From: David Rowley <drowley@postgresql.org>
To: pgsql-committers@lists.postgresql.org
Subject: pgsql: Teach MSVC that elog/ereport ERROR doesn't return
Date: Sat, 27 Sep 2025 10:41:31 +0000
Message-ID: <E1v2SMt-000Jjy-0z@gemulon.postgresql.org> (raw)
Teach MSVC that elog/ereport ERROR doesn't return
It had always been intended that this already works correctly as
pg_unreachable() uses __assume(0) on MSVC, and that directs the compiler
in a way so it knows that a given function won't return. However, with
ereport_domain(), it didn't work...
It's now understood that the failure to determine that elog(ERROR) does not
return comes from the inability of the MSVC compiler to detect the "const
int elevel_" is the same as the "elevel" macro parameter. MSVC seems to be
unable to make the "if (elevel_ >= ERROR) branch constantly-true when the
macro is used with any elevel >= ERROR, therefore the pg_unreachable() is
seen to only be present in a *conditional* branch rather than present
*unconditionally*.
While there seems to be no way to force the compiler into knowing that
elevel_ is equal to elevel within the ereport_domain() macro, there is a
way in C11 to determine if the elevel parameter is a compile-time
constant or not. This is done via some hackery using the _Generic()
intrinsic function, which gives us functionality similar to GCC's
__builtin_constant_p(), albeit only for integers.
Here we define pg_builtin_integer_constant_p() for this purpose.
Callers can check for availability via HAVE_PG_BUILTIN_INTEGER_CONSTANT_P.
ereport_domain() has been adjusted to use
pg_builtin_integer_constant_p() instead of __builtin_constant_p().
It's not quite clear at this stage if this now allows us to forego doing
the likes of "return NULL; /* keep compiler quiet */" as there may be other
compilers in use that have similar struggles. It's just a matter of time
before someone commits a function that does not "return" a value after
an elog(ERROR). Let's make time and lack of complaints about said commit
be the judge of if we need to continue the "/* keep compiler quiet */"
palaver.
Author: David Rowley <drowleyml@gmail.com>
Reviewed-by: Peter Eisentraut <peter@eisentraut.org>
Discussion: https://postgr.es/m/CAApHDvom02B_XNVSkvxznVUyZbjGAR+5myA89ZcbEd3=PA9UcA@mail.gmail.com
Branch
------
master
Details
-------
https://git.postgresql.org/pg/commitdiff/59c2f03d1ece7b9b215751a508b3a84728419246
Modified Files
--------------
src/include/c.h | 27 +++++++++++++++++++++++++++
src/include/utils/elog.h | 35 ++++++++++++++++++-----------------
2 files changed, 45 insertions(+), 17 deletions(-)
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: pgsql-committers@postgresql.org
Cc: drowley@postgresql.org, pgsql-committers@lists.postgresql.org
Subject: Re: pgsql: Teach MSVC that elog/ereport ERROR doesn't return
In-Reply-To: <E1v2SMt-000Jjy-0z@gemulon.postgresql.org>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox