x86/mm/64: Make 5-level paging support unconditional

Both Intel and AMD CPUs support 5-level paging, which is expected to
become more widely adopted in the future. All major x86 Linux
distributions have the feature enabled.

Remove CONFIG_X86_5LEVEL and related #ifdeffery for it to make it more readable.

Suggested-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250516123306.3812286-4-kirill.shutemov@linux.intel.com

Author: kiryl

Documentation/arch/x86/cpuinfo.rst

@@ -173,10 +173,10 @@ For example, when an old kernel is running on new hardware.
 The kernel disabled support for it at compile-time
 --------------------------------------------------
 
-For example, if 5-level-paging is not enabled when building (i.e.,
-CONFIG_X86_5LEVEL is not selected) the flag "la57" will not show up [#f1]_.
+For example, if Linear Address Masking (LAM) is not enabled when building (i.e.,
+CONFIG_ADDRESS_MASKING is not selected) the flag "lam" will not show up.
 Even though the feature will still be detected via CPUID, the kernel disables
-it by clearing via setup_clear_cpu_cap(X86_FEATURE_LA57).
+it by clearing via setup_clear_cpu_cap(X86_FEATURE_LAM).
 
 The feature is disabled at boot-time
 ------------------------------------
@@ -200,5 +200,3 @@ missing at runtime. For example, AVX flags will not show up if XSAVE feature
 is disabled since they depend on XSAVE feature. Another example would be broken
 CPUs and them missing microcode patches. Due to that, the kernel decides not to
 enable a feature.
-
-.. [#f1] 5-level paging uses linear address of 57 bits.

Documentation/arch/x86/x86_64/5level-paging.rst

@@ -22,15 +22,6 @@ QEMU 2.9 and later support 5-level paging.
 Virtual memory layout for 5-level paging is described in
 Documentation/arch/x86/x86_64/mm.rst
 
-
-Enabling 5-level paging
-=======================
-CONFIG_X86_5LEVEL=y enables the feature.
-
-Kernel with CONFIG_X86_5LEVEL=y still able to boot on 4-level hardware.
-In this case additional page table level -- p4d -- will be folded at
-runtime.
-
 User-space and large virtual address space
 ==========================================
 On x86, 5-level paging enables 56-bit userspace virtual address space.

arch/x86/Kconfig

@@ -427,8 +427,7 @@ config DYNAMIC_PHYSICAL_MASK
 
 config PGTABLE_LEVELS
 	int
-	default 5 if X86_5LEVEL
-	default 4 if X86_64
+	default 5 if X86_64
 	default 3 if X86_PAE
 	default 2
 
@@ -1464,25 +1463,6 @@ config X86_PAE
 	  has the cost of more pagetable lookup overhead, and also
 	  consumes more pagetable space per process.
 
-config X86_5LEVEL
-	bool "Enable 5-level page tables support"
-	default y
-	depends on X86_64
-	help
-	  5-level paging enables access to larger address space:
-	  up to 128 PiB of virtual address space and 4 PiB of
-	  physical address space.
-
-	  It will be supported by future Intel CPUs.
-
-	  A kernel with the option enabled can be booted on machines that
-	  support 4- or 5-level paging.
-
-	  See Documentation/arch/x86/x86_64/5level-paging.rst for more
-	  information.
-
-	  Say N if unsure.
-
 config X86_DIRECT_GBPAGES
 	def_bool y
 	depends on X86_64

arch/x86/Kconfig.cpufeatures

@@ -132,10 +132,6 @@ config X86_DISABLED_FEATURE_OSPKE
 	def_bool y
 	depends on !X86_INTEL_MEMORY_PROTECTION_KEYS
 
-config X86_DISABLED_FEATURE_LA57
-	def_bool y
-	depends on !X86_5LEVEL
-
 config X86_DISABLED_FEATURE_PTI
 	def_bool y
 	depends on !MITIGATION_PAGE_TABLE_ISOLATION

arch/x86/boot/compressed/pgtable_64.c

@@ -10,12 +10,10 @@
 #define BIOS_START_MIN		0x20000U	/* 128K, less than this is insane */
 #define BIOS_START_MAX		0x9f000U	/* 640K, absolute maximum */
 
-#ifdef CONFIG_X86_5LEVEL
 /* __pgtable_l5_enabled needs to be in .data to avoid being cleared along with .bss */
 unsigned int __section(".data") __pgtable_l5_enabled;
 unsigned int __section(".data") pgdir_shift = 39;
 unsigned int __section(".data") ptrs_per_p4d = 1;
-#endif
 
 /* Buffer to preserve trampoline memory */
 static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
@@ -114,18 +112,13 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable)
 	 * Check if LA57 is desired and supported.
 	 *
 	 * 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
-	 *
-	 * 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)))) {
+	if (!cmdline_find_option_bool("no5lvl") &&
+	    native_cpuid_eax(0) >= 7 && (native_cpuid_ecx(7) & BIT(16))) {
 		l5_required = true;
 
 		/* Initialize variables for 5-level paging */

arch/x86/boot/header.S

@@ -361,12 +361,8 @@ xloadflags:
 #endif
 
 #ifdef CONFIG_X86_64
-#ifdef CONFIG_X86_5LEVEL
 #define XLF56 (XLF_5LEVEL|XLF_5LEVEL_ENABLED)
 #else
-#define XLF56 XLF_5LEVEL
-#endif
-#else
 #define XLF56 0
 #endif
 

arch/x86/boot/startup/map_kernel.c

@@ -16,9 +16,6 @@ extern unsigned int next_early_pgt;
 
 static inline bool check_la57_support(void)
 {
-	if (!IS_ENABLED(CONFIG_X86_5LEVEL))
-		return false;
-
 	/*
 	 * 5-level paging is detected and enabled at kernel decompression
 	 * stage. Only check if it has been enabled there.
@@ -129,7 +126,7 @@ unsigned long __head __startup_64(unsigned long p2v_offset,
 	pgd = rip_rel_ptr(early_top_pgt);
 	pgd[pgd_index(__START_KERNEL_map)] += load_delta;
 
-	if (IS_ENABLED(CONFIG_X86_5LEVEL) && la57) {
+	if (la57) {
 		p4d = (p4dval_t *)rip_rel_ptr(level4_kernel_pgt);
 		p4d[MAX_PTRS_PER_P4D - 1] += load_delta;
 

arch/x86/entry/vsyscall/vsyscall_64.c

@@ -341,9 +341,7 @@ void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
 	pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
 	set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
 	p4d = p4d_offset(pgd, VSYSCALL_ADDR);
-#if CONFIG_PGTABLE_LEVELS >= 5
 	set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER));
-#endif
 	pud = pud_offset(p4d, VSYSCALL_ADDR);
 	set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
 	pmd = pmd_offset(pud, VSYSCALL_ADDR);

arch/x86/include/asm/page_64.h

@@ -62,7 +62,6 @@ static inline void clear_page(void *page)
 void copy_page(void *to, void *from);
 KCFI_REFERENCE(copy_page);
 
-#ifdef CONFIG_X86_5LEVEL
 /*
  * User space process size.  This is the first address outside the user range.
  * There are a few constraints that determine this:
@@ -93,7 +92,6 @@ static __always_inline unsigned long task_size_max(void)
 
 	return ret;
 }
-#endif	/* CONFIG_X86_5LEVEL */
 
 #endif	/* !__ASSEMBLER__ */
 

arch/x86/include/asm/page_64_types.h

@@ -48,14 +48,7 @@
 /* See Documentation/arch/x86/x86_64/mm.rst for a description of the memory map. */
 
 #define __PHYSICAL_MASK_SHIFT	52
-
-#ifdef CONFIG_X86_5LEVEL
 #define __VIRTUAL_MASK_SHIFT	(pgtable_l5_enabled() ? 56 : 47)
-/* See task_size_max() in <asm/page_64.h> */
-#else
-#define __VIRTUAL_MASK_SHIFT	47
-#define task_size_max()		((_AC(1,UL) << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
-#endif
 
 #define TASK_SIZE_MAX		task_size_max()
 #define DEFAULT_MAP_WINDOW	((1UL << 47) - PAGE_SIZE)