Merge tag 'x86-core-2025-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core x86 updates from Ingo Molnar:
 "Boot code changes:

   - A large series of changes to reorganize the x86 boot code into a
     better isolated and easier to maintain base of PIC early startup
     code in arch/x86/boot/startup/, by Ard Biesheuvel.

     Motivation & background:

  	| Since commit
  	|
  	|    c88d71508e36 ("x86/boot/64: Rewrite startup_64() in C")
  	|
  	| dated Jun 6 2017, we have been using C code on the boot path in a way
  	| that is not supported by the toolchain, i.e., to execute non-PIC C
  	| code from a mapping of memory that is different from the one provided
  	| to the linker. It should have been obvious at the time that this was a
  	| bad idea, given the need to sprinkle fixup_pointer() calls left and
  	| right to manipulate global variables (including non-pointer variables)
  	| without crashing.
  	|
  	| This C startup code has been expanding, and in particular, the SEV-SNP
  	| startup code has been expanding over the past couple of years, and
  	| grown many of these warts, where the C code needs to use special
  	| annotations or helpers to access global objects.

     This tree includes the first phase of this work-in-progress x86
     boot code reorganization.

  Scalability enhancements and micro-optimizations:

   - Improve code-patching scalability (Eric Dumazet)

   - Remove MFENCEs for X86_BUG_CLFLUSH_MONITOR (Andrew Cooper)

  CPU features enumeration updates:

   - Thorough reorganization and cleanup of CPUID parsing APIs (Ahmed S.
     Darwish)

   - Fix, refactor and clean up the cacheinfo code (Ahmed S. Darwish,
     Thomas Gleixner)

   - Update CPUID bitfields to x86-cpuid-db v2.3 (Ahmed S. Darwish)

  Memory management changes:

   - Allow temporary MMs when IRQs are on (Andy Lutomirski)

   - Opt-in to IRQs-off activate_mm() (Andy Lutomirski)

   - Simplify choose_new_asid() and generate better code (Borislav
     Petkov)

   - Simplify 32-bit PAE page table handling (Dave Hansen)

   - Always use dynamic memory layout (Kirill A. Shutemov)

   - Make SPARSEMEM_VMEMMAP the only memory model (Kirill A. Shutemov)

   - Make 5-level paging support unconditional (Kirill A. Shutemov)

   - Stop prefetching current->mm->mmap_lock on page faults (Mateusz
     Guzik)

   - Predict valid_user_address() returning true (Mateusz Guzik)

   - Consolidate initmem_init() (Mike Rapoport)

  FPU support and vector computing:

   - Enable Intel APX support (Chang S. Bae)

   - Reorgnize and clean up the xstate code (Chang S. Bae)

   - Make task_struct::thread constant size (Ingo Molnar)

   - Restore fpu_thread_struct_whitelist() to fix
     CONFIG_HARDENED_USERCOPY=y (Kees Cook)

   - Simplify the switch_fpu_prepare() + switch_fpu_finish() logic (Oleg
     Nesterov)

   - Always preserve non-user xfeatures/flags in __state_perm (Sean
     Christopherson)

  Microcode loader changes:

   - Help users notice when running old Intel microcode (Dave Hansen)

   - AMD: Do not return error when microcode update is not necessary
     (Annie Li)

   - AMD: Clean the cache if update did not load microcode (Boris
     Ostrovsky)

  Code patching (alternatives) changes:

   - Simplify, reorganize and clean up the x86 text-patching code (Ingo
     Molnar)

   - Make smp_text_poke_batch_process() subsume
     smp_text_poke_batch_finish() (Nikolay Borisov)

   - Refactor the {,un}use_temporary_mm() code (Peter Zijlstra)

  Debugging support:

   - Add early IDT and GDT loading to debug relocate_kernel() bugs
     (David Woodhouse)

   - Print the reason for the last reset on modern AMD CPUs (Yazen
     Ghannam)

   - Add AMD Zen debugging document (Mario Limonciello)

   - Fix opcode map (!REX2) superscript tags (Masami Hiramatsu)

   - Stop decoding i64 instructions in x86-64 mode at opcode (Masami
     Hiramatsu)

  CPU bugs and bug mitigations:

   - Remove X86_BUG_MMIO_UNKNOWN (Borislav Petkov)

   - Fix SRSO reporting on Zen1/2 with SMT disabled (Borislav Petkov)

   - Restructure and harmonize the various CPU bug mitigation methods
     (David Kaplan)

   - Fix spectre_v2 mitigation default on Intel (Pawan Gupta)

  MSR API:

   - Large MSR code and API cleanup (Xin Li)

   - In-kernel MSR API type cleanups and renames (Ingo Molnar)

  PKEYS:

   - Simplify PKRU update in signal frame (Chang S. Bae)

  NMI handling code:

   - Clean up, refactor and simplify the NMI handling code (Sohil Mehta)

   - Improve NMI duration console printouts (Sohil Mehta)

  Paravirt guests interface:

   - Restrict PARAVIRT_XXL to 64-bit only (Kirill A. Shutemov)

  SEV support:

   - Share the sev_secrets_pa value again (Tom Lendacky)

  x86 platform changes:

   - Introduce the <asm/amd/> header namespace (Ingo Molnar)

   - i2c: piix4, x86/platform: Move the SB800 PIIX4 FCH definitions to
     <asm/amd/fch.h> (Mario Limonciello)

  Fixes and cleanups:

   - x86 assembly code cleanups and fixes (Uros Bizjak)

   - Misc fixes and cleanups (Andi Kleen, Andy Lutomirski, Andy
     Shevchenko, Ard Biesheuvel, Bagas Sanjaya, Baoquan He, Borislav
     Petkov, Chang S. Bae, Chao Gao, Dan Williams, Dave Hansen, David
     Kaplan, David Woodhouse, Eric Biggers, Ingo Molnar, Josh Poimboeuf,
     Juergen Gross, Malaya Kumar Rout, Mario Limonciello, Nathan
     Chancellor, Oleg Nesterov, Pawan Gupta, Peter Zijlstra, Shivank
     Garg, Sohil Mehta, Thomas Gleixner, Uros Bizjak, Xin Li)"

* tag 'x86-core-2025-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (331 commits)
  x86/bugs: Fix spectre_v2 mitigation default on Intel
  x86/bugs: Restructure ITS mitigation
  x86/xen/msr: Fix uninitialized variable 'err'
  x86/msr: Remove a superfluous inclusion of <asm/asm.h>
  x86/paravirt: Restrict PARAVIRT_XXL to 64-bit only
  x86/mm/64: Make 5-level paging support unconditional
  x86/mm/64: Make SPARSEMEM_VMEMMAP the only memory model
  x86/mm/64: Always use dynamic memory layout
  x86/bugs: Fix indentation due to ITS merge
  x86/cpuid: Rename hypervisor_cpuid_base()/for_each_possible_hypervisor_cpuid_base() to cpuid_base_hypervisor()/for_each_possible_cpuid_base_hypervisor()
  x86/cpu/intel: Rename CPUID(0x2) descriptors iterator parameter
  x86/cacheinfo: Rename CPUID(0x2) descriptors iterator parameter
  x86/cpuid: Rename cpuid_get_leaf_0x2_regs() to cpuid_leaf_0x2()
  x86/cpuid: Rename have_cpuid_p() to cpuid_feature()
  x86/cpuid: Set <asm/cpuid/api.h> as the main CPUID header
  x86/cpuid: Move CPUID(0x2) APIs into <cpuid/api.h>
  x86/msr: Add rdmsrl_on_cpu() compatibility wrapper
  x86/mm: Fix kernel-doc descriptions of various pgtable methods
  x86/asm-offsets: Export certain 'struct cpuinfo_x86' fields for 64-bit asm use too
  x86/boot: Defer initialization of VM space related global variables
  ...

1 files changed, 339 insertions, 720 deletions

diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index b3a520959b51..adfa7e8bb865 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -1,35 +1,28 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- *	Routines to identify caches on Intel CPU.
+ * x86 CPU caches detection and configuration
  *
- *	Changes:
- *	Venkatesh Pallipadi	: Adding cache identification through cpuid(4)
- *	Ashok Raj <ashok.raj@intel.com>: Work with CPU hotplug infrastructure.
- *	Andi Kleen / Andreas Herrmann	: CPUID4 emulation on AMD.
+ * Previous changes
+ * - Venkatesh Pallipadi:		Cache identification through CPUID(0x4)
+ * - Ashok Raj <ashok.raj@intel.com>:	Work with CPU hotplug infrastructure
+ * - Andi Kleen / Andreas Herrmann:	CPUID(0x4) emulation on AMD
  */
 
 #include <linux/cacheinfo.h>
-#include <linux/capability.h>
 #include <linux/cpu.h>
 #include <linux/cpuhotplug.h>
-#include <linux/pci.h>
 #include <linux/stop_machine.h>
-#include <linux/sysfs.h>
 
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 #include <asm/cacheinfo.h>
 #include <asm/cpufeature.h>
+#include <asm/cpuid/api.h>
 #include <asm/mtrr.h>
 #include <asm/smp.h>
 #include <asm/tlbflush.h>
 
 #include "cpu.h"
 
-#define LVL_1_INST	1
-#define LVL_1_DATA	2
-#define LVL_2		3
-#define LVL_3		4
-
 /* Shared last level cache maps */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 
@@ -41,208 +34,127 @@ static cpumask_var_t cpu_cacheinfo_mask;
 /* Kernel controls MTRR and/or PAT MSRs. */
 unsigned int memory_caching_control __ro_after_init;
 
-struct _cache_table {
-	unsigned char descriptor;
-	char cache_type;
-	short size;
-};
-
-#define MB(x)	((x) * 1024)
-
-/* All the cache descriptor types we care about (no TLB or
-   trace cache entries) */
-
-static const struct _cache_table cache_table[] =
-{
-	{ 0x06, LVL_1_INST, 8 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x08, LVL_1_INST, 16 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x09, LVL_1_INST, 32 },	/* 4-way set assoc, 64 byte line size */
-	{ 0x0a, LVL_1_DATA, 8 },	/* 2 way set assoc, 32 byte line size */
-	{ 0x0c, LVL_1_DATA, 16 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x0d, LVL_1_DATA, 16 },	/* 4-way set assoc, 64 byte line size */
-	{ 0x0e, LVL_1_DATA, 24 },	/* 6-way set assoc, 64 byte line size */
-	{ 0x21, LVL_2,      256 },	/* 8-way set assoc, 64 byte line size */
-	{ 0x22, LVL_3,      512 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x23, LVL_3,      MB(1) },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x25, LVL_3,      MB(2) },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x29, LVL_3,      MB(4) },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x2c, LVL_1_DATA, 32 },	/* 8-way set assoc, 64 byte line size */
-	{ 0x30, LVL_1_INST, 32 },	/* 8-way set assoc, 64 byte line size */
-	{ 0x39, LVL_2,      128 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x3a, LVL_2,      192 },	/* 6-way set assoc, sectored cache, 64 byte line size */
-	{ 0x3b, LVL_2,      128 },	/* 2-way set assoc, sectored cache, 64 byte line size */
-	{ 0x3c, LVL_2,      256 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x3d, LVL_2,      384 },	/* 6-way set assoc, sectored cache, 64 byte line size */
-	{ 0x3e, LVL_2,      512 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x3f, LVL_2,      256 },	/* 2-way set assoc, 64 byte line size */
-	{ 0x41, LVL_2,      128 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x42, LVL_2,      256 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x43, LVL_2,      512 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x44, LVL_2,      MB(1) },	/* 4-way set assoc, 32 byte line size */
-	{ 0x45, LVL_2,      MB(2) },	/* 4-way set assoc, 32 byte line size */
-	{ 0x46, LVL_3,      MB(4) },	/* 4-way set assoc, 64 byte line size */
-	{ 0x47, LVL_3,      MB(8) },	/* 8-way set assoc, 64 byte line size */
-	{ 0x48, LVL_2,      MB(3) },	/* 12-way set assoc, 64 byte line size */
-	{ 0x49, LVL_3,      MB(4) },	/* 16-way set assoc, 64 byte line size */
-	{ 0x4a, LVL_3,      MB(6) },	/* 12-way set assoc, 64 byte line size */
-	{ 0x4b, LVL_3,      MB(8) },	/* 16-way set assoc, 64 byte line size */
-	{ 0x4c, LVL_3,      MB(12) },	/* 12-way set assoc, 64 byte line size */
-	{ 0x4d, LVL_3,      MB(16) },	/* 16-way set assoc, 64 byte line size */
-	{ 0x4e, LVL_2,      MB(6) },	/* 24-way set assoc, 64 byte line size */
-	{ 0x60, LVL_1_DATA, 16 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x66, LVL_1_DATA, 8 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x67, LVL_1_DATA, 16 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x68, LVL_1_DATA, 32 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x78, LVL_2,      MB(1) },	/* 4-way set assoc, 64 byte line size */
-	{ 0x79, LVL_2,      128 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x7a, LVL_2,      256 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x7b, LVL_2,      512 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x7c, LVL_2,      MB(1) },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x7d, LVL_2,      MB(2) },	/* 8-way set assoc, 64 byte line size */
-	{ 0x7f, LVL_2,      512 },	/* 2-way set assoc, 64 byte line size */
-	{ 0x80, LVL_2,      512 },	/* 8-way set assoc, 64 byte line size */
-	{ 0x82, LVL_2,      256 },	/* 8-way set assoc, 32 byte line size */
-	{ 0x83, LVL_2,      512 },	/* 8-way set assoc, 32 byte line size */
-	{ 0x84, LVL_2,      MB(1) },	/* 8-way set assoc, 32 byte line size */
-	{ 0x85, LVL_2,      MB(2) },	/* 8-way set assoc, 32 byte line size */
-	{ 0x86, LVL_2,      512 },	/* 4-way set assoc, 64 byte line size */
-	{ 0x87, LVL_2,      MB(1) },	/* 8-way set assoc, 64 byte line size */
-	{ 0xd0, LVL_3,      512 },	/* 4-way set assoc, 64 byte line size */
-	{ 0xd1, LVL_3,      MB(1) },	/* 4-way set assoc, 64 byte line size */
-	{ 0xd2, LVL_3,      MB(2) },	/* 4-way set assoc, 64 byte line size */
-	{ 0xd6, LVL_3,      MB(1) },	/* 8-way set assoc, 64 byte line size */
-	{ 0xd7, LVL_3,      MB(2) },	/* 8-way set assoc, 64 byte line size */
-	{ 0xd8, LVL_3,      MB(4) },	/* 12-way set assoc, 64 byte line size */
-	{ 0xdc, LVL_3,      MB(2) },	/* 12-way set assoc, 64 byte line size */
-	{ 0xdd, LVL_3,      MB(4) },	/* 12-way set assoc, 64 byte line size */
-	{ 0xde, LVL_3,      MB(8) },	/* 12-way set assoc, 64 byte line size */
-	{ 0xe2, LVL_3,      MB(2) },	/* 16-way set assoc, 64 byte line size */
-	{ 0xe3, LVL_3,      MB(4) },	/* 16-way set assoc, 64 byte line size */
-	{ 0xe4, LVL_3,      MB(8) },	/* 16-way set assoc, 64 byte line size */
-	{ 0xea, LVL_3,      MB(12) },	/* 24-way set assoc, 64 byte line size */
-	{ 0xeb, LVL_3,      MB(18) },	/* 24-way set assoc, 64 byte line size */
-	{ 0xec, LVL_3,      MB(24) },	/* 24-way set assoc, 64 byte line size */
-	{ 0x00, 0, 0}
-};
-
-
 enum _cache_type {
-	CTYPE_NULL = 0,
-	CTYPE_DATA = 1,
-	CTYPE_INST = 2,
-	CTYPE_UNIFIED = 3
+	CTYPE_NULL	= 0,
+	CTYPE_DATA	= 1,
+	CTYPE_INST	= 2,
+	CTYPE_UNIFIED	= 3
 };
 
 union _cpuid4_leaf_eax {
 	struct {
-		enum _cache_type	type:5;
-		unsigned int		level:3;
-		unsigned int		is_self_initializing:1;
-		unsigned int		is_fully_associative:1;
-		unsigned int		reserved:4;
-		unsigned int		num_threads_sharing:12;
-		unsigned int		num_cores_on_die:6;
+		enum _cache_type	type			:5;
+		unsigned int		level			:3;
+		unsigned int		is_self_initializing	:1;
+		unsigned int		is_fully_associative	:1;
+		unsigned int		reserved		:4;
+		unsigned int		num_threads_sharing	:12;
+		unsigned int		num_cores_on_die	:6;
 	} split;
 	u32 full;
 };
 
 union _cpuid4_leaf_ebx {
 	struct {
-		unsigned int		coherency_line_size:12;
-		unsigned int		physical_line_partition:10;
-		unsigned int		ways_of_associativity:10;
+		unsigned int		coherency_line_size	:12;
+		unsigned int		physical_line_partition	:10;
+		unsigned int		ways_of_associativity	:10;
 	} split;
 	u32 full;
 };
 
 union _cpuid4_leaf_ecx {
 	struct {
-		unsigned int		number_of_sets:32;
+		unsigned int		number_of_sets		:32;
 	} split;
 	u32 full;
 };
 
-struct _cpuid4_info_regs {
+struct _cpuid4_info {
 	union _cpuid4_leaf_eax eax;
 	union _cpuid4_leaf_ebx ebx;
 	union _cpuid4_leaf_ecx ecx;
 	unsigned int id;
 	unsigned long size;
-	struct amd_northbridge *nb;
 };
 
-/* AMD doesn't have CPUID4. Emulate it here to report the same
-   information to the user.  This makes some assumptions about the machine:
-   L2 not shared, no SMT etc. that is currently true on AMD CPUs.
+/* Map CPUID(0x4) EAX.cache_type to <linux/cacheinfo.h> types */
+static const enum cache_type cache_type_map[] = {
+	[CTYPE_NULL]	= CACHE_TYPE_NOCACHE,
+	[CTYPE_DATA]	= CACHE_TYPE_DATA,
+	[CTYPE_INST]	= CACHE_TYPE_INST,
+	[CTYPE_UNIFIED] = CACHE_TYPE_UNIFIED,
+};
+
+/*
+ * Fallback AMD CPUID(0x4) emulation
+ * AMD CPUs with TOPOEXT can just use CPUID(0x8000001d)
+ *
+ * @AMD_L2_L3_INVALID_ASSOC: cache info for the respective L2/L3 cache should
+ * be determined from CPUID(0x8000001d) instead of CPUID(0x80000006).
+ */
+
+#define AMD_CPUID4_FULLY_ASSOCIATIVE	0xffff
+#define AMD_L2_L3_INVALID_ASSOC		0x9
 
-   In theory the TLBs could be reported as fake type (they are in "dummy").
-   Maybe later */
 union l1_cache {
 	struct {
-		unsigned line_size:8;
-		unsigned lines_per_tag:8;
-		unsigned assoc:8;
-		unsigned size_in_kb:8;
+		unsigned line_size	:8;
+		unsigned lines_per_tag	:8;
+		unsigned assoc		:8;
+		unsigned size_in_kb	:8;
 	};
-	unsigned val;
+	unsigned int val;
 };
 
 union l2_cache {
 	struct {
-		unsigned line_size:8;
-		unsigned lines_per_tag:4;
-		unsigned assoc:4;
-		unsigned size_in_kb:16;
+		unsigned line_size	:8;
+		unsigned lines_per_tag	:4;
+		unsigned assoc		:4;
+		unsigned size_in_kb	:16;
 	};
-	unsigned val;
+	unsigned int val;
 };
 
 union l3_cache {
 	struct {
-		unsigned line_size:8;
-		unsigned lines_per_tag:4;
-		unsigned assoc:4;
-		unsigned res:2;
-		unsigned size_encoded:14;
+		unsigned line_size	:8;
+		unsigned lines_per_tag	:4;
+		unsigned assoc		:4;
+		unsigned res		:2;
+		unsigned size_encoded	:14;
 	};
-	unsigned val;
+	unsigned int val;
 };
 
+/* L2/L3 associativity mapping */
 static const unsigned short assocs[] = {
-	[1] = 1,
-	[2] = 2,
-	[4] = 4,
-	[6] = 8,
-	[8] = 16,
-	[0xa] = 32,
-	[0xb] = 48,
-	[0xc] = 64,
-	[0xd] = 96,
-	[0xe] = 128,
-	[0xf] = 0xffff /* fully associative - no way to show this currently */
+	[1]		= 1,
+	[2]		= 2,
+	[3]		= 3,
+	[4]		= 4,
+	[5]		= 6,
+	[6]		= 8,
+	[8]		= 16,
+	[0xa]		= 32,
+	[0xb]		= 48,
+	[0xc]		= 64,
+	[0xd]		= 96,
+	[0xe]		= 128,
+	[0xf]		= AMD_CPUID4_FULLY_ASSOCIATIVE
 };
 
 static const unsigned char levels[] = { 1, 1, 2, 3 };
-static const unsigned char types[] = { 1, 2, 3, 3 };
+static const unsigned char types[]  = { 1, 2, 3, 3 };
 
-static const enum cache_type cache_type_map[] = {
-	[CTYPE_NULL] = CACHE_TYPE_NOCACHE,
-	[CTYPE_DATA] = CACHE_TYPE_DATA,
-	[CTYPE_INST] = CACHE_TYPE_INST,
-	[CTYPE_UNIFIED] = CACHE_TYPE_UNIFIED,
-};
-
-static void
-amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
-		     union _cpuid4_leaf_ebx *ebx,
-		     union _cpuid4_leaf_ecx *ecx)
+static void legacy_amd_cpuid4(int index, union _cpuid4_leaf_eax *eax,
+			      union _cpuid4_leaf_ebx *ebx, union _cpuid4_leaf_ecx *ecx)
 {
-	unsigned dummy;
-	unsigned line_size, lines_per_tag, assoc, size_in_kb;
-	union l1_cache l1i, l1d;
+	unsigned int dummy, line_size, lines_per_tag, assoc, size_in_kb;
+	union l1_cache l1i, l1d, *l1;
 	union l2_cache l2;
 	union l3_cache l3;
-	union l1_cache *l1 = &l1d;
 
 	eax->full = 0;
 	ebx->full = 0;
@@ -251,430 +163,155 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	cpuid(0x80000005, &dummy, &dummy, &l1d.val, &l1i.val);
 	cpuid(0x80000006, &dummy, &dummy, &l2.val, &l3.val);
 
-	switch (leaf) {
+	l1 = &l1d;
+	switch (index) {
 	case 1:
 		l1 = &l1i;
 		fallthrough;
 	case 0:
 		if (!l1->val)
 			return;
-		assoc = assocs[l1->assoc];
-		line_size = l1->line_size;
-		lines_per_tag = l1->lines_per_tag;
-		size_in_kb = l1->size_in_kb;
+
+		assoc		= (l1->assoc == 0xff) ? AMD_CPUID4_FULLY_ASSOCIATIVE : l1->assoc;
+		line_size	= l1->line_size;
+		lines_per_tag	= l1->lines_per_tag;
+		size_in_kb	= l1->size_in_kb;
 		break;
 	case 2:
-		if (!l2.val)
+		if (!l2.assoc || l2.assoc == AMD_L2_L3_INVALID_ASSOC)
 			return;
-		assoc = assocs[l2.assoc];
-		line_size = l2.line_size;
-		lines_per_tag = l2.lines_per_tag;
-		/* cpu_data has errata corrections for K7 applied */
-		size_in_kb = __this_cpu_read(cpu_info.x86_cache_size);
+
+		/* Use x86_cache_size as it might have K7 errata fixes */
+		assoc		= assocs[l2.assoc];
+		line_size	= l2.line_size;
+		lines_per_tag	= l2.lines_per_tag;
+		size_in_kb	= __this_cpu_read(cpu_info.x86_cache_size);
 		break;
 	case 3:
-		if (!l3.val)
+		if (!l3.assoc || l3.assoc == AMD_L2_L3_INVALID_ASSOC)
 			return;
-		assoc = assocs[l3.assoc];
-		line_size = l3.line_size;
-		lines_per_tag = l3.lines_per_tag;
-		size_in_kb = l3.size_encoded * 512;
+
+		assoc		= assocs[l3.assoc];
+		line_size	= l3.line_size;
+		lines_per_tag	= l3.lines_per_tag;
+		size_in_kb	= l3.size_encoded * 512;
 		if (boot_cpu_has(X86_FEATURE_AMD_DCM)) {
-			size_in_kb = size_in_kb >> 1;
-			assoc = assoc >> 1;
+			size_in_kb	= size_in_kb >> 1;
+			assoc		= assoc >> 1;
 		}
 		break;
 	default:
 		return;
 	}
 
-	eax->split.is_self_initializing = 1;
-	eax->split.type = types[leaf];
-	eax->split.level = levels[leaf];
-	eax->split.num_threads_sharing = 0;
-	eax->split.num_cores_on_die = topology_num_cores_per_package();
+	eax->split.is_self_initializing		= 1;
+	eax->split.type				= types[index];
+	eax->split.level			= levels[index];
+	eax->split.num_threads_sharing		= 0;
+	eax->split.num_cores_on_die		= topology_num_cores_per_package();
 
-
-	if (assoc == 0xffff)
+	if (assoc == AMD_CPUID4_FULLY_ASSOCIATIVE)
 		eax->split.is_fully_associative = 1;
-	ebx->split.coherency_line_size = line_size - 1;
-	ebx->split.ways_of_associativity = assoc - 1;
-	ebx->split.physical_line_partition = lines_per_tag - 1;
-	ecx->split.number_of_sets = (size_in_kb * 1024) / line_size /
-		(ebx->split.ways_of_associativity + 1) - 1;
-}
-
-#if defined(CONFIG_AMD_NB) && defined(CONFIG_SYSFS)
-
-/*
- * 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 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 *this_leaf, char *buf,
-				  unsigned int slot)
-{
-	int index;
-	struct amd_northbridge *nb = this_leaf->priv;
-
-	index = amd_get_l3_disable_slot(nb, slot);
-	if (index >= 0)
-		return sprintf(buf, "%d\n", index);
-
-	return sprintf(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 *this_leaf = dev_get_drvdata(dev);		\
-	return show_cache_disable(this_leaf, buf, slot);		\
-}
-SHOW_CACHE_DISABLE(0)
-SHOW_CACHE_DISABLE(1)
-
-static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu,
-				 unsigned 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 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 *this_leaf,
-				   const char *buf, size_t count,
-				   unsigned int slot)
-{
-	unsigned long val = 0;
-	int cpu, err = 0;
-	struct amd_northbridge *nb = this_leaf->priv;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	cpu = cpumask_first(&this_leaf->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 *this_leaf = dev_get_drvdata(dev);		\
-	return store_cache_disable(this_leaf, 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 *this_leaf = dev_get_drvdata(dev);
-	int cpu = cpumask_first(&this_leaf->shared_cpu_map);
-
-	return sprintf(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 *this_leaf = dev_get_drvdata(dev);
-	int cpu = cpumask_first(&this_leaf->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;
+	ebx->split.coherency_line_size		= line_size - 1;
+	ebx->split.ways_of_associativity	= assoc - 1;
+	ebx->split.physical_line_partition	= lines_per_tag - 1;
+	ecx->split.number_of_sets		= (size_in_kb * 1024) / line_size /
+		(ebx->split.ways_of_associativity + 1) - 1;
 }
 
-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)
+static int cpuid4_info_fill_done(struct _cpuid4_info *id4, union _cpuid4_leaf_eax eax,
+				 union _cpuid4_leaf_ebx ebx, union _cpuid4_leaf_ecx ecx)
 {
-	struct device *dev = kobj_to_dev(kobj);
-	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
-	umode_t mode = attr->mode;
-
-	if (!this_leaf->priv)
-		return 0;
-
-	if ((attr == &dev_attr_subcaches.attr) &&
-	    amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
-		return mode;
+	if (eax.split.type == CTYPE_NULL)
+		return -EIO;
 
-	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;
+	id4->eax = eax;
+	id4->ebx = ebx;
+	id4->ecx = ecx;
+	id4->size = (ecx.split.number_of_sets          + 1) *
+		    (ebx.split.coherency_line_size     + 1) *
+		    (ebx.split.physical_line_partition + 1) *
+		    (ebx.split.ways_of_associativity   + 1);
 
 	return 0;
 }
 
-static struct attribute_group cache_private_group = {
-	.is_visible = cache_private_attrs_is_visible,
-};
-
-static void init_amd_l3_attrs(void)
-{
-	int n = 1;
-	static struct attribute **amd_l3_attrs;
-
-	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 *this_leaf)
+static int amd_fill_cpuid4_info(int index, struct _cpuid4_info *id4)
 {
-	struct amd_northbridge *nb = this_leaf->priv;
-
-	if (this_leaf->level < 3 || !nb)
-		return NULL;
+	union _cpuid4_leaf_eax eax;
+	union _cpuid4_leaf_ebx ebx;
+	union _cpuid4_leaf_ecx ecx;
+	u32 ignored;
 
-	if (nb && nb->l3_cache.indices)
-		init_amd_l3_attrs();
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT) || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+		cpuid_count(0x8000001d, index, &eax.full, &ebx.full, &ecx.full, &ignored);
+	else
+		legacy_amd_cpuid4(index, &eax, &ebx, &ecx);
 
-	return &cache_private_group;
+	return cpuid4_info_fill_done(id4, eax, ebx, ecx);
 }
 
-static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index)
+static int intel_fill_cpuid4_info(int index, struct _cpuid4_info *id4)
 {
-	int node;
+	union _cpuid4_leaf_eax eax;
+	union _cpuid4_leaf_ebx ebx;
+	union _cpuid4_leaf_ecx ecx;
+	u32 ignored;
 
-	/* only for L3, and not in virtualized environments */
-	if (index < 3)
-		return;
+	cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &ignored);
 
-	node = topology_amd_node_id(smp_processor_id());
-	this_leaf->nb = node_to_amd_nb(node);
-	if (this_leaf->nb && !this_leaf->nb->l3_cache.indices)
-		amd_calc_l3_indices(this_leaf->nb);
+	return cpuid4_info_fill_done(id4, eax, ebx, ecx);
 }
-#else
-#define amd_init_l3_cache(x, y)
-#endif  /* CONFIG_AMD_NB && CONFIG_SYSFS */
 
-static int
-cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf)
+static int fill_cpuid4_info(int index, struct _cpuid4_info *id4)
 {
-	union _cpuid4_leaf_eax	eax;
-	union _cpuid4_leaf_ebx	ebx;
-	union _cpuid4_leaf_ecx	ecx;
-	unsigned		edx;
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
-		if (boot_cpu_has(X86_FEATURE_TOPOEXT))
-			cpuid_count(0x8000001d, index, &eax.full,
-				    &ebx.full, &ecx.full, &edx);
-		else
-			amd_cpuid4(index, &eax, &ebx, &ecx);
-		amd_init_l3_cache(this_leaf, index);
-	} else if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
-		cpuid_count(0x8000001d, index, &eax.full,
-			    &ebx.full, &ecx.full, &edx);
-		amd_init_l3_cache(this_leaf, index);
-	} else {
-		cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
-	}
+	u8 cpu_vendor = boot_cpu_data.x86_vendor;
 
-	if (eax.split.type == CTYPE_NULL)
-		return -EIO; /* better error ? */
-
-	this_leaf->eax = eax;
-	this_leaf->ebx = ebx;
-	this_leaf->ecx = ecx;
-	this_leaf->size = (ecx.split.number_of_sets          + 1) *
-			  (ebx.split.coherency_line_size     + 1) *
-			  (ebx.split.physical_line_partition + 1) *
-			  (ebx.split.ways_of_associativity   + 1);
-	return 0;
+	return (cpu_vendor == X86_VENDOR_AMD || cpu_vendor == X86_VENDOR_HYGON) ?
+		amd_fill_cpuid4_info(index, id4) :
+		intel_fill_cpuid4_info(index, id4);
 }
 
 static int find_num_cache_leaves(struct cpuinfo_x86 *c)
 {
-	unsigned int		eax, ebx, ecx, edx, op;
-	union _cpuid4_leaf_eax	cache_eax;
-	int 			i = -1;
-
-	if (c->x86_vendor == X86_VENDOR_AMD ||
-	    c->x86_vendor == X86_VENDOR_HYGON)
-		op = 0x8000001d;
-	else
-		op = 4;
+	unsigned int eax, ebx, ecx, edx, op;
+	union _cpuid4_leaf_eax cache_eax;
+	int i = -1;
 
+	/* Do a CPUID(op) loop to calculate num_cache_leaves */
+	op = (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) ? 0x8000001d : 4;
 	do {
 		++i;
-		/* Do cpuid(op) loop to find out num_cache_leaves */
 		cpuid_count(op, i, &eax, &ebx, &ecx, &edx);
 		cache_eax.full = eax;
 	} while (cache_eax.split.type != CTYPE_NULL);
 	return i;
 }
 
+/*
+ * AMD/Hygon CPUs may have multiple LLCs if L3 caches exist.
+ */
+
 void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id)
 {
-	/*
-	 * We may have multiple LLCs if L3 caches exist, so check if we
-	 * have an L3 cache by looking at the L3 cache CPUID leaf.
-	 */
-	if (!cpuid_edx(0x80000006))
+	if (!cpuid_amd_hygon_has_l3_cache())
 		return;
 
 	if (c->x86 < 0x17) {
-		/* LLC is at the node level. */
+		/* Pre-Zen: LLC is at the node level */
 		c->topo.llc_id = die_id;
 	} else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
 		/*
-		 * LLC is at the core complex level.
-		 * Core complex ID is ApicId[3] for these processors.
+		 * Family 17h up to 1F models: LLC is at the core
+		 * complex level.  Core complex ID is ApicId[3].
 		 */
 		c->topo.llc_id = c->topo.apicid >> 3;
 	} else {
 		/*
-		 * LLC ID is calculated from the number of threads sharing the
-		 * cache.
-		 * */
+		 * Newer families: LLC ID is calculated from the number
+		 * of threads sharing the L3 cache.
+		 */
 		u32 eax, ebx, ecx, edx, num_sharing_cache = 0;
 		u32 llc_index = find_num_cache_leaves(c) - 1;
 
@@ -683,25 +320,21 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id)
 			num_sharing_cache = ((eax >> 14) & 0xfff) + 1;
 
 		if (num_sharing_cache) {
-			int bits = get_count_order(num_sharing_cache);
+			int index_msb = get_count_order(num_sharing_cache);
 
-			c->topo.llc_id = c->topo.apicid >> bits;
+			c->topo.llc_id = c->topo.apicid >> index_msb;
 		}
 	}
 }
 
 void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c)
 {
-	/*
-	 * We may have multiple LLCs if L3 caches exist, so check if we
-	 * have an L3 cache by looking at the L3 cache CPUID leaf.
-	 */
-	if (!cpuid_edx(0x80000006))
+	if (!cpuid_amd_hygon_has_l3_cache())
 		return;
 
 	/*
-	 * LLC is at the core complex level.
-	 * Core complex ID is ApicId[3] for these processors.
+	 * Hygons are similar to AMD Family 17h up to 1F models: LLC is
+	 * at the core complex level.  Core complex ID is ApicId[3].
 	 */
 	c->topo.llc_id = c->topo.apicid >> 3;
 }
@@ -710,14 +343,10 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 {
 	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
 
-	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT))
 		ci->num_leaves = find_num_cache_leaves(c);
-	} else if (c->extended_cpuid_level >= 0x80000006) {
-		if (cpuid_edx(0x80000006) & 0xf000)
-			ci->num_leaves = 4;
-		else
-			ci->num_leaves = 3;
-	}
+	else if (c->extended_cpuid_level >= 0x80000006)
+		ci->num_leaves = (cpuid_edx(0x80000006) & 0xf000) ? 4 : 3;
 }
 
 void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
@@ -727,148 +356,131 @@ void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
 	ci->num_leaves = find_num_cache_leaves(c);
 }
 
-void init_intel_cacheinfo(struct cpuinfo_x86 *c)
+static void intel_cacheinfo_done(struct cpuinfo_x86 *c, unsigned int l3,
+				 unsigned int l2, unsigned int l1i, unsigned int l1d)
 {
-	/* Cache sizes */
-	unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0;
-	unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
-	unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
-	unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
-	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
+	/*
+	 * If llc_id is still unset, then cpuid_level < 4, which implies
+	 * that the only possibility left is SMT.  Since CPUID(0x2) doesn't
+	 * specify any shared caches and SMT shares all caches, we can
+	 * unconditionally set LLC ID to the package ID so that all
+	 * threads share it.
+	 */
+	if (c->topo.llc_id == BAD_APICID)
+		c->topo.llc_id = c->topo.pkg_id;
 
-	if (c->cpuid_level > 3) {
-		/*
-		 * There should be at least one leaf. A non-zero value means
-		 * that the number of leaves has been initialized.
-		 */
-		if (!ci->num_leaves)
-			ci->num_leaves = find_num_cache_leaves(c);
+	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : l1i + l1d);
 
-		/*
-		 * Whenever possible use cpuid(4), deterministic cache
-		 * parameters cpuid leaf to find the cache details
-		 */
-		for (i = 0; i < ci->num_leaves; i++) {
-			struct _cpuid4_info_regs this_leaf = {};
-			int retval;
+	if (!l2)
+		cpu_detect_cache_sizes(c);
+}
 
-			retval = cpuid4_cache_lookup_regs(i, &this_leaf);
-			if (retval < 0)
-				continue;
+/*
+ * Legacy Intel CPUID(0x2) path if CPUID(0x4) is not available.
+ */
+static void intel_cacheinfo_0x2(struct cpuinfo_x86 *c)
+{
+	unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0;
+	const struct leaf_0x2_table *desc;
+	union leaf_0x2_regs regs;
+	u8 *ptr;
 
-			switch (this_leaf.eax.split.level) {
-			case 1:
-				if (this_leaf.eax.split.type == CTYPE_DATA)
-					new_l1d = this_leaf.size/1024;
-				else if (this_leaf.eax.split.type == CTYPE_INST)
-					new_l1i = this_leaf.size/1024;
-				break;
-			case 2:
-				new_l2 = this_leaf.size/1024;
-				num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
-				index_msb = get_count_order(num_threads_sharing);
-				l2_id = c->topo.apicid & ~((1 << index_msb) - 1);
-				break;
-			case 3:
-				new_l3 = this_leaf.size/1024;
-				num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
-				index_msb = get_count_order(num_threads_sharing);
-				l3_id = c->topo.apicid & ~((1 << index_msb) - 1);
-				break;
-			default:
-				break;
-			}
-		}
-	}
+	if (c->cpuid_level < 2)
+		return;
 
-	/* Don't use CPUID(2) if CPUID(4) is supported. */
-	if (!ci->num_leaves && c->cpuid_level > 1) {
-		/* supports eax=2  call */
-		int j, n;
-		unsigned int regs[4];
-		unsigned char *dp = (unsigned char *)regs;
-
-		/* 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++) {
-				unsigned char des = dp[j];
-				unsigned char k = 0;
-
-				/* look up this descriptor in the table */
-				while (cache_table[k].descriptor != 0) {
-					if (cache_table[k].descriptor == des) {
-						switch (cache_table[k].cache_type) {
-						case LVL_1_INST:
-							l1i += cache_table[k].size;
-							break;
-						case LVL_1_DATA:
-							l1d += cache_table[k].size;
-							break;
-						case LVL_2:
-							l2 += cache_table[k].size;
-							break;
-						case LVL_3:
-							l3 += cache_table[k].size;
-							break;
-						}
-
-						break;
-					}
-
-					k++;
-				}
-			}
+	cpuid_leaf_0x2(&regs);
+	for_each_cpuid_0x2_desc(regs, ptr, desc) {
+		switch (desc->c_type) {
+		case CACHE_L1_INST:	l1i += desc->c_size; break;
+		case CACHE_L1_DATA:	l1d += desc->c_size; break;
+		case CACHE_L2:		l2  += desc->c_size; break;
+		case CACHE_L3:		l3  += desc->c_size; break;
 		}
 	}
 
-	if (new_l1d)
-		l1d = new_l1d;
+	intel_cacheinfo_done(c, l3, l2, l1i, l1d);
+}
 
-	if (new_l1i)
-		l1i = new_l1i;
+static unsigned int calc_cache_topo_id(struct cpuinfo_x86 *c, const struct _cpuid4_info *id4)
+{
+	unsigned int num_threads_sharing;
+	int index_msb;
 
-	if (new_l2) {
-		l2 = new_l2;
-		c->topo.llc_id = l2_id;
-		c->topo.l2c_id = l2_id;
-	}
+	num_threads_sharing = 1 + id4->eax.split.num_threads_sharing;
+	index_msb = get_count_order(num_threads_sharing);
+	return c->topo.apicid & ~((1 << index_msb) - 1);
+}
 
-	if (new_l3) {
-		l3 = new_l3;
-		c->topo.llc_id = l3_id;
-	}
+static bool intel_cacheinfo_0x4(struct cpuinfo_x86 *c)
+{
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
+	unsigned int l2_id = BAD_APICID, l3_id = BAD_APICID;
+	unsigned int l1d = 0, l1i = 0, l2 = 0, l3 = 0;
+
+	if (c->cpuid_level < 4)
+		return false;
 
 	/*
-	 * If llc_id is not yet set, this means cpuid_level < 4 which in
-	 * turns means that the only possibility is SMT (as indicated in
-	 * cpuid1). Since cpuid2 doesn't specify shared caches, and we know
-	 * that SMT shares all caches, we can unconditionally set cpu_llc_id to
-	 * c->topo.pkg_id.
+	 * There should be at least one leaf. A non-zero value means
+	 * that the number of leaves has been previously initialized.
 	 */
-	if (c->topo.llc_id == BAD_APICID)
-		c->topo.llc_id = c->topo.pkg_id;
+	if (!ci->num_leaves)
+		ci->num_leaves = find_num_cache_leaves(c);
+
+	if (!ci->num_leaves)
+		return false;
 
-	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
+	for (int i = 0; i < ci->num_leaves; i++) {
+		struct _cpuid4_info id4 = {};
+		int ret;
 
-	if (!l2)
-		cpu_detect_cache_sizes(c);
+		ret = intel_fill_cpuid4_info(i, &id4);
+		if (ret < 0)
+			continue;
+
+		switch (id4.eax.split.level) {
+		case 1:
+			if (id4.eax.split.type == CTYPE_DATA)
+				l1d = id4.size / 1024;
+			else if (id4.eax.split.type == CTYPE_INST)
+				l1i = id4.size / 1024;
+			break;
+		case 2:
+			l2 = id4.size / 1024;
+			l2_id = calc_cache_topo_id(c, &id4);
+			break;
+		case 3:
+			l3 = id4.size / 1024;
+			l3_id = calc_cache_topo_id(c, &id4);
+			break;
+		default:
+			break;
+		}
+	}
+
+	c->topo.l2c_id = l2_id;
+	c->topo.llc_id = (l3_id == BAD_APICID) ? l2_id : l3_id;
+	intel_cacheinfo_done(c, l3, l2, l1i, l1d);
+	return true;
+}
+
+void init_intel_cacheinfo(struct cpuinfo_x86 *c)
+{
+	/* Don't use CPUID(0x2) if CPUID(0x4) is supported. */
+	if (intel_cacheinfo_0x4(c))
+		return;
+
+	intel_cacheinfo_0x2(c);
 }
 
+/*
+ * <linux/cacheinfo.h> shared_cpu_map setup, AMD/Hygon
+ */
 static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
-				    struct _cpuid4_info_regs *base)
+				    const struct _cpuid4_info *id4)
 {
 	struct cpu_cacheinfo *this_cpu_ci;
-	struct cacheinfo *this_leaf;
+	struct cacheinfo *ci;
 	int i, sibling;
 
 	/*
@@ -880,18 +492,18 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
 			this_cpu_ci = get_cpu_cacheinfo(i);
 			if (!this_cpu_ci->info_list)
 				continue;
-			this_leaf = this_cpu_ci->info_list + index;
+
+			ci = this_cpu_ci->info_list + index;
 			for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) {
 				if (!cpu_online(sibling))
 					continue;
-				cpumask_set_cpu(sibling,
-						&this_leaf->shared_cpu_map);
+				cpumask_set_cpu(sibling, &ci->shared_cpu_map);
 			}
 		}
 	} else if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		unsigned int apicid, nshared, first, last;
 
-		nshared = base->eax.split.num_threads_sharing + 1;
+		nshared = id4->eax.split.num_threads_sharing + 1;
 		apicid = cpu_data(cpu).topo.apicid;
 		first = apicid - (apicid % nshared);
 		last = first + nshared - 1;
@@ -905,14 +517,13 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
 			if ((apicid < first) || (apicid > last))
 				continue;
 
-			this_leaf = this_cpu_ci->info_list + index;
+			ci = this_cpu_ci->info_list + index;
 
 			for_each_online_cpu(sibling) {
 				apicid = cpu_data(sibling).topo.apicid;
 				if ((apicid < first) || (apicid > last))
 					continue;
-				cpumask_set_cpu(sibling,
-						&this_leaf->shared_cpu_map);
+				cpumask_set_cpu(sibling, &ci->shared_cpu_map);
 			}
 		}
 	} else
@@ -921,25 +532,27 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
 	return 1;
 }
 
+/*
+ * <linux/cacheinfo.h> shared_cpu_map setup, Intel + fallback AMD/Hygon
+ */
 static void __cache_cpumap_setup(unsigned int cpu, int index,
-				 struct _cpuid4_info_regs *base)
+				 const struct _cpuid4_info *id4)
 {
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-	struct cacheinfo *this_leaf, *sibling_leaf;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	struct cacheinfo *ci, *sibling_ci;
 	unsigned long num_threads_sharing;
 	int index_msb, i;
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	if (c->x86_vendor == X86_VENDOR_AMD ||
-	    c->x86_vendor == X86_VENDOR_HYGON) {
-		if (__cache_amd_cpumap_setup(cpu, index, base))
+	if (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) {
+		if (__cache_amd_cpumap_setup(cpu, index, id4))
 			return;
 	}
 
-	this_leaf = this_cpu_ci->info_list + index;
-	num_threads_sharing = 1 + base->eax.split.num_threads_sharing;
+	ci = this_cpu_ci->info_list + index;
+	num_threads_sharing = 1 + id4->eax.split.num_threads_sharing;
 
-	cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
+	cpumask_set_cpu(cpu, &ci->shared_cpu_map);
 	if (num_threads_sharing == 1)
 		return;
 
@@ -949,30 +562,29 @@ static void __cache_cpumap_setup(unsigned int cpu, int index,
 		if (cpu_data(i).topo.apicid >> index_msb == c->topo.apicid >> index_msb) {
 			struct cpu_cacheinfo *sib_cpu_ci = get_cpu_cacheinfo(i);
 
+			/* Skip if itself or no cacheinfo */
 			if (i == cpu || !sib_cpu_ci->info_list)
-				continue;/* skip if itself or no cacheinfo */
-			sibling_leaf = sib_cpu_ci->info_list + index;
-			cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
-			cpumask_set_cpu(cpu, &sibling_leaf->shared_cpu_map);
+				continue;
+
+			sibling_ci = sib_cpu_ci->info_list + index;
+			cpumask_set_cpu(i, &ci->shared_cpu_map);
+			cpumask_set_cpu(cpu, &sibling_ci->shared_cpu_map);
 		}
 }
 
-static void ci_leaf_init(struct cacheinfo *this_leaf,
-			 struct _cpuid4_info_regs *base)
+static void ci_info_init(struct cacheinfo *ci, const struct _cpuid4_info *id4,
+			 struct amd_northbridge *nb)
 {
-	this_leaf->id = base->id;
-	this_leaf->attributes = CACHE_ID;
-	this_leaf->level = base->eax.split.level;
-	this_leaf->type = cache_type_map[base->eax.split.type];
-	this_leaf->coherency_line_size =
-				base->ebx.split.coherency_line_size + 1;
-	this_leaf->ways_of_associativity =
-				base->ebx.split.ways_of_associativity + 1;
-	this_leaf->size = base->size;
-	this_leaf->number_of_sets = base->ecx.split.number_of_sets + 1;
-	this_leaf->physical_line_partition =
-				base->ebx.split.physical_line_partition + 1;
-	this_leaf->priv = base->nb;
+	ci->id				= id4->id;
+	ci->attributes			= CACHE_ID;
+	ci->level			= id4->eax.split.level;
+	ci->type			= cache_type_map[id4->eax.split.type];
+	ci->coherency_line_size		= id4->ebx.split.coherency_line_size + 1;
+	ci->ways_of_associativity	= id4->ebx.split.ways_of_associativity + 1;
+	ci->size			= id4->size;
+	ci->number_of_sets		= id4->ecx.split.number_of_sets + 1;
+	ci->physical_line_partition	= id4->ebx.split.physical_line_partition + 1;
+	ci->priv			= nb;
 }
 
 int init_cache_level(unsigned int cpu)
@@ -987,38 +599,45 @@ int init_cache_level(unsigned int cpu)
 }
 
 /*
- * The max shared threads number comes from CPUID.4:EAX[25-14] with input
+ * The max shared threads number comes from CPUID(0x4) EAX[25-14] with input
  * ECX as cache index. Then right shift apicid by the number's order to get
  * cache id for this cache node.
  */
-static void get_cache_id(int cpu, struct _cpuid4_info_regs *id4_regs)
+static void get_cache_id(int cpu, struct _cpuid4_info *id4)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	unsigned long num_threads_sharing;
 	int index_msb;
 
-	num_threads_sharing = 1 + id4_regs->eax.split.num_threads_sharing;
+	num_threads_sharing = 1 + id4->eax.split.num_threads_sharing;
 	index_msb = get_count_order(num_threads_sharing);
-	id4_regs->id = c->topo.apicid >> index_msb;
+	id4->id = c->topo.apicid >> index_msb;
 }
 
 int populate_cache_leaves(unsigned int cpu)
 {
-	unsigned int idx, ret;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
-	struct _cpuid4_info_regs id4_regs = {};
+	struct cacheinfo *ci = this_cpu_ci->info_list;
+	u8 cpu_vendor = boot_cpu_data.x86_vendor;
+	struct amd_northbridge *nb = NULL;
+	struct _cpuid4_info id4 = {};
+	int idx, ret;
 
 	for (idx = 0; idx < this_cpu_ci->num_leaves; idx++) {
-		ret = cpuid4_cache_lookup_regs(idx, &id4_regs);
+		ret = fill_cpuid4_info(idx, &id4);
 		if (ret)
 			return ret;
-		get_cache_id(cpu, &id4_regs);
-		ci_leaf_init(this_leaf++, &id4_regs);
-		__cache_cpumap_setup(cpu, idx, &id4_regs);
+
+		get_cache_id(cpu, &id4);
+
+		if (cpu_vendor == X86_VENDOR_AMD || cpu_vendor == X86_VENDOR_HYGON)
+			nb = amd_init_l3_cache(idx);
+
+		ci_info_init(ci++, &id4, nb);
+		__cache_cpumap_setup(cpu, idx, &id4);
 	}
-	this_cpu_ci->cpu_map_populated = true;
 
+	this_cpu_ci->cpu_map_populated = true;
 	return 0;
 }
 
@@ -1034,31 +653,33 @@ int populate_cache_leaves(unsigned int cpu)
 static unsigned long saved_cr4;
 static DEFINE_RAW_SPINLOCK(cache_disable_lock);
 
+/*
+ * Cache flushing is the most time-consuming step when programming the
+ * MTRRs.  On many Intel CPUs without known erratas, it can be skipped
+ * if the CPU declares cache self-snooping support.
+ */
+static void maybe_flush_caches(void)
+{
+	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+		wbinvd();
+}
+
 void cache_disable(void) __acquires(cache_disable_lock)
 {
 	unsigned long cr0;
 
 	/*
-	 * Note that this is not ideal
-	 * since the cache is only flushed/disabled for this CPU while the
-	 * MTRRs are changed, but changing this requires more invasive
-	 * changes to the way the kernel boots
+	 * This is not ideal since the cache is only flushed/disabled
+	 * for this CPU while the MTRRs are changed, but changing this
+	 * requires more invasive changes to the way the kernel boots.
 	 */
-
 	raw_spin_lock(&cache_disable_lock);
 
 	/* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
 	cr0 = read_cr0() | X86_CR0_CD;
 	write_cr0(cr0);
 
-	/*
-	 * Cache flushing is the most time-consuming step when programming
-	 * the MTRRs. Fortunately, as per the Intel Software Development
-	 * Manual, we can skip it if the processor supports cache self-
-	 * snooping.
-	 */
-	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
-		wbinvd();
+	maybe_flush_caches();
 
 	/* Save value of CR4 and clear Page Global Enable (bit 7) */
 	if (cpu_feature_enabled(X86_FEATURE_PGE)) {
@@ -1073,9 +694,7 @@ void cache_disable(void) __acquires(cache_disable_lock)
 	if (cpu_feature_enabled(X86_FEATURE_MTRR))
 		mtrr_disable();
 
-	/* Again, only flush caches if we have to. */
-	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
-		wbinvd();
+	maybe_flush_caches();
 }
 
 void cache_enable(void) __releases(cache_disable_lock)