kernel_optimize_test/arch/x86/kernel/apic/ipi.c

// SPDX-License-Identifier: GPL-2.0
#include <linux/cpumask.h>
#include <linux/interrupt.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/cpu.h>

#include <asm/smp.h>
#include <asm/mtrr.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/apic.h>
#include <asm/proto.h>
#include <asm/ipi.h>

void __default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest)
{
	/*
	 * Subtle. In the case of the 'never do double writes' workaround
	 * we have to lock out interrupts to be safe.  As we don't care
	 * of the value read we use an atomic rmw access to avoid costly
	 * cli/sti.  Otherwise we use an even cheaper single atomic write
	 * to the APIC.
	 */
	unsigned int cfg;

	/*
	 * Wait for idle.
	 */
	__xapic_wait_icr_idle();

	/*
	 * No need to touch the target chip field
	 */
	cfg = __prepare_ICR(shortcut, vector, dest);

	/*
	 * Send the IPI. The write to APIC_ICR fires this off.
	 */
	native_apic_mem_write(APIC_ICR, cfg);
}

/*
 * This is used to send an IPI with no shorthand notation (the destination is
 * specified in bits 56 to 63 of the ICR).
 */
void __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest)
{
	unsigned long cfg;

	/*
	 * Wait for idle.
	 */
	if (unlikely(vector == NMI_VECTOR))
		safe_apic_wait_icr_idle();
	else
		__xapic_wait_icr_idle();

	/*
	 * prepare target chip field
	 */
	cfg = __prepare_ICR2(mask);
	native_apic_mem_write(APIC_ICR2, cfg);

	/*
	 * program the ICR
	 */
	cfg = __prepare_ICR(0, vector, dest);

	/*
	 * Send the IPI. The write to APIC_ICR fires this off.
	 */
	native_apic_mem_write(APIC_ICR, cfg);
}

void default_send_IPI_single_phys(int cpu, int vector)
{
	unsigned long flags;

	local_irq_save(flags);
	__default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, cpu),
				      vector, APIC_DEST_PHYSICAL);
	local_irq_restore(flags);
}

void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector)
{
	unsigned long query_cpu;
	unsigned long flags;

	/*
	 * Hack. The clustered APIC addressing mode doesn't allow us to send
	 * to an arbitrary mask, so I do a unicast to each CPU instead.
	 * - mbligh
	 */
	local_irq_save(flags);
	for_each_cpu(query_cpu, mask) {
		__default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid,
				query_cpu), vector, APIC_DEST_PHYSICAL);
	}
	local_irq_restore(flags);
}

void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
						 int vector)
{
	unsigned int this_cpu = smp_processor_id();
	unsigned int query_cpu;
	unsigned long flags;

	/* See Hack comment above */

	local_irq_save(flags);
	for_each_cpu(query_cpu, mask) {
		if (query_cpu == this_cpu)
			continue;
		__default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid,
				 query_cpu), vector, APIC_DEST_PHYSICAL);
	}
	local_irq_restore(flags);
}

/*
 * Helper function for APICs which insist on cpumasks
 */
void default_send_IPI_single(int cpu, int vector)
{
	apic->send_IPI_mask(cpumask_of(cpu), vector);
}

#ifdef CONFIG_X86_32

void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
						 int vector)
{
	unsigned long flags;
	unsigned int query_cpu;

	/*
	 * Hack. The clustered APIC addressing mode doesn't allow us to send
	 * to an arbitrary mask, so I do a unicasts to each CPU instead. This
	 * should be modified to do 1 message per cluster ID - mbligh
	 */

	local_irq_save(flags);
	for_each_cpu(query_cpu, mask)
		__default_send_IPI_dest_field(
			early_per_cpu(x86_cpu_to_logical_apicid, query_cpu),
			vector, apic->dest_logical);
	local_irq_restore(flags);
}

void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
						 int vector)
{
	unsigned long flags;
	unsigned int query_cpu;
	unsigned int this_cpu = smp_processor_id();

	/* See Hack comment above */

	local_irq_save(flags);
	for_each_cpu(query_cpu, mask) {
		if (query_cpu == this_cpu)
			continue;
		__default_send_IPI_dest_field(
			early_per_cpu(x86_cpu_to_logical_apicid, query_cpu),
			vector, apic->dest_logical);
		}
	local_irq_restore(flags);
}

/*
 * This is only used on smaller machines.
 */
void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector)
{
	unsigned long mask = cpumask_bits(cpumask)[0];
	unsigned long flags;

	if (!mask)
		return;

	local_irq_save(flags);
	WARN_ON(mask & ~cpumask_bits(cpu_online_mask)[0]);
	__default_send_IPI_dest_field(mask, vector, apic->dest_logical);
	local_irq_restore(flags);
}

void default_send_IPI_allbutself(int vector)
{
	/*
	 * if there are no other CPUs in the system then we get an APIC send
	 * error if we try to broadcast, thus avoid sending IPIs in this case.
	 */
	if (!(num_online_cpus() > 1))
		return;

	__default_local_send_IPI_allbutself(vector);
}

void default_send_IPI_all(int vector)
{
	__default_local_send_IPI_all(vector);
}

void default_send_IPI_self(int vector)
{
	__default_send_IPI_shortcut(APIC_DEST_SELF, vector, apic->dest_logical);
}

/* must come after the send_IPI functions above for inlining */
static int convert_apicid_to_cpu(int apic_id)
{
	int i;

	for_each_possible_cpu(i) {
		if (per_cpu(x86_cpu_to_apicid, i) == apic_id)
			return i;
	}
	return -1;
}

int safe_smp_processor_id(void)
{
	int apicid, cpuid;

	if (!boot_cpu_has(X86_FEATURE_APIC))
		return 0;

	apicid = hard_smp_processor_id();
	if (apicid == BAD_APICID)
		return 0;

	cpuid = convert_apicid_to_cpu(apicid);

	return cpuid >= 0 ? cpuid : 0;
}
#endif