diff options
Diffstat (limited to 'arch/x86/kernel')
63 files changed, 866 insertions, 639 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 616ebd2..9abf855 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -2,7 +2,11 @@ # Makefile for the linux kernel. # -extra-y := head_$(BITS).o head$(BITS).o head.o vmlinux.lds +extra-y := head_$(BITS).o +extra-y += head$(BITS).o +extra-y += ebda.o +extra-y += platform-quirks.o +extra-y += vmlinux.lds CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 8c2f1ef..f115a58 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -136,7 +136,7 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) { struct acpi_table_madt *madt = NULL; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -EINVAL; madt = (struct acpi_table_madt *)table; @@ -913,6 +913,15 @@ late_initcall(hpet_insert_resource); static int __init acpi_parse_fadt(struct acpi_table_header *table) { + if (!(acpi_gbl_FADT.boot_flags & ACPI_FADT_LEGACY_DEVICES)) { + pr_debug("ACPI: no legacy devices present\n"); + x86_platform.legacy.devices.pnpbios = 0; + } + + if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) { + pr_debug("ACPI: not registering RTC platform device\n"); + x86_platform.legacy.rtc = 0; + } #ifdef CONFIG_X86_PM_TIMER /* detect the location of the ACPI PM Timer */ @@ -951,7 +960,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) { int count; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; /* @@ -979,7 +988,7 @@ static int __init acpi_parse_madt_lapic_entries(void) int ret; struct acpi_subtable_proc madt_proc[2]; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; /* @@ -1125,7 +1134,7 @@ static int __init acpi_parse_madt_ioapic_entries(void) if (acpi_disabled || acpi_noirq) return -ENODEV; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; /* diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 25f9093..5cb272a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -11,6 +11,7 @@ #include <linux/stop_machine.h> #include <linux/slab.h> #include <linux/kdebug.h> +#include <asm/text-patching.h> #include <asm/alternative.h> #include <asm/sections.h> #include <asm/pgtable.h> diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d356987..60078a6 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -607,7 +607,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev) long tapic = apic_read(APIC_TMCCT); unsigned long pm = acpi_pm_read_early(); - if (cpu_has_tsc) + if (boot_cpu_has(X86_FEATURE_TSC)) tsc = rdtsc(); switch (lapic_cal_loops++) { @@ -668,7 +668,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) *delta = (long)res; /* Correct the tsc counter value */ - if (cpu_has_tsc) { + if (boot_cpu_has(X86_FEATURE_TSC)) { res = (((u64)(*deltatsc)) * pm_100ms); do_div(res, deltapm); apic_printk(APIC_VERBOSE, "TSC delta adjusted to " @@ -760,7 +760,7 @@ static int __init calibrate_APIC_clock(void) apic_printk(APIC_VERBOSE, "..... calibration result: %u\n", lapic_timer_frequency); - if (cpu_has_tsc) { + if (boot_cpu_has(X86_FEATURE_TSC)) { apic_printk(APIC_VERBOSE, "..... CPU clock speed is " "%ld.%04ld MHz.\n", (deltatsc / LAPIC_CAL_LOOPS) / (1000000 / HZ), @@ -1085,7 +1085,7 @@ void lapic_shutdown(void) { unsigned long flags; - if (!cpu_has_apic && !apic_from_smp_config()) + if (!boot_cpu_has(X86_FEATURE_APIC) && !apic_from_smp_config()) return; local_irq_save(flags); @@ -1134,7 +1134,7 @@ void __init init_bsp_APIC(void) * Don't do the setup now if we have a SMP BIOS as the * through-I/O-APIC virtual wire mode might be active. */ - if (smp_found_config || !cpu_has_apic) + if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC)) return; /* @@ -1227,7 +1227,7 @@ void setup_local_APIC(void) unsigned long long tsc = 0, ntsc; long long max_loops = cpu_khz ? cpu_khz : 1000000; - if (cpu_has_tsc) + if (boot_cpu_has(X86_FEATURE_TSC)) tsc = rdtsc(); if (disable_apic) { @@ -1311,7 +1311,7 @@ void setup_local_APIC(void) break; } if (queued) { - if (cpu_has_tsc && cpu_khz) { + if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { ntsc = rdtsc(); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else @@ -1445,7 +1445,7 @@ static void __x2apic_disable(void) { u64 msr; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return; rdmsrl(MSR_IA32_APICBASE, msr); @@ -1561,7 +1561,7 @@ void __init check_x2apic(void) pr_info("x2apic: enabled by BIOS, switching to x2apic ops\n"); x2apic_mode = 1; x2apic_state = X2APIC_ON; - } else if (!cpu_has_x2apic) { + } else if (!boot_cpu_has(X86_FEATURE_X2APIC)) { x2apic_state = X2APIC_DISABLED; } } @@ -1632,7 +1632,7 @@ void __init enable_IR_x2apic(void) */ static int __init detect_init_APIC(void) { - if (!cpu_has_apic) { + if (!boot_cpu_has(X86_FEATURE_APIC)) { pr_info("No local APIC present\n"); return -1; } @@ -1711,14 +1711,14 @@ static int __init detect_init_APIC(void) goto no_apic; case X86_VENDOR_INTEL: if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 || - (boot_cpu_data.x86 == 5 && cpu_has_apic)) + (boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC))) break; goto no_apic; default: goto no_apic; } - if (!cpu_has_apic) { + if (!boot_cpu_has(X86_FEATURE_APIC)) { /* * Over-ride BIOS and try to enable the local APIC only if * "lapic" specified. @@ -2233,19 +2233,19 @@ int __init APIC_init_uniprocessor(void) return -1; } #ifdef CONFIG_X86_64 - if (!cpu_has_apic) { + if (!boot_cpu_has(X86_FEATURE_APIC)) { disable_apic = 1; pr_info("Apic disabled by BIOS\n"); return -1; } #else - if (!smp_found_config && !cpu_has_apic) + if (!smp_found_config && !boot_cpu_has(X86_FEATURE_APIC)) return -1; /* * Complain if the BIOS pretends there is one. */ - if (!cpu_has_apic && + if (!boot_cpu_has(X86_FEATURE_APIC) && APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) { pr_err("BIOS bug, local APIC 0x%x not detected!...\n", boot_cpu_physical_apicid); @@ -2426,7 +2426,7 @@ static void apic_pm_activate(void) static int __init init_lapic_sysfs(void) { /* XXX: remove suspend/resume procs if !apic_pm_state.active? */ - if (cpu_has_apic) + if (boot_cpu_has(X86_FEATURE_APIC)) register_syscore_ops(&lapic_syscore_ops); return 0; diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 331a7a0..13d19ed 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -100,13 +100,13 @@ static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask, static u32 noop_apic_read(u32 reg) { - WARN_ON_ONCE((cpu_has_apic && !disable_apic)); + WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic); return 0; } static void noop_apic_write(u32 reg, u32 v) { - WARN_ON_ONCE(cpu_has_apic && !disable_apic); + WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic); } struct apic apic_noop = { diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index fdb0fbf..84e33ff 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1454,7 +1454,7 @@ void native_disable_io_apic(void) ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry); } - if (cpu_has_apic || apic_from_smp_config()) + if (boot_cpu_has(X86_FEATURE_APIC) || apic_from_smp_config()) disconnect_bsp_APIC(ioapic_i8259.pin != -1); } diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 28bde88..2a0f225 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -230,7 +230,7 @@ int safe_smp_processor_id(void) { int apicid, cpuid; - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return 0; apicid = hard_smp_processor_id(); diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index ef49551..a5e400a 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -944,7 +944,7 @@ static int __init print_ICs(void) print_PIC(); /* don't print out if apic is not there */ - if (!cpu_has_apic && !apic_from_smp_config()) + if (!boot_cpu_has(X86_FEATURE_APIC) && !apic_from_smp_config()) return 0; print_local_APICs(show_lapic); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 9307f18..c7364bd 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -2267,7 +2267,7 @@ static int __init apm_init(void) dmi_check_system(apm_dmi_table); - if (apm_info.bios.version == 0 || paravirt_enabled() || machine_is_olpc()) { + if (apm_info.bios.version == 0 || machine_is_olpc()) { printk(KERN_INFO "apm: BIOS not found.\n"); return -ENODEV; } diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 5c04246..674134e 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -80,6 +80,7 @@ void common(void) { OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); OFFSET(BP_version, boot_params, hdr.version); OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment); + OFFSET(BP_init_size, boot_params, hdr.init_size); OFFSET(BP_pref_address, boot_params, hdr.pref_address); OFFSET(BP_code32_start, boot_params, hdr.code32_start); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 7b76eb6..c343a54 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -565,14 +565,17 @@ static void early_init_amd(struct cpuinfo_x86 *c) * can safely set X86_FEATURE_EXTD_APICID unconditionally for families * after 16h. */ - if (cpu_has_apic && c->x86 > 0x16) { - set_cpu_cap(c, X86_FEATURE_EXTD_APICID); - } else if (cpu_has_apic && c->x86 >= 0xf) { - /* check CPU config space for extended APIC ID */ - unsigned int val; - val = read_pci_config(0, 24, 0, 0x68); - if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18))) + if (boot_cpu_has(X86_FEATURE_APIC)) { + if (c->x86 > 0x16) set_cpu_cap(c, X86_FEATURE_EXTD_APICID); + else if (c->x86 >= 0xf) { + /* check CPU config space for extended APIC ID */ + unsigned int val; + + val = read_pci_config(0, 24, 0, 0x68); + if ((val >> 17 & 0x3) == 0x3) + set_cpu_cap(c, X86_FEATURE_EXTD_APICID); + } } #endif @@ -628,6 +631,7 @@ static void init_amd_k8(struct cpuinfo_x86 *c) */ msr_set_bit(MSR_K7_HWCR, 6); #endif + set_cpu_bug(c, X86_BUG_SWAPGS_FENCE); } static void init_amd_gh(struct cpuinfo_x86 *c) @@ -746,7 +750,7 @@ static void init_amd(struct cpuinfo_x86 *c) if (c->x86 >= 0xf) set_cpu_cap(c, X86_FEATURE_K8); - if (cpu_has_xmm2) { + if (cpu_has(c, X86_FEATURE_XMM2)) { /* MFENCE stops RDTSC speculation */ set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8394b3d..6ef6ed9 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -430,7 +430,7 @@ void load_percpu_segment(int cpu) #ifdef CONFIG_X86_32 loadsegment(fs, __KERNEL_PERCPU); #else - loadsegment(gs, 0); + __loadsegment_simple(gs, 0); wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu)); #endif load_stack_canary_segment(); @@ -717,6 +717,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c) } } + if (c->extended_cpuid_level >= 0x80000007) { + cpuid(0x80000007, &eax, &ebx, &ecx, &edx); + + c->x86_capability[CPUID_8000_0007_EBX] = ebx; + c->x86_power = edx; + } + if (c->extended_cpuid_level >= 0x80000008) { cpuid(0x80000008, &eax, &ebx, &ecx, &edx); @@ -729,9 +736,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_phys_bits = 36; #endif - if (c->extended_cpuid_level >= 0x80000007) - c->x86_power = cpuid_edx(0x80000007); - if (c->extended_cpuid_level >= 0x8000000a) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); @@ -862,30 +866,34 @@ static void detect_nopl(struct cpuinfo_x86 *c) #else set_cpu_cap(c, X86_FEATURE_NOPL); #endif +} +static void detect_null_seg_behavior(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_X86_64 /* - * ESPFIX is a strange bug. All real CPUs have it. Paravirt - * systems that run Linux at CPL > 0 may or may not have the - * issue, but, even if they have the issue, there's absolutely - * nothing we can do about it because we can't use the real IRET - * instruction. + * Empirically, writing zero to a segment selector on AMD does + * not clear the base, whereas writing zero to a segment + * selector on Intel does clear the base. Intel's behavior + * allows slightly faster context switches in the common case + * where GS is unused by the prev and next threads. * - * NB: For the time being, only 32-bit kernels support - * X86_BUG_ESPFIX as such. 64-bit kernels directly choose - * whether to apply espfix using paravirt hooks. If any - * non-paravirt system ever shows up that does *not* have the - * ESPFIX issue, we can change this. + * Since neither vendor documents this anywhere that I can see, + * detect it directly instead of hardcoding the choice by + * vendor. + * + * I've designated AMD's behavior as the "bug" because it's + * counterintuitive and less friendly. */ -#ifdef CONFIG_X86_32 -#ifdef CONFIG_PARAVIRT - do { - extern void native_iret(void); - if (pv_cpu_ops.iret == native_iret) - set_cpu_bug(c, X86_BUG_ESPFIX); - } while (0); -#else - set_cpu_bug(c, X86_BUG_ESPFIX); -#endif + + unsigned long old_base, tmp; + rdmsrl(MSR_FS_BASE, old_base); + wrmsrl(MSR_FS_BASE, 1); + loadsegment(fs, 0); + rdmsrl(MSR_FS_BASE, tmp); + if (tmp != 0) + set_cpu_bug(c, X86_BUG_NULL_SEG); + wrmsrl(MSR_FS_BASE, old_base); #endif } @@ -921,6 +929,33 @@ static void generic_identify(struct cpuinfo_x86 *c) get_model_name(c); /* Default name */ detect_nopl(c); + + detect_null_seg_behavior(c); + + /* + * ESPFIX is a strange bug. All real CPUs have it. Paravirt + * systems that run Linux at CPL > 0 may or may not have the + * issue, but, even if they have the issue, there's absolutely + * nothing we can do about it because we can't use the real IRET + * instruction. + * + * NB: For the time being, only 32-bit kernels support + * X86_BUG_ESPFIX as such. 64-bit kernels directly choose + * whether to apply espfix using paravirt hooks. If any + * non-paravirt system ever shows up that does *not* have the + * ESPFIX issue, we can change this. + */ +#ifdef CONFIG_X86_32 +# ifdef CONFIG_PARAVIRT + do { + extern void native_iret(void); + if (pv_cpu_ops.iret == native_iret) + set_cpu_bug(c, X86_BUG_ESPFIX); + } while (0); +# else + set_cpu_bug(c, X86_BUG_ESPFIX); +# endif +#endif } static void x86_init_cache_qos(struct cpuinfo_x86 *c) @@ -1076,12 +1111,12 @@ void enable_sep_cpu(void) struct tss_struct *tss; int cpu; + if (!boot_cpu_has(X86_FEATURE_SEP)) + return; + cpu = get_cpu(); tss = &per_cpu(cpu_tss, cpu); - if (!boot_cpu_has(X86_FEATURE_SEP)) - goto out; - /* * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field -- * see the big comment in struct x86_hw_tss's definition. @@ -1096,7 +1131,6 @@ void enable_sep_cpu(void) wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); -out: put_cpu(); } #endif @@ -1528,7 +1562,7 @@ void cpu_init(void) pr_info("Initializing CPU#%d\n", cpu); if (cpu_feature_enabled(X86_FEATURE_VME) || - cpu_has_tsc || + boot_cpu_has(X86_FEATURE_TSC) || boot_cpu_has(X86_FEATURE_DE)) cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 6adef9c..bd9dcd6 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -333,7 +333,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) switch (dir0_lsn) { case 0xd: /* either a 486SLC or DLC w/o DEVID */ dir0_msn = 0; - p = Cx486_name[(cpu_has_fpu ? 1 : 0)]; + p = Cx486_name[!!boot_cpu_has(X86_FEATURE_FPU)]; break; case 0xe: /* a 486S A step */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 1f7fdb9..8dae51f 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -152,9 +152,9 @@ static void early_init_intel(struct cpuinfo_x86 *c) * the TLB when any changes are made to any of the page table entries. * The operating system must reload CR3 to cause the TLB to be flushed" * - * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should - * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE - * to be modified + * As a result, boot_cpu_has(X86_FEATURE_PGE) in arch/x86/include/asm/tlbflush.h + * should be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE + * to be modified. */ if (c->x86 == 5 && c->x86_model == 9) { pr_info("Disabling PGE capability bit\n"); @@ -233,7 +233,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * The Quark is also family 5, but does not have the same bug. */ clear_cpu_bug(c, X86_BUG_F00F); - if (!paravirt_enabled() && c->x86 == 5 && c->x86_model < 9) { + if (c->x86 == 5 && c->x86_model < 9) { static int f00f_workaround_enabled; set_cpu_bug(c, X86_BUG_F00F); @@ -281,7 +281,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * integrated APIC (see 11AP erratum in "Pentium Processor * Specification Update"). */ - if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 && + if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 && (c->x86_mask < 0x6 || c->x86_mask == 0xb)) set_cpu_bug(c, X86_BUG_11AP); @@ -336,7 +336,7 @@ static int intel_num_cpu_cores(struct cpuinfo_x86 *c) { unsigned int eax, ebx, ecx, edx; - if (c->cpuid_level < 4) + if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4) return 1; /* Intel has a non-standard dependency on %ecx for this CPUID level. */ @@ -456,7 +456,7 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON); } - if (cpu_has_xmm2) + if (cpu_has(c, X86_FEATURE_XMM2)) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); if (boot_cpu_has(X86_FEATURE_DS)) { @@ -468,7 +468,7 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_PEBS); } - if (c->x86 == 6 && cpu_has_clflush && + if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_CLFLUSH) && (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47)) set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR); diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 2658e2a..93d824e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -26,6 +26,52 @@ static struct gen_pool *mce_evt_pool; static LLIST_HEAD(mce_event_llist); static char gen_pool_buf[MCE_POOLSZ]; +/* + * Compare the record "t" with each of the records on list "l" to see if + * an equivalent one is present in the list. + */ +static bool is_duplicate_mce_record(struct mce_evt_llist *t, struct mce_evt_llist *l) +{ + struct mce_evt_llist *node; + struct mce *m1, *m2; + + m1 = &t->mce; + + llist_for_each_entry(node, &l->llnode, llnode) { + m2 = &node->mce; + + if (!mce_cmp(m1, m2)) + return true; + } + return false; +} + +/* + * The system has panicked - we'd like to peruse the list of MCE records + * that have been queued, but not seen by anyone yet. The list is in + * reverse time order, so we need to reverse it. While doing that we can + * also drop duplicate records (these were logged because some banks are + * shared between cores or by all threads on a socket). + */ +struct llist_node *mce_gen_pool_prepare_records(void) +{ + struct llist_node *head; + LLIST_HEAD(new_head); + struct mce_evt_llist *node, *t; + + head = llist_del_all(&mce_event_llist); + if (!head) + return NULL; + + /* squeeze out duplicates while reversing order */ + llist_for_each_entry_safe(node, t, head, llnode) { + if (!is_duplicate_mce_record(node, t)) + llist_add(&node->llnode, &new_head); + } + + return new_head.first; +} + void mce_gen_pool_process(void) { struct llist_node *head; diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 547720e..cd74a3f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -35,6 +35,7 @@ void mce_gen_pool_process(void); bool mce_gen_pool_empty(void); int mce_gen_pool_add(struct mce *mce); int mce_gen_pool_init(void); +struct llist_node *mce_gen_pool_prepare_records(void); extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); @@ -81,3 +82,17 @@ static inline int apei_clear_mce(u64 record_id) #endif void mce_inject_log(struct mce *m); + +/* + * We consider records to be equivalent if bank+status+addr+misc all match. + * This is only used when the system is going down because of a fatal error + * to avoid cluttering the console log with essentially repeated information. + * In normal processing all errors seen are logged. + */ +static inline bool mce_cmp(struct mce *m1, struct mce *m2) +{ + return m1->bank != m2->bank || + m1->status != m2->status || + m1->addr != m2->addr || + m1->misc != m2->misc; +} diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 5119766..631356c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -204,6 +204,33 @@ static int error_context(struct mce *m) return IN_KERNEL; } +static int mce_severity_amd_smca(struct mce *m, int err_ctx) +{ + u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank); + u32 low, high; + + /* + * We need to look at the following bits: + * - "succor" bit (data poisoning support), and + * - TCC bit (Task Context Corrupt) + * in MCi_STATUS to determine error severity. + */ + if (!mce_flags.succor) + return MCE_PANIC_SEVERITY; + + if (rdmsr_safe(addr, &low, &high)) + return MCE_PANIC_SEVERITY; + + /* TCC (Task context corrupt). If set and if IN_KERNEL, panic. */ + if ((low & MCI_CONFIG_MCAX) && + (m->status & MCI_STATUS_TCC) && + (err_ctx == IN_KERNEL)) + return MCE_PANIC_SEVERITY; + + /* ...otherwise invoke hwpoison handler. */ + return MCE_AR_SEVERITY; +} + /* * See AMD Error Scope Hierarchy table in a newer BKDG. For example * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features" @@ -225,6 +252,9 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc * to at least kill process to prolong system operation. */ if (mce_flags.overflow_recov) { + if (mce_flags.smca) + return mce_severity_amd_smca(m, ctx); + /* software can try to contain */ if (!(m->mcgstatus & MCG_STATUS_RIPV) && (ctx == IN_KERNEL)) return MCE_PANIC_SEVERITY; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index f0c921b..92e5e37 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -161,7 +161,6 @@ void mce_log(struct mce *mce) if (!mce_gen_pool_add(mce)) irq_work_queue(&mce_irq_work); - mce->finished = 0; wmb(); for (;;) { entry = mce_log_get_idx_check(mcelog.next); @@ -194,7 +193,6 @@ void mce_log(struct mce *mce) mcelog.entry[entry].finished = 1; wmb(); - mce->finished = 1; set_bit(0, &mce_need_notify); } @@ -224,6 +222,53 @@ void mce_unregister_decode_chain(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); +static inline u32 ctl_reg(int bank) +{ + return MSR_IA32_MCx_CTL(bank); +} + +static inline u32 status_reg(int bank) +{ + return MSR_IA32_MCx_STATUS(bank); +} + +static inline u32 addr_reg(int bank) +{ + return MSR_IA32_MCx_ADDR(bank); +} + +static inline u32 misc_reg(int bank) +{ + return MSR_IA32_MCx_MISC(bank); +} + +static inline u32 smca_ctl_reg(int bank) +{ + return MSR_AMD64_SMCA_MCx_CTL(bank); +} + +static inline u32 smca_status_reg(int bank) +{ + return MSR_AMD64_SMCA_MCx_STATUS(bank); +} + +static inline u32 smca_addr_reg(int bank) +{ + return MSR_AMD64_SMCA_MCx_ADDR(bank); +} + +static inline u32 smca_misc_reg(int bank) +{ + return MSR_AMD64_SMCA_MCx_MISC(bank); +} + +struct mca_msr_regs msr_ops = { + .ctl = ctl_reg, + .status = status_reg, + .addr = addr_reg, + .misc = misc_reg +}; + static void print_mce(struct mce *m) { int ret = 0; @@ -290,7 +335,9 @@ static void wait_for_panic(void) static void mce_panic(const char *msg, struct mce *final, char *exp) { - int i, apei_err = 0; + int apei_err = 0; + struct llist_node *pending; + struct mce_evt_llist *l; if (!fake_panic) { /* @@ -307,11 +354,10 @@ static void mce_panic(const char *msg, struct mce *final, char *exp) if (atomic_inc_return(&mce_fake_panicked) > 1) return; } + pending = mce_gen_pool_prepare_records(); /* First print corrected ones that are still unlogged */ - for (i = 0; i < MCE_LOG_LEN; i++) { - struct mce *m = &mcelog.entry[i]; - if (!(m->status & MCI_STATUS_VAL)) - continue; + llist_for_each_entry(l, pending, llnode) { + struct mce *m = &l->mce; if (!(m->status & MCI_STATUS_UC)) { print_mce(m); if (!apei_err) @@ -319,13 +365,11 @@ static void mce_panic(const char *msg, struct mce *final, char *exp) } } /* Now print uncorrected but with the final one last */ - for (i = 0; i < MCE_LOG_LEN; i++) { - struct mce *m = &mcelog.entry[i]; - if (!(m->status & MCI_STATUS_VAL)) - continue; + llist_for_each_entry(l, pending, llnode) { + struct mce *m = &l->mce; if (!(m->status & MCI_STATUS_UC)) continue; - if (!final || memcmp(m, final, sizeof(struct mce))) { + if (!final || mce_cmp(m, final)) { print_mce(m); if (!apei_err) apei_err = apei_write_mce(m); @@ -356,11 +400,11 @@ static int msr_to_offset(u32 msr) if (msr == mca_cfg.rip_msr) return offsetof(struct mce, ip); - if (msr == MSR_IA32_MCx_STATUS(bank)) + if (msr == msr_ops.status(bank)) return offsetof(struct mce, status); - if (msr == MSR_IA32_MCx_ADDR(bank)) + if (msr == msr_ops.addr(bank)) return offsetof(struct mce, addr); - if (msr == MSR_IA32_MCx_MISC(bank)) + if (msr == msr_ops.misc(bank)) return offsetof(struct mce, misc); if (msr == MSR_IA32_MCG_STATUS) return offsetof(struct mce, mcgstatus); @@ -523,9 +567,9 @@ static struct notifier_block mce_srao_nb = { static void mce_read_aux(struct mce *m, int i) { if (m->status & MCI_STATUS_MISCV) - m->misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i)); + m->misc = mce_rdmsrl(msr_ops.misc(i)); if (m->status & MCI_STATUS_ADDRV) { - m->addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i)); + m->addr = mce_rdmsrl(msr_ops.addr(i)); /* * Mask the reported address by the reported granularity. @@ -607,7 +651,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) m.tsc = 0; barrier(); - m.status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); + m.status = mce_rdmsrl(msr_ops.status(i)); if (!(m.status & MCI_STATUS_VAL)) continue; @@ -654,7 +698,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) /* * Clear state for this bank. */ - mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0); + mce_wrmsrl(msr_ops.status(i), 0); } /* @@ -679,7 +723,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, char *tmp; for (i = 0; i < mca_cfg.banks; i++) { - m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); + m->status = mce_rdmsrl(msr_ops.status(i)); if (m->status & MCI_STATUS_VAL) { __set_bit(i, validp); if (quirk_no_way_out) @@ -830,9 +874,9 @@ static int mce_start(int *no_way_out) atomic_add(*no_way_out, &global_nwo); /* - * global_nwo should be updated before mce_callin + * Rely on the implied barrier below, such that global_nwo + * is updated before mce_callin. */ - smp_wmb(); order = atomic_inc_return(&mce_callin); /* @@ -957,7 +1001,7 @@ static void mce_clear_state(unsigned long *toclear) for (i = 0; i < mca_cfg.banks; i++) { if (test_bit(i, toclear)) - mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0); + mce_wrmsrl(msr_ops.status(i), 0); } } @@ -994,11 +1038,12 @@ void do_machine_check(struct pt_regs *regs, long error_code) int i; int worst = 0; int severity; + /* * Establish sequential order between the CPUs entering the machine * check handler. */ - int order; + int order = -1; /* * If no_way_out gets set, there is no safe way to recover from this * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. @@ -1012,7 +1057,12 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(toclear, MAX_NR_BANKS); DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); char *msg = "Unknown"; - int lmce = 0; + + /* + * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES + * on Intel. + */ + int lmce = 1; /* If this CPU is offline, just bail out. */ if (cpu_is_offline(smp_processor_id())) { @@ -1051,19 +1101,20 @@ void do_machine_check(struct pt_regs *regs, long error_code) kill_it = 1; /* - * Check if this MCE is signaled to only this logical processor + * Check if this MCE is signaled to only this logical processor, + * on Intel only. */ - if (m.mcgstatus & MCG_STATUS_LMCES) - lmce = 1; - else { - /* - * Go through all the banks in exclusion of the other CPUs. - * This way we don't report duplicated events on shared banks - * because the first one to see it will clear it. - * If this is a Local MCE, then no need to perform rendezvous. - */ + if (m.cpuvendor == X86_VENDOR_INTEL) + lmce = m.mcgstatus & MCG_STATUS_LMCES; + + /* + * Go through all banks in exclusion of the other CPUs. This way we + * don't report duplicated events on shared banks because the first one + * to see it will clear it. If this is a Local MCE, then no need to + * perform rendezvous. + */ + if (!lmce) order = mce_start(&no_way_out); - } for (i = 0; i < cfg->banks; i++) { __clear_bit(i, toclear); @@ -1076,7 +1127,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) m.addr = 0; m.bank = i; - m.status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); + m.status = mce_rdmsrl(msr_ops.status(i)); if ((m.status & MCI_STATUS_VAL) == 0) continue; @@ -1420,7 +1471,6 @@ static void __mcheck_cpu_init_generic(void) enum mcp_flags m_fl = 0; mce_banks_t all_banks; u64 cap; - int i; if (!mca_cfg.bootlog) m_fl = MCP_DONTLOG; @@ -1436,14 +1486,19 @@ static void __mcheck_cpu_init_generic(void) rdmsrl(MSR_IA32_MCG_CAP, cap); if (cap & MCG_CTL_P) wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); +} + +static void __mcheck_cpu_init_clear_banks(void) +{ + int i; for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (!b->init) continue; - wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); - wrmsrl(MSR_IA32_MCx_STATUS(i), 0); + wrmsrl(msr_ops.ctl(i), b->ctl); + wrmsrl(msr_ops.status(i), 0); } } @@ -1495,7 +1550,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) */ clear_bit(10, (unsigned long *)&mce_banks[4].ctl); } - if (c->x86 <= 17 && cfg->bootlog < 0) { + if (c->x86 < 17 && cfg->bootlog < 0) { /* * Lots of broken BIOS around that don't clear them * by default and leave crap in there. Don't log: @@ -1628,11 +1683,19 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) break; case X86_VENDOR_AMD: { - u32 ebx = cpuid_ebx(0x80000007); + mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV); + mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); + mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); - mce_flags.overflow_recov = !!(ebx & BIT(0)); - mce_flags.succor = !!(ebx & BIT(1)); - mce_flags.smca = !!(ebx & BIT(3)); + /* + * Install proper ops for Scalable MCA enabled processors + */ + if (mce_flags.smca) { + msr_ops.ctl = smca_ctl_reg; + msr_ops.status = smca_status_reg; + msr_ops.addr = smca_addr_reg; + msr_ops.misc = smca_misc_reg; + } mce_amd_feature_init(c); break; @@ -1717,6 +1780,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(c); + __mcheck_cpu_init_clear_banks(); __mcheck_cpu_init_timer(); } @@ -2082,7 +2146,7 @@ static void mce_disable_error_reporting(void) struct mce_bank *b = &mce_banks[i]; if (b->init) - wrmsrl(MSR_IA32_MCx_CTL(i), 0); + wrmsrl(msr_ops.ctl(i), 0); } return; } @@ -2121,6 +2185,7 @@ static void mce_syscore_resume(void) { __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info)); + __mcheck_cpu_init_clear_banks(); } static struct syscore_ops mce_syscore_ops = { @@ -2138,6 +2203,7 @@ static void mce_cpu_restart(void *data) if (!mce_available(raw_cpu_ptr(&cpu_info))) return; __mcheck_cpu_init_generic(); + __mcheck_cpu_init_clear_banks(); __mcheck_cpu_init_timer(); } @@ -2413,7 +2479,7 @@ static void mce_reenable_cpu(void *h) struct mce_bank *b = &mce_banks[i]; if (b->init) - wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); + wrmsrl(msr_ops.ctl(i), b->ctl); } } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 9d656fd..10b0661 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -54,14 +54,6 @@ /* Threshold LVT offset is at MSR0xC0000410[15:12] */ #define SMCA_THR_LVT_OFF 0xF000 -/* - * OS is required to set the MCAX bit to acknowledge that it is now using the - * new MSR ranges and new registers under each bank. It also means that the OS - * will configure deferred errors in the new MCx_CONFIG register. If the bit is - * not set, uncorrectable errors will cause a system panic. - */ -#define SMCA_MCAX_EN_OFF 0x1 - static const char * const th_names[] = { "load_store", "insn_fetch", @@ -333,7 +325,7 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high, /* Fall back to method we used for older processors: */ switch (block) { case 0: - addr = MSR_IA32_MCx_MISC(bank); + addr = msr_ops.misc(bank); break; case 1: offset = ((low & MASK_BLKPTR_LO) >> 21); @@ -351,6 +343,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, int offset, u32 misc_high) { unsigned int cpu = smp_processor_id(); + u32 smca_low, smca_high, smca_addr; struct threshold_block b; int new; @@ -369,24 +362,49 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, b.interrupt_enable = 1; - if (mce_flags.smca) { - u32 smca_low, smca_high; - u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); + if (!mce_flags.smca) { + new = (misc_high & MASK_LVTOFF_HI) >> 20; + goto set_offset; + } - if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { - smca_high |= SMCA_MCAX_EN_OFF; - wrmsr(smca_addr, smca_low, smca_high); - } + smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); - /* Gather LVT offset for thresholding: */ - if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) - goto out; + if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { + /* + * OS is required to set the MCAX bit to acknowledge that it is + * now using the new MSR ranges and new registers under each + * bank. It also means that the OS will configure deferred + * errors in the new MCx_CONFIG register. If the bit is not set, + * uncorrectable errors will cause a system panic. + * + * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.) + */ + smca_high |= BIT(0); - new = (smca_low & SMCA_THR_LVT_OFF) >> 12; - } else { - new = (misc_high & MASK_LVTOFF_HI) >> 20; + /* + * SMCA logs Deferred Error information in MCA_DE{STAT,ADDR} + * registers with the option of additionally logging to + * MCA_{STATUS,ADDR} if MCA_CONFIG[LogDeferredInMcaStat] is set. + * + * This bit is usually set by BIOS to retain the old behavior + * for OSes that don't use the new registers. Linux supports the + * new registers so let's disable that additional logging here. + * + * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in the high + * portion of the MSR). + */ + smca_high &= ~BIT(2); + + wrmsr(smca_addr, smca_low, smca_high); } + /* Gather LVT offset for thresholding: */ + if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) + goto out; + + new = (smca_low & SMCA_THR_LVT_OFF) >> 12; + +set_offset: offset = setup_APIC_mce_threshold(offset, new); if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt)) @@ -430,12 +448,23 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) deferred_error_interrupt_enable(c); } -static void __log_error(unsigned int bank, bool threshold_err, u64 misc) +static void +__log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) { + u32 msr_status = msr_ops.status(bank); + u32 msr_addr = msr_ops.addr(bank); struct mce m; u64 status; - rdmsrl(MSR_IA32_MCx_STATUS(bank), status); + WARN_ON_ONCE(deferred_err && threshold_err); + + if (deferred_err && mce_flags.smca) { + msr_status = MSR_AMD64_SMCA_MCx_DESTAT(bank); + msr_addr = MSR_AMD64_SMCA_MCx_DEADDR(bank); + } + + rdmsrl(msr_status, status); + if (!(status & MCI_STATUS_VAL)) return; @@ -448,10 +477,11 @@ static void __log_error(unsigned int bank, bool threshold_err, u64 misc) m.misc = misc; if (m.status & MCI_STATUS_ADDRV) - rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr); + rdmsrl(msr_addr, m.addr); mce_log(&m); - wrmsrl(MSR_IA32_MCx_STATUS(bank), 0); + + wrmsrl(msr_status, 0); } static inline void __smp_deferred_error_interrupt(void) @@ -479,17 +509,21 @@ asmlinkage __visible void smp_trace_deferred_error_interrupt(void) /* APIC interrupt handler for deferred errors */ static void amd_deferred_error_interrupt(void) { - u64 status; unsigned int bank; + u32 msr_status; + u64 status; for (bank = 0; bank < mca_cfg.banks; ++bank) { - rdmsrl(MSR_IA32_MCx_STATUS(bank), status); + msr_status = (mce_flags.smca) ? MSR_AMD64_SMCA_MCx_DESTAT(bank) + : msr_ops.status(bank); + + rdmsrl(msr_status, status); if (!(status & MCI_STATUS_VAL) || !(status & MCI_STATUS_DEFERRED)) continue; - __log_error(bank, false, 0); + __log_error(bank, true, false, 0); break; } } @@ -544,7 +578,7 @@ static void amd_threshold_interrupt(void) return; log: - __log_error(bank, true, ((u64)high << 32) | low); + __log_error(bank, false, true, ((u64)high << 32) | low); } /* diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 1e8bb6c..1defb8e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -84,7 +84,7 @@ static int cmci_supported(int *banks) */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; - if (!cpu_has_apic || lapic_get_maxlvt() < 6) + if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6) return 0; rdmsrl(MSR_IA32_MCG_CAP, cap); *banks = min_t(unsigned, MAX_NR_BANKS, cap & 0xff); diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index ac780ca..6b9dc4d 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -450,7 +450,7 @@ asmlinkage __visible void smp_trace_thermal_interrupt(struct pt_regs *regs) /* Thermal monitoring depends on APIC, ACPI and clock modulation */ static int intel_thermal_supported(struct cpuinfo_x86 *c) { - if (!cpu_has_apic) + if (!boot_cpu_has(X86_FEATURE_APIC)) return 0; if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC)) return 0; diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index f8c81ba..b1086f7 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -137,7 +137,7 @@ static void prepare_set(void) u32 cr0; /* Save value of CR4 and clear Page Global Enable (bit 7) */ - if (cpu_has_pge) { + if (boot_cpu_has(X86_FEATURE_PGE)) { cr4 = __read_cr4(); __write_cr4(cr4 & ~X86_CR4_PGE); } @@ -170,7 +170,7 @@ static void post_set(void) write_cr0(read_cr0() & ~X86_CR0_CD); /* Restore value of CR4 */ - if (cpu_has_pge) + if (boot_cpu_has(X86_FEATURE_PGE)) __write_cr4(cr4); } diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 19f5736..16e37a2 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -444,11 +444,24 @@ static void __init print_mtrr_state(void) pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); } +/* PAT setup for BP. We need to go through sync steps here */ +void __init mtrr_bp_pat_init(void) +{ + unsigned long flags; + + local_irq_save(flags); + prepare_set(); + + pat_init(); + + post_set(); + local_irq_restore(flags); +} + /* Grab all of the MTRR state for this CPU into *state */ bool __init get_mtrr_state(void) { struct mtrr_var_range *vrs; - unsigned long flags; unsigned lo, dummy; unsigned int i; @@ -481,15 +494,6 @@ bool __init get_mtrr_state(void) mtrr_state_set = 1; - /* PAT setup for BP. We need to go through sync steps here */ - local_irq_save(flags); - prepare_set(); - - pat_init(); - - post_set(); - local_irq_restore(flags); - return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED); } @@ -741,7 +745,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) wbinvd(); /* Save value of CR4 and clear Page Global Enable (bit 7) */ - if (cpu_has_pge) { + if (boot_cpu_has(X86_FEATURE_PGE)) { cr4 = __read_cr4(); __write_cr4(cr4 & ~X86_CR4_PGE); } @@ -771,7 +775,7 @@ static void post_set(void) __releases(set_atomicity_lock) write_cr0(read_cr0() & ~X86_CR0_CD); /* Restore value of CR4 */ - if (cpu_has_pge) + if (boot_cpu_has(X86_FEATURE_PGE)) __write_cr4(cr4); raw_spin_unlock(&set_atomicity_lock); } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 10f8d47..7d393ec 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -752,6 +752,9 @@ void __init mtrr_bp_init(void) /* BIOS may override */ __mtrr_enabled = get_mtrr_state(); + if (mtrr_enabled()) + mtrr_bp_pat_init(); + if (mtrr_cleanup(phys_addr)) { changed_by_mtrr_cleanup = 1; mtrr_if->set_all(); @@ -759,8 +762,16 @@ void __init mtrr_bp_init(void) } } - if (!mtrr_enabled()) + if (!mtrr_enabled()) { pr_info("MTRR: Disabled\n"); + + /* + * PAT initialization relies on MTRR's rendezvous handler. + * Skip PAT init until the handler can initialize both + * features independently. + */ + pat_disable("MTRRs disabled, skipping PAT initialization too."); + } } void mtrr_ap_init(void) diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 951884d..6c7ced0 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -52,6 +52,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt); void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); bool get_mtrr_state(void); +void mtrr_bp_pat_init(void); extern void set_mtrr_ops(const struct mtrr_ops *ops); diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 364e583..8cac429 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -94,7 +94,7 @@ static void __init vmware_platform_setup(void) */ static uint32_t __init vmware_platform(void) { - if (cpu_has_hypervisor) { + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { unsigned int eax; unsigned int hyper_vendor_id[3]; diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 1f4acd6..3fe45f8 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -151,7 +151,7 @@ static void __init dtb_lapic_setup(void) return; /* Did the boot loader setup the local APIC ? */ - if (!cpu_has_apic) { + if (!boot_cpu_has(X86_FEATURE_APIC)) { if (apic_force_enable(r.start)) return; } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 8efa57a..2bb25c3 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -260,19 +260,12 @@ int __die(const char *str, struct pt_regs *regs, long err) unsigned long sp; #endif printk(KERN_DEFAULT - "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter); -#ifdef CONFIG_PREEMPT - printk("PREEMPT "); -#endif -#ifdef CONFIG_SMP - printk("SMP "); -#endif - if (debug_pagealloc_enabled()) - printk("DEBUG_PAGEALLOC "); -#ifdef CONFIG_KASAN - printk("KASAN"); -#endif - printk("\n"); + "%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter, + IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", + IS_ENABLED(CONFIG_SMP) ? " SMP" : "", + debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", + IS_ENABLED(CONFIG_KASAN) ? " KASAN" : ""); + if (notify_die(DIE_OOPS, str, regs, err, current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP) return 1; diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/ebda.c index 992f442..afe65df 100644 --- a/arch/x86/kernel/head.c +++ b/arch/x86/kernel/ebda.c @@ -38,7 +38,7 @@ void __init reserve_ebda_region(void) * that the paravirt case can handle memory setup * correctly, without our help. */ - if (paravirt_enabled()) + if (!x86_platform.legacy.ebda_search) return; /* end of low (conventional) memory */ diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c index dd9ca9b6..aad34aa 100644 --- a/arch/x86/kernel/fpu/bugs.c +++ b/arch/x86/kernel/fpu/bugs.c @@ -21,11 +21,15 @@ static double __initdata y = 3145727.0; * We should really only care about bugs here * anyway. Not features. */ -static void __init check_fpu(void) +void __init fpu__init_check_bugs(void) { u32 cr0_saved; s32 fdiv_bug; + /* kernel_fpu_begin/end() relies on patched alternative instructions. */ + if (!boot_cpu_has(X86_FEATURE_FPU)) + return; + /* We might have CR0::TS set already, clear it: */ cr0_saved = read_cr0(); write_cr0(cr0_saved & ~X86_CR0_TS); @@ -59,13 +63,3 @@ static void __init check_fpu(void) pr_warn("Hmm, FPU with FDIV bug\n"); } } - -void __init fpu__init_check_bugs(void) -{ - /* - * kernel_fpu_begin/end() in check_fpu() relies on the patched - * alternative instructions. - */ - if (cpu_has_fpu) - check_fpu(); -} diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 8e37cc8..9702754 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -217,14 +217,14 @@ static inline void fpstate_init_fstate(struct fregs_state *fp) void fpstate_init(union fpregs_state *state) { - if (!cpu_has_fpu) { + if (!static_cpu_has(X86_FEATURE_FPU)) { fpstate_init_soft(&state->soft); return; } memset(state, 0, xstate_size); - if (cpu_has_fxsr) + if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); else fpstate_init_fstate(&state->fsave); @@ -237,7 +237,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) dst_fpu->fpregs_active = 0; dst_fpu->last_cpu = -1; - if (!src_fpu->fpstate_active || !cpu_has_fpu) + if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != ¤t->thread.fpu); @@ -506,33 +506,6 @@ void fpu__clear(struct fpu *fpu) * x87 math exception handling: */ -static inline unsigned short get_fpu_cwd(struct fpu *fpu) -{ - if (cpu_has_fxsr) { - return fpu->state.fxsave.cwd; - } else { - return (unsigned short)fpu->state.fsave.cwd; - } -} - -static inline unsigned short get_fpu_swd(struct fpu *fpu) -{ - if (cpu_has_fxsr) { - return fpu->state.fxsave.swd; - } else { - return (unsigned short)fpu->state.fsave.swd; - } -} - -static inline unsigned short get_fpu_mxcsr(struct fpu *fpu) -{ - if (cpu_has_xmm) { - return fpu->state.fxsave.mxcsr; - } else { - return MXCSR_DEFAULT; - } -} - int fpu__exception_code(struct fpu *fpu, int trap_nr) { int err; @@ -547,10 +520,15 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr) * so if this combination doesn't produce any single exception, * then we have a bad program that isn't synchronizing its FPU usage * and it will suffer the consequences since we won't be able to - * fully reproduce the context of the exception + * fully reproduce the context of the exception. */ - cwd = get_fpu_cwd(fpu); - swd = get_fpu_swd(fpu); + if (boot_cpu_has(X86_FEATURE_FXSR)) { + cwd = fpu->state.fxsave.cwd; + swd = fpu->state.fxsave.swd; + } else { + cwd = (unsigned short)fpu->state.fsave.cwd; + swd = (unsigned short)fpu->state.fsave.swd; + } err = swd & ~cwd; } else { @@ -560,7 +538,11 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr) * unmasked exception was caught we must mask the exception mask bits * at 0x1f80, and then use these to mask the exception bits at 0x3f. */ - unsigned short mxcsr = get_fpu_mxcsr(fpu); + unsigned short mxcsr = MXCSR_DEFAULT; + + if (boot_cpu_has(X86_FEATURE_XMM)) + mxcsr = fpu->state.fxsave.mxcsr; + err = ~(mxcsr >> 7) & mxcsr; } diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 54c86ff..aacfd7a 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -29,22 +29,22 @@ static void fpu__init_cpu_generic(void) unsigned long cr0; unsigned long cr4_mask = 0; - if (cpu_has_fxsr) + if (boot_cpu_has(X86_FEATURE_FXSR)) cr4_mask |= X86_CR4_OSFXSR; - if (cpu_has_xmm) + if (boot_cpu_has(X86_FEATURE_XMM)) cr4_mask |= X86_CR4_OSXMMEXCPT; if (cr4_mask) cr4_set_bits(cr4_mask); cr0 = read_cr0(); cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ - if (!cpu_has_fpu) + if (!boot_cpu_has(X86_FEATURE_FPU)) cr0 |= X86_CR0_EM; write_cr0(cr0); /* Flush out any pending x87 state: */ #ifdef CONFIG_MATH_EMULATION - if (!cpu_has_fpu) + if (!boot_cpu_has(X86_FEATURE_FPU)) fpstate_init_soft(¤t->thread.fpu.state.soft); else #endif @@ -89,7 +89,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) } #ifndef CONFIG_MATH_EMULATION - if (!cpu_has_fpu) { + if (!boot_cpu_has(X86_FEATURE_FPU)) { pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n"); for (;;) asm volatile("hlt"); @@ -106,7 +106,7 @@ static void __init fpu__init_system_mxcsr(void) { unsigned int mask = 0; - if (cpu_has_fxsr) { + if (boot_cpu_has(X86_FEATURE_FXSR)) { /* Static because GCC does not get 16-byte stack alignment right: */ static struct fxregs_state fxregs __initdata; @@ -212,7 +212,7 @@ static void __init fpu__init_system_xstate_size_legacy(void) * fpu__init_system_xstate(). */ - if (!cpu_has_fpu) { + if (!boot_cpu_has(X86_FEATURE_FPU)) { /* * Disable xsave as we do not support it if i387 * emulation is enabled. @@ -221,7 +221,7 @@ static void __init fpu__init_system_xstate_size_legacy(void) setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); xstate_size = sizeof(struct swregs_state); } else { - if (cpu_has_fxsr) + if (boot_cpu_has(X86_FEATURE_FXSR)) xstate_size = sizeof(struct fxregs_state); else xstate_size = sizeof(struct fregs_state); diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 8bd1c00..81422df 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -21,7 +21,10 @@ int regset_xregset_fpregs_active(struct task_struct *target, const struct user_r { struct fpu *target_fpu = &target->thread.fpu; - return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0; + if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active) + return regset->n; + else + return 0; } int xfpregs_get(struct task_struct *target, const struct user_regset *regset, @@ -30,7 +33,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, { struct fpu *fpu = &target->thread.fpu; - if (!cpu_has_fxsr) + if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; fpu__activate_fpstate_read(fpu); @@ -47,7 +50,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; int ret; - if (!cpu_has_fxsr) + if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; fpu__activate_fpstate_write(fpu); @@ -65,7 +68,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, * update the header bits in the xsave header, indicating the * presence of FP and SSE state. */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE; return ret; @@ -79,7 +82,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, struct xregs_state *xsave; int ret; - if (!cpu_has_xsave) + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -ENODEV; fpu__activate_fpstate_read(fpu); @@ -108,7 +111,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, struct xregs_state *xsave; int ret; - if (!cpu_has_xsave) + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -ENODEV; fpu__activate_fpstate_write(fpu); @@ -275,10 +278,10 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, fpu__activate_fpstate_read(fpu); - if (!static_cpu_has(X86_FEATURE_FPU)) + if (!boot_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - if (!cpu_has_fxsr) + if (!boot_cpu_has(X86_FEATURE_FXSR)) return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &fpu->state.fsave, 0, -1); @@ -306,10 +309,10 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, fpu__activate_fpstate_write(fpu); fpstate_sanitize_xstate(fpu); - if (!static_cpu_has(X86_FEATURE_FPU)) + if (!boot_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - if (!cpu_has_fxsr) + if (!boot_cpu_has(X86_FEATURE_FXSR)) return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpu->state.fsave, 0, -1); @@ -325,7 +328,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, * update the header bit in the xsave header, indicating the * presence of FP. */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FP; return ret; } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index b48ef35..4ea2a59 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -190,7 +190,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu) */ void fpu__init_cpu_xstate(void) { - if (!cpu_has_xsave || !xfeatures_mask) + if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask) return; cr4_set_bits(X86_CR4_OSXSAVE); @@ -280,7 +280,7 @@ static void __init setup_xstate_comp(void) xstate_comp_offsets[0] = 0; xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space); - if (!cpu_has_xsaves) { + if (!boot_cpu_has(X86_FEATURE_XSAVES)) { for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { if (xfeature_enabled(i)) { xstate_comp_offsets[i] = xstate_offsets[i]; @@ -316,13 +316,13 @@ static void __init setup_init_fpu_buf(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; - if (!cpu_has_xsave) + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return; setup_xstate_features(); print_xstate_features(); - if (cpu_has_xsaves) { + if (boot_cpu_has(X86_FEATURE_XSAVES)) { init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask; init_fpstate.xsave.header.xfeatures = xfeatures_mask; } @@ -417,7 +417,7 @@ static int xfeature_size(int xfeature_nr) */ static int using_compacted_format(void) { - return cpu_has_xsaves; + return boot_cpu_has(X86_FEATURE_XSAVES); } static void __xstate_dump_leaves(void) @@ -549,7 +549,7 @@ static unsigned int __init calculate_xstate_size(void) unsigned int eax, ebx, ecx, edx; unsigned int calculated_xstate_size; - if (!cpu_has_xsaves) { + if (!boot_cpu_has(X86_FEATURE_XSAVES)) { /* * - CPUID function 0DH, sub-function 0: * EBX enumerates the size (in bytes) required by @@ -630,7 +630,7 @@ void __init fpu__init_system_xstate(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; - if (!cpu_has_xsave) { + if (!boot_cpu_has(X86_FEATURE_XSAVE)) { pr_info("x86/fpu: Legacy x87 FPU detected.\n"); return; } @@ -667,7 +667,7 @@ void __init fpu__init_system_xstate(void) pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", xfeatures_mask, xstate_size, - cpu_has_xsaves ? "compacted" : "standard"); + boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard"); } /* @@ -678,7 +678,7 @@ void fpu__resume_cpu(void) /* * Restore XCR0 on xsave capable CPUs: */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 2911ef3..d784bb5 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -34,6 +34,8 @@ asmlinkage __visible void __init i386_start_kernel(void) cr4_init_shadow(); sanitize_boot_params(&boot_params); + x86_early_init_platform_quirks(); + /* Call the subarch specific early setup function */ switch (boot_params.hdr.hardware_subarch) { case X86_SUBARCH_INTEL_MID: diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 1f4422d..b72fb0b 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -182,6 +182,7 @@ void __init x86_64_start_reservations(char *real_mode_data) if (!boot_params.hdr.version) copy_bootdata(__va(real_mode_data)); + x86_early_init_platform_quirks(); reserve_ebda_region(); switch (boot_params.hdr.hardware_subarch) { diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index af11129..6f8902b 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -555,62 +555,53 @@ early_idt_handler_common: */ cld - cmpl $2,(%esp) # X86_TRAP_NMI - je .Lis_nmi # Ignore NMI - - cmpl $2,%ss:early_recursion_flag - je hlt_loop incl %ss:early_recursion_flag - push %eax # 16(%esp) - push %ecx # 12(%esp) - push %edx # 8(%esp) - push %ds # 4(%esp) - push %es # 0(%esp) - movl $(__KERNEL_DS),%eax - movl %eax,%ds - movl %eax,%es - - cmpl $(__KERNEL_CS),32(%esp) - jne 10f + /* The vector number is in pt_regs->gs */ - leal 28(%esp),%eax # Pointer to %eip - call early_fixup_exception - andl %eax,%eax - jnz ex_entry /* found an exception entry */ - -10: -#ifdef CONFIG_PRINTK - xorl %eax,%eax - movw %ax,2(%esp) /* clean up the segment values on some cpus */ - movw %ax,6(%esp) - movw %ax,34(%esp) - leal 40(%esp),%eax - pushl %eax /* %esp before the exception */ - pushl %ebx - pushl %ebp - pushl %esi - pushl %edi - movl %cr2,%eax - pushl %eax - pushl (20+6*4)(%esp) /* trapno */ - pushl $fault_msg - call printk -#endif - call dump_stack -hlt_loop: - hlt - jmp hlt_loop - -ex_entry: - pop %es - pop %ds - pop %edx - pop %ecx - pop %eax - decl %ss:early_recursion_flag -.Lis_nmi: - addl $8,%esp /* drop vector number and error code */ + cld + pushl %fs /* pt_regs->fs */ + movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ + pushl %es /* pt_regs->es */ + movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ + pushl %ds /* pt_regs->ds */ + movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ + pushl %eax /* pt_regs->ax */ + pushl %ebp /* pt_regs->bp */ + pushl %edi /* pt_regs->di */ + pushl %esi /* pt_regs->si */ + pushl %edx /* pt_regs->dx */ + pushl %ecx /* pt_regs->cx */ + pushl %ebx /* pt_regs->bx */ + + /* Fix up DS and ES */ + movl $(__KERNEL_DS), %ecx + movl %ecx, %ds + movl %ecx, %es + + /* Load the vector number into EDX */ + movl PT_GS(%esp), %edx + + /* Load GS into pt_regs->gs and clear high bits */ + movw %gs, PT_GS(%esp) + movw $0, PT_GS+2(%esp) + + movl %esp, %eax /* args are pt_regs (EAX), trapnr (EDX) */ + call early_fixup_exception + + popl %ebx /* pt_regs->bx */ + popl %ecx /* pt_regs->cx */ + popl %edx /* pt_regs->dx */ + popl %esi /* pt_regs->si */ + popl %edi /* pt_regs->di */ + popl %ebp /* pt_regs->bp */ + popl %eax /* pt_regs->ax */ + popl %ds /* pt_regs->ds */ + popl %es /* pt_regs->es */ + popl %fs /* pt_regs->fs */ + popl %gs /* pt_regs->gs */ + decl %ss:early_recursion_flag + addl $4, %esp /* pop pt_regs->orig_ax */ iret ENDPROC(early_idt_handler_common) @@ -647,10 +638,14 @@ ignore_int: popl %eax #endif iret + +hlt_loop: + hlt + jmp hlt_loop ENDPROC(ignore_int) __INITDATA .align 4 -early_recursion_flag: +GLOBAL(early_recursion_flag) .long 0 __REFDATA @@ -715,19 +710,6 @@ __INITRODATA int_msg: .asciz "Unknown interrupt or fault at: %p %p %p\n" -fault_msg: -/* fault info: */ - .ascii "BUG: Int %d: CR2 %p\n" -/* regs pushed in early_idt_handler: */ - .ascii " EDI %p ESI %p EBP %p EBX %p\n" - .ascii " ESP %p ES %p DS %p\n" - .ascii " EDX %p ECX %p EAX %p\n" -/* fault frame: */ - .ascii " vec %p err %p EIP %p CS %p flg %p\n" - .ascii "Stack: %p %p %p %p %p %p %p %p\n" - .ascii " %p %p %p %p %p %p %p %p\n" - .asciz " %p %p %p %p %p %p %p %p\n" - #include "../../x86/xen/xen-head.S" /* diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 22fbf9d..5df831e 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -20,6 +20,7 @@ #include <asm/processor-flags.h> #include <asm/percpu.h> #include <asm/nops.h> +#include "../entry/calling.h" #ifdef CONFIG_PARAVIRT #include <asm/asm-offsets.h> @@ -64,6 +65,14 @@ startup_64: * tables and then reload them. */ + /* + * Setup stack for verify_cpu(). "-8" because stack_start is defined + * this way, see below. Our best guess is a NULL ptr for stack + * termination heuristics and we don't want to break anything which + * might depend on it (kgdb, ...). + */ + leaq (__end_init_task - 8)(%rip), %rsp + /* Sanitize CPU configuration */ call verify_cpu @@ -350,90 +359,48 @@ early_idt_handler_common: */ cld - cmpl $2,(%rsp) # X86_TRAP_NMI - je .Lis_nmi # Ignore NMI - - cmpl $2,early_recursion_flag(%rip) - jz 1f incl early_recursion_flag(%rip) - pushq %rax # 64(%rsp) - pushq %rcx # 56(%rsp) - pushq %rdx # 48(%rsp) - pushq %rsi # 40(%rsp) - pushq %rdi # 32(%rsp) - pushq %r8 # 24(%rsp) - pushq %r9 # 16(%rsp) - pushq %r10 # 8(%rsp) - pushq %r11 # 0(%rsp) - - cmpl $__KERNEL_CS,96(%rsp) - jne 11f - - cmpl $14,72(%rsp) # Page fault? + /* The vector number is currently in the pt_regs->di slot. */ + pushq %rsi /* pt_regs->si */ + movq 8(%rsp), %rsi /* RSI = vector number */ + movq %rdi, 8(%rsp) /* pt_regs->di = RDI */ + pushq %rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq %rax /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + pushq %r9 /* pt_regs->r9 */ + pushq %r10 /* pt_regs->r10 */ + pushq %r11 /* pt_regs->r11 */ + pushq %rbx /* pt_regs->bx */ + pushq %rbp /* pt_regs->bp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ + + cmpq $14,%rsi /* Page fault? */ jnz 10f - GET_CR2_INTO(%rdi) # can clobber any volatile register if pv + GET_CR2_INTO(%rdi) /* Can clobber any volatile register if pv */ call early_make_pgtable andl %eax,%eax - jz 20f # All good + jz 20f /* All good */ 10: - leaq 88(%rsp),%rdi # Pointer to %rip + movq %rsp,%rdi /* RDI = pt_regs; RSI is already trapnr */ call early_fixup_exception - andl %eax,%eax - jnz 20f # Found an exception entry - -11: -#ifdef CONFIG_EARLY_PRINTK - GET_CR2_INTO(%r9) # can clobber any volatile register if pv - movl 80(%rsp),%r8d # error code - movl 72(%rsp),%esi # vector number - movl 96(%rsp),%edx # %cs - movq 88(%rsp),%rcx # %rip - xorl %eax,%eax - leaq early_idt_msg(%rip),%rdi - call early_printk - cmpl $2,early_recursion_flag(%rip) - jz 1f - call dump_stack -#ifdef CONFIG_KALLSYMS - leaq early_idt_ripmsg(%rip),%rdi - movq 40(%rsp),%rsi # %rip again - call __print_symbol -#endif -#endif /* EARLY_PRINTK */ -1: hlt - jmp 1b - -20: # Exception table entry found or page table generated - popq %r11 - popq %r10 - popq %r9 - popq %r8 - popq %rdi - popq %rsi - popq %rdx - popq %rcx - popq %rax + +20: decl early_recursion_flag(%rip) -.Lis_nmi: - addq $16,%rsp # drop vector number and error code - INTERRUPT_RETURN + jmp restore_regs_and_iret ENDPROC(early_idt_handler_common) __INITDATA .balign 4 -early_recursion_flag: +GLOBAL(early_recursion_flag) .long 0 -#ifdef CONFIG_EARLY_PRINTK -early_idt_msg: - .asciz "PANIC: early exception %02lx rip %lx:%lx error %lx cr2 %lx\n" -early_idt_ripmsg: - .asciz "RIP %s\n" -#endif /* CONFIG_EARLY_PRINTK */ - #define NEXT_PAGE(name) \ .balign PAGE_SIZE; \ GLOBAL(name) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index a1f0e4a..f112af7 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -54,7 +54,7 @@ struct hpet_dev { char name[10]; }; -inline struct hpet_dev *EVT_TO_HPET_DEV(struct clock_event_device *evtdev) +static inline struct hpet_dev *EVT_TO_HPET_DEV(struct clock_event_device *evtdev) { return container_of(evtdev, struct hpet_dev, evt); } @@ -773,7 +773,6 @@ static struct clocksource clocksource_hpet = { .mask = HPET_MASK, .flags = CLOCK_SOURCE_IS_CONTINUOUS, .resume = hpet_resume_counter, - .archdata = { .vclock_mode = VCLOCK_HPET }, }; static int hpet_clocksource_register(void) diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index e565e0e..fc25f69 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -13,6 +13,7 @@ #include <linux/cpu.h> #include <asm/kprobes.h> #include <asm/alternative.h> +#include <asm/text-patching.h> #ifdef HAVE_JUMP_LABEL diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 2da6ee9..04cde52 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -45,6 +45,7 @@ #include <linux/uaccess.h> #include <linux/memory.h> +#include <asm/text-patching.h> #include <asm/debugreg.h> #include <asm/apicdef.h> #include <asm/apic.h> diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index ae703ac..38cf7a7 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -51,6 +51,7 @@ #include <linux/ftrace.h> #include <linux/frame.h> +#include <asm/text-patching.h> #include <asm/cacheflush.h> #include <asm/desc.h> #include <asm/pgtable.h> diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 7b3b9d1..4425f59 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -29,6 +29,7 @@ #include <linux/kallsyms.h> #include <linux/ftrace.h> +#include <asm/text-patching.h> #include <asm/cacheflush.h> #include <asm/desc.h> #include <asm/pgtable.h> diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 8079508..eea2a6f 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -285,14 +285,6 @@ static void __init paravirt_ops_setup(void) { pv_info.name = "KVM"; - /* - * KVM isn't paravirt in the sense of paravirt_enabled. A KVM - * guest kernel works like a bare metal kernel with additional - * features, and paravirt_enabled is about features that are - * missing. - */ - pv_info.paravirt_enabled = 0; - if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY)) pv_cpu_ops.io_delay = kvm_io_delay; @@ -522,7 +514,7 @@ static noinline uint32_t __kvm_cpuid_base(void) if (boot_cpu_data.cpuid_level < 0) return 0; /* So we don't blow up on old processors */ - if (cpu_has_hypervisor) + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0); return 0; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 005c03e..477ae80 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -31,6 +31,7 @@ #include <linux/jump_label.h> #include <linux/random.h> +#include <asm/text-patching.h> #include <asm/page.h> #include <asm/pgtable.h> #include <asm/setup.h> diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index f08ac28..7b3b3f2 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -294,7 +294,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void) struct pv_info pv_info = { .name = "bare hardware", - .paravirt_enabled = 0, .kernel_rpl = 0, .shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */ @@ -339,8 +338,10 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .write_cr8 = native_write_cr8, #endif .wbinvd = native_wbinvd, - .read_msr = native_read_msr_safe, - .write_msr = native_write_msr_safe, + .read_msr = native_read_msr, + .write_msr = native_write_msr, + .read_msr_safe = native_read_msr_safe, + .write_msr_safe = native_write_msr_safe, .read_pmc = native_read_pmc, .load_tr_desc = native_load_tr_desc, .set_ldt = native_set_ldt, diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c index 35ccf75..f712dfd 100644 --- a/arch/x86/kernel/pci-iommu_table.c +++ b/arch/x86/kernel/pci-iommu_table.c @@ -72,7 +72,7 @@ void __init check_iommu_entries(struct iommu_table_entry *start, } } #else -inline void check_iommu_entries(struct iommu_table_entry *start, +void __init check_iommu_entries(struct iommu_table_entry *start, struct iommu_table_entry *finish) { } diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c new file mode 100644 index 0000000..b2f8a33 --- /dev/null +++ b/arch/x86/kernel/platform-quirks.c @@ -0,0 +1,35 @@ +#include <linux/kernel.h> +#include <linux/init.h> + +#include <asm/setup.h> +#include <asm/bios_ebda.h> + +void __init x86_early_init_platform_quirks(void) +{ + x86_platform.legacy.rtc = 1; + x86_platform.legacy.ebda_search = 0; + x86_platform.legacy.devices.pnpbios = 1; + + switch (boot_params.hdr.hardware_subarch) { + case X86_SUBARCH_PC: + x86_platform.legacy.ebda_search = 1; + break; + case X86_SUBARCH_XEN: + case X86_SUBARCH_LGUEST: + case X86_SUBARCH_INTEL_MID: + case X86_SUBARCH_CE4100: + x86_platform.legacy.devices.pnpbios = 0; + x86_platform.legacy.rtc = 0; + break; + } + + if (x86_platform.set_legacy_features) + x86_platform.set_legacy_features(); +} + +#if defined(CONFIG_PNPBIOS) +bool __init arch_pnpbios_disabled(void) +{ + return x86_platform.legacy.devices.pnpbios == 0; +} +#endif diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6cbab31..6b16c36 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -136,25 +136,6 @@ void release_thread(struct task_struct *dead_task) } } -static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr) -{ - struct user_desc ud = { - .base_addr = addr, - .limit = 0xfffff, - .seg_32bit = 1, - .limit_in_pages = 1, - .useable = 1, - }; - struct desc_struct *desc = t->thread.tls_array; - desc += tls; - fill_ldt(desc, &ud); -} - -static inline u32 read_32bit_tls(struct task_struct *t, int tls) -{ - return get_desc_base(&t->thread.tls_array[tls]); -} - int copy_thread_tls(unsigned long clone_flags, unsigned long sp, unsigned long arg, struct task_struct *p, unsigned long tls) { @@ -169,9 +150,9 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); - p->thread.gs = p->thread.gsindex ? 0 : me->thread.gs; + p->thread.gsbase = p->thread.gsindex ? 0 : me->thread.gsbase; savesegment(fs, p->thread.fsindex); - p->thread.fs = p->thread.fsindex ? 0 : me->thread.fs; + p->thread.fsbase = p->thread.fsindex ? 0 : me->thread.fsbase; savesegment(es, p->thread.es); savesegment(ds, p->thread.ds); memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); @@ -210,7 +191,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, */ if (clone_flags & CLONE_SETTLS) { #ifdef CONFIG_IA32_EMULATION - if (is_ia32_task()) + if (in_ia32_syscall()) err = do_set_thread_area(p, -1, (struct user_desc __user *)tls, 0); else @@ -282,7 +263,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); - unsigned fsindex, gsindex; + unsigned prev_fsindex, prev_gsindex; fpu_switch_t fpu_switch; fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); @@ -292,8 +273,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * * (e.g. xen_load_tls()) */ - savesegment(fs, fsindex); - savesegment(gs, gsindex); + savesegment(fs, prev_fsindex); + savesegment(gs, prev_gsindex); /* * Load TLS before restoring any segments so that segment loads @@ -336,66 +317,104 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Switch FS and GS. * * These are even more complicated than DS and ES: they have - * 64-bit bases are that controlled by arch_prctl. Those bases - * only differ from the values in the GDT or LDT if the selector - * is 0. - * - * Loading the segment register resets the hidden base part of - * the register to 0 or the value from the GDT / LDT. If the - * next base address zero, writing 0 to the segment register is - * much faster than using wrmsr to explicitly zero the base. - * - * The thread_struct.fs and thread_struct.gs values are 0 - * if the fs and gs bases respectively are not overridden - * from the values implied by fsindex and gsindex. They - * are nonzero, and store the nonzero base addresses, if - * the bases are overridden. - * - * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should - * be impossible. - * - * Therefore we need to reload the segment registers if either - * the old or new selector is nonzero, and we need to override - * the base address if next thread expects it to be overridden. + * 64-bit bases are that controlled by arch_prctl. The bases + * don't necessarily match the selectors, as user code can do + * any number of things to cause them to be inconsistent. * - * This code is unnecessarily slow in the case where the old and - * new indexes are zero and the new base is nonzero -- it will - * unnecessarily write 0 to the selector before writing the new - * base address. + * We don't promise to preserve the bases if the selectors are + * nonzero. We also don't promise to preserve the base if the + * selector is zero and the base doesn't match whatever was + * most recently passed to ARCH_SET_FS/GS. (If/when the + * FSGSBASE instructions are enabled, we'll need to offer + * stronger guarantees.) * - * Note: This all depends on arch_prctl being the only way that - * user code can override the segment base. Once wrfsbase and - * wrgsbase are enabled, most of this code will need to change. + * As an invariant, + * (fsbase != 0 && fsindex != 0) || (gsbase != 0 && gsindex != 0) is + * impossible. */ - if (unlikely(fsindex | next->fsindex | prev->fs)) { + if (next->fsindex) { + /* Loading a nonzero value into FS sets the index and base. */ loadsegment(fs, next->fsindex); - - /* - * If user code wrote a nonzero value to FS, then it also - * cleared the overridden base address. - * - * XXX: if user code wrote 0 to FS and cleared the base - * address itself, we won't notice and we'll incorrectly - * restore the prior base address next time we reschdule - * the process. - */ - if (fsindex) - prev->fs = 0; + } else { + if (next->fsbase) { + /* Next index is zero but next base is nonzero. */ + if (prev_fsindex) + loadsegment(fs, 0); + wrmsrl(MSR_FS_BASE, next->fsbase); + } else { + /* Next base and index are both zero. */ + if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { + /* + * We don't know the previous base and can't + * find out without RDMSR. Forcibly clear it. + */ + loadsegment(fs, __USER_DS); + loadsegment(fs, 0); + } else { + /* + * If the previous index is zero and ARCH_SET_FS + * didn't change the base, then the base is + * also zero and we don't need to do anything. + */ + if (prev->fsbase || prev_fsindex) + loadsegment(fs, 0); + } + } } - if (next->fs) - wrmsrl(MSR_FS_BASE, next->fs); - prev->fsindex = fsindex; + /* + * Save the old state and preserve the invariant. + * NB: if prev_fsindex == 0, then we can't reliably learn the base + * without RDMSR because Intel user code can zero it without telling + * us and AMD user code can program any 32-bit value without telling + * us. + */ + if (prev_fsindex) + prev->fsbase = 0; + prev->fsindex = prev_fsindex; - if (unlikely(gsindex | next->gsindex | prev->gs)) { + if (next->gsindex) { + /* Loading a nonzero value into GS sets the index and base. */ load_gs_index(next->gsindex); - - /* This works (and fails) the same way as fsindex above. */ - if (gsindex) - prev->gs = 0; + } else { + if (next->gsbase) { + /* Next index is zero but next base is nonzero. */ + if (prev_gsindex) + load_gs_index(0); + wrmsrl(MSR_KERNEL_GS_BASE, next->gsbase); + } else { + /* Next base and index are both zero. */ + if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { + /* + * We don't know the previous base and can't + * find out without RDMSR. Forcibly clear it. + * + * This contains a pointless SWAPGS pair. + * Fixing it would involve an explicit check + * for Xen or a new pvop. + */ + load_gs_index(__USER_DS); + load_gs_index(0); + } else { + /* + * If the previous index is zero and ARCH_SET_GS + * didn't change the base, then the base is + * also zero and we don't need to do anything. + */ + if (prev->gsbase || prev_gsindex) + load_gs_index(0); + } + } } - if (next->gs) - wrmsrl(MSR_KERNEL_GS_BASE, next->gs); - prev->gsindex = gsindex; + /* + * Save the old state and preserve the invariant. + * NB: if prev_gsindex == 0, then we can't reliably learn the base + * without RDMSR because Intel user code can zero it without telling + * us and AMD user code can program any 32-bit value without telling + * us. + */ + if (prev_gsindex) + prev->gsbase = 0; + prev->gsindex = prev_gsindex; switch_fpu_finish(next_fpu, fpu_switch); @@ -516,23 +535,11 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) if (addr >= TASK_SIZE_OF(task)) return -EPERM; cpu = get_cpu(); - /* handle small bases via the GDT because that's faster to - switch. */ - if (addr <= 0xffffffff) { - set_32bit_tls(task, GS_TLS, addr); - if (doit) { - load_TLS(&task->thread, cpu); - load_gs_index(GS_TLS_SEL); - } - task->thread.gsindex = GS_TLS_SEL; - task->thread.gs = 0; - } else { - task->thread.gsindex = 0; - task->thread.gs = addr; - if (doit) { - load_gs_index(0); - ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr); - } + task->thread.gsindex = 0; + task->thread.gsbase = addr; + if (doit) { + load_gs_index(0); + ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr); } put_cpu(); break; @@ -542,52 +549,30 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) if (addr >= TASK_SIZE_OF(task)) return -EPERM; cpu = get_cpu(); - /* handle small bases via the GDT because that's faster to - switch. */ - if (addr <= 0xffffffff) { - set_32bit_tls(task, FS_TLS, addr); - if (doit) { - load_TLS(&task->thread, cpu); - loadsegment(fs, FS_TLS_SEL); - } - task->thread.fsindex = FS_TLS_SEL; - task->thread.fs = 0; - } else { - task->thread.fsindex = 0; - task->thread.fs = addr; - if (doit) { - /* set the selector to 0 to not confuse - __switch_to */ - loadsegment(fs, 0); - ret = wrmsrl_safe(MSR_FS_BASE, addr); - } + task->thread.fsindex = 0; + task->thread.fsbase = addr; + if (doit) { + /* set the selector to 0 to not confuse __switch_to */ + loadsegment(fs, 0); + ret = wrmsrl_safe(MSR_FS_BASE, addr); } put_cpu(); break; case ARCH_GET_FS: { unsigned long base; - if (task->thread.fsindex == FS_TLS_SEL) - base = read_32bit_tls(task, FS_TLS); - else if (doit) + if (doit) rdmsrl(MSR_FS_BASE, base); else - base = task->thread.fs; + base = task->thread.fsbase; ret = put_user(base, (unsigned long __user *)addr); break; } case ARCH_GET_GS: { unsigned long base; - unsigned gsindex; - if (task->thread.gsindex == GS_TLS_SEL) - base = read_32bit_tls(task, GS_TLS); - else if (doit) { - savesegment(gs, gsindex); - if (gsindex) - rdmsrl(MSR_KERNEL_GS_BASE, base); - else - base = task->thread.gs; - } else - base = task->thread.gs; + if (doit) + rdmsrl(MSR_KERNEL_GS_BASE, base); + else + base = task->thread.gsbase; ret = put_user(base, (unsigned long __user *)addr); break; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 32e9d9c..e60ef91 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -303,29 +303,11 @@ static int set_segment_reg(struct task_struct *task, switch (offset) { case offsetof(struct user_regs_struct,fs): - /* - * If this is setting fs as for normal 64-bit use but - * setting fs_base has implicitly changed it, leave it. - */ - if ((value == FS_TLS_SEL && task->thread.fsindex == 0 && - task->thread.fs != 0) || - (value == 0 && task->thread.fsindex == FS_TLS_SEL && - task->thread.fs == 0)) - break; task->thread.fsindex = value; if (task == current) loadsegment(fs, task->thread.fsindex); break; case offsetof(struct user_regs_struct,gs): - /* - * If this is setting gs as for normal 64-bit use but - * setting gs_base has implicitly changed it, leave it. - */ - if ((value == GS_TLS_SEL && task->thread.gsindex == 0 && - task->thread.gs != 0) || - (value == 0 && task->thread.gsindex == GS_TLS_SEL && - task->thread.gs == 0)) - break; task->thread.gsindex = value; if (task == current) load_gs_index(task->thread.gsindex); @@ -417,7 +399,7 @@ static int putreg(struct task_struct *child, * to set either thread.fs or thread.fsindex and the * corresponding GDT slot. */ - if (child->thread.fs != value) + if (child->thread.fsbase != value) return do_arch_prctl(child, ARCH_SET_FS, value); return 0; case offsetof(struct user_regs_struct,gs_base): @@ -426,7 +408,7 @@ static int putreg(struct task_struct *child, */ if (value >= TASK_SIZE_OF(child)) return -EIO; - if (child->thread.gs != value) + if (child->thread.gsbase != value) return do_arch_prctl(child, ARCH_SET_GS, value); return 0; #endif @@ -453,31 +435,17 @@ static unsigned long getreg(struct task_struct *task, unsigned long offset) #ifdef CONFIG_X86_64 case offsetof(struct user_regs_struct, fs_base): { /* - * do_arch_prctl may have used a GDT slot instead of - * the MSR. To userland, it appears the same either - * way, except the %fs segment selector might not be 0. + * XXX: This will not behave as expected if called on + * current or if fsindex != 0. */ - unsigned int seg = task->thread.fsindex; - if (task->thread.fs != 0) - return task->thread.fs; - if (task == current) - asm("movl %%fs,%0" : "=r" (seg)); - if (seg != FS_TLS_SEL) - return 0; - return get_desc_base(&task->thread.tls_array[FS_TLS]); + return task->thread.fsbase; } case offsetof(struct user_regs_struct, gs_base): { /* - * Exactly the same here as the %fs handling above. + * XXX: This will not behave as expected if called on + * current or if fsindex != 0. */ - unsigned int seg = task->thread.gsindex; - if (task->thread.gs != 0) - return task->thread.gs; - if (task == current) - asm("movl %%gs,%0" : "=r" (seg)); - if (seg != GS_TLS_SEL) - return 0; - return get_desc_base(&task->thread.tls_array[GS_TLS]); + return task->thread.gsbase; } #endif } @@ -1266,7 +1234,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { #ifdef CONFIG_X86_X32_ABI - if (!is_ia32_task()) + if (!in_ia32_syscall()) return x32_arch_ptrace(child, request, caddr, cdata); #endif #ifdef CONFIG_IA32_EMULATION diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index ab0adc0..a9b31eb 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -535,6 +535,15 @@ static void native_machine_emergency_restart(void) mode = reboot_mode == REBOOT_WARM ? 0x1234 : 0; *((unsigned short *)__va(0x472)) = mode; + /* + * If an EFI capsule has been registered with the firmware then + * override the reboot= parameter. + */ + if (efi_capsule_pending(NULL)) { + pr_info("EFI capsule is pending, forcing EFI reboot.\n"); + reboot_type = BOOT_EFI; + } + for (;;) { /* Could also try the reset bit in the Hammer NB */ switch (reboot_type) { diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 4af8d06..eceaa08 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -14,6 +14,7 @@ #include <asm/time.h> #include <asm/intel-mid.h> #include <asm/rtc.h> +#include <asm/setup.h> #ifdef CONFIG_X86_32 /* @@ -185,22 +186,7 @@ static __init int add_rtc_cmos(void) } } #endif - if (of_have_populated_dt()) - return 0; - - /* Intel MID platforms don't have ioport rtc */ - if (intel_mid_identify_cpu()) - return -ENODEV; - -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) { - /* This warning can likely go away again in a year or two. */ - pr_info("ACPI: not registering RTC platform device\n"); - return -ENODEV; - } -#endif - - if (paravirt_enabled() && !paravirt_has(RTC)) + if (!x86_platform.legacy.rtc) return -ENODEV; platform_device_register(&rtc_device); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 548ddf7..22cc2f9 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -248,18 +248,17 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, if (config_enabled(CONFIG_X86_64)) sp -= 128; - if (!onsigstack) { - /* This is the X/Open sanctioned signal stack switching. */ - if (ka->sa.sa_flags & SA_ONSTACK) { - if (current->sas_ss_size) - sp = current->sas_ss_sp + current->sas_ss_size; - } else if (config_enabled(CONFIG_X86_32) && - (regs->ss & 0xffff) != __USER_DS && - !(ka->sa.sa_flags & SA_RESTORER) && - ka->sa.sa_restorer) { - /* This is the legacy signal stack switching. */ - sp = (unsigned long) ka->sa.sa_restorer; - } + /* This is the X/Open sanctioned signal stack switching. */ + if (ka->sa.sa_flags & SA_ONSTACK) { + if (sas_ss_flags(sp) == 0) + sp = current->sas_ss_sp + current->sas_ss_size; + } else if (config_enabled(CONFIG_X86_32) && + !onsigstack && + (regs->ss & 0xffff) != __USER_DS && + !(ka->sa.sa_flags & SA_RESTORER) && + ka->sa.sa_restorer) { + /* This is the legacy signal stack switching. */ + sp = (unsigned long) ka->sa.sa_restorer; } if (fpu->fpstate_active) { @@ -391,7 +390,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, put_user_ex(&frame->uc, &frame->puc); /* Create the ucontext. */ - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); else put_user_ex(0, &frame->uc.uc_flags); @@ -442,7 +441,7 @@ static unsigned long frame_uc_flags(struct pt_regs *regs) { unsigned long flags; - if (cpu_has_xsave) + if (boot_cpu_has(X86_FEATURE_XSAVE)) flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS; else flags = UC_SIGCONTEXT_SS; @@ -762,7 +761,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { #ifdef CONFIG_X86_64 - if (is_ia32_task()) + if (in_ia32_syscall()) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index a2065d3..fafe8b9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -332,6 +332,11 @@ static void __init smp_init_package_map(void) * primary cores. */ ncpus = boot_cpu_data.x86_max_cores; + if (!ncpus) { + pr_warn("x86_max_cores == zero !?!?"); + ncpus = 1; + } + __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus); /* @@ -1231,7 +1236,7 @@ static int __init smp_sanity_check(unsigned max_cpus) * If we couldn't find a local APIC, then get out of here now! */ if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) && - !cpu_has_apic) { + !boot_cpu_has(X86_FEATURE_APIC)) { if (!disable_apic) { pr_err("BIOS bug, local APIC #%d not detected!...\n", boot_cpu_physical_apicid); diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index b285d4e..623965e 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -68,6 +68,21 @@ struct efifb_dmi_info efifb_dmi_list[] = { [M_UNKNOWN] = { NULL, 0, 0, 0, 0, OVERRIDE_NONE } }; +void efifb_setup_from_dmi(struct screen_info *si, const char *opt) +{ + int i; + + for (i = 0; i < M_UNKNOWN; i++) { + if (efifb_dmi_list[i].base != 0 && + !strcmp(opt, efifb_dmi_list[i].optname)) { + si->lfb_base = efifb_dmi_list[i].base; + si->lfb_linelength = efifb_dmi_list[i].stride; + si->lfb_width = efifb_dmi_list[i].width; + si->lfb_height = efifb_dmi_list[i].height; + } + } +} + #define choose_value(dmivalue, fwvalue, field, flags) ({ \ typeof(fwvalue) _ret_ = fwvalue; \ if ((flags) & (field)) \ @@ -106,14 +121,24 @@ static int __init efifb_set_system(const struct dmi_system_id *id) continue; for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { resource_size_t start, end; + unsigned long flags; + + flags = pci_resource_flags(dev, i); + if (!(flags & IORESOURCE_MEM)) + continue; + + if (flags & IORESOURCE_UNSET) + continue; + + if (pci_resource_len(dev, i) == 0) + continue; start = pci_resource_start(dev, i); - if (start == 0) - break; end = pci_resource_end(dev, i); if (screen_info.lfb_base >= start && screen_info.lfb_base < end) { found_bar = 1; + break; } } } diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index e72a07f..9b0185f 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -74,12 +74,6 @@ void __init tboot_probe(void) return; } - /* only a natively booted kernel should be using TXT */ - if (paravirt_enabled()) { - pr_warning("non-0 tboot_addr but pv_ops is enabled\n"); - return; - } - /* Map and check for tboot UUID. */ set_fixmap(FIX_TBOOT_BASE, boot_params.tboot_addr); tboot = (struct tboot *)fix_to_virt(FIX_TBOOT_BASE); diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c index ab40954..f386bad 100644 --- a/arch/x86/kernel/tce_64.c +++ b/arch/x86/kernel/tce_64.c @@ -40,7 +40,7 @@ static inline void flush_tce(void* tceaddr) { /* a single tce can't cross a cache line */ - if (cpu_has_clflush) + if (boot_cpu_has(X86_FEATURE_CLFLUSH)) clflush(tceaddr); else wbinvd(); diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 7fc5e84..9692a5e 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -114,6 +114,7 @@ int do_set_thread_area(struct task_struct *p, int idx, int can_allocate) { struct user_desc info; + unsigned short __maybe_unused sel, modified_sel; if (copy_from_user(&info, u_info, sizeof(info))) return -EFAULT; @@ -141,6 +142,47 @@ int do_set_thread_area(struct task_struct *p, int idx, set_tls_desc(p, idx, &info, 1); + /* + * If DS, ES, FS, or GS points to the modified segment, forcibly + * refresh it. Only needed on x86_64 because x86_32 reloads them + * on return to user mode. + */ + modified_sel = (idx << 3) | 3; + + if (p == current) { +#ifdef CONFIG_X86_64 + savesegment(ds, sel); + if (sel == modified_sel) + loadsegment(ds, sel); + + savesegment(es, sel); + if (sel == modified_sel) + loadsegment(es, sel); + + savesegment(fs, sel); + if (sel == modified_sel) + loadsegment(fs, sel); + + savesegment(gs, sel); + if (sel == modified_sel) + load_gs_index(sel); +#endif + +#ifdef CONFIG_X86_32_LAZY_GS + savesegment(gs, sel); + if (sel == modified_sel) + loadsegment(gs, sel); +#endif + } else { +#ifdef CONFIG_X86_64 + if (p->thread.fsindex == modified_sel) + p->thread.fsbase = info.base_addr; + + if (p->thread.gsindex == modified_sel) + p->thread.gsbase = info.base_addr; +#endif + } + return 0; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 06cbe25..d159048 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -51,6 +51,7 @@ #include <asm/processor.h> #include <asm/debugreg.h> #include <linux/atomic.h> +#include <asm/text-patching.h> #include <asm/ftrace.h> #include <asm/traps.h> #include <asm/desc.h> diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index c9c4c7c..38ba6de 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -36,7 +36,7 @@ static int __read_mostly tsc_unstable; /* native_sched_clock() is called before tsc_init(), so we must start with the TSC soft disabled to prevent - erroneous rdtsc usage on !cpu_has_tsc processors */ + erroneous rdtsc usage on !boot_cpu_has(X86_FEATURE_TSC) processors */ static int __read_mostly tsc_disabled = -1; static DEFINE_STATIC_KEY_FALSE(__use_tsc); @@ -834,15 +834,15 @@ int recalibrate_cpu_khz(void) #ifndef CONFIG_SMP unsigned long cpu_khz_old = cpu_khz; - if (cpu_has_tsc) { - tsc_khz = x86_platform.calibrate_tsc(); - cpu_khz = tsc_khz; - cpu_data(0).loops_per_jiffy = - cpufreq_scale(cpu_data(0).loops_per_jiffy, - cpu_khz_old, cpu_khz); - return 0; - } else + if (!boot_cpu_has(X86_FEATURE_TSC)) return -ENODEV; + + tsc_khz = x86_platform.calibrate_tsc(); + cpu_khz = tsc_khz; + cpu_data(0).loops_per_jiffy = cpufreq_scale(cpu_data(0).loops_per_jiffy, + cpu_khz_old, cpu_khz); + + return 0; #else return -ENODEV; #endif @@ -922,9 +922,6 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, struct cpufreq_freqs *freq = data; unsigned long *lpj; - if (cpu_has(&cpu_data(freq->cpu), X86_FEATURE_CONSTANT_TSC)) - return 0; - lpj = &boot_cpu_data.loops_per_jiffy; #ifdef CONFIG_SMP if (!(freq->flags & CPUFREQ_CONST_LOOPS)) @@ -954,9 +951,9 @@ static struct notifier_block time_cpufreq_notifier_block = { .notifier_call = time_cpufreq_notifier }; -static int __init cpufreq_tsc(void) +static int __init cpufreq_register_tsc_scaling(void) { - if (!cpu_has_tsc) + if (!boot_cpu_has(X86_FEATURE_TSC)) return 0; if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) return 0; @@ -965,7 +962,7 @@ static int __init cpufreq_tsc(void) return 0; } -core_initcall(cpufreq_tsc); +core_initcall(cpufreq_register_tsc_scaling); #endif /* CONFIG_CPU_FREQ */ @@ -1081,7 +1078,7 @@ static void __init check_system_tsc_reliable(void) */ int unsynchronized_tsc(void) { - if (!cpu_has_tsc || tsc_unstable) + if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_unstable) return 1; #ifdef CONFIG_SMP @@ -1205,7 +1202,7 @@ out: static int __init init_tsc_clocksource(void) { - if (!cpu_has_tsc || tsc_disabled > 0 || !tsc_khz) + if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz) return 0; if (tsc_clocksource_reliable) @@ -1242,7 +1239,7 @@ void __init tsc_init(void) u64 lpj; int cpu; - if (!cpu_has_tsc) { + if (!boot_cpu_has(X86_FEATURE_TSC)) { setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 92ae6ac..6aa0f4d 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -92,7 +92,7 @@ unsigned long try_msr_calibrate_tsc(void) if (freq_desc_tables[cpu_index].msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); - ratio = (lo >> 8) & 0x1f; + ratio = (lo >> 8) & 0xff; } else { rdmsr(MSR_IA32_PERF_STATUS, lo, hi); ratio = (hi >> 8) & 0x1f; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index bf4db6e..6c1ff31 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -516,7 +516,7 @@ struct uprobe_xol_ops { static inline int sizeof_long(void) { - return is_ia32_task() ? 4 : 8; + return in_ia32_syscall() ? 4 : 8; } static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) @@ -578,7 +578,7 @@ static void default_abort_op(struct arch_uprobe *auprobe, struct pt_regs *regs) riprel_post_xol(auprobe, regs); } -static struct uprobe_xol_ops default_xol_ops = { +static const struct uprobe_xol_ops default_xol_ops = { .pre_xol = default_pre_xol_op, .post_xol = default_post_xol_op, .abort = default_abort_op, @@ -695,7 +695,7 @@ static void branch_clear_offset(struct arch_uprobe *auprobe, struct insn *insn) 0, insn->immediate.nbytes); } -static struct uprobe_xol_ops branch_xol_ops = { +static const struct uprobe_xol_ops branch_xol_ops = { .emulate = branch_emulate_op, .post_xol = branch_post_xol_op, }; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 4c941f8..9297a00 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -334,7 +334,7 @@ SECTIONS __brk_limit = .; } - . = ALIGN(PAGE_SIZE); + . = ALIGN(PAGE_SIZE); /* keep VO_INIT_SIZE page aligned */ _end = .; STABS_DEBUG |