1 files changed, 177 insertions, 84 deletions

diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index c123628d3f8..d9d69e6930e 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -58,19 +58,7 @@ static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s)
 
 static inline struct dev_cgroup *task_devcgroup(struct task_struct *task)
 {
-	return css_to_devcgroup(task_css(task, devices_subsys_id));
-}
-
-struct cgroup_subsys devices_subsys;
-
-static int devcgroup_can_attach(struct cgroup_subsys_state *new_css,
-				struct cgroup_taskset *set)
-{
-	struct task_struct *task = cgroup_taskset_first(set);
-
-	if (current != task && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-	return 0;
+	return css_to_devcgroup(task_css(task, devices_cgrp_id));
 }
 
 /*
@@ -194,7 +182,7 @@ static inline bool is_devcg_online(const struct dev_cgroup *devcg)
 static int devcgroup_online(struct cgroup_subsys_state *css)
 {
 	struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
-	struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css_parent(css));
+	struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css->parent);
 	int ret = 0;
 
 	mutex_lock(&devcgroup_mutex);
@@ -284,10 +272,9 @@ static void set_majmin(char *str, unsigned m)
 		sprintf(str, "%u", m);
 }
 
-static int devcgroup_seq_read(struct cgroup_subsys_state *css,
-			      struct cftype *cft, struct seq_file *m)
+static int devcgroup_seq_show(struct seq_file *m, void *v)
 {
-	struct dev_cgroup *devcgroup = css_to_devcgroup(css);
+	struct dev_cgroup *devcgroup = css_to_devcgroup(seq_css(m));
 	struct dev_exception_item *ex;
 	char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN];
 
@@ -319,57 +306,138 @@ static int devcgroup_seq_read(struct cgroup_subsys_state *css,
 }
 
 /**
- * may_access - verifies if a new exception is part of what is allowed
- *		by a dev cgroup based on the default policy +
- *		exceptions. This is used to make sure a child cgroup
- *		won't have more privileges than its parent or to
- *		verify if a certain access is allowed.
- * @dev_cgroup: dev cgroup to be tested against
- * @refex: new exception
- * @behavior: behavior of the exception
+ * match_exception	- iterates the exception list trying to find a complete match
+ * @exceptions: list of exceptions
+ * @type: device type (DEV_BLOCK or DEV_CHAR)
+ * @major: device file major number, ~0 to match all
+ * @minor: device file minor number, ~0 to match all
+ * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD)
+ *
+ * It is considered a complete match if an exception is found that will
+ * contain the entire range of provided parameters.
+ *
+ * Return: true in case it matches an exception completely
  */
-static bool may_access(struct dev_cgroup *dev_cgroup,
-		       struct dev_exception_item *refex,
-		       enum devcg_behavior behavior)
+static bool match_exception(struct list_head *exceptions, short type,
+			    u32 major, u32 minor, short access)
 {
 	struct dev_exception_item *ex;
-	bool match = false;
 
-	rcu_lockdep_assert(rcu_read_lock_held() ||
-			   lockdep_is_held(&devcgroup_mutex),
-			   "device_cgroup::may_access() called without proper synchronization");
+	list_for_each_entry_rcu(ex, exceptions, list) {
+		if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
+			continue;
+		if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR))
+			continue;
+		if (ex->major != ~0 && ex->major != major)
+			continue;
+		if (ex->minor != ~0 && ex->minor != minor)
+			continue;
+		/* provided access cannot have more than the exception rule */
+		if (access & (~ex->access))
+			continue;
+		return true;
+	}
+	return false;
+}
+
+/**
+ * match_exception_partial - iterates the exception list trying to find a partial match
+ * @exceptions: list of exceptions
+ * @type: device type (DEV_BLOCK or DEV_CHAR)
+ * @major: device file major number, ~0 to match all
+ * @minor: device file minor number, ~0 to match all
+ * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD)
+ *
+ * It is considered a partial match if an exception's range is found to
+ * contain *any* of the devices specified by provided parameters. This is
+ * used to make sure no extra access is being granted that is forbidden by
+ * any of the exception list.
+ *
+ * Return: true in case the provided range mat matches an exception completely
+ */
+static bool match_exception_partial(struct list_head *exceptions, short type,
+				    u32 major, u32 minor, short access)
+{
+	struct dev_exception_item *ex;
 
-	list_for_each_entry_rcu(ex, &dev_cgroup->exceptions, list) {
-		if ((refex->type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
+	list_for_each_entry_rcu(ex, exceptions, list) {
+		if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
 			continue;
-		if ((refex->type & DEV_CHAR) && !(ex->type & DEV_CHAR))
+		if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR))
 			continue;
-		if (ex->major != ~0 && ex->major != refex->major)
+		/*
+		 * We must be sure that both the exception and the provided
+		 * range aren't masking all devices
+		 */
+		if (ex->major != ~0 && major != ~0 && ex->major != major)
 			continue;
-		if (ex->minor != ~0 && ex->minor != refex->minor)
+		if (ex->minor != ~0 && minor != ~0 && ex->minor != minor)
 			continue;
-		if (refex->access & (~ex->access))
+		/*
+		 * In order to make sure the provided range isn't matching
+		 * an exception, all its access bits shouldn't match the
+		 * exception's access bits
+		 */
+		if (!(access & ex->access))
 			continue;
-		match = true;
-		break;
+		return true;
 	}
+	return false;
+}
+
+/**
+ * verify_new_ex - verifies if a new exception is allowed by parent cgroup's permissions
+ * @dev_cgroup: dev cgroup to be tested against
+ * @refex: new exception
+ * @behavior: behavior of the exception's dev_cgroup
+ *
+ * This is used to make sure a child cgroup won't have more privileges
+ * than its parent
+ */
+static bool verify_new_ex(struct dev_cgroup *dev_cgroup,
+		          struct dev_exception_item *refex,
+		          enum devcg_behavior behavior)
+{
+	bool match = false;
+
+	rcu_lockdep_assert(rcu_read_lock_held() ||
+			   lockdep_is_held(&devcgroup_mutex),
+			   "device_cgroup:verify_new_ex called without proper synchronization");
 
 	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) {
 		if (behavior == DEVCG_DEFAULT_ALLOW) {
-			/* the exception will deny access to certain devices */
+			/*
+			 * new exception in the child doesn't matter, only
+			 * adding extra restrictions
+			 */ 
 			return true;
 		} else {
-			/* the exception will allow access to certain devices */
+			/*
+			 * new exception in the child will add more devices
+			 * that can be acessed, so it can't match any of
+			 * parent's exceptions, even slightly
+			 */ 
+			match = match_exception_partial(&dev_cgroup->exceptions,
+							refex->type,
+							refex->major,
+							refex->minor,
+							refex->access);
+
 			if (match)
-				/*
-				 * a new exception allowing access shouldn't
-				 * match an parent's exception
-				 */
 				return false;
 			return true;
 		}
 	} else {
-		/* only behavior == DEVCG_DEFAULT_DENY allowed here */
+		/*
+		 * Only behavior == DEVCG_DEFAULT_DENY allowed here, therefore
+		 * the new exception will add access to more devices and must
+		 * be contained completely in an parent's exception to be
+		 * allowed
+		 */
+		match = match_exception(&dev_cgroup->exceptions, refex->type,
+					refex->major, refex->minor,
+					refex->access);
+
 		if (match)
 			/* parent has an exception that matches the proposed */
 			return true;
@@ -387,11 +455,42 @@ static bool may_access(struct dev_cgroup *dev_cgroup,
 static int parent_has_perm(struct dev_cgroup *childcg,
 				  struct dev_exception_item *ex)
 {
-	struct dev_cgroup *parent = css_to_devcgroup(css_parent(&childcg->css));
+	struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent);
 
 	if (!parent)
 		return 1;
-	return may_access(parent, ex, childcg->behavior);
+	return verify_new_ex(parent, ex, childcg->behavior);
+}
+
+/**
+ * parent_allows_removal - verify if it's ok to remove an exception
+ * @childcg: child cgroup from where the exception will be removed
+ * @ex: exception being removed
+ *
+ * When removing an exception in cgroups with default ALLOW policy, it must
+ * be checked if removing it will give the child cgroup more access than the
+ * parent.
+ *
+ * Return: true if it's ok to remove exception, false otherwise
+ */
+static bool parent_allows_removal(struct dev_cgroup *childcg,
+				  struct dev_exception_item *ex)
+{
+	struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent);
+
+	if (!parent)
+		return true;
+
+	/* It's always allowed to remove access to devices */
+	if (childcg->behavior == DEVCG_DEFAULT_DENY)
+		return true;
+
+	/*
+	 * Make sure you're not removing part or a whole exception existing in
+	 * the parent cgroup
+	 */
+	return !match_exception_partial(&parent->exceptions, ex->type,
+					ex->major, ex->minor, ex->access);
 }
 
 /**
@@ -488,13 +587,6 @@ static int propagate_exception(struct dev_cgroup *devcg_root,
 	return rc;
 }
 
-static inline bool has_children(struct dev_cgroup *devcgroup)
-{
-	struct cgroup *cgrp = devcgroup->css.cgroup;
-
-	return !list_empty(&cgrp->children);
-}
-
 /*
  * Modify the exception list using allow/deny rules.
  * CAP_SYS_ADMIN is needed for this.  It's at least separate from CAP_MKNOD
@@ -509,13 +601,13 @@ static inline bool has_children(struct dev_cgroup *devcgroup)
  * parent cgroup has the access you're asking for.
  */
 static int devcgroup_update_access(struct dev_cgroup *devcgroup,
-				   int filetype, const char *buffer)
+				   int filetype, char *buffer)
 {
 	const char *b;
 	char temp[12];		/* 11 + 1 characters needed for a u32 */
 	int count, rc = 0;
 	struct dev_exception_item ex;
-	struct dev_cgroup *parent = css_to_devcgroup(css_parent(&devcgroup->css));
+	struct dev_cgroup *parent = css_to_devcgroup(devcgroup->css.parent);
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -527,7 +619,7 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 	case 'a':
 		switch (filetype) {
 		case DEVCG_ALLOW:
-			if (has_children(devcgroup))
+			if (css_has_online_children(&devcgroup->css))
 				return -EINVAL;
 
 			if (!may_allow_all(parent))
@@ -543,7 +635,7 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 				return rc;
 			break;
 		case DEVCG_DENY:
-			if (has_children(devcgroup))
+			if (css_has_online_children(&devcgroup->css))
 				return -EINVAL;
 
 			dev_exception_clean(devcgroup);
@@ -629,17 +721,21 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 
 	switch (filetype) {
 	case DEVCG_ALLOW:
-		if (!parent_has_perm(devcgroup, &ex))
-			return -EPERM;
 		/*
 		 * If the default policy is to allow by default, try to remove
 		 * an matching exception instead. And be silent about it: we
 		 * don't want to break compatibility
 		 */
 		if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
+			/* Check if the parent allows removing it first */
+			if (!parent_allows_removal(devcgroup, &ex))
+				return -EPERM;
 			dev_exception_rm(devcgroup, &ex);
-			return 0;
+			break;
 		}
+
+		if (!parent_has_perm(devcgroup, &ex))
+			return -EPERM;
 		rc = dev_exception_add(devcgroup, &ex);
 		break;
 	case DEVCG_DENY:
@@ -664,45 +760,42 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 	return rc;
 }
 
-static int devcgroup_access_write(struct cgroup_subsys_state *css,
-				  struct cftype *cft, const char *buffer)
+static ssize_t devcgroup_access_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
 {
 	int retval;
 
 	mutex_lock(&devcgroup_mutex);
-	retval = devcgroup_update_access(css_to_devcgroup(css),
-					 cft->private, buffer);
+	retval = devcgroup_update_access(css_to_devcgroup(of_css(of)),
+					 of_cft(of)->private, strstrip(buf));
 	mutex_unlock(&devcgroup_mutex);
-	return retval;
+	return retval ?: nbytes;
 }
 
 static struct cftype dev_cgroup_files[] = {
 	{
 		.name = "allow",
-		.write_string  = devcgroup_access_write,
+		.write = devcgroup_access_write,
 		.private = DEVCG_ALLOW,
 	},
 	{
 		.name = "deny",
-		.write_string = devcgroup_access_write,
+		.write = devcgroup_access_write,
 		.private = DEVCG_DENY,
 	},
 	{
 		.name = "list",
-		.read_seq_string = devcgroup_seq_read,
+		.seq_show = devcgroup_seq_show,
 		.private = DEVCG_LIST,
 	},
 	{ }	/* terminate */
 };
 
-struct cgroup_subsys devices_subsys = {
-	.name = "devices",
-	.can_attach = devcgroup_can_attach,
+struct cgroup_subsys devices_cgrp_subsys = {
 	.css_alloc = devcgroup_css_alloc,
 	.css_free = devcgroup_css_free,
 	.css_online = devcgroup_online,
 	.css_offline = devcgroup_offline,
-	.subsys_id = devices_subsys_id,
 	.base_cftypes = dev_cgroup_files,
 };
 
@@ -720,18 +813,18 @@ static int __devcgroup_check_permission(short type, u32 major, u32 minor,
 				        short access)
 {
 	struct dev_cgroup *dev_cgroup;
-	struct dev_exception_item ex;
-	int rc;
-
-	memset(&ex, 0, sizeof(ex));
-	ex.type = type;
-	ex.major = major;
-	ex.minor = minor;
-	ex.access = access;
+	bool rc;
 
 	rcu_read_lock();
 	dev_cgroup = task_devcgroup(current);
-	rc = may_access(dev_cgroup, &ex, dev_cgroup->behavior);
+	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW)
+		/* Can't match any of the exceptions, even partially */
+		rc = !match_exception_partial(&dev_cgroup->exceptions,
+					      type, major, minor, access);
+	else
+		/* Need to match completely one exception to be allowed */
+		rc = match_exception(&dev_cgroup->exceptions, type, major,
+				     minor, access);
 	rcu_read_unlock();
 
 	if (!rc)