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.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: thomas.lendacky@amd.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515707194-20531-6-git-send-email-dwmw@amazon.co.uk

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

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;
 

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;
 

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: