From: Li Shaohua <shaohua.li@intel.com>
Boot a CPU at runtime.
Signed-off-by: Li Shaohua<shaohua.li@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
---
arch/i386/kernel/smpboot.c | 112 +++++++++++++++++++++++++++++++++------------
drivers/base/cpu.c | 8 ++-
include/asm-i386/smp.h | 3 +
3 files changed, 94 insertions(+), 29 deletions(-)
diff -puN arch/i386/kernel/smpboot.c~physical-cpu-hot-add arch/i386/kernel/smpboot.c
--- 25/arch/i386/kernel/smpboot.c~physical-cpu-hot-add 2005-06-18 02:48:48.000000000 -0700
+++ 25-akpm/arch/i386/kernel/smpboot.c 2005-06-18 02:48:48.000000000 -0700
@@ -91,6 +91,12 @@ cpumask_t cpu_callout_map;
EXPORT_SYMBOL(cpu_callout_map);
static cpumask_t smp_commenced_mask;
+/* TSC's upper 32 bits can't be written in eariler CPU (before prescott), there
+ * is no way to resync one AP against BP. TBD: for prescott and above, we
+ * should use IA64's algorithm
+ */
+static int __devinitdata tsc_sync_disabled;
+
/* Per CPU bogomips and other parameters */
struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned;
EXPORT_SYMBOL(cpu_data);
@@ -428,7 +434,7 @@ static void __devinit smp_callin(void)
/*
* Synchronize the TSC with the BP
*/
- if (cpu_has_tsc && cpu_khz)
+ if (cpu_has_tsc && cpu_khz && !tsc_sync_disabled)
synchronize_tsc_ap();
}
@@ -830,6 +836,31 @@ static inline int alloc_cpu_id(void)
return cpu;
}
+#ifdef CONFIG_HOTPLUG_CPU
+static struct task_struct * __devinitdata cpu_idle_tasks[NR_CPUS];
+static inline struct task_struct * alloc_idle_task(int cpu)
+{
+ struct task_struct *idle;
+
+ if ((idle = cpu_idle_tasks[cpu]) != NULL) {
+ /* initialize thread_struct. we really want to avoid destroy
+ * idle tread
+ */
+ idle->thread.esp = (unsigned long)(((struct pt_regs *)
+ (THREAD_SIZE + (unsigned long) idle->thread_info)) - 1);
+ init_idle(idle, cpu);
+ return idle;
+ }
+ idle = fork_idle(cpu);
+
+ if (!IS_ERR(idle))
+ cpu_idle_tasks[cpu] = idle;
+ return idle;
+}
+#else
+#define alloc_idle_task(cpu) fork_idle(cpu)
+#endif
+
static int __devinit do_boot_cpu(int apicid, int cpu)
/*
* NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
@@ -849,7 +880,7 @@ static int __devinit do_boot_cpu(int api
* We can't use kernel_thread since we must avoid to
* reschedule the child.
*/
- idle = fork_idle(cpu);
+ idle = alloc_idle_task(cpu);
if (IS_ERR(idle))
panic("failed fork for CPU %d", cpu);
idle->thread.eip = (unsigned long) start_secondary;
@@ -952,6 +983,55 @@ void cpu_exit_clear(void)
cpu_clear(cpu, smp_commenced_mask);
unmap_cpu_to_logical_apicid(cpu);
}
+
+struct warm_boot_cpu_info {
+ struct completion *complete;
+ int apicid;
+ int cpu;
+};
+
+static void __devinit do_warm_boot_cpu(void *p)
+{
+ struct warm_boot_cpu_info *info = p;
+ do_boot_cpu(info->apicid, info->cpu);
+ complete(info->complete);
+}
+
+int __devinit smp_prepare_cpu(int cpu)
+{
+ DECLARE_COMPLETION(done);
+ struct warm_boot_cpu_info info;
+ struct work_struct task;
+ int apicid, ret;
+
+ lock_cpu_hotplug();
+ apicid = x86_cpu_to_apicid[cpu];
+ if (apicid == BAD_APICID) {
+ ret = -ENODEV;
+ goto exit;
+ }
+
+ info.complete = &done;
+ info.apicid = apicid;
+ info.cpu = cpu;
+ INIT_WORK(&task, do_warm_boot_cpu, &info);
+
+ tsc_sync_disabled = 1;
+
+ /* init low mem mapping */
+ memcpy(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS,
+ sizeof(swapper_pg_dir[0]) * KERNEL_PGD_PTRS);
+ flush_tlb_all();
+ schedule_work(&task);
+ wait_for_completion(&done);
+
+ tsc_sync_disabled = 0;
+ zap_low_mappings();
+ ret = 0;
+exit:
+ unlock_cpu_hotplug();
+ return ret;
+}
#endif
static void smp_tune_scheduling (void)
@@ -1195,24 +1275,6 @@ void __devinit smp_prepare_boot_cpu(void
}
#ifdef CONFIG_HOTPLUG_CPU
-
-/* must be called with the cpucontrol mutex held */
-static int __devinit cpu_enable(unsigned int cpu)
-{
- /* get the target out of its holding state */
- per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
- wmb();
-
- /* wait for the processor to ack it. timeout? */
- while (!cpu_online(cpu))
- cpu_relax();
-
- fixup_irqs(cpu_online_map);
- /* counter the disable in fixup_irqs() */
- local_irq_enable();
- return 0;
-}
-
static void
remove_siblinginfo(int cpu)
{
@@ -1298,14 +1360,6 @@ int __devinit __cpu_up(unsigned int cpu)
return -EIO;
}
-#ifdef CONFIG_HOTPLUG_CPU
- /* Already up, and in cpu_quiescent now? */
- if (cpu_isset(cpu, smp_commenced_mask)) {
- cpu_enable(cpu);
- return 0;
- }
-#endif
-
local_irq_enable();
per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
/* Unleash the CPU! */
@@ -1321,10 +1375,12 @@ void __init smp_cpus_done(unsigned int m
setup_ioapic_dest();
#endif
zap_low_mappings();
+#ifndef CONFIG_HOTPLUG_CPU
/*
* Disable executability of the SMP trampoline:
*/
set_kernel_exec((unsigned long)trampoline_base, trampoline_exec);
+#endif
}
void __init smp_intr_init(void)
diff -puN drivers/base/cpu.c~physical-cpu-hot-add drivers/base/cpu.c
--- 25/drivers/base/cpu.c~physical-cpu-hot-add 2005-06-18 02:48:48.000000000 -0700
+++ 25-akpm/drivers/base/cpu.c 2005-06-18 02:48:48.000000000 -0700
@@ -16,6 +16,10 @@ struct sysdev_class cpu_sysdev_class = {
EXPORT_SYMBOL(cpu_sysdev_class);
#ifdef CONFIG_HOTPLUG_CPU
+#ifndef __HAVE_ARCH_SMP_PREPARE_CPU
+#define smp_prepare_cpu(cpu) (0)
+#endif
+
static ssize_t show_online(struct sys_device *dev, char *buf)
{
struct cpu *cpu = container_of(dev, struct cpu, sysdev);
@@ -36,7 +40,9 @@ static ssize_t store_online(struct sys_d
kobject_hotplug(&dev->kobj, KOBJ_OFFLINE);
break;
case '1':
- ret = cpu_up(cpu->sysdev.id);
+ ret = smp_prepare_cpu(cpu->sysdev.id);
+ if (ret == 0)
+ ret = cpu_up(cpu->sysdev.id);
break;
default:
ret = -EINVAL;
diff -puN include/asm-i386/smp.h~physical-cpu-hot-add include/asm-i386/smp.h
--- 25/include/asm-i386/smp.h~physical-cpu-hot-add 2005-06-18 02:48:48.000000000 -0700
+++ 25-akpm/include/asm-i386/smp.h 2005-06-18 02:48:48.000000000 -0700
@@ -51,6 +51,9 @@ extern u8 x86_cpu_to_apicid[];
#ifdef CONFIG_HOTPLUG_CPU
extern void cpu_exit_clear(void);
extern void cpu_uninit(void);
+
+#define __HAVE_ARCH_SMP_PREPARE_CPU
+extern int smp_prepare_cpu(int cpu);
#endif
/*
_