cgroup: add xattr support

This is one of the items in the plumber's wish list.

For use cases:

>> What would the use case be for this?
>
> Attaching meta information to services, in an easily discoverable
> way. For example, in systemd we create one cgroup for each service, and
> could then store data like the main pid of the specific service as an
> xattr on the cgroup itself. That way we'd have almost all service state
> in the cgroupfs, which would make it possible to terminate systemd and
> later restart it without losing any state information. But there's more:
> for example, some very peculiar services cannot be terminated on
> shutdown (i.e. fakeraid DM stuff) and it would be really nice if the
> services in question could just mark that on their cgroup, by setting an
> xattr. On the more desktopy side of things there are other
> possibilities: for example there are plans defining what an application
> is along the lines of a cgroup (i.e. an app being a collection of
> processes). With xattrs one could then attach an icon or human readable
> program name on the cgroup.
>
> The key idea is that this would allow attaching runtime meta information
> to cgroups and everything they model (services, apps, vms), that doesn't
> need any complex userspace infrastructure, has good access control
> (i.e. because the file system enforces that anyway, and there's the
> "trusted." xattr namespace), notifications (inotify), and can easily be
> shared among applications.
>
> Lennart

v7:
- no changes
v6:
- remove user xattr namespace, only allow trusted and security
v5:
- check for capabilities before setting/removing xattrs
v4:
- no changes
v3:
- instead of config option, use mount option to enable xattr support

Original-patch-by: Li Zefan <lizefan@huawei.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Lennart Poettering <lpoetter@redhat.com>
Signed-off-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Aristeu Rozanski <aris@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 93 insertions, 7 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 875a7130647c..508b4a97ab19 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -276,7 +276,8 @@ inline int cgroup_is_removed(const struct cgroup *cgrp)
 
 /* bits in struct cgroupfs_root flags field */
 enum {
-	ROOT_NOPREFIX, /* mounted subsystems have no named prefix */
+	ROOT_NOPREFIX,	/* mounted subsystems have no named prefix */
+	ROOT_XATTR,	/* supports extended attributes */
 };
 
 static int cgroup_is_releasable(const struct cgroup *cgrp)
@@ -913,15 +914,19 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		 */
 		BUG_ON(!list_empty(&cgrp->pidlists));
 
+		simple_xattrs_free(&cgrp->xattrs);
+
 		kfree_rcu(cgrp, rcu_head);
 	} else {
 		struct cfent *cfe = __d_cfe(dentry);
 		struct cgroup *cgrp = dentry->d_parent->d_fsdata;
+		struct cftype *cft = cfe->type;
 
 		WARN_ONCE(!list_empty(&cfe->node) &&
 			  cgrp != &cgrp->root->top_cgroup,
 			  "cfe still linked for %s\n", cfe->type->name);
 		kfree(cfe);
+		simple_xattrs_free(&cft->xattrs);
 	}
 	iput(inode);
 }
@@ -1140,6 +1145,8 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_printf(seq, ",%s", ss->name);
 	if (test_bit(ROOT_NOPREFIX, &root->flags))
 		seq_puts(seq, ",noprefix");
+	if (test_bit(ROOT_XATTR, &root->flags))
+		seq_puts(seq, ",xattr");
 	if (strlen(root->release_agent_path))
 		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
 	if (clone_children(&root->top_cgroup))
@@ -1208,6 +1215,10 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			opts->clone_children = true;
 			continue;
 		}
+		if (!strcmp(token, "xattr")) {
+			set_bit(ROOT_XATTR, &opts->flags);
+			continue;
+		}
 		if (!strncmp(token, "release_agent=", 14)) {
 			/* Specifying two release agents is forbidden */
 			if (opts->release_agent)
@@ -1425,6 +1436,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	mutex_init(&cgrp->pidlist_mutex);
 	INIT_LIST_HEAD(&cgrp->event_list);
 	spin_lock_init(&cgrp->event_list_lock);
+	simple_xattrs_init(&cgrp->xattrs);
 }
 
 static void init_cgroup_root(struct cgroupfs_root *root)
@@ -1769,6 +1781,8 @@ static void cgroup_kill_sb(struct super_block *sb) {
 	mutex_unlock(&cgroup_root_mutex);
 	mutex_unlock(&cgroup_mutex);
 
+	simple_xattrs_free(&cgrp->xattrs);
+
 	kill_litter_super(sb);
 	cgroup_drop_root(root);
 }
@@ -2575,6 +2589,64 @@ static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
 	return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
 }
 
+static struct simple_xattrs *__d_xattrs(struct dentry *dentry)
+{
+	if (S_ISDIR(dentry->d_inode->i_mode))
+		return &__d_cgrp(dentry)->xattrs;
+	else
+		return &__d_cft(dentry)->xattrs;
+}
+
+static inline int xattr_enabled(struct dentry *dentry)
+{
+	struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
+	return test_bit(ROOT_XATTR, &root->flags);
+}
+
+static bool is_valid_xattr(const char *name)
+{
+	if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
+	    !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN))
+		return true;
+	return false;
+}
+
+static int cgroup_setxattr(struct dentry *dentry, const char *name,
+			   const void *val, size_t size, int flags)
+{
+	if (!xattr_enabled(dentry))
+		return -EOPNOTSUPP;
+	if (!is_valid_xattr(name))
+		return -EINVAL;
+	return simple_xattr_set(__d_xattrs(dentry), name, val, size, flags);
+}
+
+static int cgroup_removexattr(struct dentry *dentry, const char *name)
+{
+	if (!xattr_enabled(dentry))
+		return -EOPNOTSUPP;
+	if (!is_valid_xattr(name))
+		return -EINVAL;
+	return simple_xattr_remove(__d_xattrs(dentry), name);
+}
+
+static ssize_t cgroup_getxattr(struct dentry *dentry, const char *name,
+			       void *buf, size_t size)
+{
+	if (!xattr_enabled(dentry))
+		return -EOPNOTSUPP;
+	if (!is_valid_xattr(name))
+		return -EINVAL;
+	return simple_xattr_get(__d_xattrs(dentry), name, buf, size);
+}
+
+static ssize_t cgroup_listxattr(struct dentry *dentry, char *buf, size_t size)
+{
+	if (!xattr_enabled(dentry))
+		return -EOPNOTSUPP;
+	return simple_xattr_list(__d_xattrs(dentry), buf, size);
+}
+
 static const struct file_operations cgroup_file_operations = {
 	.read = cgroup_file_read,
 	.write = cgroup_file_write,
@@ -2583,11 +2655,22 @@ static const struct file_operations cgroup_file_operations = {
 	.release = cgroup_file_release,
 };
 
+static const struct inode_operations cgroup_file_inode_operations = {
+	.setxattr = cgroup_setxattr,
+	.getxattr = cgroup_getxattr,
+	.listxattr = cgroup_listxattr,
+	.removexattr = cgroup_removexattr,
+};
+
 static const struct inode_operations cgroup_dir_inode_operations = {
 	.lookup = cgroup_lookup,
 	.mkdir = cgroup_mkdir,
 	.rmdir = cgroup_rmdir,
 	.rename = cgroup_rename,
+	.setxattr = cgroup_setxattr,
+	.getxattr = cgroup_getxattr,
+	.listxattr = cgroup_listxattr,
+	.removexattr = cgroup_removexattr,
 };
 
 static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
@@ -2635,6 +2718,7 @@ static int cgroup_create_file(struct dentry *dentry, umode_t mode,
 	} else if (S_ISREG(mode)) {
 		inode->i_size = 0;
 		inode->i_fop = &cgroup_file_operations;
+		inode->i_op = &cgroup_file_inode_operations;
 	}
 	d_instantiate(dentry, inode);
 	dget(dentry);	/* Extra count - pin the dentry in core */
@@ -2695,7 +2779,7 @@ static umode_t cgroup_file_mode(const struct cftype *cft)
 }
 
 static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
-			   const struct cftype *cft)
+			   struct cftype *cft)
 {
 	struct dentry *dir = cgrp->dentry;
 	struct cgroup *parent = __d_cgrp(dir);
@@ -2705,6 +2789,8 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 	umode_t mode;
 	char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
 
+	simple_xattrs_init(&cft->xattrs);
+
 	/* does @cft->flags tell us to skip creation on @cgrp? */
 	if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
 		return 0;
@@ -2745,9 +2831,9 @@ out:
 }
 
 static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
-			      const struct cftype cfts[], bool is_add)
+			      struct cftype cfts[], bool is_add)
 {
-	const struct cftype *cft;
+	struct cftype *cft;
 	int err, ret = 0;
 
 	for (cft = cfts; cft->name[0] != '\0'; cft++) {
@@ -2781,7 +2867,7 @@ static void cgroup_cfts_prepare(void)
 }
 
 static void cgroup_cfts_commit(struct cgroup_subsys *ss,
-			       const struct cftype *cfts, bool is_add)
+			       struct cftype *cfts, bool is_add)
 	__releases(&cgroup_mutex) __releases(&cgroup_cft_mutex)
 {
 	LIST_HEAD(pending);
@@ -2832,7 +2918,7 @@ static void cgroup_cfts_commit(struct cgroup_subsys *ss,
  * function currently returns 0 as long as @cfts registration is successful
  * even if some file creation attempts on existing cgroups fail.
  */
-int cgroup_add_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts)
+int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 {
 	struct cftype_set *set;
 
@@ -2862,7 +2948,7 @@ EXPORT_SYMBOL_GPL(cgroup_add_cftypes);
  * Returns 0 on successful unregistration, -ENOENT if @cfts is not
  * registered with @ss.
  */
-int cgroup_rm_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts)
+int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 {
 	struct cftype_set *set;