[PATCH] fcntl: Add 32bit filesystem mode

[Linus Walleij]

It was brought to my attention that this bug from 2018 was
still unresolved: 32 bit emulators like QEMU were given
64 bit hashes when running 32 bit emulation on 64 bit systems.

This adds a fcntl() operation to set the underlying filesystem
into 32bit mode even if the file hanle was opened using 64bit
mode without the compat syscalls.

Programs that need the 32 bit file system behavior need to
issue a fcntl() system call such as in this example:

  #define F_SET_FILE_32BIT_FS (1024 + 15)

  int main(int argc, char** argv) {
    DIR* dir;
    int err;
    int fd;

    dir = opendir("/boot");
    fd = dirfd(dir);
    err = fcntl(fd, F_SET_FILE_32BIT_FS);
    if (err) {
      printf("fcntl() failed! err=%d\n", err);
      return 1;
    }
    printf("dir=%p\n", dir);
    printf("readdir(dir)=%p\n", readdir(dir));
    printf("errno=%d: %s\n", errno, strerror(errno));
    return 0;
  }

This can be pretty hard to test since C libraries and linux
userspace security extensions aggressively filter the parameters
that are passed down and allowed to commit into actual system
calls.

Cc: Florian Weimer <address@hidden>
Cc: Peter Maydell <address@hidden>
Cc: Andy Lutomirski <address@hidden>
Suggested-by: Theodore Ts'o <address@hidden>
Link: https://bugs.launchpad.net/qemu/+bug/1805913
Link: https://lore.kernel.org/lkml/address@hidden/
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=205957
Signed-off-by: Linus Walleij <address@hidden>
---
 fs/fcntl.c                       | 4 ++++
 include/uapi/linux/fcntl.h       | 9 +++++++++
 tools/include/uapi/linux/fcntl.h | 9 +++++++++
 tools/perf/trace/beauty/fcntl.c  | 3 ++-
 4 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/fs/fcntl.c b/fs/fcntl.c
index 2e4c0fa2074b..d194b1265bd4 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -426,6 +426,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned 
long arg,
        case F_SET_FILE_RW_HINT:
                err = fcntl_rw_hint(filp, cmd, arg);
                break;
+       case F_SET_FILE_32BIT_FS:
+               filp->f_mode |= FMODE_32BITHASH;
+               err = 0;
+               break;
        default:
                break;
        }
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index ca88b7bce553..b9ad934147e8 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -73,6 +73,15 @@
  */
 #define RWF_WRITE_LIFE_NOT_SET RWH_WRITE_LIFE_NOT_SET
 
+/*
+ * This instructs the kernel to provide 32bit semantics (such as hashes) from
+ * the file system layer, when running a userland that depend on 32bit
+ * semantics on a kernel that supports 64bit userland, but does not use the
+ * compat ioctl() for e.g. open(), so that the kernel would otherwise assume
+ * that the userland process is capable of dealing with 64bit semantics.
+ */
+#define F_SET_FILE_32BIT_FS    (F_LINUX_SPECIFIC_BASE + 15)
+
 /*
  * Types of directory notifications that may be requested.
  */
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index ca88b7bce553..b9ad934147e8 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -73,6 +73,15 @@
  */
 #define RWF_WRITE_LIFE_NOT_SET RWH_WRITE_LIFE_NOT_SET
 
+/*
+ * This instructs the kernel to provide 32bit semantics (such as hashes) from
+ * the file system layer, when running a userland that depend on 32bit
+ * semantics on a kernel that supports 64bit userland, but does not use the
+ * compat ioctl() for e.g. open(), so that the kernel would otherwise assume
+ * that the userland process is capable of dealing with 64bit semantics.
+ */
+#define F_SET_FILE_32BIT_FS    (F_LINUX_SPECIFIC_BASE + 15)
+
 /*
  * Types of directory notifications that may be requested.
  */
diff --git a/tools/perf/trace/beauty/fcntl.c b/tools/perf/trace/beauty/fcntl.c
index 56ef83b3d130..da80264678cb 100644
--- a/tools/perf/trace/beauty/fcntl.c
+++ b/tools/perf/trace/beauty/fcntl.c
@@ -94,7 +94,8 @@ size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t 
size, struct syscall_ar
            cmd == F_OFD_SETLK || cmd == F_OFD_SETLKW || cmd == F_OFD_GETLK ||
            cmd == F_GETOWN_EX || cmd == F_SETOWN_EX ||
            cmd == F_GET_RW_HINT || cmd == F_SET_RW_HINT ||
-           cmd == F_GET_FILE_RW_HINT || cmd == F_SET_FILE_RW_HINT)
+           cmd == F_GET_FILE_RW_HINT || cmd == F_SET_FILE_RW_HINT ||
+           cmd == F_SET_FILE_32BIT_FS)
                return syscall_arg__scnprintf_hex(bf, size, arg);
 
        return syscall_arg__scnprintf_long(bf, size, arg);
-- 
2.25.1