update ceph source to reef 18.1.2

[ceph.git] / ceph / src / crypto / isa-l / isa-l_crypto / aes / cbc_enc_256_x8_sb.asm

diff --git a/ceph/src/crypto/isa-l/isa-l_crypto/aes/cbc_enc_256_x8_sb.asm b/ceph/src/crypto/isa-l/isa-l_crypto/aes/cbc_enc_256_x8_sb.asm
index 74ad399d46bc820500943a14801b58bfe489f59d..83e53ac117167d94f5abc5a1633c8b86aed73730 100644 (file)
--- a/ceph/src/crypto/isa-l/isa-l_crypto/aes/cbc_enc_256_x8_sb.asm
+++ b/ceph/src/crypto/isa-l/isa-l_crypto/aes/cbc_enc_256_x8_sb.asm
@@ -2,7 +2,7 @@
 ;  Copyright(c) 2011-2016 Intel Corporation All rights reserved.
 ;
 ;  Redistribution and use in source and binary forms, with or without
-;  modification, are permitted provided that the following conditions 
+;  modification, are permitted provided that the following conditions
 ;  are met:
 ;    * Redistributions of source code must retain the above copyright
 ;      notice, this list of conditions and the following disclaimer.
@@ -76,31 +76,31 @@
 %define func(x) proc_frame x
 %macro FUNC_SAVE 0
        alloc_stack     stack_size
-       save_xmm128     xmm6, 0*16
-       save_xmm128     xmm7, 1*16
-       save_xmm128     xmm8, 2*16
-       save_xmm128     xmm9, 3*16
-       save_xmm128     xmm10, 4*16
-       save_xmm128     xmm11, 5*16
-       save_xmm128     xmm12, 6*16
-       save_xmm128     xmm13, 7*16
-       save_xmm128     xmm14, 8*16
-       save_xmm128     xmm15, 9*16
+       vmovdqa [rsp + 0*16], xmm6
+       vmovdqa [rsp + 1*16], xmm7
+       vmovdqa [rsp + 2*16], xmm8
+       vmovdqa [rsp + 3*16], xmm9
+       vmovdqa [rsp + 4*16], xmm10
+       vmovdqa [rsp + 5*16], xmm11
+       vmovdqa [rsp + 6*16], xmm12
+       vmovdqa [rsp + 7*16], xmm13
+       vmovdqa [rsp + 8*16], xmm14
+       vmovdqa [rsp + 9*16], xmm15
        end_prolog
        mov     LEN, arg(4)
 %endmacro
 
 %macro FUNC_RESTORE 0
-       movdqa  xmm6, [rsp + 0*16]
-       movdqa  xmm7, [rsp + 1*16]
-       movdqa  xmm8, [rsp + 2*16]
-       movdqa  xmm9, [rsp + 3*16]
-       movdqa  xmm10, [rsp + 4*16]
-       movdqa  xmm11, [rsp + 5*16]
-       movdqa  xmm12, [rsp + 6*16]
-       movdqa  xmm13, [rsp + 7*16]
-       movdqa  xmm14, [rsp + 8*16]
-       movdqa  xmm15, [rsp + 9*16]
+       vmovdqa xmm6, [rsp + 0*16]
+       vmovdqa xmm7, [rsp + 1*16]
+       vmovdqa xmm8, [rsp + 2*16]
+       vmovdqa xmm9, [rsp + 3*16]
+       vmovdqa xmm10, [rsp + 4*16]
+       vmovdqa xmm11, [rsp + 5*16]
+       vmovdqa xmm12, [rsp + 6*16]
+       vmovdqa xmm13, [rsp + 7*16]
+       vmovdqa xmm14, [rsp + 8*16]
+       vmovdqa xmm15, [rsp + 9*16]
        add     rsp, stack_size
 %endmacro
 %endif
@@ -111,7 +111,7 @@
 %define PARALLEL_BLOCKS (UNROLLED_LOOPS)
 
 ; instruction set specific operation definitions
-%define MOVDQ         movdqu
+%define MOVDQ         vmovdqu
 %macro PXOR 2
    vpxor %1, %1, %2
 %endm
@@ -127,8 +127,9 @@
 %include "cbc_common.asm"
 
 
-global aes_cbc_enc_256_x8:function
+mk_global aes_cbc_enc_256_x8, function
 func(aes_cbc_enc_256_x8)
+       endbranch
        FUNC_SAVE
 
        mov     IDX, 0