diff options
Diffstat (limited to 'arch/x86/kernel')
106 files changed, 1355 insertions, 1860 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 4f2e66e29ec..d87f09bc5a5 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -89,7 +89,6 @@ obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_HPET_TIMER) += hpet.o obj-$(CONFIG_K8_NB) += k8.o -obj-$(CONFIG_MGEODE_LX) += geode_32.o mfgpt_32.o obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index fd5ca97a2ad..6f35260bb3e 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -4,7 +4,7 @@ obj-$(CONFIG_ACPI) += boot.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_rm.o wakeup_$(BITS).o ifneq ($(CONFIG_ACPI_PROCESSOR),) -obj-y += cstate.o processor.o +obj-y += cstate.o endif $(obj)/wakeup_rm.o: $(obj)/realmode/wakeup.bin diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 67e929b8987..036d28adf59 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -624,6 +624,7 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) } hpet_address = hpet_tbl->address.address; + hpet_blockid = hpet_tbl->sequence; /* * Some broken BIOSes advertise HPET at 0x0. We really do not @@ -1122,7 +1123,7 @@ static int __init acpi_parse_madt_ioapic_entries(void) if (!acpi_sci_override_gsi) acpi_sci_ioapic_setup(acpi_gbl_FADT.sci_interrupt, 0, 0); - /* Fill in identity legacy mapings where no override */ + /* Fill in identity legacy mappings where no override */ mp_config_acpi_legacy_irqs(); count = @@ -1528,16 +1529,10 @@ static struct dmi_system_id __initdata acpi_dmi_table_late[] = { * if acpi_blacklisted() acpi_disabled = 1; * acpi_irq_model=... * ... - * - * return value: (currently ignored) - * 0: success - * !0: failure */ -int __init acpi_boot_table_init(void) +void __init acpi_boot_table_init(void) { - int error; - dmi_check_system(acpi_dmi_table); /* @@ -1545,15 +1540,14 @@ int __init acpi_boot_table_init(void) * One exception: acpi=ht continues far enough to enumerate LAPICs */ if (acpi_disabled && !acpi_ht) - return 1; + return; /* * Initialize the ACPI boot-time table parser. */ - error = acpi_table_init(); - if (error) { + if (acpi_table_init()) { disable_acpi(); - return error; + return; } acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf); @@ -1561,18 +1555,15 @@ int __init acpi_boot_table_init(void) /* * blacklist may disable ACPI entirely */ - error = acpi_blacklisted(); - if (error) { + if (acpi_blacklisted()) { if (acpi_force) { printk(KERN_WARNING PREFIX "acpi=force override\n"); } else { printk(KERN_WARNING PREFIX "Disabling ACPI support\n"); disable_acpi(); - return error; + return; } } - - return 0; } int __init early_acpi_boot_init(void) diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 59cdfa4686b..2e837f5080f 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); diff --git a/arch/x86/kernel/acpi/processor.c b/arch/x86/kernel/acpi/processor.c deleted file mode 100644 index d85d1b2432b..00000000000 --- a/arch/x86/kernel/acpi/processor.c +++ /dev/null @@ -1,101 +0,0 @@ -/* - * Copyright (C) 2005 Intel Corporation - * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> - * - Added _PDC for platforms with Intel CPUs - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/acpi.h> - -#include <acpi/processor.h> -#include <asm/acpi.h> - -static void init_intel_pdc(struct acpi_processor *pr, struct cpuinfo_x86 *c) -{ - struct acpi_object_list *obj_list; - union acpi_object *obj; - u32 *buf; - - /* allocate and initialize pdc. It will be used later. */ - obj_list = kmalloc(sizeof(struct acpi_object_list), GFP_KERNEL); - if (!obj_list) { - printk(KERN_ERR "Memory allocation error\n"); - return; - } - - obj = kmalloc(sizeof(union acpi_object), GFP_KERNEL); - if (!obj) { - printk(KERN_ERR "Memory allocation error\n"); - kfree(obj_list); - return; - } - - buf = kmalloc(12, GFP_KERNEL); - if (!buf) { - printk(KERN_ERR "Memory allocation error\n"); - kfree(obj); - kfree(obj_list); - return; - } - - buf[0] = ACPI_PDC_REVISION_ID; - buf[1] = 1; - buf[2] = ACPI_PDC_C_CAPABILITY_SMP; - - /* - * The default of PDC_SMP_T_SWCOORD bit is set for intel x86 cpu so - * that OSPM is capable of native ACPI throttling software - * coordination using BIOS supplied _TSD info. - */ - buf[2] |= ACPI_PDC_SMP_T_SWCOORD; - if (cpu_has(c, X86_FEATURE_EST)) - buf[2] |= ACPI_PDC_EST_CAPABILITY_SWSMP; - - if (cpu_has(c, X86_FEATURE_ACPI)) - buf[2] |= ACPI_PDC_T_FFH; - - /* - * If mwait/monitor is unsupported, C2/C3_FFH will be disabled - */ - if (!cpu_has(c, X86_FEATURE_MWAIT)) - buf[2] &= ~(ACPI_PDC_C_C2C3_FFH); - - obj->type = ACPI_TYPE_BUFFER; - obj->buffer.length = 12; - obj->buffer.pointer = (u8 *) buf; - obj_list->count = 1; - obj_list->pointer = obj; - pr->pdc = obj_list; - - return; -} - - -/* Initialize _PDC data based on the CPU vendor */ -void arch_acpi_processor_init_pdc(struct acpi_processor *pr) -{ - struct cpuinfo_x86 *c = &cpu_data(pr->id); - - pr->pdc = NULL; - if (c->x86_vendor == X86_VENDOR_INTEL || - c->x86_vendor == X86_VENDOR_CENTAUR) - init_intel_pdc(pr, c); - - return; -} - -EXPORT_SYMBOL(arch_acpi_processor_init_pdc); - -void arch_acpi_processor_cleanup_pdc(struct acpi_processor *pr) -{ - if (pr->pdc) { - kfree(pr->pdc->pointer->buffer.pointer); - kfree(pr->pdc->pointer); - kfree(pr->pdc); - pr->pdc = NULL; - } -} - -EXPORT_SYMBOL(arch_acpi_processor_cleanup_pdc); diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index ca93638ba43..f9961034e55 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -78,12 +78,9 @@ int acpi_save_state_mem(void) #ifndef CONFIG_64BIT store_gdt((struct desc_ptr *)&header->pmode_gdt); - header->pmode_efer_low = nx_enabled; - if (header->pmode_efer_low & 1) { - /* This is strange, why not save efer, always? */ - rdmsr(MSR_EFER, header->pmode_efer_low, - header->pmode_efer_high); - } + if (rdmsr_safe(MSR_EFER, &header->pmode_efer_low, + &header->pmode_efer_high)) + header->pmode_efer_low = header->pmode_efer_high = 0; #endif /* !CONFIG_64BIT */ header->pmode_cr0 = read_cr0(); @@ -119,29 +116,32 @@ void acpi_restore_state_mem(void) /** - * acpi_reserve_bootmem - do _very_ early ACPI initialisation + * acpi_reserve_wakeup_memory - do _very_ early ACPI initialisation * * We allocate a page from the first 1MB of memory for the wakeup * routine for when we come back from a sleep state. The * runtime allocator allows specification of <16MB pages, but not * <1MB pages. */ -void __init acpi_reserve_bootmem(void) +void __init acpi_reserve_wakeup_memory(void) { + unsigned long mem; + if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) { printk(KERN_ERR "ACPI: Wakeup code way too big, S3 disabled.\n"); return; } - acpi_realmode = (unsigned long)alloc_bootmem_low(WAKEUP_SIZE); + mem = find_e820_area(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE); - if (!acpi_realmode) { + if (mem == -1L) { printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n"); return; } - - acpi_wakeup_address = virt_to_phys((void *)acpi_realmode); + acpi_realmode = (unsigned long) phys_to_virt(mem); + acpi_wakeup_address = mem; + reserve_early(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP"); } @@ -162,6 +162,8 @@ static int __init acpi_sleep_setup(char *str) #endif if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); + if (strncmp(str, "sci_force_enable", 16) == 0) + acpi_set_sci_en_on_resume(); str = strchr(str, ','); if (str != NULL) str += strspn(str, ", \t"); diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 32fb09102a1..23824fef789 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -19,7 +19,7 @@ #include <linux/pci.h> #include <linux/gfp.h> -#include <linux/bitops.h> +#include <linux/bitmap.h> #include <linux/debugfs.h> #include <linux/scatterlist.h> #include <linux/dma-mapping.h> @@ -166,6 +166,43 @@ static void iommu_uninit_device(struct device *dev) { kfree(dev->archdata.iommu); } + +void __init amd_iommu_uninit_devices(void) +{ + struct pci_dev *pdev = NULL; + + for_each_pci_dev(pdev) { + + if (!check_device(&pdev->dev)) + continue; + + iommu_uninit_device(&pdev->dev); + } +} + +int __init amd_iommu_init_devices(void) +{ + struct pci_dev *pdev = NULL; + int ret = 0; + + for_each_pci_dev(pdev) { + + if (!check_device(&pdev->dev)) + continue; + + ret = iommu_init_device(&pdev->dev); + if (ret) + goto out_free; + } + + return 0; + +out_free: + + amd_iommu_uninit_devices(); + + return ret; +} #ifdef CONFIG_AMD_IOMMU_STATS /* @@ -1125,7 +1162,7 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom, address = (address % APERTURE_RANGE_SIZE) >> PAGE_SHIFT; - iommu_area_free(range->bitmap, address, pages); + bitmap_clear(range->bitmap, address, pages); } @@ -1587,6 +1624,11 @@ static struct notifier_block device_nb = { .notifier_call = device_change_notifier, }; +void amd_iommu_init_notifier(void) +{ + bus_register_notifier(&pci_bus_type, &device_nb); +} + /***************************************************************************** * * The next functions belong to the dma_ops mapping/unmapping code. @@ -1783,7 +1825,7 @@ retry: goto out; /* - * aperture was sucessfully enlarged by 128 MB, try + * aperture was successfully enlarged by 128 MB, try * allocation again */ goto retry; @@ -2145,8 +2187,6 @@ static void prealloc_protection_domains(void) if (!check_device(&dev->dev)) continue; - iommu_init_device(&dev->dev); - /* Is there already any domain for it? */ if (domain_for_device(&dev->dev)) continue; @@ -2215,8 +2255,6 @@ int __init amd_iommu_init_dma_ops(void) register_iommu(&amd_iommu_ops); - bus_register_notifier(&pci_bus_type, &device_nb); - amd_iommu_stats_init(); return 0; @@ -2490,7 +2528,7 @@ int __init amd_iommu_init_passthrough(void) struct pci_dev *dev = NULL; u16 devid; - /* allocate passthroug domain */ + /* allocate passthrough domain */ pt_domain = protection_domain_alloc(); if (!pt_domain) return -ENOMEM; diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 7ffc3996523..fb490ce7dd5 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -138,6 +138,11 @@ int amd_iommus_present; bool amd_iommu_np_cache __read_mostly; /* + * Set to true if ACPI table parsing and hardware intialization went properly + */ +static bool amd_iommu_initialized; + +/* * List of protection domains - used during resume */ LIST_HEAD(amd_iommu_pd_list); @@ -929,6 +934,8 @@ static int __init init_iommu_all(struct acpi_table_header *table) } WARN_ON(p != end); + amd_iommu_initialized = true; + return 0; } @@ -1263,6 +1270,9 @@ static 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; @@ -1274,6 +1284,10 @@ static int __init amd_iommu_init(void) if (ret) goto free; + ret = amd_iommu_init_devices(); + if (ret) + goto free; + if (iommu_pass_through) ret = amd_iommu_init_passthrough(); else @@ -1281,6 +1295,8 @@ static int __init amd_iommu_init(void) if (ret) goto free; + amd_iommu_init_notifier(); + enable_iommus(); if (iommu_pass_through) @@ -1296,6 +1312,9 @@ out: return ret; free: + + amd_iommu_uninit_devices(); + free_pages((unsigned long)amd_iommu_pd_alloc_bitmap, get_order(MAX_DOMAIN_ID/8)); @@ -1336,6 +1355,9 @@ void __init amd_iommu_detect(void) iommu_detected = 1; amd_iommu_detected = 1; x86_init.iommu.iommu_init = amd_iommu_init; + + /* Make sure ACS will be enabled */ + pci_request_acs(); } } diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index e0dfb6856aa..f147a95fd84 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -31,6 +31,7 @@ #include <asm/x86_init.h> int gart_iommu_aperture; +EXPORT_SYMBOL_GPL(gart_iommu_aperture); int gart_iommu_aperture_disabled __initdata; int gart_iommu_aperture_allowed __initdata; @@ -280,7 +281,8 @@ void __init early_gart_iommu_check(void) * or BIOS forget to put that in reserved. * try to update e820 to make that region as reserved. */ - int i, fix, slot; + u32 agp_aper_base = 0, agp_aper_order = 0; + int i, fix, slot, valid_agp = 0; u32 ctl; u32 aper_size = 0, aper_order = 0, last_aper_order = 0; u64 aper_base = 0, last_aper_base = 0; @@ -290,6 +292,8 @@ void __init early_gart_iommu_check(void) return; /* This is mostly duplicate of iommu_hole_init */ + agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp); + fix = 0; for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { int bus; @@ -342,10 +346,10 @@ void __init early_gart_iommu_check(void) } } - if (!fix) + if (valid_agp) return; - /* different nodes have different setting, disable them all at first*/ + /* disable them all at first */ for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { int bus; int dev_base, dev_limit; @@ -458,8 +462,6 @@ out: if (aper_alloc) { /* Got the aperture from the AGP bridge */ - } else if (!valid_agp) { - /* Do nothing */ } else if ((!no_iommu && max_pfn > MAX_DMA32_PFN) || force_iommu || valid_agp || diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ad8c75b9e45..3987e4408f7 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -61,12 +61,6 @@ unsigned int boot_cpu_physical_apicid = -1U; /* * The highest APIC ID seen during enumeration. - * - * On AMD, this determines the messaging protocol we can use: if all APIC IDs - * are in the 0 ... 7 range, then we can use logical addressing which - * has some performance advantages (better broadcasting). - * - * If there's an APIC ID above 8, we use physical addressing. */ unsigned int max_physical_apicid; @@ -647,7 +641,7 @@ static int __init calibrate_APIC_clock(void) calibration_result = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS; apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta); - apic_printk(APIC_VERBOSE, "..... mult: %ld\n", lapic_clockevent.mult); + apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult); apic_printk(APIC_VERBOSE, "..... calibration result: %u\n", calibration_result); @@ -1341,7 +1335,7 @@ void enable_x2apic(void) rdmsr(MSR_IA32_APICBASE, msr, msr2); if (!(msr & X2APIC_ENABLE)) { - pr_info("Enabling x2apic\n"); + printk_once(KERN_INFO "Enabling x2apic\n"); wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0); } } @@ -1898,14 +1892,17 @@ void __cpuinit generic_processor_info(int apicid, int version) 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) + if (num_processors > 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; + } } #endif diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index d0c99abc26c..e3c3d820c32 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; @@ -306,10 +311,7 @@ physflat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, if (cpumask_test_cpu(cpu, cpu_online_mask)) break; } - if (cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu); - - return BAD_APICID; + return per_cpu(x86_cpu_to_apicid, cpu); } struct apic apic_physflat = { diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index d9acc3bee0f..e31b9ffe25f 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -127,7 +127,7 @@ static u32 noop_apic_read(u32 reg) static void noop_apic_write(u32 reg, u32 v) { - WARN_ON_ONCE((cpu_has_apic || !disable_apic)); + WARN_ON_ONCE(cpu_has_apic && !disable_apic); } struct apic apic_noop = { diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 38dcecfa581..cb804c5091b 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -131,10 +131,7 @@ static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, if (cpumask_test_cpu(cpu, cpu_online_mask)) break; } - if (cpu < nr_cpu_ids) - return bigsmp_cpu_to_logical_apicid(cpu); - - return BAD_APICID; + return bigsmp_cpu_to_logical_apicid(cpu); } static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index e85f8fb7f8e..dd2b5f26464 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -27,6 +27,9 @@ * * http://www.unisys.com */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/notifier.h> #include <linux/spinlock.h> #include <linux/cpumask.h> @@ -223,9 +226,9 @@ static int parse_unisys_oem(char *oemptr) mip_addr = val; mip = (struct mip_reg *)val; mip_reg = __va(mip); - pr_debug("es7000_mipcfg: host_reg = 0x%lx \n", + pr_debug("host_reg = 0x%lx\n", (unsigned long)host_reg); - pr_debug("es7000_mipcfg: mip_reg = 0x%lx \n", + pr_debug("mip_reg = 0x%lx\n", (unsigned long)mip_reg); success++; break; @@ -401,7 +404,7 @@ static void es7000_enable_apic_mode(void) if (!es7000_plat) return; - printk(KERN_INFO "ES7000: Enabling APIC mode.\n"); + pr_info("Enabling APIC mode.\n"); memset(&es7000_mip_reg, 0, sizeof(struct mip_reg)); es7000_mip_reg.off_0x00 = MIP_SW_APIC; es7000_mip_reg.off_0x38 = MIP_VALID; @@ -514,8 +517,7 @@ static void es7000_setup_apic_routing(void) { int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id()); - printk(KERN_INFO - "Enabling APIC mode: %s. Using %d I/O APICs, target cpus %lx\n", + pr_info("Enabling APIC mode: %s. Using %d I/O APICs, target cpus %lx\n", (apic_version[apic] == 0x14) ? "Physical Cluster" : "Logical Cluster", nr_ioapics, cpumask_bits(es7000_target_cpus())[0]); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index c0b4468683f..53243ca7816 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2276,26 +2276,28 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq /* * Either sets desc->affinity to a valid value, and returns - * ->cpu_mask_to_apicid of that, or returns BAD_APICID and + * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and * leaves desc->affinity untouched. */ unsigned int -set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask) +set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask, + unsigned int *dest_id) { struct irq_cfg *cfg; unsigned int irq; if (!cpumask_intersects(mask, cpu_online_mask)) - return BAD_APICID; + return -1; irq = desc->irq; cfg = desc->chip_data; if (assign_irq_vector(irq, cfg, mask)) - return BAD_APICID; + return -1; cpumask_copy(desc->affinity, mask); - return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain); + *dest_id = apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain); + return 0; } static int @@ -2311,12 +2313,11 @@ set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask) cfg = desc->chip_data; spin_lock_irqsave(&ioapic_lock, flags); - dest = set_desc_affinity(desc, mask); - if (dest != BAD_APICID) { + ret = set_desc_affinity(desc, mask, &dest); + if (!ret) { /* Only the high 8 bits are valid. */ dest = SET_APIC_LOGICAL_ID(dest); __target_IO_APIC_irq(irq, dest, cfg); - ret = 0; } spin_unlock_irqrestore(&ioapic_lock, flags); @@ -2431,7 +2432,14 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) continue; cfg = irq_cfg(irq); - spin_lock(&desc->lock); + raw_spin_lock(&desc->lock); + + /* + * Check if the irq migration is in progress. If so, we + * haven't received the cleanup request yet for this irq. + */ + if (cfg->move_in_progress) + goto unlock; if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) goto unlock; @@ -2450,7 +2458,7 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) } __get_cpu_var(vector_irq)[vector] = -1; unlock: - spin_unlock(&desc->lock); + raw_spin_unlock(&desc->lock); } irq_exit(); @@ -3267,7 +3275,8 @@ void destroy_irq(unsigned int irq) * MSI message composition */ #ifdef CONFIG_PCI_MSI -static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg) +static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, + struct msi_msg *msg, u8 hpet_id) { struct irq_cfg *cfg; int err; @@ -3301,7 +3310,10 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms irte.dest_id = IRTE_DEST(dest); /* Set source-id of interrupt request */ - set_msi_sid(&irte, pdev); + if (pdev) + set_msi_sid(&irte, pdev); + else + set_hpet_sid(&irte, hpet_id); modify_irte(irq, &irte); @@ -3347,8 +3359,7 @@ static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask) struct msi_msg msg; unsigned int dest; - dest = set_desc_affinity(desc, mask); - if (dest == BAD_APICID) + if (set_desc_affinity(desc, mask, &dest)) return -1; cfg = desc->chip_data; @@ -3380,8 +3391,7 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask) if (get_irte(irq, &irte)) return -1; - dest = set_desc_affinity(desc, mask); - if (dest == BAD_APICID) + if (set_desc_affinity(desc, mask, &dest)) return -1; irte.vector = cfg->vector; @@ -3466,7 +3476,7 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) int ret; struct msi_msg msg; - ret = msi_compose_msg(dev, irq, &msg); + ret = msi_compose_msg(dev, irq, &msg, -1); if (ret < 0) return ret; @@ -3563,8 +3573,7 @@ static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask) struct msi_msg msg; unsigned int dest; - dest = set_desc_affinity(desc, mask); - if (dest == BAD_APICID) + if (set_desc_affinity(desc, mask, &dest)) return -1; cfg = desc->chip_data; @@ -3599,7 +3608,7 @@ int arch_setup_dmar_msi(unsigned int irq) int ret; struct msi_msg msg; - ret = msi_compose_msg(NULL, irq, &msg); + ret = msi_compose_msg(NULL, irq, &msg, -1); if (ret < 0) return ret; dmar_msi_write(irq, &msg); @@ -3619,8 +3628,7 @@ static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask) struct msi_msg msg; unsigned int dest; - dest = set_desc_affinity(desc, mask); - if (dest == BAD_APICID) + if (set_desc_affinity(desc, mask, &dest)) return -1; cfg = desc->chip_data; @@ -3639,6 +3647,19 @@ static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask) #endif /* CONFIG_SMP */ +static struct irq_chip ir_hpet_msi_type = { + .name = "IR-HPET_MSI", + .unmask = hpet_msi_unmask, + .mask = hpet_msi_mask, +#ifdef CONFIG_INTR_REMAP + .ack = ir_ack_apic_edge, +#ifdef CONFIG_SMP + .set_affinity = ir_set_msi_irq_affinity, +#endif +#endif + .retrigger = ioapic_retrigger_irq, +}; + static struct irq_chip hpet_msi_type = { .name = "HPET_MSI", .unmask = hpet_msi_unmask, @@ -3650,20 +3671,36 @@ static struct irq_chip hpet_msi_type = { .retrigger = ioapic_retrigger_irq, }; -int arch_setup_hpet_msi(unsigned int irq) +int arch_setup_hpet_msi(unsigned int irq, unsigned int id) { int ret; struct msi_msg msg; struct irq_desc *desc = irq_to_desc(irq); - ret = msi_compose_msg(NULL, irq, &msg); + if (intr_remapping_enabled) { + struct intel_iommu *iommu = map_hpet_to_ir(id); + int index; + + if (!iommu) + return -1; + + index = alloc_irte(iommu, irq, 1); + if (index < 0) + return -1; + } + + ret = msi_compose_msg(NULL, irq, &msg, id); if (ret < 0) return ret; hpet_msi_write(irq, &msg); desc->status |= IRQ_MOVE_PCNTXT; - set_irq_chip_and_handler_name(irq, &hpet_msi_type, handle_edge_irq, - "edge"); + if (irq_remapped(irq)) + set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type, + handle_edge_irq, "edge"); + else + set_irq_chip_and_handler_name(irq, &hpet_msi_type, + handle_edge_irq, "edge"); return 0; } @@ -3697,8 +3734,7 @@ static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask) struct irq_cfg *cfg; unsigned int dest; - dest = set_desc_affinity(desc, mask); - if (dest == BAD_APICID) + if (set_desc_affinity(desc, mask, &dest)) return -1; cfg = desc->chip_data; diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index 6389432a9db..0159a69396c 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -361,7 +361,7 @@ void stop_apic_nmi_watchdog(void *unused) */ static DEFINE_PER_CPU(unsigned, last_irq_sum); -static DEFINE_PER_CPU(local_t, alert_counter); +static DEFINE_PER_CPU(long, alert_counter); static DEFINE_PER_CPU(int, nmi_touch); void touch_nmi_watchdog(void) @@ -438,8 +438,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) * Ayiee, looks like this CPU is stuck ... * wait a few IRQs (5 seconds) before doing the oops ... */ - local_inc(&__get_cpu_var(alert_counter)); - if (local_read(&__get_cpu_var(alert_counter)) == 5 * nmi_hz) + __this_cpu_inc(per_cpu_var(alert_counter)); + if (__this_cpu_read(per_cpu_var(alert_counter)) == 5 * nmi_hz) /* * die_nmi will return ONLY if NOTIFY_STOP happens.. */ @@ -447,7 +447,7 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) regs, panic_on_timeout); } else { __get_cpu_var(last_irq_sum) = sum; - local_set(&__get_cpu_var(alert_counter), 0); + __this_cpu_write(per_cpu_var(alert_counter), 0); } /* see if the nmi watchdog went off */ diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 07cdbdcd7a9..98c4665f251 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -264,11 +264,6 @@ static void __init smp_read_mpc_oem(struct mpc_table *mpc) static __init void early_check_numaq(void) { /* - * Find possible boot-time SMP configuration: - */ - early_find_smp_config(); - - /* * get boot-time SMP configuration: */ if (smp_found_config) diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index c4cbd3080c1..450fe2064a1 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_processors > 8) + apic = &apic_physflat; printk(KERN_INFO "Setting APIC routing to %s\n", apic->name); diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index a5371ec3677..cf69c59f491 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -148,10 +148,7 @@ x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, break; } - if (cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_logical_apicid, cpu); - - return BAD_APICID; + return per_cpu(x86_cpu_to_logical_apicid, cpu); } static unsigned int x2apic_cluster_phys_get_apic_id(unsigned long x) diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index a8989aadc99..8972f38c5ce 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -146,10 +146,7 @@ x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, break; } - if (cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu); - - return BAD_APICID; + return per_cpu(x86_cpu_to_apicid, cpu); } static unsigned int x2apic_phys_get_apic_id(unsigned long x) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 130c4b93487..21db3cbea7d 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -30,10 +30,24 @@ #include <asm/apic.h> #include <asm/ipi.h> #include <asm/smp.h> +#include <asm/x86_init.h> DEFINE_PER_CPU(int, x2apic_extra_bits); static enum uv_system_type uv_system_type; +static u64 gru_start_paddr, gru_end_paddr; +int uv_min_hub_revision_id; +EXPORT_SYMBOL_GPL(uv_min_hub_revision_id); + +static inline bool is_GRU_range(u64 start, u64 end) +{ + return start >= gru_start_paddr && end <= gru_end_paddr; +} + +static bool uv_is_untracked_pat_range(u64 start, u64 end) +{ + return is_ISA_range(start, end) || is_GRU_range(start, end); +} static int early_get_nodeid(void) { @@ -43,19 +57,27 @@ static int early_get_nodeid(void) mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr)); node_id.v = *mmr; early_iounmap(mmr, sizeof(*mmr)); + + /* Currently, all blades have same revision number */ + uv_min_hub_revision_id = node_id.s.revision; + return node_id.s.node_id; } static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { + int nodeid; + if (!strcmp(oem_id, "SGI")) { + nodeid = early_get_nodeid(); + x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; if (!strcmp(oem_table_id, "UVL")) uv_system_type = UV_LEGACY_APIC; else if (!strcmp(oem_table_id, "UVX")) uv_system_type = UV_X2APIC; else if (!strcmp(oem_table_id, "UVH")) { __get_cpu_var(x2apic_extra_bits) = - early_get_nodeid() << (UV_APIC_PNODE_SHIFT - 1); + nodeid << (UV_APIC_PNODE_SHIFT - 1); uv_system_type = UV_NON_UNIQUE_APIC; return 1; } @@ -212,10 +234,7 @@ uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, if (cpumask_test_cpu(cpu, cpu_online_mask)) break; } - if (cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu); - - return BAD_APICID; + return per_cpu(x86_cpu_to_apicid, cpu); } static unsigned int x2apic_get_apic_id(unsigned long x) @@ -364,13 +383,13 @@ 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) @@ -385,8 +404,12 @@ static __init void map_gru_high(int max_pnode) int shift = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT; 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); + if (gru.s.enable) { + map_high("GRU", gru.s.base, shift, shift, max_pnode, map_wb); + gru_start_paddr = ((u64)gru.s.base << shift); + gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1); + + } } static __init void map_mmr_high(int max_pnode) @@ -396,7 +419,7 @@ 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 +429,8 @@ 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 map_low_mmrs(void) @@ -615,8 +639,10 @@ 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++; @@ -637,15 +663,13 @@ 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/bios_uv.c b/arch/x86/kernel/bios_uv.c index 63a88e1f987..b0206a211b0 100644 --- a/arch/x86/kernel/bios_uv.c +++ b/arch/x86/kernel/bios_uv.c @@ -101,21 +101,17 @@ s64 uv_bios_get_sn_info(int fc, int *uvtype, long *partid, long *coher, } int -uv_bios_mq_watchlist_alloc(int blade, unsigned long addr, unsigned int mq_size, +uv_bios_mq_watchlist_alloc(unsigned long addr, unsigned int mq_size, unsigned long *intr_mmr_offset) { - union uv_watchlist_u size_blade; u64 watchlist; s64 ret; - size_blade.size = mq_size; - size_blade.blade = blade; - /* * bios returns watchlist number or negative error number. */ ret = (int)uv_bios_call_irqsave(UV_BIOS_WATCHLIST_ALLOC, addr, - size_blade.val, (u64)intr_mmr_offset, + mq_size, (u64)intr_mmr_offset, (u64)&watchlist, 0); if (ret < BIOS_STATUS_SUCCESS) return ret; diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c index c965e521271..468489b57aa 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/addon_cpuid_features.c @@ -74,6 +74,7 @@ void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c) unsigned int eax, ebx, ecx, edx, sub_index; unsigned int ht_mask_width, core_plus_mask_width; unsigned int core_select_mask, core_level_siblings; + static bool printed; if (c->cpuid_level < 0xb) return; @@ -127,12 +128,14 @@ void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c) c->x86_max_cores = (core_level_siblings / smp_num_siblings); - - printk(KERN_INFO "CPU: Physical Processor ID: %d\n", - c->phys_proc_id); - if (c->x86_max_cores > 1) - printk(KERN_INFO "CPU: Processor Core ID: %d\n", - c->cpu_core_id); + if (!printed) { + printk(KERN_INFO "CPU: Physical Processor ID: %d\n", + c->phys_proc_id); + if (c->x86_max_cores > 1) + printk(KERN_INFO "CPU: Processor Core ID: %d\n", + c->cpu_core_id); + printed = 1; + } return; #endif } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 7128b3799ce..e485825130d 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; - - /* 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; + /* store NodeID, use llc_shared_map to store sibling info */ + per_cpu(cpu_llc_id, cpu) = value & 7; - /* 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 @@ -375,8 +352,6 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) node = nearby_node(apicid); } numa_set_node(cpu, node); - - printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node); #endif } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a4ec8b64754..4868e4a951e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -427,6 +427,7 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_HT u32 eax, ebx, ecx, edx; int index_msb, core_bits; + static bool printed; if (!cpu_has(c, X86_FEATURE_HT)) return; @@ -442,7 +443,7 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) smp_num_siblings = (ebx & 0xff0000) >> 16; if (smp_num_siblings == 1) { - printk(KERN_INFO "CPU: Hyper-Threading is disabled\n"); + printk_once(KERN_INFO "CPU0: Hyper-Threading is disabled\n"); goto out; } @@ -469,11 +470,12 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) ((1 << core_bits) - 1); out: - if ((c->x86_max_cores * smp_num_siblings) > 1) { + if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) { printk(KERN_INFO "CPU: Physical Processor ID: %d\n", c->phys_proc_id); printk(KERN_INFO "CPU: Processor Core ID: %d\n", c->cpu_core_id); + printed = 1; } #endif } @@ -1093,7 +1095,7 @@ static void clear_all_debug_regs(void) void __cpuinit cpu_init(void) { - struct orig_ist *orig_ist; + struct orig_ist *oist; struct task_struct *me; struct tss_struct *t; unsigned long v; @@ -1102,7 +1104,7 @@ void __cpuinit cpu_init(void) cpu = stack_smp_processor_id(); t = &per_cpu(init_tss, cpu); - orig_ist = &per_cpu(orig_ist, cpu); + oist = &per_cpu(orig_ist, cpu); #ifdef CONFIG_NUMA if (cpu != 0 && percpu_read(node_number) == 0 && @@ -1115,7 +1117,7 @@ void __cpuinit cpu_init(void) if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) panic("CPU#%d already initialized!\n", cpu); - printk(KERN_INFO "Initializing CPU#%d\n", cpu); + pr_debug("Initializing CPU#%d\n", cpu); clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); @@ -1136,19 +1138,19 @@ void __cpuinit cpu_init(void) wrmsrl(MSR_KERNEL_GS_BASE, 0); barrier(); - check_efer(); + x86_configure_nx(); if (cpu != 0) enable_x2apic(); /* * set up and load the per-CPU TSS */ - if (!orig_ist->ist[0]) { + if (!oist->ist[0]) { char *estacks = per_cpu(exception_stacks, cpu); for (v = 0; v < N_EXCEPTION_STACKS; v++) { estacks += exception_stack_sizes[v]; - orig_ist->ist[v] = t->x86_tss.ist[v] = + oist->ist[v] = t->x86_tss.ist[v] = (unsigned long)estacks; } } diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c index dca325c0399..b368cd86299 100644 --- a/arch/x86/kernel/cpu/cpu_debug.c +++ b/arch/x86/kernel/cpu/cpu_debug.c @@ -30,9 +30,9 @@ #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_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpud_arr); +static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], cpud_priv_arr); +static DEFINE_PER_CPU(int, cpud_priv_count); static DEFINE_MUTEX(cpu_debug_lock); @@ -531,7 +531,7 @@ static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg, /* Already intialized */ if (file == CPU_INDEX_BIT) - if (per_cpu(cpu_arr[type].init, cpu)) + if (per_cpu(cpud_arr[type].init, cpu)) return 0; priv = kzalloc(sizeof(*priv), GFP_KERNEL); @@ -543,8 +543,8 @@ static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg, priv->reg = reg; priv->file = file; mutex_lock(&cpu_debug_lock); - per_cpu(priv_arr[type], cpu) = priv; - per_cpu(cpu_priv_count, cpu)++; + per_cpu(cpud_priv_arr[type], cpu) = priv; + per_cpu(cpud_priv_count, cpu)++; mutex_unlock(&cpu_debug_lock); if (file) @@ -552,10 +552,10 @@ static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg, dentry, (void *)priv, &cpu_fops); else { debugfs_create_file(cpu_base[type].name, S_IRUGO, - per_cpu(cpu_arr[type].dentry, cpu), + per_cpu(cpud_arr[type].dentry, cpu), (void *)priv, &cpu_fops); mutex_lock(&cpu_debug_lock); - per_cpu(cpu_arr[type].init, cpu) = 1; + per_cpu(cpud_arr[type].init, cpu) = 1; mutex_unlock(&cpu_debug_lock); } @@ -615,7 +615,7 @@ static int cpu_init_allreg(unsigned cpu, struct dentry *dentry) 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; + per_cpu(cpud_arr[type].dentry, cpu) = cpu_dentry; if (type < CPU_TSS_BIT) err = cpu_init_msr(cpu, type, cpu_dentry); @@ -647,11 +647,11 @@ static int cpu_init_cpu(void) 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) { + cpu, nr_cpu_ids, per_cpu(cpud_priv_count, cpu)); + if (per_cpu(cpud_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; + per_cpu(cpud_priv_count, cpu), MAX_CPU_FILES); + per_cpu(cpud_priv_count, cpu) = MAX_CPU_FILES; err = -ENFILE; } if (err) @@ -676,8 +676,8 @@ static void __exit cpu_debug_exit(void) 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)); + for (i = 0; i < per_cpu(cpud_priv_count, cpu); i++) + kfree(per_cpu(cpud_priv_arr[i], cpu)); } module_init(cpu_debug_init); diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 8b581d3905c..1b1920fa7c8 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -68,9 +68,9 @@ struct acpi_cpufreq_data { unsigned int cpu_feature; }; -static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data); +static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data); -static DEFINE_PER_CPU(struct aperfmperf, old_perf); +static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf); /* acpi_perf_data is a pointer to percpu data. */ static struct acpi_processor_performance *acpi_perf_data; @@ -190,9 +190,11 @@ static void do_drv_write(void *_cmd) static void drv_read(struct drv_cmd *cmd) { + int err; cmd->val = 0; - smp_call_function_single(cpumask_any(cmd->mask), do_drv_read, cmd, 1); + err = smp_call_function_any(cmd->mask, do_drv_read, cmd, 1); + WARN_ON_ONCE(err); /* smp_call_function_any() was buggy? */ } static void drv_write(struct drv_cmd *cmd) @@ -214,14 +216,14 @@ static u32 get_cur_val(const struct cpumask *mask) if (unlikely(cpumask_empty(mask))) return 0; - switch (per_cpu(drv_data, cpumask_first(mask))->cpu_feature) { + switch (per_cpu(acfreq_data, cpumask_first(mask))->cpu_feature) { case SYSTEM_INTEL_MSR_CAPABLE: cmd.type = SYSTEM_INTEL_MSR_CAPABLE; cmd.addr.msr.reg = MSR_IA32_PERF_STATUS; break; case SYSTEM_IO_CAPABLE: cmd.type = SYSTEM_IO_CAPABLE; - perf = per_cpu(drv_data, cpumask_first(mask))->acpi_data; + perf = per_cpu(acfreq_data, cpumask_first(mask))->acpi_data; cmd.addr.io.port = perf->control_register.address; cmd.addr.io.bit_width = perf->control_register.bit_width; break; @@ -268,8 +270,8 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy, if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1)) return 0; - ratio = calc_aperfmperf_ratio(&per_cpu(old_perf, cpu), &perf); - per_cpu(old_perf, cpu) = perf; + ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf); + per_cpu(acfreq_old_perf, cpu) = perf; retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT; @@ -278,7 +280,7 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy, static unsigned int get_cur_freq_on_cpu(unsigned int cpu) { - struct acpi_cpufreq_data *data = per_cpu(drv_data, cpu); + struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu); unsigned int freq; unsigned int cached_freq; @@ -322,7 +324,7 @@ static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq, static int acpi_cpufreq_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { - struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu); + struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu); struct acpi_processor_performance *perf; struct cpufreq_freqs freqs; struct drv_cmd cmd; @@ -416,7 +418,7 @@ out: static int acpi_cpufreq_verify(struct cpufreq_policy *policy) { - struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu); + struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu); dprintk("acpi_cpufreq_verify\n"); @@ -574,7 +576,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) return -ENOMEM; data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu); - per_cpu(drv_data, cpu) = data; + per_cpu(acfreq_data, cpu) = data; if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS; @@ -725,20 +727,20 @@ err_unreg: acpi_processor_unregister_performance(perf, cpu); err_free: kfree(data); - per_cpu(drv_data, cpu) = NULL; + per_cpu(acfreq_data, cpu) = NULL; return result; } static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy) { - struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu); + struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu); dprintk("acpi_cpufreq_cpu_exit\n"); if (data) { cpufreq_frequency_table_put_attr(policy->cpu); - per_cpu(drv_data, policy->cpu) = NULL; + per_cpu(acfreq_data, policy->cpu) = NULL; acpi_processor_unregister_performance(data->acpi_data, policy->cpu); kfree(data); @@ -749,7 +751,7 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy) static int acpi_cpufreq_resume(struct cpufreq_policy *policy) { - struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu); + struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu); dprintk("acpi_cpufreq_resume\n"); @@ -764,14 +766,15 @@ static struct freq_attr *acpi_cpufreq_attr[] = { }; static struct cpufreq_driver acpi_cpufreq_driver = { - .verify = acpi_cpufreq_verify, - .target = acpi_cpufreq_target, - .init = acpi_cpufreq_cpu_init, - .exit = acpi_cpufreq_cpu_exit, - .resume = acpi_cpufreq_resume, - .name = "acpi-cpufreq", - .owner = THIS_MODULE, - .attr = acpi_cpufreq_attr, + .verify = acpi_cpufreq_verify, + .target = acpi_cpufreq_target, + .bios_limit = acpi_processor_get_bios_limit, + .init = acpi_cpufreq_cpu_init, + .exit = acpi_cpufreq_cpu_exit, + .resume = acpi_cpufreq_resume, + .name = "acpi-cpufreq", + .owner = THIS_MODULE, + .attr = acpi_cpufreq_attr, }; static int __init acpi_cpufreq_init(void) diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c index cabd2fa3fc9..7e7eea4f826 100644 --- a/arch/x86/kernel/cpu/cpufreq/longhaul.c +++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c @@ -885,7 +885,7 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) /* Find ACPI data for processor */ acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, - ACPI_UINT32_MAX, &longhaul_walk_callback, + ACPI_UINT32_MAX, &longhaul_walk_callback, NULL, NULL, (void *)&pr); /* Check ACPI support for C3 state */ diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c index f10dea409f4..cb01dac267d 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c @@ -164,7 +164,7 @@ static int powernow_k6_cpu_init(struct cpufreq_policy *policy) } /* cpuinfo and default policy values */ - policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; + policy->cpuinfo.transition_latency = 200000; policy->cur = busfreq * max_multiplier; result = cpufreq_frequency_table_cpuinfo(policy, clock_ratio); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c index d47c775eb0a..9a97116f89e 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c @@ -714,14 +714,17 @@ static struct freq_attr *powernow_table_attr[] = { }; static struct cpufreq_driver powernow_driver = { - .verify = powernow_verify, - .target = powernow_target, - .get = powernow_get, - .init = powernow_cpu_init, - .exit = powernow_cpu_exit, - .name = "powernow-k7", - .owner = THIS_MODULE, - .attr = powernow_table_attr, + .verify = powernow_verify, + .target = powernow_target, + .get = powernow_get, +#ifdef CONFIG_X86_POWERNOW_K7_ACPI + .bios_limit = acpi_processor_get_bios_limit, +#endif + .init = powernow_cpu_init, + .exit = powernow_cpu_exit, + .name = "powernow-k7", + .owner = THIS_MODULE, + .attr = powernow_table_attr, }; static int __init powernow_init(void) diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 3f12dabeab5..f125e5c551c 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -1118,7 +1118,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsigned relation) { - cpumask_t oldmask; + cpumask_var_t oldmask; struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu); u32 checkfid; u32 checkvid; @@ -1131,9 +1131,13 @@ static int powernowk8_target(struct cpufreq_policy *pol, checkfid = data->currfid; checkvid = data->currvid; - /* only run on specific CPU from here on */ - oldmask = current->cpus_allowed; - set_cpus_allowed_ptr(current, &cpumask_of_cpu(pol->cpu)); + /* only run on specific CPU from here on. */ + /* This is poor form: use a workqueue or smp_call_function_single */ + if (!alloc_cpumask_var(&oldmask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_copy(oldmask, tsk_cpus_allowed(current)); + set_cpus_allowed_ptr(current, cpumask_of(pol->cpu)); if (smp_processor_id() != pol->cpu) { printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu); @@ -1193,7 +1197,8 @@ static int powernowk8_target(struct cpufreq_policy *pol, ret = 0; err_out: - set_cpus_allowed_ptr(current, &oldmask); + set_cpus_allowed_ptr(current, oldmask); + free_cpumask_var(oldmask); return ret; } @@ -1393,14 +1398,15 @@ static struct freq_attr *powernow_k8_attr[] = { }; static struct cpufreq_driver cpufreq_amd64_driver = { - .verify = powernowk8_verify, - .target = powernowk8_target, - .init = powernowk8_cpu_init, - .exit = __devexit_p(powernowk8_cpu_exit), - .get = powernowk8_get, - .name = "powernow-k8", - .owner = THIS_MODULE, - .attr = powernow_k8_attr, + .verify = powernowk8_verify, + .target = powernowk8_target, + .bios_limit = acpi_processor_get_bios_limit, + .init = powernowk8_cpu_init, + .exit = __devexit_p(powernowk8_cpu_exit), + .get = powernowk8_get, + .name = "powernow-k8", + .owner = THIS_MODULE, + .attr = powernow_k8_attr, }; /* driver entry point for init */ diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c index 3ae5a7a3a50..2ce8e0b5cc5 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c @@ -39,7 +39,7 @@ static struct pci_dev *speedstep_chipset_dev; /* speedstep_processor */ -static unsigned int speedstep_processor; +static enum speedstep_processor speedstep_processor; static u32 pmbase; diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c index f4c290b8482..ad0083abfa2 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c @@ -34,7 +34,7 @@ static int relaxed_check; * GET PROCESSOR CORE SPEED IN KHZ * *********************************************************************/ -static unsigned int pentium3_get_frequency(unsigned int processor) +static unsigned int pentium3_get_frequency(enum speedstep_processor processor) { /* See table 14 of p3_ds.pdf and table 22 of 29834003.pdf */ struct { @@ -227,7 +227,7 @@ static unsigned int pentium4_get_frequency(void) /* Warning: may get called from smp_call_function_single. */ -unsigned int speedstep_get_frequency(unsigned int processor) +unsigned int speedstep_get_frequency(enum speedstep_processor processor) { switch (processor) { case SPEEDSTEP_CPU_PCORE: @@ -380,7 +380,7 @@ EXPORT_SYMBOL_GPL(speedstep_detect_processor); * DETECT SPEEDSTEP SPEEDS * *********************************************************************/ -unsigned int speedstep_get_freqs(unsigned int processor, +unsigned int speedstep_get_freqs(enum speedstep_processor processor, unsigned int *low_speed, unsigned int *high_speed, unsigned int *transition_latency, diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h index 2b6c04e5a30..70d9cea1219 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h @@ -11,18 +11,18 @@ /* processors */ - -#define SPEEDSTEP_CPU_PIII_C_EARLY 0x00000001 /* Coppermine core */ -#define SPEEDSTEP_CPU_PIII_C 0x00000002 /* Coppermine core */ -#define SPEEDSTEP_CPU_PIII_T 0x00000003 /* Tualatin core */ -#define SPEEDSTEP_CPU_P4M 0x00000004 /* P4-M */ - +enum speedstep_processor { + SPEEDSTEP_CPU_PIII_C_EARLY = 0x00000001, /* Coppermine core */ + SPEEDSTEP_CPU_PIII_C = 0x00000002, /* Coppermine core */ + SPEEDSTEP_CPU_PIII_T = 0x00000003, /* Tualatin core */ + SPEEDSTEP_CPU_P4M = 0x00000004, /* P4-M */ /* the following processors are not speedstep-capable and are not auto-detected * in speedstep_detect_processor(). However, their speed can be detected using * the speedstep_get_frequency() call. */ -#define SPEEDSTEP_CPU_PM 0xFFFFFF03 /* Pentium M */ -#define SPEEDSTEP_CPU_P4D 0xFFFFFF04 /* desktop P4 */ -#define SPEEDSTEP_CPU_PCORE 0xFFFFFF05 /* Core */ + SPEEDSTEP_CPU_PM = 0xFFFFFF03, /* Pentium M */ + SPEEDSTEP_CPU_P4D = 0xFFFFFF04, /* desktop P4 */ + SPEEDSTEP_CPU_PCORE = 0xFFFFFF05, /* Core */ +}; /* speedstep states -- only two of them */ @@ -31,10 +31,10 @@ /* detect a speedstep-capable processor */ -extern unsigned int speedstep_detect_processor (void); +extern enum speedstep_processor speedstep_detect_processor(void); /* detect the current speed (in khz) of the processor */ -extern unsigned int speedstep_get_frequency(unsigned int processor); +extern unsigned int speedstep_get_frequency(enum speedstep_processor processor); /* detect the low and high speeds of the processor. The callback @@ -42,7 +42,7 @@ extern unsigned int speedstep_get_frequency(unsigned int processor); * SPEEDSTEP_LOW; the second argument is zero so that no * cpufreq_notify_transition calls are initiated. */ -extern unsigned int speedstep_get_freqs(unsigned int processor, +extern unsigned int speedstep_get_freqs(enum speedstep_processor processor, unsigned int *low_speed, unsigned int *high_speed, unsigned int *transition_latency, diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c index befea088e4f..04d73c114e4 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c @@ -35,7 +35,7 @@ static int smi_cmd; static unsigned int smi_sig; /* info about the processor */ -static unsigned int speedstep_processor; +static enum speedstep_processor speedstep_processor; /* * There are only two frequency states for each processor. Values diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 40e1835b35e..879666f4d87 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -70,7 +70,6 @@ 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; } @@ -263,11 +262,13 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) /* Don't do the funky fallback heuristics the AMD version employs for now. */ node = apicid_to_node[apicid]; - if (node == NUMA_NO_NODE || !node_online(node)) + if (node == NUMA_NO_NODE) node = first_node(node_online_map); + else if (!node_online(node)) { + /* reuse the value from init_cpu_to_node() */ + node = cpu_to_node(cpu); + } numa_set_node(cpu, node); - - printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node); #endif } diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 0df4c2b7107..fc6c8ef92dc 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -94,7 +94,7 @@ 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 +102,9 @@ 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} }; @@ -496,26 +499,27 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) #ifdef CONFIG_SYSFS /* pointer to _cpuid4_info array (for each cache leaf) */ -static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info); -#define CPUID4_INFO_IDX(x, y) (&((per_cpu(cpuid4_info, x))[y])) +static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info); +#define CPUID4_INFO_IDX(x, y) (&((per_cpu(ici_cpuid4_info, x))[y])) #ifdef CONFIG_SMP 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) { - if (!per_cpu(cpuid4_info, i)) + for_each_cpu(i, c->llc_shared_map) { + if (!per_cpu(ici_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; } @@ -532,7 +536,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) c->apicid >> index_msb) { cpumask_set_cpu(i, to_cpumask(this_leaf->shared_cpu_map)); - if (i != cpu && per_cpu(cpuid4_info, i)) { + if (i != cpu && per_cpu(ici_cpuid4_info, i)) { sibling_leaf = CPUID4_INFO_IDX(i, index); cpumask_set_cpu(cpu, to_cpumask( @@ -571,8 +575,8 @@ static void __cpuinit free_cache_attributes(unsigned int cpu) for (i = 0; i < num_cache_leaves; i++) cache_remove_shared_cpu_map(cpu, i); - kfree(per_cpu(cpuid4_info, cpu)); - per_cpu(cpuid4_info, cpu) = NULL; + kfree(per_cpu(ici_cpuid4_info, cpu)); + per_cpu(ici_cpuid4_info, cpu) = NULL; } static int @@ -611,15 +615,15 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu) if (num_cache_leaves == 0) return -ENOENT; - per_cpu(cpuid4_info, cpu) = kzalloc( + per_cpu(ici_cpuid4_info, cpu) = kzalloc( sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL); - if (per_cpu(cpuid4_info, cpu) == NULL) + if (per_cpu(ici_cpuid4_info, cpu) == NULL) return -ENOMEM; smp_call_function_single(cpu, get_cpu_leaves, &retval, true); if (retval) { - kfree(per_cpu(cpuid4_info, cpu)); - per_cpu(cpuid4_info, cpu) = NULL; + kfree(per_cpu(ici_cpuid4_info, cpu)); + per_cpu(ici_cpuid4_info, cpu) = NULL; } return retval; @@ -631,7 +635,7 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu) extern struct sysdev_class cpu_sysdev_class; /* from drivers/base/cpu.c */ /* pointer to kobject for cpuX/cache */ -static DEFINE_PER_CPU(struct kobject *, cache_kobject); +static DEFINE_PER_CPU(struct kobject *, ici_cache_kobject); struct _index_kobject { struct kobject kobj; @@ -640,8 +644,8 @@ struct _index_kobject { }; /* pointer to array of kobjects for cpuX/cache/indexY */ -static DEFINE_PER_CPU(struct _index_kobject *, index_kobject); -#define INDEX_KOBJECT_PTR(x, y) (&((per_cpu(index_kobject, x))[y])) +static DEFINE_PER_CPU(struct _index_kobject *, ici_index_kobject); +#define INDEX_KOBJECT_PTR(x, y) (&((per_cpu(ici_index_kobject, x))[y])) #define show_one_plus(file_name, object, val) \ static ssize_t show_##file_name \ @@ -860,10 +864,10 @@ static struct kobj_type ktype_percpu_entry = { static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu) { - kfree(per_cpu(cache_kobject, cpu)); - kfree(per_cpu(index_kobject, cpu)); - per_cpu(cache_kobject, cpu) = NULL; - per_cpu(index_kobject, cpu) = NULL; + kfree(per_cpu(ici_cache_kobject, cpu)); + kfree(per_cpu(ici_index_kobject, cpu)); + per_cpu(ici_cache_kobject, cpu) = NULL; + per_cpu(ici_index_kobject, cpu) = NULL; free_cache_attributes(cpu); } @@ -879,14 +883,14 @@ static int __cpuinit cpuid4_cache_sysfs_init(unsigned int cpu) return err; /* Allocate all required memory */ - per_cpu(cache_kobject, cpu) = + per_cpu(ici_cache_kobject, cpu) = kzalloc(sizeof(struct kobject), GFP_KERNEL); - if (unlikely(per_cpu(cache_kobject, cpu) == NULL)) + if (unlikely(per_cpu(ici_cache_kobject, cpu) == NULL)) goto err_out; - per_cpu(index_kobject, cpu) = kzalloc( + per_cpu(ici_index_kobject, cpu) = kzalloc( sizeof(struct _index_kobject) * num_cache_leaves, GFP_KERNEL); - if (unlikely(per_cpu(index_kobject, cpu) == NULL)) + if (unlikely(per_cpu(ici_index_kobject, cpu) == NULL)) goto err_out; return 0; @@ -910,7 +914,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) if (unlikely(retval < 0)) return retval; - retval = kobject_init_and_add(per_cpu(cache_kobject, cpu), + retval = kobject_init_and_add(per_cpu(ici_cache_kobject, cpu), &ktype_percpu_entry, &sys_dev->kobj, "%s", "cache"); if (retval < 0) { @@ -924,12 +928,12 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) this_object->index = i; retval = kobject_init_and_add(&(this_object->kobj), &ktype_cache, - per_cpu(cache_kobject, cpu), + per_cpu(ici_cache_kobject, cpu), "index%1lu", i); if (unlikely(retval)) { for (j = 0; j < i; j++) kobject_put(&(INDEX_KOBJECT_PTR(cpu, j)->kobj)); - kobject_put(per_cpu(cache_kobject, cpu)); + kobject_put(per_cpu(ici_cache_kobject, cpu)); cpuid4_cache_sysfs_exit(cpu); return retval; } @@ -937,7 +941,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) } cpumask_set_cpu(cpu, to_cpumask(cache_dev_map)); - kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD); + kobject_uevent(per_cpu(ici_cache_kobject, cpu), KOBJ_ADD); return 0; } @@ -946,7 +950,7 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev) unsigned int cpu = sys_dev->id; unsigned long i; - if (per_cpu(cpuid4_info, cpu) == NULL) + if (per_cpu(ici_cpuid4_info, cpu) == NULL) return; if (!cpumask_test_cpu(cpu, to_cpumask(cache_dev_map))) return; @@ -954,7 +958,7 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev) for (i = 0; i < num_cache_leaves; i++) kobject_put(&(INDEX_KOBJECT_PTR(cpu, i)->kobj)); - kobject_put(per_cpu(cache_kobject, cpu)); + kobject_put(per_cpu(ici_cache_kobject, cpu)); cpuid4_cache_sysfs_exit(cpu); } diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 472763d9209..73734baa50f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -74,7 +74,7 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs) m->finished = 0; } -static cpumask_t mce_inject_cpumask; +static cpumask_var_t mce_inject_cpumask; static int mce_raise_notify(struct notifier_block *self, unsigned long val, void *data) @@ -82,9 +82,9 @@ static int mce_raise_notify(struct notifier_block *self, struct die_args *args = (struct die_args *)data; int cpu = smp_processor_id(); struct mce *m = &__get_cpu_var(injectm); - if (val != DIE_NMI_IPI || !cpu_isset(cpu, mce_inject_cpumask)) + if (val != DIE_NMI_IPI || !cpumask_test_cpu(cpu, mce_inject_cpumask)) return NOTIFY_DONE; - cpu_clear(cpu, mce_inject_cpumask); + cpumask_clear_cpu(cpu, mce_inject_cpumask); if (m->inject_flags & MCJ_EXCEPTION) raise_exception(m, args->regs); else if (m->status) @@ -148,22 +148,22 @@ static void raise_mce(struct mce *m) unsigned long start; int cpu; get_online_cpus(); - mce_inject_cpumask = cpu_online_map; - cpu_clear(get_cpu(), mce_inject_cpumask); + cpumask_copy(mce_inject_cpumask, cpu_online_mask); + cpumask_clear_cpu(get_cpu(), mce_inject_cpumask); for_each_online_cpu(cpu) { struct mce *mcpu = &per_cpu(injectm, cpu); if (!mcpu->finished || MCJ_CTX(mcpu->inject_flags) != MCJ_CTX_RANDOM) - cpu_clear(cpu, mce_inject_cpumask); + cpumask_clear_cpu(cpu, mce_inject_cpumask); } - if (!cpus_empty(mce_inject_cpumask)) - apic->send_IPI_mask(&mce_inject_cpumask, NMI_VECTOR); + if (!cpumask_empty(mce_inject_cpumask)) + apic->send_IPI_mask(mce_inject_cpumask, NMI_VECTOR); start = jiffies; - while (!cpus_empty(mce_inject_cpumask)) { + while (!cpumask_empty(mce_inject_cpumask)) { if (!time_before(jiffies, start + 2*HZ)) { printk(KERN_ERR "Timeout waiting for mce inject NMI %lx\n", - *cpus_addr(mce_inject_cpumask)); + *cpumask_bits(mce_inject_cpumask)); break; } cpu_relax(); @@ -210,6 +210,8 @@ static ssize_t mce_write(struct file *filp, const char __user *ubuf, static int inject_init(void) { + if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL)) + return -ENOMEM; printk(KERN_INFO "Machine check injector initialized\n"); mce_chrdev_ops.write = mce_write; register_die_notifier(&mce_raise_nb); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 0bcaa387586..a8aacd4b513 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1388,13 +1388,14 @@ static void __mcheck_cpu_init_timer(void) struct timer_list *t = &__get_cpu_var(mce_timer); int *n = &__get_cpu_var(mce_next_interval); + setup_timer(t, mce_start_timer, smp_processor_id()); + if (mce_ignore_ce) return; *n = check_interval * HZ; if (!*n) return; - setup_timer(t, mce_start_timer, smp_processor_id()); t->expires = round_jiffies(jiffies + *n); add_timer_on(t, smp_processor_id()); } @@ -1928,7 +1929,7 @@ error2: sysdev_remove_file(&per_cpu(mce_dev, cpu), &mce_banks[j].attr); error: while (--i >= 0) - sysdev_remove_file(&per_cpu(mce_dev, cpu), &mce_banks[i].attr); + sysdev_remove_file(&per_cpu(mce_dev, cpu), mce_attrs[i]); sysdev_unregister(&per_cpu(mce_dev, cpu)); @@ -2016,9 +2017,11 @@ 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/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 4fef985fc22..81c499eceb2 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -256,6 +256,16 @@ asmlinkage void smp_thermal_interrupt(struct pt_regs *regs) ack_APIC_irq(); } +/* Thermal monitoring depends on APIC, ACPI and clock modulation */ +static int intel_thermal_supported(struct cpuinfo_x86 *c) +{ + if (!cpu_has_apic) + return 0; + if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC)) + return 0; + return 1; +} + void __init mcheck_intel_therm_init(void) { /* @@ -263,8 +273,7 @@ void __init mcheck_intel_therm_init(void) * 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)) + if (intel_thermal_supported(&boot_cpu_data)) lvtthmr_init = apic_read(APIC_LVTTHMR); } @@ -274,8 +283,7 @@ void intel_init_thermal(struct cpuinfo_x86 *c) 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)) + if (!intel_thermal_supported(c)) return; /* @@ -339,8 +347,8 @@ void intel_init_thermal(struct cpuinfo_x86 *c) l = apic_read(APIC_LVTTHMR); apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); - printk(KERN_INFO "CPU%d: Thermal monitoring enabled (%s)\n", - cpu, tm2 ? "TM2" : "TM1"); + printk_once(KERN_INFO "CPU0: Thermal monitoring enabled (%s)\n", + tm2 ? "TM2" : "TM1"); /* enable thermal throttle processing */ atomic_set(&therm_throt_en, 1); diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 73c86db5acb..09b1698e046 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -170,6 +170,41 @@ static int __init cmp_range(const void *x1, const void *x2) return start1 - start2; } +static int __init clean_sort_range(struct res_range *range, int az) +{ + int i, j, k = az - 1, nr_range = 0; + + for (i = 0; i < k; i++) { + if (range[i].end) + continue; + for (j = k; j > i; j--) { + if (range[j].end) { + k = j; + break; + } + } + if (j == i) + break; + range[i].start = range[k].start; + range[i].end = range[k].end; + range[k].start = 0; + range[k].end = 0; + k--; + } + /* count it */ + for (i = 0; i < az; i++) { + if (!range[i].end) { + nr_range = i; + break; + } + } + + /* sort them */ + sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); + + return nr_range; +} + #define BIOS_BUG_MSG KERN_WARNING \ "WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n" @@ -223,22 +258,18 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range, subtract_range(range, extra_remove_base, extra_remove_base + extra_remove_size - 1); - /* get new range num */ - nr_range = 0; - for (i = 0; i < RANGE_NUM; i++) { - if (!range[i].end) - continue; - nr_range++; - } if (debug_print) { printk(KERN_DEBUG "After UC checking\n"); - for (i = 0; i < nr_range; i++) + for (i = 0; i < RANGE_NUM; i++) { + if (!range[i].end) + continue; printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", range[i].start, range[i].end + 1); + } } /* sort the ranges */ - sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); + nr_range = clean_sort_range(range, RANGE_NUM); if (debug_print) { printk(KERN_DEBUG "After sorting\n"); for (i = 0; i < nr_range; i++) @@ -689,8 +720,6 @@ static int __init mtrr_need_cleanup(void) continue; if (!size) type = MTRR_NUM_TYPES; - if (type == MTRR_TYPE_WRPROT) - type = MTRR_TYPE_UNCACHABLE; num[type]++; } diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 3c1b12d461d..e006e56f699 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -4,6 +4,7 @@ #include <linux/proc_fs.h> #include <linux/module.h> #include <linux/ctype.h> +#include <linux/string.h> #include <linux/init.h> #define LINE_SIZE 80 @@ -133,8 +134,7 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos) return -EINVAL; base = simple_strtoull(line + 5, &ptr, 0); - while (isspace(*ptr)) - ptr++; + ptr = skip_spaces(ptr); if (strncmp(ptr, "size=", 5)) return -EINVAL; @@ -142,14 +142,11 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos) size = simple_strtoull(ptr + 5, &ptr, 0); if ((base & 0xfff) || (size & 0xfff)) return -EINVAL; - while (isspace(*ptr)) - ptr++; + ptr = skip_spaces(ptr); if (strncmp(ptr, "type=", 5)) return -EINVAL; - ptr += 5; - while (isspace(*ptr)) - ptr++; + ptr = skip_spaces(ptr + 5); for (i = 0; i < MTRR_NUM_TYPES; ++i) { if (strcmp(ptr, mtrr_strings[i])) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index c1bbed1021d..8c1c07073cc 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1286,7 +1286,7 @@ x86_perf_event_set_period(struct perf_event *event, return 0; /* - * If we are way outside a reasoable range then just skip forward: + * If we are way outside a reasonable range then just skip forward: */ if (unlikely(left <= -period)) { left = period; @@ -1343,6 +1343,13 @@ intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx) bits |= 0x2; if (hwc->config & ARCH_PERFMON_EVENTSEL_OS) bits |= 0x1; + + /* + * ANY bit is supported in v3 and up + */ + if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY) + bits |= 0x4; + bits <<= (idx * 4); mask = 0xfULL << (idx * 4); @@ -1632,6 +1639,7 @@ static void intel_pmu_drain_bts_buffer(struct cpu_hw_events *cpuc) data.period = event->hw.last_period; data.addr = 0; + data.raw = NULL; regs.ip = 0; /* @@ -1749,6 +1757,7 @@ static int p6_pmu_handle_irq(struct pt_regs *regs) u64 val; data.addr = 0; + data.raw = NULL; cpuc = &__get_cpu_var(cpu_hw_events); @@ -1794,6 +1803,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) u64 ack, status; data.addr = 0; + data.raw = NULL; cpuc = &__get_cpu_var(cpu_hw_events); @@ -1857,6 +1867,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs) u64 val; data.addr = 0; + data.raw = NULL; cpuc = &__get_cpu_var(cpu_hw_events); @@ -2062,12 +2073,6 @@ static __init int p6_pmu_init(void) x86_pmu = p6_pmu; - if (!cpu_has_apic) { - pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n"); - pr_info("no hardware sampling interrupt available.\n"); - x86_pmu.apic = 0; - } - return 0; } @@ -2159,6 +2164,16 @@ static __init int amd_pmu_init(void) return 0; } +static void __init pmu_check_apic(void) +{ + if (cpu_has_apic) + return; + + x86_pmu.apic = 0; + pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n"); + pr_info("no hardware sampling interrupt available.\n"); +} + void __init init_hw_perf_events(void) { int err; @@ -2180,6 +2195,8 @@ void __init init_hw_perf_events(void) return; } + pmu_check_apic(); + pr_cont("%s PMU driver.\n", x86_pmu.name); if (x86_pmu.num_events > X86_PMC_MAX_GENERIC) { @@ -2287,7 +2304,7 @@ void callchain_store(struct perf_callchain_entry *entry, u64 ip) static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry); static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry); -static DEFINE_PER_CPU(int, in_nmi_frame); +static DEFINE_PER_CPU(int, in_ignored_frame); static void @@ -2303,8 +2320,9 @@ static void backtrace_warning(void *data, char *msg) static int backtrace_stack(void *data, char *name) { - per_cpu(in_nmi_frame, smp_processor_id()) = - x86_is_stack_id(NMI_STACK, name); + per_cpu(in_ignored_frame, smp_processor_id()) = + x86_is_stack_id(NMI_STACK, name) || + x86_is_stack_id(DEBUG_STACK, name); return 0; } @@ -2313,7 +2331,7 @@ static void backtrace_address(void *data, unsigned long addr, int reliable) { struct perf_callchain_entry *entry = data; - if (per_cpu(in_nmi_frame, smp_processor_id())) + if (per_cpu(in_ignored_frame, smp_processor_id())) return; if (reliable) @@ -2325,6 +2343,7 @@ static const struct stacktrace_ops backtrace_ops = { .warning_symbol = backtrace_warning_symbol, .stack = backtrace_stack, .address = backtrace_address, + .walk_stack = print_context_stack_bp, }; #include "../dumpstack.h" @@ -2335,7 +2354,7 @@ perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry) callchain_store(entry, PERF_CONTEXT_KERNEL); callchain_store(entry, regs->ip); - dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry); + dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry); } /* diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 7ef24a79699..cb27fd6136c 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -187,7 +187,8 @@ 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; @@ -216,7 +217,7 @@ 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; } diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c index ef42a038f1a..1c47390dd0e 100644 --- a/arch/x86/kernel/ds.c +++ b/arch/x86/kernel/ds.c @@ -265,13 +265,13 @@ struct ds_context { int cpu; }; -static DEFINE_PER_CPU(struct ds_context *, cpu_context); +static DEFINE_PER_CPU(struct ds_context *, cpu_ds_context); static struct ds_context *ds_get_context(struct task_struct *task, int cpu) { struct ds_context **p_context = - (task ? &task->thread.ds_ctx : &per_cpu(cpu_context, cpu)); + (task ? &task->thread.ds_ctx : &per_cpu(cpu_ds_context, cpu)); struct ds_context *context = NULL; struct ds_context *new_context = NULL; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index b8ce165dde5..6d817554780 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -109,6 +109,32 @@ print_context_stack(struct thread_info *tinfo, } return bp; } +EXPORT_SYMBOL_GPL(print_context_stack); + +unsigned long +print_context_stack_bp(struct thread_info *tinfo, + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data, + unsigned long *end, int *graph) +{ + struct stack_frame *frame = (struct stack_frame *)bp; + unsigned long *ret_addr = &frame->return_address; + + while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) { + unsigned long addr = *ret_addr; + + if (!__kernel_text_address(addr)) + break; + + ops->address(data, addr, 1); + frame = frame->next_frame; + ret_addr = &frame->return_address; + print_ftrace_graph_addr(addr, data, ops, tinfo, graph); + } + + return (unsigned long)frame; +} +EXPORT_SYMBOL_GPL(print_context_stack_bp); static void @@ -141,10 +167,11 @@ static void print_trace_address(void *data, unsigned long addr, int reliable) } static const struct stacktrace_ops print_trace_ops = { - .warning = print_trace_warning, - .warning_symbol = print_trace_warning_symbol, - .stack = print_trace_stack, - .address = print_trace_address, + .warning = print_trace_warning, + .warning_symbol = print_trace_warning_symbol, + .stack = print_trace_stack, + .address = print_trace_address, + .walk_stack = print_context_stack, }; void @@ -188,7 +215,7 @@ void dump_stack(void) } EXPORT_SYMBOL(dump_stack); -static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED; +static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED; static int die_owner = -1; static unsigned int die_nest_count; @@ -207,11 +234,11 @@ unsigned __kprobes long oops_begin(void) /* racy, but better than risking deadlock. */ raw_local_irq_save(flags); cpu = smp_processor_id(); - if (!__raw_spin_trylock(&die_lock)) { + if (!arch_spin_trylock(&die_lock)) { if (cpu == die_owner) /* nested oops. should stop eventually */; else - __raw_spin_lock(&die_lock); + arch_spin_lock(&die_lock); } die_nest_count++; die_owner = cpu; @@ -231,7 +258,7 @@ void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr) die_nest_count--; if (!die_nest_count) /* Nest count reaches zero, release the lock. */ - __raw_spin_unlock(&die_lock); + arch_spin_unlock(&die_lock); raw_local_irq_restore(flags); oops_exit(); diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h index 81086c227ab..4fd1420faff 100644 --- a/arch/x86/kernel/dumpstack.h +++ b/arch/x86/kernel/dumpstack.h @@ -14,12 +14,6 @@ #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) #endif -extern unsigned long -print_context_stack(struct thread_info *tinfo, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data, - unsigned long *end, int *graph); - extern void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, char *log_lvl); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index e0ed4c7abb6..ae775ca47b2 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -58,7 +58,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, context = (struct thread_info *) ((unsigned long)stack & (~(THREAD_SIZE - 1))); - bp = print_context_stack(context, stack, bp, ops, data, NULL, &graph); + bp = ops->walk_stack(context, stack, bp, ops, data, NULL, &graph); stack = (unsigned long *)context->previous_esp; if (!stack) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 8e740934bd1..0ad9597073f 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -103,6 +103,35 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, return NULL; } +static inline int +in_irq_stack(unsigned long *stack, unsigned long *irq_stack, + unsigned long *irq_stack_end) +{ + return (stack >= irq_stack && stack < irq_stack_end); +} + +/* + * We are returning from the irq stack and go to the previous one. + * If the previous stack is also in the irq stack, then bp in the first + * frame of the irq stack points to the previous, interrupted one. + * Otherwise we have another level of indirection: We first save + * the bp of the previous stack, then we switch the stack to the irq one + * and save a new bp that links to the previous one. + * (See save_args()) + */ +static inline unsigned long +fixup_bp_irq_link(unsigned long bp, unsigned long *stack, + unsigned long *irq_stack, unsigned long *irq_stack_end) +{ +#ifdef CONFIG_FRAME_POINTER + struct stack_frame *frame = (struct stack_frame *)bp; + + if (!in_irq_stack(stack, irq_stack, irq_stack_end)) + return (unsigned long)frame->next_frame; +#endif + return bp; +} + /* * x86-64 can have up to three kernel stacks: * process stack @@ -159,8 +188,8 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (ops->stack(data, id) < 0) break; - bp = print_context_stack(tinfo, stack, bp, ops, - data, estack_end, &graph); + bp = ops->walk_stack(tinfo, stack, bp, ops, + data, estack_end, &graph); ops->stack(data, "<EOE>"); /* * We link to the next stack via the @@ -175,7 +204,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, irq_stack = irq_stack_end - (IRQ_STACK_SIZE - 64) / sizeof(*irq_stack); - if (stack >= irq_stack && stack < irq_stack_end) { + if (in_irq_stack(stack, irq_stack, irq_stack_end)) { if (ops->stack(data, "IRQ") < 0) break; bp = print_context_stack(tinfo, stack, bp, @@ -186,6 +215,8 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, * pointer (index -1 to end) in the IRQ stack: */ stack = (unsigned long *) (irq_stack_end[-1]); + bp = fixup_bp_irq_link(bp, stack, irq_stack, + irq_stack_end); irq_stack_end = NULL; ops->stack(data, "EOI"); continue; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d17d482a04f..a1a7876cadc 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -724,7 +724,7 @@ core_initcall(e820_mark_nvs_memory); /* * Early reserved memory areas. */ -#define MAX_EARLY_RES 20 +#define MAX_EARLY_RES 32 struct early_res { u64 start, end; @@ -732,7 +732,16 @@ struct early_res { char overlap_ok; }; static struct early_res early_res[MAX_EARLY_RES] __initdata = { - { 0, PAGE_SIZE, "BIOS data page" }, /* BIOS data page */ + { 0, PAGE_SIZE, "BIOS data page", 1 }, /* BIOS data page */ +#if defined(CONFIG_X86_32) && defined(CONFIG_X86_TRAMPOLINE) + /* + * But first pinch a few for the stack/trampoline stuff + * FIXME: Don't need the extra page at 4K, but need to fix + * trampoline before removing it. (see the GDT stuff) + */ + { PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE", 1 }, +#endif + {} }; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 50b9c220e12..44a8e0dc673 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -725,22 +725,61 @@ END(syscall_badsys) /* * System calls that need a pt_regs pointer. */ -#define PTREGSCALL(name) \ +#define PTREGSCALL0(name) \ ALIGN; \ ptregs_##name: \ leal 4(%esp),%eax; \ jmp sys_##name; -PTREGSCALL(iopl) -PTREGSCALL(fork) -PTREGSCALL(clone) -PTREGSCALL(vfork) -PTREGSCALL(execve) -PTREGSCALL(sigaltstack) -PTREGSCALL(sigreturn) -PTREGSCALL(rt_sigreturn) -PTREGSCALL(vm86) -PTREGSCALL(vm86old) +#define PTREGSCALL1(name) \ + ALIGN; \ +ptregs_##name: \ + leal 4(%esp),%edx; \ + movl (PT_EBX+4)(%esp),%eax; \ + jmp sys_##name; + +#define PTREGSCALL2(name) \ + ALIGN; \ +ptregs_##name: \ + leal 4(%esp),%ecx; \ + movl (PT_ECX+4)(%esp),%edx; \ + movl (PT_EBX+4)(%esp),%eax; \ + jmp sys_##name; + +#define PTREGSCALL3(name) \ + ALIGN; \ +ptregs_##name: \ + leal 4(%esp),%eax; \ + pushl %eax; \ + movl PT_EDX(%eax),%ecx; \ + movl PT_ECX(%eax),%edx; \ + movl PT_EBX(%eax),%eax; \ + call sys_##name; \ + addl $4,%esp; \ + ret + +PTREGSCALL1(iopl) +PTREGSCALL0(fork) +PTREGSCALL0(vfork) +PTREGSCALL3(execve) +PTREGSCALL2(sigaltstack) +PTREGSCALL0(sigreturn) +PTREGSCALL0(rt_sigreturn) +PTREGSCALL2(vm86) +PTREGSCALL1(vm86old) + +/* Clone is an oddball. The 4th arg is in %edi */ + ALIGN; +ptregs_clone: + leal 4(%esp),%eax + pushl %eax + pushl PT_EDI(%eax) + movl PT_EDX(%eax),%ecx + movl PT_ECX(%eax),%edx + movl PT_EBX(%eax),%eax + call sys_clone + addl $8,%esp + ret .macro FIXUP_ESPFIX_STACK /* @@ -1008,12 +1047,8 @@ END(spurious_interrupt_bug) ENTRY(kernel_thread_helper) pushl $0 # fake return address for unwinder CFI_STARTPROC - movl %edx,%eax - push %edx - CFI_ADJUST_CFA_OFFSET 4 - call *%ebx - push %eax - CFI_ADJUST_CFA_OFFSET 4 + movl %edi,%eax + call *%esi call do_exit ud2 # padding for call trace CFI_ENDPROC diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 4deb8fc849d..0697ff13983 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -977,8 +977,8 @@ apicinterrupt UV_BAU_MESSAGE \ #endif apicinterrupt LOCAL_TIMER_VECTOR \ apic_timer_interrupt smp_apic_timer_interrupt -apicinterrupt GENERIC_INTERRUPT_VECTOR \ - generic_interrupt smp_generic_interrupt +apicinterrupt X86_PLATFORM_IPI_VECTOR \ + x86_platform_ipi smp_x86_platform_ipi #ifdef CONFIG_SMP apicinterrupt INVALIDATE_TLB_VECTOR_START+0 \ @@ -1076,10 +1076,10 @@ ENTRY(\sym) TRACE_IRQS_OFF movq %rsp,%rdi /* pt_regs pointer */ xorl %esi,%esi /* no error code */ - PER_CPU(init_tss, %rbp) - subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp) + PER_CPU(init_tss, %r12) + subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%r12) call \do_sym - addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp) + addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%r12) jmp paranoid_exit /* %ebx: no swapgs flag */ CFI_ENDPROC END(\sym) @@ -1166,63 +1166,20 @@ bad_gs: jmp 2b .previous -/* - * Create a kernel thread. - * - * C extern interface: - * extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) - * - * asm input arguments: - * rdi: fn, rsi: arg, rdx: flags - */ -ENTRY(kernel_thread) - CFI_STARTPROC - FAKE_STACK_FRAME $child_rip - SAVE_ALL - - # rdi: flags, rsi: usp, rdx: will be &pt_regs - movq %rdx,%rdi - orq kernel_thread_flags(%rip),%rdi - movq $-1, %rsi - movq %rsp, %rdx - - xorl %r8d,%r8d - xorl %r9d,%r9d - - # clone now - call do_fork - movq %rax,RAX(%rsp) - xorl %edi,%edi - - /* - * It isn't worth to check for reschedule here, - * so internally to the x86_64 port you can rely on kernel_thread() - * not to reschedule the child before returning, this avoids the need - * of hacks for example to fork off the per-CPU idle tasks. - * [Hopefully no generic code relies on the reschedule -AK] - */ - RESTORE_ALL - UNFAKE_STACK_FRAME - ret - CFI_ENDPROC -END(kernel_thread) - -ENTRY(child_rip) +ENTRY(kernel_thread_helper) pushq $0 # fake return address CFI_STARTPROC /* * Here we are in the child and the registers are set as they were * at kernel_thread() invocation in the parent. */ - movq %rdi, %rax - movq %rsi, %rdi - call *%rax + call *%rsi # exit mov %eax, %edi call do_exit ud2 # padding for call trace CFI_ENDPROC -END(child_rip) +END(kernel_thread_helper) /* * execve(). This function needs to use IRET, not SYSRET, to set up all state properly. diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 5a1b9758fd6..30968924543 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -189,9 +189,26 @@ static void wait_for_nmi(void) nmi_wait_count++; } +static inline int +within(unsigned long addr, unsigned long start, unsigned long end) +{ + return addr >= start && addr < end; +} + static int do_ftrace_mod_code(unsigned long ip, void *new_code) { + /* + * On x86_64, kernel text mappings are mapped read-only with + * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead + * of the kernel text mapping to modify the kernel text. + * + * For 32bit kernels, these mappings are same and we can use + * kernel identity mapping to modify code. + */ + if (within(ip, (unsigned long)_text, (unsigned long)_etext)) + ip = (unsigned long)__va(__pa(ip)); + mod_code_ip = (void *)ip; mod_code_newcode = new_code; diff --git a/arch/x86/kernel/geode_32.c b/arch/x86/kernel/geode_32.c deleted file mode 100644 index 9b08e852fd1..00000000000 --- a/arch/x86/kernel/geode_32.c +++ /dev/null @@ -1,196 +0,0 @@ -/* - * AMD Geode southbridge support code - * Copyright (C) 2006, Advanced Micro Devices, Inc. - * Copyright (C) 2007, Andres Salomon <dilinger@debian.org> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public License - * as published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/ioport.h> -#include <linux/io.h> -#include <asm/msr.h> -#include <asm/geode.h> - -static struct { - char *name; - u32 msr; - int size; - u32 base; -} lbars[] = { - { "geode-pms", MSR_LBAR_PMS, LBAR_PMS_SIZE, 0 }, - { "geode-acpi", MSR_LBAR_ACPI, LBAR_ACPI_SIZE, 0 }, - { "geode-gpio", MSR_LBAR_GPIO, LBAR_GPIO_SIZE, 0 }, - { "geode-mfgpt", MSR_LBAR_MFGPT, LBAR_MFGPT_SIZE, 0 } -}; - -static void __init init_lbars(void) -{ - u32 lo, hi; - int i; - - for (i = 0; i < ARRAY_SIZE(lbars); i++) { - rdmsr(lbars[i].msr, lo, hi); - if (hi & 0x01) - lbars[i].base = lo & 0x0000ffff; - - if (lbars[i].base == 0) - printk(KERN_ERR "geode: Couldn't initialize '%s'\n", - lbars[i].name); - } -} - -int geode_get_dev_base(unsigned int dev) -{ - BUG_ON(dev >= ARRAY_SIZE(lbars)); - return lbars[dev].base; -} -EXPORT_SYMBOL_GPL(geode_get_dev_base); - -/* === GPIO API === */ - -void geode_gpio_set(u32 gpio, unsigned int reg) -{ - u32 base = geode_get_dev_base(GEODE_DEV_GPIO); - - if (!base) - return; - - /* low bank register */ - if (gpio & 0xFFFF) - outl(gpio & 0xFFFF, base + reg); - /* high bank register */ - gpio >>= 16; - if (gpio) - outl(gpio, base + 0x80 + reg); -} -EXPORT_SYMBOL_GPL(geode_gpio_set); - -void geode_gpio_clear(u32 gpio, unsigned int reg) -{ - u32 base = geode_get_dev_base(GEODE_DEV_GPIO); - - if (!base) - return; - - /* low bank register */ - if (gpio & 0xFFFF) - outl((gpio & 0xFFFF) << 16, base + reg); - /* high bank register */ - gpio &= (0xFFFF << 16); - if (gpio) - outl(gpio, base + 0x80 + reg); -} -EXPORT_SYMBOL_GPL(geode_gpio_clear); - -int geode_gpio_isset(u32 gpio, unsigned int reg) -{ - u32 base = geode_get_dev_base(GEODE_DEV_GPIO); - u32 val; - - if (!base) - return 0; - - /* low bank register */ - if (gpio & 0xFFFF) { - val = inl(base + reg) & (gpio & 0xFFFF); - if ((gpio & 0xFFFF) == val) - return 1; - } - /* high bank register */ - gpio >>= 16; - if (gpio) { - val = inl(base + 0x80 + reg) & gpio; - if (gpio == val) - return 1; - } - return 0; -} -EXPORT_SYMBOL_GPL(geode_gpio_isset); - -void geode_gpio_set_irq(unsigned int group, unsigned int irq) -{ - u32 lo, hi; - - if (group > 7 || irq > 15) - return; - - rdmsr(MSR_PIC_ZSEL_HIGH, lo, hi); - - lo &= ~(0xF << (group * 4)); - lo |= (irq & 0xF) << (group * 4); - - wrmsr(MSR_PIC_ZSEL_HIGH, lo, hi); -} -EXPORT_SYMBOL_GPL(geode_gpio_set_irq); - -void geode_gpio_setup_event(unsigned int gpio, int pair, int pme) -{ - u32 base = geode_get_dev_base(GEODE_DEV_GPIO); - u32 offset, shift, val; - - if (gpio >= 24) - offset = GPIO_MAP_W; - else if (gpio >= 16) - offset = GPIO_MAP_Z; - else if (gpio >= 8) - offset = GPIO_MAP_Y; - else - offset = GPIO_MAP_X; - - shift = (gpio % 8) * 4; - - val = inl(base + offset); - - /* Clear whatever was there before */ - val &= ~(0xF << shift); - - /* And set the new value */ - - val |= ((pair & 7) << shift); - - /* Set the PME bit if this is a PME event */ - - if (pme) - val |= (1 << (shift + 3)); - - outl(val, base + offset); -} -EXPORT_SYMBOL_GPL(geode_gpio_setup_event); - -int geode_has_vsa2(void) -{ - static int has_vsa2 = -1; - - if (has_vsa2 == -1) { - u16 val; - - /* - * The VSA has virtual registers that we can query for a - * signature. - */ - outw(VSA_VR_UNLOCK, VSA_VRC_INDEX); - outw(VSA_VR_SIGNATURE, VSA_VRC_INDEX); - - val = inw(VSA_VRC_DATA); - has_vsa2 = (val == AMD_VSA_SIG || val == GSW_VSA_SIG); - } - - return has_vsa2; -} -EXPORT_SYMBOL_GPL(geode_has_vsa2); - -static int __init geode_southbridge_init(void) -{ - if (!is_geode()) - return -ENODEV; - - init_lbars(); - (void) mfgpt_timer_setup(); - return 0; -} - -postcore_initcall(geode_southbridge_init); diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 4f8e2507e8f..5051b94c906 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -29,8 +29,6 @@ static void __init i386_default_early_setup(void) void __init i386_start_kernel(void) { - reserve_trampoline_memory(); - reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 0b06cd778fd..b5a9896ca1e 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -98,8 +98,6 @@ void __init x86_64_start_reservations(char *real_mode_data) { copy_bootdata(__va(real_mode_data)); - reserve_trampoline_memory(); - reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 050c278481b..7fd318bac59 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -18,6 +18,8 @@ #include <asm/asm-offsets.h> #include <asm/setup.h> #include <asm/processor-flags.h> +#include <asm/msr-index.h> +#include <asm/cpufeature.h> #include <asm/percpu.h> /* Physical address */ @@ -297,25 +299,27 @@ ENTRY(startup_32_smp) orl %edx,%eax movl %eax,%cr4 - btl $5, %eax # check if PAE is enabled - jnc 6f + testb $X86_CR4_PAE, %al # check if PAE is enabled + jz 6f /* Check if extended functions are implemented */ movl $0x80000000, %eax cpuid - cmpl $0x80000000, %eax - jbe 6f + /* Value must be in the range 0x80000001 to 0x8000ffff */ + subl $0x80000001, %eax + cmpl $(0x8000ffff-0x80000001), %eax + ja 6f mov $0x80000001, %eax cpuid /* Execute Disable bit supported? */ - btl $20, %edx + btl $(X86_FEATURE_NX & 31), %edx jnc 6f /* Setup EFER (Extended Feature Enable Register) */ - movl $0xc0000080, %ecx + movl $MSR_EFER, %ecx rdmsr - btsl $11, %eax + btsl $_EFER_NX, %eax /* Make changes effective */ wrmsr diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 22db86a3764..2d8b5035371 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -262,11 +262,11 @@ ENTRY(secondary_startup_64) .quad x86_64_start_kernel ENTRY(initial_gs) .quad INIT_PER_CPU_VAR(irq_stack_union) - __FINITDATA ENTRY(stack_start) .quad init_thread_union+THREAD_SIZE-8 .word 0 + __FINITDATA bad_address: jmp bad_address @@ -340,6 +340,7 @@ ENTRY(name) i = i + 1 ; \ .endr + .data /* * This default setting generates an ident mapping at address 0x100000 * and a mapping for the kernel that precisely maps virtual address diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index dedc2bddf7a..ba6e6588460 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -33,6 +33,7 @@ * HPET address is set in acpi/boot.c, when an ACPI entry exists */ unsigned long hpet_address; +u8 hpet_blockid; /* OS timer block num */ #ifdef CONFIG_PCI_MSI static unsigned long hpet_num_timers; #endif @@ -47,12 +48,12 @@ struct hpet_dev { char name[10]; }; -unsigned long hpet_readl(unsigned long a) +inline unsigned int hpet_readl(unsigned int a) { return readl(hpet_virt_address + a); } -static inline void hpet_writel(unsigned long d, unsigned long a) +static inline void hpet_writel(unsigned int d, unsigned int a) { writel(d, hpet_virt_address + a); } @@ -167,7 +168,7 @@ do { \ static void hpet_reserve_msi_timers(struct hpet_data *hd); -static void hpet_reserve_platform_timers(unsigned long id) +static void hpet_reserve_platform_timers(unsigned int id) { struct hpet __iomem *hpet = hpet_virt_address; struct hpet_timer __iomem *timer = &hpet->hpet_timers[2]; @@ -205,7 +206,7 @@ static void hpet_reserve_platform_timers(unsigned long id) } #else -static void hpet_reserve_platform_timers(unsigned long id) { } +static void hpet_reserve_platform_timers(unsigned int id) { } #endif /* @@ -246,7 +247,7 @@ static void hpet_reset_counter(void) static void hpet_start_counter(void) { - unsigned long cfg = hpet_readl(HPET_CFG); + unsigned int cfg = hpet_readl(HPET_CFG); cfg |= HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); } @@ -271,7 +272,7 @@ static void hpet_resume_counter(void) static void hpet_enable_legacy_int(void) { - unsigned long cfg = hpet_readl(HPET_CFG); + unsigned int cfg = hpet_readl(HPET_CFG); cfg |= HPET_CFG_LEGACY; hpet_writel(cfg, HPET_CFG); @@ -314,7 +315,7 @@ static int hpet_setup_msi_irq(unsigned int irq); static void hpet_set_mode(enum clock_event_mode mode, struct clock_event_device *evt, int timer) { - unsigned long cfg, cmp, now; + unsigned int cfg, cmp, now; uint64_t delta; switch (mode) { @@ -323,7 +324,7 @@ static void hpet_set_mode(enum clock_event_mode mode, delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult; delta >>= evt->shift; now = hpet_readl(HPET_COUNTER); - cmp = now + (unsigned long) delta; + cmp = now + (unsigned int) delta; cfg = hpet_readl(HPET_Tn_CFG(timer)); /* Make sure we use edge triggered interrupts */ cfg &= ~HPET_TN_LEVEL; @@ -339,7 +340,7 @@ static void hpet_set_mode(enum clock_event_mode mode, * (See AMD-8111 HyperTransport I/O Hub Data Sheet, * Publication # 24674) */ - hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer)); + hpet_writel((unsigned int) delta, HPET_Tn_CMP(timer)); hpet_start_counter(); hpet_print_config(); break; @@ -383,13 +384,24 @@ 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. */ - WARN_ON_ONCE((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt); + WARN_ONCE(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; + return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0; } static void hpet_legacy_set_mode(enum clock_event_mode mode, @@ -415,7 +427,7 @@ static struct hpet_dev *hpet_devs; void hpet_msi_unmask(unsigned int irq) { struct hpet_dev *hdev = get_irq_data(irq); - unsigned long cfg; + unsigned int cfg; /* unmask it */ cfg = hpet_readl(HPET_Tn_CFG(hdev->num)); @@ -425,7 +437,7 @@ void hpet_msi_unmask(unsigned int irq) void hpet_msi_mask(unsigned int irq) { - unsigned long cfg; + unsigned int cfg; struct hpet_dev *hdev = get_irq_data(irq); /* mask it */ @@ -467,7 +479,7 @@ static int hpet_msi_next_event(unsigned long delta, static int hpet_setup_msi_irq(unsigned int irq) { - if (arch_setup_hpet_msi(irq)) { + if (arch_setup_hpet_msi(irq, hpet_blockid)) { destroy_irq(irq); return -EINVAL; } @@ -584,6 +596,8 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) unsigned int num_timers_used = 0; int i; + if (boot_cpu_has(X86_FEATURE_ARAT)) + return; id = hpet_readl(HPET_ID); num_timers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT); @@ -598,7 +612,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) for (i = start_timer; i < num_timers - RESERVE_TIMERS; i++) { struct hpet_dev *hdev = &hpet_devs[num_timers_used]; - unsigned long cfg = hpet_readl(HPET_Tn_CFG(i)); + unsigned int cfg = hpet_readl(HPET_Tn_CFG(i)); /* Only consider HPET timer with MSI support */ if (!(cfg & HPET_TN_FSB_CAP)) @@ -813,7 +827,7 @@ static int hpet_clocksource_register(void) */ int __init hpet_enable(void) { - unsigned long id; + unsigned int id; int i; if (!is_hpet_capable()) @@ -872,10 +886,8 @@ int __init hpet_enable(void) if (id & HPET_ID_LEGSUP) { hpet_legacy_clockevent_register(); - hpet_msi_capability_lookup(2); return 1; } - hpet_msi_capability_lookup(0); return 0; out_nohpet: @@ -908,9 +920,17 @@ static __init int hpet_late_init(void) if (!hpet_virt_address) return -ENODEV; + if (hpet_readl(HPET_ID) & HPET_ID_LEGSUP) + hpet_msi_capability_lookup(2); + else + hpet_msi_capability_lookup(0); + hpet_reserve_platform_timers(hpet_readl(HPET_ID)); hpet_print_config(); + if (boot_cpu_has(X86_FEATURE_ARAT)) + return 0; + for_each_online_cpu(cpu) { hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu); } @@ -925,7 +945,7 @@ fs_initcall(hpet_late_init); void hpet_disable(void) { if (is_hpet_capable()) { - unsigned long cfg = hpet_readl(HPET_CFG); + unsigned int cfg = hpet_readl(HPET_CFG); if (hpet_legacy_int_enabled) { cfg &= ~HPET_CFG_LEGACY; @@ -965,8 +985,8 @@ static int hpet_prev_update_sec; static struct rtc_time hpet_alarm_time; static unsigned long hpet_pie_count; static u32 hpet_t1_cmp; -static unsigned long hpet_default_delta; -static unsigned long hpet_pie_delta; +static u32 hpet_default_delta; +static u32 hpet_pie_delta; static unsigned long hpet_pie_limit; static rtc_irq_handler irq_handler; @@ -1017,7 +1037,8 @@ EXPORT_SYMBOL_GPL(hpet_unregister_irq_handler); */ int hpet_rtc_timer_init(void) { - unsigned long cfg, cnt, delta, flags; + unsigned int cfg, cnt, delta; + unsigned long flags; if (!is_hpet_enabled()) return 0; @@ -1027,7 +1048,7 @@ int hpet_rtc_timer_init(void) clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC; clc >>= hpet_clockevent.shift + DEFAULT_RTC_SHIFT; - hpet_default_delta = (unsigned long) clc; + hpet_default_delta = clc; } if (!(hpet_rtc_flags & RTC_PIE) || hpet_pie_limit) @@ -1113,7 +1134,7 @@ int hpet_set_periodic_freq(unsigned long freq) clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC; do_div(clc, freq); clc >>= hpet_clockevent.shift; - hpet_pie_delta = (unsigned long) clc; + hpet_pie_delta = clc; } return 1; } @@ -1127,7 +1148,7 @@ EXPORT_SYMBOL_GPL(hpet_rtc_dropped_irq); static void hpet_rtc_timer_reinit(void) { - unsigned long cfg, delta; + unsigned int cfg, delta; int lost_ints = -1; if (unlikely(!hpet_rtc_flags)) { diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index d42f65ac492..05d5fec64a9 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -362,8 +362,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp, return ret; } - if (bp->callback) - ret = arch_store_info(bp); + ret = arch_store_info(bp); if (ret < 0) return ret; @@ -519,7 +518,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) break; } - (bp->callback)(bp, args->regs); + perf_bp_event(bp, args->regs); rcu_read_unlock(); } diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 99c4d308f16..8eec0ec59af 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -103,9 +103,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) * on system-call entry - see also fork() and the signal handling * code. */ -static int do_iopl(unsigned int level, struct pt_regs *regs) +long sys_iopl(unsigned int level, struct pt_regs *regs) { unsigned int old = (regs->flags >> 12) & 3; + struct thread_struct *t = ¤t->thread; if (level > 3) return -EINVAL; @@ -115,29 +116,8 @@ static int do_iopl(unsigned int level, struct pt_regs *regs) return -EPERM; } regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12); - - return 0; -} - -#ifdef CONFIG_X86_32 -long sys_iopl(struct pt_regs *regs) -{ - unsigned int level = regs->bx; - struct thread_struct *t = ¤t->thread; - int rc; - - rc = do_iopl(level, regs); - if (rc < 0) - goto out; - t->iopl = level << 12; set_iopl_mask(t->iopl); -out: - return rc; -} -#else -asmlinkage long sys_iopl(unsigned int level, struct pt_regs *regs) -{ - return do_iopl(level, regs); + + return 0; } -#endif diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index fee6cc2b207..91fd0c70a18 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -18,7 +18,7 @@ atomic_t irq_err_count; /* Function pointer for generic interrupt vector handling */ -void (*generic_interrupt_extension)(void) = NULL; +void (*x86_platform_ipi_callback)(void) = NULL; /* * 'what should we do if we get a hw irq event on an illegal vector'. @@ -72,10 +72,10 @@ static int show_other_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", irq_stats(j)->apic_pending_irqs); seq_printf(p, " Performance pending work\n"); #endif - if (generic_interrupt_extension) { + if (x86_platform_ipi_callback) { seq_printf(p, "%*s: ", prec, "PLT"); for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->generic_irqs); + seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis); seq_printf(p, " Platform interrupts\n"); } #ifdef CONFIG_SMP @@ -149,7 +149,7 @@ int show_interrupts(struct seq_file *p, void *v) if (!desc) return 0; - spin_lock_irqsave(&desc->lock, flags); + raw_spin_lock_irqsave(&desc->lock, flags); for_each_online_cpu(j) any_count |= kstat_irqs_cpu(i, j); action = desc->action; @@ -170,7 +170,7 @@ int show_interrupts(struct seq_file *p, void *v) seq_putc(p, '\n'); out: - spin_unlock_irqrestore(&desc->lock, flags); + raw_spin_unlock_irqrestore(&desc->lock, flags); return 0; } @@ -187,8 +187,8 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += irq_stats(cpu)->apic_perf_irqs; sum += irq_stats(cpu)->apic_pending_irqs; #endif - if (generic_interrupt_extension) - sum += irq_stats(cpu)->generic_irqs; + if (x86_platform_ipi_callback) + sum += irq_stats(cpu)->x86_platform_ipis; #ifdef CONFIG_SMP sum += irq_stats(cpu)->irq_resched_count; sum += irq_stats(cpu)->irq_call_count; @@ -251,9 +251,9 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs) } /* - * Handler for GENERIC_INTERRUPT_VECTOR. + * Handler for X86_PLATFORM_IPI_VECTOR. */ -void smp_generic_interrupt(struct pt_regs *regs) +void smp_x86_platform_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -263,10 +263,10 @@ void smp_generic_interrupt(struct pt_regs *regs) irq_enter(); - inc_irq_stat(generic_irqs); + inc_irq_stat(x86_platform_ipis); - if (generic_interrupt_extension) - generic_interrupt_extension(); + if (x86_platform_ipi_callback) + x86_platform_ipi_callback(); irq_exit(); @@ -294,12 +294,12 @@ void fixup_irqs(void) continue; /* interrupt's are disabled at this point */ - spin_lock(&desc->lock); + raw_spin_lock(&desc->lock); affinity = desc->affinity; if (!irq_has_action(irq) || cpumask_equal(affinity, cpu_online_mask)) { - spin_unlock(&desc->lock); + raw_spin_unlock(&desc->lock); continue; } @@ -326,7 +326,7 @@ void fixup_irqs(void) if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->unmask) desc->chip->unmask(irq); - spin_unlock(&desc->lock); + raw_spin_unlock(&desc->lock); if (break_affinity && set_affinity) printk("Broke affinity for irq %i\n", irq); @@ -356,10 +356,10 @@ void fixup_irqs(void) irq = __get_cpu_var(vector_irq)[vector]; desc = irq_to_desc(irq); - spin_lock(&desc->lock); + raw_spin_lock(&desc->lock); if (desc->chip->retrigger) desc->chip->retrigger(irq); - spin_unlock(&desc->lock); + raw_spin_unlock(&desc->lock); } } } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 40f30773fb2..d5932226614 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -200,8 +200,8 @@ static void __init apic_intr_init(void) /* self generated IPI for local APIC timer */ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); - /* generic IPI for platform specific use */ - alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt); + /* IPI for X86 platform specific use */ + alloc_intr_gate(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi); /* IPI vectors for APIC spurious and error interrupts */ alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 20a5b368946..dd74fe7273b 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -86,9 +86,15 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) gdb_regs[GDB_DS] = regs->ds; gdb_regs[GDB_ES] = regs->es; gdb_regs[GDB_CS] = regs->cs; - gdb_regs[GDB_SS] = __KERNEL_DS; gdb_regs[GDB_FS] = 0xFFFF; gdb_regs[GDB_GS] = 0xFFFF; + if (user_mode_vm(regs)) { + gdb_regs[GDB_SS] = regs->ss; + gdb_regs[GDB_SP] = regs->sp; + } else { + gdb_regs[GDB_SS] = __KERNEL_DS; + gdb_regs[GDB_SP] = kernel_stack_pointer(regs); + } #else gdb_regs[GDB_R8] = regs->r8; gdb_regs[GDB_R9] = regs->r9; @@ -101,8 +107,8 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) gdb_regs32[GDB_PS] = regs->flags; gdb_regs32[GDB_CS] = regs->cs; gdb_regs32[GDB_SS] = regs->ss; -#endif gdb_regs[GDB_SP] = kernel_stack_pointer(regs); +#endif } /** @@ -220,8 +226,7 @@ static void kgdb_correct_hw_break(void) dr7 |= ((breakinfo[breakno].len << 2) | breakinfo[breakno].type) << ((breakno << 2) + 16); - if (breakno >= 0 && breakno <= 3) - set_debugreg(breakinfo[breakno].addr, breakno); + set_debugreg(breakinfo[breakno].addr, breakno); } else { if ((dr7 & breakbit) && !breakinfo[breakno].enabled) { @@ -395,7 +400,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, /* set the trace bit if we're stepping */ if (remcomInBuffer[0] == 's') { linux_regs->flags |= X86_EFLAGS_TF; - kgdb_single_step = 1; atomic_set(&kgdb_cpu_doing_single_step, raw_smp_processor_id()); } diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 1f3186ce213..5b8c7505b3b 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -481,7 +481,7 @@ static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs, /* * Interrupts are disabled on entry as trap3 is an interrupt gate and they - * remain disabled thorough out this function. + * remain disabled throughout this function. */ static int __kprobes kprobe_handler(struct pt_regs *regs) { @@ -818,7 +818,7 @@ no_change: /* * Interrupts are disabled on entry as trap1 is an interrupt gate and they - * remain disabled thoroughout this function. + * remain disabled throughout this function. */ static int __kprobes post_kprobe_handler(struct pt_regs *regs) { diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index c843f8406da..a3fa43ba5d3 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -158,8 +158,7 @@ int machine_kexec_prepare(struct kimage *image) { int error; - if (nx_enabled) - set_pages_x(image->control_code_page, 1); + set_pages_x(image->control_code_page, 1); error = machine_kexec_alloc_page_tables(image); if (error) return error; @@ -173,8 +172,7 @@ int machine_kexec_prepare(struct kimage *image) */ void machine_kexec_cleanup(struct kimage *image) { - if (nx_enabled) - set_pages_nx(image->control_code_page, 1); + set_pages_nx(image->control_code_page, 1); machine_kexec_free_page_tables(image); } diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c deleted file mode 100644 index 2a62d843f01..00000000000 --- a/arch/x86/kernel/mfgpt_32.c +++ /dev/null @@ -1,410 +0,0 @@ -/* - * Driver/API for AMD Geode Multi-Function General Purpose Timers (MFGPT) - * - * Copyright (C) 2006, Advanced Micro Devices, Inc. - * Copyright (C) 2007, Andres Salomon <dilinger@debian.org> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public License - * as published by the Free Software Foundation. - * - * The MFGPTs are documented in AMD Geode CS5536 Companion Device Data Book. - */ - -/* - * We are using the 32.768kHz input clock - it's the only one that has the - * ranges we find desirable. The following table lists the suitable - * divisors and the associated Hz, minimum interval and the maximum interval: - * - * Divisor Hz Min Delta (s) Max Delta (s) - * 1 32768 .00048828125 2.000 - * 2 16384 .0009765625 4.000 - * 4 8192 .001953125 8.000 - * 8 4096 .00390625 16.000 - * 16 2048 .0078125 32.000 - * 32 1024 .015625 64.000 - * 64 512 .03125 128.000 - * 128 256 .0625 256.000 - * 256 128 .125 512.000 - */ - -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/module.h> -#include <asm/geode.h> - -#define MFGPT_DEFAULT_IRQ 7 - -static struct mfgpt_timer_t { - unsigned int avail:1; -} mfgpt_timers[MFGPT_MAX_TIMERS]; - -/* Selected from the table above */ - -#define MFGPT_DIVISOR 16 -#define MFGPT_SCALE 4 /* divisor = 2^(scale) */ -#define MFGPT_HZ (32768 / MFGPT_DIVISOR) -#define MFGPT_PERIODIC (MFGPT_HZ / HZ) - -/* Allow for disabling of MFGPTs */ -static int disable; -static int __init mfgpt_disable(char *s) -{ - disable = 1; - return 1; -} -__setup("nomfgpt", mfgpt_disable); - -/* Reset the MFGPT timers. This is required by some broken BIOSes which already - * do the same and leave the system in an unstable state. TinyBIOS 0.98 is - * affected at least (0.99 is OK with MFGPT workaround left to off). - */ -static int __init mfgpt_fix(char *s) -{ - u32 val, dummy; - - /* The following udocumented bit resets the MFGPT timers */ - val = 0xFF; dummy = 0; - wrmsr(MSR_MFGPT_SETUP, val, dummy); - return 1; -} -__setup("mfgptfix", mfgpt_fix); - -/* - * Check whether any MFGPTs are available for the kernel to use. In most - * cases, firmware that uses AMD's VSA code will claim all timers during - * bootup; we certainly don't want to take them if they're already in use. - * In other cases (such as with VSAless OpenFirmware), the system firmware - * leaves timers available for us to use. - */ - - -static int timers = -1; - -static void geode_mfgpt_detect(void) -{ - int i; - u16 val; - - timers = 0; - - if (disable) { - printk(KERN_INFO "geode-mfgpt: MFGPT support is disabled\n"); - goto done; - } - - if (!geode_get_dev_base(GEODE_DEV_MFGPT)) { - printk(KERN_INFO "geode-mfgpt: MFGPT LBAR is not set up\n"); - goto done; - } - - for (i = 0; i < MFGPT_MAX_TIMERS; i++) { - val = geode_mfgpt_read(i, MFGPT_REG_SETUP); - if (!(val & MFGPT_SETUP_SETUP)) { - mfgpt_timers[i].avail = 1; - timers++; - } - } - -done: - printk(KERN_INFO "geode-mfgpt: %d MFGPT timers available.\n", timers); -} - -int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable) -{ - u32 msr, mask, value, dummy; - int shift = (cmp == MFGPT_CMP1) ? 0 : 8; - - if (timer < 0 || timer >= MFGPT_MAX_TIMERS) - return -EIO; - - /* - * The register maps for these are described in sections 6.17.1.x of - * the AMD Geode CS5536 Companion Device Data Book. - */ - switch (event) { - case MFGPT_EVENT_RESET: - /* - * XXX: According to the docs, we cannot reset timers above - * 6; that is, resets for 7 and 8 will be ignored. Is this - * a problem? -dilinger - */ - msr = MSR_MFGPT_NR; - mask = 1 << (timer + 24); - break; - - case MFGPT_EVENT_NMI: - msr = MSR_MFGPT_NR; - mask = 1 << (timer + shift); - break; - - case MFGPT_EVENT_IRQ: - msr = MSR_MFGPT_IRQ; - mask = 1 << (timer + shift); - break; - - default: - return -EIO; - } - - rdmsr(msr, value, dummy); - - if (enable) - value |= mask; - else - value &= ~mask; - - wrmsr(msr, value, dummy); - return 0; -} -EXPORT_SYMBOL_GPL(geode_mfgpt_toggle_event); - -int geode_mfgpt_set_irq(int timer, int cmp, int *irq, int enable) -{ - u32 zsel, lpc, dummy; - int shift; - - if (timer < 0 || timer >= MFGPT_MAX_TIMERS) - return -EIO; - - /* - * Unfortunately, MFGPTs come in pairs sharing their IRQ lines. If VSA - * is using the same CMP of the timer's Siamese twin, the IRQ is set to - * 2, and we mustn't use nor change it. - * XXX: Likewise, 2 Linux drivers might clash if the 2nd overwrites the - * IRQ of the 1st. This can only happen if forcing an IRQ, calling this - * with *irq==0 is safe. Currently there _are_ no 2 drivers. - */ - rdmsr(MSR_PIC_ZSEL_LOW, zsel, dummy); - shift = ((cmp == MFGPT_CMP1 ? 0 : 4) + timer % 4) * 4; - if (((zsel >> shift) & 0xF) == 2) - return -EIO; - - /* Choose IRQ: if none supplied, keep IRQ already set or use default */ - if (!*irq) - *irq = (zsel >> shift) & 0xF; - if (!*irq) - *irq = MFGPT_DEFAULT_IRQ; - - /* Can't use IRQ if it's 0 (=disabled), 2, or routed to LPC */ - if (*irq < 1 || *irq == 2 || *irq > 15) - return -EIO; - rdmsr(MSR_PIC_IRQM_LPC, lpc, dummy); - if (lpc & (1 << *irq)) - return -EIO; - - /* All chosen and checked - go for it */ - if (geode_mfgpt_toggle_event(timer, cmp, MFGPT_EVENT_IRQ, enable)) - return -EIO; - if (enable) { - zsel = (zsel & ~(0xF << shift)) | (*irq << shift); - wrmsr(MSR_PIC_ZSEL_LOW, zsel, dummy); - } - - return 0; -} - -static int mfgpt_get(int timer) -{ - mfgpt_timers[timer].avail = 0; - printk(KERN_INFO "geode-mfgpt: Registered timer %d\n", timer); - return timer; -} - -int geode_mfgpt_alloc_timer(int timer, int domain) -{ - int i; - - if (timers == -1) { - /* timers haven't been detected yet */ - geode_mfgpt_detect(); - } - - if (!timers) - return -1; - - if (timer >= MFGPT_MAX_TIMERS) - return -1; - - if (timer < 0) { - /* Try to find an available timer */ - for (i = 0; i < MFGPT_MAX_TIMERS; i++) { - if (mfgpt_timers[i].avail) - return mfgpt_get(i); - - if (i == 5 && domain == MFGPT_DOMAIN_WORKING) - break; - } - } else { - /* If they requested a specific timer, try to honor that */ - if (mfgpt_timers[timer].avail) - return mfgpt_get(timer); - } - - /* No timers available - too bad */ - return -1; -} -EXPORT_SYMBOL_GPL(geode_mfgpt_alloc_timer); - - -#ifdef CONFIG_GEODE_MFGPT_TIMER - -/* - * The MFPGT timers on the CS5536 provide us with suitable timers to use - * as clock event sources - not as good as a HPET or APIC, but certainly - * better than the PIT. This isn't a general purpose MFGPT driver, but - * a simplified one designed specifically to act as a clock event source. - * For full details about the MFGPT, please consult the CS5536 data sheet. - */ - -#include <linux/clocksource.h> -#include <linux/clockchips.h> - -static unsigned int mfgpt_tick_mode = CLOCK_EVT_MODE_SHUTDOWN; -static u16 mfgpt_event_clock; - -static int irq; -static int __init mfgpt_setup(char *str) -{ - get_option(&str, &irq); - return 1; -} -__setup("mfgpt_irq=", mfgpt_setup); - -static void mfgpt_disable_timer(u16 clock) -{ - /* avoid races by clearing CMP1 and CMP2 unconditionally */ - geode_mfgpt_write(clock, MFGPT_REG_SETUP, (u16) ~MFGPT_SETUP_CNTEN | - MFGPT_SETUP_CMP1 | MFGPT_SETUP_CMP2); -} - -static int mfgpt_next_event(unsigned long, struct clock_event_device *); -static void mfgpt_set_mode(enum clock_event_mode, struct clock_event_device *); - -static struct clock_event_device mfgpt_clockevent = { - .name = "mfgpt-timer", - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, - .set_mode = mfgpt_set_mode, - .set_next_event = mfgpt_next_event, - .rating = 250, - .cpumask = cpu_all_mask, - .shift = 32 -}; - -static void mfgpt_start_timer(u16 delta) -{ - geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_CMP2, (u16) delta); - geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_COUNTER, 0); - - geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_SETUP, - MFGPT_SETUP_CNTEN | MFGPT_SETUP_CMP2); -} - -static void mfgpt_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) -{ - mfgpt_disable_timer(mfgpt_event_clock); - - if (mode == CLOCK_EVT_MODE_PERIODIC) - mfgpt_start_timer(MFGPT_PERIODIC); - - mfgpt_tick_mode = mode; -} - -static int mfgpt_next_event(unsigned long delta, struct clock_event_device *evt) -{ - mfgpt_start_timer(delta); - return 0; -} - -static irqreturn_t mfgpt_tick(int irq, void *dev_id) -{ - u16 val = geode_mfgpt_read(mfgpt_event_clock, MFGPT_REG_SETUP); - - /* See if the interrupt was for us */ - if (!(val & (MFGPT_SETUP_SETUP | MFGPT_SETUP_CMP2 | MFGPT_SETUP_CMP1))) - return IRQ_NONE; - - /* Turn off the clock (and clear the event) */ - mfgpt_disable_timer(mfgpt_event_clock); - - if (mfgpt_tick_mode == CLOCK_EVT_MODE_SHUTDOWN) - return IRQ_HANDLED; - - /* Clear the counter */ - geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_COUNTER, 0); - - /* Restart the clock in periodic mode */ - - if (mfgpt_tick_mode == CLOCK_EVT_MODE_PERIODIC) { - geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_SETUP, - MFGPT_SETUP_CNTEN | MFGPT_SETUP_CMP2); - } - - mfgpt_clockevent.event_handler(&mfgpt_clockevent); - return IRQ_HANDLED; -} - -static struct irqaction mfgptirq = { - .handler = mfgpt_tick, - .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER, - .name = "mfgpt-timer" -}; - -int __init mfgpt_timer_setup(void) -{ - int timer, ret; - u16 val; - - timer = geode_mfgpt_alloc_timer(MFGPT_TIMER_ANY, MFGPT_DOMAIN_WORKING); - if (timer < 0) { - printk(KERN_ERR - "mfgpt-timer: Could not allocate a MFPGT timer\n"); - return -ENODEV; - } - - mfgpt_event_clock = timer; - - /* Set up the IRQ on the MFGPT side */ - if (geode_mfgpt_setup_irq(mfgpt_event_clock, MFGPT_CMP2, &irq)) { - printk(KERN_ERR "mfgpt-timer: Could not set up IRQ %d\n", irq); - return -EIO; - } - - /* And register it with the kernel */ - ret = setup_irq(irq, &mfgptirq); - - if (ret) { - printk(KERN_ERR - "mfgpt-timer: Unable to set up the interrupt.\n"); - goto err; - } - - /* Set the clock scale and enable the event mode for CMP2 */ - val = MFGPT_SCALE | (3 << 8); - - geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_SETUP, val); - - /* Set up the clock event */ - mfgpt_clockevent.mult = div_sc(MFGPT_HZ, NSEC_PER_SEC, - mfgpt_clockevent.shift); - mfgpt_clockevent.min_delta_ns = clockevent_delta2ns(0xF, - &mfgpt_clockevent); - mfgpt_clockevent.max_delta_ns = clockevent_delta2ns(0xFFFE, - &mfgpt_clockevent); - - printk(KERN_INFO - "mfgpt-timer: Registering MFGPT timer %d as a clock event, using IRQ %d\n", - timer, irq); - clockevents_register_device(&mfgpt_clockevent); - - return 0; - -err: - geode_mfgpt_release_irq(mfgpt_event_clock, MFGPT_CMP2, &irq); - printk(KERN_ERR - "mfgpt-timer: Unable to set up the MFGPT clock source\n"); - return -EIO; -} - -#endif diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index f4c538b681c..37542b67c57 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -13,6 +13,9 @@ * Licensed under the terms of the GNU General Public * License version 2. See file COPYING for details. */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/firmware.h> #include <linux/pci_ids.h> #include <linux/uaccess.h> @@ -33,6 +36,9 @@ MODULE_LICENSE("GPL v2"); #define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000 #define UCODE_UCODE_TYPE 0x00000001 +const struct firmware *firmware; +static int supported_cpu; + struct equiv_cpu_entry { u32 installed_cpu; u32 fixed_errata_mask; @@ -71,17 +77,14 @@ static struct equiv_cpu_entry *equiv_cpu_table; static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) { - struct cpuinfo_x86 *c = &cpu_data(cpu); u32 dummy; - memset(csig, 0, sizeof(*csig)); - if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) { - printk(KERN_WARNING "microcode: CPU%d: AMD CPU family 0x%x not " - "supported\n", cpu, c->x86); + if (!supported_cpu) return -1; - } + + memset(csig, 0, sizeof(*csig)); rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy); - printk(KERN_INFO "microcode: CPU%d: patch_level=0x%x\n", cpu, csig->rev); + pr_info("CPU%d: patch_level=0x%x\n", cpu, csig->rev); return 0; } @@ -103,23 +106,16 @@ static int get_matching_microcode(int cpu, void *mc, int rev) i++; } - if (!equiv_cpu_id) { - printk(KERN_WARNING "microcode: CPU%d: cpu revision " - "not listed in equivalent cpu table\n", cpu); + if (!equiv_cpu_id) return 0; - } - if (mc_header->processor_rev_id != equiv_cpu_id) { - printk(KERN_ERR "microcode: CPU%d: patch mismatch " - "(processor_rev_id: %x, equiv_cpu_id: %x)\n", - cpu, mc_header->processor_rev_id, equiv_cpu_id); + if (mc_header->processor_rev_id != equiv_cpu_id) return 0; - } /* ucode might be chipset specific -- currently we don't support this */ if (mc_header->nb_dev_id || mc_header->sb_dev_id) { - printk(KERN_ERR "microcode: CPU%d: loading of chipset " - "specific code not yet supported\n", cpu); + pr_err("CPU%d: loading of chipset specific code not yet supported\n", + cpu); return 0; } @@ -148,14 +144,12 @@ static int apply_microcode_amd(int cpu) /* check current patch id and patch's id for match */ if (rev != mc_amd->hdr.patch_id) { - printk(KERN_ERR "microcode: CPU%d: update failed " - "(for patch_level=0x%x)\n", cpu, mc_amd->hdr.patch_id); + pr_err("CPU%d: update failed (for patch_level=0x%x)\n", + cpu, mc_amd->hdr.patch_id); return -1; } - printk(KERN_INFO "microcode: CPU%d: updated (new patch_level=0x%x)\n", - cpu, rev); - + pr_info("CPU%d: updated (new patch_level=0x%x)\n", cpu, rev); uci->cpu_sig.rev = rev; return 0; @@ -178,18 +172,14 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size) return NULL; if (section_hdr[0] != UCODE_UCODE_TYPE) { - printk(KERN_ERR "microcode: error: invalid type field in " - "container file section header\n"); + pr_err("error: invalid type field in container file section header\n"); return NULL; } total_size = (unsigned long) (section_hdr[4] + (section_hdr[5] << 8)); - printk(KERN_DEBUG "microcode: size %u, total_size %u\n", - size, total_size); - if (total_size > size || total_size > UCODE_MAX_SIZE) { - printk(KERN_ERR "microcode: error: size mismatch\n"); + pr_err("error: size mismatch\n"); return NULL; } @@ -218,15 +208,13 @@ static int install_equiv_cpu_table(const u8 *buf) size = buf_pos[2]; if (buf_pos[1] != UCODE_EQUIV_CPU_TABLE_TYPE || !size) { - printk(KERN_ERR "microcode: error: invalid type field in " - "container file section header\n"); + pr_err("error: invalid type field in container file section header\n"); return 0; } equiv_cpu_table = (struct equiv_cpu_entry *) vmalloc(size); if (!equiv_cpu_table) { - printk(KERN_ERR "microcode: failed to allocate " - "equivalent CPU table\n"); + pr_err("failed to allocate equivalent CPU table\n"); return 0; } @@ -259,8 +247,7 @@ generic_load_microcode(int cpu, const u8 *data, size_t size) offset = install_equiv_cpu_table(ucode_ptr); if (!offset) { - printk(KERN_ERR "microcode: failed to create " - "equivalent cpu table\n"); + pr_err("failed to create equivalent cpu table\n"); return UCODE_ERROR; } @@ -291,8 +278,7 @@ generic_load_microcode(int cpu, const u8 *data, size_t size) if (!leftover) { vfree(uci->mc); uci->mc = new_mc; - pr_debug("microcode: CPU%d found a matching microcode " - "update with version 0x%x (current=0x%x)\n", + pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); } else { vfree(new_mc); @@ -308,33 +294,26 @@ generic_load_microcode(int cpu, const u8 *data, size_t size) static enum ucode_state request_microcode_fw(int cpu, struct device *device) { - const char *fw_name = "amd-ucode/microcode_amd.bin"; - const struct firmware *firmware; enum ucode_state ret; - if (request_firmware(&firmware, fw_name, device)) { - printk(KERN_ERR "microcode: failed to load file %s\n", fw_name); + if (firmware == NULL) return UCODE_NFOUND; - } if (*(u32 *)firmware->data != UCODE_MAGIC) { - printk(KERN_ERR "microcode: invalid UCODE_MAGIC (0x%08x)\n", + pr_err("invalid UCODE_MAGIC (0x%08x)\n", *(u32 *)firmware->data); return UCODE_ERROR; } ret = generic_load_microcode(cpu, firmware->data, firmware->size); - release_firmware(firmware); - return ret; } static enum ucode_state request_microcode_user(int cpu, const void __user *buf, size_t size) { - printk(KERN_INFO "microcode: AMD microcode update via " - "/dev/cpu/microcode not supported\n"); + pr_info("AMD microcode update via /dev/cpu/microcode not supported\n"); return UCODE_ERROR; } @@ -346,7 +325,31 @@ static void microcode_fini_cpu_amd(int cpu) uci->mc = NULL; } +void init_microcode_amd(struct device *device) +{ + const char *fw_name = "amd-ucode/microcode_amd.bin"; + struct cpuinfo_x86 *c = &boot_cpu_data; + + WARN_ON(c->x86_vendor != X86_VENDOR_AMD); + + if (c->x86 < 0x10) { + pr_warning("AMD CPU family 0x%x not supported\n", c->x86); + return; + } + supported_cpu = 1; + + if (request_firmware(&firmware, fw_name, device)) + pr_err("failed to load file %s\n", fw_name); +} + +void fini_microcode_amd(void) +{ + release_firmware(firmware); +} + static struct microcode_ops microcode_amd_ops = { + .init = init_microcode_amd, + .fini = fini_microcode_amd, .request_microcode_user = request_microcode_user, .request_microcode_fw = request_microcode_fw, .collect_cpu_info = collect_cpu_info_amd, diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 2bcad3926ed..0c863243309 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -70,6 +70,9 @@ * Fix sigmatch() macro to handle old CPUs with pf == 0. * Thanks to Stuart Swales for pointing out this bug. */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/platform_device.h> #include <linux/miscdevice.h> #include <linux/capability.h> @@ -209,7 +212,7 @@ static ssize_t microcode_write(struct file *file, const char __user *buf, ssize_t ret = -EINVAL; if ((len >> PAGE_SHIFT) > totalram_pages) { - pr_err("microcode: too much data (max %ld pages)\n", totalram_pages); + pr_err("too much data (max %ld pages)\n", totalram_pages); return ret; } @@ -244,7 +247,7 @@ static int __init microcode_dev_init(void) error = misc_register(µcode_dev); if (error) { - pr_err("microcode: can't misc_register on minor=%d\n", MICROCODE_MINOR); + pr_err("can't misc_register on minor=%d\n", MICROCODE_MINOR); return error; } @@ -359,7 +362,7 @@ static enum ucode_state microcode_resume_cpu(int cpu) if (!uci->mc) return UCODE_NFOUND; - pr_debug("microcode: CPU%d updated upon resume\n", cpu); + pr_debug("CPU%d updated upon resume\n", cpu); apply_microcode_on_target(cpu); return UCODE_OK; @@ -379,7 +382,7 @@ static enum ucode_state microcode_init_cpu(int cpu) ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev); if (ustate == UCODE_OK) { - pr_debug("microcode: CPU%d updated upon init\n", cpu); + pr_debug("CPU%d updated upon init\n", cpu); apply_microcode_on_target(cpu); } @@ -406,7 +409,7 @@ static int mc_sysdev_add(struct sys_device *sys_dev) if (!cpu_online(cpu)) return 0; - pr_debug("microcode: CPU%d added\n", cpu); + pr_debug("CPU%d added\n", cpu); err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group); if (err) @@ -425,7 +428,7 @@ static int mc_sysdev_remove(struct sys_device *sys_dev) if (!cpu_online(cpu)) return 0; - pr_debug("microcode: CPU%d removed\n", cpu); + pr_debug("CPU%d removed\n", cpu); microcode_fini_cpu(cpu); sysfs_remove_group(&sys_dev->kobj, &mc_attr_group); return 0; @@ -473,15 +476,15 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) microcode_update_cpu(cpu); case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: - pr_debug("microcode: CPU%d added\n", cpu); + pr_debug("CPU%d added\n", cpu); if (sysfs_create_group(&sys_dev->kobj, &mc_attr_group)) - pr_err("microcode: Failed to create group for CPU%d\n", cpu); + pr_err("Failed to create group for CPU%d\n", cpu); break; case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: /* Suspend is in progress, only remove the interface */ sysfs_remove_group(&sys_dev->kobj, &mc_attr_group); - pr_debug("microcode: CPU%d removed\n", cpu); + pr_debug("CPU%d removed\n", cpu); break; case CPU_DEAD: case CPU_UP_CANCELED_FROZEN: @@ -507,7 +510,7 @@ static int __init microcode_init(void) microcode_ops = init_amd_microcode(); if (!microcode_ops) { - pr_err("microcode: no support for this CPU vendor\n"); + pr_err("no support for this CPU vendor\n"); return -ENODEV; } @@ -518,6 +521,9 @@ static int __init microcode_init(void) return PTR_ERR(microcode_pdev); } + if (microcode_ops->init) + microcode_ops->init(µcode_pdev->dev); + get_online_cpus(); mutex_lock(µcode_mutex); @@ -538,8 +544,7 @@ static int __init microcode_init(void) register_hotcpu_notifier(&mc_cpu_notifier); pr_info("Microcode Update Driver: v" MICROCODE_VERSION - " <tigran@aivazian.fsnet.co.uk>," - " Peter Oruba\n"); + " <tigran@aivazian.fsnet.co.uk>, Peter Oruba\n"); return 0; } @@ -561,6 +566,9 @@ static void __exit microcode_exit(void) platform_device_unregister(microcode_pdev); + if (microcode_ops->fini) + microcode_ops->fini(); + microcode_ops = NULL; pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n"); diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index 0d334ddd0a9..ebd193e476c 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -70,6 +70,9 @@ * Fix sigmatch() macro to handle old CPUs with pf == 0. * Thanks to Stuart Swales for pointing out this bug. */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/firmware.h> #include <linux/uaccess.h> #include <linux/kernel.h> @@ -146,8 +149,7 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 || cpu_has(c, X86_FEATURE_IA64)) { - printk(KERN_ERR "microcode: CPU%d not a capable Intel " - "processor\n", cpu_num); + pr_err("CPU%d not a capable Intel processor\n", cpu_num); return -1; } @@ -165,8 +167,8 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) /* get the current revision from MSR 0x8B */ rdmsr(MSR_IA32_UCODE_REV, val[0], csig->rev); - printk(KERN_INFO "microcode: CPU%d sig=0x%x, pf=0x%x, revision=0x%x\n", - cpu_num, csig->sig, csig->pf, csig->rev); + pr_info("CPU%d sig=0x%x, pf=0x%x, revision=0x%x\n", + cpu_num, csig->sig, csig->pf, csig->rev); return 0; } @@ -194,28 +196,24 @@ static int microcode_sanity_check(void *mc) data_size = get_datasize(mc_header); if (data_size + MC_HEADER_SIZE > total_size) { - printk(KERN_ERR "microcode: error! " - "Bad data size in microcode data file\n"); + pr_err("error! Bad data size in microcode data file\n"); return -EINVAL; } if (mc_header->ldrver != 1 || mc_header->hdrver != 1) { - printk(KERN_ERR "microcode: error! " - "Unknown microcode update format\n"); + pr_err("error! Unknown microcode update format\n"); return -EINVAL; } ext_table_size = total_size - (MC_HEADER_SIZE + data_size); if (ext_table_size) { if ((ext_table_size < EXT_HEADER_SIZE) || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) { - printk(KERN_ERR "microcode: error! " - "Small exttable size in microcode data file\n"); + pr_err("error! Small exttable size in microcode data file\n"); return -EINVAL; } ext_header = mc + MC_HEADER_SIZE + data_size; if (ext_table_size != exttable_size(ext_header)) { - printk(KERN_ERR "microcode: error! " - "Bad exttable size in microcode data file\n"); + pr_err("error! Bad exttable size in microcode data file\n"); return -EFAULT; } ext_sigcount = ext_header->count; @@ -230,8 +228,7 @@ static int microcode_sanity_check(void *mc) while (i--) ext_table_sum += ext_tablep[i]; if (ext_table_sum) { - printk(KERN_WARNING "microcode: aborting, " - "bad extended signature table checksum\n"); + pr_warning("aborting, bad extended signature table checksum\n"); return -EINVAL; } } @@ -242,7 +239,7 @@ static int microcode_sanity_check(void *mc) while (i--) orig_sum += ((int *)mc)[i]; if (orig_sum) { - printk(KERN_ERR "microcode: aborting, bad checksum\n"); + pr_err("aborting, bad checksum\n"); return -EINVAL; } if (!ext_table_size) @@ -255,7 +252,7 @@ static int microcode_sanity_check(void *mc) - (mc_header->sig + mc_header->pf + mc_header->cksum) + (ext_sig->sig + ext_sig->pf + ext_sig->cksum); if (sum) { - printk(KERN_ERR "microcode: aborting, bad checksum\n"); + pr_err("aborting, bad checksum\n"); return -EINVAL; } } @@ -327,13 +324,11 @@ static int apply_microcode(int cpu) rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); if (val[1] != mc_intel->hdr.rev) { - printk(KERN_ERR "microcode: CPU%d update " - "to revision 0x%x failed\n", - cpu_num, mc_intel->hdr.rev); + pr_err("CPU%d update to revision 0x%x failed\n", + cpu_num, mc_intel->hdr.rev); return -1; } - printk(KERN_INFO "microcode: CPU%d updated to revision " - "0x%x, date = %04x-%02x-%02x \n", + pr_info("CPU%d updated to revision 0x%x, date = %04x-%02x-%02x \n", cpu_num, val[1], mc_intel->hdr.date & 0xffff, mc_intel->hdr.date >> 24, @@ -362,8 +357,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, mc_size = get_totalsize(&mc_header); if (!mc_size || mc_size > leftover) { - printk(KERN_ERR "microcode: error!" - "Bad data in microcode data file\n"); + pr_err("error! Bad data in microcode data file\n"); break; } @@ -405,9 +399,8 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, vfree(uci->mc); uci->mc = (struct microcode_intel *)new_mc; - pr_debug("microcode: CPU%d found a matching microcode update with" - " version 0x%x (current=0x%x)\n", - cpu, new_rev, uci->cpu_sig.rev); + pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", + cpu, new_rev, uci->cpu_sig.rev); out: return state; } @@ -429,7 +422,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device) c->x86, c->x86_model, c->x86_mask); if (request_firmware(&firmware, name, device)) { - pr_debug("microcode: data file %s load failed\n", name); + pr_debug("data file %s load failed\n", name); return UCODE_NFOUND; } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 5be95ef4ffe..40b54ceb68b 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -667,36 +667,18 @@ void __init default_get_smp_config(unsigned int early) */ } -static void __init smp_reserve_bootmem(struct mpf_intel *mpf) +static void __init smp_reserve_memory(struct mpf_intel *mpf) { unsigned long size = get_mpc_size(mpf->physptr); -#ifdef CONFIG_X86_32 - /* - * We cannot access to MPC table to compute table size yet, - * as only few megabytes from the bottom is mapped now. - * PC-9800's MPC table places on the very last of physical - * memory; so that simply reserving PAGE_SIZE from mpf->physptr - * yields BUG() in reserve_bootmem. - * also need to make sure physptr is below than max_low_pfn - * we don't need reserve the area above max_low_pfn - */ - unsigned long end = max_low_pfn * PAGE_SIZE; - if (mpf->physptr < end) { - if (mpf->physptr + size > end) - size = end - mpf->physptr; - reserve_bootmem_generic(mpf->physptr, size, BOOTMEM_DEFAULT); - } -#else - reserve_bootmem_generic(mpf->physptr, size, BOOTMEM_DEFAULT); -#endif + reserve_early(mpf->physptr, mpf->physptr+size, "MP-table mpc"); } -static int __init smp_scan_config(unsigned long base, unsigned long length, - unsigned reserve) +static int __init smp_scan_config(unsigned long base, unsigned long length) { unsigned int *bp = phys_to_virt(base); struct mpf_intel *mpf; + unsigned long mem; apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n", bp, length); @@ -717,12 +699,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, printk(KERN_INFO "found SMP MP-table at [%p] %llx\n", mpf, (u64)virt_to_phys(mpf)); - if (!reserve) - return 1; - reserve_bootmem_generic(virt_to_phys(mpf), sizeof(*mpf), - BOOTMEM_DEFAULT); + mem = virt_to_phys(mpf); + reserve_early(mem, mem + sizeof(*mpf), "MP-table mpf"); if (mpf->physptr) - smp_reserve_bootmem(mpf); + smp_reserve_memory(mpf); return 1; } @@ -732,7 +712,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, return 0; } -void __init default_find_smp_config(unsigned int reserve) +void __init default_find_smp_config(void) { unsigned int address; @@ -744,9 +724,9 @@ void __init default_find_smp_config(unsigned int reserve) * 2) Scan the top 1K of base RAM * 3) Scan the 64K of bios */ - if (smp_scan_config(0x0, 0x400, reserve) || - smp_scan_config(639 * 0x400, 0x400, reserve) || - smp_scan_config(0xF0000, 0x10000, reserve)) + if (smp_scan_config(0x0, 0x400) || + smp_scan_config(639 * 0x400, 0x400) || + smp_scan_config(0xF0000, 0x10000)) return; /* * If it is an SMP machine we should know now, unless the @@ -767,7 +747,7 @@ void __init default_find_smp_config(unsigned int reserve) address = get_bios_ebda(); if (address) - smp_scan_config(address, 0x400, reserve); + smp_scan_config(address, 0x400); } #ifdef CONFIG_X86_IO_APIC @@ -965,9 +945,6 @@ void __init early_reserve_e820_mpc_new(void) { if (enable_update_mptable && alloc_mptable) { u64 startt = 0; -#ifdef CONFIG_X86_TRAMPOLINE - startt = TRAMPOLINE_BASE; -#endif mpc_new_phys = early_reserve_e820(startt, mpc_new_length, 4); } } diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 553449951b8..4bd93c9b2b2 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -172,11 +172,10 @@ static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg) static int msr_open(struct inode *inode, struct file *file) { - unsigned int cpu = iminor(file->f_path.dentry->d_inode); - struct cpuinfo_x86 *c = &cpu_data(cpu); + unsigned int cpu; + struct cpuinfo_x86 *c; cpu = iminor(file->f_path.dentry->d_inode); - if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; /* No such CPU */ @@ -247,7 +246,7 @@ 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; @@ -275,7 +274,7 @@ 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; } diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c index 4006c522adc..9d1d263f786 100644 --- a/arch/x86/kernel/olpc.c +++ b/arch/x86/kernel/olpc.c @@ -212,7 +212,7 @@ static int __init olpc_init(void) unsigned char *romsig; /* The ioremap check is dangerous; limit what we run it on */ - if (!is_geode() || geode_has_vsa2()) + if (!is_geode() || cs5535_has_vsa2()) return 0; spin_lock_init(&ec_lock); @@ -244,7 +244,7 @@ static int __init olpc_init(void) (unsigned char *) &olpc_platform_info.ecver, 1); /* check to see if the VSA exists */ - if (geode_has_vsa2()) + if (cs5535_has_vsa2()) olpc_platform_info.flags |= OLPC_F_VSA; printk(KERN_INFO "OLPC board revision %s%X (EC=%x)\n", diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 3a7c5a44082..676b8c77a97 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -8,9 +8,9 @@ #include <asm/paravirt.h> static inline void -default_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags) +default_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) { - __raw_spin_lock(lock); + arch_spin_lock(lock); } struct pv_lock_ops pv_lock_ops = { diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index c563e4c8ff3..2bbde607814 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -31,7 +31,7 @@ #include <linux/string.h> #include <linux/crash_dump.h> #include <linux/dma-mapping.h> -#include <linux/bitops.h> +#include <linux/bitmap.h> #include <linux/pci_ids.h> #include <linux/pci.h> #include <linux/delay.h> @@ -212,7 +212,7 @@ static void iommu_range_reserve(struct iommu_table *tbl, spin_lock_irqsave(&tbl->it_lock, flags); - iommu_area_reserve(tbl->it_map, index, npages); + bitmap_set(tbl->it_map, index, npages); spin_unlock_irqrestore(&tbl->it_lock, flags); } @@ -303,7 +303,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, spin_lock_irqsave(&tbl->it_lock, flags); - iommu_area_free(tbl->it_map, entry, npages); + bitmap_clear(tbl->it_map, entry, npages); spin_unlock_irqrestore(&tbl->it_lock, flags); } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index afcc58b69c7..75e14e21f61 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -124,8 +124,8 @@ void __init pci_iommu_alloc(void) /* free the range so iommu could get some range less than 4G */ dma32_free_bootmem(); #endif - if (pci_swiotlb_init()) - return; + if (pci_swiotlb_detect()) + goto out; gart_iommu_hole_init(); @@ -135,6 +135,8 @@ void __init pci_iommu_alloc(void) /* needs to be called after gart_iommu_hole_init */ amd_iommu_detect(); +out: + pci_swiotlb_init(); } void *dma_generic_alloc_coherent(struct device *dev, size_t size, diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index e6a0d402f17..34de53b46f8 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -23,7 +23,7 @@ #include <linux/module.h> #include <linux/topology.h> #include <linux/interrupt.h> -#include <linux/bitops.h> +#include <linux/bitmap.h> #include <linux/kdebug.h> #include <linux/scatterlist.h> #include <linux/iommu-helper.h> @@ -126,7 +126,7 @@ static void free_iommu(unsigned long offset, int size) unsigned long flags; spin_lock_irqsave(&iommu_bitmap_lock, flags); - iommu_area_free(iommu_gart_bitmap, offset, size); + bitmap_clear(iommu_gart_bitmap, offset, size); if (offset >= next_bit) next_bit = offset + size; spin_unlock_irqrestore(&iommu_bitmap_lock, flags); @@ -710,7 +710,8 @@ static void gart_iommu_shutdown(void) struct pci_dev *dev; int i; - if (no_agp) + /* don't shutdown it if there is AGP installed */ + if (!no_agp) return; for (i = 0; i < num_k8_northbridges; i++) { @@ -791,7 +792,7 @@ int __init gart_iommu_init(void) * Out of IOMMU space handling. * Reserve some invalid pages at the beginning of the GART. */ - iommu_area_reserve(iommu_gart_bitmap, 0, EMERGENCY_PAGES); + bitmap_set(iommu_gart_bitmap, 0, EMERGENCY_PAGES); pr_info("PCI-DMA: Reserving %luMB of IOMMU area in the AGP aperture\n", iommu_size >> 20); diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index e3c0a66b9e7..7d2829dde20 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -43,12 +43,12 @@ static struct dma_map_ops swiotlb_dma_ops = { }; /* - * pci_swiotlb_init - initialize swiotlb if necessary + * pci_swiotlb_detect - set swiotlb to 1 if necessary * * This returns non-zero if we are forced to use swiotlb (by the boot * option). */ -int __init pci_swiotlb_init(void) +int __init pci_swiotlb_detect(void) { int use_swiotlb = swiotlb | swiotlb_force; @@ -60,10 +60,13 @@ int __init pci_swiotlb_init(void) if (swiotlb_force) swiotlb = 1; + return use_swiotlb; +} + +void __init pci_swiotlb_init(void) +{ if (swiotlb) { swiotlb_init(0); dma_ops = &swiotlb_dma_ops; } - - return use_swiotlb; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 5e2ba634ea1..02c3ee013cc 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -10,6 +10,8 @@ #include <linux/clockchips.h> #include <linux/random.h> #include <linux/user-return-notifier.h> +#include <linux/dmi.h> +#include <linux/utsname.h> #include <trace/events/power.h> #include <linux/hw_breakpoint.h> #include <asm/system.h> @@ -90,6 +92,25 @@ void exit_thread(void) } } +void show_regs_common(void) +{ + const char *board, *product; + + board = dmi_get_system_info(DMI_BOARD_NAME); + if (!board) + board = ""; + product = dmi_get_system_info(DMI_PRODUCT_NAME); + if (!product) + product = ""; + + printk(KERN_CONT "\n"); + printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s %s/%s\n", + current->pid, current->comm, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version, board, product); +} + void flush_thread(void) { struct task_struct *tsk = current; @@ -234,6 +255,78 @@ int sys_vfork(struct pt_regs *regs) NULL, NULL); } +long +sys_clone(unsigned long clone_flags, unsigned long newsp, + void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) +{ + if (!newsp) + newsp = regs->sp; + return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); +} + +/* + * This gets run with %si containing the + * function to call, and %di containing + * the "args". + */ +extern void kernel_thread_helper(void); + +/* + * Create a kernel thread + */ +int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) +{ + struct pt_regs regs; + + memset(®s, 0, sizeof(regs)); + + regs.si = (unsigned long) fn; + regs.di = (unsigned long) arg; + +#ifdef CONFIG_X86_32 + regs.ds = __USER_DS; + regs.es = __USER_DS; + regs.fs = __KERNEL_PERCPU; + regs.gs = __KERNEL_STACK_CANARY; +#else + regs.ss = __KERNEL_DS; +#endif + + regs.orig_ax = -1; + regs.ip = (unsigned long) kernel_thread_helper; + regs.cs = __KERNEL_CS | get_kernel_rpl(); + regs.flags = X86_EFLAGS_IF | 0x2; + + /* Ok, create the new process.. */ + return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL); +} +EXPORT_SYMBOL(kernel_thread); + +/* + * sys_execve() executes a new program. + */ +long sys_execve(char __user *name, char __user * __user *argv, + char __user * __user *envp, struct pt_regs *regs) +{ + long error; + char *filename; + + filename = getname(name); + error = PTR_ERR(filename); + if (IS_ERR(filename)) + return error; + error = do_execve(filename, argv, envp, regs); + +#ifdef CONFIG_X86_32 + if (error == 0) { + /* Make sure we don't return using sysenter.. */ + set_thread_flag(TIF_IRET); + } +#endif + + putname(filename); + return error; +} /* * Idle related variables and functions diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 075580b3568..37ad1e046aa 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -23,7 +23,6 @@ #include <linux/vmalloc.h> #include <linux/user.h> #include <linux/interrupt.h> -#include <linux/utsname.h> #include <linux/delay.h> #include <linux/reboot.h> #include <linux/init.h> @@ -35,7 +34,6 @@ #include <linux/tick.h> #include <linux/percpu.h> #include <linux/prctl.h> -#include <linux/dmi.h> #include <linux/ftrace.h> #include <linux/uaccess.h> #include <linux/io.h> @@ -128,7 +126,6 @@ void __show_regs(struct pt_regs *regs, int all) unsigned long d0, d1, d2, d3, d6, d7; unsigned long sp; unsigned short ss, gs; - const char *board; if (user_mode_vm(regs)) { sp = regs->sp; @@ -140,27 +137,18 @@ void __show_regs(struct pt_regs *regs, int all) savesegment(gs, gs); } - printk("\n"); + show_regs_common(); - board = dmi_get_system_info(DMI_PRODUCT_NAME); - if (!board) - board = ""; - printk("Pid: %d, comm: %s %s (%s %.*s) %s\n", - task_pid_nr(current), current->comm, - print_tainted(), init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version, board); - - printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n", + printk(KERN_DEFAULT "EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n", (u16)regs->cs, regs->ip, regs->flags, smp_processor_id()); print_symbol("EIP is at %s\n", regs->ip); - printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", + printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", regs->ax, regs->bx, regs->cx, regs->dx); - printk("ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n", + printk(KERN_DEFAULT "ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n", regs->si, regs->di, regs->bp, sp); - printk(" DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n", + printk(KERN_DEFAULT " DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n", (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss); if (!all) @@ -170,19 +158,19 @@ void __show_regs(struct pt_regs *regs, int all) cr2 = read_cr2(); cr3 = read_cr3(); cr4 = read_cr4_safe(); - printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", + printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4); get_debugreg(d0, 0); get_debugreg(d1, 1); get_debugreg(d2, 2); get_debugreg(d3, 3); - printk("DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", + printk(KERN_DEFAULT "DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", d0, d1, d2, d3); get_debugreg(d6, 6); get_debugreg(d7, 7); - printk("DR6: %08lx DR7: %08lx\n", + printk(KERN_DEFAULT "DR6: %08lx DR7: %08lx\n", d6, d7); } @@ -192,39 +180,6 @@ void show_regs(struct pt_regs *regs) show_trace(NULL, regs, ®s->sp, regs->bp); } -/* - * This gets run with %bx containing the - * function to call, and %dx containing - * the "args". - */ -extern void kernel_thread_helper(void); - -/* - * Create a kernel thread - */ -int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) -{ - struct pt_regs regs; - - memset(®s, 0, sizeof(regs)); - - regs.bx = (unsigned long) fn; - regs.dx = (unsigned long) arg; - - regs.ds = __USER_DS; - regs.es = __USER_DS; - regs.fs = __KERNEL_PERCPU; - regs.gs = __KERNEL_STACK_CANARY; - regs.orig_ax = -1; - regs.ip = (unsigned long) kernel_thread_helper; - regs.cs = __KERNEL_CS | get_kernel_rpl(); - regs.flags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2; - - /* Ok, create the new process.. */ - return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL); -} -EXPORT_SYMBOL(kernel_thread); - void release_thread(struct task_struct *dead_task) { BUG_ON(dead_task->mm); @@ -436,46 +391,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } -int sys_clone(struct pt_regs *regs) -{ - unsigned long clone_flags; - unsigned long newsp; - int __user *parent_tidptr, *child_tidptr; - - clone_flags = regs->bx; - newsp = regs->cx; - parent_tidptr = (int __user *)regs->dx; - child_tidptr = (int __user *)regs->di; - if (!newsp) - newsp = regs->sp; - return do_fork(clone_flags, newsp, regs, 0, parent_tidptr, child_tidptr); -} - -/* - * sys_execve() executes a new program. - */ -int sys_execve(struct pt_regs *regs) -{ - int error; - char *filename; - - filename = getname((char __user *) regs->bx); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - goto out; - error = do_execve(filename, - (char __user * __user *) regs->cx, - (char __user * __user *) regs->dx, - regs); - if (error == 0) { - /* Make sure we don't return using sysenter.. */ - set_thread_flag(TIF_IRET); - } - putname(filename); -out: - return error; -} - #define top_esp (THREAD_SIZE - sizeof(unsigned long)) #define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long)) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a98fe88fab6..f9e033150cd 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -26,7 +26,6 @@ #include <linux/slab.h> #include <linux/user.h> #include <linux/interrupt.h> -#include <linux/utsname.h> #include <linux/delay.h> #include <linux/module.h> #include <linux/ptrace.h> @@ -38,7 +37,6 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/ftrace.h> -#include <linux/dmi.h> #include <asm/pgtable.h> #include <asm/system.h> @@ -59,8 +57,6 @@ asmlinkage extern void ret_from_fork(void); DEFINE_PER_CPU(unsigned long, old_rsp); static DEFINE_PER_CPU(unsigned char, is_idle); -unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED; - static ATOMIC_NOTIFIER_HEAD(idle_notifier); void idle_notifier_register(struct notifier_block *n) @@ -163,31 +159,21 @@ void __show_regs(struct pt_regs *regs, int all) unsigned long d0, d1, d2, d3, d6, d7; unsigned int fsindex, gsindex; unsigned int ds, cs, es; - const char *board; - - printk("\n"); - print_modules(); - board = dmi_get_system_info(DMI_PRODUCT_NAME); - if (!board) - board = ""; - printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s %s\n", - current->pid, current->comm, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version, board); - printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip); + + show_regs_common(); + printk(KERN_DEFAULT "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip); printk_address(regs->ip, 1); - printk(KERN_INFO "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, + printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->sp, regs->flags); - printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n", + printk(KERN_DEFAULT "RAX: %016lx RBX: %016lx RCX: %016lx\n", regs->ax, regs->bx, regs->cx); - printk(KERN_INFO "RDX: %016lx RSI: %016lx RDI: %016lx\n", + printk(KERN_DEFAULT "RDX: %016lx RSI: %016lx RDI: %016lx\n", regs->dx, regs->si, regs->di); - printk(KERN_INFO "RBP: %016lx R08: %016lx R09: %016lx\n", + printk(KERN_DEFAULT "RBP: %016lx R08: %016lx R09: %016lx\n", regs->bp, regs->r8, regs->r9); - printk(KERN_INFO "R10: %016lx R11: %016lx R12: %016lx\n", + printk(KERN_DEFAULT "R10: %016lx R11: %016lx R12: %016lx\n", regs->r10, regs->r11, regs->r12); - printk(KERN_INFO "R13: %016lx R14: %016lx R15: %016lx\n", + printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); asm("movl %%ds,%0" : "=r" (ds)); @@ -208,21 +194,21 @@ void __show_regs(struct pt_regs *regs, int all) cr3 = read_cr3(); cr4 = read_cr4(); - printk(KERN_INFO "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", + printk(KERN_DEFAULT "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", fs, fsindex, gs, gsindex, shadowgs); - printk(KERN_INFO "CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, + printk(KERN_DEFAULT "CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, es, cr0); - printk(KERN_INFO "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, + printk(KERN_DEFAULT "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, cr4); get_debugreg(d0, 0); get_debugreg(d1, 1); get_debugreg(d2, 2); - printk(KERN_INFO "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2); + printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2); get_debugreg(d3, 3); get_debugreg(d6, 6); get_debugreg(d7, 7); - printk(KERN_INFO "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7); + printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7); } void show_regs(struct pt_regs *regs) @@ -285,8 +271,9 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, *childregs = *regs; childregs->ax = 0; - childregs->sp = sp; - if (sp == ~0UL) + if (user_mode(regs)) + childregs->sp = sp; + else childregs->sp = (unsigned long)childregs; p->thread.sp = (unsigned long) childregs; @@ -349,26 +336,42 @@ out: return err; } -void -start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) +static void +start_thread_common(struct pt_regs *regs, unsigned long new_ip, + unsigned long new_sp, + unsigned int _cs, unsigned int _ss, unsigned int _ds) { loadsegment(fs, 0); - loadsegment(es, 0); - loadsegment(ds, 0); + loadsegment(es, _ds); + loadsegment(ds, _ds); load_gs_index(0); regs->ip = new_ip; regs->sp = new_sp; percpu_write(old_rsp, new_sp); - regs->cs = __USER_CS; - regs->ss = __USER_DS; - regs->flags = 0x200; + regs->cs = _cs; + regs->ss = _ss; + regs->flags = X86_EFLAGS_IF; set_fs(USER_DS); /* * Free the old FP and other extended state */ free_thread_xstate(current); } -EXPORT_SYMBOL_GPL(start_thread); + +void +start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) +{ + start_thread_common(regs, new_ip, new_sp, + __USER_CS, __USER_DS, 0); +} + +#ifdef CONFIG_IA32_EMULATION +void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp) +{ + start_thread_common(regs, new_ip, new_sp, + __USER32_CS, __USER32_DS, __USER32_DS); +} +#endif /* * switch_to(x,y) should switch tasks from x to y. @@ -504,25 +507,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } -/* - * sys_execve() executes a new program. - */ -asmlinkage -long sys_execve(char __user *name, char __user * __user *argv, - char __user * __user *envp, struct pt_regs *regs) -{ - long error; - char *filename; - - filename = getname(name); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - return error; - error = do_execve(filename, argv, envp, regs); - putname(filename); - return error; -} - void set_personality_64bit(void) { /* inherit personality from parent */ @@ -537,15 +521,6 @@ void set_personality_64bit(void) current->personality &= ~READ_IMPLIES_EXEC; } -asmlinkage long -sys_clone(unsigned long clone_flags, unsigned long newsp, - void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) -{ - if (!newsp) - newsp = regs->sp; - return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); -} - 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 04d182a7cfd..017d937639f 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -509,14 +509,14 @@ 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); @@ -535,14 +535,14 @@ 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) @@ -555,7 +555,9 @@ static int genregs_set(struct task_struct *target, return ret; } -static void ptrace_triggered(struct perf_event *bp, void *data) +static void ptrace_triggered(struct perf_event *bp, int nmi, + struct perf_sample_data *data, + struct pt_regs *regs) { int i; struct thread_struct *thread = &(current->thread); @@ -593,13 +595,13 @@ static unsigned long ptrace_get_dr7(struct perf_event *bp[]) return dr7; } -static struct perf_event * +static int ptrace_modify_breakpoint(struct perf_event *bp, int len, int type, struct task_struct *tsk, int disabled) { int err; int gen_len, gen_type; - DEFINE_BREAKPOINT_ATTR(attr); + struct perf_event_attr attr; /* * We shoud have at least an inactive breakpoint at this @@ -607,18 +609,18 @@ ptrace_modify_breakpoint(struct perf_event *bp, int len, int type, * written the address register first */ if (!bp) - return ERR_PTR(-EINVAL); + return -EINVAL; err = arch_bp_generic_fields(len, type, &gen_len, &gen_type); if (err) - return ERR_PTR(err); + return err; attr = bp->attr; attr.bp_len = gen_len; attr.bp_type = gen_type; attr.disabled = disabled; - return modify_user_hw_breakpoint(bp, &attr, bp->callback, tsk); + return modify_user_hw_breakpoint(bp, &attr); } /* @@ -656,28 +658,17 @@ restore: if (!second_pass) continue; - thread->ptrace_bps[i] = NULL; - bp = ptrace_modify_breakpoint(bp, len, type, + rc = ptrace_modify_breakpoint(bp, len, type, tsk, 1); - if (IS_ERR(bp)) { - rc = PTR_ERR(bp); - thread->ptrace_bps[i] = NULL; + if (rc) break; - } - thread->ptrace_bps[i] = bp; } continue; } - bp = ptrace_modify_breakpoint(bp, len, type, tsk, 0); - - /* Incorrect bp, or we have a bug in bp API */ - if (IS_ERR(bp)) { - rc = PTR_ERR(bp); - thread->ptrace_bps[i] = NULL; + rc = ptrace_modify_breakpoint(bp, len, type, tsk, 0); + if (rc) break; - } - thread->ptrace_bps[i] = bp; } /* * Make a second pass to free the remaining unused breakpoints @@ -721,9 +712,10 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr, { struct perf_event *bp; struct thread_struct *t = &tsk->thread; - DEFINE_BREAKPOINT_ATTR(attr); + struct perf_event_attr attr; if (!t->ptrace_bps[nr]) { + hw_breakpoint_init(&attr); /* * Put stub len and type to register (reserve) an inactive but * correct bp @@ -734,26 +726,32 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr, attr.disabled = 1; bp = register_user_hw_breakpoint(&attr, ptrace_triggered, tsk); + + /* + * CHECKME: the previous code returned -EIO if the addr wasn't + * a valid task virtual addr. The new one will return -EINVAL in + * this case. + * -EINVAL may be what we want for in-kernel breakpoints users, + * but -EIO looks better for ptrace, since we refuse a register + * writing for the user. And anyway this is the previous + * behaviour. + */ + if (IS_ERR(bp)) + return PTR_ERR(bp); + + t->ptrace_bps[nr] = bp; } else { + int err; + bp = t->ptrace_bps[nr]; - t->ptrace_bps[nr] = NULL; attr = bp->attr; attr.bp_addr = addr; - bp = modify_user_hw_breakpoint(bp, &attr, bp->callback, tsk); + err = modify_user_hw_breakpoint(bp, &attr); + if (err) + return err; } - /* - * CHECKME: the previous code returned -EIO if the addr wasn't a - * valid task virtual addr. The new one will return -EINVAL in this - * case. - * -EINVAL may be what we want for in-kernel breakpoints users, but - * -EIO looks better for ptrace, since we refuse a register writing - * for the user. And anyway this is the previous behaviour. - */ - if (IS_ERR(bp)) - return PTR_ERR(bp); - t->ptrace_bps[nr] = bp; return 0; } @@ -1460,14 +1458,14 @@ 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++)) @@ -1488,14 +1486,14 @@ 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) @@ -1678,21 +1676,33 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task) #endif } -void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, - int error_code, int si_code) +static void fill_sigtrap_info(struct task_struct *tsk, + struct pt_regs *regs, + int error_code, int si_code, + struct siginfo *info) { - struct siginfo info; - tsk->thread.trap_no = 1; tsk->thread.error_code = error_code; - memset(&info, 0, sizeof(info)); - info.si_signo = SIGTRAP; - info.si_code = si_code; + memset(info, 0, sizeof(*info)); + info->si_signo = SIGTRAP; + info->si_code = si_code; + info->si_addr = user_mode_vm(regs) ? (void __user *)regs->ip : NULL; +} + +void user_single_step_siginfo(struct task_struct *tsk, + struct pt_regs *regs, + struct siginfo *info) +{ + fill_sigtrap_info(tsk, regs, 0, TRAP_BRKPT, info); +} - /* User-mode ip? */ - info.si_addr = user_mode_vm(regs) ? (void __user *) regs->ip : NULL; +void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, + int error_code, int si_code) +{ + struct siginfo info; + fill_sigtrap_info(tsk, regs, error_code, si_code, &info); /* Send us the fake SIGTRAP */ force_sig_info(SIGTRAP, &info, tsk); } @@ -1757,29 +1767,22 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs) asmregparm void syscall_trace_leave(struct pt_regs *regs) { + bool step; + if (unlikely(current->audit_context)) audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_exit(regs, regs->ax); - if (test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, 0); - /* * If TIF_SYSCALL_EMU is set, we only get here because of * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP). * We already reported this syscall instruction in - * syscall_trace_enter(), so don't do any more now. - */ - if (unlikely(test_thread_flag(TIF_SYSCALL_EMU))) - return; - - /* - * If we are single-stepping, synthesize a trap to follow the - * system call instruction. + * syscall_trace_enter(). */ - if (test_thread_flag(TIF_SINGLESTEP) && - tracehook_consider_fatal_signal(current, SIGTRAP)) - send_sigtrap(current, regs, 0, TRAP_BRKPT); + step = unlikely(test_thread_flag(TIF_SINGLESTEP)) && + !test_thread_flag(TIF_SYSCALL_EMU); + if (step || test_thread_flag(TIF_SYSCALL_TRACE)) + tracehook_report_syscall_exit(regs, step); } diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 6c3b2c6fd77..18093d7498f 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -499,6 +499,7 @@ static void __init quirk_amd_nb_node(struct pci_dev *dev) { struct pci_dev *nb_ht; unsigned int devfn; + u32 node; u32 val; devfn = PCI_DEVFN(PCI_SLOT(dev->devfn), 0); @@ -507,7 +508,13 @@ static void __init quirk_amd_nb_node(struct pci_dev *dev) return; pci_read_config_dword(nb_ht, 0x60, &val); - set_dev_node(&dev->dev, val & 7); + node = val & 7; + /* + * Some hardware may return an invalid node ID, + * so check it first: + */ + if (node_online(node)) + set_dev_node(&dev->dev, node); pci_dev_put(nb_ht); } diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 2b97fc5b124..1545bc0c984 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -259,6 +259,14 @@ 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"), + }, + }, { } }; diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c index 61a837743fe..fda313ebbb0 100644 --- a/arch/x86/kernel/reboot_fixups_32.c +++ b/arch/x86/kernel/reboot_fixups_32.c @@ -12,7 +12,7 @@ #include <linux/interrupt.h> #include <asm/reboot_fixups.h> #include <asm/msr.h> -#include <asm/geode.h> +#include <linux/cs5535.h> static void cs5530a_warm_reset(struct pci_dev *dev) { @@ -80,6 +80,7 @@ void mach_reboot_fixups(void) continue; cur->reboot_fixup(dev); + pci_dev_put(dev); } } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 82e88cdda9b..f7b8b9894b2 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -73,6 +73,7 @@ #include <asm/mtrr.h> #include <asm/apic.h> +#include <asm/trampoline.h> #include <asm/e820.h> #include <asm/mpspec.h> #include <asm/setup.h> @@ -106,6 +107,7 @@ #include <asm/percpu.h> #include <asm/topology.h> #include <asm/apicdef.h> +#include <asm/k8.h> #ifdef CONFIG_X86_64 #include <asm/numa_64.h> #endif @@ -487,42 +489,11 @@ static void __init reserve_early_setup_data(void) #ifdef CONFIG_KEXEC -/** - * Reserve @size bytes of crashkernel memory at any suitable offset. - * - * @size: Size of the crashkernel memory to reserve. - * Returns the base address on success, and -1ULL on failure. - */ -static -unsigned long long __init find_and_reserve_crashkernel(unsigned long long size) -{ - const unsigned long long alignment = 16<<20; /* 16M */ - unsigned long long start = 0LL; - - while (1) { - int ret; - - start = find_e820_area(start, ULONG_MAX, size, alignment); - if (start == -1ULL) - return start; - - /* try to reserve it */ - ret = reserve_bootmem_generic(start, size, BOOTMEM_EXCLUSIVE); - if (ret >= 0) - return start; - - start += alignment; - } -} - static inline unsigned long long get_total_mem(void) { unsigned long long total; - total = max_low_pfn - min_low_pfn; -#ifdef CONFIG_HIGHMEM - total += highend_pfn - highstart_pfn; -#endif + total = max_pfn - min_low_pfn; return total << PAGE_SHIFT; } @@ -542,21 +513,25 @@ static void __init reserve_crashkernel(void) /* 0 means: find the address automatically */ if (crash_base <= 0) { - crash_base = find_and_reserve_crashkernel(crash_size); + const unsigned long long alignment = 16<<20; /* 16M */ + + crash_base = find_e820_area(alignment, ULONG_MAX, crash_size, + alignment); if (crash_base == -1ULL) { - pr_info("crashkernel reservation failed. " - "No suitable area found.\n"); + pr_info("crashkernel reservation failed - No suitable area found.\n"); return; } } else { - ret = reserve_bootmem_generic(crash_base, crash_size, - BOOTMEM_EXCLUSIVE); - if (ret < 0) { - pr_info("crashkernel reservation failed - " - "memory is in use\n"); + unsigned long long start; + + start = find_e820_area(crash_base, ULONG_MAX, crash_size, + 1<<20); + if (start != crash_base) { + pr_info("crashkernel reservation failed - memory is in use.\n"); return; } } + reserve_early(crash_base, crash_base + crash_size, "CRASH KERNEL"); printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " "for crashkernel (System RAM: %ldMB)\n", @@ -699,6 +674,9 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = { void __init setup_arch(char **cmdline_p) { + int acpi = 0; + int k8 = 0; + #ifdef CONFIG_X86_32 memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); visws_early_detect(); @@ -791,21 +769,18 @@ void __init setup_arch(char **cmdline_p) strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; -#ifdef CONFIG_X86_64 /* - * Must call this twice: Once just to detect whether hardware doesn't - * support NX (so that the early EHCI debug console setup can safely - * call set_fixmap(), and then again after parsing early parameters to - * honor the respective command line option. + * x86_configure_nx() is called before parse_early_param() to detect + * whether hardware doesn't support NX (so that the early EHCI debug + * console setup can safely call set_fixmap()). It may then be called + * again from within noexec_setup() during parsing early parameters + * to honor the respective command line option. */ - check_efer(); -#endif + x86_configure_nx(); parse_early_param(); -#ifdef CONFIG_X86_64 - check_efer(); -#endif + x86_report_nx(); /* Must be before kernel pagetables are setup */ vmi_activate(); @@ -901,6 +876,20 @@ void __init setup_arch(char **cmdline_p) reserve_brk(); + /* + * Find and reserve possible boot-time SMP configuration: + */ + find_smp_config(); + + reserve_trampoline_memory(); + +#ifdef CONFIG_ACPI_SLEEP + /* + * Reserve low memory region for sleep support. + * even before init_memory_mapping + */ + acpi_reserve_wakeup_memory(); +#endif init_gbpages(); /* max_pfn_mapped is updated here */ @@ -927,6 +916,8 @@ void __init setup_arch(char **cmdline_p) reserve_initrd(); + reserve_crashkernel(); + vsmp_init(); io_delay_init(); @@ -942,23 +933,15 @@ void __init setup_arch(char **cmdline_p) /* * Parse SRAT to discover nodes. */ - acpi_numa_init(); + acpi = acpi_numa_init(); #endif - initmem_init(0, max_pfn); - -#ifdef CONFIG_ACPI_SLEEP - /* - * Reserve low memory region for sleep support. - */ - acpi_reserve_bootmem(); +#ifdef CONFIG_K8_NUMA + if (!acpi) + k8 = !k8_numa_init(0, max_pfn); #endif - /* - * Find and reserve possible boot-time SMP configuration: - */ - find_smp_config(); - reserve_crashkernel(); + initmem_init(0, max_pfn, acpi, k8); #ifdef CONFIG_X86_64 /* diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index d559af913e1..35abcb8b00e 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> @@ -20,9 +22,9 @@ #include <asm/stackprotector.h> #ifdef CONFIG_DEBUG_PER_CPU_MAPS -# define DBG(x...) printk(KERN_DEBUG x) +# define DBG(fmt, ...) pr_dbg(fmt, ##__VA_ARGS__) #else -# define DBG(x...) +# define DBG(fmt, ...) do { if (0) pr_dbg(fmt, ##__VA_ARGS__); } while (0) #endif DEFINE_PER_CPU(int, cpu_number); @@ -116,8 +118,8 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, } else { ptr = __alloc_bootmem_node_nopanic(NODE_DATA(node), size, align, goal); - pr_debug("per cpu data for cpu%d %lu bytes on node%d at " - "%016lx\n", cpu, size, node, __pa(ptr)); + pr_debug("per cpu data for cpu%d %lu bytes on node%d at %016lx\n", + cpu, size, node, __pa(ptr)); } return ptr; #else @@ -198,8 +200,7 @@ void __init setup_per_cpu_areas(void) pcpu_cpu_distance, pcpu_fc_alloc, pcpu_fc_free); if (rc < 0) - pr_warning("PERCPU: %s allocator failed (%d), " - "falling back to page size\n", + pr_warning("%s allocator failed (%d), falling back to page size\n", pcpu_fc_names[pcpu_chosen_fc], rc); } if (rc < 0) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 74fe6d86dc5..4fd173cd8e5 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -545,22 +545,12 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, } #endif /* CONFIG_X86_32 */ -#ifdef CONFIG_X86_32 -int sys_sigaltstack(struct pt_regs *regs) -{ - const stack_t __user *uss = (const stack_t __user *)regs->bx; - stack_t __user *uoss = (stack_t __user *)regs->cx; - - return do_sigaltstack(uss, uoss, regs->sp); -} -#else /* !CONFIG_X86_32 */ -asmlinkage long +long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, struct pt_regs *regs) { return do_sigaltstack(uss, uoss, regs->sp); } -#endif /* CONFIG_X86_32 */ /* * Do a signal return; undo the signal stack. diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 324f2a44c22..678d0b8c26f 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -671,6 +671,26 @@ static void __cpuinit do_fork_idle(struct work_struct *work) complete(&c_idle->done); } +/* reduce the number of lines printed when booting a large cpu count system */ +static void __cpuinit announce_cpu(int cpu, int apicid) +{ + static int current_node = -1; + int node = cpu_to_node(cpu); + + if (system_state == SYSTEM_BOOTING) { + if (node != current_node) { + if (current_node > (-1)) + pr_cont(" Ok.\n"); + current_node = node; + pr_info("Booting Node %3d, Processors ", node); + } + pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " Ok.\n" : ""); + return; + } else + pr_info("Booting Node %d Processor %d APIC 0x%x\n", + node, cpu, apicid); +} + /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. @@ -687,7 +707,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), }; - INIT_WORK(&c_idle.work, do_fork_idle); + INIT_WORK_ON_STACK(&c_idle.work, do_fork_idle); alternatives_smp_switch(1); @@ -713,6 +733,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) if (IS_ERR(c_idle.idle)) { printk("failed fork for CPU %d\n", cpu); + destroy_work_on_stack(&c_idle.work); return PTR_ERR(c_idle.idle); } @@ -736,9 +757,8 @@ do_rest: /* start_ip had better be page-aligned! */ start_ip = setup_trampoline(); - /* So we see what's up */ - printk(KERN_INFO "Booting processor %d APIC 0x%x ip 0x%lx\n", - cpu, apicid, start_ip); + /* So we see what's up */ + announce_cpu(cpu, apicid); /* * This grunge runs the startup process for @@ -787,21 +807,17 @@ do_rest: udelay(100); } - if (cpumask_test_cpu(cpu, cpu_callin_mask)) { - /* number CPUs logically, starting from 1 (BSP is 0) */ - pr_debug("OK.\n"); - printk(KERN_INFO "CPU%d: ", cpu); - print_cpu_info(&cpu_data(cpu)); - pr_debug("CPU has booted.\n"); - } else { + if (cpumask_test_cpu(cpu, cpu_callin_mask)) + pr_debug("CPU%d: has booted.\n", cpu); + else { boot_error = 1; if (*((volatile unsigned char *)trampoline_base) == 0xA5) /* trampoline started but...? */ - printk(KERN_ERR "Stuck ??\n"); + pr_err("CPU%d: Stuck ??\n", cpu); else /* trampoline code not run */ - printk(KERN_ERR "Not responding.\n"); + pr_err("CPU%d: Not responding.\n", cpu); if (apic->inquire_remote_apic) apic->inquire_remote_apic(apicid); } @@ -831,6 +847,7 @@ do_rest: smpboot_restore_warm_reset_vector(); } + destroy_work_on_stack(&c_idle.work); return boot_error; } @@ -1291,14 +1308,16 @@ void native_cpu_die(unsigned int cpu) for (i = 0; i < 10; i++) { /* They ack this in play_dead by setting CPU_DEAD */ if (per_cpu(cpu_state, cpu) == CPU_DEAD) { - printk(KERN_INFO "CPU %d is now offline\n", cpu); + if (system_state == SYSTEM_RUNNING) + pr_info("CPU %u is now offline\n", cpu); + if (1 == num_online_cpus()) alternatives_smp_switch(0); return; } msleep(100); } - printk(KERN_ERR "CPU %u didn't die...\n", cpu); + pr_err("CPU %u didn't die...\n", cpu); } void play_dead_common(void) diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index c3eb207181f..922eefbb3f6 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -53,17 +53,19 @@ save_stack_address_nosched(void *data, unsigned long addr, int reliable) } static const struct stacktrace_ops save_stack_ops = { - .warning = save_stack_warning, - .warning_symbol = save_stack_warning_symbol, - .stack = save_stack_stack, - .address = save_stack_address, + .warning = save_stack_warning, + .warning_symbol = save_stack_warning_symbol, + .stack = save_stack_stack, + .address = save_stack_address, + .walk_stack = print_context_stack, }; static const struct stacktrace_ops save_stack_ops_nosched = { - .warning = save_stack_warning, - .warning_symbol = save_stack_warning_symbol, - .stack = save_stack_stack, - .address = save_stack_address_nosched, + .warning = save_stack_warning, + .warning_symbol = save_stack_warning_symbol, + .stack = save_stack_stack, + .address = save_stack_address_nosched, + .walk_stack = print_context_stack, }; /* diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c index 1884a8d12bf..dee1ff7cba5 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 45e00eb09c3..8aa2057efd1 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 70c2125d55b..15228b5d3eb 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/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index 1740c85e24b..364d015efeb 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/trampoline.c b/arch/x86/kernel/trampoline.c index cd022121cab..c652ef62742 100644 --- a/arch/x86/kernel/trampoline.c +++ b/arch/x86/kernel/trampoline.c @@ -12,21 +12,19 @@ #endif /* ready for x86_64 and x86 */ -unsigned char *__trampinitdata trampoline_base = __va(TRAMPOLINE_BASE); +unsigned char *__trampinitdata trampoline_base; void __init reserve_trampoline_memory(void) { -#ifdef CONFIG_X86_32 - /* - * But first pinch a few for the stack/trampoline stuff - * FIXME: Don't need the extra page at 4K, but need to fix - * trampoline before removing it. (see the GDT stuff) - */ - reserve_early(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE"); -#endif + unsigned long mem; + /* Has to be in very low memory so we can execute real-mode AP code. */ - reserve_early(TRAMPOLINE_BASE, TRAMPOLINE_BASE + TRAMPOLINE_SIZE, - "TRAMPOLINE"); + mem = find_e820_area(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE); + if (mem == -1L) + panic("Cannot allocate trampoline\n"); + + trampoline_base = __va(mem); + reserve_early(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE"); } /* diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index cd982f48e23..597683aa5ba 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -763,6 +763,7 @@ 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/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index eed156851f5..0aa5fed8b9e 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -33,7 +33,7 @@ static __cpuinitdata atomic_t stop_count; * we want to have the fastest, inlined, non-debug version * of a critical section, to be able to prove TSC time-warps: */ -static __cpuinitdata raw_spinlock_t sync_lock = __RAW_SPIN_LOCK_UNLOCKED; +static __cpuinitdata arch_spinlock_t sync_lock = __ARCH_SPIN_LOCK_UNLOCKED; static __cpuinitdata cycles_t last_tsc; static __cpuinitdata cycles_t max_warp; @@ -62,13 +62,13 @@ static __cpuinit void check_tsc_warp(void) * previous TSC that was measured (possibly on * another CPU) and update the previous TSC timestamp. */ - __raw_spin_lock(&sync_lock); + arch_spin_lock(&sync_lock); prev = last_tsc; rdtsc_barrier(); now = get_cycles(); rdtsc_barrier(); last_tsc = now; - __raw_spin_unlock(&sync_lock); + arch_spin_unlock(&sync_lock); /* * Be nice every now and then (and also check whether @@ -87,10 +87,10 @@ static __cpuinit void check_tsc_warp(void) * we saw a time-warp of the TSC going backwards: */ if (unlikely(prev > now)) { - __raw_spin_lock(&sync_lock); + arch_spin_lock(&sync_lock); max_warp = max(max_warp, prev - now); nr_warps++; - __raw_spin_unlock(&sync_lock); + arch_spin_unlock(&sync_lock); } } WARN(!(now-start), diff --git a/arch/x86/kernel/uv_irq.c b/arch/x86/kernel/uv_irq.c index 61d805df4c9..ece73d8e324 100644 --- a/arch/x86/kernel/uv_irq.c +++ b/arch/x86/kernel/uv_irq.c @@ -215,8 +215,7 @@ static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask) unsigned long mmr_offset; unsigned mmr_pnode; - dest = set_desc_affinity(desc, mask); - if (dest == BAD_APICID) + if (set_desc_affinity(desc, mask, &dest)) return -1; mmr_value = 0; diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c index 583f11d5c48..3c84aa001c1 100644 --- a/arch/x86/kernel/uv_time.c +++ b/arch/x86/kernel/uv_time.c @@ -74,7 +74,7 @@ struct uv_rtc_timer_head { */ static struct uv_rtc_timer_head **blade_info __read_mostly; -static int uv_rtc_enable; +static int uv_rtc_evt_enable; /* * Hardware interface routines @@ -90,7 +90,7 @@ static void uv_rtc_send_IPI(int cpu) pnode = uv_apicid_to_pnode(apicid); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (apicid << UVH_IPI_INT_APIC_ID_SHFT) | - (GENERIC_INTERRUPT_VECTOR << UVH_IPI_INT_VECTOR_SHFT); + (X86_PLATFORM_IPI_VECTOR << UVH_IPI_INT_VECTOR_SHFT); uv_write_global_mmr64(pnode, UVH_IPI_INT, val); } @@ -115,7 +115,7 @@ static int uv_setup_intr(int cpu, u64 expires) uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS, UVH_EVENT_OCCURRED0_RTC1_MASK); - val = (GENERIC_INTERRUPT_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) | + val = (X86_PLATFORM_IPI_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) | ((u64)cpu_physical_id(cpu) << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT); /* Set configuration */ @@ -123,7 +123,10 @@ static int uv_setup_intr(int cpu, u64 expires) /* Initialize comparator value */ uv_write_global_mmr64(pnode, UVH_INT_CMPB, expires); - return (expires < uv_read_rtc(NULL) && !uv_intr_pending(pnode)); + if (uv_read_rtc(NULL) <= expires) + return 0; + + return !uv_intr_pending(pnode); } /* @@ -223,6 +226,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires) next_cpu = head->next_cpu; *t = expires; + /* Will this one be next to go off? */ if (next_cpu < 0 || bcpu == next_cpu || expires < head->cpu[next_cpu].expires) { @@ -231,7 +235,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires) *t = ULLONG_MAX; uv_rtc_find_next_timer(head, pnode); spin_unlock_irqrestore(&head->lock, flags); - return 1; + return -ETIME; } } @@ -244,7 +248,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires) * * Returns 1 if this timer was pending. */ -static int uv_rtc_unset_timer(int cpu) +static int uv_rtc_unset_timer(int cpu, int force) { int pnode = uv_cpu_to_pnode(cpu); int bid = uv_cpu_to_blade_id(cpu); @@ -256,14 +260,15 @@ static int uv_rtc_unset_timer(int cpu) spin_lock_irqsave(&head->lock, flags); - if (head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) + if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force) rc = 1; - *t = ULLONG_MAX; - - /* Was the hardware setup for this timer? */ - if (head->next_cpu == bcpu) - uv_rtc_find_next_timer(head, pnode); + if (rc) { + *t = ULLONG_MAX; + /* Was the hardware setup for this timer? */ + if (head->next_cpu == bcpu) + uv_rtc_find_next_timer(head, pnode); + } spin_unlock_irqrestore(&head->lock, flags); @@ -310,32 +315,32 @@ static void uv_rtc_timer_setup(enum clock_event_mode mode, break; case CLOCK_EVT_MODE_UNUSED: case CLOCK_EVT_MODE_SHUTDOWN: - uv_rtc_unset_timer(ced_cpu); + uv_rtc_unset_timer(ced_cpu, 1); break; } } static void uv_rtc_interrupt(void) { - struct clock_event_device *ced = &__get_cpu_var(cpu_ced); int cpu = smp_processor_id(); + struct clock_event_device *ced = &per_cpu(cpu_ced, cpu); if (!ced || !ced->event_handler) return; - if (uv_rtc_unset_timer(cpu) != 1) + if (uv_rtc_unset_timer(cpu, 0) != 1) return; ced->event_handler(ced); } -static int __init uv_enable_rtc(char *str) +static int __init uv_enable_evt_rtc(char *str) { - uv_rtc_enable = 1; + uv_rtc_evt_enable = 1; return 1; } -__setup("uvrtc", uv_enable_rtc); +__setup("uvrtcevt", uv_enable_evt_rtc); static __init void uv_rtc_register_clockevents(struct work_struct *dummy) { @@ -350,27 +355,32 @@ static __init int uv_rtc_setup_clock(void) { int rc; - if (!uv_rtc_enable || !is_uv_system() || generic_interrupt_extension) + if (!is_uv_system()) return -ENODEV; - generic_interrupt_extension = uv_rtc_interrupt; - clocksource_uv.mult = clocksource_hz2mult(sn_rtc_cycles_per_second, clocksource_uv.shift); + /* If single blade, prefer tsc */ + if (uv_num_possible_blades() == 1) + clocksource_uv.rating = 250; + rc = clocksource_register(&clocksource_uv); - if (rc) { - generic_interrupt_extension = NULL; + if (rc) + printk(KERN_INFO "UV RTC clocksource failed rc %d\n", rc); + else + printk(KERN_INFO "UV RTC clocksource registered freq %lu MHz\n", + sn_rtc_cycles_per_second/(unsigned long)1E6); + + if (rc || !uv_rtc_evt_enable || x86_platform_ipi_callback) return rc; - } /* Setup and register clockevents */ rc = uv_rtc_allocate_timers(); - if (rc) { - clocksource_unregister(&clocksource_uv); - generic_interrupt_extension = NULL; - return rc; - } + if (rc) + goto error; + + x86_platform_ipi_callback = uv_rtc_interrupt; clock_event_device_uv.mult = div_sc(sn_rtc_cycles_per_second, NSEC_PER_SEC, clock_event_device_uv.shift); @@ -383,11 +393,19 @@ static __init int uv_rtc_setup_clock(void) rc = schedule_on_each_cpu(uv_rtc_register_clockevents); if (rc) { - clocksource_unregister(&clocksource_uv); - generic_interrupt_extension = NULL; + x86_platform_ipi_callback = NULL; uv_rtc_deallocate_timers(); + goto error; } + printk(KERN_INFO "UV RTC clockevents registered\n"); + + return 0; + +error: + clocksource_unregister(&clocksource_uv); + printk(KERN_INFO "UV RTC clockevents failed rc %d\n", rc); + return rc; } arch_initcall(uv_rtc_setup_clock); diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index abda6f53e71..34a279a7471 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -197,7 +197,7 @@ static void __init MP_processor_info(struct mpc_cpu *m) apic_version[m->apicid] = ver; } -static void __init visws_find_smp_config(unsigned int reserve) +static void __init visws_find_smp_config(void) { struct mpc_cpu *mp = phys_to_virt(CO_CPU_TAB_PHYS); unsigned short ncpus = readw(phys_to_virt(CO_CPU_NUM_PHYS)); diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 9c4e6253905..5ffb5622f79 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -197,9 +197,8 @@ out: static int do_vm86_irq_handling(int subfunction, int irqnumber); static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk); -int sys_vm86old(struct pt_regs *regs) +int sys_vm86old(struct vm86_struct __user *v86, struct pt_regs *regs) { - struct vm86_struct __user *v86 = (struct vm86_struct __user *)regs->bx; struct kernel_vm86_struct info; /* declare this _on top_, * this avoids wasting of stack space. * This remains on the stack until we @@ -227,7 +226,7 @@ out: } -int sys_vm86(struct pt_regs *regs) +int sys_vm86(unsigned long cmd, unsigned long arg, struct pt_regs *regs) { struct kernel_vm86_struct info; /* declare this _on top_, * this avoids wasting of stack space. @@ -239,12 +238,12 @@ int sys_vm86(struct pt_regs *regs) struct vm86plus_struct __user *v86; tsk = current; - switch (regs->bx) { + switch (cmd) { case VM86_REQUEST_IRQ: case VM86_FREE_IRQ: case VM86_GET_IRQ_BITS: case VM86_GET_AND_RESET_IRQ: - ret = do_vm86_irq_handling(regs->bx, (int)regs->cx); + ret = do_vm86_irq_handling(cmd, (int)arg); goto out; case VM86_PLUS_INSTALL_CHECK: /* @@ -261,7 +260,7 @@ int sys_vm86(struct pt_regs *regs) ret = -EPERM; if (tsk->thread.saved_sp0) goto out; - v86 = (struct vm86plus_struct __user *)regs->cx; + v86 = (struct vm86plus_struct __user *)arg; tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs, offsetof(struct kernel_vm86_struct, regs32) - sizeof(info.regs)); diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index 611b9e2360d..74c92bb194d 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -226,7 +226,7 @@ static void __devinit vmi_time_init_clockevent(void) evt->min_delta_ns = clockevent_delta2ns(1, evt); evt->cpumask = cpumask_of(cpu); - printk(KERN_WARNING "vmi: registering clock event %s. mult=%lu shift=%u\n", + printk(KERN_WARNING "vmi: registering clock event %s. mult=%u shift=%u\n", evt->name, evt->mult, evt->shift); clockevents_register_device(evt); } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 3c68fe2d46c..f92a0da608c 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -41,6 +41,32 @@ ENTRY(phys_startup_64) jiffies_64 = jiffies; #endif +#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +/* + * On 64-bit, align RODATA to 2MB so that even with CONFIG_DEBUG_RODATA + * we retain large page mappings for boundaries spanning kernel text, rodata + * and data sections. + * + * However, kernel identity mappings will have different RWX permissions + * to the pages mapping to text and to the pages padding (which are freed) the + * text section. Hence kernel identity mappings will be broken to smaller + * pages. For 64-bit, kernel text and kernel identity mappings are different, + * so we can enable protection checks that come with CONFIG_DEBUG_RODATA, + * as well as retain 2MB large page mappings for kernel text. + */ +#define X64_ALIGN_DEBUG_RODATA_BEGIN . = ALIGN(HPAGE_SIZE); + +#define X64_ALIGN_DEBUG_RODATA_END \ + . = ALIGN(HPAGE_SIZE); \ + __end_rodata_hpage_align = .; + +#else + +#define X64_ALIGN_DEBUG_RODATA_BEGIN +#define X64_ALIGN_DEBUG_RODATA_END + +#endif + PHDRS { text PT_LOAD FLAGS(5); /* R_E */ data PT_LOAD FLAGS(7); /* RWE */ @@ -90,7 +116,9 @@ SECTIONS EXCEPTION_TABLE(16) :text = 0x9090 + X64_ALIGN_DEBUG_RODATA_BEGIN RO_DATA(PAGE_SIZE) + X64_ALIGN_DEBUG_RODATA_END /* Data */ .data : AT(ADDR(.data) - LOAD_OFFSET) { @@ -107,13 +135,13 @@ SECTIONS PAGE_ALIGNED_DATA(PAGE_SIZE) - CACHELINE_ALIGNED_DATA(CONFIG_X86_L1_CACHE_BYTES) + CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES) DATA_DATA CONSTRUCTORS /* rarely changed data like cpu maps */ - READ_MOSTLY_DATA(CONFIG_X86_INTERNODE_CACHE_BYTES) + READ_MOSTLY_DATA(INTERNODE_CACHE_BYTES) /* End of data section */ _edata = .; @@ -137,12 +165,12 @@ SECTIONS *(.vsyscall_0) } :user - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(L1_CACHE_BYTES); .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { *(.vsyscall_fn) } - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(L1_CACHE_BYTES); .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) { *(.vsyscall_gtod_data) } @@ -166,7 +194,7 @@ SECTIONS } vgetcpu_mode = VVIRT(.vgetcpu_mode); - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(L1_CACHE_BYTES); .jiffies : AT(VLOAD(.jiffies)) { *(.jiffies) } @@ -291,9 +319,7 @@ SECTIONS __brk_limit = .; } - .end : AT(ADDR(.end) - LOAD_OFFSET) { - _end = .; - } + _end = .; STABS_DEBUG DWARF_DEBUG diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index e02d92d12bc..9055e5872ff 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; diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index a1029769b6f..619f7f88b8c 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -17,8 +17,6 @@ EXPORT_SYMBOL(mcount); #endif -EXPORT_SYMBOL(kernel_thread); - EXPORT_SYMBOL(__get_user_1); EXPORT_SYMBOL(__get_user_2); EXPORT_SYMBOL(__get_user_4); @@ -56,4 +54,6 @@ EXPORT_SYMBOL(__memcpy); EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(init_level4_pgt); -EXPORT_SYMBOL(load_gs_index); +#ifndef CONFIG_PARAVIRT +EXPORT_SYMBOL(native_load_gs_index); +#endif diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index d11c5ff7c65..ccd179dec36 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -13,6 +13,7 @@ #include <asm/e820.h> #include <asm/time.h> #include <asm/irq.h> +#include <asm/pat.h> #include <asm/tsc.h> #include <asm/iommu.h> @@ -80,4 +81,5 @@ struct x86_platform_ops x86_platform = { .get_wallclock = mach_get_cmos_time, .set_wallclock = mach_set_rtc_mmss, .iommu_shutdown = iommu_shutdown_noop, + .is_untracked_pat_range = is_ISA_range, }; |