1 files changed, 161 insertions, 78 deletions

diff --git a/kernel/sys.c b/kernel/sys.c
index 7cb426a58965..e9ad44489828 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -492,10 +492,6 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
                 return -ENOMEM;
         old = current_cred();
 
-        retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE);
-        if (retval)
-                goto error;
-
         retval = -EPERM;
         if (rgid != (gid_t) -1) {
                 if (old->gid == rgid ||
@@ -543,10 +539,6 @@ SYSCALL_DEFINE1(setgid, gid_t, gid)
                 return -ENOMEM;
         old = current_cred();
 
-        retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID);
-        if (retval)
-                goto error;
-
         retval = -EPERM;
         if (capable(CAP_SETGID))
                 new->gid = new->egid = new->sgid = new->fsgid = gid;
@@ -610,10 +602,6 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
                 return -ENOMEM;
         old = current_cred();
 
-        retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE);
-        if (retval)
-                goto error;
-
         retval = -EPERM;
         if (ruid != (uid_t) -1) {
                 new->uid = ruid;
@@ -675,10 +663,6 @@ SYSCALL_DEFINE1(setuid, uid_t, uid)
                 return -ENOMEM;
         old = current_cred();
 
-        retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID);
-        if (retval)
-                goto error;
-
         retval = -EPERM;
         if (capable(CAP_SETUID)) {
                 new->suid = new->uid = uid;
@@ -719,9 +703,6 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
         if (!new)
                 return -ENOMEM;
 
-        retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES);
-        if (retval)
-                goto error;
         old = current_cred();
 
         retval = -EPERM;
@@ -788,10 +769,6 @@ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
                 return -ENOMEM;
         old = current_cred();
 
-        retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES);
-        if (retval)
-                goto error;
-
         retval = -EPERM;
         if (!capable(CAP_SETGID)) {
                 if (rgid != (gid_t) -1 && rgid != old->gid &&
@@ -851,9 +828,6 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid)
         old = current_cred();
         old_fsuid = old->fsuid;
 
-        if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS) < 0)
-                goto error;
-
         if (uid == old->uid  || uid == old->euid  ||
             uid == old->suid || uid == old->fsuid ||
             capable(CAP_SETUID)) {
@@ -864,7 +838,6 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid)
                 }
         }
 
-error:
         abort_creds(new);
         return old_fsuid;
 
@@ -888,9 +861,6 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid)
         old = current_cred();
         old_fsgid = old->fsgid;
 
-        if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS))
-                goto error;
-
         if (gid == old->gid  || gid == old->egid  ||
             gid == old->sgid || gid == old->fsgid ||
             capable(CAP_SETGID)) {
@@ -900,7 +870,6 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid)
                 }
         }
 
-error:
         abort_creds(new);
         return old_fsgid;
 
@@ -1267,15 +1236,14 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
 
 SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim)
 {
-        if (resource >= RLIM_NLIMITS)
-                return -EINVAL;
-        else {
-                struct rlimit value;
-                task_lock(current->group_leader);
-                value = current->signal->rlim[resource];
-                task_unlock(current->group_leader);
-                return copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
-        }
+        struct rlimit value;
+        int ret;
+
+        ret = do_prlimit(current, resource, NULL, &value);
+        if (!ret)
+                ret = copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
+
+        return ret;
 }
 
 #ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT
@@ -1303,44 +1271,89 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
 
 #endif
 
-SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
+static inline bool rlim64_is_infinity(__u64 rlim64)
 {
-        struct rlimit new_rlim, *old_rlim;
-        int retval;
+#if BITS_PER_LONG < 64
+        return rlim64 >= ULONG_MAX;
+#else
+        return rlim64 == RLIM64_INFINITY;
+#endif
+}
+
+static void rlim_to_rlim64(const struct rlimit *rlim, struct rlimit64 *rlim64)
+{
+        if (rlim->rlim_cur == RLIM_INFINITY)
+                rlim64->rlim_cur = RLIM64_INFINITY;
+        else
+                rlim64->rlim_cur = rlim->rlim_cur;
+        if (rlim->rlim_max == RLIM_INFINITY)
+                rlim64->rlim_max = RLIM64_INFINITY;
+        else
+                rlim64->rlim_max = rlim->rlim_max;
+}
+
+static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim)
+{
+        if (rlim64_is_infinity(rlim64->rlim_cur))
+                rlim->rlim_cur = RLIM_INFINITY;
+        else
+                rlim->rlim_cur = (unsigned long)rlim64->rlim_cur;
+        if (rlim64_is_infinity(rlim64->rlim_max))
+                rlim->rlim_max = RLIM_INFINITY;
+        else
+                rlim->rlim_max = (unsigned long)rlim64->rlim_max;
+}
+
+/* make sure you are allowed to change @tsk limits before calling this */
+int do_prlimit(struct task_struct *tsk, unsigned int resource,
+                struct rlimit *new_rlim, struct rlimit *old_rlim)
+{
+        struct rlimit *rlim;
+        int retval = 0;
 
         if (resource >= RLIM_NLIMITS)
                 return -EINVAL;
-        if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
-                return -EFAULT;
-        if (new_rlim.rlim_cur > new_rlim.rlim_max)
-                return -EINVAL;
-        old_rlim = current->signal->rlim + resource;
-        if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
-            !capable(CAP_SYS_RESOURCE))
-                return -EPERM;
-        if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
-                return -EPERM;
-
-        retval = security_task_setrlimit(resource, &new_rlim);
-        if (retval)
-                return retval;
-
-        if (resource == RLIMIT_CPU && new_rlim.rlim_cur == 0) {
-                /*
-                 * The caller is asking for an immediate RLIMIT_CPU
-                 * expiry.  But we use the zero value to mean "it was
-                 * never set".  So let's cheat and make it one second
-                 * instead
-                 */
-                new_rlim.rlim_cur = 1;
+        if (new_rlim) {
+                if (new_rlim->rlim_cur > new_rlim->rlim_max)
+                        return -EINVAL;
+                if (resource == RLIMIT_NOFILE &&
+                                new_rlim->rlim_max > sysctl_nr_open)
+                        return -EPERM;
         }
 
-        task_lock(current->group_leader);
-        *old_rlim = new_rlim;
-        task_unlock(current->group_leader);
-
-        if (resource != RLIMIT_CPU)
+        /* protect tsk->signal and tsk->sighand from disappearing */
+        read_lock(&tasklist_lock);
+        if (!tsk->sighand) {
+                retval = -ESRCH;
                 goto out;
+        }
+
+        rlim = tsk->signal->rlim + resource;
+        task_lock(tsk->group_leader);
+        if (new_rlim) {
+                if (new_rlim->rlim_max > rlim->rlim_max &&
+                                !capable(CAP_SYS_RESOURCE))
+                        retval = -EPERM;
+                if (!retval)
+                        retval = security_task_setrlimit(tsk->group_leader,
+                                        resource, new_rlim);
+                if (resource == RLIMIT_CPU && new_rlim->rlim_cur == 0) {
+                        /*
+                         * The caller is asking for an immediate RLIMIT_CPU
+                         * expiry.  But we use the zero value to mean "it was
+                         * never set".  So let's cheat and make it one second
+                         * instead
+                         */
+                        new_rlim->rlim_cur = 1;
+                }
+        }
+        if (!retval) {
+                if (old_rlim)
+                        *old_rlim = *rlim;
+                if (new_rlim)
+                        *rlim = *new_rlim;
+        }
+        task_unlock(tsk->group_leader);
 
         /*
          * RLIMIT_CPU handling.   Note that the kernel fails to return an error
@@ -1348,14 +1361,84 @@ SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
          * very long-standing error, and fixing it now risks breakage of
          * applications, so we live with it
          */
-        if (new_rlim.rlim_cur == RLIM_INFINITY)
-                goto out;
-
-        update_rlimit_cpu(new_rlim.rlim_cur);
+         if (!retval && new_rlim && resource == RLIMIT_CPU &&
+                         new_rlim->rlim_cur != RLIM_INFINITY)
+                update_rlimit_cpu(tsk, new_rlim->rlim_cur);
 out:
+        read_unlock(&tasklist_lock);
+        return retval;
+}
+
+/* rcu lock must be held */
+static int check_prlimit_permission(struct task_struct *task)
+{
+        const struct cred *cred = current_cred(), *tcred;
+
+        tcred = __task_cred(task);
+        if ((cred->uid != tcred->euid ||
+             cred->uid != tcred->suid ||
+             cred->uid != tcred->uid  ||
+             cred->gid != tcred->egid ||
+             cred->gid != tcred->sgid ||
+             cred->gid != tcred->gid) &&
+             !capable(CAP_SYS_RESOURCE)) {
+                return -EPERM;
+        }
+
         return 0;
 }
 
+SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource,
+                const struct rlimit64 __user *, new_rlim,
+                struct rlimit64 __user *, old_rlim)
+{
+        struct rlimit64 old64, new64;
+        struct rlimit old, new;
+        struct task_struct *tsk;
+        int ret;
+
+        if (new_rlim) {
+                if (copy_from_user(&new64, new_rlim, sizeof(new64)))
+                        return -EFAULT;
+                rlim64_to_rlim(&new64, &new);
+        }
+
+        rcu_read_lock();
+        tsk = pid ? find_task_by_vpid(pid) : current;
+        if (!tsk) {
+                rcu_read_unlock();
+                return -ESRCH;
+        }
+        ret = check_prlimit_permission(tsk);
+        if (ret) {
+                rcu_read_unlock();
+                return ret;
+        }
+        get_task_struct(tsk);
+        rcu_read_unlock();
+
+        ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL,
+                        old_rlim ? &old : NULL);
+
+        if (!ret && old_rlim) {
+                rlim_to_rlim64(&old, &old64);
+                if (copy_to_user(old_rlim, &old64, sizeof(old64)))
+                        ret = -EFAULT;
+        }
+
+        put_task_struct(tsk);
+        return ret;
+}
+
+SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
+{
+        struct rlimit new_rlim;
+
+        if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
+                return -EFAULT;
+        return do_prlimit(current, resource, &new_rlim, NULL);
+}
+
 /*
  * It would make sense to put struct rusage in the task_struct,
  * except that would make the task_struct be *really big*.  After
@@ -1663,9 +1746,9 @@ SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
 
 char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
 
-static void argv_cleanup(char **argv, char **envp)
+static void argv_cleanup(struct subprocess_info *info)
 {
-        argv_free(argv);
+        argv_free(info->argv);
 }
 
 /**
@@ -1699,7 +1782,7 @@ int orderly_poweroff(bool force)
                 goto out;
         }
 
-        call_usermodehelper_setcleanup(info, argv_cleanup);
+        call_usermodehelper_setfns(info, NULL, argv_cleanup, NULL);
 
         ret = call_usermodehelper_exec(info, UMH_NO_WAIT);