Merge branch 'x86/cpu' into x86/core, to resolve conflicts

Conflicts: arch/x86/kernel/cpu/bugs.c Signed-off-by: Ingo Molnar <mingo@kernel.org>
2026-06-01 02:53:36 +02:00 · 2025-05-13 10:37:01 +02:00 · 2025-05-13 10:37:01 +02:00 · 2fb8414e64
commit 2fb8414e64
parent 821f82125c c1ab4ce3cb
54 changed files with 1721 additions and 1484 deletions
--- a/6
+++ b/6
@ -1097,7 +1097,7 @@ R:	Carlos Bilbao <carlos.bilbao@kernel.org>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	Documentation/arch/x86/amd_hsmp.rst
-F:	arch/x86/include/asm/amd_hsmp.h
+F:	arch/x86/include/asm/amd/hsmp.h
 F:	arch/x86/include/uapi/asm/amd_hsmp.h
 F:	drivers/platform/x86/amd/hsmp/

@ -1142,7 +1142,7 @@ M:	Mario Limonciello <mario.limonciello@amd.com>
 M:	Yazen Ghannam <yazen.ghannam@amd.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
-F:	arch/x86/include/asm/amd_node.h
+F:	arch/x86/include/asm/amd/node.h
 F:	arch/x86/kernel/amd_node.c

 AMD PDS CORE DRIVER
@ -26290,7 +26290,7 @@ R:	Ahmed S. Darwish <darwi@linutronix.de>
 L:	x86-cpuid@lists.linux.dev
 S:	Maintained
 W:	https://x86-cpuid.org
-F:	tools/arch/x86/kcpuid/cpuid.csv
+F:	tools/arch/x86/kcpuid/

 X86 ENTRY CODE
 M:	Andy Lutomirski <luto@kernel.org>
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@ -26,7 +26,7 @@ static u32 ibs_caps;
 #include <linux/hardirq.h>

 #include <asm/nmi.h>
-#include <asm/amd-ibs.h>
+#include <asm/amd/ibs.h>

 /* attr.config2 */
 #define IBS_SW_FILTER_MASK	1
--- a/arch/x86/include/asm/amd/hsmp.h
+++ b/arch/x86/include/asm/amd/hsmp.h
@ -1,5 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-
 #ifndef _ASM_X86_AMD_HSMP_H_
 #define _ASM_X86_AMD_HSMP_H_

@ -13,4 +12,5 @@ static inline int hsmp_send_message(struct hsmp_message *msg)
 	return -ENODEV;
 }
 #endif
+
 #endif /*_ASM_X86_AMD_HSMP_H_*/
--- a/arch/x86/include/asm/amd/ibs.h
+++ b/arch/x86/include/asm/amd/ibs.h
@ -1,4 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_AMD_IBS_H
+#define _ASM_X86_AMD_IBS_H
+
 /*
 * From PPR Vol 1 for AMD Family 19h Model 01h B1
 * 55898 Rev 0.35 - Feb 5, 2021
@ -151,3 +154,5 @@ struct perf_ibs_data {
 	};
 	u64		regs[MSR_AMD64_IBS_REG_COUNT_MAX];
 };
+
+#endif /* _ASM_X86_AMD_IBS_H */
--- a/arch/x86/include/asm/amd/nb.h
+++ b/arch/x86/include/asm/amd/nb.h
@ -4,7 +4,7 @@

 #include <linux/ioport.h>
 #include <linux/pci.h>
-#include <asm/amd_node.h>
+#include <asm/amd/node.h>

 struct amd_nb_bus_dev_range {
 	u8 bus;
--- a/arch/x86/include/asm/amd/node.h
+++ b/arch/x86/include/asm/amd/node.h
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@ -476,11 +476,11 @@
 #define X86_FEATURE_CLEAR_BHB_LOOP	(21*32+ 1) /* Clear branch history at syscall entry using SW loop */
 #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_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 */
-#define X86_FEATURE_PREFER_YMM		(21*32 + 8) /* Avoid ZMM registers due to downclocking */
+#define X86_FEATURE_CLEAR_BHB_VMEXIT	(21*32+ 4) /* Clear branch history at vmexit using SW loop */
+#define X86_FEATURE_AMD_FAST_CPPC	(21*32+ 5) /* Fast CPPC */
+#define X86_FEATURE_AMD_HTR_CORES	(21*32+ 6) /* Heterogeneous Core Topology */
+#define X86_FEATURE_AMD_WORKLOAD_CLASS	(21*32+ 7) /* Workload Classification */
+#define X86_FEATURE_PREFER_YMM		(21*32+ 8) /* Avoid ZMM registers due to downclocking */

 /*
 * BUG word(s)
@ -519,7 +519,7 @@
 #define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* "itlb_multihit" CPU may incur MCE during certain page attribute changes */
 #define X86_BUG_SRBDS			X86_BUG(24) /* "srbds" CPU may leak RNG bits if not mitigated */
 #define X86_BUG_MMIO_STALE_DATA		X86_BUG(25) /* "mmio_stale_data" CPU is affected by Processor MMIO Stale Data vulnerabilities */
-#define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) /* "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */
+/* unused, was #define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */
 #define X86_BUG_RETBLEED		X86_BUG(27) /* "retbleed" CPU is affected by RETBleed */
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* "eibrs_pbrsb" EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* "smt_rsb" CPU is vulnerable to Cross-Thread Return Address Predictions */
@ -527,10 +527,10 @@
 #define X86_BUG_TDX_PW_MCE		X86_BUG(31) /* "tdx_pw_mce" CPU may incur #MC if non-TD software does partial write to TDX private memory */

 /* BUG word 2 */
-#define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* "srso" AMD SRSO bug */
-#define X86_BUG_DIV0			X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */
-#define X86_BUG_RFDS			X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
-#define X86_BUG_BHI			X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
-#define X86_BUG_IBPB_NO_RET	   	X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
-#define X86_BUG_SPECTRE_V2_USER		X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
+#define X86_BUG_SRSO			X86_BUG( 1*32+ 0) /* "srso" AMD SRSO bug */
+#define X86_BUG_DIV0			X86_BUG( 1*32+ 1) /* "div0" AMD DIV0 speculation bug */
+#define X86_BUG_RFDS			X86_BUG( 1*32+ 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
+#define X86_BUG_BHI			X86_BUG( 1*32+ 3) /* "bhi" CPU is affected by Branch History Injection */
+#define X86_BUG_IBPB_NO_RET		X86_BUG( 1*32+ 4) /* "ibpb_no_ret" IBPB omits return target predictions */
+#define X86_BUG_SPECTRE_V2_USER		X86_BUG( 1*32+ 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
 #endif /* _ASM_X86_CPUFEATURES_H */
--- a/arch/x86/include/asm/cpuid.h
+++ b/arch/x86/include/asm/cpuid.h
@ -4,5 +4,6 @@
 #define _ASM_X86_CPUID_H

 #include <asm/cpuid/api.h>
+#include <asm/cpuid/leaf_0x2_api.h>

 #endif /* _ASM_X86_CPUID_H */
--- a/arch/x86/include/asm/cpuid/api.h
+++ b/arch/x86/include/asm/cpuid/api.h
@ -36,9 +36,9 @@ static inline void native_cpuid(u32 *eax, u32 *ebx,
 }

 #define NATIVE_CPUID_REG(reg)					\
-static inline u32 native_cpuid_##reg(u32 op)	\
+static inline u32 native_cpuid_##reg(u32 op)			\
 {								\
-	u32 eax = op, ebx, ecx = 0, edx;		\
+	u32 eax = op, ebx, ecx = 0, edx;			\
 								\
 	native_cpuid(&eax, &ebx, &ecx, &edx);			\
 								\
@ -207,4 +207,13 @@ static inline u32 hypervisor_cpuid_base(const char *sig, u32 leaves)
 	return 0;
 }

+/*
+ * CPUID(0x80000006) parsing helpers
+ */
+
+static inline bool cpuid_amd_hygon_has_l3_cache(void)
+{
+	return cpuid_edx(0x80000006);
+}
+
 #endif /* _ASM_X86_CPUID_API_H */
--- a/arch/x86/include/asm/cpuid/leaf_0x2_api.h
+++ b/arch/x86/include/asm/cpuid/leaf_0x2_api.h
@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_CPUID_LEAF_0x2_API_H
+#define _ASM_X86_CPUID_LEAF_0x2_API_H
+
+#include <asm/cpuid/api.h>
+#include <asm/cpuid/types.h>
+
+/**
+ * cpuid_get_leaf_0x2_regs() - Return sanitized leaf 0x2 register output
+ * @regs:	Output parameter
+ *
+ * Query CPUID leaf 0x2 and store its output in @regs.	Force set any
+ * invalid 1-byte descriptor returned by the hardware to zero (the NULL
+ * cache/TLB descriptor) before returning it to the caller.
+ *
+ * Use for_each_leaf_0x2_entry() to iterate over the register output in
+ * parsed form.
+ */
+static inline void cpuid_get_leaf_0x2_regs(union leaf_0x2_regs *regs)
+{
+	cpuid_leaf(0x2, regs);
+
+	/*
+	 * All Intel CPUs must report an iteration count of 1.	In case
+	 * of bogus hardware, treat all returned descriptors as NULL.
+	 */
+	if (regs->desc[0] != 0x01) {
+		for (int i = 0; i < 4; i++)
+			regs->regv[i] = 0;
+		return;
+	}
+
+	/*
+	 * The most significant bit (MSB) of each register must be clear.
+	 * If a register is invalid, replace its descriptors with NULL.
+	 */
+	for (int i = 0; i < 4; i++) {
+		if (regs->reg[i].invalid)
+			regs->regv[i] = 0;
+	}
+}
+
+/**
+ * for_each_leaf_0x2_entry() - Iterator for parsed leaf 0x2 descriptors
+ * @regs:   Leaf 0x2 register output, returned by cpuid_get_leaf_0x2_regs()
+ * @__ptr:  u8 pointer, for macro internal use only
+ * @entry:  Pointer to parsed descriptor information at each iteration
+ *
+ * Loop over the 1-byte descriptors in the passed leaf 0x2 output registers
+ * @regs.  Provide the parsed information for each descriptor through @entry.
+ *
+ * To handle cache-specific descriptors, switch on @entry->c_type.  For TLB
+ * descriptors, switch on @entry->t_type.
+ *
+ * Example usage for cache descriptors::
+ *
+ *	const struct leaf_0x2_table *entry;
+ *	union leaf_0x2_regs regs;
+ *	u8 *ptr;
+ *
+ *	cpuid_get_leaf_0x2_regs(&regs);
+ *	for_each_leaf_0x2_entry(regs, ptr, entry) {
+ *		switch (entry->c_type) {
+ *			...
+ *		}
+ *	}
+ */
+#define for_each_leaf_0x2_entry(regs, __ptr, entry)				\
+	for (__ptr = &(regs).desc[1];						\
+	     __ptr < &(regs).desc[16] && (entry = &cpuid_0x2_table[*__ptr]);	\
+	     __ptr++)
+
+#endif /* _ASM_X86_CPUID_LEAF_0x2_API_H */
--- a/arch/x86/include/asm/cpuid/types.h
+++ b/arch/x86/include/asm/cpuid/types.h
@ -2,6 +2,7 @@
 #ifndef _ASM_X86_CPUID_TYPES_H
 #define _ASM_X86_CPUID_TYPES_H

+#include <linux/build_bug.h>
 #include <linux/types.h>

 /*
@ -29,4 +30,99 @@ enum cpuid_regs_idx {
 #define CPUID_LEAF_FREQ		0x16
 #define CPUID_LEAF_TILE		0x1d

+/*
+ * Types for CPUID(0x2) parsing
+ * Check <asm/cpuid/leaf_0x2_api.h>
+ */
+
+struct leaf_0x2_reg {
+		u32		: 31,
+			invalid	: 1;
+};
+
+union leaf_0x2_regs {
+	struct leaf_0x2_reg	reg[4];
+	u32			regv[4];
+	u8			desc[16];
+};
+
+/*
+ * Leaf 0x2 1-byte descriptors' cache types
+ * To be used for their mappings at cpuid_0x2_table[]
+ *
+ * Start at 1 since type 0 is reserved for HW byte descriptors which are
+ * not recognized by the kernel; i.e., those without an explicit mapping.
+ */
+enum _cache_table_type {
+	CACHE_L1_INST		= 1,
+	CACHE_L1_DATA,
+	CACHE_L2,
+	CACHE_L3
+	/* Adjust __TLB_TABLE_TYPE_BEGIN before adding more types */
+} __packed;
+#ifndef __CHECKER__
+static_assert(sizeof(enum _cache_table_type) == 1);
+#endif
+
+/*
+ * Ensure that leaf 0x2 cache and TLB type values do not intersect,
+ * since they share the same type field at struct cpuid_0x2_table.
+ */
+#define __TLB_TABLE_TYPE_BEGIN		(CACHE_L3 + 1)
+
+/*
+ * Leaf 0x2 1-byte descriptors' TLB types
+ * To be used for their mappings at cpuid_0x2_table[]
+ */
+enum _tlb_table_type {
+	TLB_INST_4K		= __TLB_TABLE_TYPE_BEGIN,
+	TLB_INST_4M,
+	TLB_INST_2M_4M,
+	TLB_INST_ALL,
+
+	TLB_DATA_4K,
+	TLB_DATA_4M,
+	TLB_DATA_2M_4M,
+	TLB_DATA_4K_4M,
+	TLB_DATA_1G,
+	TLB_DATA_1G_2M_4M,
+
+	TLB_DATA0_4K,
+	TLB_DATA0_4M,
+	TLB_DATA0_2M_4M,
+
+	STLB_4K,
+	STLB_4K_2M,
+} __packed;
+#ifndef __CHECKER__
+static_assert(sizeof(enum _tlb_table_type) == 1);
+#endif
+
+/*
+ * Combined parsing table for leaf 0x2 cache and TLB descriptors.
+ */
+
+struct leaf_0x2_table {
+	union {
+		enum _cache_table_type	c_type;
+		enum _tlb_table_type	t_type;
+	};
+	union {
+		short			c_size;
+		short			entries;
+	};
+};
+
+extern const struct leaf_0x2_table cpuid_0x2_table[256];
+
+/*
+ * All of leaf 0x2's one-byte TLB descriptors implies the same number of entries
+ * for their respective TLB types.  TLB descriptor 0x63 is an exception: it
+ * implies 4 dTLB entries for 1GB pages and 32 dTLB entries for 2MB or 4MB pages.
+ *
+ * Encode that descriptor's dTLB entry count for 2MB/4MB pages here, as the entry
+ * count for dTLB 1GB pages is already encoded at the cpuid_0x2_table[]'s mapping.
+ */
+#define TLB_0x63_2M_4M_ENTRIES		32
+
 #endif /* _ASM_X86_CPUID_TYPES_H */
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@ -327,7 +327,7 @@
 .endm

 .macro CLEAR_BRANCH_HISTORY_VMEXIT
-	ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT
+	ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_VMEXIT
 .endm
 #else
 #define CLEAR_BRANCH_HISTORY
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@ -272,7 +272,7 @@ int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
 	}

 	/* detect if running on heterogeneous design */
-	if (cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES)) {
+	if (cpu_feature_enabled(X86_FEATURE_AMD_HTR_CORES)) {
 		switch (core_type) {
 		case TOPO_CPU_TYPE_UNKNOWN:
 			pr_warn("Undefined core type found for cpu %d\n", cpu);
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@ -39,7 +39,7 @@
 #include <asm/gart.h>
 #include <asm/set_memory.h>
 #include <asm/dma.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 #include <asm/x86_init.h>

 static unsigned long iommu_bus_base;	/* GART remapping area (physical) */
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@ -13,7 +13,9 @@
 #include <linux/export.h>
 #include <linux/spinlock.h>
 #include <linux/pci_ids.h>
-#include <asm/amd_nb.h>
+
+#include <asm/amd/nb.h>
+#include <asm/cpuid.h>

 static u32 *flush_words;

@ -91,10 +93,7 @@ static int amd_cache_northbridges(void)
 	if (amd_gart_present())
 		amd_northbridges.flags |= AMD_NB_GART;

-	/*
-	 * Check for L3 cache presence.
-	 */
-	if (!cpuid_edx(0x80000006))
+	if (!cpuid_amd_hygon_has_l3_cache())
 		return 0;

 	/*
--- a/arch/x86/kernel/amd_node.c
+++ b/arch/x86/kernel/amd_node.c
@ -9,7 +9,7 @@
 */

 #include <linux/debugfs.h>
-#include <asm/amd_node.h>
+#include <asm/amd/node.h>

 /*
 * AMD Nodes are a physical collection of I/O devices within an SoC. There can be one
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@ -29,7 +29,7 @@
 #include <asm/gart.h>
 #include <asm/pci-direct.h>
 #include <asm/dma.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 #include <asm/x86_init.h>
 #include <linux/crash_dump.h>

--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@ -24,7 +24,7 @@ obj-y			+= rdrand.o
 obj-y			+= match.o
 obj-y			+= bugs.o
 obj-y			+= aperfmperf.o
-obj-y			+= cpuid-deps.o
+obj-y			+= cpuid-deps.o cpuid_0x2_table.o
 obj-y			+= umwait.o
 obj-y 			+= capflags.o powerflags.o

@ -38,6 +38,9 @@ obj-y					+= intel.o tsx.o
 obj-$(CONFIG_PM)			+= intel_epb.o
 endif
 obj-$(CONFIG_CPU_SUP_AMD)		+= amd.o
+ifeq ($(CONFIG_AMD_NB)$(CONFIG_SYSFS),yy)
+obj-y					+= amd_cache_disable.o
+endif
 obj-$(CONFIG_CPU_SUP_HYGON)		+= hygon.o
 obj-$(CONFIG_CPU_SUP_CYRIX_32)		+= cyrix.o
 obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
--- a/arch/x86/kernel/cpu/amd_cache_disable.c
+++ b/arch/x86/kernel/cpu/amd_cache_disable.c
@ -0,0 +1,301 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD L3 cache_disable_{0,1} sysfs handling
+ * Documentation/ABI/testing/sysfs-devices-system-cpu
+ */
+
+#include <linux/cacheinfo.h>
+#include <linux/capability.h>
+#include <linux/pci.h>
+#include <linux/sysfs.h>
+
+#include <asm/amd/nb.h>
+
+#include "cpu.h"
+
+/*
+ * L3 cache descriptors
+ */
+static void amd_calc_l3_indices(struct amd_northbridge *nb)
+{
+	struct amd_l3_cache *l3 = &nb->l3_cache;
+	unsigned int sc0, sc1, sc2, sc3;
+	u32 val = 0;
+
+	pci_read_config_dword(nb->misc, 0x1C4, &val);
+
+	/* calculate subcache sizes */
+	l3->subcaches[0] = sc0 = !(val & BIT(0));
+	l3->subcaches[1] = sc1 = !(val & BIT(4));
+
+	if (boot_cpu_data.x86 == 0x15) {
+		l3->subcaches[0] = sc0 += !(val & BIT(1));
+		l3->subcaches[1] = sc1 += !(val & BIT(5));
+	}
+
+	l3->subcaches[2] = sc2 = !(val & BIT(8))  + !(val & BIT(9));
+	l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
+
+	l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
+}
+
+/*
+ * check whether a slot used for disabling an L3 index is occupied.
+ * @l3: L3 cache descriptor
+ * @slot: slot number (0..1)
+ *
+ * @returns: the disabled index if used or negative value if slot free.
+ */
+static int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned int slot)
+{
+	unsigned int reg = 0;
+
+	pci_read_config_dword(nb->misc, 0x1BC + slot * 4, &reg);
+
+	/* check whether this slot is activated already */
+	if (reg & (3UL << 30))
+		return reg & 0xfff;
+
+	return -1;
+}
+
+static ssize_t show_cache_disable(struct cacheinfo *ci, char *buf, unsigned int slot)
+{
+	int index;
+	struct amd_northbridge *nb = ci->priv;
+
+	index = amd_get_l3_disable_slot(nb, slot);
+	if (index >= 0)
+		return sysfs_emit(buf, "%d\n", index);
+
+	return sysfs_emit(buf, "FREE\n");
+}
+
+#define SHOW_CACHE_DISABLE(slot)					\
+static ssize_t								\
+cache_disable_##slot##_show(struct device *dev,				\
+			    struct device_attribute *attr, char *buf)	\
+{									\
+	struct cacheinfo *ci = dev_get_drvdata(dev);			\
+	return show_cache_disable(ci, buf, slot);			\
+}
+
+SHOW_CACHE_DISABLE(0)
+SHOW_CACHE_DISABLE(1)
+
+static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu,
+				 unsigned int slot, unsigned long idx)
+{
+	int i;
+
+	idx |= BIT(30);
+
+	/*
+	 *  disable index in all 4 subcaches
+	 */
+	for (i = 0; i < 4; i++) {
+		u32 reg = idx | (i << 20);
+
+		if (!nb->l3_cache.subcaches[i])
+			continue;
+
+		pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
+
+		/*
+		 * We need to WBINVD on a core on the node containing the L3
+		 * cache which indices we disable therefore a simple wbinvd()
+		 * is not sufficient.
+		 */
+		wbinvd_on_cpu(cpu);
+
+		reg |= BIT(31);
+		pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
+	}
+}
+
+/*
+ * disable a L3 cache index by using a disable-slot
+ *
+ * @l3:    L3 cache descriptor
+ * @cpu:   A CPU on the node containing the L3 cache
+ * @slot:  slot number (0..1)
+ * @index: index to disable
+ *
+ * @return: 0 on success, error status on failure
+ */
+static int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu,
+				   unsigned int slot, unsigned long index)
+{
+	int ret = 0;
+
+	/*  check if @slot is already used or the index is already disabled */
+	ret = amd_get_l3_disable_slot(nb, slot);
+	if (ret >= 0)
+		return -EEXIST;
+
+	if (index > nb->l3_cache.indices)
+		return -EINVAL;
+
+	/* check whether the other slot has disabled the same index already */
+	if (index == amd_get_l3_disable_slot(nb, !slot))
+		return -EEXIST;
+
+	amd_l3_disable_index(nb, cpu, slot, index);
+
+	return 0;
+}
+
+static ssize_t store_cache_disable(struct cacheinfo *ci, const char *buf,
+				   size_t count, unsigned int slot)
+{
+	struct amd_northbridge *nb = ci->priv;
+	unsigned long val = 0;
+	int cpu, err = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	cpu = cpumask_first(&ci->shared_cpu_map);
+
+	if (kstrtoul(buf, 10, &val) < 0)
+		return -EINVAL;
+
+	err = amd_set_l3_disable_slot(nb, cpu, slot, val);
+	if (err) {
+		if (err == -EEXIST)
+			pr_warn("L3 slot %d in use/index already disabled!\n",
+				   slot);
+		return err;
+	}
+	return count;
+}
+
+#define STORE_CACHE_DISABLE(slot)					\
+static ssize_t								\
+cache_disable_##slot##_store(struct device *dev,			\
+			     struct device_attribute *attr,		\
+			     const char *buf, size_t count)		\
+{									\
+	struct cacheinfo *ci = dev_get_drvdata(dev);			\
+	return store_cache_disable(ci, buf, count, slot);		\
+}
+
+STORE_CACHE_DISABLE(0)
+STORE_CACHE_DISABLE(1)
+
+static ssize_t subcaches_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	struct cacheinfo *ci = dev_get_drvdata(dev);
+	int cpu = cpumask_first(&ci->shared_cpu_map);
+
+	return sysfs_emit(buf, "%x\n", amd_get_subcaches(cpu));
+}
+
+static ssize_t subcaches_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count)
+{
+	struct cacheinfo *ci = dev_get_drvdata(dev);
+	int cpu = cpumask_first(&ci->shared_cpu_map);
+	unsigned long val;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (kstrtoul(buf, 16, &val) < 0)
+		return -EINVAL;
+
+	if (amd_set_subcaches(cpu, val))
+		return -EINVAL;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(cache_disable_0);
+static DEVICE_ATTR_RW(cache_disable_1);
+static DEVICE_ATTR_RW(subcaches);
+
+static umode_t cache_private_attrs_is_visible(struct kobject *kobj,
+					      struct attribute *attr, int unused)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cacheinfo *ci = dev_get_drvdata(dev);
+	umode_t mode = attr->mode;
+
+	if (!ci->priv)
+		return 0;
+
+	if ((attr == &dev_attr_subcaches.attr) &&
+	    amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+		return mode;
+
+	if ((attr == &dev_attr_cache_disable_0.attr ||
+	     attr == &dev_attr_cache_disable_1.attr) &&
+	    amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+		return mode;
+
+	return 0;
+}
+
+static struct attribute_group cache_private_group = {
+	.is_visible = cache_private_attrs_is_visible,
+};
+
+static void init_amd_l3_attrs(void)
+{
+	static struct attribute **amd_l3_attrs;
+	int n = 1;
+
+	if (amd_l3_attrs) /* already initialized */
+		return;
+
+	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+		n += 2;
+	if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+		n += 1;
+
+	amd_l3_attrs = kcalloc(n, sizeof(*amd_l3_attrs), GFP_KERNEL);
+	if (!amd_l3_attrs)
+		return;
+
+	n = 0;
+	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) {
+		amd_l3_attrs[n++] = &dev_attr_cache_disable_0.attr;
+		amd_l3_attrs[n++] = &dev_attr_cache_disable_1.attr;
+	}
+	if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+		amd_l3_attrs[n++] = &dev_attr_subcaches.attr;
+
+	cache_private_group.attrs = amd_l3_attrs;
+}
+
+const struct attribute_group *cache_get_priv_group(struct cacheinfo *ci)
+{
+	struct amd_northbridge *nb = ci->priv;
+
+	if (ci->level < 3 || !nb)
+		return NULL;
+
+	if (nb && nb->l3_cache.indices)
+		init_amd_l3_attrs();
+
+	return &cache_private_group;
+}
+
+struct amd_northbridge *amd_init_l3_cache(int index)
+{
+	struct amd_northbridge *nb;
+	int node;
+
+	/* only for L3, and not in virtualized environments */
+	if (index < 3)
+		return NULL;
+
+	node = topology_amd_node_id(smp_processor_id());
+	nb = node_to_amd_nb(node);
+	if (nb && !nb->l3_cache.indices)
+		amd_calc_l3_indices(nb);
+
+	return nb;
+}
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@ -551,7 +551,6 @@ static const char * const mmio_strings[] = {
 static void __init mmio_select_mitigation(void)
 {
 	if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) ||
-	     boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) ||
 	     cpu_mitigations_off()) {
 		mmio_mitigation = MMIO_MITIGATION_OFF;
 		return;
@ -1880,13 +1879,13 @@ static void __init bhi_apply_mitigation(void)

 	if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) {
 		pr_info("Spectre BHI mitigation: SW BHB clearing on VM exit only\n");
-		setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_VMEXIT);
 		return;
 	}

 	pr_info("Spectre BHI mitigation: SW BHB clearing on syscall and VM exit\n");
 	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP);
-	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_VMEXIT);
 }

 static void __init spectre_v2_select_mitigation(void)
@ -2947,9 +2946,6 @@ static ssize_t tsx_async_abort_show_state(char *buf)

 static ssize_t mmio_stale_data_show_state(char *buf)
 {
-	if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
-		return sysfs_emit(buf, "Unknown: No mitigations\n");
-
 	if (mmio_mitigation == MMIO_MITIGATION_OFF)
 		return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]);

@ -3025,7 +3021,7 @@ static const char *spectre_bhi_state(void)
 		 !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) &&
 		 rrsba_disabled)
 		return "; BHI: Retpoline";
-	else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT))
+	else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_VMEXIT))
 		return "; BHI: Vulnerable, KVM: SW loop";

 	return "; BHI: Vulnerable";
@ -3134,7 +3130,6 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 		return srbds_show_state(buf);

 	case X86_BUG_MMIO_STALE_DATA:
-	case X86_BUG_MMIO_UNKNOWN:
 		return mmio_stale_data_show_state(buf);

 	case X86_BUG_RETBLEED:
@ -3203,10 +3198,7 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *

 ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
-		return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_UNKNOWN);
-	else
-		return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
+	return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
 }

 ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf)
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@ -1006,17 +1006,18 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_D_1_EAX] = eax;
 	}

-	/* AMD-defined flags: level 0x80000001 */
+	/*
+	 * Check if extended CPUID leaves are implemented: Max extended
+	 * CPUID leaf must be in the 0x80000001-0x8000ffff range.
+	 */
 	eax = cpuid_eax(0x80000000);
-	c->extended_cpuid_level = eax;
+	c->extended_cpuid_level = ((eax & 0xffff0000) == 0x80000000) ? eax : 0;

-	if ((eax & 0xffff0000) == 0x80000000) {
-		if (eax >= 0x80000001) {
-			cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
+	if (c->extended_cpuid_level >= 0x80000001) {
+		cpuid(0x80000001, &eax, &ebx, &ecx, &edx);

-			c->x86_capability[CPUID_8000_0001_ECX] = ecx;
-			c->x86_capability[CPUID_8000_0001_EDX] = edx;
-		}
+		c->x86_capability[CPUID_8000_0001_ECX] = ecx;
+		c->x86_capability[CPUID_8000_0001_EDX] = edx;
 	}

 	if (c->extended_cpuid_level >= 0x80000007) {
@ -1403,15 +1404,10 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	 * Affected CPU list is generally enough to enumerate the vulnerability,
 	 * but for virtualization case check for ARCH_CAP MSR bits also, VMM may
 	 * not want the guest to enumerate the bug.
-	 *
-	 * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist,
-	 * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits.
 	 */
 	if (!arch_cap_mmio_immune(x86_arch_cap_msr)) {
 		if (cpu_matches(cpu_vuln_blacklist, MMIO))
 			setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
-		else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO))
-			setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN);
 	}

 	if (!cpu_has(c, X86_FEATURE_BTC_NO)) {
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@ -75,6 +75,15 @@ extern void check_null_seg_clears_base(struct cpuinfo_x86 *c);
 void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id);
 void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c);

+#if defined(CONFIG_AMD_NB) && defined(CONFIG_SYSFS)
+struct amd_northbridge *amd_init_l3_cache(int index);
+#else
+static inline struct amd_northbridge *amd_init_l3_cache(int index)
+{
+	return NULL;
+}
+#endif
+
 unsigned int aperfmperf_get_khz(int cpu);
 void cpu_select_mitigations(void);

--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@ -82,8 +82,12 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_XFD,			X86_FEATURE_XSAVES    },
 	{ X86_FEATURE_XFD,			X86_FEATURE_XGETBV1   },
 	{ X86_FEATURE_AMX_TILE,			X86_FEATURE_XFD       },
+	{ X86_FEATURE_AMX_FP16,			X86_FEATURE_AMX_TILE  },
+	{ X86_FEATURE_AMX_BF16,			X86_FEATURE_AMX_TILE  },
+	{ X86_FEATURE_AMX_INT8,			X86_FEATURE_AMX_TILE  },
 	{ X86_FEATURE_SHSTK,			X86_FEATURE_XSAVES    },
 	{ X86_FEATURE_FRED,			X86_FEATURE_LKGS      },
+	{ X86_FEATURE_SPEC_CTRL_SSBD,		X86_FEATURE_SPEC_CTRL },
 	{}
 };

--- a/arch/x86/kernel/cpu/cpuid_0x2_table.c
+++ b/arch/x86/kernel/cpu/cpuid_0x2_table.c
@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/sizes.h>
+
+#include <asm/cpuid/types.h>
+
+#include "cpu.h"
+
+#define CACHE_ENTRY(_desc, _type, _size)	\
+	[_desc] = {				\
+		.c_type = (_type),		\
+		.c_size = (_size) / SZ_1K,	\
+	}
+
+#define TLB_ENTRY(_desc, _type, _entries)	\
+	[_desc] = {				\
+		.t_type = (_type),		\
+		.entries = (_entries),		\
+	}
+
+const struct leaf_0x2_table cpuid_0x2_table[256] = {
+	CACHE_ENTRY(0x06, CACHE_L1_INST,	SZ_8K	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x08, CACHE_L1_INST,	SZ_16K	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x09, CACHE_L1_INST,	SZ_32K	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x0a, CACHE_L1_DATA,	SZ_8K	),	/* 2 way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x0c, CACHE_L1_DATA,	SZ_16K	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x0d, CACHE_L1_DATA,	SZ_16K	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x0e, CACHE_L1_DATA,	SZ_24K	),	/* 6-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x21, CACHE_L2,		SZ_256K	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x22, CACHE_L3,		SZ_512K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x23, CACHE_L3,		SZ_1M	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x25, CACHE_L3,		SZ_2M	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x29, CACHE_L3,		SZ_4M	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x2c, CACHE_L1_DATA,	SZ_32K	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x30, CACHE_L1_INST,	SZ_32K	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x39, CACHE_L2,		SZ_128K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x3a, CACHE_L2,		SZ_192K	),	/* 6-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x3b, CACHE_L2,		SZ_128K	),	/* 2-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x3c, CACHE_L2,		SZ_256K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x3d, CACHE_L2,		SZ_384K	),	/* 6-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x3e, CACHE_L2,		SZ_512K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x3f, CACHE_L2,		SZ_256K	),	/* 2-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x41, CACHE_L2,		SZ_128K	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x42, CACHE_L2,		SZ_256K	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x43, CACHE_L2,		SZ_512K	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x44, CACHE_L2,		SZ_1M	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x45, CACHE_L2,		SZ_2M	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x46, CACHE_L3,		SZ_4M	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x47, CACHE_L3,		SZ_8M	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x48, CACHE_L2,		SZ_3M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x49, CACHE_L3,		SZ_4M	),	/* 16-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x4a, CACHE_L3,		SZ_6M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x4b, CACHE_L3,		SZ_8M	),	/* 16-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x4c, CACHE_L3,		SZ_12M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x4d, CACHE_L3,		SZ_16M	),	/* 16-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x4e, CACHE_L2,		SZ_6M	),	/* 24-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x60, CACHE_L1_DATA,	SZ_16K	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x66, CACHE_L1_DATA,	SZ_8K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x67, CACHE_L1_DATA,	SZ_16K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x68, CACHE_L1_DATA,	SZ_32K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x78, CACHE_L2,		SZ_1M	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x79, CACHE_L2,		SZ_128K	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x7a, CACHE_L2,		SZ_256K	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x7b, CACHE_L2,		SZ_512K	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x7c, CACHE_L2,		SZ_1M	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x7d, CACHE_L2,		SZ_2M	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x7f, CACHE_L2,		SZ_512K	),	/* 2-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x80, CACHE_L2,		SZ_512K	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x82, CACHE_L2,		SZ_256K	),	/* 8-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x83, CACHE_L2,		SZ_512K	),	/* 8-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x84, CACHE_L2,		SZ_1M	),	/* 8-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x85, CACHE_L2,		SZ_2M	),	/* 8-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x86, CACHE_L2,		SZ_512K	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x87, CACHE_L2,		SZ_1M	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xd0, CACHE_L3,		SZ_512K	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xd1, CACHE_L3,		SZ_1M	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xd2, CACHE_L3,		SZ_2M	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xd6, CACHE_L3,		SZ_1M	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xd7, CACHE_L3,		SZ_2M	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xd8, CACHE_L3,		SZ_4M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xdc, CACHE_L3,		SZ_2M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xdd, CACHE_L3,		SZ_4M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xde, CACHE_L3,		SZ_8M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xe2, CACHE_L3,		SZ_2M	),	/* 16-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xe3, CACHE_L3,		SZ_4M	),	/* 16-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xe4, CACHE_L3,		SZ_8M	),	/* 16-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xea, CACHE_L3,		SZ_12M	),	/* 24-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xeb, CACHE_L3,		SZ_18M	),	/* 24-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xec, CACHE_L3,		SZ_24M	),	/* 24-way set assoc, 64 byte line size */
+
+	TLB_ENTRY(  0x01, TLB_INST_4K,		32	),	/* TLB_INST 4 KByte pages, 4-way set associative */
+	TLB_ENTRY(  0x02, TLB_INST_4M,		2	),	/* TLB_INST 4 MByte pages, full associative */
+	TLB_ENTRY(  0x03, TLB_DATA_4K,		64	),	/* TLB_DATA 4 KByte pages, 4-way set associative */
+	TLB_ENTRY(  0x04, TLB_DATA_4M,		8	),	/* TLB_DATA 4 MByte pages, 4-way set associative */
+	TLB_ENTRY(  0x05, TLB_DATA_4M,		32	),	/* TLB_DATA 4 MByte pages, 4-way set associative */
+	TLB_ENTRY(  0x0b, TLB_INST_4M,		4	),	/* TLB_INST 4 MByte pages, 4-way set associative */
+	TLB_ENTRY(  0x4f, TLB_INST_4K,		32	),	/* TLB_INST 4 KByte pages */
+	TLB_ENTRY(  0x50, TLB_INST_ALL,		64	),	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	TLB_ENTRY(  0x51, TLB_INST_ALL,		128	),	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	TLB_ENTRY(  0x52, TLB_INST_ALL,		256	),	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	TLB_ENTRY(  0x55, TLB_INST_2M_4M,	7	),	/* TLB_INST 2-MByte or 4-MByte pages, fully associative */
+	TLB_ENTRY(  0x56, TLB_DATA0_4M,		16	),	/* TLB_DATA0 4 MByte pages, 4-way set associative */
+	TLB_ENTRY(  0x57, TLB_DATA0_4K,		16	),	/* TLB_DATA0 4 KByte pages, 4-way associative */
+	TLB_ENTRY(  0x59, TLB_DATA0_4K,		16	),	/* TLB_DATA0 4 KByte pages, fully associative */
+	TLB_ENTRY(  0x5a, TLB_DATA0_2M_4M,	32	),	/* TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative */
+	TLB_ENTRY(  0x5b, TLB_DATA_4K_4M,	64	),	/* TLB_DATA 4 KByte and 4 MByte pages */
+	TLB_ENTRY(  0x5c, TLB_DATA_4K_4M,	128	),	/* TLB_DATA 4 KByte and 4 MByte pages */
+	TLB_ENTRY(  0x5d, TLB_DATA_4K_4M,	256	),	/* TLB_DATA 4 KByte and 4 MByte pages */
+	TLB_ENTRY(  0x61, TLB_INST_4K,		48	),	/* TLB_INST 4 KByte pages, full associative */
+	TLB_ENTRY(  0x63, TLB_DATA_1G_2M_4M,	4	),	/* TLB_DATA 1 GByte pages, 4-way set associative
+								 * (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here) */
+	TLB_ENTRY(  0x6b, TLB_DATA_4K,		256	),	/* TLB_DATA 4 KByte pages, 8-way associative */
+	TLB_ENTRY(  0x6c, TLB_DATA_2M_4M,	128	),	/* TLB_DATA 2 MByte or 4 MByte pages, 8-way associative */
+	TLB_ENTRY(  0x6d, TLB_DATA_1G,		16	),	/* TLB_DATA 1 GByte pages, fully associative */
+	TLB_ENTRY(  0x76, TLB_INST_2M_4M,	8	),	/* TLB_INST 2-MByte or 4-MByte pages, fully associative */
+	TLB_ENTRY(  0xb0, TLB_INST_4K,		128	),	/* TLB_INST 4 KByte pages, 4-way set associative */
+	TLB_ENTRY(  0xb1, TLB_INST_2M_4M,	4	),	/* TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries */
+	TLB_ENTRY(  0xb2, TLB_INST_4K,		64	),	/* TLB_INST 4KByte pages, 4-way set associative */
+	TLB_ENTRY(  0xb3, TLB_DATA_4K,		128	),	/* TLB_DATA 4 KByte pages, 4-way set associative */
+	TLB_ENTRY(  0xb4, TLB_DATA_4K,		256	),	/* TLB_DATA 4 KByte pages, 4-way associative */
+	TLB_ENTRY(  0xb5, TLB_INST_4K,		64	),	/* TLB_INST 4 KByte pages, 8-way set associative */
+	TLB_ENTRY(  0xb6, TLB_INST_4K,		128	),	/* TLB_INST 4 KByte pages, 8-way set associative */
+	TLB_ENTRY(  0xba, TLB_DATA_4K,		64	),	/* TLB_DATA 4 KByte pages, 4-way associative */
+	TLB_ENTRY(  0xc0, TLB_DATA_4K_4M,	8	),	/* TLB_DATA 4 KByte and 4 MByte pages, 4-way associative */
+	TLB_ENTRY(  0xc1, STLB_4K_2M,		1024	),	/* STLB 4 KByte and 2 MByte pages, 8-way associative */
+	TLB_ENTRY(  0xc2, TLB_DATA_2M_4M,	16	),	/* TLB_DATA 2 MByte/4MByte pages, 4-way associative */
+	TLB_ENTRY(  0xca, STLB_4K,		512	),	/* STLB 4 KByte pages, 4-way associative */
+};
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@ -6,6 +6,7 @@
 #include <linux/minmax.h>
 #include <linux/smp.h>
 #include <linux/string.h>
+#include <linux/types.h>

 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
@ -15,6 +16,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu.h>
+#include <asm/cpuid.h>
 #include <asm/hwcap2.h>
 #include <asm/intel-family.h>
 #include <asm/microcode.h>
@ -646,103 +648,11 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 }
 #endif

-#define TLB_INST_4K		0x01
-#define TLB_INST_4M		0x02
-#define TLB_INST_2M_4M		0x03
-
-#define TLB_INST_ALL		0x05
-#define TLB_INST_1G		0x06
-
-#define TLB_DATA_4K		0x11
-#define TLB_DATA_4M		0x12
-#define TLB_DATA_2M_4M		0x13
-#define TLB_DATA_4K_4M		0x14
-
-#define TLB_DATA_1G		0x16
-#define TLB_DATA_1G_2M_4M	0x17
-
-#define TLB_DATA0_4K		0x21
-#define TLB_DATA0_4M		0x22
-#define TLB_DATA0_2M_4M		0x23
-
-#define STLB_4K			0x41
-#define STLB_4K_2M		0x42
-
-/*
- * All of leaf 0x2's one-byte TLB descriptors implies the same number of
- * entries for their respective TLB types.  The 0x63 descriptor is an
- * exception: it implies 4 dTLB entries for 1GB pages 32 dTLB entries
- * for 2MB or 4MB pages.  Encode descriptor 0x63 dTLB entry count for
- * 2MB/4MB pages here, as its count for dTLB 1GB pages is already at the
- * intel_tlb_table[] mapping.
- */
-#define TLB_0x63_2M_4M_ENTRIES	32
-
-struct _tlb_table {
-	unsigned char descriptor;
-	char tlb_type;
-	unsigned int entries;
-};
-
-static const struct _tlb_table intel_tlb_table[] = {
-	{ 0x01, TLB_INST_4K,		32},	/* TLB_INST 4 KByte pages, 4-way set associative */
-	{ 0x02, TLB_INST_4M,		2},	/* TLB_INST 4 MByte pages, full associative */
-	{ 0x03, TLB_DATA_4K,		64},	/* TLB_DATA 4 KByte pages, 4-way set associative */
-	{ 0x04, TLB_DATA_4M,		8},	/* TLB_DATA 4 MByte pages, 4-way set associative */
-	{ 0x05, TLB_DATA_4M,		32},	/* TLB_DATA 4 MByte pages, 4-way set associative */
-	{ 0x0b, TLB_INST_4M,		4},	/* TLB_INST 4 MByte pages, 4-way set associative */
-	{ 0x4f, TLB_INST_4K,		32},	/* TLB_INST 4 KByte pages */
-	{ 0x50, TLB_INST_ALL,		64},	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
-	{ 0x51, TLB_INST_ALL,		128},	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
-	{ 0x52, TLB_INST_ALL,		256},	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
-	{ 0x55, TLB_INST_2M_4M,		7},	/* TLB_INST 2-MByte or 4-MByte pages, fully associative */
-	{ 0x56, TLB_DATA0_4M,		16},	/* TLB_DATA0 4 MByte pages, 4-way set associative */
-	{ 0x57, TLB_DATA0_4K,		16},	/* TLB_DATA0 4 KByte pages, 4-way associative */
-	{ 0x59, TLB_DATA0_4K,		16},	/* TLB_DATA0 4 KByte pages, fully associative */
-	{ 0x5a, TLB_DATA0_2M_4M,	32},	/* TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative */
-	{ 0x5b, TLB_DATA_4K_4M,		64},	/* TLB_DATA 4 KByte and 4 MByte pages */
-	{ 0x5c, TLB_DATA_4K_4M,		128},	/* TLB_DATA 4 KByte and 4 MByte pages */
-	{ 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_2M_4M,	4},	/* TLB_DATA 1 GByte pages, 4-way set associative
-						 * (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here) */
-	{ 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 */
-	{ 0xb2, TLB_INST_4K,		64},	/* TLB_INST 4KByte pages, 4-way set associative */
-	{ 0xb3, TLB_DATA_4K,		128},	/* TLB_DATA 4 KByte pages, 4-way set associative */
-	{ 0xb4, TLB_DATA_4K,		256},	/* TLB_DATA 4 KByte pages, 4-way associative */
-	{ 0xb5, TLB_INST_4K,		64},	/* TLB_INST 4 KByte pages, 8-way set associative */
-	{ 0xb6, TLB_INST_4K,		128},	/* TLB_INST 4 KByte pages, 8-way set associative */
-	{ 0xba, TLB_DATA_4K,		64},	/* TLB_DATA 4 KByte pages, 4-way associative */
-	{ 0xc0, TLB_DATA_4K_4M,		8},	/* TLB_DATA 4 KByte and 4 MByte pages, 4-way associative */
-	{ 0xc1, STLB_4K_2M,		1024},	/* STLB 4 KByte and 2 MByte pages, 8-way associative */
-	{ 0xc2, TLB_DATA_2M_4M,		16},	/* TLB_DATA 2 MByte/4MByte pages, 4-way associative */
-	{ 0xca, STLB_4K,		512},	/* STLB 4 KByte pages, 4-way associative */
-	{ 0x00, 0, 0 }
-};
-
-static void intel_tlb_lookup(const unsigned char desc)
+static void intel_tlb_lookup(const struct leaf_0x2_table *entry)
 {
-	unsigned int entries;
-	unsigned char k;
+	short entries = entry->entries;

-	if (desc == 0)
-		return;
-
-	/* look up this descriptor in the table */
-	for (k = 0; intel_tlb_table[k].descriptor != desc &&
-	     intel_tlb_table[k].descriptor != 0; k++)
-		;
-
-	if (intel_tlb_table[k].tlb_type == 0)
-		return;
-
-	entries = intel_tlb_table[k].entries;
-	switch (intel_tlb_table[k].tlb_type) {
+	switch (entry->t_type) {
 	case STLB_4K:
 		tlb_lli_4k = max(tlb_lli_4k, entries);
 		tlb_lld_4k = max(tlb_lld_4k, entries);
@ -799,28 +709,16 @@ static void intel_tlb_lookup(const unsigned char desc)

 static void intel_detect_tlb(struct cpuinfo_x86 *c)
 {
-	int i, j, n;
-	unsigned int regs[4];
-	unsigned char *desc = (unsigned char *)regs;
+	const struct leaf_0x2_table *entry;
+	union leaf_0x2_regs regs;
+	u8 *ptr;

 	if (c->cpuid_level < 2)
 		return;

-	/* Number of times to iterate */
-	n = cpuid_eax(2) & 0xFF;
-
-	for (i = 0 ; i < n ; i++) {
-		cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
-
-		/* If bit 31 is set, this is an unknown format */
-		for (j = 0 ; j < 4 ; j++)
-			if (regs[j] & (1 << 31))
-				regs[j] = 0;
-
-		/* Byte 0 is level count, not a descriptor */
-		for (j = 1 ; j < 16 ; j++)
-			intel_tlb_lookup(desc[j]);
-	}
+	cpuid_get_leaf_0x2_regs(&regs);
+	for_each_leaf_0x2_entry(regs, ptr, entry)
+		intel_tlb_lookup(entry);
 }

 static const struct cpu_dev intel_cpu_dev = {
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@ -24,7 +24,7 @@
 #include <linux/pci.h>
 #include <linux/uaccess.h>

-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 #include <asm/apic.h>
 #include <asm/irq_vectors.h>
 #include <asm/mce.h>
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@ -53,7 +53,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ 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 },
+	{ X86_FEATURE_AMD_HTR_CORES,		CPUID_EAX, 30, 0x80000026, 0 },
 	{ 0, 0, 0, 0, 0 }
 };

--- a/arch/x86/kernel/cpu/topology_amd.c
+++ b/arch/x86/kernel/cpu/topology_amd.c
@ -182,7 +182,7 @@ 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))
+	if (cpu_feature_enabled(X86_FEATURE_AMD_HTR_CORES))
 		tscan->c->topo.cpu_type = cpuid_ebx(0x80000026);

 	if (!has_topoext && !parse_8000_0008(tscan))
--- a/arch/x86/mm/amdtopology.c
+++ b/arch/x86/mm/amdtopology.c
@ -25,7 +25,7 @@
 #include <asm/numa.h>
 #include <asm/mpspec.h>
 #include <asm/apic.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>

 static unsigned char __initdata nodeids[8];

--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@ -18,7 +18,7 @@
 #include <asm/e820/api.h>
 #include <asm/proto.h>
 #include <asm/dma.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>

 #include "numa_internal.h"

--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@ -5,7 +5,7 @@
 #include <linux/cpu.h>
 #include <linux/range.h>

-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 #include <asm/pci_x86.h>

 #include <asm/pci-direct.h>
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@ -9,7 +9,7 @@
 #include <linux/pci.h>
 #include <linux/suspend.h>
 #include <linux/vgaarb.h>
-#include <asm/amd_node.h>
+#include <asm/amd/node.h>
 #include <asm/hpet.h>
 #include <asm/pci_x86.h>

--- a/drivers/char/agp/amd64-agp.c
+++ b/drivers/char/agp/amd64-agp.c
@ -16,7 +16,7 @@
 #include <linux/mmzone.h>
 #include <asm/page.h>		/* PAGE_SIZE */
 #include <asm/e820/api.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 #include <asm/gart.h>
 #include "agp.h"

--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@ -2,8 +2,8 @@
 #include <linux/ras.h>
 #include <linux/string_choices.h>
 #include "amd64_edac.h"
-#include <asm/amd_nb.h>
-#include <asm/amd_node.h>
+#include <asm/amd/nb.h>
+#include <asm/amd/node.h>

 static struct edac_pci_ctl_info *pci_ctl;

--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@ -20,7 +20,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
-#include <asm/amd_node.h>
+#include <asm/amd/node.h>
 #include <asm/processor.h>

 MODULE_DESCRIPTION("AMD Family 10h+ CPU core temperature monitor");
--- a/drivers/platform/x86/amd/hsmp/acpi.c
+++ b/drivers/platform/x86/amd/hsmp/acpi.c
@ -9,7 +9,7 @@

 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

-#include <asm/amd_hsmp.h>
+#include <asm/amd/hsmp.h>

 #include <linux/acpi.h>
 #include <linux/device.h>
@ -23,7 +23,7 @@

 #include <uapi/asm-generic/errno-base.h>

-#include <asm/amd_node.h>
+#include <asm/amd/node.h>

 #include "hsmp.h"

--- a/drivers/platform/x86/amd/hsmp/hsmp.c
+++ b/drivers/platform/x86/amd/hsmp/hsmp.c
@ -7,7 +7,7 @@
 * This file provides a device implementation for HSMP interface
 */

-#include <asm/amd_hsmp.h>
+#include <asm/amd/hsmp.h>

 #include <linux/acpi.h>
 #include <linux/delay.h>
--- a/drivers/platform/x86/amd/hsmp/plat.c
+++ b/drivers/platform/x86/amd/hsmp/plat.c
@ -9,7 +9,7 @@

 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

-#include <asm/amd_hsmp.h>
+#include <asm/amd/hsmp.h>

 #include <linux/build_bug.h>
 #include <linux/device.h>
@ -18,7 +18,7 @@
 #include <linux/platform_device.h>
 #include <linux/sysfs.h>

-#include <asm/amd_node.h>
+#include <asm/amd/node.h>

 #include "hsmp.h"

--- a/drivers/platform/x86/amd/pmc/mp1_stb.c
+++ b/drivers/platform/x86/amd/pmc/mp1_stb.c
@ -11,7 +11,7 @@

 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
--- a/drivers/platform/x86/amd/pmc/pmc.c
+++ b/drivers/platform/x86/amd/pmc/pmc.c
@ -28,7 +28,7 @@
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>

-#include <asm/amd_node.h>
+#include <asm/amd/node.h>

 #include "pmc.h"

--- a/drivers/platform/x86/amd/pmf/core.c
+++ b/drivers/platform/x86/amd/pmf/core.c
@ -14,7 +14,7 @@
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/power_supply.h>
-#include <asm/amd_node.h>
+#include <asm/amd/node.h>
 #include "pmf.h"

 /* PMF-SMU communication registers */
--- a/drivers/pnp/quirks.c
+++ b/drivers/pnp/quirks.c
@ -290,7 +290,7 @@ static void quirk_system_pci_resources(struct pnp_dev *dev)

 #ifdef CONFIG_AMD_NB

-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>

 static void quirk_amd_mmconfig_area(struct pnp_dev *dev)
 {
--- a/drivers/ras/amd/atl/internal.h
+++ b/drivers/ras/amd/atl/internal.h
@ -17,8 +17,8 @@
 #include <linux/bitops.h>
 #include <linux/ras.h>

-#include <asm/amd_nb.h>
-#include <asm/amd_node.h>
+#include <asm/amd/nb.h>
+#include <asm/amd/node.h>

 #include "reg_fields.h"

--- a/sound/soc/amd/acp/acp-rembrandt.c
+++ b/sound/soc/amd/acp/acp-rembrandt.c
@ -22,7 +22,7 @@
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>

-#include <asm/amd_node.h>
+#include <asm/amd/node.h>

 #include "amd.h"
 #include "../mach-config.h"
--- a/sound/soc/amd/acp/acp63.c
+++ b/sound/soc/amd/acp/acp63.c
@ -21,7 +21,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/pci.h>

-#include <asm/amd_node.h>
+#include <asm/amd/node.h>

 #include "amd.h"
 #include "acp-mach.h"
--- a/sound/soc/amd/acp/acp70.c
+++ b/sound/soc/amd/acp/acp70.c
@ -23,7 +23,7 @@
 #include "amd.h"
 #include "acp-mach.h"

-#include <asm/amd_node.h>
+#include <asm/amd/node.h>

 #define DRV_NAME "acp_asoc_acp70"

--- a/sound/soc/sof/amd/acp.c
+++ b/sound/soc/sof/amd/acp.c
@ -16,7 +16,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>

-#include <asm/amd_node.h>
+#include <asm/amd/node.h>

 #include "../ops.h"
 #include "acp.h"
--- a/tools/arch/x86/include/asm/amd/ibs.h
+++ b/tools/arch/x86/include/asm/amd/ibs.h
@ -4,7 +4,7 @@
 * 55898 Rev 0.35 - Feb 5, 2021
 */

-#include "msr-index.h"
+#include "../msr-index.h"

 /* IBS_OP_DATA2 DataSrc */
 #define IBS_DATA_SRC_LOC_CACHE			 2
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@ -476,11 +476,11 @@
 #define X86_FEATURE_CLEAR_BHB_LOOP	(21*32+ 1) /* Clear branch history at syscall entry using SW loop */
 #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_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 */
-#define X86_FEATURE_PREFER_YMM		(21*32 + 8) /* Avoid ZMM registers due to downclocking */
+#define X86_FEATURE_CLEAR_BHB_VMEXIT	(21*32+ 4) /* Clear branch history at vmexit using SW loop */
+#define X86_FEATURE_AMD_FAST_CPPC	(21*32+ 5) /* Fast CPPC */
+#define X86_FEATURE_AMD_HTR_CORES	(21*32+ 6) /* Heterogeneous Core Topology */
+#define X86_FEATURE_AMD_WORKLOAD_CLASS	(21*32+ 7) /* Workload Classification */
+#define X86_FEATURE_PREFER_YMM		(21*32+ 8) /* Avoid ZMM registers due to downclocking */

 /*
 * BUG word(s)
@ -519,7 +519,7 @@
 #define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* "itlb_multihit" CPU may incur MCE during certain page attribute changes */
 #define X86_BUG_SRBDS			X86_BUG(24) /* "srbds" CPU may leak RNG bits if not mitigated */
 #define X86_BUG_MMIO_STALE_DATA		X86_BUG(25) /* "mmio_stale_data" CPU is affected by Processor MMIO Stale Data vulnerabilities */
-#define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) /* "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */
+/* unused, was #define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */
 #define X86_BUG_RETBLEED		X86_BUG(27) /* "retbleed" CPU is affected by RETBleed */
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* "eibrs_pbrsb" EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* "smt_rsb" CPU is vulnerable to Cross-Thread Return Address Predictions */
@ -527,10 +527,10 @@
 #define X86_BUG_TDX_PW_MCE		X86_BUG(31) /* "tdx_pw_mce" CPU may incur #MC if non-TD software does partial write to TDX private memory */

 /* BUG word 2 */
-#define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* "srso" AMD SRSO bug */
-#define X86_BUG_DIV0			X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */
-#define X86_BUG_RFDS			X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
-#define X86_BUG_BHI			X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
-#define X86_BUG_IBPB_NO_RET	   	X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
-#define X86_BUG_SPECTRE_V2_USER		X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
+#define X86_BUG_SRSO			X86_BUG( 1*32+ 0) /* "srso" AMD SRSO bug */
+#define X86_BUG_DIV0			X86_BUG( 1*32+ 1) /* "div0" AMD DIV0 speculation bug */
+#define X86_BUG_RFDS			X86_BUG( 1*32+ 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
+#define X86_BUG_BHI			X86_BUG( 1*32+ 3) /* "bhi" CPU is affected by Branch History Injection */
+#define X86_BUG_IBPB_NO_RET		X86_BUG( 1*32+ 4) /* "ibpb_no_ret" IBPB omits return target predictions */
+#define X86_BUG_SPECTRE_V2_USER		X86_BUG( 1*32+ 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
 #endif /* _ASM_X86_CPUFEATURES_H */
--- a/tools/arch/x86/kcpuid/cpuid.csv
+++ b/tools/arch/x86/kcpuid/cpuid.csv
--- a/tools/arch/x86/kcpuid/kcpuid.c
+++ b/tools/arch/x86/kcpuid/kcpuid.c
@ -1,14 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE

-#include <stdio.h>
+#include <cpuid.h>
+#include <err.h>
+#include <getopt.h>
 #include <stdbool.h>
+#include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <getopt.h>

 #define ARRAY_SIZE(x)	(sizeof(x) / sizeof((x)[0]))
 #define min(a, b)	(((a) < (b)) ? (a) : (b))
+#define __noreturn	__attribute__((__noreturn__))

 typedef unsigned int u32;
 typedef unsigned long long u64;
@ -49,7 +52,7 @@ static const char * const reg_names[] = {
 struct subleaf {
 	u32 index;
 	u32 sub;
-	u32 eax, ebx, ecx, edx;
+	u32 output[NR_REGS];
 	struct reg_desc info[NR_REGS];
 };

@ -63,21 +66,64 @@ struct cpuid_func {
 	int nr;
 };

+enum range_index {
+	RANGE_STD = 0,			/* Standard */
+	RANGE_EXT = 0x80000000,		/* Extended */
+	RANGE_TSM = 0x80860000,		/* Transmeta */
+	RANGE_CTR = 0xc0000000,		/* Centaur/Zhaoxin */
+};
+
+#define CPUID_INDEX_MASK		0xffff0000
+#define CPUID_FUNCTION_MASK		(~CPUID_INDEX_MASK)
+
 struct cpuid_range {
 	/* array of main leafs */
 	struct cpuid_func *funcs;
 	/* number of valid leafs */
 	int nr;
-	bool is_ext;
+	enum range_index index;
 };

-/*
- * basic:  basic functions range: [0... ]
- * ext:    extended functions range: [0x80000000... ]
- */
-struct cpuid_range *leafs_basic, *leafs_ext;
+static struct cpuid_range ranges[] = {
+	{	.index		= RANGE_STD,	},
+	{	.index		= RANGE_EXT,	},
+	{	.index		= RANGE_TSM,	},
+	{	.index		= RANGE_CTR,	},
+};
+
+static char *range_to_str(struct cpuid_range *range)
+{
+	switch (range->index) {
+	case RANGE_STD:		return "Standard";
+	case RANGE_EXT:		return "Extended";
+	case RANGE_TSM:		return "Transmeta";
+	case RANGE_CTR:		return "Centaur";
+	default:		return NULL;
+	}
+}
+
+#define __for_each_cpuid_range(range, __condition)				\
+	for (unsigned int i = 0;						\
+	     i < ARRAY_SIZE(ranges) && ((range) = &ranges[i]) && (__condition);	\
+	     i++)
+
+#define for_each_valid_cpuid_range(range)	__for_each_cpuid_range(range, (range)->nr != 0)
+#define for_each_cpuid_range(range)		__for_each_cpuid_range(range, true)
+
+struct cpuid_range *index_to_cpuid_range(u32 index)
+{
+	u32 func_idx = index & CPUID_FUNCTION_MASK;
+	u32 range_idx = index & CPUID_INDEX_MASK;
+	struct cpuid_range *range;
+
+	for_each_valid_cpuid_range(range) {
+		if (range->index == range_idx && (u32)range->nr > func_idx)
+			return range;
+	}
+
+	return NULL;
+}

-static bool is_amd;
 static bool show_details;
 static bool show_raw;
 static bool show_flags_only = true;
@ -85,16 +131,16 @@ static u32 user_index = 0xFFFFFFFF;
 static u32 user_sub = 0xFFFFFFFF;
 static int flines;

-static inline void cpuid(u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
-{
-	/* ecx is often an input as well as an output. */
-	asm volatile("cpuid"
-	    : "=a" (*eax),
-	      "=b" (*ebx),
-	      "=c" (*ecx),
-	      "=d" (*edx)
-	    : "0" (*eax), "2" (*ecx));
-}
+/*
+ * Force using <cpuid.h> __cpuid_count() instead of __cpuid(). The
+ * latter leaves ECX uninitialized, which can break CPUID queries.
+ */
+
+#define cpuid(leaf, a, b, c, d)				\
+	__cpuid_count(leaf, 0, a, b, c, d)
+
+#define cpuid_count(leaf, subleaf, a, b, c, d)		\
+	__cpuid_count(leaf, subleaf, a, b, c, d)

 static inline bool has_subleafs(u32 f)
 {
@ -117,11 +163,11 @@ static void leaf_print_raw(struct subleaf *leaf)
 		if (leaf->sub == 0)
 			printf("0x%08x: subleafs:\n", leaf->index);

-		printf(" %2d: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n",
-			leaf->sub, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx);
+		printf(" %2d: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", leaf->sub,
+		       leaf->output[0], leaf->output[1], leaf->output[2], leaf->output[3]);
 	} else {
-		printf("0x%08x: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n",
-			leaf->index, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx);
+		printf("0x%08x: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", leaf->index,
+		       leaf->output[0], leaf->output[1], leaf->output[2], leaf->output[3]);
 	}
 }

@ -140,19 +186,19 @@ static bool cpuid_store(struct cpuid_range *range, u32 f, int subleaf,
 	 * Cut off vendor-prefix from CPUID function as we're using it as an
 	 * index into ->funcs.
 	 */
-	func = &range->funcs[f & 0xffff];
+	func = &range->funcs[f & CPUID_FUNCTION_MASK];

 	if (!func->leafs) {
 		func->leafs = malloc(sizeof(struct subleaf));
 		if (!func->leafs)
-			perror("malloc func leaf");
+			err(EXIT_FAILURE, NULL);

 		func->nr = 1;
 	} else {
 		s = func->nr;
 		func->leafs = realloc(func->leafs, (s + 1) * sizeof(*leaf));
 		if (!func->leafs)
-			perror("realloc f->leafs");
+			err(EXIT_FAILURE, NULL);

 		func->nr++;
 	}
@ -161,84 +207,73 @@ static bool cpuid_store(struct cpuid_range *range, u32 f, int subleaf,

 	leaf->index = f;
 	leaf->sub = subleaf;
-	leaf->eax = a;
-	leaf->ebx = b;
-	leaf->ecx = c;
-	leaf->edx = d;
+	leaf->output[R_EAX] = a;
+	leaf->output[R_EBX] = b;
+	leaf->output[R_ECX] = c;
+	leaf->output[R_EDX] = d;

 	return false;
 }

 static void raw_dump_range(struct cpuid_range *range)
 {
-	u32 f;
-	int i;
-
-	printf("%s Leafs :\n", range->is_ext ? "Extended" : "Basic");
+	printf("%s Leafs :\n", range_to_str(range));
 	printf("================\n");

-	for (f = 0; (int)f < range->nr; f++) {
+	for (u32 f = 0; (int)f < range->nr; f++) {
 		struct cpuid_func *func = &range->funcs[f];
-		u32 index = f;
-
-		if (range->is_ext)
-			index += 0x80000000;

 		/* Skip leaf without valid items */
 		if (!func->nr)
 			continue;

 		/* First item is the main leaf, followed by all subleafs */
-		for (i = 0; i < func->nr; i++)
+		for (int i = 0; i < func->nr; i++)
 			leaf_print_raw(&func->leafs[i]);
 	}
 }

 #define MAX_SUBLEAF_NUM		64
-struct cpuid_range *setup_cpuid_range(u32 input_eax)
+#define MAX_RANGE_INDEX_OFFSET	0xff
+void setup_cpuid_range(struct cpuid_range *range)
 {
-	u32 max_func, idx_func, subleaf, max_subleaf;
-	u32 eax, ebx, ecx, edx, f = input_eax;
-	struct cpuid_range *range;
-	bool allzero;
+	u32 max_func, range_funcs_sz;
+	u32 eax, ebx, ecx, edx;

-	eax = input_eax;
-	ebx = ecx = edx = 0;
+	cpuid(range->index, max_func, ebx, ecx, edx);

-	cpuid(&eax, &ebx, &ecx, &edx);
-	max_func = eax;
-	idx_func = (max_func & 0xffff) + 1;
+	/*
+	 * If the CPUID range's maximum function value is garbage, then it
+	 * is not recognized by this CPU.  Set the range's number of valid
+	 * leaves to zero so that for_each_valid_cpu_range() can ignore it.
+	 */
+	if (max_func < range->index || max_func > (range->index + MAX_RANGE_INDEX_OFFSET)) {
+		range->nr = 0;
+		return;
+	}

-	range = malloc(sizeof(struct cpuid_range));
-	if (!range)
-		perror("malloc range");
+	range->nr = (max_func & CPUID_FUNCTION_MASK) + 1;
+	range_funcs_sz = range->nr * sizeof(struct cpuid_func);

-	if (input_eax & 0x80000000)
-		range->is_ext = true;
-	else
-		range->is_ext = false;
-
-	range->funcs = malloc(sizeof(struct cpuid_func) * idx_func);
+	range->funcs = malloc(range_funcs_sz);
 	if (!range->funcs)
-		perror("malloc range->funcs");
+		err(EXIT_FAILURE, NULL);

-	range->nr = idx_func;
-	memset(range->funcs, 0, sizeof(struct cpuid_func) * idx_func);
+	memset(range->funcs, 0, range_funcs_sz);

-	for (; f <= max_func; f++) {
-		eax = f;
-		subleaf = ecx = 0;
+	for (u32 f = range->index; f <= max_func; f++) {
+		u32 max_subleaf = MAX_SUBLEAF_NUM;
+		bool allzero;

-		cpuid(&eax, &ebx, &ecx, &edx);
-		allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx);
+		cpuid(f, eax, ebx, ecx, edx);
+
+		allzero = cpuid_store(range, f, 0, eax, ebx, ecx, edx);
 		if (allzero)
 			continue;

 		if (!has_subleafs(f))
 			continue;

-		max_subleaf = MAX_SUBLEAF_NUM;
-
 		/*
 		 * Some can provide the exact number of subleafs,
 		 * others have to be tried (0xf)
@ -256,20 +291,15 @@ struct cpuid_range *setup_cpuid_range(u32 input_eax)
 		if (f == 0x80000026)
 			max_subleaf = 5;

-		for (subleaf = 1; subleaf < max_subleaf; subleaf++) {
-			eax = f;
-			ecx = subleaf;
+		for (u32 subleaf = 1; subleaf < max_subleaf; subleaf++) {
+			cpuid_count(f, subleaf, eax, ebx, ecx, edx);

-			cpuid(&eax, &ebx, &ecx, &edx);
-			allzero = cpuid_store(range, f, subleaf,
-						eax, ebx, ecx, edx);
+			allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx);
 			if (allzero)
 				continue;
 		}

 	}
-
-	return range;
 }

 /*
@ -280,15 +310,13 @@ struct cpuid_range *setup_cpuid_range(u32 input_eax)
 *	0,    0,  EAX,   31:0, max_basic_leafs,  Max input value for supported subleafs
 *	1,    0,  ECX,      0, sse3,  Streaming SIMD Extensions 3(SSE3)
 */
-static int parse_line(char *line)
+static void parse_line(char *line)
 {
 	char *str;
-	int i;
 	struct cpuid_range *range;
 	struct cpuid_func *func;
 	struct subleaf *leaf;
 	u32 index;
-	u32 sub;
 	char buffer[512];
 	char *buf;
 	/*
@ -310,12 +338,12 @@ static int parse_line(char *line)

 	/* Skip comments and NULL line */
 	if (line[0] == '#' || line[0] == '\n')
-		return 0;
+		return;

 	strncpy(buffer, line, 511);
 	buffer[511] = 0;
 	str = buffer;
-	for (i = 0; i < 5; i++) {
+	for (int i = 0; i < 5; i++) {
 		tokens[i] = strtok(str, ",");
 		if (!tokens[i])
 			goto err_exit;
@ -328,21 +356,19 @@ static int parse_line(char *line)
 	/* index/main-leaf */
 	index = strtoull(tokens[0], NULL, 0);

-	if (index & 0x80000000)
-		range = leafs_ext;
-	else
-		range = leafs_basic;
-
-	index &= 0x7FFFFFFF;
-	/* Skip line parsing for non-existing indexes */
-	if ((int)index >= range->nr)
-		return -1;
+	/*
+	 * Skip line parsing if the index is not covered by known-valid
+	 * CPUID ranges on this CPU.
+	 */
+	range = index_to_cpuid_range(index);
+	if (!range)
+		return;

+	/* Skip line parsing if the index CPUID output is all zero */
+	index &= CPUID_FUNCTION_MASK;
 	func = &range->funcs[index];
-
-	/* Return if the index has no valid item on this platform */
 	if (!func->nr)
-		return 0;
+		return;

 	/* subleaf */
 	buf = tokens[1];
@ -355,11 +381,11 @@ static int parse_line(char *line)
 		subleaf_start = strtoul(start, NULL, 0);
 		subleaf_end = min(subleaf_end, (u32)(func->nr - 1));
 		if (subleaf_start > subleaf_end)
-			return 0;
+			return;
 	} else {
 		subleaf_start = subleaf_end;
 		if (subleaf_start > (u32)(func->nr - 1))
-			return 0;
+			return;
 	}

 	/* register */
@ -382,7 +408,7 @@ static int parse_line(char *line)
 	bit_end = strtoul(end, NULL, 0);
 	bit_start = (start) ? strtoul(start, NULL, 0) : bit_end;

-	for (sub = subleaf_start; sub <= subleaf_end; sub++) {
+	for (u32 sub = subleaf_start; sub <= subleaf_end; sub++) {
 		leaf = &func->leafs[sub];
 		reg = &leaf->info[reg_index];
 		bdesc = &reg->descs[reg->nr++];
@ -392,12 +418,11 @@ static int parse_line(char *line)
 		strcpy(bdesc->simp, strtok(tokens[4], " \t"));
 		strcpy(bdesc->detail, tokens[5]);
 	}
-	return 0;
+	return;

 err_exit:
-	printf("Warning: wrong line format:\n");
-	printf("\tline[%d]: %s\n", flines, line);
-	return -1;
+	warnx("Wrong line format:\n"
+	      "\tline[%d]: %s", flines, line);
 }

 /* Parse csv file, and construct the array of all leafs and subleafs */
@ -418,10 +443,8 @@ static void parse_text(void)
 		file = fopen("./cpuid.csv", "r");
 	}

-	if (!file) {
-		printf("Fail to open '%s'\n", filename);
-		return;
-	}
+	if (!file)
+		err(EXIT_FAILURE, "%s", filename);

 	while (1) {
 		ret = getline(&line, &len, file);
@ -436,21 +459,13 @@ static void parse_text(void)
 	fclose(file);
 }

-
-/* Decode every eax/ebx/ecx/edx */
-static void decode_bits(u32 value, struct reg_desc *rdesc, enum cpuid_reg reg)
+static void show_reg(const struct reg_desc *rdesc, u32 value)
 {
-	struct bits_desc *bdesc;
-	int start, end, i;
+	const struct bits_desc *bdesc;
+	int start, end;
 	u32 mask;

-	if (!rdesc->nr) {
-		if (show_details)
-			printf("\t %s: 0x%08x\n", reg_names[reg], value);
-		return;
-	}
-
-	for (i = 0; i < rdesc->nr; i++) {
+	for (int i = 0; i < rdesc->nr; i++) {
 		bdesc = &rdesc->descs[i];

 		start = bdesc->start;
@ -480,23 +495,21 @@ static void decode_bits(u32 value, struct reg_desc *rdesc, enum cpuid_reg reg)
 	}
 }

+static void show_reg_header(bool has_entries, u32 leaf, u32 subleaf, const char *reg_name)
+{
+	if (show_details && has_entries)
+		printf("CPUID_0x%x_%s[0x%x]:\n", leaf, reg_name, subleaf);
+}
+
 static void show_leaf(struct subleaf *leaf)
 {
-	if (!leaf)
-		return;
-
-	if (show_raw) {
+	if (show_raw)
 		leaf_print_raw(leaf);
-	} else {
-		if (show_details)
-			printf("CPUID_0x%x_ECX[0x%x]:\n",
-				leaf->index, leaf->sub);
-	}

-	decode_bits(leaf->eax, &leaf->info[R_EAX], R_EAX);
-	decode_bits(leaf->ebx, &leaf->info[R_EBX], R_EBX);
-	decode_bits(leaf->ecx, &leaf->info[R_ECX], R_ECX);
-	decode_bits(leaf->edx, &leaf->info[R_EDX], R_EDX);
+	for (int i = R_EAX; i < NR_REGS; i++) {
+		show_reg_header((leaf->info[i].nr > 0), leaf->index, leaf->sub, reg_names[i]);
+		show_reg(&leaf->info[i], leaf->output[i]);
+	}

 	if (!show_raw && show_details)
 		printf("\n");
@ -504,46 +517,37 @@ static void show_leaf(struct subleaf *leaf)

 static void show_func(struct cpuid_func *func)
 {
-	int i;
-
-	if (!func)
-		return;
-
-	for (i = 0; i < func->nr; i++)
+	for (int i = 0; i < func->nr; i++)
 		show_leaf(&func->leafs[i]);
 }

 static void show_range(struct cpuid_range *range)
 {
-	int i;
-
-	for (i = 0; i < range->nr; i++)
+	for (int i = 0; i < range->nr; i++)
 		show_func(&range->funcs[i]);
 }

 static inline struct cpuid_func *index_to_func(u32 index)
 {
+	u32 func_idx = index & CPUID_FUNCTION_MASK;
 	struct cpuid_range *range;
-	u32 func_idx;

-	range = (index & 0x80000000) ? leafs_ext : leafs_basic;
-	func_idx = index & 0xffff;
-
-	if ((func_idx + 1) > (u32)range->nr) {
-		printf("ERR: invalid input index (0x%x)\n", index);
+	range = index_to_cpuid_range(index);
+	if (!range)
 		return NULL;
-	}
+
 	return &range->funcs[func_idx];
 }

 static void show_info(void)
 {
+	struct cpuid_range *range;
 	struct cpuid_func *func;

 	if (show_raw) {
 		/* Show all of the raw output of 'cpuid' instr */
-		raw_dump_range(leafs_basic);
-		raw_dump_range(leafs_ext);
+		for_each_valid_cpuid_range(range)
+			raw_dump_range(range);
 		return;
 	}

@ -551,18 +555,19 @@ static void show_info(void)
 		/* Only show specific leaf/subleaf info */
 		func = index_to_func(user_index);
 		if (!func)
-			return;
+			errx(EXIT_FAILURE, "Invalid input leaf (0x%x)", user_index);

 		/* Dump the raw data also */
 		show_raw = true;

 		if (user_sub != 0xFFFFFFFF) {
-			if (user_sub + 1 <= (u32)func->nr) {
-				show_leaf(&func->leafs[user_sub]);
-				return;
+			if (user_sub + 1 > (u32)func->nr) {
+				errx(EXIT_FAILURE, "Leaf 0x%x has no valid subleaf = 0x%x",
+				     user_index, user_sub);
 			}

-			printf("ERR: invalid input subleaf (0x%x)\n", user_sub);
+			show_leaf(&func->leafs[user_sub]);
+			return;
 		}

 		show_func(func);
@ -570,38 +575,21 @@ static void show_info(void)
 	}

 	printf("CPU features:\n=============\n\n");
-	show_range(leafs_basic);
-	show_range(leafs_ext);
+	for_each_valid_cpuid_range(range)
+		show_range(range);
 }

-static void setup_platform_cpuid(void)
+static void __noreturn usage(int exit_code)
 {
-	 u32 eax, ebx, ecx, edx;
-
-	/* Check vendor */
-	eax = ebx = ecx = edx = 0;
-	cpuid(&eax, &ebx, &ecx, &edx);
-
-	/* "htuA" */
-	if (ebx == 0x68747541)
-		is_amd = true;
-
-	/* Setup leafs for the basic and extended range */
-	leafs_basic = setup_cpuid_range(0x0);
-	leafs_ext = setup_cpuid_range(0x80000000);
-}
-
-static void usage(void)
-{
-	printf("kcpuid [-abdfhr] [-l leaf] [-s subleaf]\n"
-		"\t-a|--all             Show both bit flags and complex bit fields info\n"
-		"\t-b|--bitflags        Show boolean flags only\n"
-		"\t-d|--detail          Show details of the flag/fields (default)\n"
-		"\t-f|--flags           Specify the cpuid csv file\n"
-		"\t-h|--help            Show usage info\n"
-		"\t-l|--leaf=index      Specify the leaf you want to check\n"
-		"\t-r|--raw             Show raw cpuid data\n"
-		"\t-s|--subleaf=sub     Specify the subleaf you want to check\n"
+	errx(exit_code, "kcpuid [-abdfhr] [-l leaf] [-s subleaf]\n"
+	     "\t-a|--all             Show both bit flags and complex bit fields info\n"
+	     "\t-b|--bitflags        Show boolean flags only\n"
+	     "\t-d|--detail          Show details of the flag/fields (default)\n"
+	     "\t-f|--flags           Specify the CPUID CSV file\n"
+	     "\t-h|--help            Show usage info\n"
+	     "\t-l|--leaf=index      Specify the leaf you want to check\n"
+	     "\t-r|--raw             Show raw CPUID data\n"
+	     "\t-s|--subleaf=sub     Specify the subleaf you want to check"
 	);
 }

@ -617,7 +605,7 @@ static struct option opts[] = {
 	{ NULL, 0, NULL, 0 }
 };

-static int parse_options(int argc, char *argv[])
+static void parse_options(int argc, char *argv[])
 {
 	int c;

@ -637,9 +625,7 @@ static int parse_options(int argc, char *argv[])
 			user_csv = optarg;
 			break;
 		case 'h':
-			usage();
-			exit(1);
-			break;
+			usage(EXIT_SUCCESS);
 		case 'l':
 			/* main leaf */
 			user_index = strtoul(optarg, NULL, 0);
@ -652,11 +638,8 @@ static int parse_options(int argc, char *argv[])
 			user_sub = strtoul(optarg, NULL, 0);
 			break;
 		default:
-			printf("%s: Invalid option '%c'\n", argv[0], optopt);
-			return -1;
-	}
-
-	return 0;
+			usage(EXIT_FAILURE);
+		}
 }

 /*
@ -669,11 +652,13 @@ static int parse_options(int argc, char *argv[])
 */
 int main(int argc, char *argv[])
 {
-	if (parse_options(argc, argv))
-		return -1;
+	struct cpuid_range *range;
+
+	parse_options(argc, argv);

 	/* Setup the cpuid leafs of current platform */
-	setup_platform_cpuid();
+	for_each_cpuid_range(range)
+		setup_cpuid_range(range);

 	/* Read and parse the 'cpuid.csv' */
 	parse_text();
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@ -186,7 +186,7 @@ done
 # diff with extra ignore lines
 check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))" -I"^#include <linux/cfi_types.h>"'
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
-check arch/x86/include/asm/amd-ibs.h  '-I "^#include [<\"]\(asm/\)*msr-index.h"'
+check arch/x86/include/asm/amd/ibs.h  '-I "^#include [<\"]\(asm/\)*msr-index.h"'
 check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"'
 check include/linux/unaligned.h '-I "^#include <linux/unaligned/packed_struct.h>" -I "^#include <asm/byteorder.h>" -I "^#pragma GCC diagnostic"'
 check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
--- a/tools/perf/util/amd-sample-raw.c
+++ b/tools/perf/util/amd-sample-raw.c
@ -9,7 +9,7 @@
 #include <inttypes.h>

 #include <linux/string.h>
-#include "../../arch/x86/include/asm/amd-ibs.h"
+#include "../../arch/x86/include/asm/amd/ibs.h"

 #include "debug.h"
 #include "session.h"