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

Pull user namespace enhancements from Eric Biederman:
 "This is a course correction for the user namespace, so that we can
  reach an inexpensive, maintainable, and reasonably complete
  implementation.

  Highlights:
   - Config guards make it impossible to enable the user namespace and
     code that has not been converted to be user namespace safe.

   - Use of the new kuid_t type ensures the if you somehow get past the
     config guards the kernel will encounter type errors if you enable
     user namespaces and attempt to compile in code whose permission
     checks have not been updated to be user namespace safe.

   - All uids from child user namespaces are mapped into the initial
     user namespace before they are processed.  Removing the need to add
     an additional check to see if the user namespace of the compared
     uids remains the same.

   - With the user namespaces compiled out the performance is as good or
     better than it is today.

   - For most operations absolutely nothing changes performance or
     operationally with the user namespace enabled.

   - The worst case performance I could come up with was timing 1
     billion cache cold stat operations with the user namespace code
     enabled.  This went from 156s to 164s on my laptop (or 156ns to
     164ns per stat operation).

   - (uid_t)-1 and (gid_t)-1 are reserved as an internal error value.
     Most uid/gid setting system calls treat these value specially
     anyway so attempting to use -1 as a uid would likely cause
     entertaining failures in userspace.

   - If setuid is called with a uid that can not be mapped setuid fails.
     I have looked at sendmail, login, ssh and every other program I
     could think of that would call setuid and they all check for and
     handle the case where setuid fails.

   - If stat or a similar system call is called from a context in which
     we can not map a uid we lie and return overflowuid.  The LFS
     experience suggests not lying and returning an error code might be
     better, but the historical precedent with uids is different and I
     can not think of anything that would break by lying about a uid we
     can't map.

   - Capabilities are localized to the current user namespace making it
     safe to give the initial user in a user namespace all capabilities.

  My git tree covers all of the modifications needed to convert the core
  kernel and enough changes to make a system bootable to runlevel 1."

Fix up trivial conflicts due to nearby independent changes in fs/stat.c

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (46 commits)
  userns:  Silence silly gcc warning.
  cred: use correct cred accessor with regards to rcu read lock
  userns: Convert the move_pages, and migrate_pages permission checks to use uid_eq
  userns: Convert cgroup permission checks to use uid_eq
  userns: Convert tmpfs to use kuid and kgid where appropriate
  userns: Convert sysfs to use kgid/kuid where appropriate
  userns: Convert sysctl permission checks to use kuid and kgids.
  userns: Convert proc to use kuid/kgid where appropriate
  userns: Convert ext4 to user kuid/kgid where appropriate
  userns: Convert ext3 to use kuid/kgid where appropriate
  userns: Convert ext2 to use kuid/kgid where appropriate.
  userns: Convert devpts to use kuid/kgid where appropriate
  userns: Convert binary formats to use kuid/kgid where appropriate
  userns: Add negative depends on entries to avoid building code that is userns unsafe
  userns: signal remove unnecessary map_cred_ns
  userns: Teach inode_capable to understand inodes whose uids map to other namespaces.
  userns: Fail exec for suid and sgid binaries with ids outside our user namespace.
  userns: Convert stat to return values mapped from kuids and kgids
  userns: Convert user specfied uids and gids in chown into kuids and kgid
  userns: Use uid_eq gid_eq helpers when comparing kuids and kgids in the vfs
  ...

arch/arm/kernel/sys_oabi-compat.c

@@ -124,8 +124,8 @@ static long cp_oldabi_stat64(struct kstat *stat,
 	tmp.__st_ino = stat->ino;
 	tmp.st_mode = stat->mode;
 	tmp.st_nlink = stat->nlink;
-	tmp.st_uid = stat->uid;
-	tmp.st_gid = stat->gid;
+	tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid);
+	tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid);
 	tmp.st_rdev = huge_encode_dev(stat->rdev);
 	tmp.st_size = stat->size;
 	tmp.st_blocks = stat->blocks;

arch/parisc/hpux/fs.c

@@ -159,8 +159,8 @@ static int cp_hpux_stat(struct kstat *stat, struct hpux_stat64 __user *statbuf)
 	tmp.st_ino = stat->ino;
 	tmp.st_mode = stat->mode;
 	tmp.st_nlink = stat->nlink;
-	tmp.st_uid = stat->uid;
-	tmp.st_gid = stat->gid;
+	tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid);
+	tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid);
 	tmp.st_rdev = new_encode_dev(stat->rdev);
 	tmp.st_size = stat->size;
 	tmp.st_atime = stat->atime.tv_sec;

arch/s390/kernel/compat_linux.c

@@ -173,11 +173,14 @@ asmlinkage long sys32_setfsgid16(u16 gid)
 
 static int groups16_to_user(u16 __user *grouplist, struct group_info *group_info)
 {
+	struct user_namespace *user_ns = current_user_ns();
 	int i;
 	u16 group;
+	kgid_t kgid;
 
 	for (i = 0; i < group_info->ngroups; i++) {
-		group = (u16)GROUP_AT(group_info, i);
+		kgid = GROUP_AT(group_info, i);
+		group = (u16)from_kgid_munged(user_ns, kgid);
 		if (put_user(group, grouplist+i))
 			return -EFAULT;
 	}
@@ -187,13 +190,20 @@ static int groups16_to_user(u16 __user *grouplist, struct group_info *group_info
 
 static int groups16_from_user(struct group_info *group_info, u16 __user *grouplist)
 {
+	struct user_namespace *user_ns = current_user_ns();
 	int i;
 	u16 group;
+	kgid_t kgid;
 
 	for (i = 0; i < group_info->ngroups; i++) {
 		if (get_user(group, grouplist+i))
 			return  -EFAULT;
-		GROUP_AT(group_info, i) = (gid_t)group;
+
+		kgid = make_kgid(user_ns, (gid_t)group);
+		if (!gid_valid(kgid))
+			return -EINVAL;
+
+		GROUP_AT(group_info, i) = kgid;
 	}
 
 	return 0;
@@ -537,8 +547,8 @@ static int cp_stat64(struct stat64_emu31 __user *ubuf, struct kstat *stat)
 	tmp.__st_ino = (u32)stat->ino;
 	tmp.st_mode = stat->mode;
 	tmp.st_nlink = (unsigned int)stat->nlink;
-	tmp.st_uid = stat->uid;
-	tmp.st_gid = stat->gid;
+	tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid);
+	tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid);
 	tmp.st_rdev = huge_encode_dev(stat->rdev);
 	tmp.st_size = stat->size;
 	tmp.st_blksize = (u32)stat->blksize;

arch/sparc/kernel/sys_sparc32.c

@@ -139,8 +139,8 @@ static int cp_compat_stat64(struct kstat *stat,
 	err |= put_user(stat->ino, &statbuf->st_ino);
 	err |= put_user(stat->mode, &statbuf->st_mode);
 	err |= put_user(stat->nlink, &statbuf->st_nlink);
-	err |= put_user(stat->uid, &statbuf->st_uid);
-	err |= put_user(stat->gid, &statbuf->st_gid);
+	err |= put_user(from_kuid_munged(current_user_ns(), stat->uid), &statbuf->st_uid);
+	err |= put_user(from_kgid_munged(current_user_ns(), stat->gid), &statbuf->st_gid);
 	err |= put_user(huge_encode_dev(stat->rdev), &statbuf->st_rdev);
 	err |= put_user(0, (unsigned long __user *) &statbuf->__pad3[0]);
 	err |= put_user(stat->size, &statbuf->st_size);

arch/x86/ia32/sys_ia32.c

@@ -71,8 +71,8 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat)
 {
 	typeof(ubuf->st_uid) uid = 0;
 	typeof(ubuf->st_gid) gid = 0;
-	SET_UID(uid, stat->uid);
-	SET_GID(gid, stat->gid);
+	SET_UID(uid, from_kuid_munged(current_user_ns(), stat->uid));
+	SET_GID(gid, from_kgid_munged(current_user_ns(), stat->gid));
 	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(struct stat64)) ||
 	    __put_user(huge_encode_dev(stat->dev), &ubuf->st_dev) ||
 	    __put_user(stat->ino, &ubuf->__st_ino) ||

arch/x86/mm/fault.c

@@ -582,7 +582,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 		pte_t *pte = lookup_address(address, &level);
 
 		if (pte && pte_present(*pte) && !pte_exec(*pte))
-			printk(nx_warning, current_uid());
+			printk(nx_warning, from_kuid(&init_user_ns, current_uid()));
 	}
 
 	printk(KERN_ALERT "BUG: unable to handle kernel ");

fs/attr.c

@@ -47,14 +47,14 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
 
 	/* Make sure a caller can chown. */
 	if ((ia_valid & ATTR_UID) &&
-	    (current_fsuid() != inode->i_uid ||
-	     attr->ia_uid != inode->i_uid) && !capable(CAP_CHOWN))
+	    (!uid_eq(current_fsuid(), inode->i_uid) ||
+	     !uid_eq(attr->ia_uid, inode->i_uid)) && !capable(CAP_CHOWN))
 		return -EPERM;
 
 	/* Make sure caller can chgrp. */
 	if ((ia_valid & ATTR_GID) &&
-	    (current_fsuid() != inode->i_uid ||
-	    (!in_group_p(attr->ia_gid) && attr->ia_gid != inode->i_gid)) &&
+	    (!uid_eq(current_fsuid(), inode->i_uid) ||
+	    (!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) &&
 	    !capable(CAP_CHOWN))
 		return -EPERM;
 

fs/binfmt_elf.c

@@ -226,10 +226,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	NEW_AUX_ENT(AT_BASE, interp_load_addr);
 	NEW_AUX_ENT(AT_FLAGS, 0);
 	NEW_AUX_ENT(AT_ENTRY, exec->e_entry);
-	NEW_AUX_ENT(AT_UID, cred->uid);
-	NEW_AUX_ENT(AT_EUID, cred->euid);
-	NEW_AUX_ENT(AT_GID, cred->gid);
-	NEW_AUX_ENT(AT_EGID, cred->egid);
+	NEW_AUX_ENT(AT_UID, from_kuid_munged(cred->user_ns, cred->uid));
+	NEW_AUX_ENT(AT_EUID, from_kuid_munged(cred->user_ns, cred->euid));
+	NEW_AUX_ENT(AT_GID, from_kgid_munged(cred->user_ns, cred->gid));
+	NEW_AUX_ENT(AT_EGID, from_kgid_munged(cred->user_ns, cred->egid));
  	NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm));
 	NEW_AUX_ENT(AT_RANDOM, (elf_addr_t)(unsigned long)u_rand_bytes);
 	NEW_AUX_ENT(AT_EXECFN, bprm->exec);
@@ -1356,8 +1356,8 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
 	psinfo->pr_flag = p->flags;
 	rcu_read_lock();
 	cred = __task_cred(p);
-	SET_UID(psinfo->pr_uid, cred->uid);
-	SET_GID(psinfo->pr_gid, cred->gid);
+	SET_UID(psinfo->pr_uid, from_kuid_munged(cred->user_ns, cred->uid));
+	SET_GID(psinfo->pr_gid, from_kgid_munged(cred->user_ns, cred->gid));
 	rcu_read_unlock();
 	strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname));
 	

fs/binfmt_elf_fdpic.c

@@ -627,10 +627,10 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 	NEW_AUX_ENT(AT_BASE,	interp_params->elfhdr_addr);
 	NEW_AUX_ENT(AT_FLAGS,	0);
 	NEW_AUX_ENT(AT_ENTRY,	exec_params->entry_addr);
-	NEW_AUX_ENT(AT_UID,	(elf_addr_t) cred->uid);
-	NEW_AUX_ENT(AT_EUID,	(elf_addr_t) cred->euid);
-	NEW_AUX_ENT(AT_GID,	(elf_addr_t) cred->gid);
-	NEW_AUX_ENT(AT_EGID,	(elf_addr_t) cred->egid);
+	NEW_AUX_ENT(AT_UID,	(elf_addr_t) from_kuid_munged(cred->user_ns, cred->uid));
+	NEW_AUX_ENT(AT_EUID,	(elf_addr_t) from_kuid_munged(cred->user_ns, cred->euid));
+	NEW_AUX_ENT(AT_GID,	(elf_addr_t) from_kgid_munged(cred->user_ns, cred->gid));
+	NEW_AUX_ENT(AT_EGID,	(elf_addr_t) from_kgid_munged(cred->user_ns, cred->egid));
 	NEW_AUX_ENT(AT_SECURE,	security_bprm_secureexec(bprm));
 	NEW_AUX_ENT(AT_EXECFN,	bprm->exec);
 
@@ -1421,8 +1421,8 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
 	psinfo->pr_flag = p->flags;
 	rcu_read_lock();
 	cred = __task_cred(p);
-	SET_UID(psinfo->pr_uid, cred->uid);
-	SET_GID(psinfo->pr_gid, cred->gid);
+	SET_UID(psinfo->pr_uid, from_kuid_munged(cred->user_ns, cred->uid));
+	SET_GID(psinfo->pr_gid, from_kgid_munged(cred->user_ns, cred->gid));
 	rcu_read_unlock();
 	strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname));
 

fs/compat.c

@@ -144,8 +144,8 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
 	tmp.st_nlink = stat->nlink;
 	if (tmp.st_nlink != stat->nlink)
 		return -EOVERFLOW;
-	SET_UID(tmp.st_uid, stat->uid);
-	SET_GID(tmp.st_gid, stat->gid);
+	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
+	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
 	tmp.st_rdev = old_encode_dev(stat->rdev);
 	if ((u64) stat->size > MAX_NON_LFS)
 		return -EOVERFLOW;

fs/devpts/inode.c

@@ -98,8 +98,8 @@ static struct vfsmount *devpts_mnt;
 struct pts_mount_opts {
 	int setuid;
 	int setgid;
-	uid_t   uid;
-	gid_t   gid;
+	kuid_t   uid;
+	kgid_t   gid;
 	umode_t mode;
 	umode_t ptmxmode;
 	int newinstance;
@@ -158,11 +158,13 @@ static inline struct super_block *pts_sb_from_inode(struct inode *inode)
 static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
 {
 	char *p;
+	kuid_t uid;
+	kgid_t gid;
 
 	opts->setuid  = 0;
 	opts->setgid  = 0;
-	opts->uid     = 0;
-	opts->gid     = 0;
+	opts->uid     = GLOBAL_ROOT_UID;
+	opts->gid     = GLOBAL_ROOT_GID;
 	opts->mode    = DEVPTS_DEFAULT_MODE;
 	opts->ptmxmode = DEVPTS_DEFAULT_PTMX_MODE;
 	opts->max     = NR_UNIX98_PTY_MAX;
@@ -184,13 +186,19 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
 		case Opt_uid:
 			if (match_int(&args[0], &option))
 				return -EINVAL;
-			opts->uid = option;
+			uid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(uid))
+				return -EINVAL;
+			opts->uid = uid;
 			opts->setuid = 1;
 			break;
 		case Opt_gid:
 			if (match_int(&args[0], &option))
 				return -EINVAL;
-			opts->gid = option;
+			gid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(gid))
+				return -EINVAL;
+			opts->gid = gid;
 			opts->setgid = 1;
 			break;
 		case Opt_mode:
@@ -315,9 +323,9 @@ static int devpts_show_options(struct seq_file *seq, struct dentry *root)
 	struct pts_mount_opts *opts = &fsi->mount_opts;
 
 	if (opts->setuid)
-		seq_printf(seq, ",uid=%u", opts->uid);
+		seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, opts->uid));
 	if (opts->setgid)
-		seq_printf(seq, ",gid=%u", opts->gid);
+		seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, opts->gid));
 	seq_printf(seq, ",mode=%03o", opts->mode);
 #ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 	seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode);

fs/ecryptfs/messaging.c

@@ -303,7 +303,7 @@ int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t euid,
 		mutex_unlock(&ecryptfs_daemon_hash_mux);
 		goto wake_up;
 	}
-	tsk_user_ns = __task_cred(msg_ctx->task)->user->user_ns;
+	tsk_user_ns = __task_cred(msg_ctx->task)->user_ns;
 	ctx_euid = task_euid(msg_ctx->task);
 	rc = ecryptfs_find_daemon_by_euid(&daemon, ctx_euid, tsk_user_ns);
 	rcu_read_unlock();

fs/exec.c

@@ -1139,7 +1139,7 @@ void setup_new_exec(struct linux_binprm * bprm)
 	/* This is the point of no return */
 	current->sas_ss_sp = current->sas_ss_size = 0;
 
-	if (current_euid() == current_uid() && current_egid() == current_gid())
+	if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid()))
 		set_dumpable(current->mm, 1);
 	else
 		set_dumpable(current->mm, suid_dumpable);
@@ -1153,8 +1153,8 @@ void setup_new_exec(struct linux_binprm * bprm)
 	current->mm->task_size = TASK_SIZE;
 
 	/* install the new credentials */
-	if (bprm->cred->uid != current_euid() ||
-	    bprm->cred->gid != current_egid()) {
+	if (!uid_eq(bprm->cred->uid, current_euid()) ||
+	    !gid_eq(bprm->cred->gid, current_egid())) {
 		current->pdeath_signal = 0;
 	} else {
 		would_dump(bprm, bprm->file);
@@ -1299,8 +1299,11 @@ int prepare_binprm(struct linux_binprm *bprm)
 	    !current->no_new_privs) {
 		/* Set-uid? */
 		if (mode & S_ISUID) {
+			if (!kuid_has_mapping(bprm->cred->user_ns, inode->i_uid))
+				return -EPERM;
 			bprm->per_clear |= PER_CLEAR_ON_SETID;
 			bprm->cred->euid = inode->i_uid;
+
 		}
 
 		/* Set-gid? */
@@ -1310,6 +1313,8 @@ int prepare_binprm(struct linux_binprm *bprm)
 		 * executable.
 		 */
 		if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
+			if (!kgid_has_mapping(bprm->cred->user_ns, inode->i_gid))
+				return -EPERM;
 			bprm->per_clear |= PER_CLEAR_ON_SETID;
 			bprm->cred->egid = inode->i_gid;
 		}
@@ -2142,7 +2147,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 	if (__get_dumpable(cprm.mm_flags) == 2) {
 		/* Setuid core dump mode */
 		flag = O_EXCL;		/* Stop rewrite attacks */
-		cred->fsuid = 0;	/* Dump root private */
+		cred->fsuid = GLOBAL_ROOT_UID;	/* Dump root private */
 	}
 
 	retval = coredump_wait(exit_code, &core_state);
@@ -2243,7 +2248,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 		 * Dont allow local users get cute and trick others to coredump
 		 * into their pre-created files.
 		 */
-		if (inode->i_uid != current_fsuid())
+		if (!uid_eq(inode->i_uid, current_fsuid()))
 			goto close_fail;
 		if (!cprm.file->f_op || !cprm.file->f_op->write)
 			goto close_fail;

fs/ext2/balloc.c

@@ -1193,8 +1193,9 @@ static int ext2_has_free_blocks(struct ext2_sb_info *sbi)
 	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
 	root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count);
 	if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
-		sbi->s_resuid != current_fsuid() &&
-		(sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
+		!uid_eq(sbi->s_resuid, current_fsuid()) &&
+		(gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) ||
+		 !in_group_p (sbi->s_resgid))) {
 		return 0;
 	}
 	return 1;

fs/ext2/ext2.h

@@ -82,8 +82,8 @@ struct ext2_sb_info {
 	struct buffer_head ** s_group_desc;
 	unsigned long  s_mount_opt;
 	unsigned long s_sb_block;
-	uid_t s_resuid;
-	gid_t s_resgid;
+	kuid_t s_resuid;
+	kgid_t s_resgid;
 	unsigned short s_mount_state;
 	unsigned short s_pad;
 	int s_addr_per_block_bits;
@@ -637,8 +637,8 @@ static inline void verify_offsets(void)
  */
 struct ext2_mount_options {
 	unsigned long s_mount_opt;
-	uid_t s_resuid;
-	gid_t s_resgid;
+	kuid_t s_resuid;
+	kgid_t s_resgid;
 };
 
 /*

fs/ext2/inode.c

@@ -1293,6 +1293,8 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 	struct inode *inode;
 	long ret = -EIO;
 	int n;
+	uid_t i_uid;
+	gid_t i_gid;
 
 	inode = iget_locked(sb, ino);
 	if (!inode)
@@ -1310,12 +1312,14 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 	}
 
 	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
-	inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
-	inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
+	i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
+	i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
 	if (!(test_opt (inode->i_sb, NO_UID32))) {
-		inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
-		inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
+		i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
+		i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
 	}
+	i_uid_write(inode, i_uid);
+	i_gid_write(inode, i_gid);
 	set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
 	inode->i_size = le32_to_cpu(raw_inode->i_size);
 	inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
@@ -1413,8 +1417,8 @@ static int __ext2_write_inode(struct inode *inode, int do_sync)
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	struct super_block *sb = inode->i_sb;
 	ino_t ino = inode->i_ino;
-	uid_t uid = inode->i_uid;
-	gid_t gid = inode->i_gid;
+	uid_t uid = i_uid_read(inode);
+	gid_t gid = i_gid_read(inode);
 	struct buffer_head * bh;
 	struct ext2_inode * raw_inode = ext2_get_inode(sb, ino, &bh);
 	int n;
@@ -1529,8 +1533,8 @@ int ext2_setattr(struct dentry *dentry, struct iattr *iattr)
 
 	if (is_quota_modification(inode, iattr))
 		dquot_initialize(inode);
-	if ((iattr->ia_valid & ATTR_UID && iattr->ia_uid != inode->i_uid) ||
-	    (iattr->ia_valid & ATTR_GID && iattr->ia_gid != inode->i_gid)) {
+	if ((iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)) ||
+	    (iattr->ia_valid & ATTR_GID && !gid_eq(iattr->ia_gid, inode->i_gid))) {
 		error = dquot_transfer(inode, iattr);
 		if (error)
 			return error;

fs/ext2/super.c

@@ -228,13 +228,15 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",grpid");
 	if (!test_opt(sb, GRPID) && (def_mount_opts & EXT2_DEFM_BSDGROUPS))
 		seq_puts(seq, ",nogrpid");
-	if (sbi->s_resuid != EXT2_DEF_RESUID ||
+	if (!uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT2_DEF_RESUID)) ||
 	    le16_to_cpu(es->s_def_resuid) != EXT2_DEF_RESUID) {
-		seq_printf(seq, ",resuid=%u", sbi->s_resuid);
+		seq_printf(seq, ",resuid=%u",
+				from_kuid_munged(&init_user_ns, sbi->s_resuid));
 	}
-	if (sbi->s_resgid != EXT2_DEF_RESGID ||
+	if (!gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT2_DEF_RESGID)) ||
 	    le16_to_cpu(es->s_def_resgid) != EXT2_DEF_RESGID) {
-		seq_printf(seq, ",resgid=%u", sbi->s_resgid);
+		seq_printf(seq, ",resgid=%u",
+				from_kgid_munged(&init_user_ns, sbi->s_resgid));
 	}
 	if (test_opt(sb, ERRORS_RO)) {
 		int def_errors = le16_to_cpu(es->s_errors);
@@ -436,6 +438,8 @@ static int parse_options(char *options, struct super_block *sb)
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
 	substring_t args[MAX_OPT_ARGS];
 	int option;
+	kuid_t uid;
+	kgid_t gid;
 
 	if (!options)
 		return 1;
@@ -462,12 +466,23 @@ static int parse_options(char *options, struct super_block *sb)
 		case Opt_resuid:
 			if (match_int(&args[0], &option))
 				return 0;
-			sbi->s_resuid = option;
+			uid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(uid)) {
+				ext2_msg(sb, KERN_ERR, "Invalid uid value %d", option);
+				return -1;
+
+			}
+			sbi->s_resuid = uid;
 			break;
 		case Opt_resgid:
 			if (match_int(&args[0], &option))
 				return 0;
-			sbi->s_resgid = option;
+			gid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(gid)) {
+				ext2_msg(sb, KERN_ERR, "Invalid gid value %d", option);
+				return -1;
+			}
+			sbi->s_resgid = gid;
 			break;
 		case Opt_sb:
 			/* handled by get_sb_block() instead of here */
@@ -841,8 +856,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	else
 		set_opt(sbi->s_mount_opt, ERRORS_RO);
 
-	sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
-	sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
+	sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid));
+	sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid));
 	
 	set_opt(sbi->s_mount_opt, RESERVATION);
 

fs/ext3/balloc.c

@@ -1439,8 +1439,9 @@ static int ext3_has_free_blocks(struct ext3_sb_info *sbi, int use_reservation)
 	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
 	root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count);
 	if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
-		!use_reservation && sbi->s_resuid != current_fsuid() &&
-		(sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
+		!use_reservation && !uid_eq(sbi->s_resuid, current_fsuid()) &&
+		(gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) ||
+		 !in_group_p (sbi->s_resgid))) {
 		return 0;
 	}
 	return 1;

fs/ext3/ext3.h

@@ -243,8 +243,8 @@ struct ext3_new_group_data {
  */
 struct ext3_mount_options {
 	unsigned long s_mount_opt;
-	uid_t s_resuid;
-	gid_t s_resgid;
+	kuid_t s_resuid;
+	kgid_t s_resgid;
 	unsigned long s_commit_interval;
 #ifdef CONFIG_QUOTA
 	int s_jquota_fmt;
@@ -637,8 +637,8 @@ struct ext3_sb_info {
 	struct buffer_head ** s_group_desc;
 	unsigned long  s_mount_opt;
 	ext3_fsblk_t s_sb_block;
-	uid_t s_resuid;
-	gid_t s_resgid;
+	kuid_t s_resuid;
+	kgid_t s_resgid;
 	unsigned short s_mount_state;
 	unsigned short s_pad;
 	int s_addr_per_block_bits;

fs/ext3/inode.c

@@ -2891,6 +2891,8 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino)
 	transaction_t *transaction;
 	long ret;
 	int block;
+	uid_t i_uid;
+	gid_t i_gid;
 
 	inode = iget_locked(sb, ino);
 	if (!inode)
@@ -2907,12 +2909,14 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino)
 	bh = iloc.bh;
 	raw_inode = ext3_raw_inode(&iloc);
 	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
-	inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
-	inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
+	i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
+	i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
 	if(!(test_opt (inode->i_sb, NO_UID32))) {
-		inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
-		inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
+		i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
+		i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
 	}
+	i_uid_write(inode, i_uid);
+	i_gid_write(inode, i_gid);
 	set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
 	inode->i_size = le32_to_cpu(raw_inode->i_size);
 	inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
@@ -3068,6 +3072,8 @@ static int ext3_do_update_inode(handle_t *handle,
 	struct ext3_inode_info *ei = EXT3_I(inode);
 	struct buffer_head *bh = iloc->bh;
 	int err = 0, rc, block;
+	uid_t i_uid;
+	gid_t i_gid;
 
 again:
 	/* we can't allow multiple procs in here at once, its a bit racey */
@@ -3080,27 +3086,29 @@ again:
 
 	ext3_get_inode_flags(ei);
 	raw_inode->i_mode = cpu_to_le16(inode->i_mode);
+	i_uid = i_uid_read(inode);
+	i_gid = i_gid_read(inode);
 	if(!(test_opt(inode->i_sb, NO_UID32))) {
-		raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid));
-		raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid));
+		raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid));
+		raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid));
 /*
  * Fix up interoperability with old kernels. Otherwise, old inodes get
  * re-used with the upper 16 bits of the uid/gid intact
  */
 		if(!ei->i_dtime) {
 			raw_inode->i_uid_high =
-				cpu_to_le16(high_16_bits(inode->i_uid));
+				cpu_to_le16(high_16_bits(i_uid));
 			raw_inode->i_gid_high =
-				cpu_to_le16(high_16_bits(inode->i_gid));
+				cpu_to_le16(high_16_bits(i_gid));
 		} else {
 			raw_inode->i_uid_high = 0;
 			raw_inode->i_gid_high = 0;
 		}
 	} else {
 		raw_inode->i_uid_low =
-			cpu_to_le16(fs_high2lowuid(inode->i_uid));
+			cpu_to_le16(fs_high2lowuid(i_uid));
 		raw_inode->i_gid_low =
-			cpu_to_le16(fs_high2lowgid(inode->i_gid));
+			cpu_to_le16(fs_high2lowgid(i_gid));
 		raw_inode->i_uid_high = 0;
 		raw_inode->i_gid_high = 0;
 	}
@@ -3262,8 +3270,8 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if (is_quota_modification(inode, attr))
 		dquot_initialize(inode);
-	if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
-		(ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
+	if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) ||
+	    (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) {
 		handle_t *handle;
 
 		/* (user+group)*(old+new) structure, inode write (sb,

fs/ext3/super.c

@@ -617,13 +617,15 @@ static int ext3_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",grpid");
 	if (!test_opt(sb, GRPID) && (def_mount_opts & EXT3_DEFM_BSDGROUPS))
 		seq_puts(seq, ",nogrpid");
-	if (sbi->s_resuid != EXT3_DEF_RESUID ||
+	if (!uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT3_DEF_RESUID)) ||
 	    le16_to_cpu(es->s_def_resuid) != EXT3_DEF_RESUID) {
-		seq_printf(seq, ",resuid=%u", sbi->s_resuid);
+		seq_printf(seq, ",resuid=%u",
+				from_kuid_munged(&init_user_ns, sbi->s_resuid));
 	}
-	if (sbi->s_resgid != EXT3_DEF_RESGID ||
+	if (!gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT3_DEF_RESGID)) ||
 	    le16_to_cpu(es->s_def_resgid) != EXT3_DEF_RESGID) {
-		seq_printf(seq, ",resgid=%u", sbi->s_resgid);
+		seq_printf(seq, ",resgid=%u",
+				from_kgid_munged(&init_user_ns, sbi->s_resgid));
 	}
 	if (test_opt(sb, ERRORS_RO)) {
 		int def_errors = le16_to_cpu(es->s_errors);
@@ -967,6 +969,8 @@ static int parse_options (char *options, struct super_block *sb,
 	substring_t args[MAX_OPT_ARGS];
 	int data_opt = 0;
 	int option;
+	kuid_t uid;
+	kgid_t gid;
 #ifdef CONFIG_QUOTA
 	int qfmt;
 #endif
@@ -1000,12 +1004,23 @@ static int parse_options (char *options, struct super_block *sb,
 		case Opt_resuid:
 			if (match_int(&args[0], &option))
 				return 0;
-			sbi->s_resuid = option;
+			uid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(uid)) {
+				ext3_msg(sb, KERN_ERR, "Invalid uid value %d", option);
+				return -1;
+
+			}
+			sbi->s_resuid = uid;
 			break;
 		case Opt_resgid:
 			if (match_int(&args[0], &option))
 				return 0;
-			sbi->s_resgid = option;
+			gid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(gid)) {
+				ext3_msg(sb, KERN_ERR, "Invalid gid value %d", option);
+				return -1;
+			}
+			sbi->s_resgid = gid;
 			break;
 		case Opt_sb:
 			/* handled by get_sb_block() instead of here */
@@ -1651,8 +1666,8 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 	}
 	sb->s_fs_info = sbi;
 	sbi->s_mount_opt = 0;
-	sbi->s_resuid = EXT3_DEF_RESUID;
-	sbi->s_resgid = EXT3_DEF_RESGID;
+	sbi->s_resuid = make_kuid(&init_user_ns, EXT3_DEF_RESUID);
+	sbi->s_resgid = make_kgid(&init_user_ns, EXT3_DEF_RESGID);
 	sbi->s_sb_block = sb_block;
 
 	blocksize = sb_min_blocksize(sb, EXT3_MIN_BLOCK_SIZE);
@@ -1716,8 +1731,8 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 	else
 		set_opt(sbi->s_mount_opt, ERRORS_RO);
 
-	sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
-	sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
+	sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid));
+	sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid));
 
 	/* enable barriers by default */
 	set_opt(sbi->s_mount_opt, BARRIER);

fs/ext4/balloc.c

@@ -461,8 +461,8 @@ static int ext4_has_free_clusters(struct ext4_sb_info *sbi,
 		return 1;
 
 	/* Hm, nope.  Are (enough) root reserved clusters available? */
-	if (sbi->s_resuid == current_fsuid() ||
-	    ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) ||
+	if (uid_eq(sbi->s_resuid, current_fsuid()) ||
+	    (!gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) && in_group_p(sbi->s_resgid)) ||
 	    capable(CAP_SYS_RESOURCE) ||
 		(flags & EXT4_MB_USE_ROOT_BLOCKS)) {
 

fs/ext4/ext4.h

@@ -1153,8 +1153,8 @@ struct ext4_sb_info {
 	unsigned int s_mount_flags;
 	unsigned int s_def_mount_opt;
 	ext4_fsblk_t s_sb_block;
-	uid_t s_resuid;
-	gid_t s_resgid;
+	kuid_t s_resuid;
+	kgid_t s_resgid;
 	unsigned short s_mount_state;
 	unsigned short s_pad;
 	int s_addr_per_block_bits;

fs/ext4/ialloc.c

@@ -808,8 +808,8 @@ got:
 	}
 	if (owner) {
 		inode->i_mode = mode;
-		inode->i_uid = owner[0];
-		inode->i_gid = owner[1];
+		i_uid_write(inode, owner[0]);
+		i_gid_write(inode, owner[1]);
 	} else if (test_opt(sb, GRPID)) {
 		inode->i_mode = mode;
 		inode->i_uid = current_fsuid();

fs/ext4/inode.c

@@ -3630,6 +3630,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	journal_t *journal = EXT4_SB(sb)->s_journal;
 	long ret;
 	int block;
+	uid_t i_uid;
+	gid_t i_gid;
 
 	inode = iget_locked(sb, ino);
 	if (!inode)
@@ -3645,12 +3647,14 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		goto bad_inode;
 	raw_inode = ext4_raw_inode(&iloc);
 	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
-	inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
-	inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
+	i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
+	i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
 	if (!(test_opt(inode->i_sb, NO_UID32))) {
-		inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
-		inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
+		i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
+		i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
 	}
+	i_uid_write(inode, i_uid);
+	i_gid_write(inode, i_gid);
 	set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
 
 	ext4_clear_state_flags(ei);	/* Only relevant on 32-bit archs */
@@ -3870,6 +3874,8 @@ static int ext4_do_update_inode(handle_t *handle,
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct buffer_head *bh = iloc->bh;
 	int err = 0, rc, block;
+	uid_t i_uid;
+	gid_t i_gid;
 
 	/* For fields not not tracking in the in-memory inode,
 	 * initialise them to zero for new inodes. */
@@ -3878,27 +3884,27 @@ static int ext4_do_update_inode(handle_t *handle,
 
 	ext4_get_inode_flags(ei);
 	raw_inode->i_mode = cpu_to_le16(inode->i_mode);
+	i_uid = i_uid_read(inode);
+	i_gid = i_gid_read(inode);
 	if (!(test_opt(inode->i_sb, NO_UID32))) {
-		raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid));
-		raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid));
+		raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid));
+		raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid));
 /*
  * Fix up interoperability with old kernels. Otherwise, old inodes get
  * re-used with the upper 16 bits of the uid/gid intact
  */
 		if (!ei->i_dtime) {
 			raw_inode->i_uid_high =
-				cpu_to_le16(high_16_bits(inode->i_uid));
+				cpu_to_le16(high_16_bits(i_uid));
 			raw_inode->i_gid_high =
-				cpu_to_le16(high_16_bits(inode->i_gid));
+				cpu_to_le16(high_16_bits(i_gid));
 		} else {
 			raw_inode->i_uid_high = 0;
 			raw_inode->i_gid_high = 0;
 		}
 	} else {
-		raw_inode->i_uid_low =
-			cpu_to_le16(fs_high2lowuid(inode->i_uid));
-		raw_inode->i_gid_low =
-			cpu_to_le16(fs_high2lowgid(inode->i_gid));
+		raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid));
+		raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid));
 		raw_inode->i_uid_high = 0;
 		raw_inode->i_gid_high = 0;
 	}
@@ -4084,8 +4090,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if (is_quota_modification(inode, attr))
 		dquot_initialize(inode);
-	if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
-		(ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
+	if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) ||
+	    (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) {
 		handle_t *handle;
 
 		/* (user+group)*(old+new) structure, inode write (sb,

fs/ext4/migrate.c

@@ -466,8 +466,8 @@ int ext4_ext_migrate(struct inode *inode)
 	}
 	goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
 		EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
-	owner[0] = inode->i_uid;
-	owner[1] = inode->i_gid;
+	owner[0] = i_uid_read(inode);
+	owner[1] = i_gid_read(inode);
 	tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
 				   S_IFREG, NULL, goal, owner);
 	if (IS_ERR(tmp_inode)) {

fs/ext4/super.c

@@ -1448,6 +1448,8 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	const struct mount_opts *m;
+	kuid_t uid;
+	kgid_t gid;
 	int arg = 0;
 
 #ifdef CONFIG_QUOTA
@@ -1474,10 +1476,20 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			 "Ignoring removed %s option", opt);
 		return 1;
 	case Opt_resuid:
-		sbi->s_resuid = arg;
+		uid = make_kuid(current_user_ns(), arg);
+		if (!uid_valid(uid)) {
+			ext4_msg(sb, KERN_ERR, "Invalid uid value %d", arg);
+			return -1;
+		}
+		sbi->s_resuid = uid;
 		return 1;
 	case Opt_resgid:
-		sbi->s_resgid = arg;
+		gid = make_kgid(current_user_ns(), arg);
+		if (!gid_valid(gid)) {
+			ext4_msg(sb, KERN_ERR, "Invalid gid value %d", arg);
+			return -1;
+		}
+		sbi->s_resgid = gid;
 		return 1;
 	case Opt_abort:
 		sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
@@ -1732,12 +1744,14 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 		SEQ_OPTS_PRINT("%s", token2str(m->token));
 	}
 
-	if (nodefs || sbi->s_resuid != EXT4_DEF_RESUID ||
+	if (nodefs || !uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT4_DEF_RESUID)) ||
 	    le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID)
-		SEQ_OPTS_PRINT("resuid=%u", sbi->s_resuid);
-	if (nodefs || sbi->s_resgid != EXT4_DEF_RESGID ||
+		SEQ_OPTS_PRINT("resuid=%u",
+				from_kuid_munged(&init_user_ns, sbi->s_resuid));
+	if (nodefs || !gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT4_DEF_RESGID)) ||
 	    le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID)
-		SEQ_OPTS_PRINT("resgid=%u", sbi->s_resgid);
+		SEQ_OPTS_PRINT("resgid=%u",
+				from_kgid_munged(&init_user_ns, sbi->s_resgid));
 	def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors);
 	if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO)
 		SEQ_OPTS_PUTS("errors=remount-ro");
@@ -2980,8 +2994,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 	sb->s_fs_info = sbi;
 	sbi->s_mount_opt = 0;
-	sbi->s_resuid = EXT4_DEF_RESUID;
-	sbi->s_resgid = EXT4_DEF_RESGID;
+	sbi->s_resuid = make_kuid(&init_user_ns, EXT4_DEF_RESUID);
+	sbi->s_resgid = make_kgid(&init_user_ns, EXT4_DEF_RESGID);
 	sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
 	sbi->s_sb_block = sb_block;
 	if (sb->s_bdev->bd_part)
@@ -3060,8 +3074,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (def_mount_opts & EXT4_DEFM_DISCARD)
 		set_opt(sb, DISCARD);
 
-	sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
-	sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
+	sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid));
+	sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid));
 	sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ;
 	sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME;
 	sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
@@ -4213,8 +4227,8 @@ static int ext4_unfreeze(struct super_block *sb)
 struct ext4_mount_options {
 	unsigned long s_mount_opt;
 	unsigned long s_mount_opt2;
-	uid_t s_resuid;
-	gid_t s_resgid;
+	kuid_t s_resuid;
+	kgid_t s_resgid;
 	unsigned long s_commit_interval;
 	u32 s_min_batch_time, s_max_batch_time;
 #ifdef CONFIG_QUOTA

fs/fcntl.c

@@ -532,9 +532,9 @@ static inline int sigio_perm(struct task_struct *p,
 
 	rcu_read_lock();
 	cred = __task_cred(p);
-	ret = ((fown->euid == 0 ||
-		fown->euid == cred->suid || fown->euid == cred->uid ||
-		fown->uid  == cred->suid || fown->uid  == cred->uid) &&
+	ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) ||
+		uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) ||
+		uid_eq(fown->uid,  cred->suid) || uid_eq(fown->uid,  cred->uid)) &&
 	       !security_file_send_sigiotask(p, fown, sig));
 	rcu_read_unlock();
 	return ret;

fs/inode.c

@@ -135,8 +135,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_fop = &empty_fops;
 	inode->__i_nlink = 1;
 	inode->i_opflags = 0;
-	inode->i_uid = 0;
-	inode->i_gid = 0;
+	i_uid_write(inode, 0);
+	i_gid_write(inode, 0);
 	atomic_set(&inode->i_writecount, 0);
 	inode->i_size = 0;
 	inode->i_blocks = 0;
@@ -1732,11 +1732,9 @@ EXPORT_SYMBOL(inode_init_owner);
  */
 bool inode_owner_or_capable(const struct inode *inode)
 {
-	struct user_namespace *ns = inode_userns(inode);
-
-	if (current_user_ns() == ns && current_fsuid() == inode->i_uid)
+	if (uid_eq(current_fsuid(), inode->i_uid))
 		return true;
-	if (ns_capable(ns, CAP_FOWNER))
+	if (inode_capable(inode, CAP_FOWNER))
 		return true;
 	return false;
 }

fs/ioprio.c

@@ -37,8 +37,8 @@ int set_task_ioprio(struct task_struct *task, int ioprio)
 
 	rcu_read_lock();
 	tcred = __task_cred(task);
-	if (tcred->uid != cred->euid &&
-	    tcred->uid != cred->uid && !capable(CAP_SYS_NICE)) {
+	if (!uid_eq(tcred->uid, cred->euid) &&
+	    !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) {
 		rcu_read_unlock();
 		return -EPERM;
 	}
@@ -65,6 +65,7 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
 	struct task_struct *p, *g;
 	struct user_struct *user;
 	struct pid *pgrp;
+	kuid_t uid;
 	int ret;
 
 	switch (class) {
@@ -110,16 +111,19 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
 			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
 			break;
 		case IOPRIO_WHO_USER:
+			uid = make_kuid(current_user_ns(), who);
+			if (!uid_valid(uid))
+				break;
 			if (!who)
 				user = current_user();
 			else
-				user = find_user(who);
+				user = find_user(uid);
 
 			if (!user)
 				break;
 
 			do_each_thread(g, p) {
-				if (__task_cred(p)->uid != who)
+				if (!uid_eq(task_uid(p), uid))
 					continue;
 				ret = set_task_ioprio(p, ioprio);
 				if (ret)
@@ -174,6 +178,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
 	struct task_struct *g, *p;
 	struct user_struct *user;
 	struct pid *pgrp;
+	kuid_t uid;
 	int ret = -ESRCH;
 	int tmpio;
 
@@ -203,16 +208,17 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
 			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
 			break;
 		case IOPRIO_WHO_USER:
+			uid = make_kuid(current_user_ns(), who);
 			if (!who)
 				user = current_user();
 			else
-				user = find_user(who);
+				user = find_user(uid);
 
 			if (!user)
 				break;
 
 			do_each_thread(g, p) {
-				if (__task_cred(p)->uid != user->uid)
+				if (!uid_eq(task_uid(p), user->uid))
 					continue;
 				tmpio = get_task_ioprio(p);
 				if (tmpio < 0)

fs/locks.c

@@ -1446,7 +1446,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
 	struct inode *inode = dentry->d_inode;
 	int error;
 
-	if ((current_fsuid() != inode->i_uid) && !capable(CAP_LEASE))
+	if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE))
 		return -EACCES;
 	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;

fs/namei.c

@@ -218,10 +218,7 @@ static int acl_permission_check(struct inode *inode, int mask)
 {
 	unsigned int mode = inode->i_mode;
 
-	if (current_user_ns() != inode_userns(inode))
-		goto other_perms;
-
-	if (likely(current_fsuid() == inode->i_uid))
+	if (likely(uid_eq(current_fsuid(), inode->i_uid)))
 		mode >>= 6;
 	else {
 		if (IS_POSIXACL(inode) && (mode & S_IRWXG)) {
@@ -234,7 +231,6 @@ static int acl_permission_check(struct inode *inode, int mask)
 			mode >>= 3;
 	}
 
-other_perms:
 	/*
 	 * If the DACs are ok we don't need any capability check.
 	 */
@@ -270,10 +266,10 @@ int generic_permission(struct inode *inode, int mask)
 
 	if (S_ISDIR(inode->i_mode)) {
 		/* DACs are overridable for directories */
-		if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE))
+		if (inode_capable(inode, CAP_DAC_OVERRIDE))
 			return 0;
 		if (!(mask & MAY_WRITE))
-			if (ns_capable(inode_userns(inode), CAP_DAC_READ_SEARCH))
+			if (inode_capable(inode, CAP_DAC_READ_SEARCH))
 				return 0;
 		return -EACCES;
 	}
@@ -283,7 +279,7 @@ int generic_permission(struct inode *inode, int mask)
 	 * at least one exec bit set.
 	 */
 	if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
-		if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE))
+		if (inode_capable(inode, CAP_DAC_OVERRIDE))
 			return 0;
 
 	/*
@@ -291,7 +287,7 @@ int generic_permission(struct inode *inode, int mask)
 	 */
 	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
 	if (mask == MAY_READ)
-		if (ns_capable(inode_userns(inode), CAP_DAC_READ_SEARCH))
+		if (inode_capable(inode, CAP_DAC_READ_SEARCH))
 			return 0;
 
 	return -EACCES;
@@ -1934,19 +1930,15 @@ static int user_path_parent(int dfd, const char __user *path,
  */
 static inline int check_sticky(struct inode *dir, struct inode *inode)
 {
-	uid_t fsuid = current_fsuid();
+	kuid_t fsuid = current_fsuid();
 
 	if (!(dir->i_mode & S_ISVTX))
 		return 0;
-	if (current_user_ns() != inode_userns(inode))
-		goto other_userns;
-	if (inode->i_uid == fsuid)
+	if (uid_eq(inode->i_uid, fsuid))
 		return 0;
-	if (dir->i_uid == fsuid)
+	if (uid_eq(dir->i_uid, fsuid))
 		return 0;
-
-other_userns:
-	return !ns_capable(inode_userns(inode), CAP_FOWNER);
+	return !inode_capable(inode, CAP_FOWNER);
 }
 
 /*
@@ -2534,8 +2526,7 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
 	if (error)
 		return error;
 
-	if ((S_ISCHR(mode) || S_ISBLK(mode)) &&
-	    !ns_capable(inode_userns(dir), CAP_MKNOD))
+	if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
 		return -EPERM;
 
 	if (!dir->i_op->mknod)

fs/nfsd/auth.c

@@ -1,6 +1,7 @@
 /* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */
 
 #include <linux/sched.h>
+#include <linux/user_namespace.h>
 #include "nfsd.h"
 #include "auth.h"
 
@@ -56,8 +57,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 			goto oom;
 
 		for (i = 0; i < rqgi->ngroups; i++) {
-			if (!GROUP_AT(rqgi, i))
-				GROUP_AT(gi, i) = exp->ex_anon_gid;
+			if (gid_eq(GLOBAL_ROOT_GID, GROUP_AT(rqgi, i)))
+				GROUP_AT(gi, i) = make_kgid(&init_user_ns, exp->ex_anon_gid);
 			else
 				GROUP_AT(gi, i) = GROUP_AT(rqgi, i);
 		}

fs/open.c

@@ -316,7 +316,8 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
 
 	if (!issecure(SECURE_NO_SETUID_FIXUP)) {
 		/* Clear the capabilities if we switch to a non-root user */
-		if (override_cred->uid)
+		kuid_t root_uid = make_kuid(override_cred->user_ns, 0);
+		if (!uid_eq(override_cred->uid, root_uid))
 			cap_clear(override_cred->cap_effective);
 		else
 			override_cred->cap_effective =
@@ -505,15 +506,24 @@ static int chown_common(struct path *path, uid_t user, gid_t group)
 	struct inode *inode = path->dentry->d_inode;
 	int error;
 	struct iattr newattrs;
+	kuid_t uid;
+	kgid_t gid;
+
+	uid = make_kuid(current_user_ns(), user);
+	gid = make_kgid(current_user_ns(), group);
 
 	newattrs.ia_valid =  ATTR_CTIME;
 	if (user != (uid_t) -1) {
+		if (!uid_valid(uid))
+			return -EINVAL;
 		newattrs.ia_valid |= ATTR_UID;
-		newattrs.ia_uid = user;
+		newattrs.ia_uid = uid;
 	}
 	if (group != (gid_t) -1) {
+		if (!gid_valid(gid))
+			return -EINVAL;
 		newattrs.ia_valid |= ATTR_GID;
-		newattrs.ia_gid = group;
+		newattrs.ia_gid = gid;
 	}
 	if (!S_ISDIR(inode->i_mode))
 		newattrs.ia_valid |=

fs/proc/array.c

@@ -81,6 +81,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/ptrace.h>
 #include <linux/tracehook.h>
+#include <linux/user_namespace.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -161,6 +162,7 @@ static inline const char *get_task_state(struct task_struct *tsk)
 static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *p)
 {
+	struct user_namespace *user_ns = current_user_ns();
 	struct group_info *group_info;
 	int g;
 	struct fdtable *fdt = NULL;
@@ -189,8 +191,14 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 		task_tgid_nr_ns(p, ns),
 		pid_nr_ns(pid, ns),
 		ppid, tpid,
-		cred->uid, cred->euid, cred->suid, cred->fsuid,
-		cred->gid, cred->egid, cred->sgid, cred->fsgid);
+		from_kuid_munged(user_ns, cred->uid),
+		from_kuid_munged(user_ns, cred->euid),
+		from_kuid_munged(user_ns, cred->suid),
+		from_kuid_munged(user_ns, cred->fsuid),
+		from_kgid_munged(user_ns, cred->gid),
+		from_kgid_munged(user_ns, cred->egid),
+		from_kgid_munged(user_ns, cred->sgid),
+		from_kgid_munged(user_ns, cred->fsgid));
 
 	task_lock(p);
 	if (p->files)
@@ -205,7 +213,8 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 	task_unlock(p);
 
 	for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++)
-		seq_printf(m, "%d ", GROUP_AT(group_info, g));
+		seq_printf(m, "%d ",
+			   from_kgid_munged(user_ns, GROUP_AT(group_info, g)));
 	put_cred(cred);
 
 	seq_putc(m, '\n');

fs/proc/base.c

@@ -81,6 +81,7 @@
 #include <linux/oom.h>
 #include <linux/elf.h>
 #include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
 #include <linux/fs_struct.h>
 #include <linux/slab.h>
 #include <linux/flex_array.h>
@@ -1561,8 +1562,8 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 	generic_fillattr(inode, stat);
 
 	rcu_read_lock();
-	stat->uid = 0;
-	stat->gid = 0;
+	stat->uid = GLOBAL_ROOT_UID;
+	stat->gid = GLOBAL_ROOT_GID;
 	task = pid_task(proc_pid(inode), PIDTYPE_PID);
 	if (task) {
 		if (!has_pid_permissions(pid, task, 2)) {
@@ -1622,8 +1623,8 @@ int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
 			inode->i_gid = cred->egid;
 			rcu_read_unlock();
 		} else {
-			inode->i_uid = 0;
-			inode->i_gid = 0;
+			inode->i_uid = GLOBAL_ROOT_UID;
+			inode->i_gid = GLOBAL_ROOT_GID;
 		}
 		inode->i_mode &= ~(S_ISUID | S_ISGID);
 		security_task_to_inode(task, inode);
@@ -1815,8 +1816,8 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
 					inode->i_gid = cred->egid;
 					rcu_read_unlock();
 				} else {
-					inode->i_uid = 0;
-					inode->i_gid = 0;
+					inode->i_uid = GLOBAL_ROOT_UID;
+					inode->i_gid = GLOBAL_ROOT_GID;
 				}
 
 				i_mode = S_IFLNK;
@@ -2045,8 +2046,8 @@ static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd)
 			inode->i_gid = cred->egid;
 			rcu_read_unlock();
 		} else {
-			inode->i_uid = 0;
-			inode->i_gid = 0;
+			inode->i_uid = GLOBAL_ROOT_UID;
+			inode->i_gid = GLOBAL_ROOT_GID;
 		}
 		security_task_to_inode(task, inode);
 		status = 1;
@@ -2924,6 +2925,74 @@ static int proc_tgid_io_accounting(struct task_struct *task, char *buffer)
 }
 #endif /* CONFIG_TASK_IO_ACCOUNTING */
 
+#ifdef CONFIG_USER_NS
+static int proc_id_map_open(struct inode *inode, struct file *file,
+	struct seq_operations *seq_ops)
+{
+	struct user_namespace *ns = NULL;
+	struct task_struct *task;
+	struct seq_file *seq;
+	int ret = -EINVAL;
+
+	task = get_proc_task(inode);
+	if (task) {
+		rcu_read_lock();
+		ns = get_user_ns(task_cred_xxx(task, user_ns));
+		rcu_read_unlock();
+		put_task_struct(task);
+	}
+	if (!ns)
+		goto err;
+
+	ret = seq_open(file, seq_ops);
+	if (ret)
+		goto err_put_ns;
+
+	seq = file->private_data;
+	seq->private = ns;
+
+	return 0;
+err_put_ns:
+	put_user_ns(ns);
+err:
+	return ret;
+}
+
+static int proc_id_map_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	put_user_ns(ns);
+	return seq_release(inode, file);
+}
+
+static int proc_uid_map_open(struct inode *inode, struct file *file)
+{
+	return proc_id_map_open(inode, file, &proc_uid_seq_operations);
+}
+
+static int proc_gid_map_open(struct inode *inode, struct file *file)
+{
+	return proc_id_map_open(inode, file, &proc_gid_seq_operations);
+}
+
+static const struct file_operations proc_uid_map_operations = {
+	.open		= proc_uid_map_open,
+	.write		= proc_uid_map_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_id_map_release,
+};
+
+static const struct file_operations proc_gid_map_operations = {
+	.open		= proc_gid_map_open,
+	.write		= proc_gid_map_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_id_map_release,
+};
+#endif /* CONFIG_USER_NS */
+
 static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task)
 {
@@ -3026,6 +3095,10 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_HARDWALL
 	INF("hardwall",   S_IRUGO, proc_pid_hardwall),
 #endif
+#ifdef CONFIG_USER_NS
+	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
+	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
+#endif
 };
 
 static int proc_tgid_base_readdir(struct file * filp,
@@ -3381,6 +3454,10 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_HARDWALL
 	INF("hardwall",   S_IRUGO, proc_pid_hardwall),
 #endif
+#ifdef CONFIG_USER_NS
+	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
+	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
+#endif
 };
 
 static int proc_tid_base_readdir(struct file * filp,

fs/proc/inode.c

@@ -108,8 +108,8 @@ static int proc_show_options(struct seq_file *seq, struct dentry *root)
 	struct super_block *sb = root->d_sb;
 	struct pid_namespace *pid = sb->s_fs_info;
 
-	if (pid->pid_gid)
-		seq_printf(seq, ",gid=%lu", (unsigned long)pid->pid_gid);
+	if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID))
+		seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid));
 	if (pid->hide_pid != 0)
 		seq_printf(seq, ",hidepid=%u", pid->hide_pid);
 

fs/proc/proc_sysctl.c

@@ -371,9 +371,9 @@ void register_sysctl_root(struct ctl_table_root *root)
 
 static int test_perm(int mode, int op)
 {
-	if (!current_euid())
+	if (uid_eq(current_euid(), GLOBAL_ROOT_UID))
 		mode >>= 6;
-	else if (in_egroup_p(0))
+	else if (in_egroup_p(GLOBAL_ROOT_GID))
 		mode >>= 3;
 	if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
 		return 0;

fs/proc/root.c

@@ -67,7 +67,7 @@ static int proc_parse_options(char *options, struct pid_namespace *pid)
 		case Opt_gid:
 			if (match_int(&args[0], &option))
 				return 0;
-			pid->pid_gid = option;
+			pid->pid_gid = make_kgid(current_user_ns(), option);
 			break;
 		case Opt_hidepid:
 			if (match_int(&args[0], &option))

fs/stat.c

@@ -138,8 +138,8 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta
 	tmp.st_nlink = stat->nlink;
 	if (tmp.st_nlink != stat->nlink)
 		return -EOVERFLOW;
-	SET_UID(tmp.st_uid, stat->uid);
-	SET_GID(tmp.st_gid, stat->gid);
+	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
+	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
 	tmp.st_rdev = old_encode_dev(stat->rdev);
 #if BITS_PER_LONG == 32
 	if (stat->size > MAX_NON_LFS)
@@ -224,8 +224,8 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
 	tmp.st_nlink = stat->nlink;
 	if (tmp.st_nlink != stat->nlink)
 		return -EOVERFLOW;
-	SET_UID(tmp.st_uid, stat->uid);
-	SET_GID(tmp.st_gid, stat->gid);
+	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
+	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
 	tmp.st_rdev = encode_dev(stat->rdev);
 	tmp.st_size = stat->size;
 	tmp.st_atime = stat->atime.tv_sec;
@@ -355,8 +355,8 @@ static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf)
 #endif
 	tmp.st_mode = stat->mode;
 	tmp.st_nlink = stat->nlink;
-	tmp.st_uid = stat->uid;
-	tmp.st_gid = stat->gid;
+	tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid);
+	tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid);
 	tmp.st_atime = stat->atime.tv_sec;
 	tmp.st_atime_nsec = stat->atime.tv_nsec;
 	tmp.st_mtime = stat->mtime.tv_sec;

fs/sysfs/inode.c

@@ -62,8 +62,8 @@ static struct sysfs_inode_attrs *sysfs_init_inode_attrs(struct sysfs_dirent *sd)
 
 	/* assign default attributes */
 	iattrs->ia_mode = sd->s_mode;
-	iattrs->ia_uid = 0;
-	iattrs->ia_gid = 0;
+	iattrs->ia_uid = GLOBAL_ROOT_UID;
+	iattrs->ia_gid = GLOBAL_ROOT_GID;
 	iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME;
 
 	return attrs;

include/linux/capability.h

@@ -377,6 +377,7 @@ struct cpu_vfs_cap_data {
 
 #ifdef __KERNEL__
 
+struct inode;
 struct dentry;
 struct user_namespace;
 
@@ -551,6 +552,7 @@ extern bool has_ns_capability_noaudit(struct task_struct *t,
 extern bool capable(int cap);
 extern bool ns_capable(struct user_namespace *ns, int cap);
 extern bool nsown_capable(int cap);
+extern bool inode_capable(const struct inode *inode, int cap);
 
 /* audit system wants to get cap info from files as well */
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);

include/linux/cred.h

@@ -17,6 +17,7 @@
 #include <linux/key.h>
 #include <linux/selinux.h>
 #include <linux/atomic.h>
+#include <linux/uidgid.h>
 
 struct user_struct;
 struct cred;
@@ -26,14 +27,14 @@ struct inode;
  * COW Supplementary groups list
  */
 #define NGROUPS_SMALL		32
-#define NGROUPS_PER_BLOCK	((unsigned int)(PAGE_SIZE / sizeof(gid_t)))
+#define NGROUPS_PER_BLOCK	((unsigned int)(PAGE_SIZE / sizeof(kgid_t)))
 
 struct group_info {
 	atomic_t	usage;
 	int		ngroups;
 	int		nblocks;
-	gid_t		small_block[NGROUPS_SMALL];
-	gid_t		*blocks[0];
+	kgid_t		small_block[NGROUPS_SMALL];
+	kgid_t		*blocks[0];
 };
 
 /**
@@ -66,14 +67,14 @@ extern struct group_info init_groups;
 extern void groups_free(struct group_info *);
 extern int set_current_groups(struct group_info *);
 extern int set_groups(struct cred *, struct group_info *);
-extern int groups_search(const struct group_info *, gid_t);
+extern int groups_search(const struct group_info *, kgid_t);
 
 /* access the groups "array" with this macro */
 #define GROUP_AT(gi, i) \
 	((gi)->blocks[(i) / NGROUPS_PER_BLOCK][(i) % NGROUPS_PER_BLOCK])
 
-extern int in_group_p(gid_t);
-extern int in_egroup_p(gid_t);
+extern int in_group_p(kgid_t);
+extern int in_egroup_p(kgid_t);
 
 /*
  * The common credentials for a thread group
@@ -122,14 +123,14 @@ struct cred {
 #define CRED_MAGIC	0x43736564
 #define CRED_MAGIC_DEAD	0x44656144
 #endif
-	uid_t		uid;		/* real UID of the task */
-	gid_t		gid;		/* real GID of the task */
-	uid_t		suid;		/* saved UID of the task */
-	gid_t		sgid;		/* saved GID of the task */
-	uid_t		euid;		/* effective UID of the task */
-	gid_t		egid;		/* effective GID of the task */
-	uid_t		fsuid;		/* UID for VFS ops */
-	gid_t		fsgid;		/* GID for VFS ops */
+	kuid_t		uid;		/* real UID of the task */
+	kgid_t		gid;		/* real GID of the task */
+	kuid_t		suid;		/* saved UID of the task */
+	kgid_t		sgid;		/* saved GID of the task */
+	kuid_t		euid;		/* effective UID of the task */
+	kgid_t		egid;		/* effective GID of the task */
+	kuid_t		fsuid;		/* UID for VFS ops */
+	kgid_t		fsgid;		/* GID for VFS ops */
 	unsigned	securebits;	/* SUID-less security management */
 	kernel_cap_t	cap_inheritable; /* caps our children can inherit */
 	kernel_cap_t	cap_permitted;	/* caps we're permitted */
@@ -146,7 +147,7 @@ struct cred {
 	void		*security;	/* subjective LSM security */
 #endif
 	struct user_struct *user;	/* real user ID subscription */
-	struct user_namespace *user_ns; /* cached user->user_ns */
+	struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */
 	struct group_info *group_info;	/* supplementary groups for euid/fsgid */
 	struct rcu_head	rcu;		/* RCU deletion hook */
 };
@@ -357,11 +358,11 @@ static inline void put_cred(const struct cred *_cred)
 #define current_user()		(current_cred_xxx(user))
 #define current_security()	(current_cred_xxx(security))
 
+extern struct user_namespace init_user_ns;
 #ifdef CONFIG_USER_NS
 #define current_user_ns()	(current_cred_xxx(user_ns))
 #define task_user_ns(task)	(task_cred_xxx((task), user_ns))
 #else
-extern struct user_namespace init_user_ns;
 #define current_user_ns()	(&init_user_ns)
 #define task_user_ns(task)	(&init_user_ns)
 #endif

include/linux/fs.h

@@ -402,6 +402,7 @@ struct inodes_stat_t {
 #include <linux/atomic.h>
 #include <linux/shrinker.h>
 #include <linux/migrate_mode.h>
+#include <linux/uidgid.h>
 
 #include <asm/byteorder.h>
 
@@ -469,8 +470,8 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 struct iattr {
 	unsigned int	ia_valid;
 	umode_t		ia_mode;
-	uid_t		ia_uid;
-	gid_t		ia_gid;
+	kuid_t		ia_uid;
+	kgid_t		ia_gid;
 	loff_t		ia_size;
 	struct timespec	ia_atime;
 	struct timespec	ia_mtime;
@@ -761,8 +762,8 @@ struct posix_acl;
 struct inode {
 	umode_t			i_mode;
 	unsigned short		i_opflags;
-	uid_t			i_uid;
-	gid_t			i_gid;
+	kuid_t			i_uid;
+	kgid_t			i_gid;
 	unsigned int		i_flags;
 
 #ifdef CONFIG_FS_POSIX_ACL
@@ -927,6 +928,31 @@ static inline void i_size_write(struct inode *inode, loff_t i_size)
 #endif
 }
 
+/* Helper functions so that in most cases filesystems will
+ * not need to deal directly with kuid_t and kgid_t and can
+ * instead deal with the raw numeric values that are stored
+ * in the filesystem.
+ */
+static inline uid_t i_uid_read(const struct inode *inode)
+{
+	return from_kuid(&init_user_ns, inode->i_uid);
+}
+
+static inline gid_t i_gid_read(const struct inode *inode)
+{
+	return from_kgid(&init_user_ns, inode->i_gid);
+}
+
+static inline void i_uid_write(struct inode *inode, uid_t uid)
+{
+	inode->i_uid = make_kuid(&init_user_ns, uid);
+}
+
+static inline void i_gid_write(struct inode *inode, gid_t gid)
+{
+	inode->i_gid = make_kgid(&init_user_ns, gid);
+}
+
 static inline unsigned iminor(const struct inode *inode)
 {
 	return MINOR(inode->i_rdev);
@@ -943,7 +969,7 @@ struct fown_struct {
 	rwlock_t lock;          /* protects pid, uid, euid fields */
 	struct pid *pid;	/* pid or -pgrp where SIGIO should be sent */
 	enum pid_type pid_type;	/* Kind of process group SIGIO should be sent to */
-	uid_t uid, euid;	/* uid/euid of process setting the owner */
+	kuid_t uid, euid;	/* uid/euid of process setting the owner */
 	int signum;		/* posix.1b rt signal to be delivered on IO */
 };
 
@@ -1527,12 +1553,6 @@ enum {
 #define vfs_check_frozen(sb, level) \
 	wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))
 
-/*
- * until VFS tracks user namespaces for inodes, just make all files
- * belong to init_user_ns
- */
-extern struct user_namespace init_user_ns;
-#define inode_userns(inode) (&init_user_ns)
 extern bool inode_owner_or_capable(const struct inode *inode);
 
 /* not quite ready to be deprecated, but... */

include/linux/pid_namespace.h

@@ -31,7 +31,7 @@ struct pid_namespace {
 #ifdef CONFIG_BSD_PROCESS_ACCT
 	struct bsd_acct_struct *bacct;
 #endif
-	gid_t pid_gid;
+	kgid_t pid_gid;
 	int hide_pid;
 	int reboot;	/* group exit code if this pidns was rebooted */
 };

include/linux/proc_fs.h

@@ -52,8 +52,8 @@ struct proc_dir_entry {
 	unsigned int low_ino;
 	umode_t mode;
 	nlink_t nlink;
-	uid_t uid;
-	gid_t gid;
+	kuid_t uid;
+	kgid_t gid;
 	loff_t size;
 	const struct inode_operations *proc_iops;
 	/*

include/linux/quotaops.h

@@ -22,8 +22,8 @@ static inline struct quota_info *sb_dqopt(struct super_block *sb)
 static inline bool is_quota_modification(struct inode *inode, struct iattr *ia)
 {
 	return (ia->ia_valid & ATTR_SIZE && ia->ia_size != inode->i_size) ||
-		(ia->ia_valid & ATTR_UID && ia->ia_uid != inode->i_uid) ||
-		(ia->ia_valid & ATTR_GID && ia->ia_gid != inode->i_gid);
+		(ia->ia_valid & ATTR_UID && !uid_eq(ia->ia_uid, inode->i_uid)) ||
+		(ia->ia_valid & ATTR_GID && !gid_eq(ia->ia_gid, inode->i_gid));
 }
 
 #if defined(CONFIG_QUOTA)

include/linux/sched.h

@@ -90,6 +90,7 @@ struct sched_param {
 #include <linux/latencytop.h>
 #include <linux/cred.h>
 #include <linux/llist.h>
+#include <linux/uidgid.h>
 
 #include <asm/processor.h>
 
@@ -728,8 +729,7 @@ struct user_struct {
 
 	/* Hash table maintenance information */
 	struct hlist_node uidhash_node;
-	uid_t uid;
-	struct user_namespace *user_ns;
+	kuid_t uid;
 
 #ifdef CONFIG_PERF_EVENTS
 	atomic_long_t locked_vm;
@@ -738,7 +738,7 @@ struct user_struct {
 
 extern int uids_sysfs_init(void);
 
-extern struct user_struct *find_user(uid_t);
+extern struct user_struct *find_user(kuid_t);
 
 extern struct user_struct root_user;
 #define INIT_USER (&root_user)
@@ -2142,14 +2142,13 @@ extern struct task_struct *find_task_by_pid_ns(pid_t nr,
 extern void __set_special_pids(struct pid *pid);
 
 /* per-UID process charging. */
-extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
+extern struct user_struct * alloc_uid(kuid_t);
 static inline struct user_struct *get_uid(struct user_struct *u)
 {
 	atomic_inc(&u->__count);
 	return u;
 }
 extern void free_uid(struct user_struct *);
-extern void release_uids(struct user_namespace *ns);
 
 #include <asm/current.h>
 

include/linux/shmem_fs.h

@@ -28,8 +28,8 @@ struct shmem_sb_info {
 	unsigned long max_inodes;   /* How many inodes are allowed */
 	unsigned long free_inodes;  /* How many are left for allocation */
 	spinlock_t stat_lock;	    /* Serialize shmem_sb_info changes */
-	uid_t uid;		    /* Mount uid for root directory */
-	gid_t gid;		    /* Mount gid for root directory */
+	kuid_t uid;		    /* Mount uid for root directory */
+	kgid_t gid;		    /* Mount gid for root directory */
 	umode_t mode;		    /* Mount mode for root directory */
 	struct mempolicy *mpol;     /* default memory policy for mappings */
 };

include/linux/stat.h

@@ -58,14 +58,15 @@
 
 #include <linux/types.h>
 #include <linux/time.h>
+#include <linux/uidgid.h>
 
 struct kstat {
 	u64		ino;
 	dev_t		dev;
 	umode_t		mode;
 	unsigned int	nlink;
-	uid_t		uid;
-	gid_t		gid;
+	kuid_t		uid;
+	kgid_t		gid;
 	dev_t		rdev;
 	loff_t		size;
 	struct timespec  atime;

include/linux/uidgid.h

@@ -0,0 +1,200 @@
+#ifndef _LINUX_UIDGID_H
+#define _LINUX_UIDGID_H
+
+/*
+ * A set of types for the internal kernel types representing uids and gids.
+ *
+ * The types defined in this header allow distinguishing which uids and gids in
+ * the kernel are values used by userspace and which uid and gid values are
+ * the internal kernel values.  With the addition of user namespaces the values
+ * can be different.  Using the type system makes it possible for the compiler
+ * to detect when we overlook these differences.
+ *
+ */
+#include <linux/types.h>
+#include <linux/highuid.h>
+
+struct user_namespace;
+extern struct user_namespace init_user_ns;
+
+#ifdef CONFIG_UIDGID_STRICT_TYPE_CHECKS
+
+typedef struct {
+	uid_t val;
+} kuid_t;
+
+
+typedef struct {
+	gid_t val;
+} kgid_t;
+
+#define KUIDT_INIT(value) (kuid_t){ value }
+#define KGIDT_INIT(value) (kgid_t){ value }
+
+static inline uid_t __kuid_val(kuid_t uid)
+{
+	return uid.val;
+}
+
+static inline gid_t __kgid_val(kgid_t gid)
+{
+	return gid.val;
+}
+
+#else
+
+typedef uid_t kuid_t;
+typedef gid_t kgid_t;
+
+static inline uid_t __kuid_val(kuid_t uid)
+{
+	return uid;
+}
+
+static inline gid_t __kgid_val(kgid_t gid)
+{
+	return gid;
+}
+
+#define KUIDT_INIT(value) ((kuid_t) value )
+#define KGIDT_INIT(value) ((kgid_t) value )
+
+#endif
+
+#define GLOBAL_ROOT_UID KUIDT_INIT(0)
+#define GLOBAL_ROOT_GID KGIDT_INIT(0)
+
+#define INVALID_UID KUIDT_INIT(-1)
+#define INVALID_GID KGIDT_INIT(-1)
+
+static inline bool uid_eq(kuid_t left, kuid_t right)
+{
+	return __kuid_val(left) == __kuid_val(right);
+}
+
+static inline bool gid_eq(kgid_t left, kgid_t right)
+{
+	return __kgid_val(left) == __kgid_val(right);
+}
+
+static inline bool uid_gt(kuid_t left, kuid_t right)
+{
+	return __kuid_val(left) > __kuid_val(right);
+}
+
+static inline bool gid_gt(kgid_t left, kgid_t right)
+{
+	return __kgid_val(left) > __kgid_val(right);
+}
+
+static inline bool uid_gte(kuid_t left, kuid_t right)
+{
+	return __kuid_val(left) >= __kuid_val(right);
+}
+
+static inline bool gid_gte(kgid_t left, kgid_t right)
+{
+	return __kgid_val(left) >= __kgid_val(right);
+}
+
+static inline bool uid_lt(kuid_t left, kuid_t right)
+{
+	return __kuid_val(left) < __kuid_val(right);
+}
+
+static inline bool gid_lt(kgid_t left, kgid_t right)
+{
+	return __kgid_val(left) < __kgid_val(right);
+}
+
+static inline bool uid_lte(kuid_t left, kuid_t right)
+{
+	return __kuid_val(left) <= __kuid_val(right);
+}
+
+static inline bool gid_lte(kgid_t left, kgid_t right)
+{
+	return __kgid_val(left) <= __kgid_val(right);
+}
+
+static inline bool uid_valid(kuid_t uid)
+{
+	return !uid_eq(uid, INVALID_UID);
+}
+
+static inline bool gid_valid(kgid_t gid)
+{
+	return !gid_eq(gid, INVALID_GID);
+}
+
+#ifdef CONFIG_USER_NS
+
+extern kuid_t make_kuid(struct user_namespace *from, uid_t uid);
+extern kgid_t make_kgid(struct user_namespace *from, gid_t gid);
+
+extern uid_t from_kuid(struct user_namespace *to, kuid_t uid);
+extern gid_t from_kgid(struct user_namespace *to, kgid_t gid);
+extern uid_t from_kuid_munged(struct user_namespace *to, kuid_t uid);
+extern gid_t from_kgid_munged(struct user_namespace *to, kgid_t gid);
+
+static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid)
+{
+	return from_kuid(ns, uid) != (uid_t) -1;
+}
+
+static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid)
+{
+	return from_kgid(ns, gid) != (gid_t) -1;
+}
+
+#else
+
+static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid)
+{
+	return KUIDT_INIT(uid);
+}
+
+static inline kgid_t make_kgid(struct user_namespace *from, gid_t gid)
+{
+	return KGIDT_INIT(gid);
+}
+
+static inline uid_t from_kuid(struct user_namespace *to, kuid_t kuid)
+{
+	return __kuid_val(kuid);
+}
+
+static inline gid_t from_kgid(struct user_namespace *to, kgid_t kgid)
+{
+	return __kgid_val(kgid);
+}
+
+static inline uid_t from_kuid_munged(struct user_namespace *to, kuid_t kuid)
+{
+	uid_t uid = from_kuid(to, kuid);
+	if (uid == (uid_t)-1)
+		uid = overflowuid;
+	return uid;
+}
+
+static inline gid_t from_kgid_munged(struct user_namespace *to, kgid_t kgid)
+{
+	gid_t gid = from_kgid(to, kgid);
+	if (gid == (gid_t)-1)
+		gid = overflowgid;
+	return gid;
+}
+
+static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid)
+{
+	return true;
+}
+
+static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid)
+{
+	return true;
+}
+
+#endif /* CONFIG_USER_NS */
+
+#endif /* _LINUX_UIDGID_H */

include/linux/user_namespace.h

@@ -6,14 +6,24 @@
 #include <linux/sched.h>
 #include <linux/err.h>
 
-#define UIDHASH_BITS	(CONFIG_BASE_SMALL ? 3 : 7)
-#define UIDHASH_SZ	(1 << UIDHASH_BITS)
+#define UID_GID_MAP_MAX_EXTENTS 5
+
+struct uid_gid_map {	/* 64 bytes -- 1 cache line */
+	u32 nr_extents;
+	struct uid_gid_extent {
+		u32 first;
+		u32 lower_first;
+		u32 count;
+	} extent[UID_GID_MAP_MAX_EXTENTS];
+};
 
 struct user_namespace {
+	struct uid_gid_map	uid_map;
+	struct uid_gid_map	gid_map;
 	struct kref		kref;
-	struct hlist_head	uidhash_table[UIDHASH_SZ];
-	struct user_struct	*creator;
-	struct work_struct	destroyer;
+	struct user_namespace	*parent;
+	kuid_t			owner;
+	kgid_t			group;
 };
 
 extern struct user_namespace init_user_ns;
@@ -36,9 +46,11 @@ static inline void put_user_ns(struct user_namespace *ns)
 		kref_put(&ns->kref, free_user_ns);
 }
 
-uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t uid);
-gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t gid);
-
+struct seq_operations;
+extern struct seq_operations proc_uid_seq_operations;
+extern struct seq_operations proc_gid_seq_operations;
+extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *);
+extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *);
 #else
 
 static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
@@ -55,17 +67,6 @@ static inline void put_user_ns(struct user_namespace *ns)
 {
 }
 
-static inline uid_t user_ns_map_uid(struct user_namespace *to,
-	const struct cred *cred, uid_t uid)
-{
-	return uid;
-}
-static inline gid_t user_ns_map_gid(struct user_namespace *to,
-	const struct cred *cred, gid_t gid)
-{
-	return gid;
-}
-
 #endif
 
 #endif /* _LINUX_USER_H */

include/trace/events/ext3.h

@@ -24,8 +24,8 @@ TRACE_EVENT(ext3_free_inode,
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
 		__entry->mode	= inode->i_mode;
-		__entry->uid	= inode->i_uid;
-		__entry->gid	= inode->i_gid;
+		__entry->uid	= i_uid_read(inode);
+		__entry->gid	= i_gid_read(inode);
 		__entry->blocks	= inode->i_blocks;
 	),
 

include/trace/events/ext4.h

@@ -36,8 +36,8 @@ TRACE_EVENT(ext4_free_inode,
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
 		__entry->mode	= inode->i_mode;
-		__entry->uid	= inode->i_uid;
-		__entry->gid	= inode->i_gid;
+		__entry->uid	= i_uid_read(inode);
+		__entry->gid	= i_gid_read(inode);
 		__entry->blocks	= inode->i_blocks;
 	),
 

init/Kconfig

@@ -873,7 +873,10 @@ config IPC_NS
 config USER_NS
 	bool "User namespace (EXPERIMENTAL)"
 	depends on EXPERIMENTAL
-	default y
+	depends on UIDGID_CONVERTED
+	select UIDGID_STRICT_TYPE_CHECKS
+
+	default n
 	help
 	  This allows containers, i.e. vservers, to use user namespaces
 	  to provide different user info for different servers.
@@ -897,6 +900,131 @@ config NET_NS
 
 endif # NAMESPACES
 
+config UIDGID_CONVERTED
+	# True if all of the selected software conmponents are known
+	# to have uid_t and gid_t converted to kuid_t and kgid_t
+	# where appropriate and are otherwise safe to use with
+	# the user namespace.
+	bool
+	default y
+
+	# List of kernel pieces that need user namespace work
+	# Features
+	depends on SYSVIPC = n
+	depends on IMA = n
+	depends on EVM = n
+	depends on KEYS = n
+	depends on AUDIT = n
+	depends on AUDITSYSCALL = n
+	depends on TASKSTATS = n
+	depends on TRACING = n
+	depends on FS_POSIX_ACL = n
+	depends on QUOTA = n
+	depends on QUOTACTL = n
+	depends on DEBUG_CREDENTIALS = n
+	depends on BSD_PROCESS_ACCT = n
+	depends on DRM = n
+	depends on PROC_EVENTS = n
+
+	# Networking
+	depends on NET = n
+	depends on NET_9P = n
+	depends on IPX = n
+	depends on PHONET = n
+	depends on NET_CLS_FLOW = n
+	depends on NETFILTER_XT_MATCH_OWNER = n
+	depends on NETFILTER_XT_MATCH_RECENT = n
+	depends on NETFILTER_XT_TARGET_LOG = n
+	depends on NETFILTER_NETLINK_LOG = n
+	depends on INET = n
+	depends on IPV6 = n
+	depends on IP_SCTP = n
+	depends on AF_RXRPC = n
+	depends on LLC2 = n
+	depends on NET_KEY = n
+	depends on INET_DIAG = n
+	depends on DNS_RESOLVER = n
+	depends on AX25 = n
+	depends on ATALK = n
+
+	# Filesystems
+	depends on USB_DEVICEFS = n
+	depends on USB_GADGETFS = n
+	depends on USB_FUNCTIONFS = n
+	depends on DEVTMPFS = n
+	depends on XENFS = n
+
+	depends on 9P_FS = n
+	depends on ADFS_FS = n
+	depends on AFFS_FS = n
+	depends on AFS_FS = n
+	depends on AUTOFS4_FS = n
+	depends on BEFS_FS = n
+	depends on BFS_FS = n
+	depends on BTRFS_FS = n
+	depends on CEPH_FS = n
+	depends on CIFS = n
+	depends on CODA_FS = n
+	depends on CONFIGFS_FS = n
+	depends on CRAMFS = n
+	depends on DEBUG_FS = n
+	depends on ECRYPT_FS = n
+	depends on EFS_FS = n
+	depends on EXOFS_FS = n
+	depends on FAT_FS = n
+	depends on FUSE_FS = n
+	depends on GFS2_FS = n
+	depends on HFS_FS = n
+	depends on HFSPLUS_FS = n
+	depends on HPFS_FS = n
+	depends on HUGETLBFS = n
+	depends on ISO9660_FS = n
+	depends on JFFS2_FS = n
+	depends on JFS_FS = n
+	depends on LOGFS = n
+	depends on MINIX_FS = n
+	depends on NCP_FS = n
+	depends on NFSD = n
+	depends on NFS_FS = n
+	depends on NILFS2_FS = n
+	depends on NTFS_FS = n
+	depends on OCFS2_FS = n
+	depends on OMFS_FS = n
+	depends on QNX4FS_FS = n
+	depends on QNX6FS_FS = n
+	depends on REISERFS_FS = n
+	depends on SQUASHFS = n
+	depends on SYSV_FS = n
+	depends on UBIFS_FS = n
+	depends on UDF_FS = n
+	depends on UFS_FS = n
+	depends on VXFS_FS = n
+	depends on XFS_FS = n
+
+	depends on !UML || HOSTFS = n
+
+	# The rare drivers that won't build
+	depends on AIRO = n
+	depends on AIRO_CS = n
+	depends on TUN = n
+	depends on INFINIBAND_QIB = n
+	depends on BLK_DEV_LOOP = n
+	depends on ANDROID_BINDER_IPC = n
+
+	# Security modules
+	depends on SECURITY_TOMOYO = n
+	depends on SECURITY_APPARMOR = n
+
+config UIDGID_STRICT_TYPE_CHECKS
+	bool "Require conversions between uid/gids and their internal representation"
+	depends on UIDGID_CONVERTED
+	default n
+	help
+	 While the nececessary conversions are being added to all subsystems this option allows
+	 the code to continue to build for unconverted subsystems.
+
+	 Say Y here if you want the strict type checking enabled
+
 config SCHED_AUTOGROUP
 	bool "Automatic process group scheduling"
 	select EVENTFD

ipc/mqueue.c

@@ -66,6 +66,7 @@ struct mqueue_inode_info {
 
 	struct sigevent notify;
 	struct pid* notify_owner;
+	struct user_namespace *notify_user_ns;
 	struct user_struct *user;	/* user who created, for accounting */
 	struct sock *notify_sock;
 	struct sk_buff *notify_cookie;
@@ -139,6 +140,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
 		INIT_LIST_HEAD(&info->e_wait_q[0].list);
 		INIT_LIST_HEAD(&info->e_wait_q[1].list);
 		info->notify_owner = NULL;
+		info->notify_user_ns = NULL;
 		info->qsize = 0;
 		info->user = NULL;	/* set when all is ok */
 		memset(&info->attr, 0, sizeof(info->attr));
@@ -536,8 +538,7 @@ static void __do_notify(struct mqueue_inode_info *info)
 			rcu_read_lock();
 			sig_i.si_pid = task_tgid_nr_ns(current,
 						ns_of_pid(info->notify_owner));
-			sig_i.si_uid = user_ns_map_uid(info->user->user_ns,
-						current_cred(), current_uid());
+			sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid());
 			rcu_read_unlock();
 
 			kill_pid_info(info->notify.sigev_signo,
@@ -550,7 +551,9 @@ static void __do_notify(struct mqueue_inode_info *info)
 		}
 		/* after notification unregisters process */
 		put_pid(info->notify_owner);
+		put_user_ns(info->notify_user_ns);
 		info->notify_owner = NULL;
+		info->notify_user_ns = NULL;
 	}
 	wake_up(&info->wait_q);
 }
@@ -575,7 +578,9 @@ static void remove_notification(struct mqueue_inode_info *info)
 		netlink_sendskb(info->notify_sock, info->notify_cookie);
 	}
 	put_pid(info->notify_owner);
+	put_user_ns(info->notify_user_ns);
 	info->notify_owner = NULL;
+	info->notify_user_ns = NULL;
 }
 
 static int mq_attr_ok(struct ipc_namespace *ipc_ns, struct mq_attr *attr)
@@ -1140,6 +1145,7 @@ retry:
 		}
 
 		info->notify_owner = get_pid(task_tgid(current));
+		info->notify_user_ns = get_user_ns(current_user_ns());
 		inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	}
 	spin_unlock(&info->lock);

ipc/namespace.c

@@ -46,7 +46,7 @@ static struct ipc_namespace *create_ipc_ns(struct task_struct *tsk,
 	ipcns_notify(IPCNS_CREATED);
 	register_ipcns_notifier(ns);
 
-	ns->user_ns = get_user_ns(task_cred_xxx(tsk, user)->user_ns);
+	ns->user_ns = get_user_ns(task_cred_xxx(tsk, user_ns));
 
 	return ns;
 }

kernel/capability.c

@@ -419,3 +419,24 @@ bool nsown_capable(int cap)
 {
 	return ns_capable(current_user_ns(), cap);
 }
+
+/**
+ * inode_capable - Check superior capability over inode
+ * @inode: The inode in question
+ * @cap: The capability in question
+ *
+ * Return true if the current task has the given superior capability
+ * targeted at it's own user namespace and that the given inode is owned
+ * by the current user namespace or a child namespace.
+ *
+ * Currently we check to see if an inode is owned by the current
+ * user namespace by seeing if the inode's owner maps into the
+ * current user namespace.
+ *
+ */
+bool inode_capable(const struct inode *inode, int cap)
+{
+	struct user_namespace *ns = current_user_ns();
+
+	return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid);
+}

kernel/cgroup.c

@@ -2214,9 +2214,9 @@ retry_find_task:
 		 * only need to check permissions on one of them.
 		 */
 		tcred = __task_cred(tsk);
-		if (cred->euid &&
-		    cred->euid != tcred->uid &&
-		    cred->euid != tcred->suid) {
+		if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
+		    !uid_eq(cred->euid, tcred->uid) &&
+		    !uid_eq(cred->euid, tcred->suid)) {
 			rcu_read_unlock();
 			ret = -EACCES;
 			goto out_unlock_cgroup;

kernel/cred.c

@@ -49,6 +49,14 @@ struct cred init_cred = {
 	.subscribers		= ATOMIC_INIT(2),
 	.magic			= CRED_MAGIC,
 #endif
+	.uid			= GLOBAL_ROOT_UID,
+	.gid			= GLOBAL_ROOT_GID,
+	.suid			= GLOBAL_ROOT_UID,
+	.sgid			= GLOBAL_ROOT_GID,
+	.euid			= GLOBAL_ROOT_UID,
+	.egid			= GLOBAL_ROOT_GID,
+	.fsuid			= GLOBAL_ROOT_UID,
+	.fsgid			= GLOBAL_ROOT_GID,
 	.securebits		= SECUREBITS_DEFAULT,
 	.cap_inheritable	= CAP_EMPTY_SET,
 	.cap_permitted		= CAP_FULL_SET,
@@ -148,6 +156,7 @@ static void put_cred_rcu(struct rcu_head *rcu)
 	if (cred->group_info)
 		put_group_info(cred->group_info);
 	free_uid(cred->user);
+	put_user_ns(cred->user_ns);
 	kmem_cache_free(cred_jar, cred);
 }
 
@@ -303,6 +312,7 @@ struct cred *prepare_creds(void)
 	set_cred_subscribers(new, 0);
 	get_group_info(new->group_info);
 	get_uid(new->user);
+	get_user_ns(new->user_ns);
 
 #ifdef CONFIG_KEYS
 	key_get(new->thread_keyring);
@@ -414,11 +424,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 			goto error_put;
 	}
 
-	/* cache user_ns in cred.  Doesn't need a refcount because it will
-	 * stay pinned by cred->user
-	 */
-	new->user_ns = new->user->user_ns;
-
 #ifdef CONFIG_KEYS
 	/* new threads get their own thread keyrings if their parent already
 	 * had one */
@@ -493,10 +498,10 @@ int commit_creds(struct cred *new)
 	get_cred(new); /* we will require a ref for the subj creds too */
 
 	/* dumpability changes */
-	if (old->euid != new->euid ||
-	    old->egid != new->egid ||
-	    old->fsuid != new->fsuid ||
-	    old->fsgid != new->fsgid ||
+	if (!uid_eq(old->euid, new->euid) ||
+	    !gid_eq(old->egid, new->egid) ||
+	    !uid_eq(old->fsuid, new->fsuid) ||
+	    !gid_eq(old->fsgid, new->fsgid) ||
 	    !cap_issubset(new->cap_permitted, old->cap_permitted)) {
 		if (task->mm)
 			set_dumpable(task->mm, suid_dumpable);
@@ -505,9 +510,9 @@ int commit_creds(struct cred *new)
 	}
 
 	/* alter the thread keyring */
-	if (new->fsuid != old->fsuid)
+	if (!uid_eq(new->fsuid, old->fsuid))
 		key_fsuid_changed(task);
-	if (new->fsgid != old->fsgid)
+	if (!gid_eq(new->fsgid, old->fsgid))
 		key_fsgid_changed(task);
 
 	/* do it
@@ -524,16 +529,16 @@ int commit_creds(struct cred *new)
 	alter_cred_subscribers(old, -2);
 
 	/* send notifications */
-	if (new->uid   != old->uid  ||
-	    new->euid  != old->euid ||
-	    new->suid  != old->suid ||
-	    new->fsuid != old->fsuid)
+	if (!uid_eq(new->uid,   old->uid)  ||
+	    !uid_eq(new->euid,  old->euid) ||
+	    !uid_eq(new->suid,  old->suid) ||
+	    !uid_eq(new->fsuid, old->fsuid))
 		proc_id_connector(task, PROC_EVENT_UID);
 
-	if (new->gid   != old->gid  ||
-	    new->egid  != old->egid ||
-	    new->sgid  != old->sgid ||
-	    new->fsgid != old->fsgid)
+	if (!gid_eq(new->gid,   old->gid)  ||
+	    !gid_eq(new->egid,  old->egid) ||
+	    !gid_eq(new->sgid,  old->sgid) ||
+	    !gid_eq(new->fsgid, old->fsgid))
 		proc_id_connector(task, PROC_EVENT_GID);
 
 	/* release the old obj and subj refs both */
@@ -678,6 +683,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	atomic_set(&new->usage, 1);
 	set_cred_subscribers(new, 0);
 	get_uid(new->user);
+	get_user_ns(new->user_ns);
 	get_group_info(new->group_info);
 
 #ifdef CONFIG_KEYS

kernel/exit.c

@@ -1214,7 +1214,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 	unsigned long state;
 	int retval, status, traced;
 	pid_t pid = task_pid_vnr(p);
-	uid_t uid = __task_cred(p)->uid;
+	uid_t uid = from_kuid_munged(current_user_ns(), __task_cred(p)->uid);
 	struct siginfo __user *infop;
 
 	if (!likely(wo->wo_flags & WEXITED))
@@ -1427,7 +1427,7 @@ static int wait_task_stopped(struct wait_opts *wo,
 	if (!unlikely(wo->wo_flags & WNOWAIT))
 		*p_code = 0;
 
-	uid = task_uid(p);
+	uid = from_kuid_munged(current_user_ns(), task_uid(p));
 unlock_sig:
 	spin_unlock_irq(&p->sighand->siglock);
 	if (!exit_code)
@@ -1500,7 +1500,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 	}
 	if (!unlikely(wo->wo_flags & WNOWAIT))
 		p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
-	uid = task_uid(p);
+	uid = from_kuid_munged(current_user_ns(), task_uid(p));
 	spin_unlock_irq(&p->sighand->siglock);
 
 	pid = task_pid_vnr(p);

kernel/groups.c

@@ -31,7 +31,7 @@ struct group_info *groups_alloc(int gidsetsize)
 		group_info->blocks[0] = group_info->small_block;
 	else {
 		for (i = 0; i < nblocks; i++) {
-			gid_t *b;
+			kgid_t *b;
 			b = (void *)__get_free_page(GFP_USER);
 			if (!b)
 				goto out_undo_partial_alloc;
@@ -66,18 +66,15 @@ EXPORT_SYMBOL(groups_free);
 static int groups_to_user(gid_t __user *grouplist,
 			  const struct group_info *group_info)
 {
+	struct user_namespace *user_ns = current_user_ns();
 	int i;
 	unsigned int count = group_info->ngroups;
 
-	for (i = 0; i < group_info->nblocks; i++) {
-		unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
-		unsigned int len = cp_count * sizeof(*grouplist);
-
-		if (copy_to_user(grouplist, group_info->blocks[i], len))
+	for (i = 0; i < count; i++) {
+		gid_t gid;
+		gid = from_kgid_munged(user_ns, GROUP_AT(group_info, i));
+		if (put_user(gid, grouplist+i))
 			return -EFAULT;
-
-		grouplist += NGROUPS_PER_BLOCK;
-		count -= cp_count;
 	}
 	return 0;
 }
@@ -86,18 +83,21 @@ static int groups_to_user(gid_t __user *grouplist,
 static int groups_from_user(struct group_info *group_info,
     gid_t __user *grouplist)
 {
+	struct user_namespace *user_ns = current_user_ns();
 	int i;
 	unsigned int count = group_info->ngroups;
 
-	for (i = 0; i < group_info->nblocks; i++) {
-		unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
-		unsigned int len = cp_count * sizeof(*grouplist);
-
-		if (copy_from_user(group_info->blocks[i], grouplist, len))
+	for (i = 0; i < count; i++) {
+		gid_t gid;
+		kgid_t kgid;
+		if (get_user(gid, grouplist+i))
 			return -EFAULT;
 
-		grouplist += NGROUPS_PER_BLOCK;
-		count -= cp_count;
+		kgid = make_kgid(user_ns, gid);
+		if (!gid_valid(kgid))
+			return -EINVAL;
+
+		GROUP_AT(group_info, i) = kgid;
 	}
 	return 0;
 }
@@ -117,9 +117,9 @@ static void groups_sort(struct group_info *group_info)
 		for (base = 0; base < max; base++) {
 			int left = base;
 			int right = left + stride;
-			gid_t tmp = GROUP_AT(group_info, right);
+			kgid_t tmp = GROUP_AT(group_info, right);
 
-			while (left >= 0 && GROUP_AT(group_info, left) > tmp) {
+			while (left >= 0 && gid_gt(GROUP_AT(group_info, left), tmp)) {
 				GROUP_AT(group_info, right) =
 				    GROUP_AT(group_info, left);
 				right = left;
@@ -132,7 +132,7 @@ static void groups_sort(struct group_info *group_info)
 }
 
 /* a simple bsearch */
-int groups_search(const struct group_info *group_info, gid_t grp)
+int groups_search(const struct group_info *group_info, kgid_t grp)
 {
 	unsigned int left, right;
 
@@ -143,9 +143,9 @@ int groups_search(const struct group_info *group_info, gid_t grp)
 	right = group_info->ngroups;
 	while (left < right) {
 		unsigned int mid = (left+right)/2;
-		if (grp > GROUP_AT(group_info, mid))
+		if (gid_gt(grp, GROUP_AT(group_info, mid)))
 			left = mid + 1;
-		else if (grp < GROUP_AT(group_info, mid))
+		else if (gid_lt(grp, GROUP_AT(group_info, mid)))
 			right = mid;
 		else
 			return 1;
@@ -256,24 +256,24 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
 /*
  * Check whether we're fsgid/egid or in the supplemental group..
  */
-int in_group_p(gid_t grp)
+int in_group_p(kgid_t grp)
 {
 	const struct cred *cred = current_cred();
 	int retval = 1;
 
-	if (grp != cred->fsgid)
+	if (!gid_eq(grp, cred->fsgid))
 		retval = groups_search(cred->group_info, grp);
 	return retval;
 }
 
 EXPORT_SYMBOL(in_group_p);
 
-int in_egroup_p(gid_t grp)
+int in_egroup_p(kgid_t grp)
 {
 	const struct cred *cred = current_cred();
 	int retval = 1;
 
-	if (grp != cred->egid)
+	if (!gid_eq(grp, cred->egid))
 		retval = groups_search(cred->group_info, grp);
 	return retval;
 }

kernel/ptrace.c

@@ -198,15 +198,14 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 		return 0;
 	rcu_read_lock();
 	tcred = __task_cred(task);
-	if (cred->user->user_ns == tcred->user->user_ns &&
-	    (cred->uid == tcred->euid &&
-	     cred->uid == tcred->suid &&
-	     cred->uid == tcred->uid  &&
-	     cred->gid == tcred->egid &&
-	     cred->gid == tcred->sgid &&
-	     cred->gid == tcred->gid))
+	if (uid_eq(cred->uid, tcred->euid) &&
+	    uid_eq(cred->uid, tcred->suid) &&
+	    uid_eq(cred->uid, tcred->uid)  &&
+	    gid_eq(cred->gid, tcred->egid) &&
+	    gid_eq(cred->gid, tcred->sgid) &&
+	    gid_eq(cred->gid, tcred->gid))
 		goto ok;
-	if (ptrace_has_cap(tcred->user->user_ns, mode))
+	if (ptrace_has_cap(tcred->user_ns, mode))
 		goto ok;
 	rcu_read_unlock();
 	return -EPERM;

kernel/sched/core.c

@@ -4070,11 +4070,8 @@ static bool check_same_owner(struct task_struct *p)
 
 	rcu_read_lock();
 	pcred = __task_cred(p);
-	if (cred->user->user_ns == pcred->user->user_ns)
-		match = (cred->euid == pcred->euid ||
-			 cred->euid == pcred->uid);
-	else
-		match = false;
+	match = (uid_eq(cred->euid, pcred->euid) ||
+		 uid_eq(cred->euid, pcred->uid));
 	rcu_read_unlock();
 	return match;
 }

kernel/signal.c

@@ -767,14 +767,13 @@ static int kill_ok_by_cred(struct task_struct *t)
 	const struct cred *cred = current_cred();
 	const struct cred *tcred = __task_cred(t);
 
-	if (cred->user->user_ns == tcred->user->user_ns &&
-	    (cred->euid == tcred->suid ||
-	     cred->euid == tcred->uid ||
-	     cred->uid  == tcred->suid ||
-	     cred->uid  == tcred->uid))
+	if (uid_eq(cred->euid, tcred->suid) ||
+	    uid_eq(cred->euid, tcred->uid)  ||
+	    uid_eq(cred->uid,  tcred->suid) ||
+	    uid_eq(cred->uid,  tcred->uid))
 		return 1;
 
-	if (ns_capable(tcred->user->user_ns, CAP_KILL))
+	if (ns_capable(tcred->user_ns, CAP_KILL))
 		return 1;
 
 	return 0;
@@ -1020,15 +1019,6 @@ static inline int legacy_queue(struct sigpending *signals, int sig)
 	return (sig < SIGRTMIN) && sigismember(&signals->signal, sig);
 }
 
-/*
- * map the uid in struct cred into user namespace *ns
- */
-static inline uid_t map_cred_ns(const struct cred *cred,
-				struct user_namespace *ns)
-{
-	return user_ns_map_uid(ns, cred, cred->uid);
-}
-
 #ifdef CONFIG_USER_NS
 static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t)
 {
@@ -1038,8 +1028,10 @@ static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_str
 	if (SI_FROMKERNEL(info))
 		return;
 
-	info->si_uid = user_ns_map_uid(task_cred_xxx(t, user_ns),
-					current_cred(), info->si_uid);
+	rcu_read_lock();
+	info->si_uid = from_kuid_munged(task_cred_xxx(t, user_ns),
+					make_kuid(current_user_ns(), info->si_uid));
+	rcu_read_unlock();
 }
 #else
 static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t)
@@ -1106,7 +1098,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
 			q->info.si_code = SI_USER;
 			q->info.si_pid = task_tgid_nr_ns(current,
 							task_active_pid_ns(t));
-			q->info.si_uid = current_uid();
+			q->info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
 			break;
 		case (unsigned long) SEND_SIG_PRIV:
 			q->info.si_signo = sig;
@@ -1387,10 +1379,8 @@ static int kill_as_cred_perm(const struct cred *cred,
 			     struct task_struct *target)
 {
 	const struct cred *pcred = __task_cred(target);
-	if (cred->user_ns != pcred->user_ns)
-		return 0;
-	if (cred->euid != pcred->suid && cred->euid != pcred->uid &&
-	    cred->uid  != pcred->suid && cred->uid  != pcred->uid)
+	if (!uid_eq(cred->euid, pcred->suid) && !uid_eq(cred->euid, pcred->uid) &&
+	    !uid_eq(cred->uid,  pcred->suid) && !uid_eq(cred->uid,  pcred->uid))
 		return 0;
 	return 1;
 }
@@ -1678,8 +1668,8 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 	 */
 	rcu_read_lock();
 	info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
-	info.si_uid = map_cred_ns(__task_cred(tsk),
-			task_cred_xxx(tsk->parent, user_ns));
+	info.si_uid = from_kuid_munged(task_cred_xxx(tsk->parent, user_ns),
+				       task_uid(tsk));
 	rcu_read_unlock();
 
 	info.si_utime = cputime_to_clock_t(tsk->utime + tsk->signal->utime);
@@ -1762,8 +1752,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
 	 */
 	rcu_read_lock();
 	info.si_pid = task_pid_nr_ns(tsk, parent->nsproxy->pid_ns);
-	info.si_uid = map_cred_ns(__task_cred(tsk),
-			task_cred_xxx(parent, user_ns));
+	info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk));
 	rcu_read_unlock();
 
 	info.si_utime = cputime_to_clock_t(tsk->utime);
@@ -1973,7 +1962,7 @@ static void ptrace_do_notify(int signr, int exit_code, int why)
 	info.si_signo = signr;
 	info.si_code = exit_code;
 	info.si_pid = task_pid_vnr(current);
-	info.si_uid = current_uid();
+	info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
 
 	/* Let the debugger run.  */
 	ptrace_stop(exit_code, why, 1, &info);
@@ -2181,8 +2170,8 @@ static int ptrace_signal(int signr, siginfo_t *info,
 		info->si_code = SI_USER;
 		rcu_read_lock();
 		info->si_pid = task_pid_vnr(current->parent);
-		info->si_uid = map_cred_ns(__task_cred(current->parent),
-				current_user_ns());
+		info->si_uid = from_kuid_munged(current_user_ns(),
+						task_uid(current->parent));
 		rcu_read_unlock();
 	}
 
@@ -2835,7 +2824,7 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
 	info.si_errno = 0;
 	info.si_code = SI_USER;
 	info.si_pid = task_tgid_vnr(current);
-	info.si_uid = current_uid();
+	info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
 
 	return kill_something_info(sig, &info, pid);
 }
@@ -2878,7 +2867,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig)
 	info.si_errno = 0;
 	info.si_code = SI_TKILL;
 	info.si_pid = task_tgid_vnr(current);
-	info.si_uid = current_uid();
+	info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
 
 	return do_send_specific(tgid, pid, sig, &info);
 }

kernel/sys.c

@@ -93,10 +93,8 @@
 int overflowuid = DEFAULT_OVERFLOWUID;
 int overflowgid = DEFAULT_OVERFLOWGID;
 
-#ifdef CONFIG_UID16
 EXPORT_SYMBOL(overflowuid);
 EXPORT_SYMBOL(overflowgid);
-#endif
 
 /*
  * the same as above, but for filesystems which can only store a 16-bit
@@ -133,11 +131,10 @@ static bool set_one_prio_perm(struct task_struct *p)
 {
 	const struct cred *cred = current_cred(), *pcred = __task_cred(p);
 
-	if (pcred->user->user_ns == cred->user->user_ns &&
-	    (pcred->uid  == cred->euid ||
-	     pcred->euid == cred->euid))
+	if (uid_eq(pcred->uid,  cred->euid) ||
+	    uid_eq(pcred->euid, cred->euid))
 		return true;
-	if (ns_capable(pcred->user->user_ns, CAP_SYS_NICE))
+	if (ns_capable(pcred->user_ns, CAP_SYS_NICE))
 		return true;
 	return false;
 }
@@ -177,6 +174,7 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
 	const struct cred *cred = current_cred();
 	int error = -EINVAL;
 	struct pid *pgrp;
+	kuid_t uid;
 
 	if (which > PRIO_USER || which < PRIO_PROCESS)
 		goto out;
@@ -209,18 +207,19 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
 			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
 			break;
 		case PRIO_USER:
-			user = (struct user_struct *) cred->user;
+			uid = make_kuid(cred->user_ns, who);
+			user = cred->user;
 			if (!who)
-				who = cred->uid;
-			else if ((who != cred->uid) &&
-				 !(user = find_user(who)))
+				uid = cred->uid;
+			else if (!uid_eq(uid, cred->uid) &&
+				 !(user = find_user(uid)))
 				goto out_unlock;	/* No processes for this user */
 
 			do_each_thread(g, p) {
-				if (__task_cred(p)->uid == who)
+				if (uid_eq(task_uid(p), uid))
 					error = set_one_prio(p, niceval, error);
 			} while_each_thread(g, p);
-			if (who != cred->uid)
+			if (!uid_eq(uid, cred->uid))
 				free_uid(user);		/* For find_user() */
 			break;
 	}
@@ -244,6 +243,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
 	const struct cred *cred = current_cred();
 	long niceval, retval = -ESRCH;
 	struct pid *pgrp;
+	kuid_t uid;
 
 	if (which > PRIO_USER || which < PRIO_PROCESS)
 		return -EINVAL;
@@ -274,21 +274,22 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
 			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
 			break;
 		case PRIO_USER:
-			user = (struct user_struct *) cred->user;
+			uid = make_kuid(cred->user_ns, who);
+			user = cred->user;
 			if (!who)
-				who = cred->uid;
-			else if ((who != cred->uid) &&
-				 !(user = find_user(who)))
+				uid = cred->uid;
+			else if (!uid_eq(uid, cred->uid) &&
+				 !(user = find_user(uid)))
 				goto out_unlock;	/* No processes for this user */
 
 			do_each_thread(g, p) {
-				if (__task_cred(p)->uid == who) {
+				if (uid_eq(task_uid(p), uid)) {
 					niceval = 20 - task_nice(p);
 					if (niceval > retval)
 						retval = niceval;
 				}
 			} while_each_thread(g, p);
-			if (who != cred->uid)
+			if (!uid_eq(uid, cred->uid))
 				free_uid(user);		/* for find_user() */
 			break;
 	}
@@ -553,9 +554,19 @@ void ctrl_alt_del(void)
  */
 SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
 {
+	struct user_namespace *ns = current_user_ns();
 	const struct cred *old;
 	struct cred *new;
 	int retval;
+	kgid_t krgid, kegid;
+
+	krgid = make_kgid(ns, rgid);
+	kegid = make_kgid(ns, egid);
+
+	if ((rgid != (gid_t) -1) && !gid_valid(krgid))
+		return -EINVAL;
+	if ((egid != (gid_t) -1) && !gid_valid(kegid))
+		return -EINVAL;
 
 	new = prepare_creds();
 	if (!new)
@@ -564,25 +575,25 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
 
 	retval = -EPERM;
 	if (rgid != (gid_t) -1) {
-		if (old->gid == rgid ||
-		    old->egid == rgid ||
+		if (gid_eq(old->gid, krgid) ||
+		    gid_eq(old->egid, krgid) ||
 		    nsown_capable(CAP_SETGID))
-			new->gid = rgid;
+			new->gid = krgid;
 		else
 			goto error;
 	}
 	if (egid != (gid_t) -1) {
-		if (old->gid == egid ||
-		    old->egid == egid ||
-		    old->sgid == egid ||
+		if (gid_eq(old->gid, kegid) ||
+		    gid_eq(old->egid, kegid) ||
+		    gid_eq(old->sgid, kegid) ||
 		    nsown_capable(CAP_SETGID))
-			new->egid = egid;
+			new->egid = kegid;
 		else
 			goto error;
 	}
 
 	if (rgid != (gid_t) -1 ||
-	    (egid != (gid_t) -1 && egid != old->gid))
+	    (egid != (gid_t) -1 && !gid_eq(kegid, old->gid)))
 		new->sgid = new->egid;
 	new->fsgid = new->egid;
 
@@ -600,9 +611,15 @@ error:
  */
 SYSCALL_DEFINE1(setgid, gid_t, gid)
 {
+	struct user_namespace *ns = current_user_ns();
 	const struct cred *old;
 	struct cred *new;
 	int retval;
+	kgid_t kgid;
+
+	kgid = make_kgid(ns, gid);
+	if (!gid_valid(kgid))
+		return -EINVAL;
 
 	new = prepare_creds();
 	if (!new)
@@ -611,9 +628,9 @@ SYSCALL_DEFINE1(setgid, gid_t, gid)
 
 	retval = -EPERM;
 	if (nsown_capable(CAP_SETGID))
-		new->gid = new->egid = new->sgid = new->fsgid = gid;
-	else if (gid == old->gid || gid == old->sgid)
-		new->egid = new->fsgid = gid;
+		new->gid = new->egid = new->sgid = new->fsgid = kgid;
+	else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid))
+		new->egid = new->fsgid = kgid;
 	else
 		goto error;
 
@@ -631,7 +648,7 @@ static int set_user(struct cred *new)
 {
 	struct user_struct *new_user;
 
-	new_user = alloc_uid(current_user_ns(), new->uid);
+	new_user = alloc_uid(new->uid);
 	if (!new_user)
 		return -EAGAIN;
 
@@ -670,9 +687,19 @@ static int set_user(struct cred *new)
  */
 SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
 {
+	struct user_namespace *ns = current_user_ns();
 	const struct cred *old;
 	struct cred *new;
 	int retval;
+	kuid_t kruid, keuid;
+
+	kruid = make_kuid(ns, ruid);
+	keuid = make_kuid(ns, euid);
+
+	if ((ruid != (uid_t) -1) && !uid_valid(kruid))
+		return -EINVAL;
+	if ((euid != (uid_t) -1) && !uid_valid(keuid))
+		return -EINVAL;
 
 	new = prepare_creds();
 	if (!new)
@@ -681,29 +708,29 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
 
 	retval = -EPERM;
 	if (ruid != (uid_t) -1) {
-		new->uid = ruid;
-		if (old->uid != ruid &&
-		    old->euid != ruid &&
+		new->uid = kruid;
+		if (!uid_eq(old->uid, kruid) &&
+		    !uid_eq(old->euid, kruid) &&
 		    !nsown_capable(CAP_SETUID))
 			goto error;
 	}
 
 	if (euid != (uid_t) -1) {
-		new->euid = euid;
-		if (old->uid != euid &&
-		    old->euid != euid &&
-		    old->suid != euid &&
+		new->euid = keuid;
+		if (!uid_eq(old->uid, keuid) &&
+		    !uid_eq(old->euid, keuid) &&
+		    !uid_eq(old->suid, keuid) &&
 		    !nsown_capable(CAP_SETUID))
 			goto error;
 	}
 
-	if (new->uid != old->uid) {
+	if (!uid_eq(new->uid, old->uid)) {
 		retval = set_user(new);
 		if (retval < 0)
 			goto error;
 	}
 	if (ruid != (uid_t) -1 ||
-	    (euid != (uid_t) -1 && euid != old->uid))
+	    (euid != (uid_t) -1 && !uid_eq(keuid, old->uid)))
 		new->suid = new->euid;
 	new->fsuid = new->euid;
 
@@ -731,9 +758,15 @@ error:
  */
 SYSCALL_DEFINE1(setuid, uid_t, uid)
 {
+	struct user_namespace *ns = current_user_ns();
 	const struct cred *old;
 	struct cred *new;
 	int retval;
+	kuid_t kuid;
+
+	kuid = make_kuid(ns, uid);
+	if (!uid_valid(kuid))
+		return -EINVAL;
 
 	new = prepare_creds();
 	if (!new)
@@ -742,17 +775,17 @@ SYSCALL_DEFINE1(setuid, uid_t, uid)
 
 	retval = -EPERM;
 	if (nsown_capable(CAP_SETUID)) {
-		new->suid = new->uid = uid;
-		if (uid != old->uid) {
+		new->suid = new->uid = kuid;
+		if (!uid_eq(kuid, old->uid)) {
 			retval = set_user(new);
 			if (retval < 0)
 				goto error;
 		}
-	} else if (uid != old->uid && uid != new->suid) {
+	} else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) {
 		goto error;
 	}
 
-	new->fsuid = new->euid = uid;
+	new->fsuid = new->euid = kuid;
 
 	retval = security_task_fix_setuid(new, old, LSM_SETID_ID);
 	if (retval < 0)
@@ -772,9 +805,24 @@ error:
  */
 SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
 {
+	struct user_namespace *ns = current_user_ns();
 	const struct cred *old;
 	struct cred *new;
 	int retval;
+	kuid_t kruid, keuid, ksuid;
+
+	kruid = make_kuid(ns, ruid);
+	keuid = make_kuid(ns, euid);
+	ksuid = make_kuid(ns, suid);
+
+	if ((ruid != (uid_t) -1) && !uid_valid(kruid))
+		return -EINVAL;
+
+	if ((euid != (uid_t) -1) && !uid_valid(keuid))
+		return -EINVAL;
+
+	if ((suid != (uid_t) -1) && !uid_valid(ksuid))
+		return -EINVAL;
 
 	new = prepare_creds();
 	if (!new)
@@ -784,29 +832,29 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
 
 	retval = -EPERM;
 	if (!nsown_capable(CAP_SETUID)) {
-		if (ruid != (uid_t) -1 && ruid != old->uid &&
-		    ruid != old->euid  && ruid != old->suid)
+		if (ruid != (uid_t) -1        && !uid_eq(kruid, old->uid) &&
+		    !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid))
 			goto error;
-		if (euid != (uid_t) -1 && euid != old->uid &&
-		    euid != old->euid  && euid != old->suid)
+		if (euid != (uid_t) -1        && !uid_eq(keuid, old->uid) &&
+		    !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid))
 			goto error;
-		if (suid != (uid_t) -1 && suid != old->uid &&
-		    suid != old->euid  && suid != old->suid)
+		if (suid != (uid_t) -1        && !uid_eq(ksuid, old->uid) &&
+		    !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid))
 			goto error;
 	}
 
 	if (ruid != (uid_t) -1) {
-		new->uid = ruid;
-		if (ruid != old->uid) {
+		new->uid = kruid;
+		if (!uid_eq(kruid, old->uid)) {
 			retval = set_user(new);
 			if (retval < 0)
 				goto error;
 		}
 	}
 	if (euid != (uid_t) -1)
-		new->euid = euid;
+		new->euid = keuid;
 	if (suid != (uid_t) -1)
-		new->suid = suid;
+		new->suid = ksuid;
 	new->fsuid = new->euid;
 
 	retval = security_task_fix_setuid(new, old, LSM_SETID_RES);
@@ -820,14 +868,19 @@ error:
 	return retval;
 }
 
-SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid)
+SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp)
 {
 	const struct cred *cred = current_cred();
 	int retval;
+	uid_t ruid, euid, suid;
+
+	ruid = from_kuid_munged(cred->user_ns, cred->uid);
+	euid = from_kuid_munged(cred->user_ns, cred->euid);
+	suid = from_kuid_munged(cred->user_ns, cred->suid);
 
-	if (!(retval   = put_user(cred->uid,  ruid)) &&
-	    !(retval   = put_user(cred->euid, euid)))
-		retval = put_user(cred->suid, suid);
+	if (!(retval   = put_user(ruid, ruidp)) &&
+	    !(retval   = put_user(euid, euidp)))
+		retval = put_user(suid, suidp);
 
 	return retval;
 }
@@ -837,9 +890,22 @@ SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __u
  */
 SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
 {
+	struct user_namespace *ns = current_user_ns();
 	const struct cred *old;
 	struct cred *new;
 	int retval;
+	kgid_t krgid, kegid, ksgid;
+
+	krgid = make_kgid(ns, rgid);
+	kegid = make_kgid(ns, egid);
+	ksgid = make_kgid(ns, sgid);
+
+	if ((rgid != (gid_t) -1) && !gid_valid(krgid))
+		return -EINVAL;
+	if ((egid != (gid_t) -1) && !gid_valid(kegid))
+		return -EINVAL;
+	if ((sgid != (gid_t) -1) && !gid_valid(ksgid))
+		return -EINVAL;
 
 	new = prepare_creds();
 	if (!new)
@@ -848,23 +914,23 @@ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
 
 	retval = -EPERM;
 	if (!nsown_capable(CAP_SETGID)) {
-		if (rgid != (gid_t) -1 && rgid != old->gid &&
-		    rgid != old->egid  && rgid != old->sgid)
+		if (rgid != (gid_t) -1        && !gid_eq(krgid, old->gid) &&
+		    !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid))
 			goto error;
-		if (egid != (gid_t) -1 && egid != old->gid &&
-		    egid != old->egid  && egid != old->sgid)
+		if (egid != (gid_t) -1        && !gid_eq(kegid, old->gid) &&
+		    !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid))
 			goto error;
-		if (sgid != (gid_t) -1 && sgid != old->gid &&
-		    sgid != old->egid  && sgid != old->sgid)
+		if (sgid != (gid_t) -1        && !gid_eq(ksgid, old->gid) &&
+		    !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid))
 			goto error;
 	}
 
 	if (rgid != (gid_t) -1)
-		new->gid = rgid;
+		new->gid = krgid;
 	if (egid != (gid_t) -1)
-		new->egid = egid;
+		new->egid = kegid;
 	if (sgid != (gid_t) -1)
-		new->sgid = sgid;
+		new->sgid = ksgid;
 	new->fsgid = new->egid;
 
 	return commit_creds(new);
@@ -874,14 +940,19 @@ error:
 	return retval;
 }
 
-SYSCALL_DEFINE3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid)
+SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp)
 {
 	const struct cred *cred = current_cred();
 	int retval;
+	gid_t rgid, egid, sgid;
+
+	rgid = from_kgid_munged(cred->user_ns, cred->gid);
+	egid = from_kgid_munged(cred->user_ns, cred->egid);
+	sgid = from_kgid_munged(cred->user_ns, cred->sgid);
 
-	if (!(retval   = put_user(cred->gid,  rgid)) &&
-	    !(retval   = put_user(cred->egid, egid)))
-		retval = put_user(cred->sgid, sgid);
+	if (!(retval   = put_user(rgid, rgidp)) &&
+	    !(retval   = put_user(egid, egidp)))
+		retval = put_user(sgid, sgidp);
 
 	return retval;
 }
@@ -898,18 +969,24 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid)
 	const struct cred *old;
 	struct cred *new;
 	uid_t old_fsuid;
+	kuid_t kuid;
+
+	old = current_cred();
+	old_fsuid = from_kuid_munged(old->user_ns, old->fsuid);
+
+	kuid = make_kuid(old->user_ns, uid);
+	if (!uid_valid(kuid))
+		return old_fsuid;
 
 	new = prepare_creds();
 	if (!new)
-		return current_fsuid();
-	old = current_cred();
-	old_fsuid = old->fsuid;
+		return old_fsuid;
 
-	if (uid == old->uid  || uid == old->euid  ||
-	    uid == old->suid || uid == old->fsuid ||
+	if (uid_eq(kuid, old->uid)  || uid_eq(kuid, old->euid)  ||
+	    uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) ||
 	    nsown_capable(CAP_SETUID)) {
-		if (uid != old_fsuid) {
-			new->fsuid = uid;
+		if (!uid_eq(kuid, old->fsuid)) {
+			new->fsuid = kuid;
 			if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
 				goto change_okay;
 		}
@@ -931,18 +1008,24 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid)
 	const struct cred *old;
 	struct cred *new;
 	gid_t old_fsgid;
+	kgid_t kgid;
+
+	old = current_cred();
+	old_fsgid = from_kgid_munged(old->user_ns, old->fsgid);
+
+	kgid = make_kgid(old->user_ns, gid);
+	if (!gid_valid(kgid))
+		return old_fsgid;
 
 	new = prepare_creds();
 	if (!new)
-		return current_fsgid();
-	old = current_cred();
-	old_fsgid = old->fsgid;
+		return old_fsgid;
 
-	if (gid == old->gid  || gid == old->egid  ||
-	    gid == old->sgid || gid == old->fsgid ||
+	if (gid_eq(kgid, old->gid)  || gid_eq(kgid, old->egid)  ||
+	    gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) ||
 	    nsown_capable(CAP_SETGID)) {
-		if (gid != old_fsgid) {
-			new->fsgid = gid;
+		if (!gid_eq(kgid, old->fsgid)) {
+			new->fsgid = kgid;
 			goto change_okay;
 		}
 	}
@@ -1498,15 +1581,14 @@ static int check_prlimit_permission(struct task_struct *task)
 		return 0;
 
 	tcred = __task_cred(task);
-	if (cred->user->user_ns == tcred->user->user_ns &&
-	    (cred->uid == tcred->euid &&
-	     cred->uid == tcred->suid &&
-	     cred->uid == tcred->uid  &&
-	     cred->gid == tcred->egid &&
-	     cred->gid == tcred->sgid &&
-	     cred->gid == tcred->gid))
+	if (uid_eq(cred->uid, tcred->euid) &&
+	    uid_eq(cred->uid, tcred->suid) &&
+	    uid_eq(cred->uid, tcred->uid)  &&
+	    gid_eq(cred->gid, tcred->egid) &&
+	    gid_eq(cred->gid, tcred->sgid) &&
+	    gid_eq(cred->gid, tcred->gid))
 		return 0;
-	if (ns_capable(tcred->user->user_ns, CAP_SYS_RESOURCE))
+	if (ns_capable(tcred->user_ns, CAP_SYS_RESOURCE))
 		return 0;
 
 	return -EPERM;

kernel/timer.c

@@ -1435,25 +1435,25 @@ SYSCALL_DEFINE0(getppid)
 SYSCALL_DEFINE0(getuid)
 {
 	/* Only we change this so SMP safe */
-	return current_uid();
+	return from_kuid_munged(current_user_ns(), current_uid());
 }
 
 SYSCALL_DEFINE0(geteuid)
 {
 	/* Only we change this so SMP safe */
-	return current_euid();
+	return from_kuid_munged(current_user_ns(), current_euid());
 }
 
 SYSCALL_DEFINE0(getgid)
 {
 	/* Only we change this so SMP safe */
-	return current_gid();
+	return from_kgid_munged(current_user_ns(), current_gid());
 }
 
 SYSCALL_DEFINE0(getegid)
 {
 	/* Only we change this so SMP safe */
-	return  current_egid();
+	return from_kgid_munged(current_user_ns(), current_egid());
 }
 
 #endif

kernel/uid16.c

@@ -81,14 +81,19 @@ SYSCALL_DEFINE3(setresuid16, old_uid_t, ruid, old_uid_t, euid, old_uid_t, suid)
 	return ret;
 }
 
-SYSCALL_DEFINE3(getresuid16, old_uid_t __user *, ruid, old_uid_t __user *, euid, old_uid_t __user *, suid)
+SYSCALL_DEFINE3(getresuid16, old_uid_t __user *, ruidp, old_uid_t __user *, euidp, old_uid_t __user *, suidp)
 {
 	const struct cred *cred = current_cred();
 	int retval;
+	old_uid_t ruid, euid, suid;
 
-	if (!(retval   = put_user(high2lowuid(cred->uid),  ruid)) &&
-	    !(retval   = put_user(high2lowuid(cred->euid), euid)))
-		retval = put_user(high2lowuid(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;
 }
@@ -103,14 +108,19 @@ SYSCALL_DEFINE3(setresgid16, old_gid_t, rgid, old_gid_t, egid, old_gid_t, sgid)
 }
 
 
-SYSCALL_DEFINE3(getresgid16, old_gid_t __user *, rgid, old_gid_t __user *, egid, old_gid_t __user *, sgid)
+SYSCALL_DEFINE3(getresgid16, old_gid_t __user *, rgidp, old_gid_t __user *, egidp, old_gid_t __user *, sgidp)
 {
 	const struct cred *cred = current_cred();
 	int retval;
+	old_gid_t 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(cred->gid),  rgid)) &&
-	    !(retval   = put_user(high2lowgid(cred->egid), egid)))
-		retval = put_user(high2lowgid(cred->sgid), sgid);
+	if (!(retval   = put_user(rgid, rgidp)) &&
+	    !(retval   = put_user(egid, egidp)))
+		retval = put_user(sgid, sgidp);
 
 	return retval;
 }
@@ -134,11 +144,14 @@ SYSCALL_DEFINE1(setfsgid16, old_gid_t, gid)
 static int groups16_to_user(old_gid_t __user *grouplist,
     struct group_info *group_info)
 {
+	struct user_namespace *user_ns = current_user_ns();
 	int i;
 	old_gid_t group;
+	kgid_t kgid;
 
 	for (i = 0; i < group_info->ngroups; i++) {
-		group = high2lowgid(GROUP_AT(group_info, i));
+		kgid = GROUP_AT(group_info, i);
+		group = high2lowgid(from_kgid_munged(user_ns, kgid));
 		if (put_user(group, grouplist+i))
 			return -EFAULT;
 	}
@@ -149,13 +162,20 @@ static int groups16_to_user(old_gid_t __user *grouplist,
 static int groups16_from_user(struct group_info *group_info,
     old_gid_t __user *grouplist)
 {
+	struct user_namespace *user_ns = current_user_ns();
 	int i;
 	old_gid_t group;
+	kgid_t kgid;
 
 	for (i = 0; i < group_info->ngroups; i++) {
 		if (get_user(group, grouplist+i))
 			return  -EFAULT;
-		GROUP_AT(group_info, i) = low2highgid(group);
+
+		kgid = make_kgid(user_ns, low2highgid(group));
+		if (!gid_valid(kgid))
+			return -EINVAL;
+
+		GROUP_AT(group_info, i) = kgid;
 	}
 
 	return 0;
@@ -211,20 +231,20 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
 
 SYSCALL_DEFINE0(getuid16)
 {
-	return high2lowuid(current_uid());
+	return high2lowuid(from_kuid_munged(current_user_ns(), current_uid()));
 }
 
 SYSCALL_DEFINE0(geteuid16)
 {
-	return high2lowuid(current_euid());
+	return high2lowuid(from_kuid_munged(current_user_ns(), current_euid()));
 }
 
 SYSCALL_DEFINE0(getgid16)
 {
-	return high2lowgid(current_gid());
+	return high2lowgid(from_kgid_munged(current_user_ns(), current_gid()));
 }
 
 SYSCALL_DEFINE0(getegid16)
 {
-	return high2lowgid(current_egid());
+	return high2lowgid(from_kgid_munged(current_user_ns(), current_egid()));
 }

kernel/user.c

@@ -22,10 +22,27 @@
  * and 1 for... ?
  */
 struct user_namespace init_user_ns = {
+	.uid_map = {
+		.nr_extents = 1,
+		.extent[0] = {
+			.first = 0,
+			.lower_first = 0,
+			.count = 4294967295U,
+		},
+	},
+	.gid_map = {
+		.nr_extents = 1,
+		.extent[0] = {
+			.first = 0,
+			.lower_first = 0,
+			.count = 4294967295U,
+		},
+	},
 	.kref = {
 		.refcount	= ATOMIC_INIT(3),
 	},
-	.creator = &root_user,
+	.owner = GLOBAL_ROOT_UID,
+	.group = GLOBAL_ROOT_GID,
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
@@ -34,11 +51,14 @@ EXPORT_SYMBOL_GPL(init_user_ns);
  * when changing user ID's (ie setuid() and friends).
  */
 
+#define UIDHASH_BITS	(CONFIG_BASE_SMALL ? 3 : 7)
+#define UIDHASH_SZ	(1 << UIDHASH_BITS)
 #define UIDHASH_MASK		(UIDHASH_SZ - 1)
 #define __uidhashfn(uid)	(((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK)
-#define uidhashentry(ns, uid)	((ns)->uidhash_table + __uidhashfn((uid)))
+#define uidhashentry(uid)	(uidhash_table + __uidhashfn((__kuid_val(uid))))
 
 static struct kmem_cache *uid_cachep;
+struct hlist_head uidhash_table[UIDHASH_SZ];
 
 /*
  * The uidhash_lock is mostly taken from process context, but it is
@@ -51,14 +71,14 @@ static struct kmem_cache *uid_cachep;
  */
 static DEFINE_SPINLOCK(uidhash_lock);
 
-/* root_user.__count is 2, 1 for init task cred, 1 for init_user_ns->user_ns */
+/* root_user.__count is 1, for init task cred */
 struct user_struct root_user = {
-	.__count	= ATOMIC_INIT(2),
+	.__count	= ATOMIC_INIT(1),
 	.processes	= ATOMIC_INIT(1),
 	.files		= ATOMIC_INIT(0),
 	.sigpending	= ATOMIC_INIT(0),
 	.locked_shm     = 0,
-	.user_ns	= &init_user_ns,
+	.uid		= GLOBAL_ROOT_UID,
 };
 
 /*
@@ -72,16 +92,15 @@ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
 static void uid_hash_remove(struct user_struct *up)
 {
 	hlist_del_init(&up->uidhash_node);
-	put_user_ns(up->user_ns);
 }
 
-static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
+static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent)
 {
 	struct user_struct *user;
 	struct hlist_node *h;
 
 	hlist_for_each_entry(user, h, hashent, uidhash_node) {
-		if (user->uid == uid) {
+		if (uid_eq(user->uid, uid)) {
 			atomic_inc(&user->__count);
 			return user;
 		}
@@ -110,14 +129,13 @@ static void free_user(struct user_struct *up, unsigned long flags)
  *
  * If the user_struct could not be found, return NULL.
  */
-struct user_struct *find_user(uid_t uid)
+struct user_struct *find_user(kuid_t uid)
 {
 	struct user_struct *ret;
 	unsigned long flags;
-	struct user_namespace *ns = current_user_ns();
 
 	spin_lock_irqsave(&uidhash_lock, flags);
-	ret = uid_hash_find(uid, uidhashentry(ns, uid));
+	ret = uid_hash_find(uid, uidhashentry(uid));
 	spin_unlock_irqrestore(&uidhash_lock, flags);
 	return ret;
 }
@@ -136,9 +154,9 @@ void free_uid(struct user_struct *up)
 		local_irq_restore(flags);
 }
 
-struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
+struct user_struct *alloc_uid(kuid_t uid)
 {
-	struct hlist_head *hashent = uidhashentry(ns, uid);
+	struct hlist_head *hashent = uidhashentry(uid);
 	struct user_struct *up, *new;
 
 	spin_lock_irq(&uidhash_lock);
@@ -153,8 +171,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 		new->uid = uid;
 		atomic_set(&new->__count, 1);
 
-		new->user_ns = get_user_ns(ns);
-
 		/*
 		 * Before adding this, check whether we raced
 		 * on adding the same user already..
@@ -162,7 +178,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 		spin_lock_irq(&uidhash_lock);
 		up = uid_hash_find(uid, hashent);
 		if (up) {
-			put_user_ns(ns);
 			key_put(new->uid_keyring);
 			key_put(new->session_keyring);
 			kmem_cache_free(uid_cachep, new);
@@ -187,11 +202,11 @@ static int __init uid_cache_init(void)
 			0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 
 	for(n = 0; n < UIDHASH_SZ; ++n)
-		INIT_HLIST_HEAD(init_user_ns.uidhash_table + n);
+		INIT_HLIST_HEAD(uidhash_table + n);
 
 	/* Insert the root user immediately (init already runs as root) */
 	spin_lock_irq(&uidhash_lock);
-	uid_hash_insert(&root_user, uidhashentry(&init_user_ns, 0));
+	uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
 	spin_unlock_irq(&uidhash_lock);
 
 	return 0;

kernel/user_namespace.c

@@ -11,9 +11,20 @@
 #include <linux/user_namespace.h>
 #include <linux/highuid.h>
 #include <linux/cred.h>
+#include <linux/securebits.h>
+#include <linux/keyctl.h>
+#include <linux/key-type.h>
+#include <keys/user-type.h>
+#include <linux/seq_file.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/ctype.h>
 
 static struct kmem_cache *user_ns_cachep __read_mostly;
 
+static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
+				struct uid_gid_map *map);
+
 /*
  * Create a new user namespace, deriving the creator from the user in the
  * passed credentials, and replacing that user with the new root user for the
@@ -24,109 +35,565 @@ static struct kmem_cache *user_ns_cachep __read_mostly;
  */
 int create_user_ns(struct cred *new)
 {
-	struct user_namespace *ns;
-	struct user_struct *root_user;
-	int n;
+	struct user_namespace *ns, *parent_ns = new->user_ns;
+	kuid_t owner = new->euid;
+	kgid_t group = new->egid;
+
+	/* The creator needs a mapping in the parent user namespace
+	 * or else we won't be able to reasonably tell userspace who
+	 * created a user_namespace.
+	 */
+	if (!kuid_has_mapping(parent_ns, owner) ||
+	    !kgid_has_mapping(parent_ns, group))
+		return -EPERM;
 
-	ns = kmem_cache_alloc(user_ns_cachep, GFP_KERNEL);
+	ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL);
 	if (!ns)
 		return -ENOMEM;
 
 	kref_init(&ns->kref);
+	ns->parent = parent_ns;
+	ns->owner = owner;
+	ns->group = group;
 
-	for (n = 0; n < UIDHASH_SZ; ++n)
-		INIT_HLIST_HEAD(ns->uidhash_table + n);
-
-	/* Alloc new root user.  */
-	root_user = alloc_uid(ns, 0);
-	if (!root_user) {
-		kmem_cache_free(user_ns_cachep, ns);
-		return -ENOMEM;
-	}
-
-	/* set the new root user in the credentials under preparation */
-	ns->creator = new->user;
-	new->user = root_user;
-	new->uid = new->euid = new->suid = new->fsuid = 0;
-	new->gid = new->egid = new->sgid = new->fsgid = 0;
-	put_group_info(new->group_info);
-	new->group_info = get_group_info(&init_groups);
+	/* Start with the same capabilities as init but useless for doing
+	 * anything as the capabilities are bound to the new user namespace.
+	 */
+	new->securebits = SECUREBITS_DEFAULT;
+	new->cap_inheritable = CAP_EMPTY_SET;
+	new->cap_permitted = CAP_FULL_SET;
+	new->cap_effective = CAP_FULL_SET;
+	new->cap_bset = CAP_FULL_SET;
 #ifdef CONFIG_KEYS
 	key_put(new->request_key_auth);
 	new->request_key_auth = NULL;
 #endif
 	/* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */
 
-	/* root_user holds a reference to ns, our reference can be dropped */
-	put_user_ns(ns);
+	/* Leave the new->user_ns reference with the new user namespace. */
+	/* Leave the reference to our user_ns with the new cred. */
+	new->user_ns = ns;
 
 	return 0;
 }
 
-/*
- * Deferred destructor for a user namespace.  This is required because
- * free_user_ns() may be called with uidhash_lock held, but we need to call
- * back to free_uid() which will want to take the lock again.
- */
-static void free_user_ns_work(struct work_struct *work)
+void free_user_ns(struct kref *kref)
 {
-	struct user_namespace *ns =
-		container_of(work, struct user_namespace, destroyer);
-	free_uid(ns->creator);
+	struct user_namespace *parent, *ns =
+		container_of(kref, struct user_namespace, kref);
+
+	parent = ns->parent;
 	kmem_cache_free(user_ns_cachep, ns);
+	put_user_ns(parent);
 }
+EXPORT_SYMBOL(free_user_ns);
 
-void free_user_ns(struct kref *kref)
+static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count)
 {
-	struct user_namespace *ns =
-		container_of(kref, struct user_namespace, kref);
+	unsigned idx, extents;
+	u32 first, last, id2;
+
+	id2 = id + count - 1;
+
+	/* Find the matching extent */
+	extents = map->nr_extents;
+	smp_read_barrier_depends();
+	for (idx = 0; idx < extents; idx++) {
+		first = map->extent[idx].first;
+		last = first + map->extent[idx].count - 1;
+		if (id >= first && id <= last &&
+		    (id2 >= first && id2 <= last))
+			break;
+	}
+	/* Map the id or note failure */
+	if (idx < extents)
+		id = (id - first) + map->extent[idx].lower_first;
+	else
+		id = (u32) -1;
 
-	INIT_WORK(&ns->destroyer, free_user_ns_work);
-	schedule_work(&ns->destroyer);
+	return id;
 }
-EXPORT_SYMBOL(free_user_ns);
 
-uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t uid)
+static u32 map_id_down(struct uid_gid_map *map, u32 id)
 {
-	struct user_namespace *tmp;
+	unsigned idx, extents;
+	u32 first, last;
 
-	if (likely(to == cred->user->user_ns))
-		return uid;
+	/* Find the matching extent */
+	extents = map->nr_extents;
+	smp_read_barrier_depends();
+	for (idx = 0; idx < extents; idx++) {
+		first = map->extent[idx].first;
+		last = first + map->extent[idx].count - 1;
+		if (id >= first && id <= last)
+			break;
+	}
+	/* Map the id or note failure */
+	if (idx < extents)
+		id = (id - first) + map->extent[idx].lower_first;
+	else
+		id = (u32) -1;
 
+	return id;
+}
 
-	/* Is cred->user the creator of the target user_ns
-	 * or the creator of one of it's parents?
-	 */
-	for ( tmp = to; tmp != &init_user_ns;
-	      tmp = tmp->creator->user_ns ) {
-		if (cred->user == tmp->creator) {
-			return (uid_t)0;
-		}
+static u32 map_id_up(struct uid_gid_map *map, u32 id)
+{
+	unsigned idx, extents;
+	u32 first, last;
+
+	/* Find the matching extent */
+	extents = map->nr_extents;
+	smp_read_barrier_depends();
+	for (idx = 0; idx < extents; idx++) {
+		first = map->extent[idx].lower_first;
+		last = first + map->extent[idx].count - 1;
+		if (id >= first && id <= last)
+			break;
 	}
+	/* Map the id or note failure */
+	if (idx < extents)
+		id = (id - first) + map->extent[idx].first;
+	else
+		id = (u32) -1;
+
+	return id;
+}
+
+/**
+ *	make_kuid - Map a user-namespace uid pair into a kuid.
+ *	@ns:  User namespace that the uid is in
+ *	@uid: User identifier
+ *
+ *	Maps a user-namespace uid pair into a kernel internal kuid,
+ *	and returns that kuid.
+ *
+ *	When there is no mapping defined for the user-namespace uid
+ *	pair INVALID_UID is returned.  Callers are expected to test
+ *	for and handle handle INVALID_UID being returned.  INVALID_UID
+ *	may be tested for using uid_valid().
+ */
+kuid_t make_kuid(struct user_namespace *ns, uid_t uid)
+{
+	/* Map the uid to a global kernel uid */
+	return KUIDT_INIT(map_id_down(&ns->uid_map, uid));
+}
+EXPORT_SYMBOL(make_kuid);
+
+/**
+ *	from_kuid - Create a uid from a kuid user-namespace pair.
+ *	@targ: The user namespace we want a uid in.
+ *	@kuid: The kernel internal uid to start with.
+ *
+ *	Map @kuid into the user-namespace specified by @targ and
+ *	return the resulting uid.
+ *
+ *	There is always a mapping into the initial user_namespace.
+ *
+ *	If @kuid has no mapping in @targ (uid_t)-1 is returned.
+ */
+uid_t from_kuid(struct user_namespace *targ, kuid_t kuid)
+{
+	/* Map the uid from a global kernel uid */
+	return map_id_up(&targ->uid_map, __kuid_val(kuid));
+}
+EXPORT_SYMBOL(from_kuid);
 
-	/* No useful relationship so no mapping */
-	return overflowuid;
+/**
+ *	from_kuid_munged - Create a uid from a kuid user-namespace pair.
+ *	@targ: The user namespace we want a uid in.
+ *	@kuid: The kernel internal uid to start with.
+ *
+ *	Map @kuid into the user-namespace specified by @targ and
+ *	return the resulting uid.
+ *
+ *	There is always a mapping into the initial user_namespace.
+ *
+ *	Unlike from_kuid from_kuid_munged never fails and always
+ *	returns a valid uid.  This makes from_kuid_munged appropriate
+ *	for use in syscalls like stat and getuid where failing the
+ *	system call and failing to provide a valid uid are not an
+ *	options.
+ *
+ *	If @kuid has no mapping in @targ overflowuid is returned.
+ */
+uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid)
+{
+	uid_t uid;
+	uid = from_kuid(targ, kuid);
+
+	if (uid == (uid_t) -1)
+		uid = overflowuid;
+	return uid;
 }
+EXPORT_SYMBOL(from_kuid_munged);
 
-gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t gid)
+/**
+ *	make_kgid - Map a user-namespace gid pair into a kgid.
+ *	@ns:  User namespace that the gid is in
+ *	@uid: group identifier
+ *
+ *	Maps a user-namespace gid pair into a kernel internal kgid,
+ *	and returns that kgid.
+ *
+ *	When there is no mapping defined for the user-namespace gid
+ *	pair INVALID_GID is returned.  Callers are expected to test
+ *	for and handle INVALID_GID being returned.  INVALID_GID may be
+ *	tested for using gid_valid().
+ */
+kgid_t make_kgid(struct user_namespace *ns, gid_t gid)
 {
-	struct user_namespace *tmp;
+	/* Map the gid to a global kernel gid */
+	return KGIDT_INIT(map_id_down(&ns->gid_map, gid));
+}
+EXPORT_SYMBOL(make_kgid);
 
-	if (likely(to == cred->user->user_ns))
-		return gid;
+/**
+ *	from_kgid - Create a gid from a kgid user-namespace pair.
+ *	@targ: The user namespace we want a gid in.
+ *	@kgid: The kernel internal gid to start with.
+ *
+ *	Map @kgid into the user-namespace specified by @targ and
+ *	return the resulting gid.
+ *
+ *	There is always a mapping into the initial user_namespace.
+ *
+ *	If @kgid has no mapping in @targ (gid_t)-1 is returned.
+ */
+gid_t from_kgid(struct user_namespace *targ, kgid_t kgid)
+{
+	/* Map the gid from a global kernel gid */
+	return map_id_up(&targ->gid_map, __kgid_val(kgid));
+}
+EXPORT_SYMBOL(from_kgid);
+
+/**
+ *	from_kgid_munged - Create a gid from a kgid user-namespace pair.
+ *	@targ: The user namespace we want a gid in.
+ *	@kgid: The kernel internal gid to start with.
+ *
+ *	Map @kgid into the user-namespace specified by @targ and
+ *	return the resulting gid.
+ *
+ *	There is always a mapping into the initial user_namespace.
+ *
+ *	Unlike from_kgid from_kgid_munged never fails and always
+ *	returns a valid gid.  This makes from_kgid_munged appropriate
+ *	for use in syscalls like stat and getgid where failing the
+ *	system call and failing to provide a valid gid are not options.
+ *
+ *	If @kgid has no mapping in @targ overflowgid is returned.
+ */
+gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid)
+{
+	gid_t gid;
+	gid = from_kgid(targ, kgid);
 
-	/* Is cred->user the creator of the target user_ns
-	 * or the creator of one of it's parents?
+	if (gid == (gid_t) -1)
+		gid = overflowgid;
+	return gid;
+}
+EXPORT_SYMBOL(from_kgid_munged);
+
+static int uid_m_show(struct seq_file *seq, void *v)
+{
+	struct user_namespace *ns = seq->private;
+	struct uid_gid_extent *extent = v;
+	struct user_namespace *lower_ns;
+	uid_t lower;
+
+	lower_ns = current_user_ns();
+	if ((lower_ns == ns) && lower_ns->parent)
+		lower_ns = lower_ns->parent;
+
+	lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first));
+
+	seq_printf(seq, "%10u %10u %10u\n",
+		extent->first,
+		lower,
+		extent->count);
+
+	return 0;
+}
+
+static int gid_m_show(struct seq_file *seq, void *v)
+{
+	struct user_namespace *ns = seq->private;
+	struct uid_gid_extent *extent = v;
+	struct user_namespace *lower_ns;
+	gid_t lower;
+
+	lower_ns = current_user_ns();
+	if ((lower_ns == ns) && lower_ns->parent)
+		lower_ns = lower_ns->parent;
+
+	lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first));
+
+	seq_printf(seq, "%10u %10u %10u\n",
+		extent->first,
+		lower,
+		extent->count);
+
+	return 0;
+}
+
+static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map)
+{
+	struct uid_gid_extent *extent = NULL;
+	loff_t pos = *ppos;
+
+	if (pos < map->nr_extents)
+		extent = &map->extent[pos];
+
+	return extent;
+}
+
+static void *uid_m_start(struct seq_file *seq, loff_t *ppos)
+{
+	struct user_namespace *ns = seq->private;
+
+	return m_start(seq, ppos, &ns->uid_map);
+}
+
+static void *gid_m_start(struct seq_file *seq, loff_t *ppos)
+{
+	struct user_namespace *ns = seq->private;
+
+	return m_start(seq, ppos, &ns->gid_map);
+}
+
+static void *m_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return seq->op->start(seq, pos);
+}
+
+static void m_stop(struct seq_file *seq, void *v)
+{
+	return;
+}
+
+struct seq_operations proc_uid_seq_operations = {
+	.start = uid_m_start,
+	.stop = m_stop,
+	.next = m_next,
+	.show = uid_m_show,
+};
+
+struct seq_operations proc_gid_seq_operations = {
+	.start = gid_m_start,
+	.stop = m_stop,
+	.next = m_next,
+	.show = gid_m_show,
+};
+
+static DEFINE_MUTEX(id_map_mutex);
+
+static ssize_t map_write(struct file *file, const char __user *buf,
+			 size_t count, loff_t *ppos,
+			 int cap_setid,
+			 struct uid_gid_map *map,
+			 struct uid_gid_map *parent_map)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	struct uid_gid_map new_map;
+	unsigned idx;
+	struct uid_gid_extent *extent, *last = NULL;
+	unsigned long page = 0;
+	char *kbuf, *pos, *next_line;
+	ssize_t ret = -EINVAL;
+
+	/*
+	 * The id_map_mutex serializes all writes to any given map.
+	 *
+	 * Any map is only ever written once.
+	 *
+	 * An id map fits within 1 cache line on most architectures.
+	 *
+	 * On read nothing needs to be done unless you are on an
+	 * architecture with a crazy cache coherency model like alpha.
+	 *
+	 * There is a one time data dependency between reading the
+	 * count of the extents and the values of the extents.  The
+	 * desired behavior is to see the values of the extents that
+	 * were written before the count of the extents.
+	 *
+	 * To achieve this smp_wmb() is used on guarantee the write
+	 * order and smp_read_barrier_depends() is guaranteed that we
+	 * don't have crazy architectures returning stale data.
+	 *
 	 */
-	for ( tmp = to; tmp != &init_user_ns;
-	      tmp = tmp->creator->user_ns ) {
-		if (cred->user == tmp->creator) {
-			return (gid_t)0;
+	mutex_lock(&id_map_mutex);
+
+	ret = -EPERM;
+	/* Only allow one successful write to the map */
+	if (map->nr_extents != 0)
+		goto out;
+
+	/* Require the appropriate privilege CAP_SETUID or CAP_SETGID
+	 * over the user namespace in order to set the id mapping.
+	 */
+	if (!ns_capable(ns, cap_setid))
+		goto out;
+
+	/* Get a buffer */
+	ret = -ENOMEM;
+	page = __get_free_page(GFP_TEMPORARY);
+	kbuf = (char *) page;
+	if (!page)
+		goto out;
+
+	/* Only allow <= page size writes at the beginning of the file */
+	ret = -EINVAL;
+	if ((*ppos != 0) || (count >= PAGE_SIZE))
+		goto out;
+
+	/* Slurp in the user data */
+	ret = -EFAULT;
+	if (copy_from_user(kbuf, buf, count))
+		goto out;
+	kbuf[count] = '\0';
+
+	/* Parse the user data */
+	ret = -EINVAL;
+	pos = kbuf;
+	new_map.nr_extents = 0;
+	for (;pos; pos = next_line) {
+		extent = &new_map.extent[new_map.nr_extents];
+
+		/* Find the end of line and ensure I don't look past it */
+		next_line = strchr(pos, '\n');
+		if (next_line) {
+			*next_line = '\0';
+			next_line++;
+			if (*next_line == '\0')
+				next_line = NULL;
 		}
+
+		pos = skip_spaces(pos);
+		extent->first = simple_strtoul(pos, &pos, 10);
+		if (!isspace(*pos))
+			goto out;
+
+		pos = skip_spaces(pos);
+		extent->lower_first = simple_strtoul(pos, &pos, 10);
+		if (!isspace(*pos))
+			goto out;
+
+		pos = skip_spaces(pos);
+		extent->count = simple_strtoul(pos, &pos, 10);
+		if (*pos && !isspace(*pos))
+			goto out;
+
+		/* Verify there is not trailing junk on the line */
+		pos = skip_spaces(pos);
+		if (*pos != '\0')
+			goto out;
+
+		/* Verify we have been given valid starting values */
+		if ((extent->first == (u32) -1) ||
+		    (extent->lower_first == (u32) -1 ))
+			goto out;
+
+		/* Verify count is not zero and does not cause the extent to wrap */
+		if ((extent->first + extent->count) <= extent->first)
+			goto out;
+		if ((extent->lower_first + extent->count) <= extent->lower_first)
+			goto out;
+
+		/* For now only accept extents that are strictly in order */
+		if (last &&
+		    (((last->first + last->count) > extent->first) ||
+		     ((last->lower_first + last->count) > extent->lower_first)))
+			goto out;
+
+		new_map.nr_extents++;
+		last = extent;
+
+		/* Fail if the file contains too many extents */
+		if ((new_map.nr_extents == UID_GID_MAP_MAX_EXTENTS) &&
+		    (next_line != NULL))
+			goto out;
+	}
+	/* Be very certaint the new map actually exists */
+	if (new_map.nr_extents == 0)
+		goto out;
+
+	ret = -EPERM;
+	/* Validate the user is allowed to use user id's mapped to. */
+	if (!new_idmap_permitted(ns, cap_setid, &new_map))
+		goto out;
+
+	/* Map the lower ids from the parent user namespace to the
+	 * kernel global id space.
+	 */
+	for (idx = 0; idx < new_map.nr_extents; idx++) {
+		u32 lower_first;
+		extent = &new_map.extent[idx];
+
+		lower_first = map_id_range_down(parent_map,
+						extent->lower_first,
+						extent->count);
+
+		/* Fail if we can not map the specified extent to
+		 * the kernel global id space.
+		 */
+		if (lower_first == (u32) -1)
+			goto out;
+
+		extent->lower_first = lower_first;
 	}
 
-	/* No useful relationship so no mapping */
-	return overflowgid;
+	/* Install the map */
+	memcpy(map->extent, new_map.extent,
+		new_map.nr_extents*sizeof(new_map.extent[0]));
+	smp_wmb();
+	map->nr_extents = new_map.nr_extents;
+
+	*ppos = count;
+	ret = count;
+out:
+	mutex_unlock(&id_map_mutex);
+	if (page)
+		free_page(page);
+	return ret;
+}
+
+ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+
+	if (!ns->parent)
+		return -EPERM;
+
+	return map_write(file, buf, size, ppos, CAP_SETUID,
+			 &ns->uid_map, &ns->parent->uid_map);
+}
+
+ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+
+	if (!ns->parent)
+		return -EPERM;
+
+	return map_write(file, buf, size, ppos, CAP_SETGID,
+			 &ns->gid_map, &ns->parent->gid_map);
+}
+
+static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
+				struct uid_gid_map *new_map)
+{
+	/* Allow the specified ids if we have the appropriate capability
+	 * (CAP_SETUID or CAP_SETGID) over the parent user namespace.
+	 */
+	if (ns_capable(ns->parent, cap_setid))
+		return true;
+
+	return false;
 }
 
 static __init int user_namespaces_init(void)

kernel/utsname.c

@@ -43,7 +43,7 @@ static struct uts_namespace *clone_uts_ns(struct task_struct *tsk,
 
 	down_read(&uts_sem);
 	memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
-	ns->user_ns = get_user_ns(task_cred_xxx(tsk, user)->user_ns);
+	ns->user_ns = get_user_ns(task_cred_xxx(tsk, user_ns));
 	up_read(&uts_sem);
 	return ns;
 }

mm/mempolicy.c

@@ -1334,8 +1334,8 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
 	 * userid as the target process.
 	 */
 	tcred = __task_cred(task);
-	if (cred->euid != tcred->suid && cred->euid != tcred->uid &&
-	    cred->uid  != tcred->suid && cred->uid  != tcred->uid &&
+	if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) &&
+	    !uid_eq(cred->uid,  tcred->suid) && !uid_eq(cred->uid,  tcred->uid) &&
 	    !capable(CAP_SYS_NICE)) {
 		rcu_read_unlock();
 		err = -EPERM;

mm/migrate.c

@@ -1371,8 +1371,8 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 	 * userid as the target process.
 	 */
 	tcred = __task_cred(task);
-	if (cred->euid != tcred->suid && cred->euid != tcred->uid &&
-	    cred->uid  != tcred->suid && cred->uid  != tcred->uid &&
+	if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) &&
+	    !uid_eq(cred->uid,  tcred->suid) && !uid_eq(cred->uid,  tcred->uid) &&
 	    !capable(CAP_SYS_NICE)) {
 		rcu_read_unlock();
 		err = -EPERM;

mm/oom_kill.c

@@ -410,8 +410,8 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas
 		}
 
 		pr_info("[%5d] %5d %5d %8lu %8lu %3u     %3d         %5d %s\n",
-			task->pid, task_uid(task), task->tgid,
-			task->mm->total_vm, get_mm_rss(task->mm),
+			task->pid, from_kuid(&init_user_ns, task_uid(task)),
+			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
 			task_cpu(task), task->signal->oom_adj,
 			task->signal->oom_score_adj, task->comm);
 		task_unlock(task);

mm/shmem.c

@@ -2075,6 +2075,8 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
 			       bool remount)
 {
 	char *this_char, *value, *rest;
+	uid_t uid;
+	gid_t gid;
 
 	while (options != NULL) {
 		this_char = options;
@@ -2134,15 +2136,21 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
 		} else if (!strcmp(this_char,"uid")) {
 			if (remount)
 				continue;
-			sbinfo->uid = simple_strtoul(value, &rest, 0);
+			uid = simple_strtoul(value, &rest, 0);
 			if (*rest)
 				goto bad_val;
+			sbinfo->uid = make_kuid(current_user_ns(), uid);
+			if (!uid_valid(sbinfo->uid))
+				goto bad_val;
 		} else if (!strcmp(this_char,"gid")) {
 			if (remount)
 				continue;
-			sbinfo->gid = simple_strtoul(value, &rest, 0);
+			gid = simple_strtoul(value, &rest, 0);
 			if (*rest)
 				goto bad_val;
+			sbinfo->gid = make_kgid(current_user_ns(), gid);
+			if (!gid_valid(sbinfo->gid))
+				goto bad_val;
 		} else if (!strcmp(this_char,"mpol")) {
 			if (mpol_parse_str(value, &sbinfo->mpol, 1))
 				goto bad_val;
@@ -2210,10 +2218,12 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root)
 		seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes);
 	if (sbinfo->mode != (S_IRWXUGO | S_ISVTX))
 		seq_printf(seq, ",mode=%03ho", sbinfo->mode);
-	if (sbinfo->uid != 0)
-		seq_printf(seq, ",uid=%u", sbinfo->uid);
-	if (sbinfo->gid != 0)
-		seq_printf(seq, ",gid=%u", sbinfo->gid);
+	if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID))
+		seq_printf(seq, ",uid=%u",
+				from_kuid_munged(&init_user_ns, sbinfo->uid));
+	if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID))
+		seq_printf(seq, ",gid=%u",
+				from_kgid_munged(&init_user_ns, sbinfo->gid));
 	shmem_show_mpol(seq, sbinfo->mpol);
 	return 0;
 }

net/core/sock.c

@@ -813,8 +813,8 @@ void cred_to_ucred(struct pid *pid, const struct cred *cred,
 	if (cred) {
 		struct user_namespace *current_ns = current_user_ns();
 
-		ucred->uid = user_ns_map_uid(current_ns, cred, cred->euid);
-		ucred->gid = user_ns_map_gid(current_ns, cred, cred->egid);
+		ucred->uid = from_kuid(current_ns, cred->euid);
+		ucred->gid = from_kgid(current_ns, cred->egid);
 	}
 }
 EXPORT_SYMBOL_GPL(cred_to_ucred);

net/ipv4/ping.c

@@ -207,17 +207,22 @@ static int ping_init_sock(struct sock *sk)
 	gid_t range[2];
 	struct group_info *group_info = get_current_groups();
 	int i, j, count = group_info->ngroups;
+	kgid_t low, high;
 
 	inet_get_ping_group_range_net(net, range, range+1);
+	low = make_kgid(&init_user_ns, range[0]);
+	high = make_kgid(&init_user_ns, range[1]);
+	if (!gid_valid(low) || !gid_valid(high) || gid_lt(high, low))
+		return -EACCES;
+
 	if (range[0] <= group && group <= range[1])
 		return 0;
 
 	for (i = 0; i < group_info->nblocks; i++) {
 		int cp_count = min_t(int, NGROUPS_PER_BLOCK, count);
-
 		for (j = 0; j < cp_count; j++) {
-			group = group_info->blocks[i][j];
-			if (range[0] <= group && group <= range[1])
+			kgid_t gid = group_info->blocks[i][j];
+			if (gid_lte(low, gid) && gid_lte(gid, high))
 				return 0;
 		}
 

net/sunrpc/auth_generic.c

@@ -160,8 +160,8 @@ generic_match(struct auth_cred *acred, struct rpc_cred *cred, int flags)
 	if (gcred->acred.group_info->ngroups != acred->group_info->ngroups)
 		goto out_nomatch;
 	for (i = 0; i < gcred->acred.group_info->ngroups; i++) {
-		if (GROUP_AT(gcred->acred.group_info, i) !=
-				GROUP_AT(acred->group_info, i))
+		if (!gid_eq(GROUP_AT(gcred->acred.group_info, i),
+				GROUP_AT(acred->group_info, i)))
 			goto out_nomatch;
 	}
 out_match:

net/sunrpc/auth_gss/svcauth_gss.c

@@ -41,6 +41,7 @@
 #include <linux/types.h>
 #include <linux/module.h>
 #include <linux/pagemap.h>
+#include <linux/user_namespace.h>
 
 #include <linux/sunrpc/auth_gss.h>
 #include <linux/sunrpc/gss_err.h>
@@ -470,9 +471,13 @@ static int rsc_parse(struct cache_detail *cd,
 		status = -EINVAL;
 		for (i=0; i<N; i++) {
 			gid_t gid;
+			kgid_t kgid;
 			if (get_int(&mesg, &gid))
 				goto out;
-			GROUP_AT(rsci.cred.cr_group_info, i) = gid;
+			kgid = make_kgid(&init_user_ns, gid);
+			if (!gid_valid(kgid))
+				goto out;
+			GROUP_AT(rsci.cred.cr_group_info, i) = kgid;
 		}
 
 		/* mech name */

net/sunrpc/auth_unix.c

@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/auth.h>
+#include <linux/user_namespace.h>
 
 #define NFS_NGROUPS	16
 
@@ -78,8 +79,11 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 		groups = NFS_NGROUPS;
 
 	cred->uc_gid = acred->gid;
-	for (i = 0; i < groups; i++)
-		cred->uc_gids[i] = GROUP_AT(acred->group_info, i);
+	for (i = 0; i < groups; i++) {
+		gid_t gid;
+		gid = from_kgid(&init_user_ns, GROUP_AT(acred->group_info, i));
+		cred->uc_gids[i] = gid;
+	}
 	if (i < NFS_NGROUPS)
 		cred->uc_gids[i] = NOGROUP;
 
@@ -126,9 +130,12 @@ unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags)
 		groups = acred->group_info->ngroups;
 	if (groups > NFS_NGROUPS)
 		groups = NFS_NGROUPS;
-	for (i = 0; i < groups ; i++)
-		if (cred->uc_gids[i] != GROUP_AT(acred->group_info, i))
+	for (i = 0; i < groups ; i++) {
+		gid_t gid;
+		gid = from_kgid(&init_user_ns, GROUP_AT(acred->group_info, i));
+		if (cred->uc_gids[i] != gid)
 			return 0;
+	}
 	if (groups < NFS_NGROUPS &&
 	    cred->uc_gids[groups] != NOGROUP)
 		return 0;

net/sunrpc/svcauth_unix.c

@@ -14,6 +14,7 @@
 #include <net/sock.h>
 #include <net/ipv6.h>
 #include <linux/kernel.h>
+#include <linux/user_namespace.h>
 #define RPCDBG_FACILITY	RPCDBG_AUTH
 
 #include <linux/sunrpc/clnt.h>
@@ -530,11 +531,15 @@ static int unix_gid_parse(struct cache_detail *cd,
 
 	for (i = 0 ; i < gids ; i++) {
 		int gid;
+		kgid_t kgid;
 		rv = get_int(&mesg, &gid);
 		err = -EINVAL;
 		if (rv)
 			goto out;
-		GROUP_AT(ug.gi, i) = gid;
+		kgid = make_kgid(&init_user_ns, gid);
+		if (!gid_valid(kgid))
+			goto out;
+		GROUP_AT(ug.gi, i) = kgid;
 	}
 
 	ugp = unix_gid_lookup(cd, uid);
@@ -563,6 +568,7 @@ static int unix_gid_show(struct seq_file *m,
 			 struct cache_detail *cd,
 			 struct cache_head *h)
 {
+	struct user_namespace *user_ns = current_user_ns();
 	struct unix_gid *ug;
 	int i;
 	int glen;
@@ -580,7 +586,7 @@ static int unix_gid_show(struct seq_file *m,
 
 	seq_printf(m, "%u %d:", ug->uid, glen);
 	for (i = 0; i < glen; i++)
-		seq_printf(m, " %d", GROUP_AT(ug->gi, i));
+		seq_printf(m, " %d", from_kgid_munged(user_ns, GROUP_AT(ug->gi, i)));
 	seq_printf(m, "\n");
 	return 0;
 }
@@ -831,8 +837,12 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp)
 	cred->cr_group_info = groups_alloc(slen);
 	if (cred->cr_group_info == NULL)
 		return SVC_CLOSE;
-	for (i = 0; i < slen; i++)
-		GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv);
+	for (i = 0; i < slen; i++) {
+		kgid_t kgid = make_kgid(&init_user_ns, svc_getnl(argv));
+		if (!gid_valid(kgid))
+			goto badcred;
+		GROUP_AT(cred->cr_group_info, i) = kgid;
+	}
 	if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) {
 		*authp = rpc_autherr_badverf;
 		return SVC_DENIED;

security/commoncap.c

@@ -77,12 +77,12 @@ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns,
 		int cap, int audit)
 {
 	for (;;) {
-		/* The creator of the user namespace has all caps. */
-		if (targ_ns != &init_user_ns && targ_ns->creator == cred->user)
+		/* The owner of the user namespace has all caps. */
+		if (targ_ns != &init_user_ns && uid_eq(targ_ns->owner, cred->euid))
 			return 0;
 
 		/* Do we have the necessary capabilities? */
-		if (targ_ns == cred->user->user_ns)
+		if (targ_ns == cred->user_ns)
 			return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM;
 
 		/* Have we tried all of the parent namespaces? */
@@ -93,7 +93,7 @@ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns,
 		 *If you have a capability in a parent user ns, then you have
 		 * it over all children user namespaces as well.
 		 */
-		targ_ns = targ_ns->creator->user_ns;
+		targ_ns = targ_ns->parent;
 	}
 
 	/* We never get here */
@@ -137,10 +137,10 @@ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode)
 	rcu_read_lock();
 	cred = current_cred();
 	child_cred = __task_cred(child);
-	if (cred->user->user_ns == child_cred->user->user_ns &&
+	if (cred->user_ns == child_cred->user_ns &&
 	    cap_issubset(child_cred->cap_permitted, cred->cap_permitted))
 		goto out;
-	if (ns_capable(child_cred->user->user_ns, CAP_SYS_PTRACE))
+	if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE))
 		goto out;
 	ret = -EPERM;
 out:
@@ -169,10 +169,10 @@ int cap_ptrace_traceme(struct task_struct *parent)
 	rcu_read_lock();
 	cred = __task_cred(parent);
 	child_cred = current_cred();
-	if (cred->user->user_ns == child_cred->user->user_ns &&
+	if (cred->user_ns == child_cred->user_ns &&
 	    cap_issubset(child_cred->cap_permitted, cred->cap_permitted))
 		goto out;
-	if (has_ns_capability(parent, child_cred->user->user_ns, CAP_SYS_PTRACE))
+	if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE))
 		goto out;
 	ret = -EPERM;
 out:
@@ -215,7 +215,7 @@ static inline int cap_inh_is_capped(void)
 	/* they are so limited unless the current task has the CAP_SETPCAP
 	 * capability
 	 */
-	if (cap_capable(current_cred(), current_cred()->user->user_ns,
+	if (cap_capable(current_cred(), current_cred()->user_ns,
 			CAP_SETPCAP, SECURITY_CAP_AUDIT) == 0)
 		return 0;
 	return 1;
@@ -473,19 +473,22 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 	struct cred *new = bprm->cred;
 	bool effective, has_cap = false;
 	int ret;
+	kuid_t root_uid;
 
 	effective = false;
 	ret = get_file_caps(bprm, &effective, &has_cap);
 	if (ret < 0)
 		return ret;
 
+	root_uid = make_kuid(new->user_ns, 0);
+
 	if (!issecure(SECURE_NOROOT)) {
 		/*
 		 * If the legacy file capability is set, then don't set privs
 		 * for a setuid root binary run by a non-root user.  Do set it
 		 * for a root user just to cause least surprise to an admin.
 		 */
-		if (has_cap && new->uid != 0 && new->euid == 0) {
+		if (has_cap && !uid_eq(new->uid, root_uid) && uid_eq(new->euid, root_uid)) {
 			warn_setuid_and_fcaps_mixed(bprm->filename);
 			goto skip;
 		}
@@ -496,12 +499,12 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 		 *
 		 * If only the real uid is 0, we do not set the effective bit.
 		 */
-		if (new->euid == 0 || new->uid == 0) {
+		if (uid_eq(new->euid, root_uid) || uid_eq(new->uid, root_uid)) {
 			/* pP' = (cap_bset & ~0) | (pI & ~0) */
 			new->cap_permitted = cap_combine(old->cap_bset,
 							 old->cap_inheritable);
 		}
-		if (new->euid == 0)
+		if (uid_eq(new->euid, root_uid))
 			effective = true;
 	}
 skip:
@@ -516,8 +519,8 @@ skip:
 	 *
 	 * In addition, if NO_NEW_PRIVS, then ensure we get no new privs.
 	 */
-	if ((new->euid != old->uid ||
-	     new->egid != old->gid ||
+	if ((!uid_eq(new->euid, old->uid) ||
+	     !gid_eq(new->egid, old->gid) ||
 	     !cap_issubset(new->cap_permitted, old->cap_permitted)) &&
 	    bprm->unsafe & ~LSM_UNSAFE_PTRACE_CAP) {
 		/* downgrade; they get no more than they had, and maybe less */
@@ -553,7 +556,7 @@ skip:
 	 */
 	if (!cap_isclear(new->cap_effective)) {
 		if (!cap_issubset(CAP_FULL_SET, new->cap_effective) ||
-		    new->euid != 0 || new->uid != 0 ||
+		    !uid_eq(new->euid, root_uid) || !uid_eq(new->uid, root_uid) ||
 		    issecure(SECURE_NOROOT)) {
 			ret = audit_log_bprm_fcaps(bprm, new, old);
 			if (ret < 0)
@@ -578,16 +581,17 @@ skip:
 int cap_bprm_secureexec(struct linux_binprm *bprm)
 {
 	const struct cred *cred = current_cred();
+	kuid_t root_uid = make_kuid(cred->user_ns, 0);
 
-	if (cred->uid != 0) {
+	if (!uid_eq(cred->uid, root_uid)) {
 		if (bprm->cap_effective)
 			return 1;
 		if (!cap_isclear(cred->cap_permitted))
 			return 1;
 	}
 
-	return (cred->euid != cred->uid ||
-		cred->egid != cred->gid);
+	return (!uid_eq(cred->euid, cred->uid) ||
+		!gid_eq(cred->egid, cred->gid));
 }
 
 /**
@@ -677,15 +681,21 @@ int cap_inode_removexattr(struct dentry *dentry, const char *name)
  */
 static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old)
 {
-	if ((old->uid == 0 || old->euid == 0 || old->suid == 0) &&
-	    (new->uid != 0 && new->euid != 0 && new->suid != 0) &&
+	kuid_t root_uid = make_kuid(old->user_ns, 0);
+
+	if ((uid_eq(old->uid, root_uid) ||
+	     uid_eq(old->euid, root_uid) ||
+	     uid_eq(old->suid, root_uid)) &&
+	    (!uid_eq(new->uid, root_uid) &&
+	     !uid_eq(new->euid, root_uid) &&
+	     !uid_eq(new->suid, root_uid)) &&
 	    !issecure(SECURE_KEEP_CAPS)) {
 		cap_clear(new->cap_permitted);
 		cap_clear(new->cap_effective);
 	}
-	if (old->euid == 0 && new->euid != 0)
+	if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid))
 		cap_clear(new->cap_effective);
-	if (old->euid != 0 && new->euid == 0)
+	if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid))
 		new->cap_effective = new->cap_permitted;
 }
 
@@ -718,11 +728,12 @@ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags)
 		 *          if not, we might be a bit too harsh here.
 		 */
 		if (!issecure(SECURE_NO_SETUID_FIXUP)) {
-			if (old->fsuid == 0 && new->fsuid != 0)
+			kuid_t root_uid = make_kuid(old->user_ns, 0);
+			if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid))
 				new->cap_effective =
 					cap_drop_fs_set(new->cap_effective);
 
-			if (old->fsuid != 0 && new->fsuid == 0)
+			if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid))
 				new->cap_effective =
 					cap_raise_fs_set(new->cap_effective,
 							 new->cap_permitted);
@@ -875,7 +886,7 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 		    || ((new->securebits & SECURE_ALL_LOCKS & ~arg2))	/*[2]*/
 		    || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS))	/*[3]*/
 		    || (cap_capable(current_cred(),
-				    current_cred()->user->user_ns, CAP_SETPCAP,
+				    current_cred()->user_ns, CAP_SETPCAP,
 				    SECURITY_CAP_AUDIT) != 0)		/*[4]*/
 			/*
 			 * [1] no changing of bits that are locked

security/keys/key.c

@@ -253,7 +253,7 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 	quotalen = desclen + type->def_datalen;
 
 	/* get hold of the key tracking for this user */
-	user = key_user_lookup(uid, cred->user->user_ns);
+	user = key_user_lookup(uid, cred->user_ns);
 	if (!user)
 		goto no_memory_1;
 

security/keys/permission.c

@@ -36,7 +36,7 @@ int key_task_permission(const key_ref_t key_ref, const struct cred *cred,
 
 	key = key_ref_to_ptr(key_ref);
 
-	if (key->user->user_ns != cred->user->user_ns)
+	if (key->user->user_ns != cred->user_ns)
 		goto use_other_perms;
 
 	/* use the second 8-bits of permissions for keys the caller owns */
@@ -53,7 +53,8 @@ int key_task_permission(const key_ref_t key_ref, const struct cred *cred,
 			goto use_these_perms;
 		}
 
-		ret = groups_search(cred->group_info, key->gid);
+		ret = groups_search(cred->group_info,
+				    make_kgid(current_user_ns(), key->gid));
 		if (ret) {
 			kperm = key->perm >> 8;
 			goto use_these_perms;

security/keys/process_keys.c

@@ -860,7 +860,7 @@ void key_replace_session_keyring(void)
 	new-> sgid	= old-> sgid;
 	new->fsgid	= old->fsgid;
 	new->user	= get_uid(old->user);
-	new->user_ns	= new->user->user_ns;
+	new->user_ns	= get_user_ns(new->user_ns);
 	new->group_info	= get_group_info(old->group_info);
 
 	new->securebits	= old->securebits;