/*
* arch/s390/kernel/smp.c
*
- * Copyright IBM Corp. 1999,2007
+ * Copyright IBM Corp. 1999, 2009
* Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
* Martin Schwidefsky (schwidefsky@de.ibm.com)
* Heiko Carstens (heiko.carstens@de.ibm.com)
* cpu_number_map in other architectures.
*/
+#define KMSG_COMPONENT "cpu"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
#include <linux/module.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/cache.h>
#include <linux/interrupt.h>
+#include <linux/irqflags.h>
#include <linux/cpu.h>
#include <linux/timex.h>
#include <linux/bootmem.h>
#include <asm/timer.h>
#include <asm/lowcore.h>
#include <asm/sclp.h>
-#include <asm/cpu.h>
+#include <asm/cputime.h>
+#include <asm/vdso.h>
#include "entry.h"
-/*
- * An array with a pointer the lowcore of every CPU.
- */
-struct _lowcore *lowcore_ptr[NR_CPUS];
-EXPORT_SYMBOL(lowcore_ptr);
-
-cpumask_t cpu_online_map = CPU_MASK_NONE;
-EXPORT_SYMBOL(cpu_online_map);
-
-cpumask_t cpu_possible_map = CPU_MASK_ALL;
-EXPORT_SYMBOL(cpu_possible_map);
-
static struct task_struct *current_set[NR_CPUS];
static u8 smp_cpu_type;
static void smp_ext_bitcall(int, ec_bit_sig);
-/*
- * Structure and data for __smp_call_function_map(). This is designed to
- * minimise static memory requirements. It also looks cleaner.
- */
-static DEFINE_SPINLOCK(call_lock);
-
-struct call_data_struct {
- void (*func) (void *info);
- void *info;
- cpumask_t started;
- cpumask_t finished;
- int wait;
-};
-
-static struct call_data_struct *call_data;
-
-/*
- * 'Call function' interrupt callback
- */
-static void do_call_function(void)
-{
- void (*func) (void *info) = call_data->func;
- void *info = call_data->info;
- int wait = call_data->wait;
-
- cpu_set(smp_processor_id(), call_data->started);
- (*func)(info);
- if (wait)
- cpu_set(smp_processor_id(), call_data->finished);;
-}
-
-static void __smp_call_function_map(void (*func) (void *info), void *info,
- int wait, cpumask_t map)
-{
- struct call_data_struct data;
- int cpu, local = 0;
-
- /*
- * Can deadlock when interrupts are disabled or if in wrong context.
- */
- WARN_ON(irqs_disabled() || in_irq());
-
- /*
- * Check for local function call. We have to have the same call order
- * as in on_each_cpu() because of machine_restart_smp().
- */
- if (cpu_isset(smp_processor_id(), map)) {
- local = 1;
- cpu_clear(smp_processor_id(), map);
- }
-
- cpus_and(map, map, cpu_online_map);
- if (cpus_empty(map))
- goto out;
-
- data.func = func;
- data.info = info;
- data.started = CPU_MASK_NONE;
- data.wait = wait;
- if (wait)
- data.finished = CPU_MASK_NONE;
-
- call_data = &data;
-
- for_each_cpu_mask(cpu, map)
- smp_ext_bitcall(cpu, ec_call_function);
-
- /* Wait for response */
- while (!cpus_equal(map, data.started))
- cpu_relax();
- if (wait)
- while (!cpus_equal(map, data.finished))
- cpu_relax();
-out:
- if (local) {
- local_irq_disable();
- func(info);
- local_irq_enable();
- }
-}
-
-/*
- * smp_call_function:
- * @func: the function to run; this must be fast and non-blocking
- * @info: an arbitrary pointer to pass to the function
- * @wait: if true, wait (atomically) until function has completed on other CPUs
- *
- * Run a function on all other CPUs.
- *
- * You must not call this function with disabled interrupts, from a
- * hardware interrupt handler or from a bottom half.
- */
-int smp_call_function(void (*func) (void *info), void *info, int wait)
-{
- cpumask_t map;
-
- spin_lock(&call_lock);
- map = cpu_online_map;
- cpu_clear(smp_processor_id(), map);
- __smp_call_function_map(func, info, wait, map);
- spin_unlock(&call_lock);
- return 0;
-}
-EXPORT_SYMBOL(smp_call_function);
-
-/*
- * smp_call_function_single:
- * @cpu: the CPU where func should run
- * @func: the function to run; this must be fast and non-blocking
- * @info: an arbitrary pointer to pass to the function
- * @wait: if true, wait (atomically) until function has completed on other CPUs
- *
- * Run a function on one processor.
- *
- * You must not call this function with disabled interrupts, from a
- * hardware interrupt handler or from a bottom half.
- */
-int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
- int wait)
-{
- spin_lock(&call_lock);
- __smp_call_function_map(func, info, wait, cpumask_of_cpu(cpu));
- spin_unlock(&call_lock);
- return 0;
-}
-EXPORT_SYMBOL(smp_call_function_single);
-
-/**
- * smp_call_function_mask(): Run a function on a set of other CPUs.
- * @mask: The set of cpus to run on. Must not include the current cpu.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
- *
- * Returns 0 on success, else a negative status code.
- *
- * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
- int wait)
-{
- spin_lock(&call_lock);
- cpu_clear(smp_processor_id(), mask);
- __smp_call_function_map(func, info, wait, mask);
- spin_unlock(&call_lock);
- return 0;
-}
-EXPORT_SYMBOL(smp_call_function_mask);
-
void smp_send_stop(void)
{
int cpu, rc;
/* Disable all interrupts/machine checks */
__load_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK);
-
- /* write magic number to zero page (absolute 0) */
- lowcore_ptr[smp_processor_id()]->panic_magic = __PANIC_MAGIC;
+ trace_hardirqs_off();
/* stop all processors */
for_each_online_cpu(cpu) {
bits = xchg(&S390_lowcore.ext_call_fast, 0);
if (test_bit(ec_call_function, &bits))
- do_call_function();
+ generic_smp_call_function_interrupt();
+
+ if (test_bit(ec_call_function_single, &bits))
+ generic_smp_call_function_single_interrupt();
}
/*
udelay(10);
}
+void arch_send_call_function_ipi(cpumask_t mask)
+{
+ int cpu;
+
+ for_each_cpu_mask(cpu, mask)
+ smp_ext_bitcall(cpu, ec_call_function);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+ smp_ext_bitcall(cpu, ec_call_function_single);
+}
+
#ifndef CONFIG_64BIT
/*
* this function sends a 'purge tlb' signal to another CPU.
*/
#define CPU_INIT_NO 1
-#if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_ZFCPDUMP_MODULE)
+#ifdef CONFIG_ZFCPDUMP
/*
* zfcpdump_prefix_array holds prefix registers for the following scenario:
if (ipl_info.type != IPL_TYPE_FCP_DUMP)
return;
if (cpu >= NR_CPUS) {
- printk(KERN_WARNING "Registers for cpu %i not saved since dump "
- "kernel was compiled with NR_CPUS=%i\n", cpu, NR_CPUS);
+ pr_warning("CPU %i exceeds the maximum %i and is excluded from "
+ "the dump\n", cpu, NR_CPUS - 1);
return;
}
zfcpdump_save_areas[cpu] = kmalloc(sizeof(union save_area), GFP_KERNEL);
static inline void smp_get_save_area(unsigned int cpu, unsigned int phy_cpu) { }
-#endif /* CONFIG_ZFCPDUMP || CONFIG_ZFCPDUMP_MODULE */
+#endif /* CONFIG_ZFCPDUMP */
static int cpu_stopped(int cpu)
{
{
int cpu_id, logical_cpu;
- logical_cpu = first_cpu(avail);
- if (logical_cpu == NR_CPUS)
+ logical_cpu = cpumask_first(&avail);
+ if (logical_cpu >= nr_cpu_ids)
return 0;
for (cpu_id = 0; cpu_id <= 65535; cpu_id++) {
if (cpu_known(cpu_id))
continue;
cpu_set(logical_cpu, cpu_present_map);
smp_cpu_state[logical_cpu] = CPU_STATE_CONFIGURED;
- logical_cpu = next_cpu(logical_cpu, avail);
- if (logical_cpu == NR_CPUS)
+ logical_cpu = cpumask_next(logical_cpu, &avail);
+ if (logical_cpu >= nr_cpu_ids)
break;
}
return 0;
int cpu_id, logical_cpu, cpu;
int rc;
- logical_cpu = first_cpu(avail);
- if (logical_cpu == NR_CPUS)
+ logical_cpu = cpumask_first(&avail);
+ if (logical_cpu >= nr_cpu_ids)
return 0;
info = kmalloc(sizeof(*info), GFP_KERNEL);
if (!info)
smp_cpu_state[logical_cpu] = CPU_STATE_STANDBY;
else
smp_cpu_state[logical_cpu] = CPU_STATE_CONFIGURED;
- logical_cpu = next_cpu(logical_cpu, avail);
- if (logical_cpu == NR_CPUS)
+ logical_cpu = cpumask_next(logical_cpu, &avail);
+ if (logical_cpu >= nr_cpu_ids)
break;
}
out:
c_cpus = 1;
s_cpus = 0;
- boot_cpu_addr = S390_lowcore.cpu_data.cpu_addr;
+ boot_cpu_addr = __cpu_logical_map[0];
info = kmalloc(sizeof(*info), GFP_KERNEL);
if (!info)
panic("smp_detect_cpus failed to allocate memory\n");
}
out:
kfree(info);
- printk(KERN_INFO "CPUs: %d configured, %d standby\n", c_cpus, s_cpus);
+ pr_info("%d configured CPUs, %d standby CPUs\n", c_cpus, s_cpus);
get_online_cpus();
__smp_rescan_cpus();
put_online_cpus();
preempt_disable();
/* Enable TOD clock interrupts on the secondary cpu. */
init_cpu_timer();
-#ifdef CONFIG_VIRT_TIMER
/* Enable cpu timer interrupts on the secondary cpu. */
init_cpu_vtimer();
-#endif
/* Enable pfault pseudo page faults on this cpu. */
pfault_init();
+ /* call cpu notifiers */
+ notify_cpu_starting(smp_processor_id());
/* Mark this cpu as online */
- spin_lock(&call_lock);
+ ipi_call_lock();
cpu_set(smp_processor_id(), cpu_online_map);
- spin_unlock(&call_lock);
+ ipi_call_unlock();
/* Switch on interrupts */
local_irq_enable();
/* Print info about this processor */
- print_cpu_info(&S390_lowcore.cpu_data);
+ print_cpu_info();
/* cpu_idle will call schedule for us */
cpu_idle();
return 0;
save_area = get_zeroed_page(GFP_KERNEL);
if (!save_area)
- goto out_save_area;
+ goto out;
lowcore->extended_save_area_addr = (u32) save_area;
}
+#else
+ if (vdso_alloc_per_cpu(cpu, lowcore))
+ goto out;
#endif
lowcore_ptr[cpu] = lowcore;
return 0;
-#ifndef CONFIG_64BIT
-out_save_area:
- free_page(panic_stack);
-#endif
out:
+ free_page(panic_stack);
free_pages(async_stack, ASYNC_ORDER);
free_pages((unsigned long) lowcore, lc_order);
return -ENOMEM;
}
-#ifdef CONFIG_HOTPLUG_CPU
static void smp_free_lowcore(int cpu)
{
struct _lowcore *lowcore;
#ifndef CONFIG_64BIT
if (MACHINE_HAS_IEEE)
free_page((unsigned long) lowcore->extended_save_area_addr);
+#else
+ vdso_free_per_cpu(cpu, lowcore);
#endif
free_page(lowcore->panic_stack - PAGE_SIZE);
free_pages(lowcore->async_stack - ASYNC_SIZE, ASYNC_ORDER);
free_pages((unsigned long) lowcore, lc_order);
lowcore_ptr[cpu] = NULL;
}
-#endif /* CONFIG_HOTPLUG_CPU */
/* Upping and downing of CPUs */
int __cpuinit __cpu_up(unsigned int cpu)
struct _lowcore *cpu_lowcore;
struct stack_frame *sf;
sigp_ccode ccode;
+ u32 lowcore;
if (smp_cpu_state[cpu] != CPU_STATE_CONFIGURED)
return -EIO;
if (smp_alloc_lowcore(cpu))
return -ENOMEM;
-
- ccode = signal_processor_p((__u32)(unsigned long)(lowcore_ptr[cpu]),
- cpu, sigp_set_prefix);
- if (ccode) {
- printk("sigp_set_prefix failed for cpu %d "
- "with condition code %d\n",
- (int) cpu, (int) ccode);
- return -EIO;
- }
+ do {
+ ccode = signal_processor(cpu, sigp_initial_cpu_reset);
+ if (ccode == sigp_busy)
+ udelay(10);
+ if (ccode == sigp_not_operational)
+ goto err_out;
+ } while (ccode == sigp_busy);
+
+ lowcore = (u32)(unsigned long)lowcore_ptr[cpu];
+ while (signal_processor_p(lowcore, cpu, sigp_set_prefix) == sigp_busy)
+ udelay(10);
idle = current_set[cpu];
cpu_lowcore = lowcore_ptr[cpu];
: : "a" (&cpu_lowcore->access_regs_save_area) : "memory");
cpu_lowcore->percpu_offset = __per_cpu_offset[cpu];
cpu_lowcore->current_task = (unsigned long) idle;
- cpu_lowcore->cpu_data.cpu_nr = cpu;
+ cpu_lowcore->cpu_nr = cpu;
cpu_lowcore->kernel_asce = S390_lowcore.kernel_asce;
- cpu_lowcore->ipl_device = S390_lowcore.ipl_device;
+ cpu_lowcore->machine_flags = S390_lowcore.machine_flags;
+ cpu_lowcore->ftrace_func = S390_lowcore.ftrace_func;
eieio();
while (signal_processor(cpu, sigp_restart) == sigp_busy)
while (!cpu_online(cpu))
cpu_relax();
return 0;
+
+err_out:
+ smp_free_lowcore(cpu);
+ return -EIO;
}
static int __init setup_possible_cpus(char *s)
int pcpus, cpu;
pcpus = simple_strtoul(s, NULL, 0);
- cpu_possible_map = cpumask_of_cpu(0);
- for (cpu = 1; cpu < pcpus && cpu < NR_CPUS; cpu++)
- cpu_set(cpu, cpu_possible_map);
+ init_cpu_possible(cpumask_of(0));
+ for (cpu = 1; cpu < pcpus && cpu < nr_cpu_ids; cpu++)
+ set_cpu_possible(cpu, true);
return 0;
}
early_param("possible_cpus", setup_possible_cpus);
while (!smp_cpu_not_running(cpu))
cpu_relax();
smp_free_lowcore(cpu);
- printk(KERN_INFO "Processor %d spun down\n", cpu);
+ pr_info("Processor %d stopped\n", cpu);
}
void cpu_die(void)
/* request the 0x1201 emergency signal external interrupt */
if (register_external_interrupt(0x1201, do_ext_call_interrupt) != 0)
panic("Couldn't request external interrupt 0x1201");
- print_cpu_info(&S390_lowcore.cpu_data);
+ print_cpu_info();
/* Reallocate current lowcore, but keep its contents. */
lc_order = sizeof(long) == 8 ? 1 : 0;
lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, lc_order);
panic_stack = __get_free_page(GFP_KERNEL);
async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER);
+ BUG_ON(!lowcore || !panic_stack || !async_stack);
#ifndef CONFIG_64BIT
if (MACHINE_HAS_IEEE)
save_area = get_zeroed_page(GFP_KERNEL);
#ifndef CONFIG_64BIT
if (MACHINE_HAS_IEEE)
lowcore->extended_save_area_addr = (u32) save_area;
+#else
+ if (vdso_alloc_per_cpu(smp_processor_id(), lowcore))
+ BUG();
#endif
set_prefix((u32)(unsigned long) lowcore);
local_mcck_enable();
{
struct s390_idle_data *idle;
unsigned long long idle_count;
+ unsigned int sequence;
idle = &per_cpu(s390_idle, dev->id);
- spin_lock_irq(&idle->lock);
+repeat:
+ sequence = idle->sequence;
+ smp_rmb();
+ if (sequence & 1)
+ goto repeat;
idle_count = idle->idle_count;
- spin_unlock_irq(&idle->lock);
+ if (idle->idle_enter)
+ idle_count++;
+ smp_rmb();
+ if (idle->sequence != sequence)
+ goto repeat;
return sprintf(buf, "%llu\n", idle_count);
}
static SYSDEV_ATTR(idle_count, 0444, show_idle_count, NULL);
struct sysdev_attribute *attr, char *buf)
{
struct s390_idle_data *idle;
- unsigned long long new_time;
+ unsigned long long now, idle_time, idle_enter;
+ unsigned int sequence;
idle = &per_cpu(s390_idle, dev->id);
- spin_lock_irq(&idle->lock);
- if (idle->in_idle) {
- new_time = get_clock();
- idle->idle_time += new_time - idle->idle_enter;
- idle->idle_enter = new_time;
- }
- new_time = idle->idle_time;
- spin_unlock_irq(&idle->lock);
- return sprintf(buf, "%llu\n", new_time >> 12);
+ now = get_clock();
+repeat:
+ sequence = idle->sequence;
+ smp_rmb();
+ if (sequence & 1)
+ goto repeat;
+ idle_time = idle->idle_time;
+ idle_enter = idle->idle_enter;
+ if (idle_enter != 0ULL && idle_enter < now)
+ idle_time += now - idle_enter;
+ smp_rmb();
+ if (idle->sequence != sequence)
+ goto repeat;
+ return sprintf(buf, "%llu\n", idle_time >> 12);
}
static SYSDEV_ATTR(idle_time_us, 0444, show_idle_time, NULL);
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
idle = &per_cpu(s390_idle, cpu);
- spin_lock_irq(&idle->lock);
- idle->idle_enter = 0;
- idle->idle_time = 0;
- idle->idle_count = 0;
- spin_unlock_irq(&idle->lock);
+ memset(idle, 0, sizeof(struct s390_idle_data));
if (sysfs_create_group(&s->kobj, &cpu_online_attr_group))
return NOTIFY_BAD;
break;
return rc;
}
-static ssize_t __ref rescan_store(struct sys_device *dev,
- struct sysdev_attribute *attr,
- const char *buf,
+static ssize_t __ref rescan_store(struct sysdev_class *class, const char *buf,
size_t count)
{
int rc;
rc = smp_rescan_cpus();
return rc ? rc : count;
}
-static SYSDEV_ATTR(rescan, 0200, NULL, rescan_store);
+static SYSDEV_CLASS_ATTR(rescan, 0200, NULL, rescan_store);
#endif /* CONFIG_HOTPLUG_CPU */
-static ssize_t dispatching_show(struct sys_device *dev,
- struct sysdev_attribute *attr,
- char *buf)
+static ssize_t dispatching_show(struct sysdev_class *class, char *buf)
{
ssize_t count;
return count;
}
-static ssize_t dispatching_store(struct sys_device *dev,
- struct sysdev_attribute *attr,
- const char *buf, size_t count)
+static ssize_t dispatching_store(struct sysdev_class *dev, const char *buf,
+ size_t count)
{
int val, rc;
char delim;
put_online_cpus();
return rc ? rc : count;
}
-static SYSDEV_ATTR(dispatching, 0644, dispatching_show, dispatching_store);
+static SYSDEV_CLASS_ATTR(dispatching, 0644, dispatching_show,
+ dispatching_store);
+
+/*
+ * If the resume kernel runs on another cpu than the suspended kernel,
+ * we have to switch the cpu IDs in the logical map.
+ */
+void smp_switch_boot_cpu_in_resume(u32 resume_phys_cpu_id,
+ struct _lowcore *suspend_lowcore)
+{
+ int cpu, suspend_cpu_id, resume_cpu_id;
+ u32 suspend_phys_cpu_id;
+
+ suspend_phys_cpu_id = __cpu_logical_map[suspend_lowcore->cpu_nr];
+ suspend_cpu_id = suspend_lowcore->cpu_nr;
+
+ for_each_present_cpu(cpu) {
+ if (__cpu_logical_map[cpu] == resume_phys_cpu_id) {
+ resume_cpu_id = cpu;
+ goto found;
+ }
+ }
+ panic("Could not find resume cpu in logical map.\n");
+
+found:
+ printk("Resume cpu ID: %i/%i\n", resume_phys_cpu_id, resume_cpu_id);
+ printk("Suspend cpu ID: %i/%i\n", suspend_phys_cpu_id, suspend_cpu_id);
+
+ __cpu_logical_map[resume_cpu_id] = suspend_phys_cpu_id;
+ __cpu_logical_map[suspend_cpu_id] = resume_phys_cpu_id;
+
+ lowcore_ptr[suspend_cpu_id]->cpu_addr = resume_phys_cpu_id;
+}
+
+u32 smp_get_phys_cpu_id(void)
+{
+ return __cpu_logical_map[smp_processor_id()];
+}
static int __init topology_init(void)
{
register_cpu_notifier(&smp_cpu_nb);
#ifdef CONFIG_HOTPLUG_CPU
- rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
- &attr_rescan.attr);
+ rc = sysdev_class_create_file(&cpu_sysdev_class, &attr_rescan);
if (rc)
return rc;
#endif
- rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
- &attr_dispatching.attr);
+ rc = sysdev_class_create_file(&cpu_sysdev_class, &attr_dispatching);
if (rc)
return rc;
for_each_present_cpu(cpu) {