diff options
Diffstat (limited to 'arch/x86/kernel')
| -rw-r--r-- | arch/x86/kernel/acpi/boot.c | 3 | ||||
| -rw-r--r-- | arch/x86/kernel/apic/io_apic.c | 5 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/internal.h | 16 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/rdtgroup.c | 185 | ||||
| -rw-r--r-- | arch/x86/kernel/e820.c | 10 | ||||
| -rw-r--r-- | arch/x86/kernel/ftrace.c | 42 | ||||
| -rw-r--r-- | arch/x86/kernel/kexec-bzimage64.c | 14 | ||||
| -rw-r--r-- | arch/x86/kernel/kvmclock.c | 20 | ||||
| -rw-r--r-- | arch/x86/kernel/setup_percpu.c | 10 |
9 files changed, 197 insertions, 108 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 2624de16cd7a..8dcbf6890714 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -935,6 +935,9 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) #define HPET_RESOURCE_NAME_SIZE 9 hpet_res = memblock_alloc(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE, SMP_CACHE_BYTES); + if (!hpet_res) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE); hpet_res->name = (void *)&hpet_res[1]; hpet_res->flags = IORESOURCE_MEM; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 264e3221d923..53aa234a6803 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2581,6 +2581,8 @@ static struct resource * __init ioapic_setup_resources(void) n *= nr_ioapics; mem = memblock_alloc(n, SMP_CACHE_BYTES); + if (!mem) + panic("%s: Failed to allocate %lu bytes\n", __func__, n); res = (void *)mem; mem += sizeof(struct resource) * nr_ioapics; @@ -2625,6 +2627,9 @@ fake_ioapic_page: #endif ioapic_phys = (unsigned long)memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (!ioapic_phys) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, PAGE_SIZE, PAGE_SIZE); ioapic_phys = __pa(ioapic_phys); } set_fixmap_nocache(idx, ioapic_phys); diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 822b7db634ee..e49b77283924 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -4,6 +4,7 @@ #include <linux/sched.h> #include <linux/kernfs.h> +#include <linux/fs_context.h> #include <linux/jump_label.h> #define MSR_IA32_L3_QOS_CFG 0xc81 @@ -40,6 +41,21 @@ #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) + +struct rdt_fs_context { + struct kernfs_fs_context kfc; + bool enable_cdpl2; + bool enable_cdpl3; + bool enable_mba_mbps; +}; + +static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) +{ + struct kernfs_fs_context *kfc = fc->fs_private; + + return container_of(kfc, struct rdt_fs_context, kfc); +} + DECLARE_STATIC_KEY_FALSE(rdt_enable_key); /** diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 8388adf241b2..399601eda8e4 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -24,6 +24,7 @@ #include <linux/cpu.h> #include <linux/debugfs.h> #include <linux/fs.h> +#include <linux/fs_parser.h> #include <linux/sysfs.h> #include <linux/kernfs.h> #include <linux/seq_buf.h> @@ -32,6 +33,7 @@ #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/task_work.h> +#include <linux/user_namespace.h> #include <uapi/linux/magic.h> @@ -1858,46 +1860,6 @@ static void cdp_disable_all(void) cdpl2_disable(); } -static int parse_rdtgroupfs_options(char *data) -{ - char *token, *o = data; - int ret = 0; - - while ((token = strsep(&o, ",")) != NULL) { - if (!*token) { - ret = -EINVAL; - goto out; - } - - if (!strcmp(token, "cdp")) { - ret = cdpl3_enable(); - if (ret) - goto out; - } else if (!strcmp(token, "cdpl2")) { - ret = cdpl2_enable(); - if (ret) - goto out; - } else if (!strcmp(token, "mba_MBps")) { - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - ret = set_mba_sc(true); - else - ret = -EINVAL; - if (ret) - goto out; - } else { - ret = -EINVAL; - goto out; - } - } - - return 0; - -out: - pr_err("Invalid mount option \"%s\"\n", token); - - return ret; -} - /* * We don't allow rdtgroup directories to be created anywhere * except the root directory. Thus when looking for the rdtgroup @@ -1969,13 +1931,27 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, struct kernfs_node **mon_data_kn); -static struct dentry *rdt_mount(struct file_system_type *fs_type, - int flags, const char *unused_dev_name, - void *data) +static int rdt_enable_ctx(struct rdt_fs_context *ctx) +{ + int ret = 0; + + if (ctx->enable_cdpl2) + ret = cdpl2_enable(); + + if (!ret && ctx->enable_cdpl3) + ret = cdpl3_enable(); + + if (!ret && ctx->enable_mba_mbps) + ret = set_mba_sc(true); + + return ret; +} + +static int rdt_get_tree(struct fs_context *fc) { + struct rdt_fs_context *ctx = rdt_fc2context(fc); struct rdt_domain *dom; struct rdt_resource *r; - struct dentry *dentry; int ret; cpus_read_lock(); @@ -1984,53 +1960,42 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, * resctrl file system can only be mounted once. */ if (static_branch_unlikely(&rdt_enable_key)) { - dentry = ERR_PTR(-EBUSY); + ret = -EBUSY; goto out; } - ret = parse_rdtgroupfs_options(data); - if (ret) { - dentry = ERR_PTR(ret); + ret = rdt_enable_ctx(ctx); + if (ret < 0) goto out_cdp; - } closid_init(); ret = rdtgroup_create_info_dir(rdtgroup_default.kn); - if (ret) { - dentry = ERR_PTR(ret); - goto out_cdp; - } + if (ret < 0) + goto out_mba; if (rdt_mon_capable) { ret = mongroup_create_dir(rdtgroup_default.kn, NULL, "mon_groups", &kn_mongrp); - if (ret) { - dentry = ERR_PTR(ret); + if (ret < 0) goto out_info; - } kernfs_get(kn_mongrp); ret = mkdir_mondata_all(rdtgroup_default.kn, &rdtgroup_default, &kn_mondata); - if (ret) { - dentry = ERR_PTR(ret); + if (ret < 0) goto out_mongrp; - } kernfs_get(kn_mondata); rdtgroup_default.mon.mon_data_kn = kn_mondata; } ret = rdt_pseudo_lock_init(); - if (ret) { - dentry = ERR_PTR(ret); + if (ret) goto out_mondata; - } - dentry = kernfs_mount(fs_type, flags, rdt_root, - RDTGROUP_SUPER_MAGIC, NULL); - if (IS_ERR(dentry)) + ret = kernfs_get_tree(fc); + if (ret < 0) goto out_psl; if (rdt_alloc_capable) @@ -2059,14 +2024,95 @@ out_mongrp: kernfs_remove(kn_mongrp); out_info: kernfs_remove(kn_info); +out_mba: + if (ctx->enable_mba_mbps) + set_mba_sc(false); out_cdp: cdp_disable_all(); out: rdt_last_cmd_clear(); mutex_unlock(&rdtgroup_mutex); cpus_read_unlock(); + return ret; +} + +enum rdt_param { + Opt_cdp, + Opt_cdpl2, + Opt_mba_mpbs, + nr__rdt_params +}; + +static const struct fs_parameter_spec rdt_param_specs[] = { + fsparam_flag("cdp", Opt_cdp), + fsparam_flag("cdpl2", Opt_cdpl2), + fsparam_flag("mba_mpbs", Opt_mba_mpbs), + {} +}; + +static const struct fs_parameter_description rdt_fs_parameters = { + .name = "rdt", + .specs = rdt_param_specs, +}; + +static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct rdt_fs_context *ctx = rdt_fc2context(fc); + struct fs_parse_result result; + int opt; + + opt = fs_parse(fc, &rdt_fs_parameters, param, &result); + if (opt < 0) + return opt; - return dentry; + switch (opt) { + case Opt_cdp: + ctx->enable_cdpl3 = true; + return 0; + case Opt_cdpl2: + ctx->enable_cdpl2 = true; + return 0; + case Opt_mba_mpbs: + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return -EINVAL; + ctx->enable_mba_mbps = true; + return 0; + } + + return -EINVAL; +} + +static void rdt_fs_context_free(struct fs_context *fc) +{ + struct rdt_fs_context *ctx = rdt_fc2context(fc); + + kernfs_free_fs_context(fc); + kfree(ctx); +} + +static const struct fs_context_operations rdt_fs_context_ops = { + .free = rdt_fs_context_free, + .parse_param = rdt_parse_param, + .get_tree = rdt_get_tree, +}; + +static int rdt_init_fs_context(struct fs_context *fc) +{ + struct rdt_fs_context *ctx; + + ctx = kzalloc(sizeof(struct rdt_fs_context), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->kfc.root = rdt_root; + ctx->kfc.magic = RDTGROUP_SUPER_MAGIC; + fc->fs_private = &ctx->kfc; + fc->ops = &rdt_fs_context_ops; + if (fc->user_ns) + put_user_ns(fc->user_ns); + fc->user_ns = get_user_ns(&init_user_ns); + fc->global = true; + return 0; } static int reset_all_ctrls(struct rdt_resource *r) @@ -2239,9 +2285,10 @@ static void rdt_kill_sb(struct super_block *sb) } static struct file_system_type rdt_fs_type = { - .name = "resctrl", - .mount = rdt_mount, - .kill_sb = rdt_kill_sb, + .name = "resctrl", + .init_fs_context = rdt_init_fs_context, + .parameters = &rdt_fs_parameters, + .kill_sb = rdt_kill_sb, }; static int mon_addfile(struct kernfs_node *parent_kn, const char *name, diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index a687d10da417..2879e234e193 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -14,6 +14,7 @@ #include <linux/acpi.h> #include <linux/firmware-map.h> #include <linux/sort.h> +#include <linux/memory_hotplug.h> #include <asm/e820/api.h> #include <asm/setup.h> @@ -775,7 +776,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) { u64 addr; - addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); + addr = memblock_phys_alloc(size, align); if (addr) { e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n"); @@ -878,6 +879,10 @@ static int __init parse_memopt(char *p) e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1); +#ifdef CONFIG_MEMORY_HOTPLUG + max_mem_size = mem_size; +#endif + return 0; } early_param("mem", parse_memopt); @@ -1092,6 +1097,9 @@ void __init e820__reserve_resources(void) res = memblock_alloc(sizeof(*res) * e820_table->nr_entries, SMP_CACHE_BYTES); + if (!res) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(*res) * e820_table->nr_entries); e820_res = res; for (i = 0; i < e820_table->nr_entries; i++) { diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 3e3789c8f8e1..ef49517f6bb2 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -49,7 +49,7 @@ int ftrace_arch_code_modify_post_process(void) union ftrace_code_union { char code[MCOUNT_INSN_SIZE]; struct { - unsigned char e8; + unsigned char op; int offset; } __attribute__((packed)); }; @@ -59,20 +59,23 @@ static int ftrace_calc_offset(long ip, long addr) return (int)(addr - ip); } -static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +static unsigned char * +ftrace_text_replace(unsigned char op, unsigned long ip, unsigned long addr) { static union ftrace_code_union calc; - calc.e8 = 0xe8; + calc.op = op; calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - /* - * No locking needed, this must be called via kstop_machine - * which in essence is like running on a uniprocessor machine. - */ return calc.code; } +static unsigned char * +ftrace_call_replace(unsigned long ip, unsigned long addr) +{ + return ftrace_text_replace(0xe8, ip, addr); +} + static inline int within(unsigned long addr, unsigned long start, unsigned long end) { @@ -665,22 +668,6 @@ int __init ftrace_dyn_arch_init(void) return 0; } -#if defined(CONFIG_X86_64) || defined(CONFIG_FUNCTION_GRAPH_TRACER) -static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) -{ - static union ftrace_code_union calc; - - /* Jmp not a call (ignore the .e8) */ - calc.e8 = 0xe9; - calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - - /* - * ftrace external locks synchronize the access to the static variable. - */ - return calc.code; -} -#endif - /* Currently only x86_64 supports dynamic trampolines */ #ifdef CONFIG_X86_64 @@ -892,8 +879,8 @@ static void *addr_from_call(void *ptr) return NULL; /* Make sure this is a call */ - if (WARN_ON_ONCE(calc.e8 != 0xe8)) { - pr_warn("Expected e8, got %x\n", calc.e8); + if (WARN_ON_ONCE(calc.op != 0xe8)) { + pr_warn("Expected e8, got %x\n", calc.op); return NULL; } @@ -964,6 +951,11 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops) #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); +static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) +{ + return ftrace_text_replace(0xe9, ip, addr); +} + static int ftrace_mod_jmp(unsigned long ip, void *func) { unsigned char *new; diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 1f3b77367948..22f60dd26460 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -538,9 +538,17 @@ static int bzImage64_cleanup(void *loader_data) #ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) { - return verify_pefile_signature(kernel, kernel_len, - VERIFY_USE_SECONDARY_KEYRING, - VERIFYING_KEXEC_PE_SIGNATURE); + int ret; + + ret = verify_pefile_signature(kernel, kernel_len, + VERIFY_USE_SECONDARY_KEYRING, + VERIFYING_KEXEC_PE_SIGNATURE); + if (ret == -ENOKEY && IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING)) { + ret = verify_pefile_signature(kernel, kernel_len, + VERIFY_USE_PLATFORM_KEYRING, + VERIFYING_KEXEC_PE_SIGNATURE); + } + return ret; } #endif diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index e811d4d1c824..904494b924c1 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -104,12 +104,8 @@ static u64 kvm_sched_clock_read(void) static inline void kvm_sched_clock_init(bool stable) { - if (!stable) { - pv_ops.time.sched_clock = kvm_clock_read; + if (!stable) clear_sched_clock_stable(); - return; - } - kvm_sched_clock_offset = kvm_clock_read(); pv_ops.time.sched_clock = kvm_sched_clock_read; @@ -355,6 +351,20 @@ void __init kvmclock_init(void) machine_ops.crash_shutdown = kvm_crash_shutdown; #endif kvm_get_preset_lpj(); + + /* + * X86_FEATURE_NONSTOP_TSC is TSC runs at constant rate + * with P/T states and does not stop in deep C-states. + * + * Invariant TSC exposed by host means kvmclock is not necessary: + * can use TSC as clocksource. + * + */ + if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && + boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && + !check_tsc_unstable()) + kvm_clock.rating = 299; + clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); pv_info.name = "KVM"; } diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 13af08827eef..4bf46575568a 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -106,22 +106,22 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, void *ptr; if (!node_online(node) || !NODE_DATA(node)) { - ptr = memblock_alloc_from_nopanic(size, align, goal); + ptr = memblock_alloc_from(size, align, goal); pr_info("cpu %d has no node %d or node-local memory\n", cpu, node); pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", cpu, size, __pa(ptr)); } else { - ptr = memblock_alloc_try_nid_nopanic(size, align, goal, - MEMBLOCK_ALLOC_ACCESSIBLE, - node); + ptr = memblock_alloc_try_nid(size, align, goal, + MEMBLOCK_ALLOC_ACCESSIBLE, + node); pr_debug("per cpu data for cpu%d %lu bytes on node%d at %016lx\n", cpu, size, node, __pa(ptr)); } return ptr; #else - return memblock_alloc_from_nopanic(size, align, goal); + return memblock_alloc_from(size, align, goal); #endif } |
