[PATCH v7 04/11] x86/retpoline/crypto: Convert crypto assembler indirect jumps

From: David Woodhouse
Date: Tue Jan 09 2018 - 09:44:29 EST


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

Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
Acked-By: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx>
Acked-by: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: gnomes@xxxxxxxxxxxxxxxxxxx
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Jiri Kosina <jikos@xxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxx>
Cc: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxxx>
Cc: Paul Turner <pjt@xxxxxxxxxx>
Cc: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
---
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 | 3 ++-
4 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 16627fe..3d09e3a 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
+ CALL_NOSPEC %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
+ CALL_NOSPEC %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..a14af6e 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;
+ CALL_NOSPEC %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..b66bbfa 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;
+ CALL_NOSPEC %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..d9b734d 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

@@ -172,7 +173,7 @@ continue_block:
movzxw (bufp, %rax, 2), len
lea crc_array(%rip), bufp
lea (bufp, len, 1), bufp
- jmp *bufp
+ JMP_NOSPEC bufp

################################################################
## 2a) PROCESS FULL BLOCKS:
--
2.7.4