linux-kernel - [PATCH v4 02/13] x86/retpoline/crypto: Convert crypto assembler indirect jumps

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

Message-Id: <1515117669-24787-3-git-send-email-dwmw@amazon.co.uk>
Date:   Fri,  5 Jan 2018 02:00:58 +0000
From:   David Woodhouse <dwmw@...zon.co.uk>
To:     Andi Kleen <ak@...ux.intel.com>
Cc:     Paul Turner <pjt@...gle.com>, LKML <linux-kernel@...r.kernel.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Greg Kroah-Hartman <gregkh@...ux-foundation.org>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Dave Hansen <dave.hansen@...el.com>, tglx@...utronix.de,
        Kees Cook <keescook@...gle.com>,
        Rik van Riel <riel@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Andy Lutomirski <luto@...capital.net>,
        Jiri Kosina <jikos@...nel.org>, gnomes@...rguk.ukuu.org.uk
Subject: [PATCH v4 02/13] x86/retpoline/crypto: Convert crypto assembler indirect jumps

Convert all indirect jumps in crypto assembler code to use non-speculative
sequences when CONFIG_RETPOLINE is enabled.

[Andi Kleen: Fix crc32c 'bufp' handling]
Signed-off-by: David Woodhouse <dwmw@...zon.co.uk>
---
 arch/x86/crypto/aesni-intel_asm.S            | 5 +++--
 arch/x86/crypto/camellia-aesni-avx-asm_64.S  | 3 ++-
 arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 3 ++-
 arch/x86/crypto/crc32c-pcl-intel-asm_64.S    | 4 +++-
 4 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 16627fe..074c137 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -32,6 +32,7 @@
 #include <linux/linkage.h>
 #include <asm/inst.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 
 /*
  * The following macros are used to move an (un)aligned 16 byte value to/from
@@ -2884,7 +2885,7 @@ ENTRY(aesni_xts_crypt8)
 	pxor INC, STATE4
 	movdqu IV, 0x30(OUTP)
 
-	call *%r11
+	NOSPEC_CALL r11
 
 	movdqu 0x00(OUTP), INC
 	pxor INC, STATE1
@@ -2929,7 +2930,7 @@ ENTRY(aesni_xts_crypt8)
 	_aesni_gf128mul_x_ble()
 	movups IV, (IVP)
 
-	call *%r11
+	NOSPEC_CALL r11
 
 	movdqu 0x40(OUTP), INC
 	pxor INC, STATE1
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index f7c495e..98a717b 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -17,6 +17,7 @@
 
 #include <linux/linkage.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
@@ -1227,7 +1228,7 @@ camellia_xts_crypt_16way:
 	vpxor 14 * 16(%rax), %xmm15, %xmm14;
 	vpxor 15 * 16(%rax), %xmm15, %xmm15;
 
-	call *%r9;
+	NOSPEC_CALL r9;
 
 	addq $(16 * 16), %rsp;
 
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index eee5b39..99d09d3 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -12,6 +12,7 @@
 
 #include <linux/linkage.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
@@ -1343,7 +1344,7 @@ camellia_xts_crypt_32way:
 	vpxor 14 * 32(%rax), %ymm15, %ymm14;
 	vpxor 15 * 32(%rax), %ymm15, %ymm15;
 
-	call *%r9;
+	NOSPEC_CALL r9;
 
 	addq $(16 * 32), %rsp;
 
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 7a7de27..480f4e3 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -45,6 +45,7 @@
 
 #include <asm/inst.h>
 #include <linux/linkage.h>
+#include <asm/nospec-branch.h>
 
 ## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction
 
@@ -75,6 +76,7 @@
 .text
 ENTRY(crc_pcl)
 #define    bufp		%rdi
+#define    bufp_raw	 rdi
 #define    bufp_dw	%edi
 #define    bufp_w	%di
 #define    bufp_b	%dil
@@ -172,7 +174,7 @@ continue_block:
 	movzxw  (bufp, %rax, 2), len
 	lea	crc_array(%rip), bufp
 	lea     (bufp, len, 1), bufp
-	jmp     *bufp
+	NOSPEC_JMP bufp_raw
 
 	################################################################
 	## 2a) PROCESS FULL BLOCKS:
-- 
2.7.4