Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull user namespace and namespace infrastructure changes from Eric W Biederman:
 "This set of changes starts with a few small enhnacements to the user
  namespace.  reboot support, allowing more arbitrary mappings, and
  support for mounting devpts, ramfs, tmpfs, and mqueuefs as just the
  user namespace root.

  I do my best to document that if you care about limiting your
  unprivileged users that when you have the user namespace support
  enabled you will need to enable memory control groups.

  There is a minor bug fix to prevent overflowing the stack if someone
  creates way too many user namespaces.

  The bulk of the changes are a continuation of the kuid/kgid push down
  work through the filesystems.  These changes make using uids and gids
  typesafe which ensures that these filesystems are safe to use when
  multiple user namespaces are in use.  The filesystems converted for
  3.9 are ceph, 9p, afs, ocfs2, gfs2, ncpfs, nfs, nfsd, and cifs.  The
  changes for these filesystems were a little more involved so I split
  the changes into smaller hopefully obviously correct changes.

  XFS is the only filesystem that remains.  I was hoping I could get
  that in this release so that user namespace support would be enabled
  with an allyesconfig or an allmodconfig but it looks like the xfs
  changes need another couple of days before it they are ready."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (93 commits)
  cifs: Enable building with user namespaces enabled.
  cifs: Convert struct cifs_ses to use a kuid_t and a kgid_t
  cifs: Convert struct cifs_sb_info to use kuids and kgids
  cifs: Modify struct smb_vol to use kuids and kgids
  cifs: Convert struct cifsFileInfo to use a kuid
  cifs: Convert struct cifs_fattr to use kuid and kgids
  cifs: Convert struct tcon_link to use a kuid.
  cifs: Modify struct cifs_unix_set_info_args to hold a kuid_t and a kgid_t
  cifs: Convert from a kuid before printing current_fsuid
  cifs: Use kuids and kgids SID to uid/gid mapping
  cifs: Pass GLOBAL_ROOT_UID and GLOBAL_ROOT_GID to keyring_alloc
  cifs: Use BUILD_BUG_ON to validate uids and gids are the same size
  cifs: Override unmappable incoming uids and gids
  nfsd: Enable building with user namespaces enabled.
  nfsd: Properly compare and initialize kuids and kgids
  nfsd: Store ex_anon_uid and ex_anon_gid as kuids and kgids
  nfsd: Modify nfsd4_cb_sec to use kuids and kgids
  nfsd: Handle kuids and kgids in the nfs4acl to posix_acl conversion
  nfsd: Convert nfsxdr to use kuids and kgids
  nfsd: Convert nfs3xdr to use kuids and kgids
  ...

75 files changed, 773 insertions, 500 deletions

diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index da8eefbe830..afd4724b2d9 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -74,19 +74,20 @@ int v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid)
  *
  */
 
-static struct p9_fid *v9fs_fid_find(struct dentry *dentry, u32 uid, int any)
+static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
 {
 	struct v9fs_dentry *dent;
 	struct p9_fid *fid, *ret;
 
 	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p) uid %d any %d\n",
-		 dentry->d_name.name, dentry, uid, any);
+		 dentry->d_name.name, dentry, from_kuid(&init_user_ns, uid),
+		 any);
 	dent = (struct v9fs_dentry *) dentry->d_fsdata;
 	ret = NULL;
 	if (dent) {
 		spin_lock(&dent->lock);
 		list_for_each_entry(fid, &dent->fidlist, dlist) {
-			if (any || fid->uid == uid) {
+			if (any || uid_eq(fid->uid, uid)) {
 				ret = fid;
 				break;
 			}
@@ -126,7 +127,7 @@ err_out:
 }
 
 static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
-					       uid_t uid, int any)
+					       kuid_t uid, int any)
 {
 	struct dentry *ds;
 	char **wnames, *uname;
@@ -233,7 +234,7 @@ err_out:
 
 struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
 {
-	uid_t uid;
+	kuid_t uid;
 	int  any, access;
 	struct v9fs_session_info *v9ses;
 
@@ -253,7 +254,7 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
 		break;
 
 	default:
-		uid = ~0;
+		uid = INVALID_UID;
 		any = 0;
 		break;
 	}
@@ -272,7 +273,7 @@ struct p9_fid *v9fs_fid_clone(struct dentry *dentry)
 	return ret;
 }
 
-static struct p9_fid *v9fs_fid_clone_with_uid(struct dentry *dentry, uid_t uid)
+static struct p9_fid *v9fs_fid_clone_with_uid(struct dentry *dentry, kuid_t uid)
 {
 	struct p9_fid *fid, *ret;
 
@@ -289,7 +290,7 @@ struct p9_fid *v9fs_writeback_fid(struct dentry *dentry)
 	int err;
 	struct p9_fid *fid;
 
-	fid = v9fs_fid_clone_with_uid(dentry, 0);
+	fid = v9fs_fid_clone_with_uid(dentry, GLOBAL_ROOT_UID);
 	if (IS_ERR(fid))
 		goto error_out;
 	/*
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index d934f04e773..58e6cbce415 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -161,7 +161,13 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 				ret = r;
 				continue;
 			}
-			v9ses->dfltuid = option;
+			v9ses->dfltuid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(v9ses->dfltuid)) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "uid field, but not a uid?\n");
+				ret = -EINVAL;
+				continue;
+			}
 			break;
 		case Opt_dfltgid:
 			r = match_int(&args[0], &option);
@@ -171,7 +177,13 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 				ret = r;
 				continue;
 			}
-			v9ses->dfltgid = option;
+			v9ses->dfltgid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(v9ses->dfltgid)) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "gid field, but not a gid?\n");
+				ret = -EINVAL;
+				continue;
+			}
 			break;
 		case Opt_afid:
 			r = match_int(&args[0], &option);
@@ -248,8 +260,9 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 			else if (strcmp(s, "client") == 0) {
 				v9ses->flags |= V9FS_ACCESS_CLIENT;
 			} else {
+				uid_t uid;
 				v9ses->flags |= V9FS_ACCESS_SINGLE;
-				v9ses->uid = simple_strtoul(s, &e, 10);
+				uid = simple_strtoul(s, &e, 10);
 				if (*e != '\0') {
 					ret = -EINVAL;
 					pr_info("Unknown access argument %s\n",
@@ -257,6 +270,13 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 					kfree(s);
 					goto free_and_return;
 				}
+				v9ses->uid = make_kuid(current_user_ns(), uid);
+				if (!uid_valid(v9ses->uid)) {
+					ret = -EINVAL;
+					pr_info("Uknown uid %s\n", s);
+					kfree(s);
+					goto free_and_return;
+				}
 			}
 
 			kfree(s);
@@ -319,7 +339,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	list_add(&v9ses->slist, &v9fs_sessionlist);
 	spin_unlock(&v9fs_sessionlist_lock);
 
-	v9ses->uid = ~0;
+	v9ses->uid = INVALID_UID;
 	v9ses->dfltuid = V9FS_DEFUID;
 	v9ses->dfltgid = V9FS_DEFGID;
 
@@ -364,7 +384,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 
 		v9ses->flags &= ~V9FS_ACCESS_MASK;
 		v9ses->flags |= V9FS_ACCESS_ANY;
-		v9ses->uid = ~0;
+		v9ses->uid = INVALID_UID;
 	}
 	if (!v9fs_proto_dotl(v9ses) ||
 		!((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) {
@@ -375,7 +395,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 		v9ses->flags &= ~V9FS_ACL_MASK;
 	}
 
-	fid = p9_client_attach(v9ses->clnt, NULL, v9ses->uname, ~0,
+	fid = p9_client_attach(v9ses->clnt, NULL, v9ses->uname, INVALID_UID,
 							v9ses->aname);
 	if (IS_ERR(fid)) {
 		retval = PTR_ERR(fid);
@@ -387,7 +407,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	if ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_SINGLE)
 		fid->uid = v9ses->uid;
 	else
-		fid->uid = ~0;
+		fid->uid = INVALID_UID;
 
 #ifdef CONFIG_9P_FSCACHE
 	/* register the session for caching */
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 34c59f14a1c..a8e127c8962 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -109,9 +109,9 @@ struct v9fs_session_info {
 	char *uname;		/* user name to mount as */
 	char *aname;		/* name of remote hierarchy being mounted */
 	unsigned int maxdata;	/* max data for client interface */
-	unsigned int dfltuid;	/* default uid/muid for legacy support */
-	unsigned int dfltgid;	/* default gid for legacy support */
-	u32 uid;		/* if ACCESS_SINGLE, the uid that has access */
+	kuid_t dfltuid;		/* default uid/muid for legacy support */
+	kgid_t dfltgid;		/* default gid for legacy support */
+	kuid_t uid;		/* if ACCESS_SINGLE, the uid that has access */
 	struct p9_client *clnt;	/* 9p client */
 	struct list_head slist; /* list of sessions registered with v9fs */
 	struct backing_dev_info bdi;
@@ -165,8 +165,8 @@ extern struct inode *v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses,
 #define V9FS_PORT	564
 #define V9FS_DEFUSER	"nobody"
 #define V9FS_DEFANAME	""
-#define V9FS_DEFUID	(-2)
-#define V9FS_DEFGID	(-2)
+#define V9FS_DEFUID	KUIDT_INIT(-2)
+#define V9FS_DEFGID	KGIDT_INIT(-2)
 
 static inline struct v9fs_session_info *v9fs_inode2v9ses(struct inode *inode)
 {
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 57d017ac68e..b5340c829de 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -225,9 +225,9 @@ v9fs_blank_wstat(struct p9_wstat *wstat)
 	wstat->uid = NULL;
 	wstat->gid = NULL;
 	wstat->muid = NULL;
-	wstat->n_uid = ~0;
-	wstat->n_gid = ~0;
-	wstat->n_muid = ~0;
+	wstat->n_uid = INVALID_UID;
+	wstat->n_gid = INVALID_GID;
+	wstat->n_muid = INVALID_UID;
 	wstat->extension = NULL;
 }
 
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 8d24ad66dfb..07f409288d1 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -57,7 +57,7 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
  * group of the new file system object.
  */
 
-static gid_t v9fs_get_fsgid_for_create(struct inode *dir_inode)
+static kgid_t v9fs_get_fsgid_for_create(struct inode *dir_inode)
 {
 	BUG_ON(dir_inode == NULL);
 
@@ -245,7 +245,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 			  int *opened)
 {
 	int err = 0;
-	gid_t gid;
+	kgid_t gid;
 	umode_t mode;
 	char *name = NULL;
 	struct p9_qid qid;
@@ -396,7 +396,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
 	int err;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid = NULL, *dfid = NULL;
-	gid_t gid;
+	kgid_t gid;
 	char *name;
 	umode_t mode;
 	struct inode *inode;
@@ -697,7 +697,7 @@ v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry,
 		const char *symname)
 {
 	int err;
-	gid_t gid;
+	kgid_t gid;
 	char *name;
 	struct p9_qid qid;
 	struct inode *inode;
@@ -837,7 +837,7 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 		dev_t rdev)
 {
 	int err;
-	gid_t gid;
+	kgid_t gid;
 	char *name;
 	umode_t mode;
 	struct v9fs_session_info *v9ses;
diff --git a/fs/afs/afs.h b/fs/afs/afs.h
index c548aa346f0..3c462ff6db6 100644
--- a/fs/afs/afs.h
+++ b/fs/afs/afs.h
@@ -119,8 +119,8 @@ struct afs_file_status {
 	u64			size;		/* file size */
 	afs_dataversion_t	data_version;	/* current data version */
 	u32			author;		/* author ID */
-	u32			owner;		/* owner ID */
-	u32			group;		/* group ID */
+	kuid_t			owner;		/* owner ID */
+	kgid_t			group;		/* group ID */
 	afs_access_t		caller_access;	/* access rights for authenticated caller */
 	afs_access_t		anon_access;	/* access rights for unauthenticated caller */
 	umode_t			mode;		/* UNIX mode */
@@ -133,13 +133,6 @@ struct afs_file_status {
 /*
  * AFS file status change request
  */
-struct afs_store_status {
-	u32			mask;		/* which bits of the struct are set */
-	u32			mtime_client;	/* last time client changed data */
-	u32			owner;		/* owner ID */
-	u32			group;		/* group ID */
-	umode_t			mode;		/* UNIX mode */
-};
 
 #define AFS_SET_MTIME		0x01		/* set the mtime */
 #define AFS_SET_OWNER		0x02		/* set the owner ID */
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index b960ff05ea0..c2e930ec288 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -42,6 +42,8 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
 	umode_t mode;
 	u64 data_version, size;
 	u32 changed = 0; /* becomes non-zero if ctime-type changes seen */
+	kuid_t owner;
+	kgid_t group;
 
 #define EXTRACT(DST)				\
 	do {					\
@@ -56,7 +58,9 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
 	size = ntohl(*bp++);
 	data_version = ntohl(*bp++);
 	EXTRACT(status->author);
-	EXTRACT(status->owner);
+	owner = make_kuid(&init_user_ns, ntohl(*bp++));
+	changed |= !uid_eq(owner, status->owner);
+	status->owner = owner;
 	EXTRACT(status->caller_access); /* call ticket dependent */
 	EXTRACT(status->anon_access);
 	EXTRACT(status->mode);
@@ -65,7 +69,9 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
 	bp++; /* seg size */
 	status->mtime_client = ntohl(*bp++);
 	status->mtime_server = ntohl(*bp++);
-	EXTRACT(status->group);
+	group = make_kgid(&init_user_ns, ntohl(*bp++));
+	changed |= !gid_eq(group, status->group);
+	status->group = group;
 	bp++; /* sync counter */
 	data_version |= (u64) ntohl(*bp++) << 32;
 	EXTRACT(status->lock_count);
@@ -181,12 +187,12 @@ static void xdr_encode_AFS_StoreStatus(__be32 **_bp, struct iattr *attr)
 
 	if (attr->ia_valid & ATTR_UID) {
 		mask |= AFS_SET_OWNER;
-		owner = attr->ia_uid;
+		owner = from_kuid(&init_user_ns, attr->ia_uid);
 	}
 
 	if (attr->ia_valid & ATTR_GID) {
 		mask |= AFS_SET_GROUP;
-		group = attr->ia_gid;
+		group = from_kgid(&init_user_ns, attr->ia_gid);
 	}
 
 	if (attr->ia_valid & ATTR_MODE) {
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 95cffd38239..789bc253b5f 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -69,7 +69,7 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
 
 	set_nlink(inode, vnode->status.nlink);
 	inode->i_uid		= vnode->status.owner;
-	inode->i_gid		= 0;
+	inode->i_gid		= GLOBAL_ROOT_GID;
 	inode->i_size		= vnode->status.size;
 	inode->i_ctime.tv_sec	= vnode->status.mtime_server;
 	inode->i_ctime.tv_nsec	= 0;
@@ -175,8 +175,8 @@ struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name,
 	inode->i_mode		= S_IFDIR | S_IRUGO | S_IXUGO;
 	inode->i_op		= &afs_autocell_inode_operations;
 	set_nlink(inode, 2);
-	inode->i_uid		= 0;
-	inode->i_gid		= 0;
+	inode->i_uid		= GLOBAL_ROOT_UID;
+	inode->i_gid		= GLOBAL_ROOT_GID;
 	inode->i_ctime.tv_sec	= get_seconds();
 	inode->i_ctime.tv_nsec	= 0;
 	inode->i_atime		= inode->i_mtime = inode->i_ctime;
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 43165009428..7c31ec39957 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -24,6 +24,8 @@
 #include <linux/parser.h>
 #include <linux/statfs.h>
 #include <linux/sched.h>
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
 #include "internal.h"
 
 #define AFS_FS_MAGIC 0x6B414653 /* 'kAFS' */
@@ -363,6 +365,10 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
 
 	memset(&params, 0, sizeof(params));
 
+	ret = -EINVAL;
+	if (current->nsproxy->net_ns != &init_net)
+		goto error;
+
 	/* parse the options and device name */
 	if (options) {
 		ret = afs_parse_options(&params, options, &dev_name);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index a1d9bb30c1b..ae2be696eb5 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -930,7 +930,7 @@ static int send_cap_msg(struct ceph_mds_session *session,
 			u64 size, u64 max_size,
 			struct timespec *mtime, struct timespec *atime,
 			u64 time_warp_seq,
-			uid_t uid, gid_t gid, umode_t mode,
+			kuid_t uid, kgid_t gid, umode_t mode,
 			u64 xattr_version,
 			struct ceph_buffer *xattrs_buf,
 			u64 follows)
@@ -974,8 +974,8 @@ static int send_cap_msg(struct ceph_mds_session *session,
 		ceph_encode_timespec(&fc->atime, atime);
 	fc->time_warp_seq = cpu_to_le32(time_warp_seq);
 
-	fc->uid = cpu_to_le32(uid);
-	fc->gid = cpu_to_le32(gid);
+	fc->uid = cpu_to_le32(from_kuid(&init_user_ns, uid));
+	fc->gid = cpu_to_le32(from_kgid(&init_user_ns, gid));
 	fc->mode = cpu_to_le32(mode);
 
 	fc->xattr_version = cpu_to_le64(xattr_version);
@@ -1081,8 +1081,8 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	struct timespec mtime, atime;
 	int wake = 0;
 	umode_t mode;
-	uid_t uid;
-	gid_t gid;
+	kuid_t uid;
+	kgid_t gid;
 	struct ceph_mds_session *session;
 	u64 xattr_version = 0;
 	struct ceph_buffer *xattr_blob = NULL;
@@ -2359,10 +2359,11 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
 
 	if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
 		inode->i_mode = le32_to_cpu(grant->mode);
-		inode->i_uid = le32_to_cpu(grant->uid);
-		inode->i_gid = le32_to_cpu(grant->gid);
+		inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
+		inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
 		dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
-		     inode->i_uid, inode->i_gid);
+		     from_kuid(&init_user_ns, inode->i_uid),
+		     from_kgid(&init_user_ns, inode->i_gid));
 	}
 
 	if ((issued & CEPH_CAP_LINK_EXCL) == 0)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 2971eaa65cd..d45895f4a04 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -612,10 +612,11 @@ s