Move auto-generated 'bindings' to a separate inner module.

Re-export only things that are used by other modules.

In the future, I'm imagining that we run bindgen twice, for Postgres
v14 and v15. The two sets of bindings would go into separate
'bindings_v14' and 'bindings_v15' modules.

Rearrange postgres_ffi modules.

Move function, to avoid Postgres version dependency in timelines.rs
Move function to generate a logical-message WAL record to postgres_ffi.

libs/postgres_ffi/src/controlfile_utils.rs

@@ -23,7 +23,7 @@
 //! information. You can use PostgreSQL's pg_controldata utility to view its
 //! contents.
 //!
-use crate::{ControlFileData, PG_CONTROL_FILE_SIZE};
+use super::bindings::{ControlFileData, PG_CONTROL_FILE_SIZE};
 
 use anyhow::{bail, Result};
 use bytes::{Bytes, BytesMut};

libs/postgres_ffi/src/lib.rs

@@ -7,21 +7,62 @@
 // https://github.com/rust-lang/rust-bindgen/issues/1651
 #![allow(deref_nullptr)]
 
-use serde::{Deserialize, Serialize};
 use utils::lsn::Lsn;
 
-include!(concat!(env!("OUT_DIR"), "/bindings.rs"));
+macro_rules! postgres_ffi {
+    ($version:ident) => {
+        #[path = "."]
+        pub mod $version {
+            // fixme: does this have to be 'pub'?
+            pub mod bindings {
+                // bindgen generates bindings for a lot of stuff we don't need
+                #![allow(dead_code)]
 
-pub mod controlfile_utils;
-pub mod nonrelfile_utils;
-pub mod pg_constants;
-pub mod relfile_utils;
-pub mod waldecoder;
-pub mod xlog_utils;
+                use serde::{Deserialize, Serialize};
+                include!(concat!(env!("OUT_DIR"), "/bindings.rs"));
+            }
+            pub mod controlfile_utils;
+            pub mod nonrelfile_utils;
+            pub mod pg_constants;
+            pub mod relfile_utils;
+            pub mod waldecoder;
+            pub mod xlog_utils;
+
+            // Re-export some symbols from bindings
+            pub use bindings::DBState_DB_SHUTDOWNED;
+            pub use bindings::{CheckPoint, ControlFileData, XLogRecord};
+        }
+    };
+}
+
+postgres_ffi!(v14);
+
+// Export some widely used datatypes that are unlikely to change across Postgres versions
+pub use v14::bindings::{uint32, uint64, Oid};
+pub use v14::bindings::{BlockNumber, OffsetNumber};
+pub use v14::bindings::{MultiXactId, TransactionId};
+
+// Likewise for these, although the assumption that these don't change is a little more iffy.
+pub use v14::bindings::{MultiXactOffset, MultiXactStatus};
+
+// from pg_config.h. These can be changed with configure options --with-blocksize=BLOCKSIZE and
+// --with-segsize=SEGSIZE, but assume the defaults for now.
+pub const BLCKSZ: u16 = 8192;
+pub const RELSEG_SIZE: u32 = 1024 * 1024 * 1024 / (BLCKSZ as u32);
+pub const XLOG_BLCKSZ: usize = 8192;
+
+// PG timeline is always 1, changing it doesn't have any useful meaning in Neon.
+//
+// NOTE: this is not to be confused with Neon timelines; different concept!
+//
+// It's a shaky assumption, that it's always 1. We might import a
+// PostgreSQL data directory that has gone through timeline bumps,
+// for example. FIXME later.
+pub const PG_TLI: u32 = 1;
 
 //  See TransactionIdIsNormal in transam.h
 pub const fn transaction_id_is_normal(id: TransactionId) -> bool {
-    id > pg_constants::FIRST_NORMAL_TRANSACTION_ID
+    id > v14::pg_constants::FIRST_NORMAL_TRANSACTION_ID
 }
 
 // See TransactionIdPrecedes in transam.c

libs/postgres_ffi/src/nonrelfile_utils.rs

@@ -1,11 +1,12 @@
 //!
 //! Common utilities for dealing with PostgreSQL non-relation files.
 //!
-use crate::{pg_constants, transaction_id_precedes};
+use crate::transaction_id_precedes;
+use super::pg_constants;
 use bytes::BytesMut;
 use log::*;
 
-use crate::MultiXactId;
+use super::bindings::MultiXactId;
 
 pub fn transaction_id_set_status(xid: u32, status: u8, page: &mut BytesMut) {
     trace!(

libs/postgres_ffi/src/pg_constants.rs

@@ -7,7 +7,8 @@
 //! comments on them.
 //!
 
-use crate::PageHeaderData;
+use super::bindings::PageHeaderData;
+use crate::BLCKSZ;
 
 //
 // From pg_tablespace_d.h
@@ -31,11 +32,6 @@ pub const SMGR_TRUNCATE_HEAP: u32 = 0x0001;
 pub const SMGR_TRUNCATE_VM: u32 = 0x0002;
 pub const SMGR_TRUNCATE_FSM: u32 = 0x0004;
 
-// from pg_config.h. These can be changed with configure options --with-blocksize=BLOCKSIZE and
-// --with-segsize=SEGSIZE, but assume the defaults for now.
-pub const BLCKSZ: u16 = 8192;
-pub const RELSEG_SIZE: u32 = 1024 * 1024 * 1024 / (BLCKSZ as u32);
-
 //
 // From bufpage.h
 //
@@ -213,7 +209,6 @@ pub const FIRST_NORMAL_OBJECT_ID: u32 = 16384;
 /* FIXME: pageserver should request wal_seg_size from compute node */
 pub const WAL_SEGMENT_SIZE: usize = 16 * 1024 * 1024;
 
-pub const XLOG_BLCKSZ: usize = 8192;
 pub const XLOG_CHECKPOINT_SHUTDOWN: u8 = 0x00;
 pub const XLOG_CHECKPOINT_ONLINE: u8 = 0x10;
 pub const XLP_LONG_HEADER: u16 = 0x0002;

libs/postgres_ffi/src/relfile_utils.rs

@@ -1,7 +1,7 @@
 //!
 //! Common utilities for dealing with PostgreSQL relation files.
 //!
-use crate::pg_constants;
+use super::pg_constants;
 use once_cell::sync::OnceCell;
 use regex::Regex;
 

libs/postgres_ffi/src/waldecoder.rs

@@ -10,10 +10,7 @@
 //!
 use super::pg_constants;
 use super::xlog_utils::*;
-use super::XLogLongPageHeaderData;
-use super::XLogPageHeaderData;
-use super::XLogRecord;
-use super::XLOG_PAGE_MAGIC;
+use super::bindings::{XLogLongPageHeaderData, XLogPageHeaderData, XLogRecord, XLOG_PAGE_MAGIC};
 use bytes::{Buf, BufMut, Bytes, BytesMut};
 use crc32c::*;
 use log::*;

libs/postgres_ffi/src/xlog_utils.rs

@@ -7,22 +7,24 @@
 // have been named the same as the corresponding PostgreSQL functions instead.
 //
 
-use crate::pg_constants;
-use crate::CheckPoint;
-use crate::FullTransactionId;
-use crate::XLogLongPageHeaderData;
-use crate::XLogPageHeaderData;
-use crate::XLogRecord;
-use crate::XLOG_PAGE_MAGIC;
+use crc32c::crc32c_append;
 
-use crate::pg_constants::WAL_SEGMENT_SIZE;
-use crate::waldecoder::WalStreamDecoder;
+use super::bindings::{
+    CheckPoint, FullTransactionId, XLogLongPageHeaderData, XLogPageHeaderData, XLogRecord,
+    XLOG_PAGE_MAGIC,
+};
+use super::pg_constants;
+use super::pg_constants::WAL_SEGMENT_SIZE;
+use crate::v14::waldecoder::WalStreamDecoder;
+use crate::PG_TLI;
+use crate::{uint32, uint64, Oid};
 
 use bytes::BytesMut;
 use bytes::{Buf, Bytes};
 
 use log::*;
 
+use serde::Serialize;
 use std::fs::File;
 use std::io::prelude::*;
 use std::io::ErrorKind;
@@ -47,9 +49,6 @@ pub const XLOG_SIZE_OF_XLOG_RECORD: usize = std::mem::size_of::<XLogRecord>();
 #[allow(clippy::identity_op)]
 pub const SIZE_OF_XLOG_RECORD_DATA_HEADER_SHORT: usize = 1 * 2;
 
-// PG timeline is always 1, changing it doesn't have useful meaning in Zenith.
-pub const PG_TLI: u32 = 1;
-
 pub type XLogRecPtr = u64;
 pub type TimeLineID = u32;
 pub type TimestampTz = i64;
@@ -346,6 +345,85 @@ pub fn generate_wal_segment(segno: u64, system_id: u64) -> Result<Bytes, Seriali
     Ok(seg_buf.freeze())
 }
 
+#[repr(C)]
+#[derive(Serialize)]
+struct XlLogicalMessage {
+    db_id: Oid,
+    transactional: uint32, // bool, takes 4 bytes due to alignment in C structures
+    prefix_size: uint64,
+    message_size: uint64,
+}
+
+impl XlLogicalMessage {
+    pub fn encode(&self) -> Bytes {
+        use utils::bin_ser::LeSer;
+        self.ser().unwrap().into()
+    }
+}
+
+/// Create new WAL record for non-transactional logical message.
+/// Used for creating artificial WAL for tests, as LogicalMessage
+/// record is basically no-op.
+///
+/// NOTE: This leaves the xl_prev field zero. The safekeeper and
+/// pageserver tolerate that, but PostgreSQL does not.
+pub fn encode_logical_message(prefix: &str, message: &str) -> Vec<u8> {
+    let mut prefix_bytes: Vec<u8> = Vec::with_capacity(prefix.len() + 1);
+    prefix_bytes.write_all(prefix.as_bytes()).unwrap();
+    prefix_bytes.push(0);
+
+    let message_bytes = message.as_bytes();
+
+    let logical_message = XlLogicalMessage {
+        db_id: 0,
+        transactional: 0,
+        prefix_size: prefix_bytes.len() as u64,
+        message_size: message_bytes.len() as u64,
+    };
+
+    let mainrdata = logical_message.encode();
+    let mainrdata_len: usize = mainrdata.len() + prefix_bytes.len() + message_bytes.len();
+    // only short mainrdata is supported for now
+    assert!(mainrdata_len <= 255);
+    let mainrdata_len = mainrdata_len as u8;
+
+    let mut data: Vec<u8> = vec![pg_constants::XLR_BLOCK_ID_DATA_SHORT, mainrdata_len];
+    data.extend_from_slice(&mainrdata);
+    data.extend_from_slice(&prefix_bytes);
+    data.extend_from_slice(message_bytes);
+
+    let total_len = XLOG_SIZE_OF_XLOG_RECORD + data.len();
+
+    let mut header = XLogRecord {
+        xl_tot_len: total_len as u32,
+        xl_xid: 0,
+        xl_prev: 0,
+        xl_info: 0,
+        xl_rmid: 21,
+        __bindgen_padding_0: [0u8; 2usize],
+        xl_crc: 0, // crc will be calculated later
+    };
+
+    let header_bytes = header.encode().expect("failed to encode header");
+    let crc = crc32c_append(0, &data);
+    let crc = crc32c_append(crc, &header_bytes[0..XLOG_RECORD_CRC_OFFS]);
+    header.xl_crc = crc;
+
+    let mut wal: Vec<u8> = Vec::new();
+    wal.extend_from_slice(&header.encode().expect("failed to encode header"));
+    wal.extend_from_slice(&data);
+
+    // WAL start position must be aligned at 8 bytes,
+    // this will add padding for the next WAL record.
+    const PADDING: usize = 8;
+    let padding_rem = wal.len() % PADDING;
+    if padding_rem != 0 {
+        wal.resize(wal.len() + PADDING - padding_rem, 0);
+    }
+
+    wal
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -547,4 +625,15 @@ mod tests {
         checkpoint.update_next_xid(1024);
         assert_eq!(checkpoint.nextXid.value, 2048);
     }
+
+    #[test]
+    pub fn test_encode_logical_message() {
+        let expected = [
+            64, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21, 0, 0, 170, 34, 166, 227, 255,
+            38, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 112, 114,
+            101, 102, 105, 120, 0, 109, 101, 115, 115, 97, 103, 101,
+        ];
+        let actual = encode_logical_message("prefix", "message");
+        assert_eq!(expected, actual[..]);
+    }
 }