pageinspect: Fix handling of all-zero pages

Getting from get_raw_page() an all-zero page is considered as a valid
case by the buffer manager and it can happen for example when finding a
corrupted page with zero_damaged_pages enabled (using zero_damaged_pages
to look at corrupted pages happens), or after a crash when a relation
file is extended before any WAL for its new data is generated (before a
vacuum or autovacuum job comes in to do some cleanup).

However, all the functions of pageinspect, as of the index AMs (except
hash that has its own idea of new pages), heap, the FSM or the page
header have never worked with all-zero pages, causing various crashes
when going through the page internals.

This commit changes all the pageinspect functions to be compliant with
all-zero pages, where the choice is made to return NULL or no rows for
SRFs when finding a new page.  get_raw_page() still works the same way,
returning a batch of zeros in the bytea of the page retrieved.  A hard
error could be used but NULL, while more invasive, is useful when
scanning relation files in full to get a batch of results for a single
relation in one query.  Tests are added for all the code paths
impacted.

Reported-by: Daria Lepikhova
Author: Michael Paquier
Discussion: https://postgr.es/m/561e187b-3549-c8d5-03f5-525c14e65bd0@postgrespro.ru
Backpatch-through: 10

15 files changed, 154 insertions, 0 deletions

diff --git a/contrib/pageinspect/brinfuncs.c b/contrib/pageinspect/brinfuncs.c
index 95b58ac0d2..04a90c4782 100644
--- a/contrib/pageinspect/brinfuncs.c
+++ b/contrib/pageinspect/brinfuncs.c
@@ -58,6 +58,9 @@ brin_page_type(PG_FUNCTION_ARGS)
 
 	page = get_page_from_raw(raw_page);
 
+	if (PageIsNew(page))
+		PG_RETURN_NULL();
+
 	/* verify the special space has the expected size */
 	if (PageGetSpecialSize(page) != MAXALIGN(sizeof(BrinSpecialSpace)))
 			ereport(ERROR,
@@ -95,6 +98,9 @@ verify_brin_page(bytea *raw_page, uint16 type, const char *strtype)
 {
 	Page		page = get_page_from_raw(raw_page);
 
+	if (PageIsNew(page))
+		return page;
+
 	/* verify the special space has the expected size */
 	if (PageGetSpecialSize(page) != MAXALIGN(sizeof(BrinSpecialSpace)))
 			ereport(ERROR,
@@ -182,6 +188,13 @@ brin_page_items(PG_FUNCTION_ARGS)
 	/* minimally verify the page we got */
 	page = verify_brin_page(raw_page, BRIN_PAGETYPE_REGULAR, "regular");
 
+	if (PageIsNew(page))
+	{
+		brin_free_desc(bdesc);
+		index_close(indexRel, AccessShareLock);
+		PG_RETURN_NULL();
+	}
+
 	/*
 	 * Initialize output functions for all indexed datatypes; simplifies
 	 * calling them later.
@@ -348,6 +361,9 @@ brin_metapage_info(PG_FUNCTION_ARGS)
 
 	page = verify_brin_page(raw_page, BRIN_PAGETYPE_META, "metapage");
 
+	if (PageIsNew(page))
+		PG_RETURN_NULL();
+
 	/* Build a tuple descriptor for our result type */
 	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
 		elog(ERROR, "return type must be a row type");
@@ -399,6 +415,12 @@ brin_revmap_data(PG_FUNCTION_ARGS)
 		/* minimally verify the page we got */
 		page = verify_brin_page(raw_page, BRIN_PAGETYPE_REVMAP, "revmap");
 
+		if (PageIsNew(page))
+		{
+			MemoryContextSwitchTo(mctx);
+			PG_RETURN_NULL();
+		}
+
 		state = palloc(sizeof(*state));
 		state->tids = ((RevmapContents *) PageGetContents(page))->rm_tids;
 		state->idx = 0;
diff --git a/contrib/pageinspect/btreefuncs.c b/contrib/pageinspect/btreefuncs.c
index 447f1fae91..3093aa894f 100644
--- a/contrib/pageinspect/btreefuncs.c
+++ b/contrib/pageinspect/btreefuncs.c
@@ -545,6 +545,12 @@ bt_page_items_bytea(PG_FUNCTION_ARGS)
 
 		uargs->page = get_page_from_raw(raw_page);
 
+		if (PageIsNew(uargs->page))
+		{
+			MemoryContextSwitchTo(mctx);
+			PG_RETURN_NULL();
+		}
+
 		uargs->offset = FirstOffsetNumber;
 
 		/* verify the special space has the expected size */
diff --git a/contrib/pageinspect/expected/brin.out b/contrib/pageinspect/expected/brin.out
index 62ee783b60..d19cdc3b95 100644
--- a/contrib/pageinspect/expected/brin.out
+++ b/contrib/pageinspect/expected/brin.out
@@ -62,4 +62,29 @@ ERROR:  input page is not a valid BRIN page
 SELECT * FROM brin_revmap_data(get_raw_page('test1', 0));
 ERROR:  input page is not a valid BRIN page
 \set VERBOSITY default
+-- Tests with all-zero pages.
+SHOW block_size \gset
+SELECT brin_page_type(decode(repeat('00', :block_size), 'hex'));
+ brin_page_type 
+----------------
+ 
+(1 row)
+
+SELECT brin_page_items(decode(repeat('00', :block_size), 'hex'), 'test1_a_idx');
+ brin_page_items 
+-----------------
+(0 rows)
+
+SELECT brin_metapage_info(decode(repeat('00', :block_size), 'hex'));
+ brin_metapage_info 
+--------------------
+ 
+(1 row)
+
+SELECT brin_revmap_data(decode(repeat('00', :block_size), 'hex'));
+ brin_revmap_data 
+------------------
+ 
+(1 row)
+
 DROP TABLE test1;
diff --git a/contrib/pageinspect/expected/btree.out b/contrib/pageinspect/expected/btree.out
index e6c5a0f968..f6eba981e1 100644
--- a/contrib/pageinspect/expected/btree.out
+++ b/contrib/pageinspect/expected/btree.out
@@ -93,4 +93,10 @@ ERROR:  input page is not a valid btree page
 SELECT bt_page_items(get_raw_page('test1_a_brin', 0));
 ERROR:  input page is not a valid btree page
 \set VERBOSITY default
+-- Tests with all-zero pages.
+SHOW block_size \gset
+SELECT bt_page_items(decode(repeat('00', :block_size), 'hex'));
+-[ RECORD 1 ]-+-
+bt_page_items | 
+
 DROP TABLE test1;
diff --git a/contrib/pageinspect/expected/gin.out b/contrib/pageinspect/expected/gin.out
index c1f93ffaa1..5f49ff577b 100644
--- a/contrib/pageinspect/expected/gin.out
+++ b/contrib/pageinspect/expected/gin.out
@@ -54,3 +54,17 @@ ERROR:  input page is not a valid GIN data leaf page
 SELECT * FROM gin_leafpage_items(get_raw_page('test1', 0));
 ERROR:  input page is not a valid GIN data leaf page
 \set VERBOSITY default
+-- Tests with all-zero pages.
+SHOW block_size \gset
+SELECT gin_leafpage_items(decode(repeat('00', :block_size), 'hex'));
+-[ RECORD 1 ]------+-
+gin_leafpage_items | 
+
+SELECT gin_metapage_info(decode(repeat('00', :block_size), 'hex'));
+-[ RECORD 1 ]-----+-
+gin_metapage_info | 
+
+SELECT gin_page_opaque_info(decode(repeat('00', :block_size), 'hex'));
+-[ RECORD 1 ]--------+-
+gin_page_opaque_info | 
+
diff --git a/contrib/pageinspect/expected/hash.out b/contrib/pageinspect/expected/hash.out
index 7db8abe099..82f1875288 100644
--- a/contrib/pageinspect/expected/hash.out
+++ b/contrib/pageinspect/expected/hash.out
@@ -186,4 +186,16 @@ ERROR:  input page is not a valid hash page
 SELECT hash_page_type(get_raw_page('test_hash', 0));
 ERROR:  input page is not a valid hash page
 \set VERBOSITY default
+-- Tests with all-zero pages.
+SHOW block_size \gset
+SELECT hash_metapage_info(decode(repeat('00', :block_size), 'hex'));
+ERROR:  page is not a hash meta page
+SELECT hash_page_items(decode(repeat('00', :block_size), 'hex'));
+ERROR:  page is not a hash bucket or overflow page
+SELECT hash_page_stats(decode(repeat('00', :block_size), 'hex'));
+ERROR:  page is not a hash bucket or overflow page
+SELECT hash_page_type(decode(repeat('00', :block_size), 'hex'));
+-[ RECORD 1 ]--+-------
+hash_page_type | unused
+
 DROP TABLE test_hash;
diff --git a/contrib/pageinspect/expected/page.out b/contrib/pageinspect/expected/page.out
index 74deb23c59..717ceccda3 100644
--- a/contrib/pageinspect/expected/page.out
+++ b/contrib/pageinspect/expected/page.out
@@ -212,3 +212,23 @@ ERROR:  invalid page size
 SELECT page_header('ccc'::bytea);
 ERROR:  invalid page size
 \set VERBOSITY default
+-- Tests with all-zero pages.
+SHOW block_size \gset
+SELECT fsm_page_contents(decode(repeat('00', :block_size), 'hex'));
+ fsm_page_contents 
+-------------------
+ 
+(1 row)
+
+SELECT page_header(decode(repeat('00', :block_size), 'hex'));
+      page_header      
+-----------------------
+ (0/0,0,0,0,0,0,0,0,0)
+(1 row)
+
+SELECT page_checksum(decode(repeat('00', :block_size), 'hex'), 1);
+ page_checksum 
+---------------
+              
+(1 row)
+
diff --git a/contrib/pageinspect/fsmfuncs.c b/contrib/pageinspect/fsmfuncs.c
index 9f596d26fd..c1d0ea351e 100644
--- a/contrib/pageinspect/fsmfuncs.c
+++ b/contrib/pageinspect/fsmfuncs.c
@@ -46,6 +46,10 @@ fsm_page_contents(PG_FUNCTION_ARGS)
 				 errmsg("must be superuser to use raw page functions")));
 
 	page = get_page_from_raw(raw_page);
+
+	if (PageIsNew(page))
+		PG_RETURN_NULL();
+
 	fsmpage = (FSMPage) PageGetContents(page);
 
 	initStringInfo(&sinfo);
diff --git a/contrib/pageinspect/ginfuncs.c b/contrib/pageinspect/ginfuncs.c
index 5cecb46e2e..1b482a0999 100644
--- a/contrib/pageinspect/ginfuncs.c
+++ b/contrib/pageinspect/ginfuncs.c
@@ -49,6 +49,9 @@ gin_metapage_info(PG_FUNCTION_ARGS)
 
 	page = get_page_from_raw(raw_page);
 
+	if (PageIsNew(page))
+		PG_RETURN_NULL();
+
 	if (PageGetSpecialSize(page) != MAXALIGN(sizeof(GinPageOpaqueData)))
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
@@ -115,6 +118,9 @@ gin_page_opaque_info(PG_FUNCTION_ARGS)
 
 	page = get_page_from_raw(raw_page);
 
+	if (PageIsNew(page))
+		PG_RETURN_NULL();
+
 	if (PageGetSpecialSize(page) != MAXALIGN(sizeof(GinPageOpaqueData)))
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
@@ -200,6 +206,12 @@ gin_leafpage_items(PG_FUNCTION_ARGS)
 
 		page = get_page_from_raw(raw_page);
 
+		if (PageIsNew(page))
+		{
+			MemoryContextSwitchTo(mctx);
+			PG_RETURN_NULL();
+		}
+
 		if (PageGetSpecialSize(page) != MAXALIGN(sizeof(GinPageOpaqueData)))
 			ereport(ERROR,
 					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
diff --git a/contrib/pageinspect/rawpage.c b/contrib/pageinspect/rawpage.c
index 3240061621..0e2799bc8f 100644
--- a/contrib/pageinspect/rawpage.c
+++ b/contrib/pageinspect/rawpage.c
@@ -296,5 +296,8 @@ page_checksum(PG_FUNCTION_ARGS)
 
 	page = get_page_from_raw(raw_page);
 
+	if (PageIsNew(page))
+		PG_RETURN_NULL();
+
 	PG_RETURN_INT16(pg_checksum_page((char *) page, blkno));
 }
diff --git a/contrib/pageinspect/sql/brin.sql b/contrib/pageinspect/sql/brin.sql
index dc5d1661b6..45098c1ef5 100644
--- a/contrib/pageinspect/sql/brin.sql
+++ b/contrib/pageinspect/sql/brin.sql
@@ -27,4 +27,11 @@ SELECT * FROM brin_metapage_info(get_raw_page('test1', 0));
 SELECT * FROM brin_revmap_data(get_raw_page('test1', 0));
 \set VERBOSITY default
 
+-- Tests with all-zero pages.
+SHOW block_size \gset
+SELECT brin_page_type(decode(repeat('00', :block_size), 'hex'));
+SELECT brin_page_items(decode(repeat('00', :block_size), 'hex'), 'test1_a_idx');
+SELECT brin_metapage_info(decode(repeat('00', :block_size), 'hex'));
+SELECT brin_revmap_data(decode(repeat('00', :block_size), 'hex'));
+
 DROP TABLE test1;
diff --git a/contrib/pageinspect/sql/btree.sql b/contrib/pageinspect/sql/btree.sql
index cde0083586..75587c1aca 100644
--- a/contrib/pageinspect/sql/btree.sql
+++ b/contrib/pageinspect/sql/btree.sql
@@ -41,4 +41,8 @@ SELECT bt_page_items(get_raw_page('test1', 0));
 SELECT bt_page_items(get_raw_page('test1_a_brin', 0));
 \set VERBOSITY default
 
+-- Tests with all-zero pages.
+SHOW block_size \gset
+SELECT bt_page_items(decode(repeat('00', :block_size), 'hex'));
+
 DROP TABLE test1;
diff --git a/contrib/pageinspect/sql/gin.sql b/contrib/pageinspect/sql/gin.sql
index 342354a481..b0c20c0307 100644
--- a/contrib/pageinspect/sql/gin.sql
+++ b/contrib/pageinspect/sql/gin.sql
@@ -31,3 +31,9 @@ SELECT * FROM gin_metapage_info(get_raw_page('test1', 0));
 SELECT * FROM gin_page_opaque_info(get_raw_page('test1', 0));
 SELECT * FROM gin_leafpage_items(get_raw_page('test1', 0));
 \set VERBOSITY default
+
+-- Tests with all-zero pages.
+SHOW block_size \gset
+SELECT gin_leafpage_items(decode(repeat('00', :block_size), 'hex'));
+SELECT gin_metapage_info(decode(repeat('00', :block_size), 'hex'));
+SELECT gin_page_opaque_info(decode(repeat('00', :block_size), 'hex'));
diff --git a/contrib/pageinspect/sql/hash.sql b/contrib/pageinspect/sql/hash.sql
index 8fd209c815..3acdc7d955 100644
--- a/contrib/pageinspect/sql/hash.sql
+++ b/contrib/pageinspect/sql/hash.sql
@@ -96,4 +96,11 @@ SELECT hash_page_stats(get_raw_page('test_hash', 0));
 SELECT hash_page_type(get_raw_page('test_hash', 0));
 \set VERBOSITY default
 
+-- Tests with all-zero pages.
+SHOW block_size \gset
+SELECT hash_metapage_info(decode(repeat('00', :block_size), 'hex'));
+SELECT hash_page_items(decode(repeat('00', :block_size), 'hex'));
+SELECT hash_page_stats(decode(repeat('00', :block_size), 'hex'));
+SELECT hash_page_type(decode(repeat('00', :block_size), 'hex'));
+
 DROP TABLE test_hash;
diff --git a/contrib/pageinspect/sql/page.sql b/contrib/pageinspect/sql/page.sql
index bb78546e17..172f252638 100644
--- a/contrib/pageinspect/sql/page.sql
+++ b/contrib/pageinspect/sql/page.sql
@@ -89,3 +89,9 @@ SELECT fsm_page_contents('aaa'::bytea);
 SELECT page_checksum('bbb'::bytea, 0);
 SELECT page_header('ccc'::bytea);
 \set VERBOSITY default
+
+-- Tests with all-zero pages.
+SHOW block_size \gset
+SELECT fsm_page_contents(decode(repeat('00', :block_size), 'hex'));
+SELECT page_header(decode(repeat('00', :block_size), 'hex'));
+SELECT page_checksum(decode(repeat('00', :block_size), 'hex'), 1);