diff options
Diffstat (limited to 'arch/x86/kernel')
53 files changed, 2463 insertions, 297 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 05110c1097ae..581386c7e429 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -75,7 +75,7 @@ apm-y := apm_32.o obj-$(CONFIG_APM) += apm.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SMP) += smpboot.o -obj-$(CONFIG_SMP) += tsc_sync.o +obj-$(CONFIG_X86_TSC) += tsc_sync.o obj-$(CONFIG_SMP) += setup_percpu.o obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-y += apic/ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4764fa56924d..64422f850e95 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -715,7 +715,7 @@ int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) int nid; nid = acpi_get_node(handle); - if (nid != -1) { + if (nid != NUMA_NO_NODE) { set_apicid_to_node(physid, nid); numa_set_node(cpu, nid); } @@ -930,6 +930,13 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table) x86_platform.legacy.devices.pnpbios = 0; } + if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && + !(acpi_gbl_FADT.boot_flags & ACPI_FADT_8042) && + x86_platform.legacy.i8042 != X86_LEGACY_I8042_PLATFORM_ABSENT) { + pr_debug("ACPI: i8042 controller is absent\n"); + x86_platform.legacy.i8042 = X86_LEGACY_I8042_FIRMWARE_ABSENT; + } + if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) { pr_debug("ACPI: not registering RTC platform device\n"); x86_platform.legacy.rtc = 0; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 5cb272a7a5a3..c5b8f760473c 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -337,7 +337,11 @@ done: n_dspl, (unsigned long)orig_insn + n_dspl + repl_len); } -static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr) +/* + * "noinline" to cause control flow change and thus invalidate I$ and + * cause refetch after modification. + */ +static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr) { unsigned long flags; @@ -346,7 +350,6 @@ static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr) local_irq_save(flags); add_nops(instr + (a->instrlen - a->padlen), a->padlen); - sync_core(); local_irq_restore(flags); DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ", @@ -359,9 +362,12 @@ static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr) * This implies that asymmetric systems where APs have less capabilities than * the boot processor are not handled. Tough. Make sure you disable such * features by hand. + * + * Marked "noinline" to cause control flow change and thus insn cache + * to refetch changed I$ lines. */ -void __init_or_module apply_alternatives(struct alt_instr *start, - struct alt_instr *end) +void __init_or_module noinline apply_alternatives(struct alt_instr *start, + struct alt_instr *end) { struct alt_instr *a; u8 *instr, *replacement; @@ -667,7 +673,6 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode, unsigned long flags; local_irq_save(flags); memcpy(addr, opcode, len); - sync_core(); local_irq_restore(flags); /* Could also do a CLFLUSH here to speed up CPU recovery; but that causes hangs on some VIA CPUs. */ diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 456316f6c868..65721dc73bd8 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -234,7 +234,7 @@ static __init int apbt_late_init(void) if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT || !apb_timer_block_enabled) return 0; - return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "X86_APB_DEAD", NULL, + return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "x86/apb:dead", NULL, apbt_cpu_dead); } fs_initcall(apbt_late_init); @@ -247,7 +247,7 @@ void apbt_setup_secondary_clock(void) {} static int apbt_clocksource_register(void) { u64 start, now; - cycle_t t1; + u64 t1; /* Start the counter, use timer 2 as source, timer 0/1 for event */ dw_apb_clocksource_start(clocksource_apbt); @@ -355,7 +355,7 @@ unsigned long apbt_quick_calibrate(void) { int i, scale; u64 old, new; - cycle_t t1, t2; + u64 t1, t2; unsigned long khz = 0; u32 loop, shift; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index bb47e5eacd44..5b7e43eff139 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2160,21 +2160,6 @@ int __generic_processor_info(int apicid, int version, bool enabled) } /* - * This can happen on physical hotplug. The sanity check at boot time - * is done from native_smp_prepare_cpus() after num_possible_cpus() is - * established. - */ - if (topology_update_package_map(apicid, cpu) < 0) { - int thiscpu = max + disabled_cpus; - - pr_warning("APIC: Package limit reached. Processor %d/0x%x ignored.\n", - thiscpu, apicid); - - disabled_cpus++; - return -ENOSPC; - } - - /* * Validate version */ if (version == 0x0) { diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 200af5ae9662..5a35f208ed95 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -191,7 +191,7 @@ static int x2apic_cluster_probe(void) if (!x2apic_mode) return 0; - ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE", + ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare", x2apic_prepare_cpu, x2apic_dead_cpu); if (ret < 0) { pr_err("Failed to register X2APIC_PREPARE\n"); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 643818a7688b..45d44c173cf9 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -234,7 +234,7 @@ #include <linux/i8253.h> #include <linux/cpuidle.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/desc.h> #include <asm/olpc.h> #include <asm/paravirt.h> diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 33b63670bf09..52000010c62e 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -32,6 +32,8 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o +obj-$(CONFIG_INTEL_RDT_A) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_schemata.o + obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_MICROCODE) += microcode/ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 71cae73a5076..1d3167269a67 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -309,15 +309,8 @@ static void amd_get_topology(struct cpuinfo_x86 *c) /* get information required for multi-node processors */ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - 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 = cpuid_ecx(0x8000001e) & 7; /* * We may have multiple LLCs if L3 caches exist, so check if we diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 729f92ba8224..9bab7a8a4293 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -667,13 +667,14 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_1_EDX] = edx; } + /* Thermal and Power Management Leaf: level 0x00000006 (eax) */ + if (c->cpuid_level >= 0x00000006) + c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006); + /* Additional Intel-defined flags: level 0x00000007 */ if (c->cpuid_level >= 0x00000007) { cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); - c->x86_capability[CPUID_7_0_EBX] = ebx; - - c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006); c->x86_capability[CPUID_7_ECX] = ecx; } @@ -979,29 +980,21 @@ static void x86_init_cache_qos(struct cpuinfo_x86 *c) } /* - * The physical to logical package id mapping is initialized from the - * acpi/mptables information. Make sure that CPUID actually agrees with - * that. + * Validate that ACPI/mptables have the same information about the + * effective APIC id and update the package map. */ -static void sanitize_package_id(struct cpuinfo_x86 *c) +static void validate_apic_and_package_id(struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP - unsigned int pkg, apicid, cpu = smp_processor_id(); + unsigned int apicid, cpu = smp_processor_id(); apicid = apic->cpu_present_to_apicid(cpu); - pkg = apicid >> boot_cpu_data.x86_coreid_bits; - if (apicid != c->initial_apicid) { - pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x CPUID: %x\n", + if (apicid != c->apicid) { + pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n", cpu, apicid, c->initial_apicid); - c->initial_apicid = apicid; - } - if (pkg != c->phys_proc_id) { - pr_err(FW_BUG "CPU%u: Using firmware package id %u instead of %u\n", - cpu, pkg, c->phys_proc_id); - c->phys_proc_id = pkg; } - c->logical_proc_id = topology_phys_to_logical_pkg(pkg); + BUG_ON(topology_update_package_map(c->phys_proc_id, cpu)); #else c->logical_proc_id = 0; #endif @@ -1132,7 +1125,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) #ifdef CONFIG_NUMA numa_add_cpu(smp_processor_id()); #endif - sanitize_package_id(c); } /* @@ -1187,6 +1179,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) enable_sep_cpu(); #endif mtrr_ap_init(); + validate_apic_and_package_id(c); } static __init int setup_noclflush(char *arg) @@ -1228,7 +1221,7 @@ 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/intel.c b/arch/x86/kernel/cpu/intel.c index fcd484d2bb03..203f860d2ab3 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: diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index be6337156502..0282b0df004a 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -153,6 +153,7 @@ struct _cpuid4_info_regs { union _cpuid4_leaf_eax eax; union _cpuid4_leaf_ebx ebx; union _cpuid4_leaf_ecx ecx; + unsigned int id; unsigned long size; struct amd_northbridge *nb; }; @@ -894,6 +895,8 @@ static void __cache_cpumap_setup(unsigned int cpu, int index, static void ci_leaf_init(struct cacheinfo *this_leaf, struct _cpuid4_info_regs *base) { + this_leaf->id = base->id; + this_leaf->attributes = CACHE_ID; this_leaf->level = base->eax.split.level; this_leaf->type = cache_type_map[base->eax.split.type]; this_leaf->coherency_line_size = @@ -920,6 +923,22 @@ static int __init_cache_level(unsigned int cpu) return 0; } +/* + * The max shared threads number comes from CPUID.4:EAX[25-14] with input + * ECX as cache index. Then right shift apicid by the number's order to get + * cache id for this cache node. + */ +static void get_cache_id(int cpu, struct _cpuid4_info_regs *id4_regs) +{ + struct cpuinfo_x86 *c = &cpu_data(cpu); + unsigned long num_threads_sharing; + int index_msb; + + num_threads_sharing = 1 + id4_regs->eax.split.num_threads_sharing; + index_msb = get_count_order(num_threads_sharing); + id4_regs->id = c->apicid >> index_msb; +} + static int __populate_cache_leaves(unsigned int cpu) { unsigned int idx, ret; @@ -931,6 +950,7 @@ static int __populate_cache_leaves(unsigned int cpu) ret = cpuid4_cache_lookup_regs(idx, &id4_regs); if (ret) return ret; + get_cache_id(cpu, &id4_regs); ci_leaf_init(this_leaf++, &id4_regs); __cache_cpumap_setup(cpu, idx, &id4_regs); } diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c new file mode 100644 index 000000000000..5a533fefefa0 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -0,0 +1,403 @@ +/* + * Resource Director Technology(RDT) + * - Cache Allocation code. + * + * Copyright (C) 2016 Intel Corporation + * + * Authors: + * Fenghua Yu <fenghua.yu@intel.com> + * Tony Luck <tony.luck@intel.com> + * Vikas Shivappa <vikas.shivappa@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual June 2016, volume 3, section 17.17. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/slab.h> +#include <linux/err.h> +#include <linux/cacheinfo.h> +#include <linux/cpuhotplug.h> + +#include <asm/intel-family.h> +#include <asm/intel_rdt.h> + +/* Mutex to protect rdtgroup access. */ +DEFINE_MUTEX(rdtgroup_mutex); + +DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid); + +#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains) + +struct rdt_resource rdt_resources_all[] = { + { + .name = "L3", + .domains = domain_init(RDT_RESOURCE_L3), + .msr_base = IA32_L3_CBM_BASE, + .min_cbm_bits = 1, + .cache_level = 3, + .cbm_idx_multi = 1, + .cbm_idx_offset = 0 + }, + { + .name = "L3DATA", + .domains = domain_init(RDT_RESOURCE_L3DATA), + .msr_base = IA32_L3_CBM_BASE, + .min_cbm_bits = 1, + .cache_level = 3, + .cbm_idx_multi = 2, + .cbm_idx_offset = 0 + }, + { + .name = "L3CODE", + .domains = domain_init(RDT_RESOURCE_L3CODE), + .msr_base = IA32_L3_CBM_BASE, + .min_cbm_bits = 1, + .cache_level = 3, + .cbm_idx_multi = 2, + .cbm_idx_offset = 1 + }, + { + .name = "L2", + .domains = domain_init(RDT_RESOURCE_L2), + .msr_base = IA32_L2_CBM_BASE, + .min_cbm_bits = 1, + .cache_level = 2, + .cbm_idx_multi = 1, + .cbm_idx_offset = 0 + }, +}; + +static int cbm_idx(struct rdt_resource *r, int closid) +{ + return closid * r->cbm_idx_multi + r->cbm_idx_offset; +} + +/* + * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs + * as they do not have CPUID enumeration support for Cache allocation. + * The check for Vendor/Family/Model is not enough to guarantee that + * the MSRs won't #GP fault because only the following SKUs support + * CAT: + * Intel(R) Xeon(R) CPU E5-2658 v3 @ 2.20GHz + * Intel(R) Xeon(R) CPU E5-2648L v3 @ 1.80GHz + * Intel(R) Xeon(R) CPU E5-2628L v3 @ 2.00GHz + * Intel(R) Xeon(R) CPU E5-2618L v3 @ 2.30GHz + * Intel(R) Xeon(R) CPU E5-2608L v3 @ 2.00GHz + * Intel(R) Xeon(R) CPU E5-2658A v3 @ 2.20GHz + * + * Probe by trying to write the first of the L3 cach mask registers + * and checking that the bits stick. Max CLOSids is always 4 and max cbm length + * is always 20 on hsw server parts. The minimum cache bitmask length + * allowed for HSW server is always 2 bits. Hardcode all of them. + */ +static inline bool cache_alloc_hsw_probe(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + boot_cpu_data.x86 == 6 && + boot_cpu_data.x86_model == INTEL_FAM6_HASWELL_X) { + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + u32 l, h, max_cbm = BIT_MASK(20) - 1; + + if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0)) + return false; + rdmsr(IA32_L3_CBM_BASE, l, h); + + /* If all the bits were set in MSR, return success */ + if (l != max_cbm) + return false; + + r->num_closid = 4; + r->cbm_len = 20; + r->max_cbm = max_cbm; + r->min_cbm_bits = 2; + r->capable = true; + r->enabled = true; + + return true; + } + + return false; +} + +static void rdt_get_config(int idx, struct rdt_resource *r) +{ + union cpuid_0x10_1_eax eax; + union cpuid_0x10_1_edx edx; + u32 ebx, ecx; + + cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full); + r->num_closid = edx.split.cos_max + 1; + r->cbm_len = eax.split.cbm_len + 1; + r->max_cbm = BIT_MASK(eax.split.cbm_len + 1) - 1; + r->capable = true; + r->enabled = true; +} + +static void rdt_get_cdp_l3_config(int type) +{ + struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3]; + struct rdt_resource *r = &rdt_resources_all[type]; + + r->num_closid = r_l3->num_closid / 2; + r->cbm_len = r_l3->cbm_len; + r->max_cbm = r_l3->max_cbm; + r->capable = true; + /* + * By default, CDP is disabled. CDP can be enabled by mount parameter + * "cdp" during resctrl file system mount time. + */ + r->enabled = false; +} + +static inline bool get_rdt_resources(void) +{ + bool ret = false; + + if (cache_alloc_hsw_probe()) + return true; + + if (!boot_cpu_has(X86_FEATURE_RDT_A)) + return false; + + if (boot_cpu_has(X86_FEATURE_CAT_L3)) { + rdt_get_config(1, &rdt_resources_all[RDT_RESOURCE_L3]); + if (boot_cpu_has(X86_FEATURE_CDP_L3)) { + rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA); + rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE); + } + ret = true; + } + if (boot_cpu_has(X86_FEATURE_CAT_L2)) { + /* CPUID 0x10.2 fields are same format at 0x10.1 */ + rdt_get_config(2, &rdt_resources_all[RDT_RESOURCE_L2]); + ret = true; + } + + return ret; +} + +static int get_cache_id(int cpu, int level) +{ + struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu); + int i; + + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == level) + return ci->info_list[i].id; + } + + return -1; +} + +void rdt_cbm_update(void *arg) +{ + struct msr_param *m = (struct msr_param *)arg; + struct rdt_resource *r = m->res; + int i, cpu = smp_processor_id(); + struct rdt_domain *d; + + list_for_each_entry(d, &r->domains, list) { + /* Find the domain that contains this CPU */ + if (cpumask_test_cpu(cpu, &d->cpu_mask)) + goto found; + } + pr_info_once("cpu %d not found in any domain for resource %s\n", + cpu, r->name); + + return; + +found: + for (i = m->low; i < m->high; i++) { + int idx = cbm_idx(r, i); + + wrmsrl(r->msr_base + idx, d->cbm[i]); + } +} + +/* + * rdt_find_domain - Find a domain in a resource that matches input resource id + * + * Search resource r's domain list to find the resource id. If the resource + * id is found in a domain, return the domain. Otherwise, if requested by + * caller, return the first domain whose id is bigger than the input id. + * The domain list is sorted by id in ascending order. + */ +static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, + struct list_head **pos) +{ + struct rdt_domain *d; + struct list_head *l; + + if (id < 0) + return ERR_PTR(id); + + list_for_each(l, &r->domains) { + d = list_entry(l, struct rdt_domain, list); + /* When id is found, return its domain. */ + if (id == d->id) + return d; + /* Stop searching when finding id's position in sorted list. */ + if (id < d->id) + break; + } + + if (pos) + *pos = l; + + return NULL; +} + +/* + * domain_add_cpu - Add a cpu to a resource's domain list. + * + * If an existing domain in the resource r's domain list matches the cpu's + * resource id, add the cpu in the domain. + * + * Otherwise, a new domain is allocated and inserted into the right position + * in the domain list sorted by id in ascending order. + * + * The order in the domain list is visible to users when we print entries + * in the schemata file and schemata input is validated to have the same order + * as this list. + */ +static void domain_add_cpu(int cpu, struct rdt_resource *r) +{ + int i, id = get_cache_id(cpu, r->cache_level); + struct list_head *add_pos = NULL; + struct rdt_domain *d; + + d = rdt_find_domain(r, id, &add_pos); + if (IS_ERR(d)) { + pr_warn("Could't find cache id for cpu %d\n", cpu); + return; + } + + if (d) { + cpumask_set_cpu(cpu, &d->cpu_mask); + return; + } + + d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu)); + if (!d) + return; + + d->id = id; + + d->cbm = kmalloc_array(r->num_closid, sizeof(*d->cbm), GFP_KERNEL); + if (!d->cbm) { + kfree(d); + return; + } + + for (i = 0; i < r->num_closid; i++) { + int idx = cbm_idx(r, i); + + d->cbm[i] = r->max_cbm; + wrmsrl(r->msr_base + idx, d->cbm[i]); + } + + cpumask_set_cpu(cpu, &d->cpu_mask); + list_add_tail(&d->list, add_pos); + r->num_domains++; +} + +static void domain_remove_cpu(int cpu, struct rdt_resource *r) +{ + int id = get_cache_id(cpu, r->cache_level); + struct rdt_domain *d; + + d = rdt_find_domain(r, id, NULL); + if (IS_ERR_OR_NULL(d)) { + pr_warn("Could't find cache id for cpu %d\n", cpu); + return; + } + + cpumask_clear_cpu(cpu, &d->cpu_mask); + if (cpumask_empty(&d->cpu_mask)) { + r->num_domains--; + kfree(d->cbm); + list_del(&d->list); + kfree(d); + } +} + +static void clear_closid(int cpu) +{ + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + + per_cpu(cpu_closid, cpu) = 0; + state->closid = 0; + wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, 0); +} + +static int intel_rdt_online_cpu(unsigned int cpu) +{ + struct rdt_resource *r; + + mutex_lock(&rdtgroup_mutex); + for_each_capable_rdt_resource(r) + domain_add_cpu(cpu, r); + /* The cpu is set in default rdtgroup after online. */ + cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); + clear_closid(cpu); + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +static int intel_rdt_offline_cpu(unsigned int cpu) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + + mutex_lock(&rdtgroup_mutex); + for_each_capable_rdt_resource(r) + domain_remove_cpu(cpu, r); + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) + break; + } + clear_closid(cpu); + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +static int __init intel_rdt_late_init(void) +{ + struct rdt_resource *r; + int state, ret; + + if (!get_rdt_resources()) + return -ENODEV; + + state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "x86/rdt/cat:online:", + intel_rdt_online_cpu, intel_rdt_offline_cpu); + if (state < 0) + return state; + + ret = rdtgroup_init(); + if (ret) { + cpuhp_remove_state(state); + return ret; + } + + for_each_capable_rdt_resource(r) + pr_info("Intel RDT %s allocation detected\n", r->name); + + return 0; +} + +late_initcall(intel_rdt_late_init); diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c new file mode 100644 index 000000000000..8af04afdfcb9 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -0,0 +1,1115 @@ +/* + * User interface for Resource Alloction in Resource Director Technology(RDT) + * + * Copyright (C) 2016 Intel Corporation + * + * Author: Fenghua Yu <fenghua.yu@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/cpu.h> +#include <linux/fs.h> +#include <linux/sysfs.h> +#include <linux/kernfs.h> +#include <linux/seq_file.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/cpu.h> +#include <linux/task_work.h> + +#include <uapi/linux/magic.h> + +#include <asm/intel_rdt.h> +#include <asm/intel_rdt_common.h> + +DEFINE_STATIC_KEY_FALSE(rdt_enable_key); +struct kernfs_root *rdt_root; +struct rdtgroup rdtgroup_default; +LIST_HEAD(rdt_all_groups); + +/* Kernel fs node for "info" directory under root */ +static struct kernfs_node *kn_info; + +/* + * Trivial allocator for CLOSIDs. Since h/w only supports a small number, + * we can keep a bitmap of free CLOSIDs in a single integer. + * + * Using a global CLOSID across all resources has some advantages and + * some drawbacks: + * + We can simply set "current->closid" to assign a task to a resource + * group. + * + Context switch code can avoid extra memory references deciding which + * CLOSID to load into the PQR_ASSOC MSR + * - We give up some options in configuring resource groups across multi-socket + * systems. + * - Our choices on how to configure each resource become progressively more + * limited as the number of resources grows. + */ +static int closid_free_map; + +static void closid_init(void) +{ + struct rdt_resource *r; + int rdt_min_closid = 32; + + /* Compute rdt_min_closid across all resources */ + for_each_enabled_rdt_resource(r) + rdt_min_closid = min(rdt_min_closid, r->num_closid); + + closid_free_map = BIT_MASK(rdt_min_closid) - 1; + + /* CLOSID 0 is always reserved for the default group */ + closid_free_map &= ~1; +} + +int closid_alloc(void) +{ + int closid = ffs(closid_free_map); + + if (closid == 0) + return -ENOSPC; + closid--; + closid_free_map &= ~(1 << closid); + + return closid; +} + +static void closid_free(int closid) +{ + closid_free_map |= 1 << closid; +} + +/* set uid and gid of rdtgroup dirs and files to that of the creator */ +static int rdtgroup_kn_set_ugid(struct kernfs_node *kn) +{ + struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = current_fsuid(), + .ia_gid = current_fsgid(), }; + + if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) && + gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID)) + return 0; + + return kernfs_setattr(kn, &iattr); +} + +static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft) +{ + struct kernfs_node *kn; + int ret; + + kn = __kernfs_create_file(parent_kn, rft->name, rft->mode, + 0, rft->kf_ops, rft, NULL, NULL); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) { + kernfs_remove(kn); + return ret; + } + + return 0; +} + +static int rdtgroup_add_files(struct kernfs_node *kn, struct rftype *rfts, + int len) +{ + struct rftype *rft; + int ret; + + lockdep_assert_held(&rdtgroup_mutex); + + for (rft = rfts; rft < rfts + len; rft++) { + ret = rdtgroup_add_file(kn, rft); + if (ret) + goto error; + } + + return 0; +error: + pr_warn("Failed to add %s, err=%d\n", rft->name, ret); + while (--rft >= rfts) + kernfs_remove_by_name(kn, rft->name); + return ret; +} + +static int rdtgroup_seqfile_show(struct seq_file *m, void *arg) +{ + struct kernfs_open_file *of = m->private; + struct rftype *rft = of->kn->priv; + + if (rft->seq_show) + return rft->seq_show(of, m, arg); + return 0; +} + +static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct rftype *rft = of->kn->priv; + + if (rft->write) + return rft->write(of, buf, nbytes, off); + + return -EINVAL; +} + +static struct kernfs_ops rdtgroup_kf_single_ops = { + .atomic_write_len = PAGE_SIZE, + .write = rdtgroup_file_write, + .seq_show = rdtgroup_seqfile_show, +}; + +static int rdtgroup_cpus_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + + if (rdtgrp) + seq_printf(s, "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask)); + else + ret = -ENOENT; + rdtgroup_kn_unlock(of->kn); + + return ret; +} + +/* + * This is safe against intel_rdt_sched_in() called from __switch_to() + * because __switch_to() is executed with interrupts disabled. A local call + * from rdt_update_closid() is proteced against __switch_to() because + * preemption is disabled. + */ +static void rdt_update_cpu_closid(void *closid) +{ + if (closid) + this_cpu_write(cpu_closid, *(int *)closid); + /* + * We cannot unconditionally write the MSR because the current + * executing task might have its own closid selected. Just reuse + * the context switch code. + */ + intel_rdt_sched_in(); +} + +/* + * Update the PGR_ASSOC MSR on all cpus in @cpu_mask, + * + * Per task closids must have been set up before calling this function. + * + * The per cpu closids are updated with the smp function call, when @closid + * is not NULL. If @closid is NULL then all affected percpu closids must + * have been set up before calling this function. + */ +static void +rdt_update_closid(const struct cpumask *cpu_mask, int *closid) +{ + int cpu = get_cpu(); + + if (cpumask_test_cpu(cpu, cpu_mask)) + rdt_update_cpu_closid(closid); + smp_call_function_many(cpu_mask, rdt_update_cpu_closid, closid, 1); + put_cpu(); +} + +static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + cpumask_var_t tmpmask, newmask; + struct rdtgroup *rdtgrp, *r; + int ret; + + if (!buf) + return -EINVAL; + + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) + return -ENOMEM; + if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) { + free_cpumask_var(tmpmask); + return -ENOMEM; + } + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + ret = -ENOENT; + goto unlock; + } + + ret = cpumask_parse(buf, newmask); + if (ret) + goto unlock; + + /* check that user didn't specify any offline cpus */ + cpumask_andnot(tmpmask, newmask, cpu_online_mask); + if (cpumask_weight(tmpmask)) { + ret = -EINVAL; + goto unlock; + } + + /* Check whether cpus are dropped from this group */ + cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); + if (cpumask_weight(tmpmask)) { + /* Can't drop from default group */ + if (rdtgrp == &rdtgroup_default) { + ret = -EINVAL; + goto unlock; + } + /* Give any dropped cpus to rdtgroup_default */ + cpumask_or(&rdtgroup_default.cpu_mask, + &rdtgroup_default.cpu_mask, tmpmask); + rdt_update_closid(tmpmask, &rdtgroup_default.closid); + } + + /* + * If we added cpus, remove them from previous group that owned them + * and update per-cpu closid + */ + cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); + if (cpumask_weight(tmpmask)) { + list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { + if (r == rdtgrp) + continue; + cpumask_andnot(&r->cpu_mask, &r->cpu_mask, tmpmask); + } + rdt_update_closid(tmpmask, &rdtgrp->closid); + } + + /* Done pushing/pulling - update this group with new mask */ + cpumask_copy(&rdtgrp->cpu_mask, newmask); + +unlock: + rdtgroup_kn_unlock(of->kn); + free_cpumask_var(tmpmask); + free_cpumask_var(newmask); + + return ret ?: nbytes; +} + +struct task_move_callback { + struct callback_head work; + struct rdtgroup *rdtgrp; +}; + +static void move_myself(struct callback_head *head) +{ + struct task_move_callback *callback; + struct rdtgroup *rdtgrp; + + callback = container_of(head, struct task_move_callback, work); + rdtgrp = callback->rdtgrp; + + /* + * If resource group was deleted before this task work callback + * was invoked, then assign the task to root group and free the + * resource group. + */ + if (atomic_dec_and_test(&rdtgrp->waitcount) && + (rdtgrp->flags & RDT_DELETED)) { + current->closid = 0; + kfree(rdtgrp); + } + + preempt_disable(); + /* update PQR_ASSOC MSR to make resource group go into effect */ + intel_rdt_sched_in(); + preempt_enable(); + + kfree(callback); +} + +static int __rdtgroup_move_task(struct task_struct *tsk, + struct rdtgroup *rdtgrp) +{ + struct task_move_callback *callback; + int ret; + + callback = kzalloc(sizeof(*callback), GFP_KERNEL); + if (!callback) + return -ENOMEM; + callback->work.func = move_myself; + callback->rdtgrp = rdtgrp; + + /* + * Take a refcount, so rdtgrp cannot be freed before the + * callback has been invoked. + */ + atomic_inc(&rdtgrp->waitcount); + ret = task_work_add(tsk, &callback->work, true); + if (ret) { + /* + * Task is exiting. Drop the refcount and free the callback. + * No need to check the refcount as the group cannot be + * deleted before the write function unlocks rdtgroup_mutex. + */ + atomic_dec(&rdtgrp->waitcount); + kfree(callback); + } else { + tsk->closid = rdtgrp->closid; + } + return ret; +} + +static int rdtgroup_task_write_permission(struct task_struct *task, + struct kernfs_open_file *of) +{ + const struct cred *tcred = get_task_cred(task); + const struct cred *cred = current_cred(); + int ret = 0; + + /* + * Even if we're attaching all tasks in the thread group, we only + * need to check permissions on one of them. + */ + if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && + !uid_eq(cred->euid, tcred->uid) && + !uid_eq(cred->euid, tcred->suid)) + ret = -EPERM; + + put_cred(tcred); + return ret; +} + +static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp, + struct kernfs_open_file *of) +{ + struct task_struct *tsk; + int ret; + + rcu_read_lock(); + if (pid) { + tsk = find_task_by_vpid(pid); + if (!tsk) { + rcu_read_unlock(); + return -ESRCH; + } + } else { + tsk = current; + } + + get_task_struct(tsk); + rcu_read_unlock(); + + ret = rdtgroup_task_write_permission(tsk, of); + if (!ret) + ret = __rdtgroup_move_task(tsk, rdtgrp); + + put_task_struct(tsk); + return ret; +} + +static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + pid_t pid; + + if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) + return -EINVAL; + rdtgrp = rdtgroup_kn_lock_live(of->kn); + + if (rdtgrp) + ret = rdtgroup_move_task(pid, rdtgrp, of); + else + ret = -ENOENT; + + rdtgroup_kn_unlock(of->kn); + + return ret ?: nbytes; +} + +static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s) +{ + struct task_struct *p, *t; + + rcu_read_lock(); + for_each_process_thread(p, t) { + if (t->closid == r->closid) + seq_printf(s, "%d\n", t->pid); + } + rcu_read_unlock(); +} + +static int rdtgroup_tasks_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (rdtgrp) + show_rdt_tasks(rdtgrp, s); + else + ret = -ENOENT; + rdtgroup_kn_unlock(of->kn); + + return ret; +} + +/* Files in each rdtgroup */ +static struct rftype rdtgroup_base_files[] = { + { + .name = "cpus", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_cpus_write, + .seq_show = rdtgroup_cpus_show, + }, + { + .name = "tasks", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_tasks_write, + .seq_show = rdtgroup_tasks_show, + }, + { + .name = "schemata", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_schemata_write, + .seq_show = rdtgroup_schemata_show, + }, +}; + +static int rdt_num_closids_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%d\n", r->num_closid); + + return 0; +} + +static int rdt_cbm_mask_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%x\n", r->max_cbm); + + return 0; +} + +static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%d\n", r->min_cbm_bits); + + return 0; +} + +/* rdtgroup information files for one cache resource. */ +static struct rftype res_info_files[] = { + { + .name = "num_closids", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_num_closids_show, + }, + { + .name = "cbm_mask", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_cbm_mask_show, + }, + { + .name = "min_cbm_bits", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_min_cbm_bits_show, + }, +}; + +static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) +{ + struct kernfs_node *kn_subdir; + struct rdt_resource *r; + int ret; + + /* create the directory */ + kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); + if (IS_ERR(kn_info)) + return PTR_ERR(kn_info); + kernfs_get(kn_info); + + for_each_enabled_rdt_resource(r) { + kn_subdir = kernfs_create_dir(kn_info, r->name, + kn_info->mode, r); + if (IS_ERR(kn_subdir)) { + ret = PTR_ERR(kn_subdir); + goto out_destroy; + } + kernfs_get(kn_subdir); + ret = rdtgroup_kn_set_ugid(kn_subdir); + if (ret) + goto out_destroy; + ret = rdtgroup_add_files(kn_subdir, res_info_files, + ARRAY_SIZE(res_info_files)); + if (ret) + goto out_destroy; + kernfs_activate(kn_subdir); + } + + /* + * This extra ref will be put in kernfs_remove() and guarantees + * that @rdtgrp->kn is always accessible. + */ + kernfs_get(kn_info); + + ret = rdtgroup_kn_set_ugid(kn_info); + if (ret) + goto out_destroy; + + kernfs_activate(kn_info); + + return 0; + +out_destroy: + kernfs_remove(kn_info); + return ret; +} + +static void l3_qos_cfg_update(void *arg) +{ + bool *enable = arg; + + wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL); +} + +static int set_l3_qos_cfg(struct rdt_resource *r, bool enable) +{ + cpumask_var_t cpu_mask; + struct rdt_domain *d; + int cpu; + + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + + list_for_each_entry(d, &r->domains, list) { + /* Pick one CPU from each domain instance to update MSR */ + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + } + cpu = get_cpu(); + /* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */ + if (cpumask_test_cpu(cpu, cpu_mask)) + l3_qos_cfg_update(&enable); + /* Update QOS_CFG MSR on all other cpus in cpu_mask. */ + smp_call_function_many(cpu_mask, l3_qos_cfg_update, &enable, 1); + put_cpu(); + + free_cpumask_var(cpu_mask); + + return 0; +} + +static int cdp_enable(void) +{ + struct rdt_resource *r_l3data = &rdt_resources_all[RDT_RESOURCE_L3DATA]; + struct rdt_resource *r_l3code = &rdt_resources_all[RDT_RESOURCE_L3CODE]; + struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3]; + int ret; + + if (!r_l3->capable || !r_l3data->capable || !r_l3code->capable) + return -EINVAL; + + ret = set_l3_qos_cfg(r_l3, true); + if (!ret) { + r_l3->enabled = false; + r_l3data->enabled = true; + r_l3code->enabled = true; + } + return ret; +} + +static void cdp_disable(void) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + + r->enabled = r->capable; + + if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) { + rdt_resources_all[RDT_RESOURCE_L3DATA].enabled = false; + rdt_resources_all[RDT_RESOURCE_L3CODE].enabled = false; + set_l3_qos_cfg(r, false); + } +} + +static int parse_rdtgroupfs_options(char *data) +{ + char *token, *o = data; + int ret = 0; + + while ((token = strsep(&o, ",")) != NULL) { + if (!*token) + return -EINVAL; + + if (!strcmp(token, "cdp")) + ret = cdp_enable(); + } + + return ret; +} + +/* + * We don't allow rdtgroup directories to be created anywhere + * except the root directory. Thus when looking for the rdtgroup + * structure for a kernfs node we are either looking at a directory, + * in which case the rdtgroup structure is pointed at by the "priv" + * field, otherwise we have a file, and need only look to the parent + * to find the rdtgroup. + */ +static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn) +{ + if (kernfs_type(kn) == KERNFS_DIR) { + /* + * All the resource directories use "kn->priv" + * to point to the "struct rdtgroup" for the + * resource. "info" and its subdirectories don't + * have rdtgroup structures, so return NULL here. + */ + if (kn == kn_info || kn->parent == kn_info) + return NULL; + else + return kn->priv; + } else { + return kn->parent->priv; + } +} + +struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) +{ + struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn); + + if (!rdtgrp) + return NULL; + + atomic_inc(&rdtgrp->waitcount); + kernfs_break_active_protection(kn); + + mutex_lock(&rdtgroup_mutex); + + /* Was this group deleted while we waited? */ + if (rdtgrp->flags & RDT_DELETED) + return NULL; + + return rdtgrp; +} + +void rdtgroup_kn_unlock(struct kernfs_node *kn) +{ + struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn); + + if (!rdtgrp) + return; + + mutex_unlock(&rdtgroup_mutex); + + if (atomic_dec_and_test(&rdtgrp->waitcount) && + (rdtgrp->flags & RDT_DELETED)) { + kernfs_unbreak_active_protection(kn); + kernfs_put(kn); + kfree(rdtgrp); + } else { + kernfs_unbreak_active_protection(kn); + } +} + +static struct dentry *rdt_mount(struct file_system_type *fs_type, + int flags, const char *unused_dev_name, + void *data) +{ + struct dentry *dentry; + int ret; + + mutex_lock(&rdtgroup_mutex); + /* + * resctrl file system can only be mounted once. + */ + if (static_branch_unlikely(&rdt_enable_key)) { + dentry = ERR_PTR(-EBUSY); + goto out; + } + + ret = parse_rdtgroupfs_options(data); + if (ret) { + dentry = ERR_PTR(ret); + goto out_cdp; + } + + closid_init(); + + ret = rdtgroup_create_info_dir(rdtgroup_default.kn); + if (ret) { + dentry = ERR_PTR(ret); + goto out_cdp; + } + + dentry = kernfs_mount(fs_type, flags, rdt_root, + RDTGROUP_SUPER_MAGIC, NULL); + if (IS_ERR(dentry)) + goto out_cdp; + + static_branch_enable(&rdt_enable_key); + goto out; + +out_cdp: + cdp_disable(); +out: + mutex_unlock(&rdtgroup_mutex); + + return dentry; +} + +static int reset_all_cbms(struct rdt_resource *r) +{ + struct msr_param msr_param; + cpumask_var_t cpu_mask; + struct rdt_domain *d; + int i, cpu; + + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + + msr_param.res = r; + msr_param.low = 0; + msr_param.high = r->num_closid; + + /* + * Disable resource control for this resource by setting all + * CBMs in all domains to the maximum mask value. Pick one CPU + * from each domain to update the MSRs below. + */ + list_for_each_entry(d, &r->domains, list) { + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + + for (i = 0; i < r->num_closid; i++) + d->cbm[i] = r->max_cbm; + } + cpu = get_cpu(); + /* Update CBM on this cpu if it's in cpu_mask. */ + if (cpumask_test_cpu(cpu, cpu_mask)) + rdt_cbm_update(&msr_param); + /* Update CBM on all other cpus in cpu_mask. */ + smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1); + put_cpu(); + + free_cpumask_var(cpu_mask); + + return 0; +} + +/* + * Move tasks from one to the other group. If @from is NULL, then all tasks + * in the systems are moved unconditionally (used for teardown). + * + * If @mask is not NULL the cpus on which moved tasks are running are set + * in that mask so the update smp function call is restricted to affected + * cpus. + */ +static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, + struct cpumask *mask) +{ + struct task_struct *p, *t; + + read_lock(&tasklist_lock); + for_each_process_thread(p, t) { + if (!from || t->closid == from->closid) { + t->closid = to->closid; +#ifdef CONFIG_SMP + /* + * This is safe on x86 w/o barriers as the ordering + * of writing to task_cpu() and t->on_cpu is + * reverse to the reading here. The detection is + * inaccurate as tasks might move or schedule + * before the smp function call takes place. In + * such a case the function call is pointless, but + * there is no other side effect. + */ + if (mask && t->on_cpu) + cpumask_set_cpu(task_cpu(t), mask); +#endif + } + } + read_unlock(&tasklist_lock); +} + +/* + * Forcibly remove all of subdirectories under root. + */ +static void rmdir_all_sub(void) +{ + struct rdtgroup *rdtgrp, *tmp; + + /* Move all tasks to the default resource group */ + rdt_move_group_tasks(NULL, &rdtgroup_default, NULL); + + list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) { + /* Remove each rdtgroup other than root */ + if (rdtgrp == &rdtgroup_default) + continue; + + /* + * Give any CPUs back to the default group. We cannot copy + * cpu_online_mask because a CPU might have executed the + * offline callback already, but is still marked online. + */ + cpumask_or(&rdtgroup_default.cpu_mask, + &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); + + kernfs_remove(rdtgrp->kn); + list_del(&rdtgrp->rdtgroup_list); + kfree(rdtgrp); + } + /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ + get_online_cpus(); + rdt_update_closid(cpu_online_mask, &rdtgroup_default.closid); + put_online_cpus(); + + kernfs_remove(kn_info); +} + +static void rdt_kill_sb(struct super_block *sb) +{ + struct rdt_resource *r; + + mutex_lock(&rdtgroup_mutex); + + /*Put everything back to default values. */ + for_each_enabled_rdt_resource(r) + reset_all_cbms(r); + cdp_disable(); + rmdir_all_sub(); + static_branch_disable(&rdt_enable_key); + kernfs_kill_sb(sb); + mutex_unlock(&rdtgroup_mutex); +} + +static struct file_system_type rdt_fs_type = { + .name = "resctrl", + .mount = rdt_mount, + .kill_sb = rdt_kill_sb, +}; + +static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, + umode_t mode) +{ + struct rdtgroup *parent, *rdtgrp; + struct kernfs_node *kn; + int ret, closid; + + /* Only allow mkdir in the root directory */ + if (parent_kn != rdtgroup_default.kn) + return -EPERM; + + /* Do not accept '\n' to avoid unparsable situation. */ + if (strchr(name, '\n')) + return -EINVAL; + + parent = rdtgroup_kn_lock_live(parent_kn); + if (!parent) { + ret = -ENODEV; + goto out_unlock; + } + + ret = closid_alloc(); + if (ret < 0) + goto out_unlock; + closid = ret; + + /* allocate the rdtgroup. */ + rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL); + if (!rdtgrp) { + ret = -ENOSPC; + goto out_closid_free; + } + rdtgrp->closid = closid; + list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); + + /* kernfs creates the directory for rdtgrp */ + kn = kernfs_create_dir(parent->kn, name, mode, rdtgrp); + if (IS_ERR(kn)) { + ret = PTR_ERR(kn); + goto out_cancel_ref; + } + rdtgrp->kn = kn; + + /* + * kernfs_remove() will drop the reference count on "kn" which + * will free it. But we still need it to stick around for the + * rdtgroup_kn_unlock(kn} call below. Take one extra reference + * here, which will be dropped inside rdtgroup_kn_unlock(). + */ + kernfs_get(kn); + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + ret = rdtgroup_add_files(kn, rdtgroup_base_files, + ARRAY_SIZE(rdtgroup_base_files)); + if (ret) + goto out_destroy; + + kernfs_activate(kn); + + ret = 0; + goto out_unlock; + +out_destroy: + kernfs_remove(rdtgrp->kn); +out_cancel_ref: + list_del(&rdtgrp->rdtgroup_list); + kfree(rdtgrp); +out_closid_free: + closid_free(closid); +out_unlock: + rdtgroup_kn_unlock(parent_kn); + return ret; +} + +static int rdtgroup_rmdir(struct kernfs_node *kn) +{ + int ret, cpu, closid = rdtgroup_default.closid; + struct rdtgroup *rdtgrp; + cpumask_var_t tmpmask; + + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) + return -ENOMEM; + + rdtgrp = rdtgroup_kn_lock_live(kn); + if (!rdtgrp) { + ret = -EPERM; + goto out; + } + + /* Give any tasks back to the default group */ + rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask); + + /* Give any CPUs back to the default group */ + cpumask_or(&rdtgroup_default.cpu_mask, + &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); + + /* Update per cpu closid of the moved CPUs first */ + for_each_cpu(cpu, &rdtgrp->cpu_mask) + per_cpu(cpu_closid, cpu) = closid; + /* + * Update the MSR on moved CPUs and CPUs which have moved + * task running on them. + */ + cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); + rdt_update_closid(tmpmask, NULL); + + rdtgrp->flags = RDT_DELETED; + closid_free(rdtgrp->closid); + list_del(&rdtgrp->rdtgroup_list); + + /* + * one extra hold on this, will drop when we kfree(rdtgrp) + * in rdtgroup_kn_unlock() + */ + kernfs_get(kn); + kernfs_remove(rdtgrp->kn); + ret = 0; +out: + rdtgroup_kn_unlock(kn); + free_cpumask_var(tmpmask); + return ret; +} + +static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) +{ + if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) + seq_puts(seq, ",cdp"); + return 0; +} + +static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = { + .mkdir = rdtgroup_mkdir, + .rmdir = rdtgroup_rmdir, + .show_options = rdtgroup_show_options, +}; + +static int __init rdtgroup_setup_root(void) +{ + int ret; + + rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops, + KERNFS_ROOT_CREATE_DEACTIVATED, + &rdtgroup_default); + if (IS_ERR(rdt_root)) + return PTR_ERR(rdt_root); + + mutex_lock(&rdtgroup_mutex); + + rdtgroup_default.closid = 0; + list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); + + ret = rdtgroup_add_files(rdt_root->kn, rdtgroup_base_files, + ARRAY_SIZE(rdtgroup_base_files)); + if (ret) { + kernfs_destroy_root(rdt_root); + goto out; + } + + rdtgroup_default.kn = rdt_root->kn; + kernfs_activate(rdtgroup_default.kn); + +out: + mutex_unlock(&rdtgroup_mutex); + + return ret; +} + +/* + * rdtgroup_init - rdtgroup initialization + * + * Setup resctrl file system including set up root, create mount point, + * register rdtgroup filesystem, and initialize files under root directory. + * + * Return: 0 on success or -errno + */ +int __init rdtgroup_init(void) +{ + int ret = 0; + + ret = rdtgroup_setup_root(); + if (ret) + return ret; + + ret = sysfs_create_mount_point(fs_kobj, "resctrl"); + if (ret) + goto cleanup_root; + + ret = register_filesystem(&rdt_fs_type); + if (ret) + goto cleanup_mountpoint; + + return 0; + +cleanup_mountpoint: + sysfs_remove_mount_point(fs_kobj, "resctrl"); +cleanup_root: + kernfs_destroy_root(rdt_root); + + return ret; +} diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_schemata.c new file mode 100644 index 000000000000..f369cb8db0d5 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_schemata.c @@ -0,0 +1,245 @@ +/* + * Resource Director Technology(RDT) + * - Cache Allocation code. + * + * Copyright (C) 2016 Intel Corporation + * + * Authors: + * Fenghua Yu <fenghua.yu@intel.com> + * Tony Luck <tony.luck@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual June 2016, volume 3, section 17.17. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernfs.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <asm/intel_rdt.h> + +/* + * Check whether a cache bit mask is valid. The SDM says: + * Please note that all (and only) contiguous '1' combinations + * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.). + * Additionally Haswell requires at least two bits set. + */ +static bool cbm_validate(unsigned long var, struct rdt_resource *r) +{ + unsigned long first_bit, zero_bit; + + if (var == 0 || var > r->max_cbm) + return false; + + first_bit = find_first_bit(&var, r->cbm_len); + zero_bit = find_next_zero_bit(&var, r->cbm_len, first_bit); + + if (find_next_bit(&var, r->cbm_len, zero_bit) < r->cbm_len) + return false; + + if ((zero_bit - first_bit) < r->min_cbm_bits) + return false; + return true; +} + +/* + * Read one cache bit mask (hex). Check that it is valid for the current + * resource type. + */ +static int parse_cbm(char *buf, struct rdt_resource *r) +{ + unsigned long data; + int ret; + + ret = kstrtoul(buf, 16, &data); + if (ret) + return ret; + if (!cbm_validate(data, r)) + return -EINVAL; + r->tmp_cbms[r->num_tmp_cbms++] = data; + + return 0; +} + +/* + * For each domain in this resource we expect to find a series of: + * id=mask + * separated by ";". The "id" is in decimal, and must appear in the + * right order. + */ +static int parse_line(char *line, struct rdt_resource *r) +{ + char *dom = NULL, *id; + struct rdt_domain *d; + unsigned long dom_id; + + list_for_each_entry(d, &r->domains, list) { + dom = strsep(&line, ";"); + if (!dom) + return -EINVAL; + id = strsep(&dom, "="); + if (kstrtoul(id, 10, &dom_id) || dom_id != d->id) + return -EINVAL; + if (parse_cbm(dom, r)) + return -EINVAL; + } + + /* Any garbage at the end of the line? */ + if (line && line[0]) + return -EINVAL; + return 0; +} + +static int update_domains(struct rdt_resource *r, int closid) +{ + struct msr_param msr_param; + cpumask_var_t cpu_mask; + struct rdt_domain *d; + int cpu, idx = 0; + + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + + msr_param.low = closid; + msr_param.high = msr_param.low + 1; + msr_param.res = r; + + list_for_each_entry(d, &r->domains, list) { + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + d->cbm[msr_param.low] = r->tmp_cbms[idx++]; + } + cpu = get_cpu(); + /* Update CBM on this cpu if it's in cpu_mask. */ + if (cpumask_test_cpu(cpu, cpu_mask)) + rdt_cbm_update(&msr_param); + /* Update CBM on other cpus. */ + smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1); + put_cpu(); + + free_cpumask_var(cpu_mask); + + return 0; +} + +ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + char *tok, *resname; + int closid, ret = 0; + u32 *l3_cbms = NULL; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + buf[nbytes - 1] = '\0'; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + closid = rdtgrp->closid; + + /* get scratch space to save all the masks while we validate input */ + for_each_enabled_rdt_resource(r) { + r->tmp_cbms = kcalloc(r->num_domains, sizeof(*l3_cbms), + GFP_KERNEL); + if (!r->tmp_cbms) { + ret = -ENOMEM; + goto out; + } + r->num_tmp_cbms = 0; + } + + while ((tok = strsep(&buf, "\n")) != NULL) { + resname = strsep(&tok, ":"); + if (!tok) { + ret = -EINVAL; + goto out; + } + for_each_enabled_rdt_resource(r) { + if (!strcmp(resname, r->name) && + closid < r->num_closid) { + ret = parse_line(tok, r); + if (ret) + goto out; + break; + } + } + if (!r->name) { + ret = -EINVAL; + goto out; + } + } + + /* Did the parser find all the masks we need? */ + for_each_enabled_rdt_resource(r) { + if (r->num_tmp_cbms != r->num_domains) { + ret = -EINVAL; + goto out; + } + } + + for_each_enabled_rdt_resource(r) { + ret = update_domains(r, closid); + if (ret) + goto out; + } + +out: + rdtgroup_kn_unlock(of->kn); + for_each_enabled_rdt_resource(r) { + kfree(r->tmp_cbms); + r->tmp_cbms = NULL; + } + return ret ?: nbytes; +} + +static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid) +{ + struct rdt_domain *dom; + bool sep = false; + + seq_printf(s, "%s:", r->name); + list_for_each_entry(dom, &r->domains, list) { + if (sep) + seq_puts(s, ";"); + seq_printf(s, "%d=%x", dom->id, dom->cbm[closid]); + sep = true; + } + seq_puts(s, "\n"); +} + +int rdtgroup_schemata_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + int closid, ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (rdtgrp) { + closid = rdtgrp->closid; + for_each_enabled_rdt_resource(r) { + if (closid < r->num_closid) + show_doms(s, r, closid); + } + } else { + ret = -ENOENT; + } + rdtgroup_kn_unlock(of->kn); + return ret; +} diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index c7efbcfbeda6..87cc9ab7a13c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -14,7 +14,7 @@ #include <linux/init.h> #include <linux/debugfs.h> #include <asm/mce.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include "mce-internal.h" diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index ffacfdcacb85..a5fd137417a2 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -1182,6 +1182,9 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) const char *name = get_name(bank, NULL); int err = 0; + if (!dev) + return -ENODEV; + if (is_shared_bank(bank)) { nb = node_to_amd_nb(amd_get_nb_id(cpu)); diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 6f353bdb3a25..6a31e2691f3a 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -116,10 +116,11 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table, /* * This scans the ucode blob for the proper container as we can have multiple - * containers glued together. + * containers glued together. Returns the equivalence ID from the equivalence + * table or 0 if none found. */ -static struct container -find_proper_container(u8 *ucode, size_t size, u16 *ret_id) +static u16 +find_proper_container(u8 *ucode, size_t size, struct container *ret_cont) { struct container ret = { NULL, 0 }; u32 eax, ebx, ecx, edx; @@ -138,7 +139,7 @@ find_proper_container(u8 *ucode, size_t size, u16 *ret_id) if (header[0] != UCODE_MAGIC || header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ header[2] == 0) /* size */ - return ret; + return eq_id; eax = 0x00000001; ecx = 0; @@ -163,8 +164,9 @@ find_proper_container(u8 *ucode, size_t size, u16 *ret_id) * ucode update loop below */ left = ret.size - offset; - *ret_id = eq_id; - return ret; + + *ret_cont = ret; + return eq_id; } /* @@ -189,7 +191,7 @@ find_proper_container(u8 *ucode, size_t size, u16 *ret_id) ucode = data; } - return ret; + return eq_id; } static int __apply_microcode_amd(struct microcode_amd *mc_amd) @@ -214,17 +216,18 @@ static int __apply_microcode_amd(struct microcode_amd *mc_amd) * and on 32-bit during save_microcode_in_initrd_amd() -- we can call * load_microcode_amd() to save equivalent cpu table and microcode patches in * kernel heap memory. + * + * Returns true if container found (sets @ret_cont), false otherwise. */ -static struct container -apply_microcode_early_amd(void *ucode, size_t size, bool save_patch) +static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch, + struct container *ret_cont) { - struct container ret = { NULL, 0 }; u8 (*patch)[PATCH_MAX_SIZE]; + u32 rev, *header, *new_rev; + struct container ret; int offset, left; - u32 rev, *header; - u8 *data; u16 eq_id = 0; - u32 *new_rev; + u8 *data; #ifdef CONFIG_X86_32 new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); @@ -235,11 +238,11 @@ apply_microcode_early_amd(void *ucode, size_t size, bool save_patch) #endif if (check_current_patch_level(&rev, true)) - return (struct container){ NULL, 0 }; + return false; - ret = find_proper_container(ucode, size, &eq_id); + eq_id = find_proper_container(ucode, size, &ret); if (!eq_id) - return (struct container){ NULL, 0 }; + return false; this_equiv_id = eq_id; header = (u32 *)ret.data; @@ -273,7 +276,11 @@ apply_microcode_early_amd(void *ucode, size_t size, bool save_patch) data += offset; left -= offset; } - return ret; + + if (ret_cont) + *ret_cont = ret; + + return true; } static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) @@ -294,6 +301,7 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) void __init load_ucode_amd_bsp(unsigned int family) { struct ucode_cpu_info *uci; + u32 eax, ebx, ecx, edx; struct cpio_data cp; const char *path; bool use_pa; @@ -315,9 +323,12 @@ void __init load_ucode_amd_bsp(unsigned int family) return; /* Get BSP's CPUID.EAX(1), needed in load_microcode_amd() */ - uci->cpu_sig.sig = cpuid_eax(1); + eax = 1; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + uci->cpu_sig.sig = eax; - apply_microcode_early_amd(cp.data, cp.size, true); + apply_microcode_early_amd(cp.data, cp.size, true, NULL); } #ifdef CONFIG_X86_32 @@ -349,7 +360,7 @@ void load_ucode_amd_ap(unsigned int family) * This would set amd_ucode_patch above so that the following APs can * use it directly instead of going down this path again. */ - apply_microcode_early_amd(cp.data, cp.size, true); + apply_microcode_early_amd(cp.data, cp.size, true, NULL); } #else void load_ucode_amd_ap(unsigned int family) @@ -387,8 +398,7 @@ reget: } } - cont = apply_microcode_early_amd(cp.data, cp.size, false); - if (!(cont.data && cont.size)) { + if (!apply_microcode_early_amd(cp.data, cp.size, false, &cont)) { cont.size = -1; return; } @@ -443,7 +453,7 @@ int __init save_microcode_in_initrd_amd(unsigned int fam) return -EINVAL; } - cont = find_proper_container(cp.data, cp.size, &eq_id); + eq_id = find_proper_container(cp.data, cp.size, &cont); if (!eq_id) { cont.size = -1; return -EINVAL; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 6996413c78c3..2af69d27da62 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -44,7 +44,7 @@ #define DRIVER_VERSION "2.2" static struct microcode_ops *microcode_ops; -static bool dis_ucode_ldr; +static bool dis_ucode_ldr = true; LIST_HEAD(microcode_cache); @@ -76,6 +76,7 @@ struct cpu_info_ctx { static bool __init check_loader_disabled_bsp(void) { static const char *__dis_opt_str = "dis_ucode_ldr"; + u32 a, b, c, d; #ifdef CONFIG_X86_32 const char *cmdline = (const char *)__pa_nodebug(boot_command_line); @@ -88,8 +89,23 @@ static bool __init check_loader_disabled_bsp(void) bool *res = &dis_ucode_ldr; #endif - if (cmdline_find_option_bool(cmdline, option)) - *res = true; + if (!have_cpuid_p()) + return *res; + + 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; } @@ -121,9 +137,6 @@ void __init load_ucode_bsp(void) if (check_loader_disabled_bsp()) return; - if (!have_cpuid_p()) - return; - vendor = x86_cpuid_vendor(); family = x86_cpuid_family(); @@ -157,9 +170,6 @@ void load_ucode_ap(void) if (check_loader_disabled_ap()) return; - if (!have_cpuid_p()) - return; - vendor = x86_cpuid_vendor(); family = x86_cpuid_family(); @@ -233,14 +243,12 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) # endif /* - * Did we relocate the ramdisk? - * - * So we possibly relocate the ramdisk *after* applying microcode on the - * BSP so we rely on use_pa (use physical addresses) - even if it is not - * absolutely correct - to determine whether we've done the ramdisk - * relocation already. + * Fixup the start address: after reserve_initrd() runs, initrd_start + * 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. */ - if (!use_pa && relocated_ramdisk) + if (!use_pa && initrd_start) start = initrd_start; return find_cpio_data(path, (void *)start, size, NULL); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 54d50c3694d8..3f329b74e040 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -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); @@ -390,15 +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 */ - sync_core(); - - /* 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; @@ -582,7 +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) @@ -590,21 +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 */ - sync_core(); - - /* 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); @@ -784,8 +772,8 @@ 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)) @@ -802,33 +790,28 @@ 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 */ - sync_core(); - /* 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; } @@ -840,7 +823,7 @@ 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) { @@ -881,6 +864,7 @@ 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 */ } @@ -906,7 +890,7 @@ 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/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 6c044543545e..65e20c97e04b 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -30,6 +30,7 @@ #include <asm/apic.h> #include <asm/timer.h> #include <asm/reboot.h> +#include <asm/nmi.h> struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); @@ -132,9 +133,9 @@ static uint32_t __init ms_hyperv_platform(void) return 0; } -static cycle_t read_hv_clock(struct clocksource *arg) +static u64 read_hv_clock(struct clocksource *arg) { - cycle_t current_tick; + u64 current_tick; /* * Read the partition counter to get the current tick count. This count * is set to 0 when the partition is created and is incremented in @@ -157,6 +158,26 @@ static unsigned char hv_get_nmi_reason(void) return 0; } +#ifdef CONFIG_X86_LOCAL_APIC +/* + * Prior to WS2016 Debug-VM sends NMIs to all CPUs which makes + * it dificult to process CHANNELMSG_UNLOAD in case of crash. Handle + * unknown NMI on the first CPU which gets it. + */ +static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs) +{ + static atomic_t nmi_cpu = ATOMIC_INIT(-1); + + if (!unknown_nmi_panic) + return NMI_DONE; + + if (atomic_cmpxchg(&nmi_cpu, -1, raw_smp_processor_id()) != -1) + return NMI_HANDLED; + + return NMI_DONE; +} +#endif + static void __init ms_hyperv_init_platform(void) { /* @@ -182,6 +203,9 @@ static void __init ms_hyperv_init_platform(void) pr_info("HyperV: LAPIC Timer Frequency: %#x\n", lapic_timer_frequency); } + + register_nmi_handler(NMI_UNKNOWN, hv_nmi_unknown, NMI_FLAG_FIRST, + "hv_nmi_unknown"); #endif if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index d1316f9c8329..d9794060fe22 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -20,12 +20,15 @@ struct cpuid_bit { /* Please keep the leaf sorted by cpuid_bit.level for faster search. */ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, - { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, - { X86_FEATURE_INTEL_PT, CPUID_EBX, 25, 0x00000007, 0 }, + { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, + { X86_FEATURE_INTEL_PT, CPUID_EBX, 25, 0x00000007, 0 }, { X86_FEATURE_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 }, { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 0 }, - { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, - { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, + { X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 }, + { X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 }, + { X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 }, + { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, + { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 650830e39e3a..3741461c63a0 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -631,9 +631,9 @@ static int determine_backup_region(u64 start, u64 end, void *arg) int crash_load_segments(struct kimage *image) { - unsigned long src_start, src_sz, elf_sz; - void *elf_addr; int ret; + struct kexec_buf kbuf = { .image = image, .buf_min = 0, + .buf_max = ULONG_MAX, .top_down = false }; /* * Determine and load a segment for backup area. First 640K RAM @@ -647,43 +647,44 @@ int crash_load_segments(struct kimage *image) if (ret < 0) return ret; - src_start = image->arch.backup_src_start; - src_sz = image->arch.backup_src_sz; - /* Add backup segment. */ - if (src_sz) { + if (image->arch.backup_src_sz) { + kbuf.buffer = &crash_zero_bytes; + kbuf.bufsz = sizeof(crash_zero_bytes); + kbuf.memsz = image->arch.backup_src_sz; + kbuf.buf_align = PAGE_SIZE; /* * Ideally there is no source for backup segment. This is * copied in purgatory after crash. Just add a zero filled * segment for now to make sure checksum logic works fine. */ - ret = kexec_add_buffer(image, (char *)&crash_zero_bytes, - sizeof(crash_zero_bytes), src_sz, - PAGE_SIZE, 0, -1, 0, - &image->arch.backup_load_addr); + ret = kexec_add_buffer(&kbuf); if (ret) return ret; + image->arch.backup_load_addr = kbuf.mem; pr_debug("Loaded backup region at 0x%lx backup_start=0x%lx memsz=0x%lx\n", - image->arch.backup_load_addr, src_start, src_sz); + image->arch.backup_load_addr, + image->arch.backup_src_start, kbuf.memsz); } /* Prepare elf headers and add a segment */ - ret = prepare_elf_headers(image, &elf_addr, &elf_sz); + ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz); if (ret) return ret; - image->arch.elf_headers = elf_addr; - image->arch.elf_headers_sz = elf_sz; + image->arch.elf_headers = kbuf.buffer; + image->arch.elf_headers_sz = kbuf.bufsz; - ret = kexec_add_buffer(image, (char *)elf_addr, elf_sz, elf_sz, - ELF_CORE_HEADER_ALIGN, 0, -1, 0, - &image->arch.elf_load_addr); + kbuf.memsz = kbuf.bufsz; + kbuf.buf_align = ELF_CORE_HEADER_ALIGN; + ret = kexec_add_buffer(&kbuf); if (ret) { vfree((void *)image->arch.elf_headers); return ret; } + image->arch.elf_load_addr = kbuf.mem; pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - image->arch.elf_load_addr, elf_sz, elf_sz); + image->arch.elf_load_addr, kbuf.bufsz, kbuf.bufsz); return ret; } diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c index 11891ca7b716..538fedea9b3f 100644 --- a/arch/x86/kernel/crash_dump_32.c +++ b/arch/x86/kernel/crash_dump_32.c @@ -10,7 +10,7 @@ #include <linux/highmem.h> #include <linux/crash_dump.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> static void *kdump_buf_page; diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c index f6dfd9334b67..b2f7207ba86c 100644 --- a/arch/x86/kernel/doublefault.c +++ b/arch/x86/kernel/doublefault.c @@ -3,7 +3,7 @@ #include <linux/init_task.h> #include <linux/fs.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/desc.h> diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 90de28841242..b467b14b03eb 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -298,12 +298,13 @@ ENTRY(start_cpu) * REX.W + FF /5 JMP m16:64 Jump far, absolute indirect, * address given in m16:64. */ - call 1f # put return address on stack for unwinder -1: xorq %rbp, %rbp # clear frame pointer + pushq $.Lafter_lret # put return address on stack for unwinder + xorq %rbp, %rbp # clear frame pointer movq initial_code(%rip), %rax pushq $__KERNEL_CS # set correct cs pushq %rax # target address in negative space lretq +.Lafter_lret: ENDPROC(start_cpu) #include "verify_cpu.S" diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 274fab99169d..85e87b46c318 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -791,7 +791,7 @@ static union hpet_lock hpet __cacheline_aligned = { { .lock = __ARCH_SPIN_LOCK_UNLOCKED, }, }; -static cycle_t read_hpet(struct clocksource *cs) +static u64 read_hpet(struct clocksource *cs) { unsigned long flags; union hpet_lock old, new; @@ -802,7 +802,7 @@ static cycle_t read_hpet(struct clocksource *cs) * Read HPET directly if in NMI. */ if (in_nmi()) - return (cycle_t)hpet_readl(HPET_COUNTER); + return (u64)hpet_readl(HPET_COUNTER); /* * Read the current state of the lock and HPET value atomically. @@ -821,7 +821,7 @@ static cycle_t read_hpet(struct clocksource *cs) WRITE_ONCE(hpet.value, new.value); arch_spin_unlock(&hpet.lock); local_irq_restore(flags); - return (cycle_t)new.value; + return (u64)new.value; } local_irq_restore(flags); @@ -843,15 +843,15 @@ contended: new.lockval = READ_ONCE(hpet.lockval); } while ((new.value == old.value) && arch_spin_is_locked(&new.lock)); - return (cycle_t)new.value; + return (u64)new.value; } #else /* * For UP or 32-bit. */ -static cycle_t read_hpet(struct clocksource *cs) +static u64 read_hpet(struct clocksource *cs) { - return (cycle_t)hpet_readl(HPET_COUNTER); + return (u64)hpet_readl(HPET_COUNTER); } #endif @@ -867,7 +867,7 @@ static struct clocksource clocksource_hpet = { static int hpet_clocksource_register(void) { u64 start, now; - cycle_t t1; + u64 t1; /* Start the counter */ hpet_restart_counter(); @@ -1051,11 +1051,11 @@ static __init int hpet_late_init(void) return 0; /* This notifier should be called after workqueue is ready */ - ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "AP_X86_HPET_ONLINE", + ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "x86/hpet:online", hpet_cpuhp_online, NULL); if (ret) return ret; - ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "X86_HPET_DEAD", NULL, + ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "x86/hpet:dead", NULL, hpet_cpuhp_dead); if (ret) goto err_cpuhp; diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 3407b148c240..d0a814a9d96a 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -331,17 +331,17 @@ static void *bzImage64_load(struct kimage *image, char *kernel, struct setup_header *header; int setup_sects, kern16_size, ret = 0; - unsigned long setup_header_size, params_cmdline_sz, params_misc_sz; + unsigned long setup_header_size, params_cmdline_sz; struct boot_params *params; unsigned long bootparam_load_addr, kernel_load_addr, initrd_load_addr; unsigned long purgatory_load_addr; - unsigned long kernel_bufsz, kernel_memsz, kernel_align; - char *kernel_buf; struct bzimage64_data *ldata; struct kexec_entry64_regs regs64; void *stack; unsigned int setup_hdr_offset = offsetof(struct boot_params, hdr); unsigned int efi_map_offset, efi_map_sz, efi_setup_data_offset; + struct kexec_buf kbuf = { .image = image, .buf_max = ULONG_MAX, + .top_down = true }; header = (struct setup_header *)(kernel + setup_hdr_offset); setup_sects = header->setup_sects; @@ -402,11 +402,11 @@ static void *bzImage64_load(struct kimage *image, char *kernel, params_cmdline_sz = sizeof(struct boot_params) + cmdline_len + MAX_ELFCOREHDR_STR_LEN; params_cmdline_sz = ALIGN(params_cmdline_sz, 16); - params_misc_sz = params_cmdline_sz + efi_map_sz + + kbuf.bufsz = params_cmdline_sz + efi_map_sz + sizeof(struct setup_data) + sizeof(struct efi_setup_data); - params = kzalloc(params_misc_sz, GFP_KERNEL); + params = kzalloc(kbuf.bufsz, GFP_KERNEL); if (!params) return ERR_PTR(-ENOMEM); efi_map_offset = params_cmdline_sz; @@ -418,37 +418,41 @@ static void *bzImage64_load(struct kimage *image, char *kernel, /* Is there a limit on setup header size? */ memcpy(¶ms->hdr, (kernel + setup_hdr_offset), setup_header_size); - ret = kexec_add_buffer(image, (char *)params, params_misc_sz, - params_misc_sz, 16, MIN_BOOTPARAM_ADDR, - ULONG_MAX, 1, &bootparam_load_addr); + kbuf.buffer = params; + kbuf.memsz = kbuf.bufsz; + kbuf.buf_align = 16; + kbuf.buf_min = MIN_BOOTPARAM_ADDR; + ret = kexec_add_buffer(&kbuf); if (ret) goto out_free_params; + bootparam_load_addr = kbuf.mem; pr_debug("Loaded boot_param, command line and misc at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - bootparam_load_addr, params_misc_sz, params_misc_sz); + bootparam_load_addr, kbuf.bufsz, kbuf.bufsz); /* Load kernel */ - kernel_buf = kernel + kern16_size; - kernel_bufsz = kernel_len - kern16_size; - kernel_memsz = PAGE_ALIGN(header->init_size); - kernel_align = header->kernel_alignment; - - ret = kexec_add_buffer(image, kernel_buf, - kernel_bufsz, kernel_memsz, kernel_align, - MIN_KERNEL_LOAD_ADDR, ULONG_MAX, 1, - &kernel_load_addr); + kbuf.buffer = kernel + kern16_size; + kbuf.bufsz = kernel_len - kern16_size; + kbuf.memsz = PAGE_ALIGN(header->init_size); + kbuf.buf_align = header->kernel_alignment; + kbuf.buf_min = MIN_KERNEL_LOAD_ADDR; + ret = kexec_add_buffer(&kbuf); if (ret) goto out_free_params; + kernel_load_addr = kbuf.mem; pr_debug("Loaded 64bit kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - kernel_load_addr, kernel_memsz, kernel_memsz); + kernel_load_addr, kbuf.bufsz, kbuf.memsz); /* Load initrd high */ if (initrd) { - ret = kexec_add_buffer(image, initrd, initrd_len, initrd_len, - PAGE_SIZE, MIN_INITRD_LOAD_ADDR, - ULONG_MAX, 1, &initrd_load_addr); + kbuf.buffer = initrd; + kbuf.bufsz = kbuf.memsz = initrd_len; + kbuf.buf_align = PAGE_SIZE; + kbuf.buf_min = MIN_INITRD_LOAD_ADDR; + ret = kexec_add_buffer(&kbuf); if (ret) goto out_free_params; + initrd_load_addr = kbuf.mem; pr_debug("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n", initrd_load_addr, initrd_len, initrd_len); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index d9d8d16b69db..eb3509338ae0 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -56,7 +56,7 @@ #include <asm/cacheflush.h> #include <asm/desc.h> #include <asm/pgtable.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/alternative.h> #include <asm/insn.h> #include <asm/debugreg.h> diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 3bb4c5f021f6..3d1bee9d6a72 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -33,7 +33,7 @@ #include <asm/cacheflush.h> #include <asm/desc.h> #include <asm/pgtable.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/alternative.h> #include <asm/insn.h> #include <asm/debugreg.h> diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 60b9949f1e65..2a5cafdf8808 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -32,7 +32,7 @@ static int kvmclock __ro_after_init = 1; static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK; -static cycle_t kvm_sched_clock_offset; +static u64 kvm_sched_clock_offset; static int parse_no_kvmclock(char *arg) { @@ -79,10 +79,10 @@ static int kvm_set_wallclock(const struct timespec *now) return -1; } -static cycle_t kvm_clock_read(void) +static u64 kvm_clock_read(void) { struct pvclock_vcpu_time_info *src; - cycle_t ret; + u64 ret; int cpu; preempt_disable_notrace(); @@ -93,12 +93,12 @@ static cycle_t kvm_clock_read(void) return ret; } -static cycle_t kvm_clock_get_cycles(struct clocksource *cs) +static u64 kvm_clock_get_cycles(struct clocksource *cs) { return kvm_clock_read(); } -static cycle_t kvm_sched_clock_read(void) +static u64 kvm_sched_clock_read(void) { return kvm_clock_read() - kvm_sched_clock_offset; } diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 8c1f218926d7..307b1f4543de 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -328,7 +328,7 @@ void machine_kexec(struct kimage *image) void arch_crash_save_vmcoreinfo(void) { - VMCOREINFO_SYMBOL(phys_base); + VMCOREINFO_NUMBER(phys_base); VMCOREINFO_SYMBOL(init_level4_pgt); #ifdef CONFIG_NUMA @@ -337,9 +337,7 @@ void arch_crash_save_vmcoreinfo(void) #endif vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); - VMCOREINFO_PAGE_OFFSET(PAGE_OFFSET); - VMCOREINFO_VMALLOC_START(VMALLOC_START); - VMCOREINFO_VMEMMAP_START(VMEMMAP_START); + VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE); } /* arch-dependent functionality related to kexec file-based syscall */ diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index f5e3ff835cc8..ef688804f80d 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -224,7 +224,6 @@ static int __init msr_init(void) return 0; out_class: - cpuhp_remove_state(cpuhp_msr_state); class_destroy(msr_class); out_chrdev: __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index d33ef165b1f8..553acbbb4d32 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -68,7 +68,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, #endif default: -patch_default: +patch_default: __maybe_unused ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index f4fcf26c9fce..11aaf1eaa0e4 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -80,7 +80,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, #endif default: -patch_default: +patch_default: __maybe_unused ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index b47edb8f5256..410efb2c7b80 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -68,12 +68,10 @@ static struct dma_map_ops swiotlb_dma_ops = { */ int __init pci_swiotlb_detect_override(void) { - int use_swiotlb = swiotlb | swiotlb_force; - - if (swiotlb_force) + if (swiotlb_force == SWIOTLB_FORCE) swiotlb = 1; - return use_swiotlb; + return swiotlb; } IOMMU_INIT_FINISH(pci_swiotlb_detect_override, pci_xen_swiotlb_detect, diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c index 24a50301f150..91271122f0df 100644 --- a/arch/x86/kernel/platform-quirks.c +++ b/arch/x86/kernel/platform-quirks.c @@ -6,6 +6,7 @@ void __init x86_early_init_platform_quirks(void) { + x86_platform.legacy.i8042 = X86_LEGACY_I8042_EXPECTED_PRESENT; x86_platform.legacy.rtc = 1; x86_platform.legacy.reserve_bios_regions = 0; x86_platform.legacy.devices.pnpbios = 1; @@ -16,10 +17,14 @@ void __init x86_early_init_platform_quirks(void) break; case X86_SUBARCH_XEN: case X86_SUBARCH_LGUEST: + x86_platform.legacy.devices.pnpbios = 0; + x86_platform.legacy.rtc = 0; + break; case X86_SUBARCH_INTEL_MID: case X86_SUBARCH_CE4100: x86_platform.legacy.devices.pnpbios = 0; x86_platform.legacy.rtc = 0; + x86_platform.legacy.i8042 = X86_LEGACY_I8042_PLATFORM_ABSENT; break; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 43c36d8a6ae2..b615a1113f58 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -23,7 +23,7 @@ #include <asm/cpu.h> #include <asm/apic.h> #include <asm/syscalls.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/mwait.h> #include <asm/fpu/internal.h> #include <asm/debugreg.h> @@ -235,6 +235,7 @@ static inline void play_dead(void) void arch_cpu_idle_enter(void) { + tsc_verify_tsc_adjust(false); local_touch_nmi(); } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index d0d744108594..a0ac3e81518a 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -53,6 +53,7 @@ #include <asm/debugreg.h> #include <asm/switch_to.h> #include <asm/vm86.h> +#include <asm/intel_rdt.h> void __show_regs(struct pt_regs *regs, int all) { @@ -296,5 +297,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) this_cpu_write(current_task, next_p); + /* Load the Intel cache allocation PQR MSR. */ + intel_rdt_sched_in(); + return prev_p; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a76b65e3e615..a61e141b6891 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -49,6 +49,7 @@ #include <asm/switch_to.h> #include <asm/xen/hypervisor.h> #include <asm/vdso.h> +#include <asm/intel_rdt.h> __visible DEFINE_PER_CPU(unsigned long, rsp_scratch); @@ -476,6 +477,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) loadsegment(ss, __KERNEL_DS); } + /* Load the Intel cache allocation PQR MSR. */ + intel_rdt_sched_in(); + return prev_p; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 0e63c0267f99..9cc7d5a330ef 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -24,7 +24,7 @@ #include <linux/export.h> #include <linux/context_tracking.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/fpu/internal.h> diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 5b2cc889ce34..9e93fe5803b4 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -71,10 +71,10 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) return flags & valid_flags; } -cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) +u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) { unsigned version; - cycle_t ret; + u64 ret; u64 last; u8 flags; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 0c37d4fd01b2..46732dc3b73c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -103,7 +103,6 @@ static unsigned int max_physical_pkg_id __read_mostly; unsigned int __max_logical_packages __read_mostly; EXPORT_SYMBOL(__max_logical_packages); static unsigned int logical_packages __read_mostly; -static bool logical_packages_frozen __read_mostly; /* Maximum number of SMT threads on any online core */ int __max_smt_threads __read_mostly; @@ -273,9 +272,14 @@ static void notrace start_secondary(void *unused) cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } -int topology_update_package_map(unsigned int apicid, unsigned int cpu) +/** + * topology_update_package_map - Update the physical to logical package map + * @pkg: The physical package id as retrieved via CPUID + * @cpu: The cpu for which this is updated + */ +int topology_update_package_map(unsigned int pkg, unsigned int cpu) { - unsigned int new, pkg = apicid >> boot_cpu_data.x86_coreid_bits; + unsigned int new; /* Called from early boot ? */ if (!physical_package_map) @@ -288,16 +292,17 @@ int topology_update_package_map(unsigned int apicid, unsigned int cpu) if (test_and_set_bit(pkg, physical_package_map)) goto found; - if (logical_packages_frozen) { - physical_to_logical_pkg[pkg] = -1; - pr_warn("APIC(%x) Package %u exceeds logical package max\n", - apicid, pkg); + if (logical_packages >= __max_logical_packages) { + pr_warn("Package %u of CPU %u exceeds BIOS package data %u.\n", + logical_packages, cpu, __max_logical_packages); return -ENOSPC; } new = logical_packages++; - pr_info("APIC(%x) Converting physical %u to logical package %u\n", - apicid, pkg, new); + if (new != pkg) { + pr_info("CPU %u Converting physical %u to logical package %u\n", + cpu, pkg, new); + } physical_to_logical_pkg[pkg] = new; found: @@ -318,9 +323,9 @@ int topology_phys_to_logical_pkg(unsigned int phys_pkg) } EXPORT_SYMBOL(topology_phys_to_logical_pkg); -static void __init smp_init_package_map(void) +static void __init smp_init_package_map(struct cpuinfo_x86 *c, unsigned int cpu) { - unsigned int ncpus, cpu; + unsigned int ncpus; size_t size; /* @@ -365,27 +370,9 @@ static void __init smp_init_package_map(void) size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long); physical_package_map = kzalloc(size, GFP_KERNEL); - for_each_present_cpu(cpu) { - unsigned int apicid = apic->cpu_present_to_apicid(cpu); - - if (apicid == BAD_APICID || !apic->apic_id_valid(apicid)) - continue; - if (!topology_update_package_map(apicid, cpu)) - continue; - pr_warn("CPU %u APICId %x disabled\n", cpu, apicid); - per_cpu(x86_bios_cpu_apicid, cpu) = BAD_APICID; - set_cpu_possible(cpu, false); - set_cpu_present(cpu, false); - } - - if (logical_packages > __max_logical_packages) { - pr_warn("Detected more packages (%u), then computed by BIOS data (%u).\n", - logical_packages, __max_logical_packages); - logical_packages_frozen = true; - __max_logical_packages = logical_packages; - } - pr_info("Max logical packages: %u\n", __max_logical_packages); + + topology_update_package_map(c->phys_proc_id, cpu); } void __init smp_store_boot_cpu_info(void) @@ -395,7 +382,7 @@ void __init smp_store_boot_cpu_info(void) *c = boot_cpu_data; c->cpu_index = id; - smp_init_package_map(); + smp_init_package_map(c, id); } /* @@ -1476,15 +1463,15 @@ __init void prefill_possible_map(void) possible = i; } + nr_cpu_ids = possible; + pr_info("Allowing %d CPUs, %d hotplug CPUs\n", possible, max_t(int, possible - num_processors, 0)); + reset_cpu_possible_mask(); + for (i = 0; i < possible; i++) set_cpu_possible(i, true); - for (; i < NR_CPUS; i++) - set_cpu_possible(i, false); - - nr_cpu_ids = possible; } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 8402907825b0..b868fa1b812b 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -408,7 +408,7 @@ static __init int tboot_late_init(void) tboot_create_trampoline(); atomic_set(&ap_wfs_count, 0); - cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "AP_X86_TBOOT_DYING", NULL, + cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "x86/tboot:dying", NULL, tboot_dying_cpu); #ifdef CONFIG_DEBUG_FS debugfs_create_file("tboot_log", S_IRUSR, diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c index 27538f183c3b..a3b875c9e6af 100644 --- a/arch/x86/kernel/test_nx.c +++ b/arch/x86/kernel/test_nx.c @@ -13,7 +13,7 @@ #include <linux/sort.h> #include <linux/slab.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/asm.h> extern int rodata_test_data; diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 9692a5e9fdab..6c8934406dc9 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -5,7 +5,7 @@ #include <linux/regset.h> #include <linux/syscalls.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/desc.h> #include <asm/ldt.h> #include <asm/processor.h> diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c index 1c113db9ed57..15515132bf0d 100644 --- a/arch/x86/kernel/tracepoint.c +++ b/arch/x86/kernel/tracepoint.c @@ -34,7 +34,7 @@ static void switch_idt(void *arg) local_irq_restore(flags); } -void trace_irq_vector_regfunc(void) +int trace_irq_vector_regfunc(void) { mutex_lock(&irq_vector_mutex); if (!trace_irq_vector_refcount) { @@ -44,6 +44,7 @@ void trace_irq_vector_regfunc(void) } trace_irq_vector_refcount++; mutex_unlock(&irq_vector_mutex); + return 0; } void trace_irq_vector_unregfunc(void) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 46b2f41f8b05..e41af597aed8 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: @@ -702,6 +703,20 @@ unsigned long native_calibrate_tsc(void) } } + /* + * TSC frequency determined by CPUID is a "hardware reported" + * frequency and is the most accurate one so far we have. This + * is considered a known frequency. + */ + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); + + /* + * For Atom SoCs TSC is the only reliable clocksource. + * Mark TSC reliable so no watchdog on it. + */ + if (boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT) + setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); + return crystal_khz * ebx_numerator / eax_denominator; } @@ -1043,18 +1058,20 @@ static void detect_art(void) if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF) return; - cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator, - &art_to_tsc_numerator, unused, unused+1); - - /* Don't enable ART in a VM, non-stop TSC required */ + /* Don't enable ART in a VM, non-stop TSC and TSC_ADJUST required */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR) || !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) || - art_to_tsc_denominator < ART_MIN_DENOMINATOR) + !boot_cpu_has(X86_FEATURE_TSC_ADJUST)) return; - if (rdmsrl_safe(MSR_IA32_TSC_ADJUST, &art_to_tsc_offset)) + cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator, + &art_to_tsc_numerator, unused, unused+1); + + if (art_to_tsc_denominator < ART_MIN_DENOMINATOR) return; + rdmsrl(MSR_IA32_TSC_ADJUST, art_to_tsc_offset); + /* Make this sticky over multiple CPU init calls */ setup_force_cpu_cap(X86_FEATURE_ART); } @@ -1064,6 +1081,11 @@ static void detect_art(void) static struct clocksource clocksource_tsc; +static void tsc_resume(struct clocksource *cs) +{ + tsc_verify_tsc_adjust(true); +} + /* * We used to compare the TSC to the cycle_last value in the clocksource * structure to avoid a nasty time-warp. This can be observed in a @@ -1080,9 +1102,9 @@ static struct clocksource clocksource_tsc; * checking the result of read_tsc() - cycle_last for being negative. * That works because CLOCKSOURCE_MASK(64) does not mask out any bit. */ -static cycle_t read_tsc(struct clocksource *cs) +static u64 read_tsc(struct clocksource *cs) { - return (cycle_t)rdtsc_ordered(); + return (u64)rdtsc_ordered(); } /* @@ -1096,6 +1118,7 @@ static struct clocksource clocksource_tsc = { .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_MUST_VERIFY, .archdata = { .vclock_mode = VCLOCK_TSC }, + .resume = tsc_resume, }; void mark_tsc_unstable(char *reason) @@ -1170,7 +1193,7 @@ int unsynchronized_tsc(void) /* * Convert ART to TSC given numerator/denominator found in detect_art() */ -struct system_counterval_t convert_art_to_tsc(cycle_t art) +struct system_counterval_t convert_art_to_tsc(u64 art) { u64 tmp, res, rem; @@ -1283,10 +1306,10 @@ static int __init init_tsc_clocksource(void) clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; /* - * Trust the results of the earlier calibration on systems - * exporting a reliable TSC. + * When TSC frequency is known (retrieved via MSR or CPUID), we skip + * the refined calibration and directly register it as a clocksource. */ - if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) { + if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { clocksource_register_khz(&clocksource_tsc, tsc_khz); return 0; } @@ -1363,6 +1386,8 @@ 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_msr.c b/arch/x86/kernel/tsc_msr.c index 0fe720d64fef..19afdbd7d0a7 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -100,5 +100,24 @@ unsigned long cpu_khz_from_msr(void) #ifdef CONFIG_X86_LOCAL_APIC lapic_timer_frequency = (freq * 1000) / HZ; #endif + + /* + * TSC frequency determined by MSR is always considered "known" + * because it is reported by HW. + * Another fact is that on MSR capable platforms, PIT/HPET is + * generally not available so calibration won't work at all. + */ + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); + + /* + * Unfortunately there is no way for hardware to tell whether the + * TSC is reliable. We were told by silicon design team that TSC + * on Atom SoCs are always "reliable". TSC is also the only + * reliable clocksource on these SoCs (HPET is either not present + * or not functional) so mark TSC reliable which removes the + * requirement for a watchdog clocksource. + */ + setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); + return res; } diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 78083bf23ed1..d0db011051a5 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -14,18 +14,166 @@ * ( The serial nature of the boot logic and the CPU hotplug lock * protects against more than 2 CPUs entering this code. ) */ +#include <linux/topology.h> #include <linux/spinlock.h> #include <linux/kernel.h> #include <linux/smp.h> #include <linux/nmi.h> #include <asm/tsc.h> +struct tsc_adjust { + s64 bootval; + s64 adjusted; + unsigned long nextcheck; + bool warned; +}; + +static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust); + +void tsc_verify_tsc_adjust(bool resume) +{ + struct tsc_adjust *adj = this_cpu_ptr(&tsc_adjust); + s64 curval; + + if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST)) + return; + + /* Rate limit the MSR check */ + if (!resume && time_before(jiffies, adj->nextcheck)) + return; + + adj->nextcheck = jiffies + HZ; + + rdmsrl(MSR_IA32_TSC_ADJUST, curval); + if (adj->adjusted == curval) + return; + + /* Restore the original value */ + wrmsrl(MSR_IA32_TSC_ADJUST, adj->adjusted); + + if (!adj->warned || resume) { + pr_warn(FW_BUG "TSC ADJUST differs: CPU%u %lld --> %lld. Restoring\n", + smp_processor_id(), adj->adjusted, curval); + adj->warned = true; + } +} + +static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval, + unsigned int cpu, bool bootcpu) +{ + /* + * First online CPU in a package stores the boot value in the + * adjustment value. This value might change later via the sync + * mechanism. If that fails we still can yell about boot values not + * being consistent. + * + * On the boot cpu we just force set the ADJUST value to 0 if it's + * non zero. We don't do that on non boot cpus because physical + * hotplug should have set the ADJUST register to a value > 0 so + * the TSC is in sync with the already running cpus. + * + * But we always force positive ADJUST values. Otherwise the TSC + * deadline timer creates an interrupt storm. We also have to + * prevent values > 0x7FFFFFFF as those wreckage the timer as well. + */ + if ((bootcpu && bootval != 0) || (!bootcpu && bootval < 0) || + (bootval > 0x7FFFFFFF)) { + pr_warn(FW_BUG "TSC ADJUST: CPU%u: %lld force to 0\n", cpu, + bootval); + wrmsrl(MSR_IA32_TSC_ADJUST, 0); + bootval = 0; + } + cur->adjusted = bootval; +} + +#ifndef CONFIG_SMP +bool __init tsc_store_and_check_tsc_adjust(bool bootcpu) +{ + struct tsc_adjust *cur = this_cpu_ptr(&tsc_adjust); + s64 bootval; + + if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST)) + return false; + + rdmsrl(MSR_IA32_TSC_ADJUST, bootval); + cur->bootval = bootval; + cur->nextcheck = jiffies + HZ; + tsc_sanitize_first_cpu(cur, bootval, smp_processor_id(), bootcpu); + return false; +} + +#else /* !CONFIG_SMP */ + +/* + * Store and check the TSC ADJUST MSR if available + */ +bool tsc_store_and_check_tsc_adjust(bool bootcpu) +{ + struct tsc_adjust *ref, *cur = this_cpu_ptr(&tsc_adjust); + unsigned int refcpu, cpu = smp_processor_id(); + struct cpumask *mask; + s64 bootval; + + if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST)) + return false; + + rdmsrl(MSR_IA32_TSC_ADJUST, bootval); + cur->bootval = bootval; + cur->nextcheck = jiffies + HZ; + cur->warned = false; + + /* + * Check whether this CPU is the first in a package to come up. In + * this case do not check the boot value against another package + * because the new package might have been physically hotplugged, + * where TSC_ADJUST is expected to be different. When called on the + * boot CPU topology_core_cpumask() might not be available yet. + */ + mask = topology_core_cpumask(cpu); + refcpu = mask ? cpumask_any_but(mask, cpu) : nr_cpu_ids; + + if (refcpu >= nr_cpu_ids) { + tsc_sanitize_first_cpu(cur, bootval, smp_processor_id(), + bootcpu); + return false; + } + + ref = per_cpu_ptr(&tsc_adjust, refcpu); + /* + * Compare the boot value and complain if it differs in the + * package. + */ + if (bootval != ref->bootval) { + pr_warn(FW_BUG "TSC ADJUST differs: Reference CPU%u: %lld CPU%u: %lld\n", + refcpu, ref->bootval, cpu, bootval); + } + /* + * The TSC_ADJUST values in a package must be the same. If the boot + * value on this newly upcoming CPU differs from the adjustment + * value of the already online CPU in this package, set it to that + * adjusted value. + */ + if (bootval != ref->adjusted) { + pr_warn("TSC ADJUST synchronize: Reference CPU%u: %lld CPU%u: %lld\n", + refcpu, ref->adjusted, cpu, bootval); + cur->adjusted = ref->adjusted; + wrmsrl(MSR_IA32_TSC_ADJUST, ref->adjusted); + } + /* + * We have the TSCs forced to be in sync on this package. Skip sync + * test: + */ + return true; +} + /* * Entry/exit counters that make sure that both CPUs * run the measurement code at once: */ static atomic_t start_count; static atomic_t stop_count; +static atomic_t skip_test; +static atomic_t test_runs; /* * We use a raw spinlock in this exceptional case, because @@ -37,15 +185,16 @@ static arch_spinlock_t sync_lock = __ARCH_SPIN_LOCK_UNLOCKED; static cycles_t last_tsc; static cycles_t max_warp; static int nr_warps; +static int random_warps; /* * TSC-warp measurement loop running on both CPUs. This is not called * if there is no TSC. */ -static void check_tsc_warp(unsigned int timeout) +static cycles_t check_tsc_warp(unsigned int timeout) { - cycles_t start, now, prev, end; - int i; + cycles_t start, now, prev, end, cur_max_warp = 0; + int i, cur_warps = 0; start = rdtsc_ordered(); /* @@ -85,13 +234,22 @@ static void check_tsc_warp(unsigned int timeout) if (unlikely(prev > now)) { arch_spin_lock(&sync_lock); max_warp = max(max_warp, prev - now); + cur_max_warp = max_warp; + /* + * Check whether this bounces back and forth. Only + * one CPU should observe time going backwards. + */ + if (cur_warps != nr_warps) + random_warps++; nr_warps++; + cur_warps = nr_warps; arch_spin_unlock(&sync_lock); } } WARN(!(now-start), "Warning: zero tsc calibration delta: %Ld [max: %Ld]\n", now-start, end-start); + return cur_max_warp; } /* @@ -136,15 +294,26 @@ void check_tsc_sync_source(int cpu) } /* - * Reset it - in case this is a second bootup: + * Set the maximum number of test runs to + * 1 if the CPU does not provide the TSC_ADJUST MSR + * 3 if the MSR is available, so the target can try to adjust */ - atomic_set(&stop_count, 0); - + if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST)) + atomic_set(&test_runs, 1); + else + atomic_set(&test_runs, 3); +retry: /* - * Wait for the target to arrive: + * Wait for the target to start or to skip the test: */ - while (atomic_read(&start_count) != cpus-1) + while (atomic_read(&start_count) != cpus - 1) { + if (atomic_read(&skip_test) > 0) { + atomic_set(&skip_test, 0); + return; + } cpu_relax(); + } + /* * Trigger the target to continue into the measurement too: */ @@ -155,21 +324,35 @@ void check_tsc_sync_source(int cpu) while (atomic_read(&stop_count) != cpus-1) cpu_relax(); - if (nr_warps) { + /* + * If the test was successful set the number of runs to zero and + * stop. If not, decrement the number of runs an check if we can + * retry. In case of random warps no retry is attempted. + */ + if (!nr_warps) { + atomic_set(&test_runs, 0); + + pr_debug("TSC synchronization [CPU#%d -> CPU#%d]: passed\n", + smp_processor_id(), cpu); + + } else if (atomic_dec_and_test(&test_runs) || random_warps) { + /* Force it to 0 if random warps brought us here */ + atomic_set(&test_runs, 0); + pr_warning("TSC synchronization [CPU#%d -> CPU#%d]:\n", smp_processor_id(), cpu); pr_warning("Measured %Ld cycles TSC warp between CPUs, " "turning off TSC clock.\n", max_warp); + if (random_warps) + pr_warning("TSC warped randomly between CPUs\n"); mark_tsc_unstable("check_tsc_sync_source failed"); - } else { - pr_debug("TSC synchronization [CPU#%d -> CPU#%d]: passed\n", - smp_processor_id(), cpu); } /* * Reset it - just in case we boot another CPU later: */ atomic_set(&start_count, 0); + random_warps = 0; nr_warps = 0; max_warp = 0; last_tsc = 0; @@ -178,6 +361,12 @@ void check_tsc_sync_source(int cpu) * Let the target continue with the bootup: */ atomic_inc(&stop_count); + + /* + * Retry, if there is a chance to do so. + */ + if (atomic_read(&test_runs) > 0) + goto retry; } /* @@ -185,6 +374,9 @@ void check_tsc_sync_source(int cpu) */ void check_tsc_sync_target(void) { + struct tsc_adjust *cur = this_cpu_ptr(&tsc_adjust); + unsigned int cpu = smp_processor_id(); + cycles_t cur_max_warp, gbl_max_warp; int cpus = 2; /* Also aborts if there is no TSC. */ @@ -192,6 +384,16 @@ void check_tsc_sync_target(void) return; /* + * Store, verify and sanitize the TSC adjust register. If + * successful skip the test. + */ + if (tsc_store_and_check_tsc_adjust(false)) { + atomic_inc(&skip_test); + return; + } + +retry: + /* * Register this CPU's participation and wait for the * source CPU to start the measurement: */ @@ -199,7 +401,12 @@ void check_tsc_sync_target(void) while (atomic_read(&start_count) != cpus) cpu_relax(); - check_tsc_warp(loop_timeout(smp_processor_id())); + cur_max_warp = check_tsc_warp(loop_timeout(cpu)); + + /* + * Store the maximum observed warp value for a potential retry: + */ + gbl_max_warp = max_warp; /* * Ok, we are done: @@ -211,4 +418,61 @@ void check_tsc_sync_target(void) */ while (atomic_read(&stop_count) != cpus) cpu_relax(); + + /* + * Reset it for the next sync test: + */ + atomic_set(&stop_count, 0); + + /* + * Check the number of remaining test runs. If not zero, the test + * failed and a retry with adjusted TSC is possible. If zero the + * test was either successful or failed terminally. + */ + if (!atomic_read(&test_runs)) + return; + + /* + * If the warp value of this CPU is 0, then the other CPU + * observed time going backwards so this TSC was ahead and + * needs to move backwards. + */ + if (!cur_max_warp) + cur_max_warp = -gbl_max_warp; + + /* + * Add the result to the previous adjustment value. + * + * The adjustement value is slightly off by the overhead of the + * sync mechanism (observed values are ~200 TSC cycles), but this + * really depends on CPU, node distance and frequency. So + * compensating for this is hard to get right. Experiments show + * that the warp is not longer detectable when the observed warp + * value is used. In the worst case the adjustment needs to go + * through a 3rd run for fine tuning. + */ + cur->adjusted += cur_max_warp; + + /* + * TSC deadline timer stops working or creates an interrupt storm + * with adjust values < 0 and > x07ffffff. + * + * To allow adjust values > 0x7FFFFFFF we need to disable the + * deadline timer and use the local APIC timer, but that requires + * more intrusive changes and we do not have any useful information + * from Intel about the underlying HW wreckage yet. + */ + if (cur->adjusted < 0) + cur->adjusted = 0; + if (cur->adjusted > 0x7FFFFFFF) + cur->adjusted = 0x7FFFFFFF; + + pr_warn("TSC ADJUST compensate: CPU%u observed %lld warp. Adjust: %lld\n", + cpu, cur_max_warp, cur->adjusted); + + wrmsrl(MSR_IA32_TSC_ADJUST, cur->adjusted); + goto retry; + } + +#endif /* CONFIG_SMP */ diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index ea7b7f9a3b9e..23d15565d02a 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -6,6 +6,52 @@ #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; + bool prev_zero, zero = false; + unsigned long word; + + if (dumped_before) + return; + + dumped_before = true; + + printk_deferred("unwind stack type:%d next_sp:%p mask:%lx graph_idx:%d\n", + state->stack_info.type, state->stack_info.next_sp, + state->stack_mask, state->graph_idx); + + for (sp = state->orig_sp; sp < state->stack_info.end; sp++) { + word = READ_ONCE_NOCHECK(*sp); + + prev_zero = zero; + zero = word == 0; + + if (zero) { + if (!prev_zero) + printk_deferred("%p: %016x ...\n", sp, 0); + continue; + } + + printk_deferred("%p: %016lx (%pB)\n", sp, word, (void *)word); + } +} + unsigned long unwind_get_return_address(struct unwind_state *state) { unsigned long addr; @@ -17,18 +63,11 @@ 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); - if (!__kernel_text_address(addr)) { - printk_deferred_once(KERN_WARNING - "WARNING: unrecognized kernel stack return address %p at %p in %s:%d\n", - (void *)addr, addr_p, state->task->comm, - state->task->pid); - return 0; - } - - return addr; + return __kernel_text_address(addr) ? addr : 0; } EXPORT_SYMBOL_GPL(unwind_get_return_address); @@ -46,7 +85,14 @@ static bool is_last_task_frame(struct unwind_state *state) unsigned long bp = (unsigned long)state->bp; unsigned long regs = (unsigned long)task_pt_regs(state->task); - return bp == regs - FRAME_HEADER_SIZE; + /* + * We have to check for the last task frame at two different locations + * because gcc can occasionally decide to realign the stack pointer and + * change the offset of the stack frame by a word in the prologue of a + * function called by head/entry code. + */ + return bp == regs - FRAME_HEADER_SIZE || + bp == regs - FRAME_HEADER_SIZE - sizeof(long); } /* @@ -67,6 +113,7 @@ static bool update_stack_state(struct unwind_state *state, void *addr, size_t len) { struct stack_info *info = &state->stack_info; + enum stack_type orig_type = info->type; /* * If addr isn't on the current stack, switch to the next one. @@ -80,6 +127,9 @@ static bool update_stack_state(struct unwind_state *state, void *addr, &state->stack_mask)) return false; + if (!state->orig_sp || info->type != orig_type) + state->orig_sp = addr; + return true; } @@ -128,7 +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); @@ -173,16 +223,28 @@ 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", state->regs, state->task->comm, state->task->pid, next_frame); + unwind_dump(state, (unsigned long *)state->regs); } else { printk_deferred_once(KERN_WARNING "WARNING: kernel stack frame pointer at %p in %s:%d has bad value %p\n", state->bp, state->task->comm, state->task->pid, next_frame); + unwind_dump(state, state->bp); } the_end: state->stack_info.type = STACK_TYPE_UNKNOWN; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 01f30e56f99e..ec5d7545e6dc 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -47,7 +47,7 @@ #include <linux/slab.h> #include <linux/security.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/io.h> #include <asm/tlbflush.h> #include <asm/irq.h> diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 0bd9f1287f39..11a93f005268 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -89,7 +89,6 @@ struct x86_cpuinit_ops x86_cpuinit = { }; static void default_nmi_init(void) { }; -static int default_i8042_detect(void) { return 1; }; struct x86_platform_ops x86_platform __ro_after_init = { .calibrate_cpu = native_calibrate_cpu, @@ -100,7 +99,6 @@ struct x86_platform_ops x86_platform __ro_after_init = { .is_untracked_pat_range = is_ISA_range, .nmi_init = default_nmi_init, .get_nmi_reason = default_get_nmi_reason, - .i8042_detect = default_i8042_detect, .save_sched_clock_state = tsc_save_sched_clock_state, .restore_sched_clock_state = tsc_restore_sched_clock_state, }; |