Message-ID: <d28cb2c5-4ea8-406d-937a-9e292ebfd5d5@iki.fi>
Date: Thu, 11 Apr 2024 20:07:30 +0300
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: pgsql: Refactor libpq state machine for negotiating encryption
To: Thomas Munro <thomas.munro@gmail.com>
Cc: Heikki Linnakangas <heikki.linnakangas@iki.fi>,
 pgsql-committers@lists.postgresql.org, Tom Lane <tgl@sss.pgh.pa.us>
References: <E1rtdlT-001383-HT@gemulon.postgresql.org>
 <CA+hUKG+HRTtB+x+KKKj_cfX6sNhbeGuqmGxjGMwdVPG7YGFP8w@mail.gmail.com>
 <32196.1712791542@sss.pgh.pa.us>
 <CA+hUKGK5Ku5rH2aXEEcmGZEJmrxOskmk+HK-k2oSduPcgvNVkA@mail.gmail.com>
Content-Language: en-US
From: Heikki Linnakangas <hlinnaka@iki.fi>
In-Reply-To: 
 <CA+hUKGK5Ku5rH2aXEEcmGZEJmrxOskmk+HK-k2oSduPcgvNVkA@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Archived-At: 
 <https://www.postgresql.org/message-id/d28cb2c5-4ea8-406d-937a-9e292ebfd5d5%40iki.fi>
Precedence: bulk

Thanks for the report!

On 11/04/2024 02:33, Thomas Munro wrote:
> On Thu, Apr 11, 2024 at 11:25 AM Tom Lane <tgl@sss.pgh.pa.us> wrote:
>> Thomas Munro <thomas.munro@gmail.com> writes:
>>> If -Dssl=none and -Dgssapi=disabled, compilation of fe-connect.c
>>> fails: call to undeclared function 'encryption_negotiation_failed'.  I
>>> didn't look too hard, but maybe ENABLE_GSS and USE_GSS are confused?
>>
>> For me, configure --with-gssapi fails like that, but the other three
>> combinations of --with-openssl and --with-gssapi compile OK.  I don't
>> find it terribly surprising that the buildfarm isn't covering that
>> combination ...
> 
> Oops, right, correction to my report: it is indeed -Dssl=none
> -Dgssapi=enabled that is broken, not the other combinations.

Yes, I misspelled ENABLE_GSS as USE_GSS.

After fixing that, the new tests are failing; the expected output for 
many of the cases is different when GSSAPI support is not compiled in. I 
think the test tables need to be rearranged some more to take that into 
account, or we will end up with a ridiculous amount of different 
expected outputs.

I will take a closer look at that tomorrow. As a bandaid fix, we could 
temporarily disable the new tests with that combination of configure 
options, it's still better test coverage than not having the tests at 
all. But given that no buildfarm members are testing that combination I 
think it can wait a day.

-- 
Heikki Linnakangas
Neon (https://neon.tech)