lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <170249982674.398.5844405041679284531.tip-bot2@tip-bot2>
Date:   Wed, 13 Dec 2023 20:37:06 -0000
From:   "tip-bot2 for Borislav Petkov (AMD)" <tip-bot2@...utronix.de>
To:     linux-tip-commits@...r.kernel.org
Cc:     "Borislav Petkov (AMD)" <bp@...en8.de>,
        Tom Lendacky <thomas.lendacky@....com>, x86@...nel.org,
        linux-kernel@...r.kernel.org
Subject: [tip: x86/sev] x86/sev: Do the C-bit verification only on the BSP

The following commit has been merged into the x86/sev branch of tip:

Commit-ID:     30579c8baa5b4bd986420a984dad2940f1ff65d3
Gitweb:        https://git.kernel.org/tip/30579c8baa5b4bd986420a984dad2940f1ff65d3
Author:        Borislav Petkov (AMD) <bp@...en8.de>
AuthorDate:    Thu, 30 Nov 2023 14:26:01 +01:00
Committer:     Borislav Petkov (AMD) <bp@...en8.de>
CommitterDate: Wed, 13 Dec 2023 21:07:56 +01:00

x86/sev: Do the C-bit verification only on the BSP

There's no need to do it on every AP.

The C-bit value read on the BSP and also verified there, is used
everywhere from now on.

No functional changes - just a bit faster booting APs.

Signed-off-by: Borislav Petkov (AMD) <bp@...en8.de>
Acked-by: Tom Lendacky <thomas.lendacky@....com>
Link: https://lore.kernel.org/r/20231130132601.10317-1-bp@alien8.de
---
 arch/x86/kernel/head_64.S | 31 ++++++++++++++++++++++---------
 1 file changed, 22 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 086a2c3..d1dc39a 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -114,6 +114,28 @@ SYM_CODE_START_NOALIGN(startup_64)
 
 	/* Form the CR3 value being sure to include the CR3 modifier */
 	addq	$(early_top_pgt - __START_KERNEL_map), %rax
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	mov	%rax, %rdi
+	mov	%rax, %r14
+
+	addq	phys_base(%rip), %rdi
+
+	/*
+	 * For SEV guests: Verify that the C-bit is correct. A malicious
+	 * hypervisor could lie about the C-bit position to perform a ROP
+	 * attack on the guest by writing to the unencrypted stack and wait for
+	 * the next RET instruction.
+	 */
+	call	sev_verify_cbit
+
+	/*
+	 * Restore CR3 value without the phys_base which will be added
+	 * below, before writing %cr3.
+	 */
+	 mov	%r14, %rax
+#endif
+
 	jmp 1f
 SYM_CODE_END(startup_64)
 
@@ -193,15 +215,6 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	addq	phys_base(%rip), %rax
 
 	/*
-	 * For SEV guests: Verify that the C-bit is correct. A malicious
-	 * hypervisor could lie about the C-bit position to perform a ROP
-	 * attack on the guest by writing to the unencrypted stack and wait for
-	 * the next RET instruction.
-	 */
-	movq	%rax, %rdi
-	call	sev_verify_cbit
-
-	/*
 	 * Switch to new page-table
 	 *
 	 * For the boot CPU this switches to early_top_pgt which still has the

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ