Merge branch 'exec-for-v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull execve updates from Eric Biederman:
 "This set of changes ultimately fixes the interaction of posix file
  lock and exec. Fundamentally most of the change is just moving where
  unshare_files is called during exec, and tweaking the users of
  files_struct so that the count of files_struct is not unnecessarily
  played with.

  Along the way fcheck and related helpers were renamed to more
  accurately reflect what they do.

  There were also many other small changes that fell out, as this is the
  first time in a long time much of this code has been touched.

  Benchmarks haven't turned up any practical issues but Al Viro has
  observed a possibility for a lot of pounding on task_lock. So I have
  some changes in progress to convert put_files_struct to always rcu
  free files_struct. That wasn't ready for the merge window so that will
  have to wait until next time"

* 'exec-for-v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (27 commits)
  exec: Move io_uring_task_cancel after the point of no return
  coredump: Document coredump code exclusively used by cell spufs
  file: Remove get_files_struct
  file: Rename __close_fd_get_file close_fd_get_file
  file: Replace ksys_close with close_fd
  file: Rename __close_fd to close_fd and remove the files parameter
  file: Merge __alloc_fd into alloc_fd
  file: In f_dupfd read RLIMIT_NOFILE once.
  file: Merge __fd_install into fd_install
  proc/fd: In fdinfo seq_show don't use get_files_struct
  bpf/task_iter: In task_file_seq_get_next use task_lookup_next_fd_rcu
  proc/fd: In proc_readfd_common use task_lookup_next_fd_rcu
  file: Implement task_lookup_next_fd_rcu
  kcmp: In get_file_raw_ptr use task_lookup_fd_rcu
  proc/fd: In tid_fd_mode use task_lookup_fd_rcu
  file: Implement task_lookup_fd_rcu
  file: Rename fcheck lookup_fd_rcu
  file: Replace fcheck_files with files_lookup_fd_rcu
  file: Factor files_lookup_fd_locked out of fcheck_files
  file: Rename __fcheck_files to files_lookup_fd_raw
  ...

1 files changed, 58 insertions, 66 deletions

diff --git a/fs/file.c b/fs/file.c
index e08e4daccac3..8434e0afecc7 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -158,7 +158,7 @@ static int expand_fdtable(struct files_struct *files, unsigned int nr)
 	spin_unlock(&files->file_lock);
 	new_fdt = alloc_fdtable(nr);
 
-	/* make sure all __fd_install() have seen resize_in_progress
+	/* make sure all fd_install() have seen resize_in_progress
 	 * or have finished their rcu_read_lock_sched() section.
 	 */
 	if (atomic_read(&files->count) > 1)
@@ -181,7 +181,7 @@ static int expand_fdtable(struct files_struct *files, unsigned int nr)
 	rcu_assign_pointer(files->fdt, new_fdt);
 	if (cur_fdt != &files->fdtab)
 		call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
-	/* coupled with smp_rmb() in __fd_install() */
+	/* coupled with smp_rmb() in fd_install() */
 	smp_wmb();
 	return 1;
 }
@@ -411,19 +411,6 @@ static struct fdtable *close_files(struct files_struct * files)
 	return fdt;
 }
 
-struct files_struct *get_files_struct(struct task_struct *task)
-{
-	struct files_struct *files;
-
-	task_lock(task);
-	files = task->files;
-	if (files)
-		atomic_inc(&files->count);
-	task_unlock(task);
-
-	return files;
-}
-
 void put_files_struct(struct files_struct *files)
 {
 	if (atomic_dec_and_test(&files->count)) {
@@ -436,18 +423,6 @@ void put_files_struct(struct files_struct *files)
 	}
 }
 
-void reset_files_struct(struct files_struct *files)
-{
-	struct task_struct *tsk = current;
-	struct files_struct *old;
-
-	old = tsk->files;
-	task_lock(tsk);
-	tsk->files = files;
-	task_unlock(tsk);
-	put_files_struct(old);
-}
-
 void exit_files(struct task_struct *tsk)
 {
 	struct files_struct * files = tsk->files;
@@ -492,9 +467,9 @@ static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start)
 /*
  * allocate a file descriptor, mark it busy.
  */
-int __alloc_fd(struct files_struct *files,
-	       unsigned start, unsigned end, unsigned flags)
+static int alloc_fd(unsigned start, unsigned end, unsigned flags)
 {
+	struct files_struct *files = current->files;
 	unsigned int fd;
 	int error;
 	struct fdtable *fdt;
@@ -550,14 +525,9 @@ out:
 	return error;
 }
 
-static int alloc_fd(unsigned start, unsigned flags)
-{
-	return __alloc_fd(current->files, start, rlimit(RLIMIT_NOFILE), flags);
-}
-
 int __get_unused_fd_flags(unsigned flags, unsigned long nofile)
 {
-	return __alloc_fd(current->files, 0, nofile, flags);
+	return alloc_fd(0, nofile, flags);
 }
 
 int get_unused_fd_flags(unsigned flags)
@@ -596,17 +566,13 @@ EXPORT_SYMBOL(put_unused_fd);
  * It should never happen - if we allow dup2() do it, _really_ bad things
  * will follow.
  *
- * NOTE: __fd_install() variant is really, really low-level; don't
- * use it unless you are forced to by truly lousy API shoved down
- * your throat.  'files' *MUST* be either current->files or obtained
- * by get_files_struct(current) done by whoever had given it to you,
- * or really bad things will happen.  Normally you want to use
- * fd_install() instead.
+ * This consumes the "file" refcount, so callers should treat it
+ * as if they had called fput(file).
  */
 
-void __fd_install(struct files_struct *files, unsigned int fd,
-		struct file *file)
+void fd_install(unsigned int fd, struct file *file)
 {
+	struct files_struct *files = current->files;
 	struct fdtable *fdt;
 
 	rcu_read_lock_sched();
@@ -628,15 +594,6 @@ void __fd_install(struct files_struct *files, unsigned int fd,
 	rcu_read_unlock_sched();
 }
 
-/*
- * This consumes the "file" refcount, so callers should treat it
- * as if they had called fput(file).
- */
-void fd_install(unsigned int fd, struct file *file)
-{
-	__fd_install(current->files, fd, file);
-}
-
 EXPORT_SYMBOL(fd_install);
 
 static struct file *pick_file(struct files_struct *files, unsigned fd)
@@ -659,11 +616,9 @@ out_unlock:
 	return file;
 }
 
-/*
- * The same warnings as for __alloc_fd()/__fd_install() apply here...
- */
-int __close_fd(struct files_struct *files, unsigned fd)
+int close_fd(unsigned fd)
 {
+	struct files_struct *files = current->files;
 	struct file *file;
 
 	file = pick_file(files, fd);
@@ -672,7 +627,7 @@ int __close_fd(struct files_struct *files, unsigned fd)
 
 	return filp_close(file, files);
 }
-EXPORT_SYMBOL(__close_fd); /* for ksys_close() */
+EXPORT_SYMBOL(close_fd); /* for ksys_close() */
 
 static inline void __range_cloexec(struct files_struct *cur_fds,
 				   unsigned int fd, unsigned int max_fd)
@@ -777,11 +732,11 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
 }
 
 /*
- * variant of __close_fd that gets a ref on the file for later fput.
+ * 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
  * an fput().
  */
-int __close_fd_get_file(unsigned int fd, struct file **res)
+int close_fd_get_file(unsigned int fd, struct file **res)
 {
 	struct files_struct *files = current->files;
 	struct file *file;
@@ -850,7 +805,7 @@ static struct file *__fget_files(struct files_struct *files, unsigned int fd,
 
 	rcu_read_lock();
 loop:
-	file = fcheck_files(files, fd);
+	file = files_lookup_fd_rcu(files, fd);
 	if (file) {
 		/* File object ref couldn't be taken.
 		 * dup2() atomicity guarantee is the reason
@@ -901,6 +856,42 @@ struct file *fget_task(struct task_struct *task, unsigned int fd)
 	return file;
 }
 
+struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd)
+{
+	/* Must be called with rcu_read_lock held */
+	struct files_struct *files;
+	struct file *file = NULL;
+
+	task_lock(task);
+	files = task->files;
+	if (files)
+		file = files_lookup_fd_rcu(files, fd);
+	task_unlock(task);
+
+	return file;
+}
+
+struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *ret_fd)
+{
+	/* Must be called with rcu_read_lock held */
+	struct files_struct *files;
+	unsigned int fd = *ret_fd;
+	struct file *file = NULL;
+
+	task_lock(task);
+	files = task->files;
+	if (files) {
+		for (; fd < files_fdtable(files)->max_fds; fd++) {
+			file = files_lookup_fd_rcu(files, fd);
+			if (file)
+				break;
+		}
+	}
+	task_unlock(task);
+	*ret_fd = fd;
+	return file;
+}
+
 /*
  * Lightweight file lookup - no refcnt increment if fd table isn't shared.
  *
@@ -923,7 +914,7 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask)
 	struct file *file;
 
 	if (atomic_read(&files->count) == 1) {
-		file = __fcheck_files(files, fd);
+		file = files_lookup_fd_raw(files, fd);
 		if (!file || unlikely(file->f_mode & mask))
 			return 0;
 		return (unsigned long)file;
@@ -1045,7 +1036,7 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
 	struct files_struct *files = current->files;
 
 	if (!file)
-		return __close_fd(files, fd);
+		return close_fd(fd);
 
 	if (fd >= rlimit(RLIMIT_NOFILE))
 		return -EBADF;
@@ -1134,7 +1125,7 @@ static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
 
 	spin_lock(&files->file_lock);
 	err = expand_files(files, newfd);
-	file = fcheck(oldfd);
+	file = files_lookup_fd_locked(files, oldfd);
 	if (unlikely(!file))
 		goto Ebadf;
 	if (unlikely(err < 0)) {
@@ -1163,7 +1154,7 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
 		int retval = oldfd;
 
 		rcu_read_lock();
-		if (!fcheck_files(files, oldfd))
+		if (!files_lookup_fd_rcu(files, oldfd))
 			retval = -EBADF;
 		rcu_read_unlock();
 		return retval;
@@ -1188,10 +1179,11 @@ SYSCALL_DEFINE1(dup, unsigned int, fildes)
 
 int f_dupfd(unsigned int from, struct file *file, unsigned flags)
 {
+	unsigned long nofile = rlimit(RLIMIT_NOFILE);
 	int err;
-	if (from >= rlimit(RLIMIT_NOFILE))
+	if (from >= nofile)
 		return -EINVAL;
-	err = alloc_fd(from, flags);
+	err = alloc_fd(from, nofile, flags);
 	if (err >= 0) {
 		get_file(file);
 		fd_install(err, file);