diff options
Diffstat (limited to 'arch/x86/kernel/cpu')
| -rw-r--r-- | arch/x86/kernel/cpu/amd.c | 28 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/bugs.c | 283 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/centaur.c | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/common.c | 166 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/hypervisor.c | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/intel.c | 66 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/intel_rdt.c | 76 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/intel_rdt.h | 5 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 117 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/dev-mcelog.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce-severity.c | 26 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce.c | 31 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce_amd.c | 29 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/microcode/core.c | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/microcode/intel.c | 42 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/scattered.c | 4 |
16 files changed, 749 insertions, 138 deletions
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index bcb75dc97d44..ea831c858195 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -829,8 +829,32 @@ static void init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_K8); if (cpu_has(c, X86_FEATURE_XMM2)) { - /* MFENCE stops RDTSC speculation */ - set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + unsigned long long val; + int ret; + + /* + * A serializing LFENCE has less overhead than MFENCE, so + * use it for execution serialization. On families which + * don't have that MSR, LFENCE is already serializing. + * msr_set_bit() uses the safe accessors, too, even if the MSR + * is not present. + */ + msr_set_bit(MSR_F10H_DECFG, + MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + + /* + * Verify that the MSR write was successful (could be running + * under a hypervisor) and only then assume that LFENCE is + * serializing. + */ + ret = rdmsrl_safe(MSR_F10H_DECFG, &val); + if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) { + /* A serializing LFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); + } else { + /* MFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + } } /* diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index ba0b2424c9b0..71949bf2de5a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -10,6 +10,11 @@ */ #include <linux/init.h> #include <linux/utsname.h> +#include <linux/cpu.h> +#include <linux/module.h> + +#include <asm/nospec-branch.h> +#include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> @@ -19,6 +24,9 @@ #include <asm/alternative.h> #include <asm/pgtable.h> #include <asm/set_memory.h> +#include <asm/intel-family.h> + +static void __init spectre_v2_select_mitigation(void); void __init check_bugs(void) { @@ -29,6 +37,9 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); } + /* Select the proper spectre mitigation before patching alternatives */ + spectre_v2_select_mitigation(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -60,3 +71,275 @@ void __init check_bugs(void) set_memory_4k((unsigned long)__va(0), 1); #endif } + +/* The kernel command line selection */ +enum spectre_v2_mitigation_cmd { + SPECTRE_V2_CMD_NONE, + SPECTRE_V2_CMD_AUTO, + SPECTRE_V2_CMD_FORCE, + SPECTRE_V2_CMD_RETPOLINE, + SPECTRE_V2_CMD_RETPOLINE_GENERIC, + SPECTRE_V2_CMD_RETPOLINE_AMD, +}; + +static const char *spectre_v2_strings[] = { + [SPECTRE_V2_NONE] = "Vulnerable", + [SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline", + [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline", + [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", + [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", +}; + +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V2 : " fmt + +static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; + +#ifdef RETPOLINE +static bool spectre_v2_bad_module; + +bool retpoline_module_ok(bool has_retpoline) +{ + if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline) + return true; + + pr_err("System may be vulnerable to spectre v2\n"); + spectre_v2_bad_module = true; + return false; +} + +static inline const char *spectre_v2_module_string(void) +{ + return spectre_v2_bad_module ? " - vulnerable module loaded" : ""; +} +#else +static inline const char *spectre_v2_module_string(void) { return ""; } +#endif + +static void __init spec2_print_if_insecure(const char *reason) +{ + if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s selected on command line.\n", reason); +} + +static void __init spec2_print_if_secure(const char *reason) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s selected on command line.\n", reason); +} + +static inline bool retp_compiler(void) +{ + return __is_defined(RETPOLINE); +} + +static inline bool match_option(const char *arg, int arglen, const char *opt) +{ + int len = strlen(opt); + + return len == arglen && !strncmp(arg, opt, len); +} + +static const struct { + const char *option; + enum spectre_v2_mitigation_cmd cmd; + bool secure; +} mitigation_options[] = { + { "off", SPECTRE_V2_CMD_NONE, false }, + { "on", SPECTRE_V2_CMD_FORCE, true }, + { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "auto", SPECTRE_V2_CMD_AUTO, false }, +}; + +static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) +{ + char arg[20]; + int ret, i; + enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; + + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_NONE; + else { + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, + sizeof(arg)); + if (ret < 0) + return SPECTRE_V2_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { + if (!match_option(arg, ret, mitigation_options[i].option)) + continue; + cmd = mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + } + + if ((cmd == SPECTRE_V2_CMD_RETPOLINE || + cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || + cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && + !IS_ENABLED(CONFIG_RETPOLINE)) { + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); + return SPECTRE_V2_CMD_AUTO; + } + + if (mitigation_options[i].secure) + spec2_print_if_secure(mitigation_options[i].option); + else + spec2_print_if_insecure(mitigation_options[i].option); + + return cmd; +} + +/* Check for Skylake-like CPUs (for RSB handling) */ +static bool __init is_skylake_era(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + boot_cpu_data.x86 == 6) { + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_SKYLAKE_MOBILE: + case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_KABYLAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_DESKTOP: + return true; + } + } + return false; +} + +static void __init spectre_v2_select_mitigation(void) +{ + enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); + enum spectre_v2_mitigation mode = SPECTRE_V2_NONE; + + /* + * If the CPU is not affected and the command line mode is NONE or AUTO + * then nothing to do. + */ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) && + (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO)) + return; + + switch (cmd) { + case SPECTRE_V2_CMD_NONE: + return; + + case SPECTRE_V2_CMD_FORCE: + case SPECTRE_V2_CMD_AUTO: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; + case SPECTRE_V2_CMD_RETPOLINE_AMD: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_amd; + break; + case SPECTRE_V2_CMD_RETPOLINE_GENERIC: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_generic; + break; + case SPECTRE_V2_CMD_RETPOLINE: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; + } + pr_err("kernel not compiled with retpoline; no mitigation available!"); + return; + +retpoline_auto: + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + retpoline_amd: + if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { + pr_err("LFENCE not serializing. Switching to generic retpoline\n"); + goto retpoline_generic; + } + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : + SPECTRE_V2_RETPOLINE_MINIMAL_AMD; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD); + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } else { + retpoline_generic: + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC : + SPECTRE_V2_RETPOLINE_MINIMAL; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } + + spectre_v2_enabled = mode; + pr_info("%s\n", spectre_v2_strings[mode]); + + /* + * If neither SMEP or KPTI are available, there is a risk of + * hitting userspace addresses in the RSB after a context switch + * from a shallow call stack to a deeper one. To prevent this fill + * the entire RSB, even when using IBRS. + * + * Skylake era CPUs have a separate issue with *underflow* of the + * RSB, when they will predict 'ret' targets from the generic BTB. + * The proper mitigation for this is IBRS. If IBRS is not supported + * or deactivated in favour of retpolines the RSB fill on context + * switch is required. + */ + if ((!boot_cpu_has(X86_FEATURE_PTI) && + !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { + setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); + pr_info("Filling RSB on context switch\n"); + } + + /* Initialize Indirect Branch Prediction Barrier if supported */ + if (boot_cpu_has(X86_FEATURE_IBPB)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + pr_info("Enabling Indirect Branch Prediction Barrier\n"); + } +} + +#undef pr_fmt + +#ifdef CONFIG_SYSFS +ssize_t cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + return sprintf(buf, "Not affected\n"); + if (boot_cpu_has(X86_FEATURE_PTI)) + return sprintf(buf, "Mitigation: PTI\n"); + return sprintf(buf, "Vulnerable\n"); +} + +ssize_t cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) + return sprintf(buf, "Not affected\n"); + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); +} + +ssize_t cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + return sprintf(buf, "Not affected\n"); + + return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + spectre_v2_module_string()); +} +#endif + +void __ibp_barrier(void) +{ + __wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0); +} +EXPORT_SYMBOL_GPL(__ibp_barrier); diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 68bc6d9b3132..c578cd29c2d2 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -106,6 +106,10 @@ static void early_init_centaur(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSENTER32); #endif + if (c->x86_power & (1 << 8)) { + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); + } } static void init_centaur(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index fa998ca8aa5a..d63f4b5706e4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -47,6 +47,8 @@ #include <asm/pat.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> #ifdef CONFIG_X86_LOCAL_APIC #include <asm/uv/uv.h> @@ -476,8 +478,8 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c) return NULL; /* Not found */ } -__u32 cpu_caps_cleared[NCAPINTS]; -__u32 cpu_caps_set[NCAPINTS]; +__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +__u32 cpu_caps_set[NCAPINTS + NBUGINTS]; void load_percpu_segment(int cpu) { @@ -490,28 +492,23 @@ void load_percpu_segment(int cpu) load_stack_canary_segment(); } -/* Setup the fixmap mapping only once per-processor */ -static inline void setup_fixmap_gdt(int cpu) -{ -#ifdef CONFIG_X86_64 - /* On 64-bit systems, we use a read-only fixmap GDT. */ - pgprot_t prot = PAGE_KERNEL_RO; -#else - /* - * On native 32-bit systems, the GDT cannot be read-only because - * our double fault handler uses a task gate, and entering through - * a task gate needs to change an available TSS to busy. If the GDT - * is read-only, that will triple fault. - * - * On Xen PV, the GDT must be read-only because the hypervisor requires - * it. - */ - pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ? - PAGE_KERNEL_RO : PAGE_KERNEL; +#ifdef CONFIG_X86_32 +/* The 32-bit entry code needs to find cpu_entry_area. */ +DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); #endif - __set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot); -} +#ifdef CONFIG_X86_64 +/* + * Special IST stacks which the CPU switches to when it calls + * an IST-marked descriptor entry. Up to 7 stacks (hardware + * limit), all of them are 4K, except the debug stack which + * is 8K. + */ +static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { + [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, + [DEBUG_STACK - 1] = DEBUG_STKSZ +}; +#endif /* Load the original GDT from the per-cpu structure */ void load_direct_gdt(int cpu) @@ -747,12 +744,32 @@ static void apply_forced_caps(struct cpuinfo_x86 *c) { int i; - for (i = 0; i < NCAPINTS; i++) { + for (i = 0; i < NCAPINTS + NBUGINTS; i++) { c->x86_capability[i] &= ~cpu_caps_cleared[i]; c->x86_capability[i] |= cpu_caps_set[i]; } } +static void init_speculation_control(struct cpuinfo_x86 *c) +{ + /* + * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support, + * and they also have a different bit for STIBP support. Also, + * a hypervisor might have set the individual AMD bits even on + * Intel CPUs, for finer-grained selection of what's available. + * + * We use the AMD bits in 0x8000_0008 EBX as the generic hardware + * features, which are visible in /proc/cpuinfo and used by the + * kernel. So set those accordingly from the Intel bits. + */ + if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_IBPB); + } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) + set_cpu_cap(c, X86_FEATURE_STIBP); +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -774,6 +791,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); c->x86_capability[CPUID_7_0_EBX] = ebx; c->x86_capability[CPUID_7_ECX] = ecx; + c->x86_capability[CPUID_7_EDX] = edx; } /* Extended state features: level 0x0000000d */ @@ -846,6 +864,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); init_scattered_cpuid_features(c); + init_speculation_control(c); /* * Clear/Set all flags overridden by options, after probe. @@ -881,6 +900,41 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #endif } +static const __initconst struct x86_cpu_id cpu_no_speculation[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_CENTAUR, 5 }, + { X86_VENDOR_INTEL, 5 }, + { X86_VENDOR_NSC, 5 }, + { X86_VENDOR_ANY, 4 }, + {} +}; + +static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { + { X86_VENDOR_AMD }, + {} +}; + +static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c) +{ + u64 ia32_cap = 0; + + if (x86_match_cpu(cpu_no_meltdown)) + return false; + + if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + + /* Rogue Data Cache Load? No! */ + if (ia32_cap & ARCH_CAP_RDCL_NO) + return false; + + return true; +} + /* * Do minimum CPU detection early. * Fields really needed: vendor, cpuid_level, family, model, mask, @@ -927,6 +981,14 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) } setup_force_cpu_cap(X86_FEATURE_ALWAYS); + + if (!x86_match_cpu(cpu_no_speculation)) { + if (cpu_vulnerable_to_meltdown(c)) + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + } + fpu__init_system(c); #ifdef CONFIG_X86_32 @@ -1250,7 +1312,7 @@ void enable_sep_cpu(void) return; cpu = get_cpu(); - tss = &per_cpu(cpu_tss, cpu); + tss = &per_cpu(cpu_tss_rw, cpu); /* * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field -- @@ -1259,11 +1321,7 @@ void enable_sep_cpu(void) tss->x86_tss.ss1 = __KERNEL_CS; wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0); - - wrmsr(MSR_IA32_SYSENTER_ESP, - (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack), - 0); - + wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0); wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); put_cpu(); @@ -1357,25 +1415,22 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -/* - * Special IST stacks which the CPU switches to when it calls - * an IST-marked descriptor entry. Up to 7 stacks (hardware - * limit), all of them are 4K, except the debug stack which - * is 8K. - */ -static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { - [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, - [DEBUG_STACK - 1] = DEBUG_STKSZ -}; - -static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks - [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); - /* May not be marked __init: used by software suspend */ void syscall_init(void) { + extern char _entry_trampoline[]; + extern char entry_SYSCALL_64_trampoline[]; + + int cpu = smp_processor_id(); + unsigned long SYSCALL64_entry_trampoline = + (unsigned long)get_cpu_entry_area(cpu)->entry_trampoline + + (entry_SYSCALL_64_trampoline - _entry_trampoline); + wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); - wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); + if (static_cpu_has(X86_FEATURE_PTI)) + wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline); + else + wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat); @@ -1386,7 +1441,7 @@ void syscall_init(void) * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit). */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); @@ -1530,7 +1585,7 @@ void cpu_init(void) if (cpu) load_ucode_ap(); - t = &per_cpu(cpu_tss, cpu); + t = &per_cpu(cpu_tss_rw, cpu); oist = &per_cpu(orig_ist, cpu); #ifdef CONFIG_NUMA @@ -1569,7 +1624,7 @@ void cpu_init(void) * set up and load the per-CPU TSS */ if (!oist->ist[0]) { - char *estacks = per_cpu(exception_stacks, cpu); + char *estacks = get_cpu_entry_area(cpu)->exception_stacks; for (v = 0; v < N_EXCEPTION_STACKS; v++) { estacks += exception_stack_sizes[v]; @@ -1580,7 +1635,7 @@ void cpu_init(void) } } - t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; /* * <= is required because the CPU will access up to @@ -1596,11 +1651,12 @@ void cpu_init(void) enter_lazy_tlb(&init_mm, me); /* - * Initialize the TSS. Don't bother initializing sp0, as the initial - * task never enters user mode. + * Initialize the TSS. sp0 points to the entry trampoline stack + * regardless of what task is running. */ - set_tss_desc(cpu, t); + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); + load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1)); load_mm_ldt(&init_mm); @@ -1612,7 +1668,6 @@ void cpu_init(void) if (is_uv_system()) uv_cpu_init(); - setup_fixmap_gdt(cpu); load_fixmap_gdt(cpu); } @@ -1622,7 +1677,7 @@ void cpu_init(void) { int cpu = smp_processor_id(); struct task_struct *curr = current; - struct tss_struct *t = &per_cpu(cpu_tss, cpu); + struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu); wait_for_master_cpu(cpu); @@ -1657,12 +1712,12 @@ void cpu_init(void) * Initialize the TSS. Don't bother initializing sp0, as the initial * task never enters user mode. */ - set_tss_desc(cpu, t); + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); load_mm_ldt(&init_mm); - t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; #ifdef CONFIG_DOUBLEFAULT /* Set up doublefault TSS pointer in the GDT */ @@ -1674,7 +1729,6 @@ void cpu_init(void) fpu__init_cpu(); - setup_fixmap_gdt(cpu); load_fixmap_gdt(cpu); } #endif diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index bea8d3e24f50..479ca4728de0 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -31,6 +31,7 @@ extern const struct hypervisor_x86 x86_hyper_ms_hyperv; extern const struct hypervisor_x86 x86_hyper_xen_pv; extern const struct hypervisor_x86 x86_hyper_xen_hvm; extern const struct hypervisor_x86 x86_hyper_kvm; +extern const struct hypervisor_x86 x86_hyper_jailhouse; static const __initconst struct hypervisor_x86 * const hypervisors[] = { @@ -45,6 +46,9 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] = #ifdef CONFIG_KVM_GUEST &x86_hyper_kvm, #endif +#ifdef CONFIG_JAILHOUSE_GUEST + &x86_hyper_jailhouse, +#endif }; enum x86_hypervisor_type x86_hyper_type; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index b1af22073e28..319bf989fad1 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -102,6 +102,59 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) ELF_HWCAP2 |= HWCAP2_RING3MWAIT; } +/* + * Early microcode releases for the Spectre v2 mitigation were broken. + * Information taken from; + * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-update-guidance.pdf + * - https://kb.vmware.com/s/article/52345 + * - Microcode revisions observed in the wild + * - Release note from 20180108 microcode release + */ +struct sku_microcode { + u8 model; + u8 stepping; + u32 microcode; +}; +static const struct sku_microcode spectre_bad_microcodes[] = { + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x84 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x84 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 }, + { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, + { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, + { INTEL_FAM6_SKYLAKE_MOBILE, 0x03, 0xc2 }, + { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, + { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, + { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, + { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 }, + { INTEL_FAM6_BROADWELL_XEON_D, 0x03, 0x07000011 }, + { INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 }, + { INTEL_FAM6_HASWELL_ULT, 0x01, 0x21 }, + { INTEL_FAM6_HASWELL_GT3E, 0x01, 0x18 }, + { INTEL_FAM6_HASWELL_CORE, 0x03, 0x23 }, + { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, + { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, + { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, + /* Updated in the 20180108 release; blacklist until we know otherwise */ + { INTEL_FAM6_ATOM_GEMINI_LAKE, 0x01, 0x22 }, + /* Observed in the wild */ + { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, + { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, +}; + +static bool bad_spectre_microcode(struct cpuinfo_x86 *c) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { + if (c->x86_model == spectre_bad_microcodes[i].model && + c->x86_mask == spectre_bad_microcodes[i].stepping) + return (c->microcode <= spectre_bad_microcodes[i].microcode); + } + return false; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -122,6 +175,19 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) c->microcode = intel_get_microcode_revision(); + /* Now if any of them are set, check the blacklist and clear the lot */ + if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) || + cpu_has(c, X86_FEATURE_INTEL_STIBP) || + cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) || + cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) { + pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n"); + setup_clear_cpu_cap(X86_FEATURE_IBRS); + setup_clear_cpu_cap(X86_FEATURE_IBPB); + setup_clear_cpu_cap(X86_FEATURE_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); + setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); + } + /* * Atom erratum AAE44/AAF40/AAG38/AAH41: * diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 88dcf8479013..410629f10ad3 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -135,6 +135,40 @@ struct rdt_resource rdt_resources_all[] = { .format_str = "%d=%0*x", .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_L2DATA] = + { + .rid = RDT_RESOURCE_L2DATA, + .name = "L2DATA", + .domains = domain_init(RDT_RESOURCE_L2DATA), + .msr_base = IA32_L2_CBM_BASE, + .msr_update = cat_wrmsr, + .cache_level = 2, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 2, + .cbm_idx_offset = 0, + }, + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, + [RDT_RESOURCE_L2CODE] = + { + .rid = RDT_RESOURCE_L2CODE, + .name = "L2CODE", + .domains = domain_init(RDT_RESOURCE_L2CODE), + .msr_base = IA32_L2_CBM_BASE, + .msr_update = cat_wrmsr, + .cache_level = 2, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 2, + .cbm_idx_offset = 1, + }, + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, [RDT_RESOURCE_MBA] = { .rid = RDT_RESOURCE_MBA, @@ -259,15 +293,15 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) r->alloc_enabled = true; } -static void rdt_get_cdp_l3_config(int type) +static void rdt_get_cdp_config(int level, int type) { - struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3]; + struct rdt_resource *r_l = &rdt_resources_all[level]; struct rdt_resource *r = &rdt_resources_all[type]; - r->num_closid = r_l3->num_closid / 2; - r->cache.cbm_len = r_l3->cache.cbm_len; - r->default_ctrl = r_l3->default_ctrl; - r->cache.shareable_bits = r_l3->cache.shareable_bits; + r->num_closid = r_l->num_closid / 2; + r->cache.cbm_len = r_l->cache.cbm_len; + r->default_ctrl = r_l->default_ctrl; + r->cache.shareable_bits = r_l->cache.shareable_bits; r->data_width = (r->cache.cbm_len + 3) / 4; r->alloc_capable = true; /* @@ -277,6 +311,18 @@ static void rdt_get_cdp_l3_config(int type) r->alloc_enabled = false; } +static void rdt_get_cdp_l3_config(void) +{ + rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA); + rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3CODE); +} + +static void rdt_get_cdp_l2_config(void) +{ + rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA); + rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2CODE); +} + static int get_cache_id(int cpu, int level) { struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu); @@ -525,10 +571,6 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) */ if (static_branch_unlikely(&rdt_mon_enable_key)) rmdir_mondata_subdir_allrdtgrp(r, d->id); - kfree(d->ctrl_val); - kfree(d->rmid_busy_llc); - kfree(d->mbm_total); - kfree(d->mbm_local); list_del(&d->list); if (is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); @@ -545,6 +587,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cancel_delayed_work(&d->cqm_limbo); } + kfree(d->ctrl_val); + kfree(d->rmid_busy_llc); + kfree(d->mbm_total); + kfree(d->mbm_local); kfree(d); return; } @@ -645,6 +691,7 @@ enum { RDT_FLAG_L3_CAT, RDT_FLAG_L3_CDP, RDT_FLAG_L2_CAT, + RDT_FLAG_L2_CDP, RDT_FLAG_MBA, }; @@ -667,6 +714,7 @@ static struct rdt_options rdt_options[] __initdata = { RDT_OPT(RDT_FLAG_L3_CAT, "l3cat", X86_FEATURE_CAT_L3), RDT_OPT(RDT_FLAG_L3_CDP, "l3cdp", X86_FEATURE_CDP_L3), RDT_OPT(RDT_FLAG_L2_CAT, "l2cat", X86_FEATURE_CAT_L2), + RDT_OPT(RDT_FLAG_L2_CDP, "l2cdp", X86_FEATURE_CDP_L2), RDT_OPT(RDT_FLAG_MBA, "mba", X86_FEATURE_MBA), }; #define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options) @@ -729,15 +777,15 @@ static __init bool get_rdt_alloc_resources(void) if (rdt_cpu_has(X86_FEATURE_CAT_L3)) { rdt_get_cache_alloc_cfg(1, &rdt_resources_all[RDT_RESOURCE_L3]); - if (rdt_cpu_has(X86_FEATURE_CDP_L3)) { - rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA); - rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE); - } + if (rdt_cpu_has(X86_FEATURE_CDP_L3)) + rdt_get_cdp_l3_config(); ret = true; } if (rdt_cpu_has(X86_FEATURE_CAT_L2)) { /* CPUID 0x10.2 fields are same format at 0x10.1 */ rdt_get_cache_alloc_cfg(2, &rdt_resources_all[RDT_RESOURCE_L2]); + if (rdt_cpu_has(X86_FEATURE_CDP_L2)) + rdt_get_cdp_l2_config(); ret = true; } diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 3397244984f5..3fd7a70ee04a 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -7,12 +7,15 @@ #include <linux/jump_label.h> #define IA32_L3_QOS_CFG 0xc81 +#define IA32_L2_QOS_CFG 0xc82 #define IA32_L3_CBM_BASE 0xc90 #define IA32_L2_CBM_BASE 0xd10 #define IA32_MBA_THRTL_BASE 0xd50 #define L3_QOS_CDP_ENABLE 0x01ULL +#define L2_QOS_CDP_ENABLE 0x01ULL + /* * Event IDs are used to program IA32_QM_EVTSEL before reading event * counter from IA32_QM_CTR @@ -357,6 +360,8 @@ enum { RDT_RESOURCE_L3DATA, RDT_RESOURCE_L3CODE, RDT_RESOURCE_L2, + RDT_RESOURCE_L2DATA, + RDT_RESOURCE_L2CODE, RDT_RESOURCE_MBA, /* Must be the last */ diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 64c5ff97ee0d..bdab7d2f51af 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -990,6 +990,7 @@ out_destroy: kernfs_remove(kn); return ret; } + static void l3_qos_cfg_update(void *arg) { bool *enable = arg; @@ -997,8 +998,17 @@ static void l3_qos_cfg_update(void *arg) wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL); } -static int set_l3_qos_cfg(struct rdt_resource *r, bool enable) +static void l2_qos_cfg_update(void *arg) { + bool *enable = arg; + + wrmsrl(IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL); +} + +static int set_cache_qos_cfg(int level, bool enable) +{ + void (*update)(void *arg); + struct rdt_resource *r_l; cpumask_var_t cpu_mask; struct rdt_domain *d; int cpu; @@ -1006,16 +1016,24 @@ static int set_l3_qos_cfg(struct rdt_resource *r, bool enable) if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; - list_for_each_entry(d, &r->domains, list) { + if (level == RDT_RESOURCE_L3) + update = l3_qos_cfg_update; + else if (level == RDT_RESOURCE_L2) + update = l2_qos_cfg_update; + else + return -EINVAL; + + r_l = &rdt_resources_all[level]; + list_for_each_entry(d, &r_l->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(&enable); /* Update QOS_CFG MSR on all other cpus in cpu_mask. */ - smp_call_function_many(cpu_mask, l3_qos_cfg_update, &enable, 1); + smp_call_function_many(cpu_mask, update, &enable, 1); put_cpu(); free_cpumask_var(cpu_mask); @@ -1023,52 +1041,99 @@ static int set_l3_qos_cfg(struct rdt_resource *r, bool enable) return 0; } -static int cdp_enable(void) +static int cdp_enable(int level, int data_type, int code_type) { - 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]; + struct rdt_resource *r_ldata = &rdt_resources_all[data_type]; + struct rdt_resource *r_lcode = &rdt_resources_all[code_type]; + struct rdt_resource *r_l = &rdt_resources_all[level]; int ret; - if (!r_l3->alloc_capable || !r_l3data->alloc_capable || - !r_l3code->alloc_capable) + if (!r_l->alloc_capable || !r_ldata->alloc_capable || + !r_lcode->alloc_capable) return -EINVAL; - ret = set_l3_qos_cfg(r_l3, true); + ret = set_cache_qos_cfg(level, true); if (!ret) { - r_l3->alloc_enabled = false; - r_l3data->alloc_enabled = true; - r_l3code->alloc_enabled = true; + r_l->alloc_enabled = false; + r_ldata->alloc_enabled = true; + r_lcode->alloc_enabled = true; } return ret; } -static void cdp_disable(void) +static int cdpl3_enable(void) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + return cdp_enable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, + RDT_RESOURCE_L3CODE); +} + +static int cdpl2_enable(void) +{ + return cdp_enable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA, + RDT_RESOURCE_L2CODE); +} + +static void cdp_disable(int level, int data_type, int code_type) +{ + struct rdt_resource *r = &rdt_resources_all[level]; r->alloc_enabled = r->alloc_capable; - if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) { - rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled = false; - rdt_resources_all[RDT_RESOURCE_L3CODE].alloc_enabled = false; - set_l3_qos_cfg(r, false); + if (rdt_resources_all[data_type].alloc_enabled) { + rdt_resources_all[data_type].alloc_enabled = false; + rdt_resources_all[code_type].alloc_enabled = false; + set_cache_qos_cfg(level, false); } } +static void cdpl3_disable(void) +{ + cdp_disable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, RDT_RESOURCE_L3CODE); +} + +static void cdpl2_disable(void) +{ + cdp_disable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA, RDT_RESOURCE_L2CODE); +} + +static void cdp_disable_all(void) +{ + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) + cdpl3_disable(); + if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) + cdpl2_disable(); +} + static int parse_rdtgroupfs_options(char *data) { char *token, *o = data; int ret = 0; while ((token = strsep(&o, ",")) != NULL) { - if (!*token) - return -EINVAL; + if (!*token) { + ret = -EINVAL; + goto out; + } - if (!strcmp(token, "cdp")) - ret = cdp_enable(); + if (!strcmp(token, "cdp")) { + ret = cdpl3_enable(); + if (ret) + goto out; + } else if (!strcmp(token, "cdpl2")) { + ret = cdpl2_enable(); + if (ret) + goto out; + } else { + ret = -EINVAL; + goto out; + } } + return 0; + +out: + pr_err("Invalid mount option \"%s\"\n", token); + return ret; } @@ -1223,7 +1288,7 @@ out_mongrp: out_info: kernfs_remove(kn_info); out_cdp: - cdp_disable(); + cdp_disable_all(); out: rdt_last_cmd_clear(); mutex_unlock(&rdtgroup_mutex); @@ -1383,7 +1448,7 @@ static void rdt_kill_sb(struct super_block *sb) /*Put everything back to default values. */ for_each_alloc_enabled_rdt_resource(r) reset_all_ctrls(r); - cdp_disable(); + cdp_disable_all(); rmdir_all_sub(); static_branch_disable_cpuslocked(&rdt_alloc_enable_key); static_branch_disable_cpuslocked(&rdt_mon_enable_key); diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c index 7f85b76f43bc..213e8c2ca702 100644 --- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c @@ -243,7 +243,7 @@ out: return err ? err : buf - ubuf; } -static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait) +static __poll_t mce_chrdev_poll(struct file *file, poll_table *wait) { poll_wait(file, &mce_chrdev_wait, wait); if (READ_ONCE(mcelog.next)) diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 4ca632a06e0b..5bbd06f38ff6 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -59,6 +59,7 @@ static struct severity { #define MCGMASK(x, y) .mcgmask = x, .mcgres = y #define MASK(x, y) .mask = x, .result = y #define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S) +#define MCI_UC_AR (MCI_STATUS_UC|MCI_STATUS_AR) #define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR) #define MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV) @@ -101,6 +102,22 @@ static struct severity { NOSER, BITCLR(MCI_STATUS_UC) ), + /* + * known AO MCACODs reported via MCE or CMC: + * + * SRAO could be signaled either via a machine check exception or + * CMCI with the corresponding bit S 1 or 0. So we don't need to + * check bit S for SRAO. + */ + MCESEV( + AO, "Action optional: memory scrubbing error", + SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB) + ), + MCESEV( + AO, "Action optional: last level cache writeback error", + SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB) + ), + /* ignore OVER for UCNA */ MCESEV( UCNA, "Uncorrected no action required", @@ -149,15 +166,6 @@ static struct severity { SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_SAR) ), - /* known AO MCACODs: */ - MCESEV( - AO, "Action optional: memory scrubbing error", - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD_SCRUBMSK, MCI_UC_S|MCACOD_SCRUB) - ), - MCESEV( - AO, "Action optional: last level cache writeback error", - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_S|MCACOD_L3WB) - ), MCESEV( SOME, "Action optional: unknown MCACOD", SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_S) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index b1d616d08eee..3a8e88a611eb 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -14,7 +14,6 @@ #include <linux/capability.h> #include <linux/miscdevice.h> #include <linux/ratelimit.h> -#include <linux/kallsyms.h> #include <linux/rcupdate.h> #include <linux/kobject.h> #include <linux/uaccess.h> @@ -235,7 +234,7 @@ static void __print_mce(struct mce *m) m->cs, m->ip); if (m->cs == __KERNEL_CS) - print_symbol("{%s}", m->ip); + pr_cont("{%pS}", (void *)m->ip); pr_cont("\n"); } @@ -503,10 +502,8 @@ static int mce_usable_address(struct mce *m) bool mce_is_memory_error(struct mce *m) { if (m->cpuvendor == X86_VENDOR_AMD) { - /* ErrCodeExt[20:16] */ - u8 xec = (m->status >> 16) & 0x1f; + return amd_mce_is_memory_error(m); - return (xec == 0x0 || xec == 0x8); } else if (m->cpuvendor == X86_VENDOR_INTEL) { /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes @@ -530,6 +527,17 @@ bool mce_is_memory_error(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_memory_error); +static bool mce_is_correctable(struct mce *m) +{ + if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) + return false; + + if (m->status & MCI_STATUS_UC) + return false; + + return true; +} + static bool cec_add_mce(struct mce *m) { if (!m) @@ -537,7 +545,7 @@ static bool cec_add_mce(struct mce *m) /* We eat only correctable DRAM errors with usable addresses. */ if (mce_is_memory_error(m) && - !(m->status & MCI_STATUS_UC) && + mce_is_correctable(m) && mce_usable_address(m)) if (!cec_add_elem(m->addr >> PAGE_SHIFT)) return true; @@ -582,7 +590,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; - memory_failure(pfn, MCE_VECTOR, 0); + memory_failure(pfn, 0); } return NOTIFY_OK; @@ -1046,7 +1054,7 @@ static int do_memory_failure(struct mce *m) pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr); if (!(m->mcgstatus & MCG_STATUS_RIPV)) flags |= MF_MUST_KILL; - ret = memory_failure(m->addr >> PAGE_SHIFT, MCE_VECTOR, flags); + ret = memory_failure(m->addr >> PAGE_SHIFT, flags); if (ret) pr_err("Memory error not recovered"); return ret; @@ -1325,7 +1333,7 @@ out_ist: EXPORT_SYMBOL_GPL(do_machine_check); #ifndef CONFIG_MEMORY_FAILURE -int memory_failure(unsigned long pfn, int vector, int flags) +int memory_failure(unsigned long pfn, int flags) { /* mce_severity() should not hand us an ACTION_REQUIRED error */ BUG_ON(flags & MF_ACTION_REQUIRED); @@ -1785,6 +1793,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code) void (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check; +dotraplinkage void do_mce(struct pt_regs *regs, long error_code) +{ + machine_check_vector(regs, error_code); +} + /* * Called for each booted CPU to set up machine checks. * Must be called with preempt off: diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 486f640b02ef..0f32ad242324 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -110,6 +110,20 @@ const char *smca_get_long_name(enum smca_bank_types t) } EXPORT_SYMBOL_GPL(smca_get_long_name); +static enum smca_bank_types smca_get_bank_type(struct mce *m) +{ + struct smca_bank *b; + + if (m->bank >= N_SMCA_BANK_TYPES) + return N_SMCA_BANK_TYPES; + + b = &smca_banks[m->bank]; + if (!b->hwid) + return N_SMCA_BANK_TYPES; + + return b->hwid->bank_type; +} + static struct smca_hwid smca_hwid_mcatypes[] = { /* { bank_type, hwid_mcatype, xec_bitmap } */ @@ -407,7 +421,9 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c) (deferred_error_int_vector != amd_deferred_error_interrupt)) deferred_error_int_vector = amd_deferred_error_interrupt; - low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC; + if (!mce_flags.smca) + low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC; + wrmsr(MSR_CU_DEF_ERR, low, high); } @@ -738,6 +754,17 @@ out_err: } EXPORT_SYMBOL_GPL(umc_normaddr_to_sysaddr); +bool amd_mce_is_memory_error(struct mce *m) +{ + /* ErrCodeExt[20:16] */ + u8 xec = (m->status >> 16) & 0x1f; + + if (mce_flags.smca) + return smca_get_bank_type(m) == SMCA_UMC && xec == 0x0; + + return m->bank == 4 && xec == 0x8; +} + static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) { struct mce m; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index c4fa4a85d4cb..319dd65f98a2 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -239,7 +239,7 @@ static int __init save_microcode_in_initrd(void) break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - return save_microcode_in_initrd_amd(cpuid_eax(1)); + ret = save_microcode_in_initrd_amd(cpuid_eax(1)); break; default: break; @@ -560,7 +560,7 @@ static ssize_t pf_show(struct device *dev, return sprintf(buf, "0x%x\n", uci->cpu_sig.pf); } -static DEVICE_ATTR(reload, 0200, NULL, reload_store); +static DEVICE_ATTR_WO(reload); static DEVICE_ATTR(version, 0400, version_show, NULL); static DEVICE_ATTR(processor_flags, 0400, pf_show, NULL); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 7dbcb7adf797..f7c55b0e753a 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -45,6 +45,9 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; /* Current microcode patch used in early patching on the APs. */ static struct microcode_intel *intel_ucode_patch; +/* last level cache size per core */ +static int llc_size_per_core; + static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, unsigned int s2, unsigned int p2) { @@ -565,15 +568,6 @@ static void print_ucode(struct ucode_cpu_info *uci) } #else -/* - * Flush global tlb. We only do this in x86_64 where paging has been enabled - * already and PGE should be enabled as well. - */ -static inline void flush_tlb_early(void) -{ - __native_flush_tlb_global_irq_disabled(); -} - static inline void print_ucode(struct ucode_cpu_info *uci) { struct microcode_intel *mc; @@ -602,10 +596,6 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) 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 = rev; if (early) @@ -923,8 +913,19 @@ static bool is_blacklisted(unsigned int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); - if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) { - pr_err_once("late loading on model 79 is disabled.\n"); + /* + * Late loading on model 79 with microcode revision less than 0x0b000021 + * and LLC size per core bigger than 2.5MB may result in a system hang. + * This behavior is documented in item BDF90, #334165 (Intel Xeon + * Processor E7-8800/4800 v4 Product Family). + */ + if (c->x86 == 6 && + c->x86_model == INTEL_FAM6_BROADWELL_X && + c->x86_mask == 0x01 && + llc_size_per_core > 2621440 && + c->microcode < 0x0b000021) { + pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); + pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); return true; } @@ -979,6 +980,15 @@ static struct microcode_ops microcode_intel_ops = { .apply_microcode = apply_microcode_intel, }; +static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) +{ + u64 llc_size = c->x86_cache_size * 1024; + + do_div(llc_size, c->x86_max_cores); + + return (int)llc_size; +} + struct microcode_ops * __init init_intel_microcode(void) { struct cpuinfo_x86 *c = &boot_cpu_data; @@ -989,5 +999,7 @@ struct microcode_ops * __init init_intel_microcode(void) return NULL; } + llc_size_per_core = calc_llc_size_per_core(c); + return µcode_intel_ops; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 05459ad3db46..4075d2be5357 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -21,12 +21,10 @@ struct cpuid_bit { 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_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 }, - { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 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_CDP_L2, CPUID_ECX, 2, 0x00000010, 2 }, { X86_FEATURE_MBA, CPUID_EBX, 3, 0x00000010, 0 }, { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, |