diff options
Diffstat (limited to 'arch/x86/kernel')
31 files changed, 218 insertions, 213 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 64422f850e95..7ff007ed899d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -35,6 +35,7 @@ #include <linux/bootmem.h> #include <linux/ioport.h> #include <linux/pci.h> +#include <linux/efi-bgrt.h> #include <asm/irqdomain.h> #include <asm/pci_x86.h> @@ -1557,6 +1558,12 @@ int __init early_acpi_boot_init(void) return 0; } +static int __init acpi_parse_bgrt(struct acpi_table_header *table) +{ + efi_bgrt_init(table); + return 0; +} + int __init acpi_boot_init(void) { /* those are executed after early-quirks are executed */ @@ -1581,6 +1588,8 @@ int __init acpi_boot_init(void) acpi_process_madt(); acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet); + if (IS_ENABLED(CONFIG_ACPI_BGRT)) + acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); if (!acpi_noirq) x86_init.pci.init = pci_acpi_init; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 945e512a112a..bd6b8c270c24 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2115,6 +2115,7 @@ static inline void __init check_timer(void) if (idx != -1 && irq_trigger(idx)) unmask_ioapic_irq(irq_get_chip_data(0)); } + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) @@ -2136,6 +2137,7 @@ static inline void __init check_timer(void) * legacy devices should be connected to IO APIC #0 */ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); legacy_pic->unmask(0); if (timer_irq_works()) { diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 45d44c173cf9..4a7080c84a5a 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -905,8 +905,8 @@ static int apm_cpu_idle(struct cpuidle_device *dev, { static int use_apm_idle; /* = 0 */ static unsigned int last_jiffies; /* = 0 */ - static unsigned int last_stime; /* = 0 */ - cputime_t stime, utime; + static u64 last_stime; /* = 0 */ + u64 stime, utime; int apm_idle_done = 0; unsigned int jiffies_since_last_check = jiffies - last_jiffies; @@ -919,7 +919,7 @@ recalc: } else if (jiffies_since_last_check > idle_period) { unsigned int idle_percentage; - idle_percentage = cputime_to_jiffies(stime - last_stime); + idle_percentage = nsecs_to_jiffies(stime - last_stime); idle_percentage *= 100; idle_percentage /= jiffies_since_last_check; use_apm_idle = (idle_percentage > idle_threshold); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index c62e015b126c..de827d6ac8c2 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -81,6 +81,7 @@ void common(void) { BLANK(); OFFSET(BP_scratch, boot_params, scratch); + OFFSET(BP_secure_boot, boot_params, secure_boot); OFFSET(BP_loadflags, boot_params, hdr.loadflags); OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); OFFSET(BP_version, boot_params, hdr.version); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 71cae73a5076..4e95b2e0d95f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -312,12 +312,19 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - node_id = ecx & 7; - /* get compute unit information */ - smp_num_siblings = ((ebx >> 8) & 3) + 1; - c->x86_max_cores /= smp_num_siblings; - c->cpu_core_id = ebx & 0xff; + node_id = ecx & 0xff; + smp_num_siblings = ((ebx >> 8) & 0xff) + 1; + + if (c->x86 == 0x15) + c->cu_id = ebx & 0xff; + + if (c->x86 >= 0x17) { + c->cpu_core_id = ebx & 0xff; + + if (smp_num_siblings > 1) + c->x86_max_cores /= smp_num_siblings; + } /* * We may have multiple LLCs if L3 caches exist, so check if we @@ -548,8 +555,10 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (!check_tsc_unstable()) - set_sched_clock_stable(); + if (check_tsc_unstable()) + clear_sched_clock_stable(); + } else { + clear_sched_clock_stable(); } /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 1661d8ec9280..2c234a6d94c4 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,5 +1,5 @@ -#include <linux/bitops.h> -#include <linux/kernel.h> + +#include <linux/sched.h> #include <asm/cpufeature.h> #include <asm/e820.h> @@ -104,6 +104,8 @@ static void early_init_centaur(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSENTER32); #endif + + clear_sched_clock_stable(); } static void init_centaur(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index dc1697ca5191..3bcf6d880611 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -83,6 +83,7 @@ static void default_init(struct cpuinfo_x86 *c) strcpy(c->x86_model_id, "386"); } #endif + clear_sched_clock_stable(); } static const struct cpu_dev default_cpu = { @@ -1015,6 +1016,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; c->x86_coreid_bits = 0; + c->cu_id = 0xff; #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; c->x86_phys_bits = 36; @@ -1055,6 +1057,8 @@ static void identify_cpu(struct cpuinfo_x86 *c) */ if (this_cpu->c_init) this_cpu->c_init(c); + else + clear_sched_clock_stable(); /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); @@ -1221,7 +1225,7 @@ static __init int setup_disablecpuid(char *arg) { int bit; - if (get_option(&arg, &bit) && bit < NCAPINTS*32) + if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32) setup_clear_cpu_cap(bit); else return 0; diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index bd9dcd6b712d..47416f959a48 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -9,6 +9,7 @@ #include <asm/pci-direct.h> #include <asm/tsc.h> #include <asm/cpufeature.h> +#include <linux/sched.h> #include "cpu.h" @@ -183,6 +184,7 @@ static void early_init_cyrix(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); break; } + clear_sched_clock_stable(); } static void init_cyrix(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fcd484d2bb03..026c728d6ba7 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -14,6 +14,7 @@ #include <asm/bugs.h> #include <asm/cpu.h> #include <asm/intel-family.h> +#include <asm/microcode_intel.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> @@ -78,14 +79,8 @@ static void early_init_intel(struct cpuinfo_x86 *c) (c->x86 == 0x6 && c->x86_model >= 0x0e)) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); - if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) { - unsigned lower_word; - - wrmsr(MSR_IA32_UCODE_REV, 0, 0); - /* Required by the SDM */ - sync_core(); - rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode); - } + if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) + c->microcode = intel_get_microcode_revision(); /* * Atom erratum AAE44/AAF40/AAG38/AAH41: @@ -124,8 +119,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (!check_tsc_unstable()) - set_sched_clock_stable(); + if (check_tsc_unstable()) + clear_sched_clock_stable(); + } else { + clear_sched_clock_stable(); } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c index 83f1a98d37db..2eee85379689 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -52,8 +52,11 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) if (severity >= GHES_SEV_RECOVERABLE) m.status |= MCI_STATUS_UC; - if (severity >= GHES_SEV_PANIC) + + if (severity >= GHES_SEV_PANIC) { m.status |= MCI_STATUS_PCC; + m.tsc = rdtsc(); + } m.addr = mem_err->physical_addr; mce_log(&m); diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 93d824ec3120..1e5a50c11d3c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -72,7 +72,7 @@ struct llist_node *mce_gen_pool_prepare_records(void) return new_head.first; } -void mce_gen_pool_process(void) +void mce_gen_pool_process(struct work_struct *__unused) { struct llist_node *head; struct mce_evt_llist *node, *tmp; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 517619ea6498..99165b206df3 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; @@ -192,9 +191,7 @@ 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-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index cd74a3f00aea..903043e6a62b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -31,7 +31,7 @@ struct mce_evt_llist { struct mce mce; }; -void mce_gen_pool_process(void); +void mce_gen_pool_process(struct work_struct *__unused); bool mce_gen_pool_empty(void); int mce_gen_pool_add(struct mce *mce); int mce_gen_pool_init(void); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 00ef43233e03..8e9725c607ea 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -128,7 +128,6 @@ void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); - m->tsc = rdtsc(); /* We hope get_seconds stays lockless */ m->time = get_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; @@ -217,9 +216,7 @@ void mce_register_decode_chain(struct notifier_block *nb) { atomic_inc(&num_notifiers); - /* Ensure SRAO notifier has the highest priority in the decode chain. */ - if (nb != &mce_srao_nb && nb->priority == INT_MAX) - nb->priority -= 1; + WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC); atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); } @@ -583,7 +580,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, } static struct notifier_block mce_srao_nb = { .notifier_call = srao_decode_notifier, - .priority = INT_MAX, + .priority = MCE_PRIO_SRAO, }; static int mce_default_notifier(struct notifier_block *nb, unsigned long val, @@ -609,7 +606,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val, static struct notifier_block mce_default_nb = { .notifier_call = mce_default_notifier, /* lowest prio, we want it to run last. */ - .priority = 0, + .priority = MCE_PRIO_LOWEST, }; /* @@ -710,14 +707,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_gather_info(&m, NULL); - /* - * m.tsc was set in mce_setup(). Clear it if not requested. - * - * FIXME: Propagate @flags to mce_gather_info/mce_setup() to avoid - * that dance. - */ - if (!(flags & MCP_TIMESTAMP)) - m.tsc = 0; + if (flags & MCP_TIMESTAMP) + m.tsc = rdtsc(); for (i = 0; i < mca_cfg.banks; i++) { if (!mce_banks[i].ctl || !test_bit(i, *b)) @@ -1156,6 +1147,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) goto out; mce_gather_info(&m, regs); + m.tsc = rdtsc(); final = this_cpu_ptr(&mces_seen); *final = m; @@ -1322,41 +1314,6 @@ int memory_failure(unsigned long pfn, int vector, int flags) #endif /* - * Action optional processing happens here (picking up - * from the list of faulting pages that do_machine_check() - * placed into the genpool). - */ -static void mce_process_work(struct work_struct *dummy) -{ - mce_gen_pool_process(); -} - -#ifdef CONFIG_X86_MCE_INTEL -/*** - * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog - * @cpu: The CPU on which the event occurred. - * @status: Event status information - * - * This function should be called by the thermal interrupt after the - * event has been processed and the decision was made to log the event - * further. - * - * The status parameter will be saved to the 'status' field of 'struct mce' - * and historically has been the register value of the - * MSR_IA32_THERMAL_STATUS (Intel) msr. - */ -void mce_log_therm_throt_event(__u64 status) -{ - struct mce m; - - mce_setup(&m); - m.bank = MCE_THERMAL_BANK; - m.status = status; - mce_log(&m); -} -#endif /* CONFIG_X86_MCE_INTEL */ - -/* * Periodic polling timer for "silent" machine check errors. If the * poller finds an MCE, poll 2x faster. When the poller finds no more * errors, poll 2x slower (up to check_interval seconds). @@ -1373,20 +1330,15 @@ static unsigned long mce_adjust_timer_default(unsigned long interval) static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; -static void __restart_timer(struct timer_list *t, unsigned long interval) +static void __start_timer(struct timer_list *t, unsigned long interval) { unsigned long when = jiffies + interval; unsigned long flags; local_irq_save(flags); - if (timer_pending(t)) { - if (time_before(when, t->expires)) - mod_timer(t, when); - } else { - t->expires = round_jiffies(when); - add_timer_on(t, smp_processor_id()); - } + if (!timer_pending(t) || time_before(when, t->expires)) + mod_timer(t, round_jiffies(when)); local_irq_restore(flags); } @@ -1421,7 +1373,7 @@ static void mce_timer_fn(unsigned long data) done: __this_cpu_write(mce_next_interval, iv); - __restart_timer(t, iv); + __start_timer(t, iv); } /* @@ -1432,7 +1384,7 @@ void mce_timer_kick(unsigned long interval) struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned long iv = __this_cpu_read(mce_next_interval); - __restart_timer(t, interval); + __start_timer(t, interval); if (interval < iv) __this_cpu_write(mce_next_interval, interval); @@ -1779,17 +1731,15 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) } } -static void mce_start_timer(unsigned int cpu, struct timer_list *t) +static void mce_start_timer(struct timer_list *t) { unsigned long iv = check_interval * HZ; if (mca_cfg.ignore_ce || !iv) return; - per_cpu(mce_next_interval, cpu) = iv; - - t->expires = round_jiffies(jiffies + iv); - add_timer_on(t, cpu); + this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); } static void __mcheck_cpu_setup_timer(void) @@ -1806,7 +1756,7 @@ static void __mcheck_cpu_init_timer(void) unsigned int cpu = smp_processor_id(); setup_pinned_timer(t, mce_timer_fn, cpu); - mce_start_timer(cpu, t); + mce_start_timer(t); } /* Handle unconfigured int18 (should never happen) */ @@ -2196,7 +2146,7 @@ int __init mcheck_init(void) mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); - INIT_WORK(&mce_work, mce_process_work); + INIT_WORK(&mce_work, mce_gen_pool_process); init_irq_work(&mce_irq_work, mce_irq_work_cb); return 0; @@ -2566,7 +2516,7 @@ static int mce_cpu_dead(unsigned int cpu) static int mce_cpu_online(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); int ret; mce_device_create(cpu); @@ -2577,13 +2527,13 @@ static int mce_cpu_online(unsigned int cpu) return ret; } mce_reenable_cpu(); - mce_start_timer(cpu, t); + mce_start_timer(t); return 0; } static int mce_cpu_pre_down(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); mce_disable_cpu(); del_timer_sync(t); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index a5fd137417a2..9e5427df3243 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -192,6 +192,7 @@ static void get_smca_bank_info(unsigned int bank) smca_banks[bank].hwid = s_hwid; smca_banks[bank].id = instance_id; + smca_banks[bank].sysfs_id = s_hwid->count++; break; } } @@ -777,7 +778,8 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) mce_setup(&m); m.status = status; - m.bank = bank; + m.bank = bank; + m.tsc = rdtsc(); if (threshold_err) m.misc = misc; @@ -1064,9 +1066,12 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return NULL; } + if (smca_banks[bank].hwid->count == 1) + return smca_get_name(bank_type); + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "%s_%x", smca_get_name(bank_type), - smca_banks[bank].id); + smca_banks[bank].sysfs_id); return buf_mcatype; } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 465aca8be009..85469f84c921 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -6,7 +6,7 @@ * * Maintains a counter in /sys that keeps track of the number of thermal * events, such that the user knows how bad the thermal problem might be - * (since the logging to syslog and mcelog is rate limited). + * (since the logging to syslog is rate limited). * * Author: Dmitriy Zavin (dmitriyz@google.com) * @@ -141,13 +141,8 @@ static struct attribute_group thermal_attr_group = { * IRQ has been acknowledged. * * It will take care of rate limiting and printing messages to the syslog. - * - * Returns: 0 : Event should NOT be further logged, i.e. still in - * "timeout" from previous log message. - * 1 : Event should be logged further, and a message has been - * printed to the syslog. */ -static int therm_throt_process(bool new_event, int event, int level) +static void therm_throt_process(bool new_event, int event, int level) { struct _thermal_state *state; unsigned int this_cpu = smp_processor_id(); @@ -162,16 +157,16 @@ static int therm_throt_process(bool new_event, int event, int level) else if (event == POWER_LIMIT_EVENT) state = &pstate->core_power_limit; else - return 0; + return; } else if (level == PACKAGE_LEVEL) { if (event == THERMAL_THROTTLING_EVENT) state = &pstate->package_throttle; else if (event == POWER_LIMIT_EVENT) state = &pstate->package_power_limit; else - return 0; + return; } else - return 0; + return; old_event = state->new_event; state->new_event = new_event; @@ -181,7 +176,7 @@ static int therm_throt_process(bool new_event, int event, int level) if (time_before64(now, state->next_check) && state->count != state->last_count) - return 0; + return; state->next_check = now + CHECK_INTERVAL; state->last_count = state->count; @@ -193,16 +188,14 @@ static int therm_throt_process(bool new_event, int event, int level) this_cpu, level == CORE_LEVEL ? "Core" : "Package", state->count); - return 1; + return; } if (old_event) { if (event == THERMAL_THROTTLING_EVENT) pr_info("CPU%d: %s temperature/speed normal\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package"); - return 1; + return; } - - return 0; } static int thresh_event_valid(int level, int event) @@ -365,10 +358,9 @@ static void intel_thermal_interrupt(void) /* Check for violation of core thermal thresholds*/ notify_thresholds(msr_val); - if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT, - THERMAL_THROTTLING_EVENT, - CORE_LEVEL) != 0) - mce_log_therm_throt_event(msr_val); + therm_throt_process(msr_val & THERM_STATUS_PROCHOT, + THERMAL_THROTTLING_EVENT, + CORE_LEVEL); if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 6a31e2691f3a..079e81733a58 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -384,8 +384,9 @@ void load_ucode_amd_ap(unsigned int family) reget: if (!get_builtin_microcode(&cp, family)) { #ifdef CONFIG_BLK_DEV_INITRD - cp = find_cpio_data(ucode_path, (void *)initrd_start, - initrd_end - initrd_start, NULL); + if (!initrd_gone) + cp = find_cpio_data(ucode_path, (void *)initrd_start, + initrd_end - initrd_start, NULL); #endif if (!(cp.data && cp.size)) { /* diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 2af69d27da62..73102d932760 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -46,6 +46,8 @@ static struct microcode_ops *microcode_ops; static bool dis_ucode_ldr = true; +bool initrd_gone; + LIST_HEAD(microcode_cache); /* @@ -190,21 +192,24 @@ void load_ucode_ap(void) static int __init save_microcode_in_initrd(void) { struct cpuinfo_x86 *c = &boot_cpu_data; + int ret = -EINVAL; switch (c->x86_vendor) { case X86_VENDOR_INTEL: if (c->x86 >= 6) - return save_microcode_in_initrd_intel(); + ret = save_microcode_in_initrd_intel(); break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - return save_microcode_in_initrd_amd(c->x86); + ret = save_microcode_in_initrd_amd(c->x86); break; default: break; } - return -EINVAL; + initrd_gone = true; + + return ret; } struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) @@ -247,9 +252,16 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) * has the virtual address of the beginning of the initrd. It also * possibly relocates the ramdisk. In either case, initrd_start contains * the updated address so use that instead. + * + * initrd_gone is for the hotplug case where we've thrown out initrd + * already. */ - if (!use_pa && initrd_start) - start = initrd_start; + if (!use_pa) { + if (initrd_gone) + return (struct cpio_data){ NULL, 0, "" }; + if (initrd_start) + start = initrd_start; + } return find_cpio_data(path, (void *)start, size, NULL); #else /* !CONFIG_BLK_DEV_INITRD */ diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index b624b54912e1..8325d8a09ab0 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -41,7 +41,7 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; -/* Current microcode patch used in early patching */ +/* Current microcode patch used in early patching on the APs. */ struct microcode_intel *intel_ucode_patch; static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, @@ -150,7 +150,7 @@ static struct ucode_patch *__alloc_microcode_buf(void *data, unsigned int size) { struct ucode_patch *p; - p = kzalloc(size, GFP_KERNEL); + p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); @@ -368,26 +368,6 @@ next: return patch; } -static void cpuid_1(void) -{ - /* - * According to the Intel SDM, Volume 3, 9.11.7: - * - * CPUID returns a value in a model specific register in - * addition to its usual register return values. The - * semantics of CPUID cause it to deposit an update ID value - * in the 64-bit model-specific register at address 08BH - * (IA32_BIOS_SIGN_ID). If no update is present in the - * processor, the value in the MSR remains unmodified. - * - * Use native_cpuid -- this code runs very early and we don't - * want to mess with paravirt. - */ - unsigned int eax = 1, ebx, ecx = 0, edx; - - native_cpuid(&eax, &ebx, &ecx, &edx); -} - static int collect_cpu_info_early(struct ucode_cpu_info *uci) { unsigned int val[2]; @@ -410,15 +390,8 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci) native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); csig.pf = 1 << ((val[1] >> 18) & 7); } - native_wrmsrl(MSR_IA32_UCODE_REV, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - cpuid_1(); - - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - csig.rev = val[1]; + csig.rev = intel_get_microcode_revision(); uci->cpu_sig = csig; uci->valid = 1; @@ -602,7 +575,7 @@ static inline void print_ucode(struct ucode_cpu_info *uci) static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) { struct microcode_intel *mc; - unsigned int val[2]; + u32 rev; mc = uci->mc; if (!mc) @@ -610,21 +583,16 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) /* write microcode via MSR 0x79 */ native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); - native_wrmsrl(MSR_IA32_UCODE_REV, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - cpuid_1(); - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - if (val[1] != mc->hdr.rev) + rev = intel_get_microcode_revision(); + if (rev != mc->hdr.rev) return -1; #ifdef CONFIG_X86_64 /* Flush global tlb. This is precaution. */ flush_tlb_early(); #endif - uci->cpu_sig.rev = val[1]; + uci->cpu_sig.rev = rev; if (early) print_ucode(uci); @@ -639,12 +607,6 @@ int __init save_microcode_in_initrd_intel(void) struct ucode_cpu_info uci; struct cpio_data cp; - /* - * AP loading didn't find any microcode patch, no need to save anything. - */ - if (!intel_ucode_patch || IS_ERR(intel_ucode_patch)) - return 0; - if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path, false); @@ -660,7 +622,6 @@ int __init save_microcode_in_initrd_intel(void) return 0; } - /* * @res_patch, output: a pointer to the patch we found. */ @@ -804,8 +765,8 @@ static int apply_microcode_intel(int cpu) struct microcode_intel *mc; struct ucode_cpu_info *uci; struct cpuinfo_x86 *c; - unsigned int val[2]; static int prev_rev; + u32 rev; /* We should bind the task to the CPU */ if (WARN_ON(raw_smp_processor_id() != cpu)) @@ -822,33 +783,28 @@ static int apply_microcode_intel(int cpu) /* write microcode via MSR 0x79 */ wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); - wrmsrl(MSR_IA32_UCODE_REV, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - cpuid_1(); - /* get the current revision from MSR 0x8B */ - rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); + rev = intel_get_microcode_revision(); - if (val[1] != mc->hdr.rev) { + if (rev != mc->hdr.rev) { pr_err("CPU%d update to revision 0x%x failed\n", cpu, mc->hdr.rev); return -1; } - if (val[1] != prev_rev) { + if (rev != prev_rev) { pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n", - val[1], + rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24, (mc->hdr.date >> 16) & 0xff); - prev_rev = val[1]; + prev_rev = rev; } c = &cpu_data(cpu); - uci->cpu_sig.rev = val[1]; - c->microcode = val[1]; + uci->cpu_sig.rev = rev; + c->microcode = rev; return 0; } @@ -860,7 +816,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL; int new_rev = uci->cpu_sig.rev; unsigned int leftover = size; - unsigned int curr_mc_size = 0; + unsigned int curr_mc_size = 0, new_mc_size = 0; unsigned int csig, cpf; while (leftover) { @@ -901,6 +857,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, vfree(new_mc); new_rev = mc_header.rev; new_mc = mc; + new_mc_size = mc_size; mc = NULL; /* trigger new vmalloc */ } @@ -926,7 +883,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, * permanent memory. So it will be loaded early when a CPU is hot added * or resumes. */ - save_mc_for_early(new_mc, curr_mc_size); + save_mc_for_early(new_mc, new_mc_size); pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 34178564be2a..c1ea5b999839 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -1,4 +1,5 @@ #include <linux/kernel.h> +#include <linux/sched.h> #include <linux/mm.h> #include <asm/cpufeature.h> #include <asm/msr.h> @@ -14,6 +15,8 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) if (xlvl >= 0x80860001) c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } + + clear_sched_clock_stable(); } static void init_transmeta(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e4e97a5355ce..de7234401275 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -9,6 +9,7 @@ #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> +#include <asm/fpu/xstate.h> #include <asm/traps.h> #include <linux/hardirq.h> @@ -183,7 +184,8 @@ void fpstate_init(union fpregs_state *state) * it will #GP. Make sure it is replaced after the memset(). */ if (static_cpu_has(X86_FEATURE_XSAVES)) - state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT; + state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | + xfeatures_mask; if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 85e87b46c318..dc6ba5bda9fc 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -352,6 +352,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer) } else { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq)); irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); disable_irq(hdev->irq); irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index cb9c1ed1d391..f73f475d0573 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -132,10 +132,8 @@ int sched_set_itmt_support(void) sysctl_sched_itmt_enabled = 1; - if (sysctl_sched_itmt_enabled) { - x86_topology_update = true; - rebuild_sched_domains(); - } + x86_topology_update = true; + rebuild_sched_domains(); mutex_unlock(&itmt_update_mutex); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index eb3509338ae0..520b8dfe1640 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -745,7 +745,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) * will be the real return address, and all the rest will * point to kretprobe_trampoline. */ - hlist_for_each_entry_safe(ri, tmp, head, hlist) { + hlist_for_each_entry(ri, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 2a5cafdf8808..542710b99f52 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -107,12 +107,12 @@ static inline void kvm_sched_clock_init(bool stable) { if (!stable) { pv_time_ops.sched_clock = kvm_clock_read; + clear_sched_clock_stable(); return; } kvm_sched_clock_offset = kvm_clock_read(); pv_time_ops.sched_clock = kvm_sched_clock_read; - set_sched_clock_stable(); printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n", kvm_sched_clock_offset); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 4cfba947d774..69780edf0dde 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1176,6 +1176,20 @@ void __init setup_arch(char **cmdline_p) /* Allocate bigger log buffer */ setup_log_buf(1); + if (efi_enabled(EFI_BOOT)) { + switch (boot_params.secure_boot) { + case efi_secureboot_mode_disabled: + pr_info("Secure boot disabled\n"); + break; + case efi_secureboot_mode_enabled: + pr_info("Secure boot enabled\n"); + break; + default: + pr_info("Secure boot could not be determined\n"); + break; + } + } + reserve_initrd(); acpi_table_upgrade(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 46732dc3b73c..99b920d0e516 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -433,9 +433,15 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) int cpu1 = c->cpu_index, cpu2 = o->cpu_index; if (c->phys_proc_id == o->phys_proc_id && - per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) && - c->cpu_core_id == o->cpu_core_id) - return topology_sane(c, o, "smt"); + per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) { + if (c->cpu_core_id == o->cpu_core_id) + return topology_sane(c, o, "smt"); + + if ((c->cu_id != 0xff) && + (o->cu_id != 0xff) && + (c->cu_id == o->cu_id)) + return topology_sane(c, o, "smt"); + } } else if (c->phys_proc_id == o->phys_proc_id && c->cpu_core_id == o->cpu_core_id) { diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index be3a49ee0356..2724dc82f992 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -694,6 +694,7 @@ unsigned long native_calibrate_tsc(void) crystal_khz = 24000; /* 24.0 MHz */ break; case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_ATOM_DENVERTON: crystal_khz = 25000; /* 25.0 MHz */ break; case INTEL_FAM6_ATOM_GOLDMONT: @@ -1106,6 +1107,16 @@ static u64 read_tsc(struct clocksource *cs) return (u64)rdtsc_ordered(); } +static void tsc_cs_mark_unstable(struct clocksource *cs) +{ + if (tsc_unstable) + return; + tsc_unstable = 1; + clear_sched_clock_stable(); + disable_sched_clock_irqtime(); + pr_info("Marking TSC unstable due to clocksource watchdog\n"); +} + /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ @@ -1118,6 +1129,7 @@ static struct clocksource clocksource_tsc = { CLOCK_SOURCE_MUST_VERIFY, .archdata = { .vclock_mode = VCLOCK_TSC }, .resume = tsc_resume, + .mark_unstable = tsc_cs_mark_unstable, }; void mark_tsc_unstable(char *reason) @@ -1355,6 +1367,9 @@ void __init tsc_init(void) (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); + /* Sanitize TSC ADJUST before cyc2ns gets initialized */ + tsc_store_and_check_tsc_adjust(true); + /* * Secondary CPUs do not run through tsc_init(), so set up * all the scale factors for all CPUs, assuming the same @@ -1385,8 +1400,6 @@ void __init tsc_init(void) if (unsynchronized_tsc()) mark_tsc_unstable("TSCs unsynchronized"); - else - tsc_store_and_check_tsc_adjust(true); check_system_tsc_reliable(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index d0db011051a5..728f75378475 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -286,13 +286,6 @@ void check_tsc_sync_source(int cpu) if (unsynchronized_tsc()) return; - if (tsc_clocksource_reliable) { - if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING) - pr_info( - "Skipped synchronization checks as TSC is reliable.\n"); - return; - } - /* * Set the maximum number of test runs to * 1 if the CPU does not provide the TSC_ADJUST MSR @@ -380,14 +373,19 @@ void check_tsc_sync_target(void) int cpus = 2; /* Also aborts if there is no TSC. */ - if (unsynchronized_tsc() || tsc_clocksource_reliable) + if (unsynchronized_tsc()) return; /* * Store, verify and sanitize the TSC adjust register. If * successful skip the test. + * + * The test is also skipped when the TSC is marked reliable. This + * is true for SoCs which have no fallback clocksource. On these + * SoCs the TSC is frequency synchronized, but still the TSC ADJUST + * register might have been wreckaged by the BIOS.. */ - if (tsc_store_and_check_tsc_adjust(false)) { + if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) { atomic_inc(&skip_test); return; } diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 4443e499f279..23d15565d02a 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -6,6 +6,21 @@ #define FRAME_HEADER_SIZE (sizeof(long) * 2) +/* + * This disables KASAN checking when reading a value from another task's stack, + * since the other task could be running on another CPU and could have poisoned + * the stack in the meantime. + */ +#define READ_ONCE_TASK_STACK(task, x) \ +({ \ + unsigned long val; \ + if (task == current) \ + val = READ_ONCE(x); \ + else \ + val = READ_ONCE_NOCHECK(x); \ + val; \ +}) + static void unwind_dump(struct unwind_state *state, unsigned long *sp) { static bool dumped_before = false; @@ -48,7 +63,8 @@ unsigned long unwind_get_return_address(struct unwind_state *state) if (state->regs && user_mode(state->regs)) return 0; - addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p, + addr = READ_ONCE_TASK_STACK(state->task, *addr_p); + addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr, addr_p); return __kernel_text_address(addr) ? addr : 0; @@ -162,7 +178,7 @@ bool unwind_next_frame(struct unwind_state *state) if (state->regs) next_bp = (unsigned long *)state->regs->bp; else - next_bp = (unsigned long *)*state->bp; + next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task,*state->bp); /* is the next frame pointer an encoded pointer to pt_regs? */ regs = decode_frame_pointer(next_bp); @@ -207,6 +223,16 @@ bool unwind_next_frame(struct unwind_state *state) return true; bad_address: + /* + * When unwinding a non-current task, the task might actually be + * running on another CPU, in which case it could be modifying its + * stack while we're reading it. This is generally not a problem and + * can be ignored as long as the caller understands that unwinding + * another task will not always succeed. + */ + if (state->task != current) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index ec5d7545e6dc..0442d98367ae 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -160,11 +160,12 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) static void mark_screen_rdonly(struct mm_struct *mm) { + struct vm_area_struct *vma; + spinlock_t *ptl; pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; - spinlock_t *ptl; int i; down_write(&mm->mmap_sem); @@ -177,7 +178,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) pmd = pmd_offset(pud, 0xA0000); if (pmd_trans_huge(*pmd)) { - struct vm_area_struct *vma = find_vma(mm, 0xA0000); + vma = find_vma(mm, 0xA0000); split_huge_pmd(vma, pmd, 0xA0000); } if (pmd_none_or_clear_bad(pmd)) |
