// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

// +build darwin freebsd linux netbsd openbsd

// Fork, exec, wait, etc.

package syscall

import (
	"runtime"
	"sync"
	"unsafe"
)

// Lock synchronizing creation of new file descriptors with fork.
//
// We want the child in a fork/exec sequence to inherit only the
// file descriptors we intend.  To do that, we mark all file
// descriptors close-on-exec and then, in the child, explicitly
// unmark the ones we want the exec'ed program to keep.
// Unix doesn't make this easy: there is, in general, no way to
// allocate a new file descriptor close-on-exec.  Instead you
// have to allocate the descriptor and then mark it close-on-exec.
// If a fork happens between those two events, the child's exec
// will inherit an unwanted file descriptor.
//
// This lock solves that race: the create new fd/mark close-on-exec
// operation is done holding ForkLock for reading, and the fork itself
// is done holding ForkLock for writing.  At least, that's the idea.
// There are some complications.
//
// Some system calls that create new file descriptors can block
// for arbitrarily long times: open on a hung NFS server or named
// pipe, accept on a socket, and so on.  We can't reasonably grab
// the lock across those operations.
//
// It is worse to inherit some file descriptors than others.
// If a non-malicious child accidentally inherits an open ordinary file,
// that's not a big deal.  On the other hand, if a long-lived child
// accidentally inherits the write end of a pipe, then the reader
// of that pipe will not see EOF until that child exits, potentially
// causing the parent program to hang.  This is a common problem
// in threaded C programs that use popen.
//
// Luckily, the file descriptors that are most important not to
// inherit are not the ones that can take an arbitrarily long time
// to create: pipe returns instantly, and the net package uses
// non-blocking I/O to accept on a listening socket.
// The rules for which file descriptor-creating operations use the
// ForkLock are as follows:
//
// 1) Pipe.    Does not block.  Use the ForkLock.
// 2) Socket.  Does not block.  Use the ForkLock.
// 3) Accept.  If using non-blocking mode, use the ForkLock.
//             Otherwise, live with the race.
// 4) Open.    Can block.  Use O_CLOEXEC if available (Linux).
//             Otherwise, live with the race.
// 5) Dup.     Does not block.  Use the ForkLock.
//             On Linux, could use fcntl F_DUPFD_CLOEXEC
//             instead of the ForkLock, but only for dup(fd, -1).

var ForkLock sync.RWMutex

// Convert array of string to array
// of NUL-terminated byte pointer.
func StringSlicePtr(ss []string) []*byte {
	bb := make([]*byte, len(ss)+1)
	for i := 0; i < len(ss); i++ {
		bb[i] = StringBytePtr(ss[i])
	}
	bb[len(ss)] = nil
	return bb
}

func CloseOnExec(fd int) { fcntl(fd, F_SETFD, FD_CLOEXEC) }

func SetNonblock(fd int, nonblocking bool) (err error) {
	flag, err := fcntl(fd, F_GETFL, 0)
	if err != nil {
		return err
	}
	if nonblocking {
		flag |= O_NONBLOCK
	} else {
		flag &= ^O_NONBLOCK
	}
	_, err = fcntl(fd, F_SETFL, flag)
	return err
}

// Credential holds user and group identities to be assumed
// by a child process started by StartProcess.
type Credential struct {
	Uid    uint32   // User ID.
	Gid    uint32   // Group ID.
	Groups []uint32 // Supplementary group IDs.
}

// ProcAttr holds attributes that will be applied to a new process started
// by StartProcess.
type ProcAttr struct {
	Dir   string    // Current working directory.
	Env   []string  // Environment.
	Files []uintptr // File descriptors.
	Sys   *SysProcAttr
}

var zeroProcAttr ProcAttr
var zeroSysProcAttr SysProcAttr

func forkExec(argv0 string, argv []string, attr *ProcAttr) (pid int, err error) {
	var p [2]int
	var n int
	var err1 Errno
	var wstatus WaitStatus

	if attr == nil {
		attr = &zeroProcAttr
	}
	sys := attr.Sys
	if sys == nil {
		sys = &zeroSysProcAttr
	}

	p[0] = -1
	p[1] = -1

	// Convert args to C form.
	argv0p := StringBytePtr(argv0)
	argvp := StringSlicePtr(argv)
	envvp := StringSlicePtr(attr.Env)

	if runtime.GOOS == "freebsd" && len(argv[0]) > len(argv0) {
		argvp[0] = argv0p
	}

	var chroot *byte
	if sys.Chroot != "" {
		chroot = StringBytePtr(sys.Chroot)
	}
	var dir *byte
	if attr.Dir != "" {
		dir = StringBytePtr(attr.Dir)
	}

	// Acquire the fork lock so that no other threads
	// create new fds that are not yet close-on-exec
	// before we fork.
	ForkLock.Lock()

	// Allocate child status pipe close on exec.
	if err = Pipe(p[0:]); err != nil {
		goto error
	}
	if _, err = fcntl(p[0], F_SETFD, FD_CLOEXEC); err != nil {
		goto error
	}
	if _, err = fcntl(p[1], F_SETFD, FD_CLOEXEC); err != nil {
		goto error
	}

	// Kick off child.
	pid, err1 = forkAndExecInChild(argv0p, argvp, envvp, chroot, dir, attr, sys, p[1])
	if err1 != 0 {
		err = Errno(err1)
		goto error
	}
	ForkLock.Unlock()

	// Read child error status from pipe.
	Close(p[1])
	n, err = read(p[0], (*byte)(unsafe.Pointer(&err1)), int(unsafe.Sizeof(err1)))
	Close(p[0])
	if err != nil || n != 0 {
		if n == int(unsafe.Sizeof(err1)) {
			err = Errno(err1)
		}
		if err == nil {
			err = EPIPE
		}

		// Child failed; wait for it to exit, to make sure
		// the zombies don't accumulate.
		_, err1 := Wait4(pid, &wstatus, 0, nil)
		for err1 == EINTR {
			_, err1 = Wait4(pid, &wstatus, 0, nil)
		}
		return 0, err
	}

	// Read got EOF, so pipe closed on exec, so exec succeeded.
	return pid, nil

error:
	if p[0] >= 0 {
		Close(p[0])
		Close(p[1])
	}
	ForkLock.Unlock()
	return 0, err
}

// Combination of fork and exec, careful to be thread safe.
func ForkExec(argv0 string, argv []string, attr *ProcAttr) (pid int, err error) {
	return forkExec(argv0, argv, attr)
}

// StartProcess wraps ForkExec for package os.
func StartProcess(argv0 string, argv []string, attr *ProcAttr) (pid int, handle uintptr, err error) {
	pid, err = forkExec(argv0, argv, attr)
	return pid, 0, err
}

// Ordinary exec.
func Exec(argv0 string, argv []string, envv []string) (err error) {
	_, _, err1 := RawSyscall(SYS_EXECVE,
		uintptr(unsafe.Pointer(StringBytePtr(argv0))),
		uintptr(unsafe.Pointer(&StringSlicePtr(argv)[0])),
		uintptr(unsafe.Pointer(&StringSlicePtr(envv)[0])))
	return Errno(err1)
}