aboutsummaryrefslogtreecommitdiff
path: root/src/interfaces
Commit message (Collapse)AuthorAge
* Correctly copy the target host identification in PQcancelCreate.Tom Lane45 hours
| | | | | | | | | | | | | | | PQcancelCreate failed to copy struct pg_conn_host's "type" field, instead leaving it zero (a/k/a CHT_HOST_NAME). This seemingly has no great ill effects if it should have been CHT_UNIX_SOCKET instead, but if it should have been CHT_HOST_ADDRESS then a null-pointer dereference will occur when the cancelConn is used. Bug: #18974 Reported-by: Maxim Boguk <maxim.boguk@gmail.com> Author: Sergei Kornilov <sk@zsrv.org> Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us> Discussion: https://postgr.es/m/18974-575f02b2168b36b3@postgresql.org Backpatch-through: 17
* libpq: Message style improvementsPeter Eisentraut8 days
|
* Fix allocation check to test the right variableDaniel Gustafsson2025-06-17
| | | | | | | | | | The memory allocation for cancelConn->be_cancel_key was accidentally checking the be_cancel_key member in the conn object instead of the one in cancelConn. Author: Ranier Vilela <ranier.vf@gmail.com> Reviewed-by: Daniel Gustafsson <daniel@yesql.se> Discussion: https://postgr.es/m/CAEudQAq4ySDR6dsg9xwurBXwud02hX7XCOZZAcZx-JMn6A06nA@mail.gmail.com
* libpq-oauth: Add exports.list to .gitignorePeter Eisentraut2025-06-16
|
* Don't reduce output request size on non-Unix-socket connections.Tom Lane2025-06-10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Traditionally, libpq's pqPutMsgEnd has rounded down the amount-to-send to be a multiple of 8K when it is eagerly writing some data. This still seems like a good idea when sending through a Unix socket, as pipes typically have a buffer size of 8K or some fraction/multiple of that. But there's not much argument for it on a TCP connection, since (a) standard MTU values are not commensurate with that, and (b) the kernel typically applies its own packet splitting/merging logic. Worse, our SSL and GSSAPI code paths both have API stipulations that if they fail to send all the data that was offered in the previous write attempt, we mustn't offer less data in the next attempt; else we may get "SSL error: bad length" or "GSSAPI caller failed to retransmit all data needing to be retried". The previous write attempt might've been pqFlush attempting to send everything in the buffer, so pqPutMsgEnd can't safely write less than the full buffer contents. (Well, we could add some more state to track exactly how much the previous write attempt was, but there's little value evident in such extra complication.) Hence, apply the round-down only on AF_UNIX sockets, where we never use SSL or GSSAPI. Interestingly, we had a very closely related bug report before, which I attempted to fix in commit d053a879b. But the test case we had then seemingly didn't trigger this pqFlush-then-pqPutMsgEnd scenario, or at least we failed to recognize this variant of the bug. Bug: #18907 Reported-by: Dorjpalam Batbaatar <htgn.dbat.95@gmail.com> Author: Tom Lane <tgl@sss.pgh.pa.us> Discussion: https://postgr.es/m/18907-d41b9bcf6f29edda@postgresql.org Backpatch-through: 13
* Allow larger packets during GSSAPI authentication exchange.Tom Lane2025-05-30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Our GSSAPI code only allows packet sizes up to 16kB. However it emerges that during authentication, larger packets might be needed; various authorities suggest 48kB or 64kB as the maximum packet size. This limitation caused login failure for AD users who belong to many AD groups. To add insult to injury, we gave an unintelligible error message, typically "GSSAPI context establishment error: The routine must be called again to complete its function: Unknown error". As noted in code comments, the 16kB packet limit is effectively a protocol constant once we are doing normal data transmission: the GSSAPI code splits the data stream at those points, and if we change the limit then we will have cross-version compatibility problems due to the receiver's buffer being too small in some combinations. However, during the authentication exchange the packet sizes are not determined by us, but by the underlying GSSAPI library. So we might as well just try to send what the library tells us to. An unpatched recipient will fail on a packet larger than 16kB, but that's not worse than the sender failing without even trying. So this doesn't introduce any meaningful compatibility problem. We still need a buffer size limit, but we can easily make it be 64kB rather than 16kB until transport negotiation is complete. (Larger values were discussed, but don't seem likely to add anything.) Reported-by: Chris Gooch <cgooch@bamfunds.com> Fix-suggested-by: Jacob Champion <jacob.champion@enterprisedb.com> Author: Tom Lane <tgl@sss.pgh.pa.us> Reviewed-by: Jacob Champion <jacob.champion@enterprisedb.com> Discussion: https://postgr.es/m/DS0PR22MB5971A9C8A3F44BCC6293C4DABE99A@DS0PR22MB5971.namprd22.prod.outlook.com Backpatch-through: 13
* oauth: Correct missing comma in Requires.privateJacob Champion2025-05-23
| | | | | | | | | | | | | | | | | | I added libcurl to the Requires.private section of libpq.pc in commit b0635bfda, but I missed that the Autoconf side needs commas added explicitly. Configurations which used both --with-libcurl and --with-openssl ended up with the following entry: Requires.private: libssl, libcrypto libcurl The pkg-config parser appears to be fairly lenient in this case, and accepts the whitespace as an equivalent separator, but let's not rely on that. Add an add_to_list macro (inspired by Makefile.global's add_to_path) to build up the PKG_CONFIG_REQUIRES_PRIVATE list correctly. Reported-by: Wolfgang Walther <walther@technowledgy.de> Reviewed-by: Fabrízio de Royes Mello <fabriziomello@gmail.com> Discussion: https://postgr.es/m/CAOYmi+k2z7Rqj5xiWLUT0+bSXLvdE7TYgS5gCOSqSyXyTSSXiQ@mail.gmail.com
* oauth: Limit JSON parsing depth in the clientJacob Champion2025-05-23
| | | | | | | | | | | | | | Check the ctx->nested level as we go, to prevent a server from running the client out of stack space. The limit we choose when communicating with authorization servers can't be overly strict, since those servers will continue to add extensions in their JSON documents which we need to correctly ignore. For the SASL communication, we can be more conservative, since there are no defined extensions (and the peer is probably more Postgres code). Reviewed-by: Aleksander Alekseev <aleksander@timescale.com> Discussion: https://postgr.es/m/CAOYmi%2Bm71aRUEi0oQE9ciBnBS8xVtMn3CifaPu2kmJzUfhOZgA%40mail.gmail.com
* Fix assorted new memory leaks in libpq.Tom Lane2025-05-22
| | | | | | | | | | | | | | | | | | | | | | Valgrind'ing the postgres_fdw tests showed me that libpq was leaking PGconn.be_cancel_key. It looks like freePGconn is expecting pqDropServerData to release it ... but in a cancel connection object, that doesn't happen. Looking a little closer, I was dismayed to find that freePGconn also missed freeing the pgservice, min_protocol_version, max_protocol_version, sslkeylogfile, scram_client_key_binary, and scram_server_key_binary strings. There's much less excuse for those oversights. Worse, that's from five different commits (a460251f0, 4b99fed75, 285613c60, 2da74d8d6, 761c79508), some of them by extremely senior hackers. Fortunately, all of these are new in v18, so we haven't shipped any leaky versions of libpq. While at it, reorder the operations in freePGconn to match the order of the fields in struct PGconn. Some of those free's seem to have been inserted with the aid of a dartboard.
* Replace deprecated log_connections values in docs and testsMelanie Plageman2025-05-22
| | | | | | | | | | | | | | | | | | | | | | | | | 9219093cab2607f modularized log_connections output to allow more granular control over which aspects of connection establishment are logged. It converted the boolean log_connections GUC into a list of strings and deprecated previously supported boolean-like values on, off, true, false, 1, 0, yes, and no. Those values still work, but they are supported mainly for backwards compatability. As such, documented examples of log_connections should not use these deprecated values. Update references in the docs to deprecated log_connections values. Many of the tests use log_connections. This commit also updates the tests to use the new values of log_connections. In some of the tests, the updated log_connections value covers a narrower set of aspects (e.g. the 'authentication' aspect in the tests in src/test/authentication and the 'receipt' aspect in src/test/postmaster). In other cases, the new value for log_connections is a superset of the previous included aspects (e.g. 'all' in src/test/kerberos/t/001_auth.pl). Reported-by: Peter Eisentraut <peter@eisentraut.org> Author: Melanie Plageman <melanieplageman@gmail.com> Reviewed-by: Peter Eisentraut <peter@eisentraut.org> Reviewed-by: Jacob Champion <jacob.champion@enterprisedb.com> Discussion: https://postgr.es/m/e1586594-3b69-4aea-87ce-73a7488cdc97%40eisentraut.org
* ecpg: Add missing newline in meson.buildMichael Paquier2025-05-19
| | | | | | | Noticed while performing a routine sanity check of the files in the tree. Issue introduced by 28f04984f0c2. Discussion: https://postgr.es/m/CALa6HA4_Wu7-2PV0xv-Q84cT8eG7rTx6bdjUV0Pc=McAwkNMfQ@mail.gmail.com
* Use 'void *' for arbitrary buffers, 'uint8 *' for byte arraysHeikki Linnakangas2025-05-08
| | | | | | | | | | | | | A 'void *' argument suggests that the caller might pass an arbitrary struct, which is appropriate for functions like libc's read/write, or pq_sendbytes(). 'uint8 *' is more appropriate for byte arrays that have no structure, like the cancellation keys or SCRAM tokens. Some places used 'char *', but 'uint8 *' is better because 'char *' is commonly used for null-terminated strings. Change code around SCRAM, MD5 authentication, and cancellation key handling to follow these conventions. Discussion: https://www.postgresql.org/message-id/61be9e31-7b7d-49d5-bc11-721800d89d64@eisentraut.org
* Use more mundane 'int' type for cancel key lengths in libpqHeikki Linnakangas2025-05-08
| | | | | | | | The documented max length of a cancel key is 256 bytes, so it fits in uint8. It nevertheless seems weird to not just use 'int', like in commit 0f1433f053 for the backend. Discussion: https://www.postgresql.org/message-id/61be9e31-7b7d-49d5-bc11-721800d89d64%40eisentraut.org
* With GB18030, prevent SIGSEGV from reading past end of allocation.Noah Misch2025-05-05
| | | | | | | | | | | | | | | | | | | | | With GB18030 as source encoding, applications could crash the server via SQL functions convert() or convert_from(). Applications themselves could crash after passing unterminated GB18030 input to libpq functions PQescapeLiteral(), PQescapeIdentifier(), PQescapeStringConn(), or PQescapeString(). Extension code could crash by passing unterminated GB18030 input to jsonapi.h functions. All those functions have been intended to handle untrusted, unterminated input safely. A crash required allocating the input such that the last byte of the allocation was the last byte of a virtual memory page. Some malloc() implementations take measures against that, making the SIGSEGV hard to reach. Back-patch to v13 (all supported versions). Author: Noah Misch <noah@leadboat.com> Author: Andres Freund <andres@anarazel.de> Reviewed-by: Masahiko Sawada <sawada.mshk@gmail.com> Backpatch-through: 13 Security: CVE-2025-4207
* Translation updatesPeter Eisentraut2025-05-05
| | | | | Source-Git-URL: https://git.postgresql.org/git/pgtranslation/messages.git Source-Git-Hash: f90ee4803c30491e5c49996b973b8a30de47bfb2
* oauth: Correct SSL dependency for libpq-oauth.aJacob Champion2025-05-02
| | | | | | | | | | | libpq-oauth.a includes libpq-int.h, which includes OpenSSL headers. The Autoconf side picks up the necessary include directories via CPPFLAGS, but Meson needs the dependency to be made explicit. Reported-by: Nathan Bossart <nathandbossart@gmail.com> Tested-by: Nathan Bossart <nathandbossart@gmail.com> Tested-by: Tom Lane <tgl@sss.pgh.pa.us> Discussion: https://postgr.es/m/aBTgjDfrdOZmaPgv%40nathan
* oauth: Fix Autoconf build on macOSJacob Champion2025-05-01
| | | | | | | | | Oversight in b0635bfda. -lintl is necessary for gettext on Mac, which libpq-oauth depends on via pgport/pgcommon. (I'd incorrectly removed this change from an earlier version of the patch, where it was suggested by Peter Eisentraut.) Per buildfarm member indri.
* oauth: Move the builtin flow into a separate moduleJacob Champion2025-05-01
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The additional packaging footprint of the OAuth Curl dependency, as well as the existence of libcurl in the address space even if OAuth isn't ever used by a client, has raised some concerns. Split off this dependency into a separate loadable module called libpq-oauth. When configured using --with-libcurl, libpq.so searches for this new module via dlopen(). End users may choose not to install the libpq-oauth module, in which case the default flow is disabled. For static applications using libpq.a, the libpq-oauth staticlib is a mandatory link-time dependency for --with-libcurl builds. libpq.pc has been updated accordingly. The default flow relies on some libpq internals. Some of these can be safely duplicated (such as the SIGPIPE handlers), but others need to be shared between libpq and libpq-oauth for thread-safety. To avoid exporting these internals to all libpq clients forever, these dependencies are instead injected from the libpq side via an initialization function. This also lets libpq communicate the offsets of PGconn struct members to libpq-oauth, so that we can function without crashing if the module on the search path came from a different build of Postgres. (A minor-version upgrade could swap the libpq-oauth module out from under a long-running libpq client before it does its first load of the OAuth flow.) This ABI is considered "private". The module has no SONAME or version symlinks, and it's named libpq-oauth-<major>.so to avoid mixing and matching across Postgres versions. (Future improvements may promote this "OAuth flow plugin" to a first-class concept, at which point we would need a public API to replace this anyway.) Additionally, NLS support for error messages in b3f0be788a was incomplete, because the new error macros weren't being scanned by xgettext. Fix that now. Per request from Tom Lane and Bruce Momjian. Based on an initial patch by Daniel Gustafsson, who also contributed docs changes. The "bare" dlopen() concept came from Thomas Munro. Many people reviewed the design and implementation; thank you! Co-authored-by: Daniel Gustafsson <daniel@yesql.se> Reviewed-by: Andres Freund <andres@anarazel.de> Reviewed-by: Christoph Berg <myon@debian.org> Reviewed-by: Daniel Gustafsson <daniel@yesql.se> Reviewed-by: Jelte Fennema-Nio <postgres@jeltef.nl> Reviewed-by: Peter Eisentraut <peter@eisentraut.org> Reviewed-by: Wolfgang Walther <walther@technowledgy.de> Discussion: https://postgr.es/m/641687.1742360249%40sss.pgh.pa.us
* oauth: Classify oauth_client_secret as a passwordJacob Champion2025-04-29
| | | | | | | | | | | Tell UIs to hide the value of oauth_client_secret, like the other passwords. Due to the previous commit, this does not affect postgres_fdw and dblink, but add a comment to try to warn others of the hazard in the future. Reported-by: Noah Misch <noah@leadboat.com> Reviewed-by: Noah Misch <noah@leadboat.com> Discussion: https://postgr.es/m/20250415191435.55.nmisch%40google.com
* Fix terminology in comment and messagePeter Eisentraut2025-04-25
| | | | Should be "bracket" not "brace" for [].
* Allocate JsonLexContexts on the heap to avoid warningsDaniel Gustafsson2025-04-23
| | | | | | | | | | | | | | The stack allocated JsonLexContexts, in combination with codepaths using goto, were causing warnings when compiling with LTO enabled as the optimizer is unable to figure out that is safe. Rather than contort the code with workarounds for this simply heap allocate the structs instead as these are not in any performance critical paths. Author: Daniel Gustafsson <daniel@yesql.se> Reported-by: Tom Lane <tgl@sss.pgh.pa.us> Reviewed-by: Jacob Champion <jacob.champion@enterprisedb.com> Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us> Discussion: https://postgr.es/m/2074634.1744839761@sss.pgh.pa.us
* Fix a few more duplicate words in commentsDavid Rowley2025-04-21
| | | | | | | | Similar to 84fd3bc14 but these ones were found using a regex that can span multiple lines. Author: David Rowley <dgrowleyml@gmail.com> Discussion: https://postgr.es/m/CAApHDvrMcr8XD107H3NV=WHgyBcu=sx5+7=WArr-n_cWUqdFXQ@mail.gmail.com
* Fix typos and grammar in the codeMichael Paquier2025-04-19
| | | | | | | | The large majority of these have been introduced by recent commits done in the v18 development cycle. Author: Alexander Lakhin <exclusion@gmail.com> Discussion: https://postgr.es/m/9a7763ab-5252-429d-a943-b28941e0e28b@gmail.com
* Fixup various new-to-v18 usages of appendPQExpBufferDavid Rowley2025-04-17
| | | | | | | | Use appendPQExpBufferStr when there are no parameters and appendPQExpBufferChar when the string length is 1. Author: David Rowley <drowleyml@gmail.com> Discussion: https://postgr.es/m/CAApHDvoARMvPeXTTC0HnpARBHn-WgVstc8XFCyMGOzvgu_1HvQ@mail.gmail.com
* Mark sslkeylogfile as Debug optionDaniel Gustafsson2025-04-13
| | | | | | | | | | | Mark the sslkeylogile option as "D" debug as this truly is a debug option, and it will allow postgres_fdw et.al to filter it out as well. Also update the display length to match that for an ssl key as they are both filename based inputs. Author: Daniel Gustafsson <daniel@yesql.se> Reported-by: Jacob Champion <jacob.champion@enterprisedb.com> Discussion: https://postgr.es/m/CAOYmi+=5GyBKpu7bU4D_xkAnYJTj=rMzGaUvHO99-DpNG_YKcw@mail.gmail.com
* libpq: Fix some issues in TAP tests for service filesMichael Paquier2025-04-07
| | | | | | | | | | | | | | | | | | | | | | | The valid service file was not correctly shaped, as append_to_file() was called with an array as input. This is changed so as the parameter and value pairs from the valid connection string are appended to the valid service file one by one. Even with the first issue fixed, the tests should fail. However, they have been passing because all the connection attempts relied on the default values given to PGPORT and PGHOST from the node when using Cluster.pm's connect_ok() and connect_fails(), rather than the data in the service file. The test is updated to use an interesting trick: a dummy node is initialized but not started, and all the connection attempts are done through it. This ensures that the data inside the service file is used for all the connection tests. Note that breaking the contents of the valid service file on purpose makes all the tests that rely on it fail. Issues introduced by 72c2f36d5727. Author: Andrew Jackson <andrewjackson947@gmail.com> Discussion: https://postgr.es/m/CAKK5BkG_6_YSaebM6gG=8EuKaY7_VX1RFgYeySuwFPh8FZY73g@mail.gmail.com
* Quote filename in error messageDaniel Gustafsson2025-04-05
| | | | | | | | | | Project standard is to quote filenames in error and log messages, which commit 2da74d8d640 missed in two error messages. Author: Kyotaro Horiguchi <horikyota.ntt@gmail.com> Reported-by: Kyotaro Horiguchi <horikyota.ntt@gmail.com> Reviewed-by: Daniel Gustafsson <daniel@yesql.se> Discussion: https://postgr.es/m/20250404.120328.103562371975971823.horikyota.ntt@gmail.com
* oauth: Fix build on platforms without epoll/kqueueDaniel Gustafsson2025-04-03
| | | | | | | | | | | | | | register_socket() missed a variable declaration if neither HAVE_SYS_EPOLL_H nor HAVE_SYS_EVENT_H was defined. While we're fixing that, adjust the tests to check pg_config.h for one of the multiplexer implementations, rather than assuming that Windows is the only platform without support. (Christoph reported this on hurd-amd64, an experimental Debian.) Author: Jacob Champion <jacob.champion@enterprisedb.com> Reported-by: Christoph Berg <myon@debian.org> Discussion: https://postgr.es/m/Z-sPFl27Y0ZC-VBl%40msg.df7cb.de
* libpq: Add support for dumping SSL key material to fileDaniel Gustafsson2025-04-03
| | | | | | | | | | | | This adds a new connection parameter which instructs libpq to write out keymaterial clientside into a file in order to make connection debugging with Wireshark and similar tools possible. The file format used is the standardized NSS format. Author: Abhishek Chanda <abhishek.becs@gmail.com> Co-authored-by: Daniel Gustafsson <daniel@yesql.se> Reviewed-by: Jacob Champion <jacob.champion@enterprisedb.com> Discussion: https://postgr.es/m/CAKiP-K85C8uQbzXKWf5wHQPkuygGUGcufke713iHmYWOe9q2dA@mail.gmail.com
* Make cancel request keys longerHeikki Linnakangas2025-04-02
| | | | | | | | | | | | | | | | | | | | | | | Currently, the cancel request key is a 32-bit token, which isn't very much entropy. If you want to cancel another session's query, you can brute-force it. In most environments, an unauthorized cancellation of a query isn't very serious, but it nevertheless would be nice to have more protection from it. Hence make the key longer, to make it harder to guess. The longer cancellation keys are generated when using the new protocol version 3.2. For connections using version 3.0, short 4-bytes keys are still used. The new longer key length is not hardcoded in the protocol anymore, the client is expected to deal with variable length keys, up to 256 bytes. This flexibility allows e.g. a connection pooler to add more information to the cancel key, which might be useful for finding the connection. Reviewed-by: Jelte Fennema-Nio <postgres@jeltef.nl> Reviewed-by: Robert Haas <robertmhaas@gmail.com> (earlier versions) Discussion: https://www.postgresql.org/message-id/508d0505-8b7a-4864-a681-e7e5edfe32aa@iki.fi
* libpq: Add min/max_protocol_version connection optionsHeikki Linnakangas2025-04-02
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | All supported version of the PostgreSQL server send the NegotiateProtocolVersion message when an unsupported minor protocol version is requested by a client. But many other applications that implement the PostgreSQL protocol (connection poolers, or other databases) do not, and the same is true for PostgreSQL server versions older than 9.3. Connecting to such other applications thus fails if a client requests a protocol version different than 3.0. This patch adds a max_protocol_version connection option to libpq that specifies the protocol version that libpq should request from the server. Currently only 3.0 is supported, but that will change in a future commit that bumps the protocol version. Even after that version bump the default will likely stay 3.0 for the time being. Once more of the ecosystem supports the NegotiateProtocolVersion message we might want to change the default to the latest minor version. This also adds the similar min_protocol_version connection option, to allow the client to specify that connecting should fail if a lower protocol version is attempted by the server. This can be used to ensure that certain protocol features are used, which can be particularly useful if those features impact security. Author: Jelte Fennema-Nio <postgres@jeltef.nl> Reviewed-by: Robert Haas <robertmhaas@gmail.com> (earlier versions) Discussion: https://www.postgresql.org/message-id/CAGECzQTfc_O%2BHXqAo5_-xG4r3EFVsTefUeQzSvhEyyLDba-O9w@mail.gmail.com Discussion: https://www.postgresql.org/message-id/CAGECzQRbAGqJnnJJxTdKewTsNOovUt4bsx3NFfofz3m2j-t7tA@mail.gmail.com
* libpq: Handle NegotiateProtocolVersion message differentlyHeikki Linnakangas2025-04-02
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Previously libpq would always error out if the server sends a NegotiateProtocolVersion message. This was fine because libpq only supported a single protocol version and did not support any protocol parameters. But in the upcoming commits, we will introduce a new protocol version and the NegotiateProtocolVersion message starts to actually be used. This patch modifies the client side checks to allow a range of supported protocol versions, instead of only allowing the exact version that was requested. Currently this "range" only contains the 3.0 version, but in a future commit we'll change this. Also clarify the error messages, making them suitable for the world where libpq will support multiple protocol versions and protocol extensions. Note that until the later commits that introduce new protocol version, this change does not have any behavioural effect, because libpq will only request version 3.0 and will never send protocol parameters, and therefore will never receive a NegotiateProtocolVersion message from the server. Author: Jelte Fennema-Nio <postgres@jeltef.nl> Reviewed-by: Robert Haas <robertmhaas@gmail.com> (earlier versions) Discussion: https://www.postgresql.org/message-id/CAGECzQTfc_O%2BHXqAo5_-xG4r3EFVsTefUeQzSvhEyyLDba-O9w@mail.gmail.com Discussion: https://www.postgresql.org/message-id/CAGECzQRbAGqJnnJJxTdKewTsNOovUt4bsx3NFfofz3m2j-t7tA@mail.gmail.com
* Revert "Tidy up locale thread safety in ECPG library."Peter Eisentraut2025-03-28
| | | | | | | | This reverts commit 8e993bff5326b00ced137c837fce7cd1e0ecae14. It causes various build failures on the buildfarm, to be investigated. Discussion: https://postgr.es/m/CWZBBRR6YA8D.8EHMDRGLCKCD%40neon.tech
* Tidy up locale thread safety in ECPG library.Peter Eisentraut2025-03-28
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Remove setlocale() and _configthreadlocal() as fallback strategy on systems that don't have uselocale(), where ECPG tries to control LC_NUMERIC formatting on input and output of floating point numbers. It was probably broken on some systems (NetBSD), and the code was also quite messy and complicated, with obsolete configure tests (Windows). It was also arguably broken, or at least had unstated environmental requirements, if pgtypeslib code was called directly. Instead, introduce PG_C_LOCALE to refer to the "C" locale as a locale_t value. It maps to the special constant LC_C_LOCALE when defined by libc (macOS, NetBSD), or otherwise uses a process-lifetime locale_t that is allocated on first use, just as ECPG previously did itself. The new replacement might be more widely useful. Then change the float parsing and printing code to pass that to _l() functions where appropriate. Unfortunately the portability of those functions is a bit complicated. First, many obvious and useful _l() functions are missing from POSIX, though most standard libraries define some of them anyway. Second, although the thread-safe save/restore technique can be used to replace the missing ones, Windows and NetBSD refused to implement standard uselocale(). They might have a point: "wide scope" uselocale() is hard to combine with other code and error-prone, especially in library code. Luckily they have the _l() functions we want so far anyway. So we have to be prepared for both ways of doing things: 1. In ECPG, use strtod_l() for parsing, and supply a port.h replacement using uselocale() over a limited scope if missing. 2. Inside our own snprintf.c, use three different approaches to format floats. For frontend code, call libc's snprintf_l(), or wrap libc's snprintf() in uselocale() if it's missing. For backend code, snprintf.c can keep assuming that the global locale's LC_NUMERIC is "C" and call libc's snprintf() without change, for now. (It might eventually be possible to call our in-tree Ryū routines to display floats in snprintf.c, given the C-locale-always remit of our in-tree snprintf(), but this patch doesn't risk changing anything that complicated.) Author: Thomas Munro <thomas.munro@gmail.com> Reviewed-by: Peter Eisentraut <peter@eisentraut.org> Reviewed-by: Tristan Partin <tristan@partin.io> Reviewed-by: Heikki Linnakangas <hlinnaka@iki.fi> Discussion: https://postgr.es/m/CWZBBRR6YA8D.8EHMDRGLCKCD%40neon.tech
* libpq: Add TAP tests for service files and namesMichael Paquier2025-03-27
| | | | | | | | | | | | | | | | | | | | | | | | | | | This commit adds a set of regression tests that checks various patterns with service names and service files, with: - Service file with no contents, used as default for PGSERVICEFILE to prevent any lookups at the HOME directory of an environment where the test is run. - Service file with valid service name and its section. - Service file at the root of PGSYSCONFDIR, named pg_service.conf. - Missing service file. - Service name defined as a connection parameter or as PGSERVICE. Note that PGSYSCONFDIR is set to always point at a temporary directory created by the test, so as we never try to look at SYSCONFDIR. This set of tests has come up as a useful independent addition while discussing a patch that adds an equivalent of PGSERVICEFILE as a connection parameter as there have never been any tests for service files and service names. Torsten Foertsch and Ryo Kanbayashi have provided a basic implementation, that I have expanded to what is introduced in this commit. Author: Torsten Foertsch <tfoertsch123@gmail.com> Author: Ryo Kanbayashi <kanbayashi.dev@gmail.com> Author: Michael Paquier <michael@paquier.xyz> Discussion: https://postgr.es/m/CAKkG4_nCjx3a_F3gyXHSPWxD8Sd8URaM89wey7fG_9g7KBkOCQ@mail.gmail.com
* Move GSSAPI includes into its own headerDaniel Gustafsson2025-03-26
| | | | | | | | | | | | | | | | | | | | | | | Due to a conflict in macro names on Windows between <wincrypt.h> and <openssl/ssl.h> these headers need to be included using a predictable pattern with an undef to handle that. The GSSAPI header <gssapi.h> does include <wincrypt.h> which cause problems with compiling PostgreSQL using MSVC when OpenSSL and GSSAPI are both enabled in the tree. Rather than fixing piecemeal for each file including gssapi headers, move the the includes and undef to a new file which should be used to centralize the logic. This patch is a reworked version of a patch by Imran Zaheer proposed earlier in the thread. Once this has proven effective in master we should look at backporting this as the problem exist at least since v16. Author: Daniel Gustafsson <daniel@yesql.se> Co-authored-by: Imran Zaheer <imran.zhir@gmail.com> Reported-by: Dave Page <dpage@pgadmin.org> Reviewed-by: Andres Freund <andres@anarazel.de> Reviewed-by: vignesh C <vignesh21@gmail.com> Discussion: https://postgr.es/m/20240708173204.3f3xjilglx5wuzx6@awork3.anarazel.de
* libpq: Deprecate pg_int64.Thomas Munro2025-03-25
| | | | | | | | | | | | | | | | | | | | | | | Previously we used pg_int64 in three function prototypes in libpq. It was added by commit 461ef73f to expose the platform-dependent type used for int64 in the C89 era. As of commit 962da900 it is defined as standard int64_t, and the dust seems to have settled. Let's just use int64_t directly in these three client-facing functions instead of (yet) another name. We've required C99 and thus <stdint.h> since PostgreSQL 12, C89 and C++98 compilers are long gone, and client applications very likely use standard types for their own 64-bit needs. This also cleans up the obscure placement of a new #include <stdint.h> directive in postgres_ext.h, required for the new definition. The typedef was hiding in there for historical reasons, but it doesn't fit postgres_ext.h's own description of its purpose and there is no evidence of client applications including postgres_ext.h directly to see it. Keep a typedef marked deprecated for backward compatibility, but move it into libpq-fe.h where it was used. Reviewed-by: Peter Eisentraut <peter@eisentraut.org> Discussion: https://postgr.es/m/CA%2BhUKGKn_EkNNGMY5RzMcKP%2Ba6urT4JF%3DCPhw_zHtQwjvX6P2g%40mail.gmail.com
* Fix "make clean" for new TAP suite.Noah Misch2025-03-23
| | | | Commit 28f04984f0c240b76e61f00cd247554fbc850056 missed this.
* Revert workarounds for -Wmissing-braces false positives on old GCCPeter Eisentraut2025-03-20
| | | | | | | | | | | | | | | | | | | | | | | | | | | We have collected several instances of a workaround for GCC bug 53119, which caused false-positive compiler warnings. This bug has long been fixed, but was still seen on the buildfarm, most recently on lapwing with gcc (Debian 4.7.2-5). (The GCC bug tracker mentions that a fix was backported to 4.7.4 and 4.8.3.) That compiler no longer runs warning-free since commit 6fdd5d95634, so we don't need to keep these workarounds. And furthermore, the consensus appears to be that we don't want to keep supporting that era of platform anymore at all. This reverts the following commits: d937904cce6a3d82e4f9c2127de7b59105a134b3 506428d091760650971433f6bc083531c307b368 b449afb582bb9015bfbb85abc10ce122aef9ec70 6392f2a0968c20ecde4d27b6652703ad931fce92 bad0763a4d7be3005eae35d460c73ac4bc7ebaad 5e0c761d0a13c7b4f7c5de618ac38560d74d74d0 and makes a few similar fixes to newer code. Discussion: https://www.postgresql.org/message-id/flat/e170d61f-01ab-4cf9-ab68-91cd1fac62c5%40eisentraut.org Discussion: https://www.postgresql.org/message-id/flat/CA%2BTgmoYEAm-KKZibAP3hSqbTFTjUd47XtVcf3xSFDpyecXX9uQ%40mail.gmail.com
* Fix compiler warning for commit 434dbf69.Thomas Munro2025-03-19
| | | | Reported-by: Tom Lane <tgl@sss.pgh.pa.us>
* oauth: Simplify copy of PGoauthBearerRequestThomas Munro2025-03-19
| | | | | | | | | Follow-up to 03366b61d. Since there are no more const members in the PGoauthBearerRequest struct, the previous memcpy() can be replaced with simple assignment. Author: Jacob Champion <jacob.champion@enterprisedb.com> Discussion: https://postgr.es/m/p4bd7mn6dxr2zdak74abocyltpfdxif4pxqzixqpxpetjwt34h%40qc6jgfmoddvq
* oauth: Fix postcondition for set_timer on macOSThomas Munro2025-03-19
| | | | | | | | | | | | | | On macOS, readding an EVFILT_TIMER to a kqueue does not appear to clear out previously queued timer events, so checks for timer expiration do not work correctly during token retrieval. Switching to IPv4-only communication exposes the problem, because libcurl is no longer clearing out other timeouts related to Happy Eyeballs dual-stack handling. Fully remove and re-register the kqueue timer events during each call to set_timer(), to clear out any stale expirations. Author: Jacob Champion <jacob.champion@enterprisedb.com> Discussion: https://postgr.es/m/CAOYmi%2Bn4EDOOUL27_OqYT2-F2rS6S%2B3mK-ppWb2Ec92UEoUbYA%40mail.gmail.com
* Apply more consistent style for command options in TAP testsMichael Paquier2025-03-17
| | | | | | | | | | | | | | This commit reshapes the grammar of some commands to apply a more consistent style across the board, following rules similar to ce1b0f9da03e: - Elimination of some pointless used-once variables. - Use of long options, to self-document better the options used. - Use of fat commas to link option names and their assigned values, including redirections, so as perltidy can be tricked to put them together. Author: Dagfinn Ilmari Mannsåker <ilmari@ilmari.org> Discussion: https://postgr.es/m/87jz8rzf3h.fsf@wibble.ilmari.org
* pg_noreturn to replace pg_attribute_noreturn()Peter Eisentraut2025-03-13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We want to support a "noreturn" decoration on more compilers besides just GCC-compatible ones, but for that we need to move the decoration in front of the function declaration instead of either behind it or wherever, which is the current style afforded by GCC-style attributes. Also rename the macro to "pg_noreturn" to be similar to the C11 standard "noreturn". pg_noreturn is now supported on all compilers that support C11 (using _Noreturn), as well as GCC-compatible ones (using __attribute__, as before), as well as MSVC (using __declspec). (When PostgreSQL requires C11, the latter two variants can be dropped.) Now, all supported compilers effectively support pg_noreturn, so the extra code for !HAVE_PG_ATTRIBUTE_NORETURN can be dropped. This also fixes a possible problem if third-party code includes stdnoreturn.h, because then the current definition of #define pg_attribute_noreturn() __attribute__((noreturn)) would cause an error. Note that the C standard does not support a noreturn attribute on function pointer types. So we have to drop these here. There are only two instances at this time, so it's not a big loss. In one case, we can make up for it by adding the pg_noreturn to a wrapper function and adding a pg_unreachable(), in the other case, the latter was already done before. Reviewed-by: Dagfinn Ilmari Mannsåker <ilmari@ilmari.org> Reviewed-by: Andres Freund <andres@anarazel.de> Discussion: https://www.postgresql.org/message-id/flat/pxr5b3z7jmkpenssra5zroxi7qzzp6eswuggokw64axmdixpnk@zbwxuq7gbbcw
* Update nls.mk for newly added filePeter Eisentraut2025-03-11
| | | | | Commit f18231e8175 moved some code to a new file, but the new file wasn't added to nls.mk.
* ecpg: Fix compiler warning in ecpg build with Meson.Fujii Masao2025-03-06
| | | | | | | | | | | | | | Previously, Meson could produce a warning about the use of 'deps' in ecpg: WARNING: Project targets '>=0.54' but uses a feature introduced in '0.60.0': list.<plus>. The right-hand operand was not a list. The right-hand operand of 'deps' should be a list. This commit fixes the warning by wrapping it with square brackets. This issue was introduced in commit 28f04984f0c. Author: Jacob Champion <jacob.champion@enterprisedb.com> Discussion: https://postgr.es/m/CAOYmi+ks8wO06Ymxduw2h_eQJ_D4_jHGeyMK0P=p5Q3psnEdMA@mail.gmail.com
* Add .gitignore entry for ecpg test detritus.Tom Lane2025-03-04
| | | | Oversight in commit 28f04984f.
* ecpg: Add TAP test for the ecpg command.Fujii Masao2025-03-04
| | | | | | | | | | | | | | This commit adds a TAP test to verify that the ecpg command correctly detects unsupported or disallowed statements in input files and reports the appropriate error or warning messages. This test helps catch bugs like the one introduced in commit 3d009e45bd, which broke ecpg's handling of unsupported COPY FROM STDIN statements, later fixed by commit 94b914f601b. Author: Ryo Kanbayashi <kanbayashi.dev@gmail.com> Reviewed-by: Fujii Masao <masao.fujii@gmail.com> Discussion: https://postgr.es/m/CANOn0EzoMyxA1m-quDS1UeQUq6FNki6+GGiGucgr9tm2R78rKw@mail.gmail.com
* Work around OAuth/EVFILT_TIMER quirk on NetBSD.Thomas Munro2025-03-01
| | | | | | | | | | | | | | | | | | | | | | | NetBSD's EVFILT_TIMER doesn't like zero timeouts, as introduced by commit b3f0be788. Steal the workaround from the same problem on Linux from a few lines up: round zero up to one. Do this only for NetBSD, as the other systems with the kevent() API accept zero and shouldn't have to insert a small bogus wait. Future improvement ideas: * when NetBSD < 10 falls out of support, we could try NODE_ABSTIME for the "fire now" meaning if timeout == 0 * when libcurl tells us to start a 0ms timer and call it back, we could figure out how to handle that more directly without involving the kernel (the current architecture doesn't make that straightforward) Failures with EINVAL errors could be seen on the new optional NetBSD CI task that we're trying to keep green as a candidate for inclusion as default-enabled CI task. The NetBSD build farm animals aren't testing OAuth yet, so no breakage there. Reviewed-by: Jacob Champion <jacob.champion@enterprisedb.com> Discussion: https://postgr.es/m/CA%2BhUKGJ%2BWyJ26QGvO_nkgvbxgw%2B03U4EQ4Hxw%2BQBft6Np%2BXW7w%40mail.gmail.com
* oauth: Rename macro to avoid collisions on WindowsDaniel Gustafsson2025-02-24
| | | | | | | | | | | | | | | | | | | | | | | | | | Our json parsing defined the macros OPTIONAL and REQUIRED to decorate the structs with for increased readability. This however collides with macros in the <windef.h> header on Windows. ../src/interfaces/libpq/fe-auth-oauth-curl.c:398:9: warning: "OPTIONAL" redefined 398 | #define OPTIONAL false | ^~~~~~~~ In file included from D:/a/_temp/msys64/ucrt64/include/windef.h:9, from D:/a/_temp/msys64/ucrt64/include/windows.h:69, from D:/a/_temp/msys64/ucrt64/include/winsock2.h:23, from ../src/include/port/win32_port.h:60, from ../src/include/port.h:24, from ../src/include/c.h:1331, from ../src/include/postgres_fe.h:28, from ../src/interfaces/libpq/fe-auth-oauth-curl.c:16: include/minwindef.h:65:9: note: this is the location of the previous definition 65 | #define OPTIONAL | ^~~~~~~~ Rename to avoid compilation errors in anticipation of implementing support for Windows. Reported-by: Dave Cramer (on PostgreSQL Hacking Discord)
generated by cgit v1.2.3 (git 2.25.1) at 2025-07-04 16:58:03 +0000