summaryrefslogtreecommitdiff
path: root/fs/file.c
diff options
context:
space:
mode:
authorChristian Brauner <christian.brauner@ubuntu.com>2019-05-24 12:30:34 +0300
committerChristian Brauner <christian.brauner@ubuntu.com>2020-06-17 01:05:19 +0300
commit278a5fbaed89dacd04e9d052f4594ffd0e0585de (patch)
tree1a3b571782988d933eb66b109f1b0d662b495bdf /fs/file.c
parentb3a9e3b9622ae10064826dccb4f7a52bd88c7407 (diff)
downloadlinux-278a5fbaed89dacd04e9d052f4594ffd0e0585de.tar.xz
open: add close_range()
This adds the close_range() syscall. It allows to efficiently close a range of file descriptors up to all file descriptors of a calling task. I was contacted by FreeBSD as they wanted to have the same close_range() syscall as we proposed here. We've coordinated this and in the meantime, Kyle was fast enough to merge close_range() into FreeBSD already in April: https://reviews.freebsd.org/D21627 https://svnweb.freebsd.org/base?view=revision&revision=359836 and the current plan is to backport close_range() to FreeBSD 12.2 (cf. [2]) once its merged in Linux too. Python is in the process of switching to close_range() on FreeBSD and they are waiting on us to merge this to switch on Linux as well: https://bugs.python.org/issue38061 The syscall came up in a recent discussion around the new mount API and making new file descriptor types cloexec by default. During this discussion, Al suggested the close_range() syscall (cf. [1]). Note, a syscall in this manner has been requested by various people over time. First, it helps to close all file descriptors of an exec()ing task. This can be done safely via (quoting Al's example from [1] verbatim): /* that exec is sensitive */ unshare(CLONE_FILES); /* we don't want anything past stderr here */ close_range(3, ~0U); execve(....); The code snippet above is one way of working around the problem that file descriptors are not cloexec by default. This is aggravated by the fact that we can't just switch them over without massively regressing userspace. For a whole class of programs having an in-kernel method of closing all file descriptors is very helpful (e.g. demons, service managers, programming language standard libraries, container managers etc.). (Please note, unshare(CLONE_FILES) should only be needed if the calling task is multi-threaded and shares the file descriptor table with another thread in which case two threads could race with one thread allocating file descriptors and the other one closing them via close_range(). For the general case close_range() before the execve() is sufficient.) Second, it allows userspace to avoid implementing closing all file descriptors by parsing through /proc/<pid>/fd/* and calling close() on each file descriptor. From looking at various large(ish) userspace code bases this or similar patterns are very common in: - service managers (cf. [4]) - libcs (cf. [6]) - container runtimes (cf. [5]) - programming language runtimes/standard libraries - Python (cf. [2]) - Rust (cf. [7], [8]) As Dmitry pointed out there's even a long-standing glibc bug about missing kernel support for this task (cf. [3]). In addition, the syscall will also work for tasks that do not have procfs mounted and on kernels that do not have procfs support compiled in. In such situations the only way to make sure that all file descriptors are closed is to call close() on each file descriptor up to UINT_MAX or RLIMIT_NOFILE, OPEN_MAX trickery (cf. comment [8] on Rust). The performance is striking. For good measure, comparing the following simple close_all_fds() userspace implementation that is essentially just glibc's version in [6]: static int close_all_fds(void) { int dir_fd; DIR *dir; struct dirent *direntp; dir = opendir("/proc/self/fd"); if (!dir) return -1; dir_fd = dirfd(dir); while ((direntp = readdir(dir))) { int fd; if (strcmp(direntp->d_name, ".") == 0) continue; if (strcmp(direntp->d_name, "..") == 0) continue; fd = atoi(direntp->d_name); if (fd == dir_fd || fd == 0 || fd == 1 || fd == 2) continue; close(fd); } closedir(dir); return 0; } to close_range() yields: 1. closing 4 open files: - close_all_fds(): ~280 us - close_range(): ~24 us 2. closing 1000 open files: - close_all_fds(): ~5000 us - close_range(): ~800 us close_range() is designed to allow for some flexibility. Specifically, it does not simply always close all open file descriptors of a task. Instead, callers can specify an upper bound. This is e.g. useful for scenarios where specific file descriptors are created with well-known numbers that are supposed to be excluded from getting closed. For extra paranoia close_range() comes with a flags argument. This can e.g. be used to implement extension. Once can imagine userspace wanting to stop at the first error instead of ignoring errors under certain circumstances. There might be other valid ideas in the future. In any case, a flag argument doesn't hurt and keeps us on the safe side. From an implementation side this is kept rather dumb. It saw some input from David and Jann but all nonsense is obviously my own! - Errors to close file descriptors are currently ignored. (Could be changed by setting a flag in the future if needed.) - __close_range() is a rather simplistic wrapper around __close_fd(). My reasoning behind this is based on the nature of how __close_fd() needs to release an fd. But maybe I misunderstood specifics: We take the files_lock and rcu-dereference the fdtable of the calling task, we find the entry in the fdtable, get the file and need to release files_lock before calling filp_close(). In the meantime the fdtable might have been altered so we can't just retake the spinlock and keep the old rcu-reference of the fdtable around. Instead we need to grab a fresh reference to the fdtable. If my reasoning is correct then there's really no point in fancyfying __close_range(): We just need to rcu-dereference the fdtable of the calling task once to cap the max_fd value correctly and then go on calling __close_fd() in a loop. /* References */ [1]: https://lore.kernel.org/lkml/20190516165021.GD17978@ZenIV.linux.org.uk/ [2]: https://github.com/python/cpython/blob/9e4f2f3a6b8ee995c365e86d976937c141d867f8/Modules/_posixsubprocess.c#L220 [3]: https://sourceware.org/bugzilla/show_bug.cgi?id=10353#c7 [4]: https://github.com/systemd/systemd/blob/5238e9575906297608ff802a27e2ff9effa3b338/src/basic/fd-util.c#L217 [5]: https://github.com/lxc/lxc/blob/ddf4b77e11a4d08f09b7b9cd13e593f8c047edc5/src/lxc/start.c#L236 [6]: https://sourceware.org/git/?p=glibc.git;a=blob;f=sysdeps/unix/sysv/linux/grantpt.c;h=2030e07fa6e652aac32c775b8c6e005844c3c4eb;hb=HEAD#l17 Note that this is an internal implementation that is not exported. Currently, libc seems to not provide an exported version of this because of missing kernel support to do this. Note, in a recent patch series Florian made grantpt() a nop thereby removing the code referenced here. [7]: https://github.com/rust-lang/rust/issues/12148 [8]: https://github.com/rust-lang/rust/blob/5f47c0613ed4eb46fca3633c1297364c09e5e451/src/libstd/sys/unix/process2.rs#L303-L308 Rust's solution is slightly different but is equally unperformant. Rust calls getdtablesize() which is a glibc library function that simply returns the current RLIMIT_NOFILE or OPEN_MAX values. Rust then goes on to call close() on each fd. That's obviously overkill for most tasks. Rarely, tasks - especially non-demons - hit RLIMIT_NOFILE or OPEN_MAX. Let's be nice and assume an unprivileged user with RLIMIT_NOFILE set to 1024. Even in this case, there's a very high chance that in the common case Rust is calling the close() syscall 1021 times pointlessly if the task just has 0, 1, and 2 open. Suggested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Kyle Evans <self@kyle-evans.net> Cc: Jann Horn <jannh@google.com> Cc: David Howells <dhowells@redhat.com> Cc: Dmitry V. Levin <ldv@altlinux.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Florian Weimer <fweimer@redhat.com> Cc: linux-api@vger.kernel.org
Diffstat (limited to 'fs/file.c')
-rw-r--r--fs/file.c64
1 files changed, 56 insertions, 8 deletions
diff --git a/fs/file.c b/fs/file.c
index abb8b7081d7a..1b8ff05e8311 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -10,6 +10,7 @@
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/fs.h>
+#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/slab.h>
@@ -620,12 +621,9 @@ void fd_install(unsigned int fd, struct file *file)
EXPORT_SYMBOL(fd_install);
-/*
- * The same warnings as for __alloc_fd()/__fd_install() apply here...
- */
-int __close_fd(struct files_struct *files, unsigned fd)
+static struct file *pick_file(struct files_struct *files, unsigned fd)
{
- struct file *file;
+ struct file *file = NULL;
struct fdtable *fdt;
spin_lock(&files->file_lock);
@@ -637,15 +635,65 @@ int __close_fd(struct files_struct *files, unsigned fd)
goto out_unlock;
rcu_assign_pointer(fdt->fd[fd], NULL);
__put_unused_fd(files, fd);
- spin_unlock(&files->file_lock);
- return filp_close(file, files);
out_unlock:
spin_unlock(&files->file_lock);
- return -EBADF;
+ return file;
+}
+
+/*
+ * The same warnings as for __alloc_fd()/__fd_install() apply here...
+ */
+int __close_fd(struct files_struct *files, unsigned fd)
+{
+ struct file *file;
+
+ file = pick_file(files, fd);
+ if (!file)
+ return -EBADF;
+
+ return filp_close(file, files);
}
EXPORT_SYMBOL(__close_fd); /* for ksys_close() */
+/**
+ * __close_range() - Close all file descriptors in a given range.
+ *
+ * @fd: starting file descriptor to close
+ * @max_fd: last file descriptor to close
+ *
+ * This closes a range of file descriptors. All file descriptors
+ * from @fd up to and including @max_fd are closed.
+ */
+int __close_range(struct files_struct *files, unsigned fd, unsigned max_fd)
+{
+ unsigned int cur_max;
+
+ if (fd > max_fd)
+ return -EINVAL;
+
+ rcu_read_lock();
+ cur_max = files_fdtable(files)->max_fds;
+ rcu_read_unlock();
+
+ /* cap to last valid index into fdtable */
+ cur_max--;
+
+ max_fd = min(max_fd, cur_max);
+ while (fd <= max_fd) {
+ struct file *file;
+
+ file = pick_file(files, fd++);
+ if (!file)
+ continue;
+
+ filp_close(file, files);
+ cond_resched();
+ }
+
+ return 0;
+}
+
/*
* variant of __close_fd that gets a ref on the file for later fput.
* The caller must ensure that filp_close() called on the file, and then