linux-stable/arch/x86/kernel/x86_init.c
Linus Torvalds 1a2a76c268 A set of fixes for X86:
- Ensure that the PIT is set up when the local APIC is disable or
    configured in legacy mode. This is caused by an ordering issue
    introduced in the recent changes which skip PIT initialization when the
    TSC and APIC frequencies are already known.
 
  - Handle malformed SRAT tables during early ACPI parsing which caused an
    infinite loop anda boot hang.
 
  - Fix a long standing race in the affinity setting code which affects PCI
    devices with non-maskable MSI interrupts. The problem is caused by the
    non-atomic writes of the MSI address (destination APIC id) and data
    (vector) fields which the device uses to construct the MSI message. The
    non-atomic writes are mandated by PCI.
 
    If both fields change and the device raises an interrupt after writing
    address and before writing data, then the MSI block constructs a
    inconsistent message which causes interrupts to be lost and subsequent
    malfunction of the device.
 
    The fix is to redirect the interrupt to the new vector on the current
    CPU first and then switch it over to the new target CPU. This allows to
    observe an eventually raised interrupt in the transitional stage (old
    CPU, new vector) to be observed in the APIC IRR and retriggered on the
    new target CPU and the new vector. The potential spurious interrupts
    caused by this are harmless and can in the worst case expose a buggy
    driver (all handlers have to be able to deal with spurious interrupts as
    they can and do happen for various reasons).
 
  - Add the missing suspend/resume mechanism for the HYPERV hypercall page
    which prevents resume hibernation on HYPERV guests. This change got
    lost before the merge window.
 
  - Mask the IOAPIC before disabling the local APIC to prevent potentially
    stale IOAPIC remote IRR bits which cause stale interrupt lines after
    resume.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEQp8+kY+LLUocC4bMphj1TA10mKEFAl5AEJwTHHRnbHhAbGlu
 dXRyb25peC5kZQAKCRCmGPVMDXSYoWY2D/47ur9gsVQGryKzneVAr0SCsq4Un11e
 uifX4ldu4gCEBRTYhpgcpiFKeLvY/QJ6uOD+gQUHyy/s+lCf6yzE6UhXEqSCtcT7
 LkSxD8jAFf6KhMA6iqYBfyxUsPMXBetLjjHWsyc/kf15O/vbYm7qf05timmNZkDS
 S7C+yr3KRqRjLR7G7t4twlgC9aLcNUQihUdsH2qyTvjnlkYHJLDa0/Js7bFYYKVx
 9GdUDLvPFB1mZ76g012De4R3kJsWitiyLlQ38DP5VysKulnszUCdiXlgCEFrgxvQ
 OQhLafQzOAzvxQmP+1alODR0dmJZA8k0zsDeeTB/vTpRvv6+Pe2qUswLSpauBzuq
 TpDsrv8/5pwZh28+91f/Unk+tH8NaVNtGe/Uf+ePxIkn1nbqL84o4NHGplM6R97d
 HAWdZQZ1cGRLf6YRRJ+57oM/5xE3vBbF1Wn0+QDTFwdsk2vcxuQ4eB3M/8E1V7Zk
 upp8ty50bZ5+rxQ8XTq/eb8epSRnfLoBYpi4ux6MIOWRdmKDl40cDeZCzA2kNP7m
 qY1haaRN3ksqvhzc0Yf6cL+CgvC4ur8gRHezfOqmBzVoaLyVEFIVjgjR/ojf0bq8
 /v+L9D5+IdIv4jEZruRRs0gOXNDzoBbvf0qKGaO0tUTWiDsv7c5AGixp8aozniHS
 HXsv1lIpRuC7WQ==
 =WxKD
 -----END PGP SIGNATURE-----

Merge tag 'x86-urgent-2020-02-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Thomas Gleixner:
 "A set of fixes for X86:

   - Ensure that the PIT is set up when the local APIC is disable or
     configured in legacy mode. This is caused by an ordering issue
     introduced in the recent changes which skip PIT initialization when
     the TSC and APIC frequencies are already known.

   - Handle malformed SRAT tables during early ACPI parsing which caused
     an infinite loop anda boot hang.

   - Fix a long standing race in the affinity setting code which affects
     PCI devices with non-maskable MSI interrupts. The problem is caused
     by the non-atomic writes of the MSI address (destination APIC id)
     and data (vector) fields which the device uses to construct the MSI
     message. The non-atomic writes are mandated by PCI.

     If both fields change and the device raises an interrupt after
     writing address and before writing data, then the MSI block
     constructs a inconsistent message which causes interrupts to be
     lost and subsequent malfunction of the device.

     The fix is to redirect the interrupt to the new vector on the
     current CPU first and then switch it over to the new target CPU.
     This allows to observe an eventually raised interrupt in the
     transitional stage (old CPU, new vector) to be observed in the APIC
     IRR and retriggered on the new target CPU and the new vector.

     The potential spurious interrupts caused by this are harmless and
     can in the worst case expose a buggy driver (all handlers have to
     be able to deal with spurious interrupts as they can and do happen
     for various reasons).

   - Add the missing suspend/resume mechanism for the HYPERV hypercall
     page which prevents resume hibernation on HYPERV guests. This
     change got lost before the merge window.

   - Mask the IOAPIC before disabling the local APIC to prevent
     potentially stale IOAPIC remote IRR bits which cause stale
     interrupt lines after resume"

* tag 'x86-urgent-2020-02-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/apic: Mask IOAPIC entries when disabling the local APIC
  x86/hyperv: Suspend/resume the hypercall page for hibernation
  x86/apic/msi: Plug non-maskable MSI affinity race
  x86/boot: Handle malformed SRAT tables during early ACPI parsing
  x86/timer: Don't skip PIT setup when APIC is disabled or in legacy mode
2020-02-09 12:11:12 -08:00

183 lines
4.7 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/acpi.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/memtype.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) { }
static int __init iommu_init_noop(void) { return 0; }
static void iommu_shutdown_noop(void) { }
bool __init bool_x86_init_noop(void) { return false; }
void x86_op_int_noop(int cpu) { }
static __init int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; }
static __init void get_rtc_noop(struct timespec64 *now) { }
static __initconst const struct of_device_id of_cmos_match[] = {
{ .compatible = "motorola,mc146818" },
{}
};
/*
* Allow devicetree configured systems to disable the RTC by setting the
* corresponding DT node's status property to disabled. Code is optimized
* out for CONFIG_OF=n builds.
*/
static __init void x86_wallclock_init(void)
{
struct device_node *node = of_find_matching_node(NULL, of_cmos_match);
if (node && !of_device_is_available(node)) {
x86_platform.get_wallclock = get_rtc_noop;
x86_platform.set_wallclock = set_rtc_noop;
}
}
/*
* 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_select = apic_intr_mode_select,
.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_wallclock_init,
},
.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,
.init_after_bootmem = x86_init_noop,
},
.acpi = {
.set_root_pointer = x86_default_set_root_pointer,
.get_root_pointer = x86_default_get_root_pointer,
.reduced_hw_early_init = acpi_generic_reduced_hw_init,
},
};
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_early,
.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_apic_ops x86_apic_ops __ro_after_init = {
.io_apic_read = native_io_apic_read,
.restore = native_restore_boot_irq_mode,
};