[PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Michael Stone]

Daniel Bernstein has observed [1] that security-conscious userland processes
may benefit from the ability to irrevocably remove their ability to create,
bind, connect to, or send messages except in the case of previously connected
sockets or AF_UNIX filesystem sockets. We provide this facility by implementing
support for a new prctl(PR_SET_NETWORK) flag named PR_NETWORK_OFF.

This facility is particularly attractive to security platforms like OLPC
Bitfrost [2] and to isolation programs like Rainbow [3] and Plash [4].

[1]: http://cr.yp.to/unix/disablenetwork.html
[2]: http://wiki.laptop.org/go/OLPC_Bitfrost
[3]: http://wiki.laptop.org/go/Rainbow
[4]: http://plash.beasts.org/

Signed-off-by: Michael Stone <michael@laptop.org>
---
 include/linux/prctl.h         |    7 +++++++
 include/linux/prctl_network.h |    7 +++++++
 include/linux/sched.h         |    2 ++
 kernel/Makefile               |    2 +-
 kernel/prctl_network.c        |   37 +++++++++++++++++++++++++++++++++++++
 kernel/sys.c                  |    7 +++++++
 6 files changed, 61 insertions(+), 1 deletions(-)
 create mode 100644 include/linux/prctl_network.h
 create mode 100644 kernel/prctl_network.c

diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index a3baeb2..4eb4110 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -102,4 +102,11 @@
 
 #define PR_MCE_KILL_GET 34
 
+/* Get/set process disable-network flags */
+#define PR_SET_NETWORK	35
+#define PR_GET_NETWORK	36
+# define PR_NETWORK_ON        0
+# define PR_NETWORK_OFF       1
+# define PR_NETWORK_ALL_FLAGS 1
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/linux/prctl_network.h b/include/linux/prctl_network.h
new file mode 100644
index 0000000..2db83eb
--- /dev/null
+++ b/include/linux/prctl_network.h
@@ -0,0 +1,7 @@
+#ifndef _LINUX_PRCTL_NETWORK_H
+#define _LINUX_PRCTL_NETWORK_H
+
+extern long prctl_get_network(void);
+extern long prctl_set_network(unsigned long);
+
+#endif /* _LINUX_PRCTL_NETWORK_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5c858f3..751d372 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1395,6 +1395,8 @@ struct task_struct {
 	unsigned int sessionid;
 #endif
 	seccomp_t seccomp;
+/* Flags for limiting networking via prctl(PR_SET_NETWORK). */
+  unsigned long network;
 
 /* Thread group tracking */
    	u32 parent_exec_id;
diff --git a/kernel/Makefile b/kernel/Makefile
index 864ff75..cafbff2 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -10,7 +10,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
-	    async.o
+	    async.o prctl_network.o
 obj-y += groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
diff --git a/kernel/prctl_network.c b/kernel/prctl_network.c
new file mode 100644
index 0000000..d173716
--- /dev/null
+++ b/kernel/prctl_network.c
@@ -0,0 +1,37 @@
+/*
+ * linux/kernel/prctl_network.c
+ *
+ * Copyright 2009  Michael Stone <michael@laptop.org>
+ *
+ * Turn off a process's ability to access new networks.
+ * See Documentation/prctl_network.txt for details.
+ */
+
+#include <linux/prctl_network.h>
+#include <linux/sched.h>
+#include <linux/prctl.h>
+
+long prctl_get_network(void)
+{
+	return current->network;
+}
+
+long prctl_set_network(unsigned long network_flags)
+{
+	long ret;
+
+	/* only dropping access is permitted */
+	ret = -EPERM;
+        if (current->network & ~network_flags)
+		goto out;
+
+	ret = -EINVAL;
+	if (network_flags & ~PR_NETWORK_ALL_FLAGS)
+		goto out;
+
+	current->network = network_flags;
+	ret = 0;
+
+out:
+	return ret;
+}
diff --git a/kernel/sys.c b/kernel/sys.c
index 20ccfb5..4eccc66 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -35,6 +35,7 @@
 #include <linux/cpu.h>
 #include <linux/ptrace.h>
 #include <linux/fs_struct.h>
+#include <linux/prctl_network.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -1576,6 +1577,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			else
 				error = PR_MCE_KILL_DEFAULT;
 			break;
+		case PR_SET_NETWORK:
+			error = prctl_set_network(arg2);
+			break;
+		case PR_GET_NETWORK:
+			error = prctl_get_network();
+			break;
 		default:
 			error = -EINVAL;
 			break;
-- 
1.5.6.5

Re: [PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Andi Kleen]

On Wed, Dec 16, 2009 at 10:32:43AM -0500, Michael Stone wrote:
> Daniel Bernstein has observed [1] that security-conscious userland processes
> may benefit from the ability to irrevocably remove their ability to create,
> bind, connect to, or send messages except in the case of previously connected
> sockets or AF_UNIX filesystem sockets. We provide this facility by implementing
> support for a new prctl(PR_SET_NETWORK) flag named PR_NETWORK_OFF.
> 
> This facility is particularly attractive to security platforms like OLPC
> Bitfrost [2] and to isolation programs like Rainbow [3] and Plash [4].

What would stop them from ptracing someone else running under the same
uid who still has the network access? If you ptrace you can do
arbitary system calls.

-Andi

-- 
ak@linux.intel.com -- Speaking for myself only.

Re: [PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Michael Stone]

Andi Kleen wrote:
> On Wed, Dec 16, 2009 at 10:32:43AM -0500, Michael Stone wrote:
>> Daniel Bernstein has observed [1] that security-conscious userland processes
>> may benefit from the ability to irrevocably remove their ability to create,
>> bind, connect to, or send messages except in the case of previously
>> connected sockets or AF_UNIX filesystem sockets. We provide this facility by
>> implementing support for a new prctl(PR_SET_NETWORK) flag named
>> PR_NETWORK_OFF.
>> 
>> This facility is particularly attractive to security platforms like OLPC
>> Bitfrost [2] and to isolation programs like Rainbow [3] and Plash [4].
> 
> What would stop them from ptracing someone else running under the same
> uid who still has the network access? 

Just like in the (revised from last year) rlimits version, there's a hunk in
the prctl_network semantics patch which disables networking-via-ptrace() like
so:

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 23bd09c..5b38db0 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -151,6 +151,8 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
                dumpable = get_dumpable(task->mm);
        if (!dumpable && !capable(CAP_SYS_PTRACE))
                return -EPERM;
+       if (current->network)
+               return -EPERM;

        return security_ptrace_access_check(task, mode);
  }

More questions?

Regards, and thanks for your interest,

Michael

Re: [PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Andi Kleen]

On Wed, Dec 16, 2009 at 08:25:40PM -0500, Michael Stone wrote:
> Andi Kleen wrote:
>> On Wed, Dec 16, 2009 at 10:32:43AM -0500, Michael Stone wrote:
>>> Daniel Bernstein has observed [1] that security-conscious userland processes
>>> may benefit from the ability to irrevocably remove their ability to create,
>>> bind, connect to, or send messages except in the case of previously
>>> connected sockets or AF_UNIX filesystem sockets. We provide this facility by
>>> implementing support for a new prctl(PR_SET_NETWORK) flag named
>>> PR_NETWORK_OFF.
>>>
>>> This facility is particularly attractive to security platforms like OLPC
>>> Bitfrost [2] and to isolation programs like Rainbow [3] and Plash [4].
>>
>> What would stop them from ptracing someone else running under the same
>> uid who still has the network access? 
>
> Just like in the (revised from last year) rlimits version, there's a hunk in
> the prctl_network semantics patch which disables networking-via-ptrace() like
> so:

Hmm, ok. Missed that. I hope there are not more big holes. Obviously
can't allow to change other executables, but I guess that's ok.

It's still some overlap with network name spaces, but there are also
some not directly mappable semantic differences.

I haven't reviewed the patches in detail btw.

-Andi

-- 
ak@linux.intel.com -- Speaking for myself only.

Re: [PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Andi Kleen]

> This is not very good because in some situations it is useful to disable
> connect() and bind() while still allowing ptracing of other processes.  For
> example, Plash creates a new UID for each sandbox and it is possible to use
> strace and gdb inside a sandbox.  Currently Plash is not able to block
> network access or allow only limited network access.  If you treat ptrace()
> this way we won't have the ability to use strace and gdb while limiting
> network access.

No that's not what the hunk does. I first thought the same. But it actually
just limits these processes from initiating ptracing themselves. You can still
attach gdb/strace to them.

Now I'm not sure if that's closing all holes, but at least I can't come
up with any obvious ones currently. I think I would still prefer a more
general security container in general.

-Andi
-- 
ak@linux.intel.com -- Speaking for myself only.

Re: [PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Mark Seaborn]

Andi Kleen <andi@firstfloor.org> wrote:

> > This is not very good because in some situations it is useful to disable
> > connect() and bind() while still allowing ptracing of other processes.  For
> > example, Plash creates a new UID for each sandbox and it is possible to use
> > strace and gdb inside a sandbox.  Currently Plash is not able to block
> > network access or allow only limited network access.  If you treat ptrace()
> > this way we won't have the ability to use strace and gdb while limiting
> > network access.
> 
> No that's not what the hunk does. I first thought the same. But it actually
> just limits these processes from initiating ptracing themselves. You can still
> attach gdb/strace to them.

No, I specifically mean running gdb/strace *inside* the sandbox so
that sandboxed processes can initiate ptrace on other processes inside
the same sandbox.  At the moment you can create a Plash sandbox and
run strace inside it with a command like the following, and strace
will successfully ptrace the subprocess that it spawns:

pola-run -B -e strace echo foo

I wouldn't want this to stop working just because the "disable
networking" flag has been set for all processes in the sandbox.

In practice Plash would set "disable networking" for all sandboxed
processes and then selectively enable limited network access by
passing file descriptors into the sandboxed processes via a socket.


> Now I'm not sure if that's closing all holes, but at least I can't come
> up with any obvious ones currently. I think I would still prefer a more
> general security container in general.

Well, yeah, adding a boolean just for network access seems pretty ad-hoc.

It sets alarm bells ringing if "disable networking" also functions as
"disable initiating ptrace()".  Isn't there a way of doing the latter
independently?

Cheers,
Mark

Re: [PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Michael Stone]

Mark, Andi, Eric, and Randy,

First, thanks for all the comments, questions, and suggestions. They're very
much appreciated.

@Randy: In the revised patches that follow, I moved the documentation to

   Documentation/prctl/network.txt 

as you requested.

@Américo: In the revised patches that follow, I moved prctl_{get,set}_network()
into sys/kernel.c as you suggested.

@Eric, Mark: regarding ptrace()-ing from network-disabled processes: I agree
that this functionality is critical and I have altered the
__ptrace_may_access() check to support it. 

The new rule I propose is equivalent to the rule I used in ptrace_set_network()
and is similar to the rule that Eric proposed earlier this afternoon. I now
propose:

   "You may ptrace() any process that has all the network restrictions you do."

This should take care of your use of strace without bending anything else into
an unnatural shape.

------------------------

@Andi, Mark

Next, let's talk about the "ad-hoc"-ness of the current patches. There seem to
be three issues:

   1. What is "network access"?

   2. How should "network access" be access-controlled?

   3. Should we add a per-process boolean flag enabling and disabling some
      kinds of network access?

Here are my thoughts:

   1. "Network access" refers to the ability of a security principal to send
      messages to or to receive messages from a different principal. For our
      purposes, principals may be thought of as processes.

   2. Messages are sent and received over "channels". Common channels include
      open file descriptors, memory segments, message queues, file systems,
      process signalling trees, and ptrace attachments.
      
   3. The creation of new channels between principals is a security-sensitive
      operation. 

   4. The decision about whether or not to authorize opening a new channel
      between security principals should be based on five inputs:

            a) the general system policy, if any, of the sysadmin
            b) the personal policies, if any, of the human operator(s)
            c) the authors' policies, if any, in security principal(s)
            d) the channel being requested
            e) security labels like pids, uids, and acls labeling the principals

   5. Linux today has pretty good support for controlling the creation of
      channels involving the filesystem and involving shared daemons. It has
      mediocre support for access control involving sysv-ipc mechanisms. It has
      terrible support for access control involving non-local principals like
      "the collection of people and programs receiving packets sent to
      destination 18.0.0.1:80 from source 192.168.0.3:34661".

   6. We can make it easier and safer to write and to run software by improving
      the access control mechanisms available for deciding whether or not to
      open new channels.

   7. The best way to improve said access control mechanisms today is to add a
      facility that permits any process to drop the (heretofor not formally
      recognized) privilege that causes the kernel to open new *insufficiently
      access controlled* network channels.

   8. Anything that has to pass a regular Unix uid/gid/world discretionary
      access check *and* which the partner principal(s) have the opportunity to
      turn down is sufficiently access controlled. Everything else is not.

      (For example, filesystem Unix sockets are sufficiently controlled but
      ptrace is not because the process being traced has no opportunity to say
      "don't open this channel".)

   9. My patch implements the simplest and most usable improvement available in
      this area.

Critiques?

Alternately, you've both expressed some interest in a more general facility for
restricting network access. Do either of you have specific ideas on what you'd
like to see?

Michael
--
To unsubscribe from this list: send the line "unsubscribe linux-security-module" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK) interface. (v2)

[Michael Stone]

Daniel Bernstein has observed [1] that security-conscious userland processes
may benefit from the ability to irrevocably remove their ability to create,
bind, connect to, or send messages except in the case of previously connected
sockets or AF_UNIX filesystem sockets. We provide this facility by implementing
support for a new prctl(PR_SET_NETWORK) flag named PR_NETWORK_OFF.

This facility is particularly attractive to security platforms like OLPC
Bitfrost [2] and to isolation programs like Rainbow [3] and Plash [4].

[1]: http://cr.yp.to/unix/disablenetwork.html
[2]: http://wiki.laptop.org/go/OLPC_Bitfrost
[3]: http://wiki.laptop.org/go/Rainbow
[4]: http://plash.beasts.org/

Signed-off-by: Michael Stone <michael@laptop.org>
---
  include/linux/prctl.h         |    7 +++++++
  include/linux/prctl_network.h |    7 +++++++
  include/linux/sched.h         |    2 ++
  kernel/sys.c                  |   32 ++++++++++++++++++++++++++++++++
  4 files changed, 48 insertions(+), 0 deletions(-)
  create mode 100644 include/linux/prctl_network.h

diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index a3baeb2..4eb4110 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -102,4 +102,11 @@
  
  #define PR_MCE_KILL_GET 34
  
+/* Get/set process disable-network flags */
+#define PR_SET_NETWORK	35
+#define PR_GET_NETWORK	36
+# define PR_NETWORK_ON        0
+# define PR_NETWORK_OFF       1
+# define PR_NETWORK_ALL_FLAGS 1
+
  #endif /* _LINUX_PRCTL_H */
diff --git a/include/linux/prctl_network.h b/include/linux/prctl_network.h
new file mode 100644
index 0000000..2db83eb
--- /dev/null
+++ b/include/linux/prctl_network.h
@@ -0,0 +1,7 @@
+#ifndef _LINUX_PRCTL_NETWORK_H
+#define _LINUX_PRCTL_NETWORK_H
+
+extern long prctl_get_network(void);
+extern long prctl_set_network(unsigned long);
+
+#endif /* _LINUX_PRCTL_NETWORK_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5c858f3..751d372 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1395,6 +1395,8 @@ struct task_struct {
  	unsigned int sessionid;
  #endif
  	seccomp_t seccomp;
+/* Flags for limiting networking via prctl(PR_SET_NETWORK). */
+  unsigned long network;
  
  /* Thread group tracking */
     	u32 parent_exec_id;
diff --git a/kernel/sys.c b/kernel/sys.c
index 20ccfb5..411a2ff 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -35,6 +35,7 @@
  #include <linux/cpu.h>
  #include <linux/ptrace.h>
  #include <linux/fs_struct.h>
+#include <linux/prctl_network.h>
  
  #include <linux/compat.h>
  #include <linux/syscalls.h>
@@ -1576,6 +1577,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
  			else
  				error = PR_MCE_KILL_DEFAULT;
  			break;
+		case PR_SET_NETWORK:
+			error = prctl_set_network(arg2);
+			break;
+		case PR_GET_NETWORK:
+			error = prctl_get_network();
+			break;
  		default:
  			error = -EINVAL;
  			break;
@@ -1583,6 +1590,31 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
  	return error;
  }
  
+long prctl_get_network(void)
+{
+	return current->network;
+}
+
+long prctl_set_network(unsigned long network_flags)
+{
+	long ret;
+
+	/* only dropping access is permitted */
+	ret = -EPERM;
+        if (current->network & ~network_flags)
+		goto out;
+
+	ret = -EINVAL;
+	if (network_flags & ~PR_NETWORK_ALL_FLAGS)
+		goto out;
+
+	current->network = network_flags;
+	ret = 0;
+
+out:
+	return ret;
+}
+
  SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
  		struct getcpu_cache __user *, unused)
  {
-- 
1.6.6.rc1

Re: [PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK) interface. (v2)

[Valdis.Kletnieks]

[-- Attachment #1: Type: text/plain, Size: 850 bytes --]

On Thu, 17 Dec 2009 22:29:57 EST, Michael Stone said:
> Daniel Bernstein has observed [1] that security-conscious userland processes
> may benefit from the ability to irrevocably remove their ability to create,
> bind, connect to, or send messages except in the case of previously connected
> sockets or AF_UNIX filesystem sockets. We provide this facility by implementing
> support for a new prctl(PR_SET_NETWORK) flag named PR_NETWORK_OFF.

Dan does indeed have a point - but is this better achieved via either
the already-existing LSM interfaces (opening the stacking-LSM can of worms
again), or the SECCOMP framework?  We already have 2 other ways to turn off
stuff, do we really want a third way?

Alternatively, could a more generalized prctl interface be leveraged to handle
SECCOMP, and/or other targeted things that want to stack with LSM?


[-- Attachment #2: Type: application/pgp-signature, Size: 227 bytes --]

Re: [PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK) interface. (v2)

[Alan Cox]

On Thu, 17 Dec 2009 22:29:57 -0500
Michael Stone <michael@laptop.org> wrote:

> Daniel Bernstein has observed [1] that security-conscious userland processes

Dan Bernstein has observed many things .. ;)

> may benefit from the ability to irrevocably remove their ability to create,
> bind, connect to, or send messages except in the case of previously connected
> sockets or AF_UNIX filesystem sockets. We provide this facility by implementing
> support for a new prctl(PR_SET_NETWORK) flag named PR_NETWORK_OFF.

This is a security model, it belongs as a security model using LSM. You
can already do it with SELinux and the like as far as I can see but
that's not to say you shouldn't submit it also as a small handy
standalone security module for people who don't want to load the big
security modules.

Otherwise you end up putting crap in fast paths that nobody needs but
everyone pays for and weird tests and hacks for address family and like
into core network code.

The fact the patches look utterly ugly should be telling you something -
which is that you are using the wrong hammer

Re: [PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK)

[Michael Stone]

Alan Cox wrote:

> This is a security model, it belongs as a security model using LSM. 

I'll see what I can cook up for you.

However, please don't be surprised when the resulting cover letter states that
the LSM-based version *does not* resolve the situation to my satisfaction as a
userland hacker due to the well-known and long-standing adoption and
compositionality problems facing small LSMs. ;)

Regards,

Michael

P.S. - Dan is cited in my patch because I wish to honor him for anticipating my
desires early, clearly, and in writing. However, if you know of an earlier
citation, then I'll be happy to include that one too.

Re: [PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK)

[Alan Cox]

> the LSM-based version *does not* resolve the situation to my satisfaction as a
> userland hacker due to the well-known and long-standing adoption and
> compositionality problems facing small LSMs. ;)

For things like Fedora it's probably an "interesting idea, perhaps we
should do it using SELinux" sort of problem, but a config option for a
magic network prctl is also going to be hard to adopt without producing a
good use case - and avoiding that by dumping crap into everyones kernel
fast paths isn't a good idea either.

Re: [PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK)

[Eric W. Biederman]

Alan Cox <alan@lxorguk.ukuu.org.uk> writes:

>> the LSM-based version *does not* resolve the situation to my satisfaction as a
>> userland hacker due to the well-known and long-standing adoption and
>> compositionality problems facing small LSMs. ;)
>
> For things like Fedora it's probably an "interesting idea, perhaps we
> should do it using SELinux" sort of problem, but a config option for a
> magic network prctl is also going to be hard to adopt without producing a
> good use case - and avoiding that by dumping crap into everyones kernel
> fast paths isn't a good idea either.

If I understand the problem the goal is to disable access to ipc
mechanism that don't have the usual unix permissions.  To get
something that is usable for non-root processes, and to get something
that is widely deployed so you don't have to jump through hoops in
end user applications to use it.

We have widely deployed mechanisms that are what you want or nearly
what you want already in the form of the various namespaces built for
containers.

I propose you introduce a permanent disable of executing suid 
applications. 

After which point it is another trivial patch to allow unsharing of
the network namespace if executing suid applications are disabled.

Eric

Re: [PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK)

[Michael Stone]

> Eric Biederman writes:
>> Alan Cox <alan@lxorguk.ukuu.org.uk> writes:
>>> Michael Stone writes:
>>>> the LSM-based version *does not* resolve the situation to my satisfaction as a
>>>> userland hacker due to the well-known and long-standing adoption and
>>>> compositionality problems facing small LSMs. ;)
>>>
>>> For things like Fedora it's probably an "interesting idea, perhaps we
>>> should do it using SELinux" sort of problem, but a config option for a
>>> magic network prctl is also going to be hard to adopt without producing a
>>> good use case - and avoiding that by dumping crap into everyones kernel
>>> fast paths isn't a good idea either.
>
>If I understand the problem the goal is to disable access to ipc
>mechanism that don't have the usual unix permissions.  To get
>something that is usable for non-root processes, and to get something
>that is widely deployed so you don't have to jump through hoops in
>end user applications to use it.

Eric,

You understand correctly. Thank you for this cogent restatement.

>We have widely deployed mechanisms that are what you want or nearly
>what you want already in the form of the various namespaces built for
>containers.

It's true that your work is closer to what I want than anything else that I've
seen so far...

>I propose you introduce a permanent disable of executing suid 
>applications. 

I'm open to the idea but I don't understand the need that motivates it yet.

Could you please explain further? (or point me to an existing explanation?)

>After which point it is another trivial patch to allow unsharing of
>the network namespace if executing suid applications are disabled.

How do you propose to address the problem with the Unix sockets?

Regards,

Michael

Re: [PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK)

[Eric W. Biederman]

Michael Stone <michael@laptop.org> writes:

>> Eric Biederman writes:
>>> Alan Cox <alan@lxorguk.ukuu.org.uk> writes:
>>>> Michael Stone writes:
>>>>> the LSM-based version *does not* resolve the situation to my satisfaction as a
>>>>> userland hacker due to the well-known and long-standing adoption and
>>>>> compositionality problems facing small LSMs. ;)
>>>>
>>>> For things like Fedora it's probably an "interesting idea, perhaps we
>>>> should do it using SELinux" sort of problem, but a config option for a
>>>> magic network prctl is also going to be hard to adopt without producing a
>>>> good use case - and avoiding that by dumping crap into everyones kernel
>>>> fast paths isn't a good idea either.
>>
>>If I understand the problem the goal is to disable access to ipc
>>mechanism that don't have the usual unix permissions.  To get
>>something that is usable for non-root processes, and to get something
>>that is widely deployed so you don't have to jump through hoops in
>>end user applications to use it.
>
> Eric,
>
> You understand correctly. Thank you for this cogent restatement.
>
>>We have widely deployed mechanisms that are what you want or nearly
>>what you want already in the form of the various namespaces built for
>>containers.
>
> It's true that your work is closer to what I want than anything else that I've
> seen so far...
>
>> I propose you introduce a permanent disable of executing suid applications. 
>
> I'm open to the idea but I don't understand the need that motivates it yet.
> Could you please explain further? (or point me to an existing explanation?)

With namespaces it is possible to masquarade as a trusted source,
of information to a suid program such as /etc/passwd or a NIS server.

A one-way removal of the ability to exec suid programs is generally
simple and handy like chroot, and removes the need for CAP_SYS_ADMIN
in most cases.

Plan 9 did not support suid executables and supported an unprivileged
equivalent of unshare(NEWNS).

I need the full unprivileged unshare of USERNS for my primary
uses today as I need to perform normally root only activities
like mounting loopback devices, and setting up networking. Your
uses of limiting of ipc do not appear to require that.

>>After which point it is another trivial patch to allow unsharing of
>>the network namespace if executing suid applications are disabled.
>
> How do you propose to address the problem with the Unix sockets?

Careful code review of the patch to allow talking between network
namespaces with unix domain sockets.  This is a feature that we
simply have not merged yet.  Semantically it is fine today. It is
simply no one has answered the question what other implications
could there be.  Now that I know of 2 or 3 compelling use
cases and most of the rest of the work done.  It seems time to
relax the restriction.

Eric

[PATCH 0/3] Discarding networking privilege via LSM

[Michael Stone]

Alan,

As you requested, here's a (rough) draft of my patch series which uses the
security_* hooks instead of direct modification of the networking functions. 

Have you further suggestions for improvement?

Regards,

Michael

P.S. - The most notable behavioral difference between this patch and the
previous one is that abstract unix sockets are exempted from control in this
patch but are restricted by the previous one. We can revisit this detail in
subsequent patches if this approach seems viable.

Michael Stone (3):
   Security: Add prctl(PR_{GET,SET}_NETWORK) interface. (v3)
   Security: Implement prctl(PR_SET_NETWORK, PR_NETWORK_OFF) semantics. (v3)
   Security: Document prctl(PR_{GET,SET}_NETWORK). (v3)

  Documentation/prctl/network.txt |   74 ++++++++++++++++++++++++++
  include/linux/prctl.h           |    7 +++
  include/linux/prctl_network.h   |    7 +++
  include/linux/sched.h           |    2 +
  kernel/sys.c                    |   32 +++++++++++
  security/Kconfig                |   13 +++++
  security/Makefile               |    1 +
  security/prctl_network.c        |  110 +++++++++++++++++++++++++++++++++++++++
  8 files changed, 246 insertions(+), 0 deletions(-)
  create mode 100644 Documentation/prctl/network.txt
  create mode 100644 include/linux/prctl_network.h
  create mode 100644 security/prctl_network.c

[PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK) interface. (v3)

[Michael Stone]

Daniel Bernstein has observed [1] that security-conscious userland processes
may benefit from the ability to irrevocably remove their ability to create,
bind, connect to, or send messages except in the case of previously connected
sockets or AF_UNIX filesystem sockets. We provide this facility via a new
prctl option-pair (PR_SET_NETWORK, PR_GET_NETWORK) and a new
prctl(PR_SET_NETWORK) flag named PR_NETWORK_OFF.

This facility is particularly attractive to security platforms like OLPC
Bitfrost [2] and to isolation programs like Rainbow [3] and Plash [4].

[1]: http://cr.yp.to/unix/disablenetwork.html
[2]: http://wiki.laptop.org/go/OLPC_Bitfrost
[3]: http://wiki.laptop.org/go/Rainbow
[4]: http://plash.beasts.org/

Signed-off-by: Michael Stone <michael@laptop.org>
---
  include/linux/prctl.h         |    7 +++++++
  include/linux/prctl_network.h |    7 +++++++
  include/linux/sched.h         |    2 ++
  kernel/sys.c                  |   32 ++++++++++++++++++++++++++++++++
  4 files changed, 48 insertions(+), 0 deletions(-)
  create mode 100644 include/linux/prctl_network.h

diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index a3baeb2..4eb4110 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -102,4 +102,11 @@
  
  #define PR_MCE_KILL_GET 34
  
+/* Get/set process disable-network flags */
+#define PR_SET_NETWORK	35
+#define PR_GET_NETWORK	36
+# define PR_NETWORK_ON        0
+# define PR_NETWORK_OFF       1
+# define PR_NETWORK_ALL_FLAGS 1
+
  #endif /* _LINUX_PRCTL_H */
diff --git a/include/linux/prctl_network.h b/include/linux/prctl_network.h
new file mode 100644
index 0000000..2db83eb
--- /dev/null
+++ b/include/linux/prctl_network.h
@@ -0,0 +1,7 @@
+#ifndef _LINUX_PRCTL_NETWORK_H
+#define _LINUX_PRCTL_NETWORK_H
+
+extern long prctl_get_network(void);
+extern long prctl_set_network(unsigned long);
+
+#endif /* _LINUX_PRCTL_NETWORK_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f2f842d..0c65c55 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1402,6 +1402,8 @@ struct task_struct {
  	unsigned int sessionid;
  #endif
  	seccomp_t seccomp;
+/* Flags for limiting networking via prctl(PR_SET_NETWORK). */
+  unsigned long network;
  
  /* Thread group tracking */
     	u32 parent_exec_id;
diff --git a/kernel/sys.c b/kernel/sys.c
index 26a6b73..e7d345c 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -35,6 +35,7 @@
  #include <linux/cpu.h>
  #include <linux/ptrace.h>
  #include <linux/fs_struct.h>
+#include <linux/prctl_network.h>
  
  #include <linux/compat.h>
  #include <linux/syscalls.h>
@@ -1578,6 +1579,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
  			else
  				error = PR_MCE_KILL_DEFAULT;
  			break;
+		case PR_SET_NETWORK:
+			error = prctl_set_network(arg2);
+			break;
+		case PR_GET_NETWORK:
+			error = prctl_get_network();
+			break;
  		default:
  			error = -EINVAL;
  			break;
@@ -1585,6 +1592,31 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
  	return error;
  }
  
+long prctl_get_network(void)
+{
+	return current->network;
+}
+
+long prctl_set_network(unsigned long network_flags)
+{
+	long ret;
+
+	/* only dropping access is permitted */
+	ret = -EPERM;
+        if (current->network & ~network_flags)
+		goto out;
+
+	ret = -EINVAL;
+	if (network_flags & ~PR_NETWORK_ALL_FLAGS)
+		goto out;
+
+	current->network = network_flags;
+	ret = 0;
+
+out:
+	return ret;
+}
+
  SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
  		struct getcpu_cache __user *, unused)
  {
-- 
1.6.6.rc1

Re: [PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK) interface. (v3)

[Samir Bellabes]

Michael Stone <michael@laptop.org> writes:

> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index f2f842d..0c65c55 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1402,6 +1402,8 @@ struct task_struct {
>   	unsigned int sessionid;
>   #endif
>   	seccomp_t seccomp;
> +/* Flags for limiting networking via prctl(PR_SET_NETWORK). */
> +  unsigned long network;
>   
>   /* Thread group tracking */
>      	u32 parent_exec_id;

I think this is unnecessary, as LSM module, you should use the
void* security member of the structure cred. 

this member allows you to mark task_struct as you which, it's a kind of
abstraction provided to all security modules.

Re: [PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK) interface. (v3)

[Michael Stone]

> I think this is unnecessary, as LSM module, you should use the
> void* security member of the structure cred. 

The change you propose is easily made but I'm having trouble seeing how making
it would help my purpose: the field you name is already in use by other parts
of the kernel which my functionality is intended to complement.

That being said, I'd be very happy to prepare a version of the patch using the
strategy you suggest if it would be directly useful to you or if you can show
me how it would contribute to my goals.

Regards, and thanks for your comment,

Michael

P.S. - Perhaps a reasonable alternative would be to the definition of the field
conditional on CONFIGURE_SECURITY_PRCTL_NETWORK?

Re: [PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK) interface. (v3)

[Tetsuo Handa]

Samir Bellabes wrote:
> > diff --git a/include/linux/sched.h b/include/linux/sched.h
> > index f2f842d..0c65c55 100644
> > --- a/include/linux/sched.h
> > +++ b/include/linux/sched.h
> > @@ -1402,6 +1402,8 @@ struct task_struct {
> >   	unsigned int sessionid;
> >   #endif
> >   	seccomp_t seccomp;
> > +/* Flags for limiting networking via prctl(PR_SET_NETWORK). */
> > +  unsigned long network;
> >   
> >   /* Thread group tracking */
> >      	u32 parent_exec_id;
> 
> I think this is unnecessary, as LSM module, you should use the
> void* security member of the structure cred. 
> 
> this member allows you to mark task_struct as you which, it's a kind of
> abstraction provided to all security modules.

I want to use per task_struct variable. Since cred is copy-on-write, we have to
use kmalloc()/kfree() whenever we modify variable in cred. That introduces
unnwanted error paths (i.e. memory allocation failure) and overhead.

Old version of TOMOYO had similar mechanism that allows userland programs to
disable specific operations (disable chroot(), disable execve(), disable
mount() etc. ; which is different from POSIX capabilities).
I added "unsigned int dropped_capability;" to task_struct for implementing it.
Adding variables to task_struct makes it possible to error-path-free.
I prefer adding "void *security;" to task_struct which is duplicated upon fork() and
released upon exit().

[PATCH 2/3] Security: Implement prctl(PR_SET_NETWORK, PR_NETWORK_OFF) semantics. (v3)

[Michael Stone]

Implement security_* hooks for socket_create, socket_bind, socket_connect,
socket_sendmsg, and ptrace_access_check which return -EPERM when called from a
process with networking restrictions. Exempt AF_UNIX sockets.

Signed-off-by: Michael Stone <michael@laptop.org>
---
  security/Kconfig         |   13 +++++
  security/Makefile        |    1 +
  security/prctl_network.c |  110 ++++++++++++++++++++++++++++++++++++++++++++++
  3 files changed, 124 insertions(+), 0 deletions(-)
  create mode 100644 security/prctl_network.c

diff --git a/security/Kconfig b/security/Kconfig
index 226b955..740a7fe 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -137,6 +137,19 @@ config LSM_MMAP_MIN_ADDR
  	  this low address space will need the permission specific to the
  	  systems running LSM.
  
+config SECURITY_PRCTL_NETWORK
+	tristate "prctl(PR_{GET,SET}_NETWORK) support"
+	depends on SECURITY_NETWORK
+	help
+    This enables processes to drop networking privileges via
+    prctl(PR_SET_NETWORK, PR_NETWORK_OFF), which is used by OLPC's isolation
+    shell, <http://wiki.laptop.org/go/Rainbow> to implement discretionary
+    network isolation.
+
+    See Documentation/prctl/network.txt for more information about this LSM.
+
+	  If you are unsure how to answer this question, answer N.
+
  source security/selinux/Kconfig
  source security/smack/Kconfig
  source security/tomoyo/Kconfig
diff --git a/security/Makefile b/security/Makefile
index da20a19..92ce65d 100644
--- a/security/Makefile
+++ b/security/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_SECURITY_SMACK)		+= smack/built-in.o
  obj-$(CONFIG_AUDIT)			+= lsm_audit.o
  obj-$(CONFIG_SECURITY_TOMOYO)		+= tomoyo/built-in.o
  obj-$(CONFIG_CGROUP_DEVICE)		+= device_cgroup.o
+obj-$(CONFIG_SECURITY_PRCTL_NETWORK)	+= prctl_network.o
  
  # Object integrity file lists
  subdir-$(CONFIG_IMA)			+= integrity/ima
diff --git a/security/prctl_network.c b/security/prctl_network.c
new file mode 100644
index 0000000..2da6051
--- /dev/null
+++ b/security/prctl_network.c
@@ -0,0 +1,110 @@
+/*
+ * prctl_network LSM.
+ *
+ * Copyright (C) 2008-2009 Michael Stone <michael@laptop.org>
+ * Based on sample code from security/root_plug.c, (C) 2002 Greg Kroah-Hartman.
+ *
+ * Implements the prctl(PR_SET_NETWORK, PR_NETWORK_OFF) syscall.
+ *
+ * See Documentation/prctl/network.txt for more information about this code.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <net/sock.h>
+#include <linux/socket.h>
+#include <linux/security.h>
+
+static inline int maybe_allow(void)
+{
+	if (current->network)
+		return -EPERM;
+	return 0;
+}
+
+static inline int prctl_network_socket_create_hook (int family, int type,
+						int protocol, int kern)
+{
+	if (family == AF_UNIX)
+		return 0;
+	return maybe_allow();
+}
+
+static inline int prctl_network_socket_bind_hook(struct socket * sock,
+					     struct sockaddr * address,
+					     int addrlen)
+{
+	if (address->sa_family == AF_UNIX)
+		return 0;
+	return maybe_allow();
+}
+
+static inline int prctl_network_socket_connect_hook(struct socket * sock,
+						struct sockaddr * address,
+						int addrlen)
+{
+	if (address->sa_family == AF_UNIX)
+		return 0;
+	return maybe_allow();
+}
+
+static inline int prctl_network_socket_sendmsg_hook(struct socket * sock,
+						struct msghdr * msg, int size)
+{
+	if (sock->sk->sk_family != PF_UNIX &&
+		current->network &&
+		(msg->msg_name != NULL || msg->msg_namelen != 0))
+		return -EPERM;
+	return 0;
+}
+
+static inline int prctl_network_ptrace_access_check_hook(struct task_struct *child, unsigned int mode)
+{
+	/* does current have networking restrictions not shared by child? */
+	if (current->network & ~child->network)
+		return -EPERM;
+	return 0;
+}
+
+/* static inline int prctl_network_ptrace_traceme(struct task_struct *parent) ? */
+
+static struct security_operations prctl_network_security_ops = {
+	.name                   = "prctl_net",
+	.socket_create		= prctl_network_socket_create_hook,
+	.socket_bind		= prctl_network_socket_bind_hook,
+	.socket_connect		= prctl_network_socket_connect_hook,
+	.socket_sendmsg		= prctl_network_socket_sendmsg_hook,
+	.ptrace_access_check	= prctl_network_ptrace_access_check_hook,
+};
+
+static int __init prctl_network_security_init (void)
+{
+	if (!security_module_enable(&prctl_network_security_ops)) {
+		printk (KERN_INFO
+			"Failure enabling prctl_network_lsm.\n");
+		return 0;
+	}
+
+	/* register ourselves with the security framework */
+	if (register_security (&prctl_network_security_ops)) {
+		printk (KERN_INFO
+			"Failure registering prctl_network_lsm with the kernel\n");
+		return 0;
+	}
+
+	printk (KERN_INFO "prctl_network_lsm initialized\n");
+
+	return 0;
+}
+
+security_initcall (prctl_network_security_init);
+
+MODULE_DESCRIPTION("prctl_network LSM; implementing prctl(PR_SET_NETWORK, PR_NETWORK_OFF).");
+MODULE_LICENSE("GPL");
-- 
1.6.6.rc1

[PATCH 3/3] Security: Document prctl(PR_{GET,SET}_NETWORK). (v3)

[Michael Stone]

Explain the purpose, interface, and semantics of the
prctl(PR_{GET,SET}_network) facility and LSM.

Also reference some example userland clients.

Signed-off-by: Michael Stone <michael@laptop.org>
---
  Documentation/prctl/network.txt |   74 +++++++++++++++++++++++++++++++++++++++
  1 files changed, 74 insertions(+), 0 deletions(-)
  create mode 100644 Documentation/prctl/network.txt

diff --git a/Documentation/prctl/network.txt b/Documentation/prctl/network.txt
new file mode 100644
index 0000000..8b45d23
--- /dev/null
+++ b/Documentation/prctl/network.txt
@@ -0,0 +1,74 @@
+Purpose
+-------
+
+Daniel Bernstein has observed [1] that security-conscious userland processes
+may benefit from the ability to irrevocably remove their ability to create,
+bind, connect to, or send messages except in the case of previously connected
+sockets or AF_UNIX filesystem sockets.
+
+This facility is particularly attractive to security platforms like OLPC
+Bitfrost [2] and to isolation programs like Rainbow [3] and Plash [4] because:
+
+  * it integrates well with standard techniques for writing privilege-separated
+    Unix programs
+
+  * it integrates well with the need to perform limited socket I/O, e.g., when
+    running X clients
+
+  * it's available to unprivileged programs
+
+  * it's a discretionary feature available to all of distributors,
+    administrators, authors, and users
+
+  * its effect is entirely local, rather than global (like netfilter)
+
+  * it's simple enough to have some hope of being used correctly
+
+Implementation
+--------------
+
+After considering implementations based on the Linux Security Module (LSM)
+framework, on SELinux, on network namespaces (CLONE_NEWNET), on direct
+modification of the kernel syscall and task_struct APIs and after seeking
+advice from members of LKML, we came to the conclusion that the best way to
+implement this feature was to extend the prctl() framework with a new pair of
+options named PR_{GET,SET}_NETWORK and to write an LSM to implement the
+resulting PR_NETWORK_OFF semantics. These options cause prctl() to read or
+modify "current->network".
+
+Semantics
+---------
+
+current->network is a flags field which is preserved across all variants of
+fork() and exec().
+
+Writes which attempt to clear bits in current->network return -EPERM.
+
+The default value for current->network is named PR_NETWORK_ON and is defined
+to be 0.
+
+Presently, only one flag is defined: PR_NETWORK_OFF.
+
+More flags may be defined in the future if they become needed.
+
+Attempts to set undefined flags result in -EINVAL.
+
+When PR_NETWORK_OFF is set, implementations of syscalls which may be used by
+the current process to perform autonomous networking will return -EPERM. For
+example, calls to socket(), bind(), connect(), sendmsg(), and ptrace() will
+return -EPERM except for cases we are manipulating an AF_UNIX socket or, in the
+case of sendmsg(), unless we are manipulating a previously connected socket,
+i.e. one with
+
+  msg.msg_name == NULL && msg.msg_namelen == 0
+
+or, in the case of ptrace(), unless we are ptracing() a process which has all
+of our own networking restriction flags set.
+
+References
+----------
+
+[1]: http://cr.yp.to/unix/disablenetwork.html
+[2]: http://wiki.laptop.org/go/OLPC_Bitfrost
+[3]: http://wiki.laptop.org/go/Rainbow
+[4]: http://plash.beasts.org/
-- 
1.6.6.rc1

Re: [PATCH 1/3] Security: Add prctl(PR_{GET,SET}_NETWORK)

[Pavel Machek]

On Fri 2009-12-18 11:33:48, Michael Stone wrote:
> Alan Cox wrote:
>
>> This is a security model, it belongs as a security model using LSM. 
>
> I'll see what I can cook up for you.
>
> However, please don't be surprised when the resulting cover letter states that
> the LSM-based version *does not* resolve the situation to my satisfaction as a
> userland hacker due to the well-known and long-standing adoption and
> compositionality problems facing small LSMs. ;)

Maybe it is time to fix the LSM? This excuse is much too common...
									Pavel
-- 
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html

[PATCH 2/3] Security: Implement prctl(PR_SET_NETWORK, PR_NETWORK_OFF) semantics. (v2)

[Michael Stone]

Return -EPERM any time we try to __sock_create(), sys_connect(), sys_bind(),
sys_sendmsg(), or __ptrace_may_access() from a process with PR_NETWORK_OFF set
in current->network unless we're working on a socket which is already connected
or on a non-abstract AF_UNIX socket.

Signed-off-by: Michael Stone <michael@laptop.org>
---
  kernel/fork.c      |    2 ++
  kernel/ptrace.c    |    3 +++
  kernel/sys.c       |    2 +-
  net/socket.c       |   51 ++++++++++++++++++++++++++++++++++++++-------------
  net/unix/af_unix.c |   19 +++++++++++++++++++
  5 files changed, 63 insertions(+), 14 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index 9bd9144..01a7644 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1130,6 +1130,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
  
  	p->bts = NULL;
  
+	p->network = current->network;
+
  	p->stack_start = stack_start;
  
  	/* Perform scheduler related setup. Assign this task to a CPU. */
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 23bd09c..bcf87ba 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -151,6 +151,9 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
  		dumpable = get_dumpable(task->mm);
  	if (!dumpable && !capable(CAP_SYS_PTRACE))
  		return -EPERM;
+	/* does current have networking restrictions not shared by task? */
+	if (current->network & ~task->network)
+		return -EPERM;
  
  	return security_ptrace_access_check(task, mode);
  }
diff --git a/kernel/sys.c b/kernel/sys.c
index 411a2ff..481fa9c 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1601,7 +1601,7 @@ long prctl_set_network(unsigned long network_flags)
  
  	/* only dropping access is permitted */
  	ret = -EPERM;
-        if (current->network & ~network_flags)
+	if (current->network & ~network_flags)
  		goto out;
  
  	ret = -EINVAL;
diff --git a/net/socket.c b/net/socket.c
index b94c3dd..e59f906 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -87,6 +87,7 @@
  #include <linux/wireless.h>
  #include <linux/nsproxy.h>
  #include <linux/magic.h>
+#include <linux/sched.h>
  
  #include <asm/uaccess.h>
  #include <asm/unistd.h>
@@ -576,6 +577,12 @@ static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock,
  	if (err)
  		return err;
  
+	err = -EPERM;
+	if (sock->sk->sk_family != AF_UNIX &&
+		current->network &&
+		(msg->msg_name != NULL || msg->msg_namelen != 0))
+		return err;
+
  	return sock->ops->sendmsg(iocb, sock, msg, size);
  }
  
@@ -1227,6 +1234,9 @@ static int __sock_create(struct net *net, int family, int type, int protocol,
  	if (err)
  		return err;
  
+	if (family != AF_UNIX && current->network)
+		return -EPERM;
+
  	/*
  	 *	Allocate the socket and allow the family to set things up. if
  	 *	the protocol is 0, the family is instructed to select an appropriate
@@ -1465,19 +1475,29 @@ SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
  	int err, fput_needed;
  
  	sock = sockfd_lookup_light(fd, &err, &fput_needed);
-	if (sock) {
-		err = move_addr_to_kernel(umyaddr, addrlen, (struct sockaddr *)&address);
-		if (err >= 0) {
-			err = security_socket_bind(sock,
-						   (struct sockaddr *)&address,
-						   addrlen);
-			if (!err)
-				err = sock->ops->bind(sock,
-						      (struct sockaddr *)
-						      &address, addrlen);
-		}
-		fput_light(sock->file, fput_needed);
-	}
+	if (!sock)
+		goto out;
+
+	err = move_addr_to_kernel(umyaddr, addrlen, (struct sockaddr *)&address);
+	if (err < 0)
+		goto out_fput;
+
+	err = security_socket_bind(sock,
+				   (struct sockaddr *)&address,
+				   addrlen);
+	if (err)
+		goto out_fput;
+
+	err = (((struct sockaddr *)&address)->sa_family != AF_UNIX &&
+		current->network) ? -EPERM : 0;
+	if (err)
+		goto out_fput;
+
+	err = sock->ops->bind(sock, (struct sockaddr *) &address, addrlen);
+
+out_fput:
+	fput_light(sock->file, fput_needed);
+out:
  	return err;
  }
  
@@ -1639,6 +1659,11 @@ SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
  	if (err)
  		goto out_put;
  
+	err = (((struct sockaddr *)&address)->sa_family != AF_UNIX &&
+		current->network) ? -EPERM : 0;
+	if (err)
+		goto out_put;
+
  	err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen,
  				 sock->file->f_flags);
  out_put:
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index f255119..5087ae3 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -797,6 +797,10 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
  		goto out;
  	addr_len = err;
  
+	err = (current->network && !sunaddr->sun_path[0]) ? -EPERM : 0;
+	if (err)
+		goto out;
+
  	mutex_lock(&u->readlock);
  
  	err = -EINVAL;
@@ -934,6 +938,10 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
  			goto out;
  		alen = err;
  
+		err = (current->network && !sunaddr->sun_path[0]) ? -EPERM : 0;
+		if (err)
+			goto out;
+
  		if (test_bit(SOCK_PASSCRED, &sock->flags) &&
  		    !unix_sk(sk)->addr && (err = unix_autobind(sock)) != 0)
  			goto out;
@@ -1033,6 +1041,10 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
  		goto out;
  	addr_len = err;
  
+	err = (current->network && !sunaddr->sun_path[0]) ? -EPERM : 0;
+	if (err)
+		goto out;
+
  	if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr &&
  	    (err = unix_autobind(sock)) != 0)
  		goto out;
@@ -1370,6 +1382,10 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
  		if (err < 0)
  			goto out;
  		namelen = err;
+
+		err = -EPERM;
+		if (current->network && !sunaddr->sun_path[0])
+			goto out;
  	} else {
  		sunaddr = NULL;
  		err = -ENOTCONN;
@@ -1520,6 +1536,9 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
  	if (msg->msg_namelen) {
  		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
  		goto out_err;
+		/* prctl(PR_SET_NETWORK) requires no change here since
+		 * connection-less unix stream sockets are not supported.
+		 * See Documentation/prctl/network.txt for details. */
  	} else {
  		sunaddr = NULL;
  		err = -ENOTCONN;
-- 
1.6.6.rc1

Re: [PATCH 2/3] Security: Implement prctl(PR_SET_NETWORK, PR_NETWORK_OFF) semantics. (v2)

[Eric W. Biederman]

Michael Stone <michael@laptop.org> writes:

> Return -EPERM any time we try to __sock_create(), sys_connect(), sys_bind(),
> sys_sendmsg(), or __ptrace_may_access() from a process with PR_NETWORK_OFF set
> in current->network unless we're working on a socket which is already connected
> or on a non-abstract AF_UNIX socket.

It appears to me that the current security hooks are sufficient for what
you are doing.

The one true security module business prevents you from actually using the
security hooks, but could you create wrappers for the network security
hooks so the logic of the network stack does not need to change.

At the very least the huge separation of the test for AF_UNIX and
the test to see if it is a an anonymous AF_UNIX socket is pretty
large.  Structuring the code in such a way as to keep that together would
be nice.

Eric

[PATCH 3/3] Security: Document prctl(PR_{GET,SET}_NETWORK). (v2)

[Michael Stone]

Explain the purpose, interface, and semantics of the
prctl(PR_{GET,SET}_network) facility.

Also reference some example userland clients.

Signed-off-by: Michael Stone <michael@laptop.org>
---
  Documentation/prctl/network.txt |   72 +++++++++++++++++++++++++++++++++++++++
  1 files changed, 72 insertions(+), 0 deletions(-)
  create mode 100644 Documentation/prctl/network.txt

diff --git a/Documentation/prctl/network.txt b/Documentation/prctl/network.txt
new file mode 100644
index 0000000..b337722
--- /dev/null
+++ b/Documentation/prctl/network.txt
@@ -0,0 +1,72 @@
+Purpose
+-------
+
+Daniel Bernstein has observed [1] that security-conscious userland processes
+may benefit from the ability to irrevocably remove their ability to create,
+bind, connect to, or send messages except in the case of previously connected
+sockets or AF_UNIX filesystem sockets.
+
+This facility is particularly attractive to security platforms like OLPC
+Bitfrost [2] and to isolation programs like Rainbow [3] and Plash [4] because:
+
+  * it integrates well with standard techniques for writing privilege-separated
+    Unix programs
+
+  * it integrates well with the need to perform limited socket I/O, e.g., when
+    running X clients
+
+  * it's available to unprivileged programs
+
+  * it's a discretionary feature available to all of distributors,
+    administrators, authors, and users
+
+  * its effect is entirely local, rather than global (like netfilter)
+
+  * it's simple enough to have some hope of being used correctly
+
+Implementation
+--------------
+
+After considering implementations based on the Linux Security Module (LSM)
+framework, on SELinux in particular, on network namespaces (CLONE_NEWNET), and
+on direct modification of the kernel syscall and task_struct APIs, we came to
+the conclusion that the best way to implement this feature was to extend the
+prctl() framework with a new pair of options named PR_{GET,SET}_NETWORK. These
+options cause prctl() to read or modify "current->network".
+
+Semantics
+---------
+
+current->network is a flags field which is preserved across all variants of
+fork() and exec().
+
+Writes which attempt to clear bits in current->network return -EPERM.
+
+The default value for current->network is named PR_NETWORK_OFF and is defined
+to be 0.
+
+Presently, only one flag is defined: PR_NETWORK_OFF.
+
+More flags may be defined in the future if they become needed.
+
+Attempts to set undefined flags result in -EINVAL.
+
+When PR_NETWORK_OFF is set, implementations of syscalls which may be used by
+the current process to perform autonomous networking will return -EPERM. For
+example, calls to socket(), bind(), connect(), sendmsg(), and ptrace() will
+return -EPERM except for cases we are manipulating an AF_UNIX socket whose name
+does not begin with \0 or, in the case of sendmsg(), unless we are manipulating
+a previously connected socket, i.e. one with
+
+  msg.msg_name == NULL && msg.msg_namelen == 0
+
+or, in the case of ptrace(), we are ptracing() a process which has all of our
+own networking restriction flags set.
+
+References
+----------
+
+[1]: http://cr.yp.to/unix/disablenetwork.html
+[2]: http://wiki.laptop.org/go/OLPC_Bitfrost
+[3]: http://wiki.laptop.org/go/Rainbow
+[4]: http://plash.beasts.org/
-- 
1.6.6.rc1

Re: [PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Stephen Hemminger]

On Thu, 17 Dec 2009 22:00:57 -0500
Michael Stone <michael@laptop.org> wrote:

>    5. Linux today has pretty good support for controlling the creation of
>       channels involving the filesystem and involving shared daemons. It has
>       mediocre support for access control involving sysv-ipc mechanisms. It has
>       terrible support for access control involving non-local principals like
>       "the collection of people and programs receiving packets sent to
>       destination 18.0.0.1:80 from source 192.168.0.3:34661".

The policy control for this is done today on linux via the firewalling infrastructure.
It is not clear to me that moving over to the security infrastructure is an overall
gain from the security or user interface perspective.

Re: [PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Mark Seaborn]

On Fri, Dec 18, 2009 at 3:00 AM, Michael Stone <michael@laptop.org> wrote:

> @Eric, Mark: regarding ptrace()-ing from network-disabled processes: I agree
> that this functionality is critical and I have altered the
> __ptrace_may_access() check to support it.
> The new rule I propose is equivalent to the rule I used in ptrace_set_network()
> and is similar to the rule that Eric proposed earlier this afternoon. I now
> propose:
>
>  "You may ptrace() any process that has all the network restrictions you do."
>
> This should take care of your use of strace without bending anything else into
> an unnatural shape.

I am in two minds about this.  On the one hand, it adds the
flexibility that I asked for.  On the other hand, it is a more
complicated rule to have fixed in the kernel.

It still seems wrong to me that the disable-networking flag should
affect ptrace() at all.

The reason is that the disable-networking flag is not useful on its
own.  Anyone who uses it will use it in combination with some other
authority-limiting mechanism.  They will already have a story for how
to prevent sandboxed processes with interfering with other processes
via ptrace(), kill(), writing to ~/.bashrc, etc.  There's no point in
disabling network access for a process if it has full access to your
home directory and can cause programs to be run with your full
authority as a user.

So if there is already a way to control access to ptrace(), we
shouldn't add another check to the kernel's access control rules.
They are complicated enough already.


On ad-hocness: I am very much in favour of providing unprivileged
mechanisms for switching off sources of ambient authority.  But it
does not seem very useful to provide an unprivileged mechanism to
switch off network access if there is no unprivileged mechanism for
switching off access to the filesystem namespace, which is usually a
more important source of authority.  Maybe we should solve both
problems?

Cheers,
Mark

Re: [PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Américo Wang]

On Wed, Dec 16, 2009 at 11:32 PM, Michael Stone <michael@laptop.org> wrote:
> Daniel Bernstein has observed [1] that security-conscious userland processes
> may benefit from the ability to irrevocably remove their ability to create,
> bind, connect to, or send messages except in the case of previously connected
> sockets or AF_UNIX filesystem sockets. We provide this facility by implementing
> support for a new prctl(PR_SET_NETWORK) flag named PR_NETWORK_OFF.
>
> This facility is particularly attractive to security platforms like OLPC
> Bitfrost [2] and to isolation programs like Rainbow [3] and Plash [4].
>
> [1]: http://cr.yp.to/unix/disablenetwork.html
> [2]: http://wiki.laptop.org/go/OLPC_Bitfrost
> [3]: http://wiki.laptop.org/go/Rainbow
> [4]: http://plash.beasts.org/
>
> Signed-off-by: Michael Stone <michael@laptop.org>
> ---
>  include/linux/prctl.h         |    7 +++++++
>  include/linux/prctl_network.h |    7 +++++++
>  include/linux/sched.h         |    2 ++
>  kernel/Makefile               |    2 +-
>  kernel/prctl_network.c        |   37 +++++++++++++++++++++++++++++++++++++
>  kernel/sys.c                  |    7 +++++++
>  6 files changed, 61 insertions(+), 1 deletions(-)
>  create mode 100644 include/linux/prctl_network.h
>  create mode 100644 kernel/prctl_network.c
>
> diff --git a/include/linux/prctl.h b/include/linux/prctl.h
> index a3baeb2..4eb4110 100644
> --- a/include/linux/prctl.h
> +++ b/include/linux/prctl.h
> @@ -102,4 +102,11 @@
>
>  #define PR_MCE_KILL_GET 34
>
> +/* Get/set process disable-network flags */
> +#define PR_SET_NETWORK 35
> +#define PR_GET_NETWORK 36
> +# define PR_NETWORK_ON        0
> +# define PR_NETWORK_OFF       1
> +# define PR_NETWORK_ALL_FLAGS 1
> +
>  #endif /* _LINUX_PRCTL_H */
> diff --git a/include/linux/prctl_network.h b/include/linux/prctl_network.h
> new file mode 100644
> index 0000000..2db83eb
> --- /dev/null
> +++ b/include/linux/prctl_network.h
> @@ -0,0 +1,7 @@
> +#ifndef _LINUX_PRCTL_NETWORK_H
> +#define _LINUX_PRCTL_NETWORK_H
> +
> +extern long prctl_get_network(void);
> +extern long prctl_set_network(unsigned long);
> +
> +#endif /* _LINUX_PRCTL_NETWORK_H */
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 5c858f3..751d372 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1395,6 +1395,8 @@ struct task_struct {
>        unsigned int sessionid;
>  #endif
>        seccomp_t seccomp;
> +/* Flags for limiting networking via prctl(PR_SET_NETWORK). */
> +  unsigned long network;
>
>  /* Thread group tracking */
>        u32 parent_exec_id;
> diff --git a/kernel/Makefile b/kernel/Makefile
> index 864ff75..cafbff2 100644
> --- a/kernel/Makefile
> +++ b/kernel/Makefile
> @@ -10,7 +10,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
>            kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
>            hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
>            notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
> -           async.o
> +           async.o prctl_network.o
>  obj-y += groups.o
>
>  ifdef CONFIG_FUNCTION_TRACER
> diff --git a/kernel/prctl_network.c b/kernel/prctl_network.c
> new file mode 100644
> index 0000000..d173716
> --- /dev/null
> +++ b/kernel/prctl_network.c
> @@ -0,0 +1,37 @@
> +/*
> + * linux/kernel/prctl_network.c
> + *
> + * Copyright 2009  Michael Stone <michael@laptop.org>
> + *
> + * Turn off a process's ability to access new networks.
> + * See Documentation/prctl_network.txt for details.
> + */
> +
> +#include <linux/prctl_network.h>
> +#include <linux/sched.h>
> +#include <linux/prctl.h>
> +
> +long prctl_get_network(void)
> +{
> +       return current->network;
> +}
> +
> +long prctl_set_network(unsigned long network_flags)
> +{
> +       long ret;
> +
> +       /* only dropping access is permitted */
> +       ret = -EPERM;
> +        if (current->network & ~network_flags)
> +               goto out;
> +
> +       ret = -EINVAL;
> +       if (network_flags & ~PR_NETWORK_ALL_FLAGS)
> +               goto out;
> +
> +       current->network = network_flags;
> +       ret = 0;
> +
> +out:
> +       return ret;
> +}


Sorry that I didn't follow the original disscusion.
Any reason why you introdce a new source file?
Why not just adding them to kernel/sys.c?


> diff --git a/kernel/sys.c b/kernel/sys.c
> index 20ccfb5..4eccc66 100644
> --- a/kernel/sys.c
> +++ b/kernel/sys.c
> @@ -35,6 +35,7 @@
>  #include <linux/cpu.h>
>  #include <linux/ptrace.h>
>  #include <linux/fs_struct.h>
> +#include <linux/prctl_network.h>
>
>  #include <linux/compat.h>
>  #include <linux/syscalls.h>
> @@ -1576,6 +1577,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
>                        else
>                                error = PR_MCE_KILL_DEFAULT;
>                        break;
> +               case PR_SET_NETWORK:
> +                       error = prctl_set_network(arg2);
> +                       break;
> +               case PR_GET_NETWORK:
> +                       error = prctl_get_network();
> +                       break;
>                default:
>                        error = -EINVAL;
>                        break;
> --
> 1.5.6.5
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
>

Re: [PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Michael Stone]

Américo Wang wrote:

> Any reason why you introdce a new source file?
> Why not just adding them to kernel/sys.c?

Modifying kernel/sys.c would be fine too, I think. I'll incorporate this
suggestion into the next revision of the prctl()-based patches.

Thanks!

Michael
--
To unsubscribe from this list: send the line "unsubscribe linux-security-module" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Randy Dunlap]

On Wed, 16 Dec 2009 10:32:43 -0500 Michael Stone wrote:


> ---
>  include/linux/prctl.h         |    7 +++++++
>  include/linux/prctl_network.h |    7 +++++++
>  include/linux/sched.h         |    2 ++
>  kernel/Makefile               |    2 +-
>  kernel/prctl_network.c        |   37 +++++++++++++++++++++++++++++++++++++
>  kernel/sys.c                  |    7 +++++++
>  6 files changed, 61 insertions(+), 1 deletions(-)
>  create mode 100644 include/linux/prctl_network.h
>  create mode 100644 kernel/prctl_network.c
> 

> diff --git a/kernel/prctl_network.c b/kernel/prctl_network.c
> new file mode 100644
> index 0000000..d173716
> --- /dev/null
> +++ b/kernel/prctl_network.c
> @@ -0,0 +1,37 @@
> +/*
> + * linux/kernel/prctl_network.c
> + *
> + * Copyright 2009  Michael Stone <michael@laptop.org>
> + *
> + * Turn off a process's ability to access new networks.
> + * See Documentation/prctl_network.txt for details.
> + */

Where is Documentation/prctl_network.txt ?
and it should probably be Documentation/prctl/network.txt .

thanks,
---
~Randy

Re: [PATCH] Security: Add prctl(PR_{GET,SET}_NETWORK) interface.

[Randy Dunlap]

On Thu, 17 Dec 2009 09:23:26 -0800 Randy Dunlap wrote:

> On Wed, 16 Dec 2009 10:32:43 -0500 Michael Stone wrote:
> 
> 
> > ---
> >  include/linux/prctl.h         |    7 +++++++
> >  include/linux/prctl_network.h |    7 +++++++
> >  include/linux/sched.h         |    2 ++
> >  kernel/Makefile               |    2 +-
> >  kernel/prctl_network.c        |   37 +++++++++++++++++++++++++++++++++++++
> >  kernel/sys.c                  |    7 +++++++
> >  6 files changed, 61 insertions(+), 1 deletions(-)
> >  create mode 100644 include/linux/prctl_network.h
> >  create mode 100644 kernel/prctl_network.c
> > 
> 
> > diff --git a/kernel/prctl_network.c b/kernel/prctl_network.c
> > new file mode 100644
> > index 0000000..d173716
> > --- /dev/null
> > +++ b/kernel/prctl_network.c
> > @@ -0,0 +1,37 @@
> > +/*
> > + * linux/kernel/prctl_network.c
> > + *
> > + * Copyright 2009  Michael Stone <michael@laptop.org>
> > + *
> > + * Turn off a process's ability to access new networks.
> > + * See Documentation/prctl_network.txt for details.
> > + */
> 
> Where is Documentation/prctl_network.txt ?
> and it should probably be Documentation/prctl/network.txt .

gag, I see it.  Sorry about that.
I think that the file name still needs to be changed.

---
~Randy

[PATCH] Security: Implement prctl(PR_SET_NETWORK, PR_NETWORK_OFF) semantics.

[Michael Stone]

Return -EPERM any time we try to __sock_create(), sys_connect(), sys_bind(),
sys_sendmsg(), or __ptrace_may_access() from a process with PR_NETWORK_OFF set
in current->network unless we're working on a socket which is already connected
or on a non-abstract AF_UNIX socket.

Signed-off-by: Michael Stone <michael@laptop.org>
---
 kernel/fork.c      |    2 ++
 kernel/ptrace.c    |    2 ++
 net/socket.c       |   51 ++++++++++++++++++++++++++++++++++++++-------------
 net/unix/af_unix.c |   19 +++++++++++++++++++
 4 files changed, 61 insertions(+), 13 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index 9bd9144..01a7644 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1130,6 +1130,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	p->bts = NULL;
 
+	p->network = current->network;
+
 	p->stack_start = stack_start;
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 23bd09c..5b38db0 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -151,6 +151,8 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 		dumpable = get_dumpable(task->mm);
 	if (!dumpable && !capable(CAP_SYS_PTRACE))
 		return -EPERM;
+	if (current->network)
+		return -EPERM;
 
 	return security_ptrace_access_check(task, mode);
 }
diff --git a/net/socket.c b/net/socket.c
index b94c3dd..e59f906 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -87,6 +87,7 @@
 #include <linux/wireless.h>
 #include <linux/nsproxy.h>
 #include <linux/magic.h>
+#include <linux/sched.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -576,6 +577,12 @@ static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	if (err)
 		return err;
 
+	err = -EPERM;
+	if (sock->sk->sk_family != AF_UNIX &&
+		current->network &&
+		(msg->msg_name != NULL || msg->msg_namelen != 0))
+		return err;
+
 	return sock->ops->sendmsg(iocb, sock, msg, size);
 }
 
@@ -1227,6 +1234,9 @@ static int __sock_create(struct net *net, int family, int type, int protocol,
 	if (err)
 		return err;
 
+	if (family != AF_UNIX && current->network)
+		return -EPERM;
+
 	/*
 	 *	Allocate the socket and allow the family to set things up. if
 	 *	the protocol is 0, the family is instructed to select an appropriate
@@ -1465,19 +1475,29 @@ SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
 	int err, fput_needed;
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
-	if (sock) {
-		err = move_addr_to_kernel(umyaddr, addrlen, (struct sockaddr *)&address);
-		if (err >= 0) {
-			err = security_socket_bind(sock,
-						   (struct sockaddr *)&address,
-						   addrlen);
-			if (!err)
-				err = sock->ops->bind(sock,
-						      (struct sockaddr *)
-						      &address, addrlen);
-		}
-		fput_light(sock->file, fput_needed);
-	}
+	if (!sock)
+		goto out;
+
+	err = move_addr_to_kernel(umyaddr, addrlen, (struct sockaddr *)&address);
+	if (err < 0)
+		goto out_fput;
+
+	err = security_socket_bind(sock,
+				   (struct sockaddr *)&address,
+				   addrlen);
+	if (err)
+		goto out_fput;
+
+	err = (((struct sockaddr *)&address)->sa_family != AF_UNIX &&
+		current->network) ? -EPERM : 0;
+	if (err)
+		goto out_fput;
+
+	err = sock->ops->bind(sock, (struct sockaddr *) &address, addrlen);
+
+out_fput:
+	fput_light(sock->file, fput_needed);
+out:
 	return err;
 }
 
@@ -1639,6 +1659,11 @@ SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
 	if (err)
 		goto out_put;
 
+	err = (((struct sockaddr *)&address)->sa_family != AF_UNIX &&
+		current->network) ? -EPERM : 0;
+	if (err)
+		goto out_put;
+
 	err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen,
 				 sock->file->f_flags);
 out_put:
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index f255119..2d984a9 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -797,6 +797,10 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	addr_len = err;
 
+	err = (current->network && !sunaddr->sun_path[0]) ? -EPERM : 0;
+	if (err)
+		goto out;
+
 	mutex_lock(&u->readlock);
 
 	err = -EINVAL;
@@ -934,6 +938,10 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
 			goto out;
 		alen = err;
 
+		err = (current->network && !sunaddr->sun_path[0]) ? -EPERM : 0;
+		if (err)
+			goto out;
+
 		if (test_bit(SOCK_PASSCRED, &sock->flags) &&
 		    !unix_sk(sk)->addr && (err = unix_autobind(sock)) != 0)
 			goto out;
@@ -1033,6 +1041,10 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		goto out;
 	addr_len = err;
 
+	err = (current->network && !sunaddr->sun_path[0]) ? -EPERM : 0;
+	if (err)
+		goto out;
+
 	if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr &&
 	    (err = unix_autobind(sock)) != 0)
 		goto out;
@@ -1370,6 +1382,10 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		if (err < 0)
 			goto out;
 		namelen = err;
+
+		err = -EPERM;
+		if (current->network && !sunaddr->sun_path[0])
+			goto out;
 	} else {
 		sunaddr = NULL;
 		err = -ENOTCONN;
@@ -1520,6 +1536,9 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (msg->msg_namelen) {
 		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
 		goto out_err;
+		/* prctl(PR_SET_NETWORK) requires no change here since
+		 * connection-less unix stream sockets are not supported.
+		 * See Documentation/prctl_network.txt for details. */
 	} else {
 		sunaddr = NULL;
 		err = -ENOTCONN;
-- 
1.5.6.5

Re: [PATCH] Security: Implement prctl(PR_SET_NETWORK, PR_NETWORK_OFF) semantics.

[Eric W. Biederman]

Michael Stone <michael@laptop.org> writes:

> diff --git a/kernel/ptrace.c b/kernel/ptrace.c
> index 23bd09c..5b38db0 100644
> --- a/kernel/ptrace.c
> +++ b/kernel/ptrace.c
> @@ -151,6 +151,8 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
>  		dumpable = get_dumpable(task->mm);
>  	if (!dumpable && !capable(CAP_SYS_PTRACE))
>  		return -EPERM;
> +	if (current->network)
> +		return -EPERM;

The principle should be: you gain no privileges by ptracing.
Therefore this check should be:

	if (current->network && !task->network)
		return -EPERM;

Which keeps the ptrace logic from being a larger hammer than it needs
to be.

Eric

[PATCH] Security: Document prctl(PR_{GET,SET}_NETWORK).

[Michael Stone]

Explain the purpose, interface, and semantics of the
prctl(PR_{GET,SET}_network) facility.

Also reference some example userland clients.

Signed-off-by: Michael Stone <michael@laptop.org>
---
 Documentation/prctl_network.txt |   69 +++++++++++++++++++++++++++++++++++++++
 1 files changed, 69 insertions(+), 0 deletions(-)
 create mode 100644 Documentation/prctl_network.txt

diff --git a/Documentation/prctl_network.txt b/Documentation/prctl_network.txt
new file mode 100644
index 0000000..bcf2f72
--- /dev/null
+++ b/Documentation/prctl_network.txt
@@ -0,0 +1,69 @@
+Purpose
+-------
+
+Daniel Bernstein has observed [1] that security-conscious userland processes
+may benefit from the ability to irrevocably remove their ability to create,
+bind, connect to, or send messages except in the case of previously connected
+sockets or AF_UNIX filesystem sockets.
+
+This facility is particularly attractive to security platforms like OLPC
+Bitfrost [2] and to isolation programs like Rainbow [3] and Plash [4] because:
+
+  * it integrates well with standard techniques for writing privilege-separated
+    Unix programs
+
+  * it integrates well with the need to perform limited socket I/O, e.g., when
+    running X clients
+
+  * it's available to unprivileged programs
+
+  * it's a discretionary feature available to all of distributors,
+    administrators, authors, and users
+
+  * its effect is entirely local, rather than global (like netfilter)
+
+  * it's simple enough to have some hope of being used correctly
+
+Implementation
+--------------
+
+After considering implementations based on the Linux Security Module (LSM)
+framework, on SELinux in particular, on network namespaces (CLONE_NEWNET), and
+on direct modification of the kernel syscall and task_struct APIs, we came to
+the conclusion that the best way to implement this feature was to extend the
+prctl() framework with a new pair of options named PR_{GET,SET}_NETWORK. These
+options cause prctl() to read or modify "current->network".
+
+Semantics
+---------
+
+current->network is a flags field which is preserved across all variants of
+fork() and exec().
+
+Writes which attempt to clear bits in current->network return -EPERM.
+
+The default value for current->network is named PR_NETWORK_OFF and is defined
+to be 0.
+
+Presently, only one flag is defined: PR_NETWORK_OFF.
+
+More flags may be defined in the future if they become needed.
+
+Attempts to set undefined flags result in -EINVAL.
+
+When PR_NETWORK_OFF is set, implementations of syscalls which may be used by
+the current process to perform autonomous networking will return -EPERM. For
+example, calls to socket(), bind(), connect(), sendmsg(), and ptrace() will
+return -EPERM except for cases we are manipulating an AF_UNIX socket whose name
+does not begin with \0 or, in the case of sendmsg(), unless we are manipulating
+a previously connected socket, i.e. one with
+
+  msg.msg_name == NULL && msg.msg_namelen == 0.
+
+References
+----------
+
+[1]: http://cr.yp.to/unix/disablenetwork.html
+[2]: http://wiki.laptop.org/go/OLPC_Bitfrost
+[3]: http://wiki.laptop.org/go/Rainbow
+[4]: http://plash.beasts.org/
-- 
1.5.6.5