AArch64: Gate various crypto intrinsics availability based on features

The 64-bit variant of PMULL{2} and AES instructions are available if FEAT_AES
is implemented according to the Arm ARM [1].  Similarly FEAT_SHA1 and
FEAT_SHA256 enable the use of SHA1 and SHA256 instruction variants.
This patch fixes arm_neon.h to correctly reflect the feature availability based
on '+aes' and '+sha2' as opposed to the ambiguous catch-all '+crypto'.

[1] Section D17.2.61, C7.2.215

2022-01-11  Tejas Belagod  <tejas.belagod@arm.com>

gcc/ChangeLog:

	* config/aarch64/arm_neon.h (vmull_p64, vmull_high_p64, vaeseq_u8,
	vaesdq_u8, vaesmcq_u8, vaesimcq_u8): Gate under "nothing+aes".
	(vsha1*_u32, vsha256*_u32): Gate under "nothing+sha2".

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/acle/pmull64.c: New.
	* gcc.target/aarch64/aes-fuse-1.c: Replace '+crypto' with corresponding
	feature flag based on the intrinsic.
	* gcc.target/aarch64/aes-fuse-2.c: Likewise.
	* gcc.target/aarch64/aes_1.c: Likewise.
	* gcc.target/aarch64/aes_2.c: Likewise.
	* gcc.target/aarch64/aes_xor_combine.c: Likewise.
	* gcc.target/aarch64/sha1_1.c: Likewise.
	* gcc.target/aarch64/sha256_1.c: Likewise.
	* gcc.target/aarch64/target_attr_crypto_ice_1.c: Likewise.

gcc/config/aarch64/arm_neon.h

@@ -7496,7 +7496,7 @@ vqrdmlshs_laneq_s32 (int32_t __a, int32_t __b, int32x4_t __c, const int __d)
 #pragma GCC pop_options
 
 #pragma GCC push_options
-#pragma GCC target ("+nothing+crypto")
+#pragma GCC target ("+nothing+aes")
 /* vaes  */
 
 __extension__ extern __inline uint8x16_t
@@ -7526,6 +7526,22 @@ vaesimcq_u8 (uint8x16_t data)
 {
   return __builtin_aarch64_crypto_aesimcv16qi_uu (data);
 }
+
+__extension__ extern __inline poly128_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vmull_p64 (poly64_t __a, poly64_t __b)
+{
+  return
+    __builtin_aarch64_crypto_pmulldi_ppp (__a, __b);
+}
+
+__extension__ extern __inline poly128_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vmull_high_p64 (poly64x2_t __a, poly64x2_t __b)
+{
+  return __builtin_aarch64_crypto_pmullv2di_ppp (__a, __b);
+}
+
 #pragma GCC pop_options
 
 /* vcage  */
@@ -20772,7 +20788,7 @@ vrsrad_n_u64 (uint64_t __a, uint64_t __b, const int __c)
 }
 
 #pragma GCC push_options
-#pragma GCC target ("+nothing+crypto")
+#pragma GCC target ("+nothing+sha2")
 
 /* vsha1  */
 
@@ -20849,21 +20865,6 @@ vsha256su1q_u32 (uint32x4_t __tw0_3, uint32x4_t __w8_11, uint32x4_t __w12_15)
 						       __w12_15);
 }
 
-__extension__ extern __inline poly128_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vmull_p64 (poly64_t __a, poly64_t __b)
-{
-  return
-    __builtin_aarch64_crypto_pmulldi_ppp (__a, __b);
-}
-
-__extension__ extern __inline poly128_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vmull_high_p64 (poly64x2_t __a, poly64x2_t __b)
-{
-  return __builtin_aarch64_crypto_pmullv2di_ppp (__a, __b);
-}
-
 #pragma GCC pop_options
 
 /* vshl */

gcc/testsuite/gcc.target/aarch64/acle/pmull64.c

@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.2-a" } */
+
+#pragma push_options
+#pragma GCC target ("+aes")
+
+#include "arm_neon.h"
+
+int foo (poly64_t a, poly64_t b)
+{
+  return vgetq_lane_s32 (vreinterpretq_s32_p128 (vmull_p64 (a, b)), 0);
+}
+
+/* { dg-final { scan-assembler "\tpmull\tv" } } */

gcc/testsuite/gcc.target/aarch64/aes-fuse-1.c

@@ -1,6 +1,6 @@
 /* { dg-do compile } */
-/* { dg-options "-O3 -mcpu=cortex-a72+crypto -dp" } */
-/* { dg-additional-options "-march=armv8-a+crypto" { target { aarch64*-*-* } } }*/
+/* { dg-options "-O3 -mcpu=cortex-a72+aes -dp" } */
+/* { dg-additional-options "-march=armv8-a+aes" { target { aarch64*-*-* } } }*/
 
 #include <arm_neon.h>
 

gcc/testsuite/gcc.target/aarch64/aes-fuse-2.c

@@ -1,6 +1,6 @@
 /* { dg-do compile } */
-/* { dg-options "-O3 -mcpu=cortex-a72+crypto -dp" } */
-/* { dg-additional-options "-march=armv8-a+crypto" { target { aarch64*-*-* } } }*/
+/* { dg-options "-O3 -mcpu=cortex-a72+aes -dp" } */
+/* { dg-additional-options "-march=armv8-a+aes" { target { aarch64*-*-* } } }*/
 
 #include <arm_neon.h>
 

gcc/testsuite/gcc.target/aarch64/aes_1.c

@@ -1,6 +1,6 @@
 
 /* { dg-do compile } */
-/* { dg-options "-march=armv8-a+crypto" } */
+/* { dg-options "-march=armv8-a+aes" } */
 
 #include "arm_neon.h"
 

gcc/testsuite/gcc.target/aarch64/aes_2.c

@@ -1,6 +1,6 @@
 
 /* { dg-do compile } */
-/* { dg-options "-O3 -march=armv8-a+crypto" } */
+/* { dg-options "-O3 -march=armv8-a+aes" } */
 
 #include "arm_neon.h"
 
@@ -76,4 +76,6 @@ test7 (uint8x16_t a, uint8x16_t b)
   return result;
 }
 /* { dg-final { scan-assembler-not "mov" } } */
+/* { dg-final { scan-assembler "aesd\tv" } } */
+/* { dg-final { scan-assembler "aese\tv" } } */
 

gcc/testsuite/gcc.target/aarch64/aes_xor_combine.c

@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O3 -mcpu=cortex-a55+crypto" } */
+/* { dg-options "-O3 -mcpu=cortex-a55+aes" } */
 #include <arm_neon.h>
 
 #define AESE(r, v, key) (r = vaeseq_u8 ((v), (key)));

gcc/testsuite/gcc.target/aarch64/sha1_1.c

@@ -1,6 +1,6 @@
 
 /* { dg-do compile } */
-/* { dg-options "-march=armv8-a+crypto" } */
+/* { dg-options "-march=armv8-a+sha2" } */
 
 #include "arm_neon.h"
 

gcc/testsuite/gcc.target/aarch64/sha256_1.c

@@ -1,6 +1,6 @@
 
 /* { dg-do compile } */
-/* { dg-options "-march=armv8-a+crypto" } */
+/* { dg-options "-march=armv8-a+sha2" } */
 
 #include "arm_neon.h"
 

gcc/testsuite/gcc.target/aarch64/target_attr_crypto_ice_1.c

@@ -6,7 +6,7 @@
 /* Unless we do something about re-laying out the SIMD builtin types
    this testcase ICEs during expansion of the crypto builtin.  */
 
-__attribute__ ((target ("cpu=cortex-a57+crypto")))
+__attribute__ ((target ("cpu=cortex-a57+sha2")))
 uint32x4_t
 test_vsha1cq_u32 (uint32x4_t hash_abcd, uint32_t hash_e, uint32x4_t wk)
 {