ARM: Add Versatile Express SMP support

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 58080e1..4bb7730 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1121,10 +1121,11 @@
 config SMP
 	bool "Symmetric Multi-Processing (EXPERIMENTAL)"
 	depends on EXPERIMENTAL && (REALVIEW_EB_ARM11MP || REALVIEW_EB_A9MP ||\
-		 MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 || ARCH_U8500)
+		 MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 ||\
+		 ARCH_U8500 || ARCH_VEXPRESS_CA9X4)
 	depends on GENERIC_CLOCKEVENTS
 	select USE_GENERIC_SMP_HELPERS
-	select HAVE_ARM_SCU if (ARCH_REALVIEW || ARCH_OMAP4 || ARCH_U8500)
+	select HAVE_ARM_SCU if (ARCH_REALVIEW || ARCH_OMAP4 || ARCH_U8500 || ARCH_VEXPRESS_CA9X4)
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index 3c5e160..1b71b77 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -4,3 +4,5 @@
 
 obj-y					:= v2m.o
 obj-$(CONFIG_ARCH_VEXPRESS_CA9X4)	+= ct-ca9x4.o
+obj-$(CONFIG_SMP)			+= platsmp.o headsmp.o
+obj-$(CONFIG_LOCAL_TIMERS)		+= localtimer.o
diff --git a/arch/arm/mach-vexpress/headsmp.S b/arch/arm/mach-vexpress/headsmp.S
new file mode 100644
index 0000000..8a78ff6
--- /dev/null
+++ b/arch/arm/mach-vexpress/headsmp.S
@@ -0,0 +1,39 @@
+/*
+ *  linux/arch/arm/mach-vexpress/headsmp.S
+ *
+ *  Copyright (c) 2003 ARM Limited
+ *  All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+	__INIT
+
+/*
+ * Versatile Express specific entry point for secondary CPUs.  This
+ * provides a "holding pen" into which all secondary cores are held
+ * until we're ready for them to initialise.
+ */
+ENTRY(vexpress_secondary_startup)
+	mrc	p15, 0, r0, c0, c0, 5
+	and	r0, r0, #15
+	adr	r4, 1f
+	ldmia	r4, {r5, r6}
+	sub	r4, r4, r5
+	add	r6, r6, r4
+pen:	ldr	r7, [r6]
+	cmp	r7, r0
+	bne	pen
+
+	/*
+	 * we've been released from the holding pen: secondary_stack
+	 * should now contain the SVC stack for this core
+	 */
+	b	secondary_startup
+
+1:	.long	.
+	.long	pen_release
diff --git a/arch/arm/mach-vexpress/include/mach/smp.h b/arch/arm/mach-vexpress/include/mach/smp.h
new file mode 100644
index 0000000..72a9621
--- /dev/null
+++ b/arch/arm/mach-vexpress/include/mach/smp.h
@@ -0,0 +1,21 @@
+#ifndef __MACH_SMP_H
+#define __MACH_SMP_H
+
+#include <asm/hardware/gic.h>
+
+#define hard_smp_processor_id()				\
+	({						\
+		unsigned int cpunum;			\
+		__asm__("mrc p15, 0, %0, c0, c0, 5"	\
+			: "=r" (cpunum));		\
+		cpunum &= 0x0F;				\
+	})
+
+/*
+ * We use IRQ1 as the IPI
+ */
+static inline void smp_cross_call(const struct cpumask *mask)
+{
+	gic_raise_softirq(mask, 1);
+}
+#endif
diff --git a/arch/arm/mach-vexpress/localtimer.c b/arch/arm/mach-vexpress/localtimer.c
new file mode 100644
index 0000000..c0e3a59
--- /dev/null
+++ b/arch/arm/mach-vexpress/localtimer.c
@@ -0,0 +1,26 @@
+/*
+ *  linux/arch/arm/mach-vexpress/localtimer.c
+ *
+ *  Copyright (C) 2002 ARM Ltd.
+ *  All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/clockchips.h>
+
+#include <asm/smp_twd.h>
+#include <asm/localtimer.h>
+#include <mach/irqs.h>
+
+/*
+ * Setup the local clock events for a CPU.
+ */
+void __cpuinit local_timer_setup(struct clock_event_device *evt)
+{
+	evt->irq = IRQ_LOCALTIMER;
+	twd_timer_setup(evt);
+}
diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c
new file mode 100644
index 0000000..6709706
--- /dev/null
+++ b/arch/arm/mach-vexpress/platsmp.c
@@ -0,0 +1,190 @@
+/*
+ *  linux/arch/arm/mach-vexpress/platsmp.c
+ *
+ *  Copyright (C) 2002 ARM Ltd.
+ *  All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/jiffies.h>
+#include <linux/smp.h>
+#include <linux/io.h>
+
+#include <asm/cacheflush.h>
+#include <asm/localtimer.h>
+#include <asm/smp_scu.h>
+#include <asm/unified.h>
+
+#include <mach/ct-ca9x4.h>
+#include <mach/motherboard.h>
+#define V2M_PA_CS7 0x10000000
+
+#include "core.h"
+
+extern void vexpress_secondary_startup(void);
+
+/*
+ * control for which core is the next to come out of the secondary
+ * boot "holding pen"
+ */
+volatile int __cpuinitdata pen_release = -1;
+
+static void __iomem *scu_base_addr(void)
+{
+	return MMIO_P2V(A9_MPCORE_SCU);
+}
+
+static DEFINE_SPINLOCK(boot_lock);
+
+void __cpuinit platform_secondary_init(unsigned int cpu)
+{
+	trace_hardirqs_off();
+
+	/*
+	 * if any interrupts are already enabled for the primary
+	 * core (e.g. timer irq), then they will not have been enabled
+	 * for us: do so
+	 */
+	gic_cpu_init(0, gic_cpu_base_addr);
+
+	/*
+	 * let the primary processor know we're out of the
+	 * pen, then head off into the C entry point
+	 */
+	pen_release = -1;
+	smp_wmb();
+
+	/*
+	 * Synchronise with the boot thread.
+	 */
+	spin_lock(&boot_lock);
+	spin_unlock(&boot_lock);
+}
+
+int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
+{
+	unsigned long timeout;
+
+	/*
+	 * Set synchronisation state between this boot processor
+	 * and the secondary one
+	 */
+	spin_lock(&boot_lock);
+
+	/*
+	 * This is really belt and braces; we hold unintended secondary
+	 * CPUs in the holding pen until we're ready for them.  However,
+	 * since we haven't sent them a soft interrupt, they shouldn't
+	 * be there.
+	 */
+	pen_release = cpu;
+	__cpuc_flush_dcache_area((void *)&pen_release, sizeof(pen_release));
+	outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1));
+
+	/*
+	 * Send the secondary CPU a soft interrupt, thereby causing
+	 * the boot monitor to read the system wide flags register,
+	 * and branch to the address found there.
+	 */
+	smp_cross_call(cpumask_of(cpu));
+
+	timeout = jiffies + (1 * HZ);
+	while (time_before(jiffies, timeout)) {
+		smp_rmb();
+		if (pen_release == -1)
+			break;
+
+		udelay(10);
+	}
+
+	/*
+	 * now the secondary core is starting up let it run its
+	 * calibrations, then wait for it to finish
+	 */
+	spin_unlock(&boot_lock);
+
+	return pen_release != -1 ? -ENOSYS : 0;
+}
+
+/*
+ * Initialise the CPU possible map early - this describes the CPUs
+ * which may be present or become present in the system.
+ */
+void __init smp_init_cpus(void)
+{
+	void __iomem *scu_base = scu_base_addr();
+	unsigned int i, ncores;
+
+	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
+
+	/* sanity check */
+	if (ncores == 0) {
+		printk(KERN_ERR
+		       "vexpress: strange CM count of 0? Default to 1\n");
+
+		ncores = 1;
+	}
+
+	if (ncores > NR_CPUS) {
+		printk(KERN_WARNING
+		       "vexpress: no. of cores (%d) greater than configured "
+		       "maximum of %d - clipping\n",
+		       ncores, NR_CPUS);
+		ncores = NR_CPUS;
+	}
+
+	for (i = 0; i < ncores; i++)
+		set_cpu_possible(i, true);
+}
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+	unsigned int ncores = num_possible_cpus();
+	unsigned int cpu = smp_processor_id();
+	int i;
+
+	smp_store_cpu_info(cpu);
+
+	/*
+	 * are we trying to boot more cores than exist?
+	 */
+	if (max_cpus > ncores)
+		max_cpus = ncores;
+
+	/*
+	 * Initialise the present map, which describes the set of CPUs
+	 * actually populated at the present time.
+	 */
+	for (i = 0; i < max_cpus; i++)
+		set_cpu_present(i, true);
+
+	/*
+	 * Initialise the SCU if there are more than one CPU and let
+	 * them know where to start.
+	 */
+	if (max_cpus > 1) {
+		/*
+		 * Enable the local timer or broadcast device for the
+		 * boot CPU, but only if we have more than one CPU.
+		 */
+		percpu_timer_setup();
+
+		scu_enable(scu_base_addr());
+
+		/*
+		 * Write the address of secondary startup into the
+		 * system-wide flags register. The boot monitor waits
+		 * until it receives a soft interrupt, and then the
+		 * secondary CPU branches to this address.
+		 */
+		writel(~0, MMIO_P2V(V2M_SYS_FLAGSCLR));
+		writel(BSYM(virt_to_phys(vexpress_secondary_startup)),
+			MMIO_P2V(V2M_SYS_FLAGSSET));
+	}
+}