path: root/src/micro/port_linux.c

/* Linux port: stdin/stdout a byte at a time, the syscalls, diagnostics
   on stderr. same behaviour as io_linux.c plus core.c's hostcall.
   1..6 are files, getenv and unix time. 7 exits the process, 8 is a
   counter, 9 reports the machine size. */
#include <stdio.h>
#include <errno.h>
#include <fcntl.h>
#ifdef _WIN32
#include <io.h>
#include <process.h>
#ifndef O_BINARY
#define O_BINARY _O_BINARY
#endif
#if defined(_MSC_VER)
#define open _open
#define close _close
#define read _read
#define write _write
#endif
#else
#include <unistd.h>
#include <sys/socket.h>
#include <sys/wait.h>
#include <poll.h>
#include <signal.h>
#ifndef O_BINARY
#define O_BINARY 0
#endif
#endif
#include <stdlib.h>
#include <string.h>
#include <time.h>
#include "micro_port.h"
#include "bops.h"
#ifdef ZY_THREADS
#define VM_TLS _Thread_local
#else
#define VM_TLS
#endif

/* the machine's memory: a block that grows by realloc, zero in the new part. the
   base can move on a grow, which micro.c takes into account (it re-reads m). */
static VM_TLS Cell *lmem;
static VM_TLS UCell lcap;

Cell *micro_mem_alloc(UCell words)
{
	Cell *n;
	if (words <= lcap && lmem) return lmem;
	if (words > ((UCell)-1) / sizeof(Cell)) return NULL;
	n = realloc(lmem, words * sizeof(Cell));
	if (!n) return NULL;
	memset(n + lcap, 0, (words - lcap) * sizeof(Cell));
	lmem = n;
	lcap = words;
	return n;
}

#if defined(ZY_THREADS)
static VM_TLS unsigned char input_bytes[65536];
static VM_TLS int input_position, input_count, input_ended;
static int input_fill(int wait) {
 if (input_position < input_count) return 1;
 if (input_ended) return 0;
 if (!wait) { struct pollfd descriptor = {0, POLLIN, 0}; if (poll(&descriptor, 1, 0) <= 0) return 0; }
 else fflush(stdout);
 int n = (int)read(0, input_bytes, sizeof input_bytes);
 if (n <= 0) { input_ended = 1; return 0; }
 input_position = 0; input_count = n; return 1;
}
int micro_getc(void) { return input_fill(1) ? input_bytes[input_position++] : -1; }
int micro_eof(void) { input_fill(0); return input_ended; }
#else
int micro_getc(void) { int c = getchar(); return c == EOF ? -1 : c; }
int micro_eof(void) { int c = getchar(); if (c == EOF) return 1; ungetc(c, stdin); return 0; }
#endif

void micro_putc(int c) { putchar(c & 255); }

void micro_msg(const char *s) { fputs(s, stderr); }

static int zcstr(Cell *mem, Cell addr, char *dst, int max)
{
	int i = 0, c;
	if (max < 1) return -1;
	if ((UCell)addr >= (UCell)micro_mem_words()) { dst[0] = 0; return -1; }
	while (i < max - 1 && (UCell)(addr + i) < (UCell)micro_mem_words()) {
		c = (int)mem[addr + i];
		if (!c) break;
		dst[i++] = (char)c;
	}
	dst[i] = 0;
	return i;
}

static int inmem(Cell a) { return (UCell)a < (UCell)micro_mem_words(); }

/* the command line and the environment, kept for ops 21 to 24: the same
   contract as src/core/core.c. a program read from stdin has no file name, so
   argv[0] is <eval>. */
#ifndef _WIN32
extern char **environ;
#endif
static VM_TLS int zy_argc;
static VM_TLS char **zy_argv;
static VM_TLS int zy_envc;
static VM_TLS char **zy_envp;

static void zy_args(int argc, char **argv)
{
	char **e;
	int n = 0;
#ifdef _WIN32
	e = _environ;
#else
	e = environ;
#endif
	while (e && e[n]) n++;
	zy_envp = e; zy_envc = n;
	zy_argv = argv;
	zy_argc = argc > 0 ? argc : 1;
}

/* copy entry a of a char ** into vm words, one character per word, terminated
   like SYS_GETENV. a zero buffer asks for the length only. lead, when given,
   replaces entry zero. */
static Cell vecstr(Cell *mem, char **v, int count, Cell a, Cell b, Cell c, const char *lead)
{
	char *e;
	int i = 0;
	if (a < 0 || a >= (Cell)count) return -1;
	e = (a == 0 && lead) ? (char *)lead : v[a];
	if (!e) return -1;
	if (!b) { while (e[i]) i++; return i; }
	if (c < 1 || !inmem(b)) return -1;
	while (e[i] && i < c - 1 && inmem(b + i)) { mem[b + i] = (unsigned char)e[i]; i++; }
	if (inmem(b + i)) mem[b + i] = 0;
	return i;
}

static Cell host_rand(void)
{
	static VM_TLS uint64_t s;
	if (!s) s = (uint64_t)time(0) ^ 0x9E3779B97F4A7C15ull;
	if (!s) s = 0x9E3779B97F4A7C15ull;
	s ^= s << 13; s ^= s >> 7; s ^= s << 17;
	if ((Cell)s == -1) s ^= 0x100;
	return (Cell)s;
}

static int memory_words(const char *name, UCell fallback, UCell *words)
{
	const char *s = getenv(name);
	char *end;
	unsigned long long value;
	if (!s) { *words = fallback; return 1; }
	errno = 0;
	value = strtoull(s, &end, 10);
	if (errno || end == s || *end || !value || value > 0x7fffffffULL) return 0;
	*words = (UCell)value;
	return 1;
}

Cell micro_syscall(Cell *mem, Cell op, Cell a, Cell b, Cell c)
{
	char path[1024], tmp[512];
	int n, i, got;
	switch (op) {
	case 43: { /* clone an isolated execution context with a bidirectional channel */
#if !defined(_WIN32) && !defined(__wasm__)
		int fd[2]; pid_t child;
		if (!inmem(a) || socketpair(AF_UNIX, SOCK_STREAM, 0, fd) < 0) return -1;
		fflush(NULL); child = fork();
		if (child < 0) { close(fd[0]); close(fd[1]); return -1; }
		if (!child) { close(fd[0]); mem[a] = fd[1]; return 0; }
		close(fd[1]); mem[a] = fd[0]; return child;
#else
		return -1;
#endif
	}
	case 44: case 45: { /* write/read complete word buffers on a context channel */
#if !defined(_WIN32) && !defined(__wasm__)
		size_t done = 0, length; ssize_t got; unsigned char *buffer;
		if (b < 0 || c < 0 || c > (Cell)micro_mem_words() - b) return -1;
		buffer = (unsigned char *)(mem + b); length = (size_t)c * sizeof(Cell);
		while (done < length) {
			if (op == 44) {
#ifdef __APPLE__
				int enabled = 1; setsockopt((int)a, SOL_SOCKET, SO_NOSIGPIPE, &enabled, sizeof enabled);
				#ifdef MSG_NOSIGNAL
				got = send((int)a, buffer + done, length - done, MSG_NOSIGNAL);
#else
				got = send((int)a, buffer + done, length - done, 0);
#endif
#else
				got = send((int)a, buffer + done, length - done, MSG_NOSIGNAL);
#endif
			} else got = read((int)a, buffer + done, length - done);
			if (got < 0 && errno == EINTR) continue;
			if (got <= 0) return -1;
			done += (size_t)got;
		}
		return c;
#else
		return -1;
#endif
	}
	case 46: { /* channel readiness, with a millisecond timeout */
#if !defined(_WIN32) && !defined(__wasm__)
		struct pollfd fd; int ready; fd.fd = (int)a; fd.events = POLLIN; fd.revents = 0;
		do { ready = poll(&fd, 1, (int)b); } while (ready < 0 && errno == EINTR);
		return ready > 0 ? !!(fd.revents & (POLLIN | POLLHUP)) : ready;
#else
		return -1;
#endif
	}
	case 47: case 49: { /* join a child context, optionally terminating it first */
#if !defined(_WIN32) && !defined(__wasm__)
		int status; pid_t joined;
		if (a <= 0) return -1;
		if (op == 49) kill((pid_t)a, SIGTERM);
		do { joined = waitpid((pid_t)a, &status, 0); } while (joined < 0 && errno == EINTR);
		return joined < 0 ? -1 : WIFEXITED(status) ? WEXITSTATUS(status) : -1;
#else
		return -1;
#endif
	}
	case 50: { /* monotonic milliseconds for elapsed-time measurements */
#if !defined(_WIN32) && !defined(__wasm__)
		struct timespec now; if (clock_gettime(CLOCK_MONOTONIC, &now) < 0) return -1;
		return (Cell)now.tv_sec * 1000 + now.tv_nsec / 1000000;
#else
		return -1;
#endif
	}
	case 48: { /* sleep for a bounded millisecond duration */
#if !defined(_WIN32) && !defined(__wasm__)
		struct timespec duration;
		if (a < 0 || a > 86400000) return -1;
		duration.tv_sec = (time_t)(a / 1000); duration.tv_nsec = (long)(a % 1000) * 1000000;
		while (nanosleep(&duration, &duration) < 0) if (errno != EINTR) return -1;
		return 0;
#else
		return -1;
#endif
	}
	case 1:
		if (zcstr(mem, a, path, 1024) < 0) return -1;
		if (b == 1) return open(path, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
		return open(path, O_RDONLY | O_BINARY);
	case 2:
		return close((int)a);
	case 3:
		if (c < 0 || !inmem(b)) return -1;
		n = 0;
		while (n < c) {
			i = (int)(c - n);
			if (i > 512) i = 512;
			if (!inmem(b + n)) break;
			if (!inmem(b + n + i - 1)) i = (int)(micro_mem_words() - (b + n));
			if (i <= 0) break;
			got = (int)read((int)a, tmp, (size_t)i);
			if (got <= 0) break;
			for (i = 0; i < got; i++) mem[b + n + i] = (unsigned char)tmp[i];
			n += got;
		}
		return n;
	case 4:
		if (c < 0 || !inmem(b)) return -1;
		n = 0;
		while (n < c) {
			i = (int)(c - n);
			if (i > 512) i = 512;
			if (!inmem(b + n)) break;
			if (!inmem(b + n + i - 1)) i = (int)(micro_mem_words() - (b + n));
			if (i <= 0) break;
			for (got = 0; got < i; got++) tmp[got] = (char)mem[b + n + got];
			got = (int)write((int)a, tmp, (size_t)i);
			if (got <= 0) break;
			n += got;
		}
		return n;
	case 5: {
		char *e;
		if (zcstr(mem, a, path, 1024) < 0) return -1;
		e = getenv(path);
		if (!e) return -1;
		if (c < 1 || !inmem(b)) return -1;
		i = 0;
		while (e[i] && i < c - 1 && inmem(b + i)) { mem[b + i] = (unsigned char)e[i]; i++; }
		if (inmem(b + i)) mem[b + i] = 0;
		return i;
	}
	case 6:
		return (Cell)time(0);
	case 7:
		exit((int)a);
	case 8:
		return host_rand();
	case 9:
		if (a == 0) return micro_mem_words();
		if (a == 1) return HEAP_LO;
		if (a == 2) return HEAP_HI;
		if (a == 3) return (Cell)micro_mem_words() * 8;
		return -1;
	case 10:
		if (bop_cstr(mem, a, path, 1024, micro_mem_words()) < 0) return -1;
		if (b == 1) return open(path, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
		return open(path, O_RDONLY | O_BINARY);
	case 11:
		if (c < 0 || (c > 0 && !bop_ok(b, 1, micro_mem_words()))) return -1;
		n = 0;
		while (n < c) {
			i = (int)(c - n);
			if (i > 512) i = 512;
			i = bop_span(b + n, i, micro_mem_words());
			if (i <= 0) break;
			got = (int)read((int)a, tmp, (size_t)i);
			if (got <= 0) break;
			for (i = 0; i < got; i++) bop_put1(mem, b + n + i, (unsigned char)tmp[i]);
			n += got;
		}
		return n;
	case 12:
		if (c < 0 || (c > 0 && !bop_ok(b, 1, micro_mem_words()))) return -1;
		n = 0;
		while (n < c) {
			i = (int)(c - n);
			if (i > 512) i = 512;
			i = bop_span(b + n, i, micro_mem_words());
			if (i <= 0) break;
			for (got = 0; got < i; got++) tmp[got] = (char)bop_load(mem, b + n + got, 1);
			got = (int)write((int)a, tmp, (size_t)i);
			if (got <= 0) break;
			n += got;
		}
		return n;
	case 13: {
		char *e;
		if (bop_cstr(mem, a, path, 1024, micro_mem_words()) < 0) return -1;
		e = getenv(path);
		if (!e) return -1;
		if (c < 1 || !bop_ok(b, 1, micro_mem_words())) return -1;
		i = 0;
		while (e[i] && i < c - 1 && bop_ok(b + i, 1, micro_mem_words())) { bop_put1(mem, b + i, (unsigned char)e[i]); i++; }
		if (bop_ok(b + i, 1, micro_mem_words())) bop_put1(mem, b + i, 0);
		return i;
	}
	case 21:
		return (Cell)zy_argc;
	case 22:
		return vecstr(mem, zy_argv, zy_argc, a, b, c, "<eval>");
	case 23:
		return (Cell)zy_envc;
	case 24:
		return vecstr(mem, zy_envp, zy_envc, a, b, c, 0);
	default:
		return -1;
	}
}

int main(int argc, char **argv) {
	UCell initial, limit;
	if (argc > 1 && (!strcmp(argv[1], "--help") || !strcmp(argv[1], "-h"))) {
		fputs("usage: zym [program arguments] < input\n"
		      "runs the embedded image with the portable vm; compiler images read source from stdin.\n"
		      "input after a backtick is program input; run-only images read program input directly.\n"
		      "program arguments are available through std.argv; stdin has the name <eval>.\n"
		      "options:\n  --help, -h  show this help and exit\n"
		      "environment:\n"
		      "  TINYVM_MEMORY_WORDS      initial vm memory in words\n"
		      "  TINYVM_MAX_MEMORY_WORDS  maximum vm memory in words\n", stdout);
		return 0;
	}
	if (argc > 1 && argv[1][0] == '-' && argv[1][1] == '-' && strcmp(argv[1], "--explain-checks")) {	/* the compiler reads that one */
		fprintf(stderr, "micro: unknown option %s; use --help for usage\n", argv[1]);
		return 2;
	}
#ifdef _WIN32
	_setmode(_fileno(stdin), _O_BINARY);
	_setmode(_fileno(stdout), _O_BINARY);
#endif
	zy_args(argc, argv);
	if (!memory_words("TINYVM_MEMORY_WORDS", MICRO_MW_INIT, &initial) ||
	    !memory_words("TINYVM_MAX_MEMORY_WORDS", MICRO_MW_LIMIT, &limit) ||
	    initial > limit || !micro_memory_config(initial, limit)) {
		fputs("micro: invalid memory configuration\n", stderr);
		return 1;
	}
	return micro_run();
}

#ifdef ZY_THREADS
struct PortSnapshot {
 unsigned char bytes[65536];
 int position, count, ended, argc, envc;
 char **argv, **envp;
};
size_t micro_context_port_size(void) { return sizeof(struct PortSnapshot); }
void micro_context_port_save(void *destination) {
 struct PortSnapshot *snapshot = destination;
 memcpy(snapshot->bytes, input_bytes, sizeof input_bytes);
 snapshot->position = input_position; snapshot->count = input_count; snapshot->ended = input_ended;
 snapshot->argc = zy_argc; snapshot->argv = zy_argv; snapshot->envc = zy_envc; snapshot->envp = zy_envp;
}
void micro_context_port_restore(const void *source) {
 const struct PortSnapshot *snapshot = source;
 memcpy(input_bytes, snapshot->bytes, sizeof input_bytes);
 input_position = snapshot->position; input_count = snapshot->count; input_ended = snapshot->ended;
 zy_argc = snapshot->argc; zy_argv = snapshot->argv; zy_envc = snapshot->envc; zy_envp = snapshot->envp;
}
void micro_context_port_free(void) { free(lmem); lmem = 0; lcap = 0; }
#endif