Remove race conditions between ECPGdebug() and ecpg_log().
Coverity complains that ECPGdebug is accessing debugstream without
holding debug_mutex, which is a fair complaint: we should take
debug_mutex while changing the settings ecpg_log looks at.
In some branches it also complains about unlocked use of simple_debug.
I think it's intentional and safe to have a quick unlocked check of
simple_debug at the start of ecpg_log, since that early exit will
always be taken in non-debug cases. But we should recheck
simple_debug after acquiring the mutex. In the worst case, calling
ECPGdebug concurrently with ecpg_log in another thread could result
in a null-pointer dereference due to debugstream transiently being
NULL while simple_debug isn't 0.
This is largely hypothetical, since it's unlikely anybody uses
ECPGdebug() at all in the field, and our own regression tests
don't seem to be hitting the theoretical race conditions either.
Still, if we're going to the trouble of having mutexes here, we ought
to be using them in a way that's actually safe not just almost safe.
Hence, back-patch to all supported branches.
Branch
------
master
Details
-------
https://git.postgresql.org/pg/commitdiff/0162a9bde267a0dc88f35a8d286514c059e1e0e2
Modified Files
--------------
src/interfaces/ecpg/ecpglib/misc.c | 39 +++++++++++++++++++++++++++-----------
1 file changed, 28 insertions(+), 11 deletions(-)