diff options
Diffstat (limited to 'arch/i386/kernel/cpu')
25 files changed, 1055 insertions, 324 deletions
diff --git a/arch/i386/kernel/cpu/Makefile b/arch/i386/kernel/cpu/Makefile index 010aecfffbc..74f27a463db 100644 --- a/arch/i386/kernel/cpu/Makefile +++ b/arch/i386/kernel/cpu/Makefile @@ -2,7 +2,7 @@ # Makefile for x86-compatible CPU details and quirks # -obj-y := common.o proc.o +obj-y := common.o proc.o bugs.o obj-y += amd.o obj-y += cyrix.o @@ -17,3 +17,5 @@ obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_CPU_FREQ) += cpufreq/ + +obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c index 2d47db48297..4fec702afd7 100644 --- a/arch/i386/kernel/cpu/amd.c +++ b/arch/i386/kernel/cpu/amd.c @@ -53,6 +53,8 @@ static __cpuinit int amd_apic_timer_broken(void) return 0; } +int force_mwait __cpuinitdata; + static void __cpuinit init_amd(struct cpuinfo_x86 *c) { u32 l, h; @@ -275,6 +277,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) if (amd_apic_timer_broken()) set_bit(X86_FEATURE_LAPIC_TIMER_BROKEN, c->x86_capability); + + if (c->x86 == 0x10 && !force_mwait) + clear_bit(X86_FEATURE_MWAIT, c->x86_capability); } static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 * c, unsigned int size) @@ -314,13 +319,3 @@ int __init amd_init_cpu(void) cpu_devs[X86_VENDOR_AMD] = &amd_cpu_dev; return 0; } - -//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/bugs.c b/arch/i386/kernel/cpu/bugs.c new file mode 100644 index 00000000000..54428a2500f --- /dev/null +++ b/arch/i386/kernel/cpu/bugs.c @@ -0,0 +1,191 @@ +/* + * arch/i386/cpu/bugs.c + * + * Copyright (C) 1994 Linus Torvalds + * + * Cyrix stuff, June 1998 by: + * - Rafael R. Reilova (moved everything from head.S), + * <rreilova@ececs.uc.edu> + * - Channing Corn (tests & fixes), + * - Andrew D. Balsa (code cleanup). + */ +#include <linux/init.h> +#include <linux/utsname.h> +#include <asm/processor.h> +#include <asm/i387.h> +#include <asm/msr.h> +#include <asm/paravirt.h> +#include <asm/alternative.h> + +static int __init no_halt(char *s) +{ + boot_cpu_data.hlt_works_ok = 0; + return 1; +} + +__setup("no-hlt", no_halt); + +static int __init mca_pentium(char *s) +{ + mca_pentium_flag = 1; + return 1; +} + +__setup("mca-pentium", mca_pentium); + +static int __init no_387(char *s) +{ + boot_cpu_data.hard_math = 0; + write_cr0(0xE | read_cr0()); + return 1; +} + +__setup("no387", no_387); + +static double __initdata x = 4195835.0; +static double __initdata y = 3145727.0; + +/* + * This used to check for exceptions.. + * However, it turns out that to support that, + * the XMM trap handlers basically had to + * be buggy. So let's have a correct XMM trap + * handler, and forget about printing out + * some status at boot. + * + * We should really only care about bugs here + * anyway. Not features. + */ +static void __init check_fpu(void) +{ + if (!boot_cpu_data.hard_math) { +#ifndef CONFIG_MATH_EMULATION + printk(KERN_EMERG "No coprocessor found and no math emulation present.\n"); + printk(KERN_EMERG "Giving up.\n"); + for (;;) ; +#endif + return; + } + +/* trap_init() enabled FXSR and company _before_ testing for FP problems here. */ + /* Test for the divl bug.. */ + __asm__("fninit\n\t" + "fldl %1\n\t" + "fdivl %2\n\t" + "fmull %2\n\t" + "fldl %1\n\t" + "fsubp %%st,%%st(1)\n\t" + "fistpl %0\n\t" + "fwait\n\t" + "fninit" + : "=m" (*&boot_cpu_data.fdiv_bug) + : "m" (*&x), "m" (*&y)); + if (boot_cpu_data.fdiv_bug) + printk("Hmm, FPU with FDIV bug.\n"); +} + +static void __init check_hlt(void) +{ + if (paravirt_enabled()) + return; + + printk(KERN_INFO "Checking 'hlt' instruction... "); + if (!boot_cpu_data.hlt_works_ok) { + printk("disabled\n"); + return; + } + halt(); + halt(); + halt(); + halt(); + printk("OK.\n"); +} + +/* + * Most 386 processors have a bug where a POPAD can lock the + * machine even from user space. + */ + +static void __init check_popad(void) +{ +#ifndef CONFIG_X86_POPAD_OK + int res, inp = (int) &res; + + printk(KERN_INFO "Checking for popad bug... "); + __asm__ __volatile__( + "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx " + : "=&a" (res) + : "d" (inp) + : "ecx", "edi" ); + /* If this fails, it means that any user program may lock the CPU hard. Too bad. */ + if (res != 12345678) printk( "Buggy.\n" ); + else printk( "OK.\n" ); +#endif +} + +/* + * Check whether we are able to run this kernel safely on SMP. + * + * - In order to run on a i386, we need to be compiled for i386 + * (for due to lack of "invlpg" and working WP on a i386) + * - In order to run on anything without a TSC, we need to be + * compiled for a i486. + * - In order to support the local APIC on a buggy Pentium machine, + * we need to be compiled with CONFIG_X86_GOOD_APIC disabled, + * which happens implicitly if compiled for a Pentium or lower + * (unless an advanced selection of CPU features is used) as an + * otherwise config implies a properly working local APIC without + * the need to do extra reads from the APIC. +*/ + +static void __init check_config(void) +{ +/* + * We'd better not be a i386 if we're configured to use some + * i486+ only features! (WP works in supervisor mode and the + * new "invlpg" and "bswap" instructions) + */ +#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_BSWAP) + if (boot_cpu_data.x86 == 3) + panic("Kernel requires i486+ for 'invlpg' and other features"); +#endif + +/* + * If we configured ourselves for a TSC, we'd better have one! + */ +#ifdef CONFIG_X86_TSC + if (!cpu_has_tsc && !tsc_disable) + panic("Kernel compiled for Pentium+, requires TSC feature!"); +#endif + +/* + * If we were told we had a good local APIC, check for buggy Pentia, + * i.e. all B steppings and the C2 stepping of P54C when using their + * integrated APIC (see 11AP erratum in "Pentium Processor + * Specification Update"). + */ +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_GOOD_APIC) + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL + && cpu_has_apic + && boot_cpu_data.x86 == 5 + && boot_cpu_data.x86_model == 2 + && (boot_cpu_data.x86_mask < 6 || boot_cpu_data.x86_mask == 11)) + panic("Kernel compiled for PMMX+, assumes a local APIC without the read-before-write bug!"); +#endif +} + + +void __init check_bugs(void) +{ + identify_boot_cpu(); +#ifndef CONFIG_SMP + printk("CPU: "); + print_cpu_info(&boot_cpu_data); +#endif + check_config(); + check_fpu(); + check_hlt(); + check_popad(); + init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); + alternative_instructions(); +} diff --git a/arch/i386/kernel/cpu/centaur.c b/arch/i386/kernel/cpu/centaur.c index 8c25047975c..473eac883c7 100644 --- a/arch/i386/kernel/cpu/centaur.c +++ b/arch/i386/kernel/cpu/centaur.c @@ -469,13 +469,3 @@ int __init centaur_init_cpu(void) cpu_devs[X86_VENDOR_CENTAUR] = ¢aur_cpu_dev; return 0; } - -//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 dcbbd0a8bfc..794d593c47e 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -18,15 +18,37 @@ #include <asm/apic.h> #include <mach_apic.h> #endif -#include <asm/pda.h> #include "cpu.h" -DEFINE_PER_CPU(struct Xgt_desc_struct, cpu_gdt_descr); -EXPORT_PER_CPU_SYMBOL(cpu_gdt_descr); +DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = { + [GDT_ENTRY_KERNEL_CS] = { 0x0000ffff, 0x00cf9a00 }, + [GDT_ENTRY_KERNEL_DS] = { 0x0000ffff, 0x00cf9200 }, + [GDT_ENTRY_DEFAULT_USER_CS] = { 0x0000ffff, 0x00cffa00 }, + [GDT_ENTRY_DEFAULT_USER_DS] = { 0x0000ffff, 0x00cff200 }, + /* + * Segments used for calling PnP BIOS have byte granularity. + * They code segments and data segments have fixed 64k limits, + * the transfer segment sizes are set at run time. + */ + [GDT_ENTRY_PNPBIOS_CS32] = { 0x0000ffff, 0x00409a00 },/* 32-bit code */ + [GDT_ENTRY_PNPBIOS_CS16] = { 0x0000ffff, 0x00009a00 },/* 16-bit code */ + [GDT_ENTRY_PNPBIOS_DS] = { 0x0000ffff, 0x00009200 }, /* 16-bit data */ + [GDT_ENTRY_PNPBIOS_TS1] = { 0x00000000, 0x00009200 },/* 16-bit data */ + [GDT_ENTRY_PNPBIOS_TS2] = { 0x00000000, 0x00009200 },/* 16-bit data */ + /* + * The APM segments have byte granularity and their bases + * are set at run time. All have 64k limits. + */ + [GDT_ENTRY_APMBIOS_BASE] = { 0x0000ffff, 0x00409a00 },/* 32-bit code */ + /* 16-bit code */ + [GDT_ENTRY_APMBIOS_BASE+1] = { 0x0000ffff, 0x00009a00 }, + [GDT_ENTRY_APMBIOS_BASE+2] = { 0x0000ffff, 0x00409200 }, /* data */ -struct i386_pda *_cpu_pda[NR_CPUS] __read_mostly; -EXPORT_SYMBOL(_cpu_pda); + [GDT_ENTRY_ESPFIX_SS] = { 0x00000000, 0x00c09200 }, + [GDT_ENTRY_PERCPU] = { 0x00000000, 0x00000000 }, +} }; +EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); static int cachesize_override __cpuinitdata = -1; static int disable_x86_fxsr __cpuinitdata; @@ -368,7 +390,7 @@ __setup("serialnumber", x86_serial_nr_setup); /* * This does the hard work of actually picking apart the CPU stuff... */ -void __cpuinit identify_cpu(struct cpuinfo_x86 *c) +static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) { int i; @@ -479,15 +501,22 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) /* Init Machine Check Exception if available. */ mcheck_init(c); +} - if (c == &boot_cpu_data) - sysenter_setup(); +void __init identify_boot_cpu(void) +{ + identify_cpu(&boot_cpu_data); + sysenter_setup(); enable_sep_cpu(); + mtrr_bp_init(); +} - if (c == &boot_cpu_data) - mtrr_bp_init(); - else - mtrr_ap_init(); +void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c) +{ + BUG_ON(c == &boot_cpu_data); + identify_cpu(c); + enable_sep_cpu(); + mtrr_ap_init(); } #ifdef CONFIG_X86_HT @@ -601,129 +630,36 @@ void __init early_cpu_init(void) #endif } -/* Make sure %gs is initialized properly in idle threads */ +/* Make sure %fs is initialized properly in idle threads */ struct pt_regs * __devinit idle_regs(struct pt_regs *regs) { memset(regs, 0, sizeof(struct pt_regs)); - regs->xfs = __KERNEL_PDA; + regs->xfs = __KERNEL_PERCPU; return regs; } -static __cpuinit int alloc_gdt(int cpu) +/* Current gdt points %fs at the "master" per-cpu area: after this, + * it's on the real one. */ +void switch_to_new_gdt(void) { - struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu); - struct desc_struct *gdt; - struct i386_pda *pda; - - gdt = (struct desc_struct *)cpu_gdt_descr->address; - pda = cpu_pda(cpu); - - /* - * 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) { - BUG_ON(gdt != NULL || pda != NULL); - - gdt = alloc_bootmem_pages(PAGE_SIZE); - pda = alloc_bootmem(sizeof(*pda)); - /* alloc_bootmem(_pages) panics on failure, so no check */ - - memset(gdt, 0, PAGE_SIZE); - memset(pda, 0, sizeof(*pda)); - } else { - /* GDT and PDA might already have been allocated if - this is a CPU hotplug re-insertion. */ - if (gdt == NULL) - gdt = (struct desc_struct *)get_zeroed_page(GFP_KERNEL); - - if (pda == NULL) - pda = kmalloc_node(sizeof(*pda), GFP_KERNEL, cpu_to_node(cpu)); - - if (unlikely(!gdt || !pda)) { - free_pages((unsigned long)gdt, 0); - kfree(pda); - return 0; - } - } - - cpu_gdt_descr->address = (unsigned long)gdt; - cpu_pda(cpu) = pda; - - return 1; -} + struct Xgt_desc_struct gdt_descr; -/* Initial PDA used by boot CPU */ -struct i386_pda boot_pda = { - ._pda = &boot_pda, - .cpu_number = 0, - .pcurrent = &init_task, -}; - -static inline void set_kernel_fs(void) -{ - /* Set %fs for this CPU's PDA. Memory clobber is to create a - barrier with respect to any PDA operations, so the compiler - doesn't move any before here. */ - asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_PDA) : "memory"); + gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id()); + gdt_descr.size = GDT_SIZE - 1; + load_gdt(&gdt_descr); + asm("mov %0, %%fs" : : "r" (__KERNEL_PERCPU) : "memory"); } -/* Initialize the CPU's GDT and PDA. The boot CPU does this for - itself, but secondaries find this done for them. */ -__cpuinit int init_gdt(int cpu, struct task_struct *idle) -{ - struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu); - struct desc_struct *gdt; - struct i386_pda *pda; - - /* For non-boot CPUs, the GDT and PDA should already have been - allocated. */ - if (!alloc_gdt(cpu)) { - printk(KERN_CRIT "CPU%d failed to allocate GDT or PDA\n", cpu); - return 0; - } - - gdt = (struct desc_struct *)cpu_gdt_descr->address; - pda = cpu_pda(cpu); - - BUG_ON(gdt == NULL || pda == NULL); - - /* - * Initialize the per-CPU GDT with the boot GDT, - * and set up the GDT descriptor: - */ - memcpy(gdt, cpu_gdt_table, GDT_SIZE); - cpu_gdt_descr->size = GDT_SIZE - 1; - - pack_descriptor((u32 *)&gdt[GDT_ENTRY_PDA].a, - (u32 *)&gdt[GDT_ENTRY_PDA].b, - (unsigned long)pda, sizeof(*pda) - 1, - 0x80 | DESCTYPE_S | 0x2, 0); /* present read-write data segment */ - - memset(pda, 0, sizeof(*pda)); - pda->_pda = pda; - pda->cpu_number = cpu; - pda->pcurrent = idle; - - return 1; -} - -void __cpuinit cpu_set_gdt(int cpu) -{ - struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu); - - /* Reinit these anyway, even if they've already been done (on - the boot CPU, this will transition from the boot gdt+pda to - the real ones). */ - load_gdt(cpu_gdt_descr); - set_kernel_fs(); -} - -/* Common CPU init for both boot and secondary CPUs */ -static void __cpuinit _cpu_init(int cpu, struct task_struct *curr) +/* + * cpu_init() initializes state that is per-CPU. Some data is already + * initialized (naturally) in the bootstrap process, such as the GDT + * and IDT. We reload them nevertheless, this function acts as a + * 'CPU state barrier', nothing should get across. + */ +void __cpuinit cpu_init(void) { + int cpu = smp_processor_id(); + struct task_struct *curr = current; struct tss_struct * t = &per_cpu(init_tss, cpu); struct thread_struct *thread = &curr->thread; @@ -744,6 +680,7 @@ static void __cpuinit _cpu_init(int cpu, struct task_struct *curr) } load_idt(&idt_descr); + switch_to_new_gdt(); /* * Set up and load the per-CPU TSS and LDT @@ -783,38 +720,6 @@ static void __cpuinit _cpu_init(int cpu, struct task_struct *curr) mxcsr_feature_mask_init(); } -/* Entrypoint to initialize secondary CPU */ -void __cpuinit secondary_cpu_init(void) -{ - int cpu = smp_processor_id(); - struct task_struct *curr = current; - - _cpu_init(cpu, curr); -} - -/* - * cpu_init() initializes state that is per-CPU. Some data is already - * initialized (naturally) in the bootstrap process, such as the GDT - * and IDT. We reload them nevertheless, this function acts as a - * 'CPU state barrier', nothing should get across. - */ -void __cpuinit cpu_init(void) -{ - int cpu = smp_processor_id(); - struct task_struct *curr = current; - - /* Set up the real GDT and PDA, so we can transition from the - boot versions. */ - if (!init_gdt(cpu, curr)) { - /* failed to allocate something; not much we can do... */ - for (;;) - local_irq_enable(); - } - - cpu_set_gdt(cpu); - _cpu_init(cpu, curr); -} - #ifdef CONFIG_HOTPLUG_CPU void __cpuinit cpu_uninit(void) { diff --git a/arch/i386/kernel/cpu/cpufreq/longhaul.c b/arch/i386/kernel/cpu/cpufreq/longhaul.c index 2b030d6ccbf..a3df9c039bd 100644 --- a/arch/i386/kernel/cpu/cpufreq/longhaul.c +++ b/arch/i386/kernel/cpu/cpufreq/longhaul.c @@ -590,20 +590,23 @@ static acpi_status longhaul_walk_callback(acpi_handle obj_handle, static int enable_arbiter_disable(void) { struct pci_dev *dev; + int status; int reg; u8 pci_cmd; + status = 1; /* Find PLE133 host bridge */ reg = 0x78; - dev = pci_find_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8601_0, NULL); + dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8601_0, + NULL); /* Find CLE266 host bridge */ if (dev == NULL) { reg = 0x76; - dev = pci_find_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_862X_0, NULL); + dev = pci_get_device(PCI_VENDOR_ID_VIA, + PCI_DEVICE_ID_VIA_862X_0, NULL); /* Find CN400 V-Link host bridge */ if (dev == NULL) - dev = pci_find_device(PCI_VENDOR_ID_VIA, 0x7259, NULL); - + dev = pci_get_device(PCI_VENDOR_ID_VIA, 0x7259, NULL); } if (dev != NULL) { /* Enable access to port 0x22 */ @@ -615,10 +618,11 @@ static int enable_arbiter_disable(void) if (!(pci_cmd & 1<<7)) { printk(KERN_ERR PFX "Can't enable access to port 0x22.\n"); - return 0; + status = 0; } } - return 1; + pci_dev_put(dev); + return status; } return 0; } @@ -629,7 +633,7 @@ static int longhaul_setup_vt8235(void) u8 pci_cmd; /* Find VT8235 southbridge */ - dev = pci_find_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, NULL); + dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, NULL); if (dev != NULL) { /* Set transition time to max */ pci_read_config_byte(dev, 0xec, &pci_cmd); @@ -641,6 +645,7 @@ static int longhaul_setup_vt8235(void) pci_read_config_byte(dev, 0xe5, &pci_cmd); pci_cmd |= 1 << 7; pci_write_config_byte(dev, 0xe5, pci_cmd); + pci_dev_put(dev); return 1; } return 0; @@ -678,7 +683,7 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) sizeof(samuel2_eblcr)); break; case 1 ... 15: - longhaul_version = TYPE_LONGHAUL_V2; + longhaul_version = TYPE_LONGHAUL_V1; if (c->x86_mask < 8) { cpu_model = CPU_SAMUEL2; cpuname = "C3 'Samuel 2' [C5B]"; diff --git a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c index 4786fedca6e..4c76b511e19 100644 --- a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c @@ -27,7 +27,6 @@ #include <linux/cpufreq.h> #include <linux/slab.h> #include <linux/cpumask.h> -#include <linux/sched.h> /* current / set_cpus_allowed() */ #include <asm/processor.h> #include <asm/msr.h> @@ -62,7 +61,7 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate) if (!cpu_online(cpu) || (newstate > DC_DISABLE) || (newstate == DC_RESV)) return -EINVAL; - rdmsr(MSR_IA32_THERM_STATUS, l, h); + rdmsr_on_cpu(cpu, MSR_IA32_THERM_STATUS, &l, &h); if (l & 0x01) dprintk("CPU#%d currently thermal throttled\n", cpu); @@ -70,10 +69,10 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate) if (has_N44_O17_errata[cpu] && (newstate == DC_25PT || newstate == DC_DFLT)) newstate = DC_38PT; - rdmsr(MSR_IA32_THERM_CONTROL, l, h); + rdmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, &l, &h); if (newstate == DC_DISABLE) { dprintk("CPU#%d disabling modulation\n", cpu); - wrmsr(MSR_IA32_THERM_CONTROL, l & ~(1<<4), h); + wrmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, l & ~(1<<4), h); } else { dprintk("CPU#%d setting duty cycle to %d%%\n", cpu, ((125 * newstate) / 10)); @@ -84,7 +83,7 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate) */ l = (l & ~14); l = l | (1<<4) | ((newstate & 0x7)<<1); - wrmsr(MSR_IA32_THERM_CONTROL, l, h); + wrmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, l, h); } return 0; @@ -111,7 +110,6 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy, { unsigned int newstate = DC_RESV; struct cpufreq_freqs freqs; - cpumask_t cpus_allowed; int i; if (cpufreq_frequency_table_target(policy, &p4clockmod_table[0], target_freq, relation, &newstate)) @@ -132,17 +130,8 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy, /* run on each logical CPU, see section 13.15.3 of IA32 Intel Architecture Software * Developer's Manual, Volume 3 */ - cpus_allowed = current->cpus_allowed; - - for_each_cpu_mask(i, policy->cpus) { - cpumask_t this_cpu = cpumask_of_cpu(i); - - set_cpus_allowed(current, this_cpu); - BUG_ON(smp_processor_id() != i); - + for_each_cpu_mask(i, policy->cpus) cpufreq_p4_setdc(i, p4clockmod_table[newstate].index); - } - set_cpus_allowed(current, cpus_allowed); /* notifiers */ for_each_cpu_mask(i, policy->cpus) { @@ -256,17 +245,9 @@ static int cpufreq_p4_cpu_exit(struct cpufreq_policy *policy) static unsigned int cpufreq_p4_get(unsigned int cpu) { - cpumask_t cpus_allowed; u32 l, h; - cpus_allowed = current->cpus_allowed; - - set_cpus_allowed(current, cpumask_of_cpu(cpu)); - BUG_ON(smp_processor_id() != cpu); - - rdmsr(MSR_IA32_THERM_CONTROL, l, h); - - set_cpus_allowed(current, cpus_allowed); + rdmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, &l, &h); if (l & 0x10) { l = l >> 1; diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c index fe3b67005eb..7cf3d207b6b 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c @@ -661,7 +661,8 @@ static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst, dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid); data->powernow_table = powernow_table; - print_basics(data); + if (first_cpu(cpu_core_map[data->cpu]) == data->cpu) + print_basics(data); for (j = 0; j < data->numps; j++) if ((pst[j].fid==data->currfid) && (pst[j].vid==data->currvid)) @@ -814,7 +815,8 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) /* fill in data */ data->numps = data->acpi_data.state_count; - print_basics(data); + if (first_cpu(cpu_core_map[data->cpu]) == data->cpu) + print_basics(data); powernow_k8_acpi_pst_values(data, 0); /* notify BIOS that we exist */ diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.h b/arch/i386/kernel/cpu/cpufreq/powernow-k8.h index 0fb2a3001ba..95be5013c98 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.h @@ -215,8 +215,10 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid); static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index); +#ifdef CONFIG_X86_POWERNOW_K8_ACPI static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table); static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table); +#endif #ifdef CONFIG_SMP static inline void define_siblings(int cpu, cpumask_t cpu_sharedcore_mask[]) diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c index f43b987f952..35489fd6885 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c @@ -720,6 +720,7 @@ static int centrino_target (struct cpufreq_policy *policy, cpu_set(j, set_mask); set_cpus_allowed(current, set_mask); + preempt_disable(); if (unlikely(!cpu_isset(smp_processor_id(), set_mask))) { dprintk("couldn't limit to CPUs in this domain\n"); retval = -EAGAIN; @@ -727,6 +728,7 @@ static int centrino_target (struct cpufreq_policy *policy, /* We haven't started the transition yet. */ goto migrate_end; } + preempt_enable(); break; } @@ -761,10 +763,13 @@ static int centrino_target (struct cpufreq_policy *policy, } wrmsr(MSR_IA32_PERF_CTL, oldmsr, h); - if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) + if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) { + preempt_enable(); break; + } cpu_set(j, covered_cpus); + preempt_enable(); } for_each_cpu_mask(k, online_policy_cpus) { @@ -796,8 +801,11 @@ static int centrino_target (struct cpufreq_policy *policy, cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } } + set_cpus_allowed(current, saved_mask); + return 0; migrate_end: + preempt_enable(); set_cpus_allowed(current, saved_mask); return 0; } diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c index d59277c0091..b1acc8ce316 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c @@ -13,7 +13,6 @@ #include <linux/moduleparam.h> #include <linux/init.h> #include <linux/cpufreq.h> -#include <linux/pci.h> #include <linux/slab.h> #include <asm/msr.h> diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c b/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c index ff0d8980611..e1c509aa305 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c @@ -17,10 +17,10 @@ #include <linux/moduleparam.h> #include <linux/init.h> #include <linux/cpufreq.h> -#include <linux/pci.h> #include <linux/slab.h> #include <linux/delay.h> #include <asm/ist.h> +#include <asm/io.h> #include "speedstep-lib.h" diff --git a/arch/i386/kernel/cpu/cyrix.c b/arch/i386/kernel/cpu/cyrix.c index de27bd07bc9..0b8411a864f 100644 --- a/arch/i386/kernel/cpu/cyrix.c +++ b/arch/i386/kernel/cpu/cyrix.c @@ -279,7 +279,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) */ if (vendor == PCI_VENDOR_ID_CYRIX && (device == PCI_DEVICE_ID_CYRIX_5510 || device == PCI_DEVICE_ID_CYRIX_5520)) - pit_latch_buggy = 1; + mark_tsc_unstable("cyrix 5510/5520 detected"); } #endif c->x86_cache_size=16; /* Yep 16K integrated cache thats it */ @@ -448,16 +448,6 @@ int __init cyrix_init_cpu(void) return 0; } -//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 __cpuinitdata = { .c_vendor = "NSC", .c_ident = { "Geode by NSC" }, @@ -470,12 +460,3 @@ int __init nsc_init_cpu(void) return 0; } -//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.c b/arch/i386/kernel/cpu/intel.c index 56fe2658495..dc4e08147b1 100644 --- a/arch/i386/kernel/cpu/intel.c +++ b/arch/i386/kernel/cpu/intel.c @@ -188,8 +188,10 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) } #endif - if (c->x86 == 15) + if (c->x86 == 15) { set_bit(X86_FEATURE_P4, c->x86_capability); + set_bit(X86_FEATURE_SYNC_RDTSC, c->x86_capability); + } if (c->x86 == 6) set_bit(X86_FEATURE_P3, c->x86_capability); if ((c->x86 == 0xf && c->x86_model >= 0x03) || diff --git a/arch/i386/kernel/cpu/mcheck/k7.c b/arch/i386/kernel/cpu/mcheck/k7.c index b0862af595a..f9fa4142551 100644 --- a/arch/i386/kernel/cpu/mcheck/k7.c +++ b/arch/i386/kernel/cpu/mcheck/k7.c @@ -75,6 +75,9 @@ void amd_mcheck_init(struct cpuinfo_x86 *c) machine_check_vector = k7_machine_check; wmb(); + if (!cpu_has(c, X86_FEATURE_MCE)) + return; + printk (KERN_INFO "Intel machine check architecture supported.\n"); rdmsr (MSR_IA32_MCG_CAP, l, h); if (l & (1<<8)) /* Control register present ? */ @@ -82,9 +85,13 @@ void amd_mcheck_init(struct cpuinfo_x86 *c) nr_mce_banks = l & 0xff; /* Clear status for MC index 0 separately, we don't touch CTL, - * as some Athlons cause spurious MCEs when its enabled. */ - wrmsr (MSR_IA32_MC0_STATUS, 0x0, 0x0); - for (i=1; i<nr_mce_banks; i++) { + * as some K7 Athlons cause spurious MCEs when its enabled. */ + if (boot_cpu_data.x86 == 6) { + wrmsr (MSR_IA32_MC0_STATUS, 0x0, 0x0); + i = 1; + } else + i = 0; + for (; i<nr_mce_banks; i++) { wrmsr (MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff); wrmsr (MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0); } diff --git a/arch/i386/kernel/cpu/mcheck/mce.c b/arch/i386/kernel/cpu/mcheck/mce.c index 4f10c62d180..56cd485b127 100644 --- a/arch/i386/kernel/cpu/mcheck/mce.c +++ b/arch/i386/kernel/cpu/mcheck/mce.c @@ -38,8 +38,7 @@ void mcheck_init(struct cpuinfo_x86 *c) switch (c->x86_vendor) { case X86_VENDOR_AMD: - if (c->x86==6 || c->x86==15) - amd_mcheck_init(c); + amd_mcheck_init(c); break; case X86_VENDOR_INTEL: diff --git a/arch/i386/kernel/cpu/mcheck/p4.c b/arch/i386/kernel/cpu/mcheck/p4.c index 504434a4601..1509edfb231 100644 --- a/arch/i386/kernel/cpu/mcheck/p4.c +++ b/arch/i386/kernel/cpu/mcheck/p4.c @@ -124,13 +124,10 @@ static void intel_init_thermal(struct cpuinfo_x86 *c) /* P4/Xeon Extended MCE MSR retrieval, return 0 if unsupported */ -static inline int intel_get_extended_msrs(struct intel_mce_extended_msrs *r) +static inline void intel_get_extended_msrs(struct intel_mce_extended_msrs *r) { u32 h; - if (mce_num_extended_msrs == 0) - goto done; - rdmsr (MSR_IA32_MCG_EAX, r->eax, h); rdmsr (MSR_IA32_MCG_EBX, r->ebx, h); rdmsr (MSR_IA32_MCG_ECX, r->ecx, h); @@ -141,12 +138,6 @@ static inline int intel_get_extended_msrs(struct intel_mce_extended_msrs *r) rdmsr (MSR_IA32_MCG_ESP, r->esp, h); rdmsr (MSR_IA32_MCG_EFLAGS, r->eflags, h); rdmsr (MSR_IA32_MCG_EIP, r->eip, h); - - /* can we rely on kmalloc to do a dynamic - * allocation for the reserved registers? - */ -done: - return mce_num_extended_msrs; } static fastcall void intel_machine_check(struct pt_regs * regs, long error_code) @@ -155,7 +146,6 @@ static fastcall void intel_machine_check(struct pt_regs * regs, long error_code) u32 alow, ahigh, high, low; u32 mcgstl, mcgsth; int i; - struct intel_mce_extended_msrs dbg; rdmsr (MSR_IA32_MCG_STATUS, mcgstl, mcgsth); if (mcgstl & (1<<0)) /* Recoverable ? */ @@ -164,7 +154,9 @@ static fastcall void intel_machine_check(struct pt_regs * regs, long error_code) printk (KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n", smp_processor_id(), mcgsth, mcgstl); - if (intel_get_extended_msrs(&dbg)) { + if (mce_num_extended_msrs > 0) { + struct intel_mce_extended_msrs dbg; + intel_get_extended_msrs(&dbg); printk (KERN_DEBUG "CPU %d: EIP: %08x EFLAGS: %08x\n", smp_processor_id(), dbg.eip, dbg.eflags); printk (KERN_DEBUG "\teax: %08x ebx: %08x ecx: %08x edx: %08x\n", diff --git a/arch/i386/kernel/cpu/mtrr/generic.c b/arch/i386/kernel/cpu/mtrr/generic.c index f77fc53db65..5367e32e040 100644 --- a/arch/i386/kernel/cpu/mtrr/generic.c +++ b/arch/i386/kernel/cpu/mtrr/generic.c @@ -20,13 +20,25 @@ struct mtrr_state { mtrr_type def_type; }; +struct fixed_range_block { + int base_msr; /* start address of an MTRR block */ + int ranges; /* number of MTRRs in this block */ +}; + +static struct fixed_range_block fixed_range_blocks[] = { + { MTRRfix64K_00000_MSR, 1 }, /* one 64k MTRR */ + { MTRRfix16K_80000_MSR, 2 }, /* two 16k MTRRs */ + { MTRRfix4K_C0000_MSR, 8 }, /* eight 4k MTRRs */ + {} +}; + static unsigned long smp_changes_mask; static struct mtrr_state mtrr_state = {}; #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "mtrr." -static __initdata int mtrr_show; +static int mtrr_show; module_param_named(show, mtrr_show, bool, 0); /* Get the MSR pair relating to a var range */ @@ -37,7 +49,7 @@ get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr) rdmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi); } -static void __init +static void get_fixed_ranges(mtrr_type * frs) { unsigned int *p = (unsigned int *) frs; @@ -51,12 +63,18 @@ get_fixed_ranges(mtrr_type * frs) rdmsr(MTRRfix4K_C0000_MSR + i, p[6 + i * 2], p[7 + i * 2]); } -static void __init print_fixed(unsigned base, unsigned step, const mtrr_type*types) +void mtrr_save_fixed_ranges(void *info) +{ + get_fixed_ranges(mtrr_state.fixed_ranges); +} + +static void __cpuinit print_fixed(unsigned base, unsigned step, const mtrr_type*types) { unsigned i; for (i = 0; i < 8; ++i, ++types, base += step) - printk(KERN_INFO "MTRR %05X-%05X %s\n", base, base + step - 1, mtrr_attrib_to_str(*types)); + printk(KERN_INFO "MTRR %05X-%05X %s\n", + base, base + step - 1, mtrr_attrib_to_str(*types)); } /* Grab all of the MTRR state for this CPU into *state */ @@ -147,6 +165,44 @@ void mtrr_wrmsr(unsigned msr, unsigned a, unsigned b) smp_processor_id(), msr, a, b); } +/** + * Enable and allow read/write of extended fixed-range MTRR bits on K8 CPUs + * see AMD publication no. 24593, chapter 3.2.1 for more information + */ +static inline void k8_enable_fixed_iorrs(void) +{ + unsigned lo, hi; + + rdmsr(MSR_K8_SYSCFG, lo, hi); + mtrr_wrmsr(MSR_K8_SYSCFG, lo + | K8_MTRRFIXRANGE_DRAM_ENABLE + | K8_MTRRFIXRANGE_DRAM_MODIFY, hi); +} + +/** + * Checks and updates an fixed-range MTRR if it differs from the value it + * should have. If K8 extenstions are wanted, update the K8 SYSCFG MSR also. + * see AMD publication no. 24593, chapter 7.8.1, page 233 for more information + * \param msr MSR address of the MTTR which should be checked and updated + * \param changed pointer which indicates whether the MTRR needed to be changed + * \param msrwords pointer to the MSR values which the MSR should have + */ +static void set_fixed_range(int msr, int * changed, unsigned int * msrwords) +{ + unsigned lo, hi; + + rdmsr(msr, lo, hi); + + if (lo != msrwords[0] || hi != msrwords[1]) { + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD && + boot_cpu_data.x86 == 15 && + ((msrwords[0] | msrwords[1]) & K8_MTRR_RDMEM_WRMEM_MASK)) + k8_enable_fixed_iorrs(); + mtrr_wrmsr(msr, msrwords[0], msrwords[1]); + *changed = TRUE; + } +} + int generic_get_free_region(unsigned long base, unsigned long size, int replace_reg) /* [SUMMARY] Get a free MTRR. <base> The starting (base) address of the region. @@ -196,36 +252,21 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, *type = base_lo & 0xff; } +/** + * Checks and updates the fixed-range MTRRs if they differ from the saved set + * \param frs pointer to fixed-range MTRR values, saved by get_fixed_ranges() + */ static int set_fixed_ranges(mtrr_type * frs) { - unsigned int *p = (unsigned int *) frs; + unsigned long long *saved = (unsigned long long *) frs; int changed = FALSE; - int i; - unsigned int lo, hi; + int block=-1, range; - rdmsr(MTRRfix64K_00000_MSR, lo, hi); - if (p[0] != lo || p[1] != hi) { - mtrr_wrmsr(MTRRfix64K_00000_MSR, p[0], p[1]); - changed = TRUE; - } + while (fixed_range_blocks[++block].ranges) + for (range=0; range < fixed_range_blocks[block].ranges; range++) + set_fixed_range(fixed_range_blocks[block].base_msr + range, + &changed, (unsigned int *) saved++); - for (i = 0; i < 2; i++) { - rdmsr(MTRRfix16K_80000_MSR + i, lo, hi); - if (p[2 + i * 2] != lo || p[3 + i * 2] != hi) { - mtrr_wrmsr(MTRRfix16K_80000_MSR + i, p[2 + i * 2], - p[3 + i * 2]); - changed = TRUE; - } - } - - for (i = 0; i < 8; i++) { - rdmsr(MTRRfix4K_C0000_MSR + i, lo, hi); - if (p[6 + i * 2] != lo || p[7 + i * 2] != hi) { - mtrr_wrmsr(MTRRfix4K_C0000_MSR + i, p[6 + i * 2], - p[7 + i * 2]); - changed = TRUE; - } - } return changed; } @@ -428,7 +469,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, unsigned i } } - if (base + size < 0x100) { + if (base < 0x100) { printk(KERN_WARNING "mtrr: cannot set region below 1 MiB (0x%lx000,0x%lx000)\n", base, size); return -EINVAL; diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c index 0acfb6a5a22..02a2f39e5e0 100644 --- a/arch/i386/kernel/cpu/mtrr/main.c +++ b/arch/i386/kernel/cpu/mtrr/main.c @@ -729,6 +729,17 @@ void mtrr_ap_init(void) local_irq_restore(flags); } +/** + * Save current fixed-range MTRR state of the BSP + */ +void mtrr_save_state(void) +{ + if (smp_processor_id() == 0) + mtrr_save_fixed_ranges(NULL); + else + smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1); +} + static int __init mtrr_init_finialize(void) { if (!mtrr_if) diff --git a/arch/i386/kernel/cpu/nexgen.c b/arch/i386/kernel/cpu/nexgen.c index 8bf23cc80c6..961fbe1a748 100644 --- a/arch/i386/kernel/cpu/nexgen.c +++ b/arch/i386/kernel/cpu/nexgen.c @@ -58,13 +58,3 @@ int __init nexgen_init_cpu(void) cpu_devs[X86_VENDOR_NEXGEN] = &nexgen_cpu_dev; return 0; } - -//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/perfctr-watchdog.c b/arch/i386/kernel/cpu/perfctr-watchdog.c new file mode 100644 index 00000000000..2b04c8f1db6 --- /dev/null +++ b/arch/i386/kernel/cpu/perfctr-watchdog.c @@ -0,0 +1,658 @@ +/* local apic based NMI watchdog for various CPUs. + This file also handles reservation of performance counters for coordination + with other users (like oprofile). + + Note that these events normally don't tick when the CPU idles. This means + the frequency varies with CPU load. + + Original code for K7/P6 written by Keith Owens */ + +#include <linux/percpu.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/bitops.h> +#include <linux/smp.h> +#include <linux/nmi.h> +#include <asm/apic.h> +#include <asm/intel_arch_perfmon.h> + +struct nmi_watchdog_ctlblk { + unsigned int cccr_msr; + unsigned int perfctr_msr; /* the MSR to reset in NMI handler */ + unsigned int evntsel_msr; /* the MSR to select the events to handle */ +}; + +/* Interface defining a CPU specific perfctr watchdog */ +struct wd_ops { + int (*reserve)(void); + void (*unreserve)(void); + int (*setup)(unsigned nmi_hz); + void (*rearm)(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz); + void (*stop)(void *); + unsigned perfctr; + unsigned evntsel; + u64 checkbit; +}; + +static struct wd_ops *wd_ops; + +/* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's + * offset from MSR_P4_BSU_ESCR0. It will be the max for all platforms (for now) + */ +#define NMI_MAX_COUNTER_BITS 66 + +/* perfctr_nmi_owner tracks the ownership of the perfctr registers: + * evtsel_nmi_owner tracks the ownership of the event selection + * - different performance counters/ event selection may be reserved for + * different subsystems this reservation system just tries to coordinate + * things a little + */ +static DECLARE_BITMAP(perfctr_nmi_owner, NMI_MAX_COUNTER_BITS); +static DECLARE_BITMAP(evntsel_nmi_owner, NMI_MAX_COUNTER_BITS); + +static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk); + +/* converts an msr to an appropriate reservation bit */ +static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) +{ + return wd_ops ? msr - wd_ops->perfctr : 0; +} + +/* converts an msr to an appropriate reservation bit */ +/* returns the bit offset of the event selection register */ +static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) +{ + return wd_ops ? msr - wd_ops->evntsel : 0; +} + +/* checks for a bit availability (hack for oprofile) */ +int avail_to_resrv_perfctr_nmi_bit(unsigned int counter) +{ + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + return (!test_bit(counter, perfctr_nmi_owner)); +} + +/* checks the an msr for availability */ +int avail_to_resrv_perfctr_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_perfctr_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + return (!test_bit(counter, perfctr_nmi_owner)); +} + +int reserve_perfctr_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_perfctr_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + if (!test_and_set_bit(counter, perfctr_nmi_owner)) + return 1; + return 0; +} + +void release_perfctr_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_perfctr_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + clear_bit(counter, perfctr_nmi_owner); +} + +int reserve_evntsel_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_evntsel_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + if (!test_and_set_bit(counter, evntsel_nmi_owner)) + return 1; + return 0; +} + +void release_evntsel_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_evntsel_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + clear_bit(counter, evntsel_nmi_owner); +} + +EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi); +EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit); +EXPORT_SYMBOL(reserve_perfctr_nmi); +EXPORT_SYMBOL(release_perfctr_nmi); +EXPORT_SYMBOL(reserve_evntsel_nmi); +EXPORT_SYMBOL(release_evntsel_nmi); + +void disable_lapic_nmi_watchdog(void) +{ + BUG_ON(nmi_watchdog != NMI_LOCAL_APIC); + + if (atomic_read(&nmi_active) <= 0) + return; + + on_each_cpu(wd_ops->stop, NULL, 0, 1); + wd_ops->unreserve(); + + BUG_ON(atomic_read(&nmi_active) != 0); +} + +void enable_lapic_nmi_watchdog(void) +{ + BUG_ON(nmi_watchdog != NMI_LOCAL_APIC); + + /* are we already enabled */ + if (atomic_read(&nmi_active) != 0) + return; + + /* are we lapic aware */ + if (!wd_ops) + return; + if (!wd_ops->reserve()) { + printk(KERN_ERR "NMI watchdog: cannot reserve perfctrs\n"); + return; + } + + on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1); + touch_nmi_watchdog(); +} + +/* + * Activate the NMI watchdog via the local APIC. + */ + +static unsigned int adjust_for_32bit_ctr(unsigned int hz) +{ + u64 counter_val; + unsigned int retval = hz; + + /* + * On Intel CPUs with P6/ARCH_PERFMON only 32 bits in the counter + * are writable, with higher bits sign extending from bit 31. + * So, we can only program the counter with 31 bit values and + * 32nd bit should be 1, for 33.. to be 1. + * Find the appropriate nmi_hz + */ + counter_val = (u64)cpu_khz * 1000; + do_div(counter_val, retval); + if (counter_val > 0x7fffffffULL) { + u64 count = (u64)cpu_khz * 1000; + do_div(count, 0x7fffffffUL); + retval = count + 1; + } + return retval; +} + +static void +write_watchdog_counter(unsigned int perfctr_msr, const char *descr, unsigned nmi_hz) +{ + u64 count = (u64)cpu_khz * 1000; + + do_div(count, nmi_hz); + if(descr) + Dprintk("setting %s to -0x%08Lx\n", descr, count); + wrmsrl(perfctr_msr, 0 - count); +} + +static void write_watchdog_counter32(unsigned int perfctr_msr, + const char *descr, unsigned nmi_hz) +{ + u64 count = (u64)cpu_khz * 1000; + + do_div(count, nmi_hz); + if(descr) + Dprintk("setting %s to -0x%08Lx\n", descr, count); + wrmsr(perfctr_msr, (u32)(-count), 0); +} + +/* AMD K7/K8/Family10h/Family11h support. AMD keeps this interface + nicely stable so there is not much variety */ + +#define K7_EVNTSEL_ENABLE (1 << 22) +#define K7_EVNTSEL_INT (1 << 20) +#define K7_EVNTSEL_OS (1 << 17) +#define K7_EVNTSEL_USR (1 << 16) +#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING 0x76 +#define K7_NMI_EVENT K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING + +static int setup_k7_watchdog(unsigned nmi_hz) +{ + unsigned int perfctr_msr, evntsel_msr; + unsigned int evntsel; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + perfctr_msr = MSR_K7_PERFCTR0; + evntsel_msr = MSR_K7_EVNTSEL0; + + wrmsrl(perfctr_msr, 0UL); + + evntsel = K7_EVNTSEL_INT + | K7_EVNTSEL_OS + | K7_EVNTSEL_USR + | K7_NMI_EVENT; + + /* setup the timer */ + wrmsr(evntsel_msr, evntsel, 0); + write_watchdog_counter(perfctr_msr, "K7_PERFCTR0",nmi_hz); + apic_write(APIC_LVTPC, APIC_DM_NMI); + evntsel |= K7_EVNTSEL_ENABLE; + wrmsr(evntsel_msr, evntsel, 0); + + wd->perfctr_msr = perfctr_msr; + wd->evntsel_msr = evntsel_msr; + wd->cccr_msr = 0; //unused + return 1; +} + +static void single_msr_stop_watchdog(void *arg) +{ + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + wrmsr(wd->evntsel_msr, 0, 0); +} + +static int single_msr_reserve(void) +{ + if (!reserve_perfctr_nmi(wd_ops->perfctr)) + return 0; + + if (!reserve_evntsel_nmi(wd_ops->evntsel)) { + release_perfctr_nmi(wd_ops->perfctr); + return 0; + } + return 1; +} + +static void single_msr_unreserve(void) +{ + release_evntsel_nmi(wd_ops->perfctr); + release_perfctr_nmi(wd_ops->evntsel); +} + +static void single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) +{ + /* start the cycle over again */ + write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz); +} + +static struct wd_ops k7_wd_ops = { + .reserve = single_msr_reserve, + .unreserve = single_msr_unreserve, + .setup = setup_k7_watchdog, + .rearm = single_msr_rearm, + .stop = single_msr_stop_watchdog, + .perfctr = MSR_K7_PERFCTR0, + .evntsel = MSR_K7_EVNTSEL0, + .checkbit = 1ULL<<63, +}; + +/* Intel Model 6 (PPro+,P2,P3,P-M,Core1) */ + +#define P6_EVNTSEL0_ENABLE (1 << 22) +#define P6_EVNTSEL_INT (1 << 20) +#define P6_EVNTSEL_OS (1 << 17) +#define P6_EVNTSEL_USR (1 << 16) +#define P6_EVENT_CPU_CLOCKS_NOT_HALTED 0x79 +#define P6_NMI_EVENT P6_EVENT_CPU_CLOCKS_NOT_HALTED + +static int setup_p6_watchdog(unsigned nmi_hz) +{ + unsigned int perfctr_msr, evntsel_msr; + unsigned int evntsel; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + perfctr_msr = MSR_P6_PERFCTR0; + evntsel_msr = MSR_P6_EVNTSEL0; + + wrmsrl(perfctr_msr, 0UL); + + evntsel = P6_EVNTSEL_INT + | P6_EVNTSEL_OS + | P6_EVNTSEL_USR + | P6_NMI_EVENT; + + /* setup the timer */ + wrmsr(evntsel_msr, evntsel, 0); + nmi_hz = adjust_for_32bit_ctr(nmi_hz); + write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0",nmi_hz); + apic_write(APIC_LVTPC, APIC_DM_NMI); + evntsel |= P6_EVNTSEL0_ENABLE; + wrmsr(evntsel_msr, evntsel, 0); + + wd->perfctr_msr = perfctr_msr; + wd->evntsel_msr = evntsel_msr; + wd->cccr_msr = 0; //unused + return 1; +} + +static void p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) +{ + /* P6 based Pentium M need to re-unmask + * the apic vector but it doesn't hurt + * other P6 variant. + * ArchPerfom/Core Duo also needs this */ + apic_write(APIC_LVTPC, APIC_DM_NMI); + /* P6/ARCH_PERFMON has 32 bit counter write */ + write_watchdog_counter32(wd->perfctr_msr, NULL,nmi_hz); +} + +static struct wd_ops p6_wd_ops = { + .reserve = single_msr_reserve, + .unreserve = single_msr_unreserve, + .setup = setup_p6_watchdog, + .rearm = p6_rearm, + .stop = single_msr_stop_watchdog, + .perfctr = MSR_P6_PERFCTR0, + .evntsel = MSR_P6_EVNTSEL0, + .checkbit = 1ULL<<39, +}; + +/* Intel P4 performance counters. By far the most complicated of all. */ + +#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1<<7) +#define P4_ESCR_EVENT_SELECT(N) ((N)<<25) +#define P4_ESCR_OS (1<<3) +#define P4_ESCR_USR (1<<2) +#define P4_CCCR_OVF_PMI0 (1<<26) +#define P4_CCCR_OVF_PMI1 (1<<27) +#define P4_CCCR_THRESHOLD(N) ((N)<<20) +#define P4_CCCR_COMPLEMENT (1<<19) +#define P4_CCCR_COMPARE (1<<18) +#define P4_CCCR_REQUIRED (3<<16) +#define P4_CCCR_ESCR_SELECT(N) ((N)<<13) +#define P4_CCCR_ENABLE (1<<12) +#define P4_CCCR_OVF (1<<31) + +/* Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter + CRU_ESCR0 (with any non-null event selector) through a complemented + max threshold. [IA32-Vol3, Section 14.9.9] */ + +static int setup_p4_watchdog(unsigned nmi_hz) +{ + unsigned int perfctr_msr, evntsel_msr, cccr_msr; + unsigned int evntsel, cccr_val; + unsigned int misc_enable, dummy; + unsigned int ht_num; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy); + if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL)) + return 0; + +#ifdef CONFIG_SMP + /* detect which hyperthread we are on */ + if (smp_num_siblings == 2) { + unsigned int ebx, apicid; + + ebx = cpuid_ebx(1); + apicid = (ebx >> 24) & 0xff; + ht_num = apicid & 1; + } else +#endif + ht_num = 0; + + /* performance counters are shared resources + * assign each hyperthread its own set + * (re-use the ESCR0 register, seems safe + * and keeps the cccr_val the same) + */ + if (!ht_num) { + /* logical cpu 0 */ + perfctr_msr = MSR_P4_IQ_PERFCTR0; + evntsel_msr = MSR_P4_CRU_ESCR0; + cccr_msr = MSR_P4_IQ_CCCR0; + cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4); + } else { + /* logical cpu 1 */ + perfctr_msr = MSR_P4_IQ_PERFCTR1; + evntsel_msr = MSR_P4_CRU_ESCR0; + cccr_msr = MSR_P4_IQ_CCCR1; + cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4); + } + + evntsel = P4_ESCR_EVENT_SELECT(0x3F) + | P4_ESCR_OS + | P4_ESCR_USR; + + cccr_val |= P4_CCCR_THRESHOLD(15) + | P4_CCCR_COMPLEMENT + | P4_CCCR_COMPARE + | P4_CCCR_REQUIRED; + + wrmsr(evntsel_msr, evntsel, 0); + wrmsr(cccr_msr, cccr_val, 0); + write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0", nmi_hz); + apic_write(APIC_LVTPC, APIC_DM_NMI); + cccr_val |= P4_CCCR_ENABLE; + wrmsr(cccr_msr, cccr_val, 0); + wd->perfctr_msr = perfctr_msr; + wd->evntsel_msr = evntsel_msr; + wd->cccr_msr = cccr_msr; + return 1; +} + +static void stop_p4_watchdog(void *arg) +{ + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + wrmsr(wd->cccr_msr, 0, 0); + wrmsr(wd->evntsel_msr, 0, 0); +} + +static int p4_reserve(void) +{ + if (!reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR0)) + return 0; +#ifdef CONFIG_SMP + if (smp_num_siblings > 1 && !reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR1)) + goto fail1; +#endif + if (!reserve_evntsel_nmi(MSR_P4_CRU_ESCR0)) + goto fail2; + /* RED-PEN why is ESCR1 not reserved here? */ + return 1; + fail2: +#ifdef CONFIG_SMP + if (smp_num_siblings > 1) + release_perfctr_nmi(MSR_P4_IQ_PERFCTR1); + fail1: +#endif + release_perfctr_nmi(MSR_P4_IQ_PERFCTR0); + return 0; +} + +static void p4_unreserve(void) +{ +#ifdef CONFIG_SMP + if (smp_num_siblings > 1) + release_evntsel_nmi(MSR_P4_IQ_PERFCTR1); +#endif + release_evntsel_nmi(MSR_P4_IQ_PERFCTR0); + release_perfctr_nmi(MSR_P4_CRU_ESCR0); +} + +static void p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) +{ + unsigned dummy; + /* + * P4 quirks: + * - An overflown perfctr will assert its interrupt + * until the OVF flag in its CCCR is cleared. + * - LVTPC is masked on interrupt and must be + * unmasked by the LVTPC handler. + */ + rdmsrl(wd->cccr_msr, dummy); + dummy &= ~P4_CCCR_OVF; + wrmsrl(wd->cccr_msr, dummy); + apic_write(APIC_LVTPC, APIC_DM_NMI); + /* start the cycle over again */ + write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz); +} + +static struct wd_ops p4_wd_ops = { + .reserve = p4_reserve, + .unreserve = p4_unreserve, + .setup = setup_p4_watchdog, + .rearm = p4_rearm, + .stop = stop_p4_watchdog, + /* RED-PEN this is wrong for the other sibling */ + .perfctr = MSR_P4_BPU_PERFCTR0, + .evntsel = MSR_P4_BSU_ESCR0, + .checkbit = 1ULL<<39, +}; + +/* Watchdog using the Intel architected PerfMon. Used for Core2 and hopefully + all future Intel CPUs. */ + +#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL +#define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK + +static int setup_intel_arch_watchdog(unsigned nmi_hz) +{ + unsigned int ebx; + union cpuid10_eax eax; + unsigned int unused; + unsigned int perfctr_msr, evntsel_msr; + unsigned int evntsel; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + /* + * Check whether the Architectural PerfMon supports + * Unhalted Core Cycles Event or not. + * NOTE: Corresponding bit = 0 in ebx indicates event present. + */ + cpuid(10, &(eax.full), &ebx, &unused, &unused); + if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) || + (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) + return 0; + + perfctr_msr = MSR_ARCH_PERFMON_PERFCTR1; + evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL1; + + wrmsrl(perfctr_msr, 0UL); + + evntsel = ARCH_PERFMON_EVENTSEL_INT + | ARCH_PERFMON_EVENTSEL_OS + | ARCH_PERFMON_EVENTSEL_USR + | ARCH_PERFMON_NMI_EVENT_SEL + | ARCH_PERFMON_NMI_EVENT_UMASK; + + /* setup the timer */ + wrmsr(evntsel_msr, evntsel, 0); + nmi_hz = adjust_for_32bit_ctr(nmi_hz); + write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0", nmi_hz); + apic_write(APIC_LVTPC, APIC_DM_NMI); + evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE; + wrmsr(evntsel_msr, evntsel, 0); + + wd->perfctr_msr = perfctr_msr; + wd->evntsel_msr = evntsel_msr; + wd->cccr_msr = 0; //unused + wd_ops->checkbit = 1ULL << (eax.split.bit_width - 1); + return 1; +} + +static struct wd_ops intel_arch_wd_ops = { + .reserve = single_msr_reserve, + .unreserve = single_msr_unreserve, + .setup = setup_intel_arch_watchdog, + .rearm = p6_rearm, + .stop = single_msr_stop_watchdog, + .perfctr = MSR_ARCH_PERFMON_PERFCTR0, + .evntsel = MSR_ARCH_PERFMON_EVENTSEL0, +}; + +static void probe_nmi_watchdog(void) +{ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15 && + boot_cpu_data.x86 != 16) + return; + wd_ops = &k7_wd_ops; + break; + case X86_VENDOR_INTEL: + if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { + wd_ops = &intel_arch_wd_ops; + break; + } + switch (boot_cpu_data.x86) { + case 6: + if (boot_cpu_data.x86_model > 0xd) + return; + + wd_ops = &p6_wd_ops; + break; + case 15: + if (boot_cpu_data.x86_model > 0x4) + return; + + wd_ops = &p4_wd_ops; + break; + default: + return; + } + break; + } +} + +/* Interface to nmi.c */ + +int lapic_watchdog_init(unsigned nmi_hz) +{ + if (!wd_ops) { + probe_nmi_watchdog(); + if (!wd_ops) + return -1; + } + + if (!(wd_ops->setup(nmi_hz))) { + printk(KERN_ERR "Cannot setup NMI watchdog on CPU %d\n", + raw_smp_processor_id()); + return -1; + } + + return 0; +} + +void lapic_watchdog_stop(void) +{ + if (wd_ops) + wd_ops->stop(NULL); +} + +unsigned lapic_adjust_nmi_hz(unsigned hz) +{ + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + if (wd->perfctr_msr == MSR_P6_PERFCTR0 || + wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR1) + hz = adjust_for_32bit_ctr(hz); + return hz; +} + +int lapic_wd_event(unsigned nmi_hz) +{ + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + u64 ctr; + rdmsrl(wd->perfctr_msr, ctr); + if (ctr & wd_ops->checkbit) { /* perfctr still running? */ + return 0; + } + wd_ops->rearm(wd, nmi_hz); + return 1; +} + +int lapic_watchdog_ok(void) +{ + return wd_ops != NULL; +} diff --git a/arch/i386/kernel/cpu/proc.c b/arch/i386/kernel/cpu/proc.c index 47e3ebbfb28..89d91e6cc97 100644 --- a/arch/i386/kernel/cpu/proc.c +++ b/arch/i386/kernel/cpu/proc.c @@ -72,8 +72,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) "stc", "100mhzsteps", "hwpstate", - NULL, - NULL, /* constant_tsc - moved to flags */ + "", /* constant_tsc - moved to flags */ /* nothing */ }; struct cpuinfo_x86 *c = v; diff --git a/arch/i386/kernel/cpu/rise.c b/arch/i386/kernel/cpu/rise.c index 9317f741498..50076f22e90 100644 --- a/arch/i386/kernel/cpu/rise.c +++ b/arch/i386/kernel/cpu/rise.c @@ -50,12 +50,3 @@ int __init rise_init_cpu(void) return 0; } -//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 5678d46863c..6471a5a1320 100644 --- a/arch/i386/kernel/cpu/transmeta.c +++ b/arch/i386/kernel/cpu/transmeta.c @@ -112,13 +112,3 @@ int __init transmeta_init_cpu(void) cpu_devs[X86_VENDOR_TRANSMETA] = &transmeta_cpu_dev; return 0; } - -//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 1bf3f87e9c5..a7a4e75bdcd 100644 --- a/arch/i386/kernel/cpu/umc.c +++ b/arch/i386/kernel/cpu/umc.c @@ -24,13 +24,3 @@ int __init umc_init_cpu(void) cpu_devs[X86_VENDOR_UMC] = &umc_cpu_dev; return 0; } - -//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); |