add framework to support archs without a native wait4 syscall

this commit should make no codegen change for existing archs, but is a
prerequisite for new archs including riscv32. the wait4 emulation
backend provides both cancellable and non-cancellable variants because
waitpid is required to be a cancellation point, but all of our other
uses are not, and most of them cannot be.

based on patch by Stefan O'Rear.

src/internal/emulate_wait4.c

@@ -0,0 +1,55 @@
+#include <sys/wait.h>
+#include "syscall.h"
+
+#ifndef SYS_wait4
+hidden long __emulate_wait4(int pid, int *status, int options, void *kru, int cp)
+{
+	idtype_t t;
+	int r;
+	siginfo_t info;
+
+	info.si_pid = 0;
+	if (pid < -1) {
+		t = P_PGID;
+		pid = -pid;
+	} else if (pid == -1) {
+		t = P_ALL;
+	} else if (pid == 0) {
+		t = P_PGID;
+	} else {
+		t = P_PID;
+	}
+
+	if (cp) r = __syscall_cp(SYS_waitid, t, pid, &info, options|WEXITED, kru);
+	else r = __syscall(SYS_waitid, t, pid, &info, options|WEXITED, kru);
+
+	if (r<0) return r;
+
+	if (info.si_pid && status) {
+		int sw=0;
+		switch (info.si_code) {
+		case CLD_CONTINUED:
+			sw = 0xffff;
+			break;
+		case CLD_DUMPED:
+			sw = info.si_status&0x7f | 0x80;
+			break;
+		case CLD_EXITED:
+			sw = (info.si_status&0xff) << 8;
+			break;
+		case CLD_KILLED:
+			sw = info.si_status&0x7f;
+			break;
+		case CLD_STOPPED:
+		case CLD_TRAPPED:
+			/* see ptrace(2); the high bits of si_status can contain */
+			/* PTRACE_EVENT_ values which must be preserved */
+			sw = (info.si_status << 8) + 0x7f;
+			break;
+		}
+		*status = sw;
+	}
+
+	return info.si_pid;
+}
+#endif

src/internal/syscall.h

@@ -391,6 +391,18 @@ static inline long __alt_socketcall(int sys, int sock, int cp, syscall_arg_t a,
 #define __sys_open_cp(...) __SYSCALL_DISP(__sys_open_cp,,__VA_ARGS__)
 #define sys_open_cp(...) __syscall_ret(__sys_open_cp(__VA_ARGS__))
 
+#ifdef SYS_wait4
+#define __sys_wait4(a,b,c,d) __syscall(SYS_wait4,a,b,c,d)
+#define __sys_wait4_cp(a,b,c,d) __syscall_cp(SYS_wait4,a,b,c,d)
+#else
+hidden long __emulate_wait4(int, int *, int, void *, int);
+#define __sys_wait4(a,b,c,d) __emulate_wait4(a,b,c,d,0)
+#define __sys_wait4_cp(a,b,c,d) __emulate_wait4(a,b,c,d,1)
+#endif
+
+#define sys_wait4(a,b,c,d) __syscall_ret(__sys_wait4(a,b,c,d))
+#define sys_wait4_cp(a,b,c,d) __syscall_ret(__sys_wait4_cp(a,b,c,d))
+
 hidden void __procfdname(char __buf[static 15+3*sizeof(int)], unsigned);
 
 hidden void *__vdsosym(const char *, const char *);

src/linux/wait4.c

@@ -26,7 +26,7 @@ pid_t wait4(pid_t pid, int *status, int options, struct rusage *ru)
 	}
 #endif
 	char *dest = ru ? (char *)&ru->ru_maxrss - 4*sizeof(long) : 0;
-	r = __syscall(SYS_wait4, pid, status, options, dest);
+	r = __sys_wait4(pid, status, options, dest);
 	if (r>0 && ru && sizeof(time_t) > sizeof(long)) {
 		long kru[4];
 		memcpy(kru, dest, 4*sizeof(long));

src/process/waitpid.c

@@ -3,5 +3,5 @@
 
 pid_t waitpid(pid_t pid, int *status, int options)
 {
-	return syscall_cp(SYS_wait4, pid, status, options, 0);
+	return sys_wait4_cp(pid, status, options, 0);
 }

src/stdio/pclose.c

@@ -7,7 +7,7 @@ int pclose(FILE *f)
 	int status, r;
 	pid_t pid = f->pipe_pid;
 	fclose(f);
-	while ((r=__syscall(SYS_wait4, pid, &status, 0, 0)) == -EINTR);
+	while ((r=__sys_wait4(pid, &status, 0, 0)) == -EINTR);
 	if (r<0) return __syscall_ret(r);
 	return status;
 }

src/unistd/faccessat.c

@@ -53,7 +53,7 @@ int faccessat(int fd, const char *filename, int amode, int flag)
 	if (pid<0 || __syscall(SYS_read, p[0], &ret, sizeof ret) != sizeof(ret))
 		ret = -EBUSY;
 	__syscall(SYS_close, p[0]);
-	__syscall(SYS_wait4, pid, &status, __WCLONE, 0);
+	__sys_wait4(pid, &status, __WCLONE, 0);
 
 	__restore_sigs(&set);