#include <linux/irq.h>
#include <linux/percpu.h>
#include <linux/clockchips.h>
+#include <linux/completion.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
#include <asm/cacheflush.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
+#include <asm/exception.h>
+#include <asm/idmap.h>
+#include <asm/topology.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
IPI_CPU_STOP,
};
-static inline void identity_mapping_add(pgd_t *pgd, unsigned long start,
- unsigned long end)
-{
- unsigned long addr, prot;
- pmd_t *pmd;
-
- prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE;
- if (cpu_architecture() <= CPU_ARCH_ARMv5TEJ && !cpu_is_xscale())
- prot |= PMD_BIT4;
-
- for (addr = start & PGDIR_MASK; addr < end;) {
- pmd = pmd_offset(pgd + pgd_index(addr), addr);
- pmd[0] = __pmd(addr | prot);
- addr += SECTION_SIZE;
- pmd[1] = __pmd(addr | prot);
- addr += SECTION_SIZE;
- flush_pmd_entry(pmd);
- outer_clean_range(__pa(pmd), __pa(pmd + 1));
- }
-}
-
-static inline void identity_mapping_del(pgd_t *pgd, unsigned long start,
- unsigned long end)
-{
- unsigned long addr;
- pmd_t *pmd;
-
- for (addr = start & PGDIR_MASK; addr < end; addr += PGDIR_SIZE) {
- pmd = pmd_offset(pgd + pgd_index(addr), addr);
- pmd[0] = __pmd(0);
- pmd[1] = __pmd(0);
- clean_pmd_entry(pmd);
- outer_clean_range(__pa(pmd), __pa(pmd + 1));
- }
-}
-
int __cpuinit __cpu_up(unsigned int cpu)
{
struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu);
struct task_struct *idle = ci->idle;
- pgd_t *pgd;
int ret;
/*
init_idle(idle, cpu);
}
- /*
- * Allocate initial page tables to allow the new CPU to
- * enable the MMU safely. This essentially means a set
- * of our "standard" page tables, with the addition of
- * a 1:1 mapping for the physical address of the kernel.
- */
- pgd = pgd_alloc(&init_mm);
- if (!pgd)
- return -ENOMEM;
-
- if (PHYS_OFFSET != PAGE_OFFSET) {
-#ifndef CONFIG_HOTPLUG_CPU
- identity_mapping_add(pgd, __pa(__init_begin), __pa(__init_end));
-#endif
- identity_mapping_add(pgd, __pa(_stext), __pa(_etext));
- identity_mapping_add(pgd, __pa(_sdata), __pa(_edata));
- }
-
/*
* We need to tell the secondary core where to find
* its stack and the page tables.
*/
secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
- secondary_data.pgdir = virt_to_phys(pgd);
+ secondary_data.pgdir = virt_to_phys(idmap_pgd);
+ secondary_data.swapper_pg_dir = virt_to_phys(swapper_pg_dir);
__cpuc_flush_dcache_area(&secondary_data, sizeof(secondary_data));
outer_clean_range(__pa(&secondary_data), __pa(&secondary_data + 1));
barrier();
}
- if (!cpu_online(cpu))
+ if (!cpu_online(cpu)) {
+ pr_crit("CPU%u: failed to come online\n", cpu);
ret = -EIO;
+ }
+ } else {
+ pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
}
secondary_data.stack = NULL;
secondary_data.pgdir = 0;
- if (PHYS_OFFSET != PAGE_OFFSET) {
-#ifndef CONFIG_HOTPLUG_CPU
- identity_mapping_del(pgd, __pa(__init_begin), __pa(__init_end));
-#endif
- identity_mapping_del(pgd, __pa(_stext), __pa(_etext));
- identity_mapping_del(pgd, __pa(_sdata), __pa(_edata));
- }
-
- pgd_free(&init_mm, pgd);
-
- if (ret) {
- printk(KERN_CRIT "CPU%u: processor failed to boot\n", cpu);
-
- /*
- * FIXME: We need to clean up the new idle thread. --rmk
- */
- }
-
return ret;
}
#ifdef CONFIG_HOTPLUG_CPU
+static void percpu_timer_stop(void);
+
/*
* __cpu_disable runs on the processor to be shutdown.
*/
/*
* Stop the local timer for this CPU.
*/
- local_timer_stop();
+ percpu_timer_stop();
/*
* Flush user cache and TLB mappings, and then remove this CPU
return 0;
}
+static DECLARE_COMPLETION(cpu_died);
+
/*
* called on the thread which is asking for a CPU to be shutdown -
* waits until shutdown has completed, or it is timed out.
*/
void __cpu_die(unsigned int cpu)
{
+ if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+ pr_err("CPU%u: cpu didn't die\n", cpu);
+ return;
+ }
+ printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);
+
if (!platform_cpu_kill(cpu))
printk("CPU%u: unable to kill\n", cpu);
}
{
unsigned int cpu = smp_processor_id();
- local_irq_disable();
idle_task_exit();
+ local_irq_disable();
+ mb();
+
+ /* Tell __cpu_die() that this CPU is now safe to dispose of */
+ complete(&cpu_died);
+
/*
* actual CPU shutdown procedure is at least platform (if not
- * CPU) specific
+ * CPU) specific.
*/
platform_cpu_die(cpu);
* to be repeated to undo the effects of taking the CPU offline.
*/
__asm__("mov sp, %0\n"
+ " mov fp, #0\n"
" b secondary_start_kernel"
:
: "r" (task_stack_page(current) + THREAD_SIZE - 8));
}
#endif /* CONFIG_HOTPLUG_CPU */
+/*
+ * Called by both boot and secondaries to move global data into
+ * per-processor storage.
+ */
+static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
+{
+ struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
+
+ cpu_info->loops_per_jiffy = loops_per_jiffy;
+
+ store_cpu_topology(cpuid);
+}
+
+static void percpu_timer_setup(void);
+
/*
* This is the secondary CPU boot entry. We're using this CPUs
* idle thread stack, but a set of temporary page tables.
* All kernel threads share the same mm context; grab a
* reference and switch to it.
*/
- atomic_inc(&mm->mm_users);
atomic_inc(&mm->mm_count);
current->active_mm = mm;
cpumask_set_cpu(cpu, mm_cpumask(mm));
cpu_init();
preempt_disable();
+ trace_hardirqs_off();
/*
* Give the platform a chance to do its own initialisation.
*/
platform_secondary_init(cpu);
- /*
- * Enable local interrupts.
- */
notify_cpu_starting(cpu);
- local_irq_enable();
- local_fiq_enable();
-
- /*
- * Setup the percpu timer for this CPU.
- */
- percpu_timer_setup();
calibrate_delay();
smp_store_cpu_info(cpu);
/*
- * OK, now it's safe to let the boot CPU continue
+ * OK, now it's safe to let the boot CPU continue. Wait for
+ * the CPU migration code to notice that the CPU is online
+ * before we continue.
*/
set_cpu_online(cpu, true);
/*
- * OK, it's off to the idle thread for us
+ * Setup the percpu timer for this CPU.
*/
- cpu_idle();
-}
+ percpu_timer_setup();
-/*
- * Called by both boot and secondaries to move global data into
- * per-processor storage.
- */
-void __cpuinit smp_store_cpu_info(unsigned int cpuid)
-{
- struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
+ local_irq_enable();
+ local_fiq_enable();
- cpu_info->loops_per_jiffy = loops_per_jiffy;
+ /*
+ * OK, it's off to the idle thread for us
+ */
+ cpu_idle();
}
void __init smp_cpus_done(unsigned int max_cpus)
per_cpu(cpu_data, cpu).idle = current;
}
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+ unsigned int ncores = num_possible_cpus();
+
+ init_cpu_topology();
+
+ smp_store_cpu_info(smp_processor_id());
+
+ /*
+ * are we trying to boot more cores than exist?
+ */
+ if (max_cpus > ncores)
+ max_cpus = ncores;
+ if (ncores > 1 && max_cpus) {
+ /*
+ * Enable the local timer or broadcast device for the
+ * boot CPU, but only if we have more than one CPU.
+ */
+ percpu_timer_setup();
+
+ /*
+ * Initialise the present map, which describes the set of CPUs
+ * actually populated at the present time. A platform should
+ * re-initialize the map in platform_smp_prepare_cpus() if
+ * present != possible (e.g. physical hotplug).
+ */
+ init_cpu_present(&cpu_possible_map);
+
+ /*
+ * Initialise the SCU if there are more than one CPU
+ * and let them know where to start.
+ */
+ platform_smp_prepare_cpus(max_cpus);
+ }
+}
+
+static void (*smp_cross_call)(const struct cpumask *, unsigned int);
+
+void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
+{
+ smp_cross_call = fn;
+}
+
void arch_send_call_function_ipi_mask(const struct cpumask *mask)
{
smp_cross_call(mask, IPI_CALL_FUNC);
smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
}
+static const char *ipi_types[NR_IPI] = {
+#define S(x,s) [x - IPI_TIMER] = s
+ S(IPI_TIMER, "Timer broadcast interrupts"),
+ S(IPI_RESCHEDULE, "Rescheduling interrupts"),
+ S(IPI_CALL_FUNC, "Function call interrupts"),
+ S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
+ S(IPI_CPU_STOP, "CPU stop interrupts"),
+};
+
void show_ipi_list(struct seq_file *p, int prec)
{
- unsigned int cpu;
+ unsigned int cpu, i;
- seq_printf(p, "%*s: ", prec, "IPI");
+ for (i = 0; i < NR_IPI; i++) {
+ seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);
+
+ for_each_present_cpu(cpu)
+ seq_printf(p, "%10u ",
+ __get_irq_stat(cpu, ipi_irqs[i]));
+
+ seq_printf(p, " %s\n", ipi_types[i]);
+ }
+}
+
+u64 smp_irq_stat_cpu(unsigned int cpu)
+{
+ u64 sum = 0;
+ int i;
- for_each_present_cpu(cpu)
- seq_printf(p, "%10u ", __get_irq_stat(cpu, ipi_irqs));
+ for (i = 0; i < NR_IPI; i++)
+ sum += __get_irq_stat(cpu, ipi_irqs[i]);
- seq_printf(p, " Inter-processor interrupts\n");
+ return sum;
}
/*
static void ipi_timer(void)
{
struct clock_event_device *evt = &__get_cpu_var(percpu_clockevent);
- irq_enter();
evt->event_handler(evt);
- irq_exit();
}
-#ifdef CONFIG_LOCAL_TIMERS
-asmlinkage void __exception do_local_timer(struct pt_regs *regs)
-{
- struct pt_regs *old_regs = set_irq_regs(regs);
- int cpu = smp_processor_id();
-
- if (local_timer_ack()) {
- __inc_irq_stat(cpu, local_timer_irqs);
- ipi_timer();
- }
-
- set_irq_regs(old_regs);
-}
-
-void show_local_irqs(struct seq_file *p, int prec)
-{
- unsigned int cpu;
-
- seq_printf(p, "%*s: ", prec, "LOC");
-
- for_each_present_cpu(cpu)
- seq_printf(p, "%10u ", __get_irq_stat(cpu, local_timer_irqs));
-
- seq_printf(p, " Local timer interrupts\n");
-}
-#endif
-
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
static void smp_timer_broadcast(const struct cpumask *mask)
{
#define smp_timer_broadcast NULL
#endif
-#ifndef CONFIG_LOCAL_TIMERS
static void broadcast_timer_set_mode(enum clock_event_mode mode,
struct clock_event_device *evt)
{
}
-static void local_timer_setup(struct clock_event_device *evt)
+static void __cpuinit broadcast_timer_setup(struct clock_event_device *evt)
{
evt->name = "dummy_timer";
evt->features = CLOCK_EVT_FEAT_ONESHOT |
clockevents_register_device(evt);
}
+
+static struct local_timer_ops *lt_ops;
+
+#ifdef CONFIG_LOCAL_TIMERS
+int local_timer_register(struct local_timer_ops *ops)
+{
+ if (lt_ops)
+ return -EBUSY;
+
+ lt_ops = ops;
+ return 0;
+}
#endif
-void __cpuinit percpu_timer_setup(void)
+static void __cpuinit percpu_timer_setup(void)
{
unsigned int cpu = smp_processor_id();
struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
evt->cpumask = cpumask_of(cpu);
evt->broadcast = smp_timer_broadcast;
- local_timer_setup(evt);
+ if (!lt_ops || lt_ops->setup(evt))
+ broadcast_timer_setup(evt);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * The generic clock events code purposely does not stop the local timer
+ * on CPU_DEAD/CPU_DEAD_FROZEN hotplug events, so we have to do it
+ * manually here.
+ */
+static void percpu_timer_stop(void)
+{
+ unsigned int cpu = smp_processor_id();
+ struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
+
+ if (lt_ops)
+ lt_ops->stop(evt);
}
+#endif
-static DEFINE_SPINLOCK(stop_lock);
+static DEFINE_RAW_SPINLOCK(stop_lock);
/*
* ipi_cpu_stop - handle IPI from smp_send_stop()
{
if (system_state == SYSTEM_BOOTING ||
system_state == SYSTEM_RUNNING) {
- spin_lock(&stop_lock);
+ raw_spin_lock(&stop_lock);
printk(KERN_CRIT "CPU%u: stopping\n", cpu);
dump_stack();
- spin_unlock(&stop_lock);
+ raw_spin_unlock(&stop_lock);
}
set_cpu_online(cpu, false);
local_fiq_disable();
local_irq_disable();
+#ifdef CONFIG_HOTPLUG_CPU
+ platform_cpu_kill(cpu);
+#endif
+
while (1)
cpu_relax();
}
/*
* Main handler for inter-processor interrupts
*/
-asmlinkage void __exception do_IPI(int ipinr, struct pt_regs *regs)
+asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs)
+{
+ handle_IPI(ipinr, regs);
+}
+
+void handle_IPI(int ipinr, struct pt_regs *regs)
{
unsigned int cpu = smp_processor_id();
struct pt_regs *old_regs = set_irq_regs(regs);
- __inc_irq_stat(cpu, ipi_irqs);
+ if (ipinr >= IPI_TIMER && ipinr < IPI_TIMER + NR_IPI)
+ __inc_irq_stat(cpu, ipi_irqs[ipinr - IPI_TIMER]);
switch (ipinr) {
case IPI_TIMER:
+ irq_enter();
ipi_timer();
+ irq_exit();
break;
case IPI_RESCHEDULE:
- /*
- * nothing more to do - eveything is
- * done on the interrupt return path
- */
+ scheduler_ipi();
break;
case IPI_CALL_FUNC:
+ irq_enter();
generic_smp_call_function_interrupt();
+ irq_exit();
break;
case IPI_CALL_FUNC_SINGLE:
+ irq_enter();
generic_smp_call_function_single_interrupt();
+ irq_exit();
break;
case IPI_CPU_STOP:
+ irq_enter();
ipi_cpu_stop(cpu);
+ irq_exit();
break;
default:
void smp_send_stop(void)
{
- cpumask_t mask = cpu_online_map;
- cpu_clear(smp_processor_id(), mask);
- if (!cpus_empty(mask))
- smp_cross_call(&mask, IPI_CPU_STOP);
-}
+ unsigned long timeout;
-/*
- * not supported here
- */
-int setup_profiling_timer(unsigned int multiplier)
-{
- return -EINVAL;
-}
+ if (num_online_cpus() > 1) {
+ cpumask_t mask = cpu_online_map;
+ cpu_clear(smp_processor_id(), mask);
-static void
-on_each_cpu_mask(void (*func)(void *), void *info, int wait,
- const struct cpumask *mask)
-{
- preempt_disable();
+ smp_cross_call(&mask, IPI_CPU_STOP);
+ }
- smp_call_function_many(mask, func, info, wait);
- if (cpumask_test_cpu(smp_processor_id(), mask))
- func(info);
+ /* Wait up to one second for other CPUs to stop */
+ timeout = USEC_PER_SEC;
+ while (num_online_cpus() > 1 && timeout--)
+ udelay(1);
- preempt_enable();
+ if (num_online_cpus() > 1)
+ pr_warning("SMP: failed to stop secondary CPUs\n");
}
-/**********************************************************************/
-
/*
- * TLB operations
+ * not supported here
*/
-struct tlb_args {
- struct vm_area_struct *ta_vma;
- unsigned long ta_start;
- unsigned long ta_end;
-};
-
-static inline void ipi_flush_tlb_all(void *ignored)
-{
- local_flush_tlb_all();
-}
-
-static inline void ipi_flush_tlb_mm(void *arg)
-{
- struct mm_struct *mm = (struct mm_struct *)arg;
-
- local_flush_tlb_mm(mm);
-}
-
-static inline void ipi_flush_tlb_page(void *arg)
-{
- struct tlb_args *ta = (struct tlb_args *)arg;
-
- local_flush_tlb_page(ta->ta_vma, ta->ta_start);
-}
-
-static inline void ipi_flush_tlb_kernel_page(void *arg)
-{
- struct tlb_args *ta = (struct tlb_args *)arg;
-
- local_flush_tlb_kernel_page(ta->ta_start);
-}
-
-static inline void ipi_flush_tlb_range(void *arg)
-{
- struct tlb_args *ta = (struct tlb_args *)arg;
-
- local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
-}
-
-static inline void ipi_flush_tlb_kernel_range(void *arg)
-{
- struct tlb_args *ta = (struct tlb_args *)arg;
-
- local_flush_tlb_kernel_range(ta->ta_start, ta->ta_end);
-}
-
-void flush_tlb_all(void)
-{
- if (tlb_ops_need_broadcast())
- on_each_cpu(ipi_flush_tlb_all, NULL, 1);
- else
- local_flush_tlb_all();
-}
-
-void flush_tlb_mm(struct mm_struct *mm)
-{
- if (tlb_ops_need_broadcast())
- on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm));
- else
- local_flush_tlb_mm(mm);
-}
-
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
-{
- if (tlb_ops_need_broadcast()) {
- struct tlb_args ta;
- ta.ta_vma = vma;
- ta.ta_start = uaddr;
- on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mm_cpumask(vma->vm_mm));
- } else
- local_flush_tlb_page(vma, uaddr);
-}
-
-void flush_tlb_kernel_page(unsigned long kaddr)
-{
- if (tlb_ops_need_broadcast()) {
- struct tlb_args ta;
- ta.ta_start = kaddr;
- on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
- } else
- local_flush_tlb_kernel_page(kaddr);
-}
-
-void flush_tlb_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
-{
- if (tlb_ops_need_broadcast()) {
- struct tlb_args ta;
- ta.ta_vma = vma;
- ta.ta_start = start;
- ta.ta_end = end;
- on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mm_cpumask(vma->vm_mm));
- } else
- local_flush_tlb_range(vma, start, end);
-}
-
-void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+int setup_profiling_timer(unsigned int multiplier)
{
- if (tlb_ops_need_broadcast()) {
- struct tlb_args ta;
- ta.ta_start = start;
- ta.ta_end = end;
- on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
- } else
- local_flush_tlb_kernel_range(start, end);
+ return -EINVAL;
}