- Add a feature flag which denotes AMD CPUs supporting workload classification

with the purpose of using such hints when making scheduling decisions
 
 - Determine the boost enumerator for each AMD core based on its type: efficiency
   or performance, in the cppc driver
 
 - Add the type of a CPU to the topology CPU descriptor with the goal of
   supporting and making decisions based on the type of the respective core
 
 - Add a feature flag to denote AMD cores which have heterogeneous topology and
   enable SD_ASYM_PACKING for those
 
 - Check microcode revisions before disabling PCID on Intel
 
 - Cleanups and fixlets
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmc7q0UACgkQEsHwGGHe
 VUq27Q//TADIn/rZj95OuWLYFXduOpzdyfF6BAOabRjUpIWTGJ5YdKjj1TCA2wUE
 6SiHZWQxQropB3NgeICcDT+3OGdGzE2qywzpXspUDsBPraWx+9CA56qREYafpRps
 88ZQZJWHla2/0kHN5oM4fYe05mWMLAFgIhG4tPH/7sj54Zqar40nhVksz3WjKAid
 yEfzbdVeRI5sNoujyHzGANXI0Fo98nAyi5Qj9kXL9W/UV1JmoQ78Rq7V9IIgOBsc
 l6Gv/h0CNtH9voqfrfUb07VHk8ZqSJ37xUnrnKdidncWGCWEAoZRr7wU+I9CHKIs
 tzdx+zq6JC3YN0IwsZCjk4me+BqVLJxW2oDgW7esPifye6ElyEo4T9UO9LEpE1qm
 ReAByoIMdSXWwXuITwy4NxLPKPCpU7RyJCiqFzpJp0g4qUq2cmlyERDirf6eknXL
 s+dmRaglEdcQT/EL+Y+vfFdQtLdwJmOu+nPPjjFxeRcIDB+u1sXJMEFbyvkLL6FE
 HOdNxL+5n/3M8Lbh77KIS5uCcjXL2VCkZK2/hyoifUb+JZR/ENoqYjElkMXOplyV
 KQIfcTzVCLRVvZApf/MMkTO86cpxMDs7YLYkgFxDsBjRdoq/Mzub8yzWn6kLZtmP
 ANNH4uYVtjrHE1nxJSA0JgYQlJKYeNU5yhLiTLKhHL5BwDYfiz8=
 =420r
 -----END PGP SIGNATURE-----

Merge tag 'x86_cpu_for_v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cpuid updates from Borislav Petkov:

 - Add a feature flag which denotes AMD CPUs supporting workload
   classification with the purpose of using such hints when making
   scheduling decisions

 - Determine the boost enumerator for each AMD core based on its type:
   efficiency or performance, in the cppc driver

 - Add the type of a CPU to the topology CPU descriptor with the goal of
   supporting and making decisions based on the type of the respective
   core

 - Add a feature flag to denote AMD cores which have heterogeneous
   topology and enable SD_ASYM_PACKING for those

 - Check microcode revisions before disabling PCID on Intel

 - Cleanups and fixlets

* tag 'x86_cpu_for_v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu: Remove redundant CONFIG_NUMA guard around numa_add_cpu()
  x86/cpu: Fix FAM5_QUARK_X1000 to use X86_MATCH_VFM()
  x86/cpu: Fix formatting of cpuid_bits[] in scattered.c
  x86/cpufeatures: Add X86_FEATURE_AMD_WORKLOAD_CLASS feature bit
  x86/amd: Use heterogeneous core topology for identifying boost numerator
  x86/cpu: Add CPU type to struct cpuinfo_topology
  x86/cpu: Enable SD_ASYM_PACKING for PKG domain on AMD
  x86/cpufeatures: Add X86_FEATURE_AMD_HETEROGENEOUS_CORES
  x86/cpufeatures: Rename X86_FEATURE_FAST_CPPC to have AMD prefix
  x86/mm: Don't disable PCID when INVLPG has been fixed by microcode

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)

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 */

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 {

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;

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;

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
 }
 
 /*

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);

arch/x86/kernel/cpu/scattered.c

@@ -45,13 +45,15 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ 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_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 }
 };
 

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;
 

arch/x86/kernel/cpu/topology_common.c

@@ -3,6 +3,7 @@
 
 #include <xen/xen.h>
 
+#include <asm/intel-family.h>
 #include <asm/apic.h>
 #include <asm/processor.h>
 #include <asm/smp.h>
@@ -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))

arch/x86/kernel/smpboot.c

@@ -497,7 +497,8 @@ static int x86_cluster_flags(void)
 
 static int x86_die_flags(void)
 {
-	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU) ||
+	    cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES))
 		return x86_sched_itmt_flags();
 
 	return 0;

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;

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),
 	{ }
 };
 

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),
 	{}
 };
 

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),
 	{}
 };
 

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;

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);

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)