Support huge pages on Windows

Add support for huge pages (called large pages on Windows) to the
Windows build.

This (probably) breaks compatibility with Windows versions prior to
Windows 2003 or Windows Vista.

Authors: Takayuki Tsunakawa and Thomas Munro
Reviewed by: Magnus Hagander, Amit Kapila

3 files changed, 188 insertions, 18 deletions

diff --git a/src/backend/port/win32_shmem.c b/src/backend/port/win32_shmem.c
index 4991ed46f12..fa80cebfbd8 100644
--- a/src/backend/port/win32_shmem.c
+++ b/src/backend/port/win32_shmem.c
@@ -21,6 +21,7 @@ HANDLE		UsedShmemSegID = INVALID_HANDLE_VALUE;
 void	   *UsedShmemSegAddr = NULL;
 static Size UsedShmemSegSize = 0;
 
+static bool EnableLockPagesPrivilege(int elevel);
 static void pgwin32_SharedMemoryDelete(int status, Datum shmId);
 
 /*
@@ -103,6 +104,66 @@ PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2)
 	return true;
 }
 
+/*
+ * EnableLockPagesPrivilege
+ *
+ * Try to acquire SeLockMemoryPrivilege so we can use large pages.
+ */
+static bool
+EnableLockPagesPrivilege(int elevel)
+{
+	HANDLE hToken;
+	TOKEN_PRIVILEGES tp;
+	LUID luid;
+
+	if (!OpenProcessToken(GetCurrentProcess(), TOKEN_ADJUST_PRIVILEGES | TOKEN_QUERY, &hToken))
+	{
+		ereport(elevel,
+				(errmsg("could not enable Lock Pages in Memory user right: error code %lu", GetLastError()),
+				 errdetail("Failed system call was %s.", "OpenProcessToken")));
+		return FALSE;
+	}
+
+	if (!LookupPrivilegeValue(NULL, SE_LOCK_MEMORY_NAME, &luid))
+	{
+		ereport(elevel,
+				(errmsg("could not enable Lock Pages in Memory user right: error code %lu", GetLastError()),
+				 errdetail("Failed system call was %s.", "LookupPrivilegeValue")));
+		CloseHandle(hToken);
+		return FALSE;
+	}
+	tp.PrivilegeCount = 1;
+	tp.Privileges[0].Luid = luid;
+	tp.Privileges[0].Attributes = SE_PRIVILEGE_ENABLED;
+
+	if (!AdjustTokenPrivileges(hToken, FALSE, &tp, 0, NULL, NULL))
+	{
+		ereport(elevel,
+				(errmsg("could not enable Lock Pages in Memory user right: error code %lu", GetLastError()),
+				 errdetail("Failed system call was %s.", "AdjustTokenPrivileges")));
+		CloseHandle(hToken);
+		return FALSE;
+	}
+
+	if (GetLastError() != ERROR_SUCCESS)
+	{
+		if (GetLastError() == ERROR_NOT_ALL_ASSIGNED)
+			ereport(elevel,
+					(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
+					 errmsg("could not enable Lock Pages in Memory user right"),
+					 errhint("Assign Lock Pages in Memory user right to the Windows user account which runs PostgreSQL.")));
+		else
+			ereport(elevel,
+					(errmsg("could not enable Lock Pages in Memory user right: error code %lu", GetLastError()),
+					 errdetail("Failed system call was %s.", "AdjustTokenPrivileges")));
+		CloseHandle(hToken);
+		return FALSE;
+	}
+
+	CloseHandle(hToken);
+
+	return TRUE;
+}
 
 /*
  * PGSharedMemoryCreate
@@ -127,11 +188,9 @@ PGSharedMemoryCreate(Size size, bool makePrivate, int port,
 	int			i;
 	DWORD		size_high;
 	DWORD		size_low;
-
-	if (huge_pages == HUGE_PAGES_ON)
-		ereport(ERROR,
-				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-				 errmsg("huge pages not supported on this platform")));
+	SIZE_T		largePageSize = 0;
+	Size		orig_size = size;
+	DWORD		flProtect = PAGE_READWRITE;
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
@@ -140,6 +199,35 @@ PGSharedMemoryCreate(Size size, bool makePrivate, int port,
 
 	UsedShmemSegAddr = NULL;
 
+	if (huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY)
+	{
+		/* Does the processor support large pages? */
+		largePageSize = GetLargePageMinimum();
+		if (largePageSize == 0)
+		{
+			ereport(huge_pages == HUGE_PAGES_ON ? FATAL : DEBUG1,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("the processor does not support large pages")));
+			ereport(DEBUG1,
+					(errmsg("disabling huge pages")));
+		}
+		else if (!EnableLockPagesPrivilege(huge_pages == HUGE_PAGES_ON ? FATAL : DEBUG1))
+		{
+			ereport(DEBUG1,
+					(errmsg("disabling huge pages")));
+		}
+		else
+		{
+			/* Huge pages available and privilege enabled, so turn on */
+			flProtect = PAGE_READWRITE | SEC_COMMIT | SEC_LARGE_PAGES;
+
+			/* Round size up as appropriate. */
+			if (size % largePageSize != 0)
+				size += largePageSize - (size % largePageSize);
+		}
+	}
+
+retry:
 #ifdef _WIN64
 	size_high = size >> 32;
 #else
@@ -163,16 +251,35 @@ PGSharedMemoryCreate(Size size, bool makePrivate, int port,
 
 		hmap = CreateFileMapping(INVALID_HANDLE_VALUE,	/* Use the pagefile */
 								 NULL,	/* Default security attrs */
-								 PAGE_READWRITE,	/* Memory is Read/Write */
+								 flProtect,
 								 size_high, /* Size Upper 32 Bits	*/
 								 size_low,	/* Size Lower 32 bits */
 								 szShareMem);
 
 		if (!hmap)
-			ereport(FATAL,
-					(errmsg("could not create shared memory segment: error code %lu", GetLastError()),
-					 errdetail("Failed system call was CreateFileMapping(size=%zu, name=%s).",
-							   size, szShareMem)));
+		{
+			if (GetLastError() == ERROR_NO_SYSTEM_RESOURCES &&
+				huge_pages == HUGE_PAGES_TRY &&
+				(flProtect & SEC_LARGE_PAGES) != 0)
+			{
+				elog(DEBUG1, "CreateFileMapping(%zu) with SEC_LARGE_PAGES failed, "
+					 "huge pages disabled",
+					 size);
+
+				/*
+				 * Use the original size, not the rounded-up value, when falling back
+				 * to non-huge pages.
+				 */
+				size = orig_size;
+				flProtect = PAGE_READWRITE;
+				goto retry;
+			}
+			else
+				ereport(FATAL,
+						(errmsg("could not create shared memory segment: error code %lu", GetLastError()),
+						 errdetail("Failed system call was CreateFileMapping(size=%zu, name=%s).",
+								   size, szShareMem)));
+		}
 
 		/*
 		 * If the segment already existed, CreateFileMapping() will return a
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 72f6be329ef..d03ba234b5d 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -3913,7 +3913,7 @@ static struct config_enum ConfigureNamesEnum[] =
 
 	{
 		{"huge_pages", PGC_POSTMASTER, RESOURCES_MEM,
-			gettext_noop("Use of huge pages on Linux."),
+			gettext_noop("Use of huge pages on Linux or Windows."),
 			NULL
 		},
 		&huge_pages,
diff --git a/src/bin/pg_ctl/pg_ctl.c b/src/bin/pg_ctl/pg_ctl.c
index 62c72c3fcfa..9bc830b0852 100644
--- a/src/bin/pg_ctl/pg_ctl.c
+++ b/src/bin/pg_ctl/pg_ctl.c
@@ -144,6 +144,7 @@ static void WINAPI pgwin32_ServiceHandler(DWORD);
 static void WINAPI pgwin32_ServiceMain(DWORD, LPTSTR *);
 static void pgwin32_doRunAsService(void);
 static int	CreateRestrictedProcess(char *cmd, PROCESS_INFORMATION *processInfo, bool as_service);
+static PTOKEN_PRIVILEGES GetPrivilegesToDelete(HANDLE hToken);
 #endif
 
 static pgpid_t get_pgpid(bool is_status_request);
@@ -1623,11 +1624,6 @@ typedef BOOL (WINAPI * __SetInformationJobObject) (HANDLE, JOBOBJECTINFOCLASS, L
 typedef BOOL (WINAPI * __AssignProcessToJobObject) (HANDLE, HANDLE);
 typedef BOOL (WINAPI * __QueryInformationJobObject) (HANDLE, JOBOBJECTINFOCLASS, LPVOID, DWORD, LPDWORD);
 
-/* Windows API define missing from some versions of MingW headers */
-#ifndef  DISABLE_MAX_PRIVILEGE
-#define DISABLE_MAX_PRIVILEGE	0x1
-#endif
-
 /*
  * Create a restricted token, a job object sandbox, and execute the specified
  * process with it.
@@ -1650,6 +1646,7 @@ CreateRestrictedProcess(char *cmd, PROCESS_INFORMATION *processInfo, bool as_ser
 	HANDLE		restrictedToken;
 	SID_IDENTIFIER_AUTHORITY NtAuthority = {SECURITY_NT_AUTHORITY};
 	SID_AND_ATTRIBUTES dropSids[2];
+	PTOKEN_PRIVILEGES delPrivs;
 
 	/* Functions loaded dynamically */
 	__CreateRestrictedToken _CreateRestrictedToken = NULL;
@@ -1708,14 +1705,21 @@ CreateRestrictedProcess(char *cmd, PROCESS_INFORMATION *processInfo, bool as_ser
 		return 0;
 	}
 
+	/* Get list of privileges to remove */
+	delPrivs = GetPrivilegesToDelete(origToken);
+	if (delPrivs == NULL)
+		/* Error message already printed */
+		return 0;
+
 	b = _CreateRestrictedToken(origToken,
-							   DISABLE_MAX_PRIVILEGE,
+							   0,
 							   sizeof(dropSids) / sizeof(dropSids[0]),
 							   dropSids,
-							   0, NULL,
+							   delPrivs->PrivilegeCount, delPrivs->Privileges,
 							   0, NULL,
 							   &restrictedToken);
 
+	free(delPrivs);
 	FreeSid(dropSids[1].Sid);
 	FreeSid(dropSids[0].Sid);
 	CloseHandle(origToken);
@@ -1832,6 +1836,65 @@ CreateRestrictedProcess(char *cmd, PROCESS_INFORMATION *processInfo, bool as_ser
 	 */
 	return r;
 }
+
+/*
+ * Get a list of privileges to delete from the access token. We delete all privileges
+ * except SeLockMemoryPrivilege which is needed to use large pages, and
+ * SeChangeNotifyPrivilege which is enabled by default in DISABLE_MAX_PRIVILEGE.
+ */
+static PTOKEN_PRIVILEGES
+GetPrivilegesToDelete(HANDLE hToken)
+{
+	int			i, j;
+	DWORD		length;
+	PTOKEN_PRIVILEGES tokenPrivs;
+	LUID		luidLockPages;
+	LUID		luidChangeNotify;
+
+	if (!LookupPrivilegeValue(NULL, SE_LOCK_MEMORY_NAME, &luidLockPages) ||
+		!LookupPrivilegeValue(NULL, SE_CHANGE_NOTIFY_NAME, &luidChangeNotify))
+	{
+		write_stderr(_("%s: could not get LUIDs for privileges: error code %lu\n"),
+					 progname, (unsigned long) GetLastError());
+		return NULL;
+	}
+
+	if (!GetTokenInformation(hToken, TokenPrivileges, NULL, 0, &length) &&
+		GetLastError() != ERROR_INSUFFICIENT_BUFFER)
+	{
+		write_stderr(_("%s: could not get token information: error code %lu\n"),
+					 progname, (unsigned long) GetLastError());
+		return NULL;
+	}
+
+	tokenPrivs = (PTOKEN_PRIVILEGES) malloc(length);
+	if (tokenPrivs == NULL)
+	{
+		write_stderr(_("%s: out of memory\n"), progname);
+		return NULL;
+	}
+
+	if (!GetTokenInformation(hToken, TokenPrivileges, tokenPrivs, length, &length))
+	{
+		write_stderr(_("%s: could not get token information: error code %lu\n"),
+					 progname, (unsigned long) GetLastError());
+		free(tokenPrivs);
+		return NULL;
+	}
+
+	for (i = 0; i < tokenPrivs->PrivilegeCount; i++)
+	{
+		if (memcmp(&tokenPrivs->Privileges[i].Luid, &luidLockPages, sizeof(LUID)) == 0 ||
+			memcmp(&tokenPrivs->Privileges[i].Luid, &luidChangeNotify, sizeof(LUID)) == 0)
+		{
+			for (j = i; j < tokenPrivs->PrivilegeCount - 1; j++)
+				tokenPrivs->Privileges[j] = tokenPrivs->Privileges[j + 1];
+			tokenPrivs->PrivilegeCount--;
+		}
+	}
+
+	return tokenPrivs;
+}
 #endif							/* WIN32 */
 
 static void