diff options
Diffstat (limited to 'arch/x86/kernel')
29 files changed, 583 insertions, 156 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 9b294c13809a..8be5926cce51 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -28,7 +28,6 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n -OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y OBJECT_FILES_NON_STANDARD_paravirt_patch.o := y diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 04205ce127a1..1ae5439a9a85 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -45,6 +45,7 @@ EXPORT_SYMBOL(acpi_disabled); #define PREFIX "ACPI: " int acpi_noirq; /* skip ACPI IRQ initialization */ +int acpi_nobgrt; /* skip ACPI BGRT */ int acpi_pci_disabled; /* skip ACPI PCI scan and IRQ initialization */ EXPORT_SYMBOL(acpi_pci_disabled); @@ -1619,7 +1620,7 @@ int __init acpi_boot_init(void) acpi_process_madt(); acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet); - if (IS_ENABLED(CONFIG_ACPI_BGRT)) + if (IS_ENABLED(CONFIG_ACPI_BGRT) && !acpi_nobgrt) acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); if (!acpi_noirq) @@ -1671,6 +1672,13 @@ static int __init parse_acpi(char *arg) } early_param("acpi", parse_acpi); +static int __init parse_acpi_bgrt(char *arg) +{ + acpi_nobgrt = true; + return 0; +} +early_param("bgrt_disable", parse_acpi_bgrt); + /* FIXME: Using pci= for an ACPI parameter is a travesty. */ static int __init parse_pci(char *arg) { @@ -1740,7 +1748,7 @@ int __acpi_acquire_global_lock(unsigned int *lock) new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1)); val = cmpxchg(lock, old, new); } while (unlikely (val != old)); - return (new < 3) ? -1 : 0; + return ((new & 0x3) < 3) ? -1 : 0; } int __acpi_release_global_lock(unsigned int *lock) diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 26b7256f590f..ed3b04483972 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -43,7 +43,7 @@ unsigned long acpi_get_wakeup_address(void) * * Wrapper around acpi_enter_sleep_state() to be called by assmebly. */ -acpi_status asmlinkage __visible x86_acpi_enter_sleep_state(u8 state) +asmlinkage acpi_status __visible x86_acpi_enter_sleep_state(u8 state) { return acpi_enter_sleep_state(state); } diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index d06c2079b6c1..171a40c74db6 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -19,4 +19,4 @@ extern void do_suspend_lowlevel(void); extern int x86_acpi_suspend_lowlevel(void); -acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state); +asmlinkage acpi_status x86_acpi_enter_sleep_state(u8 state); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 69aed0ebbdfc..b6b3297851f3 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -36,10 +36,9 @@ static const struct pci_device_id amd_root_ids[] = { {} }; - #define PCI_DEVICE_ID_AMD_CNB17H_F4 0x1704 -const struct pci_device_id amd_nb_misc_ids[] = { +static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) }, @@ -56,7 +55,6 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, {} }; -EXPORT_SYMBOL_GPL(amd_nb_misc_ids); static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 5f973fed3c9f..81b9c63dae1b 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -546,12 +546,6 @@ static struct clock_event_device lapic_clockevent = { }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); -#define DEADLINE_MODEL_MATCH_FUNC(model, func) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&func } - -#define DEADLINE_MODEL_MATCH_REV(model, rev) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)rev } - static u32 hsx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { @@ -588,23 +582,23 @@ static u32 skx_deadline_rev(void) } static const struct x86_cpu_id deadline_match[] = { - DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), - DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_D, bdx_deadline_rev), - DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X, skx_deadline_rev), + X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X, &hsx_deadline_rev), + X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X, 0x0b000020), + X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D, &bdx_deadline_rev), + X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE_X, &skx_deadline_rev), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL, 0x22), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_L, 0x20), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_G, 0x17), + X86_MATCH_INTEL_FAM6_MODEL( HASWELL, 0x22), + X86_MATCH_INTEL_FAM6_MODEL( HASWELL_L, 0x20), + X86_MATCH_INTEL_FAM6_MODEL( HASWELL_G, 0x17), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL, 0x25), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_G, 0x17), + X86_MATCH_INTEL_FAM6_MODEL( BROADWELL, 0x25), + X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_G, 0x17), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_L, 0xb2), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE, 0xb2), + X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE_L, 0xb2), + X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE, 0xb2), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_L, 0x52), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE, 0x52), + X86_MATCH_INTEL_FAM6_MODEL( KABYLAKE_L, 0x52), + X86_MATCH_INTEL_FAM6_MODEL( KABYLAKE, 0x52), {}, }; diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 2c5676b0a6e7..67768e54438b 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -557,6 +557,12 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, irqd->hwirq = virq + i; irqd_set_single_target(irqd); /* + * Prevent that any of these interrupts is invoked in + * non interrupt context via e.g. generic_handle_irq() + * as that can corrupt the affinity move state. + */ + irqd_set_handle_enforce_irqctx(irqd); + /* * Legacy vectors are already assigned when the IOAPIC * takes them over. They stay on the same vector. This is * required for check_timer() to work correctly as it might @@ -838,13 +844,15 @@ static void free_moved_vector(struct apic_chip_data *apicd) bool managed = apicd->is_managed; /* - * This should never happen. Managed interrupts are not - * migrated except on CPU down, which does not involve the - * cleanup vector. But try to keep the accounting correct - * nevertheless. + * Managed interrupts are usually not migrated away + * from an online CPU, but CPU isolation 'managed_irq' + * can make that happen. + * 1) Activation does not take the isolation into account + * to keep the code simple + * 2) Migration away from an isolated CPU can happen when + * a non-isolated CPU which is in the calculated + * affinity mask comes online. */ - WARN_ON_ONCE(managed); - trace_vector_free_moved(apicd->irq, cpu, vector, managed); irq_matrix_free(vector_matrix, cpu, vector, managed); per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 5c7ee3df4d0b..3ca07ad552ae 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -88,7 +88,6 @@ static void __used common(void) OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment); OFFSET(BP_init_size, boot_params, hdr.init_size); OFFSET(BP_pref_address, boot_params, hdr.pref_address); - OFFSET(BP_code32_start, boot_params, hdr.code32_start); BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 82826f2275cc..2b4256ebe86e 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -3,6 +3,8 @@ # error "Please do not build this file directly, build asm-offsets.c instead" #endif +#include <linux/efi.h> + #include <asm/ucontext.h> #define __SYSCALL_I386(nr, sym, qual) [nr] = 1, @@ -64,4 +66,7 @@ void foo(void) BLANK(); DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); DEFINE(NR_syscalls, sizeof(syscalls)); + + BLANK(); + DEFINE(EFI_svam, offsetof(efi_runtime_services_t, set_virtual_address_map)); } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ac83a0fef628..547ad7bbf0e0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -28,6 +28,7 @@ static const int amd_erratum_383[]; static const int amd_erratum_400[]; +static const int amd_erratum_1054[]; static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); /* @@ -393,6 +394,35 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; } +static void amd_detect_ppin(struct cpuinfo_x86 *c) +{ + unsigned long long val; + + if (!cpu_has(c, X86_FEATURE_AMD_PPIN)) + return; + + /* When PPIN is defined in CPUID, still need to check PPIN_CTL MSR */ + if (rdmsrl_safe(MSR_AMD_PPIN_CTL, &val)) + goto clear_ppin; + + /* PPIN is locked in disabled mode, clear feature bit */ + if ((val & 3UL) == 1UL) + goto clear_ppin; + + /* If PPIN is disabled, try to enable it */ + if (!(val & 2UL)) { + wrmsrl_safe(MSR_AMD_PPIN_CTL, val | 2UL); + rdmsrl_safe(MSR_AMD_PPIN_CTL, &val); + } + + /* If PPIN_EN bit is 1, return from here; otherwise fall through */ + if (val & 2UL) + return; + +clear_ppin: + clear_cpu_cap(c, X86_FEATURE_AMD_PPIN); +} + u16 amd_get_nb_id(int cpu) { return per_cpu(cpu_llc_id, cpu); @@ -925,7 +955,8 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; case 0x16: init_amd_jg(c); break; - case 0x17: init_amd_zn(c); break; + case 0x17: fallthrough; + case 0x19: init_amd_zn(c); break; } /* @@ -940,6 +971,7 @@ static void init_amd(struct cpuinfo_x86 *c) amd_detect_cmp(c); amd_get_topology(c); srat_detect_node(c); + amd_detect_ppin(c); init_amd_cacheinfo(c); @@ -972,6 +1004,15 @@ static void init_amd(struct cpuinfo_x86 *c) /* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */ if (!cpu_has(c, X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + + /* + * Turn on the Instructions Retired free counter on machines not + * susceptible to erratum #1054 "Instructions Retired Performance + * Counter May Be Inaccurate". + */ + if (cpu_has(c, X86_FEATURE_IRPERF) && + !cpu_has_amd_erratum(c, amd_erratum_1054)) + msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); } #ifdef CONFIG_X86_32 @@ -1099,6 +1140,10 @@ static const int amd_erratum_400[] = static const int amd_erratum_383[] = AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); +/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ +static const int amd_erratum_1054[] = + AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); + static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 52c9bfbbdb2a..137644a52716 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -445,7 +445,7 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c) * cpuid bit to be set. We need to ensure that we * update that bit in this CPU's "cpu_info". */ - get_cpu_cap(c); + set_cpu_cap(c, X86_FEATURE_OSPKE); } #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS @@ -1008,8 +1008,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_ITLB_MULTIHIT BIT(7) #define NO_SPECTRE_V2 BIT(8) -#define VULNWL(_vendor, _family, _model, _whitelist) \ - { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } +#define VULNWL(vendor, family, model, whitelist) \ + X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) #define VULNWL_INTEL(model, whitelist) \ VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist) diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index 6dd78d8235e4..d3482eb43ff3 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -16,12 +16,17 @@ * respective wildcard entries. * * A typical table entry would be to match a specific CPU - * { X86_VENDOR_INTEL, 6, 0x12 } - * or to match a specific CPU feature - * { X86_FEATURE_MATCH(X86_FEATURE_FOOBAR) } + * + * X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_BROADWELL, + * X86_FEATURE_ANY, NULL); * * Fields can be wildcarded with %X86_VENDOR_ANY, %X86_FAMILY_ANY, - * %X86_MODEL_ANY, %X86_FEATURE_ANY or 0 (except for vendor) + * %X86_MODEL_ANY, %X86_FEATURE_ANY (except for vendor) + * + * asm/cpu_device_id.h contains a set of useful macros which are shortcuts + * for various common selections. The above can be shortened to: + * + * X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, NULL); * * Arrays used to match for this should also be declared using * MODULE_DEVICE_TABLE(x86cpu, ...) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index b3a50d962851..52de616a8065 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1163,9 +1163,12 @@ static const struct sysfs_ops threshold_ops = { .store = store, }; +static void threshold_block_release(struct kobject *kobj); + static struct kobj_type threshold_ktype = { .sysfs_ops = &threshold_ops, .default_attrs = default_attrs, + .release = threshold_block_release, }; static const char *get_name(unsigned int bank, struct threshold_block *b) @@ -1198,8 +1201,9 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return buf_mcatype; } -static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, - unsigned int block, u32 address) +static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb, + unsigned int bank, unsigned int block, + u32 address) { struct threshold_block *b = NULL; u32 low, high; @@ -1243,16 +1247,12 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, INIT_LIST_HEAD(&b->miscj); - if (per_cpu(threshold_banks, cpu)[bank]->blocks) { - list_add(&b->miscj, - &per_cpu(threshold_banks, cpu)[bank]->blocks->miscj); - } else { - per_cpu(threshold_banks, cpu)[bank]->blocks = b; - } + if (tb->blocks) + list_add(&b->miscj, &tb->blocks->miscj); + else + tb->blocks = b; - err = kobject_init_and_add(&b->kobj, &threshold_ktype, - per_cpu(threshold_banks, cpu)[bank]->kobj, - get_name(bank, b)); + err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b)); if (err) goto out_free; recurse: @@ -1260,7 +1260,7 @@ recurse: if (!address) return 0; - err = allocate_threshold_blocks(cpu, bank, block, address); + err = allocate_threshold_blocks(cpu, tb, bank, block, address); if (err) goto out_free; @@ -1345,8 +1345,6 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out_free; } - per_cpu(threshold_banks, cpu)[bank] = b; - if (is_shared_bank(bank)) { refcount_set(&b->cpus, 1); @@ -1357,9 +1355,13 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) } } - err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank)); - if (!err) - goto out; + err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank)); + if (err) + goto out_free; + + per_cpu(threshold_banks, cpu)[bank] = b; + + return 0; out_free: kfree(b); @@ -1368,8 +1370,12 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) return err; } -static void deallocate_threshold_block(unsigned int cpu, - unsigned int bank) +static void threshold_block_release(struct kobject *kobj) +{ + kfree(to_block(kobj)); +} + +static void deallocate_threshold_block(unsigned int cpu, unsigned int bank) { struct threshold_block *pos = NULL; struct threshold_block *tmp = NULL; @@ -1379,13 +1385,11 @@ static void deallocate_threshold_block(unsigned int cpu, return; list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) { - kobject_put(&pos->kobj); list_del(&pos->miscj); - kfree(pos); + kobject_put(&pos->kobj); } - kfree(per_cpu(threshold_banks, cpu)[bank]->blocks); - per_cpu(threshold_banks, cpu)[bank]->blocks = NULL; + kobject_put(&head->blocks->kobj); } static void __threshold_remove_blocks(struct threshold_bank *b) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 2c4f949611e4..dd06fce537fc 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -142,6 +142,8 @@ void mce_setup(struct mce *m) if (this_cpu_has(X86_FEATURE_INTEL_PPIN)) rdmsrl(MSR_PPIN, m->ppin); + else if (this_cpu_has(X86_FEATURE_AMD_PPIN)) + rdmsrl(MSR_AMD_PPIN, m->ppin); m->microcode = boot_cpu_data.microcode; } @@ -1877,6 +1879,8 @@ bool filter_mce(struct mce *m) { if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) return amd_filter_mce(m); + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + return intel_filter_mce(m); return false; } diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index 7c8958dee103..d089567a9ce8 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -29,11 +29,7 @@ static char *mce_helper_argv[2] = { mce_helper, NULL }; * separate MCEs from kernel messages to avoid bogus bug reports. */ -static struct mce_log_buffer mcelog = { - .signature = MCE_LOG_SIGNATURE, - .len = MCE_LOG_LEN, - .recordlen = sizeof(struct mce), -}; +static struct mce_log_buffer *mcelog; static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); @@ -45,21 +41,21 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val, mutex_lock(&mce_chrdev_read_mutex); - entry = mcelog.next; + entry = mcelog->next; /* * When the buffer fills up discard new entries. Assume that the * earlier errors are the more interesting ones: */ - if (entry >= MCE_LOG_LEN) { - set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog.flags); + if (entry >= mcelog->len) { + set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog->flags); goto unlock; } - mcelog.next = entry + 1; + mcelog->next = entry + 1; - memcpy(mcelog.entry + entry, mce, sizeof(struct mce)); - mcelog.entry[entry].finished = 1; + memcpy(mcelog->entry + entry, mce, sizeof(struct mce)); + mcelog->entry[entry].finished = 1; /* wake processes polling /dev/mcelog */ wake_up_interruptible(&mce_chrdev_wait); @@ -214,21 +210,21 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, /* Only supports full reads right now */ err = -EINVAL; - if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) + if (*off != 0 || usize < mcelog->len * sizeof(struct mce)) goto out; - next = mcelog.next; + next = mcelog->next; err = 0; for (i = 0; i < next; i++) { - struct mce *m = &mcelog.entry[i]; + struct mce *m = &mcelog->entry[i]; err |= copy_to_user(buf, m, sizeof(*m)); buf += sizeof(*m); } - memset(mcelog.entry, 0, next * sizeof(struct mce)); - mcelog.next = 0; + memset(mcelog->entry, 0, next * sizeof(struct mce)); + mcelog->next = 0; if (err) err = -EFAULT; @@ -242,7 +238,7 @@ out: static __poll_t mce_chrdev_poll(struct file *file, poll_table *wait) { poll_wait(file, &mce_chrdev_wait, wait); - if (READ_ONCE(mcelog.next)) + if (READ_ONCE(mcelog->next)) return EPOLLIN | EPOLLRDNORM; if (!mce_apei_read_done && apei_check_mce()) return EPOLLIN | EPOLLRDNORM; @@ -261,13 +257,13 @@ static long mce_chrdev_ioctl(struct file *f, unsigned int cmd, case MCE_GET_RECORD_LEN: return put_user(sizeof(struct mce), p); case MCE_GET_LOG_LEN: - return put_user(MCE_LOG_LEN, p); + return put_user(mcelog->len, p); case MCE_GETCLEAR_FLAGS: { unsigned flags; do { - flags = mcelog.flags; - } while (cmpxchg(&mcelog.flags, flags, 0) != flags); + flags = mcelog->flags; + } while (cmpxchg(&mcelog->flags, flags, 0) != flags); return put_user(flags, p); } @@ -339,8 +335,18 @@ static struct miscdevice mce_chrdev_device = { static __init int dev_mcelog_init_device(void) { + int mce_log_len; int err; + mce_log_len = max(MCE_LOG_MIN_LEN, num_online_cpus()); + mcelog = kzalloc(sizeof(*mcelog) + mce_log_len * sizeof(struct mce), GFP_KERNEL); + if (!mcelog) + return -ENOMEM; + + strncpy(mcelog->signature, MCE_LOG_SIGNATURE, sizeof(mcelog->signature)); + mcelog->len = mce_log_len; + mcelog->recordlen = sizeof(struct mce); + /* register character device /dev/mcelog */ err = misc_register(&mce_chrdev_device); if (err) { @@ -350,6 +356,7 @@ static __init int dev_mcelog_init_device(void) else pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); + kfree(mcelog); return err; } diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index 5627b1091b85..d8f9230d2034 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -493,17 +493,18 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) return; if ((val & 3UL) == 1UL) { - /* PPIN available but disabled: */ + /* PPIN locked in disabled mode */ return; } - /* If PPIN is disabled, but not locked, try to enable: */ - if (!(val & 3UL)) { + /* If PPIN is disabled, try to enable */ + if (!(val & 2UL)) { wrmsrl_safe(MSR_PPIN_CTL, val | 2UL); rdmsrl_safe(MSR_PPIN_CTL, &val); } - if ((val & 3UL) == 2UL) + /* Is the enable bit set? */ + if (val & 2UL) set_cpu_cap(c, X86_FEATURE_INTEL_PPIN); } } @@ -520,3 +521,20 @@ void mce_intel_feature_clear(struct cpuinfo_x86 *c) { intel_clear_lmce(); } + +bool intel_filter_mce(struct mce *m) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + /* MCE errata HSD131, HSM142, HSW131, BDM48, and HSM142 */ + if ((c->x86 == 6) && + ((c->x86_model == INTEL_FAM6_HASWELL) || + (c->x86_model == INTEL_FAM6_HASWELL_L) || + (c->x86_model == INTEL_FAM6_BROADWELL) || + (c->x86_model == INTEL_FAM6_HASWELL_G)) && + (m->bank == 0) && + ((m->status & 0xa0000000ffffffff) == 0x80000000000f0005)) + return true; + + return false; +} diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index b785c0d0b590..97db18441d2c 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -48,6 +48,7 @@ void cmci_disable_bank(int bank); void intel_init_cmci(void); void intel_init_lmce(void); void intel_clear_lmce(void); +bool intel_filter_mce(struct mce *m); #else # define cmci_intel_adjust_timer mce_adjust_timer_default static inline bool mce_intel_cmci_poll(void) { return false; } @@ -56,6 +57,7 @@ static inline void cmci_disable_bank(int bank) { } static inline void intel_init_cmci(void) { } static inline void intel_init_lmce(void) { } static inline void intel_clear_lmce(void) { } +static inline bool intel_filter_mce(struct mce *m) { return false; }; #endif void mce_timer_kick(unsigned long interval); diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index 58b4ee3cda77..f36dc0742085 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -486,9 +486,14 @@ static int thermal_throttle_offline(unsigned int cpu) { struct thermal_state *state = &per_cpu(thermal_state, cpu); struct device *dev = get_cpu_device(cpu); + u32 l; + + /* Mask the thermal vector before draining evtl. pending work */ + l = apic_read(APIC_LVTTHMR); + apic_write(APIC_LVTTHMR, l | APIC_LVT_MASKED); - cancel_delayed_work(&state->package_throttle.therm_work); - cancel_delayed_work(&state->core_throttle.therm_work); + cancel_delayed_work_sync(&state->package_throttle.therm_work); + cancel_delayed_work_sync(&state->core_throttle.therm_work); state->package_throttle.rate_control_active = false; state->core_throttle.rate_control_active = false; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 3923ab4630d7..f66a6b90f954 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -67,11 +67,6 @@ __HEAD SYM_CODE_START(startup_32) movl pa(initial_stack),%ecx - /* test KEEP_SEGMENTS flag to see if the bootloader is asking - us to not reload segments */ - testb $KEEP_SEGMENTS, BP_loadflags(%esi) - jnz 2f - /* * Set segments to known values. */ @@ -82,7 +77,6 @@ SYM_CODE_START(startup_32) movl %eax,%fs movl %eax,%gs movl %eax,%ss -2: leal -__PAGE_OFFSET(%ecx),%esp /* diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c index 4d4f5d9faac3..7dfb1e808928 100644 --- a/arch/x86/kernel/ima_arch.c +++ b/arch/x86/kernel/ima_arch.c @@ -10,8 +10,6 @@ extern struct boot_params boot_params; static enum efi_secureboot_mode get_sb_mode(void) { - efi_char16_t efi_SecureBoot_name[] = L"SecureBoot"; - efi_char16_t efi_SetupMode_name[] = L"SecureBoot"; efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID; efi_status_t status; unsigned long size; @@ -19,13 +17,13 @@ static enum efi_secureboot_mode get_sb_mode(void) size = sizeof(secboot); - if (!efi_enabled(EFI_RUNTIME_SERVICES)) { + if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE)) { pr_info("ima: secureboot mode unknown, no efi\n"); return efi_secureboot_mode_unknown; } /* Get variable contents into buffer */ - status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid, + status = efi.get_variable(L"SecureBoot", &efi_variable_guid, NULL, &size, &secboot); if (status == EFI_NOT_FOUND) { pr_info("ima: secureboot mode disabled\n"); @@ -38,7 +36,7 @@ static enum efi_secureboot_mode get_sb_mode(void) } size = sizeof(setupmode); - status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid, + status = efi.get_variable(L"SetupMode", &efi_variable_guid, NULL, &size, &setupmode); if (status != EFI_SUCCESS) /* ignore unknown SetupMode */ diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index f293d872602a..db6578d45157 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -141,9 +141,8 @@ prepare_add_efi_setup_data(struct boot_params *params, struct setup_data *sd = (void *)params + efi_setup_data_offset; struct efi_setup_data *esd = (void *)sd + sizeof(struct setup_data); - esd->fw_vendor = efi.fw_vendor; - esd->runtime = efi.runtime; - esd->tables = efi.config_table; + esd->fw_vendor = efi_fw_vendor; + esd->tables = efi_config_table; esd->smbios = efi.smbios; sd->type = SETUP_EFI; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 3f45b5c43a71..ea13f6888284 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -71,6 +71,21 @@ found: return (unsigned long)buf; } +static void synthesize_clac(kprobe_opcode_t *addr) +{ + /* + * Can't be static_cpu_has() due to how objtool treats this feature bit. + * This isn't a fast path anyway. + */ + if (!boot_cpu_has(X86_FEATURE_SMAP)) + return; + + /* Replace the NOP3 with CLAC */ + addr[0] = 0x0f; + addr[1] = 0x01; + addr[2] = 0xca; +} + /* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) { @@ -92,6 +107,9 @@ asm ( /* We don't bother saving the ss register */ " pushq %rsp\n" " pushfq\n" + ".global optprobe_template_clac\n" + "optprobe_template_clac:\n" + ASM_NOP3 SAVE_REGS_STRING " movq %rsp, %rsi\n" ".global optprobe_template_val\n" @@ -111,6 +129,9 @@ asm ( #else /* CONFIG_X86_32 */ " pushl %esp\n" " pushfl\n" + ".global optprobe_template_clac\n" + "optprobe_template_clac:\n" + ASM_NOP3 SAVE_REGS_STRING " movl %esp, %edx\n" ".global optprobe_template_val\n" @@ -134,6 +155,8 @@ asm ( void optprobe_template_func(void); STACK_FRAME_NON_STANDARD(optprobe_template_func); +#define TMPL_CLAC_IDX \ + ((long)optprobe_template_clac - (long)optprobe_template_entry) #define TMPL_MOVE_IDX \ ((long)optprobe_template_val - (long)optprobe_template_entry) #define TMPL_CALL_IDX \ @@ -389,6 +412,8 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, op->optinsn.size = ret; len = TMPL_END_IDX + op->optinsn.size; + synthesize_clac(buf + TMPL_CLAC_IDX); + /* Set probe information */ synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d817f255aed8..6efe0410fb72 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -425,7 +425,29 @@ static void __init sev_map_percpu_data(void) } } +static bool pv_tlb_flush_supported(void) +{ + return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)); +} + +static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask); + #ifdef CONFIG_SMP + +static bool pv_ipi_supported(void) +{ + return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI); +} + +static bool pv_sched_yield_supported(void) +{ + return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)); +} + #define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG) static void __send_ipi_mask(const struct cpumask *mask, int vector) @@ -490,12 +512,12 @@ static void kvm_send_ipi_mask(const struct cpumask *mask, int vector) static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) { unsigned int this_cpu = smp_processor_id(); - struct cpumask new_mask; + struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask); const struct cpumask *local_mask; - cpumask_copy(&new_mask, mask); - cpumask_clear_cpu(this_cpu, &new_mask); - local_mask = &new_mask; + cpumask_copy(new_mask, mask); + cpumask_clear_cpu(this_cpu, new_mask); + local_mask = new_mask; __send_ipi_mask(local_mask, vector); } @@ -575,7 +597,6 @@ static void __init kvm_apf_trap_init(void) update_intr_gate(X86_TRAP_PF, async_page_fault); } -static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask); static void kvm_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info) @@ -583,7 +604,7 @@ static void kvm_flush_tlb_others(const struct cpumask *cpumask, u8 state; int cpu; struct kvm_steal_time *src; - struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask); + struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask); cpumask_copy(flushmask, cpumask); /* @@ -619,11 +640,10 @@ static void __init kvm_guest_init(void) pv_ops.time.steal_clock = kvm_steal_clock; } - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + if (pv_tlb_flush_supported()) { pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others; pv_ops.mmu.tlb_remove_table = tlb_remove_table; + pr_info("KVM setup pv remote TLB flush\n"); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) @@ -632,9 +652,7 @@ static void __init kvm_guest_init(void) #ifdef CONFIG_SMP smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus; smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; - if (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && - !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + if (pv_sched_yield_supported()) { smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi; pr_info("KVM setup pv sched yield\n"); } @@ -700,7 +718,7 @@ static uint32_t __init kvm_detect(void) static void __init kvm_apic_init(void) { #if defined(CONFIG_SMP) - if (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI)) + if (pv_ipi_supported()) kvm_setup_pv_ipi(); #endif } @@ -732,26 +750,31 @@ static __init int activate_jump_labels(void) } arch_initcall(activate_jump_labels); -static __init int kvm_setup_pv_tlb_flush(void) +static __init int kvm_alloc_cpumask(void) { int cpu; + bool alloc = false; if (!kvm_para_available() || nopv) return 0; - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + if (pv_tlb_flush_supported()) + alloc = true; + +#if defined(CONFIG_SMP) + if (pv_ipi_supported()) + alloc = true; +#endif + + if (alloc) for_each_possible_cpu(cpu) { - zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), + zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu), GFP_KERNEL, cpu_to_node(cpu)); } - pr_info("KVM setup pv remote TLB flush\n"); - } return 0; } -arch_initcall(kvm_setup_pv_tlb_flush); +arch_initcall(kvm_alloc_cpumask); #ifdef CONFIG_PARAVIRT_SPINLOCKS diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 789f5e4f89de..c131ba4e70ef 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -30,6 +30,7 @@ #include <asm/timer.h> #include <asm/special_insns.h> #include <asm/tlb.h> +#include <asm/io_bitmap.h> /* * nop stub, which must not clobber anything *including the stack* to @@ -341,6 +342,10 @@ struct paravirt_patch_template pv_ops = { .cpu.iret = native_iret, .cpu.swapgs = native_swapgs, +#ifdef CONFIG_X86_IOPL_IOPERM + .cpu.update_io_bitmap = native_tss_update_io_bitmap, +#endif + .cpu.start_context_switch = paravirt_nop, .cpu.end_context_switch = paravirt_nop, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 839b5244e3b7..3053c85e0e42 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -374,7 +374,7 @@ static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm) /** * tss_update_io_bitmap - Update I/O bitmap before exiting to usermode */ -void tss_update_io_bitmap(void) +void native_tss_update_io_bitmap(void) { struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); struct thread_struct *t = ¤t->thread; diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index ef3ba99068d3..a4d9a261425b 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -9,6 +9,8 @@ #include <asm/kexec.h> #include <asm/processor-flags.h> #include <asm/pgtable_types.h> +#include <asm/nospec-branch.h> +#include <asm/unwind_hints.h> /* * Must be relocatable PIC code callable as a C function @@ -39,6 +41,7 @@ .align PAGE_SIZE .code64 SYM_CODE_START_NOALIGN(relocate_kernel) + UNWIND_HINT_EMPTY /* * %rdi indirection_page * %rsi page_list @@ -105,6 +108,7 @@ SYM_CODE_START_NOALIGN(relocate_kernel) SYM_CODE_END(relocate_kernel) SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) + UNWIND_HINT_EMPTY /* set return address to 0 if not preserving context */ pushq $0 /* store the start address on the stack */ @@ -192,14 +196,12 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) 1: popq %rdx leaq PAGE_SIZE(%r10), %rsp + ANNOTATE_RETPOLINE_SAFE call *%rdx /* get the re-entry point of the peer system */ movq 0(%rsp), %rbp - call 1f -1: - popq %r8 - subq $(1b - relocate_kernel), %r8 + leaq relocate_kernel(%rip), %r8 movq CP_PA_SWAP_PAGE(%r8), %r10 movq CP_PA_BACKUP_PAGES_MAP(%r8), %rdi movq CP_PA_TABLE_PAGE(%r8), %rax @@ -212,6 +214,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) SYM_CODE_END(identity_mapped) SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) + UNWIND_HINT_EMPTY movq RSP(%r8), %rsp movq CR4(%r8), %rax movq %rax, %cr4 @@ -233,6 +236,7 @@ SYM_CODE_END(virtual_mapped) /* Do the copies */ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) + UNWIND_HINT_EMPTY movq %rdi, %rcx /* Put the page_list in %rcx */ xorl %edi, %edi xorl %esi, %esi diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 69881b2d446c..d59525d2ead3 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -147,6 +147,8 @@ static inline void smpboot_restore_warm_reset_vector(void) *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; } +static void init_freq_invariance(void); + /* * Report back to the Boot Processor during boot time or to the caller processor * during CPU online. @@ -183,6 +185,8 @@ static void smp_callin(void) */ set_cpu_sibling_map(raw_smp_processor_id()); + init_freq_invariance(); + /* * Get our bogomips. * Update loops_per_jiffy in cpu_data. Previous call to @@ -466,7 +470,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) */ static const struct x86_cpu_id snc_cpu[] = { - { X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X }, + X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, NULL), {} }; @@ -1337,7 +1341,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_sched_topology(x86_topology); set_cpu_sibling_map(0); - + init_freq_invariance(); smp_sanity_check(); switch (apic_intr_mode) { @@ -1764,3 +1768,287 @@ void native_play_dead(void) } #endif + +/* + * APERF/MPERF frequency ratio computation. + * + * The scheduler wants to do frequency invariant accounting and needs a <1 + * ratio to account for the 'current' frequency, corresponding to + * freq_curr / freq_max. + * + * Since the frequency freq_curr on x86 is controlled by micro-controller and + * our P-state setting is little more than a request/hint, we need to observe + * the effective frequency 'BusyMHz', i.e. the average frequency over a time + * interval after discarding idle time. This is given by: + * + * BusyMHz = delta_APERF / delta_MPERF * freq_base + * + * where freq_base is the max non-turbo P-state. + * + * The freq_max term has to be set to a somewhat arbitrary value, because we + * can't know which turbo states will be available at a given point in time: + * it all depends on the thermal headroom of the entire package. We set it to + * the turbo level with 4 cores active. + * + * Benchmarks show that's a good compromise between the 1C turbo ratio + * (freq_curr/freq_max would rarely reach 1) and something close to freq_base, + * which would ignore the entire turbo range (a conspicuous part, making + * freq_curr/freq_max always maxed out). + * + * An exception to the heuristic above is the Atom uarch, where we choose the + * highest turbo level for freq_max since Atom's are generally oriented towards + * power efficiency. + * + * Setting freq_max to anything less than the 1C turbo ratio makes the ratio + * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1. + */ + +DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key); + +static DEFINE_PER_CPU(u64, arch_prev_aperf); +static DEFINE_PER_CPU(u64, arch_prev_mperf); +static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE; +static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE; + +void arch_set_max_freq_ratio(bool turbo_disabled) +{ + arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : + arch_turbo_freq_ratio; +} + +static bool turbo_disabled(void) +{ + u64 misc_en; + int err; + + err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en); + if (err) + return false; + + return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); +} + +static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) +{ + int err; + + err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq); + if (err) + return false; + + err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */ + *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */ + + return true; +} + +#include <asm/cpu_device_id.h> +#include <asm/intel-family.h> + +#define ICPU(model) \ + {X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF, 0} + +static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = { + ICPU(INTEL_FAM6_XEON_PHI_KNL), + ICPU(INTEL_FAM6_XEON_PHI_KNM), + {} +}; + +static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = { + ICPU(INTEL_FAM6_SKYLAKE_X), + {} +}; + +static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = { + ICPU(INTEL_FAM6_ATOM_GOLDMONT), + ICPU(INTEL_FAM6_ATOM_GOLDMONT_D), + ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS), + {} +}; + +static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, + int num_delta_fratio) +{ + int fratio, delta_fratio, found; + int err, i; + u64 msr; + + if (!x86_match_cpu(has_knl_turbo_ratio_limits)) + return false; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); + if (err) + return false; + + fratio = (msr >> 8) & 0xFF; + i = 16; + found = 0; + do { + if (found >= num_delta_fratio) { + *turbo_freq = fratio; + return true; + } + + delta_fratio = (msr >> (i + 5)) & 0x7; + + if (delta_fratio) { + found += 1; + fratio -= delta_fratio; + } + + i += 8; + } while (i < 64); + + return true; +} + +static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) +{ + u64 ratios, counts; + u32 group_size; + int err, i; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios); + if (err) + return false; + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts); + if (err) + return false; + + for (i = 0; i < 64; i += 8) { + group_size = (counts >> i) & 0xFF; + if (group_size >= size) { + *turbo_freq = (ratios >> i) & 0xFF; + return true; + } + } + + return false; +} + +static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) +{ + int err; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); + if (err) + return false; + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, turbo_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + *turbo_freq = (*turbo_freq >> 24) & 0xFF; /* 4C turbo */ + + return true; +} + +static bool intel_set_max_freq_ratio(void) +{ + u64 base_freq, turbo_freq; + + if (slv_set_max_freq_ratio(&base_freq, &turbo_freq)) + goto out; + + if (x86_match_cpu(has_glm_turbo_ratio_limits) && + skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) + goto out; + + if (knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) + goto out; + + if (x86_match_cpu(has_skx_turbo_ratio_limits) && + skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4)) + goto out; + + if (core_set_max_freq_ratio(&base_freq, &turbo_freq)) + goto out; + + return false; + +out: + arch_turbo_freq_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, + base_freq); + arch_set_max_freq_ratio(turbo_disabled()); + return true; +} + +static void init_counter_refs(void *arg) +{ + u64 aperf, mperf; + + rdmsrl(MSR_IA32_APERF, aperf); + rdmsrl(MSR_IA32_MPERF, mperf); + + this_cpu_write(arch_prev_aperf, aperf); + this_cpu_write(arch_prev_mperf, mperf); +} + +static void init_freq_invariance(void) +{ + bool ret = false; + + if (smp_processor_id() != 0 || !boot_cpu_has(X86_FEATURE_APERFMPERF)) + return; + + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + ret = intel_set_max_freq_ratio(); + + if (ret) { + on_each_cpu(init_counter_refs, NULL, 1); + static_branch_enable(&arch_scale_freq_key); + } else { + pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); + } +} + +DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; + +void arch_scale_freq_tick(void) +{ + u64 freq_scale; + u64 aperf, mperf; + u64 acnt, mcnt; + + if (!arch_scale_freq_invariant()) + return; + + rdmsrl(MSR_IA32_APERF, aperf); + rdmsrl(MSR_IA32_MPERF, mperf); + + acnt = aperf - this_cpu_read(arch_prev_aperf); + mcnt = mperf - this_cpu_read(arch_prev_mperf); + if (!mcnt) + return; + + this_cpu_write(arch_prev_aperf, aperf); + this_cpu_write(arch_prev_mperf, mperf); + + acnt <<= 2*SCHED_CAPACITY_SHIFT; + mcnt *= arch_max_freq_ratio; + + freq_scale = div64_u64(acnt, mcnt); + + if (freq_scale > SCHED_CAPACITY_SCALE) + freq_scale = SCHED_CAPACITY_SCALE; + + this_cpu_write(arch_freq_scale, freq_scale); +} diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index be5bc2e47c71..b8810ebbc8ae 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -59,39 +59,29 @@ __setup("cpu0_hotplug", enable_cpu0_hotplug); */ int _debug_hotplug_cpu(int cpu, int action) { - struct device *dev = get_cpu_device(cpu); int ret; if (!cpu_is_hotpluggable(cpu)) return -EINVAL; - lock_device_hotplug(); - switch (action) { case 0: - ret = cpu_down(cpu); - if (!ret) { + ret = remove_cpu(cpu); + if (!ret) pr_info("DEBUG_HOTPLUG_CPU0: CPU %u is now offline\n", cpu); - dev->offline = true; - kobject_uevent(&dev->kobj, KOBJ_OFFLINE); - } else + else pr_debug("Can't offline CPU%d.\n", cpu); break; case 1: - ret = cpu_up(cpu); - if (!ret) { - dev->offline = false; - kobject_uevent(&dev->kobj, KOBJ_ONLINE); - } else { + ret = add_cpu(cpu); + if (ret) pr_debug("Can't online CPU%d.\n", cpu); - } + break; default: ret = -EINVAL; } - unlock_device_hotplug(); - return ret; } diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index e0cbe4f2af49..bf528aae8ece 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -63,13 +63,13 @@ static const struct freq_desc freq_desc_lgm = { }; static const struct x86_cpu_id tsc_msr_cpu_ids[] = { - INTEL_CPU_FAM6(ATOM_SALTWELL_MID, freq_desc_pnw), - INTEL_CPU_FAM6(ATOM_SALTWELL_TABLET, freq_desc_clv), - INTEL_CPU_FAM6(ATOM_SILVERMONT, freq_desc_byt), - INTEL_CPU_FAM6(ATOM_SILVERMONT_MID, freq_desc_tng), - INTEL_CPU_FAM6(ATOM_AIRMONT, freq_desc_cht), - INTEL_CPU_FAM6(ATOM_AIRMONT_MID, freq_desc_ann), - INTEL_CPU_FAM6(ATOM_AIRMONT_NP, freq_desc_lgm), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL_MID, &freq_desc_pnw), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL_TABLET,&freq_desc_clv), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT, &freq_desc_byt), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID, &freq_desc_tng), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT, &freq_desc_cht), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT_MID, &freq_desc_ann), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT_NP, &freq_desc_lgm), {} }; |