diff options
Diffstat (limited to 'arch/i386/kernel/cpu')
27 files changed, 1004 insertions, 580 deletions
diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c index e4758095d87a..41cfea57232b 100644 --- a/arch/i386/kernel/cpu/amd.c +++ b/arch/i386/kernel/cpu/amd.c @@ -104,10 +104,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) f_vide(); rdtscl(d2); d = d2-d; - - /* Knock these two lines out if it debugs out ok */ - printk(KERN_INFO "AMD K6 stepping B detected - "); - /* -- cut here -- */ + if (d > 20*K6_BUG_LOOP) printk("system stability may be impaired when more than 32 MB are used.\n"); else diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index d9f3e3c31f05..8689d62abd4a 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -18,14 +18,15 @@ #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(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]); -EXPORT_PER_CPU_SYMBOL(cpu_16bit_stack); +struct i386_pda *_cpu_pda[NR_CPUS] __read_mostly; +EXPORT_SYMBOL(_cpu_pda); static int cachesize_override __cpuinitdata = -1; static int disable_x86_fxsr __cpuinitdata; @@ -53,7 +54,7 @@ static struct cpu_dev __cpuinitdata default_cpu = { .c_init = default_init, .c_vendor = "Unknown", }; -static struct cpu_dev * this_cpu = &default_cpu; +static struct cpu_dev * this_cpu __cpuinitdata = &default_cpu; static int __init cachesize_setup(char *str) { @@ -235,29 +236,14 @@ static int __cpuinit have_cpuid_p(void) return flag_is_changeable_p(X86_EFLAGS_ID); } -/* Do minimum CPU detection early. - Fields really needed: vendor, cpuid_level, family, model, mask, cache alignment. - The others are not touched to avoid unwanted side effects. - - WARNING: this function is only called on the BP. Don't add code here - that is supposed to run on all CPUs. */ -static void __init early_cpu_detect(void) +void __init cpu_detect(struct cpuinfo_x86 *c) { - struct cpuinfo_x86 *c = &boot_cpu_data; - - c->x86_cache_alignment = 32; - - if (!have_cpuid_p()) - return; - /* Get vendor name */ cpuid(0x00000000, &c->cpuid_level, (int *)&c->x86_vendor_id[0], (int *)&c->x86_vendor_id[8], (int *)&c->x86_vendor_id[4]); - get_cpu_vendor(c, 1); - c->x86 = 4; if (c->cpuid_level >= 0x00000001) { u32 junk, tfms, cap0, misc; @@ -274,6 +260,26 @@ static void __init early_cpu_detect(void) } } +/* Do minimum CPU detection early. + Fields really needed: vendor, cpuid_level, family, model, mask, cache alignment. + The others are not touched to avoid unwanted side effects. + + WARNING: this function is only called on the BP. Don't add code here + that is supposed to run on all CPUs. */ +static void __init early_cpu_detect(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + c->x86_cache_alignment = 32; + + if (!have_cpuid_p()) + return; + + cpu_detect(c); + + get_cpu_vendor(c, 1); +} + static void __cpuinit generic_identify(struct cpuinfo_x86 * c) { u32 tfms, xlvl; @@ -308,6 +314,8 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 * c) #else c->apicid = (ebx >> 24) & 0xFF; #endif + if (c->x86_capability[0] & (1<<19)) + c->x86_clflush_size = ((ebx >> 8) & 0xff) * 8; } else { /* Have CPUID level 0 only - unheard of */ c->x86 = 4; @@ -372,6 +380,7 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) c->x86_vendor_id[0] = '\0'; /* Unset */ c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; + c->x86_clflush_size = 32; memset(&c->x86_capability, 0, sizeof c->x86_capability); if (!have_cpuid_p()) { @@ -591,42 +600,24 @@ void __init early_cpu_init(void) disable_pse = 1; #endif } -/* - * 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) + +/* Make sure %gs is initialized properly in idle threads */ +struct pt_regs * __devinit idle_regs(struct pt_regs *regs) { - int cpu = smp_processor_id(); - struct tss_struct * t = &per_cpu(init_tss, cpu); - struct thread_struct *thread = ¤t->thread; - 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); + memset(regs, 0, sizeof(struct pt_regs)); + regs->xgs = __KERNEL_PDA; + return regs; +} - if (cpu_test_and_set(cpu, cpu_initialized)) { - printk(KERN_WARNING "CPU#%d already initialized!\n", cpu); - for (;;) local_irq_enable(); - } - printk(KERN_INFO "Initializing CPU#%d\n", cpu); +static __cpuinit int alloc_gdt(int cpu) +{ + struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu); + struct desc_struct *gdt; + struct i386_pda *pda; - if (cpu_has_vme || cpu_has_tsc || cpu_has_de) - clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); - if (tsc_disable && cpu_has_tsc) { - printk(KERN_NOTICE "Disabling TSC...\n"); - /**** FIX-HPA: DOES THIS REALLY BELONG HERE? ****/ - clear_bit(X86_FEATURE_TSC, boot_cpu_data.x86_capability); - set_in_cr4(X86_CR4_TSD); - } + gdt = (struct desc_struct *)cpu_gdt_descr->address; + pda = cpu_pda(cpu); - /* The CPU hotplug case */ - if (cpu_gdt_descr->address) { - gdt = (struct desc_struct *)cpu_gdt_descr->address; - memset(gdt, 0, PAGE_SIZE); - goto old_gdt; - } /* * This is a horrible hack to allocate the GDT. The problem * is that cpu_init() is called really early for the boot CPU @@ -634,43 +625,130 @@ void __cpuinit cpu_init(void) * 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 */ + 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 = (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(); + /* 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; } } -old_gdt: + + cpu_gdt_descr->address = (unsigned long)gdt; + cpu_pda(cpu) = pda; + + return 1; +} + +/* 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_gs(void) +{ + /* Set %gs 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, %%gs" : : "r" (__KERNEL_PDA) : "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; - /* Set up GDT entry for 16bit stack */ - *(__u64 *)(&gdt[GDT_ENTRY_ESPFIX_SS]) |= - ((((__u64)stk16_off) << 16) & 0x000000ffffff0000ULL) | - ((((__u64)stk16_off) << 32) & 0xff00000000000000ULL) | - (CPU_16BIT_STACK_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 */ - cpu_gdt_descr->size = GDT_SIZE - 1; - cpu_gdt_descr->address = (unsigned long)gdt; + memset(pda, 0, sizeof(*pda)); + pda->_pda = pda; + pda->cpu_number = cpu; + pda->pcurrent = idle; + + return 1; +} + +/* Common CPU init for both boot and secondary CPUs */ +static void __cpuinit _cpu_init(int cpu, struct task_struct *curr) +{ + struct tss_struct * t = &per_cpu(init_tss, cpu); + struct thread_struct *thread = &curr->thread; + 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_gs(); + + if (cpu_test_and_set(cpu, cpu_initialized)) { + printk(KERN_WARNING "CPU#%d already initialized!\n", cpu); + for (;;) local_irq_enable(); + } + + printk(KERN_INFO "Initializing CPU#%d\n", cpu); + + if (cpu_has_vme || cpu_has_tsc || cpu_has_de) + clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); + if (tsc_disable && cpu_has_tsc) { + printk(KERN_NOTICE "Disabling TSC...\n"); + /**** FIX-HPA: DOES THIS REALLY BELONG HERE? ****/ + clear_bit(X86_FEATURE_TSC, boot_cpu_data.x86_capability); + set_in_cr4(X86_CR4_TSD); + } + load_idt(&idt_descr); /* * Set up and load the per-CPU TSS and LDT */ atomic_inc(&init_mm.mm_count); - current->active_mm = &init_mm; - BUG_ON(current->mm); - enter_lazy_tlb(&init_mm, current); + curr->active_mm = &init_mm; + if (curr->mm) + BUG(); + enter_lazy_tlb(&init_mm, curr); load_esp0(t, thread); set_tss_desc(cpu,t); @@ -682,8 +760,8 @@ old_gdt: __set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss); #endif - /* Clear %fs and %gs. */ - asm volatile ("movl %0, %%fs; movl %0, %%gs" : : "r" (0)); + /* Clear %fs. */ + asm volatile ("mov %0, %%fs" : : "r" (0)); /* Clear all 6 debug registers: */ set_debugreg(0, 0); @@ -701,6 +779,37 @@ old_gdt: 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_init(cpu, curr); +} + #ifdef CONFIG_HOTPLUG_CPU void __cpuinit cpu_uninit(void) { diff --git a/arch/i386/kernel/cpu/cpufreq/Kconfig b/arch/i386/kernel/cpu/cpufreq/Kconfig index ccc1edff5c97..5299c5bf4454 100644 --- a/arch/i386/kernel/cpu/cpufreq/Kconfig +++ b/arch/i386/kernel/cpu/cpufreq/Kconfig @@ -17,6 +17,7 @@ config X86_ACPI_CPUFREQ help This driver adds a CPUFreq driver which utilizes the ACPI Processor Performance States. + This driver also supports Intel Enhanced Speedstep. For details, take a look at <file:Documentation/cpu-freq/>. @@ -121,11 +122,14 @@ config X86_SPEEDSTEP_CENTRINO If in doubt, say N. config X86_SPEEDSTEP_CENTRINO_ACPI - bool "Use ACPI tables to decode valid frequency/voltage pairs" + bool "Use ACPI tables to decode valid frequency/voltage (deprecated)" depends on X86_SPEEDSTEP_CENTRINO && ACPI_PROCESSOR depends on !(X86_SPEEDSTEP_CENTRINO = y && ACPI_PROCESSOR = m) default y help + This is deprecated and this functionality is now merged into + acpi_cpufreq (X86_ACPI_CPUFREQ). Use that driver instead of + speedstep_centrino. Use primarily the information provided in the BIOS ACPI tables to determine valid CPU frequency and voltage pairings. It is required for the driver to work on non-Banias CPUs. diff --git a/arch/i386/kernel/cpu/cpufreq/Makefile b/arch/i386/kernel/cpu/cpufreq/Makefile index 2e894f1c8910..8de3abe322a9 100644 --- a/arch/i386/kernel/cpu/cpufreq/Makefile +++ b/arch/i386/kernel/cpu/cpufreq/Makefile @@ -7,9 +7,9 @@ obj-$(CONFIG_SC520_CPUFREQ) += sc520_freq.o obj-$(CONFIG_X86_LONGRUN) += longrun.o obj-$(CONFIG_X86_GX_SUSPMOD) += gx-suspmod.o obj-$(CONFIG_X86_SPEEDSTEP_ICH) += speedstep-ich.o -obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o obj-$(CONFIG_X86_SPEEDSTEP_LIB) += speedstep-lib.o obj-$(CONFIG_X86_SPEEDSTEP_SMI) += speedstep-smi.o obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o +obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o obj-$(CONFIG_X86_P4_CLOCKMOD) += p4-clockmod.o obj-$(CONFIG_X86_CPUFREQ_NFORCE2) += cpufreq-nforce2.o diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c index 57c880bf0bd6..10baa3501ed3 100644 --- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -1,9 +1,10 @@ /* - * acpi-cpufreq.c - ACPI Processor P-States Driver ($Revision: 1.3 $) + * acpi-cpufreq.c - ACPI Processor P-States Driver ($Revision: 1.4 $) * * Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com> * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> * Copyright (C) 2002 - 2004 Dominik Brodowski <linux@brodo.de> + * Copyright (C) 2006 Denis Sadykov <denis.m.sadykov@intel.com> * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * @@ -27,202 +28,370 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> +#include <linux/smp.h> +#include <linux/sched.h> #include <linux/cpufreq.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> #include <linux/compiler.h> -#include <linux/sched.h> /* current */ #include <linux/dmi.h> -#include <asm/io.h> -#include <asm/delay.h> -#include <asm/uaccess.h> #include <linux/acpi.h> #include <acpi/processor.h> +#include <asm/io.h> +#include <asm/msr.h> +#include <asm/processor.h> +#include <asm/cpufeature.h> +#include <asm/delay.h> +#include <asm/uaccess.h> + #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "acpi-cpufreq", msg) MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski"); MODULE_DESCRIPTION("ACPI Processor P-States Driver"); MODULE_LICENSE("GPL"); +enum { + UNDEFINED_CAPABLE = 0, + SYSTEM_INTEL_MSR_CAPABLE, + SYSTEM_IO_CAPABLE, +}; + +#define INTEL_MSR_RANGE (0xffff) +#define CPUID_6_ECX_APERFMPERF_CAPABILITY (0x1) -struct cpufreq_acpi_io { - struct acpi_processor_performance *acpi_data; - struct cpufreq_frequency_table *freq_table; - unsigned int resume; +struct acpi_cpufreq_data { + struct acpi_processor_performance *acpi_data; + struct cpufreq_frequency_table *freq_table; + unsigned int max_freq; + unsigned int resume; + unsigned int cpu_feature; }; -static struct cpufreq_acpi_io *acpi_io_data[NR_CPUS]; -static struct acpi_processor_performance *acpi_perf_data[NR_CPUS]; +static struct acpi_cpufreq_data *drv_data[NR_CPUS]; +static struct acpi_processor_performance *acpi_perf_data[NR_CPUS]; static struct cpufreq_driver acpi_cpufreq_driver; static unsigned int acpi_pstate_strict; -static int -acpi_processor_write_port( - u16 port, - u8 bit_width, - u32 value) +static int check_est_cpu(unsigned int cpuid) { - if (bit_width <= 8) { - outb(value, port); - } else if (bit_width <= 16) { - outw(value, port); - } else if (bit_width <= 32) { - outl(value, port); - } else { - return -ENODEV; + struct cpuinfo_x86 *cpu = &cpu_data[cpuid]; + + if (cpu->x86_vendor != X86_VENDOR_INTEL || + !cpu_has(cpu, X86_FEATURE_EST)) + return 0; + + return 1; +} + +static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data) +{ + struct acpi_processor_performance *perf; + int i; + + perf = data->acpi_data; + + for (i=0; i<perf->state_count; i++) { + if (value == perf->states[i].status) + return data->freq_table[i].frequency; } return 0; } -static int -acpi_processor_read_port( - u16 port, - u8 bit_width, - u32 *ret) +static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data) { - *ret = 0; - if (bit_width <= 8) { - *ret = inb(port); - } else if (bit_width <= 16) { - *ret = inw(port); - } else if (bit_width <= 32) { - *ret = inl(port); - } else { - return -ENODEV; + int i; + struct acpi_processor_performance *perf; + + msr &= INTEL_MSR_RANGE; + perf = data->acpi_data; + + for (i=0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) { + if (msr == perf->states[data->freq_table[i].index].status) + return data->freq_table[i].frequency; } - return 0; + return data->freq_table[0].frequency; } -static int -acpi_processor_set_performance ( - struct cpufreq_acpi_io *data, - unsigned int cpu, - int state) +static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data) { - u16 port = 0; - u8 bit_width = 0; - int i = 0; - int ret = 0; - u32 value = 0; - int retval; - struct acpi_processor_performance *perf; - - dprintk("acpi_processor_set_performance\n"); - - retval = 0; - perf = data->acpi_data; - if (state == perf->state) { - if (unlikely(data->resume)) { - dprintk("Called after resume, resetting to P%d\n", state); - data->resume = 0; - } else { - dprintk("Already at target state (P%d)\n", state); - return (retval); - } + switch (data->cpu_feature) { + case SYSTEM_INTEL_MSR_CAPABLE: + return extract_msr(val, data); + case SYSTEM_IO_CAPABLE: + return extract_io(val, data); + default: + return 0; } +} + +struct msr_addr { + u32 reg; +}; - dprintk("Transitioning from P%d to P%d\n", perf->state, state); +struct io_addr { + u16 port; + u8 bit_width; +}; - /* - * First we write the target state's 'control' value to the - * control_register. - */ +typedef union { + struct msr_addr msr; + struct io_addr io; +} drv_addr_union; - port = perf->control_register.address; - bit_width = perf->control_register.bit_width; - value = (u32) perf->states[state].control; +struct drv_cmd { + unsigned int type; + cpumask_t mask; + drv_addr_union addr; + u32 val; +}; - dprintk("Writing 0x%08x to port 0x%04x\n", value, port); +static void do_drv_read(struct drv_cmd *cmd) +{ + u32 h; + + switch (cmd->type) { + case SYSTEM_INTEL_MSR_CAPABLE: + rdmsr(cmd->addr.msr.reg, cmd->val, h); + break; + case SYSTEM_IO_CAPABLE: + acpi_os_read_port((acpi_io_address)cmd->addr.io.port, + &cmd->val, + (u32)cmd->addr.io.bit_width); + break; + default: + break; + } +} - ret = acpi_processor_write_port(port, bit_width, value); - if (ret) { - dprintk("Invalid port width 0x%04x\n", bit_width); - return (ret); +static void do_drv_write(struct drv_cmd *cmd) +{ + u32 h = 0; + + switch (cmd->type) { + case SYSTEM_INTEL_MSR_CAPABLE: + wrmsr(cmd->addr.msr.reg, cmd->val, h); + break; + case SYSTEM_IO_CAPABLE: + acpi_os_write_port((acpi_io_address)cmd->addr.io.port, + cmd->val, + (u32)cmd->addr.io.bit_width); + break; + default: + break; } +} +static void drv_read(struct drv_cmd *cmd) +{ + cpumask_t saved_mask = current->cpus_allowed; + cmd->val = 0; + + set_cpus_allowed(current, cmd->mask); + do_drv_read(cmd); + set_cpus_allowed(current, saved_mask); +} + +static void drv_write(struct drv_cmd *cmd) +{ + cpumask_t saved_mask = current->cpus_allowed; + unsigned int i; + + for_each_cpu_mask(i, cmd->mask) { + set_cpus_allowed(current, cpumask_of_cpu(i)); + do_drv_write(cmd); + } + + set_cpus_allowed(current, saved_mask); + return; +} + +static u32 get_cur_val(cpumask_t mask) +{ + struct acpi_processor_performance *perf; + struct drv_cmd cmd; + + if (unlikely(cpus_empty(mask))) + return 0; + + switch (drv_data[first_cpu(mask)]->cpu_feature) { + case SYSTEM_INTEL_MSR_CAPABLE: + cmd.type = SYSTEM_INTEL_MSR_CAPABLE; + cmd.addr.msr.reg = MSR_IA32_PERF_STATUS; + break; + case SYSTEM_IO_CAPABLE: + cmd.type = SYSTEM_IO_CAPABLE; + perf = drv_data[first_cpu(mask)]->acpi_data; + cmd.addr.io.port = perf->control_register.address; + cmd.addr.io.bit_width = perf->control_register.bit_width; + break; + default: + return 0; + } + + cmd.mask = mask; + + drv_read(&cmd); + + dprintk("get_cur_val = %u\n", cmd.val); + + return cmd.val; +} + +/* + * Return the measured active (C0) frequency on this CPU since last call + * to this function. + * Input: cpu number + * Return: Average CPU frequency in terms of max frequency (zero on error) + * + * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance + * over a period of time, while CPU is in C0 state. + * IA32_MPERF counts at the rate of max advertised frequency + * IA32_APERF counts at the rate of actual CPU frequency + * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and + * no meaning should be associated with absolute values of these MSRs. + */ +static unsigned int get_measured_perf(unsigned int cpu) +{ + union { + struct { + u32 lo; + u32 hi; + } split; + u64 whole; + } aperf_cur, mperf_cur; + + cpumask_t saved_mask; + unsigned int perf_percent; + unsigned int retval; + + saved_mask = current->cpus_allowed; + set_cpus_allowed(current, cpumask_of_cpu(cpu)); + if (get_cpu() != cpu) { + /* We were not able to run on requested processor */ + put_cpu(); + return 0; + } + + rdmsr(MSR_IA32_APERF, aperf_cur.split.lo, aperf_cur.split.hi); + rdmsr(MSR_IA32_MPERF, mperf_cur.split.lo, mperf_cur.split.hi); + + wrmsr(MSR_IA32_APERF, 0,0); + wrmsr(MSR_IA32_MPERF, 0,0); + +#ifdef __i386__ /* - * Assume the write went through when acpi_pstate_strict is not used. - * As read status_register is an expensive operation and there - * are no specific error cases where an IO port write will fail. + * We dont want to do 64 bit divide with 32 bit kernel + * Get an approximate value. Return failure in case we cannot get + * an approximate value. */ - if (acpi_pstate_strict) { - /* Then we read the 'status_register' and compare the value - * with the target state's 'status' to make sure the - * transition was successful. - * Note that we'll poll for up to 1ms (100 cycles of 10us) - * before giving up. - */ - - port = perf->status_register.address; - bit_width = perf->status_register.bit_width; - - dprintk("Looking for 0x%08x from port 0x%04x\n", - (u32) perf->states[state].status, port); - - for (i = 0; i < 100; i++) { - ret = acpi_processor_read_port(port, bit_width, &value); - if (ret) { - dprintk("Invalid port width 0x%04x\n", bit_width); - return (ret); - } - if (value == (u32) perf->states[state].status) - break; - udelay(10); - } - } else { - value = (u32) perf->states[state].status; + if (unlikely(aperf_cur.split.hi || mperf_cur.split.hi)) { + int shift_count; + u32 h; + + h = max_t(u32, aperf_cur.split.hi, mperf_cur.split.hi); + shift_count = fls(h); + + aperf_cur.whole >>= shift_count; + mperf_cur.whole >>= shift_count; + } + + if (((unsigned long)(-1) / 100) < aperf_cur.split.lo) { + int shift_count = 7; + aperf_cur.split.lo >>= shift_count; + mperf_cur.split.lo >>= shift_count; + } + + if (aperf_cur.split.lo && mperf_cur.split.lo) + perf_percent = (aperf_cur.split.lo * 100) / mperf_cur.split.lo; + else + perf_percent = 0; + +#else + if (unlikely(((unsigned long)(-1) / 100) < aperf_cur.whole)) { + int shift_count = 7; + aperf_cur.whole >>= shift_count; + mperf_cur.whole >>= shift_count; } - if (unlikely(value != (u32) perf->states[state].status)) { - printk(KERN_WARNING "acpi-cpufreq: Transition failed\n"); - retval = -ENODEV; - return (retval); + if (aperf_cur.whole && mperf_cur.whole) + perf_percent = (aperf_cur.whole * 100) / mperf_cur.whole; + else + perf_percent = 0; + +#endif + + retval = drv_data[cpu]->max_freq * perf_percent / 100; + + put_cpu(); + set_cpus_allowed(current, saved_mask); + + dprintk("cpu %d: performance percent %d\n", cpu, perf_percent); + return retval; +} + +static unsigned int get_cur_freq_on_cpu(unsigned int cpu) +{ + struct acpi_cpufreq_data *data = drv_data[cpu]; + unsigned int freq; + + dprintk("get_cur_freq_on_cpu (%d)\n", cpu); + + if (unlikely(data == NULL || + data->acpi_data == NULL || data->freq_table == NULL)) { + return 0; } - dprintk("Transition successful after %d microseconds\n", i * 10); + freq = extract_freq(get_cur_val(cpumask_of_cpu(cpu)), data); + dprintk("cur freq = %u\n", freq); - perf->state = state; - return (retval); + return freq; } +static unsigned int check_freqs(cpumask_t mask, unsigned int freq, + struct acpi_cpufreq_data *data) +{ + unsigned int cur_freq; + unsigned int i; + + for (i=0; i<100; i++) { + cur_freq = extract_freq(get_cur_val(mask), data); + if (cur_freq == freq) + return 1; + udelay(10); + } + return 0; +} -static int -acpi_cpufreq_target ( - struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) +static int acpi_cpufreq_target(struct cpufreq_policy *policy, + unsigned int target_freq, unsigned int relation) { - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; + struct acpi_cpufreq_data *data = drv_data[policy->cpu]; struct acpi_processor_performance *perf; struct cpufreq_freqs freqs; cpumask_t online_policy_cpus; - cpumask_t saved_mask; - cpumask_t set_mask; - cpumask_t covered_cpus; - unsigned int cur_state = 0; - unsigned int next_state = 0; - unsigned int result = 0; - unsigned int j; - unsigned int tmp; + struct drv_cmd cmd; + unsigned int msr; + unsigned int next_state = 0; /* Index into freq_table */ + unsigned int next_perf_state = 0; /* Index into perf table */ + unsigned int i; + int result = 0; - dprintk("acpi_cpufreq_setpolicy\n"); + dprintk("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu); - result = cpufreq_frequency_table_target(policy, - data->freq_table, - target_freq, - relation, - &next_state); - if (unlikely(result)) - return (result); + if (unlikely(data == NULL || + data->acpi_data == NULL || data->freq_table == NULL)) { + return -ENODEV; + } perf = data->acpi_data; - cur_state = perf->state; - freqs.old = data->freq_table[cur_state].frequency; - freqs.new = data->freq_table[next_state].frequency; + result = cpufreq_frequency_table_target(policy, + data->freq_table, + target_freq, + relation, &next_state); + if (unlikely(result)) + return -ENODEV; #ifdef CONFIG_HOTPLUG_CPU /* cpufreq holds the hotplug lock, so we are safe from here on */ @@ -231,106 +400,85 @@ acpi_cpufreq_target ( online_policy_cpus = policy->cpus; #endif - for_each_cpu_mask(j, online_policy_cpus) { - freqs.cpu = j; - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); + next_perf_state = data->freq_table[next_state].index; + if (perf->state == next_perf_state) { + if (unlikely(data->resume)) { + dprintk("Called after resume, resetting to P%d\n", + next_perf_state); + data->resume = 0; + } else { + dprintk("Already at target state (P%d)\n", + next_perf_state); + return 0; + } } - /* - * We need to call driver->target() on all or any CPU in - * policy->cpus, depending on policy->shared_type. - */ - saved_mask = current->cpus_allowed; - cpus_clear(covered_cpus); - for_each_cpu_mask(j, online_policy_cpus) { - /* - * Support for SMP systems. - * Make sure we are running on CPU that wants to change freq - */ - cpus_clear(set_mask); - if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) - cpus_or(set_mask, set_mask, online_policy_cpus); - else - cpu_set(j, set_mask); - - set_cpus_allowed(current, set_mask); - if (unlikely(!cpu_isset(smp_processor_id(), set_mask))) { - dprintk("couldn't limit to CPUs in this domain\n"); - result = -EAGAIN; - break; - } + switch (data->cpu_feature) { + case SYSTEM_INTEL_MSR_CAPABLE: + cmd.type = SYSTEM_INTEL_MSR_CAPABLE; + cmd.addr.msr.reg = MSR_IA32_PERF_CTL; + msr = + (u32) perf->states[next_perf_state]. + control & INTEL_MSR_RANGE; + cmd.val = get_cur_val(online_policy_cpus); + cmd.val = (cmd.val & ~INTEL_MSR_RANGE) | msr; + break; + case SYSTEM_IO_CAPABLE: + cmd.type = SYSTEM_IO_CAPABLE; + cmd.addr.io.port = perf->control_register.address; + cmd.addr.io.bit_width = perf->control_register.bit_width; + cmd.val = (u32) perf->states[next_perf_state].control; + break; + default: + return -ENODEV; + } - result = acpi_processor_set_performance (data, j, next_state); - if (result) { - result = -EAGAIN; - break; - } + cpus_clear(cmd.mask); - if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) - break; - - cpu_set(j, covered_cpus); - } + if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY) + cmd.mask = online_policy_cpus; + else + cpu_set(policy->cpu, cmd.mask); - for_each_cpu_mask(j, online_policy_cpus) { - freqs.cpu = j; - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + freqs.old = perf->states[perf->state].core_frequency * 1000; + freqs.new = data->freq_table[next_state].frequency; + for_each_cpu_mask(i, cmd.mask) { + freqs.cpu = i; + cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } - if (unlikely(result)) { - /* - * We have failed halfway through the frequency change. - * We have sent callbacks to online_policy_cpus and - * acpi_processor_set_performance() has been called on - * coverd_cpus. Best effort undo.. - */ - - if (!cpus_empty(covered_cpus)) { - for_each_cpu_mask(j, covered_cpus) { - policy->cpu = j; - acpi_processor_set_performance (data, - j, - cur_state); - } - } + drv_write(&cmd); - tmp = freqs.new; - freqs.new = freqs.old; - freqs.old = tmp; - for_each_cpu_mask(j, online_policy_cpus) { - freqs.cpu = j; - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + if (acpi_pstate_strict) { + if (!check_freqs(cmd.mask, freqs.new, data)) { + dprintk("acpi_cpufreq_target failed (%d)\n", + policy->cpu); + return -EAGAIN; } } - set_cpus_allowed(current, saved_mask); - return (result); -} + for_each_cpu_mask(i, cmd.mask) { + freqs.cpu = i; + cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + } + perf->state = next_perf_state; + return result; +} -static int -acpi_cpufreq_verify ( - struct cpufreq_policy *policy) +static int acpi_cpufreq_verify(struct cpufreq_policy *policy) { - unsigned int result = 0; - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; + struct acpi_cpufreq_data *data = drv_data[policy->cpu]; dprintk("acpi_cpufreq_verify\n"); - result = cpufreq_frequency_table_verify(policy, - data->freq_table); - - return (result); + return cpufreq_frequency_table_verify(policy, data->freq_table); } - static unsigned long -acpi_cpufreq_guess_freq ( - struct cpufreq_acpi_io *data, - unsigned int cpu) +acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu) { - struct acpi_processor_performance *perf = data->acpi_data; + struct acpi_processor_performance *perf = data->acpi_data; if (cpu_khz) { /* search the closest match to cpu_khz */ @@ -338,16 +486,16 @@ acpi_cpufreq_guess_freq ( unsigned long freq; unsigned long freqn = perf->states[0].core_frequency * 1000; - for (i = 0; i < (perf->state_count - 1); i++) { + for (i=0; i<(perf->state_count-1); i++) { freq = freqn; freqn = perf->states[i+1].core_frequency * 1000; if ((2 * cpu_khz) > (freqn + freq)) { perf->state = i; - return (freq); + return freq; } } - perf->state = perf->state_count - 1; - return (freqn); + perf->state = perf->state_count-1; + return freqn; } else { /* assume CPU is at P0... */ perf->state = 0; @@ -355,7 +503,6 @@ acpi_cpufreq_guess_freq ( } } - /* * acpi_cpufreq_early_init - initialize ACPI P-States library * @@ -364,30 +511,34 @@ acpi_cpufreq_guess_freq ( * do _PDC and _PSD and find out the processor dependency for the * actual init that will happen later... */ -static int acpi_cpufreq_early_init_acpi(void) +static int acpi_cpufreq_early_init(void) { - struct acpi_processor_performance *data; - unsigned int i, j; + struct acpi_processor_performance *data; + cpumask_t covered; + unsigned int i, j; dprintk("acpi_cpufreq_early_init\n"); for_each_possible_cpu(i) { - data = kzalloc(sizeof(struct acpi_processor_performance), - GFP_KERNEL); + data = kzalloc(sizeof(struct acpi_processor_performance), + GFP_KERNEL); if (!data) { - for_each_possible_cpu(j) { + for_each_cpu_mask(j, covered) { kfree(acpi_perf_data[j]); acpi_perf_data[j] = NULL; } - return (-ENOMEM); + return -ENOMEM; } acpi_perf_data[i] = data; + cpu_set(i, covered); } /* Do initialization in ACPI core */ - return acpi_processor_preregister_performance(acpi_perf_data); + acpi_processor_preregister_performance(acpi_perf_data); + return 0; } +#ifdef CONFIG_SMP /* * Some BIOSes do SW_ANY coordination internally, either set it up in hw * or do it in BIOS firmware and won't inform about it to OS. If not @@ -414,39 +565,42 @@ static struct dmi_system_id sw_any_bug_dmi_table[] = { }, { } }; +#endif -static int -acpi_cpufreq_cpu_init ( - struct cpufreq_policy *policy) +static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) { - unsigned int i; - unsigned int cpu = policy->cpu; - struct cpufreq_acpi_io *data; - unsigned int result = 0; + unsigned int i; + unsigned int valid_states = 0; + unsigned int cpu = policy->cpu; + struct acpi_cpufreq_data *data; + unsigned int result = 0; struct cpuinfo_x86 *c = &cpu_data[policy->cpu]; - struct acpi_processor_performance *perf; + struct acpi_processor_performance *perf; dprintk("acpi_cpufreq_cpu_init\n"); if (!acpi_perf_data[cpu]) - return (-ENODEV); + return -ENODEV; - data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL); + data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL); if (!data) - return (-ENOMEM); + return -ENOMEM; data->acpi_data = acpi_perf_data[cpu]; - acpi_io_data[cpu] = data; + drv_data[cpu] = data; - result = acpi_processor_register_performance(data->acpi_data, cpu); + if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) + acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS; + result = acpi_processor_register_performance(data->acpi_data, cpu); if (result) goto err_free; perf = data->acpi_data; policy->shared_type = perf->shared_type; + /* - * Will let policy->cpus know about dependency only when software + * Will let policy->cpus know about dependency only when software * coordination is required. */ if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL || @@ -462,10 +616,6 @@ acpi_cpufreq_cpu_init ( } #endif - if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { - acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS; - } - /* capability check */ if (perf->state_count <= 1) { dprintk("No P-States\n"); @@ -473,17 +623,33 @@ acpi_cpufreq_cpu_init ( goto err_unreg; } - if ((perf->control_register.space_id != ACPI_ADR_SPACE_SYSTEM_IO) || - (perf->status_register.space_id != ACPI_ADR_SPACE_SYSTEM_IO)) { - dprintk("Unsupported address space [%d, %d]\n", - (u32) (perf->control_register.space_id), - (u32) (perf->status_register.space_id)); + if (perf->control_register.space_id != perf->status_register.space_id) { result = -ENODEV; goto err_unreg; } - /* alloc freq_table */ - data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) * (perf->state_count + 1), GFP_KERNEL); + switch (perf->control_register.space_id) { + case ACPI_ADR_SPACE_SYSTEM_IO: + dprintk("SYSTEM IO addr space\n"); + data->cpu_feature = SYSTEM_IO_CAPABLE; + break; + case ACPI_ADR_SPACE_FIXED_HARDWARE: + dprintk("HARDWARE addr space\n"); + if (!check_est_cpu(cpu)) { + result = -ENODEV; + goto err_unreg; + } + data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE; + break; + default: + dprintk("Unknown addr space %d\n", + (u32) (perf->control_register.space_id)); + result = -ENODEV; + goto err_unreg; + } + + data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) * + (perf->state_count+1), GFP_KERNEL); if (!data->freq_table) { result = -ENOMEM; goto err_unreg; @@ -492,129 +658,141 @@ acpi_cpufreq_cpu_init ( /* detect transition latency */ policy->cpuinfo.transition_latency = 0; for (i=0; i<perf->state_count; i++) { - if ((perf->states[i].transition_latency * 1000) > policy->cpuinfo.transition_latency) - policy->cpuinfo.transition_latency = perf->states[i].transition_latency * 1000; + if ((perf->states[i].transition_latency * 1000) > + policy->cpuinfo.transition_latency) + policy->cpuinfo.transition_latency = + perf->states[i].transition_latency * 1000; } policy->governor = CPUFREQ_DEFAULT_GOVERNOR; - /* The current speed is unknown and not detectable by ACPI... */ - policy->cur = acpi_cpufreq_guess_freq(data, policy->cpu); - + data->max_freq = perf->states[0].core_frequency * 1000; /* table init */ - for (i=0; i<=perf->state_count; i++) - { - data->freq_table[i].index = i; - if (i<perf->state_count) - data->freq_table[i].frequency = perf->states[i].core_frequency * 1000; - else - data->freq_table[i].frequency = CPUFREQ_TABLE_END; + for (i=0; i<perf->state_count; i++) { + if (i>0 && perf->states[i].core_frequency == + perf->states[i-1].core_frequency) + continue; + + data->freq_table[valid_states].index = i; + data->freq_table[valid_states].frequency = + perf->states[i].core_frequency * 1000; + valid_states++; } + data->freq_table[valid_states].frequency = CPUFREQ_TABLE_END; + perf->state = 0; result = cpufreq_frequency_table_cpuinfo(policy, data->freq_table); - if (result) { + if (result) goto err_freqfree; + + switch (perf->control_register.space_id) { + case ACPI_ADR_SPACE_SYSTEM_IO: + /* Current speed is unknown and not detectable by IO port */ + policy->cur = acpi_cpufreq_guess_freq(data, policy->cpu); + break; + case ACPI_ADR_SPACE_FIXED_HARDWARE: + acpi_cpufreq_driver.get = get_cur_freq_on_cpu; + policy->cur = get_cur_freq_on_cpu(cpu); + break; + default: + break; } /* notify BIOS that we exist */ acpi_processor_notify_smm(THIS_MODULE); - printk(KERN_INFO "acpi-cpufreq: CPU%u - ACPI performance management activated.\n", - cpu); + /* Check for APERF/MPERF support in hardware */ + if (c->x86_vendor == X86_VENDOR_INTEL && c->cpuid_level >= 6) { + unsigned int ecx; + ecx = cpuid_ecx(6); + if (ecx & CPUID_6_ECX_APERFMPERF_CAPABILITY) + acpi_cpufreq_driver.getavg = get_measured_perf; + } + + dprintk("CPU%u - ACPI performance management activated.\n", cpu); for (i = 0; i < perf->state_count; i++) dprintk(" %cP%d: %d MHz, %d mW, %d uS\n", - (i == perf->state?'*':' '), i, + (i == perf->state ? '*' : ' '), i, (u32) perf->states[i].core_frequency, (u32) perf->states[i].power, (u32) perf->states[i].transition_latency); cpufreq_frequency_table_get_attr(data->freq_table, policy->cpu); - + /* * the first call to ->target() should result in us actually * writing something to the appropriate registers. */ data->resume = 1; - - return (result); - err_freqfree: + return result; + +err_freqfree: kfree(data->freq_table); - err_unreg: +err_unreg: acpi_processor_unregister_performance(perf, cpu); - err_free: +err_free: kfree(data); - acpi_io_data[cpu] = NULL; + drv_data[cpu] = NULL; - return (result); + return result; } - -static int -acpi_cpufreq_cpu_exit ( - struct cpufreq_policy *policy) +static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy) { - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; - + struct acpi_cpufreq_data *data = drv_data[policy->cpu]; dprintk("acpi_cpufreq_cpu_exit\n"); if (data) { cpufreq_frequency_table_put_attr(policy->cpu); - acpi_io_data[policy->cpu] = NULL; - acpi_processor_unregister_performance(data->acpi_data, policy->cpu); + drv_data[policy->cpu] = NULL; + acpi_processor_unregister_performance(data->acpi_data, + policy->cpu); kfree(data); } - return (0); + return 0; } -static int -acpi_cpufreq_resume ( - struct cpufreq_policy *policy) +static int acpi_cpufreq_resume(struct cpufreq_policy *policy) { - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; - + struct acpi_cpufreq_data *data = drv_data[policy->cpu]; dprintk("acpi_cpufreq_resume\n"); data->resume = 1; - return (0); + return 0; } - -static struct freq_attr* acpi_cpufreq_attr[] = { +static struct freq_attr *acpi_cpufreq_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; static struct cpufreq_driver acpi_cpufreq_driver = { - .verify = acpi_cpufreq_verify, - .target = acpi_cpufreq_target, - .init = acpi_cpufreq_cpu_init, - .exit = acpi_cpufreq_cpu_exit, - .resume = acpi_cpufreq_resume, - .name = "acpi-cpufreq", - .owner = THIS_MODULE, - .attr = acpi_cpufreq_attr, + .verify = acpi_cpufreq_verify, + .target = acpi_cpufreq_target, + .init = acpi_cpufreq_cpu_init, + .exit = acpi_cpufreq_cpu_exit, + .resume = acpi_cpufreq_resume, + .name = "acpi-cpufreq", + .owner = THIS_MODULE, + .attr = acpi_cpufreq_attr, }; - -static int __init -acpi_cpufreq_init (void) +static int __init acpi_cpufreq_init(void) { dprintk("acpi_cpufreq_init\n"); - acpi_cpufreq_early_init_acpi(); + acpi_cpufreq_early_init(); return cpufreq_register_driver(&acpi_cpufreq_driver); } - -static void __exit -acpi_cpufreq_exit (void) +static void __exit acpi_cpufreq_exit(void) { - unsigned int i; + unsigned int i; dprintk("acpi_cpufreq_exit\n"); cpufreq_unregister_driver(&acpi_cpufreq_driver); @@ -627,7 +805,9 @@ acpi_cpufreq_exit (void) } module_param(acpi_pstate_strict, uint, 0644); -MODULE_PARM_DESC(acpi_pstate_strict, "value 0 or non-zero. non-zero -> strict ACPI checks are performed during frequency changes."); +MODULE_PARM_DESC(acpi_pstate_strict, + "value 0 or non-zero. non-zero -> strict ACPI checks are " + "performed during frequency changes."); late_initcall(acpi_cpufreq_init); module_exit(acpi_cpufreq_exit); diff --git a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c index 92afa3bc84f1..6667e9cceb9f 100644 --- a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c +++ b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c @@ -447,7 +447,6 @@ static int __init cpufreq_gx_init(void) int ret; struct gxfreq_params *params; struct pci_dev *gx_pci; - u32 class_rev; /* Test if we have the right hardware */ if ((gx_pci = gx_detect_chipset()) == NULL) @@ -472,8 +471,7 @@ static int __init cpufreq_gx_init(void) pci_read_config_byte(params->cs55x0, PCI_PMER2, &(params->pci_pmer2)); pci_read_config_byte(params->cs55x0, PCI_MODON, &(params->on_duration)); pci_read_config_byte(params->cs55x0, PCI_MODOFF, &(params->off_duration)); - pci_read_config_dword(params->cs55x0, PCI_CLASS_REVISION, &class_rev); - params->pci_rev = class_rev && 0xff; + pci_read_config_byte(params->cs55x0, PCI_REVISION_ID, ¶ms->pci_rev); if ((ret = cpufreq_register_driver(&gx_suspmod_driver))) { kfree(params); diff --git a/arch/i386/kernel/cpu/cpufreq/longhaul.c b/arch/i386/kernel/cpu/cpufreq/longhaul.c index 7233abe5d695..e940e00b96c9 100644 --- a/arch/i386/kernel/cpu/cpufreq/longhaul.c +++ b/arch/i386/kernel/cpu/cpufreq/longhaul.c @@ -52,6 +52,10 @@ #define CPU_EZRA_T 4 #define CPU_NEHEMIAH 5 +/* Flags */ +#define USE_ACPI_C3 (1 << 1) +#define USE_NORTHBRIDGE (1 << 2) + static int cpu_model; static unsigned int numscales=16; static unsigned int fsb; @@ -68,7 +72,7 @@ static unsigned int minmult, maxmult; static int can_scale_voltage; static struct acpi_processor *pr = NULL; static struct acpi_processor_cx *cx = NULL; -static int port22_en; +static u8 longhaul_flags; /* Module parameters */ static int scale_voltage; @@ -80,7 +84,6 @@ static int ignore_latency; /* Clock ratios multiplied by 10 */ static int clock_ratio[32]; static int eblcr_table[32]; -static unsigned int highest_speed, lowest_speed; /* kHz */ static int longhaul_version; static struct cpufreq_frequency_table *longhaul_table; @@ -178,7 +181,7 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index) safe_halt(); /* Change frequency on next halt or sleep */ wrmsrl(MSR_VIA_LONGHAUL, longhaul.val); - if (port22_en) { + if (!cx_address) { ACPI_FLUSH_CPU_CACHE(); /* Invoke C1 */ halt(); @@ -189,7 +192,6 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index) /* Dummy op - must do something useless after P_LVL3 read */ t = inl(acpi_fadt.xpm_tmr_blk.address); } - /* Disable bus ratio bit */ local_irq_disable(); longhaul.bits.RevisionKey = longhaul.bits.RevisionID; @@ -243,15 +245,14 @@ static void longhaul_setstate(unsigned int clock_ratio_index) outb(0xFF,0xA1); /* Overkill */ outb(0xFE,0x21); /* TMR0 only */ - if (pr->flags.bm_control) { + if (longhaul_flags & USE_NORTHBRIDGE) { + /* Disable AGP and PCI arbiters */ + outb(3, 0x22); + } else if ((pr != NULL) && pr->flags.bm_control) { /* Disable bus master arbitration */ acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1, ACPI_MTX_DO_NOT_LOCK); - } else if (port22_en) { - /* Disable AGP and PCI arbiters */ - outb(3, 0x22); } - switch (longhaul_version) { /* @@ -278,22 +279,25 @@ static void longhaul_setstate(unsigned int clock_ratio_index) * to work in practice. */ case TYPE_POWERSAVER: - /* Don't allow wakeup */ - acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0, - ACPI_MTX_DO_NOT_LOCK); - do_powersaver(cx->address, clock_ratio_index); + if (longhaul_flags & USE_ACPI_C3) { + /* Don't allow wakeup */ + acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0, + ACPI_MTX_DO_NOT_LOCK); + do_powersaver(cx->address, clock_ratio_index); + } else { + do_powersaver(0, clock_ratio_index); + } break; } - if (pr->flags.bm_control) { + if (longhaul_flags & USE_NORTHBRIDGE) { + /* Enable arbiters */ + outb(0, 0x22); + } else if ((pr != NULL) && pr->flags.bm_control) { /* Enable bus master arbitration */ acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0, ACPI_MTX_DO_NOT_LOCK); - } else if (port22_en) { - /* Enable arbiters */ - outb(0, 0x22); } - outb(pic2_mask,0xA1); /* restore mask */ outb(pic1_mask,0x21); @@ -314,12 +318,12 @@ static void longhaul_setstate(unsigned int clock_ratio_index) #define ROUNDING 0xf -static int _guess(int guess) +static int _guess(int guess, int mult) { int target; - target = ((maxmult/10)*guess); - if (maxmult%10 != 0) + target = ((mult/10)*guess); + if (mult%10 != 0) target += (guess/2); target += ROUNDING/2; target &= ~ROUNDING; @@ -327,17 +331,17 @@ static int _guess(int guess) } -static int guess_fsb(void) +static int guess_fsb(int mult) { int speed = (cpu_khz/1000); int i; - int speeds[3] = { 66, 100, 133 }; + int speeds[] = { 66, 100, 133, 200 }; speed += ROUNDING/2; speed &= ~ROUNDING; - for (i=0; i<3; i++) { - if (_guess(speeds[i]) == speed) + for (i=0; i<4; i++) { + if (_guess(speeds[i], mult) == speed) return speeds[i]; } return 0; @@ -354,9 +358,7 @@ static int __init longhaul_get_ranges(void) 130, 150, 160, 140, -1, 155, -1, 145 }; unsigned int j, k = 0; union msr_longhaul longhaul; - unsigned long lo, hi; - unsigned int eblcr_fsb_table_v1[] = { 66, 133, 100, -1 }; - unsigned int eblcr_fsb_table_v2[] = { 133, 100, -1, 66 }; + int mult = 0; switch (longhaul_version) { case TYPE_LONGHAUL_V1: @@ -364,30 +366,18 @@ static int __init longhaul_get_ranges(void) /* Ugh, Longhaul v1 didn't have the min/max MSRs. Assume min=3.0x & max = whatever we booted at. */ minmult = 30; - maxmult = longhaul_get_cpu_mult(); - rdmsr (MSR_IA32_EBL_CR_POWERON, lo, hi); - invalue = (lo & (1<<18|1<<19)) >>18; - if (cpu_model==CPU_SAMUEL || cpu_model==CPU_SAMUEL2) - fsb = eblcr_fsb_table_v1[invalue]; - else - fsb = guess_fsb(); + maxmult = mult = longhaul_get_cpu_mult(); break; case TYPE_POWERSAVER: /* Ezra-T */ if (cpu_model==CPU_EZRA_T) { + minmult = 30; rdmsrl (MSR_VIA_LONGHAUL, longhaul.val); invalue = longhaul.bits.MaxMHzBR; if (longhaul.bits.MaxMHzBR4) invalue += 16; - maxmult=ezra_t_multipliers[invalue]; - - invalue = longhaul.bits.MinMHzBR; - if (longhaul.bits.MinMHzBR4 == 1) - minmult = 30; - else - minmult = ezra_t_multipliers[invalue]; - fsb = eblcr_fsb_table_v2[longhaul.bits.MaxMHzFSB]; + maxmult = mult = ezra_t_multipliers[invalue]; break; } @@ -407,21 +397,16 @@ static int __init longhaul_get_ranges(void) * But it works, so we don't grumble. */ minmult=40; - maxmult=longhaul_get_cpu_mult(); - - /* Starting with the 1.2GHz parts, theres a 200MHz bus. */ - if ((cpu_khz/1000) > 1200) - fsb = 200; - else - fsb = eblcr_fsb_table_v2[longhaul.bits.MaxMHzFSB]; + maxmult = mult = longhaul_get_cpu_mult(); break; } } + fsb = guess_fsb(mult); dprintk ("MinMult:%d.%dx MaxMult:%d.%dx\n", minmult/10, minmult%10, maxmult/10, maxmult%10); - if (fsb == -1) { + if (fsb == 0) { printk (KERN_INFO PFX "Invalid (reserved) FSB!\n"); return -EINVAL; } @@ -583,6 +568,10 @@ static int enable_arbiter_disable(void) if (dev == NULL) { reg = 0x76; dev = pci_find_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); + } if (dev != NULL) { /* Enable access to port 0x22 */ @@ -687,27 +676,32 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) /* Find ACPI data for processor */ acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, ACPI_UINT32_MAX, &longhaul_walk_callback, NULL, (void *)&pr); - if (pr == NULL) - goto err_acpi; - if (longhaul_version == TYPE_POWERSAVER) { - /* Check ACPI support for C3 state */ + /* Check ACPI support for C3 state */ + if ((pr != NULL) && (longhaul_version == TYPE_POWERSAVER)) { cx = &pr->power.states[ACPI_STATE_C3]; if (cx->address > 0 && (cx->latency <= 1000 || ignore_latency != 0) ) { + longhaul_flags |= USE_ACPI_C3; goto print_support_type; } } + /* Check if northbridge is friendly */ + if (enable_arbiter_disable()) { + longhaul_flags |= USE_NORTHBRIDGE; + goto print_support_type; + } + + /* No ACPI C3 or we can't use it */ /* Check ACPI support for bus master arbiter disable */ - if (!pr->flags.bm_control) { - if (enable_arbiter_disable()) { - port22_en = 1; - } else { - goto err_acpi; - } + if ((pr == NULL) || !(pr->flags.bm_control)) { + printk(KERN_ERR PFX + "No ACPI support. Unsupported northbridge.\n"); + return -ENODEV; } + print_support_type: - if (!port22_en) { + if (!(longhaul_flags & USE_NORTHBRIDGE)) { printk (KERN_INFO PFX "Using ACPI support.\n"); } else { printk (KERN_INFO PFX "Using northbridge support.\n"); @@ -732,10 +726,6 @@ print_support_type: cpufreq_frequency_table_get_attr(longhaul_table, policy->cpu); return 0; - -err_acpi: - printk(KERN_ERR PFX "No ACPI support. No VT8601 or VT8623 northbridge. Aborting.\n"); - return -ENODEV; } static int __devexit longhaul_cpu_exit(struct cpufreq_policy *policy) @@ -770,8 +760,8 @@ static int __init longhaul_init(void) #ifdef CONFIG_SMP if (num_online_cpus() > 1) { - return -ENODEV; printk(KERN_ERR PFX "More than 1 CPU detected, longhaul disabled.\n"); + return -ENODEV; } #endif #ifdef CONFIG_X86_IO_APIC @@ -783,8 +773,10 @@ static int __init longhaul_init(void) switch (c->x86_model) { case 6 ... 9: return cpufreq_register_driver(&longhaul_driver); + case 10: + printk(KERN_ERR PFX "Use acpi-cpufreq driver for VIA C7\n"); default: - printk (KERN_INFO PFX "Unknown VIA CPU. Contact davej@codemonkey.org.uk\n"); + ;; } return -ENODEV; diff --git a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c index 304d2eaa4a1b..bec50170b75a 100644 --- a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c @@ -163,29 +163,27 @@ static int cpufreq_p4_verify(struct cpufreq_policy *policy) static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) { - if ((c->x86 == 0x06) && (c->x86_model == 0x09)) { - /* Pentium M (Banias) */ - printk(KERN_WARNING PFX "Warning: Pentium M detected. " - "The speedstep_centrino module offers voltage scaling" - " in addition of frequency scaling. You should use " - "that instead of p4-clockmod, if possible.\n"); - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PM); - } - - if ((c->x86 == 0x06) && (c->x86_model == 0x0D)) { - /* Pentium M (Dothan) */ - printk(KERN_WARNING PFX "Warning: Pentium M detected. " - "The speedstep_centrino module offers voltage scaling" - " in addition of frequency scaling. You should use " - "that instead of p4-clockmod, if possible.\n"); - /* on P-4s, the TSC runs with constant frequency independent whether - * throttling is active or not. */ - p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PM); + if (c->x86 == 0x06) { + if (cpu_has(c, X86_FEATURE_EST)) + printk(KERN_WARNING PFX "Warning: EST-capable CPU detected. " + "The acpi-cpufreq module offers voltage scaling" + " in addition of frequency scaling. You should use " + "that instead of p4-clockmod, if possible.\n"); + switch (c->x86_model) { + case 0x0E: /* Core */ + case 0x0F: /* Core Duo */ + p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; + return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PCORE); + case 0x0D: /* Pentium M (Dothan) */ + p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; + /* fall through */ + case 0x09: /* Pentium M (Banias) */ + return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PM); + } } if (c->x86 != 0xF) { - printk(KERN_WARNING PFX "Unknown p4-clockmod-capable CPU. Please send an e-mail to <linux@brodo.de>\n"); + printk(KERN_WARNING PFX "Unknown p4-clockmod-capable CPU. Please send an e-mail to <cpufreq@lists.linux.org.uk>\n"); return 0; } diff --git a/arch/i386/kernel/cpu/cpufreq/sc520_freq.c b/arch/i386/kernel/cpu/cpufreq/sc520_freq.c index ef457d50f4ac..b8fb4b521c62 100644 --- a/arch/i386/kernel/cpu/cpufreq/sc520_freq.c +++ b/arch/i386/kernel/cpu/cpufreq/sc520_freq.c @@ -153,6 +153,7 @@ static struct cpufreq_driver sc520_freq_driver = { static int __init sc520_freq_init(void) { struct cpuinfo_x86 *c = cpu_data; + int err; /* Test if we have the right hardware */ if(c->x86_vendor != X86_VENDOR_AMD || @@ -166,7 +167,11 @@ static int __init sc520_freq_init(void) return -ENOMEM; } - return cpufreq_register_driver(&sc520_freq_driver); + err = cpufreq_register_driver(&sc520_freq_driver); + if (err) + iounmap(cpuctl); + + return err; } diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c index e8993baf3d14..f43b987f952b 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c @@ -36,6 +36,7 @@ #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-centrino", msg) +#define INTEL_MSR_RANGE (0xffff) struct cpu_id { @@ -379,6 +380,7 @@ static int centrino_cpu_early_init_acpi(void) } +#ifdef CONFIG_SMP /* * Some BIOSes do SW_ANY coordination internally, either set it up in hw * or do it in BIOS firmware and won't inform about it to OS. If not @@ -392,7 +394,6 @@ static int sw_any_bug_found(struct dmi_system_id *d) return 0; } - static struct dmi_system_id sw_any_bug_dmi_table[] = { { .callback = sw_any_bug_found, @@ -405,7 +406,7 @@ static struct dmi_system_id sw_any_bug_dmi_table[] = { }, { } }; - +#endif /* * centrino_cpu_init_acpi - register with ACPI P-States library @@ -463,8 +464,9 @@ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) } for (i=0; i<p->state_count; i++) { - if (p->states[i].control != p->states[i].status) { - dprintk("Different control (%llu) and status values (%llu)\n", + if ((p->states[i].control & INTEL_MSR_RANGE) != + (p->states[i].status & INTEL_MSR_RANGE)) { + dprintk("Different MSR bits in control (%llu) and status (%llu)\n", p->states[i].control, p->states[i].status); result = -EINVAL; goto err_unreg; @@ -500,7 +502,7 @@ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) } for (i=0; i<p->state_count; i++) { - centrino_model[cpu]->op_points[i].index = p->states[i].control; + centrino_model[cpu]->op_points[i].index = p->states[i].control & INTEL_MSR_RANGE; centrino_model[cpu]->op_points[i].frequency = p->states[i].core_frequency * 1000; dprintk("adding state %i with frequency %u and control value %04x\n", i, centrino_model[cpu]->op_points[i].frequency, centrino_model[cpu]->op_points[i].index); @@ -531,6 +533,9 @@ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) /* notify BIOS that we exist */ acpi_processor_notify_smm(THIS_MODULE); + printk("speedstep-centrino with X86_SPEEDSTEP_CENTRINO_ACPI " + "config is deprecated.\n " + "Use X86_ACPI_CPUFREQ (acpi-cpufreq) instead.\n" ); return 0; diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c index 4f46cac155c4..d59277c00911 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c @@ -123,6 +123,36 @@ static unsigned int pentiumM_get_frequency(void) return (msr_tmp * 100 * 1000); } +static unsigned int pentium_core_get_frequency(void) +{ + u32 fsb = 0; + u32 msr_lo, msr_tmp; + + rdmsr(MSR_FSB_FREQ, msr_lo, msr_tmp); + /* see table B-2 of 25366920.pdf */ + switch (msr_lo & 0x07) { + case 5: + fsb = 100000; + break; + case 1: + fsb = 133333; + break; + case 3: + fsb = 166667; + break; + default: + printk(KERN_ERR "PCORE - MSR_FSB_FREQ undefined value"); + } + + rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp); + dprintk("PCORE - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp); + + msr_tmp = (msr_lo >> 22) & 0x1f; + dprintk("bits 22-26 are 0x%x, speed is %u\n", msr_tmp, (msr_tmp * fsb)); + + return (msr_tmp * fsb); +} + static unsigned int pentium4_get_frequency(void) { @@ -174,6 +204,8 @@ static unsigned int pentium4_get_frequency(void) unsigned int speedstep_get_processor_frequency(unsigned int processor) { switch (processor) { + case SPEEDSTEP_PROCESSOR_PCORE: + return pentium_core_get_frequency(); case SPEEDSTEP_PROCESSOR_PM: return pentiumM_get_frequency(); case SPEEDSTEP_PROCESSOR_P4D: diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h index b735429c50b4..b11bcc608cac 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h @@ -22,6 +22,7 @@ * the speedstep_get_processor_frequency() call. */ #define SPEEDSTEP_PROCESSOR_PM 0xFFFFFF03 /* Pentium M */ #define SPEEDSTEP_PROCESSOR_P4D 0xFFFFFF04 /* desktop P4 */ +#define SPEEDSTEP_PROCESSOR_PCORE 0xFFFFFF05 /* Core */ /* speedstep states -- only two of them */ diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c b/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c index c28333d53646..ff0d89806114 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c @@ -360,9 +360,6 @@ static int __init speedstep_init(void) case SPEEDSTEP_PROCESSOR_PIII_C: case SPEEDSTEP_PROCESSOR_PIII_C_EARLY: break; - case SPEEDSTEP_PROCESSOR_P4M: - printk(KERN_INFO "speedstep-smi: you're trying to use this cpufreq driver on a Pentium 4-based CPU. Most likely it will not work.\n"); - break; default: speedstep_processor = 0; } diff --git a/arch/i386/kernel/cpu/cyrix.c b/arch/i386/kernel/cpu/cyrix.c index c0c3b59de32c..abcff92f994c 100644 --- a/arch/i386/kernel/cpu/cyrix.c +++ b/arch/i386/kernel/cpu/cyrix.c @@ -173,7 +173,7 @@ static void __cpuinit geode_configure(void) ccr4 = getCx86(CX86_CCR4); ccr4 |= 0x38; /* FPU fast, DTE cache, Mem bypass */ - setCx86(CX86_CCR3, ccr3); + setCx86(CX86_CCR4, ccr4); set_cx86_memwb(); set_cx86_reorder(); diff --git a/arch/i386/kernel/cpu/intel.c b/arch/i386/kernel/cpu/intel.c index 94a95aa5227e..56fe26584957 100644 --- a/arch/i386/kernel/cpu/intel.c +++ b/arch/i386/kernel/cpu/intel.c @@ -107,7 +107,7 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) * Note that the workaround only should be initialized once... */ c->f00f_bug = 0; - if ( c->x86 == 5 ) { + if (!paravirt_enabled() && c->x86 == 5) { static int f00f_workaround_enabled = 0; c->f00f_bug = 1; @@ -195,8 +195,16 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) if ((c->x86 == 0xf && c->x86_model >= 0x03) || (c->x86 == 0x6 && c->x86_model >= 0x0e)) set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability); -} + if (cpu_has_ds) { + unsigned int l1; + rdmsr(MSR_IA32_MISC_ENABLE, l1, l2); + if (!(l1 & (1<<11))) + set_bit(X86_FEATURE_BTS, c->x86_capability); + if (!(l1 & (1<<12))) + set_bit(X86_FEATURE_PEBS, c->x86_capability); + } +} static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 * c, unsigned int size) { diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index 5c43be47587f..80b4c5d421b1 100644 --- a/arch/i386/kernel/cpu/intel_cacheinfo.c +++ b/arch/i386/kernel/cpu/intel_cacheinfo.c @@ -480,12 +480,10 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu) if (num_cache_leaves == 0) return -ENOENT; - cpuid4_info[cpu] = kmalloc( + cpuid4_info[cpu] = kzalloc( sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL); if (unlikely(cpuid4_info[cpu] == NULL)) return -ENOMEM; - memset(cpuid4_info[cpu], 0, - sizeof(struct _cpuid4_info) * num_cache_leaves); oldmask = current->cpus_allowed; retval = set_cpus_allowed(current, cpumask_of_cpu(cpu)); @@ -658,17 +656,14 @@ static int __cpuinit cpuid4_cache_sysfs_init(unsigned int cpu) return -ENOENT; /* Allocate all required memory */ - cache_kobject[cpu] = kmalloc(sizeof(struct kobject), GFP_KERNEL); + cache_kobject[cpu] = kzalloc(sizeof(struct kobject), GFP_KERNEL); if (unlikely(cache_kobject[cpu] == NULL)) goto err_out; - memset(cache_kobject[cpu], 0, sizeof(struct kobject)); - index_kobject[cpu] = kmalloc( + index_kobject[cpu] = kzalloc( sizeof(struct _index_kobject ) * num_cache_leaves, GFP_KERNEL); if (unlikely(index_kobject[cpu] == NULL)) goto err_out; - memset(index_kobject[cpu], 0, - sizeof(struct _index_kobject) * num_cache_leaves); return 0; diff --git a/arch/i386/kernel/cpu/mcheck/non-fatal.c b/arch/i386/kernel/cpu/mcheck/non-fatal.c index 1f9153ae5b03..6b5d3518a1c0 100644 --- a/arch/i386/kernel/cpu/mcheck/non-fatal.c +++ b/arch/i386/kernel/cpu/mcheck/non-fatal.c @@ -51,10 +51,10 @@ static void mce_checkregs (void *info) } } -static void mce_work_fn(void *data); -static DECLARE_WORK(mce_work, mce_work_fn, NULL); +static void mce_work_fn(struct work_struct *work); +static DECLARE_DELAYED_WORK(mce_work, mce_work_fn); -static void mce_work_fn(void *data) +static void mce_work_fn(struct work_struct *work) { on_each_cpu(mce_checkregs, NULL, 1, 1); schedule_delayed_work(&mce_work, MCE_RATE); diff --git a/arch/i386/kernel/cpu/mcheck/therm_throt.c b/arch/i386/kernel/cpu/mcheck/therm_throt.c index 2d8703b7ce65..065005c3f168 100644 --- a/arch/i386/kernel/cpu/mcheck/therm_throt.c +++ b/arch/i386/kernel/cpu/mcheck/therm_throt.c @@ -20,6 +20,7 @@ #include <linux/cpu.h> #include <asm/cpu.h> #include <linux/notifier.h> +#include <linux/jiffies.h> #include <asm/therm_throt.h> /* How long to wait between reporting thermal events */ @@ -115,7 +116,6 @@ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev) return sysfs_create_group(&sys_dev->kobj, &thermal_throttle_attr_group); } -#ifdef CONFIG_HOTPLUG_CPU static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev) { return sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group); @@ -152,7 +152,6 @@ static struct notifier_block thermal_throttle_cpu_notifier = { .notifier_call = thermal_throttle_cpu_callback, }; -#endif /* CONFIG_HOTPLUG_CPU */ static __init int thermal_throttle_init_device(void) { diff --git a/arch/i386/kernel/cpu/mtrr/Makefile b/arch/i386/kernel/cpu/mtrr/Makefile index a25b701ab84e..191fc0533649 100644 --- a/arch/i386/kernel/cpu/mtrr/Makefile +++ b/arch/i386/kernel/cpu/mtrr/Makefile @@ -1,5 +1,3 @@ obj-y := main.o if.o generic.o state.o -obj-y += amd.o -obj-y += cyrix.o -obj-y += centaur.o +obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o diff --git a/arch/i386/kernel/cpu/mtrr/amd.c b/arch/i386/kernel/cpu/mtrr/amd.c index 1a1e04b6fd00..0949cdbf848a 100644 --- a/arch/i386/kernel/cpu/mtrr/amd.c +++ b/arch/i386/kernel/cpu/mtrr/amd.c @@ -7,7 +7,7 @@ static void amd_get_mtrr(unsigned int reg, unsigned long *base, - unsigned int *size, mtrr_type * type) + unsigned long *size, mtrr_type * type) { unsigned long low, high; diff --git a/arch/i386/kernel/cpu/mtrr/centaur.c b/arch/i386/kernel/cpu/mtrr/centaur.c index 33f00ac314ef..cb9aa3a7a7ab 100644 --- a/arch/i386/kernel/cpu/mtrr/centaur.c +++ b/arch/i386/kernel/cpu/mtrr/centaur.c @@ -17,7 +17,7 @@ static u8 centaur_mcr_type; /* 0 for winchip, 1 for winchip2 */ */ static int -centaur_get_free_region(unsigned long base, unsigned long size) +centaur_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. <size> The size (in bytes) of the region. @@ -26,10 +26,11 @@ centaur_get_free_region(unsigned long base, unsigned long size) { int i, max; mtrr_type ltype; - unsigned long lbase; - unsigned int lsize; + unsigned long lbase, lsize; max = num_var_ranges; + if (replace_reg >= 0 && replace_reg < max) + return replace_reg; for (i = 0; i < max; ++i) { if (centaur_mcr_reserved & (1 << i)) continue; @@ -49,7 +50,7 @@ mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) static void centaur_get_mcr(unsigned int reg, unsigned long *base, - unsigned int *size, mtrr_type * type) + unsigned long *size, mtrr_type * type) { *base = centaur_mcr[reg].high >> PAGE_SHIFT; *size = -(centaur_mcr[reg].low & 0xfffff000) >> PAGE_SHIFT; diff --git a/arch/i386/kernel/cpu/mtrr/cyrix.c b/arch/i386/kernel/cpu/mtrr/cyrix.c index 9027a987006b..0737a596db43 100644 --- a/arch/i386/kernel/cpu/mtrr/cyrix.c +++ b/arch/i386/kernel/cpu/mtrr/cyrix.c @@ -9,7 +9,7 @@ int arr3_protected; static void cyrix_get_arr(unsigned int reg, unsigned long *base, - unsigned int *size, mtrr_type * type) + unsigned long *size, mtrr_type * type) { unsigned long flags; unsigned char arr, ccr3, rcr, shift; @@ -77,7 +77,7 @@ cyrix_get_arr(unsigned int reg, unsigned long *base, } static int -cyrix_get_free_region(unsigned long base, unsigned long size) +cyrix_get_free_region(unsigned long base, unsigned long size, int replace_reg) /* [SUMMARY] Get a free ARR. <base> The starting (base) address of the region. <size> The size (in bytes) of the region. @@ -86,9 +86,24 @@ cyrix_get_free_region(unsigned long base, unsigned long size) { int i; mtrr_type ltype; - unsigned long lbase; - unsigned int lsize; + unsigned long lbase, lsize; + switch (replace_reg) { + case 7: + if (size < 0x40) + break; + case 6: + case 5: + case 4: + return replace_reg; + case 3: + if (arr3_protected) + break; + case 2: + case 1: + case 0: + return replace_reg; + } /* If we are to set up a region >32M then look at ARR7 immediately */ if (size > 0x2000) { cyrix_get_arr(7, &lbase, &lsize, <ype); @@ -214,7 +229,7 @@ static void cyrix_set_arr(unsigned int reg, unsigned long base, typedef struct { unsigned long base; - unsigned int size; + unsigned long size; mtrr_type type; } arr_state_t; diff --git a/arch/i386/kernel/cpu/mtrr/generic.c b/arch/i386/kernel/cpu/mtrr/generic.c index 0b61eed8bbd8..f77fc53db654 100644 --- a/arch/i386/kernel/cpu/mtrr/generic.c +++ b/arch/i386/kernel/cpu/mtrr/generic.c @@ -3,6 +3,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/mm.h> +#include <linux/module.h> #include <asm/io.h> #include <asm/mtrr.h> #include <asm/msr.h> @@ -15,12 +16,19 @@ struct mtrr_state { struct mtrr_var_range *var_ranges; mtrr_type fixed_ranges[NUM_FIXED_RANGES]; unsigned char enabled; + unsigned char have_fixed; mtrr_type def_type; }; 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; +module_param_named(show, mtrr_show, bool, 0); + /* Get the MSR pair relating to a var range */ static void __init get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr) @@ -43,6 +51,14 @@ 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) +{ + 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)); +} + /* Grab all of the MTRR state for this CPU into *state */ void __init get_mtrr_state(void) { @@ -58,13 +74,49 @@ void __init get_mtrr_state(void) } vrs = mtrr_state.var_ranges; + rdmsr(MTRRcap_MSR, lo, dummy); + mtrr_state.have_fixed = (lo >> 8) & 1; + for (i = 0; i < num_var_ranges; i++) get_mtrr_var_range(i, &vrs[i]); - get_fixed_ranges(mtrr_state.fixed_ranges); + if (mtrr_state.have_fixed) + get_fixed_ranges(mtrr_state.fixed_ranges); rdmsr(MTRRdefType_MSR, lo, dummy); mtrr_state.def_type = (lo & 0xff); mtrr_state.enabled = (lo & 0xc00) >> 10; + + if (mtrr_show) { + int high_width; + + printk(KERN_INFO "MTRR default type: %s\n", mtrr_attrib_to_str(mtrr_state.def_type)); + if (mtrr_state.have_fixed) { + printk(KERN_INFO "MTRR fixed ranges %sabled:\n", + mtrr_state.enabled & 1 ? "en" : "dis"); + print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0); + for (i = 0; i < 2; ++i) + print_fixed(0x80000 + i * 0x20000, 0x04000, mtrr_state.fixed_ranges + (i + 1) * 8); + for (i = 0; i < 8; ++i) + print_fixed(0xC0000 + i * 0x08000, 0x01000, mtrr_state.fixed_ranges + (i + 3) * 8); + } + printk(KERN_INFO "MTRR variable ranges %sabled:\n", + mtrr_state.enabled & 2 ? "en" : "dis"); + high_width = ((size_or_mask ? ffs(size_or_mask) - 1 : 32) - (32 - PAGE_SHIFT) + 3) / 4; + for (i = 0; i < num_var_ranges; ++i) { + if (mtrr_state.var_ranges[i].mask_lo & (1 << 11)) + printk(KERN_INFO "MTRR %u base %0*X%05X000 mask %0*X%05X000 %s\n", + i, + high_width, + mtrr_state.var_ranges[i].base_hi, + mtrr_state.var_ranges[i].base_lo >> 12, + high_width, + mtrr_state.var_ranges[i].mask_hi, + mtrr_state.var_ranges[i].mask_lo >> 12, + mtrr_attrib_to_str(mtrr_state.var_ranges[i].base_lo & 0xff)); + else + printk(KERN_INFO "MTRR %u disabled\n", i); + } + } } /* Some BIOS's are fucked and don't set all MTRRs the same! */ @@ -95,7 +147,7 @@ void mtrr_wrmsr(unsigned msr, unsigned a, unsigned b) smp_processor_id(), msr, a, b); } -int generic_get_free_region(unsigned long base, unsigned long size) +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. <size> The size (in bytes) of the region. @@ -104,10 +156,11 @@ int generic_get_free_region(unsigned long base, unsigned long size) { int i, max; mtrr_type ltype; - unsigned long lbase; - unsigned lsize; + unsigned long lbase, lsize; max = num_var_ranges; + if (replace_reg >= 0 && replace_reg < max) + return replace_reg; for (i = 0; i < max; ++i) { mtrr_if->get(i, &lbase, &lsize, <ype); if (lsize == 0) @@ -117,7 +170,7 @@ int generic_get_free_region(unsigned long base, unsigned long size) } static void generic_get_mtrr(unsigned int reg, unsigned long *base, - unsigned int *size, mtrr_type * type) + unsigned long *size, mtrr_type *type) { unsigned int mask_lo, mask_hi, base_lo, base_hi; @@ -202,7 +255,9 @@ static int set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr) return changed; } -static unsigned long set_mtrr_state(u32 deftype_lo, u32 deftype_hi) +static u32 deftype_lo, deftype_hi; + +static unsigned long set_mtrr_state(void) /* [SUMMARY] Set the MTRR state for this CPU. <state> The MTRR state information to read. <ctxt> Some relevant CPU context. @@ -217,14 +272,14 @@ static unsigned long set_mtrr_state(u32 deftype_lo, u32 deftype_hi) if (set_mtrr_var_ranges(i, &mtrr_state.var_ranges[i])) change_mask |= MTRR_CHANGE_MASK_VARIABLE; - if (set_fixed_ranges(mtrr_state.fixed_ranges)) + if (mtrr_state.have_fixed && set_fixed_ranges(mtrr_state.fixed_ranges)) change_mask |= MTRR_CHANGE_MASK_FIXED; /* Set_mtrr_restore restores the old value of MTRRdefType, so to set it we fiddle with the saved value */ if ((deftype_lo & 0xff) != mtrr_state.def_type || ((deftype_lo & 0xc00) >> 10) != mtrr_state.enabled) { - deftype_lo |= (mtrr_state.def_type | mtrr_state.enabled << 10); + deftype_lo = (deftype_lo & ~0xcff) | mtrr_state.def_type | (mtrr_state.enabled << 10); change_mask |= MTRR_CHANGE_MASK_DEFTYPE; } @@ -233,7 +288,6 @@ static unsigned long set_mtrr_state(u32 deftype_lo, u32 deftype_hi) static unsigned long cr4 = 0; -static u32 deftype_lo, deftype_hi; static DEFINE_SPINLOCK(set_atomicity_lock); /* @@ -271,7 +325,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) rdmsr(MTRRdefType_MSR, deftype_lo, deftype_hi); /* Disable MTRRs, and set the default type to uncached */ - mtrr_wrmsr(MTRRdefType_MSR, deftype_lo & 0xf300UL, deftype_hi); + mtrr_wrmsr(MTRRdefType_MSR, deftype_lo & ~0xcff, deftype_hi); } static void post_set(void) __releases(set_atomicity_lock) @@ -300,7 +354,7 @@ static void generic_set_all(void) prepare_set(); /* Actually set the state */ - mask = set_mtrr_state(deftype_lo,deftype_hi); + mask = set_mtrr_state(); post_set(); local_irq_restore(flags); @@ -366,7 +420,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, unsigned i printk(KERN_WARNING "mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); return -EINVAL; } - if (!(base + size < 0x70000000 || base > 0x7003FFFF) && + if (!(base + size < 0x70000 || base > 0x7003F) && (type == MTRR_TYPE_WRCOMB || type == MTRR_TYPE_WRBACK)) { printk(KERN_WARNING "mtrr: writable mtrr between 0x70000000 and 0x7003FFFF may hang the CPU.\n"); diff --git a/arch/i386/kernel/cpu/mtrr/if.c b/arch/i386/kernel/cpu/mtrr/if.c index 5ac051bb9d55..5ae1705eafa6 100644 --- a/arch/i386/kernel/cpu/mtrr/if.c +++ b/arch/i386/kernel/cpu/mtrr/if.c @@ -17,7 +17,7 @@ extern unsigned int *usage_table; #define FILE_FCOUNT(f) (((struct seq_file *)((f)->private_data))->private) -static char *mtrr_strings[MTRR_NUM_TYPES] = +static const char *const mtrr_strings[MTRR_NUM_TYPES] = { "uncachable", /* 0 */ "write-combining", /* 1 */ @@ -28,7 +28,7 @@ static char *mtrr_strings[MTRR_NUM_TYPES] = "write-back", /* 6 */ }; -char *mtrr_attrib_to_str(int x) +const char *mtrr_attrib_to_str(int x) { return (x <= 6) ? mtrr_strings[x] : "?"; } @@ -44,10 +44,9 @@ mtrr_file_add(unsigned long base, unsigned long size, max = num_var_ranges; if (fcount == NULL) { - fcount = kmalloc(max * sizeof *fcount, GFP_KERNEL); + fcount = kzalloc(max * sizeof *fcount, GFP_KERNEL); if (!fcount) return -ENOMEM; - memset(fcount, 0, max * sizeof *fcount); FILE_FCOUNT(file) = fcount; } if (!page) { @@ -155,6 +154,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) { int err = 0; mtrr_type type; + unsigned long size; struct mtrr_sentry sentry; struct mtrr_gentry gentry; void __user *arg = (void __user *) __arg; @@ -235,15 +235,15 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) case MTRRIOC_GET_ENTRY: if (gentry.regnum >= num_var_ranges) return -EINVAL; - mtrr_if->get(gentry.regnum, &gentry.base, &gentry.size, &type); + mtrr_if->get(gentry.regnum, &gentry.base, &size, &type); /* Hide entries that go above 4GB */ - if (gentry.base + gentry.size > 0x100000 - || gentry.size == 0x100000) + if (gentry.base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT)) + || size >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))) gentry.base = gentry.size = gentry.type = 0; else { gentry.base <<= PAGE_SHIFT; - gentry.size <<= PAGE_SHIFT; + gentry.size = size << PAGE_SHIFT; gentry.type = type; } @@ -273,8 +273,14 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) case MTRRIOC_GET_PAGE_ENTRY: if (gentry.regnum >= num_var_ranges) return -EINVAL; - mtrr_if->get(gentry.regnum, &gentry.base, &gentry.size, &type); - gentry.type = type; + mtrr_if->get(gentry.regnum, &gentry.base, &size, &type); + /* Hide entries that would overflow */ + if (size != (__typeof__(gentry.size))size) + gentry.base = gentry.size = gentry.type = 0; + else { + gentry.size = size; + gentry.type = type; + } break; } @@ -353,8 +359,7 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset) char factor; int i, max, len; mtrr_type type; - unsigned long base; - unsigned int size; + unsigned long base, size; len = 0; max = num_var_ranges; @@ -373,7 +378,7 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset) } /* RED-PEN: base can be > 32bit */ len += seq_printf(seq, - "reg%02i: base=0x%05lx000 (%4liMB), size=%4i%cB: %s, count=%d\n", + "reg%02i: base=0x%05lx000 (%4luMB), size=%4lu%cB: %s, count=%d\n", i, base, base >> (20 - PAGE_SHIFT), size, factor, mtrr_attrib_to_str(type), usage_table[i]); } diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c index fff90bda4733..16bb7ea87145 100644 --- a/arch/i386/kernel/cpu/mtrr/main.c +++ b/arch/i386/kernel/cpu/mtrr/main.c @@ -59,7 +59,11 @@ struct mtrr_ops * mtrr_if = NULL; static void set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type); +#ifndef CONFIG_X86_64 extern int arr3_protected; +#else +#define arr3_protected 0 +#endif void set_mtrr_ops(struct mtrr_ops * ops) { @@ -168,6 +172,13 @@ static void ipi_handler(void *info) #endif +static inline int types_compatible(mtrr_type type1, mtrr_type type2) { + return type1 == MTRR_TYPE_UNCACHABLE || + type2 == MTRR_TYPE_UNCACHABLE || + (type1 == MTRR_TYPE_WRTHROUGH && type2 == MTRR_TYPE_WRBACK) || + (type1 == MTRR_TYPE_WRBACK && type2 == MTRR_TYPE_WRTHROUGH); +} + /** * set_mtrr - update mtrrs on all processors * @reg: mtrr in question @@ -263,8 +274,8 @@ static void set_mtrr(unsigned int reg, unsigned long base, /** * mtrr_add_page - Add a memory type region - * @base: Physical base address of region in pages (4 KB) - * @size: Physical size of region in pages (4 KB) + * @base: Physical base address of region in pages (in units of 4 kB!) + * @size: Physical size of region in pages (4 kB) * @type: Type of MTRR desired * @increment: If this is true do usage counting on the region * @@ -300,11 +311,9 @@ static void set_mtrr(unsigned int reg, unsigned long base, int mtrr_add_page(unsigned long base, unsigned long size, unsigned int type, char increment) { - int i; + int i, replace, error; mtrr_type ltype; - unsigned long lbase; - unsigned int lsize; - int error; + unsigned long lbase, lsize; if (!mtrr_if) return -ENXIO; @@ -324,12 +333,18 @@ int mtrr_add_page(unsigned long base, unsigned long size, return -ENOSYS; } + if (!size) { + printk(KERN_WARNING "mtrr: zero sized request\n"); + return -EINVAL; + } + if (base & size_or_mask || size & size_or_mask) { printk(KERN_WARNING "mtrr: base or size exceeds the MTRR width\n"); return -EINVAL; } error = -EINVAL; + replace = -1; /* No CPU hotplug when we change MTRR entries */ lock_cpu_hotplug(); @@ -337,21 +352,28 @@ int mtrr_add_page(unsigned long base, unsigned long size, mutex_lock(&mtrr_mutex); for (i = 0; i < num_var_ranges; ++i) { mtrr_if->get(i, &lbase, &lsize, <ype); - if (base >= lbase + lsize) - continue; - if ((base < lbase) && (base + size <= lbase)) + if (!lsize || base > lbase + lsize - 1 || base + size - 1 < lbase) continue; /* At this point we know there is some kind of overlap/enclosure */ - if ((base < lbase) || (base + size > lbase + lsize)) { + if (base < lbase || base + size - 1 > lbase + lsize - 1) { + if (base <= lbase && base + size - 1 >= lbase + lsize - 1) { + /* New region encloses an existing region */ + if (type == ltype) { + replace = replace == -1 ? i : -2; + continue; + } + else if (types_compatible(type, ltype)) + continue; + } printk(KERN_WARNING "mtrr: 0x%lx000,0x%lx000 overlaps existing" - " 0x%lx000,0x%x000\n", base, size, lbase, + " 0x%lx000,0x%lx000\n", base, size, lbase, lsize); goto out; } /* New region is enclosed by an existing region */ if (ltype != type) { - if (type == MTRR_TYPE_UNCACHABLE) + if (types_compatible(type, ltype)) continue; printk (KERN_WARNING "mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n", base, size, mtrr_attrib_to_str(ltype), @@ -364,10 +386,18 @@ int mtrr_add_page(unsigned long base, unsigned long size, goto out; } /* Search for an empty MTRR */ - i = mtrr_if->get_free_region(base, size); + i = mtrr_if->get_free_region(base, size, replace); if (i >= 0) { set_mtrr(i, base, size, type); - usage_table[i] = 1; + if (likely(replace < 0)) + usage_table[i] = 1; + else { + usage_table[i] = usage_table[replace] + !!increment; + if (unlikely(replace != i)) { + set_mtrr(replace, 0, 0, 0); + usage_table[replace] = 0; + } + } } else printk(KERN_INFO "mtrr: no more MTRRs available\n"); error = i; @@ -455,8 +485,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) { int i, max; mtrr_type ltype; - unsigned long lbase; - unsigned int lsize; + unsigned long lbase, lsize; int error = -EINVAL; if (!mtrr_if) @@ -544,9 +573,11 @@ extern void centaur_init_mtrr(void); static void __init init_ifs(void) { +#ifndef CONFIG_X86_64 amd_init_mtrr(); cyrix_init_mtrr(); centaur_init_mtrr(); +#endif } /* The suspend/resume methods are only for CPU without MTRR. CPU using generic @@ -555,7 +586,7 @@ static void __init init_ifs(void) struct mtrr_value { mtrr_type ltype; unsigned long lbase; - unsigned int lsize; + unsigned long lsize; }; static struct mtrr_value * mtrr_state; @@ -565,10 +596,8 @@ static int mtrr_save(struct sys_device * sysdev, pm_message_t state) int i; int size = num_var_ranges * sizeof(struct mtrr_value); - mtrr_state = kmalloc(size,GFP_ATOMIC); - if (mtrr_state) - memset(mtrr_state,0,size); - else + mtrr_state = kzalloc(size,GFP_ATOMIC); + if (!mtrr_state) return -ENOMEM; for (i = 0; i < num_var_ranges; i++) { diff --git a/arch/i386/kernel/cpu/mtrr/mtrr.h b/arch/i386/kernel/cpu/mtrr/mtrr.h index 99c9f2682041..d61ea9db6cfe 100644 --- a/arch/i386/kernel/cpu/mtrr/mtrr.h +++ b/arch/i386/kernel/cpu/mtrr/mtrr.h @@ -43,15 +43,16 @@ struct mtrr_ops { void (*set_all)(void); void (*get)(unsigned int reg, unsigned long *base, - unsigned int *size, mtrr_type * type); - int (*get_free_region) (unsigned long base, unsigned long size); - + unsigned long *size, mtrr_type * type); + int (*get_free_region)(unsigned long base, unsigned long size, + int replace_reg); int (*validate_add_page)(unsigned long base, unsigned long size, unsigned int type); int (*have_wrcomb)(void); }; -extern int generic_get_free_region(unsigned long base, unsigned long size); +extern int generic_get_free_region(unsigned long base, unsigned long size, + int replace_reg); extern int generic_validate_add_page(unsigned long base, unsigned long size, unsigned int type); @@ -62,17 +63,17 @@ extern int positive_have_wrcomb(void); /* library functions for processor-specific routines */ struct set_mtrr_context { unsigned long flags; - unsigned long deftype_lo; - unsigned long deftype_hi; unsigned long cr4val; - unsigned long ccr3; + u32 deftype_lo; + u32 deftype_hi; + u32 ccr3; }; struct mtrr_var_range { - unsigned long base_lo; - unsigned long base_hi; - unsigned long mask_lo; - unsigned long mask_hi; + u32 base_lo; + u32 base_hi; + u32 mask_lo; + u32 mask_hi; }; void set_mtrr_done(struct set_mtrr_context *ctxt); @@ -92,6 +93,6 @@ extern struct mtrr_ops * mtrr_if; extern unsigned int num_var_ranges; void mtrr_state_warn(void); -char *mtrr_attrib_to_str(int x); +const char *mtrr_attrib_to_str(int x); void mtrr_wrmsr(unsigned, unsigned, unsigned); diff --git a/arch/i386/kernel/cpu/proc.c b/arch/i386/kernel/cpu/proc.c index 76aac088a323..6624d8583c42 100644 --- a/arch/i386/kernel/cpu/proc.c +++ b/arch/i386/kernel/cpu/proc.c @@ -152,9 +152,10 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, " [%d]", i); } - seq_printf(m, "\nbogomips\t: %lu.%02lu\n\n", + seq_printf(m, "\nbogomips\t: %lu.%02lu\n", c->loops_per_jiffy/(500000/HZ), (c->loops_per_jiffy/(5000/HZ)) % 100); + seq_printf(m, "clflush size\t: %u\n\n", c->x86_clflush_size); return 0; } |