1 files changed, 138 insertions, 73 deletions

diff --git a/security/commoncap.c b/security/commoncap.c
index 64c2ed9c901..b9d613e0ef1 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -27,6 +27,9 @@
 #include <linux/sched.h>
 #include <linux/prctl.h>
 #include <linux/securebits.h>
+#include <linux/user_namespace.h>
+#include <linux/binfmts.h>
+#include <linux/personality.h>
 
 /*
  * If a non-root user executes a setuid-root binary in
@@ -52,22 +55,13 @@ static void warn_setuid_and_fcaps_mixed(const char *fname)
 
 int cap_netlink_send(struct sock *sk, struct sk_buff *skb)
 {
-	NETLINK_CB(skb).eff_cap = current_cap();
 	return 0;
 }
 
-int cap_netlink_recv(struct sk_buff *skb, int cap)
-{
-	if (!cap_raised(NETLINK_CB(skb).eff_cap, cap))
-		return -EPERM;
-	return 0;
-}
-EXPORT_SYMBOL(cap_netlink_recv);
-
 /**
  * cap_capable - Determine whether a task has a particular effective capability
- * @tsk: The task to query
  * @cred: The credentials to use
+ * @ns:  The user namespace in which we need the capability
  * @cap: The capability to check for
  * @audit: Whether to write an audit message or not
  *
@@ -79,10 +73,39 @@ EXPORT_SYMBOL(cap_netlink_recv);
  * cap_has_capability() returns 0 when a task has a capability, but the
  * kernel's capable() and has_capability() returns 1 for this case.
  */
-int cap_capable(struct task_struct *tsk, const struct cred *cred, int cap,
-		int audit)
+int cap_capable(const struct cred *cred, struct user_namespace *targ_ns,
+		int cap, int audit)
 {
-	return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM;
+	struct user_namespace *ns = targ_ns;
+
+	/* See if cred has the capability in the target user namespace
+	 * by examining the target user namespace and all of the target
+	 * user namespace's parents.
+	 */
+	for (;;) {
+		/* Do we have the necessary capabilities? */
+		if (ns == cred->user_ns)
+			return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM;
+
+		/* Have we tried all of the parent namespaces? */
+		if (ns == &init_user_ns)
+			return -EPERM;
+
+		/* 
+		 * The owner of the user namespace in the parent of the
+		 * user namespace has all caps.
+		 */
+		if ((ns->parent == cred->user_ns) && uid_eq(ns->owner, cred->euid))
+			return 0;
+
+		/*
+		 * If you have a capability in a parent user ns, then you have
+		 * it over all children user namespaces as well.
+		 */
+		ns = ns->parent;
+	}
+
+	/* We never get here */
 }
 
 /**
@@ -93,7 +116,7 @@ int cap_capable(struct task_struct *tsk, const struct cred *cred, int cap,
  * Determine whether the current process may set the system clock and timezone
  * information, returning 0 if permission granted, -ve if denied.
  */
-int cap_settime(struct timespec *ts, struct timezone *tz)
+int cap_settime(const struct timespec *ts, const struct timezone *tz)
 {
 	if (!capable(CAP_SYS_TIME))
 		return -EPERM;
@@ -106,18 +129,30 @@ int cap_settime(struct timespec *ts, struct timezone *tz)
  * @child: The process to be accessed
  * @mode: The mode of attachment.
  *
+ * If we are in the same or an ancestor user_ns and have all the target
+ * task's capabilities, then ptrace access is allowed.
+ * If we have the ptrace capability to the target user_ns, then ptrace
+ * access is allowed.
+ * Else denied.
+ *
  * Determine whether a process may access another, returning 0 if permission
  * granted, -ve if denied.
  */
 int cap_ptrace_access_check(struct task_struct *child, unsigned int mode)
 {
 	int ret = 0;
+	const struct cred *cred, *child_cred;
 
 	rcu_read_lock();
-	if (!cap_issubset(__task_cred(child)->cap_permitted,
-			  current_cred()->cap_permitted) &&
-	    !capable(CAP_SYS_PTRACE))
-		ret = -EPERM;
+	cred = current_cred();
+	child_cred = __task_cred(child);
+	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_ns, CAP_SYS_PTRACE))
+		goto out;
+	ret = -EPERM;
+out:
 	rcu_read_unlock();
 	return ret;
 }
@@ -126,18 +161,30 @@ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode)
  * cap_ptrace_traceme - Determine whether another process may trace the current
  * @parent: The task proposed to be the tracer
  *
+ * If parent is in the same or an ancestor user_ns and has all current's
+ * capabilities, then ptrace access is allowed.
+ * If parent has the ptrace capability to current's user_ns, then ptrace
+ * access is allowed.
+ * Else denied.
+ *
  * Determine whether the nominated task is permitted to trace the current
  * process, returning 0 if permission is granted, -ve if denied.
  */
 int cap_ptrace_traceme(struct task_struct *parent)
 {
 	int ret = 0;
+	const struct cred *cred, *child_cred;
 
 	rcu_read_lock();
-	if (!cap_issubset(current_cred()->cap_permitted,
-			  __task_cred(parent)->cap_permitted) &&
-	    !has_capability(parent, CAP_SYS_PTRACE))
-		ret = -EPERM;
+	cred = __task_cred(parent);
+	child_cred = current_cred();
+	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_ns, CAP_SYS_PTRACE))
+		goto out;
+	ret = -EPERM;
+out:
 	rcu_read_unlock();
 	return ret;
 }
@@ -177,8 +224,8 @@ 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, current_cred(), CAP_SETPCAP,
-			SECURITY_CAP_AUDIT) == 0)
+	if (cap_capable(current_cred(), current_cred()->user_ns,
+			CAP_SETPCAP, SECURITY_CAP_AUDIT) == 0)
 		return 0;
 	return 1;
 }
@@ -286,7 +333,8 @@ int cap_inode_killpriv(struct dentry *dentry)
  */
 static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps,
 					  struct linux_binprm *bprm,
-					  bool *effective)
+					  bool *effective,
+					  bool *has_cap)
 {
 	struct cred *new = bprm->cred;
 	unsigned i;
@@ -295,6 +343,9 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps,
 	if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE)
 		*effective = true;
 
+	if (caps->magic_etc & VFS_CAP_REVISION_MASK)
+		*has_cap = true;
+
 	CAP_FOR_EACH_U32(i) {
 		__u32 permitted = caps->permitted.cap[i];
 		__u32 inheritable = caps->inheritable.cap[i];
@@ -378,7 +429,7 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data
  * its xattrs and, if present, apply them to the proposed credentials being
  * constructed by execve().
  */
-static int get_file_caps(struct linux_binprm *bprm, bool *effective)
+static int get_file_caps(struct linux_binprm *bprm, bool *effective, bool *has_cap)
 {
 	struct dentry *dentry;
 	int rc = 0;
@@ -389,7 +440,7 @@ static int get_file_caps(struct linux_binprm *bprm, bool *effective)
 	if (!file_caps_enabled)
 		return 0;
 
-	if (bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID)
+	if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
 		return 0;
 
 	dentry = dget(bprm->file->f_dentry);
@@ -404,7 +455,7 @@ static int get_file_caps(struct linux_binprm *bprm, bool *effective)
 		goto out;
 	}
 
-	rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective);
+	rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_cap);
 	if (rc == -EINVAL)
 		printk(KERN_NOTICE "%s: cap_from_disk returned %d for %s\n",
 		       __func__, rc, bprm->filename);
@@ -429,21 +480,24 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 {
 	const struct cred *old = current_cred();
 	struct cred *new = bprm->cred;
-	bool effective;
+	bool effective, has_cap = false;
 	int ret;
+	kuid_t root_uid;
 
 	effective = false;
-	ret = get_file_caps(bprm, &effective);
+	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 (effective && 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;
 		}
@@ -454,25 +508,33 @@ 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:
 
+	/* if we have fs caps, clear dangerous personality flags */
+	if (!cap_issubset(new->cap_permitted, old->cap_permitted))
+		bprm->per_clear |= PER_CLEAR_ON_SETID;
+
+
 	/* Don't let someone trace a set[ug]id/setpcap binary with the revised
-	 * credentials unless they have the appropriate permit
+	 * credentials unless they have the appropriate permit.
+	 *
+	 * 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 */
-		if (!capable(CAP_SETUID)) {
+		if (!capable(CAP_SETUID) ||
+		    (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) {
 			new->euid = new->uid;
 			new->egid = new->gid;
 		}
@@ -483,15 +545,10 @@ skip:
 	new->suid = new->fsuid = new->euid;
 	new->sgid = new->fsgid = new->egid;
 
-	/* For init, we want to retain the capabilities set in the initial
-	 * task.  Thus we skip the usual capability rules
-	 */
-	if (!is_global_init(current)) {
-		if (effective)
-			new->cap_effective = new->cap_permitted;
-		else
-			cap_clear(new->cap_effective);
-	}
+	if (effective)
+		new->cap_effective = new->cap_permitted;
+	else
+		cap_clear(new->cap_effective);
 	bprm->cap_effective = effective;
 
 	/*
@@ -508,7 +565,7 @@ 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)
@@ -533,16 +590,17 @@ 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));
 }
 
 /**
@@ -632,15 +690,21 @@ 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;
 }
 
@@ -673,11 +737,12 @@ 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);
@@ -703,16 +768,16 @@ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags)
  */
 static int cap_safe_nice(struct task_struct *p)
 {
-	int is_subset;
+	int is_subset, ret = 0;
 
 	rcu_read_lock();
 	is_subset = cap_issubset(__task_cred(p)->cap_permitted,
 				 current_cred()->cap_permitted);
+	if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE))
+		ret = -EPERM;
 	rcu_read_unlock();
 
-	if (!is_subset && !capable(CAP_SYS_NICE))
-		return -EPERM;
-	return 0;
+	return ret;
 }
 
 /**
@@ -759,7 +824,7 @@ int cap_task_setnice(struct task_struct *p, int nice)
  */
 static long cap_prctl_drop(struct cred *new, unsigned long cap)
 {
-	if (!capable(CAP_SETPCAP))
+	if (!ns_capable(current_user_ns(), CAP_SETPCAP))
 		return -EPERM;
 	if (!cap_valid(cap))
 		return -EINVAL;
@@ -829,7 +894,8 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 		     & (new->securebits ^ arg2))			/*[1]*/
 		    || ((new->securebits & SECURE_ALL_LOCKS & ~arg2))	/*[2]*/
 		    || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS))	/*[3]*/
-		    || (cap_capable(current, current_cred(), CAP_SETPCAP,
+		    || (cap_capable(current_cred(),
+				    current_cred()->user_ns, CAP_SETPCAP,
 				    SECURITY_CAP_AUDIT) != 0)		/*[4]*/
 			/*
 			 * [1] no changing of bits that are locked
@@ -894,34 +960,27 @@ int cap_vm_enough_memory(struct mm_struct *mm, long pages)
 {
 	int cap_sys_admin = 0;
 
-	if (cap_capable(current, current_cred(), CAP_SYS_ADMIN,
+	if (cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN,
 			SECURITY_CAP_NOAUDIT) == 0)
 		cap_sys_admin = 1;
 	return __vm_enough_memory(mm, pages, cap_sys_admin);
 }
 
 /*
- * cap_file_mmap - check if able to map given addr
- * @file: unused
- * @reqprot: unused
- * @prot: unused
- * @flags: unused
+ * cap_mmap_addr - check if able to map given addr
  * @addr: address attempting to be mapped
- * @addr_only: unused
  *
  * If the process is attempting to map memory below dac_mmap_min_addr they need
  * CAP_SYS_RAWIO.  The other parameters to this function are unused by the
  * capability security module.  Returns 0 if this mapping should be allowed
  * -EPERM if not.
  */
-int cap_file_mmap(struct file *file, unsigned long reqprot,
-		  unsigned long prot, unsigned long flags,
-		  unsigned long addr, unsigned long addr_only)
+int cap_mmap_addr(unsigned long addr)
 {
 	int ret = 0;
 
 	if (addr < dac_mmap_min_addr) {
-		ret = cap_capable(current, current_cred(), CAP_SYS_RAWIO,
+		ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO,
 				  SECURITY_CAP_AUDIT);
 		/* set PF_SUPERPRIV if it turns out we allow the low mmap */
 		if (ret == 0)
@@ -929,3 +988,9 @@ int cap_file_mmap(struct file *file, unsigned long reqprot,
 	}
 	return ret;
 }
+
+int cap_mmap_file(struct file *file, unsigned long reqprot,
+		  unsigned long prot, unsigned long flags)
+{
+	return 0;
+}