pgsql: libpq: Correct processing of startup response messages

From: Peter Eisentraut <peter(at)eisentraut(dot)org>
To: pgsql-committers(at)lists(dot)postgresql(dot)org
Subject: pgsql: libpq: Correct processing of startup response messages
Date: 2022-11-17 13:40:18
Message-ID: E1ovf7q-000bXS-1z@gemulon.postgresql.org
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-committers

libpq: Correct processing of startup response messages

After sending a startup message, libpq expects either an error
response ('E') or an authentication request ('R'). Before processing
the message, it ensures it has read enough bytes to correspond to the
length specified in the message. However, when processing the 'R'
message, if an EOF status is returned it loops back waiting for more
input, even though we already checked that we have enough input. In
this particular case, this is probably not reachable anyway, because
other code ensures we have enough bytes for an authentication request
message, but the code is wrong and misleading. In the more general
case, processing a faulty message could result in an EOF status, which
would then result in an infinite loop waiting for the end of a message
that will never come. The correction is to make this an error.

Reported-by: Jacob Champion <jchampion(at)timescale(dot)com>
Discussion: https://www.postgresql.org/message-id/flat/f9c7862f-b864-8ef7-a861-c4638c83e209(at)enterprisedb(dot)com

Branch
------
master

Details
-------
https://git.postgresql.org/pg/commitdiff/dce92e59b1a9ff8401a660a1ac448ea37d498284

Modified Files
--------------
src/interfaces/libpq/fe-connect.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)

Browse pgsql-committers by date

  From Date Subject
Next Message Peter Eisentraut 2022-11-17 14:47:56 pgsql: libpq: Handle NegotiateProtocolVersion message
Previous Message Daniel Gustafsson 2022-11-17 12:18:09 pgsql: Fix wording in comment