userns: user namespaces: convert several capable() calls

CAP_IPC_OWNER and CAP_IPC_LOCK can be checked against current_user_ns(),
because the resource comes from current's own ipc namespace.

setuid/setgid are to uids in own namespace, so again checks can be against
current_user_ns().

Changelog:
	Jan 11: Use task_ns_capable() in place of sched_capable().
	Jan 11: Use nsown_capable() as suggested by Bastian Blank.
	Jan 11: Clarify (hopefully) some logic in futex and sched.c
	Feb 15: use ns_capable for ipc, not nsown_capable
	Feb 23: let copy_ipcs handle setting ipc_ns->user_ns
	Feb 23: pass ns down rather than taking it from current

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Daniel Lezcano <daniel.lezcano@free.fr>
Acked-by: David Howells <dhowells@redhat.com>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

13 files changed, 75 insertions, 45 deletions

diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index d3c32dcec623..a6d1655f9607 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -5,6 +5,7 @@
 #include <linux/idr.h>
 #include <linux/rwsem.h>
 #include <linux/notifier.h>
+#include <linux/nsproxy.h>
 
 /*
  * ipc namespace events
@@ -93,7 +94,7 @@ static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; }
 
 #if defined(CONFIG_IPC_NS)
 extern struct ipc_namespace *copy_ipcs(unsigned long flags,
-                                       struct ipc_namespace *ns);
+                                       struct task_struct *tsk);
 static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 {
         if (ns)
@@ -104,12 +105,12 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 extern void put_ipc_ns(struct ipc_namespace *ns);
 #else
 static inline struct ipc_namespace *copy_ipcs(unsigned long flags,
-                struct ipc_namespace *ns)
+                                              struct task_struct *tsk)
 {
         if (flags & CLONE_NEWIPC)
                 return ERR_PTR(-EINVAL);
 
-        return ns;
+        return tsk->nsproxy->ipc_ns;
 }
 
 static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
diff --git a/ipc/msg.c b/ipc/msg.c
index 747b65507a91..0e732e92e22f 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -421,7 +421,7 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
                         return -EFAULT;
         }
 
-        ipcp = ipcctl_pre_down(&msg_ids(ns), msqid, cmd,
+        ipcp = ipcctl_pre_down(ns, &msg_ids(ns), msqid, cmd,
                                &msqid64.msg_perm, msqid64.msg_qbytes);
         if (IS_ERR(ipcp))
                 return PTR_ERR(ipcp);
@@ -539,7 +539,7 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
                         success_return = 0;
                 }
                 err = -EACCES;
-                if (ipcperms(&msq->q_perm, S_IRUGO))
+                if (ipcperms(ns, &msq->q_perm, S_IRUGO))
                         goto out_unlock;
 
                 err = security_msg_queue_msgctl(msq, cmd);
@@ -664,7 +664,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
                 struct msg_sender s;
 
                 err = -EACCES;
-                if (ipcperms(&msq->q_perm, S_IWUGO))
+                if (ipcperms(ns, &msq->q_perm, S_IWUGO))
                         goto out_unlock_free;
 
                 err = security_msg_queue_msgsnd(msq, msg, msgflg);
@@ -774,7 +774,7 @@ long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
                 struct list_head *tmp;
 
                 msg = ERR_PTR(-EACCES);
-                if (ipcperms(&msq->q_perm, S_IRUGO))
+                if (ipcperms(ns, &msq->q_perm, S_IRUGO))
                         goto out_unlock;
 
                 msg = ERR_PTR(-EAGAIN);
diff --git a/ipc/namespace.c b/ipc/namespace.c
index aa1889962693..3c3e5223e7e5 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -15,7 +15,8 @@
 
 #include "util.h"
 
-static struct ipc_namespace *create_ipc_ns(struct ipc_namespace *old_ns)
+static struct ipc_namespace *create_ipc_ns(struct task_struct *tsk,
+                                           struct ipc_namespace *old_ns)
 {
         struct ipc_namespace *ns;
         int err;
@@ -44,17 +45,19 @@ static struct ipc_namespace *create_ipc_ns(struct ipc_namespace *old_ns)
         ipcns_notify(IPCNS_CREATED);
         register_ipcns_notifier(ns);
 
-        ns->user_ns = old_ns->user_ns;
-        get_user_ns(ns->user_ns);
+        ns->user_ns = get_user_ns(task_cred_xxx(tsk, user)->user_ns);
 
         return ns;
 }
 
-struct ipc_namespace *copy_ipcs(unsigned long flags, struct ipc_namespace *ns)
+struct ipc_namespace *copy_ipcs(unsigned long flags,
+                                struct task_struct *tsk)
 {
+        struct ipc_namespace *ns = tsk->nsproxy->ipc_ns;
+
         if (!(flags & CLONE_NEWIPC))
                 return get_ipc_ns(ns);
-        return create_ipc_ns(ns);
+        return create_ipc_ns(tsk, ns);
 }
 
 /*
diff --git a/ipc/sem.c b/ipc/sem.c
index 0e0d49bbb867..ae040a0727c2 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -817,7 +817,7 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid,
                 }
 
                 err = -EACCES;
-                if (ipcperms (&sma->sem_perm, S_IRUGO))
+                if (ipcperms(ns, &sma->sem_perm, S_IRUGO))
                         goto out_unlock;
 
                 err = security_sem_semctl(sma, cmd);
@@ -862,7 +862,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
         nsems = sma->sem_nsems;
 
         err = -EACCES;
-        if (ipcperms (&sma->sem_perm, (cmd==SETVAL||cmd==SETALL)?S_IWUGO:S_IRUGO))
+        if (ipcperms(ns, &sma->sem_perm,
+                        (cmd == SETVAL || cmd == SETALL) ? S_IWUGO : S_IRUGO))
                 goto out_unlock;
 
         err = security_sem_semctl(sma, cmd);
@@ -1047,7 +1048,8 @@ static int semctl_down(struct ipc_namespace *ns, int semid,
                         return -EFAULT;
         }
 
-        ipcp = ipcctl_pre_down(&sem_ids(ns), semid, cmd, &semid64.sem_perm, 0);
+        ipcp = ipcctl_pre_down(ns, &sem_ids(ns), semid, cmd,
+                               &semid64.sem_perm, 0);
         if (IS_ERR(ipcp))
                 return PTR_ERR(ipcp);
 
@@ -1386,7 +1388,7 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
                 goto out_unlock_free;
 
         error = -EACCES;
-        if (ipcperms(&sma->sem_perm, alter ? S_IWUGO : S_IRUGO))
+        if (ipcperms(ns, &sma->sem_perm, alter ? S_IWUGO : S_IRUGO))
                 goto out_unlock_free;
 
         error = security_sem_semop(sma, sops, nsops, alter);
diff --git a/ipc/shm.c b/ipc/shm.c
index 7d3bb22a9302..8644452f5c4c 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -623,7 +623,8 @@ static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
                         return -EFAULT;
         }
 
-        ipcp = ipcctl_pre_down(&shm_ids(ns), shmid, cmd, &shmid64.shm_perm, 0);
+        ipcp = ipcctl_pre_down(ns, &shm_ids(ns), shmid, cmd,
+                               &shmid64.shm_perm, 0);
         if (IS_ERR(ipcp))
                 return PTR_ERR(ipcp);
 
@@ -737,7 +738,7 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
                         result = 0;
                 }
                 err = -EACCES;
-                if (ipcperms (&shp->shm_perm, S_IRUGO))
+                if (ipcperms(ns, &shp->shm_perm, S_IRUGO))
                         goto out_unlock;
                 err = security_shm_shmctl(shp, cmd);
                 if (err)
@@ -773,7 +774,7 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
 
                 audit_ipc_obj(&(shp->shm_perm));
 
-                if (!capable(CAP_IPC_LOCK)) {
+                if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) {
                         uid_t euid = current_euid();
                         err = -EPERM;
                         if (euid != shp->shm_perm.uid &&
@@ -888,7 +889,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr)
         }
 
         err = -EACCES;
-        if (ipcperms(&shp->shm_perm, acc_mode))
+        if (ipcperms(ns, &shp->shm_perm, acc_mode))
                 goto out_unlock;
 
         err = security_shm_shmat(shp, shmaddr, shmflg);
diff --git a/ipc/util.c b/ipc/util.c
index 69a0cc13d966..8fd1b891ec0c 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -329,12 +329,14 @@ retry:
  *
  *      It is called with ipc_ids.rw_mutex and ipcp->lock held.
  */
-static int ipc_check_perms(struct kern_ipc_perm *ipcp, struct ipc_ops *ops,
-                        struct ipc_params *params)
+static int ipc_check_perms(struct ipc_namespace *ns,
+                           struct kern_ipc_perm *ipcp,
+                           struct ipc_ops *ops,
+                           struct ipc_params *params)
 {
         int err;
 
-        if (ipcperms(ipcp, params->flg))
+        if (ipcperms(ns, ipcp, params->flg))
                 err = -EACCES;
         else {
                 err = ops->associate(ipcp, params->flg);
@@ -396,7 +398,7 @@ retry:
                                  * ipc_check_perms returns the IPC id on
                                  * success
                                  */
-                                err = ipc_check_perms(ipcp, ops, params);
+                                err = ipc_check_perms(ns, ipcp, ops, params);
                 }
                 ipc_unlock(ipcp);
         }
@@ -610,10 +612,12 @@ void ipc_rcu_putref(void *ptr)
  *
  *      Check user, group, other permissions for access
  *      to ipc resources. return 0 if allowed
+ *
+ *      @flag will most probably be 0 or S_...UGO from <linux/stat.h>
  */
  
-int ipcperms (struct kern_ipc_perm *ipcp, short flag)
-{       /* flag will most probably be 0 or S_...UGO from <linux/stat.h> */
+int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flag)
+{
         uid_t euid = current_euid();
         int requested_mode, granted_mode;
 
@@ -627,7 +631,7 @@ int ipcperms (struct kern_ipc_perm *ipcp, short flag)
                 granted_mode >>= 3;
         /* is there some bit set in requested_mode but not in granted_mode? */
         if ((requested_mode & ~granted_mode & 0007) && 
-            !capable(CAP_IPC_OWNER))
+            !ns_capable(ns->user_ns, CAP_IPC_OWNER))
                 return -1;
 
         return security_ipc_permission(ipcp, flag);
@@ -765,6 +769,7 @@ void ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
 
 /**
  * ipcctl_pre_down - retrieve an ipc and check permissions for some IPC_XXX cmd
+ * @ids:  the ipc namespace
  * @ids:  the table of ids where to look for the ipc
  * @id:   the id of the ipc to retrieve
  * @cmd:  the cmd to check
@@ -779,7 +784,8 @@ void ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
  *  - returns the ipc with both ipc and rw_mutex locks held in case of success
  *    or an err-code without any lock held otherwise.
  */
-struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd,
+struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
+                                      struct ipc_ids *ids, int id, int cmd,
                                       struct ipc64_perm *perm, int extra_perm)
 {
         struct kern_ipc_perm *ipcp;
@@ -799,8 +805,8 @@ struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd,
                                          perm->gid, perm->mode);
 
         euid = current_euid();
-        if (euid == ipcp->cuid ||
-            euid == ipcp->uid  || capable(CAP_SYS_ADMIN))
+        if (euid == ipcp->cuid || euid == ipcp->uid  ||
+            ns_capable(ns->user_ns, CAP_SYS_ADMIN))
                 return ipcp;
 
         err = -EPERM;
diff --git a/ipc/util.h b/ipc/util.h
index 764b51a37a6a..6f5c20bedaab 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -103,7 +103,7 @@ int ipc_get_maxid(struct ipc_ids *);
 void ipc_rmid(struct ipc_ids *, struct kern_ipc_perm *);
 
 /* must be called with ipcp locked */
-int ipcperms(struct kern_ipc_perm *ipcp, short flg);
+int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flg);
 
 /* for rare, potentially huge allocations.
  * both function can sleep
@@ -126,7 +126,8 @@ struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int);
 void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out);
 void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out);
 void ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out);
-struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd,
+struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
+                                      struct ipc_ids *ids, int id, int cmd,
                                       struct ipc64_perm *perm, int extra_perm);
 
 #ifndef __ARCH_WANT_IPC_PARSE_VERSION
diff --git a/kernel/futex.c b/kernel/futex.c
index bda415715382..6570c459f31c 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2418,10 +2418,19 @@ SYSCALL_DEFINE3(get_robust_list, int, pid,
                         goto err_unlock;
                 ret = -EPERM;
                 pcred = __task_cred(p);
+                /* If victim is in different user_ns, then uids are not
+                   comparable, so we must have CAP_SYS_PTRACE */
+                if (cred->user->user_ns != pcred->user->user_ns) {
+                        if (!ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
+                                goto err_unlock;
+                        goto ok;
+                }
+                /* If victim is in same user_ns, then uids are comparable */
                 if (cred->euid != pcred->euid &&
                     cred->euid != pcred->uid &&
-                    !capable(CAP_SYS_PTRACE))
+                    !ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
                         goto err_unlock;
+ok:
                 head = p->robust_list;
                 rcu_read_unlock();
         }
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index a7934ac75e5b..5f9e689dc8f0 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -153,10 +153,19 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
                         goto err_unlock;
                 ret = -EPERM;
                 pcred = __task_cred(p);
+                /* If victim is in different user_ns, then uids are not
+                   comparable, so we must have CAP_SYS_PTRACE */
+                if (cred->user->user_ns != pcred->user->user_ns) {
+                        if (!ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
+                                goto err_unlock;
+                        goto ok;
+                }
+                /* If victim is in same user_ns, then uids are comparable */
                 if (cred->euid != pcred->euid &&
                     cred->euid != pcred->uid &&
-                    !capable(CAP_SYS_PTRACE))
+                    !ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
                         goto err_unlock;
+ok:
                 head = p->compat_robust_list;
                 rcu_read_unlock();
         }
diff --git a/kernel/groups.c b/kernel/groups.c
index 253dc0f35cf4..1cc476d52dd3 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -233,7 +233,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
         struct group_info *group_info;
         int retval;
 
-        if (!capable(CAP_SETGID))
+        if (!nsown_capable(CAP_SETGID))
                 return -EPERM;
         if ((unsigned)gidsetsize > NGROUPS_MAX)
                 return -EINVAL;
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index ac8a56e90bf8..a05d191ffdd9 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -75,16 +75,11 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
                 goto out_uts;
         }
 
-        new_nsp->ipc_ns = copy_ipcs(flags, tsk->nsproxy->ipc_ns);
+        new_nsp->ipc_ns = copy_ipcs(flags, tsk);
         if (IS_ERR(new_nsp->ipc_ns)) {
                 err = PTR_ERR(new_nsp->ipc_ns);
                 goto out_ipc;
         }
-        if (new_nsp->ipc_ns != tsk->nsproxy->ipc_ns) {
-                put_user_ns(new_nsp->ipc_ns->user_ns);
-                new_nsp->ipc_ns->user_ns = task_cred_xxx(tsk, user)->user_ns;
-                get_user_ns(new_nsp->ipc_ns->user_ns);
-        }
 
         new_nsp->pid_ns = copy_pid_ns(flags, task_active_pid_ns(tsk));
         if (IS_ERR(new_nsp->pid_ns)) {
diff --git a/kernel/sched.c b/kernel/sched.c
index a172494a9a63..480adeb63f8f 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4892,8 +4892,11 @@ static bool check_same_owner(struct task_struct *p)
 
         rcu_read_lock();
         pcred = __task_cred(p);
-        match = (cred->euid == pcred->euid ||
-                 cred->euid == pcred->uid);
+        if (cred->user->user_ns == pcred->user->user_ns)
+                match = (cred->euid == pcred->euid ||
+                         cred->euid == pcred->uid);
+        else
+                match = false;
         rcu_read_unlock();
         return match;
 }
@@ -5221,7 +5224,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
                 goto out_free_cpus_allowed;
         }
         retval = -EPERM;
-        if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
+        if (!check_same_owner(p) && !task_ns_capable(p, CAP_SYS_NICE))
                 goto out_unlock;
 
         retval = security_task_setscheduler(p);
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 419209893d87..51c6e89e8619 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -189,7 +189,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
         struct group_info *group_info;
         int retval;
 
-        if (!capable(CAP_SETGID))
+        if (!nsown_capable(CAP_SETGID))
                 return -EPERM;
         if ((unsigned)gidsetsize > NGROUPS_MAX)
                 return -EINVAL;