Add defenses to btree and hash index AMs to do simple sanity checks

on every index page they read; in particular to catch the case of an
all-zero page, which PageHeaderIsValid allows to pass.  It turns out
hash already had this idea, but it was just Assert()ing things rather
than doing a straight error check, and the Asserts were partially
redundant with PageHeaderIsValid anyway.  Per recent failure example
from Jim Nasby.  (gist still needs the same treatment.)

diff --git a/src/backend/access/hash/hash.c b/src/backend/access/hash/hash.c
index 2cff9509b6a9cf457d845e9ed3bdfd7ce3f0321a..de9652346d437a7adc4bc9728d44a07f7bfc7210 100644 (file)
--- a/src/backend/access/hash/hash.c
+++ b/src/backend/access/hash/hash.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/access/hash/hash.c,v 1.81 2005/10/15 02:49:08 momjian Exp $
+ *   $PostgreSQL: pgsql/src/backend/access/hash/hash.c,v 1.82 2005/11/06 19:29:00 tgl Exp $
  *
  * NOTES
  *   This file contains only the public interface routines.
@@ -513,8 +513,8 @@ hashbulkdelete(PG_FUNCTION_ARGS)
     * each bucket.
     */
    metabuf = _hash_getbuf(rel, HASH_METAPAGE, HASH_READ);
+   _hash_checkpage(rel, metabuf, LH_META_PAGE);
    metap = (HashMetaPage) BufferGetPage(metabuf);
-   _hash_checkpage(rel, (Page) metap, LH_META_PAGE);
    orig_maxbucket = metap->hashm_maxbucket;
    orig_ntuples = metap->hashm_ntuples;
    memcpy(&local_metapage, metap, sizeof(local_metapage));
@@ -555,8 +555,8 @@ loop_top:
            vacuum_delay_point();
 
            buf = _hash_getbuf(rel, blkno, HASH_WRITE);
+           _hash_checkpage(rel, buf, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
            page = BufferGetPage(buf);
-           _hash_checkpage(rel, page, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
            opaque = (HashPageOpaque) PageGetSpecialPointer(page);
            Assert(opaque->hasho_bucket == cur_bucket);
 
@@ -614,8 +614,8 @@ loop_top:
 
    /* Write-lock metapage and check for split since we started */
    metabuf = _hash_getbuf(rel, HASH_METAPAGE, HASH_WRITE);
+   _hash_checkpage(rel, metabuf, LH_META_PAGE);
    metap = (HashMetaPage) BufferGetPage(metabuf);
-   _hash_checkpage(rel, (Page) metap, LH_META_PAGE);
 
    if (cur_maxbucket != metap->hashm_maxbucket)
    {

diff --git a/src/backend/access/hash/hashinsert.c b/src/backend/access/hash/hashinsert.c
index 9976489ae9dc530b3699e5f93269dd1bac99700a..065cbe32c51411f260da95caed5cc73834cbfb1e 100644 (file)
--- a/src/backend/access/hash/hashinsert.c
+++ b/src/backend/access/hash/hashinsert.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/access/hash/hashinsert.c,v 1.39 2005/10/18 01:06:23 tgl Exp $
+ *   $PostgreSQL: pgsql/src/backend/access/hash/hashinsert.c,v 1.40 2005/11/06 19:29:00 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -73,8 +73,8 @@ _hash_doinsert(Relation rel, HashItem hitem)
 
    /* Read the metapage */
    metabuf = _hash_getbuf(rel, HASH_METAPAGE, HASH_READ);
+   _hash_checkpage(rel, metabuf, LH_META_PAGE);
    metap = (HashMetaPage) BufferGetPage(metabuf);
-   _hash_checkpage(rel, (Page) metap, LH_META_PAGE);
 
    /*
     * Check whether the item can fit on a hash page at all. (Eventually, we
@@ -111,8 +111,8 @@ _hash_doinsert(Relation rel, HashItem hitem)
 
    /* Fetch the primary bucket page for the bucket */
    buf = _hash_getbuf(rel, blkno, HASH_WRITE);
+   _hash_checkpage(rel, buf, LH_BUCKET_PAGE);
    page = BufferGetPage(buf);
-   _hash_checkpage(rel, page, LH_BUCKET_PAGE);
    pageopaque = (HashPageOpaque) PageGetSpecialPointer(page);
    Assert(pageopaque->hasho_bucket == bucket);
 
@@ -151,7 +151,7 @@ _hash_doinsert(Relation rel, HashItem hitem)
            /* should fit now, given test above */
            Assert(PageGetFreeSpace(page) >= itemsz);
        }
-       _hash_checkpage(rel, page, LH_OVERFLOW_PAGE);
+       _hash_checkpage(rel, buf, LH_OVERFLOW_PAGE);
        pageopaque = (HashPageOpaque) PageGetSpecialPointer(page);
        Assert(pageopaque->hasho_bucket == bucket);
    }
@@ -204,8 +204,8 @@ _hash_pgaddtup(Relation rel,
    OffsetNumber itup_off;
    Page        page;
 
+   _hash_checkpage(rel, buf, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
    page = BufferGetPage(buf);
-   _hash_checkpage(rel, page, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
 
    itup_off = OffsetNumberNext(PageGetMaxOffsetNumber(page));
    if (PageAddItem(page, (Item) hitem, itemsize, itup_off, LP_USED)

diff --git a/src/backend/access/hash/hashovfl.c b/src/backend/access/hash/hashovfl.c
index 7289d9a0b355a5545adc68546dd1bd65ceadcf31..aa433bc70a0509d4fce5a6e57c069bba53a21070 100644 (file)
--- a/src/backend/access/hash/hashovfl.c
+++ b/src/backend/access/hash/hashovfl.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/access/hash/hashovfl.c,v 1.47 2005/10/15 02:49:08 momjian Exp $
+ *   $PostgreSQL: pgsql/src/backend/access/hash/hashovfl.c,v 1.48 2005/11/06 19:29:00 tgl Exp $
  *
  * NOTES
  *   Overflow pages look like ordinary relation pages.
@@ -124,8 +124,8 @@ _hash_addovflpage(Relation rel, Buffer metabuf, Buffer buf)
    {
        BlockNumber nextblkno;
 
+       _hash_checkpage(rel, buf, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
        page = BufferGetPage(buf);
-       _hash_checkpage(rel, page, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
        pageopaque = (HashPageOpaque) PageGetSpecialPointer(page);
        nextblkno = pageopaque->hasho_nextblkno;
 
@@ -183,8 +183,8 @@ _hash_getovflpage(Relation rel, Buffer metabuf)
    /* Get exclusive lock on the meta page */
    _hash_chgbufaccess(rel, metabuf, HASH_NOLOCK, HASH_WRITE);
 
+   _hash_checkpage(rel, metabuf, LH_META_PAGE);
    metap = (HashMetaPage) BufferGetPage(metabuf);
-   _hash_checkpage(rel, (Page) metap, LH_META_PAGE);
 
    /* start search at hashm_firstfree */
    orig_firstfree = metap->hashm_firstfree;
@@ -222,8 +222,8 @@ _hash_getovflpage(Relation rel, Buffer metabuf)
        _hash_chgbufaccess(rel, metabuf, HASH_READ, HASH_NOLOCK);
 
        mapbuf = _hash_getbuf(rel, mapblkno, HASH_WRITE);
+       _hash_checkpage(rel, mapbuf, LH_BITMAP_PAGE);
        mappage = BufferGetPage(mapbuf);
-       _hash_checkpage(rel, mappage, LH_BITMAP_PAGE);
        freep = HashPageGetBitmap(mappage);
 
        for (; bit <= last_inpage; j++, bit += BITS_PER_MAP)
@@ -379,9 +379,9 @@ _hash_freeovflpage(Relation rel, Buffer ovflbuf)
    Bucket      bucket;
 
    /* Get information from the doomed page */
+   _hash_checkpage(rel, ovflbuf, LH_OVERFLOW_PAGE);
    ovflblkno = BufferGetBlockNumber(ovflbuf);
    ovflpage = BufferGetPage(ovflbuf);
-   _hash_checkpage(rel, ovflpage, LH_OVERFLOW_PAGE);
    ovflopaque = (HashPageOpaque) PageGetSpecialPointer(ovflpage);
    nextblkno = ovflopaque->hasho_nextblkno;
    prevblkno = ovflopaque->hasho_prevblkno;
@@ -403,7 +403,7 @@ _hash_freeovflpage(Relation rel, Buffer ovflbuf)
        Page        prevpage = BufferGetPage(prevbuf);
        HashPageOpaque prevopaque = (HashPageOpaque) PageGetSpecialPointer(prevpage);
 
-       _hash_checkpage(rel, prevpage, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
+       _hash_checkpage(rel, prevbuf, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
        Assert(prevopaque->hasho_bucket == bucket);
        prevopaque->hasho_nextblkno = nextblkno;
        _hash_wrtbuf(rel, prevbuf);
@@ -414,7 +414,7 @@ _hash_freeovflpage(Relation rel, Buffer ovflbuf)
        Page        nextpage = BufferGetPage(nextbuf);
        HashPageOpaque nextopaque = (HashPageOpaque) PageGetSpecialPointer(nextpage);
 
-       _hash_checkpage(rel, nextpage, LH_OVERFLOW_PAGE);
+       _hash_checkpage(rel, nextbuf, LH_OVERFLOW_PAGE);
        Assert(nextopaque->hasho_bucket == bucket);
        nextopaque->hasho_prevblkno = prevblkno;
        _hash_wrtbuf(rel, nextbuf);
@@ -422,8 +422,8 @@ _hash_freeovflpage(Relation rel, Buffer ovflbuf)
 
    /* Read the metapage so we can determine which bitmap page to use */
    metabuf = _hash_getbuf(rel, HASH_METAPAGE, HASH_READ);
+   _hash_checkpage(rel, metabuf, LH_META_PAGE);
    metap = (HashMetaPage) BufferGetPage(metabuf);
-   _hash_checkpage(rel, (Page) metap, LH_META_PAGE);
 
    /* Identify which bit to set */
    ovflbitno = blkno_to_bitno(metap, ovflblkno);
@@ -440,8 +440,8 @@ _hash_freeovflpage(Relation rel, Buffer ovflbuf)
 
    /* Clear the bitmap bit to indicate that this overflow page is free */
    mapbuf = _hash_getbuf(rel, blkno, HASH_WRITE);
+   _hash_checkpage(rel, mapbuf, LH_BITMAP_PAGE);
    mappage = BufferGetPage(mapbuf);
-   _hash_checkpage(rel, mappage, LH_BITMAP_PAGE);
    freep = HashPageGetBitmap(mappage);
    Assert(ISSET(freep, bitmapbit));
    CLRBIT(freep, bitmapbit);
@@ -569,8 +569,8 @@ _hash_squeezebucket(Relation rel,
     */
    wblkno = bucket_blkno;
    wbuf = _hash_getbuf(rel, wblkno, HASH_WRITE);
+   _hash_checkpage(rel, wbuf, LH_BUCKET_PAGE);
    wpage = BufferGetPage(wbuf);
-   _hash_checkpage(rel, wpage, LH_BUCKET_PAGE);
    wopaque = (HashPageOpaque) PageGetSpecialPointer(wpage);
 
    /*
@@ -593,8 +593,8 @@ _hash_squeezebucket(Relation rel,
        if (ropaque != wopaque)
            _hash_relbuf(rel, rbuf);
        rbuf = _hash_getbuf(rel, rblkno, HASH_WRITE);
+       _hash_checkpage(rel, rbuf, LH_OVERFLOW_PAGE);
        rpage = BufferGetPage(rbuf);
-       _hash_checkpage(rel, rpage, LH_OVERFLOW_PAGE);
        ropaque = (HashPageOpaque) PageGetSpecialPointer(rpage);
        Assert(ropaque->hasho_bucket == bucket);
    } while (BlockNumberIsValid(ropaque->hasho_nextblkno));
@@ -635,8 +635,8 @@ _hash_squeezebucket(Relation rel,
                }
 
                wbuf = _hash_getbuf(rel, wblkno, HASH_WRITE);
+               _hash_checkpage(rel, wbuf, LH_OVERFLOW_PAGE);
                wpage = BufferGetPage(wbuf);
-               _hash_checkpage(rel, wpage, LH_OVERFLOW_PAGE);
                wopaque = (HashPageOpaque) PageGetSpecialPointer(wpage);
                Assert(wopaque->hasho_bucket == bucket);
            }
@@ -688,8 +688,8 @@ _hash_squeezebucket(Relation rel,
            _hash_freeovflpage(rel, rbuf);
 
            rbuf = _hash_getbuf(rel, rblkno, HASH_WRITE);
+           _hash_checkpage(rel, rbuf, LH_OVERFLOW_PAGE);
            rpage = BufferGetPage(rbuf);
-           _hash_checkpage(rel, rpage, LH_OVERFLOW_PAGE);
            ropaque = (HashPageOpaque) PageGetSpecialPointer(rpage);
            Assert(ropaque->hasho_bucket == bucket);
 

diff --git a/src/backend/access/hash/hashpage.c b/src/backend/access/hash/hashpage.c
index b40c20b480b35d78967304d727cd18158316146e..ab0bf935fb6196220c85f912c826d19100d517cb 100644 (file)
--- a/src/backend/access/hash/hashpage.c
+++ b/src/backend/access/hash/hashpage.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/access/hash/hashpage.c,v 1.52 2005/10/15 02:49:08 momjian Exp $
+ *   $PostgreSQL: pgsql/src/backend/access/hash/hashpage.c,v 1.53 2005/11/06 19:29:00 tgl Exp $
  *
  * NOTES
  *   Postgres hash pages look like ordinary relation pages.  The opaque
@@ -103,9 +103,11 @@ _hash_droplock(Relation rel, BlockNumber whichlock, int access)
  *     (ie, the buffer is "locked and pinned").
  *
  *     XXX P_NEW is not used because, unlike the tree structures, we
- *     need the bucket blocks to be at certain block numbers.  we must
- *     depend on the caller to call _hash_pageinit on the block if it
- *     knows that this is a new block.
+ *     need the bucket blocks to be at certain block numbers.
+ *
+ *     All call sites should call either _hash_pageinit or _hash_checkpage
+ *     on the returned page, depending on whether the block is expected
+ *     to be new or not.
  */
 Buffer
 _hash_getbuf(Relation rel, BlockNumber blkno, int access)
@@ -380,8 +382,8 @@ _hash_expandtable(Relation rel, Buffer metabuf)
    /* Write-lock the meta page */
    _hash_chgbufaccess(rel, metabuf, HASH_NOLOCK, HASH_WRITE);
 
+   _hash_checkpage(rel, metabuf, LH_META_PAGE);
    metap = (HashMetaPage) BufferGetPage(metabuf);
-   _hash_checkpage(rel, (Page) metap, LH_META_PAGE);
 
    /*
     * Check to see if split is still needed; someone else might have already
@@ -555,15 +557,15 @@ _hash_splitbucket(Relation rel,
     * either bucket.
     */
    oblkno = start_oblkno;
-   nblkno = start_nblkno;
    obuf = _hash_getbuf(rel, oblkno, HASH_WRITE);
-   nbuf = _hash_getbuf(rel, nblkno, HASH_WRITE);
+   _hash_checkpage(rel, obuf, LH_BUCKET_PAGE);
    opage = BufferGetPage(obuf);
-   npage = BufferGetPage(nbuf);
-
-   _hash_checkpage(rel, opage, LH_BUCKET_PAGE);
    oopaque = (HashPageOpaque) PageGetSpecialPointer(opage);
 
+   nblkno = start_nblkno;
+   nbuf = _hash_getbuf(rel, nblkno, HASH_WRITE);
+   npage = BufferGetPage(nbuf);
+
    /* initialize the new bucket's primary page */
    _hash_pageinit(npage, BufferGetPageSize(nbuf));
    nopaque = (HashPageOpaque) PageGetSpecialPointer(npage);
@@ -602,8 +604,8 @@ _hash_splitbucket(Relation rel,
            _hash_wrtbuf(rel, obuf);
 
            obuf = _hash_getbuf(rel, oblkno, HASH_WRITE);
+           _hash_checkpage(rel, obuf, LH_OVERFLOW_PAGE);
            opage = BufferGetPage(obuf);
-           _hash_checkpage(rel, opage, LH_OVERFLOW_PAGE);
            oopaque = (HashPageOpaque) PageGetSpecialPointer(opage);
            ooffnum = FirstOffsetNumber;
            omaxoffnum = PageGetMaxOffsetNumber(opage);
@@ -642,8 +644,8 @@ _hash_splitbucket(Relation rel,
                _hash_chgbufaccess(rel, nbuf, HASH_WRITE, HASH_NOLOCK);
                /* chain to a new overflow page */
                nbuf = _hash_addovflpage(rel, metabuf, nbuf);
+               _hash_checkpage(rel, nbuf, LH_OVERFLOW_PAGE);
                npage = BufferGetPage(nbuf);
-               _hash_checkpage(rel, npage, LH_OVERFLOW_PAGE);
                /* we don't need nopaque within the loop */
            }
 

diff --git a/src/backend/access/hash/hashsearch.c b/src/backend/access/hash/hashsearch.c
index a0d9f4afb94794073bfbf631c8251822870aba46..dff2268ba503cbd9ec3ab55d8b9b92272a9f0d0c 100644 (file)
--- a/src/backend/access/hash/hashsearch.c
+++ b/src/backend/access/hash/hashsearch.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/access/hash/hashsearch.c,v 1.41 2005/10/18 01:06:23 tgl Exp $
+ *   $PostgreSQL: pgsql/src/backend/access/hash/hashsearch.c,v 1.42 2005/11/06 19:29:00 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,8 +53,8 @@ _hash_next(IndexScanDesc scan, ScanDirection dir)
    /* if we're here, _hash_step found a valid tuple */
    current = &(scan->currentItemData);
    offnum = ItemPointerGetOffsetNumber(current);
+   _hash_checkpage(rel, buf, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
    page = BufferGetPage(buf);
-   _hash_checkpage(rel, page, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
    hitem = (HashItem) PageGetItem(page, PageGetItemId(page, offnum));
    itup = &hitem->hash_itup;
    scan->xs_ctup.t_self = itup->t_tid;
@@ -77,8 +77,8 @@ _hash_readnext(Relation rel,
    if (BlockNumberIsValid(blkno))
    {
        *bufp = _hash_getbuf(rel, blkno, HASH_READ);
+       _hash_checkpage(rel, *bufp, LH_OVERFLOW_PAGE);
        *pagep = BufferGetPage(*bufp);
-       _hash_checkpage(rel, *pagep, LH_OVERFLOW_PAGE);
        *opaquep = (HashPageOpaque) PageGetSpecialPointer(*pagep);
    }
 }
@@ -98,8 +98,8 @@ _hash_readprev(Relation rel,
    if (BlockNumberIsValid(blkno))
    {
        *bufp = _hash_getbuf(rel, blkno, HASH_READ);
+       _hash_checkpage(rel, *bufp, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
        *pagep = BufferGetPage(*bufp);
-       _hash_checkpage(rel, *pagep, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
        *opaquep = (HashPageOpaque) PageGetSpecialPointer(*pagep);
    }
 }
@@ -168,8 +168,8 @@ _hash_first(IndexScanDesc scan, ScanDirection dir)
 
    /* Read the metapage */
    metabuf = _hash_getbuf(rel, HASH_METAPAGE, HASH_READ);
+   _hash_checkpage(rel, metabuf, LH_META_PAGE);
    metap = (HashMetaPage) BufferGetPage(metabuf);
-   _hash_checkpage(rel, (Page) metap, LH_META_PAGE);
 
    /*
     * Compute the target bucket number, and convert to block number.
@@ -198,8 +198,8 @@ _hash_first(IndexScanDesc scan, ScanDirection dir)
 
    /* Fetch the primary bucket page for the bucket */
    buf = _hash_getbuf(rel, blkno, HASH_READ);
+   _hash_checkpage(rel, buf, LH_BUCKET_PAGE);
    page = BufferGetPage(buf);
-   _hash_checkpage(rel, page, LH_BUCKET_PAGE);
    opaque = (HashPageOpaque) PageGetSpecialPointer(page);
    Assert(opaque->hasho_bucket == bucket);
 
@@ -216,8 +216,8 @@ _hash_first(IndexScanDesc scan, ScanDirection dir)
 
    /* if we're here, _hash_step found a valid tuple */
    offnum = ItemPointerGetOffsetNumber(current);
+   _hash_checkpage(rel, buf, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
    page = BufferGetPage(buf);
-   _hash_checkpage(rel, page, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
    hitem = (HashItem) PageGetItem(page, PageGetItemId(page, offnum));
    itup = &hitem->hash_itup;
    scan->xs_ctup.t_self = itup->t_tid;
@@ -254,8 +254,8 @@ _hash_step(IndexScanDesc scan, Buffer *bufP, ScanDirection dir)
    current = &(scan->currentItemData);
 
    buf = *bufP;
+   _hash_checkpage(rel, buf, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
    page = BufferGetPage(buf);
-   _hash_checkpage(rel, page, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
    opaque = (HashPageOpaque) PageGetSpecialPointer(page);
 
    /*

diff --git a/src/backend/access/hash/hashutil.c b/src/backend/access/hash/hashutil.c
index da0a91630f2282d2216b8cfc02eaa1ab703fb284..34d395c04ea450e04acda002f1666e3e086bf976 100644 (file)
--- a/src/backend/access/hash/hashutil.c
+++ b/src/backend/access/hash/hashutil.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/access/hash/hashutil.c,v 1.42 2005/05/11 01:26:01 neilc Exp $
+ *   $PostgreSQL: pgsql/src/backend/access/hash/hashutil.c,v 1.43 2005/11/06 19:29:00 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -110,12 +110,50 @@ _hash_log2(uint32 num)
  * _hash_checkpage -- sanity checks on the format of all hash pages
  */
 void
-_hash_checkpage(Relation rel, Page page, int flags)
+_hash_checkpage(Relation rel, Buffer buf, int flags)
 {
-   Assert(page);
+   Page        page = BufferGetPage(buf);
 
    /*
-    * When checking the metapage, always verify magic number and version.
+    * ReadBuffer verifies that every newly-read page passes PageHeaderIsValid,
+    * which means it either contains a reasonably sane page header or is
+    * all-zero.  We have to defend against the all-zero case, however.
+    */
+   if (PageIsNew(page))
+       ereport(ERROR,
+               (errcode(ERRCODE_INDEX_CORRUPTED),
+                errmsg("index \"%s\" contains unexpected zero page at block %u",
+                       RelationGetRelationName(rel),
+                       BufferGetBlockNumber(buf)),
+                errhint("Please REINDEX it.")));
+
+   /*
+    * Additionally check that the special area looks sane.
+    */
+   if (((PageHeader) (page))->pd_special !=
+          (BLCKSZ - MAXALIGN(sizeof(HashPageOpaqueData))))
+       ereport(ERROR,
+               (errcode(ERRCODE_INDEX_CORRUPTED),
+                errmsg("index \"%s\" contains corrupted page at block %u",
+                       RelationGetRelationName(rel),
+                       BufferGetBlockNumber(buf)),
+                errhint("Please REINDEX it.")));
+
+   if (flags)
+   {
+       HashPageOpaque opaque = (HashPageOpaque) PageGetSpecialPointer(page);
+
+       if ((opaque->hasho_flag & flags) == 0)
+           ereport(ERROR,
+                   (errcode(ERRCODE_INDEX_CORRUPTED),
+                    errmsg("index \"%s\" contains corrupted page at block %u",
+                           RelationGetRelationName(rel),
+                           BufferGetBlockNumber(buf)),
+                    errhint("Please REINDEX it.")));
+   }
+
+   /*
+    * When checking the metapage, also verify magic number and version.
     */
    if (flags == LH_META_PAGE)
    {
@@ -130,25 +168,8 @@ _hash_checkpage(Relation rel, Page page, int flags)
        if (metap->hashm_version != HASH_VERSION)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
-                    errmsg("index \"%s\" has wrong hash version", RelationGetRelationName(rel)),
+                    errmsg("index \"%s\" has wrong hash version",
+                           RelationGetRelationName(rel)),
                     errhint("Please REINDEX it.")));
    }
-
-   /*
-    * These other checks are for debugging purposes only.
-    */
-#ifdef USE_ASSERT_CHECKING
-   Assert(((PageHeader) (page))->pd_lower >= SizeOfPageHeaderData);
-   Assert(((PageHeader) (page))->pd_upper <=
-          (BLCKSZ - MAXALIGN(sizeof(HashPageOpaqueData))));
-   Assert(((PageHeader) (page))->pd_special ==
-          (BLCKSZ - MAXALIGN(sizeof(HashPageOpaqueData))));
-   Assert(PageGetPageSize(page) == BLCKSZ);
-   if (flags)
-   {
-       HashPageOpaque opaque = (HashPageOpaque) PageGetSpecialPointer(page);
-
-       Assert(opaque->hasho_flag & flags);
-   }
-#endif   /* USE_ASSERT_CHECKING */
 }

diff --git a/src/backend/access/nbtree/nbtinsert.c b/src/backend/access/nbtree/nbtinsert.c
index 33c7612aac5592b2ca6b41ed60d859695fa51424..3ef40a5cb6c96603bf957cc7e5d1ff7061dbcebf 100644 (file)
--- a/src/backend/access/nbtree/nbtinsert.c
+++ b/src/backend/access/nbtree/nbtinsert.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/access/nbtree/nbtinsert.c,v 1.127 2005/10/15 02:49:09 momjian Exp $
+ *   $PostgreSQL: pgsql/src/backend/access/nbtree/nbtinsert.c,v 1.128 2005/11/06 19:29:00 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -672,7 +672,7 @@ _bt_split(Relation rel, Buffer buf, OffsetNumber firstright,
    rightpage = BufferGetPage(rbuf);
 
    _bt_pageinit(leftpage, BufferGetPageSize(buf));
-   _bt_pageinit(rightpage, BufferGetPageSize(rbuf));
+   /* rightpage was already initialized by _bt_getbuf */
 
    /* init btree private data */
    oopaque = (BTPageOpaque) PageGetSpecialPointer(origpage);

diff --git a/src/backend/access/nbtree/nbtpage.c b/src/backend/access/nbtree/nbtpage.c
index 927860030c870ff35d7af9751224660949301a7e..7433c7781046e6feaf3bd6dfc1e5946520aa1612 100644 (file)
--- a/src/backend/access/nbtree/nbtpage.c
+++ b/src/backend/access/nbtree/nbtpage.c
@@ -9,7 +9,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/access/nbtree/nbtpage.c,v 1.88 2005/10/15 02:49:09 momjian Exp $
+ *   $PostgreSQL: pgsql/src/backend/access/nbtree/nbtpage.c,v 1.89 2005/11/06 19:29:00 tgl Exp $
  *
  * NOTES
  *    Postgres btree pages look like ordinary relation pages.  The opaque
@@ -222,8 +222,6 @@ _bt_getroot(Relation rel, int access)
        rootbuf = _bt_getbuf(rel, P_NEW, BT_WRITE);
        rootblkno = BufferGetBlockNumber(rootbuf);
        rootpage = BufferGetPage(rootbuf);
-
-       _bt_pageinit(rootpage, BufferGetPageSize(rootbuf));
        rootopaque = (BTPageOpaque) PageGetSpecialPointer(rootpage);
        rootopaque->btpo_prev = rootopaque->btpo_next = P_NONE;
        rootopaque->btpo_flags = (BTP_LEAF | BTP_ROOT);
@@ -405,14 +403,50 @@ _bt_gettrueroot(Relation rel)
    return rootbuf;
 }
 
+/*
+ * _bt_checkpage() -- Verify that a freshly-read page looks sane.
+ */
+void
+_bt_checkpage(Relation rel, Buffer buf)
+{
+   Page        page = BufferGetPage(buf);
+
+   /*
+    * ReadBuffer verifies that every newly-read page passes PageHeaderIsValid,
+    * which means it either contains a reasonably sane page header or is
+    * all-zero.  We have to defend against the all-zero case, however.
+    */
+   if (PageIsNew(page))
+       ereport(ERROR,
+               (errcode(ERRCODE_INDEX_CORRUPTED),
+                errmsg("index \"%s\" contains unexpected zero page at block %u",
+                       RelationGetRelationName(rel),
+                       BufferGetBlockNumber(buf)),
+                errhint("Please REINDEX it.")));
+
+   /*
+    * Additionally check that the special area looks sane.
+    */
+   if (((PageHeader) (page))->pd_special !=
+       (BLCKSZ - MAXALIGN(sizeof(BTPageOpaqueData))))
+       ereport(ERROR,
+               (errcode(ERRCODE_INDEX_CORRUPTED),
+                errmsg("index \"%s\" contains corrupted page at block %u",
+                       RelationGetRelationName(rel),
+                       BufferGetBlockNumber(buf)),
+                errhint("Please REINDEX it.")));
+}
+
 /*
  * _bt_getbuf() -- Get a buffer by block number for read or write.
  *
- *     blkno == P_NEW means to get an unallocated index page.
+ *     blkno == P_NEW means to get an unallocated index page.  The page
+ *     will be initialized before returning it.
  *
  *     When this routine returns, the appropriate lock is set on the
  *     requested buffer and its reference count has been incremented
- *     (ie, the buffer is "locked and pinned").
+ *     (ie, the buffer is "locked and pinned").  Also, we apply
+ *     _bt_checkpage to sanity-check the page (except in P_NEW case).
  */
 Buffer
 _bt_getbuf(Relation rel, BlockNumber blkno, int access)
@@ -424,6 +458,7 @@ _bt_getbuf(Relation rel, BlockNumber blkno, int access)
        /* Read an existing block of the relation */
        buf = ReadBuffer(rel, blkno);
        LockBuffer(buf, access);
+       _bt_checkpage(rel, buf);
    }
    else
    {
@@ -538,6 +573,7 @@ _bt_relandgetbuf(Relation rel, Buffer obuf, BlockNumber blkno, int access)
        LockBuffer(obuf, BUFFER_LOCK_UNLOCK);
    buf = ReleaseAndReadBuffer(obuf, rel, blkno);
    LockBuffer(buf, access);
+   _bt_checkpage(rel, buf);
    return buf;
 }
 

diff --git a/src/backend/access/nbtree/nbtree.c b/src/backend/access/nbtree/nbtree.c
index 10e2fe6190d35f7959ed7236dc636daeba2aea15..9ddc326bd2f783e386c76688bbde92b13245b45e 100644 (file)
--- a/src/backend/access/nbtree/nbtree.c
+++ b/src/backend/access/nbtree/nbtree.c
@@ -12,7 +12,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/access/nbtree/nbtree.c,v 1.132 2005/10/15 02:49:09 momjian Exp $
+ *   $PostgreSQL: pgsql/src/backend/access/nbtree/nbtree.c,v 1.133 2005/11/06 19:29:00 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -734,8 +734,8 @@ btvacuumcleanup(PG_FUNCTION_ARGS)
     * buffer and it will be fully initialized before we can examine it.  (See
     * also vacuumlazy.c, which has the same issue.)
     *
-    * We can skip locking for new or temp relations, however, since no one else
-    * could be accessing them.
+    * We can skip locking for new or temp relations, however, since no one
+    * else could be accessing them.
     */
    needLock = !RELATION_IS_LOCAL(rel);
 
@@ -772,9 +772,17 @@ btvacuumcleanup(PG_FUNCTION_ARGS)
        Page        page;
        BTPageOpaque opaque;
 
-       buf = _bt_getbuf(rel, blkno, BT_READ);
+       /*
+        * We can't use _bt_getbuf() here because it always applies
+        * _bt_checkpage(), which will barf on an all-zero page.
+        * We want to recycle all-zero pages, not fail.
+        */
+       buf = ReadBuffer(rel, blkno);
+       LockBuffer(buf, BT_READ);
        page = BufferGetPage(buf);
        opaque = (BTPageOpaque) PageGetSpecialPointer(page);
+       if (!PageIsNew(page))
+           _bt_checkpage(rel, buf);
        if (_bt_page_recyclable(page))
        {
            /* Okay to recycle this page */

diff --git a/src/include/access/hash.h b/src/include/access/hash.h
index b433524f7c061ae17b21d7c41da150a4750146d3..f56b609dcf8164833df845447e5d936e1d61a789 100644 (file)
--- a/src/include/access/hash.h
+++ b/src/include/access/hash.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/hash.h,v 1.63 2005/10/15 02:49:42 momjian Exp $
+ * $PostgreSQL: pgsql/src/include/access/hash.h,v 1.64 2005/11/06 19:29:01 tgl Exp $
  *
  * NOTES
  *     modeled after Margo Seltzer's hash implementation for unix.
@@ -310,7 +310,7 @@ extern uint32 _hash_datum2hashkey(Relation rel, Datum key);
 extern Bucket _hash_hashkey2bucket(uint32 hashkey, uint32 maxbucket,
                     uint32 highmask, uint32 lowmask);
 extern uint32 _hash_log2(uint32 num);
-extern void _hash_checkpage(Relation rel, Page page, int flags);
+extern void _hash_checkpage(Relation rel, Buffer buf, int flags);
 
 /* hash.c */
 extern void hash_redo(XLogRecPtr lsn, XLogRecord *record);

diff --git a/src/include/access/nbtree.h b/src/include/access/nbtree.h
index 72f0a02f7757854d37a5a9b1ded106f7e669251d..9cd00d554da41c1fef8845b65cda56eb7e4203dc 100644 (file)
--- a/src/include/access/nbtree.h
+++ b/src/include/access/nbtree.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/nbtree.h,v 1.87 2005/10/15 02:49:42 momjian Exp $
+ * $PostgreSQL: pgsql/src/include/access/nbtree.h,v 1.88 2005/11/06 19:29:01 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -429,6 +429,7 @@ extern void _bt_metapinit(Relation rel);
 extern void _bt_initmetapage(Page page, BlockNumber rootbknum, uint32 level);
 extern Buffer _bt_getroot(Relation rel, int access);
 extern Buffer _bt_gettrueroot(Relation rel);
+extern void _bt_checkpage(Relation rel, Buffer buf);
 extern Buffer _bt_getbuf(Relation rel, BlockNumber blkno, int access);
 extern Buffer _bt_relandgetbuf(Relation rel, Buffer obuf,
                 BlockNumber blkno, int access);