linux_dsm_epyc7002/arch/powerpc/kernel/smp.c
Paul Mackerras 3b5750644b [POWERPC] Bolt in SLB entry for kernel stack on secondary cpus
This fixes a regression reported by Kamalesh Bulabel where a POWER4
machine would crash because of an SLB miss at a point where the SLB
miss exception was unrecoverable.  This regression is tracked at:

http://bugzilla.kernel.org/show_bug.cgi?id=10082

SLB misses at such points shouldn't happen because the kernel stack is
the only memory accessed other than things in the first segment of the
linear mapping (which is mapped at all times by entry 0 of the SLB).
The context switch code ensures that SLB entry 2 covers the kernel
stack, if it is not already covered by entry 0.  None of entries 0
to 2 are ever replaced by the SLB miss handler.

Where this went wrong is that the context switch code assumes it
doesn't have to write to SLB entry 2 if the new kernel stack is in the
same segment as the old kernel stack, since entry 2 should already be
correct.  However, when we start up a secondary cpu, it calls
slb_initialize, which doesn't set up entry 2.  This is correct for
the boot cpu, where we will be using a stack in the kernel BSS at this
point (i.e. init_thread_union), but not necessarily for secondary
cpus, whose initial stack can be allocated anywhere.  This doesn't
cause any immediate problem since the SLB miss handler will just
create an SLB entry somewhere else to cover the initial stack.

In fact it's possible for the cpu to go quite a long time without SLB
entry 2 being valid.  Eventually, though, the entry created by the SLB
miss handler will get overwritten by some other entry, and if the next
access to the stack is at an unrecoverable point, we get the crash.

This fixes the problem by making slb_initialize create a suitable
entry for the kernel stack, if we are on a secondary cpu and the stack
isn't covered by SLB entry 0.  This requires initializing the
get_paca()->kstack field earlier, so I do that in smp_create_idle
where the current field is initialized.  This also abstracts a bit of
the computation that mk_esid_data in slb.c does so that it can be used
in slb_initialize.

Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-05-02 15:00:45 +10:00

650 lines
14 KiB
C

/*
* SMP support for ppc.
*
* Written by Cort Dougan (cort@cs.nmt.edu) borrowing a great
* deal of code from the sparc and intel versions.
*
* Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
*
* PowerPC-64 Support added by Dave Engebretsen, Peter Bergner, and
* Mike Corrigan {engebret|bergner|mikec}@us.ibm.com
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#undef DEBUG
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/cache.h>
#include <linux/err.h>
#include <linux/sysdev.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <asm/ptrace.h>
#include <asm/atomic.h>
#include <asm/irq.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/prom.h>
#include <asm/smp.h>
#include <asm/time.h>
#include <asm/machdep.h>
#include <asm/cputable.h>
#include <asm/system.h>
#include <asm/mpic.h>
#include <asm/vdso_datapage.h>
#ifdef CONFIG_PPC64
#include <asm/paca.h>
#endif
#ifdef DEBUG
#include <asm/udbg.h>
#define DBG(fmt...) udbg_printf(fmt)
#else
#define DBG(fmt...)
#endif
int smp_hw_index[NR_CPUS];
struct thread_info *secondary_ti;
cpumask_t cpu_possible_map = CPU_MASK_NONE;
cpumask_t cpu_online_map = CPU_MASK_NONE;
DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
EXPORT_SYMBOL(cpu_online_map);
EXPORT_SYMBOL(cpu_possible_map);
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
/* SMP operations for this machine */
struct smp_ops_t *smp_ops;
static volatile unsigned int cpu_callin_map[NR_CPUS];
void smp_call_function_interrupt(void);
int smt_enabled_at_boot = 1;
static int ipi_fail_ok;
static void (*crash_ipi_function_ptr)(struct pt_regs *) = NULL;
#ifdef CONFIG_PPC64
void __devinit smp_generic_kick_cpu(int nr)
{
BUG_ON(nr < 0 || nr >= NR_CPUS);
/*
* The processor is currently spinning, waiting for the
* cpu_start field to become non-zero After we set cpu_start,
* the processor will continue on to secondary_start
*/
paca[nr].cpu_start = 1;
smp_mb();
}
#endif
void smp_message_recv(int msg)
{
switch(msg) {
case PPC_MSG_CALL_FUNCTION:
smp_call_function_interrupt();
break;
case PPC_MSG_RESCHEDULE:
/* XXX Do we have to do this? */
set_need_resched();
break;
case PPC_MSG_DEBUGGER_BREAK:
if (crash_ipi_function_ptr) {
crash_ipi_function_ptr(get_irq_regs());
break;
}
#ifdef CONFIG_DEBUGGER
debugger_ipi(get_irq_regs());
break;
#endif /* CONFIG_DEBUGGER */
/* FALLTHROUGH */
default:
printk("SMP %d: smp_message_recv(): unknown msg %d\n",
smp_processor_id(), msg);
break;
}
}
void smp_send_reschedule(int cpu)
{
if (likely(smp_ops))
smp_ops->message_pass(cpu, PPC_MSG_RESCHEDULE);
}
#ifdef CONFIG_DEBUGGER
void smp_send_debugger_break(int cpu)
{
if (likely(smp_ops))
smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK);
}
#endif
#ifdef CONFIG_KEXEC
void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
{
crash_ipi_function_ptr = crash_ipi_callback;
if (crash_ipi_callback && smp_ops) {
mb();
smp_ops->message_pass(MSG_ALL_BUT_SELF, PPC_MSG_DEBUGGER_BREAK);
}
}
#endif
static void stop_this_cpu(void *dummy)
{
local_irq_disable();
while (1)
;
}
/*
* Structure and data for smp_call_function(). This is designed to minimise
* static memory requirements. It also looks cleaner.
* Stolen from the i386 version.
*/
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(call_lock);
static struct call_data_struct {
void (*func) (void *info);
void *info;
atomic_t started;
atomic_t finished;
int wait;
} *call_data;
/* delay of at least 8 seconds */
#define SMP_CALL_TIMEOUT 8
/*
* These functions send a 'generic call function' IPI to other online
* CPUS in the system.
*
* [SUMMARY] Run a function on other CPUs.
* <func> The function to run. This must be fast and non-blocking.
* <info> An arbitrary pointer to pass to the function.
* <nonatomic> currently unused.
* <wait> If true, wait (atomically) until function has completed on other CPUs.
* [RETURNS] 0 on success, else a negative status code. Does not return until
* remote CPUs are nearly ready to execute <<func>> or are or have executed.
* <map> is a cpu map of the cpus to send IPI to.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
*/
static int __smp_call_function_map(void (*func) (void *info), void *info,
int nonatomic, int wait, cpumask_t map)
{
struct call_data_struct data;
int ret = -1, num_cpus;
int cpu;
u64 timeout;
if (unlikely(smp_ops == NULL))
return ret;
data.func = func;
data.info = info;
atomic_set(&data.started, 0);
data.wait = wait;
if (wait)
atomic_set(&data.finished, 0);
/* remove 'self' from the map */
if (cpu_isset(smp_processor_id(), map))
cpu_clear(smp_processor_id(), map);
/* sanity check the map, remove any non-online processors. */
cpus_and(map, map, cpu_online_map);
num_cpus = cpus_weight(map);
if (!num_cpus)
goto done;
call_data = &data;
smp_wmb();
/* Send a message to all CPUs in the map */
for_each_cpu_mask(cpu, map)
smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION);
timeout = get_tb() + (u64) SMP_CALL_TIMEOUT * tb_ticks_per_sec;
/* Wait for indication that they have received the message */
while (atomic_read(&data.started) != num_cpus) {
HMT_low();
if (get_tb() >= timeout) {
printk("smp_call_function on cpu %d: other cpus not "
"responding (%d)\n", smp_processor_id(),
atomic_read(&data.started));
if (!ipi_fail_ok)
debugger(NULL);
goto out;
}
}
/* optionally wait for the CPUs to complete */
if (wait) {
while (atomic_read(&data.finished) != num_cpus) {
HMT_low();
if (get_tb() >= timeout) {
printk("smp_call_function on cpu %d: other "
"cpus not finishing (%d/%d)\n",
smp_processor_id(),
atomic_read(&data.finished),
atomic_read(&data.started));
debugger(NULL);
goto out;
}
}
}
done:
ret = 0;
out:
call_data = NULL;
HMT_medium();
return ret;
}
static int __smp_call_function(void (*func)(void *info), void *info,
int nonatomic, int wait)
{
int ret;
spin_lock(&call_lock);
ret =__smp_call_function_map(func, info, nonatomic, wait,
cpu_online_map);
spin_unlock(&call_lock);
return ret;
}
int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
int wait)
{
/* Can deadlock when called with interrupts disabled */
WARN_ON(irqs_disabled());
return __smp_call_function(func, info, nonatomic, wait);
}
EXPORT_SYMBOL(smp_call_function);
int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
int nonatomic, int wait)
{
cpumask_t map = CPU_MASK_NONE;
int ret = 0;
/* Can deadlock when called with interrupts disabled */
WARN_ON(irqs_disabled());
if (!cpu_online(cpu))
return -EINVAL;
cpu_set(cpu, map);
if (cpu != get_cpu()) {
spin_lock(&call_lock);
ret = __smp_call_function_map(func, info, nonatomic, wait, map);
spin_unlock(&call_lock);
} else {
local_irq_disable();
func(info);
local_irq_enable();
}
put_cpu();
return ret;
}
EXPORT_SYMBOL(smp_call_function_single);
void smp_send_stop(void)
{
int nolock;
/* It's OK to fail sending the IPI, since the alternative is to
* be stuck forever waiting on the other CPU to take the interrupt.
*
* It's better to at least continue and go through reboot, since this
* function is usually called at panic or reboot time in the first
* place.
*/
ipi_fail_ok = 1;
/* Don't deadlock in case we got called through panic */
nolock = !spin_trylock(&call_lock);
__smp_call_function_map(stop_this_cpu, NULL, 1, 0, cpu_online_map);
if (!nolock)
spin_unlock(&call_lock);
}
void smp_call_function_interrupt(void)
{
void (*func) (void *info);
void *info;
int wait;
/* call_data will be NULL if the sender timed out while
* waiting on us to receive the call.
*/
if (!call_data)
return;
func = call_data->func;
info = call_data->info;
wait = call_data->wait;
if (!wait)
smp_mb__before_atomic_inc();
/*
* Notify initiating CPU that I've grabbed the data and am
* about to execute the function
*/
atomic_inc(&call_data->started);
/*
* At this point the info structure may be out of scope unless wait==1
*/
(*func)(info);
if (wait) {
smp_mb__before_atomic_inc();
atomic_inc(&call_data->finished);
}
}
extern struct gettimeofday_struct do_gtod;
struct thread_info *current_set[NR_CPUS];
DECLARE_PER_CPU(unsigned int, pvr);
static void __devinit smp_store_cpu_info(int id)
{
per_cpu(pvr, id) = mfspr(SPRN_PVR);
}
static void __init smp_create_idle(unsigned int cpu)
{
struct task_struct *p;
/* create a process for the processor */
p = fork_idle(cpu);
if (IS_ERR(p))
panic("failed fork for CPU %u: %li", cpu, PTR_ERR(p));
#ifdef CONFIG_PPC64
paca[cpu].__current = p;
paca[cpu].kstack = (unsigned long) task_thread_info(p)
+ THREAD_SIZE - STACK_FRAME_OVERHEAD;
#endif
current_set[cpu] = task_thread_info(p);
task_thread_info(p)->cpu = cpu;
}
void __init smp_prepare_cpus(unsigned int max_cpus)
{
unsigned int cpu;
DBG("smp_prepare_cpus\n");
/*
* setup_cpu may need to be called on the boot cpu. We havent
* spun any cpus up but lets be paranoid.
*/
BUG_ON(boot_cpuid != smp_processor_id());
/* Fixup boot cpu */
smp_store_cpu_info(boot_cpuid);
cpu_callin_map[boot_cpuid] = 1;
if (smp_ops)
max_cpus = smp_ops->probe();
else
max_cpus = 1;
smp_space_timers(max_cpus);
for_each_possible_cpu(cpu)
if (cpu != boot_cpuid)
smp_create_idle(cpu);
}
void __devinit smp_prepare_boot_cpu(void)
{
BUG_ON(smp_processor_id() != boot_cpuid);
cpu_set(boot_cpuid, cpu_online_map);
#ifdef CONFIG_PPC64
paca[boot_cpuid].__current = current;
#endif
current_set[boot_cpuid] = task_thread_info(current);
}
#ifdef CONFIG_HOTPLUG_CPU
/* State of each CPU during hotplug phases */
DEFINE_PER_CPU(int, cpu_state) = { 0 };
int generic_cpu_disable(void)
{
unsigned int cpu = smp_processor_id();
if (cpu == boot_cpuid)
return -EBUSY;
cpu_clear(cpu, cpu_online_map);
#ifdef CONFIG_PPC64
vdso_data->processorCount--;
fixup_irqs(cpu_online_map);
#endif
return 0;
}
int generic_cpu_enable(unsigned int cpu)
{
/* Do the normal bootup if we haven't
* already bootstrapped. */
if (system_state != SYSTEM_RUNNING)
return -ENOSYS;
/* get the target out of it's holding state */
per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
smp_wmb();
while (!cpu_online(cpu))
cpu_relax();
#ifdef CONFIG_PPC64
fixup_irqs(cpu_online_map);
/* counter the irq disable in fixup_irqs */
local_irq_enable();
#endif
return 0;
}
void generic_cpu_die(unsigned int cpu)
{
int i;
for (i = 0; i < 100; i++) {
smp_rmb();
if (per_cpu(cpu_state, cpu) == CPU_DEAD)
return;
msleep(100);
}
printk(KERN_ERR "CPU%d didn't die...\n", cpu);
}
void generic_mach_cpu_die(void)
{
unsigned int cpu;
local_irq_disable();
cpu = smp_processor_id();
printk(KERN_DEBUG "CPU%d offline\n", cpu);
__get_cpu_var(cpu_state) = CPU_DEAD;
smp_wmb();
while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
cpu_relax();
cpu_set(cpu, cpu_online_map);
local_irq_enable();
}
#endif
static int __devinit cpu_enable(unsigned int cpu)
{
if (smp_ops && smp_ops->cpu_enable)
return smp_ops->cpu_enable(cpu);
return -ENOSYS;
}
int __cpuinit __cpu_up(unsigned int cpu)
{
int c;
secondary_ti = current_set[cpu];
if (!cpu_enable(cpu))
return 0;
if (smp_ops == NULL ||
(smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu)))
return -EINVAL;
/* Make sure callin-map entry is 0 (can be leftover a CPU
* hotplug
*/
cpu_callin_map[cpu] = 0;
/* The information for processor bringup must
* be written out to main store before we release
* the processor.
*/
smp_mb();
/* wake up cpus */
DBG("smp: kicking cpu %d\n", cpu);
smp_ops->kick_cpu(cpu);
/*
* wait to see if the cpu made a callin (is actually up).
* use this value that I found through experimentation.
* -- Cort
*/
if (system_state < SYSTEM_RUNNING)
for (c = 50000; c && !cpu_callin_map[cpu]; c--)
udelay(100);
#ifdef CONFIG_HOTPLUG_CPU
else
/*
* CPUs can take much longer to come up in the
* hotplug case. Wait five seconds.
*/
for (c = 25; c && !cpu_callin_map[cpu]; c--) {
msleep(200);
}
#endif
if (!cpu_callin_map[cpu]) {
printk("Processor %u is stuck.\n", cpu);
return -ENOENT;
}
printk("Processor %u found.\n", cpu);
if (smp_ops->give_timebase)
smp_ops->give_timebase();
/* Wait until cpu puts itself in the online map */
while (!cpu_online(cpu))
cpu_relax();
return 0;
}
/* Activate a secondary processor. */
int __devinit start_secondary(void *unused)
{
unsigned int cpu = smp_processor_id();
atomic_inc(&init_mm.mm_count);
current->active_mm = &init_mm;
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
preempt_disable();
cpu_callin_map[cpu] = 1;
smp_ops->setup_cpu(cpu);
if (smp_ops->take_timebase)
smp_ops->take_timebase();
if (system_state > SYSTEM_BOOTING)
snapshot_timebase();
secondary_cpu_time_init();
spin_lock(&call_lock);
cpu_set(cpu, cpu_online_map);
spin_unlock(&call_lock);
local_irq_enable();
cpu_idle();
return 0;
}
int setup_profiling_timer(unsigned int multiplier)
{
return 0;
}
void __init smp_cpus_done(unsigned int max_cpus)
{
cpumask_t old_mask;
/* We want the setup_cpu() here to be called from CPU 0, but our
* init thread may have been "borrowed" by another CPU in the meantime
* se we pin us down to CPU 0 for a short while
*/
old_mask = current->cpus_allowed;
set_cpus_allowed(current, cpumask_of_cpu(boot_cpuid));
if (smp_ops)
smp_ops->setup_cpu(boot_cpuid);
set_cpus_allowed(current, old_mask);
snapshot_timebases();
dump_numa_cpu_topology();
}
#ifdef CONFIG_HOTPLUG_CPU
int __cpu_disable(void)
{
if (smp_ops->cpu_disable)
return smp_ops->cpu_disable();
return -ENOSYS;
}
void __cpu_die(unsigned int cpu)
{
if (smp_ops->cpu_die)
smp_ops->cpu_die(cpu);
}
#endif