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()

1 files changed, 110 insertions, 11 deletions

diff --git a/fs/file.c b/fs/file.c
index 4fb111735d1d1..4cb9ef4d85719 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 @@ static unsigned int count_open_files(struct fdtable *fdt)
 	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 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
 
 	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 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
 		 */
 		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 @@ 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);
@@ -642,15 +651,105 @@ 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(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