diff options
Diffstat (limited to 'arch/x86/kernel')
67 files changed, 25437 insertions, 6 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 577d08f4b8bb..45855c97923e 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -1,5 +1,5 @@ ifeq ($(CONFIG_X86_32),y) include ${srctree}/arch/x86/kernel/Makefile_32 else -include ${srctree}/arch/x86_64/kernel/Makefile_64 +include ${srctree}/arch/x86/kernel/Makefile_64 endif diff --git a/arch/x86/kernel/Makefile_32 b/arch/x86/kernel/Makefile_32 index 5096f486d389..cb25523026a6 100644 --- a/arch/x86/kernel/Makefile_32 +++ b/arch/x86/kernel/Makefile_32 @@ -83,6 +83,4 @@ $(obj)/vsyscall-syms.o: $(src)/vsyscall_32.lds \ $(obj)/vsyscall-sysenter_32.o $(obj)/vsyscall-note_32.o FORCE $(call if_changed,syscall) -k8-y += ../../x86_64/kernel/k8.o -stacktrace-y += ../../x86_64/kernel/stacktrace.o diff --git a/arch/x86/kernel/Makefile_64 b/arch/x86/kernel/Makefile_64 new file mode 100644 index 000000000000..6e6b5909e465 --- /dev/null +++ b/arch/x86/kernel/Makefile_64 @@ -0,0 +1,54 @@ +# +# Makefile for the linux kernel. +# + +extra-y := head_64.o head64.o init_task_64.o vmlinux.lds +EXTRA_AFLAGS := -traditional +obj-y := process_64.o signal_64.o entry_64.o traps_64.o irq_64.o \ + ptrace_64.o time_64.o ioport_64.o ldt_64.o setup_64.o i8259_64.o sys_x86_64.o \ + x8664_ksyms_64.o i387_64.o syscall_64.o vsyscall_64.o \ + setup64.o bootflag.o e820_64.o reboot_64.o quirks.o i8237.o \ + pci-dma_64.o pci-nommu_64.o alternative.o hpet_64.o tsc_64.o bugs_64.o \ + perfctr-watchdog.o + +obj-$(CONFIG_STACKTRACE) += stacktrace.o +obj-$(CONFIG_X86_MCE) += mce_64.o therm_throt.o +obj-$(CONFIG_X86_MCE_INTEL) += mce_intel_64.o +obj-$(CONFIG_X86_MCE_AMD) += mce_amd_64.o +obj-$(CONFIG_MTRR) += ../../x86/kernel/cpu/mtrr/ +obj-$(CONFIG_ACPI) += ../../x86/kernel/acpi/ +obj-$(CONFIG_X86_MSR) += msr.o +obj-$(CONFIG_MICROCODE) += microcode.o +obj-$(CONFIG_X86_CPUID) += cpuid.o +obj-$(CONFIG_SMP) += smp_64.o smpboot_64.o trampoline_64.o tsc_sync.o +obj-y += apic_64.o nmi_64.o +obj-y += io_apic_64.o mpparse_64.o genapic_64.o genapic_flat_64.o +obj-$(CONFIG_KEXEC) += machine_kexec_64.o relocate_kernel_64.o crash_64.o +obj-$(CONFIG_CRASH_DUMP) += crash_dump_64.o +obj-$(CONFIG_PM) += suspend_64.o +obj-$(CONFIG_HIBERNATION) += suspend_asm_64.o +obj-$(CONFIG_CPU_FREQ) += ../../x86/kernel/cpu/cpufreq/ +obj-$(CONFIG_EARLY_PRINTK) += early_printk.o +obj-$(CONFIG_IOMMU) += pci-gart_64.o aperture_64.o +obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o +obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o +obj-$(CONFIG_KPROBES) += kprobes_64.o +obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o +obj-$(CONFIG_X86_VSMP) += vsmp_64.o +obj-$(CONFIG_K8_NB) += k8.o +obj-$(CONFIG_AUDIT) += audit_64.o + +obj-$(CONFIG_MODULES) += module_64.o +obj-$(CONFIG_PCI) += early-quirks_64.o + +obj-y += topology.o +obj-y += intel_cacheinfo.o +obj-y += addon_cpuid_features.o +obj-y += pcspeaker.o + +CFLAGS_vsyscall_64.o := $(PROFILING) -g0 + +therm_throt-y += ../../x86/kernel/cpu/mcheck/therm_throt.o +intel_cacheinfo-y += ../../x86/kernel/cpu/intel_cacheinfo.o +addon_cpuid_features-y += ../../x86/kernel/cpu/addon_cpuid_features.o +perfctr-watchdog-y += ../../x86/kernel/cpu/perfctr-watchdog.o diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 5e3b3f5496c5..8b4357e1efe0 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -269,7 +269,7 @@ no_longmode: movb $0xbc,%al ; outb %al,$0x80 jmp no_longmode -#include "../../../x86_64/kernel/verify_cpu_64.S" +#include "../verify_cpu_64.S" /* This code uses an extended set of video mode numbers. These include: * Aliases for standard modes diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c new file mode 100644 index 000000000000..8f681cae7bf7 --- /dev/null +++ b/arch/x86/kernel/aperture_64.c @@ -0,0 +1,298 @@ +/* + * Firmware replacement code. + * + * Work around broken BIOSes that don't set an aperture or only set the + * aperture in the AGP bridge. + * If all fails map the aperture over some low memory. This is cheaper than + * doing bounce buffering. The memory is lost. This is done at early boot + * because only the bootmem allocator can allocate 32+MB. + * + * Copyright 2002 Andi Kleen, SuSE Labs. + */ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/bootmem.h> +#include <linux/mmzone.h> +#include <linux/pci_ids.h> +#include <linux/pci.h> +#include <linux/bitops.h> +#include <linux/ioport.h> +#include <asm/e820.h> +#include <asm/io.h> +#include <asm/iommu.h> +#include <asm/pci-direct.h> +#include <asm/dma.h> +#include <asm/k8.h> + +int iommu_aperture; +int iommu_aperture_disabled __initdata = 0; +int iommu_aperture_allowed __initdata = 0; + +int fallback_aper_order __initdata = 1; /* 64MB */ +int fallback_aper_force __initdata = 0; + +int fix_aperture __initdata = 1; + +static struct resource gart_resource = { + .name = "GART", + .flags = IORESOURCE_MEM, +}; + +static void __init insert_aperture_resource(u32 aper_base, u32 aper_size) +{ + gart_resource.start = aper_base; + gart_resource.end = aper_base + aper_size - 1; + insert_resource(&iomem_resource, &gart_resource); +} + +/* This code runs before the PCI subsystem is initialized, so just + access the northbridge directly. */ + +static u32 __init allocate_aperture(void) +{ + u32 aper_size; + void *p; + + if (fallback_aper_order > 7) + fallback_aper_order = 7; + aper_size = (32 * 1024 * 1024) << fallback_aper_order; + + /* + * Aperture has to be naturally aligned. This means an 2GB aperture won't + * have much chance of finding a place in the lower 4GB of memory. + * Unfortunately we cannot move it up because that would make the + * IOMMU useless. + */ + p = __alloc_bootmem_nopanic(aper_size, aper_size, 0); + if (!p || __pa(p)+aper_size > 0xffffffff) { + printk("Cannot allocate aperture memory hole (%p,%uK)\n", + p, aper_size>>10); + if (p) + free_bootmem(__pa(p), aper_size); + return 0; + } + printk("Mapping aperture over %d KB of RAM @ %lx\n", + aper_size >> 10, __pa(p)); + insert_aperture_resource((u32)__pa(p), aper_size); + return (u32)__pa(p); +} + +static int __init aperture_valid(u64 aper_base, u32 aper_size) +{ + if (!aper_base) + return 0; + if (aper_size < 64*1024*1024) { + printk("Aperture too small (%d MB)\n", aper_size>>20); + return 0; + } + if (aper_base + aper_size > 0x100000000UL) { + printk("Aperture beyond 4GB. Ignoring.\n"); + return 0; + } + if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) { + printk("Aperture pointing to e820 RAM. Ignoring.\n"); + return 0; + } + return 1; +} + +/* Find a PCI capability */ +static __u32 __init find_cap(int num, int slot, int func, int cap) +{ + u8 pos; + int bytes; + if (!(read_pci_config_16(num,slot,func,PCI_STATUS) & PCI_STATUS_CAP_LIST)) + return 0; + pos = read_pci_config_byte(num,slot,func,PCI_CAPABILITY_LIST); + for (bytes = 0; bytes < 48 && pos >= 0x40; bytes++) { + u8 id; + pos &= ~3; + id = read_pci_config_byte(num,slot,func,pos+PCI_CAP_LIST_ID); + if (id == 0xff) + break; + if (id == cap) + return pos; + pos = read_pci_config_byte(num,slot,func,pos+PCI_CAP_LIST_NEXT); + } + return 0; +} + +/* Read a standard AGPv3 bridge header */ +static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order) +{ + u32 apsize; + u32 apsizereg; + int nbits; + u32 aper_low, aper_hi; + u64 aper; + + printk("AGP bridge at %02x:%02x:%02x\n", num, slot, func); + apsizereg = read_pci_config_16(num,slot,func, cap + 0x14); + if (apsizereg == 0xffffffff) { + printk("APSIZE in AGP bridge unreadable\n"); + return 0; + } + + apsize = apsizereg & 0xfff; + /* Some BIOS use weird encodings not in the AGPv3 table. */ + if (apsize & 0xff) + apsize |= 0xf00; + nbits = hweight16(apsize); + *order = 7 - nbits; + if ((int)*order < 0) /* < 32MB */ + *order = 0; + + aper_low = read_pci_config(num,slot,func, 0x10); + aper_hi = read_pci_config(num,slot,func,0x14); + aper = (aper_low & ~((1<<22)-1)) | ((u64)aper_hi << 32); + + printk("Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n", + aper, 32 << *order, apsizereg); + + if (!aperture_valid(aper, (32*1024*1024) << *order)) + return 0; + return (u32)aper; +} + +/* Look for an AGP bridge. Windows only expects the aperture in the + AGP bridge and some BIOS forget to initialize the Northbridge too. + Work around this here. + + Do an PCI bus scan by hand because we're running before the PCI + subsystem. + + All K8 AGP bridges are AGPv3 compliant, so we can do this scan + generically. It's probably overkill to always scan all slots because + the AGP bridges should be always an own bus on the HT hierarchy, + but do it here for future safety. */ +static __u32 __init search_agp_bridge(u32 *order, int *valid_agp) +{ + int num, slot, func; + + /* Poor man's PCI discovery */ + for (num = 0; num < 256; num++) { + for (slot = 0; slot < 32; slot++) { + for (func = 0; func < 8; func++) { + u32 class, cap; + u8 type; + class = read_pci_config(num,slot,func, + PCI_CLASS_REVISION); + if (class == 0xffffffff) + break; + + switch (class >> 16) { + case PCI_CLASS_BRIDGE_HOST: + case PCI_CLASS_BRIDGE_OTHER: /* needed? */ + /* AGP bridge? */ + cap = find_cap(num,slot,func,PCI_CAP_ID_AGP); + if (!cap) + break; + *valid_agp = 1; + return read_agp(num,slot,func,cap,order); + } + + /* No multi-function device? */ + type = read_pci_config_byte(num,slot,func, + PCI_HEADER_TYPE); + if (!(type & 0x80)) + break; + } + } + } + printk("No AGP bridge found\n"); + return 0; +} + +void __init iommu_hole_init(void) +{ + int fix, num; + u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0; + u64 aper_base, last_aper_base = 0; + int valid_agp = 0; + + if (iommu_aperture_disabled || !fix_aperture || !early_pci_allowed()) + return; + + printk(KERN_INFO "Checking aperture...\n"); + + fix = 0; + for (num = 24; num < 32; num++) { + if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00))) + continue; + + iommu_detected = 1; + iommu_aperture = 1; + + aper_order = (read_pci_config(0, num, 3, 0x90) >> 1) & 7; + aper_size = (32 * 1024 * 1024) << aper_order; + aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff; + aper_base <<= 25; + + printk("CPU %d: aperture @ %Lx size %u MB\n", num-24, + aper_base, aper_size>>20); + + if (!aperture_valid(aper_base, aper_size)) { + fix = 1; + break; + } + + if ((last_aper_order && aper_order != last_aper_order) || + (last_aper_base && aper_base != last_aper_base)) { + fix = 1; + break; + } + last_aper_order = aper_order; + last_aper_base = aper_base; + } + + if (!fix && !fallback_aper_force) { + if (last_aper_base) { + unsigned long n = (32 * 1024 * 1024) << last_aper_order; + insert_aperture_resource((u32)last_aper_base, n); + } + return; + } + + if (!fallback_aper_force) + aper_alloc = search_agp_bridge(&aper_order, &valid_agp); + + if (aper_alloc) { + /* Got the aperture from the AGP bridge */ + } else if (swiotlb && !valid_agp) { + /* Do nothing */ + } else if ((!no_iommu && end_pfn > MAX_DMA32_PFN) || + force_iommu || + valid_agp || + fallback_aper_force) { + printk("Your BIOS doesn't leave a aperture memory hole\n"); + printk("Please enable the IOMMU option in the BIOS setup\n"); + printk("This costs you %d MB of RAM\n", + 32 << fallback_aper_order); + + aper_order = fallback_aper_order; + aper_alloc = allocate_aperture(); + if (!aper_alloc) { + /* Could disable AGP and IOMMU here, but it's probably + not worth it. But the later users cannot deal with + bad apertures and turning on the aperture over memory + causes very strange problems, so it's better to + panic early. */ + panic("Not enough memory for aperture"); + } + } else { + return; + } + + /* Fix up the north bridges */ + for (num = 24; num < 32; num++) { + if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00))) + continue; + + /* Don't enable translation yet. That is done later. + Assume this BIOS didn't initialise the GART so + just overwrite all previous bits */ + write_pci_config(0, num, 3, 0x90, aper_order<<1); + write_pci_config(0, num, 3, 0x94, aper_alloc>>25); + } +} diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c new file mode 100644 index 000000000000..925758dbca0c --- /dev/null +++ b/arch/x86/kernel/apic_64.c @@ -0,0 +1,1253 @@ +/* + * Local APIC handling, local APIC timers + * + * (c) 1999, 2000 Ingo Molnar <mingo@redhat.com> + * + * Fixes + * Maciej W. Rozycki : Bits for genuine 82489DX APICs; + * thanks to Eric Gilmore + * and Rolf G. Tews + * for testing these extensively. + * Maciej W. Rozycki : Various updates and fixes. + * Mikael Pettersson : Power Management for UP-APIC. + * Pavel Machek and + * Mikael Pettersson : PM converted to driver model. + */ + +#include <linux/init.h> + +#include <linux/mm.h> +#include <linux/delay.h> +#include <linux/bootmem.h> +#include <linux/interrupt.h> +#include <linux/mc146818rtc.h> +#include <linux/kernel_stat.h> +#include <linux/sysdev.h> +#include <linux/module.h> +#include <linux/ioport.h> + +#include <asm/atomic.h> +#include <asm/smp.h> +#include <asm/mtrr.h> +#include <asm/mpspec.h> +#include <asm/pgalloc.h> +#include <asm/mach_apic.h> +#include <asm/nmi.h> +#include <asm/idle.h> +#include <asm/proto.h> +#include <asm/timex.h> +#include <asm/hpet.h> +#include <asm/apic.h> + +int apic_mapped; +int apic_verbosity; +int apic_runs_main_timer; +int apic_calibrate_pmtmr __initdata; + +int disable_apic_timer __initdata; + +/* Local APIC timer works in C2? */ +int local_apic_timer_c2_ok; +EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok); + +static struct resource *ioapic_resources; +static struct resource lapic_resource = { + .name = "Local APIC", + .flags = IORESOURCE_MEM | IORESOURCE_BUSY, +}; + +/* + * cpu_mask that denotes the CPUs that needs timer interrupt coming in as + * IPIs in place of local APIC timers + */ +static cpumask_t timer_interrupt_broadcast_ipi_mask; + +/* Using APIC to generate smp_local_timer_interrupt? */ +int using_apic_timer __read_mostly = 0; + +static void apic_pm_activate(void); + +void apic_wait_icr_idle(void) +{ + while (apic_read(APIC_ICR) & APIC_ICR_BUSY) + cpu_relax(); +} + +unsigned int safe_apic_wait_icr_idle(void) +{ + unsigned int send_status; + int timeout; + + timeout = 0; + do { + send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY; + if (!send_status) + break; + udelay(100); + } while (timeout++ < 1000); + + return send_status; +} + +void enable_NMI_through_LVT0 (void * dummy) +{ + unsigned int v; + + /* unmask and set to NMI */ + v = APIC_DM_NMI; + apic_write(APIC_LVT0, v); +} + +int get_maxlvt(void) +{ + unsigned int v, maxlvt; + + v = apic_read(APIC_LVR); + maxlvt = GET_APIC_MAXLVT(v); + return maxlvt; +} + +/* + * 'what should we do if we get a hw irq event on an illegal vector'. + * each architecture has to answer this themselves. + */ +void ack_bad_irq(unsigned int irq) +{ + printk("unexpected IRQ trap at vector %02x\n", irq); + /* + * Currently unexpected vectors happen only on SMP and APIC. + * We _must_ ack these because every local APIC has only N + * irq slots per priority level, and a 'hanging, unacked' IRQ + * holds up an irq slot - in excessive cases (when multiple + * unexpected vectors occur) that might lock up the APIC + * completely. + * But don't ack when the APIC is disabled. -AK + */ + if (!disable_apic) + ack_APIC_irq(); +} + +void clear_local_APIC(void) +{ + int maxlvt; + unsigned int v; + + maxlvt = get_maxlvt(); + + /* + * Masking an LVT entry can trigger a local APIC error + * if the vector is zero. Mask LVTERR first to prevent this. + */ + if (maxlvt >= 3) { + v = ERROR_APIC_VECTOR; /* any non-zero vector will do */ + apic_write(APIC_LVTERR, v | APIC_LVT_MASKED); + } + /* + * Careful: we have to set masks only first to deassert + * any level-triggered sources. + */ + v = apic_read(APIC_LVTT); + apic_write(APIC_LVTT, v | APIC_LVT_MASKED); + v = apic_read(APIC_LVT0); + apic_write(APIC_LVT0, v | APIC_LVT_MASKED); + v = apic_read(APIC_LVT1); + apic_write(APIC_LVT1, v | APIC_LVT_MASKED); + if (maxlvt >= 4) { + v = apic_read(APIC_LVTPC); + apic_write(APIC_LVTPC, v | APIC_LVT_MASKED); + } + + /* + * Clean APIC state for other OSs: + */ + apic_write(APIC_LVTT, APIC_LVT_MASKED); + apic_write(APIC_LVT0, APIC_LVT_MASKED); + apic_write(APIC_LVT1, APIC_LVT_MASKED); + if (maxlvt >= 3) + apic_write(APIC_LVTERR, APIC_LVT_MASKED); + if (maxlvt >= 4) + apic_write(APIC_LVTPC, APIC_LVT_MASKED); + apic_write(APIC_ESR, 0); + apic_read(APIC_ESR); +} + +void disconnect_bsp_APIC(int virt_wire_setup) +{ + /* Go back to Virtual Wire compatibility mode */ + unsigned long value; + + /* For the spurious interrupt use vector F, and enable it */ + value = apic_read(APIC_SPIV); + value &= ~APIC_VECTOR_MASK; + value |= APIC_SPIV_APIC_ENABLED; + value |= 0xf; + apic_write(APIC_SPIV, value); + + if (!virt_wire_setup) { + /* For LVT0 make it edge triggered, active high, external and enabled */ + value = apic_read(APIC_LVT0); + value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING | + APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR | + APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED ); + value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING; + value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT); + apic_write(APIC_LVT0, value); + } else { + /* Disable LVT0 */ + apic_write(APIC_LVT0, APIC_LVT_MASKED); + } + + /* For LVT1 make it edge triggered, active high, nmi and enabled */ + value = apic_read(APIC_LVT1); + value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING | + APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR | + APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED); + value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING; + value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_NMI); + apic_write(APIC_LVT1, value); +} + +void disable_local_APIC(void) +{ + unsigned int value; + + clear_local_APIC(); + + /* + * Disable APIC (implies clear |