linux/arch/x86/kernel/smp.c
Andi Kleen 4ef702c10b x86: fix panic with interrupts off (needed for MCE)
For some time each panic() called with interrupts disabled
triggered the !irqs_disabled() WARN_ON in smp_call_function(),
producing ugly backtraces and confusing users.

This is a common situation with machine checks for example which
tend to call panic with interrupts disabled, but will also hit
in other situations e.g. panic during early boot.  In fact it
means that panic cannot be called in many circumstances, which
would be bad.

This all started with the new fancy queued smp_call_function,
which is then used by the shutdown path to shut down the other
CPUs.

On closer examination it turned out that the fancy RCU
smp_call_function() does lots of things not suitable in a panic
situation anyways, like allocating memory and relying on complex
system state.

I originally tried to patch this over by checking for panic
there, but it was quite complicated and the original patch
was also not very popular.  This also didn't fix some of the
underlying complexity problems.

The new code in post 2.6.29 tries to patch around this by
checking for oops_in_progress, but that is not enough to make
this fully safe and I don't think that's a real solution
because panic has to be reliable.

So instead use an own vector to reboot.  This makes the reboot
code extremly straight forward, which is definitely a big plus
in a panic situation where it is important to avoid relying on
too much kernel state.  The new simple code is also safe to be
called from interupts off region because it is very very simple.

There can be situations where it is important that panic
is reliable.  For example on a fatal machine check the panic
is needed to get the system up again and running as quickly
as possible.  So it's important that panic is reliable and
all function it calls simple.

This is why I came up with this simple vector scheme.
It's very hard to beat in simplicity.  Vectors are not
particularly precious anymore since all big systems are
using per CPU vectors.

Another possibility would have been to use an NMI similar
to kdump, but there is still the problem that NMIs don't
work reliably on some systems due to BIOS issues.  NMIs
would have been able to stop CPUs running with interrupts
off too.  In the sake of universal reliability I opted for
using a non NMI vector for now.

I put the reboot vector into the highest priority bucket of
the APIC vectors and moved the 64bit UV_BAU message down
instead into the next lower priority.

[ Impact: bug fix, fixes an old regression ]

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-06-03 14:45:35 -07:00

238 lines
6.7 KiB
C

/*
* Intel SMP support routines.
*
* (c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk>
* (c) 1998-99, 2000, 2009 Ingo Molnar <mingo@redhat.com>
* (c) 2002,2003 Andi Kleen, SuSE Labs.
*
* i386 and x86_64 integration by Glauber Costa <gcosta@redhat.com>
*
* This code is released under the GNU General Public License version 2 or
* later.
*/
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/spinlock.h>
#include <linux/kernel_stat.h>
#include <linux/mc146818rtc.h>
#include <linux/cache.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <asm/mtrr.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/apic.h>
/*
* Some notes on x86 processor bugs affecting SMP operation:
*
* Pentium, Pentium Pro, II, III (and all CPUs) have bugs.
* The Linux implications for SMP are handled as follows:
*
* Pentium III / [Xeon]
* None of the E1AP-E3AP errata are visible to the user.
*
* E1AP. see PII A1AP
* E2AP. see PII A2AP
* E3AP. see PII A3AP
*
* Pentium II / [Xeon]
* None of the A1AP-A3AP errata are visible to the user.
*
* A1AP. see PPro 1AP
* A2AP. see PPro 2AP
* A3AP. see PPro 7AP
*
* Pentium Pro
* None of 1AP-9AP errata are visible to the normal user,
* except occasional delivery of 'spurious interrupt' as trap #15.
* This is very rare and a non-problem.
*
* 1AP. Linux maps APIC as non-cacheable
* 2AP. worked around in hardware
* 3AP. fixed in C0 and above steppings microcode update.
* Linux does not use excessive STARTUP_IPIs.
* 4AP. worked around in hardware
* 5AP. symmetric IO mode (normal Linux operation) not affected.
* 'noapic' mode has vector 0xf filled out properly.
* 6AP. 'noapic' mode might be affected - fixed in later steppings
* 7AP. We do not assume writes to the LVT deassering IRQs
* 8AP. We do not enable low power mode (deep sleep) during MP bootup
* 9AP. We do not use mixed mode
*
* Pentium
* There is a marginal case where REP MOVS on 100MHz SMP
* machines with B stepping processors can fail. XXX should provide
* an L1cache=Writethrough or L1cache=off option.
*
* B stepping CPUs may hang. There are hardware work arounds
* for this. We warn about it in case your board doesn't have the work
* arounds. Basically that's so I can tell anyone with a B stepping
* CPU and SMP problems "tough".
*
* Specific items [From Pentium Processor Specification Update]
*
* 1AP. Linux doesn't use remote read
* 2AP. Linux doesn't trust APIC errors
* 3AP. We work around this
* 4AP. Linux never generated 3 interrupts of the same priority
* to cause a lost local interrupt.
* 5AP. Remote read is never used
* 6AP. not affected - worked around in hardware
* 7AP. not affected - worked around in hardware
* 8AP. worked around in hardware - we get explicit CS errors if not
* 9AP. only 'noapic' mode affected. Might generate spurious
* interrupts, we log only the first one and count the
* rest silently.
* 10AP. not affected - worked around in hardware
* 11AP. Linux reads the APIC between writes to avoid this, as per
* the documentation. Make sure you preserve this as it affects
* the C stepping chips too.
* 12AP. not affected - worked around in hardware
* 13AP. not affected - worked around in hardware
* 14AP. we always deassert INIT during bootup
* 15AP. not affected - worked around in hardware
* 16AP. not affected - worked around in hardware
* 17AP. not affected - worked around in hardware
* 18AP. not affected - worked around in hardware
* 19AP. not affected - worked around in BIOS
*
* If this sounds worrying believe me these bugs are either ___RARE___,
* or are signal timing bugs worked around in hardware and there's
* about nothing of note with C stepping upwards.
*/
/*
* this function sends a 'reschedule' IPI to another CPU.
* it goes straight through and wastes no time serializing
* anything. Worst case is that we lose a reschedule ...
*/
static void native_smp_send_reschedule(int cpu)
{
if (unlikely(cpu_is_offline(cpu))) {
WARN_ON(1);
return;
}
apic->send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR);
}
void native_send_call_func_single_ipi(int cpu)
{
apic->send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR);
}
void native_send_call_func_ipi(const struct cpumask *mask)
{
cpumask_var_t allbutself;
if (!alloc_cpumask_var(&allbutself, GFP_ATOMIC)) {
apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
return;
}
cpumask_copy(allbutself, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), allbutself);
if (cpumask_equal(mask, allbutself) &&
cpumask_equal(cpu_online_mask, cpu_callout_mask))
apic->send_IPI_allbutself(CALL_FUNCTION_VECTOR);
else
apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
free_cpumask_var(allbutself);
}
/*
* this function calls the 'stop' function on all other CPUs in the system.
*/
asmlinkage void smp_reboot_interrupt(void)
{
ack_APIC_irq();
irq_enter();
stop_this_cpu(NULL);
irq_exit();
}
static void native_smp_send_stop(void)
{
unsigned long flags;
unsigned long wait;
if (reboot_force)
return;
/*
* Use an own vector here because smp_call_function
* does lots of things not suitable in a panic situation.
* On most systems we could also use an NMI here,
* but there are a few systems around where NMI
* is problematic so stay with an non NMI for now
* (this implies we cannot stop CPUs spinning with irq off
* currently)
*/
if (num_online_cpus() > 1) {
apic->send_IPI_allbutself(REBOOT_VECTOR);
/* Don't wait longer than a second */
wait = USEC_PER_SEC;
while (num_online_cpus() > 1 && wait--)
udelay(1);
}
local_irq_save(flags);
disable_local_APIC();
local_irq_restore(flags);
}
/*
* Reschedule call back. Nothing to do,
* all the work is done automatically when
* we return from the interrupt.
*/
void smp_reschedule_interrupt(struct pt_regs *regs)
{
ack_APIC_irq();
inc_irq_stat(irq_resched_count);
}
void smp_call_function_interrupt(struct pt_regs *regs)
{
ack_APIC_irq();
irq_enter();
generic_smp_call_function_interrupt();
inc_irq_stat(irq_call_count);
irq_exit();
}
void smp_call_function_single_interrupt(struct pt_regs *regs)
{
ack_APIC_irq();
irq_enter();
generic_smp_call_function_single_interrupt();
inc_irq_stat(irq_call_count);
irq_exit();
}
struct smp_ops smp_ops = {
.smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
.smp_prepare_cpus = native_smp_prepare_cpus,
.smp_cpus_done = native_smp_cpus_done,
.smp_send_stop = native_smp_send_stop,
.smp_send_reschedule = native_smp_send_reschedule,
.cpu_up = native_cpu_up,
.cpu_die = native_cpu_die,
.cpu_disable = native_cpu_disable,
.play_dead = native_play_dead,
.send_call_func_ipi = native_send_call_func_ipi,
.send_call_func_single_ipi = native_send_call_func_single_ipi,
};
EXPORT_SYMBOL_GPL(smp_ops);