Merge branch 'for-5.7-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:

 - Reverted stricter synchronization for cgroup recursive stats which
   was prepping it for event counter usage which never got merged. The
   change was causing performation regressions in some cases.

 - Restore bpf-based device-cgroup operation even when cgroup1 device
   cgroup is disabled.

 - An out-param init fix.

* 'for-5.7-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  device_cgroup: Cleanup cgroup eBPF device filter code
  xattr: fix uninitialized out-param
  Revert "cgroup: Add memory barriers to plug cgroup_rstat_updated() race window"

Author: torvalds

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -1050,7 +1050,7 @@ void kfd_dec_compute_active(struct kfd_dev *dev);
 /* Check with device cgroup if @kfd device is accessible */
 static inline int kfd_devcgroup_check_permission(struct kfd_dev *kfd)
 {
-#if defined(CONFIG_CGROUP_DEVICE)
+#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
 	struct drm_device *ddev = kfd->ddev;
 
 	return devcgroup_check_permission(DEVCG_DEV_CHAR, ddev->driver->major,

fs/xattr.c

@@ -876,6 +876,9 @@ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
 	struct simple_xattr *new_xattr = NULL;
 	int err = 0;
 
+	if (removed_size)
+		*removed_size = -1;
+
 	/* value == NULL means remove */
 	if (value) {
 		new_xattr = simple_xattr_alloc(value, size);
@@ -914,9 +917,6 @@ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
 		list_add(&new_xattr->list, &xattrs->head);
 		xattr = NULL;
 	}
-
-	if (removed_size)
-		*removed_size = -1;
 out:
 	spin_unlock(&xattrs->lock);
 	if (xattr) {

include/linux/device_cgroup.h

@@ -1,6 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/fs.h>
-#include <linux/bpf-cgroup.h>
 
 #define DEVCG_ACC_MKNOD 1
 #define DEVCG_ACC_READ  2
@@ -11,16 +10,10 @@
 #define DEVCG_DEV_CHAR  2
 #define DEVCG_DEV_ALL   4  /* this represents all devices */
 
-#ifdef CONFIG_CGROUP_DEVICE
-int devcgroup_check_permission(short type, u32 major, u32 minor,
-			       short access);
-#else
-static inline int devcgroup_check_permission(short type, u32 major, u32 minor,
-					     short access)
-{ return 0; }
-#endif
 
 #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
+int devcgroup_check_permission(short type, u32 major, u32 minor,
+			       short access);
 static inline int devcgroup_inode_permission(struct inode *inode, int mask)
 {
 	short type, access = 0;
@@ -61,6 +54,9 @@ static inline int devcgroup_inode_mknod(int mode, dev_t dev)
 }
 
 #else
+static inline int devcgroup_check_permission(short type, u32 major, u32 minor,
+			       short access)
+{ return 0; }
 static inline int devcgroup_inode_permission(struct inode *inode, int mask)
 { return 0; }
 static inline int devcgroup_inode_mknod(int mode, dev_t dev)

kernel/cgroup/rstat.c

@@ -33,12 +33,9 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
 		return;
 
 	/*
-	 * Paired with the one in cgroup_rstat_cpu_pop_updated().  Either we
-	 * see NULL updated_next or they see our updated stat.
-	 */
-	smp_mb();
-
-	/*
+	 * Speculative already-on-list test. This may race leading to
+	 * temporary inaccuracies, which is fine.
+	 *
 	 * Because @parent's updated_children is terminated with @parent
 	 * instead of NULL, we can tell whether @cgrp is on the list by
 	 * testing the next pointer for NULL.
@@ -134,13 +131,6 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 		*nextp = rstatc->updated_next;
 		rstatc->updated_next = NULL;
 
-		/*
-		 * Paired with the one in cgroup_rstat_cpu_updated().
-		 * Either they see NULL updated_next or we see their
-		 * updated stat.
-		 */
-		smp_mb();
-
 		return pos;
 	}
 

security/Makefile

@@ -30,7 +30,7 @@ obj-$(CONFIG_SECURITY_YAMA)		+= yama/
 obj-$(CONFIG_SECURITY_LOADPIN)		+= loadpin/
 obj-$(CONFIG_SECURITY_SAFESETID)       += safesetid/
 obj-$(CONFIG_SECURITY_LOCKDOWN_LSM)	+= lockdown/
-obj-$(CONFIG_CGROUP_DEVICE)		+= device_cgroup.o
+obj-$(CONFIG_CGROUPS)			+= device_cgroup.o
 obj-$(CONFIG_BPF_LSM)			+= bpf/
 
 # Object integrity file lists

security/device_cgroup.c

@@ -15,6 +15,8 @@
 #include <linux/rcupdate.h>
 #include <linux/mutex.h>
 
+#ifdef CONFIG_CGROUP_DEVICE
+
 static DEFINE_MUTEX(devcgroup_mutex);
 
 enum devcg_behavior {
@@ -792,7 +794,7 @@ struct cgroup_subsys devices_cgrp_subsys = {
 };
 
 /**
- * __devcgroup_check_permission - checks if an inode operation is permitted
+ * devcgroup_legacy_check_permission - checks if an inode operation is permitted
  * @dev_cgroup: the dev cgroup to be tested against
  * @type: device type
  * @major: device major number
@@ -801,7 +803,7 @@ struct cgroup_subsys devices_cgrp_subsys = {
  *
  * returns 0 on success, -EPERM case the operation is not permitted
  */
-static int __devcgroup_check_permission(short type, u32 major, u32 minor,
+static int devcgroup_legacy_check_permission(short type, u32 major, u32 minor,
 					short access)
 {
 	struct dev_cgroup *dev_cgroup;
@@ -825,13 +827,24 @@ static int __devcgroup_check_permission(short type, u32 major, u32 minor,
 	return 0;
 }
 
+#endif /* CONFIG_CGROUP_DEVICE */
+
+#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
+
 int devcgroup_check_permission(short type, u32 major, u32 minor, short access)
 {
 	int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access);
 
 	if (rc)
 		return -EPERM;
 
-	return __devcgroup_check_permission(type, major, minor, access);
+	#ifdef CONFIG_CGROUP_DEVICE
+	return devcgroup_legacy_check_permission(type, major, minor, access);
+
+	#else /* CONFIG_CGROUP_DEVICE */
+	return 0;
+
+	#endif /* CONFIG_CGROUP_DEVICE */
 }
 EXPORT_SYMBOL(devcgroup_check_permission);
+#endif /* defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) */