[PATCH] files: lock-free fd look-up

With the use of RCU in files structure, the look-up of files using fds can now
be lock-free.  The lookup is protected by rcu_read_lock()/rcu_read_unlock().
This patch changes the readers to use lock-free lookup.

Signed-off-by: Maneesh Soni <maneesh@in.ibm.com>
Signed-off-by: Ravikiran Thirumalai <kiran_th@gmail.com>
Signed-off-by: Dipankar Sarma <dipankar@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

9 files changed, 39 insertions, 27 deletions

diff --git a/arch/mips/kernel/irixioctl.c b/arch/mips/kernel/irixioctl.c
index 4cd3d38..3cdc223 100644
--- a/arch/mips/kernel/irixioctl.c
+++ b/arch/mips/kernel/irixioctl.c
@@ -14,6 +14,7 @@
 #include <linux/syscalls.h>
 #include <linux/tty.h>
 #include <linux/file.h>
+#include <linux/rcupdate.h>
 
 #include <asm/uaccess.h>
 #include <asm/ioctl.h>
@@ -33,7 +34,7 @@ static struct tty_struct *get_tty(int fd)
 	struct file *filp;
 	struct tty_struct *ttyp = NULL;
 
-	spin_lock(&current->files->file_lock);
+	rcu_read_lock();
 	filp = fcheck(fd);
 	if(filp && filp->private_data) {
 		ttyp = (struct tty_struct *) filp->private_data;
@@ -41,7 +42,7 @@ static struct tty_struct *get_tty(int fd)
 		if(ttyp->magic != TTY_MAGIC)
 			ttyp =NULL;
 	}
-	spin_unlock(&current->files->file_lock);
+	rcu_read_unlock();
 	return ttyp;
 }
 
diff --git a/arch/sparc64/solaris/ioctl.c b/arch/sparc64/solaris/ioctl.c
index 3747664..be0a054 100644
--- a/arch/sparc64/solaris/ioctl.c
+++ b/arch/sparc64/solaris/ioctl.c
@@ -24,6 +24,7 @@
 #include <linux/netdevice.h>
 #include <linux/mtio.h>
 #include <linux/time.h>
+#include <linux/rcupdate.h>
 #include <linux/compat.h>
 
 #include <net/sock.h>
@@ -295,16 +296,16 @@ static inline int solaris_sockmod(unsigned int fd, unsigned int cmd, u32 arg)
 	struct inode *ino;
 	struct fdtable *fdt;
 	/* I wonder which of these tests are superfluous... --patrik */
-	spin_lock(&current->files->file_lock);
+	rcu_read_lock();
 	fdt = files_fdtable(current->files);
 	if (! fdt->fd[fd] ||
 	    ! fdt->fd[fd]->f_dentry ||
 	    ! (ino = fdt->fd[fd]->f_dentry->d_inode) ||
 	    ! S_ISSOCK(ino->i_mode)) {
-		spin_unlock(&current->files->file_lock);
+		rcu_read_unlock();
 		return TBADF;
 	}
-	spin_unlock(&current->files->file_lock);
+	rcu_read_unlock();
 	
 	switch (cmd & 0xff) {
 	case 109: /* SI_SOCKPARAMS */
diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c
index 0bfc7af..e5953f3 100644
--- a/drivers/char/tty_io.c
+++ b/drivers/char/tty_io.c
@@ -2480,7 +2480,7 @@ static void __do_SAK(void *arg)
 		}
 		task_lock(p);
 		if (p->files) {
-			spin_lock(&p->files->file_lock);
+			rcu_read_lock();
 			fdt = files_fdtable(p->files);
 			for (i=0; i < fdt->max_fds; i++) {
 				filp = fcheck_files(p->files, i);
@@ -2495,7 +2495,7 @@ static void __do_SAK(void *arg)
 					break;
 				}
 			}
-			spin_unlock(&p->files->file_lock);
+			rcu_read_unlock();
 		}
 		task_unlock(p);
 	} while_each_task_pid(session, PIDTYPE_SID, p);
diff --git a/fs/fcntl.c b/fs/fcntl.c
index d2f3ed8..863b46e 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -40,10 +40,10 @@ static inline int get_close_on_exec(unsigned int fd)
 	struct files_struct *files = current->files;
 	struct fdtable *fdt;
 	int res;
-	spin_lock(&files->file_lock);
+	rcu_read_lock();
 	fdt = files_fdtable(files);
 	res = FD_ISSET(fd, fdt->close_on_exec);
-	spin_unlock(&files->file_lock);
+	rcu_read_unlock();
 	return res;
 }
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index d0087a0..23db452 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -62,6 +62,7 @@
 #include <linux/namespace.h>
 #include <linux/mm.h>
 #include <linux/smp_lock.h>
+#include <linux/rcupdate.h>
 #include <linux/kallsyms.h>
 #include <linux/mount.h>
 #include <linux/security.h>
@@ -283,16 +284,16 @@ static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsm
 
 	files = get_files_struct(task);
 	if (files) {
-		spin_lock(&files->file_lock);
+		rcu_read_lock();
 		file = fcheck_files(files, fd);
 		if (file) {
 			*mnt = mntget(file->f_vfsmnt);
 			*dentry = dget(file->f_dentry);
-			spin_unlock(&files->file_lock);
+			rcu_read_unlock();
 			put_files_struct(files);
 			return 0;
 		}
-		spin_unlock(&files->file_lock);
+		rcu_read_unlock();
 		put_files_struct(files);
 	}
 	return -ENOENT;
@@ -1062,7 +1063,7 @@ static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir)
 			files = get_files_struct(p);
 			if (!files)
 				goto out;
-			spin_lock(&files->file_lock);
+			rcu_read_lock();
 			fdt = files_fdtable(files);
 			for (fd = filp->f_pos-2;
 			     fd < fdt->max_fds;
@@ -1071,7 +1072,7 @@ static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir)
 
 				if (!fcheck_files(files, fd))
 					continue;
-				spin_unlock(&files->file_lock);
+				rcu_read_unlock();
 
 				j = NUMBUF;
 				i = fd;
@@ -1083,12 +1084,12 @@ static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir)
 
 				ino = fake_ino(tid, PROC_TID_FD_DIR + fd);
 				if (filldir(dirent, buf+j, NUMBUF-j, fd+2, ino, DT_LNK) < 0) {
-					spin_lock(&files->file_lock);
+					rcu_read_lock();
 					break;
 				}
-				spin_lock(&files->file_lock);
+				rcu_read_lock();
 			}
-			spin_unlock(&files->file_lock);
+			rcu_read_unlock();
 			put_files_struct(files);
 	}
 out:
@@ -1263,9 +1264,9 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
 
 	files = get_files_struct(task);
 	if (files) {
-		spin_lock(&files->file_lock);
+		rcu_read_lock();
 		if (fcheck_files(files, fd)) {
-			spin_unlock(&files->file_lock);
+			rcu_read_unlock();
 			put_files_struct(files);
 			if (task_dumpable(task)) {
 				inode->i_uid = task->euid;
@@ -1277,7 +1278,7 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
 			security_task_to_inode(task, inode);
 			return 1;
 		}
-		spin_unlock(&files->file_lock);
+		rcu_read_unlock();
 		put_files_struct(files);
 	}
 	d_drop(dentry);
@@ -1369,7 +1370,7 @@ static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry,
 	if (!files)
 		goto out_unlock;
 	inode->i_mode = S_IFLNK;
-	spin_lock(&files->file_lock);
+	rcu_read_lock();
 	file = fcheck_files(files, fd);
 	if (!file)
 		goto out_unlock2;
@@ -1377,7 +1378,7 @@ static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry,
 		inode->i_mode |= S_IRUSR | S_IXUSR;
 	if (file->f_mode & 2)
 		inode->i_mode |= S_IWUSR | S_IXUSR;
-	spin_unlock(&files->file_lock);
+	rcu_read_unlock();
 	put_files_struct(files);
 	inode->i_op = &proc_pid_link_inode_operations;
 	inode->i_size = 64;
@@ -1387,7 +1388,7 @@ static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry,
 	return NULL;
 
 out_unlock2:
-	spin_unlock(&files->file_lock);
+	rcu_read_unlock();
 	put_files_struct(files);
 out_unlock:
 	iput(inode);
diff --git a/fs/select.c b/fs/select.c
index 2e56325..f10a103 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -22,6 +22,7 @@
 #include <linux/personality.h> /* for STICKY_TIMEOUTS */
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/rcupdate.h>
 
 #include <asm/uaccess.h>
 
@@ -185,9 +186,9 @@ int do_select(int n, fd_set_bits *fds, long *timeout)
 	int retval, i;
 	long __timeout = *timeout;
 
- 	spin_lock(&current->files->file_lock);
+	rcu_read_lock();
 	retval = max_select_fd(n, fds);
-	spin_unlock(&current->files->file_lock);
+	rcu_read_unlock();
 
 	if (retval < 0)
 		return retval;
@@ -329,8 +330,10 @@ sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, s
 		goto out_nofds;
 
 	/* max_fdset can increase, so grab it once to avoid race */
+	rcu_read_lock();
 	fdt = files_fdtable(current->files);
 	max_fdset = fdt->max_fdset;
+	rcu_read_unlock();
 	if (n > max_fdset)
 		n = max_fdset;
 
@@ -469,10 +472,14 @@ asmlinkage long sys_poll(struct pollfd __user * ufds, unsigned int nfds, long ti
 	struct poll_list *head;
  	struct poll_list *walk;
 	struct fdtable *fdt;
+	int max_fdset;
 
 	/* Do a sanity check on nfds ... */
+	rcu_read_lock();
 	fdt = files_fdtable(current->files);
-	if (nfds > fdt->max_fdset && nfds > OPEN_MAX)
+	max_fdset = fdt->max_fdset;
+	rcu_read_unlock();
+	if (nfds > max_fdset && nfds > OPEN_MAX)
 		return -EINVAL;
 
 	if (timeout) {
diff --git a/net/ipv4/netfilter/ipt_owner.c b/net/ipv4/netfilter/ipt_owner.c
index c1889f8..0cee286 100644
--- a/net/ipv4/netfilter/ipt_owner.c
+++ b/net/ipv4/netfilter/ipt_owner.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/file.h>
+#include <linux/rcupdate.h>
 #include <net/sock.h>
 
 #include <linux/netfilter_ipv4/ipt_owner.h>
diff --git a/net/ipv6/netfilter/ip6t_owner.c b/net/ipv6/netfilter/ip6t_owner.c
index 9b91dec..4de4cda 100644
--- a/net/ipv6/netfilter/ip6t_owner.c
+++ b/net/ipv6/netfilter/ip6t_owner.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/file.h>
+#include <linux/rcupdate.h>
 #include <net/sock.h>
 
 #include <linux/netfilter_ipv6/ip6t_owner.h>
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index acb5a49..f40c822 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -1652,7 +1652,7 @@ static inline void flush_unauthorized_files(struct files_struct * files)
 						continue;
 					}
 					if (devnull) {
-						atomic_inc(&devnull->f_count);
+						rcuref_inc(&devnull->f_count);
 					} else {
 						devnull = dentry_open(dget(selinux_null), mntget(selinuxfs_mount), O_RDWR);
 						if (!devnull) {