Remove dead pread and pwrite replacement code.

pread() and pwrite() are in SUSv2, and all targeted Unix systems have
them.

Previously, we defined pg_pread and pg_pwrite to emulate these function
with lseek() on old Unixen.  The names with a pg_ prefix were a reminder
of a portability hazard: they might change the current file position.
That hazard is gone, so we can drop the prefixes.

Since the remaining replacement code is Windows-only, move it into
src/port/win32p{read,write}.c, and move the declarations into
src/include/port/win32_port.h.

No need for vestigial HAVE_PREAD, HAVE_PWRITE macros as they were only
used for declarations in port.h which have now moved into win32_port.h.

Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us>
Reviewed-by: Greg Stark <stark@mit.edu>
Reviewed-by: Robert Haas <robertmhaas@gmail.com>
Reviewed-by: Andres Freund <andres@anarazel.de>
Discussion: https://postgr.es/m/CA+hUKGJ3LHeP9w5Fgzdr4G8AnEtJ=z=p6hGDEm4qYGEUX5B6fQ@mail.gmail.com

configure

@@ -16728,32 +16728,6 @@ esac
 
 fi
 
-ac_fn_c_check_func "$LINENO" "pread" "ac_cv_func_pread"
-if test "x$ac_cv_func_pread" = xyes; then :
-  $as_echo "#define HAVE_PREAD 1" >>confdefs.h
-
-else
-  case " $LIBOBJS " in
-  *" pread.$ac_objext "* ) ;;
-  *) LIBOBJS="$LIBOBJS pread.$ac_objext"
- ;;
-esac
-
-fi
-
-ac_fn_c_check_func "$LINENO" "pwrite" "ac_cv_func_pwrite"
-if test "x$ac_cv_func_pwrite" = xyes; then :
-  $as_echo "#define HAVE_PWRITE 1" >>confdefs.h
-
-else
-  case " $LIBOBJS " in
-  *" pwrite.$ac_objext "* ) ;;
-  *) LIBOBJS="$LIBOBJS pwrite.$ac_objext"
- ;;
-esac
-
-fi
-
 ac_fn_c_check_func "$LINENO" "strlcat" "ac_cv_func_strlcat"
 if test "x$ac_cv_func_strlcat" = xyes; then :
   $as_echo "#define HAVE_STRLCAT 1" >>confdefs.h
@@ -17015,6 +16989,18 @@ esac
  ;;
 esac
 
+  case " $LIBOBJS " in
+  *" win32pread.$ac_objext "* ) ;;
+  *) LIBOBJS="$LIBOBJS win32pread.$ac_objext"
+ ;;
+esac
+
+  case " $LIBOBJS " in
+  *" win32pwrite.$ac_objext "* ) ;;
+  *) LIBOBJS="$LIBOBJS win32pwrite.$ac_objext"
+ ;;
+esac
+
   case " $LIBOBJS " in
   *" win32security.$ac_objext "* ) ;;
   *) LIBOBJS="$LIBOBJS win32security.$ac_objext"

configure.ac

@@ -1876,8 +1876,6 @@ AC_REPLACE_FUNCS(m4_normalize([
 	getpeereid
 	inet_aton
 	mkdtemp
-	pread
-	pwrite
 	strlcat
 	strlcpy
 	strnlen
@@ -1943,6 +1941,8 @@ if test "$PORTNAME" = "win32"; then
   AC_LIBOBJ(win32error)
   AC_LIBOBJ(win32link)
   AC_LIBOBJ(win32ntdll)
+  AC_LIBOBJ(win32pread)
+  AC_LIBOBJ(win32pwrite)
   AC_LIBOBJ(win32security)
   AC_LIBOBJ(win32setlocale)
   AC_LIBOBJ(win32stat)

contrib/pg_stat_statements/pg_stat_statements.c

@@ -2103,9 +2103,9 @@ qtext_store(const char *query, int query_len,
 	if (fd < 0)
 		goto error;
 
-	if (pg_pwrite(fd, query, query_len, off) != query_len)
+	if (pwrite(fd, query, query_len, off) != query_len)
 		goto error;
-	if (pg_pwrite(fd, "\0", 1, off + query_len) != 1)
+	if (pwrite(fd, "\0", 1, off + query_len) != 1)
 		goto error;
 
 	CloseTransientFile(fd);

src/backend/access/heap/rewriteheap.c

@@ -1149,7 +1149,7 @@ heap_xlog_logical_rewrite(XLogReaderState *r)
 	/* write out tail end of mapping file (again) */
 	errno = 0;
 	pgstat_report_wait_start(WAIT_EVENT_LOGICAL_REWRITE_MAPPING_WRITE);
-	if (pg_pwrite(fd, data, len, xlrec->offset) != len)
+	if (pwrite(fd, data, len, xlrec->offset) != len)
 	{
 		/* if write didn't set errno, assume problem is no disk space */
 		if (errno == 0)

src/backend/access/transam/slru.c

@@ -718,7 +718,7 @@ SlruPhysicalReadPage(SlruCtl ctl, int pageno, int slotno)
 
 	errno = 0;
 	pgstat_report_wait_start(WAIT_EVENT_SLRU_READ);
-	if (pg_pread(fd, shared->page_buffer[slotno], BLCKSZ, offset) != BLCKSZ)
+	if (pread(fd, shared->page_buffer[slotno], BLCKSZ, offset) != BLCKSZ)
 	{
 		pgstat_report_wait_end();
 		slru_errcause = SLRU_READ_FAILED;
@@ -873,7 +873,7 @@ SlruPhysicalWritePage(SlruCtl ctl, int pageno, int slotno, SlruWriteAll fdata)
 
 	errno = 0;
 	pgstat_report_wait_start(WAIT_EVENT_SLRU_WRITE);
-	if (pg_pwrite(fd, shared->page_buffer[slotno], BLCKSZ, offset) != BLCKSZ)
+	if (pwrite(fd, shared->page_buffer[slotno], BLCKSZ, offset) != BLCKSZ)
 	{
 		pgstat_report_wait_end();
 		/* if write didn't set errno, assume problem is no disk space */

src/backend/access/transam/xlog.c

@@ -2189,7 +2189,7 @@ XLogWrite(XLogwrtRqst WriteRqst, TimeLineID tli, bool flexible)
 					INSTR_TIME_SET_CURRENT(start);
 
 				pgstat_report_wait_start(WAIT_EVENT_WAL_WRITE);
-				written = pg_pwrite(openLogFile, from, nleft, startoffset);
+				written = pwrite(openLogFile, from, nleft, startoffset);
 				pgstat_report_wait_end();
 
 				/*
@@ -3011,7 +3011,7 @@ XLogFileInitInternal(XLogSegNo logsegno, TimeLineID logtli,
 		 * enough.
 		 */
 		errno = 0;
-		if (pg_pwrite(fd, zbuffer.data, 1, wal_segment_size - 1) != 1)
+		if (pwrite(fd, zbuffer.data, 1, wal_segment_size - 1) != 1)
 		{
 			/* if write didn't set errno, assume no disk space */
 			save_errno = errno ? errno : ENOSPC;

src/backend/access/transam/xlogreader.c

@@ -1514,7 +1514,7 @@ 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 = pread(state->seg.ws_file, p, segbytes, (off_t) startoff);
 
 #ifndef FRONTEND
 		pgstat_report_wait_end();

src/backend/access/transam/xlogrecovery.c

@@ -3260,7 +3260,7 @@ retry:
 	readOff = targetPageOff;
 
 	pgstat_report_wait_start(WAIT_EVENT_WAL_READ);
-	r = pg_pread(readFile, readBuf, XLOG_BLCKSZ, (off_t) readOff);
+	r = pread(readFile, readBuf, XLOG_BLCKSZ, (off_t) readOff);
 	if (r != XLOG_BLCKSZ)
 	{
 		char		fname[MAXFNAMELEN];

src/backend/replication/basebackup.c

@@ -1822,7 +1822,7 @@ basebackup_read_file(int fd, char *buf, size_t nbytes, off_t offset,
 	int			rc;
 
 	pgstat_report_wait_start(WAIT_EVENT_BASEBACKUP_READ);
-	rc = pg_pread(fd, buf, nbytes, offset);
+	rc = pread(fd, buf, nbytes, offset);
 	pgstat_report_wait_end();
 
 	if (rc < 0)

src/backend/replication/walreceiver.c

@@ -915,7 +915,7 @@ XLogWalRcvWrite(char *buf, Size nbytes, XLogRecPtr recptr, TimeLineID tli)
 		/* OK to write the logs */
 		errno = 0;
 
-		byteswritten = pg_pwrite(recvFile, buf, segbytes, (off_t) startoff);
+		byteswritten = pwrite(recvFile, buf, segbytes, (off_t) startoff);
 		if (byteswritten <= 0)
 		{
 			char		xlogfname[MAXFNAMELEN];

src/backend/storage/file/fd.c

@@ -2063,7 +2063,7 @@ FileRead(File file, char *buffer, int amount, off_t offset,
 
 retry:
 	pgstat_report_wait_start(wait_event_info);
-	returnCode = pg_pread(vfdP->fd, buffer, amount, offset);
+	returnCode = pread(vfdP->fd, buffer, amount, offset);
 	pgstat_report_wait_end();
 
 	if (returnCode < 0)
@@ -2145,7 +2145,7 @@ FileWrite(File file, char *buffer, int amount, off_t offset,
 retry:
 	errno = 0;
 	pgstat_report_wait_start(wait_event_info);
-	returnCode = pg_pwrite(VfdCache[file].fd, buffer, amount, offset);
+	returnCode = pwrite(VfdCache[file].fd, buffer, amount, offset);
 	pgstat_report_wait_end();
 
 	/* if write didn't set errno, assume problem is no disk space */

src/backend/utils/init/miscinit.c

@@ -1429,7 +1429,7 @@ AddToDataDirLockFile(int target_line, const char *str)
 	len = strlen(destbuffer);
 	errno = 0;
 	pgstat_report_wait_start(WAIT_EVENT_LOCK_FILE_ADDTODATADIR_WRITE);
-	if (pg_pwrite(fd, destbuffer, len, 0) != len)
+	if (pwrite(fd, destbuffer, len, 0) != len)
 	{
 		pgstat_report_wait_end();
 		/* if write didn't set errno, assume problem is no disk space */

src/bin/pg_test_fsync/pg_test_fsync.c

@@ -312,10 +312,10 @@ test_sync(int writes_per_op)
 		for (ops = 0; alarm_triggered == false; ops++)
 		{
 			for (writes = 0; writes < writes_per_op; writes++)
-				if (pg_pwrite(tmpfile,
+				if (pwrite(tmpfile,
-							  buf,
+						   buf,
-							  XLOG_BLCKSZ,
+						   XLOG_BLCKSZ,
-							  writes * XLOG_BLCKSZ) != XLOG_BLCKSZ)
+						   writes * XLOG_BLCKSZ) != XLOG_BLCKSZ)
 					die("write failed");
 		}
 		STOP_TIMER;
@@ -338,10 +338,10 @@ test_sync(int writes_per_op)
 	for (ops = 0; alarm_triggered == false; ops++)
 	{
 		for (writes = 0; writes < writes_per_op; writes++)
-			if (pg_pwrite(tmpfile,
+			if (pwrite(tmpfile,
-						  buf,
+					   buf,
-						  XLOG_BLCKSZ,
+					   XLOG_BLCKSZ,
-						  writes * XLOG_BLCKSZ) != XLOG_BLCKSZ)
+					   writes * XLOG_BLCKSZ) != XLOG_BLCKSZ)
 				die("write failed");
 		fdatasync(tmpfile);
 	}
@@ -363,10 +363,10 @@ test_sync(int writes_per_op)
 	for (ops = 0; alarm_triggered == false; ops++)
 	{
 		for (writes = 0; writes < writes_per_op; writes++)
-			if (pg_pwrite(tmpfile,
+			if (pwrite(tmpfile,
-						  buf,
+					   buf,
-						  XLOG_BLCKSZ,
+					   XLOG_BLCKSZ,
-						  writes * XLOG_BLCKSZ) != XLOG_BLCKSZ)
+					   writes * XLOG_BLCKSZ) != XLOG_BLCKSZ)
 				die("write failed");
 		if (fsync(tmpfile) != 0)
 			die("fsync failed");
@@ -387,10 +387,10 @@ test_sync(int writes_per_op)
 	for (ops = 0; alarm_triggered == false; ops++)
 	{
 		for (writes = 0; writes < writes_per_op; writes++)
-			if (pg_pwrite(tmpfile,
+			if (pwrite(tmpfile,
-						  buf,
+					   buf,
-						  XLOG_BLCKSZ,
+					   XLOG_BLCKSZ,
-						  writes * XLOG_BLCKSZ) != XLOG_BLCKSZ)
+					   writes * XLOG_BLCKSZ) != XLOG_BLCKSZ)
 				die("write failed");
 		if (pg_fsync_writethrough(tmpfile) != 0)
 			die("fsync failed");
@@ -419,10 +419,10 @@ test_sync(int writes_per_op)
 		for (ops = 0; alarm_triggered == false; ops++)
 		{
 			for (writes = 0; writes < writes_per_op; writes++)
-				if (pg_pwrite(tmpfile,
+				if (pwrite(tmpfile,
-							  buf,
+						   buf,
-							  XLOG_BLCKSZ,
+						   XLOG_BLCKSZ,
-							  writes * XLOG_BLCKSZ) != XLOG_BLCKSZ)
+						   writes * XLOG_BLCKSZ) != XLOG_BLCKSZ)
 
 					/*
 					 * This can generate write failures if the filesystem has
@@ -484,10 +484,10 @@ test_open_sync(const char *msg, int writes_size)
 		for (ops = 0; alarm_triggered == false; ops++)
 		{
 			for (writes = 0; writes < 16 / writes_size; writes++)
-				if (pg_pwrite(tmpfile,
+				if (pwrite(tmpfile,
-							  buf,
+						   buf,
-							  writes_size * 1024,
+						   writes_size * 1024,
-							  writes * writes_size * 1024) !=
+						   writes * writes_size * 1024) !=
 					writes_size * 1024)
 					die("write failed");
 		}
@@ -586,7 +586,7 @@ test_non_sync(void)
 	START_TIMER;
 	for (ops = 0; alarm_triggered == false; ops++)
 	{
-		if (pg_pwrite(tmpfile, buf, XLOG_BLCKSZ, 0) != XLOG_BLCKSZ)
+		if (pwrite(tmpfile, buf, XLOG_BLCKSZ, 0) != XLOG_BLCKSZ)
 			die("write failed");
 	}
 	STOP_TIMER;

src/include/access/xlogreader.h

@@ -375,11 +375,11 @@ extern bool XLogReaderValidatePageHeader(XLogReaderState *state,
 
 /*
  * Error information from WALRead that both backend and frontend caller can
- * process.  Currently only errors from pg_pread can be reported.
+ * process.  Currently only errors from pread can be reported.
  */
 typedef struct WALReadError
 {
-	int			wre_errno;		/* errno set by the last pg_pread() */
+	int			wre_errno;		/* errno set by the last pread() */
 	int			wre_off;		/* Offset we tried to read from. */
 	int			wre_req;		/* Bytes requested to be read. */
 	int			wre_read;		/* Bytes read by the last read(). */

src/include/pg_config.h.in

@@ -388,9 +388,6 @@
 /* Define to 1 if you have the `ppoll' function. */
 #undef HAVE_PPOLL
 
-/* Define to 1 if you have the `pread' function. */
-#undef HAVE_PREAD
-
 /* Define to 1 if the PS_STRINGS thing exists. */
 #undef HAVE_PS_STRINGS
 
@@ -406,9 +403,6 @@
 /* Have PTHREAD_PRIO_INHERIT. */
 #undef HAVE_PTHREAD_PRIO_INHERIT
 
-/* Define to 1 if you have the `pwrite' function. */
-#undef HAVE_PWRITE
-
 /* Define to 1 if you have the <readline.h> header file. */
 #undef HAVE_READLINE_H
 

src/include/port.h

@@ -417,25 +417,6 @@ extern char *mkdtemp(char *path);
 extern int	inet_aton(const char *cp, struct in_addr *addr);
 #endif
 
-/*
- * Windows and older Unix don't have pread(2) and pwrite(2).  We have
- * replacement functions, but they have slightly different semantics so we'll
- * use a name with a pg_ prefix to avoid confusion.
- */
-#ifdef HAVE_PREAD
-#define pg_pread pread
-#else
-extern ssize_t pg_pread(int fd, void *buf, size_t nbyte, off_t offset);
-#endif
-
-#ifdef HAVE_PWRITE
-#define pg_pwrite pwrite
-#else
-extern ssize_t pg_pwrite(int fd, const void *buf, size_t nbyte, off_t offset);
-#endif
-
-/* For pg_pwritev() and pg_preadv(), see port/pg_iovec.h. */
-
 #if !HAVE_DECL_STRLCAT
 extern size_t strlcat(char *dst, const char *src, size_t siz);
 #endif

src/include/port/win32_port.h

@@ -562,4 +562,10 @@ typedef unsigned short mode_t;
 #define HAVE_BUGGY_STRTOF 1
 #endif
 
+/* in port/win32pread.c */
+extern ssize_t pread(int fd, void *buf, size_t nbyte, off_t offset);
+
+/* in port/win32pwrite.c */
+extern ssize_t pwrite(int fd, const void *buf, size_t nbyte, off_t offset);
+
 #endif							/* PG_WIN32_PORT_H */

src/port/preadv.c

@@ -30,7 +30,7 @@ pg_preadv(int fd, const struct iovec *iov, int iovcnt, off_t offset)
 {
 #ifdef HAVE_READV
 	if (iovcnt == 1)
-		return pg_pread(fd, iov[0].iov_base, iov[0].iov_len, offset);
+		return pread(fd, iov[0].iov_base, iov[0].iov_len, offset);
 	if (lseek(fd, offset, SEEK_SET) < 0)
 		return -1;
 	return readv(fd, iov, iovcnt);
@@ -40,7 +40,7 @@ pg_preadv(int fd, const struct iovec *iov, int iovcnt, off_t offset)
 
 	for (int i = 0; i < iovcnt; ++i)
 	{
-		part = pg_pread(fd, iov[i].iov_base, iov[i].iov_len, offset);
+		part = pread(fd, iov[i].iov_base, iov[i].iov_len, offset);
 		if (part < 0)
 		{
 			if (i == 0)

src/port/pwritev.c

@@ -30,7 +30,7 @@ pg_pwritev(int fd, const struct iovec *iov, int iovcnt, off_t offset)
 {
 #ifdef HAVE_WRITEV
 	if (iovcnt == 1)
-		return pg_pwrite(fd, iov[0].iov_base, iov[0].iov_len, offset);
+		return pwrite(fd, iov[0].iov_base, iov[0].iov_len, offset);
 	if (lseek(fd, offset, SEEK_SET) < 0)
 		return -1;
 	return writev(fd, iov, iovcnt);
@@ -40,7 +40,7 @@ pg_pwritev(int fd, const struct iovec *iov, int iovcnt, off_t offset)
 
 	for (int i = 0; i < iovcnt; ++i)
 	{
-		part = pg_pwrite(fd, iov[i].iov_base, iov[i].iov_len, offset);
+		part = pwrite(fd, iov[i].iov_base, iov[i].iov_len, offset);
 		if (part < 0)
 		{
 			if (i == 0)

src/port/win32pread.c

@@ -1,15 +1,12 @@
 /*-------------------------------------------------------------------------
  *
- * pread.c
+ * win32pread.c
- *	  Implementation of pread(2) for platforms that lack one.
+ *	  Implementation of pread(2) for Windows.
  *
  * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
- *	  src/port/pread.c
+ *	  src/port/win32pread.c
- *
- * Note that this implementation changes the current file position, unlike
- * the POSIX function, so we use the name pg_pread().
  *
  *-------------------------------------------------------------------------
  */
@@ -17,16 +14,11 @@
 
 #include "postgres.h"
 
-#ifdef WIN32
 #include <windows.h>
-#else
-#include <unistd.h>
-#endif
 
 ssize_t
-pg_pread(int fd, void *buf, size_t size, off_t offset)
+pread(int fd, void *buf, size_t size, off_t offset)
 {
-#ifdef WIN32
 	OVERLAPPED	overlapped = {0};
 	HANDLE		handle;
 	DWORD		result;
@@ -49,10 +41,4 @@ pg_pread(int fd, void *buf, size_t size, off_t offset)
 	}
 
 	return result;
-#else
-	if (lseek(fd, offset, SEEK_SET) < 0)
-		return -1;
-
-	return read(fd, buf, size);
-#endif
 }

src/port/win32pwrite.c

@@ -1,15 +1,12 @@
 /*-------------------------------------------------------------------------
  *
- * pwrite.c
+ * win32pwrite.c
- *	  Implementation of pwrite(2) for platforms that lack one.
+ *	  Implementation of pwrite(2) for Windows.
  *
  * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
- *	  src/port/pwrite.c
+ *	  src/port/win32pwrite.c
- *
- * Note that this implementation changes the current file position, unlike
- * the POSIX function, so we use the name pg_pwrite().
  *
  *-------------------------------------------------------------------------
  */
@@ -17,16 +14,11 @@
 
 #include "postgres.h"
 
-#ifdef WIN32
 #include <windows.h>
-#else
-#include <unistd.h>
-#endif
 
 ssize_t
-pg_pwrite(int fd, const void *buf, size_t size, off_t offset)
+pwrite(int fd, const void *buf, size_t size, off_t offset)
 {
-#ifdef WIN32
 	OVERLAPPED	overlapped = {0};
 	HANDLE		handle;
 	DWORD		result;
@@ -46,10 +38,4 @@ pg_pwrite(int fd, const void *buf, size_t size, off_t offset)
 	}
 
 	return result;
-#else
-	if (lseek(fd, offset, SEEK_SET) < 0)
-		return -1;
-
-	return write(fd, buf, size);
-#endif
 }

src/tools/msvc/Mkvcbuild.pm

@@ -104,13 +104,15 @@ sub mkvcbuild
 	  getaddrinfo.c gettimeofday.c inet_net_ntop.c kill.c open.c
 	  snprintf.c strlcat.c strlcpy.c dirmod.c noblock.c path.c
 	  dirent.c getopt.c getopt_long.c
-	  pread.c preadv.c pwrite.c pwritev.c pg_bitutils.c
+	  preadv.c pwritev.c pg_bitutils.c
 	  pg_strong_random.c pgcheckdir.c pgmkdirp.c pgsleep.c pgstrcasecmp.c
 	  pqsignal.c mkdtemp.c qsort.c qsort_arg.c bsearch_arg.c quotes.c system.c
 	  strerror.c tar.c
 	  win32dlopen.c
 	  win32env.c win32error.c
 	  win32link.c
+	  win32pread.c
+	  win32pwrite.c
 	  win32ntdll.c
 	  win32security.c win32setlocale.c win32stat.c);
 

src/tools/msvc/Solution.pm

@@ -324,13 +324,11 @@ sub GenerateFiles
 		HAVE_POSIX_FALLOCATE        => undef,
 		HAVE_PPC_LWARX_MUTEX_HINT   => undef,
 		HAVE_PPOLL                  => undef,
-		HAVE_PREAD                  => undef,
 		HAVE_PS_STRINGS             => undef,
 		HAVE_PTHREAD                => undef,
 		HAVE_PTHREAD_BARRIER_WAIT   => undef,
 		HAVE_PTHREAD_IS_THREADED_NP => undef,
 		HAVE_PTHREAD_PRIO_INHERIT   => undef,
-		HAVE_PWRITE                 => undef,
 		HAVE_READLINE_H             => undef,
 		HAVE_READLINE_HISTORY_H     => undef,
 		HAVE_READLINE_READLINE_H    => undef,