llvm.lists.linux.dev 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>,
	 Brian Gerst <brgerst@gmail.com>,
	linux-arch@vger.kernel.org, llvm@lists.linux.dev
Subject: [PATCH v2 04/17] x86/startup_64: Drop global variables to keep track of LA57 state
Date: Thu, 25 Jan 2024 12:28:23 +0100	[thread overview]
Message-ID: <20240125112818.2016733-23-ardb+git@google.com> (raw)
In-Reply-To: <20240125112818.2016733-19-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.
Other assignments of global variables related to the number of paging
levels can be deferred to the primary C entrypoint that actually runs
from the kernel virtual mapping.

This removes the need for writing to __ro_after_init from the code that
executes extremely early via the 1:1 mapping.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/boot/compressed/pgtable_64.c   |  2 -
 arch/x86/include/asm/pgtable_64_types.h | 15 +++---
 arch/x86/kernel/cpu/common.c            |  2 -
 arch/x86/kernel/head64.c                | 52 ++++----------------
 arch/x86/mm/kasan_init_64.c             |  3 --
 arch/x86/mm/mem_encrypt_identity.c      |  9 ----
 6 files changed, 15 insertions(+), 68 deletions(-)

diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 51f957b24ba7..0586cc216aa6 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -128,8 +128,6 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable)
 
 		/* Initialize variables for 5-level paging */
 		__pgtable_l5_enabled = 1;
-		pgdir_shift = 48;
-		ptrs_per_p4d = 512;
 	}
 
 	/*
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 38b54b992f32..ecc010fbb377 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -22,28 +22,25 @@ typedef struct { pteval_t pte; } pte_t;
 typedef struct { pmdval_t pmd; } pmd_t;
 
 #ifdef CONFIG_X86_5LEVEL
+#ifdef USE_EARLY_PGTABLE_L5
 extern unsigned int __pgtable_l5_enabled;
 
-#ifdef USE_EARLY_PGTABLE_L5
 /*
- * cpu_feature_enabled() is not available in early boot code.
- * Use variable instead.
+ * CR4.LA57 may not be set to its final value yet in the early boot code.
+ * Use a variable instead.
  */
 static inline bool pgtable_l5_enabled(void)
 {
 	return __pgtable_l5_enabled;
 }
 #else
-#define pgtable_l5_enabled() cpu_feature_enabled(X86_FEATURE_LA57)
+#define pgtable_l5_enabled() !!(native_read_cr4() & X86_CR4_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;
-
 #endif	/* !__ASSEMBLY__ */
 
 #define SHARED_KERNEL_PMD	0
@@ -53,7 +50,7 @@ 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 +58,7 @@ 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))
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0b97bcde70c6..20ac11a2c06b 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 dc0956067944..d636bb02213f 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>
@@ -50,14 +47,6 @@ 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);
@@ -95,37 +84,6 @@ static unsigned long __head *fixup_long(void *ptr, unsigned long physaddr)
 	return fixup_pointer(ptr, physaddr);
 }
 
-#ifdef CONFIG_X86_5LEVEL
-static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr)
-{
-	return fixup_pointer(ptr, physaddr);
-}
-
-static bool __head check_la57_support(unsigned long physaddr)
-{
-	/*
-	 * 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;
-
-	*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;
-	*fixup_long(&vmalloc_base, physaddr) = __VMALLOC_BASE_L5;
-	*fixup_long(&vmemmap_base, physaddr) = __VMEMMAP_BASE_L5;
-
-	return true;
-}
-#else
-static bool __head check_la57_support(unsigned long physaddr)
-{
-	return false;
-}
-#endif
-
 static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd)
 {
 	unsigned long vaddr, vaddr_end;
@@ -189,7 +147,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	int i;
 	unsigned int *next_pgt_ptr;
 
-	la57 = check_la57_support(physaddr);
+	la57 = pgtable_l5_enabled();
 
 	/* Is the address too large? */
 	if (physaddr >> MAX_PHYSMEM_BITS)
@@ -486,6 +444,14 @@ 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);
 
+#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
+	if (pgtable_l5_enabled()) {
+		page_offset_base	= __PAGE_OFFSET_BASE_L5;
+		vmalloc_base		= __VMALLOC_BASE_L5;
+		vmemmap_base		= __VMEMMAP_BASE_L5;
+	}
+#endif
+
 	cr4_init_shadow();
 
 	/* Kill off the identity-map trampoline */
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 d73aeb16417f..67d4530548ce 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>
-- 
2.43.0.429.g432eaa2c6b-goog


  parent reply	other threads:[~2024-01-25 11:32 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-01-25 11:28 [PATCH v2 00/17] x86: Confine early 1:1 mapped startup code Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 01/17] x86/startup_64: Drop long return to initial_code pointer Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 02/17] x86/startup_64: Simplify calculation of initial page table address Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 03/17] x86/startup_64: Simplify CR4 handling in startup code Ard Biesheuvel
2024-01-25 11:28 ` Ard Biesheuvel [this message]
2024-01-25 11:28 ` [PATCH v2 05/17] x86/startup_64: Simplify virtual switch on primary boot Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 06/17] x86/head64: Replace pointer fixups with PIE codegen Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 07/17] x86/head64: Simplify GDT/IDT initialization code Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 08/17] asm-generic: Add special .pi.text section for position independent code Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 09/17] x86: Move return_thunk to __pitext section Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 10/17] x86/head64: Move early startup code into __pitext Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 11/17] modpost: Warn about calls from __pitext into other text sections Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 12/17] x86/coco: Make cc_set_mask() static inline Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 13/17] x86/sev: Make all code reachable from 1:1 mapping __pitext Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 14/17] x86/sev: Avoid WARN() in early code Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 15/17] x86/sev: Use PIC codegen for early SEV startup code Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 16/17] x86/sev: Drop inline asm LEA instructions for RIP-relative references Ard Biesheuvel
2024-01-25 20:46   ` Kevin Loughlin
2024-01-25 23:24     ` Ard Biesheuvel
2024-01-25 11:28 ` [PATCH v2 17/17] x86/startup_64: Don't bother setting up GS before the kernel is mapped Ard Biesheuvel
2024-01-25 22:23 ` [PATCH v2 00/17] x86: Confine early 1:1 mapped startup code Nathan Chancellor

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=20240125112818.2016733-23-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=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).