Received-SPF: pass (google.com: domain of linux-kernel+bounces-95737-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Date: Thu,  7 Mar 2024 15:30:31 +0100
In-Reply-To: <20240307143027.206179-6-ardb+git@google.com>
Precedence: bulk
Mime-Version: 1.0
References: <20240307143027.206179-6-ardb+git@google.com>
Message-ID: <20240307143027.206179-9-ardb+git@google.com>
Subject: [RFC PATCH v6.10 3/4] x86/boot/64: Determine VA/PA offset before
 entering C code
From: Ard Biesheuvel <ardb+git@google.com>
To: linux-kernel@google.com
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>, Kees Cook <keescook@chromium.org>, Brian Gerst <brgerst@gmail.com>, 
	linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"

From: Ard Biesheuvel <ardb@kernel.org>

We will start using an explicit virtual-to-physical offset in the early
1:1 mapped C code to derive the kernel virtual addresses of _text and
_end without having to rely on absolute symbol references, which should
be avoided in such code.

Currently, phys_base is used for this purpose, which is derived from the
kernel virtual address of _text, and this would lead to a circular
dependency. So instead, derive virtual-to-physical offset in asm code,
using the kernel VA of common_startup_64, which we already keep in a
global variable for other reasons.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/include/asm/setup.h | 3 ++-
 arch/x86/kernel/head64.c     | 8 +++++---
 arch/x86/kernel/head_64.S    | 2 ++
 3 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index e61e68d71cba..cc1994516af2 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -47,7 +47,8 @@ extern unsigned long saved_video_mode;
 
 extern void reserve_standard_io_resources(void);
 extern void i386_reserve_resources(void);
-extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp);
+extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp,
+				  unsigned long va_offset);
 extern void startup_64_setup_gdt_idt(void);
 extern void early_setup_idt(void);
 extern void __init do_early_exception(struct pt_regs *regs, int trapnr);
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 212e8e06aeba..8fd80cf07691 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -131,10 +131,12 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv
  * doesn't have to generate PC-relative relocations when accessing globals from
  * that function. Clang actually does not generate them, which leads to
  * boot-time crashes. To work around this problem, every global pointer must
- * be accessed using RIP_REL_REF().
+ * be accessed using RIP_REL_REF(). Kernel virtual addresses can be determined
+ * by subtracting va_offset from the RIP-relative address.
  */
 unsigned long __head __startup_64(unsigned long physaddr,
-				  struct boot_params *bp)
+				  struct boot_params *bp,
+				  unsigned long va_offset)
 {
 	pmd_t (*early_pgts)[PTRS_PER_PMD] = RIP_REL_REF(early_dynamic_pgts);
 	unsigned long pgtable_flags;
@@ -156,7 +158,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	 * Compute the delta between the address I am compiled to run at
 	 * and the address I am actually running at.
 	 */
-	load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map);
+	load_delta = __START_KERNEL_map + va_offset;
 	RIP_REL_REF(phys_base) = load_delta;
 
 	/* Is the address not 2M aligned? */
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 79f7c342e3da..3622744349d1 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -107,6 +107,8 @@ SYM_CODE_START_NOALIGN(startup_64)
 	 */
 	leaq	_text(%rip), %rdi
 	movq	%r15, %rsi
+	leaq	common_startup_64(%rip), %rdx
+	subq	0f(%rip), %rdx
 	call	__startup_64
 
 	/* Form the CR3 value being sure to include the CR3 modifier */
-- 
2.44.0.278.ge034bb2e1d-goog