Received-SPF: pass (google.com: domain of linux-kernel+bounces-158504-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Date: Thu, 25 Apr 2024 14:04:21 +0200
In-Reply-To: <20240425120416.2041037-6-ardb+git@google.com>
Precedence: bulk
Mime-Version: 1.0
References: <20240425120416.2041037-6-ardb+git@google.com>
Message-ID: <20240425120416.2041037-10-ardb+git@google.com>
Subject: [PATCH v2 4/4] x86/boot/64: Avoid intentional absolute symbol
 references in .head.text
From: Ard Biesheuvel <ardb+git@google.com>
To: linux-kernel@vger.kernel.org
Cc: x86@kernel.org, Ard Biesheuvel <ardb@kernel.org>, Tom Lendacky <thomas.lendacky@amd.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>
Content-Type: text/plain; charset="UTF-8"

From: Ard Biesheuvel <ardb@kernel.org>

The code in .head.text executes from a 1:1 mapping and cannot generally
refer to global variables using their kernel virtual addresses. However,
there are some occurrences of such references that are valid: the kernel
virtual addresses of _text and _end are needed to populate the page
tables correctly, and some other section markers are used in a similar
way.

To avoid the need for making exceptions to the rule that .head.text must
not contain any absolute symbol references, derive these addresses from
the RIP-relative 1:1 mapped physical addresses, which can be safely
determined using RIP_REL_REF().

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/kernel/head64.c | 30 ++++++++++++--------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 81696a4967e6..c0f20962f9b1 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -91,9 +91,11 @@ static inline bool check_la57_support(void)
 	return true;
 }
 
-static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd)
+static unsigned long __head sme_postprocess_startup(struct boot_params *bp,
+						    pmdval_t *pmd,
+						    unsigned long p2v_offset)
 {
-	unsigned long vaddr, vaddr_end;
+	unsigned long paddr, paddr_end;
 	int i;
 
 	/* Encrypt the kernel and related (if SME is active) */
@@ -106,10 +108,10 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv
 	 * attribute.
 	 */
 	if (sme_get_me_mask()) {
-		vaddr = (unsigned long)__start_bss_decrypted;
-		vaddr_end = (unsigned long)__end_bss_decrypted;
+		paddr = (unsigned long)&RIP_REL_REF(__start_bss_decrypted);
+		paddr_end = (unsigned long)&RIP_REL_REF(__end_bss_decrypted);
 
-		for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
+		for (; paddr < paddr_end; paddr += PMD_SIZE) {
 			/*
 			 * On SNP, transition the page to shared in the RMP table so that
 			 * it is consistent with the page table attribute change.
@@ -118,11 +120,11 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv
 			 * mapping (kernel .text). PVALIDATE, by way of
 			 * early_snp_set_memory_shared(), requires a valid virtual
 			 * address but the kernel is currently running off of the identity
-			 * mapping so use __pa() to get a *currently* valid virtual address.
+			 * mapping so use the PA to get a *currently* valid virtual address.
 			 */
-			early_snp_set_memory_shared(__pa(vaddr), __pa(vaddr), PTRS_PER_PMD);
+			early_snp_set_memory_shared(paddr, paddr, PTRS_PER_PMD);
 
-			i = pmd_index(vaddr);
+			i = pmd_index(paddr - p2v_offset);
 			pmd[i] -= sme_get_me_mask();
 		}
 	}
@@ -146,6 +148,7 @@ unsigned long __head __startup_64(unsigned long p2v_offset,
 {
 	pmd_t (*early_pgts)[PTRS_PER_PMD] = RIP_REL_REF(early_dynamic_pgts);
 	unsigned long physaddr = (unsigned long)&RIP_REL_REF(_text);
+	unsigned long va_text, va_end;
 	unsigned long pgtable_flags;
 	unsigned long load_delta;
 	pgdval_t *pgd;
@@ -172,6 +175,9 @@ unsigned long __head __startup_64(unsigned long p2v_offset,
 	if (load_delta & ~PMD_MASK)
 		for (;;);
 
+	va_text = physaddr - p2v_offset;
+	va_end  = (unsigned long)&RIP_REL_REF(_end) - p2v_offset;
+
 	/* Include the SME encryption mask in the fixup value */
 	load_delta += sme_get_me_mask();
 
@@ -232,7 +238,7 @@ unsigned long __head __startup_64(unsigned long p2v_offset,
 	pmd_entry += sme_get_me_mask();
 	pmd_entry +=  physaddr;
 
-	for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) {
+	for (i = 0; i < DIV_ROUND_UP(va_end - va_text, PMD_SIZE); i++) {
 		int idx = i + (physaddr >> PMD_SHIFT);
 
 		pmd[idx % PTRS_PER_PMD] = pmd_entry + i * PMD_SIZE;
@@ -257,11 +263,11 @@ unsigned long __head __startup_64(unsigned long p2v_offset,
 	pmd = &RIP_REL_REF(level2_kernel_pgt)->pmd;
 
 	/* invalidate pages before the kernel image */
-	for (i = 0; i < pmd_index((unsigned long)_text); i++)
+	for (i = 0; i < pmd_index(va_text); i++)
 		pmd[i] &= ~_PAGE_PRESENT;
 
 	/* fixup pages that are part of the kernel image */
-	for (; i <= pmd_index((unsigned long)_end); i++)
+	for (; i <= pmd_index(va_end); i++)
 		if (pmd[i] & _PAGE_PRESENT)
 			pmd[i] += load_delta;
 
@@ -269,7 +275,7 @@ unsigned long __head __startup_64(unsigned long p2v_offset,
 	for (; i < PTRS_PER_PMD; i++)
 		pmd[i] &= ~_PAGE_PRESENT;
 
-	return sme_postprocess_startup(bp, pmd);
+	return sme_postprocess_startup(bp, pmd, p2v_offset);
 }
 
 /* Wipe all early page tables except for the kernel symbol map */
-- 
2.44.0.769.g3c40516874-goog