diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 913fd3a7bac6..ea33439a5d00 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -473,7 +473,9 @@ #define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */ #define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */ #define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */ -#define X86_FEATURE_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */ +#define X86_FEATURE_AMD_FAST_CPPC (21*32 + 5) /* Fast CPPC */ +#define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */ +#define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32 + 7) /* Workload Classification */ /* * BUG word(s) diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 1a42f829667a..6d7b04ffc5fd 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -177,10 +177,15 @@ #define INTEL_XEON_PHI_KNM IFM(6, 0x85) /* Knights Mill */ /* Family 5 */ -#define INTEL_FAM5_QUARK_X1000 0x09 /* Quark X1000 SoC */ #define INTEL_QUARK_X1000 IFM(5, 0x09) /* Quark X1000 SoC */ /* Family 19 */ #define INTEL_PANTHERCOVE_X IFM(19, 0x01) /* Diamond Rapids */ +/* CPU core types */ +enum intel_cpu_type { + INTEL_CPU_TYPE_ATOM = 0x20, + INTEL_CPU_TYPE_CORE = 0x40, +}; + #endif /* _ASM_X86_INTEL_FAMILY_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 4a686f0e5dbf..c0975815980c 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -105,6 +105,24 @@ struct cpuinfo_topology { // Cache level topology IDs u32 llc_id; u32 l2c_id; + + // Hardware defined CPU-type + union { + u32 cpu_type; + struct { + // CPUID.1A.EAX[23-0] + u32 intel_native_model_id :24; + // CPUID.1A.EAX[31-24] + u32 intel_type :8; + }; + struct { + // CPUID 0x80000026.EBX + u32 amd_num_processors :16, + amd_power_eff_ranking :8, + amd_native_model_id :4, + amd_type :4; + }; + }; }; struct cpuinfo_x86 { diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 92f3664dd933..fd41103ad342 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -114,6 +114,12 @@ enum x86_topology_domains { TOPO_MAX_DOMAIN, }; +enum x86_topology_cpu_type { + TOPO_CPU_TYPE_PERFORMANCE, + TOPO_CPU_TYPE_EFFICIENCY, + TOPO_CPU_TYPE_UNKNOWN, +}; + struct x86_topology_system { unsigned int dom_shifts[TOPO_MAX_DOMAIN]; unsigned int dom_size[TOPO_MAX_DOMAIN]; @@ -149,6 +155,9 @@ extern unsigned int __max_threads_per_core; extern unsigned int __num_threads_per_package; extern unsigned int __num_cores_per_package; +const char *get_topology_cpu_type_name(struct cpuinfo_x86 *c); +enum x86_topology_cpu_type get_topology_cpu_type(struct cpuinfo_x86 *c); + static inline unsigned int topology_max_packages(void) { return __max_logical_packages; diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index aab9d0570841..d745dd586303 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -239,8 +239,10 @@ EXPORT_SYMBOL_GPL(amd_detect_prefcore); */ int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator) { + enum x86_topology_cpu_type core_type = get_topology_cpu_type(&cpu_data(cpu)); bool prefcore; int ret; + u32 tmp; ret = amd_detect_prefcore(&prefcore); if (ret) @@ -266,6 +268,27 @@ int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator) break; } } + + /* detect if running on heterogeneous design */ + if (cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES)) { + switch (core_type) { + case TOPO_CPU_TYPE_UNKNOWN: + pr_warn("Undefined core type found for cpu %d\n", cpu); + break; + case TOPO_CPU_TYPE_PERFORMANCE: + /* use the max scale for performance cores */ + *numerator = CPPC_HIGHEST_PERF_PERFORMANCE; + return 0; + case TOPO_CPU_TYPE_EFFICIENCY: + /* use the highest perf value for efficiency cores */ + ret = amd_get_highest_perf(cpu, &tmp); + if (ret) + return ret; + *numerator = tmp; + return 0; + } + } + *numerator = CPPC_HIGHEST_PERF_PREFCORE; return 0; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f43bb974fc66..f7e5155f85dd 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1906,9 +1906,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) /* Init Machine Check Exception if available. */ mcheck_cpu_init(c); -#ifdef CONFIG_NUMA numa_add_cpu(smp_processor_id()); -#endif } /* diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c index 3baf3e435834..10719aba6276 100644 --- a/arch/x86/kernel/cpu/debugfs.c +++ b/arch/x86/kernel/cpu/debugfs.c @@ -22,6 +22,7 @@ static int cpu_debug_show(struct seq_file *m, void *p) seq_printf(m, "die_id: %u\n", c->topo.die_id); seq_printf(m, "cu_id: %u\n", c->topo.cu_id); seq_printf(m, "core_id: %u\n", c->topo.core_id); + seq_printf(m, "cpu_type: %s\n", get_topology_cpu_type_name(c)); seq_printf(m, "logical_pkg_id: %u\n", c->topo.logical_pkg_id); seq_printf(m, "logical_die_id: %u\n", c->topo.logical_die_id); seq_printf(m, "llc_id: %u\n", c->topo.llc_id); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index c84c30188fdf..16f3ca30626a 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -24,34 +24,36 @@ struct cpuid_bit { * levels are different and there is a separate entry for each. */ static const struct cpuid_bit cpuid_bits[] = { - { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, - { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, - { X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 }, - { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, - { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 }, - { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, - { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, - { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, - { X86_FEATURE_CQM_MBM_LOCAL, CPUID_EDX, 2, 0x0000000f, 1 }, - { X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 }, - { X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 }, - { X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 }, - { X86_FEATURE_CDP_L2, CPUID_ECX, 2, 0x00000010, 2 }, - { X86_FEATURE_MBA, CPUID_EBX, 3, 0x00000010, 0 }, - { X86_FEATURE_PER_THREAD_MBA, CPUID_ECX, 0, 0x00000010, 3 }, - { X86_FEATURE_SGX1, CPUID_EAX, 0, 0x00000012, 0 }, - { X86_FEATURE_SGX2, CPUID_EAX, 1, 0x00000012, 0 }, - { X86_FEATURE_SGX_EDECCSSA, CPUID_EAX, 11, 0x00000012, 0 }, - { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, - { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, - { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, - { X86_FEATURE_FAST_CPPC, CPUID_EDX, 15, 0x80000007, 0 }, - { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, - { X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 }, - { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, - { X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 }, - { X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 }, + { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, + { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, + { X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 }, + { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, + { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 }, + { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, + { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, + { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, + { X86_FEATURE_CQM_MBM_LOCAL, CPUID_EDX, 2, 0x0000000f, 1 }, + { X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 }, + { X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 }, + { X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 }, + { X86_FEATURE_CDP_L2, CPUID_ECX, 2, 0x00000010, 2 }, + { X86_FEATURE_MBA, CPUID_EBX, 3, 0x00000010, 0 }, + { X86_FEATURE_PER_THREAD_MBA, CPUID_ECX, 0, 0x00000010, 3 }, + { X86_FEATURE_SGX1, CPUID_EAX, 0, 0x00000012, 0 }, + { X86_FEATURE_SGX2, CPUID_EAX, 1, 0x00000012, 0 }, + { X86_FEATURE_SGX_EDECCSSA, CPUID_EAX, 11, 0x00000012, 0 }, + { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, + { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, + { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, + { X86_FEATURE_AMD_FAST_CPPC, CPUID_EDX, 15, 0x80000007, 0 }, + { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, + { X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 }, + { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, + { X86_FEATURE_AMD_WORKLOAD_CLASS, CPUID_EAX, 22, 0x80000021, 0 }, + { X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 }, + { X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 }, { X86_FEATURE_AMD_LBR_PMC_FREEZE, CPUID_EAX, 2, 0x80000022, 0 }, + { X86_FEATURE_AMD_HETEROGENEOUS_CORES, CPUID_EAX, 30, 0x80000026, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c index 7d476fa697ca..03b3c9c3a45e 100644 --- a/arch/x86/kernel/cpu/topology_amd.c +++ b/arch/x86/kernel/cpu/topology_amd.c @@ -182,6 +182,9 @@ static void parse_topology_amd(struct topo_scan *tscan) if (cpu_feature_enabled(X86_FEATURE_TOPOEXT)) has_topoext = cpu_parse_topology_ext(tscan); + if (cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES)) + tscan->c->topo.cpu_type = cpuid_ebx(0x80000026); + if (!has_topoext && !parse_8000_0008(tscan)) return; diff --git a/arch/x86/kernel/cpu/topology_common.c b/arch/x86/kernel/cpu/topology_common.c index 9a6069e7133c..8277c64f88db 100644 --- a/arch/x86/kernel/cpu/topology_common.c +++ b/arch/x86/kernel/cpu/topology_common.c @@ -3,6 +3,7 @@ #include +#include #include #include #include @@ -27,6 +28,36 @@ void topology_set_dom(struct topo_scan *tscan, enum x86_topology_domains dom, } } +enum x86_topology_cpu_type get_topology_cpu_type(struct cpuinfo_x86 *c) +{ + if (c->x86_vendor == X86_VENDOR_INTEL) { + switch (c->topo.intel_type) { + case INTEL_CPU_TYPE_ATOM: return TOPO_CPU_TYPE_EFFICIENCY; + case INTEL_CPU_TYPE_CORE: return TOPO_CPU_TYPE_PERFORMANCE; + } + } + if (c->x86_vendor == X86_VENDOR_AMD) { + switch (c->topo.amd_type) { + case 0: return TOPO_CPU_TYPE_PERFORMANCE; + case 1: return TOPO_CPU_TYPE_EFFICIENCY; + } + } + + return TOPO_CPU_TYPE_UNKNOWN; +} + +const char *get_topology_cpu_type_name(struct cpuinfo_x86 *c) +{ + switch (get_topology_cpu_type(c)) { + case TOPO_CPU_TYPE_PERFORMANCE: + return "performance"; + case TOPO_CPU_TYPE_EFFICIENCY: + return "efficiency"; + default: + return "unknown"; + } +} + static unsigned int __maybe_unused parse_num_cores_legacy(struct cpuinfo_x86 *c) { struct { @@ -87,6 +118,7 @@ static void parse_topology(struct topo_scan *tscan, bool early) .cu_id = 0xff, .llc_id = BAD_APICID, .l2c_id = BAD_APICID, + .cpu_type = TOPO_CPU_TYPE_UNKNOWN, }; struct cpuinfo_x86 *c = tscan->c; struct { @@ -132,6 +164,8 @@ static void parse_topology(struct topo_scan *tscan, bool early) case X86_VENDOR_INTEL: if (!IS_ENABLED(CONFIG_CPU_SUP_INTEL) || !cpu_parse_topology_ext(tscan)) parse_legacy(tscan); + if (c->cpuid_level >= 0x1a) + c->topo.cpu_type = cpuid_eax(0x1a); break; case X86_VENDOR_HYGON: if (IS_ENABLED(CONFIG_CPU_SUP_HYGON)) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 766f092dab80..b5a8f0891135 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -497,8 +497,9 @@ static int x86_cluster_flags(void) static int x86_die_flags(void) { - if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) - return x86_sched_itmt_flags(); + if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU) || + cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES)) + return x86_sched_itmt_flags(); return 0; } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index eb503f53c319..101725c149c4 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -263,28 +263,33 @@ static void __init probe_page_size_mask(void) } /* - * INVLPG may not properly flush Global entries - * on these CPUs when PCIDs are enabled. + * INVLPG may not properly flush Global entries on + * these CPUs. New microcode fixes the issue. */ static const struct x86_cpu_id invlpg_miss_ids[] = { - X86_MATCH_VFM(INTEL_ALDERLAKE, 0), - X86_MATCH_VFM(INTEL_ALDERLAKE_L, 0), - X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, 0), - X86_MATCH_VFM(INTEL_RAPTORLAKE, 0), - X86_MATCH_VFM(INTEL_RAPTORLAKE_P, 0), - X86_MATCH_VFM(INTEL_RAPTORLAKE_S, 0), + X86_MATCH_VFM(INTEL_ALDERLAKE, 0x2e), + X86_MATCH_VFM(INTEL_ALDERLAKE_L, 0x42c), + X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, 0x11), + X86_MATCH_VFM(INTEL_RAPTORLAKE, 0x118), + X86_MATCH_VFM(INTEL_RAPTORLAKE_P, 0x4117), + X86_MATCH_VFM(INTEL_RAPTORLAKE_S, 0x2e), {} }; static void setup_pcid(void) { + const struct x86_cpu_id *invlpg_miss_match; + if (!IS_ENABLED(CONFIG_X86_64)) return; if (!boot_cpu_has(X86_FEATURE_PCID)) return; - if (x86_match_cpu(invlpg_miss_ids)) { + invlpg_miss_match = x86_match_cpu(invlpg_miss_ids); + + if (invlpg_miss_match && + boot_cpu_data.microcode < invlpg_miss_match->driver_data) { pr_info("Incomplete global flushes, disabling PCID"); setup_clear_cpu_cap(X86_FEATURE_PCID); return; diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index f0cc00032751..846bf49f2508 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -656,8 +656,7 @@ static int qrk_capsule_setup_info(struct capsule_info *cap_info, void **pkbuff, } static const struct x86_cpu_id efi_capsule_quirk_ids[] = { - X86_MATCH_VENDOR_FAM_MODEL(INTEL, 5, INTEL_FAM5_QUARK_X1000, - &qrk_capsule_setup_info), + X86_MATCH_VFM(INTEL_QUARK_X1000, &qrk_capsule_setup_info), { } }; diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index d3d456925b2a..ee25b032c0b3 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -569,7 +569,7 @@ static void __init imr_fixup_memmap(struct imr_device *idev) } static const struct x86_cpu_id imr_ids[] __initconst = { - X86_MATCH_VENDOR_FAM_MODEL(INTEL, 5, INTEL_FAM5_QUARK_X1000, NULL), + X86_MATCH_VFM(INTEL_QUARK_X1000, NULL), {} }; diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c index 84ba715f44d1..657925b0f428 100644 --- a/arch/x86/platform/intel-quark/imr_selftest.c +++ b/arch/x86/platform/intel-quark/imr_selftest.c @@ -105,7 +105,7 @@ static void __init imr_self_test(void) } static const struct x86_cpu_id imr_ids[] __initconst = { - X86_MATCH_VENDOR_FAM_MODEL(INTEL, 5, INTEL_FAM5_QUARK_X1000, NULL), + X86_MATCH_VFM(INTEL_QUARK_X1000, NULL), {} }; diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index f834cc8205e2..d7630bab2516 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -850,7 +850,7 @@ static u32 amd_pstate_get_transition_delay_us(unsigned int cpu) transition_delay_ns = cppc_get_transition_latency(cpu); if (transition_delay_ns == CPUFREQ_ETERNAL) { - if (cpu_feature_enabled(X86_FEATURE_FAST_CPPC)) + if (cpu_feature_enabled(X86_FEATURE_AMD_FAST_CPPC)) return AMD_PSTATE_FAST_CPPC_TRANSITION_DELAY; else return AMD_PSTATE_TRANSITION_DELAY; diff --git a/drivers/thermal/intel/intel_quark_dts_thermal.c b/drivers/thermal/intel/intel_quark_dts_thermal.c index 47296a14db3c..89498eb29a89 100644 --- a/drivers/thermal/intel/intel_quark_dts_thermal.c +++ b/drivers/thermal/intel/intel_quark_dts_thermal.c @@ -401,7 +401,7 @@ static struct soc_sensor_entry *alloc_soc_dts(void) } static const struct x86_cpu_id qrk_thermal_ids[] __initconst = { - X86_MATCH_VENDOR_FAM_MODEL(INTEL, 5, INTEL_FAM5_QUARK_X1000, NULL), + X86_MATCH_VFM(INTEL_QUARK_X1000, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, qrk_thermal_ids); diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index dd4682857c12..23698d0f4bb4 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -472,7 +472,7 @@ #define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */ #define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */ #define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */ -#define X86_FEATURE_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */ +#define X86_FEATURE_AMD_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */ /* * BUG word(s)