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
  ...

85 files changed, 1787 insertions, 605 deletions

diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index af0aaebf4de6..3e94811690ce 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/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;
diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c
index 0dc8543acb4f..c71eb6c79897 100644
--- a/arch/parisc/hpux/fs.c
+++ b/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;
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index ab64bdbab2ae..65426525d9f2 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/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;
diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index 29c478ffed91..f7392336961f 100644
--- a/arch/sparc/kernel/sys_sparc32.c
+++ b/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);
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index edca9c0a79cc..4540bece0946 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/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) ||
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 3ecfd1aaf214..76dcd9d8e0bc 100644
--- a/arch/x86/mm/fault.c
+++ b/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 ");
diff --git a/fs/attr.c b/fs/attr.c
index 73f69a6ce9ed..584620e5dee5 100644
--- a/fs/attr.c
+++ b/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;
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 16f735417072..e658dd134b95 100644
--- a/fs/binfmt_elf.c
+++ b/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));
 	
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index d390a0fffc65..3d77cf81ba3c 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/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));
 
diff --git a/fs/compat.c b/fs/compat.c
index f2944ace7a7b..0781e619a62a 100644
--- a/fs/compat.c
+++ b/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;
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 10f5e0b484db..979c1e309c73 100644
--- a/fs/devpts/inode.c
+++ b/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);
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index ab2248090515..a750f957b145 100644
--- a/fs/ecryptfs/messaging.c
+++ b/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();
diff --git a/fs/exec.c b/fs/exec.c
index 1e8efdc80412..52c9e2ff6e6b 100644
--- a/fs/exec.c
+++ b/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())) {</