/*
- * dev_cgroup.c - device cgroup subsystem
+ * device_cgroup.c - device cgroup subsystem
*
* Copyright 2007 IBM Corp
*/
#include <linux/ctype.h>
#include <linux/list.h>
#include <linux/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/rcupdate.h>
+#include <linux/mutex.h>
#define ACC_MKNOD 1
#define ACC_READ 2
#define DEV_CHAR 2
#define DEV_ALL 4 /* this represents all devices */
+static DEFINE_MUTEX(devcgroup_mutex);
+
/*
* 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 devcgroup_mutex 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)
+{
+ return container_of(s, struct dev_cgroup, css);
+}
+
static inline struct dev_cgroup *cgroup_to_devcgroup(struct cgroup *cgroup)
{
- return container_of(cgroup_subsys_state(cgroup, devices_subsys_id),
- struct dev_cgroup, css);
+ return css_to_devcgroup(cgroup_subsys_state(cgroup, devices_subsys_id));
+}
+
+static inline struct dev_cgroup *task_devcgroup(struct task_struct *task)
+{
+ return css_to_devcgroup(task_subsys_state(task, devices_subsys_id));
}
struct cgroup_subsys devices_subsys;
}
/*
- * called under cgroup_lock()
+ * called under devcgroup_mutex
*/
static int dev_whitelist_copy(struct list_head *dest, struct list_head *orig)
{
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
+ * called under devcgroup_mutex
*/
static int dev_whitelist_add(struct dev_cgroup *dev_cgroup,
struct dev_whitelist_item *wh)
{
- struct dev_whitelist_item *whcopy;
+ 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_add_tail(&whcopy->list, &dev_cgroup->whitelist);
- spin_unlock(&dev_cgroup->lock);
+ list_for_each_entry(walk, &dev_cgroup->whitelist, list) {
+ if (walk->type != wh->type)
+ continue;
+ if (walk->major != wh->major)
+ continue;
+ if (walk->minor != wh->minor)
+ continue;
+
+ walk->access |= wh->access;
+ kfree(whcopy);
+ whcopy = NULL;
+ }
+
+ if (whcopy != NULL)
+ list_add_tail_rcu(&whcopy->list, &dev_cgroup->whitelist);
return 0;
}
/*
- * called under cgroup_lock()
- * since the list is visible to other tasks, we need the spinlock also
+ * called under devcgroup_mutex
*/
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);
+ kfree_rcu(walk, rcu);
}
}
- 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);
+ mutex_lock(&devcgroup_mutex);
ret = dev_whitelist_copy(&dev_cgroup->whitelist,
&parent_dev_cgroup->whitelist);
+ mutex_unlock(&devcgroup_mutex);
if (ret) {
kfree(dev_cgroup);
return ERR_PTR(ret);
}
}
- spin_lock_init(&dev_cgroup->lock);
return &dev_cgroup->css;
}
#define DEVCG_ALLOW 1
#define DEVCG_DENY 2
+#define DEVCG_LIST 3
+
+#define MAJMINLEN 13
+#define ACCLEN 4
static void set_access(char *acc, short access)
{
int idx = 0;
- memset(acc, 0, 4);
+ memset(acc, 0, ACCLEN);
if (access & ACC_READ)
acc[idx++] = 'r';
if (access & ACC_WRITE)
return 'X';
}
-static void set_majmin(char *str, int len, unsigned m)
+static void set_majmin(char *str, unsigned m)
{
- memset(str, 0, len);
if (m == ~0)
- sprintf(str, "*");
+ strcpy(str, "*");
else
- snprintf(str, len, "%d", m);
+ sprintf(str, "%u", m);
}
-static char *print_whitelist(struct dev_cgroup *devcgroup, int *len)
+static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft,
+ struct seq_file *m)
{
- char *buf, *s, acc[4];
+ struct dev_cgroup *devcgroup = cgroup_to_devcgroup(cgroup);
struct dev_whitelist_item *wh;
- int ret;
- int count = 0;
- char maj[10], min[10];
+ char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN];
- buf = kmalloc(4096, GFP_KERNEL);
- if (!buf)
- return ERR_PTR(-ENOMEM);
- s = buf;
- *s = '\0';
- *len = 0;
-
- 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, 10, wh->major);
- set_majmin(min, 10, wh->minor);
- ret = snprintf(s, 4095-(s-buf), "%c %s:%s %s\n",
- type_to_char(wh->type), maj, min, acc);
- if (s+ret >= buf+4095) {
- kfree(buf);
- buf = ERR_PTR(-ENOMEM);
- break;
- }
- s += ret;
- *len += ret;
- count++;
+ 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);
-
- return buf;
-}
+ rcu_read_unlock();
-static ssize_t devcgroup_access_read(struct cgroup *cgroup,
- struct cftype *cft, struct file *file,
- char __user *userbuf, size_t nbytes, loff_t *ppos)
-{
- struct dev_cgroup *devcgroup = cgroup_to_devcgroup(cgroup);
- int filetype = cft->private;
- char *buffer;
- int uninitialized_var(len);
- int retval;
-
- if (filetype != DEVCG_ALLOW)
- return -EINVAL;
- buffer = print_whitelist(devcgroup, &len);
- if (IS_ERR(buffer))
- return PTR_ERR(buffer);
-
- retval = simple_read_from_buffer(userbuf, nbytes, ppos, buffer, len);
- kfree(buffer);
- return retval;
+ return 0;
}
/*
* does the access granted to dev_cgroup c contain the access
* requested in whitelist item refwh.
* return 1 if yes, 0 if no.
- * call with c->lock held
+ * call with devcgroup_mutex held
*/
static int may_access_whitelist(struct dev_cgroup *c,
struct dev_whitelist_item *refwh)
continue;
if (whitem->minor != ~0 && whitem->minor != refwh->minor)
continue;
- if (refwh->access & (~(whitem->access | ACC_MASK)))
+ if (refwh->access & (~whitem->access))
continue;
return 1;
}
* when adding a new allow rule to a device whitelist, the rule
* must be allowed in the parent device
*/
-static int parent_has_perm(struct cgroup *childcg,
+static int parent_has_perm(struct dev_cgroup *childcg,
struct dev_whitelist_item *wh)
{
- struct cgroup *pcg = childcg->parent;
+ 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);
}
/*
* new access is only allowed if you're in the top-level cgroup, or your
* parent cgroup has the access you're asking for.
*/
-static ssize_t devcgroup_access_write(struct cgroup *cgroup, struct cftype *cft,
- struct file *file, const char __user *userbuf,
- size_t nbytes, loff_t *ppos)
+static int devcgroup_update_access(struct dev_cgroup *devcgroup,
+ int filetype, const char *buffer)
{
- struct cgroup *cur_cgroup;
- struct dev_cgroup *devcgroup, *cur_devcgroup;
- int filetype = cft->private;
- char *buffer, *b;
- int retval = 0, count;
+ const char *b;
+ char *endp;
+ int count;
struct dev_whitelist_item wh;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- devcgroup = cgroup_to_devcgroup(cgroup);
- cur_cgroup = task_cgroup(current, devices_subsys.subsys_id);
- cur_devcgroup = cgroup_to_devcgroup(cur_cgroup);
-
- buffer = kmalloc(nbytes+1, GFP_KERNEL);
- if (!buffer)
- return -ENOMEM;
-
- if (copy_from_user(buffer, userbuf, nbytes)) {
- retval = -EFAULT;
- goto out1;
- }
- buffer[nbytes] = 0; /* nul-terminate */
-
- cgroup_lock();
- if (cgroup_is_removed(cgroup)) {
- retval = -ENODEV;
- goto out2;
- }
-
memset(&wh, 0, sizeof(wh));
b = buffer;
case 'a':
wh.type = DEV_ALL;
wh.access = ACC_MASK;
+ wh.major = ~0;
+ wh.minor = ~0;
goto handle;
case 'b':
wh.type = DEV_BLOCK;
wh.type = DEV_CHAR;
break;
default:
- retval = -EINVAL;
- goto out2;
+ return -EINVAL;
}
b++;
- if (!isspace(*b)) {
- retval = -EINVAL;
- goto out2;
- }
+ if (!isspace(*b))
+ return -EINVAL;
b++;
if (*b == '*') {
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 {
- retval = -EINVAL;
- goto out2;
- }
- if (*b != ':') {
- retval = -EINVAL;
- goto out2;
+ return -EINVAL;
}
+ if (*b != ':')
+ return -EINVAL;
b++;
/* read minor */
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 {
- retval = -EINVAL;
- goto out2;
- }
- if (!isspace(*b)) {
- retval = -EINVAL;
- goto out2;
+ return -EINVAL;
}
+ if (!isspace(*b))
+ return -EINVAL;
for (b++, count = 0; count < 3; count++, b++) {
switch (*b) {
case 'r':
count = 3;
break;
default:
- retval = -EINVAL;
- goto out2;
+ return -EINVAL;
}
}
handle:
- retval = 0;
switch (filetype) {
case DEVCG_ALLOW:
- if (!parent_has_perm(cgroup, &wh))
- retval = -EPERM;
- else
- retval = dev_whitelist_add(devcgroup, &wh);
- break;
+ if (!parent_has_perm(devcgroup, &wh))
+ return -EPERM;
+ return dev_whitelist_add(devcgroup, &wh);
case DEVCG_DENY:
dev_whitelist_rm(devcgroup, &wh);
break;
default:
- retval = -EINVAL;
- goto out2;
+ return -EINVAL;
}
+ return 0;
+}
- if (retval == 0)
- retval = nbytes;
+static int devcgroup_access_write(struct cgroup *cgrp, struct cftype *cft,
+ const char *buffer)
+{
+ int retval;
-out2:
- cgroup_unlock();
-out1:
- kfree(buffer);
+ mutex_lock(&devcgroup_mutex);
+ retval = devcgroup_update_access(cgroup_to_devcgroup(cgrp),
+ cft->private, buffer);
+ mutex_unlock(&devcgroup_mutex);
return retval;
}
static struct cftype dev_cgroup_files[] = {
{
.name = "allow",
- .read = devcgroup_access_read,
- .write = devcgroup_access_write,
+ .write_string = devcgroup_access_write,
.private = DEVCG_ALLOW,
},
{
.name = "deny",
- .write = devcgroup_access_write,
+ .write_string = devcgroup_access_write,
.private = DEVCG_DENY,
},
+ {
+ .name = "list",
+ .read_seq_string = devcgroup_seq_read,
+ .private = DEVCG_LIST,
+ },
};
static int devcgroup_populate(struct cgroup_subsys *ss,
.name = "devices",
.can_attach = devcgroup_can_attach,
.create = devcgroup_create,
- .destroy = devcgroup_destroy,
+ .destroy = devcgroup_destroy,
.populate = devcgroup_populate,
.subsys_id = devices_subsys_id,
};
-int devcgroup_inode_permission(struct inode *inode, int mask)
+int __devcgroup_inode_permission(struct inode *inode, int mask)
{
- struct cgroup *cgroup;
struct dev_cgroup *dev_cgroup;
struct dev_whitelist_item *wh;
- dev_t device = inode->i_rdev;
- if (!device)
- return 0;
- if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode))
- return 0;
- cgroup = task_cgroup(current, devices_subsys.subsys_id);
- dev_cgroup = cgroup_to_devcgroup(cgroup);
- if (!dev_cgroup)
- return 0;
+ rcu_read_lock();
+
+ dev_cgroup = task_devcgroup(current);
- spin_lock(&dev_cgroup->lock);
- list_for_each_entry(wh, &dev_cgroup->whitelist, list) {
+ list_for_each_entry_rcu(wh, &dev_cgroup->whitelist, list) {
if (wh->type & DEV_ALL)
- goto acc_check;
+ goto found;
if ((wh->type & DEV_BLOCK) && !S_ISBLK(inode->i_mode))
continue;
if ((wh->type & DEV_CHAR) && !S_ISCHR(inode->i_mode))
continue;
if (wh->minor != ~0 && wh->minor != iminor(inode))
continue;
-acc_check:
+
if ((mask & MAY_WRITE) && !(wh->access & ACC_WRITE))
continue;
if ((mask & MAY_READ) && !(wh->access & ACC_READ))
continue;
- spin_unlock(&dev_cgroup->lock);
+found:
+ rcu_read_unlock();
return 0;
}
- spin_unlock(&dev_cgroup->lock);
+
+ rcu_read_unlock();
return -EPERM;
}
int devcgroup_inode_mknod(int mode, dev_t dev)
{
- struct cgroup *cgroup;
struct dev_cgroup *dev_cgroup;
struct dev_whitelist_item *wh;
- cgroup = task_cgroup(current, devices_subsys.subsys_id);
- dev_cgroup = cgroup_to_devcgroup(cgroup);
- 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;
+ goto found;
if ((wh->type & DEV_BLOCK) && !S_ISBLK(mode))
continue;
if ((wh->type & DEV_CHAR) && !S_ISCHR(mode))
continue;
if (wh->minor != ~0 && wh->minor != MINOR(dev))
continue;
-acc_check:
+
if (!(wh->access & ACC_MKNOD))
continue;
- spin_unlock(&dev_cgroup->lock);
+found:
+ rcu_read_unlock();
return 0;
}
- spin_unlock(&dev_cgroup->lock);
+
+ rcu_read_unlock();
+
return -EPERM;
}
Code Review / linux-2.6.git / blobdiff