update from bk repository

34 files changed, 634 insertions, 329 deletions

diff --git a/acinclude.m4 b/acinclude.m4
index eaf6d628e4e..7fb3b094f50 100644
--- a/acinclude.m4
+++ b/acinclude.m4
@@ -1095,11 +1095,11 @@ AC_MSG_CHECKING(for OpenSSL)
     AC_MSG_RESULT(no)
 	if test ! -z "$openssl_includes"
 	then
-		AC_MSG_ERROR(Can't have --with-openssl-includes without --with-openssl);
+		AC_MSG_ERROR(Can't have --with-openssl-includes without --with-openssl)
 	fi
 	if test ! -z "$openssl_libs"
 	then
-		AC_MSG_ERROR(Can't have --with-openssl-libs without --with-openssl);
+		AC_MSG_ERROR(Can't have --with-openssl-libs without --with-openssl)
 	fi
   fi
   AC_SUBST(openssl_libs)
diff --git a/client/mysql.cc b/client/mysql.cc
index d8810ba3c28..e4002822fcc 100644
--- a/client/mysql.cc
+++ b/client/mysql.cc
@@ -1,4 +1,4 @@
-/* Copyright (C) 2000-2003 MySQL AB
+/* Copyright (C) 2000-2008 MySQL AB
 
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
@@ -729,7 +729,7 @@ static void usage(int version)
   if (version)
     return;
   printf("\
-Copyright (C) 2002 MySQL AB\n\
+Copyright (C) 2000-2008 MySQL AB\n\
 This software comes with ABSOLUTELY NO WARRANTY. This is free software,\n\
 and you are welcome to modify and redistribute it under the GPL license\n");
   printf("Usage: %s [OPTIONS] [database]\n", my_progname);
@@ -1910,7 +1910,8 @@ com_charset(String *buffer __attribute__((unused)), char *line)
 static int
 com_go(String *buffer,char *line __attribute__((unused)))
 {
-  char		buff[200], time_buff[32], *pos;
+  char		buff[200]; /* about 110 chars used so far */
+  char		time_buff[52+3+1]; /* time max + space&parens + NUL */
   MYSQL_RES	*result;
   ulong		timer, warnings;
   uint		error= 0;
@@ -1973,6 +1974,8 @@ com_go(String *buffer,char *line __attribute__((unused)))
 
   do
   {
+    char *pos;
+
     if (quick)
     {
       if (!(result=mysql_use_result(&mysql)) && mysql_field_count(&mysql))
@@ -1988,7 +1991,9 @@ com_go(String *buffer,char *line __attribute__((unused)))
     if (verbose >= 3 || !opt_silent)
       mysql_end_timer(timer,time_buff);
     else
-      time_buff[0]=0;
+      time_buff[0]= '\0';
+
+    /* Every branch must truncate  buff . */
     if (result)
     {
       if (!mysql_num_rows(result) && ! quick)
@@ -2045,6 +2050,7 @@ com_go(String *buffer,char *line __attribute__((unused)))
       fflush(stdout);
     mysql_free_result(result);
   } while (!(err= mysql_next_result(&mysql)));
+
   if (err >= 1)
     error= put_error(&mysql);
 
@@ -3275,6 +3281,11 @@ static ulong start_timer(void)
 }
 
 
+/** 
+  Write as many as 52+1 bytes to buff, in the form of a legible duration of time.
+
+  len("4294967296 days, 23 hours, 59 minutes, 60.00 seconds")  ->  52
+*/
 static void nice_time(double sec,char *buff,bool part_second)
 {
   ulong tmp;
diff --git a/client/mysqltest.c b/client/mysqltest.c
index 04dfce28ab4..d5a03961364 100644
--- a/client/mysqltest.c
+++ b/client/mysqltest.c
@@ -3067,7 +3067,7 @@ void do_get_file_name(struct st_command *command,
   if (*p)
     *p++= 0;
   command->last_argument= p;
-  strmake(dest, name, dest_max_len);
+  strmake(dest, name, dest_max_len - 1);
 }
 
 
@@ -6375,7 +6375,7 @@ int main(int argc, char **argv)
 
 	if (save_file[0])
 	{
-	  strmake(command->require_file, save_file, sizeof(save_file));
+	  strmake(command->require_file, save_file, sizeof(save_file) - 1);
 	  save_file[0]= 0;
 	}
 	run_query(cur_con, command, flags);
diff --git a/configure.in b/configure.in
index 01b5734a3b0..6d58ab4b2aa 100644
--- a/configure.in
+++ b/configure.in
@@ -5,7 +5,7 @@ AC_INIT(sql/mysqld.cc)
 AC_CANONICAL_SYSTEM
 # The Docs Makefile.am parses this line!
 # remember to also change ndb version below and update version.c in ndb
-AM_INIT_AUTOMAKE(mysql, 4.1.24)
+AM_INIT_AUTOMAKE(mysql, 4.1.25)
 AM_CONFIG_HEADER(config.h)
 
 PROTOCOL_VERSION=10
@@ -21,14 +21,24 @@ NDB_SHARED_LIB_VERSION=$NDB_SHARED_LIB_MAJOR_VERSION:0:0
 # ndb version
 NDB_VERSION_MAJOR=4
 NDB_VERSION_MINOR=1
-NDB_VERSION_BUILD=24
+NDB_VERSION_BUILD=25
 NDB_VERSION_STATUS=""
 
 # Set all version vars based on $VERSION. How do we do this more elegant ?
 # Remember that regexps needs to quote [ and ] since this is run through m4
-MYSQL_NO_DASH_VERSION=`echo $VERSION | sed -e "s|[[a-z]]*-.*$||"`
-MYSQL_BASE_VERSION=`echo $MYSQL_NO_DASH_VERSION | sed -e "s|\.[[^.]]*$||"`
-MYSQL_VERSION_ID=`echo $MYSQL_NO_DASH_VERSION. | sed -e 's/[[^0-9.]]//g; s/\./  /g; s/ \([[0-9]]\) / 0\\1 /g; s/ //g'`
+# We take some made up examples
+#
+#  VERSION                  5.1.40sp1-alpha     5.0.34a
+#  MYSQL_NO_DASH_VERSION    5.1.40sp1           5.0.34a
+#  MYSQL_NUMERIC_VERSION    5.1.40              5.0.34
+#  MYSQL_BASE_VERSION       5.1                 5.0
+#  MYSQL_VERSION_ID         50140               50034
+#
+MYSQL_NO_DASH_VERSION=`echo $VERSION | sed -e "s|-.*$||"`
+MYSQL_NUMERIC_VERSION=`echo $MYSQL_NO_DASH_VERSION | sed -e "s|[[a-z]][[a-z0-9]]*$||"`
+MYSQL_BASE_VERSION=`echo $MYSQL_NUMERIC_VERSION | sed -e "s|\.[[^.]]*$||"`
+MYSQL_VERSION_ID=`echo $MYSQL_NUMERIC_VERSION | \
+    awk -F. '{printf "%d%0.2d%0.2d", $1, $2, $3}'`
 
 # The port should be constant for a LONG time
 MYSQL_TCP_PORT_DEFAULT=3306
@@ -205,7 +215,7 @@ CC_VERSION=`$CC --version | sed 1q`
 esac
 if test $? -eq "0"
 then
-  AC_MSG_CHECKING("C Compiler version");
+  AC_MSG_CHECKING("C Compiler version")
   AC_MSG_RESULT("$CC $CC_VERSION")
 else
 CC_VERSION=""
@@ -220,7 +230,7 @@ CXX_VERSION=`$CXX --version | sed 1q`
 esac
 if test $? -eq "0"
 then
-  AC_MSG_CHECKING("C++ compiler version");
+  AC_MSG_CHECKING("C++ compiler version")
   AC_MSG_RESULT("$CXX $CXX_VERSION")
 else
 CXX_VERSION=""
@@ -1369,7 +1379,7 @@ See the Installation chapter in the Reference Manual for more information.])
             AC_MSG_RESULT("no need to check headers")
         fi
         
-        AC_MSG_CHECKING("for pthread_create in -lpthread");
+        AC_MSG_CHECKING("for pthread_create in -lpthread")
         ac_save_LIBS="$LIBS"
         LIBS="$LIBS -lpthread"
         AC_TRY_LINK( [#include <pthread.h>],
@@ -1429,7 +1439,7 @@ then
       then
 	AC_MSG_RESULT("yes")
       else
-	AC_MSG_ERROR([On SCO UNIX MySQL must be compiled with gcc. See the Installation chapter in the Reference Manual.]);
+	AC_MSG_ERROR([On SCO UNIX MySQL must be compiled with gcc. See the Installation chapter in the Reference Manual.])
       fi
       AC_MSG_RESULT("yes")
     elif test -f /usr/local/lib/libpthread.a -o -f /usr/local/lib/libpthread.so
@@ -1445,7 +1455,7 @@ then
       then
 	AC_MSG_RESULT("yes")
       else
-	AC_MSG_ERROR([On SCO UNIX MySQL must be compiled with gcc. See the Installation chapter in the Reference Manual.]);
+	AC_MSG_ERROR([On SCO UNIX MySQL must be compiled with gcc. See the Installation chapter in the Reference Manual.])
       fi
       AC_MSG_RESULT("yes")
     # Hack for SCO UnixWare 7.1.x
@@ -1487,7 +1497,7 @@ then
         AC_MSG_RESULT("no")
       fi
     else
-      AC_MSG_ERROR([On SCO UNIX MySQL requires that the FSUThreads package is installed. See the Installation chapter in the Reference Manual.]);
+      AC_MSG_ERROR([On SCO UNIX MySQL requires that the FSUThreads package is installed. See the Installation chapter in the Reference Manual.])
     fi
   else
     AC_MSG_RESULT("no")
@@ -1585,7 +1595,7 @@ else
   if test "$with_mit_threads" = "no"
   then
     # pthread_create is in standard libraries (As in BSDI 3.0)
-    AC_MSG_CHECKING("for pthread_create in -libc");
+    AC_MSG_CHECKING("for pthread_create in -libc")
     AC_TRY_LINK(
     [#include <pthread.h>],
     [ (void) pthread_create((pthread_t*) 0,(pthread_attr_t*) 0, 0, 0); ],
@@ -1593,7 +1603,7 @@ else
     AC_MSG_RESULT("$with_posix_threads")
     if test "$with_posix_threads" = "no"
     then
-      AC_MSG_CHECKING("for pthread_create in -lpthread");
+      AC_MSG_CHECKING("for pthread_create in -lpthread")
       ac_save_LIBS="$LIBS"
       LIBS="$LIBS -lpthread"
       AC_TRY_LINK(
@@ -1604,7 +1614,7 @@ else
       if test "$with_posix_threads" = "no"
       then
         LIBS=" $ac_save_LIBS -lpthreads"
-        AC_MSG_CHECKING("for pthread_create in -lpthreads");
+        AC_MSG_CHECKING("for pthread_create in -lpthreads")
         AC_TRY_LINK(
         [#include <pthread.h>],
         [ pthread_create((pthread_t*) 0,(pthread_attr_t*) 0, 0, 0); ],
@@ -1614,7 +1624,7 @@ else
         then
 	  # This is for FreeBSD
 	  LIBS="$ac_save_LIBS -pthread"
-	  AC_MSG_CHECKING("for pthread_create in -pthread");
+	  AC_MSG_CHECKING("for pthread_create in -pthread")
 	  AC_TRY_LINK(
 	  [#include <pthread.h>],
 	  [ pthread_create((pthread_t*) 0,(pthread_attr_t*) 0, 0, 0); ],
@@ -1895,7 +1905,7 @@ if test "$ac_cv_conv_longlong_to_float" != "yes"
 then
   AC_MSG_ERROR([Your compiler cannot convert a longlong value to a float!
 If you are using gcc 2.8.# you should upgrade to egcs 1.0.3 or newer and try
-again]);
+again])
 fi
 fi
 AC_CHECK_TYPES([sigset_t, off_t], [], [], [#include <sys/types.h>])
@@ -2047,7 +2057,7 @@ CFLAGS="$ORG_CFLAGS"
 AC_CHECK_FUNC(fseeko,
 [if test "$large_file_support" = no -a "$TARGET_LINUX" = "true";
 then
-  AC_MSG_ERROR("Found fseeko symbol but large_file_support is not enabled!");
+  AC_MSG_ERROR("Found fseeko symbol but large_file_support is not enabled!")
 fi]
 )
 
@@ -2740,7 +2750,7 @@ do
       ;;
     *)
       AC_MSG_ERROR([Charset '$cs' not available. (Available are: $CHARSETS_AVAILABLE).
-      See the Installation chapter in the Reference Manual.]);
+      See the Installation chapter in the Reference Manual.])
   esac
 done
 
@@ -2917,7 +2927,7 @@ case $default_charset in
       ;;
     *)
       AC_MSG_ERROR([Charset $cs not available. (Available are: $CHARSETS_AVAILABLE).
-      See the Installation chapter in the Reference Manual.]);
+      See the Installation chapter in the Reference Manual.])
 esac
 
 if test "$default_collation" = default; then
@@ -2942,7 +2952,7 @@ else
       Collation $default_collation is not valid for character set $default_charset.
       Valid collations are: $default_charset_collations.
       See the Installation chapter in the Reference Manual.
-  ]);
+  ])
 fi
 
 AC_DEFINE_UNQUOTED([MYSQL_DEFAULT_CHARSET_NAME], ["$default_charset"],
diff --git a/innobase/buf/buf0buf.c b/innobase/buf/buf0buf.c
index 31a581d2ba8..90da3205a82 100644
--- a/innobase/buf/buf0buf.c
+++ b/innobase/buf/buf0buf.c
@@ -221,6 +221,9 @@ in the free list to the frames.
 5) When we have AWE enabled, we disable adaptive hash indexes.
 */
 
+/* Value in microseconds */
+static const int WAIT_FOR_READ	= 20000;
+
 buf_pool_t*	buf_pool = NULL; /* The buffer buf_pool of the database */
 
 ulint		buf_dbg_counter	= 0; /* This is used to insert validation
@@ -466,6 +469,9 @@ buf_block_init(
 
 	block->n_pointers = 0;
 
+	mutex_create(&block->mutex);
+	mutex_set_level(&block->mutex, SYNC_BUF_BLOCK);
+
 	rw_lock_create(&(block->lock));
 	ut_ad(rw_lock_validate(&(block->lock)));
 
@@ -734,8 +740,15 @@ buf_awe_map_page_to_frame(
 	bck = UT_LIST_GET_LAST(buf_pool->awe_LRU_free_mapped);
 
 	while (bck) {	
-		if (bck->state == BUF_BLOCK_FILE_PAGE
-	    	    && (bck->buf_fix_count != 0 || bck->io_fix != 0)) {
+		ibool skip;
+
+		mutex_enter(&bck->mutex);
+
+		skip = (bck->state == BUF_BLOCK_FILE_PAGE
+			&& (bck->buf_fix_count != 0 || bck->io_fix != 0));
+
+		if (skip) {
+			mutex_exit(&bck->mutex);
 
 			/* We have to skip this */
 			bck = UT_LIST_GET_PREV(awe_LRU_free_mapped, bck);
@@ -768,6 +781,8 @@ buf_awe_map_page_to_frame(
 
 			buf_pool->n_pages_awe_remapped++;
 			
+			mutex_exit(&bck->mutex);
+
 			return;
 		}
 	}
@@ -806,13 +821,22 @@ buf_block_make_young(
 /*=================*/
 	buf_block_t*	block)	/* in: block to make younger */
 {
+#ifdef UNIV_SYNC_DEBUG
+	ut_ad(!mutex_own(&(buf_pool->mutex)));
+#endif /* UNIV_SYNC_DEBUG */
+
+	/* Note that we read freed_page_clock's without holding any mutex:
+	this is allowed since the result is used only in heuristics */
+
 	if (buf_pool->freed_page_clock >= block->freed_page_clock 
-				+ 1 + (buf_pool->curr_size / 1024)) {
+				+ 1 + (buf_pool->curr_size / 4)) {
 
+		mutex_enter(&buf_pool->mutex);
 		/* There has been freeing activity in the LRU list:
 		best to move to the head of the LRU list */
 
 		buf_LRU_make_block_young(block);
+		mutex_exit(&buf_pool->mutex);
 	}
 }
 
@@ -847,12 +871,16 @@ buf_block_free(
 /*===========*/
 	buf_block_t*	block)	/* in, own: block to be freed */
 {
-	ut_a(block->state != BUF_BLOCK_FILE_PAGE);
-
 	mutex_enter(&(buf_pool->mutex));
 
+	mutex_enter(&block->mutex);
+
+	ut_a(block->state != BUF_BLOCK_FILE_PAGE);
+
 	buf_LRU_block_free_non_file_page(block);
 
+	mutex_exit(&block->mutex);
+
 	mutex_exit(&(buf_pool->mutex));
 }
 
@@ -1071,9 +1099,8 @@ buf_page_get_gen(
 #endif
 	buf_pool->n_page_gets++;
 loop:
-	mutex_enter_fast(&(buf_pool->mutex));
-
 	block = NULL;
+	mutex_enter_fast(&(buf_pool->mutex));
 	
 	if (guess) {
 		block = buf_block_align(guess);
@@ -1111,6 +1138,8 @@ loop:
 		goto loop;
 	}
 
+	mutex_enter(&block->mutex);
+
 	ut_a(block->state == BUF_BLOCK_FILE_PAGE);
 
 	must_read = FALSE;
@@ -1120,9 +1149,9 @@ loop:
 		must_read = TRUE;
 
 		if (mode == BUF_GET_IF_IN_POOL) {
-
 			/* The page is only being read to buffer */
-			mutex_exit(&(buf_pool->mutex));
+			mutex_exit(&buf_pool->mutex);
+			mutex_exit(&block->mutex);
 
 			return(NULL);
 		}
@@ -1146,7 +1175,7 @@ loop:
 #else
 	buf_block_buf_fix_inc(block);
 #endif
-	buf_block_make_young(block);
+	mutex_exit(&buf_pool->mutex);
 
 	/* Check if this is the first access to the page */
 
@@ -1154,10 +1183,13 @@ loop:
 
 	block->accessed = TRUE;
 
+	mutex_exit(&block->mutex);
+
+	buf_block_make_young(block);
+
 #ifdef UNIV_DEBUG_FILE_ACCESSES
 	ut_a(block->file_page_was_freed == FALSE);
 #endif	
-	mutex_exit(&(buf_pool->mutex));
 
 #ifdef UNIV_DEBUG
 	buf_dbg_counter++;
@@ -1182,13 +1214,14 @@ loop:
 		}
 
 		if (!success) {
-			mutex_enter(&(buf_pool->mutex));
+			mutex_enter(&block->mutex);
 
 			block->buf_fix_count--;
+
+			mutex_exit(&block->mutex);
 #ifdef UNIV_SYNC_DEBUG
 			rw_lock_s_unlock(&(block->debug_latch));
 #endif			
-			mutex_exit(&(buf_pool->mutex));
 
 			return(NULL);
 		}
@@ -1199,18 +1232,16 @@ loop:
 			completes */
 
 		        for (;;) {
-			        mutex_enter(&(buf_pool->mutex));
+				mutex_enter(&block->mutex);
 
 		                if (block->io_fix == BUF_IO_READ) {
 
-				        mutex_exit(&(buf_pool->mutex));
+					mutex_exit(&block->mutex);
 				  
-				        /* Sleep 20 milliseconds */
-
-				        os_thread_sleep(20000);
+					os_thread_sleep(WAIT_FOR_READ);
 				} else {
 				  
-				       mutex_exit(&(buf_pool->mutex));
+					mutex_exit(&block->mutex);
 
 				       break;
 				}
@@ -1268,14 +1299,14 @@ buf_page_optimistic_get_func(
 
 	ut_ad(mtr && block);
 	ut_ad((rw_latch == RW_S_LATCH) || (rw_latch == RW_X_LATCH));
-	
-	mutex_enter(&(buf_pool->mutex));
 
 	/* If AWE is used, block may have a different frame now, e.g., NULL */
-	
+
+	mutex_enter(&block->mutex);
+
 	if (block->state != BUF_BLOCK_FILE_PAGE || block->frame != guess) {
 
-		mutex_exit(&(buf_pool->mutex));
+		mutex_exit(&block->mutex);
 
 		return(FALSE);
 	}
@@ -1285,15 +1316,14 @@ buf_page_optimistic_get_func(
 #else
 	buf_block_buf_fix_inc(block);
 #endif
-	buf_block_make_young(block);
-
-	/* Check if this is the first access to the page */
-
 	accessed = block->accessed;
-
 	block->accessed = TRUE;
 
-	mutex_exit(&(buf_pool->mutex));
+	mutex_exit(&block->mutex);
+
+	buf_block_make_young(block);
+
+	/* Check if this is the first access to the page */
 
 	ut_ad(!ibuf_inside() || ibuf_page(block->space, block->offset));
 
@@ -1308,14 +1338,15 @@ buf_page_optimistic_get_func(
 	}
 
 	if (!success) {
-		mutex_enter(&(buf_pool->mutex));
-		
+		mutex_enter(&block->mutex);
+
 		block->buf_fix_count--;
+
+		mutex_exit(&block->mutex);
+
 #ifdef UNIV_SYNC_DEBUG
 		rw_lock_s_unlock(&(block->debug_latch));
-#endif			
-		mutex_exit(&(buf_pool->mutex));
-
+#endif
 		return(FALSE);
 	}
 
@@ -1329,14 +1360,15 @@ buf_page_optimistic_get_func(
 			rw_lock_x_unlock(&(block->lock));
 		}
 
-		mutex_enter(&(buf_pool->mutex));
-		
+		mutex_enter(&block->mutex);
+
 		block->buf_fix_count--;
+
+		mutex_exit(&block->mutex);
+
 #ifdef UNIV_SYNC_DEBUG
 		rw_lock_s_unlock(&(block->debug_latch));
-#endif			
-		mutex_exit(&(buf_pool->mutex));
-		
+#endif
 		return(FALSE);
 	}
 
@@ -1394,10 +1426,10 @@ buf_page_get_known_nowait(
 	ut_ad(mtr);
 	ut_ad((rw_latch == RW_S_LATCH) || (rw_latch == RW_X_LATCH));
 	
-	mutex_enter(&(buf_pool->mutex));
-
 	block = buf_block_align(guess);
 
+	mutex_enter(&block->mutex);
+
 	if (block->state == BUF_BLOCK_REMOVE_HASH) {
 	        /* Another thread is just freeing the block from the LRU list
 	        of the buffer pool: do not try to access this page; this
@@ -1406,7 +1438,7 @@ buf_page_get_known_nowait(
 		we have already removed it from the page address hash table
 		of the buffer pool. */
 
-	        mutex_exit(&(buf_pool->mutex));
+		mutex_exit(&block->mutex);
 
 		return(FALSE);
 	}
@@ -1418,12 +1450,12 @@ buf_page_get_known_nowait(
 #else
 	buf_block_buf_fix_inc(block);
 #endif
+	mutex_exit(&block->mutex);
+
 	if (mode == BUF_MAKE_YOUNG) {
 		buf_block_make_young(block);
 	}
 
-	mutex_exit(&(buf_pool->mutex));
-
 	ut_ad(!ibuf_inside() || (mode == BUF_KEEP_OLD));
 
 	if (rw_latch == RW_S_LATCH) {
@@ -1437,13 +1469,15 @@ buf_page_get_known_nowait(
 	}
 	
 	if (!success) {
-		mutex_enter(&(buf_pool->mutex));
+		mutex_enter(&block->mutex);
 		
 		block->buf_fix_count--;
+
+		mutex_exit(&block->mutex);
+
 #ifdef UNIV_SYNC_DEBUG
 		rw_lock_s_unlock(&(block->debug_latch));
 #endif		
-		mutex_exit(&(buf_pool->mutex));
 
 		return(FALSE);
 	}
@@ -1491,8 +1525,7 @@ buf_page_init_for_backup_restore(
 	block->offset 		= offset;
 
 	block->lock_hash_val	= 0;
-	block->lock_mutex	= NULL;
-	
+
 	block->freed_page_clock = 0;
 
 	block->newest_modification = ut_dulint_zero;
@@ -1524,6 +1557,7 @@ buf_page_init(
 {
 #ifdef UNIV_SYNC_DEBUG
 	ut_ad(mutex_own(&(buf_pool->mutex)));
+	ut_ad(mutex_own(&(block->mutex)));
 #endif /* UNIV_SYNC_DEBUG */
 	ut_a(block->state != BUF_BLOCK_FILE_PAGE);
 
@@ -1537,8 +1571,7 @@ buf_page_init(
 	block->check_index_page_at_flush = FALSE;
 	
 	block->lock_hash_val	= lock_rec_hash(space, offset);
-	block->lock_mutex	= NULL;
-	
+
 	/* Insert into the hash table of file pages */
 
         if (buf_page_hash_get(space, offset)) {
@@ -1630,6 +1663,7 @@ buf_page_init_for_read(
 	ut_a(block);
 
 	mutex_enter(&(buf_pool->mutex));
+	mutex_enter(&block->mutex);
 
 	if (fil_tablespace_deleted_or_being_deleted_in_mem(space,
 							tablespace_version)) {
@@ -1642,7 +1676,9 @@ buf_page_init_for_read(
 		/* The page belongs to a space which has been deleted or is
 		being deleted, or the page is already in buf_pool, return */
 
+		mutex_exit(&block->mutex);
 		mutex_exit(&(buf_pool->mutex));
+
 		buf_block_free(block);
 
 		if (mode == BUF_READ_IBUF_PAGES_ONLY) {
@@ -1662,6 +1698,7 @@ buf_page_init_for_read(
 	buf_LRU_add_block(block, TRUE); 	/* TRUE == to old blocks */
 	
 	block->io_fix = BUF_IO_READ;
+
 	buf_pool->n_pend_reads++;
 	
 	/* We set a pass-type x-lock on the frame because then the same
@@ -1673,6 +1710,7 @@ buf_page_init_for_read(
 	
 	rw_lock_x_lock_gen(&(block->lock), BUF_IO_READ);
 	
+	mutex_exit(&block->mutex);
  	mutex_exit(&(buf_pool->mutex));
 
 	if (mode == BUF_READ_IBUF_PAGES_ONLY) {
@@ -1735,6 +1773,8 @@ buf_page_create(
 
 	block = free_block;
 	
+	mutex_enter(&block->mutex);
+
 	buf_page_init(space, offset, block);
 
 	/* The block must be put to the LRU list */
@@ -1745,13 +1785,15 @@ buf_page_create(
 #else
 	buf_block_buf_fix_inc(block);
 #endif
+	buf_pool->n_pages_created++;
+
+	mutex_exit(&(buf_pool->mutex));
+
 	mtr_memo_push(mtr, block, MTR_MEMO_BUF_FIX);
 
 	block->accessed = TRUE;
 	
-	buf_pool->n_pages_created++;
-
-	mutex_exit(&(buf_pool->mutex));
+	mutex_exit(&block->mutex);
 
 	/* Delete possible entries for the page from the insert buffer:
 	such can exist if the page belonged to an index which was dropped */
@@ -1800,6 +1842,12 @@ buf_page_io_complete(
 
 	ut_a(block->state == BUF_BLOCK_FILE_PAGE);
 
+	/* We do not need protect block->io_fix here by block->mutex to read
+	it because this is the only function where we can change the value
+	from BUF_IO_READ or BUF_IO_WRITE to some other value, and our code
+	ensures that this is the only thread that handles the i/o for this
+	block. */
+
 	io_type = block->io_fix;
 
 	if (io_type == BUF_IO_READ) {
@@ -1868,11 +1916,12 @@ buf_page_io_complete(
 		}
 	}
 	
+	mutex_enter(&(buf_pool->mutex));
+	mutex_enter(&block->mutex);
+
 #ifdef UNIV_IBUF_DEBUG
 	ut_a(ibuf_count_get(block->space, block->offset) == 0);
 #endif
-	mutex_enter(&(buf_pool->mutex));
-	
 	/* Because this thread which does the unlocking is not the same that
 	did the locking, we use a pass value != 0 in unlock, which simply
 	removes the newest lock debug record, without checking the thread
@@ -1911,6 +1960,7 @@ buf_page_io_complete(
 		}
 	}
 	
+	mutex_exit(&block->mutex);
 	mutex_exit(&(buf_pool->mutex));
 
 	if (buf_debug_prints) {
@@ -1970,6 +2020,8 @@ buf_validate(void)
 
 		block = buf_pool_get_nth_block(buf_pool, i);
 
+		mutex_enter(&block->mutex);
+
 		if (block->state == BUF_BLOCK_FILE_PAGE) {
 
 			ut_a(buf_page_hash_get(block->space,
@@ -2013,6 +2065,8 @@ buf_validate(void)
 		} else if (block->state == BUF_BLOCK_NOT_USED) {
 			n_free++;
 		}
+
+		mutex_exit(&block->mutex);
  	}
 
 	if (n_lru + n_free > buf_pool->curr_size) {
@@ -2303,16 +2357,21 @@ buf_all_freed(void)
 
 		block = buf_pool_get_nth_block(buf_pool, i);
 
+		mutex_enter(&block->mutex);
+
 		if (block->state == BUF_BLOCK_FILE_PAGE) {
 
 			if (!buf_flush_ready_for_replace(block)) {
 
 				fprintf(stderr,
 					"Page %lu %lu still fixed or dirty\n",
-					(ulong) block->space, (ulong) block->offset);
+					(ulong) block->space,
+					(ulong) block->offset);
 			    	ut_error;
 			}
 		}
+
+		mutex_exit(&block->mutex);
  	}
 
 	mutex_exit(&(buf_pool->mutex));
diff --git a/innobase/buf/buf0flu.c b/innobase/buf/buf0flu.c
index 4df0e9962fb..a8252781f61 100644
--- a/innobase/buf/buf0flu.c
+++ b/innobase/buf/buf0flu.c
@@ -114,6 +114,7 @@ buf_flush_ready_for_replace(
 {
 #ifdef UNIV_SYNC_DEBUG
 	ut_ad(mutex_own(&(buf_pool->mutex)));
+	ut_ad(mutex_own(&block->mutex));
 #endif /* UNIV_SYNC_DEBUG */
 	if (block->state != BUF_BLOCK_FILE_PAGE) {
 		ut_print_timestamp(stderr);
@@ -148,6 +149,7 @@ buf_flush_ready_for_flush(
 {
 #ifdef UNIV_SYNC_DEBUG
 	ut_ad(mutex_own(&(buf_pool->mutex)));
+	ut_ad(mutex_own(&(block->mutex)));
 #endif /* UNIV_SYNC_DEBUG */
 	ut_a(block->state == BUF_BLOCK_FILE_PAGE);
 
@@ -533,8 +535,15 @@ buf_flush_try_page(
 
 	ut_a(!block || block->state == BUF_BLOCK_FILE_PAGE);
 
+	if (!block) {
+		mutex_exit(&(buf_pool->mutex));
+		return(0);
+	}
+
+	mutex_enter(&block->mutex);
+
 	if (flush_type == BUF_FLUSH_LIST
-	    && block && buf_flush_ready_for_flush(block, flush_type)) {
+	    && buf_flush_ready_for_flush(block, flush_type)) {
 	
 		block->io_fix = BUF_IO_WRITE;
 
@@ -572,6 +581,7 @@ buf_flush_try_page(
 			locked = TRUE;
 		}
 
+		mutex_exit(&block->mutex);
 		mutex_exit(&(buf_pool->mutex));
 
 		if (!locked) {
@@ -590,8 +600,8 @@ buf_flush_try_page(
 		
 		return(1);
 
-	} else if (flush_type == BUF_FLUSH_LRU && block
-			&& buf_flush_ready_for_flush(block, flush_type)) {
+	} else if (flush_type == BUF_FLUSH_LRU
+		   && buf_flush_ready_for_flush(block, flush_type)) {
 
 		/* VERY IMPORTANT:
 		Because any thread may call the LRU flush, even when owning
@@ -631,14 +641,15 @@ buf_flush_try_page(
 		buf_pool mutex: this ensures that the latch is acquired
 		immediately. */
 		
+		mutex_exit(&block->mutex);
 		mutex_exit(&(buf_pool->mutex));
 
 		buf_flush_write_block_low(block);
 
 		return(1);
 
-	} else if (flush_type == BUF_FLUSH_SINGLE_PAGE && block
-			&& buf_flush_ready_for_flush(block, flush_type)) {
+	} else if (flush_type == BUF_FLUSH_SINGLE_PAGE
+		   && buf_flush_ready_for_flush(block, flush_type)) {
 	
 		block->io_fix = BUF_IO_WRITE;
 
@@ -664,6 +675,7 @@ buf_flush_try_page(
 
 		(buf_pool->n_flush[flush_type])++;
 
+		mutex_exit(&block->mutex);
 		mutex_exit(&(buf_pool->mutex));
 
 		rw_lock_s_lock_gen(&(block->lock), BUF_IO_WRITE);
@@ -678,11 +690,12 @@ buf_flush_try_page(
 		buf_flush_write_block_low(block);
 		
 		return(1);
-	} else {
-		mutex_exit(&(buf_pool->mutex));
+	}
 
-		return(0);
-	}		
+	mutex_exit(&block->mutex);
+	mutex_exit(&(buf_pool->mutex));
+
+	return(0);
 }
 
 /***************************************************************
@@ -727,34 +740,48 @@ buf_flush_try_neighbors(
 		block = buf_page_hash_get(space, i);
 		ut_a(!block || block->state == BUF_BLOCK_FILE_PAGE);
 
-		if (block && flush_type == BUF_FLUSH_LRU && i != offset
-		    && !block->old) {
+		if (!block) {
+
+			continue;
+
+		} else if (flush_type == BUF_FLUSH_LRU && i != offset
+			   && !block->old) {
 
 		        /* We avoid flushing 'non-old' blocks in an LRU flush,
 		        because the flushed blocks are soon freed */
 
 		        continue;
-		}
+		} else {
+
+			mutex_enter(&block->mutex);
+
+			if (buf_flush_ready_for_flush(block, flush_type)
+			    && (i == offset || block->buf_fix_count == 0)) {
+				/* We only try to flush those
+				neighbors != offset where the buf fix count is
+				zero, as we then know that we probably can
+				latch the page without a semaphore wait.
+				Semaphore waits are expensive because we must
+				flush the doublewrite buffer before we start
+				waiting. */
 
-		if (block && buf_flush_ready_for_flush(block, flush_type)
-		   && (i == offset || block->buf_fix_count == 0)) {
-			/* We only try to flush those neighbors != offset
-			where the buf fix count is zero, as we then know that
-			we probably can latch the page without a semaphore
-			wait. Semaphore waits are expensive because we must
-			flush the doublewrite buffer before we start
-			waiting. */
+				mutex_exit(&block->mutex);
 
-			mutex_exit(&(buf_pool->mutex));
+				mutex_exit(&(buf_pool->mutex));
 
-			/* Note: as we release the buf_pool mutex above, in
-			buf_flush_try_page we cannot be sure the page is still
-			in a flushable state: therefore we check it again
-			inside that function. */
+				/* Note: as we release the buf_pool mutex
+				above, in buf_flush_try_page we cannot be sure
+				the page is still in a flushable state:
+				therefore we check it again inside that
+				function. */
 
-			count += buf_flush_try_page(space, i, flush_type);
+				count += buf_flush_try_page(space, i,
+							    flush_type);
 
-			mutex_enter(&(buf_pool->mutex));
+				mutex_enter(&(buf_pool->mutex));
+			} else {
+				mutex_exit(&block->mutex);
+			}
 		}
 	}
 				
@@ -848,12 +875,15 @@ buf_flush_batch(
 	    	while ((block != NULL) && !found) {
 			ut_a(block->state == BUF_BLOCK_FILE_PAGE);
 
+			mutex_enter(&block->mutex);
+
 			if (buf_flush_ready_for_flush(block, flush_type)) {
 
 				found = TRUE;
 				space = block->space;
 				offset = block->offset;
 	    
+				mutex_exit(&block->mutex);
 				mutex_exit(&(buf_pool->mutex));
 
 				old_page_count = page_count;
@@ -871,10 +901,14 @@ buf_flush_batch(
 
 			} else if (flush_type == BUF_FLUSH_LRU) {
 
+				mutex_exit(&block->mutex);
+
 				block = UT_LIST_GET_PREV(LRU, block);
 			} else {
 				ut_ad(flush_type == BUF_FLUSH_LIST);
 
+				mutex_exit(&block->mutex);
+
 				block = UT_LIST_GET_PREV(flush_list, block);
 			}
 	    	}
@@ -951,10 +985,14 @@ buf_flush_LRU_recommendation(void)
 	       				+ BUF_FLUSH_EXTRA_MARGIN)
 	       && (distance < BUF_LRU_FREE_SEARCH_LEN)) {
 
+		mutex_enter(&block->mutex);
+
 		if (buf_flush_ready_for_replace(block)) {
 			n_replaceable++;
 		}
 
+		mutex_exit(&block->mutex);
+
 		distance++;
 			
 		block = UT_LIST_GET_PREV(LRU, block);
diff --git a/innobase/buf/buf0lru.c b/innobase/buf/buf0lru.c
index 05e92933edf..681b4d81462 100644
--- a/innobase/buf/buf0lru.c
+++ b/innobase/buf/buf0lru.c
@@ -86,6 +86,9 @@ scan_again:
 	block = UT_LIST_GET_LAST(buf_pool->LRU);
 
 	while (block != NULL) {
+
+		mutex_enter(&block->mutex);
+
 	        ut_a(block->state == BUF_BLOCK_FILE_PAGE);
 
 		if (block->space == id
@@ -112,6 +115,8 @@ scan_again:
 			if (block->is_hashed) {
 				page_no = block->offset;
 			
+				mutex_exit(&block->mutex);
+
 				mutex_exit(&(buf_pool->mutex));
 
 				/* Note that the following call will acquire
@@ -138,6 +143,7 @@ scan_again:
 			buf_LRU_block_free_hashed_page(block);
 		}
 next_page:
+		mutex_exit(&block->mutex);
 		block = UT_LIST_GET_PREV(LRU, block);
 	}
 
@@ -211,6 +217,9 @@ buf_LRU_search_and_free_block(
 
 	while (block != NULL) {
 	        ut_a(block->in_LRU_list);
+
+		mutex_enter(&block->mutex);
+
 		if (buf_flush_ready_for_replace(block)) {
 
 			if (buf_debug_prints) {
@@ -223,6 +232,7 @@ buf_LRU_search_and_free_block(
 			buf_LRU_block_remove_hashed_page(block);
 
 			mutex_exit(&(buf_pool->mutex));
+			mutex_exit(&block->mutex);
 
 			/* Remove possible adaptive hash index built on the
 			page; in the case of AWE the block may not have a
@@ -231,15 +241,21 @@ buf_LRU_search_and_free_block(
 			if (block->frame) {
 				btr_search_drop_page_hash_index(block->frame);
 			}
-			mutex_enter(&(buf_pool->mutex));
 
 			ut_a(block->buf_fix_count == 0);
 
+			mutex_enter(&(buf_pool->mutex));
+			mutex_enter(&block->mutex);
+
 			buf_LRU_block_free_hashed_page(block);
 			freed = TRUE;
+			mutex_exit(&block->mutex);
 
 			break;
 		}
+
+		mutex_exit(&block->mutex);
+
 		block = UT_LIST_GET_PREV(LRU, block);
 		distance++;
 
@@ -413,8 +429,12 @@ loop:
 			}
 		}
 		
+		mutex_enter(&block->mutex);
+
 		block->state = BUF_BLOCK_READY_FOR_USE;
 
+		mutex_exit(&block->mutex);
+
 		mutex_exit(&(buf_pool->mutex));
 
 		if (started_monitor) {
@@ -815,6 +835,7 @@ buf_LRU_block_free_non_file_page(
 {
 #ifdef UNIV_SYNC_DEBUG
 	ut_ad(mutex_own(&(buf_pool->mutex)));
+	ut_ad(mutex_own(&block->mutex));
 #endif /* UNIV_SYNC_DEBUG */
 	ut_ad(block);
 	
@@ -854,6 +875,7 @@ buf_LRU_block_remove_hashed_page(
 {
 #ifdef UNIV_SYNC_DEBUG
 	ut_ad(mutex_own(&(buf_pool->mutex)));
+	ut_ad(mutex_own(&block->mutex));
 #endif /* UNIV_SYNC_DEBUG */
 	ut_ad(block);
 	
@@ -911,6 +933,7 @@ buf_LRU_block_free_hashed_page(
 {
 #ifdef UNIV_SYNC_DEBUG
 	ut_ad(mutex_own(&(buf_pool->mutex)));
+	ut_ad(mutex_own(&block->mutex));
 #endif /* UNIV_SYNC_DEBUG */
 	ut_a(block->state == BUF_BLOCK_REMOVE_HASH);
 
diff --git a/innobase/include/buf0buf.h b/innobase/include/buf0buf.h
index 53599d03c73..f9c69581476 100644
--- a/innobase/include/buf0buf.h
+++ b/innobase/include/buf0buf.h
@@ -455,8 +455,8 @@ Gets the mutex number protecting the page record lock hash chain in the lock
 table. */
 UNIV_INLINE
 mutex_t*
-buf_frame_get_lock_mutex(
-/*=====================*/
+buf_frame_get_mutex(
+/*================*/
 			/* out: mutex */
 	byte*	ptr);	/* in: pointer to within a buffer frame */
 /***********************************************************************
@@ -699,7 +699,10 @@ struct buf_block_struct{
 
 	ulint		magic_n;	/* magic number to check */
 	ulint		state;		/* state of the control block:
-					BUF_BLOCK_NOT_USED, ... */
+					BUF_BLOCK_NOT_USED, ...; changing
+					this is only allowed when a thread
+					has BOTH the buffer pool mutex AND
+					block->mutex locked */
 	byte*		frame;		/* pointer to buffer frame which
 					is of size UNIV_PAGE_SIZE, and
 					aligned to an address divisible by
@@ -717,8 +720,12 @@ struct buf_block_struct{
 	ulint		offset;		/* page number within the space */
 	ulint		lock_hash_val;	/* hashed value of the page address
 					in the record lock hash table */
-	mutex_t*	lock_mutex;	/* mutex protecting the chain in the
-					record lock hash table */
+	mutex_t		mutex;		/* mutex protecting this block:
+					state (also protected by the buffer
+					pool mutex), io_fix, buf_fix_count,
+					and accessed; we introduce this new
+					mutex in InnoDB-5.1 to relieve
+					contention on the buffer pool mutex */
 	rw_lock_t	lock;		/* read-write lock of the buffer
 					frame */
 	buf_block_t*	hash;		/* node used in chaining to the page
@@ -774,20 +781,27 @@ struct buf_block_struct{
 					in heuristic algorithms, because of
 					the possibility of a wrap-around! */
 	ulint		freed_page_clock;/* the value of freed_page_clock
-					buffer pool when this block was
-					last time put to the head of the
-					LRU list */
+					of the buffer pool when this block was
+					the last time put to the head of the
+					LRU list; a thread is allowed to
+					read this for heuristic purposes
+					without holding any mutex or latch */
 	ibool		old;		/* TRUE if the block is in the old
 					blocks in the LRU list */
 	ibool		accessed;	/* TRUE if the page has been accessed
 					while in the buffer pool: read-ahead
 					may read in pages which have not been
-					accessed yet */
+					accessed yet; this is protected by
+					block->mutex; a thread is allowed to
+					read this for heuristic purposes
+					without holding any mutex or latch */
 	ulint		buf_fix_count;	/* count of how manyfold this block
-					is currently bufferfixed */
+					is currently bufferfixed; this is
+					protected by block->mutex */
 	ulint		io_fix;		/* if a read is pending to the frame,
 					io_fix is BUF_IO_READ, in the case
-					of a write BUF_IO_WRITE, otherwise 0 */
+					of a write BUF_IO_WRITE, otherwise 0;
+					this is protected by block->mutex */
 	/* 4. Optimistic search field */
 
 	dulint		modify_clock;	/* this clock is incremented every
@@ -940,7 +954,9 @@ struct buf_pool_struct{
 					number of buffer blocks removed from
 					the end of the LRU list; NOTE that
 					this counter may wrap around at 4
-					billion! */
+					billion! A thread is allowed to
+					read this for heuristic purposes
+					without holding any mutex or latch */
 	ulint		LRU_flush_ended;/* when an LRU flush ends for a page,
 					this is incremented by one; this is
 					set to zero when a buffer block is
diff --git a/innobase/include/buf0buf.ic b/innobase/include/buf0buf.ic
index 681a0ef000a..8a18b2fb0fa 100644
--- a/innobase/include/buf0buf.ic
+++ b/innobase/include/buf0buf.ic
@@ -333,8 +333,8 @@ Gets the mutex number protecting the page record lock hash chain in the lock
 table. */
 UNIV_INLINE
 mutex_t*
-buf_frame_get_lock_mutex(
-/*=====================*/
+buf_frame_get_mutex(
+/*================*/
 			/* out: mutex */
 	byte*	ptr)	/* in: pointer to within a buffer frame */
 {
@@ -342,7 +342,7 @@ buf_frame_get_lock_mutex(
 
 	block = buf_block_align(ptr);
 
-	return(block->lock_mutex);
+	return(&block->mutex);
 }
 
 /*************************************************************************
@@ -521,6 +521,7 @@ buf_block_buf_fix_inc_debug(
 	ret = rw_lock_s_lock_func_nowait(&(block->debug_latch), file, line);
 
 	ut_ad(ret == TRUE);
+	ut_ad(mutex_own(&block->mutex));
 #endif
 	block->buf_fix_count++;
 }
@@ -533,6 +534,9 @@ buf_block_buf_fix_inc(
 /*==================*/
 	buf_block_t*	block)	/* in: block to bufferfix */
 {
+#ifdef UNIV_SYNC_DEBUG
+	ut_ad(mutex_own(&block->mutex));
+#endif
 	block->buf_fix_count++;
 }
 #endif /* UNIV_SYNC_DEBUG */
@@ -627,23 +631,24 @@ buf_page_release(
 	
 	ut_ad(block);
 
-	mutex_enter_fast(&(buf_pool->mutex));
-
 	ut_a(block->state == BUF_BLOCK_FILE_PAGE);
 	ut_a(block->buf_fix_count > 0);
 
 	if (rw_latch == RW_X_LATCH && mtr->modifications) {
-
+		mutex_enter(&buf_pool->mutex);
 		buf_flush_note_modification(block, mtr);
+		mutex_exit(&buf_pool->mutex);
 	}
 
+	mutex_enter(&block->mutex);
+
 #ifdef UNIV_SYNC_DEBUG
 	rw_lock_s_unlock(&(block->debug_latch));
 #endif
 	buf_fix_count = block->buf_fix_count;
 	block->buf_fix_count = buf_fix_count - 1;
 
-	mutex_exit(&(buf_pool->mutex));
+	mutex_exit(&block->mutex);
 
 	if (rw_latch == RW_S_LATCH) {
 		rw_lock_s_unlock(&(block->lock));
diff --git a/innobase/include/sync0arr.h b/innobase/include/sync0arr.h
index fecd910683e..ba712d14aad 100644
--- a/innobase/include/sync0arr.h
+++ b/innobase/include/sync0arr.h
@@ -75,17 +75,12 @@ sync_array_free_cell(
 	sync_array_t*	arr,	/* in: wait array */
         ulint    	index);  /* in: index of the cell in array */
 /**************************************************************************
-Looks for the cells in the wait array which refer
-to the wait object specified,
-and sets their corresponding events to the signaled state. In this
-way releases the threads waiting for the object to contend for the object.
-It is possible that no such cell is found, in which case does nothing. */
+Note that one of the wait objects was signalled. */
 
 void
-sync_array_signal_object(
-/*=====================*/
-	sync_array_t*	arr,	/* in: wait array */
-	void*		object);/* in: wait object */
+sync_array_object_signalled(
+/*========================*/
+	sync_array_t*	arr);	/* in: wait array */
 /**************************************************************************
 If the wakeup algorithm does not work perfectly at semaphore relases,
 this function will do the waking (see the comment in mutex_exit). This
diff --git a/innobase/include/sync0rw.h b/innobase/include/sync0rw.h
index 9a988a03e92..c59608e0916 100644
--- a/innobase/include/sync0rw.h
+++ b/innobase/include/sync0rw.h
@@ -410,6 +410,7 @@ blocked by readers, a writer may queue for the lock by setting the writer
 field. Then no new readers are allowed in. */
 
 struct rw_lock_struct {
+	os_event_t	event;	/* Used by sync0arr.c for thread queueing */
 	ulint	reader_count;	/* Number of readers who have locked this
 				lock in the shared mode */
 	ulint	writer; 	/* This field is set to RW_LOCK_EX if there
diff --git a/innobase/include/sync0rw.ic b/innobase/include/sync0rw.ic
index 3a92100ba01..92a75059ee3 100644
--- a/innobase/include/sync0rw.ic
+++ b/innobase/include/sync0rw.ic
@@ -380,7 +380,8 @@ rw_lock_s_unlock_func(
 	mutex_exit(mutex);
 
 	if (sg == TRUE) {
-		sync_array_signal_object(sync_primary_wait_array, lock);
+		os_event_set(lock->event);
+		sync_array_object_signalled(sync_primary_wait_array);
 	}
 
         ut_ad(rw_lock_validate(lock));
@@ -459,7 +460,8 @@ rw_lock_x_unlock_func(
 	mutex_exit(&(lock->mutex));
 
 	if (sg == TRUE) {
-		sync_array_signal_object(sync_primary_wait_array, lock);
+		os_event_set(lock->event);
+		sync_array_object_signalled(sync_primary_wait_array);
 	}
 
         ut_ad(rw_lock_validate(lock));
diff --git a/innobase/include/sync0sync.h b/innobase/include/sync0sync.h
index 8e0ec715b12..1b008c69d3c 100644
--- a/innobase/include/sync0sync.h
+++ b/innobase/include/sync0sync.h
@@ -447,6 +447,7 @@ Do not use its fields directly! The structure used in the spin lock
 implementation of a mutual exclusion semaphore. */
 
 struct mutex_struct {
+	os_event_t	event;	/* Used by sync0arr.c for the wait queue */
 	ulint	lock_word;	/* This ulint is the target of the atomic
 				test-and-set instruction in Win32 */
 #if !defined(_WIN32) || !defined(UNIV_CAN_USE_X86_ASSEMBLER)
diff --git a/innobase/os/os0sync.c b/innobase/os/os0sync.c
index 4ad9473fe66..bf82f69023d 100644
--- a/innobase/os/os0sync.c
+++ b/innobase/os/os0sync.c
@@ -21,6 +21,7 @@ Created 9/6/1995 Heikki Tuuri
 
 /* Type definition for an operating system mutex struct */
 struct os_mutex_struct{ 
+	os_event_t	event;	/* Used by sync0arr.c for queing threads */
 	void*		handle;	/* OS handle to mutex */
 	ulint		count;	/* we use this counter to check
 				that the same thread does not
@@ -35,6 +36,7 @@ struct os_mutex_struct{
 /* Mutex protecting counts and the lists of OS mutexes and events */
 os_mutex_t	os_sync_mutex;
 ibool		os_sync_mutex_inited	= FALSE;
+ibool		os_sync_free_called	= FALSE;
 
 /* This is incremented by 1 in os_thread_create and decremented by 1 in
 os_thread_exit */
@@ -50,6 +52,10 @@ ulint	os_event_count		= 0;
 ulint	os_mutex_count		= 0;
 ulint	os_fast_mutex_count	= 0;
 
+/* Because a mutex is embedded inside an event and there is an
+event embedded inside a mutex, on free, this generates a recursive call.
+This version of the free event function doesn't acquire the global lock */
+static void os_event_free_internal(os_event_t	event);
 
 /*************************************************************
 Initializes global event and OS 'slow' mutex lists. */
@@ -76,6 +82,7 @@ os_sync_free(void)
 	os_event_t	event;
 	os_mutex_t	mutex;
 
+	os_sync_free_called = TRUE;
 	event = UT_LIST_GET_FIRST(os_event_list);
 
 	while (event) {
@@ -99,6 +106,7 @@ os_sync_free(void)
 
 	      mutex = UT_LIST_GET_FIRST(os_mutex_list);
 	}
+	os_sync_free_called = FALSE;
 }
 
 /*************************************************************
@@ -146,14 +154,21 @@ os_event_create(
 	event->signal_count = 0;
 #endif /* __WIN__ */
 
-        /* Put to the list of events */
-	os_mutex_enter(os_sync_mutex);
+	/* The os_sync_mutex can be NULL because during startup an event
+	can be created [ because it's embedded in the mutex/rwlock ] before
+	this module has been initialized */
+	if (os_sync_mutex != NULL) {
+		os_mutex_enter(os_sync_mutex);
+	}
 
+	/* Put to the list of events */
 	UT_LIST_ADD_FIRST(os_event_list, os_event_list, event);
 
 	os_event_count++;
 
-	os_mutex_exit(os_sync_mutex);
+	if (os_sync_mutex != NULL) {
+		os_mutex_exit(os_sync_mutex);
+	}
 
 	return(event);
 }
@@ -256,6 +271,35 @@ os_event_reset(
 }
 
 /**************************************************************
+Frees an event object, without acquiring the global lock. */
+static
+void
+os_event_free_internal(
+/*===================*/
+	os_event_t	event)	/* in: event to free */
+{
+#ifdef __WIN__
+	ut_a(event);
+
+	ut_a(CloseHandle(event->handle));
+#else
+	ut_a(event);
+
+	/* This is to avoid freeing the mutex twice */
+	os_fast_mutex_free(&(event->os_mutex));
+
+	ut_a(0 == pthread_cond_destroy(&(event->cond_var)));
+#endif
+	/* Remove from the list of events */
+
+	UT_LIST_REMOVE(os_event_list, os_event_list, event);
+
+	os_event_count--;
+
+	ut_free(event);
+}
+
+/**************************************************************
 Frees an event object. */
 
 void
@@ -456,6 +500,7 @@ os_mutex_create(
 
 	mutex_str->handle = mutex;
 	mutex_str->count = 0;
+	mutex_str->event = os_event_create(NULL);
 
 	if (os_sync_mutex_inited) {
 		/* When creating os_sync_mutex itself we cannot reserve it */
@@ -532,6 +577,10 @@ os_mutex_free(
 {
 	ut_a(mutex);
 
+	if (!os_sync_free_called) {
+		os_event_free_internal(mutex->event);
+	}
+
 	if (os_sync_mutex_inited) {
 		os_mutex_enter(os_sync_mutex);
 	}
diff --git a/innobase/sync/sync0arr.c b/innobase/sync/sync0arr.c
index 198ef49ca9f..64f9310bad3 100644
--- a/innobase/sync/sync0arr.c
+++ b/innobase/sync/sync0arr.c
@@ -62,9 +62,6 @@ struct sync_cell_struct {
 	ibool		waiting;	/* TRUE if the thread has already
 					called sync_array_event_wait
 					on this cell */
-	ibool		event_set;	/* TRUE if the event is set */
-        os_event_t 	event;   	/* operating system event
-                                        semaphore handle */
 	time_t		reservation_time;/* time when the thread reserved
 					the wait cell */
 };
@@ -218,10 +215,7 @@ sync_array_create(
         for (i = 0; i < n_cells; i++) {
 		cell = sync_array_get_nth_cell(arr, i);        	
                 cell->wait_object = NULL;
-
-                /* Create an operating system event semaphore with no name */
-                cell->event = os_event_create(NULL);
-		cell->event_set = FALSE; /* it is created in reset state */
+		cell->waiting = FALSE;
 	}
 
 	return(arr);
@@ -235,19 +229,12 @@ sync_array_free(
 /*============*/
 	sync_array_t*	arr)	/* in, own: sync wait array */
 {
-        ulint           i;
-        sync_cell_t*   	cell;
 	ulint		protection;
 
         ut_a(arr->n_reserved == 0);
         
 	sync_array_validate(arr);
         
-        for (i = 0; i < arr->n_cells; i++) {
-		cell = sync_array_get_nth_cell(arr, i);        	
-		os_event_free(cell->event);
-        }
-
 	protection = arr->protection;
 
         /* Release the mutex protecting the wait array complex */
@@ -293,27 +280,19 @@ sync_array_validate(
 }
 
 /***********************************************************************
-Puts the cell event in set state. */
-static
-void
-sync_cell_event_set(
-/*================*/
-	sync_cell_t*	cell)	/* in: array cell */
-{
-	os_event_set(cell->event);
-	cell->event_set = TRUE;
-}		
-
-/***********************************************************************
 Puts the cell event in reset state. */
 static
 void
 sync_cell_event_reset(
 /*==================*/
-	sync_cell_t*	cell)	/* in: array cell */
+	ulint		type,	/* in: lock type mutex/rw_lock */
+	void*		object) /* in: the rw_lock/mutex object */
 {
-	os_event_reset(cell->event);
-	cell->event_set = FALSE;
+	if (type == SYNC_MUTEX) {
+		os_event_reset(((mutex_t *) object)->event);
+	} else {
+		os_event_reset(((rw_lock_t *) object)->event);
+	}
 }		
 
 /**********************************************************************
@@ -346,14 +325,7 @@ sync_array_reserve_cell(
 
                 if (cell->wait_object == NULL) {
 
-                        /* Make sure the event is reset */
-			if (cell->event_set) {	
-                        	sync_cell_event_reset(cell);
-			}
-
-			cell->reservation_time = time(NULL);
-			cell->thread = os_thread_get_curr_id();
-
+			cell->waiting = FALSE;
 			cell->wait_object = object;
 
 			if (type == SYNC_MUTEX) {
@@ -363,7 +335,6 @@ sync_array_reserve_cell(
 			}
 				
 			cell->request_type = type;
-			cell->waiting = FALSE;
 			
 			cell->file = file;
 			cell->line = line;
@@ -373,6 +344,13 @@ sync_array_reserve_cell(
 			*index = i;
 
 			sync_array_exit(arr);
+
+			/* Make sure the event is reset */
+			sync_cell_event_reset(type, object);
+
+			cell->reservation_time = time(NULL);
+
+			cell->thread = os_thread_get_curr_id();
                         
                         return;
                 }
@@ -408,7 +386,12 @@ sync_array_wait_event(
 	ut_a(!cell->waiting);
 	ut_ad(os_thread_get_curr_id() == cell->thread);
 
-       	event = cell->event;
+	if (cell->request_type == SYNC_MUTEX) {
+		event = ((mutex_t*) cell->wait_object)->event;
+	} else {
+		event = ((rw_lock_t*) cell->wait_object)->event;
+	}
+
        	cell->waiting = TRUE;
 
 #ifdef UNIV_SYNC_DEBUG
@@ -510,10 +493,6 @@ sync_array_cell_print(
         if (!cell->waiting) {
 		fputs("wait has ended\n", file);
 	}
-
-        if (cell->event_set) {
-		fputs("wait is ending\n", file);
-	}
 }
 
 #ifdef UNIV_SYNC_DEBUG
@@ -623,7 +602,7 @@ sync_array_detect_deadlock(
 	
 	depth++;
 	
-	if (cell->event_set || !cell->waiting) {
+	if (!cell->waiting) {
 
 		return(FALSE); /* No deadlock here */
 	}
@@ -802,6 +781,7 @@ sync_array_free_cell(
 
         ut_a(cell->wait_object != NULL);
 
+	cell->waiting = FALSE;
 	cell->wait_object =  NULL;
 
 	ut_a(arr->n_reserved > 0);
@@ -811,44 +791,17 @@ sync_array_free_cell(
 }
 
 /**************************************************************************
-Looks for the cells in the wait array which refer to the wait object
-specified, and sets their corresponding events to the signaled state. In this
-way releases the threads waiting for the object to contend for the object.
-It is possible that no such cell is found, in which case does nothing. */
+Increments the signalled count. */
 
 void
-sync_array_signal_object(
-/*=====================*/
-	sync_array_t*	arr,	/* in: wait array */
-	void*		object)	/* in: wait object */
+sync_array_object_signalled(
+/*========================*/
+	sync_array_t*	arr)	/* in: wait array */
 {
-        sync_cell_t*   	cell;
-        ulint           count;
-        ulint           i;
-
         sync_array_enter(arr);
 
 	arr->sg_count++;
 
-	i = 0;
-	count = 0;
-
-        while (count < arr->n_reserved) {
-
-        	cell = sync_array_get_nth_cell(arr, i);
-
-                if (cell->wait_object != NULL) {
-
-                        count++;
-                        if (cell->wait_object == object) {
-
-                        	sync_cell_event_set(cell);
-                        }
-                }
-
-                i++;
-        }
-
         sync_array_exit(arr);
 }
 
@@ -881,7 +834,17 @@ sync_arr_wake_threads_if_sema_free(void)
 
                         if (sync_arr_cell_can_wake_up(cell)) {
 
-                        	sync_cell_event_set(cell);
+				if (cell->request_type == SYNC_MUTEX) {
+					mutex_t*	mutex;
+
+					mutex = cell->wait_object;
+					os_event_set(mutex->event);
+				} else {
+					rw_lock_t*	lock;
+
+					lock = cell->wait_object;
+					os_event_set(lock->event);
+				}
                         }
                 }
 
@@ -911,7 +874,7 @@ sync_array_print_long_waits(void)
 
         	cell = sync_array_get_nth_cell(sync_primary_wait_array, i);
 
-                if (cell->wait_object != NULL
+		if (cell->wait_object != NULL && cell->waiting
 		    && difftime(time(NULL), cell->reservation_time) > 240) {
 			fputs("InnoDB: Warning: a long semaphore wait:\n",
 				stderr);
@@ -919,7 +882,7 @@ sync_array_print_long_waits(void)
 			noticed = TRUE;
                 }
 
-                if (cell->wait_object != NULL
+		if (cell->wait_object != NULL && cell->waiting
 		    && difftime(time(NULL), cell->reservation_time)
 		    > fatal_timeout) {
 			fatal = TRUE;
diff --git a/innobase/sync/sync0rw.c b/innobase/sync/sync0rw.c
index 77757685208..384c2e6dfad 100644
--- a/innobase/sync/sync0rw.c
+++ b/innobase/sync/sync0rw.c
@@ -123,6 +123,7 @@ rw_lock_create_func(
 	lock->last_x_file_name = "not yet reserved";
 	lock->last_s_line = 0;
 	lock->last_x_line = 0;
+	lock->event = os_event_create(NULL);
 
 	mutex_enter(&rw_lock_list_mutex);
 	
@@ -158,6 +159,7 @@ rw_lock_free(
 	mutex_free(rw_lock_get_mutex(lock));
 
 	mutex_enter(&rw_lock_list_mutex);
+	os_event_free(lock->event);
 
 	if (UT_LIST_GET_PREV(list, lock)) {
 		ut_a(UT_LIST_GET_PREV(list, lock)->magic_n == RW_LOCK_MAGIC_N);
diff --git a/innobase/sync/sync0sync.c b/innobase/sync/sync0sync.c
index 86306e49cac..468789c120d 100644
--- a/innobase/sync/sync0sync.c
+++ b/innobase/sync/sync0sync.c
@@ -210,6 +210,7 @@ mutex_create_func(
 	os_fast_mutex_init(&(mutex->os_fast_mutex));
 	mutex->lock_word = 0;
 #endif
+	mutex->event = os_event_create(NULL);
 	mutex_set_waiters(mutex, 0);
 	mutex->magic_n = MUTEX_MAGIC_N;
 #ifdef UNIV_SYNC_DEBUG
@@ -275,6 +276,8 @@ mutex_free(
 		mutex_exit(&mutex_list_mutex);
 	}
 
+	os_event_free(mutex->event);
+
 #if !defined(_WIN32) || !defined(UNIV_CAN_USE_X86_ASSEMBLER) 
 	os_fast_mutex_free(&(mutex->os_fast_mutex));
 #endif
@@ -498,8 +501,8 @@ mutex_signal_object(
 
 	/* The memory order of resetting the waiters field and
 	signaling the object is important. See LEMMA 1 above. */
-
-	sync_array_signal_object(sync_primary_wait_array, mutex);
+	os_event_set(mutex->event);
+	sync_array_object_signalled(sync_primary_wait_array);
 }
 
 #ifdef UNIV_SYNC_DEBUG
@@ -1047,6 +1050,7 @@ sync_thread_add_level(
 		ut_a(sync_thread_levels_g(array, SYNC_PURGE_SYS));
 	} else if (level == SYNC_TREE_NODE) {
 		ut_a(sync_thread_levels_contain(array, SYNC_INDEX_TREE)
+		     || sync_thread_levels_contain(array, SYNC_DICT_OPERATION)
 		     || sync_thread_levels_g(array, SYNC_TREE_NODE - 1));
 	} else if (level == SYNC_TREE_NODE_FROM_HASH) {
 		ut_a(1);
diff --git a/libmysql/libmysql.c b/libmysql/libmysql.c
index e963c0e429c..6916c643f6c 100644
--- a/libmysql/libmysql.c
+++ b/libmysql/libmysql.c
@@ -4522,14 +4522,11 @@ my_bool STDCALL mysql_stmt_free_result(MYSQL_STMT *stmt)
   {
     MYSQL *mysql= stmt->mysql;
 
-    if (result->data)
-    {
-      /* Result buffered */
-      free_root(&result->alloc, MYF(MY_KEEP_PREALLOC));
-      result->data= NULL;
-      result->rows= 0;
-      stmt->data_cursor= NULL;
-    }
+    /* Result buffered */
+    free_root(&result->alloc, MYF(MY_KEEP_PREALLOC));
+    result->data= NULL;
+    result->rows= 0;
+    stmt->data_cursor= NULL;
 
     if (mysql && stmt->field_count &&
         (int) stmt->state > (int) MYSQL_STMT_PREPARE_DONE)
diff --git a/libmysqld/lib_sql.cc b/libmysqld/lib_sql.cc
index 7f2059db7cd..0665641d3b6 100644
--- a/libmysqld/lib_sql.cc
+++ b/libmysqld/lib_sql.cc
@@ -668,7 +668,7 @@ bool Protocol::send_fields(List<Item> *list, uint flag)
     DBUG_RETURN(0);
 
   field_count= list->elements;
-  field_alloc= thd->current_stmt ? &thd->current_stmt->mem_root :
+  field_alloc= thd->current_stmt ? &thd->current_stmt->result.alloc :
                                    &mysql->field_alloc;
   if (!(client_field= mysql->fields= 
 	(MYSQL_FIELD *)alloc_root(field_alloc, 
diff --git a/mysql-test/mysql-test-run.pl b/mysql-test/mysql-test-run.pl
index d60bb4663f2..2cf18222868 100755
--- a/mysql-test/mysql-test-run.pl
+++ b/mysql-test/mysql-test-run.pl
@@ -188,6 +188,7 @@ our $opt_force;
 our $opt_reorder= 0;
 our $opt_enable_disabled;
 our $opt_mem= $ENV{'MTR_MEM'};
+our $opt_report_features;
 
 our $opt_gcov;
 our $opt_gcov_err;
diff --git a/mysql-test/r/symlink.result b/mysql-test/r/symlink.result
index 32dc72b8219..09715d30703 100644
--- a/mysql-test/r/symlink.result
+++ b/mysql-test/r/symlink.result
@@ -91,23 +91,15 @@ t1	CREATE TABLE `t1` (
 ) ENGINE=MyISAM DEFAULT CHARSET=latin1
 drop table t1;
 CREATE TABLE t1(a INT)
-DATA DIRECTORY='TEST_DIR/master-data/mysql'
-INDEX DIRECTORY='TEST_DIR/master-data/mysql';
-RENAME TABLE t1 TO user;
-ERROR HY000: Can't create/write to file 'TEST_DIR/master-data/mysql/user.MYI' (Errcode: 17)
-DROP TABLE t1;
-show create table t1;
-Table	Create Table
-t1	CREATE TABLE `t1` (
-  `i` int(11) default NULL
-) ENGINE=MyISAM DEFAULT CHARSET=latin1
-drop table t1;
-show create table t1;
-Table	Create Table
-t1	CREATE TABLE `t1` (
-  `i` int(11) default NULL
-) ENGINE=MyISAM DEFAULT CHARSET=latin1
-drop table t1;
+DATA DIRECTORY='TEST_DIR/tmp'
+INDEX DIRECTORY='TEST_DIR/tmp';
+ERROR HY000: Can't create/write to file 'TEST_DIR/tmp/t1.MYI' (Errcode: 17)
+CREATE TABLE t2(a INT)
+DATA DIRECTORY='TEST_DIR/tmp'
+INDEX DIRECTORY='TEST_DIR/tmp';
+RENAME TABLE t2 TO t1;
+ERROR HY000: Can't create/write to file 'TEST_DIR/tmp/t1.MYI' (Errcode: 17)
+DROP TABLE t2;
 show create table t1;
 Table	Create Table
 t1	CREATE TEMPORARY TABLE `t1` (
@@ -144,4 +136,16 @@ t1	CREATE TABLE `t1` (
 ) ENGINE=MyISAM DEFAULT CHARSET=latin1 DATA DIRECTORY='MYSQLTEST_VARDIR/tmp/'
 drop table t1;
 deallocate prepare stmt;
+CREATE TABLE t1(a INT)
+DATA DIRECTORY='TEST_DIR/var/master-data/test';
+ERROR HY000: Incorrect arguments to DATA DIRECORY
+CREATE TABLE t1(a INT)
+DATA DIRECTORY='TEST_DIR/var/master-data/';
+ERROR HY000: Incorrect arguments to DATA DIRECORY
+CREATE TABLE t1(a INT)
+INDEX DIRECTORY='TEST_DIR/var/master-data';
+ERROR HY000: Incorrect arguments to INDEX DIRECORY
+CREATE TABLE t1(a INT)
+INDEX DIRECTORY='TEST_DIR/var/master-data_var';
+ERROR HY000: Can't create/write to file 'TEST_DIR/var/master-data_var/t1.MYI' (Errcode: 2)
 End of 4.1 tests
diff --git a/mysql-test/t/symlink.test b/mysql-test/t/symlink.test
index 40127a697ac..c8790c450f9 100644
--- a/mysql-test/t/symlink.test
+++ b/mysql-test/t/symlink.test
@@ -121,29 +121,22 @@ drop table t1;
 #
 # BUG#32111 - Security Breach via DATA/INDEX DIRECORY and RENAME TABLE
 #
+--write_file $MYSQLTEST_VARDIR/tmp/t1.MYI
+EOF
 --replace_result $MYSQLTEST_VARDIR TEST_DIR
+--error 1
 eval CREATE TABLE t1(a INT)
-DATA DIRECTORY='$MYSQLTEST_VARDIR/master-data/mysql'
-INDEX DIRECTORY='$MYSQLTEST_VARDIR/master-data/mysql';
+DATA DIRECTORY='$MYSQLTEST_VARDIR/tmp'
+INDEX DIRECTORY='$MYSQLTEST_VARDIR/tmp';
+--replace_result $MYSQLTEST_VARDIR TEST_DIR
+eval CREATE TABLE t2(a INT)
+DATA DIRECTORY='$MYSQLTEST_VARDIR/tmp'
+INDEX DIRECTORY='$MYSQLTEST_VARDIR/tmp';
 --replace_result $MYSQLTEST_VARDIR TEST_DIR
 --error 1
-RENAME TABLE t1 TO user;
-DROP TABLE t1;
-
-#
-# Test specifying DATA DIRECTORY that is the same as what would normally
-# have been chosen. (Bug #8707)
-#
-disable_query_log;
-eval create table t1 (i int) data directory = "$MYSQL_TEST_DIR/var/master-data/test/";
-enable_query_log;
-show create table t1;
-drop table t1;
-disable_query_log;
-eval create table t1 (i int) index directory = "$MYSQL_TEST_DIR/var/master-data/test/";
-enable_query_log;
-show create table t1;
-drop table t1;
+RENAME TABLE t2 TO t1;
+DROP TABLE t2;
+--remove_file $MYSQLTEST_VARDIR/tmp/t1.MYI
 
 #
 # Bug#8706 - temporary table with data directory option fails
@@ -201,4 +194,24 @@ show create table t1;
 drop table t1;
 deallocate prepare stmt;
 
+#
+# Bug#32167 another privilege bypass with DATA/INDEX DIRECORY
+#
+--replace_result $MYSQL_TEST_DIR TEST_DIR
+--error 1210
+eval CREATE TABLE t1(a INT)
+DATA DIRECTORY='$MYSQL_TEST_DIR/var/master-data/test';
+--replace_result $MYSQL_TEST_DIR TEST_DIR
+--error 1210
+eval CREATE TABLE t1(a INT)
+DATA DIRECTORY='$MYSQL_TEST_DIR/var/master-data/';
+--replace_result $MYSQL_TEST_DIR TEST_DIR
+--error 1210
+eval CREATE TABLE t1(a INT)
+INDEX DIRECTORY='$MYSQL_TEST_DIR/var/master-data';
+--replace_result $MYSQL_TEST_DIR TEST_DIR
+--error 1
+eval CREATE TABLE t1(a INT)
+INDEX DIRECTORY='$MYSQL_TEST_DIR/var/master-data_var';
+
 --echo End of 4.1 tests
diff --git a/mysys/mf_pack.c b/mysys/mf_pack.c
index 049aa59a578..485b2c5ec3d 100644
--- a/mysys/mf_pack.c
+++ b/mysys/mf_pack.c
@@ -272,7 +272,7 @@ void symdirget(char *dir)
 
   SYNOPSIS
     unpack_dirname()
-    to			Store result here.  May be = from
+    to			result-buffer, FN_REFLEN characters. may be == from
     from		'Packed' directory name (may contain ~)
 
  IMPLEMENTATION
@@ -398,7 +398,7 @@ uint unpack_filename(my_string to, const char *from)
 
 	/* Convert filename (unix standard) to system standard */
 	/* Used before system command's like open(), create() .. */
-	/* Returns length of to */
+	/* Returns used length of to; total length should be FN_REFLEN */
 
 uint system_filename(my_string to, const char *from)
 {
diff --git a/ndb/src/common/util/SocketServer.cpp b/ndb/src/common/util/SocketServer.cpp
index 755764c7700..3486567e33d 100644
--- a/ndb/src/common/util/SocketServer.cpp
+++ b/ndb/src/common/util/SocketServer.cpp
@@ -111,7 +111,7 @@ SocketServer::setup(SocketServer::Service * service,
   const int on = 1;
   if (setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, 
 		 (const char*)&on, sizeof(on)) == -1) {
-    DBUG_PRINT("error",("getsockopt() - %d - %s",
+    DBUG_PRINT("error",("setsockopt() - %d - %s",
 			errno, strerror(errno)));
     NDB_CLOSE_SOCKET(sock);
     DBUG_RETURN(false);
diff --git a/scripts/make_binary_distribution.sh b/scripts/make_binary_distribution.sh
index 917ac0a19c1..24a99df2248 100644
--- a/scripts/make_binary_distribution.sh
+++ b/scripts/make_binary_distribution.sh
@@ -322,11 +322,13 @@ BASE=$BASE2
 #
 
 if [ x"@GXX@" = x"yes" ] ; then
-  gcclib=`@CC@ @CFLAGS@ --print-libgcc-file`
-  if [ $? -ne 0 ] ; then
-    echo "Warning: Couldn't find libgcc.a!"
-  else
+  gcclib=`@CC@ @CFLAGS@ --print-libgcc-file 2>/dev/null` || true
+  if [ -z "$gcclib" ] ; then
+    echo "Warning: Compiler doesn't tell libgcc.a!"
+  elif [ -f "$gcclib" ] ; then
     $CP $gcclib $BASE/lib/libmygcc.a
+  else
+    echo "Warning: Compiler result '$gcclib' not found / no file!"
   fi
 fi
 
diff --git a/sql/log.cc b/sql/log.cc
index b91ec2b3dee..4e0964fe9d6 100644
--- a/sql/log.cc
+++ b/sql/log.cc
@@ -963,10 +963,10 @@ err:
 void MYSQL_LOG::make_log_name(char* buf, const char* log_ident)
 {
   uint dir_len = dirname_length(log_file_name); 
-  if (dir_len > FN_REFLEN)
+  if (dir_len >= FN_REFLEN)
     dir_len=FN_REFLEN-1;
   strnmov(buf, log_file_name, dir_len);
-  strmake(buf+dir_len, log_ident, FN_REFLEN - dir_len);
+  strmake(buf+dir_len, log_ident, FN_REFLEN - dir_len -1);
 }
 
 
diff --git a/sql/mysql_priv.h b/sql/mysql_priv.h
index b6170ba35f9..4b0031d1f2a 100644
--- a/sql/mysql_priv.h
+++ b/sql/mysql_priv.h
@@ -890,6 +890,7 @@ void my_dbopt_free(void);
 extern time_t start_time;
 extern char *mysql_data_home,server_version[SERVER_VERSION_LENGTH],
 	    mysql_real_data_home[], *opt_mysql_tmpdir, mysql_charsets_dir[],
+	    mysql_unpacked_real_data_home[],
             def_ft_boolean_syntax[sizeof(ft_boolean_syntax)];
 #define mysql_tmpdir (my_tmpdir(&mysql_tmpdir_list))
 extern MY_TMPDIR mysql_tmpdir_list;
diff --git a/sql/mysqld.cc b/sql/mysqld.cc
index 62105e0093a..8111df7ad4d 100644
--- a/sql/mysqld.cc
+++ b/sql/mysqld.cc
@@ -390,6 +390,7 @@ const char *opt_date_time_formats[3];
 char compiled_default_collation_name[]= MYSQL_DEFAULT_COLLATION_NAME;
 char *language_ptr, *default_collation_name, *default_character_set_name;
 char mysql_data_home_buff[2], *mysql_data_home=mysql_real_data_home;
+char mysql_unpacked_real_data_home[FN_REFLEN];
 struct passwd *user_info;
 char server_version[SERVER_VERSION_LENGTH];
 char *mysqld_unix_port, *opt_mysql_tmpdir;
@@ -6896,6 +6897,9 @@ static void fix_paths(void)
     pos[1]= 0;
   }
   convert_dirname(mysql_real_data_home,mysql_real_data_home,NullS);
+  (void) fn_format(buff, mysql_real_data_home, "", "",
+                   (MY_RETURN_REAL_PATH|MY_RESOLVE_SYMLINKS));
+  (void) unpack_dirname(mysql_unpacked_real_data_home, buff);
   convert_dirname(language,language,NullS);
   (void) my_load_path(mysql_home,mysql_home,""); // Resolve current dir
   (void) my_load_path(mysql_real_data_home,mysql_real_data_home,mysql_home);
diff --git a/sql/repl_failsafe.cc b/sql/repl_failsafe.cc
index 4c8703226a6..4ea90346638 100644
--- a/sql/repl_failsafe.cc
+++ b/sql/repl_failsafe.cc
@@ -926,7 +926,7 @@ int load_master_data(THD* thd)
 			     0, (SLAVE_IO | SLAVE_SQL)))
           send_error(thd, ER_MASTER_INFO);
 	strmake(active_mi->master_log_name, row[0],
-		sizeof(active_mi->master_log_name));
+		sizeof(active_mi->master_log_name) -1);
 	active_mi->master_log_pos= my_strtoll10(row[1], (char**) 0, &error);
         /* at least in recent versions, the condition below should be false */
 	if (active_mi->master_log_pos < BIN_LOG_HEADER_SIZE)
diff --git a/sql/sql_parse.cc b/sql/sql_parse.cc
index 24f9ef30569..4bbd425d80b 100644
--- a/sql/sql_parse.cc
+++ b/sql/sql_parse.cc
@@ -65,7 +65,8 @@ static bool append_file_to_dir(THD *thd, const char **filename_ptr,
 			       const char *table_name);
              
 static TABLE_LIST* get_table_by_alias(TABLE_LIST* tl, const char* db,
-  const char* alias);      
+  const char* alias);
+static bool test_if_data_home_dir(const char *dir);
 
 const char *any_db="*any*";	// Special symbol for check_access
 
@@ -2531,6 +2532,20 @@ mysql_execute_command(THD *thd)
                    "INDEX DIRECTORY option ignored");
     create_info.data_file_name= create_info.index_file_name= NULL;
 #else
+
+    if (test_if_data_home_dir(lex->create_info.data_file_name))
+    {
+      my_error(ER_WRONG_ARGUMENTS,MYF(0),"DATA DIRECORY");
+      res= -1;
+      break;
+    }
+    if (test_if_data_home_dir(lex->create_info.index_file_name))
+    {
+      my_error(ER_WRONG_ARGUMENTS,MYF(0),"INDEX DIRECORY");
+      res= -1;
+      break;
+    }
+
     /* Fix names if symlinked tables */
     if (append_file_to_dir(thd, &create_info.data_file_name,
 			   create_table->real_name) ||
@@ -5920,3 +5935,47 @@ Item *negate_expression(THD *thd, Item *expr)
     return negated;
   return new Item_func_not(expr);
 }
+
+
+/*
+  Check if path does not contain mysql data home directory
+
+  SYNOPSIS
+    test_if_data_home_dir()
+    dir                     directory
+    conv_home_dir           converted data home directory
+    home_dir_len            converted data home directory length
+
+  RETURN VALUES
+    0	ok
+    1	error  
+*/
+
+static bool test_if_data_home_dir(const char *dir)
+{
+  char path[FN_REFLEN], conv_path[FN_REFLEN];
+  uint dir_len, home_dir_len= strlen(mysql_unpacked_real_data_home);
+  DBUG_ENTER("test_if_data_home_dir");
+
+  if (!dir)
+    DBUG_RETURN(0);
+
+  (void) fn_format(path, dir, "", "",
+                   (MY_RETURN_REAL_PATH|MY_RESOLVE_SYMLINKS));
+  dir_len= unpack_dirname(conv_path, dir);
+
+  if (home_dir_len <= dir_len)
+  {
+    if (lower_case_file_system)
+    {
+      if (!my_strnncoll(default_charset_info, (const uchar*) conv_path,
+                        home_dir_len,
+                        (const uchar*) mysql_unpacked_real_data_home,
+                        home_dir_len))
+        DBUG_RETURN(1);
+    }
+    else if (!memcmp(conv_path, mysql_unpacked_real_data_home, home_dir_len))
+      DBUG_RETURN(1);
+  }
+  DBUG_RETURN(0);
+}
diff --git a/sql/sql_show.cc b/sql/sql_show.cc
index bf0e254d3e4..741d30e6a99 100644
--- a/sql/sql_show.cc
+++ b/sql/sql_show.cc
@@ -136,7 +136,8 @@ int mysqld_show_tables(THD *thd,const char *db,const char *wild)
 {
   Item_string *field=new Item_string("",0,thd->charset());
   List<Item> field_list;
-  char path[FN_LEN],*end;
+  char path[FN_REFLEN],*end;                    // for unpack_dirname()
+
   List<char> files;
   char *file_name;
   Protocol *protocol= thd->protocol;
@@ -457,7 +458,7 @@ int mysqld_extend_show_tables(THD *thd,const char *db,const char *wild)
   Item *item;
   List<char> files;
   List<Item> field_list;
-  char path[FN_LEN];
+  char path[FN_REFLEN];                         // for unpack_dirname()
   char *file_name;
   TABLE *table;
   Protocol *protocol= thd->protocol;
diff --git a/sql/unireg.cc b/sql/unireg.cc
index e5ee0222f20..dcb49bc1766 100644
--- a/sql/unireg.cc
+++ b/sql/unireg.cc
@@ -140,6 +140,14 @@ bool mysql_create_frm(THD *thd, my_string file_name,
   strmake((char*) forminfo+47,create_info->comment ? create_info->comment : "",
 	  60);
   forminfo[46]=(uchar) strlen((char*)forminfo+47);	// Length of comment
+#ifdef EXTRA_DEBUG
+  /*
+    EXTRA_DEBUG causes strmake() to initialize its buffer behind the
+    payload with a magic value to detect wrong buffer-sizes. We
+    explicitly zero that segment again.
+  */
+  memset((char*) forminfo+47 + forminfo[46], 0, 61 - forminfo[46]);
+#endif
 
   if (my_pwrite(file,(byte*) fileinfo,64,0L,MYF_RW) ||
       my_pwrite(file,(byte*) keybuff,key_info_length,
diff --git a/strings/strmake.c b/strings/strmake.c
index d2252f648f6..47d8a04e361 100644
--- a/strings/strmake.c
+++ b/strings/strmake.c
@@ -28,23 +28,25 @@
 #include <my_global.h>
 #include "m_string.h"
 
-#ifdef BAD_STRING_COMPILER
-
-char *strmake(char *dst,const char *src,uint length)
+char *strmake(register char *dst, register const char *src, uint length)
 {
-  reg1 char *res;
-
-  if ((res=memccpy(dst,src,0,length)))
-    return res-1;
-  dst[length]=0;
-  return dst+length;
-}
-
-#define strmake strmake_overlapp	/* Use orginal for overlapping str */
+#ifdef EXTRA_DEBUG
+  /*
+    'length' is the maximum length of the string; the buffer needs
+    to be one character larger to accomodate the terminating '\0'.
+    This is easy to get wrong, so we make sure we write to the
+    entire length of the buffer to identify incorrect buffer-sizes.
+    We only initialise the "unused" part of the buffer here, a) for
+    efficiency, and b) because dst==src is allowed, so initialising
+    the entire buffer would overwrite the source-string. Also, we
+    write a character rather than '\0' as this makes spotting these
+    problems in the results easier.
+  */
+  uint n= strlen(src) + 1;
+  if (n <= length)
+    memset(dst + n, (int) 'Z', length - n + 1);
 #endif
 
-char *strmake(register char *dst, register const char *src, uint length)
-{
   while (length--)
     if (! (*dst++ = *src++))
       return dst-1;
diff --git a/support-files/mysql.spec.sh b/support-files/mysql.spec.sh
index b28af51d43e..c6d599c5842 100644
--- a/support-files/mysql.spec.sh
+++ b/support-files/mysql.spec.sh
@@ -1,4 +1,22 @@
-%define mysql_version		@VERSION@
+# Copyright (C) 2000-2007 MySQL AB
+# 
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; version 2 of the License.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License
+# along with this program; see the file COPYING. If not, write to the
+# Free Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston
+# MA  02110-1301  USA.
+
+%define mysql_version   @VERSION@
+%define mysql_vendor    MySQL AB
+
 # use "rpmbuild --with static" or "rpm --define '_with_static 1'" (for RPM 3.x)
 # to enable static linking (off by default)
 %{?_with_static:%define STATIC_BUILD 1}
@@ -9,7 +27,7 @@
 %define release 0.glibc23
 %endif
 %define license GPL
-%define mysqld_user		mysql
+%define mysqld_user	mysql
 %define mysqld_group	mysql
 %define server_suffix -standard
 %define mysqldatadir /var/lib/mysql
@@ -20,6 +38,23 @@
 
 %define see_base For a description of MySQL see the base MySQL RPM or http://www.mysql.com
 
+# On SuSE 9 no separate "debuginfo" package is built. To enable basic
+# debugging on that platform, we don't strip binaries on SuSE 9. We
+# disable the strip of binaries by redefining the RPM macro
+# "__os_install_post" leaving out the script calls that normally does
+# this. We do this in all cases, as on platforms where "debuginfo" is
+# created, a script "find-debuginfo.sh" will be called that will do
+# the strip anyway, part of separating the executable and debug
+# information into separate files put into separate packages.
+#
+# Some references (shows more advanced conditional usage):
+# http://www.redhat.com/archives/rpm-list/2001-November/msg00257.html
+# http://www.redhat.com/archives/rpm-list/2003-February/msg00275.html
+# http://www.redhat.com/archives/rhl-devel-list/2004-January/msg01546.html
+# http://lists.opensuse.org/archive/opensuse-commit/2006-May/1171.html
+
+%define __os_install_post /usr/lib/rpm/brp-compress
+
 Name: MySQL
 Summary:	MySQL: a very fast and reliable SQL database server
 Group:		Applications/Databases
@@ -29,7 +64,7 @@ License:	%{license}
 Source:		http://www.mysql.com/Downloads/MySQL-@MYSQL_BASE_VERSION@/mysql-%{mysql_version}.tar.gz
 URL:		http://www.mysql.com/
 Packager:	MySQL Production Engineering Team <build@mysql.com>
-Vendor:		MySQL AB
+Vendor:		%{mysql_vendor}
 Provides:	msqlormysql MySQL-server mysql
 BuildRequires: ncurses-devel
 Obsoletes:	mysql
@@ -46,12 +81,9 @@ is intended for mission-critical, heavy-load production systems as well
 as for embedding into mass-deployed software. MySQL is a trademark of
 MySQL AB.
 
-The MySQL software has Dual Licensing, which means you can use the MySQL
-software free of charge under the GNU General Public License
-(http://www.gnu.org/licenses/). You can also purchase commercial MySQL
-licenses from MySQL AB if you do not wish to be bound by the terms of
-the GPL. See the chapter "Licensing and Support" in the manual for
-further info.
+Copyright (C) 2000-2007 MySQL AB
+This software comes with ABSOLUTELY NO WARRANTY. This is free software,
+and you are welcome to modify and redistribute it under the GPL license.
 
 The MySQL web site (http://www.mysql.com/) provides the latest
 news and information about the MySQL software. Also please see the
@@ -71,12 +103,9 @@ is intended for mission-critical, heavy-load production systems as well
 as for embedding into mass-deployed software. MySQL is a trademark of
 MySQL AB.
 
-The MySQL software has Dual Licensing, which means you can use the MySQL
-software free of charge under the GNU General Public License
-(http://www.gnu.org/licenses/). You can also purchase commercial MySQL
-licenses from MySQL AB if you do not wish to be bound by the terms of
-the GPL. See the chapter "Licensing and Support" in the manual for
-further info.
+Copyright (C) 2000-2007 MySQL AB
+This software comes with ABSOLUTELY NO WARRANTY. This is free software,
+and you are welcome to modify and redistribute it under the GPL license.
 
 The MySQL web site (http://www.mysql.com/) provides the latest
 news and information about the MySQL software. Also please see the
@@ -86,7 +115,7 @@ This package includes the MySQL server binary (incl. InnoDB) as well
 as related utilities to run and administrate a MySQL server.
 
 If you want to access and work with the database, you have to install
-package "MySQL-client" as well!
+the package "MySQL-client" as well!
 
 %package client
 Summary: MySQL - Client
@@ -253,7 +282,7 @@ sh -c  "PATH=\"${MYSQL_BUILD_PATH:-$PATH}\" \
             --includedir=%{_includedir} \
             --mandir=%{_mandir} \
 	    --enable-thread-safe-client \
-	    --with-readline ;
+	    --with-readline ; \
 	    # Add this for more debugging support
 	    # --with-debug
 	    # Add this for MyISAM RAID support:
@@ -319,7 +348,10 @@ then
   cp -fp config.log "$MYSQL_MAXCONFLOG_DEST"
 fi
 
-make test-bt
+( cd mysql-test
+  perl ./mysql-test-run.pl --comment="max"    --force --report-features
+  perl ./mysql-test-run.pl --comment="max+ps" --force --ps-protocol
+  true )
 
 # Save mysqld-max
 ./libtool --mode=execute cp sql/mysqld sql/mysqld-max
@@ -332,7 +364,7 @@ make test-bt
 (cd ndb; make install DESTDIR=$RBR)
 
 # Install embedded server library in the build root
-install -m 644 libmysqld/libmysqld.a $RBR%{_libdir}/mysql/
+install -m644 libmysqld/libmysqld.a $RBR%{_libdir}/mysql/
 
 # Include libgcc.a in the devel subpackage (BUG 4921)
 if expr "$CC" : ".*gcc.*" > /dev/null ;
@@ -341,7 +373,7 @@ then
   if [ -f $libgcc ]
   then
     %define have_libgcc 1
-    install -m 644 $libgcc $RBR%{_libdir}/mysql/libmygcc.a
+    install -m644 $libgcc $RBR%{_libdir}/mysql/libmygcc.a
   fi
 fi
 
@@ -382,10 +414,8 @@ then
   cp -fp config.log "$MYSQL_CONFLOG_DEST"
 fi
 
-( cd mysql-test
-  perl ./mysql-test-run.pl --force --report-features
-  perl ./mysql-test-run.pl --force --ps-protocol
-  true )
+echo "# standard"
+make test-bt
 
 %install
 RBR=$RPM_BUILD_ROOT
@@ -400,7 +430,6 @@ install -d $RBR%{_libdir}
 install -d $RBR%{_mandir}
 install -d $RBR%{_sbindir}
 
-
 # Install all binaries stripped 
 make install-strip DESTDIR=$RBR benchdir_root=%{_datadir}
 
@@ -414,12 +443,12 @@ install -s -m755 $MBD/sql/mysqld-max $RBR%{_sbindir}/mysqld-max
 install -s -m755 $MBD/extra/perror.ndb $RBR%{_bindir}/perror
 
 # install symbol files ( for stack trace resolution)
-install -m644 $MBD/sql/mysqld-max.sym $RBR%{_libdir}/mysql/mysqld-max.sym
-install -m644 $MBD/sql/mysqld.sym $RBR%{_libdir}/mysql/mysqld.sym
+install -m 644 $MBD/sql/mysqld-max.sym $RBR%{_libdir}/mysql/mysqld-max.sym
+install -m 644 $MBD/sql/mysqld.sym $RBR%{_libdir}/mysql/mysqld.sym
 
 # Install logrotate and autostart
-install -m644 $MBD/support-files/mysql-log-rotate $RBR%{_sysconfdir}/logrotate.d/mysql
-install -m755 $MBD/support-files/mysql.server $RBR%{_sysconfdir}/init.d/mysql
+install -m 644 $MBD/support-files/mysql-log-rotate $RBR%{_sysconfdir}/logrotate.d/mysql
+install -m 755 $MBD/support-files/mysql.server $RBR%{_sysconfdir}/init.d/mysql
 
 # Create a symlink "rcmysql", pointing to the init.script. SuSE users
 # will appreciate that, as all services usually offer this.
@@ -451,7 +480,7 @@ fi
 mysql_datadir=%{mysqldatadir}
 
 # Create data directory if needed
-if test ! -d $mysql_datadir; then mkdir -m755 $mysql_datadir; fi
+if test ! -d $mysql_datadir; then mkdir -m 755 $mysql_datadir; fi
 if test ! -d $mysql_datadir/mysql; then mkdir $mysql_datadir/mysql; fi
 if test ! -d $mysql_datadir/test; then mkdir $mysql_datadir/test; fi
 
@@ -493,12 +522,11 @@ chmod -R og-rw $mysql_datadir/mysql
 # Allow safe_mysqld to start mysqld and print a message before we exit
 sleep 2
 
-
 %post ndb-storage
 mysql_clusterdir=/var/lib/mysql-cluster
 
 # Create cluster directory if needed
-if test ! -d $mysql_clusterdir; then mkdir -m755 $mysql_clusterdir; fi
+if test ! -d $mysql_clusterdir; then mkdir -m 755 $mysql_clusterdir; fi
 
 
 %post Max
@@ -642,10 +670,12 @@ fi
 %files ndb-storage
 %defattr(-,root,root,0755)
 %attr(755, root, root) %{_sbindir}/ndbd
+%doc %attr(644, root, man) %{_mandir}/man8/ndbd.8*
 
 %files ndb-management
 %defattr(-,root,root,0755)
 %attr(755, root, root) %{_sbindir}/ndb_mgmd
+%doc %attr(644, root, man) %{_mandir}/man8/ndb_mgmd.8*
 
 %files ndb-tools
 %defattr(-,root,root,0755)
@@ -737,6 +767,10 @@ fi
 # itself - note that they must be ordered by date (important when
 # merging BK trees)
 %changelog 
+* Wed Mar 19 2008 Joerg Bruehe <joerg@mysql.com>
+
+- Add the man pages for "ndbd" and "ndb_mgmd".
+
 * Fri Mar 02 2007 Joerg Bruehe <joerg@mysql.com>
 
 - Add several man pages for NDB which are now created.