Some archs -- arm64 and s390x -- implemented chacha using instructions
that are available most places, but aren't always available. The kernel
handles this just fine, but the selftest does not. Check the hwcaps
before running, and skip the test if the cpu doesn't support it. As
well, on s390x, always emit the fallback instructions of an alternative
block, to ensure maximum compatibility.

Co-authored-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 tools/include/asm/alternative.h               | 10 ++++++++++
 .../testing/selftests/vDSO/vdso_test_chacha.c | 20 +++++++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h
index 7ce02a223732..8e548ac8f740 100644
--- a/tools/include/asm/alternative.h
+++ b/tools/include/asm/alternative.h
@@ -2,8 +2,18 @@
 #ifndef _TOOLS_ASM_ALTERNATIVE_ASM_H
 #define _TOOLS_ASM_ALTERNATIVE_ASM_H
 
+#if defined(__s390x__)
+#ifdef __ASSEMBLY__
+.macro ALTERNATIVE oldinstr, newinstr, feature
+	\oldinstr
+.endm
+#endif
+#else
+
 /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
 
 #define ALTERNATIVE #
 
 #endif
+
+#endif
diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha.c b/tools/testing/selftests/vDSO/vdso_test_chacha.c
index e81d72c9882e..b1ea532c5996 100644
--- a/tools/testing/selftests/vDSO/vdso_test_chacha.c
+++ b/tools/testing/selftests/vDSO/vdso_test_chacha.c
@@ -5,11 +5,29 @@
 
 #include <tools/le_byteshift.h>
 #include <sys/random.h>
+#include <sys/auxv.h>
 #include <string.h>
 #include <stdint.h>
 #include <stdbool.h>
 #include "../kselftest.h"
 
+#if defined(__aarch64__)
+static bool cpu_has_capabilities(void)
+{
+	return getauxval(AT_HWCAP) & HWCAP_ASIMD;
+}
+#elif defined(__s390x__)
+static bool cpu_has_capabilities(void)
+{
+	return getauxval(AT_HWCAP) & HWCAP_S390_VXRS;
+}
+#else
+static bool cpu_has_capabilities(void)
+{
+	return true;
+}
+#endif
+
 static uint32_t rol32(uint32_t word, unsigned int shift)
 {
 	return (word << (shift & 31)) | (word >> ((-shift) & 31));
@@ -67,6 +85,8 @@ int main(int argc, char *argv[])
 	uint8_t output1[BLOCK_SIZE * BLOCKS], output2[BLOCK_SIZE * BLOCKS];
 
 	ksft_print_header();
+	if (!cpu_has_capabilities())
+		ksft_exit_skip("Required CPU capabilities missing\n");
 	ksft_set_plan(1);
 
 	for (unsigned int trial = 0; trial < TRIALS; ++trial) {
-- 
2.46.0