From df6bbe73b86cda28472b9ecc61ac2deff5b2837b Mon Sep 17 00:00:00 2001
From: Michael Paquier <michael@paquier.xyz>
Date: Thu, 14 Apr 2022 15:09:26 +0900
Subject: [PATCH] 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
---
 contrib/pageinspect/brinfuncs.c        | 22 ++++++++++++++++++++++
 contrib/pageinspect/btreefuncs.c       |  6 ++++++
 contrib/pageinspect/expected/brin.out  | 25 +++++++++++++++++++++++++
 contrib/pageinspect/expected/btree.out |  6 ++++++
 contrib/pageinspect/expected/gin.out   | 14 ++++++++++++++
 contrib/pageinspect/expected/gist.out  | 18 ++++++++++++++++++
 contrib/pageinspect/expected/hash.out  | 12 ++++++++++++
 contrib/pageinspect/expected/page.out  | 20 ++++++++++++++++++++
 contrib/pageinspect/fsmfuncs.c         |  4 ++++
 contrib/pageinspect/ginfuncs.c         | 12 ++++++++++++
 contrib/pageinspect/gistfuncs.c        | 12 ++++++++++++
 contrib/pageinspect/rawpage.c          |  3 +++
 contrib/pageinspect/sql/brin.sql       |  7 +++++++
 contrib/pageinspect/sql/btree.sql      |  4 ++++
 contrib/pageinspect/sql/gin.sql        |  6 ++++++
 contrib/pageinspect/sql/gist.sql       |  6 ++++++
 contrib/pageinspect/sql/hash.sql       |  7 +++++++
 contrib/pageinspect/sql/page.sql       |  6 ++++++
 18 files changed, 190 insertions(+)

diff --git a/contrib/pageinspect/brinfuncs.c b/contrib/pageinspect/brinfuncs.c
index 4faccd3074..2c3da717e7 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.
@@ -359,6 +372,9 @@ 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");
@@ -410,6 +426,12 @@ 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 7651c59bbf..2044b88d48 100644
--- a/contrib/pageinspect/btreefuncs.c
+++ b/contrib/pageinspect/btreefuncs.c
@@ -611,6 +611,12 @@ 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 89d2160990..035a81a759 100644
--- a/contrib/pageinspect/expected/btree.out
+++ b/contrib/pageinspect/expected/btree.out
@@ -99,4 +99,10 @@ 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 e9fdb4cf20..ff1da6a5a1 100644
--- a/contrib/pageinspect/expected/gin.out
+++ b/contrib/pageinspect/expected/gin.out
@@ -54,4 +54,18 @@ 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 | 
+
 DROP TABLE test1;
diff --git a/contrib/pageinspect/expected/gist.out b/contrib/pageinspect/expected/gist.out
index 3161d1decd..469fc5eabf 100644
--- a/contrib/pageinspect/expected/gist.out
+++ b/contrib/pageinspect/expected/gist.out
@@ -89,4 +89,22 @@ ERROR:  input page is not a valid GiST page
 SELECT gist_page_items_bytea(get_raw_page('test_gist_btree', 0));
 ERROR:  input page is not a valid GiST page
 \set VERBOSITY default
+-- Tests with all-zero pages.
+SHOW block_size \gset
+SELECT gist_page_items_bytea(decode(repeat('00', :block_size), 'hex'));
+ gist_page_items_bytea 
+-----------------------
+(0 rows)
+
+SELECT gist_page_items(decode(repeat('00', :block_size), 'hex'), 'test_gist_idx'::regclass);
+ gist_page_items 
+-----------------
+(0 rows)
+
+SELECT gist_page_opaque_info(decode(repeat('00', :block_size), 'hex'));
+ gist_page_opaque_info 
+-----------------------
+ 
+(1 row)
+
 DROP TABLE test_gist;
diff --git a/contrib/pageinspect/expected/hash.out b/contrib/pageinspect/expected/hash.out
index 96c9511457..5d6a518834 100644
--- a/contrib/pageinspect/expected/hash.out
+++ b/contrib/pageinspect/expected/hash.out
@@ -190,4 +190,16 @@ 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 3f86ae5f24..8134eda1d7 100644
--- a/contrib/pageinspect/expected/page.out
+++ b/contrib/pageinspect/expected/page.out
@@ -216,3 +216,23 @@ 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 30d609afcf..719275022d 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 b0fa6a079f..7a297f1d61 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/gistfuncs.c b/contrib/pageinspect/gistfuncs.c
index be2ee8433a..d1c3c321f8 100644
--- a/contrib/pageinspect/gistfuncs.c
+++ b/contrib/pageinspect/gistfuncs.c
@@ -55,6 +55,9 @@ gist_page_opaque_info(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(GISTPageOpaqueData)))
 			ereport(ERROR,
@@ -156,6 +159,9 @@ gist_page_items_bytea(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(GISTPageOpaqueData)))
 			ereport(ERROR,
@@ -272,6 +278,12 @@ gist_page_items(PG_FUNCTION_ARGS)
 
 	page = get_page_from_raw(raw_page);
 
+	if (PageIsNew(page))
+	{
+		index_close(indexRel, AccessShareLock);
+		PG_RETURN_NULL();
+	}
+
 	/* Avoid bogus PageGetMaxOffsetNumber() call with deleted pages */
 	if (GistPageIsDeleted(page))
 		elog(NOTICE, "page is deleted");
diff --git a/contrib/pageinspect/rawpage.c b/contrib/pageinspect/rawpage.c
index da46854cc4..c882a62f9f 100644
--- a/contrib/pageinspect/rawpage.c
+++ b/contrib/pageinspect/rawpage.c
@@ -349,6 +349,9 @@ page_checksum_internal(PG_FUNCTION_ARGS, enum pageinspect_version ext_version)
 
 	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 44d83f90ba..1f554f0f67 100644
--- a/contrib/pageinspect/sql/btree.sql
+++ b/contrib/pageinspect/sql/btree.sql
@@ -44,4 +44,8 @@ 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 6499b5c72b..b57466d7eb 100644
--- a/contrib/pageinspect/sql/gin.sql
+++ b/contrib/pageinspect/sql/gin.sql
@@ -32,4 +32,10 @@ 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'));
+
 DROP TABLE test1;
diff --git a/contrib/pageinspect/sql/gist.sql b/contrib/pageinspect/sql/gist.sql
index 58f4c35d1d..ee46e09053 100644
--- a/contrib/pageinspect/sql/gist.sql
+++ b/contrib/pageinspect/sql/gist.sql
@@ -44,4 +44,10 @@ SELECT gist_page_items_bytea(get_raw_page('test_gist', 0));
 SELECT gist_page_items_bytea(get_raw_page('test_gist_btree', 0));
 \set VERBOSITY default
 
+-- Tests with all-zero pages.
+SHOW block_size \gset
+SELECT gist_page_items_bytea(decode(repeat('00', :block_size), 'hex'));
+SELECT gist_page_items(decode(repeat('00', :block_size), 'hex'), 'test_gist_idx'::regclass);
+SELECT gist_page_opaque_info(decode(repeat('00', :block_size), 'hex'));
+
 DROP TABLE test_gist;
diff --git a/contrib/pageinspect/sql/hash.sql b/contrib/pageinspect/sql/hash.sql
index ccc984c086..320fb9fa9f 100644
--- a/contrib/pageinspect/sql/hash.sql
+++ b/contrib/pageinspect/sql/hash.sql
@@ -98,4 +98,11 @@ 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 38b1681541..b5c41cc8ac 100644
--- a/contrib/pageinspect/sql/page.sql
+++ b/contrib/pageinspect/sql/page.sql
@@ -91,3 +91,9 @@ 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);