diff options
Diffstat (limited to 'arch/x86/kernel/cpu')
37 files changed, 5353 insertions, 670 deletions
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 570e8bb1f386..1f5d2291c31e 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -17,7 +17,7 @@ KCOV_INSTRUMENT_perf_event.o := n nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_common.o := $(nostackp) -obj-y := intel_cacheinfo.o scattered.o topology.o +obj-y := cacheinfo.o scattered.o topology.o obj-y += common.o obj-y += rdrand.o obj-y += match.o @@ -28,14 +28,17 @@ obj-y += cpuid-deps.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel.o +obj-$(CONFIG_CPU_SUP_INTEL) += intel.o intel_pconfig.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o +obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o 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) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o intel_rdt_ctrlmondata.o +obj-$(CONFIG_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o +obj-$(CONFIG_INTEL_RDT) += intel_rdt_ctrlmondata.o intel_rdt_pseudo_lock.o +CFLAGS_intel_rdt_pseudo_lock.o = -I$(src) obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f0e6456ca7d3..eeea634bee0a 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -9,7 +9,9 @@ #include <linux/random.h> #include <asm/processor.h> #include <asm/apic.h> +#include <asm/cacheinfo.h> #include <asm/cpu.h> +#include <asm/spec-ctrl.h> #include <asm/smp.h> #include <asm/pci-direct.h> #include <asm/delay.h> @@ -230,8 +232,6 @@ static void init_amd_k7(struct cpuinfo_x86 *c) } } - set_cpu_cap(c, X86_FEATURE_K7); - /* calling is from identify_secondary_cpu() ? */ if (!c->cpu_index) return; @@ -297,7 +297,6 @@ static int nearby_node(int apicid) } #endif -#ifdef CONFIG_SMP /* * Fix up cpu_core_id for pre-F17h systems to be in the * [0 .. cores_per_node - 1] range. Not really needed but @@ -314,6 +313,13 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c) c->cpu_core_id %= cus_per_node; } + +static void amd_get_topology_early(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_TOPOEXT)) + smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; +} + /* * Fixup core topology information for * (1) AMD multi-node processors @@ -327,12 +333,12 @@ static void amd_get_topology(struct cpuinfo_x86 *c) /* get information required for multi-node processors */ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + int err; u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); node_id = ecx & 0xff; - smp_num_siblings = ((ebx >> 8) & 0xff) + 1; if (c->x86 == 0x15) c->cu_id = ebx & 0xff; @@ -345,21 +351,15 @@ static void amd_get_topology(struct cpuinfo_x86 *c) } /* - * We may have multiple LLCs if L3 caches exist, so check if we - * have an L3 cache by looking at the L3 cache CPUID leaf. + * In case leaf B is available, use it to derive + * topology information. */ - if (cpuid_edx(0x80000006)) { - if (c->x86 == 0x17) { - /* - * LLC is at the core complex level. - * Core complex id is ApicId[3]. - */ - per_cpu(cpu_llc_id, cpu) = c->apicid >> 3; - } else { - /* LLC is at the node level. */ - per_cpu(cpu_llc_id, cpu) = node_id; - } - } + err = detect_extended_topology(c); + if (!err) + c->x86_coreid_bits = get_count_order(c->x86_max_cores); + + cacheinfo_amd_init_llc_id(c, cpu, node_id); + } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { u64 value; @@ -375,7 +375,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c) legacy_fixup_core_id(c); } } -#endif /* * On a AMD dual core setup the lower bits of the APIC id distinguish the cores. @@ -383,7 +382,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c) */ static void amd_detect_cmp(struct cpuinfo_x86 *c) { -#ifdef CONFIG_SMP unsigned bits; int cpu = smp_processor_id(); @@ -394,17 +392,11 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) c->phys_proc_id = c->initial_apicid >> bits; /* use socket ID also for last level cache */ per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; - amd_get_topology(c); -#endif } u16 amd_get_nb_id(int cpu) { - u16 id = 0; -#ifdef CONFIG_SMP - id = per_cpu(cpu_llc_id, cpu); -#endif - return id; + return per_cpu(cpu_llc_id, cpu); } EXPORT_SYMBOL_GPL(amd_get_nb_id); @@ -554,6 +546,28 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) rdmsrl(MSR_FAM10H_NODE_ID, value); nodes_per_socket = ((value >> 3) & 7) + 1; } + + if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && + !boot_cpu_has(X86_FEATURE_VIRT_SSBD) && + c->x86 >= 0x15 && c->x86 <= 0x17) { + unsigned int bit; + + switch (c->x86) { + case 0x15: bit = 54; break; + case 0x16: bit = 33; break; + case 0x17: bit = 10; break; + default: return; + } + /* + * Try to cache the base value so further operations can + * avoid RMW. If that faults, do not enable SSBD. + */ + if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) { + setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD); + setup_force_cpu_cap(X86_FEATURE_SSBD); + x86_amd_ls_cfg_ssbd_mask = 1ULL << bit; + } + } } static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) @@ -603,10 +617,19 @@ clear_sev: static void early_init_amd(struct cpuinfo_x86 *c) { + u64 value; u32 dummy; early_init_amd_mc(c); +#ifdef CONFIG_X86_32 + if (c->x86 == 6) + set_cpu_cap(c, X86_FEATURE_K7); +#endif + + if (c->x86 >= 0xf) + set_cpu_cap(c, X86_FEATURE_K8); + rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); /* @@ -673,6 +696,22 @@ static void early_init_amd(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_AMD_E400); early_detect_mem_encrypt(c); + + /* Re-enable TopologyExtensions if switched off by BIOS */ + if (c->x86 == 0x15 && + (c->x86_model >= 0x10 && c->x86_model <= 0x6f) && + !cpu_has(c, X86_FEATURE_TOPOEXT)) { + + if (msr_set_bit(0xc0011005, 54) > 0) { + rdmsrl(0xc0011005, value); + if (value & BIT_64(54)) { + set_cpu_cap(c, X86_FEATURE_TOPOEXT); + pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); + } + } + } + + amd_get_topology_early(c); } static void init_amd_k8(struct cpuinfo_x86 *c) @@ -716,7 +755,7 @@ static void init_amd_k8(struct cpuinfo_x86 *c) static void init_amd_gh(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_64 +#ifdef CONFIG_MMCONF_FAM10H /* do this for boot cpu */ if (c == &boot_cpu_data) check_enable_amd_mmconf_dmi(); @@ -764,19 +803,6 @@ static void init_amd_bd(struct cpuinfo_x86 *c) { u64 value; - /* re-enable TopologyExtensions if switched off by BIOS */ - if ((c->x86_model >= 0x10) && (c->x86_model <= 0x6f) && - !cpu_has(c, X86_FEATURE_TOPOEXT)) { - - if (msr_set_bit(0xc0011005, 54) > 0) { - rdmsrl(0xc0011005, value); - if (value & BIT_64(54)) { - set_cpu_cap(c, X86_FEATURE_TOPOEXT); - pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); - } - } - } - /* * The way access filter has a performance penalty on some workloads. * Disable it on the affected CPUs. @@ -791,6 +817,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c) static void init_amd_zn(struct cpuinfo_x86 *c) { + set_cpu_cap(c, X86_FEATURE_ZEN); /* * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects * all up to and including B1. @@ -839,21 +866,12 @@ static void init_amd(struct cpuinfo_x86 *c) cpu_detect_cache_sizes(c); - /* Multi core CPU? */ - if (c->extended_cpuid_level >= 0x80000008) { - amd_detect_cmp(c); - srat_detect_node(c); - } - -#ifdef CONFIG_X86_32 - detect_ht(c); -#endif + amd_detect_cmp(c); + amd_get_topology(c); + srat_detect_node(c); init_amd_cacheinfo(c); - if (c->x86 >= 0xf) - set_cpu_cap(c, X86_FEATURE_K8); - if (cpu_has(c, X86_FEATURE_XMM2)) { unsigned long long val; int ret; @@ -904,7 +922,7 @@ static void init_amd(struct cpuinfo_x86 *c) static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) { /* AMD errata T13 (order #21922) */ - if ((c->x86 == 6)) { + if (c->x86 == 6) { /* Duron Rev A0 */ if (c->x86_model == 3 && c->x86_stepping == 0) size = 64; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bfca937bdcc3..c37e66e493bf 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -12,34 +12,85 @@ #include <linux/utsname.h> #include <linux/cpu.h> #include <linux/module.h> +#include <linux/nospec.h> +#include <linux/prctl.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> #include <asm/fpu/internal.h> #include <asm/msr.h> +#include <asm/vmx.h> #include <asm/paravirt.h> #include <asm/alternative.h> #include <asm/pgtable.h> #include <asm/set_memory.h> #include <asm/intel-family.h> +#include <asm/e820/api.h> +#include <asm/hypervisor.h> static void __init spectre_v2_select_mitigation(void); +static void __init ssb_select_mitigation(void); +static void __init l1tf_select_mitigation(void); + +/* The base value of the SPEC_CTRL MSR that always has to be preserved. */ +u64 x86_spec_ctrl_base; +EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); +static DEFINE_MUTEX(spec_ctrl_mutex); + +/* + * The vendor and possibly platform specific bits which can be modified in + * x86_spec_ctrl_base. + */ +static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS; + +/* + * AMD specific MSR info for Speculative Store Bypass control. + * x86_amd_ls_cfg_ssbd_mask is initialized in identify_boot_cpu(). + */ +u64 __ro_after_init x86_amd_ls_cfg_base; +u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask; void __init check_bugs(void) { identify_boot_cpu(); + /* + * identify_boot_cpu() initialized SMT support information, let the + * core code know. + */ + cpu_smt_check_topology_early(); + if (!IS_ENABLED(CONFIG_SMP)) { pr_info("CPU: "); print_cpu_info(&boot_cpu_data); } + /* + * Read the SPEC_CTRL MSR to account for reserved bits which may + * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD + * init code as it is not enumerated and depends on the family. + */ + if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + + /* Allow STIBP in MSR_SPEC_CTRL if supported */ + if (boot_cpu_has(X86_FEATURE_STIBP)) + x86_spec_ctrl_mask |= SPEC_CTRL_STIBP; + /* Select the proper spectre mitigation before patching alternatives */ spectre_v2_select_mitigation(); + /* + * Select proper mitigation for any exposure to the Speculative Store + * Bypass vulnerability. + */ + ssb_select_mitigation(); + + l1tf_select_mitigation(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -88,12 +139,83 @@ static const char *spectre_v2_strings[] = { [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", + [SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS", }; #undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt -static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; +static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = + SPECTRE_V2_NONE; + +void +x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) +{ + u64 msrval, guestval, hostval = x86_spec_ctrl_base; + struct thread_info *ti = current_thread_info(); + + /* Is MSR_SPEC_CTRL implemented ? */ + if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) { + /* + * Restrict guest_spec_ctrl to supported values. Clear the + * modifiable bits in the host base value and or the + * modifiable bits from the guest value. + */ + guestval = hostval & ~x86_spec_ctrl_mask; + guestval |= guest_spec_ctrl & x86_spec_ctrl_mask; + + /* SSBD controlled in MSR_SPEC_CTRL */ + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) + hostval |= ssbd_tif_to_spec_ctrl(ti->flags); + + if (hostval != guestval) { + msrval = setguest ? guestval : hostval; + wrmsrl(MSR_IA32_SPEC_CTRL, msrval); + } + } + + /* + * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update + * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported. + */ + if (!static_cpu_has(X86_FEATURE_LS_CFG_SSBD) && + !static_cpu_has(X86_FEATURE_VIRT_SSBD)) + return; + + /* + * If the host has SSBD mitigation enabled, force it in the host's + * virtual MSR value. If its not permanently enabled, evaluate + * current's TIF_SSBD thread flag. + */ + if (static_cpu_has(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE)) + hostval = SPEC_CTRL_SSBD; + else + hostval = ssbd_tif_to_spec_ctrl(ti->flags); + + /* Sanitize the guest value */ + guestval = guest_virt_spec_ctrl & SPEC_CTRL_SSBD; + + if (hostval != guestval) { + unsigned long tif; + + tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) : + ssbd_spec_ctrl_to_tif(hostval); + + speculative_store_bypass_update(tif); + } +} +EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl); + +static void x86_amd_ssb_disable(void) +{ + u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask; + + if (boot_cpu_has(X86_FEATURE_VIRT_SSBD)) + wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD); + else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + wrmsrl(MSR_AMD64_LS_CFG, msrval); +} #ifdef RETPOLINE static bool spectre_v2_bad_module; @@ -188,6 +310,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) } if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON && 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; @@ -201,21 +324,44 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return cmd; } -/* Check for Skylake-like CPUs (for RSB handling) */ -static bool __init is_skylake_era(void) +static bool stibp_needed(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; - } + if (spectre_v2_enabled == SPECTRE_V2_NONE) + return false; + + if (!boot_cpu_has(X86_FEATURE_STIBP)) + return false; + + return true; +} + +static void update_stibp_msr(void *info) +{ + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); +} + +void arch_smt_update(void) +{ + u64 mask; + + if (!stibp_needed()) + return; + + mutex_lock(&spec_ctrl_mutex); + mask = x86_spec_ctrl_base; + if (cpu_smt_control == CPU_SMT_ENABLED) + mask |= SPEC_CTRL_STIBP; + else + mask &= ~SPEC_CTRL_STIBP; + + if (mask != x86_spec_ctrl_base) { + pr_info("Spectre v2 cross-process SMT mitigation: %s STIBP\n", + cpu_smt_control == CPU_SMT_ENABLED ? + "Enabling" : "Disabling"); + x86_spec_ctrl_base = mask; + on_each_cpu(update_stibp_msr, NULL, 1); } - return false; + mutex_unlock(&spec_ctrl_mutex); } static void __init spectre_v2_select_mitigation(void) @@ -237,6 +383,13 @@ static void __init spectre_v2_select_mitigation(void) case SPECTRE_V2_CMD_FORCE: case SPECTRE_V2_CMD_AUTO: + if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { + mode = SPECTRE_V2_IBRS_ENHANCED; + /* Force it so VMEXIT will restore correctly */ + x86_spec_ctrl_base |= SPEC_CTRL_IBRS; + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + goto specv2_set_mode; + } if (IS_ENABLED(CONFIG_RETPOLINE)) goto retpoline_auto; break; @@ -257,7 +410,8 @@ static void __init spectre_v2_select_mitigation(void) return; retpoline_auto: - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { retpoline_amd: if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); @@ -274,26 +428,20 @@ retpoline_auto: setup_force_cpu_cap(X86_FEATURE_RETPOLINE); } +specv2_set_mode: spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); /* - * If neither SMEP nor PTI 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. + * If spectre v2 protection has been enabled, unconditionally fill + * RSB during a context switch; this protects against two independent + * issues: * - * 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. + * - RSB underflow (and switch to BTB) on Skylake+ + * - SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs */ - 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("Spectre v2 mitigation: Filling RSB on context switch\n"); - } + setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); + pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n"); /* Initialize Indirect Branch Prediction Barrier if supported */ if (boot_cpu_has(X86_FEATURE_IBPB)) { @@ -303,41 +451,475 @@ retpoline_auto: /* * Retpoline means the kernel is safe because it has no indirect - * branches. But firmware isn't, so use IBRS to protect that. + * branches. Enhanced IBRS protects firmware too, so, enable restricted + * speculation around firmware calls only when Enhanced IBRS isn't + * supported. + * + * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because + * the user might select retpoline on the kernel command line and if + * the CPU supports Enhanced IBRS, kernel might un-intentionally not + * enable IBRS around firmware calls. */ - if (boot_cpu_has(X86_FEATURE_IBRS)) { + if (boot_cpu_has(X86_FEATURE_IBRS) && mode != SPECTRE_V2_IBRS_ENHANCED) { setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } + + /* Enable STIBP if appropriate */ + arch_smt_update(); +} + +#undef pr_fmt +#define pr_fmt(fmt) "Speculative Store Bypass: " fmt + +static enum ssb_mitigation ssb_mode __ro_after_init = SPEC_STORE_BYPASS_NONE; + +/* The kernel command line selection */ +enum ssb_mitigation_cmd { + SPEC_STORE_BYPASS_CMD_NONE, + SPEC_STORE_BYPASS_CMD_AUTO, + SPEC_STORE_BYPASS_CMD_ON, + SPEC_STORE_BYPASS_CMD_PRCTL, + SPEC_STORE_BYPASS_CMD_SECCOMP, +}; + +static const char *ssb_strings[] = { + [SPEC_STORE_BYPASS_NONE] = "Vulnerable", + [SPEC_STORE_BYPASS_DISABLE] = "Mitigation: Speculative Store Bypass disabled", + [SPEC_STORE_BYPASS_PRCTL] = "Mitigation: Speculative Store Bypass disabled via prctl", + [SPEC_STORE_BYPASS_SECCOMP] = "Mitigation: Speculative Store Bypass disabled via prctl and seccomp", +}; + +static const struct { + const char *option; + enum ssb_mitigation_cmd cmd; +} ssb_mitigation_options[] = { + { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */ + { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */ + { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */ + { "prctl", SPEC_STORE_BYPASS_CMD_PRCTL }, /* Disable Speculative Store Bypass via prctl */ + { "seccomp", SPEC_STORE_BYPASS_CMD_SECCOMP }, /* Disable Speculative Store Bypass via prctl and seccomp */ +}; + +static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) +{ + enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO; + char arg[20]; + int ret, i; + + if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) { + return SPEC_STORE_BYPASS_CMD_NONE; + } else { + ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable", + arg, sizeof(arg)); + if (ret < 0) + return SPEC_STORE_BYPASS_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) { + if (!match_option(arg, ret, ssb_mitigation_options[i].option)) + continue; + + cmd = ssb_mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(ssb_mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", arg); + return SPEC_STORE_BYPASS_CMD_AUTO; + } + } + + return cmd; +} + +static enum ssb_mitigation __init __ssb_select_mitigation(void) +{ + enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE; + enum ssb_mitigation_cmd cmd; + + if (!boot_cpu_has(X86_FEATURE_SSBD)) + return mode; + + cmd = ssb_parse_cmdline(); + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) && + (cmd == SPEC_STORE_BYPASS_CMD_NONE || + cmd == SPEC_STORE_BYPASS_CMD_AUTO)) + return mode; + + switch (cmd) { + case SPEC_STORE_BYPASS_CMD_AUTO: + case SPEC_STORE_BYPASS_CMD_SECCOMP: + /* + * Choose prctl+seccomp as the default mode if seccomp is + * enabled. + */ + if (IS_ENABLED(CONFIG_SECCOMP)) + mode = SPEC_STORE_BYPASS_SECCOMP; + else + mode = SPEC_STORE_BYPASS_PRCTL; + break; + case SPEC_STORE_BYPASS_CMD_ON: + mode = SPEC_STORE_BYPASS_DISABLE; + break; + case SPEC_STORE_BYPASS_CMD_PRCTL: + mode = SPEC_STORE_BYPASS_PRCTL; + break; + case SPEC_STORE_BYPASS_CMD_NONE: + break; + } + + /* + * We have three CPU feature flags that are in play here: + * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. + * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass + * - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation + */ + if (mode == SPEC_STORE_BYPASS_DISABLE) { + setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE); + /* + * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may + * use a completely different MSR and bit dependent on family. + */ + if (!static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) && + !static_cpu_has(X86_FEATURE_AMD_SSBD)) { + x86_amd_ssb_disable(); + } else { + x86_spec_ctrl_base |= SPEC_CTRL_SSBD; + x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + } + } + + return mode; +} + +static void ssb_select_mitigation(void) +{ + ssb_mode = __ssb_select_mitigation(); + + if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + pr_info("%s\n", ssb_strings[ssb_mode]); +} + +#undef pr_fmt +#define pr_fmt(fmt) "Speculation prctl: " fmt + +static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + bool update; + + if (ssb_mode != SPEC_STORE_BYPASS_PRCTL && + ssb_mode != SPEC_STORE_BYPASS_SECCOMP) + return -ENXIO; + + switch (ctrl) { + case PR_SPEC_ENABLE: + /* If speculation is force disabled, enable is not allowed */ + if (task_spec_ssb_force_disable(task)) + return -EPERM; + task_clear_spec_ssb_disable(task); + update = test_and_clear_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_DISABLE: + task_set_spec_ssb_disable(task); + update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_FORCE_DISABLE: + task_set_spec_ssb_disable(task); + task_set_spec_ssb_force_disable(task); + update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + break; + default: + return -ERANGE; + } + + /* + * If being set on non-current task, delay setting the CPU + * mitigation until it is next scheduled. + */ + if (task == current && update) + speculative_store_bypass_update_current(); + + return 0; +} + +int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, + unsigned long ctrl) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssb_prctl_set(task, ctrl); + default: + return -ENODEV; + } +} + +#ifdef CONFIG_SECCOMP +void arch_seccomp_spec_mitigate(struct task_struct *task) +{ + if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP) + ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE); +} +#endif + +static int ssb_prctl_get(struct task_struct *task) +{ + switch (ssb_mode) { + case SPEC_STORE_BYPASS_DISABLE: + return PR_SPEC_DISABLE; + case SPEC_STORE_BYPASS_SECCOMP: + case SPEC_STORE_BYPASS_PRCTL: + if (task_spec_ssb_force_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ssb_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + default: + if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + return PR_SPEC_ENABLE; + return PR_SPEC_NOT_AFFECTED; + } +} + +int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssb_prctl_get(task); + default: + return -ENODEV; + } +} + +void x86_spec_ctrl_setup_ap(void) +{ + if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + + if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) + x86_amd_ssb_disable(); +} + +#undef pr_fmt +#define pr_fmt(fmt) "L1TF: " fmt + +/* Default mitigation for L1TF-affected CPUs */ +enum l1tf_mitigations l1tf_mitigation __ro_after_init = L1TF_MITIGATION_FLUSH; +#if IS_ENABLED(CONFIG_KVM_INTEL) +EXPORT_SYMBOL_GPL(l1tf_mitigation); +#endif +enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; +EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation); + +/* + * These CPUs all support 44bits physical address space internally in the + * cache but CPUID can report a smaller number of physical address bits. + * + * The L1TF mitigation uses the top most address bit for the inversion of + * non present PTEs. When the installed memory reaches into the top most + * address bit due to memory holes, which has been observed on machines + * which report 36bits physical address bits and have 32G RAM installed, + * then the mitigation range check in l1tf_select_mitigation() triggers. + * This is a false positive because the mitigation is still possible due to + * the fact that the cache uses 44bit internally. Use the cache bits + * instead of the reported physical bits and adjust them on the affected + * machines to 44bit if the reported bits are less than 44. + */ +static void override_cache_bits(struct cpuinfo_x86 *c) +{ + if (c->x86 != 6) + return; + + switch (c->x86_model) { + case INTEL_FAM6_NEHALEM: + case INTEL_FAM6_WESTMERE: + case INTEL_FAM6_SANDYBRIDGE: + case INTEL_FAM6_IVYBRIDGE: + case INTEL_FAM6_HASWELL_CORE: + case INTEL_FAM6_HASWELL_ULT: + case INTEL_FAM6_HASWELL_GT3E: + case INTEL_FAM6_BROADWELL_CORE: + case INTEL_FAM6_BROADWELL_GT3E: + case INTEL_FAM6_SKYLAKE_MOBILE: + case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_KABYLAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_DESKTOP: + if (c->x86_cache_bits < 44) + c->x86_cache_bits = 44; + break; + } +} + +static void __init l1tf_select_mitigation(void) +{ + u64 half_pa; + + if (!boot_cpu_has_bug(X86_BUG_L1TF)) + return; + + override_cache_bits(&boot_cpu_data); + + switch (l1tf_mitigation) { + case L1TF_MITIGATION_OFF: + case L1TF_MITIGATION_FLUSH_NOWARN: + case L1TF_MITIGATION_FLUSH: + break; + case L1TF_MITIGATION_FLUSH_NOSMT: + case L1TF_MITIGATION_FULL: + cpu_smt_disable(false); + break; + case L1TF_MITIGATION_FULL_FORCE: + cpu_smt_disable(true); + break; + } + +#if CONFIG_PGTABLE_LEVELS == 2 + pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n"); + return; +#endif + + half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT; + if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) { + pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n"); + pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n", + half_pa); + pr_info("However, doing so will make a part of your RAM unusable.\n"); + pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html might help you decide.\n"); + return; + } + + setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV); } +static int __init l1tf_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_L1TF)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + l1tf_mitigation = L1TF_MITIGATION_OFF; + else if (!strcmp(str, "flush,nowarn")) + l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOWARN; + else if (!strcmp(str, "flush")) + l1tf_mitigation = L1TF_MITIGATION_FLUSH; + else if (!strcmp(str, "flush,nosmt")) + l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT; + else if (!strcmp(str, "full")) + l1tf_mitigation = L1TF_MITIGATION_FULL; + else if (!strcmp(str, "full,force")) + l1tf_mitigation = L1TF_MITIGATION_FULL_FORCE; + + return 0; +} +early_param("l1tf", l1tf_cmdline); + #undef pr_fmt #ifdef CONFIG_SYSFS -ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) + +#define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion" + +#if IS_ENABLED(CONFIG_KVM_INTEL) +static const char *l1tf_vmx_states[] = { + [VMENTER_L1D_FLUSH_AUTO] = "auto", + [VMENTER_L1D_FLUSH_NEVER] = "vulnerable", + [VMENTER_L1D_FLUSH_COND] = "conditional cache flushes", + [VMENTER_L1D_FLUSH_ALWAYS] = "cache flushes", + [VMENTER_L1D_FLUSH_EPT_DISABLED] = "EPT disabled", + [VMENTER_L1D_FLUSH_NOT_REQUIRED] = "flush not necessary" +}; + +static ssize_t l1tf_show_state(char *buf) +{ + if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) + return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + + if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED || + (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER && + cpu_smt_control == CPU_SMT_ENABLED)) + return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation]); + + return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation], + cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled"); +} +#else +static ssize_t l1tf_show_state(char *buf) +{ + return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); +} +#endif + +static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, + char *buf, unsigned int bug) { - if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + int ret; + + if (!boot_cpu_has_bug(bug)) return sprintf(buf, "Not affected\n"); - if (boot_cpu_has(X86_FEATURE_PTI)) - return sprintf(buf, "Mitigation: PTI\n"); + + switch (bug) { + case X86_BUG_CPU_MELTDOWN: + if (boot_cpu_has(X86_FEATURE_PTI)) + return sprintf(buf, "Mitigation: PTI\n"); + + if (hypervisor_is_type(X86_HYPER_XEN_PV)) + return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); + + break; + + case X86_BUG_SPECTRE_V1: + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + + case X86_BUG_SPECTRE_V2: + ret = sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + (x86_spec_ctrl_base & SPEC_CTRL_STIBP) ? ", STIBP" : "", + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + spectre_v2_module_string()); + return ret; + + case X86_BUG_SPEC_STORE_BYPASS: + return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); + + case X86_BUG_L1TF: + if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) + return l1tf_show_state(buf); + break; + default: + break; + } + return sprintf(buf, "Vulnerable\n"); } +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_CPU_MELTDOWN); +} + 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"); + return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V1); } 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 cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2); +} + +ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS); +} - return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], - boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - spectre_v2_module_string()); +ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_L1TF); } #endif diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 54d04d574148..dc1b9342e9c4 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -20,6 +20,8 @@ #include <asm/amd_nb.h> #include <asm/smp.h> +#include "cpu.h" + #define LVL_1_INST 1 #define LVL_1_DATA 2 #define LVL_2 3 @@ -600,6 +602,10 @@ cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf) else amd_cpuid4(index, &eax, &ebx, &ecx); amd_init_l3_cache(this_leaf, index); + } else if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { + cpuid_count(0x8000001d, index, &eax.full, + &ebx.full, &ecx.full, &edx); + amd_init_l3_cache(this_leaf, index); } else { cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx); } @@ -623,7 +629,8 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) union _cpuid4_leaf_eax cache_eax; int i = -1; - if (c->x86_vendor == X86_VENDOR_AMD) + if (c->x86_vendor == X86_VENDOR_AMD || + c->x86_vendor == X86_VENDOR_HYGON) op = 0x8000001d; else op = 4; @@ -637,6 +644,61 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) return i; } +void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) +{ + /* + * We may have multiple LLCs if L3 caches exist, so check if we + * have an L3 cache by looking at the L3 cache CPUID leaf. + */ + if (!cpuid_edx(0x80000006)) + return; + + if (c->x86 < 0x17) { + /* LLC is at the node level. */ + per_cpu(cpu_llc_id, cpu) = node_id; + } else if (c->x86 == 0x17 && + c->x86_model >= 0 && c->x86_model <= 0x1F) { + /* + * LLC is at the core complex level. + * Core complex ID is ApicId[3] for these processors. + */ + per_cpu(cpu_llc_id, cpu) = c->apicid >> 3; + } else { + /* + * LLC ID is calculated from the number of threads sharing the + * cache. + * */ + u32 eax, ebx, ecx, edx, num_sharing_cache = 0; + u32 llc_index = find_num_cache_leaves(c) - 1; + + cpuid_count(0x8000001d, llc_index, &eax, &ebx, &ecx, &edx); + if (eax) + num_sharing_cache = ((eax >> 14) & 0xfff) + 1; + + if (num_sharing_cache) { + int bits = get_count_order(num_sharing_cache); + + per_cpu(cpu_llc_id, cpu) = c->apicid >> bits; + } + } +} + +void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) +{ + /* + * We may have multiple LLCs if L3 caches exist, so check if we + * have an L3 cache by looking at the L3 cache CPUID leaf. + */ + if (!cpuid_edx(0x80000006)) + return; + + /* + * LLC is at the core complex level. + * Core complex ID is ApicId[3] for these processors. + */ + per_cpu(cpu_llc_id, cpu) = c->apicid >> 3; +} + void init_amd_cacheinfo(struct cpuinfo_x86 *c) { @@ -650,7 +712,12 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c) } } -unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) +void init_hygon_cacheinfo(struct cpuinfo_x86 *c) +{ + num_cache_leaves = find_num_cache_leaves(c); +} + +void init_intel_cacheinfo(struct cpuinfo_x86 *c) { /* Cache sizes */ unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0; @@ -802,7 +869,8 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d)); - return l2; + if (!l2) + cpu_detect_cache_sizes(c); } static int __cache_amd_cpumap_setup(unsigned int cpu, int index, @@ -871,7 +939,8 @@ static void __cache_cpumap_setup(unsigned int cpu, int index, int index_msb, i; struct cpuinfo_x86 *c = &cpu_data(cpu); - if (c->x86_vendor == X86_VENDOR_AMD) { + if (c->x86_vendor == X86_VENDOR_AMD || + c->x86_vendor == X86_VENDOR_HYGON) { if (__cache_amd_cpumap_setup(cpu, index, base)) return; } diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index e5ec0f11c0de..14433ff5b828 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -18,6 +18,13 @@ #define RNG_ENABLED (1 << 3) #define RNG_ENABLE (1 << 6) /* MSR_VIA_RNG */ +#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000 +#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000 +#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000 +#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001 +#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002 +#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020 + static void init_c3(struct cpuinfo_x86 *c) { u32 lo, hi; @@ -112,6 +119,31 @@ static void early_init_centaur(struct cpuinfo_x86 *c) } } +static void centaur_detect_vmx_virtcap(struct cpuinfo_x86 *c) +{ + u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2; + + rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high); + msr_ctl = vmx_msr_high | vmx_msr_low; + + if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW) + set_cpu_cap(c, X86_FEATURE_TPR_SHADOW); + if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI) + set_cpu_cap(c, X86_FEATURE_VNMI); + if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) { + rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, + vmx_msr_low, vmx_msr_high); + msr_ctl2 = vmx_msr_high | vmx_msr_low; + if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) && + (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)) + set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); + if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) + set_cpu_cap(c, X86_FEATURE_EPT); + if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID) + set_cpu_cap(c, X86_FEATURE_VPID); + } +} + static void init_centaur(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_32 @@ -128,6 +160,24 @@ static void init_centaur(struct cpuinfo_x86 *c) clear_cpu_cap(c, 0*32+31); #endif early_init_centaur(c); + init_intel_cacheinfo(c); + detect_num_cpu_cores(c); +#ifdef CONFIG_X86_32 + detect_ht(c); +#endif + + if (c->cpuid_level > 9) { + unsigned int eax = cpuid_eax(10); + + /* + * Check for version and the number of counters + * Version(eax[7:0]) can't be 0; + * Counters(eax[15:8]) should be greater than 1; + */ + if ((eax & 0xff) && (((eax >> 8) & 0xff) > 1)) + set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON); + } + switch (c->x86) { #ifdef CONFIG_X86_32 case 5: @@ -199,6 +249,9 @@ static void init_centaur(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); #endif + + if (cpu_has(c, X86_FEATURE_VMX)) + centaur_detect_vmx_virtcap(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 348cf4821240..ffb181f959d2 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1,4 +1,7 @@ -#include <linux/bootmem.h> +/* cpu_feature_enabled() cannot be used this early */ +#define USE_EARLY_PGTABLE_L5 + +#include <linux/memblock.h> #include <linux/linkage.h> #include <linux/bitops.h> #include <linux/kernel.h> @@ -66,6 +69,13 @@ cpumask_var_t cpu_callin_mask; /* representing cpus for which sibling maps can be computed */ cpumask_var_t cpu_sibling_setup_mask; +/* Number of siblings per CPU package */ +int smp_num_siblings = 1; +EXPORT_SYMBOL(smp_num_siblings); + +/* Last level cache ID of each logical CPU */ +DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID; + /* correctly size the local cpu masks */ void __init setup_cpu_local_masks(void) { @@ -487,7 +497,7 @@ void load_percpu_segment(int cpu) loadsegment(fs, __KERNEL_PERCPU); #else __loadsegment_simple(gs, 0); - wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu)); + wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu)); #endif load_stack_canary_segment(); } @@ -577,6 +587,19 @@ static void get_model_name(struct cpuinfo_x86 *c) *(s + 1) = '\0'; } +void detect_num_cpu_cores(struct cpuinfo_x86 *c) +{ + unsigned int eax, ebx, ecx, edx; + + c->x86_max_cores = 1; + if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4) + return; + + cpuid_count(4, 0, &eax, &ebx, &ecx, &edx); + if (eax & 0x1f) + c->x86_max_cores = (eax >> 26) + 1; +} + void cpu_detect_cache_sizes(struct cpuinfo_x86 *c) { unsigned int n, dummy, ebx, ecx, edx, l2size; @@ -638,33 +661,36 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } -void detect_ht(struct cpuinfo_x86 *c) +int detect_ht_early(struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP u32 eax, ebx, ecx, edx; - int index_msb, core_bits; - static bool printed; if (!cpu_has(c, X86_FEATURE_HT)) - return; + return -1; if (cpu_has(c, X86_FEATURE_CMP_LEGACY)) - goto out; + return -1; if (cpu_has(c, X86_FEATURE_XTOPOLOGY)) - return; + return -1; cpuid(1, &eax, &ebx, &ecx, &edx); smp_num_siblings = (ebx & 0xff0000) >> 16; - - if (smp_num_siblings == 1) { + if (smp_num_siblings == 1) pr_info_once("CPU0: Hyper-Threading is disabled\n"); - goto out; - } +#endif + return 0; +} - if (smp_num_siblings <= 1) - goto out; +void detect_ht(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + int index_msb, core_bits; + + if (detect_ht_early(c) < 0) + return; index_msb = get_count_order(smp_num_siblings); c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb); @@ -677,15 +703,6 @@ void detect_ht(struct cpuinfo_x86 *c) c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) & ((1 << core_bits) - 1); - -out: - if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) { - pr_info("CPU: Physical Processor ID: %d\n", - c->phys_proc_id); - pr_info("CPU: Processor Core ID: %d\n", - c->cpu_core_id); - printed = 1; - } #endif } @@ -757,17 +774,38 @@ static void init_speculation_control(struct cpuinfo_x86 *c) * 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); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) set_cpu_cap(c, X86_FEATURE_STIBP); + + if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) || + cpu_has(c, X86_FEATURE_VIRT_SSBD)) + set_cpu_cap(c, X86_FEATURE_SSBD); + + if (cpu_has(c, X86_FEATURE_AMD_IBRS)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); + } + + if (cpu_has(c, X86_FEATURE_AMD_IBPB)) + set_cpu_cap(c, X86_FEATURE_IBPB); + + if (cpu_has(c, X86_FEATURE_AMD_STIBP)) { + set_cpu_cap(c, X86_FEATURE_STIBP); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); + } + + if (cpu_has(c, X86_FEATURE_AMD_SSBD)) { + set_cpu_cap(c, X86_FEATURE_SSBD); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); + clear_cpu_cap(c, X86_FEATURE_VIRT_SSBD); + } } void get_cpu_cap(struct cpuinfo_x86 *c) @@ -850,15 +888,8 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000008) { cpuid(0x80000008, &eax, &ebx, &ecx, &edx); - - c->x86_virt_bits = (eax >> 8) & 0xff; - c->x86_phys_bits = eax & 0xff; c->x86_capability[CPUID_8000_0008_EBX] = ebx; } -#ifdef CONFIG_X86_32 - else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) - c->x86_phys_bits = 36; -#endif if (c->extended_cpuid_level >= 0x8000000a) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); @@ -874,6 +905,23 @@ void get_cpu_cap(struct cpuinfo_x86 *c) apply_forced_caps(c); } +void get_cpu_address_sizes(struct cpuinfo_x86 *c) +{ + u32 eax, ebx, ecx, edx; + + if (c->extended_cpuid_level >= 0x80000008) { + cpuid(0x80000008, &eax, &ebx, &ecx, &edx); + + c->x86_virt_bits = (eax >> 8) & 0xff; + c->x86_phys_bits = eax & 0xff; + } +#ifdef CONFIG_X86_32 + else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) + c->x86_phys_bits = 36; +#endif + c->x86_cache_bits = c->x86_phys_bits; +} + static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_32 @@ -901,11 +949,11 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) } 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_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL_TABLET, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_BONNELL_MID, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL_MID, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_BONNELL, X86_FEATURE_ANY }, { X86_VENDOR_CENTAUR, 5 }, { X86_VENDOR_INTEL, 5 }, { X86_VENDOR_NSC, 5 }, @@ -915,24 +963,93 @@ static const __initconst struct x86_cpu_id cpu_no_speculation[] = { static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { { X86_VENDOR_AMD }, + { X86_VENDOR_HYGON }, + {} +}; + +/* Only list CPUs which speculate but are non susceptible to SSB */ +static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_X }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_MID }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, + { X86_VENDOR_AMD, 0x12, }, + { X86_VENDOR_AMD, 0x11, }, + { X86_VENDOR_AMD, 0x10, }, + { X86_VENDOR_AMD, 0xf, }, + {} +}; + +static const __initconst struct x86_cpu_id cpu_no_l1tf[] = { + /* in addition to cpu_no_speculation */ + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_X }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_MID }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT_MID }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_X }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_PLUS }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, {} }; -static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c) +static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0; - if (x86_match_cpu(cpu_no_meltdown)) - return false; + if (x86_match_cpu(cpu_no_speculation)) + return; + + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + if (!x86_match_cpu(cpu_no_spec_store_bypass) && + !(ia32_cap & ARCH_CAP_SSB_NO) && + !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) + setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); + + if (ia32_cap & ARCH_CAP_IBRS_ALL) + setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); + + if (x86_match_cpu(cpu_no_meltdown)) + return; + /* Rogue Data Cache Load? No! */ if (ia32_cap & ARCH_CAP_RDCL_NO) - return false; + return; + + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - return true; + if (x86_match_cpu(cpu_no_l1tf)) + return; + + setup_force_cpu_bug(X86_BUG_L1TF); +} + +/* + * The NOPL instruction is supposed to exist on all CPUs of family >= 6; + * unfortunately, that's not true in practice because of early VIA + * chips and (more importantly) broken virtualizers that are not easy + * to detect. In the latter case it doesn't even *fail* reliably, so + * probing for it doesn't even work. Disable it completely on 32-bit + * unless we can find a reliable way to detect all the broken cases. + * Enable it explicitly on 64-bit for non-constant inputs of cpu_has(). + */ +static void detect_nopl(void) +{ +#ifdef CONFIG_X86_32 + setup_clear_cpu_cap(X86_FEATURE_NOPL); +#else + setup_force_cpu_cap(X86_FEATURE_NOPL); +#endif } /* @@ -957,14 +1074,18 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) #endif c->x86_cache_alignment = c->x86_clflush_size; - memset(&c->x86_capability, 0, sizeof c->x86_capability); + memset(&c->x86_capability, 0, sizeof(c->x86_capability)); c->extended_cpuid_level = 0; + if (!have_cpuid_p()) + identify_cpu_without_cpuid(c); + /* cyrix could have cpuid enabled via c_identify()*/ if (have_cpuid_p()) { cpu_detect(c); get_cpu_vendor(c); get_cpu_cap(c); + get_cpu_address_sizes(c); setup_force_cpu_cap(X86_FEATURE_CPUID); if (this_cpu->c_early_init) @@ -976,18 +1097,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_bsp_init) this_cpu->c_bsp_init(c); } else { - identify_cpu_without_cpuid(c); setup_clear_cpu_cap(X86_FEATURE_CPUID); } 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); - } + cpu_set_bug_bits(c); fpu__init_system(c); @@ -998,6 +1113,23 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) */ setup_clear_cpu_cap(X86_FEATURE_PCID); #endif + + /* + * Later in the boot process pgtable_l5_enabled() relies on + * cpu_feature_enabled(X86_FEATURE_LA57). If 5-level paging is not + * enabled by this point we need to clear the feature bit to avoid + * false-positives at the later stage. + * + * pgtable_l5_enabled() can be false here for several reasons: + * - 5-level paging is disabled compile-time; + * - it's 32-bit kernel; + * - machine doesn't support 5-level paging; + * - user specified 'no5lvl' in kernel command line. + */ + if (!pgtable_l5_enabled()) + setup_clear_cpu_cap(X86_FEATURE_LA57); + + detect_nopl(); } void __init early_cpu_init(void) @@ -1033,24 +1165,6 @@ void __init early_cpu_init(void) early_identify_cpu(&boot_cpu_data); } -/* - * The NOPL instruction is supposed to exist on all CPUs of family >= 6; - * unfortunately, that's not true in practice because of early VIA - * chips and (more importantly) broken virtualizers that are not easy - * to detect. In the latter case it doesn't even *fail* reliably, so - * probing for it doesn't even work. Disable it completely on 32-bit - * unless we can find a reliable way to detect all the broken cases. - * Enable it explicitly on 64-bit for non-constant inputs of cpu_has(). - */ -static void detect_nopl(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_X86_32 - clear_cpu_cap(c, X86_FEATURE_NOPL); -#else - set_cpu_cap(c, X86_FEATURE_NOPL); -#endif -} - static void detect_null_seg_behavior(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_64 @@ -1097,6 +1211,8 @@ static void generic_identify(struct cpuinfo_x86 *c) get_cpu_cap(c); + get_cpu_address_sizes(c); + if (c->cpuid_level >= 0x00000001) { c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF; #ifdef CONFIG_X86_32 @@ -1111,8 +1227,6 @@ static void generic_identify(struct cpuinfo_x86 *c) get_model_name(c); /* Default name */ - detect_nopl(c); - detect_null_seg_behavior(c); /* @@ -1129,10 +1243,10 @@ static void generic_identify(struct cpuinfo_x86 *c) * ESPFIX issue, we can change this. */ #ifdef CONFIG_X86_32 -# ifdef CONFIG_PARAVIRT +# ifdef CONFIG_PARAVIRT_XXL do { extern void native_iret(void); - if (pv_cpu_ops.iret == native_iret) + if (pv_ops.cpu.iret == native_iret) set_cpu_bug(c, X86_BUG_ESPFIX); } while (0); # else @@ -1203,7 +1317,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->x86_virt_bits = 32; #endif c->x86_cache_alignment = c->x86_clflush_size; - memset(&c->x86_capability, 0, sizeof c->x86_capability); + memset(&c->x86_capability, 0, sizeof(c->x86_capability)); generic_identify(c); @@ -1347,6 +1461,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) #endif mtrr_ap_init(); validate_apic_and_package_id(c); + x86_spec_ctrl_setup_ap(); } static __init int setup_noclflush(char *arg) @@ -1398,6 +1513,7 @@ __setup("clearcpuid=", setup_clearcpuid); #ifdef CONFIG_X86_64 DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE) __visible; +EXPORT_PER_CPU_SYMBOL_GPL(irq_stack_union); /* * The following percpu variables are hot. Align current_task to @@ -1418,19 +1534,8 @@ EXPORT_PER_CPU_SYMBOL(__preempt_count); /* 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); - if (static_cpu_has(X86_FEATURE_PTI)) - wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline); - else - wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); + wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat); @@ -1441,7 +1546,8 @@ 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, (unsigned long)(cpu_entry_stack(cpu) + 1)); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, + (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); @@ -1507,7 +1613,7 @@ DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) = (unsigned long)&init_thread_union + THREAD_SIZE; EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack); -#ifdef CONFIG_CC_STACKPROTECTOR +#ifdef CONFIG_STACKPROTECTOR DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); #endif @@ -1556,6 +1662,29 @@ static void wait_for_master_cpu(int cpu) #endif } +#ifdef CONFIG_X86_64 +static void setup_getcpu(int cpu) +{ + unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu)); + struct desc_struct d = { }; + + if (static_cpu_has(X86_FEATURE_RDTSCP)) + write_rdtscp_aux(cpudata); + + /* Store CPU and node number in limit. */ + d.limit0 = cpudata; + d.limit1 = cpudata >> 16; + + d.type = 5; /* RO data, expand down, accessed */ + d.dpl = 3; /* Visible to user code */ + d.s = 1; /* Not a system segment */ + d.p = 1; /* Present */ + d.d = 1; /* 32-bit */ + + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_CPUNODE, &d, DESCTYPE_S); +} +#endif + /* * cpu_init() initializes state that is per-CPU. Some data is already * initialized (naturally) in the bootstrap process, such as the GDT @@ -1593,6 +1722,7 @@ void cpu_init(void) early_cpu_to_node(cpu) != NUMA_NO_NODE) set_numa_node(early_cpu_to_node(cpu)); #endif + setup_getcpu(cpu); me = current; @@ -1709,11 +1839,12 @@ void cpu_init(void) enter_lazy_tlb(&init_mm, curr); /* - * 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, &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); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index e806b11a99af..da5446acc241 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -46,8 +46,24 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; extern void get_cpu_cap(struct cpuinfo_x86 *c); +extern void get_cpu_address_sizes(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); +extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c); +extern u32 get_scattered_cpuid_leaf(unsigned int level, + unsigned int sub_leaf, + enum cpuid_regs_idx reg); +extern void init_intel_cacheinfo(struct cpuinfo_x86 *c); +extern void init_amd_cacheinfo(struct cpuinfo_x86 *c); +extern void init_hygon_cacheinfo(struct cpuinfo_x86 *c); + +extern void detect_num_cpu_cores(struct cpuinfo_x86 *c); +extern int detect_extended_topology_early(struct cpuinfo_x86 *c); +extern int detect_extended_topology(struct cpuinfo_x86 *c); +extern int detect_ht_early(struct cpuinfo_x86 *c); +extern void detect_ht(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); +extern void x86_spec_ctrl_setup_ap(void); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index 904b0a3c4e53..2c0bd38a44ab 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -19,7 +19,7 @@ struct cpuid_dep { * called from cpu hotplug. It shouldn't do anything in this case, * but it's difficult to tell that to the init reference checker. */ -const static struct cpuid_dep cpuid_deps[] = { +static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE }, { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE }, { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE }, diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 8949b7ae6d92..d12226f60168 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -437,7 +437,7 @@ static void cyrix_identify(struct cpuinfo_x86 *c) /* enable MAPEN */ setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable cpuid */ - setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x80); + setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x80); /* disable MAPEN */ setCx86(CX86_CCR3, ccr3); local_irq_restore(flags); diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c new file mode 100644 index 000000000000..cf25405444ab --- /dev/null +++ b/arch/x86/kernel/cpu/hygon.c @@ -0,0 +1,408 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Hygon Processor Support for Linux + * + * Copyright (C) 2018 Chengdu Haiguang IC Design Co., Ltd. + * + * Author: Pu Wen <puwen@hygon.cn> + */ +#include <linux/io.h> + +#include <asm/cpu.h> +#include <asm/smp.h> +#include <asm/cacheinfo.h> +#include <asm/spec-ctrl.h> +#include <asm/delay.h> +#ifdef CONFIG_X86_64 +# include <asm/set_memory.h> +#endif + +#include "cpu.h" + +/* + * nodes_per_socket: Stores the number of nodes per socket. + * Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8] + */ +static u32 nodes_per_socket = 1; + +#ifdef CONFIG_NUMA +/* + * To workaround broken NUMA config. Read the comment in + * srat_detect_node(). + */ +static int nearby_node(int apicid) +{ + int i, node; + + for (i = apicid - 1; i >= 0; i--) { + node = __apicid_to_node[i]; + if (node != NUMA_NO_NODE && node_online(node)) + return node; + } + for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) { + node = __apicid_to_node[i]; + if (node != NUMA_NO_NODE && node_online(node)) + return node; + } + return first_node(node_online_map); /* Shouldn't happen */ +} +#endif + +static void hygon_get_topology_early(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_TOPOEXT)) + smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; +} + +/* + * Fixup core topology information for + * (1) Hygon multi-node processors + * Assumption: Number of cores in each internal node is the same. + * (2) Hygon processors supporting compute units + */ +static void hygon_get_topology(struct cpuinfo_x86 *c) +{ + u8 node_id; + int cpu = smp_processor_id(); + + /* get information required for multi-node processors */ + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + int err; + u32 eax, ebx, ecx, edx; + + cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); + + node_id = ecx & 0xff; + + c->cpu_core_id = ebx & 0xff; + + if (smp_num_siblings > 1) + c->x86_max_cores /= smp_num_siblings; + + /* + * In case leaf B is available, use it to derive + * topology information. + */ + err = detect_extended_topology(c); + if (!err) + c->x86_coreid_bits = get_count_order(c->x86_max_cores); + + cacheinfo_hygon_init_llc_id(c, cpu, node_id); + } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { + u64 value; + + rdmsrl(MSR_FAM10H_NODE_ID, value); + node_id = value & 7; + + per_cpu(cpu_llc_id, cpu) = node_id; + } else + return; + + if (nodes_per_socket > 1) + set_cpu_cap(c, X86_FEATURE_AMD_DCM); +} + +/* + * On Hygon setup the lower bits of the APIC id distinguish the cores. + * Assumes number of cores is a power of two. + */ +static void hygon_detect_cmp(struct cpuinfo_x86 *c) +{ + unsigned int bits; + int cpu = smp_processor_id(); + + bits = c->x86_coreid_bits; + /* Low order bits define the core id (index of core in socket) */ + c->cpu_core_id = c->initial_apicid & ((1 << bits)-1); + /* Convert the initial APIC ID into the socket ID */ + c->phys_proc_id = c->initial_apicid >> bits; + /* use socket ID also for last level cache */ + per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; +} + +static void srat_detect_node(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_NUMA + int cpu = smp_processor_id(); + int node; + unsigned int apicid = c->apicid; + + node = numa_cpu_node(cpu); + if (node == NUMA_NO_NODE) + node = per_cpu(cpu_llc_id, cpu); + + /* + * On multi-fabric platform (e.g. Numascale NumaChip) a + * platform-specific handler needs to be called to fixup some + * IDs of the CPU. + */ + if (x86_cpuinit.fixup_cpu_id) + x86_cpuinit.fixup_cpu_id(c, node); + + if (!node_online(node)) { + /* + * Two possibilities here: + * + * - The CPU is missing memory and no node was created. In + * that case try picking one from a nearby CPU. + * + * - The APIC IDs differ from the HyperTransport node IDs. + * Assume they are all increased by a constant offset, but + * in the same order as the HT nodeids. If that doesn't + * result in a usable node fall back to the path for the + * previous case. + * + * This workaround operates directly on the mapping between + * APIC ID and NUMA node, assuming certain relationship + * between APIC ID, HT node ID and NUMA topology. As going + * through CPU mapping may alter the outcome, directly + * access __apicid_to_node[]. + */ + int ht_nodeid = c->initial_apicid; + + if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE) + node = __apicid_to_node[ht_nodeid]; + /* Pick a nearby node */ + if (!node_online(node)) + node = nearby_node(apicid); + } + numa_set_node(cpu, node); +#endif +} + +static void early_init_hygon_mc(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + unsigned int bits, ecx; + + /* Multi core CPU? */ + if (c->extended_cpuid_level < 0x80000008) + return; + + ecx = cpuid_ecx(0x80000008); + + c->x86_max_cores = (ecx & 0xff) + 1; + + /* CPU telling us the core id bits shift? */ + bits = (ecx >> 12) & 0xF; + + /* Otherwise recompute */ + if (bits == 0) { + while ((1 << bits) < c->x86_max_cores) + bits++; + } + + c->x86_coreid_bits = bits; +#endif +} + +static void bsp_init_hygon(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_X86_64 + unsigned long long tseg; + + /* + * Split up direct mapping around the TSEG SMM area. + * Don't do it for gbpages because there seems very little + * benefit in doing so. + */ + if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { + unsigned long pfn = tseg >> PAGE_SHIFT; + + pr_debug("tseg: %010llx\n", tseg); + if (pfn_range_is_mapped(pfn, pfn + 1)) + set_memory_4k((unsigned long)__va(tseg), 1); + } +#endif + + if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { + u64 val; + + rdmsrl(MSR_K7_HWCR, val); + if (!(val & BIT(24))) + pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n"); + } + + if (cpu_has(c, X86_FEATURE_MWAITX)) + use_mwaitx_delay(); + + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + u32 ecx; + + ecx = cpuid_ecx(0x8000001e); + nodes_per_socket = ((ecx >> 8) & 7) + 1; + } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { + u64 value; + + rdmsrl(MSR_FAM10H_NODE_ID, value); + nodes_per_socket = ((value >> 3) & 7) + 1; + } + + if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && + !boot_cpu_has(X86_FEATURE_VIRT_SSBD)) { + /* + * Try to cache the base value so further operations can + * avoid RMW. If that faults, do not enable SSBD. + */ + if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) { + setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD); + setup_force_cpu_cap(X86_FEATURE_SSBD); + x86_amd_ls_cfg_ssbd_mask = 1ULL << 10; + } + } +} + +static void early_init_hygon(struct cpuinfo_x86 *c) +{ + u32 dummy; + + early_init_hygon_mc(c); + + set_cpu_cap(c, X86_FEATURE_K8); + + rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); + + /* + * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate + * with P/T states and does not stop in deep C-states + */ + if (c->x86_power & (1 << 8)) { + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); + } + + /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ + if (c->x86_power & BIT(12)) + set_cpu_cap(c, X86_FEATURE_ACC_POWER); + +#ifdef CONFIG_X86_64 + set_cpu_cap(c, X86_FEATURE_SYSCALL32); +#endif + +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) + /* + * ApicID can always be treated as an 8-bit value for Hygon APIC So, we + * can safely set X86_FEATURE_EXTD_APICID unconditionally. + */ + if (boot_cpu_has(X86_FEATURE_APIC)) + set_cpu_cap(c, X86_FEATURE_EXTD_APICID); +#endif + + /* + * This is only needed to tell the kernel whether to use VMCALL + * and VMMCALL. VMMCALL is never executed except under virt, so + * we can set it unconditionally. + */ + set_cpu_cap(c, X86_FEATURE_VMMCALL); + + hygon_get_topology_early(c); +} + +static void init_hygon(struct cpuinfo_x86 *c) +{ + early_init_hygon(c); + + /* + * Bit 31 in normal CPUID used for nonstandard 3DNow ID; + * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway + */ + clear_cpu_cap(c, 0*32+31); + + set_cpu_cap(c, X86_FEATURE_REP_GOOD); + + /* get apicid instead of initial apic id from cpuid */ + c->apicid = hard_smp_processor_id(); + + set_cpu_cap(c, X86_FEATURE_ZEN); + set_cpu_cap(c, X86_FEATURE_CPB); + + cpu_detect_cache_sizes(c); + + hygon_detect_cmp(c); + hygon_get_topology(c); + srat_detect_node(c); + + init_hygon_cacheinfo(c); + + if (cpu_has(c, X86_FEATURE_XMM2)) { + 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); + } + } + + /* + * Hygon processors have APIC timer running in deep C states. + */ + set_cpu_cap(c, X86_FEATURE_ARAT); + + /* Hygon CPUs don't reset SS attributes on SYSRET, Xen does. */ + if (!cpu_has(c, X86_FEATURE_XENPV)) + set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); +} + +static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c) +{ + u32 ebx, eax, ecx, edx; + u16 mask = 0xfff; + + if (c->extended_cpuid_level < 0x80000006) + return; + + cpuid(0x80000006, &eax, &ebx, &ecx, &edx); + + tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask; + tlb_lli_4k[ENTRIES] = ebx & mask; + + /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ + if (!((eax >> 16) & mask)) + tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff; + else + tlb_lld_2m[ENTRIES] = (eax >> 16) & mask; + + /* a 4M entry uses two 2M entries */ + tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1; + + /* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ + if (!(eax & mask)) { + cpuid(0x80000005, &eax, &ebx, &ecx, &edx); + tlb_lli_2m[ENTRIES] = eax & 0xff; + } else + tlb_lli_2m[ENTRIES] = eax & mask; + + tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1; +} + +static const struct cpu_dev hygon_cpu_dev = { + .c_vendor = "Hygon", + .c_ident = { "HygonGenuine" }, + .c_early_init = early_init_hygon, + .c_detect_tlb = cpu_detect_tlb_hygon, + .c_bsp_init = bsp_init_hygon, + .c_init = init_hygon, + .c_x86_vendor = X86_VENDOR_HYGON, +}; + +cpu_dev_register(hygon_cpu_dev); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index c3af167d0a70..fc3c07fe7df5 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -150,6 +150,9 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_HYPERVISOR)) return false; + if (c->x86 != 6) + return false; + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && c->x86_stepping == spectre_bad_microcodes[i].stepping) @@ -188,7 +191,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) 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_MSR_SPEC_CTRL); setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SSBD); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL_SSBD); } /* @@ -298,6 +304,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) } check_mpx_erratum(c); + + /* + * Get the number of SMT siblings early from the extended topology + * leaf, if available. Otherwise try the legacy SMT detection. + */ + if (detect_extended_topology_early(c) < 0) + detect_ht_early(c); } #ifdef CONFIG_X86_32 @@ -453,24 +466,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -/* - * find out the number of processor cores on the die - */ -static int intel_num_cpu_cores(struct cpuinfo_x86 *c) -{ - unsigned int eax, ebx, ecx, edx; - - if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4) - return 1; - - /* Intel has a non-standard dependency on %ecx for this CPUID level. */ - cpuid_count(4, 0, &eax, &ebx, &ecx, &edx); - if (eax & 0x1f) - return (eax >> 26) + 1; - else - return 1; -} - static void detect_vmx_virtcap(struct cpuinfo_x86 *c) { /* Intel VMX MSR indicated features */ @@ -480,14 +475,17 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c) #define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001 #define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002 #define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020 +#define x86_VMX_FEATURE_EPT_CAP_AD 0x00200000 u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2; + u32 msr_vpid_cap, msr_ept_cap; clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW); clear_cpu_cap(c, X86_FEATURE_VNMI); clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); clear_cpu_cap(c, X86_FEATURE_EPT); clear_cpu_cap(c, X86_FEATURE_VPID); + clear_cpu_cap(c, X86_FEATURE_EPT_AD); rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high); msr_ctl = vmx_msr_high | vmx_msr_low; @@ -502,13 +500,102 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c) if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) && (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)) set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) + if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) { set_cpu_cap(c, X86_FEATURE_EPT); + rdmsr(MSR_IA32_VMX_EPT_VPID_CAP, + msr_ept_cap, msr_vpid_cap); + if (msr_ept_cap & x86_VMX_FEATURE_EPT_CAP_AD) + set_cpu_cap(c, X86_FEATURE_EPT_AD); + } if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID) set_cpu_cap(c, X86_FEATURE_VPID); } } +#define MSR_IA32_TME_ACTIVATE 0x982 + +/* Helpers to access TME_ACTIVATE MSR */ +#define TME_ACTIVATE_LOCKED(x) (x & 0x1) +#define TME_ACTIVATE_ENABLED(x) (x & 0x2) + +#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ +#define TME_ACTIVATE_POLICY_AES_XTS_128 0 + +#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ + +#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ +#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 + +/* Values for mktme_status (SW only construct) */ +#define MKTME_ENABLED 0 +#define MKTME_DISABLED 1 +#define MKTME_UNINITIALIZED 2 +static int mktme_status = MKTME_UNINITIALIZED; + +static void detect_tme(struct cpuinfo_x86 *c) +{ + u64 tme_activate, tme_policy, tme_crypto_algs; + int keyid_bits = 0, nr_keyids = 0; + static u64 tme_activate_cpu0 = 0; + + rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); + + if (mktme_status != MKTME_UNINITIALIZED) { + if (tme_activate != tme_activate_cpu0) { + /* Broken BIOS? */ + pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); + pr_err_once("x86/tme: MKTME is not usable\n"); + mktme_status = MKTME_DISABLED; + + /* Proceed. We may need to exclude bits from x86_phys_bits. */ + } + } else { + tme_activate_cpu0 = tme_activate; + } + + if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { + pr_info_once("x86/tme: not enabled by BIOS\n"); + mktme_status = MKTME_DISABLED; + return; + } + + if (mktme_status != MKTME_UNINITIALIZED) + goto detect_keyid_bits; + + pr_info("x86/tme: enabled by BIOS\n"); + + tme_policy = TME_ACTIVATE_POLICY(tme_activate); + if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) + pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); + + tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); + if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { + pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", + tme_crypto_algs); + mktme_status = MKTME_DISABLED; + } +detect_keyid_bits: + keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); + nr_keyids = (1UL << keyid_bits) - 1; + if (nr_keyids) { + pr_info_once("x86/mktme: enabled by BIOS\n"); + pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); + } else { + pr_info_once("x86/mktme: disabled by BIOS\n"); + } + + if (mktme_status == MKTME_UNINITIALIZED) { + /* MKTME is usable */ + mktme_status = MKTME_ENABLED; + } + + /* + * KeyID bits effectively lower the number of physical address + * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + */ + c->x86_phys_bits -= keyid_bits; +} + static void init_intel_energy_perf(struct cpuinfo_x86 *c) { u64 epb; @@ -569,8 +656,6 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c) static void init_intel(struct cpuinfo_x86 *c) { - unsigned int l2 = 0; - early_init_intel(c); intel_workarounds(c); @@ -587,19 +672,13 @@ static void init_intel(struct cpuinfo_x86 *c) * let's use the legacy cpuid vector 0x1 and 0x4 for topology * detection. */ - c->x86_max_cores = intel_num_cpu_cores(c); + detect_num_cpu_cores(c); #ifdef CONFIG_X86_32 detect_ht(c); #endif } - l2 = init_intel_cacheinfo(c); - - /* Detect legacy cache sizes if init_intel_cacheinfo did not */ - if (l2 == 0) { - cpu_detect_cache_sizes(c); - l2 = c->x86_cache_size; - } + init_intel_cacheinfo(c); if (c->cpuid_level > 9) { unsigned eax = cpuid_eax(10); @@ -612,7 +691,8 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); if (boot_cpu_has(X86_FEATURE_DS)) { - unsigned int l1; + unsigned int l1, l2; + rdmsr(MSR_IA32_MISC_ENABLE, l1, l2); if (!(l1 & (1<<11))) set_cpu_cap(c, X86_FEATURE_BTS); @@ -640,6 +720,7 @@ static void init_intel(struct cpuinfo_x86 *c) * Dixon is NOT a Celeron. */ if (c->x86 == 6) { + unsigned int l2 = c->x86_cache_size; char *p = NULL; switch (c->x86_model) { @@ -679,6 +760,9 @@ static void init_intel(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_VMX)) detect_vmx_virtcap(c); + if (cpu_has(c, X86_FEATURE_TME)) + detect_tme(c); + init_intel_energy_perf(c); init_intel_misc_features(c); @@ -748,6 +832,9 @@ static const struct _tlb_table intel_tlb_table[] = { { 0x5d, TLB_DATA_4K_4M, 256, " TLB_DATA 4 KByte and 4 MByte pages" }, { 0x61, TLB_INST_4K, 48, " TLB_INST 4 KByte pages, full associative" }, { 0x63, TLB_DATA_1G, 4, " TLB_DATA 1 GByte pages, 4-way set associative" }, + { 0x6b, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 8-way associative" }, + { 0x6c, TLB_DATA_2M_4M, 128, " TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" }, + { 0x6d, TLB_DATA_1G, 16, " TLB_DATA 1 GByte pages, fully associative" }, { 0x76, TLB_INST_2M_4M, 8, " TLB_INST 2-MByte or 4-MByte pages, fully associative" }, { 0xb0, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 4-way set associative" }, { 0xb1, TLB_INST_2M_4M, 4, " TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" }, diff --git a/arch/x86/kernel/cpu/intel_pconfig.c b/arch/x86/kernel/cpu/intel_pconfig.c new file mode 100644 index 000000000000..0771a905b286 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_pconfig.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel PCONFIG instruction support. + * + * Copyright (C) 2017 Intel Corporation + * + * Author: + * Kirill A. Shutemov <kirill.shutemov@linux.intel.com> + */ + +#include <asm/cpufeature.h> +#include <asm/intel_pconfig.h> + +#define PCONFIG_CPUID 0x1b + +#define PCONFIG_CPUID_SUBLEAF_MASK ((1 << 12) - 1) + +/* Subleaf type (EAX) for PCONFIG CPUID leaf (0x1B) */ +enum { + PCONFIG_CPUID_SUBLEAF_INVALID = 0, + PCONFIG_CPUID_SUBLEAF_TARGETID = 1, +}; + +/* Bitmask of supported targets */ +static u64 targets_supported __read_mostly; + +int pconfig_target_supported(enum pconfig_target target) +{ + /* + * We would need to re-think the implementation once we get > 64 + * PCONFIG targets. Spec allows up to 2^32 targets. + */ + BUILD_BUG_ON(PCONFIG_TARGET_NR >= 64); + + if (WARN_ON_ONCE(target >= 64)) + return 0; + return targets_supported & (1ULL << target); +} + +static int __init intel_pconfig_init(void) +{ + int subleaf; + + if (!boot_cpu_has(X86_FEATURE_PCONFIG)) + return 0; + + /* + * Scan subleafs of PCONFIG CPUID leaf. + * + * Subleafs of the same type need not to be consecutive. + * + * Stop on the first invalid subleaf type. All subleafs after the first + * invalid are invalid too. + */ + for (subleaf = 0; subleaf < INT_MAX; subleaf++) { + struct cpuid_regs regs; + + cpuid_count(PCONFIG_CPUID, subleaf, + ®s.eax, ®s.ebx, ®s.ecx, ®s.edx); + + switch (regs.eax & PCONFIG_CPUID_SUBLEAF_MASK) { + case PCONFIG_CPUID_SUBLEAF_INVALID: + /* Stop on the first invalid subleaf */ + goto out; + case PCONFIG_CPUID_SUBLEAF_TARGETID: + /* Mark supported PCONFIG targets */ + if (regs.ebx < 64) + targets_supported |= (1ULL << regs.ebx); + if (regs.ecx < 64) + targets_supported |= (1ULL << regs.ecx); + if (regs.edx < 64) + targets_supported |= (1ULL << regs.edx); + break; + default: + /* Unknown CPUID.PCONFIG subleaf: ignore */ + break; + } + } +out: + return 0; +} +arch_initcall(intel_pconfig_init); diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 589b948e6e01..44272b7107ad 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -33,8 +33,8 @@ #include <asm/intel_rdt_sched.h> #include "intel_rdt.h" -#define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 +#define MBA_MAX_MBPS U32_MAX /* Mutex to protect rdtgroup access. */ DEFINE_MUTEX(rdtgroup_mutex); @@ -178,7 +178,7 @@ struct rdt_resource rdt_resources_all[] = { .msr_update = mba_wrmsr, .cache_level = 3, .parse_ctrlval = parse_bw, - .format_str = "%d=%*d", + .format_str = "%d=%*u", .fflags = RFTYPE_RES_MB, }, }; @@ -230,6 +230,14 @@ static inline void cache_alloc_hsw_probe(void) rdt_alloc_capable = true; } +bool is_mba_sc(struct rdt_resource *r) +{ + if (!r) + return rdt_resources_all[RDT_RESOURCE_MBA].membw.mba_sc; + + return r->membw.mba_sc; +} + /* * rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values * exposed to user interface and the h/w understandable delay values. @@ -341,7 +349,7 @@ static int get_cache_id(int cpu, int level) * that can be written to QOS_MSRs. * There are currently no SKUs which support non linear delay values. */ -static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) +u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) { if (r->membw.delay_linear) return MAX_MBA_BW - bw; @@ -431,25 +439,40 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, return NULL; } +void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm) +{ + int i; + + /* + * Initialize the Control MSRs to having no control. + * For Cache Allocation: Set all bits in cbm + * For Memory Allocation: Set b/w requested to 100% + * and the bandwidth in MBps to U32_MAX + */ + for (i = 0; i < r->num_closid; i++, dc++, dm++) { + *dc = r->default_ctrl; + *dm = MBA_MAX_MBPS; + } +} + static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) { struct msr_param m; - u32 *dc; - int i; + u32 *dc, *dm; dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL); if (!dc) return -ENOMEM; - d->ctrl_val = dc; + dm = kmalloc_array(r->num_closid, sizeof(*d->mbps_val), GFP_KERNEL); + if (!dm) { + kfree(dc); + return -ENOMEM; + } - /* - * Initialize the Control MSRs to having no control. - * For Cache Allocation: Set all bits in cbm - * For Memory Allocation: Set b/w requested to 100 - */ - for (i = 0; i < r->num_closid; i++, dc++) - *dc = r->default_ctrl; + d->ctrl_val = dc; + d->mbps_val = dm; + setup_default_ctrlval(r, dc, dm); m.low = 0; m.high = r->num_closid; @@ -462,9 +485,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) size_t tsize; if (is_llc_occupancy_enabled()) { - d->rmid_busy_llc = kcalloc(BITS_TO_LONGS(r->num_rmid), - sizeof(unsigned long), - GFP_KERNEL); + d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL); if (!d->rmid_busy_llc) return -ENOMEM; INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); @@ -473,7 +494,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) tsize = sizeof(*d->mbm_total); d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL); if (!d->mbm_total) { - kfree(d->rmid_busy_llc); + bitmap_free(d->rmid_busy_llc); return -ENOMEM; } } @@ -481,7 +502,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) tsize = sizeof(*d->mbm_local); d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL); if (!d->mbm_local) { - kfree(d->rmid_busy_llc); + bitmap_free(d->rmid_busy_llc); kfree(d->mbm_total); return -ENOMEM; } @@ -587,8 +608,16 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cancel_delayed_work(&d->cqm_limbo); } + /* + * rdt_domain "d" is going to be freed below, so clear + * its pointer from pseudo_lock_region struct. + */ + if (d->plr) + d->plr->d = NULL; + kfree(d->ctrl_val); - kfree(d->rmid_busy_llc); + kfree(d->mbps_val); + bitmap_free(d->rmid_busy_llc); kfree(d->mbm_total); kfree(d->mbm_local); kfree(d); @@ -821,6 +850,8 @@ static __init void rdt_quirks(void) case INTEL_FAM6_SKYLAKE_X: if (boot_cpu_data.x86_stepping <= 4) set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat"); + else + set_rdt_options("!l3cat"); } } @@ -833,6 +864,8 @@ static __init bool get_rdt_resources(void) return (rdt_mon_capable || rdt_alloc_capable); } +static enum cpuhp_state rdt_online; + static int __init intel_rdt_late_init(void) { struct rdt_resource *r; @@ -854,6 +887,7 @@ static int __init intel_rdt_late_init(void) cpuhp_remove_state(state); return ret; } + rdt_online = state; for_each_alloc_capable_rdt_resource(r) pr_info("Intel RDT %s allocation detected\n", r->name); @@ -865,3 +899,11 @@ static int __init intel_rdt_late_init(void) } late_initcall(intel_rdt_late_init); + +static void __exit intel_rdt_exit(void) +{ + cpuhp_remove_state(rdt_online); + rdtgroup_exit(); +} + +__exitcall(intel_rdt_exit); diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 3fd7a70ee04a..3736f6dc9545 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -28,6 +28,7 @@ #define MBM_CNTR_WIDTH 24 #define MBM_OVERFLOW_INTERVAL 1000 +#define MAX_MBA_BW 100u #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) @@ -80,6 +81,34 @@ enum rdt_group_type { }; /** + * enum rdtgrp_mode - Mode of a RDT resource group + * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations + * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed + * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking + * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations + * allowed AND the allocations are Cache Pseudo-Locked + * + * The mode of a resource group enables control over the allowed overlap + * between allocations associated with different resource groups (classes + * of service). User is able to modify the mode of a resource group by + * writing to the "mode" resctrl file associated with the resource group. + * + * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by + * writing the appropriate text to the "mode" file. A resource group enters + * "pseudo-locked" mode after the schemata is written while the resource + * group is in "pseudo-locksetup" mode. + */ +enum rdtgrp_mode { + RDT_MODE_SHAREABLE = 0, + RDT_MODE_EXCLUSIVE, + RDT_MODE_PSEUDO_LOCKSETUP, + RDT_MODE_PSEUDO_LOCKED, + + /* Must be last */ + RDT_NUM_MODES, +}; + +/** * struct mongroup - store mon group's data in resctrl fs. * @mon_data_kn kernlfs node for the mon_data directory * @parent: parent rdtgrp @@ -94,6 +123,43 @@ struct mongroup { }; /** + * struct pseudo_lock_region - pseudo-lock region information + * @r: RDT resource to which this pseudo-locked region + * belongs + * @d: RDT domain to which this pseudo-locked region + * belongs + * @cbm: bitmask of the pseudo-locked region + * @lock_thread_wq: waitqueue used to wait on the pseudo-locking thread + * completion + * @thread_done: variable used by waitqueue to test if pseudo-locking + * thread completed + * @cpu: core associated with the cache on which the setup code + * will be run + * @line_size: size of the cache lines + * @size: size of pseudo-locked region in bytes + * @kmem: the kernel memory associated with pseudo-locked region + * @minor: minor number of character device associated with this + * region + * @debugfs_dir: pointer to this region's directory in the debugfs + * filesystem + * @pm_reqs: Power management QoS requests related to this region + */ +struct pseudo_lock_region { + struct rdt_resource *r; + struct rdt_domain *d; + u32 cbm; + wait_queue_head_t lock_thread_wq; + int thread_done; + int cpu; + unsigned int line_size; + unsigned int size; + void *kmem; + unsigned int minor; + struct dentry *debugfs_dir; + struct list_head pm_reqs; +}; + +/** * struct rdtgroup - store rdtgroup's data in resctrl file system. * @kn: kernfs node * @rdtgroup_list: linked list for all rdtgroups @@ -105,16 +171,20 @@ struct mongroup { * @type: indicates type of this rdtgroup - either * monitor only or ctrl_mon group * @mon: mongroup related data + * @mode: mode of resource group + * @plr: pseudo-locked region */ struct rdtgroup { - struct kernfs_node *kn; - struct list_head rdtgroup_list; - u32 closid; - struct cpumask cpu_mask; - int flags; - atomic_t waitcount; - enum rdt_group_type type; - struct mongroup mon; + struct kernfs_node *kn; + struct list_head rdtgroup_list; + u32 closid; + struct cpumask cpu_mask; + int flags; + atomic_t waitcount; + enum rdt_group_type type; + struct mongroup mon; + enum rdtgrp_mode mode; + struct pseudo_lock_region *plr; }; /* rdtgroup.flags */ @@ -147,6 +217,7 @@ extern struct list_head rdt_all_groups; extern int max_name_width, max_data_width; int __init rdtgroup_init(void); +void __exit rdtgroup_exit(void); /** * struct rftype - describe each file in the resctrl file system @@ -180,10 +251,20 @@ struct rftype { * struct mbm_state - status for each MBM counter in each domain * @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes) * @prev_msr Value of IA32_QM_CTR for this RMID last time we read it + * @chunks_bw Total local data moved. Used for bandwidth calculation + * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting + * @prev_bw The most recent bandwidth in MBps + * @delta_bw Difference between the current and previous bandwidth + * @delta_comp Indicates whether to compute the delta_bw */ struct mbm_state { u64 chunks; u64 prev_msr; + u64 chunks_bw; + u64 prev_bw_msr; + u32 prev_bw; + u32 delta_bw; + bool delta_comp; }; /** @@ -202,23 +283,27 @@ struct mbm_state { * @cqm_work_cpu: * worker cpu for CQM h/w counters * @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID) + * @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps * @new_ctrl: new ctrl value to be loaded * @have_new_ctrl: did user provide new_ctrl for this domain + * @plr: pseudo-locked region (if any) associated with domain */ struct rdt_domain { - struct list_head list; - int id; - struct cpumask cpu_mask; - unsigned long *rmid_busy_llc; - struct mbm_state *mbm_total; - struct mbm_state *mbm_local; - struct delayed_work mbm_over; - struct delayed_work cqm_limbo; - int mbm_work_cpu; - int cqm_work_cpu; - u32 *ctrl_val; - u32 new_ctrl; - bool have_new_ctrl; + struct list_head list; + int id; + struct cpumask cpu_mask; + unsigned long *rmid_busy_llc; + struct mbm_state *mbm_total; + struct mbm_state *mbm_local; + struct delayed_work mbm_over; + struct delayed_work cqm_limbo; + int mbm_work_cpu; + int cqm_work_cpu; + u32 *ctrl_val; + u32 *mbps_val; + u32 new_ctrl; + bool have_new_ctrl; + struct pseudo_lock_region *plr; }; /** @@ -259,6 +344,7 @@ struct rdt_cache { * @min_bw: Minimum memory bandwidth percentage user can request * @bw_gran: Granularity at which the memory bandwidth is allocated * @delay_linear: True if memory B/W delay is in linear scale + * @mba_sc: True if MBA software controller(mba_sc) is enabled * @mb_map: Mapping of memory B/W percentage to memory B/W delay */ struct rdt_membw { @@ -266,6 +352,7 @@ struct rdt_membw { u32 min_bw; u32 bw_gran; u32 delay_linear; + bool mba_sc; u32 *mb_map; }; @@ -295,6 +382,11 @@ static inline bool is_mbm_event(int e) e <= QOS_L3_MBM_LOCAL_EVENT_ID); } +struct rdt_parse_data { + struct rdtgroup *rdtgrp; + char *buf; +}; + /** * struct rdt_resource - attributes of an RDT resource * @rid: The index of the resource @@ -336,16 +428,19 @@ struct rdt_resource { struct rdt_cache cache; struct rdt_membw membw; const char *format_str; - int (*parse_ctrlval) (char *buf, struct rdt_resource *r, - struct rdt_domain *d); + int (*parse_ctrlval)(struct rdt_parse_data *data, + struct rdt_resource *r, + struct rdt_domain *d); struct list_head evt_list; int num_rmid; unsigned int mon_scale; unsigned long fflags; }; -int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d); -int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d); +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); extern struct mutex rdtgroup_mutex; @@ -353,7 +448,7 @@ extern struct rdt_resource rdt_resources_all[]; extern struct rdtgroup rdtgroup_default; DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); -int __init rdtgroup_init(void); +extern struct dentry *debugfs_resctrl; enum { RDT_RESOURCE_L3, @@ -424,13 +519,33 @@ void rdt_last_cmd_printf(const char *fmt, ...); void rdt_ctrl_update(void *arg); struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn); void rdtgroup_kn_unlock(struct kernfs_node *kn); +int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name); +int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, + umode_t mask); struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, struct list_head **pos); ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); +bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + unsigned long cbm, int closid, bool exclusive); +unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d, + unsigned long cbm); +enum rdtgrp_mode rdtgroup_mode_by_closid(int closid); +int rdtgroup_tasks_assigned(struct rdtgroup *r); +int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); +int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm); +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d); +int rdt_pseudo_lock_init(void); +void rdt_pseudo_lock_release(void); +int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); +void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); +int update_domains(struct rdt_resource *r, int closid); +int closids_supported(void); +void closid_free(int closid); int alloc_rmid(void); void free_rmid(u32 rmid); int rdt_get_mon_l3_config(struct rdt_resource *r); @@ -445,6 +560,9 @@ void mon_event_read(struct rmid_read *rr, struct rdt_domain *d, void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms); void mbm_handle_overflow(struct work_struct *work); +bool is_mba_sc(struct rdt_resource *r); +void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm); +u32 delay_bw_map(unsigned long bw, struct rdt_resource *r); void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms); void cqm_handle_limbo(struct work_struct *work); bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index 23e1d5c249c6..27937458c231 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -53,7 +53,8 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return false; } - if (bw < r->membw.min_bw || bw > r->default_ctrl) { + if ((bw < r->membw.min_bw || bw > r->default_ctrl) && + !is_mba_sc(r)) { rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw, r->membw.min_bw, r->default_ctrl); return false; @@ -63,18 +64,19 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } -int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { - unsigned long data; + unsigned long bw_val; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; } - if (!bw_validate(buf, &data, r)) + if (!bw_validate(data->buf, &bw_val, r)) return -EINVAL; - d->new_ctrl = data; + d->new_ctrl = bw_val; d->have_new_ctrl = true; return 0; @@ -86,7 +88,7 @@ int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d) * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.). * Additionally Haswell requires at least two bits set. */ -static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r) +static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) { unsigned long first_bit, zero_bit, val; unsigned int cbm_len = r->cache.cbm_len; @@ -125,18 +127,55 @@ static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r) * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { - unsigned long data; + struct rdtgroup *rdtgrp = data->rdtgrp; + u32 cbm_val; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; } - if(!cbm_validate(buf, &data, r)) + /* + * Cannot set up more than one pseudo-locked region in a cache + * hierarchy. + */ + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + rdtgroup_pseudo_locked_in_hierarchy(d)) { + rdt_last_cmd_printf("pseudo-locked region in hierarchy\n"); + return -EINVAL; + } + + if (!cbm_validate(data->buf, &cbm_val, r)) + return -EINVAL; + + if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE || + rdtgrp->mode == RDT_MODE_SHAREABLE) && + rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) { + rdt_last_cmd_printf("CBM overlaps with pseudo-locked region\n"); + return -EINVAL; + } + + /* + * The CBM may not overlap with the CBM of another closid if + * either is exclusive. + */ + if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) { + rdt_last_cmd_printf("overlaps with exclusive group\n"); return -EINVAL; - d->new_ctrl = data; + } + + if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) { + if (rdtgrp->mode == RDT_MODE_EXCLUSIVE || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + rdt_last_cmd_printf("overlaps with other group\n"); + return -EINVAL; + } + } + + d->new_ctrl = cbm_val; d->have_new_ctrl = true; return 0; @@ -148,12 +187,20 @@ int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d) * separated by ";". The "id" is in decimal, and must match one of * the "id"s for this resource. */ -static int parse_line(char *line, struct rdt_resource *r) +static int parse_line(char *line, struct rdt_resource *r, + struct rdtgroup *rdtgrp) { + struct rdt_parse_data data; char *dom = NULL, *id; struct rdt_domain *d; unsigned long dom_id; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + r->rid == RDT_RESOURCE_MBA) { + rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n"); + return -EINVAL; + } + next: if (!line || line[0] == '\0') return 0; @@ -166,19 +213,38 @@ next: dom = strim(dom); list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { - if (r->parse_ctrlval(dom, r, d)) + data.buf = dom; + data.rdtgrp = rdtgrp; + if (r->parse_ctrlval(&data, r, d)) return -EINVAL; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * In pseudo-locking setup mode and just + * parsed a valid CBM that should be + * pseudo-locked. Only one locked region per + * resource group and domain so just do + * the required initialization for single + * region and return. + */ + rdtgrp->plr->r = r; + rdtgrp->plr->d = d; + rdtgrp->plr->cbm = d->new_ctrl; + d->plr = rdtgrp->plr; + return 0; + } goto next; } } return -EINVAL; } -static int update_domains(struct rdt_resource *r, int closid) +int update_domains(struct rdt_resource *r, int closid) { struct msr_param msr_param; cpumask_var_t cpu_mask; struct rdt_domain *d; + bool mba_sc; + u32 *dc; int cpu; if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) @@ -188,13 +254,20 @@ static int update_domains(struct rdt_resource *r, int closid) msr_param.high = msr_param.low + 1; msr_param.res = r; + mba_sc = is_mba_sc(r); list_for_each_entry(d, &r->domains, list) { - if (d->have_new_ctrl && d->new_ctrl != d->ctrl_val[closid]) { + dc = !mba_sc ? d->ctrl_val : d->mbps_val; + if (d->have_new_ctrl && d->new_ctrl != dc[closid]) { cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); - d->ctrl_val[closid] = d->new_ctrl; + dc[closid] = d->new_ctrl; } } - if (cpumask_empty(cpu_mask)) + + /* + * Avoid writing the control msr with control values when + * MBA software controller is enabled + */ + if (cpumask_empty(cpu_mask) || mba_sc) goto done; cpu = get_cpu(); /* Update CBM on this cpu if it's in cpu_mask. */ @@ -210,13 +283,14 @@ done: return 0; } -static int rdtgroup_parse_resource(char *resname, char *tok, int closid) +static int rdtgroup_parse_resource(char *resname, char *tok, + struct rdtgroup *rdtgrp) { struct rdt_resource *r; for_each_alloc_enabled_rdt_resource(r) { - if (!strcmp(resname, r->name) && closid < r->num_closid) - return parse_line(tok, r); + if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid) + return parse_line(tok, r, rdtgrp); } rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname); return -EINVAL; @@ -229,7 +303,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, struct rdt_domain *dom; struct rdt_resource *r; char *tok, *resname; - int closid, ret = 0; + int ret = 0; /* Valid input requires a trailing newline */ if (nbytes == 0 || buf[nbytes - 1] != '\n') @@ -243,7 +317,15 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, } rdt_last_cmd_clear(); - closid = rdtgrp->closid; + /* + * No changes to pseudo-locked region allowed. It has to be removed + * and re-created instead. + */ + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + ret = -EINVAL; + rdt_last_cmd_puts("resource group is pseudo-locked\n"); + goto out; + } for_each_alloc_enabled_rdt_resource(r) { list_for_each_entry(dom, &r->domains, list) @@ -262,17 +344,27 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, ret = -EINVAL; goto out; } - ret = rdtgroup_parse_resource(resname, tok, closid); + ret = rdtgroup_parse_resource(resname, tok, rdtgrp); if (ret) goto out; } for_each_alloc_enabled_rdt_resource(r) { - ret = update_domains(r, closid); + ret = update_domains(r, rdtgrp->closid); if (ret) goto out; } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * If pseudo-locking fails we keep the resource group in + * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service + * active and updated for just the domain the pseudo-locked + * region was requested for. + */ + ret = rdtgroup_pseudo_lock_create(rdtgrp); + } + out: rdtgroup_kn_unlock(of->kn); return ret ?: nbytes; @@ -282,13 +374,17 @@ static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid) { struct rdt_domain *dom; bool sep = false; + u32 ctrl_val; seq_printf(s, "%*s:", max_name_width, r->name); list_for_each_entry(dom, &r->domains, list) { if (sep) seq_puts(s, ";"); + + ctrl_val = (!is_mba_sc(r) ? dom->ctrl_val[closid] : + dom->mbps_val[closid]); seq_printf(s, r->format_str, dom->id, max_data_width, - dom->ctrl_val[closid]); + ctrl_val); sep = true; } seq_puts(s, "\n"); @@ -304,10 +400,26 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { - closid = rdtgrp->closid; - for_each_alloc_enabled_rdt_resource(r) { - if (closid < r->num_closid) - show_doms(s, r, closid); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + for_each_alloc_enabled_rdt_resource(r) + seq_printf(s, "%s:uninitialized\n", r->name); + } else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + seq_printf(s, "%s:%d=%x\n", + rdtgrp->plr->r->name, + rdtgrp->plr->d->id, + rdtgrp->plr->cbm); + } + } else { + closid = rdtgrp->closid; + for_each_alloc_enabled_rdt_resource(r) { + if (closid < r->num_closid) + show_doms(s, r, closid); + } } } else { ret = -ENOENT; diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c index 681450eee428..b0f3aed76b75 100644 --- a/arch/x86/kernel/cpu/intel_rdt_monitor.c +++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c @@ -225,10 +225,18 @@ void free_rmid(u32 rmid) list_add_tail(&entry->list, &rmid_free_lru); } +static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr) +{ + u64 shift = 64 - MBM_CNTR_WIDTH, chunks; + + chunks = (cur_msr << shift) - (prev_msr << shift); + return chunks >>= shift; +} + static int __mon_event_count(u32 rmid, struct rmid_read *rr) { - u64 chunks, shift, tval; struct mbm_state *m; + u64 chunks, tval; tval = __rmid_read(rmid, rr->evtid); if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) { @@ -254,14 +262,12 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) } if (rr->first) { - m->prev_msr = tval; - m->chunks = 0; + memset(m, 0, sizeof(struct mbm_state)); + m->prev_bw_msr = m->prev_msr = tval; return 0; } - shift = 64 - MBM_CNTR_WIDTH; - chunks = (tval << shift) - (m->prev_msr << shift); - chunks >>= shift; + chunks = mbm_overflow_count(m->prev_msr, tval); m->chunks += chunks; m->prev_msr = tval; @@ -270,6 +276,32 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) } /* + * Supporting function to calculate the memory bandwidth + * and delta bandwidth in MBps. + */ +static void mbm_bw_count(u32 rmid, struct rmid_read *rr) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + struct mbm_state *m = &rr->d->mbm_local[rmid]; + u64 tval, cur_bw, chunks; + + tval = __rmid_read(rmid, rr->evtid); + if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) + return; + + chunks = mbm_overflow_count(m->prev_bw_msr, tval); + m->chunks_bw += chunks; + m->chunks = m->chunks_bw; + cur_bw = (chunks * r->mon_scale) >> 20; + + if (m->delta_comp) + m->delta_bw = abs(cur_bw - m->prev_bw); + m->delta_comp = false; + m->prev_bw = cur_bw; + m->prev_bw_msr = tval; +} + +/* * This is called via IPI to read the CQM/MBM counters * on a domain. */ @@ -297,6 +329,118 @@ void mon_event_count(void *info) } } +/* + * Feedback loop for MBA software controller (mba_sc) + * + * mba_sc is a feedback loop where we periodically read MBM counters and + * adjust the bandwidth percentage values via the IA32_MBA_THRTL_MSRs so + * that: + * + * current bandwdith(cur_bw) < user specified bandwidth(user_bw) + * + * This uses the MBM counters to measure the bandwidth and MBA throttle + * MSRs to control the bandwidth for a particular rdtgrp. It builds on the + * fact that resctrl rdtgroups have both monitoring and control. + * + * The frequency of the checks is 1s and we just tag along the MBM overflow + * timer. Having 1s interval makes the calculation of bandwidth simpler. + * + * Although MBA's goal is to restrict the bandwidth to a maximum, there may + * be a need to increase the bandwidth to avoid uncecessarily restricting + * the L2 <-> L3 traffic. + * + * Since MBA controls the L2 external bandwidth where as MBM measures the + * L3 external bandwidth the following sequence could lead to such a + * situation. + * + * Consider an rdtgroup which had high L3 <-> memory traffic in initial + * phases -> mba_sc kicks in and reduced bandwidth percentage values -> but + * after some time rdtgroup has mostly L2 <-> L3 traffic. + * + * In this case we may restrict the rdtgroup's L2 <-> L3 traffic as its + * throttle MSRs already have low percentage values. To avoid + * unnecessarily restricting such rdtgroups, we also increase the bandwidth. + */ +static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) +{ + u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val; + struct mbm_state *pmbm_data, *cmbm_data; + u32 cur_bw, delta_bw, user_bw; + struct rdt_resource *r_mba; + struct rdt_domain *dom_mba; + struct list_head *head; + struct rdtgroup *entry; + + r_mba = &rdt_resources_all[RDT_RESOURCE_MBA]; + closid = rgrp->closid; + rmid = rgrp->mon.rmid; + pmbm_data = &dom_mbm->mbm_local[rmid]; + + dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba); + if (!dom_mba) { + pr_warn_once("Failure to get domain for MBA update\n"); + return; + } + + cur_bw = pmbm_data->prev_bw; + user_bw = dom_mba->mbps_val[closid]; + delta_bw = pmbm_data->delta_bw; + cur_msr_val = dom_mba->ctrl_val[closid]; + + /* + * For Ctrl groups read data from child monitor groups. + */ + head = &rgrp->mon.crdtgrp_list; + list_for_each_entry(entry, head, mon.crdtgrp_list) { + cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; + cur_bw += cmbm_data->prev_bw; + delta_bw += cmbm_data->delta_bw; + } + + /* + * Scale up/down the bandwidth linearly for the ctrl group. The + * bandwidth step is the bandwidth granularity specified by the + * hardware. + * + * The delta_bw is used when increasing the bandwidth so that we + * dont alternately increase and decrease the control values + * continuously. + * + * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if + * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep + * switching between 90 and 110 continuously if we only check + * cur_bw < user_bw. + */ + if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) { + new_msr_val = cur_msr_val - r_mba->membw.bw_gran; + } else if (cur_msr_val < MAX_MBA_BW && + (user_bw > (cur_bw + delta_bw))) { + new_msr_val = cur_msr_val + r_mba->membw.bw_gran; + } else { + return; + } + + cur_msr = r_mba->msr_base + closid; + wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba)); + dom_mba->ctrl_val[closid] = new_msr_val; + + /* + * Delta values are updated dynamically package wise for each + * rdtgrp everytime the throttle MSR changes value. + * + * This is because (1)the increase in bandwidth is not perfectly + * linear and only "approximately" linear even when the hardware + * says it is linear.(2)Also since MBA is a core specific + * mechanism, the delta values vary based on number of cores used + * by the rdtgrp. + */ + pmbm_data->delta_comp = true; + list_for_each_entry(entry, head, mon.crdtgrp_list) { + cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; + cmbm_data->delta_comp = true; + } +} + static void mbm_update(struct rdt_domain *d, int rmid) { struct rmid_read rr; @@ -314,7 +458,16 @@ static void mbm_update(struct rdt_domain *d, int rmid) } if (is_mbm_local_enabled()) { rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; - __mon_event_count(rmid, &rr); + + /* + * Call the MBA software controller only for the + * control groups and when user has enabled + * the software controller explicitly. + */ + if (!is_mba_sc(NULL)) + __mon_event_count(rmid, &rr); + else + mbm_bw_count(rmid, &rr); } } @@ -385,6 +538,9 @@ void mbm_handle_overflow(struct work_struct *work) head = &prgrp->mon.crdtgrp_list; list_for_each_entry(crgrp, head, mon.crdtgrp_list) mbm_update(d, crgrp->mon.rmid); + + if (is_mba_sc(NULL)) + update_mba_bw(prgrp, d); } schedule_delayed_work_on(cpu, &d->mbm_over, delay); diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c new file mode 100644 index 000000000000..815b4e92522c --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c @@ -0,0 +1,1599 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Resource Director Technology (RDT) + * + * Pseudo-locking support built on top of Cache Allocation Technology (CAT) + * + * Copyright (C) 2018 Intel Corporation + * + * Author: Reinette Chatre <reinette.chatre@intel.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/cacheinfo.h> +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/debugfs.h> +#include <linux/kthread.h> +#include <linux/mman.h> +#include <linux/perf_event.h> +#include <linux/pm_qos.h> +#include <linux/slab.h> +#include <linux/uaccess.h> + +#include <asm/cacheflush.h> +#include <asm/intel-family.h> +#include <asm/intel_rdt_sched.h> +#include <asm/perf_event.h> + +#include "../../events/perf_event.h" /* For X86_CONFIG() */ +#include "intel_rdt.h" + +#define CREATE_TRACE_POINTS +#include "intel_rdt_pseudo_lock_event.h" + +/* + * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware + * prefetcher state. Details about this register can be found in the MSR + * tables for specific platforms found in Intel's SDM. + */ +#define MSR_MISC_FEATURE_CONTROL 0x000001a4 + +/* + * The bits needed to disable hardware prefetching varies based on the + * platform. During initialization we will discover which bits to use. + */ +static u64 prefetch_disable_bits; + +/* + * Major number assigned to and shared by all devices exposing + * pseudo-locked regions. + */ +static unsigned int pseudo_lock_major; +static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0); +static struct class *pseudo_lock_class; + +/** + * get_prefetch_disable_bits - prefetch disable bits of supported platforms + * + * Capture the list of platforms that have been validated to support + * pseudo-locking. This includes testing to ensure pseudo-locked regions + * with low cache miss rates can be created under variety of load conditions + * as well as that these pseudo-locked regions can maintain their low cache + * miss rates under variety of load conditions for significant lengths of time. + * + * After a platform has been validated to support pseudo-locking its + * hardware prefetch disable bits are included here as they are documented + * in the SDM. + * + * When adding a platform here also add support for its cache events to + * measure_cycles_perf_fn() + * + * Return: + * If platform is supported, the bits to disable hardware prefetchers, 0 + * if platform is not supported. + */ +static u64 get_prefetch_disable_bits(void) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || + boot_cpu_data.x86 != 6) + return 0; + + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_BROADWELL_X: + /* + * SDM defines bits of MSR_MISC_FEATURE_CONTROL register + * as: + * 0 L2 Hardware Prefetcher Disable (R/W) + * 1 L2 Adjacent Cache Line Prefetcher Disable (R/W) + * 2 DCU Hardware Prefetcher Disable (R/W) + * 3 DCU IP Prefetcher Disable (R/W) + * 63:4 Reserved + */ + return 0xF; + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + /* + * SDM defines bits of MSR_MISC_FEATURE_CONTROL register + * as: + * 0 L2 Hardware Prefetcher Disable (R/W) + * 1 Reserved + * 2 DCU Hardware Prefetcher Disable (R/W) + * 63:3 Reserved + */ + return 0x5; + } + + return 0; +} + +/** + * pseudo_lock_minor_get - Obtain available minor number + * @minor: Pointer to where new minor number will be stored + * + * A bitmask is used to track available minor numbers. Here the next free + * minor number is marked as unavailable and returned. + * + * Return: 0 on success, <0 on failure. + */ +static int pseudo_lock_minor_get(unsigned int *minor) +{ + unsigned long first_bit; + + first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS); + + if (first_bit == MINORBITS) + return -ENOSPC; + + __clear_bit(first_bit, &pseudo_lock_minor_avail); + *minor = first_bit; + + return 0; +} + +/** + * pseudo_lock_minor_release - Return minor number to available + * @minor: The minor number made available + */ +static void pseudo_lock_minor_release(unsigned int minor) +{ + __set_bit(minor, &pseudo_lock_minor_avail); +} + +/** + * region_find_by_minor - Locate a pseudo-lock region by inode minor number + * @minor: The minor number of the device representing pseudo-locked region + * + * When the character device is accessed we need to determine which + * pseudo-locked region it belongs to. This is done by matching the minor + * number of the device to the pseudo-locked region it belongs. + * + * Minor numbers are assigned at the time a pseudo-locked region is associated + * with a cache instance. + * + * Return: On success return pointer to resource group owning the pseudo-locked + * region, NULL on failure. + */ +static struct rdtgroup *region_find_by_minor(unsigned int minor) +{ + struct rdtgroup *rdtgrp, *rdtgrp_match = NULL; + + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (rdtgrp->plr && rdtgrp->plr->minor == minor) { + rdtgrp_match = rdtgrp; + break; + } + } + return rdtgrp_match; +} + +/** + * pseudo_lock_pm_req - A power management QoS request list entry + * @list: Entry within the @pm_reqs list for a pseudo-locked region + * @req: PM QoS request + */ +struct pseudo_lock_pm_req { + struct list_head list; + struct dev_pm_qos_request req; +}; + +static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr) +{ + struct pseudo_lock_pm_req *pm_req, *next; + + list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) { + dev_pm_qos_remove_request(&pm_req->req); + list_del(&pm_req->list); + kfree(pm_req); + } +} + +/** + * pseudo_lock_cstates_constrain - Restrict cores from entering C6 + * + * To prevent the cache from being affected by power management entering + * C6 has to be avoided. This is accomplished by requesting a latency + * requirement lower than lowest C6 exit latency of all supported + * platforms as found in the cpuidle state tables in the intel_idle driver. + * At this time it is possible to do so with a single latency requirement + * for all supported platforms. + * + * Since Goldmont is supported, which is affected by X86_BUG_MONITOR, + * the ACPI latencies need to be considered while keeping in mind that C2 + * may be set to map to deeper sleep states. In this case the latency + * requirement needs to prevent entering C2 also. + */ +static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr) +{ + struct pseudo_lock_pm_req *pm_req; + int cpu; + int ret; + + for_each_cpu(cpu, &plr->d->cpu_mask) { + pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL); + if (!pm_req) { + rdt_last_cmd_puts("fail allocating mem for PM QoS\n"); + ret = -ENOMEM; + goto out_err; + } + ret = dev_pm_qos_add_request(get_cpu_device(cpu), + &pm_req->req, + DEV_PM_QOS_RESUME_LATENCY, + 30); + if (ret < 0) { + rdt_last_cmd_printf("fail to add latency req cpu%d\n", + cpu); + kfree(pm_req); + ret = -1; + goto out_err; + } + list_add(&pm_req->list, &plr->pm_reqs); + } + + return 0; + +out_err: + pseudo_lock_cstates_relax(plr); + return ret; +} + +/** + * pseudo_lock_region_clear - Reset pseudo-lock region data + * @plr: pseudo-lock region + * + * All content of the pseudo-locked region is reset - any memory allocated + * freed. + * + * Return: void + */ +static void pseudo_lock_region_clear(struct pseudo_lock_region *plr) +{ + plr->size = 0; + plr->line_size = 0; + kfree(plr->kmem); + plr->kmem = NULL; + plr->r = NULL; + if (plr->d) + plr->d->plr = NULL; + plr->d = NULL; + plr->cbm = 0; + plr->debugfs_dir = NULL; +} + +/** + * pseudo_lock_region_init - Initialize pseudo-lock region information + * @plr: pseudo-lock region + * + * Called after user provided a schemata to be pseudo-locked. From the + * schemata the &struct pseudo_lock_region is on entry already initialized + * with the resource, domain, and capacity bitmask. Here the information + * required for pseudo-locking is deduced from this data and &struct + * pseudo_lock_region initialized further. This information includes: + * - size in bytes of the region to be pseudo-locked + * - cache line size to know the stride with which data needs to be accessed + * to be pseudo-locked + * - a cpu associated with the cache instance on which the pseudo-locking + * flow can be executed + * + * Return: 0 on success, <0 on failure. Descriptive error will be written + * to last_cmd_status buffer. + */ +static int pseudo_lock_region_init(struct pseudo_lock_region *plr) +{ + struct cpu_cacheinfo *ci; + int ret; + int i; + + /* Pick the first cpu we find that is associated with the cache. */ + plr->cpu = cpumask_first(&plr->d->cpu_mask); + + if (!cpu_online(plr->cpu)) { + rdt_last_cmd_printf("cpu %u associated with cache not online\n", + plr->cpu); + ret = -ENODEV; + goto out_region; + } + + ci = get_cpu_cacheinfo(plr->cpu); + + plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm); + + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == plr->r->cache_level) { + plr->line_size = ci->info_list[i].coherency_line_size; + return 0; + } + } + + ret = -1; + rdt_last_cmd_puts("unable to determine cache line size\n"); +out_region: + pseudo_lock_region_clear(plr); + return ret; +} + +/** + * pseudo_lock_init - Initialize a pseudo-lock region + * @rdtgrp: resource group to which new pseudo-locked region will belong + * + * A pseudo-locked region is associated with a resource group. When this + * association is created the pseudo-locked region is initialized. The + * details of the pseudo-locked region are not known at this time so only + * allocation is done and association established. + * + * Return: 0 on success, <0 on failure + */ +static int pseudo_lock_init(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr; + + plr = kzalloc(sizeof(*plr), GFP_KERNEL); + if (!plr) + return -ENOMEM; + + init_waitqueue_head(&plr->lock_thread_wq); + INIT_LIST_HEAD(&plr->pm_reqs); + rdtgrp->plr = plr; + return 0; +} + +/** + * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked + * @plr: pseudo-lock region + * + * Initialize the details required to set up the pseudo-locked region and + * allocate the contiguous memory that will be pseudo-locked to the cache. + * + * Return: 0 on success, <0 on failure. Descriptive error will be written + * to last_cmd_status buffer. + */ +static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr) +{ + int ret; + + ret = pseudo_lock_region_init(plr); + if (ret < 0) + return ret; + + /* + * We do not yet support contiguous regions larger than + * KMALLOC_MAX_SIZE. + */ + if (plr->size > KMALLOC_MAX_SIZE) { + rdt_last_cmd_puts("requested region exceeds maximum size\n"); + ret = -E2BIG; + goto out_region; + } + + plr->kmem = kzalloc(plr->size, GFP_KERNEL); + if (!plr->kmem) { + rdt_last_cmd_puts("unable to allocate memory\n"); + ret = -ENOMEM; + goto out_region; + } + + ret = 0; + goto out; +out_region: + pseudo_lock_region_clear(plr); +out: + return ret; +} + +/** + * pseudo_lock_free - Free a pseudo-locked region + * @rdtgrp: resource group to which pseudo-locked region belonged + * + * The pseudo-locked region's resources have already been released, or not + * yet created at this point. Now it can be freed and disassociated from the + * resource group. + * + * Return: void + */ +static void pseudo_lock_free(struct rdtgroup *rdtgrp) +{ + pseudo_lock_region_clear(rdtgrp->plr); + kfree(rdtgrp->plr); + rdtgrp->plr = NULL; +} + +/** + * pseudo_lock_fn - Load kernel memory into cache + * @_rdtgrp: resource group to which pseudo-lock region belongs + * + * This is the core pseudo-locking flow. + * + * First we ensure that the kernel memory cannot be found in the cache. + * Then, while taking care that there will be as little interference as + * possible, the memory to be loaded is accessed while core is running + * with class of service set to the bitmask of the pseudo-locked region. + * After this is complete no future CAT allocations will be allowed to + * overlap with this bitmask. + * + * Local register variables are utilized to ensure that the memory region + * to be locked is the only memory access made during the critical locking + * loop. + * + * Return: 0. Waiter on waitqueue will be woken on completion. + */ +static int pseudo_lock_fn(void *_rdtgrp) +{ + struct rdtgroup *rdtgrp = _rdtgrp; + struct pseudo_lock_region *plr = rdtgrp->plr; + u32 rmid_p, closid_p; + unsigned long i; +#ifdef CONFIG_KASAN + /* + * The registers used for local register variables are also used + * when KASAN is active. When KASAN is active we use a regular + * variable to ensure we always use a valid pointer, but the cost + * is that this variable will enter the cache through evicting the + * memory we are trying to lock into the cache. Thus expect lower + * pseudo-locking success rate when KASAN is active. + */ + unsigned int line_size; + unsigned int size; + void *mem_r; +#else + register unsigned int line_size asm("esi"); + register unsigned int size asm("edi"); +#ifdef CONFIG_X86_64 + register void *mem_r asm("rbx"); +#else + register void *mem_r asm("ebx"); +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_KASAN */ + + /* + * Make sure none of the allocated memory is cached. If it is we + * will get a cache hit in below loop from outside of pseudo-locked + * region. + * wbinvd (as opposed to clflush/clflushopt) is required to + * increase likelihood that allocated cache portion will be filled + * with associated memory. + */ + native_wbinvd(); + + /* + * Always called with interrupts enabled. By disabling interrupts + * ensure that we will not be preempted during this critical section. + */ + local_irq_disable(); + + /* + * Call wrmsr and rdmsr as directly as possible to avoid tracing + * clobbering local register variables or affecting cache accesses. + * + * Disable the hardware prefetcher so that when the end of the memory + * being pseudo-locked is reached the hardware will not read beyond + * the buffer and evict pseudo-locked memory read earlier from the + * cache. + */ + __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + closid_p = this_cpu_read(pqr_state.cur_closid); + rmid_p = this_cpu_read(pqr_state.cur_rmid); + mem_r = plr->kmem; + size = plr->size; + line_size = plr->line_size; + /* + * Critical section begin: start by writing the closid associated + * with the capacity bitmask of the cache region being + * pseudo-locked followed by reading of kernel memory to load it + * into the cache. + */ + __wrmsr(IA32_PQR_ASSOC, rmid_p, rdtgrp->closid); + /* + * Cache was flushed earlier. Now access kernel memory to read it + * into cache region associated with just activated plr->closid. + * Loop over data twice: + * - In first loop the cache region is shared with the page walker + * as it populates the paging structure caches (including TLB). + * - In the second loop the paging structure caches are used and + * cache region is populated with the memory being referenced. + */ + for (i = 0; i < size; i += PAGE_SIZE) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + for (i = 0; i < size; i += line_size) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + /* + * Critical section end: restore closid with capacity bitmask that + * does not overlap with pseudo-locked region. + */ + __wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p); + + /* Re-enable the hardware prefetcher(s) */ + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); + + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +/** + * rdtgroup_monitor_in_progress - Test if monitoring in progress + * @r: resource group being queried + * + * Return: 1 if monitor groups have been created for this resource + * group, 0 otherwise. + */ +static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp) +{ + return !list_empty(&rdtgrp->mon.crdtgrp_list); +} + +/** + * rdtgroup_locksetup_user_restrict - Restrict user access to group + * @rdtgrp: resource group needing access restricted + * + * A resource group used for cache pseudo-locking cannot have cpus or tasks + * assigned to it. This is communicated to the user by restricting access + * to all the files that can be used to make such changes. + * + * Permissions restored with rdtgroup_locksetup_user_restore() + * + * Return: 0 on success, <0 on failure. If a failure occurs during the + * restriction of access an attempt will be made to restore permissions but + * the state of the mode of these files will be uncertain when a failure + * occurs. + */ +static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp) +{ + int ret; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks"); + if (ret) + return ret; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus"); + if (ret) + goto err_tasks; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list"); + if (ret) + goto err_cpus; + + if (rdt_mon_capable) { + ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups"); + if (ret) + goto err_cpus_list; + } + + ret = 0; + goto out; + +err_cpus_list: + rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777); +err_cpus: + rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777); +err_tasks: + rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777); +out: + return ret; +} + +/** + * rdtgroup_locksetup_user_restore - Restore user access to group + * @rdtgrp: resource group needing access restored + * + * Restore all file access previously removed using + * rdtgroup_locksetup_user_restrict() + * + * Return: 0 on success, <0 on failure. If a failure occurs during the + * restoration of access an attempt will be made to restrict permissions + * again but the state of the mode of these files will be uncertain when + * a failure occurs. + */ +static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp) +{ + int ret; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777); + if (ret) + return ret; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777); + if (ret) + goto err_tasks; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777); + if (ret) + goto err_cpus; + + if (rdt_mon_capable) { + ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777); + if (ret) + goto err_cpus_list; + } + + ret = 0; + goto out; + +err_cpus_list: + rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list"); +err_cpus: + rdtgroup_kn_mode_restrict(rdtgrp, "cpus"); +err_tasks: + rdtgroup_kn_mode_restrict(rdtgrp, "tasks"); +out: + return ret; +} + +/** + * rdtgroup_locksetup_enter - Resource group enters locksetup mode + * @rdtgrp: resource group requested to enter locksetup mode + * + * A resource group enters locksetup mode to reflect that it would be used + * to represent a pseudo-locked region and is in the process of being set + * up to do so. A resource group used for a pseudo-locked region would + * lose the closid associated with it so we cannot allow it to have any + * tasks or cpus assigned nor permit tasks or cpus to be assigned in the + * future. Monitoring of a pseudo-locked region is not allowed either. + * + * The above and more restrictions on a pseudo-locked region are checked + * for and enforced before the resource group enters the locksetup mode. + * + * Returns: 0 if the resource group successfully entered locksetup mode, <0 + * on failure. On failure the last_cmd_status buffer is updated with text to + * communicate details of failure to the user. + */ +int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) +{ + int ret; + + /* + * The default resource group can neither be removed nor lose the + * default closid associated with it. + */ + if (rdtgrp == &rdtgroup_default) { + rdt_last_cmd_puts("cannot pseudo-lock default group\n"); + return -EINVAL; + } + + /* + * Cache Pseudo-locking not supported when CDP is enabled. + * + * Some things to consider if you would like to enable this + * support (using L3 CDP as example): + * - When CDP is enabled two separate resources are exposed, + * L3DATA and L3CODE, but they are actually on the same cache. + * The implication for pseudo-locking is that if a + * pseudo-locked region is created on a domain of one + * resource (eg. L3CODE), then a pseudo-locked region cannot + * be created on that same domain of the other resource + * (eg. L3DATA). This is because the creation of a + * pseudo-locked region involves a call to wbinvd that will + * affect all cache allocations on particular domain. + * - Considering the previous, it may be possible to only + * expose one of the CDP resources to pseudo-locking and + * hide the other. For example, we could consider to only + * expose L3DATA and since the L3 cache is unified it is + * still possible to place instructions there are execute it. + * - If only one region is exposed to pseudo-locking we should + * still keep in mind that availability of a portion of cache + * for pseudo-locking should take into account both resources. + * Similarly, if a pseudo-locked region is created in one + * resource, the portion of cache used by it should be made + * unavailable to all future allocations from both resources. + */ + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled || + rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) { + rdt_last_cmd_puts("CDP enabled\n"); + return -EINVAL; + } + + /* + * Not knowing the bits to disable prefetching implies that this + * platform does not support Cache Pseudo-Locking. + */ + prefetch_disable_bits = get_prefetch_disable_bits(); + if (prefetch_disable_bits == 0) { + rdt_last_cmd_puts("pseudo-locking not supported\n"); + return -EINVAL; + } + + if (rdtgroup_monitor_in_progress(rdtgrp)) { + rdt_last_cmd_puts("monitoring in progress\n"); + return -EINVAL; + } + + if (rdtgroup_tasks_assigned(rdtgrp)) { + rdt_last_cmd_puts("tasks assigned to resource group\n"); + return -EINVAL; + } + + if (!cpumask_empty(&rdtgrp->cpu_mask)) { + rdt_last_cmd_puts("CPUs assigned to resource group\n"); + return -EINVAL; + } + + if (rdtgroup_locksetup_user_restrict(rdtgrp)) { + rdt_last_cmd_puts("unable to modify resctrl permissions\n"); + return -EIO; + } + + ret = pseudo_lock_init(rdtgrp); + if (ret) { + rdt_last_cmd_puts("unable to init pseudo-lock region\n"); + goto out_release; + } + + /* + * If this system is capable of monitoring a rmid would have been + * allocated when the control group was created. This is not needed + * anymore when this group would be used for pseudo-locking. This + * is safe to call on platforms not capable of monitoring. + */ + free_rmid(rdtgrp->mon.rmid); + + ret = 0; + goto out; + +out_release: + rdtgroup_locksetup_user_restore(rdtgrp); +out: + return ret; +} + +/** + * rdtgroup_locksetup_exit - resource group exist locksetup mode + * @rdtgrp: resource group + * + * When a resource group exits locksetup mode the earlier restrictions are + * lifted. + * + * Return: 0 on success, <0 on failure + */ +int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) +{ + int ret; + + if (rdt_mon_capable) { + ret = alloc_rmid(); + if (ret < 0) { + rdt_last_cmd_puts("out of RMIDs\n"); + return ret; + } + rdtgrp->mon.rmid = ret; + } + + ret = rdtgroup_locksetup_user_restore(rdtgrp); + if (ret) { + free_rmid(rdtgrp->mon.rmid); + return ret; + } + + pseudo_lock_free(rdtgrp); + return 0; +} + +/** + * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked + * @d: RDT domain + * @cbm: CBM to test + * + * @d represents a cache instance and @cbm a capacity bitmask that is + * considered for it. Determine if @cbm overlaps with any existing + * pseudo-locked region on @d. + * + * @cbm is unsigned long, even if only 32 bits are used, to make the + * bitmap functions work correctly. + * + * Return: true if @cbm overlaps with pseudo-locked region on @d, false + * otherwise. + */ +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm) +{ + unsigned int cbm_len; + unsigned long cbm_b; + + if (d->plr) { + cbm_len = d->plr->r->cache.cbm_len; + cbm_b = d->plr->cbm; + if (bitmap_intersects(&cbm, &cbm_b, cbm_len)) + return true; + } + return false; +} + +/** + * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy + * @d: RDT domain under test + * + * The setup of a pseudo-locked region affects all cache instances within + * the hierarchy of the region. It is thus essential to know if any + * pseudo-locked regions exist within a cache hierarchy to prevent any + * attempts to create new pseudo-locked regions in the same hierarchy. + * + * Return: true if a pseudo-locked region exists in the hierarchy of @d or + * if it is not possible to test due to memory allocation issue, + * false otherwise. + */ +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) +{ + cpumask_var_t cpu_with_psl; + struct rdt_resource *r; + struct rdt_domain *d_i; + bool ret = false; + + if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL)) + return true; + + /* + * First determine which cpus have pseudo-locked regions + * associated with them. + */ + for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(d_i, &r->domains, list) { + if (d_i->plr) + cpumask_or(cpu_with_psl, cpu_with_psl, + &d_i->cpu_mask); + } + } + + /* + * Next test if new pseudo-locked region would intersect with + * existing region. + */ + if (cpumask_intersects(&d->cpu_mask, cpu_with_psl)) + ret = true; + + free_cpumask_var(cpu_with_psl); + return ret; +} + +/** + * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory + * @_plr: pseudo-lock region to measure + * + * There is no deterministic way to test if a memory region is cached. One + * way is to measure how long it takes to read the memory, the speed of + * access is a good way to learn how close to the cpu the data was. Even + * more, if the prefetcher is disabled and the memory is read at a stride + * of half the cache line, then a cache miss will be easy to spot since the + * read of the first half would be significantly slower than the read of + * the second half. + * + * Return: 0. Waiter on waitqueue will be woken on completion. + */ +static int measure_cycles_lat_fn(void *_plr) +{ + struct pseudo_lock_region *plr = _plr; + unsigned long i; + u64 start, end; + void *mem_r; + + local_irq_disable(); + /* + * Disable hardware prefetchers. + */ + wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + mem_r = READ_ONCE(plr->kmem); + /* + * Dummy execute of the time measurement to load the needed + * instructions into the L1 instruction cache. + */ + start = rdtsc_ordered(); + for (i = 0; i < plr->size; i += 32) { + start = rdtsc_ordered(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + end = rdtsc_ordered(); + trace_pseudo_lock_mem_latency((u32)(end - start)); + } + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +/* + * Create a perf_event_attr for the hit and miss perf events that will + * be used during the performance measurement. A perf_event maintains + * a pointer to its perf_event_attr so a unique attribute structure is + * created for each perf_event. + * + * The actual configuration of the event is set right before use in order + * to use the X86_CONFIG macro. + */ +static struct perf_event_attr perf_miss_attr = { + .type = PERF_TYPE_RAW, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 0, + .exclude_user = 1, +}; + +static struct perf_event_attr perf_hit_attr = { + .type = PERF_TYPE_RAW, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 0, + .exclude_user = 1, +}; + +struct residency_counts { + u64 miss_before, hits_before; + u64 miss_after, hits_after; +}; + +static int measure_residency_fn(struct perf_event_attr *miss_attr, + struct perf_event_attr *hit_attr, + struct pseudo_lock_region *plr, + struct residency_counts *counts) +{ + u64 hits_before = 0, hits_after = 0, miss_before = 0, miss_after = 0; + struct perf_event *miss_event, *hit_event; + int hit_pmcnum, miss_pmcnum; + unsigned int line_size; + unsigned int size; + unsigned long i; + void *mem_r; + u64 tmp; + + miss_event = perf_event_create_kernel_counter(miss_attr, plr->cpu, + NULL, NULL, NULL); + if (IS_ERR(miss_event)) + goto out; + + hit_event = perf_event_create_kernel_counter(hit_attr, plr->cpu, + NULL, NULL, NULL); + if (IS_ERR(hit_event)) + goto out_miss; + + local_irq_disable(); + /* + * Check any possible error state of events used by performing + * one local read. + */ + if (perf_event_read_local(miss_event, &tmp, NULL, NULL)) { + local_irq_enable(); + goto out_hit; + } + if (perf_event_read_local(hit_event, &tmp, NULL, NULL)) { + local_irq_enable(); + goto out_hit; + } + + /* + * Disable hardware prefetchers. + */ + wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + + /* Initialize rest of local variables */ + /* + * Performance event has been validated right before this with + * interrupts disabled - it is thus safe to read the counter index. + */ + miss_pmcnum = x86_perf_rdpmc_index(miss_event); + hit_pmcnum = x86_perf_rdpmc_index(hit_event); + line_size = READ_ONCE(plr->line_size); + mem_r = READ_ONCE(plr->kmem); + size = READ_ONCE(plr->size); + + /* + * Read counter variables twice - first to load the instructions + * used in L1 cache, second to capture accurate value that does not + * include cache misses incurred because of instruction loads. + */ + rdpmcl(hit_pmcnum, hits_before); + rdpmcl(miss_pmcnum, miss_before); + /* + * From SDM: Performing back-to-back fast reads are not guaranteed + * to be monotonic. + * Use LFENCE to ensure all previous instructions are retired + * before proceeding. + */ + rmb(); + rdpmcl(hit_pmcnum, hits_before); + rdpmcl(miss_pmcnum, miss_before); + /* + * Use LFENCE to ensure all previous instructions are retired + * before proceeding. + */ + rmb(); + for (i = 0; i < size; i += line_size) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + /* + * Use LFENCE to ensure all previous instructions are retired + * before proceeding. + */ + rmb(); + rdpmcl(hit_pmcnum, hits_after); + rdpmcl(miss_pmcnum, miss_after); + /* + * Use LFENCE to ensure all previous instructions are retired + * before proceeding. + */ + rmb(); + /* Re-enable hardware prefetchers */ + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); +out_hit: + perf_event_release_kernel(hit_event); +out_miss: + perf_event_release_kernel(miss_event); +out: + /* + * All counts will be zero on failure. + */ + counts->miss_before = miss_before; + counts->hits_before = hits_before; + counts->miss_after = miss_after; + counts->hits_after = hits_after; + return 0; +} + +static int measure_l2_residency(void *_plr) +{ + struct pseudo_lock_region *plr = _plr; + struct residency_counts counts = {0}; + + /* + * Non-architectural event for the Goldmont Microarchitecture + * from Intel x86 Architecture Software Developer Manual (SDM): + * MEM_LOAD_UOPS_RETIRED D1H (event number) + * Umask values: + * L2_HIT 02H + * L2_MISS 10H + */ + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + perf_miss_attr.config = X86_CONFIG(.event = 0xd1, + .umask = 0x10); + perf_hit_attr.config = X86_CONFIG(.event = 0xd1, + .umask = 0x2); + break; + default: + goto out; + } + + measure_residency_fn(&perf_miss_attr, &perf_hit_attr, plr, &counts); + /* + * If a failure prevented the measurements from succeeding + * tracepoints will still be written and all counts will be zero. + */ + trace_pseudo_lock_l2(counts.hits_after - counts.hits_before, + counts.miss_after - counts.miss_before); +out: + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +static int measure_l3_residency(void *_plr) +{ + struct pseudo_lock_region *plr = _plr; + struct residency_counts counts = {0}; + + /* + * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event + * has two "no fix" errata associated with it: BDM35 and BDM100. On + * this platform the following events are used instead: + * LONGEST_LAT_CACHE 2EH (Documented in SDM) + * REFERENCE 4FH + * MISS 41H + */ + + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_BROADWELL_X: + /* On BDW the hit event counts references, not hits */ + perf_hit_attr.config = X86_CONFIG(.event = 0x2e, + .umask = 0x4f); + perf_miss_attr.config = X86_CONFIG(.event = 0x2e, + .umask = 0x41); + break; + default: + goto out; + } + + measure_residency_fn(&perf_miss_attr, &perf_hit_attr, plr, &counts); + /* + * If a failure prevented the measurements from succeeding + * tracepoints will still be written and all counts will be zero. + */ + + counts.miss_after -= counts.miss_before; + if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) { + /* + * On BDW references and misses are counted, need to adjust. + * Sometimes the "hits" counter is a bit more than the + * references, for example, x references but x + 1 hits. + * To not report invalid hit values in this case we treat + * that as misses equal to references. + */ + /* First compute the number of cache references measured */ + counts.hits_after -= counts.hits_before; + /* Next convert references to cache hits */ + counts.hits_after -= min(counts.miss_after, counts.hits_after); + } else { + counts.hits_after -= counts.hits_before; + } + + trace_pseudo_lock_l3(counts.hits_after, counts.miss_after); +out: + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +/** + * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region + * + * The measurement of latency to access a pseudo-locked region should be + * done from a cpu that is associated with that pseudo-locked region. + * Determine which cpu is associated with this region and start a thread on + * that cpu to perform the measurement, wait for that thread to complete. + * + * Return: 0 on success, <0 on failure + */ +static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + struct task_struct *thread; + unsigned int cpu; + int ret = -1; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + if (rdtgrp->flags & RDT_DELETED) { + ret = -ENODEV; + goto out; + } + + if (!plr->d) { + ret = -ENODEV; + goto out; + } + + plr->thread_done = 0; + cpu = cpumask_first(&plr->d->cpu_mask); + if (!cpu_online(cpu)) { + ret = -ENODEV; + goto out; + } + + plr->cpu = cpu; + + if (sel == 1) + thread = kthread_create_on_node(measure_cycles_lat_fn, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else if (sel == 2) + thread = kthread_create_on_node(measure_l2_residency, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else if (sel == 3) + thread = kthread_create_on_node(measure_l3_residency, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else + goto out; + + if (IS_ERR(thread)) { + ret = PTR_ERR(thread); + goto out; + } + kthread_bind(thread, cpu); + wake_up_process(thread); + + ret = wait_event_interruptible(plr->lock_thread_wq, + plr->thread_done == 1); + if (ret < 0) + goto out; + + ret = 0; + +out: + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + return ret; +} + +static ssize_t pseudo_lock_measure_trigger(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct rdtgroup *rdtgrp = file->private_data; + size_t buf_size; + char buf[32]; + int ret; + int sel; + + buf_size = min(count, (sizeof(buf) - 1)); + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + ret = kstrtoint(buf, 10, &sel); + if (ret == 0) { + if (sel != 1 && sel != 2 && sel != 3) + return -EINVAL; + ret = debugfs_file_get(file->f_path.dentry); + if (ret) + return ret; + ret = pseudo_lock_measure_cycles(rdtgrp, sel); + if (ret == 0) + ret = count; + debugfs_file_put(file->f_path.dentry); + } + + return ret; +} + +static const struct file_operations pseudo_measure_fops = { + .write = pseudo_lock_measure_trigger, + .open = simple_open, + .llseek = default_llseek, +}; + +/** + * rdtgroup_pseudo_lock_create - Create a pseudo-locked region + * @rdtgrp: resource group to which pseudo-lock region belongs + * + * Called when a resource group in the pseudo-locksetup mode receives a + * valid schemata that should be pseudo-locked. Since the resource group is + * in pseudo-locksetup mode the &struct pseudo_lock_region has already been + * allocated and initialized with the essential information. If a failure + * occurs the resource group remains in the pseudo-locksetup mode with the + * &struct pseudo_lock_region associated with it, but cleared from all + * information and ready for the user to re-attempt pseudo-locking by + * writing the schemata again. + * + * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0 + * on failure. Descriptive error will be written to last_cmd_status buffer. + */ +int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + struct task_struct *thread; + unsigned int new_minor; + struct device *dev; + int ret; + + ret = pseudo_lock_region_alloc(plr); + if (ret < 0) + return ret; + + ret = pseudo_lock_cstates_constrain(plr); + if (ret < 0) { + ret = -EINVAL; + goto out_region; + } + + plr->thread_done = 0; + + thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp, + cpu_to_node(plr->cpu), + "pseudo_lock/%u", plr->cpu); + if (IS_ERR(thread)) { + ret = PTR_ERR(thread); + rdt_last_cmd_printf("locking thread returned error %d\n", ret); + goto out_cstates; + } + + kthread_bind(thread, plr->cpu); + wake_up_process(thread); + + ret = wait_event_interruptible(plr->lock_thread_wq, + plr->thread_done == 1); + if (ret < 0) { + /* + * If the thread does not get on the CPU for whatever + * reason and the process which sets up the region is + * interrupted then this will leave the thread in runnable + * state and once it gets on the CPU it will derefence + * the cleared, but not freed, plr struct resulting in an + * empty pseudo-locking loop. + */ + rdt_last_cmd_puts("locking thread interrupted\n"); + goto out_cstates; + } + + ret = pseudo_lock_minor_get(&new_minor); + if (ret < 0) { + rdt_last_cmd_puts("unable to obtain a new minor number\n"); + goto out_cstates; + } + + /* + * Unlock access but do not release the reference. The + * pseudo-locked region will still be here on return. + * + * The mutex has to be released temporarily to avoid a potential + * deadlock with the mm->mmap_sem semaphore which is obtained in + * the device_create() and debugfs_create_dir() callpath below + * as well as before the mmap() callback is called. + */ + mutex_unlock(&rdtgroup_mutex); + + if (!IS_ERR_OR_NULL(debugfs_resctrl)) { + plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name, + debugfs_resctrl); + if (!IS_ERR_OR_NULL(plr->debugfs_dir)) + debugfs_create_file("pseudo_lock_measure", 0200, + plr->debugfs_dir, rdtgrp, + &pseudo_measure_fops); + } + + dev = device_create(pseudo_lock_class, NULL, + MKDEV(pseudo_lock_major, new_minor), + rdtgrp, "%s", rdtgrp->kn->name); + + mutex_lock(&rdtgroup_mutex); + + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + rdt_last_cmd_printf("failed to create character device: %d\n", + ret); + goto out_debugfs; + } + + /* We released the mutex - check if group was removed while we did so */ + if (rdtgrp->flags & RDT_DELETED) { + ret = -ENODEV; + goto out_device; + } + + plr->minor = new_minor; + + rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED; + closid_free(rdtgrp->closid); + rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444); + rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444); + + ret = 0; + goto out; + +out_device: + device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor)); +out_debugfs: + debugfs_remove_recursive(plr->debugfs_dir); + pseudo_lock_minor_release(new_minor); +out_cstates: + pseudo_lock_cstates_relax(plr); +out_region: + pseudo_lock_region_clear(plr); +out: + return ret; +} + +/** + * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region + * @rdtgrp: resource group to which the pseudo-locked region belongs + * + * The removal of a pseudo-locked region can be initiated when the resource + * group is removed from user space via a "rmdir" from userspace or the + * unmount of the resctrl filesystem. On removal the resource group does + * not go back to pseudo-locksetup mode before it is removed, instead it is + * removed directly. There is thus assymmetry with the creation where the + * &struct pseudo_lock_region is removed here while it was not created in + * rdtgroup_pseudo_lock_create(). + * + * Return: void + */ +void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * Default group cannot be a pseudo-locked region so we can + * free closid here. + */ + closid_free(rdtgrp->closid); + goto free; + } + + pseudo_lock_cstates_relax(plr); + debugfs_remove_recursive(rdtgrp->plr->debugfs_dir); + device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor)); + pseudo_lock_minor_release(plr->minor); + +free: + pseudo_lock_free(rdtgrp); +} + +static int pseudo_lock_dev_open(struct inode *inode, struct file *filp) +{ + struct rdtgroup *rdtgrp; + + mutex_lock(&rdtgroup_mutex); + + rdtgrp = region_find_by_minor(iminor(inode)); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + + filp->private_data = rdtgrp; + atomic_inc(&rdtgrp->waitcount); + /* Perform a non-seekable open - llseek is not supported */ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); + + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +static int pseudo_lock_dev_release(struct inode *inode, struct file *filp) +{ + struct rdtgroup *rdtgrp; + + mutex_lock(&rdtgroup_mutex); + rdtgrp = filp->private_data; + WARN_ON(!rdtgrp); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + filp->private_data = NULL; + atomic_dec(&rdtgrp->waitcount); + mutex_unlock(&rdtgroup_mutex); + return 0; +} + +static int pseudo_lock_dev_mremap(struct vm_area_struct *area) +{ + /* Not supported */ + return -EINVAL; +} + +static const struct vm_operations_struct pseudo_mmap_ops = { + .mremap = pseudo_lock_dev_mremap, +}; + +static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) +{ + unsigned long vsize = vma->vm_end - vma->vm_start; + unsigned long off = vma->vm_pgoff << PAGE_SHIFT; + struct pseudo_lock_region *plr; + struct rdtgroup *rdtgrp; + unsigned long physical; + unsigned long psize; + + mutex_lock(&rdtgroup_mutex); + + rdtgrp = filp->private_data; + WARN_ON(!rdtgrp); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + + plr = rdtgrp->plr; + + if (!plr->d) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + + /* + * Task is required to run with affinity to the cpus associated + * with the pseudo-locked region. If this is not the case the task + * may be scheduled elsewhere and invalidate entries in the + * pseudo-locked region. + */ + if (!cpumask_subset(¤t->cpus_allowed, &plr->d->cpu_mask)) { + mutex_unlock(&rdtgroup_mutex); + return -EINVAL; + } + + physical = __pa(plr->kmem) >> PAGE_SHIFT; + psize = plr->size - off; + + if (off > plr->size) { + mutex_unlock(&rdtgroup_mutex); + return -ENOSPC; + } + + /* + * Ensure changes are carried directly to the memory being mapped, + * do not allow copy-on-write mapping. + */ + if (!(vma->vm_flags & VM_SHARED)) { + mutex_unlock(&rdtgroup_mutex); + return -EINVAL; + } + + if (vsize > psize) { + mutex_unlock(&rdtgroup_mutex); + return -ENOSPC; + } + + memset(plr->kmem + off, 0, vsize); + + if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff, + vsize, vma->vm_page_prot)) { + mutex_unlock(&rdtgroup_mutex); + return -EAGAIN; + } + vma->vm_ops = &pseudo_mmap_ops; + mutex_unlock(&rdtgroup_mutex); + return 0; +} + +static const struct file_operations pseudo_lock_dev_fops = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = NULL, + .write = NULL, + .open = pseudo_lock_dev_open, + .release = pseudo_lock_dev_release, + .mmap = pseudo_lock_dev_mmap, +}; + +static char *pseudo_lock_devnode(struct device *dev, umode_t *mode) +{ + struct rdtgroup *rdtgrp; + + rdtgrp = dev_get_drvdata(dev); + if (mode) + *mode = 0600; + return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name); +} + +int rdt_pseudo_lock_init(void) +{ + int ret; + + ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops); + if (ret < 0) + return ret; + + pseudo_lock_major = ret; + + pseudo_lock_class = class_create(THIS_MODULE, "pseudo_lock"); + if (IS_ERR(pseudo_lock_class)) { + ret = PTR_ERR(pseudo_lock_class); + unregister_chrdev(pseudo_lock_major, "pseudo_lock"); + return ret; + } + + pseudo_lock_class->devnode = pseudo_lock_devnode; + return 0; +} + +void rdt_pseudo_lock_release(void) +{ + class_destroy(pseudo_lock_class); + pseudo_lock_class = NULL; + unregister_chrdev(pseudo_lock_major, "pseudo_lock"); + pseudo_lock_major = 0; +} diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h new file mode 100644 index 000000000000..2c041e6d9f05 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM resctrl + +#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PSEUDO_LOCK_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(pseudo_lock_mem_latency, + TP_PROTO(u32 latency), + TP_ARGS(latency), + TP_STRUCT__entry(__field(u32, latency)), + TP_fast_assign(__entry->latency = latency), + TP_printk("latency=%u", __entry->latency) + ); + +TRACE_EVENT(pseudo_lock_l2, + TP_PROTO(u64 l2_hits, u64 l2_miss), + TP_ARGS(l2_hits, l2_miss), + TP_STRUCT__entry(__field(u64, l2_hits) + __field(u64, l2_miss)), + TP_fast_assign(__entry->l2_hits = l2_hits; + __entry->l2_miss = l2_miss;), + TP_printk("hits=%llu miss=%llu", + __entry->l2_hits, __entry->l2_miss)); + +TRACE_EVENT(pseudo_lock_l3, + TP_PROTO(u64 l3_hits, u64 l3_miss), + TP_ARGS(l3_hits, l3_miss), + TP_STRUCT__entry(__field(u64, l3_hits) + __field(u64, l3_miss)), + TP_fast_assign(__entry->l3_hits = l3_hits; + __entry->l3_miss = l3_miss;), + TP_printk("hits=%llu miss=%llu", + __entry->l3_hits, __entry->l3_miss)); + +#endif /* _TRACE_PSEUDO_LOCK_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE intel_rdt_pseudo_lock_event +#include <trace/define_trace.h> diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index fca759d272a1..f27b8115ffa2 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -20,7 +20,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/cacheinfo.h> #include <linux/cpu.h> +#include <linux/debugfs.h> #include <linux/fs.h> #include <linux/sysfs.h> #include <linux/kernfs.h> @@ -55,6 +57,8 @@ static struct kernfs_node *kn_mondata; static struct seq_buf last_cmd_status; static char last_cmd_status_buf[512]; +struct dentry *debugfs_resctrl; + void rdt_last_cmd_clear(void) { lockdep_assert_held(&rdtgroup_mutex); @@ -93,6 +97,12 @@ void rdt_last_cmd_printf(const char *fmt, ...) * limited as the number of resources grows. */ static int closid_free_map; +static int closid_free_map_len; + +int closids_supported(void) +{ + return closid_free_map_len; +} static void closid_init(void) { @@ -107,6 +117,7 @@ static void closid_init(void) /* CLOSID 0 is always reserved for the default group */ closid_free_map &= ~1; + closid_free_map_len = rdt_min_closid; } static int closid_alloc(void) @@ -121,11 +132,65 @@ static int closid_alloc(void) return closid; } -static void closid_free(int closid) +void closid_free(int closid) { closid_free_map |= 1 << closid; } +/** + * closid_allocated - test if provided closid is in use + * @closid: closid to be tested + * + * Return: true if @closid is currently associated with a resource group, + * false if @closid is free + */ +static bool closid_allocated(unsigned int closid) +{ + return (closid_free_map & (1 << closid)) == 0; +} + +/** + * rdtgroup_mode_by_closid - Return mode of resource group with closid + * @closid: closid if the resource group + * + * Each resource group is associated with a @closid. Here the mode + * of a resource group can be queried by searching for it using its closid. + * + * Return: mode as &enum rdtgrp_mode of resource group with closid @closid + */ +enum rdtgrp_mode rdtgroup_mode_by_closid(int closid) +{ + struct rdtgroup *rdtgrp; + + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (rdtgrp->closid == closid) + return rdtgrp->mode; + } + + return RDT_NUM_MODES; +} + +static const char * const rdt_mode_str[] = { + [RDT_MODE_SHAREABLE] = "shareable", + [RDT_MODE_EXCLUSIVE] = "exclusive", + [RDT_MODE_PSEUDO_LOCKSETUP] = "pseudo-locksetup", + [RDT_MODE_PSEUDO_LOCKED] = "pseudo-locked", +}; + +/** + * rdtgroup_mode_str - Return the string representation of mode + * @mode: the resource group mode as &enum rdtgroup_mode + * + * Return: string representation of valid mode, "unknown" otherwise + */ +static const char *rdtgroup_mode_str(enum rdtgrp_mode mode) +{ + if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES) + return "unknown"; + + return rdt_mode_str[mode]; +} + /* set uid and gid of rdtgroup dirs and files to that of the creator */ static int rdtgroup_kn_set_ugid(struct kernfs_node *kn) { @@ -146,6 +211,7 @@ static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft) int ret; kn = __kernfs_create_file(parent_kn, rft->name, rft->mode, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0, rft->kf_ops, rft, NULL, NULL); if (IS_ERR(kn)) return PTR_ERR(kn); @@ -202,13 +268,27 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { struct rdtgroup *rdtgrp; + struct cpumask *mask; int ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { - seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", - cpumask_pr_args(&rdtgrp->cpu_mask)); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + mask = &rdtgrp->plr->d->cpu_mask; + seq_printf(s, is_cpu_list(of) ? + "%*pbl\n" : "%*pb\n", + cpumask_pr_args(mask)); + } + } else { + seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", + cpumask_pr_args(&rdtgrp->cpu_mask)); + } } else { ret = -ENOENT; } @@ -394,6 +474,13 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, goto unlock; } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = -EINVAL; + rdt_last_cmd_puts("pseudo-locking in progress\n"); + goto unlock; + } + if (is_cpu_list(of)) ret = cpulist_parse(buf, newmask); else @@ -509,6 +596,32 @@ static int __rdtgroup_move_task(struct task_struct *tsk, return ret; } +/** + * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group + * @r: Resource group + * + * Return: 1 if tasks have been assigned to @r, 0 otherwise + */ +int rdtgroup_tasks_assigned(struct rdtgroup *r) +{ + struct task_struct *p, *t; + int ret = 0; + + lockdep_assert_held(&rdtgroup_mutex); + + rcu_read_lock(); + for_each_process_thread(p, t) { + if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) || + (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) { + ret = 1; + break; + } + } + rcu_read_unlock(); + + return ret; +} + static int rdtgroup_task_write_permission(struct task_struct *task, struct kernfs_open_file *of) { @@ -570,13 +683,22 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return -EINVAL; rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } rdt_last_cmd_clear(); - if (rdtgrp) - ret = rdtgroup_move_task(pid, rdtgrp, of); - else - ret = -ENOENT; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = -EINVAL; + rdt_last_cmd_puts("pseudo-locking in progress\n"); + goto unlock; + } + ret = rdtgroup_move_task(pid, rdtgrp, of); + +unlock: rdtgroup_kn_unlock(of->kn); return ret ?: nbytes; @@ -662,6 +784,94 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of, return 0; } +/** + * rdt_bit_usage_show - Display current usage of resources + * + * A domain is a shared resource that can now be allocated differently. Here + * we display the current regions of the domain as an annotated bitmask. + * For each domain of this resource its allocation bitmask + * is annotated as below to indicate the current usage of the corresponding bit: + * 0 - currently unused + * X - currently available for sharing and used by software and hardware + * H - currently used by hardware only but available for software use + * S - currently used and shareable by software only + * E - currently used exclusively by one resource group + * P - currently pseudo-locked by one resource group + */ +static int rdt_bit_usage_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + u32 sw_shareable = 0, hw_shareable = 0; + u32 exclusive = 0, pseudo_locked = 0; + struct rdt_domain *dom; + int i, hwb, swb, excl, psl; + enum rdtgrp_mode mode; + bool sep = false; + u32 *ctrl; + + mutex_lock(&rdtgroup_mutex); + hw_shareable = r->cache.shareable_bits; + list_for_each_entry(dom, &r->domains, list) { + if (sep) + seq_putc(seq, ';'); + ctrl = dom->ctrl_val; + sw_shareable = 0; + exclusive = 0; + seq_printf(seq, "%d=", dom->id); + for (i = 0; i < closids_supported(); i++, ctrl++) { + if (!closid_allocated(i)) + continue; + mode = rdtgroup_mode_by_closid(i); + switch (mode) { + case RDT_MODE_SHAREABLE: + sw_shareable |= *ctrl; + break; + case RDT_MODE_EXCLUSIVE: + exclusive |= *ctrl; + break; + case RDT_MODE_PSEUDO_LOCKSETUP: + /* + * RDT_MODE_PSEUDO_LOCKSETUP is possible + * here but not included since the CBM + * associated with this CLOSID in this mode + * is not initialized and no task or cpu can be + * assigned this CLOSID. + */ + break; + case RDT_MODE_PSEUDO_LOCKED: + case RDT_NUM_MODES: + WARN(1, + "invalid mode for closid %d\n", i); + break; + } + } + for (i = r->cache.cbm_len - 1; i >= 0; i--) { + pseudo_locked = dom->plr ? dom->plr->cbm : 0; + hwb = test_bit(i, (unsigned long *)&hw_shareable); + swb = test_bit(i, (unsigned long *)&sw_shareable); + excl = test_bit(i, (unsigned long *)&exclusive); + psl = test_bit(i, (unsigned long *)&pseudo_locked); + if (hwb && swb) + seq_putc(seq, 'X'); + else if (hwb && !swb) + seq_putc(seq, 'H'); + else if (!hwb && swb) + seq_putc(seq, 'S'); + else if (excl) + seq_putc(seq, 'E'); + else if (psl) + seq_putc(seq, 'P'); + else /* Unused bits remain */ + seq_putc(seq, '0'); + } + sep = true; + } + seq_putc(seq, '\n'); + mutex_unlock(&rdtgroup_mutex); + return 0; +} + static int rdt_min_bw_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -740,6 +950,403 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, return nbytes; } +/* + * rdtgroup_mode_show - Display mode of this resource group + */ +static int rdtgroup_mode_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode)); + + rdtgroup_kn_unlock(of->kn); + return 0; +} + +/** + * rdt_cdp_peer_get - Retrieve CDP peer if it exists + * @r: RDT resource to which RDT domain @d belongs + * @d: Cache instance for which a CDP peer is requested + * @r_cdp: RDT resource that shares hardware with @r (RDT resource peer) + * Used to return the result. + * @d_cdp: RDT domain that shares hardware with @d (RDT domain peer) + * Used to return the result. + * + * RDT resources are managed independently and by extension the RDT domains + * (RDT resource instances) are managed independently also. The Code and + * Data Prioritization (CDP) RDT resources, while managed independently, + * could refer to the same underlying hardware. For example, + * RDT_RESOURCE_L2CODE and RDT_RESOURCE_L2DATA both refer to the L2 cache. + * + * When provided with an RDT resource @r and an instance of that RDT + * resource @d rdt_cdp_peer_get() will return if there is a peer RDT + * resource and the exact instance that shares the same hardware. + * + * Return: 0 if a CDP peer was found, <0 on error or if no CDP peer exists. + * If a CDP peer was found, @r_cdp will point to the peer RDT resource + * and @d_cdp will point to the peer RDT domain. + */ +static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, + struct rdt_resource **r_cdp, + struct rdt_domain **d_cdp) +{ + struct rdt_resource *_r_cdp = NULL; + struct rdt_domain *_d_cdp = NULL; + int ret = 0; + + switch (r->rid) { + case RDT_RESOURCE_L3DATA: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3CODE]; + break; + case RDT_RESOURCE_L3CODE: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3DATA]; + break; + case RDT_RESOURCE_L2DATA: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2CODE]; + break; + case RDT_RESOURCE_L2CODE: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2DATA]; + break; + default: + ret = -ENOENT; + goto out; + } + + /* + * When a new CPU comes online and CDP is enabled then the new + * RDT domains (if any) associated with both CDP RDT resources + * are added in the same CPU online routine while the + * rdtgroup_mutex is held. It should thus not happen for one + * RDT domain to exist and be associated with its RDT CDP + * resource but there is no RDT domain associated with the + * peer RDT CDP resource. Hence the WARN. + */ + _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); + if (WARN_ON(!_d_cdp)) { + _r_cdp = NULL; + ret = -EINVAL; + } + +out: + *r_cdp = _r_cdp; + *d_cdp = _d_cdp; + + return ret; +} + +/** + * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other + * @r: Resource to which domain instance @d belongs. + * @d: The domain instance for which @closid is being tested. + * @cbm: Capacity bitmask being tested. + * @closid: Intended closid for @cbm. + * @exclusive: Only check if overlaps with exclusive resource groups + * + * Checks if provided @cbm intended to be used for @closid on domain + * @d overlaps with any other closids or other hardware usage associated + * with this domain. If @exclusive is true then only overlaps with + * resource groups in exclusive mode will be considered. If @exclusive + * is false then overlaps with any resource group or hardware entities + * will be considered. + * + * @cbm is unsigned long, even if only 32 bits are used, to make the + * bitmap functions work correctly. + * + * Return: false if CBM does not overlap, true if it does. + */ +static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + unsigned long cbm, int closid, bool exclusive) +{ + enum rdtgrp_mode mode; + unsigned long ctrl_b; + u32 *ctrl; + int i; + + /* Check for any overlap with regions used by hardware directly */ + if (!exclusive) { + ctrl_b = r->cache.shareable_bits; + if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) + return true; + } + + /* Check for overlap with other resource groups */ + ctrl = d->ctrl_val; + for (i = 0; i < closids_supported(); i++, ctrl++) { + ctrl_b = *ctrl; + mode = rdtgroup_mode_by_closid(i); + if (closid_allocated(i) && i != closid && + mode != RDT_MODE_PSEUDO_LOCKSETUP) { + if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) { + if (exclusive) { + if (mode == RDT_MODE_EXCLUSIVE) + return true; + continue; + } + return true; + } + } + } + + return false; +} + +/** + * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware + * @r: Resource to which domain instance @d belongs. + * @d: The domain instance for which @closid is being tested. + * @cbm: Capacity bitmask being tested. + * @closid: Intended closid for @cbm. + * @exclusive: Only check if overlaps with exclusive resource groups + * + * Resources that can be allocated using a CBM can use the CBM to control + * the overlap of these allocations. rdtgroup_cmb_overlaps() is the test + * for overlap. Overlap test is not limited to the specific resource for + * which the CBM is intended though - when dealing with CDP resources that + * share the underlying hardware the overlap check should be performed on + * the CDP resource sharing the hardware also. + * + * Refer to description of __rdtgroup_cbm_overlaps() for the details of the + * overlap test. + * + * Return: true if CBM overlap detected, false if there is no overlap + */ +bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + unsigned long cbm, int closid, bool exclusive) +{ + struct rdt_resource *r_cdp; + struct rdt_domain *d_cdp; + + if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, exclusive)) + return true; + + if (rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp) < 0) + return false; + + return __rdtgroup_cbm_overlaps(r_cdp, d_cdp, cbm, closid, exclusive); +} + +/** + * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive + * + * An exclusive resource group implies that there should be no sharing of + * its allocated resources. At the time this group is considered to be + * exclusive this test can determine if its current schemata supports this + * setting by testing for overlap with all other resource groups. + * + * Return: true if resource group can be exclusive, false if there is overlap + * with allocations of other resource groups and thus this resource group + * cannot be exclusive. + */ +static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) +{ + int closid = rdtgrp->closid; + struct rdt_resource *r; + bool has_cache = false; + struct rdt_domain *d; + + for_each_alloc_enabled_rdt_resource(r) { + if (r->rid == RDT_RESOURCE_MBA) + continue; + has_cache = true; + list_for_each_entry(d, &r->domains, list) { + if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid], + rdtgrp->closid, false)) { + rdt_last_cmd_puts("schemata overlaps\n"); + return false; + } + } + } + + if (!has_cache) { + rdt_last_cmd_puts("cannot be exclusive without CAT/CDP\n"); + return false; + } + + return true; +} + +/** + * rdtgroup_mode_write - Modify the resource group's mode + * + */ +static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + enum rdtgrp_mode mode; + int ret = 0; + + /* 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; + } + + rdt_last_cmd_clear(); + + mode = rdtgrp->mode; + + if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) || + (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) || + (!strcmp(buf, "pseudo-locksetup") && + mode == RDT_MODE_PSEUDO_LOCKSETUP) || + (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED)) + goto out; + + if (mode == RDT_MODE_PSEUDO_LOCKED) { + rdt_last_cmd_printf("cannot change pseudo-locked group\n"); + ret = -EINVAL; + goto out; + } + + if (!strcmp(buf, "shareable")) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = rdtgroup_locksetup_exit(rdtgrp); + if (ret) + goto out; + } + rdtgrp->mode = RDT_MODE_SHAREABLE; + } else if (!strcmp(buf, "exclusive")) { + if (!rdtgroup_mode_test_exclusive(rdtgrp)) { + ret = -EINVAL; + goto out; + } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = rdtgroup_locksetup_exit(rdtgrp); + if (ret) + goto out; + } + rdtgrp->mode = RDT_MODE_EXCLUSIVE; + } else if (!strcmp(buf, "pseudo-locksetup")) { + ret = rdtgroup_locksetup_enter(rdtgrp); + if (ret) + goto out; + rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP; + } else { + rdt_last_cmd_printf("unknown/unsupported mode\n"); + ret = -EINVAL; + } + +out: + rdtgroup_kn_unlock(of->kn); + return ret ?: nbytes; +} + +/** + * rdtgroup_cbm_to_size - Translate CBM to size in bytes + * @r: RDT resource to which @d belongs. + * @d: RDT domain instance. + * @cbm: bitmask for which the size should be computed. + * + * The bitmask provided associated with the RDT domain instance @d will be + * translated into how many bytes it represents. The size in bytes is + * computed by first dividing the total cache size by the CBM length to + * determine how many bytes each bit in the bitmask represents. The result + * is multiplied with the number of bits set in the bitmask. + * + * @cbm is unsigned long, even if only 32 bits are used to make the + * bitmap functions work correctly. + */ +unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, + struct rdt_domain *d, unsigned long cbm) +{ + struct cpu_cacheinfo *ci; + unsigned int size = 0; + int num_b, i; + + num_b = bitmap_weight(&cbm, r->cache.cbm_len); + ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask)); + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == r->cache_level) { + size = ci->info_list[i].size / r->cache.cbm_len * num_b; + break; + } + } + + return size; +} + +/** + * rdtgroup_size_show - Display size in bytes of allocated regions + * + * The "size" file mirrors the layout of the "schemata" file, printing the + * size in bytes of each region instead of the capacity bitmask. + * + */ +static int rdtgroup_size_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + struct rdt_domain *d; + unsigned int size; + int ret = 0; + bool sep; + u32 ctrl; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + seq_printf(s, "%*s:", max_name_width, + rdtgrp->plr->r->name); + size = rdtgroup_cbm_to_size(rdtgrp->plr->r, + rdtgrp->plr->d, + rdtgrp->plr->cbm); + seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); + } + goto out; + } + + for_each_alloc_enabled_rdt_resource(r) { + sep = false; + seq_printf(s, "%*s:", max_name_width, r->name); + list_for_each_entry(d, &r->domains, list) { + if (sep) + seq_putc(s, ';'); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + size = 0; + } else { + ctrl = (!is_mba_sc(r) ? + d->ctrl_val[rdtgrp->closid] : + d->mbps_val[rdtgrp->closid]); + if (r->rid == RDT_RESOURCE_MBA) + size = ctrl; + else + size = rdtgroup_cbm_to_size(r, d, ctrl); + } + seq_printf(s, "%d=%u", d->id, size); + sep = true; + } + seq_putc(s, '\n'); + } + +out: + rdtgroup_kn_unlock(of->kn); + + return ret; +} + /* rdtgroup information files for one cache resource. */ static struct rftype res_common_files[] = { { @@ -792,6 +1399,13 @@ static struct rftype res_common_files[] = { .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, { + .name = "bit_usage", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_bit_usage_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { .name = "min_bandwidth", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, @@ -853,6 +1467,22 @@ static struct rftype res_common_files[] = { .seq_show = rdtgroup_schemata_show, .fflags = RF_CTRL_BASE, }, + { + .name = "mode", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_mode_write, + .seq_show = rdtgroup_mode_show, + .fflags = RF_CTRL_BASE, + }, + { + .name = "size", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdtgroup_size_show, + .fflags = RF_CTRL_BASE, + }, + }; static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags) @@ -883,6 +1513,103 @@ error: return ret; } +/** + * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file + * @r: The resource group with which the file is associated. + * @name: Name of the file + * + * The permissions of named resctrl file, directory, or link are modified + * to not allow read, write, or execute by any user. + * + * WARNING: This function is intended to communicate to the user that the + * resctrl file has been locked down - that it is not relevant to the + * particular state the system finds itself in. It should not be relied + * on to protect from user access because after the file's permissions + * are restricted the user can still change the permissions using chmod + * from the command line. + * + * Return: 0 on success, <0 on failure. + */ +int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name) +{ + struct iattr iattr = {.ia_valid = ATTR_MODE,}; + struct kernfs_node *kn; + int ret = 0; + + kn = kernfs_find_and_get_ns(r->kn, name, NULL); + if (!kn) + return -ENOENT; + + switch (kernfs_type(kn)) { + case KERNFS_DIR: + iattr.ia_mode = S_IFDIR; + break; + case KERNFS_FILE: + iattr.ia_mode = S_IFREG; + break; + case KERNFS_LINK: + iattr.ia_mode = S_IFLNK; + break; + } + + ret = kernfs_setattr(kn, &iattr); + kernfs_put(kn); + return ret; +} + +/** + * rdtgroup_kn_mode_restore - Restore user access to named resctrl file + * @r: The resource group with which the file is associated. + * @name: Name of the file + * @mask: Mask of permissions that should be restored + * + * Restore the permissions of the named file. If @name is a directory the + * permissions of its parent will be used. + * + * Return: 0 on success, <0 on failure. + */ +int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, + umode_t mask) +{ + struct iattr iattr = {.ia_valid = ATTR_MODE,}; + struct kernfs_node *kn, *parent; + struct rftype *rfts, *rft; + int ret, len; + + rfts = res_common_files; + len = ARRAY_SIZE(res_common_files); + + for (rft = rfts; rft < rfts + len; rft++) { + if (!strcmp(rft->name, name)) + iattr.ia_mode = rft->mode & mask; + } + + kn = kernfs_find_and_get_ns(r->kn, name, NULL); + if (!kn) + return -ENOENT; + + switch (kernfs_type(kn)) { + case KERNFS_DIR: + parent = kernfs_get_parent(kn); + if (parent) { + iattr.ia_mode |= parent->mode; + kernfs_put(parent); + } + iattr.ia_mode |= S_IFDIR; + break; + case KERNFS_FILE: + iattr.ia_mode |= S_IFREG; + break; + case KERNFS_LINK: + iattr.ia_mode |= S_IFLNK; + break; + } + + ret = kernfs_setattr(kn, &iattr); + kernfs_put(kn); + return ret; +} + static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, unsigned long fflags) { @@ -1005,6 +1732,11 @@ static void l2_qos_cfg_update(void *arg) wrmsrl(IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL); } +static inline bool is_mba_linear(void) +{ + return rdt_resources_all[RDT_RESOURCE_MBA].membw.delay_linear; +} + static int set_cache_qos_cfg(int level, bool enable) { void (*update)(void *arg); @@ -1041,6 +1773,28 @@ static int set_cache_qos_cfg(int level, bool enable) return 0; } +/* + * Enable or disable the MBA software controller + * which helps user specify bandwidth in MBps. + * MBA software controller is supported only if + * MBM is supported and MBA is in linear scale. + */ +static int set_mba_sc(bool mba_sc) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA]; + struct rdt_domain *d; + + if (!is_mbm_enabled() || !is_mba_linear() || + mba_sc == is_mba_sc(r)) + return -EINVAL; + + r->membw.mba_sc = mba_sc; + list_for_each_entry(d, &r->domains, list) + setup_default_ctrlval(r, d->ctrl_val, d->mbps_val); + + return 0; +} + static int cdp_enable(int level, int data_type, int code_type) { struct rdt_resource *r_ldata = &rdt_resources_all[data_type]; @@ -1123,6 +1877,10 @@ static int parse_rdtgroupfs_options(char *data) ret = cdpl2_enable(); if (ret) goto out; + } else if (!strcmp(token, "mba_MBps")) { + ret = set_mba_sc(true); + if (ret) + goto out; } else { ret = -EINVAL; goto out; @@ -1193,6 +1951,9 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) if (atomic_dec_and_test(&rdtgrp->waitcount) && (rdtgrp->flags & RDT_DELETED)) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + rdtgroup_pseudo_lock_remove(rdtgrp); kernfs_unbreak_active_protection(kn); kernfs_put(rdtgrp->kn); kfree(rdtgrp); @@ -1258,10 +2019,16 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, rdtgroup_default.mon.mon_data_kn = kn_mondata; } + ret = rdt_pseudo_lock_init(); + if (ret) { + dentry = ERR_PTR(ret); + goto out_mondata; + } + dentry = kernfs_mount(fs_type, flags, rdt_root, RDTGROUP_SUPER_MAGIC, NULL); if (IS_ERR(dentry)) - goto out_mondata; + goto out_psl; if (rdt_alloc_capable) static_branch_enable_cpuslocked(&rdt_alloc_enable_key); @@ -1279,6 +2046,8 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, goto out; +out_psl: + rdt_pseudo_lock_release(); out_mondata: if (rdt_mon_capable) kernfs_remove(kn_mondata); @@ -1416,6 +2185,10 @@ static void rmdir_all_sub(void) if (rdtgrp == &rdtgroup_default) continue; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + rdtgroup_pseudo_lock_remove(rdtgrp); + /* * Give any CPUs back to the default group. We cannot copy * cpu_online_mask because a CPU might have executed the @@ -1445,11 +2218,15 @@ static void rdt_kill_sb(struct super_block *sb) cpus_read_lock(); mutex_lock(&rdtgroup_mutex); + set_mba_sc(false); + /*Put everything back to default values. */ for_each_alloc_enabled_rdt_resource(r) reset_all_ctrls(r); cdp_disable_all(); rmdir_all_sub(); + rdt_pseudo_lock_release(); + rdtgroup_default.mode = RDT_MODE_SHAREABLE; static_branch_disable_cpuslocked(&rdt_alloc_enable_key); static_branch_disable_cpuslocked(&rdt_mon_enable_key); static_branch_disable_cpuslocked(&rdt_enable_key); @@ -1470,7 +2247,8 @@ static int mon_addfile(struct kernfs_node *parent_kn, const char *name, struct kernfs_node *kn; int ret = 0; - kn = __kernfs_create_file(parent_kn, name, 0444, 0, + kn = __kernfs_create_file(parent_kn, name, 0444, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0, &kf_mondata_ops, priv, NULL, NULL); if (IS_ERR(kn)) return PTR_ERR(kn); @@ -1649,6 +2427,145 @@ out_destroy: return ret; } +/** + * cbm_ensure_valid - Enforce validity on provided CBM + * @_val: Candidate CBM + * @r: RDT resource to which the CBM belongs + * + * The provided CBM represents all cache portions available for use. This + * may be represented by a bitmap that does not consist of contiguous ones + * and thus be an invalid CBM. + * Here the provided CBM is forced to be a valid CBM by only considering + * the first set of contiguous bits as valid and clearing all bits. + * The intention here is to provide a valid default CBM with which a new + * resource group is initialized. The user can follow this with a + * modification to the CBM if the default does not satisfy the + * requirements. + */ +static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r) +{ + /* + * Convert the u32 _val to an unsigned long required by all the bit + * operations within this function. No more than 32 bits of this + * converted value can be accessed because all bit operations are + * additionally provided with cbm_len that is initialized during + * hardware enumeration using five bits from the EAX register and + * thus never can exceed 32 bits. + */ + unsigned long *val = (unsigned long *)_val; + unsigned int cbm_len = r->cache.cbm_len; + unsigned long first_bit, zero_bit; + + if (*val == 0) + return; + + first_bit = find_first_bit(val, cbm_len); + zero_bit = find_next_zero_bit(val, cbm_len, first_bit); + + /* Clear any remaining bits to ensure contiguous region */ + bitmap_clear(val, zero_bit, cbm_len - zero_bit); +} + +/** + * rdtgroup_init_alloc - Initialize the new RDT group's allocations + * + * A new RDT group is being created on an allocation capable (CAT) + * supporting system. Set this group up to start off with all usable + * allocations. That is, all shareable and unused bits. + * + * All-zero CBM is invalid. If there are no more shareable bits available + * on any domain then the entire allocation will fail. + */ +static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) +{ + struct rdt_resource *r_cdp = NULL; + struct rdt_domain *d_cdp = NULL; + u32 used_b = 0, unused_b = 0; + u32 closid = rdtgrp->closid; + struct rdt_resource *r; + unsigned long tmp_cbm; + enum rdtgrp_mode mode; + struct rdt_domain *d; + u32 peer_ctl, *ctrl; + int i, ret; + + for_each_alloc_enabled_rdt_resource(r) { + /* + * Only initialize default allocations for CBM cache + * resources + */ + if (r->rid == RDT_RESOURCE_MBA) + continue; + list_for_each_entry(d, &r->domains, list) { + rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp); + d->have_new_ctrl = false; + d->new_ctrl = r->cache.shareable_bits; + used_b = r->cache.shareable_bits; + ctrl = d->ctrl_val; + for (i = 0; i < closids_supported(); i++, ctrl++) { + if (closid_allocated(i) && i != closid) { + mode = rdtgroup_mode_by_closid(i); + if (mode == RDT_MODE_PSEUDO_LOCKSETUP) + break; + /* + * If CDP is active include peer + * domain's usage to ensure there + * is no overlap with an exclusive + * group. + */ + if (d_cdp) + peer_ctl = d_cdp->ctrl_val[i]; + else + peer_ctl = 0; + used_b |= *ctrl | peer_ctl; + if (mode == RDT_MODE_SHAREABLE) + d->new_ctrl |= *ctrl | peer_ctl; + } + } + if (d->plr && d->plr->cbm > 0) + used_b |= d->plr->cbm; + unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1); + unused_b &= BIT_MASK(r->cache.cbm_len) - 1; + d->new_ctrl |= unused_b; + /* + * Force the initial CBM to be valid, user can + * modify the CBM based on system availability. + */ + cbm_ensure_valid(&d->new_ctrl, r); + /* + * Assign the u32 CBM to an unsigned long to ensure + * that bitmap_weight() does not access out-of-bound + * memory. + */ + tmp_cbm = d->new_ctrl; + if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < + r->cache.min_cbm_bits) { + rdt_last_cmd_printf("no space on %s:%d\n", + r->name, d->id); + return -ENOSPC; + } + d->have_new_ctrl = true; + } + } + + for_each_alloc_enabled_rdt_resource(r) { + /* + * Only initialize default allocations for CBM cache + * resources + */ + if (r->rid == RDT_RESOURCE_MBA) + continue; + ret = update_domains(r, rdtgrp->closid); + if (ret < 0) { + rdt_last_cmd_puts("failed to initialize allocations\n"); + return ret; + } + rdtgrp->mode = RDT_MODE_SHAREABLE; + } + + return 0; +} + static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, struct kernfs_node *prgrp_kn, const char *name, umode_t mode, @@ -1667,6 +2584,14 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, goto out_unlock; } + if (rtype == RDTMON_GROUP && + (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) { + ret = -EINVAL; + rdt_last_cmd_puts("pseudo-locking in progress\n"); + goto out_unlock; + } + /* allocate the rdtgroup. */ rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL); if (!rdtgrp) { @@ -1807,6 +2732,10 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, ret = 0; rdtgrp->closid = closid; + ret = rdtgroup_init_alloc(rdtgrp); + if (ret < 0) + goto out_id_free; + list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); if (rdt_mon_capable) { @@ -1817,15 +2746,16 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL); if (ret) { rdt_last_cmd_puts("kernfs subdir error\n"); - goto out_id_free; + goto out_del_list; } } goto out_unlock; +out_del_list: + list_del(&rdtgrp->rdtgroup_list); out_id_free: closid_free(closid); - list_del(&rdtgrp->rdtgroup_list); out_common_fail: mkdir_rdt_prepare_clean(rdtgrp); out_unlock: @@ -1912,6 +2842,21 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, return 0; } +static int rdtgroup_ctrl_remove(struct kernfs_node *kn, + struct rdtgroup *rdtgrp) +{ + rdtgrp->flags = RDT_DELETED; + 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); + return 0; +} + static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) { @@ -1937,7 +2882,6 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); update_closid_rmid(tmpmask, NULL); - rdtgrp->flags = RDT_DELETED; closid_free(rdtgrp->closid); free_rmid(rdtgrp->mon.rmid); @@ -1946,14 +2890,7 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, */ free_all_child_rdtgrp(rdtgrp); - 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); + rdtgroup_ctrl_remove(kn, rdtgrp); return 0; } @@ -1981,13 +2918,19 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) * If the rdtgroup is a mon group and parent directory * is a valid "mon_groups" directory, remove the mon group. */ - if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) - ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); - else if (rdtgrp->type == RDTMON_GROUP && - is_mon_groups(parent_kn, kn->name)) + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + ret = rdtgroup_ctrl_remove(kn, rdtgrp); + } else { + ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); + } + } else if (rdtgrp->type == RDTMON_GROUP && + is_mon_groups(parent_kn, kn->name)) { ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask); - else + } else { ret = -EPERM; + } out: rdtgroup_kn_unlock(kn); @@ -1999,6 +2942,13 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) { if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) seq_puts(seq, ",cdp"); + + if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) + seq_puts(seq, ",cdpl2"); + + if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA])) + seq_puts(seq, ",mba_MBps"); + return 0; } @@ -2013,7 +2963,8 @@ static int __init rdtgroup_setup_root(void) int ret; rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops, - KERNFS_ROOT_CREATE_DEACTIVATED, + KERNFS_ROOT_CREATE_DEACTIVATED | + KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK, &rdtgroup_default); if (IS_ERR(rdt_root)) return PTR_ERR(rdt_root); @@ -2069,6 +3020,29 @@ int __init rdtgroup_init(void) if (ret) goto cleanup_mountpoint; + /* + * Adding the resctrl debugfs directory here may not be ideal since + * it would let the resctrl debugfs directory appear on the debugfs + * filesystem before the resctrl filesystem is mounted. + * It may also be ok since that would enable debugging of RDT before + * resctrl is mounted. + * The reason why the debugfs directory is created here and not in + * rdt_mount() is because rdt_mount() takes rdtgroup_mutex and + * during the debugfs directory creation also &sb->s_type->i_mutex_key + * (the lockdep class of inode->i_rwsem). Other filesystem + * interactions (eg. SyS_getdents) have the lock ordering: + * &sb->s_type->i_mutex_key --> &mm->mmap_sem + * During mmap(), called with &mm->mmap_sem, the rdtgroup_mutex + * is taken, thus creating dependency: + * &mm->mmap_sem --> rdtgroup_mutex for the latter that can cause + * issues considering the other two lock dependencies. + * By creating the debugfs directory here we avoid a dependency + * that may cause deadlock (even though file operations cannot + * occur until the filesystem is mounted, but I do not know how to + * tell lockdep that). + */ + debugfs_resctrl = debugfs_create_dir("resctrl", NULL); + return 0; cleanup_mountpoint: @@ -2078,3 +3052,11 @@ cleanup_root: return ret; } + +void __exit rdtgroup_exit(void) +{ + debugfs_remove_recursive(debugfs_resctrl); + unregister_filesystem(&rdt_fs_type); + sysfs_remove_mount_point(fs_kobj, "resctrl"); + kernfs_destroy_root(rdt_root); +} diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c index 97685a0c3175..27f394ac983f 100644 --- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c @@ -38,9 +38,6 @@ static struct mce_log_buffer mcelog = { static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); -/* User mode helper program triggered by machine check event */ -extern char mce_helper[128]; - static int dev_mce_log(struct notifier_block *nb, unsigned long val, void *data) { diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 231ad23b24a9..1fc424c40a31 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -48,7 +48,7 @@ static struct dentry *dfs_inj; static u8 n_banks; -#define MAX_FLAG_OPT_SIZE 3 +#define MAX_FLAG_OPT_SIZE 4 #define NBCFG 0x44 enum injection_type { @@ -108,6 +108,9 @@ static void setup_inj_struct(struct mce *m) memset(m, 0, sizeof(struct mce)); m->cpuvendor = boot_cpu_data.x86_vendor; + m->time = ktime_get_real_seconds(); + m->cpuid = cpuid_eax(1); + m->microcode = boot_cpu_data.microcode; } /* Update fake mce registers on current CPU. */ @@ -491,7 +494,7 @@ static void do_inject(void) unsigned int cpu = i_mce.extcpu; u8 b = i_mce.bank; - rdtscll(i_mce.tsc); + i_mce.tsc = rdtsc_ordered(); if (i_mce.misc) i_mce.status |= MCI_STATUS_MISCV; @@ -576,6 +579,9 @@ static int inj_bank_set(void *data, u64 val) m->bank = val; do_inject(); + /* Reset injection struct */ + setup_inj_struct(&i_mce); + return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index e956eb267061..ceb67cd5918f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -113,21 +113,61 @@ static inline void mce_register_injector_chain(struct notifier_block *nb) { } static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } #endif +struct mca_config { + bool dont_log_ce; + bool cmci_disabled; + bool ignore_ce; + + __u64 lmce_disabled : 1, + disabled : 1, + ser : 1, + recovery : 1, + bios_cmci_threshold : 1, + __reserved : 59; + + u8 banks; + s8 bootlog; + int tolerant; + int monarch_timeout; + int panic_timeout; + u32 rip_msr; +}; + extern struct mca_config mca_cfg; -#ifndef CONFIG_X86_64 -/* - * On 32-bit systems it would be difficult to safely unmap a poison page - * from the kernel 1:1 map because there are no non-canonical addresses that - * we can use to refer to the address without risking a speculative access. - * However, this isn't much of an issue because: - * 1) Few unmappable pages are in the 1:1 map. Most are in HIGHMEM which - * are only mapped into the kernel as needed - * 2) Few people would run a 32-bit kernel on a machine that supports - * recoverable errors because they have too much memory to boot 32-bit. - */ -static inline void mce_unmap_kpfn(unsigned long pfn) {} -#define mce_unmap_kpfn mce_unmap_kpfn -#endif +struct mce_vendor_flags { + /* + * Indicates that overflow conditions are not fatal, when set. + */ + __u64 overflow_recov : 1, + + /* + * (AMD) SUCCOR stands for S/W UnCorrectable error COntainment and + * Recovery. It indicates support for data poisoning in HW and deferred + * error interrupts. + */ + succor : 1, + + /* + * (AMD) SMCA: This bit indicates support for Scalable MCA which expands + * the register space for each MCA bank and also increases number of + * banks. Also, to accommodate the new banks and registers, the MCA + * register space is moved to a new MSR range. + */ + smca : 1, + + __reserved_0 : 61; +}; + +extern struct mce_vendor_flags mce_flags; + +struct mca_msr_regs { + u32 (*ctl) (int bank); + u32 (*status) (int bank); + u32 (*addr) (int bank); + u32 (*misc) (int bank); +}; + +extern struct mca_msr_regs msr_ops; #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 5bbd06f38ff6..44396d521987 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -160,6 +160,11 @@ static struct severity { SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), USER ), + MCESEV( + PANIC, "Data load in unrecoverable area of kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + KERNEL + ), #endif MCESEV( PANIC, "Action required: unknown MCACOD", @@ -331,7 +336,8 @@ int (*mce_severity)(struct mce *m, int tolerant, char **msg, bool is_excp) = void __init mcheck_vendor_init_severity(void) { - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) mce_severity = mce_severity_amd; } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 466f47301334..36d2696c9563 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -42,6 +42,7 @@ #include <linux/irq_work.h> #include <linux/export.h> #include <linux/jump_label.h> +#include <linux/set_memory.h> #include <asm/intel-family.h> #include <asm/processor.h> @@ -50,7 +51,6 @@ #include <asm/mce.h> #include <asm/msr.h> #include <asm/reboot.h> -#include <asm/set_memory.h> #include "mce-internal.h" @@ -108,10 +108,6 @@ static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); -#ifndef mce_unmap_kpfn -static void mce_unmap_kpfn(unsigned long pfn); -#endif - /* * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. @@ -123,8 +119,8 @@ void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); - /* We hope get_seconds stays lockless */ - m->time = get_seconds(); + /* need the internal __ version to avoid deadlocks */ + m->time = __ktime_get_real_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; m->cpuid = cpuid_eax(1); m->socketid = cpu_data(m->extcpu).phys_proc_id; @@ -273,7 +269,9 @@ static void __print_mce(struct mce *m) static void print_mce(struct mce *m) { __print_mce(m); - pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); + + if (m->cpuvendor != X86_VENDOR_AMD && m->cpuvendor != X86_VENDOR_HYGON) + pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); } #define PANIC_TIMEOUT 5 /* 5 seconds */ @@ -487,7 +485,7 @@ static void mce_report_event(struct pt_regs *regs) * be somewhat complicated (e.g. segment offset would require an instruction * parser). So only support physical addresses up to page granuality for now. */ -static int mce_usable_address(struct mce *m) +int mce_usable_address(struct mce *m) { if (!(m->status & MCI_STATUS_ADDRV)) return 0; @@ -507,12 +505,13 @@ static int mce_usable_address(struct mce *m) return 1; } +EXPORT_SYMBOL_GPL(mce_usable_address); bool mce_is_memory_error(struct mce *m) { - if (m->cpuvendor == X86_VENDOR_AMD) { + if (m->cpuvendor == X86_VENDOR_AMD || + m->cpuvendor == X86_VENDOR_HYGON) { return amd_mce_is_memory_error(m); - } else if (m->cpuvendor == X86_VENDOR_INTEL) { /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes @@ -536,16 +535,20 @@ bool mce_is_memory_error(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_memory_error); -static bool mce_is_correctable(struct mce *m) +bool mce_is_correctable(struct mce *m) { if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) return false; + if (m->cpuvendor == X86_VENDOR_HYGON && m->status & MCI_STATUS_DEFERRED) + return false; + if (m->status & MCI_STATUS_UC) return false; return true; } +EXPORT_SYMBOL_GPL(mce_is_correctable); static bool cec_add_mce(struct mce *m) { @@ -600,7 +603,7 @@ 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; if (!memory_failure(pfn, 0)) - mce_unmap_kpfn(pfn); + set_mce_nospec(pfn); } return NOTIFY_OK; @@ -770,23 +773,25 @@ EXPORT_SYMBOL_GPL(machine_check_poll); static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, struct pt_regs *regs) { - int i, ret = 0; char *tmp; + int i; for (i = 0; i < mca_cfg.banks; i++) { m->status = mce_rdmsrl(msr_ops.status(i)); - if (m->status & MCI_STATUS_VAL) { - __set_bit(i, validp); - if (quirk_no_way_out) - quirk_no_way_out(i, m, regs); - } + if (!(m->status & MCI_STATUS_VAL)) + continue; + + __set_bit(i, validp); + if (quirk_no_way_out) + quirk_no_way_out(i, m, regs); if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + mce_read_aux(m, i); *msg = tmp; - ret = 1; + return 1; } } - return ret; + return 0; } /* @@ -1068,49 +1073,104 @@ static int do_memory_failure(struct mce *m) if (ret) pr_err("Memory error not recovered"); else - mce_unmap_kpfn(m->addr >> PAGE_SHIFT); + set_mce_nospec(m->addr >> PAGE_SHIFT); return ret; } -#ifndef mce_unmap_kpfn -static void mce_unmap_kpfn(unsigned long pfn) -{ - unsigned long decoy_addr; - - /* - * Unmap this page from the kernel 1:1 mappings to make sure - * we don't log more errors because of speculative access to - * the page. - * We would like to just call: - * set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1); - * but doing that would radically increase the odds of a - * speculative access to the poison page because we'd have - * the virtual address of the kernel 1:1 mapping sitting - * around in registers. - * Instead we get tricky. We create a non-canonical address - * that looks just like the one we want, but has bit 63 flipped. - * This relies on set_memory_np() not checking whether we passed - * a legal address. - */ /* - * Build time check to see if we have a spare virtual bit. Don't want - * to leave this until run time because most developers don't have a - * system that can exercise this code path. This will only become a - * problem if/when we move beyond 5-level page tables. + * Cases where we avoid rendezvous handler timeout: + * 1) If this CPU is offline. * - * Hard code "9" here because cpp doesn't grok ilog2(PTRS_PER_PGD) + * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to + * skip those CPUs which remain looping in the 1st kernel - see + * crash_nmi_callback(). + * + * Note: there still is a small window between kexec-ing and the new, + * kdump kernel establishing a new #MC handler where a broadcasted MCE + * might not get handled properly. */ -#if PGDIR_SHIFT + 9 < 63 - decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); -#else -#error "no unused virtual bit available" -#endif +static bool __mc_check_crashing_cpu(int cpu) +{ + if (cpu_is_offline(cpu) || + (crashing_cpu != -1 && crashing_cpu != cpu)) { + u64 mcgstatus; - if (set_memory_np(decoy_addr, 1)) - pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); + mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + if (mcgstatus & MCG_STATUS_RIPV) { + mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); + return true; + } + } + return false; +} + +static void __mc_scan_banks(struct mce *m, struct mce *final, + unsigned long *toclear, unsigned long *valid_banks, + int no_way_out, int *worst) +{ + struct mca_config *cfg = &mca_cfg; + int severity, i; + + for (i = 0; i < cfg->banks; i++) { + __clear_bit(i, toclear); + if (!test_bit(i, valid_banks)) + continue; + + if (!mce_banks[i].ctl) + continue; + + m->misc = 0; + m->addr = 0; + m->bank = i; + + m->status = mce_rdmsrl(msr_ops.status(i)); + if (!(m->status & MCI_STATUS_VAL)) + continue; + + /* + * Corrected or non-signaled errors are handled by + * machine_check_poll(). Leave them alone, unless this panics. + */ + if (!(m->status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) && + !no_way_out) + continue; + + /* Set taint even when machine check was not enabled. */ + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + + severity = mce_severity(m, cfg->tolerant, NULL, true); + + /* + * When machine check was for corrected/deferred handler don't + * touch, unless we're panicking. + */ + if ((severity == MCE_KEEP_SEVERITY || + severity == MCE_UCNA_SEVERITY) && !no_way_out) + continue; + + __set_bit(i, toclear); + + /* Machine check event was not enabled. Clear, but ignore. */ + if (severity == MCE_NO_SEVERITY) + continue; + + mce_read_aux(m, i); + + /* assuming valid severity level != 0 */ + m->severity = severity; + + mce_log(m); + + if (severity > *worst) { + *final = *m; + *worst = severity; + } + } + + /* mce_clear_state will clear *final, save locally for use later */ + *m = *final; } -#endif /* * The actual machine check handler. This only handles real @@ -1126,68 +1186,45 @@ static void mce_unmap_kpfn(unsigned long pfn) */ void do_machine_check(struct pt_regs *regs, long error_code) { + DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); + DECLARE_BITMAP(toclear, MAX_NR_BANKS); struct mca_config *cfg = &mca_cfg; + int cpu = smp_processor_id(); + char *msg = "Unknown"; struct mce m, *final; - int i; int worst = 0; - int severity; /* * Establish sequential order between the CPUs entering the machine * check handler. */ int order = -1; + /* * If no_way_out gets set, there is no safe way to recover from this * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. */ int no_way_out = 0; + /* * If kill_it gets set, there might be a way to recover from this * error. */ int kill_it = 0; - DECLARE_BITMAP(toclear, MAX_NR_BANKS); - DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); - char *msg = "Unknown"; /* * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES * on Intel. */ int lmce = 1; - int cpu = smp_processor_id(); - /* - * Cases where we avoid rendezvous handler timeout: - * 1) If this CPU is offline. - * - * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to - * skip those CPUs which remain looping in the 1st kernel - see - * crash_nmi_callback(). - * - * Note: there still is a small window between kexec-ing and the new, - * kdump kernel establishing a new #MC handler where a broadcasted MCE - * might not get handled properly. - */ - if (cpu_is_offline(cpu) || - (crashing_cpu != -1 && crashing_cpu != cpu)) { - u64 mcgstatus; - - mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); - if (mcgstatus & MCG_STATUS_RIPV) { - mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); - return; - } - } + if (__mc_check_crashing_cpu(cpu)) + return; ist_enter(regs); this_cpu_inc(mce_exception_count); - if (!cfg->banks) - goto out; - mce_gather_info(&m, regs); m.tsc = rdtsc(); @@ -1215,75 +1252,20 @@ void do_machine_check(struct pt_regs *regs, long error_code) lmce = m.mcgstatus & MCG_STATUS_LMCES; /* + * Local machine check may already know that we have to panic. + * Broadcast machine check begins rendezvous in mce_start() * Go through all banks in exclusion of the other CPUs. This way we * don't report duplicated events on shared banks because the first one - * to see it will clear it. If this is a Local MCE, then no need to - * perform rendezvous. + * to see it will clear it. */ - if (!lmce) + if (lmce) { + if (no_way_out) + mce_panic("Fatal local machine check", &m, msg); + } else { order = mce_start(&no_way_out); - - for (i = 0; i < cfg->banks; i++) { - __clear_bit(i, toclear); - if (!test_bit(i, valid_banks)) - continue; - if (!mce_banks[i].ctl) - continue; - - m.misc = 0; - m.addr = 0; - m.bank = i; - - m.status = mce_rdmsrl(msr_ops.status(i)); - if ((m.status & MCI_STATUS_VAL) == 0) - continue; - - /* - * Non uncorrected or non signaled errors are handled by - * machine_check_poll. Leave them alone, unless this panics. - */ - if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) && - !no_way_out) - continue; - - /* - * Set taint even when machine check was not enabled. - */ - add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - - severity = mce_severity(&m, cfg->tolerant, NULL, true); - - /* - * When machine check was for corrected/deferred handler don't - * touch, unless we're panicing. - */ - if ((severity == MCE_KEEP_SEVERITY || - severity == MCE_UCNA_SEVERITY) && !no_way_out) - continue; - __set_bit(i, toclear); - if (severity == MCE_NO_SEVERITY) { - /* - * Machine check event was not enabled. Clear, but - * ignore. - */ - continue; - } - - mce_read_aux(&m, i); - - /* assuming valid severity level != 0 */ - m.severity = severity; - - mce_log(&m); - - if (severity > worst) { - *final = m; - worst = severity; - } } - /* mce_clear_state will clear *final, save locally for use later */ - m = *final; + __mc_scan_banks(&m, final, toclear, valid_banks, no_way_out, &worst); if (!no_way_out) mce_clear_state(toclear); @@ -1297,12 +1279,17 @@ void do_machine_check(struct pt_regs *regs, long error_code) no_way_out = worst >= MCE_PANIC_SEVERITY; } else { /* - * Local MCE skipped calling mce_reign() - * If we found a fatal error, we need to panic here. + * If there was a fatal machine check we should have + * already called mce_panic earlier in this function. + * Since we re-read the banks, we might have found + * something new. Check again to see if we found a + * fatal error. We call "mce_severity()" again to + * make sure we have the right "msg". */ - if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) - mce_panic("Machine check from unknown source", - NULL, NULL); + if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) { + mce_severity(&m, cfg->tolerant, &msg, true); + mce_panic("Local fatal machine check!", &m, msg); + } } /* @@ -1317,7 +1304,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) if (worst > 0) mce_report_event(regs); mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); -out: + sync_core(); if (worst != MCE_AR_SEVERITY && !kill_it) @@ -1333,7 +1320,7 @@ out: local_irq_disable(); ist_end_non_atomic(); } else { - if (!fixup_exception(regs, X86_TRAP_MC)) + if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0)) mce_panic("Failed kernel mode recovery", &m, NULL); } @@ -1467,7 +1454,7 @@ static int __mcheck_cpu_mce_banks_init(void) int i; u8 num_banks = mca_cfg.banks; - mce_banks = kzalloc(num_banks * sizeof(struct mce_bank), GFP_KERNEL); + mce_banks = kcalloc(num_banks, sizeof(struct mce_bank), GFP_KERNEL); if (!mce_banks) return -ENOMEM; @@ -1516,7 +1503,7 @@ static int __mcheck_cpu_cap_init(void) mca_cfg.rip_msr = MSR_IA32_MCG_EIP; if (cap & MCG_SER_P) - mca_cfg.ser = true; + mca_cfg.ser = 1; return 0; } @@ -1723,7 +1710,7 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) */ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) { - if (c->x86_vendor == X86_VENDOR_AMD) { + if (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) { mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV); mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); @@ -1737,6 +1724,21 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) } } +static void mce_centaur_feature_init(struct cpuinfo_x86 *c) +{ + struct mca_config *cfg = &mca_cfg; + + /* + * All newer Centaur CPUs support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if ((c->x86 == 6 && c->x86_model == 0xf && c->x86_stepping >= 0xe) || + c->x86 > 6) { + if (cfg->monarch_timeout < 0) + cfg->monarch_timeout = USEC_PER_SEC; + } +} + static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) { switch (c->x86_vendor) { @@ -1750,6 +1752,14 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) break; } + case X86_VENDOR_HYGON: + mce_hygon_feature_init(c); + break; + + case X86_VENDOR_CENTAUR: + mce_centaur_feature_init(c); + break; + default: break; } @@ -1824,12 +1834,12 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) return; if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) { - mca_cfg.disabled = true; + mca_cfg.disabled = 1; return; } if (mce_gen_pool_init()) { - mca_cfg.disabled = true; + mca_cfg.disabled = 1; pr_emerg("Couldn't allocate MCE records pool!\n"); return; } @@ -1907,11 +1917,11 @@ static int __init mcheck_enable(char *str) if (*str == '=') str++; if (!strcmp(str, "off")) - cfg->disabled = true; + cfg->disabled = 1; else if (!strcmp(str, "no_cmci")) cfg->cmci_disabled = true; else if (!strcmp(str, "no_lmce")) - cfg->lmce_disabled = true; + cfg->lmce_disabled = 1; else if (!strcmp(str, "dont_log_ce")) cfg->dont_log_ce = true; else if (!strcmp(str, "ignore_ce")) @@ -1919,9 +1929,9 @@ static int __init mcheck_enable(char *str) else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) cfg->bootlog = (str[0] == 'b'); else if (!strcmp(str, "bios_cmci_threshold")) - cfg->bios_cmci_threshold = true; + cfg->bios_cmci_threshold = 1; else if (!strcmp(str, "recovery")) - cfg->recovery = true; + cfg->recovery = 1; else if (isdigit(str[0])) { if (get_option(&str, &cfg->tolerant) == 2) get_option(&str, &(cfg->monarch_timeout)); @@ -1971,12 +1981,14 @@ static void mce_disable_error_reporting(void) static void vendor_disable_error_reporting(void) { /* - * Don't clear on Intel or AMD CPUs. Some of these MSRs are socket-wide. + * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs + * are socket-wide. * Disabling them for just a single offlined CPU is bad, since it will * inhibit reporting for all shared resources on the socket like the * last level cache (LLC), the integrated memory controller (iMC), etc. */ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON || boot_cpu_data.x86_vendor == X86_VENDOR_AMD) return; @@ -2145,9 +2157,6 @@ static ssize_t store_int_with_restart(struct device *s, if (check_interval == old_check_interval) return ret; - if (check_interval < 1) - check_interval = 1; - mutex_lock(&mce_sysfs_mutex); mce_restart(); mutex_unlock(&mce_sysfs_mutex); @@ -2208,7 +2217,7 @@ static int mce_device_create(unsigned int cpu) if (dev) return 0; - dev = kzalloc(sizeof *dev, GFP_KERNEL); + dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return -ENOMEM; dev->id = cpu; @@ -2355,6 +2364,12 @@ static __init int mcheck_init_device(void) { int err; + /* + * Check if we have a spare virtual bit. This will only become + * a problem if/when we move beyond 5-level page tables. + */ + MAYBE_BUILD_BUG_ON(__VIRTUAL_MASK_SHIFT >= 63); + if (!mce_available(&boot_cpu_data)) { err = -EIO; goto err_out; @@ -2403,7 +2418,7 @@ device_initcall_sync(mcheck_init_device); */ static int __init mcheck_disable(char *str) { - mca_cfg.disabled = true; + mca_cfg.disabled = 1; return 1; } __setup("nomce", mcheck_disable); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 0f32ad242324..dd33c357548f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -82,6 +82,7 @@ static struct smca_bank_name smca_names[] = { [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" }, [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, [SMCA_DE] = { "decode_unit", "Decode Unit" }, + [SMCA_RESERVED] = { "reserved", "Reserved" }, [SMCA_EX] = { "execution_unit", "Execution Unit" }, [SMCA_FP] = { "floating_point", "Floating Point Unit" }, [SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" }, @@ -93,6 +94,11 @@ static struct smca_bank_name smca_names[] = { [SMCA_SMU] = { "smu", "System Management Unit" }, }; +static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init = +{ + [0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 } +}; + const char *smca_get_name(enum smca_bank_types t) { if (t >= N_SMCA_BANK_TYPES) @@ -110,14 +116,14 @@ 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) +static enum smca_bank_types smca_get_bank_type(unsigned int bank) { struct smca_bank *b; - if (m->bank >= N_SMCA_BANK_TYPES) + if (bank >= MAX_NR_BANKS) return N_SMCA_BANK_TYPES; - b = &smca_banks[m->bank]; + b = &smca_banks[bank]; if (!b->hwid) return N_SMCA_BANK_TYPES; @@ -127,6 +133,9 @@ static enum smca_bank_types smca_get_bank_type(struct mce *m) static struct smca_hwid smca_hwid_mcatypes[] = { /* { bank_type, hwid_mcatype, xec_bitmap } */ + /* Reserved type */ + { SMCA_RESERVED, HWID_MCATYPE(0x00, 0x0), 0x0 }, + /* ZN Core (HWID=0xB0) MCA types */ { SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFEF }, { SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF }, @@ -427,34 +436,50 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c) wrmsr(MSR_CU_DEF_ERR, low, high); } -static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 high, - unsigned int bank, unsigned int block) +static u32 smca_get_block_address(unsigned int bank, unsigned int block) { - u32 addr = 0, offset = 0; + u32 low, high; + u32 addr = 0; - if (mce_flags.smca) { - if (!block) { - addr = MSR_AMD64_SMCA_MCx_MISC(bank); - } else { - /* - * For SMCA enabled processors, BLKPTR field of the - * first MISC register (MCx_MISC0) indicates presence of - * additional MISC register set (MISC1-4). - */ - u32 low, high; + if (smca_get_bank_type(bank) == SMCA_RESERVED) + return addr; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) - return addr; + if (!block) + return MSR_AMD64_SMCA_MCx_MISC(bank); - if (!(low & MCI_CONFIG_MCAX)) - return addr; + /* Check our cache first: */ + if (smca_bank_addrs[bank][block] != -1) + return smca_bank_addrs[bank][block]; - if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) && - (low & MASK_BLKPTR_LO)) - addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); - } + /* + * For SMCA enabled processors, BLKPTR field of the first MISC register + * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4). + */ + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) + goto out; + + if (!(low & MCI_CONFIG_MCAX)) + goto out; + + if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) && + (low & MASK_BLKPTR_LO)) + addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); + +out: + smca_bank_addrs[bank][block] = addr; + return addr; +} + +static u32 get_block_address(u32 current_addr, u32 low, u32 high, + unsigned int bank, unsigned int block) +{ + u32 addr = 0, offset = 0; + + if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS)) return addr; - } + + if (mce_flags.smca) + return smca_get_block_address(bank, block); /* Fall back to method we used for older processors: */ switch (block) { @@ -532,7 +557,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) smca_configure(bank, cpu); for (block = 0; block < NR_BLOCKS; ++block) { - address = get_block_address(cpu, address, low, high, bank, block); + address = get_block_address(address, low, high, bank, block); if (!address) break; @@ -760,7 +785,7 @@ bool amd_mce_is_memory_error(struct mce *m) u8 xec = (m->status >> 16) & 0x1f; if (mce_flags.smca) - return smca_get_bank_type(m) == SMCA_UMC && xec == 0x0; + return smca_get_bank_type(m->bank) == SMCA_UMC && xec == 0x0; return m->bank == 4 && xec == 0x8; } @@ -1063,7 +1088,7 @@ static struct kobj_type threshold_ktype = { static const char *get_name(unsigned int bank, struct threshold_block *b) { - unsigned int bank_type; + enum smca_bank_types bank_type; if (!mce_flags.smca) { if (b && bank == 4) @@ -1072,11 +1097,10 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return th_names[bank]; } - if (!smca_banks[bank].hwid) + bank_type = smca_get_bank_type(bank); + if (bank_type >= N_SMCA_BANK_TYPES) return NULL; - bank_type = smca_banks[bank].hwid->bank_type; - if (b && bank_type == SMCA_UMC) { if (b->block < ARRAY_SIZE(smca_umc_block_names)) return smca_umc_block_names[b->block]; @@ -1150,7 +1174,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, if (err) goto out_free; recurse: - address = get_block_address(cpu, address, low, high, bank, ++block); + address = get_block_address(address, low, high, bank, ++block); if (!address) return 0; @@ -1360,7 +1384,7 @@ int mce_threshold_create_device(unsigned int cpu) if (bp) return 0; - bp = kzalloc(sizeof(struct threshold_bank *) * mca_cfg.banks, + bp = kcalloc(mca_cfg.banks, sizeof(struct threshold_bank *), GFP_KERNEL); if (!bp) return -ENOMEM; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 48179928ff38..07b5fc00b188 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -58,7 +58,7 @@ static u8 amd_ucode_patch[PATCH_MAX_SIZE]; /* * Microcode patch container file is prepended to the initrd in cpio - * format. See Documentation/x86/early-microcode.txt + * format. See Documentation/x86/microcode.txt */ static const char ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin"; @@ -504,6 +504,7 @@ static enum ucode_state apply_microcode_amd(int cpu) struct microcode_amd *mc_amd; struct ucode_cpu_info *uci; struct ucode_patch *p; + enum ucode_state ret; u32 rev, dummy; BUG_ON(raw_smp_processor_id() != cpu); @@ -521,9 +522,8 @@ static enum ucode_state apply_microcode_amd(int cpu) /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { - c->microcode = rev; - uci->cpu_sig.rev = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } if (__apply_microcode_amd(mc_amd)) { @@ -531,13 +531,21 @@ static enum ucode_state apply_microcode_amd(int cpu) cpu, mc_amd->hdr.patch_id); return UCODE_ERROR; } - pr_info("CPU%d: new patch_level=0x%08x\n", cpu, - mc_amd->hdr.patch_id); - uci->cpu_sig.rev = mc_amd->hdr.patch_id; - c->microcode = mc_amd->hdr.patch_id; + rev = mc_amd->hdr.patch_id; + ret = UCODE_UPDATED; + + pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev); - return UCODE_UPDATED; +out: + uci->cpu_sig.rev = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; + + return ret; } static int install_equiv_cpu_table(const u8 *buf) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 10c4fc2c91f8..2637ff09d6a0 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -70,7 +70,7 @@ static DEFINE_MUTEX(microcode_mutex); /* * Serialize late loading so that CPUs get updated one-by-one. */ -static DEFINE_SPINLOCK(update_lock); +static DEFINE_RAW_SPINLOCK(update_lock); struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; @@ -509,12 +509,20 @@ static struct platform_device *microcode_pdev; static int check_online_cpus(void) { - if (num_online_cpus() == num_present_cpus()) - return 0; + unsigned int cpu; - pr_err("Not all CPUs online, aborting microcode update.\n"); + /* + * Make sure all CPUs are online. It's fine for SMT to be disabled if + * all the primary threads are still online. + */ + for_each_present_cpu(cpu) { + if (topology_is_primary_thread(cpu) && !cpu_online(cpu)) { + pr_err("Not all CPUs online, aborting microcode update.\n"); + return -EINVAL; + } + } - return -EINVAL; + return 0; } static atomic_t late_cpus_in; @@ -560,18 +568,16 @@ static int __reload_late(void *info) if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC)) return -1; - spin_lock(&update_lock); + raw_spin_lock(&update_lock); apply_microcode_local(&err); - spin_unlock(&update_lock); + raw_spin_unlock(&update_lock); + /* siblings return UCODE_OK because their engine got updated already */ if (err > UCODE_NFOUND) { pr_warn("Error reloading microcode on CPU %d\n", cpu); - return -1; - /* siblings return UCODE_OK because their engine got updated already */ + ret = -1; } else if (err == UCODE_UPDATED || err == UCODE_OK) { ret = 1; - } else { - return ret; } /* @@ -660,8 +666,8 @@ static ssize_t pf_show(struct device *dev, } static DEVICE_ATTR_WO(reload); -static DEVICE_ATTR(version, 0400, version_show, NULL); -static DEVICE_ATTR(processor_flags, 0400, pf_show, NULL); +static DEVICE_ATTR(version, 0444, version_show, NULL); +static DEVICE_ATTR(processor_flags, 0444, pf_show, NULL); static struct attribute *mc_default_attrs[] = { &dev_attr_version.attr, diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 32b8e5724f96..16936a24795c 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -190,8 +190,11 @@ static void save_microcode_patch(void *data, unsigned int size) p = memdup_patch(data, size); if (!p) pr_err("Error allocating buffer %p\n", data); - else + else { list_replace(&iter->plist, &p->plist); + kfree(iter->data); + kfree(iter); + } } } @@ -485,7 +488,6 @@ static void show_saved_mc(void) */ static void save_mc_for_early(u8 *mc, unsigned int size) { -#ifdef CONFIG_HOTPLUG_CPU /* Synchronization during CPU hotplug. */ static DEFINE_MUTEX(x86_cpu_microcode_mutex); @@ -495,7 +497,6 @@ static void save_mc_for_early(u8 *mc, unsigned int size) show_saved_mc(); mutex_unlock(&x86_cpu_microcode_mutex); -#endif } static bool load_builtin_intel_microcode(struct cpio_data *cp) @@ -794,6 +795,7 @@ static enum ucode_state apply_microcode_intel(int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_intel *mc; + enum ucode_state ret; static int prev_rev; u32 rev; @@ -816,9 +818,8 @@ static enum ucode_state apply_microcode_intel(int cpu) */ rev = intel_get_microcode_revision(); if (rev >= mc->hdr.rev) { - uci->cpu_sig.rev = rev; - c->microcode = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } /* @@ -847,10 +848,17 @@ static enum ucode_state apply_microcode_intel(int cpu) prev_rev = rev; } + ret = UCODE_UPDATED; + +out: uci->cpu_sig.rev = rev; - c->microcode = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; - return UCODE_UPDATED; + return ret; } static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 9340f41ce8d3..e81a2db42df7 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -20,9 +20,10 @@ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kexec.h> +#include <linux/i8253.h> #include <asm/processor.h> #include <asm/hypervisor.h> -#include <asm/hyperv.h> +#include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> #include <asm/desc.h> #include <asm/irq_regs.h> @@ -37,10 +38,11 @@ EXPORT_SYMBOL_GPL(ms_hyperv); #if IS_ENABLED(CONFIG_HYPERV) static void (*vmbus_handler)(void); +static void (*hv_stimer0_handler)(void); static void (*hv_kexec_handler)(void); static void (*hv_crash_handler)(struct pt_regs *regs); -void hyperv_vector_handler(struct pt_regs *regs) +__visible void __irq_entry hyperv_vector_handler(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -49,7 +51,7 @@ void hyperv_vector_handler(struct pt_regs *regs) if (vmbus_handler) vmbus_handler(); - if (ms_hyperv.hints & HV_X64_DEPRECATING_AEOI_RECOMMENDED) + if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED) ack_APIC_irq(); exiting_irq(); @@ -69,6 +71,41 @@ void hv_remove_vmbus_irq(void) EXPORT_SYMBOL_GPL(hv_setup_vmbus_irq); EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq); +/* + * Routines to do per-architecture handling of stimer0 + * interrupts when in Direct Mode + */ + +__visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + entering_irq(); + inc_irq_stat(hyperv_stimer0_count); + if (hv_stimer0_handler) + hv_stimer0_handler(); + ack_APIC_irq(); + + exiting_irq(); + set_irq_regs(old_regs); +} + +int hv_setup_stimer0_irq(int *irq, int *vector, void (*handler)(void)) +{ + *vector = HYPERV_STIMER0_VECTOR; + *irq = 0; /* Unused on x86/x64 */ + hv_stimer0_handler = handler; + return 0; +} +EXPORT_SYMBOL_GPL(hv_setup_stimer0_irq); + +void hv_remove_stimer0_irq(int irq) +{ + /* We have no way to deallocate the interrupt gate */ + hv_stimer0_handler = NULL; +} +EXPORT_SYMBOL_GPL(hv_remove_stimer0_irq); + void hv_setup_kexec_handler(void (*handler)(void)) { hv_kexec_handler = handler; @@ -163,6 +200,16 @@ static unsigned long hv_get_tsc_khz(void) return freq / 1000; } +#if defined(CONFIG_SMP) && IS_ENABLED(CONFIG_HYPERV) +static void __init hv_smp_prepare_boot_cpu(void) +{ + native_smp_prepare_boot_cpu(); +#if defined(CONFIG_X86_64) && defined(CONFIG_PARAVIRT_SPINLOCKS) + hv_init_spinlocks(); +#endif +} +#endif + static void __init ms_hyperv_init_platform(void) { int hv_host_info_eax; @@ -180,8 +227,8 @@ static void __init ms_hyperv_init_platform(void) pr_info("Hyper-V: features 0x%x, hints 0x%x\n", ms_hyperv.features, ms_hyperv.hints); - ms_hyperv.max_vp_index = cpuid_eax(HVCPUID_IMPLEMENTATION_LIMITS); - ms_hyperv.max_lp_index = cpuid_ebx(HVCPUID_IMPLEMENTATION_LIMITS); + ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS); + ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS); pr_debug("Hyper-V: max %u virtual processors, %u logical processors\n", ms_hyperv.max_vp_index, ms_hyperv.max_lp_index); @@ -189,11 +236,12 @@ static void __init ms_hyperv_init_platform(void) /* * Extract host information. */ - if (cpuid_eax(HVCPUID_VENDOR_MAXFUNCTION) >= HVCPUID_VERSION) { - hv_host_info_eax = cpuid_eax(HVCPUID_VERSION); - hv_host_info_ebx = cpuid_ebx(HVCPUID_VERSION); - hv_host_info_ecx = cpuid_ecx(HVCPUID_VERSION); - hv_host_info_edx = cpuid_edx(HVCPUID_VERSION); + if (cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS) >= + HYPERV_CPUID_VERSION) { + hv_host_info_eax = cpuid_eax(HYPERV_CPUID_VERSION); + hv_host_info_ebx = cpuid_ebx(HYPERV_CPUID_VERSION); + hv_host_info_ecx = cpuid_ecx(HYPERV_CPUID_VERSION); + hv_host_info_edx = cpuid_edx(HYPERV_CPUID_VERSION); pr_info("Hyper-V Host Build:%d-%d.%d-%d-%d.%d\n", hv_host_info_eax, hv_host_info_ebx >> 16, @@ -207,6 +255,11 @@ static void __init ms_hyperv_init_platform(void) x86_platform.calibrate_cpu = hv_get_tsc_khz; } + if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) { + ms_hyperv.nested_features = + cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); + } + #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { @@ -243,6 +296,16 @@ static void __init ms_hyperv_init_platform(void) if (efi_enabled(EFI_BOOT)) x86_platform.get_nmi_reason = hv_get_nmi_reason; + /* + * Hyper-V VMs have a PIT emulation quirk such that zeroing the + * counter register during PIT shutdown restarts the PIT. So it + * continues to interrupt @18.2 HZ. Setting i8253_clear_counter + * to false tells pit_shutdown() not to zero the counter so that + * the PIT really is shutdown. Generation 2 VMs don't have a PIT, + * and setting this value has no effect. + */ + i8253_clear_counter_on_shutdown = false; + #if IS_ENABLED(CONFIG_HYPERV) /* * Setup the hook to get control post apic initialization. @@ -257,6 +320,14 @@ static void __init ms_hyperv_init_platform(void) alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR, hyperv_reenlightenment_vector); + /* Setup the IDT for stimer0 */ + if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) + alloc_intr_gate(HYPERV_STIMER0_VECTOR, + hv_stimer0_callback_vector); + +# ifdef CONFIG_SMP + smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu; +# endif #endif } diff --git a/arch/x86/kernel/cpu/mtrr/Makefile b/arch/x86/kernel/cpu/mtrr/Makefile index ad9e5ed81181..2ad9107ee980 100644 --- a/arch/x86/kernel/cpu/mtrr/Makefile +++ b/arch/x86/kernel/cpu/mtrr/Makefile @@ -1,3 +1,3 @@ -obj-y := main.o if.o generic.o cleanup.o +obj-y := mtrr.o if.o generic.o cleanup.o obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 765afd599039..3668c5df90c6 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -831,7 +831,8 @@ int __init amd_special_default_mtrr(void) { u32 l, h; - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) return 0; if (boot_cpu_data.x86 < 0xf) return 0; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index e12ee86906c6..86e277f8daf4 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -798,7 +798,7 @@ static void generic_set_all(void) local_irq_restore(flags); /* Use the atomic bitops to update the global mask */ - for (count = 0; count < sizeof mask * 8; ++count) { + for (count = 0; count < sizeof(mask) * 8; ++count) { if (mask & 0x01) set_bit(count, &smp_changes_mask); mask >>= 1; diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 558444b23923..2e173d47b450 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -43,7 +43,7 @@ mtrr_file_add(unsigned long base, unsigned long size, max = num_var_ranges; if (fcount == NULL) { - fcount = kzalloc(max * sizeof *fcount, GFP_KERNEL); + fcount = kcalloc(max, sizeof(*fcount), GFP_KERNEL); if (!fcount) return -ENOMEM; FILE_FCOUNT(file) = fcount; @@ -106,17 +106,10 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos) memset(line, 0, LINE_SIZE); - length = len; - length--; - - if (length > LINE_SIZE - 1) - length = LINE_SIZE - 1; - + len = min_t(size_t, len, LINE_SIZE - 1); + length = strncpy_from_user(line, buf, len); if (length < 0) - return -EINVAL; - - if (copy_from_user(line, buf, length)) - return -EFAULT; + return length; linelen = strlen(line); ptr = line + linelen - 1; @@ -149,17 +142,16 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos) return -EINVAL; ptr = skip_spaces(ptr + 5); - for (i = 0; i < MTRR_NUM_TYPES; ++i) { - if (strcmp(ptr, mtrr_strings[i])) - continue; - base >>= PAGE_SHIFT; - size >>= PAGE_SHIFT; - err = mtrr_add_page((unsigned long)base, (unsigned long)size, i, true); - if (err < 0) - return err; - return len; - } - return -EINVAL; + i = match_string(mtrr_strings, MTRR_NUM_TYPES, ptr); + if (i < 0) + return i; + + base >>= PAGE_SHIFT; + size >>= PAGE_SHIFT; + err = mtrr_add_page((unsigned long)base, (unsigned long)size, i, true); + if (err < 0) + return err; + return len; } static long @@ -182,12 +174,12 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) case MTRRIOC_SET_PAGE_ENTRY: case MTRRIOC_DEL_PAGE_ENTRY: case MTRRIOC_KILL_PAGE_ENTRY: - if (copy_from_user(&sentry, arg, sizeof sentry)) + if (copy_from_user(&sentry, arg, sizeof(sentry))) return -EFAULT; break; case MTRRIOC_GET_ENTRY: case MTRRIOC_GET_PAGE_ENTRY: - if (copy_from_user(&gentry, arg, sizeof gentry)) + if (copy_from_user(&gentry, arg, sizeof(gentry))) return -EFAULT; break; #ifdef CONFIG_COMPAT @@ -340,7 +332,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) switch (cmd) { case MTRRIOC_GET_ENTRY: case MTRRIOC_GET_PAGE_ENTRY: - if (copy_to_user(arg, &gentry, sizeof gentry)) + if (copy_to_user(arg, &gentry, sizeof(gentry))) err = -EFAULT; break; #ifdef CONFIG_COMPAT diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 7468de429087..507039c20128 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -46,6 +46,7 @@ #include <linux/pci.h> #include <linux/smp.h> #include <linux/syscore_ops.h> +#include <linux/rcupdate.h> #include <asm/cpufeature.h> #include <asm/e820/api.h> @@ -100,7 +101,7 @@ static int have_wrcomb(void) if (dev->vendor == PCI_VENDOR_ID_SERVERWORKS && dev->device == PCI_DEVICE_ID_SERVERWORKS_LE && dev->revision <= 5) { - pr_info("mtrr: Serverworks LE rev < 6 detected. Write-combining disabled.\n"); + pr_info("Serverworks LE rev < 6 detected. Write-combining disabled.\n"); pci_dev_put(dev); return 0; } @@ -110,7 +111,7 @@ static int have_wrcomb(void) */ if (dev->vendor == PCI_VENDOR_ID_INTEL && dev->device == PCI_DEVICE_ID_INTEL_82451NX) { - pr_info("mtrr: Intel 450NX MMC detected. Write-combining disabled.\n"); + pr_info("Intel 450NX MMC detected. Write-combining disabled.\n"); pci_dev_put(dev); return 0; } @@ -126,7 +127,7 @@ static void __init set_num_var_ranges(void) if (use_intel()) rdmsr(MSR_MTRRcap, config, dummy); - else if (is_cpu(AMD)) + else if (is_cpu(AMD) || is_cpu(HYGON)) config = 2; else if (is_cpu(CYRIX) || is_cpu(CENTAUR)) config = 8; @@ -312,24 +313,24 @@ int mtrr_add_page(unsigned long base, unsigned long size, return error; if (type >= MTRR_NUM_TYPES) { - pr_warn("mtrr: type: %u invalid\n", type); + pr_warn("type: %u invalid\n", type); return -EINVAL; } /* If the type is WC, check that this processor supports it */ if ((type == MTRR_TYPE_WRCOMB) && !have_wrcomb()) { - pr_warn("mtrr: your processor doesn't support write-combining\n"); + pr_warn("your processor doesn't support write-combining\n"); return -ENOSYS; } if (!size) { - pr_warn("mtrr: zero sized request\n"); + pr_warn("zero sized request\n"); return -EINVAL; } if ((base | (base + size - 1)) >> (boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) { - pr_warn("mtrr: base or size exceeds the MTRR width\n"); + pr_warn("base or size exceeds the MTRR width\n"); return -EINVAL; } @@ -360,8 +361,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, } else if (types_compatible(type, ltype)) continue; } - pr_warn("mtrr: 0x%lx000,0x%lx000 overlaps existing" - " 0x%lx000,0x%lx000\n", base, size, lbase, + pr_warn("0x%lx000,0x%lx000 overlaps existing 0x%lx000,0x%lx000\n", base, size, lbase, lsize); goto out; } @@ -369,7 +369,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, if (ltype != type) { if (types_compatible(type, ltype)) continue; - pr_warn("mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n", + pr_warn("type mismatch for %lx000,%lx000 old: %s new: %s\n", base, size, mtrr_attrib_to_str(ltype), mtrr_attrib_to_str(type)); goto out; @@ -395,7 +395,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, } } } else { - pr_info("mtrr: no more MTRRs available\n"); + pr_info("no more MTRRs available\n"); } error = i; out: @@ -407,8 +407,8 @@ int mtrr_add_page(unsigned long base, unsigned long size, static int mtrr_check(unsigned long base, unsigned long size) { if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) { - pr_warn("mtrr: size and base must be multiples of 4 kiB\n"); - pr_debug("mtrr: size: 0x%lx base: 0x%lx\n", size, base); + pr_warn("size and base must be multiples of 4 kiB\n"); + pr_debug("size: 0x%lx base: 0x%lx\n", size, base); dump_stack(); return -1; } @@ -499,22 +499,22 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) } } if (reg < 0) { - pr_debug("mtrr: no MTRR for %lx000,%lx000 found\n", + pr_debug("no MTRR for %lx000,%lx000 found\n", base, size); goto out; } } if (reg >= max) { - pr_warn("mtrr: register: %d too big\n", reg); + pr_warn("register: %d too big\n", reg); goto out; } mtrr_if->get(reg, &lbase, &lsize, <ype); if (lsize < 1) { - pr_warn("mtrr: MTRR %d not used\n", reg); + pr_warn("MTRR %d not used\n", reg); goto out; } if (mtrr_usage_table[reg] < 1) { - pr_warn("mtrr: reg: %d has count=0\n", reg); + pr_warn("reg: %d has count=0\n", reg); goto out; } if (--mtrr_usage_table[reg] < 1) @@ -775,7 +775,7 @@ void __init mtrr_bp_init(void) } if (!mtrr_enabled()) { - pr_info("MTRR: Disabled\n"); + pr_info("Disabled\n"); /* * PAT initialization relies on MTRR's rendezvous handler. @@ -793,6 +793,9 @@ void mtrr_ap_init(void) if (!use_intel() || mtrr_aps_delayed_init) return; + + rcu_cpu_starting(smp_processor_id()); + /* * Ideally we should hold mtrr_mutex here to avoid mtrr entries * changed, but this routine will be called in cpu boot time, diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index d389083330c5..9556930cd8c1 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -46,6 +46,7 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) { /* returns the bit offset of the performance counter register */ switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_HYGON: case X86_VENDOR_AMD: if (msr >= MSR_F15H_PERF_CTR) return (msr - MSR_F15H_PERF_CTR) >> 1; @@ -74,6 +75,7 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) { /* returns the bit offset of the event selection register */ switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_HYGON: case X86_VENDOR_AMD: if (msr >= MSR_F15H_PERF_CTL) return (msr - MSR_F15H_PERF_CTL) >> 1; diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index b099024d339c..71ca064e3794 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -22,21 +22,13 @@ #define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) #define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff) -/* - * Check for extended topology enumeration cpuid leaf 0xb and if it - * exists, use it for populating initial_apicid and cpu topology - * detection. - */ -void detect_extended_topology(struct cpuinfo_x86 *c) +int detect_extended_topology_early(struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP - unsigned int eax, ebx, ecx, edx, sub_index; - unsigned int ht_mask_width, core_plus_mask_width; - unsigned int core_select_mask, core_level_siblings; - static bool printed; + unsigned int eax, ebx, ecx, edx; if (c->cpuid_level < 0xb) - return; + return -1; cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx); @@ -44,7 +36,7 @@ void detect_extended_topology(struct cpuinfo_x86 *c) * check if the cpuid leaf 0xb is actually implemented. */ if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) - return; + return -1; set_cpu_cap(c, X86_FEATURE_XTOPOLOGY); @@ -52,10 +44,30 @@ void detect_extended_topology(struct cpuinfo_x86 *c) * initial apic id, which also represents 32-bit extended x2apic id. */ c->initial_apicid = edx; + smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); +#endif + return 0; +} + +/* + * Check for extended topology enumeration cpuid leaf 0xb and if it + * exists, use it for populating initial_apicid and cpu topology + * detection. + */ +int detect_extended_topology(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + unsigned int eax, ebx, ecx, edx, sub_index; + unsigned int ht_mask_width, core_plus_mask_width; + unsigned int core_select_mask, core_level_siblings; + + if (detect_extended_topology_early(c) < 0) + return -1; /* * Populate HT related information from sub-leaf level 0. */ + cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx); core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); @@ -86,15 +98,6 @@ void detect_extended_topology(struct cpuinfo_x86 *c) c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); c->x86_max_cores = (core_level_siblings / smp_num_siblings); - - if (!printed) { - pr_info("CPU: Physical Processor ID: %d\n", - c->phys_proc_id); - if (c->x86_max_cores > 1) - pr_info("CPU: Processor Core ID: %d\n", - c->cpu_core_id); - printed = 1; - } - return; #endif + return 0; } diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 8e005329648b..0eda91f8eeac 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -77,7 +77,7 @@ static __init int setup_vmw_sched_clock(char *s) } early_param("no-vmw-sched-clock", setup_vmw_sched_clock); -static unsigned long long vmware_sched_clock(void) +static unsigned long long notrace vmware_sched_clock(void) { unsigned long long ns; @@ -97,14 +97,14 @@ static void __init vmware_sched_clock_setup(void) d->cyc2ns_offset = mul_u64_u32_shr(tsc_now, d->cyc2ns_mul, d->cyc2ns_shift); - pv_time_ops.sched_clock = vmware_sched_clock; + pv_ops.time.sched_clock = vmware_sched_clock; pr_info("using sched offset of %llu ns\n", d->cyc2ns_offset); } static void __init vmware_paravirt_ops_setup(void) { pv_info.name = "VMware hypervisor"; - pv_cpu_ops.io_delay = paravirt_nop; + pv_ops.cpu.io_delay = paravirt_nop; if (vmware_tsc_khz && vmw_sched_clock) vmware_sched_clock_setup(); |
