[PATCH] files: Use rcu lock to get the file structures for better performance

[Muchun Song <songmuchun@xxxxxxxxxxxxx>]

There is another safe way to get the file structure without
holding the files->file_lock. That is rcu lock, and this way
has better performance. So use the rcu lock instead of the
files->file_lock.

Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
---
 fs/proc/fd.c         | 31 ++++++++++++++++++++++++-------
 kernel/bpf/syscall.c | 17 +++++++++++------
 kernel/kcmp.c        | 15 ++++++++++-----
 3 files changed, 45 insertions(+), 18 deletions(-)

diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 81882a13212d3..5d5b0f091d32a 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -34,19 +34,27 @@ static int seq_show(struct seq_file *m, void *v)
 	if (files) {
 		unsigned int fd = proc_fd(m->private);
 
-		spin_lock(&files->file_lock);
+		rcu_read_lock();
+again:
 		file = fcheck_files(files, fd);
 		if (file) {
-			struct fdtable *fdt = files_fdtable(files);
+			struct fdtable *fdt;
+
+			if (!get_file_rcu(file)) {
+				/*
+				 * we loop to catch the new file (or NULL
+				 * pointer).
+				 */
+				goto again;
+			}
 
+			fdt = files_fdtable(files);
 			f_flags = file->f_flags;
 			if (close_on_exec(fd, fdt))
 				f_flags |= O_CLOEXEC;
-
-			get_file(file);
 			ret = 0;
 		}
-		spin_unlock(&files->file_lock);
+		rcu_read_unlock();
 		put_files_struct(files);
 	}
 
@@ -160,14 +168,23 @@ static int proc_fd_link(struct dentry *dentry, struct path *path)
 		unsigned int fd = proc_fd(d_inode(dentry));
 		struct file *fd_file;
 
-		spin_lock(&files->file_lock);
+		rcu_read_lock();
+again:
 		fd_file = fcheck_files(files, fd);
 		if (fd_file) {
+			if (!get_file_rcu(fd_file)) {
+				/*
+				 * we loop to catch the new file
+				 * (or NULL pointer).
+				 */
+				goto again;
+			}
 			*path = fd_file->f_path;
 			path_get(&fd_file->f_path);
+			fput(fd_file);
 			ret = 0;
 		}
-		spin_unlock(&files->file_lock);
+		rcu_read_unlock();
 		put_files_struct(files);
 	}
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8608d6e1b0e0e..441c91378a1fc 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3451,14 +3451,19 @@ static int bpf_task_fd_query(const union bpf_attr *attr,
 	if (!files)
 		return -ENOENT;
 
-	err = 0;
-	spin_lock(&files->file_lock);
+	rcu_read_lock();
+again:
 	file = fcheck_files(files, fd);
-	if (!file)
+	if (file) {
+		if (!get_file_rcu(file)) {
+			/* we loop to catch the new file (or NULL pointer) */
+			goto again;
+		}
+		err = 0;
+	} else {
 		err = -EBADF;
-	else
-		get_file(file);
-	spin_unlock(&files->file_lock);
+	}
+	rcu_read_unlock();
 	put_files_struct(files);
 
 	if (err)
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index b3ff9288c6cc9..3b4f2a54186f2 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -120,13 +120,18 @@ static int kcmp_epoll_target(struct task_struct *task1,
 	if (!files)
 		return -EBADF;
 
-	spin_lock(&files->file_lock);
+	rcu_read_lock();
+again:
 	filp_epoll = fcheck_files(files, slot.efd);
-	if (filp_epoll)
-		get_file(filp_epoll);
-	else
+	if (filp_epoll) {
+		if (!get_file_rcu(filp_epoll)) {
+			/* we loop to catch the new file (or NULL pointer) */
+			goto again;
+		}
+	} else {
 		filp_tgt = ERR_PTR(-EBADF);
-	spin_unlock(&files->file_lock);
+	}
+	rcu_read_unlock();
 	put_files_struct(files);
 
 	if (filp_epoll) {
-- 
2.11.0