SQLite

Check-in [45362437d4]
Login

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Overview
Comment:Increase the maximum page size from 32k to 64k.
Downloads: Tarball | ZIP archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: 45362437d491fbe0f033a67b398f8ba68cbf1b3b
User & Date: drh 2010-08-12 02:41:12.000
Context
2010-08-12
11:25
Add coverage tests for pager.c. (check-in: 228c5b16af user: dan tags: trunk)
02:41
Increase the maximum page size from 32k to 64k. (check-in: 45362437d4 user: drh tags: trunk)
2010-08-11
18:56
Improve coverage of pager.c. (check-in: 2fa05d01b6 user: dan tags: trunk)
Changes
Unified Diff Ignore Whitespace Patch
Changes to src/btree.c.
1151
1152
1153
1154
1155
1156
1157

1158
1159
1160
1161
1162
1163
1164
1165
1166
1167

1168
1169
1170
1171
1172
1173
1174
  usableSize = pPage->pBt->usableSize;
  assert( nByte < usableSize-8 );

  nFrag = data[hdr+7];
  assert( pPage->cellOffset == hdr + 12 - 4*pPage->leaf );
  gap = pPage->cellOffset + 2*pPage->nCell;
  top = get2byte(&data[hdr+5]);

  if( gap>top ) return SQLITE_CORRUPT_BKPT;
  testcase( gap+2==top );
  testcase( gap+1==top );
  testcase( gap==top );

  if( nFrag>=60 ){
    /* Always defragment highly fragmented pages */
    rc = defragmentPage(pPage);
    if( rc ) return rc;
    top = get2byte(&data[hdr+5]);

  }else if( gap+2<=top ){
    /* Search the freelist looking for a free slot big enough to satisfy 
    ** the request. The allocation is made from the first free slot in 
    ** the list that is large enough to accomadate it.
    */
    int pc, addr;
    for(addr=hdr+1; (pc = get2byte(&data[addr]))>0; addr=pc){







>










>







1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
  usableSize = pPage->pBt->usableSize;
  assert( nByte < usableSize-8 );

  nFrag = data[hdr+7];
  assert( pPage->cellOffset == hdr + 12 - 4*pPage->leaf );
  gap = pPage->cellOffset + 2*pPage->nCell;
  top = get2byte(&data[hdr+5]);
  if( top==0 ) top = 65536;
  if( gap>top ) return SQLITE_CORRUPT_BKPT;
  testcase( gap+2==top );
  testcase( gap+1==top );
  testcase( gap==top );

  if( nFrag>=60 ){
    /* Always defragment highly fragmented pages */
    rc = defragmentPage(pPage);
    if( rc ) return rc;
    top = get2byte(&data[hdr+5]);
    if( top==0 ) top = 65536;
  }else if( gap+2<=top ){
    /* Search the freelist looking for a free slot big enough to satisfy 
    ** the request. The allocation is made from the first free slot in 
    ** the list that is large enough to accomadate it.
    */
    int pc, addr;
    for(addr=hdr+1; (pc = get2byte(&data[addr]))>0; addr=pc){
1203
1204
1205
1206
1207
1208
1209

1210
1211
1212
1213
1214
1215
1216
  ** the allocation.  If not, defragment.
  */
  testcase( gap+2+nByte==top );
  if( gap+2+nByte>top ){
    rc = defragmentPage(pPage);
    if( rc ) return rc;
    top = get2byte(&data[hdr+5]);

    assert( gap+nByte<=top );
  }


  /* Allocate memory from the gap in between the cell pointer array
  ** and the cell content area.  The btreeInitPage() call has already
  ** validated the freelist.  Given that the freelist is valid, there







>







1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
  ** the allocation.  If not, defragment.
  */
  testcase( gap+2+nByte==top );
  if( gap+2+nByte>top ){
    rc = defragmentPage(pPage);
    if( rc ) return rc;
    top = get2byte(&data[hdr+5]);
    if( top==0 ) top = 65536;
    assert( gap+nByte<=top );
  }


  /* Allocate memory from the gap in between the cell pointer array
  ** and the cell content area.  The btreeInitPage() call has already
  ** validated the freelist.  Given that the freelist is valid, there
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392

1393
1394
1395
1396
1397
1398
1399
  assert( pPage->aData == sqlite3PagerGetData(pPage->pDbPage) );

  if( !pPage->isInit ){
    u16 pc;            /* Address of a freeblock within pPage->aData[] */
    u8 hdr;            /* Offset to beginning of page header */
    u8 *data;          /* Equal to pPage->aData */
    BtShared *pBt;        /* The main btree structure */
    u16 usableSize;    /* Amount of usable space on each page */
    u16 cellOffset;    /* Offset from start of page to first cell pointer */
    u16 nFree;         /* Number of unused bytes on the page */
    u16 top;           /* First byte of the cell content area */
    int iCellFirst;    /* First allowable cell or freeblock offset */
    int iCellLast;     /* Last possible cell or freeblock offset */

    pBt = pPage->pBt;

    hdr = pPage->hdrOffset;
    data = pPage->aData;
    if( decodeFlags(pPage, data[hdr]) ) return SQLITE_CORRUPT_BKPT;
    assert( pBt->pageSize>=512 && pBt->pageSize<=32768 );
    pPage->maskPage = pBt->pageSize - 1;
    pPage->nOverflow = 0;
    usableSize = pBt->usableSize;
    pPage->cellOffset = cellOffset = hdr + 12 - 4*pPage->leaf;
    top = get2byte(&data[hdr+5]);

    pPage->nCell = get2byte(&data[hdr+3]);
    if( pPage->nCell>MX_CELL(pBt) ){
      /* To many cells for a single page.  The page must be corrupt */
      return SQLITE_CORRUPT_BKPT;
    }
    testcase( pPage->nCell==MX_CELL(pBt) );








|
|
|
|








|
|




>







1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
  assert( pPage->aData == sqlite3PagerGetData(pPage->pDbPage) );

  if( !pPage->isInit ){
    u16 pc;            /* Address of a freeblock within pPage->aData[] */
    u8 hdr;            /* Offset to beginning of page header */
    u8 *data;          /* Equal to pPage->aData */
    BtShared *pBt;        /* The main btree structure */
    int usableSize;    /* Amount of usable space on each page */
    int cellOffset;    /* Offset from start of page to first cell pointer */
    int nFree;         /* Number of unused bytes on the page */
    int top;           /* First byte of the cell content area */
    int iCellFirst;    /* First allowable cell or freeblock offset */
    int iCellLast;     /* Last possible cell or freeblock offset */

    pBt = pPage->pBt;

    hdr = pPage->hdrOffset;
    data = pPage->aData;
    if( decodeFlags(pPage, data[hdr]) ) return SQLITE_CORRUPT_BKPT;
    assert( pBt->pageSize>=512 && pBt->pageSize<=65536 );
    pPage->maskPage = (u16)(pBt->pageSize - 1);
    pPage->nOverflow = 0;
    usableSize = pBt->usableSize;
    pPage->cellOffset = cellOffset = hdr + 12 - 4*pPage->leaf;
    top = get2byte(&data[hdr+5]);
    if( top==0 ) top = 65536;
    pPage->nCell = get2byte(&data[hdr+3]);
    if( pPage->nCell>MX_CELL(pBt) ){
      /* To many cells for a single page.  The page must be corrupt */
      return SQLITE_CORRUPT_BKPT;
    }
    testcase( pPage->nCell==MX_CELL(pBt) );

1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
  data[hdr+7] = 0;
  put2byte(&data[hdr+5], pBt->usableSize);
  pPage->nFree = pBt->usableSize - first;
  decodeFlags(pPage, flags);
  pPage->hdrOffset = hdr;
  pPage->cellOffset = first;
  pPage->nOverflow = 0;
  assert( pBt->pageSize>=512 && pBt->pageSize<=32768 );
  pPage->maskPage = pBt->pageSize - 1;
  pPage->nCell = 0;
  pPage->isInit = 1;
}


/*
** Convert a DbPage obtained from the pager into a MemPage used by







|
|







1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
  data[hdr+7] = 0;
  put2byte(&data[hdr+5], pBt->usableSize);
  pPage->nFree = pBt->usableSize - first;
  decodeFlags(pPage, flags);
  pPage->hdrOffset = hdr;
  pPage->cellOffset = first;
  pPage->nOverflow = 0;
  assert( pBt->pageSize>=512 && pBt->pageSize<=65536 );
  pPage->maskPage = (u16)(pBt->pageSize - 1);
  pPage->nCell = 0;
  pPage->isInit = 1;
}


/*
** Convert a DbPage obtained from the pager into a MemPage used by
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
  
    pBt->pCursor = 0;
    pBt->pPage1 = 0;
    pBt->readOnly = sqlite3PagerIsreadonly(pBt->pPager);
#ifdef SQLITE_SECURE_DELETE
    pBt->secureDelete = 1;
#endif
    pBt->pageSize = get2byte(&zDbHeader[16]);
    if( pBt->pageSize<512 || pBt->pageSize>SQLITE_MAX_PAGE_SIZE
         || ((pBt->pageSize-1)&pBt->pageSize)!=0 ){
      pBt->pageSize = 0;
#ifndef SQLITE_OMIT_AUTOVACUUM
      /* If the magic name ":memory:" will create an in-memory database, then
      ** leave the autoVacuum mode at 0 (do not auto-vacuum), even if
      ** SQLITE_DEFAULT_AUTOVACUUM is true. On the other hand, if







|







1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
  
    pBt->pCursor = 0;
    pBt->pPage1 = 0;
    pBt->readOnly = sqlite3PagerIsreadonly(pBt->pPager);
#ifdef SQLITE_SECURE_DELETE
    pBt->secureDelete = 1;
#endif
    pBt->pageSize = (zDbHeader[16]<<8) | (zDbHeader[17]<<16);
    if( pBt->pageSize<512 || pBt->pageSize>SQLITE_MAX_PAGE_SIZE
         || ((pBt->pageSize-1)&pBt->pageSize)!=0 ){
      pBt->pageSize = 0;
#ifndef SQLITE_OMIT_AUTOVACUUM
      /* If the magic name ":memory:" will create an in-memory database, then
      ** leave the autoVacuum mode at 0 (do not auto-vacuum), even if
      ** SQLITE_DEFAULT_AUTOVACUUM is true. On the other hand, if
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
    nReserve = pBt->pageSize - pBt->usableSize;
  }
  assert( nReserve>=0 && nReserve<=255 );
  if( pageSize>=512 && pageSize<=SQLITE_MAX_PAGE_SIZE &&
        ((pageSize-1)&pageSize)==0 ){
    assert( (pageSize & 7)==0 );
    assert( !pBt->pPage1 && !pBt->pCursor );
    pBt->pageSize = (u16)pageSize;
    freeTempSpace(pBt);
  }
  rc = sqlite3PagerSetPagesize(pBt->pPager, &pBt->pageSize, nReserve);
  pBt->usableSize = pBt->pageSize - (u16)nReserve;
  if( iFix ) pBt->pageSizeFixed = 1;
  sqlite3BtreeLeave(p);
  return rc;







|







2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
    nReserve = pBt->pageSize - pBt->usableSize;
  }
  assert( nReserve>=0 && nReserve<=255 );
  if( pageSize>=512 && pageSize<=SQLITE_MAX_PAGE_SIZE &&
        ((pageSize-1)&pageSize)==0 ){
    assert( (pageSize & 7)==0 );
    assert( !pBt->pPage1 && !pBt->pCursor );
    pBt->pageSize = (u32)pageSize;
    freeTempSpace(pBt);
  }
  rc = sqlite3PagerSetPagesize(pBt->pPager, &pBt->pageSize, nReserve);
  pBt->usableSize = pBt->pageSize - (u16)nReserve;
  if( iFix ) pBt->pageSizeFixed = 1;
  sqlite3BtreeLeave(p);
  return rc;
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315

2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
    ** embedded fraction must be 12.5% for both leaf-data and non-leaf-data.
    ** The original design allowed these amounts to vary, but as of
    ** version 3.6.0, we require them to be fixed.
    */
    if( memcmp(&page1[21], "\100\040\040",3)!=0 ){
      goto page1_init_failed;
    }
    pageSize = get2byte(&page1[16]);
    if( ((pageSize-1)&pageSize)!=0 || pageSize<512 ||
        (SQLITE_MAX_PAGE_SIZE<32768 && pageSize>SQLITE_MAX_PAGE_SIZE)

    ){
      goto page1_init_failed;
    }
    assert( (pageSize & 7)==0 );
    usableSize = pageSize - page1[20];
    if( pageSize!=pBt->pageSize ){
      /* After reading the first page of the database assuming a page size
      ** of BtShared.pageSize, we have discovered that the page-size is
      ** actually pageSize. Unlock the database, leave pBt->pPage1 at
      ** zero and return SQLITE_OK. The caller will call this function
      ** again with the correct page-size.
      */
      releasePage(pPage1);
      pBt->usableSize = (u16)usableSize;
      pBt->pageSize = (u16)pageSize;
      freeTempSpace(pBt);
      rc = sqlite3PagerSetPagesize(pBt->pPager, &pBt->pageSize,
                                   pageSize-usableSize);
      return rc;
    }
    if( nPageHeader>nPageFile ){
      rc = SQLITE_CORRUPT_BKPT;
      goto page1_init_failed;
    }
    if( usableSize<480 ){
      goto page1_init_failed;
    }
    pBt->pageSize = (u16)pageSize;
    pBt->usableSize = (u16)usableSize;
#ifndef SQLITE_OMIT_AUTOVACUUM
    pBt->autoVacuum = (get4byte(&page1[36 + 4*4])?1:0);
    pBt->incrVacuum = (get4byte(&page1[36 + 7*4])?1:0);
#endif
  }

  /* maxLocal is the maximum amount of payload to store locally for







|
|
|
>













|
|












|
|







2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
    ** embedded fraction must be 12.5% for both leaf-data and non-leaf-data.
    ** The original design allowed these amounts to vary, but as of
    ** version 3.6.0, we require them to be fixed.
    */
    if( memcmp(&page1[21], "\100\040\040",3)!=0 ){
      goto page1_init_failed;
    }
    pageSize = (page1[16]<<8) | (page1[17]<<16);
    if( ((pageSize-1)&pageSize)!=0
     || pageSize>SQLITE_MAX_PAGE_SIZE 
     || pageSize<=256 
    ){
      goto page1_init_failed;
    }
    assert( (pageSize & 7)==0 );
    usableSize = pageSize - page1[20];
    if( pageSize!=pBt->pageSize ){
      /* After reading the first page of the database assuming a page size
      ** of BtShared.pageSize, we have discovered that the page-size is
      ** actually pageSize. Unlock the database, leave pBt->pPage1 at
      ** zero and return SQLITE_OK. The caller will call this function
      ** again with the correct page-size.
      */
      releasePage(pPage1);
      pBt->usableSize = (u32)usableSize;
      pBt->pageSize = (u32)pageSize;
      freeTempSpace(pBt);
      rc = sqlite3PagerSetPagesize(pBt->pPager, &pBt->pageSize,
                                   pageSize-usableSize);
      return rc;
    }
    if( nPageHeader>nPageFile ){
      rc = SQLITE_CORRUPT_BKPT;
      goto page1_init_failed;
    }
    if( usableSize<480 ){
      goto page1_init_failed;
    }
    pBt->pageSize = (u32)pageSize;
    pBt->usableSize = (u32)usableSize;
#ifndef SQLITE_OMIT_AUTOVACUUM
    pBt->autoVacuum = (get4byte(&page1[36 + 4*4])?1:0);
    pBt->incrVacuum = (get4byte(&page1[36 + 7*4])?1:0);
#endif
  }

  /* maxLocal is the maximum amount of payload to store locally for
2413
2414
2415
2416
2417
2418
2419
2420

2421
2422
2423
2424
2425
2426
2427
  pP1 = pBt->pPage1;
  assert( pP1!=0 );
  data = pP1->aData;
  rc = sqlite3PagerWrite(pP1->pDbPage);
  if( rc ) return rc;
  memcpy(data, zMagicHeader, sizeof(zMagicHeader));
  assert( sizeof(zMagicHeader)==16 );
  put2byte(&data[16], pBt->pageSize);

  data[18] = 1;
  data[19] = 1;
  assert( pBt->usableSize<=pBt->pageSize && pBt->usableSize+255>=pBt->pageSize);
  data[20] = (u8)(pBt->pageSize - pBt->usableSize);
  data[21] = 64;
  data[22] = 32;
  data[23] = 32;







|
>







2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
  pP1 = pBt->pPage1;
  assert( pP1!=0 );
  data = pP1->aData;
  rc = sqlite3PagerWrite(pP1->pDbPage);
  if( rc ) return rc;
  memcpy(data, zMagicHeader, sizeof(zMagicHeader));
  assert( sizeof(zMagicHeader)==16 );
  data[16] = (pBt->pageSize>>8)&0xff;
  data[17] = (pBt->pageSize>>16)&0xff;
  data[18] = 1;
  data[19] = 1;
  assert( pBt->usableSize<=pBt->pageSize && pBt->usableSize+255>=pBt->pageSize);
  data[20] = (u8)(pBt->pageSize - pBt->usableSize);
  data[21] = 64;
  data[22] = 32;
  data[23] = 32;
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
        }else{
          assert( nCellKey>intKey );
          c = +1;
        }
        pCur->validNKey = 1;
        pCur->info.nKey = nCellKey;
      }else{
        /* The maximum supported page-size is 32768 bytes. This means that
        ** the maximum number of record bytes stored on an index B-Tree
        ** page is at most 8198 bytes, which may be stored as a 2-byte
        ** varint. This information is used to attempt to avoid parsing 
        ** the entire cell by checking for the cases where the record is 
        ** stored entirely within the b-tree page by inspecting the first 
        ** 2 bytes of the cell.
        */
        int nCell = pCell[0];
        if( !(nCell & 0x80) && nCell<=pPage->maxLocal ){







|

|







4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
        }else{
          assert( nCellKey>intKey );
          c = +1;
        }
        pCur->validNKey = 1;
        pCur->info.nKey = nCellKey;
      }else{
        /* The maximum supported page-size is 65536 bytes. This means that
        ** the maximum number of record bytes stored on an index B-Tree
        ** page is less than 16384 bytes and may be stored as a 2-byte
        ** varint. This information is used to attempt to avoid parsing 
        ** the entire cell by checking for the cases where the record is 
        ** stored entirely within the b-tree page by inspecting the first 
        ** 2 bytes of the cell.
        */
        int nCell = pCell[0];
        if( !(nCell & 0x80) && nCell<=pPage->maxLocal ){
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
  u8 *ptr;          /* Used for moving information around in data[] */

  int nSkip = (iChild ? 4 : 0);

  if( *pRC ) return;

  assert( i>=0 && i<=pPage->nCell+pPage->nOverflow );
  assert( pPage->nCell<=MX_CELL(pPage->pBt) && MX_CELL(pPage->pBt)<=5460 );
  assert( pPage->nOverflow<=ArraySize(pPage->aOvfl) );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  /* The cell should normally be sized correctly.  However, when moving a
  ** malformed cell from a leaf page to an interior page, if the cell size
  ** wanted to be less than 4 but got rounded up to 4 on the leaf, then size
  ** might be less than 8 (leaf-size + pointer) on the interior node.  Hence
  ** the term after the || in the following assert(). */







|







5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
  u8 *ptr;          /* Used for moving information around in data[] */

  int nSkip = (iChild ? 4 : 0);

  if( *pRC ) return;

  assert( i>=0 && i<=pPage->nCell+pPage->nOverflow );
  assert( pPage->nCell<=MX_CELL(pPage->pBt) && MX_CELL(pPage->pBt)<=10921 );
  assert( pPage->nOverflow<=ArraySize(pPage->aOvfl) );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  /* The cell should normally be sized correctly.  However, when moving a
  ** malformed cell from a leaf page to an interior page, if the cell size
  ** wanted to be less than 4 but got rounded up to 4 on the leaf, then size
  ** might be less than 8 (leaf-size + pointer) on the interior node.  Hence
  ** the term after the || in the following assert(). */
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
  int cellbody;     /* Address of next cell body */
  u8 * const data = pPage->aData;             /* Pointer to data for pPage */
  const int hdr = pPage->hdrOffset;           /* Offset of header on pPage */
  const int nUsable = pPage->pBt->usableSize; /* Usable size of page */

  assert( pPage->nOverflow==0 );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  assert( nCell>=0 && nCell<=MX_CELL(pPage->pBt) && MX_CELL(pPage->pBt)<=5460 );
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );

  /* Check that the page has just been zeroed by zeroPage() */
  assert( pPage->nCell==0 );
  assert( get2byte(&data[hdr+5])==nUsable );

  pCellptr = &data[pPage->cellOffset + nCell*2];
  cellbody = nUsable;
  for(i=nCell-1; i>=0; i--){
    pCellptr -= 2;
    cellbody -= aSize[i];
    put2byte(pCellptr, cellbody);







|




|







5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
  int cellbody;     /* Address of next cell body */
  u8 * const data = pPage->aData;             /* Pointer to data for pPage */
  const int hdr = pPage->hdrOffset;           /* Offset of header on pPage */
  const int nUsable = pPage->pBt->usableSize; /* Usable size of page */

  assert( pPage->nOverflow==0 );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  assert( nCell>=0 && nCell<=MX_CELL(pPage->pBt) && MX_CELL(pPage->pBt)<=10921);
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );

  /* Check that the page has just been zeroed by zeroPage() */
  assert( pPage->nCell==0 );
  assert( get2byte(&data[hdr+5])==(nUsable&0xffff) );

  pCellptr = &data[pPage->cellOffset + nCell*2];
  cellbody = nUsable;
  for(i=nCell-1; i>=0; i--){
    pCellptr -= 2;
    cellbody -= aSize[i];
    put2byte(pCellptr, cellbody);
7655
7656
7657
7658
7659
7660
7661
7662

7663
7664
7665
7666
7667
7668
7669
  */
  data = pPage->aData;
  hdr = pPage->hdrOffset;
  hit = sqlite3PageMalloc( pBt->pageSize );
  if( hit==0 ){
    pCheck->mallocFailed = 1;
  }else{
    u16 contentOffset = get2byte(&data[hdr+5]);

    assert( contentOffset<=usableSize );  /* Enforced by btreeInitPage() */
    memset(hit+contentOffset, 0, usableSize-contentOffset);
    memset(hit, 1, contentOffset);
    nCell = get2byte(&data[hdr+3]);
    cellStart = hdr + 12 - 4*pPage->leaf;
    for(i=0; i<nCell; i++){
      int pc = get2byte(&data[cellStart+i*2]);







|
>







7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
  */
  data = pPage->aData;
  hdr = pPage->hdrOffset;
  hit = sqlite3PageMalloc( pBt->pageSize );
  if( hit==0 ){
    pCheck->mallocFailed = 1;
  }else{
    int contentOffset = get2byte(&data[hdr+5]);
    if( contentOffset==0 ) contentOffset = 65536;
    assert( contentOffset<=usableSize );  /* Enforced by btreeInitPage() */
    memset(hit+contentOffset, 0, usableSize-contentOffset);
    memset(hit, 1, contentOffset);
    nCell = get2byte(&data[hdr+3]);
    cellStart = hdr + 12 - 4*pPage->leaf;
    for(i=0; i<nCell; i++){
      int pc = get2byte(&data[cellStart+i*2]);
Changes to src/btreeInt.h.
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
** page has a small header which contains the Ptr(N) pointer and other
** information such as the size of key and data.
**
** FORMAT DETAILS
**
** The file is divided into pages.  The first page is called page 1,
** the second is page 2, and so forth.  A page number of zero indicates
** "no such page".  The page size can be any power of 2 between 512 and 32768.
** Each page can be either a btree page, a freelist page, an overflow
** page, or a pointer-map page.
**
** The first page is always a btree page.  The first 100 bytes of the first
** page contain a special header (the "file header") that describes the file.
** The format of the file header is as follows:
**







|







42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
** page has a small header which contains the Ptr(N) pointer and other
** information such as the size of key and data.
**
** FORMAT DETAILS
**
** The file is divided into pages.  The first page is called page 1,
** the second is page 2, and so forth.  A page number of zero indicates
** "no such page".  The page size can be any power of 2 between 512 and 65536.
** Each page can be either a btree page, a freelist page, an overflow
** page, or a pointer-map page.
**
** The first page is always a btree page.  The first 100 bytes of the first
** page contain a special header (the "file header") that describes the file.
** The format of the file header is as follows:
**
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423


424
425
426
427
428
429
430
  u8 pageSizeFixed;     /* True if the page size can no longer be changed */
  u8 secureDelete;      /* True if secure_delete is enabled */
  u8 initiallyEmpty;    /* Database is empty at start of transaction */
#ifndef SQLITE_OMIT_AUTOVACUUM
  u8 autoVacuum;        /* True if auto-vacuum is enabled */
  u8 incrVacuum;        /* True if incr-vacuum is enabled */
#endif
  u16 pageSize;         /* Total number of bytes on a page */
  u16 usableSize;       /* Number of usable bytes on each page */
  u16 maxLocal;         /* Maximum local payload in non-LEAFDATA tables */
  u16 minLocal;         /* Minimum local payload in non-LEAFDATA tables */
  u16 maxLeaf;          /* Maximum local payload in a LEAFDATA table */
  u16 minLeaf;          /* Minimum local payload in a LEAFDATA table */
  u8 inTransaction;     /* Transaction state */
  u8 doNotUseWAL;       /* If true, do not open write-ahead-log file */


  int nTransaction;     /* Number of open transactions (read + write) */
  u32 nPage;            /* Number of pages in the database */
  void *pSchema;        /* Pointer to space allocated by sqlite3BtreeSchema() */
  void (*xFreeSchema)(void*);  /* Destructor for BtShared.pSchema */
  sqlite3_mutex *mutex; /* Non-recursive mutex required to access this struct */
  Bitvec *pHasContent;  /* Set of pages moved to free-list this transaction */
#ifndef SQLITE_OMIT_SHARED_CACHE







<
<






>
>







409
410
411
412
413
414
415


416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
  u8 pageSizeFixed;     /* True if the page size can no longer be changed */
  u8 secureDelete;      /* True if secure_delete is enabled */
  u8 initiallyEmpty;    /* Database is empty at start of transaction */
#ifndef SQLITE_OMIT_AUTOVACUUM
  u8 autoVacuum;        /* True if auto-vacuum is enabled */
  u8 incrVacuum;        /* True if incr-vacuum is enabled */
#endif


  u16 maxLocal;         /* Maximum local payload in non-LEAFDATA tables */
  u16 minLocal;         /* Minimum local payload in non-LEAFDATA tables */
  u16 maxLeaf;          /* Maximum local payload in a LEAFDATA table */
  u16 minLeaf;          /* Minimum local payload in a LEAFDATA table */
  u8 inTransaction;     /* Transaction state */
  u8 doNotUseWAL;       /* If true, do not open write-ahead-log file */
  u32 pageSize;         /* Total number of bytes on a page */
  u32 usableSize;       /* Number of usable bytes on each page */
  int nTransaction;     /* Number of open transactions (read + write) */
  u32 nPage;            /* Number of pages in the database */
  void *pSchema;        /* Pointer to space allocated by sqlite3BtreeSchema() */
  void (*xFreeSchema)(void*);  /* Destructor for BtShared.pSchema */
  sqlite3_mutex *mutex; /* Non-recursive mutex required to access this struct */
  Bitvec *pHasContent;  /* Set of pages moved to free-list this transaction */
#ifndef SQLITE_OMIT_SHARED_CACHE
Changes to src/pager.c.
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
  ){
    return rc;
  }

  if( pPager->journalOff==0 ){
    u32 iPageSize;               /* Page-size field of journal header */
    u32 iSectorSize;             /* Sector-size field of journal header */
    u16 iPageSize16;             /* Copy of iPageSize in 16-bit variable */

    /* Read the page-size and sector-size journal header fields. */
    if( SQLITE_OK!=(rc = read32bits(pPager->jfd, iHdrOff+20, &iSectorSize))
     || SQLITE_OK!=(rc = read32bits(pPager->jfd, iHdrOff+24, &iPageSize))
    ){
      return rc;
    }







<







1501
1502
1503
1504
1505
1506
1507

1508
1509
1510
1511
1512
1513
1514
  ){
    return rc;
  }

  if( pPager->journalOff==0 ){
    u32 iPageSize;               /* Page-size field of journal header */
    u32 iSectorSize;             /* Sector-size field of journal header */


    /* Read the page-size and sector-size journal header fields. */
    if( SQLITE_OK!=(rc = read32bits(pPager->jfd, iHdrOff+20, &iSectorSize))
     || SQLITE_OK!=(rc = read32bits(pPager->jfd, iHdrOff+24, &iPageSize))
    ){
      return rc;
    }
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
      return SQLITE_DONE;
    }

    /* Update the page-size to match the value read from the journal. 
    ** Use a testcase() macro to make sure that malloc failure within 
    ** PagerSetPagesize() is tested.
    */
    iPageSize16 = (u16)iPageSize;
    rc = sqlite3PagerSetPagesize(pPager, &iPageSize16, -1);
    testcase( rc!=SQLITE_OK );
    assert( rc!=SQLITE_OK || iPageSize16==(u16)iPageSize );

    /* Update the assumed sector-size to match the value used by 
    ** the process that created this journal. If this journal was
    ** created by a process other than this one, then this routine
    ** is being called from within pager_playback(). The local value
    ** of Pager.sectorSize is restored at the end of that routine.
    */







<
|

<







1530
1531
1532
1533
1534
1535
1536

1537
1538

1539
1540
1541
1542
1543
1544
1545
      return SQLITE_DONE;
    }

    /* Update the page-size to match the value read from the journal. 
    ** Use a testcase() macro to make sure that malloc failure within 
    ** PagerSetPagesize() is tested.
    */

    rc = sqlite3PagerSetPagesize(pPager, &iPageSize, -1);
    testcase( rc!=SQLITE_OK );


    /* Update the assumed sector-size to match the value used by 
    ** the process that created this journal. If this journal was
    ** created by a process other than this one, then this routine
    ** is being called from within pager_playback(). The local value
    ** of Pager.sectorSize is restored at the end of that routine.
    */
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
** In all other cases, SQLITE_OK is returned.
**
** If the page size is not changed, either because one of the enumerated
** conditions above is not true, the pager was in error state when this
** function was called, or because the memory allocation attempt failed, 
** then *pPageSize is set to the old, retained page size before returning.
*/
int sqlite3PagerSetPagesize(Pager *pPager, u16 *pPageSize, int nReserve){
  /* It is not possible to do a full assert_pager_state() here, as this
  ** function may be called from within PagerOpen(), before the state
  ** of the Pager object is internally consistent.
  **
  ** At one point this function returned an error if the pager was in 
  ** PAGER_ERROR state. But since PAGER_ERROR state guarantees that
  ** there is at least one outstanding page reference, this function
  ** is a no-op for that case anyhow.
  */

  u16 pageSize = *pPageSize;
  assert( pageSize==0 || (pageSize>=512 && pageSize<=SQLITE_MAX_PAGE_SIZE) );
  if( (pPager->memDb==0 || pPager->dbSize==0)
   && sqlite3PcacheRefCount(pPager->pPCache)==0 
   && pageSize && pageSize!=pPager->pageSize 
  ){
    char *pNew;                 /* New temp space */
    i64 nByte = 0;







|










|







3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
** In all other cases, SQLITE_OK is returned.
**
** If the page size is not changed, either because one of the enumerated
** conditions above is not true, the pager was in error state when this
** function was called, or because the memory allocation attempt failed, 
** then *pPageSize is set to the old, retained page size before returning.
*/
int sqlite3PagerSetPagesize(Pager *pPager, u32 *pPageSize, int nReserve){
  /* It is not possible to do a full assert_pager_state() here, as this
  ** function may be called from within PagerOpen(), before the state
  ** of the Pager object is internally consistent.
  **
  ** At one point this function returned an error if the pager was in 
  ** PAGER_ERROR state. But since PAGER_ERROR state guarantees that
  ** there is at least one outstanding page reference, this function
  ** is a no-op for that case anyhow.
  */

  u32 pageSize = *pPageSize;
  assert( pageSize==0 || (pageSize>=512 && pageSize<=SQLITE_MAX_PAGE_SIZE) );
  if( (pPager->memDb==0 || pPager->dbSize==0)
   && sqlite3PcacheRefCount(pPager->pPCache)==0 
   && pageSize && pageSize!=pPager->pageSize 
  ){
    char *pNew;                 /* New temp space */
    i64 nByte = 0;
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
      pPager->pageSize = pageSize;
      sqlite3PageFree(pPager->pTmpSpace);
      pPager->pTmpSpace = pNew;
      sqlite3PcacheSetPageSize(pPager->pPCache, pageSize);
    }
  }

  *pPageSize = (u16)pPager->pageSize;
  if( nReserve<0 ) nReserve = pPager->nReserve;
  assert( nReserve>=0 && nReserve<1000 );
  pPager->nReserve = (i16)nReserve;
  pagerReportSize(pPager);
  return SQLITE_OK;
}








|







3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
      pPager->pageSize = pageSize;
      sqlite3PageFree(pPager->pTmpSpace);
      pPager->pTmpSpace = pNew;
      sqlite3PcacheSetPageSize(pPager->pPCache, pageSize);
    }
  }

  *pPageSize = pPager->pageSize;
  if( nReserve<0 ) nReserve = pPager->nReserve;
  assert( nReserve>=0 && nReserve<1000 );
  pPager->nReserve = (i16)nReserve;
  pagerReportSize(pPager);
  return SQLITE_OK;
}

4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
  int readOnly = 0;        /* True if this is a read-only file */
  int journalFileSize;     /* Bytes to allocate for each journal fd */
  char *zPathname = 0;     /* Full path to database file */
  int nPathname = 0;       /* Number of bytes in zPathname */
  int useJournal = (flags & PAGER_OMIT_JOURNAL)==0; /* False to omit journal */
  int noReadlock = (flags & PAGER_NO_READLOCK)!=0;  /* True to omit read-lock */
  int pcacheSize = sqlite3PcacheSize();       /* Bytes to allocate for PCache */
  u16 szPageDflt = SQLITE_DEFAULT_PAGE_SIZE;  /* Default page size */

  /* Figure out how much space is required for each journal file-handle
  ** (there are two of them, the main journal and the sub-journal). This
  ** is the maximum space required for an in-memory journal file handle 
  ** and a regular journal file-handle. Note that a "regular journal-handle"
  ** may be a wrapper capable of caching the first portion of the journal
  ** file in memory to implement the atomic-write optimization (see 







|







4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
  int readOnly = 0;        /* True if this is a read-only file */
  int journalFileSize;     /* Bytes to allocate for each journal fd */
  char *zPathname = 0;     /* Full path to database file */
  int nPathname = 0;       /* Number of bytes in zPathname */
  int useJournal = (flags & PAGER_OMIT_JOURNAL)==0; /* False to omit journal */
  int noReadlock = (flags & PAGER_NO_READLOCK)!=0;  /* True to omit read-lock */
  int pcacheSize = sqlite3PcacheSize();       /* Bytes to allocate for PCache */
  u32 szPageDflt = SQLITE_DEFAULT_PAGE_SIZE;  /* Default page size */

  /* Figure out how much space is required for each journal file-handle
  ** (there are two of them, the main journal and the sub-journal). This
  ** is the maximum space required for an in-memory journal file handle 
  ** and a regular journal file-handle. Note that a "regular journal-handle"
  ** may be a wrapper capable of caching the first portion of the journal
  ** file in memory to implement the atomic-write optimization (see 
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
    if( rc==SQLITE_OK && !readOnly ){
      setSectorSize(pPager);
      assert(SQLITE_DEFAULT_PAGE_SIZE<=SQLITE_MAX_DEFAULT_PAGE_SIZE);
      if( szPageDflt<pPager->sectorSize ){
        if( pPager->sectorSize>SQLITE_MAX_DEFAULT_PAGE_SIZE ){
          szPageDflt = SQLITE_MAX_DEFAULT_PAGE_SIZE;
        }else{
          szPageDflt = (u16)pPager->sectorSize;
        }
      }
#ifdef SQLITE_ENABLE_ATOMIC_WRITE
      {
        int iDc = sqlite3OsDeviceCharacteristics(pPager->fd);
        int ii;
        assert(SQLITE_IOCAP_ATOMIC512==(512>>8));







|







4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
    if( rc==SQLITE_OK && !readOnly ){
      setSectorSize(pPager);
      assert(SQLITE_DEFAULT_PAGE_SIZE<=SQLITE_MAX_DEFAULT_PAGE_SIZE);
      if( szPageDflt<pPager->sectorSize ){
        if( pPager->sectorSize>SQLITE_MAX_DEFAULT_PAGE_SIZE ){
          szPageDflt = SQLITE_MAX_DEFAULT_PAGE_SIZE;
        }else{
          szPageDflt = (u32)pPager->sectorSize;
        }
      }
#ifdef SQLITE_ENABLE_ATOMIC_WRITE
      {
        int iDc = sqlite3OsDeviceCharacteristics(pPager->fd);
        int ii;
        assert(SQLITE_IOCAP_ATOMIC512==(512>>8));
Changes to src/pager.h.
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
  void(*)(DbPage*)
);
int sqlite3PagerClose(Pager *pPager);
int sqlite3PagerReadFileheader(Pager*, int, unsigned char*);

/* Functions used to configure a Pager object. */
void sqlite3PagerSetBusyhandler(Pager*, int(*)(void *), void *);
int sqlite3PagerSetPagesize(Pager*, u16*, int);
int sqlite3PagerMaxPageCount(Pager*, int);
void sqlite3PagerSetCachesize(Pager*, int);
void sqlite3PagerSetSafetyLevel(Pager*,int,int);
int sqlite3PagerLockingMode(Pager *, int);
int sqlite3PagerSetJournalMode(Pager *, int);
int sqlite3PagerGetJournalMode(Pager*);
int sqlite3PagerOkToChangeJournalMode(Pager*);







|







95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
  void(*)(DbPage*)
);
int sqlite3PagerClose(Pager *pPager);
int sqlite3PagerReadFileheader(Pager*, int, unsigned char*);

/* Functions used to configure a Pager object. */
void sqlite3PagerSetBusyhandler(Pager*, int(*)(void *), void *);
int sqlite3PagerSetPagesize(Pager*, u32*, int);
int sqlite3PagerMaxPageCount(Pager*, int);
void sqlite3PagerSetCachesize(Pager*, int);
void sqlite3PagerSetSafetyLevel(Pager*,int,int);
int sqlite3PagerLockingMode(Pager *, int);
int sqlite3PagerSetJournalMode(Pager *, int);
int sqlite3PagerGetJournalMode(Pager*);
int sqlite3PagerOkToChangeJournalMode(Pager*);
Changes to src/sqliteLimit.h.
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
/*
** The maximum value of a ?nnn wildcard that the parser will accept.
*/
#ifndef SQLITE_MAX_VARIABLE_NUMBER
# define SQLITE_MAX_VARIABLE_NUMBER 999
#endif

/* Maximum page size.  The upper bound on this value is 32768.  This a limit
** imposed by the necessity of storing the value in a 2-byte unsigned integer
** and the fact that the page size must be a power of 2.
**
** If this limit is changed, then the compiled library is technically
** incompatible with an SQLite library compiled with a different limit. If
** a process operating on a database with a page-size of 65536 bytes 
** crashes, then an instance of SQLite compiled with the default page-size 
** limit will not be able to rollback the aborted transaction. This could
** lead to database corruption.
*/
#ifndef SQLITE_MAX_PAGE_SIZE
# define SQLITE_MAX_PAGE_SIZE 32768
#endif


/*
** The default size of a database page.
*/
#ifndef SQLITE_DEFAULT_PAGE_SIZE







|
|
<









|







129
130
131
132
133
134
135
136
137

138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
/*
** The maximum value of a ?nnn wildcard that the parser will accept.
*/
#ifndef SQLITE_MAX_VARIABLE_NUMBER
# define SQLITE_MAX_VARIABLE_NUMBER 999
#endif

/* Maximum page size.  The upper bound on this value is 65536.  This a limit
** imposed by the use of 16-bit offsets within each page.

**
** If this limit is changed, then the compiled library is technically
** incompatible with an SQLite library compiled with a different limit. If
** a process operating on a database with a page-size of 65536 bytes 
** crashes, then an instance of SQLite compiled with the default page-size 
** limit will not be able to rollback the aborted transaction. This could
** lead to database corruption.
*/
#ifndef SQLITE_MAX_PAGE_SIZE
# define SQLITE_MAX_PAGE_SIZE 65536
#endif


/*
** The default size of a database page.
*/
#ifndef SQLITE_DEFAULT_PAGE_SIZE
Changes to src/test2.c.
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
*/
static int pager_open(
  void *NotUsed,
  Tcl_Interp *interp,    /* The TCL interpreter that invoked this command */
  int argc,              /* Number of arguments */
  const char **argv      /* Text of each argument */
){
  u16 pageSize;
  Pager *pPager;
  int nPage;
  int rc;
  char zBuf[100];
  if( argc!=3 ){
    Tcl_AppendResult(interp, "wrong # args: should be \"", argv[0],
       " FILENAME N-PAGE\"", 0);







|







68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
*/
static int pager_open(
  void *NotUsed,
  Tcl_Interp *interp,    /* The TCL interpreter that invoked this command */
  int argc,              /* Number of arguments */
  const char **argv      /* Text of each argument */
){
  u32 pageSize;
  Pager *pPager;
  int nPage;
  int rc;
  char zBuf[100];
  if( argc!=3 ){
    Tcl_AppendResult(interp, "wrong # args: should be \"", argv[0],
       " FILENAME N-PAGE\"", 0);
Changes to src/test_vfs.c.
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
        Tcl_AppendResult(interp, "no such file: ", Tcl_GetString(objv[2]), 0);
        return TCL_ERROR;
      }
      if( objc==4 ){
        int n;
        u8 *a = Tcl_GetByteArrayFromObj(objv[3], &n);
        int pgsz = pBuffer->pgsz;
        if( pgsz==0 ) pgsz = 32768;
        for(i=0; i*pgsz<n; i++){
          int nByte = pgsz;
          tvfsAllocPage(pBuffer, i, pgsz);
          if( n-i*pgsz<pgsz ){
            nByte = n;
          }
          memcpy(pBuffer->aPage[i], &a[i*pgsz], nByte);
        }
      }

      pObj = Tcl_NewObj();
      for(i=0; pBuffer->aPage[i]; i++){
        int pgsz = pBuffer->pgsz;
        if( pgsz==0 ) pgsz = 32768;
        Tcl_AppendObjToObj(pObj, Tcl_NewByteArrayObj(pBuffer->aPage[i], pgsz));
      }
      Tcl_SetObjResult(interp, pObj);
      break;
    }

    case CMD_FILTER: {







|













|







996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
        Tcl_AppendResult(interp, "no such file: ", Tcl_GetString(objv[2]), 0);
        return TCL_ERROR;
      }
      if( objc==4 ){
        int n;
        u8 *a = Tcl_GetByteArrayFromObj(objv[3], &n);
        int pgsz = pBuffer->pgsz;
        if( pgsz==0 ) pgsz = 65536;
        for(i=0; i*pgsz<n; i++){
          int nByte = pgsz;
          tvfsAllocPage(pBuffer, i, pgsz);
          if( n-i*pgsz<pgsz ){
            nByte = n;
          }
          memcpy(pBuffer->aPage[i], &a[i*pgsz], nByte);
        }
      }

      pObj = Tcl_NewObj();
      for(i=0; pBuffer->aPage[i]; i++){
        int pgsz = pBuffer->pgsz;
        if( pgsz==0 ) pgsz = 65536;
        Tcl_AppendObjToObj(pObj, Tcl_NewByteArrayObj(pBuffer->aPage[i], pgsz));
      }
      Tcl_SetObjResult(interp, pObj);
      break;
    }

    case CMD_FILTER: {
Changes to src/wal.c.
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
struct Wal {
  sqlite3_vfs *pVfs;         /* The VFS used to create pDbFd */
  sqlite3_file *pDbFd;       /* File handle for the database file */
  sqlite3_file *pWalFd;      /* File handle for WAL file */
  u32 iCallback;             /* Value to pass to log callback (or 0) */
  int nWiData;               /* Size of array apWiData */
  volatile u32 **apWiData;   /* Pointer to wal-index content in memory */
  u16 szPage;                /* Database page size */
  i16 readLock;              /* Which read lock is being held.  -1 for none */
  u8 exclusiveMode;          /* Non-zero if connection is in exclusive mode */
  u8 writeLock;              /* True if in a write transaction */
  u8 ckptLock;               /* True if holding a checkpoint lock */
  u8 readOnly;               /* True if the WAL file is open read-only */
  WalIndexHdr hdr;           /* Wal-index header for current transaction */
  const char *zWalName;      /* Name of WAL file */







|







406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
struct Wal {
  sqlite3_vfs *pVfs;         /* The VFS used to create pDbFd */
  sqlite3_file *pDbFd;       /* File handle for the database file */
  sqlite3_file *pWalFd;      /* File handle for WAL file */
  u32 iCallback;             /* Value to pass to log callback (or 0) */
  int nWiData;               /* Size of array apWiData */
  volatile u32 **apWiData;   /* Pointer to wal-index content in memory */
  u32 szPage;                /* Database page size */
  i16 readLock;              /* Which read lock is being held.  -1 for none */
  u8 exclusiveMode;          /* Non-zero if connection is in exclusive mode */
  u8 writeLock;              /* True if in a write transaction */
  u8 ckptLock;               /* True if holding a checkpoint lock */
  u8 readOnly;               /* True if the WAL file is open read-only */
  WalIndexHdr hdr;           /* Wal-index header for current transaction */
  const char *zWalName;      /* Name of WAL file */
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
     || szPage&(szPage-1) 
     || szPage>SQLITE_MAX_PAGE_SIZE 
     || szPage<512 
    ){
      goto finished;
    }
    pWal->hdr.bigEndCksum = (u8)(magic&0x00000001);
    pWal->szPage = (u16)szPage;
    pWal->nCkpt = sqlite3Get4byte(&aBuf[12]);
    memcpy(&pWal->hdr.aSalt, &aBuf[16], 8);

    /* Verify that the WAL header checksum is correct */
    walChecksumBytes(pWal->hdr.bigEndCksum==SQLITE_BIGENDIAN, 
        aBuf, WAL_HDRSIZE-2*4, 0, pWal->hdr.aFrameCksum
    );







|







1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
     || szPage&(szPage-1) 
     || szPage>SQLITE_MAX_PAGE_SIZE 
     || szPage<512 
    ){
      goto finished;
    }
    pWal->hdr.bigEndCksum = (u8)(magic&0x00000001);
    pWal->szPage = szPage;
    pWal->nCkpt = sqlite3Get4byte(&aBuf[12]);
    memcpy(&pWal->hdr.aSalt, &aBuf[16], 8);

    /* Verify that the WAL header checksum is correct */
    walChecksumBytes(pWal->hdr.bigEndCksum==SQLITE_BIGENDIAN, 
        aBuf, WAL_HDRSIZE-2*4, 0, pWal->hdr.aFrameCksum
    );
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
      rc = walIndexAppend(pWal, ++iFrame, pgno);
      if( rc!=SQLITE_OK ) break;

      /* If nTruncate is non-zero, this is a commit record. */
      if( nTruncate ){
        pWal->hdr.mxFrame = iFrame;
        pWal->hdr.nPage = nTruncate;
        pWal->hdr.szPage = (u16)szPage;
        aFrameCksum[0] = pWal->hdr.aFrameCksum[0];
        aFrameCksum[1] = pWal->hdr.aFrameCksum[1];
      }
    }

    sqlite3_free(aFrame);
  }







|







1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
      rc = walIndexAppend(pWal, ++iFrame, pgno);
      if( rc!=SQLITE_OK ) break;

      /* If nTruncate is non-zero, this is a commit record. */
      if( nTruncate ){
        pWal->hdr.mxFrame = iFrame;
        pWal->hdr.nPage = nTruncate;
        pWal->hdr.szPage = (szPage>=0x10000) ? (szPage>>16) : szPage;
        aFrameCksum[0] = pWal->hdr.aFrameCksum[0];
        aFrameCksum[1] = pWal->hdr.aFrameCksum[1];
      }
    }

    sqlite3_free(aFrame);
  }
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527


1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
static int walCheckpoint(
  Wal *pWal,                      /* Wal connection */
  int sync_flags,                 /* Flags for OsSync() (or 0) */
  int nBuf,                       /* Size of zBuf in bytes */
  u8 *zBuf                        /* Temporary buffer to use */
){
  int rc;                         /* Return code */
  int szPage = pWal->hdr.szPage;  /* Database page-size */
  WalIterator *pIter = 0;         /* Wal iterator context */
  u32 iDbpage = 0;                /* Next database page to write */
  u32 iFrame = 0;                 /* Wal frame containing data for iDbpage */
  u32 mxSafeFrame;                /* Max frame that can be backfilled */
  u32 mxPage;                     /* Max database page to write */
  int i;                          /* Loop counter */
  volatile WalCkptInfo *pInfo;    /* The checkpoint status information */



  if( pWal->hdr.mxFrame==0 ) return SQLITE_OK;

  /* Allocate the iterator */
  rc = walIteratorInit(pWal, &pIter);
  if( rc!=SQLITE_OK ){
    return rc;
  }
  assert( pIter );

  /*** TODO:  Move this test out to the caller.  Make it an assert() here ***/
  if( pWal->hdr.szPage!=nBuf ){
    rc = SQLITE_CORRUPT_BKPT;
    goto walcheckpoint_out;
  }

  /* Compute in mxSafeFrame the index of the last frame of the WAL that is
  ** safe to write into the database.  Frames beyond mxSafeFrame might
  ** overwrite database pages that are in use by active readers and thus







|








>
>










|







1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
static int walCheckpoint(
  Wal *pWal,                      /* Wal connection */
  int sync_flags,                 /* Flags for OsSync() (or 0) */
  int nBuf,                       /* Size of zBuf in bytes */
  u8 *zBuf                        /* Temporary buffer to use */
){
  int rc;                         /* Return code */
  int szPage;                     /* Database page-size */
  WalIterator *pIter = 0;         /* Wal iterator context */
  u32 iDbpage = 0;                /* Next database page to write */
  u32 iFrame = 0;                 /* Wal frame containing data for iDbpage */
  u32 mxSafeFrame;                /* Max frame that can be backfilled */
  u32 mxPage;                     /* Max database page to write */
  int i;                          /* Loop counter */
  volatile WalCkptInfo *pInfo;    /* The checkpoint status information */

  szPage = pWal->hdr.szPage;
  if( szPage<512 ) szPage <<= 16;
  if( pWal->hdr.mxFrame==0 ) return SQLITE_OK;

  /* Allocate the iterator */
  rc = walIteratorInit(pWal, &pIter);
  if( rc!=SQLITE_OK ){
    return rc;
  }
  assert( pIter );

  /*** TODO:  Move this test out to the caller.  Make it an assert() here ***/
  if( szPage!=nBuf ){
    rc = SQLITE_CORRUPT_BKPT;
    goto walcheckpoint_out;
  }

  /* Compute in mxSafeFrame the index of the last frame of the WAL that is
  ** safe to write into the database.  Frames beyond mxSafeFrame might
  ** overwrite database pages that are in use by active readers and thus
1723
1724
1725
1726
1727
1728
1729

1730
1731
1732
1733
1734
1735
1736
    return 1;   /* Checksum does not match */
  }

  if( memcmp(&pWal->hdr, &h1, sizeof(WalIndexHdr)) ){
    *pChanged = 1;
    memcpy(&pWal->hdr, &h1, sizeof(WalIndexHdr));
    pWal->szPage = pWal->hdr.szPage;

  }

  /* The header was successfully read. Return zero. */
  return 0;
}

/*







>







1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
    return 1;   /* Checksum does not match */
  }

  if( memcmp(&pWal->hdr, &h1, sizeof(WalIndexHdr)) ){
    *pChanged = 1;
    memcpy(&pWal->hdr, &h1, sizeof(WalIndexHdr));
    pWal->szPage = pWal->hdr.szPage;
    if( pWal->szPage<512 ) pWal->szPage <<= 16;
  }

  /* The header was successfully read. Return zero. */
  return 0;
}

/*
2152
2153
2154
2155
2156
2157
2158




2159
2160
2161
2162
2163
2164
2165
2166
  }
#endif

  /* If iRead is non-zero, then it is the log frame number that contains the
  ** required page. Read and return data from the log file.
  */
  if( iRead ){




    i64 iOffset = walFrameOffset(iRead, pWal->hdr.szPage) + WAL_FRAME_HDRSIZE;
    *pInWal = 1;
    /* testcase( IS_BIG_INT(iOffset) ); // requires a 4GiB WAL */
    return sqlite3OsRead(pWal->pWalFd, pOut, nOut, iOffset);
  }

  *pInWal = 0;
  return SQLITE_OK;







>
>
>
>
|







2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
  }
#endif

  /* If iRead is non-zero, then it is the log frame number that contains the
  ** required page. Read and return data from the log file.
  */
  if( iRead ){
    int sz;
    i64 iOffset;
    sz = pWal->hdr.szPage;
    if( sz<512 ) sz <<= 16;
    iOffset = walFrameOffset(iRead, sz) + WAL_FRAME_HDRSIZE;
    *pInWal = 1;
    /* testcase( IS_BIG_INT(iOffset) ); // requires a 4GiB WAL */
    return sqlite3OsRead(pWal->pWalFd, pOut, nOut, iOffset);
  }

  *pInWal = 0;
  return SQLITE_OK;
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
    sqlite3Put4byte(&aWalHdr[12], pWal->nCkpt);
    sqlite3_randomness(8, pWal->hdr.aSalt);
    memcpy(&aWalHdr[16], pWal->hdr.aSalt, 8);
    walChecksumBytes(1, aWalHdr, WAL_HDRSIZE-2*4, 0, aCksum);
    sqlite3Put4byte(&aWalHdr[24], aCksum[0]);
    sqlite3Put4byte(&aWalHdr[28], aCksum[1]);
    
    pWal->szPage = (u16)szPage;
    pWal->hdr.bigEndCksum = SQLITE_BIGENDIAN;
    pWal->hdr.aFrameCksum[0] = aCksum[0];
    pWal->hdr.aFrameCksum[1] = aCksum[1];

    rc = sqlite3OsWrite(pWal->pWalFd, aWalHdr, sizeof(aWalHdr), 0);
    WALTRACE(("WAL%p: wal-header write %s\n", pWal, rc ? "failed" : "ok"));
    if( rc!=SQLITE_OK ){







|







2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
    sqlite3Put4byte(&aWalHdr[12], pWal->nCkpt);
    sqlite3_randomness(8, pWal->hdr.aSalt);
    memcpy(&aWalHdr[16], pWal->hdr.aSalt, 8);
    walChecksumBytes(1, aWalHdr, WAL_HDRSIZE-2*4, 0, aCksum);
    sqlite3Put4byte(&aWalHdr[24], aCksum[0]);
    sqlite3Put4byte(&aWalHdr[28], aCksum[1]);
    
    pWal->szPage = szPage;
    pWal->hdr.bigEndCksum = SQLITE_BIGENDIAN;
    pWal->hdr.aFrameCksum[0] = aCksum[0];
    pWal->hdr.aFrameCksum[1] = aCksum[1];

    rc = sqlite3OsWrite(pWal->pWalFd, aWalHdr, sizeof(aWalHdr), 0);
    WALTRACE(("WAL%p: wal-header write %s\n", pWal, rc ? "failed" : "ok"));
    if( rc!=SQLITE_OK ){
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
    iFrame++;
    nLast--;
    rc = walIndexAppend(pWal, iFrame, pLast->pgno);
  }

  if( rc==SQLITE_OK ){
    /* Update the private copy of the header. */
    pWal->hdr.szPage = (u16)szPage;
    pWal->hdr.mxFrame = iFrame;
    if( isCommit ){
      pWal->hdr.iChange++;
      pWal->hdr.nPage = nTruncate;
    }
    /* If this is a commit, update the wal-index header too. */
    if( isCommit ){







|







2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
    iFrame++;
    nLast--;
    rc = walIndexAppend(pWal, iFrame, pLast->pgno);
  }

  if( rc==SQLITE_OK ){
    /* Update the private copy of the header. */
    pWal->hdr.szPage = szPage>=0x10000 ? (szPage >> 16) : szPage;
    pWal->hdr.mxFrame = iFrame;
    if( isCommit ){
      pWal->hdr.iChange++;
      pWal->hdr.nPage = nTruncate;
    }
    /* If this is a commit, update the wal-index header too. */
    if( isCommit ){
Changes to test/pager1.test.
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
          3   20    32       {1 2 3 4}
          4   20    33       {1 2 3 4}
          5   20    65536    {1 2 3 4}
          6   20    131072   {1 2 3 4}

          7   24    511      {1 2 3 4}
          8   24    513      {1 2 3 4}
          9   24    65536    {1 2 3 4}

         10   32    65536    {1 2}
} {
  do_test pager1.4.3.$tn {
    faultsim_restore_and_reopen
    hexio_write test.db-journal $ofst [format %.8x $value]
    execsql { SELECT * FROM t1 }







|







498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
          3   20    32       {1 2 3 4}
          4   20    33       {1 2 3 4}
          5   20    65536    {1 2 3 4}
          6   20    131072   {1 2 3 4}

          7   24    511      {1 2 3 4}
          8   24    513      {1 2 3 4}
          9   24    131072   {1 2 3 4}

         10   32    65536    {1 2}
} {
  do_test pager1.4.3.$tn {
    faultsim_restore_and_reopen
    hexio_write test.db-journal $ofst [format %.8x $value]
    execsql { SELECT * FROM t1 }
Changes to test/wal.test.
1235
1236
1237
1238
1239
1240
1241
1242

1243
1244
1245
1246
1247
1248
1249
  3    512    1
  4   1024    1
  5   2048    1
  6   4096    1
  7   8192    1
  8  16384    1
  9  32768    1
 10  65536    0

 11   1016    0
} {

  if {$::SQLITE_MAX_PAGE_SIZE < $pgsz} {
    set works 0
  }








|
>







1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
  3    512    1
  4   1024    1
  5   2048    1
  6   4096    1
  7   8192    1
  8  16384    1
  9  32768    1
 10  65536    1
 11 131072    0
 11   1016    0
} {

  if {$::SQLITE_MAX_PAGE_SIZE < $pgsz} {
    set works 0
  }