rlimit: permit setting RLIMIT_NOFILE to RLIM_INFINITY

When a process wants to set the limit of open files to RLIM_INFINITY it
gets EPERM even if it has CAP_SYS_RESOURCE capability.

For example, BIND does:

...
#elif defined(NR_OPEN) && defined(__linux__)
        /*
         * Some Linux kernels don't accept RLIM_INFINIT; the maximum
         * possible value is the NR_OPEN defined in linux/fs.h.
         */
        if (resource == isc_resource_openfiles && rlim_value == RLIM_INFINITY) {
                rl.rlim_cur = rl.rlim_max = NR_OPEN;
                unixresult = setrlimit(unixresource, &rl);
                if (unixresult == 0)
                        return (ISC_R_SUCCESS);
        }
#elif ...

If we allow setting RLIMIT_NOFILE to RLIM_INFINITY we increase portability
- you don't have to check if OS is linux and then use different schema for
limits.

The spec says "Specifying RLIM_INFINITY as any resource limit value on a
successful call to setrlimit() shall inhibit enforcement of that resource
limit." and we're presently not doing that.

Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/kernel/sys.c b/kernel/sys.c
index 234d945..d5b79f6 100644 (file)
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1450,14 +1450,22 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
                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;
+
+       if (resource == RLIMIT_NOFILE) {
+               if (new_rlim.rlim_max == RLIM_INFINITY)
+                       new_rlim.rlim_max = sysctl_nr_open;
+               if (new_rlim.rlim_cur == RLIM_INFINITY)
+                       new_rlim.rlim_cur = sysctl_nr_open;
+               if (new_rlim.rlim_max > sysctl_nr_open)
+                       return -EPERM;
+       }
+
+       if (new_rlim.rlim_cur > new_rlim.rlim_max)
+               return -EINVAL;
 
        retval = security_task_setrlimit(resource, &new_rlim);
        if (retval)