diff options
Diffstat (limited to 'arch/x86/kernel')
39 files changed, 790 insertions, 198 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 1e5eb9f2ff5f..a1e4a6c3f394 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -321,13 +321,12 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e #ifdef CONFIG_X86_IO_APIC #define MP_ISA_BUS 0 +static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity, + u8 trigger, u32 gsi); + static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) { - int ioapic; - int pin; - struct mpc_intsrc mp_irq; - /* * Check bus_irq boundary. */ @@ -337,14 +336,6 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, } /* - * Convert 'gsi' to 'ioapic.pin'. - */ - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return; - pin = mp_find_ioapic_pin(ioapic, gsi); - - /* * TBD: This check is for faulty timer entries, where the override * erroneously sets the trigger to level, resulting in a HUGE * increase of timer interrupts! @@ -352,16 +343,8 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, if ((bus_irq == 0) && (trigger == 3)) trigger = 1; - mp_irq.type = MP_INTSRC; - mp_irq.irqtype = mp_INT; - mp_irq.irqflag = (trigger << 2) | polarity; - mp_irq.srcbus = MP_ISA_BUS; - mp_irq.srcbusirq = bus_irq; /* IRQ */ - mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */ - mp_irq.dstirq = pin; /* INTIN# */ - - mp_save_irq(&mp_irq); - + if (mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi) < 0) + return; /* * Reset default identity mapping if gsi is also an legacy IRQ, * otherwise there will be more than one entry with the same GSI @@ -408,6 +391,34 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, return 0; } +static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity, + u8 trigger, u32 gsi) +{ + struct mpc_intsrc mp_irq; + int ioapic, pin; + + /* Convert 'gsi' to 'ioapic.pin'(INTIN#) */ + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) { + pr_warn("Failed to find ioapic for gsi : %u\n", gsi); + return ioapic; + } + + pin = mp_find_ioapic_pin(ioapic, gsi); + + mp_irq.type = MP_INTSRC; + mp_irq.irqtype = mp_INT; + mp_irq.irqflag = (trigger << 2) | polarity; + mp_irq.srcbus = MP_ISA_BUS; + mp_irq.srcbusirq = bus_irq; + mp_irq.dstapic = mpc_ioapic_id(ioapic); + mp_irq.dstirq = pin; + + mp_save_irq(&mp_irq); + + return 0; +} + static int __init acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end) { @@ -452,7 +463,11 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, if (acpi_sci_flags & ACPI_MADT_POLARITY_MASK) polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK; - mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + if (bus_irq < NR_IRQS_LEGACY) + mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + else + mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi); + acpi_penalize_sci_irq(bus_irq, trigger, polarity); /* diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 25f909362b7a..89829c3d5a74 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -45,17 +45,6 @@ static int __init setup_noreplace_smp(char *str) } __setup("noreplace-smp", setup_noreplace_smp); -#ifdef CONFIG_PARAVIRT -static int __initdata_or_module noreplace_paravirt = 0; - -static int __init setup_noreplace_paravirt(char *str) -{ - noreplace_paravirt = 1; - return 1; -} -__setup("noreplace-paravirt", setup_noreplace_paravirt); -#endif - #define DPRINTK(fmt, args...) \ do { \ if (debug_alternative) \ @@ -339,9 +328,12 @@ done: static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr) { unsigned long flags; + int i; - if (instr[0] != 0x90) - return; + for (i = 0; i < a->padlen; i++) { + if (instr[i] != 0x90) + return; + } local_irq_save(flags); add_nops(instr + (a->instrlen - a->padlen), a->padlen); @@ -584,9 +576,6 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start, struct paravirt_patch_site *p; char insnbuf[MAX_PATCH_LEN]; - if (noreplace_paravirt) - return; - for (p = start; p < end; p++) { unsigned int used; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index fc91c98bee01..fd945099fc95 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2592,8 +2592,8 @@ static struct resource * __init ioapic_setup_resources(void) res[num].flags = IORESOURCE_MEM | IORESOURCE_BUSY; snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i); mem += IOAPIC_RESOURCE_NAME_SIZE; + ioapics[i].iomem_res = &res[num]; num++; - ioapics[i].iomem_res = res; } ioapic_resources = res; diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 0988e204f1e3..592e260ba05b 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -91,8 +91,12 @@ out_data: return NULL; } -static void free_apic_chip_data(struct apic_chip_data *data) +static void free_apic_chip_data(unsigned int virq, struct apic_chip_data *data) { +#ifdef CONFIG_X86_IO_APIC + if (virq < nr_legacy_irqs()) + legacy_irq_data[virq] = NULL; +#endif if (data) { free_cpumask_var(data->domain); free_cpumask_var(data->old_domain); @@ -316,11 +320,7 @@ static void x86_vector_free_irqs(struct irq_domain *domain, apic_data = irq_data->chip_data; irq_domain_reset_irq_data(irq_data); raw_spin_unlock_irqrestore(&vector_lock, flags); - free_apic_chip_data(apic_data); -#ifdef CONFIG_X86_IO_APIC - if (virq + i < nr_legacy_irqs()) - legacy_irq_data[virq + i] = NULL; -#endif + free_apic_chip_data(virq + i, apic_data); } } } @@ -359,14 +359,17 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, irq_data->chip_data = data; irq_data->hwirq = virq + i; err = assign_irq_vector_policy(virq + i, node, data, info); - if (err) + if (err) { + irq_data->chip_data = NULL; + free_apic_chip_data(virq + i, data); goto error; + } } return 0; error: - x86_vector_free_irqs(domain, virq, i + 1); + x86_vector_free_irqs(domain, virq, i); return err; } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 58031303e304..8f184615053b 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -16,13 +16,11 @@ obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += common.o obj-y += rdrand.o obj-y += match.o +obj-y += bugs.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o -obj-$(CONFIG_X86_32) += bugs.o -obj-$(CONFIG_X86_64) += bugs_64.o - obj-$(CONFIG_CPU_SUP_INTEL) += intel.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e2defc7593a4..4bf9e77f3e05 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -746,8 +746,32 @@ static void init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_K8); if (cpu_has_xmm2) { - /* MFENCE stops RDTSC speculation */ - set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + unsigned long long val; + int ret; + + /* + * A serializing LFENCE has less overhead than MFENCE, so + * use it for execution serialization. On families which + * don't have that MSR, LFENCE is already serializing. + * msr_set_bit() uses the safe accessors, too, even if the MSR + * is not present. + */ + msr_set_bit(MSR_F10H_DECFG, + MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + + /* + * Verify that the MSR write was successful (could be running + * under a hypervisor) and only then assume that LFENCE is + * serializing. + */ + ret = rdmsrl_safe(MSR_F10H_DECFG, &val); + if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) { + /* A serializing LFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); + } else { + /* MFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + } } /* diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bd17db15a2c1..2bbc74f8a4a8 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -9,6 +9,11 @@ */ #include <linux/init.h> #include <linux/utsname.h> +#include <linux/cpu.h> +#include <linux/module.h> + +#include <asm/nospec-branch.h> +#include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> @@ -16,15 +21,25 @@ #include <asm/msr.h> #include <asm/paravirt.h> #include <asm/alternative.h> +#include <asm/pgtable.h> +#include <asm/cacheflush.h> +#include <asm/intel-family.h> + +static void __init spectre_v2_select_mitigation(void); void __init check_bugs(void) { identify_boot_cpu(); -#ifndef CONFIG_SMP - pr_info("CPU: "); - print_cpu_info(&boot_cpu_data); -#endif + if (!IS_ENABLED(CONFIG_SMP)) { + pr_info("CPU: "); + print_cpu_info(&boot_cpu_data); + } + + /* Select the proper spectre mitigation before patching alternatives */ + spectre_v2_select_mitigation(); + +#ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. * @@ -40,4 +55,277 @@ void __init check_bugs(void) alternative_instructions(); fpu__init_check_bugs(); +#else /* CONFIG_X86_64 */ + alternative_instructions(); + + /* + * Make sure the first 2MB area is not mapped by huge pages + * There are typically fixed size MTRRs in there and overlapping + * MTRRs into large pages causes slow downs. + * + * Right now we don't do that with gbpages because there seems + * very little benefit for that case. + */ + if (!direct_gbpages) + set_memory_4k((unsigned long)__va(0), 1); +#endif +} + +/* The kernel command line selection */ +enum spectre_v2_mitigation_cmd { + SPECTRE_V2_CMD_NONE, + SPECTRE_V2_CMD_AUTO, + SPECTRE_V2_CMD_FORCE, + SPECTRE_V2_CMD_RETPOLINE, + SPECTRE_V2_CMD_RETPOLINE_GENERIC, + SPECTRE_V2_CMD_RETPOLINE_AMD, +}; + +static const char *spectre_v2_strings[] = { + [SPECTRE_V2_NONE] = "Vulnerable", + [SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline", + [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline", + [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", + [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", +}; + +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V2 : " fmt + +static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; + + +#ifdef RETPOLINE +static bool spectre_v2_bad_module; + +bool retpoline_module_ok(bool has_retpoline) +{ + if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline) + return true; + + pr_err("System may be vulnerable to spectre v2\n"); + spectre_v2_bad_module = true; + return false; +} + +static inline const char *spectre_v2_module_string(void) +{ + return spectre_v2_bad_module ? " - vulnerable module loaded" : ""; +} +#else +static inline const char *spectre_v2_module_string(void) { return ""; } +#endif + +static void __init spec2_print_if_insecure(const char *reason) +{ + if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s selected on command line.\n", reason); +} + +static void __init spec2_print_if_secure(const char *reason) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s selected on command line.\n", reason); +} + +static inline bool retp_compiler(void) +{ + return __is_defined(RETPOLINE); +} + +static inline bool match_option(const char *arg, int arglen, const char *opt) +{ + int len = strlen(opt); + + return len == arglen && !strncmp(arg, opt, len); +} + +static const struct { + const char *option; + enum spectre_v2_mitigation_cmd cmd; + bool secure; +} mitigation_options[] = { + { "off", SPECTRE_V2_CMD_NONE, false }, + { "on", SPECTRE_V2_CMD_FORCE, true }, + { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "auto", SPECTRE_V2_CMD_AUTO, false }, +}; + +static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) +{ + char arg[20]; + int ret, i; + enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; + + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_NONE; + else { + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, + sizeof(arg)); + if (ret < 0) + return SPECTRE_V2_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { + if (!match_option(arg, ret, mitigation_options[i].option)) + continue; + cmd = mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", arg); + return SPECTRE_V2_CMD_AUTO; + } + } + + if ((cmd == SPECTRE_V2_CMD_RETPOLINE || + cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || + cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && + !IS_ENABLED(CONFIG_RETPOLINE)) { + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); + return SPECTRE_V2_CMD_AUTO; + } + + if (mitigation_options[i].secure) + spec2_print_if_secure(mitigation_options[i].option); + else + spec2_print_if_insecure(mitigation_options[i].option); + + return cmd; } + +/* Check for Skylake-like CPUs (for RSB handling) */ +static bool __init is_skylake_era(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + boot_cpu_data.x86 == 6) { + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_SKYLAKE_MOBILE: + case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_KABYLAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_DESKTOP: + return true; + } + } + return false; +} + +static void __init spectre_v2_select_mitigation(void) +{ + enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); + enum spectre_v2_mitigation mode = SPECTRE_V2_NONE; + + /* + * If the CPU is not affected and the command line mode is NONE or AUTO + * then nothing to do. + */ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) && + (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO)) + return; + + switch (cmd) { + case SPECTRE_V2_CMD_NONE: + return; + + case SPECTRE_V2_CMD_FORCE: + case SPECTRE_V2_CMD_AUTO: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; + case SPECTRE_V2_CMD_RETPOLINE_AMD: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_amd; + break; + case SPECTRE_V2_CMD_RETPOLINE_GENERIC: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_generic; + break; + case SPECTRE_V2_CMD_RETPOLINE: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; + } + pr_err("kernel not compiled with retpoline; no mitigation available!"); + return; + +retpoline_auto: + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + retpoline_amd: + if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { + pr_err("LFENCE not serializing. Switching to generic retpoline\n"); + goto retpoline_generic; + } + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : + SPECTRE_V2_RETPOLINE_MINIMAL_AMD; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD); + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } else { + retpoline_generic: + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC : + SPECTRE_V2_RETPOLINE_MINIMAL; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } + + spectre_v2_enabled = mode; + pr_info("%s\n", spectre_v2_strings[mode]); + + /* + * If neither SMEP or KPTI are available, there is a risk of + * hitting userspace addresses in the RSB after a context switch + * from a shallow call stack to a deeper one. To prevent this fill + * the entire RSB, even when using IBRS. + * + * Skylake era CPUs have a separate issue with *underflow* of the + * RSB, when they will predict 'ret' targets from the generic BTB. + * The proper mitigation for this is IBRS. If IBRS is not supported + * or deactivated in favour of retpolines the RSB fill on context + * switch is required. + */ + if ((!boot_cpu_has(X86_FEATURE_KAISER) && + !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { + setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); + pr_info("Filling RSB on context switch\n"); + } +} + +#undef pr_fmt + +#ifdef CONFIG_SYSFS +ssize_t cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + return sprintf(buf, "Not affected\n"); + if (boot_cpu_has(X86_FEATURE_KAISER)) + return sprintf(buf, "Mitigation: PTI\n"); + return sprintf(buf, "Vulnerable\n"); +} + +ssize_t cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) + return sprintf(buf, "Not affected\n"); + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); +} + +ssize_t cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + return sprintf(buf, "Not affected\n"); + + return sprintf(buf, "%s%s\n", spectre_v2_strings[spectre_v2_enabled], + spectre_v2_module_string()); +} +#endif diff --git a/arch/x86/kernel/cpu/bugs_64.c b/arch/x86/kernel/cpu/bugs_64.c deleted file mode 100644 index 04f0fe5af83e..000000000000 --- a/arch/x86/kernel/cpu/bugs_64.c +++ /dev/null @@ -1,33 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * Copyright (C) 2000 SuSE - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <asm/alternative.h> -#include <asm/bugs.h> -#include <asm/processor.h> -#include <asm/mtrr.h> -#include <asm/cacheflush.h> - -void __init check_bugs(void) -{ - identify_boot_cpu(); -#if !defined(CONFIG_SMP) - printk(KERN_INFO "CPU: "); - print_cpu_info(&boot_cpu_data); -#endif - alternative_instructions(); - - /* - * Make sure the first 2MB area is not mapped by huge pages - * There are typically fixed size MTRRs in there and overlapping - * MTRRs into large pages causes slow downs. - * - * Right now we don't do that with gbpages because there seems - * very little benefit for that case. - */ - if (!direct_gbpages) - set_memory_4k((unsigned long)__va(0), 1); -} diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 637ca414d431..8eabbafff213 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -92,7 +92,7 @@ static const struct cpu_dev default_cpu = { static const struct cpu_dev *this_cpu = &default_cpu; -DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { +DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page) = { .gdt = { #ifdef CONFIG_X86_64 /* * We need valid kernel segments for data and code in long mode too @@ -162,6 +162,40 @@ static int __init x86_mpx_setup(char *s) } __setup("nompx", x86_mpx_setup); +#ifdef CONFIG_X86_64 +static int __init x86_pcid_setup(char *s) +{ + /* require an exact match without trailing characters */ + if (strlen(s)) + return 0; + + /* do not emit a message if the feature is not present */ + if (!boot_cpu_has(X86_FEATURE_PCID)) + return 1; + + setup_clear_cpu_cap(X86_FEATURE_PCID); + pr_info("nopcid: PCID feature disabled\n"); + return 1; +} +__setup("nopcid", x86_pcid_setup); +#endif + +static int __init x86_noinvpcid_setup(char *s) +{ + /* noinvpcid doesn't accept parameters */ + if (s) + return -EINVAL; + + /* do not emit a message if the feature is not present */ + if (!boot_cpu_has(X86_FEATURE_INVPCID)) + return 0; + + setup_clear_cpu_cap(X86_FEATURE_INVPCID); + pr_info("noinvpcid: INVPCID feature disabled\n"); + return 0; +} +early_param("noinvpcid", x86_noinvpcid_setup); + #ifdef CONFIG_X86_32 static int cachesize_override = -1; static int disable_x86_serial_nr = 1; @@ -287,6 +321,39 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) } } +static void setup_pcid(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_PCID)) { + if (cpu_has(c, X86_FEATURE_PGE) || kaiser_enabled) { + cr4_set_bits(X86_CR4_PCIDE); + /* + * INVPCID has two "groups" of types: + * 1/2: Invalidate an individual address + * 3/4: Invalidate all contexts + * + * 1/2 take a PCID, but 3/4 do not. So, 3/4 + * ignore the PCID argument in the descriptor. + * But, we have to be careful not to call 1/2 + * with an actual non-zero PCID in them before + * we do the above cr4_set_bits(). + */ + if (cpu_has(c, X86_FEATURE_INVPCID)) + set_cpu_cap(c, X86_FEATURE_INVPCID_SINGLE); + } else { + /* + * flush_tlb_all(), as currently implemented, won't + * work if PCID is on but PGE is not. Since that + * combination doesn't exist on real hardware, there's + * no reason to try to fully support it, but it's + * polite to avoid corrupting data if we're on + * an improperly configured VM. + */ + clear_cpu_cap(c, X86_FEATURE_PCID); + } + } + kaiser_setup_pcid(); +} + /* * Some CPU features depend on higher CPUID levels, which may not always * be available due to CPUID level capping or broken virtualization @@ -365,8 +432,8 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c) return NULL; /* Not found */ } -__u32 cpu_caps_cleared[NCAPINTS]; -__u32 cpu_caps_set[NCAPINTS]; +__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +__u32 cpu_caps_set[NCAPINTS + NBUGINTS]; void load_percpu_segment(int cpu) { @@ -597,6 +664,16 @@ void cpu_detect(struct cpuinfo_x86 *c) } } +static void apply_forced_caps(struct cpuinfo_x86 *c) +{ + int i; + + for (i = 0; i < NCAPINTS + NBUGINTS; i++) { + c->x86_capability[i] &= ~cpu_caps_cleared[i]; + c->x86_capability[i] |= cpu_caps_set[i]; + } +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 tfms, xlvl; @@ -753,7 +830,22 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) } setup_force_cpu_cap(X86_FEATURE_ALWAYS); + + if (c->x86_vendor != X86_VENDOR_AMD) + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + fpu__init_system(c); + +#ifdef CONFIG_X86_32 + /* + * Regardless of whether PCID is enumerated, the SDM says + * that it can't be enabled in 32-bit mode. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); +#endif } void __init early_cpu_init(void) @@ -863,7 +955,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) int i; c->loops_per_jiffy = loops_per_jiffy; - c->x86_cache_size = -1; + c->x86_cache_size = 0; c->x86_vendor = X86_VENDOR_UNKNOWN; c->x86_model = c->x86_mask = 0; /* So far unknown... */ c->x86_vendor_id[0] = '\0'; /* Unset */ @@ -888,11 +980,8 @@ static void identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_identify) this_cpu->c_identify(c); - /* Clear/Set all flags overriden by options, after probe */ - for (i = 0; i < NCAPINTS; i++) { - c->x86_capability[i] &= ~cpu_caps_cleared[i]; - c->x86_capability[i] |= cpu_caps_set[i]; - } + /* Clear/Set all flags overridden by options, after probe */ + apply_forced_caps(c); #ifdef CONFIG_X86_64 c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); @@ -918,6 +1007,9 @@ static void identify_cpu(struct cpuinfo_x86 *c) setup_smep(c); setup_smap(c); + /* Set up PCID */ + setup_pcid(c); + /* * The vendor-specific functions might have changed features. * Now we do "generic changes." @@ -950,10 +1042,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) * Clear/Set all flags overriden by options, need do it * before following smp all cpus cap AND. */ - for (i = 0; i < NCAPINTS; i++) { - c->x86_capability[i] &= ~cpu_caps_cleared[i]; - c->x86_capability[i] |= cpu_caps_set[i]; - } + apply_forced_caps(c); /* * On SMP, boot_cpu_data holds the common feature set between @@ -1173,7 +1262,7 @@ static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { [DEBUG_STACK - 1] = DEBUG_STKSZ }; -static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks +DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(char, exception_stacks [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); /* May not be marked __init: used by software suspend */ @@ -1336,6 +1425,14 @@ void cpu_init(void) * try to read it. */ cr4_init_shadow(); + if (!kaiser_enabled) { + /* + * secondary_startup_64() deferred setting PGE in cr4: + * probe_page_size_mask() sets it on the boot cpu, + * but it needs to be set on each secondary cpu. + */ + cr4_set_bits(X86_CR4_PGE); + } /* * Load microcode on this cpu if a valid microcode is available. diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index e38d338a6447..b4ca91cf55b0 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -934,6 +934,8 @@ static int __populate_cache_leaves(unsigned int cpu) ci_leaf_init(this_leaf++, &id4_regs); __cache_cpumap_setup(cpu, idx, &id4_regs); } + this_cpu_ci->cpu_map_populated = true; + return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 4cfba4371a71..101bfae369e1 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -152,7 +152,6 @@ static void raise_mce(struct mce *m) if (context == MCJ_CTX_RANDOM) return; -#ifdef CONFIG_X86_LOCAL_APIC if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) { unsigned long start; int cpu; @@ -193,9 +192,7 @@ static void raise_mce(struct mce *m) raise_local(); put_cpu(); put_online_cpus(); - } else -#endif - { + } else { preempt_disable(); raise_local(); preempt_enable(); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 7e8a736d09db..364fbad72e60 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1672,6 +1672,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code) void (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check; +dotraplinkage void do_mce(struct pt_regs *regs, long error_code) +{ + machine_check_vector(regs, error_code); +} + /* * Called for each booted CPU to set up machine checks. * Must be called with preempt off: diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 2233f8a76615..6da6f9cd6d2d 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -131,6 +131,9 @@ static size_t compute_container_size(u8 *data, u32 total_size) return size; } +static enum ucode_state +load_microcode_amd(bool save, u8 family, const u8 *data, size_t size); + /* * Early load occurs before we can vmalloc(). So we look for the microcode * patch container file in initrd, traverse equivalent cpu table, look for a @@ -438,7 +441,7 @@ int __init save_microcode_in_initrd_amd(void) eax = cpuid_eax(0x00000001); eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); - ret = load_microcode_amd(smp_processor_id(), eax, container, container_size); + ret = load_microcode_amd(true, eax, container, container_size); if (ret != UCODE_OK) retval = -EINVAL; @@ -580,6 +583,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, #define F14H_MPB_MAX_SIZE 1824 #define F15H_MPB_MAX_SIZE 4096 #define F16H_MPB_MAX_SIZE 3458 +#define F17H_MPB_MAX_SIZE 3200 switch (family) { case 0x14: @@ -591,6 +595,9 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, case 0x16: max_size = F16H_MPB_MAX_SIZE; break; + case 0x17: + max_size = F17H_MPB_MAX_SIZE; + break; default: max_size = F1XH_MPB_MAX_SIZE; break; @@ -850,7 +857,8 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, return UCODE_OK; } -enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size) +static enum ucode_state +load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) { enum ucode_state ret; @@ -864,8 +872,8 @@ enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t s #ifdef CONFIG_X86_32 /* save BSP's matching patch for early load */ - if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) { - struct ucode_patch *p = find_patch(cpu); + if (save) { + struct ucode_patch *p = find_patch(0); if (p) { memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), @@ -897,11 +905,12 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, { char fw_name[36] = "amd-ucode/microcode_amd.bin"; struct cpuinfo_x86 *c = &cpu_data(cpu); + bool bsp = c->cpu_index == boot_cpu_data.cpu_index; enum ucode_state ret = UCODE_NFOUND; const struct firmware *fw; /* reload ucode container only on the boot cpu */ - if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index) + if (!refresh_fw || !bsp) return UCODE_OK; if (c->x86 >= 0x15) @@ -918,7 +927,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, goto fw_release; } - ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size); + ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size); fw_release: release_firmware(fw); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index b3e94ef461fd..ce5f8a2e7ae6 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -44,7 +44,7 @@ static struct microcode_ops *microcode_ops; -static bool dis_ucode_ldr; +static bool dis_ucode_ldr = true; static int __init disable_loader(char *str) { @@ -81,6 +81,7 @@ struct cpu_info_ctx { static bool __init check_loader_disabled_bsp(void) { + u32 a, b, c, d; #ifdef CONFIG_X86_32 const char *cmdline = (const char *)__pa_nodebug(boot_command_line); const char *opt = "dis_ucode_ldr"; @@ -93,8 +94,20 @@ static bool __init check_loader_disabled_bsp(void) bool *res = &dis_ucode_ldr; #endif - if (cmdline_find_option_bool(cmdline, option)) - *res = true; + a = 1; + c = 0; + native_cpuid(&a, &b, &c, &d); + + /* + * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not + * completely accurate as xen pv guests don't see that CPUID bit set but + * that's good enough as they don't land on the BSP path anyway. + */ + if (c & BIT(31)) + return *res; + + if (cmdline_find_option_bool(cmdline, option) <= 0) + *res = false; return *res; } @@ -122,9 +135,7 @@ void __init load_ucode_bsp(void) { int vendor; unsigned int family; - - if (check_loader_disabled_bsp()) - return; + bool intel = true; if (!have_cpuid_p()) return; @@ -134,16 +145,27 @@ void __init load_ucode_bsp(void) switch (vendor) { case X86_VENDOR_INTEL: - if (family >= 6) - load_ucode_intel_bsp(); + if (family < 6) + return; break; + case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_bsp(family); + if (family < 0x10) + return; + intel = false; break; + default: - break; + return; } + + if (check_loader_disabled_bsp()) + return; + + if (intel) + load_ucode_intel_bsp(); + else + load_ucode_amd_bsp(family); } static bool check_loader_disabled_ap(void) @@ -162,9 +184,6 @@ void load_ucode_ap(void) if (check_loader_disabled_ap()) return; - if (!have_cpuid_p()) - return; - vendor = x86_vendor(); family = x86_family(); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index abf581ade8d2..2f38a99cdb98 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -39,6 +39,9 @@ #include <asm/setup.h> #include <asm/msr.h> +/* last level cache size per core */ +static int llc_size_per_core; + static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; static struct mc_saved_data { unsigned int mc_saved_count; @@ -994,8 +997,19 @@ static bool is_blacklisted(unsigned int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); - if (c->x86 == 6 && c->x86_model == 79) { - pr_err_once("late loading on model 79 is disabled.\n"); + /* + * Late loading on model 79 with microcode revision less than 0x0b000021 + * and LLC size per core bigger than 2.5MB may result in a system hang. + * This behavior is documented in item BDF90, #334165 (Intel Xeon + * Processor E7-8800/4800 v4 Product Family). + */ + if (c->x86 == 6 && + c->x86_model == 79 && + c->x86_mask == 0x01 && + llc_size_per_core > 2621440 && + c->microcode < 0x0b000021) { + pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); + pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); return true; } @@ -1059,6 +1073,15 @@ static struct microcode_ops microcode_intel_ops = { .microcode_fini_cpu = microcode_fini_cpu, }; +static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) +{ + u64 llc_size = c->x86_cache_size * 1024ULL; + + do_div(llc_size, c->x86_max_cores); + + return (int)llc_size; +} + struct microcode_ops * __init init_intel_microcode(void) { struct cpuinfo_x86 *c = &boot_cpu_data; @@ -1069,6 +1092,8 @@ struct microcode_ops * __init init_intel_microcode(void) return NULL; } + llc_size_per_core = calc_llc_size_per_core(c); + return µcode_intel_ops; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 5b2f2306fbcc..b52a8d08ab36 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -188,8 +188,8 @@ static void release_pmc_hardware(void) {} static bool check_hw_exists(void) { - u64 val, val_fail, val_new= ~0; - int i, reg, reg_fail, ret = 0; + u64 val, val_fail = -1, val_new= ~0; + int i, reg, reg_fail = -1, ret = 0; int bios_fail = 0; int reg_safe = -1; diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c index 2cad71d1b14c..5af11c46d0b9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_bts.c +++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c @@ -22,6 +22,7 @@ #include <linux/debugfs.h> #include <linux/device.h> #include <linux/coredump.h> +#include <linux/kaiser.h> #include <asm-generic/sizes.h> #include <asm/perf_event.h> @@ -67,6 +68,23 @@ static size_t buf_size(struct page *page) return 1 << (PAGE_SHIFT + page_private(page)); } +static void bts_buffer_free_aux(void *data) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + struct bts_buffer *buf = data; + int nbuf; + + for (nbuf = 0; nbuf < buf->nr_bufs; nbuf++) { + struct page *page = buf->buf[nbuf].page; + void *kaddr = page_address(page); + size_t page_size = buf_size(page); + + kaiser_remove_mapping((unsigned long)kaddr, page_size); + } +#endif + kfree(data); +} + static void * bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite) { @@ -103,29 +121,33 @@ bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite) buf->real_size = size - size % BTS_RECORD_SIZE; for (pg = 0, nbuf = 0, offset = 0, pad = 0; nbuf < buf->nr_bufs; nbuf++) { - unsigned int __nr_pages; + void *kaddr = pages[pg]; + size_t page_size; + + page = virt_to_page(kaddr); + page_size = buf_size(page); + + if (kaiser_add_mapping((unsigned long)kaddr, + page_size, __PAGE_KERNEL) < 0) { + buf->nr_bufs = nbuf; + bts_buffer_free_aux(buf); + return NULL; + } - page = virt_to_page(pages[pg]); - __nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1; buf->buf[nbuf].page = page; buf->buf[nbuf].offset = offset; buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0); - buf->buf[nbuf].size = buf_size(page) - buf->buf[nbuf].displacement; + buf->buf[nbuf].size = page_size - buf->buf[nbuf].displacement; pad = buf->buf[nbuf].size % BTS_RECORD_SIZE; buf->buf[nbuf].size -= pad; - pg += __nr_pages; - offset += __nr_pages << PAGE_SHIFT; + pg += page_size >> PAGE_SHIFT; + offset += page_size; } return buf; } -static void bts_buffer_free_aux(void *data) -{ - kfree(data); -} - static unsigned long bts_buffer_offset(struct bts_buffer *buf, unsigned int idx) { return buf->buf[idx].offset + buf->buf[idx].displacement; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 1e7de3cefc9c..f01b3a12dce0 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -2,11 +2,15 @@ #include <linux/types.h> #include <linux/slab.h> +#include <asm/kaiser.h> #include <asm/perf_event.h> #include <asm/insn.h> #include "perf_event.h" +static +DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct debug_store, cpu_debug_store); + /* The size of a BTS record in bytes: */ #define BTS_RECORD_SIZE 24 @@ -268,6 +272,39 @@ void fini_debug_store_on_cpu(int cpu) static DEFINE_PER_CPU(void *, insn_buffer); +static void *dsalloc(size_t size, gfp_t flags, int node) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + unsigned int order = get_order(size); + struct page *page; + unsigned long addr; + + page = __alloc_pages_node(node, flags | __GFP_ZERO, order); + if (!page) + return NULL; + addr = (unsigned long)page_address(page); + if (kaiser_add_mapping(addr, size, __PAGE_KERNEL) < 0) { + __free_pages(page, order); + addr = 0; + } + return (void *)addr; +#else + return kmalloc_node(size, flags | __GFP_ZERO, node); +#endif +} + +static void dsfree(const void *buffer, size_t size) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + if (!buffer) + return; + kaiser_remove_mapping((unsigned long)buffer, size); + free_pages((unsigned long)buffer, get_order(size)); +#else + kfree(buffer); +#endif +} + static int alloc_pebs_buffer(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -278,7 +315,7 @@ static int alloc_pebs_buffer(int cpu) if (!x86_pmu.pebs) return 0; - buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); + buffer = dsalloc(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -289,7 +326,7 @@ static int alloc_pebs_buffer(int cpu) if (x86_pmu.intel_cap.pebs_format < 2) { ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node); if (!ibuffer) { - kfree(buffer); + dsfree(buffer, x86_pmu.pebs_buffer_size); return -ENOMEM; } per_cpu(insn_buffer, cpu) = ibuffer; @@ -315,7 +352,8 @@ static void release_pebs_buffer(int cpu) kfree(per_cpu(insn_buffer, cpu)); per_cpu(insn_buffer, cpu) = NULL; - kfree((void *)(unsigned long)ds->pebs_buffer_base); + dsfree((void *)(unsigned long)ds->pebs_buffer_base, + x86_pmu.pebs_buffer_size); ds->pebs_buffer_base = 0; } @@ -329,7 +367,7 @@ static int alloc_bts_buffer(int cpu) if (!x86_pmu.bts) return 0; - buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node); + buffer = dsalloc(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node); if (unlikely(!buffer)) { WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__); return -ENOMEM; @@ -355,19 +393,15 @@ static void release_bts_buffer(int cpu) if (!ds || !x86_pmu.bts) return; - kfree((void *)(unsigned long)ds->bts_buffer_base); + dsfree((void *)(unsigned long)ds->bts_buffer_base, BTS_BUFFER_SIZE); ds->bts_buffer_base = 0; } static int alloc_ds_buffer(int cpu) { - int node = cpu_to_node(cpu); - struct debug_store *ds; - - ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node); - if (unlikely(!ds)) - return -ENOMEM; + struct debug_store *ds = per_cpu_ptr(&cpu_debug_store, cpu); + memset(ds, 0, sizeof(*ds)); per_cpu(cpu_hw_events, cpu).ds = ds; return 0; @@ -381,7 +415,6 @@ static void release_ds_buffer(int cpu) return; per_cpu(cpu_hw_events, cpu).ds = NULL; - kfree(ds); } void release_ds_buffers(void) diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 18ca99f2798b..935225c0375f 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -87,8 +87,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) } /* Cache size */ - if (c->x86_cache_size >= 0) - seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); + if (c->x86_cache_size) + seq_printf(m, "cache size\t: %u KB\n", c->x86_cache_size); show_cpuinfo_core(m, c, cpu); show_cpuinfo_misc(m, c); diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 4d38416e2a7f..b02cb2ec6726 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -41,6 +41,7 @@ #include <asm/pgalloc.h> #include <asm/setup.h> #include <asm/espfix.h> +#include <asm/kaiser.h> /* * Note: we only need 6*8 = 48 bytes for the espfix stack, but round @@ -126,6 +127,15 @@ void __init init_espfix_bsp(void) /* Install the espfix pud into the kernel page directory */ pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); + /* + * Just copy the top-level PGD that is mapping the espfix + * area to ensure it is mapped into the shadow user page + * tables. + */ + if (kaiser_enabled) { + set_pgd(native_get_shadow_pgd(pgd_p), + __pgd(_KERNPG_TABLE | __pa((pud_t *)espfix_pud_page))); + } /* Randomize the locations */ init_espfix_random(); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 8f1a3f443f7d..70284d38fdc2 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -669,14 +669,17 @@ __PAGE_ALIGNED_BSS initial_pg_pmd: .fill 1024*KPMDS,4,0 #else -ENTRY(initial_page_table) +.globl initial_page_table +initial_page_table: .fill 1024,4,0 #endif initial_pg_fixmap: .fill 1024,4,0 -ENTRY(empty_zero_page) +.globl empty_zero_page +empty_zero_page: .fill 4096,1,0 -ENTRY(swapper_pg_dir) +.globl swapper_pg_dir +swapper_pg_dir: .fill 1024,4,0 /* diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ffdc0e860390..4034e905741a 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -183,8 +183,8 @@ ENTRY(secondary_startup_64) movq $(init_level4_pgt - __START_KERNEL_map), %rax 1: - /* Enable PAE mode and PGE */ - movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx + /* Enable PAE and PSE, but defer PGE until kaiser_enabled is decided */ + movl $(X86_CR4_PAE | X86_CR4_PSE), %ecx movq %rcx, %cr4 /* Setup early boot stage 4 level pagetables. */ @@ -441,6 +441,27 @@ early_idt_ripmsg: .balign PAGE_SIZE; \ GLOBAL(name) +#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * Each PGD needs to be 8k long and 8k aligned. We do not + * ever go out to userspace with these, so we do not + * strictly *need* the second page, but this allows us to + * have a single set_pgd() implementation that does not + * need to worry about whether it has 4k or 8k to work + * with. + * + * This ensures PGDs are 8k long: + */ +#define KAISER_USER_PGD_FILL 512 +/* This ensures they are 8k-aligned: */ +#define NEXT_PGD_PAGE(name) \ + .balign 2 * PAGE_SIZE; \ +GLOBAL(name) +#else +#define NEXT_PGD_PAGE(name) NEXT_PAGE(name) +#define KAISER_USER_PGD_FILL 0 +#endif + /* Automate the creation of 1 to 1 mapping pmd entries */ #define PMDS(START, PERM, COUNT) \ i = 0 ; \ @@ -450,9 +471,10 @@ GLOBAL(name) .endr __INITDATA -NEXT_PAGE(early_level4_pgt) +NEXT_PGD_PAGE(early_level4_pgt) .fill 511,8,0 .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .fill KAISER_USER_PGD_FILL,8,0 NEXT_PAGE(early_dynamic_pgts) .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0 @@ -460,16 +482,18 @@ NEXT_PAGE(early_dynamic_pgts) .data #ifndef CONFIG_XEN -NEXT_PAGE(init_level4_pgt) +NEXT_PGD_PAGE(init_level4_pgt) .fill 512,8,0 + .fill KAISER_USER_PGD_FILL,8,0 #else -NEXT_PAGE(init_level4_pgt) +NEXT_PGD_PAGE(init_level4_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE .org init_level4_pgt + L4_PAGE_OFFSET*8, 0 .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE .org init_level4_pgt + L4_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .fill KAISER_USER_PGD_FILL,8,0 NEXT_PAGE(level3_ident_pgt) .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE @@ -480,6 +504,7 @@ NEXT_PAGE(level2_ident_pgt) */ PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) #endif + .fill KAISER_USER_PGD_FILL,8,0 NEXT_PAGE(level3_kernel_pgt) .fill L3_START_KERNEL,8,0 diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 61521dc19c10..9f669fdd2010 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -102,8 +102,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_puts(p, " Rescheduling interrupts\n"); seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->irq_call_count - - irq_stats(j)->irq_tlb_count); + seq_printf(p, "%10u ", irq_stats(j)->irq_call_count); seq_puts(p, " Function call interrupts\n"); seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 38da8f29a9c8..528b7aa1780d 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -20,6 +20,7 @@ #include <linux/mm.h> #include <asm/apic.h> +#include <asm/nospec-branch.h> #ifdef CONFIG_DEBUG_STACKOVERFLOW @@ -55,17 +56,17 @@ DEFINE_PER_CPU(struct irq_stack *, softirq_stack); static void call_on_stack(void *func, void *stack) { asm volatile("xchgl %%ebx,%%esp \n" - "call *%%edi \n" + CALL_NOSPEC "movl %%ebx,%%esp \n" : "=b" (stack) : "0" (stack), - "D"(func) + [thunk_target] "D"(func) : "memory", "cc", "edx", "ecx", "eax"); } static inline void *current_stack(void) { - return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); + return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1)); } static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) @@ -89,17 +90,17 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) /* Save the next esp at the bottom of the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); asm volatile("xchgl %%ebx,%%esp \n" - "call *%%edi \n" + CALL_NOSPEC "movl %%ebx,%%esp \n" : "=a" (arg1), "=b" (isp) : "0" (desc), "1" (isp), - "D" (desc->handle_irq) + [thunk_target] "D" (desc->handle_irq) : "memory", "cc", "ecx"); return 1; } @@ -142,7 +143,7 @@ void do_softirq_own_stack(void) /* Push the previous esp onto the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; call_on_stack(__do_softirq, isp); } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 1423ab1b0312..f480b38a03c3 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -51,7 +51,7 @@ static struct irqaction irq2 = { .flags = IRQF_NO_THREAD, }; -DEFINE_PER_CPU(vector_irq_t, vector_irq) = { +DEFINE_PER_CPU_USER_MAPPED(vector_irq_t, vector_irq) = { [0 ... NR_VECTORS - 1] = VECTOR_UNUSED, }; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index c9d488f3e4cd..ea8e2b846101 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -36,6 +36,7 @@ #include <asm/alternative.h> #include <asm/insn.h> #include <asm/debugreg.h> +#include <asm/nospec-branch.h> #include "common.h" @@ -191,7 +192,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src) } /* Check whether insn is indirect jump */ -static int insn_is_indirect_jump(struct insn *insn) +static int __insn_is_indirect_jump(struct insn *insn) { return ((insn->opcode.bytes[0] == 0xff && (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ @@ -225,6 +226,26 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) return (start <= target && target <= start + len); } +static int insn_is_indirect_jump(struct insn *insn) +{ + int ret = __insn_is_indirect_jump(insn); + +#ifdef CONFIG_RETPOLINE + /* + * Jump to x86_indirect_thunk_* is treated as an indirect jump. + * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with + * older gcc may use indirect jump. So we add this check instead of + * replace indirect-jump check. + */ + if (!ret) + ret = insn_jump_into_range(insn, + (unsigned long)__indirect_thunk_start, + (unsigned long)__indirect_thunk_end - + (unsigned long)__indirect_thunk_start); +#endif + return ret; +} + /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 2bd81e302427..ec1b06dc82d2 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -45,6 +45,11 @@ early_param("no-kvmclock", parse_no_kvmclock); static struct pvclock_vsyscall_time_info *hv_clock; static struct pvclock_wall_clock wall_clock; +struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) +{ + return hv_clock; +} + /* * The wallclock is the time of day when we booted. Since then, some time may * have elapsed since the hypervisor wrote the data. So we try to account for diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index d6279593bcdd..bc429365b72a 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> +#include <linux/kaiser.h> #include <asm/ldt.h> #include <asm/desc.h> @@ -34,11 +35,21 @@ static void flush_ldt(void *current_mm) set_ldt(pc->ldt->entries, pc->ldt->size); } +static void __free_ldt_struct(struct ldt_struct *ldt) +{ + if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(ldt->entries); + else + free_page((unsigned long)ldt->entries); + kfree(ldt); +} + /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ static struct ldt_struct *alloc_ldt_struct(int size) { struct ldt_struct *new_ldt; int alloc_size; + int ret; if (size > LDT_ENTRIES) return NULL; @@ -66,7 +77,13 @@ static struct ldt_struct *alloc_ldt_struct(int size) return NULL; } + ret = kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size, + __PAGE_KERNEL); new_ldt->size = size; + if (ret) { + __free_ldt_struct(new_ldt); + return NULL; + } return new_ldt; } @@ -92,12 +109,10 @@ static void free_ldt_struct(struct ldt_struct *ldt) if (likely(!ldt)) return; + kaiser_remove_mapping((unsigned long)ldt->entries, + ldt->size * LDT_ENTRY_SIZE); paravirt_free_ldt(ldt->entries, ldt->size); - if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(ldt->entries); - else - free_page((unsigned long)ldt->entries); - kfree(ldt); + __free_ldt_struct(ldt); } /* diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index 5d9afbcb6074..09284cfab86f 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -7,7 +7,7 @@ #include <linux/linkage.h> #include <asm/ptrace.h> #include <asm/ftrace.h> - +#include <asm/nospec-branch.h> .code64 .section .entry.text, "ax" @@ -285,8 +285,9 @@ trace: * ip and parent ip are used and the list function is called when * function tracing is enabled. */ - call *ftrace_trace_function + movq ftrace_trace_function, %r8 + CALL_NOSPEC %r8 restore_mcount_regs jmp fgraph_trace @@ -329,5 +330,5 @@ GLOBAL(return_to_handler) movq 8(%rsp), %rdx movq (%rsp), %rax addq $24, %rsp - jmp *%rdi + JMP_NOSPEC %rdi #endif diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 8aa05583bc42..0677bf8d3a42 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -9,7 +9,6 @@ DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); -DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); @@ -62,7 +61,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); PATCH_SITE(pv_cpu_ops, clts); - PATCH_SITE(pv_mmu_ops, flush_tlb_single); PATCH_SITE(pv_cpu_ops, wbinvd); #if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 9f7c21c22477..7c5c5dc90ffa 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -39,7 +39,7 @@ * section. Since TSS's are completely CPU-local, we want them * on exact cacheline boundaries, to eliminate cacheline ping-pong. */ -__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { +__visible DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct tss_struct, cpu_tss) = { .x86_tss = { .sp0 = TOP_OF_INIT_STACK, #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index f660d63f40fe..9a16932c7258 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -93,6 +93,10 @@ void __noreturn machine_real_restart(unsigned int type) load_cr3(initial_page_table); #else write_cr3(real_mode_header->trampoline_pgd); + + /* Exiting long mode will fail if CR4.PCIDE is set. */ + if (static_cpu_has(X86_FEATURE_PCID)) + cr4_clear_bits(X86_CR4_PCIDE); #endif /* Jump to the identity-mapped low memory code */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index e67b834279b2..bbaae4cf9e8e 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -112,6 +112,7 @@ #include <asm/alternative.h> #include <asm/prom.h> #include <asm/microcode.h> +#include <asm/kaiser.h> /* * max_low_pfn_mapped: highest direct mapped pfn under 4GB @@ -1016,6 +1017,12 @@ void __init setup_arch(char **cmdline_p) */ init_hypervisor_platform(); + /* + * This needs to happen right after XENPV is set on xen and + * kaiser_enabled is checked below in cleanup_highmap(). + */ + kaiser_check_boottime_disable(); + x86_init.resources.probe_roms(); /* after parse_early_param, so could debug it */ diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fbabe4fcc7fb..fe89f938e0f0 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -104,14 +104,10 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) spin_lock_irqsave(&rtc_lock, flags); CMOS_WRITE(0xa, 0xf); spin_unlock_irqrestore(&rtc_lock, flags); - local_flush_tlb(); - pr_debug("1.\n"); *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = start_eip >> 4; - pr_debug("2.\n"); *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = start_eip & 0xf; - pr_debug("3.\n"); } static inline void smpboot_restore_warm_reset_vector(void) @@ -119,11 +115,6 @@ static inline void smpboot_restore_warm_reset_vector(void) unsigned long flags; /* - * Install writable page 0 entry to set BIOS data area. - */ - local_flush_tlb(); - - /* * Paranoid: Set warm reset code and vector here back * to default values. */ diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 91a4496db434..c77ab1f51fbe 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -140,6 +140,16 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn, return -1; set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot)); pte_unmap(pte); + + /* + * PTI poisons low addresses in the kernel page tables in the + * name of making them unusable for userspace. To execute + * code at such a low address, the poison must be cleared. + * + * Note: 'pgd' actually gets set in pud_alloc(). + */ + pgd->pgd &= ~_PAGE_NX; + return 0; } diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c index 1c113db9ed57..2bb5ee464df3 100644 --- a/arch/x86/kernel/tracepoint.c +++ b/arch/x86/kernel/tracepoint.c @@ -9,10 +9,12 @@ #include <linux/atomic.h> atomic_t trace_idt_ctr = ATOMIC_INIT(0); +__aligned(PAGE_SIZE) struct desc_ptr trace_idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) trace_idt_table }; /* No need to be aligned, but done to keep all IDTs defined the same way. */ +__aligned(PAGE_SIZE) gate_desc trace_idt_table[NR_VECTORS] __page_aligned_bss; static int trace_irq_vector_refcount; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 679302c312f8..22b81f35c500 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -166,7 +166,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) * from double_fault. */ BUG_ON((unsigned long)(current_top_of_stack() - - current_stack_pointer()) >= THREAD_SIZE); + current_stack_pointer) >= THREAD_SIZE); preempt_enable_no_resched(); } diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 524619351961..510e80da7de4 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -187,7 +187,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) pte_unmap_unlock(pte, ptl); out: up_write(&mm->mmap_sem); - flush_tlb(); + flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, 0UL); } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 74e4bf11f562..e065065a4dfb 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -104,6 +104,13 @@ SECTIONS IRQENTRY_TEXT *(.fixup) *(.gnu.warning) + +#ifdef CONFIG_RETPOLINE + __indirect_thunk_start = .; + *(.text.__x86.indirect_thunk) + __indirect_thunk_end = .; +#endif + /* End of text section */ _etext = .; } :text = 0x9090 |