1 files changed, 281 insertions, 199 deletions

diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index e8aad69f0d69..7fec575d32d6 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -1,9 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * device_cgroup.c - device cgroup subsystem
  *
  * Copyright 2007 IBM Corp
  */
 
+#include <linux/bpf-cgroup.h>
 #include <linux/device_cgroup.h>
 #include <linux/cgroup.h>
 #include <linux/ctype.h>
@@ -14,14 +16,7 @@
 #include <linux/rcupdate.h>
 #include <linux/mutex.h>
 
-#define ACC_MKNOD 1
-#define ACC_READ  2
-#define ACC_WRITE 4
-#define ACC_MASK (ACC_MKNOD | ACC_READ | ACC_WRITE)
-
-#define DEV_BLOCK 1
-#define DEV_CHAR  2
-#define DEV_ALL   4  /* this represents all devices */
+#ifdef CONFIG_CGROUP_DEVICE
 
 static DEFINE_MUTEX(devcgroup_mutex);
 
@@ -53,29 +48,12 @@ struct dev_cgroup {
 
 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 css_to_devcgroup(cgroup_subsys_state(cgroup, devices_subsys_id));
+	return s ? container_of(s, struct dev_cgroup, css) : NULL;
 }
 
 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;
-
-static int devcgroup_can_attach(struct cgroup *new_cgrp,
-				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));
 }
 
 /*
@@ -104,6 +82,17 @@ free_and_exit:
 	return -ENOMEM;
 }
 
+static void dev_exceptions_move(struct list_head *dest, struct list_head *orig)
+{
+	struct dev_exception_item *ex, *tmp;
+
+	lockdep_assert_held(&devcgroup_mutex);
+
+	list_for_each_entry_safe(ex, tmp, orig, list) {
+		list_move_tail(&ex->list, dest);
+	}
+}
+
 /*
  * called under devcgroup_mutex
  */
@@ -193,18 +182,16 @@ static inline bool is_devcg_online(const struct dev_cgroup *devcg)
 /**
  * devcgroup_online - initializes devcgroup's behavior and exceptions based on
  * 		      parent's
- * @cgroup: cgroup getting online
+ * @css: css getting online
  * returns 0 in case of success, error code otherwise
  */
-static int devcgroup_online(struct cgroup *cgroup)
+static int devcgroup_online(struct cgroup_subsys_state *css)
 {
-	struct dev_cgroup *dev_cgroup, *parent_dev_cgroup = NULL;
+	struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
+	struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css->parent);
 	int ret = 0;
 
 	mutex_lock(&devcgroup_mutex);
-	dev_cgroup = cgroup_to_devcgroup(cgroup);
-	if (cgroup->parent)
-		parent_dev_cgroup = cgroup_to_devcgroup(cgroup->parent);
 
 	if (parent_dev_cgroup == NULL)
 		dev_cgroup->behavior = DEVCG_DEFAULT_ALLOW;
@@ -219,9 +206,9 @@ static int devcgroup_online(struct cgroup *cgroup)
 	return ret;
 }
 
-static void devcgroup_offline(struct cgroup *cgroup)
+static void devcgroup_offline(struct cgroup_subsys_state *css)
 {
-	struct dev_cgroup *dev_cgroup = cgroup_to_devcgroup(cgroup);
+	struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
 
 	mutex_lock(&devcgroup_mutex);
 	dev_cgroup->behavior = DEVCG_DEFAULT_NONE;
@@ -229,9 +216,10 @@ static void devcgroup_offline(struct cgroup *cgroup)
 }
 
 /*
- * called from kernel/cgroup.c with cgroup_lock() held.
+ * called from kernel/cgroup/cgroup.c with cgroup_lock() held.
  */
-static struct cgroup_subsys_state *devcgroup_css_alloc(struct cgroup *cgroup)
+static struct cgroup_subsys_state *
+devcgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
 	struct dev_cgroup *dev_cgroup;
 
@@ -244,11 +232,10 @@ static struct cgroup_subsys_state *devcgroup_css_alloc(struct cgroup *cgroup)
 	return &dev_cgroup->css;
 }
 
-static void devcgroup_css_free(struct cgroup *cgroup)
+static void devcgroup_css_free(struct cgroup_subsys_state *css)
 {
-	struct dev_cgroup *dev_cgroup;
+	struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
 
-	dev_cgroup = cgroup_to_devcgroup(cgroup);
 	__dev_exception_clean(dev_cgroup);
 	kfree(dev_cgroup);
 }
@@ -257,46 +244,40 @@ static void devcgroup_css_free(struct cgroup *cgroup)
 #define DEVCG_DENY 2
 #define DEVCG_LIST 3
 
-#define MAJMINLEN 13
-#define ACCLEN 4
-
-static void set_access(char *acc, short access)
+static void seq_putaccess(struct seq_file *m, short access)
 {
-	int idx = 0;
-	memset(acc, 0, ACCLEN);
-	if (access & ACC_READ)
-		acc[idx++] = 'r';
-	if (access & ACC_WRITE)
-		acc[idx++] = 'w';
-	if (access & ACC_MKNOD)
-		acc[idx++] = 'm';
+	if (access & DEVCG_ACC_READ)
+		seq_putc(m, 'r');
+	if (access & DEVCG_ACC_WRITE)
+		seq_putc(m, 'w');
+	if (access & DEVCG_ACC_MKNOD)
+		seq_putc(m, 'm');
 }
 
-static char type_to_char(short type)
+static void seq_puttype(struct seq_file *m, short type)
 {
-	if (type == DEV_ALL)
-		return 'a';
-	if (type == DEV_CHAR)
-		return 'c';
-	if (type == DEV_BLOCK)
-		return 'b';
-	return 'X';
+	if (type == DEVCG_DEV_ALL)
+		seq_putc(m, 'a');
+	else if (type == DEVCG_DEV_CHAR)
+		seq_putc(m, 'c');
+	else if (type == DEVCG_DEV_BLOCK)
+		seq_putc(m, 'b');
+	else
+		seq_putc(m, 'X');
 }
 
-static void set_majmin(char *str, unsigned m)
+static void seq_putversion(struct seq_file *m, unsigned int version)
 {
-	if (m == ~0)
-		strcpy(str, "*");
+	if (version == ~0)
+		seq_putc(m, '*');
 	else
-		sprintf(str, "%u", m);
+		seq_printf(m, "%u", version);
 }
 
-static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft,
-				struct seq_file *m)
+static int devcgroup_seq_show(struct seq_file *m, void *v)
 {
-	struct dev_cgroup *devcgroup = cgroup_to_devcgroup(cgroup);
+	struct dev_cgroup *devcgroup = css_to_devcgroup(seq_css(m));
 	struct dev_exception_item *ex;
-	char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN];
 
 	rcu_read_lock();
 	/*
@@ -306,18 +287,17 @@ static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft,
 	 * This way, the file remains as a "whitelist of devices"
 	 */
 	if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
-		set_access(acc, ACC_MASK);
-		set_majmin(maj, ~0);
-		set_majmin(min, ~0);
-		seq_printf(m, "%c %s:%s %s\n", type_to_char(DEV_ALL),
-			   maj, min, acc);
+		seq_puts(m, "a *:* rwm\n");
 	} else {
 		list_for_each_entry_rcu(ex, &devcgroup->exceptions, list) {
-			set_access(acc, ex->access);
-			set_majmin(maj, ex->major);
-			set_majmin(min, ex->minor);
-			seq_printf(m, "%c %s:%s %s\n", type_to_char(ex->type),
-				   maj, min, acc);
+			seq_puttype(m, ex->type);
+			seq_putc(m, ' ');
+			seq_putversion(m, ex->major);
+			seq_putc(m, ':');
+			seq_putversion(m, ex->minor);
+			seq_putc(m, ' ');
+			seq_putaccess(m, ex->access);
+			seq_putc(m, '\n');
 		}
 	}
 	rcu_read_unlock();
@@ -326,57 +306,139 @@ static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft,
 }
 
 /**
- * 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 (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR)
+ * @major: device file major number, ~0 to match all
+ * @minor: device file minor number, ~0 to match all
+ * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_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 & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK))
+			continue;
+		if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_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 (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR)
+ * @major: device file major number, ~0 to match all
+ * @minor: device file minor number, ~0 to match all
+ * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_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,
+				lockdep_is_held(&devcgroup_mutex)) {
+		if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK))
 			continue;
-		if ((refex->type & DEV_CHAR) && !(ex->type & DEV_CHAR))
+		if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_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_WARN(!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 accessed, 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;
@@ -394,13 +456,42 @@ static bool may_access(struct dev_cgroup *dev_cgroup,
 static int parent_has_perm(struct dev_cgroup *childcg,
 				  struct dev_exception_item *ex)
 {
-	struct cgroup *pcg = childcg->css.cgroup->parent;
-	struct dev_cgroup *parent;
+	struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent);
 
-	if (!pcg)
+	if (!parent)
 		return 1;
-	parent = cgroup_to_devcgroup(pcg);
-	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);
 }
 
 /**
@@ -427,7 +518,7 @@ static inline int may_allow_all(struct dev_cgroup *parent)
  * This is one of the three key functions for hierarchy implementation.
  * This function is responsible for re-evaluating all the cgroup's active
  * exceptions due to a parent's exception change.
- * Refer to Documentation/cgroups/devices.txt for more details.
+ * Refer to Documentation/admin-guide/cgroup-v1/devices.rst for more details.
  */
 static void revalidate_active_exceptions(struct dev_cgroup *devcg)
 {
@@ -451,13 +542,13 @@ static void revalidate_active_exceptions(struct dev_cgroup *devcg)
 static int propagate_exception(struct dev_cgroup *devcg_root,
 			       struct dev_exception_item *ex)
 {
-	struct cgroup *root = devcg_root->css.cgroup, *pos;
+	struct cgroup_subsys_state *pos;
 	int rc = 0;
 
 	rcu_read_lock();
 
-	cgroup_for_each_descendant_pre(pos, root) {
-		struct dev_cgroup *devcg = cgroup_to_devcgroup(pos);
+	css_for_each_descendant_pre(pos, &devcg_root->css) {
+		struct dev_cgroup *devcg = css_to_devcgroup(pos);
 
 		/*
 		 * Because devcgroup_mutex is held, no devcg will become
@@ -465,7 +556,7 @@ static int propagate_exception(struct dev_cgroup *devcg_root,
 		 * methods), and online ones are safe to access outside RCU
 		 * read lock without bumping refcnt.
 		 */
-		if (!is_devcg_online(devcg))
+		if (pos == &devcg_root->css || !is_devcg_online(devcg))
 			continue;
 
 		rcu_read_unlock();
@@ -478,7 +569,7 @@ static int propagate_exception(struct dev_cgroup *devcg_root,
 		    devcg->behavior == DEVCG_DEFAULT_ALLOW) {
 			rc = dev_exception_add(devcg, ex);
 			if (rc)
-				break;
+				return rc;
 		} else {
 			/*
 			 * in the other possible cases:
@@ -497,13 +588,6 @@ 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
@@ -518,45 +602,55 @@ 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 cgroup *p = devcgroup->css.cgroup;
-	struct dev_cgroup *parent = NULL;
+	struct dev_cgroup *parent = css_to_devcgroup(devcgroup->css.parent);
+	struct dev_cgroup tmp_devcgrp;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (p->parent)
-		parent = cgroup_to_devcgroup(p->parent);
-
 	memset(&ex, 0, sizeof(ex));
+	memset(&tmp_devcgrp, 0, sizeof(tmp_devcgrp));
 	b = buffer;
 
 	switch (*b) {
 	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))
 				return -EPERM;
-			dev_exception_clean(devcgroup);
-			devcgroup->behavior = DEVCG_DEFAULT_ALLOW;
-			if (!parent)
+			if (!parent) {
+				devcgroup->behavior = DEVCG_DEFAULT_ALLOW;
+				dev_exception_clean(devcgroup);
 				break;
+			}
 
+			INIT_LIST_HEAD(&tmp_devcgrp.exceptions);
+			rc = dev_exceptions_copy(&tmp_devcgrp.exceptions,
+						 &devcgroup->exceptions);
+			if (rc)
+				return rc;
+			dev_exception_clean(devcgroup);
 			rc = dev_exceptions_copy(&devcgroup->exceptions,
 						 &parent->exceptions);
-			if (rc)
+			if (rc) {
+				dev_exceptions_move(&devcgroup->exceptions,
+						    &tmp_devcgrp.exceptions);
 				return rc;
+			}
+			devcgroup->behavior = DEVCG_DEFAULT_ALLOW;
+			dev_exception_clean(&tmp_devcgrp);
 			break;
 		case DEVCG_DENY:
-			if (has_children(devcgroup))
+			if (css_has_online_children(&devcgroup->css))
 				return -EINVAL;
 
 			dev_exception_clean(devcgroup);
@@ -567,10 +661,10 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 		}
 		return 0;
 	case 'b':
-		ex.type = DEV_BLOCK;
+		ex.type = DEVCG_DEV_BLOCK;
 		break;
 	case 'c':
-		ex.type = DEV_CHAR;
+		ex.type = DEVCG_DEV_CHAR;
 		break;
 	default:
 		return -EINVAL;
@@ -623,13 +717,13 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 	for (b++, count = 0; count < 3; count++, b++) {
 		switch (*b) {
 		case 'r':
-			ex.access |= ACC_READ;
+			ex.access |= DEVCG_ACC_READ;
 			break;
 		case 'w':
-			ex.access |= ACC_WRITE;
+			ex.access |= DEVCG_ACC_WRITE;
 			break;
 		case 'm':
-			ex.access |= ACC_MKNOD;
+			ex.access |= DEVCG_ACC_MKNOD;
 			break;
 		case '\n':
 		case '\0':
@@ -642,17 +736,21 @@ 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:
@@ -677,74 +775,70 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 	return rc;
 }
 
-static int devcgroup_access_write(struct cgroup *cgrp, 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(cgroup_to_devcgroup(cgrp),
-					 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,
+	.legacy_cftypes = dev_cgroup_files,
 };
 
 /**
- * __devcgroup_check_permission - checks if an inode operation is permitted
- * @dev_cgroup: the dev cgroup to be tested against
+ * devcgroup_legacy_check_permission - checks if an inode operation is permitted
  * @type: device type
  * @major: device major number
  * @minor: device minor number
- * @access: combination of ACC_WRITE, ACC_READ and ACC_MKNOD
+ * @access: combination of DEVCG_ACC_WRITE, DEVCG_ACC_READ and DEVCG_ACC_MKNOD
  *
  * returns 0 on success, -EPERM case the operation is not permitted
  */
-static int __devcgroup_check_permission(short type, u32 major, u32 minor,
-				        short access)
+static int devcgroup_legacy_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)
@@ -753,36 +847,24 @@ static int __devcgroup_check_permission(short type, u32 major, u32 minor,
 	return 0;
 }
 
-int __devcgroup_inode_permission(struct inode *inode, int mask)
-{
-	short type, access = 0;
-
-	if (S_ISBLK(inode->i_mode))
-		type = DEV_BLOCK;
-	if (S_ISCHR(inode->i_mode))
-		type = DEV_CHAR;
-	if (mask & MAY_WRITE)
-		access |= ACC_WRITE;
-	if (mask & MAY_READ)
-		access |= ACC_READ;
-
-	return __devcgroup_check_permission(type, imajor(inode), iminor(inode),
-			access);
-}
+#endif /* CONFIG_CGROUP_DEVICE */
+
+#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
 
-int devcgroup_inode_mknod(int mode, dev_t dev)
+int devcgroup_check_permission(short type, u32 major, u32 minor, short access)
 {
-	short type;
+	int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access);
 
-	if (!S_ISBLK(mode) && !S_ISCHR(mode))
-		return 0;
+	if (rc)
+		return rc;
 
-	if (S_ISBLK(mode))
-		type = DEV_BLOCK;
-	else
-		type = DEV_CHAR;
+	#ifdef CONFIG_CGROUP_DEVICE
+	return devcgroup_legacy_check_permission(type, major, minor, access);
 
-	return __devcgroup_check_permission(type, MAJOR(dev), MINOR(dev),
-			ACC_MKNOD);
+	#else /* CONFIG_CGROUP_DEVICE */
+	return 0;
 
+	#endif /* CONFIG_CGROUP_DEVICE */
 }
+EXPORT_SYMBOL(devcgroup_check_permission);
+#endif /* defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) */