pgsql: oauth: Disallow OAuth connections via postgres_fdw/dblink

From: Jacob Champion <jchampion(at)postgresql(dot)org>
To: pgsql-committers(at)lists(dot)postgresql(dot)org
Subject: pgsql: oauth: Disallow OAuth connections via postgres_fdw/dblink
Date: 2025-04-29 20:23:24
Message-ID: E1u9rUC-000D6N-0R@gemulon.postgresql.org
Views: Whole Thread | Raw Message | Download mbox | Resend email
Thread:
Lists: pgsql-committers

oauth: Disallow OAuth connections via postgres_fdw/dblink

A subsequent commit will reclassify oauth_client_secret from dispchar=""
to dispchar="*", so that UIs will treat it like a secret. For our FDWs,
this change will move that option from SERVER to USER MAPPING, which we
need to avoid.

But upon further discussion, we don't really want our FDWs to use our
builtin Device Authorization flow at all, for several reasons:

- the URL and code would be printed to the server logs, not sent over
the client connection
- tokens are not cached/refreshed, so every single connection has to be
manually authorized by a user with a browser
- oauth_client_secret needs to belong to the foreign server, but options
on SERVER are publicly accessible
- all non-superusers would need password_required=false, which is
dangerous

Future OAuth work can use FDWs as a motivating use case. But for now,
disallow all oauth_* connection options for these two extensions.

Reviewed-by: Noah Misch <noah(at)leadboat(dot)com>
Discussion: https://postgr.es/m/20250415191435.55.nmisch%40google.com

Branch
------
master

Details
-------
https://git.postgresql.org/pg/commitdiff/d2e7d2a09d7d17656418f8c859074db690af19ec

Modified Files
--------------
contrib/dblink/dblink.c | 7 +++++++
contrib/dblink/expected/dblink.out | 11 +++++++++++
contrib/dblink/sql/dblink.sql | 8 ++++++++
contrib/postgres_fdw/expected/postgres_fdw.out | 11 +++++++++++
contrib/postgres_fdw/option.c | 7 +++++++
contrib/postgres_fdw/sql/postgres_fdw.sql | 8 ++++++++
6 files changed, 52 insertions(+)

Browse pgsql-committers by date

  From Date Subject
Next Message Tom Lane 2025-04-29 21:27:58 pgsql: Give up on running with NetBSD/OpenBSD's default semaphore setti
Previous Message Peter Eisentraut 2025-04-29 17:19:10 pgsql: Fix whitespace typo in string