Merge tag 'vfs-7.1-rc1.xattr' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs xattr updates from Christian Brauner:
 "This reworks the simple_xattr infrastructure and adds support for
  user.* extended attributes on sockets.

  The simple_xattr subsystem currently uses an rbtree protected by a
  reader-writer spinlock. This series replaces the rbtree with an
  rhashtable giving O(1) average-case lookup with RCU-based lockless
  reads. This sped up concurrent access patterns on tmpfs quite a bit
  and it's an overall easy enough conversion to do and gets rid or
  rwlock_t.

  The conversion is done incrementally: a new rhashtable path is added
  alongside the existing rbtree, consumers are migrated one at a time
  (shmem, kernfs, pidfs), and then the rbtree code is removed. All three
  consumers switch from embedded structs to pointer-based lazy
  allocation so the rhashtable overhead is only paid for inodes that
  actually use xattrs.

  With this infrastructure in place the series adds support for user.*
  xattrs on sockets. Path-based AF_UNIX sockets inherit xattr support
  from the underlying filesystem (e.g. tmpfs) but sockets in sockfs -
  that is everything created via socket() including abstract namespace
  AF_UNIX sockets - had no xattr support at all.

  The xattr_permission() checks are reworked to allow user.* xattrs on
  S_IFSOCK inodes. Sockfs sockets get per-inode limits of 128 xattrs and
  128KB total value size matching the limits already in use for kernfs.

  The practical motivation comes from several directions. systemd and
  GNOME are expanding their use of Varlink as an IPC mechanism.

  For D-Bus there are tools like dbus-monitor that can observe IPC
  traffic across the system but this only works because D-Bus has a
  central broker.

  For Varlink there is no broker and there is currently no way to
  identify which sockets speak Varlink. With user.* xattrs on sockets a
  service can label its socket with the IPC protocol it speaks (e.g.,
  user.varlink=1) and an eBPF program can then selectively capture
  traffic on those sockets. Enumerating bound sockets via netlink
  combined with these xattr labels gives a way to discover all Varlink
  IPC entrypoints for debugging and introspection.

  Similarly, systemd-journald wants to use xattrs on the /dev/log socket
  for protocol negotiation to indicate whether RFC 5424 structured
  syslog is supported or whether only the legacy RFC 3164 format should
  be used.

  In containers these labels are particularly useful as high-privilege
  or more complicated solutions for socket identification aren't
  available.

  The series comes with comprehensive selftests covering path-based
  AF_UNIX sockets, sockfs socket operations, per-inode limit
  enforcement, and xattr operations across multiple address families
  (AF_INET, AF_INET6, AF_NETLINK, AF_PACKET)"

* tag 'vfs-7.1-rc1.xattr' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  selftests/xattr: test xattrs on various socket families
  selftests/xattr: sockfs socket xattr tests
  selftests/xattr: path-based AF_UNIX socket xattr tests
  xattr: support extended attributes on sockets
  xattr,net: support limited amount of extended attributes on sockfs sockets
  xattr: move user limits for xattrs to generic infra
  xattr: switch xattr_permission() to switch statement
  xattr: add xattr_permission_error()
  xattr: remove rbtree-based simple_xattr infrastructure
  pidfs: adapt to rhashtable-based simple_xattrs
  kernfs: adapt to rhashtable-based simple_xattrs with lazy allocation
  shmem: adapt to rhashtable-based simple_xattrs with lazy allocation
  xattr: add rhashtable-based simple_xattr infrastructure
  xattr: add rcu_head and rhash_head to struct simple_xattr

1 files changed, 92 insertions, 27 deletions

diff --git a/net/socket.c b/net/socket.c
index 05952188127f..d25be67e4b84 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -315,45 +315,70 @@ efault_end:
 
 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;