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
  ...

6 files changed, 48 insertions, 20 deletions

diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 260b162..8a40457 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -65,7 +65,20 @@ static struct posix_acl *ocfs2_acl_from_xattr(const void *value, size_t size)
 
 		acl->a_entries[n].e_tag  = le16_to_cpu(entry->e_tag);
 		acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm);
-		acl->a_entries[n].e_id   = le32_to_cpu(entry->e_id);
+		switch(acl->a_entries[n].e_tag) {
+		case ACL_USER:
+			acl->a_entries[n].e_uid =
+				make_kuid(&init_user_ns,
+					  le32_to_cpu(entry->e_id));
+			break;
+		case ACL_GROUP:
+			acl->a_entries[n].e_gid =
+				make_kgid(&init_user_ns,
+					  le32_to_cpu(entry->e_id));
+			break;
+		default:
+			break;
+		}
 		value += sizeof(struct posix_acl_entry);
 
 	}
@@ -91,7 +104,21 @@ static void *ocfs2_acl_to_xattr(const struct posix_acl *acl, size_t *size)
 	for (n = 0; n < acl->a_count; n++, entry++) {
 		entry->e_tag  = cpu_to_le16(acl->a_entries[n].e_tag);
 		entry->e_perm = cpu_to_le16(acl->a_entries[n].e_perm);
-		entry->e_id   = cpu_to_le32(acl->a_entries[n].e_id);
+		switch(acl->a_entries[n].e_tag) {
+		case ACL_USER:
+			entry->e_id = cpu_to_le32(
+				from_kuid(&init_user_ns,
+					  acl->a_entries[n].e_uid));
+			break;
+		case ACL_GROUP:
+			entry->e_id = cpu_to_le32(
+				from_kgid(&init_user_ns,
+					  acl->a_entries[n].e_gid));
+			break;
+		default:
+			entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID);
+			break;
+		}
 	}
 	return ocfs2_acl;
 }
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 88577eb..12ae194 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2045,8 +2045,8 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode)
 	lvb->lvb_version   = OCFS2_LVB_VERSION;
 	lvb->lvb_isize	   = cpu_to_be64(i_size_read(inode));
 	lvb->lvb_iclusters = cpu_to_be32(oi->ip_clusters);
-	lvb->lvb_iuid      = cpu_to_be32(inode->i_uid);
-	lvb->lvb_igid      = cpu_to_be32(inode->i_gid);
+	lvb->lvb_iuid      = cpu_to_be32(i_uid_read(inode));
+	lvb->lvb_igid      = cpu_to_be32(i_gid_read(inode));
 	lvb->lvb_imode     = cpu_to_be16(inode->i_mode);
 	lvb->lvb_inlink    = cpu_to_be16(inode->i_nlink);
 	lvb->lvb_iatime_packed  =
@@ -2095,8 +2095,8 @@ static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
 	else
 		inode->i_blocks = ocfs2_inode_sector_count(inode);
 
-	inode->i_uid     = be32_to_cpu(lvb->lvb_iuid);
-	inode->i_gid     = be32_to_cpu(lvb->lvb_igid);
+	i_uid_write(inode, be32_to_cpu(lvb->lvb_iuid));
+	i_gid_write(inode, be32_to_cpu(lvb->lvb_igid));
 	inode->i_mode    = be16_to_cpu(lvb->lvb_imode);
 	set_nlink(inode, be16_to_cpu(lvb->lvb_inlink));
 	ocfs2_unpack_timespec(&inode->i_atime,
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 37d313e..0a2924a 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1116,7 +1116,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
 			    dentry->d_name.len, dentry->d_name.name,
 			    attr->ia_valid, attr->ia_mode,
-			    attr->ia_uid, attr->ia_gid);
+			    from_kuid(&init_user_ns, attr->ia_uid),
+			    from_kgid(&init_user_ns, attr->ia_gid));
 
 	/* ensuring we don't even attempt to truncate a symlink */
 	if (S_ISLNK(inode->i_mode))
@@ -1174,14 +1175,14 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		}
 	}
 
-	if ((attr->ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
-	    (attr->ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
+	if ((attr->ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) ||
+	    (attr->ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) {
 		/*
 		 * Gather pointers to quota structures so that allocation /
 		 * freeing of quota structures happens here and not inside
 		 * dquot_transfer() where we have problems with lock ordering
 		 */
-		if (attr->ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid
+		if (attr->ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)
 		    && OCFS2_HAS_RO_COMPAT_FEATURE(sb,
 		    OCFS2_FEATURE_RO_COMPAT_USRQUOTA)) {
 			transfer_to[USRQUOTA] = dqget(sb, make_kqid_uid(attr->ia_uid));
@@ -1190,7 +1191,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 				goto bail_unlock;
 			}
 		}
-		if (attr->ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid
+		if (attr->ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid)
 		    && OCFS2_HAS_RO_COMPAT_FEATURE(sb,
 		    OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)) {
 			transfer_to[GRPQUOTA] = dqget(sb, make_kqid_gid(attr->ia_gid));
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index d89e08a..f87f9bd 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -269,8 +269,8 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
 	inode->i_generation = le32_to_cpu(fe->i_generation);
 	inode->i_rdev = huge_decode_dev(le64_to_cpu(fe->id1.dev1.i_rdev));
 	inode->i_mode = le16_to_cpu(fe->i_mode);
-	inode->i_uid = le32_to_cpu(fe->i_uid);
-	inode->i_gid = le32_to_cpu(fe->i_gid);
+	i_uid_write(inode, le32_to_cpu(fe->i_uid));
+	i_gid_write(inode, le32_to_cpu(fe->i_gid));
 
 	/* Fast symlinks will have i_size but no allocated clusters. */
 	if (S_ISLNK(inode->i_mode) && !fe->i_clusters) {
@@ -1259,8 +1259,8 @@ int ocfs2_mark_inode_dirty(handle_t *handle,
 
 	fe->i_size = cpu_to_le64(i_size_read(inode));
 	ocfs2_set_links_count(fe, inode->i_nlink);
-	fe->i_uid = cpu_to_le32(inode->i_uid);
-	fe->i_gid = cpu_to_le32(inode->i_gid);
+	fe->i_uid = cpu_to_le32(i_uid_read(inode));
+	fe->i_gid = cpu_to_le32(i_gid_read(inode));
 	fe->i_mode = cpu_to_le16(inode->i_mode);
 	fe->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
 	fe->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
@@ -1290,8 +1290,8 @@ void ocfs2_refresh_inode(struct inode *inode,
 	ocfs2_set_inode_flags(inode);
 	i_size_write(inode, le64_to_cpu(fe->i_size));
 	set_nlink(inode, ocfs2_read_links_count(fe));
-	inode->i_uid = le32_to_cpu(fe->i_uid);
-	inode->i_gid = le32_to_cpu(fe->i_gid);
+	i_uid_write(inode, le32_to_cpu(fe->i_uid));
+	i_gid_write(inode, le32_to_cpu(fe->i_gid));
 	inode->i_mode = le16_to_cpu(fe->i_mode);
 	if (S_ISLNK(inode->i_mode) && le32_to_cpu(fe->i_clusters) == 0)
 		inode->i_blocks = 0;
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index f1fd074..04ee1b5 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -512,8 +512,8 @@ static int __ocfs2_mknod_locked(struct inode *dir,
 	fe->i_suballoc_loc = cpu_to_le64(suballoc_loc);
 	fe->i_suballoc_bit = cpu_to_le16(suballoc_bit);
 	fe->i_suballoc_slot = cpu_to_le16(inode_ac->ac_alloc_slot);
-	fe->i_uid = cpu_to_le32(inode->i_uid);
-	fe->i_gid = cpu_to_le32(inode->i_gid);
+	fe->i_uid = cpu_to_le32(i_uid_read(inode));
+	fe->i_gid = cpu_to_le32(i_gid_read(inode));
 	fe->i_mode = cpu_to_le16(inode->i_mode);
 	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
 		fe->id1.dev1.i_rdev = cpu_to_le64(huge_encode_dev(dev));
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 30a0550..934a4ac 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4407,7 +4407,7 @@ static int ocfs2_vfs_reflink(struct dentry *old_dentry, struct inode *dir,
 	 * rights to do so.
 	 */
 	if (preserve) {
-		if ((current_fsuid() != inode->i_uid) && !capable(CAP_CHOWN))
+		if (!uid_eq(current_fsuid(), inode->i_uid) && !capable(CAP_CHOWN))
 			return -EPERM;
 		if (!in_group_p(inode->i_gid) && !capable(CAP_CHOWN))
 			return -EPERM;