diff options
Diffstat (limited to 'arch/i386')
49 files changed, 487 insertions, 259 deletions
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index cbde675bc95..5b1a7d46d1d 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -47,15 +47,6 @@ config DMI source "init/Kconfig" -config DOUBLEFAULT - default y - bool "Enable doublefault exception handler" if EMBEDDED - help - This option allows trapping of rare doublefault exceptions that - would otherwise cause a system to silently reboot. Disabling this - option saves about 4k and might cause you much additional grey - hair. - menu "Processor type and features" choice @@ -451,12 +442,50 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" + depends on X86_CMPXCHG64 help Select this if you have a 32-bit processor and more than 4 gigabytes of physical RAM. endchoice +choice + depends on EXPERIMENTAL && !X86_PAE + prompt "Memory split" + default VMSPLIT_3G + help + Select the desired split between kernel and user memory. + + If the address range available to the kernel is less than the + physical memory installed, the remaining memory will be available + as "high memory". Accessing high memory is a little more costly + than low memory, as it needs to be mapped into the kernel first. + Note that increasing the kernel address space limits the range + available to user programs, making the address space there + tighter. Selecting anything other than the default 3G/1G split + will also likely make your kernel incompatible with binary-only + kernel modules. + + If you are not absolutely sure what you are doing, leave this + option alone! + + config VMSPLIT_3G + bool "3G/1G user/kernel split" + config VMSPLIT_3G_OPT + bool "3G/1G user/kernel split (for full 1G low memory)" + config VMSPLIT_2G + bool "2G/2G user/kernel split" + config VMSPLIT_1G + bool "1G/3G user/kernel split" +endchoice + +config PAGE_OFFSET + hex + default 0xB0000000 if VMSPLIT_3G_OPT + default 0x78000000 if VMSPLIT_2G + default 0x40000000 if VMSPLIT_1G + default 0xC0000000 + config HIGHMEM bool depends on HIGHMEM64G || HIGHMEM4G @@ -704,13 +733,22 @@ config PHYSICAL_START config HOTPLUG_CPU bool "Support for hot-pluggable CPUs (EXPERIMENTAL)" - depends on SMP && HOTPLUG && EXPERIMENTAL + depends on SMP && HOTPLUG && EXPERIMENTAL && !X86_VOYAGER ---help--- Say Y here to experiment with turning CPUs off and on. CPUs can be controlled through /sys/devices/system/cpu. Say N. +config DOUBLEFAULT + default y + bool "Enable doublefault exception handler" if EMBEDDED + help + This option allows trapping of rare doublefault exceptions that + would otherwise cause a system to silently reboot. Disabling this + option saves about 4k and might cause you much additional grey + hair. + endmenu @@ -1022,6 +1060,7 @@ source "arch/i386/oprofile/Kconfig" config KPROBES bool "Kprobes (EXPERIMENTAL)" + depends on EXPERIMENTAL && MODULES help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes diff --git a/arch/i386/boot/.gitignore b/arch/i386/boot/.gitignore new file mode 100644 index 00000000000..495f20c085d --- /dev/null +++ b/arch/i386/boot/.gitignore @@ -0,0 +1,3 @@ +bootsect +bzImage +setup diff --git a/arch/i386/boot/tools/.gitignore b/arch/i386/boot/tools/.gitignore new file mode 100644 index 00000000000..378eac25d31 --- /dev/null +++ b/arch/i386/boot/tools/.gitignore @@ -0,0 +1 @@ +build diff --git a/arch/i386/kernel/.gitignore b/arch/i386/kernel/.gitignore new file mode 100644 index 00000000000..40836ad9079 --- /dev/null +++ b/arch/i386/kernel/.gitignore @@ -0,0 +1 @@ +vsyscall.lds diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile index 60c3f76dfca..65656c033d7 100644 --- a/arch/i386/kernel/Makefile +++ b/arch/i386/kernel/Makefile @@ -7,11 +7,11 @@ extra-y := head.o init_task.o vmlinux.lds obj-y := process.o semaphore.o signal.o entry.o traps.o irq.o \ ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_i386.o \ pci-dma.o i386_ksyms.o i387.o dmi_scan.o bootflag.o \ - quirks.o i8237.o + quirks.o i8237.o topology.o obj-y += cpu/ obj-y += timers/ -obj-$(CONFIG_ACPI) += acpi/ +obj-y += acpi/ obj-$(CONFIG_X86_BIOS_REBOOT) += reboot.o obj-$(CONFIG_MCA) += mca.o obj-$(CONFIG_X86_MSR) += msr.o diff --git a/arch/i386/kernel/acpi/Makefile b/arch/i386/kernel/acpi/Makefile index 267ca48e1b6..7e9ac99354f 100644 --- a/arch/i386/kernel/acpi/Makefile +++ b/arch/i386/kernel/acpi/Makefile @@ -1,8 +1,8 @@ -obj-y := boot.o +obj-$(CONFIG_ACPI) += boot.o obj-$(CONFIG_X86_IO_APIC) += earlyquirk.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup.o ifneq ($(CONFIG_ACPI_PROCESSOR),) -obj-y += cstate.o +obj-y += cstate.o processor.o endif diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index 2111529dea7..f1a21945963 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -248,10 +248,17 @@ acpi_parse_lapic(acpi_table_entry_header * header, const unsigned long end) acpi_table_print_madt_entry(header); - /* Register even disabled CPUs for cpu hotplug */ - - x86_acpiid_to_apicid[processor->acpi_id] = processor->id; + /* Record local apic id only when enabled */ + if (processor->flags.enabled) + x86_acpiid_to_apicid[processor->acpi_id] = processor->id; + /* + * We need to register disabled CPU as well to permit + * counting disabled CPUs. This allows us to size + * cpus_possible_map more accurately, to permit + * to not preallocating memory for all NR_CPUS + * when we use CPU hotplug. + */ mp_register_lapic(processor->id, /* APIC ID */ processor->flags.enabled); /* Enabled? */ @@ -464,7 +471,7 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) * success: return IRQ number (>=0) * failure: return < 0 */ -int acpi_register_gsi(u32 gsi, int edge_level, int active_high_low) +int acpi_register_gsi(u32 gsi, int triggering, int polarity) { unsigned int irq; unsigned int plat_gsi = gsi; @@ -476,14 +483,14 @@ int acpi_register_gsi(u32 gsi, int edge_level, int active_high_low) if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) { extern void eisa_set_level_irq(unsigned int irq); - if (edge_level == ACPI_LEVEL_SENSITIVE) + if (triggering == ACPI_LEVEL_SENSITIVE) eisa_set_level_irq(gsi); } #endif #ifdef CONFIG_X86_IO_APIC if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) { - plat_gsi = mp_register_gsi(gsi, edge_level, active_high_low); + plat_gsi = mp_register_gsi(gsi, triggering, polarity); } #endif acpi_gsi_to_irq(plat_gsi, &irq); @@ -1104,9 +1111,6 @@ int __init acpi_boot_table_init(void) disable_acpi(); return error; } -#ifdef __i386__ - check_acpi_pci(); -#endif acpi_table_parse(ACPI_BOOT, acpi_parse_sbf); diff --git a/arch/i386/kernel/acpi/cstate.c b/arch/i386/kernel/acpi/cstate.c index 4c3036ba65d..25db49ef177 100644 --- a/arch/i386/kernel/acpi/cstate.c +++ b/arch/i386/kernel/acpi/cstate.c @@ -14,64 +14,6 @@ #include <acpi/processor.h> #include <asm/acpi.h> -static void acpi_processor_power_init_intel_pdc(struct acpi_processor_power - *pow) -{ - struct acpi_object_list *obj_list; - union acpi_object *obj; - u32 *buf; - - /* allocate and initialize pdc. It will be used later. */ - obj_list = kmalloc(sizeof(struct acpi_object_list), GFP_KERNEL); - if (!obj_list) { - printk(KERN_ERR "Memory allocation error\n"); - return; - } - - obj = kmalloc(sizeof(union acpi_object), GFP_KERNEL); - if (!obj) { - printk(KERN_ERR "Memory allocation error\n"); - kfree(obj_list); - return; - } - - buf = kmalloc(12, GFP_KERNEL); - if (!buf) { - printk(KERN_ERR "Memory allocation error\n"); - kfree(obj); - kfree(obj_list); - return; - } - - buf[0] = ACPI_PDC_REVISION_ID; - buf[1] = 1; - buf[2] = ACPI_PDC_C_CAPABILITY_SMP; - - obj->type = ACPI_TYPE_BUFFER; - obj->buffer.length = 12; - obj->buffer.pointer = (u8 *) buf; - obj_list->count = 1; - obj_list->pointer = obj; - pow->pdc = obj_list; - - return; -} - -/* Initialize _PDC data based on the CPU vendor */ -void acpi_processor_power_init_pdc(struct acpi_processor_power *pow, - unsigned int cpu) -{ - struct cpuinfo_x86 *c = cpu_data + cpu; - - pow->pdc = NULL; - if (c->x86_vendor == X86_VENDOR_INTEL) - acpi_processor_power_init_intel_pdc(pow); - - return; -} - -EXPORT_SYMBOL(acpi_processor_power_init_pdc); - /* * Initialize bm_flags based on the CPU cache properties * On SMP it depends on cache configuration diff --git a/arch/i386/kernel/acpi/earlyquirk.c b/arch/i386/kernel/acpi/earlyquirk.c index f1b9d2a46da..2e3b643a4dc 100644 --- a/arch/i386/kernel/acpi/earlyquirk.c +++ b/arch/i386/kernel/acpi/earlyquirk.c @@ -7,14 +7,22 @@ #include <linux/pci.h> #include <asm/pci-direct.h> #include <asm/acpi.h> +#include <asm/apic.h> static int __init check_bridge(int vendor, int device) { +#ifdef CONFIG_ACPI /* According to Nvidia all timer overrides are bogus. Just ignore them all. */ if (vendor == PCI_VENDOR_ID_NVIDIA) { acpi_skip_timer_override = 1; } +#endif + if (vendor == PCI_VENDOR_ID_ATI && timer_over_8254 == 1) { + timer_over_8254 = 0; + printk(KERN_INFO "ATI board detected. Disabling timer routing " + "over 8254.\n"); + } return 0; } diff --git a/arch/i386/kernel/acpi/processor.c b/arch/i386/kernel/acpi/processor.c new file mode 100644 index 00000000000..9f4cc02717e --- /dev/null +++ b/arch/i386/kernel/acpi/processor.c @@ -0,0 +1,75 @@ +/* + * arch/i386/kernel/acpi/processor.c + * + * Copyright (C) 2005 Intel Corporation + * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * - Added _PDC for platforms with Intel CPUs + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/acpi.h> + +#include <acpi/processor.h> +#include <asm/acpi.h> + +static void init_intel_pdc(struct acpi_processor *pr, struct cpuinfo_x86 *c) +{ + struct acpi_object_list *obj_list; + union acpi_object *obj; + u32 *buf; + + /* allocate and initialize pdc. It will be used later. */ + obj_list = kmalloc(sizeof(struct acpi_object_list), GFP_KERNEL); + if (!obj_list) { + printk(KERN_ERR "Memory allocation error\n"); + return; + } + + obj = kmalloc(sizeof(union acpi_object), GFP_KERNEL); + if (!obj) { + printk(KERN_ERR "Memory allocation error\n"); + kfree(obj_list); + return; + } + + buf = kmalloc(12, GFP_KERNEL); + if (!buf) { + printk(KERN_ERR "Memory allocation error\n"); + kfree(obj); + kfree(obj_list); + return; + } + + buf[0] = ACPI_PDC_REVISION_ID; + buf[1] = 1; + buf[2] = ACPI_PDC_C_CAPABILITY_SMP; + + if (cpu_has(c, X86_FEATURE_EST)) + buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP; + + obj->type = ACPI_TYPE_BUFFER; + obj->buffer.length = 12; + obj->buffer.pointer = (u8 *) buf; + obj_list->count = 1; + obj_list->pointer = obj; + pr->pdc = obj_list; + + return; +} + +/* Initialize _PDC data based on the CPU vendor */ +void arch_acpi_processor_init_pdc(struct acpi_processor *pr) +{ + unsigned int cpu = pr->id; + struct cpuinfo_x86 *c = cpu_data + cpu; + + pr->pdc = NULL; + if (c->x86_vendor == X86_VENDOR_INTEL) + init_intel_pdc(pr, c); + + return; +} + +EXPORT_SYMBOL(arch_acpi_processor_init_pdc); diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index acd3f1e34ca..776c90989e0 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -75,8 +75,10 @@ void ack_bad_irq(unsigned int irq) * holds up an irq slot - in excessive cases (when multiple * unexpected vectors occur) that might lock up the APIC * completely. + * But only ack when the APIC is enabled -AK */ - ack_APIC_irq(); + if (cpu_has_apic) + ack_APIC_irq(); } void __init apic_intr_init(void) @@ -568,16 +570,18 @@ void __devinit setup_local_APIC(void) */ void lapic_shutdown(void) { + unsigned long flags; + if (!cpu_has_apic) return; - local_irq_disable(); + local_irq_save(flags); clear_local_APIC(); if (enabled_via_apicbase) disable_local_APIC(); - local_irq_enable(); + local_irq_restore(flags); } #ifdef CONFIG_PM @@ -1303,6 +1307,7 @@ int __init APIC_init_uniprocessor (void) if (!cpu_has_apic && APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) { printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n", boot_cpu_physical_apicid); + clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability); return -1; } diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c index 333578a4e91..0810f81f2a0 100644 --- a/arch/i386/kernel/cpu/amd.c +++ b/arch/i386/kernel/cpu/amd.c @@ -282,3 +282,11 @@ int __init amd_init_cpu(void) } //early_arch_initcall(amd_init_cpu); + +static int __init amd_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_AMD] = NULL; + return 0; +} + +late_initcall(amd_exit_cpu); diff --git a/arch/i386/kernel/cpu/centaur.c b/arch/i386/kernel/cpu/centaur.c index 394814e5767..f52669ecb93 100644 --- a/arch/i386/kernel/cpu/centaur.c +++ b/arch/i386/kernel/cpu/centaur.c @@ -405,10 +405,6 @@ static void __init init_centaur(struct cpuinfo_x86 *c) winchip2_protect_mcr(); #endif break; - case 10: - name="4"; - /* no info on the WC4 yet */ - break; default: name="??"; } @@ -474,3 +470,11 @@ int __init centaur_init_cpu(void) } //early_arch_initcall(centaur_init_cpu); + +static int __init centaur_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_CENTAUR] = NULL; + return 0; +} + +late_initcall(centaur_exit_cpu); diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index 15aee26ec2b..e6bd095ae10 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -4,6 +4,7 @@ #include <linux/smp.h> #include <linux/module.h> #include <linux/percpu.h> +#include <linux/bootmem.h> #include <asm/semaphore.h> #include <asm/processor.h> #include <asm/i387.h> @@ -18,6 +19,9 @@ #include "cpu.h" +DEFINE_PER_CPU(struct Xgt_desc_struct, cpu_gdt_descr); +EXPORT_PER_CPU_SYMBOL(cpu_gdt_descr); + DEFINE_PER_CPU(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]); EXPORT_PER_CPU_SYMBOL(cpu_16bit_stack); @@ -44,6 +48,7 @@ static void default_init(struct cpuinfo_x86 * c) static struct cpu_dev default_cpu = { .c_init = default_init, + .c_vendor = "Unknown", }; static struct cpu_dev * this_cpu = &default_cpu; @@ -150,6 +155,7 @@ static void __devinit get_cpu_vendor(struct cpuinfo_x86 *c, int early) { char *v = c->x86_vendor_id; int i; + static int printed; for (i = 0; i < X86_VENDOR_NUM; i++) { if (cpu_devs[i]) { @@ -159,10 +165,17 @@ static void __devinit get_cpu_vendor(struct cpuinfo_x86 *c, int early) c->x86_vendor = i; if (!early) this_cpu = cpu_devs[i]; - break; + return; } } } + if (!printed) { + printed++; + printk(KERN_ERR "CPU: Vendor unknown, using generic init.\n"); + printk(KERN_ERR "CPU: Your system may be unstable.\n"); + } + c->x86_vendor = X86_VENDOR_UNKNOWN; + this_cpu = &default_cpu; } @@ -265,10 +278,10 @@ void __devinit generic_identify(struct cpuinfo_x86 * c) c->x86_capability[4] = excap; c->x86 = (tfms >> 8) & 15; c->x86_model = (tfms >> 4) & 15; - if (c->x86 == 0xf) { + if (c->x86 == 0xf) c->x86 += (tfms >> 20) & 0xff; + if (c->x86 >= 0x6) c->x86_model += ((tfms >> 16) & 0xF) << 4; - } c->x86_mask = tfms & 15; } else { /* Have CPUID level 0 only - unheard of */ @@ -562,8 +575,9 @@ void __devinit cpu_init(void) int cpu = smp_processor_id(); struct tss_struct * t = &per_cpu(init_tss, cpu); struct thread_struct *thread = ¤t->thread; - struct desc_struct *gdt = get_cpu_gdt_table(cpu); + struct desc_struct *gdt; __u32 stk16_off = (__u32)&per_cpu(cpu_16bit_stack, cpu); + struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu); if (cpu_test_and_set(cpu, cpu_initialized)) { printk(KERN_WARNING "CPU#%d already initialized!\n", cpu); @@ -581,6 +595,25 @@ void __devinit cpu_init(void) } /* + * This is a horrible hack to allocate the GDT. The problem + * is that cpu_init() is called really early for the boot CPU + * (and hence needs bootmem) but much later for the secondary + * CPUs, when bootmem will have gone away + */ + if (NODE_DATA(0)->bdata->node_bootmem_map) { + gdt = (struct desc_struct *)alloc_bootmem_pages(PAGE_SIZE); + /* alloc_bootmem_pages panics on failure, so no check */ + memset(gdt, 0, PAGE_SIZE); + } else { + gdt = (struct desc_struct *)get_zeroed_page(GFP_KERNEL); + if (unlikely(!gdt)) { + printk(KERN_CRIT "CPU%d failed to allocate GDT\n", cpu); + for (;;) + local_irq_enable(); + } + } + + /* * Initialize the per-CPU GDT with the boot GDT, * and set up the GDT descriptor: */ @@ -592,10 +625,10 @@ void __devinit cpu_init(void) ((((__u64)stk16_off) << 32) & 0xff00000000000000ULL) | (CPU_16BIT_STACK_SIZE - 1); - cpu_gdt_descr[cpu].size = GDT_SIZE - 1; - cpu_gdt_descr[cpu].address = (unsigned long)gdt; + cpu_gdt_descr->size = GDT_SIZE - 1; + cpu_gdt_descr->address = (unsigned long)gdt; - load_gdt(&cpu_gdt_descr[cpu]); + load_gdt(cpu_gdt_descr); load_idt(&idt_descr); /* diff --git a/arch/i386/kernel/cpu/cpufreq/Kconfig b/arch/i386/kernel/cpu/cpufreq/Kconfig index 0f1eb507233..26892d2099b 100644 --- a/arch/i386/kernel/cpu/cpufreq/Kconfig +++ b/arch/i386/kernel/cpu/cpufreq/Kconfig @@ -96,6 +96,7 @@ config X86_POWERNOW_K8_ACPI config X86_GX_SUSPMOD tristate "Cyrix MediaGX/NatSemi Geode Suspend Modulation" + depends on PCI help This add the CPUFreq driver for NatSemi Geode processors which support suspend modulation. diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c index 7975e79d5fa..3852d0a4c1b 100644 --- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -295,68 +295,6 @@ acpi_cpufreq_guess_freq ( } -/* - * acpi_processor_cpu_init_pdc_est - let BIOS know about the SMP capabilities - * of this driver - * @perf: processor-specific acpi_io_data struct - * @cpu: CPU being initialized - * - * To avoid issues with legacy OSes, some BIOSes require to be informed of - * the SMP capabilities of OS P-state driver. Here we set the bits in _PDC - * accordingly, for Enhanced Speedstep. Actual call to _PDC is done in - * driver/acpi/processor.c - */ -static void -acpi_processor_cpu_init_pdc_est( - struct acpi_processor_performance *perf, - unsigned int cpu, - struct acpi_object_list *obj_list - ) -{ - union acpi_object *obj; - u32 *buf; - struct cpuinfo_x86 *c = cpu_data + cpu; - dprintk("acpi_processor_cpu_init_pdc_est\n"); - - if (!cpu_has(c, X86_FEATURE_EST)) - return; - - /* Initialize pdc. It will be used later. */ - if (!obj_list) - return; - - if (!(obj_list->count && obj_list->pointer)) - return; - - obj = obj_list->pointer; - if ((obj->buffer.length == 12) && obj->buffer.pointer) { - buf = (u32 *)obj->buffer.pointer; - buf[0] = ACPI_PDC_REVISION_ID; - buf[1] = 1; - buf[2] = ACPI_PDC_EST_CAPABILITY_SMP; - perf->pdc = obj_list; - } - return; -} - - -/* CPU specific PDC initialization */ -static void -acpi_processor_cpu_init_pdc( - struct acpi_processor_performance *perf, - unsigned int cpu, - struct acpi_object_list *obj_list - ) -{ - struct cpuinfo_x86 *c = cpu_data + cpu; - dprintk("acpi_processor_cpu_init_pdc\n"); - perf->pdc = NULL; - if (cpu_has(c, X86_FEATURE_EST)) - acpi_processor_cpu_init_pdc_est(perf, cpu, obj_list); - return; -} - - static int acpi_cpufreq_cpu_init ( struct cpufreq_policy *policy) @@ -367,14 +305,7 @@ acpi_cpufreq_cpu_init ( unsigned int result = 0; struct cpuinfo_x86 *c = &cpu_data[policy->cpu]; - union acpi_object arg0 = {ACPI_TYPE_BUFFER}; - u32 arg0_buf[3]; - struct acpi_object_list arg_list = {1, &arg0}; - dprintk("acpi_cpufreq_cpu_init\n"); - /* setup arg_list for _PDC settings */ - arg0.buffer.length = 12; - arg0.buffer.pointer = (u8 *) arg0_buf; data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL); if (!data) @@ -382,9 +313,7 @@ acpi_cpufreq_cpu_init ( acpi_io_data[cpu] = data; - acpi_processor_cpu_init_pdc(&data->acpi_data, cpu, &arg_list); result = acpi_processor_register_performance(&data->acpi_data, cpu); - data->acpi_data.pdc = NULL; if (result) goto err_free; diff --git a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c index 270f2188d68..cc73a7ae34b 100644 --- a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c @@ -52,6 +52,7 @@ enum { static int has_N44_O17_errata[NR_CPUS]; +static int has_N60_errata[NR_CPUS]; static unsigned int stock_freq; static struct cpufreq_driver p4clockmod_driver; static unsigned int cpufreq_p4_get(unsigned int cpu); @@ -226,6 +227,12 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) case 0x0f12: has_N44_O17_errata[policy->cpu] = 1; dprintk("has errata -- disabling low frequencies\n"); + break; + + case 0x0f29: + has_N60_errata[policy->cpu] = 1; + dprintk("has errata -- disabling frequencies lower than 2ghz\n"); + break; } /* get max frequency */ @@ -237,6 +244,8 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) for (i=1; (p4clockmod_table[i].frequency != CPUFREQ_TABLE_END); i++) { if ((i<2) && (has_N44_O17_errata[policy->cpu])) p4clockmod_table[i].frequency = CPUFREQ_ENTRY_INVALID; + else if (has_N60_errata[policy->cpu] && p4clockmod_table[i].frequency < 2000000) + p4clockmod_table[i].frequency = CPUFREQ_ENTRY_INVALID; else p4clockmod_table[i].frequency = (stock_freq * i)/8; } diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c index 9a826cde4fd..c173c0fa117 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c @@ -362,22 +362,10 @@ static struct acpi_processor_performance p; */ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) { - union acpi_object arg0 = {ACPI_TYPE_BUFFER}; - u32 arg0_buf[3]; - struct acpi_object_list arg_list = {1, &arg0}; unsigned long cur_freq; int result = 0, i; unsigned int cpu = policy->cpu; - /* _PDC settings */ - arg0.buffer.length = 12; - arg0.buffer.pointer = (u8 *) arg0_buf; - arg0_buf[0] = ACPI_PDC_REVISION_ID; - arg0_buf[1] = 1; - arg0_buf[2] = ACPI_PDC_EST_CAPABILITY_SMP_MSR; - - p.pdc = &arg_list; - /* register with ACPI core */ if (acpi_processor_register_performance(&p, cpu)) { dprintk(KERN_INFO PFX "obtaining ACPI data failed\n"); diff --git a/arch/i386/kernel/cpu/cyrix.c b/arch/i386/kernel/cpu/cyrix.c index 75015975d03..00f2e058797 100644 --- a/arch/i386/kernel/cpu/cyrix.c +++ b/arch/i386/kernel/cpu/cyrix.c @@ -345,7 +345,7 @@ static void __init init_cyrix(struct cpuinfo_x86 *c) /* * Handle National Semiconductor branded processors */ -static void __devinit init_nsc(struct cpuinfo_x86 *c) +static void __init init_nsc(struct cpuinfo_x86 *c) { /* There may be GX1 processors in the wild that are branded * NSC and not Cyrix. @@ -444,6 +444,14 @@ int __init cyrix_init_cpu(void) //early_arch_initcall(cyrix_init_cpu); +static int __init cyrix_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_CYRIX] = NULL; + return 0; +} + +late_initcall(cyrix_exit_cpu); + static struct cpu_dev nsc_cpu_dev __initdata = { .c_vendor = "NSC", .c_ident = { "Geode by NSC" }, @@ -458,3 +466,11 @@ int __init nsc_init_cpu(void) } //early_arch_initcall(nsc_init_cpu); + +static int __init nsc_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_NSC] = NULL; + return 0; +} + +late_initcall(nsc_exit_cpu); diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index fbfd374aa33..ffe58cee0c4 100644 --- a/arch/i386/kernel/cpu/intel_cacheinfo.c +++ b/arch/i386/kernel/cpu/intel_cacheinfo.c @@ -43,13 +43,23 @@ static struct _cache_table cache_table[] __cpuinitdata = { 0x2c, LVL_1_DATA, 32 }, /* 8-way set assoc, 64 byte line size */ { 0x30, LVL_1_INST, 32 }, /* 8-way set assoc, 64 byte line size */ { 0x39, LVL_2, 128 }, /* 4-way set assoc, sectored cache, 64 byte line size */ + { 0x3a, LVL_2, 192 }, /* 6-way set assoc, sectored cache, 64 byte line size */ { 0x3b, LVL_2, 128 }, /* 2-way set assoc, sectored cache, 64 byte line size */ { 0x3c, LVL_2, 256 }, /* 4-way set assoc, sectored cache, 64 byte line size */ + { 0x3d, LVL_2, 384 }, /* 6-way set assoc, sectored cache, 64 byte line size */ + { 0x3e, LVL_2, 512 }, /* 4-way set assoc, sectored cache, 64 byte line size */ { 0x41, LVL_2, 128 }, /* 4-way set assoc, 32 byte line size */ { 0x42, LVL_2, 256 }, /* 4-way set assoc, 32 byte line size */ { 0x43, LVL_2, 512 }, /* 4-way set assoc, 32 byte line size */ { 0x44, LVL_2, 1024 }, /* 4-way set assoc, 32 byte line size */ { 0x45, LVL_2, 2048 }, /* 4-way set assoc, 32 byte line size */ + { 0x46, LVL_3, 4096 }, /* 4-way set assoc, 64 byte line size */ + { 0x47, LVL_3, 8192 }, /* 8-way set assoc, 64 byte line size */ + { 0x49, LVL_3, 4096 }, /* 16-way set assoc, 64 byte line size */ + { 0x4a, LVL_3, 6144 }, /* 12-way set assoc, 64 byte line size */ + { 0x4b, LVL_3, 8192 }, /* 16-way set assoc, 64 byte line size */ + { 0x4c, LVL_3, 12288 }, /* 12-way set assoc, 64 byte line size */ + { 0x4d, LVL_3, 16384 }, /* 16-way set assoc, 64 byte line size */ { 0x60, LVL_1_DATA, 16 }, /* 8-way set assoc, sectored cache, 64 byte line size */ { 0x66, LVL_1_DATA, 8 }, /* 4-way set assoc, sectored cache, 64 byte line size */ { 0x67, LVL_1_DATA, 16 }, /* 4-way set assoc, sectored cache, 64 byte line size */ @@ -57,6 +67,7 @@ static struct _cache_table cache_table[] __cpuinitdata = { 0x70, LVL_TRACE, 12 }, /* 8-way set assoc */ { 0x71, LVL_TRACE, 16 }, /* 8-way set assoc */ { 0x72, LVL_TRACE, 32 }, /* 8-way set assoc */ + { 0x73, LVL_TRACE, 64 }, /* 8-way set assoc */ { 0x78, LVL_2, 1024 }, /* 4-way set assoc, 64 byte line size */ { 0x79, LVL_2, 128 }, /* 8-way set assoc, sectored cache, 64 byte line size */ { 0x7a, LVL_2, 256 }, /* 8-way set assoc, sectored cache, 64 byte line size */ @@ -141,6 +152,7 @@ static int __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_le return 0; } +/* will only be called once; __init is safe here */ static int __init find_num_cache_leaves(void) { unsigned int eax, ebx, ecx, edx; diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c index 1e9db198c44..3b4618bed70 100644 --- a/arch/i386/kernel/cpu/mtrr/main.c +++ b/arch/i386/kernel/cpu/mtrr/main.c @@ -44,12 +44,10 @@ #include <asm/msr.h> #include "mtrr.h" -#define MTRR_VERSION "2.0 (20020519)" - u32 num_var_ranges = 0; unsigned int *usage_table; -static DECLARE_MUTEX(main_lock); +static DECLARE_MUTEX(mtrr_sem); u32 size_or_mask, size_and_mask; @@ -335,7 +333,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, /* No CPU hotplug when we change MTRR entries */ lock_cpu_hotplug(); /* Search for existing MTRR */ - down(&main_lock); + down(&mtrr_sem); for (i = 0; i < num_var_ranges; ++i) { mtrr_if->get(i, &lbase, &lsize, <ype); if (base >= lbase + lsize) @@ -373,7 +371,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, printk(KERN_INFO "mtrr: no more MTRRs available\n"); error = i; out: - up(&main_lock); + up(&mtrr_sem); unlock_cpu_hotplug(); return error; } @@ -466,7 +464,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) max = num_var_ranges; /* No CPU hotplug when we change MTRR entries */ lock_cpu_hotplug(); - down(&main_lock); + down(&mtrr_sem); if (reg < 0) { /* Search for existing MTRR */ for (i = 0; i < max; ++i) { @@ -505,7 +503,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) set_mtrr(reg, 0, 0, 0); error = reg; out: - up(&main_lock); + up(&mtrr_sem); unlock_cpu_hotplug(); return error; } @@ -671,7 +669,6 @@ void __init mtrr_bp_init(void) break; } } - printk(KERN_INFO "mtrr: v%s\n",MTRR_VERSION); if (mtrr_if) { set_num_var_ranges(); @@ -688,7 +685,7 @@ void mtrr_ap_init(void) if (!mtrr_if || !use_intel()) return; /* - * Ideally we should hold main_lock here to avoid mtrr entries changed, + * Ideally we should hold mtrr_sem here to avoid mtrr entries changed, * but this routine will be called in cpu boot time, holding the lock * breaks it. This routine is called in two cases: 1.very earily time * of software resume, when there absolutely isn't mtrr entry changes; diff --git a/arch/i386/kernel/cpu/nexgen.c b/arch/i386/kernel/cpu/nexgen.c index 30898a260a5..ad87fa58058 100644 --- a/arch/i386/kernel/cpu/nexgen.c +++ b/arch/i386/kernel/cpu/nexgen.c @@ -61,3 +61,11 @@ int __init nexgen_init_cpu(void) } //early_arch_initcall(nexgen_init_cpu); + +static int __init nexgen_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_NEXGEN] = NULL; + return 0; +} + +late_initcall(nexgen_exit_cpu); diff --git a/arch/i386/kernel/cpu/rise.c b/arch/i386/kernel/cpu/rise.c index 8602425628c..d08d5a2811c 100644 --- a/arch/i386/kernel/cpu/rise.c +++ b/arch/i386/kernel/cpu/rise.c @@ -51,3 +51,11 @@ int __init rise_init_cpu(void) } //early_arch_initcall(rise_init_cpu); + +static int __init rise_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_RISE] = NULL; + return 0; +} + +late_initcall(rise_exit_cpu); diff --git a/arch/i386/kernel/cpu/transmeta.c b/arch/i386/kernel/cpu/transmeta.c index fc426380366..7214c9b577a 100644 --- a/arch/i386/kernel/cpu/transmeta.c +++ b/arch/i386/kernel/cpu/transmeta.c @@ -1,4 +1,5 @@ #include <linux/kernel.h> +#include <linux/mm.h> #include <linux/init.h> #include <asm/processor.h> #include <asm/msr.h> @@ -84,7 +85,7 @@ static void __init init_transmeta(struct cpuinfo_x86 *c) #endif } -static void transmeta_identify(struct cpuinfo_x86 * c) +static void __init transmeta_identify(struct cpuinfo_x86 * c) { u32 xlvl; generic_identify(c); @@ -111,3 +112,11 @@ int __init transmeta_init_cpu(void) } //early_arch_initcall(transmeta_init_cpu); + +static int __init transmeta_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_TRANSMETA] = NULL; + return 0; +} + +late_initcall(transmeta_exit_cpu); diff --git a/arch/i386/kernel/cpu/umc.c b/arch/i386/kernel/cpu/umc.c index 264fcad559d..2cd988f6dc5 100644 --- a/arch/i386/kernel/cpu/umc.c +++ b/arch/i386/kernel/cpu/umc.c @@ -31,3 +31,11 @@ int __init umc_init_cpu(void) } //early_arch_initcall(umc_init_cpu); + +static int __init umc_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_UMC] = NULL; + return 0; +} + +late_initcall(umc_exit_cpu); diff --git a/arch/i386/kernel/efi.c b/arch/i386/kernel/efi.c index ecad519fd39..c9cad7ba0d2 100644 --- a/arch/i386/kernel/efi.c +++ b/arch/i386/kernel/efi.c @@ -70,10 +70,13 @@ static void efi_call_phys_prelog(void) { unsigned long cr4; unsigned long temp; + struct Xgt_desc_struct *cpu_gdt_descr; spin_lock(&efi_rt_lock); local_irq_save(efi_rt_eflags); + cpu_gdt_descr = &per_cpu(cpu_gdt_descr, 0); + /* * If I don't have PSE, I should just duplicate two entries in page * directory. If I have PSE, I just need to duplicate one entry in @@ -103,17 +106,18 @@ static void efi_call_phys_prelog(void) */ local_flush_tlb(); - cpu_gdt_descr[0].address = __pa(cpu_gdt_descr[0].address); - load_gdt((struct Xgt_desc_struct *) __pa(&cpu_gdt_descr[0])); + cpu_gdt_descr->address = __pa(cpu_gdt_descr->address); + load_gdt(cpu_gdt_descr); } static void efi_call_phys_epilog(void) { unsigned long cr4; + struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, 0); + + cpu_gdt_descr->address = __va(cpu_gdt_descr->address); + load_gdt(cpu_gdt_descr); - cpu_gdt_descr[0].address = - (unsigned long) __va(cpu_gdt_descr[0].address); - load_gdt(&cpu_gdt_descr[0]); cr4 = read_cr4(); if (cr4 & X86_CR4_PSE) { diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S index 5884469f6bf..e0b7c632efb 100644 --- a/arch/i386/kernel/head.S +++ b/arch/i386/kernel/head.S @@ -398,7 +398,11 @@ ignore_int: pushl 32(%esp) pushl 40(%esp) pushl $int_msg +#ifdef CONFIG_EARLY_PRINTK + call early_printk +#else call printk +#endif addl $(5*4),%esp popl %ds popl %es @@ -530,5 +534,3 @@ ENTRY(cpu_gdt_table) .quad 0x0000000000000000 /* 0xf0 - unused */ .quad 0x0000000000000000 /* 0xf8 - GDT entry 31: double-fault TSS */ - /* Be sure this is zeroed to avoid false validations in Xen */ - .fill PAGE_SIZE_asm / 8 - GDT_ENTRIES,8,0 diff --git a/arch/i386/kernel/i386_ksyms.c b/arch/i386/kernel/i386_ksyms.c index 3999bec50c3..055325056a7 100644 --- a/arch/i386/kernel/i386_ksyms.c +++ b/arch/i386/kernel/i386_ksyms.c @@ -3,8 +3,6 @@ #include <asm/checksum.h> #include <asm/desc.h> -EXPORT_SYMBOL_GPL(cpu_gdt_descr); - EXPORT_SYMBOL(__down_failed); EXPORT_SYMBOL(__down_failed_interruptible); EXPORT_SYMBOL(__down_failed_trylock); diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c index f2dd218d88c..39d9a5fa907 100644 --- a/arch/i386/kernel/io_apic.c +++ b/arch/i386/kernel/io_apic.c @@ -51,6 +51,8 @@ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; static DEFINE_SPINLOCK(ioapic_lock); +int timer_over_8254 __initdata = 1; + /* * Is the SiS APIC rmw bug present ? * -1 = don't know, 0 = no, 1 = yes @@ -2267,7 +2269,8 @@ static inline void check_timer(void) apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); init_8259A(1); timer_ack = 1; - enable_8259A_irq(0); + if (timer_over_8254 > 0) + enable_8259A_irq(0); pin1 = find_isa_irq_pin(0, mp_INT); apic1 = find_isa_irq_apic(0, mp_INT); @@ -2392,6 +2395,20 @@ void __init setup_IO_APIC(void) print_IO_APIC(); } +static int __init setup_disable_8254_timer(char *s) +{ + timer_over_8254 = -1; + return 1; +} +static int __init setup_enable_8254_timer(char *s) +{ + timer_over_8254 = 2; + return 1; +} + +__setup("disable_8254_timer", setup_disable_8254_timer); +__setup("enable_8254_timer", setup_enable_8254_timer); + /* * Called after all the initialization is done. If we didnt find any * APIC bugs then we can allow the modify fast path @@ -2566,8 +2583,10 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id) spin_unlock_irqrestore(&ioapic_lock, flags); /* Sanity check */ - if (reg_00.bits.ID != apic_id) - panic("IOAPIC[%d]: Unable change apic_id!\n", ioapic); + if (reg_00.bits.ID != apic_id) { + printk("IOAPIC[%d]: Unable to change apic_id!\n", ioapic); + return -1; + } } apic_printk(APIC_VERBOSE, KERN_INFO diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c index 6483eeb1a4e..694a1399763 100644 --- a/arch/i386/kernel/kprobes.c +++ b/arch/i386/kernel/kprobes.c @@ -58,6 +58,11 @@ static inline int is_IF_modifier(kprobe_opcode_t opcode) int __kprobes arch_prepare_kprobe(struct kprobe *p) { + /* insn: must be on special executable page on i386. */ + p->ainsn.insn = get_insn_slot(); + if (!p->ainsn.insn) + return -ENOMEM; + memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); p->opcode = *p->addr; return 0; @@ -77,6 +82,13 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p) (unsigned long) p->addr + sizeof(kprobe_opcode_t)); } +void __kprobes arch_remove_kprobe(struct kprobe *p) +{ + down(&kprobe_mutex); + free_insn_slot(p->ainsn.insn); + up(&kprobe_mutex); +} + static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb) { kcb->prev_kprobe.kp = kprobe_running(); @@ -111,7 +123,7 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) if (p->opcode == BREAKPOINT_INSTRUCTION) regs->eip = (unsigned long)p->addr; else - regs->eip = (unsigned long)&p->ainsn.insn; + regs->eip = (unsigned long)p->ainsn.insn; } /* Called with kretprobe_lock held */ @@ -351,7 +363,7 @@ static void __kprobes resume_execution(struct kprobe *p, { unsigned long *tos = (unsigned long *)®s->esp; unsigned long next_eip = 0; - unsigned long copy_eip = (unsigned long)&p->ainsn.insn; + unsigned long copy_eip = (unsigned long)p->ainsn.insn; unsigned long orig_eip = (unsigned long)p->addr; switch (p->ainsn.insn[0]) { diff --git a/arch/i386/kernel/machine_kexec.c b/arch/i386/kernel/machine_kexec.c index a912fed4848..f73d7374a2b 100644 --- a/arch/i386/kernel/machine_kexec.c +++ b/arch/i386/kernel/machine_kexec.c @@ -116,13 +116,13 @@ static void load_segments(void) __asm__ __volatile__ ( "\tljmp $"STR(__KERNEL_CS)",$1f\n" "\t1:\n" - "\tmovl $"STR(__KERNEL_DS)",%eax\n" - "\tmovl %eax,%ds\n" - "\tmovl %eax,%es\n" - "\tmovl %eax,%fs\n" - "\tmovl %eax,%gs\n" - "\tmovl %eax,%ss\n" - ); + "\tmovl $"STR(__KERNEL_DS)",%%eax\n" + "\tmovl %%eax,%%ds\n" + "\tmovl %%eax,%%es\n" + "\tmovl %%eax,%%fs\n" + "\tmovl %%eax,%%gs\n" + "\tmovl %%eax,%%ss\n" + ::: "eax", "memory"); #undef STR #undef __STR } diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c index d3fdf0057d8..5390b521aca 100644 --- a/arch/i386/kernel/microcode.c +++ b/arch/i386/kernel/microcode.c @@ -74,6 +74,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/sched.h> +#include <linux/cpumask.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/vmalloc.h> @@ -250,8 +251,8 @@ static int find_matching_ucodes (void) error = -EINVAL; goto out; } - - for (cpu_num = 0; cpu_num < num_online_cpus(); cpu_num++) { + + for_each_online_cpu(cpu_num) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; if (uci->err != MC_NOTFOUND) /* already found a match or not an online cpu*/ continue; @@ -293,7 +294,7 @@ static int find_matching_ucodes (void) error = -EFAULT; goto out; } - for (cpu_num = 0; cpu_num < num_online_cpus(); cpu_num++) { + for_each_online_cpu(cpu_num) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; if (uci->err != MC_NOTFOUND) /* already found a match or not an online cpu*/ continue; @@ -304,7 +305,9 @@ static int find_matching_ucodes (void) } } /* now check if any cpu has matched */ - for (cpu_num = 0, allocated_flag = 0, sum = 0; cpu_num < num_online_cpus(); cpu_num++) { + allocated_flag = 0; + sum = 0; + for_each_online_cpu(cpu_num) { if (ucode_cpu_info[cpu_num].err == MC_MARKED) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; if (!allocated_flag) { @@ -415,12 +418,12 @@ static int do_microcode_update (void) } out_free: - for (i = 0; i < num_online_cpus(); i++) { + for_each_online_cpu(i) { if (ucode_cpu_info[i].mc) { int j; void *tmp = ucode_cpu_info[i].mc; vfree(tmp); - for (j = i; j < num_online_cpus(); j++) { + for_each_online_cpu(j) { if (ucode_cpu_info[j].mc == tmp) ucode_cpu_info[j].mc = NULL; } diff --git a/arch/i386/kernel/mpparse.c b/arch/i386/kernel/mpparse.c index 91a64016956..e6e2f43db85 100644 --- a/arch/i386/kernel/mpparse.c +++ b/arch/i386/kernel/mpparse.c @@ -710,7 +710,7 @@ void __init get_smp_config (void) * Read the physical hardware table. Anything here will * override the defaults. */ - if (!smp_read_mpc((void *)mpf->mpf_physptr)) { + if (!smp_read_mpc(phys_to_virt(mpf->mpf_physptr))) { smp_found_config = 0; printk(KERN_ERR "BIOS bug, MP table errors detected!...\n"); printk(KERN_ERR "... disabling SMP support. (tell your hw vendor)\n"); @@ -915,6 +915,7 @@ void __init mp_register_ioapic ( u32 gsi_base) { int idx = 0; + int tmpid; if (nr_ioapics >= MAX_IO_APICS) { printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded " @@ -935,9 +936,14 @@ void __init mp_register_ioapic ( set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 < 15)) - mp_ioapics[idx].mpc_apicid = io_apic_get_unique_id(idx, id); + tmpid = io_apic_get_unique_id(idx, id); else - mp_ioapics[idx].mpc_apicid = id; + tmpid = id; + if (tmpid == -1) { + nr_ioapics--; + return; + } + mp_ioapics[idx].mpc_apicid = tmpid; mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx); /* @@ -1080,7 +1086,7 @@ void __init mp_config_acpi_legacy_irqs (void) #define MAX_GSI_NUM 4096 -int mp_register_gsi (u32 gsi, int edge_level, int active_high_low) +int mp_register_gsi (u32 gsi, int triggering, int polarity) { int ioapic = -1; int ioapic_pin = 0; @@ -1129,7 +1135,7 @@ int mp_register_gsi (u32 gsi, int edge_level, int active_high_low) mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<<bit); - if (edge_level) { + if (triggering == ACPI_LEVEL_SENSITIVE) { /* * For PCI devices assign IRQs in order, avoiding gaps * due to unused I/O APIC pins. @@ -1151,8 +1157,8 @@ int mp_register_gsi (u32 gsi, int edge_level, int active_high_low) } io_apic_set_pci_routing(ioapic, ioapic_pin, gsi, - edge_level == ACPI_EDGE_SENSITIVE ? 0 : 1, - active_high_low == ACPI_ACTIVE_HIGH ? 0 : 1); + triggering == ACPI_EDGE_SENSITIVE ? 0 : 1, + polarity == ACPI_ACTIVE_HIGH ? 0 : 1); return gsi; } diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c index d661703ac1c..be87c5e2ee9 100644 --- a/arch/i386/kernel/nmi.c +++ b/arch/i386/kernel/nmi.c @@ -138,7 +138,7 @@ static int __init check_nmi_watchdog(void) if (nmi_watchdog == NMI_LOCAL_APIC) smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0); - for (cpu = 0; cpu < NR_CPUS; cpu++) + for_each_cpu(cpu) prev_nmi_count[cpu] = per_cpu(irq_stat, cpu).__nmi_count; local_irq_enable(); mdelay((10*1000)/nmi_hz); // wait 10 ticks @@ -357,7 +357,7 @@ static void clear_msr_range(unsigned int base, unsigned int n) wrmsr(base+i, 0, 0); } -static inline void write_watchdog_counter(const char *descr) +static void write_watchdog_counter(const char *descr) { u64 count = (u64)cpu_khz * 1000; @@ -544,7 +544,7 @@ void nmi_watchdog_tick (struct pt_regs * regs) * die_nmi will return ONLY if NOTIFY_STOP happens.. */ die_nmi(regs, "NMI Watchdog detected LOCKUP"); - + } else { last_irq_sums[cpu] = sum; alert_counter[cpu] = 0; } diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index 2185377fdde..0480454ebff 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -297,8 +297,10 @@ void show_regs(struct pt_regs * regs) if (user_mode(regs)) printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp); - printk(" EFLAGS: %08lx %s (%s)\n", - regs->eflags, print_tainted(), system_utsname.release); + printk(" EFLAGS: %08lx %s (%s %.*s)\n", + regs->eflags, print_tainted(), system_utsname.release, + (int)strcspn(system_utsname.version, " "), + system_utsname.version); printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", regs->eax,regs->ebx,regs->ecx,regs->edx); printk("ESI: %08lx EDI: %08lx EBP: %08lx", diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index 51e513b4f72..ab62a9f4701 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -1599,6 +1599,10 @@ void __init setup_arch(char **cmdline_p) if (efi_enabled) efi_map_memmap(); +#ifdef CONFIG_X86_IO_APIC + check_acpi_pci(); /* Checks more than just ACPI actually */ +#endif + #ifdef CONFIG_ACPI /* * Parse the ACPI tables for possible boot-time SMP configuration. diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index 255adb49826..eba7f53f8b4 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -87,11 +87,7 @@ EXPORT_SYMBOL(cpu_online_map); cpumask_t cpu_callin_map; cpumask_t cpu_callout_map; EXPORT_SYMBOL(cpu_callout_map); -#ifdef CONFIG_HOTPLUG_CPU -cpumask_t cpu_possible_map = CPU_MASK_ALL; -#else cpumask_t cpu_possible_map; -#endif EXPORT_SYMBOL(cpu_possible_map); static cpumask_t smp_commenced_mask; @@ -902,12 +898,6 @@ static int __devinit do_boot_cpu(int apicid, int cpu) unsigned long start_eip; unsigned short nmi_high = 0, nmi_low = 0; - if (!cpu_gdt_descr[cpu].address && - !(cpu_gdt_descr[cpu].address = get_zeroed_page(GFP_KERNEL))) { - printk("Failed to allocate GDT for CPU %d\n", cpu); - return 1; - } - ++cpucount; /* diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S index 1b665928336..ac687d00a1c 100644 --- a/arch/i386/kernel/syscall_table.S +++ b/arch/i386/kernel/syscall_table.S @@ -299,7 +299,7 @@ ENTRY(sys_call_table) .long sys_mknodat .long sys_fchownat .long sys_futimesat - .long sys_newfstatat /* 300 */ + .long sys_fstatat64 /* 300 */ .long sys_unlinkat .long sys_renameat .long sys_linkat @@ -309,3 +309,4 @@ ENTRY(sys_call_table) .long sys_faccessat .long sys_pselect6 .long sys_ppoll + .long sys_unshare /* 310 */ diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c index a14d594bfbe..9d307475985 100644 --- a/arch/i386/kernel/time.c +++ b/arch/i386/kernel/time.c @@ -412,9 +412,9 @@ static int timer_resume(struct sys_device *dev) write_seqlock_irqsave(&xtime_lock, flags); xtime.tv_sec = sec; xtime.tv_nsec = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); - jiffies += sleep_length; + jiffies_64 += sleep_length; wall_jiffies += sleep_length; + write_sequnlock_irqrestore(&xtime_lock, flags); if (last_timer->resume) last_timer->resume(); cur_timer = last_timer; diff --git a/arch/i386/kernel/timers/timer_tsc.c b/arch/i386/kernel/timers/timer_tsc.c index 47675bbbb31..a7f5a2aceba 100644 --- a/arch/i386/kernel/timers/timer_tsc.c +++ b/arch/i386/kernel/timers/timer_tsc.c @@ -45,6 +45,15 @@ static unsigned long last_tsc_high; /* msb 32 bits of Time Stamp Counter */ static unsigned long long monotonic_base; static seqlock_t monotonic_lock = SEQLOCK_UNLOCKED; +/* Avoid compensating for lost ticks before TSCs are synched */ +static int detect_lost_ticks; +static int __init start_lost_tick_compensation(void) +{ + detect_lost_ticks = 1; + return 0; +} +late_initcall(start_lost_tick_compensation); + /* convert from cycles(64bits) => nanoseconds (64bits) * basic equation: * ns = cycles / (freq / ns_per_sec) @@ -196,7 +205,8 @@ static void mark_offset_tsc_hpet(void) /* lost tick compensation */ offset = hpet_readl(HPET_T0_CMP) - hpet_tick; - if (unlikely(((offset - hpet_last) > hpet_tick) && (hpet_last != 0))) { + if (unlikely(((offset - hpet_last) > hpet_tick) && (hpet_last != 0)) + && detect_lost_ticks) { int lost_ticks = (offset - hpet_last) / hpet_tick; jiffies_64 += lost_ticks; } @@ -272,6 +282,10 @@ time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, if (val != CPUFREQ_RESUMECHANGE) write_seqlock_irq(&xtime_lock); if (!ref_freq) { + if (!freq->old){ + ref_freq = freq->new; + goto end; + } ref_freq = freq->old; loops_per_jiffy_ref = cpu_data[freq->cpu].loops_per_jiffy; #ifndef CONFIG_SMP @@ -297,6 +311,7 @@ time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, #endif } +end: if (val != CPUFREQ_RESUMECHANGE) write_sequnlock_irq(&xtime_lock); @@ -421,7 +436,7 @@ static void mark_offset_tsc(void) delta += delay_at_last_interrupt; lost = delta/(1000000/HZ); delay = delta%(1000000/HZ); - if (lost >= 2) { + if (lost >= 2 && detect_lost_ticks) { jiffies_64 += lost-1; /* sanity check to ensure we're not always losing ticks */ diff --git a/arch/i386/mach-default/topology.c b/arch/i386/kernel/topology.c index b64314069e7..67a0e1baa28 100644 --- a/arch/i386/mach-default/topology.c +++ b/arch/i386/kernel/topology.c @@ -1,12 +1,12 @@ /* - * arch/i386/mach-generic/topology.c - Populate driverfs with topology information + * arch/i386/kernel/topology.c - Populate driverfs with topology information * * Written by: Matthew Dobson, IBM Corporation * Original Code: Paul Dorwin, IBM Corporation, Patrick Mochel, OSDL * * Copyright (C) 2002, IBM Corp. * - * All rights reserved. + * All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -34,7 +34,7 @@ static struct i386_cpu cpu_devices[NR_CPUS]; int arch_register_cpu(int num){ struct node *parent = NULL; - + #ifdef CONFIG_NUMA int node = cpu_to_node(num); if (node_online(node)) diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index 0aaebf3e1cf..b814dbdcc91 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -166,7 +166,8 @@ static void show_trace_log_lvl(struct task_struct *task, stack = (unsigned long*)context->previous_esp; if (!stack) break; - printk(KERN_EMERG " =======================\n"); + printk(log_lvl); + printk(" =======================\n"); } } @@ -239,9 +240,11 @@ void show_registers(struct pt_regs *regs) } print_modules(); printk(KERN_EMERG "CPU: %d\nEIP: %04x:[<%08lx>] %s VLI\n" - "EFLAGS: %08lx (%s) \n", + "EFLAGS: %08lx (%s %.*s) \n", smp_processor_id(), 0xffff & regs->xcs, regs->eip, - print_tainted(), regs->eflags, system_utsname.release); + print_tainted(), regs->eflags, system_utsname.release, + (int)strcspn(system_utsname.version, " "), + system_utsname.version); print_symbol(KERN_EMERG "EIP is at %s\n", regs->eip); printk(KERN_EMERG "eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n", regs->eax, regs->ebx, regs->ecx, regs->edx); diff --git a/arch/i386/kernel/vsyscall-sysenter.S b/arch/i386/kernel/vsyscall-sysenter.S index 4daefb2ec1b..76b72815940 100644 --- a/arch/i386/kernel/vsyscall-sysenter.S +++ b/arch/i386/kernel/vsyscall-sysenter.S @@ -7,6 +7,21 @@ * for details. */ +/* + * The caller puts arg2 in %ecx, which gets pushed. The kernel will use + * %ecx itself for arg2. The pushing is because the sysexit instruction + * (found in entry.S) requires that we clobber %ecx with the desired %esp. + * User code might expect that %ecx is unclobbered though, as it would be + * for returning via the iret instruction, so we must push and pop. + * + * The caller puts arg3 in %edx, which the sysexit instruction requires + * for %eip. Thus, exactly as for arg2, we must push and pop. + * + * Arg6 is different. The caller puts arg6 in %ebp. Since the sysenter + * instruction clobbers %esp, the user's %esp won't even survive entry + * into the kernel. We store %esp in %ebp. Code in entry.S must fetch + * arg6 from the stack. + */ .text .globl __kernel_vsyscall .type __kernel_vsyscall,@function diff --git a/arch/i386/mach-default/Makefile b/arch/i386/mach-default/Makefile index e95bb023792..012fe34459e 100644 --- a/arch/i386/mach-default/Makefile +++ b/arch/i386/mach-default/Makefile @@ -2,4 +2,4 @@ # Makefile for the linux kernel. # -obj-y := setup.o topology.o +obj-y := setup.o diff --git a/arch/i386/mach-voyager/voyager_basic.c b/arch/i386/mach-voyager/voyager_basic.c index aa49a33a572..b584060ec00 100644 --- a/arch/i386/mach-voyager/voyager_basic.c +++ b/arch/i386/mach-voyager/voyager_basic.c @@ -23,6 +23,8 @@ #include <linux/delay.h> #include <linux/reboot.h> #include <linux/sysrq.h> +#include <linux/smp.h> +#include <linux/nodemask.h> #include <asm/io.h> #include <asm/voyager.h> #include <asm/vic.h> @@ -328,4 +330,3 @@ void machine_power_off(void) if (pm_power_off) pm_power_off(); } - diff --git a/arch/i386/mach-voyager/voyager_smp.c b/arch/i386/mach-voyager/voyager_smp.c index 72a1b9cae2e..8165626a5c3 100644 --- a/arch/i386/mach-voyager/voyager_smp.c +++ b/arch/i386/mach-voyager/voyager_smp.c @@ -240,7 +240,7 @@ static cpumask_t smp_commenced_mask = CPU_MASK_NONE; cpumask_t cpu_callin_map = CPU_MASK_NONE; cpumask_t cpu_callout_map = CPU_MASK_NONE; EXPORT_SYMBOL(cpu_callout_map); -cpumask_t cpu_possible_map = CPU_MASK_ALL; +cpumask_t cpu_possible_map = CPU_MASK_NONE; EXPORT_SYMBOL(cpu_possible_map); /* The per processor IRQ masks (these are usually kept in sync) */ @@ -402,6 +402,7 @@ find_smp_config(void) cpus_addr(phys_cpu_present_map)[0] |= voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 1) << 8; cpus_addr(phys_cpu_present_map)[0] |= voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 2) << 16; cpus_addr(phys_cpu_present_map)[0] |= voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 3) << 24; + cpu_possible_map = phys_cpu_present_map; printk("VOYAGER SMP: phys_cpu_present_map = 0x%lx\n", cpus_addr(phys_cpu_present_map)[0]); /* Here we set up the VIC to enable SMP */ /* enable the CPIs by writing the base vector to their register */ diff --git a/arch/i386/oprofile/backtrace.c b/arch/i386/oprofile/backtrace.c index 21654be3f73..c049ce414f0 100644 --- a/arch/i386/oprofile/backtrace.c +++ b/arch/i386/oprofile/backtrace.c @@ -20,7 +20,20 @@ struct frame_head { } __attribute__((packed)); static struct frame_head * -dump_backtrace(struct frame_head * head) +dump_kernel_backtrace(struct frame_head * head) +{ + oprofile_add_trace(head->ret); + + /* frame pointers should strictly progress back up the stack + * (towards higher addresses) */ + if (head >= head->ebp) + return NULL; + + return head->ebp; +} + +static struct frame_head * +dump_user_backtrace(struct frame_head * head) { struct frame_head bufhead[2]; @@ -49,7 +62,9 @@ dump_backtrace(struct frame_head * head) * | stack | * --------------- saved regs->ebp value if valid (frame_head address) * . . - * --------------- struct pt_regs stored on stack (struct pt_regs *) + * --------------- saved regs->rsp value if x86_64 + * | | + * --------------- struct pt_regs * stored on stack if 32-bit * | | * . . * | | @@ -57,13 +72,26 @@ dump_backtrace(struct frame_head * head) * | | * | | \/ Lower addresses * - * Thus, &pt_regs <-> stack base restricts the valid(ish) ebp values + * Thus, regs (or regs->rsp for x86_64) <-> stack base restricts the + * valid(ish) ebp values. Note: (1) for x86_64, NMI and several other + * exceptions use special stacks, maintained by the interrupt stack table + * (IST). These stacks are set up in trap_init() in + * arch/x86_64/kernel/traps.c. Thus, for x86_64, regs now does not point + * to the kernel stack; instead, it points to some location on the NMI + * stack. On the other hand, regs->rsp is the stack pointer saved when the + * NMI occurred. (2) For 32-bit, regs->esp is not valid because the + * processor does not save %esp on the kernel stack when interrupts occur + * in the kernel mode. */ #ifdef CONFIG_FRAME_POINTER static int valid_kernel_stack(struct frame_head * head, struct pt_regs * regs) { unsigned long headaddr = (unsigned long)head; +#ifdef CONFIG_X86_64 + unsigned long stack = (unsigned long)regs->rsp; +#else unsigned long stack = (unsigned long)regs; +#endif unsigned long stack_base = (stack & ~(THREAD_SIZE - 1)) + THREAD_SIZE; return headaddr > stack && headaddr < stack_base; @@ -90,10 +118,10 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth) if (!user_mode_vm(regs)) { while (depth-- && valid_kernel_stack(head, regs)) - head = dump_backtrace(head); + head = dump_kernel_backtrace(head); return; } while (depth-- && head) - head = dump_backtrace(head); + head = dump_user_backtrace(head); } diff --git a/arch/i386/pci/irq.c b/arch/i386/pci/irq.c index e715aa93003..3ca59cad05f 100644 --- a/arch/i386/pci/irq.c +++ b/arch/i386/pci/irq.c @@ -539,6 +539,11 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route case PCI_DEVICE_ID_INTEL_ICH7_30: case PCI_DEVICE_ID_INTEL_ICH7_31: case PCI_DEVICE_ID_INTEL_ESB2_0: + case PCI_DEVICE_ID_INTEL_ICH8_0: + case PCI_DEVICE_ID_INTEL_ICH8_1: + case PCI_DEVICE_ID_INTEL_ICH8_2: + case PCI_DEVICE_ID_INTEL_ICH8_3: + case PCI_DEVICE_ID_INTEL_ICH8_4: r->name = "PIIX/ICH"; r->get = pirq_piix_get; r->set = pirq_piix_set; diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c index 4bb4d4b0f73..0ee8a983708 100644 --- a/arch/i386/pci/mmconfig.c +++ b/arch/i386/pci/mmconfig.c @@ -36,8 +36,7 @@ static u32 get_base_addr(unsigned int seg, int bus, unsigned devfn) while (1) { ++cfg_num; if (cfg_num >= pci_mmcfg_config_num) { - /* Not found - fallback to type 1 */ - return 0; + break; } cfg = &pci_mmcfg_config[cfg_num]; if (cfg->pci_segment_group_number != seg) @@ -46,6 +45,18 @@ static u32 get_base_addr(unsigned int seg, int bus, unsigned devfn) (cfg->end_bus_number >= bus)) return cfg->base_address; } + + /* Handle more broken MCFG tables on Asus etc. + They only contain a single entry for bus 0-0. Assume + this applies to all busses. */ + cfg = &pci_mmcfg_config[0]; + if (pci_mmcfg_config_num == 1 && + cfg->pci_segment_group_number == 0 && + (cfg->start_bus_number | cfg->end_bus_number) == 0) + return cfg->base_address; + + /* Fall back to type 0 */ + return 0; } static inline void pci_exp_set_dev_base(unsigned int base, int bus, int devfn) |