From: Shaohui Zheng <[email protected]>
Subject: hotplug emulator: support cpu probe/release in x86
Add cpu interface probe/release under sysfs for x86. User can use this
interface to emulate the cpu hot-add process, it is for cpu hotplug
test purpose. Add a kernel option CONFIG_ARCH_CPU_PROBE_RELEASE for this
feature.
This interface provides a mechanism to emulate cpu hotplug with software
methods, it becomes possible to do cpu hotplug automation and stress
testing.
Directive:
*) Reserve CPU throu grub parameter like:
maxcpus=4
the rest CPUs will not be initiliazed.
*) Probe CPU
we can use the probe interface to hot-add new CPUs:
echo nid > /sys/devices/system/cpu/probe
*) Release a CPU
echo cpu > /sys/devices/system/cpu/release
A reserved CPU will be hot-added to the specified node.
1) nid == 0, the CPU will be added to the real node which the CPU
should be in
2) nid != 0, add the CPU to node nid even through it is a fake node.
Signed-off-by: Shaohui Zheng <[email protected]>
Signed-off-by: Haicheng Li <[email protected]>
---
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index b185091..339ac2d 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -28,6 +28,9 @@ struct x86_cpu {
#ifdef CONFIG_HOTPLUG_CPU
extern int arch_register_cpu(int num);
extern void arch_unregister_cpu(int);
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+extern int arch_register_cpu_emu(int num, int nid);
+#endif
#endif
DECLARE_PER_CPU(int, cpu_state);
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index c05872a..28f052c 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -647,8 +647,44 @@ int __ref acpi_map_lsapic(acpi_handle handle, int *pcpu)
}
EXPORT_SYMBOL(acpi_map_lsapic);
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+static void acpi_map_cpu2node_emu(int cpu, int physid, int nid)
+{
+#ifdef CONFIG_ACPI_NUMA
+#ifdef CONFIG_X86_64
+ apicid_to_node[physid] = nid;
+ numa_set_node(cpu, nid);
+#else /* CONFIG_X86_32 */
+ apicid_2_node[physid] = nid;
+ cpu_to_node_map[cpu] = nid;
+#endif
+#endif
+}
+
+static u16 cpu_to_apicid_saved[CONFIG_NR_CPUS];
+int __ref acpi_map_lsapic_emu(int pcpu, int nid)
+{
+ /* backup cpu apicid to array cpu_to_apicid_saved */
+ if (cpu_to_apicid_saved[pcpu] == 0 &&
+ per_cpu(x86_cpu_to_apicid, pcpu) != BAD_APICID)
+ cpu_to_apicid_saved[pcpu] = per_cpu(x86_cpu_to_apicid, pcpu);
+
+ per_cpu(x86_cpu_to_apicid, pcpu) = cpu_to_apicid_saved[pcpu];
+ acpi_map_cpu2node_emu(pcpu, per_cpu(x86_cpu_to_apicid, pcpu), nid);
+
+ return pcpu;
+}
+EXPORT_SYMBOL(acpi_map_lsapic_emu);
+#endif
+
int acpi_unmap_lsapic(int cpu)
{
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+ /* backup cpu apicid to array cpu_to_apicid_saved */
+ if (cpu_to_apicid_saved[cpu] == 0 &&
+ per_cpu(x86_cpu_to_apicid, cpu) != BAD_APICID)
+ cpu_to_apicid_saved[cpu] = per_cpu(x86_cpu_to_apicid, cpu);
+#endif
per_cpu(x86_cpu_to_apicid, cpu) = -1;
set_cpu_present(cpu, false);
num_processors--;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8b3bfc4..170d9b9 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -107,8 +107,6 @@ void cpu_hotplug_driver_unlock()
mutex_unlock(&x86_cpu_hotplug_driver_mutex);
}
-ssize_t arch_cpu_probe(const char *buf, size_t count) { return -1; }
-ssize_t arch_cpu_release(const char *buf, size_t count) { return -1; }
#else
static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
#define get_idle_for_cpu(x) (idle_thread_array[(x)])
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index f716cd9..515f08a 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -29,6 +29,9 @@
#include <linux/mmzone.h>
#include <linux/init.h>
#include <linux/smp.h>
+#include <linux/cpu.h>
+#include <linux/topology.h>
+#include <linux/acpi.h>
#include <asm/cpu.h>
static DEFINE_PER_CPU(struct x86_cpu, cpu_devices);
@@ -37,6 +40,11 @@ static DEFINE_PER_CPU(struct x86_cpu, cpu_devices);
/*
* Add nid(NUMA node id) as parameter for cpu hotplug emulation. It supports
* to register a CPU to any nodes.
+ *
+ * nid is a special parameter, it has 2 different branches:
+ * 1) when nid == NUMA_NO_NODE, the CPU will be registered into the normal node
+ * which it should be in.
+ * 2) nid != NUMA_NO_NODE, it will be registered into the specified node.
*/
static int __ref __arch_register_cpu(int num, int nid)
{
@@ -52,8 +60,23 @@ static int __ref __arch_register_cpu(int num, int nid)
if (num)
per_cpu(cpu_devices, num).cpu.hotpluggable = 1;
- return register_cpu(&per_cpu(cpu_devices, num).cpu, num);
+ if (nid == NUMA_NO_NODE)
+ return register_cpu(&per_cpu(cpu_devices, num).cpu, num);
+ else
+ return register_cpu_emu(&per_cpu(cpu_devices, num).cpu, num, nid);
+}
+
+/*
+ * Emulated version of function arch_register_cpu
+ * Parameter:
+ * num: cpu_id
+ * nid: emulated numa id
+ */
+int __ref arch_register_cpu_emu(int num, int nid)
+{
+ return __arch_register_cpu(num, nid);
}
+EXPORT_SYMBOL(arch_register_cpu_emu);
int __ref arch_register_cpu(int num)
{
@@ -66,6 +89,74 @@ void arch_unregister_cpu(int num)
unregister_cpu(&per_cpu(cpu_devices, num).cpu);
}
EXPORT_SYMBOL(arch_unregister_cpu);
+
+ssize_t arch_cpu_probe(const char *buf, size_t count)
+{
+ int nid = 0;
+ int num = 0, selected = 0;
+
+ /* check parameters */
+ if (!buf || count < 2)
+ return -EPERM;
+
+ nid = simple_strtoul(buf, NULL, 0);
+ printk(KERN_DEBUG "Add a cpu to node : %d\n", nid);
+
+ if (nid < 0 || nid > nr_node_ids - 1) {
+ printk(KERN_ERR "Invalid NUMA node id: %d (0 <= nid < %d).\n",
+ nid, nr_node_ids);
+ return -EPERM;
+ }
+
+ if (!node_online(nid)) {
+ printk(KERN_ERR "NUMA node %d is not online, give up.\n", nid);
+ return -EPERM;
+ }
+
+ /* find first uninitialized cpu */
+ for_each_present_cpu(num) {
+ if (per_cpu(cpu_sys_devices, num) == NULL) {
+ selected = num;
+ break;
+ }
+ }
+
+ if (selected >= num_possible_cpus()) {
+ printk(KERN_ERR "No free cpu, give up cpu probing.\n");
+ return -EPERM;
+ }
+
+ /* register cpu */
+ arch_register_cpu_emu(selected, nid);
+ acpi_map_lsapic_emu(selected, nid);
+
+ return count;
+}
+EXPORT_SYMBOL(arch_cpu_probe);
+
+ssize_t arch_cpu_release(const char *buf, size_t count)
+{
+ int cpu = 0;
+
+ cpu = simple_strtoul(buf, NULL, 0);
+ /* cpu 0 is not hotplugable */
+ if (cpu == 0) {
+ printk(KERN_ERR "can not release cpu 0.\n");
+ return -EPERM;
+ }
+
+ if (cpu_online(cpu)) {
+ printk(KERN_DEBUG "offline cpu %d.\n", cpu);
+ cpu_down(cpu);
+ }
+
+ arch_unregister_cpu(cpu);
+ acpi_unmap_lsapic(cpu);
+
+ return count;
+}
+EXPORT_SYMBOL(arch_cpu_release);
+
#else /* CONFIG_HOTPLUG_CPU */
static int __init arch_register_cpu(int num)
@@ -83,8 +174,14 @@ static int __init topology_init(void)
register_one_node(i);
#endif
- for_each_present_cpu(i)
- arch_register_cpu(i);
+ /*
+ * when cpu hotplug emulation enabled, register the online cpu only,
+ * the rests are reserved for cpu probe.
+ */
+ for_each_present_cpu(i) {
+ if ((cpu_hpe_on && cpu_online(i)) || !cpu_hpe_on)
+ arch_register_cpu(i);
+ }
return 0;
}
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 2485fd2..fff27ae 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -12,6 +12,7 @@
#include <linux/module.h>
#include <linux/nodemask.h>
#include <linux/sched.h>
+#include <linux/cpu.h>
#include <asm/e820.h>
#include <asm/proto.h>
@@ -914,6 +915,19 @@ void __init init_cpu_to_node(void)
}
#endif
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+static __init int cpu_hpe_setup(char *opt)
+{
+ if (!opt)
+ return -EINVAL;
+
+ if (!strncmp(opt, "on", 2) || !strncmp(opt, "1", 1))
+ cpu_hpe_on = 1;
+
+ return 0;
+}
+early_param("cpu_hpe", cpu_hpe_setup);
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
void __cpuinit numa_set_node(int cpu, int node)
{
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 347eb21..39b4026 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -530,6 +530,14 @@ static int __cpuinit acpi_processor_add(struct acpi_device *device)
goto err_free_cpumask;
sysdev = get_cpu_sysdev(pr->id);
+ /*
+ * Reserve cpu for hotplug emulation, the reserved cpu can be hot-added
+ * throu the cpu probe interface. Return directly.
+ */
+ if (sysdev == NULL) {
+ goto out;
+ }
+
if (sysfs_create_link(&device->dev.kobj, &sysdev->kobj, "sysdev")) {
result = -EFAULT;
goto err_remove_fs;
@@ -570,6 +578,7 @@ static int __cpuinit acpi_processor_add(struct acpi_device *device)
goto err_remove_sysfs;
}
+out:
return 0;
err_remove_sysfs:
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index adbfd04..a113d01 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -22,9 +22,15 @@ struct sysdev_class cpu_sysdev_class = {
};
EXPORT_SYMBOL(cpu_sysdev_class);
-static DEFINE_PER_CPU(struct sys_device *, cpu_sys_devices);
+DEFINE_PER_CPU(struct sys_device *, cpu_sys_devices);
#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * cpu_hpe_on is a switch to enable/disable cpu hotplug emulation. it is
+ * disabled in default, we can enable it throu grub parameter cpu_hpe=on
+ */
+int cpu_hpe_on;
+
static ssize_t show_online(struct sys_device *dev, struct sysdev_attribute *attr,
char *buf)
{
@@ -80,6 +86,7 @@ void unregister_cpu(struct cpu *cpu)
}
#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+
static ssize_t cpu_probe_store(struct sysdev_class *class,
struct sysdev_class_attribute *attr,
const char *buf,
@@ -250,6 +257,18 @@ int __cpuinit register_cpu(struct cpu *cpu, int num)
return __register_cpu(cpu, num, cpu_to_node(num));
}
+/*
+ * Register cpu to the specified NUMA node
+ *
+ * emulated version of function register_cpu, but is more flexible. it supports
+ * an extra parameter nid, We can register a CPU to any specified node throu
+ * this function.
+ */
+int __cpuinit register_cpu_emu(struct cpu *cpu, int num, int nid)
+{
+ return __register_cpu(cpu, num, nid);
+}
+
struct sys_device *get_cpu_sysdev(unsigned cpu)
{
if (cpu < nr_cpu_ids && cpu_possible(cpu))
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index c227757..858c980 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -102,6 +102,7 @@ void acpi_numa_arch_fixup(void);
#ifdef CONFIG_ACPI_HOTPLUG_CPU
/* Arch dependent functions for cpu hotplug support */
int acpi_map_lsapic(acpi_handle handle, int *pcpu);
+int acpi_map_lsapic_emu(int pcpu, int nid);
int acpi_unmap_lsapic(int cpu);
#endif /* CONFIG_ACPI_HOTPLUG_CPU */
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 4823af6..8447a81 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -30,7 +30,10 @@ struct cpu {
struct sys_device sysdev;
};
+DECLARE_PER_CPU(struct sys_device *, cpu_sys_devices);
+
extern int register_cpu(struct cpu *cpu, int num);
+extern int register_cpu_emu(struct cpu *cpu, int num, int nid);
extern struct sys_device *get_cpu_sysdev(unsigned cpu);
extern int cpu_add_sysdev_attr(struct sysdev_attribute *attr);
@@ -143,6 +146,7 @@ extern void put_online_cpus(void);
#define register_hotcpu_notifier(nb) register_cpu_notifier(nb)
#define unregister_hotcpu_notifier(nb) unregister_cpu_notifier(nb)
int cpu_down(unsigned int cpu);
+extern int cpu_hpe_on;
#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
extern void cpu_hotplug_driver_lock(void);
@@ -165,6 +169,7 @@ static inline void cpu_hotplug_driver_unlock(void)
/* These aren't inline functions due to a GCC bug. */
#define register_hotcpu_notifier(nb) ({ (void)(nb); 0; })
#define unregister_hotcpu_notifier(nb) ({ (void)(nb); })
+static int cpu_hpe_on;
#endif /* CONFIG_HOTPLUG_CPU */
#ifdef CONFIG_PM_SLEEP_SMP
diff --git a/mm/Kconfig b/mm/Kconfig
index a01a679..f88690c 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -162,6 +162,17 @@ config NODE_HOTPLUG_EMU
N is the number of hidden nodes, size is the memory size per
hidden node. This is only useful for debugging.
+config ARCH_CPU_PROBE_RELEASE
+ def_bool y
+ bool "CPU hotplug emulation"
+ depends on NUMA_HOTPLUG_EMU
+ ---help---
+ Enable cpu hotplug emulation. Reserve cpu with grub parameter
+ "maxcpus=N", where N is the initial CPU number, the rest physical
+ CPUs will not be initialized; there is a probe/release interface
+ is for cpu hot-add/hot-remove to specified node in software method.
+ This is for debuging and testing purpose
+
#
# If we have space for more page flags then we can enable additional
# optimizations and functionality.
--
Thanks & Regards,
Shaohui
On Sat, Nov 13, 2010 at 02:16:11PM +0800, Shaohui Zheng wrote:
> @@ -37,6 +40,11 @@ static DEFINE_PER_CPU(struct x86_cpu, cpu_devices);
> /*
> * Add nid(NUMA node id) as parameter for cpu hotplug emulation. It supports
> * to register a CPU to any nodes.
> + *
> + * nid is a special parameter, it has 2 different branches:
> + * 1) when nid == NUMA_NO_NODE, the CPU will be registered into the normal node
> + * which it should be in.
> + * 2) nid != NUMA_NO_NODE, it will be registered into the specified node.
> */
> static int __ref __arch_register_cpu(int num, int nid)
> {
> @@ -52,8 +60,23 @@ static int __ref __arch_register_cpu(int num, int nid)
> if (num)
> per_cpu(cpu_devices, num).cpu.hotpluggable = 1;
>
> - return register_cpu(&per_cpu(cpu_devices, num).cpu, num);
> + if (nid == NUMA_NO_NODE)
> + return register_cpu(&per_cpu(cpu_devices, num).cpu, num);
> + else
> + return register_cpu_emu(&per_cpu(cpu_devices, num).cpu, num, nid);
> +}
> +
This looks like an incredibly painful interface. How about scrapping all
of this _emu() mess and just reworking the register_cpu() interface?
Something like:
---
drivers/base/cpu.c | 7 ++++---
include/linux/cpu.h | 8 +++++++-
2 files changed, 11 insertions(+), 4 deletions(-)
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 251acea..039fd44 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -212,13 +212,14 @@ static SYSDEV_CLASS_ATTR(offline, 0444, print_cpus_offline, NULL);
* @cpu - cpu->hotpluggable field set to 1 will generate a control file in
* sysfs for this CPU.
* @num - CPU number to use when creating the device.
+ * @nid - Node ID to use, if any.
*
* Initialize and register the CPU device.
*/
-int __cpuinit register_cpu(struct cpu *cpu, int num)
+int __cpuinit register_cpu_node(struct cpu *cpu, int num, int nid)
{
int error;
- cpu->node_id = cpu_to_node(num);
+ cpu->node_id = nid;
cpu->sysdev.id = num;
cpu->sysdev.cls = &cpu_sysdev_class;
@@ -229,7 +230,7 @@ int __cpuinit register_cpu(struct cpu *cpu, int num)
if (!error)
per_cpu(cpu_sys_devices, num) = &cpu->sysdev;
if (!error)
- register_cpu_under_node(num, cpu_to_node(num));
+ register_cpu_under_node(num, nid);
#ifdef CONFIG_KEXEC
if (!error)
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 4823af6..d9e19c8 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -30,7 +30,13 @@ struct cpu {
struct sys_device sysdev;
};
-extern int register_cpu(struct cpu *cpu, int num);
+extern int register_cpu_node(struct cpu *cpu, int num, int nid);
+
+static inline int register_cpu(struct cpu *cpu, int num)
+{
+ return register_cpu_node(cpu, num, cpu_to_node(num));
+}
+
extern struct sys_device *get_cpu_sysdev(unsigned cpu);
extern int cpu_add_sysdev_attr(struct sysdev_attribute *attr);