Now that we've generalized the infrastructure for user.* xattrs make it
possible to set up to 128 user.* extended attributes on a sockfs inode
or up to 128kib. kernfs (cgroupfs) has the same limits and it has proven
to be quite sufficient for nearly all use-cases.

This will allow containers to label sockets and will e.g., be used by
systemd and Gnome to find various sockets in containers where
high-privilege or more complicated solutions aren't available.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 net/socket.c | 119 +++++++++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 92 insertions(+), 27 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index 136b98c54fb3..7aa94fce7a8b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -315,45 +315,70 @@ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen,
 
 static struct kmem_cache *sock_inode_cachep __ro_after_init;
 
+struct sockfs_inode {
+	struct simple_xattrs *xattrs;
+	struct simple_xattr_limits xattr_limits;
+	struct socket_alloc;
+};
+
+static struct sockfs_inode *SOCKFS_I(struct inode *inode)
+{
+	return container_of(inode, struct sockfs_inode, vfs_inode);
+}
+
 static struct inode *sock_alloc_inode(struct super_block *sb)
 {
-	struct socket_alloc *ei;
+	struct sockfs_inode *si;
 
-	ei = alloc_inode_sb(sb, sock_inode_cachep, GFP_KERNEL);
-	if (!ei)
+	si = alloc_inode_sb(sb, sock_inode_cachep, GFP_KERNEL);
+	if (!si)
 		return NULL;
-	init_waitqueue_head(&ei->socket.wq.wait);
-	ei->socket.wq.fasync_list = NULL;
-	ei->socket.wq.flags = 0;
+	si->xattrs = NULL;
+	simple_xattr_limits_init(&si->xattr_limits);
+
+	init_waitqueue_head(&si->socket.wq.wait);
+	si->socket.wq.fasync_list = NULL;
+	si->socket.wq.flags = 0;
+
+	si->socket.state = SS_UNCONNECTED;
+	si->socket.flags = 0;
+	si->socket.ops = NULL;
+	si->socket.sk = NULL;
+	si->socket.file = NULL;
 
-	ei->socket.state = SS_UNCONNECTED;
-	ei->socket.flags = 0;
-	ei->socket.ops = NULL;
-	ei->socket.sk = NULL;
-	ei->socket.file = NULL;
+	return &si->vfs_inode;
+}
+
+static void sock_evict_inode(struct inode *inode)
+{
+	struct sockfs_inode *si = SOCKFS_I(inode);
+	struct simple_xattrs *xattrs = si->xattrs;
 
-	return &ei->vfs_inode;
+	if (xattrs) {
+		simple_xattrs_free(xattrs, NULL);
+		kfree(xattrs);
+	}
+	clear_inode(inode);
 }
 
 static void sock_free_inode(struct inode *inode)
 {
-	struct socket_alloc *ei;
+	struct sockfs_inode *si = SOCKFS_I(inode);
 
-	ei = container_of(inode, struct socket_alloc, vfs_inode);
-	kmem_cache_free(sock_inode_cachep, ei);
+	kmem_cache_free(sock_inode_cachep, si);
 }
 
 static void init_once(void *foo)
 {
-	struct socket_alloc *ei = (struct socket_alloc *)foo;
+	struct sockfs_inode *si = (struct sockfs_inode *)foo;
 
-	inode_init_once(&ei->vfs_inode);
+	inode_init_once(&si->vfs_inode);
 }
 
 static void init_inodecache(void)
 {
 	sock_inode_cachep = kmem_cache_create("sock_inode_cache",
-					      sizeof(struct socket_alloc),
+					      sizeof(struct sockfs_inode),
 					      0,
 					      (SLAB_HWCACHE_ALIGN |
 					       SLAB_RECLAIM_ACCOUNT |
@@ -365,6 +390,7 @@ static void init_inodecache(void)
 static const struct super_operations sockfs_ops = {
 	.alloc_inode	= sock_alloc_inode,
 	.free_inode	= sock_free_inode,
+	.evict_inode	= sock_evict_inode,
 	.statfs		= simple_statfs,
 };
 
@@ -417,9 +443,48 @@ static const struct xattr_handler sockfs_security_xattr_handler = {
 	.set = sockfs_security_xattr_set,
 };
 
+static int sockfs_user_xattr_get(const struct xattr_handler *handler,
+				 struct dentry *dentry, struct inode *inode,
+				 const char *suffix, void *value, size_t size)
+{
+	const char *name = xattr_full_name(handler, suffix);
+	struct simple_xattrs *xattrs;
+
+	xattrs = READ_ONCE(SOCKFS_I(inode)->xattrs);
+	if (!xattrs)
+		return -ENODATA;
+
+	return simple_xattr_get(xattrs, name, value, size);
+}
+
+static int sockfs_user_xattr_set(const struct xattr_handler *handler,
+				 struct mnt_idmap *idmap,
+				 struct dentry *dentry, struct inode *inode,
+				 const char *suffix, const void *value,
+				 size_t size, int flags)
+{
+	const char *name = xattr_full_name(handler, suffix);
+	struct sockfs_inode *si = SOCKFS_I(inode);
+	struct simple_xattrs *xattrs;
+
+	xattrs = simple_xattrs_lazy_alloc(&si->xattrs, value, flags);
+	if (IS_ERR_OR_NULL(xattrs))
+		return PTR_ERR(xattrs);
+
+	return simple_xattr_set_limited(xattrs, &si->xattr_limits,
+					name, value, size, flags);
+}
+
+static const struct xattr_handler sockfs_user_xattr_handler = {
+	.prefix = XATTR_USER_PREFIX,
+	.get = sockfs_user_xattr_get,
+	.set = sockfs_user_xattr_set,
+};
+
 static const struct xattr_handler * const sockfs_xattr_handlers[] = {
 	&sockfs_xattr_handler,
 	&sockfs_security_xattr_handler,
+	&sockfs_user_xattr_handler,
 	NULL
 };
 
@@ -572,26 +637,26 @@ EXPORT_SYMBOL(sockfd_lookup);
 static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer,
 				size_t size)
 {
-	ssize_t len;
-	ssize_t used = 0;
+	struct sockfs_inode *si = SOCKFS_I(d_inode(dentry));
+	ssize_t len, used;
 
-	len = security_inode_listsecurity(d_inode(dentry), buffer, size);
+	len = simple_xattr_list(d_inode(dentry), READ_ONCE(si->xattrs),
+				buffer, size);
 	if (len < 0)
 		return len;
-	used += len;
+
+	used = len;
 	if (buffer) {
-		if (size < used)
-			return -ERANGE;
 		buffer += len;
+		size -= len;
 	}
 
-	len = (XATTR_NAME_SOCKPROTONAME_LEN + 1);
+	len = XATTR_NAME_SOCKPROTONAME_LEN + 1;
 	used += len;
 	if (buffer) {
-		if (size < used)
+		if (size < len)
 			return -ERANGE;
 		memcpy(buffer, XATTR_NAME_SOCKPROTONAME, len);
-		buffer += len;
 	}
 
 	return used;

-- 
2.47.3