On 2020-04-07, Josh Triplett wrote: > Some applications want to prevent the usual "lowest available fd" > allocation from allocating certain file descriptors. For instance, they > may want to prevent allocation of a closed fd 0, 1, or 2 other than via > dup2/dup3, or reserve some low file descriptors for other purposes. > > Add a prctl to increase the minimum fd and return the previous minimum. > > System calls that allocate a specific file descriptor, such as > dup2/dup3, ignore this minimum. > > exec resets the minimum fd, to prevent one program from interfering with > another program's expectations about fd allocation. Why is it implemented as an "increase the value" interface? It feels like this is meant to avoid some kind of security trap (with a library reducing the value) but it means that if you want to temporarily raise the minimum fd number it's not possible (without re-exec()ing yourself, which is hardly a fun thing to do). Then again, this might've been discussed before and I missed it... > Test program: > > #include > #include > #include > #include > > int main(int argc, char *argv[]) > { > if (prctl(PR_INCREASE_MIN_FD, 100, 0, 0, 0) < 0) > err(1, "prctl"); > int fd = open("/dev/null", O_RDONLY); > if (fd < 0) > err(1, "open"); > printf("%d\n", fd); // prints 100 > return 0; > } > > Signed-off-by: Josh Triplett > --- > fs/file.c | 23 +++++++++++++++++------ > include/linux/fdtable.h | 1 + > include/linux/file.h | 1 + > include/uapi/linux/prctl.h | 3 +++ > kernel/sys.c | 5 +++++ > 5 files changed, 27 insertions(+), 6 deletions(-) > > diff --git a/fs/file.c b/fs/file.c > index c8a4e4c86e55..ba06140d89af 100644 > --- a/fs/file.c > +++ b/fs/file.c > @@ -286,7 +286,6 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) > spin_lock_init(&newf->file_lock); > newf->resize_in_progress = false; > init_waitqueue_head(&newf->resize_wait); > - newf->next_fd = 0; > new_fdt = &newf->fdtab; > new_fdt->max_fds = NR_OPEN_DEFAULT; > new_fdt->close_on_exec = newf->close_on_exec_init; > @@ -295,6 +294,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) > new_fdt->fd = &newf->fd_array[0]; > > spin_lock(&oldf->file_lock); > + newf->next_fd = newf->min_fd = oldf->min_fd; > old_fdt = files_fdtable(oldf); > open_files = count_open_files(old_fdt); > > @@ -487,9 +487,7 @@ int __alloc_fd(struct files_struct *files, > spin_lock(&files->file_lock); > repeat: > fdt = files_fdtable(files); > - fd = start; > - if (fd < files->next_fd) > - fd = files->next_fd; > + fd = max3(start, files->min_fd, files->next_fd); > > if (fd < fdt->max_fds) > fd = find_next_fd(fdt, fd); > @@ -514,7 +512,7 @@ int __alloc_fd(struct files_struct *files, > goto repeat; > > if (start <= files->next_fd) > - files->next_fd = fd + 1; > + files->next_fd = max(fd + 1, files->min_fd); > > __set_open_fd(fd, fdt); > if (flags & O_CLOEXEC) > @@ -555,7 +553,7 @@ static void __put_unused_fd(struct files_struct *files, unsigned int fd) > { > struct fdtable *fdt = files_fdtable(files); > __clear_open_fd(fd, fdt); > - if (fd < files->next_fd) > + if (fd < files->next_fd && fd >= files->min_fd) > files->next_fd = fd; > } > > @@ -684,6 +682,7 @@ void do_close_on_exec(struct files_struct *files) > > /* exec unshares first */ > spin_lock(&files->file_lock); > + files->min_fd = 0; > for (i = 0; ; i++) { > unsigned long set; > unsigned fd = i * BITS_PER_LONG; > @@ -865,6 +864,18 @@ bool get_close_on_exec(unsigned int fd) > return res; > } > > +unsigned int increase_min_fd(unsigned int num) > +{ > + struct files_struct *files = current->files; > + unsigned int old_min_fd; > + > + spin_lock(&files->file_lock); > + old_min_fd = files->min_fd; > + files->min_fd += num; > + spin_unlock(&files->file_lock); > + return old_min_fd; > +} > + > static int do_dup2(struct files_struct *files, > struct file *file, unsigned fd, unsigned flags) > __releases(&files->file_lock) > diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h > index f07c55ea0c22..d1980443d8b3 100644 > --- a/include/linux/fdtable.h > +++ b/include/linux/fdtable.h > @@ -60,6 +60,7 @@ struct files_struct { > */ > spinlock_t file_lock ____cacheline_aligned_in_smp; > unsigned int next_fd; > + unsigned int min_fd; /* min for "lowest available fd" allocation */ > unsigned long close_on_exec_init[1]; > unsigned long open_fds_init[1]; > unsigned long full_fds_bits_init[1]; > diff --git a/include/linux/file.h b/include/linux/file.h > index 142d102f285e..b67986f818d2 100644 > --- a/include/linux/file.h > +++ b/include/linux/file.h > @@ -88,6 +88,7 @@ extern bool get_close_on_exec(unsigned int fd); > extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); > extern int get_unused_fd_flags(unsigned flags); > extern void put_unused_fd(unsigned int fd); > +extern unsigned int increase_min_fd(unsigned int num); > > extern void fd_install(unsigned int fd, struct file *file); > > diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h > index 07b4f8131e36..916327272d21 100644 > --- a/include/uapi/linux/prctl.h > +++ b/include/uapi/linux/prctl.h > @@ -238,4 +238,7 @@ struct prctl_mm_map { > #define PR_SET_IO_FLUSHER 57 > #define PR_GET_IO_FLUSHER 58 > > +/* Increase minimum file descriptor for "lowest available fd" allocation */ > +#define PR_INCREASE_MIN_FD 59 > + > #endif /* _LINUX_PRCTL_H */ > diff --git a/kernel/sys.c b/kernel/sys.c > index d325f3ab624a..daa0ce43cecc 100644 > --- a/kernel/sys.c > +++ b/kernel/sys.c > @@ -2514,6 +2514,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, > > error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER; > break; > + case PR_INCREASE_MIN_FD: > + if (arg3 || arg4 || arg5) > + return -EINVAL; > + error = increase_min_fd((unsigned int)arg2); > + break; > default: > error = -EINVAL; > break; > -- > 2.26.0 > -- Aleksa Sarai Senior Software Engineer (Containers) SUSE Linux GmbH