linux/arch/x86/kernel/x86_init.c
Linus Torvalds b18d62891a Merge branch 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 APIC updates from Thomas Gleixner:
 "This update provides a major overhaul of the APIC initialization and
  vector allocation code:

   - Unification of the APIC and interrupt mode setup which was
     scattered all over the place and was hard to follow. This also
     distangles the timer setup from the APIC initialization which
     brings a clear separation of functionality.

     Great detective work from Dou Lyiang!

   - Refactoring of the x86 vector allocation mechanism. The existing
     code was based on nested loops and rather convoluted APIC callbacks
     which had a horrible worst case behaviour and tried to serve all
     different use cases in one go. This led to quite odd hacks when
     supporting the new managed interupt facility for multiqueue devices
     and made it more or less impossible to deal with the vector space
     exhaustion which was a major roadblock for server hibernation.

     Aside of that the code dealing with cpu hotplug and the system
     vectors was disconnected from the actual vector management and
     allocation code, which made it hard to follow and maintain.

     Utilizing the new bitmap matrix allocator core mechanism, the new
     allocator and management code consolidates the handling of system
     vectors, legacy vectors, cpu hotplug mechanisms and the actual
     allocation which needs to be aware of system and legacy vectors and
     hotplug constraints into a single consistent entity.

     This has one visible change: The support for multi CPU targets of
     interrupts, which is only available on a certain subset of
     CPUs/APIC variants has been removed in favour of single interrupt
     targets. A proper analysis of the multi CPU target feature revealed
     that there is no real advantage as the vast majority of interrupts
     end up on the CPU with the lowest APIC id in the set of target CPUs
     anyway. That change was agreed on by the relevant folks and allowed
     to simplify the implementation significantly and to replace rather
     fragile constructs like the vector cleanup IPI with straight
     forward and solid code.

     Furthermore this allowed to cleanly separate the allocation details
     for legacy, normal and managed interrupts:

      * Legacy interrupts are not longer wasting 16 vectors
        unconditionally

      * Managed interrupts have now a guaranteed vector reservation, but
        the actual vector assignment happens when the interrupt is
        requested. It's guaranteed not to fail.

      * Normal interrupts no longer allocate vectors unconditionally
        when the interrupt is set up (IO/APIC init or MSI(X) enable).
        The mechanism has been switched to a best effort reservation
        mode. The actual allocation happens when the interrupt is
        requested. Contrary to managed interrupts the request can fail
        due to vector space exhaustion, but drivers must handle a fail
        of request_irq() anyway. When the interrupt is freed, the vector
        is handed back as well.

        This solves a long standing problem with large unconditional
        vector allocations for a certain class of enterprise devices
        which prevented server hibernation due to vector space
        exhaustion when the unused allocated vectors had to be migrated
        to CPU0 while unplugging all non boot CPUs.

     The code has been equipped with trace points and detailed debugfs
     information to aid analysis of the vector space"

* 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (60 commits)
  x86/vector/msi: Select CONFIG_GENERIC_IRQ_RESERVATION_MODE
  PCI/MSI: Set MSI_FLAG_MUST_REACTIVATE in core code
  genirq: Add config option for reservation mode
  x86/vector: Use correct per cpu variable in free_moved_vector()
  x86/apic/vector: Ignore set_affinity call for inactive interrupts
  x86/apic: Fix spelling mistake: "symmectic" -> "symmetric"
  x86/apic: Use dead_cpu instead of current CPU when cleaning up
  ACPI/init: Invoke early ACPI initialization earlier
  x86/vector: Respect affinity mask in irq descriptor
  x86/irq: Simplify hotplug vector accounting
  x86/vector: Switch IOAPIC to global reservation mode
  x86/vector/msi: Switch to global reservation mode
  x86/vector: Handle managed interrupts proper
  x86/io_apic: Reevaluate vector configuration on activate()
  iommu/amd: Reevaluate vector configuration on activate()
  iommu/vt-d: Reevaluate vector configuration on activate()
  x86/apic/msi: Force reactivation of interrupts at startup time
  x86/vector: Untangle internal state from irq_cfg
  x86/vector: Compile SMP only code conditionally
  x86/apic: Remove unused callbacks
  ...
2017-11-13 18:29:23 -08:00

153 lines
3.7 KiB
C

/*
* Copyright (C) 2009 Thomas Gleixner <tglx@linutronix.de>
*
* For licencing details see kernel-base/COPYING
*/
#include <linux/init.h>
#include <linux/ioport.h>
#include <linux/export.h>
#include <linux/pci.h>
#include <asm/bios_ebda.h>
#include <asm/paravirt.h>
#include <asm/pci_x86.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
#include <asm/apic.h>
#include <asm/e820/api.h>
#include <asm/time.h>
#include <asm/irq.h>
#include <asm/io_apic.h>
#include <asm/hpet.h>
#include <asm/pat.h>
#include <asm/tsc.h>
#include <asm/iommu.h>
#include <asm/mach_traps.h>
void x86_init_noop(void) { }
void __init x86_init_uint_noop(unsigned int unused) { }
int __init iommu_init_noop(void) { return 0; }
void iommu_shutdown_noop(void) { }
bool __init bool_x86_init_noop(void) { return false; }
void x86_op_int_noop(int cpu) { }
/*
* The platform setup functions are preset with the default functions
* for standard PC hardware.
*/
struct x86_init_ops x86_init __initdata = {
.resources = {
.probe_roms = probe_roms,
.reserve_resources = reserve_standard_io_resources,
.memory_setup = e820__memory_setup_default,
},
.mpparse = {
.mpc_record = x86_init_uint_noop,
.setup_ioapic_ids = x86_init_noop,
.mpc_apic_id = default_mpc_apic_id,
.smp_read_mpc_oem = default_smp_read_mpc_oem,
.mpc_oem_bus_info = default_mpc_oem_bus_info,
.find_smp_config = default_find_smp_config,
.get_smp_config = default_get_smp_config,
},
.irqs = {
.pre_vector_init = init_ISA_irqs,
.intr_init = native_init_IRQ,
.trap_init = x86_init_noop,
.intr_mode_init = apic_intr_mode_init
},
.oem = {
.arch_setup = x86_init_noop,
.banner = default_banner,
},
.paging = {
.pagetable_init = native_pagetable_init,
},
.timers = {
.setup_percpu_clockev = setup_boot_APIC_clock,
.timer_init = hpet_time_init,
.wallclock_init = x86_init_noop,
},
.iommu = {
.iommu_init = iommu_init_noop,
},
.pci = {
.init = x86_default_pci_init,
.init_irq = x86_default_pci_init_irq,
.fixup_irqs = x86_default_pci_fixup_irqs,
},
.hyper = {
.init_platform = x86_init_noop,
.guest_late_init = x86_init_noop,
.x2apic_available = bool_x86_init_noop,
.init_mem_mapping = x86_init_noop,
},
};
struct x86_cpuinit_ops x86_cpuinit = {
.early_percpu_clock_init = x86_init_noop,
.setup_percpu_clockev = setup_secondary_APIC_clock,
};
static void default_nmi_init(void) { };
struct x86_platform_ops x86_platform __ro_after_init = {
.calibrate_cpu = native_calibrate_cpu,
.calibrate_tsc = native_calibrate_tsc,
.get_wallclock = mach_get_cmos_time,
.set_wallclock = mach_set_rtc_mmss,
.iommu_shutdown = iommu_shutdown_noop,
.is_untracked_pat_range = is_ISA_range,
.nmi_init = default_nmi_init,
.get_nmi_reason = default_get_nmi_reason,
.save_sched_clock_state = tsc_save_sched_clock_state,
.restore_sched_clock_state = tsc_restore_sched_clock_state,
.hyper.pin_vcpu = x86_op_int_noop,
};
EXPORT_SYMBOL_GPL(x86_platform);
#if defined(CONFIG_PCI_MSI)
struct x86_msi_ops x86_msi __ro_after_init = {
.setup_msi_irqs = native_setup_msi_irqs,
.teardown_msi_irq = native_teardown_msi_irq,
.teardown_msi_irqs = default_teardown_msi_irqs,
.restore_msi_irqs = default_restore_msi_irqs,
};
/* MSI arch specific hooks */
int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
return x86_msi.setup_msi_irqs(dev, nvec, type);
}
void arch_teardown_msi_irqs(struct pci_dev *dev)
{
x86_msi.teardown_msi_irqs(dev);
}
void arch_teardown_msi_irq(unsigned int irq)
{
x86_msi.teardown_msi_irq(irq);
}
void arch_restore_msi_irqs(struct pci_dev *dev)
{
x86_msi.restore_msi_irqs(dev);
}
#endif
struct x86_io_apic_ops x86_io_apic_ops __ro_after_init = {
.read = native_io_apic_read,
.disable = native_disable_io_apic,
};