linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ard Biesheuvel <ardb+git@google.com>
To: linux-kernel@vger.kernel.org
Cc: Ard Biesheuvel <ardb@kernel.org>,
	Kevin Loughlin <kevinloughlin@google.com>,
	 Tom Lendacky <thomas.lendacky@amd.com>,
	Dionna Glaze <dionnaglaze@google.com>,
	 Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	 Dave Hansen <dave.hansen@linux.intel.com>,
	Andy Lutomirski <luto@kernel.org>,  Arnd Bergmann <arnd@arndb.de>,
	Nathan Chancellor <nathan@kernel.org>,
	 Nick Desaulniers <ndesaulniers@google.com>,
	Justin Stitt <justinstitt@google.com>,
	 Kees Cook <keescook@chromium.org>,
	Brian Gerst <brgerst@gmail.com>,
	linux-arch@vger.kernel.org,  llvm@lists.linux.dev
Subject: [PATCH v5 16/16] x86/startup_64: Drop global variables keeping track of LA57 state
Date: Wed, 21 Feb 2024 12:35:23 +0100	[thread overview]
Message-ID: <20240221113506.2565718-34-ardb+git@google.com> (raw)
In-Reply-To: <20240221113506.2565718-18-ardb+git@google.com>

From: Ard Biesheuvel <ardb@kernel.org>

On x86_64, the core kernel is entered in long mode, which implies that
paging is enabled. This means that the CR4.LA57 control bit is
guaranteed to be in sync with the number of paging levels used by the
kernel, and there is no need to store this in a variable.

There is also no need to use variables for storing the calculations of
pgdir_shift and ptrs_per_p4d, as they are easily determined on the fly.

This removes the need for two different sources of truth for determining
whether 5-level paging is in use: CR4.LA57 always reflects the actual
state, and never changes from the point of view of the 64-bit core
kernel. The only potential concern is the cost of CR4 accesses, which
can be mitigated using alternatives patching based on feature detection.

Note that even the decompressor does not manipulate any page tables
before updating CR4.LA57, so it can also avoid the associated global
variables entirely. However, as it does not implement alternatives
patching, the associated ELF sections need to be discarded.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/boot/compressed/misc.h         |  4 --
 arch/x86/boot/compressed/pgtable_64.c   | 12 ------
 arch/x86/boot/compressed/vmlinux.lds.S  |  1 +
 arch/x86/include/asm/pgtable_64_types.h | 43 ++++++++++----------
 arch/x86/kernel/cpu/common.c            |  2 -
 arch/x86/kernel/head64.c                | 33 +--------------
 arch/x86/mm/kasan_init_64.c             |  3 --
 arch/x86/mm/mem_encrypt_identity.c      |  9 ----
 8 files changed, 25 insertions(+), 82 deletions(-)

diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index bc2f0f17fb90..2b15ddd0e177 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -16,9 +16,6 @@
 
 #define __NO_FORTIFY
 
-/* cpu_feature_enabled() cannot be used this early */
-#define USE_EARLY_PGTABLE_L5
-
 /*
  * Boot stub deals with identity mappings, physical and virtual addresses are
  * the same, so override these defines.
@@ -178,7 +175,6 @@ static inline int count_immovable_mem_regions(void) { return 0; }
 #endif
 
 /* ident_map_64.c */
-extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d;
 extern void kernel_add_identity_map(unsigned long start, unsigned long end);
 
 /* Used by PAGE_KERN* macros: */
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 51f957b24ba7..ae72f53f5e77 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -9,13 +9,6 @@
 #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];
 
@@ -125,11 +118,6 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable)
 			native_cpuid_eax(0) >= 7 &&
 			(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) {
 		l5_required = true;
-
-		/* Initialize variables for 5-level paging */
-		__pgtable_l5_enabled = 1;
-		pgdir_shift = 48;
-		ptrs_per_p4d = 512;
 	}
 
 	/*
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index 083ec6d7722a..06358bb067fe 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -81,6 +81,7 @@ SECTIONS
 		*(.dynamic) *(.dynsym) *(.dynstr) *(.dynbss)
 		*(.hash) *(.gnu.hash)
 		*(.note.*)
+		*(.altinstructions .altinstr_replacement)
 	}
 
 	.got.plt (INFO) : {
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 9053dfe9fa03..2fac8ba9564a 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -6,7 +6,10 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
+#include <asm/alternative.h>
+#include <asm/cpufeatures.h>
 #include <asm/kaslr.h>
+#include <asm/processor-flags.h>
 
 /*
  * These are used to make use of C type-checking..
@@ -21,28 +24,24 @@ typedef unsigned long	pgprotval_t;
 typedef struct { pteval_t pte; } pte_t;
 typedef struct { pmdval_t pmd; } pmd_t;
 
-extern unsigned int __pgtable_l5_enabled;
-
-#ifdef CONFIG_X86_5LEVEL
-#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)
+static __always_inline __pure bool pgtable_l5_enabled(void)
 {
-	return __pgtable_l5_enabled;
-}
-#else
-#define pgtable_l5_enabled() cpu_feature_enabled(X86_FEATURE_LA57)
-#endif /* USE_EARLY_PGTABLE_L5 */
+	unsigned long r;
+	bool ret;
 
-#else
-#define pgtable_l5_enabled() 0
-#endif /* CONFIG_X86_5LEVEL */
+	if (!IS_ENABLED(CONFIG_X86_5LEVEL))
+		return false;
 
-extern unsigned int pgdir_shift;
-extern unsigned int ptrs_per_p4d;
+	asm(ALTERNATIVE_TERNARY(
+		"movq %%cr4, %[reg] \n\t btl %[la57], %k[reg]" CC_SET(c),
+		%P[feat], "stc", "clc")
+		: [reg] "=&r" (r), CC_OUT(c) (ret)
+		: [feat] "i"  (X86_FEATURE_LA57),
+		  [la57] "i"  (X86_CR4_LA57_BIT)
+		: "cc");
+
+	return ret;
+}
 
 #endif	/* !__ASSEMBLY__ */
 
@@ -53,7 +52,7 @@ extern unsigned int ptrs_per_p4d;
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map
  */
-#define PGDIR_SHIFT	pgdir_shift
+#define PGDIR_SHIFT	(pgtable_l5_enabled() ? 48 : 39)
 #define PTRS_PER_PGD	512
 
 /*
@@ -61,7 +60,7 @@ extern unsigned int ptrs_per_p4d;
  */
 #define P4D_SHIFT		39
 #define MAX_PTRS_PER_P4D	512
-#define PTRS_PER_P4D		ptrs_per_p4d
+#define PTRS_PER_P4D		(pgtable_l5_enabled() ? 512 : 1)
 #define P4D_SIZE		(_AC(1, UL) << P4D_SHIFT)
 #define P4D_MASK		(~(P4D_SIZE - 1))
 
@@ -76,6 +75,8 @@ extern unsigned int ptrs_per_p4d;
 #define PTRS_PER_PGD		512
 #define MAX_PTRS_PER_P4D	1
 
+#define MAX_POSSIBLE_PHYSMEM_BITS	46
+
 #endif /* CONFIG_X86_5LEVEL */
 
 /*
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9e35e276c55a..d88e4be88868 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/* cpu_feature_enabled() cannot be used this early */
-#define USE_EARLY_PGTABLE_L5
 
 #include <linux/memblock.h>
 #include <linux/linkage.h>
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b33f47489505..348fd69252ac 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -7,9 +7,6 @@
 
 #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>
@@ -52,14 +49,6 @@ extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
 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;
-unsigned int pgdir_shift __ro_after_init = 39;
-EXPORT_SYMBOL(pgdir_shift);
-unsigned int ptrs_per_p4d __ro_after_init = 1;
-EXPORT_SYMBOL(ptrs_per_p4d);
-#endif
-
 #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
 unsigned long page_offset_base __ro_after_init = __PAGE_OFFSET_BASE_L4;
 EXPORT_SYMBOL(page_offset_base);
@@ -78,21 +67,6 @@ static struct desc_struct startup_gdt[GDT_ENTRIES] __initdata = {
 	[GDT_ENTRY_KERNEL_DS]           = GDT_ENTRY_INIT(DESC_DATA64, 0, 0xfffff),
 };
 
-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.
-	 */
-	if (!(native_read_cr4() & X86_CR4_LA57))
-		return false;
-
-	return true;
-}
-
 static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd)
 {
 	unsigned long vaddr, vaddr_end;
@@ -155,7 +129,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	bool la57;
 	int i;
 
-	la57 = check_la57_support();
+	la57 = pgtable_l5_enabled();
 
 	/* Is the address too large? */
 	if (physaddr >> MAX_PHYSMEM_BITS)
@@ -440,10 +414,7 @@ asmlinkage __visible void __init __noreturn x86_64_start_kernel(char * real_mode
 				(__START_KERNEL & PGDIR_MASK)));
 	BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
 
-	if (check_la57_support()) {
-		__pgtable_l5_enabled	= 1;
-		pgdir_shift		= 48;
-		ptrs_per_p4d		= 512;
+	if (pgtable_l5_enabled()) {
 		page_offset_base	= __PAGE_OFFSET_BASE_L5;
 		vmalloc_base		= __VMALLOC_BASE_L5;
 		vmemmap_base		= __VMEMMAP_BASE_L5;
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 0302491d799d..85ae1ef840cc 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -2,9 +2,6 @@
 #define DISABLE_BRANCH_PROFILING
 #define pr_fmt(fmt) "kasan: " fmt
 
-/* cpu_feature_enabled() cannot be used this early */
-#define USE_EARLY_PGTABLE_L5
-
 #include <linux/memblock.h>
 #include <linux/kasan.h>
 #include <linux/kdebug.h>
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 174a7192c9cb..3da15e9a8c7d 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -27,15 +27,6 @@
 #undef CONFIG_PARAVIRT_XXL
 #undef CONFIG_PARAVIRT_SPINLOCKS
 
-/*
- * This code runs before CPU feature bits are set. By default, the
- * pgtable_l5_enabled() function uses bit X86_FEATURE_LA57 to determine if
- * 5-level paging is active, so that won't work here. USE_EARLY_PGTABLE_L5
- * is provided to handle this situation and, instead, use a variable that
- * has been set by the early boot code.
- */
-#define USE_EARLY_PGTABLE_L5
-
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/mem_encrypt.h>
-- 
2.44.0.rc0.258.g7320e95886-goog


      parent reply	other threads:[~2024-02-21 11:36 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-21 11:35 [PATCH v5 00/16] x86: Confine early 1:1 mapped startup code Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 01/16] x86/startup_64: Simplify global variable accesses in GDT/IDT programming Ard Biesheuvel
2024-02-26 12:12   ` [tip: x86/boot] x86/boot/64: " tip-bot2 for Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 02/16] x86/startup_64: Use RIP_REL_REF() to assign phys_base Ard Biesheuvel
2024-02-26 12:12   ` [tip: x86/boot] x86/boot/64: Use RIP_REL_REF() to assign 'phys_base' tip-bot2 for Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 03/16] x86/startup_64: Use RIP_REL_REF() to access early_dynamic_pgts[] Ard Biesheuvel
2024-02-26 12:12   ` [tip: x86/boot] x86/boot/64: " tip-bot2 for Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 04/16] x86/startup_64: Use RIP_REL_REF() to access __supported_pte_mask Ard Biesheuvel
2024-02-26 12:12   ` [tip: x86/boot] x86/boot/64: Use RIP_REL_REF() to access '__supported_pte_mask' tip-bot2 for Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 05/16] x86/startup_64: Use RIP_REL_REF() to access early page tables Ard Biesheuvel
2024-02-26 12:12   ` [tip: x86/boot] x86/boot/64: " tip-bot2 for Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 06/16] x86/startup_64: Use RIP_REL_REF() to access early_top_pgt[] Ard Biesheuvel
2024-02-26 12:12   ` [tip: x86/boot] x86/boot/64: " tip-bot2 for Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 07/16] x86/startup_64: Simplify CR4 handling in startup code Ard Biesheuvel
2024-02-21 14:52   ` Brian Gerst
2024-02-21 11:35 ` [PATCH v5 08/16] x86/startup_64: Defer assignment of 5-level paging global variables Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 09/16] x86/startup_64: Simplify calculation of initial page table address Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 10/16] x86/startup_64: Simplify virtual switch on primary boot Ard Biesheuvel
2024-02-23 13:11   ` Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 11/16] x86/sme: Avoid SME/SVE related checks on non-SME/SVE platforms Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 12/16] efi/libstub: Add generic support for parsing mem_encrypt= Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 13/16] x86/boot: Move mem_encrypt= parsing to the decompressor Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 14/16] x86/sme: Move early SME kernel encryption handling into .head.text Ard Biesheuvel
2024-02-21 11:35 ` [PATCH v5 15/16] x86/sev: Move early startup code into .head.text section Ard Biesheuvel
2024-02-21 11:35 ` Ard Biesheuvel [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240221113506.2565718-34-ardb+git@google.com \
    --to=ardb+git@google.com \
    --cc=ardb@kernel.org \
    --cc=arnd@arndb.de \
    --cc=bp@alien8.de \
    --cc=brgerst@gmail.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=dionnaglaze@google.com \
    --cc=justinstitt@google.com \
    --cc=keescook@chromium.org \
    --cc=kevinloughlin@google.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=llvm@lists.linux.dev \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=nathan@kernel.org \
    --cc=ndesaulniers@google.com \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).