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

…/git/ebiederm/user-namespace

Pull user namespace changes from Eric Biederman:
 "This is a mostly modest set of changes to enable basic user namespace
  support.  This allows the code to code to compile with user namespaces
  enabled and removes the assumption there is only the initial user
  namespace.  Everything is converted except for the most complex of the
  filesystems: autofs4, 9p, afs, ceph, cifs, coda, fuse, gfs2, ncpfs,
  nfs, ocfs2 and xfs as those patches need a bit more review.

  The strategy is to push kuid_t and kgid_t values are far down into
  subsystems and filesystems as reasonable.  Leaving the make_kuid and
  from_kuid operations to happen at the edge of userspace, as the values
  come off the disk, and as the values come in from the network.
  Letting compile type incompatible compile errors (present when user
  namespaces are enabled) guide me to find the issues.

  The most tricky areas have been the places where we had an implicit
  union of uid and gid values and were storing them in an unsigned int.
  Those places were converted into explicit unions.  I made certain to
  handle those places with simple trivial patches.

  Out of that work I discovered we have generic interfaces for storing
  quota by projid.  I had never heard of the project identifiers before.
  Adding full user namespace support for project identifiers accounts
  for most of the code size growth in my git tree.

  Ultimately there will be work to relax privlige checks from
  "capable(FOO)" to "ns_capable(user_ns, FOO)" where it is safe allowing
  root in a user names to do those things that today we only forbid to
  non-root users because it will confuse suid root applications.

  While I was pushing kuid_t and kgid_t changes deep into the audit code
  I made a few other cleanups.  I capitalized on the fact we process
  netlink messages in the context of the message sender.  I removed
  usage of NETLINK_CRED, and started directly using current->tty.

  Some of these patches have also made it into maintainer trees, with no
  problems from identical code from different trees showing up in
  linux-next.

  After reading through all of this code I feel like I might be able to
  win a game of kernel trivial pursuit."

Fix up some fairly trivial conflicts in netfilter uid/git logging code.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (107 commits)
  userns: Convert the ufs filesystem to use kuid/kgid where appropriate
  userns: Convert the udf filesystem to use kuid/kgid where appropriate
  userns: Convert ubifs to use kuid/kgid
  userns: Convert squashfs to use kuid/kgid where appropriate
  userns: Convert reiserfs to use kuid and kgid where appropriate
  userns: Convert jfs to use kuid/kgid where appropriate
  userns: Convert jffs2 to use kuid and kgid where appropriate
  userns: Convert hpfs to use kuid and kgid where appropriate
  userns: Convert btrfs to use kuid/kgid where appropriate
  userns: Convert bfs to use kuid/kgid where appropriate
  userns: Convert affs to use kuid/kgid wherwe appropriate
  userns: On alpha modify linux_to_osf_stat to use convert from kuids and kgids
  userns: On ia64 deal with current_uid and current_gid being kuid and kgid
  userns: On ppc convert current_uid from a kuid before printing.
  userns: Convert s390 getting uid and gid system calls to use kuid and kgid
  userns: Convert s390 hypfs to use kuid and kgid where appropriate
  userns: Convert binder ipc to use kuids
  userns: Teach security_path_chown to take kuids and kgids
  userns: Add user namespace support to IMA
  userns: Convert EVM to deal with kuids and kgids in it's hmac computation
  ...

arch/alpha/kernel/osf_sys.c

@@ -278,8 +278,8 @@ linux_to_osf_stat(struct kstat *lstat, struct osf_stat __user *osf_stat)
 	tmp.st_dev	= lstat->dev;
 	tmp.st_mode	= lstat->mode;
 	tmp.st_nlink	= lstat->nlink;
-	tmp.st_uid	= lstat->uid;
-	tmp.st_gid	= lstat->gid;
+	tmp.st_uid	= from_kuid_munged(current_user_ns(), lstat->uid);
+	tmp.st_gid	= from_kgid_munged(current_user_ns(), lstat->gid);
 	tmp.st_rdev	= lstat->rdev;
 	tmp.st_ldev	= lstat->rdev;
 	tmp.st_size	= lstat->size;

arch/ia64/kernel/mca_drv.c

@@ -158,7 +158,8 @@ mca_handler_bh(unsigned long paddr, void *iip, unsigned long ipsr)
 	ia64_mlogbuf_dump();
 	printk(KERN_ERR "OS_MCA: process [cpu %d, pid: %d, uid: %d, "
 		"iip: %p, psr: 0x%lx,paddr: 0x%lx](%s) encounters MCA.\n",
-	       raw_smp_processor_id(), current->pid, current_uid(),
+	       raw_smp_processor_id(), current->pid,
+		from_kuid(&init_user_ns, current_uid()),
 		iip, ipsr, paddr, current->comm);
 
 	spin_lock(&mca_bh_lock);

arch/ia64/kernel/perfmon.c

@@ -2380,29 +2380,29 @@ static int
 pfm_bad_permissions(struct task_struct *task)
 {
 	const struct cred *tcred;
-	uid_t uid = current_uid();
-	gid_t gid = current_gid();
+	kuid_t uid = current_uid();
+	kgid_t gid = current_gid();
 	int ret;
 
 	rcu_read_lock();
 	tcred = __task_cred(task);
 
 	/* inspired by ptrace_attach() */
 	DPRINT(("cur: uid=%d gid=%d task: euid=%d suid=%d uid=%d egid=%d sgid=%d\n",
-		uid,
-		gid,
-		tcred->euid,
-		tcred->suid,
-		tcred->uid,
-		tcred->egid,
-		tcred->sgid));
-
-	ret = ((uid != tcred->euid)
-	       || (uid != tcred->suid)
-	       || (uid != tcred->uid)
-	       || (gid != tcred->egid)
-	       || (gid != tcred->sgid)
-	       || (gid != tcred->gid)) && !capable(CAP_SYS_PTRACE);
+		from_kuid(&init_user_ns, uid),
+		from_kgid(&init_user_ns, gid),
+		from_kuid(&init_user_ns, tcred->euid),
+		from_kuid(&init_user_ns, tcred->suid),
+		from_kuid(&init_user_ns, tcred->uid),
+		from_kgid(&init_user_ns, tcred->egid),
+		from_kgid(&init_user_ns, tcred->sgid)));
+
+	ret = ((!uid_eq(uid, tcred->euid))
+	       || (!uid_eq(uid, tcred->suid))
+	       || (!uid_eq(uid, tcred->uid))
+	       || (!gid_eq(gid, tcred->egid))
+	       || (!gid_eq(gid, tcred->sgid))
+	       || (!gid_eq(gid, tcred->gid))) && !capable(CAP_SYS_PTRACE);
 
 	rcu_read_unlock();
 	return ret;

arch/ia64/kernel/signal.c

@@ -220,7 +220,7 @@ ia64_rt_sigreturn (struct sigscratch *scr)
 	si.si_errno = 0;
 	si.si_code = SI_KERNEL;
 	si.si_pid = task_pid_vnr(current);
-	si.si_uid = current_uid();
+	si.si_uid = from_kuid_munged(current_user_ns(), current_uid());
 	si.si_addr = sc;
 	force_sig_info(SIGSEGV, &si, current);
 	return retval;
@@ -317,7 +317,7 @@ force_sigsegv_info (int sig, void __user *addr)
 	si.si_errno = 0;
 	si.si_code = SI_KERNEL;
 	si.si_pid = task_pid_vnr(current);
-	si.si_uid = current_uid();
+	si.si_uid = from_kuid_munged(current_user_ns(), current_uid());
 	si.si_addr = addr;
 	force_sig_info(SIGSEGV, &si, current);
 	return 0;

arch/powerpc/mm/fault.c

@@ -470,7 +470,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (is_exec && (error_code & DSISR_PROTFAULT))
 		printk_ratelimited(KERN_CRIT "kernel tried to execute NX-protected"
 				   " page (%lx) - exploit attempt? (uid: %d)\n",
-				   address, current_uid());
+				   address, from_kuid(&init_user_ns, current_uid()));
 
 	return SIGSEGV;
 

arch/s390/hypfs/inode.c

@@ -31,8 +31,8 @@ static struct dentry *hypfs_create_update_file(struct super_block *sb,
 					       struct dentry *dir);
 
 struct hypfs_sb_info {
-	uid_t uid;			/* uid used for files and dirs */
-	gid_t gid;			/* gid used for files and dirs */
+	kuid_t uid;			/* uid used for files and dirs */
+	kgid_t gid;			/* gid used for files and dirs */
 	struct dentry *update_file;	/* file to trigger update */
 	time_t last_update;		/* last update time in secs since 1970 */
 	struct mutex lock;		/* lock to protect update process */
@@ -229,6 +229,8 @@ static int hypfs_parse_options(char *options, struct super_block *sb)
 {
 	char *str;
 	substring_t args[MAX_OPT_ARGS];
+	kuid_t uid;
+	kgid_t gid;
 
 	if (!options)
 		return 0;
@@ -243,12 +245,18 @@ static int hypfs_parse_options(char *options, struct super_block *sb)
 		case opt_uid:
 			if (match_int(&args[0], &option))
 				return -EINVAL;
-			hypfs_info->uid = option;
+			uid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(uid))
+				return -EINVAL;
+			hypfs_info->uid = uid;
 			break;
 		case opt_gid:
 			if (match_int(&args[0], &option))
 				return -EINVAL;
-			hypfs_info->gid = option;
+			gid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(gid))
+				return -EINVAL;
+			hypfs_info->gid = gid;
 			break;
 		case opt_err:
 		default:
@@ -263,8 +271,8 @@ static int hypfs_show_options(struct seq_file *s, struct dentry *root)
 {
 	struct hypfs_sb_info *hypfs_info = root->d_sb->s_fs_info;
 
-	seq_printf(s, ",uid=%u", hypfs_info->uid);
-	seq_printf(s, ",gid=%u", hypfs_info->gid);
+	seq_printf(s, ",uid=%u", from_kuid_munged(&init_user_ns, hypfs_info->uid));
+	seq_printf(s, ",gid=%u", from_kgid_munged(&init_user_ns, hypfs_info->gid));
 	return 0;
 }
 

arch/s390/kernel/compat_linux.c

@@ -131,13 +131,19 @@ asmlinkage long sys32_setresuid16(u16 ruid, u16 euid, u16 suid)
 		low2highuid(suid));
 }
 
-asmlinkage long sys32_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid)
+asmlinkage long sys32_getresuid16(u16 __user *ruidp, u16 __user *euidp, u16 __user *suidp)
 {
+	const struct cred *cred = current_cred();
 	int retval;
+	u16 ruid, euid, suid;
 
-	if (!(retval = put_user(high2lowuid(current->cred->uid), ruid)) &&
-	    !(retval = put_user(high2lowuid(current->cred->euid), euid)))
-		retval = put_user(high2lowuid(current->cred->suid), suid);
+	ruid = high2lowuid(from_kuid_munged(cred->user_ns, cred->uid));
+	euid = high2lowuid(from_kuid_munged(cred->user_ns, cred->euid));
+	suid = high2lowuid(from_kuid_munged(cred->user_ns, cred->suid));
+
+	if (!(retval   = put_user(ruid, ruidp)) &&
+	    !(retval   = put_user(euid, euidp)))
+		retval = put_user(suid, suidp);
 
 	return retval;
 }
@@ -148,13 +154,19 @@ asmlinkage long sys32_setresgid16(u16 rgid, u16 egid, u16 sgid)
 		low2highgid(sgid));
 }
 
-asmlinkage long sys32_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid)
+asmlinkage long sys32_getresgid16(u16 __user *rgidp, u16 __user *egidp, u16 __user *sgidp)
 {
+	const struct cred *cred = current_cred();
 	int retval;
+	u16 rgid, egid, sgid;
+
+	rgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->gid));
+	egid = high2lowgid(from_kgid_munged(cred->user_ns, cred->egid));
+	sgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->sgid));
 
-	if (!(retval = put_user(high2lowgid(current->cred->gid), rgid)) &&
-	    !(retval = put_user(high2lowgid(current->cred->egid), egid)))
-		retval = put_user(high2lowgid(current->cred->sgid), sgid);
+	if (!(retval   = put_user(rgid, rgidp)) &&
+	    !(retval   = put_user(egid, egidp)))
+		retval = put_user(sgid, sgidp);
 
 	return retval;
 }
@@ -258,22 +270,22 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
 
 asmlinkage long sys32_getuid16(void)
 {
-	return high2lowuid(current->cred->uid);
+	return high2lowuid(from_kuid_munged(current_user_ns(), current_uid()));
 }
 
 asmlinkage long sys32_geteuid16(void)
 {
-	return high2lowuid(current->cred->euid);
+	return high2lowuid(from_kuid_munged(current_user_ns(), current_euid()));
 }
 
 asmlinkage long sys32_getgid16(void)
 {
-	return high2lowgid(current->cred->gid);
+	return high2lowgid(from_kgid_munged(current_user_ns(), current_gid()));
 }
 
 asmlinkage long sys32_getegid16(void)
 {
-	return high2lowgid(current->cred->egid);
+	return high2lowgid(from_kgid_munged(current_user_ns(), current_egid()));
 }
 
 /*

drivers/base/devtmpfs.c

@@ -309,8 +309,8 @@ static int handle_remove(const char *nodename, struct device *dev)
 			 * before unlinking this node, reset permissions
 			 * of possible references like hardlinks
 			 */
-			newattrs.ia_uid = 0;
-			newattrs.ia_gid = 0;
+			newattrs.ia_uid = GLOBAL_ROOT_UID;
+			newattrs.ia_gid = GLOBAL_ROOT_GID;
 			newattrs.ia_mode = stat.mode & ~0777;
 			newattrs.ia_valid =
 				ATTR_UID|ATTR_GID|ATTR_MODE;

drivers/block/loop.c

@@ -1038,10 +1038,10 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 {
 	int err;
 	struct loop_func_table *xfer;
-	uid_t uid = current_uid();
+	kuid_t uid = current_uid();
 
 	if (lo->lo_encrypt_key_size &&
-	    lo->lo_key_owner != uid &&
+	    !uid_eq(lo->lo_key_owner, uid) &&
 	    !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 	if (lo->lo_state != Lo_bound)

drivers/connector/cn_proc.c

@@ -30,6 +30,7 @@
 #include <linux/gfp.h>
 #include <linux/ptrace.h>
 #include <linux/atomic.h>
+#include <linux/pid_namespace.h>
 
 #include <asm/unaligned.h>
 
@@ -127,11 +128,11 @@ void proc_id_connector(struct task_struct *task, int which_id)
 	rcu_read_lock();
 	cred = __task_cred(task);
 	if (which_id == PROC_EVENT_UID) {
-		ev->event_data.id.r.ruid = cred->uid;
-		ev->event_data.id.e.euid = cred->euid;
+		ev->event_data.id.r.ruid = from_kuid_munged(&init_user_ns, cred->uid);
+		ev->event_data.id.e.euid = from_kuid_munged(&init_user_ns, cred->euid);
 	} else if (which_id == PROC_EVENT_GID) {
-		ev->event_data.id.r.rgid = cred->gid;
-		ev->event_data.id.e.egid = cred->egid;
+		ev->event_data.id.r.rgid = from_kgid_munged(&init_user_ns, cred->gid);
+		ev->event_data.id.e.egid = from_kgid_munged(&init_user_ns, cred->egid);
 	} else {
 		rcu_read_unlock();
 		return;
@@ -303,6 +304,15 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
 	if (msg->len != sizeof(*mc_op))
 		return;
 
+	/* 
+	 * Events are reported with respect to the initial pid
+	 * and user namespaces so ignore requestors from
+	 * other namespaces.
+	 */
+	if ((current_user_ns() != &init_user_ns) ||
+	    (task_active_pid_ns(current) != &init_pid_ns))
+		return;
+
 	mc_op = (enum proc_cn_mcast_op *)msg->data;
 	switch (*mc_op) {
 	case PROC_CN_MCAST_LISTEN:

drivers/gpu/drm/drm_fops.c

@@ -251,7 +251,7 @@ static int drm_open_helper(struct inode *inode, struct file *filp,
 	filp->private_data = priv;
 	priv->filp = filp;
 	priv->uid = current_euid();
-	priv->pid = task_pid_nr(current);
+	priv->pid = get_pid(task_pid(current));
 	priv->minor = idr_find(&drm_minors_idr, minor_id);
 	priv->ioctl_count = 0;
 	/* for compatibility root is always authenticated */
@@ -524,6 +524,7 @@ int drm_release(struct inode *inode, struct file *filp)
 	if (drm_core_check_feature(dev, DRIVER_PRIME))
 		drm_prime_destroy_file_private(&file_priv->prime);
 
+	put_pid(file_priv->pid);
 	kfree(file_priv);
 
 	/* ========================================================

drivers/gpu/drm/drm_info.c

@@ -191,8 +191,9 @@ int drm_clients_info(struct seq_file *m, void *data)
 		seq_printf(m, "%c %3d %5d %5d %10u %10lu\n",
 			   priv->authenticated ? 'y' : 'n',
 			   priv->minor->index,
-			   priv->pid,
-			   priv->uid, priv->magic, priv->ioctl_count);
+			   pid_vnr(priv->pid),
+			   from_kuid_munged(seq_user_ns(m), priv->uid),
+			   priv->magic, priv->ioctl_count);
 	}
 	mutex_unlock(&dev->struct_mutex);
 	return 0;

drivers/gpu/drm/drm_ioctl.c

@@ -215,8 +215,8 @@ int drm_getclient(struct drm_device *dev, void *data,
 	list_for_each_entry(pt, &dev->filelist, lhead) {
 		if (i++ >= idx) {
 			client->auth = pt->authenticated;
-			client->pid = pt->pid;
-			client->uid = pt->uid;
+			client->pid = pid_vnr(pt->pid);
+			client->uid = from_kuid_munged(current_user_ns(), pt->uid);
 			client->magic = pt->magic;
 			client->iocs = pt->ioctl_count;
 			mutex_unlock(&dev->struct_mutex);

drivers/infiniband/hw/qib/qib_fs.c

@@ -61,8 +61,8 @@ static int qibfs_mknod(struct inode *dir, struct dentry *dentry,
 
 	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
-	inode->i_uid = 0;
-	inode->i_gid = 0;
+	inode->i_uid = GLOBAL_ROOT_UID;
+	inode->i_gid = GLOBAL_ROOT_GID;
 	inode->i_blocks = 0;
 	inode->i_atime = CURRENT_TIME;
 	inode->i_mtime = inode->i_atime;