[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>
This commit is contained in:
parent
ab2af1f500
commit
b835996f62
|
@ -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(¤t->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(¤t->files->file_lock);
|
||||
rcu_read_unlock();
|
||||
return ttyp;
|
||||
}
|
||||
|
||||
|
|
|
@ -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(¤t->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(¤t->files->file_lock);
|
||||
rcu_read_unlock();
|
||||
return TBADF;
|
||||
}
|
||||
spin_unlock(¤t->files->file_lock);
|
||||
rcu_read_unlock();
|
||||
|
||||
switch (cmd & 0xff) {
|
||||
case 109: /* SI_SOCKPARAMS */
|
||||
|
|
|
@ -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);
|
||||
|
|
|
@ -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;
|
||||
}
|
||||
|
||||
|
|
|
@ -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);
|
||||
|
|
13
fs/select.c
13
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(¤t->files->file_lock);
|
||||
rcu_read_lock();
|
||||
retval = max_select_fd(n, fds);
|
||||
spin_unlock(¤t->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) {
|
||||
|
|
|
@ -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>
|
||||
|
|
|
@ -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>
|
||||
|
|
|
@ -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) {
|
||||
|
|
Loading…
Reference in New Issue