agora inbox for pgsql-hackers@postgresql.org  
help / color / mirror / Atom feed
[PATCH v1] popcount
4+ messages / 2 participants
[nested] [flat]

* [PATCH v1] popcount
@ 2020-12-30 10:51  David Fetter <david@fetter.org>
  0 siblings, 0 replies; 4+ messages in thread

From: David Fetter @ 2020-12-30 10:51 UTC (permalink / raw)


Now it's accessible to SQL for the BIT VARYING and BYTEA types.

diff --git doc/src/sgml/func.sgml doc/src/sgml/func.sgml
index 5021ac1ca9..439a3a4a06 100644
--- doc/src/sgml/func.sgml
+++ doc/src/sgml/func.sgml
@@ -4069,6 +4069,23 @@ SELECT format('Testing %3$s, %2$s, %s', 'one', 'two', 'three');
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>popcount</primary>
+        </indexterm>
+        <function>popcount</function> ( <parameter>bytes</parameter> <type>bytea</type> )
+        <returnvalue>integer</returnvalue>
+       </para>
+       <para>
+        Counts the number of bits set in a binary string.
+       </para>
+       <para>
+        <literal>popcount('\xdeadbeef'::bytea)</literal>
+        <returnvalue>24</returnvalue>
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
@@ -4830,6 +4847,24 @@ SELECT format('Testing %3$s, %2$s, %s', 'one', 'two', 'three');
         <returnvalue>101010001010101010</returnvalue>
        </para></entry>
       </row>
+
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>popcount</primary>
+        </indexterm>
+        <function>popcount</function> ( <parameter>bits</parameter> <type>bit</type> )
+        <returnvalue>int4</returnvalue>
+       </para>
+       <para>
+        Counts the bits set in a bit string.
+       </para>
+       <para>
+        <literal>popcount(B'101010101010101010')</literal>
+        <returnvalue>9</returnvalue>
+       </para></entry>
+      </row>
+
      </tbody>
     </tgroup>
    </table>
diff --git src/include/catalog/pg_proc.dat src/include/catalog/pg_proc.dat
index 139f4a08bd..0e6d0636fa 100644
--- src/include/catalog/pg_proc.dat
+++ src/include/catalog/pg_proc.dat
@@ -1446,6 +1446,9 @@
 { oid => '752', descr => 'substitute portion of string',
   proname => 'overlay', prorettype => 'bytea',
   proargtypes => 'bytea bytea int4', prosrc => 'byteaoverlay_no_len' },
+{ oid => '8436', descr => 'count set bits',
+  proname => 'popcount', prorettype => 'int4', proargtypes => 'bytea',
+  prosrc => 'byteapopcount'},
 
 { oid => '725',
   proname => 'dist_pl', prorettype => 'float8', proargtypes => 'point line',
@@ -3865,6 +3868,9 @@
 { oid => '3033', descr => 'set bit',
   proname => 'set_bit', prorettype => 'bit', proargtypes => 'bit int4 int4',
   prosrc => 'bitsetbit' },
+{ oid => '8435', descr => 'count set bits',
+  proname => 'popcount', prorettype => 'int4', proargtypes => 'bit',
+  prosrc => 'bitpopcount'},
 
 # for macaddr type support
 { oid => '436', descr => 'I/O',
diff --git src/backend/utils/adt/varbit.c src/backend/utils/adt/varbit.c
index 3c03459f51..e92d1a7f8f 100644
--- src/backend/utils/adt/varbit.c
+++ src/backend/utils/adt/varbit.c
@@ -29,6 +29,8 @@
  *-------------------------------------------------------------------------
  */
 
+#include <math.h>
+
 #include "postgres.h"
 
 #include "access/htup_details.h"
@@ -36,6 +38,7 @@
 #include "libpq/pqformat.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/supportnodes.h"
+#include "port/pg_bitutils.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/varbit.h"
@@ -1872,3 +1875,24 @@ bitgetbit(PG_FUNCTION_ARGS)
 	else
 		PG_RETURN_INT32(0);
 }
+
+/*
+ * bitpopcount
+ *
+ * Returns the number of bits set in a bit array.
+ *
+ */
+Datum
+bitpopcount(PG_FUNCTION_ARGS)
+{
+	VarBit		*arg1 = PG_GETARG_VARBIT_P(0);
+	bits8		*p;
+	int			len, popcount;
+
+	len = ceil(VARBITLEN(arg1) / (float4)BITS_PER_BYTE);
+	p = VARBITS(arg1);
+
+	popcount = (int)pg_popcount((const char *)p, len);
+
+	PG_RETURN_INT32(popcount);
+}
diff --git src/backend/utils/adt/varlena.c src/backend/utils/adt/varlena.c
index 9300d19e0c..9e788babd3 100644
--- src/backend/utils/adt/varlena.c
+++ src/backend/utils/adt/varlena.c
@@ -3415,6 +3415,21 @@ bytea_overlay(bytea *t1, bytea *t2, int sp, int sl)
 	return result;
 }
 
+/*
+ * popcount
+ */
+Datum
+byteapopcount(PG_FUNCTION_ARGS)
+{
+	bytea	*t1 = PG_GETARG_BYTEA_PP(0);
+	int		len, result;
+
+	len = VARSIZE_ANY_EXHDR(t1);
+	result = pg_popcount(VARDATA_ANY(t1), len);
+
+	PG_RETURN_INT32(result);
+}
+
 /*
  * byteapos -
  *	  Return the position of the specified substring.
diff --git src/test/regress/expected/bit.out src/test/regress/expected/bit.out
index a1fab7ebcb..c91ad3d0d5 100644
--- src/test/regress/expected/bit.out
+++ src/test/regress/expected/bit.out
@@ -681,6 +681,19 @@ SELECT overlay(B'0101011100' placing '001' from 20);
  0101011100001
 (1 row)
 
+-- Popcount
+SELECT popcount(B'0101011100'::bit(10));
+ popcount 
+----------
+        5
+(1 row)
+
+SELECT popcount(B'1111111111'::bit(10));
+ popcount 
+----------
+       10
+(1 row)
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git src/test/regress/expected/strings.out src/test/regress/expected/strings.out
index 298b6c48c2..9780639038 100644
--- src/test/regress/expected/strings.out
+++ src/test/regress/expected/strings.out
@@ -2126,3 +2126,10 @@ SELECT encode(overlay(E'Th\\000omas'::bytea placing E'\\002\\003'::bytea from 5
  Th\000o\x02\x03
 (1 row)
 
+SET bytea_output TO hex;
+SELECT popcount(E'\\xdeadbeef'::bytea);
+ popcount 
+----------
+       24
+(1 row)
+
diff --git src/test/regress/sql/bit.sql src/test/regress/sql/bit.sql
index 7681d4ab4d..3cd9fb65d3 100644
--- src/test/regress/sql/bit.sql
+++ src/test/regress/sql/bit.sql
@@ -207,6 +207,10 @@ SELECT overlay(B'0101011100' placing '101' from 6);
 SELECT overlay(B'0101011100' placing '001' from 11);
 SELECT overlay(B'0101011100' placing '001' from 20);
 
+-- Popcount
+SELECT popcount(B'0101011100'::bit(10));
+SELECT popcount(B'1111111111'::bit(10));
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git src/test/regress/sql/strings.sql src/test/regress/sql/strings.sql
index ad5221ab6b..a35e993ab0 100644
--- src/test/regress/sql/strings.sql
+++ src/test/regress/sql/strings.sql
@@ -717,3 +717,6 @@ SELECT btrim(E'\\000trim\\000'::bytea, ''::bytea);
 SELECT encode(overlay(E'Th\\000omas'::bytea placing E'Th\\001omas'::bytea from 2),'escape');
 SELECT encode(overlay(E'Th\\000omas'::bytea placing E'\\002\\003'::bytea from 8),'escape');
 SELECT encode(overlay(E'Th\\000omas'::bytea placing E'\\002\\003'::bytea from 5 for 3),'escape');
+
+SET bytea_output TO hex;
+SELECT popcount(E'\\xdeadbeef'::bytea);


^ permalink  raw  reply  [nested|flat] 4+ messages in thread

* [PATCH v5] popcount
@ 2020-12-30 10:51  David Fetter <david@fetter.org>
  0 siblings, 0 replies; 4+ messages in thread

From: David Fetter @ 2020-12-30 10:51 UTC (permalink / raw)


Now it's accessible to SQL for the BIT VARYING and BYTEA types.

diff --git doc/src/sgml/func.sgml doc/src/sgml/func.sgml
index 68fe6a95b4..066431fd3c 100644
--- doc/src/sgml/func.sgml
+++ doc/src/sgml/func.sgml
@@ -4030,6 +4030,23 @@ SELECT format('Testing %3$s, %2$s, %s', 'one', 'two', 'three');
       </para></entry>
      </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>bit_count</primary>
+        </indexterm>
+        <function>bit_count</function> ( <parameter>bytes</parameter> <type>bytea</type> )
+        <returnvalue>bigint</returnvalue>
+       </para>
+       <para>
+        Counts the number of bits set in a binary string.
+       </para>
+       <para>
+        <literal>bit_count('\xdeadbeef'::bytea)</literal>
+        <returnvalue>24</returnvalue>
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
@@ -4830,6 +4847,23 @@ SELECT format('Testing %3$s, %2$s, %s', 'one', 'two', 'three');
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>bit_count</primary>
+        </indexterm>
+        <function>bit_count</function> ( <parameter>bits</parameter> <type>bit</type> )
+        <returnvalue>bigint</returnvalue>
+       </para>
+       <para>
+        Counts the bits set in a bit string.
+       </para>
+       <para>
+        <literal>bit_count(B'101010101010101010')</literal>
+        <returnvalue>9</returnvalue>
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
@@ -4869,6 +4903,7 @@ SELECT format('Testing %3$s, %2$s, %s', 'one', 'two', 'three');
         <returnvalue>101010001010101010</returnvalue>
        </para></entry>
       </row>
+
      </tbody>
     </tgroup>
    </table>
diff --git src/include/catalog/pg_proc.dat src/include/catalog/pg_proc.dat
index e259531f60..feb00eccf9 100644
--- src/include/catalog/pg_proc.dat
+++ src/include/catalog/pg_proc.dat
@@ -1446,6 +1446,9 @@
 { oid => '752', descr => 'substitute portion of string',
   proname => 'overlay', prorettype => 'bytea',
   proargtypes => 'bytea bytea int4', prosrc => 'byteaoverlay_no_len' },
+{ oid => '8436', descr => 'count set bits',
+  proname => 'bit_count', prorettype => 'int8', proargtypes => 'bytea',
+  prosrc => 'byteapopcount'},
 
 { oid => '725',
   proname => 'dist_pl', prorettype => 'float8', proargtypes => 'point line',
@@ -3876,6 +3879,9 @@
 { oid => '3033', descr => 'set bit',
   proname => 'set_bit', prorettype => 'bit', proargtypes => 'bit int4 int4',
   prosrc => 'bitsetbit' },
+{ oid => '8435', descr => 'count set bits',
+  proname => 'bit_count', prorettype => 'int8', proargtypes => 'bit',
+  prosrc => 'bitpopcount'},
 
 # for macaddr type support
 { oid => '436', descr => 'I/O',
diff --git src/backend/utils/adt/varbit.c src/backend/utils/adt/varbit.c
index 2235866244..c9c6c73422 100644
--- src/backend/utils/adt/varbit.c
+++ src/backend/utils/adt/varbit.c
@@ -36,6 +36,7 @@
 #include "libpq/pqformat.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/supportnodes.h"
+#include "port/pg_bitutils.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/varbit.h"
@@ -1878,3 +1879,30 @@ bitgetbit(PG_FUNCTION_ARGS)
 	else
 		PG_RETURN_INT32(0);
 }
+
+/*
+ * bitpopcount
+ *
+ * Returns the number of bits set in a bit string.
+ *
+ */
+Datum
+bitpopcount(PG_FUNCTION_ARGS)
+{
+	/* There's really no chance of an overflow here because
+	 * to get to INT64_MAX set bits, an object would have to be
+	 * an exbibyte long, exceeding what PostgreSQL can currently
+	 * store by a factor of 2^28
+	 */
+	int64		popcount;
+	VarBit		*arg1 = PG_GETARG_VARBIT_P(0);
+	bits8		*p;
+	int			len;
+
+	p = VARBITS(arg1);
+	len = (VARBITLEN(arg1) + BITS_PER_BYTE - 1) / BITS_PER_BYTE;
+
+	popcount = pg_popcount((char *)p, len);
+
+	PG_RETURN_INT64(popcount);
+}
diff --git src/backend/utils/adt/varlena.c src/backend/utils/adt/varlena.c
index 0bc345aa4d..95091887a9 100644
--- src/backend/utils/adt/varlena.c
+++ src/backend/utils/adt/varlena.c
@@ -3440,6 +3440,22 @@ bytea_overlay(bytea *t1, bytea *t2, int sp, int sl)
 	return result;
 }
 
+/*
+ * popcount
+ */
+Datum
+byteapopcount(PG_FUNCTION_ARGS)
+{
+	bytea	*t1 = PG_GETARG_BYTEA_PP(0);
+	int		len;
+	int64	result;
+
+	len = VARSIZE_ANY_EXHDR(t1);
+	result = pg_popcount(VARDATA_ANY(t1), len);
+
+	PG_RETURN_INT64(result);
+}
+
 /*
  * byteapos -
  *	  Return the position of the specified substring.
diff --git src/test/regress/expected/bit.out src/test/regress/expected/bit.out
index a7f95b846d..9b6b3d0c4f 100644
--- src/test/regress/expected/bit.out
+++ src/test/regress/expected/bit.out
@@ -710,6 +710,19 @@ SELECT overlay(B'0101011100' placing '001' from 20);
  0101011100001
 (1 row)
 
+-- Popcount
+SELECT bit_count(B'0101011100'::bit(10));
+ bit_count 
+-----------
+         5
+(1 row)
+
+SELECT bit_count(B'1111111111'::bit(10));
+ bit_count 
+-----------
+        10
+(1 row)
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git src/test/regress/expected/strings.out src/test/regress/expected/strings.out
index fb4573d85f..e8c6a99e9d 100644
--- src/test/regress/expected/strings.out
+++ src/test/regress/expected/strings.out
@@ -2227,3 +2227,10 @@ SELECT encode(overlay(E'Th\\000omas'::bytea placing E'\\002\\003'::bytea from 5
  Th\000o\x02\x03
 (1 row)
 
+SET bytea_output TO hex;
+SELECT bit_count(E'\\xdeadbeef'::bytea);
+ bit_count 
+-----------
+        24
+(1 row)
+
diff --git src/test/regress/sql/bit.sql src/test/regress/sql/bit.sql
index ea01742c4a..271aa5ea3c 100644
--- src/test/regress/sql/bit.sql
+++ src/test/regress/sql/bit.sql
@@ -215,6 +215,10 @@ SELECT overlay(B'0101011100' placing '101' from 6);
 SELECT overlay(B'0101011100' placing '001' from 11);
 SELECT overlay(B'0101011100' placing '001' from 20);
 
+-- Popcount
+SELECT bit_count(B'0101011100'::bit(10));
+SELECT bit_count(B'1111111111'::bit(10));
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git src/test/regress/sql/strings.sql src/test/regress/sql/strings.sql
index 57a48c9d0b..3fb2d66a9f 100644
--- src/test/regress/sql/strings.sql
+++ src/test/regress/sql/strings.sql
@@ -742,3 +742,6 @@ SELECT btrim(E'\\000trim\\000'::bytea, ''::bytea);
 SELECT encode(overlay(E'Th\\000omas'::bytea placing E'Th\\001omas'::bytea from 2),'escape');
 SELECT encode(overlay(E'Th\\000omas'::bytea placing E'\\002\\003'::bytea from 8),'escape');
 SELECT encode(overlay(E'Th\\000omas'::bytea placing E'\\002\\003'::bytea from 5 for 3),'escape');
+
+SET bytea_output TO hex;
+SELECT bit_count(E'\\xdeadbeef'::bytea);


^ permalink  raw  reply  [nested|flat] 4+ messages in thread

* [PATCH v2] popcount
@ 2020-12-30 10:51  David Fetter <david@fetter.org>
  0 siblings, 0 replies; 4+ messages in thread

From: David Fetter @ 2020-12-30 10:51 UTC (permalink / raw)


Now it's accessible to SQL for the BIT VARYING and BYTEA types.

diff --git doc/src/sgml/func.sgml doc/src/sgml/func.sgml
index 5021ac1ca9..439a3a4a06 100644
--- doc/src/sgml/func.sgml
+++ doc/src/sgml/func.sgml
@@ -4069,6 +4069,23 @@ SELECT format('Testing %3$s, %2$s, %s', 'one', 'two', 'three');
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>popcount</primary>
+        </indexterm>
+        <function>popcount</function> ( <parameter>bytes</parameter> <type>bytea</type> )
+        <returnvalue>integer</returnvalue>
+       </para>
+       <para>
+        Counts the number of bits set in a binary string.
+       </para>
+       <para>
+        <literal>popcount('\xdeadbeef'::bytea)</literal>
+        <returnvalue>24</returnvalue>
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
@@ -4830,6 +4847,24 @@ SELECT format('Testing %3$s, %2$s, %s', 'one', 'two', 'three');
         <returnvalue>101010001010101010</returnvalue>
        </para></entry>
       </row>
+
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>popcount</primary>
+        </indexterm>
+        <function>popcount</function> ( <parameter>bits</parameter> <type>bit</type> )
+        <returnvalue>int4</returnvalue>
+       </para>
+       <para>
+        Counts the bits set in a bit string.
+       </para>
+       <para>
+        <literal>popcount(B'101010101010101010')</literal>
+        <returnvalue>9</returnvalue>
+       </para></entry>
+      </row>
+
      </tbody>
     </tgroup>
    </table>
diff --git src/include/catalog/pg_proc.dat src/include/catalog/pg_proc.dat
index 139f4a08bd..82e3d50114 100644
--- src/include/catalog/pg_proc.dat
+++ src/include/catalog/pg_proc.dat
@@ -1446,6 +1446,9 @@
 { oid => '752', descr => 'substitute portion of string',
   proname => 'overlay', prorettype => 'bytea',
   proargtypes => 'bytea bytea int4', prosrc => 'byteaoverlay_no_len' },
+{ oid => '8436', descr => 'count set bits',
+  proname => 'popcount', prorettype => 'int8', proargtypes => 'bytea',
+  prosrc => 'byteapopcount'},
 
 { oid => '725',
   proname => 'dist_pl', prorettype => 'float8', proargtypes => 'point line',
@@ -3865,6 +3868,9 @@
 { oid => '3033', descr => 'set bit',
   proname => 'set_bit', prorettype => 'bit', proargtypes => 'bit int4 int4',
   prosrc => 'bitsetbit' },
+{ oid => '8435', descr => 'count set bits',
+  proname => 'popcount', prorettype => 'int8', proargtypes => 'bit',
+  prosrc => 'bitpopcount'},
 
 # for macaddr type support
 { oid => '436', descr => 'I/O',
diff --git src/backend/utils/adt/varbit.c src/backend/utils/adt/varbit.c
index 3c03459f51..a71c2b6bf4 100644
--- src/backend/utils/adt/varbit.c
+++ src/backend/utils/adt/varbit.c
@@ -36,6 +36,7 @@
 #include "libpq/pqformat.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/supportnodes.h"
+#include "port/pg_bitutils.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/varbit.h"
@@ -1872,3 +1873,29 @@ bitgetbit(PG_FUNCTION_ARGS)
 	else
 		PG_RETURN_INT32(0);
 }
+
+/*
+ * bitpopcount
+ *
+ * Returns the number of bits set in a bit array.
+ *
+ */
+Datum
+bitpopcount(PG_FUNCTION_ARGS)
+{
+	VarBit		*arg1 = PG_GETARG_VARBIT_P(0);
+	bits8		*p;
+	int			len;
+	int8		popcount;
+
+	/*
+	 * ceil(VARBITLEN(ARG1)/BITS_PER_BYTE)
+	 * done to minimize branches and instructions.
+	 */
+	len = (VARBITLEN(arg1) + BITS_PER_BYTE + 1) / BITS_PER_BYTE;
+	p = VARBITS(arg1);
+
+	popcount = pg_popcount((const char *)p, len);
+
+	PG_RETURN_INT64(popcount);
+}
diff --git src/backend/utils/adt/varlena.c src/backend/utils/adt/varlena.c
index 9300d19e0c..9c5e5b5592 100644
--- src/backend/utils/adt/varlena.c
+++ src/backend/utils/adt/varlena.c
@@ -3415,6 +3415,22 @@ bytea_overlay(bytea *t1, bytea *t2, int sp, int sl)
 	return result;
 }
 
+/*
+ * popcount
+ */
+Datum
+byteapopcount(PG_FUNCTION_ARGS)
+{
+	bytea	*t1 = PG_GETARG_BYTEA_PP(0);
+	int		len;
+	int8	result;
+
+	len = VARSIZE_ANY_EXHDR(t1);
+	result = pg_popcount(VARDATA_ANY(t1), len);
+
+	PG_RETURN_INT64(result);
+}
+
 /*
  * byteapos -
  *	  Return the position of the specified substring.
diff --git src/test/regress/expected/bit.out src/test/regress/expected/bit.out
index a1fab7ebcb..c91ad3d0d5 100644
--- src/test/regress/expected/bit.out
+++ src/test/regress/expected/bit.out
@@ -681,6 +681,19 @@ SELECT overlay(B'0101011100' placing '001' from 20);
  0101011100001
 (1 row)
 
+-- Popcount
+SELECT popcount(B'0101011100'::bit(10));
+ popcount 
+----------
+        5
+(1 row)
+
+SELECT popcount(B'1111111111'::bit(10));
+ popcount 
+----------
+       10
+(1 row)
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git src/test/regress/expected/strings.out src/test/regress/expected/strings.out
index 298b6c48c2..9780639038 100644
--- src/test/regress/expected/strings.out
+++ src/test/regress/expected/strings.out
@@ -2126,3 +2126,10 @@ SELECT encode(overlay(E'Th\\000omas'::bytea placing E'\\002\\003'::bytea from 5
  Th\000o\x02\x03
 (1 row)
 
+SET bytea_output TO hex;
+SELECT popcount(E'\\xdeadbeef'::bytea);
+ popcount 
+----------
+       24
+(1 row)
+
diff --git src/test/regress/sql/bit.sql src/test/regress/sql/bit.sql
index 7681d4ab4d..3cd9fb65d3 100644
--- src/test/regress/sql/bit.sql
+++ src/test/regress/sql/bit.sql
@@ -207,6 +207,10 @@ SELECT overlay(B'0101011100' placing '101' from 6);
 SELECT overlay(B'0101011100' placing '001' from 11);
 SELECT overlay(B'0101011100' placing '001' from 20);
 
+-- Popcount
+SELECT popcount(B'0101011100'::bit(10));
+SELECT popcount(B'1111111111'::bit(10));
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git src/test/regress/sql/strings.sql src/test/regress/sql/strings.sql
index ad5221ab6b..a35e993ab0 100644
--- src/test/regress/sql/strings.sql
+++ src/test/regress/sql/strings.sql
@@ -717,3 +717,6 @@ SELECT btrim(E'\\000trim\\000'::bytea, ''::bytea);
 SELECT encode(overlay(E'Th\\000omas'::bytea placing E'Th\\001omas'::bytea from 2),'escape');
 SELECT encode(overlay(E'Th\\000omas'::bytea placing E'\\002\\003'::bytea from 8),'escape');
 SELECT encode(overlay(E'Th\\000omas'::bytea placing E'\\002\\003'::bytea from 5 for 3),'escape');
+
+SET bytea_output TO hex;
+SELECT popcount(E'\\xdeadbeef'::bytea);


^ permalink  raw  reply  [nested|flat] 4+ messages in thread

* [PATCH v6 1/2] Clear padding in PgStat_HashKey keys
@ 2024-11-02 14:21  Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
  0 siblings, 0 replies; 4+ messages in thread

From: Bertrand Drouvot @ 2024-11-02 14:21 UTC (permalink / raw)

PgStat_HashKey keys are currently initialized in a way that could result in random
data in the padding bytes (if there was padding in PgStat_HashKey which is not
the case currently).

We are using sizeof(PgStat_HashKey) in pgstat_cmp_hash_key() and we compute the
hash hash key in pgstat_hash_hash_key() using the PgStat_HashKey struct size as
input. So, we have to ensure that no random data can be stored in the padding
bytes (if any) of a PgStat_HashKey key.
---
 src/backend/utils/activity/pgstat.c       |  3 +++
 src/backend/utils/activity/pgstat_shmem.c | 18 ++++++++++++++++--
 2 files changed, 19 insertions(+), 2 deletions(-)
 100.0% src/backend/utils/activity/

diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index be48432cc3..ea8c5691e8 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -938,6 +938,9 @@ pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, uint64 objid)
 
 	pgstat_prep_snapshot();
 
+	/* clear padding */
+	memset(&key, 0, sizeof(struct PgStat_HashKey));
+
 	key.kind = kind;
 	key.dboid = dboid;
 	key.objid = objid;
diff --git a/src/backend/utils/activity/pgstat_shmem.c b/src/backend/utils/activity/pgstat_shmem.c
index a09c6fee05..c1b7ff76b1 100644
--- a/src/backend/utils/activity/pgstat_shmem.c
+++ b/src/backend/utils/activity/pgstat_shmem.c
@@ -432,11 +432,18 @@ PgStat_EntryRef *
 pgstat_get_entry_ref(PgStat_Kind kind, Oid dboid, uint64 objid, bool create,
 					 bool *created_entry)
 {
-	PgStat_HashKey key = {.kind = kind,.dboid = dboid,.objid = objid};
+	PgStat_HashKey key;
 	PgStatShared_HashEntry *shhashent;
 	PgStatShared_Common *shheader = NULL;
 	PgStat_EntryRef *entry_ref;
 
+	/* clear padding */
+	memset(&key, 0, sizeof(struct PgStat_HashKey));
+
+	key.kind = kind;
+	key.dboid = dboid;
+	key.objid = objid;
+
 	/*
 	 * passing in created_entry only makes sense if we possibly could create
 	 * entry.
@@ -908,10 +915,17 @@ pgstat_drop_database_and_contents(Oid dboid)
 bool
 pgstat_drop_entry(PgStat_Kind kind, Oid dboid, uint64 objid)
 {
-	PgStat_HashKey key = {.kind = kind,.dboid = dboid,.objid = objid};
+	PgStat_HashKey key;
 	PgStatShared_HashEntry *shent;
 	bool		freed = true;
 
+	/* clear padding */
+	memset(&key, 0, sizeof(struct PgStat_HashKey));
+
+	key.kind = kind;
+	key.dboid = dboid;
+	key.objid = objid;
+
 	/* delete local reference */
 	if (pgStatEntryRefHash)
 	{
-- 
2.34.1


--gvmrl0mfoTEJEfPE
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v6-0002-Provide-relfilenode-statistics.patch"
Content-Transfer-Encoding: 8bit



^ permalink  raw  reply  [nested|flat] 4+ messages in thread


end of thread, other threads:[~2024-11-02 14:21 UTC | newest]

Thread overview: 4+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2020-12-30 10:51 [PATCH v1] popcount David Fetter <david@fetter.org>
2020-12-30 10:51 [PATCH v5] popcount David Fetter <david@fetter.org>
2020-12-30 10:51 [PATCH v2] popcount David Fetter <david@fetter.org>
2024-11-02 14:21 [PATCH v6 1/2] Clear padding in PgStat_HashKey keys Bertrand Drouvot <bertranddrouvot.pg@gmail.com>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox