diff options
Diffstat (limited to 'arch/x86/kernel')
50 files changed, 926 insertions, 1110 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index d8e5d0cdd678..d1911abac180 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -11,6 +11,8 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_tsc.o = -pg CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg +CFLAGS_REMOVE_pvclock.o = -pg +CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg endif diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 67e929b89875..23c2da87df19 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -446,6 +446,12 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) { *irq = gsi; + +#ifdef CONFIG_X86_IO_APIC + if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) + setup_IO_APIC_irq_extra(gsi); +#endif + return 0; } @@ -473,7 +479,8 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) plat_gsi = mp_register_gsi(dev, gsi, trigger, polarity); } #endif - acpi_gsi_to_irq(plat_gsi, &irq); + irq = plat_gsi; + return irq; } @@ -1184,9 +1191,6 @@ static void __init acpi_process_madt(void) if (!error) { acpi_lapic = 1; -#ifdef CONFIG_X86_BIGSMP - generic_bigsmp_probe(); -#endif /* * Parse MADT IO-APIC entries */ @@ -1196,8 +1200,6 @@ static void __init acpi_process_madt(void) acpi_ioapic = 1; smp_found_config = 1; - if (apic->setup_apic_routing) - apic->setup_apic_routing(); } } if (error == -EINVAL) { @@ -1348,14 +1350,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = { }, { .callback = force_acpi_ht, - .ident = "ASUS P2B-DS", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), - DMI_MATCH(DMI_BOARD_NAME, "P2B-DS"), - }, - }, - { - .callback = force_acpi_ht, .ident = "ASUS CUR-DLS", .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 59cdfa4686b2..fb7a5f052e2b 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -48,7 +48,7 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, * P4, Core and beyond CPUs */ if (c->x86_vendor == X86_VENDOR_INTEL && - (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 14))) + (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 0x0f))) flags->bm_control = 0; } EXPORT_SYMBOL(acpi_processor_power_init_bm_check); @@ -145,6 +145,15 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, percpu_entry->states[cx->index].eax = cx->address; percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK; } + + /* + * For _CST FFH on Intel, if GAS.access_size bit 1 is cleared, + * then we should skip checking BM_STS for this C-state. + * ref: "Intel Processor Vendor-Specific ACPI Interface Specification" + */ + if ((c->x86_vendor == X86_VENDOR_INTEL) && !(reg->access_size & 0x2)) + cx->bm_sts_skip = 1; + return retval; } EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe); diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 0285521e0a99..7cd33f75a69c 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -540,11 +540,11 @@ static void flush_all_devices_for_iommu(struct amd_iommu *iommu) static void flush_devices_by_domain(struct protection_domain *domain) { struct amd_iommu *iommu; - int i; + unsigned long i; for (i = 0; i <= amd_iommu_last_bdf; ++i) { if ((domain == NULL && amd_iommu_pd_table[i] == NULL) || - (amd_iommu_pd_table[i] != domain)) + (domain != NULL && amd_iommu_pd_table[i] != domain)) continue; iommu = amd_iommu_rlookup_table[i]; @@ -1230,9 +1230,10 @@ static void __detach_device(struct protection_domain *domain, u16 devid) /* * If we run in passthrough mode the device must be assigned to the - * passthrough domain if it is detached from any other domain + * passthrough domain if it is detached from any other domain. + * Make sure we can deassign from the pt_domain itself. */ - if (iommu_pass_through) { + if (iommu_pass_through && domain != pt_domain) { struct amd_iommu *iommu = amd_iommu_rlookup_table[devid]; __attach_device(iommu, pt_domain, devid); } @@ -1687,6 +1688,7 @@ static void __unmap_single(struct amd_iommu *iommu, size_t size, int dir) { + dma_addr_t flush_addr; dma_addr_t i, start; unsigned int pages; @@ -1694,6 +1696,7 @@ static void __unmap_single(struct amd_iommu *iommu, (dma_addr + size > dma_dom->aperture_size)) return; + flush_addr = dma_addr; pages = iommu_num_pages(dma_addr, size, PAGE_SIZE); dma_addr &= PAGE_MASK; start = dma_addr; @@ -1708,7 +1711,7 @@ static void __unmap_single(struct amd_iommu *iommu, dma_ops_free_addresses(dma_dom, dma_addr, pages); if (amd_iommu_unmap_flush || dma_dom->need_flush) { - iommu_flush_pages(iommu, dma_dom->domain.id, dma_addr, size); + iommu_flush_pages(iommu, dma_dom->domain.id, flush_addr, size); dma_dom->need_flush = false; } } @@ -2047,10 +2050,10 @@ static void prealloc_protection_domains(void) struct pci_dev *dev = NULL; struct dma_ops_domain *dma_dom; struct amd_iommu *iommu; - u16 devid; + u16 devid, __devid; while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { - devid = calc_devid(dev->bus->number, dev->devfn); + __devid = devid = calc_devid(dev->bus->number, dev->devfn); if (devid > amd_iommu_last_bdf) continue; devid = amd_iommu_alias_table[devid]; @@ -2065,6 +2068,10 @@ static void prealloc_protection_domains(void) init_unity_mappings_for_device(dma_dom, devid); dma_dom->target_dev = devid; + attach_device(iommu, &dma_dom->domain, devid); + if (__devid != devid) + attach_device(iommu, &dma_dom->domain, __devid); + list_add_tail(&dma_dom->list, &iommu_pd_list); } } @@ -2079,6 +2086,11 @@ static struct dma_map_ops amd_iommu_dma_ops = { .dma_supported = amd_iommu_dma_supported, }; +void __init amd_iommu_init_api(void) +{ + register_iommu(&amd_iommu_ops); +} + /* * The function which clues the AMD IOMMU driver into dma_ops. */ @@ -2120,8 +2132,6 @@ int __init amd_iommu_init_dma_ops(void) /* Make the driver finally visible to the drivers */ dma_ops = &amd_iommu_dma_ops; - register_iommu(&amd_iommu_ops); - bus_register_notifier(&pci_bus_type, &device_nb); amd_iommu_stats_init(); @@ -2231,9 +2241,7 @@ static void amd_iommu_domain_destroy(struct iommu_domain *dom) free_pagetable(domain); - domain_id_free(domain->id); - - kfree(domain); + protection_domain_free(domain); dom->priv = NULL; } diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index c20001e4f556..400be996de7b 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -136,6 +136,11 @@ LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the system */ /* + * Set to true if ACPI table parsing and hardware intialization went properly + */ +static bool amd_iommu_initialized; + +/* * Pointer to the device table which is shared by all AMD IOMMUs * it is indexed by the PCI device id or the HT unit id and contains * information about the domain the device belongs to as well as the @@ -617,6 +622,13 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu) iommu->last_device = calc_devid(MMIO_GET_BUS(range), MMIO_GET_LD(range)); iommu->evt_msi_num = MMIO_MSI_NUM(misc); + + if (is_rd890_iommu(iommu->dev)) { + pci_read_config_dword(iommu->dev, 0xf0, &iommu->cache_cfg[0]); + pci_read_config_dword(iommu->dev, 0xf4, &iommu->cache_cfg[1]); + pci_read_config_dword(iommu->dev, 0xf8, &iommu->cache_cfg[2]); + pci_read_config_dword(iommu->dev, 0xfc, &iommu->cache_cfg[3]); + } } /* @@ -634,29 +646,9 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu, struct ivhd_entry *e; /* - * First set the recommended feature enable bits from ACPI - * into the IOMMU control registers + * First save the recommended feature enable bits from ACPI */ - h->flags & IVHD_FLAG_HT_TUN_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : - iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); - - h->flags & IVHD_FLAG_PASSPW_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : - iommu_feature_disable(iommu, CONTROL_PASSPW_EN); - - h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : - iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); - - h->flags & IVHD_FLAG_ISOC_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_ISOC_EN) : - iommu_feature_disable(iommu, CONTROL_ISOC_EN); - - /* - * make IOMMU memory accesses cache coherent - */ - iommu_feature_enable(iommu, CONTROL_COHERENT_EN); + iommu->acpi_flags = h->flags; /* * Done. Now parse the device entries @@ -913,6 +905,8 @@ static int __init init_iommu_all(struct acpi_table_header *table) } WARN_ON(p != end); + amd_iommu_initialized = true; + return 0; } @@ -925,7 +919,7 @@ static int __init init_iommu_all(struct acpi_table_header *table) * ****************************************************************************/ -static int __init iommu_setup_msi(struct amd_iommu *iommu) +static int iommu_setup_msi(struct amd_iommu *iommu) { int r; @@ -1082,6 +1076,40 @@ static void init_device_table(void) } } +static void iommu_init_flags(struct amd_iommu *iommu) +{ + iommu->acpi_flags & IVHD_FLAG_HT_TUN_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : + iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); + + iommu->acpi_flags & IVHD_FLAG_PASSPW_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : + iommu_feature_disable(iommu, CONTROL_PASSPW_EN); + + iommu->acpi_flags & IVHD_FLAG_RESPASSPW_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : + iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); + + iommu->acpi_flags & IVHD_FLAG_ISOC_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_ISOC_EN) : + iommu_feature_disable(iommu, CONTROL_ISOC_EN); + + /* + * make IOMMU memory accesses cache coherent + */ + iommu_feature_enable(iommu, CONTROL_COHERENT_EN); +} + +static void iommu_apply_quirks(struct amd_iommu *iommu) +{ + if (is_rd890_iommu(iommu->dev)) { + pci_write_config_dword(iommu->dev, 0xf0, iommu->cache_cfg[0]); + pci_write_config_dword(iommu->dev, 0xf4, iommu->cache_cfg[1]); + pci_write_config_dword(iommu->dev, 0xf8, iommu->cache_cfg[2]); + pci_write_config_dword(iommu->dev, 0xfc, iommu->cache_cfg[3]); + } +} + /* * This function finally enables all IOMMUs found in the system after * they have been initialized @@ -1092,6 +1120,8 @@ static void enable_iommus(void) for_each_iommu(iommu) { iommu_disable(iommu); + iommu_apply_quirks(iommu); + iommu_init_flags(iommu); iommu_set_device_table(iommu); iommu_enable_command_buffer(iommu); iommu_enable_event_buffer(iommu); @@ -1263,6 +1293,9 @@ int __init amd_iommu_init(void) if (acpi_table_parse("IVRS", init_iommu_all) != 0) goto free; + if (!amd_iommu_initialized) + goto free; + if (acpi_table_parse("IVRS", init_memory_definitions) != 0) goto free; @@ -1274,14 +1307,17 @@ int __init amd_iommu_init(void) if (ret) goto free; + enable_iommus(); + if (iommu_pass_through) ret = amd_iommu_init_passthrough(); else ret = amd_iommu_init_dma_ops(); + if (ret) goto free; - enable_iommus(); + amd_iommu_init_api(); if (iommu_pass_through) goto out; @@ -1301,6 +1337,8 @@ out: return ret; free: + disable_iommus(); + free_pages((unsigned long)amd_iommu_pd_alloc_bitmap, get_order(MAX_DOMAIN_ID/8)); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 128111d8ffe0..082089ec5594 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -389,6 +389,7 @@ void __init gart_iommu_hole_init(void) for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { int bus; int dev_base, dev_limit; + u32 ctl; bus = bus_dev_ranges[i].bus; dev_base = bus_dev_ranges[i].dev_base; @@ -401,7 +402,19 @@ void __init gart_iommu_hole_init(void) iommu_detected = 1; gart_iommu_aperture = 1; - aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 1) & 7; + ctl = read_pci_config(bus, slot, 3, + AMD64_GARTAPERTURECTL); + + /* + * Before we do anything else disable the GART. It may + * still be enabled if we boot into a crash-kernel here. + * Reconfiguring the GART while it is enabled could have + * unknown side-effects. + */ + ctl &= ~GARTEN; + write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl); + + aper_order = (ctl >> 1) & 7; aper_size = (32 * 1024 * 1024) << aper_order; aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff; aper_base <<= 25; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 894aa97f0717..6702ab74c58c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -51,6 +51,7 @@ #include <asm/smp.h> #include <asm/mce.h> #include <asm/kvm_para.h> +#include <asm/tsc.h> unsigned int num_processors; @@ -246,7 +247,7 @@ static int modern_apic(void) */ static void native_apic_write_dummy(u32 reg, u32 v) { - WARN_ON_ONCE((cpu_has_apic || !disable_apic)); + WARN_ON_ONCE(cpu_has_apic && !disable_apic); } static u32 native_apic_read_dummy(u32 reg) @@ -941,7 +942,7 @@ void disable_local_APIC(void) unsigned int value; /* APIC hasn't been mapped yet */ - if (!apic_phys) + if (!x2apic_mode && !apic_phys) return; clear_local_APIC(); @@ -1172,8 +1173,13 @@ static void __cpuinit lapic_setup_esr(void) */ void __cpuinit setup_local_APIC(void) { - unsigned int value; - int i, j; + unsigned int value, queued; + int i, j, acked = 0; + unsigned long long tsc = 0, ntsc; + long long max_loops = cpu_khz; + + if (cpu_has_tsc) + rdtscll(tsc); if (disable_apic) { arch_disable_smp_support(); @@ -1225,13 +1231,32 @@ void __cpuinit setup_local_APIC(void) * the interrupt. Hence a vector might get locked. It was noticed * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. */ - for (i = APIC_ISR_NR - 1; i >= 0; i--) { - value = apic_read(APIC_ISR + i*0x10); - for (j = 31; j >= 0; j--) { - if (value & (1<<j)) - ack_APIC_irq(); + do { + queued = 0; + for (i = APIC_ISR_NR - 1; i >= 0; i--) + queued |= apic_read(APIC_IRR + i*0x10); + + for (i = APIC_ISR_NR - 1; i >= 0; i--) { + value = apic_read(APIC_ISR + i*0x10); + for (j = 31; j >= 0; j--) { + if (value & (1<<j)) { + ack_APIC_irq(); + acked++; + } + } } - } + if (acked > 256) { + printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n", + acked); + break; + } + if (cpu_has_tsc) { + rdtscll(ntsc); + max_loops = (cpu_khz << 10) - (ntsc - tsc); + } else + max_loops--; + } while (queued && max_loops > 0); + WARN_ON(max_loops <= 0); /* * Now that we are all set up, enable the APIC @@ -1664,8 +1689,8 @@ int __init APIC_init_uniprocessor(void) } #endif +#ifndef CONFIG_SMP enable_IR_x2apic(); -#ifdef CONFIG_X86_64 default_setup_apic_routing(); #endif @@ -1915,18 +1940,6 @@ void __cpuinit generic_processor_info(int apicid, int version) if (apicid > max_physical_apicid) max_physical_apicid = apicid; -#ifdef CONFIG_X86_32 - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_INTEL: - if (num_processors > 8) - def_to_bigsmp = 1; - break; - case X86_VENDOR_AMD: - if (max_physical_apicid >= 8) - def_to_bigsmp = 1; - } -#endif - #if defined(CONFIG_SMP) || defined(CONFIG_X86_64) early_per_cpu(x86_cpu_to_apicid, cpu) = apicid; early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid; diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index d0c99abc26c3..873f81f0bbd8 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -240,6 +240,11 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) printk(KERN_DEBUG "system APIC only can use physical flat"); return 1; } + + if (!strncmp(oem_id, "IBM", 3) && !strncmp(oem_table_id, "EXA", 3)) { + printk(KERN_DEBUG "IBM Summit detected, will use apic physical"); + return 1; + } #endif return 0; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index dc69f28489f5..420e43ed9719 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -332,14 +332,19 @@ void arch_init_copy_chip_data(struct irq_desc *old_desc, old_cfg = old_desc->chip_data; - memcpy(cfg, old_cfg, sizeof(struct irq_cfg)); + cfg->vector = old_cfg->vector; + cfg->move_in_progress = old_cfg->move_in_progress; + cpumask_copy(cfg->domain, old_cfg->domain); + cpumask_copy(cfg->old_domain, old_cfg->old_domain); init_copy_irq_2_pin(old_cfg, cfg, node); } -static void free_irq_cfg(struct irq_cfg *old_cfg) +static void free_irq_cfg(struct irq_cfg *cfg) { - kfree(old_cfg); + free_cpumask_var(cfg->domain); + free_cpumask_var(cfg->old_domain); + kfree(cfg); } void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc) @@ -1484,7 +1489,7 @@ static struct { static void __init setup_IO_APIC_irqs(void) { - int apic_id = 0, pin, idx, irq; + int apic_id, pin, idx, irq; int notcon = 0; struct irq_desc *desc; struct irq_cfg *cfg; @@ -1492,14 +1497,7 @@ static void __init setup_IO_APIC_irqs(void) apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); -#ifdef CONFIG_ACPI - if (!acpi_disabled && acpi_ioapic) { - apic_id = mp_find_ioapic(0); - if (apic_id < 0) - apic_id = 0; - } -#endif - + for (apic_id = 0; apic_id < nr_ioapics; apic_id++) for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) { idx = find_irq_entry(apic_id, pin, mp_INT); if (idx == -1) { @@ -1521,6 +1519,9 @@ static void __init setup_IO_APIC_irqs(void) irq = pin_2_irq(idx, apic_id, pin); + if ((apic_id > 0) && (irq > 16)) + continue; + /* * Skip the timer IRQ if there's a quirk handler * installed and if it returns 1: @@ -1550,6 +1551,56 @@ static void __init setup_IO_APIC_irqs(void) } /* + * for the gsit that is not in first ioapic + * but could not use acpi_register_gsi() + * like some special sci in IBM x3330 + */ +void setup_IO_APIC_irq_extra(u32 gsi) +{ + int apic_id = 0, pin, idx, irq; + int node = cpu_to_node(boot_cpu_id); + struct irq_desc *desc; + struct irq_cfg *cfg; + + /* + * Convert 'gsi' to 'ioapic.pin'. + */ + apic_id = mp_find_ioapic(gsi); + if (apic_id < 0) + return; + + pin = mp_find_ioapic_pin(apic_id, gsi); + idx = find_irq_entry(apic_id, pin, mp_INT); + if (idx == -1) + return; + + irq = pin_2_irq(idx, apic_id, pin); +#ifdef CONFIG_SPARSE_IRQ + desc = irq_to_desc(irq); + if (desc) + return; +#endif + desc = irq_to_desc_alloc_node(irq, node); + if (!desc) { + printk(KERN_INFO "can not get irq_desc for %d\n", irq); + return; + } + + cfg = desc->chip_data; + add_pin_to_irq_node(cfg, node, apic_id, pin); + + if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) { + pr_debug("Pin %d-%d already programmed\n", + mp_ioapics[apic_id].apicid, pin); + return; + } + set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed); + + setup_IO_APIC_irq(apic_id, pin, irq, desc, + irq_trigger(idx), irq_polarity(idx)); +} + +/* * Set up the timer pin, possibly with the 8259A-master behind. */ static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin, @@ -1690,6 +1741,8 @@ __apicdebuginit(void) print_IO_APIC(void) struct irq_pin_list *entry; cfg = desc->chip_data; + if (!cfg) + continue; entry = cfg->irq_2_pin; if (!entry) continue; @@ -3157,6 +3210,7 @@ unsigned int create_irq_nr(unsigned int irq_want, int node) continue; desc_new = move_irq_desc(desc_new, node); + cfg_new = desc_new->chip_data; if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0) irq = new; @@ -3164,12 +3218,9 @@ unsigned int create_irq_nr(unsigned int irq_want, int node) } spin_unlock_irqrestore(&vector_lock, flags); - if (irq > 0) { - dynamic_irq_init(irq); - /* restore it, in case dynamic_irq_init clear it */ - if (desc_new) - desc_new->chip_data = cfg_new; - } + if (irq > 0) + dynamic_irq_init_keep_chip_data(irq); + return irq; } @@ -3192,17 +3243,12 @@ void destroy_irq(unsigned int irq) { unsigned long flags; struct irq_cfg *cfg; - struct irq_desc *desc; - /* store it, in case dynamic_irq_cleanup clear it */ - desc = irq_to_desc(irq); - cfg = desc->chip_data; - dynamic_irq_cleanup(irq); - /* connect back irq_cfg */ - desc->chip_data = cfg; + dynamic_irq_cleanup_keep_chip_data(irq); free_irte(irq); spin_lock_irqsave(&vector_lock, flags); + cfg = irq_to_desc(irq)->chip_data; __clear_irq_vector(irq, cfg); spin_unlock_irqrestore(&vector_lock, flags); } @@ -3297,7 +3343,7 @@ static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask) cfg = desc->chip_data; - read_msi_msg_desc(desc, &msg); + get_cached_msi_msg_desc(desc, &msg); msg.data &= ~MSI_DATA_VECTOR_MASK; msg.data |= MSI_DATA_VECTOR(cfg->vector); @@ -4040,27 +4086,23 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity) #ifdef CONFIG_SMP void __init setup_ioapic_dest(void) { - int pin, ioapic = 0, irq, irq_entry; + int pin, ioapic, irq, irq_entry; struct irq_desc *desc; const struct cpumask *mask; if (skip_ioapic_setup == 1) return; -#ifdef CONFIG_ACPI - if (!acpi_disabled && acpi_ioapic) { - ioapic = mp_find_ioapic(0); - if (ioapic < 0) - ioapic = 0; - } -#endif - + for (ioapic = 0; ioapic < nr_ioapics; ioapic++) for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) { irq_entry = find_irq_entry(ioapic, pin, mp_INT); if (irq_entry == -1) continue; irq = pin_2_irq(irq_entry, ioapic, pin); + if ((ioapic > 0) && (irq > 16)) + continue; + desc = irq_to_desc(irq); /* diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 0c0182cc947d..88b9d22c8432 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -54,6 +54,31 @@ late_initcall(print_ipi_mode); void default_setup_apic_routing(void) { + int version = apic_version[boot_cpu_physical_apicid]; + + if (num_possible_cpus() > 8) { + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + if (!APIC_XAPIC(version)) { + def_to_bigsmp = 0; + break; + } + /* If P4 and above fall through */ + case X86_VENDOR_AMD: + def_to_bigsmp = 1; + } + } + +#ifdef CONFIG_X86_BIGSMP + generic_bigsmp_probe(); +#endif + + if (apic->setup_apic_routing) + apic->setup_apic_routing(); +} + +void setup_apic_flat_routing(void) +{ #ifdef CONFIG_X86_IO_APIC printk(KERN_INFO "Enabling APIC mode: Flat. Using %d I/O APICs\n", @@ -103,7 +128,7 @@ struct apic apic_default = { .init_apic_ldr = default_init_apic_ldr, .ioapic_phys_id_map = default_ioapic_phys_id_map, - .setup_apic_routing = default_setup_apic_routing, + .setup_apic_routing = setup_apic_flat_routing, .multi_timer_check = NULL, .apicid_to_node = default_apicid_to_node, .cpu_to_logical_apicid = default_cpu_to_logical_apicid, diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index c4cbd3080c1c..4c56f544f167 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -67,17 +67,8 @@ void __init default_setup_apic_routing(void) } #endif - if (apic == &apic_flat) { - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_INTEL: - if (num_processors > 8) - apic = &apic_physflat; - break; - case X86_VENDOR_AMD: - if (max_physical_apicid >= 8) - apic = &apic_physflat; - } - } + if (apic == &apic_flat && num_possible_cpus() > 8) + apic = &apic_physflat; printk(KERN_INFO "Setting APIC routing to %s\n", apic->name); diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 326c25477d3d..9ee87cfe0859 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -364,13 +364,13 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size) enum map_type {map_wb, map_uc}; -static __init void map_high(char *id, unsigned long base, int shift, - int max_pnode, enum map_type map_type) +static __init void map_high(char *id, unsigned long base, int pshift, + int bshift, int max_pnode, enum map_type map_type) { unsigned long bytes, paddr; - paddr = base << shift; - bytes = (1UL << shift) * (max_pnode + 1); + paddr = base << pshift; + bytes = (1UL << bshift) * (max_pnode + 1); printk(KERN_INFO "UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr, paddr + bytes); if (map_type == map_uc) @@ -386,7 +386,7 @@ static __init void map_gru_high(int max_pnode) gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR); if (gru.s.enable) - map_high("GRU", gru.s.base, shift, max_pnode, map_wb); + map_high("GRU", gru.s.base, shift, shift, max_pnode, map_wb); } static __init void map_mmr_high(int max_pnode) @@ -396,7 +396,7 @@ static __init void map_mmr_high(int max_pnode) mmr.v = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR); if (mmr.s.enable) - map_high("MMR", mmr.s.base, shift, max_pnode, map_uc); + map_high("MMR", mmr.s.base, shift, shift, max_pnode, map_uc); } static __init void map_mmioh_high(int max_pnode) @@ -406,7 +406,8 @@ static __init void map_mmioh_high(int max_pnode) mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR); if (mmioh.s.enable) - map_high("MMIOH", mmioh.s.base, shift, max_pnode, map_uc); + map_high("MMIOH", mmioh.s.base, shift, mmioh.s.m_io, + max_pnode, map_uc); } static __init void uv_rtc_init(void) @@ -607,8 +608,10 @@ void __init uv_system_init(void) uv_rtc_init(); for_each_present_cpu(cpu) { + int apicid = per_cpu(x86_cpu_to_apicid, cpu); + nid = cpu_to_node(cpu); - pnode = uv_apicid_to_pnode(per_cpu(x86_cpu_to_apicid, cpu)); + pnode = uv_apicid_to_pnode(apicid); blade = boot_pnode_to_blade(pnode); lcpu = uv_blade_info[blade].nr_possible_cpus; uv_blade_info[blade].nr_possible_cpus++; @@ -629,15 +632,13 @@ void __init uv_system_init(void) uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra; uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base; uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id; - uv_cpu_hub_info(cpu)->scir.offset = SCIR_LOCAL_MMR_BASE + lcpu; + uv_cpu_hub_info(cpu)->scir.offset = uv_scir_offset(apicid); uv_node_to_blade[nid] = blade; uv_cpu_to_blade[cpu] = blade; max_pnode = max(pnode, max_pnode); - printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, " - "lcpu %d, blade %d\n", - cpu, per_cpu(x86_cpu_to_apicid, cpu), pnode, nid, - lcpu, blade); + printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, lcpu %d, blade %d\n", + cpu, apicid, pnode, nid, lcpu, blade); } /* Add blade/pnode info for nodes without cpus */ diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 68537e957a9b..ff502cc59d2f 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -18,8 +18,6 @@ obj-y += vmware.o hypervisor.o sched.o obj-$(CONFIG_X86_32) += bugs.o cmpxchg.o obj-$(CONFIG_X86_64) += bugs_64.o -obj-$(CONFIG_X86_CPU_DEBUG) += cpu_debug.o - obj-$(CONFIG_CPU_SUP_INTEL) += intel.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index c910a716a71c..3940fee7ea9f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -254,59 +254,36 @@ static int __cpuinit nearby_node(int apicid) /* * Fixup core topology information for AMD multi-node processors. - * Assumption 1: Number of cores in each internal node is the same. - * Assumption 2: Mixed systems with both single-node and dual-node - * processors are not supported. + * Assumption: Number of cores in each internal node is the same. */ #ifdef CONFIG_X86_HT static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c) { -#ifdef CONFIG_PCI - u32 t, cpn; - u8 n, n_id; + unsigned long long value; + u32 nodes, cores_per_node; int cpu = smp_processor_id(); + if (!cpu_has(c, X86_FEATURE_NODEID_MSR)) + return; + /* fixup topology information only once for a core */ if (cpu_has(c, X86_FEATURE_AMD_DCM)) return; - /* check for multi-node processor on boot cpu */ - t = read_pci_config(0, 24, 3, 0xe8); - if (!(t & (1 << 29))) + rdmsrl(MSR_FAM10H_NODE_ID, value); + + nodes = ((value >> 3) & 7) + 1; + if (nodes == 1) return; set_cpu_cap(c, X86_FEATURE_AMD_DCM); + cores_per_node = c->x86_max_cores / nodes; - /* cores per node: each internal node has half the number of cores */ - cpn = c->x86_max_cores >> 1; + /* store NodeID, use llc_shared_map to store sibling info */ + per_cpu(cpu_llc_id, cpu) = value & 7; - /* even-numbered NB_id of this dual-node processor */ - n = c->phys_proc_id << 1; - - /* - * determine internal node id and assign cores fifty-fifty to - * each node of the dual-node processor - */ - t = read_pci_config(0, 24 + n, 3, 0xe8); - n = (t>>30) & 0x3; - if (n == 0) { - if (c->cpu_core_id < cpn) - n_id = 0; - else - n_id = 1; - } else { - if (c->cpu_core_id < cpn) - n_id = 1; - else - n_id = 0; - } - - /* compute entire NodeID, use llc_shared_map to store sibling info */ - per_cpu(cpu_llc_id, cpu) = (c->phys_proc_id << 1) + n_id; - - /* fixup core id to be in range from 0 to cpn */ - c->cpu_core_id = c->cpu_core_id % cpn; -#endif + /* fixup core id to be in range from 0 to (cores_per_node - 1) */ + c->cpu_core_id = c->cpu_core_id % cores_per_node; } #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index cc25c2b4a567..4e34d10b841f 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -540,7 +540,7 @@ void __cpuinit cpu_detect(struct cpuinfo_x86 *c) } } -static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) +void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) { u32 tfms, xlvl; u32 ebx; @@ -579,6 +579,7 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000007) c->x86_power = cpuid_edx(0x80000007); + init_scattered_cpuid_features(c); } static void __cpuinit identify_cpu_without_cpuid(struct cpuinfo_x86 *c) @@ -727,7 +728,6 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c) get_model_name(c); /* Default name */ - init_scattered_cpuid_features(c); detect_nopl(c); } diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 6de9a908e400..eb19c0800044 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -33,5 +33,6 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; extern void display_cacheinfo(struct cpuinfo_x86 *c); +extern void get_cpu_cap(struct cpuinfo_x86 *c); #endif diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c deleted file mode 100644 index dca325c03999..000000000000 --- a/arch/x86/kernel/cpu/cpu_debug.c +++ /dev/null @@ -1,688 +0,0 @@ -/* - * CPU x86 architecture debug code - * - * Copyright(C) 2009 Jaswinder Singh Rajput - * - * For licencing details see kernel-base/COPYING - */ - -#include <linux/interrupt.h> -#include <linux/compiler.h> -#include <linux/seq_file.h> -#include <linux/debugfs.h> -#include <linux/kprobes.h> -#include <linux/uaccess.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/percpu.h> -#include <linux/signal.h> -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/types.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/smp.h> - -#include <asm/cpu_debug.h> -#include <asm/paravirt.h> -#include <asm/system.h> -#include <asm/traps.h> -#include <asm/apic.h> -#include <asm/desc.h> - -static DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpu_arr); -static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], priv_arr); -static DEFINE_PER_CPU(int, cpu_priv_count); - -static DEFINE_MUTEX(cpu_debug_lock); - -static struct dentry *cpu_debugfs_dir; - -static struct cpu_debug_base cpu_base[] = { - { "mc", CPU_MC, 0 }, - { "monitor", CPU_MONITOR, 0 }, - { "time", CPU_TIME, 0 }, - { "pmc", CPU_PMC, 1 }, - { "platform", CPU_PLATFORM, 0 }, - { "apic", CPU_APIC, 0 }, - { "poweron", CPU_POWERON, 0 }, - { "control", CPU_CONTROL, 0 }, - { "features", CPU_FEATURES, 0 }, - { "lastbranch", CPU_LBRANCH, 0 }, - { "bios", CPU_BIOS, 0 }, - { "freq", CPU_FREQ, 0 }, - { "mtrr", CPU_MTRR, 0 }, - { "perf", CPU_PERF, 0 }, - { "cache", CPU_CACHE, 0 }, - { "sysenter", CPU_SYSENTER, 0 }, - { "therm", CPU_THERM, 0 }, - { "misc", CPU_MISC, 0 }, - { "debug", CPU_DEBUG, 0 }, - { "pat", CPU_PAT, 0 }, - { "vmx", CPU_VMX, 0 }, - { "call", CPU_CALL, 0 }, - { "base", CPU_BASE, 0 }, - { "ver", CPU_VER, 0 }, - { "conf", CPU_CONF, 0 }, - { "smm", CPU_SMM, 0 }, - { "svm", CPU_SVM, 0 }, - { "osvm", CPU_OSVM, 0 }, - { "tss", CPU_TSS, 0 }, - { "cr", CPU_CR, 0 }, - { "dt", CPU_DT, 0 }, - { "registers", CPU_REG_ALL, 0 }, -}; - -static struct cpu_file_base cpu_file[] = { - { "index", CPU_REG_ALL, 0 }, - { "value", CPU_REG_ALL, 1 }, -}; - -/* CPU Registers Range */ -static struct cpu_debug_range cpu_reg_range[] = { - { 0x00000000, 0x00000001, CPU_MC, }, - { 0x00000006, 0x00000007, CPU_MONITOR, }, - { 0x00000010, 0x00000010, CPU_TIME, }, - { 0x00000011, 0x00000013, CPU_PMC, }, - { 0x00000017, 0x00000017, CPU_PLATFORM, }, - { 0x0000001B, 0x0000001B, CPU_APIC, }, - { 0x0000002A, 0x0000002B, CPU_POWERON, }, - { 0x0000002C, 0x0000002C, CPU_FREQ, }, - { 0x0000003A, 0x0000003A, CPU_CONTROL, }, - { 0x00000040, 0x00000047, CPU_LBRANCH, }, - { 0x00000060, 0x00000067, CPU_LBRANCH, }, - { 0x00000079, 0x00000079, CPU_BIOS, }, - { 0x00000088, 0x0000008A, CPU_CACHE, }, - { 0x0000008B, 0x0000008B, CPU_BIOS, }, - { 0x0000009B, 0x0000009B, CPU_MONITOR, }, - { 0x000000C1, 0x000000C4, CPU_PMC, }, - { 0x000000CD, 0x000000CD, CPU_FREQ, }, - { 0x000000E7, 0x000000E8, CPU_PERF, }, - { 0x000000FE, 0x000000FE, CPU_MTRR, }, - - { 0x00000116, 0x0000011E, CPU_CACHE, }, - { 0x00000174, 0x00000176, CPU_SYSENTER, }, - { 0x00000179, 0x0000017B, CPU_MC, }, - { 0x00000186, 0x00000189, CPU_PMC, }, - { 0x00000198, 0x00000199, CPU_PERF, }, - { 0x0000019A, 0x0000019A, CPU_TIME, }, - { 0x0000019B, 0x0000019D, CPU_THERM, }, - { 0x000001A0, 0x000001A0, CPU_MISC, }, - { 0x000001C9, 0x000001C9, CPU_LBRANCH, }, - { 0x000001D7, 0x000001D8, CPU_LBRANCH, }, - { 0x000001D9, 0x000001D9, CPU_DEBUG, }, - { 0x000001DA, 0x000001E0, CPU_LBRANCH, }, - - { 0x00000200, 0x0000020F, CPU_MTRR, }, - { 0x00000250, 0x00000250, CPU_MTRR, }, - { 0x00000258, 0x00000259, CPU_MTRR, }, - { 0x00000268, 0x0000026F, CPU_MTRR, }, - { 0x00000277, 0x00000277, CPU_PAT, }, - { 0x000002FF, 0x000002FF, CPU_MTRR, }, - - { 0x00000300, 0x00000311, CPU_PMC, }, - { 0x00000345, 0x00000345, CPU_PMC, }, - { 0x00000360, 0x00000371, CPU_PMC, }, - { 0x0000038D, 0x00000390, CPU_PMC, }, - { 0x000003A0, 0x000003BE, CPU_PMC, }, - { 0x000003C0, 0x000003CD, CPU_PMC, }, - { 0x000003E0, 0x000003E1, CPU_PMC, }, - { 0x000003F0, 0x000003F2, CPU_PMC, }, - - { 0x00000400, 0x00000417, CPU_MC, }, - { 0x00000480, 0x0000048B, CPU_VMX, }, - - { 0x00000600, 0x00000600, CPU_DEBUG, }, - { 0x00000680, 0x0000068F, CPU_LBRANCH, }, - { 0x000006C0, 0x000006CF, CPU_LBRANCH, }, - - { 0x000107CC, 0x000107D3, CPU_PMC, }, - - { 0xC0000080, 0xC0000080, CPU_FEATURES, }, - { 0xC0000081, 0xC0000084, CPU_CALL, }, - { 0xC0000100, 0xC0000102, CPU_BASE, }, - { 0xC0000103, 0xC0000103, CPU_TIME, }, - - { 0xC0010000, 0xC0010007, CPU_PMC, }, - { 0xC0010010, 0xC0010010, CPU_CONF, }, - { 0xC0010015, 0xC0010015, CPU_CONF, }, - { 0xC0010016, 0xC001001A, CPU_MTRR, }, - { 0xC001001D, 0xC001001D, CPU_MTRR, }, - { 0xC001001F, 0xC001001F, CPU_CONF, }, - { 0xC0010030, 0xC0010035, CPU_BIOS, }, - { 0xC0010044, 0xC0010048, CPU_MC, }, - { 0xC0010050, 0xC0010056, CPU_SMM, }, - { 0xC0010058, 0xC0010058, CPU_CONF, }, - { 0xC0010060, 0xC0010060, CPU_CACHE, }, - { 0xC0010061, 0xC0010068, CPU_SMM, }, - { 0xC0010069, 0xC001006B, CPU_SMM, }, - { 0xC0010070, 0xC0010071, CPU_SMM, }, - { 0xC0010111, 0xC0010113, CPU_SMM, }, - { 0xC0010114, 0xC0010118, CPU_SVM, }, - { 0xC0010140, 0xC0010141, CPU_OSVM, }, - { 0xC0011022, 0xC0011023, CPU_CONF, }, -}; - -static int is_typeflag_valid(unsigned cpu, unsigned flag) -{ - int i; - - /* Standard Registers should be always valid */ - if (flag >= CPU_TSS) - return 1; - - for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) { - if (cpu_reg_range[i].flag == flag) - return 1; - } - - /* Invalid */ - return 0; -} - -static unsigned get_cpu_range(unsigned cpu, unsigned *min, unsigned *max, - int index, unsigned flag) -{ - if (cpu_reg_range[index].flag == flag) { - *min = cpu_reg_range[index].min; - *max = cpu_reg_range[index].max; - } else - *max = 0; - - return *max; -} - -/* This function can also be called with seq = NULL for printk */ -static void print_cpu_data(struct seq_file *seq, unsigned type, - u32 low, u32 high) -{ - struct cpu_private *priv; - u64 val = high; - - if (seq) { - priv = seq->private; - if (priv->file) { - val = (val << 32) | low; - seq_printf(seq, "0x%llx\n", val); - } else - seq_printf(seq, " %08x: %08x_%08x\n", - type, high, low); - } else - printk(KERN_INFO " %08x: %08x_%08x\n", type, high, low); -} - -/* This function can also be called with seq = NULL for printk */ -static void print_msr(struct seq_file *seq, unsigned cpu, unsigned flag) -{ - unsigned msr, msr_min, msr_max; - struct cpu_private *priv; - u32 low, high; - int i; - - if (seq) { - priv = seq->private; - if (priv->file) { - if (!rdmsr_safe_on_cpu(priv->cpu, priv->reg, - &low, &high)) - print_cpu_data(seq, priv->reg, low, high); - return; - } - } - - for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) { - if (!get_cpu_range(cpu, &msr_min, &msr_max, i, flag)) - continue; - - for (msr = msr_min; msr <= msr_max; msr++) { - if (rdmsr_safe_on_cpu(cpu, msr, &low, &high)) - continue; - print_cpu_data(seq, msr, low, high); - } - } -} - -static void print_tss(void *arg) -{ - struct pt_regs *regs = task_pt_regs(current); - struct seq_file *seq = arg; - unsigned int seg; - - seq_printf(seq, " RAX\t: %016lx\n", regs->ax); - seq_printf(seq, " RBX\t: %016lx\n", regs->bx); - seq_printf(seq, " RCX\t: %016lx\n", regs->cx); - seq_printf(seq, " RDX\t: %016lx\n", regs->dx); - - seq_printf(seq, " RSI\t: %016lx\n", regs->si); - seq_printf(seq, " RDI\t: %016lx\n", regs->di); - seq_printf(seq, " RBP\t: %016lx\n", regs->bp); - seq_printf(seq, " ESP\t: %016lx\n", regs->sp); - -#ifdef CONFIG_X86_64 - seq_printf(seq, " R08\t: %016lx\n", regs->r8); - seq_printf(seq, " R09\t: %016lx\n", regs->r9); - seq_printf(seq, " R10\t: %016lx\n", regs->r10); - seq_printf(seq, " R11\t: %016lx\n", regs->r11); - seq_printf(seq, " R12\t: %016lx\n", regs->r12); - seq_printf(seq, " R13\t: %016lx\n", regs->r13); - seq_printf(seq, " R14\t: %016lx\n", regs->r14); - seq_printf(seq, " R15\t: %016lx\n", regs->r15); -#endif - - asm("movl %%cs,%0" : "=r" (seg)); - seq_printf(seq, " CS\t: %04x\n", seg); - asm("movl %%ds,%0" : "=r" (seg)); - seq_printf(seq, " DS\t: %04x\n", seg); - seq_printf(seq, " SS\t: %04lx\n", regs->ss & 0xffff); - asm("movl %%es,%0" : "=r" (seg)); - seq_printf(seq, " ES\t: %04x\n", seg); - asm("movl %%fs,%0" : "=r" (seg)); - seq_printf(seq, " FS\t: %04x\n", seg); - asm("movl %%gs,%0" : "=r" (seg)); - seq_printf(seq, " GS\t: %04x\n", seg); - - seq_printf(seq, " EFLAGS\t: %016lx\n", regs->flags); - - seq_printf(seq, " EIP\t: %016lx\n", regs->ip); -} - -static void print_cr(void *arg) -{ - struct seq_file *seq = arg; - - seq_printf(seq, " cr0\t: %016lx\n", read_cr0()); - seq_printf(seq, " cr2\t: %016lx\n", read_cr2()); - seq_printf(seq, " cr3\t: %016lx\n", read_cr3()); - seq_printf(seq, " cr4\t: %016lx\n", read_cr4_safe()); -#ifdef CONFIG_X86_64 - seq_printf(seq, " cr8\t: %016lx\n", read_cr8()); -#endif -} - -static void print_desc_ptr(char *str, struct seq_file *seq, struct desc_ptr dt) -{ - seq_printf(seq, " %s\t: %016llx\n", str, (u64)(dt.address | dt.size)); -} - -static void print_dt(void *seq) -{ - struct desc_ptr dt; - unsigned long ldt; - - /* IDT */ - store_idt((struct desc_ptr *)&dt); - print_desc_ptr("IDT", seq, dt); - - /* GDT */ - store_gdt((struct desc_ptr *)&dt); - print_desc_ptr("GDT", seq, dt); - - /* LDT */ - store_ldt(ldt); - seq_printf(seq, " LDT\t: %016lx\n", ldt); - - /* TR */ - store_tr(ldt); - seq_printf(seq, " TR\t: %016lx\n", ldt); -} - -static void print_dr(void *arg) -{ - struct seq_file *seq = arg; - unsigned long dr; - int i; - - for (i = 0; i < 8; i++) { - /* Ignore db4, db5 */ - if ((i == 4) || (i == 5)) - continue; - get_debugreg(dr, i); - seq_printf(seq, " dr%d\t: %016lx\n", i, dr); - } - - seq_printf(seq, "\n MSR\t:\n"); -} - -static void print_apic(void *arg) -{ - struct seq_file *seq = arg; - -#ifdef CONFIG_X86_LOCAL_APIC - seq_printf(seq, " LAPIC\t:\n"); - seq_printf(seq, " ID\t\t: %08x\n", apic_read(APIC_ID) >> 24); - seq_printf(seq, " LVR\t\t: %08x\n", apic_read(APIC_LVR)); - seq_printf(seq, " TASKPRI\t: %08x\n", apic_read(APIC_TASKPRI)); - seq_printf(seq, " ARBPRI\t\t: %08x\n", apic_read(APIC_ARBPRI)); - seq_printf(seq, " PROCPRI\t: %08x\n", apic_read(APIC_PROCPRI)); - seq_printf(seq, " LDR\t\t: %08x\n", apic_read(APIC_LDR)); - seq_printf(seq, " DFR\t\t: %08x\n", apic_read(APIC_DFR)); - seq_printf(seq, " SPIV\t\t: %08x\n", apic_read(APIC_SPIV)); - seq_printf(seq, " ISR\t\t: %08x\n", apic_read(APIC_ISR)); - seq_printf(seq, " ESR\t\t: %08x\n", apic_read(APIC_ESR)); - seq_printf(seq, " ICR\t\t: %08x\n", apic_read(APIC_ICR)); - seq_printf(seq, " ICR2\t\t: %08x\n", apic_read(APIC_ICR2)); - seq_printf(seq, " LVTT\t\t: %08x\n", apic_read(APIC_LVTT)); - seq_printf(seq, " LVTTHMR\t: %08x\n", apic_read(APIC_LVTTHMR)); - seq_printf(seq, " LVTPC\t\t: %08x\n", apic_read(APIC_LVTPC)); - seq_printf(seq, " LVT0\t\t: %08x\n", apic_read(APIC_LVT0)); - seq_printf(seq, " LVT1\t\t: %08x\n", apic_read(APIC_LVT1)); - seq_printf(seq, " LVTERR\t\t: %08x\n", apic_read(APIC_LVTERR)); - seq_printf(seq, " TMICT\t\t: %08x\n", apic_read(APIC_TMICT)); - seq_printf(seq, " TMCCT\t\t: %08x\n", apic_read(APIC_TMCCT)); - seq_printf(seq, " TDCR\t\t: %08x\n", apic_read(APIC_TDCR)); - if (boot_cpu_has(X86_FEATURE_EXTAPIC)) { - unsigned int i, v, maxeilvt; - - v = apic_read(APIC_EFEAT); - maxeilvt = (v >> 16) & 0xff; - seq_printf(seq, " EFEAT\t\t: %08x\n", v); - seq_printf(seq, " ECTRL\t\t: %08x\n", apic_read(APIC_ECTRL)); - - for (i = 0; i < maxeilvt; i++) { - v = apic_read(APIC_EILVTn(i)); - seq_printf(seq, " EILVT%d\t\t: %08x\n", i, v); - } - } -#endif /* CONFIG_X86_LOCAL_APIC */ - seq_printf(seq, "\n MSR\t:\n"); -} - -static int cpu_seq_show(struct seq_file *seq, void *v) -{ - struct cpu_private *priv = seq->private; - - if (priv == NULL) - return -EINVAL; - - switch (cpu_base[priv->type].flag) { - case CPU_TSS: - smp_call_function_single(priv->cpu, print_tss, seq, 1); - break; - case CPU_CR: - smp_call_function_single(priv->cpu, print_cr, seq, 1); - break; - case CPU_DT: - smp_call_function_single(priv->cpu, print_dt, seq, 1); - break; - case CPU_DEBUG: - if (priv->file == CPU_INDEX_BIT) - smp_call_function_single(priv->cpu, print_dr, seq, 1); - print_msr(seq, priv->cpu, cpu_base[priv->type].flag); - break; - case CPU_APIC: - if (priv->file == CPU_INDEX_BIT) - smp_call_function_single(priv->cpu, print_apic, seq, 1); - print_msr(seq, priv->cpu, cpu_base[priv->type].flag); - break; - - default: - print_msr(seq, priv->cpu, cpu_base[priv->type].flag); - break; - } - seq_printf(seq, "\n"); - - return 0; -} - -static void *cpu_seq_start(struct seq_file *seq, loff_t *pos) -{ - if (*pos == 0) /* One time is enough ;-) */ - return seq; - - return NULL; -} - -static void *cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - (*pos)++; - - return cpu_seq_start(seq, pos); -} - -static void cpu_seq_stop(struct seq_file *seq, void *v) -{ -} - -static const struct seq_operations cpu_seq_ops = { - .start = cpu_seq_start, - .next = cpu_seq_next, - .stop = cpu_seq_stop, - .show = cpu_seq_show, -}; - -static int cpu_seq_open(struct inode *inode, struct file *file) -{ - struct cpu_private *priv = inode->i_private; - struct seq_file *seq; - int err; - - err = seq_open(file, &cpu_seq_ops); - if (!err) { - seq = file->private_data; - seq->private = priv; - } - - return err; -} - -static int write_msr(struct cpu_private *priv, u64 val) -{ - u32 low, high; - - high = (val >> 32) & 0xffffffff; - low = val & 0xffffffff; - - if (!wrmsr_safe_on_cpu(priv->cpu, priv->reg, low, high)) - return 0; - - return -EPERM; -} - -static int write_cpu_register(struct cpu_private *priv, const char *buf) -{ - int ret = -EPERM; - u64 val; - - ret = strict_strtoull(buf, 0, &val); - if (ret < 0) - return ret; - - /* Supporting only MSRs */ - if (priv->type < CPU_TSS_BIT) - return write_msr(priv, val); - - return ret; -} - -static ssize_t cpu_write(struct file *file, const char __user *ubuf, - size_t count, loff_t *off) -{ - struct seq_file *seq = file->private_data; - struct cpu_private *priv = seq->private; - char buf[19]; - - if ((priv == NULL) || (count >= sizeof(buf))) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, count)) - return -EFAULT; - - buf[count] = 0; - - if ((cpu_base[priv->type].write) && (cpu_file[priv->file].write)) - if (!write_cpu_register(priv, buf)) - return count; - - return -EACCES; -} - -static const struct file_operations cpu_fops = { - .owner = THIS_MODULE, - .open = cpu_seq_open, - .read = seq_read, - .write = cpu_write, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg, - unsigned file, struct dentry *dentry) -{ - struct cpu_private *priv = NULL; - - /* Already intialized */ - if (file == CPU_INDEX_BIT) - if (per_cpu(cpu_arr[type].init, cpu)) - return 0; - - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (priv == NULL) - return -ENOMEM; - - priv->cpu = cpu; - priv->type = type; - priv->reg = reg; - priv->file = file; - mutex_lock(&cpu_debug_lock); - per_cpu(priv_arr[type], cpu) = priv; - per_cpu(cpu_priv_count, cpu)++; - mutex_unlock(&cpu_debug_lock); - - if (file) - debugfs_create_file(cpu_file[file].name, S_IRUGO, - dentry, (void *)priv, &cpu_fops); - else { - debugfs_create_file(cpu_base[type].name, S_IRUGO, - per_cpu(cpu_arr[type].dentry, cpu), - (void *)priv, &cpu_fops); - mutex_lock(&cpu_debug_lock); - per_cpu(cpu_arr[type].init, cpu) = 1; - mutex_unlock(&cpu_debug_lock); - } - - return 0; -} - -static int cpu_init_regfiles(unsigned cpu, unsigned int type, unsigned reg, - struct dentry *dentry) -{ - unsigned file; - int err = 0; - - for (file = 0; file < ARRAY_SIZE(cpu_file); file++) { - err = cpu_create_file(cpu, type, reg, file, dentry); - if (err) - return err; - } - - return err; -} - -static int cpu_init_msr(unsigned cpu, unsigned type, struct dentry *dentry) -{ - struct dentry *cpu_dentry = NULL; - unsigned reg, reg_min, reg_max; - int i, err = 0; - char reg_dir[12]; - u32 low, high; - - for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) { - if (!get_cpu_range(cpu, ®_min, ®_max, i, - cpu_base[type].flag)) - continue; - - for (reg = reg_min; reg <= reg_max; reg++) { - if (rdmsr_safe_on_cpu(cpu, reg, &low, &high)) - continue; - - sprintf(reg_dir, "0x%x", reg); - cpu_dentry = debugfs_create_dir(reg_dir, dentry); - err = cpu_init_regfiles(cpu, type, reg, cpu_dentry); - if (err) - return err; - } - } - - return err; -} - -static int cpu_init_allreg(unsigned cpu, struct dentry *dentry) -{ - struct dentry *cpu_dentry = NULL; - unsigned type; - int err = 0; - - for (type = 0; type < ARRAY_SIZE(cpu_base) - 1; type++) { - if (!is_typeflag_valid(cpu, cpu_base[type].flag)) - continue; - cpu_dentry = debugfs_create_dir(cpu_base[type].name, dentry); - per_cpu(cpu_arr[type].dentry, cpu) = cpu_dentry; - - if (type < CPU_TSS_BIT) - err = cpu_init_msr(cpu, type, cpu_dentry); - else - err = cpu_create_file(cpu, type, 0, CPU_INDEX_BIT, - cpu_dentry); - if (err) - return err; - } - - return err; -} - -static int cpu_init_cpu(void) -{ - struct dentry *cpu_dentry = NULL; - struct cpuinfo_x86 *cpui; - char cpu_dir[12]; - unsigned cpu; - int err = 0; - - for (cpu = 0; cpu < nr_cpu_ids; cpu++) { - cpui = &cpu_data(cpu); - if (!cpu_has(cpui, X86_FEATURE_MSR)) - continue; - - sprintf(cpu_dir, "cpu%d", cpu); - cpu_dentry = debugfs_create_dir(cpu_dir, cpu_debugfs_dir); - err = cpu_init_allreg(cpu, cpu_dentry); - - pr_info("cpu%d(%d) debug files %d\n", - cpu, nr_cpu_ids, per_cpu(cpu_priv_count, cpu)); - if (per_cpu(cpu_priv_count, cpu) > MAX_CPU_FILES) { - pr_err("Register files count %d exceeds limit %d\n", - per_cpu(cpu_priv_count, cpu), MAX_CPU_FILES); - per_cpu(cpu_priv_count, cpu) = MAX_CPU_FILES; - err = -ENFILE; - } - if (err) - return err; - } - - return err; -} - -static int __init cpu_debug_init(void) -{ - cpu_debugfs_dir = debugfs_create_dir("cpu", arch_debugfs_dir); - - return cpu_init_cpu(); -} - -static void __exit cpu_debug_exit(void) -{ - int i, cpu; - - if (cpu_debugfs_dir) - debugfs_remove_recursive(cpu_debugfs_dir); - - for (cpu = 0; cpu < nr_cpu_ids; cpu++) - for (i = 0; i < per_cpu(cpu_priv_count, cpu); i++) - kfree(per_cpu(priv_arr[i], cpu)); -} - -module_init(cpu_debug_init); -module_exit(cpu_debug_exit); - -MODULE_AUTHOR("Jaswinder Singh Rajput"); -MODULE_DESCRIPTION("CPU Debug module"); -MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 3f12dabeab52..5e92606c4cf8 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -929,7 +929,8 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, powernow_table[i].index = index; /* Frequency may be rounded for these */ - if (boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x11) { + if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10) + || boot_cpu_data.x86 == 0x11) { powernow_table[i].frequency = freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7); } else @@ -1351,6 +1352,7 @@ static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol) kfree(data->powernow_table); kfree(data); + per_cpu(powernow_data, pol->cpu) = NULL; return 0; } @@ -1370,7 +1372,7 @@ static unsigned int powernowk8_get(unsigned int cpu) int err; if (!data) - return -EINVAL; + return 0; smp_call_function_single(cpu, query_values_on_cpu, &err, true); if (err) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 40e1835b35e8..6a77ccaed1aa 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -40,6 +40,7 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) misc_enable &= ~MSR_IA32_MISC_ENABLE_LIMIT_CPUID; wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable); c->cpuid_level = cpuid_eax(0); + get_cpu_cap(c); } } @@ -47,6 +48,27 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) (c->x86 == 0x6 && c->x86_model >= 0x0e)) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + /* + * Atom erratum AAE44/AAF40/AAG38/AAH41: + * + * A race condition between speculative fetches and invalidating + * a large page. This is worked around in microcode, but we + * need the microcode to have already been loaded... so if it is + * not, recommend a BIOS update and disable large pages. + */ + if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2) { + u32 ucode, junk; + + wrmsr(MSR_IA32_UCODE_REV, 0, 0); + sync_core(); + rdmsr(MSR_IA32_UCODE_REV, junk, ucode); + + if (ucode < 0x20e) { + printk(KERN_WARNING "Atom PSE erratum detected, BIOS microcode update recommended\n"); + clear_cpu_cap(c, X86_FEATURE_PSE); + } + } + #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSENTER32); #else @@ -70,8 +92,8 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE); - sched_clock_stable = 1; + if (!check_tsc_unstable()) + sched_clock_stable = 1; } /* diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 804c40e2bc3e..417990f04b5d 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -18,6 +18,7 @@ #include <asm/processor.h> #include <linux/smp.h> #include <asm/k8.h> +#include <asm/smp.h> #define LVL_1_INST 1 #define LVL_1_DATA 2 @@ -94,7 +95,7 @@ static const struct _cache_table __cpuinitconst cache_table[] = { 0xd1, LVL_3, 1024 }, /* 4-way set assoc, 64 byte line size */ { 0xd2, LVL_3, 2048 }, /* 4-way set assoc, 64 byte line size */ { 0xd6, LVL_3, 1024 }, /* 8-way set assoc, 64 byte line size */ - { 0xd7, LVL_3, 2038 }, /* 8-way set assoc, 64 byte line size */ + { 0xd7, LVL_3, 2048 }, /* 8-way set assoc, 64 byte line size */ { 0xd8, LVL_3, 4096 }, /* 12-way set assoc, 64 byte line size */ { 0xdc, LVL_3, 2048 }, /* 12-way set assoc, 64 byte line size */ { 0xdd, LVL_3, 4096 }, /* 12-way set assoc, 64 byte line size */ @@ -102,6 +103,9 @@ static const struct _cache_table __cpuinitconst cache_table[] = { 0xe2, LVL_3, 2048 }, /* 16-way set assoc, 64 byte line size */ { 0xe3, LVL_3, 4096 }, /* 16-way set assoc, 64 byte line size */ { 0xe4, LVL_3, 8192 }, /* 16-way set assoc, 64 byte line size */ + { 0xea, LVL_3, 12288 }, /* 24-way set assoc, 64 byte line size */ + { 0xeb, LVL_3, 18432 }, /* 24-way set assoc, 64 byte line size */ + { 0xec, LVL_3, 24576 }, /* 24-way set assoc, 64 byte line size */ { 0x00, 0, 0} }; @@ -147,7 +151,8 @@ struct _cpuid4_info { union _cpuid4_leaf_ebx ebx; union _cpuid4_leaf_ecx ecx; unsigned long size; - unsigned long can_disable; + bool can_disable; + unsigned int l3_indices; DECLARE_BITMAP(shared_cpu_map, NR_CPUS); }; @@ -157,7 +162,8 @@ struct _cpuid4_info_regs { union _cpuid4_leaf_ebx ebx; union _cpuid4_leaf_ecx ecx; unsigned long size; - unsigned long can_disable; + bool can_disable; + unsigned int l3_indices; }; unsigned short num_cache_leaves; @@ -287,6 +293,36 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, (ebx->split.ways_of_associativity + 1) - 1; } +struct _cache_attr { + struct attribute attr; + ssize_t (*show)(struct _cpuid4_info *, char *); + ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count); +}; + +#ifdef CONFIG_CPU_SUP_AMD +static unsigned int __cpuinit amd_calc_l3_indices(void) +{ + /* + * We're called over smp_call_function_single() and therefore + * are on the correct cpu. + */ + int cpu = smp_processor_id(); + int node = cpu_to_node(cpu); + struct pci_dev *dev = node_to_k8_nb_misc(node); + unsigned int sc0, sc1, sc2, sc3; + u32 val = 0; + + pci_read_config_dword(dev, 0x1C4, &val); + + /* calculate subcache sizes */ + sc0 = !(val & BIT(0)); + sc1 = !(val & BIT(4)); + sc2 = !(val & BIT(8)) + !(val & BIT(9)); + sc3 = !(val & BIT(12)) + !(val & BIT(13)); + + return (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1; +} + static void __cpuinit amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) { @@ -296,13 +332,108 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) if (boot_cpu_data.x86 == 0x11) return; - /* see erratum #382 */ - if ((boot_cpu_data.x86 == 0x10) && (boot_cpu_data.x86_model < 0x8)) + /* see errata #382 and #388 */ + if ((boot_cpu_data.x86 == 0x10) && + ((boot_cpu_data.x86_model < 0x8) || + (boot_cpu_data.x86_mask < 0x1))) return; - this_leaf->can_disable = 1; + /* not in virtualized environments */ + if (num_k8_northbridges == 0) + return; + + this_leaf->can_disable = true; + this_leaf->l3_indices = amd_calc_l3_indices(); +} + +static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, + unsigned int index) +{ + int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); + int node = amd_get_nb_id(cpu); + struct pci_dev *dev = node_to_k8_nb_misc(node); + unsigned int reg = 0; + + if (!this_leaf->can_disable) + return -EINVAL; + + if (!dev) + return -EINVAL; + + pci_read_config_dword(dev, 0x1BC + index * 4, ®); + return sprintf(buf, "0x%08x\n", reg); +} + +#define SHOW_CACHE_DISABLE(index) \ +static ssize_t \ +show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf) \ +{ \ + return show_cache_disable(this_leaf, buf, index); \ +} +SHOW_CACHE_DISABLE(0) +SHOW_CACHE_DISABLE(1) + +static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, + const char *buf, size_t count, unsigned int index) +{ + int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); + int node = amd_get_nb_id(cpu); + struct pci_dev *dev = node_to_k8_nb_misc(node); + unsigned long val = 0; + +#define SUBCACHE_MASK (3UL << 20) +#define SUBCACHE_INDEX 0xfff + + if (!this_leaf->can_disable) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!dev) + return -EINVAL; + + if (strict_strtoul(buf, 10, &val) < 0) + return -EINVAL; + + /* do not allow writes outside of allowed bits */ + if ((val & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) || + ((val & SUBCACHE_INDEX) > this_leaf->l3_indices)) + return -EINVAL; + + val |= BIT(30); + pci_write_config_dword(dev, 0x1BC + index * 4, val); + /* + * We need to WBINVD on a core on the node containing the L3 cache which + * indices we disable therefore a simple wbinvd() is not sufficient. + */ + wbinvd_on_cpu(cpu); + pci_write_config_dword(dev, 0x1BC + index * 4, val | BIT(31)); + return count; } +#define STORE_CACHE_DISABLE(index) \ +static ssize_t \ +store_cache_disable_##index(struct _cpuid4_info *this_leaf, \ + const char *buf, size_t count) \ +{ \ + return store_cache_disable(this_leaf, buf, count, index); \ +} +STORE_CACHE_DISABLE(0) +STORE_CACHE_DISABLE(1) + +static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644, + show_cache_disable_0, store_cache_disable_0); +static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644, + show_cache_disable_1, store_cache_disable_1); + +#else /* CONFIG_CPU_SUP_AMD */ +static void __cpuinit +amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) +{ +}; +#endif /* CONFIG_CPU_SUP_AMD */ + static int __cpuinit cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf) @@ -520,18 +651,19 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) { struct _cpuid4_info *this_leaf, *sibling_leaf; unsigned long num_threads_sharing; - int index_msb, i; + int index_msb, i, sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) { - struct cpuinfo_x86 *d; - for_each_online_cpu(i) { + for_each_cpu(i, c->llc_shared_map) { if (!per_cpu(cpuid4_info, i)) continue; - d = &cpu_data(i); this_leaf = CPUID4_INFO_IDX(i, index); - cpumask_copy(to_cpumask(this_leaf->shared_cpu_map), - d->llc_shared_map); + for_each_cpu(sibling, c->llc_shared_map) { + if (!cpu_online(sibling)) + continue; + set_bit(sibling, this_leaf->shared_cpu_map); + } } return; } @@ -723,82 +855,6 @@ static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf) #define to_object(k) container_of(k, struct _index_kobject, kobj) #define to_attr(a) container_of(a, struct _cache_attr, attr) -static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, - unsigned int index) -{ - int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - int node = cpu_to_node(cpu); - struct pci_dev *dev = node_to_k8_nb_misc(node); - unsigned int reg = 0; - - if (!this_leaf->can_disable) - return -EINVAL; - - if (!dev) - return -EINVAL; - - pci_read_config_dword(dev, 0x1BC + index * 4, ®); - return sprintf(buf, "%x\n", reg); -} - -#define SHOW_CACHE_DISABLE(index) \ -static ssize_t \ -show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf) \ -{ \ - return show_cache_disable(this_leaf, buf, index); \ -} -SHOW_CACHE_DISABLE(0) -SHOW_CACHE_DISABLE(1) - -static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, - const char *buf, size_t count, unsigned int index) -{ - int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - int node = cpu_to_node(cpu); - struct pci_dev *dev = node_to_k8_nb_misc(node); - unsigned long val = 0; - unsigned int scrubber = 0; - - if (!this_leaf->can_disable) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (!dev) - return -EINVAL; - - if (strict_strtoul(buf, 10, &val) < 0) - return -EINVAL; - - val |= 0xc0000000; - - pci_read_config_dword(dev, 0x58, &scrubber); - scrubber &= ~0x1f000000; - pci_write_config_dword(dev, 0x58, scrubber); - - pci_write_config_dword(dev, 0x1BC + index * 4, val & ~0x40000000); - wbinvd(); - pci_write_config_dword(dev, 0x1BC + index * 4, val); - return count; -} - -#define STORE_CACHE_DISABLE(index) \ -static ssize_t \ -store_cache_disable_##index(struct _cpuid4_info *this_leaf, \ - const char *buf, size_t count) \ -{ \ - return store_cache_disable(this_leaf, buf, count, index); \ -} -STORE_CACHE_DISABLE(0) -STORE_CACHE_DISABLE(1) - -struct _cache_attr { - struct attribute attr; - ssize_t (*show)(struct _cpuid4_info *, char *); - ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count); -}; - #define define_one_ro(_name) \ static struct _cache_attr _name = \ __ATTR(_name, 0444, show_##_name, NULL) @@ -813,23 +869,28 @@ define_one_ro(size); define_one_ro(shared_cpu_map); define_one_ro(shared_cpu_list); -static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644, - show_cache_disable_0, store_cache_disable_0); -static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644, - show_cache_disable_1, store_cache_disable_1); +#define DEFAULT_SYSFS_CACHE_ATTRS \ + &type.attr, \ + &level.attr, \ + &coherency_line_size.attr, \ + &physical_line_partition.attr, \ + &ways_of_associativity.attr, \ + &number_of_sets.attr, \ + &size.attr, \ + &shared_cpu_map.attr, \ + &shared_cpu_list.attr static struct attribute *default_attrs[] = { - &type.attr, - &level.attr, - &coherency_line_size.attr, - &physical_line_partition.attr, - &ways_of_associativity.attr, - &number_of_sets.attr, - &size.attr, - &shared_cpu_map.attr, - &shared_cpu_list.attr, + DEFAULT_SYSFS_CACHE_ATTRS, + NULL +}; + +static struct attribute *default_l3_attrs[] = { + DEFAULT_SYSFS_CACHE_ATTRS, +#ifdef CONFIG_CPU_SUP_AMD &cache_disable_0.attr, &cache_disable_1.attr, +#endif NULL }; @@ -920,6 +981,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) unsigned int cpu = sys_dev->id; unsigned long i, j; struct _index_kobject *this_object; + struct _cpuid4_info *this_leaf; int retval; retval = cpuid4_cache_sysfs_init(cpu); @@ -938,6 +1000,14 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) this_object = INDEX_KOBJECT_PTR(cpu, i); this_object->cpu = cpu; this_object->index = i; + + this_leaf = CPUID4_INFO_IDX(cpu, i); + + if (this_leaf->can_disable) + ktype_cache.default_attrs = default_l3_attrs; + else + ktype_cache.default_attrs = default_attrs; + retval = kobject_init_and_add(&(this_object->kobj), &ktype_cache, per_cpu(cache_kobject, cpu), diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 721a77ca8115..0f16a2bfd6a9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1374,13 +1374,14 @@ static void mce_init_timer(void) struct timer_list *t = &__get_cpu_var(mce_timer); int *n = &__get_cpu_var(mce_next_interval); + setup_timer(t, mcheck_timer, smp_processor_id()); + if (mce_ignore_ce) return; *n = check_interval * HZ; if (!*n) return; - setup_timer(t, mcheck_timer, smp_processor_id()); t->expires = round_jiffies(jiffies + *n); add_timer_on(t, smp_processor_id()); } @@ -1991,9 +1992,11 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: - t->expires = round_jiffies(jiffies + + if (!mce_ignore_ce && check_interval) { + t->expires = round_jiffies(jiffies + __get_cpu_var(mce_next_interval)); - add_timer_on(t, cpu); + add_timer_on(t, cpu); + } smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); break; case CPU_POST_DEAD: diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 83a3d1f4efca..8387792a696b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -140,6 +140,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) address = (low & MASK_BLKPTR_LO) >> 21; if (!address) break; + address += MCG_XBLK_ADDR; } else ++address; @@ -147,12 +148,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) if (rdmsr_safe(address, &low, &high)) break; - if (!(high & MASK_VALID_HI)) { - if (block) - continue; - else - break; - } + if (!(high & MASK_VALID_HI)) + continue; if (!(high & MASK_CNTP_HI) || (high & MASK_LOCKED_HI)) diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index b3a1dba75330..687638e655d3 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -49,6 +49,8 @@ static DEFINE_PER_CPU(struct thermal_state, thermal_state); static atomic_t therm_throt_en = ATOMIC_INIT(0); +static u32 lvtthmr_init __read_mostly; + #ifdef CONFIG_SYSFS #define define_therm_throt_sysdev_one_ro(_name) \ static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL) @@ -254,14 +256,27 @@ asmlinkage void smp_thermal_interrupt(struct pt_regs *regs) ack_APIC_irq(); } +void __init mcheck_intel_therm_init(void) +{ + /* + * This function is only called on boot CPU. Save the init thermal + * LVT value on BSP and use that value to restore APs' thermal LVT + * entry BIOS programmed later + */ + if (cpu_has(&boot_cpu_data, X86_FEATURE_ACPI) && + cpu_has(&boot_cpu_data, X86_FEATURE_ACC)) + lvtthmr_init = apic_read(APIC_LVTTHMR); +} + void intel_init_thermal(struct cpuinfo_x86 *c) { unsigned int cpu = smp_processor_id(); int tm2 = 0; u32 l, h; - /* Thermal monitoring depends on ACPI and clock modulation*/ - if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC)) + /* Thermal monitoring depends on APIC, ACPI and clock modulation */ + if (!cpu_has_apic || !cpu_has(c, X86_FEATURE_ACPI) || + !cpu_has(c, X86_FEATURE_ACC)) return; /* @@ -270,7 +285,20 @@ void intel_init_thermal(struct cpuinfo_x86 *c) * since it might be delivered via SMI already: */ rdmsr(MSR_IA32_MISC_ENABLE, l, h); - h = apic_read(APIC_LVTTHMR); + + /* + * The initial value of thermal LVT entries on all APs always reads + * 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI + * sequence to them and LVT registers are reset to 0s except for + * the mask bits which are set to 1s when APs receive INIT IPI. + * Always restore the value that BIOS has programmed on AP based on + * BSP's info we saved since BIOS is always setting the same value + * for all threads/cores + */ + apic_write(APIC_LVTTHMR, lvtthmr_init); + + h = lvtthmr_init; + if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) { printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n", cpu); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index b5801c311846..0ff02cae710b 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -190,6 +190,97 @@ static u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; +static const u64 westmere_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */ + [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPL */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */ + [ C(RESULT_MISS) ] = 0x0251, /* L1D.M_REPL */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */ + [ C(RESULT_MISS) ] = 0x024e, /* L1D_PREFETCH.MISS */ + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */ + [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */ + [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */ + [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */ + [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */ + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */ + [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.ANY */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */ + [ C(RESULT_MISS) ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P */ + [ C(RESULT_MISS) ] = 0x0185, /* ITLB_MISSES.ANY */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [ C(RESULT_MISS) ] = 0x03e8, /* BPU_CLEARS.ANY */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + static const u64 nehalem_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -914,8 +1005,11 @@ static int __hw_perf_event_init(struct perf_event *event) if (atomic_read(&active_events) == 0) { if (!reserve_pmc_hardware()) err = -EBUSY; - else + else { err = reserve_bts_hardware(); + if (err) + release_pmc_hardware(); + } } if (!err) atomic_inc(&active_events); @@ -1999,6 +2093,7 @@ static int intel_pmu_init(void) * Install the hw-cache-events table: */ switch (boot_cpu_data.x86_model) { + case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ @@ -2009,7 +2104,9 @@ static int intel_pmu_init(void) pr_cont("Core2 events, "); break; default: - case 26: + case 26: /* 45 nm nehalem, "Bloomfield" */ + case 30: /* 45 nm nehalem, "Lynnfield" */ + case 46: /* 45 nm nehalem-ex, "Beckton" */ memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2021,6 +2118,14 @@ static int intel_pmu_init(void) pr_cont("Atom events, "); break; + + case 37: /* 32 nm nehalem, "Clarkdale" */ + case 44: /* 32 nm nehalem, "Gulftown" */ + memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + + pr_cont("Westmere events, "); + break; } return 0; } diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index fab786f60ed6..898df9719afb 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -712,7 +712,7 @@ static void probe_nmi_watchdog(void) switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15 && - boot_cpu_data.x86 != 16) + boot_cpu_data.x86 != 16 && boot_cpu_data.x86 != 17) return; wd_ops = &k7_wd_ops; break; diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 1cbed97b59cf..9580152f5813 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -22,6 +22,7 @@ */ #include <linux/dmi.h> +#include <linux/jiffies.h> #include <asm/div64.h> #include <asm/vmware.h> #include <asm/x86_init.h> @@ -50,7 +51,7 @@ static inline int __vmware_platform(void) static unsigned long vmware_get_tsc_khz(void) { - uint64_t tsc_hz; + uint64_t tsc_hz, lpj; uint32_t eax, ebx, ecx, edx; VMWARE_PORT(GETHZ, eax, ebx, ecx, edx); @@ -61,6 +62,13 @@ static unsigned long vmware_get_tsc_khz(void) printk(KERN_INFO "TSC freq read from hypervisor : %lu.%03lu MHz\n", (unsigned long) tsc_hz / 1000, (unsigned long) tsc_hz % 1000); + + if (!preset_lpj) { + lpj = ((u64)tsc_hz * 1000); + do_div(lpj, HZ); + preset_lpj = lpj; + } + return tsc_hz; } diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 6a52d4b36a30..0c91110219c0 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -192,7 +192,8 @@ static int __init cpuid_init(void) int i, err = 0; i = 0; - if (register_chrdev(CPUID_MAJOR, "cpu/cpuid", &cpuid_fops)) { + if (__register_chrdev(CPUID_MAJOR, 0, NR_CPUS, + "cpu/cpuid", &cpuid_fops)) { printk(KERN_ERR "cpuid: unable to get major %d for cpuid\n", CPUID_MAJOR); err = -EBUSY; @@ -221,7 +222,7 @@ out_class: } class_destroy(cpuid_class); out_chrdev: - unregister_chrdev(CPUID_MAJOR, "cpu/cpuid"); + __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); out: return err; } @@ -233,7 +234,7 @@ static void __exit cpuid_exit(void) for_each_online_cpu(cpu) cpuid_device_destroy(cpu); class_destroy(cpuid_class); - unregister_chrdev(CPUID_MAJOR, "cpu/cpuid"); + __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); unregister_hotcpu_notifier(&cpuid_class_cpu_notifier); } diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 5e409dc298a4..ff958248e61d 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -27,7 +27,6 @@ #include <asm/cpu.h> #include <asm/reboot.h> #include <asm/virtext.h> -#include <asm/iommu.h> #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) @@ -104,10 +103,5 @@ void native_machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif - -#ifdef CONFIG_X86_64 - pci_iommu_shutdown(); -#endif - crash_save_cpu(regs, safe_smp_processor_id()); } diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index dedc2bddf7a5..c771e1a37b9d 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -33,6 +33,8 @@ * HPET address is set in acpi/boot.c, when an ACPI entry exists */ unsigned long hpet_address; +u8 hpet_msi_disable; + #ifdef CONFIG_PCI_MSI static unsigned long hpet_num_timers; #endif @@ -383,11 +385,28 @@ static int hpet_next_event(unsigned long delta, hpet_writel(cnt, HPET_Tn_CMP(timer)); /* - * We need to read back the CMP register to make sure that - * what we wrote hit the chip before we compare it to the - * counter. + * We need to read back the CMP register on certain HPET + * implementations (ATI chipsets) which seem to delay the + * transfer of the compare register into the internal compare + * logic. With small deltas this might actually be too late as + * the counter could already be higher than the compare value + * at that point and we would wait for the next hpet interrupt + * forever. We found out that reading the CMP register back + * forces the transfer so we can rely on the comparison with + * the counter register below. If the read back from the + * compare register does not match the value we programmed + * then we might have a real hardware problem. We can not do + * much about it here, but at least alert the user/admin with + * a prominent warning. + * An erratum on some chipsets (ICH9,..), results in comparator read + * immediately following a write returning old value. Workaround + * for this is to read this value second time, when first + * read returns old value. */ - WARN_ON_ONCE((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt); + if (unlikely((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt)) { + WARN_ONCE((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt, + KERN_WARNING "hpet: compare register read back failed.\n"); + } return (s32)((u32)hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0; } @@ -478,7 +497,7 @@ static int hpet_assign_irq(struct hpet_dev *dev) { unsigned int irq; - irq = create_irq(); + irq = create_irq_nr(0, -1); if (!irq) return -EINVAL; @@ -584,6 +603,9 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) unsigned int num_timers_used = 0; int i; + if (hpet_msi_disable) + return; + id = hpet_readl(HPET_ID); num_timers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT); @@ -911,6 +933,9 @@ static __init int hpet_late_init(void) hpet_reserve_platform_timers(hpet_readl(HPET_ID)); hpet_print_config(); + if (hpet_msi_disable) + return 0; + for_each_online_cpu(cpu) { hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu); } @@ -924,7 +949,7 @@ fs_initcall(hpet_late_init); void hpet_disable(void) { - if (is_hpet_capable()) { + if (is_hpet_capable() && hpet_virt_address) { unsigned long cfg = hpet_readl(HPET_CFG); if (hpet_legacy_int_enabled) { diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/k8.c index cbc4332a77b2..9b895464dd03 100644 --- a/arch/x86/kernel/k8.c +++ b/arch/x86/kernel/k8.c @@ -121,3 +121,17 @@ void k8_flush_garts(void) } EXPORT_SYMBOL_GPL(k8_flush_garts); +static __init int init_k8_nbs(void) +{ + int err = 0; + + err = cache_k8_northbridges(); + + if (err < 0) + printk(KERN_NOTICE "K8 NB: Cannot enumerate AMD northbridges.\n"); + + return err; +} + +/* This has to go after the PCI subsystem */ +fs_initcall(init_k8_nbs); diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 5be95ef4ffec..e07bc4ef2829 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -359,13 +359,6 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) x86_init.mpparse.mpc_record(1); } -#ifdef CONFIG_X86_BIGSMP - generic_bigsmp_probe(); -#endif - - if (apic->setup_apic_routing) - apic->setup_apic_routing(); - if (!num_processors) printk(KERN_ERR "MPTABLE: no processors registered!\n"); return num_processors; diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 6a3cefc7dda1..5eaeb5e35c49 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -251,7 +251,7 @@ static int __init msr_init(void) int i, err = 0; i = 0; - if (register_chrdev(MSR_MAJOR, "cpu/msr", &msr_fops)) { + if (__register_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr", &msr_fops)) { printk(KERN_ERR "msr: unable to get major %d for msr\n", MSR_MAJOR); err = -EBUSY; @@ -279,7 +279,7 @@ out_class: msr_device_destroy(i); class_destroy(msr_class); out_chrdev: - unregister_chrdev(MSR_MAJOR, "cpu/msr"); + __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); out: return err; } @@ -290,7 +290,7 @@ static void __exit msr_exit(void) for_each_online_cpu(cpu) msr_device_destroy(cpu); class_destroy(msr_class); - unregister_chrdev(MSR_MAJOR, "cpu/msr"); + __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); unregister_hotcpu_notifier(&msr_class_cpu_notifier); } diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 971a3bec47a8..1a2d4b19eb23 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -102,11 +102,16 @@ int use_calgary __read_mostly = 0; #define PMR_SOFTSTOPFAULT 0x40000000 #define PMR_HARDSTOP 0x20000000 -#define MAX_NUM_OF_PHBS 8 /* how many PHBs in total? */ -#define MAX_NUM_CHASSIS 8 /* max number of chassis */ -/* MAX_PHB_BUS_NUM is the maximal possible dev->bus->number */ -#define MAX_PHB_BUS_NUM (MAX_NUM_OF_PHBS * MAX_NUM_CHASSIS * 2) -#define PHBS_PER_CALGARY 4 +/* + * The maximum PHB bus number. + * x3950M2 (rare): 8 chassis, 48 PHBs per chassis = 384 + * x3950M2: 4 chassis, 48 PHBs per chassis = 192 + * x3950 (PCIE): 8 chassis, 32 PHBs per chassis = 256 + * x3950 (PCIX): 8 chassis, 16 PHBs per chassis = 128 + */ +#define MAX_PHB_BUS_NUM 256 + +#define PHBS_PER_CALGARY 4 /* register offsets in Calgary's internal register space */ static const unsigned long tar_offsets[] = { @@ -318,13 +323,15 @@ static inline struct iommu_table *find_iommu_table(struct device *dev) pdev = to_pci_dev(dev); + /* search up the device tree for an iommu */ pbus = pdev->bus; - - /* is the device behind a bridge? Look for the root bus */ - while (pbus->parent) + do { + tbl = pci_iommu(pbus); + if (tbl && tbl->it_busno == pbus->number) + break; + tbl = NULL; pbus = pbus->parent; - - tbl = pci_iommu(pbus); + } while (pbus); BUG_ON(tbl && (tbl->it_busno != pbus->number)); @@ -1051,8 +1058,6 @@ static int __init calgary_init_one(struct pci_dev *dev) struct iommu_table *tbl; int ret; - BUG_ON(dev->bus->number >= MAX_PHB_BUS_NUM); - bbar = busno_to_bbar(dev->bus->number); ret = calgary_setup_tar(dev, bbar); if (ret) diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index a6e804d16c35..6ac3931160d7 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -214,7 +214,7 @@ static __init int iommu_setup(char *p) if (!strncmp(p, "allowdac", 8)) forbid_dac = 0; if (!strncmp(p, "nodac", 5)) - forbid_dac = -1; + forbid_dac = 1; if (!strncmp(p, "usedac", 6)) { forbid_dac = -1; return 1; diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index a7f1b64f86e0..1c766915094e 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -553,6 +553,9 @@ static void enable_gart_translations(void) enable_gart_translation(dev, __pa(agp_gatt_table)); } + + /* Flush the GART-TLB to remove stale entries */ + k8_flush_garts(); } /* @@ -717,7 +720,7 @@ void __init gart_iommu_init(void) unsigned long scratch; long i; - if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) + if (num_k8_northbridges == 0) return; #ifndef CONFIG_AGP_AMD64 @@ -856,7 +859,7 @@ void __init gart_parse_options(char *p) #endif if (isdigit(*p) && get_option(&p, &arg)) iommu_size = arg; - if (!strncmp(p, "fullflush", 8)) + if (!strncmp(p, "fullflush", 9)) iommu_fullflush = 1; if (!strncmp(p, "nofullflush", 11)) iommu_fullflush = 0; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 5284cd2b5776..5fd5b07bf3a5 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -91,18 +91,6 @@ void flush_thread(void) { struct task_struct *tsk = current; -#ifdef CONFIG_X86_64 - if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) { - clear_tsk_thread_flag(tsk, TIF_ABI_PENDING); - if (test_tsk_thread_flag(tsk, TIF_IA32)) { - clear_tsk_thread_flag(tsk, TIF_IA32); - } else { - set_tsk_thread_flag(tsk, TIF_IA32); - current_thread_info()->status |= TS_COMPAT; - } - } -#endif - clear_tsk_thread_flag(tsk, TIF_DEBUG); tsk->thread.debugreg0 = 0; @@ -451,21 +439,39 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) } /* - * Check for AMD CPUs, which have potentially C1E support + * Check for AMD CPUs, where APIC timer interrupt does not wake up CPU from C1e. + * For more information see + * - Erratum #400 for NPT family 0xf and family 0x10 CPUs + * - Erratum #365 for family 0x11 (not affected because C1e not in use) */ static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c) { + u64 val; if (c->x86_vendor != X86_VENDOR_AMD) - return 0; - - if (c->x86 < 0x0F) - return 0; + goto no_c1e_idle; /* Family 0x0f models < rev F do not have C1E */ - if (c->x86 == 0x0f && c->x86_model < 0x40) - return 0; + if (c->x86 == 0x0F && c->x86_model >= 0x40) + return 1; - return 1; + if (c->x86 == 0x10) { + /* + * check OSVW bit for CPUs that are not affected + * by erratum #400 + */ + if (cpu_has(c, X86_FEATURE_OSVW)) { + rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val); + if (val >= 2) { + rdmsrl(MSR_AMD64_OSVW_STATUS, val); + if (!(val & BIT(1))) + goto no_c1e_idle; + } + } + return 1; + } + +no_c1e_idle: + return 0; } static cpumask_var_t c1e_mask; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index eb62cbcaa490..868fdb407bb9 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -295,11 +295,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, set_tsk_thread_flag(p, TIF_FORK); - p->thread.fs = me->thread.fs; - p->thread.gs = me->thread.gs; - savesegment(gs, p->thread.gsindex); + p->thread.gs = p->thread.gsindex ? 0 : me->thread.gs; savesegment(fs, p->thread.fsindex); + p->thread.fs = p->thread.fsindex ? 0 : me->thread.fs; savesegment(es, p->thread.es); savesegment(ds, p->thread.ds); @@ -540,6 +539,18 @@ sys_clone(unsigned long clone_flags, unsigned long newsp, return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); } +void set_personality_ia32(void) +{ + /* inherit personality from parent */ + + /* Make sure to be in 32bit mode */ + set_thread_flag(TIF_IA32); + current->personality |= force_personality32; + + /* Prepare the first "return" to user space */ + current_thread_info()->status |= TS_COMPAT; +} + unsigned long get_wchan(struct task_struct *p) { unsigned long stack; diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 7b058a2dc66a..c06acddd6830 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -408,14 +408,14 @@ static int genregs_get(struct task_struct *target, { if (kbuf) { unsigned long *k = kbuf; - while (count > 0) { + while (count >= sizeof(*k)) { *k++ = getreg(target, pos); count -= sizeof(*k); pos += sizeof(*k); } } else { unsigned long __user *u = ubuf; - while (count > 0) { + while (count >= sizeof(*u)) { if (__put_user(getreg(target, pos), u++)) return -EFAULT; count -= sizeof(*u); @@ -434,14 +434,14 @@ static int genregs_set(struct task_struct *target, int ret = 0; if (kbuf) { const unsigned long *k = kbuf; - while (count > 0 && !ret) { + while (count >= sizeof(*k) && !ret) { ret = putreg(target, pos, *k++); count -= sizeof(*k); pos += sizeof(*k); } } else { const unsigned long __user *u = ubuf; - while (count > 0 && !ret) { + while (count >= sizeof(*u) && !ret) { unsigned long word; ret = __get_user(word, u++); if (ret) @@ -1219,14 +1219,14 @@ static int genregs32_get(struct task_struct *target, { if (kbuf) { compat_ulong_t *k = kbuf; - while (count > 0) { + while (count >= sizeof(*k)) { getreg32(target, pos, k++); count -= sizeof(*k); pos += sizeof(*k); } } else { compat_ulong_t __user *u = ubuf; - while (count > 0) { + while (count >= sizeof(*u)) { compat_ulong_t word; getreg32(target, pos, &word); if (__put_user(word, u++)) @@ -1247,14 +1247,14 @@ static int genregs32_set(struct task_struct *target, int ret = 0; if (kbuf) { const compat_ulong_t *k = kbuf; - while (count > 0 && !ret) { + while (count >= sizeof(*k) && !ret) { ret = putreg32(target, pos, *k++); count -= sizeof(*k); pos += sizeof(*k); } } else { const compat_ulong_t __user *u = ubuf; - while (count > 0 && !ret) { + while (count >= sizeof(*u) && !ret) { compat_ulong_t word; ret = __get_user(word, u++); if (ret) diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 03801f2f761f..dfdfe4662e05 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -109,11 +109,14 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src) return pv_tsc_khz; } +static atomic64_t last_value = ATOMIC64_INIT(0); + cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) { struct pvclock_shadow_time shadow; unsigned version; cycle_t ret, offset; + u64 last; do { version = pvclock_get_time_values(&shadow, src); @@ -123,6 +126,27 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) barrier(); } while (version != src->version); + /* + * Assumption here is that last_value, a global accumulator, always goes + * forward. If we are less than that, we should not be much smaller. + * We assume there is an error marging we're inside, and then the correction + * does not sacrifice accuracy. + * + * For reads: global may have changed between test and return, + * but this means someone else updated poked the clock at a later time. + * We just need to make sure we are not seeing a backwards event. + * + * For updates: last_value = ret is not enough, since two vcpus could be + * updating at the same time, and one of them could be slightly behind, + * making the assumption that last_value always go forward fail to hold. + */ + last = atomic64_read(&last_value); + do { + if (ret < last) + return last; + last = atomic64_cmpxchg(&last_value, last, ret); + } while (unlikely(last != ret)); + return ret; } diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 6c3b2c6fd772..0040164f1a82 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -491,6 +491,19 @@ void force_hpet_resume(void) break; } } + +/* + * HPET MSI on some boards (ATI SB700/SB800) has side effect on + * floppy DMA. Disable HPET MSI on such platforms. + */ +static void force_disable_hpet_msi(struct pci_dev *unused) +{ + hpet_msi_disable = 1; +} + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, + force_disable_hpet_msi); + #endif #if defined(CONFIG_PCI) && defined(CONFIG_NUMA) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index f93078746e00..269c2a3cb43d 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -203,6 +203,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "0T656F"), }, }, + { /* Handle problems with rebooting on Dell OptiPlex 760 with 0G919G*/ + .callback = set_bios_reboot, + .ident = "Dell OptiPlex 760", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 760"), + DMI_MATCH(DMI_BOARD_NAME, "0G919G"), + }, + }, { /* Handle problems with rebooting on Dell 2400's */ .callback = set_bios_reboot, .ident = "Dell PowerEdge 2400", @@ -259,6 +268,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "SBC-FITPC2"), }, }, + { /* Handle problems with rebooting on ASUS P4S800 */ + .callback = set_bios_reboot, + .ident = "ASUS P4S800", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_BOARD_NAME, "P4S800"), + }, + }, { } }; @@ -444,6 +461,14 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Macmini3,1"), }, }, + { /* Handle problems with rebooting on the iMac9,1. */ + .callback = set_pci_reboot, + .ident = "Apple iMac9,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), + }, + }, { } }; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 2a34f9c5be21..d7a088849938 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -109,6 +109,7 @@ #ifdef CONFIG_X86_64 #include <asm/numa_64.h> #endif +#include <asm/mce.h> /* * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. @@ -666,19 +667,38 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"), }, }, - { /* - * AMI BIOS with low memory corruption was found on Intel DG45ID board. - * It hase different DMI_BIOS_VENDOR = "Intel Corp.", for now we will + * AMI BIOS with low memory corruption was found on Intel DG45ID and + * DG45FC boards. + * It has a different DMI_BIOS_VENDOR = "Intel Corp.", for now we will * match only DMI_BOARD_NAME and see if there is more bad products * with this vendor. */ + { .callback = dmi_low_memory_corruption, .ident = "AMI BIOS", .matches = { DMI_MATCH(DMI_BOARD_NAME, "DG45ID"), }, }, + { + .callback = dmi_low_memory_corruption, + .ident = "AMI BIOS", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "DG45FC"), + }, + }, + /* + * The Dell Inspiron Mini 1012 has DMI_BIOS_VENDOR = "Dell Inc.", so + * match on the product name. + */ + { + .callback = dmi_low_memory_corruption, + .ident = "Phoenix BIOS", + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1012"), + }, + }, #endif {} }; @@ -1031,6 +1051,8 @@ void __init setup_arch(char **cmdline_p) #endif #endif x86_init.oem.banner(); + + mcheck_intel_therm_init(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 565ebc65920e..29ec5606d244 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -88,6 +88,25 @@ DEFINE_PER_CPU(int, cpu_state) = { 0 }; static DEFINE_PER_CPU(struct task_struct *, idle_thread_array); #define get_idle_for_cpu(x) (per_cpu(idle_thread_array, x)) #define set_idle_for_cpu(x, p) (per_cpu(idle_thread_array, x) = (p)) + +/* + * We need this for trampoline_base protection from concurrent accesses when + * off- and onlining cores wildly. + */ +static DEFINE_MUTEX(x86_cpu_hotplug_driver_mutex); + +void cpu_hotplug_driver_lock() +{ + mutex_lock(&x86_cpu_hotplug_driver_mutex); +} + +void cpu_hotplug_driver_unlock() +{ + mutex_unlock(&x86_cpu_hotplug_driver_mutex); +} + +ssize_t arch_cpu_probe(const char *buf, size_t count) { return -1; } +ssize_t arch_cpu_release(const char *buf, size_t count) { return -1; } #else static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ; #define get_idle_for_cpu(x) (idle_thread_array[(x)]) @@ -1066,9 +1085,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_cpu_sibling_map(0); enable_IR_x2apic(); -#ifdef CONFIG_X86_64 default_setup_apic_routing(); -#endif if (smp_sanity_check(max_cpus) < 0) { printk(KERN_INFO "SMP disabled\n"); diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c index 1884a8d12bfa..dee1ff7cba58 100644 --- a/arch/x86/kernel/sys_i386_32.c +++ b/arch/x86/kernel/sys_i386_32.c @@ -24,31 +24,6 @@ #include <asm/syscalls.h> -asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff) -{ - int error = -EBADF; - struct file *file = NULL; - struct mm_struct *mm = current->mm; - - flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); - if (!(flags & MAP_ANONYMOUS)) { - file = fget(fd); - if (!file) - goto out; - } - - down_write(&mm->mmap_sem); - error = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); - up_write(&mm->mmap_sem); - - if (file) - fput(file); -out: - return error; -} - /* * Perform the select(nd, in, out, ex, tv) and mmap() system * calls. Linux/i386 didn't use to be able to handle more than @@ -77,7 +52,7 @@ asmlinkage int old_mmap(struct mmap_arg_struct __user *arg) if (a.offset & ~PAGE_MASK) goto out; - err = sys_mmap2(a.addr, a.len, a.prot, a.flags, + err = sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); out: return err; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 45e00eb09c3a..8aa2057efd12 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -23,26 +23,11 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, fd, unsigned long, off) { long error; - struct file *file; - error = -EINVAL; if (off & ~PAGE_MASK) goto out; - error = -EBADF; - file = NULL; - flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); - if (!(flags & MAP_ANONYMOUS)) { - file = fget(fd); - if (!file) - goto out; - } - down_write(¤t->mm->mmap_sem); - error = do_mmap_pgoff(file, addr, len, prot, flags, off >> PAGE_SHIFT); - up_write(¤t->mm->mmap_sem); - - if (file) - fput(file); + error = sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); out: return error; } diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 0157cd26d7cc..76d70a451285 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -191,7 +191,7 @@ ENTRY(sys_call_table) .long sys_ni_syscall /* reserved for streams2 */ .long ptregs_vfork /* 190 */ .long sys_getrlimit - .long sys_mmap2 + .long sys_mmap_pgoff .long sys_truncate64 .long sys_ftruncate64 .long sys_stat64 /* 195 */ diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 86c9f91b48ae..46b827778d16 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -46,6 +46,7 @@ /* Global pointer to shared data; NULL means no measured launch. */ struct tboot *tboot __read_mostly; +EXPORT_SYMBOL(tboot); /* timeout for APs (in secs) to enter wait-for-SIPI state during shutdown */ #define AP_WAIT_TIMEOUT 1 diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index 1740c85e24bb..364d015efebc 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -817,10 +817,8 @@ static int __init uv_init_blade(int blade) */ apicid = blade_to_first_apicid(blade); pa = uv_read_global_mmr64(pnode, UVH_BAU_DATA_CONFIG); - if ((pa & 0xff) != UV_BAU_MESSAGE) { - uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, + uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, ((apicid << 32) | UV_BAU_MESSAGE)); - } return 0; } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index cd982f48e23e..aaefa71888cb 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -626,6 +626,44 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) local_irq_restore(flags); } +static unsigned long long cyc2ns_suspend; + +void save_sched_clock_state(void) +{ + if (!sched_clock_stable) + return; + + cyc2ns_suspend = sched_clock(); +} + +/* + * Even on processors with invariant TSC, TSC gets reset in some the + * ACPI system sleep states. And in some systems BIOS seem to reinit TSC to + * arbitrary value (still sync'd across cpu's) during resume from such sleep + * states. To cope up with this, recompute the cyc2ns_offset for each cpu so + * that sched_clock() continues from the point where it was left off during + * suspend. + */ +void restore_sched_clock_state(void) +{ + unsigned long long offset; + unsigned long flags; + int cpu; + + if (!sched_clock_stable) + return; + + local_irq_save(flags); + + __get_cpu_var(cyc2ns_offset) = 0; + offset = cyc2ns_suspend - sched_clock(); + + for_each_possible_cpu(cpu) + per_cpu(cyc2ns_offset, cpu) = offset; + + local_irq_restore(flags); +} + #ifdef CONFIG_CPU_FREQ /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency @@ -763,6 +801,7 @@ void mark_tsc_unstable(char *reason) { if (!tsc_unstable) { tsc_unstable = 1; + sched_clock_stable = 0; printk(KERN_INFO "Marking TSC unstable due to %s\n", reason); /* Change only the rating, when not registered */ if (clocksource_tsc.mult) diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 8cb4974ff599..62f39d79b775 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -73,7 +73,8 @@ void update_vsyscall_tz(void) write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); } -void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) +void update_vsyscall(struct timespec *wall_time, struct clocksource *clock, + u32 mult) { unsigned long flags; @@ -82,7 +83,7 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) vsyscall_gtod_data.clock.vread = clock->vread; vsyscall_gtod_data.clock.cycle_last = clock->cycle_last; vsyscall_gtod_data.clock.mask = clock->mask; - vsyscall_gtod_data.clock.mult = clock->mult; + vsyscall_gtod_data.clock.mult = mult; vsyscall_gtod_data.clock.shift = clock->shift; vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec; vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec; |