory_region(struct mtk_scp *scp)
 {
 	int ret;
+	const struct mtk_scp_sizes_data *scp_sizes;
 
 	ret = of_reserved_mem_device_init(scp->dev);
 
@@ -883,8 +1023,8 @@ static int scp_map_memory_region(struct mtk_scp *scp)
 	}
 
 	/* Reserved SCP code size */
-	scp->dram_size = MAX_CODE_SIZE;
-	scp->cpu_addr = dma_alloc_coherent(scp->dev, scp->dram_size,
+	scp_sizes = scp->data->scp_sizes;
+	scp->cpu_addr = dma_alloc_coherent(scp->dev, scp_sizes->max_dram_size,
 					   &scp->dma_addr, GFP_KERNEL);
 	if (!scp->cpu_addr)
 		return -ENOMEM;
@@ -894,10 +1034,13 @@ 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)
+	const struct mtk_scp_sizes_data *scp_sizes;
+
+	scp_sizes = scp->data->scp_sizes;
+	if (scp_sizes->max_dram_size == 0)
 		return;
 
-	dma_free_coherent(scp->dev, scp->dram_size, scp->cpu_addr,
+	dma_free_coherent(scp->dev, scp_sizes->max_dram_size, scp->cpu_addr,
 			  scp->dma_addr);
 	of_reserved_mem_device_release(scp->dev);
 }
@@ -961,6 +1104,7 @@ static struct mtk_scp *scp_rproc_init(struct platform_device *pdev,
 	struct resource *res;
 	const char *fw_name = "scp.img";
 	int ret, i;
+	const struct mtk_scp_sizes_data *scp_sizes;
 
 	ret = rproc_of_parse_firmware(dev, 0, &fw_name);
 	if (ret < 0 && ret != -EINVAL)
@@ -1008,6 +1152,14 @@ static struct mtk_scp *scp_rproc_init(struct platform_device *pdev,
 		goto release_dev_mem;
 	}
 
+	scp_sizes = scp->data->scp_sizes;
+	scp->share_buf = kzalloc(scp_sizes->ipi_share_buffer_size, GFP_KERNEL);
+	if (!scp->share_buf) {
+		dev_err(dev, "Failed to allocate IPI share buffer\n");
+		ret = -ENOMEM;
+		goto release_dev_mem;
+	}
+
 	init_waitqueue_head(&scp->run.wq);
 	init_waitqueue_head(&scp->ack_wq);
 
@@ -1027,6 +1179,8 @@ static struct mtk_scp *scp_rproc_init(struct platform_device *pdev,
 remove_subdev:
 	scp_remove_rpmsg_subdev(scp);
 	scp_ipi_unregister(scp, SCP_IPI_INIT);
+	kfree(scp->share_buf);
+	scp->share_buf = NULL;
 release_dev_mem:
 	scp_unmap_memory_region(scp);
 	for (i = 0; i < SCP_IPI_MAX; i++)
@@ -1042,6 +1196,8 @@ static void scp_free(struct mtk_scp *scp)
 
 	scp_remove_rpmsg_subdev(scp);
 	scp_ipi_unregister(scp, SCP_IPI_INIT);
+	kfree(scp->share_buf);
+	scp->share_buf = NULL;
 	scp_unmap_memory_region(scp);
 	for (i = 0; i < SCP_IPI_MAX; i++)
 		mutex_destroy(&scp->ipi_desc[i].lock);
@@ -1228,6 +1384,21 @@ static void scp_remove(struct platform_device *pdev)
 	mutex_destroy(&scp_cluster->cluster_lock);
 }
 
+static const struct mtk_scp_sizes_data default_scp_sizes = {
+	.max_dram_size = 0x500000,
+	.ipi_share_buffer_size = 288,
+};
+
+static const struct mtk_scp_sizes_data mt8188_scp_sizes = {
+	.max_dram_size = 0x500000,
+	.ipi_share_buffer_size = 600,
+};
+
+static const struct mtk_scp_sizes_data mt8188_scp_c1_sizes = {
+	.max_dram_size = 0xA00000,
+	.ipi_share_buffer_size = 600,
+};
+
 static const struct mtk_scp_of_data mt8183_of_data = {
 	.scp_clk_get = mt8183_scp_clk_get,
 	.scp_before_load = mt8183_scp_before_load,
@@ -1239,6 +1410,7 @@ static const struct mtk_scp_of_data mt8183_of_data = {
 	.host_to_scp_reg = MT8183_HOST_TO_SCP,
 	.host_to_scp_int_bit = MT8183_HOST_IPC_INT_BIT,
 	.ipi_buf_offset = 0x7bdb0,
+	.scp_sizes = &default_scp_sizes,
 };
 
 static const struct mtk_scp_of_data mt8186_of_data = {
@@ -1252,18 +1424,33 @@ static const struct mtk_scp_of_data mt8186_of_data = {
 	.host_to_scp_reg = MT8183_HOST_TO_SCP,
 	.host_to_scp_int_bit = MT8183_HOST_IPC_INT_BIT,
 	.ipi_buf_offset = 0x3bdb0,
+	.scp_sizes = &default_scp_sizes,
 };
 
 static const struct mtk_scp_of_data mt8188_of_data = {
 	.scp_clk_get = mt8195_scp_clk_get,
-	.scp_before_load = mt8192_scp_before_load,
-	.scp_irq_handler = mt8192_scp_irq_handler,
+	.scp_before_load = mt8188_scp_before_load,
+	.scp_irq_handler = mt8195_scp_irq_handler,
 	.scp_reset_assert = mt8192_scp_reset_assert,
 	.scp_reset_deassert = mt8192_scp_reset_deassert,
-	.scp_stop = mt8192_scp_stop,
+	.scp_stop = mt8188_scp_stop,
 	.scp_da_to_va = mt8192_scp_da_to_va,
 	.host_to_scp_reg = MT8192_GIPC_IN_SET,
 	.host_to_scp_int_bit = MT8192_HOST_IPC_INT_BIT,
+	.scp_sizes = &mt8188_scp_sizes,
+};
+
+static const struct mtk_scp_of_data mt8188_of_data_c1 = {
+	.scp_clk_get = mt8195_scp_clk_get,
+	.scp_before_load = mt8188_scp_c1_before_load,
+	.scp_irq_handler = mt8195_scp_c1_irq_handler,
+	.scp_reset_assert = mt8195_scp_c1_reset_assert,
+	.scp_reset_deassert = mt8195_scp_c1_reset_deassert,
+	.scp_stop = mt8188_scp_c1_stop,
+	.scp_da_to_va = mt8192_scp_da_to_va,
+	.host_to_scp_reg = MT8192_GIPC_IN_SET,
+	.host_to_scp_int_bit = MT8195_CORE1_HOST_IPC_INT_BIT,
+	.scp_sizes = &mt8188_scp_c1_sizes,
 };
 
 static const struct mtk_scp_of_data mt8192_of_data = {
@@ -1276,6 +1463,7 @@ static const struct mtk_scp_of_data mt8192_of_data = {
 	.scp_da_to_va = mt8192_scp_da_to_va,
 	.host_to_scp_reg = MT8192_GIPC_IN_SET,
 	.host_to_scp_int_bit = MT8192_HOST_IPC_INT_BIT,
+	.scp_sizes = &default_scp_sizes,
 };
 
 static const struct mtk_scp_of_data mt8195_of_data = {
@@ -1288,6 +1476,7 @@ static const struct mtk_scp_of_data mt8195_of_data = {
 	.scp_da_to_va = mt8192_scp_da_to_va,
 	.host_to_scp_reg = MT8192_GIPC_IN_SET,
 	.host_to_scp_int_bit = MT8192_HOST_IPC_INT_BIT,
+	.scp_sizes = &default_scp_sizes,
 };
 
 static const struct mtk_scp_of_data mt8195_of_data_c1 = {
@@ -1300,6 +1489,13 @@ static const struct mtk_scp_of_data mt8195_of_data_c1 = {
 	.scp_da_to_va = mt8192_scp_da_to_va,
 	.host_to_scp_reg = MT8192_GIPC_IN_SET,
 	.host_to_scp_int_bit = MT8195_CORE1_HOST_IPC_INT_BIT,
+	.scp_sizes = &default_scp_sizes,
+};
+
+static const struct mtk_scp_of_data *mt8188_of_data_cores[] = {
+	&mt8188_of_data,
+	&mt8188_of_data_c1,
+	NULL
 };
 
 static const struct mtk_scp_of_data *mt8195_of_data_cores[] = {
@@ -1312,6 +1508,7 @@ static const struct of_device_id mtk_scp_of_match[] = {
 	{ .compatible = "mediatek,mt8183-scp", .data = &mt8183_of_data },
 	{ .compatible = "mediatek,mt8186-scp", .data = &mt8186_of_data },
 	{ .compatible = "mediatek,mt8188-scp", .data = &mt8188_of_data },
+	{ .compatible = "mediatek,mt8188-scp-dual", .data = &mt8188_of_data_cores },
 	{ .compatible = "mediatek,mt8192-scp", .data = &mt8192_of_data },
 	{ .compatible = "mediatek,mt8195-scp", .data = &mt8195_of_data },
 	{ .compatible = "mediatek,mt8195-scp-dual", .data = &mt8195_of_data_cores },
diff --git a/drivers/remoteproc/mtk_scp_ipi.c b/drivers/remoteproc/mtk_scp_ipi.c
index cd0b60106ec2..c068227e251e 100644
--- a/drivers/remoteproc/mtk_scp_ipi.c
+++ b/drivers/remoteproc/mtk_scp_ipi.c
@@ -162,10 +162,13 @@ int scp_ipi_send(struct mtk_scp *scp, u32 id, void *buf, unsigned int len,
 	struct mtk_share_obj __iomem *send_obj = scp->send_buf;
 	u32 val;
 	int ret;
+	const struct mtk_scp_sizes_data *scp_sizes;
+
+	scp_sizes = scp->data->scp_sizes;
 
 	if (WARN_ON(id <= SCP_IPI_INIT) || WARN_ON(id >= SCP_IPI_MAX) ||
 	    WARN_ON(id == SCP_IPI_NS_SERVICE) ||
-	    WARN_ON(len > sizeof(send_obj->share_buf)) || WARN_ON(!buf))
+	    WARN_ON(len > scp_sizes->ipi_share_buffer_size) || WARN_ON(!buf))
 		return -EINVAL;
 
 	ret = clk_prepare_enable(scp->clk);
@@ -184,7 +187,7 @@ int scp_ipi_send(struct mtk_scp *scp, u32 id, void *buf, unsigned int len,
 		goto unlock_mutex;
 	}
 
-	scp_memcpy_aligned(send_obj->share_buf, buf, len);
+	scp_memcpy_aligned(&send_obj->share_buf, buf, len);
 
 	writel(len, &send_obj->len);
 	writel(id, &send_obj->id);
diff --git a/drivers/remoteproc/remoteproc_internal.h b/drivers/remoteproc/remoteproc_internal.h
index f62a82d71dfa..0cd09e67ac14 100644
--- a/drivers/remoteproc/remoteproc_internal.h
+++ b/drivers/remoteproc/remoteproc_internal.h
@@ -72,7 +72,7 @@ void rproc_init_debugfs(void);
 void rproc_exit_debugfs(void);
 
 /* from remoteproc_sysfs.c */
-extern struct class rproc_class;
+extern const struct class rproc_class;
 int rproc_init_sysfs(void);
 void rproc_exit_sysfs(void);
 
diff --git a/drivers/remoteproc/remoteproc_sysfs.c b/drivers/remoteproc/remoteproc_sysfs.c
index 8c7ea8922638..138e752c5e4e 100644
--- a/drivers/remoteproc/remoteproc_sysfs.c
+++ b/drivers/remoteproc/remoteproc_sysfs.c
@@ -254,7 +254,7 @@ static const struct attribute_group *rproc_devgroups[] = {
 	NULL
 };
 
-struct class rproc_class = {
+const struct class rproc_class = {
 	.name		= "remoteproc",
 	.dev_groups	= rproc_devgroups,
 };
diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c
index ad3415a3851b..50e486bcfa10 100644
--- a/drivers/remoteproc/ti_k3_r5_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
@@ -103,12 +103,14 @@ struct k3_r5_soc_data {
  * @dev: cached device pointer
  * @mode: Mode to configure the Cluster - Split or LockStep
  * @cores: list of R5 cores within the cluster
+ * @core_transition: wait queue to sync core state changes
  * @soc_data: SoC-specific feature data for a R5FSS
  */
 struct k3_r5_cluster {
 	struct device *dev;
 	enum cluster_mode mode;
 	struct list_head cores;
+	wait_queue_head_t core_transition;
 	const struct k3_r5_soc_data *soc_data;
 };
 
@@ -128,6 +130,7 @@ struct k3_r5_cluster {
  * @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
+ * @released_from_reset: flag to signal when core is out of reset
  */
 struct k3_r5_core {
 	struct list_head elem;
@@ -144,6 +147,7 @@ struct k3_r5_core {
 	u32 atcm_enable;
 	u32 btcm_enable;
 	u32 loczrama;
+	bool released_from_reset;
 };
 
 /**
@@ -460,6 +464,8 @@ static int k3_r5_rproc_prepare(struct rproc *rproc)
 			ret);
 		return ret;
 	}
+	core->released_from_reset = true;
+	wake_up_interruptible(&cluster->core_transition);
 
 	/*
 	 * Newer IP revisions like on J7200 SoCs support h/w auto-initialization
@@ -542,7 +548,7 @@ static int k3_r5_rproc_start(struct rproc *rproc)
 	struct k3_r5_rproc *kproc = rproc->priv;
 	struct k3_r5_cluster *cluster = kproc->cluster;
 	struct device *dev = kproc->dev;
-	struct k3_r5_core *core;
+	struct k3_r5_core *core0, *core;
 	u32 boot_addr;
 	int ret;
 
@@ -568,6 +574,16 @@ static int k3_r5_rproc_start(struct rproc *rproc)
 				goto unroll_core_run;
 		}
 	} else {
+		/* do not allow core 1 to start before core 0 */
+		core0 = list_first_entry(&cluster->cores, struct k3_r5_core,
+					 elem);
+		if (core != core0 && core0->rproc->state == RPROC_OFFLINE) {
+			dev_err(dev, "%s: can not start core 1 before core 0\n",
+				__func__);
+			ret = -EPERM;
+			goto put_mbox;
+		}
+
 		ret = k3_r5_core_run(core);
 		if (ret)
 			goto put_mbox;
@@ -613,7 +629,8 @@ 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;
+	struct device *dev = kproc->dev;
+	struct k3_r5_core *core1, *core = kproc->core;
 	int ret;
 
 	/* halt all applicable cores */
@@ -626,6 +643,16 @@ static int k3_r5_rproc_stop(struct rproc *rproc)
 			}
 		}
 	} else {
+		/* do not allow core 0 to stop before core 1 */
+		core1 = list_last_entry(&cluster->cores, struct k3_r5_core,
+					elem);
+		if (core != core1 && core1->rproc->state != RPROC_OFFLINE) {
+			dev_err(dev, "%s: can not stop core 0 before core 1\n",
+				__func__);
+			ret = -EPERM;
+			goto out;
+		}
+
 		ret = k3_r5_core_halt(core);
 		if (ret)
 			goto out;
@@ -1140,6 +1167,12 @@ static int k3_r5_rproc_configure_mode(struct k3_r5_rproc *kproc)
 		return ret;
 	}
 
+	/*
+	 * Skip the waiting mechanism for sequential power-on of cores if the
+	 * core has already been booted by another entity.
+	 */
+	core->released_from_reset = c_state;
+
 	ret = ti_sci_proc_get_status(core->tsp, &boot_vec, &cfg, &ctrl,
 				     &stat);
 	if (ret < 0) {
@@ -1280,6 +1313,26 @@ init_rmem:
 		    cluster->mode == CLUSTER_MODE_SINGLECPU ||
 		    cluster->mode == CLUSTER_MODE_SINGLECORE)
 			break;
+
+		/*
+		 * R5 cores require to be powered on sequentially, core0
+		 * should be in higher power state than core1 in a cluster
+		 * So, wait for current core to power up before proceeding
+		 * to next core and put timeout of 2sec for each core.
+		 *
+		 * This waiting mechanism is necessary because
+		 * rproc_auto_boot_callback() for core1 can be called before
+		 * core0 due to thread execution order.
+		 */
+		ret = wait_event_interruptible_timeout(cluster->core_transition,
+						       core->released_from_reset,
+						       msecs_to_jiffies(2000));
+		if (ret <= 0) {
+			dev_err(dev,
+				"Timed out waiting for %s core to power up!\n",
+				rproc->name);
+			return ret;
+		}
 	}
 
 	return 0;
@@ -1709,6 +1762,7 @@ static int k3_r5_probe(struct platform_device *pdev)
 	cluster->dev = dev;
 	cluster->soc_data = data;
 	INIT_LIST_HEAD(&cluster->cores);
+	init_waitqueue_head(&cluster->core_transition);
 
 	ret = of_property_read_u32(np, "ti,cluster-mode", &cluster->mode);
 	if (ret < 0 && ret != -EINVAL) {
diff --git a/drivers/remoteproc/xlnx_r5_remoteproc.c b/drivers/remoteproc/xlnx_r5_remoteproc.c
index 4395edea9a64..84243d1dff9f 100644
--- a/drivers/remoteproc/xlnx_r5_remoteproc.c
+++ b/drivers/remoteproc/xlnx_r5_remoteproc.c
@@ -74,8 +74,8 @@ struct mbox_info {
 };
 
 /*
- * Hardcoded TCM bank values. This will be removed once TCM bindings are
- * accepted for system-dt specifications and upstreamed in linux kernel
+ * Hardcoded TCM bank values. This will stay in driver to maintain backward
+ * compatibility with device-tree that does not have TCM information.
  */
 static const struct mem_bank_data zynqmp_tcm_banks_split[] = {
 	{0xffe00000UL, 0x0, 0x10000UL, PD_R5_0_ATCM, "atcm0"}, /* TCM 64KB each */
@@ -84,12 +84,12 @@ static const struct mem_bank_data zynqmp_tcm_banks_split[] = {
 	{0xffeb0000UL, 0x20000, 0x10000UL, PD_R5_1_BTCM, "btcm1"},
 };
 
-/* In lockstep mode cluster combines each 64KB TCM and makes 128KB TCM */
+/* In lockstep mode cluster uses each 64KB TCM from second core as well */
 static const struct mem_bank_data zynqmp_tcm_banks_lockstep[] = {
-	{0xffe00000UL, 0x0, 0x20000UL, PD_R5_0_ATCM, "atcm0"}, /* TCM 128KB each */
-	{0xffe20000UL, 0x20000, 0x20000UL, PD_R5_0_BTCM, "btcm0"},
-	{0, 0, 0, PD_R5_1_ATCM, ""},
-	{0, 0, 0, PD_R5_1_BTCM, ""},
+	{0xffe00000UL, 0x0, 0x10000UL, PD_R5_0_ATCM, "atcm0"}, /* TCM 64KB each */
+	{0xffe20000UL, 0x20000, 0x10000UL, PD_R5_0_BTCM, "btcm0"},
+	{0xffe10000UL, 0x10000, 0x10000UL, PD_R5_1_ATCM, "atcm1"},
+	{0xffe30000UL, 0x30000, 0x10000UL, PD_R5_1_BTCM, "btcm1"},
 };
 
 /**
@@ -301,36 +301,6 @@ static void zynqmp_r5_rproc_kick(struct rproc *rproc, int vqid)
 }
 
 /*
- * zynqmp_r5_set_mode()
- *
- * set RPU cluster and TCM operation mode
- *
- * @r5_core: pointer to zynqmp_r5_core type object
- * @fw_reg_val: value expected by firmware to configure RPU cluster mode
- * @tcm_mode: value expected by fw to configure TCM mode (lockstep or split)
- *
- * Return: 0 for success and < 0 for failure
- */
-static int zynqmp_r5_set_mode(struct zynqmp_r5_core *r5_core,
-			      enum rpu_oper_mode fw_reg_val,
-			      enum rpu_tcm_comb tcm_mode)
-{
-	int ret;
-
-	ret = zynqmp_pm_set_rpu_mode(r5_core->pm_domain_id, fw_reg_val);
-	if (ret < 0) {
-		dev_err(r5_core->dev, "failed to set RPU mode\n");
-		return ret;
-	}
-
-	ret = zynqmp_pm_set_tcm_config(r5_core->pm_domain_id, tcm_mode);
-	if (ret < 0)
-		dev_err(r5_core->dev, "failed to configure TCM\n");
-
-	return ret;
-}
-
-/*
  * zynqmp_r5_rproc_start()
  * @rproc: single R5 core's corresponding rproc instance
  *
@@ -486,6 +456,7 @@ static int add_mem_regions_carveout(struct rproc *rproc)
 		}
 
 		rproc_add_carveout(rproc, rproc_mem);
+		rproc_coredump_add_segment(rproc, rmem->base, rmem->size);
 
 		dev_dbg(&rproc->dev, "reserved mem carveout %s addr=%llx, size=0x%llx",
 			it.node->name, rmem->base, rmem->size);
@@ -540,14 +511,14 @@ static int tcm_mem_map(struct rproc *rproc,
 }
 
 /*
- * add_tcm_carveout_split_mode()
+ * add_tcm_banks()
  * @rproc: single R5 core's corresponding rproc instance
  *
- * allocate and add remoteproc carveout for TCM memory in split mode
+ * allocate and add remoteproc carveout for TCM memory
  *
  * return 0 on success, otherwise non-zero value on failure
  */
-static int add_tcm_carveout_split_mode(struct rproc *rproc)
+static int add_tcm_banks(struct rproc *rproc)
 {
 	struct rproc_mem_entry *rproc_mem;
 	struct zynqmp_r5_core *r5_core;
@@ -580,10 +551,10 @@ static int add_tcm_carveout_split_mode(struct rproc *rproc)
 					     ZYNQMP_PM_REQUEST_ACK_BLOCKING);
 		if (ret < 0) {
 			dev_err(dev, "failed to turn on TCM 0x%x", pm_domain_id);
-			goto release_tcm_split;
+			goto release_tcm;
 		}
 
-		dev_dbg(dev, "TCM carveout split mode %s addr=%llx, da=0x%x, size=0x%lx",
+		dev_dbg(dev, "TCM carveout %s addr=%llx, da=0x%x, size=0x%lx",
 			bank_name, bank_addr, da, bank_size);
 
 		rproc_mem = rproc_mem_entry_init(dev, NULL, bank_addr,
@@ -593,15 +564,16 @@ static int add_tcm_carveout_split_mode(struct rproc *rproc)
 		if (!rproc_mem) {
 			ret = -ENOMEM;
 			zynqmp_pm_release_node(pm_domain_id);
-			goto release_tcm_split;
+			goto release_tcm;
 		}
 
 		rproc_add_carveout(rproc, rproc_mem);
+		rproc_coredump_add_segment(rproc, da, bank_size);
 	}
 
 	return 0;
 
-release_tcm_split:
+release_tcm:
 	/* If failed, Turn off all TCM banks turned on before */
 	for (i--; i >= 0; i--) {
 		pm_domain_id = r5_core->tcm_banks[i]->pm_domain_id;
@@ -611,127 +583,6 @@ release_tcm_split:
 }
 
 /*
- * add_tcm_carveout_lockstep_mode()
- * @rproc: single R5 core's corresponding rproc instance
- *
- * allocate and add remoteproc carveout for TCM memory in lockstep mode
- *
- * return 0 on success, otherwise non-zero value on failure
- */
-static int add_tcm_carveout_lockstep_mode(struct rproc *rproc)
-{
-	struct rproc_mem_entry *rproc_mem;
-	struct zynqmp_r5_core *r5_core;
-	int i, num_banks, ret;
-	phys_addr_t bank_addr;
-	size_t bank_size = 0;
-	struct device *dev;
-	u32 pm_domain_id;
-	char *bank_name;
-	u32 da;
-
-	r5_core = rproc->priv;
-	dev = r5_core->dev;
-
-	/* Go through zynqmp banks for r5 node */
-	num_banks = r5_core->tcm_bank_count;
-
-	/*
-	 * In lockstep mode, TCM is contiguous memory block
-	 * However, each TCM block still needs to be enabled individually.
-	 * So, Enable each TCM block individually.
-	 * Although ATCM and BTCM is contiguous memory block, add two separate
-	 * carveouts for both.
-	 */
-	for (i = 0; i < num_banks; i++) {
-		pm_domain_id = r5_core->tcm_banks[i]->pm_domain_id;
-
-		/* Turn on each TCM bank individually */
-		ret = zynqmp_pm_request_node(pm_domain_id,
-					     ZYNQMP_PM_CAPABILITY_ACCESS, 0,
-					     ZYNQMP_PM_REQUEST_ACK_BLOCKING);
-		if (ret < 0) {
-			dev_err(dev, "failed to turn on TCM 0x%x", pm_domain_id);
-			goto release_tcm_lockstep;
-		}
-
-		bank_size = r5_core->tcm_banks[i]->size;
-		if (bank_size == 0)
-			continue;
-
-		bank_addr = r5_core->tcm_banks[i]->addr;
-		da = r5_core->tcm_banks[i]->da;
-		bank_name = r5_core->tcm_banks[i]->bank_name;
-
-		/* Register TCM address range, TCM map and unmap functions */
-		rproc_mem = rproc_mem_entry_init(dev, NULL, bank_addr,
-						 bank_size, da,
-						 tcm_mem_map, tcm_mem_unmap,
-						 bank_name);
-		if (!rproc_mem) {
-			ret = -ENOMEM;
-			zynqmp_pm_release_node(pm_domain_id);
-			goto release_tcm_lockstep;
-		}
-
-		/* If registration is success, add carveouts */
-		rproc_add_carveout(rproc, rproc_mem);
-
-		dev_dbg(dev, "TCM carveout lockstep mode %s addr=0x%llx, da=0x%x, size=0x%lx",
-			bank_name, bank_addr, da, bank_size);
-	}
-
-	return 0;
-
-release_tcm_lockstep:
-	/* If failed, Turn off all TCM banks turned on before */
-	for (i--; i >= 0; i--) {
-		pm_domain_id = r5_core->tcm_banks[i]->pm_domain_id;
-		zynqmp_pm_release_node(pm_domain_id);
-	}
-	return ret;
-}
-
-/*
- * add_tcm_banks()
- * @rproc: single R5 core's corresponding rproc instance
- *
- * allocate and add remoteproc carveouts for TCM memory based on cluster mode
- *
- * return 0 on success, otherwise non-zero value on failure
- */
-static int add_tcm_banks(struct rproc *rproc)
-{
-	struct zynqmp_r5_cluster *cluster;
-	struct zynqmp_r5_core *r5_core;
-	struct device *dev;
-
-	r5_core = rproc->priv;
-	if (!r5_core)
-		return -EINVAL;
-
-	dev = r5_core->dev;
-
-	cluster = dev_get_drvdata(dev->parent);
-	if (!cluster) {
-		dev_err(dev->parent, "Invalid driver data\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * In lockstep mode TCM banks are one contiguous memory region of 256Kb
-	 * In split mode, each TCM bank is 64Kb and not contiguous.
-	 * We add memory carveouts accordingly.
-	 */
-	if (cluster->mode == SPLIT_MODE)
-		return add_tcm_carveout_split_mode(rproc);
-	else if (cluster->mode == LOCKSTEP_MODE)
-		return add_tcm_carveout_lockstep_mode(rproc);
-
-	return -EINVAL;
-}
-
-/*
  * zynqmp_r5_parse_fw()
  * @rproc: single R5 core's corresponding rproc instance
  * @fw: ptr to firmware to be loaded onto r5 core
@@ -853,6 +704,8 @@ static struct zynqmp_r5_core *zynqmp_r5_add_rproc_core(struct device *cdev)
 		return ERR_PTR(-ENOMEM);
 	}
 
+	rproc_coredump_set_elf_info(r5_rproc, ELFCLASS32, EM_ARM);
+
 	r5_rproc->auto_boot = false;
 	r5_core = r5_rproc->priv;
 	r5_core->dev = cdev;
@@ -878,6 +731,103 @@ free_rproc:
 	return ERR_PTR(ret);
 }
 
+static int zynqmp_r5_get_tcm_node_from_dt(struct zynqmp_r5_cluster *cluster)
+{
+	int i, j, tcm_bank_count, ret, tcm_pd_idx, pd_count;
+	struct of_phandle_args out_args;
+	struct zynqmp_r5_core *r5_core;
+	struct platform_device *cpdev;
+	struct mem_bank_data *tcm;
+	struct device_node *np;
+	struct resource *res;
+	u64 abs_addr, size;
+	struct device *dev;
+
+	for (i = 0; i < cluster->core_count; i++) {
+		r5_core = cluster->r5_cores[i];
+		dev = r5_core->dev;
+		np = r5_core->np;
+
+		pd_count = of_count_phandle_with_args(np, "power-domains",
+						      "#power-domain-cells");
+
+		if (pd_count <= 0) {
+			dev_err(dev, "invalid power-domains property, %d\n", pd_count);
+			return -EINVAL;
+		}
+
+		/* First entry in power-domains list is for r5 core, rest for TCM. */
+		tcm_bank_count = pd_count - 1;
+
+		if (tcm_bank_count <= 0) {
+			dev_err(dev, "invalid TCM count %d\n", tcm_bank_count);
+			return -EINVAL;
+		}
+
+		r5_core->tcm_banks = devm_kcalloc(dev, tcm_bank_count,
+						  sizeof(struct mem_bank_data *),
+						  GFP_KERNEL);
+		if (!r5_core->tcm_banks)
+			return -ENOMEM;
+
+		r5_core->tcm_bank_count = tcm_bank_count;
+		for (j = 0, tcm_pd_idx = 1; j < tcm_bank_count; j++, tcm_pd_idx++) {
+			tcm = devm_kzalloc(dev, sizeof(struct mem_bank_data),
+					   GFP_KERNEL);
+			if (!tcm)
+				return -ENOMEM;
+
+			r5_core->tcm_banks[j] = tcm;
+
+			/* Get power-domains id of TCM. */
+			ret = of_parse_phandle_with_args(np, "power-domains",
+							 "#power-domain-cells",
+							 tcm_pd_idx, &out_args);
+			if (ret) {
+				dev_err(r5_core->dev,
+					"failed to get tcm %d pm domain, ret %d\n",
+					tcm_pd_idx, ret);
+				return ret;
+			}
+			tcm->pm_domain_id = out_args.args[0];
+			of_node_put(out_args.np);
+
+			/* Get TCM address without translation. */
+			ret = of_property_read_reg(np, j, &abs_addr, &size);
+			if (ret) {
+				dev_err(dev, "failed to get reg property\n");
+				return ret;
+			}
+
+			/*
+			 * Remote processor can address only 32 bits
+			 * so convert 64-bits into 32-bits. This will discard
+			 * any unwanted upper 32-bits.
+			 */
+			tcm->da = (u32)abs_addr;
+			tcm->size = (u32)size;
+
+			cpdev = to_platform_device(dev);
+			res = platform_get_resource(cpdev, IORESOURCE_MEM, j);
+			if (!res) {
+				dev_err(dev, "failed to get tcm resource\n");
+				return -EINVAL;
+			}
+
+			tcm->addr = (u32)res->start;
+			tcm->bank_name = (char *)res->name;
+			res = devm_request_mem_region(dev, tcm->addr, tcm->size,
+						      tcm->bank_name);
+			if (!res) {
+				dev_err(dev, "failed to request tcm resource\n");
+				return -EINVAL;
+			}
+		}
+	}
+
+	return 0;
+}
+
 /**
  * zynqmp_r5_get_tcm_node()
  * Ideally this function should parse tcm node and store information
@@ -954,11 +904,18 @@ static int zynqmp_r5_core_init(struct zynqmp_r5_cluster *cluster,
 {
 	struct device *dev = cluster->dev;
 	struct zynqmp_r5_core *r5_core;
-	int ret, i;
+	int ret = -EINVAL, i;
 
-	ret = zynqmp_r5_get_tcm_node(cluster);
-	if (ret < 0) {
-		dev_err(dev, "can't get tcm node, err %d\n", ret);
+	r5_core = cluster->r5_cores[0];
+
+	/* Maintain backward compatibility for zynqmp by using hardcode TCM address. */
+	if (of_find_property(r5_core->np, "reg", NULL))
+		ret = zynqmp_r5_get_tcm_node_from_dt(cluster);
+	else if (device_is_compatible(dev, "xlnx,zynqmp-r5fss"))
+		ret = zynqmp_r5_get_tcm_node(cluster);
+
+	if (ret) {
+		dev_err(dev, "can't get tcm, err %d\n", ret);
 		return ret;
 	}
 
@@ -973,12 +930,21 @@ static int zynqmp_r5_core_init(struct zynqmp_r5_cluster *cluster,
 			return ret;
 		}
 
-		ret = zynqmp_r5_set_mode(r5_core, fw_reg_val, tcm_mode);
-		if (ret) {
-			dev_err(dev, "failed to set r5 cluster mode %d, err %d\n",
-				cluster->mode, ret);
+		ret = zynqmp_pm_set_rpu_mode(r5_core->pm_domain_id, fw_reg_val);
+		if (ret < 0) {
+			dev_err(r5_core->dev, "failed to set RPU mode\n");
 			return ret;
 		}
+
+		if (of_find_property(dev_of_node(dev), "xlnx,tcm-mode", NULL) ||
+		    device_is_compatible(dev, "xlnx,zynqmp-r5fss")) {
+			ret = zynqmp_pm_set_tcm_config(r5_core->pm_domain_id,
+						       tcm_mode);
+			if (ret < 0) {
+				dev_err(r5_core->dev, "failed to configure TCM\n");
+				return ret;
+			}
+		}
 	}
 
 	return 0;
@@ -1023,16 +989,27 @@ static int zynqmp_r5_cluster_init(struct zynqmp_r5_cluster *cluster)
 	 * fail driver probe if either of that is not set in dts.
 	 */
 	if (cluster_mode == LOCKSTEP_MODE) {
-		tcm_mode = PM_RPU_TCM_COMB;
 		fw_reg_val = PM_RPU_MODE_LOCKSTEP;
 	} else if (cluster_mode == SPLIT_MODE) {
-		tcm_mode = PM_RPU_TCM_SPLIT;
 		fw_reg_val = PM_RPU_MODE_SPLIT;
 	} else {
 		dev_err(dev, "driver does not support cluster mode %d\n", cluster_mode);
 		return -EINVAL;
 	}
 
+	if (of_find_property(dev_node, "xlnx,tcm-mode", NULL)) {
+		ret = of_property_read_u32(dev_node, "xlnx,tcm-mode", (u32 *)&tcm_mode);
+		if (ret)
+			return ret;
+	} else if (device_is_compatible(dev, "xlnx,zynqmp-r5fss")) {
+		if (cluster_mode == LOCKSTEP_MODE)
+			tcm_mode = PM_RPU_TCM_COMB;
+		else
+			tcm_mode = PM_RPU_TCM_SPLIT;
+	} else {
+		tcm_mode = PM_RPU_TCM_COMB;
+	}
+
 	/*
 	 * Number of cores is decided by number of child nodes of
 	 * r5f subsystem node in dts. If Split mode is used in dts
@@ -1216,6 +1193,8 @@ static int zynqmp_r5_remoteproc_probe(struct platform_device *pdev)
 
 /* Match table for OF platform binding */
 static const struct of_device_id zynqmp_r5_remoteproc_match[] = {
+	{ .compatible = "xlnx,versal-net-r52fss", },
+	{ .compatible = "xlnx,versal-r5fss", },
 	{ .compatible = "xlnx,zynqmp-r5fss", },
 	{ /* end of list */ },
 };