diff options
Diffstat (limited to 'arch/i386')
38 files changed, 391 insertions, 325 deletions
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index bac0da731ee3..6004bb0795e0 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -699,7 +699,7 @@ depends on PM && !X86_VISWS config APM tristate "APM (Advanced Power Management) BIOS support" - depends on PM + depends on PM && PM_LEGACY ---help--- APM is a BIOS specification for saving power using several different techniques. This is mostly useful for battery powered laptops with @@ -997,8 +997,21 @@ source "drivers/Kconfig" source "fs/Kconfig" +menu "Instrumentation Support" + depends on EXPERIMENTAL + source "arch/i386/oprofile/Kconfig" +config KPROBES + bool "Kprobes (EXPERIMENTAL)" + help + Kprobes allows you to trap at almost any kernel address and + execute a callback function. register_kprobe() establishes + a probepoint and specifies the callback. Kprobes is useful + for kernel debugging, non-intrusive instrumentation and testing. + If in doubt, say "N". +endmenu + source "arch/i386/Kconfig.debug" source "security/Kconfig" diff --git a/arch/i386/Kconfig.debug b/arch/i386/Kconfig.debug index 5228c40a6fb2..c48b424dd640 100644 --- a/arch/i386/Kconfig.debug +++ b/arch/i386/Kconfig.debug @@ -22,16 +22,6 @@ config DEBUG_STACKOVERFLOW This option will cause messages to be printed if free stack space drops below a certain limit. -config KPROBES - bool "Kprobes" - depends on DEBUG_KERNEL - help - Kprobes allows you to trap at almost any kernel address and - execute a callback function. register_kprobe() establishes - a probepoint and specifies the callback. Kprobes is useful - for kernel debugging, non-intrusive instrumentation and testing. - If in doubt, say "N". - config DEBUG_STACK_USAGE bool "Stack utilization instrumentation" depends on DEBUG_KERNEL diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index b66c13c0cc0f..f36677241ecd 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -39,17 +39,14 @@ #ifdef CONFIG_X86_64 -static inline void acpi_madt_oem_check(char *oem_id, char *oem_table_id) -{ -} extern void __init clustered_apic_check(void); -static inline int ioapic_setup_disabled(void) -{ - return 0; -} +extern int gsi_irq_sharing(int gsi); #include <asm/proto.h> +static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) { return 0; } + + #else /* X86 */ #ifdef CONFIG_X86_LOCAL_APIC @@ -57,6 +54,8 @@ static inline int ioapic_setup_disabled(void) #include <mach_mpparse.h> #endif /* CONFIG_X86_LOCAL_APIC */ +static inline int gsi_irq_sharing(int gsi) { return gsi; } + #endif /* X86 */ #define BAD_MADT_ENTRY(entry, end) ( \ @@ -459,7 +458,7 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) *irq = IO_APIC_VECTOR(gsi); else #endif - *irq = gsi; + *irq = gsi_irq_sharing(gsi); return 0; } @@ -543,7 +542,7 @@ acpi_scan_rsdp(unsigned long start, unsigned long length) * RSDP signature. */ for (offset = 0; offset < length; offset += 16) { - if (strncmp((char *)(start + offset), "RSD PTR ", sig_len)) + if (strncmp((char *)(phys_to_virt(start) + offset), "RSD PTR ", sig_len)) continue; return (start + offset); } diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index 7c724ffa08bb..496a2c9909fe 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -559,14 +559,20 @@ void __devinit setup_local_APIC(void) * If Linux enabled the LAPIC against the BIOS default * disable it down before re-entering the BIOS on shutdown. * Otherwise the BIOS may get confused and not power-off. + * Additionally clear all LVT entries before disable_local_APIC + * for the case where Linux didn't enable the LAPIC. */ void lapic_shutdown(void) { - if (!cpu_has_apic || !enabled_via_apicbase) + if (!cpu_has_apic) return; local_irq_disable(); - disable_local_APIC(); + clear_local_APIC(); + + if (enabled_via_apicbase) + disable_local_APIC(); + local_irq_enable(); } diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c index d2ef0c2aa93e..1e60acbed3c1 100644 --- a/arch/i386/kernel/apm.c +++ b/arch/i386/kernel/apm.c @@ -218,6 +218,7 @@ #include <linux/time.h> #include <linux/sched.h> #include <linux/pm.h> +#include <linux/pm_legacy.h> #include <linux/device.h> #include <linux/kernel.h> #include <linux/smp.h> @@ -447,8 +448,7 @@ static char * apm_event_name[] = { "system standby resume", "capabilities change" }; -#define NR_APM_EVENT_NAME \ - (sizeof(apm_event_name) / sizeof(apm_event_name[0])) +#define NR_APM_EVENT_NAME ARRAY_SIZE(apm_event_name) typedef struct lookup_t { int key; @@ -479,7 +479,7 @@ static const lookup_t error_table[] = { { APM_NO_ERROR, "BIOS did not set a return code" }, { APM_NOT_PRESENT, "No APM present" } }; -#define ERROR_COUNT (sizeof(error_table)/sizeof(lookup_t)) +#define ERROR_COUNT ARRAY_SIZE(error_table) /** * apm_error - display an APM error @@ -770,8 +770,26 @@ static int set_system_power_state(u_short state) static int apm_do_idle(void) { u32 eax; + u8 ret = 0; + int idled = 0; + int polling; + + polling = test_thread_flag(TIF_POLLING_NRFLAG); + if (polling) { + clear_thread_flag(TIF_POLLING_NRFLAG); + smp_mb__after_clear_bit(); + } + if (!need_resched()) { + idled = 1; + ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax); + } + if (polling) + set_thread_flag(TIF_POLLING_NRFLAG); + + if (!idled) + return 0; - if (apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax)) { + if (ret) { static unsigned long t; /* This always fails on some SMP boards running UP kernels. diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c index 53a1681cd964..e344ef88cfcd 100644 --- a/arch/i386/kernel/cpu/amd.c +++ b/arch/i386/kernel/cpu/amd.c @@ -206,9 +206,9 @@ static void __init init_amd(struct cpuinfo_x86 *c) display_cacheinfo(c); if (cpuid_eax(0x80000000) >= 0x80000008) { - c->x86_num_cores = (cpuid_ecx(0x80000008) & 0xff) + 1; - if (c->x86_num_cores & (c->x86_num_cores - 1)) - c->x86_num_cores = 1; + c->x86_max_cores = (cpuid_ecx(0x80000008) & 0xff) + 1; + if (c->x86_max_cores & (c->x86_max_cores - 1)) + c->x86_max_cores = 1; } #ifdef CONFIG_X86_HT @@ -217,15 +217,15 @@ static void __init init_amd(struct cpuinfo_x86 *c) * distingush the cores. Assumes number of cores is a power * of two. */ - if (c->x86_num_cores > 1) { + if (c->x86_max_cores > 1) { int cpu = smp_processor_id(); unsigned bits = 0; - while ((1 << bits) < c->x86_num_cores) + while ((1 << bits) < c->x86_max_cores) bits++; cpu_core_id[cpu] = phys_proc_id[cpu] & ((1<<bits)-1); phys_proc_id[cpu] >>= bits; printk(KERN_INFO "CPU %d(%d) -> Core %d\n", - cpu, c->x86_num_cores, cpu_core_id[cpu]); + cpu, c->x86_max_cores, cpu_core_id[cpu]); } #endif } diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index 74145a33cb0f..31e344b26bae 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -30,8 +30,6 @@ static int disable_x86_serial_nr __devinitdata = 1; struct cpu_dev * cpu_devs[X86_VENDOR_NUM] = {}; -extern void mcheck_init(struct cpuinfo_x86 *c); - extern int disable_pse; static void default_init(struct cpuinfo_x86 * c) @@ -233,10 +231,10 @@ static void __init early_cpu_detect(void) cpuid(0x00000001, &tfms, &misc, &junk, &cap0); c->x86 = (tfms >> 8) & 15; c->x86_model = (tfms >> 4) & 15; - if (c->x86 == 0xf) { + if (c->x86 == 0xf) c->x86 += (tfms >> 20) & 0xff; + if (c->x86 >= 0x6) c->x86_model += ((tfms >> 16) & 0xF) << 4; - } c->x86_mask = tfms & 15; if (cap0 & (1<<19)) c->x86_cache_alignment = ((misc >> 8) & 0xff) * 8; @@ -335,7 +333,7 @@ void __devinit identify_cpu(struct cpuinfo_x86 *c) c->x86_model = c->x86_mask = 0; /* So far unknown... */ c->x86_vendor_id[0] = '\0'; /* Unset */ c->x86_model_id[0] = '\0'; /* Unset */ - c->x86_num_cores = 1; + c->x86_max_cores = 1; memset(&c->x86_capability, 0, sizeof c->x86_capability); if (!have_cpuid_p()) { @@ -429,9 +427,8 @@ void __devinit identify_cpu(struct cpuinfo_x86 *c) } /* Init Machine Check Exception if available. */ -#ifdef CONFIG_X86_MCE mcheck_init(c); -#endif + if (c == &boot_cpu_data) sysenter_setup(); enable_sep_cpu(); @@ -446,52 +443,44 @@ void __devinit identify_cpu(struct cpuinfo_x86 *c) void __devinit detect_ht(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; - int index_msb, tmp; + int index_msb, core_bits; int cpu = smp_processor_id(); + cpuid(1, &eax, &ebx, &ecx, &edx); + + c->apicid = phys_pkg_id((ebx >> 24) & 0xFF, 0); + if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY)) return; - cpuid(1, &eax, &ebx, &ecx, &edx); smp_num_siblings = (ebx & 0xff0000) >> 16; if (smp_num_siblings == 1) { printk(KERN_INFO "CPU: Hyper-Threading is disabled\n"); } else if (smp_num_siblings > 1 ) { - index_msb = 31; if (smp_num_siblings > NR_CPUS) { printk(KERN_WARNING "CPU: Unsupported number of the siblings %d", smp_num_siblings); smp_num_siblings = 1; return; } - tmp = smp_num_siblings; - while ((tmp & 0x80000000 ) == 0) { - tmp <<=1 ; - index_msb--; - } - if (smp_num_siblings & (smp_num_siblings - 1)) - index_msb++; + + index_msb = get_count_order(smp_num_siblings); phys_proc_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb); printk(KERN_INFO "CPU: Physical Processor ID: %d\n", phys_proc_id[cpu]); - smp_num_siblings = smp_num_siblings / c->x86_num_cores; + smp_num_siblings = smp_num_siblings / c->x86_max_cores; - tmp = smp_num_siblings; - index_msb = 31; - while ((tmp & 0x80000000) == 0) { - tmp <<=1 ; - index_msb--; - } + index_msb = get_count_order(smp_num_siblings) ; - if (smp_num_siblings & (smp_num_siblings - 1)) - index_msb++; + core_bits = get_count_order(c->x86_max_cores); - cpu_core_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb); + cpu_core_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb) & + ((1 << core_bits) - 1); - if (c->x86_num_cores > 1) + if (c->x86_max_cores > 1) printk(KERN_INFO "CPU: Processor Core ID: %d\n", cpu_core_id[cpu]); } diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c index caa9f7711343..871366b83b3f 100644 --- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -377,10 +377,9 @@ acpi_cpufreq_cpu_init ( arg0.buffer.length = 12; arg0.buffer.pointer = (u8 *) arg0_buf; - data = kmalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL); + data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL); if (!data) return (-ENOMEM); - memset(data, 0, sizeof(struct cpufreq_acpi_io)); acpi_io_data[cpu] = data; diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k7.c b/arch/i386/kernel/cpu/cpufreq/powernow-k7.c index 73a5dc5b26b8..edcd626001da 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k7.c +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k7.c @@ -171,10 +171,9 @@ static int get_ranges (unsigned char *pst) unsigned int speed; u8 fid, vid; - powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table) * (number_scales + 1)), GFP_KERNEL); + powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) * (number_scales + 1)), GFP_KERNEL); if (!powernow_table) return -ENOMEM; - memset(powernow_table, 0, (sizeof(struct cpufreq_frequency_table) * (number_scales + 1))); for (j=0 ; j < number_scales; j++) { fid = *pst++; @@ -305,16 +304,13 @@ static int powernow_acpi_init(void) goto err0; } - acpi_processor_perf = kmalloc(sizeof(struct acpi_processor_performance), + acpi_processor_perf = kzalloc(sizeof(struct acpi_processor_performance), GFP_KERNEL); - if (!acpi_processor_perf) { retval = -ENOMEM; goto err0; } - memset(acpi_processor_perf, 0, sizeof(struct acpi_processor_performance)); - if (acpi_processor_register_performance(acpi_processor_perf, 0)) { retval = -EIO; goto err1; @@ -337,14 +333,12 @@ static int powernow_acpi_init(void) goto err2; } - powernow_table = kmalloc((number_scales + 1) * (sizeof(struct cpufreq_frequency_table)), GFP_KERNEL); + powernow_table = kzalloc((number_scales + 1) * (sizeof(struct cpufreq_frequency_table)), GFP_KERNEL); if (!powernow_table) { retval = -ENOMEM; goto err2; } - memset(powernow_table, 0, ((number_scales + 1) * sizeof(struct cpufreq_frequency_table))); - pc.val = (unsigned long) acpi_processor_perf->states[0].control; for (i = 0; i < number_scales; i++) { u8 fid, vid; diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c index 2d5c9adba0cd..68a1fc87f4ca 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c @@ -462,7 +462,6 @@ static int check_supported_cpu(unsigned int cpu) oldmask = current->cpus_allowed; set_cpus_allowed(current, cpumask_of_cpu(cpu)); - schedule(); if (smp_processor_id() != cpu) { printk(KERN_ERR "limiting to cpu %u failed\n", cpu); @@ -497,9 +496,7 @@ static int check_supported_cpu(unsigned int cpu) out: set_cpus_allowed(current, oldmask); - schedule(); return rc; - } static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, u8 maxvid) @@ -913,7 +910,6 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi /* only run on specific CPU from here on */ oldmask = current->cpus_allowed; set_cpus_allowed(current, cpumask_of_cpu(pol->cpu)); - schedule(); if (smp_processor_id() != pol->cpu) { printk(KERN_ERR "limiting to cpu %u failed\n", pol->cpu); @@ -968,8 +964,6 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi err_out: set_cpus_allowed(current, oldmask); - schedule(); - return ret; } @@ -991,12 +985,11 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol) if (!check_supported_cpu(pol->cpu)) return -ENODEV; - data = kmalloc(sizeof(struct powernow_k8_data), GFP_KERNEL); + data = kzalloc(sizeof(struct powernow_k8_data), GFP_KERNEL); if (!data) { printk(KERN_ERR PFX "unable to alloc powernow_k8_data"); return -ENOMEM; } - memset(data,0,sizeof(struct powernow_k8_data)); data->cpu = pol->cpu; @@ -1026,7 +1019,6 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol) /* only run on specific CPU from here on */ oldmask = current->cpus_allowed; set_cpus_allowed(current, cpumask_of_cpu(pol->cpu)); - schedule(); if (smp_processor_id() != pol->cpu) { printk(KERN_ERR "limiting to cpu %u failed\n", pol->cpu); @@ -1045,7 +1037,6 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol) /* run on any CPU again */ set_cpus_allowed(current, oldmask); - schedule(); pol->governor = CPUFREQ_DEFAULT_GOVERNOR; pol->cpus = cpu_core_map[pol->cpu]; @@ -1080,7 +1071,6 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol) err_out: set_cpus_allowed(current, oldmask); - schedule(); powernow_k8_cpu_exit_acpi(data); kfree(data); @@ -1116,17 +1106,14 @@ static unsigned int powernowk8_get (unsigned int cpu) set_cpus_allowed(current, oldmask); return 0; } - preempt_disable(); - + if (query_current_values_with_pending_wait(data)) goto out; khz = find_khz_freq_from_fid(data->currfid); - out: - preempt_enable_no_resched(); +out: set_cpus_allowed(current, oldmask); - return khz; } diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c index 1465974256c9..edb9873e27e3 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c @@ -67,7 +67,7 @@ static const struct cpu_id cpu_ids[] = { [CPU_MP4HT_D0] = {15, 3, 4 }, [CPU_MP4HT_E0] = {15, 4, 1 }, }; -#define N_IDS (sizeof(cpu_ids)/sizeof(cpu_ids[0])) +#define N_IDS ARRAY_SIZE(cpu_ids) struct cpu_model { @@ -423,12 +423,11 @@ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) } } - centrino_model[cpu] = kmalloc(sizeof(struct cpu_model), GFP_KERNEL); + centrino_model[cpu] = kzalloc(sizeof(struct cpu_model), GFP_KERNEL); if (!centrino_model[cpu]) { result = -ENOMEM; goto err_unreg; } - memset(centrino_model[cpu], 0, sizeof(struct cpu_model)); centrino_model[cpu]->model_name=NULL; centrino_model[cpu]->max_freq = p.states[0].core_frequency * 1000; diff --git a/arch/i386/kernel/cpu/intel.c b/arch/i386/kernel/cpu/intel.c index 43601de0f633..5e2da704f0fa 100644 --- a/arch/i386/kernel/cpu/intel.c +++ b/arch/i386/kernel/cpu/intel.c @@ -6,6 +6,7 @@ #include <linux/bitops.h> #include <linux/smp.h> #include <linux/thread_info.h> +#include <linux/module.h> #include <asm/processor.h> #include <asm/msr.h> @@ -157,7 +158,7 @@ static void __devinit init_intel(struct cpuinfo_x86 *c) if ( p ) strcpy(c->x86_model_id, p); - c->x86_num_cores = num_cpu_cores(c); + c->x86_max_cores = num_cpu_cores(c); detect_ht(c); @@ -264,5 +265,52 @@ __init int intel_cpu_init(void) return 0; } +#ifndef CONFIG_X86_CMPXCHG +unsigned long cmpxchg_386_u8(volatile void *ptr, u8 old, u8 new) +{ + u8 prev; + unsigned long flags; + + /* Poor man's cmpxchg for 386. Unsuitable for SMP */ + local_irq_save(flags); + prev = *(u8 *)ptr; + if (prev == old) + *(u8 *)ptr = new; + local_irq_restore(flags); + return prev; +} +EXPORT_SYMBOL(cmpxchg_386_u8); + +unsigned long cmpxchg_386_u16(volatile void *ptr, u16 old, u16 new) +{ + u16 prev; + unsigned long flags; + + /* Poor man's cmpxchg for 386. Unsuitable for SMP */ + local_irq_save(flags); + prev = *(u16 *)ptr; + if (prev == old) + *(u16 *)ptr = new; + local_irq_restore(flags); + return prev; +} +EXPORT_SYMBOL(cmpxchg_386_u16); + +unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new) +{ + u32 prev; + unsigned long flags; + + /* Poor man's cmpxchg for 386. Unsuitable for SMP */ + local_irq_save(flags); + prev = *(u32 *)ptr; + if (prev == old) + *(u32 *)ptr = new; + local_irq_restore(flags); + return prev; +} +EXPORT_SYMBOL(cmpxchg_386_u32); +#endif + // arch_initcall(intel_cpu_init); diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index 4dc42a189ae5..fbfd374aa336 100644 --- a/arch/i386/kernel/cpu/intel_cacheinfo.c +++ b/arch/i386/kernel/cpu/intel_cacheinfo.c @@ -293,29 +293,45 @@ static struct _cpuid4_info *cpuid4_info[NR_CPUS]; #ifdef CONFIG_SMP static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) { - struct _cpuid4_info *this_leaf; + struct _cpuid4_info *this_leaf, *sibling_leaf; unsigned long num_threads_sharing; -#ifdef CONFIG_X86_HT - struct cpuinfo_x86 *c = cpu_data + cpu; -#endif + int index_msb, i; + struct cpuinfo_x86 *c = cpu_data; this_leaf = CPUID4_INFO_IDX(cpu, index); num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing; if (num_threads_sharing == 1) cpu_set(cpu, this_leaf->shared_cpu_map); -#ifdef CONFIG_X86_HT - else if (num_threads_sharing == smp_num_siblings) - this_leaf->shared_cpu_map = cpu_sibling_map[cpu]; - else if (num_threads_sharing == (c->x86_num_cores * smp_num_siblings)) - this_leaf->shared_cpu_map = cpu_core_map[cpu]; - else - printk(KERN_DEBUG "Number of CPUs sharing cache didn't match " - "any known set of CPUs\n"); -#endif + else { + index_msb = get_count_order(num_threads_sharing); + + for_each_online_cpu(i) { + if (c[i].apicid >> index_msb == + c[cpu].apicid >> index_msb) { + cpu_set(i, this_leaf->shared_cpu_map); + if (i != cpu && cpuid4_info[i]) { + sibling_leaf = CPUID4_INFO_IDX(i, index); + cpu_set(cpu, sibling_leaf->shared_cpu_map); + } + } + } + } +} +static void __devinit cache_remove_shared_cpu_map(unsigned int cpu, int index) +{ + struct _cpuid4_info *this_leaf, *sibling_leaf; + int sibling; + + this_leaf = CPUID4_INFO_IDX(cpu, index); + for_each_cpu_mask(sibling, this_leaf->shared_cpu_map) { + sibling_leaf = CPUID4_INFO_IDX(sibling, index); + cpu_clear(cpu, sibling_leaf->shared_cpu_map); + } } #else static void __init cache_shared_cpu_map_setup(unsigned int cpu, int index) {} +static void __init cache_remove_shared_cpu_map(unsigned int cpu, int index) {} #endif static void free_cache_attributes(unsigned int cpu) @@ -574,8 +590,10 @@ static void __cpuexit cache_remove_dev(struct sys_device * sys_dev) unsigned int cpu = sys_dev->id; unsigned long i; - for (i = 0; i < num_cache_leaves; i++) + for (i = 0; i < num_cache_leaves; i++) { + cache_remove_shared_cpu_map(cpu, i); kobject_unregister(&(INDEX_KOBJECT_PTR(cpu,i)->kobj)); + } kobject_unregister(cache_kobject[cpu]); cpuid4_cache_sysfs_exit(cpu); return; diff --git a/arch/i386/kernel/cpu/mcheck/k7.c b/arch/i386/kernel/cpu/mcheck/k7.c index 7c6b9c73522f..fc5d5215e23d 100644 --- a/arch/i386/kernel/cpu/mcheck/k7.c +++ b/arch/i386/kernel/cpu/mcheck/k7.c @@ -68,7 +68,7 @@ static fastcall void k7_machine_check(struct pt_regs * regs, long error_code) /* AMD K7 machine check is Intel like */ -void __devinit amd_mcheck_init(struct cpuinfo_x86 *c) +void amd_mcheck_init(struct cpuinfo_x86 *c) { u32 l, h; int i; diff --git a/arch/i386/kernel/cpu/mcheck/mce.c b/arch/i386/kernel/cpu/mcheck/mce.c index 2cf25d2ba0f1..6170af3c271a 100644 --- a/arch/i386/kernel/cpu/mcheck/mce.c +++ b/arch/i386/kernel/cpu/mcheck/mce.c @@ -16,7 +16,7 @@ #include "mce.h" -int mce_disabled __devinitdata = 0; +int mce_disabled = 0; int nr_mce_banks; EXPORT_SYMBOL_GPL(nr_mce_banks); /* non-fatal.o */ @@ -31,7 +31,7 @@ static fastcall void unexpected_machine_check(struct pt_regs * regs, long error_ void fastcall (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check; /* This has to be run for each processor */ -void __devinit mcheck_init(struct cpuinfo_x86 *c) +void mcheck_init(struct cpuinfo_x86 *c) { if (mce_disabled==1) return; diff --git a/arch/i386/kernel/cpu/mcheck/p4.c b/arch/i386/kernel/cpu/mcheck/p4.c index 1d1e885f500a..fd2c459a31ef 100644 --- a/arch/i386/kernel/cpu/mcheck/p4.c +++ b/arch/i386/kernel/cpu/mcheck/p4.c @@ -77,7 +77,7 @@ fastcall void smp_thermal_interrupt(struct pt_regs *regs) } /* P4/Xeon Thermal regulation detect and init */ -static void __devinit intel_init_thermal(struct cpuinfo_x86 *c) +static void intel_init_thermal(struct cpuinfo_x86 *c) { u32 l, h; unsigned int cpu = smp_processor_id(); @@ -231,7 +231,7 @@ static fastcall void intel_machine_check(struct pt_regs * regs, long error_code) } -void __devinit intel_p4_mcheck_init(struct cpuinfo_x86 *c) +void intel_p4_mcheck_init(struct cpuinfo_x86 *c) { u32 l, h; int i; diff --git a/arch/i386/kernel/cpu/mcheck/p5.c b/arch/i386/kernel/cpu/mcheck/p5.c index 3a2e24baddc7..94bc43d950cf 100644 --- a/arch/i386/kernel/cpu/mcheck/p5.c +++ b/arch/i386/kernel/cpu/mcheck/p5.c @@ -28,7 +28,7 @@ static fastcall void pentium_machine_check(struct pt_regs * regs, long error_cod } /* Set up machine check reporting for processors with Intel style MCE */ -void __devinit intel_p5_mcheck_init(struct cpuinfo_x86 *c) +void intel_p5_mcheck_init(struct cpuinfo_x86 *c) { u32 l, h; diff --git a/arch/i386/kernel/cpu/mcheck/p6.c b/arch/i386/kernel/cpu/mcheck/p6.c index 979b18bc95c1..deeae42ce199 100644 --- a/arch/i386/kernel/cpu/mcheck/p6.c +++ b/arch/i386/kernel/cpu/mcheck/p6.c @@ -79,7 +79,7 @@ static fastcall void intel_machine_check(struct pt_regs * regs, long error_code) } /* Set up machine check reporting for processors with Intel style MCE */ -void __devinit intel_p6_mcheck_init(struct cpuinfo_x86 *c) +void intel_p6_mcheck_init(struct cpuinfo_x86 *c) { u32 l, h; int i; diff --git a/arch/i386/kernel/cpu/mcheck/winchip.c b/arch/i386/kernel/cpu/mcheck/winchip.c index 5b9d2dd411d3..9e424b6c293d 100644 --- a/arch/i386/kernel/cpu/mcheck/winchip.c +++ b/arch/i386/kernel/cpu/mcheck/winchip.c @@ -22,7 +22,7 @@ static fastcall void winchip_machine_check(struct pt_regs * regs, long error_cod } /* Set up machine check reporting on the Winchip C6 series */ -void __devinit winchip_mcheck_init(struct cpuinfo_x86 *c) +void winchip_mcheck_init(struct cpuinfo_x86 *c) { u32 lo, hi; machine_check_vector = winchip_machine_check; diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c index dd4ebd6af7e4..1e9db198c440 100644 --- a/arch/i386/kernel/cpu/mtrr/main.c +++ b/arch/i386/kernel/cpu/mtrr/main.c @@ -626,6 +626,14 @@ void __init mtrr_bp_init(void) if (cpuid_eax(0x80000000) >= 0x80000008) { u32 phys_addr; phys_addr = cpuid_eax(0x80000008) & 0xff; + /* CPUID workaround for Intel 0F33/0F34 CPU */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + boot_cpu_data.x86 == 0xF && + boot_cpu_data.x86_model == 0x3 && + (boot_cpu_data.x86_mask == 0x3 || + boot_cpu_data.x86_mask == 0x4)) + phys_addr = 36; + size_or_mask = ~((1 << (phys_addr - PAGE_SHIFT)) - 1); size_and_mask = ~size_or_mask & 0xfff00000; } else if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR && diff --git a/arch/i386/kernel/cpu/proc.c b/arch/i386/kernel/cpu/proc.c index 41b871ecf4b3..e7921315ae9d 100644 --- a/arch/i386/kernel/cpu/proc.c +++ b/arch/i386/kernel/cpu/proc.c @@ -94,12 +94,11 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (c->x86_cache_size >= 0) seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); #ifdef CONFIG_X86_HT - if (c->x86_num_cores * smp_num_siblings > 1) { + if (c->x86_max_cores * smp_num_siblings > 1) { seq_printf(m, "physical id\t: %d\n", phys_proc_id[n]); - seq_printf(m, "siblings\t: %d\n", - c->x86_num_cores * smp_num_siblings); + seq_printf(m, "siblings\t: %d\n", cpus_weight(cpu_core_map[n])); seq_printf(m, "core id\t\t: %d\n", cpu_core_id[n]); - seq_printf(m, "cpu cores\t: %d\n", c->x86_num_cores); + seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); } #endif diff --git a/arch/i386/kernel/crash.c b/arch/i386/kernel/crash.c index af809ccf5fbe..0248e084017c 100644 --- a/arch/i386/kernel/crash.c +++ b/arch/i386/kernel/crash.c @@ -21,6 +21,7 @@ #include <asm/hardirq.h> #include <asm/nmi.h> #include <asm/hw_irq.h> +#include <asm/apic.h> #include <mach_ipi.h> @@ -147,6 +148,7 @@ static int crash_nmi_callback(struct pt_regs *regs, int cpu) regs = &fixed_regs; } crash_save_this_cpu(regs, cpu); + disable_local_APIC(); atomic_dec(&waiting_for_crash_ipi); /* Assume hlt works */ halt(); @@ -186,6 +188,7 @@ static void nmi_shootdown_cpus(void) } /* Leave the nmi callback set */ + disable_local_APIC(); } #else static void nmi_shootdown_cpus(void) @@ -210,5 +213,9 @@ void machine_crash_shutdown(struct pt_regs *regs) /* Make a note of crashing cpu. Will be used in NMI callback.*/ crashing_cpu = smp_processor_id(); nmi_shootdown_cpus(); + lapic_shutdown(); +#if defined(CONFIG_X86_IO_APIC) + disable_IO_APIC(); +#endif crash_save_self(regs); } diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S index 9e24f7b207ee..e50b93155249 100644 --- a/arch/i386/kernel/entry.S +++ b/arch/i386/kernel/entry.S @@ -560,11 +560,10 @@ nmi_stack_fixup: nmi_debug_stack_check: cmpw $__KERNEL_CS,16(%esp) jne nmi_stack_correct - cmpl $debug - 1,(%esp) - jle nmi_stack_correct + cmpl $debug,(%esp) + jb nmi_stack_correct cmpl $debug_esp_fix_insn,(%esp) - jle nmi_debug_stack_fixup -nmi_debug_stack_fixup: + ja nmi_stack_correct FIX_STACK(24,nmi_stack_correct, 1) jmp nmi_stack_correct diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c index 6345b430b105..32b0c24ab9a6 100644 --- a/arch/i386/kernel/kprobes.c +++ b/arch/i386/kernel/kprobes.c @@ -31,22 +31,16 @@ #include <linux/config.h> #include <linux/kprobes.h> #include <linux/ptrace.h> -#include <linux/spinlock.h> #include <linux/preempt.h> #include <asm/cacheflush.h> #include <asm/kdebug.h> #include <asm/desc.h> -static struct kprobe *current_kprobe; -static unsigned long kprobe_status, kprobe_old_eflags, kprobe_saved_eflags; -static struct kprobe *kprobe_prev; -static unsigned long kprobe_status_prev, kprobe_old_eflags_prev, kprobe_saved_eflags_prev; -static struct pt_regs jprobe_saved_regs; -static long *jprobe_saved_esp; -/* copy of the kernel stack at the probe fire time */ -static kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE]; void jprobe_return_end(void); +DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + /* * returns non-zero if opcode modifies the interrupt flag. */ @@ -91,29 +85,30 @@ void __kprobes arch_remove_kprobe(struct kprobe *p) { } -static inline void save_previous_kprobe(void) +static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb) { - kprobe_prev = current_kprobe; - kprobe_status_prev = kprobe_status; - kprobe_old_eflags_prev = kprobe_old_eflags; - kprobe_saved_eflags_prev = kprobe_saved_eflags; + kcb->prev_kprobe.kp = kprobe_running(); + kcb->prev_kprobe.status = kcb->kprobe_status; + kcb->prev_kprobe.old_eflags = kcb->kprobe_old_eflags; + kcb->prev_kprobe.saved_eflags = kcb->kprobe_saved_eflags; } -static inline void restore_previous_kprobe(void) +static inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb) { - current_kprobe = kprobe_prev; - kprobe_status = kprobe_status_prev; - kprobe_old_eflags = kprobe_old_eflags_prev; - kprobe_saved_eflags = kprobe_saved_eflags_prev; + __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + kcb->kprobe_status = kcb->prev_kprobe.status; + kcb->kprobe_old_eflags = kcb->prev_kprobe.old_eflags; + kcb->kprobe_saved_eflags = kcb->prev_kprobe.saved_eflags; } -static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs) +static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) { - current_kprobe = p; - kprobe_saved_eflags = kprobe_old_eflags + __get_cpu_var(current_kprobe) = p; + kcb->kprobe_saved_eflags = kcb->kprobe_old_eflags = (regs->eflags & (TF_MASK | IF_MASK)); if (is_IF_modifier(p->opcode)) - kprobe_saved_eflags &= ~IF_MASK; + kcb->kprobe_saved_eflags &= ~IF_MASK; } static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) @@ -127,6 +122,7 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) regs->eip = (unsigned long)&p->ainsn.insn; } +/* Called with kretprobe_lock held */ void __kprobes arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) { @@ -157,9 +153,15 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) int ret = 0; kprobe_opcode_t *addr = NULL; unsigned long *lp; + struct kprobe_ctlblk *kcb; - /* We're in an interrupt, but this is clear and BUG()-safe. */ + /* + * We don't want to be preempted for the entire + * duration of kprobe processing + */ preempt_disable(); + kcb = get_kprobe_ctlblk(); + /* Check if the application is using LDT entry for its code segment and * calculate the address by reading the base address from the LDT entry. */ @@ -173,15 +175,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) } /* Check we're not actually recursing */ if (kprobe_running()) { - /* We *are* holding lock here, so this is safe. - Disarm the probe we just hit, and ignore it. */ p = get_kprobe(addr); if (p) { - if (kprobe_status == KPROBE_HIT_SS && + if (kcb->kprobe_status == KPROBE_HIT_SS && *p->ainsn.insn == BREAKPOINT_INSTRUCTION) { regs->eflags &= ~TF_MASK; - regs->eflags |= kprobe_saved_eflags; - unlock_kprobes(); + regs->eflags |= kcb->kprobe_saved_eflags; goto no_kprobe; } /* We have reentered the kprobe_handler(), since @@ -190,26 +189,23 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) * just single step on the instruction of the new probe * without calling any user handlers. */ - save_previous_kprobe(); - set_current_kprobe(p, regs); + save_previous_kprobe(kcb); + set_current_kprobe(p, regs, kcb); p->nmissed++; prepare_singlestep(p, regs); - kprobe_status = KPROBE_REENTER; + kcb->kprobe_status = KPROBE_REENTER; return 1; } else { - p = current_kprobe; + p = __get_cpu_var(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { goto ss_probe; } } - /* If it's not ours, can't be delete race, (we hold lock). */ goto no_kprobe; } - lock_kprobes(); p = get_kprobe(addr); if (!p) { - unlock_kprobes(); if (regs->eflags & VM_MASK) { /* We are in virtual-8086 mode. Return 0 */ goto no_kprobe; @@ -232,8 +228,8 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) goto no_kprobe; } - kprobe_status = KPROBE_HIT_ACTIVE; - set_current_kprobe(p, regs); + set_current_kprobe(p, regs, kcb); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; if (p->pre_handler && p->pre_handler(p, regs)) /* handler has already set things up, so skip ss setup */ @@ -241,7 +237,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) ss_probe: prepare_singlestep(p, regs); - kprobe_status = KPROBE_HIT_SS; + kcb->kprobe_status = KPROBE_HIT_SS; return 1; no_kprobe: @@ -269,9 +265,10 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) struct kretprobe_instance *ri = NULL; struct hlist_head *head; struct hlist_node *node, *tmp; - unsigned long orig_ret_address = 0; + unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline; + spin_lock_irqsave(&kretprobe_lock, flags); head = kretprobe_inst_table_head(current); /* @@ -310,14 +307,15 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address)); regs->eip = orig_ret_address; - unlock_kprobes(); + reset_current_kprobe(); + spin_unlock_irqrestore(&kretprobe_lock, flags); preempt_enable_no_resched(); - /* - * By returning a non-zero value, we are telling - * kprobe_handler() that we have handled unlocking - * and re-enabling preemption. - */ + /* + * By returning a non-zero value, we are telling + * kprobe_handler() that we don't want the post_handler + * to run (and have re-enabled preemption) + */ return 1; } @@ -343,7 +341,8 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * that is atop the stack is the address following the copied instruction. * We need to make it the address following the original instruction. */ -static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) +static void __kprobes resume_execution(struct kprobe *p, + struct pt_regs *regs, struct kprobe_ctlblk *kcb) { unsigned long *tos = (unsigned long *)®s->esp; unsigned long next_eip = 0; @@ -353,7 +352,7 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) switch (p->ainsn.insn[0]) { case 0x9c: /* pushfl */ *tos &= ~(TF_MASK | IF_MASK); - *tos |= kprobe_old_eflags; + *tos |= kcb->kprobe_old_eflags; break; case 0xc3: /* ret/lret */ case 0xcb: @@ -394,27 +393,30 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) /* * Interrupts are disabled on entry as trap1 is an interrupt gate and they - * remain disabled thoroughout this function. And we hold kprobe lock. + * remain disabled thoroughout this function. */ static inline int post_kprobe_handler(struct pt_regs *regs) { - if (!kprobe_running()) + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + if (!cur) return 0; - if ((kprobe_status != KPROBE_REENTER) && current_kprobe->post_handler) { - kprobe_status = KPROBE_HIT_SSDONE; - current_kprobe->post_handler(current_kprobe, regs, 0); + if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + cur->post_handler(cur, regs, 0); } - resume_execution(current_kprobe, regs); - regs->eflags |= kprobe_saved_eflags; + resume_execution(cur, regs, kcb); + regs->eflags |= kcb->kprobe_saved_eflags; /*Restore back the original saved kprobes variables and continue. */ - if (kprobe_status == KPROBE_REENTER) { - restore_previous_kprobe(); + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); goto out; } - unlock_kprobes(); + reset_current_kprobe(); out: preempt_enable_no_resched(); @@ -429,18 +431,19 @@ out: return 1; } -/* Interrupts disabled, kprobe_lock held. */ static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) { - if (current_kprobe->fault_handler - && current_kprobe->fault_handler(current_kprobe, regs, trapnr)) + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) return 1; - if (kprobe_status & KPROBE_HIT_SS) { - resume_execution(current_kprobe, regs); - regs->eflags |= kprobe_old_eflags; + if (kcb->kprobe_status & KPROBE_HIT_SS) { + resume_execution(cur, regs, kcb); + regs->eflags |= kcb->kprobe_old_eflags; - unlock_kprobes(); + reset_current_kprobe(); preempt_enable_no_resched(); } return 0; @@ -453,39 +456,41 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) { struct die_args *args = (struct die_args *)data; + int ret = NOTIFY_DONE; + switch (val) { case DIE_INT3: if (kprobe_handler(args->regs)) - return NOTIFY_STOP; + ret = NOTIFY_STOP; break; case DIE_DEBUG: if (post_kprobe_handler(args->regs)) - return NOTIFY_STOP; + ret = NOTIFY_STOP; break; case DIE_GPF: - if (kprobe_running() && - kprobe_fault_handler(args->regs, args->trapnr)) - return NOTIFY_STOP; - break; case DIE_PAGE_FAULT: + /* kprobe_running() needs smp_processor_id() */ + preempt_disable(); if (kprobe_running() && kprobe_fault_handler(args->regs, args->trapnr)) - return NOTIFY_STOP; + ret = NOTIFY_STOP; + preempt_enable(); break; default: break; } - return NOTIFY_DONE; + return ret; } int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); unsigned long addr; + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - jprobe_saved_regs = *regs; - jprobe_saved_esp = ®s->esp; - addr = (unsigned long)jprobe_saved_esp; + kcb->jprobe_saved_regs = *regs; + kcb->jprobe_saved_esp = ®s->esp; + addr = (unsigned long)(kcb->jprobe_saved_esp); /* * TBD: As Linus pointed out, gcc assumes that the callee @@ -494,7 +499,8 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) * we also save and restore enough stack bytes to cover * the argument area. */ - memcpy(jprobes_stack, (kprobe_opcode_t *) addr, MIN_STACK_SIZE(addr)); + memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, + MIN_STACK_SIZE(addr)); regs->eflags &= ~IF_MASK; regs->eip = (unsigned long)(jp->entry); return 1; @@ -502,36 +508,40 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) void __kprobes jprobe_return(void) { - preempt_enable_no_resched(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + asm volatile (" xchgl %%ebx,%%esp \n" " int3 \n" " .globl jprobe_return_end \n" " jprobe_return_end: \n" " nop \n"::"b" - (jprobe_saved_esp):"memory"); + (kcb->jprobe_saved_esp):"memory"); } int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) { + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); u8 *addr = (u8 *) (regs->eip - 1); - unsigned long stack_addr = (unsigned long)jprobe_saved_esp; + unsigned long stack_addr = (unsigned long)(kcb->jprobe_saved_esp); struct jprobe *jp = container_of(p, struct jprobe, kp); if ((addr > (u8 *) jprobe_return) && (addr < (u8 *) jprobe_return_end)) { - if (®s->esp != jprobe_saved_esp) { + if (®s->esp != kcb->jprobe_saved_esp) { struct pt_regs *saved_regs = - container_of(jprobe_saved_esp, struct pt_regs, esp); + container_of(kcb->jprobe_saved_esp, + struct pt_regs, esp); printk("current esp %p does not match saved esp %p\n", - ®s->esp, jprobe_saved_esp); + ®s->esp, kcb->jprobe_saved_esp); printk("Saved registers for jprobe %p\n", jp); show_registers(saved_regs); printk("Current registers\n"); show_registers(regs); BUG(); } - *regs = jprobe_saved_regs; - memcpy((kprobe_opcode_t *) stack_addr, jprobes_stack, + *regs = kcb->jprobe_saved_regs; + memcpy((kprobe_opcode_t *) stack_addr, kcb->jprobes_stack, MIN_STACK_SIZE(stack_addr)); + preempt_enable_no_resched(); return 1; } return 0; diff --git a/arch/i386/kernel/ldt.c b/arch/i386/kernel/ldt.c index fe1ffa55587d..983f95707e11 100644 --- a/arch/i386/kernel/ldt.c +++ b/arch/i386/kernel/ldt.c @@ -18,6 +18,7 @@ #include <asm/system.h> #include <asm/ldt.h> #include <asm/desc.h> +#include <asm/mmu_context.h> #ifdef CONFIG_SMP /* avoids "defined but not used" warnig */ static void flush_ldt(void *null) diff --git a/arch/i386/kernel/mca.c b/arch/i386/kernel/mca.c index 8600faeea29d..558bb207720f 100644 --- a/arch/i386/kernel/mca.c +++ b/arch/i386/kernel/mca.c @@ -132,7 +132,7 @@ static struct resource mca_standard_resources[] = { { .start = 0x100, .end = 0x107, .name = "POS (MCA)" } }; -#define MCA_STANDARD_RESOURCES (sizeof(mca_standard_resources)/sizeof(struct resource)) +#define MCA_STANDARD_RESOURCES ARRAY_SIZE(mca_standard_resources) /** * mca_read_and_store_pos - read the POS registers into a memory buffer diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index 7a14fdfd3af9..1cb261f225d5 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -99,14 +99,22 @@ EXPORT_SYMBOL(enable_hlt); */ void default_idle(void) { + local_irq_enable(); + if (!hlt_counter && boot_cpu_data.hlt_works_ok) { - local_irq_disable(); - if (!need_resched()) - safe_halt(); - else - local_irq_enable(); + clear_thread_flag(TIF_POLLING_NRFLAG); + smp_mb__after_clear_bit(); + while (!need_resched()) { + local_irq_disable(); + if (!need_resched()) + safe_halt(); + else + local_irq_enable(); + } + set_thread_flag(TIF_POLLING_NRFLAG); } else { - cpu_relax(); + while (!need_resched()) + cpu_relax(); } } #ifdef CONFIG_APM_MODULE @@ -120,29 +128,14 @@ EXPORT_SYMBOL(default_idle); */ static void poll_idle (void) { - int oldval; - local_irq_enable(); - /* - * Deal with another CPU just having chosen a thread to - * run here: - */ - oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED); - - if (!oldval) { - set_thread_flag(TIF_POLLING_NRFLAG); - asm volatile( - "2:" - "testl %0, %1;" - "rep; nop;" - "je 2b;" - : : "i"(_TIF_NEED_RESCHED), "m" (current_thread_info()->flags)); - - clear_thread_flag(TIF_POLLING_NRFLAG); - } else { - set_need_resched(); - } + asm volatile( + "2:" + "testl %0, %1;" + "rep; nop;" + "je 2b;" + : : "i"(_TIF_NEED_RESCHED), "m" (current_thread_info()->flags)); } #ifdef CONFIG_HOTPLUG_CPU @@ -179,7 +172,9 @@ static inline void play_dead(void) */ void cpu_idle(void) { - int cpu = raw_smp_processor_id(); + int cpu = smp_processor_id(); + + set_thread_flag(TIF_POLLING_NRFLAG); /* endless idle loop with no priority at all */ while (1) { @@ -201,7 +196,9 @@ void cpu_idle(void) __get_cpu_var(irq_stat).idle_timestamp = jiffies; idle(); } + preempt_enable_no_resched(); schedule(); + preempt_disable(); } } @@ -244,15 +241,12 @@ static void mwait_idle(void) { local_irq_enable(); - if (!need_resched()) { - set_thread_flag(TIF_POLLING_NRFLAG); - do { - __monitor((void *)¤t_thread_info()->flags, 0, 0); - if (need_resched()) - break; - __mwait(0, 0); - } while (!need_resched()); - clear_thread_flag(TIF_POLLING_NRFLAG); + while (!need_resched()) { + __monitor((void *)¤t_thread_info()->flags, 0, 0); + smp_mb(); + if (need_resched()) + break; + __mwait(0, 0); } } diff --git a/arch/i386/kernel/ptrace.c b/arch/i386/kernel/ptrace.c index efd11f09c996..5ffbb4b7ad05 100644 --- a/arch/i386/kernel/ptrace.c +++ b/arch/i386/kernel/ptrace.c @@ -354,49 +354,12 @@ ptrace_set_thread_area(struct task_struct *child, return 0; } -asmlinkage long sys_ptrace(long request, long pid, long addr, long data) +long arch_ptrace(struct task_struct *child, long request, long addr, long data) { - struct task_struct *child; struct user * dummy = NULL; int i, ret; unsigned long __user *datap = (unsigned long __user *)data; - lock_kernel(); - ret = -EPERM; - if (request == PTRACE_TRACEME) { - /* are we already being traced? */ - if (current->ptrace & PT_PTRACED) - goto out; - ret = security_ptrace(current->parent, current); - if (ret) - goto out; - /* set the ptrace bit in the process flags. */ - current->ptrace |= PT_PTRACED; - ret = 0; - goto out; - } - ret = -ESRCH; - read_lock(&tasklist_lock); - child = find_task_by_pid(pid); - if (child) - get_task_struct(child); - read_unlock(&tasklist_lock); - if (!child) - goto out; - - ret = -EPERM; - if (pid == 1) /* you may not mess with init */ - goto out_tsk; - - if (request == PTRACE_ATTACH) { - ret = ptrace_attach(child); - goto out_tsk; - } - - ret = ptrace_check_attach(child, request == PTRACE_KILL); - if (ret < 0) - goto out_tsk; - switch (request) { /* when I and D space are separate, these will need to be fixed. */ case PTRACE_PEEKTEXT: /* read word at location addr. */ @@ -663,10 +626,7 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data) ret = ptrace_request(child, request, addr, data); break; } -out_tsk: - put_task_struct(child); -out: - unlock_kernel(); + out_tsk: return ret; } diff --git a/arch/i386/kernel/reboot_fixups.c b/arch/i386/kernel/reboot_fixups.c index c9b87330aeea..10e21a4773dd 100644 --- a/arch/i386/kernel/reboot_fixups.c +++ b/arch/i386/kernel/reboot_fixups.c @@ -10,6 +10,7 @@ #include <asm/delay.h> #include <linux/pci.h> +#include <linux/reboot_fixups.h> static void cs5530a_warm_reset(struct pci_dev *dev) { @@ -42,7 +43,7 @@ void mach_reboot_fixups(void) struct pci_dev *dev; int i; - for (i=0; i < (sizeof(fixups_table)/sizeof(fixups_table[0])); i++) { + for (i=0; i < ARRAY_SIZE(fixups_table); i++) { cur = &(fixups_table[i]); dev = pci_get_device(cur->vendor, cur->device, NULL); if (!dev) diff --git a/arch/i386/kernel/scx200.c b/arch/i386/kernel/scx200.c index 69e203a0d330..9c968ae67c43 100644 --- a/arch/i386/kernel/scx200.c +++ b/arch/i386/kernel/scx200.c @@ -12,6 +12,7 @@ #include <linux/pci.h> #include <linux/scx200.h> +#include <linux/scx200_gpio.h> /* Verify that the configuration block really is there */ #define scx200_cb_probe(base) (inw((base) + SCx200_CBA) == (base)) diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index b48ac635f3c1..fdfcb0cba9b4 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -129,9 +129,7 @@ struct drive_info_struct { char dummy[32]; } drive_info; EXPORT_SYMBOL(drive_info); #endif struct screen_info screen_info; -#ifdef CONFIG_VT EXPORT_SYMBOL(screen_info); -#endif struct apm_info apm_info; EXPORT_SYMBOL(apm_info); struct sys_desc_table_struct { diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index 01b618e73ecd..d16520da4550 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -68,15 +68,15 @@ EXPORT_SYMBOL(smp_num_siblings); /* Package ID of each logical CPU */ int phys_proc_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID}; -EXPORT_SYMBOL(phys_proc_id); /* Core ID of each logical CPU */ int cpu_core_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID}; -EXPORT_SYMBOL(cpu_core_id); +/* representing HT siblings of each logical CPU */ cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_sibling_map); +/* representing HT and core siblings of each logical CPU */ cpumask_t cpu_core_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_core_map); @@ -444,35 +444,60 @@ static void __devinit smp_callin(void) static int cpucount; +/* representing cpus for which sibling maps can be computed */ +static cpumask_t cpu_sibling_setup_map; + static inline void set_cpu_sibling_map(int cpu) { int i; + struct cpuinfo_x86 *c = cpu_data; + + cpu_set(cpu, cpu_sibling_setup_map); if (smp_num_siblings > 1) { - for (i = 0; i < NR_CPUS; i++) { - if (!cpu_isset(i, cpu_callout_map)) - continue; - if (cpu_core_id[cpu] == cpu_core_id[i]) { + for_each_cpu_mask(i, cpu_sibling_setup_map) { + if (phys_proc_id[cpu] == phys_proc_id[i] && + cpu_core_id[cpu] == cpu_core_id[i]) { cpu_set(i, cpu_sibling_map[cpu]); cpu_set(cpu, cpu_sibling_map[i]); + cpu_set(i, cpu_core_map[cpu]); + cpu_set(cpu, cpu_core_map[i]); } } } else { cpu_set(cpu, cpu_sibling_map[cpu]); } - if (current_cpu_data.x86_num_cores > 1) { - for (i = 0; i < NR_CPUS; i++) { - if (!cpu_isset(i, cpu_callout_map)) - continue; - if (phys_proc_id[cpu] == phys_proc_id[i]) { - cpu_set(i, cpu_core_map[cpu]); - cpu_set(cpu, cpu_core_map[i]); - } - } - } else { + if (current_cpu_data.x86_max_cores == 1) { cpu_core_map[cpu] = cpu_sibling_map[cpu]; + c[cpu].booted_cores = 1; + return; + } + + for_each_cpu_mask(i, cpu_sibling_setup_map) { + if (phys_proc_id[cpu] == phys_proc_id[i]) { + cpu_set(i, cpu_core_map[cpu]); + cpu_set(cpu, cpu_core_map[i]); + /* + * Does this new cpu bringup a new core? + */ + if (cpus_weight(cpu_sibling_map[cpu]) == 1) { + /* + * for each core in package, increment + * the booted_cores for this new cpu + */ + if (first_cpu(cpu_sibling_map[i]) == i) + c[cpu].booted_cores++; + /* + * increment the core count for all + * the other cpus in this package + */ + if (i != cpu) + c[i].booted_cores++; + } else if (i != cpu && !c[cpu].booted_cores) + c[cpu].booted_cores = c[i].booted_cores; + } } } @@ -487,6 +512,7 @@ static void __devinit start_secondary(void *unused) * things done here to the most necessary things. */ cpu_init(); + preempt_disable(); smp_callin(); while (!cpu_isset(smp_processor_id(), smp_commenced_mask)) rep_nop(); @@ -612,7 +638,7 @@ static inline void __inquire_remote_apic(int apicid) printk("Inquiring remote APIC #%d...\n", apicid); - for (i = 0; i < sizeof(regs) / sizeof(*regs); i++) { + for (i = 0; i < ARRAY_SIZE(regs); i++) { printk("... APIC #%d %s: ", apicid, names[i]); /* @@ -1096,11 +1122,8 @@ static void __init smp_boot_cpus(unsigned int max_cpus) current_thread_info()->cpu = 0; smp_tune_scheduling(); - cpus_clear(cpu_sibling_map[0]); - cpu_set(0, cpu_sibling_map[0]); - cpus_clear(cpu_core_map[0]); - cpu_set(0, cpu_core_map[0]); + set_cpu_sibling_map(0); /* * If we couldn't find an SMP configuration at boot time, @@ -1279,15 +1302,24 @@ static void remove_siblinginfo(int cpu) { int sibling; + struct cpuinfo_x86 *c = cpu_data; + for_each_cpu_mask(sibling, cpu_core_map[cpu]) { + cpu_clear(cpu, cpu_core_map[sibling]); + /* + * last thread sibling in this cpu core going down + */ + if (cpus_weight(cpu_sibling_map[cpu]) == 1) + c[sibling].booted_cores--; + } + for_each_cpu_mask(sibling, cpu_sibling_map[cpu]) cpu_clear(cpu, cpu_sibling_map[sibling]); - for_each_cpu_mask(sibling, cpu_core_map[cpu]) - cpu_clear(cpu, cpu_core_map[sibling]); cpus_clear(cpu_sibling_map[cpu]); cpus_clear(cpu_core_map[cpu]); phys_proc_id[cpu] = BAD_APICID; cpu_core_id[cpu] = BAD_APICID; + cpu_clear(cpu, cpu_sibling_setup_map); } int __cpu_disable(void) diff --git a/arch/i386/kernel/srat.c b/arch/i386/kernel/srat.c index 8de658db8146..52b3ed5d2cb5 100644 --- a/arch/i386/kernel/srat.c +++ b/arch/i386/kernel/srat.c @@ -137,8 +137,8 @@ static void __init parse_memory_affinity_structure (char *sratp) "enabled and removable" : "enabled" ) ); } -#if MAX_NR_ZONES != 3 -#error "MAX_NR_ZONES != 3, chunk_to_zone requires review" +#if MAX_NR_ZONES != 4 +#error "MAX_NR_ZONES != 4, chunk_to_zone requires review" #endif /* Take a chunk of pages from page frame cstart to cend and count the number * of pages in each zone, returned via zones[]. diff --git a/arch/i386/kernel/timers/timer_pit.c b/arch/i386/kernel/timers/timer_pit.c index e42e46d35159..b9b6bd56b9ba 100644 --- a/arch/i386/kernel/timers/timer_pit.c +++ b/arch/i386/kernel/timers/timer_pit.c @@ -25,8 +25,9 @@ static int __init init_pit(char* override) { /* check clock override */ if (override[0] && strncmp(override,"pit",3)) - printk(KERN_ERR "Warning: clock= override failed. Defaulting to PIT\n"); - + printk(KERN_ERR "Warning: clock= override failed. Defaulting " + "to PIT\n"); + init_cpu_khz(); count_p = LATCH; return 0; } diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c index 542d9298da5e..06e26f006238 100644 --- a/arch/i386/mm/init.c +++ b/arch/i386/mm/init.c @@ -28,6 +28,7 @@ #include <linux/proc_fs.h> #include <linux/efi.h> #include <linux/memory_hotplug.h> +#include <linux/initrd.h> #include <asm/processor.h> #include <asm/system.h> @@ -267,7 +268,7 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) pkmap_page_table = pte; } -void __devinit free_new_highpage(struct page *page) +static void __devinit free_new_highpage(struct page *page) { set_page_count(page, 1); __free_page(page); diff --git a/arch/i386/oprofile/Kconfig b/arch/i386/oprofile/Kconfig index 5ade19801b97..d8a84088471a 100644 --- a/arch/i386/oprofile/Kconfig +++ b/arch/i386/oprofile/Kconfig @@ -1,7 +1,3 @@ - -menu "Profiling support" - depends on EXPERIMENTAL - config PROFILING bool "Profiling support (EXPERIMENTAL)" help @@ -19,5 +15,3 @@ config OPROFILE If unsure, say N. -endmenu - diff --git a/arch/i386/pci/fixup.c b/arch/i386/pci/fixup.c index 3984226a8b98..eeb1b1f2d548 100644 --- a/arch/i386/pci/fixup.c +++ b/arch/i386/pci/fixup.c @@ -433,9 +433,8 @@ static void __devinit pci_post_fixup_toshiba_ohci1394(struct pci_dev *dev) return; /* only applies to certain Toshibas (so far) */ /* Restore config space on Toshiba laptops */ - mdelay(10); pci_write_config_word(dev, PCI_CACHE_LINE_SIZE, toshiba_line_size); - pci_write_config_word(dev, PCI_INTERRUPT_LINE, dev->irq); + pci_read_config_byte(dev, PCI_INTERRUPT_LINE, (u8 *)&dev->irq); pci_write_config_dword(dev, PCI_BASE_ADDRESS_0, pci_resource_start(dev, 0)); pci_write_config_dword(dev, PCI_BASE_ADDRESS_1, diff --git a/arch/i386/power/cpu.c b/arch/i386/power/cpu.c index 1f1572692e0b..50a0bef8c85f 100644 --- a/arch/i386/power/cpu.c +++ b/arch/i386/power/cpu.c @@ -118,6 +118,7 @@ void __restore_processor_state(struct saved_context *ctxt) fix_processor_context(); do_fpu_end(); mtrr_ap_init(); + mcheck_init(&boot_cpu_data); } void restore_processor_state(void) |
