Implement sharable row-level locks, and use them for foreign key references

to eliminate unnecessary deadlocks.  This commit adds SELECT ... FOR SHARE
paralleling SELECT ... FOR UPDATE.  The implementation uses a new SLRU
data structure (managed much like pg_subtrans) to represent multiple-
transaction-ID sets.  When more than one transaction is holding a shared
lock on a particular row, we create a MultiXactId representing that set
of transactions and store its ID in the row's XMAX.  This scheme allows
an effectively unlimited number of row locks, just as we did before,
while not costing any extra overhead except when a shared lock actually
has to be shared.   Still TODO: use the regular lock manager to control
the grant order when multiple backends are waiting for a row lock.

Alvaro Herrera and Tom Lane.

doc/src/sgml/mvcc.sgml

@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/mvcc.sgml,v 2.49 2005/03/24 00:03:18 neilc Exp $
+$PostgreSQL: pgsql/doc/src/sgml/mvcc.sgml,v 2.50 2005/04/28 21:47:09 tgl Exp $
 -->
 
  <chapter id="mvcc">
@@ -253,11 +253,12 @@ $PostgreSQL: pgsql/doc/src/sgml/mvcc.sgml,v 2.49 2005/03/24 00:03:18 neilc Exp $
    </para>
 
    <para>
-    <command>UPDATE</command>, <command>DELETE</command>, and <command>SELECT
-    FOR UPDATE</command> commands behave the same as <command>SELECT</command>
+    <command>UPDATE</command>, <command>DELETE</command>, <command>SELECT
+    FOR UPDATE</command>, and <command>SELECT FOR SHARE</command> commands
+    behave the same as <command>SELECT</command>
     in terms of searching for target rows: they will only find target rows
     that were committed as of the command start time.  However, such a target
-    row may have already been updated (or deleted or marked for update) by
+    row may have already been updated (or deleted or locked) by
     another concurrent transaction by the time it is found.  In this case, the
     would-be updater will wait for the first updating transaction to commit or
     roll back (if it is still in progress).  If the first updater rolls back,
@@ -268,7 +269,10 @@ $PostgreSQL: pgsql/doc/src/sgml/mvcc.sgml,v 2.49 2005/03/24 00:03:18 neilc Exp $
     the row.  The search condition of the command (the <literal>WHERE</> clause) is
     re-evaluated to see if the updated version of the row still matches the
     search condition.  If so, the second updater proceeds with its operation,
-    starting from the updated version of the row.
+    starting from the updated version of the row.  (In the case of
+    <command>SELECT FOR UPDATE</command> and <command>SELECT FOR
+    SHARE</command>, that means it is the updated version of the row that is
+    locked and returned to the client.)
    </para>
 
    <para>
@@ -346,25 +350,26 @@ COMMIT;
    </para>
 
    <para>
-    <command>UPDATE</command>, <command>DELETE</command>, and <command>SELECT
-    FOR UPDATE</command> commands behave the same as <command>SELECT</command>
+    <command>UPDATE</command>, <command>DELETE</command>, <command>SELECT
+    FOR UPDATE</command>, and <command>SELECT FOR SHARE</command> commands
+    behave the same as <command>SELECT</command>
     in terms of searching for target rows: they will only find target rows
     that were committed as of the transaction start time.  However, such a
     target
-    row may have already been updated (or deleted or marked for update) by
+    row may have already been updated (or deleted or locked) by
     another concurrent transaction by the time it is found.  In this case, the
     serializable transaction will wait for the first updating transaction to commit or
     roll back (if it is still in progress).  If the first updater rolls back,
     then its effects are negated and the serializable transaction can proceed
     with updating the originally found row.  But if the first updater commits
-    (and actually updated or deleted the row, not just selected it for update)
+    (and actually updated or deleted the row, not just locked it)
     then the serializable transaction will be rolled back with the message
 
 <screen>
 ERROR:  could not serialize access due to concurrent update
 </screen>
 
-    because a serializable transaction cannot modify rows changed by
+    because a serializable transaction cannot modify or lock rows changed by
     other transactions after the serializable transaction began.
    </para>
 
@@ -571,10 +576,12 @@ SELECT SUM(value) FROM mytab WHERE class = 2;
 	</para>
 
 	<para>
-	 The <command>SELECT FOR UPDATE</command> command acquires a
+	 The <command>SELECT FOR UPDATE</command> and
+	 <command>SELECT FOR SHARE</command> commands acquire a
 	 lock of this mode on the target table(s) (in addition to
 	 <literal>ACCESS SHARE</literal> locks on any other tables
-	 that are referenced but not selected <option>FOR UPDATE</option>).
+	 that are referenced but not selected
+	 <option>FOR UPDATE/FOR SHARE</option>).
 	</para>
        </listitem>
       </varlistentry>
@@ -714,7 +721,7 @@ SELECT SUM(value) FROM mytab WHERE class = 2;
      <tip>
       <para>
        Only an <literal>ACCESS EXCLUSIVE</literal> lock blocks a
-       <command>SELECT</command> (without <option>FOR UPDATE</option>)
+       <command>SELECT</command> (without <option>FOR UPDATE/SHARE</option>)
        statement.
       </para>
      </tip>
@@ -725,25 +732,37 @@ SELECT SUM(value) FROM mytab WHERE class = 2;
     <title>Row-Level Locks</title>
 
     <para>
-     In addition to table-level locks, there are row-level locks.
-     A row-level lock on a specific row is automatically acquired when the
-     row is updated (or deleted or marked for update).  The lock is held
-     until the transaction commits or rolls back.
-     Row-level locks do not affect data
-     querying; they block <emphasis>writers to the same row</emphasis>
-     only.  To acquire a row-level lock on a row without actually
+     In addition to table-level locks, there are row-level locks, which
+     can be exclusive or shared locks.  An exclusive row-level lock on a
+     specific row is automatically acquired when the row is updated or
+     deleted.  The lock is held until the transaction commits or rolls
+     back.  Row-level locks do not affect data querying; they block
+     <emphasis>writers to the same row</emphasis> only.
+    </para>
+
+    <para>
+     To acquire an exclusive row-level lock on a row without actually
      modifying the row, select the row with <command>SELECT FOR
-     UPDATE</command>.  Note that once a particular row-level lock is
-     acquired, the transaction may update the row multiple times without
+     UPDATE</command>.  Note that once the row-level lock is acquired,
+     the transaction may update the row multiple times without
      fear of conflicts.
     </para>
 
+    <para>
+     To acquire a shared row-level lock on a row, select the row with
+     <command>SELECT FOR SHARE</command>.  A shared lock does not prevent
+     other transactions from acquiring the same shared lock.  However,
+     no transaction is allowed to update, delete, or exclusively lock a
+     row on which any other transaction holds a shared lock.  Any attempt
+     to do so will block until the shared locks have been released.
+    </para>
+
     <para>
      <productname>PostgreSQL</productname> doesn't remember any
      information about modified rows in memory, so it has no limit to
      the number of rows locked at one time.  However, locking a row
      may cause a disk write; thus, for example, <command>SELECT FOR
-     UPDATE</command> will modify selected rows to mark them and so
+     UPDATE</command> will modify selected rows to mark them locked, and so
      will result in disk writes.
     </para>
 
@@ -873,9 +892,10 @@ UPDATE accounts SET balance = balance - 100.00 WHERE acctnum = 22222;
 
    <para>
     To ensure the current validity of a row and protect it against
-    concurrent updates one must use <command>SELECT FOR
-    UPDATE</command> or an appropriate <command>LOCK TABLE</command>
-    statement.  (<command>SELECT FOR UPDATE</command> locks just the
+    concurrent updates one must use <command>SELECT FOR UPDATE</command>,
+    <command>SELECT FOR SHARE</command>, or an appropriate <command>LOCK
+    TABLE</command> statement.  (<command>SELECT FOR UPDATE</command>
+    or <command>SELECT FOR SHARE</command> locks just the
     returned rows against concurrent updates, while <command>LOCK
     TABLE</command> locks the whole table.)  This should be taken into
     account when porting applications to

doc/src/sgml/ref/grant.sgml

@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/ref/grant.sgml,v 1.45 2005/01/22 23:22:18 momjian Exp $
+$PostgreSQL: pgsql/doc/src/sgml/ref/grant.sgml,v 1.46 2005/04/28 21:47:09 tgl Exp $
 PostgreSQL documentation
 -->
 
@@ -131,9 +131,10 @@ GRANT { CREATE | ALL [ PRIVILEGES ] }
      <term>UPDATE</term>
      <listitem>
       <para>
-       Allows <xref linkend="sql-update" endterm="sql-update-title"> of any column of the
-       specified table.  <literal>SELECT ... FOR UPDATE</literal>
-       also requires this privilege (besides the
+       Allows <xref linkend="sql-update" endterm="sql-update-title"> of any
+       column of the specified table.  <literal>SELECT ... FOR UPDATE</literal>
+       and <literal>SELECT ... FOR SHARE</literal>
+       also require this privilege (besides the
        <literal>SELECT</literal> privilege).  For sequences, this
        privilege allows the use of the <function>nextval</function> and
        <function>setval</function> functions.

doc/src/sgml/ref/lock.sgml

@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/ref/lock.sgml,v 1.46 2005/01/22 23:22:19 momjian Exp $
+$PostgreSQL: pgsql/doc/src/sgml/ref/lock.sgml,v 1.47 2005/04/28 21:47:10 tgl Exp $
 PostgreSQL documentation
 -->
 
@@ -177,8 +177,8 @@ where <replaceable class="PARAMETER">lockmode</replaceable> is one of:
    <command>LOCK TABLE</> is concerned, differing only in the rules
    about which modes conflict with which. For information on how to
    acquire an actual row-level lock, see <xref linkend="locking-rows">
-   and the <xref linkend="sql-for-update"
-   endterm="sql-for-update-title"> in the <command>SELECT</command>
+   and the <xref linkend="sql-for-update-share"
+   endterm="sql-for-update-share-title"> in the <command>SELECT</command>
    reference documentation.
   </para>
  </refsect1>

doc/src/sgml/ref/pg_resetxlog.sgml

@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/ref/pg_resetxlog.sgml,v 1.9 2004/12/20 01:42:09 tgl Exp $
+$PostgreSQL: pgsql/doc/src/sgml/ref/pg_resetxlog.sgml,v 1.10 2005/04/28 21:47:10 tgl Exp $
 PostgreSQL documentation
 -->
 
@@ -22,6 +22,7 @@ PostgreSQL documentation
    <arg> -n </arg>
    <arg> -o <replaceable class="parameter">oid</replaceable> </arg>
    <arg> -x <replaceable class="parameter">xid</replaceable> </arg>
+   <arg> -m <replaceable class="parameter">mxid</replaceable> </arg>
    <arg> -l <replaceable class="parameter">timelineid</replaceable>,<replaceable class="parameter">fileid</replaceable>,<replaceable class="parameter">seg</replaceable> </arg>
    <arg choice="plain"><replaceable>datadir</replaceable></arg>
   </cmdsynopsis>
@@ -73,34 +74,65 @@ PostgreSQL documentation
   </para>
 
   <para>
-   The <literal>-o</>, <literal>-x</>, and <literal>-l</> switches allow
-   the next OID, next transaction ID, and WAL starting address values to
+   The <literal>-o</>, <literal>-x</>, <literal>-m</>, and <literal>-l</>
+   switches allow the next OID, next transaction ID, next multi-transaction
+   ID, and WAL starting address values to
    be set manually.  These are only needed when
    <command>pg_resetxlog</command> is unable to determine appropriate values
-   by reading <filename>pg_control</>.  A safe value for the
-   next transaction ID may be determined by looking for the numerically largest
-   file name in the directory <filename>pg_clog</> under the data directory,
-   adding one,
-   and then multiplying by 1048576.  Note that the file names are in
-   hexadecimal.  It is usually easiest to specify the switch value in
-   hexadecimal too. For example, if <filename>0011</> is the largest entry
-   in <filename>pg_clog</>, <literal>-x 0x1200000</> will work (five trailing
-   zeroes provide the proper multiplier).
-   The WAL starting address should be
-   larger than any file name currently existing in
-   the directory <filename>pg_xlog</> under the data directory.
-   These names are also in hexadecimal and have three parts.  The first
-   part is the <quote>timeline ID</> and should usually be kept the same.
-   Do not choose a value larger than 255 (<literal>0xFF</>) for the third
-   part; instead increment the second part and reset the third part to 0.
-   For example, if <filename>00000001000000320000004A</> is the
-   largest entry in <filename>pg_xlog</>, <literal>-l 0x1,0x32,0x4B</> will
-   work; but if the largest entry is
-   <filename>000000010000003A000000FF</>, choose <literal>-l 0x1,0x3B,0x0</>
-   or more.
-   There is no comparably easy way to determine a next OID that's beyond
-   the largest one in the database, but fortunately it is not critical to
-   get the next-OID setting right.
+   by reading <filename>pg_control</>.  Safe values may be determined as
+   follows:
+
+   <itemizedlist>
+    <listitem>
+     <para>
+      A safe value for the next transaction ID (<literal>-x</>)
+      may be determined by looking for the numerically largest
+      file name in the directory <filename>pg_clog</> under the data directory,
+      adding one,
+      and then multiplying by 1048576.  Note that the file names are in
+      hexadecimal.  It is usually easiest to specify the switch value in
+      hexadecimal too. For example, if <filename>0011</> is the largest entry
+      in <filename>pg_clog</>, <literal>-x 0x1200000</> will work (five
+      trailing zeroes provide the proper multiplier).
+     </para>
+    </listitem>
+
+    <listitem>
+     <para>
+      A safe value for the next multi-transaction ID (<literal>-m</>)
+      may be determined by looking for the numerically largest
+      file name in the directory <filename>pg_multixact/offsets</> under the
+      data directory, adding one, and then multiplying by 65536.  As above,
+      the file names are in hexadecimal, so the easiest way to do this is to
+      specify the switch value in hexadecimal and add four zeroes.
+     </para>
+    </listitem>
+
+    <listitem>
+     <para>
+      The WAL starting address (<literal>-l</>) should be
+      larger than any file name currently existing in
+      the directory <filename>pg_xlog</> under the data directory.
+      These names are also in hexadecimal and have three parts.  The first
+      part is the <quote>timeline ID</> and should usually be kept the same.
+      Do not choose a value larger than 255 (<literal>0xFF</>) for the third
+      part; instead increment the second part and reset the third part to 0.
+      For example, if <filename>00000001000000320000004A</> is the
+      largest entry in <filename>pg_xlog</>, <literal>-l 0x1,0x32,0x4B</> will
+      work; but if the largest entry is
+      <filename>000000010000003A000000FF</>, choose <literal>-l 0x1,0x3B,0x0</>
+      or more.
+     </para>
+    </listitem>
+
+    <listitem>
+     <para>
+      There is no comparably easy way to determine a next OID that's beyond
+      the largest one in the database, but fortunately it is not critical to
+      get the next-OID setting right.
+     </para>
+    </listitem>
+   </itemizedlist>
   </para>
 
   <para>

doc/src/sgml/ref/select.sgml

@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/ref/select.sgml,v 1.85 2005/04/22 15:32:58 momjian Exp $
+$PostgreSQL: pgsql/doc/src/sgml/ref/select.sgml,v 1.86 2005/04/28 21:47:10 tgl Exp $
 PostgreSQL documentation
 -->
 
@@ -30,7 +30,7 @@ SELECT [ ALL | DISTINCT [ ON ( <replaceable class="parameter">expression</replac
     [ ORDER BY <replaceable class="parameter">expression</replaceable> [ ASC | DESC | USING <replaceable class="parameter">operator</replaceable> ] [, ...] ]
     [ LIMIT { <replaceable class="parameter">count</replaceable> | ALL } ]
     [ OFFSET <replaceable class="parameter">start</replaceable> ]
-    [ FOR UPDATE [ OF <replaceable class="parameter">table_name</replaceable> [, ...] ] ]
+    [ FOR { UPDATE | SHARE } [ OF <replaceable class="parameter">table_name</replaceable> [, ...] ] ]
 
 where <replaceable class="parameter">from_item</replaceable> can be one of:
 
@@ -142,10 +142,11 @@ where <replaceable class="parameter">from_item</replaceable> can be one of:
 
     <listitem>
      <para>
-      The <literal>FOR UPDATE</literal> clause causes the
-      <command>SELECT</command> statement to lock the selected rows
-      against concurrent updates.  (See <xref linkend="sql-for-update"
-      endterm="sql-for-update-title"> below.)
+      If the <literal>FOR UPDATE</literal> or <literal>FOR SHARE</literal>
+      clause is specified, the
+      <command>SELECT</command> statement locks the selected rows
+      against concurrent updates.  (See <xref linkend="sql-for-update-share"
+      endterm="sql-for-update-share-title"> below.)
      </para>
     </listitem>
    </orderedlist>
@@ -153,7 +154,8 @@ where <replaceable class="parameter">from_item</replaceable> can be one of:
    
   <para>
    You must have <literal>SELECT</literal> privilege on a table to
-   read its values.  The use of <literal>FOR UPDATE</literal> requires
+   read its values.  The use of <literal>FOR UPDATE</literal> or
+   <literal>FOR SHARE</literal> requires
    <literal>UPDATE</literal> privilege as well.
   </para>
  </refsect1>
@@ -503,7 +505,8 @@ HAVING <replaceable class="parameter">condition</replaceable>
 </synopsis>
     <replaceable class="parameter">select_statement</replaceable> is
     any <command>SELECT</command> statement without an <literal>ORDER
-    BY</>, <literal>LIMIT</>, or <literal>FOR UPDATE</literal> clause.
+    BY</>, <literal>LIMIT</>, <literal>FOR UPDATE</literal>, or
+    <literal>FOR SHARE</literal> clause. 
     (<literal>ORDER BY</> and <literal>LIMIT</> can be attached to a
     subexpression if it is enclosed in parentheses.  Without
     parentheses, these clauses will be taken to apply to the result of
@@ -537,8 +540,9 @@ HAVING <replaceable class="parameter">condition</replaceable>
    </para>
     
    <para>
-    Currently, <literal>FOR UPDATE</> may not be specified either for
-    a <literal>UNION</> result or for any input of a <literal>UNION</>.
+    Currently, <literal>FOR UPDATE</> and <literal>FOR SHARE</> may not be
+    specified either for a <literal>UNION</> result or for any input of a
+    <literal>UNION</>.
    </para>
   </refsect2>
 
@@ -552,7 +556,8 @@ HAVING <replaceable class="parameter">condition</replaceable>
 </synopsis>
     <replaceable class="parameter">select_statement</replaceable> is
     any <command>SELECT</command> statement without an <literal>ORDER
-    BY</>, <literal>LIMIT</>, or <literal>FOR UPDATE</literal> clause.
+    BY</>, <literal>LIMIT</>, <literal>FOR UPDATE</literal>, or
+    <literal>FOR SHARE</literal> clause.
    </para>
 
    <para>
@@ -581,8 +586,9 @@ HAVING <replaceable class="parameter">condition</replaceable>
    </para>
     
    <para>
-    Currently, <literal>FOR UPDATE</> may not be specified either for
-    an <literal>INTERSECT</> result or for any input of an <literal>INTERSECT</>.
+    Currently, <literal>FOR UPDATE</> and <literal>FOR SHARE</> may not be
+    specified either for an <literal>INTERSECT</> result or for any input of
+    an <literal>INTERSECT</>.
    </para>
   </refsect2>
 
@@ -596,7 +602,8 @@ HAVING <replaceable class="parameter">condition</replaceable>
 </synopsis>
     <replaceable class="parameter">select_statement</replaceable> is
     any <command>SELECT</command> statement without an <literal>ORDER
-    BY</>, <literal>LIMIT</>, or <literal>FOR UPDATE</literal> clause.
+    BY</>, <literal>LIMIT</>, <literal>FOR UPDATE</literal>, or
+    <literal>FOR SHARE</literal> clause.
    </para>
 
    <para>
@@ -621,8 +628,9 @@ HAVING <replaceable class="parameter">condition</replaceable>
    </para>
     
    <para>
-    Currently, <literal>FOR UPDATE</> may not be specified either for
-    an <literal>EXCEPT</> result or for any input of an <literal>EXCEPT</>.
+    Currently, <literal>FOR UPDATE</> and <literal>FOR SHARE</> may not be
+    specified either for an <literal>EXCEPT</> result or for any input of
+    an <literal>EXCEPT</>.
    </para>
   </refsect2>
 
@@ -789,8 +797,8 @@ OFFSET <replaceable class="parameter">start</replaceable>
    </para>
   </refsect2>
 
-  <refsect2 id="SQL-FOR-UPDATE">
-   <title id="sql-for-update-title"><literal>FOR UPDATE</literal> Clause</title>
+  <refsect2 id="SQL-FOR-UPDATE-SHARE">
+   <title id="sql-for-update-share-title"><literal>FOR UPDATE</literal>/<literal>FOR SHARE</literal> Clause</title>
 
    <para>
     The <literal>FOR UPDATE</literal> clause has this form:
@@ -799,6 +807,13 @@ FOR UPDATE [ OF <replaceable class="parameter">table_name</replaceable> [, ...]
 </synopsis>
    </para>
 
+   <para>
+    The closely related <literal>FOR SHARE</literal> clause has this form:
+<synopsis>
+FOR SHARE [ OF <replaceable class="parameter">table_name</replaceable> [, ...] ]
+</synopsis>
+   </para>
+
    <para>
     <literal>FOR UPDATE</literal> causes the rows retrieved by the
     <command>SELECT</command> statement to be locked as though for
@@ -817,26 +832,44 @@ FOR UPDATE [ OF <replaceable class="parameter">table_name</replaceable> [, ...]
    </para>
 
    <para>
-    If specific tables are named in <literal>FOR UPDATE</literal>,
+    <literal>FOR SHARE</literal> behaves similarly, except that it
+    acquires a shared rather than exclusive lock on each retrieved
+    row.  A shared lock blocks other transactions from performing
+    <command>UPDATE</command>, <command>DELETE</command>, or <command>SELECT
+    FOR UPDATE</command> on these rows, but it does not prevent them
+    from performing <command>SELECT FOR SHARE</command>.
+   </para>
+
+   <para>
+    It is currently not allowed for a single <command>SELECT</command>
+    statement to include both <literal>FOR UPDATE</literal> and
+    <literal>FOR SHARE</literal>.
+   </para>
+
+   <para>
+    If specific tables are named in <literal>FOR UPDATE</literal>
+    or <literal>FOR SHARE</literal>,
     then only rows coming from those tables are locked; any other
     tables used in the <command>SELECT</command> are simply read as
     usual.
    </para>
 
    <para>
-    <literal>FOR UPDATE</literal> cannot be used in contexts where
-    returned rows can't be clearly identified with individual table
-    rows; for example it can't be used with aggregation.
+    <literal>FOR UPDATE</literal> and <literal>FOR SHARE</literal> cannot be
+    used in contexts where returned rows can't be clearly identified with
+    individual table rows; for example they can't be used with aggregation.
    </para>
 
    <para>
     It is possible for a <command>SELECT</> command using both 
-    <literal>LIMIT</literal> and  <literal>FOR UPDATE</literal> 
+    <literal>LIMIT</literal> and  <literal>FOR UPDATE/SHARE</literal> 
     clauses to return fewer rows than specified by <literal>LIMIT</literal>.
-    This is because <literal>LIMIT</> selects a number of rows,
-    but might then block requesting a <literal>FOR UPDATE</literal> lock.
-    Once the <literal>SELECT</> unblocks, the query qualification might not
-    be met and the row not be returned by <literal>SELECT</>.
+    This is because <literal>LIMIT</> is applied first.  The command
+    selects the specified number of rows,
+    but might then block trying to obtain lock on one or more of them.
+    Once the <literal>SELECT</> unblocks, the row might have been deleted
+    or updated so that it does not meet the query <literal>WHERE</> condition
+    anymore, in which case it will not be returned.
    </para>
   </refsect2>
  </refsect1>

doc/src/sgml/ref/select_into.sgml

@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/ref/select_into.sgml,v 1.34 2005/03/13 09:36:31 neilc Exp $
+$PostgreSQL: pgsql/doc/src/sgml/ref/select_into.sgml,v 1.35 2005/04/28 21:47:10 tgl Exp $
 PostgreSQL documentation
 -->
 
@@ -31,7 +31,7 @@ SELECT [ ALL | DISTINCT [ ON ( <replaceable class="PARAMETER">expression</replac
     [ ORDER BY <replaceable class="PARAMETER">expression</replaceable> [ ASC | DESC | USING <replaceable class="PARAMETER">operator</replaceable> ] [, ...] ]
     [ LIMIT { <replaceable class="PARAMETER">count</replaceable> | ALL } ]
     [ OFFSET <replaceable class="PARAMETER">start</replaceable> ]
-    [ FOR UPDATE [ OF <replaceable class="PARAMETER">tablename</replaceable> [, ...] ] ]
+    [ FOR { UPDATE | SHARE } [ OF <replaceable class="PARAMETER">tablename</replaceable> [, ...] ] ]
 </synopsis>
  </refsynopsisdiv>
 

doc/src/sgml/sql.sgml

@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/sql.sgml,v 1.35 2005/02/21 02:21:03 neilc Exp $
+$PostgreSQL: pgsql/doc/src/sgml/sql.sgml,v 1.36 2005/04/28 21:47:09 tgl Exp $
 -->
 
  <chapter id="sql-intro">
@@ -866,7 +866,7 @@ SELECT [ ALL | DISTINCT [ ON ( <replaceable class="PARAMETER">expression</replac
     [ ORDER BY <replaceable class="PARAMETER">expression</replaceable> [ ASC | DESC | USING <replaceable class="PARAMETER">operator</replaceable> ] [, ...] ]
     [ LIMIT { <replaceable class="PARAMETER">count</replaceable> | ALL } ]
     [ OFFSET <replaceable class="PARAMETER">start</replaceable> ]
-    [ FOR UPDATE [ OF <replaceable class="PARAMETER">class_name</replaceable> [, ...] ] ]
+    [ FOR { UPDATE | SHARE } [ OF <replaceable class="PARAMETER">class_name</replaceable> [, ...] ] ]
      </synopsis>
     </para>
 

doc/src/sgml/storage.sgml

@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/storage.sgml,v 1.5 2005/04/07 03:31:42 neilc Exp $
+$PostgreSQL: pgsql/doc/src/sgml/storage.sgml,v 1.6 2005/04/28 21:47:09 tgl Exp $
 -->
 
 <chapter id="storage">
@@ -74,6 +74,12 @@ Item
  <entry>Subdirectory containing transaction commit status data</entry>
 </row>
 
+<row>
+ <entry><filename>pg_multixact</></entry>
+ <entry>Subdirectory containing multi-transaction status data
+  (used for shared row locks)</entry> 
+</row>
+
 <row>
  <entry><filename>pg_subtrans</></entry>
  <entry>Subdirectory containing subtransaction status data</entry>

src/backend/access/heap/heapam.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/heap/heapam.c,v 1.187 2005/04/14 20:03:22 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/heap/heapam.c,v 1.188 2005/04/28 21:47:10 tgl Exp $
  *
  *
  * INTERFACE ROUTINES
@@ -40,12 +40,14 @@
 
 #include "access/heapam.h"
 #include "access/hio.h"
+#include "access/multixact.h"
 #include "access/tuptoaster.h"
 #include "access/valid.h"
 #include "access/xlogutils.h"
 #include "catalog/catalog.h"
 #include "catalog/namespace.h"
 #include "miscadmin.h"
+#include "storage/sinval.h"
 #include "utils/inval.h"
 #include "utils/relcache.h"
 #include "pgstat.h"
@@ -1238,30 +1240,81 @@ l1:
 	}
 	else if (result == HeapTupleBeingUpdated && wait)
 	{
-		TransactionId xwait = HeapTupleHeaderGetXmax(tp.t_data);
-
-		/* sleep until concurrent transaction ends */
-		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
-		XactLockTableWait(xwait);
-
-		LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
-		if (!TransactionIdDidCommit(xwait))
-			goto l1;
+		TransactionId xwait;
+		uint16	infomask;
 
 		/*
-		 * xwait is committed but if xwait had just marked the tuple for
-		 * update then some other xaction could update this tuple before
-		 * we got to this point.
+		 * Sleep until concurrent transaction ends.  Note that we don't care
+		 * if the locker has an exclusive or shared lock, because we need
+		 * exclusive.
 		 */
-		if (!TransactionIdEquals(HeapTupleHeaderGetXmax(tp.t_data), xwait))
-			goto l1;
-		if (!(tp.t_data->t_infomask & HEAP_XMAX_COMMITTED))
+
+		/* must copy state data before unlocking buffer */
+		xwait = HeapTupleHeaderGetXmax(tp.t_data);
+		infomask = tp.t_data->t_infomask;
+
+		if (infomask & HEAP_XMAX_IS_MULTI)
 		{
-			tp.t_data->t_infomask |= HEAP_XMAX_COMMITTED;
-			SetBufferCommitInfoNeedsSave(buffer);
+			/* wait for multixact */
+			LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
+			MultiXactIdWait((MultiXactId) xwait);
+			LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
+
+			/*
+			 * If xwait had just locked the tuple then some other xact could
+			 * update this tuple before we get to this point.  Check for xmax
+			 * change, and start over if so.
+			 */
+			if (!(tp.t_data->t_infomask & HEAP_XMAX_IS_MULTI) ||
+				!TransactionIdEquals(HeapTupleHeaderGetXmax(tp.t_data),
+									 xwait))
+				goto l1;
+
+			/*
+			 * You might think the multixact is necessarily done here, but
+			 * not so: it could have surviving members, namely our own xact
+			 * or other subxacts of this backend.  It is legal for us to
+			 * delete the tuple in either case, however (the latter case is
+			 * essentially a situation of upgrading our former shared lock
+			 * to exclusive).  We don't bother changing the on-disk hint bits
+			 * since we are about to overwrite the xmax altogether.
+			 */
 		}
-		/* if tuple was marked for update but not updated... */
-		if (tp.t_data->t_infomask & HEAP_MARKED_FOR_UPDATE)
+		else
+		{
+			/* wait for regular transaction to end */
+			LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
+			XactLockTableWait(xwait);
+			LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
+
+			/*
+			 * xwait is done, but if xwait had just locked the tuple then some
+			 * other xact could update this tuple before we get to this point.
+			 * Check for xmax change, and start over if so.
+			 */
+			if ((tp.t_data->t_infomask & HEAP_XMAX_IS_MULTI) ||
+				!TransactionIdEquals(HeapTupleHeaderGetXmax(tp.t_data),
+									 xwait))
+				goto l1;
+
+			/* Otherwise we can mark it committed or aborted */
+			if (!(tp.t_data->t_infomask & (HEAP_XMAX_COMMITTED |
+										   HEAP_XMAX_INVALID)))
+			{
+				if (TransactionIdDidCommit(xwait))
+					tp.t_data->t_infomask |= HEAP_XMAX_COMMITTED;
+				else
+					tp.t_data->t_infomask |= HEAP_XMAX_INVALID;
+				SetBufferCommitInfoNeedsSave(buffer);
+			}
+		}
+
+		/*
+		 * We may overwrite if previous xmax aborted, or if it committed
+		 * but only locked the tuple without updating it.
+		 */
+		if (tp.t_data->t_infomask & (HEAP_XMAX_INVALID |
+									 HEAP_IS_LOCKED))
 			result = HeapTupleMayBeUpdated;
 		else
 			result = HeapTupleUpdated;
@@ -1290,7 +1343,8 @@ l1:
 	/* store transaction information of xact deleting the tuple */
 	tp.t_data->t_infomask &= ~(HEAP_XMAX_COMMITTED |
 							   HEAP_XMAX_INVALID |
-							   HEAP_MARKED_FOR_UPDATE |
+							   HEAP_XMAX_IS_MULTI |
+							   HEAP_IS_LOCKED |
 							   HEAP_MOVED);
 	HeapTupleHeaderSetXmax(tp.t_data, xid);
 	HeapTupleHeaderSetCmax(tp.t_data, cid);
@@ -1465,30 +1519,81 @@ l2:
 	}
 	else if (result == HeapTupleBeingUpdated && wait)
 	{
-		TransactionId xwait = HeapTupleHeaderGetXmax(oldtup.t_data);
-
-		/* sleep until concurrent transaction ends */
-		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
-		XactLockTableWait(xwait);
-
-		LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
-		if (!TransactionIdDidCommit(xwait))
-			goto l2;
+		TransactionId xwait;
+		uint16	infomask;
 
 		/*
-		 * xwait is committed but if xwait had just marked the tuple for
-		 * update then some other xaction could update this tuple before
-		 * we got to this point.
+		 * Sleep until concurrent transaction ends.  Note that we don't care
+		 * if the locker has an exclusive or shared lock, because we need
+		 * exclusive.
 		 */
-		if (!TransactionIdEquals(HeapTupleHeaderGetXmax(oldtup.t_data), xwait))
-			goto l2;
-		if (!(oldtup.t_data->t_infomask & HEAP_XMAX_COMMITTED))
+
+		/* must copy state data before unlocking buffer */
+		xwait = HeapTupleHeaderGetXmax(oldtup.t_data);
+		infomask = oldtup.t_data->t_infomask;
+
+		if (infomask & HEAP_XMAX_IS_MULTI)
 		{
-			oldtup.t_data->t_infomask |= HEAP_XMAX_COMMITTED;
-			SetBufferCommitInfoNeedsSave(buffer);
+			/* wait for multixact */
+			LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
+			MultiXactIdWait((MultiXactId) xwait);
+			LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
+
+			/*
+			 * If xwait had just locked the tuple then some other xact could
+			 * update this tuple before we get to this point.  Check for xmax
+			 * change, and start over if so.
+			 */
+			if (!(oldtup.t_data->t_infomask & HEAP_XMAX_IS_MULTI) ||
+				!TransactionIdEquals(HeapTupleHeaderGetXmax(oldtup.t_data),
+									 xwait))
+				goto l2;
+
+			/*
+			 * You might think the multixact is necessarily done here, but
+			 * not so: it could have surviving members, namely our own xact
+			 * or other subxacts of this backend.  It is legal for us to
+			 * update the tuple in either case, however (the latter case is
+			 * essentially a situation of upgrading our former shared lock
+			 * to exclusive).  We don't bother changing the on-disk hint bits
+			 * since we are about to overwrite the xmax altogether.
+			 */
 		}
-		/* if tuple was marked for update but not updated... */
-		if (oldtup.t_data->t_infomask & HEAP_MARKED_FOR_UPDATE)
+		else
+		{
+			/* wait for regular transaction to end */
+			LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
+			XactLockTableWait(xwait);
+			LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
+
+			/*
+			 * xwait is done, but if xwait had just locked the tuple then some
+			 * other xact could update this tuple before we get to this point.
+			 * Check for xmax change, and start over if so.
+			 */
+			if ((oldtup.t_data->t_infomask & HEAP_XMAX_IS_MULTI) ||
+				!TransactionIdEquals(HeapTupleHeaderGetXmax(oldtup.t_data),
+									 xwait))
+				goto l2;
+
+			/* Otherwise we can mark it committed or aborted */
+			if (!(oldtup.t_data->t_infomask & (HEAP_XMAX_COMMITTED |
+											   HEAP_XMAX_INVALID)))
+			{
+				if (TransactionIdDidCommit(xwait))
+					oldtup.t_data->t_infomask |= HEAP_XMAX_COMMITTED;
+				else
+					oldtup.t_data->t_infomask |= HEAP_XMAX_INVALID;
+				SetBufferCommitInfoNeedsSave(buffer);
+			}
+		}
+
+		/*
+		 * We may overwrite if previous xmax aborted, or if it committed
+		 * but only locked the tuple without updating it.
+		 */
+		if (oldtup.t_data->t_infomask & (HEAP_XMAX_INVALID |
+										 HEAP_IS_LOCKED))
 			result = HeapTupleMayBeUpdated;
 		else
 			result = HeapTupleUpdated;
@@ -1556,7 +1661,8 @@ l2:
 	{
 		oldtup.t_data->t_infomask &= ~(HEAP_XMAX_COMMITTED |
 									   HEAP_XMAX_INVALID |
-									   HEAP_MARKED_FOR_UPDATE |
+									   HEAP_XMAX_IS_MULTI |
+									   HEAP_IS_LOCKED |
 									   HEAP_MOVED);
 		HeapTupleHeaderSetXmax(oldtup.t_data, xid);
 		HeapTupleHeaderSetCmax(oldtup.t_data, cid);
@@ -1642,7 +1748,8 @@ l2:
 	{
 		oldtup.t_data->t_infomask &= ~(HEAP_XMAX_COMMITTED |
 									   HEAP_XMAX_INVALID |
-									   HEAP_MARKED_FOR_UPDATE |
+									   HEAP_XMAX_IS_MULTI |
+									   HEAP_IS_LOCKED |
 									   HEAP_MOVED);
 		HeapTupleHeaderSetXmax(oldtup.t_data, xid);
 		HeapTupleHeaderSetCmax(oldtup.t_data, cid);
@@ -1739,17 +1846,18 @@ simple_heap_update(Relation relation, ItemPointer otid, HeapTuple tup)
 }
 
 /*
- *	heap_mark4update		- mark a tuple for update
+ *	heap_lock_tuple		- lock a tuple in shared or exclusive mode
  */
 HTSU_Result
-heap_mark4update(Relation relation, HeapTuple tuple, Buffer *buffer,
-				 CommandId cid)
+heap_lock_tuple(Relation relation, HeapTuple tuple, Buffer *buffer,
+				 CommandId cid, LockTupleMode mode)
 {
-	TransactionId xid = GetCurrentTransactionId();
+	TransactionId	xid;
 	ItemPointer tid = &(tuple->t_self);
 	ItemId		lp;
 	PageHeader	dp;
 	HTSU_Result	result;
+	uint16		new_infomask;
 
 	*buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(tid));
 	LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
@@ -1767,38 +1875,93 @@ l3:
 	{
 		LockBuffer(*buffer, BUFFER_LOCK_UNLOCK);
 		ReleaseBuffer(*buffer);
-		elog(ERROR, "attempted to mark4update invisible tuple");
+		elog(ERROR, "attempted to lock invisible tuple");
 	}
 	else if (result == HeapTupleBeingUpdated)
 	{
-		TransactionId xwait = HeapTupleHeaderGetXmax(tuple->t_data);
+		if (mode == LockTupleShared &&
+			(tuple->t_data->t_infomask & HEAP_XMAX_SHARED_LOCK))
+			result = HeapTupleMayBeUpdated;
+		else
+		{
+			TransactionId xwait;
+			uint16	infomask;
 
-		/* sleep until concurrent transaction ends */
-		LockBuffer(*buffer, BUFFER_LOCK_UNLOCK);
-		XactLockTableWait(xwait);
+			/*
+			 * Sleep until concurrent transaction ends.
+			 */
 
-		LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
-		if (!TransactionIdDidCommit(xwait))
-			goto l3;
+			/* must copy state data before unlocking buffer */
+			xwait = HeapTupleHeaderGetXmax(tuple->t_data);
+			infomask = tuple->t_data->t_infomask;
 
-		/*
-		 * xwait is committed but if xwait had just marked the tuple for
-		 * update then some other xaction could update this tuple before
-		 * we got to this point.
-		 */
-		if (!TransactionIdEquals(HeapTupleHeaderGetXmax(tuple->t_data), xwait))
-			goto l3;
-		if (!(tuple->t_data->t_infomask & HEAP_XMAX_COMMITTED))
-		{
-			tuple->t_data->t_infomask |= HEAP_XMAX_COMMITTED;
-			SetBufferCommitInfoNeedsSave(*buffer);
+			if (infomask & HEAP_XMAX_IS_MULTI)
+			{
+				/* wait for multixact */
+				LockBuffer(*buffer, BUFFER_LOCK_UNLOCK);
+				MultiXactIdWait((MultiXactId) xwait);
+				LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
+
+				/*
+				 * If xwait had just locked the tuple then some other xact
+				 * could update this tuple before we get to this point.
+				 * Check for xmax change, and start over if so.
+				 */
+				if (!(tuple->t_data->t_infomask & HEAP_XMAX_IS_MULTI) ||
+					!TransactionIdEquals(HeapTupleHeaderGetXmax(tuple->t_data),
+										 xwait))
+					goto l3;
+
+				/*
+				 * You might think the multixact is necessarily done here, but
+				 * not so: it could have surviving members, namely our own xact
+				 * or other subxacts of this backend.  It is legal for us to
+				 * lock the tuple in either case, however.  We don't bother
+				 * changing the on-disk hint bits since we are about to
+				 * overwrite the xmax altogether.
+				 */
+			}
+			else
+			{
+				/* wait for regular transaction to end */
+				LockBuffer(*buffer, BUFFER_LOCK_UNLOCK);
+				XactLockTableWait(xwait);
+				LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE);
+
+				/*
+				 * xwait is done, but if xwait had just locked the tuple then
+				 * some other xact could update this tuple before we get to
+				 * this point.  Check for xmax change, and start over if so.
+				 */
+				if ((tuple->t_data->t_infomask & HEAP_XMAX_IS_MULTI) ||
+					!TransactionIdEquals(HeapTupleHeaderGetXmax(tuple->t_data),
+										 xwait))
+					goto l3;
+
+				/* Otherwise we can mark it committed or aborted */
+				if (!(tuple->t_data->t_infomask & (HEAP_XMAX_COMMITTED |
+												   HEAP_XMAX_INVALID)))
+				{
+					if (TransactionIdDidCommit(xwait))
+						tuple->t_data->t_infomask |= HEAP_XMAX_COMMITTED;
+					else
+						tuple->t_data->t_infomask |= HEAP_XMAX_INVALID;
+					SetBufferCommitInfoNeedsSave(*buffer);
+				}
+			}
+
+			/*
+			 * We may lock if previous xmax aborted, or if it committed
+			 * but only locked the tuple without updating it.
+			 */
+			if (tuple->t_data->t_infomask & (HEAP_XMAX_INVALID |
+											 HEAP_IS_LOCKED))
+				result = HeapTupleMayBeUpdated;
+			else
+				result = HeapTupleUpdated;
 		}
-		/* if tuple was marked for update but not updated... */
-		if (tuple->t_data->t_infomask & HEAP_MARKED_FOR_UPDATE)
-			result = HeapTupleMayBeUpdated;
-		else
-			result = HeapTupleUpdated;
 	}
+
 	if (result != HeapTupleMayBeUpdated)
 	{
 		Assert(result == HeapTupleSelfUpdated || result == HeapTupleUpdated);
@@ -1808,21 +1971,173 @@ l3:
 	}
 
 	/*
-	 * XLOG stuff: no logging is required as long as we have no
-	 * savepoints. For savepoints private log could be used...
+	 * Compute the new xmax and infomask to store into the tuple.  Note we
+	 * do not modify the tuple just yet, because that would leave it in the
+	 * wrong state if multixact.c elogs.
 	 */
-	PageSetTLI(BufferGetPage(*buffer), ThisTimeLineID);
+	xid = GetCurrentTransactionId();
+
+	new_infomask = tuple->t_data->t_infomask;
+
+	new_infomask &= ~(HEAP_XMAX_COMMITTED |
+					  HEAP_XMAX_INVALID |
+					  HEAP_XMAX_IS_MULTI |
+					  HEAP_IS_LOCKED |
+					  HEAP_MOVED);
+
+	if (mode == LockTupleShared)
+	{
+		TransactionId	xmax = HeapTupleHeaderGetXmax(tuple->t_data);
+		uint16		old_infomask = tuple->t_data->t_infomask;
+
+		/*
+		 * If this is the first acquisition of a shared lock in the current
+		 * transaction, set my per-backend OldestMemberMXactId setting.
+		 * We can be certain that the transaction will never become a
+		 * member of any older MultiXactIds than that.  (We have to do this
+		 * even if we end up just using our own TransactionId below, since
+		 * some other backend could incorporate our XID into a MultiXact
+		 * immediately afterwards.)
+		 */
+		MultiXactIdSetOldestMember();
+
+		new_infomask |= HEAP_XMAX_SHARED_LOCK;
+
+		/*
+		 * Check to see if we need a MultiXactId because there are multiple
+		 * lockers.
+		 *
+		 * HeapTupleSatisfiesUpdate will have set the HEAP_XMAX_INVALID
+		 * bit if the xmax was a MultiXactId but it was not running anymore.
+		 * There is a race condition, which is that the MultiXactId may have
+		 * finished since then, but that uncommon case is handled within
+		 * MultiXactIdExpand.
+		 *
+		 * There is a similar race condition possible when the old xmax was
+		 * a regular TransactionId.  We test TransactionIdIsInProgress again
+		 * just to narrow the window, but it's still possible to end up
+		 * creating an unnecessary MultiXactId.  Fortunately this is harmless.
+		 */
+		if (!(old_infomask & (HEAP_XMAX_INVALID | HEAP_XMAX_COMMITTED)))
+		{
+			if (old_infomask & HEAP_XMAX_IS_MULTI)
+			{
+				/*
+				 * If the XMAX is already a MultiXactId, then we need to
+				 * expand it to include our own TransactionId.
+				 */
+				xid = MultiXactIdExpand(xmax, true, xid);
+				new_infomask |= HEAP_XMAX_IS_MULTI;
+			}
+			else if (TransactionIdIsInProgress(xmax))
+			{
+				if (TransactionIdEquals(xmax, xid))
+				{
+					/*
+					 * If the old locker is ourselves, we'll just mark the
+					 * tuple again with our own TransactionId.  However we
+					 * have to consider the possibility that we had
+					 * exclusive rather than shared lock before --- if so,
+					 * be careful to preserve the exclusivity of the lock.
+					 */
+					if (!(old_infomask & HEAP_XMAX_SHARED_LOCK))
+					{
+						new_infomask &= ~HEAP_XMAX_SHARED_LOCK;
+						new_infomask |= HEAP_XMAX_EXCL_LOCK;
+						mode = LockTupleExclusive;
+					}
+				}
+				else
+				{
+					/*
+					 * If the Xmax is a valid TransactionId, then we need to
+					 * create a new MultiXactId that includes both the old
+					 * locker and our own TransactionId.
+					 */
+					xid = MultiXactIdExpand(xmax, false, xid);
+					new_infomask |= HEAP_XMAX_IS_MULTI;
+				}
+			}
+			else
+			{
+				/*
+				 * Can get here iff HeapTupleSatisfiesUpdate saw the old
+				 * xmax as running, but it finished before
+				 * TransactionIdIsInProgress() got to run.  Treat it like
+				 * there's no locker in the tuple.
+				 */
+			}
+		}
+		else
+		{
+			/*
+			 * There was no previous locker, so just insert our own
+			 * TransactionId.
+			 */
+		}
+	}
+	else
+	{
+		/* We want an exclusive lock on the tuple */
+		new_infomask |= HEAP_XMAX_EXCL_LOCK;
+	}
+
+	START_CRIT_SECTION();
 
-	/* store transaction information of xact marking the tuple */
-	tuple->t_data->t_infomask &= ~(HEAP_XMAX_COMMITTED |
-								   HEAP_XMAX_INVALID |
-								   HEAP_MOVED);
-	tuple->t_data->t_infomask |= HEAP_MARKED_FOR_UPDATE;
+	/*
+	 * Store transaction information of xact locking the tuple.
+	 *
+	 * Note: our CID is meaningless if storing a MultiXactId, but no harm
+	 * in storing it anyway.
+	 */
+	tuple->t_data->t_infomask = new_infomask;
 	HeapTupleHeaderSetXmax(tuple->t_data, xid);
 	HeapTupleHeaderSetCmax(tuple->t_data, cid);
 	/* Make sure there is no forward chain link in t_ctid */
 	tuple->t_data->t_ctid = *tid;
 
+	/*
+	 * XLOG stuff.  You might think that we don't need an XLOG record because
+	 * there is no state change worth restoring after a crash.  You would be
+	 * wrong however: we have just written either a TransactionId or a
+	 * MultiXactId that may never have been seen on disk before, and we need
+	 * to make sure that there are XLOG entries covering those ID numbers.
+	 * Else the same IDs might be re-used after a crash, which would be
+	 * disastrous if this page made it to disk before the crash.  Essentially
+	 * we have to enforce the WAL log-before-data rule even in this case.
+	 */
+	if (!relation->rd_istemp)
+	{
+		xl_heap_lock xlrec;
+		XLogRecPtr	recptr;
+		XLogRecData rdata[2];
+
+		xlrec.target.node = relation->rd_node;
+		xlrec.target.tid = tuple->t_self;
+		xlrec.shared_lock = (mode == LockTupleShared);
+		rdata[0].buffer = InvalidBuffer;
+		rdata[0].data = (char *) &xlrec;
+		rdata[0].len = SizeOfHeapLock;
+		rdata[0].next = &(rdata[1]);
+
+		rdata[1].buffer = *buffer;
+		rdata[1].data = NULL;
+		rdata[1].len = 0;
+		rdata[1].next = NULL;
+
+		recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_LOCK, rdata);
+
+		PageSetLSN(dp, recptr);
+		PageSetTLI(dp, ThisTimeLineID);
+	}
+	else
+	{
+		/* No XLOG record, but still need to flag that XID exists on disk */
+		MyXactMadeTempRelUpdate = true;
+	}
+
+	END_CRIT_SECTION();
+
 	LockBuffer(*buffer, BUFFER_LOCK_UNLOCK);
 
 	WriteNoReleaseBuffer(*buffer);
@@ -1832,17 +2147,6 @@ l3:
 
 /* ----------------
  *		heap_markpos	- mark scan position
- *
- *		Note:
- *				Should only one mark be maintained per scan at one time.
- *		Check if this can be done generally--say calls to get the
- *		next/previous tuple and NEVER pass struct scandesc to the
- *		user AM's.  Now, the mark is sent to the executor for safekeeping.
- *		Probably can store this info into a GENERAL scan structure.
- *
- *		May be best to change this call to store the marked position
- *		(up to 2?) in the scan structure itself.
- *		Fix to use the proper caching structure.
  * ----------------
  */
 void
@@ -1858,19 +2162,6 @@ heap_markpos(HeapScanDesc scan)
 
 /* ----------------
  *		heap_restrpos	- restore position to marked location
- *
- *		Note:  there are bad side effects here.  If we were past the end
- *		of a relation when heapmarkpos is called, then if the relation is
- *		extended via insert, then the next call to heaprestrpos will set
- *		cause the added tuples to be visible when the scan continues.
- *		Problems also arise if the TID's are rearranged!!!
- *
- * XXX	might be better to do direct access instead of
- *		using the generality of heapgettup().
- *
- * XXX It is very possible that when a scan is restored, that a tuple
- * XXX which previously qualified may fail for time range purposes, unless
- * XXX some form of locking exists (ie., portals currently can act funny.
  * ----------------
  */
 void
@@ -1996,8 +2287,7 @@ log_heap_update(Relation reln, Buffer oldbuf, ItemPointerData from,
 	{
 		TransactionId xid[2];	/* xmax, xmin */
 
-		if (newtup->t_data->t_infomask & (HEAP_XMAX_INVALID |
-										  HEAP_MARKED_FOR_UPDATE))
+		if (newtup->t_data->t_infomask & (HEAP_XMAX_INVALID | HEAP_IS_LOCKED))
 			xid[0] = InvalidTransactionId;
 		else
 			xid[0] = HeapTupleHeaderGetXmax(newtup->t_data);
@@ -2185,7 +2475,8 @@ heap_xlog_delete(bool redo, XLogRecPtr lsn, XLogRecord *record)
 	{
 		htup->t_infomask &= ~(HEAP_XMAX_COMMITTED |
 							  HEAP_XMAX_INVALID |
-							  HEAP_MARKED_FOR_UPDATE |
+							  HEAP_XMAX_IS_MULTI |
+							  HEAP_IS_LOCKED |
 							  HEAP_MOVED);
 		HeapTupleHeaderSetXmax(htup, record->xl_xid);
 		HeapTupleHeaderSetCmax(htup, FirstCommandId);
@@ -2365,7 +2656,8 @@ heap_xlog_update(bool redo, XLogRecPtr lsn, XLogRecord *record, bool move)
 		{
 			htup->t_infomask &= ~(HEAP_XMAX_COMMITTED |
 								  HEAP_XMAX_INVALID |
-								  HEAP_MARKED_FOR_UPDATE |
+								  HEAP_XMAX_IS_MULTI |
+								  HEAP_IS_LOCKED |
 								  HEAP_MOVED);
 			HeapTupleHeaderSetXmax(htup, record->xl_xid);
 			HeapTupleHeaderSetCmax(htup, FirstCommandId);
@@ -2487,6 +2779,82 @@ newsame:;
 
 }
 
+static void
+heap_xlog_lock(bool redo, XLogRecPtr lsn, XLogRecord *record)
+{
+	xl_heap_lock *xlrec = (xl_heap_lock *) XLogRecGetData(record);
+	Relation	reln;
+	Buffer		buffer;
+	Page		page;
+	OffsetNumber offnum;
+	ItemId		lp = NULL;
+	HeapTupleHeader htup;
+
+	if (redo && (record->xl_info & XLR_BKP_BLOCK_1))
+		return;
+
+	reln = XLogOpenRelation(redo, RM_HEAP_ID, xlrec->target.node);
+
+	if (!RelationIsValid(reln))
+		return;
+
+	buffer = XLogReadBuffer(false, reln,
+						ItemPointerGetBlockNumber(&(xlrec->target.tid)));
+	if (!BufferIsValid(buffer))
+		elog(PANIC, "heap_lock_%sdo: no block", (redo) ? "re" : "un");
+
+	page = (Page) BufferGetPage(buffer);
+	if (PageIsNew((PageHeader) page))
+		elog(PANIC, "heap_lock_%sdo: uninitialized page", (redo) ? "re" : "un");
+
+	if (redo)
+	{
+		if (XLByteLE(lsn, PageGetLSN(page)))	/* changes are applied */
+		{
+			LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
+			ReleaseBuffer(buffer);
+			return;
+		}
+	}
+	else if (XLByteLT(PageGetLSN(page), lsn))	/* changes are not applied
+												 * ?! */
+		elog(PANIC, "heap_lock_undo: bad page LSN");
+
+	offnum = ItemPointerGetOffsetNumber(&(xlrec->target.tid));
+	if (PageGetMaxOffsetNumber(page) >= offnum)
+		lp = PageGetItemId(page, offnum);
+
+	if (PageGetMaxOffsetNumber(page) < offnum || !ItemIdIsUsed(lp))
+		elog(PANIC, "heap_lock_%sdo: invalid lp", (redo) ? "re" : "un");
+
+	htup = (HeapTupleHeader) PageGetItem(page, lp);
+
+	if (redo)
+	{
+		/*
+		 * Presently, we don't bother to restore the locked state, but
+		 * just set the XMAX_INVALID bit.
+		 */
+		htup->t_infomask &= ~(HEAP_XMAX_COMMITTED |
+							  HEAP_XMAX_INVALID |
+							  HEAP_XMAX_IS_MULTI |
+							  HEAP_IS_LOCKED |
+							  HEAP_MOVED);
+		htup->t_infomask |= HEAP_XMAX_INVALID;
+		HeapTupleHeaderSetXmax(htup, record->xl_xid);
+		HeapTupleHeaderSetCmax(htup, FirstCommandId);
+		/* Make sure there is no forward chain link in t_ctid */
+		htup->t_ctid = xlrec->target.tid;
+		PageSetLSN(page, lsn);
+		PageSetTLI(page, ThisTimeLineID);
+		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
+		WriteBuffer(buffer);
+		return;
+	}
+
+	elog(PANIC, "heap_lock_undo: unimplemented");
+}
+
 void
 heap_redo(XLogRecPtr lsn, XLogRecord *record)
 {
@@ -2505,6 +2873,8 @@ heap_redo(XLogRecPtr lsn, XLogRecord *record)
 		heap_xlog_clean(true, lsn, record);
 	else if (info == XLOG_HEAP_NEWPAGE)
 		heap_xlog_newpage(true, lsn, record);
+	else if (info == XLOG_HEAP_LOCK)
+		heap_xlog_lock(true, lsn, record);
 	else
 		elog(PANIC, "heap_redo: unknown op code %u", info);
 }
@@ -2527,6 +2897,8 @@ heap_undo(XLogRecPtr lsn, XLogRecord *record)
 		heap_xlog_clean(false, lsn, record);
 	else if (info == XLOG_HEAP_NEWPAGE)
 		heap_xlog_newpage(false, lsn, record);
+	else if (info == XLOG_HEAP_LOCK)
+		heap_xlog_lock(false, lsn, record);
 	else
 		elog(PANIC, "heap_undo: unknown op code %u", info);
 }
@@ -2589,6 +2961,16 @@ heap_desc(char *buf, uint8 xl_info, char *rec)
 				xlrec->node.spcNode, xlrec->node.dbNode,
 				xlrec->node.relNode, xlrec->blkno);
 	}
+	else if (info == XLOG_HEAP_LOCK)
+	{
+		xl_heap_lock *xlrec = (xl_heap_lock *) rec;
+
+		if (xlrec->shared_lock)
+			strcat(buf, "shared_lock: ");
+		else
+			strcat(buf, "exclusive_lock: ");
+		out_target(buf, &(xlrec->target));
+	}
 	else
 		strcat(buf, "UNKNOWN");
 }

src/backend/access/transam/Makefile

@@ -4,7 +4,7 @@
 #    Makefile for access/transam
 #
 # IDENTIFICATION
-#    $PostgreSQL: pgsql/src/backend/access/transam/Makefile,v 1.19 2004/07/01 00:49:42 tgl Exp $
+#    $PostgreSQL: pgsql/src/backend/access/transam/Makefile,v 1.20 2005/04/28 21:47:10 tgl Exp $
 #
 #-------------------------------------------------------------------------
 
@@ -12,7 +12,7 @@ subdir = src/backend/access/transam
 top_builddir = ../../../..
 include $(top_builddir)/src/Makefile.global
 
-OBJS = clog.o transam.o varsup.o xact.o xlog.o xlogutils.o rmgr.o slru.o subtrans.o
+OBJS = clog.o transam.o varsup.o xact.o xlog.o xlogutils.o rmgr.o slru.o subtrans.o multixact.o
 
 all: SUBSYS.o
 

src/backend/access/transam/xact.c

@@ -10,7 +10,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/transam/xact.c,v 1.199 2005/04/11 19:51:14 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/transam/xact.c,v 1.200 2005/04/28 21:47:10 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -20,6 +20,7 @@
 #include <time.h>
 #include <unistd.h>
 
+#include "access/multixact.h"
 #include "access/subtrans.h"
 #include "access/xact.h"
 #include "catalog/heap.h"
@@ -1565,6 +1566,8 @@ CommitTransaction(void)
 	 */
 	smgrDoPendingDeletes(true);
 
+	AtEOXact_MultiXact();
+
 	ResourceOwnerRelease(TopTransactionResourceOwner,
 						 RESOURCE_RELEASE_LOCKS,
 						 true, true);
@@ -1710,6 +1713,7 @@ AbortTransaction(void)
 	AtEOXact_Buffers(false);
 	AtEOXact_Inval(false);
 	smgrDoPendingDeletes(false);
+	AtEOXact_MultiXact();
 	ResourceOwnerRelease(TopTransactionResourceOwner,
 						 RESOURCE_RELEASE_LOCKS,
 						 false, true);
@@ -3622,9 +3626,9 @@ static void
 ShowTransactionState(const char *str)
 {
 	/* skip work if message will definitely not be printed */
-	if (log_min_messages <= DEBUG2 || client_min_messages <= DEBUG2)
+	if (log_min_messages <= DEBUG3 || client_min_messages <= DEBUG3)
 	{
-		elog(DEBUG2, "%s", str);
+		elog(DEBUG3, "%s", str);
 		ShowTransactionStateRec(CurrentTransactionState);
 	}
 }
@@ -3640,7 +3644,7 @@ ShowTransactionStateRec(TransactionState s)
 		ShowTransactionStateRec(s->parent);
 
 	/* use ereport to suppress computation if msg will not be printed */
-	ereport(DEBUG2,
+	ereport(DEBUG3,
 			(errmsg_internal("name: %s; blockState: %13s; state: %7s, xid/subid/cid: %u/%u/%u, nestlvl: %d, children: %s",
 						   PointerIsValid(s->name) ? s->name : "unnamed",
 							 BlockStateAsString(s->blockState),

src/backend/access/transam/xlog.c

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/backend/access/transam/xlog.c,v 1.188 2005/04/23 18:49:54 tgl Exp $
+ * $PostgreSQL: pgsql/src/backend/access/transam/xlog.c,v 1.189 2005/04/28 21:47:10 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -23,6 +23,7 @@
 #include <sys/time.h>
 
 #include "access/clog.h"
+#include "access/multixact.h"
 #include "access/subtrans.h"
 #include "access/xact.h"
 #include "access/xlog.h"
@@ -3534,11 +3535,13 @@ BootStrapXLOG(void)
 	checkPoint.ThisTimeLineID = ThisTimeLineID;
 	checkPoint.nextXid = FirstNormalTransactionId;
 	checkPoint.nextOid = FirstBootstrapObjectId;
+	checkPoint.nextMulti = FirstMultiXactId;
 	checkPoint.time = time(NULL);
 
 	ShmemVariableCache->nextXid = checkPoint.nextXid;
 	ShmemVariableCache->nextOid = checkPoint.nextOid;
 	ShmemVariableCache->oidCount = 0;
+	MultiXactSetNextMXact(checkPoint.nextMulti);
 
 	/* Set up the XLOG page header */
 	page->xlp_magic = XLOG_PAGE_MAGIC;
@@ -3613,6 +3616,7 @@ BootStrapXLOG(void)
 	/* Bootstrap the commit log, too */
 	BootStrapCLOG();
 	BootStrapSUBTRANS();
+	BootStrapMultiXact();
 }
 
 static char *
@@ -4187,8 +4191,8 @@ StartupXLOG(void)
 					checkPoint.undo.xlogid, checkPoint.undo.xrecoff,
 					wasShutdown ? "TRUE" : "FALSE")));
 	ereport(LOG,
-			(errmsg("next transaction ID: %u; next OID: %u",
-					checkPoint.nextXid, checkPoint.nextOid)));
+			(errmsg("next transaction ID: %u; next OID: %u; next MultiXactId: %u",
+					checkPoint.nextXid, checkPoint.nextOid, checkPoint.nextMulti)));
 	if (!TransactionIdIsNormal(checkPoint.nextXid))
 		ereport(PANIC,
 				(errmsg("invalid next transaction ID")));
@@ -4196,6 +4200,7 @@ StartupXLOG(void)
 	ShmemVariableCache->nextXid = checkPoint.nextXid;
 	ShmemVariableCache->nextOid = checkPoint.nextOid;
 	ShmemVariableCache->oidCount = 0;
+	MultiXactSetNextMXact(checkPoint.nextMulti);
 
 	/*
 	 * We must replay WAL entries using the same TimeLineID they were
@@ -4546,9 +4551,10 @@ StartupXLOG(void)
 	ControlFile->time = time(NULL);
 	UpdateControlFile();
 
-	/* Start up the commit log, too */
+	/* Start up the commit log and related stuff, too */
 	StartupCLOG();
 	StartupSUBTRANS();
+	StartupMultiXact();
 
 	ereport(LOG,
 			(errmsg("database system is ready")));
@@ -4737,6 +4743,7 @@ ShutdownXLOG(int code, Datum arg)
 	CreateCheckPoint(true, true);
 	ShutdownCLOG();
 	ShutdownSUBTRANS();
+	ShutdownMultiXact();
 	CritSectionCount--;
 
 	ereport(LOG,
@@ -4919,6 +4926,8 @@ CreateCheckPoint(bool shutdown, bool force)
 		checkPoint.nextOid += ShmemVariableCache->oidCount;
 	LWLockRelease(OidGenLock);
 
+	checkPoint.nextMulti = MultiXactGetCheckptMulti(shutdown);
+
 	/*
 	 * Having constructed the checkpoint record, ensure all shmem disk
 	 * buffers and commit-log buffers are flushed to disk.
@@ -4938,6 +4947,7 @@ CreateCheckPoint(bool shutdown, bool force)
 
 	CheckPointCLOG();
 	CheckPointSUBTRANS();
+	CheckPointMultiXact();
 	FlushBufferPool();
 
 	START_CRIT_SECTION();
@@ -5054,6 +5064,33 @@ XLogPutNextOid(Oid nextOid)
 	rdata.len = sizeof(Oid);
 	rdata.next = NULL;
 	(void) XLogInsert(RM_XLOG_ID, XLOG_NEXTOID, &rdata);
+	/*
+	 * We need not flush the NEXTOID record immediately, because any of the
+	 * just-allocated OIDs could only reach disk as part of a tuple insert
+	 * or update that would have its own XLOG record that must follow the
+	 * NEXTOID record.  Therefore, the standard buffer LSN interlock applied
+	 * to those records will ensure no such OID reaches disk before the
+	 * NEXTOID record does.
+	 */
+}
+
+/*
+ * Write a NEXT_MULTIXACT log record
+ */
+void
+XLogPutNextMultiXactId(MultiXactId nextMulti)
+{
+	XLogRecData rdata;
+
+	rdata.buffer = InvalidBuffer;
+	rdata.data = (char *) (&nextMulti);
+	rdata.len = sizeof(MultiXactId);
+	rdata.next = NULL;
+	(void) XLogInsert(RM_XLOG_ID, XLOG_NEXTMULTI, &rdata);
+	/*
+	 * We do not flush here either; this assumes that heap_lock_tuple() will
+	 * always generate a WAL record.  See notes therein.
+	 */
 }
 
 /*
@@ -5075,6 +5112,14 @@ xlog_redo(XLogRecPtr lsn, XLogRecord *record)
 			ShmemVariableCache->oidCount = 0;
 		}
 	}
+	else if (info == XLOG_NEXTMULTI)
+	{
+		MultiXactId	nextMulti;
+
+		memcpy(&nextMulti, XLogRecGetData(record), sizeof(MultiXactId));
+
+		MultiXactAdvanceNextMXact(nextMulti);
+	}
 	else if (info == XLOG_CHECKPOINT_SHUTDOWN)
 	{
 		CheckPoint	checkPoint;
@@ -5084,6 +5129,7 @@ xlog_redo(XLogRecPtr lsn, XLogRecord *record)
 		ShmemVariableCache->nextXid = checkPoint.nextXid;
 		ShmemVariableCache->nextOid = checkPoint.nextOid;
 		ShmemVariableCache->oidCount = 0;
+		MultiXactSetNextMXact(checkPoint.nextMulti);
 
 		/*
 		 * TLI may change in a shutdown checkpoint, but it shouldn't
@@ -5115,6 +5161,7 @@ xlog_redo(XLogRecPtr lsn, XLogRecord *record)
 			ShmemVariableCache->nextOid = checkPoint.nextOid;
 			ShmemVariableCache->oidCount = 0;
 		}
+		MultiXactAdvanceNextMXact(checkPoint.nextMulti);
 		/* TLI should not change in an on-line checkpoint */
 		if (checkPoint.ThisTimeLineID != ThisTimeLineID)
 			ereport(PANIC,
@@ -5139,11 +5186,12 @@ xlog_desc(char *buf, uint8 xl_info, char *rec)
 		CheckPoint *checkpoint = (CheckPoint *) rec;
 
 		sprintf(buf + strlen(buf), "checkpoint: redo %X/%X; undo %X/%X; "
-				"tli %u; xid %u; oid %u; %s",
+				"tli %u; xid %u; oid %u; multi %u; %s",
 				checkpoint->redo.xlogid, checkpoint->redo.xrecoff,
 				checkpoint->undo.xlogid, checkpoint->undo.xrecoff,
 				checkpoint->ThisTimeLineID, checkpoint->nextXid,
 				checkpoint->nextOid,
+				checkpoint->nextMulti,
 			 (info == XLOG_CHECKPOINT_SHUTDOWN) ? "shutdown" : "online");
 	}
 	else if (info == XLOG_NEXTOID)
@@ -5153,6 +5201,13 @@ xlog_desc(char *buf, uint8 xl_info, char *rec)
 		memcpy(&nextOid, rec, sizeof(Oid));
 		sprintf(buf + strlen(buf), "nextOid: %u", nextOid);
 	}
+	else if (info == XLOG_NEXTMULTI)
+	{
+		MultiXactId	multi;
+
+		memcpy(&multi, rec, sizeof(MultiXactId));
+		sprintf(buf + strlen(buf), "nextMultiXact: %u", multi);
+	}
 	else
 		strcat(buf, "UNKNOWN");
 }

src/backend/catalog/index.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/catalog/index.c,v 1.252 2005/04/14 20:03:23 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/catalog/index.c,v 1.253 2005/04/28 21:47:11 tgl Exp $
  *
  *
  * INTERFACE ROUTINES
@@ -471,7 +471,7 @@ index_create(Oid heapRelationId,
 	int			i;
 
 	/*
-	 * Only SELECT ... FOR UPDATE are allowed while doing this
+	 * Only SELECT ... FOR UPDATE/SHARE are allowed while doing this
 	 */
 	heapRelation = heap_open(heapRelationId, ShareLock);
 
@@ -1460,6 +1460,7 @@ IndexBuildHeapScan(Relation heapRelation,
 					 * a system catalog, because we often release lock on
 					 * system catalogs before committing.
 					 */
+					Assert(!(heapTuple->t_data->t_infomask & HEAP_XMAX_IS_MULTI));
 					if (!TransactionIdIsCurrentTransactionId(
 							   HeapTupleHeaderGetXmax(heapTuple->t_data))
 						&& !IsSystemRelation(heapRelation))

src/backend/commands/portalcmds.c

@@ -14,7 +14,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/portalcmds.c,v 1.40 2005/04/11 15:59:34 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/portalcmds.c,v 1.41 2005/04/28 21:47:11 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -90,7 +90,7 @@ PerformCursorOpen(DeclareCursorStmt *stmt, ParamListInfo params)
 	if (query->rowMarks != NIL)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-				 errmsg("DECLARE CURSOR ... FOR UPDATE is not supported"),
+				 errmsg("DECLARE CURSOR ... FOR UPDATE/SHARE is not supported"),
 				 errdetail("Cursors must be READ ONLY.")));
 
 	plan = planner(query, true, stmt->options, NULL);

src/backend/commands/trigger.c

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/trigger.c,v 1.186 2005/04/14 20:03:24 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/trigger.c,v 1.187 2005/04/28 21:47:11 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -1592,12 +1592,12 @@ GetTupleForTrigger(EState *estate, ResultRelInfo *relinfo,
 		HTSU_Result	test;
 
 		/*
-		 * mark tuple for update
+		 * lock tuple for update
 		 */
 		*newSlot = NULL;
 		tuple.t_self = *tid;
 ltrmark:;
-		test = heap_mark4update(relation, &tuple, &buffer, cid);
+		test = heap_lock_tuple(relation, &tuple, &buffer, cid, LockTupleExclusive);
 		switch (test)
 		{
 			case HeapTupleSelfUpdated:
@@ -1636,8 +1636,7 @@ ltrmark:;
 
 			default:
 				ReleaseBuffer(buffer);
-				elog(ERROR, "unrecognized heap_mark4update status: %u",
-					 test);
+				elog(ERROR, "invalid heap_lock_tuple status: %d", test);
 				return NULL;	/* keep compiler quiet */
 		}
 	}

src/backend/commands/vacuum.c

@@ -13,7 +13,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/vacuum.c,v 1.306 2005/04/14 20:03:24 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/vacuum.c,v 1.307 2005/04/28 21:47:12 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -1800,7 +1800,7 @@ repair_frag(VRelStats *vacrelstats, Relation onerel,
 			 !TransactionIdPrecedes(HeapTupleHeaderGetXmin(tuple.t_data),
 									OldestXmin)) ||
 				(!(tuple.t_data->t_infomask & (HEAP_XMAX_INVALID |
-											   HEAP_MARKED_FOR_UPDATE)) &&
+											   HEAP_IS_LOCKED)) &&
 				 !(ItemPointerEquals(&(tuple.t_self),
 									 &(tuple.t_data->t_ctid)))))
 			{
@@ -1839,7 +1839,7 @@ repair_frag(VRelStats *vacrelstats, Relation onerel,
 				 * we have to move to the end of chain.
 				 */
 				while (!(tp.t_data->t_infomask & (HEAP_XMAX_INVALID |
-											  HEAP_MARKED_FOR_UPDATE)) &&
+												  HEAP_IS_LOCKED)) &&
 					   !(ItemPointerEquals(&(tp.t_self),
 										   &(tp.t_data->t_ctid))))
 				{
@@ -1984,7 +1984,8 @@ repair_frag(VRelStats *vacrelstats, Relation onerel,
 					 * and we are too close to 6.5 release. - vadim
 					 * 06/11/99
 					 */
-					if (!(TransactionIdEquals(HeapTupleHeaderGetXmax(Ptp.t_data),
+					if (Ptp.t_data->t_infomask & HEAP_XMAX_IS_MULTI ||
+						!(TransactionIdEquals(HeapTupleHeaderGetXmax(Ptp.t_data),
 									 HeapTupleHeaderGetXmin(tp.t_data))))
 					{
 						ReleaseBuffer(Pbuf);

src/backend/executor/README

@@ -1,4 +1,4 @@
-$PostgreSQL: pgsql/src/backend/executor/README,v 1.4 2003/11/29 19:51:48 pgsql Exp $
+$PostgreSQL: pgsql/src/backend/executor/README,v 1.5 2005/04/28 21:47:12 tgl Exp $
 
 The Postgres Executor
 ---------------------
@@ -154,8 +154,8 @@ committed by the concurrent transaction (after waiting for it to commit,
 if need be) and re-evaluate the query qualifications to see if it would
 still meet the quals.  If so, we regenerate the updated tuple (if we are
 doing an UPDATE) from the modified tuple, and finally update/delete the
-modified tuple.  SELECT FOR UPDATE behaves similarly, except that its action
-is just to mark the modified tuple for update by the current transaction.
+modified tuple.  SELECT FOR UPDATE/SHARE behaves similarly, except that its
+action is just to lock the modified tuple.
 
 To implement this checking, we actually re-run the entire query from scratch
 for each modified tuple, but with the scan node that sourced the original
@@ -184,14 +184,14 @@ that while we are executing a recheck query for one modified tuple, we will
 hit another modified tuple in another relation.  In this case we "stack up"
 recheck queries: a sub-recheck query is spawned in which both the first and
 second modified tuples will be returned as the only components of their
-relations.  (In event of success, all these modified tuples will be marked
-for update.)  Again, this isn't necessarily quite the right thing ... but in
-simple cases it works.  Potentially, recheck queries could get nested to the
-depth of the number of FOR UPDATE relations in the query.
+relations.  (In event of success, all these modified tuples will be locked.)
+Again, this isn't necessarily quite the right thing ... but in simple cases
+it works.  Potentially, recheck queries could get nested to the depth of the
+number of FOR UPDATE/SHARE relations in the query.
 
 It should be noted also that UPDATE/DELETE expect at most one tuple to
 result from the modified query, whereas in the FOR UPDATE case it's possible
 for multiple tuples to result (since we could be dealing with a join in
 which multiple tuples join to the modified tuple).  We want FOR UPDATE to
-mark all relevant tuples, so we pass all tuples output by all the stacked
-recheck queries back to the executor toplevel for marking.
+lock all relevant tuples, so we pass all tuples output by all the stacked
+recheck queries back to the executor toplevel for locking.

src/backend/executor/execMain.c

@@ -26,7 +26,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/executor/execMain.c,v 1.246 2005/04/14 01:38:17 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/executor/execMain.c,v 1.247 2005/04/28 21:47:12 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -560,9 +560,10 @@ InitPlan(QueryDesc *queryDesc, bool explainOnly)
 	}
 
 	/*
-	 * Have to lock relations selected for update
+	 * Have to lock relations selected FOR UPDATE/FOR SHARE
 	 */
 	estate->es_rowMark = NIL;
+	estate->es_forUpdate = parseTree->forUpdate;
 	if (parseTree->rowMarks != NIL)
 	{
 		ListCell   *l;
@@ -986,7 +987,7 @@ ExecEndPlan(PlanState *planstate, EState *estate)
 		heap_close(estate->es_into_relation_descriptor, NoLock);
 
 	/*
-	 * close any relations selected FOR UPDATE, again keeping locks
+	 * close any relations selected FOR UPDATE/FOR SHARE, again keeping locks
 	 */
 	foreach(l, estate->es_rowMark)
 	{
@@ -1126,6 +1127,9 @@ lnext:	;
 										 * ctid!! */
 				tupleid = &tuple_ctid;
 			}
+			/*
+			 * Process any FOR UPDATE or FOR SHARE locking requested.
+			 */
 			else if (estate->es_rowMark != NIL)
 			{
 				ListCell   *l;
@@ -1137,6 +1141,7 @@ lnext:	;
 					Buffer		buffer;
 					HeapTupleData tuple;
 					TupleTableSlot *newSlot;
+					LockTupleMode	lockmode;
 					HTSU_Result		test;
 
 					if (!ExecGetJunkAttribute(junkfilter,
@@ -1151,9 +1156,15 @@ lnext:	;
 					if (isNull)
 						elog(ERROR, "\"%s\" is NULL", erm->resname);
 
+					if (estate->es_forUpdate)
+						lockmode = LockTupleExclusive;
+					else
+						lockmode = LockTupleShared;
+
 					tuple.t_self = *((ItemPointer) DatumGetPointer(datum));
-					test = heap_mark4update(erm->relation, &tuple, &buffer,
-											estate->es_snapshot->curcid);
+					test = heap_lock_tuple(erm->relation, &tuple, &buffer,
+										  estate->es_snapshot->curcid,
+										  lockmode);
 					ReleaseBuffer(buffer);
 					switch (test)
 					{
@@ -1189,7 +1200,7 @@ lnext:	;
 							goto lnext;
 
 						default:
-							elog(ERROR, "unrecognized heap_mark4update status: %u",
+							elog(ERROR, "unrecognized heap_lock_tuple status: %u",
 								 test);
 							return (NULL);
 					}
@@ -1574,8 +1585,8 @@ ExecUpdate(TupleTableSlot *slot,
 	 * If we generate a new candidate tuple after EvalPlanQual testing, we
 	 * must loop back here and recheck constraints.  (We don't need to
 	 * redo triggers, however.	If there are any BEFORE triggers then
-	 * trigger.c will have done mark4update to lock the correct tuple, so
-	 * there's no need to do them again.)
+	 * trigger.c will have done heap_lock_tuple to lock the correct tuple,
+	 * so there's no need to do them again.)
 	 */
 lreplace:;
 	if (resultRelationDesc->rd_att->constr)
@@ -2088,6 +2099,7 @@ EvalPlanQualStart(evalPlanQual *epq, EState *estate, evalPlanQual *priorepq)
 		epqstate->es_param_exec_vals = (ParamExecData *)
 			palloc0(estate->es_topPlan->nParamExec * sizeof(ParamExecData));
 	epqstate->es_rowMark = estate->es_rowMark;
+	epqstate->es_forUpdate = estate->es_forUpdate;
 	epqstate->es_instrument = estate->es_instrument;
 	epqstate->es_select_into = estate->es_select_into;
 	epqstate->es_into_oids = estate->es_into_oids;

src/backend/executor/execUtils.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/executor/execUtils.c,v 1.122 2005/04/23 21:32:34 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/executor/execUtils.c,v 1.123 2005/04/28 21:47:12 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -198,6 +198,7 @@ CreateExecutorState(void)
 	estate->es_processed = 0;
 	estate->es_lastoid = InvalidOid;
 	estate->es_rowMark = NIL;
+	estate->es_forUpdate = false;
 
 	estate->es_instrument = false;
 	estate->es_select_into = false;

src/backend/nodes/copyfuncs.c

@@ -15,7 +15,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/nodes/copyfuncs.c,v 1.303 2005/04/25 01:30:13 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/nodes/copyfuncs.c,v 1.304 2005/04/28 21:47:12 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -1605,6 +1605,7 @@ _copyQuery(Query *from)
 	COPY_NODE_FIELD(rtable);
 	COPY_NODE_FIELD(jointree);
 	COPY_NODE_FIELD(rowMarks);
+	COPY_SCALAR_FIELD(forUpdate);
 	COPY_NODE_FIELD(targetList);
 	COPY_NODE_FIELD(groupClause);
 	COPY_NODE_FIELD(havingQual);
@@ -1685,7 +1686,8 @@ _copySelectStmt(SelectStmt *from)
 	COPY_NODE_FIELD(sortClause);
 	COPY_NODE_FIELD(limitOffset);
 	COPY_NODE_FIELD(limitCount);
-	COPY_NODE_FIELD(forUpdate);
+	COPY_NODE_FIELD(lockedRels);
+	COPY_SCALAR_FIELD(forUpdate);
 	COPY_SCALAR_FIELD(op);
 	COPY_SCALAR_FIELD(all);
 	COPY_NODE_FIELD(larg);

src/backend/nodes/equalfuncs.c

@@ -18,7 +18,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/nodes/equalfuncs.c,v 1.240 2005/04/07 01:51:38 neilc Exp $
+ *	  $PostgreSQL: pgsql/src/backend/nodes/equalfuncs.c,v 1.241 2005/04/28 21:47:12 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -642,6 +642,7 @@ _equalQuery(Query *a, Query *b)
 	COMPARE_NODE_FIELD(rtable);
 	COMPARE_NODE_FIELD(jointree);
 	COMPARE_NODE_FIELD(rowMarks);
+	COMPARE_SCALAR_FIELD(forUpdate);
 	COMPARE_NODE_FIELD(targetList);
 	COMPARE_NODE_FIELD(groupClause);
 	COMPARE_NODE_FIELD(havingQual);
@@ -706,7 +707,8 @@ _equalSelectStmt(SelectStmt *a, SelectStmt *b)
 	COMPARE_NODE_FIELD(sortClause);
 	COMPARE_NODE_FIELD(limitOffset);
 	COMPARE_NODE_FIELD(limitCount);
-	COMPARE_NODE_FIELD(forUpdate);
+	COMPARE_NODE_FIELD(lockedRels);
+	COMPARE_SCALAR_FIELD(forUpdate);
 	COMPARE_SCALAR_FIELD(op);
 	COMPARE_SCALAR_FIELD(all);
 	COMPARE_NODE_FIELD(larg);

src/backend/nodes/outfuncs.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/nodes/outfuncs.c,v 1.250 2005/04/25 01:30:13 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/nodes/outfuncs.c,v 1.251 2005/04/28 21:47:13 tgl Exp $
  *
  * NOTES
  *	  Every node type that can appear in stored rules' parsetrees *must*
@@ -1268,7 +1268,8 @@ _outSelectStmt(StringInfo str, SelectStmt *node)
 	WRITE_NODE_FIELD(sortClause);
 	WRITE_NODE_FIELD(limitOffset);
 	WRITE_NODE_FIELD(limitCount);
-	WRITE_NODE_FIELD(forUpdate);
+	WRITE_NODE_FIELD(lockedRels);
+	WRITE_BOOL_FIELD(forUpdate);
 	WRITE_ENUM_FIELD(op, SetOperation);
 	WRITE_BOOL_FIELD(all);
 	WRITE_NODE_FIELD(larg);
@@ -1385,6 +1386,7 @@ _outQuery(StringInfo str, Query *node)
 	WRITE_NODE_FIELD(rtable);
 	WRITE_NODE_FIELD(jointree);
 	WRITE_NODE_FIELD(rowMarks);
+	WRITE_BOOL_FIELD(forUpdate);
 	WRITE_NODE_FIELD(targetList);
 	WRITE_NODE_FIELD(groupClause);
 	WRITE_NODE_FIELD(havingQual);

src/backend/nodes/readfuncs.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/nodes/readfuncs.c,v 1.176 2005/04/06 16:34:05 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/nodes/readfuncs.c,v 1.177 2005/04/28 21:47:13 tgl Exp $
  *
  * NOTES
  *	  Path and Plan nodes do not have any readfuncs support, because we
@@ -145,6 +145,7 @@ _readQuery(void)
 	READ_NODE_FIELD(rtable);
 	READ_NODE_FIELD(jointree);
 	READ_NODE_FIELD(rowMarks);
+	READ_BOOL_FIELD(forUpdate);
 	READ_NODE_FIELD(targetList);
 	READ_NODE_FIELD(groupClause);
 	READ_NODE_FIELD(havingQual);

src/backend/optimizer/path/allpaths.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/optimizer/path/allpaths.c,v 1.128 2005/04/25 01:30:13 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/optimizer/path/allpaths.c,v 1.129 2005/04/28 21:47:13 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -214,13 +214,13 @@ set_inherited_rel_pathlist(Query *root, RelOptInfo *rel,
 	ListCell   *il;
 
 	/*
-	 * XXX for now, can't handle inherited expansion of FOR UPDATE; can we
-	 * do better?
+	 * XXX for now, can't handle inherited expansion of FOR UPDATE/SHARE;
+	 * can we do better?
 	 */
 	if (list_member_int(root->rowMarks, parentRTindex))
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-				 errmsg("SELECT FOR UPDATE is not supported for inheritance queries")));
+				 errmsg("SELECT FOR UPDATE/SHARE is not supported for inheritance queries")));
 
 	/*
 	 * Initialize to compute size estimates for whole inheritance tree

src/backend/optimizer/plan/initsplan.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/optimizer/plan/initsplan.c,v 1.104 2004/12/31 22:00:09 pgsql Exp $
+ *	  $PostgreSQL: pgsql/src/backend/optimizer/plan/initsplan.c,v 1.105 2005/04/28 21:47:13 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -323,11 +323,11 @@ mark_baserels_for_outer_join(Query *root, Relids rels, Relids outerrels)
 		Assert(bms_is_subset(rel->outerjoinset, outerrels));
 
 		/*
-		 * Presently the executor cannot support FOR UPDATE marking of
+		 * Presently the executor cannot support FOR UPDATE/SHARE marking of
 		 * rels appearing on the nullable side of an outer join. (It's
 		 * somewhat unclear what that would mean, anyway: what should we
 		 * mark when a result row is generated from no element of the
-		 * nullable relation?)	So, complain if target rel is FOR UPDATE.
+		 * nullable relation?)	So, complain if target rel is FOR UPDATE/SHARE.
 		 * It's sufficient to make this check once per rel, so do it only
 		 * if rel wasn't already known nullable.
 		 */
@@ -336,7 +336,7 @@ mark_baserels_for_outer_join(Query *root, Relids rels, Relids outerrels)
 			if (list_member_int(root->rowMarks, relno))
 				ereport(ERROR,
 						(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-						 errmsg("SELECT FOR UPDATE cannot be applied to the nullable side of an outer join")));
+						 errmsg("SELECT FOR UPDATE/SHARE cannot be applied to the nullable side of an outer join")));
 		}
 
 		rel->outerjoinset = outerrels;

src/backend/optimizer/plan/planner.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/optimizer/plan/planner.c,v 1.184 2005/04/11 23:06:55 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/optimizer/plan/planner.c,v 1.185 2005/04/28 21:47:13 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -635,13 +635,13 @@ grouping_planner(Query *parse, double tuple_fraction)
 		tlist = postprocess_setop_tlist(result_plan->targetlist, tlist);
 
 		/*
-		 * Can't handle FOR UPDATE here (parser should have checked
+		 * Can't handle FOR UPDATE/SHARE here (parser should have checked
 		 * already, but let's make sure).
 		 */
 		if (parse->rowMarks)
 			ereport(ERROR,
 					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-					 errmsg("SELECT FOR UPDATE is not allowed with UNION/INTERSECT/EXCEPT")));
+					 errmsg("SELECT FOR UPDATE/SHARE is not allowed with UNION/INTERSECT/EXCEPT")));
 
 		/*
 		 * Calculate pathkeys that represent result ordering requirements

src/backend/optimizer/prep/prepjointree.c

@@ -16,7 +16,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/optimizer/prep/prepjointree.c,v 1.26 2005/04/06 16:34:06 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/optimizer/prep/prepjointree.c,v 1.27 2005/04/28 21:47:14 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -276,11 +276,22 @@ pull_up_subqueries(Query *parse, Node *jtnode, bool below_outer_join)
 			parse->rtable = list_concat(parse->rtable, subquery->rtable);
 
 			/*
-			 * Pull up any FOR UPDATE markers, too.  (OffsetVarNodes
+			 * Pull up any FOR UPDATE/SHARE markers, too.  (OffsetVarNodes
 			 * already adjusted the marker values, so just list_concat the
 			 * list.)
+			 *
+			 * Executor can't handle multiple FOR UPDATE/SHARE flags, so
+			 * complain if they are valid but different
 			 */
+			if (parse->rowMarks && subquery->rowMarks &&
+				parse->forUpdate != subquery->forUpdate)
+				ereport(ERROR,
+						(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+						 errmsg("cannot use both FOR UPDATE and FOR SHARE in one query")));
+
 			parse->rowMarks = list_concat(parse->rowMarks, subquery->rowMarks);
+			if (subquery->rowMarks)
+				parse->forUpdate = subquery->forUpdate;
 
 			/*
 			 * We also have to fix the relid sets of any parent

src/backend/optimizer/prep/preptlist.c

@@ -15,7 +15,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/optimizer/prep/preptlist.c,v 1.74 2005/04/06 16:34:06 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/optimizer/prep/preptlist.c,v 1.75 2005/04/28 21:47:14 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -102,7 +102,7 @@ preprocess_targetlist(Query *parse, List *tlist)
 	}
 
 	/*
-	 * Add TID targets for rels selected FOR UPDATE.  The executor
+	 * Add TID targets for rels selected FOR UPDATE/SHARE.  The executor
 	 * uses the TID to know which rows to lock, much as for UPDATE or
 	 * DELETE.
 	 */
@@ -111,22 +111,22 @@ preprocess_targetlist(Query *parse, List *tlist)
 		ListCell   *l;
 
 		/*
-		 * We've got trouble if the FOR UPDATE appears inside
+		 * We've got trouble if the FOR UPDATE/SHARE appears inside
 		 * grouping, since grouping renders a reference to individual
 		 * tuple CTIDs invalid.  This is also checked at parse time,
 		 * but that's insufficient because of rule substitution, query
 		 * pullup, etc.
 		 */
-		CheckSelectForUpdate(parse);
+		CheckSelectLocking(parse, parse->forUpdate);
 
 		/*
-		 * Currently the executor only supports FOR UPDATE at top
+		 * Currently the executor only supports FOR UPDATE/SHARE at top
 		 * level
 		 */
 		if (PlannerQueryLevel > 1)
 			ereport(ERROR,
 					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-					 errmsg("SELECT FOR UPDATE is not allowed in subqueries")));
+					 errmsg("SELECT FOR UPDATE/SHARE is not allowed in subqueries")));
 
 		foreach(l, parse->rowMarks)
 		{

src/backend/parser/analyze.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- *	$PostgreSQL: pgsql/src/backend/parser/analyze.c,v 1.320 2005/04/14 20:03:24 tgl Exp $
+ *	$PostgreSQL: pgsql/src/backend/parser/analyze.c,v 1.321 2005/04/28 21:47:14 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -134,7 +134,7 @@ static void transformFKConstraints(ParseState *pstate,
 					   bool isAddConstraint);
 static void applyColumnNames(List *dst, List *src);
 static List *getSetColTypes(ParseState *pstate, Node *node);
-static void transformForUpdate(Query *qry, List *forUpdate);
+static void transformLocking(Query *qry, List *lockedRels, bool forUpdate);
 static void transformConstraintAttrs(List *constraintList);
 static void transformColumnType(ParseState *pstate, ColumnDef *column);
 static void release_pstate_resources(ParseState *pstate);
@@ -1810,8 +1810,8 @@ transformSelectStmt(ParseState *pstate, SelectStmt *stmt)
 
 	qry->commandType = CMD_SELECT;
 
-	/* make FOR UPDATE clause available to addRangeTableEntry */
-	pstate->p_forUpdate = stmt->forUpdate;
+	/* make FOR UPDATE/FOR SHARE list available to addRangeTableEntry */
+	pstate->p_lockedRels = stmt->lockedRels;
 
 	/* process the FROM clause */
 	transformFromClause(pstate, stmt->fromClause);
@@ -1870,8 +1870,8 @@ transformSelectStmt(ParseState *pstate, SelectStmt *stmt)
 	if (pstate->p_hasAggs || qry->groupClause || qry->havingQual)
 		parseCheckAggregates(pstate, qry);
 
-	if (stmt->forUpdate != NIL)
-		transformForUpdate(qry, stmt->forUpdate);
+	if (stmt->lockedRels != NIL)
+		transformLocking(qry, stmt->lockedRels, stmt->forUpdate);
 
 	return qry;
 }
@@ -1899,7 +1899,8 @@ transformSetOperationStmt(ParseState *pstate, SelectStmt *stmt)
 	List	   *sortClause;
 	Node	   *limitOffset;
 	Node	   *limitCount;
-	List	   *forUpdate;
+	List	   *lockedRels;
+	bool		forUpdate;
 	Node	   *node;
 	ListCell   *left_tlist,
 			   *dtlist;
@@ -1937,18 +1938,19 @@ transformSetOperationStmt(ParseState *pstate, SelectStmt *stmt)
 	sortClause = stmt->sortClause;
 	limitOffset = stmt->limitOffset;
 	limitCount = stmt->limitCount;
+	lockedRels = stmt->lockedRels;
 	forUpdate = stmt->forUpdate;
 
 	stmt->sortClause = NIL;
 	stmt->limitOffset = NULL;
 	stmt->limitCount = NULL;
-	stmt->forUpdate = NIL;
+	stmt->lockedRels = NIL;
 
-	/* We don't support forUpdate with set ops at the moment. */
-	if (forUpdate)
+	/* We don't support FOR UPDATE/SHARE with set ops at the moment. */
+	if (lockedRels)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-				 errmsg("SELECT FOR UPDATE is not allowed with UNION/INTERSECT/EXCEPT")));
+				 errmsg("SELECT FOR UPDATE/SHARE is not allowed with UNION/INTERSECT/EXCEPT")));
 
 	/*
 	 * Recursively transform the components of the tree.
@@ -2083,8 +2085,8 @@ transformSetOperationStmt(ParseState *pstate, SelectStmt *stmt)
 	if (pstate->p_hasAggs || qry->groupClause || qry->havingQual)
 		parseCheckAggregates(pstate, qry);
 
-	if (forUpdate != NIL)
-		transformForUpdate(qry, forUpdate);
+	if (lockedRels != NIL)
+		transformLocking(qry, lockedRels, forUpdate);
 
 	return qry;
 }
@@ -2107,11 +2109,11 @@ transformSetOperationTree(ParseState *pstate, SelectStmt *stmt)
 		ereport(ERROR,
 				(errcode(ERRCODE_SYNTAX_ERROR),
 				 errmsg("INTO is only allowed on first SELECT of UNION/INTERSECT/EXCEPT")));
-	/* We don't support forUpdate with set ops at the moment. */
-	if (stmt->forUpdate)
+	/* We don't support FOR UPDATE/SHARE with set ops at the moment. */
+	if (stmt->lockedRels)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-				 errmsg("SELECT FOR UPDATE is not allowed with UNION/INTERSECT/EXCEPT")));
+				 errmsg("SELECT FOR UPDATE/SHARE is not allowed with UNION/INTERSECT/EXCEPT")));
 
 	/*
 	 * If an internal node of a set-op tree has ORDER BY, UPDATE, or LIMIT
@@ -2128,7 +2130,7 @@ transformSetOperationTree(ParseState *pstate, SelectStmt *stmt)
 	{
 		Assert(stmt->larg != NULL && stmt->rarg != NULL);
 		if (stmt->sortClause || stmt->limitOffset || stmt->limitCount ||
-			stmt->forUpdate)
+			stmt->lockedRels)
 			isLeaf = true;
 		else
 			isLeaf = false;
@@ -2711,47 +2713,67 @@ transformExecuteStmt(ParseState *pstate, ExecuteStmt *stmt)
 
 /* exported so planner can check again after rewriting, query pullup, etc */
 void
-CheckSelectForUpdate(Query *qry)
+CheckSelectLocking(Query *qry, bool forUpdate)
 {
+	const char *operation;
+
+	if (forUpdate)
+		operation = "SELECT FOR UPDATE";
+	else
+		operation = "SELECT FOR SHARE";
+
 	if (qry->setOperations)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-				 errmsg("SELECT FOR UPDATE is not allowed with UNION/INTERSECT/EXCEPT")));
+				 /* translator: %s is a SQL command, like SELECT FOR UPDATE */
+				 errmsg("%s is not allowed with UNION/INTERSECT/EXCEPT", operation)));
 	if (qry->distinctClause != NIL)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-		errmsg("SELECT FOR UPDATE is not allowed with DISTINCT clause")));
+				 /* translator: %s is a SQL command, like SELECT FOR UPDATE */
+				 errmsg("%s is not allowed with DISTINCT clause", operation)));
 	if (qry->groupClause != NIL)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-		errmsg("SELECT FOR UPDATE is not allowed with GROUP BY clause")));
+				 /* translator: %s is a SQL command, like SELECT FOR UPDATE */
+				 errmsg("%s is not allowed with GROUP BY clause", operation)));
 	if (qry->havingQual != NULL)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-		errmsg("SELECT FOR UPDATE is not allowed with HAVING clause")));
+				 /* translator: %s is a SQL command, like SELECT FOR UPDATE */
+				 errmsg("%s is not allowed with HAVING clause", operation)));
 	if (qry->hasAggs)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-				 errmsg("SELECT FOR UPDATE is not allowed with aggregate functions")));
+				 /* translator: %s is a SQL command, like SELECT FOR UPDATE */
+				 errmsg("%s is not allowed with aggregate functions", operation)));
 }
 
 /*
- * Convert FOR UPDATE name list into rowMarks list of integer relids
+ * Convert FOR UPDATE/SHARE name list into rowMarks list of integer relids
  *
- * NB: if you need to change this, see also markQueryForUpdate()
+ * NB: if you need to change this, see also markQueryForLocking()
  * in rewriteHandler.c.
  */
 static void
-transformForUpdate(Query *qry, List *forUpdate)
+transformLocking(Query *qry, List *lockedRels, bool forUpdate)
 {
-	List	   *rowMarks = qry->rowMarks;
+	List	   *rowMarks;
 	ListCell   *l;
 	ListCell   *rt;
 	Index		i;
 
-	CheckSelectForUpdate(qry);
+	if (qry->rowMarks && forUpdate != qry->forUpdate)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("cannot use both FOR UPDATE and FOR SHARE in one query")));
+	qry->forUpdate = forUpdate;
+
+	CheckSelectLocking(qry, forUpdate);
+	
+	rowMarks = qry->rowMarks;
 
-	if (linitial(forUpdate) == NULL)
+	if (linitial(lockedRels) == NULL)
 	{
 		/* all regular tables used in query */
 		i = 0;
@@ -2770,10 +2792,11 @@ transformForUpdate(Query *qry, List *forUpdate)
 				case RTE_SUBQUERY:
 
 					/*
-					 * FOR UPDATE of subquery is propagated to subquery's
-					 * rels
+					 * FOR UPDATE/SHARE of subquery is propagated to all
+					 * of subquery's rels
 					 */
-					transformForUpdate(rte->subquery, list_make1(NULL));
+					transformLocking(rte->subquery, list_make1(NULL),
+									 forUpdate);
 					break;
 				default:
 					/* ignore JOIN, SPECIAL, FUNCTION RTEs */
@@ -2784,7 +2807,7 @@ transformForUpdate(Query *qry, List *forUpdate)
 	else
 	{
 		/* just the named tables */
-		foreach(l, forUpdate)
+		foreach(l, lockedRels)
 		{
 			char	   *relname = strVal(lfirst(l));
 
@@ -2806,25 +2829,26 @@ transformForUpdate(Query *qry, List *forUpdate)
 						case RTE_SUBQUERY:
 
 							/*
-							 * FOR UPDATE of subquery is propagated to
-							 * subquery's rels
+							 * FOR UPDATE/SHARE of subquery is propagated to
+							 * all of subquery's rels
 							 */
-							transformForUpdate(rte->subquery, list_make1(NULL));
+							transformLocking(rte->subquery, list_make1(NULL),
+											 forUpdate);
 							break;
 						case RTE_JOIN:
 							ereport(ERROR,
 								 (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-								  errmsg("SELECT FOR UPDATE cannot be applied to a join")));
+								  errmsg("SELECT FOR UPDATE/SHARE cannot be applied to a join")));
 							break;
 						case RTE_SPECIAL:
 							ereport(ERROR,
 								 (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-								  errmsg("SELECT FOR UPDATE cannot be applied to NEW or OLD")));
+								  errmsg("SELECT FOR UPDATE/SHARE cannot be applied to NEW or OLD")));
 							break;
 						case RTE_FUNCTION:
 							ereport(ERROR,
 								 (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-								  errmsg("SELECT FOR UPDATE cannot be applied to a function")));
+								  errmsg("SELECT FOR UPDATE/SHARE cannot be applied to a function")));
 							break;
 						default:
 							elog(ERROR, "unrecognized RTE type: %d",
@@ -2837,7 +2861,7 @@ transformForUpdate(Query *qry, List *forUpdate)
 			if (rt == NULL)
 				ereport(ERROR,
 						(errcode(ERRCODE_UNDEFINED_TABLE),
-						 errmsg("relation \"%s\" in FOR UPDATE clause not found in FROM clause",
+						 errmsg("relation \"%s\" in FOR UPDATE/SHARE clause not found in FROM clause",
 								relname)));
 		}
 	}

src/backend/parser/gram.y

@@ -11,7 +11,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/parser/gram.y,v 2.488 2005/04/23 17:22:16 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/parser/gram.y,v 2.489 2005/04/28 21:47:14 tgl Exp $
  *
  * HISTORY
  *	  AUTHOR			DATE			MAJOR EVENT
@@ -87,7 +87,7 @@ static List *check_func_name(List *names);
 static List *extractArgTypes(List *parameters);
 static SelectStmt *findLeftmostSelect(SelectStmt *node);
 static void insertSelectOptions(SelectStmt *stmt,
-								List *sortClause, List *forUpdate,
+								List *sortClause, List *lockingClause,
 								Node *limitOffset, Node *limitCount);
 static Node *makeSetOp(SetOperation op, bool all, Node *larg, Node *rarg);
 static Node *doNegate(Node *n);
@@ -242,7 +242,8 @@ static void doNegateFloat(Value *v);
 %type <oncommit> OnCommitOption
 %type <withoids> OptWithOids WithOidsAs
 
-%type <list>	for_update_clause opt_for_update_clause update_list
+%type <list>	for_locking_clause opt_for_locking_clause
+				update_list
 %type <boolean>	opt_all
 
 %type <node>	join_outer join_qual
@@ -4886,9 +4887,9 @@ select_with_parens:
 		;
 
 /*
- *	FOR UPDATE may be before or after LIMIT/OFFSET.
+ *	FOR UPDATE/SHARE may be before or after LIMIT/OFFSET.
  *	In <=7.2.X, LIMIT/OFFSET had to be after FOR UPDATE
- *	We now support both orderings, but prefer LIMIT/OFFSET before FOR UPDATE
+ *	We now support both orderings, but prefer LIMIT/OFFSET before FOR UPDATE/SHARE
  *	2002-08-28 bjm
  */
 select_no_parens:
@@ -4899,13 +4900,13 @@ select_no_parens:
 										NULL, NULL);
 					$$ = $1;
 				}
-			| select_clause opt_sort_clause for_update_clause opt_select_limit
+			| select_clause opt_sort_clause for_locking_clause opt_select_limit
 				{
 					insertSelectOptions((SelectStmt *) $1, $2, $3,
 										list_nth($4, 0), list_nth($4, 1));
 					$$ = $1;
 				}
-			| select_clause opt_sort_clause select_limit opt_for_update_clause
+			| select_clause opt_sort_clause select_limit opt_for_locking_clause
 				{
 					insertSelectOptions((SelectStmt *) $1, $2, $4,
 										list_nth($3, 0), list_nth($3, 1));
@@ -5146,13 +5147,14 @@ having_clause:
 			| /*EMPTY*/								{ $$ = NULL; }
 		;
 
-for_update_clause:
-			FOR UPDATE update_list					{ $$ = $3; }
+for_locking_clause:
+			FOR UPDATE update_list					{ $$ = lcons(makeString("for_update"), $3); }
+			| FOR SHARE update_list					{ $$ = lcons(makeString("for_share"), $3); }
 			| FOR READ ONLY							{ $$ = NULL; }
 		;
 
-opt_for_update_clause:
-			for_update_clause						{ $$ = $1; }
+opt_for_locking_clause:
+			for_locking_clause						{ $$ = $1; }
 			| /* EMPTY */							{ $$ = NULL; }
 		;
 
@@ -8379,7 +8381,7 @@ findLeftmostSelect(SelectStmt *node)
  */
 static void
 insertSelectOptions(SelectStmt *stmt,
-					List *sortClause, List *forUpdate,
+					List *sortClause, List *lockingClause,
 					Node *limitOffset, Node *limitCount)
 {
 	/*
@@ -8394,13 +8396,27 @@ insertSelectOptions(SelectStmt *stmt,
 					 errmsg("multiple ORDER BY clauses not allowed")));
 		stmt->sortClause = sortClause;
 	}
-	if (forUpdate)
+	if (lockingClause)
 	{
-		if (stmt->forUpdate)
+		Value	   *type;
+
+		if (stmt->lockedRels)
 			ereport(ERROR,
 					(errcode(ERRCODE_SYNTAX_ERROR),
-					 errmsg("multiple FOR UPDATE clauses not allowed")));
-		stmt->forUpdate = forUpdate;
+					 errmsg("multiple FOR UPDATE/FOR SHARE clauses not allowed")));
+
+		Assert(list_length(lockingClause) > 1);
+		/* 1st is Value node containing "for_update" or "for_share" */
+		type = (Value *) linitial(lockingClause);
+		Assert(IsA(type, String));
+		if (strcmp(strVal(type), "for_update") == 0)
+			stmt->forUpdate = true;
+		else if (strcmp(strVal(type), "for_share") == 0)
+			stmt->forUpdate = false;
+		else
+			elog(ERROR, "invalid first node in locking clause");
+
+		stmt->lockedRels = list_delete_first(lockingClause);
 	}
 	if (limitOffset)
 	{

src/backend/parser/parse_relation.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/parser/parse_relation.c,v 1.106 2005/04/13 16:50:55 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/parser/parse_relation.c,v 1.107 2005/04/28 21:47:14 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -40,7 +40,7 @@ static Node *scanNameSpaceForRelid(ParseState *pstate, Node *nsnode,
 					  Oid relid);
 static void scanNameSpaceForConflict(ParseState *pstate, Node *nsnode,
 						 RangeTblEntry *rte1, const char *aliasname1);
-static bool isForUpdate(ParseState *pstate, char *refname);
+static bool isLockedRel(ParseState *pstate, char *refname);
 static void expandRelation(Oid relid, Alias *eref,
 			   int rtindex, int sublevels_up,
 			   bool include_dropped,
@@ -759,9 +759,9 @@ addRangeTableEntry(ParseState *pstate,
 	 * Get the rel's OID.  This access also ensures that we have an
 	 * up-to-date relcache entry for the rel.  Since this is typically the
 	 * first access to a rel in a statement, be careful to get the right
-	 * access level depending on whether we're doing SELECT FOR UPDATE.
+	 * access level depending on whether we're doing SELECT FOR UPDATE/SHARE.
 	 */
-	lockmode = isForUpdate(pstate, refname) ? RowShareLock : AccessShareLock;
+	lockmode = isLockedRel(pstate, refname) ? RowShareLock : AccessShareLock;
 	rel = heap_openrv(relation, lockmode);
 	rte->relid = RelationGetRelid(rel);
 
@@ -1121,17 +1121,17 @@ addRangeTableEntryForJoin(ParseState *pstate,
 }
 
 /*
- * Has the specified refname been selected FOR UPDATE?
+ * Has the specified refname been selected FOR UPDATE/FOR SHARE?
  */
 static bool
-isForUpdate(ParseState *pstate, char *refname)
+isLockedRel(ParseState *pstate, char *refname)
 {
 	/* Outer loop to check parent query levels as well as this one */
 	while (pstate != NULL)
 	{
-		if (pstate->p_forUpdate != NIL)
+		if (pstate->p_lockedRels != NIL)
 		{
-			if (linitial(pstate->p_forUpdate) == NULL)
+			if (linitial(pstate->p_lockedRels) == NULL)
 			{
 				/* all tables used in query */
 				return true;
@@ -1141,7 +1141,7 @@ isForUpdate(ParseState *pstate, char *refname)
 				/* just the named tables */
 				ListCell   *l;
 
-				foreach(l, pstate->p_forUpdate)
+				foreach(l, pstate->p_lockedRels)
 				{
 					char	   *rname = strVal(lfirst(l));
 

src/backend/parser/parse_type.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/parser/parse_type.c,v 1.73 2004/12/31 22:00:27 pgsql Exp $
+ *	  $PostgreSQL: pgsql/src/backend/parser/parse_type.c,v 1.74 2005/04/28 21:47:14 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -432,7 +432,7 @@ parseTypeString(const char *str, Oid *type_id, int32 *typmod)
 		stmt->sortClause != NIL ||
 		stmt->limitOffset != NULL ||
 		stmt->limitCount != NULL ||
-		stmt->forUpdate != NIL ||
+		stmt->lockedRels != NIL ||
 		stmt->op != SETOP_NONE)
 		goto fail;
 	if (list_length(stmt->targetList) != 1)

src/backend/rewrite/rewriteHandler.c

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/rewrite/rewriteHandler.c,v 1.150 2005/04/06 16:34:06 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/rewrite/rewriteHandler.c,v 1.151 2005/04/28 21:47:14 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -51,7 +51,7 @@ static TargetEntry *process_matched_tle(TargetEntry *src_tle,
 					TargetEntry *prior_tle,
 					const char *attrName);
 static Node *get_assignment_input(Node *node);
-static void markQueryForUpdate(Query *qry, bool skipOldNew);
+static void markQueryForLocking(Query *qry, bool forUpdate, bool skipOldNew);
 static List *matchLocks(CmdType event, RuleLock *rulelocks,
 		   int varno, Query *parsetree);
 static Query *fireRIRrules(Query *parsetree, List *activeRIRs);
@@ -745,40 +745,46 @@ ApplyRetrieveRule(Query *parsetree,
 	rte->checkAsUser = 0;
 
 	/*
-	 * FOR UPDATE of view?
+	 * FOR UPDATE/SHARE of view?
 	 */
 	if (list_member_int(parsetree->rowMarks, rt_index))
 	{
 		/*
 		 * Remove the view from the list of rels that will actually be
-		 * marked FOR UPDATE by the executor.  It will still be access-
+		 * marked FOR UPDATE/SHARE by the executor.  It will still be access-
 		 * checked for write access, though.
 		 */
 		parsetree->rowMarks = list_delete_int(parsetree->rowMarks, rt_index);
 
 		/*
-		 * Set up the view's referenced tables as if FOR UPDATE.
+		 * Set up the view's referenced tables as if FOR UPDATE/SHARE.
 		 */
-		markQueryForUpdate(rule_action, true);
+		markQueryForLocking(rule_action, parsetree->forUpdate, true);
 	}
 
 	return parsetree;
 }
 
 /*
- * Recursively mark all relations used by a view as FOR UPDATE.
+ * Recursively mark all relations used by a view as FOR UPDATE/SHARE.
  *
  * This may generate an invalid query, eg if some sub-query uses an
  * aggregate.  We leave it to the planner to detect that.
  *
- * NB: this must agree with the parser's transformForUpdate() routine.
+ * NB: this must agree with the parser's transformLocking() routine.
  */
 static void
-markQueryForUpdate(Query *qry, bool skipOldNew)
+markQueryForLocking(Query *qry, bool forUpdate, bool skipOldNew)
 {
 	Index		rti = 0;
 	ListCell   *l;
 
+	if (qry->rowMarks && forUpdate != qry->forUpdate)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("cannot use both FOR UPDATE and FOR SHARE in one query")));
+	qry->forUpdate = forUpdate;
+
 	foreach(l, qry->rtable)
 	{
 		RangeTblEntry *rte = (RangeTblEntry *) lfirst(l);
@@ -798,8 +804,8 @@ markQueryForUpdate(Query *qry, bool skipOldNew)
 		}
 		else if (rte->rtekind == RTE_SUBQUERY)
 		{
-			/* FOR UPDATE of subquery is propagated to subquery's rels */
-			markQueryForUpdate(rte->subquery, false);
+			/* FOR UPDATE/SHARE of subquery is propagated to subquery's rels */
+			markQueryForLocking(rte->subquery, forUpdate, false);
 		}
 	}
 }
@@ -911,7 +917,7 @@ fireRIRrules(Query *parsetree, List *activeRIRs)
 		 * If the relation is the query's result relation, then
 		 * RewriteQuery() already got the right lock on it, so we need no
 		 * additional lock. Otherwise, check to see if the relation is
-		 * accessed FOR UPDATE or not.
+		 * accessed FOR UPDATE/SHARE or not.
 		 */
 		if (rt_index == parsetree->resultRelation)
 			lockmode = NoLock;

src/backend/storage/ipc/ipci.c

@@ -8,13 +8,14 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/storage/ipc/ipci.c,v 1.74 2004/12/31 22:00:56 pgsql Exp $
+ *	  $PostgreSQL: pgsql/src/backend/storage/ipc/ipci.c,v 1.75 2005/04/28 21:47:15 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
 #include "postgres.h"
 
 #include "access/clog.h"
+#include "access/multixact.h"
 #include "access/subtrans.h"
 #include "access/xlog.h"
 #include "miscadmin.h"
@@ -75,6 +76,7 @@ CreateSharedMemoryAndSemaphores(bool makePrivate,
 		size += XLOGShmemSize();
 		size += CLOGShmemSize();
 		size += SUBTRANSShmemSize();
+		size += MultiXactShmemSize();
 		size += LWLockShmemSize();
 		size += SInvalShmemSize(maxBackends);
 		size += FreeSpaceShmemSize();
@@ -140,6 +142,7 @@ CreateSharedMemoryAndSemaphores(bool makePrivate,
 	XLOGShmemInit();
 	CLOGShmemInit();
 	SUBTRANSShmemInit();
+	MultiXactShmemInit();
 	InitBufferPool();
 
 	/*

src/backend/storage/lmgr/lwlock.c

@@ -15,7 +15,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/storage/lmgr/lwlock.c,v 1.27 2005/04/08 14:18:35 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/storage/lmgr/lwlock.c,v 1.28 2005/04/28 21:47:15 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -114,6 +114,12 @@ NumLWLocks(void)
 	/* subtrans.c needs one per SubTrans buffer */
 	numLocks += NUM_SLRU_BUFFERS;
 
+	/*
+	 * multixact.c needs one per MultiXact buffer, but there are
+	 * two SLRU areas for MultiXact
+	 */
+	numLocks += 2 * NUM_SLRU_BUFFERS;
+
 	/* Perhaps create a few more for use by user-defined modules? */
 
 	return numLocks;

src/backend/tcop/utility.c

@@ -10,7 +10,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/tcop/utility.c,v 1.235 2005/04/14 01:38:18 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/tcop/utility.c,v 1.236 2005/04/28 21:47:15 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -238,7 +238,7 @@ QueryIsReadOnly(Query *parsetree)
 			if (parsetree->into != NULL)
 				return false;					/* SELECT INTO */
 			else if (parsetree->rowMarks != NIL)
-				return false;					/* SELECT FOR UPDATE */
+				return false;					/* SELECT FOR UPDATE/SHARE */
 			else
 				return true;
 		case CMD_UPDATE:
@@ -1663,7 +1663,12 @@ CreateQueryTag(Query *parsetree)
 			if (parsetree->into != NULL)
 				tag = "SELECT INTO";
 			else if (parsetree->rowMarks != NIL)
-				tag = "SELECT FOR UPDATE";
+			{
+				if (parsetree->forUpdate)
+					tag = "SELECT FOR UPDATE";
+				else
+					tag = "SELECT FOR SHARE";
+			}
 			else
 				tag = "SELECT";
 			break;

src/backend/utils/adt/ri_triggers.c

@@ -17,7 +17,7 @@
  *
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  *
- * $PostgreSQL: pgsql/src/backend/utils/adt/ri_triggers.c,v 1.76 2004/12/31 22:01:22 pgsql Exp $
+ * $PostgreSQL: pgsql/src/backend/utils/adt/ri_triggers.c,v 1.77 2005/04/28 21:47:15 tgl Exp $
  *
  * ----------
  */
@@ -206,7 +206,7 @@ RI_FKey_check(PG_FUNCTION_ARGS)
 	 * tuple.
 	 *
 	 * pk_rel is opened in RowShareLock mode since that's what our eventual
-	 * SELECT FOR UPDATE will get on it.
+	 * SELECT FOR SHARE will get on it.
 	 */
 	pk_rel = heap_open(trigdata->tg_trigger->tgconstrrelid, RowShareLock);
 	fk_rel = trigdata->tg_relation;
@@ -267,7 +267,7 @@ RI_FKey_check(PG_FUNCTION_ARGS)
 			 * ----------
 			 */
 			quoteRelationName(pkrelname, pk_rel);
-			snprintf(querystr, sizeof(querystr), "SELECT 1 FROM ONLY %s x FOR UPDATE OF x",
+			snprintf(querystr, sizeof(querystr), "SELECT 1 FROM ONLY %s x FOR SHARE OF x",
 					 pkrelname);
 
 			/* Prepare and save the plan */
@@ -428,7 +428,7 @@ RI_FKey_check(PG_FUNCTION_ARGS)
 			queryoids[i] = SPI_gettypeid(fk_rel->rd_att,
 									 qkey.keypair[i][RI_KEYPAIR_FK_IDX]);
 		}
-		strcat(querystr, " FOR UPDATE OF x");
+		strcat(querystr, " FOR SHARE OF x");
 
 		/* Prepare and save the plan */
 		qplan = ri_PlanCheck(querystr, qkey.nkeypairs, queryoids,
@@ -590,7 +590,7 @@ ri_Check_Pk_Match(Relation pk_rel, Relation fk_rel,
 			queryoids[i] = SPI_gettypeid(pk_rel->rd_att,
 									 qkey.keypair[i][RI_KEYPAIR_PK_IDX]);
 		}
-		strcat(querystr, " FOR UPDATE OF x");
+		strcat(querystr, " FOR SHARE OF x");
 
 		/* Prepare and save the plan */
 		qplan = ri_PlanCheck(querystr, qkey.nkeypairs, queryoids,
@@ -655,7 +655,7 @@ RI_FKey_noaction_del(PG_FUNCTION_ARGS)
 	 * tuple.
 	 *
 	 * fk_rel is opened in RowShareLock mode since that's what our eventual
-	 * SELECT FOR UPDATE will get on it.
+	 * SELECT FOR SHARE will get on it.
 	 */
 	fk_rel = heap_open(trigdata->tg_trigger->tgconstrrelid, RowShareLock);
 	pk_rel = trigdata->tg_relation;
@@ -748,7 +748,7 @@ RI_FKey_noaction_del(PG_FUNCTION_ARGS)
 					queryoids[i] = SPI_gettypeid(pk_rel->rd_att,
 									 qkey.keypair[i][RI_KEYPAIR_PK_IDX]);
 				}
-				strcat(querystr, " FOR UPDATE OF x");
+				strcat(querystr, " FOR SHARE OF x");
 
 				/* Prepare and save the plan */
 				qplan = ri_PlanCheck(querystr, qkey.nkeypairs, queryoids,
@@ -834,7 +834,7 @@ RI_FKey_noaction_upd(PG_FUNCTION_ARGS)
 	 * and old tuple.
 	 *
 	 * fk_rel is opened in RowShareLock mode since that's what our eventual
-	 * SELECT FOR UPDATE will get on it.
+	 * SELECT FOR SHARE will get on it.
 	 */
 	fk_rel = heap_open(trigdata->tg_trigger->tgconstrrelid, RowShareLock);
 	pk_rel = trigdata->tg_relation;
@@ -939,7 +939,7 @@ RI_FKey_noaction_upd(PG_FUNCTION_ARGS)
 					queryoids[i] = SPI_gettypeid(pk_rel->rd_att,
 									 qkey.keypair[i][RI_KEYPAIR_PK_IDX]);
 				}
-				strcat(querystr, " FOR UPDATE OF x");
+				strcat(querystr, " FOR SHARE OF x");
 
 				/* Prepare and save the plan */
 				qplan = ri_PlanCheck(querystr, qkey.nkeypairs, queryoids,
@@ -1373,7 +1373,7 @@ RI_FKey_restrict_del(PG_FUNCTION_ARGS)
 	 * tuple.
 	 *
 	 * fk_rel is opened in RowShareLock mode since that's what our eventual
-	 * SELECT FOR UPDATE will get on it.
+	 * SELECT FOR SHARE will get on it.
 	 */
 	fk_rel = heap_open(trigdata->tg_trigger->tgconstrrelid, RowShareLock);
 	pk_rel = trigdata->tg_relation;
@@ -1453,7 +1453,7 @@ RI_FKey_restrict_del(PG_FUNCTION_ARGS)
 					queryoids[i] = SPI_gettypeid(pk_rel->rd_att,
 									 qkey.keypair[i][RI_KEYPAIR_PK_IDX]);
 				}
-				strcat(querystr, " FOR UPDATE OF x");
+				strcat(querystr, " FOR SHARE OF x");
 
 				/* Prepare and save the plan */
 				qplan = ri_PlanCheck(querystr, qkey.nkeypairs, queryoids,
@@ -1543,7 +1543,7 @@ RI_FKey_restrict_upd(PG_FUNCTION_ARGS)
 	 * and old tuple.
 	 *
 	 * fk_rel is opened in RowShareLock mode since that's what our eventual
-	 * SELECT FOR UPDATE will get on it.
+	 * SELECT FOR SHARE will get on it.
 	 */
 	fk_rel = heap_open(trigdata->tg_trigger->tgconstrrelid, RowShareLock);
 	pk_rel = trigdata->tg_relation;
@@ -1634,7 +1634,7 @@ RI_FKey_restrict_upd(PG_FUNCTION_ARGS)
 					queryoids[i] = SPI_gettypeid(pk_rel->rd_att,
 									 qkey.keypair[i][RI_KEYPAIR_PK_IDX]);
 				}
-				strcat(querystr, " FOR UPDATE OF x");
+				strcat(querystr, " FOR SHARE OF x");
 
 				/* Prepare and save the plan */
 				qplan = ri_PlanCheck(querystr, qkey.nkeypairs, queryoids,

src/backend/utils/time/tqual.c

@@ -16,13 +16,14 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/time/tqual.c,v 1.86 2005/03/20 23:40:27 neilc Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/time/tqual.c,v 1.87 2005/04/28 21:47:16 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
 
 #include "postgres.h"
 
+#include "access/multixact.h"
 #include "access/subtrans.h"
 #include "storage/sinval.h"
 #include "utils/tqual.h"
@@ -129,7 +130,12 @@ HeapTupleSatisfiesItself(HeapTupleHeader tuple, Buffer buffer)
 			if (tuple->t_infomask & HEAP_XMAX_INVALID)	/* xid invalid */
 				return true;
 
-			/* deleting subtransaction aborted */
+			if (tuple->t_infomask & HEAP_IS_LOCKED)		/* not deleter */
+				return true;
+
+			Assert(!(tuple->t_infomask & HEAP_XMAX_IS_MULTI));
+
+			/* deleting subtransaction aborted? */
 			if (TransactionIdDidAbort(HeapTupleHeaderGetXmax(tuple)))
 			{
 				tuple->t_infomask |= HEAP_XMAX_INVALID;
@@ -139,9 +145,6 @@ HeapTupleSatisfiesItself(HeapTupleHeader tuple, Buffer buffer)
 
 			Assert(TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)));
 
-			if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
-				return true;
-
 			return false;
 		}
 		else if (!TransactionIdDidCommit(HeapTupleHeaderGetXmin(tuple)))
@@ -167,14 +170,21 @@ HeapTupleSatisfiesItself(HeapTupleHeader tuple, Buffer buffer)
 
 	if (tuple->t_infomask & HEAP_XMAX_COMMITTED)
 	{
-		if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+		if (tuple->t_infomask & HEAP_IS_LOCKED)
 			return true;
 		return false;			/* updated by other */
 	}
 
+	if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
+	{
+		/* MultiXacts are currently only allowed to lock tuples */
+		Assert(tuple->t_infomask & HEAP_IS_LOCKED);
+		return true;
+	}
+
 	if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
 	{
-		if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+		if (tuple->t_infomask & HEAP_IS_LOCKED)
 			return true;
 		return false;
 	}
@@ -191,7 +201,7 @@ HeapTupleSatisfiesItself(HeapTupleHeader tuple, Buffer buffer)
 
 	/* xmax transaction committed */
 
-	if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+	if (tuple->t_infomask & HEAP_IS_LOCKED)
 	{
 		tuple->t_infomask |= HEAP_XMAX_INVALID;
 		SetBufferCommitInfoNeedsSave(buffer);
@@ -300,7 +310,12 @@ HeapTupleSatisfiesNow(HeapTupleHeader tuple, Buffer buffer)
 			if (tuple->t_infomask & HEAP_XMAX_INVALID)	/* xid invalid */
 				return true;
 
-			/* deleting subtransaction aborted */
+			if (tuple->t_infomask & HEAP_IS_LOCKED)		/* not deleter */
+				return true;
+
+			Assert(!(tuple->t_infomask & HEAP_XMAX_IS_MULTI));
+
+			/* deleting subtransaction aborted? */
 			if (TransactionIdDidAbort(HeapTupleHeaderGetXmax(tuple)))
 			{
 				tuple->t_infomask |= HEAP_XMAX_INVALID;
@@ -310,9 +325,6 @@ HeapTupleSatisfiesNow(HeapTupleHeader tuple, Buffer buffer)
 
 			Assert(TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)));
 
-			if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
-				return true;
-
 			if (HeapTupleHeaderGetCmax(tuple) >= GetCurrentCommandId())
 				return true;	/* deleted after scan started */
 			else
@@ -341,14 +353,21 @@ HeapTupleSatisfiesNow(HeapTupleHeader tuple, Buffer buffer)
 
 	if (tuple->t_infomask & HEAP_XMAX_COMMITTED)
 	{
-		if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+		if (tuple->t_infomask & HEAP_IS_LOCKED)
 			return true;
 		return false;
 	}
 
+	if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
+	{
+		/* MultiXacts are currently only allowed to lock tuples */
+		Assert(tuple->t_infomask & HEAP_IS_LOCKED);
+		return true;
+	}
+
 	if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
 	{
-		if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+		if (tuple->t_infomask & HEAP_IS_LOCKED)
 			return true;
 		if (HeapTupleHeaderGetCmax(tuple) >= GetCurrentCommandId())
 			return true;		/* deleted after scan started */
@@ -368,7 +387,7 @@ HeapTupleSatisfiesNow(HeapTupleHeader tuple, Buffer buffer)
 
 	/* xmax transaction committed */
 
-	if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+	if (tuple->t_infomask & HEAP_IS_LOCKED)
 	{
 		tuple->t_infomask |= HEAP_XMAX_INVALID;
 		SetBufferCommitInfoNeedsSave(buffer);
@@ -454,6 +473,22 @@ HeapTupleSatisfiesToast(HeapTupleHeader tuple, Buffer buffer)
  *	code, since UPDATE needs to know more than "is it visible?".  Also,
  *	tuples of my own xact are tested against the passed CommandId not
  *	CurrentCommandId.
+ *
+ *	The possible return codes are:
+ *
+ *	HeapTupleInvisible: the tuple didn't exist at all when the scan started,
+ *	e.g. it was created by a later CommandId.
+ *
+ *	HeapTupleMayBeUpdated: The tuple is valid and visible, so it may be
+ *	updated.
+ *
+ *	HeapTupleSelfUpdated: The tuple was updated by the current transaction,
+ *	after the current scan started.
+ *
+ *	HeapTupleUpdated: The tuple was updated by a committed transaction.
+ *
+ *	HeapTupleBeingUpdated: The tuple is being updated by an in-progress
+ *	transaction other than the current transaction.
  */
 HTSU_Result
 HeapTupleSatisfiesUpdate(HeapTupleHeader tuple, CommandId curcid,
@@ -512,7 +547,12 @@ HeapTupleSatisfiesUpdate(HeapTupleHeader tuple, CommandId curcid,
 			if (tuple->t_infomask & HEAP_XMAX_INVALID)	/* xid invalid */
 				return HeapTupleMayBeUpdated;
 
-			/* deleting subtransaction aborted */
+			if (tuple->t_infomask & HEAP_IS_LOCKED)		/* not deleter */
+				return HeapTupleMayBeUpdated;
+
+			Assert(!(tuple->t_infomask & HEAP_XMAX_IS_MULTI));
+
+			/* deleting subtransaction aborted? */
 			if (TransactionIdDidAbort(HeapTupleHeaderGetXmax(tuple)))
 			{
 				tuple->t_infomask |= HEAP_XMAX_INVALID;
@@ -522,9 +562,6 @@ HeapTupleSatisfiesUpdate(HeapTupleHeader tuple, CommandId curcid,
 
 			Assert(TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)));
 
-			if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
-				return HeapTupleMayBeUpdated;
-
 			if (HeapTupleHeaderGetCmax(tuple) >= curcid)
 				return HeapTupleSelfUpdated;	/* updated after scan
 												 * started */
@@ -555,14 +592,26 @@ HeapTupleSatisfiesUpdate(HeapTupleHeader tuple, CommandId curcid,
 
 	if (tuple->t_infomask & HEAP_XMAX_COMMITTED)
 	{
-		if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+		if (tuple->t_infomask & HEAP_IS_LOCKED)
 			return HeapTupleMayBeUpdated;
 		return HeapTupleUpdated;	/* updated by other */
 	}
 
+	if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
+	{
+		/* MultiXacts are currently only allowed to lock tuples */
+		Assert(tuple->t_infomask & HEAP_IS_LOCKED);
+
+		if (MultiXactIdIsRunning(HeapTupleHeaderGetXmax(tuple)))
+			return HeapTupleBeingUpdated;
+		tuple->t_infomask |= HEAP_XMAX_INVALID;
+		SetBufferCommitInfoNeedsSave(buffer);
+		return HeapTupleMayBeUpdated;
+	}
+
 	if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
 	{
-		if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+		if (tuple->t_infomask & HEAP_IS_LOCKED)
 			return HeapTupleMayBeUpdated;
 		if (HeapTupleHeaderGetCmax(tuple) >= curcid)
 			return HeapTupleSelfUpdated;		/* updated after scan
@@ -585,7 +634,7 @@ HeapTupleSatisfiesUpdate(HeapTupleHeader tuple, CommandId curcid,
 
 	/* xmax transaction committed */
 
-	if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+	if (tuple->t_infomask & HEAP_IS_LOCKED)
 	{
 		tuple->t_infomask |= HEAP_XMAX_INVALID;
 		SetBufferCommitInfoNeedsSave(buffer);
@@ -669,7 +718,12 @@ HeapTupleSatisfiesDirty(HeapTupleHeader tuple, Buffer buffer)
 			if (tuple->t_infomask & HEAP_XMAX_INVALID)	/* xid invalid */
 				return true;
 
-			/* deleting subtransaction aborted */
+			if (tuple->t_infomask & HEAP_IS_LOCKED)		/* not deleter */
+				return true;
+
+			Assert(!(tuple->t_infomask & HEAP_XMAX_IS_MULTI));
+
+			/* deleting subtransaction aborted? */
 			if (TransactionIdDidAbort(HeapTupleHeaderGetXmax(tuple)))
 			{
 				tuple->t_infomask |= HEAP_XMAX_INVALID;
@@ -679,9 +733,6 @@ HeapTupleSatisfiesDirty(HeapTupleHeader tuple, Buffer buffer)
 
 			Assert(TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)));
 
-			if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
-				return true;
-
 			return false;
 		}
 		else if (!TransactionIdDidCommit(HeapTupleHeaderGetXmin(tuple)))
@@ -710,15 +761,22 @@ HeapTupleSatisfiesDirty(HeapTupleHeader tuple, Buffer buffer)
 
 	if (tuple->t_infomask & HEAP_XMAX_COMMITTED)
 	{
-		if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+		if (tuple->t_infomask & HEAP_IS_LOCKED)
 			return true;
 		SnapshotDirty->tid = tuple->t_ctid;
 		return false;			/* updated by other */
 	}
 
+	if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
+	{
+		/* MultiXacts are currently only allowed to lock tuples */
+		Assert(tuple->t_infomask & HEAP_IS_LOCKED);
+		return true;
+	}
+
 	if (TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)))
 	{
-		if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+		if (tuple->t_infomask & HEAP_IS_LOCKED)
 			return true;
 		return false;
 	}
@@ -738,7 +796,7 @@ HeapTupleSatisfiesDirty(HeapTupleHeader tuple, Buffer buffer)
 
 	/* xmax transaction committed */
 
-	if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+	if (tuple->t_infomask & HEAP_IS_LOCKED)
 	{
 		tuple->t_infomask |= HEAP_XMAX_INVALID;
 		SetBufferCommitInfoNeedsSave(buffer);
@@ -828,7 +886,12 @@ HeapTupleSatisfiesSnapshot(HeapTupleHeader tuple, Snapshot snapshot,
 			if (tuple->t_infomask & HEAP_XMAX_INVALID)	/* xid invalid */
 				return true;
 
-			/* deleting subtransaction aborted */
+			if (tuple->t_infomask & HEAP_IS_LOCKED)		/* not deleter */
+				return true;
+
+			Assert(!(tuple->t_infomask & HEAP_XMAX_IS_MULTI));
+
+			/* deleting subtransaction aborted? */
 			/* FIXME -- is this correct w.r.t. the cmax of the tuple? */
 			if (TransactionIdDidAbort(HeapTupleHeaderGetXmax(tuple)))
 			{
@@ -839,9 +902,6 @@ HeapTupleSatisfiesSnapshot(HeapTupleHeader tuple, Snapshot snapshot,
 
 			Assert(TransactionIdIsCurrentTransactionId(HeapTupleHeaderGetXmax(tuple)));
 
-			if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
-				return true;
-
 			if (HeapTupleHeaderGetCmax(tuple) >= snapshot->curcid)
 				return true;	/* deleted after scan started */
 			else
@@ -902,8 +962,15 @@ HeapTupleSatisfiesSnapshot(HeapTupleHeader tuple, Snapshot snapshot,
 	if (tuple->t_infomask & HEAP_XMAX_INVALID)	/* xid invalid or aborted */
 		return true;
 
-	if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+	if (tuple->t_infomask & HEAP_IS_LOCKED)
+		return true;
+
+	if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
+	{
+		/* MultiXacts are currently only allowed to lock tuples */
+		Assert(tuple->t_infomask & HEAP_IS_LOCKED);
 		return true;
+	}
 
 	if (!(tuple->t_infomask & HEAP_XMAX_COMMITTED))
 	{
@@ -1043,7 +1110,7 @@ HeapTupleSatisfiesVacuum(HeapTupleHeader tuple, TransactionId OldestXmin,
 		{
 			if (tuple->t_infomask & HEAP_XMAX_INVALID)	/* xid invalid */
 				return HEAPTUPLE_INSERT_IN_PROGRESS;
-			if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+			if (tuple->t_infomask & HEAP_IS_LOCKED)
 				return HEAPTUPLE_INSERT_IN_PROGRESS;
 			/* inserted and then deleted by same xact */
 			return HEAPTUPLE_DELETE_IN_PROGRESS;
@@ -1074,22 +1141,30 @@ HeapTupleSatisfiesVacuum(HeapTupleHeader tuple, TransactionId OldestXmin,
 	if (tuple->t_infomask & HEAP_XMAX_INVALID)
 		return HEAPTUPLE_LIVE;
 
-	if (tuple->t_infomask & HEAP_MARKED_FOR_UPDATE)
+	if (tuple->t_infomask & HEAP_IS_LOCKED)
 	{
 		/*
-		 * "Deleting" xact really only marked it for update, so the tuple
+		 * "Deleting" xact really only locked it, so the tuple
 		 * is live in any case.  However, we must make sure that either
 		 * XMAX_COMMITTED or XMAX_INVALID gets set once the xact is gone;
 		 * otherwise it is unsafe to recycle CLOG status after vacuuming.
 		 */
 		if (!(tuple->t_infomask & HEAP_XMAX_COMMITTED))
 		{
-			if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
-				return HEAPTUPLE_LIVE;
+			if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
+			{
+				if (MultiXactIdIsRunning(HeapTupleHeaderGetXmax(tuple)))
+					return HEAPTUPLE_LIVE;
+			}
+			else
+			{
+				if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))
+					return HEAPTUPLE_LIVE;
+			}
 
 			/*
 			 * We don't really care whether xmax did commit, abort or
-			 * crash. We know that xmax did mark the tuple for update, but
+			 * crash. We know that xmax did lock the tuple, but
 			 * it did not and will never actually update it.
 			 */
 			tuple->t_infomask |= HEAP_XMAX_INVALID;
@@ -1098,6 +1173,13 @@ HeapTupleSatisfiesVacuum(HeapTupleHeader tuple, TransactionId OldestXmin,
 		return HEAPTUPLE_LIVE;
 	}
 
+	if (tuple->t_infomask & HEAP_XMAX_IS_MULTI)
+	{
+		/* MultiXacts are currently only allowed to lock tuples */
+		Assert(tuple->t_infomask & HEAP_IS_LOCKED);
+		return HEAPTUPLE_LIVE;
+	}
+
 	if (!(tuple->t_infomask & HEAP_XMAX_COMMITTED))
 	{
 		if (TransactionIdIsInProgress(HeapTupleHeaderGetXmax(tuple)))

src/bin/initdb/initdb.c

@@ -39,7 +39,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  * Portions taken from FreeBSD.
  *
- * $PostgreSQL: pgsql/src/bin/initdb/initdb.c,v 1.81 2005/04/12 19:29:24 tgl Exp $
+ * $PostgreSQL: pgsql/src/bin/initdb/initdb.c,v 1.82 2005/04/28 21:47:16 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -527,7 +527,7 @@ mkdir_p(char *path, mode_t omode)
 		{
 			/*
 			 * POSIX 1003.2: For each dir operand that does not name an
-			 * existing directory, effects equivalent to those cased by
+			 * existing directory, effects equivalent to those caused by
 			 * the following command shall occcur:
 			 *
 			 * mkdir -p -m $(umask -S),u+wx $(dirname dir) && mkdir [-m mode]
@@ -2124,6 +2124,8 @@ main(int argc, char *argv[])
 		"pg_xlog/archive_status",
 		"pg_clog",
 		"pg_subtrans",
+		"pg_multixact/members",
+		"pg_multixact/offsets",
 		"base",
 		"base/1",
 		"pg_tblspc"

src/bin/pg_controldata/pg_controldata.c

@@ -6,7 +6,7 @@
  * copyright (c) Oliver Elphick <olly@lfix.co.uk>, 2001;
  * licence: BSD
  *
- * $PostgreSQL: pgsql/src/bin/pg_controldata/pg_controldata.c,v 1.22 2005/03/29 03:01:32 tgl Exp $
+ * $PostgreSQL: pgsql/src/bin/pg_controldata/pg_controldata.c,v 1.23 2005/04/28 21:47:16 tgl Exp $
  */
 #include "postgres.h"
 
@@ -165,6 +165,7 @@ main(int argc, char *argv[])
 	printf(_("Latest checkpoint's TimeLineID:       %u\n"), ControlFile.checkPointCopy.ThisTimeLineID);
 	printf(_("Latest checkpoint's NextXID:          %u\n"), ControlFile.checkPointCopy.nextXid);
 	printf(_("Latest checkpoint's NextOID:          %u\n"), ControlFile.checkPointCopy.nextOid);
+	printf(_("Latest checkpoint's NextMultiXactId:  %u\n"), ControlFile.checkPointCopy.nextMulti);
 	printf(_("Time of latest checkpoint:            %s\n"), ckpttime_str);
 	printf(_("Database block size:                  %u\n"), ControlFile.blcksz);
 	printf(_("Blocks per segment of large relation: %u\n"), ControlFile.relseg_size);

src/bin/pg_resetxlog/pg_resetxlog.c

@@ -23,7 +23,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/bin/pg_resetxlog/pg_resetxlog.c,v 1.31 2005/04/13 18:54:56 tgl Exp $
+ * $PostgreSQL: pgsql/src/bin/pg_resetxlog/pg_resetxlog.c,v 1.32 2005/04/28 21:47:16 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -40,6 +40,7 @@
 #include <getopt.h>
 #endif
 
+#include "access/multixact.h"
 #include "access/xlog.h"
 #include "access/xlog_internal.h"
 #include "catalog/catversion.h"
@@ -75,6 +76,7 @@ main(int argc, char *argv[])
 	bool		noupdate = false;
 	TransactionId set_xid = 0;
 	Oid			set_oid = 0;
+	MultiXactId	set_mxid = 0;
 	uint32		minXlogTli = 0,
 				minXlogId = 0,
 				minXlogSeg = 0;
@@ -104,7 +106,7 @@ main(int argc, char *argv[])
 	}
 
 
-	while ((c = getopt(argc, argv, "fl:no:x:")) != -1)
+	while ((c = getopt(argc, argv, "fl:m:no:x:")) != -1)
 	{
 		switch (c)
 		{
@@ -146,6 +148,21 @@ main(int argc, char *argv[])
 				}
 				break;
 
+			case 'm':
+				set_mxid = strtoul(optarg, &endptr, 0);
+				if (endptr == optarg || *endptr != '\0')
+				{
+					fprintf(stderr, _("%s: invalid argument for option -m\n"), progname);
+					fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname);
+					exit(1);
+				}
+				if (set_mxid == 0)
+				{
+					fprintf(stderr, _("%s: multi transaction ID (-m) must not be 0\n"), progname);
+					exit(1);
+				}
+				break;
+
 			case 'l':
 				minXlogTli = strtoul(optarg, &endptr, 0);
 				if (endptr == optarg || *endptr != ',')
@@ -245,6 +262,9 @@ main(int argc, char *argv[])
 	if (set_oid != 0)
 		ControlFile.checkPointCopy.nextOid = set_oid;
 
+	if (set_mxid != 0)
+		ControlFile.checkPointCopy.nextMulti = set_mxid;
+
 	if (minXlogTli > ControlFile.checkPointCopy.ThisTimeLineID)
 		ControlFile.checkPointCopy.ThisTimeLineID = minXlogTli;
 
@@ -405,6 +425,7 @@ GuessControlValues(void)
 	ControlFile.checkPointCopy.ThisTimeLineID = 1;
 	ControlFile.checkPointCopy.nextXid = (TransactionId) 514;	/* XXX */
 	ControlFile.checkPointCopy.nextOid = FirstBootstrapObjectId;
+	ControlFile.checkPointCopy.nextMulti = FirstMultiXactId;
 	ControlFile.checkPointCopy.time = time(NULL);
 
 	ControlFile.state = DB_SHUTDOWNED;
@@ -478,6 +499,7 @@ PrintControlValues(bool guessed)
 	printf(_("Latest checkpoint's TimeLineID:       %u\n"), ControlFile.checkPointCopy.ThisTimeLineID);
 	printf(_("Latest checkpoint's NextXID:          %u\n"), ControlFile.checkPointCopy.nextXid);
 	printf(_("Latest checkpoint's NextOID:          %u\n"), ControlFile.checkPointCopy.nextOid);
+	printf(_("Latest checkpoint's NextMultiXactId:  %u\n"), ControlFile.checkPointCopy.nextMulti);
 	printf(_("Database block size:                  %u\n"), ControlFile.blcksz);
 	printf(_("Blocks per segment of large relation: %u\n"), ControlFile.relseg_size);
 	printf(_("Maximum length of identifiers:        %u\n"), ControlFile.nameDataLen);
@@ -753,6 +775,7 @@ usage(void)
 	printf(_("  -n              no update, just show extracted control values (for testing)\n"));
 	printf(_("  -o OID          set next OID\n"));
 	printf(_("  -x XID          set next transaction ID\n"));
+	printf(_("  -m multiXID     set next multi transaction ID\n"));
 	printf(_("  --help          show this help, then exit\n"));
 	printf(_("  --version       output version information, then exit\n"));
 	printf(_("\nReport bugs to <pgsql-bugs@postgresql.org>.\n"));

src/include/access/heapam.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/access/heapam.h,v 1.99 2005/04/14 20:03:27 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/access/heapam.h,v 1.100 2005/04/28 21:47:16 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -123,6 +123,12 @@ extern Datum fastgetattr(HeapTuple tup, int attnum, TupleDesc tupleDesc,
 
 /* heapam.c */
 
+typedef enum
+{
+	LockTupleShared,
+	LockTupleExclusive
+} LockTupleMode;
+
 extern Relation relation_open(Oid relationId, LOCKMODE lockmode);
 extern Relation conditional_relation_open(Oid relationId, LOCKMODE lockmode, bool nowait);
 extern Relation relation_openrv(const RangeVar *relation, LOCKMODE lockmode);
@@ -155,8 +161,8 @@ extern HTSU_Result heap_delete(Relation relation, ItemPointer tid, ItemPointer c
 			CommandId cid, Snapshot crosscheck, bool wait);
 extern HTSU_Result heap_update(Relation relation, ItemPointer otid, HeapTuple tup,
 		ItemPointer ctid, CommandId cid, Snapshot crosscheck, bool wait);
-extern HTSU_Result heap_mark4update(Relation relation, HeapTuple tup,
-				 Buffer *userbuf, CommandId cid);
+extern HTSU_Result heap_lock_tuple(Relation relation, HeapTuple tup,
+				 Buffer *userbuf, CommandId cid, LockTupleMode mode);
 
 extern Oid	simple_heap_insert(Relation relation, HeapTuple tup);
 extern void simple_heap_delete(Relation relation, ItemPointer tid);

src/include/access/htup.h

@@ -1,4 +1,4 @@
- /*-------------------------------------------------------------------------
+/*-------------------------------------------------------------------------
  *
  * htup.h
  *	  POSTGRES heap tuple definitions.
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/access/htup.h,v 1.73 2005/03/28 01:50:34 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/access/htup.h,v 1.74 2005/04/28 21:47:17 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -93,11 +93,11 @@ typedef struct HeapTupleFields
 {
 	TransactionId t_xmin;		/* inserting xact ID */
 	CommandId	t_cmin;			/* inserting command ID */
-	TransactionId t_xmax;		/* deleting xact ID */
+	TransactionId t_xmax;		/* deleting or locking xact ID */
 
 	union
 	{
-		CommandId	t_cmax;		/* deleting command ID */
+		CommandId	t_cmax;		/* deleting or locking command ID */
 		TransactionId t_xvac;	/* VACUUM FULL xact ID */
 	}			t_field4;
 } HeapTupleFields;
@@ -152,12 +152,16 @@ typedef HeapTupleHeaderData *HeapTupleHeader;
 										 * attribute(s) */
 #define HEAP_HASEXTENDED		0x000C	/* the two above combined */
 #define HEAP_HASOID				0x0010	/* has an object-id field */
-/* 0x0020, 0x0040 and 0x0080 are unused */
+/* 0x0020 is presently unused */
+#define HEAP_XMAX_EXCL_LOCK		0x0040  /* xmax is exclusive locker */
+#define HEAP_XMAX_SHARED_LOCK	0x0080  /* xmax is shared locker */
+/* if either LOCK bit is set, xmax hasn't deleted the tuple, only locked it */
+#define HEAP_IS_LOCKED	(HEAP_XMAX_EXCL_LOCK | HEAP_XMAX_SHARED_LOCK)
 #define HEAP_XMIN_COMMITTED		0x0100	/* t_xmin committed */
 #define HEAP_XMIN_INVALID		0x0200	/* t_xmin invalid/aborted */
 #define HEAP_XMAX_COMMITTED		0x0400	/* t_xmax committed */
 #define HEAP_XMAX_INVALID		0x0800	/* t_xmax invalid/aborted */
-#define HEAP_MARKED_FOR_UPDATE	0x1000	/* marked for UPDATE */
+#define HEAP_XMAX_IS_MULTI		0x1000	/* t_xmax is a MultiXactId */
 #define HEAP_UPDATED			0x2000	/* this is UPDATEd version of row */
 #define HEAP_MOVED_OFF			0x4000	/* moved to another place by
 										 * VACUUM FULL */
@@ -406,7 +410,8 @@ typedef HeapTupleData *HeapTuple;
 #define XLOG_HEAP_MOVE		0x30
 #define XLOG_HEAP_CLEAN		0x40
 #define XLOG_HEAP_NEWPAGE	0x50
-/* opcodes 0x60, 0x70 still free */
+#define XLOG_HEAP_LOCK		0x60
+/* opcode 0x70 still free */
 #define XLOG_HEAP_OPMASK	0x70
 /*
  * When we insert 1st item on new page in INSERT/UPDATE
@@ -496,4 +501,13 @@ typedef struct xl_heap_newpage
 
 #define SizeOfHeapNewpage	(offsetof(xl_heap_newpage, blkno) + sizeof(BlockNumber))
 
+/* This is what we need to know about lock */
+typedef struct xl_heap_lock
+{
+	xl_heaptid	target;			/* locked tuple id */
+	bool		shared_lock;	/* shared or exclusive row lock? */
+} xl_heap_lock;
+
+#define SizeOfHeapLock	(offsetof(xl_heap_lock, shared_lock) + sizeof(bool))
+
 #endif   /* HTUP_H */

src/include/access/multixact.h

@@ -0,0 +1,37 @@
+/*
+ * multixact.h
+ *
+ * PostgreSQL multi-transaction-log manager
+ *
+ * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * $PostgreSQL: pgsql/src/include/access/multixact.h,v 1.1 2005/04/28 21:47:17 tgl Exp $
+ */
+#ifndef MULTIXACT_H
+#define MULTIXACT_H
+
+#define InvalidMultiXactId	((MultiXactId) 0)
+#define FirstMultiXactId	((MultiXactId) 1)
+
+#define MultiXactIdIsValid(multi) ((multi) != InvalidMultiXactId)
+
+extern void MultiXactIdWait(MultiXactId multi);
+extern MultiXactId MultiXactIdExpand(MultiXactId multi, bool isMulti,
+									 TransactionId xid);
+extern bool MultiXactIdIsRunning(MultiXactId multi);
+extern void MultiXactIdSetOldestMember(void);
+
+extern void AtEOXact_MultiXact(void);
+
+extern int	MultiXactShmemSize(void);
+extern void MultiXactShmemInit(void);
+extern void BootStrapMultiXact(void);
+extern void StartupMultiXact(void);
+extern void ShutdownMultiXact(void);
+extern MultiXactId MultiXactGetCheckptMulti(bool is_shutdown);
+extern void CheckPointMultiXact(void);
+extern void MultiXactSetNextMXact(MultiXactId nextMulti);
+extern void MultiXactAdvanceNextMXact(MultiXactId minMulti);
+
+#endif   /* MULTIXACT_H */

src/include/access/xlog.h

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/access/xlog.h,v 1.59 2004/12/31 22:03:21 pgsql Exp $
+ * $PostgreSQL: pgsql/src/include/access/xlog.h,v 1.60 2005/04/28 21:47:17 tgl Exp $
  */
 #ifndef XLOG_H
 #define XLOG_H
@@ -133,6 +133,7 @@ extern void ShutdownXLOG(int code, Datum arg);
 extern void InitXLOGAccess(void);
 extern void CreateCheckPoint(bool shutdown, bool force);
 extern void XLogPutNextOid(Oid nextOid);
+extern void XLogPutNextMultiXactId(MultiXactId multi);
 extern XLogRecPtr GetRedoRecPtr(void);
 
 #endif   /* XLOG_H */

src/include/c.h

@@ -12,7 +12,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/c.h,v 1.181 2005/03/29 00:17:16 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/c.h,v 1.182 2005/04/28 21:47:17 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -365,7 +365,8 @@ typedef float float4;
 typedef double float8;
 
 /*
- * Oid, RegProcedure, TransactionId, SubTransactionId, CommandId, AclId
+ * Oid, RegProcedure, TransactionId, SubTransactionId, MultiXactId,
+ * CommandId, AclId
  */
 
 /* typedef Oid is in postgres_ext.h */
@@ -384,6 +385,9 @@ typedef uint32 SubTransactionId;
 #define InvalidSubTransactionId		((SubTransactionId) 0)
 #define TopSubTransactionId			((SubTransactionId) 1)
 
+/* MultiXactId must be equivalent to TransactionId, to fit in t_xmax */
+typedef TransactionId MultiXactId;
+
 typedef uint32 CommandId;
 
 #define FirstCommandId	((CommandId) 0)

src/include/catalog/pg_control.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_control.h,v 1.20 2005/03/29 03:01:32 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_control.h,v 1.21 2005/04/28 21:47:17 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -22,7 +22,7 @@
 
 
 /* Version identifier for this pg_control format */
-#define PG_CONTROL_VERSION	74
+#define PG_CONTROL_VERSION	81
 
 /*
  * Body of CheckPoint XLOG records.  This is declared here because we keep
@@ -39,12 +39,14 @@ typedef struct CheckPoint
 	TimeLineID	ThisTimeLineID; /* current TLI */
 	TransactionId nextXid;		/* next free XID */
 	Oid			nextOid;		/* next free OID */
+	MultiXactId	nextMulti;		/* next free MultiXactId */
 	time_t		time;			/* time stamp of checkpoint */
 } CheckPoint;
 
 /* XLOG info values for XLOG rmgr */
 #define XLOG_CHECKPOINT_SHUTDOWN		0x00
 #define XLOG_CHECKPOINT_ONLINE			0x10
+#define XLOG_NEXTMULTI					0x20
 #define XLOG_NEXTOID					0x30
 
 

src/include/nodes/execnodes.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/nodes/execnodes.h,v 1.129 2005/04/25 01:30:14 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/nodes/execnodes.h,v 1.130 2005/04/28 21:47:17 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -318,6 +318,7 @@ typedef struct EState
 	uint32		es_processed;	/* # of tuples processed */
 	Oid			es_lastoid;		/* last oid processed (by INSERT) */
 	List	   *es_rowMark;		/* not good place, but there is no other */
+	bool		es_forUpdate;	/* was it FOR UPDATE or FOR SHARE */
 
 	bool		es_instrument;	/* true requests runtime instrumentation */
 	bool		es_select_into; /* true if doing SELECT INTO */

src/include/nodes/parsenodes.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/nodes/parsenodes.h,v 1.277 2005/04/07 01:51:40 neilc Exp $
+ * $PostgreSQL: pgsql/src/include/nodes/parsenodes.h,v 1.278 2005/04/28 21:47:17 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -50,7 +50,7 @@ typedef uint32 AclMode;			/* a bitmask of privilege bits */
 #define N_ACL_RIGHTS	11		/* 1 plus the last 1<<x */
 #define ACL_ALL_RIGHTS	(-1)	/* all-privileges marker in GRANT list */
 #define ACL_NO_RIGHTS	0
-/* Currently, SELECT ... FOR UPDATE requires UPDATE privileges */
+/* Currently, SELECT ... FOR UPDATE/FOR SHARE requires UPDATE privileges */
 #define ACL_SELECT_FOR_UPDATE	ACL_UPDATE
 
 
@@ -91,7 +91,10 @@ typedef struct Query
 								 * clauses) */
 
 	List	   *rowMarks;		/* integer list of RT indexes of relations
-								 * that are selected FOR UPDATE */
+								 * that are selected FOR UPDATE/SHARE */
+
+	bool		forUpdate;		/* true if rowMarks are FOR UPDATE,
+								 * false if they are FOR SHARE */
 
 	List	   *targetList;		/* target list (of TargetEntry) */
 
@@ -688,7 +691,8 @@ typedef struct SelectStmt
 	List	   *sortClause;		/* sort clause (a list of SortBy's) */
 	Node	   *limitOffset;	/* # of result tuples to skip */
 	Node	   *limitCount;		/* # of result tuples to return */
-	List	   *forUpdate;		/* FOR UPDATE clause */
+	List	   *lockedRels;		/* FOR UPDATE or FOR SHARE relations */
+	bool		forUpdate;		/* true = FOR UPDATE, false = FOR SHARE */
 
 	/*
 	 * These fields are used only in upper-level SelectStmts.

src/include/parser/analyze.h

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/parser/analyze.h,v 1.29 2004/12/31 22:03:38 pgsql Exp $
+ * $PostgreSQL: pgsql/src/include/parser/analyze.h,v 1.30 2005/04/28 21:47:18 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -21,6 +21,6 @@ extern List *parse_analyze_varparams(Node *parseTree, Oid **paramTypes,
 						int *numParams);
 extern List *parse_sub_analyze(Node *parseTree, ParseState *parentParseState);
 extern List *analyzeCreateSchemaStmt(CreateSchemaStmt *stmt);
-extern void CheckSelectForUpdate(Query *qry);
+extern void CheckSelectLocking(Query *qry, bool forUpdate);
 
 #endif   /* ANALYZE_H */

src/include/parser/parse_node.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/parser/parse_node.h,v 1.42 2004/12/31 22:03:38 pgsql Exp $
+ * $PostgreSQL: pgsql/src/include/parser/parse_node.h,v 1.43 2005/04/28 21:47:18 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,7 +53,7 @@ typedef struct ParseState
 	Oid		   *p_paramtypes;	/* OIDs of types for $n parameter symbols */
 	int			p_numparams;	/* allocated size of p_paramtypes[] */
 	int			p_next_resno;	/* next targetlist resno to assign */
-	List	   *p_forUpdate;	/* FOR UPDATE clause, if any (see gram.y) */
+	List	   *p_lockedRels;	/* FOR UPDATE/SHARE, if any (see gram.y) */
 	Node	   *p_value_substitute;		/* what to replace VALUE with, if
 										 * any */
 	bool		p_variableparams;

src/include/storage/bufpage.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/storage/bufpage.h,v 1.64 2005/03/22 06:17:03 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/storage/bufpage.h,v 1.65 2005/04/28 21:47:18 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -135,8 +135,9 @@ typedef PageHeaderData *PageHeader;
  * Page layout version number 0 is for pre-7.3 Postgres releases.
  * Releases 7.3 and 7.4 use 1, denoting a new HeapTupleHeader layout.
  * Release 8.0 changed the HeapTupleHeader layout again.
+ * Release 8.1 redefined HeapTupleHeader infomask bits.
  */
-#define PG_PAGE_LAYOUT_VERSION		2
+#define PG_PAGE_LAYOUT_VERSION		3
 
 
 /* ----------------------------------------------------------------

src/include/storage/lmgr.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/storage/lmgr.h,v 1.45 2004/12/31 22:03:42 pgsql Exp $
+ * $PostgreSQL: pgsql/src/include/storage/lmgr.h,v 1.46 2005/04/28 21:47:18 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -23,7 +23,7 @@
 #define NoLock					0
 
 #define AccessShareLock			1		/* SELECT */
-#define RowShareLock			2		/* SELECT FOR UPDATE */
+#define RowShareLock			2		/* SELECT FOR UPDATE/FOR SHARE */
 #define RowExclusiveLock		3		/* INSERT, UPDATE, DELETE */
 #define ShareUpdateExclusiveLock 4		/* VACUUM (non-FULL) */
 #define ShareLock				5		/* CREATE INDEX */

src/include/storage/lwlock.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/storage/lwlock.h,v 1.17 2005/03/04 20:21:07 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/storage/lwlock.h,v 1.18 2005/04/28 21:47:18 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -40,6 +40,9 @@ typedef enum LWLockId
 	CheckpointStartLock,
 	CLogControlLock,
 	SubtransControlLock,
+	MultiXactGenLock,
+	MultiXactOffsetControlLock,
+	MultiXactMemberControlLock,
 	RelCacheInitLock,
 	BgWriterCommLock,