Commit Graph

22 Commits

Author SHA1 Message Date
John Baldwin
4091481652 Fix world by trimming an extra comment terminator. 2001-10-29 19:22:38 +00:00
Nick Sayer
3737d6dfe3 Add Berkeley copyright to SRA.
This is by the kind permission of Dave Safford, formerly of TAMU who wrote the
original code. Here is an excerpt of the e-mail exchange concerning this
issue:

Dave Safford wrote:
>Nick Sayer wrote:
>> Some time ago we spoke about SRA and importing it into FreeBSD. I forgot to
>> ask if you had a prefered license boilerplate for the top of the files. It
>> has come up recently, and the SRA code in FreeBSD doesn't have one.

>I really have no preference - use whatever is most convenient in the
>FreeBSD environment.

>dave safford

This is the standard BSD license with clause 3 removed and clause 4
suitably renumbered.

MFC after:	1 day
2001-10-29 16:12:16 +00:00
Mark Murray
f2ac7de925 Add __FBSDID() to diff-reduce with "base" telnet. 2001-10-01 16:04:55 +00:00
Mark Murray
21f083c0a6 Code merge and diff reduce with "base" telnet. This is the "later"
telnet, so it was treated as the reference code, except where later
commits were made to "base" telnet.
2001-08-20 12:28:40 +00:00
Nick Sayer
9286fd701f Make the PAM user-override actually override the correect thing. 2001-05-17 16:28:11 +00:00
Peter Wemm
d48d5be0d0 Fix the latest telnet breakage. Obviously this was never compiled. 2001-05-17 03:13:00 +00:00
Nick Sayer
166b3cb9a0 Make sure the protocol actively rejects bad data rather than
(potentially) not responding to an invalid SRA 'auth is' message.
2001-05-16 20:24:58 +00:00
Nick Sayer
8183ac8f53 srandomdev() affords us the opportunity to radically improve, and at the
same time simplify, the random number selection code.
2001-05-16 18:32:46 +00:00
Nick Sayer
60f581768d Catch any attempted buffer overflows. The magic numbers in this code
(512) are a little distressing, but the method really needs to be
extended to allow server-supplied DH parameters anyway.

Submitted by:	kris
2001-05-16 18:27:09 +00:00
Nick Sayer
e7157113a9 Catch malloc return failures. This should help avoid dereferencing NULL on
low-memory situations.

Submitted by:	kris
2001-05-16 18:17:55 +00:00
Nick Sayer
c7be24c970 If the uid of the attempted authentication is 0 and if the pty is
insecure, do not succeed. Copied from login.c. This functionality really
should be a PAM module.
2001-05-15 04:47:14 +00:00
Nick Sayer
053c5b3a9e Pointy hat fix -- reapply the SRA PAM patch. To -current this time. 2001-05-07 20:42:02 +00:00
Nick Sayer
989efc86f5 Fix core noted in -stable with 'auth disable SRA'.
I just mistakenly commited this to RELENG_4. I have contacted Jordan to see
about how to fix this. Pass the pointy hat.
2001-03-18 09:44:25 +00:00
Peter Wemm
ecece7e319 Add missing $FreeBSD$ to files that are NOT still on vendor a branch. 2000-07-16 05:48:49 +00:00
Nick Sayer
67bf7a0ac8 Fix 'telnet -X sra' coredump
PR# 19835
2000-07-11 15:04:05 +00:00
Kris Kennaway
19a32101dd Don't call printf with no format string. 2000-07-10 05:16:59 +00:00
Mark Murray
bf4f84d44c Get crypto from libcrypto, not libdes. 2000-02-24 19:28:31 +00:00
Nick Sayer
610fe6066a According to Mark Murray, Makefiles do not belong here. I guess we're
going to have to figure something else out.
1999-08-16 18:59:05 +00:00
Nick Sayer
0f8c8396c5 Add SRA authentication to src/crypto/telnet.
SRA does a Diffie-Hellmen exchange and then DES-encrypts the
authentication data. If the authentication is successful, it also
sets up a session key for DES encryption.

SRA was originally developed at Texas A&M University.

This code is probably export restricted (despite the fact that I
originally found it at a University in Germany).

SRA is not perfect. It is vulnerable to monkey-in-the-middle attacks
and does not use tremendously large DH constants (and thus an individual
exchange probably could be factored in a few days on modern CPU
horsepower). It does not, however, require any changes in user or
administrative behavior and foils session hijacking and sniffing.
The goal of this commit is that telnet and telnetd end up in the DES
distribution and that therefore an encrypted session telnet becomes
standard issue for FreeBSD.
1999-08-16 11:24:29 +00:00
Peter Wemm
8d0a3d19f7 Old stuff laying around: Don't use getstr which can conflict with some
curses/termcap/terminfo implementations and causes recursion.
1998-12-16 06:06:06 +00:00
Mark Murray
04c426cce3 Bring the FreeBSD changes to the virgin sources. 1997-09-07 07:02:53 +00:00
Mark Murray
81cb6ddccd Initial import of BSD telnet. This will be used to build the kerberised
telnet, and after userland diffs have been merged in, will be used to
build the non-kerberised sources as well. (See unifdef(1) for details)
1997-09-04 06:11:16 +00:00