Merge tag 'close-range-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux
Pull close_range() implementation from Christian Brauner:
"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.
This is coordinated with the FreeBSD folks which have copied our
version of this syscall and in the meantime have already merged it in
April 2019:
https://reviews.freebsd.org/D21627
https://svnweb.freebsd.org/base?view=revision&revision=359836
The syscall originally came up in a discussion around the new mount
API and making new file descriptor types cloexec by default. During
this discussion, Al suggested the close_range() syscall.
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.).
Second, it allows userspace to avoid implementing closing all file
descriptors by parsing through /proc/<pid>/fd/* and calling close() on
each file descriptor and other hacks. From looking at various
large(ish) userspace code bases this or similar patterns are very
common in service managers, container runtimes, and programming
language runtimes/standard libraries such as Python or Rust.
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.
Based on Linus' suggestion close_range() also comes with a new flag
CLOSE_RANGE_UNSHARE to more elegantly handle file descriptor dropping
right before exec. This would usually be expressed in the sequence:
unshare(CLONE_FILES);
close_range(3, ~0U);
as pointed out by Linus it might be desirable to have this be a part
of close_range() itself under a new flag CLOSE_RANGE_UNSHARE which
gets especially handy when we're closing all file descriptors above a
certain threshold.
Test-suite as always included"
* tag 'close-range-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
tests: add CLOSE_RANGE_UNSHARE tests
close_range: add CLOSE_RANGE_UNSHARE
tests: add close_range() tests
arch: wire-up close_range()
open: add close_range()
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 5ddd128..a28fb21 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -475,6 +475,7 @@
543 common fspick sys_fspick
544 common pidfd_open sys_pidfd_open
# 545 reserved for clone3
+546 common close_range sys_close_range
547 common openat2 sys_openat2
548 common pidfd_getfd sys_pidfd_getfd
549 common faccessat2 sys_faccessat2
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index d5cae5f..7e8ee4ad 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -449,6 +449,7 @@
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
435 common clone3 sys_clone3
+436 common close_range sys_close_range
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 6d95d0c..c760b9e 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -879,6 +879,8 @@
__SYSCALL(__NR_pidfd_open, sys_pidfd_open)
#define __NR_clone3 435
__SYSCALL(__NR_clone3, sys_clone3)
+#define __NR_close_range 436
+__SYSCALL(__NR_close_range, sys_close_range)
#define __NR_openat2 437
__SYSCALL(__NR_openat2, sys_openat2)
#define __NR_pidfd_getfd 438
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 49e325b..ced9c83e 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -356,6 +356,7 @@
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
# 435 reserved for clone3
+436 common close_range sys_close_range
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index f71b1bb..1a4822d 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -435,6 +435,7 @@
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
435 common clone3 __sys_clone3
+436 common close_range sys_close_range
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index edacc45..a3f4be8 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -441,6 +441,7 @@
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
435 common clone3 sys_clone3
+436 common close_range sys_close_range
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index f777141..501bc09 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -374,6 +374,7 @@
433 n32 fspick sys_fspick
434 n32 pidfd_open sys_pidfd_open
435 n32 clone3 __sys_clone3
+436 n32 close_range sys_close_range
437 n32 openat2 sys_openat2
438 n32 pidfd_getfd sys_pidfd_getfd
439 n32 faccessat2 sys_faccessat2
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index da8c763..391acbf 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -350,6 +350,7 @@
433 n64 fspick sys_fspick
434 n64 pidfd_open sys_pidfd_open
435 n64 clone3 __sys_clone3
+436 n64 close_range sys_close_range
437 n64 openat2 sys_openat2
438 n64 pidfd_getfd sys_pidfd_getfd
439 n64 faccessat2 sys_faccessat2
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 1328062..d28f12f 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -423,6 +423,7 @@
433 o32 fspick sys_fspick
434 o32 pidfd_open sys_pidfd_open
435 o32 clone3 __sys_clone3
+436 o32 close_range sys_close_range
437 o32 openat2 sys_openat2
438 o32 pidfd_getfd sys_pidfd_getfd
439 o32 faccessat2 sys_faccessat2
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 5a758fa..5d76b8f 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -433,6 +433,7 @@
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
435 common clone3 sys_clone3_wrapper
+436 common close_range sys_close_range
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index f833a31..dd87a78 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -525,6 +525,7 @@
435 32 clone3 ppc_clone3 sys_clone3
435 64 clone3 sys_clone3
435 spu clone3 sys_ni_syscall
+436 common close_range sys_close_range
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index bfdcb76..effb519 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -438,6 +438,7 @@
433 common fspick sys_fspick sys_fspick
434 common pidfd_open sys_pidfd_open sys_pidfd_open
435 common clone3 sys_clone3 sys_clone3
+436 common close_range sys_close_range sys_close_range
437 common openat2 sys_openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2 sys_faccessat2
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index acc35da..96848db 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -438,6 +438,7 @@
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
# 435 reserved for clone3
+436 common close_range sys_close_range
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 8004a27..d6447d0 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -481,6 +481,7 @@
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
# 435 reserved for clone3
+436 common close_range sys_close_range
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index d8f8a1a..3f0c654 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -440,6 +440,7 @@
433 i386 fspick sys_fspick
434 i386 pidfd_open sys_pidfd_open
435 i386 clone3 sys_clone3
+436 i386 close_range sys_close_range
437 i386 openat2 sys_openat2
438 i386 pidfd_getfd sys_pidfd_getfd
439 i386 faccessat2 sys_faccessat2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 78847b3..f8637c2 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -357,6 +357,7 @@
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
435 common clone3 sys_clone3
+436 common close_range sys_close_range
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 69d0d73..d216ccb 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -406,6 +406,7 @@
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
435 common clone3 sys_clone3
+436 common close_range sys_close_range
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
diff --git a/fs/file.c b/fs/file.c
index 4fb1117..4cb9ef4 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>
@@ -18,6 +19,7 @@
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/rcupdate.h>
+#include <linux/close_range.h>
#include <net/sock.h>
unsigned int sysctl_nr_open __read_mostly = 1024*1024;
@@ -265,12 +267,22 @@
return i;
}
+static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds)
+{
+ unsigned int count;
+
+ count = count_open_files(fdt);
+ if (max_fds < NR_OPEN_DEFAULT)
+ max_fds = NR_OPEN_DEFAULT;
+ return min(count, max_fds);
+}
+
/*
* Allocate a new files structure and copy contents from the
* passed in files structure.
* errorp will be valid only when the returned files_struct is NULL.
*/
-struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
+struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp)
{
struct files_struct *newf;
struct file **old_fds, **new_fds;
@@ -297,7 +309,7 @@
spin_lock(&oldf->file_lock);
old_fdt = files_fdtable(oldf);
- open_files = count_open_files(old_fdt);
+ open_files = sane_fdtable_size(old_fdt, max_fds);
/*
* Check whether we need to allocate a larger fd array and fd set.
@@ -328,7 +340,7 @@
*/
spin_lock(&oldf->file_lock);
old_fdt = files_fdtable(oldf);
- open_files = count_open_files(old_fdt);
+ open_files = sane_fdtable_size(old_fdt, max_fds);
}
copy_fd_bitmaps(new_fdt, old_fdt, open_files);
@@ -625,12 +637,9 @@
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);
@@ -642,15 +651,105 @@
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(unsigned fd, unsigned max_fd, unsigned int flags)
+{
+ unsigned int cur_max;
+ struct task_struct *me = current;
+ struct files_struct *cur_fds = me->files, *fds = NULL;
+
+ if (flags & ~CLOSE_RANGE_UNSHARE)
+ return -EINVAL;
+
+ if (fd > max_fd)
+ return -EINVAL;
+
+ rcu_read_lock();
+ cur_max = files_fdtable(cur_fds)->max_fds;
+ rcu_read_unlock();
+
+ /* cap to last valid index into fdtable */
+ cur_max--;
+
+ if (flags & CLOSE_RANGE_UNSHARE) {
+ int ret;
+ unsigned int max_unshare_fds = NR_OPEN_MAX;
+
+ /*
+ * If the requested range is greater than the current maximum,
+ * we're closing everything so only copy all file descriptors
+ * beneath the lowest file descriptor.
+ */
+ if (max_fd >= cur_max)
+ max_unshare_fds = fd;
+
+ ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds);
+ if (ret)
+ return ret;
+
+ /*
+ * We used to share our file descriptor table, and have now
+ * created a private one, make sure we're using it below.
+ */
+ if (fds)
+ swap(cur_fds, fds);
+ }
+
+ max_fd = min(max_fd, cur_max);
+ while (fd <= max_fd) {
+ struct file *file;
+
+ file = pick_file(cur_fds, fd++);
+ if (!file)
+ continue;
+
+ filp_close(file, cur_fds);
+ cond_resched();
+ }
+
+ if (fds) {
+ /*
+ * We're done closing the files we were supposed to. Time to install
+ * the new file descriptor table and drop the old one.
+ */
+ task_lock(me);
+ me->files = cur_fds;
+ task_unlock(me);
+ put_files_struct(fds);
+ }
+
+ 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
diff --git a/fs/open.c b/fs/open.c
index 6cd48a6..5e62f18 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1310,6 +1310,23 @@
return retval;
}
+/**
+ * close_range() - Close all file descriptors in a given range.
+ *
+ * @fd: starting file descriptor to close
+ * @max_fd: last file descriptor to close
+ * @flags: reserved for future extensions
+ *
+ * This closes a range of file descriptors. All file descriptors
+ * from @fd up to and including @max_fd are closed.
+ * Currently, errors to close a given file descriptor are ignored.
+ */
+SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd,
+ unsigned int, flags)
+{
+ return __close_range(fd, max_fd, flags);
+}
+
/*
* This routine simulates a hangup on the tty, to arrange that users
* are given clean terminals at login time.
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index f07c55e..a32bf47 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -22,6 +22,7 @@
* as this is the granularity returned by copy_fdset().
*/
#define NR_OPEN_DEFAULT BITS_PER_LONG
+#define NR_OPEN_MAX ~0U
struct fdtable {
unsigned int max_fds;
@@ -109,7 +110,7 @@
void put_files_struct(struct files_struct *fs);
void reset_files_struct(struct files_struct *);
int unshare_files(struct files_struct **);
-struct files_struct *dup_fd(struct files_struct *, int *) __latent_entropy;
+struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy;
void do_close_on_exec(struct files_struct *);
int iterate_fd(struct files_struct *, unsigned,
int (*)(const void *, struct file *, unsigned),
@@ -121,7 +122,10 @@
unsigned int fd, struct file *file);
extern int __close_fd(struct files_struct *files,
unsigned int fd);
+extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
extern int __close_fd_get_file(unsigned int fd, struct file **res);
+extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
+ struct files_struct **new_fdp);
extern struct kmem_cache *files_cachep;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index b951a87..86d9735 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -444,6 +444,8 @@
asmlinkage long sys_openat2(int dfd, const char __user *filename,
struct open_how *how, size_t size);
asmlinkage long sys_close(unsigned int fd);
+asmlinkage long sys_close_range(unsigned int fd, unsigned int max_fd,
+ unsigned int flags);
asmlinkage long sys_vhangup(void);
/* fs/pipe.c */
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index f4a0130..31001e3 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -850,6 +850,8 @@
#define __NR_clone3 435
__SYSCALL(__NR_clone3, sys_clone3)
#endif
+#define __NR_close_range 436
+__SYSCALL(__NR_close_range, sys_close_range)
#define __NR_openat2 437
__SYSCALL(__NR_openat2, sys_openat2)
diff --git a/include/uapi/linux/close_range.h b/include/uapi/linux/close_range.h
new file mode 100644
index 0000000..6928a9f
--- /dev/null
+++ b/include/uapi/linux/close_range.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_CLOSE_RANGE_H
+#define _UAPI_LINUX_CLOSE_RANGE_H
+
+/* Unshare the file descriptor table before closing file descriptors. */
+#define CLOSE_RANGE_UNSHARE (1U << 1)
+
+#endif /* _UAPI_LINUX_CLOSE_RANGE_H */
+
diff --git a/kernel/fork.c b/kernel/fork.c
index b7da900..76d3f33 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1479,7 +1479,7 @@
goto out;
}
- newf = dup_fd(oldf, &error);
+ newf = dup_fd(oldf, NR_OPEN_MAX, &error);
if (!newf)
goto out;
@@ -2866,14 +2866,15 @@
/*
* Unshare file descriptor table if it is being shared
*/
-static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
+int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
+ struct files_struct **new_fdp)
{
struct files_struct *fd = current->files;
int error = 0;
if ((unshare_flags & CLONE_FILES) &&
(fd && atomic_read(&fd->count) > 1)) {
- *new_fdp = dup_fd(fd, &error);
+ *new_fdp = dup_fd(fd, max_fds, &error);
if (!*new_fdp)
return error;
}
@@ -2933,7 +2934,7 @@
err = unshare_fs(unshare_flags, &new_fs);
if (err)
goto bad_unshare_out;
- err = unshare_fd(unshare_flags, &new_fd);
+ err = unshare_fd(unshare_flags, NR_OPEN_MAX, &new_fd);
if (err)
goto bad_unshare_cleanup_fs;
err = unshare_userns(unshare_flags, &new_cred);
@@ -3022,7 +3023,7 @@
struct files_struct *copy = NULL;
int error;
- error = unshare_fd(CLONE_FILES, ©);
+ error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, ©);
if (error || !copy) {
*displaced = NULL;
return error;
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 227ca78..017ce2a 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -6,6 +6,7 @@
TARGETS += capabilities
TARGETS += cgroup
TARGETS += clone3
+TARGETS += core
TARGETS += cpufreq
TARGETS += cpu-hotplug
TARGETS += drivers/dma-buf
diff --git a/tools/testing/selftests/core/.gitignore b/tools/testing/selftests/core/.gitignore
new file mode 100644
index 0000000..6e6712c
--- /dev/null
+++ b/tools/testing/selftests/core/.gitignore
@@ -0,0 +1 @@
+close_range_test
diff --git a/tools/testing/selftests/core/Makefile b/tools/testing/selftests/core/Makefile
new file mode 100644
index 0000000..f6f2d6f
--- /dev/null
+++ b/tools/testing/selftests/core/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+CFLAGS += -g -I../../../../usr/include/
+
+TEST_GEN_PROGS := close_range_test
+
+include ../lib.mk
+
diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
new file mode 100644
index 0000000..c99b98b
--- /dev/null
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -0,0 +1,227 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/kernel.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+#include "../clone3/clone3_selftests.h"
+
+#ifndef __NR_close_range
+#define __NR_close_range -1
+#endif
+
+#ifndef CLOSE_RANGE_UNSHARE
+#define CLOSE_RANGE_UNSHARE (1U << 1)
+#endif
+
+static inline int sys_close_range(unsigned int fd, unsigned int max_fd,
+ unsigned int flags)
+{
+ return syscall(__NR_close_range, fd, max_fd, flags);
+}
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+TEST(close_range)
+{
+ int i, ret;
+ int open_fds[101];
+
+ for (i = 0; i < ARRAY_SIZE(open_fds); i++) {
+ int fd;
+
+ fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+ ASSERT_GE(fd, 0) {
+ if (errno == ENOENT)
+ XFAIL(return, "Skipping test since /dev/null does not exist");
+ }
+
+ open_fds[i] = fd;
+ }
+
+ EXPECT_EQ(-1, sys_close_range(open_fds[0], open_fds[100], -1)) {
+ if (errno == ENOSYS)
+ XFAIL(return, "close_range() syscall not supported");
+ }
+
+ EXPECT_EQ(0, sys_close_range(open_fds[0], open_fds[50], 0));
+
+ for (i = 0; i <= 50; i++)
+ EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL));
+
+ for (i = 51; i <= 100; i++)
+ EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1);
+
+ /* create a couple of gaps */
+ close(57);
+ close(78);
+ close(81);
+ close(82);
+ close(84);
+ close(90);
+
+ EXPECT_EQ(0, sys_close_range(open_fds[51], open_fds[92], 0));
+
+ for (i = 51; i <= 92; i++)
+ EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL));
+
+ for (i = 93; i <= 100; i++)
+ EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1);
+
+ /* test that the kernel caps and still closes all fds */
+ EXPECT_EQ(0, sys_close_range(open_fds[93], open_fds[99], 0));
+
+ for (i = 93; i <= 99; i++)
+ EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL));
+
+ EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1);
+
+ EXPECT_EQ(0, sys_close_range(open_fds[100], open_fds[100], 0));
+
+ EXPECT_EQ(-1, fcntl(open_fds[100], F_GETFL));
+}
+
+TEST(close_range_unshare)
+{
+ int i, ret, status;
+ pid_t pid;
+ int open_fds[101];
+ struct clone_args args = {
+ .flags = CLONE_FILES,
+ .exit_signal = SIGCHLD,
+ };
+
+ for (i = 0; i < ARRAY_SIZE(open_fds); i++) {
+ int fd;
+
+ fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+ ASSERT_GE(fd, 0) {
+ if (errno == ENOENT)
+ XFAIL(return, "Skipping test since /dev/null does not exist");
+ }
+
+ open_fds[i] = fd;
+ }
+
+ pid = sys_clone3(&args, sizeof(args));
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ ret = sys_close_range(open_fds[0], open_fds[50],
+ CLOSE_RANGE_UNSHARE);
+ if (ret)
+ exit(EXIT_FAILURE);
+
+ for (i = 0; i <= 50; i++)
+ if (fcntl(open_fds[i], F_GETFL) != -1)
+ exit(EXIT_FAILURE);
+
+ for (i = 51; i <= 100; i++)
+ if (fcntl(open_fds[i], F_GETFL) == -1)
+ exit(EXIT_FAILURE);
+
+ /* create a couple of gaps */
+ close(57);
+ close(78);
+ close(81);
+ close(82);
+ close(84);
+ close(90);
+
+ ret = sys_close_range(open_fds[51], open_fds[92],
+ CLOSE_RANGE_UNSHARE);
+ if (ret)
+ exit(EXIT_FAILURE);
+
+ for (i = 51; i <= 92; i++)
+ if (fcntl(open_fds[i], F_GETFL) != -1)
+ exit(EXIT_FAILURE);
+
+ for (i = 93; i <= 100; i++)
+ if (fcntl(open_fds[i], F_GETFL) == -1)
+ exit(EXIT_FAILURE);
+
+ /* test that the kernel caps and still closes all fds */
+ ret = sys_close_range(open_fds[93], open_fds[99],
+ CLOSE_RANGE_UNSHARE);
+ if (ret)
+ exit(EXIT_FAILURE);
+
+ for (i = 93; i <= 99; i++)
+ if (fcntl(open_fds[i], F_GETFL) != -1)
+ exit(EXIT_FAILURE);
+
+ if (fcntl(open_fds[100], F_GETFL) == -1)
+ exit(EXIT_FAILURE);
+
+ ret = sys_close_range(open_fds[100], open_fds[100],
+ CLOSE_RANGE_UNSHARE);
+ if (ret)
+ exit(EXIT_FAILURE);
+
+ if (fcntl(open_fds[100], F_GETFL) != -1)
+ exit(EXIT_FAILURE);
+
+ exit(EXIT_SUCCESS);
+ }
+
+ EXPECT_EQ(waitpid(pid, &status, 0), pid);
+ EXPECT_EQ(true, WIFEXITED(status));
+ EXPECT_EQ(0, WEXITSTATUS(status));
+}
+
+TEST(close_range_unshare_capped)
+{
+ int i, ret, status;
+ pid_t pid;
+ int open_fds[101];
+ struct clone_args args = {
+ .flags = CLONE_FILES,
+ .exit_signal = SIGCHLD,
+ };
+
+ for (i = 0; i < ARRAY_SIZE(open_fds); i++) {
+ int fd;
+
+ fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+ ASSERT_GE(fd, 0) {
+ if (errno == ENOENT)
+ XFAIL(return, "Skipping test since /dev/null does not exist");
+ }
+
+ open_fds[i] = fd;
+ }
+
+ pid = sys_clone3(&args, sizeof(args));
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ ret = sys_close_range(open_fds[0], UINT_MAX,
+ CLOSE_RANGE_UNSHARE);
+ if (ret)
+ exit(EXIT_FAILURE);
+
+ for (i = 0; i <= 100; i++)
+ if (fcntl(open_fds[i], F_GETFL) != -1)
+ exit(EXIT_FAILURE);
+
+ exit(EXIT_SUCCESS);
+ }
+
+ EXPECT_EQ(waitpid(pid, &status, 0), pid);
+ EXPECT_EQ(true, WIFEXITED(status));
+ EXPECT_EQ(0, WEXITSTATUS(status));
+}
+
+TEST_HARNESS_MAIN
