linux-kernel - [PATCH] x86/speculation: Avoid LFENCE in FILL_RETURN

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-next>] [day] [month] [year] [list]

Message-ID: <Yv7aRJ/SvVhSdnSB@decadent.org.uk>
Date:   Fri, 19 Aug 2022 02:33:08 +0200
From:   Ben Hutchings <ben@...adent.org.uk>
To:     x86@...nel.org
Cc:     linux-kernel@...r.kernel.org, 1017425@...s.debian.org,
        Martin-Éric Racine <martin-eric.racine@....fi>,
        stable@...r.kernel.org, regressions@...ts.linux.dev,
        Daniel Sneddon <daniel.sneddon@...ux.intel.com>,
        Pawan Gupta <pawan.kumar.gupta@...ux.intel.com>
Subject: [PATCH] x86/speculation: Avoid LFENCE in FILL_RETURN_BUFFER on CPUs
 that lack it

From: Ben Hutchings <benh@...ian.org>

The mitigation for PBRSB includes adding LFENCE instructions to the
RSB filling sequence.  However, RSB filling is done on some older CPUs
that don't support the LFENCE instruction.

Define and use a BARRIER_NOSPEC macro which makes the LFENCE
conditional on X86_FEATURE_LFENCE_RDTSC, like the barrier_nospec()
macro defined for C code in <asm/barrier.h>.

Reported-by: Martin-Éric Racine <martin-eric.racine@....fi>
References: https://bugs.debian.org/1017425
Cc: stable@...r.kernel.org
Cc: regressions@...ts.linux.dev
Cc: Daniel Sneddon <daniel.sneddon@...ux.intel.com>
Cc: Pawan Gupta <pawan.kumar.gupta@...ux.intel.com>
Fixes: 2b1299322016 ("x86/speculation: Add RSB VM Exit protections")
Fixes: ba6e31af2be9 ("x86/speculation: Add LFENCE to RSB fill sequence")
Signed-off-by: Ben Hutchings <benh@...ian.org>
---
Re-sending this with properly matched From address and server.
Apologies if you got 2 copies.

Ben.

 arch/x86/include/asm/nospec-branch.h | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index e64fd20778b6..b1029fd88474 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -34,6 +34,11 @@
 
 #define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
 
+#ifdef __ASSEMBLY__
+
+/* Prevent speculative execution past this barrier. */
+#define BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC
+
 /*
  * Google experimented with loop-unrolling and this turned out to be
  * the optimal version - two calls, each with their own speculation
@@ -62,9 +67,7 @@
 	dec	reg;				\
 	jnz	771b;				\
 	/* barrier for jnz misprediction */	\
-	lfence;
-
-#ifdef __ASSEMBLY__
+	BARRIER_NOSPEC;
 
 /*
  * This should be used immediately before an indirect jump/call. It tells
@@ -138,7 +141,7 @@
 	int3
 .Lunbalanced_ret_guard_\@:
 	add $(BITS_PER_LONG/8), %_ASM_SP
-	lfence
+	BARRIER_NOSPEC
 .endm
 
  /*

Download attachment "signature.asc" of type "application/pgp-signature" (834 bytes)