https://github.com/openwall/john/issues/4585

diff --git src/arm32le.h src/arm32le.h
index 9a8ff99956..a0c60c0d26 100644
--- src/arm32le.h
+++ src/arm32le.h
@@ -27,7 +27,7 @@
 #define ARCH_INT_GT_32			0
 #endif
 
-#define ARCH_ALLOWS_UNALIGNED		0
+#define ARCH_ALLOWS_UNALIGNED		__ARM_FEATURE_UNALIGNED
 #define ARCH_INDEX(x)			((unsigned int)(unsigned char)(x))
 
 #define CPU_DETECT			0
diff --git src/arm64le.h src/arm64le.h
index a916cc0538..63b1ed932e 100644
--- src/arm64le.h
+++ src/arm64le.h
@@ -28,7 +28,7 @@
 #define ARCH_INT_GT_32			0
 #endif
 
-#define ARCH_ALLOWS_UNALIGNED		0
+#define ARCH_ALLOWS_UNALIGNED		__ARM_FEATURE_UNALIGNED
 #define ARCH_INDEX(x)			((unsigned int)(unsigned char)(x))
 
 #define CPU_DETECT			0
diff --git src/configure src/configure
index 6b9a5088c4..796660f8d7 100755
--- src/configure
+++ src/configure
@@ -9321,6 +9321,42 @@ else
      { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
 $as_echo "no" >&6; }
 
+fi
+rm -f core *.core core.conftest.* gmon.out bb.out conftest$ac_exeext \
+  conftest.$ac_objext conftest.beam conftest.$ac_ext
+fi
+
+  CC="$CC_BACKUP -march=armv8-a+simd"
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for ASIMD" >&5
+$as_echo_n "checking for ASIMD... " >&6; }
+  if test "$cross_compiling" = yes; then :
+  { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5
+$as_echo "$as_me: error: in \`$ac_pwd':" >&2;}
+as_fn_error $? "cannot run test program while cross compiling
+See \`config.log' for more details" "$LINENO" 5; }
+else
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+
+    #include <arm_neon.h>
+  #include <stdio.h>
+  extern void exit(int);
+  int main(){uint32x4_t t;*((long*)&t)=1;t=veorq_u32(t,t);if((*(unsigned*)&t)==88)printf(".");exit(0);}
+
+
+_ACEOF
+if ac_fn_c_try_run "$LINENO"; then :
+  CPU_BEST_FLAGS="-march=armv8-a+simd"
+     SIMD_NAME="ASIMD"
+     { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5
+$as_echo "yes" >&6; }
+     ARCH_LINK=arm64le.h
+
+else
+  CPU_NOTFOUND="1"
+     { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+
 fi
 rm -f core *.core core.conftest.* gmon.out bb.out conftest$ac_exeext \
   conftest.$ac_objext conftest.beam conftest.$ac_ext
@@ -9329,6 +9365,7 @@ fi
 else
   { $as_echo "$as_me:${as_lineno-$LINENO}: checking for NEON" >&5
 $as_echo_n "checking for NEON... " >&6; }
+  CC="$CC_BACKUP -mfpu=neon"
   cat confdefs.h - <<_ACEOF >conftest.$ac_ext
 /* end confdefs.h.  */
 
@@ -9350,6 +9387,34 @@ else
      { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
 $as_echo "no" >&6; }
 
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for ASIMD" >&5
+$as_echo_n "checking for ASIMD... " >&6; }
+  CC="$CC_BACKUP -march=armv8-a+simd"
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+
+    #include <arm_neon.h>
+  #include <stdio.h>
+  extern void exit(int);
+  int main(){uint32x4_t t;*((long*)&t)=1;t=veorq_u32(t,t);if((*(unsigned*)&t)==88)printf(".");exit(0);}
+
+
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  CPU_BEST_FLAGS="-march=armv8-a+simd"
+     SIMD_NAME="ASIMD"
+     ARCH_LINK=arm64le.h
+     { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5
+$as_echo "yes" >&6; }
+
+else
+  CPU_NOTFOUND="1"
+     { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+
 fi
 rm -f core conftest.err conftest.$ac_objext \
     conftest$ac_exeext conftest.$ac_ext
diff --git src/pseudo_intrinsics.h src/pseudo_intrinsics.h
index 5fabbdbb81..450e2477b5 100644
--- src/pseudo_intrinsics.h
+++ src/pseudo_intrinsics.h
@@ -66,10 +66,10 @@ typedef union {
 #define VLOADU_EMULATED         1
 #define vor(x, y)               (vtype)vorrq_u32((x).v32, (y).v32)
 #define vorn(x, y)              (vtype)vornq_u32((x).v32, (y).v32)
-#define vroti_epi32(x, i)       (i > 0 ? (vtype)vsliq_n_u32(vshrq_n_u32((x).v32, 32 - (i)), (x).v32, i) : \
-                                         (vtype)vsriq_n_u32(vshlq_n_u32((x).v32, 32 + (i)), (x).v32, -(i)))
-#define vroti_epi64(x, i)       (i > 0 ? (vtype)vsliq_n_u64(vshrq_n_u64((x).v64, 64 - (i)), (x).v64, i) : \
-                                         (vtype)vsriq_n_u64(vshlq_n_u64((x).v64, 64 + (i)), (x).v64, -(i)))
+#define vroti_epi32(x, i)       (i > 0 ? (vtype)vsliq_n_u32(vshrq_n_u32((x).v32, 32 - ((i) & 31)), (x).v32, (i) & 31) : \
+                                 (vtype)vsriq_n_u32(vshlq_n_u32((x).v32, (32 + (i)) & 31), (x).v32, (-(i)) & 31))
+#define vroti_epi64(x, i)       (i > 0 ? (vtype)vsliq_n_u64(vshrq_n_u64((x).v64, 64 - ((i) & 63)), (x).v64, (i) & 63) : \
+                                 (vtype)vsriq_n_u64(vshlq_n_u64((x).v64, (64 + (i)) & 63), (x).v64, (-(i)) & 63))
 #define vroti16_epi32           vroti_epi32
 #define vset1_epi32(i)          (vtype)vdupq_n_u32(i)
 #define vset1_epi64(i)          (vtype)vdupq_n_u64(i)