Release 4.14 arch/x86/kernel/smp.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/export.h>
#include <linux/kernel_stat.h>
#include <linux/mc146818rtc.h>
#include <linux/cache.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/gfp.h>

#include <asm/mtrr.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/apic.h>
#include <asm/nmi.h>
#include <asm/mce.h>
#include <asm/trace/irq_vectors.h>
#include <asm/kexec.h>
#include <asm/virtext.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.
 */


static atomic_t stopping_cpu = ATOMIC_INIT(-1);

static bool smp_no_nmi_ipi = false;

/*
 * 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(1, "sched: Unexpected reschedule of offline CPU#%d!\n", cpu);
		return;
	}
	apic->send_IPI(cpu, RESCHEDULE_VECTOR);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Glauber de Oliveira Costa
22
55.00%
1
25.00%
Gautham R. Shenoy
10
25.00%
1
25.00%
Prarit Bhargava
5
12.50%
1
25.00%
Thomas Gleixner
3
7.50%
1
25.00%
Total
40
100.00%
4
100.00%



void native_send_call_func_single_ipi(int cpu)
{
	apic->send_IPI(cpu, CALL_FUNCTION_SINGLE_VECTOR);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Glauber de Oliveira Costa
9
52.94%
1
33.33%
Jens Axboe
5
29.41%
1
33.33%
Thomas Gleixner
3
17.65%
1
33.33%
Total
17
100.00%
3
100.00%



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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Mike Travis
41
45.56%
3
42.86%
Glauber de Oliveira Costa
37
41.11%
1
14.29%
Ingo Molnar
6
6.67%
1
14.29%
Hugh Dickins
4
4.44%
1
14.29%
Jens Axboe
2
2.22%
1
14.29%
Total
90
100.00%
7
100.00%



static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
{
	/* We are registered on stopping cpu too, avoid spurious NMI */
	if (raw_smp_processor_id() == atomic_read(&stopping_cpu))
		return NMI_HANDLED;

	cpu_emergency_vmxoff();
	stop_this_cpu(NULL);

	return NMI_HANDLED;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Don Zickus
38
92.68%
1
50.00%
Tiantian Feng
3
7.32%
1
50.00%
Total
41
100.00%
2
100.00%

/*
 * this function calls the 'stop' function on all other CPUs in the system.
 */



asmlinkage __visible void smp_reboot_interrupt(void)
{
	ipi_entering_ack_irq();
	cpu_emergency_vmxoff();
	stop_this_cpu(NULL);
	irq_exit();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andi Kleen
19
82.61%
2
50.00%
Tiantian Feng
3
13.04%
1
25.00%
Thomas Gleixner
1
4.35%
1
25.00%
Total
23
100.00%
4
100.00%



static void native_stop_other_cpus(int wait)
{
	unsigned long flags;
	unsigned long timeout;

	if (reboot_force)
		return;

	/*
         * Use an own vector here because smp_call_function
         * does lots of things not suitable in a panic situation.
         */

	/*
         * We start by using the REBOOT_VECTOR irq.
         * The irq is treated as a sync point to allow critical
         * regions of code on other cpus to release their spin locks
         * and re-enable irqs.  Jumping straight to an NMI might
         * accidentally cause deadlocks with further shutdown/panic
         * code.  By syncing, we give the cpus up to one second to
         * finish their work before we force them off with the NMI.
         */
	if (num_online_cpus() > 1) {
		/* did someone beat us here? */
		if (atomic_cmpxchg(&stopping_cpu, -1, safe_smp_processor_id()) != -1)
			return;

		/* sync above data before sending IRQ */
		wmb();

		apic->send_IPI_allbutself(REBOOT_VECTOR);

		/*
                 * Don't wait longer than a second if the caller
                 * didn't ask us to wait.
                 */
		timeout = USEC_PER_SEC;
		while (num_online_cpus() > 1 && (wait || timeout--))
			udelay(1);
	}
	
	/* if the REBOOT_VECTOR didn't work, try with the NMI */
	if ((num_online_cpus() > 1) && (!smp_no_nmi_ipi))  {
		if (register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback,
					 NMI_FLAG_FIRST, "smp_stop"))
			/* Note: we ignore failures here */
			/* Hope the REBOOT_IRQ is good enough */
			goto finish;

		/* sync above data before sending IRQ */
		wmb();

		pr_emerg("Shutting down cpus with NMI\n");

		apic->send_IPI_allbutself(NMI_VECTOR);

		/*
                 * Don't wait longer than a 10 ms if the caller
                 * didn't ask us to wait.
                 */
		timeout = USEC_PER_MSEC * 10;
		while (num_online_cpus() > 1 && (wait || timeout--))
			udelay(1);
	}

finish:
	local_irq_save(flags);
	disable_local_APIC();
	mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
	local_irq_restore(flags);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Don Zickus
105
55.85%
3
37.50%
Andi Kleen
34
18.09%
1
12.50%
Glauber de Oliveira Costa
29
15.43%
1
12.50%
Alok N Kataria
9
4.79%
1
12.50%
Ashok Raj
9
4.79%
1
12.50%
Jens Axboe
2
1.06%
1
12.50%
Total
188
100.00%
8
100.00%

/*
 * Reschedule call back. KVM uses this interrupt to force a cpu out of
 * guest mode
 */


__visible void __irq_entry smp_reschedule_interrupt(struct pt_regs *regs)
{
	ack_APIC_irq();
	inc_irq_stat(irq_resched_count);

	if (trace_resched_ipi_enabled()) {
		/*
                 * scheduler_ipi() might call irq_enter() as well, but
                 * nested calls are fine.
                 */
		irq_enter();
		trace_reschedule_entry(RESCHEDULE_VECTOR);
		scheduler_ipi();
		trace_reschedule_exit(RESCHEDULE_VECTOR);
		irq_exit();
		return;
	}
	scheduler_ipi();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
18
35.29%
3
33.33%
Seiji Aguchi
17
33.33%
2
22.22%
Glauber de Oliveira Costa
13
25.49%
1
11.11%
Andi Kleen
1
1.96%
1
11.11%
Jens Axboe
1
1.96%
1
11.11%
Daniel Bristot de Oliveira
1
1.96%
1
11.11%
Total
51
100.00%
9
100.00%



__visible void __irq_entry smp_call_function_interrupt(struct pt_regs *regs)
{
	ipi_entering_ack_irq();
	trace_call_function_entry(CALL_FUNCTION_VECTOR);
	inc_irq_stat(irq_call_count);
	generic_smp_call_function_interrupt();
	trace_call_function_exit(CALL_FUNCTION_VECTOR);
	exiting_irq();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jens Axboe
12
33.33%
2
20.00%
Seiji Aguchi
10
27.78%
2
20.00%
Thomas Gleixner
6
16.67%
2
20.00%
Glauber de Oliveira Costa
5
13.89%
1
10.00%
Hiroshi Shimamoto
1
2.78%
1
10.00%
Daniel Bristot de Oliveira
1
2.78%
1
10.00%
Andi Kleen
1
2.78%
1
10.00%
Total
36
100.00%
10
100.00%



__visible void __irq_entry smp_call_function_single_interrupt(struct pt_regs *r)
{
	ipi_entering_ack_irq();
	trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
	inc_irq_stat(irq_call_count);
	generic_smp_call_function_single_interrupt();
	trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR);
	exiting_irq();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Seiji Aguchi
25
69.44%
1
20.00%
Thomas Gleixner
9
25.00%
2
40.00%
Daniel Bristot de Oliveira
1
2.78%
1
20.00%
Andi Kleen
1
2.78%
1
20.00%
Total
36
100.00%
5
100.00%



static int __init nonmi_ipi_setup(char *str)
{
	smp_no_nmi_ipi = true;
	return 1;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Don Zickus
18
100.00%
2
100.00%
Total
18
100.00%
2
100.00%

__setup("nonmi_ipi", nonmi_ipi_setup);


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,

	.stop_other_cpus	= native_stop_other_cpus,
#if defined(CONFIG_KEXEC_CORE)
	.crash_stop_other_cpus	= kdump_nmi_shootdown_cpus,
#endif
	.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);
Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
Glauber de Oliveira Costa
196
27.61%
2
5.56%
Don Zickus
188
26.48%
4
11.11%
Andi Kleen
56
7.89%
3
8.33%
Seiji Aguchi
55
7.75%
2
5.56%
Mike Travis
41
5.77%
3
8.33%
Thomas Gleixner
41
5.77%
5
13.89%
Jens Axboe
29
4.08%
2
5.56%
Alex Nixon
20
2.82%
1
2.78%
Hidehiro Kawai
16
2.25%
1
2.78%
Ashok Raj
12
1.69%
1
2.78%
Alok N Kataria
10
1.41%
1
2.78%
Gautham R. Shenoy
10
1.41%
1
2.78%
Tiantian Feng
9
1.27%
1
2.78%
Ingo Molnar
8
1.13%
3
8.33%
Prarit Bhargava
5
0.70%
1
2.78%
Hugh Dickins
4
0.56%
1
2.78%
Tejun Heo
3
0.42%
1
2.78%
Daniel Bristot de Oliveira
3
0.42%
1
2.78%
Paul Gortmaker
3
0.42%
1
2.78%
Hiroshi Shimamoto
1
0.14%
1
2.78%
Total
710
100.00%
36
100.00%
Directory: arch/x86/kernel

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.