Merge branch 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 boot updates from Ingo Molnar:

 - Centaur CPU updates (David Wang)

 - AMD and other CPU topology enumeration improvements and fixes
   (Borislav Petkov, Thomas Gleixner, Suravee Suthikulpanit)

 - Continued 5-level paging work (Kirill A. Shutemov)

* 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Mark __pgtable_l5_enabled __initdata
  x86/mm: Mark p4d_offset() __always_inline
  x86/mm: Introduce the 'no5lvl' kernel parameter
  x86/mm: Stop pretending pgtable_l5_enabled is a variable
  x86/mm: Unify pgtable_l5_enabled usage in early boot code
  x86/boot/compressed/64: Fix trampoline page table address calculation
  x86/CPU: Move x86_cpuinfo::x86_max_cores assignment to detect_num_cpu_cores()
  x86/Centaur: Report correct CPU/cache topology
  x86/CPU: Move cpu_detect_cache_sizes() into init_intel_cacheinfo()
  x86/CPU: Make intel_num_cpu_cores() generic
  x86/CPU: Move cpu local function declarations to local header
  x86/CPU/AMD: Derive CPU topology from CPUID function 0xB when available
  x86/CPU: Modify detect_extended_topology() to return result
  x86/CPU/AMD: Calculate last level cache ID from number of sharing threads
  x86/CPU: Rename intel_cacheinfo.c to cacheinfo.c
  perf/events/amd/uncore: Fix amd_uncore_llc ID to use pre-defined cpu_llc_id
  x86/CPU/AMD: Have smp_num_siblings and cpu_llc_id always be present
  x86/Centaur: Initialize supported CPU features properly

37 files changed, 260 insertions, 167 deletions

diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index 0cb325734cfb..af6cda0b7900 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "misc.h"
 
-#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE || CONFIG_X86_5LEVEL
 
 static unsigned long fs;
 static inline void set_fs(unsigned long seg)
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 8169e8b7a4dc..64037895b085 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -365,6 +365,7 @@ ENTRY(startup_64)
 	 * this function call.
 	 */
 	pushq	%rsi
+	movq	%rsi, %rdi		/* real mode address */
 	call	paging_prepare
 	popq	%rsi
 
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index a0a50b91ecef..b87a7582853d 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -47,7 +47,7 @@
 #include <linux/decompress/mm.h>
 
 #ifdef CONFIG_X86_5LEVEL
-unsigned int pgtable_l5_enabled __ro_after_init;
+unsigned int __pgtable_l5_enabled;
 unsigned int pgdir_shift __ro_after_init = 39;
 unsigned int ptrs_per_p4d __ro_after_init = 1;
 #endif
@@ -734,7 +734,7 @@ void choose_random_location(unsigned long input,
 
 #ifdef CONFIG_X86_5LEVEL
 	if (__read_cr4() & X86_CR4_LA57) {
-		pgtable_l5_enabled = 1;
+		__pgtable_l5_enabled = 1;
 		pgdir_shift = 48;
 		ptrs_per_p4d = 512;
 	}
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 9e11be4cae19..a423bdb42686 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -12,10 +12,8 @@
 #undef CONFIG_PARAVIRT_SPINLOCKS
 #undef CONFIG_KASAN
 
-#ifdef CONFIG_X86_5LEVEL
-/* cpu_feature_enabled() cannot be used that early */
-#define pgtable_l5_enabled __pgtable_l5_enabled
-#endif
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
 
 #include <linux/linkage.h>
 #include <linux/screen_info.h>
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index a362fa0b849c..8c5107545251 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -31,16 +31,23 @@ static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
  */
 unsigned long *trampoline_32bit __section(.data);
 
-struct paging_config paging_prepare(void)
+extern struct boot_params *boot_params;
+int cmdline_find_option_bool(const char *option);
+
+struct paging_config paging_prepare(void *rmode)
 {
 	struct paging_config paging_config = {};
 	unsigned long bios_start, ebda_start;
 
+	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
+	boot_params = rmode;
+
 	/*
 	 * Check if LA57 is desired and supported.
 	 *
-	 * There are two parts to the check:
+	 * There are several parts to the check:
 	 *   - if the kernel supports 5-level paging: CONFIG_X86_5LEVEL=y
+	 *   - if user asked to disable 5-level paging: no5lvl in cmdline
 	 *   - if the machine supports 5-level paging:
 	 *     + CPUID leaf 7 is supported
 	 *     + the leaf has the feature bit set
@@ -48,6 +55,7 @@ struct paging_config paging_prepare(void)
 	 * That's substitute for boot_cpu_has() in early boot code.
 	 */
 	if (IS_ENABLED(CONFIG_X86_5LEVEL) &&
+			!cmdline_find_option_bool("no5lvl") &&
 			native_cpuid_eax(0) >= 7 &&
 			(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) {
 		paging_config.l5_required = 1;
@@ -130,7 +138,7 @@ void cleanup_trampoline(void *pgtable)
 {
 	void *trampoline_pgtable;
 
-	trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET;
+	trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long);
 
 	/*
 	 * Move the top level page table out of trampoline memory,
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index f5cbbba99283..981ba5e8241b 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -19,6 +19,7 @@
 #include <asm/cpufeature.h>
 #include <asm/perf_event.h>
 #include <asm/msr.h>
+#include <asm/smp.h>
 
 #define NUM_COUNTERS_NB		4
 #define NUM_COUNTERS_L2		4
@@ -399,26 +400,8 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
 	}
 
 	if (amd_uncore_llc) {
-		unsigned int apicid = cpu_data(cpu).apicid;
-		unsigned int nshared, subleaf, prev_eax = 0;
-
 		uncore = *per_cpu_ptr(amd_uncore_llc, cpu);
-		/*
-		 * Iterate over Cache Topology Definition leaves until no
-		 * more cache descriptions are available.
-		 */
-		for (subleaf = 0; subleaf < 5; subleaf++) {
-			cpuid_count(0x8000001d, subleaf, &eax, &ebx, &ecx, &edx);
-
-			/* EAX[0:4] gives type of cache */
-			if (!(eax & 0x1f))
-				break;
-
-			prev_eax = eax;
-		}
-		nshared = ((prev_eax >> 14) & 0xfff) + 1;
-
-		uncore->id = apicid - (apicid % nshared);
+		uncore->id = per_cpu(cpu_llc_id, cpu);
 
 		uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);
 		*per_cpu_ptr(amd_uncore_llc, cpu) = uncore;
diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h
new file mode 100644
index 000000000000..e958e28f7ab5
--- /dev/null
+++ b/arch/x86/include/asm/cacheinfo.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_CACHEINFO_H
+#define _ASM_X86_CACHEINFO_H
+
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id);
+
+#endif /* _ASM_X86_CACHEINFO_H */
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 2c5a966dc222..6afac386a434 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -53,7 +53,7 @@
 #define __PHYSICAL_MASK_SHIFT	52
 
 #ifdef CONFIG_X86_5LEVEL
-#define __VIRTUAL_MASK_SHIFT	(pgtable_l5_enabled ? 56 : 47)
+#define __VIRTUAL_MASK_SHIFT	(pgtable_l5_enabled() ? 56 : 47)
 #else
 #define __VIRTUAL_MASK_SHIFT	47
 #endif
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 9be2bf13825b..d49bbf4bb5c8 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -574,14 +574,14 @@ static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
 }
 
 #define set_pgd(pgdp, pgdval) do {					\
-	if (pgtable_l5_enabled)						\
+	if (pgtable_l5_enabled())						\
 		__set_pgd(pgdp, pgdval);				\
 	else								\
 		set_p4d((p4d_t *)(pgdp), (p4d_t) { (pgdval).pgd });	\
 } while (0)
 
 #define pgd_clear(pgdp) do {						\
-	if (pgtable_l5_enabled)						\
+	if (pgtable_l5_enabled())						\
 		set_pgd(pgdp, __pgd(0));				\
 } while (0)
 
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 263c142a6a6c..ada6410fd2ec 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -167,7 +167,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 #if CONFIG_PGTABLE_LEVELS > 4
 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d)
 {
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return;
 	paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT);
 	set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d)));
@@ -193,7 +193,7 @@ extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d);
 static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 				  unsigned long address)
 {
-	if (pgtable_l5_enabled)
+	if (pgtable_l5_enabled())
 		___p4d_free_tlb(tlb, p4d);
 }
 
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index f1633de5a675..99ecde23c3ec 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -65,7 +65,7 @@ extern pmdval_t early_pmd_flags;
 
 #ifndef __PAGETABLE_P4D_FOLDED
 #define set_pgd(pgdp, pgd)		native_set_pgd(pgdp, pgd)
-#define pgd_clear(pgd)			(pgtable_l5_enabled ? native_pgd_clear(pgd) : 0)
+#define pgd_clear(pgd)			(pgtable_l5_enabled() ? native_pgd_clear(pgd) : 0)
 #endif
 
 #ifndef set_p4d
@@ -881,7 +881,7 @@ static inline unsigned long p4d_index(unsigned long address)
 #if CONFIG_PGTABLE_LEVELS > 4
 static inline int pgd_present(pgd_t pgd)
 {
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return 1;
 	return pgd_flags(pgd) & _PAGE_PRESENT;
 }
@@ -898,9 +898,9 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd)
 #define pgd_page(pgd)	pfn_to_page(pgd_pfn(pgd))
 
 /* to find an entry in a page-table-directory. */
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+static __always_inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 {
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return (p4d_t *)pgd;
 	return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address);
 }
@@ -909,7 +909,7 @@ static inline int pgd_bad(pgd_t pgd)
 {
 	unsigned long ignore_flags = _PAGE_USER;
 
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return 0;
 
 	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
@@ -920,7 +920,7 @@ static inline int pgd_bad(pgd_t pgd)
 
 static inline int pgd_none(pgd_t pgd)
 {
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return 0;
 	/*
 	 * There is no need to do a workaround for the KNL stray
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index e3225e83db7d..d9a001a4a872 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -15,7 +15,7 @@
 # include <asm/pgtable-2level_types.h>
 #endif
 
-#define pgtable_l5_enabled 0
+#define pgtable_l5_enabled() 0
 
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 877bc27718ae..3c5385f9a88f 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -220,7 +220,7 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
 	pgd_t pgd;
 
-	if (pgtable_l5_enabled || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) {
+	if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) {
 		*p4dp = p4d;
 		return;
 	}
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index adb47552e6bb..054765ab2da2 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -22,12 +22,23 @@ typedef struct { pteval_t pte; } pte_t;
 
 #ifdef CONFIG_X86_5LEVEL
 extern unsigned int __pgtable_l5_enabled;
-#ifndef pgtable_l5_enabled
-#define pgtable_l5_enabled cpu_feature_enabled(X86_FEATURE_LA57)
-#endif
+
+#ifdef USE_EARLY_PGTABLE_L5
+/*
+ * cpu_feature_enabled() is not available in early boot code.
+ * Use variable instead.
+ */
+static inline bool pgtable_l5_enabled(void)
+{
+	return __pgtable_l5_enabled;
+}
 #else
-#define pgtable_l5_enabled 0
-#endif
+#define pgtable_l5_enabled() cpu_feature_enabled(X86_FEATURE_LA57)
+#endif /* USE_EARLY_PGTABLE_L5 */
+
+#else
+#define pgtable_l5_enabled() 0
+#endif /* CONFIG_X86_5LEVEL */
 
 extern unsigned int pgdir_shift;
 extern unsigned int ptrs_per_p4d;
@@ -102,7 +113,7 @@ extern unsigned int ptrs_per_p4d;
 
 #define LDT_PGD_ENTRY_L4	-3UL
 #define LDT_PGD_ENTRY_L5	-112UL
-#define LDT_PGD_ENTRY		(pgtable_l5_enabled ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
+#define LDT_PGD_ENTRY		(pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
 #define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 
 #define __VMALLOC_BASE_L4	0xffffc90000000000UL
@@ -116,7 +127,7 @@ extern unsigned int ptrs_per_p4d;
 
 #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
 # define VMALLOC_START		vmalloc_base
-# define VMALLOC_SIZE_TB	(pgtable_l5_enabled ? VMALLOC_SIZE_TB_L5 : VMALLOC_SIZE_TB_L4)
+# define VMALLOC_SIZE_TB	(pgtable_l5_enabled() ? VMALLOC_SIZE_TB_L5 : VMALLOC_SIZE_TB_L4)
 # define VMEMMAP_START		vmemmap_base
 #else
 # define VMALLOC_START		__VMALLOC_BASE_L4
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 21a114914ba4..e28add6b791f 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -186,15 +186,6 @@ extern void identify_boot_cpu(void);
 extern void identify_secondary_cpu(struct cpuinfo_x86 *);
 extern void print_cpu_info(struct cpuinfo_x86 *);
 void print_cpu_msr(struct cpuinfo_x86 *);
-extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
-extern u32 get_scattered_cpuid_leaf(unsigned int level,
-				    unsigned int sub_leaf,
-				    enum cpuid_regs_idx reg);
-extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
-extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
-
-extern void detect_extended_topology(struct cpuinfo_x86 *c);
-extern void detect_ht(struct cpuinfo_x86 *c);
 
 #ifdef CONFIG_X86_32
 extern int have_cpuid_p(void);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index f75bff8f9d82..547c4fe50711 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -171,7 +171,6 @@ static inline int wbinvd_on_all_cpus(void)
 	wbinvd();
 	return 0;
 }
-#define smp_num_siblings	1
 #endif /* CONFIG_SMP */
 
 extern unsigned disabled_cpus;
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 4617a2bf123c..199218719a86 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -27,8 +27,8 @@
 # endif
 #else /* CONFIG_X86_32 */
 # define SECTION_SIZE_BITS	27 /* matt - 128 is convenient right now */
-# define MAX_PHYSADDR_BITS	(pgtable_l5_enabled ? 52 : 44)
-# define MAX_PHYSMEM_BITS	(pgtable_l5_enabled ? 52 : 46)
+# define MAX_PHYSADDR_BITS	(pgtable_l5_enabled() ? 52 : 44)
+# define MAX_PHYSMEM_BITS	(pgtable_l5_enabled() ? 52 : 46)
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index a66229f51b12..7a40196967cb 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -17,7 +17,7 @@ KCOV_INSTRUMENT_perf_event.o := n
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_common.o		:= $(nostackp)
 
-obj-y			:= intel_cacheinfo.o scattered.o topology.o
+obj-y			:= cacheinfo.o scattered.o topology.o
 obj-y			+= common.o
 obj-y			+= rdrand.o
 obj-y			+= match.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1b18be3f35a8..082d7875cef8 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -9,6 +9,7 @@
 #include <linux/random.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
+#include <asm/cacheinfo.h>
 #include <asm/cpu.h>
 #include <asm/spec-ctrl.h>
 #include <asm/smp.h>
@@ -298,7 +299,6 @@ static int nearby_node(int apicid)
 }
 #endif
 
-#ifdef CONFIG_SMP
 /*
  * Fix up cpu_core_id for pre-F17h systems to be in the
  * [0 .. cores_per_node - 1] range. Not really needed but
@@ -328,6 +328,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 	/* get information required for multi-node processors */
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+		int err;
 		u32 eax, ebx, ecx, edx;
 
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
@@ -346,21 +347,15 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		}
 
 		/*
-		 * We may have multiple LLCs if L3 caches exist, so check if we
-		 * have an L3 cache by looking at the L3 cache CPUID leaf.
+		 * In case leaf B is available, use it to derive
+		 * topology information.
 		 */
-		if (cpuid_edx(0x80000006)) {
-			if (c->x86 == 0x17) {
-				/*
-				 * LLC is at the core complex level.
-				 * Core complex id is ApicId[3].
-				 */
-				per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
-			} else {
-				/* LLC is at the node level. */
-				per_cpu(cpu_llc_id, cpu) = node_id;
-			}
-		}
+		err = detect_extended_topology(c);
+		if (!err)
+			c->x86_coreid_bits = get_count_order(c->x86_max_cores);
+
+		cacheinfo_amd_init_llc_id(c, cpu, node_id);
+
 	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
@@ -376,7 +371,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		legacy_fixup_core_id(c);
 	}
 }
-#endif
 
 /*
  * On a AMD dual core setup the lower bits of the APIC id distinguish the cores.
@@ -384,7 +378,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
  */
 static void amd_detect_cmp(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_SMP
 	unsigned bits;
 	int cpu = smp_processor_id();
 
@@ -395,17 +388,11 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 	c->phys_proc_id = c->initial_apicid >> bits;
 	/* use socket ID also for last level cache */
 	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
-	amd_get_topology(c);
-#endif
 }
 
 u16 amd_get_nb_id(int cpu)
 {
-	u16 id = 0;
-#ifdef CONFIG_SMP
-	id = per_cpu(cpu_llc_id, cpu);
-#endif
-	return id;
+	return per_cpu(cpu_llc_id, cpu);
 }
 EXPORT_SYMBOL_GPL(amd_get_nb_id);
 
@@ -864,6 +851,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	/* Multi core CPU? */
 	if (c->extended_cpuid_level >= 0x80000008) {
 		amd_detect_cmp(c);
+		amd_get_topology(c);
 		srat_detect_node(c);
 	}
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 54d04d574148..38354c66df81 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -20,6 +20,8 @@
 #include <asm/amd_nb.h>
 #include <asm/smp.h>
 
+#include "cpu.h"
+
 #define LVL_1_INST	1
 #define LVL_1_DATA	2
 #define LVL_2		3
@@ -637,6 +639,45 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c)
 	return i;
 }
 
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
+{
+	/*
+	 * We may have multiple LLCs if L3 caches exist, so check if we
+	 * have an L3 cache by looking at the L3 cache CPUID leaf.
+	 */
+	if (!cpuid_edx(0x80000006))
+		return;
+
+	if (c->x86 < 0x17) {
+		/* LLC is at the node level. */
+		per_cpu(cpu_llc_id, cpu) = node_id;
+	} else if (c->x86 == 0x17 &&
+		   c->x86_model >= 0 && c->x86_model <= 0x1F) {
+		/*
+		 * LLC is at the core complex level.
+		 * Core complex ID is ApicId[3] for these processors.
+		 */
+		per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
+	} else {
+		/*
+		 * LLC ID is calculated from the number of threads sharing the
+		 * cache.
+		 * */
+		u32 eax, ebx, ecx, edx, num_sharing_cache = 0;
+		u32 llc_index = find_num_cache_leaves(c) - 1;
+
+		cpuid_count(0x8000001d, llc_index, &eax, &ebx, &ecx, &edx);
+		if (eax)
+			num_sharing_cache = ((eax >> 14) & 0xfff) + 1;
+
+		if (num_sharing_cache) {
+			int bits = get_count_order(num_sharing_cache) - 1;
+
+			per_cpu(cpu_llc_id, cpu) = c->apicid >> bits;
+		}
+	}
+}
+
 void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 {
 
@@ -650,7 +691,7 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 	}
 }
 
-unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
+void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 {
 	/* Cache sizes */
 	unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0;
@@ -802,7 +843,8 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 
 	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
 
-	return l2;
+	if (!l2)
+		cpu_detect_cache_sizes(c);
 }
 
 static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index e5ec0f11c0de..14433ff5b828 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -18,6 +18,13 @@
 #define RNG_ENABLED	(1 << 3)
 #define RNG_ENABLE	(1 << 6)	/* MSR_VIA_RNG */
 
+#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW	0x00200000
+#define X86_VMX_FEATURE_PROC_CTLS_VNMI		0x00400000
+#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS	0x80000000
+#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC	0x00000001
+#define X86_VMX_FEATURE_PROC_CTLS2_EPT		0x00000002
+#define X86_VMX_FEATURE_PROC_CTLS2_VPID		0x00000020
+
 static void init_c3(struct cpuinfo_x86 *c)
 {
 	u32  lo, hi;
@@ -112,6 +119,31 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
 	}
 }
 
+static void centaur_detect_vmx_virtcap(struct cpuinfo_x86 *c)
+{
+	u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+
+	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
+	msr_ctl = vmx_msr_high | vmx_msr_low;
+
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
+		set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
+		set_cpu_cap(c, X86_FEATURE_VNMI);
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
+		rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+		      vmx_msr_low, vmx_msr_high);
+		msr_ctl2 = vmx_msr_high | vmx_msr_low;
+		if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
+		    (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
+			set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+			set_cpu_cap(c, X86_FEATURE_EPT);
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
+			set_cpu_cap(c, X86_FEATURE_VPID);
+	}
+}
+
 static void init_centaur(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_32
@@ -128,6 +160,24 @@ static void init_centaur(struct cpuinfo_x86 *c)
 	clear_cpu_cap(c, 0*32+31);
 #endif
 	early_init_centaur(c);
+	init_intel_cacheinfo(c);
+	detect_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+	detect_ht(c);
+#endif
+
+	if (c->cpuid_level > 9) {
+		unsigned int eax = cpuid_eax(10);
+
+		/*
+		 * Check for version and the number of counters
+		 * Version(eax[7:0]) can't be 0;
+		 * Counters(eax[15:8]) should be greater than 1;
+		 */
+		if ((eax & 0xff) && (((eax >> 8) & 0xff) > 1))
+			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+	}
+
 	switch (c->x86) {
 #ifdef CONFIG_X86_32
 	case 5:
@@ -199,6 +249,9 @@ static void init_centaur(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_64
 	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
 #endif
+
+	if (cpu_has(c, X86_FEATURE_VMX))
+		centaur_detect_vmx_virtcap(c);
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 38276f58d3bf..95c8e507580d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -66,6 +66,13 @@ cpumask_var_t cpu_callin_mask;
 /* representing cpus for which sibling maps can be computed */
 cpumask_var_t cpu_sibling_setup_mask;
 
+/* Number of siblings per CPU package */
+int smp_num_siblings = 1;
+EXPORT_SYMBOL(smp_num_siblings);
+
+/* Last level cache ID of each logical CPU */
+DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
+
 /* correctly size the local cpu masks */
 void __init setup_cpu_local_masks(void)
 {
@@ -577,6 +584,19 @@ static void get_model_name(struct cpuinfo_x86 *c)
 	*(s + 1) = '\0';
 }
 
+void detect_num_cpu_cores(struct cpuinfo_x86 *c)
+{
+	unsigned int eax, ebx, ecx, edx;
+
+	c->x86_max_cores = 1;
+	if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
+		return;
+
+	cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
+	if (eax & 0x1f)
+		c->x86_max_cores = (eax >> 26) + 1;
+}
+
 void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
 {
 	unsigned int n, dummy, ebx, ecx, edx, l2size;
@@ -1044,6 +1064,21 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	setup_clear_cpu_cap(X86_FEATURE_PCID);
 #endif
+
+	/*
+	 * Later in the boot process pgtable_l5_enabled() relies on
+	 * cpu_feature_enabled(X86_FEATURE_LA57). If 5-level paging is not
+	 * enabled by this point we need to clear the feature bit to avoid
+	 * false-positives at the later stage.
+	 *
+	 * pgtable_l5_enabled() can be false here for several reasons:
+	 *  - 5-level paging is disabled compile-time;
+	 *  - it's 32-bit kernel;
+	 *  - machine doesn't support 5-level paging;
+	 *  - user specified 'no5lvl' in kernel command line.
+	 */
+	if (!pgtable_l5_enabled())
+		setup_clear_cpu_cap(X86_FEATURE_LA57);
 }
 
 void __init early_cpu_init(void)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 37672d299e35..38216f678fc3 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -47,6 +47,16 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],
 
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
+extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern u32 get_scattered_cpuid_leaf(unsigned int level,
+				    unsigned int sub_leaf,
+				    enum cpuid_regs_idx reg);
+extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);
+extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
+
+extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
+extern int detect_extended_topology(struct cpuinfo_x86 *c);
+extern void detect_ht(struct cpuinfo_x86 *c);
 
 unsigned int aperfmperf_get_khz(int cpu);
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 577e7f7ae273..eb75564f2d25 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -456,24 +456,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 #endif
 }
 
-/*
- * find out the number of processor cores on the die
- */
-static int intel_num_cpu_cores(struct cpuinfo_x86 *c)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
-		return 1;
-
-	/* Intel has a non-standard dependency on %ecx for this CPUID level. */
-	cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
-	if (eax & 0x1f)
-		return (eax >> 26) + 1;
-	else
-		return 1;
-}
-
 static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
 {
 	/* Intel VMX MSR indicated features */
@@ -656,8 +638,6 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
 
 static void init_intel(struct cpuinfo_x86 *c)
 {
-	unsigned int l2 = 0;
-
 	early_init_intel(c);
 
 	intel_workarounds(c);
@@ -674,19 +654,13 @@ static void init_intel(struct cpuinfo_x86 *c)
 		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
 		 * detection.
 		 */
-		c->x86_max_cores = intel_num_cpu_cores(c);
+		detect_num_cpu_cores(c);
 #ifdef CONFIG_X86_32
 		detect_ht(c);
 #endif
 	}
 
-	l2 = init_intel_cacheinfo(c);
-
-	/* Detect legacy cache sizes if init_intel_cacheinfo did not */
-	if (l2 == 0) {
-		cpu_detect_cache_sizes(c);
-		l2 = c->x86_cache_size;
-	}
+	init_intel_cacheinfo(c);
 
 	if (c->cpuid_level > 9) {
 		unsigned eax = cpuid_eax(10);
@@ -699,7 +673,8 @@ static void init_intel(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
 
 	if (boot_cpu_has(X86_FEATURE_DS)) {
-		unsigned int l1;
+		unsigned int l1, l2;
+
 		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
 		if (!(l1 & (1<<11)))
 			set_cpu_cap(c, X86_FEATURE_BTS);
@@ -727,6 +702,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 	 * Dixon is NOT a Celeron.
 	 */
 	if (c->x86 == 6) {
+		unsigned int l2 = c->x86_cache_size;
 		char *p = NULL;
 
 		switch (c->x86_model) {
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index b099024d339c..81c0afb39d0a 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -27,7 +27,7 @@
  * exists, use it for populating initial_apicid and cpu topology
  * detection.
  */
-void detect_extended_topology(struct cpuinfo_x86 *c)
+int detect_extended_topology(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	unsigned int eax, ebx, ecx, edx, sub_index;
@@ -36,7 +36,7 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
 	static bool printed;
 
 	if (c->cpuid_level < 0xb)
-		return;
+		return -1;
 
 	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
 
@@ -44,7 +44,7 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
 	 * check if the cpuid leaf 0xb is actually implemented.
 	 */
 	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
-		return;
+		return -1;
 
 	set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
 
@@ -95,6 +95,6 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
 			       c->cpu_core_id);
 		printed = 1;
 	}
-	return;
 #endif
+	return 0;
 }
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 2d29e47c056e..a21d6ace648e 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -6,6 +6,10 @@
  */
 
 #define DISABLE_BRANCH_PROFILING
+
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
+
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/types.h>
@@ -32,11 +36,6 @@
 #include <asm/microcode.h>
 #include <asm/kasan.h>
 
-#ifdef CONFIG_X86_5LEVEL
-#undef pgtable_l5_enabled
-#define pgtable_l5_enabled __pgtable_l5_enabled
-#endif
-
 /*
  * Manage page tables very early on.
  */
@@ -45,8 +44,7 @@ static unsigned int __initdata next_early_pgt;
 pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
 
 #ifdef CONFIG_X86_5LEVEL
-unsigned int __pgtable_l5_enabled __ro_after_init;
-EXPORT_SYMBOL(__pgtable_l5_enabled);
+unsigned int __pgtable_l5_enabled __initdata;
 unsigned int pgdir_shift __ro_after_init = 39;
 EXPORT_SYMBOL(pgdir_shift);
 unsigned int ptrs_per_p4d __ro_after_init = 1;
@@ -82,13 +80,14 @@ static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr)
 
 static bool __head check_la57_support(unsigned long physaddr)
 {
-	if (native_cpuid_eax(0) < 7)
-		return false;
-
-	if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31))))
+	/*
+	 * 5-level paging is detected and enabled at kernel decomression
+	 * stage. Only check if it has been enabled there.
+	 */
+	if (!(native_read_cr4() & X86_CR4_LA57))
 		return false;
 
-	*fixup_int(&pgtable_l5_enabled, physaddr) = 1;
+	*fixup_int(&__pgtable_l5_enabled, physaddr) = 1;
 	*fixup_int(&pgdir_shift, physaddr) = 48;
 	*fixup_int(&ptrs_per_p4d, physaddr) = 512;
 	*fixup_long(&page_offset_base, physaddr) = __PAGE_OFFSET_BASE_L5;
@@ -281,7 +280,7 @@ again:
 	 * critical -- __PAGE_OFFSET would point us back into the dynamic
 	 * range and we might end up looping forever...
 	 */
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		p4d_p = pgd_p;
 	else if (pgd)
 		p4d_p = (p4dval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 6010449ca6d2..4c8acdfdc5a7 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -354,7 +354,8 @@ void arch_crash_save_vmcoreinfo(void)
 {
 	VMCOREINFO_NUMBER(phys_base);
 	VMCOREINFO_SYMBOL(init_top_pgt);
-	VMCOREINFO_NUMBER(pgtable_l5_enabled);
+	vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n",
+			pgtable_l5_enabled());
 
 #ifdef CONFIG_NUMA
 	VMCOREINFO_SYMBOL(node_data);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 9dd324ae4832..c2f7d1d2a5c3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -81,13 +81,6 @@
 #include <asm/cpu_device_id.h>
 #include <asm/spec-ctrl.h>
 
-/* Number of siblings per CPU package */
-int smp_num_siblings = 1;
-EXPORT_SYMBOL(smp_num_siblings);
-
-/* Last level cache ID of each logical CPU */
-DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
-
 /* representing HT siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index cc7ff5957194..2f3c9196b834 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -360,7 +360,7 @@ static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st,
 				void *pt)
 {
 	if (__pa(pt) == __pa(kasan_zero_pmd) ||
-	    (pgtable_l5_enabled && __pa(pt) == __pa(kasan_zero_p4d)) ||
+	    (pgtable_l5_enabled() && __pa(pt) == __pa(kasan_zero_p4d)) ||
 	    __pa(pt) == __pa(kasan_zero_pud)) {
 		pgprotval_t prot = pte_flags(kasan_zero_pte[0]);
 		note_page(m, st, __pgprot(prot), 0, 5);
@@ -476,8 +476,8 @@ static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 	}
 }
 
-#define pgd_large(a) (pgtable_l5_enabled ? pgd_large(a) : p4d_large(__p4d(pgd_val(a))))
-#define pgd_none(a)  (pgtable_l5_enabled ? pgd_none(a) : p4d_none(__p4d(pgd_val(a))))
+#define pgd_large(a) (pgtable_l5_enabled() ? pgd_large(a) : p4d_large(__p4d(pgd_val(a))))
+#define pgd_none(a)  (pgtable_l5_enabled() ? pgd_none(a) : p4d_none(__p4d(pgd_val(a))))
 
 static inline bool is_hypervisor_range(int idx)
 {
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 2a5a2920203d..0e634956efdf 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -440,7 +440,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pgd_none(*pgd_k))
 		return -1;
 
-	if (pgtable_l5_enabled) {
+	if (pgtable_l5_enabled()) {
 		if (pgd_none(*pgd)) {
 			set_pgd(pgd, *pgd_k);
 			arch_flush_lazy_mmu_mode();
@@ -455,7 +455,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (p4d_none(*p4d_k))
 		return -1;
 
-	if (p4d_none(*p4d) && !pgtable_l5_enabled) {
+	if (p4d_none(*p4d) && !pgtable_l5_enabled()) {
 		set_p4d(p4d, *p4d_k);
 		arch_flush_lazy_mmu_mode();
 	} else {
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index a2f0c7e20fb0..fe7a12599d8e 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -123,7 +123,7 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 		result = ident_p4d_init(info, p4d, addr, next);
 		if (result)
 			return result;
-		if (pgtable_l5_enabled) {
+		if (pgtable_l5_enabled()) {
 			set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag));
 		} else {
 			/*
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0a400606dea0..17383f9677fa 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -180,7 +180,7 @@ static void sync_global_pgds_l4(unsigned long start, unsigned long end)
  */
 void sync_global_pgds(unsigned long start, unsigned long end)
 {
-	if (pgtable_l5_enabled)
+	if (pgtable_l5_enabled())
 		sync_global_pgds_l5(start, end);
 	else
 		sync_global_pgds_l4(start, end);
@@ -643,7 +643,7 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
 	unsigned long vaddr = (unsigned long)__va(paddr);
 	int i = p4d_index(vaddr);
 
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask);
 
 	for (; i < PTRS_PER_P4D; i++, paddr = paddr_next) {
@@ -723,7 +723,7 @@ kernel_physical_mapping_init(unsigned long paddr_start,
 					   page_size_mask);
 
 		spin_lock(&init_mm.page_table_lock);
-		if (pgtable_l5_enabled)
+		if (pgtable_l5_enabled())
 			pgd_populate(&init_mm, pgd, p4d);
 		else
 			p4d_populate(&init_mm, p4d_offset(pgd, vaddr), (pud_t *) p4d);
@@ -1100,7 +1100,7 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end,
 		 * 5-level case we should free them. This code will have to change
 		 * to adapt for boot-time switching between 4 and 5 level page tables.
 		 */
-		if (pgtable_l5_enabled)
+		if (pgtable_l5_enabled())
 			free_pud_table(pud_base, p4d);
 	}
 
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 980dbebd0ca7..e3e77527f8df 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -2,10 +2,8 @@
 #define DISABLE_BRANCH_PROFILING
 #define pr_fmt(fmt) "kasan: " fmt
 
-#ifdef CONFIG_X86_5LEVEL
-/* Too early to use cpu_feature_enabled() */
-#define pgtable_l5_enabled __pgtable_l5_enabled
-#endif
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
 
 #include <linux/bootmem.h>
 #include <linux/kasan.h>
@@ -182,7 +180,7 @@ static void __init clear_pgds(unsigned long start,
 		 * With folded p4d, pgd_clear() is nop, use p4d_clear()
 		 * instead.
 		 */
-		if (pgtable_l5_enabled)
+		if (pgtable_l5_enabled())
 			pgd_clear(pgd);
 		else
 			p4d_clear(p4d_offset(pgd, start));
@@ -197,7 +195,7 @@ static inline p4d_t *early_p4d_offset(pgd_t *pgd, unsigned long addr)
 {
 	unsigned long p4d;
 
-	if (!pgtable_l5_enabled)
+	if (!pgtable_l5_enabled())
 		return (p4d_t *)pgd;
 
 	p4d = __pa_nodebug(pgd_val(*pgd)) & PTE_PFN_MASK;
@@ -284,7 +282,7 @@ void __init kasan_early_init(void)
 	for (i = 0; i < PTRS_PER_PUD; i++)
 		kasan_zero_pud[i] = __pud(pud_val);
 
-	for (i = 0; pgtable_l5_enabled && i < PTRS_PER_P4D; i++)
+	for (i = 0; pgtable_l5_enabled() && i < PTRS_PER_P4D; i++)
 		kasan_zero_p4d[i] = __p4d(p4d_val);
 
 	kasan_map_early_shadow(early_top_pgt);
@@ -315,7 +313,7 @@ void __init kasan_init(void)
 	 * bunch of things like kernel code, modules, EFI mapping, etc.
 	 * We need to take extra steps to not overwrite them.
 	 */
-	if (pgtable_l5_enabled) {
+	if (pgtable_l5_enabled()) {
 		void *ptr;
 
 		ptr = (void *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 615cc03ced84..61db77b0eda9 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -78,7 +78,7 @@ void __init kernel_randomize_memory(void)
 	struct rnd_state rand_state;
 	unsigned long remain_entropy;
 
-	vaddr_start = pgtable_l5_enabled ? __PAGE_OFFSET_BASE_L5 : __PAGE_OFFSET_BASE_L4;
+	vaddr_start = pgtable_l5_enabled() ? __PAGE_OFFSET_BASE_L5 : __PAGE_OFFSET_BASE_L4;
 	vaddr = vaddr_start;
 
 	/*
@@ -124,7 +124,7 @@ void __init kernel_randomize_memory(void)
 		 */
 		entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i);
 		prandom_bytes_state(&rand_state, &rand, sizeof(rand));
-		if (pgtable_l5_enabled)
+		if (pgtable_l5_enabled())
 			entropy = (rand % (entropy + 1)) & P4D_MASK;
 		else
 			entropy = (rand % (entropy + 1)) & PUD_MASK;
@@ -136,7 +136,7 @@ void __init kernel_randomize_memory(void)
 		 * randomization alignment.
 		 */
 		vaddr += get_padding(&kaslr_regions[i]);
-		if (pgtable_l5_enabled)
+		if (pgtable_l5_enabled())
 			vaddr = round_up(vaddr + 1, P4D_SIZE);
 		else
 			vaddr = round_up(vaddr + 1, PUD_SIZE);
@@ -212,7 +212,7 @@ void __meminit init_trampoline(void)
 		return;
 	}
 
-	if (pgtable_l5_enabled)
+	if (pgtable_l5_enabled())
 		init_trampoline_p4d();
 	else
 		init_trampoline_pud();
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index e055d1a06699..6eb1f34c3c85 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -157,7 +157,7 @@ static void sync_current_stack_to_mm(struct mm_struct *mm)
 	unsigned long sp = current_stack_pointer;
 	pgd_t *pgd = pgd_offset(mm, sp);
 
-	if (pgtable_l5_enabled) {
+	if (pgtable_l5_enabled()) {
 		if (unlikely(pgd_none(*pgd))) {
 			pgd_t *pgd_ref = pgd_offset_k(sp);
 
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index bed7e7f4e44c..e01f7ceb9e7a 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -225,7 +225,7 @@ int __init efi_alloc_page_tables(void)
 
 	pud = pud_alloc(&init_mm, p4d, EFI_VA_END);
 	if (!pud) {
-		if (pgtable_l5_enabled)
+		if (pgtable_l5_enabled())
 			free_page((unsigned long) pgd_page_vaddr(*pgd));
 		free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
 		return -ENOMEM;
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index ccf4a49bb065..67ccf64c8bd8 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -72,7 +72,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
 	 * tables used by the image kernel.
 	 */
 
-	if (pgtable_l5_enabled) {
+	if (pgtable_l5_enabled()) {
 		p4d = (p4d_t *)get_safe_page(GFP_ATOMIC);
 		if (!p4d)
 			return -ENOMEM;