/*
- * dev_cgroup.c - device cgroup subsystem
+ * device_cgroup.c - device cgroup subsystem
*
* Copyright 2007 IBM Corp
*/
#include <linux/list.h>
#include <linux/uaccess.h>
#include <linux/seq_file.h>
+#include <linux/rcupdate.h>
#define ACC_MKNOD 1
#define ACC_READ 2
/*
* whitelist locking rules:
- * cgroup_lock() cannot be taken under dev_cgroup->lock.
- * dev_cgroup->lock can be taken with or without cgroup_lock().
- *
- * modifications always require cgroup_lock
- * modifications to a list which is visible require the
- * dev_cgroup->lock *and* cgroup_lock()
- * walking the list requires dev_cgroup->lock or cgroup_lock().
- *
- * reasoning: dev_whitelist_copy() needs to kmalloc, so needs
- * a mutex, which the cgroup_lock() is. Since modifying
- * a visible list requires both locks, either lock can be
- * taken for walking the list.
+ * hold cgroup_lock() for update/read.
+ * hold rcu_read_lock() for read.
*/
struct dev_whitelist_item {
short type;
short access;
struct list_head list;
+ struct rcu_head rcu;
};
struct dev_cgroup {
struct cgroup_subsys_state css;
struct list_head whitelist;
- spinlock_t lock;
};
static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s)
struct dev_whitelist_item *wh, *tmp, *new;
list_for_each_entry(wh, orig, list) {
- new = kmalloc(sizeof(*wh), GFP_KERNEL);
+ new = kmemdup(wh, sizeof(*wh), GFP_KERNEL);
if (!new)
goto free_and_exit;
- new->major = wh->major;
- new->minor = wh->minor;
- new->type = wh->type;
- new->access = wh->access;
list_add_tail(&new->list, dest);
}
/* Stupid prototype - don't bother combining existing entries */
/*
* called under cgroup_lock()
- * since the list is visible to other tasks, we need the spinlock also
*/
static int dev_whitelist_add(struct dev_cgroup *dev_cgroup,
struct dev_whitelist_item *wh)
{
struct dev_whitelist_item *whcopy, *walk;
- whcopy = kmalloc(sizeof(*whcopy), GFP_KERNEL);
+ whcopy = kmemdup(wh, sizeof(*wh), GFP_KERNEL);
if (!whcopy)
return -ENOMEM;
- memcpy(whcopy, wh, sizeof(*whcopy));
- spin_lock(&dev_cgroup->lock);
list_for_each_entry(walk, &dev_cgroup->whitelist, list) {
if (walk->type != wh->type)
continue;
}
if (whcopy != NULL)
- list_add_tail(&whcopy->list, &dev_cgroup->whitelist);
- spin_unlock(&dev_cgroup->lock);
+ list_add_tail_rcu(&whcopy->list, &dev_cgroup->whitelist);
return 0;
}
+static void whitelist_item_free(struct rcu_head *rcu)
+{
+ struct dev_whitelist_item *item;
+
+ item = container_of(rcu, struct dev_whitelist_item, rcu);
+ kfree(item);
+}
+
/*
* called under cgroup_lock()
- * since the list is visible to other tasks, we need the spinlock also
*/
static void dev_whitelist_rm(struct dev_cgroup *dev_cgroup,
struct dev_whitelist_item *wh)
{
struct dev_whitelist_item *walk, *tmp;
- spin_lock(&dev_cgroup->lock);
list_for_each_entry_safe(walk, tmp, &dev_cgroup->whitelist, list) {
if (walk->type == DEV_ALL)
goto remove;
remove:
walk->access &= ~wh->access;
if (!walk->access) {
- list_del(&walk->list);
- kfree(walk);
+ list_del_rcu(&walk->list);
+ call_rcu(&walk->rcu, whitelist_item_free);
}
}
- spin_unlock(&dev_cgroup->lock);
}
/*
}
wh->minor = wh->major = ~0;
wh->type = DEV_ALL;
- wh->access = ACC_MKNOD | ACC_READ | ACC_WRITE;
+ wh->access = ACC_MASK;
list_add(&wh->list, &dev_cgroup->whitelist);
} else {
parent_dev_cgroup = cgroup_to_devcgroup(parent_cgroup);
}
}
- spin_lock_init(&dev_cgroup->lock);
return &dev_cgroup->css;
}
static void set_majmin(char *str, unsigned m)
{
- memset(str, 0, MAJMINLEN);
if (m == ~0)
- sprintf(str, "*");
+ strcpy(str, "*");
else
- snprintf(str, MAJMINLEN, "%u", m);
+ sprintf(str, "%u", m);
}
static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft,
struct dev_whitelist_item *wh;
char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN];
- spin_lock(&devcgroup->lock);
- list_for_each_entry(wh, &devcgroup->whitelist, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(wh, &devcgroup->whitelist, list) {
set_access(acc, wh->access);
set_majmin(maj, wh->major);
set_majmin(min, wh->minor);
seq_printf(m, "%c %s:%s %s\n", type_to_char(wh->type),
maj, min, acc);
}
- spin_unlock(&devcgroup->lock);
+ rcu_read_unlock();
return 0;
}
{
struct cgroup *pcg = childcg->css.cgroup->parent;
struct dev_cgroup *parent;
- int ret;
if (!pcg)
return 1;
parent = cgroup_to_devcgroup(pcg);
- spin_lock(&parent->lock);
- ret = may_access_whitelist(parent, wh);
- spin_unlock(&parent->lock);
- return ret;
+ return may_access_whitelist(parent, wh);
}
/*
static int devcgroup_update_access(struct dev_cgroup *devcgroup,
int filetype, const char *buffer)
{
- struct dev_cgroup *cur_devcgroup;
const char *b;
- int retval = 0, count;
+ char *endp;
+ int count;
struct dev_whitelist_item wh;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- cur_devcgroup = task_devcgroup(current);
-
memset(&wh, 0, sizeof(wh));
b = buffer;
wh.major = ~0;
b++;
} else if (isdigit(*b)) {
- wh.major = 0;
- while (isdigit(*b)) {
- wh.major = wh.major*10+(*b-'0');
- b++;
- }
+ wh.major = simple_strtoul(b, &endp, 10);
+ b = endp;
} else {
return -EINVAL;
}
wh.minor = ~0;
b++;
} else if (isdigit(*b)) {
- wh.minor = 0;
- while (isdigit(*b)) {
- wh.minor = wh.minor*10+(*b-'0');
- b++;
- }
+ wh.minor = simple_strtoul(b, &endp, 10);
+ b = endp;
} else {
return -EINVAL;
}
}
handle:
- retval = 0;
switch (filetype) {
case DEVCG_ALLOW:
if (!parent_has_perm(devcgroup, &wh))
return 0;
if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode))
return 0;
- dev_cgroup = css_to_devcgroup(task_subsys_state(current,
- devices_subsys_id));
- if (!dev_cgroup)
- return 0;
- spin_lock(&dev_cgroup->lock);
- list_for_each_entry(wh, &dev_cgroup->whitelist, list) {
+ rcu_read_lock();
+
+ dev_cgroup = task_devcgroup(current);
+
+ list_for_each_entry_rcu(wh, &dev_cgroup->whitelist, list) {
if (wh->type & DEV_ALL)
goto acc_check;
if ((wh->type & DEV_BLOCK) && !S_ISBLK(inode->i_mode))
continue;
if ((mask & MAY_READ) && !(wh->access & ACC_READ))
continue;
- spin_unlock(&dev_cgroup->lock);
+ rcu_read_unlock();
return 0;
}
- spin_unlock(&dev_cgroup->lock);
+
+ rcu_read_unlock();
return -EPERM;
}
struct dev_cgroup *dev_cgroup;
struct dev_whitelist_item *wh;
- dev_cgroup = css_to_devcgroup(task_subsys_state(current,
- devices_subsys_id));
- if (!dev_cgroup)
+ if (!S_ISBLK(mode) && !S_ISCHR(mode))
return 0;
- spin_lock(&dev_cgroup->lock);
- list_for_each_entry(wh, &dev_cgroup->whitelist, list) {
+ rcu_read_lock();
+
+ dev_cgroup = task_devcgroup(current);
+
+ list_for_each_entry_rcu(wh, &dev_cgroup->whitelist, list) {
if (wh->type & DEV_ALL)
goto acc_check;
if ((wh->type & DEV_BLOCK) && !S_ISBLK(mode))
acc_check:
if (!(wh->access & ACC_MKNOD))
continue;
- spin_unlock(&dev_cgroup->lock);
+ rcu_read_unlock();
return 0;
}
- spin_unlock(&dev_cgroup->lock);
+
+ rcu_read_unlock();
+
return -EPERM;
}
Code Review / linux-2.6.git / blobdiff