diff options
author | Tom Lane | 2025-07-08 21:00:34 +0000 |
---|---|---|
committer | Tom Lane | 2025-07-08 21:00:34 +0000 |
commit | 93001888d85c21a5b9ab1fe8dabfecb673fc007c (patch) | |
tree | ca5dc2c37b5664bd945649af174c243d7135ab09 /contrib/earthdistance/meson.build | |
parent | e03c95287764158941d317972a332565729b6af2 (diff) |
What we want in these places is "xmlChar *volatile ptr",
not "volatile xmlChar *ptr". The former means that the
pointer variable itself needs to be treated as volatile,
while the latter says that what it points to is volatile.
Since the point here is to ensure that the pointer variables
don't go crazy after a longjmp, it's the former semantics
that we need. The misplacement of "volatile" also led
to needing to cast away volatile in some places.
Also fix a number of places where variables that are assigned to
within a PG_TRY and then used after it were not initialized or
not marked as volatile. (A few buildfarm members were issuing
"may be used uninitialized" warnings about some of these variables,
which is what drew my attention to this area.) In most cases
these variables were being set as the last step within the PG_TRY
block, which might mean that we could get away without the "volatile"
marking. But doing that seems unsafe and is definitely not per our
coding conventions.
These problems seem to have come in with 732061150, so no need
for back-patch.
Diffstat (limited to 'contrib/earthdistance/meson.build')
0 files changed, 0 insertions, 0 deletions