NUMA Hotplug Emulator(v5) - Feedbacks & Responses

62 lines not on this page · raw message

Index: linux-hpe4/arch/x86/include/asm/cpu.h
===================================================================
@@ -27,6 +27,7 @@
 
 #ifdef CONFIG_HOTPLUG_CPU
 extern int arch_register_cpu(int num);
+extern int arch_register_cpu_node(int num, int nid);
 extern void arch_unregister_cpu(int);
 #endif
 

Index: linux-hpe4/arch/x86/kernel/topology.c
===================================================================
@@ -52,6 +52,15 @@
 }
 EXPORT_SYMBOL(arch_register_cpu);
 
+int __ref arch_register_cpu_node(int num, int nid)
+{
+	if (num)
+		per_cpu(cpu_devices, num).cpu.hotpluggable = 1;
+
+	return register_cpu_node(&per_cpu(cpu_devices, num).cpu, num, nid);
+}
+EXPORT_SYMBOL(arch_register_cpu_node);
+
 void arch_unregister_cpu(int num)
 {
 	unregister_cpu(&per_cpu(cpu_devices, num).cpu);

Index: linux-hpe4/drivers/base/cpu.c
===================================================================
@@ -208,17 +208,18 @@
 static SYSDEV_CLASS_ATTR(offline, 0444, print_cpus_offline, NULL);
 
 /*
- * register_cpu - Setup a sysfs device for a CPU.
+ * register_cpu_node - Setup a sysfs device for a CPU.
  * @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 @@
 	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)

Index: linux-hpe4/include/linux/cpu.h
===================================================================
@@ -30,7 +30,13 @@
 	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);

Index: linux-hpe4/arch/x86/kernel/acpi/boot.c
===================================================================
@@ -647,8 +647,44 @@
 }
 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--;

Index: linux-hpe4/arch/x86/kernel/smpboot.c
===================================================================
@@ -107,8 +107,6 @@
         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)])

99 lines not on this page · raw message

Index: linux-hpe4/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>

@@ -785,6 +786,19 @@
 }
 #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)
 {

Index: linux-hpe4/drivers/acpi/processor_driver.c
===================================================================
@@ -530,6 +530,14 @@
 		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 @@
 		goto err_remove_sysfs;
 	}
 
+out:
 	return 0;
 
 err_remove_sysfs:

Index: linux-hpe4/drivers/base/cpu.c
===================================================================
@@ -22,9 +22,15 @@
 };
 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)
 {

Index: linux-hpe4/include/linux/acpi.h
===================================================================
@@ -102,6 +102,7 @@
 #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 */
 

Index: linux-hpe4/include/linux/cpu.h
===================================================================
@@ -30,6 +30,8 @@
 	struct sys_device sysdev;
 };
 
+DECLARE_PER_CPU(struct sys_device *, cpu_sys_devices);
+
 extern int register_cpu_node(struct cpu *cpu, int num, int nid);
 
 static inline int register_cpu(struct cpu *cpu, int num)

@@ -149,6 +151,7 @@
 #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);

@@ -171,6 +174,7 @@
 /* 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

Index: linux-hpe4/arch/x86/include/asm/processor.h
===================================================================
@@ -113,6 +113,15 @@
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 #endif
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+	/*
+	 * Use a logic cpu to emulate a physical cpu's hotplug. We put the
+	 * logical cpu into a fake socket, assign a fake physical id to it,
+	 * and create a fake core.
+	 */
+	__u8		cpu_probe_on; /* A flag to enable cpu probe/release */
+#endif
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 #define X86_VENDOR_INTEL	0

Index: linux-hpe4/arch/x86/kernel/smpboot.c
===================================================================
@@ -97,6 +97,7 @@
  */
 static DEFINE_MUTEX(x86_cpu_hotplug_driver_mutex);
 
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
 void cpu_hotplug_driver_lock()
 {
         mutex_lock(&x86_cpu_hotplug_driver_mutex);

@@ -106,6 +107,7 @@
 {
         mutex_unlock(&x86_cpu_hotplug_driver_mutex);
 }
+#endif
 
 #else
 static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;

@@ -198,6 +200,8 @@
 {
 	int cpuid, phys_id;
 	unsigned long timeout;
+	u8 cpu_probe_on = 0;
+	struct cpuinfo_x86 *c;
 
 	/*
 	 * If waken up by an INIT in an 82489DX configuration

@@ -277,7 +281,20 @@
 	/*
 	 * Save our processor parameters
 	 */
+	c = &cpu_data(cpuid);
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+	cpu_probe_on = c->cpu_probe_on;
+	phys_id = c->phys_proc_id;
+#endif
+
 	smp_store_cpu_info(cpuid);
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+	if (cpu_probe_on) {
+		c->phys_proc_id = phys_id; /* restore the fake phys_proc_id */
+		c->cpu_core_id = 0; /* force the logical cpu to core 0 */
+		c->cpu_probe_on = cpu_probe_on;
+	}
+#endif
 
 	notify_cpu_starting(cpuid);
 

@@ -400,6 +417,11 @@
 {
 	int i;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	int cpu_probe_on = 0;
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+	cpu_probe_on = c->cpu_probe_on;
+#endif
 
 	cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
 

@@ -431,7 +453,8 @@
 
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
-		    per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
+		    per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i) &&
+			cpu_probe_on == 0) {
 			cpumask_set_cpu(i, c->llc_shared_map);
 			cpumask_set_cpu(cpu, cpu_data(i).llc_shared_map);
 		}

Index: linux-hpe4/arch/x86/kernel/topology.c
===================================================================
@@ -70,6 +70,36 @@
 }
 EXPORT_SYMBOL(arch_unregister_cpu);
 
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+/*
+ * Put the logical cpu into a new sokect, and encapsule it into core 0.
+ */
+static void fake_cpu_socket_info(int cpu)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	int i, phys_id = 0;
+
+	/* calculate the max phys_id */
+	for_each_present_cpu(i) {
+		struct cpuinfo_x86 *c = &cpu_data(i);
+		if (phys_id < c->phys_proc_id)
+			phys_id = c->phys_proc_id;
+	}
+
+	c->phys_proc_id = phys_id + 1; /* pick up a unused phys_proc_id */
+	c->cpu_core_id = 0; /* always put the logical cpu to core 0 */
+	c->cpu_probe_on = 1;
+}
+
+static void clear_cpu_socket_info(int cpu)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	c->phys_proc_id = 0;
+	c->cpu_core_id = 0;
+	c->cpu_probe_on = 0;
+}
+
+
 ssize_t arch_cpu_probe(const char *buf, size_t count)
 {
 	int nid = 0;

@@ -109,6 +139,7 @@
 	/* register cpu */
 	arch_register_cpu_node(selected, nid);
 	acpi_map_lsapic_emu(selected, nid);
+	fake_cpu_socket_info(selected);
 
 	return count;
 }

@@ -132,10 +163,13 @@
 
 	arch_unregister_cpu(cpu);
 	acpi_unmap_lsapic(cpu);
+	clear_cpu_socket_info(cpu);
+	set_cpu_present(cpu, true);
 
 	return count;
 }
 EXPORT_SYMBOL(arch_cpu_release);
+#endif CONFIG_ARCH_CPU_PROBE_RELEASE
 
 #else /* CONFIG_HOTPLUG_CPU */
 

86 lines not on this page · raw message

Index: linux-hpe4/include/linux/memory_hotplug.h
===================================================================
@@ -211,6 +211,14 @@
 extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
+#ifdef CONFIG_ARCH_MEMORY_PROBE
+extern ssize_t parse_memory_probe_store(const char *buf, size_t count);
+#else
+static inline ssize_t parse_memory_probe_store(const char *buf, size_t count)
+{
+	return 0;
+}
+#endif  /* CONFIG_ARCH_MEMORY_PROBE */
 
 #ifdef CONFIG_ARCH_MEMORY_PROBE
 extern ssize_t parse_memory_probe_store(const char *buf, size_t count);

Index: linux-hpe4/mm/memory_hotplug.c
===================================================================
@@ -982,4 +982,35 @@
 }
 
 module_init(node_debug_init);
+
+#ifdef CONFIG_ARCH_MEMORY_PROBE
+static struct dentry *memory_debug_root;
+
+static ssize_t debug_memory_probe_store(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	return parse_memory_probe_store(buf, count);
+}
+
+static const struct file_operations memory_probe_file_ops = {
+	.write		= debug_memory_probe_store,
+	.llseek		= generic_file_llseek,
+};
+
+static int __init memory_debug_init(void)
+{
+	memory_debug_root = debugfs_create_dir("memory", NULL);
+	if (!memory_debug_root)
+		return -ENOMEM;
+
+	if (!debugfs_create_file("probe", S_IWUSR, memory_debug_root,
+			NULL, &memory_probe_file_ops))
+		return -ENOMEM;
+
+	return 0;
+}
+
+module_init(memory_debug_init);
+
+#endif /* CONFIG_ARCH_MEMORY_PROBE */
 #endif /* CONFIG_DEBUG_FS */