Kernel+LibC: Implement the openat() syscall

POSIX's openat() is very similar to open(), except you also provide a
file descriptor referring to a directory from which relative paths
should be resolved.

Passing it the magical fd number AT_FDCWD means "resolve from current
directory" (which is indeed also what open() normally does.)

This fixes libarchive's bsdtar, since it was trying to do something
extremely wrong in the absence of openat() support. The issue has
recently been fixed upstream in libarchive:

libarchive/libarchive#1239

However, we should have openat() support anyway, so I went ahead and
implemented it. :^)

Fixes SerenityOS#748.

Kernel/Process.cpp

@@ -1351,19 +1351,56 @@ int Process::sys$open(const Syscall::SC_open_params* params)
 {
  if (!validate_read_typed(params))
  return -EFAULT;
- auto* path = params->path;
- auto path_length = params->path_length;
- auto options = params->options;
- auto mode = params->mode;
+ auto [path, path_length, options, mode] = *params;
+ if (!validate_read(path, path_length))
+ return -EFAULT;
 #ifdef DEBUG_IO
  dbgprintf("%s(%u) sys$open(\"%s\")\n", name().characters(), pid(), path);
 #endif
+ int fd = alloc_fd();
+ if (fd < 0)
+ return fd;
+ auto result = VFS::the().open(path, options, mode & ~umask(), current_directory());
+ if (result.is_error())
+ return result.error();
+ auto description = result.value();
+ if (options & O_DIRECTORY && !description->is_directory())
+ return -ENOTDIR; // FIXME: This should be handled by VFS::open.
+ description->set_file_flags(options);
+ u32 fd_flags = (options & O_CLOEXEC) ? FD_CLOEXEC : 0;
+ m_fds[fd].set(move(description), fd_flags);
+ return fd;
+}
+
+int Process::sys$openat(const Syscall::SC_openat_params* params)
+{
+ if (!validate_read_typed(params))
+ return -EFAULT;
+ auto [dirfd, path, path_length, options, mode] = *params;
  if (!validate_read(path, path_length))
  return -EFAULT;
+#ifdef DEBUG_IO
+ dbgprintf("%s(%u) sys$openat(%d, \"%s\")\n", dirfd, name().characters(), pid(), path);
+#endif
  int fd = alloc_fd();
  if (fd < 0)
  return fd;
- auto result = VFS::the().open(path, options, mode & ~umask(), current_directory());
+
+ RefPtr<Custody> base;
+ if (dirfd == AT_FDCWD) {
+ base = current_directory();
+ } else {
+ auto* base_description = file_description(dirfd);
+ if (!base_description)
+ return -EBADF;
+ if (!base_description->is_directory())
+ return -ENOTDIR;
+ if (!base_description->custody())
+ return -EINVAL;
+ base = base_description->custody();
+ }
+
+ auto result = VFS::the().open(path, options, mode & ~umask(), *base);
  if (result.is_error())
  return result.error();
  auto description = result.value();

Kernel/Process.h

@@ -124,6 +124,7 @@ class Process : public InlineLinkedListNode<Process>
  pid_t sys$getppid();
  mode_t sys$umask(mode_t);
  int sys$open(const Syscall::SC_open_params*);
+ int sys$openat(const Syscall::SC_openat_params*);
  int sys$close(int fd);
  ssize_t sys$read(int fd, u8*, ssize_t);
  ssize_t sys$write(int fd, const u8*, ssize_t);

Kernel/Syscall.h

@@ -134,7 +134,8 @@ struct timespec;
  __ENUMERATE_SYSCALL(fchdir) \
  __ENUMERATE_SYSCALL(getrandom) \
  __ENUMERATE_SYSCALL(clock_gettime) \
- __ENUMERATE_SYSCALL(clock_nanosleep)
+ __ENUMERATE_SYSCALL(clock_nanosleep) \
+ __ENUMERATE_SYSCALL(openat)
 
 namespace Syscall {
 
@@ -179,6 +180,14 @@ struct SC_open_params {
  u16 mode;
 };
 
+struct SC_openat_params {
+ int dirfd;
+ const char* path;
+ int path_length;
+ int options;
+ u16 mode;
+};
+
 struct SC_select_params {
  int nfds;
  fd_set* readfds;

Kernel/UnixTypes.h

@@ -448,3 +448,6 @@ struct ifreq {
 #define ifr_llprio ifr_ifru.ifru_metric // link layer priority
 #define ifr_hwaddr ifr_ifru.ifru_hwaddr // MAC address
 };
+
+#define AT_FDCWD -100
+

Libraries/LibC/unistd.cpp

@@ -189,6 +189,17 @@ int open_with_path_length(const char* path, size_t path_length, int options, mod
  __RETURN_WITH_ERRNO(rc, rc, -1);
 }
 
+int openat_with_path_length(int dirfd, const char* path, size_t path_length, int options, mode_t mode)
+{
+ if (path_length > INT32_MAX) {
+ errno = EINVAL;
+ return -1;
+ }
+ Syscall::SC_openat_params params { dirfd, path, (int)path_length, options, mode };
+ int rc = syscall(SC_openat, &params);
+ __RETURN_WITH_ERRNO(rc, rc, -1);
+}
+
 int open(const char* path, int options, ...)
 {
  va_list ap;
@@ -198,6 +209,15 @@ int open(const char* path, int options, ...)
  return open_with_path_length(path, strlen(path), options, mode);
 }
 
+int openat(int dirfd, const char* path, int options, ...)
+{
+ va_list ap;
+ va_start(ap, options);
+ auto mode = (mode_t)va_arg(ap, unsigned);
+ va_end(ap);
+ return openat_with_path_length(dirfd, path, strlen(path), options, mode);
+}
+
 ssize_t read(int fd, void* buf, size_t count)
 {
  int rc = syscall(SC_read, fd, buf, count);

Libraries/LibC/unistd.h

@@ -77,6 +77,9 @@ int creat(const char* path, mode_t);
 int open(const char* path, int options, ...);
 int creat_with_path_length(const char* path, size_t path_length, mode_t);
 int open_with_path_length(const char* path, size_t path_length, int options, mode_t);
+#define AT_FDCWD -100
+int openat(int dirfd, const char* path, int options, ...);
+int openat_with_path_length(int dirfd, const char* path, size_t path_length, int options, mode_t);
 ssize_t read(int fd, void* buf, size_t count);
 ssize_t write(int fd, const void* buf, size_t count);
 int close(int fd);