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, 15 insertions, 33 deletions

diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 81882a13212d..cb51763ed554 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -28,14 +28,13 @@ static int seq_show(struct seq_file *m, void *v)
 	if (!task)
 		return -ENOENT;
 
-	files = get_files_struct(task);
-	put_task_struct(task);
-
+	task_lock(task);
+	files = task->files;
 	if (files) {
 		unsigned int fd = proc_fd(m->private);
 
 		spin_lock(&files->file_lock);
-		file = fcheck_files(files, fd);
+		file = files_lookup_fd_locked(files, fd);
 		if (file) {
 			struct fdtable *fdt = files_fdtable(files);
 
@@ -47,8 +46,9 @@ static int seq_show(struct seq_file *m, void *v)
 			ret = 0;
 		}
 		spin_unlock(&files->file_lock);
-		put_files_struct(files);
 	}
+	task_unlock(task);
+	put_task_struct(task);
 
 	if (ret)
 		return ret;
@@ -57,6 +57,7 @@ static int seq_show(struct seq_file *m, void *v)
 		   (long long)file->f_pos, f_flags,
 		   real_mount(file->f_path.mnt)->mnt_id);
 
+	/* show_fd_locks() never deferences files so a stale value is safe */
 	show_fd_locks(m, file, files);
 	if (seq_has_overflowed(m))
 		goto out;
@@ -83,18 +84,13 @@ static const struct file_operations proc_fdinfo_file_operations = {
 
 static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode)
 {
-	struct files_struct *files = get_files_struct(task);
 	struct file *file;
 
-	if (!files)
-		return false;
-
 	rcu_read_lock();
-	file = fcheck_files(files, fd);
+	file = task_lookup_fd_rcu(task, fd);
 	if (file)
 		*mode = file->f_mode;
 	rcu_read_unlock();
-	put_files_struct(files);
 	return !!file;
 }
 
@@ -146,29 +142,22 @@ static const struct dentry_operations tid_fd_dentry_operations = {
 
 static int proc_fd_link(struct dentry *dentry, struct path *path)
 {
-	struct files_struct *files = NULL;
 	struct task_struct *task;
 	int ret = -ENOENT;
 
 	task = get_proc_task(d_inode(dentry));
 	if (task) {
-		files = get_files_struct(task);
-		put_task_struct(task);
-	}
-
-	if (files) {
 		unsigned int fd = proc_fd(d_inode(dentry));
 		struct file *fd_file;
 
-		spin_lock(&files->file_lock);
-		fd_file = fcheck_files(files, fd);
+		fd_file = fget_task(task, fd);
 		if (fd_file) {
 			*path = fd_file->f_path;
 			path_get(&fd_file->f_path);
 			ret = 0;
+			fput(fd_file);
 		}
-		spin_unlock(&files->file_lock);
-		put_files_struct(files);
+		put_task_struct(task);
 	}
 
 	return ret;
@@ -229,7 +218,6 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
 			      instantiate_t instantiate)
 {
 	struct task_struct *p = get_proc_task(file_inode(file));
-	struct files_struct *files;
 	unsigned int fd;
 
 	if (!p)
@@ -237,22 +225,18 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
 
 	if (!dir_emit_dots(file, ctx))
 		goto out;
-	files = get_files_struct(p);
-	if (!files)
-		goto out;
 
 	rcu_read_lock();
-	for (fd = ctx->pos - 2;
-	     fd < files_fdtable(files)->max_fds;
-	     fd++, ctx->pos++) {
+	for (fd = ctx->pos - 2;; fd++) {
 		struct file *f;
 		struct fd_data data;
 		char name[10 + 1];
 		unsigned int len;
 
-		f = fcheck_files(files, fd);
+		f = task_lookup_next_fd_rcu(p, &fd);
+		ctx->pos = fd + 2LL;
 		if (!f)
-			continue;
+			break;
 		data.mode = f->f_mode;
 		rcu_read_unlock();
 		data.fd = fd;
@@ -261,13 +245,11 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
 		if (!proc_fill_cache(file, ctx,
 				     name, len, instantiate, p,
 				     &data))
-			goto out_fd_loop;
+			goto out;
 		cond_resched();
 		rcu_read_lock();
 	}
 	rcu_read_unlock();
-out_fd_loop:
-	put_files_struct(files);
 out:
 	put_task_struct(p);
 	return 0;