tools/virtio: Fix arm64 ringtest compilation error

Add cpu_relax() for arm64 instead of directly assert(), and add assert.h
header file. Also, add smp_wmb and smp_mb for arm64.

Compilation error as follows, avoid __always_inline undefined.

    $ make
    cc -Wall -pthread -O2 -ggdb -flto -fwhole-program -c -o ring.o ring.c
    In file included from ring.c:10:
    main.h: In function ‘busy_wait’:
    main.h:99:21: warning: implicit declaration of function ‘assert’
    [-Wimplicit-function-declaration]
    99 | #define cpu_relax() assert(0)
        |                     ^~~~~~
    main.h:107:17: note: in expansion of macro ‘cpu_relax’
    107 |                 cpu_relax();
        |                 ^~~~~~~~~
    main.h:12:1: note: ‘assert’ is defined in header ‘<assert.h>’; did you
    forget to ‘#include <assert.h>’?
    11 | #include <stdbool.h>
    +++ |+#include <assert.h>
    12 |
    main.h: At top level:
    main.h:143:23: error: expected ‘;’ before ‘void’
    143 | static __always_inline
        |                       ^
        |                       ;
    144 | void __read_once_size(const volatile void *p, void *res, int
    size)
        | ~~~~
    main.h:158:23: error: expected ‘;’ before ‘void’
    158 | static __always_inline void __write_once_size(volatile void *p,
    void *res, int size)
        |                       ^~~~~
        |                       ;
    make: *** [<builtin>: ring.o] Error 1

Signed-off-by: Rong Tao <rongtao@cestc.cn>
Message-Id: <tencent_F53E159DD7925174445D830DA19FACF44B07@qq.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Author: Rtoax

tools/virtio/ringtest/main.h

@@ -8,6 +8,7 @@
 #ifndef MAIN_H
 #define MAIN_H
 
+#include <assert.h>
 #include <stdbool.h>
 
 extern int param;
@@ -95,6 +96,8 @@ extern unsigned ring_size;
 #define cpu_relax() asm ("rep; nop" ::: "memory")
 #elif defined(__s390x__)
 #define cpu_relax() barrier()
+#elif defined(__aarch64__)
+#define cpu_relax() asm ("yield" ::: "memory")
 #else
 #define cpu_relax() assert(0)
 #endif
@@ -112,6 +115,8 @@ static inline void busy_wait(void)
 
 #if defined(__x86_64__) || defined(__i386__)
 #define smp_mb()     asm volatile("lock; addl $0,-132(%%rsp)" ::: "memory", "cc")
+#elif defined(__aarch64__)
+#define smp_mb()     asm volatile("dmb ish" ::: "memory")
 #else
 /*
  * Not using __ATOMIC_SEQ_CST since gcc docs say they are only synchronized
@@ -136,10 +141,16 @@ static inline void busy_wait(void)
 
 #if defined(__i386__) || defined(__x86_64__) || defined(__s390x__)
 #define smp_wmb() barrier()
+#elif defined(__aarch64__)
+#define smp_wmb() asm volatile("dmb ishst" ::: "memory")
 #else
 #define smp_wmb() smp_release()
 #endif
 
+#ifndef __always_inline
+#define __always_inline inline __attribute__((always_inline))
+#endif
+
 static __always_inline
 void __read_once_size(const volatile void *p, void *res, int size)
 {