s390/vdso: Get rid of permutation constants

The three byte masks for VECTOR PERMUTE are not needed, since the
instruction VECTOR SHIFT LEFT DOUBLE BY BYTE can be used to implement
the required "rotate left" easily.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Jens Remus <jremus@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>

diff --git a/arch/s390/kernel/vdso64/vgetrandom-chacha.S b/arch/s390/kernel/vdso64/vgetrandom-chacha.S
index d802b0a96f4141a98fe45a11f21e699505b514cc..475711e0c6a36a1bdda9d4a8564c3d20ba6d374f 100644 (file)
--- a/arch/s390/kernel/vdso64/vgetrandom-chacha.S
+++ b/arch/s390/kernel/vdso64/vgetrandom-chacha.S
@@ -1,5 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
+#include <linux/stringify.h>
 #include <linux/linkage.h>
 #include <asm/alternative.h>
 #include <asm/fpu-insn.h>
@@ -12,9 +13,6 @@
 #define COPY1  %v5
 #define COPY2  %v6
 #define COPY3  %v7
-#define PERM4  %v16
-#define PERM8  %v17
-#define PERM12 %v18
 #define BEPERM %v19
 #define TMP0   %v20
 #define TMP1   %v21
@@ -23,12 +21,9 @@
 
        .section .rodata
 
-       .balign 128
+       .balign 32
 .Lconstants:
        .long   0x61707865,0x3320646e,0x79622d32,0x6b206574 # endian-neutral
-       .long   0x04050607,0x08090a0b,0x0c0d0e0f,0x00010203 # rotl  4 bytes
-       .long   0x08090a0b,0x0c0d0e0f,0x00010203,0x04050607 # rotl  8 bytes
-       .long   0x0c0d0e0f,0x00010203,0x04050607,0x08090a0b # rotl 12 bytes
        .long   0x03020100,0x07060504,0x0b0a0908,0x0f0e0d0c # byte swap
 
        .text
@@ -48,8 +43,8 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
        /* COPY0 = "expand 32-byte k" */
        VL      COPY0,0,,%r1
 
-       /* PERM4-PERM12,BEPERM = byte selectors for VPERM */
-       VLM     PERM4,BEPERM,16,%r1
+       /* BEPERM = byte selectors for VPERM */
+       ALTERNATIVE __stringify(VL BEPERM,16,,%r1), "brcl 0,0", ALT_FACILITY(148)
 
        /* COPY1,COPY2 = key */
        VLM     COPY1,COPY2,0,%r3
@@ -89,11 +84,11 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
        VERLLF  STATE1,STATE1,7
 
        /* STATE1[0,1,2,3] = STATE1[1,2,3,0] */
-       VPERM   STATE1,STATE1,STATE1,PERM4
+       VSLDB   STATE1,STATE1,STATE1,4
        /* STATE2[0,1,2,3] = STATE2[2,3,0,1] */
-       VPERM   STATE2,STATE2,STATE2,PERM8
+       VSLDB   STATE2,STATE2,STATE2,8
        /* STATE3[0,1,2,3] = STATE3[3,0,1,2] */
-       VPERM   STATE3,STATE3,STATE3,PERM12
+       VSLDB   STATE3,STATE3,STATE3,12
 
        /* STATE0 += STATE1, STATE3 = rotl32(STATE3 ^ STATE0, 16) */
        VAF     STATE0,STATE0,STATE1
@@ -116,11 +111,11 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
        VERLLF  STATE1,STATE1,7
 
        /* STATE1[0,1,2,3] = STATE1[3,0,1,2] */
-       VPERM   STATE1,STATE1,STATE1,PERM12
+       VSLDB   STATE1,STATE1,STATE1,12
        /* STATE2[0,1,2,3] = STATE2[2,3,0,1] */
-       VPERM   STATE2,STATE2,STATE2,PERM8
+       VSLDB   STATE2,STATE2,STATE2,8
        /* STATE3[0,1,2,3] = STATE3[1,2,3,0] */
-       VPERM   STATE3,STATE3,STATE3,PERM4
+       VSLDB   STATE3,STATE3,STATE3,4
        brctg   %r0,.Ldoubleround
 
        /* OUTPUT0 = STATE0 + STATE0 */