pgsql: Fix issue with reading zero bytes in Gzip_read.

From: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
To: pgsql-committers(at)lists(dot)postgresql(dot)org
Subject: pgsql: Fix issue with reading zero bytes in Gzip_read.
Date: 2025-10-13 16:44:30
Message-ID: E1v8Lew-001W7n-31@gemulon.postgresql.org
Views: Whole Thread | Raw Message | Download mbox | Resend email
Thread:
Lists: pgsql-committers

Fix issue with reading zero bytes in Gzip_read.

pg_dump expects a read request of zero bytes to be a no-op; see for
example ReadStr(). Gzip_read got this wrong and falsely supposed
that the resulting gzret == 0 indicated an error. We could complicate
that error-checking logic some more, but it seems best to just fall
out immediately when passed size == 0.

This bug breaks the nominally-supported case of manually gzip'ing
the toc.dat file within a directory-style dump, so back-patch to v16
where this code came in. (Prior branches already have a short-circuit
for size == 0 before their only gzread call.)

Author: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
Reviewed-by: Chao Li <li(dot)evan(dot)chao(at)gmail(dot)com>
Discussion: https://postgr.es/m/3515357.1760128017@sss.pgh.pa.us
Backpatch-through: 16

Branch
------
REL_17_STABLE

Details
-------
https://git.postgresql.org/pg/commitdiff/bf18e9bd70decd294a9be517cb5b3a260ccfdd15

Modified Files
--------------
src/bin/pg_dump/compress_gzip.c | 4 ++++
1 file changed, 4 insertions(+)

Browse pgsql-committers by date

  From Date Subject
Next Message Tom Lane 2025-10-13 17:01:54 pgsql: Fix poor buffering logic in pg_dump's lz4 and zstd compression c
Previous Message Magnus Hagander 2025-10-13 13:33:37 pgsql: docs: Fix protocol version 3.2 message format of CancelRequest