Replace off_t by pgoff_t in I/O routines

PostgreSQL's Windows port has never been able to handle files larger
than 2GB due to the use of off_t for file offsets, only 32-bit on
Windows.  This causes signed integer overflow at exactly 2^31 bytes when
trying to handle files larger than 2GB, for the routines touched by this
commit.

Note that large files are forbidden by ./configure (3c6248a828) and
meson (recent change, see 79cd66f28c).  This restriction also exists
in v16 and older versions for the now-dead MSVC scripts.

The code base already defines pgoff_t as __int64 (64-bit) on Windows for
this purpose, and some function declarations in headers use it, but many
internals still rely on off_t.  This commit switches more routines to
use pgoff_t, offering more portability, for areas mainly related to file
extensions and storage.

These are not critical for WAL segments yet, which have currently a
maximum size allowed of 1GB (well, this opens the door at allowing a
larger size for them).  This matters more for segment files if we want
to lift the large file restriction in ./configure and meson in the
future, which would make sense to remove once/if all traces of off_t are
gone from the tree.  This can additionally matter for out-of-core code
that may want files larger than 2GB in places where off_t is four bytes
in size.

Note that off_t is still used in other parts of the tree like
buffile.c, WAL sender/receiver, base backup, pg_combinebackup, etc.
These other code paths can be addressed separately, and their update
will be required if we want to remove the large file restriction in the
future.  This commit is a good first cut in itself towards more
portability, hopefully.

On Unix-like systems, pgoff_t is defined as off_t, so this change only
affects Windows behavior.

Author: Bryan Green <dbryan.green@gmail.com>
Reviewed-by: Thomas Munro <thomas.munro@gmail.com>
Reviewed-by: Michael Paquier <michael@paquier.xyz>
Discussion: https://postgr.es/m/0f238ff4-c442-42f5-adb8-01b762c94ca1@gmail.com

src/backend/access/transam/xlogreader.c

@@ -1574,7 +1574,7 @@ WALRead(XLogReaderState *state,
 
 		/* Reset errno first; eases reporting non-errno-affecting errors */
 		errno = 0;
-		readbytes = pg_pread(state->seg.ws_file, p, segbytes, (off_t) startoff);
+		readbytes = pg_pread(state->seg.ws_file, p, segbytes, (pgoff_t) startoff);
 
 #ifndef FRONTEND
 		pgstat_report_wait_end();

src/backend/access/transam/xlogrecovery.c

@@ -3429,7 +3429,7 @@ retry:
 	io_start = pgstat_prepare_io_time(track_wal_io_timing);
 
 	pgstat_report_wait_start(WAIT_EVENT_WAL_READ);
-	r = pg_pread(readFile, readBuf, XLOG_BLCKSZ, (off_t) readOff);
+	r = pg_pread(readFile, readBuf, XLOG_BLCKSZ, (pgoff_t) readOff);
 	if (r != XLOG_BLCKSZ)
 	{
 		char		fname[MAXFNAMELEN];

src/backend/replication/walreceiver.c

@@ -928,7 +928,7 @@ XLogWalRcvWrite(char *buf, Size nbytes, XLogRecPtr recptr, TimeLineID tli)
 		start = pgstat_prepare_io_time(track_wal_io_timing);
 
 		pgstat_report_wait_start(WAIT_EVENT_WAL_WRITE);
-		byteswritten = pg_pwrite(recvFile, buf, segbytes, (off_t) startoff);
+		byteswritten = pg_pwrite(recvFile, buf, segbytes, (pgoff_t) startoff);
 		pgstat_report_wait_end();
 
 		pgstat_count_io_op_time(IOOBJECT_WAL, IOCONTEXT_NORMAL,

src/backend/storage/file/fd.c

@@ -201,7 +201,7 @@ typedef struct vfd
 	File		nextFree;		/* link to next free VFD, if in freelist */
 	File		lruMoreRecently;	/* doubly linked recency-of-use list */
 	File		lruLessRecently;
-	off_t		fileSize;		/* current size of file (0 if not temporary) */
+	pgoff_t		fileSize;		/* current size of file (0 if not temporary) */
 	char	   *fileName;		/* name of file, or NULL for unused VFD */
 	/* NB: fileName is malloc'd, and must be free'd when closing the VFD */
 	int			fileFlags;		/* open(2) flags for (re)opening the file */
@@ -519,7 +519,7 @@ pg_file_exists(const char *name)
  * offset of 0 with nbytes 0 means that the entire file should be flushed
  */
 void
-pg_flush_data(int fd, off_t offset, off_t nbytes)
+pg_flush_data(int fd, pgoff_t offset, pgoff_t nbytes)
 {
 	/*
 	 * Right now file flushing is primarily used to avoid making later
@@ -635,7 +635,7 @@ retry:
 		 * may simply not be enough address space.  If so, silently fall
 		 * through to the next implementation.
 		 */
-		if (nbytes <= (off_t) SSIZE_MAX)
+		if (nbytes <= (pgoff_t) SSIZE_MAX)
 			p = mmap(NULL, nbytes, PROT_READ, MAP_SHARED, fd, offset);
 		else
 			p = MAP_FAILED;
@@ -697,7 +697,7 @@ retry:
  * Truncate an open file to a given length.
  */
 static int
-pg_ftruncate(int fd, off_t length)
+pg_ftruncate(int fd, pgoff_t length)
 {
 	int			ret;
 
@@ -714,7 +714,7 @@ retry:
  * Truncate a file to a given length by name.
  */
 int
-pg_truncate(const char *path, off_t length)
+pg_truncate(const char *path, pgoff_t length)
 {
 	int			ret;
 #ifdef WIN32
@@ -1526,7 +1526,7 @@ FileAccess(File file)
  * Called whenever a temporary file is deleted to report its size.
  */
 static void
-ReportTemporaryFileUsage(const char *path, off_t size)
+ReportTemporaryFileUsage(const char *path, pgoff_t size)
 {
 	pgstat_report_tempfile(size);
 
@@ -2077,7 +2077,7 @@ FileClose(File file)
  * this.
  */
 int
-FilePrefetch(File file, off_t offset, off_t amount, uint32 wait_event_info)
+FilePrefetch(File file, pgoff_t offset, pgoff_t amount, uint32 wait_event_info)
 {
 	Assert(FileIsValid(file));
 
@@ -2133,7 +2133,7 @@ retry:
 }
 
 void
-FileWriteback(File file, off_t offset, off_t nbytes, uint32 wait_event_info)
+FileWriteback(File file, pgoff_t offset, pgoff_t nbytes, uint32 wait_event_info)
 {
 	int			returnCode;
 
@@ -2159,7 +2159,7 @@ FileWriteback(File file, off_t offset, off_t nbytes, uint32 wait_event_info)
 }
 
 ssize_t
-FileReadV(File file, const struct iovec *iov, int iovcnt, off_t offset,
+FileReadV(File file, const struct iovec *iov, int iovcnt, pgoff_t offset,
 		  uint32 wait_event_info)
 {
 	ssize_t		returnCode;
@@ -2216,7 +2216,7 @@ retry:
 
 int
 FileStartReadV(PgAioHandle *ioh, File file,
-			   int iovcnt, off_t offset,
+			   int iovcnt, pgoff_t offset,
 			   uint32 wait_event_info)
 {
 	int			returnCode;
@@ -2241,7 +2241,7 @@ FileStartReadV(PgAioHandle *ioh, File file,
 }
 
 ssize_t
-FileWriteV(File file, const struct iovec *iov, int iovcnt, off_t offset,
+FileWriteV(File file, const struct iovec *iov, int iovcnt, pgoff_t offset,
 		   uint32 wait_event_info)
 {
 	ssize_t		returnCode;
@@ -2270,7 +2270,7 @@ FileWriteV(File file, const struct iovec *iov, int iovcnt, off_t offset,
 	 */
 	if (temp_file_limit >= 0 && (vfdP->fdstate & FD_TEMP_FILE_LIMIT))
 	{
-		off_t		past_write = offset;
+		pgoff_t		past_write = offset;
 
 		for (int i = 0; i < iovcnt; ++i)
 			past_write += iov[i].iov_len;
@@ -2309,7 +2309,7 @@ retry:
 		 */
 		if (vfdP->fdstate & FD_TEMP_FILE_LIMIT)
 		{
-			off_t		past_write = offset + returnCode;
+			pgoff_t		past_write = offset + returnCode;
 
 			if (past_write > vfdP->fileSize)
 			{
@@ -2373,7 +2373,7 @@ FileSync(File file, uint32 wait_event_info)
  * appropriate error.
  */
 int
-FileZero(File file, off_t offset, off_t amount, uint32 wait_event_info)
+FileZero(File file, pgoff_t offset, pgoff_t amount, uint32 wait_event_info)
 {
 	int			returnCode;
 	ssize_t		written;
@@ -2418,7 +2418,7 @@ FileZero(File file, off_t offset, off_t amount, uint32 wait_event_info)
  * appropriate error.
  */
 int
-FileFallocate(File file, off_t offset, off_t amount, uint32 wait_event_info)
+FileFallocate(File file, pgoff_t offset, pgoff_t amount, uint32 wait_event_info)
 {
 #ifdef HAVE_POSIX_FALLOCATE
 	int			returnCode;
@@ -2457,7 +2457,7 @@ retry:
 	return FileZero(file, offset, amount, wait_event_info);
 }
 
-off_t
+pgoff_t
 FileSize(File file)
 {
 	Assert(FileIsValid(file));
@@ -2468,14 +2468,14 @@ FileSize(File file)
 	if (FileIsNotOpen(file))
 	{
 		if (FileAccess(file) < 0)
-			return (off_t) -1;
+			return (pgoff_t) -1;
 	}
 
 	return lseek(VfdCache[file].fd, 0, SEEK_END);
 }
 
 int
-FileTruncate(File file, off_t offset, uint32 wait_event_info)
+FileTruncate(File file, pgoff_t offset, uint32 wait_event_info)
 {
 	int			returnCode;
 

src/backend/storage/smgr/md.c

@@ -487,7 +487,7 @@ void
 mdextend(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 		 const void *buffer, bool skipFsync)
 {
-	off_t		seekpos;
+	pgoff_t		seekpos;
 	int			nbytes;
 	MdfdVec    *v;
 
@@ -515,9 +515,9 @@ mdextend(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 
 	v = _mdfd_getseg(reln, forknum, blocknum, skipFsync, EXTENSION_CREATE);
 
-	seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
+	seekpos = (pgoff_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
 
-	Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
+	Assert(seekpos < (pgoff_t) BLCKSZ * RELSEG_SIZE);
 
 	if ((nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, seekpos, WAIT_EVENT_DATA_FILE_EXTEND)) != BLCKSZ)
 	{
@@ -578,7 +578,7 @@ mdzeroextend(SMgrRelation reln, ForkNumber forknum,
 	while (remblocks > 0)
 	{
 		BlockNumber segstartblock = curblocknum % ((BlockNumber) RELSEG_SIZE);
-		off_t		seekpos = (off_t) BLCKSZ * segstartblock;
+		pgoff_t		seekpos = (pgoff_t) BLCKSZ * segstartblock;
 		int			numblocks;
 
 		if (segstartblock + remblocks > RELSEG_SIZE)
@@ -607,7 +607,7 @@ mdzeroextend(SMgrRelation reln, ForkNumber forknum,
 			int			ret;
 
 			ret = FileFallocate(v->mdfd_vfd,
-								seekpos, (off_t) BLCKSZ * numblocks,
+								seekpos, (pgoff_t) BLCKSZ * numblocks,
 								WAIT_EVENT_DATA_FILE_EXTEND);
 			if (ret != 0)
 			{
@@ -630,7 +630,7 @@ mdzeroextend(SMgrRelation reln, ForkNumber forknum,
 			 * whole length of the extension.
 			 */
 			ret = FileZero(v->mdfd_vfd,
-						   seekpos, (off_t) BLCKSZ * numblocks,
+						   seekpos, (pgoff_t) BLCKSZ * numblocks,
 						   WAIT_EVENT_DATA_FILE_EXTEND);
 			if (ret < 0)
 				ereport(ERROR,
@@ -745,7 +745,7 @@ mdprefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 
 	while (nblocks > 0)
 	{
-		off_t		seekpos;
+		pgoff_t		seekpos;
 		MdfdVec    *v;
 		int			nblocks_this_segment;
 
@@ -754,9 +754,9 @@ mdprefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 		if (v == NULL)
 			return false;
 
-		seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
+		seekpos = (pgoff_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
 
-		Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
+		Assert(seekpos < (pgoff_t) BLCKSZ * RELSEG_SIZE);
 
 		nblocks_this_segment =
 			Min(nblocks,
@@ -851,7 +851,7 @@ mdreadv(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 	{
 		struct iovec iov[PG_IOV_MAX];
 		int			iovcnt;
-		off_t		seekpos;
+		pgoff_t		seekpos;
 		int			nbytes;
 		MdfdVec    *v;
 		BlockNumber nblocks_this_segment;
@@ -861,9 +861,9 @@ mdreadv(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 		v = _mdfd_getseg(reln, forknum, blocknum, false,
 						 EXTENSION_FAIL | EXTENSION_CREATE_RECOVERY);
 
-		seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
+		seekpos = (pgoff_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
 
-		Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
+		Assert(seekpos < (pgoff_t) BLCKSZ * RELSEG_SIZE);
 
 		nblocks_this_segment =
 			Min(nblocks,
@@ -986,7 +986,7 @@ mdstartreadv(PgAioHandle *ioh,
 			 SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 			 void **buffers, BlockNumber nblocks)
 {
-	off_t		seekpos;
+	pgoff_t		seekpos;
 	MdfdVec    *v;
 	BlockNumber nblocks_this_segment;
 	struct iovec *iov;
@@ -996,9 +996,9 @@ mdstartreadv(PgAioHandle *ioh,
 	v = _mdfd_getseg(reln, forknum, blocknum, false,
 					 EXTENSION_FAIL | EXTENSION_CREATE_RECOVERY);
 
-	seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
+	seekpos = (pgoff_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
 
-	Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
+	Assert(seekpos < (pgoff_t) BLCKSZ * RELSEG_SIZE);
 
 	nblocks_this_segment =
 		Min(nblocks,
@@ -1068,7 +1068,7 @@ mdwritev(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 	{
 		struct iovec iov[PG_IOV_MAX];
 		int			iovcnt;
-		off_t		seekpos;
+		pgoff_t		seekpos;
 		int			nbytes;
 		MdfdVec    *v;
 		BlockNumber nblocks_this_segment;
@@ -1078,9 +1078,9 @@ mdwritev(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 		v = _mdfd_getseg(reln, forknum, blocknum, skipFsync,
 						 EXTENSION_FAIL | EXTENSION_CREATE_RECOVERY);
 
-		seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
+		seekpos = (pgoff_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
 
-		Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
+		Assert(seekpos < (pgoff_t) BLCKSZ * RELSEG_SIZE);
 
 		nblocks_this_segment =
 			Min(nblocks,
@@ -1173,7 +1173,7 @@ mdwriteback(SMgrRelation reln, ForkNumber forknum,
 	while (nblocks > 0)
 	{
 		BlockNumber nflush = nblocks;
-		off_t		seekpos;
+		pgoff_t		seekpos;
 		MdfdVec    *v;
 		int			segnum_start,
 					segnum_end;
@@ -1202,9 +1202,9 @@ mdwriteback(SMgrRelation reln, ForkNumber forknum,
 		Assert(nflush >= 1);
 		Assert(nflush <= nblocks);
 
-		seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
+		seekpos = (pgoff_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
 
-		FileWriteback(v->mdfd_vfd, seekpos, (off_t) BLCKSZ * nflush, WAIT_EVENT_DATA_FILE_FLUSH);
+		FileWriteback(v->mdfd_vfd, seekpos, (pgoff_t) BLCKSZ * nflush, WAIT_EVENT_DATA_FILE_FLUSH);
 
 		nblocks -= nflush;
 		blocknum += nflush;
@@ -1348,7 +1348,7 @@ mdtruncate(SMgrRelation reln, ForkNumber forknum,
 			 */
 			BlockNumber lastsegblocks = nblocks - priorblocks;
 
-			if (FileTruncate(v->mdfd_vfd, (off_t) lastsegblocks * BLCKSZ, WAIT_EVENT_DATA_FILE_TRUNCATE) < 0)
+			if (FileTruncate(v->mdfd_vfd, (pgoff_t) lastsegblocks * BLCKSZ, WAIT_EVENT_DATA_FILE_TRUNCATE) < 0)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not truncate file \"%s\" to %u blocks: %m",
@@ -1484,9 +1484,9 @@ mdfd(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, uint32 *off)
 	v = _mdfd_getseg(reln, forknum, blocknum, false,
 					 EXTENSION_FAIL);
 
-	*off = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
+	*off = (pgoff_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
 
-	Assert(*off < (off_t) BLCKSZ * RELSEG_SIZE);
+	Assert(*off < (pgoff_t) BLCKSZ * RELSEG_SIZE);
 
 	return FileGetRawDesc(v->mdfd_vfd);
 }
@@ -1868,7 +1868,7 @@ _mdfd_getseg(SMgrRelation reln, ForkNumber forknum, BlockNumber blkno,
 static BlockNumber
 _mdnblocks(SMgrRelation reln, ForkNumber forknum, MdfdVec *seg)
 {
-	off_t		len;
+	pgoff_t		len;
 
 	len = FileSize(seg->mdfd_vfd);
 	if (len < 0)

src/common/file_utils.c

@@ -656,7 +656,7 @@ compute_remaining_iovec(struct iovec *destination,
  * error is returned, it is unspecified how much has been written.
  */
 ssize_t
-pg_pwritev_with_retry(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+pg_pwritev_with_retry(int fd, const struct iovec *iov, int iovcnt, pgoff_t offset)
 {
 	struct iovec iov_copy[PG_IOV_MAX];
 	ssize_t		sum = 0;
@@ -706,7 +706,7 @@ pg_pwritev_with_retry(int fd, const struct iovec *iov, int iovcnt, off_t offset)
  * is returned with errno set.
  */
 ssize_t
-pg_pwrite_zeros(int fd, size_t size, off_t offset)
+pg_pwrite_zeros(int fd, size_t size, pgoff_t offset)
 {
 	static const PGIOAlignedBlock zbuffer = {0};	/* worth BLCKSZ */
 	void	   *zerobuf_addr = unconstify(PGIOAlignedBlock *, &zbuffer)->data;

src/include/common/file_utils.h

@@ -55,9 +55,9 @@ extern int	compute_remaining_iovec(struct iovec *destination,
 extern ssize_t pg_pwritev_with_retry(int fd,
 									 const struct iovec *iov,
 									 int iovcnt,
-									 off_t offset);
+									 pgoff_t offset);
 
-extern ssize_t pg_pwrite_zeros(int fd, size_t size, off_t offset);
+extern ssize_t pg_pwrite_zeros(int fd, size_t size, pgoff_t offset);
 
 /* Filename components */
 #define PG_TEMP_FILES_DIR "pgsql_tmp"

src/include/port/pg_iovec.h

@@ -51,7 +51,7 @@ struct iovec
  * this changes the current file position.
  */
 static inline ssize_t
-pg_preadv(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+pg_preadv(int fd, const struct iovec *iov, int iovcnt, pgoff_t offset)
 {
 #if HAVE_DECL_PREADV
 	/*
@@ -90,7 +90,7 @@ pg_preadv(int fd, const struct iovec *iov, int iovcnt, off_t offset)
  * this changes the current file position.
  */
 static inline ssize_t
-pg_pwritev(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+pg_pwritev(int fd, const struct iovec *iov, int iovcnt, pgoff_t offset)
 {
 #if HAVE_DECL_PWRITEV
 	/*

src/include/port/win32_port.h

@@ -584,9 +584,9 @@ typedef unsigned short mode_t;
 #endif
 
 /* in port/win32pread.c */
-extern ssize_t pg_pread(int fd, void *buf, size_t nbyte, off_t offset);
+extern ssize_t pg_pread(int fd, void *buf, size_t nbyte, pgoff_t offset);
 
 /* in port/win32pwrite.c */
-extern ssize_t pg_pwrite(int fd, const void *buf, size_t nbyte, off_t offset);
+extern ssize_t pg_pwrite(int fd, const void *buf, size_t nbyte, pgoff_t offset);
 
 #endif							/* PG_WIN32_PORT_H */

src/include/storage/fd.h

@@ -108,17 +108,17 @@ extern File PathNameOpenFile(const char *fileName, int fileFlags);
 extern File PathNameOpenFilePerm(const char *fileName, int fileFlags, mode_t fileMode);
 extern File OpenTemporaryFile(bool interXact);
 extern void FileClose(File file);
-extern int	FilePrefetch(File file, off_t offset, off_t amount, uint32 wait_event_info);
+extern int	FilePrefetch(File file, pgoff_t offset, pgoff_t amount, uint32 wait_event_info);
-extern ssize_t FileReadV(File file, const struct iovec *iov, int iovcnt, off_t offset, uint32 wait_event_info);
+extern ssize_t FileReadV(File file, const struct iovec *iov, int iovcnt, pgoff_t offset, uint32 wait_event_info);
-extern ssize_t FileWriteV(File file, const struct iovec *iov, int iovcnt, off_t offset, uint32 wait_event_info);
+extern ssize_t FileWriteV(File file, const struct iovec *iov, int iovcnt, pgoff_t offset, uint32 wait_event_info);
-extern int	FileStartReadV(struct PgAioHandle *ioh, File file, int iovcnt, off_t offset, uint32 wait_event_info);
+extern int	FileStartReadV(struct PgAioHandle *ioh, File file, int iovcnt, pgoff_t offset, uint32 wait_event_info);
 extern int	FileSync(File file, uint32 wait_event_info);
-extern int	FileZero(File file, off_t offset, off_t amount, uint32 wait_event_info);
+extern int	FileZero(File file, pgoff_t offset, pgoff_t amount, uint32 wait_event_info);
-extern int	FileFallocate(File file, off_t offset, off_t amount, uint32 wait_event_info);
+extern int	FileFallocate(File file, pgoff_t offset, pgoff_t amount, uint32 wait_event_info);
 
-extern off_t FileSize(File file);
+extern pgoff_t FileSize(File file);
-extern int	FileTruncate(File file, off_t offset, uint32 wait_event_info);
+extern int	FileTruncate(File file, pgoff_t offset, uint32 wait_event_info);
-extern void FileWriteback(File file, off_t offset, off_t nbytes, uint32 wait_event_info);
+extern void FileWriteback(File file, pgoff_t offset, pgoff_t nbytes, uint32 wait_event_info);
 extern char *FilePathName(File file);
 extern int	FileGetRawDesc(File file);
 extern int	FileGetRawFlags(File file);
@@ -186,8 +186,8 @@ extern int	pg_fsync_no_writethrough(int fd);
 extern int	pg_fsync_writethrough(int fd);
 extern int	pg_fdatasync(int fd);
 extern bool pg_file_exists(const char *name);
-extern void pg_flush_data(int fd, off_t offset, off_t nbytes);
+extern void pg_flush_data(int fd, pgoff_t offset, pgoff_t nbytes);
-extern int	pg_truncate(const char *path, off_t length);
+extern int	pg_truncate(const char *path, pgoff_t length);
 extern void fsync_fname(const char *fname, bool isdir);
 extern int	fsync_fname_ext(const char *fname, bool isdir, bool ignore_perm, int elevel);
 extern int	durable_rename(const char *oldfile, const char *newfile, int elevel);
@@ -196,7 +196,7 @@ extern void SyncDataDirectory(void);
 extern int	data_sync_elevel(int elevel);
 
 static inline ssize_t
-FileRead(File file, void *buffer, size_t amount, off_t offset,
+FileRead(File file, void *buffer, size_t amount, pgoff_t offset,
 		 uint32 wait_event_info)
 {
 	struct iovec iov = {
@@ -208,7 +208,7 @@ FileRead(File file, void *buffer, size_t amount, off_t offset,
 }
 
 static inline ssize_t
-FileWrite(File file, const void *buffer, size_t amount, off_t offset,
+FileWrite(File file, const void *buffer, size_t amount, pgoff_t offset,
 		  uint32 wait_event_info)
 {
 	struct iovec iov = {

src/port/win32pread.c

@@ -17,7 +17,7 @@
 #include <windows.h>
 
 ssize_t
-pg_pread(int fd, void *buf, size_t size, off_t offset)
+pg_pread(int fd, void *buf, size_t size, pgoff_t offset)
 {
 	OVERLAPPED	overlapped = {0};
 	HANDLE		handle;
@@ -34,7 +34,9 @@ pg_pread(int fd, void *buf, size_t size, off_t offset)
 	size = Min(size, 1024 * 1024 * 1024);
 
 	/* Note that this changes the file position, despite not using it. */
-	overlapped.Offset = offset;
+	overlapped.Offset = (DWORD) offset;
+	overlapped.OffsetHigh = (DWORD) (offset >> 32);
+
 	if (!ReadFile(handle, buf, size, &result, &overlapped))
 	{
 		if (GetLastError() == ERROR_HANDLE_EOF)

src/port/win32pwrite.c

@@ -17,7 +17,7 @@
 #include <windows.h>
 
 ssize_t
-pg_pwrite(int fd, const void *buf, size_t size, off_t offset)
+pg_pwrite(int fd, const void *buf, size_t size, pgoff_t offset)
 {
 	OVERLAPPED	overlapped = {0};
 	HANDLE		handle;
@@ -34,7 +34,9 @@ pg_pwrite(int fd, const void *buf, size_t size, off_t offset)
 	size = Min(size, 1024 * 1024 * 1024);
 
 	/* Note that this changes the file position, despite not using it. */
-	overlapped.Offset = offset;
+	overlapped.Offset = (DWORD) offset;
+	overlapped.OffsetHigh = (DWORD) (offset >> 32);
+
 	if (!WriteFile(handle, buf, size, &result, &overlapped))
 	{
 		_dosmaperr(GetLastError());

src/tools/pgindent/typedefs.list

@@ -3860,6 +3860,7 @@ pe_test_vector
 pendingPosition
 pending_label
 pgParameterStatus
+pgoff_t
 pg_atomic_flag
 pg_atomic_uint32
 pg_atomic_uint64