[PATCH v6 0/6] ARM: rockchip: add smp functionality

@@ -8,9 +8,17 @@ Required properties:
 
 - reg : SRAM iomem address range
 
+Optional properties:
+
+- mmio-sram-reserved: ordered list of reserved chunks inside the sram that
+  should not be used by the operating system.
+  Format is <base size>, <base size>, ...; with base being relative to the
+  reg property base.
+
 Example:
 
 sram: sram at 5c000000 {
 	compatible = "mmio-sram";
 	reg = <0x5c000000 0x40000>; /* 256 KiB SRAM at address 0x5c000000 */
+	mmio-sram-reserved = <0x0 0x100>; /* reserve 0x5c000000-0x5c000100 */
 };

@@ -36,13 +36,23 @@ struct sram_dev {
 	struct clk *clk;
 };
 
+struct sram_reserve {
+	unsigned long start;
+	unsigned long size;
+};
+
 static int sram_probe(struct platform_device *pdev)
 {
 	void __iomem *virt_base;
 	struct sram_dev *sram;
 	struct resource *res;
-	unsigned long size;
-	int ret;
+	unsigned long size, cur_start, cur_size;
+	const __be32 *reserved_list = NULL;
+	int reserved_size = 0;
+	struct sram_reserve *rblocks;
+	unsigned int nblocks;
+	int ret = 0;
+	int i;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	virt_base = devm_ioremap_resource(&pdev->dev, res);

@@ -65,19 +75,111 @@ static int sram_probe(struct platform_device *pdev)
 	if (!sram->pool)
 		return -ENOMEM;
 
-	ret = gen_pool_add_virt(sram->pool, (unsigned long)virt_base,
-				res->start, size, -1);
-	if (ret < 0) {
-		if (sram->clk)
-			clk_disable_unprepare(sram->clk);
-		return ret;
+	if (pdev->dev.of_node) {
+		reserved_list = of_get_property(pdev->dev.of_node,
+						"mmio-sram-reserved",
+						&reserved_size);
+		if (reserved_list) {
+			reserved_size /= sizeof(*reserved_list);
+			if (!reserved_size || reserved_size % 2) {
+				dev_warn(&pdev->dev, "wrong number of arguments in mmio-sram-reserved\n");
+				reserved_list = NULL;
+				reserved_size = 0;
+			}
+		}
+	}
+
+	/*
+	 * We need an additional block to mark the end of the memory region
+	 * after the reserved blocks from the dt are processed.
+	 */
+	nblocks = reserved_size / 2 + 1;
+	rblocks = kmalloc((nblocks) * sizeof(*rblocks), GFP_KERNEL);
+	if (!rblocks) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+
+	cur_start = 0;
+	for (i = 0; i < nblocks - 1; i++) {
+		rblocks[i].start = be32_to_cpu(*reserved_list++);
+		rblocks[i].size = be32_to_cpu(*reserved_list++);
+
+		if (rblocks[i].start < cur_start) {
+			dev_err(&pdev->dev,
+				"unsorted reserved list (0x%lx before current 0x%lx)\n",
+				rblocks[i].start, cur_start);
+			ret = -EINVAL;
+			goto err_chunks;
+		}
+
+		if (rblocks[i].start >= size) {
+			dev_err(&pdev->dev,
+				"reserved block at 0x%lx outside the sram size 0x%lx\n",
+				rblocks[i].start, size);
+			ret = -EINVAL;
+			goto err_chunks;
+		}
+
+		if (rblocks[i].start + rblocks[i].size > size) {
+			dev_warn(&pdev->dev,
+				 "reserved block at 0x%lx to large, trimming\n",
+				 rblocks[i].start);
+			rblocks[i].size = size - rblocks[i].start;
+		}
+
+		cur_start = rblocks[i].start + rblocks[i].size;
+
+		dev_dbg(&pdev->dev, "found reserved block 0x%lx-0x%lx\n",
+			rblocks[i].start,
+			rblocks[i].start + rblocks[i].size);
+	}
+
+	/* the last chunk marks the end of the region */
+	rblocks[nblocks - 1].start = size;
+	rblocks[nblocks - 1].size = 0;
+
+	cur_start = 0;
+	for (i = 0; i < nblocks; i++) {
+		/* current start is in a reserved block, so continue after it */
+		if (rblocks[i].start == cur_start) {
+			cur_start = rblocks[i].start + rblocks[i].size;
+			continue;
+		}
+
+		/*
+		 * allocate the space between the current starting
+		 * address and the following reserved block, or the
+		 * end of the region.
+		 */
+		cur_size = rblocks[i].start - cur_start;
+
+		dev_dbg(&pdev->dev, "adding chunk 0x%lx-0x%lx\n",
+			cur_start, cur_start + cur_size);
+		ret = gen_pool_add_virt(sram->pool,
+				(unsigned long)virt_base + cur_start,
+				res->start + cur_start, cur_size, -1);
+		if (ret < 0)
+			goto err_chunks;
+
+		/* next allocation after this reserved block */
+		cur_start = rblocks[i].start + rblocks[i].size;
 	}
 
+	kfree(rblocks);
+
 	platform_set_drvdata(pdev, sram);
 
 	dev_dbg(&pdev->dev, "SRAM pool: %ld KiB @ 0x%p\n", size / 1024, virt_base);
 
 	return 0;
+
+err_chunks:
+	kfree(rblocks);
+err_alloc:
+	if (sram->clk)
+		clk_disable_unprepare(sram->clk);
+	return ret;
 }
 
 static int sram_remove(struct platform_device *pdev)

@@ -26,6 +26,11 @@
 		compatible = "simple-bus";
 		ranges;
 
+		scu at 1013c000 {
+			compatible = "arm,cortex-a9-scu";
+			reg = <0x1013c000 0x100>;
+		};
+
 		gic: interrupt-controller at 1013d000 {
 			compatible = "arm,cortex-a9-gic";
 			interrupt-controller;

@@ -5,6 +5,7 @@ config ARCH_ROCKCHIP
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_GIC
 	select CACHE_L2X0
+	select HAVE_ARM_SCU
 	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select COMMON_CLK

@@ -0,0 +1,23 @@
+Rockchip SRAM for smp bringup:
+------------------------------
+
+Rockchip's smp-capable SoCs use the first part of the sram for the bringup
+of the cores. Once the core gets powered up it executes the code that is
+residing at the very beginning of the sram.
+
+Therefore a reserved section has to be added to the mmio-sram declaration.
+
+Required node properties:
+- compatible : should contain both "rockchip,rk3066-sram", "mmio-sram"
+  so that the smp code can select the correct sram node.
+
+The rest of the properties should follow the generic mmio-sram discription
+found in ../../misc/sram.txt
+
+Example:
+
+	sram: sram at 10080000 {
+		compatible = "rockchip,rk3066-sram", "mmio-sram";
+		reg = <0x10080000 0x10000>;
+		mmio-sram-reserved = <0x0 0x50>;
+	};

@@ -64,6 +64,12 @@
 			clock-names = "timer", "pclk";
 		};
 
+		sram: sram at 10080000 {
+			compatible = "rockchip,rk3066-sram", "mmio-sram";
+			reg = <0x10080000 0x10000>;
+			mmio-sram-reserved = <0x0 0x50>;
+		};
+
 		pinctrl at 20008000 {
 			compatible = "rockchip,rk3066a-pinctrl";
 			reg = <0x20008000 0x150>;

@@ -60,6 +60,12 @@
 			interrupts = <GIC_PPI 13 0xf04>;
 		};
 
+		sram: sram at 10080000 {
+			compatible = "rockchip,rk3066-sram", "mmio-sram";
+			reg = <0x10080000 0x8000>;
+			mmio-sram-reserved = <0x0 0x50>;
+		};
+
 		pinctrl at 20008000 {
 			compatible = "rockchip,rk3188-pinctrl";
 			reg = <0x20008000 0xa0>,

@@ -0,0 +1,16 @@
+Rockchip power-management-unit:
+-------------------------------
+
+The pmu is used to turn off and on different power domains of the SoCs
+This includes the power to the CPU cores.
+
+Required node properties:
+- compatible value : = "rockchip,rk3066-pmu";
+- reg : physical base address and the size of the registers window
+
+Example:
+
+	pmu at 20004000 {
+		compatible = "rockchip,rk3066-pmu";
+		reg = <0x20004000 0x100>;
+	};

@@ -31,6 +31,11 @@
 			reg = <0x1013c000 0x100>;
 		};
 
+		pmu at 20004000 {
+			compatible = "rockchip,rk3066-pmu";
+			reg = <0x20004000 0x100>;
+		};
+
 		gic: interrupt-controller at 1013d000 {
 			compatible = "arm,cortex-a9-gic";
 			interrupt-controller;

@@ -1 +1,2 @@
 obj-$(CONFIG_ARCH_ROCKCHIP) += rockchip.o
+obj-$(CONFIG_SMP) += headsmp.o platsmp.o

@@ -0,0 +1,22 @@
+/*
+ * Copyright (c) 2013 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+extern char rockchip_secondary_trampoline;
+extern char rockchip_secondary_trampoline_end;
+
+extern unsigned long rockchip_boot_fn;
+extern void rockchip_secondary_startup(void);
+
+extern struct smp_operations rockchip_smp_ops;

@@ -0,0 +1,30 @@
+/*
+ * Copyright (c) 2013 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+ENTRY(rockchip_secondary_startup)
+	bl	v7_invalidate_l1
+	b	secondary_startup
+ENDPROC(rockchip_secondary_startup)
+
+ENTRY(rockchip_secondary_trampoline)
+	ldr	pc, 1f
+ENDPROC(rockchip_secondary_trampoline)
+	.globl	rockchip_boot_fn
+rockchip_boot_fn:
+1:	.space	4
+
+ENTRY(rockchip_secondary_trampoline_end)

@@ -0,0 +1,208 @@
+/*
+ * Copyright (c) 2013 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#include <asm/cacheflush.h>
+#include <asm/smp_scu.h>
+#include <asm/smp_plat.h>
+#include <asm/mach/map.h>
+
+#include "core.h"
+
+static void __iomem *scu_base_addr;
+static void __iomem *sram_base_addr;
+static int ncores;
+
+#define PMU_PWRDN_CON		0x08
+#define PMU_PWRDN_ST		0x0c
+
+#define PMU_PWRDN_SCU		4
+
+static void __iomem *pmu_base_addr;
+
+static inline bool pmu_power_domain_is_on(int pd)
+{
+	return !(readl_relaxed(pmu_base_addr + PMU_PWRDN_ST) & BIT(pd));
+}
+
+static void pmu_set_power_domain(int pd, bool on)
+{
+	u32 val = readl_relaxed(pmu_base_addr + PMU_PWRDN_CON);
+	if (on)
+		val &= ~BIT(pd);
+	else
+		val |=  BIT(pd);
+	writel(val, pmu_base_addr + PMU_PWRDN_CON);
+
+	while (pmu_power_domain_is_on(pd) != on) { }
+}
+
+/*
+ * Handling of CPU cores
+ */
+
+static int __cpuinit rockchip_boot_secondary(unsigned int cpu,
+					     struct task_struct *idle)
+{
+	if (!sram_base_addr || !pmu_base_addr) {
+		pr_err("%s: sram or pmu missing for cpu boot\n", __func__);
+		return -ENXIO;
+	}
+
+	if (cpu >= ncores) {
+		pr_err("%s: cpu %d outside maximum number of cpus %d\n",
+							__func__, cpu, ncores);
+		return -ENXIO;
+	}
+
+	/* start the core */
+	pmu_set_power_domain(0 + cpu, true);
+
+	return 0;
+}
+
+/**
+ * rockchip_smp_prepare_sram - populate necessary sram block
+ * Starting cores execute the code residing at the start of the on-chip sram
+ * after power-on. Therefore make sure, this sram region is reserved and
+ * big enough. After this check, copy the trampoline code that directs the
+ * core to the real startup code in ram into the sram-region.
+ * @node: mmio-sram device node
+ */
+static int __init rockchip_smp_prepare_sram(struct device_node *node)
+{
+	unsigned int trampoline_sz = &rockchip_secondary_trampoline_end -
+					    &rockchip_secondary_trampoline;
+	const __be32 *reserved_list = NULL;
+	int reserved_size;
+	int rstart = -1;
+	unsigned int rsize;
+	unsigned int i;
+
+	reserved_list = of_get_property(node, "mmio-sram-reserved",
+					&reserved_size);
+	if (!reserved_list) {
+		pr_err("%s: wrong number of arguments in mmio-sram-reserved\n",
+		       __func__);
+		return -ENOENT;
+	}
+
+	reserved_size /= sizeof(*reserved_list);
+	if (!reserved_size || reserved_size % 2) {
+		pr_err("%s: wrong number of arguments in mmio-sram-reserved\n",
+		       __func__);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < reserved_size; i += 2) {
+		/* get the next reserved block */
+		rstart = be32_to_cpu(*reserved_list++);
+		rsize = be32_to_cpu(*reserved_list++);
+
+		if (!rstart)
+			break;
+	}
+
+	if (rstart) {
+		pr_err("%s: start of sram is not reserved from mmio-sram\n",
+		       __func__);
+		return -EINVAL;
+	}
+
+	if (rsize < trampoline_sz) {
+		pr_err("%s: reserved block with size 0x%x is to small for trampoline size 0x%x\n",
+		       __func__, rsize, trampoline_sz);
+		return -EINVAL;
+	}
+
+	sram_base_addr = of_iomap(node, 0);
+
+	/* set the boot function for the sram code */
+	rockchip_boot_fn = virt_to_phys(rockchip_secondary_startup);
+
+	/* copy the trampoline to sram, that runs during startup of the core */
+	memcpy(sram_base_addr, &rockchip_secondary_trampoline, trampoline_sz);
+	flush_cache_all();
+	outer_clean_range(0, trampoline_sz);
+
+	dsb_sev();
+
+	return 0;
+}
+
+static void __init rockchip_smp_prepare_cpus(unsigned int max_cpus)
+{
+	struct device_node *node;
+	unsigned int i;
+
+	node = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-scu");
+	if (!node) {
+		pr_err("%s: missing scu\n", __func__);
+		return;
+	}
+
+	scu_base_addr = of_iomap(node, 0);
+	if (!scu_base_addr) {
+		pr_err("%s: could not map scu registers\n", __func__);
+		return;
+	}
+
+	node = of_find_compatible_node(NULL, NULL, "rockchip,rk3066-sram");
+	if (!node) {
+		pr_err("%s: could not find sram dt node\n", __func__);
+		return;
+	}
+
+	if (rockchip_smp_prepare_sram(node))
+		return;
+
+	node = of_find_compatible_node(NULL, NULL, "rockchip,rk3066-pmu");
+	if (!node) {
+		pr_err("%s: could not find sram dt node\n", __func__);
+		return;
+	}
+
+	pmu_base_addr = of_iomap(node, 0);
+	if (!pmu_base_addr) {
+		pr_err("%s: could not map pmu registers\n", __func__);
+		return;
+	}
+
+	/* enable the SCU power domain */
+	pmu_set_power_domain(PMU_PWRDN_SCU, true);
+
+	/*
+	 * While the number of cpus is gathered from dt, also get the number
+	 * of cores from the scu to verify this value when booting the cores.
+	 */
+	ncores = scu_get_core_count(scu_base_addr);
+
+	scu_enable(scu_base_addr);
+
+	/* Make sure that all cores except the first are really off */
+	for (i = 1; i < ncores; i++)
+		pmu_set_power_domain(0 + i, false);
+}
+
+struct smp_operations rockchip_smp_ops __initdata = {
+	.smp_prepare_cpus	= rockchip_smp_prepare_cpus,
+	.smp_boot_secondary	= rockchip_boot_secondary,
+};

@@ -22,6 +22,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/hardware/cache-l2x0.h>
+#include "core.h"
 
 static void __init rockchip_dt_init(void)
 {

@@ -38,6 +39,7 @@ static const char * const rockchip_board_dt_compat[] = {
 };
 
 DT_MACHINE_START(ROCKCHIP_DT, "Rockchip Cortex-A9 (Device Tree)")
+	.smp		= smp_ops(rockchip_smp_ops),
 	.init_machine	= rockchip_dt_init,
 	.dt_compat	= rockchip_board_dt_compat,
 MACHINE_END

@@ -920,6 +920,38 @@ int of_property_read_u32_index(const struct device_node *np,
 EXPORT_SYMBOL_GPL(of_property_read_u32_index);
 
 /**
+ * of_property_count_u32_elems - Count the number of u32 values in a property
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u32 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u32 and -ENODATA if the
+ * property does not have a value.
+ */
+int of_property_count_u32_elems(const struct device_node *np,
+				const char *propname)
+{
+	int elem_size = sizeof(u32);
+	int len;
+	struct property *prop = of_find_property(np, propname, &len);
+
+	if (!prop)
+		return -EINVAL;
+	if (!prop->value)
+		return -ENODATA;
+
+	if (prop->length % elem_size != 0) {
+		pr_err("size of %s is not a multiple of u32\n", propname);
+		return -EINVAL;
+	}
+
+	return len / elem_size;
+}
+EXPORT_SYMBOL_GPL(of_property_count_u32_elems);
+
+/**
  * of_property_read_u8_array - Find and read an array of u8 from a property.
  *
  * @np:		device node from which the property value is to be read.

@@ -253,6 +253,8 @@ extern struct property *of_find_property(const struct device_node *np,
 extern int of_property_read_u32_index(const struct device_node *np,
 				       const char *propname,
 				       u32 index, u32 *out_value);
+extern int of_property_count_u32_elems(const struct device_node *np,
+				       const char *propname);
 extern int of_property_read_u8_array(const struct device_node *np,
 			const char *propname, u8 *out_values, size_t sz);
 extern int of_property_read_u16_array(const struct device_node *np,

@@ -432,6 +434,12 @@ static inline int of_property_read_u32_index(const struct device_node *np,
 	return -ENOSYS;
 }
 
+static inline int of_property_count_u32_elems(const struct device_node *np,
+			const char *propname)
+{
+	return -ENOSYS;
+}
+
 static inline int of_property_read_u8_array(const struct device_node *np,
 			const char *propname, u8 *out_values, size_t sz)
 {

@@ -862,6 +862,104 @@ struct device_node *of_find_node_by_phandle(phandle handle)
 EXPORT_SYMBOL(of_find_node_by_phandle);
 
 /**
+ * of_count_property_elems_of_size - Count the number of elements in a property
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ * @elem_size:	size of the individual element
+ */
+static int of_count_property_elems_of_size(const struct device_node *np,
+				const char *propname, int elem_size)
+{
+	struct property *prop = of_find_property(np, propname, NULL);
+
+	if (!prop)
+		return -EINVAL;
+	if (!prop->value)
+		return -ENODATA;
+
+	if (prop->length % elem_size != 0) {
+		pr_err("size of %s in node %s is not a multiple of %d\n",
+		       propname, np->name, elem_size);
+		return -EINVAL;
+	}
+
+	return prop->length / elem_size;
+}
+
+/**
+ * of_property_count_u8_elems - Count the number of u8 elements in a property
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u8 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u8 and -ENODATA if the
+ * property does not have a value.
+ */
+int of_property_count_u8_elems(const struct device_node *np,
+				const char *propname)
+{
+	return of_count_property_elems_of_size(np, propname, sizeof(u8));
+}
+EXPORT_SYMBOL_GPL(of_property_count_u8_elems);
+
+/**
+ * of_property_count_u16_elems - Count the number of u16 elements in a property
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u16 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u16 and -ENODATA if the
+ * property does not have a value.
+ */
+int of_property_count_u16_elems(const struct device_node *np,
+				const char *propname)
+{
+	return of_count_property_elems_of_size(np, propname, sizeof(u16));
+}
+EXPORT_SYMBOL_GPL(of_property_count_u16_elems);
+
+/**
+ * of_property_count_u32_elems - Count the number of u32 elements in a property
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u32 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u32 and -ENODATA if the
+ * property does not have a value.
+ */
+int of_property_count_u32_elems(const struct device_node *np,
+				const char *propname)
+{
+	return of_count_property_elems_of_size(np, propname, sizeof(u32));
+}
+EXPORT_SYMBOL_GPL(of_property_count_u32_elems);
+
+/**
+ * of_property_count_u64_elems - Count the number of u64 elements in a property
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u64 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u64 and -ENODATA if the
+ * property does not have a value.
+ */
+int of_property_count_u64_elems(const struct device_node *np,
+				const char *propname)
+{
+	return of_count_property_elems_of_size(np, propname, sizeof(u64));
+}
+EXPORT_SYMBOL_GPL(of_property_count_u64_elems);
+
+/**
  * of_find_property_value_of_size
  *
  * @np:		device node from which the property value is to be read.