Merge master.kernel.org:/home/rmk/linux-2.6-arm

6 files changed, 192 insertions, 17 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index dc6d8342e5e6..6b12d71978de 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -349,6 +349,13 @@ config NR_CPUS
 	depends on SMP
 	default "4"
 
+config HOTPLUG_CPU
+	bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
+	depends on SMP && HOTPLUG && EXPERIMENTAL
+	help
+	  Say Y here to experiment with turning CPUs off and on.  CPUs
+	  can be controlled through /sys/devices/system/cpu.
+
 config PREEMPT
 	bool "Preemptible Kernel (EXPERIMENTAL)"
 	depends on EXPERIMENTAL
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 3284118f356b..9def4404e1f2 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -1050,3 +1050,34 @@ static int __init noirqdebug_setup(char *str)
 }
 
 __setup("noirqdebug", noirqdebug_setup);
+
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * The CPU has been marked offline.  Migrate IRQs off this CPU.  If
+ * the affinity settings do not allow other CPUs, force them onto any
+ * available CPU.
+ */
+void migrate_irqs(void)
+{
+	unsigned int i, cpu = smp_processor_id();
+
+	for (i = 0; i < NR_IRQS; i++) {
+		struct irqdesc *desc = irq_desc + i;
+
+		if (desc->cpu == cpu) {
+			unsigned int newcpu = any_online_cpu(desc->affinity);
+
+			if (newcpu == NR_CPUS) {
+				if (printk_ratelimit())
+					printk(KERN_INFO "IRQ%u no longer affine to CPU%u\n",
+					       i, cpu);
+
+				cpus_setall(desc->affinity);
+				newcpu = any_online_cpu(desc->affinity);
+			}
+
+			route_irq(desc, i, newcpu);
+		}
+	}
+}
+#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 409db6d5ec99..ba298277becd 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -26,6 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/kallsyms.h>
 #include <linux/init.h>
+#include <linux/cpu.h>
 
 #include <asm/system.h>
 #include <asm/io.h>
@@ -105,6 +106,14 @@ void cpu_idle(void)
 	/* endless idle loop with no priority at all */
 	while (1) {
 		void (*idle)(void) = pm_idle;
+
+#ifdef CONFIG_HOTPLUG_CPU
+		if (cpu_is_offline(smp_processor_id())) {
+			leds_event(led_idle_start);
+			cpu_die();
+		}
+#endif
+
 		if (!idle)
 			idle = default_idle;
 		preempt_disable();
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 826164945747..edb5a406922f 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -80,19 +80,23 @@ static DEFINE_SPINLOCK(smp_call_function_lock);
 
 int __cpuinit __cpu_up(unsigned int cpu)
 {
-	struct task_struct *idle;
+	struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu);
+	struct task_struct *idle = ci->idle;
 	pgd_t *pgd;
 	pmd_t *pmd;
 	int ret;
 
 	/*
-	 * Spawn a new process manually.  Grab a pointer to
-	 * its task struct so we can mess with it
+	 * Spawn a new process manually, if not already done.
+	 * Grab a pointer to its task struct so we can mess with it
 	 */
-	idle = fork_idle(cpu);
-	if (IS_ERR(idle)) {
-		printk(KERN_ERR "CPU%u: fork() failed\n", cpu);
-		return PTR_ERR(idle);
+	if (!idle) {
+		idle = fork_idle(cpu);
+		if (IS_ERR(idle)) {
+			printk(KERN_ERR "CPU%u: fork() failed\n", cpu);
+			return PTR_ERR(idle);
+		}
+		ci->idle = idle;
 	}
 
 	/*
@@ -155,6 +159,91 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	return ret;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * __cpu_disable runs on the processor to be shutdown.
+ */
+int __cpuexit __cpu_disable(void)
+{
+	unsigned int cpu = smp_processor_id();
+	struct task_struct *p;
+	int ret;
+
+	ret = mach_cpu_disable(cpu);
+	if (ret)
+		return ret;
+
+	/*
+	 * Take this CPU offline.  Once we clear this, we can't return,
+	 * and we must not schedule until we're ready to give up the cpu.
+	 */
+	cpu_clear(cpu, cpu_online_map);
+
+	/*
+	 * OK - migrate IRQs away from this CPU
+	 */
+	migrate_irqs();
+
+	/*
+	 * Flush user cache and TLB mappings, and then remove this CPU
+	 * from the vm mask set of all processes.
+	 */
+	flush_cache_all();
+	local_flush_tlb_all();
+
+	read_lock(&tasklist_lock);
+	for_each_process(p) {
+		if (p->mm)
+			cpu_clear(cpu, p->mm->cpu_vm_mask);
+	}
+	read_unlock(&tasklist_lock);
+
+	return 0;
+}
+
+/*
+ * called on the thread which is asking for a CPU to be shutdown -
+ * waits until shutdown has completed, or it is timed out.
+ */
+void __cpuexit __cpu_die(unsigned int cpu)
+{
+	if (!platform_cpu_kill(cpu))
+		printk("CPU%u: unable to kill\n", cpu);
+}
+
+/*
+ * Called from the idle thread for the CPU which has been shutdown.
+ *
+ * Note that we disable IRQs here, but do not re-enable them
+ * before returning to the caller. This is also the behaviour
+ * of the other hotplug-cpu capable cores, so presumably coming
+ * out of idle fixes this.
+ */
+void __cpuexit cpu_die(void)
+{
+	unsigned int cpu = smp_processor_id();
+
+	local_irq_disable();
+	idle_task_exit();
+
+	/*
+	 * actual CPU shutdown procedure is at least platform (if not
+	 * CPU) specific
+	 */
+	platform_cpu_die(cpu);
+
+	/*
+	 * Do not return to the idle loop - jump back to the secondary
+	 * cpu initialisation.  There's some initialisation which needs
+	 * to be repeated to undo the effects of taking the CPU offline.
+	 */
+	__asm__("mov	sp, %0\n"
+	"	b	secondary_start_kernel"
+		:
+		: "r" ((void *)current->thread_info + THREAD_SIZE - 8));
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
 /*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
@@ -236,6 +325,8 @@ void __init smp_prepare_boot_cpu(void)
 {
 	unsigned int cpu = smp_processor_id();
 
+	per_cpu(cpu_data, cpu).idle = current;
+
 	cpu_set(cpu, cpu_possible_map);
 	cpu_set(cpu, cpu_present_map);
 	cpu_set(cpu, cpu_online_map);
@@ -309,8 +400,8 @@ int smp_call_function_on_cpu(void (*func)(void *info), void *info, int retry,
 		printk(KERN_CRIT
 		       "CPU%u: smp_call_function timeout for %p(%p)\n"
 		       "      callmap %lx pending %lx, %swait\n",
-		       smp_processor_id(), func, info, callmap, data.pending,
-		       wait ? "" : "no ");
+		       smp_processor_id(), func, info, *cpus_addr(callmap),
+		       *cpus_addr(data.pending), wait ? "" : "no ");
 
 		/*
 		 * TRACE
diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c
index 01b264be5029..267bb07e39b7 100644
--- a/arch/arm/mach-realview/realview_eb.c
+++ b/arch/arm/mach-realview/realview_eb.c
@@ -43,14 +43,44 @@
 #include "clock.h"
 
 static struct map_desc realview_eb_io_desc[] __initdata = {
- { IO_ADDRESS(REALVIEW_SYS_BASE),	REALVIEW_SYS_BASE,	SZ_4K,	MT_DEVICE },
- { IO_ADDRESS(REALVIEW_GIC_CPU_BASE),	REALVIEW_GIC_CPU_BASE,	SZ_4K,	MT_DEVICE },
- { IO_ADDRESS(REALVIEW_GIC_DIST_BASE),	REALVIEW_GIC_DIST_BASE,	SZ_4K,	MT_DEVICE },
- { IO_ADDRESS(REALVIEW_SCTL_BASE),	REALVIEW_SCTL_BASE,	SZ_4K,	MT_DEVICE },
- { IO_ADDRESS(REALVIEW_TIMER0_1_BASE),	REALVIEW_TIMER0_1_BASE,	SZ_4K,	MT_DEVICE },
- { IO_ADDRESS(REALVIEW_TIMER2_3_BASE),	REALVIEW_TIMER2_3_BASE,	SZ_4K,	MT_DEVICE },
+	{
+		.virtual	= IO_ADDRESS(REALVIEW_SYS_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_SYS_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= IO_ADDRESS(REALVIEW_GIC_CPU_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_GIC_CPU_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= IO_ADDRESS(REALVIEW_GIC_DIST_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_GIC_DIST_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= IO_ADDRESS(REALVIEW_SCTL_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_SCTL_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= IO_ADDRESS(REALVIEW_TIMER0_1_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_TIMER0_1_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= IO_ADDRESS(REALVIEW_TIMER2_3_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_TIMER2_3_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	},
 #ifdef CONFIG_DEBUG_LL
- { IO_ADDRESS(REALVIEW_UART0_BASE),	REALVIEW_UART0_BASE,	SZ_4K,	MT_DEVICE },
+	{
+		.virtual	= IO_ADDRESS(REALVIEW_UART0_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_UART0_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}
 #endif
 };
 
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index fd079ff1fc53..c168f322ef8c 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -486,10 +486,17 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 
 	/*
 	 * Ask the machine support to map in the statically mapped devices.
-	 * After this point, we can start to touch devices again.
 	 */
 	if (mdesc->map_io)
 		mdesc->map_io();
+
+	/*
+	 * Finally flush the tlb again - this ensures that we're in a
+	 * consistent state wrt the writebuffer if the writebuffer needs
+	 * draining.  After this point, we can start to touch devices
+	 * again.
+	 */
+	local_flush_tlb_all();
 }
 
 /*