*
*/
+#include <linux/linkage.h>
#include "glue_helper-asm-avx.S"
.file "serpent-avx-x86_64-asm_64.S"
transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
.align 8
-.type __serpent_enc_blk8_avx,@function;
-
__serpent_enc_blk8_avx:
/* input:
* %rdi: ctx, CTX
write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
ret;
+ENDPROC(__serpent_enc_blk8_avx)
.align 8
-.type __serpent_dec_blk8_avx,@function;
-
__serpent_dec_blk8_avx:
/* input:
* %rdi: ctx, CTX
write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
ret;
+ENDPROC(__serpent_dec_blk8_avx)
-.align 8
-.global serpent_ecb_enc_8way_avx
-.type serpent_ecb_enc_8way_avx,@function;
-
-serpent_ecb_enc_8way_avx:
+ENTRY(serpent_ecb_enc_8way_avx)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
store_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
ret;
+ENDPROC(serpent_ecb_enc_8way_avx)
-.align 8
-.global serpent_ecb_dec_8way_avx
-.type serpent_ecb_dec_8way_avx,@function;
-
-serpent_ecb_dec_8way_avx:
+ENTRY(serpent_ecb_dec_8way_avx)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
store_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
ret;
+ENDPROC(serpent_ecb_dec_8way_avx)
-.align 8
-.global serpent_cbc_dec_8way_avx
-.type serpent_cbc_dec_8way_avx,@function;
-
-serpent_cbc_dec_8way_avx:
+ENTRY(serpent_cbc_dec_8way_avx)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
store_cbc_8way(%rdx, %rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
ret;
+ENDPROC(serpent_cbc_dec_8way_avx)
-.align 8
-.global serpent_ctr_8way_avx
-.type serpent_ctr_8way_avx,@function;
-
-serpent_ctr_8way_avx:
+ENTRY(serpent_ctr_8way_avx)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
store_ctr_8way(%rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
ret;
+ENDPROC(serpent_ctr_8way_avx)
*
*/
+#include <linux/linkage.h>
+
.file "serpent-sse2-i586-asm_32.S"
.text
pxor t0, x3; \
movdqu x3, (3*4*4)(out);
-.align 8
-.global __serpent_enc_blk_4way
-.type __serpent_enc_blk_4way,@function;
-
-__serpent_enc_blk_4way:
+ENTRY(__serpent_enc_blk_4way)
/* input:
* arg_ctx(%esp): ctx, CTX
* arg_dst(%esp): dst
movl arg_dst(%esp), %eax;
cmpb $0, arg_xor(%esp);
- jnz __enc_xor4;
+ jnz .L__enc_xor4;
write_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
ret;
-__enc_xor4:
+.L__enc_xor4:
xor_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
ret;
+ENDPROC(__serpent_enc_blk_4way)
-.align 8
-.global serpent_dec_blk_4way
-.type serpent_dec_blk_4way,@function;
-
-serpent_dec_blk_4way:
+ENTRY(serpent_dec_blk_4way)
/* input:
* arg_ctx(%esp): ctx, CTX
* arg_dst(%esp): dst
write_blocks(%eax, RC, RD, RB, RE, RT0, RT1, RA);
ret;
+ENDPROC(serpent_dec_blk_4way)
*
*/
+#include <linux/linkage.h>
+
.file "serpent-sse2-x86_64-asm_64.S"
.text
pxor t0, x3; \
movdqu x3, (3*4*4)(out);
-.align 8
-.global __serpent_enc_blk_8way
-.type __serpent_enc_blk_8way,@function;
-
-__serpent_enc_blk_8way:
+ENTRY(__serpent_enc_blk_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
leaq (4*4*4)(%rsi), %rax;
testb %cl, %cl;
- jnz __enc_xor8;
+ jnz .L__enc_xor8;
write_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
write_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
ret;
-__enc_xor8:
+.L__enc_xor8:
xor_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
ret;
+ENDPROC(__serpent_enc_blk_8way)
-.align 8
-.global serpent_dec_blk_8way
-.type serpent_dec_blk_8way,@function;
-
-serpent_dec_blk_8way:
+ENTRY(serpent_dec_blk_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
write_blocks(%rax, RC2, RD2, RB2, RE2, RK0, RK1, RK2);
ret;
+ENDPROC(serpent_dec_blk_8way)